nvme: implement the DEAC bit for the Write Zeroes command

While the specification allows devices to either deallocate data
or to actually write zeroes on any Write Zeroes command, many SSDs
only do the sensible thing and deallocate data when the DEAC bit
is specific.  Set it when it is supported and the caller doesn't
explicitly opt out of deallocation.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index f94b05c585cbcec4006accaa51f8e36b06e0adf0..1a87a072fbed356374ee5672f6879c4b864003fe 100644 (file)
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -850,8 +850,11 @@ static inline blk_status_t nvme_setup_write_zeroes(struct nvme_ns *ns,
        cmnd->write_zeroes.length =
                cpu_to_le16((blk_rq_bytes(req) >> ns->lba_shift) - 1);
 
+       if (!(req->cmd_flags & REQ_NOUNMAP) && (ns->features & NVME_NS_DEAC))
+               cmnd->write_zeroes.control |= cpu_to_le16(NVME_WZ_DEAC);
+
        if (nvme_ns_has_pi(ns)) {
-               cmnd->write_zeroes.control = cpu_to_le16(NVME_RW_PRINFO_PRACT);
+               cmnd->write_zeroes.control |= cpu_to_le16(NVME_RW_PRINFO_PRACT);
 
                switch (ns->pi_type) {
                case NVME_NS_DPS_PI_TYPE1:
@@ -2003,6 +2006,14 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns,
                }
        }
 
+       /*
+        * Only set the DEAC bit if the device guarantees that reads from
+        * deallocated data return zeroes.  While the DEAC bit does not
+        * require that, it must be a no-op if reads from deallocated data
+        * do not return zeroes.
+        */
+       if ((id->dlfeat & 0x7) == 0x1 && (id->dlfeat & (1 << 3)))
+               ns->features |= NVME_NS_DEAC;
        set_disk_ro(ns->disk, nvme_ns_is_readonly(ns, info));
        set_bit(NVME_NS_READY, &ns->flags);
        blk_mq_unfreeze_queue(ns->disk->queue);

diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index f9df10653f3c5aeb7b00a975c6ee3268496cfa53..16b34a49149596525f07ad1e9f71103e002aa4cb 100644 (file)
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -455,6 +455,7 @@ static inline bool nvme_ns_head_multipath(struct nvme_ns_head *head)
 enum nvme_ns_features {
        NVME_NS_EXT_LBAS = 1 << 0, /* support extended LBA format */
        NVME_NS_METADATA_SUPPORTED = 1 << 1, /* support getting generated md */
+       NVME_NS_DEAC,           /* DEAC bit in Write Zeores supported */
 };
 
 struct nvme_ns {

diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index 1d102b662e887f7327c8e4b23817ca72c16cb564..d6be2a6861000e970050ee3a72730297fa68f247 100644 (file)
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -964,6 +964,7 @@ enum {
        NVME_RW_PRINFO_PRCHK_GUARD      = 1 << 12,
        NVME_RW_PRINFO_PRACT            = 1 << 13,
        NVME_RW_DTYPE_STREAMS           = 1 << 4,
+       NVME_WZ_DEAC                    = 1 << 9,
 };
 
 struct nvme_dsm_cmd {