| Message ID | 20200915204532.1672300-1-jaegeuk@kernel.org |
|---|---|
| State | New |
| Headers | show |
| Series | [1/6] scsi: ufs: atomic update for clkgating_enable | expand |
Please ignore this patch. Thanks. On 09/15, Jaegeuk Kim wrote: > From: Jaegeuk Kim <jaegeuk@google.com> > > When testing infinite test to read sysfs entries of UFS, I got a UFS timeout > with the following kernel message. > > query: dev_cmd_send: seq_no=78082 tag=31, idn=2 > query: ufshcd_wait_for_dev_cmd: dev_cmd request timedout, tag 31 > query: __ufshcd_query_descriptor: opcode 0x01 for idn 2 failed, index 0, err = -11 > -- hibern8: dme: dme_send: cmd_id=0x17 idn=0 > query: ufshcd_query_descriptor: failed with error -11, retries 3 > -- hibern8: ufshcd_update_uic_error: LINERESET during hibern8 enter > -- hibern8: __ufshcd_uic_hibern8_enter: hibern8 enter failed. ret = -110 > > The problem is casued by hibern8 command issued by ufshcd_suspend(), which is > not aware of query command. If autohibern8 is enabled, we actually don't need > to issue hibern8 command by suspend. > > Cc: Alim Akhtar <alim.akhtar@samsung.com> > Cc: Avri Altman <avri.altman@wdc.com> > Signed-off-by: Jaegeuk Kim <jaegeuk@google.com> > --- > drivers/scsi/ufs/ufshcd.c | 20 ++++++++++++++++++-- > drivers/scsi/ufs/ufshcd.h | 1 + > 2 files changed, 19 insertions(+), 2 deletions(-) > > diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c > index 848e33ec40639..bdc82cc3824aa 100644 > --- a/drivers/scsi/ufs/ufshcd.c > +++ b/drivers/scsi/ufs/ufshcd.c > @@ -3079,8 +3079,12 @@ int ufshcd_query_descriptor_retry(struct ufs_hba *hba, > int retries; > > for (retries = QUERY_REQ_RETRIES; retries > 0; retries--) { > - err = __ufshcd_query_descriptor(hba, opcode, idn, index, > + err = -EAGAIN; > + down_read(&hba->query_lock); > + if (!ufshcd_is_link_hibern8(hba)) > + err = __ufshcd_query_descriptor(hba, opcode, idn, index, > selector, desc_buf, buf_len); > + up_read(&hba->query_lock); > if (!err || err == -EINVAL) > break; > } > @@ -8263,8 +8267,8 @@ static int ufshcd_suspend(struct ufs_hba *hba, enum ufs_pm_op pm_op) > enum ufs_pm_level pm_lvl; > enum ufs_dev_pwr_mode req_dev_pwr_mode; > enum uic_link_state req_link_state; > + bool need_upwrite = false; > > - hba->pm_op_in_progress = 1; > if (!ufshcd_is_shutdown_pm(pm_op)) { > pm_lvl = ufshcd_is_runtime_pm(pm_op) ? > hba->rpm_lvl : hba->spm_lvl; > @@ -8275,6 +8279,15 @@ static int ufshcd_suspend(struct ufs_hba *hba, enum ufs_pm_op pm_op) > req_link_state = UIC_LINK_OFF_STATE; > } > > + if (ufshcd_is_runtime_pm(pm_op) && > + req_link_state == UIC_LINK_HIBERN8_STATE && > + hba->capabilities & MASK_AUTO_HIBERN8_SUPPORT) { > + need_upwrite = true; > + if (!down_write_trylock(&hba->query_lock)) > + return -EBUSY; > + } > + hba->pm_op_in_progress = 1; > + > /* > * If we can't transition into any of the low power modes > * just gate the clocks. > @@ -8403,6 +8416,8 @@ static int ufshcd_suspend(struct ufs_hba *hba, enum ufs_pm_op pm_op) > } > > hba->pm_op_in_progress = 0; > + if (need_upwrite) > + up_write(&hba->query_lock); > > if (ret) > ufshcd_update_reg_hist(&hba->ufs_stats.suspend_err, (u32)ret); > @@ -8894,6 +8909,7 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq) > mutex_init(&hba->dev_cmd.lock); > > init_rwsem(&hba->clk_scaling_lock); > + init_rwsem(&hba->query_lock); > > ufshcd_init_clk_gating(hba); > > diff --git a/drivers/scsi/ufs/ufshcd.h b/drivers/scsi/ufs/ufshcd.h > index 363589c0bd370..6f8e05eaf9661 100644 > --- a/drivers/scsi/ufs/ufshcd.h > +++ b/drivers/scsi/ufs/ufshcd.h > @@ -754,6 +754,7 @@ struct ufs_hba { > bool is_urgent_bkops_lvl_checked; > > struct rw_semaphore clk_scaling_lock; > + struct rw_semaphore query_lock; > unsigned char desc_size[QUERY_DESC_IDN_MAX]; > atomic_t scsi_block_reqs_cnt; > > -- > 2.28.0.618.gf4bc123cb7-goog
On 2020-09-18 12:13, Jaegeuk Kim wrote: > On 09/17, Can Guo wrote: >> On 2020-09-17 00:05, Jaegeuk Kim wrote: >> > On 09/16, Bean Huo wrote: >> > > On Tue, 2020-09-15 at 13:45 -0700, Jaegeuk Kim wrote: >> > > > Cc: Avri Altman <avri.altman@wdc.com> >> > > > Signed-off-by: Jaegeuk Kim <jaegeuk@google.com> >> > > > --- >> > > > drivers/scsi/ufs/ufshcd.c | 8 ++++++++ >> > > > 1 file changed, 8 insertions(+) >> > > > >> > > > diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c >> > > > index bdc82cc3824aa..b81c116b976ff 100644 >> > > > --- a/drivers/scsi/ufs/ufshcd.c >> > > > +++ b/drivers/scsi/ufs/ufshcd.c >> > > > @@ -500,6 +500,14 @@ static void ufshcd_print_tmrs(struct ufs_hba >> > > > *hba, unsigned long bitmap) >> > > > static void ufshcd_print_host_state(struct ufs_hba *hba) >> > > > { >> > > > dev_err(hba->dev, "UFS Host state=%d\n", hba->ufshcd_state); >> > > > + if (hba->sdev_ufs_device) { >> > > > + dev_err(hba->dev, " vendor = %.8s\n", >> > > > + hba->sdev_ufs_device- >> > > > >vendor); >> > > > + dev_err(hba->dev, " model = %.16s\n", >> > > > + hba->sdev_ufs_device->model); >> > > > + dev_err(hba->dev, " rev = %.4s\n", >> > > > + hba->sdev_ufs_device->rev); >> > > > + } >> > > >> > > Hi Jaegeuk >> > > these prints have been added since this change: >> > > >> > > commit 3f8af6044713 ("scsi: ufs: Add some debug information to >> > > ufshcd_print_host_state()") >> > > >> > > https://patchwork.kernel.org/patch/11694371/ >> > >> > Cool, thank you for pointing this out. BTW, which branch can I see the >> > -next >> > patches? >> > >> >> Hi Jaegeuk, >> >> This patch comes from a series of changes trying to fix and simplify >> the UFS error handling. You can find the whole series here - they are >> picked up on scsi-queue-5.10 >> >> https://lore.kernel.org/linux-scsi/1596975355-39813-10-git-send-email-cang@codeaurora.org/ >> >> Besides, several more fixes for error handling based on above series >> are >> >> https://lore.kernel.org/patchwork/patch/1290405/ >> & >> https://lore.kernel.org/linux-scsi/159961731708.5787.8825955850640714260.b4-ty@oracle.com/ >> >> I've mainline all above changes to Android12-5.4 and Android11-5.4. > > I've seen the patches in Android branches. Thank you for the > explanation. > >> >> Moreover, there are 2 more fixes on the way for error handling, I >> will push them soon. > > BTW, could you please take a look at these patches? > > Thanks, > Sure, but since I am not in your cc or to list, so I don't know which patches. Maybe you can add me when you push the next version? Thanks. Regards, Can Guo. >> >> Thanks, >> >> Can Guo. >> >> > > >> > > Thanks, >> > > Bean
diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c index 1d157ff58d817..d929c3d1e58cc 100644 --- a/drivers/scsi/ufs/ufshcd.c +++ b/drivers/scsi/ufs/ufshcd.c @@ -1791,19 +1791,19 @@ 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; }