[PATCH 6.12.y 2/4] nvme: refactor the atomic write unit detection
flat view
COLD29d
REVIEWED: 6 (6M)
From: Sasha Levin <sashal@kernel.org>
Date: 2026-09-11 00:15:46
Subsystem:
nvm express driver, the rest · Maintainers:
Keith Busch, Jens Axboe, Christoph Hellwig, Sagi Grimberg, Linus Torvalds
2 review trailers.
From: Christoph Hellwig <hch@lst.de>
[ Upstream commit b2e607fecac15e07f50269c080e2e71b5049dfa2 ]
Move all the code out of nvme_update_disk_info into the helper, and
rename the helper to have a somewhat less clumsy name.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Luis Chamberlain <mcgrof@kernel.org>
Reviewed-by: John Garry <john.g.garry@oracle.com>
Stable adaptation for 6.12:
- Keep the existing atomic write helper refactor, but omit
BLK_FEAT_ATOMIC_WRITES: this tree enables atomic writes through the
hardware limits and does not define that feature flag.
- Call the existing discard setup helper from nvme_update_disk_info()
after setting logical_block_size. Save the disk-info validity result
and defer clearing capacity until after atomic-size validation. This
preserves the result while leaving the zoned update insertion point
clear for 3838e80fcfb32e62baffb63c6dc0a60153665a4d.
- Adapt the preceding dependency's atomic-size error path to the
single-argument blk_mq_unfreeze_queue() API and cancel the pending
limits update before unfreezing, releasing limits_lock on rejection.
No additional functions are introduced.
Stable-dep-of: 3838e80fcfb3 ("nvme: skip the zoned limits update if the zone info query failed")
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
drivers/nvme/host/core.c | 84 ++++++++++++++++++++++------------------
1 file changed, 46 insertions(+), 38 deletions(-)
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 3f2586086f6ec..deffad78d1dcf 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c@@ -1995,20 +1995,50 @@ static void nvme_configure_metadata(struct nvme_ctrl *ctrl, } -static void nvme_update_atomic_write_disk_info(struct nvme_ns *ns, - struct nvme_id_ns *id, struct queue_limits *lim, - u32 bs, u32 atomic_bs) +static u32 nvme_configure_atomic_write(struct nvme_ns *ns, + struct nvme_id_ns *id, struct queue_limits *lim, u32 bs) { - unsigned int boundary = 0; + u32 atomic_bs, boundary = 0; - if (id->nsfeat & NVME_NS_FEAT_ATOMICS && id->nawupf) { - if (le16_to_cpu(id->nabspf)) + /* + * We do not support an offset for the atomic boundaries. + */ + if (id->nabo) + return bs; + + if ((id->nsfeat & NVME_NS_FEAT_ATOMICS) && id->nawupf) { + /* + * Use the per-namespace atomic write unit when available. + */ + atomic_bs = (1 + le16_to_cpu(id->nawupf)) * bs; + if (id->nabspf) boundary = (le16_to_cpu(id->nabspf) + 1) * bs; + } else { + /* + * Use the controller wide atomic write unit. This sucks + * because the limit is defined in terms of logical blocks while + * namespaces can have different formats, and because there is + * no clear language in the specification prohibiting different + * values for different controllers in the subsystem. + */ + atomic_bs = (1 + ns->ctrl->awupf) * bs; + } + + if (!ns->ctrl->subsys->atomic_bs) { + ns->ctrl->subsys->atomic_bs = atomic_bs; + } else if (ns->ctrl->subsys->atomic_bs != atomic_bs) { + dev_err_ratelimited(ns->ctrl->device, + "%s: Inconsistent Atomic Write Size, Namespace will not be added: Subsystem=%d bytes, Controller/Namespace=%d bytes\n", + ns->disk ? ns->disk->disk_name : "?", + ns->ctrl->subsys->atomic_bs, + atomic_bs); } + lim->atomic_write_hw_max = atomic_bs; lim->atomic_write_hw_boundary = boundary; lim->atomic_write_hw_unit_min = bs; lim->atomic_write_hw_unit_max = rounddown_pow_of_two(atomic_bs); + return atomic_bs; } static u32 nvme_max_drv_segments(struct nvme_ctrl *ctrl)
@@ -2046,34 +2076,8 @@ static bool nvme_update_disk_info(struct nvme_ns *ns, struct nvme_id_ns *id, valid = false; } - atomic_bs = phys_bs = bs; - if (id->nabo == 0) { - /* - * Bit 1 indicates whether NAWUPF is defined for this namespace - * and whether it should be used instead of AWUPF. If NAWUPF == - * 0 then AWUPF must be used instead. - */ - if (id->nsfeat & NVME_NS_FEAT_ATOMICS && id->nawupf) - atomic_bs = (1 + le16_to_cpu(id->nawupf)) * bs; - else - atomic_bs = (1 + ns->ctrl->awupf) * bs; - - /* - * Set subsystem atomic bs. - */ - if (ns->ctrl->subsys->atomic_bs) { - if (atomic_bs != ns->ctrl->subsys->atomic_bs) { - dev_err_ratelimited(ns->ctrl->device, - "%s: Inconsistent Atomic Write Size, Namespace will not be added: Subsystem=%d bytes, Controller/Namespace=%d bytes\n", - ns->disk ? ns->disk->disk_name : "?", - ns->ctrl->subsys->atomic_bs, - atomic_bs); - } - } else - ns->ctrl->subsys->atomic_bs = atomic_bs; - - nvme_update_atomic_write_disk_info(ns, id, lim, bs, atomic_bs); - } + phys_bs = bs; + atomic_bs = nvme_configure_atomic_write(ns, id, lim, bs); if (id->nsfeat & NVME_NS_FEAT_IO_OPT) { /* NPWG = Namespace Preferred Write Granularity */
@@ -2097,6 +2101,7 @@ static bool nvme_update_disk_info(struct nvme_ns *ns, struct nvme_id_ns *id, lim->max_write_zeroes_sectors = UINT_MAX; else lim->max_write_zeroes_sectors = ns->ctrl->max_zeroes_sectors; + nvme_config_discard(ns, lim); return valid; }
@@ -2171,6 +2176,7 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns, struct nvme_id_ns *id; sector_t capacity; unsigned lbaf; + bool valid; int ret; ret = nvme_identify_ns(ns->ctrl, info->nsid, &id);
@@ -2207,20 +2213,22 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns, nvme_set_ctrl_limits(ns->ctrl, &lim); nvme_configure_metadata(ns->ctrl, ns->head, id, nvm, info); nvme_set_chunk_sectors(ns, id, &lim); - if (!nvme_update_disk_info(ns, id, &lim)) - capacity = 0; + valid = nvme_update_disk_info(ns, id, &lim); /* * Validate the max atomic write size fits within the subsystem's * atomic write capabilities. */ if (lim.atomic_write_hw_max > ns->ctrl->subsys->atomic_bs) { - blk_mq_unfreeze_queue(ns->disk->queue, memflags); + queue_limits_cancel_update(ns->disk->queue); + blk_mq_unfreeze_queue(ns->disk->queue); ret = -ENXIO; goto out; } - nvme_config_discard(ns, &lim); + if (!valid) + capacity = 0; + if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) && ns->head->ids.csi == NVME_CSI_ZNS) nvme_update_zone_info(ns, &lim, &zi);
--
2.53.0