Merge tag 'amd-drm-next-5.7-2020-02-26' of git://people.freedesktop.org/~agd5f/linux into drm-next

amd-drm-next-5.7-2020-02-26:

amdgpu:
- Rework VM update handling in preparation for HMM support
- HDCP srm support
- PSR fixes
- DC watermark fixes
- OLED panel support
- SR-IOV fixes
- BACO fixes
- Optimize debugging vram access
- RAS fixes
- Use BACO for runtime pm
- HDCP fixes
- XGMI fixes
- DDC fixes
- DC clock programming optimizations and fixes
- PSP fw loading sequence updates
- Drop DRIVER_USE_AGP
- Remove legacy drm load and unload callbacks

amdkfd:
- Add runtime pm support

radeon:
- Drop DRIVER_USE_AGP

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Alex Deucher <alexdeucher@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200227043142.4075-1-alexander.deucher@amd.com

1 files changed, 37 insertions, 16 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index cef94e2169fe..930633a0ed64 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -31,6 +31,7 @@
 #include "amdgpu.h"
 #include "amdgpu_ras.h"
 #include "amdgpu_atomfirmware.h"
+#include "amdgpu_xgmi.h"
 #include "ivsrcid/nbio/irqsrcs_nbif_7_4.h"
 
 const char *ras_error_string[] = {
@@ -742,20 +743,6 @@ int amdgpu_ras_error_query(struct amdgpu_device *adev,
 	return 0;
 }
 
-uint64_t get_xgmi_relative_phy_addr(struct amdgpu_device *adev, uint64_t addr)
-{
-	uint32_t df_inst_id;
-
-	if ((!adev->df.funcs)                 ||
-	    (!adev->df.funcs->get_df_inst_id) ||
-	    (!adev->df.funcs->get_dram_base_addr))
-		return addr;
-
-	df_inst_id = adev->df.funcs->get_df_inst_id(adev);
-
-	return addr + adev->df.funcs->get_dram_base_addr(adev, df_inst_id);
-}
-
 /* wrapper of psp_ras_trigger_error */
 int amdgpu_ras_error_inject(struct amdgpu_device *adev,
 		struct ras_inject_if *info)
@@ -775,8 +762,9 @@ int amdgpu_ras_error_inject(struct amdgpu_device *adev,
 
 	/* Calculate XGMI relative offset */
 	if (adev->gmc.xgmi.num_physical_nodes > 1) {
-		block_info.address = get_xgmi_relative_phy_addr(adev,
-								block_info.address);
+		block_info.address =
+			amdgpu_xgmi_get_relative_phy_addr(adev,
+							  block_info.address);
 	}
 
 	switch (info->head.block) {
@@ -1319,6 +1307,33 @@ static int amdgpu_ras_interrupt_remove_all(struct amdgpu_device *adev)
 }
 /* ih end */
 
+/* traversal all IPs except NBIO to query error counter */
+static void amdgpu_ras_log_on_err_counter(struct amdgpu_device *adev)
+{
+	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
+	struct ras_manager *obj;
+
+	if (!con)
+		return;
+
+	list_for_each_entry(obj, &con->head, node) {
+		struct ras_query_if info = {
+			.head = obj->head,
+		};
+
+		/*
+		 * PCIE_BIF IP has one different isr by ras controller
+		 * interrupt, the specific ras counter query will be
+		 * done in that isr. So skip such block from common
+		 * sync flood interrupt isr calling.
+		 */
+		if (info.head.block == AMDGPU_RAS_BLOCK__PCIE_BIF)
+			continue;
+
+		amdgpu_ras_error_query(adev, &info);
+	}
+}
+
 /* recovery begin */
 
 /* return 0 on success.
@@ -1373,6 +1388,12 @@ static void amdgpu_ras_do_recovery(struct work_struct *work)
 	struct amdgpu_ras *ras =
 		container_of(work, struct amdgpu_ras, recovery_work);
 
+	/*
+	 * Query and print non zero error counter per IP block for
+	 * awareness before recovering GPU.
+	 */
+	amdgpu_ras_log_on_err_counter(ras->adev);
+
 	if (amdgpu_device_should_recover_gpu(ras->adev))
 		amdgpu_device_gpu_recover(ras->adev, 0);
 	atomic_set(&ras->in_recovery, 0);