[PATCH 00/13] scsi: hisi_sas: Some fixes for hisi_sas

[PATCH 00/13] scsi: hisi_sas: Some fixes for hisi_sas

[Yihang Li]

This series contains some fixes including:
- Adjust priority of registering and exiting debugfs for security;
- Create trigger_dump at the end of the debugfs initialization;
- Add firmware information check;
- Enable all PHYs that are not disabled by user during controller reset;
- Reset PHY again if phyup timeout;
- Check usage count only when the runtime PM status is RPM_SUSPENDING;
- Add cond_resched() for no forced preemption model;
- Default enable interrupt coalescing;
- Update disk locked timeout to 7 seconds;
- Add time interval between two H2D FIS following soft reset spec;
- Update v3 hw STP_LINK_TIMER setting;
- Create all dump files during debugfs initialization;
- Add latest_dump for the debugfs dump;

Xingui Yang (3):
  scsi: hisi_sas: Update disk locked timeout to 7 seconds
  scsi: hisi_sas: Add time interval between two H2D FIS following soft
    reset spec
  scsi: hisi_sas: Update v3 hw STP_LINK_TIMER setting

Yihang Li (10):
  scsi: hisi_sas: Adjust priority of registering and exiting debugfs for
    security
  scsi: hisi_sas: Create trigger_dump at the end of the debugfs
    initialization
  scsi: hisi_sas: Add firmware information check
  scsi: hisi_sas: Enable all PHYs that are not disabled by user during
    controller reset
  scsi: hisi_sas: Reset PHY again if phyup timeout
  scsi: hisi_sas: Check usage count only when the runtime PM status is
    RPM_SUSPENDING
  scsi: hisi_sas: Add cond_resched() for no forced preemption model
  scsi: hisi_sas: Default enable interrupt coalescing
  scsi: hisi_sas: Create all dump files during debugfs initialization
  scsi: hisi_sas: Add latest_dump for the debugfs dump

 drivers/scsi/hisi_sas/hisi_sas.h       |   1 +
 drivers/scsi/hisi_sas/hisi_sas_main.c  |  33 ++++-
 drivers/scsi/hisi_sas/hisi_sas_v1_hw.c |  18 +++
 drivers/scsi/hisi_sas/hisi_sas_v2_hw.c |  18 +++
 drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 187 ++++++++++++++++++-------
 5 files changed, 206 insertions(+), 51 deletions(-)

-- 
2.33.0

[PATCH 01/13] scsi: hisi_sas: Adjust priority of registering and exiting debugfs for security

[Yihang Li]

To be safe, we should register debugfs at the last stage of driver
initialization and then unregister debugfs at the first stage of driver
uninstallation.

Signed-off-by: Yihang Li <liyihang9@huawei.com>
Reviewed-by: Xiang Chen <chenxiang66@hisilicon.com>
---
 drivers/scsi/hisi_sas/hisi_sas_main.c  |  4 ++--
 drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 17 ++++++-----------
 2 files changed, 8 insertions(+), 13 deletions(-)

diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index 6219807ce3b9..d3dcc4918444 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -2630,10 +2630,10 @@ static __init int hisi_sas_init(void)
 
 static __exit void hisi_sas_exit(void)
 {
-	sas_release_transport(hisi_sas_stt);
-
 	if (hisi_sas_debugfs_enable)
 		debugfs_remove(hisi_sas_debugfs_dir);
+
+	sas_release_transport(hisi_sas_stt);
 }
 
 module_init(hisi_sas_init);
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
index 4cd3a3eab6f1..63a7255d2994 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
@@ -4860,16 +4860,13 @@ hisi_sas_v3_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 					    SHOST_DIX_GUARD_CRC);
 	}
 
-	if (hisi_sas_debugfs_enable)
-		debugfs_init_v3_hw(hisi_hba);
-
 	rc = interrupt_preinit_v3_hw(hisi_hba);
 	if (rc)
-		goto err_out_undo_debugfs;
+		goto err_out_free_host;
 
 	rc = scsi_add_host(shost, dev);
 	if (rc)
-		goto err_out_undo_debugfs;
+		goto err_out_free_host;
 
 	rc = sas_register_ha(sha);
 	if (rc)
@@ -4880,6 +4877,8 @@ hisi_sas_v3_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto err_out_unregister_ha;
 
 	scsi_scan_host(shost);
+	if (hisi_sas_debugfs_enable)
+		debugfs_init_v3_hw(hisi_hba);
 
 	pm_runtime_set_autosuspend_delay(dev, 5000);
 	pm_runtime_use_autosuspend(dev);
@@ -4900,9 +4899,6 @@ hisi_sas_v3_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	sas_unregister_ha(sha);
 err_out_remove_host:
 	scsi_remove_host(shost);
-err_out_undo_debugfs:
-	if (hisi_sas_debugfs_enable)
-		debugfs_exit_v3_hw(hisi_hba);
 err_out_free_host:
 	hisi_sas_free(hisi_hba);
 	scsi_host_put(shost);
@@ -4934,6 +4930,8 @@ static void hisi_sas_v3_remove(struct pci_dev *pdev)
 	struct Scsi_Host *shost = sha->shost;
 
 	pm_runtime_get_noresume(dev);
+	if (hisi_sas_debugfs_enable)
+		debugfs_exit_v3_hw(hisi_hba);
 
 	sas_unregister_ha(sha);
 	flush_workqueue(hisi_hba->wq);
@@ -4941,9 +4939,6 @@ static void hisi_sas_v3_remove(struct pci_dev *pdev)
 
 	hisi_sas_v3_destroy_irqs(pdev, hisi_hba);
 	hisi_sas_free(hisi_hba);
-	if (hisi_sas_debugfs_enable)
-		debugfs_exit_v3_hw(hisi_hba);
-
 	scsi_host_put(shost);
 }
 
-- 
2.33.0

[PATCH 02/13] scsi: hisi_sas: Create trigger_dump at the end of the debugfs initialization

[Yihang Li]

In the current debugfs initialization process, the interface trigger_dump
is created first, and then the dump directory is created to store the
register dump information.

The issue is that after the trigger_dump interface is created, users can
access the interface to trigger dump and call debugfs_create_files_v3_hw().
In debugfs_create_files_v3_hw(), if .debugfs_dump_dentry is NULL, the file
for storing dump information is created under /sys/kernel/debug, and the
memory and information cannot be released after the driver is uninstalled.

Therefore, the creation of the trigger_dump interface is placed at the end
of debugfs initialization.

Signed-off-by: Yihang Li <liyihang9@huawei.com>
Reviewed-by: Xiang Chen <chenxiang66@hisilicon.com>
---
 drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
index 63a7255d2994..980f28d7b87f 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
@@ -4755,11 +4755,6 @@ static void debugfs_init_v3_hw(struct hisi_hba *hisi_hba)
 
 	hisi_hba->debugfs_dir = debugfs_create_dir(dev_name(dev),
 						   hisi_sas_debugfs_dir);
-	debugfs_create_file("trigger_dump", 0200,
-			    hisi_hba->debugfs_dir,
-			    hisi_hba,
-			    &debugfs_trigger_dump_v3_hw_fops);
-
 	/* create bist structures */
 	debugfs_bist_init_v3_hw(hisi_hba);
 
@@ -4768,6 +4763,10 @@ static void debugfs_init_v3_hw(struct hisi_hba *hisi_hba)
 
 	debugfs_phy_down_cnt_init_v3_hw(hisi_hba);
 	debugfs_fifo_init_v3_hw(hisi_hba);
+	debugfs_create_file("trigger_dump", 0200,
+			    hisi_hba->debugfs_dir,
+			    hisi_hba,
+			    &debugfs_trigger_dump_v3_hw_fops);
 }
 
 static int
-- 
2.33.0

[PATCH 03/13] scsi: hisi_sas: Add firmware information check

[Yihang Li]

For security purposes, after information is obtained through the FW,
check information to ensure data correctness.

In v1 and v2 hw, the maximum number of PHYs is 9, while in v3 it is 8.
In v2 and v3 hw, the maximum number of hardware queues is 16, while in v1
it is 32.

Also add some debug logs for failure.

Signed-off-by: Yihang Li <liyihang9@huawei.com>
Reviewed-by: Xiang Chen <chenxiang66@hisilicon.com>
---
 drivers/scsi/hisi_sas/hisi_sas.h       |  1 +
 drivers/scsi/hisi_sas/hisi_sas_main.c  |  7 +++++++
 drivers/scsi/hisi_sas/hisi_sas_v1_hw.c | 18 ++++++++++++++++++
 drivers/scsi/hisi_sas/hisi_sas_v2_hw.c | 18 ++++++++++++++++++
 drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 20 ++++++++++++++++++++
 5 files changed, 64 insertions(+)

diff --git a/drivers/scsi/hisi_sas/hisi_sas.h b/drivers/scsi/hisi_sas/hisi_sas.h
index d223f482488f..a44768bceb9a 100644
--- a/drivers/scsi/hisi_sas/hisi_sas.h
+++ b/drivers/scsi/hisi_sas/hisi_sas.h
@@ -307,6 +307,7 @@ enum {
 
 struct hisi_sas_hw {
 	int (*hw_init)(struct hisi_hba *hisi_hba);
+	int (*fw_info_check)(struct hisi_hba *hisi_hba);
 	int (*interrupt_preinit)(struct hisi_hba *hisi_hba);
 	void (*setup_itct)(struct hisi_hba *hisi_hba,
 			   struct hisi_sas_device *device);
diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index d3dcc4918444..e15926c40983 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -2450,6 +2450,13 @@ static struct Scsi_Host *hisi_sas_shost_alloc(struct platform_device *pdev,
 	if (hisi_sas_get_fw_info(hisi_hba) < 0)
 		goto err_out;
 
+	if (hisi_hba->hw->fw_info_check) {
+		error = hisi_hba->hw->fw_info_check(hisi_hba);
+
+		if (error)
+			return error;
+	}
+
 	error = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64));
 	if (error) {
 		dev_err(dev, "No usable DMA addressing method\n");
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c
index 71b5008c3552..70bba55bc5d0 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c
@@ -1734,6 +1734,23 @@ static struct attribute *host_v1_hw_attrs[] = {
 
 ATTRIBUTE_GROUPS(host_v1_hw);
 
+static int check_fw_info_v1_hw(struct hisi_hba *hisi_hba)
+{
+	struct device *dev = hisi_hba->dev;
+
+	if (hisi_hba->n_phy < 0 || hisi_hba->n_phy > 9) {
+		dev_err(dev, "invalid phy number from FW\n");
+		return -EINVAL;
+	}
+
+	if (hisi_hba->queue_count < 0 || hisi_hba->queue_count > 32) {
+		dev_err(dev, "invalid queue count from FW\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static const struct scsi_host_template sht_v1_hw = {
 	LIBSAS_SHT_BASE_NO_SLAVE_INIT
 	.device_configure	= hisi_sas_device_configure,
@@ -1747,6 +1764,7 @@ static const struct scsi_host_template sht_v1_hw = {
 
 static const struct hisi_sas_hw hisi_sas_v1_hw = {
 	.hw_init = hisi_sas_v1_init,
+	.fw_info_check = check_fw_info_v1_hw,
 	.setup_itct = setup_itct_v1_hw,
 	.sl_notify_ssp = sl_notify_ssp_v1_hw,
 	.clear_itct = clear_itct_v1_hw,
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
index 342d75f12051..ab6668dc5b77 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
@@ -3566,6 +3566,23 @@ static void map_queues_v2_hw(struct Scsi_Host *shost)
 	}
 }
 
+static int check_fw_info_v2_hw(struct hisi_hba *hisi_hba)
+{
+	struct device *dev = hisi_hba->dev;
+
+	if (hisi_hba->n_phy < 0 || hisi_hba->n_phy > 9) {
+		dev_err(dev, "invalid phy number from FW\n");
+		return -EINVAL;
+	}
+
+	if (hisi_hba->queue_count < 0 || hisi_hba->queue_count > 16) {
+		dev_err(dev, "invalid queue count from FW\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static const struct scsi_host_template sht_v2_hw = {
 	LIBSAS_SHT_BASE_NO_SLAVE_INIT
 	.device_configure	= hisi_sas_device_configure,
@@ -3582,6 +3599,7 @@ static const struct scsi_host_template sht_v2_hw = {
 
 static const struct hisi_sas_hw hisi_sas_v2_hw = {
 	.hw_init = hisi_sas_v2_init,
+	.fw_info_check = check_fw_info_v2_hw,
 	.interrupt_preinit = hisi_sas_v2_interrupt_preinit,
 	.setup_itct = setup_itct_v2_hw,
 	.slot_index_alloc = slot_index_alloc_quirk_v2_hw,
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
index 980f28d7b87f..d48777fc4bd9 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
@@ -3371,6 +3371,23 @@ static const struct hisi_sas_hw hisi_sas_v3_hw = {
 	.debugfs_snapshot_regs = debugfs_snapshot_regs_v3_hw,
 };
 
+static int check_fw_info_v3_hw(struct hisi_hba *hisi_hba)
+{
+	struct device *dev = hisi_hba->dev;
+
+	if (hisi_hba->n_phy < 0 || hisi_hba->n_phy > 8) {
+		dev_err(dev, "invalid phy number from FW\n");
+		return -EINVAL;
+	}
+
+	if (hisi_hba->queue_count < 0 || hisi_hba->queue_count > 16) {
+		dev_err(dev, "invalid queue count from FW\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static struct Scsi_Host *
 hisi_sas_shost_alloc_pci(struct pci_dev *pdev)
 {
@@ -3401,6 +3418,9 @@ hisi_sas_shost_alloc_pci(struct pci_dev *pdev)
 	if (hisi_sas_get_fw_info(hisi_hba) < 0)
 		goto err_out;
 
+	if (check_fw_info_v3_hw(hisi_hba) < 0)
+		goto err_out;
+
 	if (experimental_iopoll_q_cnt < 0 ||
 		experimental_iopoll_q_cnt >= hisi_hba->queue_count)
 		dev_err(dev, "iopoll queue count %d cannot exceed or equal 16, using default 0\n",
-- 
2.33.0

Re: [PATCH 03/13] scsi: hisi_sas: Add firmware information check

[kernel test robot]

Hi Yihang,

kernel test robot noticed the following build errors:

[auto build test ERROR on jejb-scsi/for-next]
[also build test ERROR on mkp-scsi/for-next linus/master v6.11 next-20240926]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]

url:    https://github.com/intel-lab-lkp/linux/commits/Yihang-Li/scsi-hisi_sas-Adjust-priority-of-registering-and-exiting-debugfs-for-security/20240926-094506
base:   https://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi.git for-next
patch link:    https://lore.kernel.org/r/20240926014332.3905399-4-liyihang9%40huawei.com
patch subject: [PATCH 03/13] scsi: hisi_sas: Add firmware information check
config: m68k-allmodconfig (https://download.01.org/0day-ci/archive/20240926/202409262042.MIMB8blU-lkp@intel.com/config)
compiler: m68k-linux-gcc (GCC) 14.1.0
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20240926/202409262042.MIMB8blU-lkp@intel.com/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202409262042.MIMB8blU-lkp@intel.com/

All errors (new ones prefixed by >>):

   drivers/scsi/hisi_sas/hisi_sas_main.c: In function 'hisi_sas_shost_alloc':
>> drivers/scsi/hisi_sas/hisi_sas_main.c:2457:32: error: returning 'int' from a function with return type 'struct Scsi_Host *' makes pointer from integer without a cast [-Wint-conversion]
    2457 |                         return error;
         |                                ^~~~~


vim +2457 drivers/scsi/hisi_sas/hisi_sas_main.c

  2424	
  2425	static struct Scsi_Host *hisi_sas_shost_alloc(struct platform_device *pdev,
  2426						      const struct hisi_sas_hw *hw)
  2427	{
  2428		struct resource *res;
  2429		struct Scsi_Host *shost;
  2430		struct hisi_hba *hisi_hba;
  2431		struct device *dev = &pdev->dev;
  2432		int error;
  2433	
  2434		shost = scsi_host_alloc(hw->sht, sizeof(*hisi_hba));
  2435		if (!shost) {
  2436			dev_err(dev, "scsi host alloc failed\n");
  2437			return NULL;
  2438		}
  2439		hisi_hba = shost_priv(shost);
  2440	
  2441		INIT_WORK(&hisi_hba->rst_work, hisi_sas_rst_work_handler);
  2442		hisi_hba->hw = hw;
  2443		hisi_hba->dev = dev;
  2444		hisi_hba->platform_dev = pdev;
  2445		hisi_hba->shost = shost;
  2446		SHOST_TO_SAS_HA(shost) = &hisi_hba->sha;
  2447	
  2448		timer_setup(&hisi_hba->timer, NULL, 0);
  2449	
  2450		if (hisi_sas_get_fw_info(hisi_hba) < 0)
  2451			goto err_out;
  2452	
  2453		if (hisi_hba->hw->fw_info_check) {
  2454			error = hisi_hba->hw->fw_info_check(hisi_hba);
  2455	
  2456			if (error)
> 2457				return error;
  2458		}
  2459	
  2460		error = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64));
  2461		if (error) {
  2462			dev_err(dev, "No usable DMA addressing method\n");
  2463			goto err_out;
  2464		}
  2465	
  2466		hisi_hba->regs = devm_platform_ioremap_resource(pdev, 0);
  2467		if (IS_ERR(hisi_hba->regs))
  2468			goto err_out;
  2469	
  2470		res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
  2471		if (res) {
  2472			hisi_hba->sgpio_regs = devm_ioremap_resource(dev, res);
  2473			if (IS_ERR(hisi_hba->sgpio_regs))
  2474				goto err_out;
  2475		}
  2476	
  2477		if (hisi_sas_alloc(hisi_hba)) {
  2478			hisi_sas_free(hisi_hba);
  2479			goto err_out;
  2480		}
  2481	
  2482		return shost;
  2483	err_out:
  2484		scsi_host_put(shost);
  2485		dev_err(dev, "shost alloc failed\n");
  2486		return NULL;
  2487	}
  2488	

-- 
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki

Re: [PATCH 03/13] scsi: hisi_sas: Add firmware information check

[kernel test robot]

Hi Yihang,

kernel test robot noticed the following build warnings:

[auto build test WARNING on jejb-scsi/for-next]
[also build test WARNING on mkp-scsi/for-next linus/master v6.11 next-20240926]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]

url:    https://github.com/intel-lab-lkp/linux/commits/Yihang-Li/scsi-hisi_sas-Adjust-priority-of-registering-and-exiting-debugfs-for-security/20240926-094506
base:   https://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi.git for-next
patch link:    https://lore.kernel.org/r/20240926014332.3905399-4-liyihang9%40huawei.com
patch subject: [PATCH 03/13] scsi: hisi_sas: Add firmware information check
config: i386-buildonly-randconfig-001-20240926 (https://download.01.org/0day-ci/archive/20240926/202409262056.WfCiaJnA-lkp@intel.com/config)
compiler: gcc-12 (Debian 12.2.0-14) 12.2.0
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20240926/202409262056.WfCiaJnA-lkp@intel.com/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202409262056.WfCiaJnA-lkp@intel.com/

All warnings (new ones prefixed by >>):

   drivers/scsi/hisi_sas/hisi_sas_main.c: In function 'hisi_sas_shost_alloc':
>> drivers/scsi/hisi_sas/hisi_sas_main.c:2457:32: warning: returning 'int' from a function with return type 'struct Scsi_Host *' makes pointer from integer without a cast [-Wint-conversion]
    2457 |                         return error;
         |                                ^~~~~


vim +2457 drivers/scsi/hisi_sas/hisi_sas_main.c

  2424	
  2425	static struct Scsi_Host *hisi_sas_shost_alloc(struct platform_device *pdev,
  2426						      const struct hisi_sas_hw *hw)
  2427	{
  2428		struct resource *res;
  2429		struct Scsi_Host *shost;
  2430		struct hisi_hba *hisi_hba;
  2431		struct device *dev = &pdev->dev;
  2432		int error;
  2433	
  2434		shost = scsi_host_alloc(hw->sht, sizeof(*hisi_hba));
  2435		if (!shost) {
  2436			dev_err(dev, "scsi host alloc failed\n");
  2437			return NULL;
  2438		}
  2439		hisi_hba = shost_priv(shost);
  2440	
  2441		INIT_WORK(&hisi_hba->rst_work, hisi_sas_rst_work_handler);
  2442		hisi_hba->hw = hw;
  2443		hisi_hba->dev = dev;
  2444		hisi_hba->platform_dev = pdev;
  2445		hisi_hba->shost = shost;
  2446		SHOST_TO_SAS_HA(shost) = &hisi_hba->sha;
  2447	
  2448		timer_setup(&hisi_hba->timer, NULL, 0);
  2449	
  2450		if (hisi_sas_get_fw_info(hisi_hba) < 0)
  2451			goto err_out;
  2452	
  2453		if (hisi_hba->hw->fw_info_check) {
  2454			error = hisi_hba->hw->fw_info_check(hisi_hba);
  2455	
  2456			if (error)
> 2457				return error;
  2458		}
  2459	
  2460		error = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64));
  2461		if (error) {
  2462			dev_err(dev, "No usable DMA addressing method\n");
  2463			goto err_out;
  2464		}
  2465	
  2466		hisi_hba->regs = devm_platform_ioremap_resource(pdev, 0);
  2467		if (IS_ERR(hisi_hba->regs))
  2468			goto err_out;
  2469	
  2470		res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
  2471		if (res) {
  2472			hisi_hba->sgpio_regs = devm_ioremap_resource(dev, res);
  2473			if (IS_ERR(hisi_hba->sgpio_regs))
  2474				goto err_out;
  2475		}
  2476	
  2477		if (hisi_sas_alloc(hisi_hba)) {
  2478			hisi_sas_free(hisi_hba);
  2479			goto err_out;
  2480		}
  2481	
  2482		return shost;
  2483	err_out:
  2484		scsi_host_put(shost);
  2485		dev_err(dev, "shost alloc failed\n");
  2486		return NULL;
  2487	}
  2488	

-- 
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki

Re: [PATCH 03/13] scsi: hisi_sas: Add firmware information check

[kernel test robot]

Hi Yihang,

kernel test robot noticed the following build errors:

[auto build test ERROR on jejb-scsi/for-next]
[also build test ERROR on mkp-scsi/for-next linus/master v6.11 next-20240926]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]

url:    https://github.com/intel-lab-lkp/linux/commits/Yihang-Li/scsi-hisi_sas-Adjust-priority-of-registering-and-exiting-debugfs-for-security/20240926-094506
base:   https://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi.git for-next
patch link:    https://lore.kernel.org/r/20240926014332.3905399-4-liyihang9%40huawei.com
patch subject: [PATCH 03/13] scsi: hisi_sas: Add firmware information check
config: x86_64-allyesconfig (https://download.01.org/0day-ci/archive/20240926/202409262135.mC6xdK2H-lkp@intel.com/config)
compiler: clang version 18.1.8 (https://github.com/llvm/llvm-project 3b5b5c1ec4a3095ab096dd780e84d7ab81f3d7ff)
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20240926/202409262135.mC6xdK2H-lkp@intel.com/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202409262135.mC6xdK2H-lkp@intel.com/

All errors (new ones prefixed by >>):

>> drivers/scsi/hisi_sas/hisi_sas_main.c:2457:11: error: incompatible integer to pointer conversion returning 'int' from a function with result type 'struct Scsi_Host *' [-Wint-conversion]
    2457 |                         return error;
         |                                ^~~~~
   drivers/scsi/hisi_sas/hisi_sas_main.c:2460:41: warning: shift count >= width of type [-Wshift-count-overflow]
    2460 |         error = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64));
         |                                                ^~~~~~~~~~~~~~~~
   include/linux/dma-mapping.h:77:54: note: expanded from macro 'DMA_BIT_MASK'
      77 | #define DMA_BIT_MASK(n) (((n) == 64) ? ~0ULL : ((1ULL<<(n))-1))
         |                                                      ^ ~~~
   1 warning and 1 error generated.


vim +2457 drivers/scsi/hisi_sas/hisi_sas_main.c

  2424	
  2425	static struct Scsi_Host *hisi_sas_shost_alloc(struct platform_device *pdev,
  2426						      const struct hisi_sas_hw *hw)
  2427	{
  2428		struct resource *res;
  2429		struct Scsi_Host *shost;
  2430		struct hisi_hba *hisi_hba;
  2431		struct device *dev = &pdev->dev;
  2432		int error;
  2433	
  2434		shost = scsi_host_alloc(hw->sht, sizeof(*hisi_hba));
  2435		if (!shost) {
  2436			dev_err(dev, "scsi host alloc failed\n");
  2437			return NULL;
  2438		}
  2439		hisi_hba = shost_priv(shost);
  2440	
  2441		INIT_WORK(&hisi_hba->rst_work, hisi_sas_rst_work_handler);
  2442		hisi_hba->hw = hw;
  2443		hisi_hba->dev = dev;
  2444		hisi_hba->platform_dev = pdev;
  2445		hisi_hba->shost = shost;
  2446		SHOST_TO_SAS_HA(shost) = &hisi_hba->sha;
  2447	
  2448		timer_setup(&hisi_hba->timer, NULL, 0);
  2449	
  2450		if (hisi_sas_get_fw_info(hisi_hba) < 0)
  2451			goto err_out;
  2452	
  2453		if (hisi_hba->hw->fw_info_check) {
  2454			error = hisi_hba->hw->fw_info_check(hisi_hba);
  2455	
  2456			if (error)
> 2457				return error;
  2458		}
  2459	
  2460		error = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64));
  2461		if (error) {
  2462			dev_err(dev, "No usable DMA addressing method\n");
  2463			goto err_out;
  2464		}
  2465	
  2466		hisi_hba->regs = devm_platform_ioremap_resource(pdev, 0);
  2467		if (IS_ERR(hisi_hba->regs))
  2468			goto err_out;
  2469	
  2470		res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
  2471		if (res) {
  2472			hisi_hba->sgpio_regs = devm_ioremap_resource(dev, res);
  2473			if (IS_ERR(hisi_hba->sgpio_regs))
  2474				goto err_out;
  2475		}
  2476	
  2477		if (hisi_sas_alloc(hisi_hba)) {
  2478			hisi_sas_free(hisi_hba);
  2479			goto err_out;
  2480		}
  2481	
  2482		return shost;
  2483	err_out:
  2484		scsi_host_put(shost);
  2485		dev_err(dev, "shost alloc failed\n");
  2486		return NULL;
  2487	}
  2488	

-- 
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki

Re: [PATCH 03/13] scsi: hisi_sas: Add firmware information check

[kernel test robot]

Hi Yihang,

kernel test robot noticed the following build warnings:

[auto build test WARNING on jejb-scsi/for-next]
[also build test WARNING on mkp-scsi/for-next linus/master v6.11 next-20240927]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]

url:    https://github.com/intel-lab-lkp/linux/commits/Yihang-Li/scsi-hisi_sas-Adjust-priority-of-registering-and-exiting-debugfs-for-security/20240926-094506
base:   https://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi.git for-next
patch link:    https://lore.kernel.org/r/20240926014332.3905399-4-liyihang9%40huawei.com
patch subject: [PATCH 03/13] scsi: hisi_sas: Add firmware information check
config: alpha-randconfig-r133-20240929 (https://download.01.org/0day-ci/archive/20240930/202409300042.USclhodY-lkp@intel.com/config)
compiler: alpha-linux-gcc (GCC) 13.3.0
reproduce: (https://download.01.org/0day-ci/archive/20240930/202409300042.USclhodY-lkp@intel.com/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202409300042.USclhodY-lkp@intel.com/

sparse warnings: (new ones prefixed by >>)
>> drivers/scsi/hisi_sas/hisi_sas_main.c:2457:32: sparse: sparse: incorrect type in return expression (different base types) @@     expected struct Scsi_Host * @@     got int [assigned] error @@
   drivers/scsi/hisi_sas/hisi_sas_main.c:2457:32: sparse:     expected struct Scsi_Host *
   drivers/scsi/hisi_sas/hisi_sas_main.c:2457:32: sparse:     got int [assigned] error
>> drivers/scsi/hisi_sas/hisi_sas_main.c:2457:32: sparse: sparse: non size-preserving integer to pointer cast

vim +2457 drivers/scsi/hisi_sas/hisi_sas_main.c

  2424	
  2425	static struct Scsi_Host *hisi_sas_shost_alloc(struct platform_device *pdev,
  2426						      const struct hisi_sas_hw *hw)
  2427	{
  2428		struct resource *res;
  2429		struct Scsi_Host *shost;
  2430		struct hisi_hba *hisi_hba;
  2431		struct device *dev = &pdev->dev;
  2432		int error;
  2433	
  2434		shost = scsi_host_alloc(hw->sht, sizeof(*hisi_hba));
  2435		if (!shost) {
  2436			dev_err(dev, "scsi host alloc failed\n");
  2437			return NULL;
  2438		}
  2439		hisi_hba = shost_priv(shost);
  2440	
  2441		INIT_WORK(&hisi_hba->rst_work, hisi_sas_rst_work_handler);
  2442		hisi_hba->hw = hw;
  2443		hisi_hba->dev = dev;
  2444		hisi_hba->platform_dev = pdev;
  2445		hisi_hba->shost = shost;
  2446		SHOST_TO_SAS_HA(shost) = &hisi_hba->sha;
  2447	
  2448		timer_setup(&hisi_hba->timer, NULL, 0);
  2449	
  2450		if (hisi_sas_get_fw_info(hisi_hba) < 0)
  2451			goto err_out;
  2452	
  2453		if (hisi_hba->hw->fw_info_check) {
  2454			error = hisi_hba->hw->fw_info_check(hisi_hba);
  2455	
  2456			if (error)
> 2457				return error;
  2458		}
  2459	
  2460		error = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64));
  2461		if (error) {
  2462			dev_err(dev, "No usable DMA addressing method\n");
  2463			goto err_out;
  2464		}
  2465	
  2466		hisi_hba->regs = devm_platform_ioremap_resource(pdev, 0);
  2467		if (IS_ERR(hisi_hba->regs))
  2468			goto err_out;
  2469	
  2470		res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
  2471		if (res) {
  2472			hisi_hba->sgpio_regs = devm_ioremap_resource(dev, res);
  2473			if (IS_ERR(hisi_hba->sgpio_regs))
  2474				goto err_out;
  2475		}
  2476	
  2477		if (hisi_sas_alloc(hisi_hba)) {
  2478			hisi_sas_free(hisi_hba);
  2479			goto err_out;
  2480		}
  2481	
  2482		return shost;
  2483	err_out:
  2484		scsi_host_put(shost);
  2485		dev_err(dev, "shost alloc failed\n");
  2486		return NULL;
  2487	}
  2488	

-- 
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki

[PATCH 04/13] scsi: hisi_sas: Enable all PHYs that are not disabled by user during controller reset

[Yihang Li]

For the controller reset operation(such as FLR or clear nexus ha in SCSI
EH), we will disable all PHYs and then enable PHY based on the
hisi_hba->phy_state obtained in hisi_sas_controller_reset_prepare(). If
the device is removed before controller reset or the PHY is not attached
to any device in directly attached scenario, the corresponding bit of
phy_state is not set. After controller reset done, the PHY is disabled.
The device cannot be identified even if user reconnect the disk.

Therefore, for PHYs that are not disabled by user, hisi_sas_phy_enable()
needs to be executed even if the corresponding bit of phy_state is not set.

Fixes: 89954f024c3a ("scsi: hisi_sas: Ensure all enabled PHYs up during controller reset")
Signed-off-by: Yihang Li <liyihang9@huawei.com>
Reviewed-by: Xiang Chen <chenxiang66@hisilicon.com>
---
 drivers/scsi/hisi_sas/hisi_sas_main.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index e15926c40983..85374800251a 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -1545,10 +1545,16 @@ void hisi_sas_controller_reset_done(struct hisi_hba *hisi_hba)
 	/* Init and wait for PHYs to come up and all libsas event finished. */
 	for (phy_no = 0; phy_no < hisi_hba->n_phy; phy_no++) {
 		struct hisi_sas_phy *phy = &hisi_hba->phy[phy_no];
+		struct asd_sas_phy *sas_phy = &phy->sas_phy;
 
-		if (!(hisi_hba->phy_state & BIT(phy_no)))
+		if (!sas_phy->phy->enabled)
 			continue;
 
+		if (!(hisi_hba->phy_state & BIT(phy_no))) {
+			hisi_sas_phy_enable(hisi_hba, phy_no, 1);
+			continue;
+		}
+
 		async_schedule_domain(hisi_sas_async_init_wait_phyup,
 				      phy, &async);
 	}
-- 
2.33.0

[PATCH 05/13] scsi: hisi_sas: Reset PHY again if phyup timeout

[Yihang Li]

In commit 89954f024c3a ("scsi: hisi_sas: Ensure all enabled PHYs up during
controller reset"), we enable PHYs in parallel through async operations
and wait for PHYs come up. However, for some directly attached SATA disks,
the PHY not come up after a timeout period and the hardware is not ready.
At this time, we should get the latest PHY hardware state, if the new PHY
state is not ready but the old PHY state is ready, call work
HISI_PHYE_LINK_RESET to give it another chance to phyup.

Signed-off-by: Yihang Li <liyihang9@huawei.com>
Reviewed-by: Xiang Chen <chenxiang66@hisilicon.com>
---
 drivers/scsi/hisi_sas/hisi_sas_main.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index 85374800251a..452baf9d5a26 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -1384,6 +1384,7 @@ static void hisi_sas_refresh_port_id(struct hisi_hba *hisi_hba)
 
 static void hisi_sas_rescan_topology(struct hisi_hba *hisi_hba, u32 state)
 {
+	u32 new_state = hisi_hba->hw->get_phys_state(hisi_hba);
 	struct asd_sas_port *_sas_port = NULL;
 	int phy_no;
 
@@ -1397,7 +1398,7 @@ static void hisi_sas_rescan_topology(struct hisi_hba *hisi_hba, u32 state)
 			continue;
 
 		/* Report PHY state change to libsas */
-		if (state & BIT(phy_no)) {
+		if (new_state & BIT(phy_no)) {
 			if (do_port_check && sas_port && sas_port->port_dev) {
 				struct domain_device *dev = sas_port->port_dev;
 
@@ -1410,6 +1411,16 @@ static void hisi_sas_rescan_topology(struct hisi_hba *hisi_hba, u32 state)
 			}
 		} else {
 			hisi_sas_phy_down(hisi_hba, phy_no, 0, GFP_KERNEL);
+
+			/*
+			 * The new_state is not ready but old_state is ready,
+			 * the two possible causes:
+			 * 1. The connected device is removed
+			 * 2. Device exists but phyup timed out
+			 */
+			if (state & BIT(phy_no))
+				hisi_sas_notify_phy_event(phy,
+							  HISI_PHYE_LINK_RESET);
 		}
 	}
 }
-- 
2.33.0

[PATCH 06/13] scsi: hisi_sas: Check usage count only when the runtime PM status is RPM_SUSPENDING

[Yihang Li]

Users can suspend the machine with 'echo disk > /sys/power/state', but the
suspend will fail because the SAS controller cannot be suspended:

[root@localhost ~]# echo freeze > /sys/power/state
-bash: echo: write error: Device or resource busy
[15104.142955] PM: suspend entry (s2idle)
...
[15104.283465] hisi_sas_v3_hw 0000:32:04.0: entering suspend state
[15104.283480] hisi_sas_v3_hw 0000:30:04.0: entering suspend state
[15104.283500] hisi_sas_v3_hw 0000:32:04.0: PM suspend: host status cannot be suspended
[15104.283508] hisi_sas_v3_hw 0000:30:04.0: PM suspend: host status cannot be suspended
[15104.283516] hisi_sas_v3_hw 0000:32:04.0: PM: pci_pm_suspend(): suspend_v3_hw+0x0/0x210 [hisi_sas_v3_hw] returns -16
[15104.283527] hisi_sas_v3_hw 0000:32:04.0: PM: dpm_run_callback(): pci_pm_suspend+0x0/0x1c0 returns -16
[15104.283524] hisi_sas_v3_hw 0000:30:04.0: PM: pci_pm_suspend(): suspend_v3_hw+0x0/0x210 [hisi_sas_v3_hw] returns -16
[15104.283533] hisi_sas_v3_hw 0000:32:04.0: PM: failed to suspend async: error -16
[15104.283536] hisi_sas_v3_hw 0000:30:04.0: PM: dpm_run_callback(): pci_pm_suspend+0x0/0x1c0 returns -16
[15104.283542] hisi_sas_v3_hw 0000:30:04.0: PM: failed to suspend async: error -16

The problem is that when the ->runtime_suspend() callback suspend_v3_hw()
is executing, the current runtime PM status is RPM_ACTIVE and the usage
count of the controller is not 0, so return immediately.

To fix it, Check the device usage count only when the runtime PM status is
RPM_SUSPENDING.

Signed-off-by: Yihang Li <liyihang9@huawei.com>
Reviewed-by: Xiang Chen <chenxiang66@hisilicon.com>
---
 drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
index d48777fc4bd9..9e65ad0e6ce0 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
@@ -5048,7 +5048,8 @@ static int _suspend_v3_hw(struct device *device)
 	interrupt_disable_v3_hw(hisi_hba);
 
 #ifdef CONFIG_PM
-	if (atomic_read(&device->power.usage_count)) {
+	if ((device->power.runtime_status == RPM_SUSPENDING) &&
+	    atomic_read(&device->power.usage_count)) {
 		dev_err(dev, "PM suspend: host status cannot be suspended\n");
 		rc = -EBUSY;
 		goto err_out;
-- 
2.33.0

[PATCH 07/13] scsi: hisi_sas: Add cond_resched() for no forced preemption model

[Yihang Li]

For no forced preemption model kernel, in the scenario where the expander
is connected to 12 high performance SAS SSDs, the following call trace
may occur:

[  214.409199][  C240] watchdog: BUG: soft lockup - CPU#240 stuck for 22s! [irq/149-hisi_sa:3211]
[  214.568533][  C240] pstate: 60400009 (nZCv daif +PAN -UAO -TCO BTYPE=--)
[  214.575224][  C240] pc : fput_many+0x8c/0xdc
[  214.579480][  C240] lr : fput+0x1c/0xf0
[  214.583302][  C240] sp : ffff80002de2b900
[  214.587298][  C240] x29: ffff80002de2b900 x28: ffff1082aa412000
[  214.593291][  C240] x27: ffff3062a0348c08 x26: ffff80003a9f6000
[  214.599284][  C240] x25: ffff1062bbac5c40 x24: 0000000000001000
[  214.605277][  C240] x23: 000000000000000a x22: 0000000000000001
[  214.611270][  C240] x21: 0000000000001000 x20: 0000000000000000
[  214.617262][  C240] x19: ffff3062a41ae580 x18: 0000000000010000
[  214.623255][  C240] x17: 0000000000000001 x16: ffffdb3a6efe5fc0
[  214.629248][  C240] x15: ffffffffffffffff x14: 0000000003ffffff
[  214.635241][  C240] x13: 000000000000ffff x12: 000000000000029c
[  214.641234][  C240] x11: 0000000000000006 x10: ffff80003a9f7fd0
[  214.647226][  C240] x9 : ffffdb3a6f0482fc x8 : 0000000000000001
[  214.653219][  C240] x7 : 0000000000000002 x6 : 0000000000000080
[  214.659212][  C240] x5 : ffff55480ee9b000 x4 : fffffde7f94c6554
[  214.665205][  C240] x3 : 0000000000000002 x2 : 0000000000000020
[  214.671198][  C240] x1 : 0000000000000021 x0 : ffff3062a41ae5b8
[  214.677191][  C240] Call trace:
[  214.680320][  C240]  fput_many+0x8c/0xdc
[  214.684230][  C240]  fput+0x1c/0xf0
[  214.687707][  C240]  aio_complete_rw+0xd8/0x1fc
[  214.692225][  C240]  blkdev_bio_end_io+0x98/0x140
[  214.696917][  C240]  bio_endio+0x160/0x1bc
[  214.701001][  C240]  blk_update_request+0x1c8/0x3bc
[  214.705867][  C240]  scsi_end_request+0x3c/0x1f0
[  214.710471][  C240]  scsi_io_completion+0x7c/0x1a0
[  214.715249][  C240]  scsi_finish_command+0x104/0x140
[  214.720200][  C240]  scsi_softirq_done+0x90/0x180
[  214.724892][  C240]  blk_mq_complete_request+0x5c/0x70
[  214.730016][  C240]  scsi_mq_done+0x48/0xac
[  214.734194][  C240]  sas_scsi_task_done+0xbc/0x16c [libsas]
[  214.739758][  C240]  slot_complete_v3_hw+0x260/0x760 [hisi_sas_v3_hw]
[  214.746185][  C240]  cq_thread_v3_hw+0xbc/0x190 [hisi_sas_v3_hw]
[  214.752179][  C240]  irq_thread_fn+0x34/0xa4
[  214.756435][  C240]  irq_thread+0xc4/0x130
[  214.760520][  C240]  kthread+0x108/0x13c
[  214.764430][  C240]  ret_from_fork+0x10/0x18

This is because in the hisi_sas driver, both the hardware interrupt
handler and the interrupt thread are executed on the same CPU. In the
performance test scenario, function irq_wait_for_interrupt() will always
return 0 if lots of interrupts occurs and the CPU will be continuously
consumed. As a result, the CPU cannot run the watchdog thread. When the
watchdog time exceeds the specified time, call trace occurs.

To fix it, add cond_resched() to execute the watchdog thread.

Signed-off-by: Yihang Li <liyihang9@huawei.com>
Reviewed-by: Xiang Chen <chenxiang66@hisilicon.com>
---
 drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
index 9e65ad0e6ce0..e6fbbefe9959 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
@@ -2493,6 +2493,7 @@ static int complete_v3_hw(struct hisi_sas_cq *cq)
 	/* update rd_point */
 	cq->rd_point = rd_point;
 	hisi_sas_write32(hisi_hba, COMPL_Q_0_RD_PTR + (0x14 * queue), rd_point);
+	cond_resched();
 
 	return completed;
 }
-- 
2.33.0

[PATCH 08/13] scsi: hisi_sas: Default enable interrupt coalescing

[Yihang Li]

In the current interrupt reporting mode, each CQ entry reports an
interrupt. However, when there are a large number of I/O hardware
completion interrupts, the following issue may occur:

[ 4682.678657][  C129] irq 134: nobody cared (try booting with the "irqpoll" option)
[ 4682.708455][  C129] Call trace:
[ 4682.711589][  C129]  dump_backtrace+0x0/0x1e4
[ 4682.715934][  C129]  show_stack+0x20/0x2c
[ 4682.719933][  C129]  dump_stack+0xd8/0x140
[ 4682.724017][  C129]  __report_bad_irq+0x54/0x180
[ 4682.728625][  C129]  note_interrupt+0x1ec/0x2f0
[ 4682.733143][  C129]  handle_irq_event+0x118/0x1ac
[ 4682.737834][  C129]  handle_fasteoi_irq+0xc8/0x200
[ 4682.742613][  C129]  __handle_domain_irq+0x84/0xf0
[ 4682.747391][  C129]  gic_handle_irq+0x88/0x2c0
[ 4682.751822][  C129]  el1_irq+0xbc/0x140
[ 4682.755648][  C129]  _find_next_bit.constprop.0+0x20/0x94
[ 4682.761036][  C129]  cpumask_next+0x24/0x30
[ 4682.765208][  C129]  gic_ipi_send_mask+0x48/0x170
[ 4682.769900][  C129]  __ipi_send_mask+0x34/0x110
[ 4682.775720][  C129]  smp_cross_call+0x3c/0xcc
[ 4682.780064][  C129]  arch_send_call_function_single_ipi+0x38/0x44
[ 4682.786146][  C129]  send_call_function_single_ipi+0xd0/0xe0
[ 4682.791794][  C129]  generic_exec_single+0xb4/0x170
[ 4682.796659][  C129]  smp_call_function_single_async+0x2c/0x40
[ 4682.802395][  C129]  blk_mq_complete_request_remote.part.0+0xec/0x100
[ 4682.808822][  C129]  blk_mq_complete_request+0x30/0x70
[ 4682.813950][  C129]  scsi_mq_done+0x48/0xac
[ 4682.818128][  C129]  sas_scsi_task_done+0xb0/0x150 [libsas]
[ 4682.823692][  C129]  slot_complete_v3_hw+0x230/0x710 [hisi_sas_v3_hw]
[ 4682.830120][  C129]  cq_thread_v3_hw+0xbc/0x190 [hisi_sas_v3_hw]
[ 4682.836114][  C129]  irq_thread_fn+0x34/0xa4
[ 4682.840371][  C129]  irq_thread+0xc4/0x130
[ 4682.844455][  C129]  kthread+0x108/0x13c
[ 4682.848365][  C129]  ret_from_fork+0x10/0x18
[ 4682.852621][  C129] handlers:
[ 4682.855577][  C129] [<00000000949e52bf>] cq_interrupt_v3_hw [hisi_sas_v3_hw] threaded [<000000005d8e3b68>] cq_thread_v3_hw [hisi_sas_v3_hw]
[ 4682.868084][  C129] Disabling IRQ #134

When the IRQ management layer processes each hardware interrupt, if the
return value of the interrupt handler is IRQ_WAKE_THREAD, it will wake up
the handler thread for this interrupt action and set IRQTF_RUNTHREAD flag,
wait for the interrupt handling thread to clear the IRQTF_RUNTHREAD flag
after execution. Later in note_interrupt(), use irq_count to count
hardware interrupts and irqs_unhandled to count interrupts for which no
thread handler is responsible. When irq_count reaches 100000 and
irqs_unhandled reaches 99000, irq will be disabled.

In the performance test scenario, I/O completion hardware interrupts are
continuously and quickly generated. As a result, the interrupt processing
thread is cyclically called in irq_thread() and does not exit, this
affects the response of the interrupt thread to the hardware interrupt and
causes irqs_unhandled to grow to 99000. Finally, the irq is disabled.

Therefore, default enable interrupt coalescing to reduce the generation of
hardware interrupts, this helps interrupt processing threads to stop
calling in irq_thread().

For interrupt coalescing, according to the actual performance test, set
the count of CQ entries to 10 and the interrupt coalescing timeout period
to 10us based on the actual performance test.

Before and after interrupt coalescing is enabled, the 4K read/write
performance is improved by about 3%, and the 256K read/write performance
is basically the same.

Signed-off-by: Yihang Li <liyihang9@huawei.com>
Reviewed-by: Xiang Chen <chenxiang66@hisilicon.com>
---
 drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 17 ++++++++++-------
 1 file changed, 10 insertions(+), 7 deletions(-)

diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
index e6fbbefe9959..310c782b4926 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
@@ -638,9 +638,11 @@ static void init_reg_v3_hw(struct hisi_hba *hisi_hba)
 	hisi_sas_write32(hisi_hba, TRANS_LOCK_ICT_TIME, 0x4A817C80);
 	hisi_sas_write32(hisi_hba, HGC_SAS_TXFAIL_RETRY_CTRL, 0x108);
 	hisi_sas_write32(hisi_hba, CFG_AGING_TIME, 0x1);
-	hisi_sas_write32(hisi_hba, INT_COAL_EN, 0x1);
-	hisi_sas_write32(hisi_hba, OQ_INT_COAL_TIME, 0x1);
-	hisi_sas_write32(hisi_hba, OQ_INT_COAL_CNT, 0x1);
+	hisi_sas_write32(hisi_hba, INT_COAL_EN, 0x3);
+	/* configure the interrupt coalescing timeout period 10us */
+	hisi_sas_write32(hisi_hba, OQ_INT_COAL_TIME, 0xa);
+	/* configure the count of CQ entries 10 */
+	hisi_sas_write32(hisi_hba, OQ_INT_COAL_CNT, 0xa);
 	hisi_sas_write32(hisi_hba, CQ_INT_CONVERGE_EN,
 			 hisi_sas_intr_conv);
 	hisi_sas_write32(hisi_hba, OQ_INT_SRC, 0xffff);
@@ -2797,14 +2799,15 @@ static void config_intr_coal_v3_hw(struct hisi_hba *hisi_hba)
 {
 	/* config those registers between enable and disable PHYs */
 	hisi_sas_stop_phys(hisi_hba);
+	hisi_sas_write32(hisi_hba, INT_COAL_EN, 0x3);
 
 	if (hisi_hba->intr_coal_ticks == 0 ||
 	    hisi_hba->intr_coal_count == 0) {
-		hisi_sas_write32(hisi_hba, INT_COAL_EN, 0x1);
-		hisi_sas_write32(hisi_hba, OQ_INT_COAL_TIME, 0x1);
-		hisi_sas_write32(hisi_hba, OQ_INT_COAL_CNT, 0x1);
+		/* configure the interrupt coalescing timeout period 10us */
+		hisi_sas_write32(hisi_hba, OQ_INT_COAL_TIME, 0xa);
+		/* configure the count of CQ entries 10 */
+		hisi_sas_write32(hisi_hba, OQ_INT_COAL_CNT, 0xa);
 	} else {
-		hisi_sas_write32(hisi_hba, INT_COAL_EN, 0x3);
 		hisi_sas_write32(hisi_hba, OQ_INT_COAL_TIME,
 				 hisi_hba->intr_coal_ticks);
 		hisi_sas_write32(hisi_hba, OQ_INT_COAL_CNT,
-- 
2.33.0

[PATCH 09/13] scsi: hisi_sas: Update disk locked timeout to 7 seconds

[Yihang Li]

From: Xingui Yang <yangxingui@huawei.com>

The sata disk will be locked after the disk sends the DMA Setup frame until
all data frame transmission is completed. The CFG_ICT_TIMER_STEP_TRSH
register is used for sata disk to configure the step size of the timer
which records the time when the disk is locked. The unit is 1us and the
default step size is 150ms. If the disk is locked for more than 7 timer
steps, the io to be sent to the disk will end abnormally.

The current timeout is only about 1 second, it is easy to trigger IO
abnormal end when the SATA hard disk returns data slowly. Adjust the
timeout to 7 seconds based on ERC time of most disks.

Signed-off-by: Xingui Yang <yangxingui@huawei.com>
Reviewed-by: Xiang Chen <chenxiang66@hisilicon.com>
Reviewed-by: Yihang Li <liyihang9@huawei.com>
---
 drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
index 310c782b4926..5c97c4463032 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
@@ -43,6 +43,7 @@
 #define CQ_INT_CONVERGE_EN		0xb0
 #define CFG_AGING_TIME			0xbc
 #define HGC_DFX_CFG2			0xc0
+#define CFG_ICT_TIMER_STEP_TRSH		0xc8
 #define CFG_ABT_SET_QUERY_IPTT	0xd4
 #define CFG_SET_ABORTED_IPTT_OFF	0
 #define CFG_SET_ABORTED_IPTT_MSK	(0xfff << CFG_SET_ABORTED_IPTT_OFF)
@@ -638,6 +639,7 @@ static void init_reg_v3_hw(struct hisi_hba *hisi_hba)
 	hisi_sas_write32(hisi_hba, TRANS_LOCK_ICT_TIME, 0x4A817C80);
 	hisi_sas_write32(hisi_hba, HGC_SAS_TXFAIL_RETRY_CTRL, 0x108);
 	hisi_sas_write32(hisi_hba, CFG_AGING_TIME, 0x1);
+	hisi_sas_write32(hisi_hba, CFG_ICT_TIMER_STEP_TRSH, 0xf4240);
 	hisi_sas_write32(hisi_hba, INT_COAL_EN, 0x3);
 	/* configure the interrupt coalescing timeout period 10us */
 	hisi_sas_write32(hisi_hba, OQ_INT_COAL_TIME, 0xa);
-- 
2.33.0

[PATCH 10/13] scsi: hisi_sas: Add time interval between two H2D FIS following soft reset spec

[Yihang Li]

From: Xingui Yang <yangxingui@huawei.com>

Spec says at least 5us between two H2D FIS when do soft reset, but be
generous and sleep for about 1ms.

Signed-off-by: Xingui Yang <yangxingui@huawei.com>
Reviewed-by: Yihang Li <liyihang9@huawei.com>
---
 drivers/scsi/hisi_sas/hisi_sas_main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index 452baf9d5a26..246712cace28 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -1321,6 +1321,7 @@ static int hisi_sas_softreset_ata_disk(struct domain_device *device)
 	}
 
 	if (rc == TMF_RESP_FUNC_COMPLETE) {
+		usleep_range(900, 1000);
 		ata_for_each_link(link, ap, EDGE) {
 			int pmp = sata_srst_pmp(link);
 
-- 
2.33.0

[PATCH 11/13] scsi: hisi_sas: Update v3 hw STP_LINK_TIMER setting

[Yihang Li]

From: Xingui Yang <yangxingui@huawei.com>

At present, it is found that some SATA HDD disks may continue to return the
HOLD primitive for more than 500ms when they are busy writing data, which
is more likely to trigger an STP link timeout exception. Now Modify STP
link timer from 500ms to the maximum value of 1.048575s.

Signed-off-by: Xingui Yang <yangxingui@huawei.com>
Reviewed-by: Yihang Li <liyihang9@huawei.com>
---
 drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
index 5c97c4463032..bc5c96320f5a 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
@@ -686,7 +686,7 @@ static void init_reg_v3_hw(struct hisi_hba *hisi_hba)
 		hisi_sas_phy_write32(hisi_hba, i, PHY_CTRL_RDY_MSK, 0x0);
 		hisi_sas_phy_write32(hisi_hba, i, PHYCTRL_DWS_RESET_MSK, 0x0);
 		hisi_sas_phy_write32(hisi_hba, i, PHYCTRL_OOB_RESTART_MSK, 0x1);
-		hisi_sas_phy_write32(hisi_hba, i, STP_LINK_TIMER, 0x7f7a120);
+		hisi_sas_phy_write32(hisi_hba, i, STP_LINK_TIMER, 0x7ffffff);
 		hisi_sas_phy_write32(hisi_hba, i, CON_CFG_DRIVER, 0x2a0a01);
 		hisi_sas_phy_write32(hisi_hba, i, SAS_EC_INT_COAL_TIME,
 				     0x30f4240);
-- 
2.33.0

[PATCH 12/13] scsi: hisi_sas: Create all dump files during debugfs initialization

[Yihang Li]

For the current debugfs of hisi_sas, after user triggers dump, the driver
allocate memory space to save the register information and create debugfs
files to display the saved information. In this process, the debugfs files
created after each dump.

Therefore, when the dump is triggered while the driver is unbind, the
following hang occurs:

[67840.853907] Unable to handle kernel NULL pointer dereference at virtual address 00000000000000a0
[67840.862947] Mem abort info:
[67840.865855]   ESR = 0x0000000096000004
[67840.869713]   EC = 0x25: DABT (current EL), IL = 32 bits
[67840.875125]   SET = 0, FnV = 0
[67840.878291]   EA = 0, S1PTW = 0
[67840.881545]   FSC = 0x04: level 0 translation fault
[67840.886528] Data abort info:
[67840.889524]   ISV = 0, ISS = 0x00000004, ISS2 = 0x00000000
[67840.895117]   CM = 0, WnR = 0, TnD = 0, TagAccess = 0
[67840.900284]   GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0
[67840.905709] user pgtable: 4k pages, 48-bit VAs, pgdp=0000002803a1f000
[67840.912263] [00000000000000a0] pgd=0000000000000000, p4d=0000000000000000
[67840.919177] Internal error: Oops: 0000000096000004 [#1] PREEMPT SMP
[67840.996435] pstate: 80400009 (Nzcv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
[67841.003628] pc : down_write+0x30/0x98
[67841.007546] lr : start_creating.part.0+0x60/0x198
[67841.012495] sp : ffff8000b979ba20
[67841.016046] x29: ffff8000b979ba20 x28: 0000000000000010 x27: 0000000000024b40
[67841.023412] x26: 0000000000000012 x25: ffff20202b355ae8 x24: ffff20202b35a8c8
[67841.030779] x23: ffffa36877928208 x22: ffffa368b4972240 x21: ffff8000b979bb18
[67841.038147] x20: ffff00281dc1e3c0 x19: fffffffffffffffe x18: 0000000000000020
[67841.045515] x17: 0000000000000000 x16: ffffa368b128a530 x15: ffffffffffffffff
[67841.052888] x14: ffff8000b979bc18 x13: ffffffffffffffff x12: ffff8000b979bb18
[67841.060263] x11: 0000000000000000 x10: 0000000000000000 x9 : ffffa368b1289b18
[67841.067640] x8 : 0000000000000012 x7 : 0000000000000000 x6 : 00000000000003a9
[67841.075014] x5 : 0000000000000000 x4 : ffff002818c5cb00 x3 : 0000000000000001
[67841.082388] x2 : 0000000000000000 x1 : ffff002818c5cb00 x0 : 00000000000000a0
[67841.089759] Call trace:
[67841.092456]  down_write+0x30/0x98
[67841.096017]  start_creating.part.0+0x60/0x198
[67841.100613]  debugfs_create_dir+0x48/0x1f8
[67841.104950]  debugfs_create_files_v3_hw+0x88/0x348 [hisi_sas_v3_hw]
[67841.111447]  debugfs_snapshot_regs_v3_hw+0x708/0x798 [hisi_sas_v3_hw]
[67841.118111]  debugfs_trigger_dump_v3_hw_write+0x9c/0x120 [hisi_sas_v3_hw]
[67841.125115]  full_proxy_write+0x68/0xc8
[67841.129175]  vfs_write+0xd8/0x3f0
[67841.132708]  ksys_write+0x70/0x108
[67841.136317]  __arm64_sys_write+0x24/0x38
[67841.140440]  invoke_syscall+0x50/0x128
[67841.144385]  el0_svc_common.constprop.0+0xc8/0xf0
[67841.149273]  do_el0_svc+0x24/0x38
[67841.152773]  el0_svc+0x38/0xd8
[67841.156009]  el0t_64_sync_handler+0xc0/0xc8
[67841.160361]  el0t_64_sync+0x1a4/0x1a8
[67841.164189] Code: b9000882 d2800002 d2800023 f9800011 (c85ffc05)
[67841.170443] ---[ end trace 0000000000000000 ]---

To fix this issue, create all directories and files during debugfs
initialization. In this way, the driver only needs to allocate memory
space to save information each time the user triggers dumping.

Signed-off-by: Yihang Li <liyihang9@huawei.com>
Reviewed-by: Xingui Yang <yangxingui@huawei.com>
---
 drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 99 ++++++++++++++++++++------
 1 file changed, 77 insertions(+), 22 deletions(-)

diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
index bc5c96320f5a..8250d44f0b3e 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
@@ -3576,6 +3576,11 @@ debugfs_to_reg_name_v3_hw(int off, int base_off,
 	return NULL;
 }
 
+static bool debugfs_dump_is_generated_v3_hw(void *p)
+{
+	return p ? true : false;
+}
+
 static void debugfs_print_reg_v3_hw(u32 *regs_val, struct seq_file *s,
 				    const struct hisi_sas_debugfs_reg *reg)
 {
@@ -3601,6 +3606,9 @@ static int debugfs_global_v3_hw_show(struct seq_file *s, void *p)
 {
 	struct hisi_sas_debugfs_regs *global = s->private;
 
+	if (!debugfs_dump_is_generated_v3_hw(global->data))
+		return -EPERM;
+
 	debugfs_print_reg_v3_hw(global->data, s,
 				&debugfs_global_reg);
 
@@ -3612,6 +3620,9 @@ static int debugfs_axi_v3_hw_show(struct seq_file *s, void *p)
 {
 	struct hisi_sas_debugfs_regs *axi = s->private;
 
+	if (!debugfs_dump_is_generated_v3_hw(axi->data))
+		return -EPERM;
+
 	debugfs_print_reg_v3_hw(axi->data, s,
 				&debugfs_axi_reg);
 
@@ -3623,6 +3634,9 @@ static int debugfs_ras_v3_hw_show(struct seq_file *s, void *p)
 {
 	struct hisi_sas_debugfs_regs *ras = s->private;
 
+	if (!debugfs_dump_is_generated_v3_hw(ras->data))
+		return -EPERM;
+
 	debugfs_print_reg_v3_hw(ras->data, s,
 				&debugfs_ras_reg);
 
@@ -3635,6 +3649,9 @@ static int debugfs_port_v3_hw_show(struct seq_file *s, void *p)
 	struct hisi_sas_debugfs_port *port = s->private;
 	const struct hisi_sas_debugfs_reg *reg_port = &debugfs_port_reg;
 
+	if (!debugfs_dump_is_generated_v3_hw(port->data))
+		return -EPERM;
+
 	debugfs_print_reg_v3_hw(port->data, s, reg_port);
 
 	return 0;
@@ -3690,6 +3707,9 @@ static int debugfs_cq_v3_hw_show(struct seq_file *s, void *p)
 	struct hisi_sas_debugfs_cq *debugfs_cq = s->private;
 	int slot;
 
+	if (!debugfs_dump_is_generated_v3_hw(debugfs_cq->complete_hdr))
+		return -EPERM;
+
 	for (slot = 0; slot < HISI_SAS_QUEUE_SLOTS; slot++)
 		debugfs_cq_show_slot_v3_hw(s, slot, debugfs_cq);
 
@@ -3711,8 +3731,12 @@ static void debugfs_dq_show_slot_v3_hw(struct seq_file *s, int slot,
 
 static int debugfs_dq_v3_hw_show(struct seq_file *s, void *p)
 {
+	struct hisi_sas_debugfs_dq *debugfs_dq = s->private;
 	int slot;
 
+	if (!debugfs_dump_is_generated_v3_hw(debugfs_dq->hdr))
+		return -EPERM;
+
 	for (slot = 0; slot < HISI_SAS_QUEUE_SLOTS; slot++)
 		debugfs_dq_show_slot_v3_hw(s, slot, s->private);
 
@@ -3726,6 +3750,9 @@ static int debugfs_iost_v3_hw_show(struct seq_file *s, void *p)
 	struct hisi_sas_iost *iost = debugfs_iost->iost;
 	int i, max_command_entries = HISI_SAS_MAX_COMMANDS;
 
+	if (!debugfs_dump_is_generated_v3_hw(iost))
+		return -EPERM;
+
 	for (i = 0; i < max_command_entries; i++, iost++) {
 		__le64 *data = &iost->qw0;
 
@@ -3745,6 +3772,9 @@ static int debugfs_iost_cache_v3_hw_show(struct seq_file *s, void *p)
 	int i, tab_idx;
 	__le64 *iost;
 
+	if (!debugfs_dump_is_generated_v3_hw(iost_cache))
+		return -EPERM;
+
 	for (i = 0; i < HISI_SAS_IOST_ITCT_CACHE_NUM; i++, iost_cache++) {
 		/*
 		 * Data struct of IOST cache:
@@ -3768,6 +3798,9 @@ static int debugfs_itct_v3_hw_show(struct seq_file *s, void *p)
 	struct hisi_sas_debugfs_itct *debugfs_itct = s->private;
 	struct hisi_sas_itct *itct = debugfs_itct->itct;
 
+	if (!debugfs_dump_is_generated_v3_hw(itct))
+		return -EPERM;
+
 	for (i = 0; i < HISI_SAS_MAX_ITCT_ENTRIES; i++, itct++) {
 		__le64 *data = &itct->qw0;
 
@@ -3787,6 +3820,9 @@ static int debugfs_itct_cache_v3_hw_show(struct seq_file *s, void *p)
 	int i, tab_idx;
 	__le64 *itct;
 
+	if (!debugfs_dump_is_generated_v3_hw(itct_cache))
+		return -EPERM;
+
 	for (i = 0; i < HISI_SAS_IOST_ITCT_CACHE_NUM; i++, itct_cache++) {
 		/*
 		 * Data struct of ITCT cache:
@@ -3804,10 +3840,9 @@ static int debugfs_itct_cache_v3_hw_show(struct seq_file *s, void *p)
 }
 DEFINE_SHOW_ATTRIBUTE(debugfs_itct_cache_v3_hw);
 
-static void debugfs_create_files_v3_hw(struct hisi_hba *hisi_hba)
+static void debugfs_create_files_v3_hw(struct hisi_hba *hisi_hba, int index)
 {
 	u64 *debugfs_timestamp;
-	int dump_index = hisi_hba->debugfs_dump_index;
 	struct dentry *dump_dentry;
 	struct dentry *dentry;
 	char name[256];
@@ -3815,17 +3850,17 @@ static void debugfs_create_files_v3_hw(struct hisi_hba *hisi_hba)
 	int c;
 	int d;
 
-	snprintf(name, 256, "%d", dump_index);
+	snprintf(name, 256, "%d", index);
 
 	dump_dentry = debugfs_create_dir(name, hisi_hba->debugfs_dump_dentry);
 
-	debugfs_timestamp = &hisi_hba->debugfs_timestamp[dump_index];
+	debugfs_timestamp = &hisi_hba->debugfs_timestamp[index];
 
 	debugfs_create_u64("timestamp", 0400, dump_dentry,
 			   debugfs_timestamp);
 
 	debugfs_create_file("global", 0400, dump_dentry,
-			    &hisi_hba->debugfs_regs[dump_index][DEBUGFS_GLOBAL],
+			    &hisi_hba->debugfs_regs[index][DEBUGFS_GLOBAL],
 			    &debugfs_global_v3_hw_fops);
 
 	/* Create port dir and files */
@@ -3834,7 +3869,7 @@ static void debugfs_create_files_v3_hw(struct hisi_hba *hisi_hba)
 		snprintf(name, 256, "%d", p);
 
 		debugfs_create_file(name, 0400, dentry,
-				    &hisi_hba->debugfs_port_reg[dump_index][p],
+				    &hisi_hba->debugfs_port_reg[index][p],
 				    &debugfs_port_v3_hw_fops);
 	}
 
@@ -3844,7 +3879,7 @@ static void debugfs_create_files_v3_hw(struct hisi_hba *hisi_hba)
 		snprintf(name, 256, "%d", c);
 
 		debugfs_create_file(name, 0400, dentry,
-				    &hisi_hba->debugfs_cq[dump_index][c],
+				    &hisi_hba->debugfs_cq[index][c],
 				    &debugfs_cq_v3_hw_fops);
 	}
 
@@ -3854,32 +3889,32 @@ static void debugfs_create_files_v3_hw(struct hisi_hba *hisi_hba)
 		snprintf(name, 256, "%d", d);
 
 		debugfs_create_file(name, 0400, dentry,
-				    &hisi_hba->debugfs_dq[dump_index][d],
+				    &hisi_hba->debugfs_dq[index][d],
 				    &debugfs_dq_v3_hw_fops);
 	}
 
 	debugfs_create_file("iost", 0400, dump_dentry,
-			    &hisi_hba->debugfs_iost[dump_index],
+			    &hisi_hba->debugfs_iost[index],
 			    &debugfs_iost_v3_hw_fops);
 
 	debugfs_create_file("iost_cache", 0400, dump_dentry,
-			    &hisi_hba->debugfs_iost_cache[dump_index],
+			    &hisi_hba->debugfs_iost_cache[index],
 			    &debugfs_iost_cache_v3_hw_fops);
 
 	debugfs_create_file("itct", 0400, dump_dentry,
-			    &hisi_hba->debugfs_itct[dump_index],
+			    &hisi_hba->debugfs_itct[index],
 			    &debugfs_itct_v3_hw_fops);
 
 	debugfs_create_file("itct_cache", 0400, dump_dentry,
-			    &hisi_hba->debugfs_itct_cache[dump_index],
+			    &hisi_hba->debugfs_itct_cache[index],
 			    &debugfs_itct_cache_v3_hw_fops);
 
 	debugfs_create_file("axi", 0400, dump_dentry,
-			    &hisi_hba->debugfs_regs[dump_index][DEBUGFS_AXI],
+			    &hisi_hba->debugfs_regs[index][DEBUGFS_AXI],
 			    &debugfs_axi_v3_hw_fops);
 
 	debugfs_create_file("ras", 0400, dump_dentry,
-			    &hisi_hba->debugfs_regs[dump_index][DEBUGFS_RAS],
+			    &hisi_hba->debugfs_regs[index][DEBUGFS_RAS],
 			    &debugfs_ras_v3_hw_fops);
 }
 
@@ -4542,22 +4577,34 @@ static void debugfs_release_v3_hw(struct hisi_hba *hisi_hba, int dump_index)
 	int i;
 
 	devm_kfree(dev, hisi_hba->debugfs_iost_cache[dump_index].cache);
+	hisi_hba->debugfs_iost_cache[dump_index].cache = NULL;
 	devm_kfree(dev, hisi_hba->debugfs_itct_cache[dump_index].cache);
+	hisi_hba->debugfs_itct_cache[dump_index].cache = NULL;
 	devm_kfree(dev, hisi_hba->debugfs_iost[dump_index].iost);
+	hisi_hba->debugfs_iost[dump_index].iost = NULL;
 	devm_kfree(dev, hisi_hba->debugfs_itct[dump_index].itct);
+	hisi_hba->debugfs_itct[dump_index].itct = NULL;
 
-	for (i = 0; i < hisi_hba->queue_count; i++)
+	for (i = 0; i < hisi_hba->queue_count; i++) {
 		devm_kfree(dev, hisi_hba->debugfs_dq[dump_index][i].hdr);
+		hisi_hba->debugfs_dq[dump_index][i].hdr = NULL;
+	}
 
-	for (i = 0; i < hisi_hba->queue_count; i++)
+	for (i = 0; i < hisi_hba->queue_count; i++) {
 		devm_kfree(dev,
 			   hisi_hba->debugfs_cq[dump_index][i].complete_hdr);
+		hisi_hba->debugfs_cq[dump_index][i].complete_hdr = NULL;
+	}
 
-	for (i = 0; i < DEBUGFS_REGS_NUM; i++)
+	for (i = 0; i < DEBUGFS_REGS_NUM; i++) {
 		devm_kfree(dev, hisi_hba->debugfs_regs[dump_index][i].data);
+		hisi_hba->debugfs_regs[dump_index][i].data = NULL;
+	}
 
-	for (i = 0; i < hisi_hba->n_phy; i++)
+	for (i = 0; i < hisi_hba->n_phy; i++) {
 		devm_kfree(dev, hisi_hba->debugfs_port_reg[dump_index][i].data);
+		hisi_hba->debugfs_port_reg[dump_index][i].data = NULL;
+	}
 }
 
 static const struct hisi_sas_debugfs_reg *debugfs_reg_array_v3_hw[DEBUGFS_REGS_NUM] = {
@@ -4684,8 +4731,6 @@ static int debugfs_snapshot_regs_v3_hw(struct hisi_hba *hisi_hba)
 	debugfs_snapshot_itct_reg_v3_hw(hisi_hba);
 	debugfs_snapshot_iost_reg_v3_hw(hisi_hba);
 
-	debugfs_create_files_v3_hw(hisi_hba);
-
 	debugfs_snapshot_restore_v3_hw(hisi_hba);
 	hisi_hba->debugfs_dump_index++;
 
@@ -4769,6 +4814,17 @@ static void debugfs_bist_init_v3_hw(struct hisi_hba *hisi_hba)
 	hisi_hba->debugfs_bist_linkrate = SAS_LINK_RATE_1_5_GBPS;
 }
 
+static void debugfs_dump_init_v3_hw(struct hisi_hba *hisi_hba)
+{
+	int i;
+
+	hisi_hba->debugfs_dump_dentry =
+			debugfs_create_dir("dump", hisi_hba->debugfs_dir);
+
+	for (i = 0; i < hisi_sas_debugfs_dump_count; i++)
+		debugfs_create_files_v3_hw(hisi_hba, i);
+}
+
 static void debugfs_exit_v3_hw(struct hisi_hba *hisi_hba)
 {
 	debugfs_remove_recursive(hisi_hba->debugfs_dir);
@@ -4784,8 +4840,7 @@ static void debugfs_init_v3_hw(struct hisi_hba *hisi_hba)
 	/* create bist structures */
 	debugfs_bist_init_v3_hw(hisi_hba);
 
-	hisi_hba->debugfs_dump_dentry =
-			debugfs_create_dir("dump", hisi_hba->debugfs_dir);
+	debugfs_dump_init_v3_hw(hisi_hba);
 
 	debugfs_phy_down_cnt_init_v3_hw(hisi_hba);
 	debugfs_fifo_init_v3_hw(hisi_hba);
-- 
2.33.0

[PATCH 13/13] scsi: hisi_sas: Add latest_dump for the debugfs dump

[Yihang Li]

Before that, after the user triggers the dump, the latest dump information
can be viewed in the directory with the maximum number in the dump
directory.

After this series patch, the driver creates all debugfs directories and
files during initialization. Therefore, users cannot know the directory
where the latest dump information is stored. So, add latest_dump file to
notify users where the latest dump information is stored.

Signed-off-by: Yihang Li <liyihang9@huawei.com>
Reviewed-by: Xingui Yang <yangxingui@huawei.com>
---
 drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
index 8250d44f0b3e..5db931663ae4 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
@@ -4814,6 +4814,19 @@ static void debugfs_bist_init_v3_hw(struct hisi_hba *hisi_hba)
 	hisi_hba->debugfs_bist_linkrate = SAS_LINK_RATE_1_5_GBPS;
 }
 
+static int debugfs_dump_index_v3_hw_show(struct seq_file *s, void *p)
+{
+	int *debugfs_dump_index = s->private;
+
+	if (*debugfs_dump_index > 0)
+		seq_printf(s, "%d\n", *debugfs_dump_index - 1);
+	else
+		seq_puts(s, "dump not triggered\n");
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(debugfs_dump_index_v3_hw);
+
 static void debugfs_dump_init_v3_hw(struct hisi_hba *hisi_hba)
 {
 	int i;
@@ -4821,6 +4834,10 @@ static void debugfs_dump_init_v3_hw(struct hisi_hba *hisi_hba)
 	hisi_hba->debugfs_dump_dentry =
 			debugfs_create_dir("dump", hisi_hba->debugfs_dir);
 
+	debugfs_create_file("latest_dump", 0400, hisi_hba->debugfs_dump_dentry,
+			    &hisi_hba->debugfs_dump_index,
+			    &debugfs_dump_index_v3_hw_fops);
+
 	for (i = 0; i < hisi_sas_debugfs_dump_count; i++)
 		debugfs_create_files_v3_hw(hisi_hba, i);
 }
-- 
2.33.0