[PATCH 2/3] drm/amdgpu: set poison supported flag for RAS (v2)

[Zhang, Hawking]

[AMD Official Use Only]

Might be better call the function is_poison_mode_supported. Other than that the series is

Reviewed-by: Hawking Zhang <Hawking.Zhang at amd.com>

-----Original Message-----
From: Zhou1, Tao <Tao.Zhou1 at amd.com> 
Sent: Wednesday, September 22, 2021 18:33
To: amd-gfx at lists.freedesktop.org; Zhang, Hawking <Hawking.Zhang at amd.com>; Clements, John <John.Clements at amd.com>; Yang, Stanley <Stanley.Yang at amd.com>
Cc: Zhou1, Tao <Tao.Zhou1 at amd.com>
Subject: [PATCH 2/3] drm/amdgpu: set poison supported flag for RAS (v2)

Add RAS poison supported flag and tell PSP RAS TA about the info.

v2: rename poison_mode to poison_supported, we can also disable poison mode even we support it.
    print poison_supported value if ras feature enablement fails.

Signed-off-by: Tao Zhou <tao.zhou1 at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c |  4 ++--  drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 32 +++++++++++++++++++++++--  drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h |  5 ++++
 3 files changed, 37 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 7d09b28889af..c5cf84829ea8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -1442,9 +1442,9 @@ static int psp_ras_initialize(struct psp_context *psp)
 	ras_cmd = (struct ta_ras_shared_memory *)psp->ras_context.context.mem_context.shared_buf;
 	memset(ras_cmd, 0, sizeof(struct ta_ras_shared_memory));
 
-	if (psp->adev->gmc.xgmi.connected_to_cpu)
+	if (amdgpu_ras_is_poison_supported(adev))
 		ras_cmd->ras_in_message.init_flags.poison_mode_en = 1;
-	else
+	if (!adev->gmc.xgmi.connected_to_cpu)
 		ras_cmd->ras_in_message.init_flags.dgpu_mode = 1;
 
 	ret = psp_ras_load(psp);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 912ea1f9fd04..5b362e944541 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -710,10 +710,10 @@ int amdgpu_ras_feature_enable(struct amdgpu_device *adev,
 	if (!amdgpu_ras_intr_triggered()) {
 		ret = psp_ras_enable_features(&adev->psp, info, enable);
 		if (ret) {
-			dev_err(adev->dev, "ras %s %s failed %d\n",
+			dev_err(adev->dev, "ras %s %s failed poison:%d ret:%d\n",
 				enable ? "enable":"disable",
 				get_ras_block_str(head),
-				ret);
+				amdgpu_ras_is_poison_supported(adev), ret);
 			goto out;
 		}
 	}
@@ -2251,6 +2251,7 @@ int amdgpu_ras_init(struct amdgpu_device *adev)  {
 	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
 	int r;
+	bool df_poison, umc_poison;
 
 	if (con)
 		return 0;
@@ -2321,6 +2322,23 @@ int amdgpu_ras_init(struct amdgpu_device *adev)
 			goto release_con;
 	}
 
+	/* Init poison supported flag, the default value is false */
+	if (adev->df.funcs &&
+	    adev->df.funcs->query_ras_poison_mode &&
+	    adev->umc.ras_funcs &&
+	    adev->umc.ras_funcs->query_ras_poison_mode) {
+		df_poison =
+			adev->df.funcs->query_ras_poison_mode(adev);
+		umc_poison =
+			adev->umc.ras_funcs->query_ras_poison_mode(adev);
+		/* Only poison is set in both DF and UMC, we can support it */
+		if (df_poison && umc_poison)
+			con->poison_supported = true;
+		else if (df_poison != umc_poison)
+			dev_warn(adev->dev, "Poison setting is inconsistent in DF/UMC(%d:%d)!\n",
+					df_poison, umc_poison);
+	}
+
 	if (amdgpu_ras_fs_init(adev)) {
 		r = -EINVAL;
 		goto release_con;
@@ -2364,6 +2382,16 @@ static int amdgpu_persistent_edc_harvesting(struct amdgpu_device *adev,
 	return 0;
 }
 
+bool amdgpu_ras_is_poison_supported(struct amdgpu_device *adev) {
+       struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
+
+       if (!con)
+               return false;
+
+       return con->poison_supported;
+}
+
 /* helper function to handle common stuff in ip late init phase */  int amdgpu_ras_late_init(struct amdgpu_device *adev,
 			 struct ras_common_if *ras_block,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
index ec42e9873aaa..d6377e1ad20a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
@@ -352,6 +352,9 @@ struct amdgpu_ras {
 	/* disable ras error count harvest in recovery */
 	bool disable_ras_err_cnt_harvest;
 
+	/* is poison mode supported */
+	bool poison_supported;
+
 	/* RAS count errors delayed work */
 	struct delayed_work ras_counte_delay_work;
 	atomic_t ras_ue_count;
@@ -649,4 +652,6 @@ int amdgpu_persistent_edc_harvesting_supported(struct amdgpu_device *adev);
 
 const char *get_ras_block_str(struct ras_common_if *ras_block);
 
+bool amdgpu_ras_is_poison_supported(struct amdgpu_device *adev);
+
 #endif
--
2.17.1