[PATCH v2 01/12] drm/amdgpu: Indirect register access for Navi12 sriov

[PATCH v2 01/12] drm/amdgpu: Indirect register access for Navi12 sriov

[Peng Ju Zhou]

Change RLCG/SOC15 register access interface to triage
GC/MMHUB access from MMIO to RLCG.

Signed-off-by: Peng Ju Zhou <PengJu.Zhou@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.h   |   4 +-
 drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c    |  68 ++++----------
 drivers/gpu/drm/amd/amdgpu/soc15_common.h | 109 +++++++++++++++-------
 3 files changed, 95 insertions(+), 86 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.h
index 4fc2ce8ce8ab..8193bd04b4b9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.h
@@ -127,8 +127,8 @@ struct amdgpu_rlc_funcs {
 	void (*reset)(struct amdgpu_device *adev);
 	void (*start)(struct amdgpu_device *adev);
 	void (*update_spm_vmid)(struct amdgpu_device *adev, unsigned vmid);
-	void (*rlcg_wreg)(struct amdgpu_device *adev, u32 offset, u32 v, u32 flag);
-	u32 (*rlcg_rreg)(struct amdgpu_device *adev, u32 offset, u32 flag);
+	void (*rlcg_wreg)(struct amdgpu_device *adev, u32 offset, u32 v, u32 hwip);
+	u32 (*rlcg_rreg)(struct amdgpu_device *adev, u32 offset, u32 hwip);
 	bool (*is_rlcg_access_range)(struct amdgpu_device *adev, uint32_t reg);
 };
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index 49fd10a15707..9320d44a67bc 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -1427,38 +1427,25 @@ static const struct soc15_reg_golden golden_settings_gc_10_1_2[] =
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmUTCL1_CTRL, 0xffffffff, 0x00800000)
 };
 
-static bool gfx_v10_is_rlcg_rw(struct amdgpu_device *adev, u32 offset, uint32_t *flag, bool write)
-{
-	/* always programed by rlcg, only for gc */
-	if (offset == SOC15_REG_OFFSET(GC, 0, mmRLC_CSIB_ADDR_HI) ||
-	    offset == SOC15_REG_OFFSET(GC, 0, mmRLC_CSIB_ADDR_LO) ||
-	    offset == SOC15_REG_OFFSET(GC, 0, mmRLC_CSIB_LENGTH) ||
-	    offset == SOC15_REG_OFFSET(GC, 0, mmGRBM_GFX_CNTL) ||
-	    offset == SOC15_REG_OFFSET(GC, 0, mmGRBM_GFX_INDEX) ||
-	    offset == SOC15_REG_OFFSET(GC, 0, mmCP_ME_CNTL)) {
-		if (!amdgpu_sriov_reg_indirect_gc(adev))
-			*flag = GFX_RLCG_GC_WRITE_OLD;
-		else
-			*flag = write ? GFX_RLCG_GC_WRITE : GFX_RLCG_GC_READ;
-
-		return true;
-	}
+static u32 gfx_v10_get_rlcg_flag(struct amdgpu_device *adev, u32 hwip, int write)
+{
+	u32 flag = -1;
 
-	/* currently support gc read/write, mmhub write */
-	if (offset >= SOC15_REG_OFFSET(GC, 0, mmSDMA0_DEC_START) &&
-	    offset <= SOC15_REG_OFFSET(GC, 0, mmRLC_GTS_OFFSET_MSB)) {
+	if (hwip == GC_HWIP) {
 		if (amdgpu_sriov_reg_indirect_gc(adev))
-			*flag = write ? GFX_RLCG_GC_WRITE : GFX_RLCG_GC_READ;
+			flag = write ? GFX_RLCG_GC_WRITE : GFX_RLCG_GC_READ;
 		else
-			return false;
+			flag = GFX_RLCG_GC_WRITE_OLD;
 	} else {
+		ASSERT(write);
 		if (amdgpu_sriov_reg_indirect_mmhub(adev))
-			*flag = GFX_RLCG_MMHUB_WRITE;
-		else
-			return false;
+			flag = GFX_RLCG_MMHUB_WRITE;
 	}
 
-	return true;
+	if (flag == -1)
+		DRM_ERROR("amdgpu: failed to get RLCG flag, IP 0x%x\n", hwip);
+
+	return flag;
 }
 
 static u32 gfx_v10_rlcg_rw(struct amdgpu_device *adev, u32 offset, u32 v, uint32_t flag)
@@ -1518,36 +1505,21 @@ static u32 gfx_v10_rlcg_rw(struct amdgpu_device *adev, u32 offset, u32 v, uint32
 	return ret;
 }
 
-static void gfx_v10_rlcg_wreg(struct amdgpu_device *adev, u32 offset, u32 value, u32 flag)
+static void gfx_v10_rlcg_wreg(struct amdgpu_device *adev, u32 offset, u32 value, u32 hwip)
 {
-	uint32_t rlcg_flag;
-
-	if (amdgpu_sriov_fullaccess(adev) &&
-	    gfx_v10_is_rlcg_rw(adev, offset, &rlcg_flag, 1)) {
-		gfx_v10_rlcg_rw(adev, offset, value, rlcg_flag);
+	u32 rlcg_flag;
 
-		return;
-	}
-	if (flag & AMDGPU_REGS_NO_KIQ)
-		WREG32_NO_KIQ(offset, value);
-	else
-		WREG32(offset, value);
+	rlcg_flag = gfx_v10_get_rlcg_flag(adev, hwip, 1);
+	gfx_v10_rlcg_rw(adev, offset, value, rlcg_flag);
 }
 
-static u32 gfx_v10_rlcg_rreg(struct amdgpu_device *adev, u32 offset, u32 flag)
+static u32 gfx_v10_rlcg_rreg(struct amdgpu_device *adev, u32 offset, u32 hwip)
 {
-	uint32_t rlcg_flag;
-
-	if (amdgpu_sriov_fullaccess(adev) &&
-	    gfx_v10_is_rlcg_rw(adev, offset, &rlcg_flag, 0))
-		return gfx_v10_rlcg_rw(adev, offset, 0, rlcg_flag);
+	u32 rlcg_flag;
 
-	if (flag & AMDGPU_REGS_NO_KIQ)
-		return RREG32_NO_KIQ(offset);
-	else
-		return RREG32(offset);
+	rlcg_flag = gfx_v10_get_rlcg_flag(adev, hwip, 0);
 
-	return 0;
+	return gfx_v10_rlcg_rw(adev, offset, 0, rlcg_flag);
 }
 
 static const struct soc15_reg_golden golden_settings_gc_10_1_nv14[] =
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15_common.h b/drivers/gpu/drm/amd/amdgpu/soc15_common.h
index 14bd794bbea6..16b659596dd6 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15_common.h
+++ b/drivers/gpu/drm/amd/amdgpu/soc15_common.h
@@ -27,28 +27,73 @@
 /* Register Access Macros */
 #define SOC15_REG_OFFSET(ip, inst, reg)	(adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg)
 
+#define RLC_GC_EN(hwip) \
+	(amdgpu_sriov_fullaccess(adev) && \
+	 (amdgpu_sriov_reg_indirect_gc(adev) && (hwip == GC_HWIP)))
+
+#define RLC_MMHUB_EN(hwip, write) \
+	(amdgpu_sriov_fullaccess(adev) && \
+	 (amdgpu_sriov_reg_indirect_mmhub(adev) && \
+	  (hwip == MMHUB_HWIP) && \
+	  (write)))
+
+#define __WREG32_SOC15_RLC__(reg, value, hwip) \
+	((((hwip == GC_HWIP) || ((hwip == MMHUB_HWIP) && RLC_MMHUB_EN(hwip, 1))) && \
+	  amdgpu_sriov_vf(adev) && adev->gfx.rlc.funcs->rlcg_wreg) ? \
+	 adev->gfx.rlc.funcs->rlcg_wreg(adev, reg, value, hwip) : \
+	 WREG32(reg, value))
+
+#define __RREG32_SOC15_RLC__(reg, hwip) \
+	((amdgpu_sriov_vf(adev) && adev->gfx.rlc.funcs->rlcg_rreg) ? \
+	 adev->gfx.rlc.funcs->rlcg_rreg(adev, reg, hwip) : \
+	 RREG32(reg))
+
+#define __WREG32_SOC15__(reg, value, hwip) \
+	(RLC_GC_EN(hwip) ? \
+	 __WREG32_SOC15_RLC__(reg, value, hwip) : \
+	 WREG32(reg, value))
+
+#define __RREG32_SOC15__(reg, hwip) \
+	(RLC_GC_EN(hwip) ? \
+	 __RREG32_SOC15_RLC__(reg, hwip) : \
+	 RREG32(reg))
+
 #define WREG32_FIELD15(ip, idx, reg, field, val)	\
-	WREG32(adev->reg_offset[ip##_HWIP][idx][mm##reg##_BASE_IDX] + mm##reg,	\
-	(RREG32(adev->reg_offset[ip##_HWIP][idx][mm##reg##_BASE_IDX] + mm##reg)	\
-	& ~REG_FIELD_MASK(reg, field)) | (val) << REG_FIELD_SHIFT(reg, field))
+	 __WREG32_SOC15__(adev->reg_offset[ip##_HWIP][idx][mm##reg##_BASE_IDX] + mm##reg,	\
+				(__RREG32_SOC15__( \
+					adev->reg_offset[ip##_HWIP][idx][mm##reg##_BASE_IDX] + mm##reg, \
+					ip##_HWIP) & \
+				~REG_FIELD_MASK(reg, field)) | (val) << REG_FIELD_SHIFT(reg, field), \
+			  ip##_HWIP)
 
 #define RREG32_SOC15(ip, inst, reg) \
-	RREG32(adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg)
+	__RREG32_SOC15__(adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg, ip##_HWIP)
+
+#define RREG32_SOC15_IP(ip, reg) __RREG32_SOC15__(reg, ip##_HWIP)
 
 #define RREG32_SOC15_NO_KIQ(ip, inst, reg) \
-	RREG32_NO_KIQ(adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg)
+	((RLC_GC_EN(ip##_HWIP) && adev->gfx.rlc.funcs->rlcg_rreg) ? \
+	 adev->gfx.rlc.funcs->rlcg_rreg(adev, reg, ip##_HWIP) : \
+	 RREG32_NO_KIQ(reg, value))
 
 #define RREG32_SOC15_OFFSET(ip, inst, reg, offset) \
-	RREG32((adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg) + offset)
+	 __RREG32_SOC15__((adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg) + offset, ip##_HWIP)
 
 #define WREG32_SOC15(ip, inst, reg, value) \
-	WREG32((adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg), value)
+	 __WREG32_SOC15__((adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg), \
+			  value, ip##_HWIP)
+
+#define WREG32_SOC15_IP(ip, reg, value) \
+	 __WREG32_SOC15__(reg, value, ip##_HWIP)
 
 #define WREG32_SOC15_NO_KIQ(ip, inst, reg, value) \
-	WREG32_NO_KIQ((adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg), value)
+	((RLC_GC_EN(ip##_HWIP) && adev->gfx.rlc.funcs->rlcg_wreg) ? \
+	 adev->gfx.rlc.funcs->rlcg_wreg(adev, reg, value, ip##_HWIP) : \
+	 WREG32_NO_KIQ(reg, value))
 
 #define WREG32_SOC15_OFFSET(ip, inst, reg, offset, value) \
-	WREG32((adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg) + offset, value)
+	 __WREG32_SOC15__((adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg) + offset, \
+			  value, ip##_HWIP)
 
 #define SOC15_WAIT_ON_RREG(ip, inst, reg, expected_value, mask) \
 ({	int ret = 0;						\
@@ -77,12 +122,7 @@
 })
 
 #define WREG32_RLC(reg, value) \
-	do { \
-		if (adev->gfx.rlc.funcs->rlcg_wreg) \
-			adev->gfx.rlc.funcs->rlcg_wreg(adev, reg, value, 0); \
-		else \
-			WREG32(reg, value);	\
-	} while (0)
+	__WREG32_SOC15_RLC__(reg, value, GC_HWIP)
 
 #define WREG32_RLC_EX(prefix, reg, value) \
 	do {							\
@@ -108,24 +148,21 @@
 		}	\
 	} while (0)
 
+/* shadow the registers in the callback function */
 #define WREG32_SOC15_RLC_SHADOW(ip, inst, reg, value) \
-	WREG32_RLC((adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg), value)
+	__WREG32_SOC15_RLC__((adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg), value, GC_HWIP)
 
+/* for GC only */
 #define RREG32_RLC(reg) \
-	(adev->gfx.rlc.funcs->rlcg_rreg ? \
-		adev->gfx.rlc.funcs->rlcg_rreg(adev, reg, 0) : RREG32(reg))
-
-#define WREG32_RLC_NO_KIQ(reg, value) \
-	do { \
-		if (adev->gfx.rlc.funcs->rlcg_wreg) \
-			adev->gfx.rlc.funcs->rlcg_wreg(adev, reg, value, AMDGPU_REGS_NO_KIQ); \
-		else \
-			WREG32_NO_KIQ(reg, value);	\
-	} while (0)
+	__RREG32_SOC15_RLC__(reg, GC_HWIP)
+
+#define WREG32_RLC_NO_KIQ(reg, value, hwip) \
+	(((RLC_GC_EN(hwip) || RLC_MMHUB_EN(hwip, 1)) && adev->gfx.rlc.funcs->rlcg_wreg) ? \
+		adev->gfx.rlc.funcs->rlcg_wreg(adev, reg, value, hwip) : WREG32_NO_KIQ(reg, value))
 
-#define RREG32_RLC_NO_KIQ(reg) \
-	(adev->gfx.rlc.funcs->rlcg_rreg ? \
-		adev->gfx.rlc.funcs->rlcg_rreg(adev, reg, AMDGPU_REGS_NO_KIQ) : RREG32_NO_KIQ(reg))
+#define RREG32_RLC_NO_KIQ(reg, hwip) \
+	(((RLC_GC_EN(hwip) || RLC_MMHUB_EN(hwip, 0)) && adev->gfx.rlc.funcs->rlcg_rreg) ? \
+		adev->gfx.rlc.funcs->rlcg_rreg(adev, reg, hwip) : RREG32_NO_KIQ(reg))
 
 #define WREG32_SOC15_RLC_SHADOW_EX(prefix, ip, inst, reg, value) \
 	do {							\
@@ -146,12 +183,12 @@
 	} while (0)
 
 #define RREG32_SOC15_RLC(ip, inst, reg) \
-	RREG32_RLC(adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg)
+	__RREG32_SOC15_RLC__(adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg, ip##_HWIP)
 
 #define WREG32_SOC15_RLC(ip, inst, reg, value) \
 	do {							\
 		uint32_t target_reg = adev->reg_offset[ip##_HWIP][0][reg##_BASE_IDX] + reg;\
-		WREG32_RLC(target_reg, value); \
+		__WREG32_SOC15_RLC__(target_reg, value, ip##_HWIP); \
 	} while (0)
 
 #define WREG32_SOC15_RLC_EX(prefix, ip, inst, reg, value) \
@@ -161,14 +198,14 @@
 	} while (0)
 
 #define WREG32_FIELD15_RLC(ip, idx, reg, field, val)   \
-	WREG32_RLC((adev->reg_offset[ip##_HWIP][idx][mm##reg##_BASE_IDX] + mm##reg), \
-	(RREG32_RLC(adev->reg_offset[ip##_HWIP][idx][mm##reg##_BASE_IDX] + mm##reg) \
-	& ~REG_FIELD_MASK(reg, field)) | (val) << REG_FIELD_SHIFT(reg, field))
+	__WREG32_SOC15_RLC__((adev->reg_offset[ip##_HWIP][idx][mm##reg##_BASE_IDX] + mm##reg), \
+		     (__RREG32_SOC15_RLC__(adev->reg_offset[ip##_HWIP][idx][mm##reg##_BASE_IDX] + mm##reg, ip##_HWIP) \
+				 & ~REG_FIELD_MASK(reg, field)) | (val) << REG_FIELD_SHIFT(reg, field), ip##_HWIP)
 
 #define WREG32_SOC15_OFFSET_RLC(ip, inst, reg, offset, value) \
-	WREG32_RLC(((adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg) + offset), value)
+	__WREG32_SOC15_RLC__((adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg) + offset, value, ip##_HWIP)
 
 #define RREG32_SOC15_OFFSET_RLC(ip, inst, reg, offset) \
-	RREG32_RLC(((adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg) + offset))
+	__RREG32_SOC15_RLC__((adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg) + offset, ip##_HWIP)
 
 #endif
-- 
2.17.1

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

[PATCH v2 02/12] drm/amdgpu: Modify GC register access from MMIO to RLCG in file gfx_v10*

[Peng Ju Zhou]

In SRIOV environment, KMD should access GC registers
with RLCG if GC indirect access flag enabled.

Signed-off-by: Peng Ju Zhou <PengJu.Zhou@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c | 34 +++++++++++++-------------
 1 file changed, 17 insertions(+), 17 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index 9320d44a67bc..dcef4be66f07 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -4897,7 +4897,7 @@ static void gfx_v10_0_init_compute_vmid(struct amdgpu_device *adev)
 	for (i = adev->vm_manager.first_kfd_vmid; i < AMDGPU_NUM_VMID; i++) {
 		nv_grbm_select(adev, 0, 0, 0, i);
 		/* CP and shaders */
-		WREG32_SOC15(GC, 0, mmSH_MEM_CONFIG, DEFAULT_SH_MEM_CONFIG);
+		WREG32_SOC15_RLC(GC, 0, mmSH_MEM_CONFIG, DEFAULT_SH_MEM_CONFIG);
 		WREG32_SOC15(GC, 0, mmSH_MEM_BASES, sh_mem_bases);
 	}
 	nv_grbm_select(adev, 0, 0, 0, 0);
@@ -5154,10 +5154,10 @@ static void gfx_v10_0_rlc_enable_srm(struct amdgpu_device *adev)
 	uint32_t tmp;
 
 	/* enable Save Restore Machine */
-	tmp = RREG32(SOC15_REG_OFFSET(GC, 0, mmRLC_SRM_CNTL));
+	tmp = RREG32_SOC15(GC, 0, mmRLC_SRM_CNTL);
 	tmp |= RLC_SRM_CNTL__AUTO_INCR_ADDR_MASK;
 	tmp |= RLC_SRM_CNTL__SRM_ENABLE_MASK;
-	WREG32(SOC15_REG_OFFSET(GC, 0, mmRLC_SRM_CNTL), tmp);
+	WREG32_SOC15(GC, 0, mmRLC_SRM_CNTL, tmp);
 }
 
 static int gfx_v10_0_rlc_load_microcode(struct amdgpu_device *adev)
@@ -7849,12 +7849,12 @@ static int gfx_v10_0_update_gfx_clock_gating(struct amdgpu_device *adev,
 static void gfx_v10_0_update_spm_vmid(struct amdgpu_device *adev, unsigned vmid)
 {
 	u32 reg, data;
-
+	/* not for *_SOC15 */
 	reg = SOC15_REG_OFFSET(GC, 0, mmRLC_SPM_MC_CNTL);
 	if (amdgpu_sriov_is_pp_one_vf(adev))
 		data = RREG32_NO_KIQ(reg);
 	else
-		data = RREG32(reg);
+		data = RREG32_SOC15(GC, 0, mmRLC_SPM_MC_CNTL);
 
 	data &= ~RLC_SPM_MC_CNTL__RLC_SPM_VMID_MASK;
 	data |= (vmid & RLC_SPM_MC_CNTL__RLC_SPM_VMID_MASK) << RLC_SPM_MC_CNTL__RLC_SPM_VMID__SHIFT;
@@ -8594,16 +8594,16 @@ gfx_v10_0_set_gfx_eop_interrupt_state(struct amdgpu_device *adev,
 
 	switch (state) {
 	case AMDGPU_IRQ_STATE_DISABLE:
-		cp_int_cntl = RREG32(cp_int_cntl_reg);
+		cp_int_cntl = RREG32_SOC15_IP(GC, cp_int_cntl_reg);
 		cp_int_cntl = REG_SET_FIELD(cp_int_cntl, CP_INT_CNTL_RING0,
 					    TIME_STAMP_INT_ENABLE, 0);
-		WREG32(cp_int_cntl_reg, cp_int_cntl);
+		WREG32_SOC15_IP(GC, cp_int_cntl_reg, cp_int_cntl);
 		break;
 	case AMDGPU_IRQ_STATE_ENABLE:
-		cp_int_cntl = RREG32(cp_int_cntl_reg);
+		cp_int_cntl = RREG32_SOC15_IP(GC, cp_int_cntl_reg);
 		cp_int_cntl = REG_SET_FIELD(cp_int_cntl, CP_INT_CNTL_RING0,
 					    TIME_STAMP_INT_ENABLE, 1);
-		WREG32(cp_int_cntl_reg, cp_int_cntl);
+		WREG32_SOC15_IP(GC, cp_int_cntl_reg, cp_int_cntl);
 		break;
 	default:
 		break;
@@ -8647,16 +8647,16 @@ static void gfx_v10_0_set_compute_eop_interrupt_state(struct amdgpu_device *adev
 
 	switch (state) {
 	case AMDGPU_IRQ_STATE_DISABLE:
-		mec_int_cntl = RREG32(mec_int_cntl_reg);
+		mec_int_cntl = RREG32_SOC15_IP(GC, mec_int_cntl_reg);
 		mec_int_cntl = REG_SET_FIELD(mec_int_cntl, CP_ME1_PIPE0_INT_CNTL,
 					     TIME_STAMP_INT_ENABLE, 0);
-		WREG32(mec_int_cntl_reg, mec_int_cntl);
+		WREG32_SOC15_IP(GC, mec_int_cntl_reg, mec_int_cntl);
 		break;
 	case AMDGPU_IRQ_STATE_ENABLE:
-		mec_int_cntl = RREG32(mec_int_cntl_reg);
+		mec_int_cntl = RREG32_SOC15_IP(GC, mec_int_cntl_reg);
 		mec_int_cntl = REG_SET_FIELD(mec_int_cntl, CP_ME1_PIPE0_INT_CNTL,
 					     TIME_STAMP_INT_ENABLE, 1);
-		WREG32(mec_int_cntl_reg, mec_int_cntl);
+		WREG32_SOC15_IP(GC, mec_int_cntl_reg, mec_int_cntl);
 		break;
 	default:
 		break;
@@ -8852,20 +8852,20 @@ static int gfx_v10_0_kiq_set_interrupt_state(struct amdgpu_device *adev,
 					    GENERIC2_INT_ENABLE, 0);
 			WREG32_SOC15(GC, 0, mmCPC_INT_CNTL, tmp);
 
-			tmp = RREG32(target);
+			tmp = RREG32_SOC15_IP(GC, target);
 			tmp = REG_SET_FIELD(tmp, CP_ME2_PIPE0_INT_CNTL,
 					    GENERIC2_INT_ENABLE, 0);
-			WREG32(target, tmp);
+			WREG32_SOC15_IP(GC, target, tmp);
 		} else {
 			tmp = RREG32_SOC15(GC, 0, mmCPC_INT_CNTL);
 			tmp = REG_SET_FIELD(tmp, CPC_INT_CNTL,
 					    GENERIC2_INT_ENABLE, 1);
 			WREG32_SOC15(GC, 0, mmCPC_INT_CNTL, tmp);
 
-			tmp = RREG32(target);
+			tmp = RREG32_SOC15_IP(GC, target);
 			tmp = REG_SET_FIELD(tmp, CP_ME2_PIPE0_INT_CNTL,
 					    GENERIC2_INT_ENABLE, 1);
-			WREG32(target, tmp);
+			WREG32_SOC15_IP(GC, target, tmp);
 		}
 		break;
 	default:
-- 
2.17.1

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

[PATCH v2 03/12] drm/amdgpu: Modify GC register access from MMIO to RLCG in file kfd_v10*

[Peng Ju Zhou]

In SRIOV environment, KMD should access GC registers
with RLCG if GC indirect access flag enabled.

Signed-off-by: Peng Ju Zhou <PengJu.Zhou@amd.com>
---
 .../drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c    | 42 +++++++++----------
 1 file changed, 21 insertions(+), 21 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c
index 62aa1a6f64ed..491acdf92f73 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c
@@ -96,8 +96,8 @@ static void kgd_program_sh_mem_settings(struct kgd_dev *kgd, uint32_t vmid,
 
 	lock_srbm(kgd, 0, 0, 0, vmid);
 
-	WREG32(SOC15_REG_OFFSET(GC, 0, mmSH_MEM_CONFIG), sh_mem_config);
-	WREG32(SOC15_REG_OFFSET(GC, 0, mmSH_MEM_BASES), sh_mem_bases);
+	WREG32_SOC15(GC, 0, mmSH_MEM_CONFIG, sh_mem_config);
+	WREG32_SOC15(GC, 0, mmSH_MEM_BASES, sh_mem_bases);
 	/* APE1 no longer exists on GFX9 */
 
 	unlock_srbm(kgd);
@@ -161,7 +161,7 @@ static int kgd_init_interrupts(struct kgd_dev *kgd, uint32_t pipe_id)
 
 	lock_srbm(kgd, mec, pipe, 0, 0);
 
-	WREG32(SOC15_REG_OFFSET(GC, 0, mmCPC_INT_CNTL),
+	WREG32_SOC15(GC, 0, mmCPC_INT_CNTL,
 		CP_INT_CNTL_RING0__TIME_STAMP_INT_ENABLE_MASK |
 		CP_INT_CNTL_RING0__OPCODE_ERROR_INT_ENABLE_MASK);
 
@@ -239,13 +239,13 @@ static int kgd_hqd_load(struct kgd_dev *kgd, void *mqd, uint32_t pipe_id,
 
 	for (reg = hqd_base;
 	     reg <= SOC15_REG_OFFSET(GC, 0, mmCP_HQD_PQ_WPTR_HI); reg++)
-		WREG32(reg, mqd_hqd[reg - hqd_base]);
+		WREG32_SOC15_IP(GC, reg, mqd_hqd[reg - hqd_base]);
 
 
 	/* Activate doorbell logic before triggering WPTR poll. */
 	data = REG_SET_FIELD(m->cp_hqd_pq_doorbell_control,
 			     CP_HQD_PQ_DOORBELL_CONTROL, DOORBELL_EN, 1);
-	WREG32(SOC15_REG_OFFSET(GC, 0, mmCP_HQD_PQ_DOORBELL_CONTROL), data);
+	WREG32_SOC15(GC, 0, mmCP_HQD_PQ_DOORBELL_CONTROL, data);
 
 	if (wptr) {
 		/* Don't read wptr with get_user because the user
@@ -274,27 +274,27 @@ static int kgd_hqd_load(struct kgd_dev *kgd, void *mqd, uint32_t pipe_id,
 		guessed_wptr += m->cp_hqd_pq_wptr_lo & ~(queue_size - 1);
 		guessed_wptr += (uint64_t)m->cp_hqd_pq_wptr_hi << 32;
 
-		WREG32(SOC15_REG_OFFSET(GC, 0, mmCP_HQD_PQ_WPTR_LO),
+		WREG32_SOC15(GC, 0, mmCP_HQD_PQ_WPTR_LO,
 		       lower_32_bits(guessed_wptr));
-		WREG32(SOC15_REG_OFFSET(GC, 0, mmCP_HQD_PQ_WPTR_HI),
+		WREG32_SOC15(GC, 0, mmCP_HQD_PQ_WPTR_HI,
 		       upper_32_bits(guessed_wptr));
-		WREG32(SOC15_REG_OFFSET(GC, 0, mmCP_HQD_PQ_WPTR_POLL_ADDR),
+		WREG32_SOC15(GC, 0, mmCP_HQD_PQ_WPTR_POLL_ADDR,
 		       lower_32_bits((uint64_t)wptr));
-		WREG32(SOC15_REG_OFFSET(GC, 0, mmCP_HQD_PQ_WPTR_POLL_ADDR_HI),
+		WREG32_SOC15(GC, 0, mmCP_HQD_PQ_WPTR_POLL_ADDR_HI,
 		       upper_32_bits((uint64_t)wptr));
 		pr_debug("%s setting CP_PQ_WPTR_POLL_CNTL1 to %x\n", __func__,
 			 (uint32_t)get_queue_mask(adev, pipe_id, queue_id));
-		WREG32(SOC15_REG_OFFSET(GC, 0, mmCP_PQ_WPTR_POLL_CNTL1),
+		WREG32_SOC15(GC, 0, mmCP_PQ_WPTR_POLL_CNTL1,
 		       (uint32_t)get_queue_mask(adev, pipe_id, queue_id));
 	}
 
 	/* Start the EOP fetcher */
-	WREG32(SOC15_REG_OFFSET(GC, 0, mmCP_HQD_EOP_RPTR),
+	WREG32_SOC15(GC, 0, mmCP_HQD_EOP_RPTR,
 	       REG_SET_FIELD(m->cp_hqd_eop_rptr,
 			     CP_HQD_EOP_RPTR, INIT_FETCHER, 1));
 
 	data = REG_SET_FIELD(m->cp_hqd_active, CP_HQD_ACTIVE, ACTIVE, 1);
-	WREG32(SOC15_REG_OFFSET(GC, 0, mmCP_HQD_ACTIVE), data);
+	WREG32_SOC15(GC, 0, mmCP_HQD_ACTIVE, data);
 
 	release_queue(kgd);
 
@@ -365,7 +365,7 @@ static int kgd_hqd_dump(struct kgd_dev *kgd,
 		if (WARN_ON_ONCE(i >= HQD_N_REGS))	\
 			break;				\
 		(*dump)[i][0] = (addr) << 2;		\
-		(*dump)[i++][1] = RREG32(addr);		\
+		(*dump)[i++][1] = RREG32_SOC15_IP(GC, addr);		\
 	} while (0)
 
 	*dump = kmalloc(HQD_N_REGS*2*sizeof(uint32_t), GFP_KERNEL);
@@ -497,13 +497,13 @@ static bool kgd_hqd_is_occupied(struct kgd_dev *kgd, uint64_t queue_address,
 	uint32_t low, high;
 
 	acquire_queue(kgd, pipe_id, queue_id);
-	act = RREG32(SOC15_REG_OFFSET(GC, 0, mmCP_HQD_ACTIVE));
+	act = RREG32_SOC15(GC, 0, mmCP_HQD_ACTIVE);
 	if (act) {
 		low = lower_32_bits(queue_address >> 8);
 		high = upper_32_bits(queue_address >> 8);
 
-		if (low == RREG32(SOC15_REG_OFFSET(GC, 0, mmCP_HQD_PQ_BASE)) &&
-		   high == RREG32(SOC15_REG_OFFSET(GC, 0, mmCP_HQD_PQ_BASE_HI)))
+		if (low == RREG32_SOC15(GC, 0, mmCP_HQD_PQ_BASE) &&
+		   high == RREG32_SOC15(GC, 0, mmCP_HQD_PQ_BASE_HI))
 			retval = true;
 	}
 	release_queue(kgd);
@@ -621,11 +621,11 @@ static int kgd_hqd_destroy(struct kgd_dev *kgd, void *mqd,
 	preempt_enable();
 #endif
 
-	WREG32(SOC15_REG_OFFSET(GC, 0, mmCP_HQD_DEQUEUE_REQUEST), type);
+	WREG32_SOC15(GC, 0, mmCP_HQD_DEQUEUE_REQUEST, type);
 
 	end_jiffies = (utimeout * HZ / 1000) + jiffies;
 	while (true) {
-		temp = RREG32(SOC15_REG_OFFSET(GC, 0, mmCP_HQD_ACTIVE));
+		temp = RREG32_SOC15(GC, 0, mmCP_HQD_ACTIVE);
 		if (!(temp & CP_HQD_ACTIVE__ACTIVE_MASK))
 			break;
 		if (time_after(jiffies, end_jiffies)) {
@@ -716,8 +716,8 @@ static int kgd_wave_control_execute(struct kgd_dev *kgd,
 
 	mutex_lock(&adev->grbm_idx_mutex);
 
-	WREG32(SOC15_REG_OFFSET(GC, 0, mmGRBM_GFX_INDEX), gfx_index_val);
-	WREG32(SOC15_REG_OFFSET(GC, 0, mmSQ_CMD), sq_cmd);
+	WREG32_SOC15(GC, 0, mmGRBM_GFX_INDEX, gfx_index_val);
+	WREG32_SOC15(GC, 0, mmSQ_CMD, sq_cmd);
 
 	data = REG_SET_FIELD(data, GRBM_GFX_INDEX,
 		INSTANCE_BROADCAST_WRITES, 1);
@@ -726,7 +726,7 @@ static int kgd_wave_control_execute(struct kgd_dev *kgd,
 	data = REG_SET_FIELD(data, GRBM_GFX_INDEX,
 		SE_BROADCAST_WRITES, 1);
 
-	WREG32(SOC15_REG_OFFSET(GC, 0, mmGRBM_GFX_INDEX), data);
+	WREG32_SOC15(GC, 0, mmGRBM_GFX_INDEX, data);
 	mutex_unlock(&adev->grbm_idx_mutex);
 
 	return 0;
-- 
2.17.1

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

[PATCH v2 04/12] drm/amdgpu: Modify GC register access from MMIO to RLCG in file soc15.c

[Peng Ju Zhou]

In SRIOV environment, KMD should access GC registers
with RLCG if GC indirect access flag enabled.

Signed-off-by: Peng Ju Zhou <PengJu.Zhou@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/soc15.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index d80e12b80c7e..bbd6ec2277d7 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -632,7 +632,9 @@ void soc15_program_register_sequence(struct amdgpu_device *adev,
 		if (entry->and_mask == 0xffffffff) {
 			tmp = entry->or_mask;
 		} else {
-			tmp = RREG32(reg);
+			tmp = (entry->hwip == GC_HWIP) ?
+				RREG32_SOC15_IP(GC, reg) : RREG32(reg);
+
 			tmp &= ~(entry->and_mask);
 			tmp |= (entry->or_mask & entry->and_mask);
 		}
@@ -643,7 +645,8 @@ void soc15_program_register_sequence(struct amdgpu_device *adev,
 			reg == SOC15_REG_OFFSET(GC, 0, mmSH_MEM_CONFIG))
 			WREG32_RLC(reg, tmp);
 		else
-			WREG32(reg, tmp);
+			(entry->hwip == GC_HWIP) ?
+				WREG32_SOC15_IP(GC, reg, tmp) : WREG32(reg, tmp);
 
 	}
 
-- 
2.17.1

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

[PATCH v2 05/12] drm/amdgpu: Modify GC register access from MMIO to RLCG in file sdma_v5*

[Peng Ju Zhou]

In SRIOV environment, KMD should access GC registers
with RLCG if GC indirect access flag enabled.

Signed-off-by: Peng Ju Zhou <PengJu.Zhou@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c | 78 ++++++++++++++------------
 1 file changed, 42 insertions(+), 36 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
index 920fc6d4a127..0673c5700db6 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
@@ -324,9 +324,9 @@ static uint64_t sdma_v5_0_ring_get_wptr(struct amdgpu_ring *ring)
 		wptr = READ_ONCE(*((u64 *)&adev->wb.wb[ring->wptr_offs]));
 		DRM_DEBUG("wptr/doorbell before shift == 0x%016llx\n", wptr);
 	} else {
-		wptr = RREG32(sdma_v5_0_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR_HI));
+		wptr = RREG32_SOC15_IP(GC, sdma_v5_0_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR_HI));
 		wptr = wptr << 32;
-		wptr |= RREG32(sdma_v5_0_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR));
+		wptr |= RREG32_SOC15_IP(GC, sdma_v5_0_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR));
 		DRM_DEBUG("wptr before shift [%i] wptr == 0x%016llx\n", ring->me, wptr);
 	}
 
@@ -367,9 +367,9 @@ static void sdma_v5_0_ring_set_wptr(struct amdgpu_ring *ring)
 				lower_32_bits(ring->wptr << 2),
 				ring->me,
 				upper_32_bits(ring->wptr << 2));
-		WREG32(sdma_v5_0_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR),
+		WREG32_SOC15_IP(GC, sdma_v5_0_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR),
 			lower_32_bits(ring->wptr << 2));
-		WREG32(sdma_v5_0_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR_HI),
+		WREG32_SOC15_IP(GC, sdma_v5_0_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR_HI),
 			upper_32_bits(ring->wptr << 2));
 	}
 }
@@ -530,12 +530,12 @@ static void sdma_v5_0_gfx_stop(struct amdgpu_device *adev)
 		amdgpu_ttm_set_buffer_funcs_status(adev, false);
 
 	for (i = 0; i < adev->sdma.num_instances; i++) {
-		rb_cntl = RREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_CNTL));
+		rb_cntl = RREG32_SOC15_IP(GC, sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_CNTL));
 		rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_GFX_RB_CNTL, RB_ENABLE, 0);
-		WREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_CNTL), rb_cntl);
-		ib_cntl = RREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_IB_CNTL));
+		WREG32_SOC15_IP(GC, sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_CNTL), rb_cntl);
+		ib_cntl = RREG32_SOC15_IP(GC, sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_IB_CNTL));
 		ib_cntl = REG_SET_FIELD(ib_cntl, SDMA0_GFX_IB_CNTL, IB_ENABLE, 0);
-		WREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_IB_CNTL), ib_cntl);
+		WREG32_SOC15_IP(GC, sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_IB_CNTL), ib_cntl);
 	}
 }
 
@@ -596,11 +596,11 @@ static void sdma_v5_0_ctx_switch_enable(struct amdgpu_device *adev, bool enable)
 		}
 
 		if (enable && amdgpu_sdma_phase_quantum) {
-			WREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_PHASE0_QUANTUM),
+			WREG32_SOC15_IP(GC, sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_PHASE0_QUANTUM),
 			       phase_quantum);
-			WREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_PHASE1_QUANTUM),
+			WREG32_SOC15_IP(GC, sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_PHASE1_QUANTUM),
 			       phase_quantum);
-			WREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_PHASE2_QUANTUM),
+			WREG32_SOC15_IP(GC, sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_PHASE2_QUANTUM),
 			       phase_quantum);
 		}
 		if (!amdgpu_sriov_vf(adev))
@@ -667,58 +667,63 @@ static int sdma_v5_0_gfx_resume(struct amdgpu_device *adev)
 
 		/* Set ring buffer size in dwords */
 		rb_bufsz = order_base_2(ring->ring_size / 4);
-		rb_cntl = RREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_CNTL));
+		rb_cntl = RREG32_SOC15_IP(GC, sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_CNTL));
 		rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_GFX_RB_CNTL, RB_SIZE, rb_bufsz);
 #ifdef __BIG_ENDIAN
 		rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_GFX_RB_CNTL, RB_SWAP_ENABLE, 1);
 		rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_GFX_RB_CNTL,
 					RPTR_WRITEBACK_SWAP_ENABLE, 1);
 #endif
-		WREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_CNTL), rb_cntl);
+		WREG32_SOC15_IP(GC, sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_CNTL), rb_cntl);
 
 		/* Initialize the ring buffer's read and write pointers */
-		WREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_RPTR), 0);
-		WREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_RPTR_HI), 0);
-		WREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_WPTR), 0);
-		WREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_WPTR_HI), 0);
+		WREG32_SOC15_IP(GC, sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_RPTR), 0);
+		WREG32_SOC15_IP(GC, sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_RPTR_HI), 0);
+		WREG32_SOC15_IP(GC, sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_WPTR), 0);
+		WREG32_SOC15_IP(GC, sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_WPTR_HI), 0);
 
 		/* setup the wptr shadow polling */
 		wptr_gpu_addr = adev->wb.gpu_addr + (ring->wptr_offs * 4);
-		WREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_WPTR_POLL_ADDR_LO),
+		WREG32_SOC15_IP(GC, sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_WPTR_POLL_ADDR_LO),
 		       lower_32_bits(wptr_gpu_addr));
-		WREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_WPTR_POLL_ADDR_HI),
+		WREG32_SOC15_IP(GC, sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_WPTR_POLL_ADDR_HI),
 		       upper_32_bits(wptr_gpu_addr));
-		wptr_poll_cntl = RREG32(sdma_v5_0_get_reg_offset(adev, i,
+		wptr_poll_cntl = RREG32_SOC15_IP(GC, sdma_v5_0_get_reg_offset(adev, i,
 							 mmSDMA0_GFX_RB_WPTR_POLL_CNTL));
 		wptr_poll_cntl = REG_SET_FIELD(wptr_poll_cntl,
 					       SDMA0_GFX_RB_WPTR_POLL_CNTL,
 					       F32_POLL_ENABLE, 1);
-		WREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_WPTR_POLL_CNTL),
+		WREG32_SOC15_IP(GC, sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_WPTR_POLL_CNTL),
 		       wptr_poll_cntl);
 
 		/* set the wb address whether it's enabled or not */
-		WREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_RPTR_ADDR_HI),
+		WREG32_SOC15_IP(GC, sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_RPTR_ADDR_HI),
 		       upper_32_bits(adev->wb.gpu_addr + wb_offset) & 0xFFFFFFFF);
-		WREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_RPTR_ADDR_LO),
+		WREG32_SOC15_IP(GC, sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_RPTR_ADDR_LO),
 		       lower_32_bits(adev->wb.gpu_addr + wb_offset) & 0xFFFFFFFC);
 
 		rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_GFX_RB_CNTL, RPTR_WRITEBACK_ENABLE, 1);
 
-		WREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_BASE), ring->gpu_addr >> 8);
-		WREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_BASE_HI), ring->gpu_addr >> 40);
+		WREG32_SOC15_IP(GC, sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_BASE),
+		       ring->gpu_addr >> 8);
+		WREG32_SOC15_IP(GC, sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_BASE_HI),
+		       ring->gpu_addr >> 40);
 
 		ring->wptr = 0;
 
 		/* before programing wptr to a less value, need set minor_ptr_update first */
-		WREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_MINOR_PTR_UPDATE), 1);
+		WREG32_SOC15_IP(GC, sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_MINOR_PTR_UPDATE), 1);
 
 		if (!amdgpu_sriov_vf(adev)) { /* only bare-metal use register write for wptr */
-			WREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_WPTR), lower_32_bits(ring->wptr) << 2);
-			WREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_WPTR_HI), upper_32_bits(ring->wptr) << 2);
+			WREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_WPTR),
+			       lower_32_bits(ring->wptr) << 2);
+			WREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_WPTR_HI),
+			       upper_32_bits(ring->wptr) << 2);
 		}
 
-		doorbell = RREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_DOORBELL));
-		doorbell_offset = RREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_DOORBELL_OFFSET));
+		doorbell = RREG32_SOC15_IP(GC, sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_DOORBELL));
+		doorbell_offset = RREG32_SOC15_IP(GC, sdma_v5_0_get_reg_offset(adev, i,
+						mmSDMA0_GFX_DOORBELL_OFFSET));
 
 		if (ring->use_doorbell) {
 			doorbell = REG_SET_FIELD(doorbell, SDMA0_GFX_DOORBELL, ENABLE, 1);
@@ -727,8 +732,9 @@ static int sdma_v5_0_gfx_resume(struct amdgpu_device *adev)
 		} else {
 			doorbell = REG_SET_FIELD(doorbell, SDMA0_GFX_DOORBELL, ENABLE, 0);
 		}
-		WREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_DOORBELL), doorbell);
-		WREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_DOORBELL_OFFSET), doorbell_offset);
+		WREG32_SOC15_IP(GC, sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_DOORBELL), doorbell);
+		WREG32_SOC15_IP(GC, sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_DOORBELL_OFFSET),
+		       doorbell_offset);
 
 		adev->nbio.funcs->sdma_doorbell_range(adev, i, ring->use_doorbell,
 						      ring->doorbell_index, 20);
@@ -737,7 +743,7 @@ static int sdma_v5_0_gfx_resume(struct amdgpu_device *adev)
 			sdma_v5_0_ring_set_wptr(ring);
 
 		/* set minor_ptr_update to 0 after wptr programed */
-		WREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_MINOR_PTR_UPDATE), 0);
+		WREG32_SOC15_IP(GC, sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_MINOR_PTR_UPDATE), 0);
 
 		if (!amdgpu_sriov_vf(adev)) {
 			/* set utc l1 enable flag always to 1 */
@@ -771,15 +777,15 @@ static int sdma_v5_0_gfx_resume(struct amdgpu_device *adev)
 
 		/* enable DMA RB */
 		rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_GFX_RB_CNTL, RB_ENABLE, 1);
-		WREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_CNTL), rb_cntl);
+		WREG32_SOC15_IP(GC, sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_CNTL), rb_cntl);
 
-		ib_cntl = RREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_IB_CNTL));
+		ib_cntl = RREG32_SOC15_IP(GC, sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_IB_CNTL));
 		ib_cntl = REG_SET_FIELD(ib_cntl, SDMA0_GFX_IB_CNTL, IB_ENABLE, 1);
 #ifdef __BIG_ENDIAN
 		ib_cntl = REG_SET_FIELD(ib_cntl, SDMA0_GFX_IB_CNTL, IB_SWAP_ENABLE, 1);
 #endif
 		/* enable DMA IBs */
-		WREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_IB_CNTL), ib_cntl);
+		WREG32_SOC15_IP(GC, sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_IB_CNTL), ib_cntl);
 
 		ring->sched.ready = true;
 
-- 
2.17.1

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

[PATCH v2 06/12] drm/amdgpu: Modify GC register access from MMIO to RLCG in file nv.c

[Peng Ju Zhou]

In SRIOV environment, KMD should access GC registers
with RLCG if GC indirect access flag enabled.

Signed-off-by: Peng Ju Zhou <PengJu.Zhou@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/nv.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c
index 82a380be8368..f2f0caf560f9 100644
--- a/drivers/gpu/drm/amd/amdgpu/nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/nv.c
@@ -363,7 +363,7 @@ void nv_grbm_select(struct amdgpu_device *adev,
 	grbm_gfx_cntl = REG_SET_FIELD(grbm_gfx_cntl, GRBM_GFX_CNTL, VMID, vmid);
 	grbm_gfx_cntl = REG_SET_FIELD(grbm_gfx_cntl, GRBM_GFX_CNTL, QUEUEID, queue);
 
-	WREG32(SOC15_REG_OFFSET(GC, 0, mmGRBM_GFX_CNTL), grbm_gfx_cntl);
+	WREG32_SOC15(GC, 0, mmGRBM_GFX_CNTL, grbm_gfx_cntl);
 }
 
 static void nv_vga_set_state(struct amdgpu_device *adev, bool state)
-- 
2.17.1

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

[PATCH v2 07/12] drm/amdgpu: Modify GC register access from MMIO to RLCG in file amdgpu_gmc.c

[Peng Ju Zhou]

In SRIOV environment, KMD should access GC registers
with RLCG if GC indirect access flag enabled.

Signed-off-by: Peng Ju Zhou <PengJu.Zhou@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c |  9 +++++++--
 drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c  | 25 +++++++++++++++++--------
 2 files changed, 24 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
index dfa67c2255f2..06ca584c5d1b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
@@ -618,13 +618,18 @@ void amdgpu_gmc_set_vm_fault_masks(struct amdgpu_device *adev, int hub_type,
 	for (i = 0; i < 16; i++) {
 		reg = hub->vm_context0_cntl + hub->ctx_distance * i;
 
-		tmp = RREG32(reg);
+		tmp = (hub_type == AMDGPU_GFXHUB_0) ?
+			RREG32_SOC15_IP(GC, reg) :
+			RREG32_SOC15_IP(MMHUB, reg);
+
 		if (enable)
 			tmp |= hub->vm_cntx_cntl_vm_fault;
 		else
 			tmp &= ~hub->vm_cntx_cntl_vm_fault;
 
-		WREG32(reg, tmp);
+		(hub_type == AMDGPU_GFXHUB_0) ?
+			WREG32_SOC15_IP(GC, reg, tmp) :
+			WREG32_SOC15_IP(MMHUB, reg, tmp);
 	}
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
index 498b28a35f5b..c25541112663 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
@@ -229,6 +229,10 @@ static void gmc_v10_0_flush_vm_hub(struct amdgpu_device *adev, uint32_t vmid,
 	/* Use register 17 for GART */
 	const unsigned eng = 17;
 	unsigned int i;
+	unsigned char hub_ip = 0;
+
+	hub_ip = (vmhub == AMDGPU_GFXHUB_0) ?
+		   GC_HWIP : MMHUB_HWIP;
 
 	spin_lock(&adev->gmc.invalidate_lock);
 	/*
@@ -242,8 +246,9 @@ static void gmc_v10_0_flush_vm_hub(struct amdgpu_device *adev, uint32_t vmid,
 	if (use_semaphore) {
 		for (i = 0; i < adev->usec_timeout; i++) {
 			/* a read return value of 1 means semaphore acuqire */
-			tmp = RREG32_NO_KIQ(hub->vm_inv_eng0_sem +
-					    hub->eng_distance * eng);
+			tmp = RREG32_RLC_NO_KIQ(hub->vm_inv_eng0_sem +
+					 hub->eng_distance * eng, hub_ip);
+
 			if (tmp & 0x1)
 				break;
 			udelay(1);
@@ -253,7 +258,9 @@ static void gmc_v10_0_flush_vm_hub(struct amdgpu_device *adev, uint32_t vmid,
 			DRM_ERROR("Timeout waiting for sem acquire in VM flush!\n");
 	}
 
-	WREG32_NO_KIQ(hub->vm_inv_eng0_req + hub->eng_distance * eng, inv_req);
+	WREG32_RLC_NO_KIQ(hub->vm_inv_eng0_req +
+			  hub->eng_distance * eng,
+			  inv_req, hub_ip);
 
 	/*
 	 * Issue a dummy read to wait for the ACK register to be cleared
@@ -261,12 +268,14 @@ static void gmc_v10_0_flush_vm_hub(struct amdgpu_device *adev, uint32_t vmid,
 	 */
 	if ((vmhub == AMDGPU_GFXHUB_0) &&
 	    (adev->asic_type < CHIP_SIENNA_CICHLID))
-		RREG32_NO_KIQ(hub->vm_inv_eng0_req + hub->eng_distance * eng);
+		RREG32_RLC_NO_KIQ(hub->vm_inv_eng0_req +
+				  hub->eng_distance * eng, hub_ip);
 
 	/* Wait for ACK with a delay.*/
 	for (i = 0; i < adev->usec_timeout; i++) {
-		tmp = RREG32_NO_KIQ(hub->vm_inv_eng0_ack +
-				    hub->eng_distance * eng);
+		tmp = RREG32_RLC_NO_KIQ(hub->vm_inv_eng0_ack +
+				  hub->eng_distance * eng, hub_ip);
+
 		tmp &= 1 << vmid;
 		if (tmp)
 			break;
@@ -280,8 +289,8 @@ static void gmc_v10_0_flush_vm_hub(struct amdgpu_device *adev, uint32_t vmid,
 		 * add semaphore release after invalidation,
 		 * write with 0 means semaphore release
 		 */
-		WREG32_NO_KIQ(hub->vm_inv_eng0_sem +
-			      hub->eng_distance * eng, 0);
+		WREG32_RLC_NO_KIQ(hub->vm_inv_eng0_sem +
+				  hub->eng_distance * eng, 0, hub_ip);
 
 	spin_unlock(&adev->gmc.invalidate_lock);
 
-- 
2.17.1

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

[PATCH v2 08/12] drm/amdgpu: Modify MMHUB register access from MMIO to RLCG in file mmhub_v2*

[Peng Ju Zhou]

From: pengzhou <PengJu.Zhou@amd.com>

In SRIOV environment, KMD should access GC registers
with RLCG if GC indirect access flag enabled.

Signed-off-by: pengzhou <PengJu.Zhou@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c | 37 +++++++++++++------------
 1 file changed, 19 insertions(+), 18 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
index ac76081b91d5..e24225b3d42a 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
@@ -29,6 +29,7 @@
 #include "mmhub/mmhub_2_0_0_default.h"
 #include "navi10_enum.h"
 
+#include "gc/gc_10_1_0_offset.h"
 #include "soc15_common.h"
 
 #define mmMM_ATC_L2_MISC_CG_Sienna_Cichlid                      0x064d
@@ -165,11 +166,11 @@ static void mmhub_v2_0_setup_vm_pt_regs(struct amdgpu_device *adev, uint32_t vmi
 {
 	struct amdgpu_vmhub *hub = &adev->vmhub[AMDGPU_MMHUB_0];
 
-	WREG32_SOC15_OFFSET(MMHUB, 0, mmMMVM_CONTEXT0_PAGE_TABLE_BASE_ADDR_LO32,
+	WREG32_SOC15_OFFSET_RLC(MMHUB, 0, mmMMVM_CONTEXT0_PAGE_TABLE_BASE_ADDR_LO32,
 			    hub->ctx_addr_distance * vmid,
 			    lower_32_bits(page_table_base));
 
-	WREG32_SOC15_OFFSET(MMHUB, 0, mmMMVM_CONTEXT0_PAGE_TABLE_BASE_ADDR_HI32,
+	WREG32_SOC15_OFFSET_RLC(MMHUB, 0, mmMMVM_CONTEXT0_PAGE_TABLE_BASE_ADDR_HI32,
 			    hub->ctx_addr_distance * vmid,
 			    upper_32_bits(page_table_base));
 }
@@ -180,14 +181,14 @@ static void mmhub_v2_0_init_gart_aperture_regs(struct amdgpu_device *adev)
 
 	mmhub_v2_0_setup_vm_pt_regs(adev, 0, pt_base);
 
-	WREG32_SOC15(MMHUB, 0, mmMMVM_CONTEXT0_PAGE_TABLE_START_ADDR_LO32,
+	WREG32_SOC15_RLC(MMHUB, 0, mmMMVM_CONTEXT0_PAGE_TABLE_START_ADDR_LO32,
 		     (u32)(adev->gmc.gart_start >> 12));
-	WREG32_SOC15(MMHUB, 0, mmMMVM_CONTEXT0_PAGE_TABLE_START_ADDR_HI32,
+	WREG32_SOC15_RLC(MMHUB, 0, mmMMVM_CONTEXT0_PAGE_TABLE_START_ADDR_HI32,
 		     (u32)(adev->gmc.gart_start >> 44));
 
-	WREG32_SOC15(MMHUB, 0, mmMMVM_CONTEXT0_PAGE_TABLE_END_ADDR_LO32,
+	WREG32_SOC15_RLC(MMHUB, 0, mmMMVM_CONTEXT0_PAGE_TABLE_END_ADDR_LO32,
 		     (u32)(adev->gmc.gart_end >> 12));
-	WREG32_SOC15(MMHUB, 0, mmMMVM_CONTEXT0_PAGE_TABLE_END_ADDR_HI32,
+	WREG32_SOC15_RLC(MMHUB, 0, mmMMVM_CONTEXT0_PAGE_TABLE_END_ADDR_HI32,
 		     (u32)(adev->gmc.gart_end >> 44));
 }
 
@@ -197,9 +198,9 @@ static void mmhub_v2_0_init_system_aperture_regs(struct amdgpu_device *adev)
 	uint32_t tmp;
 
 	/* Program the AGP BAR */
-	WREG32_SOC15(MMHUB, 0, mmMMMC_VM_AGP_BASE, 0);
-	WREG32_SOC15(MMHUB, 0, mmMMMC_VM_AGP_BOT, adev->gmc.agp_start >> 24);
-	WREG32_SOC15(MMHUB, 0, mmMMMC_VM_AGP_TOP, adev->gmc.agp_end >> 24);
+	WREG32_SOC15_RLC(MMHUB, 0, mmMMMC_VM_AGP_BASE, 0);
+	WREG32_SOC15_RLC(MMHUB, 0, mmMMMC_VM_AGP_BOT, adev->gmc.agp_start >> 24);
+	WREG32_SOC15_RLC(MMHUB, 0, mmMMMC_VM_AGP_TOP, adev->gmc.agp_end >> 24);
 
 	if (!amdgpu_sriov_vf(adev)) {
 		/* Program the system aperture low logical page number. */
@@ -308,7 +309,7 @@ static void mmhub_v2_0_enable_system_domain(struct amdgpu_device *adev)
 	tmp = REG_SET_FIELD(tmp, MMVM_CONTEXT0_CNTL, PAGE_TABLE_DEPTH, 0);
 	tmp = REG_SET_FIELD(tmp, MMVM_CONTEXT0_CNTL,
 			    RETRY_PERMISSION_OR_INVALID_PAGE_FAULT, 0);
-	WREG32_SOC15(MMHUB, 0, mmMMVM_CONTEXT0_CNTL, tmp);
+	WREG32_SOC15_RLC(MMHUB, 0, mmMMVM_CONTEXT0_CNTL, tmp);
 }
 
 static void mmhub_v2_0_disable_identity_aperture(struct amdgpu_device *adev)
@@ -370,16 +371,16 @@ static void mmhub_v2_0_setup_vmid_config(struct amdgpu_device *adev)
 		tmp = REG_SET_FIELD(tmp, MMVM_CONTEXT1_CNTL,
 				    RETRY_PERMISSION_OR_INVALID_PAGE_FAULT,
 				    !adev->gmc.noretry);
-		WREG32_SOC15_OFFSET(MMHUB, 0, mmMMVM_CONTEXT1_CNTL,
+		WREG32_SOC15_OFFSET_RLC(MMHUB, 0, mmMMVM_CONTEXT1_CNTL,
 				    i * hub->ctx_distance, tmp);
-		WREG32_SOC15_OFFSET(MMHUB, 0, mmMMVM_CONTEXT1_PAGE_TABLE_START_ADDR_LO32,
+		WREG32_SOC15_OFFSET_RLC(MMHUB, 0, mmMMVM_CONTEXT1_PAGE_TABLE_START_ADDR_LO32,
 				    i * hub->ctx_addr_distance, 0);
-		WREG32_SOC15_OFFSET(MMHUB, 0, mmMMVM_CONTEXT1_PAGE_TABLE_START_ADDR_HI32,
+		WREG32_SOC15_OFFSET_RLC(MMHUB, 0, mmMMVM_CONTEXT1_PAGE_TABLE_START_ADDR_HI32,
 				    i * hub->ctx_addr_distance, 0);
-		WREG32_SOC15_OFFSET(MMHUB, 0, mmMMVM_CONTEXT1_PAGE_TABLE_END_ADDR_LO32,
+		WREG32_SOC15_OFFSET_RLC(MMHUB, 0, mmMMVM_CONTEXT1_PAGE_TABLE_END_ADDR_LO32,
 				    i * hub->ctx_addr_distance,
 				    lower_32_bits(adev->vm_manager.max_pfn - 1));
-		WREG32_SOC15_OFFSET(MMHUB, 0, mmMMVM_CONTEXT1_PAGE_TABLE_END_ADDR_HI32,
+		WREG32_SOC15_OFFSET_RLC(MMHUB, 0, mmMMVM_CONTEXT1_PAGE_TABLE_END_ADDR_HI32,
 				    i * hub->ctx_addr_distance,
 				    upper_32_bits(adev->vm_manager.max_pfn - 1));
 	}
@@ -391,9 +392,9 @@ static void mmhub_v2_0_program_invalidation(struct amdgpu_device *adev)
 	unsigned i;
 
 	for (i = 0; i < 18; ++i) {
-		WREG32_SOC15_OFFSET(MMHUB, 0, mmMMVM_INVALIDATE_ENG0_ADDR_RANGE_LO32,
+		WREG32_SOC15_OFFSET_RLC(MMHUB, 0, mmMMVM_INVALIDATE_ENG0_ADDR_RANGE_LO32,
 				    i * hub->eng_addr_distance, 0xffffffff);
-		WREG32_SOC15_OFFSET(MMHUB, 0, mmMMVM_INVALIDATE_ENG0_ADDR_RANGE_HI32,
+		WREG32_SOC15_OFFSET_RLC(MMHUB, 0, mmMMVM_INVALIDATE_ENG0_ADDR_RANGE_HI32,
 				    i * hub->eng_addr_distance, 0x1f);
 	}
 }
@@ -422,7 +423,7 @@ static void mmhub_v2_0_gart_disable(struct amdgpu_device *adev)
 
 	/* Disable all tables */
 	for (i = 0; i < AMDGPU_NUM_VMID; i++)
-		WREG32_SOC15_OFFSET(MMHUB, 0, mmMMVM_CONTEXT0_CNTL,
+		WREG32_SOC15_OFFSET_RLC(MMHUB, 0, mmMMVM_CONTEXT0_CNTL,
 				    i * hub->ctx_distance, 0);
 
 	/* Setup TLB control */
-- 
2.17.1

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

[PATCH v2 09/12] drm/amdgpu: Use PSP to program IH_RB_CNTL* registers

[Peng Ju Zhou]

use psp to program IH_RB_CNTL* if indirect access
for ih enabled in SRIOV environment.

Signed-off-by: Victor <Victor.Zhao@amd.com>
Signed-off-by: Peng Ju Zhou <PengJu.Zhou@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/navi10_ih.c | 19 +++++++++++++++++--
 drivers/gpu/drm/amd/amdgpu/nv.c        |  2 +-
 2 files changed, 18 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/navi10_ih.c b/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
index f4e4040bbd25..2e69cf8db072 100644
--- a/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
@@ -151,7 +151,14 @@ static int navi10_ih_toggle_ring_interrupts(struct amdgpu_device *adev,
 	/* enable_intr field is only valid in ring0 */
 	if (ih == &adev->irq.ih)
 		tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, ENABLE_INTR, (enable ? 1 : 0));
-	WREG32(ih_regs->ih_rb_cntl, tmp);
+	if (amdgpu_sriov_vf(adev) && amdgpu_sriov_reg_indirect_ih(adev)) {
+		if (psp_reg_program(&adev->psp, ih_regs->psp_reg_id, tmp)) {
+			DRM_ERROR("PSP program IH_RB_CNTL failed!\n");
+			return -ETIMEDOUT;
+		}
+	} else {
+		WREG32(ih_regs->ih_rb_cntl, tmp);
+	}
 
 	if (enable) {
 		ih->enabled = true;
@@ -261,7 +268,15 @@ static int navi10_ih_enable_ring(struct amdgpu_device *adev,
 		tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_ENABLE, 0);
 		tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, RB_FULL_DRAIN_ENABLE, 1);
 	}
-	WREG32(ih_regs->ih_rb_cntl, tmp);
+
+	if (amdgpu_sriov_vf(adev) && amdgpu_sriov_reg_indirect_ih(adev)) {
+		if (psp_reg_program(&adev->psp, ih_regs->psp_reg_id, tmp)) {
+			DRM_ERROR("PSP program IH_RB_CNTL failed!\n");
+			return -ETIMEDOUT;
+		}
+	} else {
+		WREG32(ih_regs->ih_rb_cntl, tmp);
+	}
 
 	if (ih == &adev->irq.ih) {
 		/* set the ih ring 0 writeback address whether it's enabled or not */
diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c
index f2f0caf560f9..f0ba64ceb67d 100644
--- a/drivers/gpu/drm/amd/amdgpu/nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/nv.c
@@ -737,8 +737,8 @@ int nv_set_ip_blocks(struct amdgpu_device *adev)
 	case CHIP_NAVI12:
 		amdgpu_device_ip_block_add(adev, &nv_common_ip_block);
 		amdgpu_device_ip_block_add(adev, &gmc_v10_0_ip_block);
-		amdgpu_device_ip_block_add(adev, &navi10_ih_ip_block);
 		amdgpu_device_ip_block_add(adev, &psp_v11_0_ip_block);
+		amdgpu_device_ip_block_add(adev, &navi10_ih_ip_block);
 		if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP)
 			amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block);
 		if (adev->enable_virtual_display || amdgpu_sriov_vf(adev))
-- 
2.17.1

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

[PATCH v2 10/12] drm/amdgpu: Skip the program of MMMC_VM_AGP_* in SRIOV

[Peng Ju Zhou]

KMD should not program these registers, the value were
defined in the host, so skip them in the SRIOV environment.

Signed-off-by: Peng Ju Zhou <PengJu.Zhou@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
index e24225b3d42a..422d106a650b 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
@@ -197,12 +197,12 @@ static void mmhub_v2_0_init_system_aperture_regs(struct amdgpu_device *adev)
 	uint64_t value;
 	uint32_t tmp;
 
-	/* Program the AGP BAR */
-	WREG32_SOC15_RLC(MMHUB, 0, mmMMMC_VM_AGP_BASE, 0);
-	WREG32_SOC15_RLC(MMHUB, 0, mmMMMC_VM_AGP_BOT, adev->gmc.agp_start >> 24);
-	WREG32_SOC15_RLC(MMHUB, 0, mmMMMC_VM_AGP_TOP, adev->gmc.agp_end >> 24);
-
 	if (!amdgpu_sriov_vf(adev)) {
+		/* Program the AGP BAR */
+		WREG32_SOC15_RLC(MMHUB, 0, mmMMMC_VM_AGP_BASE, 0);
+		WREG32_SOC15_RLC(MMHUB, 0, mmMMMC_VM_AGP_BOT, adev->gmc.agp_start >> 24);
+		WREG32_SOC15_RLC(MMHUB, 0, mmMMMC_VM_AGP_TOP, adev->gmc.agp_end >> 24);
+
 		/* Program the system aperture low logical page number. */
 		WREG32_SOC15(MMHUB, 0, mmMMMC_VM_SYSTEM_APERTURE_LOW_ADDR,
 			     min(adev->gmc.fb_start, adev->gmc.agp_start) >> 18);
-- 
2.17.1

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

[PATCH v2 11/12] drm/amdgpu: Skip the program of GRBM_CAM* in SRIOV

[Peng Ju Zhou]

KMD should not the program these registers,
so skip them in the SRIOV environment.

Signed-off-by: Peng Ju Zhou <PengJu.Zhou@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index dcef4be66f07..88d0828a6cb0 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -7090,6 +7090,9 @@ static void gfx_v10_0_setup_grbm_cam_remapping(struct amdgpu_device *adev)
 {
 	uint32_t data;
 
+	if (amdgpu_sriov_vf(adev))
+		return;
+
 	/* initialize cam_index to 0
 	 * index will auto-inc after each data writting */
 	WREG32_SOC15(GC, 0, mmGRBM_CAM_INDEX, 0);
-- 
2.17.1

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

[PATCH v2 12/12] drm/amdgpu: Refine the error report when flush tlb.

[Peng Ju Zhou]

there are 2 hubs to flush in the gmc, to make it easier
to debug when hub flush failed, refine the logs.

Signed-off-by: Peng Ju Zhou <PengJu.Zhou@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
index c25541112663..33cd487741f7 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
@@ -297,7 +297,8 @@ static void gmc_v10_0_flush_vm_hub(struct amdgpu_device *adev, uint32_t vmid,
 	if (i < adev->usec_timeout)
 		return;
 
-	DRM_ERROR("Timeout waiting for VM flush ACK!\n");
+	DRM_ERROR("Timeout waiting for VM flush hub: %s!\n",
+		  vmhub == AMDGPU_GFXHUB_0 ? "gfxhub" : "mmhub");
 }
 
 /**
-- 
2.17.1

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

Re: [PATCH v2 12/12] drm/amdgpu: Refine the error report when flush tlb.

[Christian König]

Am 29.04.21 um 12:26 schrieb Peng Ju Zhou:
> there are 2 hubs to flush in the gmc, to make it easier
> to debug when hub flush failed, refine the logs.

NAK, we can have more than just the two hubs.

See gmc_v9_0_process_interrupt:

         if (entry->client_id == SOC15_IH_CLIENTID_VMC) {
                 hub_name = "mmhub0";
                 hub = &adev->vmhub[AMDGPU_MMHUB_0];
         } else if (entry->client_id == SOC15_IH_CLIENTID_VMC1) {
                 hub_name = "mmhub1";
                 hub = &adev->vmhub[AMDGPU_MMHUB_1];
         } else {
                 hub_name = "gfxhub0";
                 hub = &adev->vmhub[AMDGPU_GFXHUB_0];
         }

Maybe put the name into the hub structure as well.

Christian.


>
> Signed-off-by: Peng Ju Zhou <PengJu.Zhou@amd.com>
> ---
>   drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c | 3 ++-
>   1 file changed, 2 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
> index c25541112663..33cd487741f7 100644
> --- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
> @@ -297,7 +297,8 @@ static void gmc_v10_0_flush_vm_hub(struct amdgpu_device *adev, uint32_t vmid,
>   	if (i < adev->usec_timeout)
>   		return;
>   
> -	DRM_ERROR("Timeout waiting for VM flush ACK!\n");
> +	DRM_ERROR("Timeout waiting for VM flush hub: %s!\n",
> +		  vmhub == AMDGPU_GFXHUB_0 ? "gfxhub" : "mmhub");
>   }
>   
>   /**

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

RE: [PATCH v2 12/12] drm/amdgpu: Refine the error report when flush tlb.

[Zhou, Peng Ju]

[AMD Official Use Only - Internal Distribution Only]

Hi Christian
Thanks for your review, I will change it.


---------------------------------------------------------------------- 
BW
Pengju Zhou



> -----Original Message-----
> From: Christian König <ckoenig.leichtzumerken@gmail.com>
> Sent: Thursday, April 29, 2021 7:29 PM
> To: Zhou, Peng Ju <PengJu.Zhou@amd.com>; amd-gfx@lists.freedesktop.org
> Subject: Re: [PATCH v2 12/12] drm/amdgpu: Refine the error report when
> flush tlb.
> 
> Am 29.04.21 um 12:26 schrieb Peng Ju Zhou:
> > there are 2 hubs to flush in the gmc, to make it easier to debug when
> > hub flush failed, refine the logs.
> 
> NAK, we can have more than just the two hubs.
> 
> See gmc_v9_0_process_interrupt:
> 
>          if (entry->client_id == SOC15_IH_CLIENTID_VMC) {
>                  hub_name = "mmhub0";
>                  hub = &adev->vmhub[AMDGPU_MMHUB_0];
>          } else if (entry->client_id == SOC15_IH_CLIENTID_VMC1) {
>                  hub_name = "mmhub1";
>                  hub = &adev->vmhub[AMDGPU_MMHUB_1];
>          } else {
>                  hub_name = "gfxhub0";
>                  hub = &adev->vmhub[AMDGPU_GFXHUB_0];
>          }
> 
> Maybe put the name into the hub structure as well.
> 
> Christian.
> 
> 
> >
> > Signed-off-by: Peng Ju Zhou <PengJu.Zhou@amd.com>
> > ---
> >   drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c | 3 ++-
> >   1 file changed, 2 insertions(+), 1 deletion(-)
> >
> > diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
> > b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
> > index c25541112663..33cd487741f7 100644
> > --- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
> > +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
> > @@ -297,7 +297,8 @@ static void gmc_v10_0_flush_vm_hub(struct
> amdgpu_device *adev, uint32_t vmid,
> >   	if (i < adev->usec_timeout)
> >   		return;
> >
> > -	DRM_ERROR("Timeout waiting for VM flush ACK!\n");
> > +	DRM_ERROR("Timeout waiting for VM flush hub: %s!\n",
> > +		  vmhub == AMDGPU_GFXHUB_0 ? "gfxhub" : "mmhub");
> >   }
> >
> >   /**
_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx