| Message ID | 20231221-ufs-reset-ensure-effect-before-delay-v3-7-2195a1b66d2e@redhat.com (mailing list archive) |
|---|---|
| State | Changes Requested |
| Headers | show |
| Series | scsi: ufs: Remove overzealous memory barriers | expand |
On 12/21/23 11:09, Andrew Halaney wrote: > Currently, the UTP_TASK_REQ_LIST_BASE_L/UTP_TASK_REQ_LIST_BASE_H regs > are written to and then completed with an mb(). > > mb() ensure that the write completes, but completion doesn't mean that > it isn't stored in a buffer somewhere. The recommendation for > ensuring these bits have taken effect on the device is to perform a read > back to force it to make it all the way to the device. This is > documented in device-io.rst and a talk by Will Deacon on this can > be seen over here: > > https://youtu.be/i6DayghhA8Q?si=MiyxB5cKJXSaoc01&t=1678 > > Let's do that to ensure the bits hit the device. Because the mb()'s > purpose wasn't to add extra ordering (on top of the ordering guaranteed > by writel()/readl()), it can safely be removed. > > Fixes: 88441a8d355d ("scsi: ufs: core: Add hibernation callbacks") > Signed-off-by: Andrew Halaney <ahalaney@redhat.com> > --- > drivers/ufs/core/ufshcd.c | 2 +- > 1 file changed, 1 insertion(+), 1 deletion(-) > > diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c > index d1e33328ff3f..7bfb556e5b8e 100644 > --- a/drivers/ufs/core/ufshcd.c > +++ b/drivers/ufs/core/ufshcd.c > @@ -10351,7 +10351,7 @@ int ufshcd_system_restore(struct device *dev) > * are updated with the latest queue addresses. Only after > * updating these addresses, we can queue the new commands. > */ > - mb(); > + ufshcd_readl(hba, REG_UTP_TASK_REQ_LIST_BASE_H); > > /* Resuming from hibernate, assume that link was OFF */ > ufshcd_set_link_off(hba); Reviewed-by: Bart Van Assche <bvanassche@acm.org>
On 12/22/2023 3:09 AM, Andrew Halaney wrote: > Currently, the UTP_TASK_REQ_LIST_BASE_L/UTP_TASK_REQ_LIST_BASE_H regs > are written to and then completed with an mb(). > > mb() ensure that the write completes, but completion doesn't mean that > it isn't stored in a buffer somewhere. The recommendation for > ensuring these bits have taken effect on the device is to perform a read > back to force it to make it all the way to the device. This is > documented in device-io.rst and a talk by Will Deacon on this can > be seen over here: > > https://youtu.be/i6DayghhA8Q?si=MiyxB5cKJXSaoc01&t=1678 > > Let's do that to ensure the bits hit the device. Because the mb()'s > purpose wasn't to add extra ordering (on top of the ordering guaranteed > by writel()/readl()), it can safely be removed. > > Fixes: 88441a8d355d ("scsi: ufs: core: Add hibernation callbacks") > Signed-off-by: Andrew Halaney <ahalaney@redhat.com> > --- > drivers/ufs/core/ufshcd.c | 2 +- > 1 file changed, 1 insertion(+), 1 deletion(-) > > diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c > index d1e33328ff3f..7bfb556e5b8e 100644 > --- a/drivers/ufs/core/ufshcd.c > +++ b/drivers/ufs/core/ufshcd.c > @@ -10351,7 +10351,7 @@ int ufshcd_system_restore(struct device *dev) > * are updated with the latest queue addresses. Only after > * updating these addresses, we can queue the new commands. > */ > - mb(); > + ufshcd_readl(hba, REG_UTP_TASK_REQ_LIST_BASE_H); > > /* Resuming from hibernate, assume that link was OFF */ > ufshcd_set_link_off(hba); > Reviewed-by: Can Guo <quic_cang@quicinc.com>
diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index d1e33328ff3f..7bfb556e5b8e 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -10351,7 +10351,7 @@ int ufshcd_system_restore(struct device *dev) * are updated with the latest queue addresses. Only after * updating these addresses, we can queue the new commands. */ - mb(); + ufshcd_readl(hba, REG_UTP_TASK_REQ_LIST_BASE_H); /* Resuming from hibernate, assume that link was OFF */ ufshcd_set_link_off(hba);
Currently, the UTP_TASK_REQ_LIST_BASE_L/UTP_TASK_REQ_LIST_BASE_H regs are written to and then completed with an mb(). mb() ensure that the write completes, but completion doesn't mean that it isn't stored in a buffer somewhere. The recommendation for ensuring these bits have taken effect on the device is to perform a read back to force it to make it all the way to the device. This is documented in device-io.rst and a talk by Will Deacon on this can be seen over here: https://youtu.be/i6DayghhA8Q?si=MiyxB5cKJXSaoc01&t=1678 Let's do that to ensure the bits hit the device. Because the mb()'s purpose wasn't to add extra ordering (on top of the ordering guaranteed by writel()/readl()), it can safely be removed. Fixes: 88441a8d355d ("scsi: ufs: core: Add hibernation callbacks") Signed-off-by: Andrew Halaney <ahalaney@redhat.com> --- drivers/ufs/core/ufshcd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)