From 7ba150834b840f6f5cdd07ca69a4ccf39df59a66 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Fri, 7 Apr 2023 15:05:35 -0500 Subject: block: Rename BLK_STS_NEXUS to BLK_STS_RESV_CONFLICT BLK_STS_NEXUS is used for NVMe/SCSI reservation conflicts and DASD's locking feature which works similar to NVMe/SCSI reservations where a host can get a lock on a device and when the lock is taken it will get failures. This patch renames BLK_STS_NEXUS so it better reflects this type of use. Signed-off-by: Mike Christie Link: https://lore.kernel.org/r/20230407200551.12660-3-michael.christie@oracle.com Acked-by: Stefan Haberland Reviewed-by: Bart Van Assche Reviewed-by: Chaitanya Kulkarni Reviewed-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Signed-off-by: Martin K. Petersen --- block/blk-core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'block') diff --git a/block/blk-core.c b/block/blk-core.c index 9e5e0277a4d9..ff8fb7a49389 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -155,7 +155,7 @@ static const struct { [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_RESV_CONFLICT] = { -EBADE, "reservation conflict" }, [BLK_STS_MEDIUM] = { -ENODATA, "critical medium" }, [BLK_STS_PROTECTION] = { -EILSEQ, "protection" }, [BLK_STS_RESOURCE] = { -ENOMEM, "kernel resource" }, -- cgit v1.2.3 From eca2040972b411ec27483bf75dc8b84e730e88ff Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Thu, 11 May 2023 03:13:34 +0200 Subject: scsi: block: ioprio: Clean up interface definition The I/O priority user interface defines the 16-bits ioprio values as the combination of the upper 3-bits for an I/O priority class and the lower 13-bits as priority data. However, the kernel only uses the lower 3-bits of the priority data to define priority levels for the RT and BE priority classes. The data part of an ioprio value is completely ignored for the IDLE and NONE classes. This is enforced by checks done in ioprio_check_cap(), which is called for all paths that allow defining an I/O priority for I/Os: the per-context ioprio_set() system call, aio interface and io_uring interface. Clarify this fact in the uapi ioprio.h header file and introduce the IOPRIO_PRIO_LEVEL_MASK and IOPRIO_PRIO_LEVEL() macros for users to define and get priority levels in an ioprio value. The coarser macro IOPRIO_PRIO_DATA() is retained for backward compatibility with old applications already using it. There is no functional change introduced with this. In-kernel users of the IOPRIO_PRIO_DATA() macro which are explicitly handling I/O priority data as a priority level are modified to use the new IOPRIO_PRIO_LEVEL() macro without any functional change. Since f2fs is the only user of this macro not explicitly using that value as a priority level, it is left unchanged. Signed-off-by: Damien Le Moal Reviewed-by: Hannes Reinecke Reviewed-by: Christoph Hellwig Signed-off-by: Niklas Cassel Link: https://lore.kernel.org/r/20230511011356.227789-2-nks@flawful.org Signed-off-by: Martin K. Petersen --- block/bfq-iosched.c | 8 ++++---- block/ioprio.c | 6 +++--- include/uapi/linux/ioprio.h | 19 ++++++++++++++----- 3 files changed, 21 insertions(+), 12 deletions(-) (limited to 'block') diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 3164e3177965..3067b75f3fd0 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -5524,16 +5524,16 @@ bfq_set_next_ioprio_data(struct bfq_queue *bfqq, struct bfq_io_cq *bic) bfqq->new_ioprio_class = task_nice_ioclass(tsk); break; case IOPRIO_CLASS_RT: - bfqq->new_ioprio = IOPRIO_PRIO_DATA(bic->ioprio); + bfqq->new_ioprio = IOPRIO_PRIO_LEVEL(bic->ioprio); bfqq->new_ioprio_class = IOPRIO_CLASS_RT; break; case IOPRIO_CLASS_BE: - bfqq->new_ioprio = IOPRIO_PRIO_DATA(bic->ioprio); + bfqq->new_ioprio = IOPRIO_PRIO_LEVEL(bic->ioprio); bfqq->new_ioprio_class = IOPRIO_CLASS_BE; break; case IOPRIO_CLASS_IDLE: bfqq->new_ioprio_class = IOPRIO_CLASS_IDLE; - bfqq->new_ioprio = 7; + bfqq->new_ioprio = IOPRIO_NR_LEVELS - 1; break; } @@ -5830,7 +5830,7 @@ static struct bfq_queue *bfq_get_queue(struct bfq_data *bfqd, struct bfq_io_cq *bic, bool respawn) { - const int ioprio = IOPRIO_PRIO_DATA(bic->ioprio); + const int ioprio = IOPRIO_PRIO_LEVEL(bic->ioprio); const int ioprio_class = IOPRIO_PRIO_CLASS(bic->ioprio); struct bfq_queue **async_bfqq = NULL; struct bfq_queue *bfqq; diff --git a/block/ioprio.c b/block/ioprio.c index 32a456b45804..f0d9e818abc5 100644 --- a/block/ioprio.c +++ b/block/ioprio.c @@ -33,7 +33,7 @@ int ioprio_check_cap(int ioprio) { int class = IOPRIO_PRIO_CLASS(ioprio); - int data = IOPRIO_PRIO_DATA(ioprio); + int level = IOPRIO_PRIO_LEVEL(ioprio); switch (class) { case IOPRIO_CLASS_RT: @@ -49,13 +49,13 @@ int ioprio_check_cap(int ioprio) fallthrough; /* rt has prio field too */ case IOPRIO_CLASS_BE: - if (data >= IOPRIO_NR_LEVELS || data < 0) + if (level >= IOPRIO_NR_LEVELS) return -EINVAL; break; case IOPRIO_CLASS_IDLE: break; case IOPRIO_CLASS_NONE: - if (data) + if (level) return -EINVAL; break; default: diff --git a/include/uapi/linux/ioprio.h b/include/uapi/linux/ioprio.h index f70f2596a6bf..4444b4e4fdad 100644 --- a/include/uapi/linux/ioprio.h +++ b/include/uapi/linux/ioprio.h @@ -17,7 +17,7 @@ ((data) & IOPRIO_PRIO_MASK)) /* - * These are the io priority groups as implemented by the BFQ and mq-deadline + * These are the io priority classes as implemented by the BFQ and mq-deadline * schedulers. RT is the realtime class, it always gets premium service. For * ATA disks supporting NCQ IO priority, RT class IOs will be processed using * high priority NCQ commands. BE is the best-effort scheduling class, the @@ -32,11 +32,20 @@ enum { }; /* - * The RT and BE priority classes both support up to 8 priority levels. + * The RT and BE priority classes both support up to 8 priority levels that + * can be specified using the lower 3-bits of the priority data. */ -#define IOPRIO_NR_LEVELS 8 -#define IOPRIO_BE_NR IOPRIO_NR_LEVELS +#define IOPRIO_LEVEL_NR_BITS 3 +#define IOPRIO_NR_LEVELS (1 << IOPRIO_LEVEL_NR_BITS) +#define IOPRIO_LEVEL_MASK (IOPRIO_NR_LEVELS - 1) +#define IOPRIO_PRIO_LEVEL(ioprio) ((ioprio) & IOPRIO_LEVEL_MASK) +#define IOPRIO_BE_NR IOPRIO_NR_LEVELS + +/* + * Possible values for the "which" argument of the ioprio_get() and + * ioprio_set() system calls (see "man ioprio_set"). + */ enum { IOPRIO_WHO_PROCESS = 1, IOPRIO_WHO_PGRP, @@ -44,7 +53,7 @@ enum { }; /* - * Fallback BE priority level. + * Fallback BE class priority level. */ #define IOPRIO_NORM 4 #define IOPRIO_BE_NORM IOPRIO_NORM -- cgit v1.2.3 From dffc480d2df1772d6092f46f2b4c5e0de941bd47 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Thu, 11 May 2023 03:13:36 +0200 Subject: scsi: block: Introduce BLK_STS_DURATION_LIMIT Introduce the new block I/O status BLK_STS_DURATION_LIMIT for LLDDs to report command that failed due to a command duration limit being exceeded. This new status is mapped to the ETIME error code to allow users to differentiate "soft" duration limit failures from other more serious hardware related errors. If we compare BLK_STS_DURATION_LIMIT with BLK_STS_TIMEOUT: -BLK_STS_DURATION_LIMIT means that the drive gave a reply indicating that the command duration limit was exceeded before the command could be completed. This I/O status is mapped to ETIME for user space. -BLK_STS_TIMEOUT means that the drive never gave a reply at all. This I/O status is mapped to ETIMEDOUT for user space. Signed-off-by: Damien Le Moal Reviewed-by: Hannes Reinecke Reviewed-by: Christoph Hellwig Co-developed-by: Niklas Cassel Signed-off-by: Niklas Cassel Link: https://lore.kernel.org/r/20230511011356.227789-4-nks@flawful.org Signed-off-by: Martin K. Petersen --- block/blk-core.c | 3 +++ include/linux/blk_types.h | 6 ++++++ 2 files changed, 9 insertions(+) (limited to 'block') diff --git a/block/blk-core.c b/block/blk-core.c index 00c74330fa92..04ad13ec6ead 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -170,6 +170,9 @@ static const struct { [BLK_STS_ZONE_OPEN_RESOURCE] = { -ETOOMANYREFS, "open zones exceeded" }, [BLK_STS_ZONE_ACTIVE_RESOURCE] = { -EOVERFLOW, "active zones exceeded" }, + /* Command duration limit device-side timeout */ + [BLK_STS_DURATION_LIMIT] = { -ETIME, "duration limit exceeded" }, + /* everything else not covered above: */ [BLK_STS_IOERR] = { -EIO, "I/O" }, }; diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 740afe80f297..dfdcd218aaac 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -171,6 +171,12 @@ typedef u16 blk_short_t; */ #define BLK_STS_OFFLINE ((__force blk_status_t)17) +/* + * BLK_STS_DURATION_LIMIT is returned from the driver when the target device + * aborted the command because it exceeded one of its Command Duration Limits. + */ +#define BLK_STS_DURATION_LIMIT ((__force blk_status_t)18) + /** * blk_path_error - returns true if error may be path related * @error: status the request was completed with -- cgit v1.2.3 From 01584c1e233740519d0e11aa20daa323d26bf598 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Thu, 8 Jun 2023 18:55:56 +0900 Subject: scsi: block: Improve ioprio value validity checks The introduction of the macro IOPRIO_PRIO_LEVEL() in commit eca2040972b4 ("scsi: block: ioprio: Clean up interface definition") results in an iopriority level to always be masked using the macro IOPRIO_LEVEL_MASK, and thus to the kernel always seeing an acceptable value for an I/O priority level when checked in ioprio_check_cap(). Before this patch, this function would return an error for some (but not all) invalid values for a level valid range of [0..7]. Restore and improve the detection of invalid priority levels by introducing the inline function ioprio_value() to check an ioprio class, level and hint value before combining these fields into a single value to be used with ioprio_set() or AIOs. If an invalid value for the class, level or hint of an ioprio is detected, ioprio_value() returns an ioprio using the class IOPRIO_CLASS_INVALID, indicating an invalid value and causing ioprio_check_cap() to return -EINVAL. Fixes: 6c913257226a ("scsi: block: Introduce ioprio hints") Fixes: eca2040972b4 ("scsi: block: ioprio: Clean up interface definition") Signed-off-by: Damien Le Moal Link: https://lore.kernel.org/r/20230608095556.124001-1-dlemoal@kernel.org Reviewed-by: Niklas Cassel Reviewed-by: Linus Walleij Signed-off-by: Martin K. Petersen --- block/ioprio.c | 1 + include/uapi/linux/ioprio.h | 50 ++++++++++++++++++++++++++++++--------------- 2 files changed, 34 insertions(+), 17 deletions(-) (limited to 'block') diff --git a/block/ioprio.c b/block/ioprio.c index f0d9e818abc5..b5a942519a79 100644 --- a/block/ioprio.c +++ b/block/ioprio.c @@ -58,6 +58,7 @@ int ioprio_check_cap(int ioprio) if (level) return -EINVAL; break; + case IOPRIO_CLASS_INVALID: default: return -EINVAL; } diff --git a/include/uapi/linux/ioprio.h b/include/uapi/linux/ioprio.h index 4c4806e8230b..99440b2e8c35 100644 --- a/include/uapi/linux/ioprio.h +++ b/include/uapi/linux/ioprio.h @@ -2,19 +2,20 @@ #ifndef _UAPI_LINUX_IOPRIO_H #define _UAPI_LINUX_IOPRIO_H +#include +#include + /* * Gives us 8 prio classes with 13-bits of data for each class */ #define IOPRIO_CLASS_SHIFT 13 -#define IOPRIO_CLASS_MASK 0x07 +#define IOPRIO_NR_CLASSES 8 +#define IOPRIO_CLASS_MASK (IOPRIO_NR_CLASSES - 1) #define IOPRIO_PRIO_MASK ((1UL << IOPRIO_CLASS_SHIFT) - 1) #define IOPRIO_PRIO_CLASS(ioprio) \ (((ioprio) >> IOPRIO_CLASS_SHIFT) & IOPRIO_CLASS_MASK) #define IOPRIO_PRIO_DATA(ioprio) ((ioprio) & IOPRIO_PRIO_MASK) -#define IOPRIO_PRIO_VALUE(class, data) \ - ((((class) & IOPRIO_CLASS_MASK) << IOPRIO_CLASS_SHIFT) | \ - ((data) & IOPRIO_PRIO_MASK)) /* * These are the io priority classes as implemented by the BFQ and mq-deadline @@ -25,10 +26,13 @@ * served when no one else is using the disk. */ enum { - IOPRIO_CLASS_NONE, - IOPRIO_CLASS_RT, - IOPRIO_CLASS_BE, - IOPRIO_CLASS_IDLE, + IOPRIO_CLASS_NONE = 0, + IOPRIO_CLASS_RT = 1, + IOPRIO_CLASS_BE = 2, + IOPRIO_CLASS_IDLE = 3, + + /* Special class to indicate an invalid ioprio value */ + IOPRIO_CLASS_INVALID = 7, }; /* @@ -73,15 +77,6 @@ enum { #define IOPRIO_PRIO_HINT(ioprio) \ (((ioprio) >> IOPRIO_HINT_SHIFT) & IOPRIO_HINT_MASK) -/* - * Alternate macro for IOPRIO_PRIO_VALUE() to define an I/O priority with - * a class, level and hint. - */ -#define IOPRIO_PRIO_VALUE_HINT(class, level, hint) \ - ((((class) & IOPRIO_CLASS_MASK) << IOPRIO_CLASS_SHIFT) | \ - (((hint) & IOPRIO_HINT_MASK) << IOPRIO_HINT_SHIFT) | \ - ((level) & IOPRIO_LEVEL_MASK)) - /* * I/O hints. */ @@ -107,4 +102,25 @@ enum { IOPRIO_HINT_DEV_DURATION_LIMIT_7 = 7, }; +#define IOPRIO_BAD_VALUE(val, max) ((val) < 0 || (val) >= (max)) + +/* + * Return an I/O priority value based on a class, a level and a hint. + */ +static __always_inline __u16 ioprio_value(int class, int level, int hint) +{ + if (IOPRIO_BAD_VALUE(class, IOPRIO_NR_CLASSES) || + IOPRIO_BAD_VALUE(level, IOPRIO_NR_LEVELS) || + IOPRIO_BAD_VALUE(hint, IOPRIO_NR_HINTS)) + return IOPRIO_CLASS_INVALID << IOPRIO_CLASS_SHIFT; + + return (class << IOPRIO_CLASS_SHIFT) | + (hint << IOPRIO_HINT_SHIFT) | level; +} + +#define IOPRIO_PRIO_VALUE(class, level) \ + ioprio_value(class, level, IOPRIO_HINT_NONE) +#define IOPRIO_PRIO_VALUE_HINT(class, level, hint) \ + ioprio_value(class, level, hint) + #endif /* _UAPI_LINUX_IOPRIO_H */ -- cgit v1.2.3 From 9077fb2ab78cd76f710893919df6b0b7da79c2c9 Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Wed, 14 Jun 2023 12:36:10 +0200 Subject: scsi: bsg: Increase number of devices Larger setups may need to allocate more than 32k bsg devices, so increase the number of devices to the full range of minor device numbers. Signed-off-by: Hannes Reinecke Signed-off-by: Martin Wilck Link: https://lore.kernel.org/r/20230614103616.31857-2-mwilck@suse.com Reviewed-by: Christoph Hellwig Reviewed-by: Ming Lei Reviewed-by: Bart Van Assche Signed-off-by: Martin K. Petersen --- block/bsg.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'block') diff --git a/block/bsg.c b/block/bsg.c index 7eca43f33d7f..c53f24243bf2 100644 --- a/block/bsg.c +++ b/block/bsg.c @@ -36,7 +36,7 @@ static inline struct bsg_device *to_bsg_device(struct inode *inode) } #define BSG_DEFAULT_CMDS 64 -#define BSG_MAX_DEVS 32768 +#define BSG_MAX_DEVS (1 << MINORBITS) static DEFINE_IDA(bsg_minor_ida); static struct class *bsg_class; -- cgit v1.2.3