[PATCH] drm/amdgpu: Add node_id-to-die-name decoding for ih v7_1

[Alex Deucher <alexander.deucher@amd.com>]

From: Hawking Zhang <Hawking.Zhang@amd.com>

Converts node_id values into human-readable die
names to facilitate debugging

v2: squash in fix (Alex)

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ih.h |  6 ++++
 drivers/gpu/drm/amd/amdgpu/gmc_v12_1.c | 13 +++++++++
 drivers/gpu/drm/amd/amdgpu/ih_v7_0.c   | 40 +++++++++++++++++++++++++-
 3 files changed, 58 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.h
index f58b6be7fccc0..444437c300886 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.h
@@ -91,6 +91,12 @@ struct amdgpu_ih_funcs {
 	uint64_t (*decode_iv_ts)(struct amdgpu_ih_ring *ih, u32 rptr,
 				 signed int offset);
 	void (*set_rptr)(struct amdgpu_device *adev, struct amdgpu_ih_ring *ih);
+	/* Decode IH cookie node_id into a human-readable die name string.
+	 * Returns buf, or NULL if this IH version does not support node_id decoding.
+	 */
+	const char *(*node_id_to_die_name)(struct amdgpu_device *adev,
+					   unsigned int node_id,
+					   char *buf, size_t size);
 };
 
 #define amdgpu_ih_get_wptr(adev, ih) (adev)->irq.ih_funcs->get_wptr((adev), (ih))
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v12_1.c b/drivers/gpu/drm/amd/amdgpu/gmc_v12_1.c
index 7ea7b9c30bca9..855cd29cbffaa 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v12_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v12_1.c
@@ -112,6 +112,8 @@ static int gmc_v12_1_process_interrupt(struct amdgpu_device *adev,
 	const char *hub_name;
 	int ret, xcc_id = 0;
 	uint32_t status = 0;
+	const char *die_name;
+	char die_name_buf[32];
 	u64 addr;
 
 	node_id = entry->node_id;
@@ -201,6 +203,17 @@ static int gmc_v12_1_process_interrupt(struct amdgpu_device *adev,
 	dev_err(adev->dev, "  in page starting at address 0x%016llx from IH client %d (%s)\n",
 		addr, entry->client_id, soc_v1_0_ih_clientid_name[entry->client_id]);
 
+	if (adev->irq.ih_funcs &&
+	    adev->irq.ih_funcs->node_id_to_die_name) {
+		die_name = adev->irq.ih_funcs->node_id_to_die_name(adev, node_id,
+								   die_name_buf,
+								   sizeof(die_name_buf));
+		if (die_name)
+			dev_err(adev->dev,
+				"  cookie node_id %d fault from die %s\n",
+				node_id, die_name);
+	}
+
 	if (amdgpu_sriov_vf(adev))
 		return 0;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/ih_v7_0.c b/drivers/gpu/drm/amd/amdgpu/ih_v7_0.c
index 1fbe904f4223b..6de9e87e04e1a 100644
--- a/drivers/gpu/drm/amd/amdgpu/ih_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/ih_v7_0.c
@@ -798,6 +798,43 @@ static void ih_v7_0_get_clockgating_state(struct amdgpu_ip_block *ip_block, u64
 	return;
 }
 
+/*
+ * ih_v7_0_node_id_to_die_name - Decode IH cookie node_id to a die name string
+ *
+ * Currently, only applies to IH v7_1. For other IH versions returns NULL.
+ *
+ * IH v7_1 node_id encoding:
+ * node_id[N:3] = MID index
+ * node_id[2:0] = sub-slot: 0=MID, 1=AID, 2-5=AID.XCD, 6-7=RSV
+ */
+static const char *ih_v7_0_node_id_to_die_name(struct amdgpu_device *adev,
+					       unsigned int node_id,
+					       char *buf, size_t size)
+{
+	int mid_id, sub_slot;
+
+	/* Node ID to die name decoding is only defined for IH v7_1 currenlty. */
+	if (amdgpu_ip_version(adev, OSSSYS_HWIP, 0) != IP_VERSION(7, 1, 0))
+		return NULL;
+
+	mid_id = node_id >> 3;
+	sub_slot = node_id & 0x7;
+
+	if (mid_id > 1)
+		return "UNKNOWN";
+
+	if (sub_slot == 0)
+		snprintf(buf, size, "MID%d", mid_id);
+	else if (sub_slot == 1)
+		snprintf(buf, size, "AID%d", mid_id);
+	else if (sub_slot <= 5)
+		snprintf(buf, size, "AID%d.XCD%d", mid_id, sub_slot - 2);
+	else
+		snprintf(buf, size, "RSV");
+
+	return buf;
+}
+
 static const struct amd_ip_funcs ih_v7_0_ip_funcs = {
 	.name = "ih_v7_0",
 	.early_init = ih_v7_0_early_init,
@@ -819,7 +856,8 @@ static const struct amdgpu_ih_funcs ih_v7_0_funcs = {
 	.get_wptr = ih_v7_0_get_wptr,
 	.decode_iv = amdgpu_ih_decode_iv_helper,
 	.decode_iv_ts = amdgpu_ih_decode_iv_ts_helper,
-	.set_rptr = ih_v7_0_set_rptr
+	.set_rptr = ih_v7_0_set_rptr,
+	.node_id_to_die_name = ih_v7_0_node_id_to_die_name,
 };
 
 static void ih_v7_0_set_interrupt_funcs(struct amdgpu_device *adev)
-- 
2.53.0