summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--Documentation/block/biodoc.txt2
-rw-r--r--MAINTAINERS11
-rw-r--r--arch/s390/include/asm/eadm.h6
-rw-r--r--arch/s390/include/asm/sysinfo.h4
-rw-r--r--arch/s390/kernel/sysinfo.c2
-rw-r--r--arch/um/drivers/ubd_kern.c2
-rw-r--r--block/badblocks.c1
-rw-r--r--block/bfq-iosched.c59
-rw-r--r--block/bio-integrity.c8
-rw-r--r--block/bio.c85
-rw-r--r--block/blk-core.c331
-rw-r--r--block/blk-exec.c4
-rw-r--r--block/blk-flush.c16
-rw-r--r--block/blk-integrity.c4
-rw-r--r--block/blk-map.c7
-rw-r--r--block/blk-merge.c48
-rw-r--r--block/blk-mq-cpumap.c68
-rw-r--r--block/blk-mq-debugfs.c101
-rw-r--r--block/blk-mq-sched.c158
-rw-r--r--block/blk-mq-sched.h28
-rw-r--r--block/blk-mq.c399
-rw-r--r--block/blk-mq.h11
-rw-r--r--block/blk-settings.c5
-rw-r--r--block/blk-tag.c15
-rw-r--r--block/blk-timeout.c4
-rw-r--r--block/blk.h15
-rw-r--r--block/bounce.c47
-rw-r--r--block/bsg-lib.c5
-rw-r--r--block/bsg.c13
-rw-r--r--block/cfq-iosched.c9
-rw-r--r--block/elevator.c1
-rw-r--r--block/genhd.c4
-rw-r--r--block/ioprio.c3
-rw-r--r--block/kyber-iosched.c31
-rw-r--r--block/partitions/ldm.c10
-rw-r--r--block/partitions/ldm.h6
-rw-r--r--block/scsi_ioctl.c13
-rw-r--r--block/t10-pi.c32
-rw-r--r--drivers/acpi/acpi_extlog.c20
-rw-r--r--drivers/acpi/apei/ghes.c8
-rw-r--r--drivers/acpi/bus.c29
-rw-r--r--drivers/acpi/nfit/core.c54
-rw-r--r--drivers/acpi/nfit/nfit.h3
-rw-r--r--drivers/acpi/utils.c16
-rw-r--r--drivers/block/DAC960.c2
-rw-r--r--drivers/block/amiflop.c10
-rw-r--r--drivers/block/aoe/aoeblk.c1
-rw-r--r--drivers/block/aoe/aoecmd.c12
-rw-r--r--drivers/block/aoe/aoedev.c2
-rw-r--r--drivers/block/ataflop.c16
-rw-r--r--drivers/block/brd.c1
-rw-r--r--drivers/block/cciss.c4
-rw-r--r--drivers/block/drbd/drbd_actlog.c2
-rw-r--r--drivers/block/drbd/drbd_bitmap.c6
-rw-r--r--drivers/block/drbd/drbd_int.h5
-rw-r--r--drivers/block/drbd/drbd_main.c14
-rw-r--r--drivers/block/drbd/drbd_nl.c2
-rw-r--r--drivers/block/drbd/drbd_receiver.c6
-rw-r--r--drivers/block/drbd/drbd_req.c8
-rw-r--r--drivers/block/drbd/drbd_req.h2
-rw-r--r--drivers/block/drbd/drbd_worker.c16
-rw-r--r--drivers/block/floppy.c9
-rw-r--r--drivers/block/loop.c64
-rw-r--r--drivers/block/loop.h1
-rw-r--r--drivers/block/mtip32xx/mtip32xx.c54
-rw-r--r--drivers/block/mtip32xx/mtip32xx.h2
-rw-r--r--drivers/block/nbd.c44
-rw-r--r--drivers/block/null_blk.c125
-rw-r--r--drivers/block/paride/pcd.c9
-rw-r--r--drivers/block/paride/pd.c3
-rw-r--r--drivers/block/paride/pf.c19
-rw-r--r--drivers/block/pktcdvd.c40
-rw-r--r--drivers/block/ps3disk.c11
-rw-r--r--drivers/block/ps3vram.c16
-rw-r--r--drivers/block/rbd.c28
-rw-r--r--drivers/block/rsxx/dev.c17
-rw-r--r--drivers/block/rsxx/dma.c13
-rw-r--r--drivers/block/rsxx/rsxx_priv.h2
-rw-r--r--drivers/block/skd_main.c32
-rw-r--r--drivers/block/sunvdc.c4
-rw-r--r--drivers/block/swim.c8
-rw-r--r--drivers/block/swim3.c29
-rw-r--r--drivers/block/sx8.c20
-rw-r--r--drivers/block/umem.c4
-rw-r--r--drivers/block/virtio_blk.c23
-rw-r--r--drivers/block/xen-blkback/blkback.c19
-rw-r--r--drivers/block/xen-blkfront.c81
-rw-r--r--drivers/block/xsysace.c9
-rw-r--r--drivers/block/z2ram.c4
-rw-r--r--drivers/cdrom/cdrom.c7
-rw-r--r--drivers/cdrom/gdrom.c10
-rw-r--r--drivers/char/tpm/tpm_crb.c9
-rw-r--r--drivers/char/tpm/tpm_ppi.c20
-rw-r--r--drivers/gpu/drm/i915/intel_acpi.c14
-rw-r--r--drivers/gpu/drm/nouveau/nouveau_acpi.c20
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/mxm/base.c9
-rw-r--r--drivers/hid/i2c-hid/i2c-hid.c9
-rw-r--r--drivers/ide/ide-atapi.c12
-rw-r--r--drivers/ide/ide-cd.c11
-rw-r--r--drivers/ide/ide-cd_ioctl.c1
-rw-r--r--drivers/ide/ide-devsets.c1
-rw-r--r--drivers/ide/ide-disk.c1
-rw-r--r--drivers/ide/ide-dma.c2
-rw-r--r--drivers/ide/ide-eh.c16
-rw-r--r--drivers/ide/ide-floppy.c6
-rw-r--r--drivers/ide/ide-io.c10
-rw-r--r--drivers/ide/ide-ioctls.c2
-rw-r--r--drivers/ide/ide-park.c2
-rw-r--r--drivers/ide/ide-pm.c8
-rw-r--r--drivers/ide/ide-probe.c7
-rw-r--r--drivers/ide/ide-tape.c3
-rw-r--r--drivers/ide/ide-taskfile.c7
-rw-r--r--drivers/ide/siimage.c6
-rw-r--r--drivers/iommu/dmar.c11
-rw-r--r--drivers/lightnvm/core.c13
-rw-r--r--drivers/lightnvm/pblk-cache.c8
-rw-r--r--drivers/lightnvm/pblk-core.c606
-rw-r--r--drivers/lightnvm/pblk-gc.c468
-rw-r--r--drivers/lightnvm/pblk-init.c376
-rw-r--r--drivers/lightnvm/pblk-map.c75
-rw-r--r--drivers/lightnvm/pblk-rb.c79
-rw-r--r--drivers/lightnvm/pblk-read.c86
-rw-r--r--drivers/lightnvm/pblk-recovery.c130
-rw-r--r--drivers/lightnvm/pblk-rl.c90
-rw-r--r--drivers/lightnvm/pblk-sysfs.c94
-rw-r--r--drivers/lightnvm/pblk-write.c352
-rw-r--r--drivers/lightnvm/pblk.h276
-rw-r--r--drivers/lightnvm/rrpc.c10
-rw-r--r--drivers/md/bcache/bcache.h7
-rw-r--r--drivers/md/bcache/btree.c6
-rw-r--r--drivers/md/bcache/debug.c2
-rw-r--r--drivers/md/bcache/io.c6
-rw-r--r--drivers/md/bcache/journal.c2
-rw-r--r--drivers/md/bcache/movinggc.c10
-rw-r--r--drivers/md/bcache/request.c28
-rw-r--r--drivers/md/bcache/request.h2
-rw-r--r--drivers/md/bcache/super.c14
-rw-r--r--drivers/md/bcache/writeback.c4
-rw-r--r--drivers/md/dm-bio-prison-v1.c4
-rw-r--r--drivers/md/dm-bio-prison-v1.h2
-rw-r--r--drivers/md/dm-bufio.c28
-rw-r--r--drivers/md/dm-cache-target.c36
-rw-r--r--drivers/md/dm-crypt.c41
-rw-r--r--drivers/md/dm-flakey.c13
-rw-r--r--drivers/md/dm-integrity.c30
-rw-r--r--drivers/md/dm-io.c13
-rw-r--r--drivers/md/dm-log-writes.c13
-rw-r--r--drivers/md/dm-mpath.c85
-rw-r--r--drivers/md/dm-raid1.c29
-rw-r--r--drivers/md/dm-rq.c30
-rw-r--r--drivers/md/dm-rq.h2
-rw-r--r--drivers/md/dm-snap.c15
-rw-r--r--drivers/md/dm-stripe.c17
-rw-r--r--drivers/md/dm-target.c2
-rw-r--r--drivers/md/dm-thin.c67
-rw-r--r--drivers/md/dm-verity-target.c16
-rw-r--r--drivers/md/dm-zero.c4
-rw-r--r--drivers/md/dm.c88
-rw-r--r--drivers/md/md.c22
-rw-r--r--drivers/md/multipath.c10
-rw-r--r--drivers/md/raid1.c38
-rw-r--r--drivers/md/raid10.c38
-rw-r--r--drivers/md/raid5-cache.c6
-rw-r--r--drivers/md/raid5-ppl.c4
-rw-r--r--drivers/md/raid5.c24
-rw-r--r--drivers/memstick/core/ms_block.c7
-rw-r--r--drivers/memstick/core/mspro_block.c8
-rw-r--r--drivers/mmc/core/block.c37
-rw-r--r--drivers/mmc/core/queue.c3
-rw-r--r--drivers/mmc/host/sdhci-pci-core.c9
-rw-r--r--drivers/mtd/mtd_blkdevs.c31
-rw-r--r--drivers/mtd/ubi/block.c8
-rw-r--r--drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c15
-rw-r--r--drivers/nvdimm/blk.c5
-rw-r--r--drivers/nvdimm/btt.c5
-rw-r--r--drivers/nvdimm/btt_devs.c9
-rw-r--r--drivers/nvdimm/pmem.c29
-rw-r--r--drivers/nvme/host/Kconfig12
-rw-r--r--drivers/nvme/host/Makefile1
-rw-r--r--drivers/nvme/host/core.c525
-rw-r--r--drivers/nvme/host/fabrics.c73
-rw-r--r--drivers/nvme/host/fabrics.h6
-rw-r--r--drivers/nvme/host/fc.c140
-rw-r--r--drivers/nvme/host/lightnvm.c18
-rw-r--r--drivers/nvme/host/nvme.h42
-rw-r--r--drivers/nvme/host/pci.c647
-rw-r--r--drivers/nvme/host/rdma.c212
-rw-r--r--drivers/nvme/host/scsi.c2460
-rw-r--r--drivers/nvme/target/admin-cmd.c65
-rw-r--r--drivers/nvme/target/configfs.c68
-rw-r--r--drivers/nvme/target/core.c3
-rw-r--r--drivers/nvme/target/discovery.c4
-rw-r--r--drivers/nvme/target/fc.c10
-rw-r--r--drivers/nvme/target/fcloop.c2
-rw-r--r--drivers/nvme/target/io-cmd.c4
-rw-r--r--drivers/nvme/target/loop.c67
-rw-r--r--drivers/nvme/target/nvmet.h2
-rw-r--r--drivers/nvme/target/rdma.c102
-rw-r--r--drivers/pci/pci-acpi.c13
-rw-r--r--drivers/pci/pci-label.c4
-rw-r--r--drivers/s390/block/dasd.c36
-rw-r--r--drivers/s390/block/dcssblk.c2
-rw-r--r--drivers/s390/block/scm_blk.c8
-rw-r--r--drivers/s390/block/scm_blk.h4
-rw-r--r--drivers/s390/block/xpram.c2
-rw-r--r--drivers/s390/cio/eadm_sch.c6
-rw-r--r--drivers/s390/cio/scm.c2
-rw-r--r--drivers/sbus/char/jsflash.c5
-rw-r--r--drivers/scsi/osd/osd_initiator.c29
-rw-r--r--drivers/scsi/osst.c3
-rw-r--r--drivers/scsi/scsi_debug.c10
-rw-r--r--drivers/scsi/scsi_error.c3
-rw-r--r--drivers/scsi/scsi_lib.c104
-rw-r--r--drivers/scsi/scsi_transport_sas.c10
-rw-r--r--drivers/scsi/sg.c8
-rw-r--r--drivers/scsi/st.c3
-rw-r--r--drivers/target/target_core_iblock.c12
-rw-r--r--drivers/target/target_core_pscsi.c6
-rw-r--r--drivers/thermal/int340x_thermal/int3400_thermal.c8
-rw-r--r--drivers/usb/dwc3/dwc3-pci.c10
-rw-r--r--drivers/usb/host/xhci-pci.c9
-rw-r--r--drivers/usb/misc/ucsi.c6
-rw-r--r--drivers/usb/typec/typec_wcove.c8
-rw-r--r--drivers/xen/tmem.c6
-rw-r--r--fs/afs/cmservice.c16
-rw-r--r--fs/afs/internal.h11
-rw-r--r--fs/afs/main.c2
-rw-r--r--fs/aio.c15
-rw-r--r--fs/block_dev.c25
-rw-r--r--fs/btrfs/btrfs_inode.h3
-rw-r--r--fs/btrfs/check-integrity.c4
-rw-r--r--fs/btrfs/compression.c46
-rw-r--r--fs/btrfs/compression.h4
-rw-r--r--fs/btrfs/ctree.h6
-rw-r--r--fs/btrfs/disk-io.c75
-rw-r--r--fs/btrfs/disk-io.h12
-rw-r--r--fs/btrfs/extent_io.c27
-rw-r--r--fs/btrfs/extent_io.h6
-rw-r--r--fs/btrfs/file-item.c14
-rw-r--r--fs/btrfs/file.c33
-rw-r--r--fs/btrfs/inode.c82
-rw-r--r--fs/btrfs/raid56.c16
-rw-r--r--fs/btrfs/scrub.c26
-rw-r--r--fs/btrfs/volumes.c11
-rw-r--r--fs/buffer.c15
-rw-r--r--fs/crypto/bio.c2
-rw-r--r--fs/direct-io.c25
-rw-r--r--fs/ext4/file.c35
-rw-r--r--fs/ext4/page-io.c15
-rw-r--r--fs/ext4/readpage.c4
-rw-r--r--fs/ext4/super.c2
-rw-r--r--fs/f2fs/data.c10
-rw-r--r--fs/f2fs/segment.c2
-rw-r--r--fs/f2fs/super.c2
-rw-r--r--fs/fcntl.c67
-rw-r--r--fs/gfs2/incore.h1
-rw-r--r--fs/gfs2/lops.c10
-rw-r--r--fs/gfs2/meta_io.c2
-rw-r--r--fs/gfs2/ops_fstype.c6
-rw-r--r--fs/gfs2/sys.c22
-rw-r--r--fs/inode.c1
-rw-r--r--fs/iomap.c13
-rw-r--r--fs/jfs/jfs_logmgr.c2
-rw-r--r--fs/jfs/jfs_metapage.c4
-rw-r--r--fs/mpage.c4
-rw-r--r--fs/nfs/blocklayout/blocklayout.c4
-rw-r--r--fs/nfsd/blocklayout.c4
-rw-r--r--fs/nfsd/export.c4
-rw-r--r--fs/nilfs2/segbuf.c2
-rw-r--r--fs/ocfs2/cluster/heartbeat.c6
-rw-r--r--fs/ocfs2/super.c2
-rw-r--r--fs/open.c1
-rw-r--r--fs/overlayfs/copy_up.c7
-rw-r--r--fs/overlayfs/namei.c2
-rw-r--r--fs/overlayfs/overlayfs.h2
-rw-r--r--fs/read_write.c12
-rw-r--r--fs/xfs/Makefile3
-rw-r--r--fs/xfs/uuid.c63
-rw-r--r--fs/xfs/uuid.h35
-rw-r--r--fs/xfs/xfs_aops.c9
-rw-r--r--fs/xfs/xfs_buf.c7
-rw-r--r--fs/xfs/xfs_file.c32
-rw-r--r--fs/xfs/xfs_inode_item.c8
-rw-r--r--fs/xfs/xfs_iomap.c22
-rw-r--r--fs/xfs/xfs_linux.h2
-rw-r--r--fs/xfs/xfs_log_recover.c6
-rw-r--r--fs/xfs/xfs_mount.c16
-rw-r--r--fs/xfs/xfs_super.c3
-rw-r--r--include/acpi/acpi_bus.h11
-rw-r--r--include/linux/acpi.h4
-rw-r--r--include/linux/bio.h21
-rw-r--r--include/linux/blk-mq.h28
-rw-r--r--include/linux/blk_types.h26
-rw-r--r--include/linux/blkdev.h72
-rw-r--r--include/linux/cleancache.h2
-rw-r--r--include/linux/device-mapper.h4
-rw-r--r--include/linux/elevator.h7
-rw-r--r--include/linux/fs.h79
-rw-r--r--include/linux/genhd.h11
-rw-r--r--include/linux/ide.h6
-rw-r--r--include/linux/iomap.h1
-rw-r--r--include/linux/nvme-fc.h3
-rw-r--r--include/linux/nvme.h105
-rw-r--r--include/linux/pci-acpi.h2
-rw-r--r--include/linux/scatterlist.h2
-rw-r--r--include/linux/uuid.h99
-rw-r--r--include/scsi/osd_initiator.h2
-rw-r--r--include/scsi/scsi_cmnd.h1
-rw-r--r--include/scsi/scsi_request.h2
-rw-r--r--include/uapi/linux/aio_abi.h2
-rw-r--r--include/uapi/linux/dm-ioctl.h4
-rw-r--r--include/uapi/linux/fcntl.h21
-rw-r--r--include/uapi/linux/fs.h4
-rw-r--r--include/uapi/linux/loop.h3
-rw-r--r--include/uapi/linux/nbd.h4
-rw-r--r--include/uapi/linux/uuid.h28
-rw-r--r--kernel/power/swap.c14
-rw-r--r--kernel/sysctl_binary.c4
-rw-r--r--kernel/trace/blktrace.c4
-rw-r--r--lib/scatterlist.c35
-rw-r--r--lib/test_uuid.c36
-rw-r--r--lib/uuid.c33
-rw-r--r--lib/vsprintf.c4
-rw-r--r--mm/cleancache.c2
-rw-r--r--mm/filemap.c64
-rw-r--r--mm/page_io.c4
-rw-r--r--mm/shmem.c2
-rw-r--r--security/integrity/evm/evm_crypto.c2
-rw-r--r--security/integrity/ima/ima_policy.c12
-rw-r--r--sound/soc/intel/skylake/skl-nhlt.c7
-rw-r--r--tools/testing/nvdimm/test/iomap.c6
-rw-r--r--tools/testing/nvdimm/test/nfit.c2
-rw-r--r--tools/testing/nvdimm/test/nfit_test.h4
333 files changed, 6128 insertions, 6659 deletions
diff --git a/Documentation/block/biodoc.txt b/Documentation/block/biodoc.txt
index 01ddeaf64b0f..9490f2845f06 100644
--- a/Documentation/block/biodoc.txt
+++ b/Documentation/block/biodoc.txt
@@ -632,7 +632,7 @@ to i/o submission, if the bio fields are likely to be accessed after the
i/o is issued (since the bio may otherwise get freed in case i/o completion
happens in the meantime).
-The bio_clone() routine may be used to duplicate a bio, where the clone
+The bio_clone_fast() routine may be used to duplicate a bio, where the clone
shares the bio_vec_list with the original bio (i.e. both point to the
same bio_vec_list). This would typically be used for splitting i/o requests
in lvm or md.
diff --git a/MAINTAINERS b/MAINTAINERS
index 767e9d202adf..503f80a43bec 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -13462,6 +13462,17 @@ W: http://en.wikipedia.org/wiki/Util-linux
T: git git://git.kernel.org/pub/scm/utils/util-linux/util-linux.git
S: Maintained
+UUID HELPERS
+M: Christoph Hellwig <hch@lst.de>
+R: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
+L: linux-kernel@vger.kernel.org
+T: git git://git.infradead.org/users/hch/uuid.git
+F: lib/uuid.c
+F: lib/test_uuid.c
+F: include/linux/uuid.h
+F: include/uapi/linux/uuid.h
+S: Maintained
+
UVESAFB DRIVER
M: Michal Januszewski <spock@gentoo.org>
L: linux-fbdev@vger.kernel.org
diff --git a/arch/s390/include/asm/eadm.h b/arch/s390/include/asm/eadm.h
index 67026300c88e..144809a3f4f6 100644
--- a/arch/s390/include/asm/eadm.h
+++ b/arch/s390/include/asm/eadm.h
@@ -3,6 +3,7 @@
#include <linux/types.h>
#include <linux/device.h>
+#include <linux/blkdev.h>
struct arqb {
u64 data;
@@ -105,13 +106,14 @@ struct scm_driver {
int (*probe) (struct scm_device *scmdev);
int (*remove) (struct scm_device *scmdev);
void (*notify) (struct scm_device *scmdev, enum scm_event event);
- void (*handler) (struct scm_device *scmdev, void *data, int error);
+ void (*handler) (struct scm_device *scmdev, void *data,
+ blk_status_t error);
};
int scm_driver_register(struct scm_driver *scmdrv);
void scm_driver_unregister(struct scm_driver *scmdrv);
int eadm_start_aob(struct aob *aob);
-void scm_irq_handler(struct aob *aob, int error);
+void scm_irq_handler(struct aob *aob, blk_status_t error);
#endif /* _ASM_S390_EADM_H */
diff --git a/arch/s390/include/asm/sysinfo.h b/arch/s390/include/asm/sysinfo.h
index e784bed6ed7f..2b498e58b914 100644
--- a/arch/s390/include/asm/sysinfo.h
+++ b/arch/s390/include/asm/sysinfo.h
@@ -109,7 +109,7 @@ struct sysinfo_2_2_2 {
unsigned short cpus_shared;
char reserved_4[3];
unsigned char vsne;
- uuid_be uuid;
+ uuid_t uuid;
char reserved_5[160];
char ext_name[256];
};
@@ -134,7 +134,7 @@ struct sysinfo_3_2_2 {
char reserved_1[3];
unsigned char evmne;
unsigned int reserved_2;
- uuid_be uuid;
+ uuid_t uuid;
} vm[8];
char reserved_3[1504];
char ext_names[8][256];
diff --git a/arch/s390/kernel/sysinfo.c b/arch/s390/kernel/sysinfo.c
index eefcb54872a5..fb869b103825 100644
--- a/arch/s390/kernel/sysinfo.c
+++ b/arch/s390/kernel/sysinfo.c
@@ -242,7 +242,7 @@ static void print_ext_name(struct seq_file *m, int lvl,
static void print_uuid(struct seq_file *m, int i, struct sysinfo_3_2_2 *info)
{
- if (!memcmp(&info->vm[i].uuid, &NULL_UUID_BE, sizeof(uuid_be)))
+ if (uuid_is_null(&info->vm[i].uuid))
return;
seq_printf(m, "VM%02d UUID: %pUb\n", i, &info->vm[i].uuid);
}
diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c
index 85410279beab..b55fe9bf5d3e 100644
--- a/arch/um/drivers/ubd_kern.c
+++ b/arch/um/drivers/ubd_kern.c
@@ -534,7 +534,7 @@ static void ubd_handler(void)
for (count = 0; count < n/sizeof(struct io_thread_req *); count++) {
blk_end_request(
(*irq_req_buffer)[count]->req,
- 0,
+ BLK_STS_OK,
(*irq_req_buffer)[count]->length
);
kfree((*irq_req_buffer)[count]);
diff --git a/block/badblocks.c b/block/badblocks.c
index 6ebcef282314..43c71166e1e2 100644
--- a/block/badblocks.c
+++ b/block/badblocks.c
@@ -533,6 +533,7 @@ ssize_t badblocks_store(struct badblocks *bb, const char *page, size_t len,
case 3:
if (newline != '\n')
return -EINVAL;
+ /* fall through */
case 2:
if (length <= 0)
return -EINVAL;
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index ed93da2462ab..12bbc6b8657d 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -725,8 +725,12 @@ static void bfq_updated_next_req(struct bfq_data *bfqd,
}
static void
-bfq_bfqq_resume_state(struct bfq_queue *bfqq, struct bfq_io_cq *bic)
+bfq_bfqq_resume_state(struct bfq_queue *bfqq, struct bfq_data *bfqd,
+ struct bfq_io_cq *bic, bool bfq_already_existing)
{
+ unsigned int old_wr_coeff = bfqq->wr_coeff;
+ bool busy = bfq_already_existing && bfq_bfqq_busy(bfqq);
+
if (bic->saved_idle_window)
bfq_mark_bfqq_idle_window(bfqq);
else
@@ -754,6 +758,14 @@ bfq_bfqq_resume_state(struct bfq_queue *bfqq, struct bfq_io_cq *bic)
/* make sure weight will be updated, however we got here */
bfqq->entity.prio_changed = 1;
+
+ if (likely(!busy))
+ return;
+
+ if (old_wr_coeff == 1 && bfqq->wr_coeff > 1)
+ bfqd->wr_busy_queues++;
+ else if (old_wr_coeff > 1 && bfqq->wr_coeff == 1)
+ bfqd->wr_busy_queues--;
}
static int bfqq_process_refs(struct bfq_queue *bfqq)
@@ -4290,10 +4302,16 @@ static void bfq_put_rq_priv_body(struct bfq_queue *bfqq)
bfq_put_queue(bfqq);
}
-static void bfq_put_rq_private(struct request_queue *q, struct request *rq)
+static void bfq_finish_request(struct request *rq)
{
- struct bfq_queue *bfqq = RQ_BFQQ(rq);
- struct bfq_data *bfqd = bfqq->bfqd;
+ struct bfq_queue *bfqq;
+ struct bfq_data *bfqd;
+
+ if (!rq->elv.icq)
+ return;
+
+ bfqq = RQ_BFQQ(rq);
+ bfqd = bfqq->bfqd;
if (rq->rq_flags & RQF_STARTED)
bfqg_stats_update_completion(bfqq_group(bfqq),
@@ -4324,7 +4342,7 @@ static void bfq_put_rq_private(struct request_queue *q, struct request *rq)
*/
if (!RB_EMPTY_NODE(&rq->rb_node))
- bfq_remove_request(q, rq);
+ bfq_remove_request(rq->q, rq);
bfq_put_rq_priv_body(bfqq);
}
@@ -4394,20 +4412,21 @@ static struct bfq_queue *bfq_get_bfqq_handle_split(struct bfq_data *bfqd,
/*
* Allocate bfq data structures associated with this request.
*/
-static int bfq_get_rq_private(struct request_queue *q, struct request *rq,
- struct bio *bio)
+static void bfq_prepare_request(struct request *rq, struct bio *bio)
{
+ struct request_queue *q = rq->q;
struct bfq_data *bfqd = q->elevator->elevator_data;
- struct bfq_io_cq *bic = icq_to_bic(rq->elv.icq);
+ struct bfq_io_cq *bic;
const int is_sync = rq_is_sync(rq);
struct bfq_queue *bfqq;
bool new_queue = false;
- bool split = false;
+ bool bfqq_already_existing = false, split = false;
- spin_lock_irq(&bfqd->lock);
+ if (!rq->elv.icq)
+ return;
+ bic = icq_to_bic(rq->elv.icq);
- if (!bic)
- goto queue_fail;
+ spin_lock_irq(&bfqd->lock);
bfq_check_ioprio_change(bic, bio);
@@ -4432,6 +4451,8 @@ static int bfq_get_rq_private(struct request_queue *q, struct request *rq,
bfqq = bfq_get_bfqq_handle_split(bfqd, bic, bio,
true, is_sync,
NULL);
+ else
+ bfqq_already_existing = true;
}
}
@@ -4457,7 +4478,8 @@ static int bfq_get_rq_private(struct request_queue *q, struct request *rq,
* queue: restore the idle window and the
* possible weight raising period.
*/
- bfq_bfqq_resume_state(bfqq, bic);
+ bfq_bfqq_resume_state(bfqq, bfqd, bic,
+ bfqq_already_existing);
}
}
@@ -4465,13 +4487,6 @@ static int bfq_get_rq_private(struct request_queue *q, struct request *rq,
bfq_handle_burst(bfqd, bfqq);
spin_unlock_irq(&bfqd->lock);
-
- return 0;
-
-queue_fail:
- spin_unlock_irq(&bfqd->lock);
-
- return 1;
}
static void bfq_idle_slice_timer_body(struct bfq_queue *bfqq)
@@ -4950,8 +4965,8 @@ static struct elv_fs_entry bfq_attrs[] = {
static struct elevator_type iosched_bfq_mq = {
.ops.mq = {
- .get_rq_priv = bfq_get_rq_private,
- .put_rq_priv = bfq_put_rq_private,
+ .prepare_request = bfq_prepare_request,
+ .finish_request = bfq_finish_request,
.exit_icq = bfq_exit_icq,
.insert_requests = bfq_insert_requests,
.dispatch_request = bfq_dispatch_request,
diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index b5009a896a7f..b8a3a65f7364 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -224,7 +224,7 @@ static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi,
* @bio: bio to generate/verify integrity metadata for
* @proc_fn: Pointer to the relevant processing function
*/
-static int bio_integrity_process(struct bio *bio,
+static blk_status_t bio_integrity_process(struct bio *bio,
integrity_processing_fn *proc_fn)
{
struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev);
@@ -232,7 +232,7 @@ static int bio_integrity_process(struct bio *bio,
struct bvec_iter bviter;
struct bio_vec bv;
struct bio_integrity_payload *bip = bio_integrity(bio);
- unsigned int ret = 0;
+ blk_status_t ret = BLK_STS_OK;
void *prot_buf = page_address(bip->bip_vec->bv_page) +
bip->bip_vec->bv_offset;
@@ -369,7 +369,7 @@ static void bio_integrity_verify_fn(struct work_struct *work)
struct bio *bio = bip->bip_bio;
struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev);
- bio->bi_error = bio_integrity_process(bio, bi->profile->verify_fn);
+ bio->bi_status = bio_integrity_process(bio, bi->profile->verify_fn);
/* Restore original bio completion handler */
bio->bi_end_io = bip->bip_end_io;
@@ -398,7 +398,7 @@ void bio_integrity_endio(struct bio *bio)
* integrity metadata. Restore original bio end_io handler
* and run it.
*/
- if (bio->bi_error) {
+ if (bio->bi_status) {
bio->bi_end_io = bip->bip_end_io;
bio_endio(bio);
diff --git a/block/bio.c b/block/bio.c
index 26b0810fb8ea..1cfcd0df3f30 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -315,8 +315,8 @@ static struct bio *__bio_chain_endio(struct bio *bio)
{
struct bio *parent = bio->bi_private;
- if (!parent->bi_error)
- parent->bi_error = bio->bi_error;
+ if (!parent->bi_status)
+ parent->bi_status = bio->bi_status;
bio_put(bio);
return parent;
}
@@ -369,6 +369,8 @@ static void punt_bios_to_rescuer(struct bio_set *bs)
struct bio_list punt, nopunt;
struct bio *bio;
+ if (WARN_ON_ONCE(!bs->rescue_workqueue))
+ return;
/*
* In order to guarantee forward progress we must punt only bios that
* were allocated from this bio_set; otherwise, if there was a bio on
@@ -480,7 +482,8 @@ struct bio *bio_alloc_bioset(gfp_t gfp_mask, unsigned int nr_iovecs,
if (current->bio_list &&
(!bio_list_empty(&current->bio_list[0]) ||
- !bio_list_empty(&current->bio_list[1])))
+ !bio_list_empty(&current->bio_list[1])) &&
+ bs->rescue_workqueue)
gfp_mask &= ~__GFP_DIRECT_RECLAIM;
p = mempool_alloc(bs->bio_pool, gfp_mask);
@@ -550,7 +553,7 @@ EXPORT_SYMBOL(zero_fill_bio);
*
* Description:
* Put a reference to a &struct bio, either one you have gotten with
- * bio_alloc, bio_get or bio_clone. The last put of a bio will free it.
+ * bio_alloc, bio_get or bio_clone_*. The last put of a bio will free it.
**/
void bio_put(struct bio *bio)
{
@@ -599,6 +602,7 @@ void __bio_clone_fast(struct bio *bio, struct bio *bio_src)
bio->bi_bdev = bio_src->bi_bdev;
bio_set_flag(bio, BIO_CLONED);
bio->bi_opf = bio_src->bi_opf;
+ bio->bi_write_hint = bio_src->bi_write_hint;
bio->bi_iter = bio_src->bi_iter;
bio->bi_io_vec = bio_src->bi_io_vec;
@@ -682,6 +686,7 @@ struct bio *bio_clone_bioset(struct bio *bio_src, gfp_t gfp_mask,
return NULL;
bio->bi_bdev = bio_src->bi_bdev;
bio->bi_opf = bio_src->bi_opf;
+ bio->bi_write_hint = bio_src->bi_write_hint;
bio->bi_iter.bi_sector = bio_src->bi_iter.bi_sector;
bio->bi_iter.bi_size = bio_src->bi_iter.bi_size;
@@ -924,7 +929,7 @@ static void submit_bio_wait_endio(struct bio *bio)
{
struct submit_bio_ret *ret = bio->bi_private;
- ret->error = bio->bi_error;
+ ret->error = blk_status_to_errno(bio->bi_status);
complete(&ret->event);
}
@@ -1823,8 +1828,8 @@ again:
}
if (bio->bi_bdev && bio_flagged(bio, BIO_TRACE_COMPLETION)) {
- trace_block_bio_complete(bdev_get_queue(bio->bi_bdev),
- bio, bio->bi_error);
+ trace_block_bio_complete(bdev_get_queue(bio->bi_bdev), bio,
+ blk_status_to_errno(bio->bi_status));
bio_clear_flag(bio, BIO_TRACE_COMPLETION);
}
@@ -1927,9 +1932,29 @@ void bioset_free(struct bio_set *bs)
}
EXPORT_SYMBOL(bioset_free);
-static struct bio_set *__bioset_create(unsigned int pool_size,
- unsigned int front_pad,
- bool create_bvec_pool)
+/**
+ * bioset_create - Create a bio_set
+ * @pool_size: Number of bio and bio_vecs to cache in the mempool
+ * @front_pad: Number of bytes to allocate in front of the returned bio
+ * @flags: Flags to modify behavior, currently %BIOSET_NEED_BVECS
+ * and %BIOSET_NEED_RESCUER
+ *
+ * Description:
+ * Set up a bio_set to be used with @bio_alloc_bioset. Allows the caller
+ * to ask for a number of bytes to be allocated in front of the bio.
+ * Front pad allocation is useful for embedding the bio inside
+ * another structure, to avoid allocating extra data to go with the bio.
+ * Note that the bio must be embedded at the END of that structure always,
+ * or things will break badly.
+ * If %BIOSET_NEED_BVECS is set in @flags, a separate pool will be allocated
+ * for allocating iovecs. This pool is not needed e.g. for bio_clone_fast().
+ * If %BIOSET_NEED_RESCUER is set, a workqueue is created which can be used to
+ * dispatch queued requests when the mempool runs out of space.
+ *
+ */
+struct bio_set *bioset_create(unsigned int pool_size,
+ unsigned int front_pad,
+ int flags)
{
unsigned int back_pad = BIO_INLINE_VECS * sizeof(struct bio_vec);
struct bio_set *bs;
@@ -1954,12 +1979,15 @@ static struct bio_set *__bioset_create(unsigned int pool_size,
if (!bs->bio_pool)
goto bad;
- if (create_bvec_pool) {
+ if (flags & BIOSET_NEED_BVECS) {
bs->bvec_pool = biovec_create_pool(pool_size);
if (!bs->bvec_pool)
goto bad;
}
+ if (!(flags & BIOSET_NEED_RESCUER))
+ return bs;
+
bs->rescue_workqueue = alloc_workqueue("bioset", WQ_MEM_RECLAIM, 0);
if (!bs->rescue_workqueue)
goto bad;
@@ -1969,41 +1997,8 @@ bad:
bioset_free(bs);
return NULL;
}
-
-/**
- * bioset_create - Create a bio_set
- * @pool_size: Number of bio and bio_vecs to cache in the mempool
- * @front_pad: Number of bytes to allocate in front of the returned bio
- *
- * Description:
- * Set up a bio_set to be used with @bio_alloc_bioset. Allows the caller
- * to ask for a number of bytes to be allocated in front of the bio.
- * Front pad allocation is useful for embedding the bio inside
- * another structure, to avoid allocating extra data to go with the bio.
- * Note that the bio must be embedded at the END of that structure always,
- * or things will break badly.
- */
-struct bio_set *bioset_create(unsigned int pool_size, unsigned int front_pad)
-{
- return __bioset_create(pool_size, front_pad, true);
-}
EXPORT_SYMBOL(bioset_create);
-/**
- * bioset_create_nobvec - Create a bio_set without bio_vec mempool
- * @pool_size: Number of bio to cache in the mempool
- * @front_pad: Number of bytes to allocate in front of the returned bio
- *
- * Description:
- * Same functionality as bioset_create() except that mempool is not
- * created for bio_vecs. Saving some memory for bio_clone_fast() users.
- */
-struct bio_set *bioset_create_nobvec(unsigned int pool_size, unsigned int front_pad)
-{
- return __bioset_create(pool_size, front_pad, false);
-}
-EXPORT_SYMBOL(bioset_create_nobvec);
-
#ifdef CONFIG_BLK_CGROUP
/**
@@ -2118,7 +2113,7 @@ static int __init init_bio(void)
bio_integrity_init();
biovec_init_slabs();
- fs_bio_set = bioset_create(BIO_POOL_SIZE, 0);
+ fs_bio_set = bioset_create(BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
if (!fs_bio_set)
panic("bio: can't allocate bios\n");
diff --git a/block/blk-core.c b/block/blk-core.c
index a7421b772d0e..af393d5a9680 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -129,11 +129,70 @@ void blk_rq_init(struct request_queue *q, struct request *rq)
}
EXPORT_SYMBOL(blk_rq_init);
+static const struct {
+ int errno;
+ const char *name;
+} blk_errors[] = {
+ [BLK_STS_OK] = { 0, "" },
+ [BLK_STS_NOTSUPP] = { -EOPNOTSUPP, "operation not supported" },
+ [BLK_STS_TIMEOUT] = { -ETIMEDOUT, "timeout" },
+ [BLK_STS_NOSPC] = { -ENOSPC, "critical space allocation" },
+ [BLK_STS_TRANSPORT] = { -ENOLINK, "recoverable transport" },
+ [BLK_STS_TARGET] = { -EREMOTEIO, "critical target" },
+ [BLK_STS_NEXUS] = { -EBADE, "critical nexus" },
+ [BLK_STS_MEDIUM] = { -ENODATA, "critical medium" },
+ [BLK_STS_PROTECTION] = { -EILSEQ, "protection" },
+ [BLK_STS_RESOURCE] = { -ENOMEM, "kernel resource" },
+ [BLK_STS_AGAIN] = { -EAGAIN, "nonblocking retry" },
+
+ /* device mapper special case, should not leak out: */
+ [BLK_STS_DM_REQUEUE] = { -EREMCHG, "dm internal retry" },
+
+ /* everything else not covered above: */
+ [BLK_STS_IOERR] = { -EIO, "I/O" },
+};
+
+blk_status_t errno_to_blk_status(int errno)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(blk_errors); i++) {
+ if (blk_errors[i].errno == errno)
+ return (__force blk_status_t)i;
+ }
+
+ return BLK_STS_IOERR;
+}
+EXPORT_SYMBOL_GPL(errno_to_blk_status);
+
+int blk_status_to_errno(blk_status_t status)
+{
+ int idx = (__force int)status;
+
+ if (WARN_ON_ONCE(idx >= ARRAY_SIZE(blk_errors)))
+ return -EIO;
+ return blk_errors[idx].errno;
+}
+EXPORT_SYMBOL_GPL(blk_status_to_errno);
+
+static void print_req_error(struct request *req, blk_status_t status)
+{
+ int idx = (__force int)status;
+
+ if (WARN_ON_ONCE(idx >= ARRAY_SIZE(blk_errors)))
+ return;
+
+ printk_ratelimited(KERN_ERR "%s: %s error, dev %s, sector %llu\n",
+ __func__, blk_errors[idx].name, req->rq_disk ?
+ req->rq_disk->disk_name : "?",
+ (unsigned long long)blk_rq_pos(req));
+}
+
static void req_bio_endio(struct request *rq, struct bio *bio,
- unsigned int nbytes, int error)
+ unsigned int nbytes, blk_status_t error)
{
if (error)
- bio->bi_error = error;
+ bio->bi_status = error;
if (unlikely(rq->rq_flags & RQF_QUIET))
bio_set_flag(bio, BIO_QUIET);
@@ -177,10 +236,13 @@ static void blk_delay_work(struct work_struct *work)
* Description:
* Sometimes queueing needs to be postponed for a little while, to allow
* resources to come back. This function will make sure that queueing is
- * restarted around the specified time. Queue lock must be held.
+ * restarted around the specified time.
*/
void blk_delay_queue(struct request_queue *q, unsigned long msecs)
{
+ lockdep_assert_held(q->queue_lock);
+ WARN_ON_ONCE(q->mq_ops);
+
if (likely(!blk_queue_dead(q)))
queue_delayed_work(kblockd_workqueue, &q->delay_work,
msecs_to_jiffies(msecs));
@@ -198,6 +260,9 @@ EXPORT_SYMBOL(blk_delay_queue);
**/
void blk_start_queue_async(struct request_queue *q)
{
+ lockdep_assert_held(q->queue_lock);
+ WARN_ON_ONCE(q->mq_ops);
+
queue_flag_clear(QUEUE_FLAG_STOPPED, q);
blk_run_queue_async(q);
}
@@ -210,11 +275,13 @@ EXPORT_SYMBOL(blk_start_queue_async);
* Description:
* blk_start_queue() will clear the stop flag on the queue, and call
* the request_fn for the queue if it was in a stopped state when
- * entered. Also see blk_stop_queue(). Queue lock must be held.
+ * entered. Also see blk_stop_queue().
**/
void blk_start_queue(struct request_queue *q)
{
+ lockdep_assert_held(q->queue_lock);
WARN_ON(!irqs_disabled());
+ WARN_ON_ONCE(q->mq_ops);
queue_flag_clear(QUEUE_FLAG_STOPPED, q);
__blk_run_queue(q);
@@ -233,10 +300,13 @@ EXPORT_SYMBOL(blk_start_queue);
* or if it simply chooses not to queue more I/O at one point, it can
* call this function to prevent the request_fn from being called until
* the driver has signalled it's ready to go again. This happens by calling
- * blk_start_queue() to restart queue operations. Queue lock must be held.
+ * blk_start_queue() to restart queue operations.
**/
void blk_stop_queue(struct request_queue *q)
{
+ lockdep_assert_held(q->queue_lock);
+ WARN_ON_ONCE(q->mq_ops);
+
cancel_delayed_work(&q->delay_work);
queue_flag_set(QUEUE_FLAG_STOPPED, q);
}
@@ -289,6 +359,9 @@ EXPORT_SYMBOL(blk_sync_queue);
*/
inline void __blk_run_queue_uncond(struct request_queue *q)
{
+ lockdep_assert_held(q->queue_lock);
+ WARN_ON_ONCE(q->mq_ops);
+
if (unlikely(blk_queue_dead(q)))
return;
@@ -310,11 +383,13 @@ EXPORT_SYMBOL_GPL(__blk_run_queue_uncond);
* @q: The queue to run
*
* Description:
- * See @blk_run_queue. This variant must be called with the queue lock
- * held and interrupts disabled.
+ * See @blk_run_queue.
*/
void __blk_run_queue(struct request_queue *q)
{
+ lockdep_assert_held(q->queue_lock);
+ WARN_ON_ONCE(q->mq_ops);
+
if (unlikely(blk_queue_stopped(q)))
return;
@@ -328,10 +403,18 @@ EXPORT_SYMBOL(__blk_run_queue);
*
* Description:
* Tells kblockd to perform the equivalent of @blk_run_queue on behalf
- * of us. The caller must hold the queue lock.
+ * of us.
+ *
+ * Note:
+ * Since it is not allowed to run q->delay_work after blk_cleanup_queue()
+ * has canceled q->delay_work, callers must hold the queue lock to avoid
+ * race conditions between blk_cleanup_queue() and blk_run_queue_async().
*/
void blk_run_queue_async(struct request_queue *q)
{
+ lockdep_assert_held(q->queue_lock);
+ WARN_ON_ONCE(q->mq_ops);
+
if (likely(!blk_queue_stopped(q) && !blk_queue_dead(q)))
mod_delayed_work(kblockd_workqueue, &q->delay_work, 0);
}
@@ -349,6 +432,8 @@ void blk_run_queue(struct request_queue *q)
{
unsigned long flags;
+ WARN_ON_ONCE(q->mq_ops);
+
spin_lock_irqsave(q->queue_lock, flags);
__blk_run_queue(q);
spin_unlock_irqrestore(q->queue_lock, flags);
@@ -377,6 +462,7 @@ static void __blk_drain_queue(struct request_queue *q, bool drain_all)
int i;
lockdep_assert_held(q->queue_lock);
+ WARN_ON_ONCE(q->mq_ops);
while (true) {
bool drain = false;
@@ -455,6 +541,8 @@ static void __blk_drain_queue(struct request_queue *q, bool drain_all)
*/
void blk_queue_bypass_start(struct request_queue *q)
{
+ WARN_ON_ONCE(q->mq_ops);
+
spin_lock_irq(q->queue_lock);
q->bypass_depth++;
queue_flag_set(QUEUE_FLAG_BYPASS, q);
@@ -481,6 +569,9 @@ EXPORT_SYMBOL_GPL(blk_queue_bypass_start);
* @q: queue of interest
*
* Leave bypass mode and restore the normal queueing behavior.
+ *
+ * Note: although blk_queue_bypass_start() is only called for blk-sq queues,
+ * this function is called for both blk-sq and blk-mq queues.
*/
void blk_queue_bypass_end(struct request_queue *q)
{
@@ -732,7 +823,7 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
if (q->id < 0)
goto fail_q;
- q->bio_split = bioset_create(BIO_POOL_SIZE, 0);
+ q->bio_split = bioset_create(BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
if (!q->bio_split)
goto fail_id;
@@ -878,6 +969,8 @@ static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio);
int blk_init_allocated_queue(struct request_queue *q)
{
+ WARN_ON_ONCE(q->mq_ops);
+
q->fq = blk_alloc_flush_queue(q, NUMA_NO_NODE, q->cmd_size);
if (!q->fq)
return -ENOMEM;
@@ -1015,6 +1108,8 @@ int blk_update_nr_requests(struct request_queue *q, unsigned int nr)
struct request_list *rl;
int on_thresh, off_thresh;
+ WARN_ON_ONCE(q->mq_ops);
+
spin_lock_irq(q->queue_lock);
q->nr_requests = nr;
blk_queue_congestion_threshold(q);
@@ -1077,6 +1172,8 @@ static struct request *__get_request(struct request_list *rl, unsigned int op,
int may_queue;
req_flags_t rq_flags = RQF_ALLOCED;
+ lockdep_assert_held(q->queue_lock);
+
if (unlikely(blk_queue_dying(q)))
return ERR_PTR(-ENODEV);
@@ -1250,12 +1347,20 @@ static struct request *get_request(struct request_queue *q, unsigned int op,
struct request_list *rl;
struct request *rq;
+ lockdep_assert_held(q->queue_lock);
+ WARN_ON_ONCE(q->mq_ops);
+
rl = blk_get_rl(q, bio); /* transferred to @rq on success */
retry:
rq = __get_request(rl, op, bio, gfp_mask);
if (!IS_ERR(rq))
return rq;
+ if (op & REQ_NOWAIT) {
+ blk_put_rl(rl);
+ return ERR_PTR(-EAGAIN);
+ }
+
if (!gfpflags_allow_blocking(gfp_mask) || unlikely(blk_queue_dying(q))) {
blk_put_rl(rl);
return rq;
@@ -1283,16 +1388,18 @@ retry:
goto retry;
}
-static struct request *blk_old_get_request(struct request_queue *q, int rw,
- gfp_t gfp_mask)
+static struct request *blk_old_get_request(struct request_queue *q,
+ unsigned int op, gfp_t gfp_mask)
{
struct request *rq;
+ WARN_ON_ONCE(q->mq_ops);
+
/* create ioc upfront */
create_io_context(gfp_mask, q->node);
spin_lock_irq(q->queue_lock);
- rq = get_request(q, rw, NULL, gfp_mask);
+ rq = get_request(q, op, NULL, gfp_mask);
if (IS_ERR(rq)) {
spin_unlock_irq(q->queue_lock);
return rq;
@@ -1305,14 +1412,24 @@ static struct request *blk_old_get_request(struct request_queue *q, int rw,
return rq;
}
-struct request *blk_get_request(struct request_queue *q, int rw, gfp_t gfp_mask)
+struct request *blk_get_request(struct request_queue *q, unsigned int op,
+ gfp_t gfp_mask)
{
- if (q->mq_ops)
- return blk_mq_alloc_request(q, rw,
+ struct request *req;
+
+ if (q->mq_ops) {
+ req = blk_mq_alloc_request(q, op,
(gfp_mask & __GFP_DIRECT_RECLAIM) ?
0 : BLK_MQ_REQ_NOWAIT);
- else
- return blk_old_get_request(q, rw, gfp_mask);
+ if (!IS_ERR(req) && q->mq_ops->initialize_rq_fn)
+ q->mq_ops->initialize_rq_fn(req);
+ } else {
+ req = blk_old_get_request(q, op, gfp_mask);
+ if (!IS_ERR(req) && q->initialize_rq_fn)
+ q->initialize_rq_fn(req);
+ }
+
+ return req;
}
EXPORT_SYMBOL(blk_get_request);
@@ -1328,6 +1445,9 @@ EXPORT_SYMBOL(blk_get_request);
*/
void blk_requeue_request(struct request_queue *q, struct request *rq)
{
+ lockdep_assert_held(q->queue_lock);
+ WARN_ON_ONCE(q->mq_ops);
+
blk_delete_timer(rq);
blk_clear_rq_complete(rq);
trace_block_rq_requeue(q, rq);
@@ -1402,9 +1522,6 @@ static void blk_pm_put_request(struct request *rq)
static inline void blk_pm_put_request(struct request *rq) {}
#endif
-/*
- * queue lock must be held
- */
void __blk_put_request(struct request_queue *q, struct request *req)
{
req_flags_t rq_flags = req->rq_flags;
@@ -1417,6 +1534,8 @@ void __blk_put_request(struct request_queue *q, struct request *req)
return;
}
+ lockdep_assert_held(q->queue_lock);
+
blk_pm_put_request(req);
elv_completed_request(q, req);
@@ -1646,6 +1765,7 @@ void blk_init_request_from_bio(struct request *req, struct bio *bio)
req->ioprio = ioc->ioprio;
else
req->ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_NONE, 0);
+ req->write_hint = bio->bi_write_hint;
blk_rq_bio_prep(req->q, req, bio);
}
EXPORT_SYMBOL_GPL(blk_init_request_from_bio);
@@ -1665,10 +1785,10 @@ static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio)
*/
blk_queue_bounce(q, &bio);
- blk_queue_split(q, &bio, q->bio_split);
+ blk_queue_split(q, &bio);
if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) {
- bio->bi_error = -EIO;
+ bio->bi_status = BLK_STS_IOERR;
bio_endio(bio);
return BLK_QC_T_NONE;
}
@@ -1726,7 +1846,10 @@ get_rq:
req = get_request(q, bio->bi_opf, bio, GFP_NOIO);
if (IS_ERR(req)) {
__wbt_done(q->rq_wb, wb_acct);
- bio->bi_error = PTR_ERR(req);
+ if (PTR_ERR(req) == -ENOMEM)
+ bio->bi_status = BLK_STS_RESOURCE;
+ else
+ bio->bi_status = BLK_STS_IOERR;
bio_endio(bio);
goto out_unlock;
}
@@ -1881,7 +2004,7 @@ generic_make_request_checks(struct bio *bio)
{
struct request_queue *q;
int nr_sectors = bio_sectors(bio);
- int err = -EIO;
+ blk_status_t status = BLK_STS_IOERR;
char b[BDEVNAME_SIZE];
struct hd_struct *part;
@@ -1900,6 +2023,14 @@ generic_make_request_checks(struct bio *bio)
goto end_io;
}
+ /*
+ * For a REQ_NOWAIT based request, return -EOPNOTSUPP
+ * if queue is not a request based queue.
+ */
+
+ if ((bio->bi_opf & REQ_NOWAIT) && !queue_is_rq_based(q))
+ goto not_supported;
+
part = bio->bi_bdev->bd_part;
if (should_fail_request(part, bio->bi_iter.bi_size) ||
should_fail_request(&part_to_disk(part)->part0,
@@ -1924,7 +2055,7 @@ generic_make_request_checks(struct bio *bio)
!test_bit(QUEUE_FLAG_WC, &q->queue_flags)) {
bio->bi_opf &= ~(REQ_PREFLUSH | REQ_FUA);
if (!nr_sectors) {
- err = 0;
+ status = BLK_STS_OK;
goto end_io;
}
}
@@ -1976,9 +2107,9 @@ generic_make_request_checks(struct bio *bio)
return true;
not_supported:
- err = -EOPNOTSUPP;
+ status = BLK_STS_NOTSUPP;
end_io:
- bio->bi_error = err;
+ bio->bi_status = status;
bio_endio(bio);
return false;
}
@@ -2057,7 +2188,7 @@ blk_qc_t generic_make_request(struct bio *bio)
do {
struct request_queue *q = bdev_get_queue(bio->bi_bdev);
- if (likely(blk_queue_enter(q, false) == 0)) {
+ if (likely(blk_queue_enter(q, bio->bi_opf & REQ_NOWAIT) == 0)) {
struct bio_list lower, same;
/* Create a fresh bio_list for all subordinate requests */
@@ -2082,7 +2213,11 @@ blk_qc_t generic_make_request(struct bio *bio)
bio_list_merge(&bio_list_on_stack[0], &same);
bio_list_merge(&bio_list_on_stack[0], &bio_list_on_stack[1]);
} else {
- bio_io_error(bio);
+ if (unlikely(!blk_queue_dying(q) &&
+ (bio->bi_opf & REQ_NOWAIT)))
+ bio_wouldblock_error(bio);
+ else
+ bio_io_error(bio);
}
bio = bio_list_pop(&bio_list_on_stack[0]);
} while (bio);
@@ -2183,29 +2318,29 @@ static int blk_cloned_rq_check_limits(struct request_queue *q,
* @q: the queue to submit the request
* @rq: the request being queued
*/
-int blk_insert_cloned_request(struct request_queue *q, struct request *rq)
+blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request *rq)
{
unsigned long flags;
int where = ELEVATOR_INSERT_BACK;
if (blk_cloned_rq_check_limits(q, rq))
- return -EIO;
+ return BLK_STS_IOERR;
if (rq->rq_disk &&
should_fail_request(&rq->rq_disk->part0, blk_rq_bytes(rq)))
- return -EIO;
+ return BLK_STS_IOERR;
if (q->mq_ops) {
if (blk_queue_io_stat(q))
blk_account_io_start(rq, true);
blk_mq_sched_insert_request(rq, false, true, false, false);
- return 0;
+ return BLK_STS_OK;
}
spin_lock_irqsave(q->queue_lock, flags);
if (unlikely(blk_queue_dying(q))) {
spin_unlock_irqrestore(q->queue_lock, flags);
- return -ENODEV;
+ return BLK_STS_IOERR;
}
/*
@@ -2222,7 +2357,7 @@ int blk_insert_cloned_request(struct request_queue *q, struct request *rq)
__blk_run_queue(q);
spin_unlock_irqrestore(q->queue_lock, flags);
- return 0;
+ return BLK_STS_OK;
}
EXPORT_SYMBOL_GPL(blk_insert_cloned_request);
@@ -2238,9 +2373,6 @@ EXPORT_SYMBOL_GPL(blk_insert_cloned_request);
*
* Return:
* The number of bytes to fail.
- *
- * Context:
- * queue_lock must be held.
*/
unsigned int blk_rq_err_bytes(const struct request *rq)
{
@@ -2380,15 +2512,15 @@ void blk_account_io_start(struct request *rq, bool new_io)
* Return:
* Pointer to the request at the top of @q if available. Null
* otherwise.
- *
- * Context:
- * queue_lock must be held.
*/
struct request *blk_peek_request(struct request_queue *q)
{
struct request *rq;
int ret;
+ lockdep_assert_held(q->queue_lock);
+ WARN_ON_ONCE(q->mq_ops);
+
while ((rq = __elv_next_request(q)) != NULL) {
rq = blk_pm_peek_request(q, rq);
@@ -2456,15 +2588,14 @@ struct request *blk_peek_request(struct request_queue *q)
rq = NULL;
break;
} else if (ret == BLKPREP_KILL || ret == BLKPREP_INVALID) {
- int err = (ret == BLKPREP_INVALID) ? -EREMOTEIO : -EIO;
-
rq->rq_flags |= RQF_QUIET;
/*
* Mark this request as started so we don't trigger
* any debug logic in the end I/O path.
*/
blk_start_request(rq);
- __blk_end_request_all(rq, err);
+ __blk_end_request_all(rq, ret == BLKPREP_INVALID ?
+ BLK_STS_TARGET : BLK_STS_IOERR);
} else {
printk(KERN_ERR "%s: bad return=%d\n", __func__, ret);
break;
@@ -2505,12 +2636,12 @@ void blk_dequeue_request(struct request *rq)
*
* Block internal functions which don't want to start timer should
* call blk_dequeue_request().
- *
- * Context:
- * queue_lock must be held.
*/
void blk_start_request(struct request *req)
{
+ lockdep_assert_held(req->q->queue_lock);
+ WARN_ON_ONCE(req->q->mq_ops);
+
blk_dequeue_request(req);
if (test_bit(QUEUE_FLAG_STATS, &req->q->queue_flags)) {
@@ -2535,14 +2666,14 @@ EXPORT_SYMBOL(blk_start_request);
* Return:
* Pointer to the request at the top of @q if available. Null
* otherwise.
- *
- * Context:
- * queue_lock must be held.
*/
struct request *blk_fetch_request(struct request_queue *q)
{
struct request *rq;
+ lockdep_assert_held(q->queue_lock);
+ WARN_ON_ONCE(q->mq_ops);
+
rq = blk_peek_request(q);
if (rq)
blk_start_request(rq);
@@ -2553,7 +2684,7 @@ EXPORT_SYMBOL(blk_fetch_request);
/**
* blk_update_request - Special helper function for request stacking drivers
* @req: the request being processed
- * @error: %0 for success, < %0 for error
+ * @error: block status code
* @nr_bytes: number of bytes to complete @req
*
* Description:
@@ -2572,49 +2703,19 @@ EXPORT_SYMBOL(blk_fetch_request);
* %false - this request doesn't have any more data
* %true - this request has more data
**/
-bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
+bool blk_update_request(struct request *req, blk_status_t error,
+ unsigned int nr_bytes)
{
int total_bytes;
- trace_block_rq_complete(req, error, nr_bytes);
+ trace_block_rq_complete(req, blk_status_to_errno(error), nr_bytes);
if (!req->bio)
return false;
- if (error && !blk_rq_is_passthrough(req) &&
- !(req->rq_flags & RQF_QUIET)) {
- char *error_type;
-
- switch (error) {
- case -ENOLINK:
- error_type = "recoverable transport";
- break;
- case -EREMOTEIO:
- error_type = "critical target";
- break;
- case -EBADE:
- error_type = "critical nexus";
- break;
- case -ETIMEDOUT:
- error_type = "timeout";
- break;
- case -ENOSPC:
- error_type = "critical space allocation";
- break;
- case -ENODATA:
- error_type = "critical medium";
- break;
- case -EIO:
- default:
- error_type = "I/O";
- break;
- }
- printk_ratelimited(KERN_ERR "%s: %s error, dev %s, sector %llu\n",
- __func__, error_type, req->rq_disk ?
- req->rq_disk->disk_name : "?",
- (unsigned long long)blk_rq_pos(req));
-
- }
+ if (unlikely(error && !blk_rq_is_passthrough(req) &&
+ !(req->rq_flags & RQF_QUIET)))
+ print_req_error(req, error);
blk_account_io_completion(req, nr_bytes);
@@ -2680,7 +2781,7 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
}
EXPORT_SYMBOL_GPL(blk_update_request);
-static bool blk_update_bidi_request(struct request *rq, int error,
+static bool blk_update_bidi_request(struct request *rq, blk_status_t error,
unsigned int nr_bytes,
unsigned int bidi_bytes)
{
@@ -2718,13 +2819,13 @@ void blk_unprep_request(struct request *req)
}
EXPORT_SYMBOL_GPL(blk_unprep_request);
-/*
- * queue lock must be held
- */
-void blk_finish_request(struct request *req, int error)
+void blk_finish_request(struct request *req, blk_status_t error)
{
struct request_queue *q = req->q;
+ lockdep_assert_held(req->q->queue_lock);
+ WARN_ON_ONCE(q->mq_ops);
+
if (req->rq_flags & RQF_STATS)
blk_stat_add(req);
@@ -2758,7 +2859,7 @@ EXPORT_SYMBOL(blk_finish_request);
/**
* blk_end_bidi_request - Complete a bidi request
* @rq: the request to complete
- * @error: %0 for success, < %0 for error
+ * @error: block status code
* @nr_bytes: number of bytes to complete @rq
* @bidi_bytes: number of bytes to complete @rq->next_rq
*
@@ -2772,12 +2873,14 @@ EXPORT_SYMBOL(blk_finish_request);
* %false - we are done with this request
* %true - still buffers pending for this request
**/
-static bool blk_end_bidi_request(struct request *rq, int error,
+static bool blk_end_bidi_request(struct request *rq, blk_status_t error,
unsigned int nr_bytes, unsigned int bidi_bytes)
{
struct request_queue *q = rq->q;
unsigned long flags;
+ WARN_ON_ONCE(q->mq_ops);
+
if (blk_update_bidi_request(rq, error, nr_bytes, bidi_bytes))
return true;
@@ -2791,7 +2894,7 @@ static bool blk_end_bidi_request(struct request *rq, int error,
/**
* __blk_end_bidi_request - Complete a bidi request with queue lock held
* @rq: the request to complete
- * @error: %0 for success, < %0 for error
+ * @error: block status code
* @nr_bytes: number of bytes to complete @rq
* @bidi_bytes: number of bytes to complete @rq->next_rq
*
@@ -2803,9 +2906,12 @@ static bool blk_end_bidi_request(struct request *rq, int error,
* %false - we are done with this request
* %true - still buffers pending for this request
**/
-static bool __blk_end_bidi_request(struct request *rq, int error,
+static bool __blk_end_bidi_request(struct request *rq, blk_status_t error,
unsigned int nr_bytes, unsigned int bidi_bytes)
{
+ lockdep_assert_held(rq->q->queue_lock);
+ WARN_ON_ONCE(rq->q->mq_ops);
+
if (blk_update_bidi_request(rq, error, nr_bytes, bidi_bytes))
return true;
@@ -2817,7 +2923,7 @@ static bool __blk_end_bidi_request(struct request *rq, int error,
/**
* blk_end_request - Helper function for drivers to complete the request.
* @rq: the request being processed
- * @error: %0 for success, < %0 for error
+ * @error: block status code
* @nr_bytes: number of bytes to complete
*
* Description:
@@ -2828,8 +2934,10 @@ static bool __blk_end_bidi_request(struct request *rq, int error,
* %false - we are done with this request
* %true - still buffers pending for this request
**/
-bool blk_end_request(struct request *rq, int error, unsigned int nr_bytes)
+bool blk_end_request(struct request *rq, blk_status_t error,
+ unsigned int nr_bytes)
{
+ WARN_ON_ONCE(rq->q->mq_ops);
return blk_end_bidi_request(rq, error, nr_bytes, 0);
}
EXPORT_SYMBOL(blk_end_request);
@@ -2837,12 +2945,12 @@ EXPORT_SYMBOL(blk_end_request);
/**
* blk_end_request_all - Helper function for drives to finish the request.
* @rq: the request to finish
- * @error: %0 for success, < %0 for error
+ * @error: block status code
*
* Description:
* Completely finish @rq.
*/
-void blk_end_request_all(struct request *rq, int error)
+void blk_end_request_all(struct request *rq, blk_status_t error)
{
bool pending;
unsigned int bidi_bytes = 0;
@@ -2858,7 +2966,7 @@ EXPORT_SYMBOL(blk_end_request_all);
/**
* __blk_end_request - Helper function for drivers to complete the request.
* @rq: the request being processed
- * @error: %0 for success, < %0 for error
+ * @error: block status code
* @nr_bytes: number of bytes to complete
*
* Description:
@@ -2868,8 +2976,12 @@ EXPORT_SYMBOL(blk_end_request_all);
* %false - we are done with this request
* %true - still buffers pending for this request
**/
-bool __blk_end_request(struct request *rq, int error, unsigned int nr_bytes)
+bool __blk_end_request(struct request *rq, blk_status_t error,
+ unsigned int nr_bytes)
{
+ lockdep_assert_held(rq->q->queue_lock);
+ WARN_ON_ONCE(rq->q->mq_ops);
+
return __blk_end_bidi_request(rq, error, nr_bytes, 0);
}
EXPORT_SYMBOL(__blk_end_request);
@@ -2877,16 +2989,19 @@ EXPORT_SYMBOL(__blk_end_request);
/**
* __blk_end_request_all - Helper function for drives to finish the request.
* @rq: the request to finish
- * @error: %0 for success, < %0 for error
+ * @error: block status code
*
* Description:
* Completely finish @rq. Must be called with queue lock held.
*/
-void __blk_end_request_all(struct request *rq, int error)
+void __blk_end_request_all(struct request *rq, blk_status_t error)
{
bool pending;
unsigned int bidi_bytes = 0;
+ lockdep_assert_held(rq->q->queue_lock);
+ WARN_ON_ONCE(rq->q->mq_ops);
+
if (unlikely(blk_bidi_rq(rq)))
bidi_bytes = blk_rq_bytes(rq->next_rq);
@@ -2898,7 +3013,7 @@ EXPORT_SYMBOL(__blk_end_request_all);
/**
* __blk_end_request_cur - Helper function to finish the current request chunk.
* @rq: the request to finish the current chunk for
- * @error: %0 for success, < %0 for error
+ * @error: block status code
*
* Description:
* Complete the current consecutively mapped chunk from @rq. Must
@@ -2908,7 +3023,7 @@ EXPORT_SYMBOL(__blk_end_request_all);
* %false - we are done with this request
* %true - still buffers pending for this request
*/
-bool __blk_end_request_cur(struct request *rq, int error)
+bool __blk_end_request_cur(struct request *rq, blk_status_t error)
{
return __blk_end_request(rq, error, blk_rq_cur_bytes(rq));
}
@@ -3151,6 +3266,8 @@ static void queue_unplugged(struct request_queue *q, unsigned int depth,
bool from_schedule)
__releases(q->queue_lock)
{
+ lockdep_assert_held(q->queue_lock);
+
trace_block_unplug(q, depth, !from_schedule);
if (from_schedule)
@@ -3249,7 +3366,7 @@ void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule)
* Short-circuit if @q is dead
*/
if (unlikely(blk_queue_dying(q))) {
- __blk_end_request_all(rq, -ENODEV);
+ __blk_end_request_all(rq, BLK_STS_IOERR);
continue;
}
diff --git a/block/blk-exec.c b/block/blk-exec.c
index a9451e3b8587..5c0f3dc446dc 100644
--- a/block/blk-exec.c
+++ b/block/blk-exec.c
@@ -16,7 +16,7 @@
* @rq: request to complete
* @error: end I/O status of the request
*/
-static void blk_end_sync_rq(struct request *rq, int error)
+static void blk_end_sync_rq(struct request *rq, blk_status_t error)
{
struct completion *waiting = rq->end_io_data;
@@ -69,7 +69,7 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk,
if (unlikely(blk_queue_dying(q))) {
rq->rq_flags |= RQF_QUIET;
- __blk_end_request_all(rq, -ENXIO);
+ __blk_end_request_all(rq, BLK_STS_IOERR);
spin_unlock_irq(q->queue_lock);
return;
}
diff --git a/block/blk-flush.c b/block/blk-flush.c
index c4e0880b54bb..ed5fe322abba 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -164,7 +164,7 @@ static bool blk_flush_queue_rq(struct request *rq, bool add_front)
*/
static bool blk_flush_complete_seq(struct request *rq,
struct blk_flush_queue *fq,
- unsigned int seq, int error)
+ unsigned int seq, blk_status_t error)
{
struct request_queue *q = rq->q;
struct list_head *pending = &fq->flush_queue[fq->flush_pending_idx];
@@ -216,7 +216,7 @@ static bool blk_flush_complete_seq(struct request *rq,
return kicked | queued;
}
-static void flush_end_io(struct request *flush_rq, int error)
+static void flush_end_io(struct request *flush_rq, blk_status_t error)
{
struct request_queue *q = flush_rq->q;
struct list_head *running;
@@ -341,11 +341,13 @@ static bool blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq)
return blk_flush_queue_rq(flush_rq, false);
}
-static void flush_data_end_io(struct request *rq, int error)
+static void flush_data_end_io(struct request *rq, blk_status_t error)
{
struct request_queue *q = rq->q;
struct blk_flush_queue *fq = blk_get_flush_queue(q, NULL);
+ lockdep_assert_held(q->queue_lock);
+
/*
* Updating q->in_flight[] here for making this tag usable
* early. Because in blk_queue_start_tag(),
@@ -382,7 +384,7 @@ static void flush_data_end_io(struct request *rq, int error)
blk_run_queue_async(q);
}
-static void mq_flush_data_end_io(struct request *rq, int error)
+static void mq_flush_data_end_io(struct request *rq, blk_status_t error)
{
struct request_queue *q = rq->q;
struct blk_mq_hw_ctx *hctx;
@@ -411,9 +413,6 @@ static void mq_flush_data_end_io(struct request *rq, int error)
* or __blk_mq_run_hw_queue() to dispatch request.
* @rq is being submitted. Analyze what needs to be done and put it on the
* right queue.
- *
- * CONTEXT:
- * spin_lock_irq(q->queue_lock) in !mq case
*/
void blk_insert_flush(struct request *rq)
{
@@ -422,6 +421,9 @@ void blk_insert_flush(struct request *rq)
unsigned int policy = blk_flush_policy(fflags, rq);
struct blk_flush_queue *fq = blk_get_flush_queue(q, rq->mq_ctx);
+ if (!q->mq_ops)
+ lockdep_assert_held(q->queue_lock);
+
/*
* @policy now records what operations need to be done. Adjust
* REQ_PREFLUSH and FUA for the driver.
diff --git a/block/blk-integrity.c b/block/blk-integrity.c
index 0f891a9aff4d..feb30570eaf5 100644
--- a/block/blk-integrity.c
+++ b/block/blk-integrity.c
@@ -384,9 +384,9 @@ static struct kobj_type integrity_ktype = {
.sysfs_ops = &integrity_ops,
};
-static int blk_integrity_nop_fn(struct blk_integrity_iter *iter)
+static blk_status_t blk_integrity_nop_fn(struct blk_integrity_iter *iter)
{
- return 0;
+ return BLK_STS_OK;
}
static const struct blk_integrity_profile nop_profile = {
diff --git a/block/blk-map.c b/block/blk-map.c
index 3b5cb863318f..2547016aa7aa 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -16,6 +16,8 @@
*/
int blk_rq_append_bio(struct request *rq, struct bio *bio)
{
+ blk_queue_bounce(rq->q, &bio);
+
if (!rq->bio) {
blk_rq_bio_prep(rq->q, rq, bio);
} else {
@@ -72,15 +74,13 @@ static int __blk_rq_map_user_iov(struct request *rq,
map_data->offset += bio->bi_iter.bi_size;
orig_bio = bio;
- blk_queue_bounce(q, &bio);
/*
* We link the bounce buffer in and could have to traverse it
* later so we have to get a ref to prevent it from being freed
*/
- bio_get(bio);
-
ret = blk_rq_append_bio(rq, bio);
+ bio_get(bio);
if (ret) {
bio_endio(bio);
__blk_rq_unmap_user(orig_bio);
@@ -249,7 +249,6 @@ int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf,
return ret;
}
- blk_queue_bounce(q, &rq->bio);
return 0;
}
EXPORT_SYMBOL(blk_rq_map_kern);
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 3990ae406341..99038830fb42 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -108,31 +108,9 @@ static struct bio *blk_bio_segment_split(struct request_queue *q,
bool do_split = true;
struct bio *new = NULL;
const unsigned max_sectors = get_max_io_size(q, bio);
- unsigned bvecs = 0;
bio_for_each_segment(bv, bio, iter) {
/*
- * With arbitrary bio size, the incoming bio may be very
- * big. We have to split the bio into small bios so that
- * each holds at most BIO_MAX_PAGES bvecs because
- * bio_clone() can fail to allocate big bvecs.
- *
- * It should have been better to apply the limit per
- * request queue in which bio_clone() is involved,
- * instead of globally. The biggest blocker is the
- * bio_clone() in bio bounce.
- *
- * If bio is splitted by this reason, we should have
- * allowed to continue bios merging, but don't do
- * that now for making the change simple.
- *
- * TODO: deal with bio bounce's bio_clone() gracefully
- * and convert the global limit into per-queue limit.
- */
- if (bvecs++ >= BIO_MAX_PAGES)
- goto split;
-
- /*
* If the queue doesn't support SG gaps and adding this
* offset would create a gap, disallow it.
*/
@@ -202,8 +180,7 @@ split:
return do_split ? new : NULL;
}
-void blk_queue_split(struct request_queue *q, struct bio **bio,
- struct bio_set *bs)
+void blk_queue_split(struct request_queue *q, struct bio **bio)
{
struct bio *split, *res;
unsigned nsegs;
@@ -211,13 +188,13 @@ void blk_queue_split(struct request_queue *q, struct bio **bio,
switch (bio_op(*bio)) {
case REQ_OP_DISCARD:
case REQ_OP_SECURE_ERASE:
- split = blk_bio_discard_split(q, *bio, bs, &nsegs);
+ split = blk_bio_discard_split(q, *bio, q->bio_split, &nsegs);
break;
case REQ_OP_WRITE_ZEROES:
- split = blk_bio_write_zeroes_split(q, *bio, bs, &nsegs);
+ split = blk_bio_write_zeroes_split(q, *bio, q->bio_split, &nsegs);
break;
case REQ_OP_WRITE_SAME:
- split = blk_bio_write_same_split(q, *bio, bs, &nsegs);
+ split = blk_bio_write_same_split(q, *bio, q->bio_split, &nsegs);
break;
default:
split = blk_bio_segment_split(q, *bio, q->bio_split, &nsegs);
@@ -671,6 +648,9 @@ static void blk_account_io_merge(struct request *req)
static struct request *attempt_merge(struct request_queue *q,
struct request *req, struct request *next)
{
+ if (!q->mq_ops)
+ lockdep_assert_held(q->queue_lock);
+
if (!rq_mergeable(req) || !rq_mergeable(next))
return NULL;
@@ -693,6 +673,13 @@ static struct request *attempt_merge(struct request_queue *q,
return NULL;
/*
+ * Don't allow merge of different write hints, or for a hint with
+ * non-hint IO.
+ */
+ if (req->write_hint != next->write_hint)
+ return NULL;
+
+ /*
* If we are allowed to merge, then append bio list
* from next to rq and release next. merge_requests_fn
* will have updated segment counts, update sector
@@ -811,6 +798,13 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio)
!blk_write_same_mergeable(rq->bio, bio))
return false;
+ /*
+ * Don't allow merge of different write hints, or for a hint with
+ * non-hint IO.
+ */
+ if (rq->write_hint != bio->bi_write_hint)
+ return false;
+
return true;
}
diff --git a/block/blk-mq-cpumap.c b/block/blk-mq-cpumap.c
index 8e61e8640e17..2cca4fc43f45 100644
--- a/block/blk-mq-cpumap.c
+++ b/block/blk-mq-cpumap.c
@@ -14,10 +14,15 @@
#include "blk.h"
#include "blk-mq.h"
-static int cpu_to_queue_index(unsigned int nr_cpus, unsigned int nr_queues,
- const int cpu)
+static int cpu_to_queue_index(unsigned int nr_queues, const int cpu,
+ const struct cpumask *online_mask)
{
- return cpu * nr_queues / nr_cpus;
+ /*
+ * Non online CPU will be mapped to queue index 0.
+ */
+ if (!cpumask_test_cpu(cpu, online_mask))
+ return 0;
+ return cpu % nr_queues;
}
static int get_first_sibling(unsigned int cpu)
@@ -36,55 +41,26 @@ int blk_mq_map_queues(struct blk_mq_tag_set *set)
unsigned int *map = set->mq_map;
unsigned int nr_queues = set->nr_hw_queues;
const struct cpumask *online_mask = cpu_online_mask;
- unsigned int i, nr_cpus, nr_uniq_cpus, queue, first_sibling;
- cpumask_var_t cpus;
-
- if (!alloc_cpumask_var(&cpus, GFP_ATOMIC))
- return -ENOMEM;
-
- cpumask_clear(cpus);
- nr_cpus = nr_uniq_cpus = 0;
- for_each_cpu(i, online_mask) {
- nr_cpus++;
- first_sibling = get_first_sibling(i);
- if (!cpumask_test_cpu(first_sibling, cpus))
- nr_uniq_cpus++;
- cpumask_set_cpu(i, cpus);
- }
-
- queue = 0;
- for_each_possible_cpu(i) {
- if (!cpumask_test_cpu(i, online_mask)) {
- map[i] = 0;
- continue;
- }
+ unsigned int cpu, first_sibling;
+ for_each_possible_cpu(cpu) {
/*
- * Easy case - we have equal or more hardware queues. Or
- * there are no thread siblings to take into account. Do
- * 1:1 if enough, or sequential mapping if less.
+ * First do sequential mapping between CPUs and queues.
+ * In case we still have CPUs to map, and we have some number of
+ * threads per cores then map sibling threads to the same queue for
+ * performace optimizations.
*/
- if (nr_queues >= nr_cpus || nr_cpus == nr_uniq_cpus) {
- map[i] = cpu_to_queue_index(nr_cpus, nr_queues, queue);
- queue++;
- continue;
+ if (cpu < nr_queues) {
+ map[cpu] = cpu_to_queue_index(nr_queues, cpu, online_mask);
+ } else {
+ first_sibling = get_first_sibling(cpu);
+ if (first_sibling == cpu)
+ map[cpu] = cpu_to_queue_index(nr_queues, cpu, online_mask);
+ else
+ map[cpu] = map[first_sibling];
}
-
- /*
- * Less then nr_cpus queues, and we have some number of
- * threads per cores. Map sibling threads to the same
- * queue.
- */
- first_sibling = get_first_sibling(i);
- if (first_sibling == i) {
- map[i] = cpu_to_queue_index(nr_uniq_cpus, nr_queues,
- queue);
- queue++;
- } else
- map[i] = map[first_sibling];
}
- free_cpumask_var(cpus);
return 0;
}
EXPORT_SYMBOL_GPL(blk_mq_map_queues);
diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index 803aed4d7221..9ebc2945f991 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -114,10 +114,12 @@ static ssize_t queue_state_write(void *data, const char __user *buf,
blk_mq_run_hw_queues(q, true);
} else if (strcmp(op, "start") == 0) {
blk_mq_start_stopped_hw_queues(q, true);
+ } else if (strcmp(op, "kick") == 0) {
+ blk_mq_kick_requeue_list(q);
} else {
pr_err("%s: unsupported operation '%s'\n", __func__, op);
inval:
- pr_err("%s: use either 'run' or 'start'\n", __func__);
+ pr_err("%s: use 'run', 'start' or 'kick'\n", __func__);
return -EINVAL;
}
return count;
@@ -133,6 +135,29 @@ static void print_stat(struct seq_file *m, struct blk_rq_stat *stat)
}
}
+static int queue_write_hint_show(void *data, struct seq_file *m)
+{
+ struct request_queue *q = data;
+ int i;
+
+ for (i = 0; i < BLK_MAX_WRITE_HINTS; i++)
+ seq_printf(m, "hint%d: %llu\n", i, q->write_hints[i]);
+
+ return 0;
+}
+
+static ssize_t queue_write_hint_store(void *data, const char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ struct request_queue *q = data;
+ int i;
+
+ for (i = 0; i < BLK_MAX_WRITE_HINTS; i++)
+ q->write_hints[i] = 0;
+
+ return count;
+}
+
static int queue_poll_stat_show(void *data, struct seq_file *m)
{
struct request_queue *q = data;
@@ -267,6 +292,14 @@ static const char *const rqf_name[] = {
};
#undef RQF_NAME
+#define RQAF_NAME(name) [REQ_ATOM_##name] = #name
+static const char *const rqaf_name[] = {
+ RQAF_NAME(COMPLETE),
+ RQAF_NAME(STARTED),
+ RQAF_NAME(POLL_SLEPT),
+};
+#undef RQAF_NAME
+
int __blk_mq_debugfs_rq_show(struct seq_file *m, struct request *rq)
{
const struct blk_mq_ops *const mq_ops = rq->q->mq_ops;
@@ -283,6 +316,8 @@ int __blk_mq_debugfs_rq_show(struct seq_file *m, struct request *rq)
seq_puts(m, ", .rq_flags=");
blk_flags_show(m, (__force unsigned int)rq->rq_flags, rqf_name,
ARRAY_SIZE(rqf_name));
+ seq_puts(m, ", .atomic_flags=");
+ blk_flags_show(m, rq->atomic_flags, rqaf_name, ARRAY_SIZE(rqaf_name));
seq_printf(m, ", .tag=%d, .internal_tag=%d", rq->tag,
rq->internal_tag);
if (mq_ops->show_rq)
@@ -298,6 +333,37 @@ int blk_mq_debugfs_rq_show(struct seq_file *m, void *v)
}
EXPORT_SYMBOL_GPL(blk_mq_debugfs_rq_show);
+static void *queue_requeue_list_start(struct seq_file *m, loff_t *pos)
+ __acquires(&q->requeue_lock)
+{
+ struct request_queue *q = m->private;
+
+ spin_lock_irq(&q->requeue_lock);
+ return seq_list_start(&q->requeue_list, *pos);
+}
+
+static void *queue_requeue_list_next(struct seq_file *m, void *v, loff_t *pos)
+{
+ struct request_queue *q = m->private;
+
+ return seq_list_next(v, &q->requeue_list, pos);
+}
+
+static void queue_requeue_list_stop(struct seq_file *m, void *v)
+ __releases(&q->requeue_lock)
+{
+ struct request_queue *q = m->private;
+
+ spin_unlock_irq(&q->requeue_lock);
+}
+
+static const struct seq_operations queue_requeue_list_seq_ops = {
+ .start = queue_requeue_list_start,
+ .next = queue_requeue_list_next,
+ .stop = queue_requeue_list_stop,
+ .show = blk_mq_debugfs_rq_show,
+};
+
static void *hctx_dispatch_start(struct seq_file *m, loff_t *pos)
__acquires(&hctx->lock)
{
@@ -329,6 +395,36 @@ static const struct seq_operations hctx_dispatch_seq_ops = {
.show = blk_mq_debugfs_rq_show,
};
+struct show_busy_params {
+ struct seq_file *m;
+ struct blk_mq_hw_ctx *hctx;
+};
+
+/*
+ * Note: the state of a request may change while this function is in progress,
+ * e.g. due to a concurrent blk_mq_finish_request() call.
+ */
+static void hctx_show_busy_rq(struct request *rq, void *data, bool reserved)
+{
+ const struct show_busy_params *params = data;
+
+ if (blk_mq_map_queue(rq->q, rq->mq_ctx->cpu) == params->hctx &&
+ test_bit(REQ_ATOM_STARTED, &rq->atomic_flags))
+ __blk_mq_debugfs_rq_show(params->m,
+ list_entry_rq(&rq->queuelist));
+}
+
+static int hctx_busy_show(void *data, struct seq_file *m)
+{
+ struct blk_mq_hw_ctx *hctx = data;
+ struct show_busy_params params = { .m = m, .hctx = hctx };
+
+ blk_mq_tagset_busy_iter(hctx->queue->tag_set, hctx_show_busy_rq,
+ &params);
+
+ return 0;
+}
+
static int hctx_ctx_map_show(void *data, struct seq_file *m)
{
struct blk_mq_hw_ctx *hctx = data;
@@ -655,7 +751,9 @@ const struct file_operations blk_mq_debugfs_fops = {
static const struct blk_mq_debugfs_attr blk_mq_debugfs_queue_attrs[] = {
{"poll_stat", 0400, queue_poll_stat_show},
+ {"requeue_list", 0400, .seq_ops = &queue_requeue_list_seq_ops},
{"state", 0600, queue_state_show, queue_state_write},
+ {"write_hints", 0600, queue_write_hint_show, queue_write_hint_store},
{},
};
@@ -663,6 +761,7 @@ static const struct blk_mq_debugfs_attr blk_mq_debugfs_hctx_attrs[] = {
{"state", 0400, hctx_state_show},
{"flags", 0400, hctx_flags_show},
{"dispatch", 0400, .seq_ops = &hctx_dispatch_seq_ops},
+ {"busy", 0400, hctx_busy_show},
{"ctx_map", 0400, hctx_ctx_map_show},
{"tags", 0400, hctx_tags_show},
{"tags_bitmap", 0400, hctx_tags_bitmap_show},
diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index 0ded5e846335..7f0dc48ffb40 100644
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -31,11 +31,10 @@ void blk_mq_sched_free_hctx_data(struct request_queue *q,
}
EXPORT_SYMBOL_GPL(blk_mq_sched_free_hctx_data);
-static void __blk_mq_sched_assign_ioc(struct request_queue *q,
- struct request *rq,
- struct bio *bio,
- struct io_context *ioc)
+void blk_mq_sched_assign_ioc(struct request *rq, struct bio *bio)
{
+ struct request_queue *q = rq->q;
+ struct io_context *ioc = rq_ioc(bio);
struct io_cq *icq;
spin_lock_irq(q->queue_lock);
@@ -47,25 +46,8 @@ static void __blk_mq_sched_assign_ioc(struct request_queue *q,
if (!icq)
return;
}
-
+ get_io_context(icq->ioc);
rq->elv.icq = icq;
- if (!blk_mq_sched_get_rq_priv(q, rq, bio)) {
- rq->rq_flags |= RQF_ELVPRIV;
- get_io_context(icq->ioc);
- return;
- }
-
- rq->elv.icq = NULL;
-}
-
-static void blk_mq_sched_assign_ioc(struct request_queue *q,
- struct request *rq, struct bio *bio)
-{
- struct io_context *ioc;
-
- ioc = rq_ioc(bio);
- if (ioc)
- __blk_mq_sched_assign_ioc(q, rq, bio, ioc);
}
/*
@@ -107,71 +89,6 @@ static bool blk_mq_sched_restart_hctx(struct blk_mq_hw_ctx *hctx)
return false;
}
-struct request *blk_mq_sched_get_request(struct request_queue *q,
- struct bio *bio,
- unsigned int op,
- struct blk_mq_alloc_data *data)
-{
- struct elevator_queue *e = q->elevator;
- struct request *rq;
-
- blk_queue_enter_live(q);
- data->q = q;
- if (likely(!data->ctx))
- data->ctx = blk_mq_get_ctx(q);
- if (likely(!data->hctx))
- data->hctx = blk_mq_map_queue(q, data->ctx->cpu);
-
- if (e) {
- data->flags |= BLK_MQ_REQ_INTERNAL;
-
- /*
- * Flush requests are special and go directly to the
- * dispatch list.
- */
- if (!op_is_flush(op) && e->type->ops.mq.get_request) {
- rq = e->type->ops.mq.get_request(q, op, data);
- if (rq)
- rq->rq_flags |= RQF_QUEUED;
- } else
- rq = __blk_mq_alloc_request(data, op);
- } else {
- rq = __blk_mq_alloc_request(data, op);
- }
-
- if (rq) {
- if (!op_is_flush(op)) {
- rq->elv.icq = NULL;
- if (e && e->type->icq_cache)
- blk_mq_sched_assign_ioc(q, rq, bio);
- }
- data->hctx->queued++;
- return rq;
- }
-
- blk_queue_exit(q);
- return NULL;
-}
-
-void blk_mq_sched_put_request(struct request *rq)
-{
- struct request_queue *q = rq->q;
- struct elevator_queue *e = q->elevator;
-
- if (rq->rq_flags & RQF_ELVPRIV) {
- blk_mq_sched_put_rq_priv(rq->q, rq);
- if (rq->elv.icq) {
- put_io_context(rq->elv.icq->ioc);
- rq->elv.icq = NULL;
- }
- }
-
- if ((rq->rq_flags & RQF_QUEUED) && e && e->type->ops.mq.put_request)
- e->type->ops.mq.put_request(rq);
- else
- blk_mq_finish_request(rq);
-}
-
void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)
{
struct request_queue *q = hctx->queue;
@@ -180,7 +97,8 @@ void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)
bool did_work = false;
LIST_HEAD(rq_list);
- if (unlikely(blk_mq_hctx_stopped(hctx)))
+ /* RCU or SRCU read lock is needed before checking quiesced flag */
+ if (unlikely(blk_mq_hctx_stopped(hctx) || blk_queue_quiesced(q)))
return;
hctx->run++;
@@ -260,19 +178,73 @@ bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio,
}
EXPORT_SYMBOL_GPL(blk_mq_sched_try_merge);
+/*
+ * Reverse check our software queue for entries that we could potentially
+ * merge with. Currently includes a hand-wavy stop count of 8, to not spend
+ * too much time checking for merges.
+ */
+static bool blk_mq_attempt_merge(struct request_queue *q,
+ struct blk_mq_ctx *ctx, struct bio *bio)
+{
+ struct request *rq;
+ int checked = 8;
+
+ lockdep_assert_held(&ctx->lock);
+
+ list_for_each_entry_reverse(rq, &ctx->rq_list, queuelist) {
+ bool merged = false;
+
+ if (!checked--)
+ break;
+
+ if (!blk_rq_merge_ok(rq, bio))
+ continue;
+
+ switch (blk_try_merge(rq, bio)) {
+ case ELEVATOR_BACK_MERGE:
+ if (blk_mq_sched_allow_merge(q, rq, bio))
+ merged = bio_attempt_back_merge(q, rq, bio);
+ break;
+ case ELEVATOR_FRONT_MERGE:
+ if (blk_mq_sched_allow_merge(q, rq, bio))
+ merged = bio_attempt_front_merge(q, rq, bio);
+ break;
+ case ELEVATOR_DISCARD_MERGE:
+ merged = bio_attempt_discard_merge(q, rq, bio);
+ break;
+ default:
+ continue;
+ }
+
+ if (merged)
+ ctx->rq_merged++;
+ return merged;
+ }
+
+ return false;
+}
+
bool __blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio)
{
struct elevator_queue *e = q->elevator;
+ struct blk_mq_ctx *ctx = blk_mq_get_ctx(q);
+ struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu);
+ bool ret = false;
- if (e->type->ops.mq.bio_merge) {
- struct blk_mq_ctx *ctx = blk_mq_get_ctx(q);
- struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu);
-
+ if (e && e->type->ops.mq.bio_merge) {
blk_mq_put_ctx(ctx);
return e->type->ops.mq.bio_merge(hctx, bio);
}
- return false;
+ if (hctx->flags & BLK_MQ_F_SHOULD_MERGE) {
+ /* default per sw-queue merge */
+ spin_lock(&ctx->lock);
+ ret = blk_mq_attempt_merge(q, ctx, bio);
+ spin_unlock(&ctx->lock);
+ }
+
+ blk_mq_put_ctx(ctx);
+ return ret;
}
bool blk_mq_sched_try_insert_merge(struct request_queue *q, struct request *rq)
diff --git a/block/blk-mq-sched.h b/block/blk-mq-sched.h
index 5007edece51a..9267d0b7c197 100644
--- a/block/blk-mq-sched.h
+++ b/block/blk-mq-sched.h
@@ -7,8 +7,7 @@
void blk_mq_sched_free_hctx_data(struct request_queue *q,
void (*exit)(struct blk_mq_hw_ctx *));
-struct request *blk_mq_sched_get_request(struct request_queue *q, struct bio *bio, unsigned int op, struct blk_mq_alloc_data *data);
-void blk_mq_sched_put_request(struct request *rq);
+void blk_mq_sched_assign_ioc(struct request *rq, struct bio *bio);
void blk_mq_sched_request_inserted(struct request *rq);
bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio,
@@ -38,35 +37,12 @@ int blk_mq_sched_init(struct request_queue *q);
static inline bool
blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio)
{
- struct elevator_queue *e = q->elevator;
-
- if (!e || blk_queue_nomerges(q) || !bio_mergeable(bio))
+ if (blk_queue_nomerges(q) || !bio_mergeable(bio))
return false;
return __blk_mq_sched_bio_merge(q, bio);
}
-static inline int blk_mq_sched_get_rq_priv(struct request_queue *q,
- struct request *rq,
- struct bio *bio)
-{
- struct elevator_queue *e = q->elevator;
-
- if (e && e->type->ops.mq.get_rq_priv)
- return e->type->ops.mq.get_rq_priv(q, rq, bio);
-
- return 0;
-}
-
-static inline void blk_mq_sched_put_rq_priv(struct request_queue *q,
- struct request *rq)
-{
- struct elevator_queue *e = q->elevator;
-
- if (e && e->type->ops.mq.put_rq_priv)
- e->type->ops.mq.put_rq_priv(q, rq);
-}
-
static inline bool
blk_mq_sched_allow_merge(struct request_queue *q, struct request *rq,
struct bio *bio)
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 958cedaff8b8..05dfa3f270ae 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -42,7 +42,6 @@ static LIST_HEAD(all_q_list);
static void blk_mq_poll_stats_start(struct request_queue *q);
static void blk_mq_poll_stats_fn(struct blk_stat_callback *cb);
-static void __blk_mq_stop_hw_queues(struct request_queue *q, bool sync);
static int blk_mq_poll_stats_bkt(const struct request *rq)
{
@@ -154,13 +153,28 @@ void blk_mq_unfreeze_queue(struct request_queue *q)
}
EXPORT_SYMBOL_GPL(blk_mq_unfreeze_queue);
+/*
+ * FIXME: replace the scsi_internal_device_*block_nowait() calls in the
+ * mpt3sas driver such that this function can be removed.
+ */
+void blk_mq_quiesce_queue_nowait(struct request_queue *q)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(q->queue_lock, flags);
+ queue_flag_set(QUEUE_FLAG_QUIESCED, q);
+ spin_unlock_irqrestore(q->queue_lock, flags);
+}
+EXPORT_SYMBOL_GPL(blk_mq_quiesce_queue_nowait);
+
/**
- * blk_mq_quiesce_queue() - wait until all ongoing queue_rq calls have finished
+ * blk_mq_quiesce_queue() - wait until all ongoing dispatches have finished
* @q: request queue.
*
* Note: this function does not prevent that the struct request end_io()
- * callback function is invoked. Additionally, it is not prevented that
- * new queue_rq() calls occur unless the queue has been stopped first.
+ * callback function is invoked. Once this function is returned, we make
+ * sure no dispatch can happen until the queue is unquiesced via
+ * blk_mq_unquiesce_queue().
*/
void blk_mq_quiesce_queue(struct request_queue *q)
{
@@ -168,11 +182,11 @@ void blk_mq_quiesce_queue(struct request_queue *q)
unsigned int i;
bool rcu = false;
- __blk_mq_stop_hw_queues(q, true);
+ blk_mq_quiesce_queue_nowait(q);
queue_for_each_hw_ctx(q, hctx, i) {
if (hctx->flags & BLK_MQ_F_BLOCKING)
- synchronize_srcu(&hctx->queue_rq_srcu);
+ synchronize_srcu(hctx->queue_rq_srcu);
else
rcu = true;
}
@@ -181,6 +195,26 @@ void blk_mq_quiesce_queue(struct request_queue *q)
}
EXPORT_SYMBOL_GPL(blk_mq_quiesce_queue);
+/*
+ * blk_mq_unquiesce_queue() - counterpart of blk_mq_quiesce_queue()
+ * @q: request queue.
+ *
+ * This function recovers queue into the state before quiescing
+ * which is done by blk_mq_quiesce_queue.
+ */
+void blk_mq_unquiesce_queue(struct request_queue *q)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(q->queue_lock, flags);
+ queue_flag_clear(QUEUE_FLAG_QUIESCED, q);
+ spin_unlock_irqrestore(q->queue_lock, flags);
+
+ /* dispatch requests which are inserted during quiescing */
+ blk_mq_run_hw_queues(q, true);
+}
+EXPORT_SYMBOL_GPL(blk_mq_unquiesce_queue);
+
void blk_mq_wake_waiters(struct request_queue *q)
{
struct blk_mq_hw_ctx *hctx;
@@ -204,15 +238,33 @@ bool blk_mq_can_queue(struct blk_mq_hw_ctx *hctx)
}
EXPORT_SYMBOL(blk_mq_can_queue);
-void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx,
- struct request *rq, unsigned int op)
+static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
+ unsigned int tag, unsigned int op)
{
+ struct blk_mq_tags *tags = blk_mq_tags_from_data(data);
+ struct request *rq = tags->static_rqs[tag];
+
+ rq->rq_flags = 0;
+
+ if (data->flags & BLK_MQ_REQ_INTERNAL) {
+ rq->tag = -1;
+ rq->internal_tag = tag;
+ } else {
+ if (blk_mq_tag_busy(data->hctx)) {
+ rq->rq_flags = RQF_MQ_INFLIGHT;
+ atomic_inc(&data->hctx->nr_active);
+ }
+ rq->tag = tag;
+ rq->internal_tag = -1;
+ data->hctx->tags->rqs[rq->tag] = rq;
+ }
+
INIT_LIST_HEAD(&rq->queuelist);
/* csd/requeue_work/fifo_time is initialized before use */
- rq->q = q;
- rq->mq_ctx = ctx;
+ rq->q = data->q;
+ rq->mq_ctx = data->ctx;
rq->cmd_flags = op;
- if (blk_queue_io_stat(q))
+ if (blk_queue_io_stat(data->q))
rq->rq_flags |= RQF_IO_STAT;
/* do not touch atomic flags, it needs atomic ops against the timer */
rq->cpu = -1;
@@ -241,44 +293,60 @@ void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx,
rq->end_io_data = NULL;
rq->next_rq = NULL;
- ctx->rq_dispatched[op_is_sync(op)]++;
+ data->ctx->rq_dispatched[op_is_sync(op)]++;
+ return rq;
}
-EXPORT_SYMBOL_GPL(blk_mq_rq_ctx_init);
-struct request *__blk_mq_alloc_request(struct blk_mq_alloc_data *data,
- unsigned int op)
+static struct request *blk_mq_get_request(struct request_queue *q,
+ struct bio *bio, unsigned int op,
+ struct blk_mq_alloc_data *data)
{
+ struct elevator_queue *e = q->elevator;
struct request *rq;
unsigned int tag;
- tag = blk_mq_get_tag(data);
- if (tag != BLK_MQ_TAG_FAIL) {
- struct blk_mq_tags *tags = blk_mq_tags_from_data(data);
+ blk_queue_enter_live(q);
+ data->q = q;
+ if (likely(!data->ctx))
+ data->ctx = blk_mq_get_ctx(q);
+ if (likely(!data->hctx))
+ data->hctx = blk_mq_map_queue(q, data->ctx->cpu);
+ if (op & REQ_NOWAIT)
+ data->flags |= BLK_MQ_REQ_NOWAIT;
- rq = tags->static_rqs[tag];
+ if (e) {
+ data->flags |= BLK_MQ_REQ_INTERNAL;
- if (data->flags & BLK_MQ_REQ_INTERNAL) {
- rq->tag = -1;
- rq->internal_tag = tag;
- } else {
- if (blk_mq_tag_busy(data->hctx)) {
- rq->rq_flags = RQF_MQ_INFLIGHT;
- atomic_inc(&data->hctx->nr_active);
- }
- rq->tag = tag;
- rq->internal_tag = -1;
- data->hctx->tags->rqs[rq->tag] = rq;
- }
+ /*
+ * Flush requests are special and go directly to the
+ * dispatch list.
+ */
+ if (!op_is_flush(op) && e->type->ops.mq.limit_depth)
+ e->type->ops.mq.limit_depth(op, data);
+ }
- blk_mq_rq_ctx_init(data->q, data->ctx, rq, op);
- return rq;
+ tag = blk_mq_get_tag(data);
+ if (tag == BLK_MQ_TAG_FAIL) {
+ blk_queue_exit(q);
+ return NULL;
}
- return NULL;
+ rq = blk_mq_rq_ctx_init(data, tag, op);
+ if (!op_is_flush(op)) {
+ rq->elv.icq = NULL;
+ if (e && e->type->ops.mq.prepare_request) {
+ if (e->type->icq_cache && rq_ioc(bio))
+ blk_mq_sched_assign_ioc(rq, bio);
+
+ e->type->ops.mq.prepare_request(rq, bio);
+ rq->rq_flags |= RQF_ELVPRIV;
+ }
+ }
+ data->hctx->queued++;
+ return rq;
}
-EXPORT_SYMBOL_GPL(__blk_mq_alloc_request);
-struct request *blk_mq_alloc_request(struct request_queue *q, int rw,
+struct request *blk_mq_alloc_request(struct request_queue *q, unsigned int op,
unsigned int flags)
{
struct blk_mq_alloc_data alloc_data = { .flags = flags };
@@ -289,7 +357,7 @@ struct request *blk_mq_alloc_request(struct request_queue *q, int rw,
if (ret)
return ERR_PTR(ret);
- rq = blk_mq_sched_get_request(q, NULL, rw, &alloc_data);
+ rq = blk_mq_get_request(q, NULL, op, &alloc_data);
blk_mq_put_ctx(alloc_data.ctx);
blk_queue_exit(q);
@@ -304,8 +372,8 @@ struct request *blk_mq_alloc_request(struct request_queue *q, int rw,
}
EXPORT_SYMBOL(blk_mq_alloc_request);
-struct request *blk_mq_alloc_request_hctx(struct request_queue *q, int rw,
- unsigned int flags, unsigned int hctx_idx)
+struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
+ unsigned int op, unsigned int flags, unsigned int hctx_idx)
{
struct blk_mq_alloc_data alloc_data = { .flags = flags };
struct request *rq;
@@ -340,7 +408,7 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q, int rw,
cpu = cpumask_first(alloc_data.hctx->cpumask);
alloc_data.ctx = __blk_mq_get_ctx(q, cpu);
- rq = blk_mq_sched_get_request(q, NULL, rw, &alloc_data);
+ rq = blk_mq_get_request(q, NULL, op, &alloc_data);
blk_queue_exit(q);
@@ -351,17 +419,28 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q, int rw,
}
EXPORT_SYMBOL_GPL(blk_mq_alloc_request_hctx);
-void __blk_mq_finish_request(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
- struct request *rq)
+void blk_mq_free_request(struct request *rq)
{
- const int sched_tag = rq->internal_tag;
struct request_queue *q = rq->q;
+ struct elevator_queue *e = q->elevator;
+ struct blk_mq_ctx *ctx = rq->mq_ctx;
+ struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu);
+ const int sched_tag = rq->internal_tag;
+ if (rq->rq_flags & RQF_ELVPRIV) {
+ if (e && e->type->ops.mq.finish_request)
+ e->type->ops.mq.finish_request(rq);
+ if (rq->elv.icq) {
+ put_io_context(rq->elv.icq->ioc);
+ rq->elv.icq = NULL;
+ }
+ }
+
+ ctx->rq_completed[rq_is_sync(rq)]++;
if (rq->rq_flags & RQF_MQ_INFLIGHT)
atomic_dec(&hctx->nr_active);
wbt_done(q->rq_wb, &rq->issue_stat);
- rq->rq_flags = 0;
clear_bit(REQ_ATOM_STARTED, &rq->atomic_flags);
clear_bit(REQ_ATOM_POLL_SLEPT, &rq->atomic_flags);
@@ -372,29 +451,9 @@ void __blk_mq_finish_request(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
blk_mq_sched_restart(hctx);
blk_queue_exit(q);
}
-
-static void blk_mq_finish_hctx_request(struct blk_mq_hw_ctx *hctx,
- struct request *rq)
-{
- struct blk_mq_ctx *ctx = rq->mq_ctx;
-
- ctx->rq_completed[rq_is_sync(rq)]++;
- __blk_mq_finish_request(hctx, ctx, rq);
-}
-
-void blk_mq_finish_request(struct request *rq)
-{
- blk_mq_finish_hctx_request(blk_mq_map_queue(rq->q, rq->mq_ctx->cpu), rq);
-}
-EXPORT_SYMBOL_GPL(blk_mq_finish_request);
-
-void blk_mq_free_request(struct request *rq)
-{
- blk_mq_sched_put_request(rq);
-}
EXPORT_SYMBOL_GPL(blk_mq_free_request);
-inline void __blk_mq_end_request(struct request *rq, int error)
+inline void __blk_mq_end_request(struct request *rq, blk_status_t error)
{
blk_account_io_done(rq);
@@ -409,7 +468,7 @@ inline void __blk_mq_end_request(struct request *rq, int error)
}
EXPORT_SYMBOL(__blk_mq_end_request);
-void blk_mq_end_request(struct request *rq, int error)
+void blk_mq_end_request(struct request *rq, blk_status_t error)
{
if (blk_update_request(rq, error, blk_rq_bytes(rq)))
BUG();
@@ -753,50 +812,6 @@ static void blk_mq_timeout_work(struct work_struct *work)
blk_queue_exit(q);
}
-/*
- * Reverse check our software queue for entries that we could potentially
- * merge with. Currently includes a hand-wavy stop count of 8, to not spend
- * too much time checking for merges.
- */
-static bool blk_mq_attempt_merge(struct request_queue *q,
- struct blk_mq_ctx *ctx, struct bio *bio)
-{
- struct request *rq;
- int checked = 8;
-
- list_for_each_entry_reverse(rq, &ctx->rq_list, queuelist) {
- bool merged = false;
-
- if (!checked--)
- break;
-
- if (!blk_rq_merge_ok(rq, bio))
- continue;
-
- switch (blk_try_merge(rq, bio)) {
- case ELEVATOR_BACK_MERGE:
- if (blk_mq_sched_allow_merge(q, rq, bio))
- merged = bio_attempt_back_merge(q, rq, bio);
- break;
- case ELEVATOR_FRONT_MERGE:
- if (blk_mq_sched_allow_merge(q, rq, bio))
- merged = bio_attempt_front_merge(q, rq, bio);
- break;
- case ELEVATOR_DISCARD_MERGE:
- merged = bio_attempt_discard_merge(q, rq, bio);
- break;
- default:
- continue;
- }
-
- if (merged)
- ctx->rq_merged++;
- return merged;
- }
-
- return false;
-}
-
struct flush_busy_ctx_data {
struct blk_mq_hw_ctx *hctx;
struct list_head *list;
@@ -968,7 +983,7 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list)
{
struct blk_mq_hw_ctx *hctx;
struct request *rq;
- int errors, queued, ret = BLK_MQ_RQ_QUEUE_OK;
+ int errors, queued;
if (list_empty(list))
return false;
@@ -979,6 +994,7 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list)
errors = queued = 0;
do {
struct blk_mq_queue_data bd;
+ blk_status_t ret;
rq = list_first_entry(list, struct request, queuelist);
if (!blk_mq_get_driver_tag(rq, &hctx, false)) {
@@ -1019,25 +1035,20 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list)
}
ret = q->mq_ops->queue_rq(hctx, &bd);
- switch (ret) {
- case BLK_MQ_RQ_QUEUE_OK:
- queued++;
- break;
- case BLK_MQ_RQ_QUEUE_BUSY:
+ if (ret == BLK_STS_RESOURCE) {
blk_mq_put_driver_tag_hctx(hctx, rq);
list_add(&rq->queuelist, list);
__blk_mq_requeue_request(rq);
break;
- default:
- pr_err("blk-mq: bad return on queue: %d\n", ret);
- case BLK_MQ_RQ_QUEUE_ERROR:
+ }
+
+ if (unlikely(ret != BLK_STS_OK)) {
errors++;
- blk_mq_end_request(rq, -EIO);
- break;
+ blk_mq_end_request(rq, BLK_STS_IOERR);
+ continue;
}
- if (ret == BLK_MQ_RQ_QUEUE_BUSY)
- break;
+ queued++;
} while (!list_empty(list));
hctx->dispatched[queued_to_index(queued)]++;
@@ -1075,7 +1086,7 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list)
* - blk_mq_run_hw_queue() checks whether or not a queue has
* been stopped before rerunning a queue.
* - Some but not all block drivers stop a queue before
- * returning BLK_MQ_RQ_QUEUE_BUSY. Two exceptions are scsi-mq
+ * returning BLK_STS_RESOURCE. Two exceptions are scsi-mq
* and dm-rq.
*/
if (!blk_mq_sched_needs_restart(hctx) &&
@@ -1100,9 +1111,9 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
} else {
might_sleep();
- srcu_idx = srcu_read_lock(&hctx->queue_rq_srcu);
+ srcu_idx = srcu_read_lock(hctx->queue_rq_srcu);
blk_mq_sched_dispatch_requests(hctx);
- srcu_read_unlock(&hctx->queue_rq_srcu, srcu_idx);
+ srcu_read_unlock(hctx->queue_rq_srcu, srcu_idx);
}
}
@@ -1134,8 +1145,10 @@ static int blk_mq_hctx_next_cpu(struct blk_mq_hw_ctx *hctx)
static void __blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async,
unsigned long msecs)
{
- if (unlikely(blk_mq_hctx_stopped(hctx) ||
- !blk_mq_hw_queue_mapped(hctx)))
+ if (WARN_ON_ONCE(!blk_mq_hw_queue_mapped(hctx)))
+ return;
+
+ if (unlikely(blk_mq_hctx_stopped(hctx)))
return;
if (!async && !(hctx->flags & BLK_MQ_F_BLOCKING)) {
@@ -1201,34 +1214,39 @@ bool blk_mq_queue_stopped(struct request_queue *q)
}
EXPORT_SYMBOL(blk_mq_queue_stopped);
-static void __blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx, bool sync)
+/*
+ * This function is often used for pausing .queue_rq() by driver when
+ * there isn't enough resource or some conditions aren't satisfied, and
+ * BLK_MQ_RQ_QUEUE_BUSY is usually returned.
+ *
+ * We do not guarantee that dispatch can be drained or blocked
+ * after blk_mq_stop_hw_queue() returns. Please use
+ * blk_mq_quiesce_queue() for that requirement.
+ */
+void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx)
{
- if (sync)
- cancel_delayed_work_sync(&hctx->run_work);
- else
- cancel_delayed_work(&hctx->run_work);
+ cancel_delayed_work(&hctx->run_work);
set_bit(BLK_MQ_S_STOPPED, &hctx->state);
}
-
-void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx)
-{
- __blk_mq_stop_hw_queue(hctx, false);
-}
EXPORT_SYMBOL(blk_mq_stop_hw_queue);
-static void __blk_mq_stop_hw_queues(struct request_queue *q, bool sync)
+/*
+ * This function is often used for pausing .queue_rq() by driver when
+ * there isn't enough resource or some conditions aren't satisfied, and
+ * BLK_MQ_RQ_QUEUE_BUSY is usually returned.
+ *
+ * We do not guarantee that dispatch can be drained or blocked
+ * after blk_mq_stop_hw_queues() returns. Please use
+ * blk_mq_quiesce_queue() for that requirement.
+ */
+void blk_mq_stop_hw_queues(struct request_queue *q)
{
struct blk_mq_hw_ctx *hctx;
int i;
queue_for_each_hw_ctx(q, hctx, i)
- __blk_mq_stop_hw_queue(hctx, sync);
-}
-
-void blk_mq_stop_hw_queues(struct request_queue *q)
-{
- __blk_mq_stop_hw_queues(q, false);
+ blk_mq_stop_hw_queue(hctx);
}
EXPORT_SYMBOL(blk_mq_stop_hw_queues);
@@ -1295,7 +1313,7 @@ static void blk_mq_run_work_fn(struct work_struct *work)
void blk_mq_delay_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs)
{
- if (unlikely(!blk_mq_hw_queue_mapped(hctx)))
+ if (WARN_ON_ONCE(!blk_mq_hw_queue_mapped(hctx)))
return;
/*
@@ -1317,6 +1335,8 @@ static inline void __blk_mq_insert_req_list(struct blk_mq_hw_ctx *hctx,
{
struct blk_mq_ctx *ctx = rq->mq_ctx;
+ lockdep_assert_held(&ctx->lock);
+
trace_block_rq_insert(hctx->queue, rq);
if (at_head)
@@ -1330,6 +1350,8 @@ void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
{
struct blk_mq_ctx *ctx = rq->mq_ctx;
+ lockdep_assert_held(&ctx->lock);
+
__blk_mq_insert_req_list(hctx, rq, at_head);
blk_mq_hctx_mark_pending(hctx, ctx);
}
@@ -1427,30 +1449,13 @@ static inline bool hctx_allow_merges(struct blk_mq_hw_ctx *hctx)
!blk_queue_nomerges(hctx->queue);
}
-static inline bool blk_mq_merge_queue_io(struct blk_mq_hw_ctx *hctx,
- struct blk_mq_ctx *ctx,
- struct request *rq, struct bio *bio)
+static inline void blk_mq_queue_io(struct blk_mq_hw_ctx *hctx,
+ struct blk_mq_ctx *ctx,
+ struct request *rq)
{
- if (!hctx_allow_merges(hctx) || !bio_mergeable(bio)) {
- blk_mq_bio_to_request(rq, bio);
- spin_lock(&ctx->lock);
-insert_rq:
- __blk_mq_insert_request(hctx, rq, false);
- spin_unlock(&ctx->lock);
- return false;
- } else {
- struct request_queue *q = hctx->queue;
-
- spin_lock(&ctx->lock);
- if (!blk_mq_attempt_merge(q, ctx, bio)) {
- blk_mq_bio_to_request(rq, bio);
- goto insert_rq;
- }
-
- spin_unlock(&ctx->lock);
- __blk_mq_finish_request(hctx, ctx, rq);
- return true;
- }
+ spin_lock(&ctx->lock);
+ __blk_mq_insert_request(hctx, rq, false);
+ spin_unlock(&ctx->lock);
}
static blk_qc_t request_to_qc_t(struct blk_mq_hw_ctx *hctx, struct request *rq)
@@ -1471,10 +1476,11 @@ static void __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
.last = true,
};
blk_qc_t new_cookie;
- int ret;
+ blk_status_t ret;
bool run_queue = true;
- if (blk_mq_hctx_stopped(hctx)) {
+ /* RCU or SRCU read lock is needed before checking quiesced flag */
+ if (blk_mq_hctx_stopped(hctx) || blk_queue_quiesced(q)) {
run_queue = false;
goto insert;
}
@@ -1493,18 +1499,19 @@ static void __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
* would have done
*/
ret = q->mq_ops->queue_rq(hctx, &bd);
- if (ret == BLK_MQ_RQ_QUEUE_OK) {
+ switch (ret) {
+ case BLK_STS_OK:
*cookie = new_cookie;
return;
- }
-
- if (ret == BLK_MQ_RQ_QUEUE_ERROR) {
+ case BLK_STS_RESOURCE:
+ __blk_mq_requeue_request(rq);
+ goto insert;
+ default:
*cookie = BLK_QC_T_NONE;
- blk_mq_end_request(rq, -EIO);
+ blk_mq_end_request(rq, ret);
return;
}
- __blk_mq_requeue_request(rq);
insert:
blk_mq_sched_insert_request(rq, false, run_queue, false, may_sleep);
}
@@ -1521,9 +1528,9 @@ static void blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
might_sleep();
- srcu_idx = srcu_read_lock(&hctx->queue_rq_srcu);
+ srcu_idx = srcu_read_lock(hctx->queue_rq_srcu);
__blk_mq_try_issue_directly(hctx, rq, cookie, true);
- srcu_read_unlock(&hctx->queue_rq_srcu, srcu_idx);
+ srcu_read_unlock(hctx->queue_rq_srcu, srcu_idx);
}
}
@@ -1541,7 +1548,7 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
blk_queue_bounce(q, &bio);
- blk_queue_split(q, &bio, q->bio_split);
+ blk_queue_split(q, &bio);
if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) {
bio_io_error(bio);
@@ -1559,9 +1566,11 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
trace_block_getrq(q, bio, bio->bi_opf);
- rq = blk_mq_sched_get_request(q, bio, bio->bi_opf, &data);
+ rq = blk_mq_get_request(q, bio, bio->bi_opf, &data);
if (unlikely(!rq)) {
__wbt_done(q->rq_wb, wb_acct);
+ if (bio->bi_opf & REQ_NOWAIT)
+ bio_wouldblock_error(bio);
return BLK_QC_T_NONE;
}
@@ -1639,11 +1648,12 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
blk_mq_put_ctx(data.ctx);
blk_mq_bio_to_request(rq, bio);
blk_mq_sched_insert_request(rq, false, true, true, true);
- } else if (!blk_mq_merge_queue_io(data.hctx, data.ctx, rq, bio)) {
+ } else {
blk_mq_put_ctx(data.ctx);
+ blk_mq_bio_to_request(rq, bio);
+ blk_mq_queue_io(data.hctx, data.ctx, rq);
blk_mq_run_hw_queue(data.hctx, true);
- } else
- blk_mq_put_ctx(data.ctx);
+ }
return cookie;
}
@@ -1866,7 +1876,7 @@ static void blk_mq_exit_hctx(struct request_queue *q,
set->ops->exit_hctx(hctx, hctx_idx);
if (hctx->flags & BLK_MQ_F_BLOCKING)
- cleanup_srcu_struct(&hctx->queue_rq_srcu);
+ cleanup_srcu_struct(hctx->queue_rq_srcu);
blk_mq_remove_cpuhp(hctx);
blk_free_flush_queue(hctx->fq);
@@ -1900,7 +1910,6 @@ static int blk_mq_init_hctx(struct request_queue *q,
spin_lock_init(&hctx->lock);
INIT_LIST_HEAD(&hctx->dispatch);
hctx->queue = q;
- hctx->queue_num = hctx_idx;
hctx->flags = set->flags & ~BLK_MQ_F_TAG_SHARED;
cpuhp_state_add_instance_nocalls(CPUHP_BLK_MQ_DEAD, &hctx->cpuhp_dead);
@@ -1939,7 +1948,7 @@ static int blk_mq_init_hctx(struct request_queue *q,
goto free_fq;
if (hctx->flags & BLK_MQ_F_BLOCKING)
- init_srcu_struct(&hctx->queue_rq_srcu);
+ init_srcu_struct(hctx->queue_rq_srcu);
blk_mq_debugfs_register_hctx(q, hctx);
@@ -2224,6 +2233,20 @@ struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set)
}
EXPORT_SYMBOL(blk_mq_init_queue);
+static int blk_mq_hw_ctx_size(struct blk_mq_tag_set *tag_set)
+{
+ int hw_ctx_size = sizeof(struct blk_mq_hw_ctx);
+
+ BUILD_BUG_ON(ALIGN(offsetof(struct blk_mq_hw_ctx, queue_rq_srcu),
+ __alignof__(struct blk_mq_hw_ctx)) !=
+ sizeof(struct blk_mq_hw_ctx));
+
+ if (tag_set->flags & BLK_MQ_F_BLOCKING)
+ hw_ctx_size += sizeof(struct srcu_struct);
+
+ return hw_ctx_size;
+}
+
static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
struct request_queue *q)
{
@@ -2238,7 +2261,7 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
continue;
node = blk_mq_hw_queue_to_node(q->mq_map, i);
- hctxs[i] = kzalloc_node(sizeof(struct blk_mq_hw_ctx),
+ hctxs[i] = kzalloc_node(blk_mq_hw_ctx_size(set),
GFP_KERNEL, node);
if (!hctxs[i])
break;
diff --git a/block/blk-mq.h b/block/blk-mq.h
index cc67b48e3551..1a06fdf9fd4d 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -128,17 +128,6 @@ static inline struct blk_mq_tags *blk_mq_tags_from_data(struct blk_mq_alloc_data
return data->hctx->tags;
}
-/*
- * Internal helpers for request allocation/init/free
- */
-void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx,
- struct request *rq, unsigned int op);
-void __blk_mq_finish_request(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
- struct request *rq);
-void blk_mq_finish_request(struct request *rq);
-struct request *__blk_mq_alloc_request(struct blk_mq_alloc_data *data,
- unsigned int op);
-
static inline bool blk_mq_hctx_stopped(struct blk_mq_hw_ctx *hctx)
{
return test_bit(BLK_MQ_S_STOPPED, &hctx->state);
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 4fa81ed383ca..be1f115b538b 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -172,11 +172,6 @@ void blk_queue_make_request(struct request_queue *q, make_request_fn *mfn)
q->nr_batching = BLK_BATCH_REQ;
blk_set_default_limits(&q->limits);
-
- /*
- * by default assume old behaviour and bounce for any highmem page
- */
- blk_queue_bounce_limit(q, BLK_BOUNCE_HIGH);
}
EXPORT_SYMBOL(blk_queue_make_request);
diff --git a/block/blk-tag.c b/block/blk-tag.c
index 07cc329fa4b0..2290f65b9d73 100644
--- a/block/blk-tag.c
+++ b/block/blk-tag.c
@@ -258,15 +258,14 @@ EXPORT_SYMBOL(blk_queue_resize_tags);
* all transfers have been done for a request. It's important to call
* this function before end_that_request_last(), as that will put the
* request back on the free list thus corrupting the internal tag list.
- *
- * Notes:
- * queue lock must be held.
**/
void blk_queue_end_tag(struct request_queue *q, struct request *rq)
{
struct blk_queue_tag *bqt = q->queue_tags;
unsigned tag = rq->tag; /* negative tags invalid */
+ lockdep_assert_held(q->queue_lock);
+
BUG_ON(tag >= bqt->real_max_depth);
list_del_init(&rq->queuelist);
@@ -307,9 +306,6 @@ EXPORT_SYMBOL(blk_queue_end_tag);
* calling this function. The request will also be removed from
* the request queue, so it's the drivers responsibility to readd
* it if it should need to be restarted for some reason.
- *
- * Notes:
- * queue lock must be held.
**/
int blk_queue_start_tag(struct request_queue *q, struct request *rq)
{
@@ -317,6 +313,8 @@ int blk_queue_start_tag(struct request_queue *q, struct request *rq)
unsigned max_depth;
int tag;
+ lockdep_assert_held(q->queue_lock);
+
if (unlikely((rq->rq_flags & RQF_QUEUED))) {
printk(KERN_ERR
"%s: request %p for device [%s] already tagged %d",
@@ -389,14 +387,13 @@ EXPORT_SYMBOL(blk_queue_start_tag);
* Hardware conditions may dictate a need to stop all pending requests.
* In this case, we will safely clear the block side of the tag queue and
* readd all requests to the request queue in the right order.
- *
- * Notes:
- * queue lock must be held.
**/
void blk_queue_invalidate_tags(struct request_queue *q)
{
struct list_head *tmp, *n;
+ lockdep_assert_held(q->queue_lock);
+
list_for_each_safe(tmp, n, &q->tag_busy_list)
blk_requeue_request(q, list_entry_rq(tmp));
}
diff --git a/block/blk-timeout.c b/block/blk-timeout.c
index cbff183f3d9f..17ec83bb0900 100644
--- a/block/blk-timeout.c
+++ b/block/blk-timeout.c
@@ -189,13 +189,15 @@ unsigned long blk_rq_timeout(unsigned long timeout)
* Notes:
* Each request has its own timer, and as it is added to the queue, we
* set up the timer. When the request completes, we cancel the timer.
- * Queue lock must be held for the non-mq case, mq case doesn't care.
*/
void blk_add_timer(struct request *req)
{
struct request_queue *q = req->q;
unsigned long expiry;
+ if (!q->mq_ops)
+ lockdep_assert_held(q->queue_lock);
+
/* blk-mq has its own handler, so we don't need ->rq_timed_out_fn */
if (!q->mq_ops && !q->rq_timed_out_fn)
return;
diff --git a/block/blk.h b/block/blk.h
index 83c8e1100525..01ebb8185f6b 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -143,6 +143,8 @@ static inline struct request *__elv_next_request(struct request_queue *q)
struct request *rq;
struct blk_flush_queue *fq = blk_get_flush_queue(q, NULL);
+ WARN_ON_ONCE(q->mq_ops);
+
while (1) {
if (!list_empty(&q->queue_head)) {
rq = list_entry_rq(q->queue_head.next);
@@ -334,4 +336,17 @@ static inline void blk_throtl_bio_endio(struct bio *bio) { }
static inline void blk_throtl_stat_add(struct request *rq, u64 time) { }
#endif
+#ifdef CONFIG_BOUNCE
+extern int init_emergency_isa_pool(void);
+extern void blk_queue_bounce(struct request_queue *q, struct bio **bio);
+#else
+static inline int init_emergency_isa_pool(void)
+{
+ return 0;
+}
+static inline void blk_queue_bounce(struct request_queue *q, struct bio **bio)
+{
+}
+#endif /* CONFIG_BOUNCE */
+
#endif /* BLK_INTERNAL_H */
diff --git a/block/bounce.c b/block/bounce.c
index 1cb5dd3a5da1..5793c2dc1a15 100644
--- a/block/bounce.c
+++ b/block/bounce.c
@@ -22,10 +22,12 @@
#include <asm/tlbflush.h>
#include <trace/events/block.h>
+#include "blk.h"
#define POOL_SIZE 64
#define ISA_POOL_SIZE 16
+static struct bio_set *bounce_bio_set, *bounce_bio_split;
static mempool_t *page_pool, *isa_page_pool;
#if defined(CONFIG_HIGHMEM) || defined(CONFIG_NEED_BOUNCE_POOL)
@@ -40,6 +42,14 @@ static __init int init_emergency_pool(void)
BUG_ON(!page_pool);
pr_info("pool size: %d pages\n", POOL_SIZE);
+ bounce_bio_set = bioset_create(BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
+ BUG_ON(!bounce_bio_set);
+ if (bioset_integrity_create(bounce_bio_set, BIO_POOL_SIZE))
+ BUG_ON(1);
+
+ bounce_bio_split = bioset_create(BIO_POOL_SIZE, 0, 0);
+ BUG_ON(!bounce_bio_split);
+
return 0;
}
@@ -143,7 +153,7 @@ static void bounce_end_io(struct bio *bio, mempool_t *pool)
mempool_free(bvec->bv_page, pool);
}
- bio_orig->bi_error = bio->bi_error;
+ bio_orig->bi_status = bio->bi_status;
bio_endio(bio_orig);
bio_put(bio);
}
@@ -163,7 +173,7 @@ static void __bounce_end_io_read(struct bio *bio, mempool_t *pool)
{
struct bio *bio_orig = bio->bi_private;
- if (!bio->bi_error)
+ if (!bio->bi_status)
copy_to_high_bio_irq(bio_orig, bio);
bounce_end_io(bio, pool);
@@ -186,20 +196,31 @@ static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig,
int rw = bio_data_dir(*bio_orig);
struct bio_vec *to, from;
struct bvec_iter iter;
- unsigned i;
-
- bio_for_each_segment(from, *bio_orig, iter)
- if (page_to_pfn(from.bv_page) > queue_bounce_pfn(q))
- goto bounce;
+ unsigned i = 0;
+ bool bounce = false;
+ int sectors = 0;
+
+ bio_for_each_segment(from, *bio_orig, iter) {
+ if (i++ < BIO_MAX_PAGES)
+ sectors += from.bv_len >> 9;
+ if (page_to_pfn(from.bv_page) > q->limits.bounce_pfn)
+ bounce = true;
+ }
+ if (!bounce)
+ return;
- return;
-bounce:
- bio = bio_clone_bioset(*bio_orig, GFP_NOIO, fs_bio_set);
+ if (sectors < bio_sectors(*bio_orig)) {
+ bio = bio_split(*bio_orig, sectors, GFP_NOIO, bounce_bio_split);
+ bio_chain(bio, *bio_orig);
+ generic_make_request(*bio_orig);
+ *bio_orig = bio;
+ }
+ bio = bio_clone_bioset(*bio_orig, GFP_NOIO, bounce_bio_set);
bio_for_each_segment_all(to, bio, i) {
struct page *page = to->bv_page;
- if (page_to_pfn(page) <= queue_bounce_pfn(q))
+ if (page_to_pfn(page) <= q->limits.bounce_pfn)
continue;
to->bv_page = mempool_alloc(pool, q->bounce_gfp);
@@ -251,7 +272,7 @@ void blk_queue_bounce(struct request_queue *q, struct bio **bio_orig)
* don't waste time iterating over bio segments
*/
if (!(q->bounce_gfp & GFP_DMA)) {
- if (queue_bounce_pfn(q) >= blk_max_pfn)
+ if (q->limits.bounce_pfn >= blk_max_pfn)
return;
pool = page_pool;
} else {
@@ -264,5 +285,3 @@ void blk_queue_bounce(struct request_queue *q, struct bio **bio_orig)
*/
__blk_queue_bounce(q, bio_orig, pool);
}
-
-EXPORT_SYMBOL(blk_queue_bounce);
diff --git a/block/bsg-lib.c b/block/bsg-lib.c
index 0a23dbba2d30..c4513b23f57a 100644
--- a/block/bsg-lib.c
+++ b/block/bsg-lib.c
@@ -37,7 +37,7 @@ static void bsg_destroy_job(struct kref *kref)
struct bsg_job *job = container_of(kref, struct bsg_job, kref);
struct request *rq = job->req;
- blk_end_request_all(rq, scsi_req(rq)->result);
+ blk_end_request_all(rq, BLK_STS_OK);
put_device(job->dev); /* release reference for the request */
@@ -202,7 +202,7 @@ static void bsg_request_fn(struct request_queue *q)
ret = bsg_create_job(dev, req);
if (ret) {
scsi_req(req)->result = ret;
- blk_end_request_all(req, ret);
+ blk_end_request_all(req, BLK_STS_OK);
spin_lock_irq(q->queue_lock);
continue;
}
@@ -246,6 +246,7 @@ struct request_queue *bsg_setup_queue(struct device *dev, char *name,
q->bsg_job_size = dd_job_size;
q->bsg_job_fn = job_fn;
queue_flag_set_unlocked(QUEUE_FLAG_BIDI, q);
+ queue_flag_set_unlocked(QUEUE_FLAG_SCSI_PASSTHROUGH, q);
blk_queue_softirq_done(q, bsg_softirq_done);
blk_queue_rq_timeout(q, BLK_DEFAULT_SG_TIMEOUT);
diff --git a/block/bsg.c b/block/bsg.c
index 6fd08544d77e..37663b664666 100644
--- a/block/bsg.c
+++ b/block/bsg.c
@@ -236,7 +236,6 @@ bsg_map_hdr(struct bsg_device *bd, struct sg_io_v4 *hdr, fmode_t has_write_perm)
rq = blk_get_request(q, op, GFP_KERNEL);
if (IS_ERR(rq))
return rq;
- scsi_req_init(rq);
ret = blk_fill_sgv4_hdr_rq(q, rq, hdr, bd, has_write_perm);
if (ret)
@@ -294,14 +293,14 @@ out:
* async completion call-back from the block layer, when scsi/ide/whatever
* calls end_that_request_last() on a request
*/
-static void bsg_rq_end_io(struct request *rq, int uptodate)
+static void bsg_rq_end_io(struct request *rq, blk_status_t status)
{
struct bsg_command *bc = rq->end_io_data;
struct bsg_device *bd = bc->bd;
unsigned long flags;
- dprintk("%s: finished rq %p bc %p, bio %p stat %d\n",
- bd->name, rq, bc, bc->bio, uptodate);
+ dprintk("%s: finished rq %p bc %p, bio %p\n",
+ bd->name, rq, bc, bc->bio);
bc->hdr.duration = jiffies_to_msecs(jiffies - bc->hdr.duration);
@@ -750,6 +749,12 @@ static struct bsg_device *bsg_add_device(struct inode *inode,
#ifdef BSG_DEBUG
unsigned char buf[32];
#endif
+
+ if (!blk_queue_scsi_passthrough(rq)) {
+ WARN_ONCE(true, "Attempt to register a non-SCSI queue\n");
+ return ERR_PTR(-EINVAL);
+ }
+
if (!blk_get_queue(rq))
return ERR_PTR(-ENXIO);
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index b7e9c7feeab2..3d5c28945719 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -982,15 +982,6 @@ static inline u64 max_vdisktime(u64 min_vdisktime, u64 vdisktime)
return min_vdisktime;
}
-static inline u64 min_vdisktime(u64 min_vdisktime, u64 vdisktime)
-{
- s64 delta = (s64)(vdisktime - min_vdisktime);
- if (delta < 0)
- min_vdisktime = vdisktime;
-
- return min_vdisktime;
-}
-
static void update_min_vdisktime(struct cfq_rb_root *st)
{
struct cfq_group *cfqg;
diff --git a/block/elevator.c b/block/elevator.c
index dac99fbfc273..4bb2f0c93fa6 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -681,6 +681,7 @@ void __elv_add_request(struct request_queue *q, struct request *rq, int where)
*/
if (elv_attempt_insert_merge(q, rq))
break;
+ /* fall through */
case ELEVATOR_INSERT_SORT:
BUG_ON(blk_rq_is_passthrough(rq));
rq->rq_flags |= RQF_SORTED;
diff --git a/block/genhd.c b/block/genhd.c
index d252d29fe837..7f520fa25d16 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -36,7 +36,7 @@ struct kobject *block_depr;
static DEFINE_SPINLOCK(ext_devt_lock);
static DEFINE_IDR(ext_devt_idr);
-static struct device_type disk_type;
+static const struct device_type disk_type;
static void disk_check_events(struct disk_events *ev,
unsigned int *clearing_ptr);
@@ -1183,7 +1183,7 @@ static char *block_devnode(struct device *dev, umode_t *mode,
return NULL;
}
-static struct device_type disk_type = {
+static const struct device_type disk_type = {
.name = "disk",
.groups = disk_attr_groups,
.release = disk_release,
diff --git a/block/ioprio.c b/block/ioprio.c
index 4b120c9cf7e8..6f5d0b6625e3 100644
--- a/block/ioprio.c
+++ b/block/ioprio.c
@@ -75,7 +75,8 @@ SYSCALL_DEFINE3(ioprio_set, int, which, int, who, int, ioprio)
case IOPRIO_CLASS_RT:
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
- /* fall through, rt has prio field too */
+ /* fall through */
+ /* rt has prio field too */
case IOPRIO_CLASS_BE:
if (data >= IOPRIO_BE_NR || data < 0)
return -EINVAL;
diff --git a/block/kyber-iosched.c b/block/kyber-iosched.c
index b9faabc75fdb..a9f6fd3fab8e 100644
--- a/block/kyber-iosched.c
+++ b/block/kyber-iosched.c
@@ -426,33 +426,29 @@ static void rq_clear_domain_token(struct kyber_queue_data *kqd,
}
}
-static struct request *kyber_get_request(struct request_queue *q,
- unsigned int op,
- struct blk_mq_alloc_data *data)
+static void kyber_limit_depth(unsigned int op, struct blk_mq_alloc_data *data)
{
- struct kyber_queue_data *kqd = q->elevator->elevator_data;
- struct request *rq;
-
/*
* We use the scheduler tags as per-hardware queue queueing tokens.
* Async requests can be limited at this stage.
*/
- if (!op_is_sync(op))
+ if (!op_is_sync(op)) {
+ struct kyber_queue_data *kqd = data->q->elevator->elevator_data;
+
data->shallow_depth = kqd->async_depth;
+ }
+}
- rq = __blk_mq_alloc_request(data, op);
- if (rq)
- rq_set_domain_token(rq, -1);
- return rq;
+static void kyber_prepare_request(struct request *rq, struct bio *bio)
+{
+ rq_set_domain_token(rq, -1);
}
-static void kyber_put_request(struct request *rq)
+static void kyber_finish_request(struct request *rq)
{
- struct request_queue *q = rq->q;
- struct kyber_queue_data *kqd = q->elevator->elevator_data;
+ struct kyber_queue_data *kqd = rq->q->elevator->elevator_data;
rq_clear_domain_token(kqd, rq);
- blk_mq_finish_request(rq);
}
static void kyber_completed_request(struct request *rq)
@@ -815,8 +811,9 @@ static struct elevator_type kyber_sched = {
.exit_sched = kyber_exit_sched,
.init_hctx = kyber_init_hctx,
.exit_hctx = kyber_exit_hctx,
- .get_request = kyber_get_request,
- .put_request = kyber_put_request,
+ .limit_depth = kyber_limit_depth,
+ .prepare_request = kyber_prepare_request,
+ .finish_request = kyber_finish_request,
.completed_request = kyber_completed_request,
.dispatch_request = kyber_dispatch_request,
.has_work = kyber_has_work,
diff --git a/block/partitions/ldm.c b/block/partitions/ldm.c
index edcea70674c9..2a365c756648 100644
--- a/block/partitions/ldm.c
+++ b/block/partitions/ldm.c
@@ -115,7 +115,7 @@ static bool ldm_parse_privhead(const u8 *data, struct privhead *ph)
ldm_error("PRIVHEAD disk size doesn't match real disk size");
return false;
}
- if (uuid_be_to_bin(data + 0x0030, (uuid_be *)ph->disk_id)) {
+ if (uuid_parse(data + 0x0030, &ph->disk_id)) {
ldm_error("PRIVHEAD contains an invalid GUID.");
return false;
}
@@ -234,7 +234,7 @@ static bool ldm_compare_privheads (const struct privhead *ph1,
(ph1->logical_disk_size == ph2->logical_disk_size) &&
(ph1->config_start == ph2->config_start) &&
(ph1->config_size == ph2->config_size) &&
- !memcmp (ph1->disk_id, ph2->disk_id, GUID_SIZE));
+ uuid_equal(&ph1->disk_id, &ph2->disk_id));
}
/**
@@ -557,7 +557,7 @@ static struct vblk * ldm_get_disk_objid (const struct ldmdb *ldb)
list_for_each (item, &ldb->v_disk) {
struct vblk *v = list_entry (item, struct vblk, list);
- if (!memcmp (v->vblk.disk.disk_id, ldb->ph.disk_id, GUID_SIZE))
+ if (uuid_equal(&v->vblk.disk.disk_id, &ldb->ph.disk_id))
return v;
}
@@ -892,7 +892,7 @@ static bool ldm_parse_dsk3 (const u8 *buffer, int buflen, struct vblk *vb)
disk = &vb->vblk.disk;
ldm_get_vstr (buffer + 0x18 + r_diskid, disk->alt_name,
sizeof (disk->alt_name));
- if (uuid_be_to_bin(buffer + 0x19 + r_name, (uuid_be *)disk->disk_id))
+ if (uuid_parse(buffer + 0x19 + r_name, &disk->disk_id))
return false;
return true;
@@ -927,7 +927,7 @@ static bool ldm_parse_dsk4 (const u8 *buffer, int buflen, struct vblk *vb)
return false;
disk = &vb->vblk.disk;
- memcpy (disk->disk_id, buffer + 0x18 + r_name, GUID_SIZE);
+ uuid_copy(&disk->disk_id, (uuid_t *)(buffer + 0x18 + r_name));
return true;
}
diff --git a/block/partitions/ldm.h b/block/partitions/ldm.h
index 374242c0971a..f4c6055df956 100644
--- a/block/partitions/ldm.h
+++ b/block/partitions/ldm.h
@@ -112,8 +112,6 @@ struct frag { /* VBLK Fragment handling */
/* In memory LDM database structures. */
-#define GUID_SIZE 16
-
struct privhead { /* Offsets and sizes are in sectors. */
u16 ver_major;
u16 ver_minor;
@@ -121,7 +119,7 @@ struct privhead { /* Offsets and sizes are in sectors. */
u64 logical_disk_size;
u64 config_start;
u64 config_size;
- u8 disk_id[GUID_SIZE];
+ uuid_t disk_id;
};
struct tocblock { /* We have exactly two bitmaps. */
@@ -154,7 +152,7 @@ struct vblk_dgrp { /* VBLK Disk Group */
};
struct vblk_disk { /* VBLK Disk */
- u8 disk_id[GUID_SIZE];
+ uuid_t disk_id;
u8 alt_name[128];
};
diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c
index 4a294a5f7fab..7440de44dd85 100644
--- a/block/scsi_ioctl.c
+++ b/block/scsi_ioctl.c
@@ -326,7 +326,6 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk,
if (IS_ERR(rq))
return PTR_ERR(rq);
req = scsi_req(rq);
- scsi_req_init(rq);
if (hdr->cmd_len > BLK_MAX_CDB) {
req->cmd = kzalloc(hdr->cmd_len, GFP_KERNEL);
@@ -456,7 +455,6 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode,
goto error_free_buffer;
}
req = scsi_req(rq);
- scsi_req_init(rq);
cmdlen = COMMAND_SIZE(opcode);
@@ -542,7 +540,6 @@ static int __blk_send_generic(struct request_queue *q, struct gendisk *bd_disk,
rq = blk_get_request(q, REQ_OP_SCSI_OUT, __GFP_RECLAIM);
if (IS_ERR(rq))
return PTR_ERR(rq);
- scsi_req_init(rq);
rq->timeout = BLK_DEFAULT_SG_TIMEOUT;
scsi_req(rq)->cmd[0] = cmd;
scsi_req(rq)->cmd[4] = data;
@@ -744,10 +741,14 @@ int scsi_cmd_blk_ioctl(struct block_device *bd, fmode_t mode,
}
EXPORT_SYMBOL(scsi_cmd_blk_ioctl);
-void scsi_req_init(struct request *rq)
+/**
+ * scsi_req_init - initialize certain fields of a scsi_request structure
+ * @req: Pointer to a scsi_request structure.
+ * Initializes .__cmd[], .cmd, .cmd_len and .sense_len but no other members
+ * of struct scsi_request.
+ */
+void scsi_req_init(struct scsi_request *req)
{
- struct scsi_request *req = scsi_req(rq);
-
memset(req->__cmd, 0, sizeof(req->__cmd));
req->cmd = req->__cmd;
req->cmd_len = BLK_MAX_CDB;
diff --git a/block/t10-pi.c b/block/t10-pi.c
index 680c6d636298..3416dadf7b15 100644
--- a/block/t10-pi.c
+++ b/block/t10-pi.c
@@ -46,8 +46,8 @@ static __be16 t10_pi_ip_fn(void *data, unsigned int len)
* 16 bit app tag, 32 bit reference tag. Type 3 does not define the ref
* tag.
*/
-static int t10_pi_generate(struct blk_integrity_iter *iter, csum_fn *fn,
- unsigned int type)
+static blk_status_t t10_pi_generate(struct blk_integrity_iter *iter,
+ csum_fn *fn, unsigned int type)
{
unsigned int i;
@@ -67,11 +67,11 @@ static int t10_pi_generate(struct blk_integrity_iter *iter, csum_fn *fn,
iter->seed++;
}
- return 0;
+ return BLK_STS_OK;
}
-static int t10_pi_verify(struct blk_integrity_iter *iter, csum_fn *fn,
- unsigned int type)
+static blk_status_t t10_pi_verify(struct blk_integrity_iter *iter,
+ csum_fn *fn, unsigned int type)
{
unsigned int i;
@@ -91,7 +91,7 @@ static int t10_pi_verify(struct blk_integrity_iter *iter, csum_fn *fn,
"(rcvd %u)\n", iter->disk_name,
(unsigned long long)
iter->seed, be32_to_cpu(pi->ref_tag));
- return -EILSEQ;
+ return BLK_STS_PROTECTION;
}
break;
case 3:
@@ -108,7 +108,7 @@ static int t10_pi_verify(struct blk_integrity_iter *iter, csum_fn *fn,
"(rcvd %04x, want %04x)\n", iter->disk_name,
(unsigned long long)iter->seed,
be16_to_cpu(pi->guard_tag), be16_to_cpu(csum));
- return -EILSEQ;
+ return BLK_STS_PROTECTION;
}
next:
@@ -117,45 +117,45 @@ next:
iter->seed++;
}
- return 0;
+ return BLK_STS_OK;
}
-static int t10_pi_type1_generate_crc(struct blk_integrity_iter *iter)
+static blk_status_t t10_pi_type1_generate_crc(struct blk_integrity_iter *iter)
{
return t10_pi_generate(iter, t10_pi_crc_fn, 1);
}
-static int t10_pi_type1_generate_ip(struct blk_integrity_iter *iter)
+static blk_status_t t10_pi_type1_generate_ip(struct blk_integrity_iter *iter)
{
return t10_pi_generate(iter, t10_pi_ip_fn, 1);
}
-static int t10_pi_type1_verify_crc(struct blk_integrity_iter *iter)
+static blk_status_t t10_pi_type1_verify_crc(struct blk_integrity_iter *iter)
{
return t10_pi_verify(iter, t10_pi_crc_fn, 1);
}
-static int t10_pi_type1_verify_ip(struct blk_integrity_iter *iter)
+static blk_status_t t10_pi_type1_verify_ip(struct blk_integrity_iter *iter)
{
return t10_pi_verify(iter, t10_pi_ip_fn, 1);
}
-static int t10_pi_type3_generate_crc(struct blk_integrity_iter *iter)
+static blk_status_t t10_pi_type3_generate_crc(struct blk_integrity_iter *iter)
{
return t10_pi_generate(iter, t10_pi_crc_fn, 3);
}
-static int t10_pi_type3_generate_ip(struct blk_integrity_iter *iter)
+static blk_status_t t10_pi_type3_generate_ip(struct blk_integrity_iter *iter)
{
return t10_pi_generate(iter, t10_pi_ip_fn, 3);
}
-static int t10_pi_type3_verify_crc(struct blk_integrity_iter *iter)
+static blk_status_t t10_pi_type3_verify_crc(struct blk_integrity_iter *iter)
{
return t10_pi_verify(iter, t10_pi_crc_fn, 3);
}
-static int t10_pi_type3_verify_ip(struct blk_integrity_iter *iter)
+static blk_status_t t10_pi_type3_verify_ip(struct blk_integrity_iter *iter)
{
return t10_pi_verify(iter, t10_pi_ip_fn, 3);
}
diff --git a/drivers/acpi/acpi_extlog.c b/drivers/acpi/acpi_extlog.c
index 502ea4dc2080..560fdae8cc59 100644
--- a/drivers/acpi/acpi_extlog.c
+++ b/drivers/acpi/acpi_extlog.c
@@ -141,9 +141,9 @@ static int extlog_print(struct notifier_block *nb, unsigned long val,
int cpu = mce->extcpu;
struct acpi_hest_generic_status *estatus, *tmp;
struct acpi_hest_generic_data *gdata;
- const uuid_le *fru_id = &NULL_UUID_LE;
+ const guid_t *fru_id = &guid_null;
char *fru_text = "";
- uuid_le *sec_type;
+ guid_t *sec_type;
static u32 err_seq;
estatus = extlog_elog_entry_check(cpu, bank);
@@ -165,11 +165,11 @@ static int extlog_print(struct notifier_block *nb, unsigned long val,
err_seq++;
gdata = (struct acpi_hest_generic_data *)(tmp + 1);
if (gdata->validation_bits & CPER_SEC_VALID_FRU_ID)
- fru_id = (uuid_le *)gdata->fru_id;
+ fru_id = (guid_t *)gdata->fru_id;
if (gdata->validation_bits & CPER_SEC_VALID_FRU_TEXT)
fru_text = gdata->fru_text;
- sec_type = (uuid_le *)gdata->section_type;
- if (!uuid_le_cmp(*sec_type, CPER_SEC_PLATFORM_MEM)) {
+ sec_type = (guid_t *)gdata->section_type;
+ if (guid_equal(sec_type, &CPER_SEC_PLATFORM_MEM)) {
struct cper_sec_mem_err *mem = (void *)(gdata + 1);
if (gdata->error_data_length >= sizeof(*mem))
trace_extlog_mem_event(mem, err_seq, fru_id, fru_text,
@@ -182,17 +182,17 @@ out:
static bool __init extlog_get_l1addr(void)
{
- u8 uuid[16];
+ guid_t guid;
acpi_handle handle;
union acpi_object *obj;
- acpi_str_to_uuid(extlog_dsm_uuid, uuid);
-
+ if (guid_parse(extlog_dsm_uuid, &guid))
+ return false;
if (ACPI_FAILURE(acpi_get_handle(NULL, "\\_SB", &handle)))
return false;
- if (!acpi_check_dsm(handle, uuid, EXTLOG_DSM_REV, 1 << EXTLOG_FN_ADDR))
+ if (!acpi_check_dsm(handle, &guid, EXTLOG_DSM_REV, 1 << EXTLOG_FN_ADDR))
return false;
- obj = acpi_evaluate_dsm_typed(handle, uuid, EXTLOG_DSM_REV,
+ obj = acpi_evaluate_dsm_typed(handle, &guid, EXTLOG_DSM_REV,
EXTLOG_FN_ADDR, NULL, ACPI_TYPE_INTEGER);
if (!obj) {
return false;
diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index d0855c09f32f..980515e029fa 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -431,12 +431,13 @@ static void ghes_do_proc(struct ghes *ghes,
{
int sev, sec_sev;
struct acpi_hest_generic_data *gdata;
+ guid_t *sec_type;
sev = ghes_severity(estatus->error_severity);
apei_estatus_for_each_section(estatus, gdata) {
+ sec_type = (guid_t *)gdata->section_type;
sec_sev = ghes_severity(gdata->error_severity);
- if (!uuid_le_cmp(*(uuid_le *)gdata->section_type,
- CPER_SEC_PLATFORM_MEM)) {
+ if (guid_equal(sec_type, &CPER_SEC_PLATFORM_MEM)) {
struct cper_sec_mem_err *mem_err;
mem_err = (struct cper_sec_mem_err *)(gdata+1);
ghes_edac_report_mem_error(ghes, sev, mem_err);
@@ -445,8 +446,7 @@ static void ghes_do_proc(struct ghes *ghes,
ghes_handle_memory_failure(gdata, sev);
}
#ifdef CONFIG_ACPI_APEI_PCIEAER
- else if (!uuid_le_cmp(*(uuid_le *)gdata->section_type,
- CPER_SEC_PCIE)) {
+ else if (guid_equal(sec_type, &CPER_SEC_PCIE)) {
struct cper_sec_pcie *pcie_err;
pcie_err = (struct cper_sec_pcie *)(gdata+1);
if (sev == GHES_SEV_RECOVERABLE &&
diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index 784bda663d16..5a6fbe0fcaf2 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -196,42 +196,19 @@ static void acpi_print_osc_error(acpi_handle handle,
pr_debug("\n");
}
-acpi_status acpi_str_to_uuid(char *str, u8 *uuid)
-{
- int i;
- static int opc_map_to_uuid[16] = {6, 4, 2, 0, 11, 9, 16, 14, 19, 21,
- 24, 26, 28, 30, 32, 34};
-
- if (strlen(str) != 36)
- return AE_BAD_PARAMETER;
- for (i = 0; i < 36; i++) {
- if (i == 8 || i == 13 || i == 18 || i == 23) {
- if (str[i] != '-')
- return AE_BAD_PARAMETER;
- } else if (!isxdigit(str[i]))
- return AE_BAD_PARAMETER;
- }
- for (i = 0; i < 16; i++) {
- uuid[i] = hex_to_bin(str[opc_map_to_uuid[i]]) << 4;
- uuid[i] |= hex_to_bin(str[opc_map_to_uuid[i] + 1]);
- }
- return AE_OK;
-}
-EXPORT_SYMBOL_GPL(acpi_str_to_uuid);
-
acpi_status acpi_run_osc(acpi_handle handle, struct acpi_osc_context *context)
{
acpi_status status;
struct acpi_object_list input;
union acpi_object in_params[4];
union acpi_object *out_obj;
- u8 uuid[16];
+ guid_t guid;
u32 errors;
struct acpi_buffer output = {ACPI_ALLOCATE_BUFFER, NULL};
if (!context)
return AE_ERROR;
- if (ACPI_FAILURE(acpi_str_to_uuid(context->uuid_str, uuid)))
+ if (guid_parse(context->uuid_str, &guid))
return AE_ERROR;
context->ret.length = ACPI_ALLOCATE_BUFFER;
context->ret.pointer = NULL;
@@ -241,7 +218,7 @@ acpi_status acpi_run_osc(acpi_handle handle, struct acpi_osc_context *context)
input.pointer = in_params;
in_params[0].type = ACPI_TYPE_BUFFER;
in_params[0].buffer.length = 16;
- in_params[0].buffer.pointer = uuid;
+ in_params[0].buffer.pointer = (u8 *)&guid;
in_params[1].type = ACPI_TYPE_INTEGER;
in_params[1].integer.value = context->rev;
in_params[2].type = ACPI_TYPE_INTEGER;
diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c
index 656acb5d7166..097eff0b963d 100644
--- a/drivers/acpi/nfit/core.c
+++ b/drivers/acpi/nfit/core.c
@@ -74,11 +74,11 @@ struct nfit_table_prev {
struct list_head flushes;
};
-static u8 nfit_uuid[NFIT_UUID_MAX][16];
+static guid_t nfit_uuid[NFIT_UUID_MAX];
-const u8 *to_nfit_uuid(enum nfit_uuids id)
+const guid_t *to_nfit_uuid(enum nfit_uuids id)
{
- return nfit_uuid[id];
+ return &nfit_uuid[id];
}
EXPORT_SYMBOL(to_nfit_uuid);
@@ -222,7 +222,7 @@ int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm,
u32 offset, fw_status = 0;
acpi_handle handle;
unsigned int func;
- const u8 *uuid;
+ const guid_t *guid;
int rc, i;
func = cmd;
@@ -245,7 +245,7 @@ int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm,
cmd_mask = nvdimm_cmd_mask(nvdimm);
dsm_mask = nfit_mem->dsm_mask;
desc = nd_cmd_dimm_desc(cmd);
- uuid = to_nfit_uuid(nfit_mem->family);
+ guid = to_nfit_uuid(nfit_mem->family);
handle = adev->handle;
} else {
struct acpi_device *adev = to_acpi_dev(acpi_desc);
@@ -254,7 +254,7 @@ int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm,
cmd_mask = nd_desc->cmd_mask;
dsm_mask = cmd_mask;
desc = nd_cmd_bus_desc(cmd);
- uuid = to_nfit_uuid(NFIT_DEV_BUS);
+ guid = to_nfit_uuid(NFIT_DEV_BUS);
handle = adev->handle;
dimm_name = "bus";
}
@@ -289,7 +289,7 @@ int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm,
in_buf.buffer.pointer,
min_t(u32, 256, in_buf.buffer.length), true);
- out_obj = acpi_evaluate_dsm(handle, uuid, 1, func, &in_obj);
+ out_obj = acpi_evaluate_dsm(handle, guid, 1, func, &in_obj);
if (!out_obj) {
dev_dbg(dev, "%s:%s _DSM failed cmd: %s\n", __func__, dimm_name,
cmd_name);
@@ -409,7 +409,7 @@ int nfit_spa_type(struct acpi_nfit_system_address *spa)
int i;
for (i = 0; i < NFIT_UUID_MAX; i++)
- if (memcmp(to_nfit_uuid(i), spa->range_guid, 16) == 0)
+ if (guid_equal(to_nfit_uuid(i), (guid_t *)&spa->range_guid))
return i;
return -1;
}
@@ -1415,7 +1415,7 @@ static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc,
struct acpi_device *adev, *adev_dimm;
struct device *dev = acpi_desc->dev;
unsigned long dsm_mask;
- const u8 *uuid;
+ const guid_t *guid;
int i;
int family = -1;
@@ -1444,7 +1444,7 @@ static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc,
/*
* Until standardization materializes we need to consider 4
* different command sets. Note, that checking for function0 (bit0)
- * tells us if any commands are reachable through this uuid.
+ * tells us if any commands are reachable through this GUID.
*/
for (i = NVDIMM_FAMILY_INTEL; i <= NVDIMM_FAMILY_MSFT; i++)
if (acpi_check_dsm(adev_dimm->handle, to_nfit_uuid(i), 1, 1))
@@ -1474,9 +1474,9 @@ static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc,
return 0;
}
- uuid = to_nfit_uuid(nfit_mem->family);
+ guid = to_nfit_uuid(nfit_mem->family);
for_each_set_bit(i, &dsm_mask, BITS_PER_LONG)
- if (acpi_check_dsm(adev_dimm->handle, uuid, 1, 1ULL << i))
+ if (acpi_check_dsm(adev_dimm->handle, guid, 1, 1ULL << i))
set_bit(i, &nfit_mem->dsm_mask);
return 0;
@@ -1611,7 +1611,7 @@ static int acpi_nfit_register_dimms(struct acpi_nfit_desc *acpi_desc)
static void acpi_nfit_init_dsms(struct acpi_nfit_desc *acpi_desc)
{
struct nvdimm_bus_descriptor *nd_desc = &acpi_desc->nd_desc;
- const u8 *uuid = to_nfit_uuid(NFIT_DEV_BUS);
+ const guid_t *guid = to_nfit_uuid(NFIT_DEV_BUS);
struct acpi_device *adev;
int i;
@@ -1621,7 +1621,7 @@ static void acpi_nfit_init_dsms(struct acpi_nfit_desc *acpi_desc)
return;
for (i = ND_CMD_ARS_CAP; i <= ND_CMD_CLEAR_ERROR; i++)
- if (acpi_check_dsm(adev->handle, uuid, 1, 1ULL << i))
+ if (acpi_check_dsm(adev->handle, guid, 1, 1ULL << i))
set_bit(i, &nd_desc->cmd_mask);
}
@@ -3051,19 +3051,19 @@ static __init int nfit_init(void)
BUILD_BUG_ON(sizeof(struct acpi_nfit_control_region) != 80);
BUILD_BUG_ON(sizeof(struct acpi_nfit_data_region) != 40);
- acpi_str_to_uuid(UUID_VOLATILE_MEMORY, nfit_uuid[NFIT_SPA_VOLATILE]);
- acpi_str_to_uuid(UUID_PERSISTENT_MEMORY, nfit_uuid[NFIT_SPA_PM]);
- acpi_str_to_uuid(UUID_CONTROL_REGION, nfit_uuid[NFIT_SPA_DCR]);
- acpi_str_to_uuid(UUID_DATA_REGION, nfit_uuid[NFIT_SPA_BDW]);
- acpi_str_to_uuid(UUID_VOLATILE_VIRTUAL_DISK, nfit_uuid[NFIT_SPA_VDISK]);
- acpi_str_to_uuid(UUID_VOLATILE_VIRTUAL_CD, nfit_uuid[NFIT_SPA_VCD]);
- acpi_str_to_uuid(UUID_PERSISTENT_VIRTUAL_DISK, nfit_uuid[NFIT_SPA_PDISK]);
- acpi_str_to_uuid(UUID_PERSISTENT_VIRTUAL_CD, nfit_uuid[NFIT_SPA_PCD]);
- acpi_str_to_uuid(UUID_NFIT_BUS, nfit_uuid[NFIT_DEV_BUS]);
- acpi_str_to_uuid(UUID_NFIT_DIMM, nfit_uuid[NFIT_DEV_DIMM]);
- acpi_str_to_uuid(UUID_NFIT_DIMM_N_HPE1, nfit_uuid[NFIT_DEV_DIMM_N_HPE1]);
- acpi_str_to_uuid(UUID_NFIT_DIMM_N_HPE2, nfit_uuid[NFIT_DEV_DIMM_N_HPE2]);
- acpi_str_to_uuid(UUID_NFIT_DIMM_N_MSFT, nfit_uuid[NFIT_DEV_DIMM_N_MSFT]);
+ guid_parse(UUID_VOLATILE_MEMORY, &nfit_uuid[NFIT_SPA_VOLATILE]);
+ guid_parse(UUID_PERSISTENT_MEMORY, &nfit_uuid[NFIT_SPA_PM]);
+ guid_parse(UUID_CONTROL_REGION, &nfit_uuid[NFIT_SPA_DCR]);
+ guid_parse(UUID_DATA_REGION, &nfit_uuid[NFIT_SPA_BDW]);
+ guid_parse(UUID_VOLATILE_VIRTUAL_DISK, &nfit_uuid[NFIT_SPA_VDISK]);
+ guid_parse(UUID_VOLATILE_VIRTUAL_CD, &nfit_uuid[NFIT_SPA_VCD]);
+ guid_parse(UUID_PERSISTENT_VIRTUAL_DISK, &nfit_uuid[NFIT_SPA_PDISK]);
+ guid_parse(UUID_PERSISTENT_VIRTUAL_CD, &nfit_uuid[NFIT_SPA_PCD]);
+ guid_parse(UUID_NFIT_BUS, &nfit_uuid[NFIT_DEV_BUS]);
+ guid_parse(UUID_NFIT_DIMM, &nfit_uuid[NFIT_DEV_DIMM]);
+ guid_parse(UUID_NFIT_DIMM_N_HPE1, &nfit_uuid[NFIT_DEV_DIMM_N_HPE1]);
+ guid_parse(UUID_NFIT_DIMM_N_HPE2, &nfit_uuid[NFIT_DEV_DIMM_N_HPE2]);
+ guid_parse(UUID_NFIT_DIMM_N_MSFT, &nfit_uuid[NFIT_DEV_DIMM_N_MSFT]);
nfit_wq = create_singlethread_workqueue("nfit");
if (!nfit_wq)
diff --git a/drivers/acpi/nfit/nfit.h b/drivers/acpi/nfit/nfit.h
index 58fb7d68e04a..29bdd959517f 100644
--- a/drivers/acpi/nfit/nfit.h
+++ b/drivers/acpi/nfit/nfit.h
@@ -18,7 +18,6 @@
#include <linux/libnvdimm.h>
#include <linux/ndctl.h>
#include <linux/types.h>
-#include <linux/uuid.h>
#include <linux/acpi.h>
#include <acpi/acuuid.h>
@@ -237,7 +236,7 @@ static inline struct acpi_nfit_desc *to_acpi_desc(
return container_of(nd_desc, struct acpi_nfit_desc, nd_desc);
}
-const u8 *to_nfit_uuid(enum nfit_uuids id);
+const guid_t *to_nfit_uuid(enum nfit_uuids id);
int acpi_nfit_init(struct acpi_nfit_desc *acpi_desc, void *nfit, acpi_size sz);
void acpi_nfit_shutdown(void *data);
void __acpi_nfit_notify(struct device *dev, acpi_handle handle, u32 event);
diff --git a/drivers/acpi/utils.c b/drivers/acpi/utils.c
index 27d0dcfcf47d..b9d956c916f5 100644
--- a/drivers/acpi/utils.c
+++ b/drivers/acpi/utils.c
@@ -613,19 +613,19 @@ acpi_status acpi_evaluate_lck(acpi_handle handle, int lock)
/**
* acpi_evaluate_dsm - evaluate device's _DSM method
* @handle: ACPI device handle
- * @uuid: UUID of requested functions, should be 16 bytes
+ * @guid: GUID of requested functions, should be 16 bytes
* @rev: revision number of requested function
* @func: requested function number
* @argv4: the function specific parameter
*
- * Evaluate device's _DSM method with specified UUID, revision id and
+ * Evaluate device's _DSM method with specified GUID, revision id and
* function number. Caller needs to free the returned object.
*
* Though ACPI defines the fourth parameter for _DSM should be a package,
* some old BIOSes do expect a buffer or an integer etc.
*/
union acpi_object *
-acpi_evaluate_dsm(acpi_handle handle, const u8 *uuid, u64 rev, u64 func,
+acpi_evaluate_dsm(acpi_handle handle, const guid_t *guid, u64 rev, u64 func,
union acpi_object *argv4)
{
acpi_status ret;
@@ -638,7 +638,7 @@ acpi_evaluate_dsm(acpi_handle handle, const u8 *uuid, u64 rev, u64 func,
params[0].type = ACPI_TYPE_BUFFER;
params[0].buffer.length = 16;
- params[0].buffer.pointer = (char *)uuid;
+ params[0].buffer.pointer = (u8 *)guid;
params[1].type = ACPI_TYPE_INTEGER;
params[1].integer.value = rev;
params[2].type = ACPI_TYPE_INTEGER;
@@ -666,7 +666,7 @@ EXPORT_SYMBOL(acpi_evaluate_dsm);
/**
* acpi_check_dsm - check if _DSM method supports requested functions.
* @handle: ACPI device handle
- * @uuid: UUID of requested functions, should be 16 bytes at least
+ * @guid: GUID of requested functions, should be 16 bytes at least
* @rev: revision number of requested functions
* @funcs: bitmap of requested functions
*
@@ -674,7 +674,7 @@ EXPORT_SYMBOL(acpi_evaluate_dsm);
* functions. Currently only support 64 functions at maximum, should be
* enough for now.
*/
-bool acpi_check_dsm(acpi_handle handle, const u8 *uuid, u64 rev, u64 funcs)
+bool acpi_check_dsm(acpi_handle handle, const guid_t *guid, u64 rev, u64 funcs)
{
int i;
u64 mask = 0;
@@ -683,7 +683,7 @@ bool acpi_check_dsm(acpi_handle handle, const u8 *uuid, u64 rev, u64 funcs)
if (funcs == 0)
return false;
- obj = acpi_evaluate_dsm(handle, uuid, rev, 0, NULL);
+ obj = acpi_evaluate_dsm(handle, guid, rev, 0, NULL);
if (!obj)
return false;
@@ -697,7 +697,7 @@ bool acpi_check_dsm(acpi_handle handle, const u8 *uuid, u64 rev, u64 funcs)
/*
* Bit 0 indicates whether there's support for any functions other than
- * function 0 for the specified UUID and revision.
+ * function 0 for the specified GUID and revision.
*/
if ((mask & 0x1) && (mask & funcs) == funcs)
return true;
diff --git a/drivers/block/DAC960.c b/drivers/block/DAC960.c
index 26a51be77227..245a879b036e 100644
--- a/drivers/block/DAC960.c
+++ b/drivers/block/DAC960.c
@@ -3464,7 +3464,7 @@ static inline bool DAC960_ProcessCompletedRequest(DAC960_Command_T *Command,
bool SuccessfulIO)
{
struct request *Request = Command->Request;
- int Error = SuccessfulIO ? 0 : -EIO;
+ blk_status_t Error = SuccessfulIO ? BLK_STS_OK : BLK_STS_IOERR;
pci_unmap_sg(Command->Controller->PCIDevice, Command->cmd_sglist,
Command->SegmentCount, Command->DmaDirection);
diff --git a/drivers/block/amiflop.c b/drivers/block/amiflop.c
index a328f673adfe..49908c74bfcb 100644
--- a/drivers/block/amiflop.c
+++ b/drivers/block/amiflop.c
@@ -1378,7 +1378,7 @@ static void redo_fd_request(void)
struct amiga_floppy_struct *floppy;
char *data;
unsigned long flags;
- int err;
+ blk_status_t err;
next_req:
rq = set_next_request();
@@ -1392,7 +1392,7 @@ next_req:
next_segment:
/* Here someone could investigate to be more efficient */
- for (cnt = 0, err = 0; cnt < blk_rq_cur_sectors(rq); cnt++) {
+ for (cnt = 0, err = BLK_STS_OK; cnt < blk_rq_cur_sectors(rq); cnt++) {
#ifdef DEBUG
printk("fd: sector %ld + %d requested for %s\n",
blk_rq_pos(rq), cnt,
@@ -1400,7 +1400,7 @@ next_segment:
#endif
block = blk_rq_pos(rq) + cnt;
if ((int)block > floppy->blocks) {
- err = -EIO;
+ err = BLK_STS_IOERR;
break;
}
@@ -1413,7 +1413,7 @@ next_segment:
#endif
if (get_track(drive, track) == -1) {
- err = -EIO;
+ err = BLK_STS_IOERR;
break;
}
@@ -1424,7 +1424,7 @@ next_segment:
/* keep the drive spinning while writes are scheduled */
if (!fd_motor_on(drive)) {
- err = -EIO;
+ err = BLK_STS_IOERR;
break;
}
/*
diff --git a/drivers/block/aoe/aoeblk.c b/drivers/block/aoe/aoeblk.c
index 027b876370bc..6797e6c23c8a 100644
--- a/drivers/block/aoe/aoeblk.c
+++ b/drivers/block/aoe/aoeblk.c
@@ -388,6 +388,7 @@ aoeblk_gdalloc(void *vp)
d->aoemajor, d->aoeminor);
goto err_mempool;
}
+ blk_queue_bounce_limit(q, BLK_BOUNCE_HIGH);
spin_lock_irqsave(&d->lock, flags);
WARN_ON(!(d->flags & DEVFL_GD_NOW));
diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c
index 3c606c09fd5a..dc43254e05a4 100644
--- a/drivers/block/aoe/aoecmd.c
+++ b/drivers/block/aoe/aoecmd.c
@@ -1070,8 +1070,8 @@ aoe_end_request(struct aoedev *d, struct request *rq, int fastfail)
d->ip.rq = NULL;
do {
bio = rq->bio;
- bok = !fastfail && !bio->bi_error;
- } while (__blk_end_request(rq, bok ? 0 : -EIO, bio->bi_iter.bi_size));
+ bok = !fastfail && !bio->bi_status;
+ } while (__blk_end_request(rq, bok ? BLK_STS_OK : BLK_STS_IOERR, bio->bi_iter.bi_size));
/* cf. http://lkml.org/lkml/2006/10/31/28 */
if (!fastfail)
@@ -1131,7 +1131,7 @@ ktiocomplete(struct frame *f)
ahout->cmdstat, ahin->cmdstat,
d->aoemajor, d->aoeminor);
noskb: if (buf)
- buf->bio->bi_error = -EIO;
+ buf->bio->bi_status = BLK_STS_IOERR;
goto out;
}
@@ -1144,7 +1144,7 @@ noskb: if (buf)
"aoe: runt data size in read from",
(long) d->aoemajor, d->aoeminor,
skb->len, n);
- buf->bio->bi_error = -EIO;
+ buf->bio->bi_status = BLK_STS_IOERR;
break;
}
if (n > f->iter.bi_size) {
@@ -1152,7 +1152,7 @@ noskb: if (buf)
"aoe: too-large data size in read from",
(long) d->aoemajor, d->aoeminor,
n, f->iter.bi_size);
- buf->bio->bi_error = -EIO;
+ buf->bio->bi_status = BLK_STS_IOERR;
break;
}
bvcpy(skb, f->buf->bio, f->iter, n);
@@ -1654,7 +1654,7 @@ aoe_failbuf(struct aoedev *d, struct buf *buf)
if (buf == NULL)
return;
buf->iter.bi_size = 0;
- buf->bio->bi_error = -EIO;
+ buf->bio->bi_status = BLK_STS_IOERR;
if (buf->nframesout == 0)
aoe_end_buf(d, buf);
}
diff --git a/drivers/block/aoe/aoedev.c b/drivers/block/aoe/aoedev.c
index ffd1947500c6..b28fefb90391 100644
--- a/drivers/block/aoe/aoedev.c
+++ b/drivers/block/aoe/aoedev.c
@@ -170,7 +170,7 @@ aoe_failip(struct aoedev *d)
if (rq == NULL)
return;
while ((bio = d->ip.nxbio)) {
- bio->bi_error = -EIO;
+ bio->bi_status = BLK_STS_IOERR;
d->ip.nxbio = bio->bi_next;
n = (unsigned long) rq->special;
rq->special = (void *) --n;
diff --git a/drivers/block/ataflop.c b/drivers/block/ataflop.c
index fa69ecd52cb5..92da886180aa 100644
--- a/drivers/block/ataflop.c
+++ b/drivers/block/ataflop.c
@@ -378,7 +378,7 @@ static DEFINE_TIMER(readtrack_timer, fd_readtrack_check, 0, 0);
static DEFINE_TIMER(timeout_timer, fd_times_out, 0, 0);
static DEFINE_TIMER(fd_timer, check_change, 0, 0);
-static void fd_end_request_cur(int err)
+static void fd_end_request_cur(blk_status_t err)
{
if (!__blk_end_request_cur(fd_request, err))
fd_request = NULL;
@@ -620,7 +620,7 @@ static void fd_error( void )
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);
+ fd_end_request_cur(BLK_STS_IOERR);
}
else if (fd_request->error_count == RECALIBRATE_ERRORS) {
printk(KERN_WARNING "fd%d: recalibrating\n", SelectedDrive );
@@ -739,7 +739,7 @@ static void do_fd_action( int drive )
}
else {
/* all sectors finished */
- fd_end_request_cur(0);
+ fd_end_request_cur(BLK_STS_OK);
redo_fd_request();
return;
}
@@ -1144,7 +1144,7 @@ static void fd_rwsec_done1(int status)
}
else {
/* all sectors finished */
- fd_end_request_cur(0);
+ fd_end_request_cur(BLK_STS_OK);
redo_fd_request();
}
return;
@@ -1445,7 +1445,7 @@ repeat:
if (!UD.connected) {
/* drive not connected */
printk(KERN_ERR "Unknown Device: fd%d\n", drive );
- fd_end_request_cur(-EIO);
+ fd_end_request_cur(BLK_STS_IOERR);
goto repeat;
}
@@ -1461,12 +1461,12 @@ repeat:
/* user supplied disk type */
if (--type >= NUM_DISK_MINORS) {
printk(KERN_WARNING "fd%d: invalid disk format", drive );
- fd_end_request_cur(-EIO);
+ fd_end_request_cur(BLK_STS_IOERR);
goto repeat;
}
if (minor2disktype[type].drive_types > DriveType) {
printk(KERN_WARNING "fd%d: unsupported disk format", drive );
- fd_end_request_cur(-EIO);
+ fd_end_request_cur(BLK_STS_IOERR);
goto repeat;
}
type = minor2disktype[type].index;
@@ -1476,7 +1476,7 @@ repeat:
}
if (blk_rq_pos(fd_request) + 1 > UDT->blocks) {
- fd_end_request_cur(-EIO);
+ fd_end_request_cur(BLK_STS_IOERR);
goto repeat;
}
diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index 57b574f2f66a..6112e99bedf7 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -418,7 +418,6 @@ static struct brd_device *brd_alloc(int i)
blk_queue_make_request(brd->brd_queue, brd_make_request);
blk_queue_max_hw_sectors(brd->brd_queue, 1024);
- blk_queue_bounce_limit(brd->brd_queue, BLK_BOUNCE_ANY);
/* This is so fdisk will align partitions on 4k, because of
* direct_access API needing 4k alignment, returning a PFN
diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c
index cd375503f7b0..02a611993bb4 100644
--- a/drivers/block/cciss.c
+++ b/drivers/block/cciss.c
@@ -1864,7 +1864,8 @@ 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, scsi_req(rq)->result ? -EIO : 0);
+ blk_end_request_all(rq, scsi_req(rq)->result ?
+ BLK_STS_IOERR : BLK_STS_OK);
spin_lock_irqsave(&h->lock, flags);
cmd_free(h, c);
@@ -1956,6 +1957,7 @@ static int cciss_add_disk(ctlr_info_t *h, struct gendisk *disk,
disk->queue->cmd_size = sizeof(struct scsi_request);
disk->queue->request_fn = do_cciss_request;
disk->queue->queue_lock = &h->lock;
+ queue_flag_set_unlocked(QUEUE_FLAG_SCSI_PASSTHROUGH, disk->queue);
if (blk_init_allocated_queue(disk->queue) < 0)
goto cleanup_queue;
diff --git a/drivers/block/drbd/drbd_actlog.c b/drivers/block/drbd/drbd_actlog.c
index 8d7bcfa49c12..e02c45cd3c5a 100644
--- a/drivers/block/drbd/drbd_actlog.c
+++ b/drivers/block/drbd/drbd_actlog.c
@@ -178,7 +178,7 @@ static int _drbd_md_sync_page_io(struct drbd_device *device,
else
submit_bio(bio);
wait_until_done_or_force_detached(device, bdev, &device->md_io.done);
- if (!bio->bi_error)
+ if (!bio->bi_status)
err = device->md_io.error;
out:
diff --git a/drivers/block/drbd/drbd_bitmap.c b/drivers/block/drbd/drbd_bitmap.c
index a804a4107fbc..809fd245c3dc 100644
--- a/drivers/block/drbd/drbd_bitmap.c
+++ b/drivers/block/drbd/drbd_bitmap.c
@@ -959,16 +959,16 @@ static void drbd_bm_endio(struct bio *bio)
!bm_test_page_unchanged(b->bm_pages[idx]))
drbd_warn(device, "bitmap page idx %u changed during IO!\n", idx);
- if (bio->bi_error) {
+ if (bio->bi_status) {
/* ctx error will hold the completed-last non-zero error code,
* in case error codes differ. */
- ctx->error = bio->bi_error;
+ ctx->error = blk_status_to_errno(bio->bi_status);
bm_set_page_io_err(b->bm_pages[idx]);
/* Not identical to on disk version of it.
* Is BM_PAGE_IO_ERROR enough? */
if (__ratelimit(&drbd_ratelimit_state))
drbd_err(device, "IO ERROR %d on bitmap page idx %u\n",
- bio->bi_error, idx);
+ bio->bi_status, idx);
} else {
bm_clear_page_io_err(b->bm_pages[idx]);
dynamic_drbd_dbg(device, "bitmap page idx %u completed\n", idx);
diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index d5da45bb03a6..d17b6e6393c7 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -1441,6 +1441,9 @@ extern struct bio_set *drbd_md_io_bio_set;
/* to allocate from that set */
extern struct bio *bio_alloc_drbd(gfp_t gfp_mask);
+/* And a bio_set for cloning */
+extern struct bio_set *drbd_io_bio_set;
+
extern struct mutex resources_mutex;
extern int conn_lowest_minor(struct drbd_connection *connection);
@@ -1627,7 +1630,7 @@ static inline void drbd_generic_make_request(struct drbd_device *device,
__release(local);
if (!bio->bi_bdev) {
drbd_err(device, "drbd_generic_make_request: bio->bi_bdev == NULL\n");
- bio->bi_error = -ENODEV;
+ bio->bi_status = BLK_STS_IOERR;
bio_endio(bio);
return;
}
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 84455c365f57..5fb99e06ebe4 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -128,6 +128,7 @@ mempool_t *drbd_request_mempool;
mempool_t *drbd_ee_mempool;
mempool_t *drbd_md_io_page_pool;
struct bio_set *drbd_md_io_bio_set;
+struct bio_set *drbd_io_bio_set;
/* I do not use a standard mempool, because:
1) I want to hand out the pre-allocated objects first.
@@ -2098,6 +2099,8 @@ static void drbd_destroy_mempools(void)
/* D_ASSERT(device, atomic_read(&drbd_pp_vacant)==0); */
+ if (drbd_io_bio_set)
+ bioset_free(drbd_io_bio_set);
if (drbd_md_io_bio_set)
bioset_free(drbd_md_io_bio_set);
if (drbd_md_io_page_pool)
@@ -2115,6 +2118,7 @@ static void drbd_destroy_mempools(void)
if (drbd_al_ext_cache)
kmem_cache_destroy(drbd_al_ext_cache);
+ drbd_io_bio_set = NULL;
drbd_md_io_bio_set = NULL;
drbd_md_io_page_pool = NULL;
drbd_ee_mempool = NULL;
@@ -2142,6 +2146,7 @@ static int drbd_create_mempools(void)
drbd_pp_pool = NULL;
drbd_md_io_page_pool = NULL;
drbd_md_io_bio_set = NULL;
+ drbd_io_bio_set = NULL;
/* caches */
drbd_request_cache = kmem_cache_create(
@@ -2165,7 +2170,13 @@ static int drbd_create_mempools(void)
goto Enomem;
/* mempools */
- drbd_md_io_bio_set = bioset_create(DRBD_MIN_POOL_PAGES, 0);
+ drbd_io_bio_set = bioset_create(BIO_POOL_SIZE, 0, BIOSET_NEED_RESCUER);
+ if (drbd_io_bio_set == NULL)
+ goto Enomem;
+
+ drbd_md_io_bio_set = bioset_create(DRBD_MIN_POOL_PAGES, 0,
+ BIOSET_NEED_BVECS |
+ BIOSET_NEED_RESCUER);
if (drbd_md_io_bio_set == NULL)
goto Enomem;
@@ -2839,7 +2850,6 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig
/* Setting the max_hw_sectors to an odd value of 8kibyte here
This triggers a max_bio_size message upon first attach or connect */
blk_queue_max_hw_sectors(q, DRBD_MAX_BIO_SIZE_SAFE >> 8);
- blk_queue_bounce_limit(q, BLK_BOUNCE_ANY);
q->queue_lock = &resource->req_lock;
device->md_io.page = alloc_page(GFP_KERNEL);
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index 02255a0d68b9..ad0fcb43e45c 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -2294,7 +2294,7 @@ _check_net_options(struct drbd_connection *connection, struct net_conf *old_net_
static enum drbd_ret_code
check_net_options(struct drbd_connection *connection, struct net_conf *new_net_conf)
{
- static enum drbd_ret_code rv;
+ enum drbd_ret_code rv;
struct drbd_peer_device *peer_device;
int i;
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index 1b0a2be24f39..c7e95e6380fb 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -1229,9 +1229,9 @@ void one_flush_endio(struct bio *bio)
struct drbd_device *device = octx->device;
struct issue_flush_context *ctx = octx->ctx;
- if (bio->bi_error) {
- ctx->error = bio->bi_error;
- drbd_info(device, "local disk FLUSH FAILED with status %d\n", bio->bi_error);
+ if (bio->bi_status) {
+ ctx->error = blk_status_to_errno(bio->bi_status);
+ drbd_info(device, "local disk FLUSH FAILED with status %d\n", bio->bi_status);
}
kfree(octx);
bio_put(bio);
diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c
index 656624314f0d..f6e865b2d543 100644
--- a/drivers/block/drbd/drbd_req.c
+++ b/drivers/block/drbd/drbd_req.c
@@ -203,7 +203,7 @@ void start_new_tl_epoch(struct drbd_connection *connection)
void complete_master_bio(struct drbd_device *device,
struct bio_and_error *m)
{
- m->bio->bi_error = m->error;
+ m->bio->bi_status = errno_to_blk_status(m->error);
bio_endio(m->bio);
dec_ap_bio(device);
}
@@ -1157,7 +1157,7 @@ static void drbd_process_discard_req(struct drbd_request *req)
if (blkdev_issue_zeroout(bdev, req->i.sector, req->i.size >> 9,
GFP_NOIO, 0))
- req->private_bio->bi_error = -EIO;
+ req->private_bio->bi_status = BLK_STS_IOERR;
bio_endio(req->private_bio);
}
@@ -1225,7 +1225,7 @@ drbd_request_prepare(struct drbd_device *device, struct bio *bio, unsigned long
/* only pass the error to the upper layers.
* if user cannot handle io errors, that's not our business. */
drbd_err(device, "could not kmalloc() req\n");
- bio->bi_error = -ENOMEM;
+ bio->bi_status = BLK_STS_RESOURCE;
bio_endio(bio);
return ERR_PTR(-ENOMEM);
}
@@ -1560,7 +1560,7 @@ blk_qc_t drbd_make_request(struct request_queue *q, struct bio *bio)
struct drbd_device *device = (struct drbd_device *) q->queuedata;
unsigned long start_jif;
- blk_queue_split(q, &bio, q->bio_split);
+ blk_queue_split(q, &bio);
start_jif = jiffies;
diff --git a/drivers/block/drbd/drbd_req.h b/drivers/block/drbd/drbd_req.h
index eb49e7f2da91..9e1866ab238f 100644
--- a/drivers/block/drbd/drbd_req.h
+++ b/drivers/block/drbd/drbd_req.h
@@ -263,7 +263,7 @@ enum drbd_req_state_bits {
static inline void drbd_req_make_private_bio(struct drbd_request *req, struct bio *bio_src)
{
struct bio *bio;
- bio = bio_clone(bio_src, GFP_NOIO); /* XXX cannot fail?? */
+ bio = bio_clone_fast(bio_src, GFP_NOIO, drbd_io_bio_set);
req->private_bio = bio;
diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c
index 1afcb4e02d8d..1d8726a8df34 100644
--- a/drivers/block/drbd/drbd_worker.c
+++ b/drivers/block/drbd/drbd_worker.c
@@ -63,7 +63,7 @@ void drbd_md_endio(struct bio *bio)
struct drbd_device *device;
device = bio->bi_private;
- device->md_io.error = bio->bi_error;
+ device->md_io.error = blk_status_to_errno(bio->bi_status);
/* We grabbed an extra reference in _drbd_md_sync_page_io() to be able
* to timeout on the lower level device, and eventually detach from it.
@@ -177,13 +177,13 @@ void drbd_peer_request_endio(struct bio *bio)
bool is_discard = bio_op(bio) == REQ_OP_WRITE_ZEROES ||
bio_op(bio) == REQ_OP_DISCARD;
- if (bio->bi_error && __ratelimit(&drbd_ratelimit_state))
+ if (bio->bi_status && __ratelimit(&drbd_ratelimit_state))
drbd_warn(device, "%s: error=%d s=%llus\n",
is_write ? (is_discard ? "discard" : "write")
- : "read", bio->bi_error,
+ : "read", bio->bi_status,
(unsigned long long)peer_req->i.sector);
- if (bio->bi_error)
+ if (bio->bi_status)
set_bit(__EE_WAS_ERROR, &peer_req->flags);
bio_put(bio); /* no need for the bio anymore */
@@ -243,16 +243,16 @@ void drbd_request_endio(struct bio *bio)
if (__ratelimit(&drbd_ratelimit_state))
drbd_emerg(device, "delayed completion of aborted local request; disk-timeout may be too aggressive\n");
- if (!bio->bi_error)
+ if (!bio->bi_status)
drbd_panic_after_delayed_completion_of_aborted_request(device);
}
/* to avoid recursion in __req_mod */
- if (unlikely(bio->bi_error)) {
+ if (unlikely(bio->bi_status)) {
switch (bio_op(bio)) {
case REQ_OP_WRITE_ZEROES:
case REQ_OP_DISCARD:
- if (bio->bi_error == -EOPNOTSUPP)
+ if (bio->bi_status == BLK_STS_NOTSUPP)
what = DISCARD_COMPLETED_NOTSUPP;
else
what = DISCARD_COMPLETED_WITH_ERROR;
@@ -272,7 +272,7 @@ void drbd_request_endio(struct bio *bio)
}
bio_put(req->private_bio);
- req->private_bio = ERR_PTR(bio->bi_error);
+ req->private_bio = ERR_PTR(blk_status_to_errno(bio->bi_status));
/* not req_mod(), we need irqsave here! */
spin_lock_irqsave(&device->resource->req_lock, flags);
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index 60d4c7653178..ce823647a9c4 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -2202,7 +2202,7 @@ static int do_format(int drive, struct format_descr *tmp_format_req)
* =============================
*/
-static void floppy_end_request(struct request *req, int error)
+static void floppy_end_request(struct request *req, blk_status_t error)
{
unsigned int nr_sectors = current_count_sectors;
unsigned int drive = (unsigned long)req->rq_disk->private_data;
@@ -2263,7 +2263,7 @@ static void request_done(int uptodate)
DRWE->last_error_generation = DRS->generation;
}
spin_lock_irqsave(q->queue_lock, flags);
- floppy_end_request(req, -EIO);
+ floppy_end_request(req, BLK_STS_IOERR);
spin_unlock_irqrestore(q->queue_lock, flags);
}
}
@@ -3780,9 +3780,9 @@ static void floppy_rb0_cb(struct bio *bio)
struct rb0_cbdata *cbdata = (struct rb0_cbdata *)bio->bi_private;
int drive = cbdata->drive;
- if (bio->bi_error) {
+ if (bio->bi_status) {
pr_info("floppy: error %d while reading block 0\n",
- bio->bi_error);
+ bio->bi_status);
set_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags);
}
complete(&cbdata->complete);
@@ -4203,6 +4203,7 @@ static int __init do_floppy_init(void)
goto out_put_disk;
}
+ blk_queue_bounce_limit(disks[drive]->queue, BLK_BOUNCE_HIGH);
blk_queue_max_hw_sectors(disks[drive]->queue, 64);
disks[drive]->major = FLOPPY_MAJOR;
disks[drive]->first_minor = TOMINOR(drive);
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index ebbd0c3fe0ed..0de11444e317 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -221,7 +221,8 @@ static void __loop_update_dio(struct loop_device *lo, bool dio)
}
static int
-figure_loop_size(struct loop_device *lo, loff_t offset, loff_t sizelimit)
+figure_loop_size(struct loop_device *lo, loff_t offset, loff_t sizelimit,
+ loff_t logical_blocksize)
{
loff_t size = get_size(offset, sizelimit, lo->lo_backing_file);
sector_t x = (sector_t)size;
@@ -233,6 +234,12 @@ figure_loop_size(struct loop_device *lo, loff_t offset, loff_t sizelimit)
lo->lo_offset = offset;
if (lo->lo_sizelimit != sizelimit)
lo->lo_sizelimit = sizelimit;
+ if (lo->lo_flags & LO_FLAGS_BLOCKSIZE) {
+ lo->lo_logical_blocksize = logical_blocksize;
+ blk_queue_physical_block_size(lo->lo_queue, lo->lo_blocksize);
+ blk_queue_logical_block_size(lo->lo_queue,
+ lo->lo_logical_blocksize);
+ }
set_capacity(lo->lo_disk, x);
bd_set_size(bdev, (loff_t)get_capacity(bdev->bd_disk) << 9);
/* let user-space know about the new size */
@@ -457,7 +464,7 @@ static void lo_complete_rq(struct request *rq)
zero_fill_bio(bio);
}
- blk_mq_end_request(rq, cmd->ret < 0 ? -EIO : 0);
+ blk_mq_end_request(rq, cmd->ret < 0 ? BLK_STS_IOERR : BLK_STS_OK);
}
static void lo_rw_aio_complete(struct kiocb *iocb, long ret, long ret2)
@@ -813,6 +820,7 @@ static void loop_config_discard(struct loop_device *lo)
struct file *file = lo->lo_backing_file;
struct inode *inode = file->f_mapping->host;
struct request_queue *q = lo->lo_queue;
+ int lo_bits = 9;
/*
* We use punch hole to reclaim the free space used by the
@@ -832,8 +840,11 @@ 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);
- blk_queue_max_write_zeroes_sectors(q, UINT_MAX >> 9);
+ if (lo->lo_flags & LO_FLAGS_BLOCKSIZE)
+ lo_bits = blksize_bits(lo->lo_logical_blocksize);
+
+ blk_queue_max_discard_sectors(q, UINT_MAX >> lo_bits);
+ blk_queue_max_write_zeroes_sectors(q, UINT_MAX >> lo_bits);
queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q);
}
@@ -843,10 +854,16 @@ static void loop_unprepare_queue(struct loop_device *lo)
kthread_stop(lo->worker_task);
}
+static int loop_kthread_worker_fn(void *worker_ptr)
+{
+ current->flags |= PF_LESS_THROTTLE;
+ return kthread_worker_fn(worker_ptr);
+}
+
static int loop_prepare_queue(struct loop_device *lo)
{
kthread_init_worker(&lo->worker);
- lo->worker_task = kthread_run(kthread_worker_fn,
+ lo->worker_task = kthread_run(loop_kthread_worker_fn,
&lo->worker, "loop%d", lo->lo_number);
if (IS_ERR(lo->worker_task))
return -ENOMEM;
@@ -921,6 +938,7 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
lo->use_dio = false;
lo->lo_blocksize = lo_blocksize;
+ lo->lo_logical_blocksize = 512;
lo->lo_device = bdev;
lo->lo_flags = lo_flags;
lo->lo_backing_file = file;
@@ -1086,6 +1104,7 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
int err;
struct loop_func_table *xfer;
kuid_t uid = current_uid();
+ int lo_flags = lo->lo_flags;
if (lo->lo_encrypt_key_size &&
!uid_eq(lo->lo_key_owner, uid) &&
@@ -1118,12 +1137,30 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
if (err)
goto exit;
+ if (info->lo_flags & LO_FLAGS_BLOCKSIZE) {
+ if (!(lo->lo_flags & LO_FLAGS_BLOCKSIZE))
+ lo->lo_logical_blocksize = 512;
+ lo->lo_flags |= LO_FLAGS_BLOCKSIZE;
+ if (LO_INFO_BLOCKSIZE(info) != 512 &&
+ LO_INFO_BLOCKSIZE(info) != 1024 &&
+ LO_INFO_BLOCKSIZE(info) != 2048 &&
+ LO_INFO_BLOCKSIZE(info) != 4096)
+ return -EINVAL;
+ if (LO_INFO_BLOCKSIZE(info) > lo->lo_blocksize)
+ return -EINVAL;
+ }
+
if (lo->lo_offset != info->lo_offset ||
- lo->lo_sizelimit != info->lo_sizelimit)
- if (figure_loop_size(lo, info->lo_offset, info->lo_sizelimit)) {
+ lo->lo_sizelimit != info->lo_sizelimit ||
+ lo->lo_flags != lo_flags ||
+ ((lo->lo_flags & LO_FLAGS_BLOCKSIZE) &&
+ lo->lo_logical_blocksize != LO_INFO_BLOCKSIZE(info))) {
+ if (figure_loop_size(lo, info->lo_offset, info->lo_sizelimit,
+ LO_INFO_BLOCKSIZE(info))) {
err = -EFBIG;
goto exit;
}
+ }
loop_config_discard(lo);
@@ -1306,12 +1343,13 @@ loop_get_status64(struct loop_device *lo, struct loop_info64 __user *arg) {
return err;
}
-static int loop_set_capacity(struct loop_device *lo, struct block_device *bdev)
+static int loop_set_capacity(struct loop_device *lo)
{
if (unlikely(lo->lo_state != Lo_bound))
return -ENXIO;
- return figure_loop_size(lo, lo->lo_offset, lo->lo_sizelimit);
+ return figure_loop_size(lo, lo->lo_offset, lo->lo_sizelimit,
+ lo->lo_logical_blocksize);
}
static int loop_set_dio(struct loop_device *lo, unsigned long arg)
@@ -1369,7 +1407,7 @@ static int lo_ioctl(struct block_device *bdev, fmode_t mode,
case LOOP_SET_CAPACITY:
err = -EPERM;
if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN))
- err = loop_set_capacity(lo, bdev);
+ err = loop_set_capacity(lo);
break;
case LOOP_SET_DIRECT_IO:
err = -EPERM;
@@ -1645,7 +1683,7 @@ int loop_unregister_transfer(int number)
EXPORT_SYMBOL(loop_register_transfer);
EXPORT_SYMBOL(loop_unregister_transfer);
-static int loop_queue_rq(struct blk_mq_hw_ctx *hctx,
+static blk_status_t loop_queue_rq(struct blk_mq_hw_ctx *hctx,
const struct blk_mq_queue_data *bd)
{
struct loop_cmd *cmd = blk_mq_rq_to_pdu(bd->rq);
@@ -1654,7 +1692,7 @@ static int loop_queue_rq(struct blk_mq_hw_ctx *hctx,
blk_mq_start_request(bd->rq);
if (lo->lo_state != Lo_bound)
- return BLK_MQ_RQ_QUEUE_ERROR;
+ return BLK_STS_IOERR;
switch (req_op(cmd->rq)) {
case REQ_OP_FLUSH:
@@ -1669,7 +1707,7 @@ static int loop_queue_rq(struct blk_mq_hw_ctx *hctx,
kthread_queue_work(&lo->worker, &cmd->work);
- return BLK_MQ_RQ_QUEUE_OK;
+ return BLK_STS_OK;
}
static void loop_handle_cmd(struct loop_cmd *cmd)
diff --git a/drivers/block/loop.h b/drivers/block/loop.h
index fecd3f97ef8c..2c096b9a17b8 100644
--- a/drivers/block/loop.h
+++ b/drivers/block/loop.h
@@ -49,6 +49,7 @@ struct loop_device {
struct file * lo_backing_file;
struct block_device *lo_device;
unsigned lo_blocksize;
+ unsigned lo_logical_blocksize;
void *key_data;
gfp_t old_gfp_mask;
diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c
index 3a779a4f5653..61b046f256ca 100644
--- a/drivers/block/mtip32xx/mtip32xx.c
+++ b/drivers/block/mtip32xx/mtip32xx.c
@@ -532,7 +532,7 @@ static int mtip_read_log_page(struct mtip_port *port, u8 page, u16 *buffer,
static int mtip_get_smart_attr(struct mtip_port *port, unsigned int id,
struct smart_attr *attrib);
-static void mtip_complete_command(struct mtip_cmd *cmd, int status)
+static void mtip_complete_command(struct mtip_cmd *cmd, blk_status_t status)
{
struct request *req = blk_mq_rq_from_pdu(cmd);
@@ -568,7 +568,7 @@ static void mtip_handle_tfe(struct driver_data *dd)
if (test_bit(MTIP_PF_IC_ACTIVE_BIT, &port->flags)) {
cmd = mtip_cmd_from_tag(dd, MTIP_TAG_INTERNAL);
dbg_printk(MTIP_DRV_NAME " TFE for the internal command\n");
- mtip_complete_command(cmd, -EIO);
+ mtip_complete_command(cmd, BLK_STS_IOERR);
return;
}
@@ -667,7 +667,7 @@ static void mtip_handle_tfe(struct driver_data *dd)
tag,
fail_reason != NULL ?
fail_reason : "unknown");
- mtip_complete_command(cmd, -ENODATA);
+ mtip_complete_command(cmd, BLK_STS_MEDIUM);
continue;
}
}
@@ -690,7 +690,7 @@ static void mtip_handle_tfe(struct driver_data *dd)
dev_warn(&port->dd->pdev->dev,
"retiring tag %d\n", tag);
- mtip_complete_command(cmd, -EIO);
+ mtip_complete_command(cmd, BLK_STS_IOERR);
}
}
print_tags(dd, "reissued (TFE)", tagaccum, cmd_cnt);
@@ -1063,23 +1063,10 @@ static int mtip_exec_internal_command(struct mtip_port *port,
/* insert request and run queue */
blk_execute_rq(rq->q, NULL, rq, true);
- rv = int_cmd->status;
- if (rv < 0) {
- if (rv == -ERESTARTSYS) { /* interrupted */
- dev_err(&dd->pdev->dev,
- "Internal command [%02X] was interrupted after %u ms\n",
- fis->command,
- jiffies_to_msecs(jiffies - start));
- rv = -EINTR;
- goto exec_ic_exit;
- } else if (rv == 0) /* timeout */
- dev_err(&dd->pdev->dev,
- "Internal command did not complete [%02X] within timeout of %lu ms\n",
- fis->command, timeout);
- else
- dev_err(&dd->pdev->dev,
- "Internal command [%02X] wait returned code [%d] after %lu ms - unhandled\n",
- fis->command, rv, timeout);
+ if (int_cmd->status) {
+ dev_err(&dd->pdev->dev, "Internal command [%02X] failed %d\n",
+ fis->command, int_cmd->status);
+ rv = -EIO;
if (mtip_check_surprise_removal(dd->pdev) ||
test_bit(MTIP_DDF_REMOVE_PENDING_BIT,
@@ -2753,7 +2740,7 @@ static void mtip_abort_cmd(struct request *req, void *data,
dbg_printk(MTIP_DRV_NAME " Aborting request, tag = %d\n", req->tag);
clear_bit(req->tag, dd->port->cmds_to_issue);
- cmd->status = -EIO;
+ cmd->status = BLK_STS_IOERR;
mtip_softirq_done_fn(req);
}
@@ -3597,7 +3584,7 @@ static int mtip_submit_request(struct blk_mq_hw_ctx *hctx, struct request *rq)
int err;
err = mtip_send_trim(dd, blk_rq_pos(rq), blk_rq_sectors(rq));
- blk_mq_end_request(rq, err);
+ blk_mq_end_request(rq, err ? BLK_STS_IOERR : BLK_STS_OK);
return 0;
}
@@ -3633,8 +3620,8 @@ static bool mtip_check_unal_depth(struct blk_mq_hw_ctx *hctx,
return false;
}
-static int mtip_issue_reserved_cmd(struct blk_mq_hw_ctx *hctx,
- struct request *rq)
+static blk_status_t mtip_issue_reserved_cmd(struct blk_mq_hw_ctx *hctx,
+ struct request *rq)
{
struct driver_data *dd = hctx->queue->queuedata;
struct mtip_int_cmd *icmd = rq->special;
@@ -3642,7 +3629,7 @@ static int mtip_issue_reserved_cmd(struct blk_mq_hw_ctx *hctx,
struct mtip_cmd_sg *command_sg;
if (mtip_commands_active(dd->port))
- return BLK_MQ_RQ_QUEUE_BUSY;
+ return BLK_STS_RESOURCE;
/* Populate the SG list */
cmd->command_header->opts =
@@ -3666,10 +3653,10 @@ static int mtip_issue_reserved_cmd(struct blk_mq_hw_ctx *hctx,
blk_mq_start_request(rq);
mtip_issue_non_ncq_command(dd->port, rq->tag);
- return BLK_MQ_RQ_QUEUE_OK;
+ return 0;
}
-static int mtip_queue_rq(struct blk_mq_hw_ctx *hctx,
+static blk_status_t mtip_queue_rq(struct blk_mq_hw_ctx *hctx,
const struct blk_mq_queue_data *bd)
{
struct request *rq = bd->rq;
@@ -3681,15 +3668,14 @@ static int mtip_queue_rq(struct blk_mq_hw_ctx *hctx,
return mtip_issue_reserved_cmd(hctx, rq);
if (unlikely(mtip_check_unal_depth(hctx, rq)))
- return BLK_MQ_RQ_QUEUE_BUSY;
+ return BLK_STS_RESOURCE;
blk_mq_start_request(rq);
ret = mtip_submit_request(hctx, rq);
if (likely(!ret))
- return BLK_MQ_RQ_QUEUE_OK;
-
- return BLK_MQ_RQ_QUEUE_ERROR;
+ return BLK_STS_OK;
+ return BLK_STS_IOERR;
}
static void mtip_free_cmd(struct blk_mq_tag_set *set, struct request *rq,
@@ -3730,7 +3716,7 @@ static enum blk_eh_timer_return mtip_cmd_timeout(struct request *req,
if (reserved) {
struct mtip_cmd *cmd = blk_mq_rq_to_pdu(req);
- cmd->status = -ETIME;
+ cmd->status = BLK_STS_TIMEOUT;
return BLK_EH_HANDLED;
}
@@ -3961,7 +3947,7 @@ static void mtip_no_dev_cleanup(struct request *rq, void *data, bool reserv)
{
struct mtip_cmd *cmd = blk_mq_rq_to_pdu(rq);
- cmd->status = -ENODEV;
+ cmd->status = BLK_STS_IOERR;
blk_mq_complete_request(rq);
}
diff --git a/drivers/block/mtip32xx/mtip32xx.h b/drivers/block/mtip32xx/mtip32xx.h
index 37b8e3e0bb78..e8286af50e16 100644
--- a/drivers/block/mtip32xx/mtip32xx.h
+++ b/drivers/block/mtip32xx/mtip32xx.h
@@ -342,7 +342,7 @@ struct mtip_cmd {
int retries; /* The number of retries left for this command. */
int direction; /* Data transfer direction */
- int status;
+ blk_status_t status;
};
/* Structure used to describe a port. */
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index f3f191ba8ca4..977ec960dd2f 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -116,7 +116,7 @@ struct nbd_cmd {
int index;
int cookie;
struct completion send_complete;
- int status;
+ blk_status_t status;
};
#if IS_ENABLED(CONFIG_DEBUG_FS)
@@ -286,7 +286,7 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req,
struct nbd_config *config;
if (!refcount_inc_not_zero(&nbd->config_refs)) {
- cmd->status = -EIO;
+ cmd->status = BLK_STS_TIMEOUT;
return BLK_EH_HANDLED;
}
@@ -331,7 +331,7 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req,
"Connection timed out\n");
}
set_bit(NBD_TIMEDOUT, &config->runtime_flags);
- cmd->status = -EIO;
+ cmd->status = BLK_STS_IOERR;
sock_shutdown(nbd);
nbd_config_put(nbd);
@@ -400,6 +400,7 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
unsigned long size = blk_rq_bytes(req);
struct bio *bio;
u32 type;
+ u32 nbd_cmd_flags = 0;
u32 tag = blk_mq_unique_tag(req);
int sent = nsock->sent, skip = 0;
@@ -429,6 +430,9 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
return -EIO;
}
+ if (req->cmd_flags & REQ_FUA)
+ nbd_cmd_flags |= NBD_CMD_FLAG_FUA;
+
/* We did a partial send previously, and we at least sent the whole
* request struct, so just go and send the rest of the pages in the
* request.
@@ -442,7 +446,7 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
}
cmd->index = index;
cmd->cookie = nsock->cookie;
- request.type = htonl(type);
+ request.type = htonl(type | nbd_cmd_flags);
if (type != NBD_CMD_FLUSH) {
request.from = cpu_to_be64((u64)blk_rq_pos(req) << 9);
request.len = htonl(size);
@@ -465,7 +469,7 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
nsock->pending = req;
nsock->sent = sent;
}
- return BLK_MQ_RQ_QUEUE_BUSY;
+ return BLK_STS_RESOURCE;
}
dev_err_ratelimited(disk_to_dev(nbd->disk),
"Send control failed (result %d)\n", result);
@@ -506,7 +510,7 @@ send_pages:
*/
nsock->pending = req;
nsock->sent = sent;
- return BLK_MQ_RQ_QUEUE_BUSY;
+ return BLK_STS_RESOURCE;
}
dev_err(disk_to_dev(nbd->disk),
"Send data failed (result %d)\n",
@@ -574,7 +578,7 @@ 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));
- cmd->status = -EIO;
+ cmd->status = BLK_STS_IOERR;
return cmd;
}
@@ -599,7 +603,7 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
*/
if (nbd_disconnected(config) ||
config->num_connections <= 1) {
- cmd->status = -EIO;
+ cmd->status = BLK_STS_IOERR;
return cmd;
}
return ERR_PTR(-EIO);
@@ -651,7 +655,7 @@ 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);
- cmd->status = -EIO;
+ cmd->status = BLK_STS_IOERR;
blk_mq_complete_request(req);
}
@@ -740,7 +744,7 @@ static int nbd_handle_cmd(struct nbd_cmd *cmd, int index)
nbd_config_put(nbd);
return -EINVAL;
}
- cmd->status = 0;
+ cmd->status = BLK_STS_OK;
again:
nsock = config->socks[index];
mutex_lock(&nsock->tx_lock);
@@ -794,7 +798,7 @@ out:
return ret;
}
-static int nbd_queue_rq(struct blk_mq_hw_ctx *hctx,
+static blk_status_t nbd_queue_rq(struct blk_mq_hw_ctx *hctx,
const struct blk_mq_queue_data *bd)
{
struct nbd_cmd *cmd = blk_mq_rq_to_pdu(bd->rq);
@@ -818,13 +822,9 @@ static int nbd_queue_rq(struct blk_mq_hw_ctx *hctx,
* appropriate.
*/
ret = nbd_handle_cmd(cmd, hctx->queue_num);
- if (ret < 0)
- ret = BLK_MQ_RQ_QUEUE_ERROR;
- if (!ret)
- ret = BLK_MQ_RQ_QUEUE_OK;
complete(&cmd->send_complete);
- return ret;
+ return ret < 0 ? BLK_STS_IOERR : BLK_STS_OK;
}
static int nbd_add_socket(struct nbd_device *nbd, unsigned long arg,
@@ -910,6 +910,7 @@ static int nbd_reconnect_socket(struct nbd_device *nbd, unsigned long arg)
continue;
}
sk_set_memalloc(sock->sk);
+ sock->sk->sk_sndtimeo = nbd->tag_set.timeout;
atomic_inc(&config->recv_threads);
refcount_inc(&nbd->config_refs);
old = nsock->sock;
@@ -957,8 +958,12 @@ static void nbd_parse_flags(struct nbd_device *nbd)
set_disk_ro(nbd->disk, false);
if (config->flags & NBD_FLAG_SEND_TRIM)
queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, nbd->disk->queue);
- if (config->flags & NBD_FLAG_SEND_FLUSH)
- blk_queue_write_cache(nbd->disk->queue, true, false);
+ if (config->flags & NBD_FLAG_SEND_FLUSH) {
+ if (config->flags & NBD_FLAG_SEND_FUA)
+ blk_queue_write_cache(nbd->disk->queue, true, true);
+ else
+ blk_queue_write_cache(nbd->disk->queue, true, false);
+ }
else
blk_queue_write_cache(nbd->disk->queue, false, false);
}
@@ -1071,6 +1076,7 @@ static int nbd_start_device(struct nbd_device *nbd)
return -ENOMEM;
}
sk_set_memalloc(config->socks[i]->sock->sk);
+ config->socks[i]->sock->sk->sk_sndtimeo = nbd->tag_set.timeout;
atomic_inc(&config->recv_threads);
refcount_inc(&nbd->config_refs);
INIT_WORK(&args->work, recv_work);
@@ -1305,6 +1311,8 @@ static int nbd_dbg_flags_show(struct seq_file *s, void *unused)
seq_puts(s, "NBD_FLAG_READ_ONLY\n");
if (flags & NBD_FLAG_SEND_FLUSH)
seq_puts(s, "NBD_FLAG_SEND_FLUSH\n");
+ if (flags & NBD_FLAG_SEND_FUA)
+ seq_puts(s, "NBD_FLAG_SEND_FUA\n");
if (flags & NBD_FLAG_SEND_TRIM)
seq_puts(s, "NBD_FLAG_SEND_TRIM\n");
diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c
index d946e1eeac8e..71f4422eba81 100644
--- a/drivers/block/null_blk.c
+++ b/drivers/block/null_blk.c
@@ -35,7 +35,8 @@ struct nullb {
struct request_queue *q;
struct gendisk *disk;
struct nvm_dev *ndev;
- struct blk_mq_tag_set tag_set;
+ struct blk_mq_tag_set *tag_set;
+ struct blk_mq_tag_set __tag_set;
struct hrtimer timer;
unsigned int queue_depth;
spinlock_t lock;
@@ -50,6 +51,7 @@ static struct mutex lock;
static int null_major;
static int nullb_indexes;
static struct kmem_cache *ppa_cache;
+static struct blk_mq_tag_set tag_set;
enum {
NULL_IRQ_NONE = 0,
@@ -109,7 +111,7 @@ static int bs = 512;
module_param(bs, int, S_IRUGO);
MODULE_PARM_DESC(bs, "Block size (in bytes)");
-static int nr_devices = 2;
+static int nr_devices = 1;
module_param(nr_devices, int, S_IRUGO);
MODULE_PARM_DESC(nr_devices, "Number of devices to register");
@@ -121,6 +123,10 @@ static bool blocking;
module_param(blocking, bool, S_IRUGO);
MODULE_PARM_DESC(blocking, "Register as a blocking blk-mq driver device");
+static bool shared_tags;
+module_param(shared_tags, bool, S_IRUGO);
+MODULE_PARM_DESC(shared_tags, "Share tag set between devices for blk-mq");
+
static int irqmode = NULL_IRQ_SOFTIRQ;
static int null_set_irqmode(const char *str, const struct kernel_param *kp)
@@ -229,11 +235,11 @@ static void end_cmd(struct nullb_cmd *cmd)
switch (queue_mode) {
case NULL_Q_MQ:
- blk_mq_end_request(cmd->rq, 0);
+ blk_mq_end_request(cmd->rq, BLK_STS_OK);
return;
case NULL_Q_RQ:
INIT_LIST_HEAD(&cmd->rq->queuelist);
- blk_end_request_all(cmd->rq, 0);
+ blk_end_request_all(cmd->rq, BLK_STS_OK);
break;
case NULL_Q_BIO:
bio_endio(cmd->bio);
@@ -356,7 +362,7 @@ static void null_request_fn(struct request_queue *q)
}
}
-static int null_queue_rq(struct blk_mq_hw_ctx *hctx,
+static blk_status_t null_queue_rq(struct blk_mq_hw_ctx *hctx,
const struct blk_mq_queue_data *bd)
{
struct nullb_cmd *cmd = blk_mq_rq_to_pdu(bd->rq);
@@ -373,34 +379,11 @@ static int null_queue_rq(struct blk_mq_hw_ctx *hctx,
blk_mq_start_request(bd->rq);
null_handle_cmd(cmd);
- return BLK_MQ_RQ_QUEUE_OK;
-}
-
-static void null_init_queue(struct nullb *nullb, struct nullb_queue *nq)
-{
- BUG_ON(!nullb);
- BUG_ON(!nq);
-
- init_waitqueue_head(&nq->wait);
- nq->queue_depth = nullb->queue_depth;
-}
-
-static int null_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
- unsigned int index)
-{
- struct nullb *nullb = data;
- struct nullb_queue *nq = &nullb->queues[index];
-
- hctx->driver_data = nq;
- null_init_queue(nullb, nq);
- nullb->nr_queues++;
-
- return 0;
+ return BLK_STS_OK;
}
static const struct blk_mq_ops null_mq_ops = {
.queue_rq = null_queue_rq,
- .init_hctx = null_init_hctx,
.complete = null_softirq_done_fn,
};
@@ -422,11 +405,12 @@ static void cleanup_queues(struct nullb *nullb)
#ifdef CONFIG_NVM
-static void null_lnvm_end_io(struct request *rq, int error)
+static void null_lnvm_end_io(struct request *rq, blk_status_t status)
{
struct nvm_rq *rqd = rq->end_io_data;
- rqd->error = error;
+ /* XXX: lighnvm core seems to expect NVM_RSP_* values here.. */
+ rqd->error = status ? -EIO : 0;
nvm_end_io(rqd);
blk_put_request(rq);
@@ -591,8 +575,8 @@ static void null_del_dev(struct nullb *nullb)
else
del_gendisk(nullb->disk);
blk_cleanup_queue(nullb->q);
- if (queue_mode == NULL_Q_MQ)
- blk_mq_free_tag_set(&nullb->tag_set);
+ if (queue_mode == NULL_Q_MQ && nullb->tag_set == &nullb->__tag_set)
+ blk_mq_free_tag_set(nullb->tag_set);
if (!use_lightnvm)
put_disk(nullb->disk);
cleanup_queues(nullb);
@@ -614,6 +598,32 @@ static const struct block_device_operations null_fops = {
.release = null_release,
};
+static void null_init_queue(struct nullb *nullb, struct nullb_queue *nq)
+{
+ BUG_ON(!nullb);
+ BUG_ON(!nq);
+
+ init_waitqueue_head(&nq->wait);
+ nq->queue_depth = nullb->queue_depth;
+}
+
+static void null_init_queues(struct nullb *nullb)
+{
+ struct request_queue *q = nullb->q;
+ struct blk_mq_hw_ctx *hctx;
+ struct nullb_queue *nq;
+ int i;
+
+ queue_for_each_hw_ctx(q, hctx, i) {
+ if (!hctx->nr_ctx || !hctx->tags)
+ continue;
+ nq = &nullb->queues[i];
+ hctx->driver_data = nq;
+ null_init_queue(nullb, nq);
+ nullb->nr_queues++;
+ }
+}
+
static int setup_commands(struct nullb_queue *nq)
{
struct nullb_cmd *cmd;
@@ -694,6 +704,22 @@ static int null_gendisk_register(struct nullb *nullb)
return 0;
}
+static int null_init_tag_set(struct blk_mq_tag_set *set)
+{
+ set->ops = &null_mq_ops;
+ set->nr_hw_queues = submit_queues;
+ set->queue_depth = hw_queue_depth;
+ set->numa_node = home_node;
+ set->cmd_size = sizeof(struct nullb_cmd);
+ set->flags = BLK_MQ_F_SHOULD_MERGE;
+ set->driver_data = NULL;
+
+ if (blocking)
+ set->flags |= BLK_MQ_F_BLOCKING;
+
+ return blk_mq_alloc_tag_set(set);
+}
+
static int null_add_dev(void)
{
struct nullb *nullb;
@@ -715,26 +741,23 @@ static int null_add_dev(void)
goto out_free_nullb;
if (queue_mode == NULL_Q_MQ) {
- nullb->tag_set.ops = &null_mq_ops;
- nullb->tag_set.nr_hw_queues = submit_queues;
- nullb->tag_set.queue_depth = hw_queue_depth;
- nullb->tag_set.numa_node = home_node;
- nullb->tag_set.cmd_size = sizeof(struct nullb_cmd);
- 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 (shared_tags) {
+ nullb->tag_set = &tag_set;
+ rv = 0;
+ } else {
+ nullb->tag_set = &nullb->__tag_set;
+ rv = null_init_tag_set(nullb->tag_set);
+ }
+
if (rv)
goto out_cleanup_queues;
- nullb->q = blk_mq_init_queue(&nullb->tag_set);
+ nullb->q = blk_mq_init_queue(nullb->tag_set);
if (IS_ERR(nullb->q)) {
rv = -ENOMEM;
goto out_cleanup_tags;
}
+ null_init_queues(nullb);
} else if (queue_mode == NULL_Q_BIO) {
nullb->q = blk_alloc_queue_node(GFP_KERNEL, home_node);
if (!nullb->q) {
@@ -787,8 +810,8 @@ static int null_add_dev(void)
out_cleanup_blk_queue:
blk_cleanup_queue(nullb->q);
out_cleanup_tags:
- if (queue_mode == NULL_Q_MQ)
- blk_mq_free_tag_set(&nullb->tag_set);
+ if (queue_mode == NULL_Q_MQ && nullb->tag_set == &nullb->__tag_set)
+ blk_mq_free_tag_set(nullb->tag_set);
out_cleanup_queues:
cleanup_queues(nullb);
out_free_nullb:
@@ -821,6 +844,9 @@ static int __init null_init(void)
queue_mode = NULL_Q_MQ;
}
+ if (queue_mode == NULL_Q_MQ && shared_tags)
+ null_init_tag_set(&tag_set);
+
if (queue_mode == NULL_Q_MQ && use_per_node_hctx) {
if (submit_queues < nr_online_nodes) {
pr_warn("null_blk: submit_queues param is set to %u.",
@@ -881,6 +907,9 @@ static void __exit null_exit(void)
}
mutex_unlock(&lock);
+ if (queue_mode == NULL_Q_MQ && shared_tags)
+ blk_mq_free_tag_set(&tag_set);
+
kmem_cache_destroy(ppa_cache);
}
diff --git a/drivers/block/paride/pcd.c b/drivers/block/paride/pcd.c
index b1267ef34d5a..7b8c6368beb7 100644
--- a/drivers/block/paride/pcd.c
+++ b/drivers/block/paride/pcd.c
@@ -305,6 +305,7 @@ static void pcd_init_units(void)
put_disk(disk);
continue;
}
+ blk_queue_bounce_limit(disk->queue, BLK_BOUNCE_HIGH);
cd->disk = disk;
cd->pi = &cd->pia;
cd->present = 0;
@@ -783,7 +784,7 @@ static void pcd_request(void)
ps_set_intr(do_pcd_read, NULL, 0, nice);
return;
} else {
- __blk_end_request_all(pcd_req, -EIO);
+ __blk_end_request_all(pcd_req, BLK_STS_IOERR);
pcd_req = NULL;
}
}
@@ -794,7 +795,7 @@ static void do_pcd_request(struct request_queue *q)
pcd_request();
}
-static inline void next_request(int err)
+static inline void next_request(blk_status_t err)
{
unsigned long saved_flags;
@@ -837,7 +838,7 @@ static void pcd_start(void)
if (pcd_command(pcd_current, rd_cmd, 2048, "read block")) {
pcd_bufblk = -1;
- next_request(-EIO);
+ next_request(BLK_STS_IOERR);
return;
}
@@ -871,7 +872,7 @@ static void do_pcd_read_drq(void)
return;
}
pcd_bufblk = -1;
- next_request(-EIO);
+ next_request(BLK_STS_IOERR);
return;
}
diff --git a/drivers/block/paride/pd.c b/drivers/block/paride/pd.c
index 7d2402f90978..27a44b97393a 100644
--- a/drivers/block/paride/pd.c
+++ b/drivers/block/paride/pd.c
@@ -438,7 +438,7 @@ static void run_fsm(void)
phase = NULL;
spin_lock_irqsave(&pd_lock, saved_flags);
if (!__blk_end_request_cur(pd_req,
- res == Ok ? 0 : -EIO)) {
+ res == Ok ? 0 : BLK_STS_IOERR)) {
if (!set_next_request())
stop = 1;
}
@@ -863,6 +863,7 @@ static void pd_probe_drive(struct pd_unit *disk)
return;
}
blk_queue_max_hw_sectors(p->queue, cluster);
+ blk_queue_bounce_limit(p->queue, BLK_BOUNCE_HIGH);
if (disk->drive == -1) {
for (disk->drive = 0; disk->drive <= 1; disk->drive++)
diff --git a/drivers/block/paride/pf.c b/drivers/block/paride/pf.c
index f24ca7315ddc..eef7a91f667d 100644
--- a/drivers/block/paride/pf.c
+++ b/drivers/block/paride/pf.c
@@ -293,6 +293,7 @@ static void __init pf_init_units(void)
return;
}
blk_queue_max_segments(disk->queue, cluster);
+ blk_queue_bounce_limit(disk->queue, BLK_BOUNCE_HIGH);
pf->disk = disk;
pf->pi = &pf->pia;
pf->media_status = PF_NM;
@@ -801,7 +802,7 @@ static int set_next_request(void)
return pf_req != NULL;
}
-static void pf_end_request(int err)
+static void pf_end_request(blk_status_t err)
{
if (pf_req && !__blk_end_request_cur(pf_req, err))
pf_req = NULL;
@@ -821,7 +822,7 @@ repeat:
pf_count = blk_rq_cur_sectors(pf_req);
if (pf_block + pf_count > get_capacity(pf_req->rq_disk)) {
- pf_end_request(-EIO);
+ pf_end_request(BLK_STS_IOERR);
goto repeat;
}
@@ -836,7 +837,7 @@ repeat:
pi_do_claimed(pf_current->pi, do_pf_write);
else {
pf_busy = 0;
- pf_end_request(-EIO);
+ pf_end_request(BLK_STS_IOERR);
goto repeat;
}
}
@@ -868,7 +869,7 @@ static int pf_next_buf(void)
return 0;
}
-static inline void next_request(int err)
+static inline void next_request(blk_status_t err)
{
unsigned long saved_flags;
@@ -896,7 +897,7 @@ static void do_pf_read_start(void)
pi_do_claimed(pf_current->pi, do_pf_read_start);
return;
}
- next_request(-EIO);
+ next_request(BLK_STS_IOERR);
return;
}
pf_mask = STAT_DRQ;
@@ -915,7 +916,7 @@ static void do_pf_read_drq(void)
pi_do_claimed(pf_current->pi, do_pf_read_start);
return;
}
- next_request(-EIO);
+ next_request(BLK_STS_IOERR);
return;
}
pi_read_block(pf_current->pi, pf_buf, 512);
@@ -942,7 +943,7 @@ static void do_pf_write_start(void)
pi_do_claimed(pf_current->pi, do_pf_write_start);
return;
}
- next_request(-EIO);
+ next_request(BLK_STS_IOERR);
return;
}
@@ -955,7 +956,7 @@ static void do_pf_write_start(void)
pi_do_claimed(pf_current->pi, do_pf_write_start);
return;
}
- next_request(-EIO);
+ next_request(BLK_STS_IOERR);
return;
}
pi_write_block(pf_current->pi, pf_buf, 512);
@@ -975,7 +976,7 @@ static void do_pf_write_done(void)
pi_do_claimed(pf_current->pi, do_pf_write_start);
return;
}
- next_request(-EIO);
+ next_request(BLK_STS_IOERR);
return;
}
pi_disconnect(pf_current->pi);
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index 205b865ebeb9..467beca397a2 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -98,6 +98,7 @@ static int write_congestion_on = PKT_WRITE_CONGESTION_ON;
static int write_congestion_off = PKT_WRITE_CONGESTION_OFF;
static struct mutex ctl_mutex; /* Serialize open/close/setup/teardown */
static mempool_t *psd_pool;
+static struct bio_set *pkt_bio_set;
static struct class *class_pktcdvd = NULL; /* /sys/class/pktcdvd */
static struct dentry *pkt_debugfs_root = NULL; /* /sys/kernel/debug/pktcdvd */
@@ -707,7 +708,6 @@ static int pkt_generic_packet(struct pktcdvd_device *pd, struct packet_command *
REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, __GFP_RECLAIM);
if (IS_ERR(rq))
return PTR_ERR(rq);
- scsi_req_init(rq);
if (cgc->buflen) {
ret = blk_rq_map_kern(q, rq, cgc->buffer, cgc->buflen,
@@ -952,9 +952,9 @@ static void pkt_end_io_read(struct bio *bio)
pkt_dbg(2, pd, "bio=%p sec0=%llx sec=%llx err=%d\n",
bio, (unsigned long long)pkt->sector,
- (unsigned long long)bio->bi_iter.bi_sector, bio->bi_error);
+ (unsigned long long)bio->bi_iter.bi_sector, bio->bi_status);
- if (bio->bi_error)
+ if (bio->bi_status)
atomic_inc(&pkt->io_errors);
if (atomic_dec_and_test(&pkt->io_wait)) {
atomic_inc(&pkt->run_sm);
@@ -969,7 +969,7 @@ static void pkt_end_io_packet_write(struct bio *bio)
struct pktcdvd_device *pd = pkt->pd;
BUG_ON(!pd);
- pkt_dbg(2, pd, "id=%d, err=%d\n", pkt->id, bio->bi_error);
+ pkt_dbg(2, pd, "id=%d, err=%d\n", pkt->id, bio->bi_status);
pd->stats.pkt_ended++;
@@ -1305,16 +1305,16 @@ static void pkt_start_write(struct pktcdvd_device *pd, struct packet_data *pkt)
pkt_queue_bio(pd, pkt->w_bio);
}
-static void pkt_finish_packet(struct packet_data *pkt, int error)
+static void pkt_finish_packet(struct packet_data *pkt, blk_status_t status)
{
struct bio *bio;
- if (error)
+ if (status)
pkt->cache_valid = 0;
/* Finish all bios corresponding to this packet */
while ((bio = bio_list_pop(&pkt->orig_bios))) {
- bio->bi_error = error;
+ bio->bi_status = status;
bio_endio(bio);
}
}
@@ -1349,7 +1349,7 @@ static void pkt_run_state_machine(struct pktcdvd_device *pd, struct packet_data
if (atomic_read(&pkt->io_wait) > 0)
return;
- if (!pkt->w_bio->bi_error) {
+ if (!pkt->w_bio->bi_status) {
pkt_set_state(pkt, PACKET_FINISHED_STATE);
} else {
pkt_set_state(pkt, PACKET_RECOVERY_STATE);
@@ -1366,7 +1366,7 @@ static void pkt_run_state_machine(struct pktcdvd_device *pd, struct packet_data
break;
case PACKET_FINISHED_STATE:
- pkt_finish_packet(pkt, pkt->w_bio->bi_error);
+ pkt_finish_packet(pkt, pkt->w_bio->bi_status);
return;
default:
@@ -2301,7 +2301,7 @@ static void pkt_end_io_read_cloned(struct bio *bio)
struct packet_stacked_data *psd = bio->bi_private;
struct pktcdvd_device *pd = psd->pd;
- psd->bio->bi_error = bio->bi_error;
+ psd->bio->bi_status = bio->bi_status;
bio_put(bio);
bio_endio(psd->bio);
mempool_free(psd, psd_pool);
@@ -2310,7 +2310,7 @@ static void pkt_end_io_read_cloned(struct bio *bio)
static void pkt_make_request_read(struct pktcdvd_device *pd, struct bio *bio)
{
- struct bio *cloned_bio = bio_clone(bio, GFP_NOIO);
+ struct bio *cloned_bio = bio_clone_fast(bio, GFP_NOIO, pkt_bio_set);
struct packet_stacked_data *psd = mempool_alloc(psd_pool, GFP_NOIO);
psd->pd = pd;
@@ -2412,9 +2412,7 @@ static blk_qc_t pkt_make_request(struct request_queue *q, struct bio *bio)
char b[BDEVNAME_SIZE];
struct bio *split;
- blk_queue_bounce(q, &bio);
-
- blk_queue_split(q, &bio, q->bio_split);
+ blk_queue_split(q, &bio);
pd = q->queuedata;
if (!pd) {
@@ -2455,7 +2453,7 @@ static blk_qc_t pkt_make_request(struct request_queue *q, struct bio *bio)
split = bio_split(bio, last_zone -
bio->bi_iter.bi_sector,
- GFP_NOIO, fs_bio_set);
+ GFP_NOIO, pkt_bio_set);
bio_chain(split, bio);
} else {
split = bio;
@@ -2583,6 +2581,11 @@ static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev)
bdev = bdget(dev);
if (!bdev)
return -ENOMEM;
+ if (!blk_queue_scsi_passthrough(bdev_get_queue(bdev))) {
+ WARN_ONCE(true, "Attempt to register a non-SCSI queue\n");
+ bdput(bdev);
+ return -EINVAL;
+ }
ret = blkdev_get(bdev, FMODE_READ | FMODE_NDELAY, NULL);
if (ret)
return ret;
@@ -2919,6 +2922,11 @@ static int __init pkt_init(void)
sizeof(struct packet_stacked_data));
if (!psd_pool)
return -ENOMEM;
+ pkt_bio_set = bioset_create(BIO_POOL_SIZE, 0, 0);
+ if (!pkt_bio_set) {
+ mempool_destroy(psd_pool);
+ return -ENOMEM;
+ }
ret = register_blkdev(pktdev_major, DRIVER_NAME);
if (ret < 0) {
@@ -2951,6 +2959,7 @@ out:
unregister_blkdev(pktdev_major, DRIVER_NAME);
out2:
mempool_destroy(psd_pool);
+ bioset_free(pkt_bio_set);
return ret;
}
@@ -2964,6 +2973,7 @@ static void __exit pkt_exit(void)
unregister_blkdev(pktdev_major, DRIVER_NAME);
mempool_destroy(psd_pool);
+ bioset_free(pkt_bio_set);
}
MODULE_DESCRIPTION("Packet writing layer for CD/DVD drives");
diff --git a/drivers/block/ps3disk.c b/drivers/block/ps3disk.c
index a809e3e9feb8..075662f2cf46 100644
--- a/drivers/block/ps3disk.c
+++ b/drivers/block/ps3disk.c
@@ -158,7 +158,7 @@ static int ps3disk_submit_request_sg(struct ps3_storage_device *dev,
if (res) {
dev_err(&dev->sbd.core, "%s:%u: %s failed %d\n", __func__,
__LINE__, op, res);
- __blk_end_request_all(req, -EIO);
+ __blk_end_request_all(req, BLK_STS_IOERR);
return 0;
}
@@ -180,7 +180,7 @@ static int ps3disk_submit_flush_request(struct ps3_storage_device *dev,
if (res) {
dev_err(&dev->sbd.core, "%s:%u: sync cache failed 0x%llx\n",
__func__, __LINE__, res);
- __blk_end_request_all(req, -EIO);
+ __blk_end_request_all(req, BLK_STS_IOERR);
return 0;
}
@@ -208,7 +208,7 @@ static void ps3disk_do_request(struct ps3_storage_device *dev,
break;
default:
blk_dump_rq_flags(req, DEVICE_NAME " bad request");
- __blk_end_request_all(req, -EIO);
+ __blk_end_request_all(req, BLK_STS_IOERR);
}
}
}
@@ -231,7 +231,8 @@ static irqreturn_t ps3disk_interrupt(int irq, void *data)
struct ps3_storage_device *dev = data;
struct ps3disk_private *priv;
struct request *req;
- int res, read, error;
+ int res, read;
+ blk_status_t error;
u64 tag, status;
const char *op;
@@ -269,7 +270,7 @@ static irqreturn_t ps3disk_interrupt(int irq, void *data)
if (status) {
dev_dbg(&dev->sbd.core, "%s:%u: %s failed 0x%llx\n", __func__,
__LINE__, op, status);
- error = -EIO;
+ error = BLK_STS_IOERR;
} else {
dev_dbg(&dev->sbd.core, "%s:%u: %s completed\n", __func__,
__LINE__, op);
diff --git a/drivers/block/ps3vram.c b/drivers/block/ps3vram.c
index 456b4fe21559..e0e81cacd781 100644
--- a/drivers/block/ps3vram.c
+++ b/drivers/block/ps3vram.c
@@ -428,7 +428,7 @@ static void ps3vram_cache_cleanup(struct ps3_system_bus_device *dev)
kfree(priv->cache.tags);
}
-static int ps3vram_read(struct ps3_system_bus_device *dev, loff_t from,
+static blk_status_t ps3vram_read(struct ps3_system_bus_device *dev, loff_t from,
size_t len, size_t *retlen, u_char *buf)
{
struct ps3vram_priv *priv = ps3_system_bus_get_drvdata(dev);
@@ -438,7 +438,7 @@ static int ps3vram_read(struct ps3_system_bus_device *dev, loff_t from,
(unsigned int)from, len);
if (from >= priv->size)
- return -EIO;
+ return BLK_STS_IOERR;
if (len > priv->size - from)
len = priv->size - from;
@@ -472,14 +472,14 @@ static int ps3vram_read(struct ps3_system_bus_device *dev, loff_t from,
return 0;
}
-static int ps3vram_write(struct ps3_system_bus_device *dev, loff_t to,
+static blk_status_t ps3vram_write(struct ps3_system_bus_device *dev, loff_t to,
size_t len, size_t *retlen, const u_char *buf)
{
struct ps3vram_priv *priv = ps3_system_bus_get_drvdata(dev);
unsigned int cached, count;
if (to >= priv->size)
- return -EIO;
+ return BLK_STS_IOERR;
if (len > priv->size - to)
len = priv->size - to;
@@ -554,7 +554,7 @@ static struct bio *ps3vram_do_bio(struct ps3_system_bus_device *dev,
int write = bio_data_dir(bio) == WRITE;
const char *op = write ? "write" : "read";
loff_t offset = bio->bi_iter.bi_sector << 9;
- int error = 0;
+ blk_status_t error = 0;
struct bio_vec bvec;
struct bvec_iter iter;
struct bio *next;
@@ -578,7 +578,7 @@ static struct bio *ps3vram_do_bio(struct ps3_system_bus_device *dev,
if (retlen != len) {
dev_err(&dev->core, "Short %s\n", op);
- error = -EIO;
+ error = BLK_STS_IOERR;
goto out;
}
@@ -593,7 +593,7 @@ out:
next = bio_list_peek(&priv->list);
spin_unlock_irq(&priv->lock);
- bio->bi_error = error;
+ bio->bi_status = error;
bio_endio(bio);
return next;
}
@@ -606,7 +606,7 @@ static blk_qc_t ps3vram_make_request(struct request_queue *q, struct bio *bio)
dev_dbg(&dev->core, "%s\n", __func__);
- blk_queue_split(q, &bio, q->bio_split);
+ blk_queue_split(q, &bio);
spin_lock_irq(&priv->lock);
busy = !bio_list_empty(&priv->list);
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index c16f74547804..b008b6a98098 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -442,6 +442,8 @@ static DEFINE_SPINLOCK(rbd_client_list_lock);
static struct kmem_cache *rbd_img_request_cache;
static struct kmem_cache *rbd_obj_request_cache;
+static struct bio_set *rbd_bio_clone;
+
static int rbd_major;
static DEFINE_IDA(rbd_dev_id_ida);
@@ -1363,7 +1365,7 @@ static struct bio *bio_clone_range(struct bio *bio_src,
{
struct bio *bio;
- bio = bio_clone(bio_src, gfpmask);
+ bio = bio_clone_fast(bio_src, gfpmask, rbd_bio_clone);
if (!bio)
return NULL; /* ENOMEM */
@@ -2293,11 +2295,13 @@ static bool rbd_img_obj_end_request(struct rbd_obj_request *obj_request)
rbd_assert(img_request->obj_request != NULL);
more = obj_request->which < img_request->obj_request_count - 1;
} else {
+ blk_status_t status = errno_to_blk_status(result);
+
rbd_assert(img_request->rq != NULL);
- more = blk_update_request(img_request->rq, result, xferred);
+ more = blk_update_request(img_request->rq, status, xferred);
if (!more)
- __blk_mq_end_request(img_request->rq, result);
+ __blk_mq_end_request(img_request->rq, status);
}
return more;
@@ -4150,17 +4154,17 @@ err_rq:
obj_op_name(op_type), length, offset, result);
ceph_put_snap_context(snapc);
err:
- blk_mq_end_request(rq, result);
+ blk_mq_end_request(rq, errno_to_blk_status(result));
}
-static int rbd_queue_rq(struct blk_mq_hw_ctx *hctx,
+static blk_status_t rbd_queue_rq(struct blk_mq_hw_ctx *hctx,
const struct blk_mq_queue_data *bd)
{
struct request *rq = bd->rq;
struct work_struct *work = blk_mq_rq_to_pdu(rq);
queue_work(rbd_wq, work);
- return BLK_MQ_RQ_QUEUE_OK;
+ return BLK_STS_OK;
}
static void rbd_free_disk(struct rbd_device *rbd_dev)
@@ -6414,8 +6418,16 @@ static int rbd_slab_init(void)
if (!rbd_obj_request_cache)
goto out_err;
+ rbd_assert(!rbd_bio_clone);
+ rbd_bio_clone = bioset_create(BIO_POOL_SIZE, 0, 0);
+ if (!rbd_bio_clone)
+ goto out_err_clone;
+
return 0;
+out_err_clone:
+ kmem_cache_destroy(rbd_obj_request_cache);
+ rbd_obj_request_cache = NULL;
out_err:
kmem_cache_destroy(rbd_img_request_cache);
rbd_img_request_cache = NULL;
@@ -6431,6 +6443,10 @@ static void rbd_slab_exit(void)
rbd_assert(rbd_img_request_cache);
kmem_cache_destroy(rbd_img_request_cache);
rbd_img_request_cache = NULL;
+
+ rbd_assert(rbd_bio_clone);
+ bioset_free(rbd_bio_clone);
+ rbd_bio_clone = NULL;
}
static int __init rbd_init(void)
diff --git a/drivers/block/rsxx/dev.c b/drivers/block/rsxx/dev.c
index 9c566364ac9c..7f4acebf4657 100644
--- a/drivers/block/rsxx/dev.c
+++ b/drivers/block/rsxx/dev.c
@@ -149,9 +149,9 @@ static blk_qc_t rsxx_make_request(struct request_queue *q, struct bio *bio)
{
struct rsxx_cardinfo *card = q->queuedata;
struct rsxx_bio_meta *bio_meta;
- int st = -EINVAL;
+ blk_status_t st = BLK_STS_IOERR;
- blk_queue_split(q, &bio, q->bio_split);
+ blk_queue_split(q, &bio);
might_sleep();
@@ -161,15 +161,11 @@ static blk_qc_t rsxx_make_request(struct request_queue *q, struct bio *bio)
if (bio_end_sector(bio) > get_capacity(card->gendisk))
goto req_err;
- if (unlikely(card->halt)) {
- st = -EFAULT;
+ if (unlikely(card->halt))
goto req_err;
- }
- if (unlikely(card->dma_fault)) {
- st = (-EFAULT);
+ if (unlikely(card->dma_fault))
goto req_err;
- }
if (bio->bi_iter.bi_size == 0) {
dev_err(CARD_TO_DEV(card), "size zero BIO!\n");
@@ -178,7 +174,7 @@ static blk_qc_t rsxx_make_request(struct request_queue *q, struct bio *bio)
bio_meta = kmem_cache_alloc(bio_meta_pool, GFP_KERNEL);
if (!bio_meta) {
- st = -ENOMEM;
+ st = BLK_STS_RESOURCE;
goto req_err;
}
@@ -205,7 +201,7 @@ queue_err:
kmem_cache_free(bio_meta_pool, bio_meta);
req_err:
if (st)
- bio->bi_error = st;
+ bio->bi_status = st;
bio_endio(bio);
return BLK_QC_T_NONE;
}
@@ -288,7 +284,6 @@ int rsxx_setup_dev(struct rsxx_cardinfo *card)
}
blk_queue_make_request(card->queue, rsxx_make_request);
- blk_queue_bounce_limit(card->queue, BLK_BOUNCE_ANY);
blk_queue_max_hw_sectors(card->queue, blkdev_max_hw_sectors);
blk_queue_physical_block_size(card->queue, RSXX_HW_BLK_SIZE);
diff --git a/drivers/block/rsxx/dma.c b/drivers/block/rsxx/dma.c
index 5a20385f87d0..6a1b2177951c 100644
--- a/drivers/block/rsxx/dma.c
+++ b/drivers/block/rsxx/dma.c
@@ -611,7 +611,7 @@ static void rsxx_schedule_done(struct work_struct *work)
mutex_unlock(&ctrl->work_lock);
}
-static int rsxx_queue_discard(struct rsxx_cardinfo *card,
+static blk_status_t rsxx_queue_discard(struct rsxx_cardinfo *card,
struct list_head *q,
unsigned int laddr,
rsxx_dma_cb cb,
@@ -621,7 +621,7 @@ static int rsxx_queue_discard(struct rsxx_cardinfo *card,
dma = kmem_cache_alloc(rsxx_dma_pool, GFP_KERNEL);
if (!dma)
- return -ENOMEM;
+ return BLK_STS_RESOURCE;
dma->cmd = HW_CMD_BLK_DISCARD;
dma->laddr = laddr;
@@ -640,7 +640,7 @@ static int rsxx_queue_discard(struct rsxx_cardinfo *card,
return 0;
}
-static int rsxx_queue_dma(struct rsxx_cardinfo *card,
+static blk_status_t rsxx_queue_dma(struct rsxx_cardinfo *card,
struct list_head *q,
int dir,
unsigned int dma_off,
@@ -655,7 +655,7 @@ static int rsxx_queue_dma(struct rsxx_cardinfo *card,
dma = kmem_cache_alloc(rsxx_dma_pool, GFP_KERNEL);
if (!dma)
- return -ENOMEM;
+ return BLK_STS_RESOURCE;
dma->cmd = dir ? HW_CMD_BLK_WRITE : HW_CMD_BLK_READ;
dma->laddr = laddr;
@@ -677,7 +677,7 @@ static int rsxx_queue_dma(struct rsxx_cardinfo *card,
return 0;
}
-int rsxx_dma_queue_bio(struct rsxx_cardinfo *card,
+blk_status_t rsxx_dma_queue_bio(struct rsxx_cardinfo *card,
struct bio *bio,
atomic_t *n_dmas,
rsxx_dma_cb cb,
@@ -694,7 +694,7 @@ int rsxx_dma_queue_bio(struct rsxx_cardinfo *card,
unsigned int dma_len;
int dma_cnt[RSXX_MAX_TARGETS];
int tgt;
- int st;
+ blk_status_t st;
int i;
addr8 = bio->bi_iter.bi_sector << 9; /* sectors are 512 bytes */
@@ -769,7 +769,6 @@ bvec_err:
for (i = 0; i < card->n_targets; i++)
rsxx_cleanup_dma_queue(&card->ctrl[i], &dma_list[i],
FREE_DMA);
-
return st;
}
diff --git a/drivers/block/rsxx/rsxx_priv.h b/drivers/block/rsxx/rsxx_priv.h
index 6bbc64d0f690..277f27e673a2 100644
--- a/drivers/block/rsxx/rsxx_priv.h
+++ b/drivers/block/rsxx/rsxx_priv.h
@@ -391,7 +391,7 @@ int rsxx_dma_cancel(struct rsxx_dma_ctrl *ctrl);
void rsxx_dma_cleanup(void);
void rsxx_dma_queue_reset(struct rsxx_cardinfo *card);
int rsxx_dma_configure(struct rsxx_cardinfo *card);
-int rsxx_dma_queue_bio(struct rsxx_cardinfo *card,
+blk_status_t rsxx_dma_queue_bio(struct rsxx_cardinfo *card,
struct bio *bio,
atomic_t *n_dmas,
rsxx_dma_cb cb,
diff --git a/drivers/block/skd_main.c b/drivers/block/skd_main.c
index 27833e4dae2a..d0368682bd43 100644
--- a/drivers/block/skd_main.c
+++ b/drivers/block/skd_main.c
@@ -451,8 +451,8 @@ static void skd_send_special_fitmsg(struct skd_device *skdev,
struct skd_special_context *skspcl);
static void skd_request_fn(struct request_queue *rq);
static void skd_end_request(struct skd_device *skdev,
- struct skd_request_context *skreq, int error);
-static int skd_preop_sg_list(struct skd_device *skdev,
+ struct skd_request_context *skreq, blk_status_t status);
+static bool skd_preop_sg_list(struct skd_device *skdev,
struct skd_request_context *skreq);
static void skd_postop_sg_list(struct skd_device *skdev,
struct skd_request_context *skreq);
@@ -491,7 +491,7 @@ static void skd_fail_all_pending(struct skd_device *skdev)
if (req == NULL)
break;
blk_start_request(req);
- __blk_end_request_all(req, -EIO);
+ __blk_end_request_all(req, BLK_STS_IOERR);
}
}
@@ -545,7 +545,6 @@ static void skd_request_fn(struct request_queue *q)
struct request *req = NULL;
struct skd_scsi_request *scsi_req;
unsigned long io_flags;
- int error;
u32 lba;
u32 count;
int data_dir;
@@ -716,9 +715,7 @@ static void skd_request_fn(struct request_queue *q)
if (!req->bio)
goto skip_sg;
- error = skd_preop_sg_list(skdev, skreq);
-
- if (error != 0) {
+ if (!skd_preop_sg_list(skdev, skreq)) {
/*
* Complete the native request with error.
* Note that the request context is still at the
@@ -730,7 +727,7 @@ static void skd_request_fn(struct request_queue *q)
*/
pr_debug("%s:%s:%d error Out\n",
skdev->name, __func__, __LINE__);
- skd_end_request(skdev, skreq, error);
+ skd_end_request(skdev, skreq, BLK_STS_RESOURCE);
continue;
}
@@ -805,7 +802,7 @@ skip_sg:
}
static void skd_end_request(struct skd_device *skdev,
- struct skd_request_context *skreq, int error)
+ struct skd_request_context *skreq, blk_status_t error)
{
if (unlikely(error)) {
struct request *req = skreq->req;
@@ -822,7 +819,7 @@ static void skd_end_request(struct skd_device *skdev,
__blk_end_request_all(skreq->req, error);
}
-static int skd_preop_sg_list(struct skd_device *skdev,
+static bool skd_preop_sg_list(struct skd_device *skdev,
struct skd_request_context *skreq)
{
struct request *req = skreq->req;
@@ -839,7 +836,7 @@ static int skd_preop_sg_list(struct skd_device *skdev,
n_sg = blk_rq_map_sg(skdev->queue, req, sg);
if (n_sg <= 0)
- return -EINVAL;
+ return false;
/*
* Map scatterlist to PCI bus addresses.
@@ -847,7 +844,7 @@ static int skd_preop_sg_list(struct skd_device *skdev,
*/
n_sg = pci_map_sg(skdev->pdev, sg, n_sg, pci_dir);
if (n_sg <= 0)
- return -EINVAL;
+ return false;
SKD_ASSERT(n_sg <= skdev->sgs_per_request);
@@ -882,7 +879,7 @@ static int skd_preop_sg_list(struct skd_device *skdev,
}
}
- return 0;
+ return true;
}
static void skd_postop_sg_list(struct skd_device *skdev,
@@ -2333,7 +2330,7 @@ static void skd_resolve_req_exception(struct skd_device *skdev,
switch (skd_check_status(skdev, cmp_status, &skreq->err_info)) {
case SKD_CHECK_STATUS_REPORT_GOOD:
case SKD_CHECK_STATUS_REPORT_SMART_ALERT:
- skd_end_request(skdev, skreq, 0);
+ skd_end_request(skdev, skreq, BLK_STS_OK);
break;
case SKD_CHECK_STATUS_BUSY_IMMINENT:
@@ -2355,7 +2352,7 @@ static void skd_resolve_req_exception(struct skd_device *skdev,
case SKD_CHECK_STATUS_REPORT_ERROR:
default:
- skd_end_request(skdev, skreq, -EIO);
+ skd_end_request(skdev, skreq, BLK_STS_IOERR);
break;
}
}
@@ -2748,7 +2745,7 @@ static int skd_isr_completion_posted(struct skd_device *skdev,
* native request.
*/
if (likely(cmp_status == SAM_STAT_GOOD))
- skd_end_request(skdev, skreq, 0);
+ skd_end_request(skdev, skreq, BLK_STS_OK);
else
skd_resolve_req_exception(skdev, skreq);
}
@@ -3190,7 +3187,7 @@ static void skd_recover_requests(struct skd_device *skdev, int requeue)
SKD_MAX_RETRIES)
blk_requeue_request(skdev->queue, skreq->req);
else
- skd_end_request(skdev, skreq, -EIO);
+ skd_end_request(skdev, skreq, BLK_STS_IOERR);
skreq->req = NULL;
@@ -4276,6 +4273,7 @@ static int skd_cons_disk(struct skd_device *skdev)
rc = -ENOMEM;
goto err_out;
}
+ blk_queue_bounce_limit(q, BLK_BOUNCE_HIGH);
skdev->queue = q;
disk->queue = q;
diff --git a/drivers/block/sunvdc.c b/drivers/block/sunvdc.c
index 3f3a3ab3d50a..6b16ead1da58 100644
--- a/drivers/block/sunvdc.c
+++ b/drivers/block/sunvdc.c
@@ -316,7 +316,7 @@ static void vdc_end_one(struct vdc_port *port, struct vio_dring_state *dr,
rqe->req = NULL;
- __blk_end_request(req, (desc->status ? -EIO : 0), desc->size);
+ __blk_end_request(req, (desc->status ? BLK_STS_IOERR : 0), desc->size);
vdc_blk_queue_start(port);
}
@@ -1023,7 +1023,7 @@ static void vdc_queue_drain(struct vdc_port *port)
struct request *req;
while ((req = blk_fetch_request(port->disk->queue)) != NULL)
- __blk_end_request_all(req, -EIO);
+ __blk_end_request_all(req, BLK_STS_IOERR);
}
static void vdc_ldc_reset_timer(unsigned long _arg)
diff --git a/drivers/block/swim.c b/drivers/block/swim.c
index 3064be6cf375..84434d3ea19b 100644
--- a/drivers/block/swim.c
+++ b/drivers/block/swim.c
@@ -493,7 +493,7 @@ static inline int swim_read_sector(struct floppy_state *fs,
return ret;
}
-static int floppy_read_sectors(struct floppy_state *fs,
+static blk_status_t floppy_read_sectors(struct floppy_state *fs,
int req_sector, int sectors_nb,
unsigned char *buffer)
{
@@ -516,7 +516,7 @@ static int floppy_read_sectors(struct floppy_state *fs,
ret = swim_read_sector(fs, side, track, sector,
buffer);
if (try-- == 0)
- return -EIO;
+ return BLK_STS_IOERR;
} while (ret != 512);
buffer += ret;
@@ -553,7 +553,7 @@ static void do_fd_request(struct request_queue *q)
req = swim_next_request(swd);
while (req) {
- int err = -EIO;
+ blk_status_t err = BLK_STS_IOERR;
fs = req->rq_disk->private_data;
if (blk_rq_pos(req) >= fs->total_secs)
@@ -864,6 +864,8 @@ static int swim_floppy_init(struct swim_priv *swd)
put_disk(swd->unit[drive].disk);
goto exit_put_disks;
}
+ blk_queue_bounce_limit(swd->unit[drive].disk->queue,
+ BLK_BOUNCE_HIGH);
swd->unit[drive].disk->queue->queuedata = swd;
swd->unit[drive].swd = swd;
}
diff --git a/drivers/block/swim3.c b/drivers/block/swim3.c
index ba4809c9bdba..9f931f8f6b4c 100644
--- a/drivers/block/swim3.c
+++ b/drivers/block/swim3.c
@@ -257,7 +257,7 @@ static unsigned int floppy_check_events(struct gendisk *disk,
unsigned int clearing);
static int floppy_revalidate(struct gendisk *disk);
-static bool swim3_end_request(struct floppy_state *fs, int err, unsigned int nr_bytes)
+static bool swim3_end_request(struct floppy_state *fs, blk_status_t err, unsigned int nr_bytes)
{
struct request *req = fs->cur_req;
int rc;
@@ -334,7 +334,7 @@ static void start_request(struct floppy_state *fs)
if (fs->mdev->media_bay &&
check_media_bay(fs->mdev->media_bay) != MB_FD) {
swim3_dbg("%s", " media bay absent, dropping req\n");
- swim3_end_request(fs, -ENODEV, 0);
+ swim3_end_request(fs, BLK_STS_IOERR, 0);
continue;
}
@@ -350,12 +350,12 @@ static void start_request(struct floppy_state *fs)
if (blk_rq_pos(req) >= fs->total_secs) {
swim3_dbg(" pos out of bounds (%ld, max is %ld)\n",
(long)blk_rq_pos(req), (long)fs->total_secs);
- swim3_end_request(fs, -EIO, 0);
+ swim3_end_request(fs, BLK_STS_IOERR, 0);
continue;
}
if (fs->ejected) {
swim3_dbg("%s", " disk ejected\n");
- swim3_end_request(fs, -EIO, 0);
+ swim3_end_request(fs, BLK_STS_IOERR, 0);
continue;
}
@@ -364,7 +364,7 @@ static void start_request(struct floppy_state *fs)
fs->write_prot = swim3_readbit(fs, WRITE_PROT);
if (fs->write_prot) {
swim3_dbg("%s", " try to write, disk write protected\n");
- swim3_end_request(fs, -EIO, 0);
+ swim3_end_request(fs, BLK_STS_IOERR, 0);
continue;
}
}
@@ -548,7 +548,7 @@ static void act(struct floppy_state *fs)
if (fs->retries > 5) {
swim3_err("Wrong cylinder in transfer, want: %d got %d\n",
fs->req_cyl, fs->cur_cyl);
- swim3_end_request(fs, -EIO, 0);
+ swim3_end_request(fs, BLK_STS_IOERR, 0);
fs->state = idle;
return;
}
@@ -584,7 +584,7 @@ static void scan_timeout(unsigned long data)
out_8(&sw->intr_enable, 0);
fs->cur_cyl = -1;
if (fs->retries > 5) {
- swim3_end_request(fs, -EIO, 0);
+ swim3_end_request(fs, BLK_STS_IOERR, 0);
fs->state = idle;
start_request(fs);
} else {
@@ -608,7 +608,7 @@ static void seek_timeout(unsigned long data)
out_8(&sw->select, RELAX);
out_8(&sw->intr_enable, 0);
swim3_err("%s", "Seek timeout\n");
- swim3_end_request(fs, -EIO, 0);
+ swim3_end_request(fs, BLK_STS_IOERR, 0);
fs->state = idle;
start_request(fs);
spin_unlock_irqrestore(&swim3_lock, flags);
@@ -637,7 +637,7 @@ static void settle_timeout(unsigned long data)
goto unlock;
}
swim3_err("%s", "Seek settle timeout\n");
- swim3_end_request(fs, -EIO, 0);
+ swim3_end_request(fs, BLK_STS_IOERR, 0);
fs->state = idle;
start_request(fs);
unlock:
@@ -666,7 +666,7 @@ static void xfer_timeout(unsigned long data)
swim3_err("Timeout %sing sector %ld\n",
(rq_data_dir(fs->cur_req)==WRITE? "writ": "read"),
(long)blk_rq_pos(fs->cur_req));
- swim3_end_request(fs, -EIO, 0);
+ swim3_end_request(fs, BLK_STS_IOERR, 0);
fs->state = idle;
start_request(fs);
spin_unlock_irqrestore(&swim3_lock, flags);
@@ -703,7 +703,7 @@ static irqreturn_t swim3_interrupt(int irq, void *dev_id)
swim3_err("%s", "Seen sector but cyl=ff?\n");
fs->cur_cyl = -1;
if (fs->retries > 5) {
- swim3_end_request(fs, -EIO, 0);
+ swim3_end_request(fs, BLK_STS_IOERR, 0);
fs->state = idle;
start_request(fs);
} else {
@@ -786,7 +786,7 @@ static irqreturn_t swim3_interrupt(int irq, void *dev_id)
swim3_err("Error %sing block %ld (err=%x)\n",
rq_data_dir(req) == WRITE? "writ": "read",
(long)blk_rq_pos(req), err);
- swim3_end_request(fs, -EIO, 0);
+ swim3_end_request(fs, BLK_STS_IOERR, 0);
fs->state = idle;
}
} else {
@@ -795,7 +795,7 @@ static irqreturn_t swim3_interrupt(int irq, void *dev_id)
swim3_err("fd dma error: stat=%x resid=%d\n", stat, resid);
swim3_err(" state=%d, dir=%x, intr=%x, err=%x\n",
fs->state, rq_data_dir(req), intr, err);
- swim3_end_request(fs, -EIO, 0);
+ swim3_end_request(fs, BLK_STS_IOERR, 0);
fs->state = idle;
start_request(fs);
break;
@@ -1223,6 +1223,7 @@ static int swim3_attach(struct macio_dev *mdev,
put_disk(disk);
return -ENOMEM;
}
+ blk_queue_bounce_limit(disk->queue, BLK_BOUNCE_HIGH);
disk->queue->queuedata = &floppy_states[index];
if (index == 0) {
@@ -1245,7 +1246,7 @@ static int swim3_attach(struct macio_dev *mdev,
return 0;
}
-static struct of_device_id swim3_match[] =
+static const struct of_device_id swim3_match[] =
{
{
.name = "swim3",
diff --git a/drivers/block/sx8.c b/drivers/block/sx8.c
index c8e072caf56f..08586dc14e85 100644
--- a/drivers/block/sx8.c
+++ b/drivers/block/sx8.c
@@ -745,7 +745,7 @@ static unsigned int carm_fill_get_fw_ver(struct carm_host *host,
static inline void carm_end_request_queued(struct carm_host *host,
struct carm_request *crq,
- int error)
+ blk_status_t error)
{
struct request *req = crq->rq;
int rc;
@@ -791,7 +791,7 @@ static inline void carm_round_robin(struct carm_host *host)
}
static inline void carm_end_rq(struct carm_host *host, struct carm_request *crq,
- int error)
+ blk_status_t error)
{
carm_end_request_queued(host, crq, error);
if (max_queue == 1)
@@ -869,14 +869,14 @@ queue_one_request:
sg = &crq->sg[0];
n_elem = blk_rq_map_sg(q, rq, sg);
if (n_elem <= 0) {
- carm_end_rq(host, crq, -EIO);
+ carm_end_rq(host, crq, BLK_STS_IOERR);
return; /* request with no s/g entries? */
}
/* map scatterlist to PCI bus addresses */
n_elem = pci_map_sg(host->pdev, sg, n_elem, pci_dir);
if (n_elem <= 0) {
- carm_end_rq(host, crq, -EIO);
+ carm_end_rq(host, crq, BLK_STS_IOERR);
return; /* request with no s/g entries? */
}
crq->n_elem = n_elem;
@@ -937,7 +937,7 @@ queue_one_request:
static void carm_handle_array_info(struct carm_host *host,
struct carm_request *crq, u8 *mem,
- int error)
+ blk_status_t error)
{
struct carm_port *port;
u8 *msg_data = mem + sizeof(struct carm_array_info);
@@ -997,7 +997,7 @@ out:
static void carm_handle_scan_chan(struct carm_host *host,
struct carm_request *crq, u8 *mem,
- int error)
+ blk_status_t error)
{
u8 *msg_data = mem + IOC_SCAN_CHAN_OFFSET;
unsigned int i, dev_count = 0;
@@ -1029,7 +1029,7 @@ out:
}
static void carm_handle_generic(struct carm_host *host,
- struct carm_request *crq, int error,
+ struct carm_request *crq, blk_status_t error,
int cur_state, int next_state)
{
DPRINTK("ENTER\n");
@@ -1045,7 +1045,7 @@ static void carm_handle_generic(struct carm_host *host,
}
static inline void carm_handle_rw(struct carm_host *host,
- struct carm_request *crq, int error)
+ struct carm_request *crq, blk_status_t error)
{
int pci_dir;
@@ -1067,7 +1067,7 @@ static inline void carm_handle_resp(struct carm_host *host,
u32 handle = le32_to_cpu(ret_handle_le);
unsigned int msg_idx;
struct carm_request *crq;
- int error = (status == RMSG_OK) ? 0 : -EIO;
+ blk_status_t error = (status == RMSG_OK) ? 0 : BLK_STS_IOERR;
u8 *mem;
VPRINTK("ENTER, handle == 0x%x\n", handle);
@@ -1155,7 +1155,7 @@ static inline void carm_handle_resp(struct carm_host *host,
err_out:
printk(KERN_WARNING DRV_NAME "(%s): BUG: unhandled message type %d/%d\n",
pci_name(host->pdev), crq->msg_type, crq->msg_subtype);
- carm_end_rq(host, crq, -EIO);
+ carm_end_rq(host, crq, BLK_STS_IOERR);
}
static inline void carm_handle_responses(struct carm_host *host)
diff --git a/drivers/block/umem.c b/drivers/block/umem.c
index c141cc3be22b..0677d2514665 100644
--- a/drivers/block/umem.c
+++ b/drivers/block/umem.c
@@ -454,7 +454,7 @@ static void process_page(unsigned long data)
PCI_DMA_TODEVICE : PCI_DMA_FROMDEVICE);
if (control & DMASCR_HARD_ERROR) {
/* error */
- bio->bi_error = -EIO;
+ bio->bi_status = BLK_STS_IOERR;
dev_printk(KERN_WARNING, &card->dev->dev,
"I/O error on sector %d/%d\n",
le32_to_cpu(desc->local_addr)>>9,
@@ -529,7 +529,7 @@ static blk_qc_t mm_make_request(struct request_queue *q, struct bio *bio)
(unsigned long long)bio->bi_iter.bi_sector,
bio->bi_iter.bi_size);
- blk_queue_split(q, &bio, q->bio_split);
+ blk_queue_split(q, &bio);
spin_lock_irq(&card->lock);
*card->biotail = bio;
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 553cc4c542b4..0297ad7c1452 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -64,15 +64,15 @@ struct virtblk_req {
struct scatterlist sg[];
};
-static inline int virtblk_result(struct virtblk_req *vbr)
+static inline blk_status_t virtblk_result(struct virtblk_req *vbr)
{
switch (vbr->status) {
case VIRTIO_BLK_S_OK:
- return 0;
+ return BLK_STS_OK;
case VIRTIO_BLK_S_UNSUPP:
- return -ENOTTY;
+ return BLK_STS_NOTSUPP;
default:
- return -EIO;
+ return BLK_STS_IOERR;
}
}
@@ -214,7 +214,7 @@ static void virtblk_done(struct virtqueue *vq)
spin_unlock_irqrestore(&vblk->vqs[qid].lock, flags);
}
-static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx,
+static blk_status_t virtio_queue_rq(struct blk_mq_hw_ctx *hctx,
const struct blk_mq_queue_data *bd)
{
struct virtio_blk *vblk = hctx->queue->queuedata;
@@ -246,7 +246,7 @@ static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx,
break;
default:
WARN_ON_ONCE(1);
- return BLK_MQ_RQ_QUEUE_ERROR;
+ return BLK_STS_IOERR;
}
vbr->out_hdr.type = cpu_to_virtio32(vblk->vdev, type);
@@ -276,8 +276,8 @@ static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx,
/* Out of mem doesn't actually happen, since we fall back
* to direct descriptors */
if (err == -ENOMEM || err == -ENOSPC)
- return BLK_MQ_RQ_QUEUE_BUSY;
- return BLK_MQ_RQ_QUEUE_ERROR;
+ return BLK_STS_RESOURCE;
+ return BLK_STS_IOERR;
}
if (bd->last && virtqueue_kick_prepare(vblk->vqs[qid].vq))
@@ -286,7 +286,7 @@ static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx,
if (notify)
virtqueue_notify(vblk->vqs[qid].vq);
- return BLK_MQ_RQ_QUEUE_OK;
+ return BLK_STS_OK;
}
/* return id (s/n) string for *disk to *id_str
@@ -307,7 +307,7 @@ static int virtblk_get_id(struct gendisk *disk, char *id_str)
goto out;
blk_execute_rq(vblk->disk->queue, vblk->disk, req, false);
- err = virtblk_result(blk_mq_rq_to_pdu(req));
+ err = blk_status_to_errno(virtblk_result(blk_mq_rq_to_pdu(req)));
out:
blk_put_request(req);
return err;
@@ -720,9 +720,6 @@ static int virtblk_probe(struct virtio_device *vdev)
/* We can handle whatever the host told us to handle. */
blk_queue_max_segments(q, vblk->sg_elems-2);
- /* No need to bounce any requests */
- blk_queue_bounce_limit(q, BLK_BOUNCE_ANY);
-
/* No real sector limit. */
blk_queue_max_hw_sectors(q, -1U);
diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c
index 0e824091a12f..fe7cd58c43d0 100644
--- a/drivers/block/xen-blkback/blkback.c
+++ b/drivers/block/xen-blkback/blkback.c
@@ -1066,20 +1066,17 @@ static void xen_blk_drain_io(struct xen_blkif_ring *ring)
atomic_set(&blkif->drain, 0);
}
-/*
- * Completion callback on the bio's. Called as bh->b_end_io()
- */
-
-static void __end_block_io_op(struct pending_req *pending_req, int error)
+static void __end_block_io_op(struct pending_req *pending_req,
+ blk_status_t error)
{
/* An error fails the entire request. */
- if ((pending_req->operation == BLKIF_OP_FLUSH_DISKCACHE) &&
- (error == -EOPNOTSUPP)) {
+ if (pending_req->operation == BLKIF_OP_FLUSH_DISKCACHE &&
+ error == BLK_STS_NOTSUPP) {
pr_debug("flush diskcache op failed, not supported\n");
xen_blkbk_flush_diskcache(XBT_NIL, pending_req->ring->blkif->be, 0);
pending_req->status = BLKIF_RSP_EOPNOTSUPP;
- } else if ((pending_req->operation == BLKIF_OP_WRITE_BARRIER) &&
- (error == -EOPNOTSUPP)) {
+ } else if (pending_req->operation == BLKIF_OP_WRITE_BARRIER &&
+ error == BLK_STS_NOTSUPP) {
pr_debug("write barrier op failed, not supported\n");
xen_blkbk_barrier(XBT_NIL, pending_req->ring->blkif->be, 0);
pending_req->status = BLKIF_RSP_EOPNOTSUPP;
@@ -1103,7 +1100,7 @@ static void __end_block_io_op(struct pending_req *pending_req, int error)
*/
static void end_block_io_op(struct bio *bio)
{
- __end_block_io_op(bio->bi_private, bio->bi_error);
+ __end_block_io_op(bio->bi_private, bio->bi_status);
bio_put(bio);
}
@@ -1420,7 +1417,7 @@ static int dispatch_rw_block_io(struct xen_blkif_ring *ring,
for (i = 0; i < nbio; i++)
bio_put(biolist[i]);
atomic_set(&pending_req->pendcnt, 1);
- __end_block_io_op(pending_req, -EINVAL);
+ __end_block_io_op(pending_req, BLK_STS_RESOURCE);
msleep(1); /* back off a bit */
return -EIO;
}
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 39459631667c..c852ed3c01d5 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -110,11 +110,6 @@ struct blk_shadow {
unsigned long associated_id;
};
-struct split_bio {
- struct bio *bio;
- atomic_t pending;
-};
-
struct blkif_req {
int error;
};
@@ -881,7 +876,7 @@ static inline bool blkif_request_flush_invalid(struct request *req,
!info->feature_fua));
}
-static int blkif_queue_rq(struct blk_mq_hw_ctx *hctx,
+static blk_status_t blkif_queue_rq(struct blk_mq_hw_ctx *hctx,
const struct blk_mq_queue_data *qd)
{
unsigned long flags;
@@ -904,16 +899,16 @@ static int blkif_queue_rq(struct blk_mq_hw_ctx *hctx,
flush_requests(rinfo);
spin_unlock_irqrestore(&rinfo->ring_lock, flags);
- return BLK_MQ_RQ_QUEUE_OK;
+ return BLK_STS_OK;
out_err:
spin_unlock_irqrestore(&rinfo->ring_lock, flags);
- return BLK_MQ_RQ_QUEUE_ERROR;
+ return BLK_STS_IOERR;
out_busy:
spin_unlock_irqrestore(&rinfo->ring_lock, flags);
blk_mq_stop_hw_queue(hctx);
- return BLK_MQ_RQ_QUEUE_BUSY;
+ return BLK_STS_RESOURCE;
}
static void blkif_complete_rq(struct request *rq)
@@ -958,9 +953,6 @@ static void blkif_set_queue_limits(struct blkfront_info *info)
/* Make sure buffer addresses are sector-aligned. */
blk_queue_dma_alignment(rq, 511);
-
- /* Make sure we don't use bounce buffers. */
- blk_queue_bounce_limit(rq, BLK_BOUNCE_ANY);
}
static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size,
@@ -1601,14 +1593,18 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
continue;
}
- blkif_req(req)->error = (bret->status == BLKIF_RSP_OKAY) ? 0 : -EIO;
+ if (bret->status == BLKIF_RSP_OKAY)
+ blkif_req(req)->error = BLK_STS_OK;
+ else
+ blkif_req(req)->error = BLK_STS_IOERR;
+
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));
- blkif_req(req)->error = -EOPNOTSUPP;
+ blkif_req(req)->error = BLK_STS_NOTSUPP;
info->feature_discard = 0;
info->feature_secdiscard = 0;
queue_flag_clear(QUEUE_FLAG_DISCARD, rq);
@@ -1626,11 +1622,11 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
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));
- blkif_req(req)->error = -EOPNOTSUPP;
+ blkif_req(req)->error = BLK_STS_NOTSUPP;
}
if (unlikely(blkif_req(req)->error)) {
- if (blkif_req(req)->error == -EOPNOTSUPP)
- blkif_req(req)->error = 0;
+ if (blkif_req(req)->error == BLK_STS_NOTSUPP)
+ blkif_req(req)->error = BLK_STS_OK;
info->feature_fua = 0;
info->feature_flush = 0;
xlvbd_flush(info);
@@ -1996,28 +1992,13 @@ static int blkfront_probe(struct xenbus_device *dev,
return 0;
}
-static void split_bio_end(struct bio *bio)
-{
- struct split_bio *split_bio = bio->bi_private;
-
- if (atomic_dec_and_test(&split_bio->pending)) {
- split_bio->bio->bi_phys_segments = 0;
- split_bio->bio->bi_error = bio->bi_error;
- bio_endio(split_bio->bio);
- kfree(split_bio);
- }
- bio_put(bio);
-}
-
static int blkif_recover(struct blkfront_info *info)
{
- unsigned int i, r_index;
+ unsigned int r_index;
struct request *req, *n;
int rc;
- struct bio *bio, *cloned_bio;
- unsigned int segs, offset;
- int pending, size;
- struct split_bio *split_bio;
+ struct bio *bio;
+ unsigned int segs;
blkfront_gather_backend_features(info);
/* Reset limits changed by blk_mq_update_nr_hw_queues(). */
@@ -2056,34 +2037,6 @@ static int blkif_recover(struct blkfront_info *info)
while ((bio = bio_list_pop(&info->bio_list)) != NULL) {
/* Traverse the list of pending bios and re-queue them */
- if (bio_segments(bio) > segs) {
- /*
- * This bio has more segments than what we can
- * handle, we have to split it.
- */
- pending = (bio_segments(bio) + segs - 1) / segs;
- split_bio = kzalloc(sizeof(*split_bio), GFP_NOIO);
- BUG_ON(split_bio == NULL);
- atomic_set(&split_bio->pending, pending);
- split_bio->bio = bio;
- for (i = 0; i < pending; i++) {
- offset = (i * segs * XEN_PAGE_SIZE) >> 9;
- size = min((unsigned int)(segs * XEN_PAGE_SIZE) >> 9,
- (unsigned int)bio_sectors(bio) - offset);
- cloned_bio = bio_clone(bio, GFP_NOIO);
- BUG_ON(cloned_bio == NULL);
- bio_trim(cloned_bio, offset, size);
- cloned_bio->bi_private = split_bio;
- cloned_bio->bi_end_io = split_bio_end;
- submit_bio(cloned_bio);
- }
- /*
- * Now we have to wait for all those smaller bios to
- * end, so we can also end the "parent" bio.
- */
- continue;
- }
- /* We don't need to split this bio */
submit_bio(bio);
}
@@ -2137,7 +2090,7 @@ static int blkfront_resume(struct xenbus_device *dev)
merge_bio.tail = shadow[j].request->biotail;
bio_list_merge(&info->bio_list, &merge_bio);
shadow[j].request->bio = NULL;
- blk_mq_end_request(shadow[j].request, 0);
+ blk_mq_end_request(shadow[j].request, BLK_STS_OK);
}
}
diff --git a/drivers/block/xsysace.c b/drivers/block/xsysace.c
index 757dce2147e0..14459d66ef0c 100644
--- a/drivers/block/xsysace.c
+++ b/drivers/block/xsysace.c
@@ -471,7 +471,7 @@ static struct request *ace_get_next_request(struct request_queue *q)
if (!blk_rq_is_passthrough(req))
break;
blk_start_request(req);
- __blk_end_request_all(req, -EIO);
+ __blk_end_request_all(req, BLK_STS_IOERR);
}
return req;
}
@@ -499,11 +499,11 @@ static void ace_fsm_dostate(struct ace_device *ace)
/* Drop all in-flight and pending requests */
if (ace->req) {
- __blk_end_request_all(ace->req, -EIO);
+ __blk_end_request_all(ace->req, BLK_STS_IOERR);
ace->req = NULL;
}
while ((req = blk_fetch_request(ace->queue)) != NULL)
- __blk_end_request_all(req, -EIO);
+ __blk_end_request_all(req, BLK_STS_IOERR);
/* Drop back to IDLE state and notify waiters */
ace->fsm_state = ACE_FSM_STATE_IDLE;
@@ -728,7 +728,7 @@ static void ace_fsm_dostate(struct ace_device *ace)
}
/* bio finished; is there another one? */
- if (__blk_end_request_cur(ace->req, 0)) {
+ if (__blk_end_request_cur(ace->req, BLK_STS_OK)) {
/* dev_dbg(ace->dev, "next block; h=%u c=%u\n",
* blk_rq_sectors(ace->req),
* blk_rq_cur_sectors(ace->req));
@@ -993,6 +993,7 @@ static int ace_setup(struct ace_device *ace)
if (ace->queue == NULL)
goto err_blk_initq;
blk_queue_logical_block_size(ace->queue, 512);
+ blk_queue_bounce_limit(ace->queue, BLK_BOUNCE_HIGH);
/*
* Allocate and initialize GD structure
diff --git a/drivers/block/z2ram.c b/drivers/block/z2ram.c
index 968f9e52effa..41c95c9b2ab4 100644
--- a/drivers/block/z2ram.c
+++ b/drivers/block/z2ram.c
@@ -74,14 +74,14 @@ static void do_z2_request(struct request_queue *q)
while (req) {
unsigned long start = blk_rq_pos(req) << 9;
unsigned long len = blk_rq_cur_bytes(req);
- int err = 0;
+ blk_status_t err = BLK_STS_OK;
if (start + len > z2ram_size) {
pr_err(DEVICE_NAME ": bad access: block=%llu, "
"count=%u\n",
(unsigned long long)blk_rq_pos(req),
blk_rq_cur_sectors(req));
- err = -EIO;
+ err = BLK_STS_IOERR;
goto done;
}
while (len) {
diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c
index 76c952fd9ab9..e36d160c458f 100644
--- a/drivers/cdrom/cdrom.c
+++ b/drivers/cdrom/cdrom.c
@@ -2178,6 +2178,12 @@ static int cdrom_read_cdda_bpc(struct cdrom_device_info *cdi, __u8 __user *ubuf,
if (!q)
return -ENXIO;
+ if (!blk_queue_scsi_passthrough(q)) {
+ WARN_ONCE(true,
+ "Attempt read CDDA info through a non-SCSI queue\n");
+ return -EINVAL;
+ }
+
cdi->last_sense = 0;
while (nframes) {
@@ -2195,7 +2201,6 @@ static int cdrom_read_cdda_bpc(struct cdrom_device_info *cdi, __u8 __user *ubuf,
break;
}
req = scsi_req(rq);
- scsi_req_init(rq);
ret = blk_rq_map_user(q, rq, NULL, ubuf, len, GFP_KERNEL);
if (ret) {
diff --git a/drivers/cdrom/gdrom.c b/drivers/cdrom/gdrom.c
index 1372763a948f..6495b03f576c 100644
--- a/drivers/cdrom/gdrom.c
+++ b/drivers/cdrom/gdrom.c
@@ -583,7 +583,8 @@ static int gdrom_set_interrupt_handlers(void)
*/
static void gdrom_readdisk_dma(struct work_struct *work)
{
- int err, block, block_cnt;
+ int block, block_cnt;
+ blk_status_t err;
struct packet_command *read_command;
struct list_head *elem, *next;
struct request *req;
@@ -641,7 +642,7 @@ static void gdrom_readdisk_dma(struct work_struct *work)
__raw_writeb(1, GDROM_DMA_STATUS_REG);
wait_event_interruptible_timeout(request_queue,
gd.transfer == 0, GDROM_DEFAULT_TIMEOUT);
- err = gd.transfer ? -EIO : 0;
+ err = gd.transfer ? BLK_STS_IOERR : BLK_STS_OK;
gd.transfer = 0;
gd.pending = 0;
/* now seek to take the request spinlock
@@ -670,11 +671,11 @@ static void gdrom_request(struct request_queue *rq)
break;
case REQ_OP_WRITE:
pr_notice("Read only device - write request ignored\n");
- __blk_end_request_all(req, -EIO);
+ __blk_end_request_all(req, BLK_STS_IOERR);
break;
default:
printk(KERN_DEBUG "gdrom: Non-fs request ignored\n");
- __blk_end_request_all(req, -EIO);
+ __blk_end_request_all(req, BLK_STS_IOERR);
break;
}
}
@@ -812,6 +813,7 @@ static int probe_gdrom(struct platform_device *devptr)
err = -ENOMEM;
goto probe_fail_requestq;
}
+ blk_queue_bounce_limit(gd.gdrom_rq, BLK_BOUNCE_HIGH);
err = probe_gdrom_setupqueue();
if (err)
diff --git a/drivers/char/tpm/tpm_crb.c b/drivers/char/tpm/tpm_crb.c
index b917b9d5f710..c378c7b15d49 100644
--- a/drivers/char/tpm/tpm_crb.c
+++ b/drivers/char/tpm/tpm_crb.c
@@ -27,10 +27,9 @@
#define ACPI_SIG_TPM2 "TPM2"
-static const u8 CRB_ACPI_START_UUID[] = {
- /* 0000 */ 0xAB, 0x6C, 0xBF, 0x6B, 0x63, 0x54, 0x14, 0x47,
- /* 0008 */ 0xB7, 0xCD, 0xF0, 0x20, 0x3C, 0x03, 0x68, 0xD4
-};
+static const guid_t crb_acpi_start_guid =
+ GUID_INIT(0x6BBF6CAB, 0x5463, 0x4714,
+ 0xB7, 0xCD, 0xF0, 0x20, 0x3C, 0x03, 0x68, 0xD4);
enum crb_defaults {
CRB_ACPI_START_REVISION_ID = 1,
@@ -266,7 +265,7 @@ static int crb_do_acpi_start(struct tpm_chip *chip)
int rc;
obj = acpi_evaluate_dsm(chip->acpi_dev_handle,
- CRB_ACPI_START_UUID,
+ &crb_acpi_start_guid,
CRB_ACPI_START_REVISION_ID,
CRB_ACPI_START_INDEX,
NULL);
diff --git a/drivers/char/tpm/tpm_ppi.c b/drivers/char/tpm/tpm_ppi.c
index 692a2c6ae036..86dd8521feef 100644
--- a/drivers/char/tpm/tpm_ppi.c
+++ b/drivers/char/tpm/tpm_ppi.c
@@ -32,20 +32,16 @@
#define PPI_VS_REQ_START 128
#define PPI_VS_REQ_END 255
-static const u8 tpm_ppi_uuid[] = {
- 0xA6, 0xFA, 0xDD, 0x3D,
- 0x1B, 0x36,
- 0xB4, 0x4E,
- 0xA4, 0x24,
- 0x8D, 0x10, 0x08, 0x9D, 0x16, 0x53
-};
+static const guid_t tpm_ppi_guid =
+ GUID_INIT(0x3DDDFAA6, 0x361B, 0x4EB4,
+ 0xA4, 0x24, 0x8D, 0x10, 0x08, 0x9D, 0x16, 0x53);
static inline union acpi_object *
tpm_eval_dsm(acpi_handle ppi_handle, int func, acpi_object_type type,
union acpi_object *argv4)
{
BUG_ON(!ppi_handle);
- return acpi_evaluate_dsm_typed(ppi_handle, tpm_ppi_uuid,
+ return acpi_evaluate_dsm_typed(ppi_handle, &tpm_ppi_guid,
TPM_PPI_REVISION_ID,
func, argv4, type);
}
@@ -107,7 +103,7 @@ static ssize_t tpm_store_ppi_request(struct device *dev,
* is updated with function index from SUBREQ to SUBREQ2 since PPI
* version 1.1
*/
- if (acpi_check_dsm(chip->acpi_dev_handle, tpm_ppi_uuid,
+ if (acpi_check_dsm(chip->acpi_dev_handle, &tpm_ppi_guid,
TPM_PPI_REVISION_ID, 1 << TPM_PPI_FN_SUBREQ2))
func = TPM_PPI_FN_SUBREQ2;
@@ -268,7 +264,7 @@ static ssize_t show_ppi_operations(acpi_handle dev_handle, char *buf, u32 start,
"User not required",
};
- if (!acpi_check_dsm(dev_handle, tpm_ppi_uuid, TPM_PPI_REVISION_ID,
+ if (!acpi_check_dsm(dev_handle, &tpm_ppi_guid, TPM_PPI_REVISION_ID,
1 << TPM_PPI_FN_GETOPR))
return -EPERM;
@@ -341,12 +337,12 @@ void tpm_add_ppi(struct tpm_chip *chip)
if (!chip->acpi_dev_handle)
return;
- if (!acpi_check_dsm(chip->acpi_dev_handle, tpm_ppi_uuid,
+ if (!acpi_check_dsm(chip->acpi_dev_handle, &tpm_ppi_guid,
TPM_PPI_REVISION_ID, 1 << TPM_PPI_FN_VERSION))
return;
/* Cache PPI version string. */
- obj = acpi_evaluate_dsm_typed(chip->acpi_dev_handle, tpm_ppi_uuid,
+ obj = acpi_evaluate_dsm_typed(chip->acpi_dev_handle, &tpm_ppi_guid,
TPM_PPI_REVISION_ID, TPM_PPI_FN_VERSION,
NULL, ACPI_TYPE_STRING);
if (obj) {
diff --git a/drivers/gpu/drm/i915/intel_acpi.c b/drivers/gpu/drm/i915/intel_acpi.c
index eb638a1e69d2..42fb436f6cdc 100644
--- a/drivers/gpu/drm/i915/intel_acpi.c
+++ b/drivers/gpu/drm/i915/intel_acpi.c
@@ -15,13 +15,9 @@ static struct intel_dsm_priv {
acpi_handle dhandle;
} intel_dsm_priv;
-static const u8 intel_dsm_guid[] = {
- 0xd3, 0x73, 0xd8, 0x7e,
- 0xd0, 0xc2,
- 0x4f, 0x4e,
- 0xa8, 0x54,
- 0x0f, 0x13, 0x17, 0xb0, 0x1c, 0x2c
-};
+static const guid_t intel_dsm_guid =
+ GUID_INIT(0x7ed873d3, 0xc2d0, 0x4e4f,
+ 0xa8, 0x54, 0x0f, 0x13, 0x17, 0xb0, 0x1c, 0x2c);
static char *intel_dsm_port_name(u8 id)
{
@@ -80,7 +76,7 @@ static void intel_dsm_platform_mux_info(void)
int i;
union acpi_object *pkg, *connector_count;
- pkg = acpi_evaluate_dsm_typed(intel_dsm_priv.dhandle, intel_dsm_guid,
+ pkg = acpi_evaluate_dsm_typed(intel_dsm_priv.dhandle, &intel_dsm_guid,
INTEL_DSM_REVISION_ID, INTEL_DSM_FN_PLATFORM_MUX_INFO,
NULL, ACPI_TYPE_PACKAGE);
if (!pkg) {
@@ -118,7 +114,7 @@ static bool intel_dsm_pci_probe(struct pci_dev *pdev)
if (!dhandle)
return false;
- if (!acpi_check_dsm(dhandle, intel_dsm_guid, INTEL_DSM_REVISION_ID,
+ if (!acpi_check_dsm(dhandle, &intel_dsm_guid, INTEL_DSM_REVISION_ID,
1 << INTEL_DSM_FN_PLATFORM_MUX_INFO)) {
DRM_DEBUG_KMS("no _DSM method for intel device\n");
return false;
diff --git a/drivers/gpu/drm/nouveau/nouveau_acpi.c b/drivers/gpu/drm/nouveau/nouveau_acpi.c
index 39468c218027..7459ef9943ec 100644
--- a/drivers/gpu/drm/nouveau/nouveau_acpi.c
+++ b/drivers/gpu/drm/nouveau/nouveau_acpi.c
@@ -60,15 +60,13 @@ bool nouveau_is_v1_dsm(void) {
}
#ifdef CONFIG_VGA_SWITCHEROO
-static const char nouveau_dsm_muid[] = {
- 0xA0, 0xA0, 0x95, 0x9D, 0x60, 0x00, 0x48, 0x4D,
- 0xB3, 0x4D, 0x7E, 0x5F, 0xEA, 0x12, 0x9F, 0xD4,
-};
+static const guid_t nouveau_dsm_muid =
+ GUID_INIT(0x9D95A0A0, 0x0060, 0x4D48,
+ 0xB3, 0x4D, 0x7E, 0x5F, 0xEA, 0x12, 0x9F, 0xD4);
-static const char nouveau_op_dsm_muid[] = {
- 0xF8, 0xD8, 0x86, 0xA4, 0xDA, 0x0B, 0x1B, 0x47,
- 0xA7, 0x2B, 0x60, 0x42, 0xA6, 0xB5, 0xBE, 0xE0,
-};
+static const guid_t nouveau_op_dsm_muid =
+ GUID_INIT(0xA486D8F8, 0x0BDA, 0x471B,
+ 0xA7, 0x2B, 0x60, 0x42, 0xA6, 0xB5, 0xBE, 0xE0);
static int nouveau_optimus_dsm(acpi_handle handle, int func, int arg, uint32_t *result)
{
@@ -86,7 +84,7 @@ static int nouveau_optimus_dsm(acpi_handle handle, int func, int arg, uint32_t *
args_buff[i] = (arg >> i * 8) & 0xFF;
*result = 0;
- obj = acpi_evaluate_dsm_typed(handle, nouveau_op_dsm_muid, 0x00000100,
+ obj = acpi_evaluate_dsm_typed(handle, &nouveau_op_dsm_muid, 0x00000100,
func, &argv4, ACPI_TYPE_BUFFER);
if (!obj) {
acpi_handle_info(handle, "failed to evaluate _DSM\n");
@@ -138,7 +136,7 @@ static int nouveau_dsm(acpi_handle handle, int func, int arg)
.integer.value = arg,
};
- obj = acpi_evaluate_dsm_typed(handle, nouveau_dsm_muid, 0x00000102,
+ obj = acpi_evaluate_dsm_typed(handle, &nouveau_dsm_muid, 0x00000102,
func, &argv4, ACPI_TYPE_INTEGER);
if (!obj) {
acpi_handle_info(handle, "failed to evaluate _DSM\n");
@@ -259,7 +257,7 @@ static void nouveau_dsm_pci_probe(struct pci_dev *pdev, acpi_handle *dhandle_out
if (!acpi_has_method(dhandle, "_DSM"))
return;
- supports_mux = acpi_check_dsm(dhandle, nouveau_dsm_muid, 0x00000102,
+ supports_mux = acpi_check_dsm(dhandle, &nouveau_dsm_muid, 0x00000102,
1 << NOUVEAU_DSM_POWER);
optimus_funcs = nouveau_dsm_get_optimus_functions(dhandle);
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mxm/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mxm/base.c
index e3e2f5e83815..f44682d62f75 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/mxm/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mxm/base.c
@@ -81,10 +81,9 @@ mxm_shadow_dsm(struct nvkm_mxm *mxm, u8 version)
{
struct nvkm_subdev *subdev = &mxm->subdev;
struct nvkm_device *device = subdev->device;
- static char muid[] = {
- 0x00, 0xA4, 0x04, 0x40, 0x7D, 0x91, 0xF2, 0x4C,
- 0xB8, 0x9C, 0x79, 0xB6, 0x2F, 0xD5, 0x56, 0x65
- };
+ static guid_t muid =
+ GUID_INIT(0x4004A400, 0x917D, 0x4CF2,
+ 0xB8, 0x9C, 0x79, 0xB6, 0x2F, 0xD5, 0x56, 0x65);
u32 mxms_args[] = { 0x00000000 };
union acpi_object argv4 = {
.buffer.type = ACPI_TYPE_BUFFER,
@@ -105,7 +104,7 @@ mxm_shadow_dsm(struct nvkm_mxm *mxm, u8 version)
* unless you pass in exactly the version it supports..
*/
rev = (version & 0xf0) << 4 | (version & 0x0f);
- obj = acpi_evaluate_dsm(handle, muid, rev, 0x00000010, &argv4);
+ obj = acpi_evaluate_dsm(handle, &muid, rev, 0x00000010, &argv4);
if (!obj) {
nvkm_debug(subdev, "DSM MXMS failed\n");
return false;
diff --git a/drivers/hid/i2c-hid/i2c-hid.c b/drivers/hid/i2c-hid/i2c-hid.c
index fb55fb4c39fc..04015032a35a 100644
--- a/drivers/hid/i2c-hid/i2c-hid.c
+++ b/drivers/hid/i2c-hid/i2c-hid.c
@@ -872,10 +872,9 @@ static int i2c_hid_fetch_hid_descriptor(struct i2c_hid *ihid)
static int i2c_hid_acpi_pdata(struct i2c_client *client,
struct i2c_hid_platform_data *pdata)
{
- static u8 i2c_hid_guid[] = {
- 0xF7, 0xF6, 0xDF, 0x3C, 0x67, 0x42, 0x55, 0x45,
- 0xAD, 0x05, 0xB3, 0x0A, 0x3D, 0x89, 0x38, 0xDE,
- };
+ static guid_t i2c_hid_guid =
+ GUID_INIT(0x3CDFF6F7, 0x4267, 0x4555,
+ 0xAD, 0x05, 0xB3, 0x0A, 0x3D, 0x89, 0x38, 0xDE);
union acpi_object *obj;
struct acpi_device *adev;
acpi_handle handle;
@@ -884,7 +883,7 @@ static int i2c_hid_acpi_pdata(struct i2c_client *client,
if (!handle || acpi_bus_get_device(handle, &adev))
return -ENODEV;
- obj = acpi_evaluate_dsm_typed(handle, i2c_hid_guid, 1, 1, NULL,
+ obj = acpi_evaluate_dsm_typed(handle, &i2c_hid_guid, 1, 1, NULL,
ACPI_TYPE_INTEGER);
if (!obj) {
dev_err(&client->dev, "device _DSM execution failed\n");
diff --git a/drivers/ide/ide-atapi.c b/drivers/ide/ide-atapi.c
index 5901937284e7..14d1e7d9a1d6 100644
--- a/drivers/ide/ide-atapi.c
+++ b/drivers/ide/ide-atapi.c
@@ -93,7 +93,6 @@ int ide_queue_pc_tail(ide_drive_t *drive, struct gendisk *disk,
int error;
rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
- scsi_req_init(rq);
ide_req(rq)->type = ATA_PRIV_MISC;
rq->special = (char *)pc;
@@ -200,7 +199,7 @@ void ide_prep_sense(ide_drive_t *drive, struct request *rq)
memset(sense, 0, sizeof(*sense));
blk_rq_init(rq->q, sense_rq);
- scsi_req_init(sense_rq);
+ scsi_req_init(req);
err = blk_rq_map_kern(drive->queue, sense_rq, sense, sense_len,
GFP_NOIO);
@@ -273,7 +272,7 @@ void ide_retry_pc(ide_drive_t *drive)
ide_requeue_and_plug(drive, failed_rq);
if (ide_queue_sense_rq(drive, pc)) {
blk_start_request(failed_rq);
- ide_complete_rq(drive, -EIO, blk_rq_bytes(failed_rq));
+ ide_complete_rq(drive, BLK_STS_IOERR, blk_rq_bytes(failed_rq));
}
}
EXPORT_SYMBOL_GPL(ide_retry_pc);
@@ -437,7 +436,8 @@ static ide_startstop_t ide_pc_intr(ide_drive_t *drive)
/* No more interrupts */
if ((stat & ATA_DRQ) == 0) {
- int uptodate, error;
+ int uptodate;
+ blk_status_t error;
debug_log("Packet command completed, %d bytes transferred\n",
blk_rq_bytes(rq));
@@ -490,7 +490,7 @@ static ide_startstop_t ide_pc_intr(ide_drive_t *drive)
if (ata_misc_request(rq)) {
scsi_req(rq)->result = 0;
- error = 0;
+ error = BLK_STS_OK;
} else {
if (blk_rq_is_passthrough(rq) && uptodate <= 0) {
@@ -498,7 +498,7 @@ static ide_startstop_t ide_pc_intr(ide_drive_t *drive)
scsi_req(rq)->result = -EIO;
}
- error = uptodate ? 0 : -EIO;
+ error = uptodate ? BLK_STS_OK : BLK_STS_IOERR;
}
ide_complete_rq(drive, error, blk_rq_bytes(rq));
diff --git a/drivers/ide/ide-cd.c b/drivers/ide/ide-cd.c
index 07e5ff3a64c3..81e18f9628d0 100644
--- a/drivers/ide/ide-cd.c
+++ b/drivers/ide/ide-cd.c
@@ -228,7 +228,7 @@ static void ide_cd_complete_failed_rq(ide_drive_t *drive, struct request *rq)
scsi_req(failed)->sense_len = scsi_req(rq)->sense_len;
cdrom_analyze_sense_data(drive, failed);
- if (ide_end_rq(drive, failed, -EIO, blk_rq_bytes(failed)))
+ if (ide_end_rq(drive, failed, BLK_STS_IOERR, blk_rq_bytes(failed)))
BUG();
} else
cdrom_analyze_sense_data(drive, NULL);
@@ -438,7 +438,6 @@ int ide_cd_queue_pc(ide_drive_t *drive, const unsigned char *cmd,
rq = blk_get_request(drive->queue,
write ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN, __GFP_RECLAIM);
- scsi_req_init(rq);
memcpy(scsi_req(rq)->cmd, cmd, BLK_MAX_CDB);
ide_req(rq)->type = ATA_PRIV_PC;
rq->rq_flags |= rq_flags;
@@ -508,7 +507,7 @@ static bool ide_cd_error_cmd(ide_drive_t *drive, struct ide_cmd *cmd)
nr_bytes -= cmd->last_xfer_len;
if (nr_bytes > 0) {
- ide_complete_rq(drive, 0, nr_bytes);
+ ide_complete_rq(drive, BLK_STS_OK, nr_bytes);
return true;
}
@@ -674,7 +673,7 @@ static ide_startstop_t cdrom_newpc_intr(ide_drive_t *drive)
out_end:
if (blk_rq_is_scsi(rq) && rc == 0) {
scsi_req(rq)->resid_len = 0;
- blk_end_request_all(rq, 0);
+ blk_end_request_all(rq, BLK_STS_OK);
hwif->rq = NULL;
} else {
if (sense && uptodate)
@@ -699,7 +698,7 @@ out_end:
scsi_req(rq)->resid_len += cmd->last_xfer_len;
}
- ide_complete_rq(drive, uptodate ? 0 : -EIO, blk_rq_bytes(rq));
+ ide_complete_rq(drive, uptodate ? BLK_STS_OK : BLK_STS_IOERR, blk_rq_bytes(rq));
if (sense && rc == 2)
ide_error(drive, "request sense failure", stat);
@@ -844,7 +843,7 @@ out_end:
if (nsectors == 0)
nsectors = 1;
- ide_complete_rq(drive, uptodate ? 0 : -EIO, nsectors << 9);
+ ide_complete_rq(drive, uptodate ? BLK_STS_OK : BLK_STS_IOERR, nsectors << 9);
return ide_stopped;
}
diff --git a/drivers/ide/ide-cd_ioctl.c b/drivers/ide/ide-cd_ioctl.c
index 55cd736c39c6..9d26c9737e21 100644
--- a/drivers/ide/ide-cd_ioctl.c
+++ b/drivers/ide/ide-cd_ioctl.c
@@ -304,7 +304,6 @@ int ide_cdrom_reset(struct cdrom_device_info *cdi)
int ret;
rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
- scsi_req_init(rq);
ide_req(rq)->type = ATA_PRIV_MISC;
rq->rq_flags = RQF_QUIET;
blk_execute_rq(drive->queue, cd->disk, rq, 0);
diff --git a/drivers/ide/ide-devsets.c b/drivers/ide/ide-devsets.c
index 9b69c32ee560..ef7c8c43a380 100644
--- a/drivers/ide/ide-devsets.c
+++ b/drivers/ide/ide-devsets.c
@@ -166,7 +166,6 @@ int ide_devset_execute(ide_drive_t *drive, const struct ide_devset *setting,
return setting->set(drive, arg);
rq = blk_get_request(q, REQ_OP_DRV_IN, __GFP_RECLAIM);
- scsi_req_init(rq);
ide_req(rq)->type = ATA_PRIV_MISC;
scsi_req(rq)->cmd_len = 5;
scsi_req(rq)->cmd[0] = REQ_DEVSET_EXEC;
diff --git a/drivers/ide/ide-disk.c b/drivers/ide/ide-disk.c
index 7c06237f3479..241983da5fc4 100644
--- a/drivers/ide/ide-disk.c
+++ b/drivers/ide/ide-disk.c
@@ -478,7 +478,6 @@ static int set_multcount(ide_drive_t *drive, int arg)
return -EBUSY;
rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
- scsi_req_init(rq);
ide_req(rq)->type = ATA_PRIV_TASKFILE;
drive->mult_req = arg;
diff --git a/drivers/ide/ide-dma.c b/drivers/ide/ide-dma.c
index 51c81223e56d..54d4d78ca46a 100644
--- a/drivers/ide/ide-dma.c
+++ b/drivers/ide/ide-dma.c
@@ -104,7 +104,7 @@ ide_startstop_t ide_dma_intr(ide_drive_t *drive)
if ((cmd->tf_flags & IDE_TFLAG_FS) == 0)
ide_finish_cmd(drive, cmd, stat);
else
- ide_complete_rq(drive, 0,
+ ide_complete_rq(drive, BLK_STS_OK,
blk_rq_sectors(cmd->rq) << 9);
return ide_stopped;
}
diff --git a/drivers/ide/ide-eh.c b/drivers/ide/ide-eh.c
index 4b7ffd7d158d..47d5f3379748 100644
--- a/drivers/ide/ide-eh.c
+++ b/drivers/ide/ide-eh.c
@@ -135,7 +135,7 @@ ide_startstop_t ide_error(ide_drive_t *drive, const char *msg, u8 stat)
return ide_stopped;
}
scsi_req(rq)->result = err;
- ide_complete_rq(drive, err ? -EIO : 0, blk_rq_bytes(rq));
+ ide_complete_rq(drive, err ? BLK_STS_IOERR : BLK_STS_OK, blk_rq_bytes(rq));
return ide_stopped;
}
@@ -143,7 +143,7 @@ ide_startstop_t ide_error(ide_drive_t *drive, const char *msg, u8 stat)
}
EXPORT_SYMBOL_GPL(ide_error);
-static inline void ide_complete_drive_reset(ide_drive_t *drive, int err)
+static inline void ide_complete_drive_reset(ide_drive_t *drive, blk_status_t err)
{
struct request *rq = drive->hwif->rq;
@@ -151,7 +151,7 @@ static inline void ide_complete_drive_reset(ide_drive_t *drive, int err)
scsi_req(rq)->cmd[0] == REQ_DRIVE_RESET) {
if (err <= 0 && scsi_req(rq)->result == 0)
scsi_req(rq)->result = -EIO;
- ide_complete_rq(drive, err ? err : 0, blk_rq_bytes(rq));
+ ide_complete_rq(drive, err, blk_rq_bytes(rq));
}
}
@@ -191,7 +191,7 @@ static ide_startstop_t atapi_reset_pollfunc(ide_drive_t *drive)
}
/* done polling */
hwif->polling = 0;
- ide_complete_drive_reset(drive, 0);
+ ide_complete_drive_reset(drive, BLK_STS_OK);
return ide_stopped;
}
@@ -225,7 +225,7 @@ static ide_startstop_t reset_pollfunc(ide_drive_t *drive)
ide_hwif_t *hwif = drive->hwif;
const struct ide_port_ops *port_ops = hwif->port_ops;
u8 tmp;
- int err = 0;
+ blk_status_t err = BLK_STS_OK;
if (port_ops && port_ops->reset_poll) {
err = port_ops->reset_poll(drive);
@@ -247,7 +247,7 @@ static ide_startstop_t reset_pollfunc(ide_drive_t *drive)
printk(KERN_ERR "%s: reset timed-out, status=0x%02x\n",
hwif->name, tmp);
drive->failures++;
- err = -EIO;
+ err = BLK_STS_IOERR;
} else {
tmp = ide_read_error(drive);
@@ -257,7 +257,7 @@ static ide_startstop_t reset_pollfunc(ide_drive_t *drive)
} else {
ide_reset_report_error(hwif, tmp);
drive->failures++;
- err = -EIO;
+ err = BLK_STS_IOERR;
}
}
out:
@@ -392,7 +392,7 @@ static ide_startstop_t do_reset1(ide_drive_t *drive, int do_not_try_atapi)
if (io_ports->ctl_addr == 0) {
spin_unlock_irqrestore(&hwif->lock, flags);
- ide_complete_drive_reset(drive, -ENXIO);
+ ide_complete_drive_reset(drive, BLK_STS_IOERR);
return ide_stopped;
}
diff --git a/drivers/ide/ide-floppy.c b/drivers/ide/ide-floppy.c
index 8ac6048cd2df..627b1f62a749 100644
--- a/drivers/ide/ide-floppy.c
+++ b/drivers/ide/ide-floppy.c
@@ -143,7 +143,7 @@ static ide_startstop_t ide_floppy_issue_pc(ide_drive_t *drive,
drive->failed_pc = NULL;
drive->pc_callback(drive, 0);
- ide_complete_rq(drive, -EIO, done);
+ ide_complete_rq(drive, BLK_STS_IOERR, done);
return ide_stopped;
}
@@ -248,7 +248,7 @@ static ide_startstop_t ide_floppy_do_request(ide_drive_t *drive,
if (ata_misc_request(rq)) {
scsi_req(rq)->result = 0;
- ide_complete_rq(drive, 0, blk_rq_bytes(rq));
+ ide_complete_rq(drive, BLK_STS_OK, blk_rq_bytes(rq));
return ide_stopped;
} else
goto out_end;
@@ -303,7 +303,7 @@ out_end:
drive->failed_pc = NULL;
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));
+ ide_complete_rq(drive, BLK_STS_IOERR, blk_rq_bytes(rq));
return ide_stopped;
}
diff --git a/drivers/ide/ide-io.c b/drivers/ide/ide-io.c
index 323af721f8cb..3a234701d92c 100644
--- a/drivers/ide/ide-io.c
+++ b/drivers/ide/ide-io.c
@@ -54,7 +54,7 @@
#include <linux/uaccess.h>
#include <asm/io.h>
-int ide_end_rq(ide_drive_t *drive, struct request *rq, int error,
+int ide_end_rq(ide_drive_t *drive, struct request *rq, blk_status_t error,
unsigned int nr_bytes)
{
/*
@@ -112,7 +112,7 @@ void ide_complete_cmd(ide_drive_t *drive, struct ide_cmd *cmd, u8 stat, u8 err)
}
}
-int ide_complete_rq(ide_drive_t *drive, int error, unsigned int nr_bytes)
+int ide_complete_rq(ide_drive_t *drive, blk_status_t error, unsigned int nr_bytes)
{
ide_hwif_t *hwif = drive->hwif;
struct request *rq = hwif->rq;
@@ -122,7 +122,7 @@ int ide_complete_rq(ide_drive_t *drive, int error, unsigned int nr_bytes)
* if failfast is set on a request, override number of sectors
* and complete the whole request right now
*/
- if (blk_noretry_request(rq) && error <= 0)
+ if (blk_noretry_request(rq) && error)
nr_bytes = blk_rq_sectors(rq) << 9;
rc = ide_end_rq(drive, rq, error, nr_bytes);
@@ -149,7 +149,7 @@ void ide_kill_rq(ide_drive_t *drive, struct request *rq)
scsi_req(rq)->result = -EIO;
}
- ide_complete_rq(drive, -EIO, blk_rq_bytes(rq));
+ ide_complete_rq(drive, BLK_STS_IOERR, blk_rq_bytes(rq));
}
static void ide_tf_set_specify_cmd(ide_drive_t *drive, struct ide_taskfile *tf)
@@ -272,7 +272,7 @@ static ide_startstop_t execute_drive_cmd (ide_drive_t *drive,
printk("%s: DRIVE_CMD (null)\n", drive->name);
#endif
scsi_req(rq)->result = 0;
- ide_complete_rq(drive, 0, blk_rq_bytes(rq));
+ ide_complete_rq(drive, BLK_STS_OK, blk_rq_bytes(rq));
return ide_stopped;
}
diff --git a/drivers/ide/ide-ioctls.c b/drivers/ide/ide-ioctls.c
index 8c0d17297a7a..3661abb16a5f 100644
--- a/drivers/ide/ide-ioctls.c
+++ b/drivers/ide/ide-ioctls.c
@@ -126,7 +126,6 @@ static int ide_cmd_ioctl(ide_drive_t *drive, unsigned long arg)
struct request *rq;
rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
- scsi_req_init(rq);
ide_req(rq)->type = ATA_PRIV_TASKFILE;
blk_execute_rq(drive->queue, NULL, rq, 0);
err = scsi_req(rq)->result ? -EIO : 0;
@@ -224,7 +223,6 @@ static int generic_drive_reset(ide_drive_t *drive)
int ret = 0;
rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
- scsi_req_init(rq);
ide_req(rq)->type = ATA_PRIV_MISC;
scsi_req(rq)->cmd_len = 1;
scsi_req(rq)->cmd[0] = REQ_DRIVE_RESET;
diff --git a/drivers/ide/ide-park.c b/drivers/ide/ide-park.c
index 94e3107f59b9..1f264d5d3f3f 100644
--- a/drivers/ide/ide-park.c
+++ b/drivers/ide/ide-park.c
@@ -32,7 +32,6 @@ static void issue_park_cmd(ide_drive_t *drive, unsigned long timeout)
spin_unlock_irq(&hwif->lock);
rq = blk_get_request(q, REQ_OP_DRV_IN, __GFP_RECLAIM);
- scsi_req_init(rq);
scsi_req(rq)->cmd[0] = REQ_PARK_HEADS;
scsi_req(rq)->cmd_len = 1;
ide_req(rq)->type = ATA_PRIV_MISC;
@@ -48,7 +47,6 @@ static void issue_park_cmd(ide_drive_t *drive, unsigned long timeout)
* timeout has expired, so power management will be reenabled.
*/
rq = blk_get_request(q, REQ_OP_DRV_IN, GFP_NOWAIT);
- scsi_req_init(rq);
if (IS_ERR(rq))
goto out;
diff --git a/drivers/ide/ide-pm.c b/drivers/ide/ide-pm.c
index 0977fc1f40ce..544f02d673ca 100644
--- a/drivers/ide/ide-pm.c
+++ b/drivers/ide/ide-pm.c
@@ -19,7 +19,6 @@ int generic_ide_suspend(struct device *dev, pm_message_t mesg)
memset(&rqpm, 0, sizeof(rqpm));
rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
- scsi_req_init(rq);
ide_req(rq)->type = ATA_PRIV_PM_SUSPEND;
rq->special = &rqpm;
rqpm.pm_step = IDE_PM_START_SUSPEND;
@@ -40,7 +39,7 @@ int generic_ide_suspend(struct device *dev, pm_message_t mesg)
return ret;
}
-static void ide_end_sync_rq(struct request *rq, int error)
+static void ide_end_sync_rq(struct request *rq, blk_status_t error)
{
complete(rq->end_io_data);
}
@@ -57,7 +56,7 @@ static int ide_pm_execute_rq(struct request *rq)
if (unlikely(blk_queue_dying(q))) {
rq->rq_flags |= RQF_QUIET;
scsi_req(rq)->result = -ENXIO;
- __blk_end_request_all(rq, 0);
+ __blk_end_request_all(rq, BLK_STS_OK);
spin_unlock_irq(q->queue_lock);
return -ENXIO;
}
@@ -91,7 +90,6 @@ int generic_ide_resume(struct device *dev)
memset(&rqpm, 0, sizeof(rqpm));
rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
- scsi_req_init(rq);
ide_req(rq)->type = ATA_PRIV_PM_RESUME;
rq->rq_flags |= RQF_PREEMPT;
rq->special = &rqpm;
@@ -235,7 +233,7 @@ void ide_complete_pm_rq(ide_drive_t *drive, struct request *rq)
drive->hwif->rq = NULL;
- if (blk_end_request(rq, 0, 0))
+ if (blk_end_request(rq, BLK_STS_OK, 0))
BUG();
}
diff --git a/drivers/ide/ide-probe.c b/drivers/ide/ide-probe.c
index 023562565d11..01b2adfd8226 100644
--- a/drivers/ide/ide-probe.c
+++ b/drivers/ide/ide-probe.c
@@ -741,12 +741,12 @@ static void ide_port_tune_devices(ide_hwif_t *hwif)
}
}
-static int ide_init_rq(struct request_queue *q, struct request *rq, gfp_t gfp)
+static void ide_initialize_rq(struct request *rq)
{
struct ide_request *req = blk_mq_rq_to_pdu(rq);
+ scsi_req_init(&req->sreq);
req->sreq.sense = req->sense;
- return 0;
}
/*
@@ -771,8 +771,9 @@ static int ide_init_queue(ide_drive_t *drive)
return 1;
q->request_fn = do_ide_request;
- q->init_rq_fn = ide_init_rq;
+ q->initialize_rq_fn = ide_initialize_rq;
q->cmd_size = sizeof(struct ide_request);
+ queue_flag_set_unlocked(QUEUE_FLAG_SCSI_PASSTHROUGH, q);
if (blk_init_allocated_queue(q) < 0) {
blk_cleanup_queue(q);
return 1;
diff --git a/drivers/ide/ide-tape.c b/drivers/ide/ide-tape.c
index a0651f948b76..fd57e8ccc47a 100644
--- a/drivers/ide/ide-tape.c
+++ b/drivers/ide/ide-tape.c
@@ -474,7 +474,7 @@ static ide_startstop_t ide_tape_issue_pc(ide_drive_t *drive,
drive->failed_pc = NULL;
drive->pc_callback(drive, 0);
- ide_complete_rq(drive, -EIO, blk_rq_bytes(rq));
+ ide_complete_rq(drive, BLK_STS_IOERR, blk_rq_bytes(rq));
return ide_stopped;
}
ide_debug_log(IDE_DBG_SENSE, "retry #%d, cmd: 0x%02x", pc->retries,
@@ -855,7 +855,6 @@ static int idetape_queue_rw_tail(ide_drive_t *drive, int cmd, int size)
BUG_ON(size < 0 || size % tape->blk_size);
rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
- scsi_req_init(rq);
ide_req(rq)->type = ATA_PRIV_MISC;
scsi_req(rq)->cmd[13] = cmd;
rq->rq_disk = tape->disk;
diff --git a/drivers/ide/ide-taskfile.c b/drivers/ide/ide-taskfile.c
index d71199d23c9e..4efe4c6e956c 100644
--- a/drivers/ide/ide-taskfile.c
+++ b/drivers/ide/ide-taskfile.c
@@ -318,7 +318,7 @@ static void ide_error_cmd(ide_drive_t *drive, struct ide_cmd *cmd)
}
if (nr_bytes > 0)
- ide_complete_rq(drive, 0, nr_bytes);
+ ide_complete_rq(drive, BLK_STS_OK, nr_bytes);
}
}
@@ -336,7 +336,7 @@ void ide_finish_cmd(ide_drive_t *drive, struct ide_cmd *cmd, u8 stat)
ide_driveid_update(drive);
}
- ide_complete_rq(drive, err ? -EIO : 0, blk_rq_bytes(rq));
+ ide_complete_rq(drive, err ? BLK_STS_IOERR : BLK_STS_OK, blk_rq_bytes(rq));
}
/*
@@ -394,7 +394,7 @@ out_end:
if ((cmd->tf_flags & IDE_TFLAG_FS) == 0)
ide_finish_cmd(drive, cmd, stat);
else
- ide_complete_rq(drive, 0, blk_rq_sectors(cmd->rq) << 9);
+ ide_complete_rq(drive, BLK_STS_OK, blk_rq_sectors(cmd->rq) << 9);
return ide_stopped;
out_err:
ide_error_cmd(drive, cmd);
@@ -433,7 +433,6 @@ int ide_raw_taskfile(ide_drive_t *drive, struct ide_cmd *cmd, u8 *buf,
rq = blk_get_request(drive->queue,
(cmd->tf_flags & IDE_TFLAG_WRITE) ?
REQ_OP_DRV_OUT : REQ_OP_DRV_IN, __GFP_RECLAIM);
- scsi_req_init(rq);
ide_req(rq)->type = ATA_PRIV_TASKFILE;
/*
diff --git a/drivers/ide/siimage.c b/drivers/ide/siimage.c
index 6a1849bb476c..57eea5a9047f 100644
--- a/drivers/ide/siimage.c
+++ b/drivers/ide/siimage.c
@@ -406,7 +406,7 @@ static int siimage_dma_test_irq(ide_drive_t *drive)
* yet.
*/
-static int sil_sata_reset_poll(ide_drive_t *drive)
+static blk_status_t sil_sata_reset_poll(ide_drive_t *drive)
{
ide_hwif_t *hwif = drive->hwif;
void __iomem *sata_status_addr
@@ -419,11 +419,11 @@ static int sil_sata_reset_poll(ide_drive_t *drive)
if ((sata_stat & 0x03) != 0x03) {
printk(KERN_WARNING "%s: reset phy dead, status=0x%08x\n",
hwif->name, sata_stat);
- return -ENXIO;
+ return BLK_STS_IOERR;
}
}
- return 0;
+ return BLK_STS_OK;
}
/**
diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
index cbf7763d8091..c8b0329c85d2 100644
--- a/drivers/iommu/dmar.c
+++ b/drivers/iommu/dmar.c
@@ -1808,10 +1808,9 @@ IOMMU_INIT_POST(detect_intel_iommu);
* for Directed-IO Architecture Specifiction, Rev 2.2, Section 8.8
* "Remapping Hardware Unit Hot Plug".
*/
-static u8 dmar_hp_uuid[] = {
- /* 0000 */ 0xA6, 0xA3, 0xC1, 0xD8, 0x9B, 0xBE, 0x9B, 0x4C,
- /* 0008 */ 0x91, 0xBF, 0xC3, 0xCB, 0x81, 0xFC, 0x5D, 0xAF
-};
+static guid_t dmar_hp_guid =
+ GUID_INIT(0xD8C1A3A6, 0xBE9B, 0x4C9B,
+ 0x91, 0xBF, 0xC3, 0xCB, 0x81, 0xFC, 0x5D, 0xAF);
/*
* Currently there's only one revision and BIOS will not check the revision id,
@@ -1824,7 +1823,7 @@ static u8 dmar_hp_uuid[] = {
static inline bool dmar_detect_dsm(acpi_handle handle, int func)
{
- return acpi_check_dsm(handle, dmar_hp_uuid, DMAR_DSM_REV_ID, 1 << func);
+ return acpi_check_dsm(handle, &dmar_hp_guid, DMAR_DSM_REV_ID, 1 << func);
}
static int dmar_walk_dsm_resource(acpi_handle handle, int func,
@@ -1843,7 +1842,7 @@ static int dmar_walk_dsm_resource(acpi_handle handle, int func,
if (!dmar_detect_dsm(handle, func))
return 0;
- obj = acpi_evaluate_dsm_typed(handle, dmar_hp_uuid, DMAR_DSM_REV_ID,
+ obj = acpi_evaluate_dsm_typed(handle, &dmar_hp_guid, DMAR_DSM_REV_ID,
func, NULL, ACPI_TYPE_BUFFER);
if (!obj)
return -ENODEV;
diff --git a/drivers/lightnvm/core.c b/drivers/lightnvm/core.c
index 6a4aa608ad95..ddae430b6eae 100644
--- a/drivers/lightnvm/core.c
+++ b/drivers/lightnvm/core.c
@@ -252,8 +252,9 @@ static int nvm_create_tgt(struct nvm_dev *dev, struct nvm_ioctl_create *create)
}
mutex_unlock(&dev->mlock);
- if (nvm_reserve_luns(dev, s->lun_begin, s->lun_end))
- return -ENOMEM;
+ ret = nvm_reserve_luns(dev, s->lun_begin, s->lun_end);
+ if (ret)
+ return ret;
t = kmalloc(sizeof(struct nvm_target), GFP_KERNEL);
if (!t) {
@@ -640,6 +641,7 @@ EXPORT_SYMBOL(nvm_max_phys_sects);
int nvm_submit_io(struct nvm_tgt_dev *tgt_dev, struct nvm_rq *rqd)
{
struct nvm_dev *dev = tgt_dev->parent;
+ int ret;
if (!dev->ops->submit_io)
return -ENODEV;
@@ -647,7 +649,12 @@ int nvm_submit_io(struct nvm_tgt_dev *tgt_dev, struct nvm_rq *rqd)
nvm_rq_tgt_to_dev(tgt_dev, rqd);
rqd->dev = tgt_dev;
- return dev->ops->submit_io(dev, rqd);
+
+ /* In case of error, fail with right address format */
+ ret = dev->ops->submit_io(dev, rqd);
+ if (ret)
+ nvm_rq_dev_to_tgt(tgt_dev, rqd);
+ return ret;
}
EXPORT_SYMBOL(nvm_submit_io);
diff --git a/drivers/lightnvm/pblk-cache.c b/drivers/lightnvm/pblk-cache.c
index 59bcea88db84..024a8fc93069 100644
--- a/drivers/lightnvm/pblk-cache.c
+++ b/drivers/lightnvm/pblk-cache.c
@@ -31,9 +31,13 @@ int pblk_write_to_cache(struct pblk *pblk, struct bio *bio, unsigned long flags)
*/
retry:
ret = pblk_rb_may_write_user(&pblk->rwb, bio, nr_entries, &bpos);
- if (ret == NVM_IO_REQUEUE) {
+ switch (ret) {
+ case NVM_IO_REQUEUE:
io_schedule();
goto retry;
+ case NVM_IO_ERR:
+ pblk_pipeline_stop(pblk);
+ goto out;
}
if (unlikely(!bio_has_data(bio)))
@@ -58,6 +62,8 @@ retry:
atomic_long_add(nr_entries, &pblk->req_writes);
#endif
+ pblk_rl_inserted(&pblk->rl, nr_entries);
+
out:
pblk_write_should_kick(pblk);
return ret;
diff --git a/drivers/lightnvm/pblk-core.c b/drivers/lightnvm/pblk-core.c
index 5e44768ccffa..7648186bd1b1 100644
--- a/drivers/lightnvm/pblk-core.c
+++ b/drivers/lightnvm/pblk-core.c
@@ -17,7 +17,6 @@
*/
#include "pblk.h"
-#include <linux/time.h>
static void pblk_mark_bb(struct pblk *pblk, struct pblk_line *line,
struct ppa_addr *ppa)
@@ -34,7 +33,7 @@ static void pblk_mark_bb(struct pblk *pblk, struct pblk_line *line,
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);
+ pblk_line_run_ws(pblk, NULL, ppa, pblk_line_mark_bb, pblk->bb_wq);
}
static void __pblk_end_io_erase(struct pblk *pblk, struct nvm_rq *rqd)
@@ -54,6 +53,8 @@ static void __pblk_end_io_erase(struct pblk *pblk, struct nvm_rq *rqd)
*ppa = rqd->ppa_addr;
pblk_mark_bb(pblk, line, ppa);
}
+
+ atomic_dec(&pblk->inflight_io);
}
/* Erase completion assumes that only one block is erased at the time */
@@ -61,13 +62,12 @@ 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);
+ mempool_free(rqd, pblk->g_rq_pool);
}
-static void __pblk_map_invalidate(struct pblk *pblk, struct pblk_line *line,
- u64 paddr)
+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;
@@ -88,7 +88,7 @@ static void __pblk_map_invalidate(struct pblk *pblk, struct pblk_line *line,
spin_unlock(&line->lock);
return;
}
- line->vsc--;
+ le32_add_cpu(line->vsc, -1);
if (line->state == PBLK_LINESTATE_CLOSED)
move_list = pblk_line_gc_list(pblk, line);
@@ -130,18 +130,6 @@ void pblk_map_invalidate(struct pblk *pblk, struct ppa_addr 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)
{
@@ -172,8 +160,8 @@ struct nvm_rq *pblk_alloc_rqd(struct pblk *pblk, int rw)
pool = pblk->w_rq_pool;
rq_size = pblk_w_rq_size;
} else {
- pool = pblk->r_rq_pool;
- rq_size = pblk_r_rq_size;
+ pool = pblk->g_rq_pool;
+ rq_size = pblk_g_rq_size;
}
rqd = mempool_alloc(pool, GFP_KERNEL);
@@ -189,7 +177,7 @@ void pblk_free_rqd(struct pblk *pblk, struct nvm_rq *rqd, int rw)
if (rw == WRITE)
pool = pblk->w_rq_pool;
else
- pool = pblk->r_rq_pool;
+ pool = pblk->g_rq_pool;
mempool_free(rqd, pool);
}
@@ -271,35 +259,25 @@ void pblk_end_io_sync(struct nvm_rq *rqd)
complete(waiting);
}
-void pblk_flush_writer(struct pblk *pblk)
+void pblk_wait_for_meta(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;
+ do {
+ if (!atomic_read(&pblk->inflight_io))
+ break;
- 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");
- }
+ schedule();
+ } while (1);
+}
- if (bio->bi_error)
- pr_err("pblk: flush sync write failed (%u)\n", bio->bi_error);
+static void pblk_flush_writer(struct pblk *pblk)
+{
+ pblk_rb_flush(&pblk->rwb);
+ do {
+ if (!pblk_rb_read_count(&pblk->rwb))
+ break;
- bio_put(bio);
+ schedule();
+ } while (1);
}
struct list_head *pblk_line_gc_list(struct pblk *pblk, struct pblk_line *line)
@@ -307,28 +285,31 @@ 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;
+ int vsc = le32_to_cpu(*line->vsc);
+
+ lockdep_assert_held(&line->lock);
- if (!line->vsc) {
+ if (!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) {
+ } else if (vsc < lm->high_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) {
+ } else if (vsc < lm->mid_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) {
+ } else if (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) {
+ } else if (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;
@@ -338,7 +319,7 @@ struct list_head *pblk_line_gc_list(struct pblk *pblk, struct pblk_line *line)
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->id, vsc,
line->sec_in_line,
lm->high_thrs, lm->mid_thrs);
}
@@ -397,6 +378,11 @@ void pblk_log_read_err(struct pblk *pblk, struct nvm_rq *rqd)
#endif
}
+void pblk_set_sec_per_write(struct pblk *pblk, int sec_per_write)
+{
+ pblk->sec_per_write = sec_per_write;
+}
+
int pblk_submit_io(struct pblk *pblk, struct nvm_rq *rqd)
{
struct nvm_tgt_dev *dev = pblk->dev;
@@ -431,6 +417,9 @@ int pblk_submit_io(struct pblk *pblk, struct nvm_rq *rqd)
}
}
#endif
+
+ atomic_inc(&pblk->inflight_io);
+
return nvm_submit_io(dev, rqd);
}
@@ -478,7 +467,7 @@ out:
int pblk_calc_secs(struct pblk *pblk, unsigned long secs_avail,
unsigned long secs_to_flush)
{
- int max = pblk->max_write_pgs;
+ int max = pblk->sec_per_write;
int min = pblk->min_write_pgs;
int secs_to_sync = 0;
@@ -492,12 +481,26 @@ int pblk_calc_secs(struct pblk *pblk, unsigned long secs_avail,
return secs_to_sync;
}
-static u64 __pblk_alloc_page(struct pblk *pblk, struct pblk_line *line,
- int nr_secs)
+void pblk_dealloc_page(struct pblk *pblk, struct pblk_line *line, int nr_secs)
{
u64 addr;
int i;
+ addr = find_next_zero_bit(line->map_bitmap,
+ pblk->lm.sec_per_line, line->cur_sec);
+ line->cur_sec = addr - nr_secs;
+
+ for (i = 0; i < nr_secs; i++, line->cur_sec--)
+ WARN_ON(!test_and_clear_bit(line->cur_sec, line->map_bitmap));
+}
+
+u64 __pblk_alloc_page(struct pblk *pblk, struct pblk_line *line, int nr_secs)
+{
+ u64 addr;
+ int i;
+
+ lockdep_assert_held(&line->lock);
+
/* 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");
@@ -528,27 +531,37 @@ u64 pblk_alloc_page(struct pblk *pblk, struct pblk_line *line, int nr_secs)
return addr;
}
+u64 pblk_lookup_page(struct pblk *pblk, struct pblk_line *line)
+{
+ u64 paddr;
+
+ spin_lock(&line->lock);
+ paddr = find_next_zero_bit(line->map_bitmap,
+ pblk->lm.sec_per_line, line->cur_sec);
+ spin_unlock(&line->lock);
+
+ return paddr;
+}
+
/*
* 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)
+ void *emeta_buf, u64 paddr, int dir)
{
struct nvm_tgt_dev *dev = pblk->dev;
struct nvm_geo *geo = &dev->geo;
struct pblk_line_meta *lm = &pblk->lm;
+ void *ppa_list, *meta_list;
struct bio *bio;
struct nvm_rq rqd;
- struct ppa_addr *ppa_list;
- dma_addr_t dma_ppa_list;
- void *emeta = line->emeta;
+ dma_addr_t dma_ppa_list, dma_meta_list;
int min = pblk->min_write_pgs;
- int left_ppas = lm->emeta_sec;
+ int left_ppas = lm->emeta_sec[0];
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);
@@ -556,25 +569,27 @@ static int pblk_line_submit_emeta_io(struct pblk *pblk, struct pblk_line *line,
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)
+ meta_list = nvm_dev_dma_alloc(dev->parent, GFP_KERNEL,
+ &dma_meta_list);
+ if (!meta_list)
return -ENOMEM;
+ ppa_list = meta_list + pblk_dma_meta_size;
+ dma_ppa_list = dma_meta_list + pblk_dma_meta_size;
+
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);
+ bio = pblk_bio_map_addr(pblk, emeta_buf, rq_ppas, rq_len, GFP_KERNEL);
if (IS_ERR(bio)) {
ret = PTR_ERR(bio);
goto free_rqd_dma;
@@ -584,27 +599,38 @@ next_rq:
bio_set_op_attrs(bio, bio_op, 0);
rqd.bio = bio;
- rqd.opcode = cmd_op;
- rqd.flags = flags;
- rqd.nr_ppas = rq_ppas;
+ rqd.meta_list = meta_list;
rqd.ppa_list = ppa_list;
+ rqd.dma_meta_list = dma_meta_list;
rqd.dma_ppa_list = dma_ppa_list;
+ rqd.opcode = cmd_op;
+ rqd.nr_ppas = rq_ppas;
rqd.end_io = pblk_end_io_sync;
rqd.private = &wait;
if (dir == WRITE) {
+ struct pblk_sec_meta *meta_list = rqd.meta_list;
+
+ rqd.flags = pblk_set_progr_mode(pblk, 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++)
+ for (j = 0; j < min; j++, i++, paddr++) {
+ meta_list[i].lba = cpu_to_le64(ADDR_EMPTY);
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);
+ int read_type = PBLK_READ_RANDOM;
+
+ if (pblk_io_aligned(pblk, rq_ppas))
+ read_type = PBLK_READ_SEQUENTIAL;
+ rqd.flags = pblk_set_read_mode(pblk, read_type);
while (test_bit(pos, line->blk_bitmap)) {
paddr += min;
@@ -645,9 +671,11 @@ next_rq:
msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) {
pr_err("pblk: emeta I/O timed out\n");
}
+ atomic_dec(&pblk->inflight_io);
reinit_completion(&wait);
- bio_put(bio);
+ if (likely(pblk->l_mg.emeta_alloc_type == PBLK_VMALLOC_META))
+ bio_put(bio);
if (rqd.error) {
if (dir == WRITE)
@@ -656,12 +684,12 @@ next_rq:
pblk_log_read_err(pblk, &rqd);
}
- emeta += rq_len;
+ emeta_buf += 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);
+ nvm_dev_dma_free(dev->parent, rqd.meta_list, rqd.dma_meta_list);
return ret;
}
@@ -697,21 +725,24 @@ static int pblk_line_submit_smeta_io(struct pblk *pblk, struct pblk_line *line,
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);
+ lba_list = emeta_to_lbas(pblk, line->emeta->buf);
} else if (dir == READ) {
bio_op = REQ_OP_READ;
cmd_op = NVM_OP_PREAD;
- flags = pblk_set_read_mode(pblk);
+ flags = pblk_set_read_mode(pblk, PBLK_READ_SEQUENTIAL);
} 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)
+ rqd.meta_list = nvm_dev_dma_alloc(dev->parent, GFP_KERNEL,
+ &rqd.dma_meta_list);
+ if (!rqd.meta_list)
return -ENOMEM;
+ rqd.ppa_list = rqd.meta_list + pblk_dma_meta_size;
+ rqd.dma_ppa_list = rqd.dma_meta_list + pblk_dma_meta_size;
+
bio = bio_map_kern(dev->q, line->smeta, lm->smeta_len, GFP_KERNEL);
if (IS_ERR(bio)) {
ret = PTR_ERR(bio);
@@ -729,9 +760,15 @@ static int pblk_line_submit_smeta_io(struct pblk *pblk, struct pblk_line *line,
rqd.private = &wait;
for (i = 0; i < lm->smeta_sec; i++, paddr++) {
+ struct pblk_sec_meta *meta_list = rqd.meta_list;
+
rqd.ppa_list[i] = addr_to_gen_ppa(pblk, paddr, line->id);
- if (dir == WRITE)
- lba_list[paddr] = cpu_to_le64(ADDR_EMPTY);
+
+ if (dir == WRITE) {
+ u64 addr_empty = cpu_to_le64(ADDR_EMPTY);
+
+ meta_list[i].lba = lba_list[paddr] = addr_empty;
+ }
}
/*
@@ -750,6 +787,7 @@ static int pblk_line_submit_smeta_io(struct pblk *pblk, struct pblk_line *line,
msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) {
pr_err("pblk: smeta I/O timed out\n");
}
+ atomic_dec(&pblk->inflight_io);
if (rqd.error) {
if (dir == WRITE)
@@ -759,7 +797,7 @@ static int pblk_line_submit_smeta_io(struct pblk *pblk, struct pblk_line *line,
}
free_ppa_list:
- nvm_dev_dma_free(dev->parent, rqd.ppa_list, rqd.dma_ppa_list);
+ nvm_dev_dma_free(dev->parent, rqd.meta_list, rqd.dma_meta_list);
return ret;
}
@@ -771,9 +809,11 @@ int pblk_line_read_smeta(struct pblk *pblk, struct pblk_line *line)
return pblk_line_submit_smeta_io(pblk, line, bpaddr, READ);
}
-int pblk_line_read_emeta(struct pblk *pblk, struct pblk_line *line)
+int pblk_line_read_emeta(struct pblk *pblk, struct pblk_line *line,
+ void *emeta_buf)
{
- return pblk_line_submit_emeta_io(pblk, line, line->emeta_ssec, READ);
+ return pblk_line_submit_emeta_io(pblk, line, emeta_buf,
+ line->emeta_ssec, READ);
}
static void pblk_setup_e_rq(struct pblk *pblk, struct nvm_rq *rqd,
@@ -789,7 +829,7 @@ static void pblk_setup_e_rq(struct pblk *pblk, struct nvm_rq *rqd,
static int pblk_blk_erase_sync(struct pblk *pblk, struct ppa_addr ppa)
{
struct nvm_rq rqd;
- int ret;
+ int ret = 0;
DECLARE_COMPLETION_ONSTACK(wait);
memset(&rqd, 0, sizeof(struct nvm_rq));
@@ -824,14 +864,14 @@ out:
rqd.private = pblk;
__pblk_end_io_erase(pblk, &rqd);
- return 0;
+ return ret;
}
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;
+ int ret, bit = -1;
/* Erase only good blocks, one at a time */
do {
@@ -850,27 +890,59 @@ int pblk_line_erase(struct pblk *pblk, struct pblk_line *line)
WARN_ON(test_and_set_bit(bit, line->erase_bitmap));
spin_unlock(&line->lock);
- if (pblk_blk_erase_sync(pblk, ppa)) {
+ ret = pblk_blk_erase_sync(pblk, ppa);
+ if (ret) {
pr_err("pblk: failed to erase line %d\n", line->id);
- return -ENOMEM;
+ return ret;
}
} while (1);
return 0;
}
+static void pblk_line_setup_metadata(struct pblk_line *line,
+ struct pblk_line_mgmt *l_mg,
+ struct pblk_line_meta *lm)
+{
+ int meta_line;
+
+ lockdep_assert_held(&l_mg->free_lock);
+
+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);
+ line->meta_line = meta_line;
+
+ line->smeta = l_mg->sline_meta[meta_line];
+ line->emeta = l_mg->eline_meta[meta_line];
+
+ memset(line->smeta, 0, lm->smeta_len);
+ memset(line->emeta->buf, 0, lm->emeta_len[0]);
+
+ line->emeta->mem = 0;
+ atomic_set(&line->emeta->sync, 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,
+static int pblk_line_init_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;
+ struct pblk_emeta *emeta = line->emeta;
+ struct line_emeta *emeta_buf = emeta->buf;
+ struct line_smeta *smeta_buf = (struct line_smeta *)line->smeta;
int nr_blk_line;
/* After erasing the line, new bad blocks might appear and we risk
@@ -893,42 +965,44 @@ static int pblk_line_set_metadata(struct pblk *pblk, struct pblk_line *line,
}
/* Run-time metadata */
- line->lun_bitmap = ((void *)(smeta)) + sizeof(struct line_smeta);
+ line->lun_bitmap = ((void *)(smeta_buf)) + 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);
+ smeta_buf->header.identifier = cpu_to_le32(PBLK_MAGIC);
+ memcpy(smeta_buf->header.uuid, pblk->instance_uuid, 16);
+ smeta_buf->header.id = cpu_to_le32(line->id);
+ smeta_buf->header.type = cpu_to_le16(line->type);
+ smeta_buf->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);
+ smeta_buf->seq_nr = cpu_to_le64(line->seq_nr);
+ smeta_buf->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);
+ smeta_buf->prev_id = cpu_to_le32(cur->id);
+ cur->emeta->buf->next_id = cpu_to_le32(line->id);
} else {
- smeta->prev_id = cpu_to_le32(PBLK_LINE_EMPTY);
+ smeta_buf->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));
+ smeta_buf->header.crc = cpu_to_le32(
+ pblk_calc_meta_header_crc(pblk, &smeta_buf->header));
+ smeta_buf->crc = cpu_to_le32(pblk_calc_smeta_crc(pblk, smeta_buf));
/* 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;
+ memcpy(&emeta_buf->header, &smeta_buf->header,
+ sizeof(struct line_header));
+ emeta_buf->seq_nr = cpu_to_le64(line->seq_nr);
+ emeta_buf->nr_lbas = cpu_to_le64(line->sec_in_line);
+ emeta_buf->nr_valid_lbas = cpu_to_le64(0);
+ emeta_buf->next_id = cpu_to_le32(PBLK_LINE_EMPTY);
+ emeta_buf->crc = cpu_to_le32(0);
+ emeta_buf->prev_id = smeta_buf->prev_id;
return 1;
}
@@ -965,7 +1039,6 @@ static int pblk_line_init_bb(struct pblk *pblk, struct pblk_line *line,
/* 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;
@@ -973,8 +1046,7 @@ retry_smeta:
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;
+ return 1;
}
bitmap_copy(line->invalid_bitmap, line->map_bitmap, lm->sec_per_line);
@@ -983,8 +1055,8 @@ retry_smeta:
* 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);
+ off = lm->sec_per_line - lm->emeta_sec[0];
+ bitmap_set(line->invalid_bitmap, off, lm->emeta_sec[0]);
while (nr_bb) {
off -= geo->sec_per_pl;
if (!test_bit(off, line->invalid_bitmap)) {
@@ -993,9 +1065,11 @@ retry_smeta:
}
}
- line->sec_in_line -= lm->emeta_sec;
+ line->sec_in_line -= lm->emeta_sec[0];
line->emeta_ssec = off;
- line->vsc = line->left_ssecs = line->left_msecs = line->sec_in_line;
+ line->nr_valid_lbas = 0;
+ line->left_msecs = line->sec_in_line;
+ *line->vsc = cpu_to_le32(line->sec_in_line);
if (lm->sec_per_line - line->sec_in_line !=
bitmap_weight(line->invalid_bitmap, lm->sec_per_line)) {
@@ -1034,14 +1108,20 @@ static int pblk_line_prepare(struct pblk *pblk, struct pblk_line *line)
spin_lock(&line->lock);
if (line->state != PBLK_LINESTATE_FREE) {
+ mempool_free(line->invalid_bitmap, pblk->line_meta_pool);
+ mempool_free(line->map_bitmap, pblk->line_meta_pool);
spin_unlock(&line->lock);
- WARN(1, "pblk: corrupted line state\n");
- return -EINTR;
+ WARN(1, "pblk: corrupted line %d, state %d\n",
+ line->id, line->state);
+ return -EAGAIN;
}
+
line->state = PBLK_LINESTATE_OPEN;
atomic_set(&line->left_eblks, blk_in_line);
atomic_set(&line->left_seblks, blk_in_line);
+
+ line->meta_distance = lm->meta_distance;
spin_unlock(&line->lock);
/* Bad blocks do not need to be erased */
@@ -1091,15 +1171,15 @@ 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;
+ struct pblk_line *line;
+ int ret, bit;
lockdep_assert_held(&l_mg->free_lock);
-retry_get:
+retry:
if (list_empty(&l_mg->free_list)) {
pr_err("pblk: no free lines\n");
- goto out;
+ return NULL;
}
line = list_first_entry(&l_mg->free_list, struct pblk_line, list);
@@ -1115,16 +1195,22 @@ retry_get:
list_add_tail(&line->list, &l_mg->bad_list);
pr_debug("pblk: line %d is bad\n", line->id);
- goto retry_get;
+ goto retry;
}
- 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;
+ ret = pblk_line_prepare(pblk, line);
+ if (ret) {
+ if (ret == -EAGAIN) {
+ list_add(&line->list, &l_mg->corrupt_list);
+ goto retry;
+ } else {
+ pr_err("pblk: failed to prepare line %d\n", line->id);
+ list_add(&line->list, &l_mg->free_list);
+ l_mg->nr_free_lines++;
+ return NULL;
+ }
}
-out:
return line;
}
@@ -1134,6 +1220,7 @@ static struct pblk_line *pblk_line_retry(struct pblk *pblk,
struct pblk_line_mgmt *l_mg = &pblk->l_mg;
struct pblk_line *retry_line;
+retry:
spin_lock(&l_mg->free_lock);
retry_line = pblk_line_get(pblk);
if (!retry_line) {
@@ -1150,23 +1237,25 @@ static struct pblk_line *pblk_line_retry(struct pblk *pblk,
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);
+ if (pblk_line_erase(pblk, retry_line))
+ goto retry;
+
return retry_line;
}
+static void pblk_set_space_limit(struct pblk *pblk)
+{
+ struct pblk_rl *rl = &pblk->rl;
+
+ atomic_set(&rl->rb_space, 0);
+}
+
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);
@@ -1180,30 +1269,37 @@ struct pblk_line *pblk_line_get_first_data(struct pblk *pblk)
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;
+ pblk_line_setup_metadata(line, l_mg, &pblk->lm);
/* Allocate next line for preparation */
l_mg->data_next = pblk_line_get(pblk);
- if (l_mg->data_next) {
+ if (!l_mg->data_next) {
+ /* If we cannot get a new line, we need to stop the pipeline.
+ * Only allow as many writes in as we can store safely and then
+ * fail gracefully
+ */
+ pblk_set_space_limit(pblk);
+
+ l_mg->data_next = NULL;
+ } else {
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 (pblk_line_erase(pblk, line)) {
+ line = pblk_line_retry(pblk, line);
+ if (!line)
+ return NULL;
+ }
+
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)) {
+ if (!pblk_line_init_metadata(pblk, line, NULL)) {
line = pblk_line_retry(pblk, line);
if (!line)
return NULL;
@@ -1222,69 +1318,88 @@ retry_setup:
return line;
}
-struct pblk_line *pblk_line_replace_data(struct pblk *pblk)
+static void pblk_stop_writes(struct pblk *pblk, struct pblk_line *line)
+{
+ lockdep_assert_held(&pblk->l_mg.free_lock);
+
+ pblk_set_space_limit(pblk);
+ pblk->state = PBLK_STATE_STOPPING;
+}
+
+void pblk_pipeline_stop(struct pblk *pblk)
+{
+ struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+ int ret;
+
+ spin_lock(&l_mg->free_lock);
+ if (pblk->state == PBLK_STATE_RECOVERING ||
+ pblk->state == PBLK_STATE_STOPPED) {
+ spin_unlock(&l_mg->free_lock);
+ return;
+ }
+ pblk->state = PBLK_STATE_RECOVERING;
+ spin_unlock(&l_mg->free_lock);
+
+ pblk_flush_writer(pblk);
+ pblk_wait_for_meta(pblk);
+
+ ret = pblk_recov_pad(pblk);
+ if (ret) {
+ pr_err("pblk: could not close data on teardown(%d)\n", ret);
+ return;
+ }
+
+ pblk_line_close_meta_sync(pblk);
+
+ spin_lock(&l_mg->free_lock);
+ pblk->state = PBLK_STATE_STOPPED;
+ l_mg->data_line = NULL;
+ l_mg->data_next = NULL;
+ spin_unlock(&l_mg->free_lock);
+}
+
+void 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;
+ return;
l_mg->data_line = new;
-retry_line:
+ spin_lock(&l_mg->free_lock);
+ if (pblk->state != PBLK_STATE_RUNNING) {
+ l_mg->data_line = NULL;
+ l_mg->data_next = NULL;
+ spin_unlock(&l_mg->free_lock);
+ return;
+ }
+
+ pblk_line_setup_metadata(new, l_mg, &pblk->lm);
+ spin_unlock(&l_mg->free_lock);
+
+retry_erase:
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;
+ return;
} else {
io_schedule();
}
- goto retry_line;
+ goto retry_erase;
}
- 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)) {
+ if (!pblk_line_init_metadata(pblk, new, cur)) {
new = pblk_line_retry(pblk, new);
if (!new)
- return NULL;
+ return;
goto retry_setup;
}
@@ -1292,12 +1407,30 @@ retry_setup:
if (!pblk_line_init_bb(pblk, new, 1)) {
new = pblk_line_retry(pblk, new);
if (!new)
- return NULL;
+ return;
goto retry_setup;
}
- return new;
+ /* Allocate next line for preparation */
+ spin_lock(&l_mg->free_lock);
+ l_mg->data_next = pblk_line_get(pblk);
+ if (!l_mg->data_next) {
+ /* If we cannot get a new line, we need to stop the pipeline.
+ * Only allow as many writes in as we can store safely and then
+ * fail gracefully
+ */
+ pblk_stop_writes(pblk, new);
+ l_mg->data_next = NULL;
+ } else {
+ 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_rl_free_lines_dec(&pblk->rl, l_mg->data_next);
}
void pblk_line_free(struct pblk *pblk, struct pblk_line *line)
@@ -1307,6 +1440,8 @@ void pblk_line_free(struct pblk *pblk, struct pblk_line *line)
if (line->invalid_bitmap)
mempool_free(line->invalid_bitmap, pblk->line_meta_pool);
+ *line->vsc = cpu_to_le32(EMPTY_ENTRY);
+
line->map_bitmap = NULL;
line->invalid_bitmap = NULL;
line->smeta = NULL;
@@ -1339,8 +1474,8 @@ 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);
+ rqd = mempool_alloc(pblk->g_rq_pool, GFP_KERNEL);
+ memset(rqd, 0, pblk_g_rq_size);
pblk_setup_e_rq(pblk, rqd, ppa);
@@ -1368,7 +1503,8 @@ 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)
+/* For now, always erase next line */
+struct pblk_line *pblk_line_get_erase(struct pblk *pblk)
{
return pblk->l_mg.data_next;
}
@@ -1378,17 +1514,53 @@ 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)
+void pblk_line_close_meta_sync(struct pblk *pblk)
{
struct pblk_line_mgmt *l_mg = &pblk->l_mg;
- struct list_head *move_list;
+ struct pblk_line_meta *lm = &pblk->lm;
+ struct pblk_line *line, *tline;
+ LIST_HEAD(list);
- line->emeta->crc = cpu_to_le32(pblk_calc_emeta_crc(pblk, line->emeta));
+ spin_lock(&l_mg->close_lock);
+ if (list_empty(&l_mg->emeta_list)) {
+ spin_unlock(&l_mg->close_lock);
+ return;
+ }
+
+ list_cut_position(&list, &l_mg->emeta_list, l_mg->emeta_list.prev);
+ spin_unlock(&l_mg->close_lock);
+
+ list_for_each_entry_safe(line, tline, &list, list) {
+ struct pblk_emeta *emeta = line->emeta;
+
+ while (emeta->mem < lm->emeta_len[0]) {
+ int ret;
+
+ ret = pblk_submit_meta_io(pblk, line);
+ if (ret) {
+ pr_err("pblk: sync meta line %d failed (%d)\n",
+ line->id, ret);
+ return;
+ }
+ }
+ }
- if (pblk_line_submit_emeta_io(pblk, line, line->cur_sec, WRITE))
- pr_err("pblk: line %d close I/O failed\n", line->id);
+ pblk_wait_for_meta(pblk);
+}
+
+static void pblk_line_should_sync_meta(struct pblk *pblk)
+{
+ if (pblk_rl_is_limit(&pblk->rl))
+ pblk_line_close_meta_sync(pblk);
+}
+
+void pblk_line_close(struct pblk *pblk, struct pblk_line *line)
+{
+ struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+ struct pblk_line_meta *lm = &pblk->lm;
+ struct list_head *move_list;
- WARN(!bitmap_full(line->map_bitmap, line->sec_in_line),
+ WARN(!bitmap_full(line->map_bitmap, lm->sec_per_line),
"pblk: corrupt closed line %d\n", line->id);
spin_lock(&l_mg->free_lock);
@@ -1410,6 +1582,31 @@ void pblk_line_close(struct pblk *pblk, struct pblk_line *line)
spin_unlock(&line->lock);
spin_unlock(&l_mg->gc_lock);
+
+ pblk_gc_should_kick(pblk);
+}
+
+void pblk_line_close_meta(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_emeta *emeta = line->emeta;
+ struct line_emeta *emeta_buf = emeta->buf;
+
+ /* No need for exact vsc value; avoid a big line lock and take aprox. */
+ memcpy(emeta_to_vsc(pblk, emeta_buf), l_mg->vsc_list, lm->vsc_list_len);
+ memcpy(emeta_to_bb(emeta_buf), line->blk_bitmap, lm->blk_bitmap_len);
+
+ emeta_buf->nr_valid_lbas = cpu_to_le64(line->nr_valid_lbas);
+ emeta_buf->crc = cpu_to_le32(pblk_calc_emeta_crc(pblk, emeta_buf));
+
+ spin_lock(&l_mg->close_lock);
+ spin_lock(&line->lock);
+ list_add_tail(&line->list, &l_mg->emeta_list);
+ spin_unlock(&line->lock);
+ spin_unlock(&l_mg->close_lock);
+
+ pblk_line_should_sync_meta(pblk);
}
void pblk_line_close_ws(struct work_struct *work)
@@ -1449,7 +1646,8 @@ 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 *))
+ void (*work)(struct work_struct *),
+ struct workqueue_struct *wq)
{
struct pblk_line_ws *line_ws;
@@ -1462,7 +1660,7 @@ void pblk_line_run_ws(struct pblk *pblk, struct pblk_line *line, void *priv,
line_ws->priv = priv;
INIT_WORK(&line_ws->ws, work);
- queue_work(pblk->kw_wq, &line_ws->ws);
+ queue_work(wq, &line_ws->ws);
}
void pblk_down_rq(struct pblk *pblk, struct ppa_addr *ppa_list, int nr_ppas,
@@ -1471,7 +1669,7 @@ void pblk_down_rq(struct pblk *pblk, struct ppa_addr *ppa_list, int nr_ppas,
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 pos = pblk_ppa_to_pos(geo, ppa_list[0]);
int ret;
/*
@@ -1488,10 +1686,10 @@ void pblk_down_rq(struct pblk *pblk, struct ppa_addr *ppa_list, int nr_ppas,
/* 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))
+ if (test_and_set_bit(pos, lun_bitmap))
return;
- rlun = &pblk->luns[lun_id];
+ rlun = &pblk->luns[pos];
ret = down_timeout(&rlun->wr_sem, msecs_to_jiffies(5000));
if (ret) {
switch (ret) {
diff --git a/drivers/lightnvm/pblk-gc.c b/drivers/lightnvm/pblk-gc.c
index eaf479c6b63c..1d289242ab92 100644
--- a/drivers/lightnvm/pblk-gc.c
+++ b/drivers/lightnvm/pblk-gc.c
@@ -21,7 +21,6 @@
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);
}
@@ -37,10 +36,8 @@ static int pblk_gc_write(struct pblk *pblk)
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--;
- }
+ list_cut_position(&w_list, &gc->w_list, gc->w_list.prev);
+ gc->w_entries = 0;
spin_unlock(&gc->w_lock);
list_for_each_entry_safe(gc_rq, tgc_rq, &w_list, list) {
@@ -48,9 +45,8 @@ static int pblk_gc_write(struct pblk *pblk)
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);
+ kref_put(&gc_rq->line->ref, pblk_line_put);
pblk_gc_free_gc_rq(gc_rq);
}
@@ -66,52 +62,41 @@ static void pblk_gc_writer_kick(struct pblk_gc *gc)
* 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)
+static int pblk_gc_move_valid_secs(struct pblk *pblk, struct pblk_gc_rq *gc_rq)
{
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;
+ struct pblk_line *line = gc_rq->line;
void *data;
unsigned int secs_to_gc;
- int ret = NVM_IO_OK;
+ int ret = 0;
- data = kmalloc(nr_secs * geo->sec_size, GFP_KERNEL);
+ data = kmalloc(gc_rq->nr_secs * geo->sec_size, GFP_KERNEL);
if (!data) {
- ret = NVM_IO_ERR;
- goto free_lba_list;
+ ret = -ENOMEM;
+ goto out;
}
/* Read from GC victim block */
- if (pblk_submit_read_gc(pblk, lba_list, data, nr_secs,
+ if (pblk_submit_read_gc(pblk, gc_rq->lba_list, data, gc_rq->nr_secs,
&secs_to_gc, line)) {
- ret = NVM_IO_ERR;
+ ret = -EFAULT;
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;
- }
+ goto free_rq;
- 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) {
+ if (gc->w_entries >= PBLK_GC_W_QD) {
spin_unlock(&gc->w_lock);
- usleep_range(256, 1024);
+ pblk_gc_writer_kick(&pblk->gc);
+ usleep_range(128, 256);
goto retry;
}
gc->w_entries++;
@@ -120,13 +105,14 @@ retry:
pblk_gc_writer_kick(&pblk->gc);
- return NVM_IO_OK;
+ return 0;
+free_rq:
+ kfree(gc_rq);
free_data:
kfree(data);
-free_lba_list:
- kfree(lba_list);
-
+out:
+ kref_put(&line->ref, pblk_line_put);
return ret;
}
@@ -150,140 +136,203 @@ static void pblk_put_line_back(struct pblk *pblk, struct pblk_line *line)
static void pblk_gc_line_ws(struct work_struct *work)
{
+ struct pblk_line_ws *line_rq_ws = container_of(work,
+ struct pblk_line_ws, ws);
+ struct pblk *pblk = line_rq_ws->pblk;
+ struct pblk_gc *gc = &pblk->gc;
+ struct pblk_line *line = line_rq_ws->line;
+ struct pblk_gc_rq *gc_rq = line_rq_ws->priv;
+
+ up(&gc->gc_sem);
+
+ if (pblk_gc_move_valid_secs(pblk, gc_rq)) {
+ pr_err("pblk: could not GC all sectors: line:%d (%d/%d)\n",
+ line->id, *line->vsc,
+ gc_rq->nr_secs);
+ }
+
+ mempool_free(line_rq_ws, pblk->line_ws_pool);
+}
+
+static void pblk_gc_line_prepare_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_mgmt *l_mg = &pblk->l_mg;
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;
+ struct pblk_gc *gc = &pblk->gc;
+ struct line_emeta *emeta_buf;
+ struct pblk_line_ws *line_rq_ws;
+ struct pblk_gc_rq *gc_rq;
+ __le64 *lba_list;
+ int sec_left, nr_secs, bit;
+ int ret;
- pr_debug("pblk: line '%d' being reclaimed for GC\n", line->id);
+ emeta_buf = pblk_malloc(lm->emeta_len[0], l_mg->emeta_alloc_type,
+ GFP_KERNEL);
+ if (!emeta_buf) {
+ pr_err("pblk: cannot use GC emeta\n");
+ return;
+ }
- 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;
+ ret = pblk_line_read_emeta(pblk, line, emeta_buf);
+ if (ret) {
+ pr_err("pblk: line %d read emeta failed (%d)\n", line->id, ret);
+ goto fail_free_emeta;
}
- spin_unlock(&line->lock);
+ /* 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, emeta_buf);
+ if (!lba_list) {
+ pr_err("pblk: could not interpret emeta (line %d)\n", line->id);
+ goto fail_free_emeta;
+ }
+
+ sec_left = pblk_line_vsc(line);
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;
+ goto fail_free_emeta;
}
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;
- }
+ gc_rq = kmalloc(sizeof(struct pblk_gc_rq), GFP_KERNEL);
+ if (!gc_rq)
+ goto fail_free_emeta;
- nr_ppas = 0;
+ nr_secs = 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);
+ gc_rq->lba_list[nr_secs++] = le64_to_cpu(lba_list[bit]);
+ } while (nr_secs < pblk->max_write_pgs);
- if (unlikely(!nr_ppas)) {
- kfree(gc_list);
+ if (unlikely(!nr_secs)) {
+ kfree(gc_rq);
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;
- }
+ gc_rq->nr_secs = nr_secs;
+ gc_rq->line = line;
- sec_left -= nr_ppas;
+ line_rq_ws = mempool_alloc(pblk->line_ws_pool, GFP_KERNEL);
+ if (!line_rq_ws)
+ goto fail_free_gc_rq;
+
+ line_rq_ws->pblk = pblk;
+ line_rq_ws->line = line;
+ line_rq_ws->priv = gc_rq;
+
+ down(&gc->gc_sem);
+ kref_get(&line->ref);
+
+ INIT_WORK(&line_rq_ws->ws, pblk_gc_line_ws);
+ queue_work(gc->gc_line_reader_wq, &line_rq_ws->ws);
+
+ sec_left -= nr_secs;
if (sec_left > 0)
goto next_rq;
out:
- pblk_mfree(line->emeta, l_mg->emeta_alloc_type);
+ pblk_mfree(emeta_buf, 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);
+
+ kref_put(&line->ref, pblk_line_put);
+ atomic_dec(&gc->inflight_gc);
+
+ return;
+
+fail_free_gc_rq:
+ kfree(gc_rq);
+fail_free_emeta:
+ pblk_mfree(emeta_buf, l_mg->emeta_alloc_type);
+ pblk_put_line_back(pblk, line);
+ kref_put(&line->ref, pblk_line_put);
+ mempool_free(line_ws, pblk->line_ws_pool);
+ atomic_dec(&gc->inflight_gc);
+
+ pr_err("pblk: Failed to GC line %d\n", line->id);
}
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_gc *gc = &pblk->gc;
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;
- }
+ pr_debug("pblk: line '%d' being reclaimed for GC\n", line->id);
- /* 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 = mempool_alloc(pblk->line_ws_pool, GFP_KERNEL);
+ if (!line_ws)
+ return -ENOMEM;
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);
+ INIT_WORK(&line_ws->ws, pblk_gc_line_prepare_ws);
+ queue_work(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);
+static int pblk_gc_read(struct pblk *pblk)
+{
+ struct pblk_gc *gc = &pblk->gc;
+ struct pblk_line *line;
+
+ spin_lock(&gc->r_lock);
+ if (list_empty(&gc->r_list)) {
+ spin_unlock(&gc->r_lock);
+ return 1;
+ }
+
+ line = list_first_entry(&gc->r_list, struct pblk_line, list);
+ list_del(&line->list);
+ spin_unlock(&gc->r_lock);
+
+ pblk_gc_kick(pblk);
+
+ if (pblk_gc_line(pblk, line))
+ pr_err("pblk: failed to GC line %d\n", line->id);
- return 1;
+ return 0;
}
-static void pblk_gc_lines(struct pblk *pblk, struct list_head *gc_list)
+static void pblk_gc_reader_kick(struct pblk_gc *gc)
{
- struct pblk_line *line, *tline;
+ wake_up_process(gc->gc_reader_ts);
+}
- 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);
+static struct pblk_line *pblk_gc_get_victim_line(struct pblk *pblk,
+ struct list_head *group_list)
+{
+ struct pblk_line *line, *victim;
+
+ victim = list_first_entry(group_list, struct pblk_line, list);
+ list_for_each_entry(line, group_list, list) {
+ if (*line->vsc < *victim->vsc)
+ victim = line;
}
+
+ return victim;
+}
+
+static bool pblk_gc_should_run(struct pblk_gc *gc, struct pblk_rl *rl)
+{
+ unsigned int nr_blocks_free, nr_blocks_need;
+
+ nr_blocks_need = pblk_rl_high_thrs(rl);
+ nr_blocks_free = pblk_rl_nr_free_blks(rl);
+
+ /* This is not critical, no need to take lock here */
+ return ((gc->gc_active) && (nr_blocks_need > nr_blocks_free));
}
/*
@@ -296,71 +345,83 @@ 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 pblk_line *line;
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);
+ bool run_gc;
+ int inflight_gc, gc_group = 0, prev_group = 0;
+
+ do {
+ spin_lock(&l_mg->gc_lock);
+ if (list_empty(&l_mg->gc_full_list)) {
+ spin_unlock(&l_mg->gc_lock);
+ break;
+ }
+
+ line = list_first_entry(&l_mg->gc_full_list,
+ struct pblk_line, 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);
+ spin_unlock(&l_mg->gc_lock);
+
kref_put(&line->ref, pblk_line_put);
- }
- spin_unlock(&l_mg->gc_lock);
+ } while (1);
- 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);
+ run_gc = pblk_gc_should_run(&pblk->gc, &pblk->rl);
+ if (!run_gc || (atomic_read(&gc->inflight_gc) >= PBLK_GC_L_QD))
+ return;
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) {
+
+ do {
+ spin_lock(&l_mg->gc_lock);
+ if (list_empty(group_list)) {
spin_unlock(&l_mg->gc_lock);
- pblk_gc_lines(pblk, &gc_list);
- return;
+ break;
}
- line = list_first_entry(group_list, struct pblk_line, list);
- nr_blocks_free += atomic_read(&line->blk_in_line);
+ line = pblk_gc_get_victim_line(pblk, group_list);
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);
+ list_del(&line->list);
+ spin_unlock(&l_mg->gc_lock);
+
+ spin_lock(&gc->r_lock);
+ list_add_tail(&line->list, &gc->r_list);
+ spin_unlock(&gc->r_lock);
- pblk_gc_lines(pblk, &gc_list);
+ inflight_gc = atomic_inc_return(&gc->inflight_gc);
+ pblk_gc_reader_kick(gc);
- if (!prev_gc && pblk->rl.rb_state > gc_group &&
- gc_group < PBLK_NR_GC_LISTS)
+ prev_group = 1;
+
+ /* No need to queue up more GC lines than we can handle */
+ run_gc = pblk_gc_should_run(&pblk->gc, &pblk->rl);
+ if (!run_gc || inflight_gc >= PBLK_GC_L_QD)
+ break;
+ } while (1);
+
+ if (!prev_group && pblk->rl.rb_state > gc_group &&
+ gc_group < PBLK_GC_NR_LISTS)
goto next_gc_group;
}
-
-static void pblk_gc_kick(struct pblk *pblk)
+void pblk_gc_kick(struct pblk *pblk)
{
struct pblk_gc *gc = &pblk->gc;
wake_up_process(gc->gc_ts);
pblk_gc_writer_kick(gc);
+ pblk_gc_reader_kick(gc);
mod_timer(&gc->gc_timer, jiffies + msecs_to_jiffies(GC_TIME_MSECS));
}
@@ -398,42 +459,34 @@ static int pblk_gc_writer_ts(void *data)
return 0;
}
-static void pblk_gc_start(struct pblk *pblk)
+static int pblk_gc_reader_ts(void *data)
{
- pblk->gc.gc_active = 1;
+ struct pblk *pblk = data;
- pr_debug("pblk: gc start\n");
+ while (!kthread_should_stop()) {
+ if (!pblk_gc_read(pblk))
+ continue;
+ set_current_state(TASK_INTERRUPTIBLE);
+ io_schedule();
+ }
+
+ return 0;
}
-int pblk_gc_status(struct pblk *pblk)
+static void pblk_gc_start(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;
+ pblk->gc.gc_active = 1;
+ pr_debug("pblk: gc start\n");
}
-static void __pblk_gc_should_start(struct pblk *pblk)
+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);
+ pblk_gc_kick(pblk);
}
/*
@@ -442,10 +495,7 @@ void pblk_gc_should_start(struct pblk *pblk)
*/
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");
}
@@ -468,20 +518,25 @@ void pblk_gc_sysfs_state_show(struct pblk *pblk, int *gc_enabled,
spin_unlock(&gc->lock);
}
-void pblk_gc_sysfs_force(struct pblk *pblk, int force)
+int pblk_gc_sysfs_force(struct pblk *pblk, int force)
{
struct pblk_gc *gc = &pblk->gc;
- int rsv = 0;
+
+ if (force < 0 || force > 1)
+ return -EINVAL;
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);
+
+ if (force)
+ gc->gc_enabled = 1;
+ else
+ gc->gc_enabled = 0;
spin_unlock(&gc->lock);
+
+ pblk_gc_should_start(pblk);
+
+ return 0;
}
int pblk_gc_init(struct pblk *pblk)
@@ -503,30 +558,58 @@ int pblk_gc_init(struct pblk *pblk)
goto fail_free_main_kthread;
}
+ gc->gc_reader_ts = kthread_create(pblk_gc_reader_ts, pblk,
+ "pblk-gc-reader-ts");
+ if (IS_ERR(gc->gc_reader_ts)) {
+ pr_err("pblk: could not allocate GC reader kthread\n");
+ ret = PTR_ERR(gc->gc_reader_ts);
+ goto fail_free_writer_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);
+ /* Workqueue that reads valid sectors from a line and submit them to the
+ * GC writer to be recycled.
+ */
+ gc->gc_line_reader_wq = alloc_workqueue("pblk-gc-line-reader-wq",
+ WQ_MEM_RECLAIM | WQ_UNBOUND, PBLK_GC_MAX_READERS);
+ if (!gc->gc_line_reader_wq) {
+ pr_err("pblk: could not allocate GC line reader workqueue\n");
+ ret = -ENOMEM;
+ goto fail_free_reader_kthread;
+ }
+
+ /* Workqueue that prepare lines for GC */
+ gc->gc_reader_wq = alloc_workqueue("pblk-gc-line_wq",
+ WQ_MEM_RECLAIM | WQ_UNBOUND, 1);
if (!gc->gc_reader_wq) {
pr_err("pblk: could not allocate GC reader workqueue\n");
ret = -ENOMEM;
- goto fail_free_writer_kthread;
+ goto fail_free_reader_line_wq;
}
spin_lock_init(&gc->lock);
spin_lock_init(&gc->w_lock);
+ spin_lock_init(&gc->r_lock);
+
+ sema_init(&gc->gc_sem, 128);
+
INIT_LIST_HEAD(&gc->w_list);
+ INIT_LIST_HEAD(&gc->r_list);
return 0;
+fail_free_reader_line_wq:
+ destroy_workqueue(gc->gc_line_reader_wq);
+fail_free_reader_kthread:
+ kthread_stop(gc->gc_reader_ts);
fail_free_writer_kthread:
kthread_stop(gc->gc_writer_ts);
fail_free_main_kthread:
@@ -540,6 +623,7 @@ void pblk_gc_exit(struct pblk *pblk)
struct pblk_gc *gc = &pblk->gc;
flush_workqueue(gc->gc_reader_wq);
+ flush_workqueue(gc->gc_line_reader_wq);
del_timer(&gc->gc_timer);
pblk_gc_stop(pblk, 1);
@@ -547,9 +631,15 @@ void pblk_gc_exit(struct pblk *pblk)
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_reader_wq)
+ destroy_workqueue(gc->gc_reader_wq);
+
+ if (gc->gc_line_reader_wq)
+ destroy_workqueue(gc->gc_line_reader_wq);
if (gc->gc_writer_ts)
kthread_stop(gc->gc_writer_ts);
+
+ if (gc->gc_reader_ts)
+ kthread_stop(gc->gc_reader_ts);
}
diff --git a/drivers/lightnvm/pblk-init.c b/drivers/lightnvm/pblk-init.c
index ae8cd6d5af8b..8bdaf7e0e00b 100644
--- a/drivers/lightnvm/pblk-init.c
+++ b/drivers/lightnvm/pblk-init.c
@@ -20,9 +20,10 @@
#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 struct kmem_cache *pblk_blk_ws_cache, *pblk_rec_cache, *pblk_g_rq_cache,
+ *pblk_w_rq_cache, *pblk_line_meta_cache;
static DECLARE_RWSEM(pblk_lock);
+struct bio_set *pblk_bio_set;
static int pblk_rw_io(struct request_queue *q, struct pblk *pblk,
struct bio *bio)
@@ -33,7 +34,7 @@ static int pblk_rw_io(struct request_queue *q, struct pblk *pblk,
* constraint. Writes can be of arbitrary size.
*/
if (bio_data_dir(bio) == READ) {
- blk_queue_split(q, &bio, q->bio_split);
+ blk_queue_split(q, &bio);
ret = pblk_submit_read(pblk, bio);
if (ret == NVM_IO_DONE && bio_flagged(bio, BIO_CLONED))
bio_put(bio);
@@ -46,7 +47,7 @@ static int pblk_rw_io(struct request_queue *q, struct pblk *pblk,
* 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);
+ blk_queue_split(q, &bio);
return pblk_write_to_cache(pblk, bio, PBLK_IOTYPE_USER);
}
@@ -199,9 +200,9 @@ static int pblk_init_global_caches(struct pblk *pblk)
return -ENOMEM;
}
- pblk_r_rq_cache = kmem_cache_create("pblk_r_rq", pblk_r_rq_size,
+ pblk_g_rq_cache = kmem_cache_create("pblk_g_rq", pblk_g_rq_size,
0, 0, NULL);
- if (!pblk_r_rq_cache) {
+ if (!pblk_g_rq_cache) {
kmem_cache_destroy(pblk_blk_ws_cache);
kmem_cache_destroy(pblk_rec_cache);
up_write(&pblk_lock);
@@ -213,7 +214,7 @@ static int pblk_init_global_caches(struct pblk *pblk)
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);
+ kmem_cache_destroy(pblk_g_rq_cache);
up_write(&pblk_lock);
return -ENOMEM;
}
@@ -225,7 +226,7 @@ static int pblk_init_global_caches(struct pblk *pblk)
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_g_rq_cache);
kmem_cache_destroy(pblk_w_rq_cache);
up_write(&pblk_lock);
return -ENOMEM;
@@ -239,27 +240,10 @@ 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;
@@ -267,7 +251,7 @@ static int pblk_core_init(struct pblk *pblk)
if (!pblk->page_pool)
return -ENOMEM;
- pblk->line_ws_pool = mempool_create_slab_pool(geo->nr_luns,
+ pblk->line_ws_pool = mempool_create_slab_pool(PBLK_WS_POOL_SIZE,
pblk_blk_ws_cache);
if (!pblk->line_ws_pool)
goto free_page_pool;
@@ -276,41 +260,51 @@ static int pblk_core_init(struct pblk *pblk)
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)
+ pblk->g_rq_pool = mempool_create_slab_pool(PBLK_READ_REQ_POOL_SIZE,
+ pblk_g_rq_cache);
+ if (!pblk->g_rq_pool)
goto free_rec_pool;
- pblk->w_rq_pool = mempool_create_slab_pool(64, pblk_w_rq_cache);
+ pblk->w_rq_pool = mempool_create_slab_pool(geo->nr_luns * 2,
+ pblk_w_rq_cache);
if (!pblk->w_rq_pool)
- goto free_r_rq_pool;
+ goto free_g_rq_pool;
pblk->line_meta_pool =
- mempool_create_slab_pool(16, pblk_line_meta_cache);
+ mempool_create_slab_pool(PBLK_META_POOL_SIZE,
+ 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)
+ pblk->close_wq = alloc_workqueue("pblk-close-wq",
+ WQ_MEM_RECLAIM | WQ_UNBOUND, PBLK_NR_CLOSE_JOBS);
+ if (!pblk->close_wq)
goto free_line_meta_pool;
+ pblk->bb_wq = alloc_workqueue("pblk-bb-wq",
+ WQ_MEM_RECLAIM | WQ_UNBOUND, 0);
+ if (!pblk->bb_wq)
+ goto free_close_wq;
+
if (pblk_set_ppaf(pblk))
- goto free_kw_wq;
+ goto free_bb_wq;
if (pblk_rwb_init(pblk))
- goto free_kw_wq;
+ goto free_bb_wq;
INIT_LIST_HEAD(&pblk->compl_list);
return 0;
-free_kw_wq:
- destroy_workqueue(pblk->kw_wq);
+free_bb_wq:
+ destroy_workqueue(pblk->bb_wq);
+free_close_wq:
+ destroy_workqueue(pblk->close_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_g_rq_pool:
+ mempool_destroy(pblk->g_rq_pool);
free_rec_pool:
mempool_destroy(pblk->rec_pool);
free_blk_ws_pool:
@@ -322,19 +316,22 @@ free_page_pool:
static void pblk_core_free(struct pblk *pblk)
{
- if (pblk->kw_wq)
- destroy_workqueue(pblk->kw_wq);
+ if (pblk->close_wq)
+ destroy_workqueue(pblk->close_wq);
+
+ if (pblk->bb_wq)
+ destroy_workqueue(pblk->bb_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->g_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_g_rq_cache);
kmem_cache_destroy(pblk_w_rq_cache);
kmem_cache_destroy(pblk_line_meta_cache);
}
@@ -344,6 +341,12 @@ static void pblk_luns_free(struct pblk *pblk)
kfree(pblk->luns);
}
+static void pblk_free_line_bitmaps(struct pblk_line *line)
+{
+ kfree(line->blk_bitmap);
+ kfree(line->erase_bitmap);
+}
+
static void pblk_lines_free(struct pblk *pblk)
{
struct pblk_line_mgmt *l_mg = &pblk->l_mg;
@@ -355,8 +358,7 @@ static void pblk_lines_free(struct pblk *pblk)
line = &pblk->lines[i];
pblk_line_free(pblk, line);
- kfree(line->blk_bitmap);
- kfree(line->erase_bitmap);
+ pblk_free_line_bitmaps(line);
}
spin_unlock(&l_mg->free_lock);
}
@@ -368,11 +370,15 @@ static void pblk_line_meta_free(struct pblk *pblk)
kfree(l_mg->bb_template);
kfree(l_mg->bb_aux);
+ kfree(l_mg->vsc_list);
+ spin_lock(&l_mg->free_lock);
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(l_mg->sline_meta[i]);
+ pblk_mfree(l_mg->eline_meta[i]->buf, l_mg->emeta_alloc_type);
+ kfree(l_mg->eline_meta[i]);
}
+ spin_unlock(&l_mg->free_lock);
kfree(pblk->lines);
}
@@ -411,13 +417,31 @@ out:
return ret;
}
-static int pblk_bb_line(struct pblk *pblk, struct pblk_line *line)
+static int pblk_bb_line(struct pblk *pblk, struct pblk_line *line,
+ int blk_per_line)
{
- struct pblk_line_meta *lm = &pblk->lm;
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
struct pblk_lun *rlun;
int bb_cnt = 0;
int i;
+ for (i = 0; i < blk_per_line; i++) {
+ rlun = &pblk->luns[i];
+ if (rlun->bb_list[line->id] == NVM_BLK_T_FREE)
+ continue;
+
+ set_bit(pblk_ppa_to_pos(geo, rlun->bppa), line->blk_bitmap);
+ bb_cnt++;
+ }
+
+ return bb_cnt;
+}
+
+static int pblk_alloc_line_bitmaps(struct pblk *pblk, struct pblk_line *line)
+{
+ struct pblk_line_meta *lm = &pblk->lm;
+
line->blk_bitmap = kzalloc(lm->blk_bitmap_len, GFP_KERNEL);
if (!line->blk_bitmap)
return -ENOMEM;
@@ -428,16 +452,7 @@ static int pblk_bb_line(struct pblk *pblk, struct pblk_line *line)
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;
+ return 0;
}
static int pblk_luns_init(struct pblk *pblk, struct ppa_addr *luns)
@@ -505,12 +520,32 @@ static int pblk_lines_configure(struct pblk *pblk, int flags)
}
/* See comment over struct line_emeta definition */
-static unsigned int calc_emeta_len(struct pblk *pblk, struct pblk_line_meta *lm)
+static unsigned int calc_emeta_len(struct pblk *pblk)
{
- 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);
+ struct pblk_line_meta *lm = &pblk->lm;
+ struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+
+ /* Round to sector size so that lba_list starts on its own sector */
+ lm->emeta_sec[1] = DIV_ROUND_UP(
+ sizeof(struct line_emeta) + lm->blk_bitmap_len,
+ geo->sec_size);
+ lm->emeta_len[1] = lm->emeta_sec[1] * geo->sec_size;
+
+ /* Round to sector size so that vsc_list starts on its own sector */
+ lm->dsec_per_line = lm->sec_per_line - lm->emeta_sec[0];
+ lm->emeta_sec[2] = DIV_ROUND_UP(lm->dsec_per_line * sizeof(u64),
+ geo->sec_size);
+ lm->emeta_len[2] = lm->emeta_sec[2] * geo->sec_size;
+
+ lm->emeta_sec[3] = DIV_ROUND_UP(l_mg->nr_lines * sizeof(u32),
+ geo->sec_size);
+ lm->emeta_len[3] = lm->emeta_sec[3] * geo->sec_size;
+
+ lm->vsc_list_len = l_mg->nr_lines * sizeof(u32);
+
+ return (lm->emeta_len[1] + lm->emeta_len[2] + lm->emeta_len[3]);
}
static void pblk_set_provision(struct pblk *pblk, long nr_free_blks)
@@ -534,6 +569,78 @@ static void pblk_set_provision(struct pblk *pblk, long nr_free_blks)
atomic_set(&pblk->rl.free_blocks, nr_free_blks);
}
+static int pblk_lines_alloc_metadata(struct pblk *pblk)
+{
+ struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+ struct pblk_line_meta *lm = &pblk->lm;
+ int i;
+
+ /* smeta is always small enough to fit on a kmalloc memory allocation,
+ * emeta depends on the number of LUNs allocated to the pblk instance
+ */
+ for (i = 0; i < PBLK_DATA_LINES; i++) {
+ l_mg->sline_meta[i] = kmalloc(lm->smeta_len, GFP_KERNEL);
+ if (!l_mg->sline_meta[i])
+ goto fail_free_smeta;
+ }
+
+ /* emeta allocates three different buffers for managing metadata with
+ * in-memory and in-media layouts
+ */
+ for (i = 0; i < PBLK_DATA_LINES; i++) {
+ struct pblk_emeta *emeta;
+
+ emeta = kmalloc(sizeof(struct pblk_emeta), GFP_KERNEL);
+ if (!emeta)
+ goto fail_free_emeta;
+
+ if (lm->emeta_len[0] > KMALLOC_MAX_CACHE_SIZE) {
+ l_mg->emeta_alloc_type = PBLK_VMALLOC_META;
+
+ emeta->buf = vmalloc(lm->emeta_len[0]);
+ if (!emeta->buf) {
+ kfree(emeta);
+ goto fail_free_emeta;
+ }
+
+ emeta->nr_entries = lm->emeta_sec[0];
+ l_mg->eline_meta[i] = emeta;
+ } else {
+ l_mg->emeta_alloc_type = PBLK_KMALLOC_META;
+
+ emeta->buf = kmalloc(lm->emeta_len[0], GFP_KERNEL);
+ if (!emeta->buf) {
+ kfree(emeta);
+ goto fail_free_emeta;
+ }
+
+ emeta->nr_entries = lm->emeta_sec[0];
+ l_mg->eline_meta[i] = emeta;
+ }
+ }
+
+ l_mg->vsc_list = kcalloc(l_mg->nr_lines, sizeof(__le32), GFP_KERNEL);
+ if (!l_mg->vsc_list)
+ goto fail_free_emeta;
+
+ for (i = 0; i < l_mg->nr_lines; i++)
+ l_mg->vsc_list[i] = cpu_to_le32(EMPTY_ENTRY);
+
+ return 0;
+
+fail_free_emeta:
+ while (--i >= 0) {
+ vfree(l_mg->eline_meta[i]->buf);
+ kfree(l_mg->eline_meta[i]);
+ }
+
+fail_free_smeta:
+ for (i = 0; i < PBLK_DATA_LINES; i++)
+ kfree(l_mg->sline_meta[i]);
+
+ return -ENOMEM;
+}
+
static int pblk_lines_init(struct pblk *pblk)
{
struct nvm_tgt_dev *dev = pblk->dev;
@@ -542,10 +649,32 @@ static int pblk_lines_init(struct pblk *pblk)
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;
+ long nr_bad_blks, nr_free_blks;
+ int bb_distance, max_write_ppas, mod;
+ int i, ret;
+
+ 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_set_sec_per_write(pblk, pblk->min_write_pgs);
+
+ 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;
+ }
+
+ 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);
lm->sec_per_line = geo->sec_per_blk * geo->nr_luns;
lm->blk_per_line = geo->nr_luns;
@@ -554,20 +683,17 @@ static int pblk_lines_init(struct pblk *pblk)
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;
+ lm->meta_distance = (geo->nr_luns / 2) * pblk->min_write_pgs;
/* 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;
+ smeta_len = sizeof(struct line_smeta) + lm->lun_bitmap_len;
if (smeta_len > lm->smeta_len) {
i++;
goto add_smeta_page;
@@ -578,66 +704,22 @@ add_smeta_page:
*/
i = 1;
add_emeta_page:
- lm->emeta_sec = i * geo->sec_per_pl;
- lm->emeta_len = lm->emeta_sec * geo->sec_size;
+ lm->emeta_sec[0] = i * geo->sec_per_pl;
+ lm->emeta_len[0] = lm->emeta_sec[0] * geo->sec_size;
- emeta_len = calc_emeta_len(pblk, lm);
- if (emeta_len > lm->emeta_len) {
+ emeta_len = calc_emeta_len(pblk);
+ if (emeta_len > lm->emeta_len[0]) {
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;
+ lm->emeta_bb = geo->nr_luns - i;
+ lm->min_blk_line = 1 + DIV_ROUND_UP(lm->smeta_sec + lm->emeta_sec[0],
+ geo->sec_per_blk);
- 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;
- }
- }
- }
+ ret = pblk_lines_alloc_metadata(pblk);
+ if (ret)
+ goto fail;
l_mg->bb_template = kzalloc(lm->sec_bitmap_len, GFP_KERNEL);
if (!l_mg->bb_template) {
@@ -664,11 +746,14 @@ add_emeta_page:
INIT_LIST_HEAD(&l_mg->gc_low_list);
INIT_LIST_HEAD(&l_mg->gc_empty_list);
+ INIT_LIST_HEAD(&l_mg->emeta_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->close_lock);
spin_lock_init(&l_mg->gc_lock);
pblk->lines = kcalloc(l_mg->nr_lines, sizeof(struct pblk_line),
@@ -689,10 +774,16 @@ add_emeta_page:
line->type = PBLK_LINETYPE_FREE;
line->state = PBLK_LINESTATE_FREE;
line->gc_group = PBLK_LINEGC_NONE;
+ line->vsc = &l_mg->vsc_list[i];
spin_lock_init(&line->lock);
- nr_bad_blks = pblk_bb_line(pblk, line);
+ ret = pblk_alloc_line_bitmaps(pblk, line);
+ if (ret)
+ goto fail_free_lines;
+
+ nr_bad_blks = pblk_bb_line(pblk, line, lm->blk_per_line);
if (nr_bad_blks < 0 || nr_bad_blks > lm->blk_per_line) {
+ pblk_free_line_bitmaps(line);
ret = -EINVAL;
goto fail_free_lines;
}
@@ -713,24 +804,22 @@ add_emeta_page:
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:
+ while (--i >= 0)
+ pblk_free_line_bitmaps(&pblk->lines[i]);
+
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);
- }
+ pblk_line_meta_free(pblk);
fail:
for (i = 0; i < geo->nr_luns; i++)
kfree(pblk->luns[i].bb_list);
@@ -772,10 +861,9 @@ static void pblk_free(struct pblk *pblk)
static void pblk_tear_down(struct pblk *pblk)
{
- pblk_flush_writer(pblk);
+ pblk_pipeline_stop(pblk);
pblk_writer_stop(pblk);
pblk_rb_sync_l2p(&pblk->rwb);
- pblk_recov_pad(pblk);
pblk_rwb_free(pblk);
pblk_rl_free(&pblk->rl);
@@ -821,6 +909,7 @@ static void *pblk_init(struct nvm_tgt_dev *dev, struct gendisk *tdisk,
pblk->dev = dev;
pblk->disk = tdisk;
+ pblk->state = PBLK_STATE_RUNNING;
spin_lock_init(&pblk->trans_lock);
spin_lock_init(&pblk->lock);
@@ -836,8 +925,8 @@ static void *pblk_init(struct nvm_tgt_dev *dev, struct gendisk *tdisk,
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->cache_reads, 0);
atomic_long_set(&pblk->sync_reads, 0);
atomic_long_set(&pblk->recov_writes, 0);
atomic_long_set(&pblk->recov_writes, 0);
@@ -946,11 +1035,20 @@ static struct nvm_tgt_type tt_pblk = {
static int __init pblk_module_init(void)
{
- return nvm_register_tgt_type(&tt_pblk);
+ int ret;
+
+ pblk_bio_set = bioset_create(BIO_POOL_SIZE, 0, 0);
+ if (!pblk_bio_set)
+ return -ENOMEM;
+ ret = nvm_register_tgt_type(&tt_pblk);
+ if (ret)
+ bioset_free(pblk_bio_set);
+ return ret;
}
static void pblk_module_exit(void)
{
+ bioset_free(pblk_bio_set);
nvm_unregister_tgt_type(&tt_pblk);
}
diff --git a/drivers/lightnvm/pblk-map.c b/drivers/lightnvm/pblk-map.c
index 17c16955284d..a9be03cd07a8 100644
--- a/drivers/lightnvm/pblk-map.c
+++ b/drivers/lightnvm/pblk-map.c
@@ -25,9 +25,9 @@ static void pblk_map_page_data(struct pblk *pblk, unsigned int sentry,
unsigned int valid_secs)
{
struct pblk_line *line = pblk_line_get_data(pblk);
- struct line_emeta *emeta = line->emeta;
+ struct pblk_emeta *emeta = line->emeta;
struct pblk_w_ctx *w_ctx;
- __le64 *lba_list = pblk_line_emeta_to_lbas(emeta);
+ __le64 *lba_list = emeta_to_lbas(pblk, emeta->buf);
u64 paddr;
int nr_secs = pblk->min_write_pgs;
int i;
@@ -51,18 +51,20 @@ static void pblk_map_page_data(struct pblk *pblk, unsigned int sentry,
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);
+ line->nr_valid_lbas++;
} 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);
+ u64 addr_empty = cpu_to_le64(ADDR_EMPTY);
+
+ lba_list[paddr] = meta_list[i].lba = addr_empty;
+ __pblk_map_invalidate(pblk, line, paddr);
}
}
if (pblk_line_is_full(line)) {
- line = pblk_line_replace_data(pblk);
- if (!line)
- return;
+ struct pblk_line *prev_line = line;
+
+ pblk_line_replace_data(pblk);
+ pblk_line_close_meta(pblk, prev_line);
}
pblk_down_rq(pblk, ppa_list, nr_secs, lun_bitmap);
@@ -91,8 +93,9 @@ void pblk_map_erase_rq(struct pblk *pblk, struct nvm_rq *rqd,
{
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_line_meta *lm = &pblk->lm;
struct pblk_sec_meta *meta_list = rqd->meta_list;
+ struct pblk_line *e_line, *d_line;
unsigned int map_secs;
int min = pblk->min_write_pgs;
int i, erase_lun;
@@ -102,35 +105,63 @@ void pblk_map_erase_rq(struct pblk *pblk, struct nvm_rq *rqd,
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;
+ erase_lun = pblk_ppa_to_pos(geo, rqd->ppa_list[i]);
- if (!test_bit(erase_lun, e_line->erase_bitmap)) {
- if (down_trylock(&pblk->erase_sem))
- continue;
+ /* line can change after page map. We might also be writing the
+ * last line.
+ */
+ e_line = pblk_line_get_erase(pblk);
+ if (!e_line)
+ return pblk_map_rq(pblk, rqd, sentry, lun_bitmap,
+ valid_secs, i + min);
+ spin_lock(&e_line->lock);
+ if (!test_bit(erase_lun, e_line->erase_bitmap)) {
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;
+ spin_unlock(&e_line->lock);
+
/* Avoid evaluating e_line->left_eblks */
return pblk_map_rq(pblk, rqd, sentry, lun_bitmap,
valid_secs, i + min);
}
+ spin_unlock(&e_line->lock);
}
- /* 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;
+ d_line = pblk_line_get_data(pblk);
+
+ /* line can change after page map. We might also be writing the
+ * last line.
+ */
+ e_line = pblk_line_get_erase(pblk);
+ if (!e_line)
+ return;
- i = find_first_zero_bit(e_line->erase_bitmap, lm->blk_per_line);
- if (i == lm->blk_per_line)
+ /* Erase blocks that are bad in this line but might not be in next */
+ if (unlikely(ppa_empty(*erase_ppa)) &&
+ bitmap_weight(d_line->blk_bitmap, lm->blk_per_line)) {
+ int bit = -1;
+
+retry:
+ bit = find_next_bit(d_line->blk_bitmap,
+ lm->blk_per_line, bit + 1);
+ if (bit >= lm->blk_per_line)
return;
- set_bit(i, e_line->erase_bitmap);
+ spin_lock(&e_line->lock);
+ if (test_bit(bit, e_line->erase_bitmap)) {
+ spin_unlock(&e_line->lock);
+ goto retry;
+ }
+ spin_unlock(&e_line->lock);
+
+ set_bit(bit, e_line->erase_bitmap);
atomic_dec(&e_line->left_eblks);
- *erase_ppa = pblk->luns[i].bppa; /* set ch and lun */
+ *erase_ppa = pblk->luns[bit].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
index 045384ddc1f9..665a4ccfe7f5 100644
--- a/drivers/lightnvm/pblk-rb.c
+++ b/drivers/lightnvm/pblk-rb.c
@@ -199,12 +199,22 @@ static int __pblk_rb_update_l2p(struct pblk_rb *rb, unsigned int *l2p_upd,
struct pblk_line *line;
struct pblk_rb_entry *entry;
struct pblk_w_ctx *w_ctx;
+ unsigned int user_io = 0, gc_io = 0;
unsigned int i;
+ int flags;
for (i = 0; i < to_update; i++) {
entry = &rb->entries[*l2p_upd];
w_ctx = &entry->w_ctx;
+ flags = READ_ONCE(entry->w_ctx.flags);
+ if (flags & PBLK_IOTYPE_USER)
+ user_io++;
+ else if (flags & PBLK_IOTYPE_GC)
+ gc_io++;
+ else
+ WARN(1, "pblk: unknown IO type\n");
+
pblk_update_map_dev(pblk, w_ctx->lba, w_ctx->ppa,
entry->cacheline);
@@ -214,6 +224,8 @@ static int __pblk_rb_update_l2p(struct pblk_rb *rb, unsigned int *l2p_upd,
*l2p_upd = (*l2p_upd + 1) & (rb->nr_entries - 1);
}
+ pblk_rl_out(&pblk->rl, user_io, gc_io);
+
return 0;
}
@@ -357,6 +369,9 @@ static int pblk_rb_sync_point_set(struct pblk_rb *rb, struct bio *bio,
/* Protect syncs */
smp_store_release(&rb->sync_point, sync_point);
+ if (!bio)
+ return 0;
+
spin_lock_irq(&rb->s_lock);
bio_list_add(&entry->w_ctx.bios, bio);
spin_unlock_irq(&rb->s_lock);
@@ -395,6 +410,17 @@ static int pblk_rb_may_write(struct pblk_rb *rb, unsigned int nr_entries,
return 1;
}
+void pblk_rb_flush(struct pblk_rb *rb)
+{
+ struct pblk *pblk = container_of(rb, struct pblk, rwb);
+ unsigned int mem = READ_ONCE(rb->mem);
+
+ if (pblk_rb_sync_point_set(rb, NULL, mem))
+ return;
+
+ pblk_write_should_kick(pblk);
+}
+
static int pblk_rb_may_write_flush(struct pblk_rb *rb, unsigned int nr_entries,
unsigned int *pos, struct bio *bio,
int *io_ret)
@@ -431,15 +457,16 @@ 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;
+ int io_ret;
spin_lock(&rb->w_lock);
- if (!pblk_rl_user_may_insert(&pblk->rl, nr_entries)) {
+ io_ret = pblk_rl_user_may_insert(&pblk->rl, nr_entries);
+ if (io_ret) {
spin_unlock(&rb->w_lock);
- return NVM_IO_REQUEUE;
+ return io_ret;
}
- if (!pblk_rb_may_write_flush(rb, nr_entries, pos, bio, &flush_done)) {
+ if (!pblk_rb_may_write_flush(rb, nr_entries, pos, bio, &io_ret)) {
spin_unlock(&rb->w_lock);
return NVM_IO_REQUEUE;
}
@@ -447,7 +474,7 @@ int pblk_rb_may_write_user(struct pblk_rb *rb, struct bio *bio,
pblk_rl_user_in(&pblk->rl, nr_entries);
spin_unlock(&rb->w_lock);
- return flush_done;
+ return io_ret;
}
/*
@@ -521,20 +548,18 @@ out:
* 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)
+unsigned int pblk_rb_read_to_bio(struct pblk_rb *rb, struct nvm_rq *rqd,
+ struct bio *bio, unsigned int pos,
+ unsigned int nr_entries, unsigned int count)
{
struct pblk *pblk = container_of(rb, struct pblk, rwb);
+ struct request_queue *q = pblk->dev->q;
+ struct pblk_c_ctx *c_ctx = nvm_rq_to_pdu(rqd);
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 pad = 0, to_read = nr_entries;
unsigned int i;
int flags;
- int ret;
if (count < nr_entries) {
pad = nr_entries - count;
@@ -556,13 +581,6 @@ try:
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");
@@ -570,17 +588,17 @@ try:
flags |= PBLK_SUBMITTED_ENTRY;
/* Release flags on context. Protect from writes */
smp_store_release(&entry->w_ctx.flags, flags);
- goto out;
+ return NVM_IO_ERR;
}
- ret = bio_add_page(bio, page, rb->seg_size, 0);
- if (ret != rb->seg_size) {
+ if (bio_add_pc_page(q, bio, page, rb->seg_size, 0) !=
+ 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;
+ return NVM_IO_ERR;
}
if (flags & PBLK_FLUSH_ENTRY) {
@@ -607,14 +625,19 @@ try:
pos = (pos + 1) & (rb->nr_entries - 1);
}
- read = to_read;
- pblk_rl_out(&pblk->rl, user_io, gc_io);
+ if (pad) {
+ if (pblk_bio_add_pages(pblk, bio, GFP_KERNEL, pad)) {
+ pr_err("pblk: could not pad page in write bio\n");
+ return NVM_IO_ERR;
+ }
+ }
+
#ifdef CONFIG_NVM_DEBUG
atomic_long_add(pad, &((struct pblk *)
(container_of(rb, struct pblk, rwb)))->padded_writes);
#endif
-out:
- return read;
+
+ return NVM_IO_OK;
}
/*
diff --git a/drivers/lightnvm/pblk-read.c b/drivers/lightnvm/pblk-read.c
index 4a12f14d78c6..ed2ea01a0a38 100644
--- a/drivers/lightnvm/pblk-read.c
+++ b/drivers/lightnvm/pblk-read.c
@@ -76,6 +76,9 @@ retry:
}
WARN_ON(test_and_set_bit(i, read_bitmap));
advanced_bio = 1;
+#ifdef CONFIG_NVM_DEBUG
+ atomic_long_inc(&pblk->cache_reads);
+#endif
} else {
/* Read from media non-cached sectors */
rqd->ppa_list[j++] = p;
@@ -85,6 +88,11 @@ retry:
bio_advance(bio, PBLK_EXPOSED_PAGE_SIZE);
}
+ if (pblk_io_aligned(pblk, nr_secs))
+ rqd->flags = pblk_set_read_mode(pblk, PBLK_READ_SEQUENTIAL);
+ else
+ rqd->flags = pblk_set_read_mode(pblk, PBLK_READ_RANDOM);
+
#ifdef CONFIG_NVM_DEBUG
atomic_long_add(nr_secs, &pblk->inflight_reads);
#endif
@@ -94,8 +102,6 @@ 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;
@@ -107,27 +113,27 @@ 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 pblk_g_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");
+ WARN_ONCE(bio->bi_status, "pblk: corrupted read error\n");
#endif
- if (rqd->nr_ppas > 1)
- nvm_dev_dma_free(dev->parent, rqd->ppa_list, rqd->dma_ppa_list);
+ nvm_dev_dma_free(dev->parent, rqd->meta_list, rqd->dma_meta_list);
bio_put(bio);
- if (r_ctx->orig_bio) {
+ if (r_ctx->private) {
+ struct bio *orig_bio = r_ctx->private;
+
#ifdef CONFIG_NVM_DEBUG
- WARN_ONCE(r_ctx->orig_bio->bi_error,
- "pblk: corrupted read bio\n");
+ WARN_ONCE(orig_bio->bi_status, "pblk: corrupted read bio\n");
#endif
- bio_endio(r_ctx->orig_bio);
- bio_put(r_ctx->orig_bio);
+ bio_endio(orig_bio);
+ bio_put(orig_bio);
}
#ifdef CONFIG_NVM_DEBUG
@@ -136,6 +142,7 @@ static void pblk_end_io_read(struct nvm_rq *rqd)
#endif
pblk_free_rqd(pblk, rqd, READ);
+ atomic_dec(&pblk->inflight_io);
}
static int pblk_fill_partial_read_bio(struct pblk *pblk, struct nvm_rq *rqd,
@@ -173,6 +180,7 @@ static int pblk_fill_partial_read_bio(struct pblk *pblk, struct nvm_rq *rqd,
rqd->bio = new_bio;
rqd->nr_ppas = nr_holes;
+ rqd->flags = pblk_set_read_mode(pblk, PBLK_READ_RANDOM);
rqd->end_io = NULL;
if (unlikely(nr_secs > 1 && nr_holes == 1)) {
@@ -280,9 +288,14 @@ retry:
goto retry;
}
WARN_ON(test_and_set_bit(0, read_bitmap));
+#ifdef CONFIG_NVM_DEBUG
+ atomic_long_inc(&pblk->cache_reads);
+#endif
} else {
rqd->ppa_addr = ppa;
}
+
+ rqd->flags = pblk_set_read_mode(pblk, PBLK_READ_RANDOM);
}
int pblk_submit_read(struct pblk *pblk, struct bio *bio)
@@ -316,13 +329,16 @@ int pblk_submit_read(struct pblk *pblk, struct bio *bio)
*/
bio_init_idx = pblk_get_bi_idx(bio);
+ rqd->meta_list = nvm_dev_dma_alloc(dev->parent, GFP_KERNEL,
+ &rqd->dma_meta_list);
+ if (!rqd->meta_list) {
+ pr_err("pblk: not able to allocate ppa list\n");
+ goto fail_rqd_free;
+ }
+
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;
- }
+ rqd->ppa_list = rqd->meta_list + pblk_dma_meta_size;
+ rqd->dma_ppa_list = rqd->dma_meta_list + pblk_dma_meta_size;
pblk_read_ppalist_rq(pblk, rqd, &read_bitmap);
} else {
@@ -332,6 +348,7 @@ int pblk_submit_read(struct pblk *pblk, struct bio *bio)
bio_get(bio);
if (bitmap_full(&read_bitmap, nr_secs)) {
bio_endio(bio);
+ atomic_inc(&pblk->inflight_io);
pblk_end_io_read(rqd);
return NVM_IO_OK;
}
@@ -339,17 +356,17 @@ int pblk_submit_read(struct pblk *pblk, struct bio *bio)
/* 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);
+ struct pblk_g_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);
+ int_bio = bio_clone_fast(bio, GFP_KERNEL, pblk_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;
+ r_ctx->private = bio;
ret = pblk_submit_read_io(pblk, rqd);
if (ret) {
@@ -453,22 +470,19 @@ int pblk_submit_read_gc(struct pblk *pblk, u64 *lba_list, void *data,
memset(&rqd, 0, sizeof(struct nvm_rq));
+ rqd.meta_list = nvm_dev_dma_alloc(dev->parent, GFP_KERNEL,
+ &rqd.dma_meta_list);
+ if (!rqd.meta_list)
+ return NVM_IO_ERR;
+
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;
+ rqd.ppa_list = rqd.meta_list + pblk_dma_meta_size;
+ rqd.dma_ppa_list = rqd.dma_meta_list + pblk_dma_meta_size;
*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;
- }
+ if (*secs_to_gc == 1)
+ rqd.ppa_addr = rqd.ppa_list[0];
} else {
*secs_to_gc = read_rq_gc(pblk, &rqd, line, lba_list[0]);
}
@@ -490,6 +504,7 @@ int pblk_submit_read_gc(struct pblk *pblk, u64 *lba_list, void *data,
rqd.end_io = pblk_end_io_sync;
rqd.private = &wait;
rqd.nr_ppas = *secs_to_gc;
+ rqd.flags = pblk_set_read_mode(pblk, PBLK_READ_RANDOM);
rqd.bio = bio;
ret = pblk_submit_read_io(pblk, &rqd);
@@ -503,6 +518,7 @@ int pblk_submit_read_gc(struct pblk *pblk, u64 *lba_list, void *data,
msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) {
pr_err("pblk: GC read I/O timed out\n");
}
+ atomic_dec(&pblk->inflight_io);
if (rqd.error) {
atomic_long_inc(&pblk->read_failed_gc);
@@ -518,12 +534,10 @@ int pblk_submit_read_gc(struct pblk *pblk, u64 *lba_list, void *data,
#endif
out:
- if (rqd.nr_ppas > 1)
- nvm_dev_dma_free(dev->parent, rqd.ppa_list, rqd.dma_ppa_list);
+ nvm_dev_dma_free(dev->parent, rqd.meta_list, rqd.dma_meta_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);
+ nvm_dev_dma_free(dev->parent, rqd.meta_list, rqd.dma_meta_list);
return NVM_IO_ERR;
}
diff --git a/drivers/lightnvm/pblk-recovery.c b/drivers/lightnvm/pblk-recovery.c
index f8f85087cd3c..abf36f587477 100644
--- a/drivers/lightnvm/pblk-recovery.c
+++ b/drivers/lightnvm/pblk-recovery.c
@@ -120,18 +120,18 @@ int pblk_recov_setup_rq(struct pblk *pblk, struct pblk_c_ctx *c_ctx,
return 0;
}
-__le64 *pblk_recov_get_lba_list(struct pblk *pblk, struct line_emeta *emeta)
+__le64 *pblk_recov_get_lba_list(struct pblk *pblk, struct line_emeta *emeta_buf)
{
u32 crc;
- crc = pblk_calc_emeta_crc(pblk, emeta);
- if (le32_to_cpu(emeta->crc) != crc)
+ crc = pblk_calc_emeta_crc(pblk, emeta_buf);
+ if (le32_to_cpu(emeta_buf->crc) != crc)
return NULL;
- if (le32_to_cpu(emeta->header.identifier) != PBLK_MAGIC)
+ if (le32_to_cpu(emeta_buf->header.identifier) != PBLK_MAGIC)
return NULL;
- return pblk_line_emeta_to_lbas(emeta);
+ return emeta_to_lbas(pblk, emeta_buf);
}
static int pblk_recov_l2p_from_emeta(struct pblk *pblk, struct pblk_line *line)
@@ -139,19 +139,20 @@ 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;
+ struct pblk_emeta *emeta = line->emeta;
+ struct line_emeta *emeta_buf = emeta->buf;
__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);
+ lba_list = pblk_recov_get_lba_list(pblk, emeta_buf);
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);
+ nr_data_lbas = lm->sec_per_line - lm->emeta_sec[0];
+ nr_valid_lbas = le64_to_cpu(emeta_buf->nr_valid_lbas);
for (i = data_start; i < nr_data_lbas && nr_lbas < nr_valid_lbas; i++) {
struct ppa_addr ppa;
@@ -169,7 +170,7 @@ static int pblk_recov_l2p_from_emeta(struct pblk *pblk, struct pblk_line *line)
if (test_and_set_bit(i, line->invalid_bitmap))
WARN_ONCE(1, "pblk: rec. double invalidate:\n");
else
- line->vsc--;
+ le32_add_cpu(line->vsc, -1);
spin_unlock(&line->lock);
continue;
@@ -181,7 +182,7 @@ static int pblk_recov_l2p_from_emeta(struct pblk *pblk, struct pblk_line *line)
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->id, emeta_buf->nr_valid_lbas, nr_lbas);
line->left_msecs = 0;
@@ -195,7 +196,7 @@ static int pblk_calc_sec_in_line(struct pblk *pblk, struct pblk_line *line)
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 -
+ return lm->sec_per_line - lm->smeta_sec - lm->emeta_sec[0] -
nr_bb * geo->sec_per_blk;
}
@@ -240,7 +241,7 @@ static int pblk_recov_read_oob(struct pblk *pblk, struct pblk_line *line,
r_ptr_int = r_ptr;
next_read_rq:
- memset(rqd, 0, pblk_r_rq_size);
+ memset(rqd, 0, pblk_g_rq_size);
rq_ppas = pblk_calc_secs(pblk, left_ppas, 0);
if (!rq_ppas)
@@ -256,7 +257,6 @@ next_read_rq:
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;
@@ -265,6 +265,11 @@ next_read_rq:
rqd->end_io = pblk_end_io_sync;
rqd->private = &wait;
+ if (pblk_io_aligned(pblk, rq_ppas))
+ rqd->flags = pblk_set_read_mode(pblk, PBLK_READ_SEQUENTIAL);
+ else
+ rqd->flags = pblk_set_read_mode(pblk, PBLK_READ_RANDOM);
+
for (i = 0; i < rqd->nr_ppas; ) {
struct ppa_addr ppa;
int pos;
@@ -295,7 +300,7 @@ next_read_rq:
pr_err("pblk: L2P recovery read timed out\n");
return -EINTR;
}
-
+ atomic_dec(&pblk->inflight_io);
reinit_completion(&wait);
/* At this point, the read should not fail. If it does, it is a problem
@@ -333,7 +338,7 @@ static int pblk_recov_pad_oob(struct pblk *pblk, struct pblk_line *line,
struct bio *bio;
void *data;
dma_addr_t dma_ppa_list, dma_meta_list;
- __le64 *lba_list = pblk_line_emeta_to_lbas(line->emeta);
+ __le64 *lba_list = emeta_to_lbas(pblk, line->emeta->buf);
u64 w_ptr = line->cur_sec;
int left_line_ppas = line->left_msecs;
int rq_ppas, rq_len;
@@ -361,7 +366,7 @@ next_pad_rq:
bio->bi_iter.bi_sector = 0; /* internal bio */
bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
- memset(rqd, 0, pblk_r_rq_size);
+ memset(rqd, 0, pblk_g_rq_size);
rqd->bio = bio;
rqd->opcode = NVM_OP_PWRITE;
@@ -390,12 +395,12 @@ next_pad_rq:
for (j = 0; j < pblk->min_write_pgs; j++, i++, w_ptr++) {
struct ppa_addr dev_ppa;
+ u64 addr_empty = cpu_to_le64(ADDR_EMPTY);
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);
+ lba_list[w_ptr] = meta_list[i].lba = addr_empty;
rqd->ppa_list[i] = dev_ppa;
}
}
@@ -410,6 +415,7 @@ next_pad_rq:
msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) {
pr_err("pblk: L2P recovery write timed out\n");
}
+ atomic_dec(&pblk->inflight_io);
reinit_completion(&wait);
left_line_ppas -= rq_ppas;
@@ -456,7 +462,7 @@ static int pblk_recov_scan_all_oob(struct pblk *pblk, struct pblk_line *line,
rec_round = 0;
next_rq:
- memset(rqd, 0, pblk_r_rq_size);
+ memset(rqd, 0, pblk_g_rq_size);
rq_ppas = pblk_calc_secs(pblk, left_ppas, 0);
if (!rq_ppas)
@@ -472,7 +478,6 @@ next_rq:
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;
@@ -481,6 +486,11 @@ next_rq:
rqd->end_io = pblk_end_io_sync;
rqd->private = &wait;
+ if (pblk_io_aligned(pblk, rq_ppas))
+ rqd->flags = pblk_set_read_mode(pblk, PBLK_READ_SEQUENTIAL);
+ else
+ rqd->flags = pblk_set_read_mode(pblk, PBLK_READ_RANDOM);
+
for (i = 0; i < rqd->nr_ppas; ) {
struct ppa_addr ppa;
int pos;
@@ -510,6 +520,7 @@ next_rq:
msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) {
pr_err("pblk: L2P recovery read timed out\n");
}
+ atomic_dec(&pblk->inflight_io);
reinit_completion(&wait);
/* This should not happen since the read failed during normal recovery,
@@ -552,7 +563,6 @@ next_rq:
if (ret)
pr_err("pblk: OOB read failed (err:%d)\n", ret);
- line->left_ssecs = line->left_msecs;
left_ppas = 0;
}
@@ -591,7 +601,7 @@ static int pblk_recov_scan_oob(struct pblk *pblk, struct pblk_line *line,
*done = 1;
next_rq:
- memset(rqd, 0, pblk_r_rq_size);
+ memset(rqd, 0, pblk_g_rq_size);
rq_ppas = pblk_calc_secs(pblk, left_ppas, 0);
if (!rq_ppas)
@@ -607,7 +617,6 @@ next_rq:
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;
@@ -616,6 +625,11 @@ next_rq:
rqd->end_io = pblk_end_io_sync;
rqd->private = &wait;
+ if (pblk_io_aligned(pblk, rq_ppas))
+ rqd->flags = pblk_set_read_mode(pblk, PBLK_READ_SEQUENTIAL);
+ else
+ rqd->flags = pblk_set_read_mode(pblk, PBLK_READ_RANDOM);
+
for (i = 0; i < rqd->nr_ppas; ) {
struct ppa_addr ppa;
int pos;
@@ -646,6 +660,7 @@ next_rq:
msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) {
pr_err("pblk: L2P recovery read timed out\n");
}
+ atomic_dec(&pblk->inflight_io);
reinit_completion(&wait);
/* Reached the end of the written line */
@@ -658,7 +673,6 @@ next_rq:
/* 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;
@@ -770,8 +784,9 @@ struct pblk_line *pblk_recov_l2p(struct pblk *pblk)
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;
+ struct pblk_smeta *smeta;
+ struct pblk_emeta *emeta;
+ struct line_smeta *smeta_buf;
int found_lines = 0, recovered_lines = 0, open_lines = 0;
int is_next = 0;
int meta_line;
@@ -784,8 +799,9 @@ struct pblk_line *pblk_recov_l2p(struct pblk *pblk)
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;
+ smeta = l_mg->sline_meta[meta_line];
+ emeta = l_mg->eline_meta[meta_line];
+ smeta_buf = smeta->buf;
spin_unlock(&l_mg->free_lock);
/* Order data lines using their sequence number */
@@ -796,33 +812,33 @@ struct pblk_line *pblk_recov_l2p(struct pblk *pblk)
memset(smeta, 0, lm->smeta_len);
line->smeta = smeta;
- line->lun_bitmap = ((void *)(smeta)) +
+ line->lun_bitmap = ((void *)(smeta_buf)) +
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)
+ crc = pblk_calc_smeta_crc(pblk, smeta_buf);
+ if (le32_to_cpu(smeta_buf->crc) != crc)
continue;
- if (le32_to_cpu(smeta->header.identifier) != PBLK_MAGIC)
+ if (le32_to_cpu(smeta_buf->header.identifier) != PBLK_MAGIC)
continue;
- if (le16_to_cpu(smeta->header.version) != 1) {
+ if (le16_to_cpu(smeta_buf->header.version) != 1) {
pr_err("pblk: found incompatible line version %u\n",
- smeta->header.version);
+ smeta_buf->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);
+ memcpy(pblk->instance_uuid, smeta_buf->header.uuid, 16);
valid_uuid = 1;
}
- if (memcmp(pblk->instance_uuid, smeta->header.uuid, 16)) {
+ if (memcmp(pblk->instance_uuid, smeta_buf->header.uuid, 16)) {
pr_debug("pblk: ignore line %u due to uuid mismatch\n",
i);
continue;
@@ -830,9 +846,9 @@ struct pblk_line *pblk_recov_l2p(struct pblk *pblk)
/* 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);
+ line->id = le32_to_cpu(smeta_buf->header.id);
+ line->type = le16_to_cpu(smeta_buf->header.type);
+ line->seq_nr = le64_to_cpu(smeta_buf->seq_nr);
spin_unlock(&line->lock);
/* Update general metadata */
@@ -848,7 +864,7 @@ struct pblk_line *pblk_recov_l2p(struct pblk *pblk)
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);
+ line->id, smeta_buf->seq_nr);
}
if (!found_lines) {
@@ -868,15 +884,15 @@ struct pblk_line *pblk_recov_l2p(struct pblk *pblk)
recovered_lines++;
/* Calculate where emeta starts based on the line bb */
- off = lm->sec_per_line - lm->emeta_sec;
+ off = lm->sec_per_line - lm->emeta_sec[0];
nr_bb = bitmap_weight(line->blk_bitmap, lm->blk_per_line);
off -= nr_bb * geo->sec_per_pl;
- memset(emeta, 0, lm->emeta_len);
+ memset(&emeta->buf, 0, lm->emeta_len[0]);
line->emeta = emeta;
line->emeta_ssec = off;
- if (pblk_line_read_emeta(pblk, line)) {
+ if (pblk_line_read_emeta(pblk, line, line->emeta->buf)) {
pblk_recov_l2p_from_oob(pblk, line);
goto next;
}
@@ -941,9 +957,9 @@ out:
}
/*
- * Pad until smeta can be read on current data line
+ * Pad current line
*/
-void pblk_recov_pad(struct pblk *pblk)
+int pblk_recov_pad(struct pblk *pblk)
{
struct nvm_tgt_dev *dev = pblk->dev;
struct nvm_geo *geo = &dev->geo;
@@ -954,26 +970,33 @@ void pblk_recov_pad(struct pblk *pblk)
struct ppa_addr *ppa_list;
struct pblk_sec_meta *meta_list;
void *data;
+ int left_msecs;
+ int ret = 0;
dma_addr_t dma_ppa_list, dma_meta_list;
spin_lock(&l_mg->free_lock);
line = l_mg->data_line;
+ left_msecs = line->left_msecs;
spin_unlock(&l_mg->free_lock);
rqd = pblk_alloc_rqd(pblk, READ);
if (IS_ERR(rqd))
- return;
+ return PTR_ERR(rqd);
meta_list = nvm_dev_dma_alloc(dev->parent, GFP_KERNEL, &dma_meta_list);
- if (!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)
+ if (!data) {
+ ret = -ENOMEM;
goto free_meta_list;
+ }
p.ppa_list = ppa_list;
p.meta_list = meta_list;
@@ -982,12 +1005,13 @@ void pblk_recov_pad(struct pblk *pblk)
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");
+ ret = pblk_recov_pad_oob(pblk, line, p, left_msecs);
+ if (ret) {
+ pr_err("pblk: Tear down padding failed (%d)\n", ret);
goto free_data;
}
- pblk_line_close(pblk, line);
+ pblk_line_close_meta(pblk, line);
free_data:
kfree(data);
@@ -995,4 +1019,6 @@ free_meta_list:
nvm_dev_dma_free(dev->parent, meta_list, dma_meta_list);
free_rqd:
pblk_free_rqd(pblk, rqd, READ);
+
+ return ret;
}
diff --git a/drivers/lightnvm/pblk-rl.c b/drivers/lightnvm/pblk-rl.c
index ab7cbb144f3f..2e6a5361baf0 100644
--- a/drivers/lightnvm/pblk-rl.c
+++ b/drivers/lightnvm/pblk-rl.c
@@ -23,11 +23,35 @@ static void pblk_rl_kick_u_timer(struct pblk_rl *rl)
mod_timer(&rl->u_timer, jiffies + msecs_to_jiffies(5000));
}
+int pblk_rl_is_limit(struct pblk_rl *rl)
+{
+ int rb_space;
+
+ rb_space = atomic_read(&rl->rb_space);
+
+ return (rb_space == 0);
+}
+
int pblk_rl_user_may_insert(struct pblk_rl *rl, int nr_entries)
{
int rb_user_cnt = atomic_read(&rl->rb_user_cnt);
+ int rb_space = atomic_read(&rl->rb_space);
- return (!(rb_user_cnt + nr_entries > rl->rb_user_max));
+ if (unlikely(rb_space >= 0) && (rb_space - nr_entries < 0))
+ return NVM_IO_ERR;
+
+ if (rb_user_cnt >= rl->rb_user_max)
+ return NVM_IO_REQUEUE;
+
+ return NVM_IO_OK;
+}
+
+void pblk_rl_inserted(struct pblk_rl *rl, int nr_entries)
+{
+ int rb_space = atomic_read(&rl->rb_space);
+
+ if (unlikely(rb_space >= 0))
+ atomic_sub(nr_entries, &rl->rb_space);
}
int pblk_rl_gc_may_insert(struct pblk_rl *rl, int nr_entries)
@@ -37,7 +61,7 @@ int pblk_rl_gc_may_insert(struct pblk_rl *rl, int nr_entries)
/* 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));
+ return (!(rb_gc_cnt >= rl->rb_gc_max && rb_user_active));
}
void pblk_rl_user_in(struct pblk_rl *rl, int nr_entries)
@@ -77,33 +101,32 @@ 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_user_max = max;
+ rl->rb_gc_max = 0;
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;
+ rl->rb_gc_max = max - user_max;
+
+ if (free_blocks <= rl->rsv_blocks) {
+ rl->rb_user_max = 0;
+ rl->rb_gc_max = max;
+ }
+
+ /* In the worst case, we will need to GC lines in the low list
+ * (high valid sector count). If there are lines to GC on high
+ * or mid lists, these will be prioritized
+ */
+ 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);
@@ -122,11 +145,15 @@ 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)
{
- 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);
+}
+
+void pblk_gc_should_kick(struct pblk *pblk)
+{
+ struct pblk_rl *rl = &pblk->rl;
+ int ret;
/* Rates will not change that often - no need to lock update */
ret = pblk_rl_update_rates(rl, rl->rb_budget);
@@ -136,11 +163,16 @@ void pblk_rl_free_lines_dec(struct pblk_rl *rl, struct pblk_line *line)
pblk_gc_should_stop(pblk);
}
-int pblk_rl_gc_thrs(struct pblk_rl *rl)
+int pblk_rl_high_thrs(struct pblk_rl *rl)
{
return rl->high;
}
+int pblk_rl_low_thrs(struct pblk_rl *rl)
+{
+ return rl->low;
+}
+
int pblk_rl_sysfs_rate_show(struct pblk_rl *rl)
{
return rl->rb_user_max;
@@ -161,24 +193,36 @@ void pblk_rl_free(struct pblk_rl *rl)
void pblk_rl_init(struct pblk_rl *rl, int budget)
{
+ struct pblk *pblk = container_of(rl, struct pblk, rl);
+ struct pblk_line_meta *lm = &pblk->lm;
+ int min_blocks = lm->blk_per_line * PBLK_GC_RSV_LINE;
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);
+ rl->low = rl->total_blocks / PBLK_USER_LOW_THRS;
+ if (rl->low < min_blocks)
+ rl->low = min_blocks;
+
+ rl->rsv_blocks = min_blocks;
+
/* 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;
+ rl->rb_windows_pw = get_count_order(rb_windows);
/* 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_user_cnt, 0);
atomic_set(&rl->rb_gc_cnt, 0);
+ atomic_set(&rl->rb_space, -1);
setup_timer(&rl->u_timer, pblk_rl_u_timer, (unsigned long)rl);
+
rl->rb_user_active = 0;
+ rl->rb_gc_active = 0;
}
diff --git a/drivers/lightnvm/pblk-sysfs.c b/drivers/lightnvm/pblk-sysfs.c
index f0af1d1ceeff..22e6f2ad4aee 100644
--- a/drivers/lightnvm/pblk-sysfs.c
+++ b/drivers/lightnvm/pblk-sysfs.c
@@ -49,30 +49,26 @@ static ssize_t pblk_sysfs_luns_show(struct pblk *pblk, char *page)
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;
+ int rb_gc_max, 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;
+ total_blocks = pblk->rl.total_blocks;
return snprintf(page, PAGE_SIZE,
- "u:%u/%u,gc:%u/%u/%u(%u/%u)(stop:<%u,full:>%u,free:%d/%d)-%d\n",
+ "u:%u/%u,gc:%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,
@@ -150,11 +146,11 @@ static ssize_t pblk_sysfs_lines(struct pblk *pblk, char *page)
ssize_t sz = 0;
int nr_free_lines;
int cur_data, cur_log;
- int free_line_cnt = 0, closed_line_cnt = 0;
+ int free_line_cnt = 0, closed_line_cnt = 0, emeta_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 bad = 0, cor = 0;
+ int msecs = 0, cur_sec = 0, vsc = 0, sec_in_line = 0;
int map_weight = 0, meta_weight = 0;
spin_lock(&l_mg->free_lock);
@@ -166,6 +162,11 @@ static ssize_t pblk_sysfs_lines(struct pblk *pblk, char *page)
free_line_cnt++;
spin_unlock(&l_mg->free_lock);
+ spin_lock(&l_mg->close_lock);
+ list_for_each_entry(line, &l_mg->emeta_list, list)
+ emeta_line_cnt++;
+ spin_unlock(&l_mg->close_lock);
+
spin_lock(&l_mg->gc_lock);
list_for_each_entry(line, &l_mg->gc_full_list, list) {
if (line->type == PBLK_LINETYPE_DATA)
@@ -212,8 +213,6 @@ static ssize_t pblk_sysfs_lines(struct pblk *pblk, char *page)
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)
@@ -224,8 +223,7 @@ static ssize_t pblk_sysfs_lines(struct pblk *pblk, char *page)
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;
+ vsc = le32_to_cpu(*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);
@@ -235,17 +233,20 @@ static ssize_t pblk_sysfs_lines(struct pblk *pblk, char *page)
spin_unlock(&l_mg->free_lock);
if (nr_free_lines != free_line_cnt)
- pr_err("pblk: corrupted free line list\n");
+ pr_err("pblk: corrupted free line list:%d/%d\n",
+ nr_free_lines, free_line_cnt);
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",
+ "lines:d:%d,l:%d-f:%d,m:%d/%d,c:%d,b:%d,co:%d(d:%d,l:%d)t:%d\n",
cur_data, cur_log,
- free, nr_free_lines, bad, cor,
+ nr_free_lines,
+ emeta_line_cnt, meta_weight,
closed_line_cnt,
+ bad, cor,
d_line_cnt, l_line_cnt,
l_mg->nr_lines);
@@ -255,9 +256,10 @@ static ssize_t pblk_sysfs_lines(struct pblk *pblk, char *page)
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);
+ "data (%d) cur:%d, left:%d, vsc:%d, s:%d, map:%d/%d (%d)\n",
+ cur_data, cur_sec, msecs, vsc, sec_in_line,
+ map_weight, lm->sec_per_line,
+ atomic_read(&pblk->inflight_io));
return sz;
}
@@ -274,7 +276,7 @@ static ssize_t pblk_sysfs_lines_info(struct pblk *pblk, char *page)
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_len[0], lm->emeta_sec[0],
lm->emeta_bb);
sz += snprintf(page + sz, PAGE_SIZE - sz,
"bitmap lengths: sec:%d, blk:%d, lun:%d\n",
@@ -290,6 +292,11 @@ static ssize_t pblk_sysfs_lines_info(struct pblk *pblk, char *page)
return sz;
}
+static ssize_t pblk_sysfs_get_sec_per_write(struct pblk *pblk, char *page)
+{
+ return snprintf(page, PAGE_SIZE, "%d\n", pblk->sec_per_write);
+}
+
#ifdef CONFIG_NVM_DEBUG
static ssize_t pblk_sysfs_stats_debug(struct pblk *pblk, char *page)
{
@@ -303,52 +310,51 @@ static ssize_t pblk_sysfs_stats_debug(struct pblk *pblk, char *page)
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->cache_reads),
atomic_long_read(&pblk->sync_reads));
}
#endif
-static ssize_t pblk_sysfs_rate_store(struct pblk *pblk, const char *page,
- size_t len)
+static ssize_t pblk_sysfs_gc_force(struct pblk *pblk, const char *page,
+ size_t len)
{
- struct pblk_gc *gc = &pblk->gc;
size_t c_len;
- int value;
+ int ret, force;
c_len = strcspn(page, "\n");
if (c_len >= len)
return -EINVAL;
- if (kstrtouint(page, 0, &value))
+ if (kstrtouint(page, 0, &force))
return -EINVAL;
- spin_lock(&gc->lock);
- pblk_rl_set_gc_rsc(&pblk->rl, value);
- spin_unlock(&gc->lock);
+ ret = pblk_gc_sysfs_force(pblk, force);
return len;
}
-static ssize_t pblk_sysfs_gc_force(struct pblk *pblk, const char *page,
- size_t len)
+static ssize_t pblk_sysfs_set_sec_per_write(struct pblk *pblk,
+ const char *page, size_t len)
{
size_t c_len;
- int force;
+ int sec_per_write;
c_len = strcspn(page, "\n");
if (c_len >= len)
return -EINVAL;
- if (kstrtouint(page, 0, &force))
+ if (kstrtouint(page, 0, &sec_per_write))
return -EINVAL;
- if (force < 0 || force > 1)
+ if (sec_per_write < pblk->min_write_pgs
+ || sec_per_write > pblk->max_write_pgs
+ || sec_per_write % pblk->min_write_pgs != 0)
return -EINVAL;
- pblk_gc_sysfs_force(pblk, force);
+ pblk_set_sec_per_write(pblk, sec_per_write);
return len;
}
@@ -398,9 +404,9 @@ static struct attribute sys_gc_force = {
.mode = 0200,
};
-static struct attribute sys_gc_rl_max = {
- .name = "gc_rl_max",
- .mode = 0200,
+static struct attribute sys_max_sec_per_write = {
+ .name = "max_sec_per_write",
+ .mode = 0644,
};
#ifdef CONFIG_NVM_DEBUG
@@ -416,7 +422,7 @@ static struct attribute *pblk_attrs[] = {
&sys_errors_attr,
&sys_gc_state,
&sys_gc_force,
- &sys_gc_rl_max,
+ &sys_max_sec_per_write,
&sys_rb_attr,
&sys_stats_ppaf_attr,
&sys_lines_attr,
@@ -448,6 +454,8 @@ static ssize_t pblk_sysfs_show(struct kobject *kobj, struct attribute *attr,
return pblk_sysfs_lines(pblk, buf);
else if (strcmp(attr->name, "lines_info") == 0)
return pblk_sysfs_lines_info(pblk, buf);
+ else if (strcmp(attr->name, "max_sec_per_write") == 0)
+ return pblk_sysfs_get_sec_per_write(pblk, buf);
#ifdef CONFIG_NVM_DEBUG
else if (strcmp(attr->name, "stats") == 0)
return pblk_sysfs_stats_debug(pblk, buf);
@@ -460,10 +468,10 @@ static ssize_t pblk_sysfs_store(struct kobject *kobj, struct attribute *attr,
{
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)
+ if (strcmp(attr->name, "gc_force") == 0)
return pblk_sysfs_gc_force(pblk, buf, len);
+ else if (strcmp(attr->name, "max_sec_per_write") == 0)
+ return pblk_sysfs_set_sec_per_write(pblk, buf, len);
return 0;
}
diff --git a/drivers/lightnvm/pblk-write.c b/drivers/lightnvm/pblk-write.c
index aef6fd7c4a0c..3e0b84937b90 100644
--- a/drivers/lightnvm/pblk-write.c
+++ b/drivers/lightnvm/pblk-write.c
@@ -17,18 +17,6 @@
#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)
{
@@ -39,21 +27,14 @@ static unsigned long pblk_end_w_bio(struct pblk *pblk, struct nvm_rq *rqd,
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);
+ atomic_long_add(c_ctx->nr_valid, &pblk->sync_writes);
#endif
ret = pblk_rb_sync_advance(&pblk->rwb, c_ctx->nr_valid);
@@ -169,7 +150,7 @@ static void pblk_end_w_fail(struct pblk *pblk, struct nvm_rq *rqd)
}
INIT_WORK(&recovery->ws_rec, pblk_submit_rec);
- queue_work(pblk->kw_wq, &recovery->ws_rec);
+ queue_work(pblk->close_wq, &recovery->ws_rec);
out:
pblk_complete_write(pblk, rqd, c_ctx);
@@ -186,14 +167,50 @@ static void pblk_end_io_write(struct nvm_rq *rqd)
}
#ifdef CONFIG_NVM_DEBUG
else
- WARN_ONCE(rqd->bio->bi_error, "pblk: corrupted write error\n");
+ WARN_ONCE(rqd->bio->bi_status, "pblk: corrupted write error\n");
#endif
pblk_complete_write(pblk, rqd, c_ctx);
+ atomic_dec(&pblk->inflight_io);
+}
+
+static void pblk_end_io_write_meta(struct nvm_rq *rqd)
+{
+ struct pblk *pblk = rqd->private;
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ struct pblk_g_ctx *m_ctx = nvm_rq_to_pdu(rqd);
+ struct pblk_line *line = m_ctx->private;
+ struct pblk_emeta *emeta = line->emeta;
+ int pos = pblk_ppa_to_pos(geo, rqd->ppa_list[0]);
+ struct pblk_lun *rlun = &pblk->luns[pos];
+ int sync;
+
+ up(&rlun->wr_sem);
+
+ if (rqd->error) {
+ pblk_log_write_err(pblk, rqd);
+ pr_err("pblk: metadata I/O failed\n");
+ }
+#ifdef CONFIG_NVM_DEBUG
+ else
+ WARN_ONCE(rqd->bio->bi_status, "pblk: corrupted write error\n");
+#endif
+
+ sync = atomic_add_return(rqd->nr_ppas, &emeta->sync);
+ if (sync == emeta->nr_entries)
+ pblk_line_run_ws(pblk, line, NULL, pblk_line_close_ws,
+ pblk->close_wq);
+
+ bio_put(rqd->bio);
+ pblk_free_rqd(pblk, rqd, READ);
+
+ atomic_dec(&pblk->inflight_io);
}
static int pblk_alloc_w_rq(struct pblk *pblk, struct nvm_rq *rqd,
- unsigned int nr_secs)
+ unsigned int nr_secs,
+ nvm_end_io_fn(*end_io))
{
struct nvm_tgt_dev *dev = pblk->dev;
@@ -202,7 +219,7 @@ static int pblk_alloc_w_rq(struct pblk *pblk, struct nvm_rq *rqd,
rqd->nr_ppas = nr_secs;
rqd->flags = pblk_set_progr_mode(pblk, WRITE);
rqd->private = pblk;
- rqd->end_io = pblk_end_io_write;
+ rqd->end_io = end_io;
rqd->meta_list = nvm_dev_dma_alloc(dev->parent, GFP_KERNEL,
&rqd->dma_meta_list);
@@ -219,11 +236,10 @@ static int pblk_alloc_w_rq(struct pblk *pblk, struct nvm_rq *rqd,
}
static int pblk_setup_w_rq(struct pblk *pblk, struct nvm_rq *rqd,
- struct pblk_c_ctx *c_ctx)
+ struct pblk_c_ctx *c_ctx, struct ppa_addr *erase_ppa)
{
struct pblk_line_meta *lm = &pblk->lm;
- struct pblk_line *e_line = pblk_line_get_data_next(pblk);
- struct ppa_addr erase_ppa;
+ struct pblk_line *e_line = pblk_line_get_erase(pblk);
unsigned int valid = c_ctx->nr_valid;
unsigned int padded = c_ctx->nr_padded;
unsigned int nr_secs = valid + padded;
@@ -231,40 +247,23 @@ static int pblk_setup_w_rq(struct pblk *pblk, struct nvm_rq *rqd,
int ret = 0;
lun_bitmap = kzalloc(lm->lun_bitmap_len, GFP_KERNEL);
- if (!lun_bitmap) {
- ret = -ENOMEM;
- goto out;
- }
+ if (!lun_bitmap)
+ return -ENOMEM;
c_ctx->lun_bitmap = lun_bitmap;
- ret = pblk_alloc_w_rq(pblk, rqd, nr_secs);
+ ret = pblk_alloc_w_rq(pblk, rqd, nr_secs, pblk_end_io_write);
if (ret) {
kfree(lun_bitmap);
- goto out;
+ return ret;
}
- 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);
- }
- }
+ valid, erase_ppa);
- return ret;
+ return 0;
}
int pblk_setup_w_rec_rq(struct pblk *pblk, struct nvm_rq *rqd,
@@ -280,7 +279,7 @@ int pblk_setup_w_rec_rq(struct pblk *pblk, struct nvm_rq *rqd,
c_ctx->lun_bitmap = lun_bitmap;
- ret = pblk_alloc_w_rq(pblk, rqd, rqd->nr_ppas);
+ ret = pblk_alloc_w_rq(pblk, rqd, rqd->nr_ppas, pblk_end_io_write);
if (ret)
return ret;
@@ -311,16 +310,236 @@ static int pblk_calc_secs_to_sync(struct pblk *pblk, unsigned int secs_avail,
return secs_to_sync;
}
+static inline int pblk_valid_meta_ppa(struct pblk *pblk,
+ struct pblk_line *meta_line,
+ struct ppa_addr *ppa_list, int nr_ppas)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ struct pblk_line *data_line;
+ struct ppa_addr ppa, ppa_opt;
+ u64 paddr;
+ int i;
+
+ data_line = &pblk->lines[pblk_dev_ppa_to_line(ppa_list[0])];
+ paddr = pblk_lookup_page(pblk, meta_line);
+ ppa = addr_to_gen_ppa(pblk, paddr, 0);
+
+ if (test_bit(pblk_ppa_to_pos(geo, ppa), data_line->blk_bitmap))
+ return 1;
+
+ /* Schedule a metadata I/O that is half the distance from the data I/O
+ * with regards to the number of LUNs forming the pblk instance. This
+ * balances LUN conflicts across every I/O.
+ *
+ * When the LUN configuration changes (e.g., due to GC), this distance
+ * can align, which would result on a LUN deadlock. In this case, modify
+ * the distance to not be optimal, but allow metadata I/Os to succeed.
+ */
+ ppa_opt = addr_to_gen_ppa(pblk, paddr + data_line->meta_distance, 0);
+ if (unlikely(ppa_opt.ppa == ppa.ppa)) {
+ data_line->meta_distance--;
+ return 0;
+ }
+
+ for (i = 0; i < nr_ppas; i += pblk->min_write_pgs)
+ if (ppa_list[i].g.ch == ppa_opt.g.ch &&
+ ppa_list[i].g.lun == ppa_opt.g.lun)
+ return 1;
+
+ if (test_bit(pblk_ppa_to_pos(geo, ppa_opt), data_line->blk_bitmap)) {
+ for (i = 0; i < nr_ppas; i += pblk->min_write_pgs)
+ if (ppa_list[i].g.ch == ppa.g.ch &&
+ ppa_list[i].g.lun == ppa.g.lun)
+ return 0;
+
+ return 1;
+ }
+
+ return 0;
+}
+
+int pblk_submit_meta_io(struct pblk *pblk, struct pblk_line *meta_line)
+{
+ 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_emeta *emeta = meta_line->emeta;
+ struct pblk_g_ctx *m_ctx;
+ struct pblk_lun *rlun;
+ struct bio *bio;
+ struct nvm_rq *rqd;
+ void *data;
+ u64 paddr;
+ int rq_ppas = pblk->min_write_pgs;
+ int id = meta_line->id;
+ int rq_len;
+ int i, j;
+ int ret;
+
+ rqd = pblk_alloc_rqd(pblk, READ);
+ if (IS_ERR(rqd)) {
+ pr_err("pblk: cannot allocate write req.\n");
+ return PTR_ERR(rqd);
+ }
+ m_ctx = nvm_rq_to_pdu(rqd);
+ m_ctx->private = meta_line;
+
+ rq_len = rq_ppas * geo->sec_size;
+ data = ((void *)emeta->buf) + emeta->mem;
+
+ bio = pblk_bio_map_addr(pblk, data, rq_ppas, rq_len, GFP_KERNEL);
+ if (IS_ERR(bio)) {
+ ret = PTR_ERR(bio);
+ goto fail_free_rqd;
+ }
+ bio->bi_iter.bi_sector = 0; /* internal bio */
+ bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
+ rqd->bio = bio;
+
+ ret = pblk_alloc_w_rq(pblk, rqd, rq_ppas, pblk_end_io_write_meta);
+ if (ret)
+ goto fail_free_bio;
+
+ for (i = 0; i < rqd->nr_ppas; ) {
+ spin_lock(&meta_line->lock);
+ paddr = __pblk_alloc_page(pblk, meta_line, rq_ppas);
+ spin_unlock(&meta_line->lock);
+ for (j = 0; j < rq_ppas; j++, i++, paddr++)
+ rqd->ppa_list[i] = addr_to_gen_ppa(pblk, paddr, id);
+ }
+
+ rlun = &pblk->luns[pblk_ppa_to_pos(geo, rqd->ppa_list[0])];
+ ret = down_timeout(&rlun->wr_sem, msecs_to_jiffies(5000));
+ if (ret) {
+ pr_err("pblk: lun semaphore timed out (%d)\n", ret);
+ goto fail_free_bio;
+ }
+
+ emeta->mem += rq_len;
+ if (emeta->mem >= lm->emeta_len[0]) {
+ spin_lock(&l_mg->close_lock);
+ list_del(&meta_line->list);
+ WARN(!bitmap_full(meta_line->map_bitmap, lm->sec_per_line),
+ "pblk: corrupt meta line %d\n", meta_line->id);
+ spin_unlock(&l_mg->close_lock);
+ }
+
+ ret = pblk_submit_io(pblk, rqd);
+ if (ret) {
+ pr_err("pblk: emeta I/O submission failed: %d\n", ret);
+ goto fail_rollback;
+ }
+
+ return NVM_IO_OK;
+
+fail_rollback:
+ spin_lock(&l_mg->close_lock);
+ pblk_dealloc_page(pblk, meta_line, rq_ppas);
+ list_add(&meta_line->list, &meta_line->list);
+ spin_unlock(&l_mg->close_lock);
+fail_free_bio:
+ if (likely(l_mg->emeta_alloc_type == PBLK_VMALLOC_META))
+ bio_put(bio);
+fail_free_rqd:
+ pblk_free_rqd(pblk, rqd, READ);
+ return ret;
+}
+
+static int pblk_sched_meta_io(struct pblk *pblk, struct ppa_addr *prev_list,
+ int prev_n)
+{
+ struct pblk_line_meta *lm = &pblk->lm;
+ struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+ struct pblk_line *meta_line;
+
+ spin_lock(&l_mg->close_lock);
+retry:
+ if (list_empty(&l_mg->emeta_list)) {
+ spin_unlock(&l_mg->close_lock);
+ return 0;
+ }
+ meta_line = list_first_entry(&l_mg->emeta_list, struct pblk_line, list);
+ if (bitmap_full(meta_line->map_bitmap, lm->sec_per_line))
+ goto retry;
+ spin_unlock(&l_mg->close_lock);
+
+ if (!pblk_valid_meta_ppa(pblk, meta_line, prev_list, prev_n))
+ return 0;
+
+ return pblk_submit_meta_io(pblk, meta_line);
+}
+
+static int pblk_submit_io_set(struct pblk *pblk, struct nvm_rq *rqd)
+{
+ struct pblk_c_ctx *c_ctx = nvm_rq_to_pdu(rqd);
+ struct ppa_addr erase_ppa;
+ int err;
+
+ ppa_set_empty(&erase_ppa);
+
+ /* Assign lbas to ppas and populate request structure */
+ err = pblk_setup_w_rq(pblk, rqd, c_ctx, &erase_ppa);
+ if (err) {
+ pr_err("pblk: could not setup write request: %d\n", err);
+ return NVM_IO_ERR;
+ }
+
+ if (likely(ppa_empty(erase_ppa))) {
+ /* Submit metadata write for previous data line */
+ err = pblk_sched_meta_io(pblk, rqd->ppa_list, rqd->nr_ppas);
+ if (err) {
+ pr_err("pblk: metadata I/O submission failed: %d", err);
+ return NVM_IO_ERR;
+ }
+
+ /* Submit data write for current data line */
+ err = pblk_submit_io(pblk, rqd);
+ if (err) {
+ pr_err("pblk: data I/O submission failed: %d\n", err);
+ return NVM_IO_ERR;
+ }
+ } else {
+ /* Submit data write for current data line */
+ err = pblk_submit_io(pblk, rqd);
+ if (err) {
+ pr_err("pblk: data I/O submission failed: %d\n", err);
+ return NVM_IO_ERR;
+ }
+
+ /* Submit available erase for next data line */
+ if (pblk_blk_erase_async(pblk, erase_ppa)) {
+ struct pblk_line *e_line = pblk_line_get_erase(pblk);
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ int bit;
+
+ atomic_inc(&e_line->left_eblks);
+ bit = pblk_ppa_to_pos(geo, erase_ppa);
+ WARN_ON(!test_and_clear_bit(bit, e_line->erase_bitmap));
+ }
+ }
+
+ return NVM_IO_OK;
+}
+
+static void pblk_free_write_rqd(struct pblk *pblk, struct nvm_rq *rqd)
+{
+ struct pblk_c_ctx *c_ctx = nvm_rq_to_pdu(rqd);
+ struct bio *bio = rqd->bio;
+
+ if (c_ctx->nr_padded)
+ pblk_bio_free_pages(pblk, bio, rqd->nr_ppas, c_ctx->nr_padded);
+}
+
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
@@ -338,7 +557,6 @@ static int pblk_submit_write(struct pblk *pblk)
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) {
@@ -358,29 +576,14 @@ static int pblk_submit_write(struct pblk *pblk)
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) {
+ if (pblk_rb_read_to_bio(&pblk->rwb, rqd, bio, pos, secs_to_sync,
+ secs_avail)) {
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);
+ if (pblk_submit_io_set(pblk, rqd))
goto fail_free_bio;
- }
#ifdef CONFIG_NVM_DEBUG
atomic_long_add(secs_to_sync, &pblk->sub_writes);
@@ -389,8 +592,7 @@ static int pblk_submit_write(struct pblk *pblk)
return 0;
fail_free_bio:
- if (c_ctx->nr_padded)
- pblk_bio_free_pages(pblk, bio, secs_to_sync, c_ctx->nr_padded);
+ pblk_free_write_rqd(pblk, rqd);
fail_put_bio:
bio_put(bio);
fail_free_rqd:
diff --git a/drivers/lightnvm/pblk.h b/drivers/lightnvm/pblk.h
index 99f3186b5288..36c5f5999324 100644
--- a/drivers/lightnvm/pblk.h
+++ b/drivers/lightnvm/pblk.h
@@ -40,6 +40,12 @@
#define PBLK_MAX_REQ_ADDRS (64)
#define PBLK_MAX_REQ_ADDRS_PW (6)
+#define PBLK_WS_POOL_SIZE (128)
+#define PBLK_META_POOL_SIZE (128)
+#define PBLK_READ_REQ_POOL_SIZE (1024)
+
+#define PBLK_NR_CLOSE_JOBS (4)
+
#define PBLK_CACHE_NAME_LEN (DISK_NAME_LEN + 16)
#define PBLK_COMMAND_TIMEOUT_MS 30000
@@ -72,11 +78,15 @@ enum {
PBLK_BLK_ST_CLOSED = 0x2,
};
+struct pblk_sec_meta {
+ u64 reserved;
+ __le64 lba;
+};
+
/* 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
+#define PBLK_GC_NR_LISTS 3
enum {
PBLK_RL_HIGH = 1,
@@ -84,14 +94,9 @@ enum {
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 */
+/* write buffer completion context */
struct pblk_c_ctx {
struct list_head list; /* Head for out-of-order completion */
@@ -101,9 +106,9 @@ struct pblk_c_ctx {
unsigned int nr_padded;
};
-/* Read context */
-struct pblk_r_ctx {
- struct bio *orig_bio;
+/* generic context */
+struct pblk_g_ctx {
+ void *private;
};
/* Recovery context */
@@ -195,29 +200,39 @@ struct pblk_lun {
struct pblk_gc_rq {
struct pblk_line *line;
void *data;
- u64 *lba_list;
+ u64 lba_list[PBLK_MAX_REQ_ADDRS];
int nr_secs;
int secs_to_gc;
struct list_head list;
};
struct pblk_gc {
+ /* These states are not protected by a lock since (i) they are in the
+ * fast path, and (ii) they are not critical.
+ */
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 task_struct *gc_reader_ts;
+
+ struct workqueue_struct *gc_line_reader_wq;
struct workqueue_struct *gc_reader_wq;
+
struct timer_list gc_timer;
+ struct semaphore gc_sem;
+ atomic_t inflight_gc;
int w_entries;
+
struct list_head w_list;
+ struct list_head r_list;
spinlock_t lock;
spinlock_t w_lock;
+ spinlock_t r_lock;
};
struct pblk_rl {
@@ -229,10 +244,8 @@ struct pblk_rl {
*/
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 */
+#define PBLK_USER_HIGH_THRS 8 /* Begin write limit at 12% available blks */
+#define PBLK_USER_LOW_THRS 10 /* Aggressive GC at 10% available blocks */
int rb_windows_pw; /* Number of rate windows in the write buffer
* given as a power-of-2. This guarantees that
@@ -244,13 +257,19 @@ struct pblk_rl {
*/
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_user_cnt; /* User I/O buffer counter */
atomic_t rb_gc_cnt; /* GC I/O buffer counter */
+ atomic_t rb_space; /* Space limit in case of reaching capacity */
+
+ int rsv_blocks; /* Reserved blocks for GC */
int rb_user_active;
+ int rb_gc_active;
+
struct timer_list u_timer;
unsigned long long nr_secs;
@@ -258,8 +277,6 @@ struct pblk_rl {
atomic_t free_blocks;
};
-#define PBLK_LINE_NR_LUN_BITMAP 2
-#define PBLK_LINE_NR_SEC_BITMAP 2
#define PBLK_LINE_EMPTY (~0U)
enum {
@@ -310,16 +327,19 @@ struct line_smeta {
__le32 window_wr_lun; /* Number of parallel LUNs to write */
__le32 rsvd[2];
+
+ __le64 lun_bitmap[];
};
/*
- * 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
+ * Metadata layout in media:
+ * First sector:
+ * 1. struct line_emeta
+ * 2. bad block bitmap (u64 * window_wr_lun)
+ * Mid sectors (start at lbas_sector):
+ * 3. nr_lbas (u64) forming lba list
+ * Last sectors (start at vsc_sector):
+ * 4. u32 valid sector count (vsc) for all lines (~0U: free line)
*/
struct line_emeta {
struct line_header header;
@@ -339,6 +359,23 @@ struct line_emeta {
__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 */
+ __le64 bb_bitmap[]; /* Updated bad block bitmap for line */
+};
+
+struct pblk_emeta {
+ struct line_emeta *buf; /* emeta buffer in media format */
+ int mem; /* Write offset - points to next
+ * writable entry in memory
+ */
+ atomic_t sync; /* Synced - backpointer that signals the
+ * last entry that has been successfully
+ * persisted to media
+ */
+ unsigned int nr_entries; /* Number of emeta entries */
+};
+
+struct pblk_smeta {
+ struct line_smeta *buf; /* smeta buffer in persistent format */
};
struct pblk_line {
@@ -355,9 +392,12 @@ struct pblk_line {
unsigned long *lun_bitmap; /* Bitmap for LUNs mapped in line */
- struct line_smeta *smeta; /* Start metadata */
- struct line_emeta *emeta; /* End metadata */
+ struct pblk_smeta *smeta; /* Start metadata */
+ struct pblk_emeta *emeta; /* End medatada */
+
int meta_line; /* Metadata line id */
+ int meta_distance; /* Distance between data and metadata */
+
u64 smeta_ssec; /* Sector where smeta starts */
u64 emeta_ssec; /* Sector where emeta starts */
@@ -374,9 +414,10 @@ struct pblk_line {
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 */
+ unsigned int nr_valid_lbas; /* Number of valid lbas in line */
+
+ __le32 *vsc; /* Valid sector count in line */
struct kref ref; /* Write buffer L2P references */
@@ -385,13 +426,15 @@ struct pblk_line {
#define PBLK_DATA_LINES 4
-enum{
+enum {
PBLK_KMALLOC_META = 1,
PBLK_VMALLOC_META = 2,
};
-struct pblk_line_metadata {
- void *meta;
+enum {
+ PBLK_EMETA_TYPE_HEADER = 1, /* struct line_emeta first sector */
+ PBLK_EMETA_TYPE_LLBA = 2, /* lba list - type: __le64 */
+ PBLK_EMETA_TYPE_VSC = 3, /* vsc list - type: __le32 */
};
struct pblk_line_mgmt {
@@ -404,7 +447,7 @@ struct pblk_line_mgmt {
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_lists[PBLK_GC_NR_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 */
@@ -417,13 +460,16 @@ struct pblk_line_mgmt {
struct pblk_line *log_next; /* Next FTL log line */
struct pblk_line *data_next; /* Next data line */
+ struct list_head emeta_list; /* Lines queued to schedule emeta */
+
+ __le32 *vsc_list; /* Valid sector counts for all lines */
+
/* 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];
+ struct pblk_smeta *sline_meta[PBLK_DATA_LINES];
+ struct pblk_emeta *eline_meta[PBLK_DATA_LINES];
unsigned long meta_bitmap;
/* Helpers for fast bitmap calculations */
@@ -434,25 +480,40 @@ struct pblk_line_mgmt {
unsigned long l_seq_nr; /* Log line unique sequence number */
spinlock_t free_lock;
+ spinlock_t close_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 smeta_sec; /* Sectors needed for smeta */
+
+ unsigned int emeta_len[4]; /* Lengths for emeta:
+ * [0]: Total length
+ * [1]: struct line_emeta length
+ * [2]: L2P portion length
+ * [3]: vsc list length
+ */
+ unsigned int emeta_sec[4]; /* Sectors needed for emeta. Same layout
+ * as emeta_len
+ */
+
unsigned int emeta_bb; /* Boundary for bb that affects emeta */
+
+ unsigned int vsc_list_len; /* Length for vsc list */
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 dsec_per_line; /* Number of data 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 */
+
+ unsigned int meta_distance; /* Distance between data and metadata */
};
struct pblk_addr_format {
@@ -470,6 +531,13 @@ struct pblk_addr_format {
u8 sec_offset;
};
+enum {
+ PBLK_STATE_RUNNING = 0,
+ PBLK_STATE_STOPPING = 1,
+ PBLK_STATE_RECOVERING = 2,
+ PBLK_STATE_STOPPED = 3,
+};
+
struct pblk {
struct nvm_tgt_dev *dev;
struct gendisk *disk;
@@ -487,6 +555,8 @@ struct pblk {
struct pblk_rb rwb;
+ int state; /* pblk line state */
+
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
@@ -499,7 +569,7 @@ struct pblk {
/* pblk provisioning values. Used by rate limiter */
struct pblk_rl rl;
- struct semaphore erase_sem;
+ int sec_per_write;
unsigned char instance_uuid[16];
#ifdef CONFIG_NVM_DEBUG
@@ -511,8 +581,8 @@ struct pblk {
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 cache_reads; /* Read requests that hit the cache */
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 */
@@ -528,6 +598,8 @@ struct pblk {
atomic_long_t write_failed;
atomic_long_t erase_failed;
+ atomic_t inflight_io; /* General inflight I/O counter */
+
struct task_struct *writer_ts;
/* Simple translation map of logical addresses to physical addresses.
@@ -542,11 +614,13 @@ struct pblk {
mempool_t *page_pool;
mempool_t *line_ws_pool;
mempool_t *rec_pool;
- mempool_t *r_rq_pool;
+ mempool_t *g_rq_pool;
mempool_t *w_rq_pool;
mempool_t *line_meta_pool;
- struct workqueue_struct *kw_wq;
+ struct workqueue_struct *close_wq;
+ struct workqueue_struct *bb_wq;
+
struct timer_list wtimer;
struct pblk_gc gc;
@@ -559,7 +633,7 @@ struct pblk_line_ws {
struct work_struct ws;
};
-#define pblk_r_rq_size (sizeof(struct nvm_rq) + sizeof(struct pblk_r_ctx))
+#define pblk_g_rq_size (sizeof(struct nvm_rq) + sizeof(struct pblk_g_ctx))
#define pblk_w_rq_size (sizeof(struct nvm_rq) + sizeof(struct pblk_c_ctx))
/*
@@ -579,13 +653,12 @@ 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_flush(struct pblk_rb *rb);
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(struct pblk_rb *rb, struct nvm_rq *rqd,
+ struct bio *bio, 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);
@@ -612,40 +685,50 @@ ssize_t pblk_rb_sysfs(struct pblk_rb *rb, char *buf);
* pblk core
*/
struct nvm_rq *pblk_alloc_rqd(struct pblk *pblk, int rw);
+void pblk_set_sec_per_write(struct pblk *pblk, int sec_per_write);
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);
+void pblk_wait_for_meta(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);
+int pblk_submit_meta_io(struct pblk *pblk, struct pblk_line *meta_line);
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);
+void 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);
+struct pblk_line *pblk_line_get_erase(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_meta(struct pblk *pblk, struct pblk_line *line);
void pblk_line_close(struct pblk *pblk, struct pblk_line *line);
+void pblk_line_close_meta_sync(struct pblk *pblk);
+void pblk_line_close_ws(struct work_struct *work);
+void pblk_pipeline_stop(struct pblk *pblk);
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 *));
+ void (*work)(struct work_struct *),
+ struct workqueue_struct *wq);
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_line_read_emeta(struct pblk *pblk, struct pblk_line *line,
+ void *emeta_buf);
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_lookup_page(struct pblk *pblk, struct pblk_line *line);
+void pblk_dealloc_page(struct pblk *pblk, struct pblk_line *line, int nr_secs);
u64 pblk_alloc_page(struct pblk *pblk, struct pblk_line *line, int nr_secs);
+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,
@@ -656,11 +739,11 @@ 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_map_invalidate(struct pblk *pblk, struct pblk_line *line,
+ u64 paddr);
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);
@@ -702,6 +785,7 @@ void pblk_write_should_kick(struct pblk *pblk);
/*
* pblk read path
*/
+extern struct bio_set *pblk_bio_set;
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,
@@ -711,7 +795,7 @@ int pblk_submit_read_gc(struct pblk *pblk, u64 *lba_list, void *data,
*/
void pblk_submit_rec(struct work_struct *work);
struct pblk_line *pblk_recov_l2p(struct pblk *pblk);
-void pblk_recov_pad(struct pblk *pblk);
+int 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,
@@ -720,33 +804,40 @@ int pblk_recov_setup_rq(struct pblk *pblk, struct pblk_c_ctx *c_ctx,
/*
* pblk gc
*/
-#define PBLK_GC_TRIES 3
+#define PBLK_GC_MAX_READERS 8 /* Max number of outstanding GC reader jobs */
+#define PBLK_GC_W_QD 1024 /* Queue depth for inflight GC write I/Os */
+#define PBLK_GC_L_QD 4 /* Queue depth for inflight GC lines */
+#define PBLK_GC_RSV_LINE 1 /* Reserved lines for GC */
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_should_kick(struct pblk *pblk);
+void pblk_gc_kick(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);
+int 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);
+int pblk_rl_high_thrs(struct pblk_rl *rl);
+int pblk_rl_low_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_inserted(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);
+void pblk_rl_set_space_limit(struct pblk_rl *rl, int entries_left);
+int pblk_rl_is_limit(struct pblk_rl *rl);
/*
* pblk sysfs
@@ -774,9 +865,30 @@ 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)
+static inline void *emeta_to_bb(struct line_emeta *emeta)
+{
+ return emeta->bb_bitmap;
+}
+
+static inline void *emeta_to_lbas(struct pblk *pblk, struct line_emeta *emeta)
+{
+ return ((void *)emeta + pblk->lm.emeta_len[1]);
+}
+
+static inline void *emeta_to_vsc(struct pblk *pblk, struct line_emeta *emeta)
+{
+ return (emeta_to_lbas(pblk, emeta) + pblk->lm.emeta_len[2]);
+}
+
+static inline int pblk_line_vsc(struct pblk_line *line)
{
- return (emeta) + 1;
+ int vsc;
+
+ spin_lock(&line->lock);
+ vsc = le32_to_cpu(*line->vsc);
+ spin_unlock(&line->lock);
+
+ return vsc;
}
#define NVM_MEM_PAGE_WRITE (8)
@@ -964,11 +1076,11 @@ static inline struct ppa_addr addr_to_pblk_ppa(struct pblk *pblk, u64 paddr,
}
static inline u32 pblk_calc_meta_header_crc(struct pblk *pblk,
- struct line_smeta *smeta)
+ struct line_header *header)
{
u32 crc = ~(u32)0;
- crc = crc32_le(crc, (unsigned char *)smeta + sizeof(crc),
+ crc = crc32_le(crc, (unsigned char *)header + sizeof(crc),
sizeof(struct line_header) - sizeof(crc));
return crc;
@@ -996,7 +1108,7 @@ static inline u32 pblk_calc_emeta_crc(struct pblk *pblk,
crc = crc32_le(crc, (unsigned char *)emeta +
sizeof(struct line_header) + sizeof(crc),
- lm->emeta_len -
+ lm->emeta_len[0] -
sizeof(struct line_header) - sizeof(crc));
return crc;
@@ -1016,9 +1128,27 @@ static inline int pblk_set_progr_mode(struct pblk *pblk, int type)
return flags;
}
-static inline int pblk_set_read_mode(struct pblk *pblk)
+enum {
+ PBLK_READ_RANDOM = 0,
+ PBLK_READ_SEQUENTIAL = 1,
+};
+
+static inline int pblk_set_read_mode(struct pblk *pblk, int type)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ int flags;
+
+ flags = NVM_IO_SUSPEND | NVM_IO_SCRAMBLE_ENABLE;
+ if (type == PBLK_READ_SEQUENTIAL)
+ flags |= geo->plane_mode >> 1;
+
+ return flags;
+}
+
+static inline int pblk_io_aligned(struct pblk *pblk, int nr_secs)
{
- return NVM_IO_SNGL_ACCESS | NVM_IO_SUSPEND | NVM_IO_SCRAMBLE_ENABLE;
+ return !(nr_secs % pblk->min_write_pgs);
}
#ifdef CONFIG_NVM_DEBUG
diff --git a/drivers/lightnvm/rrpc.c b/drivers/lightnvm/rrpc.c
index cf0e28a0ff61..267f01ae87e4 100644
--- a/drivers/lightnvm/rrpc.c
+++ b/drivers/lightnvm/rrpc.c
@@ -279,8 +279,8 @@ static void rrpc_end_sync_bio(struct bio *bio)
{
struct completion *waiting = bio->bi_private;
- if (bio->bi_error)
- pr_err("nvm: gc request failed (%u).\n", bio->bi_error);
+ if (bio->bi_status)
+ pr_err("nvm: gc request failed (%u).\n", bio->bi_status);
complete(waiting);
}
@@ -359,7 +359,7 @@ try:
goto finished;
}
wait_for_completion_io(&wait);
- if (bio->bi_error) {
+ if (bio->bi_status) {
rrpc_inflight_laddr_release(rrpc, rqd);
goto finished;
}
@@ -385,7 +385,7 @@ try:
wait_for_completion_io(&wait);
rrpc_inflight_laddr_release(rrpc, rqd);
- if (bio->bi_error)
+ if (bio->bi_status)
goto finished;
bio_reset(bio);
@@ -994,7 +994,7 @@ static blk_qc_t rrpc_make_rq(struct request_queue *q, struct bio *bio)
struct nvm_rq *rqd;
int err;
- blk_queue_split(q, &bio, q->bio_split);
+ blk_queue_split(q, &bio);
if (bio_op(bio) == REQ_OP_DISCARD) {
rrpc_discard(rrpc, bio);
diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index c3ea03c9a1a8..dee542fff68e 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -849,10 +849,11 @@ static inline void wake_up_allocators(struct cache_set *c)
/* Forward declarations */
-void bch_count_io_errors(struct cache *, int, const char *);
+void bch_count_io_errors(struct cache *, blk_status_t, const char *);
void bch_bbio_count_io_errors(struct cache_set *, struct bio *,
- int, const char *);
-void bch_bbio_endio(struct cache_set *, struct bio *, int, const char *);
+ blk_status_t, const char *);
+void bch_bbio_endio(struct cache_set *, struct bio *, blk_status_t,
+ const char *);
void bch_bbio_free(struct bio *, struct cache_set *);
struct bio *bch_bbio_alloc(struct cache_set *);
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index 450d0e848ae4..866dcf78ff8e 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -307,7 +307,7 @@ static void bch_btree_node_read(struct btree *b)
bch_submit_bbio(bio, b->c, &b->key, 0);
closure_sync(&cl);
- if (bio->bi_error)
+ if (bio->bi_status)
set_btree_node_io_error(b);
bch_bbio_free(bio, b->c);
@@ -374,10 +374,10 @@ static void btree_node_write_endio(struct bio *bio)
struct closure *cl = bio->bi_private;
struct btree *b = container_of(cl, struct btree, io);
- if (bio->bi_error)
+ if (bio->bi_status)
set_btree_node_io_error(b);
- bch_bbio_count_io_errors(b->c, bio, bio->bi_error, "writing btree");
+ bch_bbio_count_io_errors(b->c, bio, bio->bi_status, "writing btree");
closure_put(cl);
}
diff --git a/drivers/md/bcache/debug.c b/drivers/md/bcache/debug.c
index 06f55056aaae..35a5a7210e51 100644
--- a/drivers/md/bcache/debug.c
+++ b/drivers/md/bcache/debug.c
@@ -110,7 +110,7 @@ void bch_data_verify(struct cached_dev *dc, struct bio *bio)
struct bio_vec bv, cbv;
struct bvec_iter iter, citer = { 0 };
- check = bio_clone(bio, GFP_NOIO);
+ check = bio_clone_kmalloc(bio, GFP_NOIO);
if (!check)
return;
check->bi_opf = REQ_OP_READ;
diff --git a/drivers/md/bcache/io.c b/drivers/md/bcache/io.c
index db45a88c0ce9..6a9b85095e7b 100644
--- a/drivers/md/bcache/io.c
+++ b/drivers/md/bcache/io.c
@@ -50,7 +50,7 @@ void bch_submit_bbio(struct bio *bio, struct cache_set *c,
/* IO errors */
-void bch_count_io_errors(struct cache *ca, int error, const char *m)
+void bch_count_io_errors(struct cache *ca, blk_status_t error, const char *m)
{
/*
* The halflife of an error is:
@@ -103,7 +103,7 @@ void bch_count_io_errors(struct cache *ca, int error, const char *m)
}
void bch_bbio_count_io_errors(struct cache_set *c, struct bio *bio,
- int error, const char *m)
+ blk_status_t error, const char *m)
{
struct bbio *b = container_of(bio, struct bbio, bio);
struct cache *ca = PTR_CACHE(c, &b->key, 0);
@@ -132,7 +132,7 @@ void bch_bbio_count_io_errors(struct cache_set *c, struct bio *bio,
}
void bch_bbio_endio(struct cache_set *c, struct bio *bio,
- int error, const char *m)
+ blk_status_t error, const char *m)
{
struct closure *cl = bio->bi_private;
diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c
index 1198e53d5670..0352d05e495c 100644
--- a/drivers/md/bcache/journal.c
+++ b/drivers/md/bcache/journal.c
@@ -549,7 +549,7 @@ static void journal_write_endio(struct bio *bio)
{
struct journal_write *w = bio->bi_private;
- cache_set_err_on(bio->bi_error, w->c, "journal io error");
+ cache_set_err_on(bio->bi_status, w->c, "journal io error");
closure_put(&w->c->journal.io);
}
diff --git a/drivers/md/bcache/movinggc.c b/drivers/md/bcache/movinggc.c
index 13b8a907006d..f633b30c962e 100644
--- a/drivers/md/bcache/movinggc.c
+++ b/drivers/md/bcache/movinggc.c
@@ -63,14 +63,14 @@ static void read_moving_endio(struct bio *bio)
struct moving_io *io = container_of(bio->bi_private,
struct moving_io, cl);
- if (bio->bi_error)
- io->op.error = bio->bi_error;
+ if (bio->bi_status)
+ io->op.status = bio->bi_status;
else if (!KEY_DIRTY(&b->key) &&
ptr_stale(io->op.c, &b->key, 0)) {
- io->op.error = -EINTR;
+ io->op.status = BLK_STS_IOERR;
}
- bch_bbio_endio(io->op.c, bio, bio->bi_error, "reading data to move");
+ bch_bbio_endio(io->op.c, bio, bio->bi_status, "reading data to move");
}
static void moving_init(struct moving_io *io)
@@ -92,7 +92,7 @@ static void write_moving(struct closure *cl)
struct moving_io *io = container_of(cl, struct moving_io, cl);
struct data_insert_op *op = &io->op;
- if (!op->error) {
+ if (!op->status) {
moving_init(io);
io->bio.bio.bi_iter.bi_sector = KEY_START(&io->w->key);
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index 709c9cc34369..019b3df9f1c6 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -81,7 +81,7 @@ static void bch_data_insert_keys(struct closure *cl)
if (ret == -ESRCH) {
op->replace_collision = true;
} else if (ret) {
- op->error = -ENOMEM;
+ op->status = BLK_STS_RESOURCE;
op->insert_data_done = true;
}
@@ -178,17 +178,17 @@ static void bch_data_insert_endio(struct bio *bio)
struct closure *cl = bio->bi_private;
struct data_insert_op *op = container_of(cl, struct data_insert_op, cl);
- if (bio->bi_error) {
+ if (bio->bi_status) {
/* TODO: We could try to recover from this. */
if (op->writeback)
- op->error = bio->bi_error;
+ op->status = bio->bi_status;
else if (!op->replace)
set_closure_fn(cl, bch_data_insert_error, op->wq);
else
set_closure_fn(cl, NULL, NULL);
}
- bch_bbio_endio(op->c, bio, bio->bi_error, "writing data to cache");
+ bch_bbio_endio(op->c, bio, bio->bi_status, "writing data to cache");
}
static void bch_data_insert_start(struct closure *cl)
@@ -488,15 +488,15 @@ static void bch_cache_read_endio(struct bio *bio)
* from the backing device.
*/
- if (bio->bi_error)
- s->iop.error = bio->bi_error;
+ if (bio->bi_status)
+ s->iop.status = bio->bi_status;
else if (!KEY_DIRTY(&b->key) &&
ptr_stale(s->iop.c, &b->key, 0)) {
atomic_long_inc(&s->iop.c->cache_read_races);
- s->iop.error = -EINTR;
+ s->iop.status = BLK_STS_IOERR;
}
- bch_bbio_endio(s->iop.c, bio, bio->bi_error, "reading from cache");
+ bch_bbio_endio(s->iop.c, bio, bio->bi_status, "reading from cache");
}
/*
@@ -593,9 +593,9 @@ static void request_endio(struct bio *bio)
{
struct closure *cl = bio->bi_private;
- if (bio->bi_error) {
+ if (bio->bi_status) {
struct search *s = container_of(cl, struct search, cl);
- s->iop.error = bio->bi_error;
+ s->iop.status = bio->bi_status;
/* Only cache read errors are recoverable */
s->recoverable = false;
}
@@ -611,7 +611,7 @@ static void bio_complete(struct search *s)
&s->d->disk->part0, s->start_time);
trace_bcache_request_end(s->d, s->orig_bio);
- s->orig_bio->bi_error = s->iop.error;
+ s->orig_bio->bi_status = s->iop.status;
bio_endio(s->orig_bio);
s->orig_bio = NULL;
}
@@ -664,7 +664,7 @@ static inline struct search *search_alloc(struct bio *bio,
s->iop.inode = d->id;
s->iop.write_point = hash_long((unsigned long) current, 16);
s->iop.write_prio = 0;
- s->iop.error = 0;
+ s->iop.status = 0;
s->iop.flags = 0;
s->iop.flush_journal = op_is_flush(bio->bi_opf);
s->iop.wq = bcache_wq;
@@ -707,7 +707,7 @@ static void cached_dev_read_error(struct closure *cl)
/* Retry from the backing device: */
trace_bcache_read_retry(s->orig_bio);
- s->iop.error = 0;
+ s->iop.status = 0;
do_bio_hook(s, s->orig_bio);
/* XXX: invalidate cache */
@@ -767,7 +767,7 @@ static void cached_dev_read_done_bh(struct closure *cl)
!s->cache_miss, s->iop.bypass);
trace_bcache_read(s->orig_bio, !s->cache_miss, s->iop.bypass);
- if (s->iop.error)
+ if (s->iop.status)
continue_at_nobarrier(cl, cached_dev_read_error, bcache_wq);
else if (s->iop.bio || verify(dc, &s->bio.bio))
continue_at_nobarrier(cl, cached_dev_read_done, bcache_wq);
diff --git a/drivers/md/bcache/request.h b/drivers/md/bcache/request.h
index 1ff36875c2b3..7689176951ce 100644
--- a/drivers/md/bcache/request.h
+++ b/drivers/md/bcache/request.h
@@ -10,7 +10,7 @@ struct data_insert_op {
unsigned inode;
uint16_t write_point;
uint16_t write_prio;
- short error;
+ blk_status_t status;
union {
uint16_t flags;
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index e57353e39168..8352fad765f6 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -271,7 +271,7 @@ static void write_super_endio(struct bio *bio)
{
struct cache *ca = bio->bi_private;
- bch_count_io_errors(ca, bio->bi_error, "writing superblock");
+ bch_count_io_errors(ca, bio->bi_status, "writing superblock");
closure_put(&ca->set->sb_write);
}
@@ -321,7 +321,7 @@ static void uuid_endio(struct bio *bio)
struct closure *cl = bio->bi_private;
struct cache_set *c = container_of(cl, struct cache_set, uuid_write);
- cache_set_err_on(bio->bi_error, c, "accessing uuids");
+ cache_set_err_on(bio->bi_status, c, "accessing uuids");
bch_bbio_free(bio, c);
closure_put(cl);
}
@@ -494,7 +494,7 @@ static void prio_endio(struct bio *bio)
{
struct cache *ca = bio->bi_private;
- cache_set_err_on(bio->bi_error, ca->set, "accessing priorities");
+ cache_set_err_on(bio->bi_status, ca->set, "accessing priorities");
bch_bbio_free(bio, ca->set);
closure_put(&ca->prio);
}
@@ -782,7 +782,9 @@ static int bcache_device_init(struct bcache_device *d, unsigned block_size,
minor *= BCACHE_MINORS;
- if (!(d->bio_split = bioset_create(4, offsetof(struct bbio, bio))) ||
+ if (!(d->bio_split = bioset_create(4, offsetof(struct bbio, bio),
+ BIOSET_NEED_BVECS |
+ BIOSET_NEED_RESCUER)) ||
!(d->disk = alloc_disk(BCACHE_MINORS))) {
ida_simple_remove(&bcache_minor, minor);
return -ENOMEM;
@@ -1516,7 +1518,9 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb)
sizeof(struct bbio) + sizeof(struct bio_vec) *
bucket_pages(c))) ||
!(c->fill_iter = mempool_create_kmalloc_pool(1, iter_size)) ||
- !(c->bio_split = bioset_create(4, offsetof(struct bbio, bio))) ||
+ !(c->bio_split = bioset_create(4, offsetof(struct bbio, bio),
+ BIOSET_NEED_BVECS |
+ BIOSET_NEED_RESCUER)) ||
!(c->uuids = alloc_bucket_pages(GFP_KERNEL, c)) ||
!(c->moving_gc_wq = alloc_workqueue("bcache_gc",
WQ_MEM_RECLAIM, 0)) ||
diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c
index 6ac2e48b9235..42c66e76f05e 100644
--- a/drivers/md/bcache/writeback.c
+++ b/drivers/md/bcache/writeback.c
@@ -167,7 +167,7 @@ static void dirty_endio(struct bio *bio)
struct keybuf_key *w = bio->bi_private;
struct dirty_io *io = w->private;
- if (bio->bi_error)
+ if (bio->bi_status)
SET_KEY_DIRTY(&w->key, false);
closure_put(&io->cl);
@@ -195,7 +195,7 @@ static void read_dirty_endio(struct bio *bio)
struct dirty_io *io = w->private;
bch_count_io_errors(PTR_CACHE(io->dc->disk.c, &w->key, 0),
- bio->bi_error, "reading dirty data from cache");
+ bio->bi_status, "reading dirty data from cache");
dirty_endio(bio);
}
diff --git a/drivers/md/dm-bio-prison-v1.c b/drivers/md/dm-bio-prison-v1.c
index ae7da2c30a57..82d27384d31f 100644
--- a/drivers/md/dm-bio-prison-v1.c
+++ b/drivers/md/dm-bio-prison-v1.c
@@ -229,7 +229,7 @@ void dm_cell_release_no_holder(struct dm_bio_prison *prison,
EXPORT_SYMBOL_GPL(dm_cell_release_no_holder);
void dm_cell_error(struct dm_bio_prison *prison,
- struct dm_bio_prison_cell *cell, int error)
+ struct dm_bio_prison_cell *cell, blk_status_t error)
{
struct bio_list bios;
struct bio *bio;
@@ -238,7 +238,7 @@ void dm_cell_error(struct dm_bio_prison *prison,
dm_cell_release(prison, cell, &bios);
while ((bio = bio_list_pop(&bios))) {
- bio->bi_error = error;
+ bio->bi_status = error;
bio_endio(bio);
}
}
diff --git a/drivers/md/dm-bio-prison-v1.h b/drivers/md/dm-bio-prison-v1.h
index cddd4ac07e2c..cec52ac5e1ae 100644
--- a/drivers/md/dm-bio-prison-v1.h
+++ b/drivers/md/dm-bio-prison-v1.h
@@ -91,7 +91,7 @@ void dm_cell_release_no_holder(struct dm_bio_prison *prison,
struct dm_bio_prison_cell *cell,
struct bio_list *inmates);
void dm_cell_error(struct dm_bio_prison *prison,
- struct dm_bio_prison_cell *cell, int error);
+ struct dm_bio_prison_cell *cell, blk_status_t error);
/*
* Visits the cell and then releases. Guarantees no new inmates are
diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index 840c1496b2b1..850ff6c67994 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -145,8 +145,8 @@ struct dm_buffer {
enum data_mode data_mode;
unsigned char list_mode; /* LIST_* */
unsigned hold_count;
- int read_error;
- int write_error;
+ blk_status_t read_error;
+ blk_status_t write_error;
unsigned long state;
unsigned long last_accessed;
struct dm_bufio_client *c;
@@ -555,7 +555,7 @@ static void dmio_complete(unsigned long error, void *context)
{
struct dm_buffer *b = context;
- b->bio.bi_error = error ? -EIO : 0;
+ b->bio.bi_status = error ? BLK_STS_IOERR : 0;
b->bio.bi_end_io(&b->bio);
}
@@ -588,7 +588,7 @@ static void use_dmio(struct dm_buffer *b, int rw, sector_t sector,
r = dm_io(&io_req, 1, &region, NULL);
if (r) {
- b->bio.bi_error = r;
+ b->bio.bi_status = errno_to_blk_status(r);
end_io(&b->bio);
}
}
@@ -596,7 +596,7 @@ static void use_dmio(struct dm_buffer *b, int rw, sector_t sector,
static void inline_endio(struct bio *bio)
{
bio_end_io_t *end_fn = bio->bi_private;
- int error = bio->bi_error;
+ blk_status_t status = bio->bi_status;
/*
* Reset the bio to free any attached resources
@@ -604,7 +604,7 @@ static void inline_endio(struct bio *bio)
*/
bio_reset(bio);
- bio->bi_error = error;
+ bio->bi_status = status;
end_fn(bio);
}
@@ -685,11 +685,12 @@ static void write_endio(struct bio *bio)
{
struct dm_buffer *b = container_of(bio, struct dm_buffer, bio);
- b->write_error = bio->bi_error;
- if (unlikely(bio->bi_error)) {
+ b->write_error = bio->bi_status;
+ if (unlikely(bio->bi_status)) {
struct dm_bufio_client *c = b->c;
- int error = bio->bi_error;
- (void)cmpxchg(&c->async_write_error, 0, error);
+
+ (void)cmpxchg(&c->async_write_error, 0,
+ blk_status_to_errno(bio->bi_status));
}
BUG_ON(!test_bit(B_WRITING, &b->state));
@@ -1063,7 +1064,7 @@ static void read_endio(struct bio *bio)
{
struct dm_buffer *b = container_of(bio, struct dm_buffer, bio);
- b->read_error = bio->bi_error;
+ b->read_error = bio->bi_status;
BUG_ON(!test_bit(B_READING, &b->state));
@@ -1107,7 +1108,7 @@ static void *new_read(struct dm_bufio_client *c, sector_t block,
wait_on_bit_io(&b->state, B_READING, TASK_UNINTERRUPTIBLE);
if (b->read_error) {
- int error = b->read_error;
+ int error = blk_status_to_errno(b->read_error);
dm_bufio_release(b);
@@ -1257,7 +1258,8 @@ EXPORT_SYMBOL_GPL(dm_bufio_write_dirty_buffers_async);
*/
int dm_bufio_write_dirty_buffers(struct dm_bufio_client *c)
{
- int a, f;
+ blk_status_t a;
+ int f;
unsigned long buffers_processed = 0;
struct dm_buffer *b, *tmp;
diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c
index d682a0511381..c5ea03fc7ee1 100644
--- a/drivers/md/dm-cache-target.c
+++ b/drivers/md/dm-cache-target.c
@@ -119,7 +119,7 @@ static void iot_io_end(struct io_tracker *iot, sector_t len)
*/
struct continuation {
struct work_struct ws;
- int input;
+ blk_status_t input;
};
static inline void init_continuation(struct continuation *k,
@@ -145,7 +145,7 @@ struct batcher {
/*
* The operation that everyone is waiting for.
*/
- int (*commit_op)(void *context);
+ blk_status_t (*commit_op)(void *context);
void *commit_context;
/*
@@ -171,8 +171,7 @@ struct batcher {
static void __commit(struct work_struct *_ws)
{
struct batcher *b = container_of(_ws, struct batcher, commit_work);
-
- int r;
+ blk_status_t r;
unsigned long flags;
struct list_head work_items;
struct work_struct *ws, *tmp;
@@ -205,7 +204,7 @@ static void __commit(struct work_struct *_ws)
while ((bio = bio_list_pop(&bios))) {
if (r) {
- bio->bi_error = r;
+ bio->bi_status = r;
bio_endio(bio);
} else
b->issue_op(bio, b->issue_context);
@@ -213,7 +212,7 @@ static void __commit(struct work_struct *_ws)
}
static void batcher_init(struct batcher *b,
- int (*commit_op)(void *),
+ blk_status_t (*commit_op)(void *),
void *commit_context,
void (*issue_op)(struct bio *bio, void *),
void *issue_context,
@@ -955,7 +954,7 @@ static void writethrough_endio(struct bio *bio)
dm_unhook_bio(&pb->hook_info, bio);
- if (bio->bi_error) {
+ if (bio->bi_status) {
bio_endio(bio);
return;
}
@@ -1220,7 +1219,7 @@ static void copy_complete(int read_err, unsigned long write_err, void *context)
struct dm_cache_migration *mg = container_of(context, struct dm_cache_migration, k);
if (read_err || write_err)
- mg->k.input = -EIO;
+ mg->k.input = BLK_STS_IOERR;
queue_continuation(mg->cache->wq, &mg->k);
}
@@ -1266,8 +1265,8 @@ static void overwrite_endio(struct bio *bio)
dm_unhook_bio(&pb->hook_info, bio);
- if (bio->bi_error)
- mg->k.input = bio->bi_error;
+ if (bio->bi_status)
+ mg->k.input = bio->bi_status;
queue_continuation(mg->cache->wq, &mg->k);
}
@@ -1323,8 +1322,10 @@ static void mg_complete(struct dm_cache_migration *mg, bool success)
if (mg->overwrite_bio) {
if (success)
force_set_dirty(cache, cblock);
+ else if (mg->k.input)
+ mg->overwrite_bio->bi_status = mg->k.input;
else
- mg->overwrite_bio->bi_error = (mg->k.input ? : -EIO);
+ mg->overwrite_bio->bi_status = BLK_STS_IOERR;
bio_endio(mg->overwrite_bio);
} else {
if (success)
@@ -1504,7 +1505,7 @@ static void mg_copy(struct work_struct *ws)
r = copy(mg, is_policy_promote);
if (r) {
DMERR_LIMIT("%s: migration copy failed", cache_device_name(cache));
- mg->k.input = -EIO;
+ mg->k.input = BLK_STS_IOERR;
mg_complete(mg, false);
}
}
@@ -1907,12 +1908,12 @@ static int commit(struct cache *cache, bool clean_shutdown)
/*
* Used by the batcher.
*/
-static int commit_op(void *context)
+static blk_status_t commit_op(void *context)
{
struct cache *cache = context;
if (dm_cache_changed_this_transaction(cache->cmd))
- return commit(cache, false);
+ return errno_to_blk_status(commit(cache, false));
return 0;
}
@@ -2018,7 +2019,7 @@ static void requeue_deferred_bios(struct cache *cache)
bio_list_init(&cache->deferred_bios);
while ((bio = bio_list_pop(&bios))) {
- bio->bi_error = DM_ENDIO_REQUEUE;
+ bio->bi_status = BLK_STS_DM_REQUEUE;
bio_endio(bio);
}
}
@@ -2820,7 +2821,8 @@ static int cache_map(struct dm_target *ti, struct bio *bio)
return r;
}
-static int cache_end_io(struct dm_target *ti, struct bio *bio, int error)
+static int cache_end_io(struct dm_target *ti, struct bio *bio,
+ blk_status_t *error)
{
struct cache *cache = ti->private;
unsigned long flags;
@@ -2838,7 +2840,7 @@ static int cache_end_io(struct dm_target *ti, struct bio *bio, int error)
bio_drop_shared_lock(cache, bio);
accounted_complete(cache, bio);
- return 0;
+ return DM_ENDIO_DONE;
}
static int write_dirty_bitset(struct cache *cache)
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index ebf9e72d479b..9e1b72e8f7ef 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -71,7 +71,7 @@ struct dm_crypt_io {
struct convert_context ctx;
atomic_t io_pending;
- int error;
+ blk_status_t error;
sector_t sector;
struct rb_node rb_node;
@@ -1292,7 +1292,7 @@ static void crypt_free_req(struct crypt_config *cc, void *req, struct bio *base_
/*
* Encrypt / decrypt data from one bio to another one (can be the same one)
*/
-static int crypt_convert(struct crypt_config *cc,
+static blk_status_t crypt_convert(struct crypt_config *cc,
struct convert_context *ctx)
{
unsigned int tag_offset = 0;
@@ -1343,13 +1343,13 @@ static int crypt_convert(struct crypt_config *cc,
*/
case -EBADMSG:
atomic_dec(&ctx->cc_pending);
- return -EILSEQ;
+ return BLK_STS_PROTECTION;
/*
* There was an error while processing the request.
*/
default:
atomic_dec(&ctx->cc_pending);
- return -EIO;
+ return BLK_STS_IOERR;
}
}
@@ -1463,7 +1463,7 @@ static void crypt_dec_pending(struct dm_crypt_io *io)
{
struct crypt_config *cc = io->cc;
struct bio *base_bio = io->base_bio;
- int error = io->error;
+ blk_status_t error = io->error;
if (!atomic_dec_and_test(&io->io_pending))
return;
@@ -1476,7 +1476,7 @@ static void crypt_dec_pending(struct dm_crypt_io *io)
else
kfree(io->integrity_metadata);
- base_bio->bi_error = error;
+ base_bio->bi_status = error;
bio_endio(base_bio);
}
@@ -1502,7 +1502,7 @@ static void crypt_endio(struct bio *clone)
struct dm_crypt_io *io = clone->bi_private;
struct crypt_config *cc = io->cc;
unsigned rw = bio_data_dir(clone);
- int error;
+ blk_status_t error;
/*
* free the processed pages
@@ -1510,7 +1510,7 @@ static void crypt_endio(struct bio *clone)
if (rw == WRITE)
crypt_free_buffer_pages(cc, clone);
- error = clone->bi_error;
+ error = clone->bi_status;
bio_put(clone);
if (rw == READ && !error) {
@@ -1570,7 +1570,7 @@ static void kcryptd_io_read_work(struct work_struct *work)
crypt_inc_pending(io);
if (kcryptd_io_read(io, GFP_NOIO))
- io->error = -ENOMEM;
+ io->error = BLK_STS_RESOURCE;
crypt_dec_pending(io);
}
@@ -1656,7 +1656,7 @@ static void kcryptd_crypt_write_io_submit(struct dm_crypt_io *io, int async)
sector_t sector;
struct rb_node **rbp, *parent;
- if (unlikely(io->error < 0)) {
+ if (unlikely(io->error)) {
crypt_free_buffer_pages(cc, clone);
bio_put(clone);
crypt_dec_pending(io);
@@ -1697,7 +1697,7 @@ static void kcryptd_crypt_write_convert(struct dm_crypt_io *io)
struct bio *clone;
int crypt_finished;
sector_t sector = io->sector;
- int r;
+ blk_status_t r;
/*
* Prevent io from disappearing until this function completes.
@@ -1707,7 +1707,7 @@ static void kcryptd_crypt_write_convert(struct dm_crypt_io *io)
clone = crypt_alloc_buffer(io, io->base_bio->bi_iter.bi_size);
if (unlikely(!clone)) {
- io->error = -EIO;
+ io->error = BLK_STS_IOERR;
goto dec;
}
@@ -1718,7 +1718,7 @@ static void kcryptd_crypt_write_convert(struct dm_crypt_io *io)
crypt_inc_pending(io);
r = crypt_convert(cc, &io->ctx);
- if (r < 0)
+ if (r)
io->error = r;
crypt_finished = atomic_dec_and_test(&io->ctx.cc_pending);
@@ -1740,7 +1740,7 @@ static void kcryptd_crypt_read_done(struct dm_crypt_io *io)
static void kcryptd_crypt_read_convert(struct dm_crypt_io *io)
{
struct crypt_config *cc = io->cc;
- int r = 0;
+ blk_status_t r;
crypt_inc_pending(io);
@@ -1748,7 +1748,7 @@ static void kcryptd_crypt_read_convert(struct dm_crypt_io *io)
io->sector);
r = crypt_convert(cc, &io->ctx);
- if (r < 0)
+ if (r)
io->error = r;
if (atomic_dec_and_test(&io->ctx.cc_pending))
@@ -1781,9 +1781,9 @@ static void kcryptd_async_done(struct crypto_async_request *async_req,
if (error == -EBADMSG) {
DMERR_LIMIT("INTEGRITY AEAD ERROR, sector %llu",
(unsigned long long)le64_to_cpu(*org_sector_of_dmreq(cc, dmreq)));
- io->error = -EILSEQ;
+ io->error = BLK_STS_PROTECTION;
} else if (error < 0)
- io->error = -EIO;
+ io->error = BLK_STS_IOERR;
crypt_free_req(cc, req_of_dmreq(cc, dmreq), io->base_bio);
@@ -2677,7 +2677,8 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
goto bad;
}
- cc->bs = bioset_create(MIN_IOS, 0);
+ cc->bs = bioset_create(MIN_IOS, 0, (BIOSET_NEED_BVECS |
+ BIOSET_NEED_RESCUER));
if (!cc->bs) {
ti->error = "Cannot allocate crypt bioset";
goto bad;
@@ -2795,10 +2796,10 @@ static int crypt_map(struct dm_target *ti, struct bio *bio)
* and is aligned to this size as defined in IO hints.
*/
if (unlikely((bio->bi_iter.bi_sector & ((cc->sector_size >> SECTOR_SHIFT) - 1)) != 0))
- return -EIO;
+ return DM_MAPIO_KILL;
if (unlikely(bio->bi_iter.bi_size & (cc->sector_size - 1)))
- return -EIO;
+ return DM_MAPIO_KILL;
io = dm_per_bio_data(bio, cc->per_bio_data_size);
crypt_io_init(io, cc, bio, dm_target_offset(ti, bio->bi_iter.bi_sector));
diff --git a/drivers/md/dm-flakey.c b/drivers/md/dm-flakey.c
index 13305a182611..3d04d5ce19d9 100644
--- a/drivers/md/dm-flakey.c
+++ b/drivers/md/dm-flakey.c
@@ -321,7 +321,7 @@ static int flakey_map(struct dm_target *ti, struct bio *bio)
if (bio_data_dir(bio) == READ) {
if (!fc->corrupt_bio_byte && !test_bit(DROP_WRITES, &fc->flags) &&
!test_bit(ERROR_WRITES, &fc->flags))
- return -EIO;
+ return DM_MAPIO_KILL;
goto map_bio;
}
@@ -349,7 +349,7 @@ static int flakey_map(struct dm_target *ti, struct bio *bio)
/*
* By default, error all I/O.
*/
- return -EIO;
+ return DM_MAPIO_KILL;
}
map_bio:
@@ -358,12 +358,13 @@ map_bio:
return DM_MAPIO_REMAPPED;
}
-static int flakey_end_io(struct dm_target *ti, struct bio *bio, int error)
+static int flakey_end_io(struct dm_target *ti, struct bio *bio,
+ blk_status_t *error)
{
struct flakey_c *fc = ti->private;
struct per_bio_data *pb = dm_per_bio_data(bio, sizeof(struct per_bio_data));
- if (!error && pb->bio_submitted && (bio_data_dir(bio) == READ)) {
+ if (!*error && pb->bio_submitted && (bio_data_dir(bio) == READ)) {
if (fc->corrupt_bio_byte && (fc->corrupt_bio_rw == READ) &&
all_corrupt_bio_flags_match(bio, fc)) {
/*
@@ -377,11 +378,11 @@ static int flakey_end_io(struct dm_target *ti, struct bio *bio, int error)
* Error read during the down_interval if drop_writes
* and error_writes were not configured.
*/
- return -EIO;
+ *error = BLK_STS_IOERR;
}
}
- return error;
+ return DM_ENDIO_DONE;
}
static void flakey_status(struct dm_target *ti, status_type_t type,
diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c
index 93b181088168..1b224aa9cf15 100644
--- a/drivers/md/dm-integrity.c
+++ b/drivers/md/dm-integrity.c
@@ -246,7 +246,7 @@ struct dm_integrity_io {
unsigned metadata_offset;
atomic_t in_flight;
- int bi_error;
+ blk_status_t bi_status;
struct completion *completion;
@@ -1118,8 +1118,8 @@ static void submit_flush_bio(struct dm_integrity_c *ic, struct dm_integrity_io *
static void do_endio(struct dm_integrity_c *ic, struct bio *bio)
{
int r = dm_integrity_failed(ic);
- if (unlikely(r) && !bio->bi_error)
- bio->bi_error = r;
+ if (unlikely(r) && !bio->bi_status)
+ bio->bi_status = errno_to_blk_status(r);
bio_endio(bio);
}
@@ -1127,7 +1127,7 @@ static void do_endio_flush(struct dm_integrity_c *ic, struct dm_integrity_io *di
{
struct bio *bio = dm_bio_from_per_bio_data(dio, sizeof(struct dm_integrity_io));
- if (unlikely(dio->fua) && likely(!bio->bi_error) && likely(!dm_integrity_failed(ic)))
+ if (unlikely(dio->fua) && likely(!bio->bi_status) && likely(!dm_integrity_failed(ic)))
submit_flush_bio(ic, dio);
else
do_endio(ic, bio);
@@ -1146,9 +1146,9 @@ static void dec_in_flight(struct dm_integrity_io *dio)
bio = dm_bio_from_per_bio_data(dio, sizeof(struct dm_integrity_io));
- if (unlikely(dio->bi_error) && !bio->bi_error)
- bio->bi_error = dio->bi_error;
- if (likely(!bio->bi_error) && unlikely(bio_sectors(bio) != dio->range.n_sectors)) {
+ if (unlikely(dio->bi_status) && !bio->bi_status)
+ bio->bi_status = dio->bi_status;
+ if (likely(!bio->bi_status) && unlikely(bio_sectors(bio) != dio->range.n_sectors)) {
dio->range.logical_sector += dio->range.n_sectors;
bio_advance(bio, dio->range.n_sectors << SECTOR_SHIFT);
INIT_WORK(&dio->work, integrity_bio_wait);
@@ -1322,7 +1322,7 @@ skip_io:
dec_in_flight(dio);
return;
error:
- dio->bi_error = r;
+ dio->bi_status = errno_to_blk_status(r);
dec_in_flight(dio);
}
@@ -1335,7 +1335,7 @@ static int dm_integrity_map(struct dm_target *ti, struct bio *bio)
sector_t area, offset;
dio->ic = ic;
- dio->bi_error = 0;
+ dio->bi_status = 0;
if (unlikely(bio->bi_opf & REQ_PREFLUSH)) {
submit_flush_bio(ic, dio);
@@ -1356,13 +1356,13 @@ static int dm_integrity_map(struct dm_target *ti, struct bio *bio)
DMERR("Too big sector number: 0x%llx + 0x%x > 0x%llx",
(unsigned long long)dio->range.logical_sector, bio_sectors(bio),
(unsigned long long)ic->provided_data_sectors);
- return -EIO;
+ return DM_MAPIO_KILL;
}
if (unlikely((dio->range.logical_sector | bio_sectors(bio)) & (unsigned)(ic->sectors_per_block - 1))) {
DMERR("Bio not aligned on %u sectors: 0x%llx, 0x%x",
ic->sectors_per_block,
(unsigned long long)dio->range.logical_sector, bio_sectors(bio));
- return -EIO;
+ return DM_MAPIO_KILL;
}
if (ic->sectors_per_block > 1) {
@@ -1372,7 +1372,7 @@ static int dm_integrity_map(struct dm_target *ti, struct bio *bio)
if (unlikely((bv.bv_offset | bv.bv_len) & ((ic->sectors_per_block << SECTOR_SHIFT) - 1))) {
DMERR("Bio vector (%u,%u) is not aligned on %u-sector boundary",
bv.bv_offset, bv.bv_len, ic->sectors_per_block);
- return -EIO;
+ return DM_MAPIO_KILL;
}
}
}
@@ -1387,18 +1387,18 @@ static int dm_integrity_map(struct dm_target *ti, struct bio *bio)
wanted_tag_size *= ic->tag_size;
if (unlikely(wanted_tag_size != bip->bip_iter.bi_size)) {
DMERR("Invalid integrity data size %u, expected %u", bip->bip_iter.bi_size, wanted_tag_size);
- return -EIO;
+ return DM_MAPIO_KILL;
}
}
} else {
if (unlikely(bip != NULL)) {
DMERR("Unexpected integrity data when using internal hash");
- return -EIO;
+ return DM_MAPIO_KILL;
}
}
if (unlikely(ic->mode == 'R') && unlikely(dio->write))
- return -EIO;
+ return DM_MAPIO_KILL;
get_area_and_offset(ic, dio->range.logical_sector, &area, &offset);
dio->metadata_block = get_metadata_sector_and_offset(ic, area, offset, &dio->metadata_offset);
diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c
index 8d5ca30f6551..25039607f3cb 100644
--- a/drivers/md/dm-io.c
+++ b/drivers/md/dm-io.c
@@ -58,7 +58,8 @@ struct dm_io_client *dm_io_client_create(void)
if (!client->pool)
goto bad;
- client->bios = bioset_create(min_ios, 0);
+ client->bios = bioset_create(min_ios, 0, (BIOSET_NEED_BVECS |
+ BIOSET_NEED_RESCUER));
if (!client->bios)
goto bad;
@@ -124,7 +125,7 @@ static void complete_io(struct io *io)
fn(error_bits, context);
}
-static void dec_count(struct io *io, unsigned int region, int error)
+static void dec_count(struct io *io, unsigned int region, blk_status_t error)
{
if (error)
set_bit(region, &io->error_bits);
@@ -137,9 +138,9 @@ static void endio(struct bio *bio)
{
struct io *io;
unsigned region;
- int error;
+ blk_status_t error;
- if (bio->bi_error && bio_data_dir(bio) == READ)
+ if (bio->bi_status && bio_data_dir(bio) == READ)
zero_fill_bio(bio);
/*
@@ -147,7 +148,7 @@ static void endio(struct bio *bio)
*/
retrieve_io_and_region_from_bio(bio, &io, &region);
- error = bio->bi_error;
+ error = bio->bi_status;
bio_put(bio);
dec_count(io, region, error);
@@ -319,7 +320,7 @@ static void do_region(int op, int op_flags, unsigned region,
if ((op == REQ_OP_DISCARD || op == REQ_OP_WRITE_ZEROES ||
op == REQ_OP_WRITE_SAME) && special_cmd_max_sectors == 0) {
atomic_inc(&io->count);
- dec_count(io, region, -EOPNOTSUPP);
+ dec_count(io, region, BLK_STS_NOTSUPP);
return;
}
diff --git a/drivers/md/dm-log-writes.c b/drivers/md/dm-log-writes.c
index 4dfe38655a49..a1da0eb58a93 100644
--- a/drivers/md/dm-log-writes.c
+++ b/drivers/md/dm-log-writes.c
@@ -150,10 +150,10 @@ static void log_end_io(struct bio *bio)
{
struct log_writes_c *lc = bio->bi_private;
- if (bio->bi_error) {
+ if (bio->bi_status) {
unsigned long flags;
- DMERR("Error writing log block, error=%d", bio->bi_error);
+ DMERR("Error writing log block, error=%d", bio->bi_status);
spin_lock_irqsave(&lc->blocks_lock, flags);
lc->logging_enabled = false;
spin_unlock_irqrestore(&lc->blocks_lock, flags);
@@ -586,7 +586,7 @@ static int log_writes_map(struct dm_target *ti, struct bio *bio)
spin_lock_irq(&lc->blocks_lock);
lc->logging_enabled = false;
spin_unlock_irq(&lc->blocks_lock);
- return -ENOMEM;
+ return DM_MAPIO_KILL;
}
INIT_LIST_HEAD(&block->list);
pb->block = block;
@@ -639,7 +639,7 @@ static int log_writes_map(struct dm_target *ti, struct bio *bio)
spin_lock_irq(&lc->blocks_lock);
lc->logging_enabled = false;
spin_unlock_irq(&lc->blocks_lock);
- return -ENOMEM;
+ return DM_MAPIO_KILL;
}
src = kmap_atomic(bv.bv_page);
@@ -664,7 +664,8 @@ map_bio:
return DM_MAPIO_REMAPPED;
}
-static int normal_end_io(struct dm_target *ti, struct bio *bio, int error)
+static int normal_end_io(struct dm_target *ti, struct bio *bio,
+ blk_status_t *error)
{
struct log_writes_c *lc = ti->private;
struct per_bio_data *pb = dm_per_bio_data(bio, sizeof(struct per_bio_data));
@@ -686,7 +687,7 @@ static int normal_end_io(struct dm_target *ti, struct bio *bio, int error)
spin_unlock_irqrestore(&lc->blocks_lock, flags);
}
- return error;
+ return DM_ENDIO_DONE;
}
/*
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index 3df056b73b66..0e8ab5bb3575 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -559,13 +559,13 @@ static int __multipath_map_bio(struct multipath *m, struct bio *bio, struct dm_m
if (test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags))
return DM_MAPIO_REQUEUE;
dm_report_EIO(m);
- return -EIO;
+ return DM_MAPIO_KILL;
}
mpio->pgpath = pgpath;
mpio->nr_bytes = nr_bytes;
- bio->bi_error = 0;
+ bio->bi_status = 0;
bio->bi_bdev = pgpath->path.dev->bdev;
bio->bi_opf |= REQ_FAILFAST_TRANSPORT;
@@ -621,11 +621,19 @@ static void process_queued_bios(struct work_struct *work)
blk_start_plug(&plug);
while ((bio = bio_list_pop(&bios))) {
r = __multipath_map_bio(m, bio, get_mpio_from_bio(bio));
- if (r < 0 || r == DM_MAPIO_REQUEUE) {
- bio->bi_error = r;
+ switch (r) {
+ case DM_MAPIO_KILL:
+ bio->bi_status = BLK_STS_IOERR;
+ bio_endio(bio);
+ break;
+ case DM_MAPIO_REQUEUE:
+ bio->bi_status = BLK_STS_DM_REQUEUE;
bio_endio(bio);
- } else if (r == DM_MAPIO_REMAPPED)
+ break;
+ case DM_MAPIO_REMAPPED:
generic_make_request(bio);
+ break;
+ }
}
blk_finish_plug(&plug);
}
@@ -1442,22 +1450,15 @@ static void activate_path_work(struct work_struct *work)
activate_or_offline_path(pgpath);
}
-static int noretry_error(int error)
+static int noretry_error(blk_status_t error)
{
switch (error) {
- case -EBADE:
- /*
- * EBADE signals an reservation conflict.
- * We shouldn't fail the path here as we can communicate with
- * the target. We should failover to the next path, but in
- * doing so we might be causing a ping-pong between paths.
- * So just return the reservation conflict error.
- */
- case -EOPNOTSUPP:
- case -EREMOTEIO:
- case -EILSEQ:
- case -ENODATA:
- case -ENOSPC:
+ case BLK_STS_NOTSUPP:
+ case BLK_STS_NOSPC:
+ case BLK_STS_TARGET:
+ case BLK_STS_NEXUS:
+ case BLK_STS_MEDIUM:
+ case BLK_STS_RESOURCE:
return 1;
}
@@ -1466,7 +1467,7 @@ static int noretry_error(int error)
}
static int multipath_end_io(struct dm_target *ti, struct request *clone,
- int error, union map_info *map_context)
+ blk_status_t error, union map_info *map_context)
{
struct dm_mpath_io *mpio = get_mpio(map_context);
struct pgpath *pgpath = mpio->pgpath;
@@ -1493,7 +1494,7 @@ static int multipath_end_io(struct dm_target *ti, struct request *clone,
if (atomic_read(&m->nr_valid_paths) == 0 &&
!test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags)) {
- if (error == -EIO)
+ if (error == BLK_STS_IOERR)
dm_report_EIO(m);
/* complete with the original error */
r = DM_ENDIO_DONE;
@@ -1510,24 +1511,26 @@ static int multipath_end_io(struct dm_target *ti, struct request *clone,
return r;
}
-static int do_end_io_bio(struct multipath *m, struct bio *clone,
- int error, struct dm_mpath_io *mpio)
+static int multipath_end_io_bio(struct dm_target *ti, struct bio *clone,
+ blk_status_t *error)
{
+ struct multipath *m = ti->private;
+ struct dm_mpath_io *mpio = get_mpio_from_bio(clone);
+ struct pgpath *pgpath = mpio->pgpath;
unsigned long flags;
+ int r = DM_ENDIO_DONE;
- if (!error)
- return 0; /* I/O complete */
-
- if (noretry_error(error))
- return error;
+ if (!*error || noretry_error(*error))
+ goto done;
- if (mpio->pgpath)
- fail_path(mpio->pgpath);
+ if (pgpath)
+ fail_path(pgpath);
if (atomic_read(&m->nr_valid_paths) == 0 &&
!test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags)) {
dm_report_EIO(m);
- return -EIO;
+ *error = BLK_STS_IOERR;
+ goto done;
}
/* Queue for the daemon to resubmit */
@@ -1539,23 +1542,11 @@ static int do_end_io_bio(struct multipath *m, struct bio *clone,
if (!test_bit(MPATHF_QUEUE_IO, &m->flags))
queue_work(kmultipathd, &m->process_queued_bios);
- return DM_ENDIO_INCOMPLETE;
-}
-
-static int multipath_end_io_bio(struct dm_target *ti, struct bio *clone, int error)
-{
- struct multipath *m = ti->private;
- struct dm_mpath_io *mpio = get_mpio_from_bio(clone);
- struct pgpath *pgpath;
- struct path_selector *ps;
- int r;
-
- BUG_ON(!mpio);
-
- r = do_end_io_bio(m, clone, error, mpio);
- pgpath = mpio->pgpath;
+ r = DM_ENDIO_INCOMPLETE;
+done:
if (pgpath) {
- ps = &pgpath->pg->ps;
+ struct path_selector *ps = &pgpath->pg->ps;
+
if (ps->type->end_io)
ps->type->end_io(ps, &pgpath->path, mpio->nr_bytes);
}
diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c
index 4da8858856fb..f30d8e8e9bbf 100644
--- a/drivers/md/dm-raid1.c
+++ b/drivers/md/dm-raid1.c
@@ -491,9 +491,9 @@ static void hold_bio(struct mirror_set *ms, struct bio *bio)
* If device is suspended, complete the bio.
*/
if (dm_noflush_suspending(ms->ti))
- bio->bi_error = DM_ENDIO_REQUEUE;
+ bio->bi_status = BLK_STS_DM_REQUEUE;
else
- bio->bi_error = -EIO;
+ bio->bi_status = BLK_STS_IOERR;
bio_endio(bio);
return;
@@ -627,7 +627,7 @@ static void write_callback(unsigned long error, void *context)
* degrade the array.
*/
if (bio_op(bio) == REQ_OP_DISCARD) {
- bio->bi_error = -EOPNOTSUPP;
+ bio->bi_status = BLK_STS_NOTSUPP;
bio_endio(bio);
return;
}
@@ -1210,14 +1210,14 @@ static int mirror_map(struct dm_target *ti, struct bio *bio)
r = log->type->in_sync(log, dm_rh_bio_to_region(ms->rh, bio), 0);
if (r < 0 && r != -EWOULDBLOCK)
- return r;
+ return DM_MAPIO_KILL;
/*
* If region is not in-sync queue the bio.
*/
if (!r || (r == -EWOULDBLOCK)) {
if (bio->bi_opf & REQ_RAHEAD)
- return -EWOULDBLOCK;
+ return DM_MAPIO_KILL;
queue_bio(ms, bio, rw);
return DM_MAPIO_SUBMITTED;
@@ -1229,7 +1229,7 @@ static int mirror_map(struct dm_target *ti, struct bio *bio)
*/
m = choose_mirror(ms, bio->bi_iter.bi_sector);
if (unlikely(!m))
- return -EIO;
+ return DM_MAPIO_KILL;
dm_bio_record(&bio_record->details, bio);
bio_record->m = m;
@@ -1239,7 +1239,8 @@ static int mirror_map(struct dm_target *ti, struct bio *bio)
return DM_MAPIO_REMAPPED;
}
-static int mirror_end_io(struct dm_target *ti, struct bio *bio, int error)
+static int mirror_end_io(struct dm_target *ti, struct bio *bio,
+ blk_status_t *error)
{
int rw = bio_data_dir(bio);
struct mirror_set *ms = (struct mirror_set *) ti->private;
@@ -1255,16 +1256,16 @@ static int mirror_end_io(struct dm_target *ti, struct bio *bio, int error)
if (!(bio->bi_opf & REQ_PREFLUSH) &&
bio_op(bio) != REQ_OP_DISCARD)
dm_rh_dec(ms->rh, bio_record->write_region);
- return error;
+ return DM_ENDIO_DONE;
}
- if (error == -EOPNOTSUPP)
+ if (*error == BLK_STS_NOTSUPP)
goto out;
- if ((error == -EWOULDBLOCK) && (bio->bi_opf & REQ_RAHEAD))
+ if (bio->bi_opf & REQ_RAHEAD)
goto out;
- if (unlikely(error)) {
+ if (unlikely(*error)) {
if (!bio_record->details.bi_bdev) {
/*
* There wasn't enough memory to record necessary
@@ -1272,7 +1273,7 @@ static int mirror_end_io(struct dm_target *ti, struct bio *bio, int error)
* mirror in-sync.
*/
DMERR_LIMIT("Mirror read failed.");
- return -EIO;
+ goto out;
}
m = bio_record->m;
@@ -1291,7 +1292,7 @@ static int mirror_end_io(struct dm_target *ti, struct bio *bio, int error)
dm_bio_restore(bd, bio);
bio_record->details.bi_bdev = NULL;
- bio->bi_error = 0;
+ bio->bi_status = 0;
queue_bio(ms, bio, rw);
return DM_ENDIO_INCOMPLETE;
@@ -1302,7 +1303,7 @@ static int mirror_end_io(struct dm_target *ti, struct bio *bio, int error)
out:
bio_record->details.bi_bdev = NULL;
- return error;
+ return DM_ENDIO_DONE;
}
static void mirror_presuspend(struct dm_target *ti)
diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c
index b639fa7246ee..c6ebc5b1e00e 100644
--- a/drivers/md/dm-rq.c
+++ b/drivers/md/dm-rq.c
@@ -71,7 +71,7 @@ static void dm_old_start_queue(struct request_queue *q)
static void dm_mq_start_queue(struct request_queue *q)
{
- blk_mq_start_stopped_hw_queues(q, true);
+ blk_mq_unquiesce_queue(q);
blk_mq_kick_requeue_list(q);
}
@@ -119,7 +119,7 @@ static void end_clone_bio(struct bio *clone)
struct dm_rq_target_io *tio = info->tio;
struct bio *bio = info->orig;
unsigned int nr_bytes = info->orig->bi_iter.bi_size;
- int error = clone->bi_error;
+ blk_status_t error = clone->bi_status;
bio_put(clone);
@@ -158,7 +158,7 @@ static void end_clone_bio(struct bio *clone)
* Do not use blk_end_request() here, because it may complete
* the original request before the clone, and break the ordering.
*/
- blk_update_request(tio->orig, 0, nr_bytes);
+ blk_update_request(tio->orig, BLK_STS_OK, nr_bytes);
}
static struct dm_rq_target_io *tio_from_request(struct request *rq)
@@ -216,7 +216,7 @@ static void rq_completed(struct mapped_device *md, int rw, bool run_queue)
* Must be called without clone's queue lock held,
* see end_clone_request() for more details.
*/
-static void dm_end_request(struct request *clone, int error)
+static void dm_end_request(struct request *clone, blk_status_t error)
{
int rw = rq_data_dir(clone);
struct dm_rq_target_io *tio = clone->end_io_data;
@@ -285,7 +285,7 @@ static void dm_requeue_original_request(struct dm_rq_target_io *tio, bool delay_
rq_completed(md, rw, false);
}
-static void dm_done(struct request *clone, int error, bool mapped)
+static void dm_done(struct request *clone, blk_status_t error, bool mapped)
{
int r = DM_ENDIO_DONE;
struct dm_rq_target_io *tio = clone->end_io_data;
@@ -298,7 +298,7 @@ static void dm_done(struct request *clone, int error, bool mapped)
r = rq_end_io(tio->ti, clone, error, &tio->info);
}
- if (unlikely(error == -EREMOTEIO)) {
+ if (unlikely(error == BLK_STS_TARGET)) {
if (req_op(clone) == REQ_OP_WRITE_SAME &&
!clone->q->limits.max_write_same_sectors)
disable_write_same(tio->md);
@@ -358,7 +358,7 @@ static void dm_softirq_done(struct request *rq)
* Complete the clone and the original request with the error status
* through softirq context.
*/
-static void dm_complete_request(struct request *rq, int error)
+static void dm_complete_request(struct request *rq, blk_status_t error)
{
struct dm_rq_target_io *tio = tio_from_request(rq);
@@ -375,7 +375,7 @@ static void dm_complete_request(struct request *rq, int error)
* Target's rq_end_io() function isn't called.
* This may be used when the target's map_rq() or clone_and_map_rq() functions fail.
*/
-static void dm_kill_unmapped_request(struct request *rq, int error)
+static void dm_kill_unmapped_request(struct request *rq, blk_status_t error)
{
rq->rq_flags |= RQF_FAILED;
dm_complete_request(rq, error);
@@ -384,7 +384,7 @@ static void dm_kill_unmapped_request(struct request *rq, int error)
/*
* Called with the clone's queue lock held (in the case of .request_fn)
*/
-static void end_clone_request(struct request *clone, int error)
+static void end_clone_request(struct request *clone, blk_status_t error)
{
struct dm_rq_target_io *tio = clone->end_io_data;
@@ -401,7 +401,7 @@ static void end_clone_request(struct request *clone, int error)
static void dm_dispatch_clone_request(struct request *clone, struct request *rq)
{
- int r;
+ blk_status_t r;
if (blk_queue_io_stat(clone->q))
clone->rq_flags |= RQF_IO_STAT;
@@ -506,7 +506,7 @@ static int map_request(struct dm_rq_target_io *tio)
break;
case DM_MAPIO_KILL:
/* The target wants to complete the I/O */
- dm_kill_unmapped_request(rq, -EIO);
+ dm_kill_unmapped_request(rq, BLK_STS_IOERR);
break;
default:
DMWARN("unimplemented target map return value: %d", r);
@@ -727,7 +727,7 @@ static int dm_mq_init_request(struct blk_mq_tag_set *set, struct request *rq,
return __dm_rq_init_rq(set->driver_data, rq);
}
-static int dm_mq_queue_rq(struct blk_mq_hw_ctx *hctx,
+static blk_status_t dm_mq_queue_rq(struct blk_mq_hw_ctx *hctx,
const struct blk_mq_queue_data *bd)
{
struct request *rq = bd->rq;
@@ -744,7 +744,7 @@ static int dm_mq_queue_rq(struct blk_mq_hw_ctx *hctx,
}
if (ti->type->busy && ti->type->busy(ti))
- return BLK_MQ_RQ_QUEUE_BUSY;
+ return BLK_STS_RESOURCE;
dm_start_request(md, rq);
@@ -762,10 +762,10 @@ static int dm_mq_queue_rq(struct blk_mq_hw_ctx *hctx,
rq_end_stats(md, rq);
rq_completed(md, rq_data_dir(rq), false);
blk_mq_delay_run_hw_queue(hctx, 100/*ms*/);
- return BLK_MQ_RQ_QUEUE_BUSY;
+ return BLK_STS_RESOURCE;
}
- return BLK_MQ_RQ_QUEUE_OK;
+ return BLK_STS_OK;
}
static const struct blk_mq_ops dm_mq_ops = {
diff --git a/drivers/md/dm-rq.h b/drivers/md/dm-rq.h
index f0020d21b95f..9813922e4fe5 100644
--- a/drivers/md/dm-rq.h
+++ b/drivers/md/dm-rq.h
@@ -24,7 +24,7 @@ struct dm_rq_target_io {
struct dm_target *ti;
struct request *orig, *clone;
struct kthread_work work;
- int error;
+ blk_status_t error;
union map_info info;
struct dm_stats_aux stats_aux;
unsigned long duration_jiffies;
diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c
index e152d9817c81..1ba41048b438 100644
--- a/drivers/md/dm-snap.c
+++ b/drivers/md/dm-snap.c
@@ -1590,7 +1590,7 @@ static void full_bio_end_io(struct bio *bio)
{
void *callback_data = bio->bi_private;
- dm_kcopyd_do_callback(callback_data, 0, bio->bi_error ? 1 : 0);
+ dm_kcopyd_do_callback(callback_data, 0, bio->bi_status ? 1 : 0);
}
static void start_full_bio(struct dm_snap_pending_exception *pe,
@@ -1690,7 +1690,7 @@ static int snapshot_map(struct dm_target *ti, struct bio *bio)
/* Full snapshots are not usable */
/* To get here the table must be live so s->active is always set. */
if (!s->valid)
- return -EIO;
+ return DM_MAPIO_KILL;
/* FIXME: should only take write lock if we need
* to copy an exception */
@@ -1698,7 +1698,7 @@ static int snapshot_map(struct dm_target *ti, struct bio *bio)
if (!s->valid || (unlikely(s->snapshot_overflowed) &&
bio_data_dir(bio) == WRITE)) {
- r = -EIO;
+ r = DM_MAPIO_KILL;
goto out_unlock;
}
@@ -1723,7 +1723,7 @@ static int snapshot_map(struct dm_target *ti, struct bio *bio)
if (!s->valid || s->snapshot_overflowed) {
free_pending_exception(pe);
- r = -EIO;
+ r = DM_MAPIO_KILL;
goto out_unlock;
}
@@ -1741,7 +1741,7 @@ static int snapshot_map(struct dm_target *ti, struct bio *bio)
DMERR("Snapshot overflowed: Unable to allocate exception.");
} else
__invalidate_snapshot(s, -ENOMEM);
- r = -EIO;
+ r = DM_MAPIO_KILL;
goto out_unlock;
}
}
@@ -1851,14 +1851,15 @@ out_unlock:
return r;
}
-static int snapshot_end_io(struct dm_target *ti, struct bio *bio, int error)
+static int snapshot_end_io(struct dm_target *ti, struct bio *bio,
+ blk_status_t *error)
{
struct dm_snapshot *s = ti->private;
if (is_bio_tracked(bio))
stop_tracking_chunk(s, bio);
- return 0;
+ return DM_ENDIO_DONE;
}
static void snapshot_merge_presuspend(struct dm_target *ti)
diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c
index 75152482f3ad..11621a0af887 100644
--- a/drivers/md/dm-stripe.c
+++ b/drivers/md/dm-stripe.c
@@ -375,20 +375,21 @@ static void stripe_status(struct dm_target *ti, status_type_t type,
}
}
-static int stripe_end_io(struct dm_target *ti, struct bio *bio, int error)
+static int stripe_end_io(struct dm_target *ti, struct bio *bio,
+ blk_status_t *error)
{
unsigned i;
char major_minor[16];
struct stripe_c *sc = ti->private;
- if (!error)
- return 0; /* I/O complete */
+ if (!*error)
+ return DM_ENDIO_DONE; /* I/O complete */
- if ((error == -EWOULDBLOCK) && (bio->bi_opf & REQ_RAHEAD))
- return error;
+ if (bio->bi_opf & REQ_RAHEAD)
+ return DM_ENDIO_DONE;
- if (error == -EOPNOTSUPP)
- return error;
+ if (*error == BLK_STS_NOTSUPP)
+ return DM_ENDIO_DONE;
memset(major_minor, 0, sizeof(major_minor));
sprintf(major_minor, "%d:%d",
@@ -409,7 +410,7 @@ static int stripe_end_io(struct dm_target *ti, struct bio *bio, int error)
schedule_work(&sc->trigger_event);
}
- return error;
+ return DM_ENDIO_DONE;
}
static int stripe_iterate_devices(struct dm_target *ti,
diff --git a/drivers/md/dm-target.c b/drivers/md/dm-target.c
index b242b750542f..c0d7e60820c4 100644
--- a/drivers/md/dm-target.c
+++ b/drivers/md/dm-target.c
@@ -128,7 +128,7 @@ static void io_err_dtr(struct dm_target *tt)
static int io_err_map(struct dm_target *tt, struct bio *bio)
{
- return -EIO;
+ return DM_MAPIO_KILL;
}
static int io_err_clone_and_map_rq(struct dm_target *ti, struct request *rq,
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index 28808e5ec0fd..9dec2f8cc739 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -383,8 +383,8 @@ static void end_discard(struct discard_op *op, int r)
* Even if r is set, there could be sub discards in flight that we
* need to wait for.
*/
- if (r && !op->parent_bio->bi_error)
- op->parent_bio->bi_error = r;
+ if (r && !op->parent_bio->bi_status)
+ op->parent_bio->bi_status = errno_to_blk_status(r);
bio_endio(op->parent_bio);
}
@@ -450,22 +450,20 @@ static void cell_release_no_holder(struct pool *pool,
}
static void cell_error_with_code(struct pool *pool,
- struct dm_bio_prison_cell *cell, int error_code)
+ struct dm_bio_prison_cell *cell, blk_status_t error_code)
{
dm_cell_error(pool->prison, cell, error_code);
dm_bio_prison_free_cell(pool->prison, cell);
}
-static int get_pool_io_error_code(struct pool *pool)
+static blk_status_t get_pool_io_error_code(struct pool *pool)
{
- return pool->out_of_data_space ? -ENOSPC : -EIO;
+ return pool->out_of_data_space ? BLK_STS_NOSPC : BLK_STS_IOERR;
}
static void cell_error(struct pool *pool, struct dm_bio_prison_cell *cell)
{
- int error = get_pool_io_error_code(pool);
-
- cell_error_with_code(pool, cell, error);
+ cell_error_with_code(pool, cell, get_pool_io_error_code(pool));
}
static void cell_success(struct pool *pool, struct dm_bio_prison_cell *cell)
@@ -475,7 +473,7 @@ static void cell_success(struct pool *pool, struct dm_bio_prison_cell *cell)
static void cell_requeue(struct pool *pool, struct dm_bio_prison_cell *cell)
{
- cell_error_with_code(pool, cell, DM_ENDIO_REQUEUE);
+ cell_error_with_code(pool, cell, BLK_STS_DM_REQUEUE);
}
/*----------------------------------------------------------------*/
@@ -555,17 +553,18 @@ static void __merge_bio_list(struct bio_list *bios, struct bio_list *master)
bio_list_init(master);
}
-static void error_bio_list(struct bio_list *bios, int error)
+static void error_bio_list(struct bio_list *bios, blk_status_t error)
{
struct bio *bio;
while ((bio = bio_list_pop(bios))) {
- bio->bi_error = error;
+ bio->bi_status = error;
bio_endio(bio);
}
}
-static void error_thin_bio_list(struct thin_c *tc, struct bio_list *master, int error)
+static void error_thin_bio_list(struct thin_c *tc, struct bio_list *master,
+ blk_status_t error)
{
struct bio_list bios;
unsigned long flags;
@@ -608,11 +607,11 @@ static void requeue_io(struct thin_c *tc)
__merge_bio_list(&bios, &tc->retry_on_resume_list);
spin_unlock_irqrestore(&tc->lock, flags);
- error_bio_list(&bios, DM_ENDIO_REQUEUE);
+ error_bio_list(&bios, BLK_STS_DM_REQUEUE);
requeue_deferred_cells(tc);
}
-static void error_retry_list_with_code(struct pool *pool, int error)
+static void error_retry_list_with_code(struct pool *pool, blk_status_t error)
{
struct thin_c *tc;
@@ -624,9 +623,7 @@ static void error_retry_list_with_code(struct pool *pool, int error)
static void error_retry_list(struct pool *pool)
{
- int error = get_pool_io_error_code(pool);
-
- error_retry_list_with_code(pool, error);
+ error_retry_list_with_code(pool, get_pool_io_error_code(pool));
}
/*
@@ -774,7 +771,7 @@ struct dm_thin_new_mapping {
*/
atomic_t prepare_actions;
- int err;
+ blk_status_t status;
struct thin_c *tc;
dm_block_t virt_begin, virt_end;
dm_block_t data_block;
@@ -814,7 +811,7 @@ static void copy_complete(int read_err, unsigned long write_err, void *context)
{
struct dm_thin_new_mapping *m = context;
- m->err = read_err || write_err ? -EIO : 0;
+ m->status = read_err || write_err ? BLK_STS_IOERR : 0;
complete_mapping_preparation(m);
}
@@ -825,7 +822,7 @@ static void overwrite_endio(struct bio *bio)
bio->bi_end_io = m->saved_bi_end_io;
- m->err = bio->bi_error;
+ m->status = bio->bi_status;
complete_mapping_preparation(m);
}
@@ -925,7 +922,7 @@ static void process_prepared_mapping(struct dm_thin_new_mapping *m)
struct bio *bio = m->bio;
int r;
- if (m->err) {
+ if (m->status) {
cell_error(pool, m->cell);
goto out;
}
@@ -1495,7 +1492,7 @@ static void retry_on_resume(struct bio *bio)
spin_unlock_irqrestore(&tc->lock, flags);
}
-static int should_error_unserviceable_bio(struct pool *pool)
+static blk_status_t should_error_unserviceable_bio(struct pool *pool)
{
enum pool_mode m = get_pool_mode(pool);
@@ -1503,27 +1500,27 @@ static int should_error_unserviceable_bio(struct pool *pool)
case PM_WRITE:
/* Shouldn't get here */
DMERR_LIMIT("bio unserviceable, yet pool is in PM_WRITE mode");
- return -EIO;
+ return BLK_STS_IOERR;
case PM_OUT_OF_DATA_SPACE:
- return pool->pf.error_if_no_space ? -ENOSPC : 0;
+ return pool->pf.error_if_no_space ? BLK_STS_NOSPC : 0;
case PM_READ_ONLY:
case PM_FAIL:
- return -EIO;
+ return BLK_STS_IOERR;
default:
/* Shouldn't get here */
DMERR_LIMIT("bio unserviceable, yet pool has an unknown mode");
- return -EIO;
+ return BLK_STS_IOERR;
}
}
static void handle_unserviceable_bio(struct pool *pool, struct bio *bio)
{
- int error = should_error_unserviceable_bio(pool);
+ blk_status_t error = should_error_unserviceable_bio(pool);
if (error) {
- bio->bi_error = error;
+ bio->bi_status = error;
bio_endio(bio);
} else
retry_on_resume(bio);
@@ -1533,7 +1530,7 @@ static void retry_bios_on_resume(struct pool *pool, struct dm_bio_prison_cell *c
{
struct bio *bio;
struct bio_list bios;
- int error;
+ blk_status_t error;
error = should_error_unserviceable_bio(pool);
if (error) {
@@ -2071,7 +2068,8 @@ static void process_thin_deferred_bios(struct thin_c *tc)
unsigned count = 0;
if (tc->requeue_mode) {
- error_thin_bio_list(tc, &tc->deferred_bio_list, DM_ENDIO_REQUEUE);
+ error_thin_bio_list(tc, &tc->deferred_bio_list,
+ BLK_STS_DM_REQUEUE);
return;
}
@@ -2322,7 +2320,7 @@ static void do_no_space_timeout(struct work_struct *ws)
if (get_pool_mode(pool) == PM_OUT_OF_DATA_SPACE && !pool->pf.error_if_no_space) {
pool->pf.error_if_no_space = true;
notify_of_pool_mode_change_to_oods(pool);
- error_retry_list_with_code(pool, -ENOSPC);
+ error_retry_list_with_code(pool, BLK_STS_NOSPC);
}
}
@@ -2624,7 +2622,7 @@ static int thin_bio_map(struct dm_target *ti, struct bio *bio)
thin_hook_bio(tc, bio);
if (tc->requeue_mode) {
- bio->bi_error = DM_ENDIO_REQUEUE;
+ bio->bi_status = BLK_STS_DM_REQUEUE;
bio_endio(bio);
return DM_MAPIO_SUBMITTED;
}
@@ -4177,7 +4175,8 @@ static int thin_map(struct dm_target *ti, struct bio *bio)
return thin_bio_map(ti, bio);
}
-static int thin_endio(struct dm_target *ti, struct bio *bio, int err)
+static int thin_endio(struct dm_target *ti, struct bio *bio,
+ blk_status_t *err)
{
unsigned long flags;
struct dm_thin_endio_hook *h = dm_per_bio_data(bio, sizeof(struct dm_thin_endio_hook));
@@ -4212,7 +4211,7 @@ static int thin_endio(struct dm_target *ti, struct bio *bio, int err)
if (h->cell)
cell_defer_no_holder(h->tc, h->cell);
- return 0;
+ return DM_ENDIO_DONE;
}
static void thin_presuspend(struct dm_target *ti)
diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c
index 1ec9b2c51c07..b46705ebf01f 100644
--- a/drivers/md/dm-verity-target.c
+++ b/drivers/md/dm-verity-target.c
@@ -538,13 +538,13 @@ static int verity_verify_io(struct dm_verity_io *io)
/*
* End one "io" structure with a given error.
*/
-static void verity_finish_io(struct dm_verity_io *io, int error)
+static void verity_finish_io(struct dm_verity_io *io, blk_status_t status)
{
struct dm_verity *v = io->v;
struct bio *bio = dm_bio_from_per_bio_data(io, v->ti->per_io_data_size);
bio->bi_end_io = io->orig_bi_end_io;
- bio->bi_error = error;
+ bio->bi_status = status;
verity_fec_finish_io(io);
@@ -555,15 +555,15 @@ static void verity_work(struct work_struct *w)
{
struct dm_verity_io *io = container_of(w, struct dm_verity_io, work);
- verity_finish_io(io, verity_verify_io(io));
+ verity_finish_io(io, errno_to_blk_status(verity_verify_io(io)));
}
static void verity_end_io(struct bio *bio)
{
struct dm_verity_io *io = bio->bi_private;
- if (bio->bi_error && !verity_fec_is_enabled(io->v)) {
- verity_finish_io(io, bio->bi_error);
+ if (bio->bi_status && !verity_fec_is_enabled(io->v)) {
+ verity_finish_io(io, bio->bi_status);
return;
}
@@ -643,17 +643,17 @@ static int verity_map(struct dm_target *ti, struct bio *bio)
if (((unsigned)bio->bi_iter.bi_sector | bio_sectors(bio)) &
((1 << (v->data_dev_block_bits - SECTOR_SHIFT)) - 1)) {
DMERR_LIMIT("unaligned io");
- return -EIO;
+ return DM_MAPIO_KILL;
}
if (bio_end_sector(bio) >>
(v->data_dev_block_bits - SECTOR_SHIFT) > v->data_blocks) {
DMERR_LIMIT("io out of range");
- return -EIO;
+ return DM_MAPIO_KILL;
}
if (bio_data_dir(bio) == WRITE)
- return -EIO;
+ return DM_MAPIO_KILL;
io = dm_per_bio_data(bio, ti->per_io_data_size);
io->v = v;
diff --git a/drivers/md/dm-zero.c b/drivers/md/dm-zero.c
index b616f11d8473..b65ca8dcfbdc 100644
--- a/drivers/md/dm-zero.c
+++ b/drivers/md/dm-zero.c
@@ -39,7 +39,7 @@ static int zero_map(struct dm_target *ti, struct bio *bio)
case REQ_OP_READ:
if (bio->bi_opf & REQ_RAHEAD) {
/* readahead of null bytes only wastes buffer cache */
- return -EIO;
+ return DM_MAPIO_KILL;
}
zero_fill_bio(bio);
break;
@@ -47,7 +47,7 @@ static int zero_map(struct dm_target *ti, struct bio *bio)
/* writes get silently dropped */
break;
default:
- return -EIO;
+ return DM_MAPIO_KILL;
}
bio_endio(bio);
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 37ccd73c79ec..402946035308 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -63,7 +63,7 @@ static struct workqueue_struct *deferred_remove_workqueue;
*/
struct dm_io {
struct mapped_device *md;
- int error;
+ blk_status_t status;
atomic_t io_count;
struct bio *bio;
unsigned long start_time;
@@ -768,23 +768,24 @@ static int __noflush_suspending(struct mapped_device *md)
* Decrements the number of outstanding ios that a bio has been
* cloned into, completing the original io if necc.
*/
-static void dec_pending(struct dm_io *io, int error)
+static void dec_pending(struct dm_io *io, blk_status_t error)
{
unsigned long flags;
- int io_error;
+ blk_status_t io_error;
struct bio *bio;
struct mapped_device *md = io->md;
/* Push-back supersedes any I/O errors */
if (unlikely(error)) {
spin_lock_irqsave(&io->endio_lock, flags);
- if (!(io->error > 0 && __noflush_suspending(md)))
- io->error = error;
+ if (!(io->status == BLK_STS_DM_REQUEUE &&
+ __noflush_suspending(md)))
+ io->status = error;
spin_unlock_irqrestore(&io->endio_lock, flags);
}
if (atomic_dec_and_test(&io->io_count)) {
- if (io->error == DM_ENDIO_REQUEUE) {
+ if (io->status == BLK_STS_DM_REQUEUE) {
/*
* Target requested pushing back the I/O.
*/
@@ -793,16 +794,16 @@ static void dec_pending(struct dm_io *io, int error)
bio_list_add_head(&md->deferred, io->bio);
else
/* noflush suspend was interrupted. */
- io->error = -EIO;
+ io->status = BLK_STS_IOERR;
spin_unlock_irqrestore(&md->deferred_lock, flags);
}
- io_error = io->error;
+ io_error = io->status;
bio = io->bio;
end_io_acct(io);
free_io(md, io);
- if (io_error == DM_ENDIO_REQUEUE)
+ if (io_error == BLK_STS_DM_REQUEUE)
return;
if ((bio->bi_opf & REQ_PREFLUSH) && bio->bi_iter.bi_size) {
@@ -814,7 +815,7 @@ static void dec_pending(struct dm_io *io, int error)
queue_io(md, bio);
} else {
/* done with normal IO or empty flush */
- bio->bi_error = io_error;
+ bio->bi_status = io_error;
bio_endio(bio);
}
}
@@ -838,31 +839,13 @@ void disable_write_zeroes(struct mapped_device *md)
static void clone_endio(struct bio *bio)
{
- int error = bio->bi_error;
- int r = error;
+ blk_status_t error = bio->bi_status;
struct dm_target_io *tio = container_of(bio, struct dm_target_io, clone);
struct dm_io *io = tio->io;
struct mapped_device *md = tio->io->md;
dm_endio_fn endio = tio->ti->type->end_io;
- if (endio) {
- r = endio(tio->ti, bio, error);
- if (r < 0 || r == DM_ENDIO_REQUEUE)
- /*
- * error and requeue request are handled
- * in dec_pending().
- */
- error = r;
- else if (r == DM_ENDIO_INCOMPLETE)
- /* The target will handle the io */
- return;
- else if (r) {
- DMWARN("unimplemented target endio return value: %d", r);
- BUG();
- }
- }
-
- if (unlikely(r == -EREMOTEIO)) {
+ if (unlikely(error == BLK_STS_TARGET)) {
if (bio_op(bio) == REQ_OP_WRITE_SAME &&
!bdev_get_queue(bio->bi_bdev)->limits.max_write_same_sectors)
disable_write_same(md);
@@ -871,6 +854,23 @@ static void clone_endio(struct bio *bio)
disable_write_zeroes(md);
}
+ if (endio) {
+ int r = endio(tio->ti, bio, &error);
+ switch (r) {
+ case DM_ENDIO_REQUEUE:
+ error = BLK_STS_DM_REQUEUE;
+ /*FALLTHRU*/
+ case DM_ENDIO_DONE:
+ break;
+ case DM_ENDIO_INCOMPLETE:
+ /* The target will handle the io */
+ return;
+ default:
+ DMWARN("unimplemented target endio return value: %d", r);
+ BUG();
+ }
+ }
+
free_tio(tio);
dec_pending(io, error);
}
@@ -1036,7 +1036,8 @@ static void flush_current_bio_list(struct blk_plug_cb *cb, bool from_schedule)
while ((bio = bio_list_pop(&list))) {
struct bio_set *bs = bio->bi_pool;
- if (unlikely(!bs) || bs == fs_bio_set) {
+ if (unlikely(!bs) || bs == fs_bio_set ||
+ !bs->rescue_workqueue) {
bio_list_add(&current->bio_list[i], bio);
continue;
}
@@ -1084,18 +1085,24 @@ static void __map_bio(struct dm_target_io *tio)
r = ti->type->map(ti, clone);
dm_offload_end(&o);
- if (r == DM_MAPIO_REMAPPED) {
+ switch (r) {
+ case DM_MAPIO_SUBMITTED:
+ break;
+ case DM_MAPIO_REMAPPED:
/* the bio has been remapped so dispatch it */
-
trace_block_bio_remap(bdev_get_queue(clone->bi_bdev), clone,
tio->io->bio->bi_bdev->bd_dev, sector);
-
generic_make_request(clone);
- } else if (r < 0 || r == DM_MAPIO_REQUEUE) {
- /* error the io and bail out, or requeue it if needed */
- dec_pending(tio->io, r);
+ break;
+ case DM_MAPIO_KILL:
+ dec_pending(tio->io, BLK_STS_IOERR);
+ free_tio(tio);
+ break;
+ case DM_MAPIO_REQUEUE:
+ dec_pending(tio->io, BLK_STS_DM_REQUEUE);
free_tio(tio);
- } else if (r != DM_MAPIO_SUBMITTED) {
+ break;
+ default:
DMWARN("unimplemented target map return value: %d", r);
BUG();
}
@@ -1360,7 +1367,7 @@ static void __split_and_process_bio(struct mapped_device *md,
ci.map = map;
ci.md = md;
ci.io = alloc_io(md);
- ci.io->error = 0;
+ ci.io->status = 0;
atomic_set(&ci.io->io_count, 1);
ci.io->bio = bio;
ci.io->md = md;
@@ -1527,7 +1534,6 @@ void dm_init_normal_md_queue(struct mapped_device *md)
* Initialize aspects of queue that aren't relevant for blk-mq
*/
md->queue->backing_dev_info->congested_fn = dm_any_congested;
- blk_queue_bounce_limit(md->queue, BLK_BOUNCE_ANY);
}
static void cleanup_mapped_device(struct mapped_device *md)
@@ -2654,7 +2660,7 @@ struct dm_md_mempools *dm_alloc_md_mempools(struct mapped_device *md, enum dm_qu
BUG();
}
- pools->bs = bioset_create_nobvec(pool_size, front_pad);
+ pools->bs = bioset_create(pool_size, front_pad, BIOSET_NEED_RESCUER);
if (!pools->bs)
goto out;
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 87edc342ccb3..31bcbfb09fef 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -185,7 +185,7 @@ static int start_readonly;
static bool create_on_open = true;
/* bio_clone_mddev
- * like bio_clone, but with a local bio set
+ * like bio_clone_bioset, but with a local bio set
*/
struct bio *bio_alloc_mddev(gfp_t gfp_mask, int nr_iovecs,
@@ -265,7 +265,7 @@ static blk_qc_t md_make_request(struct request_queue *q, struct bio *bio)
unsigned int sectors;
int cpu;
- blk_queue_split(q, &bio, q->bio_split);
+ blk_queue_split(q, &bio);
if (mddev == NULL || mddev->pers == NULL) {
bio_io_error(bio);
@@ -273,7 +273,7 @@ static blk_qc_t md_make_request(struct request_queue *q, struct bio *bio)
}
if (mddev->ro == 1 && unlikely(rw == WRITE)) {
if (bio_sectors(bio) != 0)
- bio->bi_error = -EROFS;
+ bio->bi_status = BLK_STS_IOERR;
bio_endio(bio);
return BLK_QC_T_NONE;
}
@@ -719,8 +719,8 @@ static void super_written(struct bio *bio)
struct md_rdev *rdev = bio->bi_private;
struct mddev *mddev = rdev->mddev;
- if (bio->bi_error) {
- pr_err("md: super_written gets error=%d\n", bio->bi_error);
+ if (bio->bi_status) {
+ pr_err("md: super_written gets error=%d\n", bio->bi_status);
md_error(mddev, rdev);
if (!test_bit(Faulty, &rdev->flags)
&& (bio->bi_opf & MD_FAILFAST)) {
@@ -801,7 +801,7 @@ int sync_page_io(struct md_rdev *rdev, sector_t sector, int size,
submit_bio_wait(bio);
- ret = !bio->bi_error;
+ ret = !bio->bi_status;
bio_put(bio);
return ret;
}
@@ -825,7 +825,7 @@ fail:
return -EINVAL;
}
-static int uuid_equal(mdp_super_t *sb1, mdp_super_t *sb2)
+static int md_uuid_equal(mdp_super_t *sb1, mdp_super_t *sb2)
{
return sb1->set_uuid0 == sb2->set_uuid0 &&
sb1->set_uuid1 == sb2->set_uuid1 &&
@@ -833,7 +833,7 @@ static int uuid_equal(mdp_super_t *sb1, mdp_super_t *sb2)
sb1->set_uuid3 == sb2->set_uuid3;
}
-static int sb_equal(mdp_super_t *sb1, mdp_super_t *sb2)
+static int md_sb_equal(mdp_super_t *sb1, mdp_super_t *sb2)
{
int ret;
mdp_super_t *tmp1, *tmp2;
@@ -1025,12 +1025,12 @@ static int super_90_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor
} else {
__u64 ev1, ev2;
mdp_super_t *refsb = page_address(refdev->sb_page);
- if (!uuid_equal(refsb, sb)) {
+ if (!md_uuid_equal(refsb, sb)) {
pr_warn("md: %s has different UUID to %s\n",
b, bdevname(refdev->bdev,b2));
goto abort;
}
- if (!sb_equal(refsb, sb)) {
+ if (!md_sb_equal(refsb, sb)) {
pr_warn("md: %s has same UUID but different superblock to %s\n",
b, bdevname(refdev->bdev, b2));
goto abort;
@@ -5428,7 +5428,7 @@ int md_run(struct mddev *mddev)
}
if (mddev->bio_set == NULL) {
- mddev->bio_set = bioset_create(BIO_POOL_SIZE, 0);
+ mddev->bio_set = bioset_create(BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
if (!mddev->bio_set)
return -ENOMEM;
}
diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c
index e95d521d93e9..68d036e64041 100644
--- a/drivers/md/multipath.c
+++ b/drivers/md/multipath.c
@@ -73,12 +73,12 @@ static void multipath_reschedule_retry (struct multipath_bh *mp_bh)
* operation and are ready to return a success/failure code to the buffer
* cache layer.
*/
-static void multipath_end_bh_io (struct multipath_bh *mp_bh, int err)
+static void multipath_end_bh_io(struct multipath_bh *mp_bh, blk_status_t status)
{
struct bio *bio = mp_bh->master_bio;
struct mpconf *conf = mp_bh->mddev->private;
- bio->bi_error = err;
+ bio->bi_status = status;
bio_endio(bio);
mempool_free(mp_bh, conf->pool);
}
@@ -89,7 +89,7 @@ static void multipath_end_request(struct bio *bio)
struct mpconf *conf = mp_bh->mddev->private;
struct md_rdev *rdev = conf->multipaths[mp_bh->path].rdev;
- if (!bio->bi_error)
+ if (!bio->bi_status)
multipath_end_bh_io(mp_bh, 0);
else if (!(bio->bi_opf & REQ_RAHEAD)) {
/*
@@ -102,7 +102,7 @@ static void multipath_end_request(struct bio *bio)
(unsigned long long)bio->bi_iter.bi_sector);
multipath_reschedule_retry(mp_bh);
} else
- multipath_end_bh_io(mp_bh, bio->bi_error);
+ multipath_end_bh_io(mp_bh, bio->bi_status);
rdev_dec_pending(rdev, conf->mddev);
}
@@ -347,7 +347,7 @@ static void multipathd(struct md_thread *thread)
pr_err("multipath: %s: unrecoverable IO read error for block %llu\n",
bdevname(bio->bi_bdev,b),
(unsigned long long)bio->bi_iter.bi_sector);
- multipath_end_bh_io(mp_bh, -EIO);
+ multipath_end_bh_io(mp_bh, BLK_STS_IOERR);
} else {
pr_err("multipath: %s: redirecting sector %llu to another IO path\n",
bdevname(bio->bi_bdev,b),
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index e1a7e3d4c5e4..98ca2c1d3226 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -277,7 +277,7 @@ static void call_bio_endio(struct r1bio *r1_bio)
struct r1conf *conf = r1_bio->mddev->private;
if (!test_bit(R1BIO_Uptodate, &r1_bio->state))
- bio->bi_error = -EIO;
+ bio->bi_status = BLK_STS_IOERR;
bio_endio(bio);
/*
@@ -335,7 +335,7 @@ static int find_bio_disk(struct r1bio *r1_bio, struct bio *bio)
static void raid1_end_read_request(struct bio *bio)
{
- int uptodate = !bio->bi_error;
+ int uptodate = !bio->bi_status;
struct r1bio *r1_bio = bio->bi_private;
struct r1conf *conf = r1_bio->mddev->private;
struct md_rdev *rdev = conf->mirrors[r1_bio->read_disk].rdev;
@@ -426,12 +426,12 @@ static void raid1_end_write_request(struct bio *bio)
struct md_rdev *rdev = conf->mirrors[mirror].rdev;
bool discard_error;
- discard_error = bio->bi_error && bio_op(bio) == REQ_OP_DISCARD;
+ discard_error = bio->bi_status && bio_op(bio) == REQ_OP_DISCARD;
/*
* 'one mirror IO has finished' event handler:
*/
- if (bio->bi_error && !discard_error) {
+ if (bio->bi_status && !discard_error) {
set_bit(WriteErrorSeen, &rdev->flags);
if (!test_and_set_bit(WantReplacement, &rdev->flags))
set_bit(MD_RECOVERY_NEEDED, &
@@ -802,7 +802,7 @@ static void flush_bio_list(struct r1conf *conf, struct bio *bio)
bio->bi_next = NULL;
bio->bi_bdev = rdev->bdev;
if (test_bit(Faulty, &rdev->flags)) {
- bio->bi_error = -EIO;
+ bio->bi_status = BLK_STS_IOERR;
bio_endio(bio);
} else if (unlikely((bio_op(bio) == REQ_OP_DISCARD) &&
!blk_queue_discard(bdev_get_queue(bio->bi_bdev))))
@@ -1856,7 +1856,7 @@ static void end_sync_read(struct bio *bio)
* or re-read if the read failed.
* We don't do much here, just schedule handling by raid1d
*/
- if (!bio->bi_error)
+ if (!bio->bi_status)
set_bit(R1BIO_Uptodate, &r1_bio->state);
if (atomic_dec_and_test(&r1_bio->remaining))
@@ -1865,7 +1865,7 @@ static void end_sync_read(struct bio *bio)
static void end_sync_write(struct bio *bio)
{
- int uptodate = !bio->bi_error;
+ int uptodate = !bio->bi_status;
struct r1bio *r1_bio = get_resync_r1bio(bio);
struct mddev *mddev = r1_bio->mddev;
struct r1conf *conf = mddev->private;
@@ -2058,7 +2058,7 @@ static int fix_sync_read_error(struct r1bio *r1_bio)
idx ++;
}
set_bit(R1BIO_Uptodate, &r1_bio->state);
- bio->bi_error = 0;
+ bio->bi_status = 0;
return 1;
}
@@ -2082,16 +2082,16 @@ static void process_checks(struct r1bio *r1_bio)
for (i = 0; i < conf->raid_disks * 2; i++) {
int j;
int size;
- int error;
+ blk_status_t status;
struct bio_vec *bi;
struct bio *b = r1_bio->bios[i];
struct resync_pages *rp = get_resync_pages(b);
if (b->bi_end_io != end_sync_read)
continue;
/* fixup the bio for reuse, but preserve errno */
- error = b->bi_error;
+ status = b->bi_status;
bio_reset(b);
- b->bi_error = error;
+ b->bi_status = status;
b->bi_vcnt = vcnt;
b->bi_iter.bi_size = r1_bio->sectors << 9;
b->bi_iter.bi_sector = r1_bio->sector +
@@ -2113,7 +2113,7 @@ static void process_checks(struct r1bio *r1_bio)
}
for (primary = 0; primary < conf->raid_disks * 2; primary++)
if (r1_bio->bios[primary]->bi_end_io == end_sync_read &&
- !r1_bio->bios[primary]->bi_error) {
+ !r1_bio->bios[primary]->bi_status) {
r1_bio->bios[primary]->bi_end_io = NULL;
rdev_dec_pending(conf->mirrors[primary].rdev, mddev);
break;
@@ -2123,7 +2123,7 @@ static void process_checks(struct r1bio *r1_bio)
int j;
struct bio *pbio = r1_bio->bios[primary];
struct bio *sbio = r1_bio->bios[i];
- int error = sbio->bi_error;
+ blk_status_t status = sbio->bi_status;
struct page **ppages = get_resync_pages(pbio)->pages;
struct page **spages = get_resync_pages(sbio)->pages;
struct bio_vec *bi;
@@ -2132,12 +2132,12 @@ static void process_checks(struct r1bio *r1_bio)
if (sbio->bi_end_io != end_sync_read)
continue;
/* Now we can 'fixup' the error value */
- sbio->bi_error = 0;
+ sbio->bi_status = 0;
bio_for_each_segment_all(bi, sbio, j)
page_len[j] = bi->bv_len;
- if (!error) {
+ if (!status) {
for (j = vcnt; j-- ; ) {
if (memcmp(page_address(ppages[j]),
page_address(spages[j]),
@@ -2149,7 +2149,7 @@ static void process_checks(struct r1bio *r1_bio)
if (j >= 0)
atomic64_add(r1_bio->sectors, &mddev->resync_mismatches);
if (j < 0 || (test_bit(MD_RECOVERY_CHECK, &mddev->recovery)
- && !error)) {
+ && !status)) {
/* No need to write to this device. */
sbio->bi_end_io = NULL;
rdev_dec_pending(conf->mirrors[i].rdev, mddev);
@@ -2400,11 +2400,11 @@ static void handle_sync_write_finished(struct r1conf *conf, struct r1bio *r1_bio
struct bio *bio = r1_bio->bios[m];
if (bio->bi_end_io == NULL)
continue;
- if (!bio->bi_error &&
+ if (!bio->bi_status &&
test_bit(R1BIO_MadeGood, &r1_bio->state)) {
rdev_clear_badblocks(rdev, r1_bio->sector, s, 0);
}
- if (bio->bi_error &&
+ if (bio->bi_status &&
test_bit(R1BIO_WriteError, &r1_bio->state)) {
if (!rdev_set_badblocks(rdev, r1_bio->sector, s, 0))
md_error(conf->mddev, rdev);
@@ -2955,7 +2955,7 @@ static struct r1conf *setup_conf(struct mddev *mddev)
if (!conf->r1bio_pool)
goto abort;
- conf->bio_split = bioset_create(BIO_POOL_SIZE, 0);
+ conf->bio_split = bioset_create(BIO_POOL_SIZE, 0, 0);
if (!conf->bio_split)
goto abort;
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 797ed60abd5e..57a250fdbbcc 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -336,7 +336,7 @@ static void raid_end_bio_io(struct r10bio *r10_bio)
struct r10conf *conf = r10_bio->mddev->private;
if (!test_bit(R10BIO_Uptodate, &r10_bio->state))
- bio->bi_error = -EIO;
+ bio->bi_status = BLK_STS_IOERR;
bio_endio(bio);
/*
@@ -389,7 +389,7 @@ static int find_bio_disk(struct r10conf *conf, struct r10bio *r10_bio,
static void raid10_end_read_request(struct bio *bio)
{
- int uptodate = !bio->bi_error;
+ int uptodate = !bio->bi_status;
struct r10bio *r10_bio = bio->bi_private;
int slot, dev;
struct md_rdev *rdev;
@@ -477,7 +477,7 @@ static void raid10_end_write_request(struct bio *bio)
struct bio *to_put = NULL;
bool discard_error;
- discard_error = bio->bi_error && bio_op(bio) == REQ_OP_DISCARD;
+ discard_error = bio->bi_status && bio_op(bio) == REQ_OP_DISCARD;
dev = find_bio_disk(conf, r10_bio, bio, &slot, &repl);
@@ -491,7 +491,7 @@ static void raid10_end_write_request(struct bio *bio)
/*
* this branch is our 'one mirror IO has finished' event handler:
*/
- if (bio->bi_error && !discard_error) {
+ if (bio->bi_status && !discard_error) {
if (repl)
/* Never record new bad blocks to replacement,
* just fail it.
@@ -913,7 +913,7 @@ static void flush_pending_writes(struct r10conf *conf)
bio->bi_next = NULL;
bio->bi_bdev = rdev->bdev;
if (test_bit(Faulty, &rdev->flags)) {
- bio->bi_error = -EIO;
+ bio->bi_status = BLK_STS_IOERR;
bio_endio(bio);
} else if (unlikely((bio_op(bio) == REQ_OP_DISCARD) &&
!blk_queue_discard(bdev_get_queue(bio->bi_bdev))))
@@ -1098,7 +1098,7 @@ static void raid10_unplug(struct blk_plug_cb *cb, bool from_schedule)
bio->bi_next = NULL;
bio->bi_bdev = rdev->bdev;
if (test_bit(Faulty, &rdev->flags)) {
- bio->bi_error = -EIO;
+ bio->bi_status = BLK_STS_IOERR;
bio_endio(bio);
} else if (unlikely((bio_op(bio) == REQ_OP_DISCARD) &&
!blk_queue_discard(bdev_get_queue(bio->bi_bdev))))
@@ -1888,7 +1888,7 @@ static void __end_sync_read(struct r10bio *r10_bio, struct bio *bio, int d)
{
struct r10conf *conf = r10_bio->mddev->private;
- if (!bio->bi_error)
+ if (!bio->bi_status)
set_bit(R10BIO_Uptodate, &r10_bio->state);
else
/* The write handler will notice the lack of
@@ -1972,7 +1972,7 @@ static void end_sync_write(struct bio *bio)
else
rdev = conf->mirrors[d].rdev;
- if (bio->bi_error) {
+ if (bio->bi_status) {
if (repl)
md_error(mddev, rdev);
else {
@@ -2021,7 +2021,7 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio)
/* find the first device with a block */
for (i=0; i<conf->copies; i++)
- if (!r10_bio->devs[i].bio->bi_error)
+ if (!r10_bio->devs[i].bio->bi_status)
break;
if (i == conf->copies)
@@ -2050,7 +2050,7 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio)
tpages = get_resync_pages(tbio)->pages;
d = r10_bio->devs[i].devnum;
rdev = conf->mirrors[d].rdev;
- if (!r10_bio->devs[i].bio->bi_error) {
+ if (!r10_bio->devs[i].bio->bi_status) {
/* We know that the bi_io_vec layout is the same for
* both 'first' and 'i', so we just compare them.
* All vec entries are PAGE_SIZE;
@@ -2633,7 +2633,7 @@ static void handle_write_completed(struct r10conf *conf, struct r10bio *r10_bio)
rdev = conf->mirrors[dev].rdev;
if (r10_bio->devs[m].bio == NULL)
continue;
- if (!r10_bio->devs[m].bio->bi_error) {
+ if (!r10_bio->devs[m].bio->bi_status) {
rdev_clear_badblocks(
rdev,
r10_bio->devs[m].addr,
@@ -2649,7 +2649,7 @@ static void handle_write_completed(struct r10conf *conf, struct r10bio *r10_bio)
if (r10_bio->devs[m].repl_bio == NULL)
continue;
- if (!r10_bio->devs[m].repl_bio->bi_error) {
+ if (!r10_bio->devs[m].repl_bio->bi_status) {
rdev_clear_badblocks(
rdev,
r10_bio->devs[m].addr,
@@ -2675,7 +2675,7 @@ static void handle_write_completed(struct r10conf *conf, struct r10bio *r10_bio)
r10_bio->devs[m].addr,
r10_bio->sectors, 0);
rdev_dec_pending(rdev, conf->mddev);
- } else if (bio != NULL && bio->bi_error) {
+ } else if (bio != NULL && bio->bi_status) {
fail = true;
if (!narrow_write_error(r10_bio, m)) {
md_error(conf->mddev, rdev);
@@ -3267,7 +3267,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
r10_bio->devs[i].repl_bio->bi_end_io = NULL;
bio = r10_bio->devs[i].bio;
- bio->bi_error = -EIO;
+ bio->bi_status = BLK_STS_IOERR;
rcu_read_lock();
rdev = rcu_dereference(conf->mirrors[d].rdev);
if (rdev == NULL || test_bit(Faulty, &rdev->flags)) {
@@ -3309,7 +3309,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
/* Need to set up for writing to the replacement */
bio = r10_bio->devs[i].repl_bio;
- bio->bi_error = -EIO;
+ bio->bi_status = BLK_STS_IOERR;
sector = r10_bio->devs[i].addr;
bio->bi_next = biolist;
@@ -3375,7 +3375,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
if (bio->bi_end_io == end_sync_read) {
md_sync_acct(bio->bi_bdev, nr_sectors);
- bio->bi_error = 0;
+ bio->bi_status = 0;
generic_make_request(bio);
}
}
@@ -3552,7 +3552,7 @@ static struct r10conf *setup_conf(struct mddev *mddev)
if (!conf->r10bio_pool)
goto out;
- conf->bio_split = bioset_create(BIO_POOL_SIZE, 0);
+ conf->bio_split = bioset_create(BIO_POOL_SIZE, 0, 0);
if (!conf->bio_split)
goto out;
@@ -4397,7 +4397,7 @@ read_more:
read_bio->bi_end_io = end_reshape_read;
bio_set_op_attrs(read_bio, REQ_OP_READ, 0);
read_bio->bi_flags &= (~0UL << BIO_RESET_BITS);
- read_bio->bi_error = 0;
+ read_bio->bi_status = 0;
read_bio->bi_vcnt = 0;
read_bio->bi_iter.bi_size = 0;
r10_bio->master_bio = read_bio;
@@ -4641,7 +4641,7 @@ static void end_reshape_write(struct bio *bio)
rdev = conf->mirrors[d].rdev;
}
- if (bio->bi_error) {
+ if (bio->bi_status) {
/* FIXME should record badblock */
md_error(mddev, rdev);
}
diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c
index 0a7af8b0a80a..bfa1e907c472 100644
--- a/drivers/md/raid5-cache.c
+++ b/drivers/md/raid5-cache.c
@@ -572,7 +572,7 @@ static void r5l_log_endio(struct bio *bio)
struct r5l_log *log = io->log;
unsigned long flags;
- if (bio->bi_error)
+ if (bio->bi_status)
md_error(log->rdev->mddev, log->rdev);
bio_put(bio);
@@ -1247,7 +1247,7 @@ static void r5l_log_flush_endio(struct bio *bio)
unsigned long flags;
struct r5l_io_unit *io;
- if (bio->bi_error)
+ if (bio->bi_status)
md_error(log->rdev->mddev, log->rdev);
spin_lock_irqsave(&log->io_list_lock, flags);
@@ -3063,7 +3063,7 @@ int r5l_init_log(struct r5conf *conf, struct md_rdev *rdev)
if (!log->io_pool)
goto io_pool;
- log->bs = bioset_create(R5L_POOL_SIZE, 0);
+ log->bs = bioset_create(R5L_POOL_SIZE, 0, BIOSET_NEED_BVECS);
if (!log->bs)
goto io_bs;
diff --git a/drivers/md/raid5-ppl.c b/drivers/md/raid5-ppl.c
index ccce92e68d7f..77cce3573aa8 100644
--- a/drivers/md/raid5-ppl.c
+++ b/drivers/md/raid5-ppl.c
@@ -397,7 +397,7 @@ static void ppl_log_endio(struct bio *bio)
pr_debug("%s: seq: %llu\n", __func__, io->seq);
- if (bio->bi_error)
+ if (bio->bi_status)
md_error(ppl_conf->mddev, log->rdev);
list_for_each_entry_safe(sh, next, &io->stripe_list, log_list) {
@@ -1150,7 +1150,7 @@ int ppl_init_log(struct r5conf *conf)
goto err;
}
- ppl_conf->bs = bioset_create(conf->raid_disks, 0);
+ ppl_conf->bs = bioset_create(conf->raid_disks, 0, 0);
if (!ppl_conf->bs) {
ret = -ENOMEM;
goto err;
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index ec0f951ae19f..62c965be97e1 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -2476,7 +2476,7 @@ static void raid5_end_read_request(struct bio * bi)
pr_debug("end_read_request %llu/%d, count: %d, error %d.\n",
(unsigned long long)sh->sector, i, atomic_read(&sh->count),
- bi->bi_error);
+ bi->bi_status);
if (i == disks) {
bio_reset(bi);
BUG();
@@ -2496,7 +2496,7 @@ static void raid5_end_read_request(struct bio * bi)
s = sh->sector + rdev->new_data_offset;
else
s = sh->sector + rdev->data_offset;
- if (!bi->bi_error) {
+ if (!bi->bi_status) {
set_bit(R5_UPTODATE, &sh->dev[i].flags);
if (test_bit(R5_ReadError, &sh->dev[i].flags)) {
/* Note that this cannot happen on a
@@ -2613,7 +2613,7 @@ static void raid5_end_write_request(struct bio *bi)
}
pr_debug("end_write_request %llu/%d, count %d, error: %d.\n",
(unsigned long long)sh->sector, i, atomic_read(&sh->count),
- bi->bi_error);
+ bi->bi_status);
if (i == disks) {
bio_reset(bi);
BUG();
@@ -2621,14 +2621,14 @@ static void raid5_end_write_request(struct bio *bi)
}
if (replacement) {
- if (bi->bi_error)
+ if (bi->bi_status)
md_error(conf->mddev, rdev);
else if (is_badblock(rdev, sh->sector,
STRIPE_SECTORS,
&first_bad, &bad_sectors))
set_bit(R5_MadeGoodRepl, &sh->dev[i].flags);
} else {
- if (bi->bi_error) {
+ if (bi->bi_status) {
set_bit(STRIPE_DEGRADED, &sh->state);
set_bit(WriteErrorSeen, &rdev->flags);
set_bit(R5_WriteError, &sh->dev[i].flags);
@@ -2649,7 +2649,7 @@ static void raid5_end_write_request(struct bio *bi)
}
rdev_dec_pending(rdev, conf->mddev);
- if (sh->batch_head && bi->bi_error && !replacement)
+ if (sh->batch_head && bi->bi_status && !replacement)
set_bit(STRIPE_BATCH_ERR, &sh->batch_head->state);
bio_reset(bi);
@@ -3381,7 +3381,7 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
sh->dev[i].sector + STRIPE_SECTORS) {
struct bio *nextbi = r5_next_bio(bi, sh->dev[i].sector);
- bi->bi_error = -EIO;
+ bi->bi_status = BLK_STS_IOERR;
md_write_end(conf->mddev);
bio_endio(bi);
bi = nextbi;
@@ -3403,7 +3403,7 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
sh->dev[i].sector + STRIPE_SECTORS) {
struct bio *bi2 = r5_next_bio(bi, sh->dev[i].sector);
- bi->bi_error = -EIO;
+ bi->bi_status = BLK_STS_IOERR;
md_write_end(conf->mddev);
bio_endio(bi);
bi = bi2;
@@ -3429,7 +3429,7 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
struct bio *nextbi =
r5_next_bio(bi, sh->dev[i].sector);
- bi->bi_error = -EIO;
+ bi->bi_status = BLK_STS_IOERR;
bio_endio(bi);
bi = nextbi;
}
@@ -5154,7 +5154,7 @@ static void raid5_align_endio(struct bio *bi)
struct mddev *mddev;
struct r5conf *conf;
struct md_rdev *rdev;
- int error = bi->bi_error;
+ blk_status_t error = bi->bi_status;
bio_put(bi);
@@ -5731,7 +5731,7 @@ static void raid5_make_request(struct mddev *mddev, struct bio * bi)
release_stripe_plug(mddev, sh);
} else {
/* cannot get stripe for read-ahead, just give-up */
- bi->bi_error = -EIO;
+ bi->bi_status = BLK_STS_IOERR;
break;
}
}
@@ -6943,7 +6943,7 @@ static struct r5conf *setup_conf(struct mddev *mddev)
goto abort;
}
- conf->bio_split = bioset_create(BIO_POOL_SIZE, 0);
+ conf->bio_split = bioset_create(BIO_POOL_SIZE, 0, 0);
if (!conf->bio_split)
goto abort;
conf->mddev = mddev;
diff --git a/drivers/memstick/core/ms_block.c b/drivers/memstick/core/ms_block.c
index 99e651c27fb7..22de7f5ed032 100644
--- a/drivers/memstick/core/ms_block.c
+++ b/drivers/memstick/core/ms_block.c
@@ -1921,12 +1921,13 @@ static void msb_io_work(struct work_struct *work)
spin_lock_irqsave(&msb->q_lock, flags);
if (len)
- if (!__blk_end_request(msb->req, 0, len))
+ if (!__blk_end_request(msb->req, BLK_STS_OK, len))
msb->req = NULL;
if (error && msb->req) {
+ blk_status_t ret = errno_to_blk_status(error);
dbg_verbose("IO: ending one sector of the request with error");
- if (!__blk_end_request(msb->req, error, msb->page_size))
+ if (!__blk_end_request(msb->req, ret, msb->page_size))
msb->req = NULL;
}
@@ -2014,7 +2015,7 @@ static void msb_submit_req(struct request_queue *q)
WARN_ON(!msb->io_queue_stopped);
while ((req = blk_fetch_request(q)) != NULL)
- __blk_end_request_all(req, -ENODEV);
+ __blk_end_request_all(req, BLK_STS_IOERR);
return;
}
diff --git a/drivers/memstick/core/mspro_block.c b/drivers/memstick/core/mspro_block.c
index c00d8a266878..8897962781bb 100644
--- a/drivers/memstick/core/mspro_block.c
+++ b/drivers/memstick/core/mspro_block.c
@@ -709,7 +709,8 @@ try_again:
msb->req_sg);
if (!msb->seg_count) {
- chunk = __blk_end_request_cur(msb->block_req, -ENOMEM);
+ chunk = __blk_end_request_cur(msb->block_req,
+ BLK_STS_RESOURCE);
continue;
}
@@ -776,7 +777,8 @@ static int mspro_block_complete_req(struct memstick_dev *card, int error)
if (error && !t_len)
t_len = blk_rq_cur_bytes(msb->block_req);
- chunk = __blk_end_request(msb->block_req, error, t_len);
+ chunk = __blk_end_request(msb->block_req,
+ errno_to_blk_status(error), t_len);
error = mspro_block_issue_req(card, chunk);
@@ -838,7 +840,7 @@ static void mspro_block_submit_req(struct request_queue *q)
if (msb->eject) {
while ((req = blk_fetch_request(q)) != NULL)
- __blk_end_request_all(req, -ENODEV);
+ __blk_end_request_all(req, BLK_STS_IOERR);
return;
}
diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c
index 8273b078686d..6ff94a948a4b 100644
--- a/drivers/mmc/core/block.c
+++ b/drivers/mmc/core/block.c
@@ -1184,9 +1184,10 @@ static void mmc_blk_issue_discard_rq(struct mmc_queue *mq, struct request *req)
struct mmc_card *card = md->queue.card;
unsigned int from, nr, arg;
int err = 0, type = MMC_BLK_DISCARD;
+ blk_status_t status = BLK_STS_OK;
if (!mmc_can_erase(card)) {
- err = -EOPNOTSUPP;
+ status = BLK_STS_NOTSUPP;
goto fail;
}
@@ -1212,10 +1213,12 @@ static void mmc_blk_issue_discard_rq(struct mmc_queue *mq, struct request *req)
if (!err)
err = mmc_erase(card, from, nr, arg);
} while (err == -EIO && !mmc_blk_reset(md, card->host, type));
- if (!err)
+ if (err)
+ status = BLK_STS_IOERR;
+ else
mmc_blk_reset_success(md, type);
fail:
- blk_end_request(req, err, blk_rq_bytes(req));
+ blk_end_request(req, status, blk_rq_bytes(req));
}
static void mmc_blk_issue_secdiscard_rq(struct mmc_queue *mq,
@@ -1225,9 +1228,10 @@ static void mmc_blk_issue_secdiscard_rq(struct mmc_queue *mq,
struct mmc_card *card = md->queue.card;
unsigned int from, nr, arg;
int err = 0, type = MMC_BLK_SECDISCARD;
+ blk_status_t status = BLK_STS_OK;
if (!(mmc_can_secure_erase_trim(card))) {
- err = -EOPNOTSUPP;
+ status = BLK_STS_NOTSUPP;
goto out;
}
@@ -1254,8 +1258,10 @@ retry:
err = mmc_erase(card, from, nr, arg);
if (err == -EIO)
goto out_retry;
- if (err)
+ if (err) {
+ status = BLK_STS_IOERR;
goto out;
+ }
if (arg == MMC_SECURE_TRIM1_ARG) {
if (card->quirks & MMC_QUIRK_INAND_CMD38) {
@@ -1270,8 +1276,10 @@ retry:
err = mmc_erase(card, from, nr, MMC_SECURE_TRIM2_ARG);
if (err == -EIO)
goto out_retry;
- if (err)
+ if (err) {
+ status = BLK_STS_IOERR;
goto out;
+ }
}
out_retry:
@@ -1280,7 +1288,7 @@ out_retry:
if (!err)
mmc_blk_reset_success(md, type);
out:
- blk_end_request(req, err, blk_rq_bytes(req));
+ blk_end_request(req, status, blk_rq_bytes(req));