[PATCH v2 15/16] nvme: Support atomic writes

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



From: Alan Adamson <alan.adamson@xxxxxxxxxx>

Support reading atomic write registers to fill in request_queue
properties.

Use following method to calculate limits:
atomic_write_max_bytes = flp2(NAWUPF ?: AWUPF)
atomic_write_unit_min = logical_block_size
atomic_write_unit_max = flp2(NAWUPF ?: AWUPF)
atomic_write_boundary = NABSPF

Signed-off-by: Alan Adamson <alan.adamson@xxxxxxxxxx>
#jpg: some rewrite
Signed-off-by: John Garry <john.g.garry@xxxxxxxxxx>
---
 drivers/nvme/host/core.c | 85 ++++++++++++++++++++++++++++++----------
 1 file changed, 64 insertions(+), 21 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 8ebdfd623e0f..fd4f09f9dbe8 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1894,12 +1894,68 @@ static void nvme_set_queue_limits(struct nvme_ctrl *ctrl,
 	blk_queue_write_cache(q, vwc, vwc);
 }
 
+static void nvme_update_atomic_write_disk_info(struct gendisk *disk,
+		struct nvme_ns *ns, struct nvme_id_ns *id, u32 bs, u32 phys_bs)
+{
+	unsigned int max_bytes = 0, unit_min = 0, unit_max = 0, boundary = 0;
+	u32 atomic_bs = bs;
+
+	if (id->nabo == 0) {
+		unsigned int ns_boundary;
+
+		/*
+		 * 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->subsys->awupf) * bs;
+
+		if (le16_to_cpu(id->nabspf))
+			ns_boundary = (le16_to_cpu(id->nabspf) + 1) * bs;
+		else
+			ns_boundary = 0;
+
+		/*
+		 * The boundary size just needs to be a multiple
+		 * of unit_max (and not necessarily a power-of-2), so
+		 * this could be relaxed in the block layer in future.
+		 */
+		if (!ns_boundary || is_power_of_2(ns_boundary)) {
+			max_bytes = atomic_bs;
+			unit_min = bs >> SECTOR_SHIFT;
+			unit_max = rounddown_pow_of_two(atomic_bs) >> SECTOR_SHIFT;
+			boundary = ns_boundary;
+		} else {
+			dev_notice(ns->ctrl->device, "Unsupported atomic write boundary (%d bytes)\n",
+				ns_boundary);
+		}
+	} else {
+		dev_info(ns->ctrl->device, "Atomic writes not supported for NABO set (%d blocks)\n",
+				id->nabo);
+	}
+
+	blk_queue_atomic_write_max_bytes(disk->queue, atomic_bs);
+	blk_queue_atomic_write_unit_min_sectors(disk->queue, bs >> SECTOR_SHIFT);
+	blk_queue_atomic_write_unit_max_sectors(disk->queue,
+		rounddown_pow_of_two(atomic_bs) >> SECTOR_SHIFT);
+	blk_queue_atomic_write_boundary_bytes(disk->queue, boundary);
+
+	/*
+	 * Linux filesystems assume writing a single physical block is
+	 * an atomic operation. Hence limit the physical block size to the
+	 * value of the Atomic Write Unit Power Fail parameter.
+	 */
+	blk_queue_physical_block_size(disk->queue, min(phys_bs, atomic_bs));
+}
+
 static void nvme_update_disk_info(struct gendisk *disk,
 		struct nvme_ns *ns, struct nvme_id_ns *id)
 {
 	sector_t capacity = nvme_lba_to_sect(ns, le64_to_cpu(id->nsze));
-	u32 bs = 1U << ns->lba_shift;
-	u32 atomic_bs, phys_bs, io_opt = 0;
+	u32 bs, phys_bs, io_opt = 0;
 
 	/*
 	 * The block layer can't support LBA sizes larger than the page size
@@ -1909,37 +1965,24 @@ static void nvme_update_disk_info(struct gendisk *disk,
 	if (ns->lba_shift > PAGE_SHIFT || ns->lba_shift < SECTOR_SHIFT) {
 		capacity = 0;
 		bs = (1 << 9);
+	} else {
+		bs = 1U << ns->lba_shift;
 	}
 
 	blk_integrity_unregister(disk);
 
-	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->subsys->awupf) * bs;
-	}
-
 	if (id->nsfeat & NVME_NS_FEAT_IO_OPT) {
 		/* NPWG = Namespace Preferred Write Granularity */
 		phys_bs = bs * (1 + le16_to_cpu(id->npwg));
 		/* NOWS = Namespace Optimal Write Size */
 		io_opt = bs * (1 + le16_to_cpu(id->nows));
+	} else {
+		phys_bs = bs;
 	}
 
+	nvme_update_atomic_write_disk_info(disk, ns, id, bs, phys_bs);
+
 	blk_queue_logical_block_size(disk->queue, bs);
-	/*
-	 * Linux filesystems assume writing a single physical block is
-	 * an atomic operation. Hence limit the physical block size to the
-	 * value of the Atomic Write Unit Power Fail parameter.
-	 */
-	blk_queue_physical_block_size(disk->queue, min(phys_bs, atomic_bs));
 	blk_queue_io_min(disk->queue, phys_bs);
 	blk_queue_io_opt(disk->queue, io_opt);
 
-- 
2.35.3





[Index of Archives]     [Linux Ext4 Filesystem]     [Union Filesystem]     [Filesystem Testing]     [Ceph Users]     [Ecryptfs]     [NTFS 3]     [AutoFS]     [Kernel Newbies]     [Share Photos]     [Security]     [Netfilter]     [Bugtraq]     [Yosemite News]     [MIPS Linux]     [ARM Linux]     [Linux Security]     [Linux Cachefs]     [Reiser Filesystem]     [Linux RAID]     [NTFS 3]     [Samba]     [Device Mapper]     [CEPH Development]

  Powered by Linux