From: Anastasia Kovaleva <a.kovaleva@yadro.com>
To: <target-devel@vger.kernel.org>
Cc: <linux-scsi@vger.kernel.org>, <linux@yadro.com>
Subject: [PATCH 1/3] target: core: Send mtl in blocks
Date: Thu, 30 Jun 2022 15:22:39 +0300 [thread overview]
Message-ID: <20220630122241.1658-2-a.kovaleva@yadro.com> (raw)
In-Reply-To: <20220630122241.1658-1-a.kovaleva@yadro.com>
A MAXIMUM TRANSFER LENGTH value indicates the maximum transfer length in
logical blocks that the device server accepts for a single command. Fix
function sending the length in sectors instead of blocks.
This patch also removes the special casing for fileio in
block_size_store since this logic in now unified in
spc_emulate_evpd_b0() for all backends.
Signed-off-by: Anastasia Kovaleva <a.kovaleva@yadro.com>
Reviewed-by: Konstantin Shelekhin <k.shelekhin@yadro.com>
Reviewed-by: Dmitriy Bogdanov <d.bogdanov@yadro.com>
---
drivers/target/target_core_configfs.c | 2 --
drivers/target/target_core_file.c | 1 -
drivers/target/target_core_spc.c | 7 ++++++-
include/target/target_core_base.h | 1 -
4 files changed, 6 insertions(+), 5 deletions(-)
diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c
index bbcbbfa72b07..51943369887a 100644
--- a/drivers/target/target_core_configfs.c
+++ b/drivers/target/target_core_configfs.c
@@ -1089,8 +1089,6 @@ static ssize_t block_size_store(struct config_item *item,
}
da->block_size = val;
- if (da->max_bytes_per_io)
- da->hw_max_sectors = da->max_bytes_per_io / val;
pr_debug("dev[%p]: SE Device block_size changed to %u\n",
da->da_dev, val);
diff --git a/drivers/target/target_core_file.c b/drivers/target/target_core_file.c
index e68f1cc8ef98..dcf4c8e47e8b 100644
--- a/drivers/target/target_core_file.c
+++ b/drivers/target/target_core_file.c
@@ -189,7 +189,6 @@ static int fd_configure_device(struct se_device *dev)
}
dev->dev_attrib.hw_block_size = fd_dev->fd_block_size;
- dev->dev_attrib.max_bytes_per_io = FD_MAX_BYTES;
dev->dev_attrib.hw_max_sectors = FD_MAX_BYTES / fd_dev->fd_block_size;
dev->dev_attrib.hw_queue_depth = FD_MAX_DEVICE_QUEUE_DEPTH;
diff --git a/drivers/target/target_core_spc.c b/drivers/target/target_core_spc.c
index c14441c89bed..c3d90e811617 100644
--- a/drivers/target/target_core_spc.c
+++ b/drivers/target/target_core_spc.c
@@ -513,6 +513,7 @@ spc_emulate_evpd_b0(struct se_cmd *cmd, unsigned char *buf)
struct se_device *dev = cmd->se_dev;
u32 mtl = 0;
int have_tp = 0, opt, min;
+ u32 io_max_blocks;
/*
* Following spc3r22 section 6.5.3 Block Limits VPD page, when
@@ -547,11 +548,15 @@ spc_emulate_evpd_b0(struct se_cmd *cmd, unsigned char *buf)
* XXX: Currently assumes single PAGE_SIZE per scatterlist for fabrics
* enforcing maximum HW scatter-gather-list entry limit
*/
+ io_max_blocks = mult_frac(
+ dev->dev_attrib.hw_max_sectors,
+ dev->dev_attrib.hw_block_size,
+ dev->dev_attrib.block_size);
if (cmd->se_tfo->max_data_sg_nents) {
mtl = (cmd->se_tfo->max_data_sg_nents * PAGE_SIZE) /
dev->dev_attrib.block_size;
}
- put_unaligned_be32(min_not_zero(mtl, dev->dev_attrib.hw_max_sectors), &buf[8]);
+ put_unaligned_be32(min_not_zero(mtl, io_max_blocks), &buf[8]);
/*
* Set OPTIMAL TRANSFER LENGTH
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index c2b36f7d917d..748d1afbadaa 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -709,7 +709,6 @@ struct se_dev_attrib {
u32 unmap_granularity;
u32 unmap_granularity_alignment;
u32 max_write_same_len;
- u32 max_bytes_per_io;
struct se_device *da_dev;
struct config_group da_group;
};
--
2.30.2
next prev parent reply other threads:[~2022-06-30 12:33 UTC|newest]
Thread overview: 10+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-06-30 12:22 [PATCH 0/3] Make target send correct io limits Anastasia Kovaleva
2022-06-30 12:22 ` Anastasia Kovaleva [this message]
2022-07-07 21:34 ` [PATCH 1/3] target: core: Send mtl in blocks Mike Christie
2022-06-30 12:22 ` [PATCH 2/3] target: core: make hw_max_sectors store the sectors amount " Anastasia Kovaleva
2022-07-07 21:38 ` Mike Christie
2022-06-30 12:22 ` [PATCH 3/3] target: core: Change the way target_xcopy_do_work sets restiction on max io Anastasia Kovaleva
2022-07-01 3:43 ` kernel test robot
2022-07-01 4:35 ` kernel test robot
2022-07-02 11:47 ` kernel test robot
2022-07-07 22:37 ` Mike Christie
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20220630122241.1658-2-a.kovaleva@yadro.com \
--to=a.kovaleva@yadro.com \
--cc=linux-scsi@vger.kernel.org \
--cc=linux@yadro.com \
--cc=target-devel@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).