[PATCH 0/9] hisi_sas: some misc changes

[PATCH 0/9] hisi_sas: some misc changes

[John Garry]

This patchset introduces some more minor misc changes to the driver.
Patches of note include:
- Pre-allocate slot DMA buffers
- some fixes for host reset handling

John Garry (2):
  scsi: hisi_sas: Add missing PHY spinlock init
  scsi: hisi_sas: Update a couple of register settings for v3 hw

Xiang Chen (2):
  scsi: hisi_sas: Use dmam_alloc_coherent()
  scsi: hisi_sas: Pre-allocate slot DMA buffers

Xiaofei Tan (5):
  scsi: hisi_sas: Only process broadcast change in phy_bcast_v3_hw()
  scsi: hisi_sas: Fix the conflict between dev gone and host reset
  scsi: hisi_sas: Adjust task reject period during host reset
  scsi: hisi_sas: Add a flag to filter PHY events during reset
  scsi: hisi_sas: Release all remaining resources in clear nexus ha

 drivers/scsi/hisi_sas/hisi_sas.h       |  10 +-
 drivers/scsi/hisi_sas/hisi_sas_main.c  | 214 +++++++++++++++------------------
 drivers/scsi/hisi_sas/hisi_sas_v1_hw.c |   3 +-
 drivers/scsi/hisi_sas/hisi_sas_v2_hw.c |   3 +-
 drivers/scsi/hisi_sas/hisi_sas_v3_hw.c |  16 ++-
 5 files changed, 122 insertions(+), 124 deletions(-)

-- 
1.9.1

[PATCH 0/9] hisi_sas: some misc changes

[John Garry]

This patchset introduces some more minor misc changes to the driver.
Patches of note include:
- Pre-allocate slot DMA buffers
- some fixes for host reset handling

John Garry (2):
  scsi: hisi_sas: Add missing PHY spinlock init
  scsi: hisi_sas: Update a couple of register settings for v3 hw

Xiang Chen (2):
  scsi: hisi_sas: Use dmam_alloc_coherent()
  scsi: hisi_sas: Pre-allocate slot DMA buffers

Xiaofei Tan (5):
  scsi: hisi_sas: Only process broadcast change in phy_bcast_v3_hw()
  scsi: hisi_sas: Fix the conflict between dev gone and host reset
  scsi: hisi_sas: Adjust task reject period during host reset
  scsi: hisi_sas: Add a flag to filter PHY events during reset
  scsi: hisi_sas: Release all remaining resources in clear nexus ha

 drivers/scsi/hisi_sas/hisi_sas.h       |  10 +-
 drivers/scsi/hisi_sas/hisi_sas_main.c  | 214 +++++++++++++++------------------
 drivers/scsi/hisi_sas/hisi_sas_v1_hw.c |   3 +-
 drivers/scsi/hisi_sas/hisi_sas_v2_hw.c |   3 +-
 drivers/scsi/hisi_sas/hisi_sas_v3_hw.c |  16 ++-
 5 files changed, 122 insertions(+), 124 deletions(-)

-- 
1.9.1

[PATCH 1/9] scsi: hisi_sas: Use dmam_alloc_coherent()

[John Garry]

From: Xiang Chen <chenxiang66@hisilicon.com>

This patch replaces the usage of dma_alloc_coherent() with the managed
version, dmam_alloc_coherent(), hereby reducing replicated code.

Signed-off-by: Xiang Chen <chenxiang66@hisilicon.com>
Signed-off-by; John Garry <john.garry@huawei.com>
---
 drivers/scsi/hisi_sas/hisi_sas_main.c | 80 +++++++++--------------------------
 1 file changed, 20 insertions(+), 60 deletions(-)

diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index 6f56297..1c424bb 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -2045,15 +2045,17 @@ int hisi_sas_alloc(struct hisi_hba *hisi_hba, struct Scsi_Host *shost)
 
 		/* Delivery queue */
 		s = sizeof(struct hisi_sas_cmd_hdr) * HISI_SAS_QUEUE_SLOTS;
-		hisi_hba->cmd_hdr[i] = dma_alloc_coherent(dev, s,
-					&hisi_hba->cmd_hdr_dma[i], GFP_KERNEL);
+		hisi_hba->cmd_hdr[i] = dmam_alloc_coherent(dev, s,
+						&hisi_hba->cmd_hdr_dma[i],
+						GFP_KERNEL);
 		if (!hisi_hba->cmd_hdr[i])
 			goto err_out;
 
 		/* Completion queue */
 		s = hisi_hba->hw->complete_hdr_size * HISI_SAS_QUEUE_SLOTS;
-		hisi_hba->complete_hdr[i] = dma_alloc_coherent(dev, s,
-				&hisi_hba->complete_hdr_dma[i], GFP_KERNEL);
+		hisi_hba->complete_hdr[i] = dmam_alloc_coherent(dev, s,
+						&hisi_hba->complete_hdr_dma[i],
+						GFP_KERNEL);
 		if (!hisi_hba->complete_hdr[i])
 			goto err_out;
 	}
@@ -2064,10 +2066,11 @@ int hisi_sas_alloc(struct hisi_hba *hisi_hba, struct Scsi_Host *shost)
 		goto err_out;
 
 	s = HISI_SAS_MAX_ITCT_ENTRIES * sizeof(struct hisi_sas_itct);
-	hisi_hba->itct = dma_zalloc_coherent(dev, s, &hisi_hba->itct_dma,
-					    GFP_KERNEL);
+	hisi_hba->itct = dmam_alloc_coherent(dev, s, &hisi_hba->itct_dma,
+					     GFP_KERNEL);
 	if (!hisi_hba->itct)
 		goto err_out;
+	memset(hisi_hba->itct, 0, s);
 
 	hisi_hba->slot_info = devm_kcalloc(dev, max_command_entries,
 					   sizeof(struct hisi_sas_slot),
@@ -2076,14 +2079,15 @@ int hisi_sas_alloc(struct hisi_hba *hisi_hba, struct Scsi_Host *shost)
 		goto err_out;
 
 	s = max_command_entries * sizeof(struct hisi_sas_iost);
-	hisi_hba->iost = dma_alloc_coherent(dev, s, &hisi_hba->iost_dma,
-					    GFP_KERNEL);
+	hisi_hba->iost = dmam_alloc_coherent(dev, s, &hisi_hba->iost_dma,
+					     GFP_KERNEL);
 	if (!hisi_hba->iost)
 		goto err_out;
 
 	s = max_command_entries * sizeof(struct hisi_sas_breakpoint);
-	hisi_hba->breakpoint = dma_alloc_coherent(dev, s,
-				&hisi_hba->breakpoint_dma, GFP_KERNEL);
+	hisi_hba->breakpoint = dmam_alloc_coherent(dev, s,
+						   &hisi_hba->breakpoint_dma,
+						   GFP_KERNEL);
 	if (!hisi_hba->breakpoint)
 		goto err_out;
 
@@ -2094,14 +2098,16 @@ int hisi_sas_alloc(struct hisi_hba *hisi_hba, struct Scsi_Host *shost)
 		goto err_out;
 
 	s = sizeof(struct hisi_sas_initial_fis) * HISI_SAS_MAX_PHYS;
-	hisi_hba->initial_fis = dma_alloc_coherent(dev, s,
-				&hisi_hba->initial_fis_dma, GFP_KERNEL);
+	hisi_hba->initial_fis = dmam_alloc_coherent(dev, s,
+						    &hisi_hba->initial_fis_dma,
+						    GFP_KERNEL);
 	if (!hisi_hba->initial_fis)
 		goto err_out;
 
 	s = HISI_SAS_MAX_ITCT_ENTRIES * sizeof(struct hisi_sas_sata_breakpoint);
-	hisi_hba->sata_breakpoint = dma_alloc_coherent(dev, s,
-				&hisi_hba->sata_breakpoint_dma, GFP_KERNEL);
+	hisi_hba->sata_breakpoint = dmam_alloc_coherent(dev, s,
+					&hisi_hba->sata_breakpoint_dma,
+					GFP_KERNEL);
 	if (!hisi_hba->sata_breakpoint)
 		goto err_out;
 	hisi_sas_init_mem(hisi_hba);
@@ -2122,54 +2128,8 @@ int hisi_sas_alloc(struct hisi_hba *hisi_hba, struct Scsi_Host *shost)
 
 void hisi_sas_free(struct hisi_hba *hisi_hba)
 {
-	struct device *dev = hisi_hba->dev;
-	int i, s, max_command_entries = hisi_hba->hw->max_command_entries;
-
-	for (i = 0; i < hisi_hba->queue_count; i++) {
-		s = sizeof(struct hisi_sas_cmd_hdr) * HISI_SAS_QUEUE_SLOTS;
-		if (hisi_hba->cmd_hdr[i])
-			dma_free_coherent(dev, s,
-					  hisi_hba->cmd_hdr[i],
-					  hisi_hba->cmd_hdr_dma[i]);
-
-		s = hisi_hba->hw->complete_hdr_size * HISI_SAS_QUEUE_SLOTS;
-		if (hisi_hba->complete_hdr[i])
-			dma_free_coherent(dev, s,
-					  hisi_hba->complete_hdr[i],
-					  hisi_hba->complete_hdr_dma[i]);
-	}
-
 	dma_pool_destroy(hisi_hba->buffer_pool);
 
-	s = HISI_SAS_MAX_ITCT_ENTRIES * sizeof(struct hisi_sas_itct);
-	if (hisi_hba->itct)
-		dma_free_coherent(dev, s,
-				  hisi_hba->itct, hisi_hba->itct_dma);
-
-	s = max_command_entries * sizeof(struct hisi_sas_iost);
-	if (hisi_hba->iost)
-		dma_free_coherent(dev, s,
-				  hisi_hba->iost, hisi_hba->iost_dma);
-
-	s = max_command_entries * sizeof(struct hisi_sas_breakpoint);
-	if (hisi_hba->breakpoint)
-		dma_free_coherent(dev, s,
-				  hisi_hba->breakpoint,
-				  hisi_hba->breakpoint_dma);
-
-
-	s = sizeof(struct hisi_sas_initial_fis) * HISI_SAS_MAX_PHYS;
-	if (hisi_hba->initial_fis)
-		dma_free_coherent(dev, s,
-				  hisi_hba->initial_fis,
-				  hisi_hba->initial_fis_dma);
-
-	s = HISI_SAS_MAX_ITCT_ENTRIES * sizeof(struct hisi_sas_sata_breakpoint);
-	if (hisi_hba->sata_breakpoint)
-		dma_free_coherent(dev, s,
-				  hisi_hba->sata_breakpoint,
-				  hisi_hba->sata_breakpoint_dma);
-
 	if (hisi_hba->wq)
 		destroy_workqueue(hisi_hba->wq);
 }
-- 
1.9.1

[PATCH 1/9] scsi: hisi_sas: Use dmam_alloc_coherent()

[John Garry]

From: Xiang Chen <chenxiang66@hisilicon.com>

This patch replaces the usage of dma_alloc_coherent() with the managed
version, dmam_alloc_coherent(), hereby reducing replicated code.

Signed-off-by: Xiang Chen <chenxiang66@hisilicon.com>
Signed-off-by; John Garry <john.garry@huawei.com>
---
 drivers/scsi/hisi_sas/hisi_sas_main.c | 80 +++++++++--------------------------
 1 file changed, 20 insertions(+), 60 deletions(-)

diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index 6f56297..1c424bb 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -2045,15 +2045,17 @@ int hisi_sas_alloc(struct hisi_hba *hisi_hba, struct Scsi_Host *shost)
 
 		/* Delivery queue */
 		s = sizeof(struct hisi_sas_cmd_hdr) * HISI_SAS_QUEUE_SLOTS;
-		hisi_hba->cmd_hdr[i] = dma_alloc_coherent(dev, s,
-					&hisi_hba->cmd_hdr_dma[i], GFP_KERNEL);
+		hisi_hba->cmd_hdr[i] = dmam_alloc_coherent(dev, s,
+						&hisi_hba->cmd_hdr_dma[i],
+						GFP_KERNEL);
 		if (!hisi_hba->cmd_hdr[i])
 			goto err_out;
 
 		/* Completion queue */
 		s = hisi_hba->hw->complete_hdr_size * HISI_SAS_QUEUE_SLOTS;
-		hisi_hba->complete_hdr[i] = dma_alloc_coherent(dev, s,
-				&hisi_hba->complete_hdr_dma[i], GFP_KERNEL);
+		hisi_hba->complete_hdr[i] = dmam_alloc_coherent(dev, s,
+						&hisi_hba->complete_hdr_dma[i],
+						GFP_KERNEL);
 		if (!hisi_hba->complete_hdr[i])
 			goto err_out;
 	}
@@ -2064,10 +2066,11 @@ int hisi_sas_alloc(struct hisi_hba *hisi_hba, struct Scsi_Host *shost)
 		goto err_out;
 
 	s = HISI_SAS_MAX_ITCT_ENTRIES * sizeof(struct hisi_sas_itct);
-	hisi_hba->itct = dma_zalloc_coherent(dev, s, &hisi_hba->itct_dma,
-					    GFP_KERNEL);
+	hisi_hba->itct = dmam_alloc_coherent(dev, s, &hisi_hba->itct_dma,
+					     GFP_KERNEL);
 	if (!hisi_hba->itct)
 		goto err_out;
+	memset(hisi_hba->itct, 0, s);
 
 	hisi_hba->slot_info = devm_kcalloc(dev, max_command_entries,
 					   sizeof(struct hisi_sas_slot),
@@ -2076,14 +2079,15 @@ int hisi_sas_alloc(struct hisi_hba *hisi_hba, struct Scsi_Host *shost)
 		goto err_out;
 
 	s = max_command_entries * sizeof(struct hisi_sas_iost);
-	hisi_hba->iost = dma_alloc_coherent(dev, s, &hisi_hba->iost_dma,
-					    GFP_KERNEL);
+	hisi_hba->iost = dmam_alloc_coherent(dev, s, &hisi_hba->iost_dma,
+					     GFP_KERNEL);
 	if (!hisi_hba->iost)
 		goto err_out;
 
 	s = max_command_entries * sizeof(struct hisi_sas_breakpoint);
-	hisi_hba->breakpoint = dma_alloc_coherent(dev, s,
-				&hisi_hba->breakpoint_dma, GFP_KERNEL);
+	hisi_hba->breakpoint = dmam_alloc_coherent(dev, s,
+						   &hisi_hba->breakpoint_dma,
+						   GFP_KERNEL);
 	if (!hisi_hba->breakpoint)
 		goto err_out;
 
@@ -2094,14 +2098,16 @@ int hisi_sas_alloc(struct hisi_hba *hisi_hba, struct Scsi_Host *shost)
 		goto err_out;
 
 	s = sizeof(struct hisi_sas_initial_fis) * HISI_SAS_MAX_PHYS;
-	hisi_hba->initial_fis = dma_alloc_coherent(dev, s,
-				&hisi_hba->initial_fis_dma, GFP_KERNEL);
+	hisi_hba->initial_fis = dmam_alloc_coherent(dev, s,
+						    &hisi_hba->initial_fis_dma,
+						    GFP_KERNEL);
 	if (!hisi_hba->initial_fis)
 		goto err_out;
 
 	s = HISI_SAS_MAX_ITCT_ENTRIES * sizeof(struct hisi_sas_sata_breakpoint);
-	hisi_hba->sata_breakpoint = dma_alloc_coherent(dev, s,
-				&hisi_hba->sata_breakpoint_dma, GFP_KERNEL);
+	hisi_hba->sata_breakpoint = dmam_alloc_coherent(dev, s,
+					&hisi_hba->sata_breakpoint_dma,
+					GFP_KERNEL);
 	if (!hisi_hba->sata_breakpoint)
 		goto err_out;
 	hisi_sas_init_mem(hisi_hba);
@@ -2122,54 +2128,8 @@ int hisi_sas_alloc(struct hisi_hba *hisi_hba, struct Scsi_Host *shost)
 
 void hisi_sas_free(struct hisi_hba *hisi_hba)
 {
-	struct device *dev = hisi_hba->dev;
-	int i, s, max_command_entries = hisi_hba->hw->max_command_entries;
-
-	for (i = 0; i < hisi_hba->queue_count; i++) {
-		s = sizeof(struct hisi_sas_cmd_hdr) * HISI_SAS_QUEUE_SLOTS;
-		if (hisi_hba->cmd_hdr[i])
-			dma_free_coherent(dev, s,
-					  hisi_hba->cmd_hdr[i],
-					  hisi_hba->cmd_hdr_dma[i]);
-
-		s = hisi_hba->hw->complete_hdr_size * HISI_SAS_QUEUE_SLOTS;
-		if (hisi_hba->complete_hdr[i])
-			dma_free_coherent(dev, s,
-					  hisi_hba->complete_hdr[i],
-					  hisi_hba->complete_hdr_dma[i]);
-	}
-
 	dma_pool_destroy(hisi_hba->buffer_pool);
 
-	s = HISI_SAS_MAX_ITCT_ENTRIES * sizeof(struct hisi_sas_itct);
-	if (hisi_hba->itct)
-		dma_free_coherent(dev, s,
-				  hisi_hba->itct, hisi_hba->itct_dma);
-
-	s = max_command_entries * sizeof(struct hisi_sas_iost);
-	if (hisi_hba->iost)
-		dma_free_coherent(dev, s,
-				  hisi_hba->iost, hisi_hba->iost_dma);
-
-	s = max_command_entries * sizeof(struct hisi_sas_breakpoint);
-	if (hisi_hba->breakpoint)
-		dma_free_coherent(dev, s,
-				  hisi_hba->breakpoint,
-				  hisi_hba->breakpoint_dma);
-
-
-	s = sizeof(struct hisi_sas_initial_fis) * HISI_SAS_MAX_PHYS;
-	if (hisi_hba->initial_fis)
-		dma_free_coherent(dev, s,
-				  hisi_hba->initial_fis,
-				  hisi_hba->initial_fis_dma);
-
-	s = HISI_SAS_MAX_ITCT_ENTRIES * sizeof(struct hisi_sas_sata_breakpoint);
-	if (hisi_hba->sata_breakpoint)
-		dma_free_coherent(dev, s,
-				  hisi_hba->sata_breakpoint,
-				  hisi_hba->sata_breakpoint_dma);
-
 	if (hisi_hba->wq)
 		destroy_workqueue(hisi_hba->wq);
 }
-- 
1.9.1

[PATCH 2/9] scsi: hisi_sas: Only process broadcast change in phy_bcast_v3_hw()

[John Garry]

From: Xiaofei Tan <tanxiaofei@huawei.com>

There are many BROADCAST primitives generated by the host. We are only
interested in BROADCAST (CHANGE) primitives currently, so only process
this.

We have applied this processing for v2 hw before, and it is also needed
for v3 hw.

Signed-off-by: Xiaofei Tan <tanxiaofei@huawei.com>
Signed-off-by: John Garry <john.garry@huawei.com>
---
 drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 8 +++++++-
 1 file changed, 7 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 9f1e2d0..0a126a82 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
@@ -131,6 +131,9 @@
 #define SL_CONTROL_NOTIFY_EN_MSK	(0x1 << SL_CONTROL_NOTIFY_EN_OFF)
 #define SL_CTA_OFF		17
 #define SL_CTA_MSK		(0x1 << SL_CTA_OFF)
+#define RX_PRIMS_STATUS			(PORT_BASE + 0x98)
+#define RX_BCAST_CHG_OFF		1
+#define RX_BCAST_CHG_MSK		(0x1 << RX_BCAST_CHG_OFF)
 #define TX_ID_DWORD0			(PORT_BASE + 0x9c)
 #define TX_ID_DWORD1			(PORT_BASE + 0xa0)
 #define TX_ID_DWORD2			(PORT_BASE + 0xa4)
@@ -1256,9 +1259,12 @@ static irqreturn_t phy_bcast_v3_hw(int phy_no, struct hisi_hba *hisi_hba)
 	struct hisi_sas_phy *phy = &hisi_hba->phy[phy_no];
 	struct asd_sas_phy *sas_phy = &phy->sas_phy;
 	struct sas_ha_struct *sas_ha = &hisi_hba->sha;
+	u32 bcast_status;
 
 	hisi_sas_phy_write32(hisi_hba, phy_no, SL_RX_BCAST_CHK_MSK, 1);
-	sas_ha->notify_port_event(sas_phy, PORTE_BROADCAST_RCVD);
+	bcast_status = hisi_sas_phy_read32(hisi_hba, phy_no, RX_PRIMS_STATUS);
+	if (bcast_status & RX_BCAST_CHG_MSK)
+		sas_ha->notify_port_event(sas_phy, PORTE_BROADCAST_RCVD);
 	hisi_sas_phy_write32(hisi_hba, phy_no, CHL_INT0,
 			     CHL_INT0_SL_RX_BCST_ACK_MSK);
 	hisi_sas_phy_write32(hisi_hba, phy_no, SL_RX_BCAST_CHK_MSK, 0);
-- 
1.9.1

[PATCH 2/9] scsi: hisi_sas: Only process broadcast change in phy_bcast_v3_hw()

[John Garry]

From: Xiaofei Tan <tanxiaofei@huawei.com>

There are many BROADCAST primitives generated by the host. We are only
interested in BROADCAST (CHANGE) primitives currently, so only process
this.

We have applied this processing for v2 hw before, and it is also needed
for v3 hw.

Signed-off-by: Xiaofei Tan <tanxiaofei@huawei.com>
Signed-off-by: John Garry <john.garry@huawei.com>
---
 drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 8 +++++++-
 1 file changed, 7 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 9f1e2d0..0a126a82 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
@@ -131,6 +131,9 @@
 #define SL_CONTROL_NOTIFY_EN_MSK	(0x1 << SL_CONTROL_NOTIFY_EN_OFF)
 #define SL_CTA_OFF		17
 #define SL_CTA_MSK		(0x1 << SL_CTA_OFF)
+#define RX_PRIMS_STATUS			(PORT_BASE + 0x98)
+#define RX_BCAST_CHG_OFF		1
+#define RX_BCAST_CHG_MSK		(0x1 << RX_BCAST_CHG_OFF)
 #define TX_ID_DWORD0			(PORT_BASE + 0x9c)
 #define TX_ID_DWORD1			(PORT_BASE + 0xa0)
 #define TX_ID_DWORD2			(PORT_BASE + 0xa4)
@@ -1256,9 +1259,12 @@ static irqreturn_t phy_bcast_v3_hw(int phy_no, struct hisi_hba *hisi_hba)
 	struct hisi_sas_phy *phy = &hisi_hba->phy[phy_no];
 	struct asd_sas_phy *sas_phy = &phy->sas_phy;
 	struct sas_ha_struct *sas_ha = &hisi_hba->sha;
+	u32 bcast_status;
 
 	hisi_sas_phy_write32(hisi_hba, phy_no, SL_RX_BCAST_CHK_MSK, 1);
-	sas_ha->notify_port_event(sas_phy, PORTE_BROADCAST_RCVD);
+	bcast_status = hisi_sas_phy_read32(hisi_hba, phy_no, RX_PRIMS_STATUS);
+	if (bcast_status & RX_BCAST_CHG_MSK)
+		sas_ha->notify_port_event(sas_phy, PORTE_BROADCAST_RCVD);
 	hisi_sas_phy_write32(hisi_hba, phy_no, CHL_INT0,
 			     CHL_INT0_SL_RX_BCST_ACK_MSK);
 	hisi_sas_phy_write32(hisi_hba, phy_no, SL_RX_BCAST_CHK_MSK, 0);
-- 
1.9.1

[PATCH 3/9] scsi: hisi_sas: Fix the conflict between dev gone and host reset

[John Garry]

From: Xiaofei Tan <tanxiaofei@huawei.com>

There is a possible conflict when a device is removed and host reset
occurs concurrently.

The reason is that then the device is notified as gone, we try to clear
the ITCT, which is notified via an interrupt. The dev gone function pends
on this event with a completion, which is completed when the ITCT
interrupt occurs.

But host reset will disable all interrupts, the wait_for_completion() may
wait indefinitely.

This patch adds an semaphore to synchronise this two processes. The
semaphore is taken by the host reset as the basis of synchronising.

Signed-off-by: Xiaofei Tan <tanxiaofei@huawei.com>
Signed-off-by: John Garry <john.garry@huawei.com>
---
 drivers/scsi/hisi_sas/hisi_sas.h      | 1 +
 drivers/scsi/hisi_sas/hisi_sas_main.c | 6 ++++++
 2 files changed, 7 insertions(+)

diff --git a/drivers/scsi/hisi_sas/hisi_sas.h b/drivers/scsi/hisi_sas/hisi_sas.h
index 7052a5d..78e5a92 100644
--- a/drivers/scsi/hisi_sas/hisi_sas.h
+++ b/drivers/scsi/hisi_sas/hisi_sas.h
@@ -277,6 +277,7 @@ struct hisi_hba {
 
 	int n_phy;
 	spinlock_t lock;
+	struct semaphore sem;
 
 	struct timer_list timer;
 	struct workqueue_struct *wq;
diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index 1c424bb..823386f 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -914,7 +914,9 @@ static void hisi_sas_dev_gone(struct domain_device *device)
 
 		hisi_sas_dereg_device(hisi_hba, device);
 
+		down(&hisi_hba->sem);
 		hisi_hba->hw->clear_itct(hisi_hba, sas_dev);
+		up(&hisi_hba->sem);
 		device->lldd_dev = NULL;
 	}
 
@@ -1364,6 +1366,7 @@ static int hisi_sas_controller_reset(struct hisi_hba *hisi_hba)
 	if (test_and_set_bit(HISI_SAS_RESET_BIT, &hisi_hba->flags))
 		return -1;
 
+	down(&hisi_hba->sem);
 	dev_info(dev, "controller resetting...\n");
 	old_state = hisi_hba->hw->get_phys_state(hisi_hba);
 
@@ -1378,6 +1381,7 @@ static int hisi_sas_controller_reset(struct hisi_hba *hisi_hba)
 	if (rc) {
 		dev_warn(dev, "controller reset failed (%d)\n", rc);
 		clear_bit(HISI_SAS_REJECT_CMD_BIT, &hisi_hba->flags);
+		up(&hisi_hba->sem);
 		scsi_unblock_requests(shost);
 		goto out;
 	}
@@ -1388,6 +1392,7 @@ static int hisi_sas_controller_reset(struct hisi_hba *hisi_hba)
 	hisi_hba->hw->phys_init(hisi_hba);
 	msleep(1000);
 	hisi_sas_refresh_port_id(hisi_hba);
+	up(&hisi_hba->sem);
 
 	if (hisi_hba->reject_stp_links_msk)
 		hisi_sas_terminate_stp_reject(hisi_hba);
@@ -2016,6 +2021,7 @@ int hisi_sas_alloc(struct hisi_hba *hisi_hba, struct Scsi_Host *shost)
 	struct device *dev = hisi_hba->dev;
 	int i, s, max_command_entries = hisi_hba->hw->max_command_entries;
 
+	sema_init(&hisi_hba->sem, 1);
 	spin_lock_init(&hisi_hba->lock);
 	for (i = 0; i < hisi_hba->n_phy; i++) {
 		hisi_sas_phy_init(hisi_hba, i);
-- 
1.9.1

[PATCH 3/9] scsi: hisi_sas: Fix the conflict between dev gone and host reset

[John Garry]

From: Xiaofei Tan <tanxiaofei@huawei.com>

There is a possible conflict when a device is removed and host reset
occurs concurrently.

The reason is that then the device is notified as gone, we try to clear
the ITCT, which is notified via an interrupt. The dev gone function pends
on this event with a completion, which is completed when the ITCT
interrupt occurs.

But host reset will disable all interrupts, the wait_for_completion() may
wait indefinitely.

This patch adds an semaphore to synchronise this two processes. The
semaphore is taken by the host reset as the basis of synchronising.

Signed-off-by: Xiaofei Tan <tanxiaofei@huawei.com>
Signed-off-by: John Garry <john.garry@huawei.com>
---
 drivers/scsi/hisi_sas/hisi_sas.h      | 1 +
 drivers/scsi/hisi_sas/hisi_sas_main.c | 6 ++++++
 2 files changed, 7 insertions(+)

diff --git a/drivers/scsi/hisi_sas/hisi_sas.h b/drivers/scsi/hisi_sas/hisi_sas.h
index 7052a5d..78e5a92 100644
--- a/drivers/scsi/hisi_sas/hisi_sas.h
+++ b/drivers/scsi/hisi_sas/hisi_sas.h
@@ -277,6 +277,7 @@ struct hisi_hba {
 
 	int n_phy;
 	spinlock_t lock;
+	struct semaphore sem;
 
 	struct timer_list timer;
 	struct workqueue_struct *wq;
diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index 1c424bb..823386f 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -914,7 +914,9 @@ static void hisi_sas_dev_gone(struct domain_device *device)
 
 		hisi_sas_dereg_device(hisi_hba, device);
 
+		down(&hisi_hba->sem);
 		hisi_hba->hw->clear_itct(hisi_hba, sas_dev);
+		up(&hisi_hba->sem);
 		device->lldd_dev = NULL;
 	}
 
@@ -1364,6 +1366,7 @@ static int hisi_sas_controller_reset(struct hisi_hba *hisi_hba)
 	if (test_and_set_bit(HISI_SAS_RESET_BIT, &hisi_hba->flags))
 		return -1;
 
+	down(&hisi_hba->sem);
 	dev_info(dev, "controller resetting...\n");
 	old_state = hisi_hba->hw->get_phys_state(hisi_hba);
 
@@ -1378,6 +1381,7 @@ static int hisi_sas_controller_reset(struct hisi_hba *hisi_hba)
 	if (rc) {
 		dev_warn(dev, "controller reset failed (%d)\n", rc);
 		clear_bit(HISI_SAS_REJECT_CMD_BIT, &hisi_hba->flags);
+		up(&hisi_hba->sem);
 		scsi_unblock_requests(shost);
 		goto out;
 	}
@@ -1388,6 +1392,7 @@ static int hisi_sas_controller_reset(struct hisi_hba *hisi_hba)
 	hisi_hba->hw->phys_init(hisi_hba);
 	msleep(1000);
 	hisi_sas_refresh_port_id(hisi_hba);
+	up(&hisi_hba->sem);
 
 	if (hisi_hba->reject_stp_links_msk)
 		hisi_sas_terminate_stp_reject(hisi_hba);
@@ -2016,6 +2021,7 @@ int hisi_sas_alloc(struct hisi_hba *hisi_hba, struct Scsi_Host *shost)
 	struct device *dev = hisi_hba->dev;
 	int i, s, max_command_entries = hisi_hba->hw->max_command_entries;
 
+	sema_init(&hisi_hba->sem, 1);
 	spin_lock_init(&hisi_hba->lock);
 	for (i = 0; i < hisi_hba->n_phy; i++) {
 		hisi_sas_phy_init(hisi_hba, i);
-- 
1.9.1

[PATCH 4/9] scsi: hisi_sas: Adjust task reject period during host reset

[John Garry]

From: Xiaofei Tan <tanxiaofei@huawei.com>

After soft_reset() for host reset, we should not be allowed to send
commands to the HW before the PHYs have come up and the port ids have been
refreshed.

Prior to this point, any commands cannot be successfully completed.

This exclusion is achieved by grabbing the host reset semaphore.

Signed-off-by: Xiaofei Tan <tanxiaofei@huawei.com>
Signed-off-by: John Garry <john.garry@huawei.com>
---
 drivers/scsi/hisi_sas/hisi_sas_main.c  | 21 ++++++++++++---------
 drivers/scsi/hisi_sas/hisi_sas_v3_hw.c |  4 +++-
 2 files changed, 15 insertions(+), 10 deletions(-)

diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index 823386f..090d3e0 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -536,8 +536,13 @@ static int hisi_sas_task_exec(struct sas_task *task, gfp_t gfp_flags,
 	struct device *dev = hisi_hba->dev;
 	struct hisi_sas_dq *dq = NULL;
 
-	if (unlikely(test_bit(HISI_SAS_REJECT_CMD_BIT, &hisi_hba->flags)))
-		return -EINVAL;
+	if (unlikely(test_bit(HISI_SAS_REJECT_CMD_BIT, &hisi_hba->flags))) {
+		if (in_softirq())
+			return -EINVAL;
+
+		down(&hisi_hba->sem);
+		up(&hisi_hba->sem);
+	}
 
 	/* protect task_prep and start_delivery sequence */
 	rc = hisi_sas_task_prep(task, &dq, is_tmf, tmf, &pass);
@@ -1383,30 +1388,28 @@ static int hisi_sas_controller_reset(struct hisi_hba *hisi_hba)
 		clear_bit(HISI_SAS_REJECT_CMD_BIT, &hisi_hba->flags);
 		up(&hisi_hba->sem);
 		scsi_unblock_requests(shost);
-		goto out;
+		clear_bit(HISI_SAS_RESET_BIT, &hisi_hba->flags);
+		return rc;
 	}
 
-	clear_bit(HISI_SAS_REJECT_CMD_BIT, &hisi_hba->flags);
-
 	/* Init and wait for PHYs to come up and all libsas event finished. */
 	hisi_hba->hw->phys_init(hisi_hba);
 	msleep(1000);
 	hisi_sas_refresh_port_id(hisi_hba);
+	clear_bit(HISI_SAS_REJECT_CMD_BIT, &hisi_hba->flags);
 	up(&hisi_hba->sem);
 
 	if (hisi_hba->reject_stp_links_msk)
 		hisi_sas_terminate_stp_reject(hisi_hba);
 	hisi_sas_reset_init_all_devices(hisi_hba);
 	scsi_unblock_requests(shost);
+	clear_bit(HISI_SAS_RESET_BIT, &hisi_hba->flags);
 
 	state = hisi_hba->hw->get_phys_state(hisi_hba);
 	hisi_sas_rescan_topology(hisi_hba, old_state, state);
 	dev_info(dev, "controller reset complete\n");
 
-out:
-	clear_bit(HISI_SAS_RESET_BIT, &hisi_hba->flags);
-
-	return rc;
+	return 0;
 }
 
 static int hisi_sas_abort_task(struct sas_task *task)
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
index 0a126a82..c40fdb8 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
@@ -2459,7 +2459,9 @@ static int hisi_sas_v3_suspend(struct pci_dev *pdev, pm_message_t state)
 		return -ENODEV;
 	}
 
-	set_bit(HISI_SAS_RESET_BIT, &hisi_hba->flags);
+	if (test_and_set_bit(HISI_SAS_RESET_BIT, &hisi_hba->flags))
+		return -1;
+
 	scsi_block_requests(shost);
 	set_bit(HISI_SAS_REJECT_CMD_BIT, &hisi_hba->flags);
 	flush_workqueue(hisi_hba->wq);
-- 
1.9.1

[PATCH 4/9] scsi: hisi_sas: Adjust task reject period during host reset

[John Garry]

From: Xiaofei Tan <tanxiaofei@huawei.com>

After soft_reset() for host reset, we should not be allowed to send
commands to the HW before the PHYs have come up and the port ids have been
refreshed.

Prior to this point, any commands cannot be successfully completed.

This exclusion is achieved by grabbing the host reset semaphore.

Signed-off-by: Xiaofei Tan <tanxiaofei@huawei.com>
Signed-off-by: John Garry <john.garry@huawei.com>
---
 drivers/scsi/hisi_sas/hisi_sas_main.c  | 21 ++++++++++++---------
 drivers/scsi/hisi_sas/hisi_sas_v3_hw.c |  4 +++-
 2 files changed, 15 insertions(+), 10 deletions(-)

diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index 823386f..090d3e0 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -536,8 +536,13 @@ static int hisi_sas_task_exec(struct sas_task *task, gfp_t gfp_flags,
 	struct device *dev = hisi_hba->dev;
 	struct hisi_sas_dq *dq = NULL;
 
-	if (unlikely(test_bit(HISI_SAS_REJECT_CMD_BIT, &hisi_hba->flags)))
-		return -EINVAL;
+	if (unlikely(test_bit(HISI_SAS_REJECT_CMD_BIT, &hisi_hba->flags))) {
+		if (in_softirq())
+			return -EINVAL;
+
+		down(&hisi_hba->sem);
+		up(&hisi_hba->sem);
+	}
 
 	/* protect task_prep and start_delivery sequence */
 	rc = hisi_sas_task_prep(task, &dq, is_tmf, tmf, &pass);
@@ -1383,30 +1388,28 @@ static int hisi_sas_controller_reset(struct hisi_hba *hisi_hba)
 		clear_bit(HISI_SAS_REJECT_CMD_BIT, &hisi_hba->flags);
 		up(&hisi_hba->sem);
 		scsi_unblock_requests(shost);
-		goto out;
+		clear_bit(HISI_SAS_RESET_BIT, &hisi_hba->flags);
+		return rc;
 	}
 
-	clear_bit(HISI_SAS_REJECT_CMD_BIT, &hisi_hba->flags);
-
 	/* Init and wait for PHYs to come up and all libsas event finished. */
 	hisi_hba->hw->phys_init(hisi_hba);
 	msleep(1000);
 	hisi_sas_refresh_port_id(hisi_hba);
+	clear_bit(HISI_SAS_REJECT_CMD_BIT, &hisi_hba->flags);
 	up(&hisi_hba->sem);
 
 	if (hisi_hba->reject_stp_links_msk)
 		hisi_sas_terminate_stp_reject(hisi_hba);
 	hisi_sas_reset_init_all_devices(hisi_hba);
 	scsi_unblock_requests(shost);
+	clear_bit(HISI_SAS_RESET_BIT, &hisi_hba->flags);
 
 	state = hisi_hba->hw->get_phys_state(hisi_hba);
 	hisi_sas_rescan_topology(hisi_hba, old_state, state);
 	dev_info(dev, "controller reset complete\n");
 
-out:
-	clear_bit(HISI_SAS_RESET_BIT, &hisi_hba->flags);
-
-	return rc;
+	return 0;
 }
 
 static int hisi_sas_abort_task(struct sas_task *task)
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
index 0a126a82..c40fdb8 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
@@ -2459,7 +2459,9 @@ static int hisi_sas_v3_suspend(struct pci_dev *pdev, pm_message_t state)
 		return -ENODEV;
 	}
 
-	set_bit(HISI_SAS_RESET_BIT, &hisi_hba->flags);
+	if (test_and_set_bit(HISI_SAS_RESET_BIT, &hisi_hba->flags))
+		return -1;
+
 	scsi_block_requests(shost);
 	set_bit(HISI_SAS_REJECT_CMD_BIT, &hisi_hba->flags);
 	flush_workqueue(hisi_hba->wq);
-- 
1.9.1

[PATCH 5/9] scsi: hisi_sas: Add a flag to filter PHY events during reset

[John Garry]

From: Xiaofei Tan <tanxiaofei@huawei.com>

During reset, we don't want PHY events reported to libsas for PHYs which
were previously attached prior to reset.

So check hisi_hba->flags for HISI_SAS_RESET_BIT to filter PHY events
during reset.

Signed-off-by: Xiaofei Tan <tanxiaofei@huawei.com>
Signed-off-by: John Garry <john.garry@huawei.com>
---
 drivers/scsi/hisi_sas/hisi_sas_main.c  | 3 ++-
 drivers/scsi/hisi_sas/hisi_sas_v1_hw.c | 3 ++-
 drivers/scsi/hisi_sas/hisi_sas_v2_hw.c | 3 ++-
 drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 3 ++-
 4 files changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index 090d3e0..006e776 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -1927,7 +1927,8 @@ void hisi_sas_phy_down(struct hisi_hba *hisi_hba, int phy_no, int rdy)
 	} else {
 		struct hisi_sas_port *port  = phy->port;
 
-		if (phy->in_reset) {
+		if (test_bit(HISI_SAS_RESET_BIT, &hisi_hba->flags) ||
+		    phy->in_reset) {
 			dev_info(dev, "ignore flutter phy%d down\n", phy_no);
 			return;
 		}
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c
index 89ab18c..3277442 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c
@@ -1469,7 +1469,8 @@ static irqreturn_t int_bcast_v1_hw(int irq, void *p)
 		goto end;
 	}
 
-	sha->notify_port_event(sas_phy, PORTE_BROADCAST_RCVD);
+	if (!test_bit(HISI_SAS_RESET_BIT, &hisi_hba->flags))
+		sha->notify_port_event(sas_phy, PORTE_BROADCAST_RCVD);
 
 end:
 	hisi_sas_phy_write32(hisi_hba, phy_no, CHL_INT2,
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
index 213c530..159576e 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
@@ -2840,7 +2840,8 @@ static void phy_bcast_v2_hw(int phy_no, struct hisi_hba *hisi_hba)
 
 	hisi_sas_phy_write32(hisi_hba, phy_no, SL_RX_BCAST_CHK_MSK, 1);
 	bcast_status = hisi_sas_phy_read32(hisi_hba, phy_no, RX_PRIMS_STATUS);
-	if (bcast_status & RX_BCAST_CHG_MSK)
+	if ((bcast_status & RX_BCAST_CHG_MSK) &&
+	    !test_bit(HISI_SAS_RESET_BIT, &hisi_hba->flags))
 		sas_ha->notify_port_event(sas_phy, PORTE_BROADCAST_RCVD);
 	hisi_sas_phy_write32(hisi_hba, phy_no, CHL_INT0,
 			     CHL_INT0_SL_RX_BCST_ACK_MSK);
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
index c40fdb8..e43881d 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
@@ -1263,7 +1263,8 @@ static irqreturn_t phy_bcast_v3_hw(int phy_no, struct hisi_hba *hisi_hba)
 
 	hisi_sas_phy_write32(hisi_hba, phy_no, SL_RX_BCAST_CHK_MSK, 1);
 	bcast_status = hisi_sas_phy_read32(hisi_hba, phy_no, RX_PRIMS_STATUS);
-	if (bcast_status & RX_BCAST_CHG_MSK)
+	if ((bcast_status & RX_BCAST_CHG_MSK) &&
+	    !test_bit(HISI_SAS_RESET_BIT, &hisi_hba->flags))
 		sas_ha->notify_port_event(sas_phy, PORTE_BROADCAST_RCVD);
 	hisi_sas_phy_write32(hisi_hba, phy_no, CHL_INT0,
 			     CHL_INT0_SL_RX_BCST_ACK_MSK);
-- 
1.9.1

[PATCH 5/9] scsi: hisi_sas: Add a flag to filter PHY events during reset

[John Garry]

From: Xiaofei Tan <tanxiaofei@huawei.com>

During reset, we don't want PHY events reported to libsas for PHYs which
were previously attached prior to reset.

So check hisi_hba->flags for HISI_SAS_RESET_BIT to filter PHY events
during reset.

Signed-off-by: Xiaofei Tan <tanxiaofei@huawei.com>
Signed-off-by: John Garry <john.garry@huawei.com>
---
 drivers/scsi/hisi_sas/hisi_sas_main.c  | 3 ++-
 drivers/scsi/hisi_sas/hisi_sas_v1_hw.c | 3 ++-
 drivers/scsi/hisi_sas/hisi_sas_v2_hw.c | 3 ++-
 drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 3 ++-
 4 files changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index 090d3e0..006e776 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -1927,7 +1927,8 @@ void hisi_sas_phy_down(struct hisi_hba *hisi_hba, int phy_no, int rdy)
 	} else {
 		struct hisi_sas_port *port  = phy->port;
 
-		if (phy->in_reset) {
+		if (test_bit(HISI_SAS_RESET_BIT, &hisi_hba->flags) ||
+		    phy->in_reset) {
 			dev_info(dev, "ignore flutter phy%d down\n", phy_no);
 			return;
 		}
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c
index 89ab18c..3277442 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c
@@ -1469,7 +1469,8 @@ static irqreturn_t int_bcast_v1_hw(int irq, void *p)
 		goto end;
 	}
 
-	sha->notify_port_event(sas_phy, PORTE_BROADCAST_RCVD);
+	if (!test_bit(HISI_SAS_RESET_BIT, &hisi_hba->flags))
+		sha->notify_port_event(sas_phy, PORTE_BROADCAST_RCVD);
 
 end:
 	hisi_sas_phy_write32(hisi_hba, phy_no, CHL_INT2,
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
index 213c530..159576e 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
@@ -2840,7 +2840,8 @@ static void phy_bcast_v2_hw(int phy_no, struct hisi_hba *hisi_hba)
 
 	hisi_sas_phy_write32(hisi_hba, phy_no, SL_RX_BCAST_CHK_MSK, 1);
 	bcast_status = hisi_sas_phy_read32(hisi_hba, phy_no, RX_PRIMS_STATUS);
-	if (bcast_status & RX_BCAST_CHG_MSK)
+	if ((bcast_status & RX_BCAST_CHG_MSK) &&
+	    !test_bit(HISI_SAS_RESET_BIT, &hisi_hba->flags))
 		sas_ha->notify_port_event(sas_phy, PORTE_BROADCAST_RCVD);
 	hisi_sas_phy_write32(hisi_hba, phy_no, CHL_INT0,
 			     CHL_INT0_SL_RX_BCST_ACK_MSK);
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
index c40fdb8..e43881d 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
@@ -1263,7 +1263,8 @@ static irqreturn_t phy_bcast_v3_hw(int phy_no, struct hisi_hba *hisi_hba)
 
 	hisi_sas_phy_write32(hisi_hba, phy_no, SL_RX_BCAST_CHK_MSK, 1);
 	bcast_status = hisi_sas_phy_read32(hisi_hba, phy_no, RX_PRIMS_STATUS);
-	if (bcast_status & RX_BCAST_CHG_MSK)
+	if ((bcast_status & RX_BCAST_CHG_MSK) &&
+	    !test_bit(HISI_SAS_RESET_BIT, &hisi_hba->flags))
 		sas_ha->notify_port_event(sas_phy, PORTE_BROADCAST_RCVD);
 	hisi_sas_phy_write32(hisi_hba, phy_no, CHL_INT0,
 			     CHL_INT0_SL_RX_BCST_ACK_MSK);
-- 
1.9.1

[PATCH 6/9] scsi: hisi_sas: Release all remaining resources in clear nexus ha

[John Garry]

From: Xiaofei Tan <tanxiaofei@huawei.com>

In host reset, we use TMF or soft-reset to re-init device, and if success,
we will release all LLDD resources of this device. If the init fails -
maybe because the device was removed or link has not come up - then do not
release the LLDD resources, but rather rely on SCSI EH to handle the
timeout for these resources later on.

But if clear nexus ha calls host reset, which is the last effort of SCSI
EH, we should release all LLDD remain resources. Because SCSI EH will
release all tasks after clear nexus ha.

Before release, we do I_T nexus reset to try to clear target remain IOs.

Signed-off-by: Xiaofei Tan <tanxiaofei@huawei.com>
Signed-off-by: John Garry <john.garry@huawei.com>
---
 drivers/scsi/hisi_sas/hisi_sas_main.c | 24 +++++++++++++++++++++---
 1 file changed, 21 insertions(+), 3 deletions(-)

diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index 006e776..da1d5fe 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -1652,14 +1652,32 @@ static int hisi_sas_lu_reset(struct domain_device *device, u8 *lun)
 static int hisi_sas_clear_nexus_ha(struct sas_ha_struct *sas_ha)
 {
 	struct hisi_hba *hisi_hba = sas_ha->lldd_ha;
+	struct device *dev = hisi_hba->dev;
 	HISI_SAS_DECLARE_RST_WORK_ON_STACK(r);
+	int rc, i;
 
 	queue_work(hisi_hba->wq, &r.work);
 	wait_for_completion(r.completion);
-	if (r.done)
-		return TMF_RESP_FUNC_COMPLETE;
+	if (!r.done)
+		return TMF_RESP_FUNC_FAILED;
+
+	for (i = 0; i < HISI_SAS_MAX_DEVICES; i++) {
+		struct hisi_sas_device *sas_dev = &hisi_hba->devices[i];
+		struct domain_device *device = sas_dev->sas_device;
+
+		if ((sas_dev->dev_type == SAS_PHY_UNUSED) || !device ||
+		    DEV_IS_EXPANDER(device->dev_type))
+			continue;
+
+		rc = hisi_sas_debug_I_T_nexus_reset(device);
+		if (rc != TMF_RESP_FUNC_COMPLETE)
+			dev_info(dev, "clear nexus ha: for device[%d] rc=%d\n",
+				 sas_dev->device_id, rc);
+	}
+
+	hisi_sas_release_tasks(hisi_hba);
 
-	return TMF_RESP_FUNC_FAILED;
+	return TMF_RESP_FUNC_COMPLETE;
 }
 
 static int hisi_sas_query_task(struct sas_task *task)
-- 
1.9.1

[PATCH 6/9] scsi: hisi_sas: Release all remaining resources in clear nexus ha

[John Garry]

From: Xiaofei Tan <tanxiaofei@huawei.com>

In host reset, we use TMF or soft-reset to re-init device, and if success,
we will release all LLDD resources of this device. If the init fails -
maybe because the device was removed or link has not come up - then do not
release the LLDD resources, but rather rely on SCSI EH to handle the
timeout for these resources later on.

But if clear nexus ha calls host reset, which is the last effort of SCSI
EH, we should release all LLDD remain resources. Because SCSI EH will
release all tasks after clear nexus ha.

Before release, we do I_T nexus reset to try to clear target remain IOs.

Signed-off-by: Xiaofei Tan <tanxiaofei@huawei.com>
Signed-off-by: John Garry <john.garry@huawei.com>
---
 drivers/scsi/hisi_sas/hisi_sas_main.c | 24 +++++++++++++++++++++---
 1 file changed, 21 insertions(+), 3 deletions(-)

diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index 006e776..da1d5fe 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -1652,14 +1652,32 @@ static int hisi_sas_lu_reset(struct domain_device *device, u8 *lun)
 static int hisi_sas_clear_nexus_ha(struct sas_ha_struct *sas_ha)
 {
 	struct hisi_hba *hisi_hba = sas_ha->lldd_ha;
+	struct device *dev = hisi_hba->dev;
 	HISI_SAS_DECLARE_RST_WORK_ON_STACK(r);
+	int rc, i;
 
 	queue_work(hisi_hba->wq, &r.work);
 	wait_for_completion(r.completion);
-	if (r.done)
-		return TMF_RESP_FUNC_COMPLETE;
+	if (!r.done)
+		return TMF_RESP_FUNC_FAILED;
+
+	for (i = 0; i < HISI_SAS_MAX_DEVICES; i++) {
+		struct hisi_sas_device *sas_dev = &hisi_hba->devices[i];
+		struct domain_device *device = sas_dev->sas_device;
+
+		if ((sas_dev->dev_type == SAS_PHY_UNUSED) || !device ||
+		    DEV_IS_EXPANDER(device->dev_type))
+			continue;
+
+		rc = hisi_sas_debug_I_T_nexus_reset(device);
+		if (rc != TMF_RESP_FUNC_COMPLETE)
+			dev_info(dev, "clear nexus ha: for device[%d] rc=%d\n",
+				 sas_dev->device_id, rc);
+	}
+
+	hisi_sas_release_tasks(hisi_hba);
 
-	return TMF_RESP_FUNC_FAILED;
+	return TMF_RESP_FUNC_COMPLETE;
 }
 
 static int hisi_sas_query_task(struct sas_task *task)
-- 
1.9.1

[PATCH 7/9] scsi: hisi_sas: Pre-allocate slot DMA buffers

[John Garry]

From: Xiang Chen <chenxiang66@hisilicon.com>

Currently the driver spends much time allocating and freeing the slot DMA
buffer for command delivery/completion. To boost the performance,
pre-allocate the buffers for all IPTT. The downside of this approach is
that we are reallocating all buffer memory upfront, so hog memory which
we may not need.

However, the current method - DMA buffer pool - also caches all buffers
and does not free them until the pool is destroyed, so is not exactly
efficient either.

On top of this, since the slot DMA buffer is slightly bigger than a 4K
page, we need to allocate 2x4K pages per buffer (for 4K page kernel),
which is quite wasteful. For 64K page size this is not such an issue.

So, for the 4K page case, in order to make memory usage more efficient,
pre-allocating larger blocks of DMA memory for the buffers can be more
efficient.

To make DMA memory usage most efficient, we would choose a single
contiguous DMA memory block, but this could use up all the DMA memory in
the system (when CMA enabled and no IOMMU), or we may just not be able to
allocate a DMA buffer large enough when no CMA or IOMMU.

To decide the block size we use the LCM (least common multiple) of the
buffer size and the page size. We roundup(64) to ensure the LCM is not
too large, even though a little memory may be wasted per block.

So, with this, the total memory requirement is about is about 17MB
for 4096 max IPTT.

Previously (for 4K pages case), it would be 32MB (for all slots
allocated).

With this change, the relative increase of IOPS for bs=4K read when
PAGE_SIZE=4K and PAGE_SIZE=64K is as follows:
    IODEPTH     4K PAGE_SIZE      64K PAGE_SIZE
    32          56%               47%
    64          53%               44%
    128         64%               43%
    256         67%               45%

Signed-off-by: Xiang Chen <chenxiang66@hisilicon.com>
Signed-off-by: John Garry <john.garry@huawei.com>
---
 drivers/scsi/hisi_sas/hisi_sas.h      |  9 ++--
 drivers/scsi/hisi_sas/hisi_sas_main.c | 78 +++++++++++++++++------------------
 2 files changed, 42 insertions(+), 45 deletions(-)

diff --git a/drivers/scsi/hisi_sas/hisi_sas.h b/drivers/scsi/hisi_sas/hisi_sas.h
index 78e5a92..beda412 100644
--- a/drivers/scsi/hisi_sas/hisi_sas.h
+++ b/drivers/scsi/hisi_sas/hisi_sas.h
@@ -16,6 +16,7 @@
 #include <linux/clk.h>
 #include <linux/dmapool.h>
 #include <linux/iopoll.h>
+#include <linux/lcm.h>
 #include <linux/mfd/syscon.h>
 #include <linux/module.h>
 #include <linux/of_address.h>
@@ -199,17 +200,18 @@ struct hisi_sas_slot {
 	int	dlvry_queue_slot;
 	int	cmplt_queue;
 	int	cmplt_queue_slot;
-	int	idx;
 	int	abort;
 	int	ready;
-	void	*buf;
-	dma_addr_t buf_dma;
 	void	*cmd_hdr;
 	dma_addr_t cmd_hdr_dma;
 	struct work_struct abort_slot;
 	struct timer_list internal_abort_timer;
 	bool is_internal;
 	struct hisi_sas_tmf_task *tmf;
+	/* Do not reorder/change members after here */
+	void	*buf;
+	dma_addr_t buf_dma;
+	int	idx;
 };
 
 struct hisi_sas_hw {
@@ -299,7 +301,6 @@ struct hisi_hba {
 
 	int	queue_count;
 
-	struct dma_pool *buffer_pool;
 	struct hisi_sas_device	devices[HISI_SAS_MAX_DEVICES];
 	struct hisi_sas_cmd_hdr	*cmd_hdr[HISI_SAS_MAX_QUEUES];
 	dma_addr_t cmd_hdr_dma[HISI_SAS_MAX_QUEUES];
diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index da1d5fe..20aab10 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -242,20 +242,16 @@ void hisi_sas_slot_task_free(struct hisi_hba *hisi_hba, struct sas_task *task,
 					     task->data_dir);
 	}
 
-	if (slot->buf)
-		dma_pool_free(hisi_hba->buffer_pool, slot->buf, slot->buf_dma);
 
 	spin_lock_irqsave(&dq->lock, flags);
 	list_del_init(&slot->entry);
 	spin_unlock_irqrestore(&dq->lock, flags);
-	slot->buf = NULL;
-	slot->task = NULL;
-	slot->port = NULL;
+
+	memset(slot, 0, offsetof(struct hisi_sas_slot, buf));
+
 	spin_lock_irqsave(&hisi_hba->lock, flags);
 	hisi_sas_slot_index_free(hisi_hba, slot->idx);
 	spin_unlock_irqrestore(&hisi_hba->lock, flags);
-
-	/* slot memory is fully zeroed when it is reused */
 }
 EXPORT_SYMBOL_GPL(hisi_sas_slot_task_free);
 
@@ -430,21 +426,13 @@ static int hisi_sas_task_prep(struct sas_task *task,
 		goto err_out_dma_unmap;
 
 	slot = &hisi_hba->slot_info[slot_idx];
-	memset(slot, 0, sizeof(struct hisi_sas_slot));
-
-	slot->buf = dma_pool_alloc(hisi_hba->buffer_pool,
-				   GFP_ATOMIC, &slot->buf_dma);
-	if (!slot->buf) {
-		rc = -ENOMEM;
-		goto err_out_tag;
-	}
 
 	spin_lock_irqsave(&dq->lock, flags_dq);
 	wr_q_index = hisi_hba->hw->get_free_slot(hisi_hba, dq);
 	if (wr_q_index < 0) {
 		spin_unlock_irqrestore(&dq->lock, flags_dq);
 		rc = -EAGAIN;
-		goto err_out_buf;
+		goto err_out_tag;
 	}
 
 	list_add_tail(&slot->delivery, &dq->list);
@@ -453,7 +441,6 @@ static int hisi_sas_task_prep(struct sas_task *task,
 	dlvry_queue = dq->id;
 	dlvry_queue_slot = wr_q_index;
 
-	slot->idx = slot_idx;
 	slot->n_elem = n_elem;
 	slot->dlvry_queue = dlvry_queue;
 	slot->dlvry_queue_slot = dlvry_queue_slot;
@@ -500,9 +487,6 @@ static int hisi_sas_task_prep(struct sas_task *task,
 
 	return 0;
 
-err_out_buf:
-	dma_pool_free(hisi_hba->buffer_pool, slot->buf,
-		      slot->buf_dma);
 err_out_tag:
 	spin_lock_irqsave(&hisi_hba->lock, flags);
 	hisi_sas_slot_index_free(hisi_hba, slot_idx);
@@ -1749,21 +1733,13 @@ static int hisi_sas_query_task(struct sas_task *task)
 	spin_unlock_irqrestore(&hisi_hba->lock, flags);
 
 	slot = &hisi_hba->slot_info[slot_idx];
-	memset(slot, 0, sizeof(struct hisi_sas_slot));
-
-	slot->buf = dma_pool_alloc(hisi_hba->buffer_pool,
-			GFP_ATOMIC, &slot->buf_dma);
-	if (!slot->buf) {
-		rc = -ENOMEM;
-		goto err_out_tag;
-	}
 
 	spin_lock_irqsave(&dq->lock, flags_dq);
 	wr_q_index = hisi_hba->hw->get_free_slot(hisi_hba, dq);
 	if (wr_q_index < 0) {
 		spin_unlock_irqrestore(&dq->lock, flags_dq);
 		rc = -EAGAIN;
-		goto err_out_buf;
+		goto err_out_tag;
 	}
 	list_add_tail(&slot->delivery, &dq->list);
 	spin_unlock_irqrestore(&dq->lock, flags_dq);
@@ -1771,7 +1747,6 @@ static int hisi_sas_query_task(struct sas_task *task)
 	dlvry_queue = dq->id;
 	dlvry_queue_slot = wr_q_index;
 
-	slot->idx = slot_idx;
 	slot->n_elem = n_elem;
 	slot->dlvry_queue = dlvry_queue;
 	slot->dlvry_queue_slot = dlvry_queue_slot;
@@ -1802,9 +1777,6 @@ static int hisi_sas_query_task(struct sas_task *task)
 
 	return 0;
 
-err_out_buf:
-	dma_pool_free(hisi_hba->buffer_pool, slot->buf,
-		      slot->buf_dma);
 err_out_tag:
 	spin_lock_irqsave(&hisi_hba->lock, flags);
 	hisi_sas_slot_index_free(hisi_hba, slot_idx);
@@ -2041,7 +2013,9 @@ void hisi_sas_init_mem(struct hisi_hba *hisi_hba)
 int hisi_sas_alloc(struct hisi_hba *hisi_hba, struct Scsi_Host *shost)
 {
 	struct device *dev = hisi_hba->dev;
-	int i, s, max_command_entries = hisi_hba->hw->max_command_entries;
+	int i, j, s, max_command_entries = hisi_hba->hw->max_command_entries;
+	int max_command_entries_ru, sz_slot_buf_ru;
+	int blk_cnt, slots_per_blk;
 
 	sema_init(&hisi_hba->sem, 1);
 	spin_lock_init(&hisi_hba->lock);
@@ -2088,11 +2062,6 @@ int hisi_sas_alloc(struct hisi_hba *hisi_hba, struct Scsi_Host *shost)
 			goto err_out;
 	}
 
-	s = sizeof(struct hisi_sas_slot_buf_table);
-	hisi_hba->buffer_pool = dma_pool_create("dma_buffer", dev, s, 16, 0);
-	if (!hisi_hba->buffer_pool)
-		goto err_out;
-
 	s = HISI_SAS_MAX_ITCT_ENTRIES * sizeof(struct hisi_sas_itct);
 	hisi_hba->itct = dmam_alloc_coherent(dev, s, &hisi_hba->itct_dma,
 					     GFP_KERNEL);
@@ -2106,6 +2075,35 @@ int hisi_sas_alloc(struct hisi_hba *hisi_hba, struct Scsi_Host *shost)
 	if (!hisi_hba->slot_info)
 		goto err_out;
 
+	/* roundup to avoid overly large block size */
+	max_command_entries_ru = roundup(max_command_entries, 64);
+	sz_slot_buf_ru = roundup(sizeof(struct hisi_sas_slot_buf_table), 64);
+	s = lcm(max_command_entries_ru, sz_slot_buf_ru);
+	blk_cnt = (max_command_entries_ru * sz_slot_buf_ru) / s;
+	slots_per_blk = s / sz_slot_buf_ru;
+	for (i = 0; i < blk_cnt; i++) {
+		struct hisi_sas_slot_buf_table *buf;
+		dma_addr_t buf_dma;
+		int slot_index = i * slots_per_blk;
+
+		buf = dmam_alloc_coherent(dev, s, &buf_dma, GFP_KERNEL);
+		if (!buf)
+			goto err_out;
+		memset(buf, 0, s);
+
+		for (j = 0; j < slots_per_blk; j++, slot_index++) {
+			struct hisi_sas_slot *slot;
+
+			slot = &hisi_hba->slot_info[slot_index];
+			slot->buf = buf;
+			slot->buf_dma = buf_dma;
+			slot->idx = slot_index;
+
+			buf++;
+			buf_dma += sizeof(*buf);
+		}
+	}
+
 	s = max_command_entries * sizeof(struct hisi_sas_iost);
 	hisi_hba->iost = dmam_alloc_coherent(dev, s, &hisi_hba->iost_dma,
 					     GFP_KERNEL);
@@ -2156,8 +2154,6 @@ int hisi_sas_alloc(struct hisi_hba *hisi_hba, struct Scsi_Host *shost)
 
 void hisi_sas_free(struct hisi_hba *hisi_hba)
 {
-	dma_pool_destroy(hisi_hba->buffer_pool);
-
 	if (hisi_hba->wq)
 		destroy_workqueue(hisi_hba->wq);
 }
-- 
1.9.1

[PATCH 7/9] scsi: hisi_sas: Pre-allocate slot DMA buffers

[John Garry]

From: Xiang Chen <chenxiang66@hisilicon.com>

Currently the driver spends much time allocating and freeing the slot DMA
buffer for command delivery/completion. To boost the performance,
pre-allocate the buffers for all IPTT. The downside of this approach is
that we are reallocating all buffer memory upfront, so hog memory which
we may not need.

However, the current method - DMA buffer pool - also caches all buffers
and does not free them until the pool is destroyed, so is not exactly
efficient either.

On top of this, since the slot DMA buffer is slightly bigger than a 4K
page, we need to allocate 2x4K pages per buffer (for 4K page kernel),
which is quite wasteful. For 64K page size this is not such an issue.

So, for the 4K page case, in order to make memory usage more efficient,
pre-allocating larger blocks of DMA memory for the buffers can be more
efficient.

To make DMA memory usage most efficient, we would choose a single
contiguous DMA memory block, but this could use up all the DMA memory in
the system (when CMA enabled and no IOMMU), or we may just not be able to
allocate a DMA buffer large enough when no CMA or IOMMU.

To decide the block size we use the LCM (least common multiple) of the
buffer size and the page size. We roundup(64) to ensure the LCM is not
too large, even though a little memory may be wasted per block.

So, with this, the total memory requirement is about is about 17MB
for 4096 max IPTT.

Previously (for 4K pages case), it would be 32MB (for all slots
allocated).

With this change, the relative increase of IOPS for bs=4K read when
PAGE_SIZE=4K and PAGE_SIZE=64K is as follows:
    IODEPTH     4K PAGE_SIZE      64K PAGE_SIZE
    32          56%               47%
    64          53%               44%
    128         64%               43%
    256         67%               45%

Signed-off-by: Xiang Chen <chenxiang66@hisilicon.com>
Signed-off-by: John Garry <john.garry@huawei.com>
---
 drivers/scsi/hisi_sas/hisi_sas.h      |  9 ++--
 drivers/scsi/hisi_sas/hisi_sas_main.c | 78 +++++++++++++++++------------------
 2 files changed, 42 insertions(+), 45 deletions(-)

diff --git a/drivers/scsi/hisi_sas/hisi_sas.h b/drivers/scsi/hisi_sas/hisi_sas.h
index 78e5a92..beda412 100644
--- a/drivers/scsi/hisi_sas/hisi_sas.h
+++ b/drivers/scsi/hisi_sas/hisi_sas.h
@@ -16,6 +16,7 @@
 #include <linux/clk.h>
 #include <linux/dmapool.h>
 #include <linux/iopoll.h>
+#include <linux/lcm.h>
 #include <linux/mfd/syscon.h>
 #include <linux/module.h>
 #include <linux/of_address.h>
@@ -199,17 +200,18 @@ struct hisi_sas_slot {
 	int	dlvry_queue_slot;
 	int	cmplt_queue;
 	int	cmplt_queue_slot;
-	int	idx;
 	int	abort;
 	int	ready;
-	void	*buf;
-	dma_addr_t buf_dma;
 	void	*cmd_hdr;
 	dma_addr_t cmd_hdr_dma;
 	struct work_struct abort_slot;
 	struct timer_list internal_abort_timer;
 	bool is_internal;
 	struct hisi_sas_tmf_task *tmf;
+	/* Do not reorder/change members after here */
+	void	*buf;
+	dma_addr_t buf_dma;
+	int	idx;
 };
 
 struct hisi_sas_hw {
@@ -299,7 +301,6 @@ struct hisi_hba {
 
 	int	queue_count;
 
-	struct dma_pool *buffer_pool;
 	struct hisi_sas_device	devices[HISI_SAS_MAX_DEVICES];
 	struct hisi_sas_cmd_hdr	*cmd_hdr[HISI_SAS_MAX_QUEUES];
 	dma_addr_t cmd_hdr_dma[HISI_SAS_MAX_QUEUES];
diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index da1d5fe..20aab10 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -242,20 +242,16 @@ void hisi_sas_slot_task_free(struct hisi_hba *hisi_hba, struct sas_task *task,
 					     task->data_dir);
 	}
 
-	if (slot->buf)
-		dma_pool_free(hisi_hba->buffer_pool, slot->buf, slot->buf_dma);
 
 	spin_lock_irqsave(&dq->lock, flags);
 	list_del_init(&slot->entry);
 	spin_unlock_irqrestore(&dq->lock, flags);
-	slot->buf = NULL;
-	slot->task = NULL;
-	slot->port = NULL;
+
+	memset(slot, 0, offsetof(struct hisi_sas_slot, buf));
+
 	spin_lock_irqsave(&hisi_hba->lock, flags);
 	hisi_sas_slot_index_free(hisi_hba, slot->idx);
 	spin_unlock_irqrestore(&hisi_hba->lock, flags);
-
-	/* slot memory is fully zeroed when it is reused */
 }
 EXPORT_SYMBOL_GPL(hisi_sas_slot_task_free);
 
@@ -430,21 +426,13 @@ static int hisi_sas_task_prep(struct sas_task *task,
 		goto err_out_dma_unmap;
 
 	slot = &hisi_hba->slot_info[slot_idx];
-	memset(slot, 0, sizeof(struct hisi_sas_slot));
-
-	slot->buf = dma_pool_alloc(hisi_hba->buffer_pool,
-				   GFP_ATOMIC, &slot->buf_dma);
-	if (!slot->buf) {
-		rc = -ENOMEM;
-		goto err_out_tag;
-	}
 
 	spin_lock_irqsave(&dq->lock, flags_dq);
 	wr_q_index = hisi_hba->hw->get_free_slot(hisi_hba, dq);
 	if (wr_q_index < 0) {
 		spin_unlock_irqrestore(&dq->lock, flags_dq);
 		rc = -EAGAIN;
-		goto err_out_buf;
+		goto err_out_tag;
 	}
 
 	list_add_tail(&slot->delivery, &dq->list);
@@ -453,7 +441,6 @@ static int hisi_sas_task_prep(struct sas_task *task,
 	dlvry_queue = dq->id;
 	dlvry_queue_slot = wr_q_index;
 
-	slot->idx = slot_idx;
 	slot->n_elem = n_elem;
 	slot->dlvry_queue = dlvry_queue;
 	slot->dlvry_queue_slot = dlvry_queue_slot;
@@ -500,9 +487,6 @@ static int hisi_sas_task_prep(struct sas_task *task,
 
 	return 0;
 
-err_out_buf:
-	dma_pool_free(hisi_hba->buffer_pool, slot->buf,
-		      slot->buf_dma);
 err_out_tag:
 	spin_lock_irqsave(&hisi_hba->lock, flags);
 	hisi_sas_slot_index_free(hisi_hba, slot_idx);
@@ -1749,21 +1733,13 @@ static int hisi_sas_query_task(struct sas_task *task)
 	spin_unlock_irqrestore(&hisi_hba->lock, flags);
 
 	slot = &hisi_hba->slot_info[slot_idx];
-	memset(slot, 0, sizeof(struct hisi_sas_slot));
-
-	slot->buf = dma_pool_alloc(hisi_hba->buffer_pool,
-			GFP_ATOMIC, &slot->buf_dma);
-	if (!slot->buf) {
-		rc = -ENOMEM;
-		goto err_out_tag;
-	}
 
 	spin_lock_irqsave(&dq->lock, flags_dq);
 	wr_q_index = hisi_hba->hw->get_free_slot(hisi_hba, dq);
 	if (wr_q_index < 0) {
 		spin_unlock_irqrestore(&dq->lock, flags_dq);
 		rc = -EAGAIN;
-		goto err_out_buf;
+		goto err_out_tag;
 	}
 	list_add_tail(&slot->delivery, &dq->list);
 	spin_unlock_irqrestore(&dq->lock, flags_dq);
@@ -1771,7 +1747,6 @@ static int hisi_sas_query_task(struct sas_task *task)
 	dlvry_queue = dq->id;
 	dlvry_queue_slot = wr_q_index;
 
-	slot->idx = slot_idx;
 	slot->n_elem = n_elem;
 	slot->dlvry_queue = dlvry_queue;
 	slot->dlvry_queue_slot = dlvry_queue_slot;
@@ -1802,9 +1777,6 @@ static int hisi_sas_query_task(struct sas_task *task)
 
 	return 0;
 
-err_out_buf:
-	dma_pool_free(hisi_hba->buffer_pool, slot->buf,
-		      slot->buf_dma);
 err_out_tag:
 	spin_lock_irqsave(&hisi_hba->lock, flags);
 	hisi_sas_slot_index_free(hisi_hba, slot_idx);
@@ -2041,7 +2013,9 @@ void hisi_sas_init_mem(struct hisi_hba *hisi_hba)
 int hisi_sas_alloc(struct hisi_hba *hisi_hba, struct Scsi_Host *shost)
 {
 	struct device *dev = hisi_hba->dev;
-	int i, s, max_command_entries = hisi_hba->hw->max_command_entries;
+	int i, j, s, max_command_entries = hisi_hba->hw->max_command_entries;
+	int max_command_entries_ru, sz_slot_buf_ru;
+	int blk_cnt, slots_per_blk;
 
 	sema_init(&hisi_hba->sem, 1);
 	spin_lock_init(&hisi_hba->lock);
@@ -2088,11 +2062,6 @@ int hisi_sas_alloc(struct hisi_hba *hisi_hba, struct Scsi_Host *shost)
 			goto err_out;
 	}
 
-	s = sizeof(struct hisi_sas_slot_buf_table);
-	hisi_hba->buffer_pool = dma_pool_create("dma_buffer", dev, s, 16, 0);
-	if (!hisi_hba->buffer_pool)
-		goto err_out;
-
 	s = HISI_SAS_MAX_ITCT_ENTRIES * sizeof(struct hisi_sas_itct);
 	hisi_hba->itct = dmam_alloc_coherent(dev, s, &hisi_hba->itct_dma,
 					     GFP_KERNEL);
@@ -2106,6 +2075,35 @@ int hisi_sas_alloc(struct hisi_hba *hisi_hba, struct Scsi_Host *shost)
 	if (!hisi_hba->slot_info)
 		goto err_out;
 
+	/* roundup to avoid overly large block size */
+	max_command_entries_ru = roundup(max_command_entries, 64);
+	sz_slot_buf_ru = roundup(sizeof(struct hisi_sas_slot_buf_table), 64);
+	s = lcm(max_command_entries_ru, sz_slot_buf_ru);
+	blk_cnt = (max_command_entries_ru * sz_slot_buf_ru) / s;
+	slots_per_blk = s / sz_slot_buf_ru;
+	for (i = 0; i < blk_cnt; i++) {
+		struct hisi_sas_slot_buf_table *buf;
+		dma_addr_t buf_dma;
+		int slot_index = i * slots_per_blk;
+
+		buf = dmam_alloc_coherent(dev, s, &buf_dma, GFP_KERNEL);
+		if (!buf)
+			goto err_out;
+		memset(buf, 0, s);
+
+		for (j = 0; j < slots_per_blk; j++, slot_index++) {
+			struct hisi_sas_slot *slot;
+
+			slot = &hisi_hba->slot_info[slot_index];
+			slot->buf = buf;
+			slot->buf_dma = buf_dma;
+			slot->idx = slot_index;
+
+			buf++;
+			buf_dma += sizeof(*buf);
+		}
+	}
+
 	s = max_command_entries * sizeof(struct hisi_sas_iost);
 	hisi_hba->iost = dmam_alloc_coherent(dev, s, &hisi_hba->iost_dma,
 					     GFP_KERNEL);
@@ -2156,8 +2154,6 @@ int hisi_sas_alloc(struct hisi_hba *hisi_hba, struct Scsi_Host *shost)
 
 void hisi_sas_free(struct hisi_hba *hisi_hba)
 {
-	dma_pool_destroy(hisi_hba->buffer_pool);
-
 	if (hisi_hba->wq)
 		destroy_workqueue(hisi_hba->wq);
 }
-- 
1.9.1

[PATCH 8/9] scsi: hisi_sas: Add missing PHY spinlock init

[John Garry]

The init is missed for hisi_sas_phy spinlock, so add it.

Signed-off-by: John Garry <john.garry@huawei.com>
---
 drivers/scsi/hisi_sas/hisi_sas_main.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index 20aab10..781b2af 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -808,6 +808,8 @@ static void hisi_sas_phy_init(struct hisi_hba *hisi_hba, int phy_no)
 
 	for (i = 0; i < HISI_PHYES_NUM; i++)
 		INIT_WORK(&phy->works[i], hisi_sas_phye_fns[i]);
+
+	spin_lock_init(&phy->lock);
 }
 
 static void hisi_sas_port_notify_formed(struct asd_sas_phy *sas_phy)
-- 
1.9.1

[PATCH 8/9] scsi: hisi_sas: Add missing PHY spinlock init

[John Garry]

The init is missed for hisi_sas_phy spinlock, so add it.

Signed-off-by: John Garry <john.garry@huawei.com>
---
 drivers/scsi/hisi_sas/hisi_sas_main.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index 20aab10..781b2af 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -808,6 +808,8 @@ static void hisi_sas_phy_init(struct hisi_hba *hisi_hba, int phy_no)
 
 	for (i = 0; i < HISI_PHYES_NUM; i++)
 		INIT_WORK(&phy->works[i], hisi_sas_phye_fns[i]);
+
+	spin_lock_init(&phy->lock);
 }
 
 static void hisi_sas_port_notify_formed(struct asd_sas_phy *sas_phy)
-- 
1.9.1

[PATCH 9/9] scsi: hisi_sas: Update a couple of register settings for v3 hw

[John Garry]

Update CFG_1US_TIMER_TRSH and CON_CFG_DRIVER settings.

Signed-off-by: John Garry <john.garry@huawei.com>
---
 drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
index e43881d..4b7688a 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
@@ -51,7 +51,6 @@
 #define CFG_ABT_SET_IPTT_DONE	0xd8
 #define CFG_ABT_SET_IPTT_DONE_OFF	0
 #define HGC_IOMB_PROC1_STATUS	0x104
-#define CFG_1US_TIMER_TRSH		0xcc
 #define CHNL_INT_STATUS			0x148
 #define HGC_AXI_FIFO_ERR_INFO  0x154
 #define AXI_ERR_INFO_OFF               0
@@ -428,7 +427,6 @@ static void init_reg_v3_hw(struct hisi_hba *hisi_hba)
 			 (u32)((1ULL << hisi_hba->queue_count) - 1));
 	hisi_sas_write32(hisi_hba, CFG_MAX_TAG, 0xfff0400);
 	hisi_sas_write32(hisi_hba, HGC_SAS_TXFAIL_RETRY_CTRL, 0x108);
-	hisi_sas_write32(hisi_hba, CFG_1US_TIMER_TRSH, 0xd);
 	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);
@@ -489,6 +487,7 @@ static void init_reg_v3_hw(struct hisi_hba *hisi_hba)
 		hisi_sas_phy_write32(hisi_hba, i, SL_RX_BCAST_CHK_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, CON_CFG_DRIVER, 0x2a0a01);
 
 		/* used for 12G negotiate */
 		hisi_sas_phy_write32(hisi_hba, i, COARSETUNE_TIME, 0x1e);
-- 
1.9.1

[PATCH 9/9] scsi: hisi_sas: Update a couple of register settings for v3 hw

[John Garry]

Update CFG_1US_TIMER_TRSH and CON_CFG_DRIVER settings.

Signed-off-by: John Garry <john.garry@huawei.com>
---
 drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
index e43881d..4b7688a 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
@@ -51,7 +51,6 @@
 #define CFG_ABT_SET_IPTT_DONE	0xd8
 #define CFG_ABT_SET_IPTT_DONE_OFF	0
 #define HGC_IOMB_PROC1_STATUS	0x104
-#define CFG_1US_TIMER_TRSH		0xcc
 #define CHNL_INT_STATUS			0x148
 #define HGC_AXI_FIFO_ERR_INFO  0x154
 #define AXI_ERR_INFO_OFF               0
@@ -428,7 +427,6 @@ static void init_reg_v3_hw(struct hisi_hba *hisi_hba)
 			 (u32)((1ULL << hisi_hba->queue_count) - 1));
 	hisi_sas_write32(hisi_hba, CFG_MAX_TAG, 0xfff0400);
 	hisi_sas_write32(hisi_hba, HGC_SAS_TXFAIL_RETRY_CTRL, 0x108);
-	hisi_sas_write32(hisi_hba, CFG_1US_TIMER_TRSH, 0xd);
 	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);
@@ -489,6 +487,7 @@ static void init_reg_v3_hw(struct hisi_hba *hisi_hba)
 		hisi_sas_phy_write32(hisi_hba, i, SL_RX_BCAST_CHK_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, CON_CFG_DRIVER, 0x2a0a01);
 
 		/* used for 12G negotiate */
 		hisi_sas_phy_write32(hisi_hba, i, COARSETUNE_TIME, 0x1e);
-- 
1.9.1

Re: [PATCH 0/9] hisi_sas: some misc changes

[Martin K. Petersen]

John,

> This patchset introduces some more minor misc changes to the driver.

Applied to 4.19/scsi-queue. Thanks!

-- 
Martin K. Petersen	Oracle Linux Engineering

Re: [PATCH 0/9] hisi_sas: some misc changes

[Martin K. Petersen]

John,

> This patchset introduces some more minor misc changes to the driver.

Applied to 4.19/scsi-queue. Thanks!

-- 
Martin K. Petersen	Oracle Linux Engineering