[f2fs-dev] [UFS v3] UFS fixes

[f2fs-dev] [UFS v3] UFS fixes

[Jaegeuk Kim]

Change log from v2:
 - use active_req-- instead of __ufshcd_release to avoid UFS timeout

Change log from v1:
 - remove clkgating_enable check in __ufshcd_release
 - use __uhfshcd_release instead of active_req.




_______________________________________________
Linux-f2fs-devel mailing list
Linux-f2fs-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel

[f2fs-dev] [PATCH v3 1/5] scsi: ufs: atomic update for clkgating_enable

[Jaegeuk Kim]

From: Jaegeuk Kim <jaegeuk@google.com>

When giving a stress test which enables/disables clkgating, we hit device
timeout sometimes. This patch avoids subtle racy condition to address it.

If we use __ufshcd_release(), I've seen that gate_work can be called in parallel
with ungate_work, which results in UFS timeout when doing hibern8.
Should avoid it.

Signed-off-by: Jaegeuk Kim <jaegeuk@google.com>
---
 drivers/scsi/ufs/ufshcd.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index b8f573a02713..e0b479f9eb8a 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -1807,19 +1807,19 @@ static ssize_t ufshcd_clkgate_enable_store(struct device *dev,
 		return -EINVAL;
 
 	value = !!value;
+
+	spin_lock_irqsave(hba->host->host_lock, flags);
 	if (value == hba->clk_gating.is_enabled)
 		goto out;
 
-	if (value) {
-		ufshcd_release(hba);
-	} else {
-		spin_lock_irqsave(hba->host->host_lock, flags);
+	if (value)
+		hba->clk_gating.active_reqs--;
+	else
 		hba->clk_gating.active_reqs++;
-		spin_unlock_irqrestore(hba->host->host_lock, flags);
-	}
 
 	hba->clk_gating.is_enabled = value;
 out:
+	spin_unlock_irqrestore(hba->host->host_lock, flags);
 	return count;
 }
 
-- 
2.29.0.rc1.297.gfa9743e501-goog



_______________________________________________
Linux-f2fs-devel mailing list
Linux-f2fs-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel

[f2fs-dev] [PATCH v3 2/5] scsi: ufs: clear UAC for FFU and RPMB LUNs

[Jaegeuk Kim]

From: Jaegeuk Kim <jaegeuk@google.com>

In order to conduct FFU or RPMB operations, UFS needs to clear UAC. This patch
clears it explicitly, so that we could get no failure given early execution.

Signed-off-by: Jaegeuk Kim <jaegeuk@google.com>
---
 drivers/scsi/ufs/ufshcd.c | 70 +++++++++++++++++++++++++++++++++++----
 drivers/scsi/ufs/ufshcd.h |  1 +
 2 files changed, 65 insertions(+), 6 deletions(-)

diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index e0b479f9eb8a..011e80a21170 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -7057,7 +7057,6 @@ static inline void ufshcd_blk_pm_runtime_init(struct scsi_device *sdev)
 static int ufshcd_scsi_add_wlus(struct ufs_hba *hba)
 {
 	int ret = 0;
-	struct scsi_device *sdev_rpmb;
 	struct scsi_device *sdev_boot;
 
 	hba->sdev_ufs_device = __scsi_add_device(hba->host, 0, 0,
@@ -7070,14 +7069,14 @@ static int ufshcd_scsi_add_wlus(struct ufs_hba *hba)
 	ufshcd_blk_pm_runtime_init(hba->sdev_ufs_device);
 	scsi_device_put(hba->sdev_ufs_device);
 
-	sdev_rpmb = __scsi_add_device(hba->host, 0, 0,
+	hba->sdev_rpmb = __scsi_add_device(hba->host, 0, 0,
 		ufshcd_upiu_wlun_to_scsi_wlun(UFS_UPIU_RPMB_WLUN), NULL);
-	if (IS_ERR(sdev_rpmb)) {
-		ret = PTR_ERR(sdev_rpmb);
+	if (IS_ERR(hba->sdev_rpmb)) {
+		ret = PTR_ERR(hba->sdev_rpmb);
 		goto remove_sdev_ufs_device;
 	}
-	ufshcd_blk_pm_runtime_init(sdev_rpmb);
-	scsi_device_put(sdev_rpmb);
+	ufshcd_blk_pm_runtime_init(hba->sdev_rpmb);
+	scsi_device_put(hba->sdev_rpmb);
 
 	sdev_boot = __scsi_add_device(hba->host, 0, 0,
 		ufshcd_upiu_wlun_to_scsi_wlun(UFS_UPIU_BOOT_WLUN), NULL);
@@ -7601,6 +7600,63 @@ static int ufshcd_add_lus(struct ufs_hba *hba)
 	return ret;
 }
 
+static int
+ufshcd_send_request_sense(struct ufs_hba *hba, struct scsi_device *sdp);
+
+static int ufshcd_clear_ua_wlun(struct ufs_hba *hba, u8 wlun)
+{
+	struct scsi_device *sdp;
+	unsigned long flags;
+	int ret = 0;
+
+	spin_lock_irqsave(hba->host->host_lock, flags);
+	if (wlun  == UFS_UPIU_UFS_DEVICE_WLUN)
+		sdp = hba->sdev_ufs_device;
+	else if (wlun  == UFS_UPIU_RPMB_WLUN)
+		sdp = hba->sdev_rpmb;
+	else
+		BUG_ON(1);
+	if (sdp) {
+		ret = scsi_device_get(sdp);
+		if (!ret && !scsi_device_online(sdp)) {
+			ret = -ENODEV;
+			scsi_device_put(sdp);
+		}
+	} else {
+		ret = -ENODEV;
+	}
+	spin_unlock_irqrestore(hba->host->host_lock, flags);
+	if (ret)
+		goto out_err;
+
+	ret = ufshcd_send_request_sense(hba, sdp);
+	scsi_device_put(sdp);
+out_err:
+	if (ret)
+		dev_err(hba->dev, "%s: UAC clear LU=%x ret = %d\n",
+				__func__, wlun, ret);
+	return ret;
+}
+
+static int ufshcd_clear_ua_wluns(struct ufs_hba *hba)
+{
+	int ret = 0;
+
+	if (!hba->wlun_dev_clr_ua)
+		goto out;
+
+	ret = ufshcd_clear_ua_wlun(hba, UFS_UPIU_UFS_DEVICE_WLUN);
+	if (!ret)
+		ret = ufshcd_clear_ua_wlun(hba, UFS_UPIU_RPMB_WLUN);
+	if (!ret)
+		hba->wlun_dev_clr_ua = false;
+out:
+	if (ret)
+		dev_err(hba->dev, "%s: Failed to clear UAC WLUNS ret = %d\n",
+				__func__, ret);
+	return ret;
+}
+
 /**
  * ufshcd_probe_hba - probe hba to detect device and initialize
  * @hba: per-adapter instance
@@ -7720,6 +7776,8 @@ static void ufshcd_async_scan(void *data, async_cookie_t cookie)
 		pm_runtime_put_sync(hba->dev);
 		ufshcd_exit_clk_scaling(hba);
 		ufshcd_hba_exit(hba);
+	} else {
+		ufshcd_clear_ua_wluns(hba);
 	}
 }
 
diff --git a/drivers/scsi/ufs/ufshcd.h b/drivers/scsi/ufs/ufshcd.h
index 47eb1430274c..718881d038f5 100644
--- a/drivers/scsi/ufs/ufshcd.h
+++ b/drivers/scsi/ufs/ufshcd.h
@@ -681,6 +681,7 @@ struct ufs_hba {
 	 * "UFS device" W-LU.
 	 */
 	struct scsi_device *sdev_ufs_device;
+	struct scsi_device *sdev_rpmb;
 
 	enum ufs_dev_pwr_mode curr_dev_pwr_mode;
 	enum uic_link_state uic_link_state;
-- 
2.29.0.rc1.297.gfa9743e501-goog



_______________________________________________
Linux-f2fs-devel mailing list
Linux-f2fs-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel

[f2fs-dev] [PATCH v3 3/5] scsi: ufs: use WQ_HIGHPRI for gating work

[Jaegeuk Kim]

From: Jaegeuk Kim <jaegeuk@google.com>

Must have WQ_MEM_RECLAIM
``WQ_MEM_RECLAIM``
  All wq which might be used in the memory reclaim paths **MUST**
  have this flag set.  The wq is guaranteed to have at least one
  execution context regardless of memory pressure.

Signed-off-by: Jaegeuk Kim <jaegeuk@google.com>
---
 drivers/scsi/ufs/ufshcd.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index 011e80a21170..bc0d623aed66 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -1867,7 +1867,7 @@ static void ufshcd_init_clk_gating(struct ufs_hba *hba)
 	snprintf(wq_name, ARRAY_SIZE(wq_name), "ufs_clk_gating_%d",
 		 hba->host->host_no);
 	hba->clk_gating.clk_gating_workq = alloc_ordered_workqueue(wq_name,
-							   WQ_MEM_RECLAIM);
+					WQ_MEM_RECLAIM | WQ_HIGHPRI);
 
 	hba->clk_gating.is_enabled = true;
 
-- 
2.29.0.rc1.297.gfa9743e501-goog



_______________________________________________
Linux-f2fs-devel mailing list
Linux-f2fs-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel

[f2fs-dev] [PATCH v3 4/5] scsi: add more contexts in the ufs tracepoints

[Jaegeuk Kim]

From: Jaegeuk Kim <jaegeuk@google.com>

This adds user-friendly tracepoints with group id.

Reviewed-by: Can Guo <cang@codeaurora.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@google.com>
---
 drivers/scsi/ufs/ufshcd.c  |  6 ++++--
 include/trace/events/ufs.h | 21 +++++++++++++++++----
 2 files changed, 21 insertions(+), 6 deletions(-)

diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index bc0d623aed66..c94610cbecae 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -348,7 +348,7 @@ static void ufshcd_add_command_trace(struct ufs_hba *hba,
 		unsigned int tag, const char *str)
 {
 	sector_t lba = -1;
-	u8 opcode = 0;
+	u8 opcode = 0, group_id = 0;
 	u32 intr, doorbell;
 	struct ufshcd_lrb *lrbp = &hba->lrb[tag];
 	struct scsi_cmnd *cmd = lrbp->cmd;
@@ -374,13 +374,15 @@ static void ufshcd_add_command_trace(struct ufs_hba *hba,
 				lba = cmd->request->bio->bi_iter.bi_sector;
 			transfer_len = be32_to_cpu(
 				lrbp->ucd_req_ptr->sc.exp_data_transfer_len);
+			if (opcode == WRITE_10)
+				group_id = lrbp->cmd->cmnd[6];
 		}
 	}
 
 	intr = ufshcd_readl(hba, REG_INTERRUPT_STATUS);
 	doorbell = ufshcd_readl(hba, REG_UTP_TRANSFER_REQ_DOOR_BELL);
 	trace_ufshcd_command(dev_name(hba->dev), str, tag,
-				doorbell, transfer_len, intr, lba, opcode);
+			doorbell, transfer_len, intr, lba, opcode, group_id);
 }
 
 static void ufshcd_print_clk_freqs(struct ufs_hba *hba)
diff --git a/include/trace/events/ufs.h b/include/trace/events/ufs.h
index 84841b3a7ffd..50654f352639 100644
--- a/include/trace/events/ufs.h
+++ b/include/trace/events/ufs.h
@@ -11,6 +11,15 @@
 
 #include <linux/tracepoint.h>
 
+#define str_opcode(opcode)						\
+	__print_symbolic(opcode,					\
+		{ WRITE_16,		"WRITE_16" },			\
+		{ WRITE_10,		"WRITE_10" },			\
+		{ READ_16,		"READ_16" },			\
+		{ READ_10,		"READ_10" },			\
+		{ SYNCHRONIZE_CACHE,	"SYNC" },			\
+		{ UNMAP,		"UNMAP" })
+
 #define UFS_LINK_STATES			\
 	EM(UIC_LINK_OFF_STATE)		\
 	EM(UIC_LINK_ACTIVE_STATE)	\
@@ -215,9 +224,10 @@ DEFINE_EVENT(ufshcd_template, ufshcd_init,
 TRACE_EVENT(ufshcd_command,
 	TP_PROTO(const char *dev_name, const char *str, unsigned int tag,
 			u32 doorbell, int transfer_len, u32 intr, u64 lba,
-			u8 opcode),
+			u8 opcode, u8 group_id),
 
-	TP_ARGS(dev_name, str, tag, doorbell, transfer_len, intr, lba, opcode),
+	TP_ARGS(dev_name, str, tag, doorbell, transfer_len,
+				intr, lba, opcode, group_id),
 
 	TP_STRUCT__entry(
 		__string(dev_name, dev_name)
@@ -228,6 +238,7 @@ TRACE_EVENT(ufshcd_command,
 		__field(u32, intr)
 		__field(u64, lba)
 		__field(u8, opcode)
+		__field(u8, group_id)
 	),
 
 	TP_fast_assign(
@@ -239,13 +250,15 @@ TRACE_EVENT(ufshcd_command,
 		__entry->intr = intr;
 		__entry->lba = lba;
 		__entry->opcode = opcode;
+		__entry->group_id = group_id;
 	),
 
 	TP_printk(
-		"%s: %s: tag: %u, DB: 0x%x, size: %d, IS: %u, LBA: %llu, opcode: 0x%x",
+		"%s: %s: tag: %u, DB: 0x%x, size: %d, IS: %u, LBA: %llu, opcode: 0x%x (%s), group_id: 0x%x",
 		__get_str(str), __get_str(dev_name), __entry->tag,
 		__entry->doorbell, __entry->transfer_len,
-		__entry->intr, __entry->lba, (u32)__entry->opcode
+		__entry->intr, __entry->lba, (u32)__entry->opcode,
+		str_opcode(__entry->opcode), (u32)__entry->group_id
 	)
 );
 
-- 
2.29.0.rc1.297.gfa9743e501-goog



_______________________________________________
Linux-f2fs-devel mailing list
Linux-f2fs-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel

[f2fs-dev] [PATCH v3 5/5] scsi: ufs: fix clkgating on/off correctly

[Jaegeuk Kim]

The below call stack prevents clk_gating at every IO completion.
We can remove the condition, ufshcd_any_tag_in_use(), since clkgating_work
will check it again.

ufshcd_complete_requests(struct ufs_hba *hba)
  ufshcd_transfer_req_compl()
    __ufshcd_transfer_req_compl()
      __ufshcd_release(hba)
        if (ufshcd_any_tag_in_use() == 1)
           return;
  ufshcd_tmc_handler(hba);
    blk_mq_tagset_busy_iter();

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 drivers/scsi/ufs/ufshcd.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index c94610cbecae..38043c6b8d5f 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -1746,7 +1746,7 @@ static void __ufshcd_release(struct ufs_hba *hba)
 
 	if (hba->clk_gating.active_reqs || hba->clk_gating.is_suspended ||
 	    hba->ufshcd_state != UFSHCD_STATE_OPERATIONAL ||
-	    ufshcd_any_tag_in_use(hba) || hba->outstanding_tasks ||
+	    hba->outstanding_tasks ||
 	    hba->active_uic_cmd || hba->uic_async_done)
 		return;
 
-- 
2.29.0.rc1.297.gfa9743e501-goog



_______________________________________________
Linux-f2fs-devel mailing list
Linux-f2fs-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel

Re: [f2fs-dev] [PATCH v3 1/5] scsi: ufs: atomic update for clkgating_enable

[Can Guo]

On 2020-10-24 23:06, Jaegeuk Kim wrote:
> From: Jaegeuk Kim <jaegeuk@google.com>
> 
> When giving a stress test which enables/disables clkgating, we hit 
> device
> timeout sometimes. This patch avoids subtle racy condition to address 
> it.
> 
> If we use __ufshcd_release(), I've seen that gate_work can be called in 
> parallel
> with ungate_work, which results in UFS timeout when doing hibern8.
> Should avoid it.
> 

I don't understand this comment. gate_work and ungate_work are queued on
an ordered workqueue and an ordered workqueue executes at most one work 
item
at any given time in the queued order. How can the two run in parallel?

Thanks,

Can Guo.

> Signed-off-by: Jaegeuk Kim <jaegeuk@google.com>
> ---
>  drivers/scsi/ufs/ufshcd.c | 12 ++++++------
>  1 file changed, 6 insertions(+), 6 deletions(-)
> 
> diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
> index b8f573a02713..e0b479f9eb8a 100644
> --- a/drivers/scsi/ufs/ufshcd.c
> +++ b/drivers/scsi/ufs/ufshcd.c
> @@ -1807,19 +1807,19 @@ static ssize_t
> ufshcd_clkgate_enable_store(struct device *dev,
>  		return -EINVAL;
> 
>  	value = !!value;
> +
> +	spin_lock_irqsave(hba->host->host_lock, flags);
>  	if (value == hba->clk_gating.is_enabled)
>  		goto out;
> 
> -	if (value) {
> -		ufshcd_release(hba);
> -	} else {
> -		spin_lock_irqsave(hba->host->host_lock, flags);
> +	if (value)
> +		hba->clk_gating.active_reqs--;
> +	else
>  		hba->clk_gating.active_reqs++;
> -		spin_unlock_irqrestore(hba->host->host_lock, flags);
> -	}
> 
>  	hba->clk_gating.is_enabled = value;
>  out:
> +	spin_unlock_irqrestore(hba->host->host_lock, flags);
>  	return count;
>  }


_______________________________________________
Linux-f2fs-devel mailing list
Linux-f2fs-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel

Re: [f2fs-dev] [PATCH v3 1/5] scsi: ufs: atomic update for clkgating_enable

[Jaegeuk Kim]

On 10/26, Can Guo wrote:
> On 2020-10-24 23:06, Jaegeuk Kim wrote:
> > From: Jaegeuk Kim <jaegeuk@google.com>
> > 
> > When giving a stress test which enables/disables clkgating, we hit
> > device
> > timeout sometimes. This patch avoids subtle racy condition to address
> > it.
> > 
> > If we use __ufshcd_release(), I've seen that gate_work can be called in
> > parallel
> > with ungate_work, which results in UFS timeout when doing hibern8.
> > Should avoid it.
> > 
> 
> I don't understand this comment. gate_work and ungate_work are queued on
> an ordered workqueue and an ordered workqueue executes at most one work item
> at any given time in the queued order. How can the two run in parallel?

When I hit UFS stuck, I saw this by clkgating tracepoint.

- REQ_CLK_OFF
- CLKS_OFF
- REQ_CLK_OFF
- REQ_CLKS_ON
..

By using active_req, I don't see any problem.

> 
> Thanks,
> 
> Can Guo.
> 
> > Signed-off-by: Jaegeuk Kim <jaegeuk@google.com>
> > ---
> >  drivers/scsi/ufs/ufshcd.c | 12 ++++++------
> >  1 file changed, 6 insertions(+), 6 deletions(-)
> > 
> > diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
> > index b8f573a02713..e0b479f9eb8a 100644
> > --- a/drivers/scsi/ufs/ufshcd.c
> > +++ b/drivers/scsi/ufs/ufshcd.c
> > @@ -1807,19 +1807,19 @@ static ssize_t
> > ufshcd_clkgate_enable_store(struct device *dev,
> >  		return -EINVAL;
> > 
> >  	value = !!value;
> > +
> > +	spin_lock_irqsave(hba->host->host_lock, flags);
> >  	if (value == hba->clk_gating.is_enabled)
> >  		goto out;
> > 
> > -	if (value) {
> > -		ufshcd_release(hba);
> > -	} else {
> > -		spin_lock_irqsave(hba->host->host_lock, flags);
> > +	if (value)
> > +		hba->clk_gating.active_reqs--;
> > +	else
> >  		hba->clk_gating.active_reqs++;
> > -		spin_unlock_irqrestore(hba->host->host_lock, flags);
> > -	}
> > 
> >  	hba->clk_gating.is_enabled = value;
> >  out:
> > +	spin_unlock_irqrestore(hba->host->host_lock, flags);
> >  	return count;
> >  }


_______________________________________________
Linux-f2fs-devel mailing list
Linux-f2fs-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel

Re: [f2fs-dev] [PATCH v3 1/5] scsi: ufs: atomic update for clkgating_enable

[Can Guo]

On 2020-10-26 14:13, Jaegeuk Kim wrote:
> On 10/26, Can Guo wrote:
>> On 2020-10-24 23:06, Jaegeuk Kim wrote:
>> > From: Jaegeuk Kim <jaegeuk@google.com>
>> >
>> > When giving a stress test which enables/disables clkgating, we hit
>> > device
>> > timeout sometimes. This patch avoids subtle racy condition to address
>> > it.
>> >
>> > If we use __ufshcd_release(), I've seen that gate_work can be called in
>> > parallel
>> > with ungate_work, which results in UFS timeout when doing hibern8.
>> > Should avoid it.
>> >
>> 
>> I don't understand this comment. gate_work and ungate_work are queued 
>> on
>> an ordered workqueue and an ordered workqueue executes at most one 
>> work item
>> at any given time in the queued order. How can the two run in 
>> parallel?
> 
> When I hit UFS stuck, I saw this by clkgating tracepoint.
> 
> - REQ_CLK_OFF
> - CLKS_OFF
> - REQ_CLK_OFF
> - REQ_CLKS_ON
> ..
> 

I don't see how can you tell that the two works are running in parallel
just from above trace. May I know what is the exact error by "UFS 
timeout
when doing hibern8"?

By using __ufshcd_release() here, I do see one potential issue if your 
test
quickly toggles on/off of clk_gating - disable it, enable it, disable it 
and
enable it, which will cause that __ufshcd_release() being called twice, 
meaning
we queue two gate_works back to back. So can you try below code and let 
me know
if it helps or not? I am OK with your current change, but I would like 
to
understand the problem. Thanks.

diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index 1791bce..3eee438 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -2271,6 +2271,8 @@ static void ufshcd_gate_work(struct work_struct 
*work)
         unsigned long flags;

         spin_lock_irqsave(hba->host->host_lock, flags);
+       if (hba->clk_gating.state == CLKS_OFF)
+               goto rel_lock;
         /*
          * In case you are here to cancel this work the gating state
          * would be marked as REQ_CLKS_ON. In this case save time by

Regards,

Can Guo.

> By using active_req, I don't see any problem.
> 
>> 
>> Thanks,
>> 
>> Can Guo.
>> 
>> > Signed-off-by: Jaegeuk Kim <jaegeuk@google.com>
>> > ---
>> >  drivers/scsi/ufs/ufshcd.c | 12 ++++++------
>> >  1 file changed, 6 insertions(+), 6 deletions(-)
>> >
>> > diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
>> > index b8f573a02713..e0b479f9eb8a 100644
>> > --- a/drivers/scsi/ufs/ufshcd.c
>> > +++ b/drivers/scsi/ufs/ufshcd.c
>> > @@ -1807,19 +1807,19 @@ static ssize_t
>> > ufshcd_clkgate_enable_store(struct device *dev,
>> >  		return -EINVAL;
>> >
>> >  	value = !!value;
>> > +
>> > +	spin_lock_irqsave(hba->host->host_lock, flags);
>> >  	if (value == hba->clk_gating.is_enabled)
>> >  		goto out;
>> >
>> > -	if (value) {
>> > -		ufshcd_release(hba);
>> > -	} else {
>> > -		spin_lock_irqsave(hba->host->host_lock, flags);
>> > +	if (value)
>> > +		hba->clk_gating.active_reqs--;
>> > +	else
>> >  		hba->clk_gating.active_reqs++;
>> > -		spin_unlock_irqrestore(hba->host->host_lock, flags);
>> > -	}
>> >
>> >  	hba->clk_gating.is_enabled = value;
>> >  out:
>> > +	spin_unlock_irqrestore(hba->host->host_lock, flags);
>> >  	return count;
>> >  }


_______________________________________________
Linux-f2fs-devel mailing list
Linux-f2fs-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel

Re: [f2fs-dev] [PATCH v3 2/5] scsi: ufs: clear UAC for FFU and RPMB LUNs

[asutoshd]

On 2020-10-24 08:06, Jaegeuk Kim wrote:
> From: Jaegeuk Kim <jaegeuk@google.com>
> 
> In order to conduct FFU or RPMB operations, UFS needs to clear UAC. 
> This patch
> clears it explicitly, so that we could get no failure given early 
> execution.
> 

What's the meaning of 'given early execution'?

> Signed-off-by: Jaegeuk Kim <jaegeuk@google.com>
> ---
>  drivers/scsi/ufs/ufshcd.c | 70 +++++++++++++++++++++++++++++++++++----
>  drivers/scsi/ufs/ufshcd.h |  1 +
>  2 files changed, 65 insertions(+), 6 deletions(-)
> 
> diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
> index e0b479f9eb8a..011e80a21170 100644
> --- a/drivers/scsi/ufs/ufshcd.c
> +++ b/drivers/scsi/ufs/ufshcd.c
> @@ -7057,7 +7057,6 @@ static inline void
> ufshcd_blk_pm_runtime_init(struct scsi_device *sdev)
>  static int ufshcd_scsi_add_wlus(struct ufs_hba *hba)
>  {
>  	int ret = 0;
> -	struct scsi_device *sdev_rpmb;
>  	struct scsi_device *sdev_boot;
> 
>  	hba->sdev_ufs_device = __scsi_add_device(hba->host, 0, 0,
> @@ -7070,14 +7069,14 @@ static int ufshcd_scsi_add_wlus(struct ufs_hba 
> *hba)
>  	ufshcd_blk_pm_runtime_init(hba->sdev_ufs_device);
>  	scsi_device_put(hba->sdev_ufs_device);
> 
> -	sdev_rpmb = __scsi_add_device(hba->host, 0, 0,
> +	hba->sdev_rpmb = __scsi_add_device(hba->host, 0, 0,
>  		ufshcd_upiu_wlun_to_scsi_wlun(UFS_UPIU_RPMB_WLUN), NULL);
> -	if (IS_ERR(sdev_rpmb)) {
> -		ret = PTR_ERR(sdev_rpmb);
> +	if (IS_ERR(hba->sdev_rpmb)) {
> +		ret = PTR_ERR(hba->sdev_rpmb);
>  		goto remove_sdev_ufs_device;
>  	}
> -	ufshcd_blk_pm_runtime_init(sdev_rpmb);
> -	scsi_device_put(sdev_rpmb);
> +	ufshcd_blk_pm_runtime_init(hba->sdev_rpmb);
> +	scsi_device_put(hba->sdev_rpmb);
> 
>  	sdev_boot = __scsi_add_device(hba->host, 0, 0,
>  		ufshcd_upiu_wlun_to_scsi_wlun(UFS_UPIU_BOOT_WLUN), NULL);
> @@ -7601,6 +7600,63 @@ static int ufshcd_add_lus(struct ufs_hba *hba)
>  	return ret;
>  }
> 
> +static int
> +ufshcd_send_request_sense(struct ufs_hba *hba, struct scsi_device 
> *sdp);
> +
> +static int ufshcd_clear_ua_wlun(struct ufs_hba *hba, u8 wlun)
> +{
> +	struct scsi_device *sdp;
> +	unsigned long flags;
> +	int ret = 0;
> +
> +	spin_lock_irqsave(hba->host->host_lock, flags);
> +	if (wlun  == UFS_UPIU_UFS_DEVICE_WLUN)
> +		sdp = hba->sdev_ufs_device;
> +	else if (wlun  == UFS_UPIU_RPMB_WLUN)
> +		sdp = hba->sdev_rpmb;
> +	else
> +		BUG_ON(1);
> +	if (sdp) {
> +		ret = scsi_device_get(sdp);
> +		if (!ret && !scsi_device_online(sdp)) {
> +			ret = -ENODEV;
> +			scsi_device_put(sdp);
> +		}
> +	} else {
> +		ret = -ENODEV;
> +	}
> +	spin_unlock_irqrestore(hba->host->host_lock, flags);
> +	if (ret)
> +		goto out_err;
> +
> +	ret = ufshcd_send_request_sense(hba, sdp);
> +	scsi_device_put(sdp);
> +out_err:
> +	if (ret)
> +		dev_err(hba->dev, "%s: UAC clear LU=%x ret = %d\n",
> +				__func__, wlun, ret);
> +	return ret;
> +}
> +
> +static int ufshcd_clear_ua_wluns(struct ufs_hba *hba)
> +{
> +	int ret = 0;
> +
> +	if (!hba->wlun_dev_clr_ua)
> +		goto out;
> +
> +	ret = ufshcd_clear_ua_wlun(hba, UFS_UPIU_UFS_DEVICE_WLUN);
> +	if (!ret)
> +		ret = ufshcd_clear_ua_wlun(hba, UFS_UPIU_RPMB_WLUN);
> +	if (!ret)
> +		hba->wlun_dev_clr_ua = false;
> +out:
> +	if (ret)
> +		dev_err(hba->dev, "%s: Failed to clear UAC WLUNS ret = %d\n",
> +				__func__, ret);
> +	return ret;
> +}
> +
>  /**
>   * ufshcd_probe_hba - probe hba to detect device and initialize
>   * @hba: per-adapter instance
> @@ -7720,6 +7776,8 @@ static void ufshcd_async_scan(void *data,
> async_cookie_t cookie)
>  		pm_runtime_put_sync(hba->dev);
>  		ufshcd_exit_clk_scaling(hba);
>  		ufshcd_hba_exit(hba);
> +	} else {
> +		ufshcd_clear_ua_wluns(hba);
>  	}
>  }
> 
> diff --git a/drivers/scsi/ufs/ufshcd.h b/drivers/scsi/ufs/ufshcd.h
> index 47eb1430274c..718881d038f5 100644
> --- a/drivers/scsi/ufs/ufshcd.h
> +++ b/drivers/scsi/ufs/ufshcd.h
> @@ -681,6 +681,7 @@ struct ufs_hba {
>  	 * "UFS device" W-LU.
>  	 */
>  	struct scsi_device *sdev_ufs_device;
> +	struct scsi_device *sdev_rpmb;
> 
>  	enum ufs_dev_pwr_mode curr_dev_pwr_mode;
>  	enum uic_link_state uic_link_state;


_______________________________________________
Linux-f2fs-devel mailing list
Linux-f2fs-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel

Re: [f2fs-dev] [PATCH v3 3/5] scsi: ufs: use WQ_HIGHPRI for gating work

[asutoshd]

On 2020-10-24 08:06, Jaegeuk Kim wrote:
> From: Jaegeuk Kim <jaegeuk@google.com>
> 
> Must have WQ_MEM_RECLAIM
> ``WQ_MEM_RECLAIM``
>   All wq which might be used in the memory reclaim paths **MUST**
>   have this flag set.  The wq is guaranteed to have at least one
>   execution context regardless of memory pressure.
> 
> Signed-off-by: Jaegeuk Kim <jaegeuk@google.com>
> ---

Reviewed-by: Asutosh Das <asutoshd@codeaurora.org>

>  drivers/scsi/ufs/ufshcd.c | 2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)
> 
> diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
> index 011e80a21170..bc0d623aed66 100644
> --- a/drivers/scsi/ufs/ufshcd.c
> +++ b/drivers/scsi/ufs/ufshcd.c
> @@ -1867,7 +1867,7 @@ static void ufshcd_init_clk_gating(struct ufs_hba 
> *hba)
>  	snprintf(wq_name, ARRAY_SIZE(wq_name), "ufs_clk_gating_%d",
>  		 hba->host->host_no);
>  	hba->clk_gating.clk_gating_workq = alloc_ordered_workqueue(wq_name,
> -							   WQ_MEM_RECLAIM);
> +					WQ_MEM_RECLAIM | WQ_HIGHPRI);
> 
>  	hba->clk_gating.is_enabled = true;


_______________________________________________
Linux-f2fs-devel mailing list
Linux-f2fs-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel

Re: [f2fs-dev] [PATCH v3 5/5] scsi: ufs: fix clkgating on/off correctly

[asutoshd]

On 2020-10-24 08:06, Jaegeuk Kim wrote:
> The below call stack prevents clk_gating at every IO completion.
> We can remove the condition, ufshcd_any_tag_in_use(), since 
> clkgating_work
> will check it again.
> 
> ufshcd_complete_requests(struct ufs_hba *hba)
>   ufshcd_transfer_req_compl()
>     __ufshcd_transfer_req_compl()
>       __ufshcd_release(hba)
>         if (ufshcd_any_tag_in_use() == 1)
>            return;
>   ufshcd_tmc_handler(hba);
>     blk_mq_tagset_busy_iter();
> 
> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
> ---

Reviewed-by: Asutosh Das <asutoshd@codeaurora.org>

>  drivers/scsi/ufs/ufshcd.c | 2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)
> 
> diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
> index c94610cbecae..38043c6b8d5f 100644
> --- a/drivers/scsi/ufs/ufshcd.c
> +++ b/drivers/scsi/ufs/ufshcd.c
> @@ -1746,7 +1746,7 @@ static void __ufshcd_release(struct ufs_hba *hba)
> 
>  	if (hba->clk_gating.active_reqs || hba->clk_gating.is_suspended ||
>  	    hba->ufshcd_state != UFSHCD_STATE_OPERATIONAL ||
> -	    ufshcd_any_tag_in_use(hba) || hba->outstanding_tasks ||
> +	    hba->outstanding_tasks ||
>  	    hba->active_uic_cmd || hba->uic_async_done)
>  		return;


_______________________________________________
Linux-f2fs-devel mailing list
Linux-f2fs-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel

Re: [f2fs-dev] [PATCH v3 2/5] scsi: ufs: clear UAC for FFU and RPMB LUNs

[Jaegeuk Kim]

On 10/26, asutoshd@codeaurora.org wrote:
> On 2020-10-24 08:06, Jaegeuk Kim wrote:
> > From: Jaegeuk Kim <jaegeuk@google.com>
> > 
> > In order to conduct FFU or RPMB operations, UFS needs to clear UAC. This
> > patch
> > clears it explicitly, so that we could get no failure given early
> > execution.
> > 
> 
> What's the meaning of 'given early execution'?

I saw there's hba->wlun_dev_clr_ua to clear UA at ufshcd_set_dev_pwr_mode(),
and thus, assumed there's other path to clear UA. So, with this patch, user
can try FFU or RPMB requests regardless of that being done.

> 
> > Signed-off-by: Jaegeuk Kim <jaegeuk@google.com>
> > ---
> >  drivers/scsi/ufs/ufshcd.c | 70 +++++++++++++++++++++++++++++++++++----
> >  drivers/scsi/ufs/ufshcd.h |  1 +
> >  2 files changed, 65 insertions(+), 6 deletions(-)
> > 
> > diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
> > index e0b479f9eb8a..011e80a21170 100644
> > --- a/drivers/scsi/ufs/ufshcd.c
> > +++ b/drivers/scsi/ufs/ufshcd.c
> > @@ -7057,7 +7057,6 @@ static inline void
> > ufshcd_blk_pm_runtime_init(struct scsi_device *sdev)
> >  static int ufshcd_scsi_add_wlus(struct ufs_hba *hba)
> >  {
> >  	int ret = 0;
> > -	struct scsi_device *sdev_rpmb;
> >  	struct scsi_device *sdev_boot;
> > 
> >  	hba->sdev_ufs_device = __scsi_add_device(hba->host, 0, 0,
> > @@ -7070,14 +7069,14 @@ static int ufshcd_scsi_add_wlus(struct ufs_hba
> > *hba)
> >  	ufshcd_blk_pm_runtime_init(hba->sdev_ufs_device);
> >  	scsi_device_put(hba->sdev_ufs_device);
> > 
> > -	sdev_rpmb = __scsi_add_device(hba->host, 0, 0,
> > +	hba->sdev_rpmb = __scsi_add_device(hba->host, 0, 0,
> >  		ufshcd_upiu_wlun_to_scsi_wlun(UFS_UPIU_RPMB_WLUN), NULL);
> > -	if (IS_ERR(sdev_rpmb)) {
> > -		ret = PTR_ERR(sdev_rpmb);
> > +	if (IS_ERR(hba->sdev_rpmb)) {
> > +		ret = PTR_ERR(hba->sdev_rpmb);
> >  		goto remove_sdev_ufs_device;
> >  	}
> > -	ufshcd_blk_pm_runtime_init(sdev_rpmb);
> > -	scsi_device_put(sdev_rpmb);
> > +	ufshcd_blk_pm_runtime_init(hba->sdev_rpmb);
> > +	scsi_device_put(hba->sdev_rpmb);
> > 
> >  	sdev_boot = __scsi_add_device(hba->host, 0, 0,
> >  		ufshcd_upiu_wlun_to_scsi_wlun(UFS_UPIU_BOOT_WLUN), NULL);
> > @@ -7601,6 +7600,63 @@ static int ufshcd_add_lus(struct ufs_hba *hba)
> >  	return ret;
> >  }
> > 
> > +static int
> > +ufshcd_send_request_sense(struct ufs_hba *hba, struct scsi_device
> > *sdp);
> > +
> > +static int ufshcd_clear_ua_wlun(struct ufs_hba *hba, u8 wlun)
> > +{
> > +	struct scsi_device *sdp;
> > +	unsigned long flags;
> > +	int ret = 0;
> > +
> > +	spin_lock_irqsave(hba->host->host_lock, flags);
> > +	if (wlun  == UFS_UPIU_UFS_DEVICE_WLUN)
> > +		sdp = hba->sdev_ufs_device;
> > +	else if (wlun  == UFS_UPIU_RPMB_WLUN)
> > +		sdp = hba->sdev_rpmb;
> > +	else
> > +		BUG_ON(1);
> > +	if (sdp) {
> > +		ret = scsi_device_get(sdp);
> > +		if (!ret && !scsi_device_online(sdp)) {
> > +			ret = -ENODEV;
> > +			scsi_device_put(sdp);
> > +		}
> > +	} else {
> > +		ret = -ENODEV;
> > +	}
> > +	spin_unlock_irqrestore(hba->host->host_lock, flags);
> > +	if (ret)
> > +		goto out_err;
> > +
> > +	ret = ufshcd_send_request_sense(hba, sdp);
> > +	scsi_device_put(sdp);
> > +out_err:
> > +	if (ret)
> > +		dev_err(hba->dev, "%s: UAC clear LU=%x ret = %d\n",
> > +				__func__, wlun, ret);
> > +	return ret;
> > +}
> > +
> > +static int ufshcd_clear_ua_wluns(struct ufs_hba *hba)
> > +{
> > +	int ret = 0;
> > +
> > +	if (!hba->wlun_dev_clr_ua)
> > +		goto out;
> > +
> > +	ret = ufshcd_clear_ua_wlun(hba, UFS_UPIU_UFS_DEVICE_WLUN);
> > +	if (!ret)
> > +		ret = ufshcd_clear_ua_wlun(hba, UFS_UPIU_RPMB_WLUN);
> > +	if (!ret)
> > +		hba->wlun_dev_clr_ua = false;
> > +out:
> > +	if (ret)
> > +		dev_err(hba->dev, "%s: Failed to clear UAC WLUNS ret = %d\n",
> > +				__func__, ret);
> > +	return ret;
> > +}
> > +
> >  /**
> >   * ufshcd_probe_hba - probe hba to detect device and initialize
> >   * @hba: per-adapter instance
> > @@ -7720,6 +7776,8 @@ static void ufshcd_async_scan(void *data,
> > async_cookie_t cookie)
> >  		pm_runtime_put_sync(hba->dev);
> >  		ufshcd_exit_clk_scaling(hba);
> >  		ufshcd_hba_exit(hba);
> > +	} else {
> > +		ufshcd_clear_ua_wluns(hba);
> >  	}
> >  }
> > 
> > diff --git a/drivers/scsi/ufs/ufshcd.h b/drivers/scsi/ufs/ufshcd.h
> > index 47eb1430274c..718881d038f5 100644
> > --- a/drivers/scsi/ufs/ufshcd.h
> > +++ b/drivers/scsi/ufs/ufshcd.h
> > @@ -681,6 +681,7 @@ struct ufs_hba {
> >  	 * "UFS device" W-LU.
> >  	 */
> >  	struct scsi_device *sdev_ufs_device;
> > +	struct scsi_device *sdev_rpmb;
> > 
> >  	enum ufs_dev_pwr_mode curr_dev_pwr_mode;
> >  	enum uic_link_state uic_link_state;


_______________________________________________
Linux-f2fs-devel mailing list
Linux-f2fs-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel

Re: [f2fs-dev] [PATCH v3 1/5] scsi: ufs: atomic update for clkgating_enable

[Jaegeuk Kim]

On 10/26, Can Guo wrote:
> On 2020-10-26 14:13, Jaegeuk Kim wrote:
> > On 10/26, Can Guo wrote:
> > > On 2020-10-24 23:06, Jaegeuk Kim wrote:
> > > > From: Jaegeuk Kim <jaegeuk@google.com>
> > > >
> > > > When giving a stress test which enables/disables clkgating, we hit
> > > > device
> > > > timeout sometimes. This patch avoids subtle racy condition to address
> > > > it.
> > > >
> > > > If we use __ufshcd_release(), I've seen that gate_work can be called in
> > > > parallel
> > > > with ungate_work, which results in UFS timeout when doing hibern8.
> > > > Should avoid it.
> > > >
> > > 
> > > I don't understand this comment. gate_work and ungate_work are
> > > queued on
> > > an ordered workqueue and an ordered workqueue executes at most one
> > > work item
> > > at any given time in the queued order. How can the two run in
> > > parallel?
> > 
> > When I hit UFS stuck, I saw this by clkgating tracepoint.
> > 
> > - REQ_CLK_OFF
> > - CLKS_OFF
> > - REQ_CLK_OFF
> > - REQ_CLKS_ON
> > ..
> > 
> 
> I don't see how can you tell that the two works are running in parallel
> just from above trace. May I know what is the exact error by "UFS timeout
> when doing hibern8"?
> 
> By using __ufshcd_release() here, I do see one potential issue if your test
> quickly toggles on/off of clk_gating - disable it, enable it, disable it and
> enable it, which will cause that __ufshcd_release() being called twice,
> meaning
> we queue two gate_works back to back. So can you try below code and let me
> know
> if it helps or not? I am OK with your current change, but I would like to
> understand the problem. Thanks.
> 
> diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
> index 1791bce..3eee438 100644
> --- a/drivers/scsi/ufs/ufshcd.c
> +++ b/drivers/scsi/ufs/ufshcd.c
> @@ -2271,6 +2271,8 @@ static void ufshcd_gate_work(struct work_struct *work)
>         unsigned long flags;
> 
>         spin_lock_irqsave(hba->host->host_lock, flags);
> +       if (hba->clk_gating.state == CLKS_OFF)
> +               goto rel_lock;
>         /*
>          * In case you are here to cancel this work the gating state
>          * would be marked as REQ_CLKS_ON. In this case save time by

This doesn't help. So, I checked this back again, and, like what you said, now
suspect __ufshcd_release() which changed state to REQ_CLKS_OFF on CLKS_OFF.

With the below change, I can see the issue anymore. Let me send v4.

---
 drivers/scsi/ufs/ufshcd.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index b8f573a02713..cc8d5f0c3fdc 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -1745,7 +1745,8 @@ static void __ufshcd_release(struct ufs_hba *hba)
 	if (hba->clk_gating.active_reqs || hba->clk_gating.is_suspended ||
 	    hba->ufshcd_state != UFSHCD_STATE_OPERATIONAL ||
 	    ufshcd_any_tag_in_use(hba) || hba->outstanding_tasks ||
-	    hba->active_uic_cmd || hba->uic_async_done)
+	    hba->active_uic_cmd || hba->uic_async_done ||
+	    hba->clk_gating.state == CLKS_OFF)
 		return;
 
 	hba->clk_gating.state = REQ_CLKS_OFF;
-- 
2.29.0.rc1.297.gfa9743e501-goog


> 
> Regards,
> 
> Can Guo.
> 
> > By using active_req, I don't see any problem.
> > 
> > > 
> > > Thanks,
> > > 
> > > Can Guo.
> > > 
> > > > Signed-off-by: Jaegeuk Kim <jaegeuk@google.com>
> > > > ---
> > > >  drivers/scsi/ufs/ufshcd.c | 12 ++++++------
> > > >  1 file changed, 6 insertions(+), 6 deletions(-)
> > > >
> > > > diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
> > > > index b8f573a02713..e0b479f9eb8a 100644
> > > > --- a/drivers/scsi/ufs/ufshcd.c
> > > > +++ b/drivers/scsi/ufs/ufshcd.c
> > > > @@ -1807,19 +1807,19 @@ static ssize_t
> > > > ufshcd_clkgate_enable_store(struct device *dev,
> > > >  		return -EINVAL;
> > > >
> > > >  	value = !!value;
> > > > +
> > > > +	spin_lock_irqsave(hba->host->host_lock, flags);
> > > >  	if (value == hba->clk_gating.is_enabled)
> > > >  		goto out;
> > > >
> > > > -	if (value) {
> > > > -		ufshcd_release(hba);
> > > > -	} else {
> > > > -		spin_lock_irqsave(hba->host->host_lock, flags);
> > > > +	if (value)
> > > > +		hba->clk_gating.active_reqs--;
> > > > +	else
> > > >  		hba->clk_gating.active_reqs++;
> > > > -		spin_unlock_irqrestore(hba->host->host_lock, flags);
> > > > -	}
> > > >
> > > >  	hba->clk_gating.is_enabled = value;
> > > >  out:
> > > > +	spin_unlock_irqrestore(hba->host->host_lock, flags);
> > > >  	return count;
> > > >  }


_______________________________________________
Linux-f2fs-devel mailing list
Linux-f2fs-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel

Re: [f2fs-dev] [PATCH v3 1/5] scsi: ufs: atomic update for clkgating_enable

[Can Guo]

On 2020-10-27 03:48, Jaegeuk Kim wrote:
> On 10/26, Can Guo wrote:
>> On 2020-10-26 14:13, Jaegeuk Kim wrote:
>> > On 10/26, Can Guo wrote:
>> > > On 2020-10-24 23:06, Jaegeuk Kim wrote:
>> > > > From: Jaegeuk Kim <jaegeuk@google.com>
>> > > >
>> > > > When giving a stress test which enables/disables clkgating, we hit
>> > > > device
>> > > > timeout sometimes. This patch avoids subtle racy condition to address
>> > > > it.
>> > > >
>> > > > If we use __ufshcd_release(), I've seen that gate_work can be called in
>> > > > parallel
>> > > > with ungate_work, which results in UFS timeout when doing hibern8.
>> > > > Should avoid it.
>> > > >
>> > >
>> > > I don't understand this comment. gate_work and ungate_work are
>> > > queued on
>> > > an ordered workqueue and an ordered workqueue executes at most one
>> > > work item
>> > > at any given time in the queued order. How can the two run in
>> > > parallel?
>> >
>> > When I hit UFS stuck, I saw this by clkgating tracepoint.
>> >
>> > - REQ_CLK_OFF
>> > - CLKS_OFF
>> > - REQ_CLK_OFF
>> > - REQ_CLKS_ON
>> > ..
>> >
>> 
>> I don't see how can you tell that the two works are running in 
>> parallel
>> just from above trace. May I know what is the exact error by "UFS 
>> timeout
>> when doing hibern8"?
>> 
>> By using __ufshcd_release() here, I do see one potential issue if your 
>> test
>> quickly toggles on/off of clk_gating - disable it, enable it, disable 
>> it and
>> enable it, which will cause that __ufshcd_release() being called 
>> twice,
>> meaning
>> we queue two gate_works back to back. So can you try below code and 
>> let me
>> know
>> if it helps or not? I am OK with your current change, but I would like 
>> to
>> understand the problem. Thanks.
>> 
>> diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
>> index 1791bce..3eee438 100644
>> --- a/drivers/scsi/ufs/ufshcd.c
>> +++ b/drivers/scsi/ufs/ufshcd.c
>> @@ -2271,6 +2271,8 @@ static void ufshcd_gate_work(struct work_struct 
>> *work)
>>         unsigned long flags;
>> 
>>         spin_lock_irqsave(hba->host->host_lock, flags);
>> +       if (hba->clk_gating.state == CLKS_OFF)
>> +               goto rel_lock;
>>         /*
>>          * In case you are here to cancel this work the gating state
>>          * would be marked as REQ_CLKS_ON. In this case save time by
> 
> This doesn't help. So, I checked this back again, and, like what you 
> said, now
> suspect __ufshcd_release() which changed state to REQ_CLKS_OFF on 
> CLKS_OFF.
> 

Aha, sorry that I gave the right analysis but wrong fix - my check won't 
help
since it is checking CLKS_OFF, but at that moment it has become 
CLKS_REQ_OFF.
Your fix is fulfiling the right purpose.

Thanks,

Can Guo.


> With the below change, I can see the issue anymore. Let me send v4.
> 
> ---
>  drivers/scsi/ufs/ufshcd.c | 3 ++-
>  1 file changed, 2 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
> index b8f573a02713..cc8d5f0c3fdc 100644
> --- a/drivers/scsi/ufs/ufshcd.c
> +++ b/drivers/scsi/ufs/ufshcd.c
> @@ -1745,7 +1745,8 @@ static void __ufshcd_release(struct ufs_hba *hba)
>  	if (hba->clk_gating.active_reqs || hba->clk_gating.is_suspended ||
>  	    hba->ufshcd_state != UFSHCD_STATE_OPERATIONAL ||
>  	    ufshcd_any_tag_in_use(hba) || hba->outstanding_tasks ||
> -	    hba->active_uic_cmd || hba->uic_async_done)
> +	    hba->active_uic_cmd || hba->uic_async_done ||
> +	    hba->clk_gating.state == CLKS_OFF)
>  		return;
> 
>  	hba->clk_gating.state = REQ_CLKS_OFF;
> --
> 2.29.0.rc1.297.gfa9743e501-goog
> 
> 
>> 
>> Regards,
>> 
>> Can Guo.
>> 
>> > By using active_req, I don't see any problem.
>> >
>> > >
>> > > Thanks,
>> > >
>> > > Can Guo.
>> > >
>> > > > Signed-off-by: Jaegeuk Kim <jaegeuk@google.com>
>> > > > ---
>> > > >  drivers/scsi/ufs/ufshcd.c | 12 ++++++------
>> > > >  1 file changed, 6 insertions(+), 6 deletions(-)
>> > > >
>> > > > diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
>> > > > index b8f573a02713..e0b479f9eb8a 100644
>> > > > --- a/drivers/scsi/ufs/ufshcd.c
>> > > > +++ b/drivers/scsi/ufs/ufshcd.c
>> > > > @@ -1807,19 +1807,19 @@ static ssize_t
>> > > > ufshcd_clkgate_enable_store(struct device *dev,
>> > > >  		return -EINVAL;
>> > > >
>> > > >  	value = !!value;
>> > > > +
>> > > > +	spin_lock_irqsave(hba->host->host_lock, flags);
>> > > >  	if (value == hba->clk_gating.is_enabled)
>> > > >  		goto out;
>> > > >
>> > > > -	if (value) {
>> > > > -		ufshcd_release(hba);
>> > > > -	} else {
>> > > > -		spin_lock_irqsave(hba->host->host_lock, flags);
>> > > > +	if (value)
>> > > > +		hba->clk_gating.active_reqs--;
>> > > > +	else
>> > > >  		hba->clk_gating.active_reqs++;
>> > > > -		spin_unlock_irqrestore(hba->host->host_lock, flags);
>> > > > -	}
>> > > >
>> > > >  	hba->clk_gating.is_enabled = value;
>> > > >  out:
>> > > > +	spin_unlock_irqrestore(hba->host->host_lock, flags);
>> > > >  	return count;
>> > > >  }


_______________________________________________
Linux-f2fs-devel mailing list
Linux-f2fs-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel