[PATCH v1 1/2] drm/amdgpu: Add sdma_v5_2 ip dump for devcoredump

Sunil Khatri sunil.khatri at amd.com
Fri Jul 12 12:23:16 UTC 2024


Add ip dump for sdma_v5_2 for devcoredump for all
instances of sdma.

Signed-off-by: Sunil Khatri <sunil.khatri at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h |  1 +
 drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c   | 82 ++++++++++++++++++++++++
 2 files changed, 83 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h
index d3706a484870..087ce0f6fa07 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h
@@ -115,6 +115,7 @@ struct amdgpu_sdma {
 	bool			has_page_queue;
 	struct ras_common_if	*ras_if;
 	struct amdgpu_sdma_ras	*ras;
+	uint32_t		*ip_dump;
 };
 
 /*
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
index cc9e961f0078..05a13086405b 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
@@ -60,6 +60,55 @@ MODULE_FIRMWARE("amdgpu/sdma_5_2_7.bin");
 #define SDMA0_HYP_DEC_REG_END 0x5893
 #define SDMA1_HYP_DEC_REG_OFFSET 0x20
 
+static const struct amdgpu_hwip_reg_entry sdma_reg_list_5_2[] = {
+	SOC15_REG_ENTRY_STR(GC, 0, mmSDMA0_STATUS_REG),
+	SOC15_REG_ENTRY_STR(GC, 0, mmSDMA0_STATUS1_REG),
+	SOC15_REG_ENTRY_STR(GC, 0, mmSDMA0_STATUS2_REG),
+	SOC15_REG_ENTRY_STR(GC, 0, mmSDMA0_STATUS3_REG),
+	SOC15_REG_ENTRY_STR(GC, 0, mmSDMA0_UCODE_CHECKSUM),
+	SOC15_REG_ENTRY_STR(GC, 0, mmSDMA0_RB_RPTR_FETCH_HI),
+	SOC15_REG_ENTRY_STR(GC, 0, mmSDMA0_RB_RPTR_FETCH),
+	SOC15_REG_ENTRY_STR(GC, 0, mmSDMA0_UTCL1_RD_STATUS),
+	SOC15_REG_ENTRY_STR(GC, 0, mmSDMA0_UTCL1_WR_STATUS),
+	SOC15_REG_ENTRY_STR(GC, 0, mmSDMA0_UTCL1_RD_XNACK0),
+	SOC15_REG_ENTRY_STR(GC, 0, mmSDMA0_UTCL1_RD_XNACK1),
+	SOC15_REG_ENTRY_STR(GC, 0, mmSDMA0_UTCL1_WR_XNACK0),
+	SOC15_REG_ENTRY_STR(GC, 0, mmSDMA0_UTCL1_WR_XNACK1),
+	SOC15_REG_ENTRY_STR(GC, 0, mmSDMA0_GFX_RB_CNTL),
+	SOC15_REG_ENTRY_STR(GC, 0, mmSDMA0_GFX_RB_RPTR),
+	SOC15_REG_ENTRY_STR(GC, 0, mmSDMA0_GFX_RB_RPTR_HI),
+	SOC15_REG_ENTRY_STR(GC, 0, mmSDMA0_GFX_RB_WPTR),
+	SOC15_REG_ENTRY_STR(GC, 0, mmSDMA0_GFX_RB_WPTR_HI),
+	SOC15_REG_ENTRY_STR(GC, 0, mmSDMA0_GFX_IB_OFFSET),
+	SOC15_REG_ENTRY_STR(GC, 0, mmSDMA0_GFX_IB_BASE_LO),
+	SOC15_REG_ENTRY_STR(GC, 0, mmSDMA0_GFX_IB_BASE_HI),
+	SOC15_REG_ENTRY_STR(GC, 0, mmSDMA0_GFX_IB_CNTL),
+	SOC15_REG_ENTRY_STR(GC, 0, mmSDMA0_GFX_IB_RPTR),
+	SOC15_REG_ENTRY_STR(GC, 0, mmSDMA0_GFX_IB_SUB_REMAIN),
+	SOC15_REG_ENTRY_STR(GC, 0, mmSDMA0_GFX_DUMMY_REG),
+	SOC15_REG_ENTRY_STR(GC, 0, mmSDMA0_PAGE_RB_CNTL),
+	SOC15_REG_ENTRY_STR(GC, 0, mmSDMA0_PAGE_RB_RPTR),
+	SOC15_REG_ENTRY_STR(GC, 0, mmSDMA0_PAGE_RB_RPTR_HI),
+	SOC15_REG_ENTRY_STR(GC, 0, mmSDMA0_PAGE_RB_WPTR),
+	SOC15_REG_ENTRY_STR(GC, 0, mmSDMA0_PAGE_RB_WPTR_HI),
+	SOC15_REG_ENTRY_STR(GC, 0, mmSDMA0_PAGE_IB_OFFSET),
+	SOC15_REG_ENTRY_STR(GC, 0, mmSDMA0_PAGE_IB_BASE_LO),
+	SOC15_REG_ENTRY_STR(GC, 0, mmSDMA0_PAGE_IB_BASE_HI),
+	SOC15_REG_ENTRY_STR(GC, 0, mmSDMA0_PAGE_DUMMY_REG),
+	SOC15_REG_ENTRY_STR(GC, 0, mmSDMA0_RLC0_RB_CNTL),
+	SOC15_REG_ENTRY_STR(GC, 0, mmSDMA0_RLC0_RB_RPTR),
+	SOC15_REG_ENTRY_STR(GC, 0, mmSDMA0_RLC0_RB_RPTR_HI),
+	SOC15_REG_ENTRY_STR(GC, 0, mmSDMA0_RLC0_RB_WPTR),
+	SOC15_REG_ENTRY_STR(GC, 0, mmSDMA0_RLC0_RB_WPTR_HI),
+	SOC15_REG_ENTRY_STR(GC, 0, mmSDMA0_RLC0_IB_OFFSET),
+	SOC15_REG_ENTRY_STR(GC, 0, mmSDMA0_RLC0_IB_BASE_LO),
+	SOC15_REG_ENTRY_STR(GC, 0, mmSDMA0_RLC0_IB_BASE_HI),
+	SOC15_REG_ENTRY_STR(GC, 0, mmSDMA0_RLC0_DUMMY_REG),
+	SOC15_REG_ENTRY_STR(GC, 0, mmSDMA0_INT_STATUS),
+	SOC15_REG_ENTRY_STR(GC, 0, mmSDMA0_VM_CNTL),
+	SOC15_REG_ENTRY_STR(GC, 0, mmGRBM_STATUS2)
+};
+
 static void sdma_v5_2_set_ring_funcs(struct amdgpu_device *adev);
 static void sdma_v5_2_set_buffer_funcs(struct amdgpu_device *adev);
 static void sdma_v5_2_set_vm_pte_funcs(struct amdgpu_device *adev);
@@ -1214,6 +1263,8 @@ static int sdma_v5_2_sw_init(void *handle)
 	struct amdgpu_ring *ring;
 	int r, i;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	uint32_t reg_count = ARRAY_SIZE(sdma_reg_list_5_2);
+	uint32_t *ptr;
 
 	/* SDMA trap event */
 	for (i = 0; i < adev->sdma.num_instances; i++) {
@@ -1245,6 +1296,13 @@ static int sdma_v5_2_sw_init(void *handle)
 			return r;
 	}
 
+	/* Allocate memory for SDMA IP Dump buffer */
+	ptr = kcalloc(adev->sdma.num_instances * reg_count, sizeof(uint32_t), GFP_KERNEL);
+	if (ptr)
+		adev->sdma.ip_dump = ptr;
+	else
+		DRM_ERROR("Failed to allocated memory for SDMA IP Dump\n");
+
 	return r;
 }
 
@@ -1258,6 +1316,8 @@ static int sdma_v5_2_sw_fini(void *handle)
 
 	amdgpu_sdma_destroy_inst_ctx(adev, true);
 
+	kfree(adev->sdma.ip_dump);
+
 	return 0;
 }
 
@@ -1662,6 +1722,27 @@ static void sdma_v5_2_ring_end_use(struct amdgpu_ring *ring)
 	amdgpu_gfx_off_ctrl(adev, true);
 }
 
+static void sdma_v5_2_dump_ip_state(void *handle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	int i, j;
+	uint32_t instance_offset;
+	uint32_t reg_count = ARRAY_SIZE(sdma_reg_list_5_2);
+
+	if (adev->sdma.ip_dump == NULL)
+		return;
+
+	amdgpu_gfx_off_ctrl(adev, false);
+	for (i = 0; i < adev->sdma.num_instances; i++) {
+		instance_offset = i * reg_count;
+		for (j = 0; j < reg_count; j++)
+			adev->sdma.ip_dump[instance_offset + j] =
+				RREG32(sdma_v5_2_get_reg_offset(
+					adev, i, sdma_reg_list_5_2[j].reg_offset));
+	}
+	amdgpu_gfx_off_ctrl(adev, true);
+}
+
 const struct amd_ip_funcs sdma_v5_2_ip_funcs = {
 	.name = "sdma_v5_2",
 	.early_init = sdma_v5_2_early_init,
@@ -1678,6 +1759,7 @@ const struct amd_ip_funcs sdma_v5_2_ip_funcs = {
 	.set_clockgating_state = sdma_v5_2_set_clockgating_state,
 	.set_powergating_state = sdma_v5_2_set_powergating_state,
 	.get_clockgating_state = sdma_v5_2_get_clockgating_state,
+	.dump_ip_state = sdma_v5_2_dump_ip_state,
 };
 
 static const struct amdgpu_ring_funcs sdma_v5_2_ring_funcs = {
-- 
2.34.1



More information about the amd-gfx mailing list