Backmerge tag 'v6.7-rc5' into drm-next

Linux 6.7-rc5

Alex requested this for some amdkfd work relying on the symbols exports.

Signed-off-by: Dave Airlie <airlied@redhat.com>

6 files changed, 44 insertions, 13 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 6c0cf64d465a..138c7b37af69 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3861,10 +3861,6 @@ static void amdgpu_device_set_mcbp(struct amdgpu_device *adev)
 		adev->gfx.mcbp = true;
 	else if (amdgpu_mcbp == 0)
 		adev->gfx.mcbp = false;
-	else if ((amdgpu_ip_version(adev, GC_HWIP, 0) >= IP_VERSION(9, 0, 0)) &&
-		 (amdgpu_ip_version(adev, GC_HWIP, 0) < IP_VERSION(10, 0, 0)) &&
-		 adev->gfx.num_gfx_rings)
-		adev->gfx.mcbp = true;
 
 	if (amdgpu_sriov_vf(adev))
 		adev->gfx.mcbp = true;
@@ -4604,6 +4600,8 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon)
 	if (r)
 		return r;
 
+	amdgpu_ttm_set_buffer_funcs_status(adev, false);
+
 	amdgpu_fence_driver_hw_fini(adev);
 
 	amdgpu_device_ip_suspend_phase2(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.h
index 2b488fcf2f95..e51e8918e667 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.h
@@ -46,6 +46,8 @@
 #define MCA_REG__STATUS__ERRORCODEEXT(x)	MCA_REG_FIELD(x, 21, 16)
 #define MCA_REG__STATUS__ERRORCODE(x)		MCA_REG_FIELD(x, 15, 0)
 
+#define MCA_REG__SYND__ERRORINFORMATION(x)	MCA_REG_FIELD(x, 17, 0)
+
 enum amdgpu_mca_ip {
 	AMDGPU_MCA_IP_UNKNOW = -1,
 	AMDGPU_MCA_IP_PSP = 0,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 72634d675e27..bacb59d8b701 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -28,6 +28,7 @@
 #include <linux/reboot.h>
 #include <linux/syscalls.h>
 #include <linux/pm_runtime.h>
+#include <linux/list_sort.h>
 
 #include "amdgpu.h"
 #include "amdgpu_ras.h"
@@ -3674,6 +3675,21 @@ static struct ras_err_node *amdgpu_ras_error_node_new(void)
 	return err_node;
 }
 
+static int ras_err_info_cmp(void *priv, const struct list_head *a, const struct list_head *b)
+{
+	struct ras_err_node *nodea = container_of(a, struct ras_err_node, node);
+	struct ras_err_node *nodeb = container_of(b, struct ras_err_node, node);
+	struct amdgpu_smuio_mcm_config_info *infoa = &nodea->err_info.mcm_info;
+	struct amdgpu_smuio_mcm_config_info *infob = &nodeb->err_info.mcm_info;
+
+	if (unlikely(infoa->socket_id != infob->socket_id))
+		return infoa->socket_id - infob->socket_id;
+	else
+		return infoa->die_id - infob->die_id;
+
+	return 0;
+}
+
 static struct ras_err_info *amdgpu_ras_error_get_info(struct ras_err_data *err_data,
 						      struct amdgpu_smuio_mcm_config_info *mcm_info)
 {
@@ -3691,6 +3707,7 @@ static struct ras_err_info *amdgpu_ras_error_get_info(struct ras_err_data *err_d
 
 	err_data->err_list_count++;
 	list_add_tail(&err_node->node, &err_data->err_node_list);
+	list_sort(NULL, &err_data->err_node_list, ras_err_info_cmp);
 
 	return &err_node->err_info;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/hdp_v4_0.c b/drivers/gpu/drm/amd/amdgpu/hdp_v4_0.c
index 49e934975719..4db6bb73ead4 100644
--- a/drivers/gpu/drm/amd/amdgpu/hdp_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/hdp_v4_0.c
@@ -129,6 +129,11 @@ static void hdp_v4_0_get_clockgating_state(struct amdgpu_device *adev,
 {
 	int data;
 
+	if (amdgpu_ip_version(adev, HDP_HWIP, 0) == IP_VERSION(4, 4, 2)) {
+		/* Default enabled */
+		*flags |= AMD_CG_SUPPORT_HDP_MGCG;
+		return;
+	}
 	/* AMD_CG_SUPPORT_HDP_LS */
 	data = RREG32(SOC15_REG_OFFSET(HDP, 0, mmHDP_MEM_POWER_LS));
 	if (data & HDP_MEM_POWER_LS__LS_ENABLE_MASK)
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c
index 3cf4684d0d3f..df1844d0800f 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c
@@ -60,7 +60,7 @@ MODULE_FIRMWARE("amdgpu/psp_14_0_0_ta.bin");
 #define GFX_CMD_USB_PD_USE_LFB 0x480
 
 /* Retry times for vmbx ready wait */
-#define PSP_VMBX_POLLING_LIMIT 20000
+#define PSP_VMBX_POLLING_LIMIT 3000
 
 /* VBIOS gfl defines */
 #define MBOX_READY_MASK 0x80000000
@@ -161,14 +161,18 @@ static int psp_v13_0_wait_for_vmbx_ready(struct psp_context *psp)
 static int psp_v13_0_wait_for_bootloader(struct psp_context *psp)
 {
 	struct amdgpu_device *adev = psp->adev;
-	int retry_loop, ret;
+	int retry_loop, retry_cnt, ret;
 
+	retry_cnt =
+		(amdgpu_ip_version(adev, MP0_HWIP, 0) == IP_VERSION(13, 0, 6)) ?
+			PSP_VMBX_POLLING_LIMIT :
+			10;
 	/* Wait for bootloader to signify that it is ready having bit 31 of
 	 * C2PMSG_35 set to 1. All other bits are expected to be cleared.
 	 * If there is an error in processing command, bits[7:0] will be set.
 	 * This is applicable for PSP v13.0.6 and newer.
 	 */
-	for (retry_loop = 0; retry_loop < PSP_VMBX_POLLING_LIMIT; retry_loop++) {
+	for (retry_loop = 0; retry_loop < retry_cnt; retry_loop++) {
 		ret = psp_wait_for(
 			psp, SOC15_REG_OFFSET(MP0, 0, regMP0_SMN_C2PMSG_35),
 			0x80000000, 0xffffffff, false);
@@ -821,7 +825,7 @@ static int psp_v13_0_query_boot_status(struct psp_context *psp)
 	if (amdgpu_ip_version(adev, MP0_HWIP, 0) != IP_VERSION(13, 0, 6))
 		return 0;
 
-	if (RREG32_SOC15(MP0, 0, regMP0_SMN_C2PMSG_59) < 0x00a10007)
+	if (RREG32_SOC15(MP0, 0, regMP0_SMN_C2PMSG_59) < 0x00a10109)
 		return 0;
 
 	for_each_inst(i, inst_mask) {
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index 9ad4d6d3122b..15033efec2ba 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -1424,11 +1424,14 @@ static void soc15_common_get_clockgating_state(void *handle, u64 *flags)
 	if (amdgpu_sriov_vf(adev))
 		*flags = 0;
 
-	adev->nbio.funcs->get_clockgating_state(adev, flags);
+	if (adev->nbio.funcs && adev->nbio.funcs->get_clockgating_state)
+		adev->nbio.funcs->get_clockgating_state(adev, flags);
 
-	adev->hdp.funcs->get_clock_gating_state(adev, flags);
+	if (adev->hdp.funcs && adev->hdp.funcs->get_clock_gating_state)
+		adev->hdp.funcs->get_clock_gating_state(adev, flags);
 
-	if (amdgpu_ip_version(adev, MP0_HWIP, 0) != IP_VERSION(13, 0, 2)) {
+	if ((amdgpu_ip_version(adev, MP0_HWIP, 0) != IP_VERSION(13, 0, 2)) &&
+	    (amdgpu_ip_version(adev, MP0_HWIP, 0) != IP_VERSION(13, 0, 6))) {
 		/* AMD_CG_SUPPORT_DRM_MGCG */
 		data = RREG32(SOC15_REG_OFFSET(MP0, 0, mmMP0_MISC_CGTT_CTRL0));
 		if (!(data & 0x01000000))
@@ -1441,9 +1444,11 @@ static void soc15_common_get_clockgating_state(void *handle, u64 *flags)
 	}
 
 	/* AMD_CG_SUPPORT_ROM_MGCG */
-	adev->smuio.funcs->get_clock_gating_state(adev, flags);
+	if (adev->smuio.funcs && adev->smuio.funcs->get_clock_gating_state)
+		adev->smuio.funcs->get_clock_gating_state(adev, flags);
 
-	adev->df.funcs->get_clockgating_state(adev, flags);
+	if (adev->df.funcs && adev->df.funcs->get_clockgating_state)
+		adev->df.funcs->get_clockgating_state(adev, flags);
 }
 
 static int soc15_common_set_powergating_state(void *handle,