/* * For read-ahead of large files to be effective, we need to read ahead * at least twice the optimal I/O size. For rotational devices that do * not report an optimal I/O size (e.g. ATA HDDs), use the maximum I/O * size to avoid falling back to the (rather inefficient) small default * read-ahead size. * * There is no hardware limitation for the read-ahead size and the user * might have increased the read-ahead size through sysfs, so don't ever * decrease it.
*/ if (!io_opt && (lim->features & BLK_FEAT_ROTATIONAL))
io_opt = (u64)lim->max_sectors << SECTOR_SHIFT;
if (WARN_ON_ONCE(!IS_ENABLED(CONFIG_BLK_DEV_ZONED))) return -EINVAL;
/* * Given that active zones include open zones, the maximum number of * open zones cannot be larger than the maximum number of active zones.
*/ if (lim->max_active_zones &&
lim->max_open_zones > lim->max_active_zones) return -EINVAL;
if (lim->zone_write_granularity < lim->logical_block_size)
lim->zone_write_granularity = lim->logical_block_size;
/* * The Zone Append size is limited by the maximum I/O size and the zone * size given that it can't span zones. * * If no max_hw_zone_append_sectors limit is provided, the block layer * will emulated it, else we're also bound by the hardware limit.
*/
lim->max_zone_append_sectors =
min_not_zero(lim->max_hw_zone_append_sectors,
min(lim->chunk_sectors, lim->max_hw_sectors)); return 0;
}
if (!bi->metadata_size) { if (bi->csum_type != BLK_INTEGRITY_CSUM_NONE ||
bi->tag_size || ((bi->flags & BLK_INTEGRITY_REF_TAG))) {
pr_warn("invalid PI settings.\n"); return -EINVAL;
}
bi->flags |= BLK_INTEGRITY_NOGENERATE | BLK_INTEGRITY_NOVERIFY; return 0;
}
if (!IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY)) {
pr_warn("integrity support disabled.\n"); return -EINVAL;
}
if (bi->csum_type == BLK_INTEGRITY_CSUM_NONE &&
(bi->flags & BLK_INTEGRITY_REF_TAG)) {
pr_warn("ref tag not support without checksum.\n"); return -EINVAL;
}
switch (bi->csum_type) { case BLK_INTEGRITY_CSUM_NONE: if (bi->pi_tuple_size) {
pr_warn("pi_tuple_size must be 0 when checksum type is none\n"); return -EINVAL;
} break; case BLK_INTEGRITY_CSUM_CRC: case BLK_INTEGRITY_CSUM_IP: if (bi->pi_tuple_size != sizeof(struct t10_pi_tuple)) {
pr_warn("pi_tuple_size mismatch for T10 PI: expected %zu, got %u\n", sizeof(struct t10_pi_tuple),
bi->pi_tuple_size); return -EINVAL;
} break; case BLK_INTEGRITY_CSUM_CRC64: if (bi->pi_tuple_size != sizeof(struct crc64_pi_tuple)) {
pr_warn("pi_tuple_size mismatch for CRC64 PI: expected %zu, got %u\n", sizeof(struct crc64_pi_tuple),
bi->pi_tuple_size); return -EINVAL;
} break;
}
if (!bi->interval_exp)
bi->interval_exp = ilog2(lim->logical_block_size);
/* * The PI generation / validation helpers do not expect intervals to * straddle multiple bio_vecs. Enforce alignment so that those are * never generated, and that each buffer is aligned as expected.
*/ if (bi->csum_type) {
lim->dma_alignment = max(lim->dma_alignment,
(1U << bi->interval_exp) - 1);
}
return 0;
}
/* * Returns max guaranteed bytes which we can fit in a bio. * * We request that an atomic_write is ITER_UBUF iov_iter (so a single vector), * so we assume that we can fit in at least PAGE_SIZE in a segment, apart from * the first and last segments.
*/ staticunsignedint blk_queue_max_guaranteed_bio(struct queue_limits *lim)
{ unsignedint max_segments = min(BIO_MAX_VECS, lim->max_segments); unsignedint length;
if (boundary_sectors) { if (WARN_ON_ONCE(lim->atomic_write_hw_max >
lim->atomic_write_hw_boundary)) goto unsupported; /* * A feature of boundary support is that it disallows bios to * be merged which would result in a merged request which * crosses either a chunk sector or atomic write HW boundary, * even though chunk sectors may be just set for performance. * For simplicity, disallow atomic writes for a chunk sector * which is non-zero and smaller than atomic write HW boundary. * Furthermore, chunk sectors must be a multiple of atomic * write HW boundary. Otherwise boundary support becomes * complicated. * Devices which do not conform to these rules can be dealt * with if and when they show up.
*/ if (WARN_ON_ONCE(lim->chunk_sectors % boundary_sectors)) goto unsupported;
/* * The boundary size just needs to be a multiple of unit_max * (and not necessarily a power-of-2), so this following check * could be relaxed in future. * Furthermore, if needed, unit_max could even be reduced so * that it is compliant with a !power-of-2 boundary.
*/ if (!is_power_of_2(boundary_sectors)) goto unsupported;
}
/* * Check that the limits in lim are valid, initialize defaults for unset * values, and cap values based on others where needed.
*/ int blk_validate_limits(struct queue_limits *lim)
{ unsignedint max_hw_sectors; unsignedint logical_block_sectors; unsignedlong seg_size; int err;
/* * Unless otherwise specified, default to 512 byte logical blocks and a * physical block size equal to the logical block size.
*/ if (!lim->logical_block_size)
lim->logical_block_size = SECTOR_SIZE; elseif (blk_validate_block_size(lim->logical_block_size)) {
pr_warn("Invalid logical block size (%d)\n", lim->logical_block_size); return -EINVAL;
} if (lim->physical_block_size < lim->logical_block_size) {
lim->physical_block_size = lim->logical_block_size;
} elseif (!is_power_of_2(lim->physical_block_size)) {
pr_warn("Invalid physical block size (%d)\n", lim->physical_block_size); return -EINVAL;
}
/* * The minimum I/O size defaults to the physical block size unless * explicitly overridden.
*/ if (lim->io_min < lim->physical_block_size)
lim->io_min = lim->physical_block_size;
/* * The optimal I/O size may not be aligned to physical block size * (because it may be limited by dma engines which have no clue about * block size of the disks attached to them), so we round it down here.
*/
lim->io_opt = round_down(lim->io_opt, lim->physical_block_size);
/* * max_hw_sectors has a somewhat weird default for historical reason, * but driver really should set their own instead of relying on this * value. * * The block layer relies on the fact that every driver can * handle at lest a page worth of data per I/O, and needs the value * aligned to the logical block size.
*/ if (!lim->max_hw_sectors)
lim->max_hw_sectors = BLK_SAFE_MAX_SECTORS; if (WARN_ON_ONCE(lim->max_hw_sectors < PAGE_SECTORS)) return -EINVAL;
logical_block_sectors = lim->logical_block_size >> SECTOR_SHIFT; if (WARN_ON_ONCE(logical_block_sectors > lim->max_hw_sectors)) return -EINVAL;
lim->max_hw_sectors = round_down(lim->max_hw_sectors,
logical_block_sectors);
/* * The actual max_sectors value is a complex beast and also takes the * max_dev_sectors value (set by SCSI ULPs) and a user configurable * value into account. The ->max_sectors value is always calculated * from these, so directly setting it won't have any effect.
*/
max_hw_sectors = min_not_zero(lim->max_hw_sectors,
lim->max_dev_sectors); if (lim->max_user_sectors) { if (lim->max_user_sectors < BLK_MIN_SEGMENT_SIZE / SECTOR_SIZE) return -EINVAL;
lim->max_sectors = min(max_hw_sectors, lim->max_user_sectors);
} elseif (lim->io_opt > (BLK_DEF_MAX_SECTORS_CAP << SECTOR_SHIFT)) {
lim->max_sectors =
min(max_hw_sectors, lim->io_opt >> SECTOR_SHIFT);
} elseif (lim->io_min > (BLK_DEF_MAX_SECTORS_CAP << SECTOR_SHIFT)) {
lim->max_sectors =
min(max_hw_sectors, lim->io_min >> SECTOR_SHIFT);
} else {
lim->max_sectors = min(max_hw_sectors, BLK_DEF_MAX_SECTORS_CAP);
}
lim->max_sectors = round_down(lim->max_sectors,
logical_block_sectors);
/* * Random default for the maximum number of segments. Driver should not * rely on this and set their own.
*/ if (!lim->max_segments)
lim->max_segments = BLK_MAX_SEGMENTS;
/* * When discard is not supported, discard_granularity should be reported * as 0 to userspace.
*/ if (lim->max_discard_sectors)
lim->discard_granularity =
max(lim->discard_granularity, lim->physical_block_size); else
lim->discard_granularity = 0;
if (!lim->max_discard_segments)
lim->max_discard_segments = 1;
/* * By default there is no limit on the segment boundary alignment, * but if there is one it can't be smaller than the page size as * that would break all the normal I/O patterns.
*/ if (!lim->seg_boundary_mask)
lim->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK; if (WARN_ON_ONCE(lim->seg_boundary_mask < BLK_MIN_SEGMENT_SIZE - 1)) return -EINVAL;
/* * Stacking device may have both virtual boundary and max segment * size limit, so allow this setting now, and long-term the two * might need to move out of stacking limits since we have immutable * bvec and lower layer bio splitting is supposed to handle the two * correctly.
*/ if (lim->virt_boundary_mask) { if (!lim->max_segment_size)
lim->max_segment_size = UINT_MAX;
} else { /* * The maximum segment size has an odd historic 64k default that * drivers probably should override. Just like the I/O size we * require drivers to at least handle a full page per segment.
*/ if (!lim->max_segment_size)
lim->max_segment_size = BLK_MAX_SEGMENT_SIZE; if (WARN_ON_ONCE(lim->max_segment_size < BLK_MIN_SEGMENT_SIZE)) return -EINVAL;
}
/* setup min segment size for building new segment in fast path */ if (lim->seg_boundary_mask > lim->max_segment_size - 1)
seg_size = lim->max_segment_size; else
seg_size = lim->seg_boundary_mask + 1;
lim->min_segment_size = min_t(unsignedint, seg_size, PAGE_SIZE);
/* * We require drivers to at least do logical block aligned I/O, but * historically could not check for that due to the separate calls * to set the limits. Once the transition is finished the check * below should be narrowed down to check the logical block size.
*/ if (!lim->dma_alignment)
lim->dma_alignment = SECTOR_SIZE - 1; if (WARN_ON_ONCE(lim->dma_alignment > PAGE_SIZE)) return -EINVAL;
/* * Set the default limits for a newly allocated queue. @lim contains the * initial limits set by the driver, which could be no limit in which case * all fields are cleared to zero.
*/ int blk_set_default_limits(struct queue_limits *lim)
{ /* * Most defaults are set by capping the bounds in blk_validate_limits, * but these limits are special and need an explicit initialization to * the max value here.
*/
lim->max_user_discard_sectors = UINT_MAX;
lim->max_user_wzeroes_unmap_sectors = UINT_MAX; return blk_validate_limits(lim);
}
/** * queue_limits_commit_update - commit an atomic update of queue limits * @q: queue to update * @lim: limits to apply * * Apply the limits in @lim that were obtained from queue_limits_start_update() * and updated by the caller to @q. The caller must have frozen the queue or * ensure that there are no outstanding I/Os by other means. * * Returns 0 if successful, else a negative error code.
*/ int queue_limits_commit_update(struct request_queue *q, struct queue_limits *lim)
{ int error;
error = blk_validate_limits(lim); if (error) goto out_unlock;
#ifdef CONFIG_BLK_INLINE_ENCRYPTION if (q->crypto_profile && lim->integrity.tag_size) {
pr_warn("blk-integrity: Integrity and hardware inline encryption are not supported together.\n");
error = -EINVAL; goto out_unlock;
} #endif
/** * queue_limits_commit_update_frozen - commit an atomic update of queue limits * @q: queue to update * @lim: limits to apply * * Apply the limits in @lim that were obtained from queue_limits_start_update() * and updated with the new values by the caller to @q. Freezes the queue * before the update and unfreezes it after. * * Returns 0 if successful, else a negative error code.
*/ int queue_limits_commit_update_frozen(struct request_queue *q, struct queue_limits *lim)
{ unsignedint memflags; int ret;
memflags = blk_mq_freeze_queue(q);
ret = queue_limits_commit_update(q, lim);
blk_mq_unfreeze_queue(q, memflags);
/** * queue_limits_set - apply queue limits to queue * @q: queue to update * @lim: limits to apply * * Apply the limits in @lim that were freshly initialized to @q. * To update existing limits use queue_limits_start_update() and * queue_limits_commit_update() instead. * * Returns 0 if successful, else a negative error code.
*/ int queue_limits_set(struct request_queue *q, struct queue_limits *lim)
{
mutex_lock(&q->limits_lock); return queue_limits_commit_update(q, lim);
}
EXPORT_SYMBOL_GPL(queue_limits_set);
/* Check if second and later bottom devices are compliant */ staticbool blk_stack_atomic_writes_tail(struct queue_limits *t, struct queue_limits *b)
{ /* We're not going to support different boundary sizes.. yet */ if (t->atomic_write_hw_boundary != b->atomic_write_hw_boundary) returnfalse;
/* Can't support this */ if (t->atomic_write_hw_unit_min > b->atomic_write_hw_unit_max) returnfalse;
/* Or this */ if (t->atomic_write_hw_unit_max < b->atomic_write_hw_unit_min) returnfalse;
/* * If chunk sectors is so large that its value in bytes overflows * UINT_MAX, then just shift it down so it definitely will fit. * We don't support atomic writes of such a large size anyway.
*/ if (check_shl_overflow(t->chunk_sectors, SECTOR_SHIFT, &chunk_bytes))
chunk_bytes = t->chunk_sectors;
/* * Find values for limits which work for chunk size. * b->atomic_write_hw_unit_{min, max} may not be aligned with chunk * size, as the chunk size is not restricted to a power-of-2. * So we need to find highest power-of-2 which works for the chunk * size. * As an example scenario, we could have t->unit_max = 16K and * t->chunk_sectors = 24KB. For this case, reduce t->unit_max to a * value aligned with both limits, i.e. 8K in this example.
*/
t->atomic_write_hw_unit_max = min(t->atomic_write_hw_unit_max,
max_pow_of_two_factor(chunk_bytes));
/** * blk_stack_limits - adjust queue_limits for stacked devices * @t: the stacking driver limits (top device) * @b: the underlying queue limits (bottom, component device) * @start: first data sector within component device * * Description: * This function is used by stacking drivers like MD and DM to ensure * that all component devices have compatible block sizes and * alignments. The stacking driver must provide a queue_limits * struct (top) and then iteratively call the stacking function for * all component (bottom) devices. The stacking function will * attempt to combine the values and ensure proper alignment. * * Returns 0 if the top and bottom queue_limits are compatible. The * top device's block sizes and alignment offsets may be adjusted to * ensure alignment with the bottom device. If no compatible sizes * and alignments exist, -1 is returned and the resulting top * queue_limits will have the misaligned flag set to indicate that * the alignment_offset is undefined.
*/ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
sector_t start)
{ unsignedint top, bottom, alignment; int ret = 0;
/* * Some feaures need to be supported both by the stacking driver and all * underlying devices. The stacking driver sets these flags before * stacking the limits, and this will clear the flags if any of the * underlying devices does not support it.
*/ if (!(b->features & BLK_FEAT_NOWAIT))
t->features &= ~BLK_FEAT_NOWAIT; if (!(b->features & BLK_FEAT_POLL))
t->features &= ~BLK_FEAT_POLL;
/* Verify that new alignment_offset is on a logical block boundary */ if (t->alignment_offset & (t->logical_block_size - 1)) {
t->flags |= BLK_FLAG_MISALIGNED;
ret = -1;
}
/** * queue_limits_stack_bdev - adjust queue_limits for stacked devices * @t: the stacking driver limits (top device) * @bdev: the underlying block device (bottom) * @offset: offset to beginning of data within component device * @pfx: prefix to use for warnings logged * * Description: * This function is used by stacking drivers like MD and DM to ensure * that all component devices have compatible block sizes and * alignments. The stacking driver must provide a queue_limits * struct (top) and then iteratively call the stacking function for * all component (bottom) devices. The stacking function will * attempt to combine the values and ensure proper alignment.
*/ void queue_limits_stack_bdev(struct queue_limits *t, struct block_device *bdev,
sector_t offset, constchar *pfx)
{ if (blk_stack_limits(t, bdev_limits(bdev),
get_start_sect(bdev) + offset))
pr_notice("%s: Warning: Device %pg is misaligned\n",
pfx, bdev);
}
EXPORT_SYMBOL_GPL(queue_limits_stack_bdev);
/** * queue_limits_stack_integrity - stack integrity profile * @t: target queue limits * @b: base queue limits * * Check if the integrity profile in the @b can be stacked into the * target @t. Stacking is possible if either: * * a) does not have any integrity information stacked into it yet * b) the integrity profile in @b is identical to the one in @t * * If @b can be stacked into @t, return %true. Else return %false and clear the * integrity information in @t.
*/ bool queue_limits_stack_integrity(struct queue_limits *t, struct queue_limits *b)
{ struct blk_integrity *ti = &t->integrity; struct blk_integrity *bi = &b->integrity;
if (!IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY)) returntrue;
Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.
Bemerkung:
Die farbliche Syntaxdarstellung und die Messung sind noch experimentell.
