Merge v6.11.10linux-rolling-stable

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

72 files changed, 641 insertions, 375 deletions

diff --git a/drivers/bluetooth/btintel.c b/drivers/bluetooth/btintel.c
index 1ccbb5157515..24d2f4f37d0f 100644
--- a/drivers/bluetooth/btintel.c
+++ b/drivers/bluetooth/btintel.c
@@ -3288,13 +3288,12 @@ static int btintel_diagnostics(struct hci_dev *hdev, struct sk_buff *skb)
 	case INTEL_TLV_TEST_EXCEPTION:
 		/* Generate devcoredump from exception */
 		if (!hci_devcd_init(hdev, skb->len)) {
-			hci_devcd_append(hdev, skb);
+			hci_devcd_append(hdev, skb_clone(skb, GFP_ATOMIC));
 			hci_devcd_complete(hdev);
 		} else {
 			bt_dev_err(hdev, "Failed to generate devcoredump");
-			kfree_skb(skb);
 		}
-		return 0;
+	break;
 	default:
 		bt_dev_err(hdev, "Invalid exception type %02X", tlv->val[0]);
 	}
diff --git a/drivers/char/tpm/tpm2-sessions.c b/drivers/char/tpm/tpm2-sessions.c
index c8fdfe901dfb..adbf47967707 100644
--- a/drivers/char/tpm/tpm2-sessions.c
+++ b/drivers/char/tpm/tpm2-sessions.c
@@ -948,10 +948,13 @@ static int tpm2_load_null(struct tpm_chip *chip, u32 *null_key)
 	/* Deduce from the name change TPM interference: */
 	dev_err(&chip->dev, "null key integrity check failed\n");
 	tpm2_flush_context(chip, tmp_null_key);
-	chip->flags |= TPM_CHIP_FLAG_DISABLE;
 
 err:
-	return rc ? -ENODEV : 0;
+	if (rc) {
+		chip->flags |= TPM_CHIP_FLAG_DISABLE;
+		rc = -ENODEV;
+	}
+	return rc;
 }
 
 /**
diff --git a/drivers/firmware/arm_scmi/perf.c b/drivers/firmware/arm_scmi/perf.c
index 4b7f1cbb9b04..408f16528862 100644
--- a/drivers/firmware/arm_scmi/perf.c
+++ b/drivers/firmware/arm_scmi/perf.c
@@ -373,7 +373,7 @@ static int iter_perf_levels_update_state(struct scmi_iterator_state *st,
 	return 0;
 }
 
-static inline void
+static inline int
 process_response_opp(struct device *dev, struct perf_dom_info *dom,
 		     struct scmi_opp *opp, unsigned int loop_idx,
 		     const struct scmi_msg_resp_perf_describe_levels *r)
@@ -386,12 +386,16 @@ process_response_opp(struct device *dev, struct perf_dom_info *dom,
 		le16_to_cpu(r->opp[loop_idx].transition_latency_us);
 
 	ret = xa_insert(&dom->opps_by_lvl, opp->perf, opp, GFP_KERNEL);
-	if (ret)
-		dev_warn(dev, "Failed to add opps_by_lvl at %d for %s - ret:%d\n",
+	if (ret) {
+		dev_info(dev, FW_BUG "Failed to add opps_by_lvl at %d for %s - ret:%d\n",
 			 opp->perf, dom->info.name, ret);
+		return ret;
+	}
+
+	return 0;
 }
 
-static inline void
+static inline int
 process_response_opp_v4(struct device *dev, struct perf_dom_info *dom,
 			struct scmi_opp *opp, unsigned int loop_idx,
 			const struct scmi_msg_resp_perf_describe_levels_v4 *r)
@@ -404,9 +408,11 @@ process_response_opp_v4(struct device *dev, struct perf_dom_info *dom,
 		le16_to_cpu(r->opp[loop_idx].transition_latency_us);
 
 	ret = xa_insert(&dom->opps_by_lvl, opp->perf, opp, GFP_KERNEL);
-	if (ret)
-		dev_warn(dev, "Failed to add opps_by_lvl at %d for %s - ret:%d\n",
+	if (ret) {
+		dev_info(dev, FW_BUG "Failed to add opps_by_lvl at %d for %s - ret:%d\n",
 			 opp->perf, dom->info.name, ret);
+		return ret;
+	}
 
 	/* Note that PERF v4 reports always five 32-bit words */
 	opp->indicative_freq = le32_to_cpu(r->opp[loop_idx].indicative_freq);
@@ -415,13 +421,21 @@ process_response_opp_v4(struct device *dev, struct perf_dom_info *dom,
 
 		ret = xa_insert(&dom->opps_by_idx, opp->level_index, opp,
 				GFP_KERNEL);
-		if (ret)
+		if (ret) {
 			dev_warn(dev,
 				 "Failed to add opps_by_idx at %d for %s - ret:%d\n",
 				 opp->level_index, dom->info.name, ret);
 
+			/* Cleanup by_lvl too */
+			xa_erase(&dom->opps_by_lvl, opp->perf);
+
+			return ret;
+		}
+
 		hash_add(dom->opps_by_freq, &opp->hash, opp->indicative_freq);
 	}
+
+	return 0;
 }
 
 static int
@@ -429,16 +443,22 @@ iter_perf_levels_process_response(const struct scmi_protocol_handle *ph,
 				  const void *response,
 				  struct scmi_iterator_state *st, void *priv)
 {
+	int ret;
 	struct scmi_opp *opp;
 	struct scmi_perf_ipriv *p = priv;
 
-	opp = &p->perf_dom->opp[st->desc_index + st->loop_idx];
+	opp = &p->perf_dom->opp[p->perf_dom->opp_count];
 	if (PROTOCOL_REV_MAJOR(p->version) <= 0x3)
-		process_response_opp(ph->dev, p->perf_dom, opp, st->loop_idx,
-				     response);
+		ret = process_response_opp(ph->dev, p->perf_dom, opp,
+					   st->loop_idx, response);
 	else
-		process_response_opp_v4(ph->dev, p->perf_dom, opp, st->loop_idx,
-					response);
+		ret = process_response_opp_v4(ph->dev, p->perf_dom, opp,
+					      st->loop_idx, response);
+
+	/* Skip BAD duplicates received from firmware */
+	if (ret)
+		return ret == -EBUSY ? 0 : ret;
+
 	p->perf_dom->opp_count++;
 
 	dev_dbg(ph->dev, "Level %d Power %d Latency %dus Ifreq %d Index %d\n",
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index e32161f6b67a..11c5e43fc2fa 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -180,7 +180,8 @@ void amdgpu_bo_placement_from_domain(struct amdgpu_bo *abo, u32 domain)
 		 * When GTT is just an alternative to VRAM make sure that we
 		 * only use it as fallback and still try to fill up VRAM first.
 		 */
-		if (domain & abo->preferred_domains & AMDGPU_GEM_DOMAIN_VRAM)
+		if (domain & abo->preferred_domains & AMDGPU_GEM_DOMAIN_VRAM &&
+		    !(adev->flags & AMD_IS_APU))
 			places[c].flags |= TTM_PL_FLAG_FALLBACK;
 		c++;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index b73136d390cc..6dfa58741afe 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -1124,8 +1124,10 @@ static void gmc_v9_0_get_coherence_flags(struct amdgpu_device *adev,
 					 uint64_t *flags)
 {
 	struct amdgpu_device *bo_adev = amdgpu_ttm_adev(bo->tbo.bdev);
-	bool is_vram = bo->tbo.resource->mem_type == TTM_PL_VRAM;
-	bool coherent = bo->flags & (AMDGPU_GEM_CREATE_COHERENT | AMDGPU_GEM_CREATE_EXT_COHERENT);
+	bool is_vram = bo->tbo.resource &&
+		bo->tbo.resource->mem_type == TTM_PL_VRAM;
+	bool coherent = bo->flags & (AMDGPU_GEM_CREATE_COHERENT |
+				     AMDGPU_GEM_CREATE_EXT_COHERENT);
 	bool ext_coherent = bo->flags & AMDGPU_GEM_CREATE_EXT_COHERENT;
 	bool uncached = bo->flags & AMDGPU_GEM_CREATE_UNCACHED;
 	struct amdgpu_vm *vm = mapping->bo_va->base.vm;
@@ -1133,6 +1135,8 @@ static void gmc_v9_0_get_coherence_flags(struct amdgpu_device *adev,
 	bool snoop = false;
 	bool is_local;
 
+	dma_resv_assert_held(bo->tbo.base.resv);
+
 	switch (amdgpu_ip_version(adev, GC_HWIP, 0)) {
 	case IP_VERSION(9, 4, 1):
 	case IP_VERSION(9, 4, 2):
@@ -1251,9 +1255,8 @@ static void gmc_v9_0_get_vm_pte(struct amdgpu_device *adev,
 		*flags &= ~AMDGPU_PTE_VALID;
 	}
 
-	if (bo && bo->tbo.resource)
-		gmc_v9_0_get_coherence_flags(adev, mapping->bo_va->base.bo,
-					     mapping, flags);
+	if ((*flags & AMDGPU_PTE_VALID) && bo)
+		gmc_v9_0_get_coherence_flags(adev, bo, mapping, flags);
 }
 
 static void gmc_v9_0_override_vm_pte_flags(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
index 62d792ed0323..0383d1f95780 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
@@ -524,7 +524,7 @@ static int mes_v12_0_set_hw_resources_1(struct amdgpu_mes *mes, int pipe)
 	mes_set_hw_res_1_pkt.header.type = MES_API_TYPE_SCHEDULER;
 	mes_set_hw_res_1_pkt.header.opcode = MES_SCH_API_SET_HW_RSRC_1;
 	mes_set_hw_res_1_pkt.header.dwsize = API_FRAME_SIZE_IN_DWORDS;
-	mes_set_hw_res_1_pkt.mes_kiq_unmap_timeout = 100;
+	mes_set_hw_res_1_pkt.mes_kiq_unmap_timeout = 0xa;
 
 	return mes_v12_0_submit_pkt_and_poll_completion(mes, pipe,
 			&mes_set_hw_res_1_pkt, sizeof(mes_set_hw_res_1_pkt),
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c
index fb37e354a9d5..1ac730328516 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c
@@ -247,6 +247,12 @@ static void nbio_v7_7_init_registers(struct amdgpu_device *adev)
 	if (def != data)
 		WREG32_SOC15(NBIO, 0, regBIF0_PCIE_MST_CTRL_3, data);
 
+	switch (adev->ip_versions[NBIO_HWIP][0]) {
+	case IP_VERSION(7, 7, 0):
+		data = RREG32_SOC15(NBIO, 0, regRCC_DEV0_EPF5_STRAP4) & ~BIT(23);
+		WREG32_SOC15(NBIO, 0, regRCC_DEV0_EPF5_STRAP4, data);
+		break;
+	}
 }
 
 static void nbio_v7_7_update_medium_grain_clock_gating(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c
index 4938e6b340e9..73065a85e0d2 100644
--- a/drivers/gpu/drm/amd/amdgpu/nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/nv.c
@@ -67,8 +67,8 @@ static const struct amd_ip_funcs nv_common_ip_funcs;
 
 /* Navi */
 static const struct amdgpu_video_codec_info nv_video_codecs_encode_array[] = {
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 2304, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 4096, 0)},
 };
 
 static const struct amdgpu_video_codecs nv_video_codecs_encode = {
@@ -94,8 +94,8 @@ static const struct amdgpu_video_codecs nv_video_codecs_decode = {
 
 /* Sienna Cichlid */
 static const struct amdgpu_video_codec_info sc_video_codecs_encode_array[] = {
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2160, 0)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 7680, 4352, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 0)},
 };
 
 static const struct amdgpu_video_codecs sc_video_codecs_encode = {
@@ -136,8 +136,8 @@ static const struct amdgpu_video_codecs sc_video_codecs_decode_vcn1 = {
 
 /* SRIOV Sienna Cichlid, not const since data is controlled by host */
 static struct amdgpu_video_codec_info sriov_sc_video_codecs_encode_array[] = {
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2160, 0)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 7680, 4352, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 0)},
 };
 
 static struct amdgpu_video_codec_info sriov_sc_video_codecs_decode_array_vcn0[] = {
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index 8d16dacdc172..307185c0e1b8 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -90,8 +90,8 @@ static const struct amd_ip_funcs soc15_common_ip_funcs;
 /* Vega, Raven, Arcturus */
 static const struct amdgpu_video_codec_info vega_video_codecs_encode_array[] =
 {
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 2304, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 4096, 0)},
 };
 
 static const struct amdgpu_video_codecs vega_video_codecs_encode =
diff --git a/drivers/gpu/drm/amd/amdgpu/soc21.c b/drivers/gpu/drm/amd/amdgpu/soc21.c
index d30ad7d56def..bba35880badb 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc21.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc21.c
@@ -49,13 +49,13 @@ static const struct amd_ip_funcs soc21_common_ip_funcs;
 
 /* SOC21 */
 static const struct amdgpu_video_codec_info vcn_4_0_0_video_codecs_encode_array_vcn0[] = {
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 0)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 0)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_AV1, 8192, 4352, 0)},
 };
 
 static const struct amdgpu_video_codec_info vcn_4_0_0_video_codecs_encode_array_vcn1[] = {
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 0)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 0)},
 };
 
@@ -96,14 +96,14 @@ static const struct amdgpu_video_codecs vcn_4_0_0_video_codecs_decode_vcn1 = {
 
 /* SRIOV SOC21, not const since data is controlled by host */
 static struct amdgpu_video_codec_info sriov_vcn_4_0_0_video_codecs_encode_array_vcn0[] = {
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 2304, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 0)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_AV1, 8192, 4352, 0)},
 };
 
 static struct amdgpu_video_codec_info sriov_vcn_4_0_0_video_codecs_encode_array_vcn1[] = {
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 2304, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 0)},
 };
 
 static struct amdgpu_video_codecs sriov_vcn_4_0_0_video_codecs_encode_vcn0 = {
diff --git a/drivers/gpu/drm/amd/amdgpu/soc24.c b/drivers/gpu/drm/amd/amdgpu/soc24.c
index fd4c3d4f8387..29a848f2466b 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc24.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc24.c
@@ -48,7 +48,7 @@
 static const struct amd_ip_funcs soc24_common_ip_funcs;
 
 static const struct amdgpu_video_codec_info vcn_5_0_0_video_codecs_encode_array_vcn0[] = {
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 0)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 0)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_AV1, 8192, 4352, 0)},
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c
index d39c670f6220..792b2eb6bbac 100644
--- a/drivers/gpu/drm/amd/amdgpu/vi.c
+++ b/drivers/gpu/drm/amd/amdgpu/vi.c
@@ -136,15 +136,15 @@ static const struct amdgpu_video_codec_info polaris_video_codecs_encode_array[]
 	{
 		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC,
 		.max_width = 4096,
-		.max_height = 2304,
-		.max_pixels_per_frame = 4096 * 2304,
+		.max_height = 4096,
+		.max_pixels_per_frame = 4096 * 4096,
 		.max_level = 0,
 	},
 	{
 		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC,
 		.max_width = 4096,
-		.max_height = 2304,
-		.max_pixels_per_frame = 4096 * 2304,
+		.max_height = 4096,
+		.max_pixels_per_frame = 4096 * 4096,
 		.max_level = 0,
 	},
 };
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 245a26cdfc52..339bdfb7af2f 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -6740,7 +6740,7 @@ create_stream_for_sink(struct drm_connector *connector,
 		if (stream->out_transfer_func.tf == TRANSFER_FUNCTION_GAMMA22)
 			tf = TRANSFER_FUNC_GAMMA_22;
 		mod_build_vsc_infopacket(stream, &stream->vsc_infopacket, stream->output_color_space, tf);
-		aconnector->psr_skip_count = AMDGPU_DM_PSR_ENTRY_DELAY;
+		aconnector->sr_skip_count = AMDGPU_DM_PSR_ENTRY_DELAY;
 
 	}
 finish:
@@ -8830,6 +8830,56 @@ static void amdgpu_dm_update_cursor(struct drm_plane *plane,
 	}
 }
 
+static void amdgpu_dm_enable_self_refresh(struct amdgpu_crtc *acrtc_attach,
+					  const struct dm_crtc_state *acrtc_state,
+					  const u64 current_ts)
+{
+	struct psr_settings *psr = &acrtc_state->stream->link->psr_settings;
+	struct replay_settings *pr = &acrtc_state->stream->link->replay_settings;
+	struct amdgpu_dm_connector *aconn =
+		(struct amdgpu_dm_connector *)acrtc_state->stream->dm_stream_context;
+
+	if (acrtc_state->update_type > UPDATE_TYPE_FAST) {
+		if (pr->config.replay_supported && !pr->replay_feature_enabled)
+			amdgpu_dm_link_setup_replay(acrtc_state->stream->link, aconn);
+		else if (psr->psr_version != DC_PSR_VERSION_UNSUPPORTED &&
+			     !psr->psr_feature_enabled)
+			if (!aconn->disallow_edp_enter_psr)
+				amdgpu_dm_link_setup_psr(acrtc_state->stream);
+	}
+
+	/* Decrement skip count when SR is enabled and we're doing fast updates. */
+	if (acrtc_state->update_type == UPDATE_TYPE_FAST &&
+	    (psr->psr_feature_enabled || pr->config.replay_supported)) {
+		if (aconn->sr_skip_count > 0)
+			aconn->sr_skip_count--;
+
+		/* Allow SR when skip count is 0. */
+		acrtc_attach->dm_irq_params.allow_sr_entry = !aconn->sr_skip_count;
+
+		/*
+		 * If sink supports PSR SU/Panel Replay, there is no need to rely on
+		 * a vblank event disable request to enable PSR/RP. PSR SU/RP
+		 * can be enabled immediately once OS demonstrates an
+		 * adequate number of fast atomic commits to notify KMD
+		 * of update events. See `vblank_control_worker()`.
+		 */
+		if (acrtc_attach->dm_irq_params.allow_sr_entry &&
+#ifdef CONFIG_DRM_AMD_SECURE_DISPLAY
+		    !amdgpu_dm_crc_window_is_activated(acrtc_state->base.crtc) &&
+#endif
+		    (current_ts - psr->psr_dirty_rects_change_timestamp_ns) > 500000000) {
+			if (pr->replay_feature_enabled && !pr->replay_allow_active)
+				amdgpu_dm_replay_enable(acrtc_state->stream, true);
+			if (psr->psr_version >= DC_PSR_VERSION_SU_1 &&
+			    !psr->psr_allow_active && !aconn->disallow_edp_enter_psr)
+				amdgpu_dm_psr_enable(acrtc_state->stream);
+		}
+	} else {
+		acrtc_attach->dm_irq_params.allow_sr_entry = false;
+	}
+}
+
 static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 				    struct drm_device *dev,
 				    struct amdgpu_display_manager *dm,
@@ -8983,7 +9033,7 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 			 * during the PSR-SU was disabled.
 			 */
 			if (acrtc_state->stream->link->psr_settings.psr_version >= DC_PSR_VERSION_SU_1 &&
-			    acrtc_attach->dm_irq_params.allow_psr_entry &&
+			    acrtc_attach->dm_irq_params.allow_sr_entry &&
 #ifdef CONFIG_DRM_AMD_SECURE_DISPLAY
 			    !amdgpu_dm_crc_window_is_activated(acrtc_state->base.crtc) &&
 #endif
@@ -9158,9 +9208,12 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 			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);
+		if (acrtc_state->update_type > UPDATE_TYPE_FAST) {
+			if (acrtc_state->stream->link->replay_settings.replay_allow_active)
+				amdgpu_dm_replay_disable(acrtc_state->stream);
+			if (acrtc_state->stream->link->psr_settings.psr_allow_active)
+				amdgpu_dm_psr_disable(acrtc_state->stream);
+		}
 		mutex_unlock(&dm->dc_lock);
 
 		/*
@@ -9201,57 +9254,7 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 			dm_update_pflip_irq_state(drm_to_adev(dev),
 						  acrtc_attach);
 
-		if (acrtc_state->update_type > UPDATE_TYPE_FAST) {
-			if (acrtc_state->stream->link->replay_settings.config.replay_supported &&
-					!acrtc_state->stream->link->replay_settings.replay_feature_enabled) {
-				struct amdgpu_dm_connector *aconn =
-					(struct amdgpu_dm_connector *)acrtc_state->stream->dm_stream_context;
-				amdgpu_dm_link_setup_replay(acrtc_state->stream->link, aconn);
-			} else if (acrtc_state->stream->link->psr_settings.psr_version != DC_PSR_VERSION_UNSUPPORTED &&
-					!acrtc_state->stream->link->psr_settings.psr_feature_enabled) {
-
-				struct amdgpu_dm_connector *aconn = (struct amdgpu_dm_connector *)
-					acrtc_state->stream->dm_stream_context;
-
-				if (!aconn->disallow_edp_enter_psr)
-					amdgpu_dm_link_setup_psr(acrtc_state->stream);
-			}
-		}
-
-		/* Decrement skip count when PSR is enabled and we're doing fast updates. */
-		if (acrtc_state->update_type == UPDATE_TYPE_FAST &&
-		    acrtc_state->stream->link->psr_settings.psr_feature_enabled) {
-			struct amdgpu_dm_connector *aconn =
-				(struct amdgpu_dm_connector *)acrtc_state->stream->dm_stream_context;
-
-			if (aconn->psr_skip_count > 0)
-				aconn->psr_skip_count--;
-
-			/* Allow PSR when skip count is 0. */
-			acrtc_attach->dm_irq_params.allow_psr_entry = !aconn->psr_skip_count;
-
-			/*
-			 * If sink supports PSR SU, there is no need to rely on
-			 * a vblank event disable request to enable PSR. PSR SU
-			 * can be enabled immediately once OS demonstrates an
-			 * adequate number of fast atomic commits to notify KMD
-			 * of update events. See `vblank_control_worker()`.
-			 */
-			if (acrtc_state->stream->link->psr_settings.psr_version >= DC_PSR_VERSION_SU_1 &&
-			    acrtc_attach->dm_irq_params.allow_psr_entry &&
-#ifdef CONFIG_DRM_AMD_SECURE_DISPLAY
-			    !amdgpu_dm_crc_window_is_activated(acrtc_state->base.crtc) &&
-#endif
-			    !acrtc_state->stream->link->psr_settings.psr_allow_active &&
-			    !aconn->disallow_edp_enter_psr &&
-			    (timestamp_ns -
-			    acrtc_state->stream->link->psr_settings.psr_dirty_rects_change_timestamp_ns) >
-			    500000000)
-				amdgpu_dm_psr_enable(acrtc_state->stream);
-		} else {
-			acrtc_attach->dm_irq_params.allow_psr_entry = false;
-		}
-
+		amdgpu_dm_enable_self_refresh(acrtc_attach, acrtc_state, timestamp_ns);
 		mutex_unlock(&dm->dc_lock);
 	}
 
@@ -12035,7 +12038,7 @@ static int parse_amd_vsdb(struct amdgpu_dm_connector *aconnector,
 			break;
 	}
 
-	while (j < EDID_LENGTH) {
+	while (j < EDID_LENGTH - sizeof(struct amd_vsdb_block)) {
 		struct amd_vsdb_block *amd_vsdb = (struct amd_vsdb_block *)&edid_ext[j];
 		unsigned int ieeeId = (amd_vsdb->ieee_id[2] << 16) | (amd_vsdb->ieee_id[1] << 8) | (amd_vsdb->ieee_id[0]);
 
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
index 2d7755e2b6c3..87a8d1d4f9a1 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
@@ -727,7 +727,7 @@ struct amdgpu_dm_connector {
 	/* Cached display modes */
 	struct drm_display_mode freesync_vid_base;
 
-	int psr_skip_count;
+	int sr_skip_count;
 	bool disallow_edp_enter_psr;
 
 	/* Record progress status of mst*/
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c
index 99014339aaa3..df3d124c4d7a 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c
@@ -251,9 +251,10 @@ static void amdgpu_dm_crtc_vblank_control_worker(struct work_struct *work)
 	else if (dm->active_vblank_irq_count)
 		dm->active_vblank_irq_count--;
 
-	dc_allow_idle_optimizations(dm->dc, dm->active_vblank_irq_count == 0);
-
-	DRM_DEBUG_KMS("Allow idle optimizations (MALL): %d\n", dm->active_vblank_irq_count == 0);
+	if (dm->active_vblank_irq_count > 0) {
+		DRM_DEBUG_KMS("Allow idle optimizations (MALL): false\n");
+		dc_allow_idle_optimizations(dm->dc, false);
+	}
 
 	/*
 	 * Control PSR based on vblank requirements from OS
@@ -265,11 +266,15 @@ static void amdgpu_dm_crtc_vblank_control_worker(struct work_struct *work)
 	 * where the SU region is the full hactive*vactive region. See
 	 * fill_dc_dirty_rects().
 	 */
-	if (vblank_work->stream && vblank_work->stream->link) {
+	if (vblank_work->stream && vblank_work->stream->link && vblank_work->acrtc) {
 		amdgpu_dm_crtc_set_panel_sr_feature(
 			vblank_work, vblank_work->enable,
-			vblank_work->acrtc->dm_irq_params.allow_psr_entry ||
-			vblank_work->stream->link->replay_settings.replay_feature_enabled);
+			vblank_work->acrtc->dm_irq_params.allow_sr_entry);
+	}
+
+	if (dm->active_vblank_irq_count == 0) {
+		DRM_DEBUG_KMS("Allow idle optimizations (MALL): true\n");
+		dc_allow_idle_optimizations(dm->dc, true);
 	}
 
 	mutex_unlock(&dm->dc_lock);
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq_params.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq_params.h
index 5c9303241aeb..6a7ecc1e4602 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq_params.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq_params.h
@@ -33,7 +33,7 @@ struct dm_irq_params {
 	struct mod_vrr_params vrr_params;
 	struct dc_stream_state *stream;
 	int active_planes;
-	bool allow_psr_entry;
+	bool allow_sr_entry;
 	struct mod_freesync_config freesync_config;
 
 #ifdef CONFIG_DEBUG_FS
diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
index be8fbb04ad98..c9a6de110b74 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
@@ -3122,14 +3122,12 @@ static enum bp_result bios_parser_get_vram_info(
 		struct dc_vram_info *info)
 {
 	struct bios_parser *bp = BP_FROM_DCB(dcb);
-	static enum bp_result result = BP_RESULT_BADBIOSTABLE;
+	enum bp_result result = BP_RESULT_BADBIOSTABLE;
 	struct atom_common_table_header *header;
 	struct atom_data_revision revision;
 
 	// vram info moved to umc_info for DCN4x
-	if (dcb->ctx->dce_version >= DCN_VERSION_4_01 &&
-		dcb->ctx->dce_version < DCN_VERSION_MAX &&
-		info && DATA_TABLES(umc_info)) {
+	if (info && DATA_TABLES(umc_info)) {
 		header = GET_IMAGE(struct atom_common_table_header,
 					DATA_TABLES(umc_info));
 
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_state.c b/drivers/gpu/drm/amd/display/dc/core/dc_state.c
index 665157f8d4cb..0d801ce84c1a 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_state.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_state.c
@@ -265,6 +265,9 @@ struct dc_state *dc_state_create_copy(struct dc_state *src_state)
 	dc_state_copy_internal(new_state, src_state);
 
 #ifdef CONFIG_DRM_AMD_DC_FP
+	new_state->bw_ctx.dml2 = NULL;
+	new_state->bw_ctx.dml2_dc_power_source = NULL;
+
 	if (src_state->bw_ctx.dml2 &&
 			!dml2_create_copy(&new_state->bw_ctx.dml2, src_state->bw_ctx.dml2)) {
 		dc_state_release(new_state);
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_pmo/dml2_pmo_dcn4_fams2.c b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_pmo/dml2_pmo_dcn4_fams2.c
index a8bebc60f059..2c2c7322cb16 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_pmo/dml2_pmo_dcn4_fams2.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_pmo/dml2_pmo_dcn4_fams2.c
@@ -30,6 +30,7 @@
 #include "dml2_pmo_dcn4_fams2.h"
 
 static const double MIN_VACTIVE_MARGIN_PCT = 0.25; // We need more than non-zero margin because DET buffer granularity can alter vactive latency hiding
+static const double MIN_BLANK_STUTTER_FACTOR = 3.0;
 
 static const enum dml2_pmo_pstate_strategy base_strategy_list_1_display[][PMO_DCN4_MAX_DISPLAYS] = {
 	// VActive Preferred
@@ -2004,6 +2005,7 @@ bool pmo_dcn4_fams2_init_for_stutter(struct dml2_pmo_init_for_stutter_in_out *in
 	struct dml2_pmo_instance *pmo = in_out->instance;
 	bool stutter_period_meets_z8_eco = true;
 	bool z8_stutter_optimization_too_expensive = false;
+	bool stutter_optimization_too_expensive = false;
 	double line_time_us, vblank_nom_time_us;
 
 	unsigned int i;
@@ -2025,10 +2027,15 @@ bool pmo_dcn4_fams2_init_for_stutter(struct dml2_pmo_init_for_stutter_in_out *in
 		line_time_us = (double)in_out->base_display_config->display_config.stream_descriptors[i].timing.h_total / (in_out->base_display_config->display_config.stream_descriptors[i].timing.pixel_clock_khz * 1000) * 1000000;
 		vblank_nom_time_us = line_time_us * in_out->base_display_config->display_config.stream_descriptors[i].timing.vblank_nom;
 
-		if (vblank_nom_time_us < pmo->soc_bb->power_management_parameters.z8_stutter_exit_latency_us) {
+		if (vblank_nom_time_us < pmo->soc_bb->power_management_parameters.z8_stutter_exit_latency_us * MIN_BLANK_STUTTER_FACTOR) {
 			z8_stutter_optimization_too_expensive = true;
 			break;
 		}
+
+		if (vblank_nom_time_us < pmo->soc_bb->power_management_parameters.stutter_enter_plus_exit_latency_us * MIN_BLANK_STUTTER_FACTOR) {
+			stutter_optimization_too_expensive = true;
+			break;
+		}
 	}
 
 	pmo->scratch.pmo_dcn4.num_stutter_candidates = 0;
@@ -2044,7 +2051,7 @@ bool pmo_dcn4_fams2_init_for_stutter(struct dml2_pmo_init_for_stutter_in_out *in
 		pmo->scratch.pmo_dcn4.z8_vblank_optimizable = false;
 	}
 
-	if (pmo->soc_bb->power_management_parameters.stutter_enter_plus_exit_latency_us > 0) {
+	if (!stutter_optimization_too_expensive && pmo->soc_bb->power_management_parameters.stutter_enter_plus_exit_latency_us > 0) {
 		pmo->scratch.pmo_dcn4.optimal_vblank_reserved_time_for_stutter_us[pmo->scratch.pmo_dcn4.num_stutter_candidates] = (unsigned int)pmo->soc_bb->power_management_parameters.stutter_enter_plus_exit_latency_us;
 		pmo->scratch.pmo_dcn4.num_stutter_candidates++;
 	}
diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
index ee1bcfaae3e3..80e60ea2d11e 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
@@ -1259,33 +1259,26 @@ static int smu_sw_init(void *handle)
 	smu->watermarks_bitmap = 0;
 	smu->power_profile_mode = PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT;
 	smu->default_power_profile_mode = PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT;
-	smu->user_dpm_profile.user_workload_mask = 0;
 
 	atomic_set(&smu->smu_power.power_gate.vcn_gated, 1);
 	atomic_set(&smu->smu_power.power_gate.jpeg_gated, 1);
 	atomic_set(&smu->smu_power.power_gate.vpe_gated, 1);
 	atomic_set(&smu->smu_power.power_gate.umsch_mm_gated, 1);
 
-	smu->workload_priority[PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT] = 0;
-	smu->workload_priority[PP_SMC_POWER_PROFILE_FULLSCREEN3D] = 1;
-	smu->workload_priority[PP_SMC_POWER_PROFILE_POWERSAVING] = 2;
-	smu->workload_priority[PP_SMC_POWER_PROFILE_VIDEO] = 3;
-	smu->workload_priority[PP_SMC_POWER_PROFILE_VR] = 4;
-	smu->workload_priority[PP_SMC_POWER_PROFILE_COMPUTE] = 5;
-	smu->workload_priority[PP_SMC_POWER_PROFILE_CUSTOM] = 6;
+	smu->workload_prority[PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT] = 0;
+	smu->workload_prority[PP_SMC_POWER_PROFILE_FULLSCREEN3D] = 1;
+	smu->workload_prority[PP_SMC_POWER_PROFILE_POWERSAVING] = 2;
+	smu->workload_prority[PP_SMC_POWER_PROFILE_VIDEO] = 3;
+	smu->workload_prority[PP_SMC_POWER_PROFILE_VR] = 4;
+	smu->workload_prority[PP_SMC_POWER_PROFILE_COMPUTE] = 5;
+	smu->workload_prority[PP_SMC_POWER_PROFILE_CUSTOM] = 6;
 
 	if (smu->is_apu ||
-	    !smu_is_workload_profile_available(smu, PP_SMC_POWER_PROFILE_FULLSCREEN3D)) {
-		smu->driver_workload_mask =
-			1 << smu->workload_priority[PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT];
-	} else {
-		smu->driver_workload_mask =
-			1 << smu->workload_priority[PP_SMC_POWER_PROFILE_FULLSCREEN3D];
-		smu->default_power_profile_mode = PP_SMC_POWER_PROFILE_FULLSCREEN3D;
-	}
+	    !smu_is_workload_profile_available(smu, PP_SMC_POWER_PROFILE_FULLSCREEN3D))
+		smu->workload_mask = 1 << smu->workload_prority[PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT];
+	else
+		smu->workload_mask = 1 << smu->workload_prority[PP_SMC_POWER_PROFILE_FULLSCREEN3D];
 
-	smu->workload_mask = smu->driver_workload_mask |
-							smu->user_dpm_profile.user_workload_mask;
 	smu->workload_setting[0] = PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT;
 	smu->workload_setting[1] = PP_SMC_POWER_PROFILE_FULLSCREEN3D;
 	smu->workload_setting[2] = PP_SMC_POWER_PROFILE_POWERSAVING;
@@ -2355,20 +2348,17 @@ static int smu_switch_power_profile(void *handle,
 		return -EINVAL;
 
 	if (!en) {
-		smu->driver_workload_mask &= ~(1 << smu->workload_priority[type]);
+		smu->workload_mask &= ~(1 << smu->workload_prority[type]);
 		index = fls(smu->workload_mask);
 		index = index > 0 && index <= WORKLOAD_POLICY_MAX ? index - 1 : 0;
 		workload[0] = smu->workload_setting[index];
 	} else {
-		smu->driver_workload_mask |= (1 << smu->workload_priority[type]);
+		smu->workload_mask |= (1 << smu->workload_prority[type]);
 		index = fls(smu->workload_mask);
 		index = index <= WORKLOAD_POLICY_MAX ? index - 1 : 0;
 		workload[0] = smu->workload_setting[index];
 	}
 
-	smu->workload_mask = smu->driver_workload_mask |
-						 smu->user_dpm_profile.user_workload_mask;
-
 	if (smu_dpm_ctx->dpm_level != AMD_DPM_FORCED_LEVEL_MANUAL &&
 		smu_dpm_ctx->dpm_level != AMD_DPM_FORCED_LEVEL_PERF_DETERMINISM)
 		smu_bump_power_profile_mode(smu, workload, 0);
@@ -3059,23 +3049,12 @@ static int smu_set_power_profile_mode(void *handle,
 				      uint32_t param_size)
 {
 	struct smu_context *smu = handle;
-	int ret;
 
 	if (!smu->pm_enabled || !smu->adev->pm.dpm_enabled ||
 	    !smu->ppt_funcs->set_power_profile_mode)
 		return -EOPNOTSUPP;
 
-	if (smu->user_dpm_profile.user_workload_mask &
-	   (1 << smu->workload_priority[param[param_size]]))
-	   return 0;
-
-	smu->user_dpm_profile.user_workload_mask =
-		(1 << smu->workload_priority[param[param_size]]);
-	smu->workload_mask = smu->user_dpm_profile.user_workload_mask |
-		smu->driver_workload_mask;
-	ret = smu_bump_power_profile_mode(smu, param, param_size);
-
-	return ret;
+	return smu_bump_power_profile_mode(smu, param, param_size);
 }
 
 static int smu_get_fan_control_mode(void *handle, u32 *fan_mode)
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
index d60d9a12a47e..b44a185d07e8 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
@@ -240,7 +240,6 @@ struct smu_user_dpm_profile {
 	/* user clock state information */
 	uint32_t clk_mask[SMU_CLK_COUNT];
 	uint32_t clk_dependency;
-	uint32_t user_workload_mask;
 };
 
 #define SMU_TABLE_INIT(tables, table_id, s, a, d)	\
@@ -558,8 +557,7 @@ struct smu_context {
 	bool disable_uclk_switch;
 
 	uint32_t workload_mask;
-	uint32_t driver_workload_mask;
-	uint32_t workload_priority[WORKLOAD_POLICY_MAX];
+	uint32_t workload_prority[WORKLOAD_POLICY_MAX];
 	uint32_t workload_setting[WORKLOAD_POLICY_MAX];
 	uint32_t power_profile_mode;
 	uint32_t default_power_profile_mode;
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c
index 31fe512028f4..c0f6b59369b7 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c
@@ -1455,6 +1455,7 @@ static int arcturus_set_power_profile_mode(struct smu_context *smu,
 		return -EINVAL;
 	}
 
+
 	if ((profile_mode == PP_SMC_POWER_PROFILE_CUSTOM) &&
 	     (smu->smc_fw_version >= 0x360d00)) {
 		if (size != 10)
@@ -1522,14 +1523,14 @@ static int arcturus_set_power_profile_mode(struct smu_context *smu,
 
 	ret = smu_cmn_send_smc_msg_with_param(smu,
 					  SMU_MSG_SetWorkloadMask,
-					  smu->workload_mask,
+					  1 << workload_type,
 					  NULL);
 	if (ret) {
 		dev_err(smu->adev->dev, "Fail to set workload type %d\n", workload_type);
 		return ret;
 	}
 
-	smu_cmn_assign_power_profile(smu);
+	smu->power_profile_mode = profile_mode;
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
index bb4ae529ae20..076620fa3ef5 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
@@ -2081,13 +2081,10 @@ static int navi10_set_power_profile_mode(struct smu_context *smu, long *input, u
 						       smu->power_profile_mode);
 	if (workload_type < 0)
 		return -EINVAL;
-
 	ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_SetWorkloadMask,
-				    smu->workload_mask, NULL);
+				    1 << workload_type, NULL);
 	if (ret)
 		dev_err(smu->adev->dev, "[%s] Failed to set work load mask!", __func__);
-	else
-		smu_cmn_assign_power_profile(smu);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
index ca94c52663c0..0d3e1a121b67 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
@@ -1786,13 +1786,10 @@ static int sienna_cichlid_set_power_profile_mode(struct smu_context *smu, long *
 						       smu->power_profile_mode);
 	if (workload_type < 0)
 		return -EINVAL;
-
 	ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_SetWorkloadMask,
-				    smu->workload_mask, NULL);
+				    1 << workload_type, NULL);
 	if (ret)
 		dev_err(smu->adev->dev, "[%s] Failed to set work load mask!", __func__);
-	else
-		smu_cmn_assign_power_profile(smu);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
index 952ee22cbc90..1fe020f1f4db 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
@@ -1079,7 +1079,7 @@ static int vangogh_set_power_profile_mode(struct smu_context *smu, long *input,
 	}
 
 	ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_ActiveProcessNotify,
-				    smu->workload_mask,
+				    1 << workload_type,
 				    NULL);
 	if (ret) {
 		dev_err_once(smu->adev->dev, "Fail to set workload type %d\n",
@@ -1087,7 +1087,7 @@ static int vangogh_set_power_profile_mode(struct smu_context *smu, long *input,
 		return ret;
 	}
 
-	smu_cmn_assign_power_profile(smu);
+	smu->power_profile_mode = profile_mode;
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c
index 62316a6707ef..cc0504b063fa 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c
@@ -890,14 +890,14 @@ static int renoir_set_power_profile_mode(struct smu_context *smu, long *input, u
 	}
 
 	ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_ActiveProcessNotify,
-				    smu->workload_mask,
+				    1 << workload_type,
 				    NULL);
 	if (ret) {
 		dev_err_once(smu->adev->dev, "Fail to set workload type %d\n", workload_type);
 		return ret;
 	}
 
-	smu_cmn_assign_power_profile(smu);
+	smu->power_profile_mode = profile_mode;
 
 	return 0;
 }
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 5dd7ceca64fe..d53e162dcd8d 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
@@ -2485,7 +2485,7 @@ static int smu_v13_0_0_set_power_profile_mode(struct smu_context *smu,
 	DpmActivityMonitorCoeffInt_t *activity_monitor =
 		&(activity_monitor_external.DpmActivityMonitorCoeffInt);
 	int workload_type, ret = 0;
-	u32 workload_mask;
+	u32 workload_mask, selected_workload_mask;
 
 	smu->power_profile_mode = input[size];
 
@@ -2552,7 +2552,7 @@ static int smu_v13_0_0_set_power_profile_mode(struct smu_context *smu,
 	if (workload_type < 0)
 		return -EINVAL;
 
-	workload_mask = 1 << workload_type;
+	selected_workload_mask = workload_mask = 1 << workload_type;
 
 	/* Add optimizations for SMU13.0.0/10.  Reuse the power saving profile */
 	if ((amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(13, 0, 0) &&
@@ -2567,22 +2567,12 @@ static int smu_v13_0_0_set_power_profile_mode(struct smu_context *smu,
 			workload_mask |= 1 << workload_type;
 	}
 
-	smu->workload_mask |= workload_mask;
 	ret = smu_cmn_send_smc_msg_with_param(smu,
 					       SMU_MSG_SetWorkloadMask,
-					       smu->workload_mask,
+					       workload_mask,
 					       NULL);
-	if (!ret) {
-		smu_cmn_assign_power_profile(smu);
-		if (smu->power_profile_mode == PP_SMC_POWER_PROFILE_POWERSAVING) {
-			workload_type = smu_cmn_to_asic_specific_index(smu,
-							       CMN2ASIC_MAPPING_WORKLOAD,
-							       PP_SMC_POWER_PROFILE_FULLSCREEN3D);
-			smu->power_profile_mode = smu->workload_mask & (1 << workload_type)
-										? PP_SMC_POWER_PROFILE_FULLSCREEN3D
-										: PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT;
-		}
-	}
+	if (!ret)
+		smu->workload_mask = selected_workload_mask;
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
index 9d0b19419de0..b891a5e0a396 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
@@ -2499,14 +2499,13 @@ static int smu_v13_0_7_set_power_profile_mode(struct smu_context *smu, long *inp
 						       smu->power_profile_mode);
 	if (workload_type < 0)
 		return -EINVAL;
-
 	ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_SetWorkloadMask,
-				    smu->workload_mask, NULL);
+				    1 << workload_type, NULL);
 
 	if (ret)
 		dev_err(smu->adev->dev, "[%s] Failed to set work load mask!", __func__);
 	else
-		smu_cmn_assign_power_profile(smu);
+		smu->workload_mask = (1 << workload_type);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c
index 8798ebfcea83..84f9b007b59f 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c
@@ -1132,7 +1132,7 @@ static int smu_v14_0_common_get_dpm_level_count(struct smu_context *smu,
 static int smu_v14_0_0_print_clk_levels(struct smu_context *smu,
 					enum smu_clk_type clk_type, char *buf)
 {
-	int i, size = 0, ret = 0;
+	int i, idx, ret = 0, size = 0;
 	uint32_t cur_value = 0, value = 0, count = 0;
 	uint32_t min, max;
 
@@ -1168,7 +1168,8 @@ static int smu_v14_0_0_print_clk_levels(struct smu_context *smu,
 			break;
 
 		for (i = 0; i < count; i++) {
-			ret = smu_v14_0_common_get_dpm_freq_by_index(smu, clk_type, i, &value);
+			idx = (clk_type == SMU_MCLK) ? (count - i - 1) : i;
+			ret = smu_v14_0_common_get_dpm_freq_by_index(smu, clk_type, idx, &value);
 			if (ret)
 				break;
 
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c
index d9f0e7f81ed7..eaf80c5b3e4d 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c
@@ -1508,11 +1508,12 @@ static int smu_v14_0_2_set_power_profile_mode(struct smu_context *smu,
 	if (workload_type < 0)
 		return -EINVAL;
 
-	ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_SetWorkloadMask,
-										  smu->workload_mask, NULL);
-
+	ret = smu_cmn_send_smc_msg_with_param(smu,
+					       SMU_MSG_SetWorkloadMask,
+					       1 << workload_type,
+					       NULL);
 	if (!ret)
-		smu_cmn_assign_power_profile(smu);
+		smu->workload_mask = 1 << workload_type;
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
index bdfc5e617333..91ad434bcdae 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
@@ -1138,14 +1138,6 @@ int smu_cmn_set_mp1_state(struct smu_context *smu,
 	return ret;
 }
 
-void smu_cmn_assign_power_profile(struct smu_context *smu)
-{
-	uint32_t index;
-	index = fls(smu->workload_mask);
-	index = index > 0 && index <= WORKLOAD_POLICY_MAX ? index - 1 : 0;
-	smu->power_profile_mode = smu->workload_setting[index];
-}
-
 bool smu_cmn_is_audio_func_enabled(struct amdgpu_device *adev)
 {
 	struct pci_dev *p = NULL;
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h
index 8a801e389659..1de685defe85 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h
@@ -130,8 +130,6 @@ void smu_cmn_init_soft_gpu_metrics(void *table, uint8_t frev, uint8_t crev);
 int smu_cmn_set_mp1_state(struct smu_context *smu,
 			  enum pp_mp1_state mp1_state);
 
-void smu_cmn_assign_power_profile(struct smu_context *smu);
-
 /*
  * Helper function to make sysfs_emit_at() happy. Align buf to
  * the current page boundary and record the offset.
diff --git a/drivers/gpu/drm/bridge/tc358768.c b/drivers/gpu/drm/bridge/tc358768.c
index 0e8813278a2f..bb1750a3dab0 100644
--- a/drivers/gpu/drm/bridge/tc358768.c
+++ b/drivers/gpu/drm/bridge/tc358768.c
@@ -125,6 +125,9 @@
 #define TC358768_DSI_CONFW_MODE_CLR	(6 << 29)
 #define TC358768_DSI_CONFW_ADDR_DSI_CONTROL	(0x3 << 24)
 
+/* TC358768_DSICMD_TX (0x0600) register */
+#define TC358768_DSI_CMDTX_DC_START	BIT(0)
+
 static const char * const tc358768_supplies[] = {
 	"vddc", "vddmipi", "vddio"
 };
@@ -229,6 +232,21 @@ static void tc358768_update_bits(struct tc358768_priv *priv, u32 reg, u32 mask,
 		tc358768_write(priv, reg, tmp);
 }
 
+static void tc358768_dsicmd_tx(struct tc358768_priv *priv)
+{
+	u32 val;
+
+	/* start transfer */
+	tc358768_write(priv, TC358768_DSICMD_TX, TC358768_DSI_CMDTX_DC_START);
+	if (priv->error)
+		return;
+
+	/* wait transfer completion */
+	priv->error = regmap_read_poll_timeout(priv->regmap, TC358768_DSICMD_TX, val,
+					       (val & TC358768_DSI_CMDTX_DC_START) == 0,
+					       100, 100000);
+}
+
 static int tc358768_sw_reset(struct tc358768_priv *priv)
 {
 	/* Assert Reset */
@@ -516,8 +534,7 @@ static ssize_t tc358768_dsi_host_transfer(struct mipi_dsi_host *host,
 		}
 	}
 
-	/* start transfer */
-	tc358768_write(priv, TC358768_DSICMD_TX, 1);
+	tc358768_dsicmd_tx(priv);
 
 	ret = tc358768_clear_error(priv);
 	if (ret)
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_gsc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_gsc_fw.c
index 551b0d7974ff..5dc0ccd07636 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_gsc_fw.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_gsc_fw.c
@@ -80,6 +80,7 @@ int intel_gsc_fw_get_binary_info(struct intel_uc_fw *gsc_fw, const void *data, s
 	const struct intel_gsc_cpd_header_v2 *cpd_header = NULL;
 	const struct intel_gsc_cpd_entry *cpd_entry = NULL;
 	const struct intel_gsc_manifest_header *manifest;
+	struct intel_uc_fw_ver min_ver = { 0 };
 	size_t min_size = sizeof(*layout);
 	int i;
 
@@ -212,33 +213,46 @@ int intel_gsc_fw_get_binary_info(struct intel_uc_fw *gsc_fw, const void *data, s
 		}
 	}
 
-	if (IS_ARROWLAKE(gt->i915)) {
+	/*
+	 * ARL SKUs require newer firmwares, but the blob is actually common
+	 * across all MTL and ARL SKUs, so we need to do an explicit version check
+	 * here rather than using a separate table entry. If a too old version
+	 * is found, then just don't use GSC rather than aborting the driver load.
+	 * Note that the major number in the GSC FW version is used to indicate
+	 * the platform, so we expect it to always be 102 for MTL/ARL binaries.
+	 */
+	if (IS_ARROWLAKE_S(gt->i915))
+		min_ver = (struct intel_uc_fw_ver){ 102, 0, 10, 1878 };
+	else if (IS_ARROWLAKE_H(gt->i915) || IS_ARROWLAKE_U(gt->i915))
+		min_ver = (struct intel_uc_fw_ver){ 102, 1, 15, 1926 };
+
+	if (IS_METEORLAKE(gt->i915) && gsc->release.major != 102) {
+		gt_info(gt, "Invalid GSC firmware for MTL/ARL, got %d.%d.%d.%d but need 102.x.x.x",
+			gsc->release.major, gsc->release.minor,
+			gsc->release.patch, gsc->release.build);
+			return -EINVAL;
+	}
+
+	if (min_ver.major) {
 		bool too_old = false;
 
-		/*
-		 * ARL requires a newer firmware than MTL did (102.0.10.1878) but the
-		 * firmware is actually common. So, need to do an explicit version check
-		 * here rather than using a separate table entry. And if the older
-		 * MTL-only version is found, then just don't use GSC rather than aborting
-		 * the driver load.
-		 */
-		if (gsc->release.major < 102) {
+		if (gsc->release.minor < min_ver.minor) {
 			too_old = true;
-		} else if (gsc->release.major == 102) {
-			if (gsc->release.minor == 0) {
-				if (gsc->release.patch < 10) {
+		} else if (gsc->release.minor == min_ver.minor) {
+			if (gsc->release.patch < min_ver.patch) {
+				too_old = true;
+			} else if (gsc->release.patch == min_ver.patch) {
+				if (gsc->release.build < min_ver.build)
 					too_old = true;
-				} else if (gsc->release.patch == 10) {
-					if (gsc->release.build < 1878)
-						too_old = true;
-				}
 			}
 		}
 
 		if (too_old) {
-			gt_info(gt, "GSC firmware too old for ARL, got %d.%d.%d.%d but need at least 102.0.10.1878",
+			gt_info(gt, "GSC firmware too old for ARL, got %d.%d.%d.%d but need at least %d.%d.%d.%d",
 				gsc->release.major, gsc->release.minor,
-				gsc->release.patch, gsc->release.build);
+				gsc->release.patch, gsc->release.build,
+				min_ver.major, min_ver.minor,
+				min_ver.patch, min_ver.build);
 			return -EINVAL;
 		}
 	}
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 110340e02a02..0c0c666f11ea 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -546,8 +546,12 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915,
 #define IS_LUNARLAKE(i915) (0 && i915)
 #define IS_BATTLEMAGE(i915)  (0 && i915)
 
-#define IS_ARROWLAKE(i915) \
-	IS_SUBPLATFORM(i915, INTEL_METEORLAKE, INTEL_SUBPLATFORM_ARL)
+#define IS_ARROWLAKE_H(i915) \
+	IS_SUBPLATFORM(i915, INTEL_METEORLAKE, INTEL_SUBPLATFORM_ARL_H)
+#define IS_ARROWLAKE_U(i915) \
+	IS_SUBPLATFORM(i915, INTEL_METEORLAKE, INTEL_SUBPLATFORM_ARL_U)
+#define IS_ARROWLAKE_S(i915) \
+	IS_SUBPLATFORM(i915, INTEL_METEORLAKE, INTEL_SUBPLATFORM_ARL_S)
 #define IS_DG2_G10(i915) \
 	IS_SUBPLATFORM(i915, INTEL_DG2, INTEL_SUBPLATFORM_G10)
 #define IS_DG2_G11(i915) \
diff --git a/drivers/gpu/drm/i915/intel_device_info.c b/drivers/gpu/drm/i915/intel_device_info.c
index 01a650253050..bd0cb707e9d4 100644
--- a/drivers/gpu/drm/i915/intel_device_info.c
+++ b/drivers/gpu/drm/i915/intel_device_info.c
@@ -202,8 +202,16 @@ static const u16 subplatform_g12_ids[] = {
 	INTEL_DG2_G12_IDS(ID),
 };
 
-static const u16 subplatform_arl_ids[] = {
-	INTEL_ARL_IDS(ID),
+static const u16 subplatform_arl_h_ids[] = {
+	INTEL_ARL_H_IDS(ID),
+};
+
+static const u16 subplatform_arl_u_ids[] = {
+	INTEL_ARL_U_IDS(ID),
+};
+
+static const u16 subplatform_arl_s_ids[] = {
+	INTEL_ARL_S_IDS(ID),
 };
 
 static bool find_devid(u16 id, const u16 *p, unsigned int num)
@@ -263,9 +271,15 @@ static void intel_device_info_subplatform_init(struct drm_i915_private *i915)
 	} else if (find_devid(devid, subplatform_g12_ids,
 			      ARRAY_SIZE(subplatform_g12_ids))) {
 		mask = BIT(INTEL_SUBPLATFORM_G12);
-	} else if (find_devid(devid, subplatform_arl_ids,
-			      ARRAY_SIZE(subplatform_arl_ids))) {
-		mask = BIT(INTEL_SUBPLATFORM_ARL);
+	} else if (find_devid(devid, subplatform_arl_h_ids,
+			      ARRAY_SIZE(subplatform_arl_h_ids))) {
+		mask = BIT(INTEL_SUBPLATFORM_ARL_H);
+	} else if (find_devid(devid, subplatform_arl_u_ids,
+			      ARRAY_SIZE(subplatform_arl_u_ids))) {
+		mask = BIT(INTEL_SUBPLATFORM_ARL_U);
+	} else if (find_devid(devid, subplatform_arl_s_ids,
+			      ARRAY_SIZE(subplatform_arl_s_ids))) {
+		mask = BIT(INTEL_SUBPLATFORM_ARL_S);
 	}
 
 	GEM_BUG_ON(mask & ~INTEL_SUBPLATFORM_MASK);
diff --git a/drivers/gpu/drm/i915/intel_device_info.h b/drivers/gpu/drm/i915/intel_device_info.h
index 643ff1bf74ee..a9fcaf33df9e 100644
--- a/drivers/gpu/drm/i915/intel_device_info.h
+++ b/drivers/gpu/drm/i915/intel_device_info.h
@@ -128,7 +128,9 @@ enum intel_platform {
 #define INTEL_SUBPLATFORM_RPLU  2
 
 /* MTL */
-#define INTEL_SUBPLATFORM_ARL	0
+#define INTEL_SUBPLATFORM_ARL_H	0
+#define INTEL_SUBPLATFORM_ARL_U	1
+#define INTEL_SUBPLATFORM_ARL_S	2
 
 enum intel_ppgtt_type {
 	INTEL_PPGTT_NONE = I915_GEM_PPGTT_NONE,
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/r535.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/r535.c
index 027867c2a8c5..99110ab2f44d 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/r535.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/r535.c
@@ -992,7 +992,7 @@ r535_dp_train_target(struct nvkm_outp *outp, u8 target, bool mst, u8 link_nr, u8
 		ctrl->data = data;
 
 		ret = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, &ctrl, sizeof(*ctrl));
-		if (ret == -EAGAIN && ctrl->retryTimeMs) {
+		if ((ret == -EAGAIN || ret == -EBUSY) && ctrl->retryTimeMs) {
 			/*
 			 * Device (likely an eDP panel) isn't ready yet, wait for the time specified
 			 * by GSP before retrying again
@@ -1060,33 +1060,44 @@ r535_dp_aux_xfer(struct nvkm_outp *outp, u8 type, u32 addr, u8 *data, u8 *psize)
 	NV0073_CTRL_DP_AUXCH_CTRL_PARAMS *ctrl;
 	u8 size = *psize;
 	int ret;
+	int retries;
 
-	ctrl = nvkm_gsp_rm_ctrl_get(&disp->rm.objcom, NV0073_CTRL_CMD_DP_AUXCH_CTRL, sizeof(*ctrl));
-	if (IS_ERR(ctrl))
-		return PTR_ERR(ctrl);
+	for (retries = 0; retries < 3; ++retries) {
+		ctrl = nvkm_gsp_rm_ctrl_get(&disp->rm.objcom, NV0073_CTRL_CMD_DP_AUXCH_CTRL, sizeof(*ctrl));
+		if (IS_ERR(ctrl))
+			return PTR_ERR(ctrl);
 
-	ctrl->subDeviceInstance = 0;
-	ctrl->displayId = BIT(outp->index);
-	ctrl->bAddrOnly = !size;
-	ctrl->cmd = type;
-	if (ctrl->bAddrOnly) {
-		ctrl->cmd = NVDEF_SET(ctrl->cmd, NV0073_CTRL, DP_AUXCH_CMD, REQ_TYPE, WRITE);
-		ctrl->cmd = NVDEF_SET(ctrl->cmd, NV0073_CTRL, DP_AUXCH_CMD,  I2C_MOT, FALSE);
-	}
-	ctrl->addr = addr;
-	ctrl->size = !ctrl->bAddrOnly ? (size - 1) : 0;
-	memcpy(ctrl->data, data, size);
+		ctrl->subDeviceInstance = 0;
+		ctrl->displayId = BIT(outp->index);
+		ctrl->bAddrOnly = !size;
+		ctrl->cmd = type;
+		if (ctrl->bAddrOnly) {
+			ctrl->cmd = NVDEF_SET(ctrl->cmd, NV0073_CTRL, DP_AUXCH_CMD, REQ_TYPE, WRITE);
+			ctrl->cmd = NVDEF_SET(ctrl->cmd, NV0073_CTRL, DP_AUXCH_CMD,  I2C_MOT, FALSE);
+		}
+		ctrl->addr = addr;
+		ctrl->size = !ctrl->bAddrOnly ? (size - 1) : 0;
+		memcpy(ctrl->data, data, size);
 
-	ret = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, &ctrl, sizeof(*ctrl));
-	if (ret) {
-		nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl);
-		return ret;
+		ret = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, &ctrl, sizeof(*ctrl));
+		if ((ret == -EAGAIN || ret == -EBUSY) && ctrl->retryTimeMs) {
+			/*
+			 * Device (likely an eDP panel) isn't ready yet, wait for the time specified
+			 * by GSP before retrying again
+			 */
+			nvkm_debug(&disp->engine.subdev,
+				   "Waiting %dms for GSP LT panel delay before retrying in AUX\n",
+				   ctrl->retryTimeMs);
+			msleep(ctrl->retryTimeMs);
+			nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl);
+		} else {
+			memcpy(data, ctrl->data, size);
+			*psize = ctrl->size;
+			ret = ctrl->replyType;
+			nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl);
+			break;
+		}
 	}
-
-	memcpy(data, ctrl->data, size);
-	*psize = ctrl->size;
-	ret = ctrl->replyType;
-	nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/falcon/fw.c b/drivers/gpu/drm/nouveau/nvkm/falcon/fw.c
index a1c8545f1249..cac6d64ab67d 100644
--- a/drivers/gpu/drm/nouveau/nvkm/falcon/fw.c
+++ b/drivers/gpu/drm/nouveau/nvkm/falcon/fw.c
@@ -89,11 +89,6 @@ nvkm_falcon_fw_boot(struct nvkm_falcon_fw *fw, struct nvkm_subdev *user,
 		nvkm_falcon_fw_dtor_sigs(fw);
 	}
 
-	/* after last write to the img, sync dma mappings */
-	dma_sync_single_for_device(fw->fw.device->dev,
-				   fw->fw.phys,
-				   sg_dma_len(&fw->fw.mem.sgl),
-				   DMA_TO_DEVICE);
 
 	FLCNFW_DBG(fw, "resetting");
 	fw->func->reset(fw);
@@ -105,6 +100,12 @@ nvkm_falcon_fw_boot(struct nvkm_falcon_fw *fw, struct nvkm_subdev *user,
 			goto done;
 	}
 
+	/* after last write to the img, sync dma mappings */
+	dma_sync_single_for_device(fw->fw.device->dev,
+				   fw->fw.phys,
+				   sg_dma_len(&fw->fw.mem.sgl),
+				   DMA_TO_DEVICE);
+
 	ret = fw->func->load(fw);
 	if (ret)
 		goto done;
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
index cf58f9da9139..d586aea30898 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
@@ -78,7 +78,7 @@ r535_rpc_status_to_errno(uint32_t rpc_status)
 	switch (rpc_status) {
 	case 0x55: /* NV_ERR_NOT_READY */
 	case 0x66: /* NV_ERR_TIMEOUT_RETRY */
-		return -EAGAIN;
+		return -EBUSY;
 	case 0x51: /* NV_ERR_NO_MEMORY */
 		return -ENOMEM;
 	default:
@@ -601,7 +601,7 @@ r535_gsp_rpc_rm_alloc_push(struct nvkm_gsp_object *object, void *argv, u32 repc)
 
 	if (rpc->status) {
 		ret = ERR_PTR(r535_rpc_status_to_errno(rpc->status));
-		if (PTR_ERR(ret) != -EAGAIN)
+		if (PTR_ERR(ret) != -EAGAIN && PTR_ERR(ret) != -EBUSY)
 			nvkm_error(&gsp->subdev, "RM_ALLOC: 0x%x\n", rpc->status);
 	} else {
 		ret = repc ? rpc->params : NULL;
@@ -660,7 +660,7 @@ r535_gsp_rpc_rm_ctrl_push(struct nvkm_gsp_object *object, void **argv, u32 repc)
 
 	if (rpc->status) {
 		ret = r535_rpc_status_to_errno(rpc->status);
-		if (ret != -EAGAIN)
+		if (ret != -EAGAIN && ret != -EBUSY)
 			nvkm_error(&gsp->subdev, "cli:0x%08x obj:0x%08x ctrl cmd:0x%08x failed: 0x%08x\n",
 				   object->client->object.handle, object->handle, rpc->cmd, rpc->status);
 	}
diff --git a/drivers/gpu/drm/panthor/panthor_mmu.c b/drivers/gpu/drm/panthor/panthor_mmu.c
index d18f32640a79..64378e8f124b 100644
--- a/drivers/gpu/drm/panthor/panthor_mmu.c
+++ b/drivers/gpu/drm/panthor/panthor_mmu.c
@@ -990,6 +990,8 @@ panthor_vm_map_pages(struct panthor_vm *vm, u64 iova, int prot,
 
 		if (!size)
 			break;
+
+		offset = 0;
 	}
 
 	return panthor_vm_flush_range(vm, start_iova, iova - start_iova);
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
index f161f40d8ce4..69900138295b 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
@@ -1093,10 +1093,10 @@ static int vop_plane_atomic_async_check(struct drm_plane *plane,
 	if (!plane->state->fb)
 		return -EINVAL;
 
-	if (state)
-		crtc_state = drm_atomic_get_existing_crtc_state(state,
-								new_plane_state->crtc);
-	else /* Special case for asynchronous cursor updates. */
+	crtc_state = drm_atomic_get_existing_crtc_state(state, new_plane_state->crtc);
+
+	/* Special case for asynchronous cursor updates. */
+	if (!crtc_state)
 		crtc_state = plane->crtc->state;
 
 	return drm_atomic_helper_check_plane_state(plane->state, crtc_state,
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
index 63b8d7591253..10d596cb4b40 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
@@ -1265,6 +1265,8 @@ static int vmw_framebuffer_surface_create_handle(struct drm_framebuffer *fb,
 	struct vmw_framebuffer_surface *vfbs = vmw_framebuffer_to_vfbs(fb);
 	struct vmw_bo *bo = vmw_user_object_buffer(&vfbs->uo);
 
+	if (WARN_ON(!bo))
+		return -EINVAL;
 	return drm_gem_handle_create(file_priv, &bo->tbo.base, handle);
 }
 
diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c
index e147ef1d0578..9a01babe679c 100644
--- a/drivers/gpu/drm/xe/xe_bo.c
+++ b/drivers/gpu/drm/xe/xe_bo.c
@@ -869,8 +869,8 @@ int xe_bo_evict_pinned(struct xe_bo *bo)
 	if (WARN_ON(!xe_bo_is_pinned(bo)))
 		return -EINVAL;
 
-	if (WARN_ON(!xe_bo_is_vram(bo)))
-		return -EINVAL;
+	if (!xe_bo_is_vram(bo))
+		return 0;
 
 	ret = ttm_bo_mem_space(&bo->ttm, &placement, &new_mem, &ctx);
 	if (ret)
@@ -920,6 +920,7 @@ int xe_bo_restore_pinned(struct xe_bo *bo)
 		.interruptible = false,
 	};
 	struct ttm_resource *new_mem;
+	struct ttm_place *place = &bo->placements[0];
 	int ret;
 
 	xe_bo_assert_held(bo);
@@ -930,9 +931,15 @@ int xe_bo_restore_pinned(struct xe_bo *bo)
 	if (WARN_ON(!xe_bo_is_pinned(bo)))
 		return -EINVAL;
 
-	if (WARN_ON(xe_bo_is_vram(bo) || !bo->ttm.ttm))
+	if (WARN_ON(xe_bo_is_vram(bo)))
+		return -EINVAL;
+
+	if (WARN_ON(!bo->ttm.ttm && !xe_bo_is_stolen(bo)))
 		return -EINVAL;
 
+	if (!mem_type_is_vram(place->mem_type))
+		return 0;
+
 	ret = ttm_bo_mem_space(&bo->ttm, &bo->placement, &new_mem, &ctx);
 	if (ret)
 		return ret;
@@ -1702,6 +1709,7 @@ int xe_bo_pin_external(struct xe_bo *bo)
 
 int xe_bo_pin(struct xe_bo *bo)
 {
+	struct ttm_place *place = &bo->placements[0];
 	struct xe_device *xe = xe_bo_device(bo);
 	int err;
 
@@ -1732,21 +1740,21 @@ int xe_bo_pin(struct xe_bo *bo)
 	 */
 	if (IS_DGFX(xe) && !(IS_ENABLED(CONFIG_DRM_XE_DEBUG) &&
 	    bo->flags & XE_BO_FLAG_INTERNAL_TEST)) {
-		struct ttm_place *place = &(bo->placements[0]);
-
 		if (mem_type_is_vram(place->mem_type)) {
 			xe_assert(xe, place->flags & TTM_PL_FLAG_CONTIGUOUS);
 
 			place->fpfn = (xe_bo_addr(bo, 0, PAGE_SIZE) -
 				       vram_region_gpu_offset(bo->ttm.resource)) >> PAGE_SHIFT;
 			place->lpfn = place->fpfn + (bo->size >> PAGE_SHIFT);
-
-			spin_lock(&xe->pinned.lock);
-			list_add_tail(&bo->pinned_link, &xe->pinned.kernel_bo_present);
-			spin_unlock(&xe->pinned.lock);
 		}
 	}
 
+	if (mem_type_is_vram(place->mem_type) || bo->flags & XE_BO_FLAG_GGTT) {
+		spin_lock(&xe->pinned.lock);
+		list_add_tail(&bo->pinned_link, &xe->pinned.kernel_bo_present);
+		spin_unlock(&xe->pinned.lock);
+	}
+
 	ttm_bo_pin(&bo->ttm);
 
 	/*
@@ -1792,23 +1800,18 @@ void xe_bo_unpin_external(struct xe_bo *bo)
 
 void xe_bo_unpin(struct xe_bo *bo)
 {
+	struct ttm_place *place = &bo->placements[0];
 	struct xe_device *xe = xe_bo_device(bo);
 
 	xe_assert(xe, !bo->ttm.base.import_attach);
 	xe_assert(xe, xe_bo_is_pinned(bo));
 
-	if (IS_DGFX(xe) && !(IS_ENABLED(CONFIG_DRM_XE_DEBUG) &&
-	    bo->flags & XE_BO_FLAG_INTERNAL_TEST)) {
-		struct ttm_place *place = &(bo->placements[0]);
-
-		if (mem_type_is_vram(place->mem_type)) {
-			spin_lock(&xe->pinned.lock);
-			xe_assert(xe, !list_empty(&bo->pinned_link));
-			list_del_init(&bo->pinned_link);
-			spin_unlock(&xe->pinned.lock);
-		}
+	if (mem_type_is_vram(place->mem_type) || bo->flags & XE_BO_FLAG_GGTT) {
+		spin_lock(&xe->pinned.lock);
+		xe_assert(xe, !list_empty(&bo->pinned_link));
+		list_del_init(&bo->pinned_link);
+		spin_unlock(&xe->pinned.lock);
 	}
-
 	ttm_bo_unpin(&bo->ttm);
 }
 
diff --git a/drivers/gpu/drm/xe/xe_bo_evict.c b/drivers/gpu/drm/xe/xe_bo_evict.c
index 541b49007d73..8fb2be061003 100644
--- a/drivers/gpu/drm/xe/xe_bo_evict.c
+++ b/drivers/gpu/drm/xe/xe_bo_evict.c
@@ -34,14 +34,22 @@ int xe_bo_evict_all(struct xe_device *xe)
 	u8 id;
 	int ret;
 
-	if (!IS_DGFX(xe))
-		return 0;
-
 	/* User memory */
-	for (mem_type = XE_PL_VRAM0; mem_type <= XE_PL_VRAM1; ++mem_type) {
+	for (mem_type = XE_PL_TT; mem_type <= XE_PL_VRAM1; ++mem_type) {
 		struct ttm_resource_manager *man =
 			ttm_manager_type(bdev, mem_type);
 
+		/*
+		 * On igpu platforms with flat CCS we need to ensure we save and restore any CCS
+		 * state since this state lives inside graphics stolen memory which doesn't survive
+		 * hibernation.
+		 *
+		 * This can be further improved by only evicting objects that we know have actually
+		 * used a compression enabled PAT index.
+		 */
+		if (mem_type == XE_PL_TT && (IS_DGFX(xe) || !xe_device_has_flat_ccs(xe)))
+			continue;
+
 		if (man) {
 			ret = ttm_resource_manager_evict_all(bdev, man);
 			if (ret)
@@ -125,9 +133,6 @@ int xe_bo_restore_kernel(struct xe_device *xe)
 	struct xe_bo *bo;
 	int ret;
 
-	if (!IS_DGFX(xe))
-		return 0;
-
 	spin_lock(&xe->pinned.lock);
 	for (;;) {
 		bo = list_first_entry_or_null(&xe->pinned.evicted,
@@ -159,7 +164,6 @@ int xe_bo_restore_kernel(struct xe_device *xe)
 		 * should setup the iosys map.
 		 */
 		xe_assert(xe, !iosys_map_is_null(&bo->vmap));
-		xe_assert(xe, xe_bo_is_vram(bo));
 
 		xe_bo_put(bo);
 
diff --git a/drivers/gpu/drm/xe/xe_oa.c b/drivers/gpu/drm/xe/xe_oa.c
index 5906df55dfdf..7b099a25e42a 100644
--- a/drivers/gpu/drm/xe/xe_oa.c
+++ b/drivers/gpu/drm/xe/xe_oa.c
@@ -1206,9 +1206,11 @@ static int xe_oa_release(struct inode *inode, struct file *file)
 	struct xe_oa_stream *stream = file->private_data;
 	struct xe_gt *gt = stream->gt;
 
+	xe_pm_runtime_get(gt_to_xe(gt));
 	mutex_lock(&gt->oa.gt_lock);
 	xe_oa_destroy_locked(stream);
 	mutex_unlock(&gt->oa.gt_lock);
+	xe_pm_runtime_put(gt_to_xe(gt));
 
 	/* Release the reference the OA stream kept on the driver */
 	drm_dev_put(&gt_to_xe(gt)->drm);
diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c
index c4cf26f1d149..be0743dac3ff 100644
--- a/drivers/infiniband/core/addr.c
+++ b/drivers/infiniband/core/addr.c
@@ -269,8 +269,6 @@ rdma_find_ndev_for_src_ip_rcu(struct net *net, const struct sockaddr *src_in)
 		break;
 #endif
 	}
-	if (!ret && dev && is_vlan_dev(dev))
-		dev = vlan_dev_real_dev(dev);
 	return ret ? ERR_PTR(ret) : dev;
 }
 
diff --git a/drivers/mailbox/qcom-cpucp-mbox.c b/drivers/mailbox/qcom-cpucp-mbox.c
index e5437c294803..44f4ed15f818 100644
--- a/drivers/mailbox/qcom-cpucp-mbox.c
+++ b/drivers/mailbox/qcom-cpucp-mbox.c
@@ -138,7 +138,7 @@ static int qcom_cpucp_mbox_probe(struct platform_device *pdev)
 		return irq;
 
 	ret = devm_request_irq(dev, irq, qcom_cpucp_mbox_irq_fn,
-			       IRQF_TRIGGER_HIGH, "apss_cpucp_mbox", cpucp);
+			       IRQF_TRIGGER_HIGH | IRQF_NO_SUSPEND, "apss_cpucp_mbox", cpucp);
 	if (ret < 0)
 		return dev_err_probe(dev, ret, "Failed to register irq: %d\n", irq);
 
diff --git a/drivers/media/dvb-core/dvbdev.c b/drivers/media/dvb-core/dvbdev.c
index 14f323fbada7..9df7c213716a 100644
--- a/drivers/media/dvb-core/dvbdev.c
+++ b/drivers/media/dvb-core/dvbdev.c
@@ -530,6 +530,9 @@ int dvb_register_device(struct dvb_adapter *adap, struct dvb_device **pdvbdev,
 	for (minor = 0; minor < MAX_DVB_MINORS; minor++)
 		if (!dvb_minors[minor])
 			break;
+#else
+	minor = nums2minor(adap->num, type, id);
+#endif
 	if (minor >= MAX_DVB_MINORS) {
 		if (new_node) {
 			list_del(&new_node->list_head);
@@ -543,17 +546,7 @@ int dvb_register_device(struct dvb_adapter *adap, struct dvb_device **pdvbdev,
 		mutex_unlock(&dvbdev_register_lock);
 		return -EINVAL;
 	}
-#else
-	minor = nums2minor(adap->num, type, id);
-	if (minor >= MAX_DVB_MINORS) {
-		dvb_media_device_free(dvbdev);
-		list_del(&dvbdev->list_head);
-		kfree(dvbdev);
-		*pdvbdev = NULL;
-		mutex_unlock(&dvbdev_register_lock);
-		return ret;
-	}
-#endif
+
 	dvbdev->minor = minor;
 	dvb_minors[minor] = dvb_device_get(dvbdev);
 	up_write(&minor_rwsem);
diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c
index 41e451235f63..e9f6e4e62290 100644
--- a/drivers/mmc/host/dw_mmc.c
+++ b/drivers/mmc/host/dw_mmc.c
@@ -2957,8 +2957,8 @@ static int dw_mci_init_slot(struct dw_mci *host)
 	if (host->use_dma == TRANS_MODE_IDMAC) {
 		mmc->max_segs = host->ring_size;
 		mmc->max_blk_size = 65535;
-		mmc->max_req_size = DW_MCI_DESC_DATA_LENGTH * host->ring_size;
-		mmc->max_seg_size = mmc->max_req_size;
+		mmc->max_seg_size = 0x1000;
+		mmc->max_req_size = mmc->max_seg_size * host->ring_size;
 		mmc->max_blk_count = mmc->max_req_size / 512;
 	} else if (host->use_dma == TRANS_MODE_EDMAC) {
 		mmc->max_segs = 64;
diff --git a/drivers/mmc/host/sunxi-mmc.c b/drivers/mmc/host/sunxi-mmc.c
index d3bd0ac99ec4..e0ab5fd635e6 100644
--- a/drivers/mmc/host/sunxi-mmc.c
+++ b/drivers/mmc/host/sunxi-mmc.c
@@ -1191,10 +1191,9 @@ static const struct sunxi_mmc_cfg sun50i_a64_emmc_cfg = {
 	.needs_new_timings = true,
 };
 
-static const struct sunxi_mmc_cfg sun50i_a100_cfg = {
+static const struct sunxi_mmc_cfg sun50i_h616_cfg = {
 	.idma_des_size_bits = 16,
 	.idma_des_shift = 2,
-	.clk_delays = NULL,
 	.can_calibrate = true,
 	.mask_data0 = true,
 	.needs_new_timings = true,
@@ -1217,8 +1216,9 @@ static const struct of_device_id sunxi_mmc_of_match[] = {
 	{ .compatible = "allwinner,sun20i-d1-mmc", .data = &sun20i_d1_cfg },
 	{ .compatible = "allwinner,sun50i-a64-mmc", .data = &sun50i_a64_cfg },
 	{ .compatible = "allwinner,sun50i-a64-emmc", .data = &sun50i_a64_emmc_cfg },
-	{ .compatible = "allwinner,sun50i-a100-mmc", .data = &sun50i_a100_cfg },
+	{ .compatible = "allwinner,sun50i-a100-mmc", .data = &sun20i_d1_cfg },
 	{ .compatible = "allwinner,sun50i-a100-emmc", .data = &sun50i_a100_emmc_cfg },
+	{ .compatible = "allwinner,sun50i-h616-mmc", .data = &sun50i_h616_cfg },
 	{ /* sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, sunxi_mmc_of_match);
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index e20bee1bdffd..66725c163263 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -934,6 +934,8 @@ static void bond_hw_addr_swap(struct bonding *bond, struct slave *new_active,
 
 		if (bond->dev->flags & IFF_UP)
 			bond_hw_addr_flush(bond->dev, old_active->dev);
+
+		bond_slave_ns_maddrs_add(bond, old_active);
 	}
 
 	if (new_active) {
@@ -950,6 +952,8 @@ static void bond_hw_addr_swap(struct bonding *bond, struct slave *new_active,
 			dev_mc_sync(new_active->dev, bond->dev);
 			netif_addr_unlock_bh(bond->dev);
 		}
+
+		bond_slave_ns_maddrs_del(bond, new_active);
 	}
 }
 
@@ -2267,6 +2271,11 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
 	bond_compute_features(bond);
 	bond_set_carrier(bond);
 
+	/* Needs to be called before bond_select_active_slave(), which will
+	 * remove the maddrs if the slave is selected as active slave.
+	 */
+	bond_slave_ns_maddrs_add(bond, new_slave);
+
 	if (bond_uses_primary(bond)) {
 		block_netpoll_tx();
 		bond_select_active_slave(bond);
@@ -2276,7 +2285,6 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
 	if (bond_mode_can_use_xmit_hash(bond))
 		bond_update_slave_arr(bond, NULL);
 
-
 	if (!slave_dev->netdev_ops->ndo_bpf ||
 	    !slave_dev->netdev_ops->ndo_xdp_xmit) {
 		if (bond->xdp_prog) {
@@ -2474,6 +2482,12 @@ static int __bond_release_one(struct net_device *bond_dev,
 	if (oldcurrent == slave)
 		bond_change_active_slave(bond, NULL);
 
+	/* Must be called after bond_change_active_slave () as the slave
+	 * might change from an active slave to a backup slave. Then it is
+	 * necessary to clear the maddrs on the backup slave.
+	 */
+	bond_slave_ns_maddrs_del(bond, slave);
+
 	if (bond_is_lb(bond)) {
 		/* Must be called only after the slave has been
 		 * detached from the list and the curr_active_slave
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index 95d59a18c022..327b6ecdc77e 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -15,6 +15,7 @@
 #include <linux/sched/signal.h>
 
 #include <net/bonding.h>
+#include <net/ndisc.h>
 
 static int bond_option_active_slave_set(struct bonding *bond,
 					const struct bond_opt_value *newval);
@@ -1234,6 +1235,68 @@ static int bond_option_arp_ip_targets_set(struct bonding *bond,
 }
 
 #if IS_ENABLED(CONFIG_IPV6)
+static bool slave_can_set_ns_maddr(const struct bonding *bond, struct slave *slave)
+{
+	return BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP &&
+	       !bond_is_active_slave(slave) &&
+	       slave->dev->flags & IFF_MULTICAST;
+}
+
+static void slave_set_ns_maddrs(struct bonding *bond, struct slave *slave, bool add)
+{
+	struct in6_addr *targets = bond->params.ns_targets;
+	char slot_maddr[MAX_ADDR_LEN];
+	int i;
+
+	if (!slave_can_set_ns_maddr(bond, slave))
+		return;
+
+	for (i = 0; i < BOND_MAX_NS_TARGETS; i++) {
+		if (ipv6_addr_any(&targets[i]))
+			break;
+
+		if (!ndisc_mc_map(&targets[i], slot_maddr, slave->dev, 0)) {
+			if (add)
+				dev_mc_add(slave->dev, slot_maddr);
+			else
+				dev_mc_del(slave->dev, slot_maddr);
+		}
+	}
+}
+
+void bond_slave_ns_maddrs_add(struct bonding *bond, struct slave *slave)
+{
+	if (!bond->params.arp_validate)
+		return;
+	slave_set_ns_maddrs(bond, slave, true);
+}
+
+void bond_slave_ns_maddrs_del(struct bonding *bond, struct slave *slave)
+{
+	if (!bond->params.arp_validate)
+		return;
+	slave_set_ns_maddrs(bond, slave, false);
+}
+
+static void slave_set_ns_maddr(struct bonding *bond, struct slave *slave,
+			       struct in6_addr *target, struct in6_addr *slot)
+{
+	char target_maddr[MAX_ADDR_LEN], slot_maddr[MAX_ADDR_LEN];
+
+	if (!bond->params.arp_validate || !slave_can_set_ns_maddr(bond, slave))
+		return;
+
+	/* remove the previous maddr from slave */
+	if (!ipv6_addr_any(slot) &&
+	    !ndisc_mc_map(slot, slot_maddr, slave->dev, 0))
+		dev_mc_del(slave->dev, slot_maddr);
+
+	/* add new maddr on slave if target is set */
+	if (!ipv6_addr_any(target) &&
+	    !ndisc_mc_map(target, target_maddr, slave->dev, 0))
+		dev_mc_add(slave->dev, target_maddr);
+}
+
 static void _bond_options_ns_ip6_target_set(struct bonding *bond, int slot,
 					    struct in6_addr *target,
 					    unsigned long last_rx)
@@ -1243,8 +1306,10 @@ static void _bond_options_ns_ip6_target_set(struct bonding *bond, int slot,
 	struct slave *slave;
 
 	if (slot >= 0 && slot < BOND_MAX_NS_TARGETS) {
-		bond_for_each_slave(bond, slave, iter)
+		bond_for_each_slave(bond, slave, iter) {
 			slave->target_last_arp_rx[slot] = last_rx;
+			slave_set_ns_maddr(bond, slave, target, &targets[slot]);
+		}
 		targets[slot] = *target;
 	}
 }
@@ -1296,15 +1361,30 @@ static int bond_option_ns_ip6_targets_set(struct bonding *bond,
 {
 	return -EPERM;
 }
+
+static void slave_set_ns_maddrs(struct bonding *bond, struct slave *slave, bool add) {}
+
+void bond_slave_ns_maddrs_add(struct bonding *bond, struct slave *slave) {}
+
+void bond_slave_ns_maddrs_del(struct bonding *bond, struct slave *slave) {}
 #endif
 
 static int bond_option_arp_validate_set(struct bonding *bond,
 					const struct bond_opt_value *newval)
 {
+	bool changed = !!bond->params.arp_validate != !!newval->value;
+	struct list_head *iter;
+	struct slave *slave;
+
 	netdev_dbg(bond->dev, "Setting arp_validate to %s (%llu)\n",
 		   newval->string, newval->value);
 	bond->params.arp_validate = newval->value;
 
+	if (changed) {
+		bond_for_each_slave(bond, slave, iter)
+			slave_set_ns_maddrs(bond, slave, !!bond->params.arp_validate);
+	}
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
index 71a168746ebe..deabed1d46a1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
@@ -866,7 +866,7 @@ mlx5_tc_ct_entry_add_rule(struct mlx5_tc_ct_priv *ct_priv,
 	return 0;
 
 err_rule:
-	mlx5_tc_ct_entry_destroy_mod_hdr(ct_priv, zone_rule->attr, zone_rule->mh);
+	mlx5_tc_ct_entry_destroy_mod_hdr(ct_priv, attr, zone_rule->mh);
 	mlx5_put_label_mapping(ct_priv, attr->ct_attr.ct_labels_id);
 err_mod_hdr:
 	kfree(attr);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
index d61be26a4df1..3db31cc10719 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
@@ -660,7 +660,7 @@ tx_sync_info_get(struct mlx5e_ktls_offload_context_tx *priv_tx,
 	while (remaining > 0) {
 		skb_frag_t *frag = &record->frags[i];
 
-		get_page(skb_frag_page(frag));
+		page_ref_inc(skb_frag_page(frag));
 		remaining -= skb_frag_size(frag);
 		info->frags[i++] = *frag;
 	}
@@ -763,7 +763,7 @@ void mlx5e_ktls_tx_handle_resync_dump_comp(struct mlx5e_txqsq *sq,
 	stats = sq->stats;
 
 	mlx5e_tx_dma_unmap(sq->pdev, dma);
-	put_page(wi->resync_dump_frag_page);
+	page_ref_dec(wi->resync_dump_frag_page);
 	stats->tls_dump_packets++;
 	stats->tls_dump_bytes += wi->num_bytes;
 }
@@ -816,12 +816,12 @@ mlx5e_ktls_tx_handle_ooo(struct mlx5e_ktls_offload_context_tx *priv_tx,
 
 err_out:
 	for (; i < info.nr_frags; i++)
-		/* The put_page() here undoes the page ref obtained in tx_sync_info_get().
+		/* The page_ref_dec() here undoes the page ref obtained in tx_sync_info_get().
 		 * Page refs obtained for the DUMP WQEs above (by page_ref_add) will be
 		 * released only upon their completions (or in mlx5e_free_txqsq_descs,
 		 * if channel closes).
 		 */
-		put_page(skb_frag_page(&info.frags[i]));
+		page_ref_dec(skb_frag_page(&info.frags[i]));
 
 	return MLX5E_KTLS_SYNC_FAIL;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 3e11c1c6d4f6..99d0b977ed3d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -4266,7 +4266,8 @@ void mlx5e_set_xdp_feature(struct net_device *netdev)
 	struct mlx5e_params *params = &priv->channels.params;
 	xdp_features_t val;
 
-	if (params->packet_merge.type != MLX5E_PACKET_MERGE_NONE) {
+	if (!netdev->netdev_ops->ndo_bpf ||
+	    params->packet_merge.type != MLX5E_PACKET_MERGE_NONE) {
 		xdp_clear_features_flag(netdev);
 		return;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
index 5bf8318cc48b..1d60465cc2ca 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
@@ -36,6 +36,7 @@
 #include "en.h"
 #include "en/port.h"
 #include "eswitch.h"
+#include "lib/mlx5.h"
 
 static int mlx5e_test_health_info(struct mlx5e_priv *priv)
 {
@@ -247,6 +248,9 @@ static int mlx5e_cond_loopback(struct mlx5e_priv *priv)
 	if (is_mdev_switchdev_mode(priv->mdev))
 		return -EOPNOTSUPP;
 
+	if (mlx5_get_sd(priv->mdev))
+		return -EOPNOTSUPP;
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index a47d6419160d..fb01acbadf73 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -1946,13 +1946,22 @@ lookup_fte_locked(struct mlx5_flow_group *g,
 		fte_tmp = NULL;
 		goto out;
 	}
+
+	nested_down_write_ref_node(&fte_tmp->node, FS_LOCK_CHILD);
+
 	if (!fte_tmp->node.active) {
+		up_write_ref_node(&fte_tmp->node, false);
+
+		if (take_write)
+			up_write_ref_node(&g->node, false);
+		else
+			up_read_ref_node(&g->node);
+
 		tree_put_node(&fte_tmp->node, false);
-		fte_tmp = NULL;
-		goto out;
+
+		return NULL;
 	}
 
-	nested_down_write_ref_node(&fte_tmp->node, FS_LOCK_CHILD);
 out:
 	if (take_write)
 		up_write_ref_node(&g->node, false);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
index 81a9232a03e1..7db9cab9bedf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
@@ -593,9 +593,11 @@ static void irq_pool_free(struct mlx5_irq_pool *pool)
 	kvfree(pool);
 }
 
-static int irq_pools_init(struct mlx5_core_dev *dev, int sf_vec, int pcif_vec)
+static int irq_pools_init(struct mlx5_core_dev *dev, int sf_vec, int pcif_vec,
+			  bool dynamic_vec)
 {
 	struct mlx5_irq_table *table = dev->priv.irq_table;
+	int sf_vec_available = sf_vec;
 	int num_sf_ctrl;
 	int err;
 
@@ -616,6 +618,13 @@ static int irq_pools_init(struct mlx5_core_dev *dev, int sf_vec, int pcif_vec)
 	num_sf_ctrl = DIV_ROUND_UP(mlx5_sf_max_functions(dev),
 				   MLX5_SFS_PER_CTRL_IRQ);
 	num_sf_ctrl = min_t(int, MLX5_IRQ_CTRL_SF_MAX, num_sf_ctrl);
+	if (!dynamic_vec && (num_sf_ctrl + 1) > sf_vec_available) {
+		mlx5_core_dbg(dev,
+			      "Not enough IRQs for SFs control and completion pool, required=%d avail=%d\n",
+			      num_sf_ctrl + 1, sf_vec_available);
+		return 0;
+	}
+
 	table->sf_ctrl_pool = irq_pool_alloc(dev, pcif_vec, num_sf_ctrl,
 					     "mlx5_sf_ctrl",
 					     MLX5_EQ_SHARE_IRQ_MIN_CTRL,
@@ -624,9 +633,11 @@ static int irq_pools_init(struct mlx5_core_dev *dev, int sf_vec, int pcif_vec)
 		err = PTR_ERR(table->sf_ctrl_pool);
 		goto err_pf;
 	}
-	/* init sf_comp_pool */
+	sf_vec_available -= num_sf_ctrl;
+
+	/* init sf_comp_pool, remaining vectors are for the SF completions */
 	table->sf_comp_pool = irq_pool_alloc(dev, pcif_vec + num_sf_ctrl,
-					     sf_vec - num_sf_ctrl, "mlx5_sf_comp",
+					     sf_vec_available, "mlx5_sf_comp",
 					     MLX5_EQ_SHARE_IRQ_MIN_COMP,
 					     MLX5_EQ_SHARE_IRQ_MAX_COMP);
 	if (IS_ERR(table->sf_comp_pool)) {
@@ -715,6 +726,7 @@ int mlx5_irq_table_get_num_comp(struct mlx5_irq_table *table)
 int mlx5_irq_table_create(struct mlx5_core_dev *dev)
 {
 	int num_eqs = mlx5_max_eq_cap_get(dev);
+	bool dynamic_vec;
 	int total_vec;
 	int pcif_vec;
 	int req_vec;
@@ -724,21 +736,31 @@ int mlx5_irq_table_create(struct mlx5_core_dev *dev)
 	if (mlx5_core_is_sf(dev))
 		return 0;
 
+	/* PCI PF vectors usage is limited by online cpus, device EQs and
+	 * PCI MSI-X capability.
+	 */
 	pcif_vec = MLX5_CAP_GEN(dev, num_ports) * num_online_cpus() + 1;
 	pcif_vec = min_t(int, pcif_vec, num_eqs);
+	pcif_vec = min_t(int, pcif_vec, pci_msix_vec_count(dev->pdev));
 
 	total_vec = pcif_vec;
 	if (mlx5_sf_max_functions(dev))
 		total_vec += MLX5_MAX_MSIX_PER_SF * mlx5_sf_max_functions(dev);
 	total_vec = min_t(int, total_vec, pci_msix_vec_count(dev->pdev));
-	pcif_vec = min_t(int, pcif_vec, pci_msix_vec_count(dev->pdev));
 
 	req_vec = pci_msix_can_alloc_dyn(dev->pdev) ? 1 : total_vec;
 	n = pci_alloc_irq_vectors(dev->pdev, 1, req_vec, PCI_IRQ_MSIX);
 	if (n < 0)
 		return n;
 
-	err = irq_pools_init(dev, total_vec - pcif_vec, pcif_vec);
+	/* Further limit vectors of the pools based on platform for non dynamic case */
+	dynamic_vec = pci_msix_can_alloc_dyn(dev->pdev);
+	if (!dynamic_vec) {
+		pcif_vec = min_t(int, n, pcif_vec);
+		total_vec = min_t(int, n, total_vec);
+	}
+
+	err = irq_pools_init(dev, total_vec - pcif_vec, pcif_vec, dynamic_vec);
 	if (err)
 		pci_free_irq_vectors(dev->pdev);
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c
index d68f0c4e7835..9739bc9867c5 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c
@@ -108,7 +108,12 @@ static int intel_eth_plat_probe(struct platform_device *pdev)
 			if (IS_ERR(dwmac->tx_clk))
 				return PTR_ERR(dwmac->tx_clk);
 
-			clk_prepare_enable(dwmac->tx_clk);
+			ret = clk_prepare_enable(dwmac->tx_clk);
+			if (ret) {
+				dev_err(&pdev->dev,
+					"Failed to enable tx_clk\n");
+				return ret;
+			}
 
 			/* Check and configure TX clock rate */
 			rate = clk_get_rate(dwmac->tx_clk);
@@ -119,7 +124,7 @@ static int intel_eth_plat_probe(struct platform_device *pdev)
 				if (ret) {
 					dev_err(&pdev->dev,
 						"Failed to set tx_clk\n");
-					return ret;
+					goto err_tx_clk_disable;
 				}
 			}
 		}
@@ -133,7 +138,7 @@ static int intel_eth_plat_probe(struct platform_device *pdev)
 			if (ret) {
 				dev_err(&pdev->dev,
 					"Failed to set clk_ptp_ref\n");
-				return ret;
+				goto err_tx_clk_disable;
 			}
 		}
 	}
@@ -149,12 +154,15 @@ static int intel_eth_plat_probe(struct platform_device *pdev)
 	}
 
 	ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res);
-	if (ret) {
-		clk_disable_unprepare(dwmac->tx_clk);
-		return ret;
-	}
+	if (ret)
+		goto err_tx_clk_disable;
 
 	return 0;
+
+err_tx_clk_disable:
+	if (dwmac->data->tx_clk_en)
+		clk_disable_unprepare(dwmac->tx_clk);
+	return ret;
 }
 
 static void intel_eth_plat_remove(struct platform_device *pdev)
@@ -162,7 +170,8 @@ static void intel_eth_plat_remove(struct platform_device *pdev)
 	struct intel_dwmac *dwmac = get_stmmac_bsp_priv(&pdev->dev);
 
 	stmmac_pltfr_remove(pdev);
-	clk_disable_unprepare(dwmac->tx_clk);
+	if (dwmac->data->tx_clk_en)
+		clk_disable_unprepare(dwmac->tx_clk);
 }
 
 static struct platform_driver intel_eth_plat_driver = {
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c
index 2a9132d6d743..001857c294fb 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c
@@ -589,9 +589,9 @@ static int mediatek_dwmac_common_data(struct platform_device *pdev,
 
 	plat->mac_interface = priv_plat->phy_mode;
 	if (priv_plat->mac_wol)
-		plat->flags |= STMMAC_FLAG_USE_PHY_WOL;
-	else
 		plat->flags &= ~STMMAC_FLAG_USE_PHY_WOL;
+	else
+		plat->flags |= STMMAC_FLAG_USE_PHY_WOL;
 	plat->riwt_off = 1;
 	plat->maxmtu = ETH_DATA_LEN;
 	plat->host_dma_width = priv_plat->variant->dma_bit_mask;
diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
index 33cb3590a5cd..55d12679b24b 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
@@ -15,6 +15,7 @@
 #include <linux/genalloc.h>
 #include <linux/if_vlan.h>
 #include <linux/interrupt.h>
+#include <linux/io-64-nonatomic-hi-lo.h>
 #include <linux/kernel.h>
 #include <linux/mfd/syscon.h>
 #include <linux/module.h>
@@ -389,6 +390,8 @@ static int prueth_perout_enable(void *clockops_data,
 	struct prueth_emac *emac = clockops_data;
 	u32 reduction_factor = 0, offset = 0;
 	struct timespec64 ts;
+	u64 current_cycle;
+	u64 start_offset;
 	u64 ns_period;
 
 	if (!on)
@@ -427,8 +430,14 @@ static int prueth_perout_enable(void *clockops_data,
 	writel(reduction_factor, emac->prueth->shram.va +
 		TIMESYNC_FW_WC_SYNCOUT_REDUCTION_FACTOR_OFFSET);
 
-	writel(0, emac->prueth->shram.va +
-		TIMESYNC_FW_WC_SYNCOUT_START_TIME_CYCLECOUNT_OFFSET);
+	current_cycle = icssg_read_time(emac->prueth->shram.va +
+					TIMESYNC_FW_WC_CYCLECOUNT_OFFSET);
+
+	/* Rounding of current_cycle count to next second */
+	start_offset = roundup(current_cycle, MSEC_PER_SEC);
+
+	hi_lo_writeq(start_offset, emac->prueth->shram.va +
+		     TIMESYNC_FW_WC_SYNCOUT_START_TIME_CYCLECOUNT_OFFSET);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.h b/drivers/net/ethernet/ti/icssg/icssg_prueth.h
index 4d1c895dacdb..169949acf253 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.h
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.h
@@ -316,6 +316,18 @@ static inline int prueth_emac_slice(struct prueth_emac *emac)
 extern const struct ethtool_ops icssg_ethtool_ops;
 extern const struct dev_pm_ops prueth_dev_pm_ops;
 
+static inline u64 icssg_read_time(const void __iomem *addr)
+{
+	u32 low, high;
+
+	do {
+		high = readl(addr + 4);
+		low = readl(addr);
+	} while (high != readl(addr + 4));
+
+	return low + ((u64)high << 32);
+}
+
 /* Classifier helpers */
 void icssg_class_set_mac_addr(struct regmap *miig_rt, int slice, u8 *mac);
 void icssg_class_set_host_mac_addr(struct regmap *miig_rt, const u8 *mac);
diff --git a/drivers/net/ethernet/vertexcom/mse102x.c b/drivers/net/ethernet/vertexcom/mse102x.c
index 33ef3a49de8e..bccf0ac66b1a 100644
--- a/drivers/net/ethernet/vertexcom/mse102x.c
+++ b/drivers/net/ethernet/vertexcom/mse102x.c
@@ -437,13 +437,15 @@ static void mse102x_tx_work(struct work_struct *work)
 	mse = &mses->mse102x;
 
 	while ((txb = skb_dequeue(&mse->txq))) {
+		unsigned int len = max_t(unsigned int, txb->len, ETH_ZLEN);
+
 		mutex_lock(&mses->lock);
 		ret = mse102x_tx_pkt_spi(mse, txb, work_timeout);
 		mutex_unlock(&mses->lock);
 		if (ret) {
 			mse->ndev->stats.tx_dropped++;
 		} else {
-			mse->ndev->stats.tx_bytes += txb->len;
+			mse->ndev->stats.tx_bytes += len;
 			mse->ndev->stats.tx_packets++;
 		}
 
diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index 51c526d227fa..ed60836180b7 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -78,7 +78,7 @@ struct phylink {
 	unsigned int pcs_neg_mode;
 	unsigned int pcs_state;
 
-	bool mac_link_dropped;
+	bool link_failed;
 	bool using_mac_select_pcs;
 
 	struct sfp_bus *sfp_bus;
@@ -1475,9 +1475,9 @@ static void phylink_resolve(struct work_struct *w)
 		cur_link_state = pl->old_link_state;
 
 	if (pl->phylink_disable_state) {
-		pl->mac_link_dropped = false;
+		pl->link_failed = false;
 		link_state.link = false;
-	} else if (pl->mac_link_dropped) {
+	} else if (pl->link_failed) {
 		link_state.link = false;
 		retrigger = true;
 	} else {
@@ -1572,7 +1572,7 @@ static void phylink_resolve(struct work_struct *w)
 			phylink_link_up(pl, link_state);
 	}
 	if (!link_state.link && retrigger) {
-		pl->mac_link_dropped = false;
+		pl->link_failed = false;
 		queue_work(system_power_efficient_wq, &pl->resolve);
 	}
 	mutex_unlock(&pl->state_mutex);
@@ -1793,6 +1793,8 @@ static void phylink_phy_change(struct phy_device *phydev, bool up)
 		pl->phy_state.pause |= MLO_PAUSE_RX;
 	pl->phy_state.interface = phydev->interface;
 	pl->phy_state.link = up;
+	if (!up)
+		pl->link_failed = true;
 	mutex_unlock(&pl->state_mutex);
 
 	phylink_run_resolve(pl);
@@ -2116,7 +2118,7 @@ EXPORT_SYMBOL_GPL(phylink_disconnect_phy);
 static void phylink_link_changed(struct phylink *pl, bool up, const char *what)
 {
 	if (!up)
-		pl->mac_link_dropped = true;
+		pl->link_failed = true;
 	phylink_run_resolve(pl);
 	phylink_dbg(pl, "%s link %s\n", what, up ? "up" : "down");
 }
@@ -2750,7 +2752,7 @@ int phylink_ethtool_set_pauseparam(struct phylink *pl,
 	 * link will cycle.
 	 */
 	if (manual_changed) {
-		pl->mac_link_dropped = true;
+		pl->link_failed = true;
 		phylink_run_resolve(pl);
 	}
 
diff --git a/drivers/perf/riscv_pmu_sbi.c b/drivers/perf/riscv_pmu_sbi.c
index 671dc55cbd3a..bc562c759e1e 100644
--- a/drivers/perf/riscv_pmu_sbi.c
+++ b/drivers/perf/riscv_pmu_sbi.c
@@ -1380,8 +1380,9 @@ static int pmu_sbi_device_probe(struct platform_device *pdev)
 			goto out_unregister;
 
 		cpu = get_cpu();
-
 		ret = pmu_sbi_snapshot_setup(pmu, cpu);
+		put_cpu();
+
 		if (ret) {
 			/* Snapshot is an optional feature. Continue if not available */
 			pmu_sbi_snapshot_free(pmu);
@@ -1395,7 +1396,6 @@ static int pmu_sbi_device_probe(struct platform_device *pdev)
 			 */
 			static_branch_enable(&sbi_pmu_snapshot_available);
 		}
-		put_cpu();
 	}
 
 	register_sysctl("kernel", sbi_pmu_sysctl_table);
diff --git a/drivers/pmdomain/arm/scmi_perf_domain.c b/drivers/pmdomain/arm/scmi_perf_domain.c
index d7ef46ccd9b8..3693423459c9 100644
--- a/drivers/pmdomain/arm/scmi_perf_domain.c
+++ b/drivers/pmdomain/arm/scmi_perf_domain.c
@@ -125,7 +125,8 @@ static int scmi_perf_domain_probe(struct scmi_device *sdev)
 		scmi_pd->ph = ph;
 		scmi_pd->genpd.name = scmi_pd->info->name;
 		scmi_pd->genpd.flags = GENPD_FLAG_ALWAYS_ON |
-				       GENPD_FLAG_OPP_TABLE_FW;
+				       GENPD_FLAG_OPP_TABLE_FW |
+				       GENPD_FLAG_DEV_NAME_FW;
 		scmi_pd->genpd.set_performance_state = scmi_pd_set_perf_state;
 		scmi_pd->genpd.attach_dev = scmi_pd_attach_dev;
 		scmi_pd->genpd.detach_dev = scmi_pd_detach_dev;
diff --git a/drivers/pmdomain/core.c b/drivers/pmdomain/core.c
index 3a4e59b93677..8a4a7850450c 100644
--- a/drivers/pmdomain/core.c
+++ b/drivers/pmdomain/core.c
@@ -7,6 +7,7 @@
 #define pr_fmt(fmt) "PM: " fmt
 
 #include <linux/delay.h>
+#include <linux/idr.h>
 #include <linux/kernel.h>
 #include <linux/io.h>
 #include <linux/platform_device.h>
@@ -23,6 +24,9 @@
 #include <linux/cpu.h>
 #include <linux/debugfs.h>
 
+/* Provides a unique ID for each genpd device */
+static DEFINE_IDA(genpd_ida);
+
 #define GENPD_RETRY_MAX_MS	250		/* Approximate */
 
 #define GENPD_DEV_CALLBACK(genpd, type, callback, dev)		\
@@ -129,6 +133,7 @@ static const struct genpd_lock_ops genpd_spin_ops = {
 #define genpd_is_cpu_domain(genpd)	(genpd->flags & GENPD_FLAG_CPU_DOMAIN)
 #define genpd_is_rpm_always_on(genpd)	(genpd->flags & GENPD_FLAG_RPM_ALWAYS_ON)
 #define genpd_is_opp_table_fw(genpd)	(genpd->flags & GENPD_FLAG_OPP_TABLE_FW)
+#define genpd_is_dev_name_fw(genpd)	(genpd->flags & GENPD_FLAG_DEV_NAME_FW)
 
 static inline bool irq_safe_dev_in_sleep_domain(struct device *dev,
 		const struct generic_pm_domain *genpd)
@@ -147,7 +152,7 @@ static inline bool irq_safe_dev_in_sleep_domain(struct device *dev,
 
 	if (ret)
 		dev_warn_once(dev, "PM domain %s will not be powered off\n",
-				genpd->name);
+			      dev_name(&genpd->dev));
 
 	return ret;
 }
@@ -232,7 +237,7 @@ static void genpd_debug_remove(struct generic_pm_domain *genpd)
 	if (!genpd_debugfs_dir)
 		return;
 
-	debugfs_lookup_and_remove(genpd->name, genpd_debugfs_dir);
+	debugfs_lookup_and_remove(dev_name(&genpd->dev), genpd_debugfs_dir);
 }
 
 static void genpd_update_accounting(struct generic_pm_domain *genpd)
@@ -689,7 +694,7 @@ static int _genpd_power_on(struct generic_pm_domain *genpd, bool timed)
 	genpd->states[state_idx].power_on_latency_ns = elapsed_ns;
 	genpd->gd->max_off_time_changed = true;
 	pr_debug("%s: Power-%s latency exceeded, new value %lld ns\n",
-		 genpd->name, "on", elapsed_ns);
+		 dev_name(&genpd->dev), "on", elapsed_ns);
 
 out:
 	raw_notifier_call_chain(&genpd->power_notifiers, GENPD_NOTIFY_ON, NULL);
@@ -740,7 +745,7 @@ static int _genpd_power_off(struct generic_pm_domain *genpd, bool timed)
 	genpd->states[state_idx].power_off_latency_ns = elapsed_ns;
 	genpd->gd->max_off_time_changed = true;
 	pr_debug("%s: Power-%s latency exceeded, new value %lld ns\n",
-		 genpd->name, "off", elapsed_ns);
+		 dev_name(&genpd->dev), "off", elapsed_ns);
 
 out:
 	raw_notifier_call_chain(&genpd->power_notifiers, GENPD_NOTIFY_OFF,
@@ -1898,7 +1903,7 @@ int dev_pm_genpd_add_notifier(struct device *dev, struct notifier_block *nb)
 
 	if (ret) {
 		dev_warn(dev, "failed to add notifier for PM domain %s\n",
-			 genpd->name);
+			 dev_name(&genpd->dev));
 		return ret;
 	}
 
@@ -1945,7 +1950,7 @@ int dev_pm_genpd_remove_notifier(struct device *dev)
 
 	if (ret) {
 		dev_warn(dev, "failed to remove notifier for PM domain %s\n",
-			 genpd->name);
+			 dev_name(&genpd->dev));
 		return ret;
 	}
 
@@ -1971,7 +1976,7 @@ static int genpd_add_subdomain(struct generic_pm_domain *genpd,
 	 */
 	if (!genpd_is_irq_safe(genpd) && genpd_is_irq_safe(subdomain)) {
 		WARN(1, "Parent %s of subdomain %s must be IRQ safe\n",
-				genpd->name, subdomain->name);
+		     dev_name(&genpd->dev), subdomain->name);
 		return -EINVAL;
 	}
 
@@ -2046,7 +2051,7 @@ int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd,
 
 	if (!list_empty(&subdomain->parent_links) || subdomain->device_count) {
 		pr_warn("%s: unable to remove subdomain %s\n",
-			genpd->name, subdomain->name);
+			dev_name(&genpd->dev), subdomain->name);
 		ret = -EBUSY;
 		goto out;
 	}
@@ -2180,6 +2185,7 @@ int pm_genpd_init(struct generic_pm_domain *genpd,
 	genpd->status = is_off ? GENPD_STATE_OFF : GENPD_STATE_ON;
 	genpd->device_count = 0;
 	genpd->provider = NULL;
+	genpd->device_id = -ENXIO;
 	genpd->has_provider = false;
 	genpd->accounting_time = ktime_get_mono_fast_ns();
 	genpd->domain.ops.runtime_suspend = genpd_runtime_suspend;
@@ -2220,7 +2226,18 @@ int pm_genpd_init(struct generic_pm_domain *genpd,
 		return ret;
 
 	device_initialize(&genpd->dev);
-	dev_set_name(&genpd->dev, "%s", genpd->name);
+
+	if (!genpd_is_dev_name_fw(genpd)) {
+		dev_set_name(&genpd->dev, "%s", genpd->name);
+	} else {
+		ret = ida_alloc(&genpd_ida, GFP_KERNEL);
+		if (ret < 0) {
+			put_device(&genpd->dev);
+			return ret;
+		}
+		genpd->device_id = ret;
+		dev_set_name(&genpd->dev, "%s_%u", genpd->name, genpd->device_id);
+	}
 
 	mutex_lock(&gpd_list_lock);
 	list_add(&genpd->gpd_list_node, &gpd_list);
@@ -2242,13 +2259,13 @@ static int genpd_remove(struct generic_pm_domain *genpd)
 
 	if (genpd->has_provider) {
 		genpd_unlock(genpd);
-		pr_err("Provider present, unable to remove %s\n", genpd->name);
+		pr_err("Provider present, unable to remove %s\n", dev_name(&genpd->dev));
 		return -EBUSY;
 	}
 
 	if (!list_empty(&genpd->parent_links) || genpd->device_count) {
 		genpd_unlock(genpd);
-		pr_err("%s: unable to remove %s\n", __func__, genpd->name);
+		pr_err("%s: unable to remove %s\n", __func__, dev_name(&genpd->dev));
 		return -EBUSY;
 	}
 
@@ -2262,9 +2279,11 @@ static int genpd_remove(struct generic_pm_domain *genpd)
 	genpd_unlock(genpd);
 	genpd_debug_remove(genpd);
 	cancel_work_sync(&genpd->power_off_work);
+	if (genpd->device_id != -ENXIO)
+		ida_free(&genpd_ida, genpd->device_id);
 	genpd_free_data(genpd);
 
-	pr_debug("%s: removed %s\n", __func__, genpd->name);
+	pr_debug("%s: removed %s\n", __func__, dev_name(&genpd->dev));
 
 	return 0;
 }
@@ -3226,12 +3245,12 @@ static int genpd_summary_one(struct seq_file *s,
 	else
 		snprintf(state, sizeof(state), "%s",
 			 status_lookup[genpd->status]);
-	seq_printf(s, "%-30s  %-30s  %u", genpd->name, state, genpd->performance_state);
+	seq_printf(s, "%-30s  %-30s  %u", dev_name(&genpd->dev), state, genpd->performance_state);
 
 	/*
 	 * Modifications on the list require holding locks on both
 	 * parent and child, so we are safe.
-	 * Also genpd->name is immutable.
+	 * Also the device name is immutable.
 	 */
 	list_for_each_entry(link, &genpd->parent_links, parent_node) {
 		if (list_is_first(&link->parent_node, &genpd->parent_links))
@@ -3456,7 +3475,7 @@ static void genpd_debug_add(struct generic_pm_domain *genpd)
 	if (!genpd_debugfs_dir)
 		return;
 
-	d = debugfs_create_dir(genpd->name, genpd_debugfs_dir);
+	d = debugfs_create_dir(dev_name(&genpd->dev), genpd_debugfs_dir);
 
 	debugfs_create_file("current_state", 0444,
 			    d, genpd, &status_fops);
diff --git a/drivers/pmdomain/imx/imx93-blk-ctrl.c b/drivers/pmdomain/imx/imx93-blk-ctrl.c
index 904ffa55b8f4..b10348ac10f0 100644
--- a/drivers/pmdomain/imx/imx93-blk-ctrl.c
+++ b/drivers/pmdomain/imx/imx93-blk-ctrl.c
@@ -313,7 +313,9 @@ static void imx93_blk_ctrl_remove(struct platform_device *pdev)
 
 	of_genpd_del_provider(pdev->dev.of_node);
 
-	for (i = 0; bc->onecell_data.num_domains; i++) {
+	pm_runtime_disable(&pdev->dev);
+
+	for (i = 0; i < bc->onecell_data.num_domains; i++) {
 		struct imx93_blk_ctrl_domain *domain = &bc->domains[i];
 
 		pm_genpd_remove(&domain->genpd);
diff --git a/drivers/vdpa/mlx5/core/mr.c b/drivers/vdpa/mlx5/core/mr.c
index bf56f3d69625..f1da0b7e08e9 100644
--- a/drivers/vdpa/mlx5/core/mr.c
+++ b/drivers/vdpa/mlx5/core/mr.c
@@ -232,7 +232,7 @@ static int map_direct_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_direct_mr
 	struct page *pg;
 	unsigned int nsg;
 	int sglen;
-	u64 pa;
+	u64 pa, offset;
 	u64 paend;
 	struct scatterlist *sg;
 	struct device *dma = mvdev->vdev.dma_dev;
@@ -255,8 +255,10 @@ static int map_direct_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_direct_mr
 	sg = mr->sg_head.sgl;
 	for (map = vhost_iotlb_itree_first(iotlb, mr->start, mr->end - 1);
 	     map; map = vhost_iotlb_itree_next(map, mr->start, mr->end - 1)) {
-		paend = map->addr + maplen(map, mr);
-		for (pa = map->addr; pa < paend; pa += sglen) {
+		offset = mr->start > map->start ? mr->start - map->start : 0;
+		pa = map->addr + offset;
+		paend = map->addr + offset + maplen(map, mr);
+		for (; pa < paend; pa += sglen) {
 			pg = pfn_to_page(__phys_to_pfn(pa));
 			if (!sg) {
 				mlx5_vdpa_warn(mvdev, "sg null. start 0x%llx, end 0x%llx\n",
diff --git a/drivers/vdpa/solidrun/snet_main.c b/drivers/vdpa/solidrun/snet_main.c
index 99428a04068d..c8b74980dbd1 100644
--- a/drivers/vdpa/solidrun/snet_main.c
+++ b/drivers/vdpa/solidrun/snet_main.c
@@ -555,7 +555,7 @@ static const struct vdpa_config_ops snet_config_ops = {
 
 static int psnet_open_pf_bar(struct pci_dev *pdev, struct psnet *psnet)
 {
-	char name[50];
+	char *name;
 	int ret, i, mask = 0;
 	/* We don't know which BAR will be used to communicate..
 	 * We will map every bar with len > 0.
@@ -573,7 +573,10 @@ static int psnet_open_pf_bar(struct pci_dev *pdev, struct psnet *psnet)
 		return -ENODEV;
 	}
 
-	snprintf(name, sizeof(name), "psnet[%s]-bars", pci_name(pdev));
+	name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "psnet[%s]-bars", pci_name(pdev));
+	if (!name)
+		return -ENOMEM;
+
 	ret = pcim_iomap_regions(pdev, mask, name);
 	if (ret) {
 		SNET_ERR(pdev, "Failed to request and map PCI BARs\n");
@@ -590,10 +593,13 @@ static int psnet_open_pf_bar(struct pci_dev *pdev, struct psnet *psnet)
 
 static int snet_open_vf_bar(struct pci_dev *pdev, struct snet *snet)
 {
-	char name[50];
+	char *name;
 	int ret;
 
-	snprintf(name, sizeof(name), "snet[%s]-bar", pci_name(pdev));
+	name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "snet[%s]-bars", pci_name(pdev));
+	if (!name)
+		return -ENOMEM;
+
 	/* Request and map BAR */
 	ret = pcim_iomap_regions(pdev, BIT(snet->psnet->cfg.vf_bar), name);
 	if (ret) {
diff --git a/drivers/vdpa/virtio_pci/vp_vdpa.c b/drivers/vdpa/virtio_pci/vp_vdpa.c
index ac4ab22f7d8b..16380764275e 100644
--- a/drivers/vdpa/virtio_pci/vp_vdpa.c
+++ b/drivers/vdpa/virtio_pci/vp_vdpa.c
@@ -612,7 +612,11 @@ static int vp_vdpa_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto mdev_err;
 	}
 
-	mdev_id = kzalloc(sizeof(struct virtio_device_id), GFP_KERNEL);
+	/*
+	 * id_table should be a null terminated array, so allocate one additional
+	 * entry here, see vdpa_mgmtdev_get_classes().
+	 */
+	mdev_id = kcalloc(2, sizeof(struct virtio_device_id), GFP_KERNEL);
 	if (!mdev_id) {
 		err = -ENOMEM;
 		goto mdev_id_err;
@@ -632,8 +636,8 @@ static int vp_vdpa_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto probe_err;
 	}
 
-	mdev_id->device = mdev->id.device;
-	mdev_id->vendor = mdev->id.vendor;
+	mdev_id[0].device = mdev->id.device;
+	mdev_id[0].vendor = mdev->id.vendor;
 	mgtdev->id_table = mdev_id;
 	mgtdev->max_supported_vqs = vp_modern_get_num_queues(mdev);
 	mgtdev->supported_features = vp_modern_get_features(mdev);