[PATCH 1/9] habanalabs: change CB's ID to be 64 bits

[PATCH 1/9] habanalabs: change CB's ID to be 64 bits

[Oded Gabbay]

Although the possible values for CB's ID are only 32 bits, there are a few
places in the code where this field is shifted and passed into a function
which expects 64 bits.

Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
---
 drivers/misc/habanalabs/common/command_buffer.c | 2 +-
 drivers/misc/habanalabs/common/debugfs.c        | 2 +-
 drivers/misc/habanalabs/common/habanalabs.h     | 4 ++--
 3 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/misc/habanalabs/common/command_buffer.c b/drivers/misc/habanalabs/common/command_buffer.c
index 7c38c4f7f9c0..33aee64f37aa 100644
--- a/drivers/misc/habanalabs/common/command_buffer.c
+++ b/drivers/misc/habanalabs/common/command_buffer.c
@@ -173,7 +173,7 @@ int hl_cb_create(struct hl_device *hdev, struct hl_cb_mgr *mgr,
 		goto release_cb;
 	}
 
-	cb->id = rc;
+	cb->id = (u64) rc;
 
 	kref_init(&cb->refcount);
 	spin_lock_init(&cb->lock);
diff --git a/drivers/misc/habanalabs/common/debugfs.c b/drivers/misc/habanalabs/common/debugfs.c
index c50c6fc9e905..25775b12139b 100644
--- a/drivers/misc/habanalabs/common/debugfs.c
+++ b/drivers/misc/habanalabs/common/debugfs.c
@@ -110,7 +110,7 @@ static int command_buffers_show(struct seq_file *s, void *data)
 			seq_puts(s, "---------------------------------------------------------------\n");
 		}
 		seq_printf(s,
-			"   %03d        %d    0x%08x      %d          %d          %d\n",
+			"   %03llu        %d    0x%08x      %d          %d          %d\n",
 			cb->id, cb->ctx_id, cb->size,
 			kref_read(&cb->refcount),
 			cb->mmap, cb->cs_cnt);
diff --git a/drivers/misc/habanalabs/common/habanalabs.h b/drivers/misc/habanalabs/common/habanalabs.h
index 52a07c8d7d7c..2decf7be3e08 100644
--- a/drivers/misc/habanalabs/common/habanalabs.h
+++ b/drivers/misc/habanalabs/common/habanalabs.h
@@ -401,11 +401,11 @@ struct hl_cb_mgr {
  * @lock: spinlock to protect mmap/cs flows.
  * @debugfs_list: node in debugfs list of command buffers.
  * @pool_list: node in pool list of command buffers.
+ * @id: the CB's ID.
  * @kernel_address: Holds the CB's kernel virtual address.
  * @bus_address: Holds the CB's DMA address.
  * @mmap_size: Holds the CB's size that was mmaped.
  * @size: holds the CB's size.
- * @id: the CB's ID.
  * @cs_cnt: holds number of CS that this CB participates in.
  * @ctx_id: holds the ID of the owner's context.
  * @mmap: true if the CB is currently mmaped to user.
@@ -418,11 +418,11 @@ struct hl_cb {
 	spinlock_t		lock;
 	struct list_head	debugfs_list;
 	struct list_head	pool_list;
+	u64			id;
 	u64			kernel_address;
 	dma_addr_t		bus_address;
 	u32			mmap_size;
 	u32			size;
-	u32			id;
 	u32			cs_cnt;
 	u32			ctx_id;
 	u8			mmap;
-- 
2.17.1

[PATCH 2/9] habanalabs: cast int to u32 before printing it with %u

[Oded Gabbay]

%u is used for unsigned so we need to cast the int variable to u32 to avoid
compiler warning.

Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
---
 drivers/misc/habanalabs/common/device.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/misc/habanalabs/common/device.c b/drivers/misc/habanalabs/common/device.c
index 35214a186913..38895493a0ed 100644
--- a/drivers/misc/habanalabs/common/device.c
+++ b/drivers/misc/habanalabs/common/device.c
@@ -286,7 +286,7 @@ static int device_early_init(struct hl_device *hdev)
 	}
 
 	for (i = 0 ; i < hdev->asic_prop.completion_queues_count ; i++) {
-		snprintf(workq_name, 32, "hl-free-jobs-%u", i);
+		snprintf(workq_name, 32, "hl-free-jobs-%u", (u32) i);
 		hdev->cq_wq[i] = create_singlethread_workqueue(workq_name);
 		if (hdev->cq_wq[i] == NULL) {
 			dev_err(hdev->dev, "Failed to allocate CQ workqueue\n");
-- 
2.17.1

[PATCH 3/9] habanalabs: eliminate redundant else condition

[Oded Gabbay]

If both parts of if-else are goto statements, we can remove the else and
put the else goto statement after the if statement.

Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
---
 drivers/misc/habanalabs/common/command_submission.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/misc/habanalabs/common/command_submission.c b/drivers/misc/habanalabs/common/command_submission.c
index 2b40aa85bec9..58327cdb6a2c 100644
--- a/drivers/misc/habanalabs/common/command_submission.c
+++ b/drivers/misc/habanalabs/common/command_submission.c
@@ -686,8 +686,8 @@ static int cs_ioctl_default(struct hl_fpriv *hpriv, void __user *chunks,
 			rc = -ENOMEM;
 			if (is_kernel_allocated_cb)
 				goto release_cb;
-			else
-				goto free_cs_object;
+
+			goto free_cs_object;
 		}
 
 		job->id = i + 1;
-- 
2.17.1

[PATCH 4/9] habanalabs: use standard BIT() and GENMASK()

[Oded Gabbay]

Use the standard macros to define bitmasks.

Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
---
 drivers/misc/habanalabs/gaudi/gaudiP.h | 44 +++++++++++++-------------
 1 file changed, 22 insertions(+), 22 deletions(-)

diff --git a/drivers/misc/habanalabs/gaudi/gaudiP.h b/drivers/misc/habanalabs/gaudi/gaudiP.h
index 5dc99f6f0296..2eb5b9330275 100644
--- a/drivers/misc/habanalabs/gaudi/gaudiP.h
+++ b/drivers/misc/habanalabs/gaudi/gaudiP.h
@@ -141,28 +141,28 @@
 #define VA_HOST_SPACE_SIZE	(VA_HOST_SPACE_END - \
 					VA_HOST_SPACE_START) /* 767TB */
 
-#define HW_CAP_PLL		0x00000001
-#define HW_CAP_HBM		0x00000002
-#define HW_CAP_MMU		0x00000004
-#define HW_CAP_MME		0x00000008
-#define HW_CAP_CPU		0x00000010
-#define HW_CAP_PCI_DMA		0x00000020
-#define HW_CAP_MSI		0x00000040
-#define HW_CAP_CPU_Q		0x00000080
-#define HW_CAP_HBM_DMA		0x00000100
-#define HW_CAP_CLK_GATE		0x00000200
-#define HW_CAP_SRAM_SCRAMBLER	0x00000400
-#define HW_CAP_HBM_SCRAMBLER	0x00000800
-
-#define HW_CAP_TPC0		0x01000000
-#define HW_CAP_TPC1		0x02000000
-#define HW_CAP_TPC2		0x04000000
-#define HW_CAP_TPC3		0x08000000
-#define HW_CAP_TPC4		0x10000000
-#define HW_CAP_TPC5		0x20000000
-#define HW_CAP_TPC6		0x40000000
-#define HW_CAP_TPC7		0x80000000
-#define HW_CAP_TPC_MASK		0xFF000000
+#define HW_CAP_PLL		BIT(0)
+#define HW_CAP_HBM		BIT(1)
+#define HW_CAP_MMU		BIT(2)
+#define HW_CAP_MME		BIT(3)
+#define HW_CAP_CPU		BIT(4)
+#define HW_CAP_PCI_DMA		BIT(5)
+#define HW_CAP_MSI		BIT(6)
+#define HW_CAP_CPU_Q		BIT(7)
+#define HW_CAP_HBM_DMA		BIT(8)
+#define HW_CAP_CLK_GATE		BIT(9)
+#define HW_CAP_SRAM_SCRAMBLER	BIT(10)
+#define HW_CAP_HBM_SCRAMBLER	BIT(11)
+
+#define HW_CAP_TPC0		BIT(24)
+#define HW_CAP_TPC1		BIT(25)
+#define HW_CAP_TPC2		BIT(26)
+#define HW_CAP_TPC3		BIT(27)
+#define HW_CAP_TPC4		BIT(28)
+#define HW_CAP_TPC5		BIT(29)
+#define HW_CAP_TPC6		BIT(30)
+#define HW_CAP_TPC7		BIT(31)
+#define HW_CAP_TPC_MASK		GENMASK(31, 24)
 #define HW_CAP_TPC_SHIFT	24
 
 #define GAUDI_CPU_PCI_MSB_ADDR(addr)	(((addr) & GENMASK_ULL(49, 39)) >> 39)
-- 
2.17.1

[PATCH 5/9] habanalabs: use FIELD_PREP() instead of <<

[Oded Gabbay]

Use the standard FIELD_PREP() macro instead of << operator to perform
bitmask operations. This ensures type check safety and eliminate compiler
warnings.

Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
---
 drivers/misc/habanalabs/common/hw_queue.c     |   9 +-
 drivers/misc/habanalabs/gaudi/gaudi.c         |  50 ++--
 .../habanalabs/include/gaudi/gaudi_masks.h    | 274 ++++++++----------
 3 files changed, 154 insertions(+), 179 deletions(-)

diff --git a/drivers/misc/habanalabs/common/hw_queue.c b/drivers/misc/habanalabs/common/hw_queue.c
index 65b9aa69a83e..e2f9ba04b32d 100644
--- a/drivers/misc/habanalabs/common/hw_queue.c
+++ b/drivers/misc/habanalabs/common/hw_queue.c
@@ -8,6 +8,7 @@
 #include "habanalabs.h"
 
 #include <linux/slab.h>
+#include <linux/bitfield.h>
 
 /*
  * hl_queue_add_ptr - add to pi or ci and checks if it wraps around
@@ -288,10 +289,10 @@ static void ext_queue_schedule_job(struct hl_cs_job *job)
 	ptr = cb->bus_address;
 
 	cq_pkt.data = cpu_to_le32(
-				((q->pi << CQ_ENTRY_SHADOW_INDEX_SHIFT)
-					& CQ_ENTRY_SHADOW_INDEX_MASK) |
-				(1 << CQ_ENTRY_SHADOW_INDEX_VALID_SHIFT) |
-				(1 << CQ_ENTRY_READY_SHIFT));
+			((q->pi << CQ_ENTRY_SHADOW_INDEX_SHIFT)
+				& CQ_ENTRY_SHADOW_INDEX_MASK) |
+			FIELD_PREP(CQ_ENTRY_SHADOW_INDEX_VALID_MASK, 1) |
+			FIELD_PREP(CQ_ENTRY_READY_MASK, 1));
 
 	/*
 	 * No need to protect pi_offset because scheduling to the
diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c
index 6febfe4fdd81..ed289a6ed622 100644
--- a/drivers/misc/habanalabs/gaudi/gaudi.c
+++ b/drivers/misc/habanalabs/gaudi/gaudi.c
@@ -659,10 +659,10 @@ static int _gaudi_init_tpc_mem(struct hl_device *hdev,
 
 	init_tpc_mem_pkt->tsize = cpu_to_le32(tpc_kernel_size);
 
-	ctl = ((PACKET_LIN_DMA << GAUDI_PKT_CTL_OPCODE_SHIFT) |
-			(1 << GAUDI_PKT_LIN_DMA_CTL_LIN_SHIFT) |
-			(1 << GAUDI_PKT_CTL_RB_SHIFT) |
-			(1 << GAUDI_PKT_CTL_MB_SHIFT));
+	ctl = FIELD_PREP(GAUDI_PKT_CTL_OPCODE_MASK, PACKET_LIN_DMA);
+	ctl |= FIELD_PREP(GAUDI_PKT_LIN_DMA_CTL_LIN_MASK, 1);
+	ctl |= FIELD_PREP(GAUDI_PKT_CTL_RB_MASK, 1);
+	ctl |= FIELD_PREP(GAUDI_PKT_CTL_MB_MASK, 1);
 
 	init_tpc_mem_pkt->ctl = cpu_to_le32(ctl);
 
@@ -2305,7 +2305,8 @@ static void gaudi_init_tpc_qmans(struct hl_device *hdev)
 
 		tpc_offset += mmTPC1_QM_GLBL_CFG0 - mmTPC0_QM_GLBL_CFG0;
 
-		gaudi->hw_cap_initialized |= 1 << (HW_CAP_TPC_SHIFT + tpc_id);
+		gaudi->hw_cap_initialized |=
+				FIELD_PREP(HW_CAP_TPC_MASK, 1 << tpc_id);
 	}
 }
 
@@ -2886,13 +2887,13 @@ static void gaudi_pre_hw_init(struct hl_device *hdev)
 					(CFG_RST_H_DMA_MASK |
 					CFG_RST_H_MME_MASK |
 					CFG_RST_H_SM_MASK |
-					CFG_RST_H_TPC_MASK));
+					CFG_RST_H_TPC_7_MASK));
 
 	WREG32(mmPSOC_GLOBAL_CONF_SOFT_RST_CFG_L, CFG_RST_L_TPC_MASK);
 
 	WREG32(mmPSOC_GLOBAL_CONF_SW_ALL_RST_CFG_H,
 					(CFG_RST_H_HBM_MASK |
-					CFG_RST_H_TPC_MASK |
+					CFG_RST_H_TPC_7_MASK |
 					CFG_RST_H_NIC_MASK |
 					CFG_RST_H_SM_MASK |
 					CFG_RST_H_DMA_MASK |
@@ -3445,9 +3446,10 @@ static int gaudi_test_queue(struct hl_device *hdev, u32 hw_queue_id)
 		goto free_fence_ptr;
 	}
 
-	tmp = (PACKET_MSG_PROT << GAUDI_PKT_CTL_OPCODE_SHIFT) |
-			(1 << GAUDI_PKT_CTL_EB_SHIFT) |
-			(1 << GAUDI_PKT_CTL_MB_SHIFT);
+	tmp = FIELD_PREP(GAUDI_PKT_CTL_OPCODE_MASK, PACKET_MSG_PROT);
+	tmp |= FIELD_PREP(GAUDI_PKT_CTL_EB_MASK, 1);
+	tmp |= FIELD_PREP(GAUDI_PKT_CTL_MB_MASK, 1);
+
 	fence_pkt->ctl = cpu_to_le32(tmp);
 	fence_pkt->value = cpu_to_le32(fence_val);
 	fence_pkt->addr = cpu_to_le64(fence_dma_addr);
@@ -4252,11 +4254,11 @@ static void gaudi_add_end_of_cb_packets(struct hl_device *hdev,
 	cq_pkt = (struct packet_msg_prot *) (uintptr_t)
 		(kernel_address + len - (sizeof(struct packet_msg_prot) * 2));
 
-	tmp = (PACKET_MSG_PROT << GAUDI_PKT_CTL_OPCODE_SHIFT) |
-			(1 << GAUDI_PKT_CTL_MB_SHIFT);
+	tmp = FIELD_PREP(GAUDI_PKT_CTL_OPCODE_MASK, PACKET_MSG_PROT);
+	tmp |= FIELD_PREP(GAUDI_PKT_CTL_MB_MASK, 1);
 
 	if (eb)
-		tmp |= (1 << GAUDI_PKT_CTL_EB_SHIFT);
+		tmp |= FIELD_PREP(GAUDI_PKT_CTL_EB_MASK, 1);
 
 	cq_pkt->ctl = cpu_to_le32(tmp);
 	cq_pkt->value = cpu_to_le32(cq_val);
@@ -4264,8 +4266,8 @@ static void gaudi_add_end_of_cb_packets(struct hl_device *hdev,
 
 	cq_pkt++;
 
-	tmp = (PACKET_MSG_PROT << GAUDI_PKT_CTL_OPCODE_SHIFT) |
-			(1 << GAUDI_PKT_CTL_MB_SHIFT);
+	tmp = FIELD_PREP(GAUDI_PKT_CTL_OPCODE_MASK, PACKET_MSG_PROT);
+	tmp |= FIELD_PREP(GAUDI_PKT_CTL_MB_MASK, 1);
 	cq_pkt->ctl = cpu_to_le32(tmp);
 	cq_pkt->value = cpu_to_le32(1);
 
@@ -4297,11 +4299,12 @@ static int gaudi_memset_device_memory(struct hl_device *hdev, u64 addr,
 	memset(lin_dma_pkt, 0, sizeof(*lin_dma_pkt));
 	cb_size = sizeof(*lin_dma_pkt);
 
-	ctl = ((PACKET_LIN_DMA << GAUDI_PKT_CTL_OPCODE_SHIFT) |
-			(1 << GAUDI_PKT_LIN_DMA_CTL_MEMSET_SHIFT) |
-			(1 << GAUDI_PKT_LIN_DMA_CTL_LIN_SHIFT) |
-			(1 << GAUDI_PKT_CTL_RB_SHIFT) |
-			(1 << GAUDI_PKT_CTL_MB_SHIFT));
+	ctl = FIELD_PREP(GAUDI_PKT_CTL_OPCODE_MASK, PACKET_LIN_DMA);
+	ctl |= FIELD_PREP(GAUDI_PKT_LIN_DMA_CTL_MEMSET_MASK, 1);
+	ctl |= FIELD_PREP(GAUDI_PKT_LIN_DMA_CTL_LIN_MASK, 1);
+	ctl |= FIELD_PREP(GAUDI_PKT_CTL_MB_MASK, 1);
+	ctl |= FIELD_PREP(GAUDI_PKT_CTL_RB_MASK, 1);
+
 	lin_dma_pkt->ctl = cpu_to_le32(ctl);
 	lin_dma_pkt->src_addr = cpu_to_le64(val);
 	lin_dma_pkt->dst_addr |= cpu_to_le64(addr);
@@ -4907,9 +4910,10 @@ static int gaudi_send_job_on_qman0(struct hl_device *hdev,
 	fence_pkt = (struct packet_msg_prot *) (uintptr_t) (cb->kernel_address +
 			job->job_cb_size - sizeof(struct packet_msg_prot));
 
-	tmp = (PACKET_MSG_PROT << GAUDI_PKT_CTL_OPCODE_SHIFT) |
-			(1 << GAUDI_PKT_CTL_EB_SHIFT) |
-			(1 << GAUDI_PKT_CTL_MB_SHIFT);
+	tmp = FIELD_PREP(GAUDI_PKT_CTL_OPCODE_MASK, PACKET_MSG_PROT);
+	tmp |= FIELD_PREP(GAUDI_PKT_CTL_EB_MASK, 1);
+	tmp |= FIELD_PREP(GAUDI_PKT_CTL_MB_MASK, 1);
+
 	fence_pkt->ctl = cpu_to_le32(tmp);
 	fence_pkt->value = cpu_to_le32(GAUDI_QMAN0_FENCE_VAL);
 	fence_pkt->addr = cpu_to_le64(fence_dma_addr);
diff --git a/drivers/misc/habanalabs/include/gaudi/gaudi_masks.h b/drivers/misc/habanalabs/include/gaudi/gaudi_masks.h
index 13ef6b2887fd..3d4f9aed41f1 100644
--- a/drivers/misc/habanalabs/include/gaudi/gaudi_masks.h
+++ b/drivers/misc/habanalabs/include/gaudi/gaudi_masks.h
@@ -9,194 +9,164 @@
 #define GAUDI_MASKS_H_
 
 #include "asic_reg/gaudi_regs.h"
+#include <linux/bitfield.h>
 
 /* Useful masks for bits in various registers */
 #define PCI_DMA_QMAN_ENABLE		(\
-	(0xF << DMA0_QM_GLBL_CFG0_PQF_EN_SHIFT) | \
-	(0xF << DMA0_QM_GLBL_CFG0_CQF_EN_SHIFT) | \
-	(0xF << DMA0_QM_GLBL_CFG0_CP_EN_SHIFT))
+	(FIELD_PREP(DMA0_QM_GLBL_CFG0_PQF_EN_MASK, 0xF)) | \
+	(FIELD_PREP(DMA0_QM_GLBL_CFG0_CQF_EN_MASK, 0xF)) | \
+	(FIELD_PREP(DMA0_QM_GLBL_CFG0_CP_EN_MASK, 0xF)))
 
 #define QMAN_EXTERNAL_MAKE_TRUSTED	(\
-	(0xF << DMA0_QM_GLBL_PROT_PQF_SHIFT) | \
-	(0xF << DMA0_QM_GLBL_PROT_CQF_SHIFT) | \
-	(0xF << DMA0_QM_GLBL_PROT_CP_SHIFT) | \
-	(0x1 << DMA0_QM_GLBL_PROT_ERR_SHIFT))
+	(FIELD_PREP(DMA0_QM_GLBL_PROT_PQF_MASK, 0xF)) | \
+	(FIELD_PREP(DMA0_QM_GLBL_PROT_CQF_MASK, 0xF)) | \
+	(FIELD_PREP(DMA0_QM_GLBL_PROT_CP_MASK, 0xF)) | \
+	(FIELD_PREP(DMA0_QM_GLBL_PROT_ERR_MASK, 0x1)))
 
 #define QMAN_INTERNAL_MAKE_TRUSTED	(\
-	(0xF << DMA0_QM_GLBL_PROT_PQF_SHIFT) | \
-	(0x1 << DMA0_QM_GLBL_PROT_ERR_SHIFT))
+	(FIELD_PREP(DMA0_QM_GLBL_PROT_PQF_MASK, 0xF)) | \
+	(FIELD_PREP(DMA0_QM_GLBL_PROT_ERR_MASK, 0x1)))
 
 #define HBM_DMA_QMAN_ENABLE		(\
-	(0xF << DMA0_QM_GLBL_CFG0_PQF_EN_SHIFT) | \
-	(0x1F << DMA0_QM_GLBL_CFG0_CQF_EN_SHIFT) | \
-	(0x1F << DMA0_QM_GLBL_CFG0_CP_EN_SHIFT))
+	(FIELD_PREP(DMA0_QM_GLBL_CFG0_PQF_EN_MASK, 0xF)) | \
+	(FIELD_PREP(DMA0_QM_GLBL_CFG0_CQF_EN_MASK, 0x1F)) | \
+	(FIELD_PREP(DMA0_QM_GLBL_CFG0_CP_EN_MASK, 0x1F)))
 
 #define QMAN_MME_ENABLE		(\
-	(0xF << MME0_QM_GLBL_CFG0_PQF_EN_SHIFT) | \
-	(0x1F << MME0_QM_GLBL_CFG0_CQF_EN_SHIFT) | \
-	(0x1F << MME0_QM_GLBL_CFG0_CP_EN_SHIFT))
+	(FIELD_PREP(MME0_QM_GLBL_CFG0_PQF_EN_MASK, 0xF)) | \
+	(FIELD_PREP(MME0_QM_GLBL_CFG0_CQF_EN_MASK, 0x1F)) | \
+	(FIELD_PREP(MME0_QM_GLBL_CFG0_CP_EN_MASK, 0x1F)))
 
 #define QMAN_TPC_ENABLE		(\
-	(0xF << TPC0_QM_GLBL_CFG0_PQF_EN_SHIFT) | \
-	(0x1F << TPC0_QM_GLBL_CFG0_CQF_EN_SHIFT) | \
-	(0x1F << TPC0_QM_GLBL_CFG0_CP_EN_SHIFT))
+	(FIELD_PREP(TPC0_QM_GLBL_CFG0_PQF_EN_MASK, 0xF)) | \
+	(FIELD_PREP(TPC0_QM_GLBL_CFG0_CQF_EN_MASK, 0x1F)) | \
+	(FIELD_PREP(TPC0_QM_GLBL_CFG0_CP_EN_MASK, 0x1F)))
 
 #define QMAN_UPPER_CP_CGM_PWR_GATE_EN	(\
-	(0x20 << DMA0_QM_CGM_CFG_IDLE_TH_SHIFT) | \
-	(0xA << DMA0_QM_CGM_CFG_G2F_TH_SHIFT) | \
-	(0x10 << DMA0_QM_CGM_CFG_CP_IDLE_MASK_SHIFT) | \
-	(1 << DMA0_QM_CGM_CFG_EN_SHIFT))
+	(FIELD_PREP(DMA0_QM_CGM_CFG_IDLE_TH_MASK, 0x20)) | \
+	(FIELD_PREP(DMA0_QM_CGM_CFG_G2F_TH_MASK, 0xA)) | \
+	(FIELD_PREP(DMA0_QM_CGM_CFG_CP_IDLE_MASK_MASK, 0x10)) | \
+	(FIELD_PREP(DMA0_QM_CGM_CFG_EN_MASK, 0x1)))
 
 #define QMAN_COMMON_CP_CGM_PWR_GATE_EN	(\
-	(0x20 << DMA0_QM_CGM_CFG_IDLE_TH_SHIFT) | \
-	(0xA << DMA0_QM_CGM_CFG_G2F_TH_SHIFT) | \
-	(0xF << DMA0_QM_CGM_CFG_CP_IDLE_MASK_SHIFT) | \
-	(1 << DMA0_QM_CGM_CFG_EN_SHIFT))
+	(FIELD_PREP(DMA0_QM_CGM_CFG_IDLE_TH_MASK, 0x20)) | \
+	(FIELD_PREP(DMA0_QM_CGM_CFG_G2F_TH_MASK, 0xA)) | \
+	(FIELD_PREP(DMA0_QM_CGM_CFG_CP_IDLE_MASK_MASK, 0xF)) | \
+	(FIELD_PREP(DMA0_QM_CGM_CFG_EN_MASK, 0x1)))
 
 #define PCI_DMA_QMAN_GLBL_ERR_CFG_MSG_EN_MASK	(\
-	(0xF << DMA0_QM_GLBL_ERR_CFG_PQF_ERR_MSG_EN_SHIFT) | \
-	(0xF << DMA0_QM_GLBL_ERR_CFG_CQF_ERR_MSG_EN_SHIFT) | \
-	(0xF << DMA0_QM_GLBL_ERR_CFG_CP_ERR_MSG_EN_SHIFT))
+	(FIELD_PREP(DMA0_QM_GLBL_ERR_CFG_PQF_ERR_MSG_EN_MASK, 0xF)) | \
+	(FIELD_PREP(DMA0_QM_GLBL_ERR_CFG_CQF_ERR_MSG_EN_MASK, 0xF)) | \
+	(FIELD_PREP(DMA0_QM_GLBL_ERR_CFG_CP_ERR_MSG_EN_MASK, 0xF)))
 
 #define PCI_DMA_QMAN_GLBL_ERR_CFG_STOP_ON_ERR_EN_MASK	(\
-	(0xF << DMA0_QM_GLBL_ERR_CFG_PQF_STOP_ON_ERR_SHIFT) | \
-	(0xF << DMA0_QM_GLBL_ERR_CFG_CQF_STOP_ON_ERR_SHIFT) | \
-	(0xF << DMA0_QM_GLBL_ERR_CFG_CP_STOP_ON_ERR_SHIFT))
+	(FIELD_PREP(DMA0_QM_GLBL_ERR_CFG_PQF_STOP_ON_ERR_MASK, 0xF)) | \
+	(FIELD_PREP(DMA0_QM_GLBL_ERR_CFG_CQF_STOP_ON_ERR_MASK, 0xF)) | \
+	(FIELD_PREP(DMA0_QM_GLBL_ERR_CFG_CP_STOP_ON_ERR_MASK, 0xF)))
 
 #define HBM_DMA_QMAN_GLBL_ERR_CFG_MSG_EN_MASK	(\
-	(0xF << DMA0_QM_GLBL_ERR_CFG_PQF_ERR_MSG_EN_SHIFT) | \
-	(0x1F << DMA0_QM_GLBL_ERR_CFG_CQF_ERR_MSG_EN_SHIFT) | \
-	(0x1F << DMA0_QM_GLBL_ERR_CFG_CP_ERR_MSG_EN_SHIFT))
+	(FIELD_PREP(DMA0_QM_GLBL_ERR_CFG_PQF_ERR_MSG_EN_MASK, 0xF)) | \
+	(FIELD_PREP(DMA0_QM_GLBL_ERR_CFG_CQF_ERR_MSG_EN_MASK, 0x1F)) | \
+	(FIELD_PREP(DMA0_QM_GLBL_ERR_CFG_CP_ERR_MSG_EN_MASK, 0x1F)))
 
 #define HBM_DMA_QMAN_GLBL_ERR_CFG_STOP_ON_ERR_EN_MASK	(\
-	(0xF << DMA0_QM_GLBL_ERR_CFG_PQF_STOP_ON_ERR_SHIFT) | \
-	(0x1F << DMA0_QM_GLBL_ERR_CFG_CQF_STOP_ON_ERR_SHIFT) | \
-	(0x1F << DMA0_QM_GLBL_ERR_CFG_CP_STOP_ON_ERR_SHIFT))
+	(FIELD_PREP(DMA0_QM_GLBL_ERR_CFG_PQF_STOP_ON_ERR_MASK, 0xF)) | \
+	(FIELD_PREP(DMA0_QM_GLBL_ERR_CFG_CQF_STOP_ON_ERR_MASK, 0x1F)) | \
+	(FIELD_PREP(DMA0_QM_GLBL_ERR_CFG_CP_STOP_ON_ERR_MASK, 0x1F)))
 
 #define TPC_QMAN_GLBL_ERR_CFG_MSG_EN_MASK	(\
-	(0xF << TPC0_QM_GLBL_ERR_CFG_PQF_ERR_MSG_EN_SHIFT) | \
-	(0x1F << TPC0_QM_GLBL_ERR_CFG_CQF_ERR_MSG_EN_SHIFT) | \
-	(0x1F << TPC0_QM_GLBL_ERR_CFG_CP_ERR_MSG_EN_SHIFT))
+	(FIELD_PREP(TPC0_QM_GLBL_ERR_CFG_PQF_ERR_MSG_EN_MASK, 0xF)) | \
+	(FIELD_PREP(TPC0_QM_GLBL_ERR_CFG_CQF_ERR_MSG_EN_MASK, 0x1F)) | \
+	(FIELD_PREP(TPC0_QM_GLBL_ERR_CFG_CP_ERR_MSG_EN_MASK, 0x1F)))
 
 #define TPC_QMAN_GLBL_ERR_CFG_STOP_ON_ERR_EN_MASK	(\
-	(0xF << TPC0_QM_GLBL_ERR_CFG_PQF_STOP_ON_ERR_SHIFT) | \
-	(0x1F << TPC0_QM_GLBL_ERR_CFG_CQF_STOP_ON_ERR_SHIFT) | \
-	(0x1F << TPC0_QM_GLBL_ERR_CFG_CP_STOP_ON_ERR_SHIFT))
+	(FIELD_PREP(TPC0_QM_GLBL_ERR_CFG_PQF_STOP_ON_ERR_MASK, 0xF)) | \
+	(FIELD_PREP(TPC0_QM_GLBL_ERR_CFG_CQF_STOP_ON_ERR_MASK, 0x1F)) | \
+	(FIELD_PREP(TPC0_QM_GLBL_ERR_CFG_CP_STOP_ON_ERR_MASK, 0x1F)))
 
 #define MME_QMAN_GLBL_ERR_CFG_MSG_EN_MASK	(\
-	(0xF << MME0_QM_GLBL_ERR_CFG_PQF_ERR_MSG_EN_SHIFT) | \
-	(0x1F << MME0_QM_GLBL_ERR_CFG_CQF_ERR_MSG_EN_SHIFT) | \
-	(0x1F << MME0_QM_GLBL_ERR_CFG_CP_ERR_MSG_EN_SHIFT))
+	(FIELD_PREP(MME0_QM_GLBL_ERR_CFG_PQF_ERR_MSG_EN_MASK, 0xF)) | \
+	(FIELD_PREP(MME0_QM_GLBL_ERR_CFG_CQF_ERR_MSG_EN_MASK, 0x1F)) | \
+	(FIELD_PREP(MME0_QM_GLBL_ERR_CFG_CP_ERR_MSG_EN_MASK, 0x1F)))
 
 #define MME_QMAN_GLBL_ERR_CFG_STOP_ON_ERR_EN_MASK	(\
-	(0xF << MME0_QM_GLBL_ERR_CFG_PQF_STOP_ON_ERR_SHIFT) | \
-	(0x1F << MME0_QM_GLBL_ERR_CFG_CQF_STOP_ON_ERR_SHIFT) | \
-	(0x1F << MME0_QM_GLBL_ERR_CFG_CP_STOP_ON_ERR_SHIFT))
+	(FIELD_PREP(MME0_QM_GLBL_ERR_CFG_PQF_STOP_ON_ERR_MASK, 0xF)) | \
+	(FIELD_PREP(MME0_QM_GLBL_ERR_CFG_CQF_STOP_ON_ERR_MASK, 0x1F)) | \
+	(FIELD_PREP(MME0_QM_GLBL_ERR_CFG_CP_STOP_ON_ERR_MASK, 0x1F)))
 
-#define QMAN_CGM1_PWR_GATE_EN	(0xA << DMA0_QM_CGM_CFG1_MASK_TH_SHIFT)
+#define QMAN_CGM1_PWR_GATE_EN	(FIELD_PREP(DMA0_QM_CGM_CFG1_MASK_TH_MASK, 0xA))
 
 /* RESET registers configuration */
-#define CFG_RST_L_PSOC_SHIFT		0
-#define CFG_RST_L_PCIE_SHIFT		1
-#define CFG_RST_L_PCIE_IF_SHIFT		2
-#define CFG_RST_L_HBM_S_PLL_SHIFT	3
-#define CFG_RST_L_TPC_S_PLL_SHIFT	4
-#define CFG_RST_L_MME_S_PLL_SHIFT	5
-#define CFG_RST_L_CPU_PLL_SHIFT		6
-#define CFG_RST_L_PCIE_PLL_SHIFT	7
-#define CFG_RST_L_NIC_S_PLL_SHIFT	8
-#define CFG_RST_L_HBM_N_PLL_SHIFT	9
-#define CFG_RST_L_TPC_N_PLL_SHIFT	10
-#define CFG_RST_L_MME_N_PLL_SHIFT	11
-#define CFG_RST_L_NIC_N_PLL_SHIFT	12
-#define CFG_RST_L_DMA_W_PLL_SHIFT	13
-#define CFG_RST_L_SIF_W_PLL_SHIFT	14
-#define CFG_RST_L_MESH_W_PLL_SHIFT	15
-#define CFG_RST_L_SRAM_W_PLL_SHIFT	16
-#define CFG_RST_L_DMA_E_PLL_SHIFT	17
-#define CFG_RST_L_SIF_E_PLL_SHIFT	18
-#define CFG_RST_L_MESH_E_PLL_SHIFT	19
-#define CFG_RST_L_SRAM_E_PLL_SHIFT	20
-#define CFG_RST_L_IF_1_SHIFT		21
-#define CFG_RST_L_IF_0_SHIFT		22
-#define CFG_RST_L_IF_2_SHIFT		23
-#define CFG_RST_L_IF_3_SHIFT		24
-#define CFG_RST_L_TPC_0_SHIFT		25
-#define CFG_RST_L_TPC_1_SHIFT		26
-#define CFG_RST_L_TPC_2_SHIFT		27
-#define CFG_RST_L_TPC_3_SHIFT		28
-#define CFG_RST_L_TPC_4_SHIFT		29
-#define CFG_RST_L_TPC_5_SHIFT		30
-#define CFG_RST_L_TPC_6_SHIFT		31
-#define CFG_RST_H_TPC_7_SHIFT		0
-#define CFG_RST_H_MME_0_SHIFT		1
-#define CFG_RST_H_MME_1_SHIFT		2
-#define CFG_RST_H_MME_2_SHIFT		3
-#define CFG_RST_H_MME_3_SHIFT		4
-#define CFG_RST_H_HBM_0_SHIFT		5
-#define CFG_RST_H_HBM_1_SHIFT		6
-#define CFG_RST_H_HBM_2_SHIFT		7
-#define CFG_RST_H_HBM_3_SHIFT		8
-#define CFG_RST_H_NIC_0_SHIFT		9
-#define CFG_RST_H_NIC_1_SHIFT		10
-#define CFG_RST_H_NIC_2_SHIFT		11
-#define CFG_RST_H_NIC_3_SHIFT		12
-#define CFG_RST_H_NIC_4_SHIFT		13
-#define CFG_RST_H_SM_0_SHIFT		14
-#define CFG_RST_H_SM_1_SHIFT		15
-#define CFG_RST_H_SM_2_SHIFT		16
-#define CFG_RST_H_SM_3_SHIFT		17
-#define CFG_RST_H_DMA_0_SHIFT		18
-#define CFG_RST_H_DMA_1_SHIFT		19
-#define CFG_RST_H_CPU_SHIFT		20
-#define CFG_RST_H_MMU_SHIFT		21
-
-
-#define CFG_RST_H_DMA_MASK		((1 << CFG_RST_H_DMA_0_SHIFT) | \
-					(1 << CFG_RST_H_DMA_1_SHIFT))
-
-#define CFG_RST_H_CPU_MASK		(1 << CFG_RST_H_CPU_SHIFT)
-#define CFG_RST_H_MMU_MASK		(1 << CFG_RST_H_MMU_SHIFT)
-
-#define CFG_RST_H_HBM_MASK		((1 << CFG_RST_H_HBM_0_SHIFT) | \
-					(1 << CFG_RST_H_HBM_1_SHIFT) | \
-					(1 << CFG_RST_H_HBM_2_SHIFT) | \
-					(1 << CFG_RST_H_HBM_3_SHIFT))
-
-#define CFG_RST_H_NIC_MASK		((1 << CFG_RST_H_NIC_0_SHIFT) | \
-					(1 << CFG_RST_H_NIC_1_SHIFT) | \
-					(1 << CFG_RST_H_NIC_2_SHIFT) | \
-					(1 << CFG_RST_H_NIC_3_SHIFT) | \
-					(1 << CFG_RST_H_NIC_4_SHIFT))
-
-#define CFG_RST_H_SM_MASK		((1 << CFG_RST_H_SM_0_SHIFT) | \
-					(1 << CFG_RST_H_SM_1_SHIFT) | \
-					(1 << CFG_RST_H_SM_2_SHIFT) | \
-					(1 << CFG_RST_H_SM_3_SHIFT))
-
-#define CFG_RST_H_MME_MASK		((1 << CFG_RST_H_MME_0_SHIFT) | \
-					(1 << CFG_RST_H_MME_1_SHIFT) | \
-					(1 << CFG_RST_H_MME_2_SHIFT) | \
-					(1 << CFG_RST_H_MME_3_SHIFT))
-
-#define CFG_RST_L_PSOC_MASK		(1 << CFG_RST_L_PSOC_SHIFT)
-
-#define CFG_RST_L_IF_MASK		((1 << CFG_RST_L_IF_0_SHIFT) | \
-					(1 << CFG_RST_L_IF_1_SHIFT) | \
-					(1 << CFG_RST_L_IF_2_SHIFT) | \
-					(1 << CFG_RST_L_IF_3_SHIFT))
-
-#define CFG_RST_L_TPC_MASK		((1 << CFG_RST_L_TPC_0_SHIFT) | \
-					(1 << CFG_RST_L_TPC_1_SHIFT) | \
-					(1 << CFG_RST_L_TPC_2_SHIFT) | \
-					(1 << CFG_RST_L_TPC_3_SHIFT) | \
-					(1 << CFG_RST_L_TPC_4_SHIFT) | \
-					(1 << CFG_RST_L_TPC_5_SHIFT) | \
-					(1 << CFG_RST_L_TPC_6_SHIFT))
-
-#define CFG_RST_H_TPC_MASK		(1 << CFG_RST_H_TPC_7_SHIFT)
-
-#define CA53_RESET			(1 << CFG_RST_H_CPU_SHIFT)
+#define CFG_RST_L_PSOC_MASK		BIT_MASK(0)
+#define CFG_RST_L_PCIE_MASK		BIT_MASK(1)
+#define CFG_RST_L_PCIE_IF_MASK		BIT_MASK(2)
+#define CFG_RST_L_HBM_S_PLL_MASK	BIT_MASK(3)
+#define CFG_RST_L_TPC_S_PLL_MASK	BIT_MASK(4)
+#define CFG_RST_L_MME_S_PLL_MASK	BIT_MASK(5)
+#define CFG_RST_L_CPU_PLL_MASK		BIT_MASK(6)
+#define CFG_RST_L_PCIE_PLL_MASK		BIT_MASK(7)
+#define CFG_RST_L_NIC_S_PLL_MASK	BIT_MASK(8)
+#define CFG_RST_L_HBM_N_PLL_MASK	BIT_MASK(9)
+#define CFG_RST_L_TPC_N_PLL_MASK	BIT_MASK(10)
+#define CFG_RST_L_MME_N_PLL_MASK	BIT_MASK(11)
+#define CFG_RST_L_NIC_N_PLL_MASK	BIT_MASK(12)
+#define CFG_RST_L_DMA_W_PLL_MASK	BIT_MASK(13)
+#define CFG_RST_L_SIF_W_PLL_MASK	BIT_MASK(14)
+#define CFG_RST_L_MESH_W_PLL_MASK	BIT_MASK(15)
+#define CFG_RST_L_SRAM_W_PLL_MASK	BIT_MASK(16)
+#define CFG_RST_L_DMA_E_PLL_MASK	BIT_MASK(17)
+#define CFG_RST_L_SIF_E_PLL_MASK	BIT_MASK(18)
+#define CFG_RST_L_MESH_E_PLL_MASK	BIT_MASK(19)
+#define CFG_RST_L_SRAM_E_PLL_MASK	BIT_MASK(20)
+
+#define CFG_RST_L_IF_1_MASK		BIT_MASK(21)
+#define CFG_RST_L_IF_0_MASK		BIT_MASK(22)
+#define CFG_RST_L_IF_2_MASK		BIT_MASK(23)
+#define CFG_RST_L_IF_3_MASK		BIT_MASK(24)
+#define CFG_RST_L_IF_MASK		GENMASK(24, 21)
+
+#define CFG_RST_L_TPC_0_MASK		BIT_MASK(25)
+#define CFG_RST_L_TPC_1_MASK		BIT_MASK(26)
+#define CFG_RST_L_TPC_2_MASK		BIT_MASK(27)
+#define CFG_RST_L_TPC_3_MASK		BIT_MASK(28)
+#define CFG_RST_L_TPC_4_MASK		BIT_MASK(29)
+#define CFG_RST_L_TPC_5_MASK		BIT_MASK(30)
+#define CFG_RST_L_TPC_6_MASK		BIT_MASK(31)
+#define CFG_RST_L_TPC_MASK		GENMASK(31, 25)
+
+#define CFG_RST_H_TPC_7_MASK		BIT_MASK(0)
+
+#define CFG_RST_H_MME_0_MASK		BIT_MASK(1)
+#define CFG_RST_H_MME_1_MASK		BIT_MASK(2)
+#define CFG_RST_H_MME_2_MASK		BIT_MASK(3)
+#define CFG_RST_H_MME_3_MASK		BIT_MASK(4)
+#define CFG_RST_H_MME_MASK		GENMASK(4, 1)
+
+#define CFG_RST_H_HBM_0_MASK		BIT_MASK(5)
+#define CFG_RST_H_HBM_1_MASK		BIT_MASK(6)
+#define CFG_RST_H_HBM_2_MASK		BIT_MASK(7)
+#define CFG_RST_H_HBM_3_MASK		BIT_MASK(8)
+#define CFG_RST_H_HBM_MASK		GENMASK(8, 5)
+
+#define CFG_RST_H_NIC_0_MASK		BIT_MASK(9)
+#define CFG_RST_H_NIC_1_MASK		BIT_MASK(10)
+#define CFG_RST_H_NIC_2_MASK		BIT_MASK(11)
+#define CFG_RST_H_NIC_3_MASK		BIT_MASK(12)
+#define CFG_RST_H_NIC_4_MASK		BIT_MASK(13)
+#define CFG_RST_H_NIC_MASK		GENMASK(13, 9)
+
+#define CFG_RST_H_SM_0_MASK		BIT_MASK(14)
+#define CFG_RST_H_SM_1_MASK		BIT_MASK(15)
+#define CFG_RST_H_SM_2_MASK		BIT_MASK(16)
+#define CFG_RST_H_SM_3_MASK		BIT_MASK(17)
+#define CFG_RST_H_SM_MASK		GENMASK(17, 14)
+
+#define CFG_RST_H_DMA_0_MASK		BIT_MASK(18)
+#define CFG_RST_H_DMA_1_MASK		BIT_MASK(19)
+#define CFG_RST_H_DMA_MASK		GENMASK(19, 18)
+
+#define CFG_RST_H_CPU_MASK		BIT_MASK(20)
+#define CFG_RST_H_MMU_MASK		BIT_MASK(21)
 
 #define UNIT_RST_L_PSOC_SHIFT		0
 #define UNIT_RST_L_PCIE_SHIFT		1
-- 
2.17.1

[PATCH 6/9] habanalabs: remove redundant assignment to variable

[Oded Gabbay]

new_dma_pkt->ctl is assigned a value and then is reassigned a new value
without the first value ever being used.

Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
---
 drivers/misc/habanalabs/gaudi/gaudi.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c
index ed289a6ed622..ffd0849e8f2d 100644
--- a/drivers/misc/habanalabs/gaudi/gaudi.c
+++ b/drivers/misc/habanalabs/gaudi/gaudi.c
@@ -3944,8 +3944,6 @@ static int gaudi_patch_dma_packet(struct hl_device *hdev,
 			}
 		}
 
-		new_dma_pkt->ctl = user_dma_pkt->ctl;
-
 		ctl = le32_to_cpu(user_dma_pkt->ctl);
 		if (likely(dma_desc_cnt))
 			ctl &= ~GAUDI_PKT_CTL_EB_MASK;
-- 
2.17.1

[PATCH 7/9] habanalabs: check TPC vector pipe is empty

[Oded Gabbay]

The driver waits for the TPC vector pipe to be empty before checking if the
TPC kernel has finished executing, but the code doesn't validate that the
pipe was indeed empty, it just wait for it without checking the return
value.

Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
---
 drivers/misc/habanalabs/gaudi/gaudi.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c
index ffd0849e8f2d..3360c3c207a9 100644
--- a/drivers/misc/habanalabs/gaudi/gaudi.c
+++ b/drivers/misc/habanalabs/gaudi/gaudi.c
@@ -6262,6 +6262,15 @@ static int gaudi_run_tpc_kernel(struct hl_device *hdev, u64 tpc_kernel,
 		1000,
 		kernel_timeout);
 
+	if (rc) {
+		dev_err(hdev->dev,
+			"Timeout while waiting for TPC%d vector pipe\n",
+			tpc_id);
+		hdev->asic_funcs->set_clock_gating(hdev);
+		mutex_unlock(&gaudi->clk_gate_mutex);
+		return -EIO;
+	}
+
 	rc = hl_poll_timeout(
 		hdev,
 		mmTPC0_CFG_WQ_INFLIGHT_CNTR + offset,
-- 
2.17.1

[PATCH 9/9] habanalabs: extend busy engines mask to 64 bits

[Oded Gabbay]

From: farah kassabri <fkassabri@habana.ai>

change busy engines bitmask to 64 bits in order to represent
more engines, needed for future ASIC support.

Signed-off-by: farah kassabri <fkassabri@habana.ai>
Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
---
 drivers/misc/habanalabs/common/habanalabs.h       | 2 +-
 drivers/misc/habanalabs/common/habanalabs_ioctl.c | 2 +-
 drivers/misc/habanalabs/gaudi/gaudi.c             | 2 +-
 drivers/misc/habanalabs/goya/goya.c               | 2 +-
 include/uapi/misc/habanalabs.h                    | 6 ++++++
 5 files changed, 10 insertions(+), 4 deletions(-)

diff --git a/drivers/misc/habanalabs/common/habanalabs.h b/drivers/misc/habanalabs/common/habanalabs.h
index 2decf7be3e08..dbf214421ae1 100644
--- a/drivers/misc/habanalabs/common/habanalabs.h
+++ b/drivers/misc/habanalabs/common/habanalabs.h
@@ -754,7 +754,7 @@ struct hl_asic_funcs {
 	void (*set_clock_gating)(struct hl_device *hdev);
 	void (*disable_clock_gating)(struct hl_device *hdev);
 	int (*debug_coresight)(struct hl_device *hdev, void *data);
-	bool (*is_device_idle)(struct hl_device *hdev, u32 *mask,
+	bool (*is_device_idle)(struct hl_device *hdev, u64 *mask,
 				struct seq_file *s);
 	int (*soft_reset_late_init)(struct hl_device *hdev);
 	void (*hw_queues_lock)(struct hl_device *hdev);
diff --git a/drivers/misc/habanalabs/common/habanalabs_ioctl.c b/drivers/misc/habanalabs/common/habanalabs_ioctl.c
index fe6c5534d378..a94800014243 100644
--- a/drivers/misc/habanalabs/common/habanalabs_ioctl.c
+++ b/drivers/misc/habanalabs/common/habanalabs_ioctl.c
@@ -132,7 +132,7 @@ static int hw_idle(struct hl_device *hdev, struct hl_info_args *args)
 		return -EINVAL;
 
 	hw_idle.is_idle = hdev->asic_funcs->is_device_idle(hdev,
-					&hw_idle.busy_engines_mask, NULL);
+					&hw_idle.busy_engines_mask_ext, NULL);
 
 	return copy_to_user(out, &hw_idle,
 		min((size_t) max_size, sizeof(hw_idle))) ? -EFAULT : 0;
diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c
index 3360c3c207a9..e56f95e6c741 100644
--- a/drivers/misc/habanalabs/gaudi/gaudi.c
+++ b/drivers/misc/habanalabs/gaudi/gaudi.c
@@ -6041,7 +6041,7 @@ static int gaudi_armcp_info_get(struct hl_device *hdev)
 	return 0;
 }
 
-static bool gaudi_is_device_idle(struct hl_device *hdev, u32 *mask,
+static bool gaudi_is_device_idle(struct hl_device *hdev, u64 *mask,
 					struct seq_file *s)
 {
 	struct gaudi_device *gaudi = hdev->asic_specific;
diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c
index 77a5963a4d10..021cd26fb018 100644
--- a/drivers/misc/habanalabs/goya/goya.c
+++ b/drivers/misc/habanalabs/goya/goya.c
@@ -5117,7 +5117,7 @@ static void goya_disable_clock_gating(struct hl_device *hdev)
 	/* clock gating not supported in Goya */
 }
 
-static bool goya_is_device_idle(struct hl_device *hdev, u32 *mask,
+static bool goya_is_device_idle(struct hl_device *hdev, u64 *mask,
 				struct seq_file *s)
 {
 	const char *fmt = "%-5d%-9s%#-14x%#-16x%#x\n";
diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h
index ca6dc1fc250e..693081728ef3 100644
--- a/include/uapi/misc/habanalabs.h
+++ b/include/uapi/misc/habanalabs.h
@@ -319,6 +319,12 @@ struct hl_info_hw_idle {
 	 * Bits definition is according to `enum <chip>_enging_id'.
 	 */
 	__u32 busy_engines_mask;
+
+	/*
+	 * Extended Bitmask of busy engines.
+	 * Bits definition is according to `enum <chip>_enging_id'.
+	 */
+	__u64 busy_engines_mask_ext;
 };
 
 struct hl_info_device_status {
-- 
2.17.1

RE: [PATCH 1/9] habanalabs: change CB's ID to be 64 bits

[Tomer Tayar]

On Sat, Aug 15, 2020 at 21:00 Oded Gabbay <oded.gabbay@gmail.com> wrote:
> Although the possible values for CB's ID are only 32 bits, there are a few
> places in the code where this field is shifted and passed into a function
> which expects 64 bits.
> 
> Reported-by: kernel test robot <lkp@intel.com>
> Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>

Reviewed-by: Tomer Tayar <ttayar@habana.ai>

RE: [PATCH 2/9] habanalabs: cast int to u32 before printing it with %u

[Tomer Tayar]

On Sat, Aug 15, 2020 at 21:00 Oded Gabbay <oded.gabbay@gmail.com> wrote:
> %u is used for unsigned so we need to cast the int variable to u32 to avoid
> compiler warning.
> 
> Reported-by: kernel test robot <lkp@intel.com>
> Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>

Reviewed-by: Tomer Tayar <ttayar@habana.ai>

RE: [PATCH 3/9] habanalabs: eliminate redundant else condition

[Tomer Tayar]

On Sat, Aug 15, 2020 at 21:00 Oded Gabbay <oded.gabbay@gmail.com> wrote:
> If both parts of if-else are goto statements, we can remove the else and
> put the else goto statement after the if statement.
> 
> Reported-by: kernel test robot <lkp@intel.com>
> Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>

Reviewed-by: Tomer Tayar <ttayar@habana.ai>

RE: [PATCH 4/9] habanalabs: use standard BIT() and GENMASK()

[Tomer Tayar]

On Sat, Aug 15, 2020 at 21:00 Oded Gabbay <oded.gabbay@gmail.com> wrote:
> Use the standard macros to define bitmasks.
> 
> Reported-by: kernel test robot <lkp@intel.com>
> Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>

Reviewed-by: Tomer Tayar <ttayar@habana.ai>

RE: [PATCH 5/9] habanalabs: use FIELD_PREP() instead of <<

[Tomer Tayar]

On Sat, Aug 15, 2020 at 21:00 Oded Gabbay <oded.gabbay@gmail.com> wrote:
> Use the standard FIELD_PREP() macro instead of << operator to perform
> bitmask operations. This ensures type check safety and eliminate compiler
> warnings.
> 
> Reported-by: kernel test robot <lkp@intel.com>
> Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>

Reviewed-by: Tomer Tayar <ttayar@habana.ai>

RE: [PATCH 6/9] habanalabs: remove redundant assignment to variable

[Tomer Tayar]

On Sat, Aug 15, 2020 at 21:00 Oded Gabbay <oded.gabbay@gmail.com> wrote:
> new_dma_pkt->ctl is assigned a value and then is reassigned a new value
> without the first value ever being used.
> 
> Reported-by: kernel test robot <lkp@intel.com>
> Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>

Reviewed-by: Tomer Tayar <ttayar@habana.ai>

RE: [PATCH 7/9] habanalabs: check TPC vector pipe is empty

[Tomer Tayar]

On Sat, Aug 15, 2020 at 21:00 Oded Gabbay <oded.gabbay@gmail.com> wrote:
> The driver waits for the TPC vector pipe to be empty before checking if the
> TPC kernel has finished executing, but the code doesn't validate that the
> pipe was indeed empty, it just wait for it without checking the return
> value.
> 
> Reported-by: kernel test robot <lkp@intel.com>
> Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>

Reviewed-by: Tomer Tayar <ttayar@habana.ai>

RE: [PATCH 8/9] habanalabs: use 1U when shifting bits

[Tomer Tayar]

On Sat, Aug 15, 2020 at 21:00 Oded Gabbay <oded.gabbay@gmail.com> wrote:
> Eliminate following warning:
> warning: Shifting signed 32-bit value by 31 bits is undefined behavior
> 
> Reported-by: kernel test robot <lkp@intel.com>
> Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>

Reviewed-by: Tomer Tayar <ttayar@habana.ai>