Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Cross-merge networking fixes after downstream PR.

Conflicts:

tools/testing/selftests/net/fcnal-test.sh
  d7a2fc1437f7 ("selftests: net: fcnal-test: check if FIPS mode is enabled")
  dd017c72dde6 ("selftests: fcnal: Test SO_DONTROUTE on TCP sockets.")
https://lore.kernel.org/all/5007b52c-dd16-dbf6-8d64-b9701bfa498b@tessares.net/
https://lore.kernel.org/all/20230619105427.4a0df9b3@canb.auug.org.au/

No adjacent changes.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

12 files changed, 255 insertions, 20 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index b1ca1ab6d6ad..393b6fb7a71d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -1615,6 +1615,7 @@ static const u16 amdgpu_unsupported_pciidlist[] = {
 	0x5874,
 	0x5940,
 	0x5941,
+	0x5b70,
 	0x5b72,
 	0x5b73,
 	0x5b74,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 3b225be89cb7..a70103ac0026 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -140,7 +140,7 @@ void amdgpu_bo_placement_from_domain(struct amdgpu_bo *abo, u32 domain)
 
 		if (flags & AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED)
 			places[c].lpfn = visible_pfn;
-		else if (adev->gmc.real_vram_size != adev->gmc.visible_vram_size)
+		else
 			places[c].flags |= TTM_PL_FLAG_TOPDOWN;
 
 		if (flags & AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 9d7e6e0e73ed..a150b7a4b4aa 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -3548,6 +3548,9 @@ static ssize_t amdgpu_psp_vbflash_read(struct file *filp, struct kobject *kobj,
 	void *fw_pri_cpu_addr;
 	int ret;
 
+	if (adev->psp.vbflash_image_size == 0)
+		return -EINVAL;
+
 	dev_info(adev->dev, "VBIOS flash to PSP started");
 
 	ret = amdgpu_bo_create_kernel(adev, adev->psp.vbflash_image_size,
@@ -3599,13 +3602,13 @@ static ssize_t amdgpu_psp_vbflash_status(struct device *dev,
 }
 
 static const struct bin_attribute psp_vbflash_bin_attr = {
-	.attr = {.name = "psp_vbflash", .mode = 0664},
+	.attr = {.name = "psp_vbflash", .mode = 0660},
 	.size = 0,
 	.write = amdgpu_psp_vbflash_write,
 	.read = amdgpu_psp_vbflash_read,
 };
 
-static DEVICE_ATTR(psp_vbflash_status, 0444, amdgpu_psp_vbflash_status, NULL);
+static DEVICE_ATTR(psp_vbflash_status, 0440, amdgpu_psp_vbflash_status, NULL);
 
 int amdgpu_psp_sysfs_init(struct amdgpu_device *adev)
 {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
index dc474b809604..49de3a3eebc7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
@@ -581,3 +581,21 @@ void amdgpu_ring_ib_end(struct amdgpu_ring *ring)
 	if (ring->is_sw_ring)
 		amdgpu_sw_ring_ib_end(ring);
 }
+
+void amdgpu_ring_ib_on_emit_cntl(struct amdgpu_ring *ring)
+{
+	if (ring->is_sw_ring)
+		amdgpu_sw_ring_ib_mark_offset(ring, AMDGPU_MUX_OFFSET_TYPE_CONTROL);
+}
+
+void amdgpu_ring_ib_on_emit_ce(struct amdgpu_ring *ring)
+{
+	if (ring->is_sw_ring)
+		amdgpu_sw_ring_ib_mark_offset(ring, AMDGPU_MUX_OFFSET_TYPE_CE);
+}
+
+void amdgpu_ring_ib_on_emit_de(struct amdgpu_ring *ring)
+{
+	if (ring->is_sw_ring)
+		amdgpu_sw_ring_ib_mark_offset(ring, AMDGPU_MUX_OFFSET_TYPE_DE);
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
index d8749444b689..2474cb71e476 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
@@ -227,6 +227,9 @@ struct amdgpu_ring_funcs {
 	int (*preempt_ib)(struct amdgpu_ring *ring);
 	void (*emit_mem_sync)(struct amdgpu_ring *ring);
 	void (*emit_wave_limit)(struct amdgpu_ring *ring, bool enable);
+	void (*patch_cntl)(struct amdgpu_ring *ring, unsigned offset);
+	void (*patch_ce)(struct amdgpu_ring *ring, unsigned offset);
+	void (*patch_de)(struct amdgpu_ring *ring, unsigned offset);
 };
 
 struct amdgpu_ring {
@@ -318,10 +321,16 @@ struct amdgpu_ring {
 #define amdgpu_ring_init_cond_exec(r) (r)->funcs->init_cond_exec((r))
 #define amdgpu_ring_patch_cond_exec(r,o) (r)->funcs->patch_cond_exec((r),(o))
 #define amdgpu_ring_preempt_ib(r) (r)->funcs->preempt_ib(r)
+#define amdgpu_ring_patch_cntl(r, o) ((r)->funcs->patch_cntl((r), (o)))
+#define amdgpu_ring_patch_ce(r, o) ((r)->funcs->patch_ce((r), (o)))
+#define amdgpu_ring_patch_de(r, o) ((r)->funcs->patch_de((r), (o)))
 
 int amdgpu_ring_alloc(struct amdgpu_ring *ring, unsigned ndw);
 void amdgpu_ring_ib_begin(struct amdgpu_ring *ring);
 void amdgpu_ring_ib_end(struct amdgpu_ring *ring);
+void amdgpu_ring_ib_on_emit_cntl(struct amdgpu_ring *ring);
+void amdgpu_ring_ib_on_emit_ce(struct amdgpu_ring *ring);
+void amdgpu_ring_ib_on_emit_de(struct amdgpu_ring *ring);
 
 void amdgpu_ring_insert_nop(struct amdgpu_ring *ring, uint32_t count);
 void amdgpu_ring_generic_pad_ib(struct amdgpu_ring *ring, struct amdgpu_ib *ib);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring_mux.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring_mux.c
index 62079f0e3ee8..73516abef662 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring_mux.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring_mux.c
@@ -105,6 +105,16 @@ static void amdgpu_mux_resubmit_chunks(struct amdgpu_ring_mux *mux)
 				amdgpu_fence_update_start_timestamp(e->ring,
 								    chunk->sync_seq,
 								    ktime_get());
+				if (chunk->sync_seq ==
+					le32_to_cpu(*(e->ring->fence_drv.cpu_addr + 2))) {
+					if (chunk->cntl_offset <= e->ring->buf_mask)
+						amdgpu_ring_patch_cntl(e->ring,
+								       chunk->cntl_offset);
+					if (chunk->ce_offset <= e->ring->buf_mask)
+						amdgpu_ring_patch_ce(e->ring, chunk->ce_offset);
+					if (chunk->de_offset <= e->ring->buf_mask)
+						amdgpu_ring_patch_de(e->ring, chunk->de_offset);
+				}
 				amdgpu_ring_mux_copy_pkt_from_sw_ring(mux, e->ring,
 								      chunk->start,
 								      chunk->end);
@@ -407,6 +417,17 @@ void amdgpu_sw_ring_ib_end(struct amdgpu_ring *ring)
 	amdgpu_ring_mux_end_ib(mux, ring);
 }
 
+void amdgpu_sw_ring_ib_mark_offset(struct amdgpu_ring *ring, enum amdgpu_ring_mux_offset_type type)
+{
+	struct amdgpu_device *adev = ring->adev;
+	struct amdgpu_ring_mux *mux = &adev->gfx.muxer;
+	unsigned offset;
+
+	offset = ring->wptr & ring->buf_mask;
+
+	amdgpu_ring_mux_ib_mark_offset(mux, ring, offset, type);
+}
+
 void amdgpu_ring_mux_start_ib(struct amdgpu_ring_mux *mux, struct amdgpu_ring *ring)
 {
 	struct amdgpu_mux_entry *e;
@@ -429,6 +450,10 @@ void amdgpu_ring_mux_start_ib(struct amdgpu_ring_mux *mux, struct amdgpu_ring *r
 	}
 
 	chunk->start = ring->wptr;
+	/* the initialized value used to check if they are set by the ib submission*/
+	chunk->cntl_offset = ring->buf_mask + 1;
+	chunk->de_offset = ring->buf_mask + 1;
+	chunk->ce_offset = ring->buf_mask + 1;
 	list_add_tail(&chunk->entry, &e->list);
 }
 
@@ -454,6 +479,41 @@ static void scan_and_remove_signaled_chunk(struct amdgpu_ring_mux *mux, struct a
 	}
 }
 
+void amdgpu_ring_mux_ib_mark_offset(struct amdgpu_ring_mux *mux,
+				    struct amdgpu_ring *ring, u64 offset,
+				    enum amdgpu_ring_mux_offset_type type)
+{
+	struct amdgpu_mux_entry *e;
+	struct amdgpu_mux_chunk *chunk;
+
+	e = amdgpu_ring_mux_sw_entry(mux, ring);
+	if (!e) {
+		DRM_ERROR("cannot find entry!\n");
+		return;
+	}
+
+	chunk = list_last_entry(&e->list, struct amdgpu_mux_chunk, entry);
+	if (!chunk) {
+		DRM_ERROR("cannot find chunk!\n");
+		return;
+	}
+
+	switch (type) {
+	case AMDGPU_MUX_OFFSET_TYPE_CONTROL:
+		chunk->cntl_offset = offset;
+		break;
+	case AMDGPU_MUX_OFFSET_TYPE_DE:
+		chunk->de_offset = offset;
+		break;
+	case AMDGPU_MUX_OFFSET_TYPE_CE:
+		chunk->ce_offset = offset;
+		break;
+	default:
+		DRM_ERROR("invalid type (%d)\n", type);
+		break;
+	}
+}
+
 void amdgpu_ring_mux_end_ib(struct amdgpu_ring_mux *mux, struct amdgpu_ring *ring)
 {
 	struct amdgpu_mux_entry *e;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring_mux.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring_mux.h
index 4be45fc14954..b22d4fb2a847 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring_mux.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring_mux.h
@@ -50,6 +50,12 @@ struct amdgpu_mux_entry {
 	struct list_head        list;
 };
 
+enum amdgpu_ring_mux_offset_type {
+	AMDGPU_MUX_OFFSET_TYPE_CONTROL,
+	AMDGPU_MUX_OFFSET_TYPE_DE,
+	AMDGPU_MUX_OFFSET_TYPE_CE,
+};
+
 struct amdgpu_ring_mux {
 	struct amdgpu_ring      *real_ring;
 
@@ -72,12 +78,18 @@ struct amdgpu_ring_mux {
  * @sync_seq: the fence seqno related with the saved IB.
  * @start:- start location on the software ring.
  * @end:- end location on the software ring.
+ * @control_offset:- the PRE_RESUME bit position used for resubmission.
+ * @de_offset:- the anchor in write_data for de meta of resubmission.
+ * @ce_offset:- the anchor in write_data for ce meta of resubmission.
  */
 struct amdgpu_mux_chunk {
 	struct list_head        entry;
 	uint32_t                sync_seq;
 	u64                     start;
 	u64                     end;
+	u64                     cntl_offset;
+	u64                     de_offset;
+	u64                     ce_offset;
 };
 
 int amdgpu_ring_mux_init(struct amdgpu_ring_mux *mux, struct amdgpu_ring *ring,
@@ -89,6 +101,8 @@ u64 amdgpu_ring_mux_get_wptr(struct amdgpu_ring_mux *mux, struct amdgpu_ring *ri
 u64 amdgpu_ring_mux_get_rptr(struct amdgpu_ring_mux *mux, struct amdgpu_ring *ring);
 void amdgpu_ring_mux_start_ib(struct amdgpu_ring_mux *mux, struct amdgpu_ring *ring);
 void amdgpu_ring_mux_end_ib(struct amdgpu_ring_mux *mux, struct amdgpu_ring *ring);
+void amdgpu_ring_mux_ib_mark_offset(struct amdgpu_ring_mux *mux, struct amdgpu_ring *ring,
+				    u64 offset, enum amdgpu_ring_mux_offset_type type);
 bool amdgpu_mcbp_handle_trailing_fence_irq(struct amdgpu_ring_mux *mux);
 
 u64 amdgpu_sw_ring_get_rptr_gfx(struct amdgpu_ring *ring);
@@ -97,6 +111,7 @@ void amdgpu_sw_ring_set_wptr_gfx(struct amdgpu_ring *ring);
 void amdgpu_sw_ring_insert_nop(struct amdgpu_ring *ring, uint32_t count);
 void amdgpu_sw_ring_ib_begin(struct amdgpu_ring *ring);
 void amdgpu_sw_ring_ib_end(struct amdgpu_ring *ring);
+void amdgpu_sw_ring_ib_mark_offset(struct amdgpu_ring *ring, enum amdgpu_ring_mux_offset_type type);
 const char *amdgpu_sw_ring_name(int idx);
 unsigned int amdgpu_sw_ring_priority(int idx);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index e7f2b7bf0ff5..a674c8a58dc2 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -755,7 +755,7 @@ static void gfx_v9_0_set_rlc_funcs(struct amdgpu_device *adev);
 static int gfx_v9_0_get_cu_info(struct amdgpu_device *adev,
 				struct amdgpu_cu_info *cu_info);
 static uint64_t gfx_v9_0_get_gpu_clock_counter(struct amdgpu_device *adev);
-static void gfx_v9_0_ring_emit_de_meta(struct amdgpu_ring *ring, bool resume);
+static void gfx_v9_0_ring_emit_de_meta(struct amdgpu_ring *ring, bool resume, bool usegds);
 static u64 gfx_v9_0_ring_get_rptr_compute(struct amdgpu_ring *ring);
 static void gfx_v9_0_query_ras_error_count(struct amdgpu_device *adev,
 					  void *ras_error_status);
@@ -5127,7 +5127,8 @@ static void gfx_v9_0_ring_emit_ib_gfx(struct amdgpu_ring *ring,
 			gfx_v9_0_ring_emit_de_meta(ring,
 						   (!amdgpu_sriov_vf(ring->adev) &&
 						   flags & AMDGPU_IB_PREEMPTED) ?
-						   true : false);
+						   true : false,
+						   job->gds_size > 0 && job->gds_base != 0);
 	}
 
 	amdgpu_ring_write(ring, header);
@@ -5138,9 +5139,83 @@ static void gfx_v9_0_ring_emit_ib_gfx(struct amdgpu_ring *ring,
 #endif
 		lower_32_bits(ib->gpu_addr));
 	amdgpu_ring_write(ring, upper_32_bits(ib->gpu_addr));
+	amdgpu_ring_ib_on_emit_cntl(ring);
 	amdgpu_ring_write(ring, control);
 }
 
+static void gfx_v9_0_ring_patch_cntl(struct amdgpu_ring *ring,
+				     unsigned offset)
+{
+	u32 control = ring->ring[offset];
+
+	control |= INDIRECT_BUFFER_PRE_RESUME(1);
+	ring->ring[offset] = control;
+}
+
+static void gfx_v9_0_ring_patch_ce_meta(struct amdgpu_ring *ring,
+					unsigned offset)
+{
+	struct amdgpu_device *adev = ring->adev;
+	void *ce_payload_cpu_addr;
+	uint64_t payload_offset, payload_size;
+
+	payload_size = sizeof(struct v9_ce_ib_state);
+
+	if (ring->is_mes_queue) {
+		payload_offset = offsetof(struct amdgpu_mes_ctx_meta_data,
+					  gfx[0].gfx_meta_data) +
+			offsetof(struct v9_gfx_meta_data, ce_payload);
+		ce_payload_cpu_addr =
+			amdgpu_mes_ctx_get_offs_cpu_addr(ring, payload_offset);
+	} else {
+		payload_offset = offsetof(struct v9_gfx_meta_data, ce_payload);
+		ce_payload_cpu_addr = adev->virt.csa_cpu_addr + payload_offset;
+	}
+
+	if (offset + (payload_size >> 2) <= ring->buf_mask + 1) {
+		memcpy((void *)&ring->ring[offset], ce_payload_cpu_addr, payload_size);
+	} else {
+		memcpy((void *)&ring->ring[offset], ce_payload_cpu_addr,
+		       (ring->buf_mask + 1 - offset) << 2);
+		payload_size -= (ring->buf_mask + 1 - offset) << 2;
+		memcpy((void *)&ring->ring[0],
+		       ce_payload_cpu_addr + ((ring->buf_mask + 1 - offset) << 2),
+		       payload_size);
+	}
+}
+
+static void gfx_v9_0_ring_patch_de_meta(struct amdgpu_ring *ring,
+					unsigned offset)
+{
+	struct amdgpu_device *adev = ring->adev;
+	void *de_payload_cpu_addr;
+	uint64_t payload_offset, payload_size;
+
+	payload_size = sizeof(struct v9_de_ib_state);
+
+	if (ring->is_mes_queue) {
+		payload_offset = offsetof(struct amdgpu_mes_ctx_meta_data,
+					  gfx[0].gfx_meta_data) +
+			offsetof(struct v9_gfx_meta_data, de_payload);
+		de_payload_cpu_addr =
+			amdgpu_mes_ctx_get_offs_cpu_addr(ring, payload_offset);
+	} else {
+		payload_offset = offsetof(struct v9_gfx_meta_data, de_payload);
+		de_payload_cpu_addr = adev->virt.csa_cpu_addr + payload_offset;
+	}
+
+	if (offset + (payload_size >> 2) <= ring->buf_mask + 1) {
+		memcpy((void *)&ring->ring[offset], de_payload_cpu_addr, payload_size);
+	} else {
+		memcpy((void *)&ring->ring[offset], de_payload_cpu_addr,
+		       (ring->buf_mask + 1 - offset) << 2);
+		payload_size -= (ring->buf_mask + 1 - offset) << 2;
+		memcpy((void *)&ring->ring[0],
+		       de_payload_cpu_addr + ((ring->buf_mask + 1 - offset) << 2),
+		       payload_size);
+	}
+}
+
 static void gfx_v9_0_ring_emit_ib_compute(struct amdgpu_ring *ring,
 					  struct amdgpu_job *job,
 					  struct amdgpu_ib *ib,
@@ -5336,6 +5411,8 @@ static void gfx_v9_0_ring_emit_ce_meta(struct amdgpu_ring *ring, bool resume)
 	amdgpu_ring_write(ring, lower_32_bits(ce_payload_gpu_addr));
 	amdgpu_ring_write(ring, upper_32_bits(ce_payload_gpu_addr));
 
+	amdgpu_ring_ib_on_emit_ce(ring);
+
 	if (resume)
 		amdgpu_ring_write_multiple(ring, ce_payload_cpu_addr,
 					   sizeof(ce_payload) >> 2);
@@ -5369,10 +5446,6 @@ static int gfx_v9_0_ring_preempt_ib(struct amdgpu_ring *ring)
 	amdgpu_ring_alloc(ring, 13);
 	gfx_v9_0_ring_emit_fence(ring, ring->trail_fence_gpu_addr,
 				 ring->trail_seq, AMDGPU_FENCE_FLAG_EXEC | AMDGPU_FENCE_FLAG_INT);
-	/*reset the CP_VMID_PREEMPT after trailing fence*/
-	amdgpu_ring_emit_wreg(ring,
-			      SOC15_REG_OFFSET(GC, 0, mmCP_VMID_PREEMPT),
-			      0x0);
 
 	/* assert IB preemption, emit the trailing fence */
 	kiq->pmf->kiq_unmap_queues(kiq_ring, ring, PREEMPT_QUEUES_NO_UNMAP,
@@ -5395,6 +5468,10 @@ static int gfx_v9_0_ring_preempt_ib(struct amdgpu_ring *ring)
 		DRM_WARN("ring %d timeout to preempt ib\n", ring->idx);
 	}
 
+	/*reset the CP_VMID_PREEMPT after trailing fence*/
+	amdgpu_ring_emit_wreg(ring,
+			      SOC15_REG_OFFSET(GC, 0, mmCP_VMID_PREEMPT),
+			      0x0);
 	amdgpu_ring_commit(ring);
 
 	/* deassert preemption condition */
@@ -5402,7 +5479,7 @@ static int gfx_v9_0_ring_preempt_ib(struct amdgpu_ring *ring)
 	return r;
 }
 
-static void gfx_v9_0_ring_emit_de_meta(struct amdgpu_ring *ring, bool resume)
+static void gfx_v9_0_ring_emit_de_meta(struct amdgpu_ring *ring, bool resume, bool usegds)
 {
 	struct amdgpu_device *adev = ring->adev;
 	struct v9_de_ib_state de_payload = {0};
@@ -5433,8 +5510,10 @@ static void gfx_v9_0_ring_emit_de_meta(struct amdgpu_ring *ring, bool resume)
 				 PAGE_SIZE);
 	}
 
-	de_payload.gds_backup_addrlo = lower_32_bits(gds_addr);
-	de_payload.gds_backup_addrhi = upper_32_bits(gds_addr);
+	if (usegds) {
+		de_payload.gds_backup_addrlo = lower_32_bits(gds_addr);
+		de_payload.gds_backup_addrhi = upper_32_bits(gds_addr);
+	}
 
 	cnt = (sizeof(de_payload) >> 2) + 4 - 2;
 	amdgpu_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, cnt));
@@ -5445,6 +5524,7 @@ static void gfx_v9_0_ring_emit_de_meta(struct amdgpu_ring *ring, bool resume)
 	amdgpu_ring_write(ring, lower_32_bits(de_payload_gpu_addr));
 	amdgpu_ring_write(ring, upper_32_bits(de_payload_gpu_addr));
 
+	amdgpu_ring_ib_on_emit_de(ring);
 	if (resume)
 		amdgpu_ring_write_multiple(ring, de_payload_cpu_addr,
 					   sizeof(de_payload) >> 2);
@@ -6855,6 +6935,9 @@ static const struct amdgpu_ring_funcs gfx_v9_0_sw_ring_funcs_gfx = {
 	.emit_reg_write_reg_wait = gfx_v9_0_ring_emit_reg_write_reg_wait,
 	.soft_recovery = gfx_v9_0_ring_soft_recovery,
 	.emit_mem_sync = gfx_v9_0_emit_mem_sync,
+	.patch_cntl = gfx_v9_0_ring_patch_cntl,
+	.patch_de = gfx_v9_0_ring_patch_de_meta,
+	.patch_ce = gfx_v9_0_ring_patch_ce_meta,
 };
 
 static const struct amdgpu_ring_funcs gfx_v9_0_ring_funcs_compute = {
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
index e5fd1e00914d..da126ff8bcbc 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
@@ -129,7 +129,11 @@ static int vcn_v4_0_sw_init(void *handle)
 		if (adev->vcn.harvest_config & (1 << i))
 			continue;
 
-		atomic_set(&adev->vcn.inst[i].sched_score, 0);
+		/* Init instance 0 sched_score to 1, so it's scheduled after other instances */
+		if (i == 0)
+			atomic_set(&adev->vcn.inst[i].sched_score, 1);
+		else
+			atomic_set(&adev->vcn.inst[i].sched_score, 0);
 
 		/* VCN UNIFIED TRAP */
 		r = amdgpu_irq_add_id(adev, amdgpu_ih_clientid_vcns[i],
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index d5cec03eaa8d..7acd73e5004f 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -7196,7 +7196,13 @@ static int amdgpu_dm_connector_get_modes(struct drm_connector *connector)
 				drm_add_modes_noedid(connector, 1920, 1080);
 	} else {
 		amdgpu_dm_connector_ddc_get_modes(connector, edid);
-		amdgpu_dm_connector_add_common_modes(encoder, connector);
+		/* most eDP supports only timings from its edid,
+		 * usually only detailed timings are available
+		 * from eDP edid. timings which are not from edid
+		 * may damage eDP
+		 */
+		if (connector->connector_type != DRM_MODE_CONNECTOR_eDP)
+			amdgpu_dm_connector_add_common_modes(encoder, connector);
 		amdgpu_dm_connector_add_freesync_modes(connector, edid);
 	}
 	amdgpu_dm_fbc_init(connector);
@@ -8198,6 +8204,12 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 		if (acrtc_state->abm_level != dm_old_crtc_state->abm_level)
 			bundle->stream_update.abm_level = &acrtc_state->abm_level;
 
+		mutex_lock(&dm->dc_lock);
+		if ((acrtc_state->update_type > UPDATE_TYPE_FAST) &&
+				acrtc_state->stream->link->psr_settings.psr_allow_active)
+			amdgpu_dm_psr_disable(acrtc_state->stream);
+		mutex_unlock(&dm->dc_lock);
+
 		/*
 		 * If FreeSync state on the stream has changed then we need to
 		 * re-adjust the min/max bounds now that DC doesn't handle this
@@ -8211,10 +8223,6 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 			spin_unlock_irqrestore(&pcrtc->dev->event_lock, flags);
 		}
 		mutex_lock(&dm->dc_lock);
-		if ((acrtc_state->update_type > UPDATE_TYPE_FAST) &&
-				acrtc_state->stream->link->psr_settings.psr_allow_active)
-			amdgpu_dm_psr_disable(acrtc_state->stream);
-
 		update_planes_and_stream_adapter(dm->dc,
 					 acrtc_state->update_type,
 					 planes_count,
diff --git a/drivers/gpu/drm/amd/display/dc/link/link_detection.c b/drivers/gpu/drm/amd/display/dc/link/link_detection.c
index a131e30fd7d6..d471d58aba92 100644
--- a/drivers/gpu/drm/amd/display/dc/link/link_detection.c
+++ b/drivers/gpu/drm/amd/display/dc/link/link_detection.c
@@ -980,6 +980,11 @@ static bool detect_link_and_local_sink(struct dc_link *link,
 					(link->dpcd_caps.dongle_type !=
 							DISPLAY_DONGLE_DP_HDMI_CONVERTER))
 				converter_disable_audio = true;
+
+			/* limited link rate to HBR3 for DPIA until we implement USB4 V2 */
+			if (link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA &&
+					link->reported_link_cap.link_rate > LINK_RATE_HIGH3)
+				link->reported_link_cap.link_rate = LINK_RATE_HIGH3;
 			break;
 		}
 
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
index 09405ef1e3c8..08577d1b84ec 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
@@ -1696,10 +1696,39 @@ static int smu_v13_0_0_set_power_profile_mode(struct smu_context *smu,
 		}
 	}
 
-	/* conv PP_SMC_POWER_PROFILE* to WORKLOAD_PPLIB_*_BIT */
-	workload_type = smu_cmn_to_asic_specific_index(smu,
+	if (smu->power_profile_mode == PP_SMC_POWER_PROFILE_COMPUTE &&
+		(((smu->adev->pdev->device == 0x744C) && (smu->adev->pdev->revision == 0xC8)) ||
+		((smu->adev->pdev->device == 0x744C) && (smu->adev->pdev->revision == 0xCC)))) {
+		ret = smu_cmn_update_table(smu,
+					   SMU_TABLE_ACTIVITY_MONITOR_COEFF,
+					   WORKLOAD_PPLIB_COMPUTE_BIT,
+					   (void *)(&activity_monitor_external),
+					   false);
+		if (ret) {
+			dev_err(smu->adev->dev, "[%s] Failed to get activity monitor!", __func__);
+			return ret;
+		}
+
+		ret = smu_cmn_update_table(smu,
+					   SMU_TABLE_ACTIVITY_MONITOR_COEFF,
+					   WORKLOAD_PPLIB_CUSTOM_BIT,
+					   (void *)(&activity_monitor_external),
+					   true);
+		if (ret) {
+			dev_err(smu->adev->dev, "[%s] Failed to set activity monitor!", __func__);
+			return ret;
+		}
+
+		workload_type = smu_cmn_to_asic_specific_index(smu,
+						       CMN2ASIC_MAPPING_WORKLOAD,
+						       PP_SMC_POWER_PROFILE_CUSTOM);
+	} else {
+		/* conv PP_SMC_POWER_PROFILE* to WORKLOAD_PPLIB_*_BIT */
+		workload_type = smu_cmn_to_asic_specific_index(smu,
 						       CMN2ASIC_MAPPING_WORKLOAD,
 						       smu->power_profile_mode);
+	}
+
 	if (workload_type < 0)
 		return -EINVAL;