shinys000114/linux
1
0
Fork 0
mirror of https://github.com/hardkernel/linux.git synced 2026-06-06 10:58:48 +09:00
Code Issues Packages Projects Releases Wiki Activity

UPSTREAM: scsi: ufs: Optimize the command queueing code

Browse Source 
Remove the clock scaling lock from ufshcd_queuecommand() since it is a
performance bottleneck. Instead check the SCSI device budget bitmaps in the
code that waits for ongoing ufshcd_queuecommand() calls. A bit is set in
sdev->budget_map just before scsi_queue_rq() is called and a bit is cleared
from that bitmap if scsi_queue_rq() does not submit the request or after
the request has finished. See also the blk_mq_{get,put}_dispatch_budget()
calls in the block layer.

There is no risk for a livelock since the block layer delays queue reruns
if queueing a request fails because the SCSI host has been blocked.

Link: https://lore.kernel.org/r/20211203231950.193369-17-bvanassche@acm.org
Cc: Asutosh Das (asd) <asutoshd@codeaurora.org>
Reviewed-by: Asutosh Das <asutoshd@codeaurora.org>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Bug: 234653003
(cherry picked from commit 8d077ede48)
Change-Id: I8f9e5c07bf7effd8a8df13de187c4a3190acffd7
Signed-off-by: Bart Van Assche <bvanassche@google.com>
This commit is contained in:
Bart Van Assche
2021-12-03 15:19:49 -08:00
committed by Bart Van Assche
parent 82c80c5065
commit ccf604bdef
2 changed files with 24 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

33
drivers/scsi/ufs/ufshcd.c
View File

@@ -1088,6 +1088,24 @@ static bool ufshcd_is_devfreq_scaling_required(struct ufs_hba *hba,
return false;
}
/*
* Determine the number of pending commands by counting the bits in the SCSI
* device budget maps. This approach has been selected because a bit is set in
* the budget map before scsi_host_queue_ready() checks the host_self_blocked
* flag. The host_self_blocked flag can be modified by calling
* scsi_block_requests() or scsi_unblock_requests().
*/
static u32 ufshcd_pending_cmds(struct ufs_hba *hba)
{
struct scsi_device *sdev;
u32 pending = 0;
shost_for_each_device(sdev, hba->host)
pending += sbitmap_weight(&sdev->budget_map);
return pending;
}
/*
* Wait until all pending SCSI commands and TMFs have finished or the timeout
* has expired.
@@ -1100,7 +1118,7 @@ static int ufshcd_wait_for_doorbell_clr(struct ufs_hba *hba,
unsigned long flags;
int ret = 0;
u32 tm_doorbell;
u32 tr_doorbell;
u32 tr_pending;
bool timeout = false, do_last_check = false;
ktime_t start;
@@ -1118,8 +1136,8 @@ static int ufshcd_wait_for_doorbell_clr(struct ufs_hba *hba,
}
tm_doorbell = ufshcd_readl(hba, REG_UTP_TASK_REQ_DOOR_BELL);
tr_doorbell = ufshcd_readl(hba, REG_UTP_TRANSFER_REQ_DOOR_BELL);
if (!tm_doorbell && !tr_doorbell) {
tr_pending = ufshcd_pending_cmds(hba);
if (!tm_doorbell && !tr_pending) {
timeout = false;
break;
} else if (do_last_check) {
@@ -1139,12 +1157,12 @@ static int ufshcd_wait_for_doorbell_clr(struct ufs_hba *hba,
do_last_check = true;
}
spin_lock_irqsave(hba->host->host_lock, flags);
} while (tm_doorbell || tr_doorbell);
} while (tm_doorbell || tr_pending);
if (timeout) {
dev_err(hba->dev,
"%s: timedout waiting for doorbell to clear (tm=0x%x, tr=0x%x)\n",
__func__, tm_doorbell, tr_doorbell);
__func__, tm_doorbell, tr_pending);
ret = -EBUSY;
}
out:
@@ -2742,9 +2760,6 @@ static int ufshcd_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd)
WARN_ONCE(tag < 0, "Invalid tag %d\n", tag);
if (!down_read_trylock(&hba->clk_scaling_lock))
return SCSI_MLQUEUE_HOST_BUSY;
/*
* Allows the UFS error handler to wait for prior ufshcd_queuecommand()
* calls.
@@ -2841,8 +2856,6 @@ static int ufshcd_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd)
out:
rcu_read_unlock();
up_read(&hba->clk_scaling_lock);
if (ufs_trigger_eh()) {
unsigned long flags;

1
drivers/scsi/ufs/ufshcd.h
View File

@@ -814,6 +814,7 @@ struct ufs_hba_monitor {
* @clk_list_head: UFS host controller clocks list node head
* @pwr_info: holds current power mode
* @max_pwr_info: keeps the device max valid pwm
* @clk_scaling_lock: used to serialize device commands and clock scaling
* @desc_size: descriptor sizes reported by device
* @urgent_bkops_lvl: keeps track of urgent bkops level for device
* @is_urgent_bkops_lvl_checked: keeps track if the urgent bkops level for