drm/radeon: Add H/W debugger kfd->kgd functions

This patch adds new interface functions to the kfd2kgd interface file. The
new functions allow to perform H/W debugger operations by writing to GPU
registers.
Signed-off-by: Yair Shachar <yair.shachar@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>

drivers/gpu/drm/amd/include/kgd_kfd_interface.h

@@ -163,6 +163,19 @@ struct kfd2kgd_calls {
 	int (*hqd_sdma_destroy)(struct kgd_dev *kgd, void *mqd,
 				unsigned int timeout);
 
+	int (*address_watch_disable)(struct kgd_dev *kgd);
+	int (*address_watch_execute)(struct kgd_dev *kgd,
+					unsigned int watch_point_id,
+					uint32_t cntl_val,
+					uint32_t addr_hi,
+					uint32_t addr_lo);
+	int (*wave_control_execute)(struct kgd_dev *kgd,
+					uint32_t gfx_index_val,
+					uint32_t sq_cmd);
+	uint32_t (*address_watch_get_offset)(struct kgd_dev *kgd,
+					unsigned int watch_point_id,
+					unsigned int reg_offset);
+
 	uint16_t (*get_fw_version)(struct kgd_dev *kgd,
 				enum kgd_engine_type type);
 };

drivers/gpu/drm/radeon/cik_reg.h

@@ -149,10 +149,30 @@
 
 #define KFD_CIK_SDMA_QUEUE_OFFSET		0x200
 
+#define SQ_IND_INDEX					0x8DE0
+#define SQ_CMD						0x8DEC
+#define SQ_IND_DATA					0x8DE4
+
+/*
+ * The TCP_WATCHx_xxxx addresses that are shown here are in dwords,
+ * and that's why they are multiplied by 4
+ */
+#define TCP_WATCH0_ADDR_H				(0x32A0*4)
+#define TCP_WATCH1_ADDR_H				(0x32A3*4)
+#define TCP_WATCH2_ADDR_H				(0x32A6*4)
+#define TCP_WATCH3_ADDR_H				(0x32A9*4)
+#define TCP_WATCH0_ADDR_L				(0x32A1*4)
+#define TCP_WATCH1_ADDR_L				(0x32A4*4)
+#define TCP_WATCH2_ADDR_L				(0x32A7*4)
+#define TCP_WATCH3_ADDR_L				(0x32AA*4)
+#define TCP_WATCH0_CNTL					(0x32A2*4)
+#define TCP_WATCH1_CNTL					(0x32A5*4)
+#define TCP_WATCH2_CNTL					(0x32A8*4)
+#define TCP_WATCH3_CNTL					(0x32AB*4)
+
 #define CPC_INT_CNTL					0xC2D0
 
 #define CP_HQD_IQ_RPTR					0xC970u
-#define AQL_ENABLE					(1U << 0)
 #define SDMA0_RLC0_RB_CNTL				0xD400u
 #define	SDMA_RB_VMID(x)					(x << 24)
 #define	SDMA0_RLC0_RB_BASE				0xD404u
@@ -186,4 +206,38 @@
 #define	SDMA0_CNTL					0xD010
 #define	SDMA1_CNTL					0xD810
 
+enum {
+	MAX_TRAPID = 8,		/* 3 bits in the bitfield.  */
+	MAX_WATCH_ADDRESSES = 4
+};
+
+enum {
+	ADDRESS_WATCH_REG_ADDR_HI = 0,
+	ADDRESS_WATCH_REG_ADDR_LO,
+	ADDRESS_WATCH_REG_CNTL,
+	ADDRESS_WATCH_REG_MAX
+};
+
+enum {				/*  not defined in the CI/KV reg file  */
+	ADDRESS_WATCH_REG_CNTL_ATC_BIT = 0x10000000UL,
+	ADDRESS_WATCH_REG_CNTL_DEFAULT_MASK = 0x00FFFFFF,
+	ADDRESS_WATCH_REG_ADDLOW_MASK_EXTENSION = 0x03000000,
+	/* extend the mask to 26 bits in order to match the low address field */
+	ADDRESS_WATCH_REG_ADDLOW_SHIFT = 6,
+	ADDRESS_WATCH_REG_ADDHIGH_MASK = 0xFFFF
+};
+
+union TCP_WATCH_CNTL_BITS {
+	struct {
+		uint32_t mask:24;
+		uint32_t vmid:4;
+		uint32_t atc:1;
+		uint32_t mode:2;
+		uint32_t valid:1;
+	} bitfields, bits;
+	uint32_t u32All;
+	signed int i32All;
+	float f32All;
+};
+
 #endif

drivers/gpu/drm/radeon/radeon_kfd.c

@@ -34,6 +34,13 @@
 
 #define CIK_PIPE_PER_MEC	(4)
 
+static const uint32_t watchRegs[MAX_WATCH_ADDRESSES * ADDRESS_WATCH_REG_MAX] = {
+	TCP_WATCH0_ADDR_H, TCP_WATCH0_ADDR_L, TCP_WATCH0_CNTL,
+	TCP_WATCH1_ADDR_H, TCP_WATCH1_ADDR_L, TCP_WATCH1_CNTL,
+	TCP_WATCH2_ADDR_H, TCP_WATCH2_ADDR_L, TCP_WATCH2_CNTL,
+	TCP_WATCH3_ADDR_H, TCP_WATCH3_ADDR_L, TCP_WATCH3_CNTL
+};
+
 struct kgd_mem {
 	struct radeon_bo *bo;
 	uint64_t gpu_addr;
@@ -79,6 +86,18 @@ static int kgd_hqd_destroy(struct kgd_dev *kgd, uint32_t reset_type,
 static bool kgd_hqd_sdma_is_occupied(struct kgd_dev *kgd, void *mqd);
 static int kgd_hqd_sdma_destroy(struct kgd_dev *kgd, void *mqd,
 				unsigned int timeout);
+static int kgd_address_watch_disable(struct kgd_dev *kgd);
+static int kgd_address_watch_execute(struct kgd_dev *kgd,
+					unsigned int watch_point_id,
+					uint32_t cntl_val,
+					uint32_t addr_hi,
+					uint32_t addr_lo);
+static int kgd_wave_control_execute(struct kgd_dev *kgd,
+					uint32_t gfx_index_val,
+					uint32_t sq_cmd);
+static uint32_t kgd_address_watch_get_offset(struct kgd_dev *kgd,
+					unsigned int watch_point_id,
+					unsigned int reg_offset);
 
 static const struct kfd2kgd_calls kfd2kgd = {
 	.init_gtt_mem_allocation = alloc_gtt_mem,
@@ -96,6 +115,10 @@ static const struct kfd2kgd_calls kfd2kgd = {
 	.hqd_sdma_is_occupied = kgd_hqd_sdma_is_occupied,
 	.hqd_destroy = kgd_hqd_destroy,
 	.hqd_sdma_destroy = kgd_hqd_sdma_destroy,
+	.address_watch_disable = kgd_address_watch_disable,
+	.address_watch_execute = kgd_address_watch_execute,
+	.wave_control_execute = kgd_wave_control_execute,
+	.address_watch_get_offset = kgd_address_watch_get_offset,
 	.get_fw_version = get_fw_version
 };
 
@@ -665,6 +688,96 @@ static int kgd_hqd_sdma_destroy(struct kgd_dev *kgd, void *mqd,
 	return 0;
 }
 
+static int kgd_address_watch_disable(struct kgd_dev *kgd)
+{
+	union TCP_WATCH_CNTL_BITS cntl;
+	unsigned int i;
+
+	cntl.u32All = 0;
+
+	cntl.bitfields.valid = 0;
+	cntl.bitfields.mask = ADDRESS_WATCH_REG_CNTL_DEFAULT_MASK;
+	cntl.bitfields.atc = 1;
+
+	/* Turning off this address until we set all the registers */
+	for (i = 0; i < MAX_WATCH_ADDRESSES; i++)
+		write_register(kgd,
+				watchRegs[i * ADDRESS_WATCH_REG_MAX +
+					ADDRESS_WATCH_REG_CNTL],
+				cntl.u32All);
+
+	return 0;
+}
+
+static int kgd_address_watch_execute(struct kgd_dev *kgd,
+					unsigned int watch_point_id,
+					uint32_t cntl_val,
+					uint32_t addr_hi,
+					uint32_t addr_lo)
+{
+	union TCP_WATCH_CNTL_BITS cntl;
+
+	cntl.u32All = cntl_val;
+
+	/* Turning off this watch point until we set all the registers */
+	cntl.bitfields.valid = 0;
+	write_register(kgd,
+			watchRegs[watch_point_id * ADDRESS_WATCH_REG_MAX +
+				ADDRESS_WATCH_REG_CNTL],
+			cntl.u32All);
+
+	write_register(kgd,
+			watchRegs[watch_point_id * ADDRESS_WATCH_REG_MAX +
+				ADDRESS_WATCH_REG_ADDR_HI],
+			addr_hi);
+
+	write_register(kgd,
+			watchRegs[watch_point_id * ADDRESS_WATCH_REG_MAX +
+				ADDRESS_WATCH_REG_ADDR_LO],
+			addr_lo);
+
+	/* Enable the watch point */
+	cntl.bitfields.valid = 1;
+
+	write_register(kgd,
+			watchRegs[watch_point_id * ADDRESS_WATCH_REG_MAX +
+				ADDRESS_WATCH_REG_CNTL],
+			cntl.u32All);
+
+	return 0;
+}
+
+static int kgd_wave_control_execute(struct kgd_dev *kgd,
+					uint32_t gfx_index_val,
+					uint32_t sq_cmd)
+{
+	struct radeon_device *rdev = get_radeon_device(kgd);
+	uint32_t data;
+
+	mutex_lock(&rdev->grbm_idx_mutex);
+
+	write_register(kgd, GRBM_GFX_INDEX, gfx_index_val);
+	write_register(kgd, SQ_CMD, sq_cmd);
+
+	/*  Restore the GRBM_GFX_INDEX register  */
+
+	data = INSTANCE_BROADCAST_WRITES | SH_BROADCAST_WRITES |
+		SE_BROADCAST_WRITES;
+
+	write_register(kgd, GRBM_GFX_INDEX, data);
+
+	mutex_unlock(&rdev->grbm_idx_mutex);
+
+	return 0;
+}
+
+static uint32_t kgd_address_watch_get_offset(struct kgd_dev *kgd,
+					unsigned int watch_point_id,
+					unsigned int reg_offset)
+{
+	return watchRegs[watch_point_id * ADDRESS_WATCH_REG_MAX + reg_offset];
+}
+
 static uint16_t get_fw_version(struct kgd_dev *kgd, enum kgd_engine_type type)
 {
 	struct radeon_device *rdev = (struct radeon_device *) kgd;