2786 files changed, 47430 insertions, 22657 deletions

diff --git a/drivers/accel/habanalabs/common/memory.c b/drivers/accel/habanalabs/common/memory.c
index 3348ad12c237..11c55fd76db5 100644
--- a/drivers/accel/habanalabs/common/memory.c
+++ b/drivers/accel/habanalabs/common/memory.c
@@ -1829,9 +1829,6 @@ static void hl_release_dmabuf(struct dma_buf *dmabuf)
 	struct hl_dmabuf_priv *hl_dmabuf = dmabuf->priv;
 	struct hl_ctx *ctx;
 
-	if (!hl_dmabuf)
-		return;
-
 	ctx = hl_dmabuf->ctx;
 
 	if (hl_dmabuf->memhash_hnode)
@@ -1859,7 +1856,12 @@ static int export_dmabuf(struct hl_ctx *ctx,
 {
 	DEFINE_DMA_BUF_EXPORT_INFO(exp_info);
 	struct hl_device *hdev = ctx->hdev;
-	int rc, fd;
+	CLASS(get_unused_fd, fd)(flags);
+
+	if (fd < 0) {
+		dev_err(hdev->dev, "failed to get a file descriptor for a dma-buf, %d\n", fd);
+		return fd;
+	}
 
 	exp_info.ops = &habanalabs_dmabuf_ops;
 	exp_info.size = total_size;
@@ -1872,13 +1874,6 @@ static int export_dmabuf(struct hl_ctx *ctx,
 		return PTR_ERR(hl_dmabuf->dmabuf);
 	}
 
-	fd = dma_buf_fd(hl_dmabuf->dmabuf, flags);
-	if (fd < 0) {
-		dev_err(hdev->dev, "failed to get a file descriptor for a dma-buf, %d\n", fd);
-		rc = fd;
-		goto err_dma_buf_put;
-	}
-
 	hl_dmabuf->ctx = ctx;
 	hl_ctx_get(hl_dmabuf->ctx);
 	atomic_inc(&ctx->hdev->dmabuf_export_cnt);
@@ -1890,13 +1885,9 @@ static int export_dmabuf(struct hl_ctx *ctx,
 	get_file(ctx->hpriv->file_priv->filp);
 
 	*dmabuf_fd = fd;
+	fd_install(take_fd(fd), hl_dmabuf->dmabuf->file);
 
 	return 0;
-
-err_dma_buf_put:
-	hl_dmabuf->dmabuf->priv = NULL;
-	dma_buf_put(hl_dmabuf->dmabuf);
-	return rc;
 }
 
 static int validate_export_params_common(struct hl_device *hdev, u64 addr, u64 size, u64 offset)
diff --git a/drivers/accel/ivpu/Kconfig b/drivers/accel/ivpu/Kconfig
index 682c53245286..e4d418b44626 100644
--- a/drivers/accel/ivpu/Kconfig
+++ b/drivers/accel/ivpu/Kconfig
@@ -8,6 +8,7 @@ config DRM_ACCEL_IVPU
 	select FW_LOADER
 	select DRM_GEM_SHMEM_HELPER
 	select GENERIC_ALLOCATOR
+	select WANT_DEV_COREDUMP
 	help
 	  Choose this option if you have a system with an 14th generation
 	  Intel CPU (Meteor Lake) or newer. Intel NPU (formerly called Intel VPU)
diff --git a/drivers/accel/ivpu/Makefile b/drivers/accel/ivpu/Makefile
index ebd682a42eb1..232ea6d28c6e 100644
--- a/drivers/accel/ivpu/Makefile
+++ b/drivers/accel/ivpu/Makefile
@@ -19,5 +19,6 @@ intel_vpu-y := \
 	ivpu_sysfs.o
 
 intel_vpu-$(CONFIG_DEBUG_FS) += ivpu_debugfs.o
+intel_vpu-$(CONFIG_DEV_COREDUMP) += ivpu_coredump.o
 
 obj-$(CONFIG_DRM_ACCEL_IVPU) += intel_vpu.o
diff --git a/drivers/accel/ivpu/ivpu_coredump.c b/drivers/accel/ivpu/ivpu_coredump.c
new file mode 100644
index 000000000000..16ad0c30818c
--- /dev/null
+++ b/drivers/accel/ivpu/ivpu_coredump.c
@@ -0,0 +1,39 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020-2024 Intel Corporation
+ */
+
+#include <linux/devcoredump.h>
+#include <linux/firmware.h>
+
+#include "ivpu_coredump.h"
+#include "ivpu_fw.h"
+#include "ivpu_gem.h"
+#include "vpu_boot_api.h"
+
+#define CRASH_DUMP_HEADER "Intel NPU crash dump"
+#define CRASH_DUMP_HEADERS_SIZE SZ_4K
+
+void ivpu_dev_coredump(struct ivpu_device *vdev)
+{
+	struct drm_print_iterator pi = {};
+	struct drm_printer p;
+	size_t coredump_size;
+	char *coredump;
+
+	coredump_size = CRASH_DUMP_HEADERS_SIZE + FW_VERSION_HEADER_SIZE +
+			ivpu_bo_size(vdev->fw->mem_log_crit) + ivpu_bo_size(vdev->fw->mem_log_verb);
+	coredump = vmalloc(coredump_size);
+	if (!coredump)
+		return;
+
+	pi.data = coredump;
+	pi.remain = coredump_size;
+	p = drm_coredump_printer(&pi);
+
+	drm_printf(&p, "%s\n", CRASH_DUMP_HEADER);
+	drm_printf(&p, "FW version: %s\n", vdev->fw->version);
+	ivpu_fw_log_print(vdev, false, &p);
+
+	dev_coredumpv(vdev->drm.dev, coredump, pi.offset, GFP_KERNEL);
+}
diff --git a/drivers/accel/ivpu/ivpu_coredump.h b/drivers/accel/ivpu/ivpu_coredump.h
new file mode 100644
index 000000000000..8efb09d02441
--- /dev/null
+++ b/drivers/accel/ivpu/ivpu_coredump.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2020-2024 Intel Corporation
+ */
+
+#ifndef __IVPU_COREDUMP_H__
+#define __IVPU_COREDUMP_H__
+
+#include <drm/drm_print.h>
+
+#include "ivpu_drv.h"
+#include "ivpu_fw_log.h"
+
+#ifdef CONFIG_DEV_COREDUMP
+void ivpu_dev_coredump(struct ivpu_device *vdev);
+#else
+static inline void ivpu_dev_coredump(struct ivpu_device *vdev)
+{
+	struct drm_printer p = drm_info_printer(vdev->drm.dev);
+
+	ivpu_fw_log_print(vdev, false, &p);
+}
+#endif
+
+#endif /* __IVPU_COREDUMP_H__ */
diff --git a/drivers/accel/ivpu/ivpu_debugfs.c b/drivers/accel/ivpu/ivpu_debugfs.c
index 8d50981594d1..df89c1c0da6d 100644
--- a/drivers/accel/ivpu/ivpu_debugfs.c
+++ b/drivers/accel/ivpu/ivpu_debugfs.c
@@ -201,7 +201,7 @@ fw_log_fops_write(struct file *file, const char __user *user_buf, size_t size, l
 	if (!size)
 		return -EINVAL;
 
-	ivpu_fw_log_clear(vdev);
+	ivpu_fw_log_mark_read(vdev);
 	return size;
 }
 
@@ -331,7 +331,7 @@ ivpu_force_recovery_fn(struct file *file, const char __user *user_buf, size_t si
 		return -EINVAL;
 
 	ret = ivpu_rpm_get(vdev);
-	if (ret)
+	if (ret < 0)
 		return ret;
 
 	ivpu_pm_trigger_recovery(vdev, "debugfs");
@@ -346,49 +346,23 @@ static const struct file_operations ivpu_force_recovery_fops = {
 	.write = ivpu_force_recovery_fn,
 };
 
-static ssize_t
-ivpu_reset_engine_fn(struct file *file, const char __user *user_buf, size_t size, loff_t *pos)
+static int ivpu_reset_engine_fn(void *data, u64 val)
 {
-	struct ivpu_device *vdev = file->private_data;
-
-	if (!size)
-		return -EINVAL;
-
-	if (ivpu_jsm_reset_engine(vdev, DRM_IVPU_ENGINE_COMPUTE))
-		return -ENODEV;
-	if (ivpu_jsm_reset_engine(vdev, DRM_IVPU_ENGINE_COPY))
-		return -ENODEV;
+	struct ivpu_device *vdev = (struct ivpu_device *)data;
 
-	return size;
+	return ivpu_jsm_reset_engine(vdev, (u32)val);
 }
 
-static const struct file_operations ivpu_reset_engine_fops = {
-	.owner = THIS_MODULE,
-	.open = simple_open,
-	.write = ivpu_reset_engine_fn,
-};
+DEFINE_DEBUGFS_ATTRIBUTE(ivpu_reset_engine_fops, NULL, ivpu_reset_engine_fn, "0x%02llx\n");
 
-static ssize_t
-ivpu_resume_engine_fn(struct file *file, const char __user *user_buf, size_t size, loff_t *pos)
+static int ivpu_resume_engine_fn(void *data, u64 val)
 {
-	struct ivpu_device *vdev = file->private_data;
-
-	if (!size)
-		return -EINVAL;
+	struct ivpu_device *vdev = (struct ivpu_device *)data;
 
-	if (ivpu_jsm_hws_resume_engine(vdev, DRM_IVPU_ENGINE_COMPUTE))
-		return -ENODEV;
-	if (ivpu_jsm_hws_resume_engine(vdev, DRM_IVPU_ENGINE_COPY))
-		return -ENODEV;
-
-	return size;
+	return ivpu_jsm_hws_resume_engine(vdev, (u32)val);
 }
 
-static const struct file_operations ivpu_resume_engine_fops = {
-	.owner = THIS_MODULE,
-	.open = simple_open,
-	.write = ivpu_resume_engine_fn,
-};
+DEFINE_DEBUGFS_ATTRIBUTE(ivpu_resume_engine_fops, NULL, ivpu_resume_engine_fn, "0x%02llx\n");
 
 static int dct_active_get(void *data, u64 *active_percent)
 {
@@ -408,7 +382,7 @@ static int dct_active_set(void *data, u64 active_percent)
 		return -EINVAL;
 
 	ret = ivpu_rpm_get(vdev);
-	if (ret)
+	if (ret < 0)
 		return ret;
 
 	if (active_percent)
@@ -423,6 +397,88 @@ static int dct_active_set(void *data, u64 active_percent)
 
 DEFINE_DEBUGFS_ATTRIBUTE(ivpu_dct_fops, dct_active_get, dct_active_set, "%llu\n");
 
+static int priority_bands_show(struct seq_file *s, void *v)
+{
+	struct ivpu_device *vdev = s->private;
+	struct ivpu_hw_info *hw = vdev->hw;
+
+	for (int band = VPU_JOB_SCHEDULING_PRIORITY_BAND_IDLE;
+	     band < VPU_JOB_SCHEDULING_PRIORITY_BAND_COUNT; band++) {
+		switch (band) {
+		case VPU_JOB_SCHEDULING_PRIORITY_BAND_IDLE:
+			seq_puts(s, "Idle:     ");
+			break;
+
+		case VPU_JOB_SCHEDULING_PRIORITY_BAND_NORMAL:
+			seq_puts(s, "Normal:   ");
+			break;
+
+		case VPU_JOB_SCHEDULING_PRIORITY_BAND_FOCUS:
+			seq_puts(s, "Focus:    ");
+			break;
+
+		case VPU_JOB_SCHEDULING_PRIORITY_BAND_REALTIME:
+			seq_puts(s, "Realtime: ");
+			break;
+		}
+
+		seq_printf(s, "grace_period %9u process_grace_period %9u process_quantum %9u\n",
+			   hw->hws.grace_period[band], hw->hws.process_grace_period[band],
+			   hw->hws.process_quantum[band]);
+	}
+
+	return 0;
+}
+
+static int priority_bands_fops_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, priority_bands_show, inode->i_private);
+}
+
+static ssize_t
+priority_bands_fops_write(struct file *file, const char __user *user_buf, size_t size, loff_t *pos)
+{
+	struct seq_file *s = file->private_data;
+	struct ivpu_device *vdev = s->private;
+	char buf[64];
+	u32 grace_period;
+	u32 process_grace_period;
+	u32 process_quantum;
+	u32 band;
+	int ret;
+
+	if (size >= sizeof(buf))
+		return -EINVAL;
+
+	ret = simple_write_to_buffer(buf, sizeof(buf) - 1, pos, user_buf, size);
+	if (ret < 0)
+		return ret;
+
+	buf[size] = '\0';
+	ret = sscanf(buf, "%u %u %u %u", &band, &grace_period, &process_grace_period,
+		     &process_quantum);
+	if (ret != 4)
+		return -EINVAL;
+
+	if (band >= VPU_JOB_SCHEDULING_PRIORITY_BAND_COUNT)
+		return -EINVAL;
+
+	vdev->hw->hws.grace_period[band] = grace_period;
+	vdev->hw->hws.process_grace_period[band] = process_grace_period;
+	vdev->hw->hws.process_quantum[band] = process_quantum;
+
+	return size;
+}
+
+static const struct file_operations ivpu_hws_priority_bands_fops = {
+	.owner = THIS_MODULE,
+	.open = priority_bands_fops_open,
+	.write = priority_bands_fops_write,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
 void ivpu_debugfs_init(struct ivpu_device *vdev)
 {
 	struct dentry *debugfs_root = vdev->drm.debugfs_root;
@@ -445,6 +501,8 @@ void ivpu_debugfs_init(struct ivpu_device *vdev)
 			    &fw_trace_hw_comp_mask_fops);
 	debugfs_create_file("fw_trace_level", 0200, debugfs_root, vdev,
 			    &fw_trace_level_fops);
+	debugfs_create_file("hws_priority_bands", 0200, debugfs_root, vdev,
+			    &ivpu_hws_priority_bands_fops);
 
 	debugfs_create_file("reset_engine", 0200, debugfs_root, vdev,
 			    &ivpu_reset_engine_fops);
diff --git a/drivers/accel/ivpu/ivpu_drv.c b/drivers/accel/ivpu/ivpu_drv.c
index c91400ecf926..00208c4a6580 100644
--- a/drivers/accel/ivpu/ivpu_drv.c
+++ b/drivers/accel/ivpu/ivpu_drv.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Copyright (C) 2020-2024 Intel Corporation
+ * Copyright (C) 2020-2025 Intel Corporation
  */
 
 #include <linux/firmware.h>
@@ -14,7 +14,7 @@
 #include <drm/drm_ioctl.h>
 #include <drm/drm_prime.h>
 
-#include "vpu_boot_api.h"
+#include "ivpu_coredump.h"
 #include "ivpu_debugfs.h"
 #include "ivpu_drv.h"
 #include "ivpu_fw.h"
@@ -29,14 +29,13 @@
 #include "ivpu_ms.h"
 #include "ivpu_pm.h"
 #include "ivpu_sysfs.h"
+#include "vpu_boot_api.h"
 
 #ifndef DRIVER_VERSION_STR
 #define DRIVER_VERSION_STR __stringify(DRM_IVPU_DRIVER_MAJOR) "." \
 			   __stringify(DRM_IVPU_DRIVER_MINOR) "."
 #endif
 
-static struct lock_class_key submitted_jobs_xa_lock_class_key;
-
 int ivpu_dbg_mask;
 module_param_named(dbg_mask, ivpu_dbg_mask, int, 0644);
 MODULE_PARM_DESC(dbg_mask, "Driver debug mask. See IVPU_DBG_* macros.");
@@ -53,9 +52,9 @@ u8 ivpu_pll_max_ratio = U8_MAX;
 module_param_named(pll_max_ratio, ivpu_pll_max_ratio, byte, 0644);
 MODULE_PARM_DESC(pll_max_ratio, "Maximum PLL ratio used to set NPU frequency");
 
-int ivpu_sched_mode;
+int ivpu_sched_mode = IVPU_SCHED_MODE_AUTO;
 module_param_named(sched_mode, ivpu_sched_mode, int, 0444);
-MODULE_PARM_DESC(sched_mode, "Scheduler mode: 0 - Default scheduler, 1 - Force HW scheduler");
+MODULE_PARM_DESC(sched_mode, "Scheduler mode: -1 - Use default scheduler, 0 - Use OS scheduler, 1 - Use HW scheduler");
 
 bool ivpu_disable_mmu_cont_pages;
 module_param_named(disable_mmu_cont_pages, ivpu_disable_mmu_cont_pages, bool, 0444);
@@ -103,6 +102,8 @@ static void file_priv_release(struct kref *ref)
 	pm_runtime_get_sync(vdev->drm.dev);
 	mutex_lock(&vdev->context_list_lock);
 	file_priv_unbind(vdev, file_priv);
+	drm_WARN_ON(&vdev->drm, !xa_empty(&file_priv->cmdq_xa));
+	xa_destroy(&file_priv->cmdq_xa);
 	mutex_unlock(&vdev->context_list_lock);
 	pm_runtime_put_autosuspend(vdev->drm.dev);
 
@@ -164,7 +165,7 @@ static int ivpu_get_param_ioctl(struct drm_device *dev, void *data, struct drm_f
 		args->value = vdev->platform;
 		break;
 	case DRM_IVPU_PARAM_CORE_CLOCK_RATE:
-		args->value = ivpu_hw_ratio_to_freq(vdev, vdev->hw->pll.max_ratio);
+		args->value = ivpu_hw_dpu_max_freq_get(vdev);
 		break;
 	case DRM_IVPU_PARAM_NUM_CONTEXTS:
 		args->value = ivpu_get_context_count(vdev);
@@ -259,6 +260,13 @@ static int ivpu_open(struct drm_device *dev, struct drm_file *file)
 	if (ret)
 		goto err_xa_erase;
 
+	file_priv->job_limit.min = FIELD_PREP(IVPU_JOB_ID_CONTEXT_MASK, (file_priv->ctx.id - 1));
+	file_priv->job_limit.max = file_priv->job_limit.min | IVPU_JOB_ID_JOB_MASK;
+
+	xa_init_flags(&file_priv->cmdq_xa, XA_FLAGS_ALLOC1);
+	file_priv->cmdq_limit.min = IVPU_CMDQ_MIN_ID;
+	file_priv->cmdq_limit.max = IVPU_CMDQ_MAX_ID;
+
 	mutex_unlock(&vdev->context_list_lock);
 	drm_dev_exit(idx);
 
@@ -346,7 +354,7 @@ static int ivpu_hw_sched_init(struct ivpu_device *vdev)
 {
 	int ret = 0;
 
-	if (vdev->hw->sched_mode == VPU_SCHEDULING_MODE_HW) {
+	if (vdev->fw->sched_mode == VPU_SCHEDULING_MODE_HW) {
 		ret = ivpu_jsm_hws_setup_priority_bands(vdev);
 		if (ret) {
 			ivpu_err(vdev, "Failed to enable hw scheduler: %d", ret);
@@ -382,7 +390,7 @@ int ivpu_boot(struct ivpu_device *vdev)
 		ivpu_err(vdev, "Failed to boot the firmware: %d\n", ret);
 		ivpu_hw_diagnose_failure(vdev);
 		ivpu_mmu_evtq_dump(vdev);
-		ivpu_fw_log_dump(vdev);
+		ivpu_dev_coredump(vdev);
 		return ret;
 	}
 
@@ -451,26 +459,6 @@ static const struct drm_driver driver = {
 	.minor = DRM_IVPU_DRIVER_MINOR,
 };
 
-static void ivpu_context_abort_invalid(struct ivpu_device *vdev)
-{
-	struct ivpu_file_priv *file_priv;
-	unsigned long ctx_id;
-
-	mutex_lock(&vdev->context_list_lock);
-
-	xa_for_each(&vdev->context_xa, ctx_id, file_priv) {
-		if (!file_priv->has_mmu_faults || file_priv->aborted)
-			continue;
-
-		mutex_lock(&file_priv->lock);
-		ivpu_context_abort_locked(file_priv);
-		file_priv->aborted = true;
-		mutex_unlock(&file_priv->lock);
-	}
-
-	mutex_unlock(&vdev->context_list_lock);
-}
-
 static irqreturn_t ivpu_irq_thread_handler(int irq, void *arg)
 {
 	struct ivpu_device *vdev = arg;
@@ -484,9 +472,6 @@ static irqreturn_t ivpu_irq_thread_handler(int irq, void *arg)
 		case IVPU_HW_IRQ_SRC_IPC:
 			ivpu_ipc_irq_thread_handler(vdev);
 			break;
-		case IVPU_HW_IRQ_SRC_MMU_EVTQ:
-			ivpu_context_abort_invalid(vdev);
-			break;
 		case IVPU_HW_IRQ_SRC_DCT:
 			ivpu_pm_dct_irq_thread_handler(vdev);
 			break;
@@ -603,13 +588,21 @@ static int ivpu_dev_init(struct ivpu_device *vdev)
 	xa_init_flags(&vdev->context_xa, XA_FLAGS_ALLOC | XA_FLAGS_LOCK_IRQ);
 	xa_init_flags(&vdev->submitted_jobs_xa, XA_FLAGS_ALLOC1);
 	xa_init_flags(&vdev->db_xa, XA_FLAGS_ALLOC1);
-	lockdep_set_class(&vdev->submitted_jobs_xa.xa_lock, &submitted_jobs_xa_lock_class_key);
 	INIT_LIST_HEAD(&vdev->bo_list);
 
+	vdev->db_limit.min = IVPU_MIN_DB;
+	vdev->db_limit.max = IVPU_MAX_DB;
+
+	INIT_WORK(&vdev->context_abort_work, ivpu_context_abort_thread_handler);
+
 	ret = drmm_mutex_init(&vdev->drm, &vdev->context_list_lock);
 	if (ret)
 		goto err_xa_destroy;
 
+	ret = drmm_mutex_init(&vdev->drm, &vdev->submitted_jobs_lock);
+	if (ret)
+		goto err_xa_destroy;
+
 	ret = drmm_mutex_init(&vdev->drm, &vdev->bo_list_lock);
 	if (ret)
 		goto err_xa_destroy;
@@ -722,6 +715,7 @@ static struct pci_device_id ivpu_pci_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_MTL) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_ARL) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_LNL) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_PTL_P) },
 	{ }
 };
 MODULE_DEVICE_TABLE(pci, ivpu_pci_ids);
diff --git a/drivers/accel/ivpu/ivpu_drv.h b/drivers/accel/ivpu/ivpu_drv.h
index 63f13b697eed..f2ba3ed8b3fc 100644
--- a/drivers/accel/ivpu/ivpu_drv.h
+++ b/drivers/accel/ivpu/ivpu_drv.h
@@ -23,9 +23,10 @@
 #define DRIVER_DESC "Driver for Intel NPU (Neural Processing Unit)"
 #define DRIVER_DATE "20230117"
 
-#define PCI_DEVICE_ID_MTL   0x7d1d
-#define PCI_DEVICE_ID_ARL   0xad1d
-#define PCI_DEVICE_ID_LNL   0x643e
+#define PCI_DEVICE_ID_MTL	0x7d1d
+#define PCI_DEVICE_ID_ARL	0xad1d
+#define PCI_DEVICE_ID_LNL	0x643e
+#define PCI_DEVICE_ID_PTL_P	0xb03e
 
 #define IVPU_HW_IP_37XX 37
 #define IVPU_HW_IP_40XX 40
@@ -46,17 +47,22 @@
 #define IVPU_MIN_DB 1
 #define IVPU_MAX_DB 255
 
-#define IVPU_NUM_ENGINES       2
+#define IVPU_JOB_ID_JOB_MASK		GENMASK(7, 0)
+#define IVPU_JOB_ID_CONTEXT_MASK	GENMASK(31, 8)
+
 #define IVPU_NUM_PRIORITIES    4
-#define IVPU_NUM_CMDQS_PER_CTX (IVPU_NUM_ENGINES * IVPU_NUM_PRIORITIES)
+#define IVPU_NUM_CMDQS_PER_CTX (IVPU_NUM_PRIORITIES)
 
-#define IVPU_CMDQ_INDEX(engine, priority) ((engine) * IVPU_NUM_PRIORITIES + (priority))
+#define IVPU_CMDQ_MIN_ID 1
+#define IVPU_CMDQ_MAX_ID 255
 
 #define IVPU_PLATFORM_SILICON 0
 #define IVPU_PLATFORM_SIMICS  2
 #define IVPU_PLATFORM_FPGA    3
 #define IVPU_PLATFORM_INVALID 8
 
+#define IVPU_SCHED_MODE_AUTO -1
+
 #define IVPU_DBG_REG	 BIT(0)
 #define IVPU_DBG_IRQ	 BIT(1)
 #define IVPU_DBG_MMU	 BIT(2)
@@ -132,12 +138,16 @@ struct ivpu_device {
 	struct mutex context_list_lock; /* Protects user context addition/removal */
 	struct xarray context_xa;
 	struct xa_limit context_xa_limit;
+	struct work_struct context_abort_work;
 
 	struct xarray db_xa;
+	struct xa_limit db_limit;
+	u32 db_next;
 
 	struct mutex bo_list_lock; /* Protects bo_list */
 	struct list_head bo_list;
 
+	struct mutex submitted_jobs_lock; /* Protects submitted_jobs */
 	struct xarray submitted_jobs_xa;
 	struct ivpu_ipc_consumer job_done_consumer;
 
@@ -152,6 +162,7 @@ struct ivpu_device {
 		int tdr;
 		int autosuspend;
 		int d0i3_entry_msg;
+		int state_dump_msg;
 	} timeout;
 };
 
@@ -163,11 +174,15 @@ struct ivpu_file_priv {
 	struct kref ref;
 	struct ivpu_device *vdev;
 	struct mutex lock; /* Protects cmdq */
-	struct ivpu_cmdq *cmdq[IVPU_NUM_CMDQS_PER_CTX];
+	struct xarray cmdq_xa;
 	struct ivpu_mmu_context ctx;
 	struct mutex ms_lock; /* Protects ms_instance_list, ms_info_bo */
 	struct list_head ms_instance_list;
 	struct ivpu_bo *ms_info_bo;
+	struct xa_limit job_limit;
+	u32 job_id_next;
+	struct xa_limit cmdq_limit;
+	u32 cmdq_id_next;
 	bool has_mmu_faults;
 	bool bound;
 	bool aborted;
@@ -215,6 +230,8 @@ static inline int ivpu_hw_ip_gen(struct ivpu_device *vdev)
 		return IVPU_HW_IP_37XX;
 	case PCI_DEVICE_ID_LNL:
 		return IVPU_HW_IP_40XX;
+	case PCI_DEVICE_ID_PTL_P:
+		return IVPU_HW_IP_50XX;
 	default:
 		dump_stack();
 		ivpu_err(vdev, "Unknown NPU IP generation\n");
@@ -229,6 +246,7 @@ static inline int ivpu_hw_btrs_gen(struct ivpu_device *vdev)
 	case PCI_DEVICE_ID_ARL:
 		return IVPU_HW_BTRS_MTL;
 	case PCI_DEVICE_ID_LNL:
+	case PCI_DEVICE_ID_PTL_P:
 		return IVPU_HW_BTRS_LNL;
 	default:
 		dump_stack();
diff --git a/drivers/accel/ivpu/ivpu_fw.c b/drivers/accel/ivpu/ivpu_fw.c
index ede6165e09d9..cd40446a22a5 100644
--- a/drivers/accel/ivpu/ivpu_fw.c
+++ b/drivers/accel/ivpu/ivpu_fw.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Copyright (C) 2020-2024 Intel Corporation
+ * Copyright (C) 2020-2025 Intel Corporation
  */
 
 #include <linux/firmware.h>
@@ -25,7 +25,6 @@
 #define FW_SHAVE_NN_MAX_SIZE	SZ_2M
 #define FW_RUNTIME_MIN_ADDR	(FW_GLOBAL_MEM_START)
 #define FW_RUNTIME_MAX_ADDR	(FW_GLOBAL_MEM_END - FW_SHARED_MEM_SIZE)
-#define FW_VERSION_HEADER_SIZE	SZ_4K
 #define FW_FILE_IMAGE_OFFSET	(VPU_FW_HEADER_SIZE + FW_VERSION_HEADER_SIZE)
 
 #define WATCHDOG_MSS_REDIRECT	32
@@ -54,15 +53,18 @@ static struct {
 	int gen;
 	const char *name;
 } fw_names[] = {
-	{ IVPU_HW_IP_37XX, "vpu_37xx.bin" },
+	{ IVPU_HW_IP_37XX, "intel/vpu/vpu_37xx_v1.bin" },
 	{ IVPU_HW_IP_37XX, "intel/vpu/vpu_37xx_v0.0.bin" },
-	{ IVPU_HW_IP_40XX, "vpu_40xx.bin" },
+	{ IVPU_HW_IP_40XX, "intel/vpu/vpu_40xx_v1.bin" },
 	{ IVPU_HW_IP_40XX, "intel/vpu/vpu_40xx_v0.0.bin" },
+	{ IVPU_HW_IP_50XX, "intel/vpu/vpu_50xx_v1.bin" },
+	{ IVPU_HW_IP_50XX, "intel/vpu/vpu_50xx_v0.0.bin" },
 };
 
 /* Production fw_names from the table above */
-MODULE_FIRMWARE("intel/vpu/vpu_37xx_v0.0.bin");
-MODULE_FIRMWARE("intel/vpu/vpu_40xx_v0.0.bin");
+MODULE_FIRMWARE("intel/vpu/vpu_37xx_v1.bin");
+MODULE_FIRMWARE("intel/vpu/vpu_40xx_v1.bin");
+MODULE_FIRMWARE("intel/vpu/vpu_50xx_v1.bin");
 
 static int ivpu_fw_request(struct ivpu_device *vdev)
 {
@@ -135,6 +137,15 @@ static bool is_within_range(u64 addr, size_t size, u64 range_start, size_t range
 	return true;
 }
 
+static u32
+ivpu_fw_sched_mode_select(struct ivpu_device *vdev, const struct vpu_firmware_header *fw_hdr)
+{
+	if (ivpu_sched_mode != IVPU_SCHED_MODE_AUTO)
+		return ivpu_sched_mode;
+
+	return VPU_SCHEDULING_MODE_OS;
+}
+
 static int ivpu_fw_parse(struct ivpu_device *vdev)
 {
 	struct ivpu_fw_info *fw = vdev->fw;
@@ -191,8 +202,10 @@ static int ivpu_fw_parse(struct ivpu_device *vdev)
 	ivpu_dbg(vdev, FW_BOOT, "Header version: 0x%x, format 0x%x\n",
 		 fw_hdr->header_version, fw_hdr->image_format);
 
-	ivpu_info(vdev, "Firmware: %s, version: %s", fw->name,
-		  (const char *)fw_hdr + VPU_FW_HEADER_SIZE);
+	if (!scnprintf(fw->version, sizeof(fw->version), "%s", fw->file->data + VPU_FW_HEADER_SIZE))
+		ivpu_warn(vdev, "Missing firmware version\n");
+
+	ivpu_info(vdev, "Firmware: %s, version: %s\n", fw->name, fw->version);
 
 	if (IVPU_FW_CHECK_API_COMPAT(vdev, fw_hdr, BOOT, 3))
 		return -EINVAL;
@@ -208,14 +221,16 @@ static int ivpu_fw_parse(struct ivpu_device *vdev)
 	fw->cold_boot_entry_point = fw_hdr->entry_point;
 	fw->entry_point = fw->cold_boot_entry_point;
 
-	fw->trace_level = min_t(u32, ivpu_log_level, IVPU_FW_LOG_FATAL);
+	fw->trace_level = min_t(u32, ivpu_fw_log_level, IVPU_FW_LOG_FATAL);
 	fw->trace_destination_mask = VPU_TRACE_DESTINATION_VERBOSE_TRACING;
 	fw->trace_hw_component_mask = -1;
 
 	fw->dvfs_mode = 0;
 
+	fw->sched_mode = ivpu_fw_sched_mode_select(vdev, fw_hdr);
 	fw->primary_preempt_buf_size = fw_hdr->preemption_buffer_1_size;
 	fw->secondary_preempt_buf_size = fw_hdr->preemption_buffer_2_size;
+	ivpu_info(vdev, "Scheduler mode: %s\n", fw->sched_mode ? "HW" : "OS");
 
 	if (fw_hdr->ro_section_start_address && !is_within_range(fw_hdr->ro_section_start_address,
 								 fw_hdr->ro_section_size,
@@ -311,7 +326,7 @@ static int ivpu_fw_mem_init(struct ivpu_device *vdev)
 		goto err_free_fw_mem;
 	}
 
-	if (ivpu_log_level <= IVPU_FW_LOG_INFO)
+	if (ivpu_fw_log_level <= IVPU_FW_LOG_INFO)
 		log_verb_size = IVPU_FW_VERBOSE_BUFFER_LARGE_SIZE;
 	else
 		log_verb_size = IVPU_FW_VERBOSE_BUFFER_SMALL_SIZE;
@@ -544,7 +559,6 @@ void ivpu_fw_boot_params_setup(struct ivpu_device *vdev, struct vpu_boot_params
 
 	boot_params->magic = VPU_BOOT_PARAMS_MAGIC;
 	boot_params->vpu_id = to_pci_dev(vdev->drm.dev)->bus->number;
-	boot_params->frequency = ivpu_hw_pll_freq_get(vdev);
 
 	/*
 	 * This param is a debug firmware feature.  It switches default clock
@@ -604,8 +618,8 @@ void ivpu_fw_boot_params_setup(struct ivpu_device *vdev, struct vpu_boot_params
 	boot_params->punit_telemetry_sram_base = ivpu_hw_telemetry_offset_get(vdev);
 	boot_params->punit_telemetry_sram_size = ivpu_hw_telemetry_size_get(vdev);
 	boot_params->vpu_telemetry_enable = ivpu_hw_telemetry_enable_get(vdev);
-	boot_params->vpu_scheduling_mode = vdev->hw->sched_mode;
-	if (vdev->hw->sched_mode == VPU_SCHEDULING_MODE_HW)
+	boot_params->vpu_scheduling_mode = vdev->fw->sched_mode;
+	if (vdev->fw->sched_mode == VPU_SCHEDULING_MODE_HW)
 		boot_params->vpu_focus_present_timer_ms = IVPU_FOCUS_PRESENT_TIMER_MS;
 	boot_params->dvfs_mode = vdev->fw->dvfs_mode;
 	if (!IVPU_WA(disable_d0i3_msg))
diff --git a/drivers/accel/ivpu/ivpu_fw.h b/drivers/accel/ivpu/ivpu_fw.h
index 40d9d17be3f5..1d0b2bd9d65c 100644
--- a/drivers/accel/ivpu/ivpu_fw.h
+++ b/drivers/accel/ivpu/ivpu_fw.h
@@ -1,11 +1,16 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * Copyright (C) 2020-2023 Intel Corporation
+ * Copyright (C) 2020-2024 Intel Corporation
  */
 
 #ifndef __IVPU_FW_H__
 #define __IVPU_FW_H__
 
+#include "vpu_jsm_api.h"
+
+#define FW_VERSION_HEADER_SIZE	SZ_4K
+#define FW_VERSION_STR_SIZE	SZ_256
+
 struct ivpu_device;
 struct ivpu_bo;
 struct vpu_boot_params;
@@ -13,6 +18,7 @@ struct vpu_boot_params;
 struct ivpu_fw_info {
 	const struct firmware *file;
 	const char *name;
+	char version[FW_VERSION_STR_SIZE];
 	struct ivpu_bo *mem;
 	struct ivpu_bo *mem_shave_nn;
 	struct ivpu_bo *mem_log_crit;
@@ -32,6 +38,7 @@ struct ivpu_fw_info {
 	u32 secondary_preempt_buf_size;
 	u64 read_only_addr;
 	u32 read_only_size;
+	u32 sched_mode;
 };
 
 int ivpu_fw_init(struct ivpu_device *vdev);
diff --git a/drivers/accel/ivpu/ivpu_fw_log.c b/drivers/accel/ivpu/ivpu_fw_log.c
index ef0adb5e0fbe..337c906b0210 100644
--- a/drivers/accel/ivpu/ivpu_fw_log.c
+++ b/drivers/accel/ivpu/ivpu_fw_log.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Copyright (C) 2020-2023 Intel Corporation
+ * Copyright (C) 2020-2024 Intel Corporation
  */
 
 #include <linux/ctype.h>
@@ -15,19 +15,19 @@
 #include "ivpu_fw_log.h"
 #include "ivpu_gem.h"
 
-#define IVPU_FW_LOG_LINE_LENGTH	  256
+#define IVPU_FW_LOG_LINE_LENGTH	256
 
-unsigned int ivpu_log_level = IVPU_FW_LOG_ERROR;
-module_param(ivpu_log_level, uint, 0444);
-MODULE_PARM_DESC(ivpu_log_level,
-		 "NPU firmware default trace level: debug=" __stringify(IVPU_FW_LOG_DEBUG)
+unsigned int ivpu_fw_log_level = IVPU_FW_LOG_ERROR;
+module_param_named(fw_log_level, ivpu_fw_log_level, uint, 0444);
+MODULE_PARM_DESC(fw_log_level,
+		 "NPU firmware default log level: debug=" __stringify(IVPU_FW_LOG_DEBUG)
 		 " info=" __stringify(IVPU_FW_LOG_INFO)
 		 " warn=" __stringify(IVPU_FW_LOG_WARN)
 		 " error=" __stringify(IVPU_FW_LOG_ERROR)
 		 " fatal=" __stringify(IVPU_FW_LOG_FATAL));
 
-static int fw_log_ptr(struct ivpu_device *vdev, struct ivpu_bo *bo, u32 *offset,
-		      struct vpu_tracing_buffer_header **log_header)
+static int fw_log_from_bo(struct ivpu_device *vdev, struct ivpu_bo *bo, u32 *offset,
+			  struct vpu_tracing_buffer_header **out_log)
 {
 	struct vpu_tracing_buffer_header *log;
 
@@ -48,7 +48,7 @@ static int fw_log_ptr(struct ivpu_device *vdev, struct ivpu_bo *bo, u32 *offset,
 		return -EINVAL;
 	}
 
-	*log_header = log;
+	*out_log = log;
 	*offset += log->size;
 
 	ivpu_dbg(vdev, FW_BOOT,
@@ -59,7 +59,7 @@ static int fw_log_ptr(struct ivpu_device *vdev, struct ivpu_bo *bo, u32 *offset,
 	return 0;
 }
 
-static void buffer_print(char *buffer, u32 size, struct drm_printer *p)
+static void fw_log_print_lines(char *buffer, u32 size, struct drm_printer *p)
 {
 	char line[IVPU_FW_LOG_LINE_LENGTH];
 	u32 index = 0;
@@ -87,56 +87,89 @@ static void buffer_print(char *buffer, u32 size, struct drm_printer *p)
 	}
 	line[index] = 0;
 	if (index != 0)
-		drm_printf(p, "%s\n", line);
+		drm_printf(p, "%s", line);
 }
 
-static void fw_log_print_buffer(struct ivpu_device *vdev, struct vpu_tracing_buffer_header *log,
-				const char *prefix, bool only_new_msgs, struct drm_printer *p)
+static void fw_log_print_buffer(struct vpu_tracing_buffer_header *log, const char *prefix,
+				bool only_new_msgs, struct drm_printer *p)
 {
-	char *log_buffer = (void *)log + log->header_size;
-	u32 log_size = log->size - log->header_size;
-	u32 log_start = log->read_index;
-	u32 log_end = log->write_index;
-
-	if (!(log->write_index || log->wrap_count) ||
-	    (log->write_index == log->read_index && only_new_msgs)) {
-		drm_printf(p, "==== %s \"%s\" log empty ====\n", prefix, log->name);
-		return;
+	char *log_data = (void *)log + log->header_size;
+	u32 data_size = log->size - log->header_size;
+	u32 log_start = only_new_msgs ? READ_ONCE(log->read_index) : 0;
+	u32 log_end = READ_ONCE(log->write_index);
+
+	if (log->wrap_count == log->read_wrap_count) {
+		if (log_end <= log_start) {
+			drm_printf(p, "==== %s \"%s\" log empty ====\n", prefix, log->name);
+			return;
+		}
+	} else if (log->wrap_count == log->read_wrap_count + 1) {
+		if (log_end > log_start)
+			log_start = log_end;
+	} else {
+		log_start = log_end;
 	}
 
 	drm_printf(p, "==== %s \"%s\" log start ====\n", prefix, log->name);
-	if (log->write_index > log->read_index) {
-		buffer_print(log_buffer + log_start, log_end - log_start, p);
+	if (log_end > log_start) {
+		fw_log_print_lines(log_data + log_start, log_end - log_start, p);
 	} else {
-		buffer_print(log_buffer + log_end, log_size - log_end, p);
-		buffer_print(log_buffer, log_end, p);
+		fw_log_print_lines(log_data + log_start, data_size - log_start, p);
+		fw_log_print_lines(log_data, log_end, p);
 	}
-	drm_printf(p, "\x1b[0m");
+	drm_printf(p, "\n\x1b[0m"); /* add new line and clear formatting */
 	drm_printf(p, "==== %s \"%s\" log end   ====\n", prefix, log->name);
 }
 
-void ivpu_fw_log_print(struct ivpu_device *vdev, bool only_new_msgs, struct drm_printer *p)
+static void
+fw_log_print_all_in_bo(struct ivpu_device *vdev, const char *name,
+		       struct ivpu_bo *bo, bool only_new_msgs, struct drm_printer *p)
 {
-	struct vpu_tracing_buffer_header *log_header;
+	struct vpu_tracing_buffer_header *log;
 	u32 next = 0;
 
-	while (fw_log_ptr(vdev, vdev->fw->mem_log_crit, &next, &log_header) == 0)
-		fw_log_print_buffer(vdev, log_header, "NPU critical", only_new_msgs, p);
+	while (fw_log_from_bo(vdev, bo, &next, &log) == 0)
+		fw_log_print_buffer(log, name, only_new_msgs, p);
+}
+
+void ivpu_fw_log_print(struct ivpu_device *vdev, bool only_new_msgs, struct drm_printer *p)
+{
+	fw_log_print_all_in_bo(vdev, "NPU critical", vdev->fw->mem_log_crit, only_new_msgs, p);
+	fw_log_print_all_in_bo(vdev, "NPU verbose", vdev->fw->mem_log_verb, only_new_msgs, p);
+}
+
+void ivpu_fw_log_mark_read(struct ivpu_device *vdev)
+{
+	struct vpu_tracing_buffer_header *log;
+	u32 next;
+
+	next = 0;
+	while (fw_log_from_bo(vdev, vdev->fw->mem_log_crit, &next, &log) == 0) {
+		log->read_index = READ_ONCE(log->write_index);
+		log->read_wrap_count = READ_ONCE(log->wrap_count);
+	}
 
 	next = 0;
-	while (fw_log_ptr(vdev, vdev->fw->mem_log_verb, &next, &log_header) == 0)
-		fw_log_print_buffer(vdev, log_header, "NPU verbose", only_new_msgs, p);
+	while (fw_log_from_bo(vdev, vdev->fw->mem_log_verb, &next, &log) == 0) {
+		log->read_index = READ_ONCE(log->write_index);
+		log->read_wrap_count = READ_ONCE(log->wrap_count);
+	}
 }
 
-void ivpu_fw_log_clear(struct ivpu_device *vdev)
+void ivpu_fw_log_reset(struct ivpu_device *vdev)
 {
-	struct vpu_tracing_buffer_header *log_header;
-	u32 next = 0;
+	struct vpu_tracing_buffer_header *log;
+	u32 next;
 
-	while (fw_log_ptr(vdev, vdev->fw->mem_log_crit, &next, &log_header) == 0)
-		log_header->read_index = log_header->write_index;
+	next = 0;
+	while (fw_log_from_bo(vdev, vdev->fw->mem_log_crit, &next, &log) == 0) {
+		log->read_index = 0;
+		log->read_wrap_count = 0;
+	}
 
 	next = 0;
-	while (fw_log_ptr(vdev, vdev->fw->mem_log_verb, &next, &log_header) == 0)
-		log_header->read_index = log_header->write_index;
+	while (fw_log_from_bo(vdev, vdev->fw->mem_log_verb, &next, &log) == 0) {
+		log->read_index = 0;
+		log->read_wrap_count = 0;
+	}
 }
diff --git a/drivers/accel/ivpu/ivpu_fw_log.h b/drivers/accel/ivpu/ivpu_fw_log.h
index 0b2573f6f315..8bb528a73cb7 100644
--- a/drivers/accel/ivpu/ivpu_fw_log.h
+++ b/drivers/accel/ivpu/ivpu_fw_log.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * Copyright (C) 2020-2023 Intel Corporation
+ * Copyright (C) 2020-2024 Intel Corporation
  */
 
 #ifndef __IVPU_FW_LOG_H__
@@ -8,8 +8,6 @@
 
 #include <linux/types.h>
 
-#include <drm/drm_print.h>
-
 #include "ivpu_drv.h"
 
 #define IVPU_FW_LOG_DEFAULT 0
@@ -19,20 +17,15 @@
 #define IVPU_FW_LOG_ERROR   4
 #define IVPU_FW_LOG_FATAL   5
 
-extern unsigned int ivpu_log_level;
-
 #define IVPU_FW_VERBOSE_BUFFER_SMALL_SIZE	SZ_1M
 #define IVPU_FW_VERBOSE_BUFFER_LARGE_SIZE	SZ_8M
 #define IVPU_FW_CRITICAL_BUFFER_SIZE		SZ_512K
 
-void ivpu_fw_log_print(struct ivpu_device *vdev, bool only_new_msgs, struct drm_printer *p);
-void ivpu_fw_log_clear(struct ivpu_device *vdev);
+extern unsigned int ivpu_fw_log_level;
 
-static inline void ivpu_fw_log_dump(struct ivpu_device *vdev)
-{
-	struct drm_printer p = drm_info_printer(vdev->drm.dev);
+void ivpu_fw_log_print(struct ivpu_device *vdev, bool only_new_msgs, struct drm_printer *p);
+void ivpu_fw_log_mark_read(struct ivpu_device *vdev);
+void ivpu_fw_log_reset(struct ivpu_device *vdev);
 
-	ivpu_fw_log_print(vdev, false, &p);
-}
 
 #endif /* __IVPU_FW_LOG_H__ */
diff --git a/drivers/accel/ivpu/ivpu_gem.c b/drivers/accel/ivpu/ivpu_gem.c
index c8daffd90f30..6b1bda7e130d 100644
--- a/drivers/accel/ivpu/ivpu_gem.c
+++ b/drivers/accel/ivpu/ivpu_gem.c
@@ -26,11 +26,21 @@ static inline void ivpu_dbg_bo(struct ivpu_device *vdev, struct ivpu_bo *bo, con
 {
 	ivpu_dbg(vdev, BO,
 		 "%6s: bo %8p vpu_addr %9llx size %8zu ctx %d has_pages %d dma_mapped %d mmu_mapped %d wc %d imported %d\n",
-		 action, bo, bo->vpu_addr, ivpu_bo_size(bo), bo->ctx ? bo->ctx->id : 0,
+		 action, bo, bo->vpu_addr, ivpu_bo_size(bo), bo->ctx_id,
 		 (bool)bo->base.pages, (bool)bo->base.sgt, bo->mmu_mapped, bo->base.map_wc,
 		 (bool)bo->base.base.import_attach);
 }
 
+static inline int ivpu_bo_lock(struct ivpu_bo *bo)
+{
+	return dma_resv_lock(bo->base.base.resv, NULL);
+}
+
+static inline void ivpu_bo_unlock(struct ivpu_bo *bo)
+{
+	dma_resv_unlock(bo->base.base.resv);
+}
+
 /*
  * ivpu_bo_pin() - pin the backing physical pages and map them to VPU.
  *
@@ -41,22 +51,22 @@ static inline void ivpu_dbg_bo(struct ivpu_device *vdev, struct ivpu_bo *bo, con
 int __must_check ivpu_bo_pin(struct ivpu_bo *bo)
 {
 	struct ivpu_device *vdev = ivpu_bo_to_vdev(bo);
+	struct sg_table *sgt;
 	int ret = 0;
 
-	mutex_lock(&bo->lock);
-
 	ivpu_dbg_bo(vdev, bo, "pin");
-	drm_WARN_ON(&vdev->drm, !bo->ctx);
 
-	if (!bo->mmu_mapped) {
-		struct sg_table *sgt = drm_gem_shmem_get_pages_sgt(&bo->base);
+	sgt = drm_gem_shmem_get_pages_sgt(&bo->base);
+	if (IS_ERR(sgt)) {
+		ret = PTR_ERR(sgt);
+		ivpu_err(vdev, "Failed to map BO in IOMMU: %d\n", ret);
+		return ret;
+	}
 
-		if (IS_ERR(sgt)) {
-			ret = PTR_ERR(sgt);
-			ivpu_err(vdev, "Failed to map BO in IOMMU: %d\n", ret);
-			goto unlock;
-		}
+	ivpu_bo_lock(bo);
 
+	if (!bo->mmu_mapped) {
+		drm_WARN_ON(&vdev->drm, !bo->ctx);
 		ret = ivpu_mmu_context_map_sgt(vdev, bo->ctx, bo->vpu_addr, sgt,
 					       ivpu_bo_is_snooped(bo));
 		if (ret) {
@@ -67,7 +77,7 @@ int __must_check ivpu_bo_pin(struct ivpu_bo *bo)
 	}
 
 unlock:
-	mutex_unlock(&bo->lock);
+	ivpu_bo_unlock(bo);
 
 	return ret;
 }
@@ -82,7 +92,7 @@ ivpu_bo_alloc_vpu_addr(struct ivpu_bo *bo, struct ivpu_mmu_context *ctx,
 	if (!drm_dev_enter(&vdev->drm, &idx))
 		return -ENODEV;
 
-	mutex_lock(&bo->lock);
+	ivpu_bo_lock(bo);
 
 	ret = ivpu_mmu_context_insert_node(ctx, range, ivpu_bo_size(bo), &bo->mm_node);
 	if (!ret) {
@@ -92,9 +102,7 @@ ivpu_bo_alloc_vpu_addr(struct ivpu_bo *bo, struct ivpu_mmu_context *ctx,
 		ivpu_err(vdev, "Failed to add BO to context %u: %d\n", ctx->id, ret);
 	}
 
-	ivpu_dbg_bo(vdev, bo, "alloc");
-
-	mutex_unlock(&bo->lock);
+	ivpu_bo_unlock(bo);
 
 	drm_dev_exit(idx);
 
@@ -105,7 +113,7 @@ static void ivpu_bo_unbind_locked(struct ivpu_bo *bo)
 {
 	struct ivpu_device *vdev = ivpu_bo_to_vdev(bo);
 
-	lockdep_assert(lockdep_is_held(&bo->lock) || !kref_read(&bo->base.base.refcount));
+	lockdep_assert(dma_resv_held(bo->base.base.resv) || !kref_read(&bo->base.base.refcount));
 
 	if (bo->mmu_mapped) {
 		drm_WARN_ON(&vdev->drm, !bo->ctx);
@@ -123,14 +131,12 @@ static void ivpu_bo_unbind_locked(struct ivpu_bo *bo)
 	if (bo->base.base.import_attach)
 		return;
 
-	dma_resv_lock(bo->base.base.resv, NULL);
 	if (bo->base.sgt) {
 		dma_unmap_sgtable(vdev->drm.dev, bo->base.sgt, DMA_BIDIRECTIONAL, 0);
 		sg_free_table(bo->base.sgt);
 		kfree(bo->base.sgt);
 		bo->base.sgt = NULL;
 	}
-	dma_resv_unlock(bo->base.base.resv);
 }
 
 void ivpu_bo_unbind_all_bos_from_context(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx)
@@ -142,12 +148,12 @@ void ivpu_bo_unbind_all_bos_from_context(struct ivpu_device *vdev, struct ivpu_m
 
 	mutex_lock(&vdev->bo_list_lock);
 	list_for_each_entry(bo, &vdev->bo_list, bo_list_node) {
-		mutex_lock(&bo->lock);
+		ivpu_bo_lock(bo);
 		if (bo->ctx == ctx) {
 			ivpu_dbg_bo(vdev, bo, "unbind");
 			ivpu_bo_unbind_locked(bo);
 		}
-		mutex_unlock(&bo->lock);
+		ivpu_bo_unlock(bo);
 	}
 	mutex_unlock(&vdev->bo_list_lock);
 }
@@ -167,12 +173,11 @@ struct drm_gem_object *ivpu_gem_create_object(struct drm_device *dev, size_t siz
 	bo->base.pages_mark_dirty_on_put = true; /* VPU can dirty a BO anytime */
 
 	INIT_LIST_HEAD(&bo->bo_list_node);
-	mutex_init(&bo->lock);
 
 	return &bo->base.base;
 }
 
-static struct ivpu_bo *ivpu_bo_alloc(struct ivpu_device *vdev, u64 size, u32 flags)
+static struct ivpu_bo *ivpu_bo_alloc(struct ivpu_device *vdev, u64 size, u32 flags, u32 ctx_id)
 {
 	struct drm_gem_shmem_object *shmem;
 	struct ivpu_bo *bo;
@@ -190,6 +195,7 @@ static struct ivpu_bo *ivpu_bo_alloc(struct ivpu_device *vdev, u64 size, u32 fla
 		return ERR_CAST(shmem);
 
 	bo = to_ivpu_bo(&shmem->base);
+	bo->ctx_id = ctx_id;
 	bo->base.map_wc = flags & DRM_IVPU_BO_WC;
 	bo->flags = flags;
 
@@ -197,6 +203,8 @@ static struct ivpu_bo *ivpu_bo_alloc(struct ivpu_device *vdev, u64 size, u32 fla
 	list_add_tail(&bo->bo_list_node, &vdev->bo_list);
 	mutex_unlock(&vdev->bo_list_lock);
 
+	ivpu_dbg_bo(vdev, bo, "alloc");
+
 	return bo;
 }
 
@@ -234,10 +242,14 @@ static void ivpu_gem_bo_free(struct drm_gem_object *obj)
 	list_del(&bo->bo_list_node);
 	mutex_unlock(&vdev->bo_list_lock);
 
-	drm_WARN_ON(&vdev->drm, !dma_resv_test_signaled(obj->resv, DMA_RESV_USAGE_READ));
+	drm_WARN_ON(&vdev->drm, !drm_gem_is_imported(&bo->base.base) &&
+		    !dma_resv_test_signaled(obj->resv, DMA_RESV_USAGE_READ));
+	drm_WARN_ON(&vdev->drm, ivpu_bo_size(bo) == 0);
+	drm_WARN_ON(&vdev->drm, bo->base.vaddr);
 
 	ivpu_bo_unbind_locked(bo);
-	mutex_destroy(&bo->lock);
+	drm_WARN_ON(&vdev->drm, bo->mmu_mapped);
+	drm_WARN_ON(&vdev->drm, bo->ctx);
 
 	drm_WARN_ON(obj->dev, bo->base.pages_use_count > 1);
 	drm_gem_shmem_free(&bo->base);
@@ -271,7 +283,7 @@ int ivpu_bo_create_ioctl(struct drm_device *dev, void *data, struct drm_file *fi
 	if (size == 0)
 		return -EINVAL;
 
-	bo = ivpu_bo_alloc(vdev, size, args->flags);
+	bo = ivpu_bo_alloc(vdev, size, args->flags, file_priv->ctx.id);
 	if (IS_ERR(bo)) {
 		ivpu_err(vdev, "Failed to allocate BO: %pe (ctx %u size %llu flags 0x%x)",
 			 bo, file_priv->ctx.id, args->size, args->flags);
@@ -279,7 +291,10 @@ int ivpu_bo_create_ioctl(struct drm_device *dev, void *data, struct drm_file *fi
 	}
 
 	ret = drm_gem_handle_create(file, &bo->base.base, &args->handle);
-	if (!ret)
+	if (ret)
+		ivpu_err(vdev, "Failed to create handle for BO: %pe (ctx %u size %llu flags 0x%x)",
+			 bo, file_priv->ctx.id, args->size, args->flags);
+	else
 		args->vpu_addr = bo->vpu_addr;
 
 	drm_gem_object_put(&bo->base.base);
@@ -302,7 +317,7 @@ ivpu_bo_create(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx,
 	drm_WARN_ON(&vdev->drm, !PAGE_ALIGNED(range->end));
 	drm_WARN_ON(&vdev->drm, !PAGE_ALIGNED(size));
 
-	bo = ivpu_bo_alloc(vdev, size, flags);
+	bo = ivpu_bo_alloc(vdev, size, flags, IVPU_GLOBAL_CONTEXT_MMU_SSID);
 	if (IS_ERR(bo)) {
 		ivpu_err(vdev, "Failed to allocate BO: %pe (vpu_addr 0x%llx size %llu flags 0x%x)",
 			 bo, range->start, size, flags);
@@ -318,9 +333,9 @@ ivpu_bo_create(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx,
 		goto err_put;
 
 	if (flags & DRM_IVPU_BO_MAPPABLE) {
-		dma_resv_lock(bo->base.base.resv, NULL);
+		ivpu_bo_lock(bo);
 		ret = drm_gem_shmem_vmap(&bo->base, &map);
-		dma_resv_unlock(bo->base.base.resv);
+		ivpu_bo_unlock(bo);
 
 		if (ret)
 			goto err_put;
@@ -343,9 +358,9 @@ void ivpu_bo_free(struct ivpu_bo *bo)
 	struct iosys_map map = IOSYS_MAP_INIT_VADDR(bo->base.vaddr);
 
 	if (bo->flags & DRM_IVPU_BO_MAPPABLE) {
-		dma_resv_lock(bo->base.base.resv, NULL);
+		ivpu_bo_lock(bo);
 		drm_gem_shmem_vunmap(&bo->base, &map);
-		dma_resv_unlock(bo->base.base.resv);
+		ivpu_bo_unlock(bo);
 	}
 
 	drm_gem_object_put(&bo->base.base);
@@ -364,12 +379,12 @@ int ivpu_bo_info_ioctl(struct drm_device *dev, void *data, struct drm_file *file
 
 	bo = to_ivpu_bo(obj);
 
-	mutex_lock(&bo->lock);
+	ivpu_bo_lock(bo);
 	args->flags = bo->flags;
 	args->mmap_offset = drm_vma_node_offset_addr(&obj->vma_node);
 	args->vpu_addr = bo->vpu_addr;
 	args->size = obj->size;
-	mutex_unlock(&bo->lock);
+	ivpu_bo_unlock(bo);
 
 	drm_gem_object_put(obj);
 	return ret;
@@ -403,10 +418,10 @@ int ivpu_bo_wait_ioctl(struct drm_device *dev, void *data, struct drm_file *file
 
 static void ivpu_bo_print_info(struct ivpu_bo *bo, struct drm_printer *p)
 {
-	mutex_lock(&bo->lock);
+	ivpu_bo_lock(bo);
 
 	drm_printf(p, "%-9p %-3u 0x%-12llx %-10lu 0x%-8x %-4u",
-		   bo, bo->ctx ? bo->ctx->id : 0, bo->vpu_addr, bo->base.base.size,
+		   bo, bo->ctx_id, bo->vpu_addr, bo->base.base.size,
 		   bo->flags, kref_read(&bo->base.base.refcount));
 
 	if (bo->base.pages)
@@ -420,7 +435,7 @@ static void ivpu_bo_print_info(struct ivpu_bo *bo, struct drm_printer *p)
 
 	drm_printf(p, "\n");
 
-	mutex_unlock(&bo->lock);
+	ivpu_bo_unlock(bo);
 }
 
 void ivpu_bo_list(struct drm_device *dev, struct drm_printer *p)
diff --git a/drivers/accel/ivpu/ivpu_gem.h b/drivers/accel/ivpu/ivpu_gem.h
index d975000abd78..07bffe98c963 100644
--- a/drivers/accel/ivpu/ivpu_gem.h
+++ b/drivers/accel/ivpu/ivpu_gem.h
@@ -17,10 +17,10 @@ struct ivpu_bo {
 	struct list_head bo_list_node;
 	struct drm_mm_node mm_node;
 
-	struct mutex lock; /* Protects: ctx, mmu_mapped, vpu_addr */
 	u64 vpu_addr;
 	u32 flags;
 	u32 job_status; /* Valid only for command buffer */
+	u32 ctx_id;
 	bool mmu_mapped;
 };
 
diff --git a/drivers/accel/ivpu/ivpu_hw.c b/drivers/accel/ivpu/ivpu_hw.c
index e69c0613513f..37ef8ce64210 100644
--- a/drivers/accel/ivpu/ivpu_hw.c
+++ b/drivers/accel/ivpu/ivpu_hw.c
@@ -89,12 +89,14 @@ static void timeouts_init(struct ivpu_device *vdev)
 		vdev->timeout.tdr = 2000000;
 		vdev->timeout.autosuspend = -1;
 		vdev->timeout.d0i3_entry_msg = 500;
+		vdev->timeout.state_dump_msg = 10;
 	} else if (ivpu_is_simics(vdev)) {
 		vdev->timeout.boot = 50;
 		vdev->timeout.jsm = 500;
 		vdev->timeout.tdr = 10000;
 		vdev->timeout.autosuspend = -1;
 		vdev->timeout.d0i3_entry_msg = 100;
+		vdev->timeout.state_dump_msg = 10;
 	} else {
 		vdev->timeout.boot = 1000;
 		vdev->timeout.jsm = 500;
@@ -104,9 +106,30 @@ static void timeouts_init(struct ivpu_device *vdev)
 		else
 			vdev->timeout.autosuspend = 100;
 		vdev->timeout.d0i3_entry_msg = 5;
+		vdev->timeout.state_dump_msg = 100;
 	}
 }
 
+static void priority_bands_init(struct ivpu_device *vdev)
+{
+	/* Idle */
+	vdev->hw->hws.grace_period[VPU_JOB_SCHEDULING_PRIORITY_BAND_IDLE] = 0;
+	vdev->hw->hws.process_grace_period[VPU_JOB_SCHEDULING_PRIORITY_BAND_IDLE] = 50000;
+	vdev->hw->hws.process_quantum[VPU_JOB_SCHEDULING_PRIORITY_BAND_IDLE] = 160000;
+	/* Normal */
+	vdev->hw->hws.grace_period[VPU_JOB_SCHEDULING_PRIORITY_BAND_NORMAL] = 50000;
+	vdev->hw->hws.process_grace_period[VPU_JOB_SCHEDULING_PRIORITY_BAND_NORMAL] = 50000;
+	vdev->hw->hws.process_quantum[VPU_JOB_SCHEDULING_PRIORITY_BAND_NORMAL] = 300000;
+	/* Focus */
+	vdev->hw->hws.grace_period[VPU_JOB_SCHEDULING_PRIORITY_BAND_FOCUS] = 50000;
+	vdev->hw->hws.process_grace_period[VPU_JOB_SCHEDULING_PRIORITY_BAND_FOCUS] = 50000;
+	vdev->hw->hws.process_quantum[VPU_JOB_SCHEDULING_PRIORITY_BAND_FOCUS] = 200000;
+	/* Realtime */
+	vdev->hw->hws.grace_period[VPU_JOB_SCHEDULING_PRIORITY_BAND_REALTIME] = 0;
+	vdev->hw->hws.process_grace_period[VPU_JOB_SCHEDULING_PRIORITY_BAND_REALTIME] = 50000;
+	vdev->hw->hws.process_quantum[VPU_JOB_SCHEDULING_PRIORITY_BAND_REALTIME] = 200000;
+}
+
 static void memory_ranges_init(struct ivpu_device *vdev)
 {
 	if (ivpu_hw_ip_gen(vdev) == IVPU_HW_IP_37XX) {
@@ -245,6 +268,7 @@ int ivpu_hw_init(struct ivpu_device *vdev)
 {
 	ivpu_hw_btrs_info_init(vdev);
 	ivpu_hw_btrs_freq_ratios_init(vdev);
+	priority_bands_init(vdev);
 	memory_ranges_init(vdev);
 	platform_init(vdev);
 	wa_init(vdev);
diff --git a/drivers/accel/ivpu/ivpu_hw.h b/drivers/accel/ivpu/ivpu_hw.h
index a96a05b2acda..1c016b99a0fd 100644
--- a/drivers/accel/ivpu/ivpu_hw.h
+++ b/drivers/accel/ivpu/ivpu_hw.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * Copyright (C) 2020-2024 Intel Corporation
+ * Copyright (C) 2020-2025 Intel Corporation
  */
 
 #ifndef __IVPU_HW_H__
@@ -45,8 +45,12 @@ struct ivpu_hw_info {
 		u8 pn_ratio;
 		u32 profiling_freq;
 	} pll;
+	struct {
+		u32 grace_period[VPU_HWS_NUM_PRIORITY_BANDS];
+		u32 process_quantum[VPU_HWS_NUM_PRIORITY_BANDS];
+		u32 process_grace_period[VPU_HWS_NUM_PRIORITY_BANDS];
+	} hws;
 	u32 tile_fuse;
-	u32 sched_mode;
 	u32 sku;
 	u16 config;
 	int dma_bits;
@@ -87,9 +91,9 @@ static inline u64 ivpu_hw_range_size(const struct ivpu_addr_range *range)
 	return range->end - range->start;
 }
 
-static inline u32 ivpu_hw_ratio_to_freq(struct ivpu_device *vdev, u32 ratio)
+static inline u32 ivpu_hw_dpu_max_freq_get(struct ivpu_device *vdev)
 {
-	return ivpu_hw_btrs_ratio_to_freq(vdev, ratio);
+	return ivpu_hw_btrs_dpu_max_freq_get(vdev);
 }
 
 static inline void ivpu_hw_irq_clear(struct ivpu_device *vdev)
@@ -97,11 +101,6 @@ static inline void ivpu_hw_irq_clear(struct ivpu_device *vdev)
 	ivpu_hw_ip_irq_clear(vdev);
 }
 
-static inline u32 ivpu_hw_pll_freq_get(struct ivpu_device *vdev)
-{
-	return ivpu_hw_btrs_pll_freq_get(vdev);
-}
-
 static inline u32 ivpu_hw_profiling_freq_get(struct ivpu_device *vdev)
 {
 	return vdev->hw->pll.profiling_freq;
diff --git a/drivers/accel/ivpu/ivpu_hw_40xx_reg.h b/drivers/accel/ivpu/ivpu_hw_40xx_reg.h
index d0b795b344c7..fc0ee8d637f9 100644
--- a/drivers/accel/ivpu/ivpu_hw_40xx_reg.h
+++ b/drivers/accel/ivpu/ivpu_hw_40xx_reg.h
@@ -115,6 +115,8 @@
 
 #define VPU_50XX_HOST_SS_AON_PWR_ISLAND_EN_POST_DLY			0x00030068u
 #define VPU_50XX_HOST_SS_AON_PWR_ISLAND_EN_POST_DLY_POST_DLY_MASK	GENMASK(7, 0)
+#define VPU_50XX_HOST_SS_AON_PWR_ISLAND_EN_POST_DLY_POST1_DLY_MASK	GENMASK(15, 8)
+#define VPU_50XX_HOST_SS_AON_PWR_ISLAND_EN_POST_DLY_POST2_DLY_MASK	GENMASK(23, 16)
 
 #define VPU_50XX_HOST_SS_AON_PWR_ISLAND_STATUS_DLY			0x0003006cu
 #define VPU_50XX_HOST_SS_AON_PWR_ISLAND_STATUS_DLY_STATUS_DLY_MASK	GENMASK(7, 0)
diff --git a/drivers/accel/ivpu/ivpu_hw_btrs.c b/drivers/accel/ivpu/ivpu_hw_btrs.c
index 745e5248803d..2d88357b9a3a 100644
--- a/drivers/accel/ivpu/ivpu_hw_btrs.c
+++ b/drivers/accel/ivpu/ivpu_hw_btrs.c
@@ -1,8 +1,10 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Copyright (C) 2020-2024 Intel Corporation
+ * Copyright (C) 2020-2025 Intel Corporation
  */
 
+#include <linux/units.h>
+
 #include "ivpu_drv.h"
 #include "ivpu_hw.h"
 #include "ivpu_hw_btrs.h"
@@ -28,17 +30,13 @@
 
 #define BTRS_LNL_ALL_IRQ_MASK ((u32)-1)
 
-#define BTRS_MTL_WP_CONFIG_1_TILE_5_3_RATIO WP_CONFIG(MTL_CONFIG_1_TILE, MTL_PLL_RATIO_5_3)
-#define BTRS_MTL_WP_CONFIG_1_TILE_4_3_RATIO WP_CONFIG(MTL_CONFIG_1_TILE, MTL_PLL_RATIO_4_3)
-#define BTRS_MTL_WP_CONFIG_2_TILE_5_3_RATIO WP_CONFIG(MTL_CONFIG_2_TILE, MTL_PLL_RATIO_5_3)
-#define BTRS_MTL_WP_CONFIG_2_TILE_4_3_RATIO WP_CONFIG(MTL_CONFIG_2_TILE, MTL_PLL_RATIO_4_3)
-#define BTRS_MTL_WP_CONFIG_0_TILE_PLL_OFF   WP_CONFIG(0, 0)
 
 #define PLL_CDYN_DEFAULT               0x80
 #define PLL_EPP_DEFAULT                0x80
 #define PLL_CONFIG_DEFAULT             0x0
-#define PLL_SIMULATION_FREQ            10000000
-#define PLL_REF_CLK_FREQ               50000000
+#define PLL_REF_CLK_FREQ               50000000ull
+#define PLL_RATIO_TO_FREQ(x)           ((x) * PLL_REF_CLK_FREQ)
+
 #define PLL_TIMEOUT_US		       (1500 * USEC_PER_MSEC)
 #define IDLE_TIMEOUT_US		       (5 * USEC_PER_MSEC)
 #define TIMEOUT_US                     (150 * USEC_PER_MSEC)
@@ -62,6 +60,8 @@
 #define DCT_ENABLE                     0x1
 #define DCT_DISABLE                    0x0
 
+static u32 pll_ratio_to_dpu_freq(struct ivpu_device *vdev, u32 ratio);
+
 int ivpu_hw_btrs_irqs_clear_with_0_mtl(struct ivpu_device *vdev)
 {
 	REGB_WR32(VPU_HW_BTRS_MTL_INTERRUPT_STAT, BTRS_MTL_ALL_IRQ_MASK);
@@ -162,8 +162,7 @@ static int info_init_mtl(struct ivpu_device *vdev)
 
 	hw->tile_fuse = BTRS_MTL_TILE_FUSE_ENABLE_BOTH;
 	hw->sku = BTRS_MTL_TILE_SKU_BOTH;
-	hw->config = BTRS_MTL_WP_CONFIG_2_TILE_4_3_RATIO;
-	hw->sched_mode = ivpu_sched_mode;
+	hw->config = WP_CONFIG(MTL_CONFIG_2_TILE, MTL_PLL_RATIO_4_3);
 
 	return 0;
 }
@@ -178,7 +177,6 @@ static int info_init_lnl(struct ivpu_device *vdev)
 	if (ret)
 		return ret;
 
-	hw->sched_mode = ivpu_sched_mode;
 	hw->tile_fuse = tile_fuse_config;
 	hw->pll.profiling_freq = PLL_PROFILING_FREQ_DEFAULT;
 
@@ -346,8 +344,8 @@ int ivpu_hw_btrs_wp_drive(struct ivpu_device *vdev, bool enable)
 
 	prepare_wp_request(vdev, &wp, enable);
 
-	ivpu_dbg(vdev, PM, "PLL workpoint request: %u Hz, config: 0x%x, epp: 0x%x, cdyn: 0x%x\n",
-		 PLL_RATIO_TO_FREQ(wp.target), wp.cfg, wp.epp, wp.cdyn);
+	ivpu_dbg(vdev, PM, "PLL workpoint request: %lu MHz, config: 0x%x, epp: 0x%x, cdyn: 0x%x\n",
+		 pll_ratio_to_dpu_freq(vdev, wp.target) / HZ_PER_MHZ, wp.cfg, wp.epp, wp.cdyn);
 
 	ret = wp_request_send(vdev, &wp);
 	if (ret) {
@@ -588,6 +586,39 @@ int ivpu_hw_btrs_wait_for_idle(struct ivpu_device *vdev)
 		return REGB_POLL_FLD(VPU_HW_BTRS_LNL_VPU_STATUS, IDLE, 0x1, IDLE_TIMEOUT_US);
 }
 
+static u32 pll_config_get_mtl(struct ivpu_device *vdev)
+{
+	return REGB_RD32(VPU_HW_BTRS_MTL_CURRENT_PLL);
+}
+
+static u32 pll_config_get_lnl(struct ivpu_device *vdev)
+{
+	return REGB_RD32(VPU_HW_BTRS_LNL_PLL_FREQ);
+}
+
+static u32 pll_ratio_to_dpu_freq_mtl(u16 ratio)
+{
+	return (PLL_RATIO_TO_FREQ(ratio) * 2) / 3;
+}
+
+static u32 pll_ratio_to_dpu_freq_lnl(u16 ratio)
+{
+	return PLL_RATIO_TO_FREQ(ratio) / 2;
+}
+
+static u32 pll_ratio_to_dpu_freq(struct ivpu_device *vdev, u32 ratio)
+{
+	if (ivpu_hw_btrs_gen(vdev) == IVPU_HW_BTRS_MTL)
+		return pll_ratio_to_dpu_freq_mtl(ratio);
+	else
+		return pll_ratio_to_dpu_freq_lnl(ratio);
+}
+
+u32 ivpu_hw_btrs_dpu_max_freq_get(struct ivpu_device *vdev)
+{
+	return pll_ratio_to_dpu_freq(vdev, vdev->hw->pll.max_ratio);
+}
+
 /* Handler for IRQs from Buttress core (irqB) */
 bool ivpu_hw_btrs_irq_handler_mtl(struct ivpu_device *vdev, int irq)
 {
@@ -597,9 +628,12 @@ bool ivpu_hw_btrs_irq_handler_mtl(struct ivpu_device *vdev, int irq)
 	if (!status)
 		return false;
 
-	if (REG_TEST_FLD(VPU_HW_BTRS_MTL_INTERRUPT_STAT, FREQ_CHANGE, status))
-		ivpu_dbg(vdev, IRQ, "FREQ_CHANGE irq: %08x",
-			 REGB_RD32(VPU_HW_BTRS_MTL_CURRENT_PLL));
+	if (REG_TEST_FLD(VPU_HW_BTRS_MTL_INTERRUPT_STAT, FREQ_CHANGE, status)) {
+		u32 pll = pll_config_get_mtl(vdev);
+
+		ivpu_dbg(vdev, IRQ, "FREQ_CHANGE irq, wp %08x, %lu MHz",
+			 pll, pll_ratio_to_dpu_freq_mtl(pll) / HZ_PER_MHZ);
+	}
 
 	if (REG_TEST_FLD(VPU_HW_BTRS_MTL_INTERRUPT_STAT, ATS_ERR, status)) {
 		ivpu_err(vdev, "ATS_ERR irq 0x%016llx", REGB_RD64(VPU_HW_BTRS_MTL_ATS_ERR_LOG_0));
@@ -649,8 +683,12 @@ bool ivpu_hw_btrs_irq_handler_lnl(struct ivpu_device *vdev, int irq)
 			ivpu_err_ratelimited(vdev, "IRQ FIFO full\n");
 	}
 
-	if (REG_TEST_FLD(VPU_HW_BTRS_LNL_INTERRUPT_STAT, FREQ_CHANGE, status))
-		ivpu_dbg(vdev, IRQ, "FREQ_CHANGE irq: %08x", REGB_RD32(VPU_HW_BTRS_LNL_PLL_FREQ));
+	if (REG_TEST_FLD(VPU_HW_BTRS_LNL_INTERRUPT_STAT, FREQ_CHANGE, status)) {
+		u32 pll = pll_config_get_lnl(vdev);
+
+		ivpu_dbg(vdev, IRQ, "FREQ_CHANGE irq, wp %08x, %lu MHz",
+			 pll, pll_ratio_to_dpu_freq_lnl(pll) / HZ_PER_MHZ);
+	}
 
 	if (REG_TEST_FLD(VPU_HW_BTRS_LNL_INTERRUPT_STAT, ATS_ERR, status)) {
 		ivpu_err(vdev, "ATS_ERR LOG1 0x%08x ATS_ERR_LOG2 0x%08x\n",
@@ -733,60 +771,6 @@ void ivpu_hw_btrs_dct_set_status(struct ivpu_device *vdev, bool enable, u32 acti
 	REGB_WR32(VPU_HW_BTRS_LNL_PCODE_MAILBOX_STATUS, val);
 }
 
-static u32 pll_ratio_to_freq_mtl(u32 ratio, u32 config)
-{
-	u32 pll_clock = PLL_REF_CLK_FREQ * ratio;
-	u32 cpu_clock;
-
-	if ((config & 0xff) == MTL_PLL_RATIO_4_3)
-		cpu_clock = pll_clock * 2 / 4;
-	else
-		cpu_clock = pll_clock * 2 / 5;
-
-	return cpu_clock;
-}
-
-u32 ivpu_hw_btrs_ratio_to_freq(struct ivpu_device *vdev, u32 ratio)
-{
-	struct ivpu_hw_info *hw = vdev->hw;
-
-	if (ivpu_hw_btrs_gen(vdev) == IVPU_HW_BTRS_MTL)
-		return pll_ratio_to_freq_mtl(ratio, hw->config);
-	else
-		return PLL_RATIO_TO_FREQ(ratio);
-}
-
-static u32 pll_freq_get_mtl(struct ivpu_device *vdev)
-{
-	u32 pll_curr_ratio;
-
-	pll_curr_ratio = REGB_RD32(VPU_HW_BTRS_MTL_CURRENT_PLL);
-	pll_curr_ratio &= VPU_HW_BTRS_MTL_CURRENT_PLL_RATIO_MASK;
-
-	if (!ivpu_is_silicon(vdev))
-		return PLL_SIMULATION_FREQ;
-
-	return pll_ratio_to_freq_mtl(pll_curr_ratio, vdev->hw->config);
-}
-
-static u32 pll_freq_get_lnl(struct ivpu_device *vdev)
-{
-	u32 pll_curr_ratio;
-
-	pll_curr_ratio = REGB_RD32(VPU_HW_BTRS_LNL_PLL_FREQ);
-	pll_curr_ratio &= VPU_HW_BTRS_LNL_PLL_FREQ_RATIO_MASK;
-
-	return PLL_RATIO_TO_FREQ(pll_curr_ratio);
-}
-
-u32 ivpu_hw_btrs_pll_freq_get(struct ivpu_device *vdev)
-{
-	if (ivpu_hw_btrs_gen(vdev) == IVPU_HW_BTRS_MTL)
-		return pll_freq_get_mtl(vdev);
-	else
-		return pll_freq_get_lnl(vdev);
-}
-
 u32 ivpu_hw_btrs_telemetry_offset_get(struct ivpu_device *vdev)
 {
 	if (ivpu_hw_btrs_gen(vdev) == IVPU_HW_BTRS_MTL)
diff --git a/drivers/accel/ivpu/ivpu_hw_btrs.h b/drivers/accel/ivpu/ivpu_hw_btrs.h
index 04f14f50fed6..3855e2df1e0c 100644
--- a/drivers/accel/ivpu/ivpu_hw_btrs.h
+++ b/drivers/accel/ivpu/ivpu_hw_btrs.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * Copyright (C) 2020-2024 Intel Corporation
+ * Copyright (C) 2020-2025 Intel Corporation
  */
 
 #ifndef __IVPU_HW_BTRS_H__
@@ -13,9 +13,8 @@
 
 #define PLL_PROFILING_FREQ_DEFAULT   38400000
 #define PLL_PROFILING_FREQ_HIGH      400000000
-#define PLL_RATIO_TO_FREQ(x)         ((x) * PLL_REF_CLK_FREQ)
 
-#define DCT_DEFAULT_ACTIVE_PERCENT 15u
+#define DCT_DEFAULT_ACTIVE_PERCENT 30u
 #define DCT_PERIOD_US		   35300u
 
 int ivpu_hw_btrs_info_init(struct ivpu_device *vdev);
@@ -32,12 +31,11 @@ int ivpu_hw_btrs_ip_reset(struct ivpu_device *vdev);
 void ivpu_hw_btrs_profiling_freq_reg_set_lnl(struct ivpu_device *vdev);
 void ivpu_hw_btrs_ats_print_lnl(struct ivpu_device *vdev);
 void ivpu_hw_btrs_clock_relinquish_disable_lnl(struct ivpu_device *vdev);
+u32 ivpu_hw_btrs_dpu_max_freq_get(struct ivpu_device *vdev);
 bool ivpu_hw_btrs_irq_handler_mtl(struct ivpu_device *vdev, int irq);
 bool ivpu_hw_btrs_irq_handler_lnl(struct ivpu_device *vdev, int irq);
 int ivpu_hw_btrs_dct_get_request(struct ivpu_device *vdev, bool *enable);
 void ivpu_hw_btrs_dct_set_status(struct ivpu_device *vdev, bool enable, u32 dct_percent);
-u32 ivpu_hw_btrs_pll_freq_get(struct ivpu_device *vdev);
-u32 ivpu_hw_btrs_ratio_to_freq(struct ivpu_device *vdev, u32 ratio);
 u32 ivpu_hw_btrs_telemetry_offset_get(struct ivpu_device *vdev);
 u32 ivpu_hw_btrs_telemetry_size_get(struct ivpu_device *vdev);
 u32 ivpu_hw_btrs_telemetry_enable_get(struct ivpu_device *vdev);
diff --git a/drivers/accel/ivpu/ivpu_hw_ip.c b/drivers/accel/ivpu/ivpu_hw_ip.c
index 60b33fc59d96..bd2582a8c80f 100644
--- a/drivers/accel/ivpu/ivpu_hw_ip.c
+++ b/drivers/accel/ivpu/ivpu_hw_ip.c
@@ -8,15 +8,12 @@
 #include "ivpu_hw.h"
 #include "ivpu_hw_37xx_reg.h"
 #include "ivpu_hw_40xx_reg.h"
+#include "ivpu_hw_btrs.h"
 #include "ivpu_hw_ip.h"
 #include "ivpu_hw_reg_io.h"
 #include "ivpu_mmu.h"
 #include "ivpu_pm.h"
 
-#define PWR_ISLAND_EN_POST_DLY_FREQ_DEFAULT 0
-#define PWR_ISLAND_EN_POST_DLY_FREQ_HIGH    18
-#define PWR_ISLAND_STATUS_DLY_FREQ_DEFAULT  3
-#define PWR_ISLAND_STATUS_DLY_FREQ_HIGH	    46
 #define PWR_ISLAND_STATUS_TIMEOUT_US        (5 * USEC_PER_MSEC)
 
 #define TIM_SAFE_ENABLE		            0xf1d0dead
@@ -268,20 +265,15 @@ void ivpu_hw_ip_idle_gen_disable(struct ivpu_device *vdev)
 		idle_gen_drive_40xx(vdev, false);
 }
 
-static void pwr_island_delay_set_50xx(struct ivpu_device *vdev)
+static void
+pwr_island_delay_set_50xx(struct ivpu_device *vdev, u32 post, u32 post1, u32 post2, u32 status)
 {
-	u32 val, post, status;
-
-	if (vdev->hw->pll.profiling_freq == PLL_PROFILING_FREQ_DEFAULT) {
-		post = PWR_ISLAND_EN_POST_DLY_FREQ_DEFAULT;
-		status = PWR_ISLAND_STATUS_DLY_FREQ_DEFAULT;
-	} else {
-		post = PWR_ISLAND_EN_POST_DLY_FREQ_HIGH;
-		status = PWR_ISLAND_STATUS_DLY_FREQ_HIGH;
-	}
+	u32 val;
 
 	val = REGV_RD32(VPU_50XX_HOST_SS_AON_PWR_ISLAND_EN_POST_DLY);
 	val = REG_SET_FLD_NUM(VPU_50XX_HOST_SS_AON_PWR_ISLAND_EN_POST_DLY, POST_DLY, post, val);
+	val = REG_SET_FLD_NUM(VPU_50XX_HOST_SS_AON_PWR_ISLAND_EN_POST_DLY, POST1_DLY, post1, val);
+	val = REG_SET_FLD_NUM(VPU_50XX_HOST_SS_AON_PWR_ISLAND_EN_POST_DLY, POST2_DLY, post2, val);
 	REGV_WR32(VPU_50XX_HOST_SS_AON_PWR_ISLAND_EN_POST_DLY, val);
 
 	val = REGV_RD32(VPU_50XX_HOST_SS_AON_PWR_ISLAND_STATUS_DLY);
@@ -686,13 +678,36 @@ static void dpu_active_drive_37xx(struct ivpu_device *vdev, bool enable)
 	REGV_WR32(VPU_37XX_HOST_SS_AON_DPU_ACTIVE, val);
 }
 
+static void pwr_island_delay_set(struct ivpu_device *vdev)
+{
+	bool high = vdev->hw->pll.profiling_freq == PLL_PROFILING_FREQ_HIGH;
+	u32 post, post1, post2, status;
+
+	if (ivpu_hw_ip_gen(vdev) < IVPU_HW_IP_50XX)
+		return;
+
+	switch (ivpu_device_id(vdev)) {
+	case PCI_DEVICE_ID_PTL_P:
+		post = high ? 18 : 0;
+		post1 = 0;
+		post2 = 0;
+		status = high ? 46 : 3;
+		break;
+
+	default:
+		dump_stack();
+		ivpu_err(vdev, "Unknown device ID\n");
+		return;
+	}
+
+	pwr_island_delay_set_50xx(vdev, post, post1, post2, status);
+}
+
 int ivpu_hw_ip_pwr_domain_enable(struct ivpu_device *vdev)
 {
 	int ret;
 
-	if (ivpu_hw_ip_gen(vdev) == IVPU_HW_IP_50XX)
-		pwr_island_delay_set_50xx(vdev);
-
+	pwr_island_delay_set(vdev);
 	pwr_island_enable(vdev);
 
 	ret = wait_for_pwr_island_status(vdev, 0x1);
diff --git a/drivers/accel/ivpu/ivpu_ipc.c b/drivers/accel/ivpu/ivpu_ipc.c
index 29b723039a34..f0402dc84758 100644
--- a/drivers/accel/ivpu/ivpu_ipc.c
+++ b/drivers/accel/ivpu/ivpu_ipc.c
@@ -299,7 +299,8 @@ ivpu_ipc_send_receive_internal(struct ivpu_device *vdev, struct vpu_jsm_msg *req
 	struct ivpu_ipc_consumer cons;
 	int ret;
 
-	drm_WARN_ON(&vdev->drm, pm_runtime_status_suspended(vdev->drm.dev));
+	drm_WARN_ON(&vdev->drm, pm_runtime_status_suspended(vdev->drm.dev) &&
+		    pm_runtime_enabled(vdev->drm.dev));
 
 	ivpu_ipc_consumer_add(vdev, &cons, channel, NULL);
 
@@ -353,6 +354,32 @@ rpm_put:
 	return ret;
 }
 
+int ivpu_ipc_send_and_wait(struct ivpu_device *vdev, struct vpu_jsm_msg *req,
+			   u32 channel, unsigned long timeout_ms)
+{
+	struct ivpu_ipc_consumer cons;
+	int ret;
+
+	ret = ivpu_rpm_get(vdev);
+	if (ret < 0)
+		return ret;
+
+	ivpu_ipc_consumer_add(vdev, &cons, channel, NULL);
+
+	ret = ivpu_ipc_send(vdev, &cons, req);
+	if (ret) {
+		ivpu_warn_ratelimited(vdev, "IPC send failed: %d\n", ret);
+		goto consumer_del;
+	}
+
+	msleep(timeout_ms);
+
+consumer_del:
+	ivpu_ipc_consumer_del(vdev, &cons);
+	ivpu_rpm_put(vdev);
+	return ret;
+}
+
 static bool
 ivpu_ipc_match_consumer(struct ivpu_device *vdev, struct ivpu_ipc_consumer *cons,
 			struct ivpu_ipc_hdr *ipc_hdr, struct vpu_jsm_msg *jsm_msg)
diff --git a/drivers/accel/ivpu/ivpu_ipc.h b/drivers/accel/ivpu/ivpu_ipc.h
index fb4de7fb8210..b4dfb504679b 100644
--- a/drivers/accel/ivpu/ivpu_ipc.h
+++ b/drivers/accel/ivpu/ivpu_ipc.h
@@ -107,5 +107,7 @@ int ivpu_ipc_send_receive_internal(struct ivpu_device *vdev, struct vpu_jsm_msg
 int ivpu_ipc_send_receive(struct ivpu_device *vdev, struct vpu_jsm_msg *req,
 			  enum vpu_ipc_msg_type expected_resp, struct vpu_jsm_msg *resp,
 			  u32 channel, unsigned long timeout_ms);
+int ivpu_ipc_send_and_wait(struct ivpu_device *vdev, struct vpu_jsm_msg *req,
+			   u32 channel, unsigned long timeout_ms);
 
 #endif /* __IVPU_IPC_H__ */
diff --git a/drivers/accel/ivpu/ivpu_job.c b/drivers/accel/ivpu/ivpu_job.c
index be2e2bf0f43f..e631098718b1 100644
--- a/drivers/accel/ivpu/ivpu_job.c
+++ b/drivers/accel/ivpu/ivpu_job.c
@@ -21,8 +21,6 @@
 #include "vpu_boot_api.h"
 
 #define CMD_BUF_IDX	     0
-#define JOB_ID_JOB_MASK	     GENMASK(7, 0)
-#define JOB_ID_CONTEXT_MASK  GENMASK(31, 8)
 #define JOB_MAX_BUFFER_COUNT 65535
 
 static void ivpu_cmdq_ring_db(struct ivpu_device *vdev, struct ivpu_cmdq *cmdq)
@@ -37,7 +35,7 @@ static int ivpu_preemption_buffers_create(struct ivpu_device *vdev,
 	u64 secondary_size = ALIGN(vdev->fw->secondary_preempt_buf_size, PAGE_SIZE);
 	struct ivpu_addr_range range;
 
-	if (vdev->hw->sched_mode != VPU_SCHEDULING_MODE_HW)
+	if (vdev->fw->sched_mode != VPU_SCHEDULING_MODE_HW)
 		return 0;
 
 	range.start = vdev->hw->ranges.user.end - (primary_size * IVPU_NUM_CMDQS_PER_CTX);
@@ -62,24 +60,24 @@ static int ivpu_preemption_buffers_create(struct ivpu_device *vdev,
 
 err_free_primary:
 	ivpu_bo_free(cmdq->primary_preempt_buf);
+	cmdq->primary_preempt_buf = NULL;
 	return -ENOMEM;
 }
 
 static void ivpu_preemption_buffers_free(struct ivpu_device *vdev,
 					 struct ivpu_file_priv *file_priv, struct ivpu_cmdq *cmdq)
 {
-	if (vdev->hw->sched_mode != VPU_SCHEDULING_MODE_HW)
+	if (vdev->fw->sched_mode != VPU_SCHEDULING_MODE_HW)
 		return;
 
-	drm_WARN_ON(&vdev->drm, !cmdq->primary_preempt_buf);
-	drm_WARN_ON(&vdev->drm, !cmdq->secondary_preempt_buf);
-	ivpu_bo_free(cmdq->primary_preempt_buf);
-	ivpu_bo_free(cmdq->secondary_preempt_buf);
+	if (cmdq->primary_preempt_buf)
+		ivpu_bo_free(cmdq->primary_preempt_buf);
+	if (cmdq->secondary_preempt_buf)
+		ivpu_bo_free(cmdq->secondary_preempt_buf);
 }
 
 static struct ivpu_cmdq *ivpu_cmdq_alloc(struct ivpu_file_priv *file_priv)
 {
-	struct xa_limit db_xa_limit = {.max = IVPU_MAX_DB, .min = IVPU_MIN_DB};
 	struct ivpu_device *vdev = file_priv->vdev;
 	struct ivpu_cmdq *cmdq;
 	int ret;
@@ -88,26 +86,16 @@ static struct ivpu_cmdq *ivpu_cmdq_alloc(struct ivpu_file_priv *file_priv)
 	if (!cmdq)
 		return NULL;
 
-	ret = xa_alloc(&vdev->db_xa, &cmdq->db_id, NULL, db_xa_limit, GFP_KERNEL);
-	if (ret) {
-		ivpu_err(vdev, "Failed to allocate doorbell id: %d\n", ret);
-		goto err_free_cmdq;
-	}
-
 	cmdq->mem = ivpu_bo_create_global(vdev, SZ_4K, DRM_IVPU_BO_WC | DRM_IVPU_BO_MAPPABLE);
 	if (!cmdq->mem)
-		goto err_erase_xa;
+		goto err_free_cmdq;
 
 	ret = ivpu_preemption_buffers_create(vdev, file_priv, cmdq);
 	if (ret)
-		goto err_free_cmdq_mem;
+		ivpu_warn(vdev, "Failed to allocate preemption buffers, preemption limited\n");
 
 	return cmdq;
 
-err_free_cmdq_mem:
-	ivpu_bo_free(cmdq->mem);
-err_erase_xa:
-	xa_erase(&vdev->db_xa, cmdq->db_id);
 err_free_cmdq:
 	kfree(cmdq);
 	return NULL;
@@ -130,13 +118,13 @@ static int ivpu_hws_cmdq_init(struct ivpu_file_priv *file_priv, struct ivpu_cmdq
 	struct ivpu_device *vdev = file_priv->vdev;
 	int ret;
 
-	ret = ivpu_jsm_hws_create_cmdq(vdev, file_priv->ctx.id, file_priv->ctx.id, cmdq->db_id,
+	ret = ivpu_jsm_hws_create_cmdq(vdev, file_priv->ctx.id, file_priv->ctx.id, cmdq->id,
 				       task_pid_nr(current), engine,
 				       cmdq->mem->vpu_addr, ivpu_bo_size(cmdq->mem));
 	if (ret)
 		return ret;
 
-	ret = ivpu_jsm_hws_set_context_sched_properties(vdev, file_priv->ctx.id, cmdq->db_id,
+	ret = ivpu_jsm_hws_set_context_sched_properties(vdev, file_priv->ctx.id, cmdq->id,
 							priority);
 	if (ret)
 		return ret;
@@ -149,21 +137,22 @@ static int ivpu_register_db(struct ivpu_file_priv *file_priv, struct ivpu_cmdq *
 	struct ivpu_device *vdev = file_priv->vdev;
 	int ret;
 
-	if (vdev->hw->sched_mode == VPU_SCHEDULING_MODE_HW)
-		ret = ivpu_jsm_hws_register_db(vdev, file_priv->ctx.id, cmdq->db_id, cmdq->db_id,
+	if (vdev->fw->sched_mode == VPU_SCHEDULING_MODE_HW)
+		ret = ivpu_jsm_hws_register_db(vdev, file_priv->ctx.id, cmdq->id, cmdq->db_id,
 					       cmdq->mem->vpu_addr, ivpu_bo_size(cmdq->mem));
 	else
 		ret = ivpu_jsm_register_db(vdev, file_priv->ctx.id, cmdq->db_id,
 					   cmdq->mem->vpu_addr, ivpu_bo_size(cmdq->mem));
 
 	if (!ret)
-		ivpu_dbg(vdev, JOB, "DB %d registered to ctx %d\n", cmdq->db_id, file_priv->ctx.id);
+		ivpu_dbg(vdev, JOB, "DB %d registered to cmdq %d ctx %d\n",
+			 cmdq->db_id, cmdq->id, file_priv->ctx.id);
 
 	return ret;
 }
 
 static int
-ivpu_cmdq_init(struct ivpu_file_priv *file_priv, struct ivpu_cmdq *cmdq, u16 engine, u8 priority)
+ivpu_cmdq_init(struct ivpu_file_priv *file_priv, struct ivpu_cmdq *cmdq, u8 priority)
 {
 	struct ivpu_device *vdev = file_priv->vdev;
 	struct vpu_job_queue_header *jobq_header;
@@ -179,13 +168,13 @@ ivpu_cmdq_init(struct ivpu_file_priv *file_priv, struct ivpu_cmdq *cmdq, u16 eng
 
 	cmdq->jobq = (struct vpu_job_queue *)ivpu_bo_vaddr(cmdq->mem);
 	jobq_header = &cmdq->jobq->header;
-	jobq_header->engine_idx = engine;
+	jobq_header->engine_idx = VPU_ENGINE_COMPUTE;
 	jobq_header->head = 0;
 	jobq_header->tail = 0;
 	wmb(); /* Flush WC buffer for jobq->header */
 
-	if (vdev->hw->sched_mode == VPU_SCHEDULING_MODE_HW) {
-		ret = ivpu_hws_cmdq_init(file_priv, cmdq, engine, priority);
+	if (vdev->fw->sched_mode == VPU_SCHEDULING_MODE_HW) {
+		ret = ivpu_hws_cmdq_init(file_priv, cmdq, VPU_ENGINE_COMPUTE, priority);
 		if (ret)
 			return ret;
 	}
@@ -211,10 +200,10 @@ static int ivpu_cmdq_fini(struct ivpu_file_priv *file_priv, struct ivpu_cmdq *cm
 
 	cmdq->db_registered = false;
 
-	if (vdev->hw->sched_mode == VPU_SCHEDULING_MODE_HW) {
-		ret = ivpu_jsm_hws_destroy_cmdq(vdev, file_priv->ctx.id, cmdq->db_id);
+	if (vdev->fw->sched_mode == VPU_SCHEDULING_MODE_HW) {
+		ret = ivpu_jsm_hws_destroy_cmdq(vdev, file_priv->ctx.id, cmdq->id);
 		if (!ret)
-			ivpu_dbg(vdev, JOB, "Command queue %d destroyed\n", cmdq->db_id);
+			ivpu_dbg(vdev, JOB, "Command queue %d destroyed\n", cmdq->id);
 	}
 
 	ret = ivpu_jsm_unregister_db(vdev, cmdq->db_id);
@@ -224,55 +213,104 @@ static int ivpu_cmdq_fini(struct ivpu_file_priv *file_priv, struct ivpu_cmdq *cm
 	return 0;
 }
 
-static struct ivpu_cmdq *ivpu_cmdq_acquire(struct ivpu_file_priv *file_priv, u16 engine,
-					   u8 priority)
+static int ivpu_db_id_alloc(struct ivpu_device *vdev, u32 *db_id)
+{
+	int ret;
+	u32 id;
+
+	ret = xa_alloc_cyclic(&vdev->db_xa, &id, NULL, vdev->db_limit, &vdev->db_next, GFP_KERNEL);
+	if (ret < 0)
+		return ret;
+
+	*db_id = id;
+	return 0;
+}
+
+static int ivpu_cmdq_id_alloc(struct ivpu_file_priv *file_priv, u32 *cmdq_id)
 {
-	int cmdq_idx = IVPU_CMDQ_INDEX(engine, priority);
-	struct ivpu_cmdq *cmdq = file_priv->cmdq[cmdq_idx];
+	int ret;
+	u32 id;
+
+	ret = xa_alloc_cyclic(&file_priv->cmdq_xa, &id, NULL, file_priv->cmdq_limit,
+			      &file_priv->cmdq_id_next, GFP_KERNEL);
+	if (ret < 0)
+		return ret;
+
+	*cmdq_id = id;
+	return 0;
+}
+
+static struct ivpu_cmdq *ivpu_cmdq_acquire(struct ivpu_file_priv *file_priv, u8 priority)
+{
+	struct ivpu_device *vdev = file_priv->vdev;
+	struct ivpu_cmdq *cmdq;
+	unsigned long id;
 	int ret;
 
 	lockdep_assert_held(&file_priv->lock);
 
+	xa_for_each(&file_priv->cmdq_xa, id, cmdq)
+		if (cmdq->priority == priority)
+			break;
+
 	if (!cmdq) {
 		cmdq = ivpu_cmdq_alloc(file_priv);
-		if (!cmdq)
+		if (!cmdq) {
+			ivpu_err(vdev, "Failed to allocate command queue\n");
 			return NULL;
-		file_priv->cmdq[cmdq_idx] = cmdq;
+		}
+
+		ret = ivpu_db_id_alloc(vdev, &cmdq->db_id);
+		if (ret) {
+			ivpu_err(file_priv->vdev, "Failed to allocate doorbell ID: %d\n", ret);
+			goto err_free_cmdq;
+		}
+
+		ret = ivpu_cmdq_id_alloc(file_priv, &cmdq->id);
+		if (ret) {
+			ivpu_err(vdev, "Failed to allocate command queue ID: %d\n", ret);
+			goto err_erase_db_id;
+		}
+
+		cmdq->priority = priority;
+		ret = xa_err(xa_store(&file_priv->cmdq_xa, cmdq->id, cmdq, GFP_KERNEL));
+		if (ret) {
+			ivpu_err(vdev, "Failed to store command queue in cmdq_xa: %d\n", ret);
+			goto err_erase_cmdq_id;
+		}
 	}
 
-	ret = ivpu_cmdq_init(file_priv, cmdq, engine, priority);
-	if (ret)
-		return NULL;
+	ret = ivpu_cmdq_init(file_priv, cmdq, priority);
+	if (ret) {
+		ivpu_err(vdev, "Failed to initialize command queue: %d\n", ret);
+		goto err_free_cmdq;
+	}
 
 	return cmdq;
+
+err_erase_cmdq_id:
+	xa_erase(&file_priv->cmdq_xa, cmdq->id);
+err_erase_db_id:
+	xa_erase(&vdev->db_xa, cmdq->db_id);
+err_free_cmdq:
+	ivpu_cmdq_free(file_priv, cmdq);
+	return NULL;
 }
 
-static void ivpu_cmdq_release_locked(struct ivpu_file_priv *file_priv, u16 engine, u8 priority)
+void ivpu_cmdq_release_all_locked(struct ivpu_file_priv *file_priv)
 {
-	int cmdq_idx = IVPU_CMDQ_INDEX(engine, priority);
-	struct ivpu_cmdq *cmdq = file_priv->cmdq[cmdq_idx];
+	struct ivpu_cmdq *cmdq;
+	unsigned long cmdq_id;
 
 	lockdep_assert_held(&file_priv->lock);
 
-	if (cmdq) {
-		file_priv->cmdq[cmdq_idx] = NULL;
+	xa_for_each(&file_priv->cmdq_xa, cmdq_id, cmdq) {
+		xa_erase(&file_priv->cmdq_xa, cmdq_id);
 		ivpu_cmdq_fini(file_priv, cmdq);
 		ivpu_cmdq_free(file_priv, cmdq);
 	}
 }
 
-void ivpu_cmdq_release_all_locked(struct ivpu_file_priv *file_priv)
-{
-	u16 engine;
-	u8 priority;
-
-	lockdep_assert_held(&file_priv->lock);
-
-	for (engine = 0; engine < IVPU_NUM_ENGINES; engine++)
-		for (priority = 0; priority < IVPU_NUM_PRIORITIES; priority++)
-			ivpu_cmdq_release_locked(file_priv, engine, priority);
-}
-
 /*
  * Mark the doorbell as unregistered
  * This function needs to be called when the VPU hardware is restarted
@@ -281,20 +319,13 @@ void ivpu_cmdq_release_all_locked(struct ivpu_file_priv *file_priv)
  */
 static void ivpu_cmdq_reset(struct ivpu_file_priv *file_priv)
 {
-	u16 engine;
-	u8 priority;
+	struct ivpu_cmdq *cmdq;
+	unsigned long cmdq_id;
 
 	mutex_lock(&file_priv->lock);
 
-	for (engine = 0; engine < IVPU_NUM_ENGINES; engine++) {
-		for (priority = 0; priority < IVPU_NUM_PRIORITIES; priority++) {
-			int cmdq_idx = IVPU_CMDQ_INDEX(engine, priority);
-			struct ivpu_cmdq *cmdq = file_priv->cmdq[cmdq_idx];
-
-			if (cmdq)
-				cmdq->db_registered = false;
-		}
-	}
+	xa_for_each(&file_priv->cmdq_xa, cmdq_id, cmdq)
+		cmdq->db_registered = false;
 
 	mutex_unlock(&file_priv->lock);
 }
@@ -314,17 +345,11 @@ void ivpu_cmdq_reset_all_contexts(struct ivpu_device *vdev)
 
 static void ivpu_cmdq_fini_all(struct ivpu_file_priv *file_priv)
 {
-	u16 engine;
-	u8 priority;
-
-	for (engine = 0; engine < IVPU_NUM_ENGINES; engine++) {
-		for (priority = 0; priority < IVPU_NUM_PRIORITIES; priority++) {
-			int cmdq_idx = IVPU_CMDQ_INDEX(engine, priority);
+	struct ivpu_cmdq *cmdq;
+	unsigned long cmdq_id;
 
-			if (file_priv->cmdq[cmdq_idx])
-				ivpu_cmdq_fini(file_priv, file_priv->cmdq[cmdq_idx]);
-		}
-	}
+	xa_for_each(&file_priv->cmdq_xa, cmdq_id, cmdq)
+		ivpu_cmdq_fini(file_priv, cmdq);
 }
 
 void ivpu_context_abort_locked(struct ivpu_file_priv *file_priv)
@@ -335,8 +360,10 @@ void ivpu_context_abort_locked(struct ivpu_file_priv *file_priv)
 
 	ivpu_cmdq_fini_all(file_priv);
 
-	if (vdev->hw->sched_mode == VPU_SCHEDULING_MODE_OS)
+	if (vdev->fw->sched_mode == VPU_SCHEDULING_MODE_OS)
 		ivpu_jsm_context_release(vdev, file_priv->ctx.id);
+
+	file_priv->aborted = true;
 }
 
 static int ivpu_cmdq_push_job(struct ivpu_cmdq *cmdq, struct ivpu_job *job)
@@ -349,24 +376,30 @@ static int ivpu_cmdq_push_job(struct ivpu_cmdq *cmdq, struct ivpu_job *job)
 
 	/* Check if there is space left in job queue */
 	if (next_entry == header->head) {
-		ivpu_dbg(vdev, JOB, "Job queue full: ctx %d engine %d db %d head %d tail %d\n",
-			 job->file_priv->ctx.id, job->engine_idx, cmdq->db_id, header->head, tail);
+		ivpu_dbg(vdev, JOB, "Job queue full: ctx %d cmdq %d db %d head %d tail %d\n",
+			 job->file_priv->ctx.id, cmdq->id, cmdq->db_id, header->head, tail);
 		return -EBUSY;
 	}
 
-	entry = &cmdq->jobq->job[tail];
+	entry = &cmdq->jobq->slot[tail].job;
 	entry->batch_buf_addr = job->cmd_buf_vpu_addr;
 	entry->job_id = job->job_id;
 	entry->flags = 0;
 	if (unlikely(ivpu_test_mode & IVPU_TEST_MODE_NULL_SUBMISSION))
 		entry->flags = VPU_JOB_FLAGS_NULL_SUBMISSION_MASK;
 
-	if (vdev->hw->sched_mode == VPU_SCHEDULING_MODE_HW &&
+	if (vdev->fw->sched_mode == VPU_SCHEDULING_MODE_HW &&
 	    (unlikely(!(ivpu_test_mode & IVPU_TEST_MODE_PREEMPTION_DISABLE)))) {
-		entry->primary_preempt_buf_addr = cmdq->primary_preempt_buf->vpu_addr;
-		entry->primary_preempt_buf_size = ivpu_bo_size(cmdq->primary_preempt_buf);
-		entry->secondary_preempt_buf_addr = cmdq->secondary_preempt_buf->vpu_addr;
-		entry->secondary_preempt_buf_size = ivpu_bo_size(cmdq->secondary_preempt_buf);
+		if (cmdq->primary_preempt_buf) {
+			entry->primary_preempt_buf_addr = cmdq->primary_preempt_buf->vpu_addr;
+			entry->primary_preempt_buf_size = ivpu_bo_size(cmdq->primary_preempt_buf);
+		}
+
+		if (cmdq->secondary_preempt_buf) {
+			entry->secondary_preempt_buf_addr = cmdq->secondary_preempt_buf->vpu_addr;
+			entry->secondary_preempt_buf_size =
+				ivpu_bo_size(cmdq->secondary_preempt_buf);
+		}
 	}
 
 	wmb(); /* Ensure that tail is updated after filling entry */
@@ -469,16 +502,14 @@ static struct ivpu_job *ivpu_job_remove_from_submitted_jobs(struct ivpu_device *
 {
 	struct ivpu_job *job;
 
-	xa_lock(&vdev->submitted_jobs_xa);
-	job = __xa_erase(&vdev->submitted_jobs_xa, job_id);
+	lockdep_assert_held(&vdev->submitted_jobs_lock);
 
+	job = xa_erase(&vdev->submitted_jobs_xa, job_id);
 	if (xa_empty(&vdev->submitted_jobs_xa) && job) {
 		vdev->busy_time = ktime_add(ktime_sub(ktime_get(), vdev->busy_start_ts),
 					    vdev->busy_time);
 	}
 
-	xa_unlock(&vdev->submitted_jobs_xa);
-
 	return job;
 }
 
@@ -486,6 +517,28 @@ static int ivpu_job_signal_and_destroy(struct ivpu_device *vdev, u32 job_id, u32
 {
 	struct ivpu_job *job;
 
+	lockdep_assert_held(&vdev->submitted_jobs_lock);
+
+	job = xa_load(&vdev->submitted_jobs_xa, job_id);
+	if (!job)
+		return -ENOENT;
+
+	if (job_status == VPU_JSM_STATUS_MVNCI_CONTEXT_VIOLATION_HW) {
+		guard(mutex)(&job->file_priv->lock);
+
+		if (job->file_priv->has_mmu_faults)
+			return 0;
+
+		/*
+		 * Mark context as faulty and defer destruction of the job to jobs abort thread
+		 * handler to synchronize between both faults and jobs returning context violation
+		 * status and ensure both are handled in the same way
+		 */
+		job->file_priv->has_mmu_faults = true;
+		queue_work(system_wq, &vdev->context_abort_work);
+		return 0;
+	}
+
 	job = ivpu_job_remove_from_submitted_jobs(vdev, job_id);
 	if (!job)
 		return -ENOENT;
@@ -503,6 +556,10 @@ static int ivpu_job_signal_and_destroy(struct ivpu_device *vdev, u32 job_id, u32
 	ivpu_stop_job_timeout_detection(vdev);
 
 	ivpu_rpm_put(vdev);
+
+	if (!xa_empty(&vdev->submitted_jobs_xa))
+		ivpu_start_job_timeout_detection(vdev);
+
 	return 0;
 }
 
@@ -511,15 +568,18 @@ void ivpu_jobs_abort_all(struct ivpu_device *vdev)
 	struct ivpu_job *job;
 	unsigned long id;
 
+	mutex_lock(&vdev->submitted_jobs_lock);
+
 	xa_for_each(&vdev->submitted_jobs_xa, id, job)
 		ivpu_job_signal_and_destroy(vdev, id, DRM_IVPU_JOB_STATUS_ABORTED);
+
+	mutex_unlock(&vdev->submitted_jobs_lock);
 }
 
 static int ivpu_job_submit(struct ivpu_job *job, u8 priority)
 {
 	struct ivpu_file_priv *file_priv = job->file_priv;
 	struct ivpu_device *vdev = job->vdev;
-	struct xa_limit job_id_range;
 	struct ivpu_cmdq *cmdq;
 	bool is_first_job;
 	int ret;
@@ -528,27 +588,25 @@ static int ivpu_job_submit(struct ivpu_job *job, u8 priority)
 	if (ret < 0)
 		return ret;
 
+	mutex_lock(&vdev->submitted_jobs_lock);
 	mutex_lock(&file_priv->lock);
 
-	cmdq = ivpu_cmdq_acquire(job->file_priv, job->engine_idx, priority);
+	cmdq = ivpu_cmdq_acquire(file_priv, priority);
 	if (!cmdq) {
 		ivpu_warn_ratelimited(vdev, "Failed to get job queue, ctx %d engine %d prio %d\n",
 				      file_priv->ctx.id, job->engine_idx, priority);
 		ret = -EINVAL;
-		goto err_unlock_file_priv;
+		goto err_unlock;
 	}
 
-	job_id_range.min = FIELD_PREP(JOB_ID_CONTEXT_MASK, (file_priv->ctx.id - 1));
-	job_id_range.max = job_id_range.min | JOB_ID_JOB_MASK;
-
-	xa_lock(&vdev->submitted_jobs_xa);
 	is_first_job = xa_empty(&vdev->submitted_jobs_xa);
-	ret = __xa_alloc(&vdev->submitted_jobs_xa, &job->job_id, job, job_id_range, GFP_KERNEL);
-	if (ret) {
+	ret = xa_alloc_cyclic(&vdev->submitted_jobs_xa, &job->job_id, job, file_priv->job_limit,
+			      &file_priv->job_id_next, GFP_KERNEL);
+	if (ret < 0) {
 		ivpu_dbg(vdev, JOB, "Too many active jobs in ctx %d\n",
 			 file_priv->ctx.id);
 		ret = -EBUSY;
-		goto err_unlock_submitted_jobs_xa;
+		goto err_unlock;
 	}
 
 	ret = ivpu_cmdq_push_job(cmdq, job);
@@ -570,20 +628,20 @@ static int ivpu_job_submit(struct ivpu_job *job, u8 priority)
 		 job->job_id, file_priv->ctx.id, job->engine_idx, priority,
 		 job->cmd_buf_vpu_addr, cmdq->jobq->header.tail);
 
-	xa_unlock(&vdev->submitted_jobs_xa);
-
 	mutex_unlock(&file_priv->lock);
 
-	if (unlikely(ivpu_test_mode & IVPU_TEST_MODE_NULL_HW))
+	if (unlikely(ivpu_test_mode & IVPU_TEST_MODE_NULL_HW)) {
 		ivpu_job_signal_and_destroy(vdev, job->job_id, VPU_JSM_STATUS_SUCCESS);
+	}
+
+	mutex_unlock(&vdev->submitted_jobs_lock);
 
 	return 0;
 
 err_erase_xa:
-	__xa_erase(&vdev->submitted_jobs_xa, job->job_id);
-err_unlock_submitted_jobs_xa:
-	xa_unlock(&vdev->submitted_jobs_xa);
-err_unlock_file_priv:
+	xa_erase(&vdev->submitted_jobs_xa, job->job_id);
+err_unlock:
+	mutex_unlock(&vdev->submitted_jobs_lock);
 	mutex_unlock(&file_priv->lock);
 	ivpu_rpm_put(vdev);
 	return ret;
@@ -673,7 +731,7 @@ int ivpu_submit_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 	int idx, ret;
 	u8 priority;
 
-	if (params->engine > DRM_IVPU_ENGINE_COPY)
+	if (params->engine != DRM_IVPU_ENGINE_COMPUTE)
 		return -EINVAL;
 
 	if (params->priority > DRM_IVPU_JOB_PRIORITY_REALTIME)
@@ -753,7 +811,6 @@ ivpu_job_done_callback(struct ivpu_device *vdev, struct ivpu_ipc_hdr *ipc_hdr,
 		       struct vpu_jsm_msg *jsm_msg)
 {
 	struct vpu_ipc_msg_payload_job_done *payload;
-	int ret;
 
 	if (!jsm_msg) {
 		ivpu_err(vdev, "IPC message has no JSM payload\n");
@@ -766,9 +823,10 @@ ivpu_job_done_callback(struct ivpu_device *vdev, struct ivpu_ipc_hdr *ipc_hdr,
 	}
 
 	payload = (struct vpu_ipc_msg_payload_job_done *)&jsm_msg->payload;
-	ret = ivpu_job_signal_and_destroy(vdev, payload->job_id, payload->job_status);
-	if (!ret && !xa_empty(&vdev->submitted_jobs_xa))
-		ivpu_start_job_timeout_detection(vdev);
+
+	mutex_lock(&vdev->submitted_jobs_lock);
+	ivpu_job_signal_and_destroy(vdev, payload->job_id, payload->job_status);
+	mutex_unlock(&vdev->submitted_jobs_lock);
 }
 
 void ivpu_job_done_consumer_init(struct ivpu_device *vdev)
@@ -781,3 +839,43 @@ void ivpu_job_done_consumer_fini(struct ivpu_device *vdev)
 {
 	ivpu_ipc_consumer_del(vdev, &vdev->job_done_consumer);
 }
+
+void ivpu_context_abort_thread_handler(struct work_struct *work)
+{
+	struct ivpu_device *vdev = container_of(work, struct ivpu_device, context_abort_work);
+	struct ivpu_file_priv *file_priv;
+	unsigned long ctx_id;
+	struct ivpu_job *job;
+	unsigned long id;
+
+	if (vdev->fw->sched_mode == VPU_SCHEDULING_MODE_HW)
+		if (ivpu_jsm_reset_engine(vdev, 0))
+			return;
+
+	mutex_lock(&vdev->context_list_lock);
+	xa_for_each(&vdev->context_xa, ctx_id, file_priv) {
+		if (!file_priv->has_mmu_faults || file_priv->aborted)
+			continue;
+
+		mutex_lock(&file_priv->lock);
+		ivpu_context_abort_locked(file_priv);
+		mutex_unlock(&file_priv->lock);
+	}
+	mutex_unlock(&vdev->context_list_lock);
+
+	if (vdev->fw->sched_mode != VPU_SCHEDULING_MODE_HW)
+		return;
+
+	if (ivpu_jsm_hws_resume_engine(vdev, 0))
+		return;
+	/*
+	 * In hardware scheduling mode NPU already has stopped processing jobs
+	 * and won't send us any further notifications, thus we have to free job related resources
+	 * and notify userspace
+	 */
+	mutex_lock(&vdev->submitted_jobs_lock);
+	xa_for_each(&vdev->submitted_jobs_xa, id, job)
+		if (job->file_priv->aborted)
+			ivpu_job_signal_and_destroy(vdev, job->job_id, DRM_IVPU_JOB_STATUS_ABORTED);
+	mutex_unlock(&vdev->submitted_jobs_lock);
+}
diff --git a/drivers/accel/ivpu/ivpu_job.h b/drivers/accel/ivpu/ivpu_job.h
index 6accb94028c7..af1ed039569c 100644
--- a/drivers/accel/ivpu/ivpu_job.h
+++ b/drivers/accel/ivpu/ivpu_job.h
@@ -28,8 +28,10 @@ struct ivpu_cmdq {
 	struct ivpu_bo *secondary_preempt_buf;
 	struct ivpu_bo *mem;
 	u32 entry_count;
+	u32 id;
 	u32 db_id;
 	bool db_registered;
+	u8 priority;
 };
 
 /**
@@ -64,6 +66,7 @@ void ivpu_cmdq_reset_all_contexts(struct ivpu_device *vdev);
 
 void ivpu_job_done_consumer_init(struct ivpu_device *vdev);
 void ivpu_job_done_consumer_fini(struct ivpu_device *vdev);
+void ivpu_context_abort_thread_handler(struct work_struct *work);
 
 void ivpu_jobs_abort_all(struct ivpu_device *vdev);
 
diff --git a/drivers/accel/ivpu/ivpu_jsm_msg.c b/drivers/accel/ivpu/ivpu_jsm_msg.c
index 88105963c1b2..7c08308d5725 100644
--- a/drivers/accel/ivpu/ivpu_jsm_msg.c
+++ b/drivers/accel/ivpu/ivpu_jsm_msg.c
@@ -7,6 +7,8 @@
 #include "ivpu_hw.h"
 #include "ivpu_ipc.h"
 #include "ivpu_jsm_msg.h"
+#include "ivpu_pm.h"
+#include "vpu_jsm_api.h"
 
 const char *ivpu_jsm_msg_type_to_str(enum vpu_ipc_msg_type type)
 {
@@ -48,9 +50,10 @@ const char *ivpu_jsm_msg_type_to_str(enum vpu_ipc_msg_type type)
 	IVPU_CASE_TO_STR(VPU_JSM_MSG_HWS_RESUME_ENGINE_DONE);
 	IVPU_CASE_TO_STR(VPU_JSM_MSG_STATE_DUMP);
 	IVPU_CASE_TO_STR(VPU_JSM_MSG_STATE_DUMP_RSP);
-	IVPU_CASE_TO_STR(VPU_JSM_MSG_BLOB_DEINIT);
+	IVPU_CASE_TO_STR(VPU_JSM_MSG_BLOB_DEINIT_DEPRECATED);
 	IVPU_CASE_TO_STR(VPU_JSM_MSG_DYNDBG_CONTROL);
 	IVPU_CASE_TO_STR(VPU_JSM_MSG_JOB_DONE);
+	IVPU_CASE_TO_STR(VPU_JSM_MSG_NATIVE_FENCE_SIGNALLED);
 	IVPU_CASE_TO_STR(VPU_JSM_MSG_ENGINE_RESET_DONE);
 	IVPU_CASE_TO_STR(VPU_JSM_MSG_ENGINE_PREEMPT_DONE);
 	IVPU_CASE_TO_STR(VPU_JSM_MSG_REGISTER_DB_DONE);
@@ -131,7 +134,7 @@ int ivpu_jsm_get_heartbeat(struct ivpu_device *vdev, u32 engine, u64 *heartbeat)
 	struct vpu_jsm_msg resp;
 	int ret;
 
-	if (engine > VPU_ENGINE_COPY)
+	if (engine != VPU_ENGINE_COMPUTE)
 		return -EINVAL;
 
 	req.payload.query_engine_hb.engine_idx = engine;
@@ -154,15 +157,17 @@ int ivpu_jsm_reset_engine(struct ivpu_device *vdev, u32 engine)
 	struct vpu_jsm_msg resp;
 	int ret;
 
-	if (engine > VPU_ENGINE_COPY)
+	if (engine != VPU_ENGINE_COMPUTE)
 		return -EINVAL;
 
 	req.payload.engine_reset.engine_idx = engine;
 
 	ret = ivpu_ipc_send_receive(vdev, &req, VPU_JSM_MSG_ENGINE_RESET_DONE, &resp,
 				    VPU_IPC_CHAN_ASYNC_CMD, vdev->timeout.jsm);
-	if (ret)
+	if (ret) {
 		ivpu_err_ratelimited(vdev, "Failed to reset engine %d: %d\n", engine, ret);
+		ivpu_pm_trigger_recovery(vdev, "Engine reset failed");
+	}
 
 	return ret;
 }
@@ -173,7 +178,7 @@ int ivpu_jsm_preempt_engine(struct ivpu_device *vdev, u32 engine, u32 preempt_id
 	struct vpu_jsm_msg resp;
 	int ret;
 
-	if (engine > VPU_ENGINE_COPY)
+	if (engine != VPU_ENGINE_COMPUTE)
 		return -EINVAL;
 
 	req.payload.engine_preempt.engine_idx = engine;
@@ -345,15 +350,17 @@ int ivpu_jsm_hws_resume_engine(struct ivpu_device *vdev, u32 engine)
 	struct vpu_jsm_msg resp;
 	int ret;
 
-	if (engine >= VPU_ENGINE_NB)
+	if (engine != VPU_ENGINE_COMPUTE)
 		return -EINVAL;
 
 	req.payload.hws_resume_engine.engine_idx = engine;
 
 	ret = ivpu_ipc_send_receive(vdev, &req, VPU_JSM_MSG_HWS_RESUME_ENGINE_DONE, &resp,
 				    VPU_IPC_CHAN_ASYNC_CMD, vdev->timeout.jsm);
-	if (ret)
+	if (ret) {
 		ivpu_err_ratelimited(vdev, "Failed to resume engine %d: %d\n", engine, ret);
+		ivpu_pm_trigger_recovery(vdev, "Engine resume failed");
+	}
 
 	return ret;
 }
@@ -408,26 +415,18 @@ int ivpu_jsm_hws_setup_priority_bands(struct ivpu_device *vdev)
 {
 	struct vpu_jsm_msg req = { .type = VPU_JSM_MSG_SET_PRIORITY_BAND_SETUP };
 	struct vpu_jsm_msg resp;
+	struct ivpu_hw_info *hw = vdev->hw;
+	struct vpu_ipc_msg_payload_hws_priority_band_setup *setup =
+		&req.payload.hws_priority_band_setup;
 	int ret;
 
-	/* Idle */
-	req.payload.hws_priority_band_setup.grace_period[0] = 0;
-	req.payload.hws_priority_band_setup.process_grace_period[0] = 50000;
-	req.payload.hws_priority_band_setup.process_quantum[0] = 160000;
-	/* Normal */
-	req.payload.hws_priority_band_setup.grace_period[1] = 50000;
-	req.payload.hws_priority_band_setup.process_grace_period[1] = 50000;
-	req.payload.hws_priority_band_setup.process_quantum[1] = 300000;
-	/* Focus */
-	req.payload.hws_priority_band_setup.grace_period[2] = 50000;
-	req.payload.hws_priority_band_setup.process_grace_period[2] = 50000;
-	req.payload.hws_priority_band_setup.process_quantum[2] = 200000;
-	/* Realtime */
-	req.payload.hws_priority_band_setup.grace_period[3] = 0;
-	req.payload.hws_priority_band_setup.process_grace_period[3] = 50000;
-	req.payload.hws_priority_band_setup.process_quantum[3] = 200000;
-
-	req.payload.hws_priority_band_setup.normal_band_percentage = 10;
+	for (int band = VPU_JOB_SCHEDULING_PRIORITY_BAND_IDLE;
+	     band < VPU_JOB_SCHEDULING_PRIORITY_BAND_COUNT; band++) {
+		setup->grace_period[band] = hw->hws.grace_period[band];
+		setup->process_grace_period[band] = hw->hws.process_grace_period[band];
+		setup->process_quantum[band] = hw->hws.process_quantum[band];
+	}
+	setup->normal_band_percentage = 10;
 
 	ret = ivpu_ipc_send_receive_internal(vdev, &req, VPU_JSM_MSG_SET_PRIORITY_BAND_SETUP_RSP,
 					     &resp, VPU_IPC_CHAN_ASYNC_CMD, vdev->timeout.jsm);
@@ -555,3 +554,11 @@ int ivpu_jsm_dct_disable(struct ivpu_device *vdev)
 	return ivpu_ipc_send_receive_internal(vdev, &req, VPU_JSM_MSG_DCT_DISABLE_DONE, &resp,
 					      VPU_IPC_CHAN_ASYNC_CMD, vdev->timeout.jsm);
 }
+
+int ivpu_jsm_state_dump(struct ivpu_device *vdev)
+{
+	struct vpu_jsm_msg req = { .type = VPU_JSM_MSG_STATE_DUMP };
+
+	return ivpu_ipc_send_and_wait(vdev, &req, VPU_IPC_CHAN_ASYNC_CMD,
+				      vdev->timeout.state_dump_msg);
+}
diff --git a/drivers/accel/ivpu/ivpu_jsm_msg.h b/drivers/accel/ivpu/ivpu_jsm_msg.h
index e4e42c0ff6e6..9e84d3526a14 100644
--- a/drivers/accel/ivpu/ivpu_jsm_msg.h
+++ b/drivers/accel/ivpu/ivpu_jsm_msg.h
@@ -43,4 +43,6 @@ int ivpu_jsm_metric_streamer_info(struct ivpu_device *vdev, u64 metric_group_mas
 				  u64 buffer_size, u32 *sample_size, u64 *info_size);
 int ivpu_jsm_dct_enable(struct ivpu_device *vdev, u32 active_us, u32 inactive_us);
 int ivpu_jsm_dct_disable(struct ivpu_device *vdev);
+int ivpu_jsm_state_dump(struct ivpu_device *vdev);
+
 #endif
diff --git a/drivers/accel/ivpu/ivpu_mmu.c b/drivers/accel/ivpu/ivpu_mmu.c
index c078e214b221..fb15eb75b5ba 100644
--- a/drivers/accel/ivpu/ivpu_mmu.c
+++ b/drivers/accel/ivpu/ivpu_mmu.c
@@ -917,8 +917,7 @@ void ivpu_mmu_irq_evtq_handler(struct ivpu_device *vdev)
 		REGV_WR32(IVPU_MMU_REG_EVTQ_CONS_SEC, vdev->mmu->evtq.cons);
 	}
 
-	if (!kfifo_put(&vdev->hw->irq.fifo, IVPU_HW_IRQ_SRC_MMU_EVTQ))
-		ivpu_err_ratelimited(vdev, "IRQ FIFO full\n");
+	queue_work(system_wq, &vdev->context_abort_work);
 }
 
 void ivpu_mmu_evtq_dump(struct ivpu_device *vdev)
diff --git a/drivers/accel/ivpu/ivpu_ms.c b/drivers/accel/ivpu/ivpu_ms.c
index 2f9d37f5c208..a961002fe25b 100644
--- a/drivers/accel/ivpu/ivpu_ms.c
+++ b/drivers/accel/ivpu/ivpu_ms.c
@@ -4,6 +4,7 @@
  */
 
 #include <drm/drm_file.h>
+#include <linux/pm_runtime.h>
 
 #include "ivpu_drv.h"
 #include "ivpu_gem.h"
@@ -44,6 +45,10 @@ int ivpu_ms_start_ioctl(struct drm_device *dev, void *data, struct drm_file *fil
 	    args->sampling_period_ns < MS_MIN_SAMPLE_PERIOD_NS)
 		return -EINVAL;
 
+	ret = ivpu_rpm_get(vdev);
+	if (ret < 0)
+		return ret;
+
 	mutex_lock(&file_priv->ms_lock);
 
 	if (get_instance_by_mask(file_priv, args->metric_group_mask)) {
@@ -96,6 +101,8 @@ err_free_ms:
 	kfree(ms);
 unlock:
 	mutex_unlock(&file_priv->ms_lock);
+
+	ivpu_rpm_put(vdev);
 	return ret;
 }
 
@@ -160,6 +167,10 @@ int ivpu_ms_get_data_ioctl(struct drm_device *dev, void *data, struct drm_file *
 	if (!args->metric_group_mask)
 		return -EINVAL;
 
+	ret = ivpu_rpm_get(vdev);
+	if (ret < 0)
+		return ret;
+
 	mutex_lock(&file_priv->ms_lock);
 
 	ms = get_instance_by_mask(file_priv, args->metric_group_mask);
@@ -187,6 +198,7 @@ int ivpu_ms_get_data_ioctl(struct drm_device *dev, void *data, struct drm_file *
 unlock:
 	mutex_unlock(&file_priv->ms_lock);
 
+	ivpu_rpm_put(vdev);
 	return ret;
 }
 
@@ -204,11 +216,17 @@ int ivpu_ms_stop_ioctl(struct drm_device *dev, void *data, struct drm_file *file
 {
 	struct ivpu_file_priv *file_priv = file->driver_priv;
 	struct drm_ivpu_metric_streamer_stop *args = data;
+	struct ivpu_device *vdev = file_priv->vdev;
 	struct ivpu_ms_instance *ms;
+	int ret;
 
 	if (!args->metric_group_mask)
 		return -EINVAL;
 
+	ret = ivpu_rpm_get(vdev);
+	if (ret < 0)
+		return ret;
+
 	mutex_lock(&file_priv->ms_lock);
 
 	ms = get_instance_by_mask(file_priv, args->metric_group_mask);
@@ -217,6 +235,7 @@ int ivpu_ms_stop_ioctl(struct drm_device *dev, void *data, struct drm_file *file
 
 	mutex_unlock(&file_priv->ms_lock);
 
+	ivpu_rpm_put(vdev);
 	return ms ? 0 : -EINVAL;
 }
 
@@ -281,6 +300,9 @@ unlock:
 void ivpu_ms_cleanup(struct ivpu_file_priv *file_priv)
 {
 	struct ivpu_ms_instance *ms, *tmp;
+	struct ivpu_device *vdev = file_priv->vdev;
+
+	pm_runtime_get_sync(vdev->drm.dev);
 
 	mutex_lock(&file_priv->ms_lock);
 
@@ -293,6 +315,8 @@ void ivpu_ms_cleanup(struct ivpu_file_priv *file_priv)
 		free_instance(file_priv, ms);
 
 	mutex_unlock(&file_priv->ms_lock);
+
+	pm_runtime_put_autosuspend(vdev->drm.dev);
 }
 
 void ivpu_ms_cleanup_all(struct ivpu_device *vdev)
diff --git a/drivers/accel/ivpu/ivpu_pm.c b/drivers/accel/ivpu/ivpu_pm.c
index 10b7ae0f866c..2269569bdee7 100644
--- a/drivers/accel/ivpu/ivpu_pm.c
+++ b/drivers/accel/ivpu/ivpu_pm.c
@@ -9,17 +9,18 @@
 #include <linux/pm_runtime.h>
 #include <linux/reboot.h>
 
-#include "vpu_boot_api.h"
+#include "ivpu_coredump.h"
 #include "ivpu_drv.h"
-#include "ivpu_hw.h"
 #include "ivpu_fw.h"
 #include "ivpu_fw_log.h"
+#include "ivpu_hw.h"
 #include "ivpu_ipc.h"
 #include "ivpu_job.h"
 #include "ivpu_jsm_msg.h"
 #include "ivpu_mmu.h"
 #include "ivpu_ms.h"
 #include "ivpu_pm.h"
+#include "vpu_boot_api.h"
 
 static bool ivpu_disable_recovery;
 module_param_named_unsafe(disable_recovery, ivpu_disable_recovery, bool, 0644);
@@ -37,6 +38,7 @@ static void ivpu_pm_prepare_cold_boot(struct ivpu_device *vdev)
 
 	ivpu_cmdq_reset_all_contexts(vdev);
 	ivpu_ipc_reset(vdev);
+	ivpu_fw_log_reset(vdev);
 	ivpu_fw_load(vdev);
 	fw->entry_point = fw->cold_boot_entry_point;
 }
@@ -73,8 +75,8 @@ static int ivpu_resume(struct ivpu_device *vdev)
 	int ret;
 
 retry:
-	pci_restore_state(to_pci_dev(vdev->drm.dev));
 	pci_set_power_state(to_pci_dev(vdev->drm.dev), PCI_D0);
+	pci_restore_state(to_pci_dev(vdev->drm.dev));
 
 	ret = ivpu_hw_power_up(vdev);
 	if (ret) {
@@ -110,40 +112,57 @@ err_power_down:
 	return ret;
 }
 
-static void ivpu_pm_recovery_work(struct work_struct *work)
+static void ivpu_pm_reset_begin(struct ivpu_device *vdev)
 {
-	struct ivpu_pm_info *pm = container_of(work, struct ivpu_pm_info, recovery_work);
-	struct ivpu_device *vdev = pm->vdev;
-	char *evt[2] = {"IVPU_PM_EVENT=IVPU_RECOVER", NULL};
-	int ret;
-
-	ivpu_err(vdev, "Recovering the NPU (reset #%d)\n", atomic_read(&vdev->pm->reset_counter));
-
-	ret = pm_runtime_resume_and_get(vdev->drm.dev);
-	if (ret)
-		ivpu_err(vdev, "Failed to resume NPU: %d\n", ret);
-
-	ivpu_fw_log_dump(vdev);
+	pm_runtime_disable(vdev->drm.dev);
 
 	atomic_inc(&vdev->pm->reset_counter);
 	atomic_set(&vdev->pm->reset_pending, 1);
 	down_write(&vdev->pm->reset_lock);
+}
+
+static void ivpu_pm_reset_complete(struct ivpu_device *vdev)
+{
+	int ret;
 
-	ivpu_suspend(vdev);
 	ivpu_pm_prepare_cold_boot(vdev);
 	ivpu_jobs_abort_all(vdev);
 	ivpu_ms_cleanup_all(vdev);
 
 	ret = ivpu_resume(vdev);
-	if (ret)
+	if (ret) {
 		ivpu_err(vdev, "Failed to resume NPU: %d\n", ret);
+		pm_runtime_set_suspended(vdev->drm.dev);
+	} else {
+		pm_runtime_set_active(vdev->drm.dev);
+	}
 
 	up_write(&vdev->pm->reset_lock);
 	atomic_set(&vdev->pm->reset_pending, 0);
 
-	kobject_uevent_env(&vdev->drm.dev->kobj, KOBJ_CHANGE, evt);
 	pm_runtime_mark_last_busy(vdev->drm.dev);
-	pm_runtime_put_autosuspend(vdev->drm.dev);
+	pm_runtime_enable(vdev->drm.dev);
+}
+
+static void ivpu_pm_recovery_work(struct work_struct *work)
+{
+	struct ivpu_pm_info *pm = container_of(work, struct ivpu_pm_info, recovery_work);
+	struct ivpu_device *vdev = pm->vdev;
+	char *evt[2] = {"IVPU_PM_EVENT=IVPU_RECOVER", NULL};
+
+	ivpu_err(vdev, "Recovering the NPU (reset #%d)\n", atomic_read(&vdev->pm->reset_counter));
+
+	ivpu_pm_reset_begin(vdev);
+
+	if (!pm_runtime_status_suspended(vdev->drm.dev)) {
+		ivpu_jsm_state_dump(vdev);
+		ivpu_dev_coredump(vdev);
+		ivpu_suspend(vdev);
+	}
+
+	ivpu_pm_reset_complete(vdev);
+
+	kobject_uevent_env(&vdev->drm.dev->kobj, KOBJ_CHANGE, evt);
 }
 
 void ivpu_pm_trigger_recovery(struct ivpu_device *vdev, const char *reason)
@@ -262,7 +281,7 @@ int ivpu_pm_runtime_suspend_cb(struct device *dev)
 	if (!is_idle || ret_d0i3) {
 		ivpu_err(vdev, "Forcing cold boot due to previous errors\n");
 		atomic_inc(&vdev->pm->reset_counter);
-		ivpu_fw_log_dump(vdev);
+		ivpu_dev_coredump(vdev);
 		ivpu_pm_prepare_cold_boot(vdev);
 	} else {
 		ivpu_pm_prepare_warm_boot(vdev);
@@ -295,7 +314,10 @@ int ivpu_rpm_get(struct ivpu_device *vdev)
 	int ret;
 
 	ret = pm_runtime_resume_and_get(vdev->drm.dev);
-	drm_WARN_ON(&vdev->drm, ret < 0);
+	if (ret < 0) {
+		ivpu_err(vdev, "Failed to resume NPU: %d\n", ret);
+		pm_runtime_set_suspended(vdev->drm.dev);
+	}
 
 	return ret;
 }
@@ -311,16 +333,13 @@ void ivpu_pm_reset_prepare_cb(struct pci_dev *pdev)
 	struct ivpu_device *vdev = pci_get_drvdata(pdev);
 
 	ivpu_dbg(vdev, PM, "Pre-reset..\n");
-	atomic_inc(&vdev->pm->reset_counter);
-	atomic_set(&vdev->pm->reset_pending, 1);
 
-	pm_runtime_get_sync(vdev->drm.dev);
-	down_write(&vdev->pm->reset_lock);
-	ivpu_prepare_for_reset(vdev);
-	ivpu_hw_reset(vdev);
-	ivpu_pm_prepare_cold_boot(vdev);
-	ivpu_jobs_abort_all(vdev);
-	ivpu_ms_cleanup_all(vdev);
+	ivpu_pm_reset_begin(vdev);
+
+	if (!pm_runtime_status_suspended(vdev->drm.dev)) {
+		ivpu_prepare_for_reset(vdev);
+		ivpu_hw_reset(vdev);
+	}
 
 	ivpu_dbg(vdev, PM, "Pre-reset done.\n");
 }
@@ -328,18 +347,12 @@ void ivpu_pm_reset_prepare_cb(struct pci_dev *pdev)
 void ivpu_pm_reset_done_cb(struct pci_dev *pdev)
 {
 	struct ivpu_device *vdev = pci_get_drvdata(pdev);
-	int ret;
 
 	ivpu_dbg(vdev, PM, "Post-reset..\n");
-	ret = ivpu_resume(vdev);
-	if (ret)
-		ivpu_err(vdev, "Failed to set RESUME state: %d\n", ret);
-	up_write(&vdev->pm->reset_lock);
-	atomic_set(&vdev->pm->reset_pending, 0);
-	ivpu_dbg(vdev, PM, "Post-reset done.\n");
 
-	pm_runtime_mark_last_busy(vdev->drm.dev);
-	pm_runtime_put_autosuspend(vdev->drm.dev);
+	ivpu_pm_reset_complete(vdev);
+
+	ivpu_dbg(vdev, PM, "Post-reset done.\n");
 }
 
 void ivpu_pm_init(struct ivpu_device *vdev)
@@ -409,16 +422,17 @@ int ivpu_pm_dct_enable(struct ivpu_device *vdev, u8 active_percent)
 	active_us = (DCT_PERIOD_US * active_percent) / 100;
 	inactive_us = DCT_PERIOD_US - active_us;
 
+	vdev->pm->dct_active_percent = active_percent;
+
+	ivpu_dbg(vdev, PM, "DCT requested %u%% (D0: %uus, D0i2: %uus)\n",
+		 active_percent, active_us, inactive_us);
+
 	ret = ivpu_jsm_dct_enable(vdev, active_us, inactive_us);
 	if (ret) {
 		ivpu_err_ratelimited(vdev, "Filed to enable DCT: %d\n", ret);
 		return ret;
 	}
 
-	vdev->pm->dct_active_percent = active_percent;
-
-	ivpu_dbg(vdev, PM, "DCT set to %u%% (D0: %uus, D0i2: %uus)\n",
-		 active_percent, active_us, inactive_us);
 	return 0;
 }
 
@@ -426,15 +440,16 @@ int ivpu_pm_dct_disable(struct ivpu_device *vdev)
 {
 	int ret;
 
+	vdev->pm->dct_active_percent = 0;
+
+	ivpu_dbg(vdev, PM, "DCT requested to be disabled\n");
+
 	ret = ivpu_jsm_dct_disable(vdev);
 	if (ret) {
 		ivpu_err_ratelimited(vdev, "Filed to disable DCT: %d\n", ret);
 		return ret;
 	}
 
-	vdev->pm->dct_active_percent = 0;
-
-	ivpu_dbg(vdev, PM, "DCT disabled\n");
 	return 0;
 }
 
@@ -446,7 +461,7 @@ void ivpu_pm_dct_irq_thread_handler(struct ivpu_device *vdev)
 	if (ivpu_hw_btrs_dct_get_request(vdev, &enable))
 		return;
 
-	if (vdev->pm->dct_active_percent)
+	if (enable)
 		ret = ivpu_pm_dct_enable(vdev, DCT_DEFAULT_ACTIVE_PERCENT);
 	else
 		ret = ivpu_pm_dct_disable(vdev);
diff --git a/drivers/accel/ivpu/ivpu_sysfs.c b/drivers/accel/ivpu/ivpu_sysfs.c
index 913669f1786e..8a616791c32f 100644
--- a/drivers/accel/ivpu/ivpu_sysfs.c
+++ b/drivers/accel/ivpu/ivpu_sysfs.c
@@ -6,6 +6,8 @@
 #include <linux/device.h>
 #include <linux/err.h>
 
+#include "ivpu_drv.h"
+#include "ivpu_fw.h"
 #include "ivpu_hw.h"
 #include "ivpu_sysfs.h"
 
@@ -28,19 +30,42 @@ npu_busy_time_us_show(struct device *dev, struct device_attribute *attr, char *b
 	struct ivpu_device *vdev = to_ivpu_device(drm);
 	ktime_t total, now = 0;
 
-	xa_lock(&vdev->submitted_jobs_xa);
+	mutex_lock(&vdev->submitted_jobs_lock);
+
 	total = vdev->busy_time;
 	if (!xa_empty(&vdev->submitted_jobs_xa))
 		now = ktime_sub(ktime_get(), vdev->busy_start_ts);
-	xa_unlock(&vdev->submitted_jobs_xa);
+	mutex_unlock(&vdev->submitted_jobs_lock);
 
 	return sysfs_emit(buf, "%lld\n", ktime_to_us(ktime_add(total, now)));
 }
 
 static DEVICE_ATTR_RO(npu_busy_time_us);
 
+/**
+ * DOC: sched_mode
+ *
+ * The sched_mode is used to report current NPU scheduling mode.
+ *
+ * It returns following strings:
+ * - "HW"		- Hardware Scheduler mode
+ * - "OS"		- Operating System Scheduler mode
+ *
+ */
+static ssize_t
+sched_mode_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct drm_device *drm = dev_get_drvdata(dev);
+	struct ivpu_device *vdev = to_ivpu_device(drm);
+
+	return sysfs_emit(buf, "%s\n", vdev->fw->sched_mode ? "HW" : "OS");
+}
+
+static DEVICE_ATTR_RO(sched_mode);
+
 static struct attribute *ivpu_dev_attrs[] = {
 	&dev_attr_npu_busy_time_us.attr,
+	&dev_attr_sched_mode.attr,
 	NULL,
 };
 
diff --git a/drivers/accel/ivpu/vpu_boot_api.h b/drivers/accel/ivpu/vpu_boot_api.h
index 82954b91b748..908e68ea1c39 100644
--- a/drivers/accel/ivpu/vpu_boot_api.h
+++ b/drivers/accel/ivpu/vpu_boot_api.h
@@ -1,14 +1,13 @@
 /* SPDX-License-Identifier: MIT */
 /*
- * Copyright (c) 2020-2023, Intel Corporation.
+ * Copyright (c) 2020-2024, Intel Corporation.
  */
 
 #ifndef VPU_BOOT_API_H
 #define VPU_BOOT_API_H
 
 /*
- * =========== FW API version information beginning ================
- *  The bellow values will be used to construct the version info this way:
+ *  The below values will be used to construct the version info this way:
  *  fw_bin_header->api_version[VPU_BOOT_API_VER_ID] = (VPU_BOOT_API_VER_MAJOR << 16) |
  *  VPU_BOOT_API_VER_MINOR;
  *  VPU_BOOT_API_VER_PATCH will be ignored. KMD and compatibility is not affected if this changes
@@ -27,19 +26,18 @@
  * Minor version changes when API backward compatibility is preserved.
  * Resets to 0 if Major version is incremented.
  */
-#define VPU_BOOT_API_VER_MINOR 24
+#define VPU_BOOT_API_VER_MINOR 26
 
 /*
  * API header changed (field names, documentation, formatting) but API itself has not been changed
  */
-#define VPU_BOOT_API_VER_PATCH 0
+#define VPU_BOOT_API_VER_PATCH 3
 
 /*
  * Index in the API version table
  * Must be unique for each API
  */
 #define VPU_BOOT_API_VER_INDEX 0
-/* ------------ FW API version information end ---------------------*/
 
 #pragma pack(push, 4)
 
@@ -164,8 +162,6 @@ enum vpu_trace_destination {
 /* VPU 30xx HW component IDs are sequential, so define first and last IDs. */
 #define VPU_TRACE_PROC_BIT_30XX_FIRST VPU_TRACE_PROC_BIT_LRT
 #define VPU_TRACE_PROC_BIT_30XX_LAST  VPU_TRACE_PROC_BIT_SHV_15
-#define VPU_TRACE_PROC_BIT_KMB_FIRST  VPU_TRACE_PROC_BIT_30XX_FIRST
-#define VPU_TRACE_PROC_BIT_KMB_LAST   VPU_TRACE_PROC_BIT_30XX_LAST
 
 struct vpu_boot_l2_cache_config {
 	u8 use;
@@ -199,6 +195,17 @@ struct vpu_warm_boot_section {
  */
 #define POWER_PROFILE_SURVIVABILITY 0x1
 
+/**
+ * Enum for dvfs_mode boot param.
+ */
+enum vpu_governor {
+	VPU_GOV_DEFAULT = 0, /* Default Governor for the system */
+	VPU_GOV_MAX_PERFORMANCE = 1, /* Maximum performance governor */
+	VPU_GOV_ON_DEMAND = 2, /* On Demand frequency control governor */
+	VPU_GOV_POWER_SAVE = 3, /* Power save governor */
+	VPU_GOV_ON_DEMAND_PRIORITY_AWARE = 4 /* On Demand priority based governor */
+};
+
 struct vpu_boot_params {
 	u32 magic;
 	u32 vpu_id;
@@ -301,7 +308,14 @@ struct vpu_boot_params {
 	u32 temp_sensor_period_ms;
 	/** PLL ratio for efficient clock frequency */
 	u32 pn_freq_pll_ratio;
-	/** DVFS Mode: Default: 0, Max Performance: 1, On Demand: 2, Power Save: 3 */
+	/**
+	 * DVFS Mode:
+	 * 0 - Default, DVFS mode selected by the firmware
+	 * 1 - Max Performance
+	 * 2 - On Demand
+	 * 3 - Power Save
+	 * 4 - On Demand Priority Aware
+	 */
 	u32 dvfs_mode;
 	/**
 	 * Depending on DVFS Mode:
@@ -332,8 +346,8 @@ struct vpu_boot_params {
 	u64 d0i3_entry_vpu_ts;
 	/*
 	 * The system time of the host operating system in microseconds.
-	 * E.g the number of microseconds since 1st of January 1970, or whatever date the
-	 * host operating system uses to maintain system time.
+	 * E.g the number of microseconds since 1st of January 1970, or whatever
+	 * date the host operating system uses to maintain system time.
 	 * This value will be used to track system time on the VPU.
 	 * The KMD is required to update this value on every VPU reset.
 	 */
@@ -382,10 +396,7 @@ struct vpu_boot_params {
 	u32 pad6[734];
 };
 
-/*
- * Magic numbers set between host and vpu to detect corruptio of tracing init
- */
-
+/* Magic numbers set between host and vpu to detect corruption of tracing init */
 #define VPU_TRACING_BUFFER_CANARY (0xCAFECAFE)
 
 /* Tracing buffer message format definitions */
@@ -405,7 +416,9 @@ struct vpu_tracing_buffer_header {
 	u32 host_canary_start;
 	/* offset from start of buffer for trace entries */
 	u32 read_index;
-	u32 pad_to_cache_line_size_0[14];
+	/* keeps track of wrapping on the reader side */
+	u32 read_wrap_count;
+	u32 pad_to_cache_line_size_0[13];
 	/* End of first cache line */
 
 	/**
diff --git a/drivers/accel/ivpu/vpu_jsm_api.h b/drivers/accel/ivpu/vpu_jsm_api.h
index 33f462b1a25d..7215c144158c 100644
--- a/drivers/accel/ivpu/vpu_jsm_api.h
+++ b/drivers/accel/ivpu/vpu_jsm_api.h
@@ -22,7 +22,7 @@
 /*
  * Minor version changes when API backward compatibility is preserved.
  */
-#define VPU_JSM_API_VER_MINOR 16
+#define VPU_JSM_API_VER_MINOR 25
 
 /*
  * API header changed (field names, documentation, formatting) but API itself has not been changed
@@ -36,7 +36,7 @@
 
 /*
  * Number of Priority Bands for Hardware Scheduling
- * Bands: RealTime, Focus, Normal, Idle
+ * Bands: Idle(0), Normal(1), Focus(2), RealTime(3)
  */
 #define VPU_HWS_NUM_PRIORITY_BANDS 4
 
@@ -74,6 +74,7 @@
 #define VPU_JSM_STATUS_MVNCI_INTERNAL_ERROR		 0xCU
 /* Job status returned when the job was preempted mid-inference */
 #define VPU_JSM_STATUS_PREEMPTED_MID_INFERENCE		 0xDU
+#define VPU_JSM_STATUS_MVNCI_CONTEXT_VIOLATION_HW	 0xEU
 
 /*
  * Host <-> VPU IPC channels.
@@ -86,18 +87,58 @@
 /*
  * Job flags bit masks.
  */
-#define VPU_JOB_FLAGS_NULL_SUBMISSION_MASK 0x00000001
-#define VPU_JOB_FLAGS_PRIVATE_DATA_MASK	   0xFF000000
+enum {
+	/*
+	 * Null submission mask.
+	 * When set, batch buffer's commands are not processed but returned as
+	 * successful immediately, except fences and timestamps.
+	 * When cleared, batch buffer's commands are processed normally.
+	 * Used for testing and profiling purposes.
+	 */
+	VPU_JOB_FLAGS_NULL_SUBMISSION_MASK = (1 << 0U),
+	/*
+	 * Inline command mask.
+	 * When set, the object in job queue is an inline command (see struct vpu_inline_cmd below).
+	 * When cleared, the object in job queue is a job (see struct vpu_job_queue_entry below).
+	 */
+	VPU_JOB_FLAGS_INLINE_CMD_MASK = (1 << 1U),
+	/*
+	 * VPU private data mask.
+	 * Reserved for the VPU to store private data about the job (or inline command)
+	 * while being processed.
+	 */
+	VPU_JOB_FLAGS_PRIVATE_DATA_MASK = 0xFFFF0000U
+};
 
 /*
- * Sizes of the reserved areas in jobs, in bytes.
+ * Job queue flags bit masks.
  */
-#define VPU_JOB_RESERVED_BYTES 8
+enum {
+	/*
+	 * No job done notification mask.
+	 * When set, indicates that no job done notification should be sent for any
+	 * job from this queue. When cleared, indicates that job done notification
+	 * should be sent for every job completed from this queue.
+	 */
+	VPU_JOB_QUEUE_FLAGS_NO_JOB_DONE_MASK = (1 << 0U),
+	/*
+	 * Native fence usage mask.
+	 * When set, indicates that job queue uses native fences (as inline commands
+	 * in job queue). Such queues may also use legacy fences (as commands in batch buffers).
+	 * When cleared, indicates the job queue only uses legacy fences.
+	 * NOTE: For queues using native fences, VPU expects that all jobs in the queue
+	 * are immediately followed by an inline command object. This object is expected
+	 * to be a fence signal command in most cases, but can also be a NOP in case the host
+	 * does not need per-job fence signalling. Other inline commands objects can be
+	 * inserted between "job and inline command" pairs.
+	 */
+	VPU_JOB_QUEUE_FLAGS_USE_NATIVE_FENCE_MASK = (1 << 1U),
 
-/*
- * Sizes of the reserved areas in job queues, in bytes.
- */
-#define VPU_JOB_QUEUE_RESERVED_BYTES 52
+	/*
+	 * Enable turbo mode for testing NPU performance; not recommended for regular usage.
+	 */
+	VPU_JOB_QUEUE_FLAGS_TURBO_MODE = (1 << 2U)
+};
 
 /*
  * Max length (including trailing NULL char) of trace entity name (e.g., the
@@ -141,23 +182,112 @@
 #define VPU_HWS_INVALID_CMDQ_HANDLE 0ULL
 
 /*
+ * Inline commands types.
+ */
+/*
+ * NOP.
+ * VPU does nothing other than consuming the inline command object.
+ */
+#define VPU_INLINE_CMD_TYPE_NOP		 0x0
+/*
+ * Fence wait.
+ * VPU waits for the fence current value to reach monitored value.
+ * Fence wait operations are executed upon job dispatching. While waiting for
+ * the fence to be satisfied, VPU blocks fetching of the next objects in the queue.
+ * Jobs present in the queue prior to the fence wait object may be processed
+ * concurrently.
+ */
+#define VPU_INLINE_CMD_TYPE_FENCE_WAIT	 0x1
+/*
+ * Fence signal.
+ * VPU sets the fence current value to the provided value. If new current value
+ * is equal to or higher than monitored value, VPU sends fence signalled notification
+ * to the host. Fence signal operations are executed upon completion of all the jobs
+ * present in the queue prior to them, and in-order relative to each other in the queue.
+ * But jobs in-between them may be processed concurrently and may complete out-of-order.
+ */
+#define VPU_INLINE_CMD_TYPE_FENCE_SIGNAL 0x2
+
+/*
+ * Job scheduling priority bands for both hardware scheduling and OS scheduling.
+ */
+enum vpu_job_scheduling_priority_band {
+	VPU_JOB_SCHEDULING_PRIORITY_BAND_IDLE = 0,
+	VPU_JOB_SCHEDULING_PRIORITY_BAND_NORMAL = 1,
+	VPU_JOB_SCHEDULING_PRIORITY_BAND_FOCUS = 2,
+	VPU_JOB_SCHEDULING_PRIORITY_BAND_REALTIME = 3,
+	VPU_JOB_SCHEDULING_PRIORITY_BAND_COUNT = 4,
+};
+
+/*
  * Job format.
+ * Jobs defines the actual workloads to be executed by a given engine.
  */
 struct vpu_job_queue_entry {
-	u64 batch_buf_addr; /**< Address of VPU commands batch buffer */
-	u32 job_id;	  /**< Job ID */
-	u32 flags; /**< Flags bit field, see VPU_JOB_FLAGS_* above */
-	u64 root_page_table_addr; /**< Address of root page table to use for this job */
-	u64 root_page_table_update_counter; /**< Page tables update events counter */
-	u64 primary_preempt_buf_addr;
+	/**< Address of VPU commands batch buffer */
+	u64 batch_buf_addr;
+	/**< Job ID */
+	u32 job_id;
+	/**< Flags bit field, see VPU_JOB_FLAGS_* above */
+	u32 flags;
+	/**
+	 * Doorbell ring timestamp taken by KMD from SoC's global system clock, in
+	 * microseconds. NPU can convert this value to its own fixed clock's timebase,
+	 * to match other profiling timestamps.
+	 */
+	u64 doorbell_timestamp;
+	/**< Extra id for job tracking, used only in the firmware perf traces */
+	u64 host_tracking_id;
 	/**< Address of the primary preemption buffer to use for this job */
-	u32 primary_preempt_buf_size;
+	u64 primary_preempt_buf_addr;
 	/**< Size of the primary preemption buffer to use for this job */
-	u32 secondary_preempt_buf_size;
+	u32 primary_preempt_buf_size;
 	/**< Size of secondary preemption buffer to use for this job */
-	u64 secondary_preempt_buf_addr;
+	u32 secondary_preempt_buf_size;
 	/**< Address of secondary preemption buffer to use for this job */
-	u8 reserved_0[VPU_JOB_RESERVED_BYTES];
+	u64 secondary_preempt_buf_addr;
+	u64 reserved_0;
+};
+
+/*
+ * Inline command format.
+ * Inline commands are the commands executed at scheduler level (typically,
+ * synchronization directives). Inline command and job objects must be of
+ * the same size and have flags field at same offset.
+ */
+struct vpu_inline_cmd {
+	u64 reserved_0;
+	/* Inline command type, see VPU_INLINE_CMD_TYPE_* defines. */
+	u32 type;
+	/* Flags bit field, see VPU_JOB_FLAGS_* above. */
+	u32 flags;
+	/* Inline command payload. Depends on inline command type. */
+	union {
+		/* Fence (wait and signal) commands' payload. */
+		struct {
+			/* Fence object handle. */
+			u64 fence_handle;
+			/* User VA of the current fence value. */
+			u64 current_value_va;
+			/* User VA of the monitored fence value (read-only). */
+			u64 monitored_value_va;
+			/* Value to wait for or write in fence location. */
+			u64 value;
+			/* User VA of the log buffer in which to add log entry on completion. */
+			u64 log_buffer_va;
+		} fence;
+		/* Other commands do not have a payload. */
+		/* Payload definition for future inline commands can be inserted here. */
+		u64 reserved_1[6];
+	} payload;
+};
+
+/*
+ * Job queue slots can be populated either with job objects or inline command objects.
+ */
+union vpu_jobq_slot {
+	struct vpu_job_queue_entry job;
+	struct vpu_inline_cmd inline_cmd;
 };
 
 /*
@@ -167,7 +297,21 @@ struct vpu_job_queue_header {
 	u32 engine_idx;
 	u32 head;
 	u32 tail;
-	u8 reserved_0[VPU_JOB_QUEUE_RESERVED_BYTES];
+	u32 flags;
+	/* Set to 1 to indicate priority_band field is valid */
+	u32 priority_band_valid;
+	/*
+	 * Priority for the work of this job queue, valid only if the HWS is NOT used
+	 * and the `priority_band_valid` is set to 1. It is applied only during
+	 * the VPU_JSM_MSG_REGISTER_DB message processing.
+	 * The device firmware might use the `priority_band` to optimize the power
+	 * management logic, but it will not affect the order of jobs.
+	 * Available priority bands: @see enum vpu_job_scheduling_priority_band
+	 */
+	u32 priority_band;
+	/* Inside realtime band assigns a further priority, limited to 0..31 range */
+	u32 realtime_priority_level;
+	u32 reserved_0[9];
 };
 
 /*
@@ -175,7 +319,7 @@ struct vpu_job_queue_header {
  */
 struct vpu_job_queue {
 	struct vpu_job_queue_header header;
-	struct vpu_job_queue_entry job[];
+	union vpu_jobq_slot slot[];
 };
 
 /**
@@ -197,9 +341,7 @@ enum vpu_trace_entity_type {
 struct vpu_hws_log_buffer_header {
 	/* Written by VPU after adding a log entry. Initialised by host to 0. */
 	u32 first_free_entry_index;
-	/* Incremented by VPU every time the VPU overwrites the 0th entry;
-	 * initialised by host to 0.
-	 */
+	/* Incremented by VPU every time the VPU writes the 0th entry; initialised by host to 0. */
 	u32 wraparound_count;
 	/*
 	 * This is the number of buffers that can be stored in the log buffer provided by the host.
@@ -230,14 +372,80 @@ struct vpu_hws_log_buffer_entry {
 	u64 operation_data[2];
 };
 
+/* Native fence log buffer types. */
+enum vpu_hws_native_fence_log_type {
+	VPU_HWS_NATIVE_FENCE_LOG_TYPE_WAITS = 1,
+	VPU_HWS_NATIVE_FENCE_LOG_TYPE_SIGNALS = 2
+};
+
+/* HWS native fence log buffer header. */
+struct vpu_hws_native_fence_log_header {
+	union {
+		struct {
+			/* Index of the first free entry in buffer. */
+			u32 first_free_entry_idx;
+			/* Incremented each time NPU wraps around the buffer to write next entry. */
+			u32 wraparound_count;
+		};
+		/* Field allowing atomic update of both fields above. */
+		u64 atomic_wraparound_and_entry_idx;
+	};
+	/* Log buffer type, see enum vpu_hws_native_fence_log_type. */
+	u64 type;
+	/* Allocated number of entries in the log buffer. */
+	u64 entry_nb;
+	u64 reserved[2];
+};
+
+/* Native fence log operation types. */
+enum vpu_hws_native_fence_log_op {
+	VPU_HWS_NATIVE_FENCE_LOG_OP_SIGNAL_EXECUTED = 0,
+	VPU_HWS_NATIVE_FENCE_LOG_OP_WAIT_UNBLOCKED = 1
+};
+
+/* HWS native fence log entry. */
+struct vpu_hws_native_fence_log_entry {
+	/* Newly signaled/unblocked fence value. */
+	u64 fence_value;
+	/* Native fence object handle to which this operation belongs. */
+	u64 fence_handle;
+	/* Operation type, see enum vpu_hws_native_fence_log_op. */
+	u64 op_type;
+	u64 reserved_0;
+	/*
+	 * VPU_HWS_NATIVE_FENCE_LOG_OP_WAIT_UNBLOCKED only: Timestamp at which fence
+	 * wait was started (in NPU SysTime).
+	 */
+	u64 fence_wait_start_ts;
+	u64 reserved_1;
+	/* Timestamp at which fence operation was completed (in NPU SysTime). */
+	u64 fence_end_ts;
+};
+
+/* Native fence log buffer. */
+struct vpu_hws_native_fence_log_buffer {
+	struct vpu_hws_native_fence_log_header header;
+	struct vpu_hws_native_fence_log_entry entry[];
+};
+
 /*
  * Host <-> VPU IPC messages types.
  */
 enum vpu_ipc_msg_type {
 	VPU_JSM_MSG_UNKNOWN = 0xFFFFFFFF,
+
 	/* IPC Host -> Device, Async commands */
 	VPU_JSM_MSG_ASYNC_CMD = 0x1100,
 	VPU_JSM_MSG_ENGINE_RESET = VPU_JSM_MSG_ASYNC_CMD,
+	/**
+	 * Preempt engine. The NPU stops (preempts) all the jobs currently
+	 * executing on the target engine making the engine become idle and ready to
+	 * execute new jobs.
+	 * NOTE: The NPU does not remove unstarted jobs (if any) from job queues of
+	 * the target engine, but it stops processing them (until the queue doorbell
+	 * is rung again); the host is responsible to reset the job queue, either
+	 * after preemption or when resubmitting jobs to the queue.
+	 */
 	VPU_JSM_MSG_ENGINE_PREEMPT = 0x1101,
 	VPU_JSM_MSG_REGISTER_DB = 0x1102,
 	VPU_JSM_MSG_UNREGISTER_DB = 0x1103,
@@ -323,9 +531,10 @@ enum vpu_ipc_msg_type {
 	 * NOTE: Please introduce new ASYNC commands before this one. *
 	 */
 	VPU_JSM_MSG_STATE_DUMP = 0x11FF,
+
 	/* IPC Host -> Device, General commands */
 	VPU_JSM_MSG_GENERAL_CMD = 0x1200,
-	VPU_JSM_MSG_BLOB_DEINIT = VPU_JSM_MSG_GENERAL_CMD,
+	VPU_JSM_MSG_BLOB_DEINIT_DEPRECATED = VPU_JSM_MSG_GENERAL_CMD,
 	/**
 	 * Control dyndbg behavior by executing a dyndbg command; equivalent to
 	 * Linux command: `echo '<dyndbg_cmd>' > <debugfs>/dynamic_debug/control`.
@@ -335,8 +544,12 @@ enum vpu_ipc_msg_type {
 	 * Perform the save procedure for the D0i3 entry
 	 */
 	VPU_JSM_MSG_PWR_D0I3_ENTER = 0x1202,
+
 	/* IPC Device -> Host, Job completion */
 	VPU_JSM_MSG_JOB_DONE = 0x2100,
+	/* IPC Device -> Host, Fence signalled */
+	VPU_JSM_MSG_NATIVE_FENCE_SIGNALLED = 0x2101,
+
 	/* IPC Device -> Host, Async command completion */
 	VPU_JSM_MSG_ASYNC_CMD_DONE = 0x2200,
 	VPU_JSM_MSG_ENGINE_RESET_DONE = VPU_JSM_MSG_ASYNC_CMD_DONE,
@@ -422,6 +635,7 @@ enum vpu_ipc_msg_type {
 	 * NOTE: Please introduce new ASYNC responses before this one. *
 	 */
 	VPU_JSM_MSG_STATE_DUMP_RSP = 0x22FF,
+
 	/* IPC Device -> Host, General command completion */
 	VPU_JSM_MSG_GENERAL_CMD_DONE = 0x2300,
 	VPU_JSM_MSG_BLOB_DEINIT_DONE = VPU_JSM_MSG_GENERAL_CMD_DONE,
@@ -600,11 +814,6 @@ struct vpu_jsm_metric_streamer_update {
 	u64 next_buffer_size;
 };
 
-struct vpu_ipc_msg_payload_blob_deinit {
-	/* 64-bit unique ID for the blob to be de-initialized. */
-	u64 blob_id;
-};
-
 struct vpu_ipc_msg_payload_job_done {
 	/* Engine to which the job was submitted. */
 	u32 engine_idx;
@@ -622,6 +831,21 @@ struct vpu_ipc_msg_payload_job_done {
 	u64 cmdq_id;
 };
 
+/*
+ * Notification message upon native fence signalling.
+ * @see VPU_JSM_MSG_NATIVE_FENCE_SIGNALLED
+ */
+struct vpu_ipc_msg_payload_native_fence_signalled {
+	/* Engine ID. */
+	u32 engine_idx;
+	/* Host SSID. */
+	u32 host_ssid;
+	/* CMDQ ID */
+	u64 cmdq_id;
+	/* Fence object handle. */
+	u64 fence_handle;
+};
+
 struct vpu_jsm_engine_reset_context {
 	/* Host SSID */
 	u32 host_ssid;
@@ -700,11 +924,6 @@ struct vpu_ipc_msg_payload_get_power_level_count_done {
 	u8 power_limit[16];
 };
 
-struct vpu_ipc_msg_payload_blob_deinit_done {
-	/* 64-bit unique ID for the blob de-initialized. */
-	u64 blob_id;
-};
-
 /* HWS priority band setup request / response */
 struct vpu_ipc_msg_payload_hws_priority_band_setup {
 	/*
@@ -794,7 +1013,10 @@ struct vpu_ipc_msg_payload_hws_set_context_sched_properties {
 	u32 reserved_0;
 	/* Command queue id */
 	u64 cmdq_id;
-	/* Priority band to assign to work of this context */
+	/*
+	 * Priority band to assign to work of this context.
+	 * Available priority bands: @see enum vpu_job_scheduling_priority_band
+	 */
 	u32 priority_band;
 	/* Inside realtime band assigns a further priority */
 	u32 realtime_priority_level;
@@ -869,9 +1091,7 @@ struct vpu_ipc_msg_payload_hws_set_scheduling_log {
 	 */
 	u64 notify_index;
 	/*
-	 * Enable extra events to be output to log for debug of scheduling algorithm.
-	 * Interpreted by VPU as a boolean to enable or disable, expected values are
-	 * 0 and 1.
+	 * Field is now deprecated, will be removed when KMD is updated to support removal
 	 */
 	u32 enable_extra_events;
 	/* Zero Padding */
@@ -1243,10 +1463,10 @@ union vpu_ipc_msg_payload {
 	struct vpu_jsm_metric_streamer_start metric_streamer_start;
 	struct vpu_jsm_metric_streamer_stop metric_streamer_stop;
 	struct vpu_jsm_metric_streamer_update metric_streamer_update;
-	struct vpu_ipc_msg_payload_blob_deinit blob_deinit;
 	struct vpu_ipc_msg_payload_ssid_release ssid_release;
 	struct vpu_jsm_hws_register_db hws_register_db;
 	struct vpu_ipc_msg_payload_job_done job_done;
+	struct vpu_ipc_msg_payload_native_fence_signalled native_fence_signalled;
 	struct vpu_ipc_msg_payload_engine_reset_done engine_reset_done;
 	struct vpu_ipc_msg_payload_engine_preempt_done engine_preempt_done;
 	struct vpu_ipc_msg_payload_register_db_done register_db_done;
@@ -1254,7 +1474,6 @@ union vpu_ipc_msg_payload {
 	struct vpu_ipc_msg_payload_query_engine_hb_done query_engine_hb_done;
 	struct vpu_ipc_msg_payload_get_power_level_count_done get_power_level_count_done;
 	struct vpu_jsm_metric_streamer_done metric_streamer_done;
-	struct vpu_ipc_msg_payload_blob_deinit_done blob_deinit_done;
 	struct vpu_ipc_msg_payload_trace_config trace_config;
 	struct vpu_ipc_msg_payload_trace_capability_rsp trace_capability;
 	struct vpu_ipc_msg_payload_trace_get_name trace_get_name;
diff --git a/drivers/accel/qaic/qaic_data.c b/drivers/accel/qaic/qaic_data.c
index c20eb63750f5..43aba57b48f0 100644
--- a/drivers/accel/qaic/qaic_data.c
+++ b/drivers/accel/qaic/qaic_data.c
@@ -172,9 +172,10 @@ static void free_slice(struct kref *kref)
 static int clone_range_of_sgt_for_slice(struct qaic_device *qdev, struct sg_table **sgt_out,
 					struct sg_table *sgt_in, u64 size, u64 offset)
 {
-	int total_len, len, nents, offf = 0, offl = 0;
 	struct scatterlist *sg, *sgn, *sgf, *sgl;
+	unsigned int len, nents, offf, offl;
 	struct sg_table *sgt;
+	size_t total_len;
 	int ret, j;
 
 	/* find out number of relevant nents needed for this mem */
@@ -182,6 +183,8 @@ static int clone_range_of_sgt_for_slice(struct qaic_device *qdev, struct sg_tabl
 	sgf = NULL;
 	sgl = NULL;
 	nents = 0;
+	offf = 0;
+	offl = 0;
 
 	size = size ? size : PAGE_SIZE;
 	for_each_sgtable_dma_sg(sgt_in, sg, j) {
@@ -554,6 +557,7 @@ static bool invalid_sem(struct qaic_sem *sem)
 static int qaic_validate_req(struct qaic_device *qdev, struct qaic_attach_slice_entry *slice_ent,
 			     u32 count, u64 total_size)
 {
+	u64 total;
 	int i;
 
 	for (i = 0; i < count; i++) {
@@ -563,7 +567,8 @@ static int qaic_validate_req(struct qaic_device *qdev, struct qaic_attach_slice_
 		      invalid_sem(&slice_ent[i].sem2) || invalid_sem(&slice_ent[i].sem3))
 			return -EINVAL;
 
-		if (slice_ent[i].offset + slice_ent[i].size > total_size)
+		if (check_add_overflow(slice_ent[i].offset, slice_ent[i].size, &total) ||
+		    total > total_size)
 			return -EINVAL;
 	}
 
diff --git a/drivers/accel/qaic/qaic_drv.c b/drivers/accel/qaic/qaic_drv.c
index f139c564eadf..10e711c96a67 100644
--- a/drivers/accel/qaic/qaic_drv.c
+++ b/drivers/accel/qaic/qaic_drv.c
@@ -432,7 +432,7 @@ static int init_pci(struct qaic_device *qdev, struct pci_dev *pdev)
 	int bars;
 	int ret;
 
-	bars = pci_select_bars(pdev, IORESOURCE_MEM);
+	bars = pci_select_bars(pdev, IORESOURCE_MEM) & 0x3f;
 
 	/* make sure the device has the expected BARs */
 	if (bars != (BIT(0) | BIT(2) | BIT(4))) {
diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index d67f63d93b2a..89fa569d6370 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -443,7 +443,7 @@ config ACPI_SBS
 	  the modules will be called sbs and sbshc.
 
 config ACPI_HED
-	tristate "Hardware Error Device"
+	bool "Hardware Error Device"
 	help
 	  This driver supports the Hardware Error Device (PNP0C33),
 	  which is used to report some hardware errors notified via
diff --git a/drivers/acpi/acpi_pnp.c b/drivers/acpi/acpi_pnp.c
index 01abf26764b0..3f5a1840f573 100644
--- a/drivers/acpi/acpi_pnp.c
+++ b/drivers/acpi/acpi_pnp.c
@@ -355,8 +355,10 @@ static bool acpi_pnp_match(const char *idstr, const struct acpi_device_id **matc
  * device represented by it.
  */
 static const struct acpi_device_id acpi_nonpnp_device_ids[] = {
+	{"INT3F0D"},
 	{"INTC1080"},
 	{"INTC1081"},
+	{"INTC1099"},
 	{""},
 };
 
diff --git a/drivers/acpi/acpi_processor.c b/drivers/acpi/acpi_processor.c
index 7cf6101cb4c7..2a99f5eb6962 100644
--- a/drivers/acpi/acpi_processor.c
+++ b/drivers/acpi/acpi_processor.c
@@ -275,7 +275,7 @@ static inline int acpi_processor_hotadd_init(struct acpi_processor *pr,
 
 static int acpi_processor_get_info(struct acpi_device *device)
 {
-	union acpi_object object = { 0 };
+	union acpi_object object = { .processor = { 0 } };
 	struct acpi_buffer buffer = { sizeof(union acpi_object), &object };
 	struct acpi_processor *pr = acpi_driver_data(device);
 	int device_declaration = 0;
diff --git a/drivers/acpi/acpica/achware.h b/drivers/acpi/acpica/achware.h
index 79bbfe00d241..b8543a34caea 100644
--- a/drivers/acpi/acpica/achware.h
+++ b/drivers/acpi/acpica/achware.h
@@ -103,8 +103,6 @@ acpi_hw_get_gpe_status(struct acpi_gpe_event_info *gpe_event_info,
 
 acpi_status acpi_hw_enable_all_runtime_gpes(void);
 
-acpi_status acpi_hw_enable_all_wakeup_gpes(void);
-
 u8 acpi_hw_check_all_gpes(acpi_handle gpe_skip_device, u32 gpe_skip_number);
 
 acpi_status
diff --git a/drivers/acpi/acpica/amlresrc.h b/drivers/acpi/acpica/amlresrc.h
index 4e88f9fc2a28..b6588b7fa898 100644
--- a/drivers/acpi/acpica/amlresrc.h
+++ b/drivers/acpi/acpica/amlresrc.h
@@ -504,10 +504,6 @@ struct aml_resource_pin_group_config {
 
 #define AML_RESOURCE_PIN_GROUP_CONFIG_REVISION    1	/* ACPI 6.2 */
 
-/* restore default alignment */
-
-#pragma pack()
-
 /* Union of all resource descriptors, so we can allocate the worst case */
 
 union aml_resource {
@@ -562,6 +558,10 @@ union aml_resource {
 	u8 byte_item;
 };
 
+/* restore default alignment */
+
+#pragma pack()
+
 /* Interfaces used by both the disassembler and compiler */
 
 void
diff --git a/drivers/acpi/acpica/dsmethod.c b/drivers/acpi/acpica/dsmethod.c
index e809c2aed78a..a232746d150a 100644
--- a/drivers/acpi/acpica/dsmethod.c
+++ b/drivers/acpi/acpica/dsmethod.c
@@ -483,6 +483,13 @@ acpi_ds_call_control_method(struct acpi_thread_state *thread,
 		return_ACPI_STATUS(AE_NULL_OBJECT);
 	}
 
+	if (this_walk_state->num_operands < obj_desc->method.param_count) {
+		ACPI_ERROR((AE_INFO, "Missing argument for method [%4.4s]",
+			    acpi_ut_get_node_name(method_node)));
+
+		return_ACPI_STATUS(AE_AML_UNINITIALIZED_ARG);
+	}
+
 	/* Init for new method, possibly wait on method mutex */
 
 	status =
diff --git a/drivers/acpi/acpica/dsutils.c b/drivers/acpi/acpica/dsutils.c
index fb9ed5e1da89..2bdae8a25e08 100644
--- a/drivers/acpi/acpica/dsutils.c
+++ b/drivers/acpi/acpica/dsutils.c
@@ -668,6 +668,8 @@ acpi_ds_create_operands(struct acpi_walk_state *walk_state,
 	union acpi_parse_object *arguments[ACPI_OBJ_NUM_OPERANDS];
 	u32 arg_count = 0;
 	u32 index = walk_state->num_operands;
+	u32 prev_num_operands = walk_state->num_operands;
+	u32 new_num_operands;
 	u32 i;
 
 	ACPI_FUNCTION_TRACE_PTR(ds_create_operands, first_arg);
@@ -696,6 +698,7 @@ acpi_ds_create_operands(struct acpi_walk_state *walk_state,
 
 	/* Create the interpreter arguments, in reverse order */
 
+	new_num_operands = index;
 	index--;
 	for (i = 0; i < arg_count; i++) {
 		arg = arguments[index];
@@ -720,7 +723,11 @@ cleanup:
 	 * pop everything off of the operand stack and delete those
 	 * objects
 	 */
-	acpi_ds_obj_stack_pop_and_delete(arg_count, walk_state);
+	walk_state->num_operands = i;
+	acpi_ds_obj_stack_pop_and_delete(new_num_operands, walk_state);
+
+	/* Restore operand count */
+	walk_state->num_operands = prev_num_operands;
 
 	ACPI_EXCEPTION((AE_INFO, status, "While creating Arg %u", index));
 	return_ACPI_STATUS(status);
diff --git a/drivers/acpi/acpica/exserial.c b/drivers/acpi/acpica/exserial.c
index 5241f4c01c76..89a4ac447a2b 100644
--- a/drivers/acpi/acpica/exserial.c
+++ b/drivers/acpi/acpica/exserial.c
@@ -201,6 +201,12 @@ acpi_ex_read_serial_bus(union acpi_operand_object *obj_desc,
 		function = ACPI_READ;
 		break;
 
+	case ACPI_ADR_SPACE_FIXED_HARDWARE:
+
+		buffer_length = ACPI_FFH_INPUT_BUFFER_SIZE;
+		function = ACPI_READ;
+		break;
+
 	default:
 		return_ACPI_STATUS(AE_AML_INVALID_SPACE_ID);
 	}
diff --git a/drivers/acpi/acpica/psobject.c b/drivers/acpi/acpica/psobject.c
index 54471083ba54..0bce1baaa62b 100644
--- a/drivers/acpi/acpica/psobject.c
+++ b/drivers/acpi/acpica/psobject.c
@@ -636,7 +636,8 @@ acpi_status
 acpi_ps_complete_final_op(struct acpi_walk_state *walk_state,
 			  union acpi_parse_object *op, acpi_status status)
 {
-	acpi_status status2;
+	acpi_status return_status = status;
+	u8 ascending = TRUE;
 
 	ACPI_FUNCTION_TRACE_PTR(ps_complete_final_op, walk_state);
 
@@ -650,7 +651,7 @@ acpi_ps_complete_final_op(struct acpi_walk_state *walk_state,
 			  op));
 	do {
 		if (op) {
-			if (walk_state->ascending_callback != NULL) {
+			if (ascending && walk_state->ascending_callback != NULL) {
 				walk_state->op = op;
 				walk_state->op_info =
 				    acpi_ps_get_opcode_info(op->common.
@@ -672,49 +673,26 @@ acpi_ps_complete_final_op(struct acpi_walk_state *walk_state,
 				}
 
 				if (status == AE_CTRL_TERMINATE) {
-					status = AE_OK;
-
-					/* Clean up */
-					do {
-						if (op) {
-							status2 =
-							    acpi_ps_complete_this_op
-							    (walk_state, op);
-							if (ACPI_FAILURE
-							    (status2)) {
-								return_ACPI_STATUS
-								    (status2);
-							}
-						}
-
-						acpi_ps_pop_scope(&
-								  (walk_state->
-								   parser_state),
-								  &op,
-								  &walk_state->
-								  arg_types,
-								  &walk_state->
-								  arg_count);
-
-					} while (op);
-
-					return_ACPI_STATUS(status);
+					ascending = FALSE;
+					return_status = AE_CTRL_TERMINATE;
 				}
 
 				else if (ACPI_FAILURE(status)) {
 
 					/* First error is most important */
 
-					(void)
-					    acpi_ps_complete_this_op(walk_state,
-								     op);
-					return_ACPI_STATUS(status);
+					ascending = FALSE;
+					return_status = status;
 				}
 			}
 
-			status2 = acpi_ps_complete_this_op(walk_state, op);
-			if (ACPI_FAILURE(status2)) {
-				return_ACPI_STATUS(status2);
+			status = acpi_ps_complete_this_op(walk_state, op);
+			if (ACPI_FAILURE(status)) {
+				ascending = FALSE;
+				if (ACPI_SUCCESS(return_status) ||
+				    return_status == AE_CTRL_TERMINATE) {
+					return_status = status;
+				}
 			}
 		}
 
@@ -724,5 +702,5 @@ acpi_ps_complete_final_op(struct acpi_walk_state *walk_state,
 
 	} while (op);
 
-	return_ACPI_STATUS(status);
+	return_ACPI_STATUS(return_status);
 }
diff --git a/drivers/acpi/acpica/rsaddr.c b/drivers/acpi/acpica/rsaddr.c
index 27384ee245f0..f92010e667cd 100644
--- a/drivers/acpi/acpica/rsaddr.c
+++ b/drivers/acpi/acpica/rsaddr.c
@@ -272,18 +272,13 @@ u8
 acpi_rs_get_address_common(struct acpi_resource *resource,
 			   union aml_resource *aml)
 {
-	struct aml_resource_address address;
-
 	ACPI_FUNCTION_ENTRY();
 
-	/* Avoid undefined behavior: member access within misaligned address */
-
-	memcpy(&address, aml, sizeof(address));
-
 	/* Validate the Resource Type */
 
-	if ((address.resource_type > 2) &&
-	    (address.resource_type < 0xC0) && (address.resource_type != 0x0A)) {
+	if ((aml->address.resource_type > 2) &&
+	    (aml->address.resource_type < 0xC0) &&
+	    (aml->address.resource_type != 0x0A)) {
 		return (FALSE);
 	}
 
@@ -304,7 +299,7 @@ acpi_rs_get_address_common(struct acpi_resource *resource,
 		/* Generic resource type, just grab the type_specific byte */
 
 		resource->data.address.info.type_specific =
-		    address.specific_flags;
+		    aml->address.specific_flags;
 	}
 
 	return (TRUE);
diff --git a/drivers/acpi/acpica/rscalc.c b/drivers/acpi/acpica/rscalc.c
index 6e7a152d6459..242daf45e20e 100644
--- a/drivers/acpi/acpica/rscalc.c
+++ b/drivers/acpi/acpica/rscalc.c
@@ -608,18 +608,12 @@ acpi_rs_get_list_length(u8 *aml_buffer,
 
 		case ACPI_RESOURCE_NAME_SERIAL_BUS:{
 
-				/* Avoid undefined behavior: member access within misaligned address */
-
-				struct aml_resource_common_serialbus
-				    common_serial_bus;
-				memcpy(&common_serial_bus, aml_resource,
-				       sizeof(common_serial_bus));
-
 				minimum_aml_resource_length =
 				    acpi_gbl_resource_aml_serial_bus_sizes
-				    [common_serial_bus.type];
+				    [aml_resource->common_serial_bus.type];
 				extra_struct_bytes +=
-				    common_serial_bus.resource_length -
+				    aml_resource->common_serial_bus.
+				    resource_length -
 				    minimum_aml_resource_length;
 				break;
 			}
@@ -688,16 +682,10 @@ acpi_rs_get_list_length(u8 *aml_buffer,
 		 */
 		if (acpi_ut_get_resource_type(aml_buffer) ==
 		    ACPI_RESOURCE_NAME_SERIAL_BUS) {
-
-			/* Avoid undefined behavior: member access within misaligned address */
-
-			struct aml_resource_common_serialbus common_serial_bus;
-			memcpy(&common_serial_bus, aml_resource,
-			       sizeof(common_serial_bus));
-
 			buffer_size =
 			    acpi_gbl_resource_struct_serial_bus_sizes
-			    [common_serial_bus.type] + extra_struct_bytes;
+			    [aml_resource->common_serial_bus.type] +
+			    extra_struct_bytes;
 		} else {
 			buffer_size =
 			    acpi_gbl_resource_struct_sizes[resource_index] +
diff --git a/drivers/acpi/acpica/rslist.c b/drivers/acpi/acpica/rslist.c
index 164c96e063c6..e46efaa889cd 100644
--- a/drivers/acpi/acpica/rslist.c
+++ b/drivers/acpi/acpica/rslist.c
@@ -55,21 +55,15 @@ acpi_rs_convert_aml_to_resources(u8 * aml,
 	aml_resource = ACPI_CAST_PTR(union aml_resource, aml);
 
 	if (acpi_ut_get_resource_type(aml) == ACPI_RESOURCE_NAME_SERIAL_BUS) {
-
-		/* Avoid undefined behavior: member access within misaligned address */
-
-		struct aml_resource_common_serialbus common_serial_bus;
-		memcpy(&common_serial_bus, aml_resource,
-		       sizeof(common_serial_bus));
-
-		if (common_serial_bus.type > AML_RESOURCE_MAX_SERIALBUSTYPE) {
+		if (aml_resource->common_serial_bus.type >
+		    AML_RESOURCE_MAX_SERIALBUSTYPE) {
 			conversion_table = NULL;
 		} else {
 			/* This is an I2C, SPI, UART, or CSI2 serial_bus descriptor */
 
 			conversion_table =
 			    acpi_gbl_convert_resource_serial_bus_dispatch
-			    [common_serial_bus.type];
+			    [aml_resource->common_serial_bus.type];
 		}
 	} else {
 		conversion_table =
diff --git a/drivers/acpi/acpica/utprint.c b/drivers/acpi/acpica/utprint.c
index 42b30b9f9312..7fad03c5252c 100644
--- a/drivers/acpi/acpica/utprint.c
+++ b/drivers/acpi/acpica/utprint.c
@@ -333,11 +333,8 @@ int vsnprintf(char *string, acpi_size size, const char *format, va_list args)
 
 	pos = string;
 
-	if (size != ACPI_UINT32_MAX) {
-		end = string + size;
-	} else {
-		end = ACPI_CAST_PTR(char, ACPI_UINT32_MAX);
-	}
+	size = ACPI_MIN(size, ACPI_PTR_DIFF(ACPI_MAX_PTR, string));
+	end = string + size;
 
 	for (; *format; ++format) {
 		if (*format != '%') {
diff --git a/drivers/acpi/acpica/utresrc.c b/drivers/acpi/acpica/utresrc.c
index cff7901f7866..e1cc3d348750 100644
--- a/drivers/acpi/acpica/utresrc.c
+++ b/drivers/acpi/acpica/utresrc.c
@@ -361,20 +361,16 @@ acpi_ut_validate_resource(struct acpi_walk_state *walk_state,
 	aml_resource = ACPI_CAST_PTR(union aml_resource, aml);
 	if (resource_type == ACPI_RESOURCE_NAME_SERIAL_BUS) {
 
-		/* Avoid undefined behavior: member access within misaligned address */
-
-		struct aml_resource_common_serialbus common_serial_bus;
-		memcpy(&common_serial_bus, aml_resource,
-		       sizeof(common_serial_bus));
-
 		/* Validate the bus_type field */
 
-		if ((common_serial_bus.type == 0) ||
-		    (common_serial_bus.type > AML_RESOURCE_MAX_SERIALBUSTYPE)) {
+		if ((aml_resource->common_serial_bus.type == 0) ||
+		    (aml_resource->common_serial_bus.type >
+		     AML_RESOURCE_MAX_SERIALBUSTYPE)) {
 			if (walk_state) {
 				ACPI_ERROR((AE_INFO,
 					    "Invalid/unsupported SerialBus resource descriptor: BusType 0x%2.2X",
-					    common_serial_bus.type));
+					    aml_resource->common_serial_bus.
+					    type));
 			}
 			return (AE_AML_INVALID_RESOURCE_TYPE);
 		}
diff --git a/drivers/acpi/apei/Kconfig b/drivers/acpi/apei/Kconfig
index 3cfe7e7475f2..070c07d68dfb 100644
--- a/drivers/acpi/apei/Kconfig
+++ b/drivers/acpi/apei/Kconfig
@@ -23,6 +23,7 @@ config ACPI_APEI_GHES
 	select ACPI_HED
 	select IRQ_WORK
 	select GENERIC_ALLOCATOR
+	select ARM_SDE_INTERFACE if ARM64
 	help
 	  Generic Hardware Error Source provides a way to report
 	  platform hardware errors (such as that from chipset). It
diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index ada93cfde9ba..91f9267c07ea 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -173,8 +173,6 @@ static struct gen_pool *ghes_estatus_pool;
 static struct ghes_estatus_cache __rcu *ghes_estatus_caches[GHES_ESTATUS_CACHES_SIZE];
 static atomic_t ghes_estatus_cache_alloced;
 
-static int ghes_panic_timeout __read_mostly = 30;
-
 static void __iomem *ghes_map(u64 pfn, enum fixed_addresses fixmap_idx)
 {
 	phys_addr_t paddr;
@@ -801,6 +799,17 @@ static bool ghes_do_proc(struct ghes *ghes,
 		}
 	}
 
+	/*
+	 * If no memory failure work is queued for abnormal synchronous
+	 * errors, do a force kill.
+	 */
+	if (sync && !queued) {
+		dev_err(ghes->dev,
+			HW_ERR GHES_PFX "%s:%d: synchronous unrecoverable error (SIGBUS)\n",
+			current->comm, task_pid_nr(current));
+		force_sig(SIGBUS);
+	}
+
 	return queued;
 }
 
@@ -983,14 +992,18 @@ static void __ghes_panic(struct ghes *ghes,
 			 struct acpi_hest_generic_status *estatus,
 			 u64 buf_paddr, enum fixed_addresses fixmap_idx)
 {
+	const char *msg = GHES_PFX "Fatal hardware error";
+
 	__ghes_print_estatus(KERN_EMERG, ghes->generic, estatus);
 
+	add_taint(TAINT_MACHINE_CHECK, LOCKDEP_STILL_OK);
+
 	ghes_clear_estatus(ghes, estatus, buf_paddr, fixmap_idx);
 
-	/* reboot to log the error! */
 	if (!panic_timeout)
-		panic_timeout = ghes_panic_timeout;
-	panic("Fatal hardware error!");
+		pr_emerg("%s but panic disabled\n", msg);
+
+	panic(msg);
 }
 
 static int ghes_proc(struct ghes *ghes)
@@ -1612,7 +1625,7 @@ void __init acpi_ghes_init(void)
 {
 	int rc;
 
-	sdei_init();
+	acpi_sdei_init();
 
 	if (acpi_disabled)
 		return;
diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index 16917dc3ad60..6234055d2598 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -1444,8 +1444,10 @@ static int __init acpi_init(void)
 	}
 
 	acpi_kobj = kobject_create_and_add("acpi", firmware_kobj);
-	if (!acpi_kobj)
-		pr_debug("%s: kset create error\n", __func__);
+	if (!acpi_kobj) {
+		pr_err("Failed to register kobject\n");
+		return -ENOMEM;
+	}
 
 	init_prmt();
 	acpi_init_pcc();
diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c
index e78e3754d99e..dab941dc984a 100644
--- a/drivers/acpi/cppc_acpi.c
+++ b/drivers/acpi/cppc_acpi.c
@@ -463,7 +463,7 @@ bool cppc_allow_fast_switch(void)
 	struct cpc_desc *cpc_ptr;
 	int cpu;
 
-	for_each_possible_cpu(cpu) {
+	for_each_present_cpu(cpu) {
 		cpc_ptr = per_cpu(cpc_desc_ptr, cpu);
 		desired_reg = &cpc_ptr->cpc_regs[DESIRED_PERF];
 		if (!CPC_IN_SYSTEM_MEMORY(desired_reg) &&
diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index 25399f6dde7e..e614e4bef9ea 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -2301,6 +2301,34 @@ static const struct dmi_system_id acpi_ec_no_wakeup[] = {
 			DMI_MATCH(DMI_PRODUCT_FAMILY, "103C_5336AN HP ZHAN 66 Pro"),
 		},
 	},
+	/*
+	 * Lenovo Legion Go S; touchscreen blocks HW sleep when woken up from EC
+	 * https://gitlab.freedesktop.org/drm/amd/-/issues/3929
+	 */
+	{
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "83L3"),
+		}
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "83N6"),
+		}
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "83Q2"),
+		}
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "83Q3"),
+		}
+	},
 	{ },
 };
 
diff --git a/drivers/acpi/fan_core.c b/drivers/acpi/fan_core.c
index 7cea4495f19b..300e5d919986 100644
--- a/drivers/acpi/fan_core.c
+++ b/drivers/acpi/fan_core.c
@@ -371,19 +371,25 @@ static int acpi_fan_probe(struct platform_device *pdev)
 	result = sysfs_create_link(&pdev->dev.kobj,
 				   &cdev->device.kobj,
 				   "thermal_cooling");
-	if (result)
+	if (result) {
 		dev_err(&pdev->dev, "Failed to create sysfs link 'thermal_cooling'\n");
+		goto err_unregister;
+	}
 
 	result = sysfs_create_link(&cdev->device.kobj,
 				   &pdev->dev.kobj,
 				   "device");
 	if (result) {
 		dev_err(&pdev->dev, "Failed to create sysfs link 'device'\n");
-		goto err_end;
+		goto err_remove_link;
 	}
 
 	return 0;
 
+err_remove_link:
+	sysfs_remove_link(&pdev->dev.kobj, "thermal_cooling");
+err_unregister:
+	thermal_cooling_device_unregister(cdev);
 err_end:
 	if (fan->acpi4)
 		acpi_fan_delete_attributes(device);
diff --git a/drivers/acpi/hed.c b/drivers/acpi/hed.c
index 7652515a6be1..3499f86c411e 100644
--- a/drivers/acpi/hed.c
+++ b/drivers/acpi/hed.c
@@ -80,7 +80,12 @@ static struct acpi_driver acpi_hed_driver = {
 		.remove = acpi_hed_remove,
 	},
 };
-module_acpi_driver(acpi_hed_driver);
+
+static int __init acpi_hed_driver_init(void)
+{
+	return acpi_bus_register_driver(&acpi_hed_driver);
+}
+subsys_initcall(acpi_hed_driver_init);
 
 MODULE_AUTHOR("Huang Ying");
 MODULE_DESCRIPTION("ACPI Hardware Error Device Driver");
diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c
index a5d47819b3a4..ae035b93da08 100644
--- a/drivers/acpi/nfit/core.c
+++ b/drivers/acpi/nfit/core.c
@@ -485,7 +485,7 @@ int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm,
 		cmd_mask = nd_desc->cmd_mask;
 		if (cmd == ND_CMD_CALL && call_pkg->nd_family) {
 			family = call_pkg->nd_family;
-			if (family > NVDIMM_BUS_FAMILY_MAX ||
+			if (call_pkg->nd_family > NVDIMM_BUS_FAMILY_MAX ||
 			    !test_bit(family, &nd_desc->bus_family_mask))
 				return -EINVAL;
 			family = array_index_nospec(family,
diff --git a/drivers/acpi/osi.c b/drivers/acpi/osi.c
index df9328c850bd..f2c943b934be 100644
--- a/drivers/acpi/osi.c
+++ b/drivers/acpi/osi.c
@@ -42,7 +42,6 @@ static struct acpi_osi_entry
 osi_setup_entries[OSI_STRING_ENTRIES_MAX] __initdata = {
 	{"Module Device", true},
 	{"Processor Device", true},
-	{"3.0 _SCP Extensions", true},
 	{"Processor Aggregator Device", true},
 };
 
diff --git a/drivers/acpi/platform_profile.c b/drivers/acpi/platform_profile.c
index d2f7fd7743a1..11278f785526 100644
--- a/drivers/acpi/platform_profile.c
+++ b/drivers/acpi/platform_profile.c
@@ -22,8 +22,8 @@ static const char * const profile_names[] = {
 };
 static_assert(ARRAY_SIZE(profile_names) == PLATFORM_PROFILE_LAST);
 
-static ssize_t platform_profile_choices_show(struct device *dev,
-					struct device_attribute *attr,
+static ssize_t platform_profile_choices_show(struct kobject *kobj,
+					struct kobj_attribute *attr,
 					char *buf)
 {
 	int len = 0;
@@ -49,8 +49,8 @@ static ssize_t platform_profile_choices_show(struct device *dev,
 	return len;
 }
 
-static ssize_t platform_profile_show(struct device *dev,
-					struct device_attribute *attr,
+static ssize_t platform_profile_show(struct kobject *kobj,
+					struct kobj_attribute *attr,
 					char *buf)
 {
 	enum platform_profile_option profile = PLATFORM_PROFILE_BALANCED;
@@ -77,8 +77,8 @@ static ssize_t platform_profile_show(struct device *dev,
 	return sysfs_emit(buf, "%s\n", profile_names[profile]);
 }
 
-static ssize_t platform_profile_store(struct device *dev,
-			    struct device_attribute *attr,
+static ssize_t platform_profile_store(struct kobject *kobj,
+			    struct kobj_attribute *attr,
 			    const char *buf, size_t count)
 {
 	int err, i;
@@ -115,12 +115,12 @@ static ssize_t platform_profile_store(struct device *dev,
 	return count;
 }
 
-static DEVICE_ATTR_RO(platform_profile_choices);
-static DEVICE_ATTR_RW(platform_profile);
+static struct kobj_attribute attr_platform_profile_choices = __ATTR_RO(platform_profile_choices);
+static struct kobj_attribute attr_platform_profile = __ATTR_RW(platform_profile);
 
 static struct attribute *platform_profile_attrs[] = {
-	&dev_attr_platform_profile_choices.attr,
-	&dev_attr_platform_profile.attr,
+	&attr_platform_profile_choices.attr,
+	&attr_platform_profile.attr,
 	NULL
 };
 
diff --git a/drivers/acpi/pptt.c b/drivers/acpi/pptt.c
index a35dd0e41c27..54676e3d82dd 100644
--- a/drivers/acpi/pptt.c
+++ b/drivers/acpi/pptt.c
@@ -229,18 +229,20 @@ static int acpi_pptt_leaf_node(struct acpi_table_header *table_hdr,
 	node_entry = ACPI_PTR_DIFF(node, table_hdr);
 	entry = ACPI_ADD_PTR(struct acpi_subtable_header, table_hdr,
 			     sizeof(struct acpi_table_pptt));
-	proc_sz = sizeof(struct acpi_pptt_processor *);
+	proc_sz = sizeof(struct acpi_pptt_processor);
 
-	while ((unsigned long)entry + proc_sz < table_end) {
+	/* ignore subtable types that are smaller than a processor node */
+	while ((unsigned long)entry + proc_sz <= table_end) {
 		cpu_node = (struct acpi_pptt_processor *)entry;
+
 		if (entry->type == ACPI_PPTT_TYPE_PROCESSOR &&
 		    cpu_node->parent == node_entry)
 			return 0;
 		if (entry->length == 0)
 			return 0;
+
 		entry = ACPI_ADD_PTR(struct acpi_subtable_header, entry,
 				     entry->length);
-
 	}
 	return 1;
 }
@@ -270,18 +272,21 @@ static struct acpi_pptt_processor *acpi_find_processor_node(struct acpi_table_he
 	table_end = (unsigned long)table_hdr + table_hdr->length;
 	entry = ACPI_ADD_PTR(struct acpi_subtable_header, table_hdr,
 			     sizeof(struct acpi_table_pptt));
-	proc_sz = sizeof(struct acpi_pptt_processor *);
+	proc_sz = sizeof(struct acpi_pptt_processor);
 
 	/* find the processor structure associated with this cpuid */
-	while ((unsigned long)entry + proc_sz < table_end) {
+	while ((unsigned long)entry + proc_sz <= table_end) {
 		cpu_node = (struct acpi_pptt_processor *)entry;
 
 		if (entry->length == 0) {
 			pr_warn("Invalid zero length subtable\n");
 			break;
 		}
+		/* entry->length may not equal proc_sz, revalidate the processor structure length */
 		if (entry->type == ACPI_PPTT_TYPE_PROCESSOR &&
 		    acpi_cpu_id == cpu_node->acpi_processor_id &&
+		    (unsigned long)entry + entry->length <= table_end &&
+		    entry->length == proc_sz + cpu_node->number_of_priv_resources * sizeof(u32) &&
 		     acpi_pptt_leaf_node(table_hdr, cpu_node)) {
 			return (struct acpi_pptt_processor *)entry;
 		}
diff --git a/drivers/acpi/prmt.c b/drivers/acpi/prmt.c
index 747f83f7114d..be033bbb126a 100644
--- a/drivers/acpi/prmt.c
+++ b/drivers/acpi/prmt.c
@@ -85,8 +85,6 @@ static u64 efi_pa_va_lookup(efi_guid_t *guid, u64 pa)
 		}
 	}
 
-	pr_warn("Failed to find VA for GUID: %pUL, PA: 0x%llx", guid, pa);
-
 	return 0;
 }
 
@@ -154,13 +152,37 @@ acpi_parse_prmt(union acpi_subtable_headers *header, const unsigned long end)
 		guid_copy(&th->guid, (guid_t *)handler_info->handler_guid);
 		th->handler_addr =
 			(void *)efi_pa_va_lookup(&th->guid, handler_info->handler_address);
+		/*
+		 * Print a warning message if handler_addr is zero which is not expected to
+		 * ever happen.
+		 */
+		if (unlikely(!th->handler_addr))
+			pr_warn("Failed to find VA of handler for GUID: %pUL, PA: 0x%llx",
+				&th->guid, handler_info->handler_address);
 
 		th->static_data_buffer_addr =
 			efi_pa_va_lookup(&th->guid, handler_info->static_data_buffer_address);
+		/*
+		 * According to the PRM specification, static_data_buffer_address can be zero,
+		 * so avoid printing a warning message in that case.  Otherwise, if the
+		 * return value of efi_pa_va_lookup() is zero, print the message.
+		 */
+		if (unlikely(!th->static_data_buffer_addr && handler_info->static_data_buffer_address))
+			pr_warn("Failed to find VA of static data buffer for GUID: %pUL, PA: 0x%llx",
+				&th->guid, handler_info->static_data_buffer_address);
 
 		th->acpi_param_buffer_addr =
 			efi_pa_va_lookup(&th->guid, handler_info->acpi_param_buffer_address);
 
+		/*
+		 * According to the PRM specification, acpi_param_buffer_address can be zero,
+		 * so avoid printing a warning message in that case.  Otherwise, if the
+		 * return value of efi_pa_va_lookup() is zero, print the message.
+		 */
+		if (unlikely(!th->acpi_param_buffer_addr && handler_info->acpi_param_buffer_address))
+			pr_warn("Failed to find VA of acpi param buffer for GUID: %pUL, PA: 0x%llx",
+				&th->guid, handler_info->acpi_param_buffer_address);
+
 	} while (++cur_handler < tm->handler_count && (handler_info = get_next_handler(handler_info)));
 
 	return 0;
@@ -287,9 +309,7 @@ static acpi_status acpi_platformrt_space_handler(u32 function,
 		if (!handler || !module)
 			goto invalid_guid;
 
-		if (!handler->handler_addr ||
-		    !handler->static_data_buffer_addr ||
-		    !handler->acpi_param_buffer_addr) {
+		if (!handler->handler_addr) {
 			buffer->prm_status = PRM_HANDLER_ERROR;
 			return AE_OK;
 		}
diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index 831fa4a12159..0888e4d618d5 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -268,6 +268,10 @@ static int acpi_processor_get_power_info_fadt(struct acpi_processor *pr)
 			 ACPI_CX_DESC_LEN, "ACPI P_LVL3 IOPORT 0x%x",
 			 pr->power.states[ACPI_STATE_C3].address);
 
+	if (!pr->power.states[ACPI_STATE_C2].address &&
+	    !pr->power.states[ACPI_STATE_C3].address)
+		return -ENODEV;
+
 	return 0;
 }
 
diff --git a/drivers/acpi/processor_perflib.c b/drivers/acpi/processor_perflib.c
index 4265814c74f8..d81f30ce2341 100644
--- a/drivers/acpi/processor_perflib.c
+++ b/drivers/acpi/processor_perflib.c
@@ -174,6 +174,9 @@ void acpi_processor_ppc_init(struct cpufreq_policy *policy)
 {
 	unsigned int cpu;
 
+	if (ignore_ppc == 1)
+		return;
+
 	for_each_cpu(cpu, policy->related_cpus) {
 		struct acpi_processor *pr = per_cpu(processors, cpu);
 		int ret;
@@ -194,6 +197,14 @@ void acpi_processor_ppc_init(struct cpufreq_policy *policy)
 		if (ret < 0)
 			pr_err("Failed to add freq constraint for CPU%d (%d)\n",
 			       cpu, ret);
+
+		if (!pr->performance)
+			continue;
+
+		ret = acpi_processor_get_platform_limit(pr);
+		if (ret)
+			pr_err("Failed to update freq constraint for CPU%d (%d)\n",
+			       cpu, ret);
 	}
 }
 
diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c
index 80a52a4e66dd..e9186339f6e6 100644
--- a/drivers/acpi/property.c
+++ b/drivers/acpi/property.c
@@ -1187,8 +1187,6 @@ static int acpi_data_prop_read(const struct acpi_device_data *data,
 		}
 		break;
 	}
-	if (nval == 0)
-		return -EINVAL;
 
 	if (obj->type == ACPI_TYPE_BUFFER) {
 		if (proptype != DEV_PROP_U8)
@@ -1212,9 +1210,11 @@ static int acpi_data_prop_read(const struct acpi_device_data *data,
 		ret = acpi_copy_property_array_uint(items, (u64 *)val, nval);
 		break;
 	case DEV_PROP_STRING:
-		ret = acpi_copy_property_array_string(
-			items, (char **)val,
-			min_t(u32, nval, obj->package.count));
+		nval = min_t(u32, nval, obj->package.count);
+		if (nval == 0)
+			return -ENODATA;
+
+		ret = acpi_copy_property_array_string(items, (char **)val, nval);
 		break;
 	default:
 		ret = -EINVAL;
diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c
index 90aaec923889..7d59c6c9185f 100644
--- a/drivers/acpi/resource.c
+++ b/drivers/acpi/resource.c
@@ -441,6 +441,13 @@ static const struct dmi_system_id irq1_level_low_skip_override[] = {
 		},
 	},
 	{
+		/* Asus Vivobook X1404VAP */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_BOARD_NAME, "X1404VAP"),
+		},
+	},
+	{
 		/* Asus Vivobook X1504VAP */
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
@@ -527,7 +534,7 @@ static const struct dmi_system_id irq1_level_low_skip_override[] = {
  */
 static const struct dmi_system_id irq1_edge_low_force_override[] = {
 	{
-		/* MECHREV Jiaolong17KS Series GM7XG0M */
+		/* MECHREVO Jiaolong17KS Series GM7XG0M */
 		.matches = {
 			DMI_MATCH(DMI_BOARD_NAME, "GM7XG0M"),
 		},
@@ -564,6 +571,12 @@ static const struct dmi_system_id irq1_edge_low_force_override[] = {
 		},
 	},
 	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Eluktronics Inc."),
+			DMI_MATCH(DMI_BOARD_NAME, "MECH-17"),
+		},
+	},
+	{
 		/* TongFang GM6XGxX/TUXEDO Stellaris 16 Gen5 AMD */
 		.matches = {
 			DMI_MATCH(DMI_BOARD_NAME, "GM6XGxX"),
diff --git a/drivers/acpi/thermal.c b/drivers/acpi/thermal.c
index 78db38c7076e..125d7df8f30a 100644
--- a/drivers/acpi/thermal.c
+++ b/drivers/acpi/thermal.c
@@ -803,7 +803,13 @@ static int acpi_thermal_add(struct acpi_device *device)
 
 	acpi_thermal_aml_dependency_fix(tz);
 
-	/* Get trip points [_CRT, _PSV, etc.] (required). */
+	/*
+	 * Set the cooling mode [_SCP] to active cooling. This needs to happen before
+	 * we retrieve the trip point values.
+	 */
+	acpi_execute_simple_method(tz->device->handle, "_SCP", ACPI_THERMAL_MODE_ACTIVE);
+
+	/* Get trip points [_ACi, _PSV, etc.] (required). */
 	acpi_thermal_get_trip_points(tz);
 
 	crit_temp = acpi_thermal_get_critical_trip(tz);
@@ -814,10 +820,6 @@ static int acpi_thermal_add(struct acpi_device *device)
 	if (result)
 		goto free_memory;
 
-	/* Set the cooling mode [_SCP] to active cooling. */
-	acpi_execute_simple_method(tz->device->handle, "_SCP",
-				   ACPI_THERMAL_MODE_ACTIVE);
-
 	/* Determine the default polling frequency [_TZP]. */
 	if (tzp)
 		tz->polling_frequency = tzp;
diff --git a/drivers/acpi/x86/utils.c b/drivers/acpi/x86/utils.c
index cb45ef5240da..4ee30c2897a2 100644
--- a/drivers/acpi/x86/utils.c
+++ b/drivers/acpi/x86/utils.c
@@ -374,7 +374,8 @@ static const struct dmi_system_id acpi_quirk_skip_dmi_ids[] = {
 			DMI_MATCH(DMI_PRODUCT_VERSION, "Blade3-10A-001"),
 		},
 		.driver_data = (void *)(ACPI_QUIRK_SKIP_I2C_CLIENTS |
-					ACPI_QUIRK_SKIP_ACPI_AC_AND_BATTERY),
+					ACPI_QUIRK_SKIP_ACPI_AC_AND_BATTERY |
+					ACPI_QUIRK_SKIP_GPIO_EVENT_HANDLERS),
 	},
 	{
 		/* Medion Lifetab S10346 */
@@ -408,6 +409,19 @@ static const struct dmi_system_id acpi_quirk_skip_dmi_ids[] = {
 					ACPI_QUIRK_SKIP_ACPI_AC_AND_BATTERY),
 	},
 	{
+		/* Vexia Edu Atla 10 tablet 5V version */
+		.matches = {
+			/* Having all 3 of these not set is somewhat unique */
+			DMI_MATCH(DMI_SYS_VENDOR, "To be filled by O.E.M."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "To be filled by O.E.M."),
+			DMI_MATCH(DMI_BOARD_NAME, "To be filled by O.E.M."),
+			/* Above strings are too generic, also match on BIOS date */
+			DMI_MATCH(DMI_BIOS_DATE, "05/14/2015"),
+		},
+		.driver_data = (void *)(ACPI_QUIRK_SKIP_I2C_CLIENTS |
+					ACPI_QUIRK_SKIP_ACPI_AC_AND_BATTERY),
+	},
+	{
 		/* Vexia Edu Atla 10 tablet 9V version */
 		.matches = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "AMI Corporation"),
diff --git a/drivers/android/binder.c b/drivers/android/binder.c
index ef353ca13c35..bdf09e8b898d 100644
--- a/drivers/android/binder.c
+++ b/drivers/android/binder.c
@@ -6374,7 +6374,7 @@ static void print_binder_transaction_ilocked(struct seq_file *m,
 		seq_printf(m, " node %d", buffer->target_node->debug_id);
 	seq_printf(m, " size %zd:%zd offset %lx\n",
 		   buffer->data_size, buffer->offsets_size,
-		   proc->alloc.buffer - buffer->user_data);
+		   buffer->user_data - proc->alloc.buffer);
 }
 
 static void print_binder_work_ilocked(struct seq_file *m,
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index 45f63b09828a..944e44caa260 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -63,6 +63,7 @@ enum board_ids {
 	board_ahci_pcs_quirk_no_devslp,
 	board_ahci_pcs_quirk_no_sntf,
 	board_ahci_yes_fbs,
+	board_ahci_yes_fbs_atapi_dma,
 
 	/* board IDs for specific chipsets in alphabetical order */
 	board_ahci_al,
@@ -188,6 +189,14 @@ static const struct ata_port_info ahci_port_info[] = {
 		.udma_mask	= ATA_UDMA6,
 		.port_ops	= &ahci_ops,
 	},
+	[board_ahci_yes_fbs_atapi_dma] = {
+		AHCI_HFLAGS	(AHCI_HFLAG_YES_FBS |
+				 AHCI_HFLAG_ATAPI_DMA_QUIRK),
+		.flags		= AHCI_FLAG_COMMON,
+		.pio_mask	= ATA_PIO4,
+		.udma_mask	= ATA_UDMA6,
+		.port_ops	= &ahci_ops,
+	},
 	/* by chipsets */
 	[board_ahci_al] = {
 		AHCI_HFLAGS	(AHCI_HFLAG_NO_PMP | AHCI_HFLAG_NO_MSI),
@@ -589,6 +598,8 @@ static const struct pci_device_id ahci_pci_tbl[] = {
 	  .driver_data = board_ahci_yes_fbs },
 	{ PCI_DEVICE(PCI_VENDOR_ID_MARVELL_EXT, 0x91a3),
 	  .driver_data = board_ahci_yes_fbs },
+	{ PCI_DEVICE(PCI_VENDOR_ID_MARVELL_EXT, 0x9215),
+	  .driver_data = board_ahci_yes_fbs_atapi_dma },
 	{ PCI_DEVICE(PCI_VENDOR_ID_MARVELL_EXT, 0x9230),
 	  .driver_data = board_ahci_yes_fbs },
 	{ PCI_DEVICE(PCI_VENDOR_ID_MARVELL_EXT, 0x9235),
@@ -1399,8 +1410,15 @@ static bool ahci_broken_suspend(struct pci_dev *pdev)
 
 static bool ahci_broken_lpm(struct pci_dev *pdev)
 {
+	/*
+	 * Platforms with LPM problems.
+	 * If driver_data is NULL, there is no existing BIOS version with
+	 * functioning LPM.
+	 * If driver_data is non-NULL, then driver_data contains the DMI BIOS
+	 * build date of the first BIOS version with functioning LPM (i.e. older
+	 * BIOS versions have broken LPM).
+	 */
 	static const struct dmi_system_id sysids[] = {
-		/* Various Lenovo 50 series have LPM issues with older BIOSen */
 		{
 			.matches = {
 				DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
@@ -1435,6 +1453,29 @@ static bool ahci_broken_lpm(struct pci_dev *pdev)
 			 */
 			.driver_data = "20180310", /* 2.35 */
 		},
+		{
+			.matches = {
+				DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+				DMI_MATCH(DMI_PRODUCT_NAME, "ASUSPRO D840MB_M840SA"),
+			},
+			/* 320 is broken, there is no known good version. */
+		},
+		{
+			/*
+			 * AMD 500 Series Chipset SATA Controller [1022:43eb]
+			 * on this motherboard timeouts on ports 5 and 6 when
+			 * LPM is enabled, at least with WDC WD20EFAX-68FB5N0
+			 * hard drives. LPM with the same drive works fine on
+			 * all other ports on the same controller.
+			 */
+			.matches = {
+				DMI_MATCH(DMI_BOARD_VENDOR,
+					  "ASUSTeK COMPUTER INC."),
+				DMI_MATCH(DMI_BOARD_NAME,
+					  "ROG STRIX B550-F GAMING (WI-FI)"),
+			},
+			/* 3621 is broken, there is no known good version. */
+		},
 		{ }	/* terminate list */
 	};
 	const struct dmi_system_id *dmi = dmi_first_match(sysids);
@@ -1444,6 +1485,9 @@ static bool ahci_broken_lpm(struct pci_dev *pdev)
 	if (!dmi)
 		return false;
 
+	if (!dmi->driver_data)
+		return true;
+
 	dmi_get_date(DMI_BIOS_DATE, &year, &month, &date);
 	snprintf(buf, sizeof(buf), "%04d%02d%02d", year, month, date);
 
@@ -1737,11 +1781,21 @@ static void ahci_update_initial_lpm_policy(struct ata_port *ap)
 		return;
 	}
 
+	/* If no Partial or no Slumber, we cannot support DIPM. */
+	if ((ap->host->flags & ATA_HOST_NO_PART) ||
+	    (ap->host->flags & ATA_HOST_NO_SSC)) {
+		ata_port_dbg(ap, "Host does not support DIPM\n");
+		ap->flags |= ATA_FLAG_NO_DIPM;
+	}
+
 	/* If no LPM states are supported by the HBA, do not bother with LPM */
 	if ((ap->host->flags & ATA_HOST_NO_PART) &&
 	    (ap->host->flags & ATA_HOST_NO_SSC) &&
 	    (ap->host->flags & ATA_HOST_NO_DEVSLP)) {
-		ata_port_dbg(ap, "no LPM states supported, not enabling LPM\n");
+		ata_port_dbg(ap,
+			"No LPM states supported, forcing LPM max_power\n");
+		ap->flags |= ATA_FLAG_NO_LPM;
+		ap->target_lpm_policy = ATA_LPM_MAX_POWER;
 		return;
 	}
 
diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h
index 8f40f75ba08c..10a5fe02f0a4 100644
--- a/drivers/ata/ahci.h
+++ b/drivers/ata/ahci.h
@@ -246,6 +246,7 @@ enum {
 	AHCI_HFLAG_NO_SXS		= BIT(26), /* SXS not supported */
 	AHCI_HFLAG_43BIT_ONLY		= BIT(27), /* 43bit DMA addr limit */
 	AHCI_HFLAG_INTEL_PCS_QUIRK	= BIT(28), /* apply Intel PCS quirk */
+	AHCI_HFLAG_ATAPI_DMA_QUIRK	= BIT(29), /* force ATAPI to use DMA */
 
 	/* ap->flags bits */
 
diff --git a/drivers/ata/ata_piix.c b/drivers/ata/ata_piix.c
index 093b940bc953..d3cda803ae06 100644
--- a/drivers/ata/ata_piix.c
+++ b/drivers/ata/ata_piix.c
@@ -1089,6 +1089,7 @@ static struct ata_port_operations ich_pata_ops = {
 };
 
 static struct attribute *piix_sidpr_shost_attrs[] = {
+	&dev_attr_link_power_management_supported.attr,
 	&dev_attr_link_power_management_policy.attr,
 	NULL
 };
diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c
index fdfa7b266218..7824e8836a54 100644
--- a/drivers/ata/libahci.c
+++ b/drivers/ata/libahci.c
@@ -111,6 +111,7 @@ static DEVICE_ATTR(em_buffer, S_IWUSR | S_IRUGO,
 static DEVICE_ATTR(em_message_supported, S_IRUGO, ahci_show_em_supported, NULL);
 
 static struct attribute *ahci_shost_attrs[] = {
+	&dev_attr_link_power_management_supported.attr,
 	&dev_attr_link_power_management_policy.attr,
 	&dev_attr_em_message_type.attr,
 	&dev_attr_em_message.attr,
@@ -1321,6 +1322,10 @@ static void ahci_dev_config(struct ata_device *dev)
 {
 	struct ahci_host_priv *hpriv = dev->link->ap->host->private_data;
 
+	if ((dev->class == ATA_DEV_ATAPI) &&
+	    (hpriv->flags & AHCI_HFLAG_ATAPI_DMA_QUIRK))
+		dev->quirks |= ATA_QUIRK_ATAPI_MOD16_DMA;
+
 	if (hpriv->flags & AHCI_HFLAG_SECT255) {
 		dev->max_sectors = 255;
 		ata_dev_info(dev,
diff --git a/drivers/ata/libata-acpi.c b/drivers/ata/libata-acpi.c
index d36e71f475ab..39a350755a1b 100644
--- a/drivers/ata/libata-acpi.c
+++ b/drivers/ata/libata-acpi.c
@@ -514,15 +514,19 @@ unsigned int ata_acpi_gtm_xfermask(struct ata_device *dev,
 EXPORT_SYMBOL_GPL(ata_acpi_gtm_xfermask);
 
 /**
- * ata_acpi_cbl_80wire		-	Check for 80 wire cable
+ * ata_acpi_cbl_pata_type - Return PATA cable type
  * @ap: Port to check
- * @gtm: GTM data to use
  *
- * Return 1 if the @gtm indicates the BIOS selected an 80wire mode.
+ * Return ATA_CBL_PATA* according to the transfer mode selected by BIOS
  */
-int ata_acpi_cbl_80wire(struct ata_port *ap, const struct ata_acpi_gtm *gtm)
+int ata_acpi_cbl_pata_type(struct ata_port *ap)
 {
 	struct ata_device *dev;
+	int ret = ATA_CBL_PATA_UNK;
+	const struct ata_acpi_gtm *gtm = ata_acpi_init_gtm(ap);
+
+	if (!gtm)
+		return ATA_CBL_PATA40;
 
 	ata_for_each_dev(dev, &ap->link, ENABLED) {
 		unsigned int xfer_mask, udma_mask;
@@ -530,13 +534,17 @@ int ata_acpi_cbl_80wire(struct ata_port *ap, const struct ata_acpi_gtm *gtm)
 		xfer_mask = ata_acpi_gtm_xfermask(dev, gtm);
 		ata_unpack_xfermask(xfer_mask, NULL, NULL, &udma_mask);
 
-		if (udma_mask & ~ATA_UDMA_MASK_40C)
-			return 1;
+		ret = ATA_CBL_PATA40;
+
+		if (udma_mask & ~ATA_UDMA_MASK_40C) {
+			ret = ATA_CBL_PATA80;
+			break;
+		}
 	}
 
-	return 0;
+	return ret;
 }
-EXPORT_SYMBOL_GPL(ata_acpi_cbl_80wire);
+EXPORT_SYMBOL_GPL(ata_acpi_cbl_pata_type);
 
 static void ata_acpi_gtf_to_tf(struct ata_device *dev,
 			       const struct ata_acpi_gtf *gtf,
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index c085dd81ebe7..0cb97181d10a 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -88,6 +88,7 @@ struct ata_force_param {
 	unsigned int	xfer_mask;
 	unsigned int	quirk_on;
 	unsigned int	quirk_off;
+	unsigned int	pflags_on;
 	u16		lflags_on;
 	u16		lflags_off;
 };
@@ -332,6 +333,35 @@ void ata_force_cbl(struct ata_port *ap)
 }
 
 /**
+ *	ata_force_pflags - force port flags according to libata.force
+ *	@ap: ATA port of interest
+ *
+ *	Force port flags according to libata.force and whine about it.
+ *
+ *	LOCKING:
+ *	EH context.
+ */
+static void ata_force_pflags(struct ata_port *ap)
+{
+	int i;
+
+	for (i = ata_force_tbl_size - 1; i >= 0; i--) {
+		const struct ata_force_ent *fe = &ata_force_tbl[i];
+
+		if (fe->port != -1 && fe->port != ap->print_id)
+			continue;
+
+		/* let pflags stack */
+		if (fe->param.pflags_on) {
+			ap->pflags |= fe->param.pflags_on;
+			ata_port_notice(ap,
+					"FORCE: port flag 0x%x forced -> 0x%x\n",
+					fe->param.pflags_on, ap->pflags);
+		}
+	}
+}
+
+/**
  *	ata_force_link_limits - force link limits according to libata.force
  *	@link: ATA link of interest
  *
@@ -486,6 +516,7 @@ static void ata_force_quirks(struct ata_device *dev)
 	}
 }
 #else
+static inline void ata_force_pflags(struct ata_port *ap) { }
 static inline void ata_force_link_limits(struct ata_link *link) { }
 static inline void ata_force_xfermask(struct ata_device *dev) { }
 static inline void ata_force_quirks(struct ata_device *dev) { }
@@ -2845,6 +2876,10 @@ int ata_dev_configure(struct ata_device *dev)
 	    (id[ATA_ID_SATA_CAPABILITY] & 0xe) == 0x2)
 		dev->quirks |= ATA_QUIRK_NOLPM;
 
+	if (dev->quirks & ATA_QUIRK_NO_LPM_ON_ATI &&
+	    ata_dev_check_adapter(dev, PCI_VENDOR_ID_ATI))
+		dev->quirks |= ATA_QUIRK_NOLPM;
+
 	if (ap->flags & ATA_FLAG_NO_LPM)
 		dev->quirks |= ATA_QUIRK_NOLPM;
 
@@ -3897,6 +3932,7 @@ static const char * const ata_quirk_names[] = {
 	[__ATA_QUIRK_MAX_SEC_1024]	= "maxsec1024",
 	[__ATA_QUIRK_MAX_TRIM_128M]	= "maxtrim128m",
 	[__ATA_QUIRK_NO_NCQ_ON_ATI]	= "noncqonati",
+	[__ATA_QUIRK_NO_LPM_ON_ATI]	= "nolpmonati",
 	[__ATA_QUIRK_NO_ID_DEV_LOG]	= "noiddevlog",
 	[__ATA_QUIRK_NO_LOG_DIR]	= "nologdir",
 	[__ATA_QUIRK_NO_FUA]		= "nofua",
@@ -4142,13 +4178,16 @@ static const struct ata_dev_quirks_entry __ata_dev_quirks[] = {
 						ATA_QUIRK_ZERO_AFTER_TRIM },
 	{ "Samsung SSD 860*",		NULL,	ATA_QUIRK_NO_NCQ_TRIM |
 						ATA_QUIRK_ZERO_AFTER_TRIM |
-						ATA_QUIRK_NO_NCQ_ON_ATI },
+						ATA_QUIRK_NO_NCQ_ON_ATI |
+						ATA_QUIRK_NO_LPM_ON_ATI },
 	{ "Samsung SSD 870*",		NULL,	ATA_QUIRK_NO_NCQ_TRIM |
 						ATA_QUIRK_ZERO_AFTER_TRIM |
-						ATA_QUIRK_NO_NCQ_ON_ATI },
+						ATA_QUIRK_NO_NCQ_ON_ATI |
+						ATA_QUIRK_NO_LPM_ON_ATI },
 	{ "SAMSUNG*MZ7LH*",		NULL,	ATA_QUIRK_NO_NCQ_TRIM |
 						ATA_QUIRK_ZERO_AFTER_TRIM |
-						ATA_QUIRK_NO_NCQ_ON_ATI, },
+						ATA_QUIRK_NO_NCQ_ON_ATI |
+						ATA_QUIRK_NO_LPM_ON_ATI },
 	{ "FCCT*M500*",			NULL,	ATA_QUIRK_NO_NCQ_TRIM |
 						ATA_QUIRK_ZERO_AFTER_TRIM },
 
@@ -5452,6 +5491,8 @@ struct ata_port *ata_port_alloc(struct ata_host *host)
 #endif
 	ata_sff_port_init(ap);
 
+	ata_force_pflags(ap);
+
 	return ap;
 }
 EXPORT_SYMBOL_GPL(ata_port_alloc);
@@ -6264,6 +6305,9 @@ EXPORT_SYMBOL_GPL(ata_platform_remove_one);
 	{ "no" #name,	.lflags_on	= (flags) },	\
 	{ #name,	.lflags_off	= (flags) }
 
+#define force_pflag_on(name, flags)			\
+	{ #name,	.pflags_on	= (flags) }
+
 #define force_quirk_on(name, flag)			\
 	{ #name,	.quirk_on	= (flag) }
 
@@ -6323,6 +6367,8 @@ static const struct ata_force_param force_tbl[] __initconst = {
 	force_lflag_on(rstonce,		ATA_LFLAG_RST_ONCE),
 	force_lflag_onoff(dbdelay,	ATA_LFLAG_NO_DEBOUNCE_DELAY),
 
+	force_pflag_on(external,	ATA_PFLAG_EXTERNAL),
+
 	force_quirk_onoff(ncq,		ATA_QUIRK_NONCQ),
 	force_quirk_onoff(ncqtrim,	ATA_QUIRK_NO_NCQ_TRIM),
 	force_quirk_onoff(ncqati,	ATA_QUIRK_NO_NCQ_ON_ATI),
diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
index 3b303d4ae37a..16cd676eae1f 100644
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -1542,8 +1542,15 @@ unsigned int atapi_eh_request_sense(struct ata_device *dev,
 	tf.flags |= ATA_TFLAG_ISADDR | ATA_TFLAG_DEVICE;
 	tf.command = ATA_CMD_PACKET;
 
-	/* is it pointless to prefer PIO for "safety reasons"? */
-	if (ap->flags & ATA_FLAG_PIO_DMA) {
+	/*
+	 * Do not use DMA if the connected device only supports PIO, even if the
+	 * port prefers PIO commands via DMA.
+	 *
+	 * Ideally, we should call atapi_check_dma() to check if it is safe for
+	 * the LLD to use DMA for REQUEST_SENSE, but we don't have a qc.
+	 * Since we can't check the command, perhaps we should only use pio?
+	 */
+	if ((ap->flags & ATA_FLAG_PIO_DMA) && !(dev->flags & ATA_DFLAG_PIO)) {
 		tf.protocol = ATAPI_PROT_DMA;
 		tf.feature |= ATAPI_PKT_DMA;
 	} else {
diff --git a/drivers/ata/libata-sata.c b/drivers/ata/libata-sata.c
index 9c76fb1ad2ec..cad3855373cb 100644
--- a/drivers/ata/libata-sata.c
+++ b/drivers/ata/libata-sata.c
@@ -900,14 +900,52 @@ static const char *ata_lpm_policy_names[] = {
 	[ATA_LPM_MIN_POWER]		= "min_power",
 };
 
+/*
+ * Check if a port supports link power management.
+ * Must be called with the port locked.
+ */
+static bool ata_scsi_lpm_supported(struct ata_port *ap)
+{
+	struct ata_link *link;
+	struct ata_device *dev;
+
+	if (ap->flags & ATA_FLAG_NO_LPM)
+		return false;
+
+	ata_for_each_link(link, ap, EDGE) {
+		ata_for_each_dev(dev, &ap->link, ENABLED) {
+			if (dev->quirks & ATA_QUIRK_NOLPM)
+				return false;
+		}
+	}
+
+	return true;
+}
+
+static ssize_t ata_scsi_lpm_supported_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	struct Scsi_Host *shost = class_to_shost(dev);
+	struct ata_port *ap = ata_shost_to_port(shost);
+	unsigned long flags;
+	bool supported;
+
+	spin_lock_irqsave(ap->lock, flags);
+	supported = ata_scsi_lpm_supported(ap);
+	spin_unlock_irqrestore(ap->lock, flags);
+
+	return sysfs_emit(buf, "%d\n", supported);
+}
+DEVICE_ATTR(link_power_management_supported, S_IRUGO,
+	    ata_scsi_lpm_supported_show, NULL);
+EXPORT_SYMBOL_GPL(dev_attr_link_power_management_supported);
+
 static ssize_t ata_scsi_lpm_store(struct device *device,
 				  struct device_attribute *attr,
 				  const char *buf, size_t count)
 {
 	struct Scsi_Host *shost = class_to_shost(device);
 	struct ata_port *ap = ata_shost_to_port(shost);
-	struct ata_link *link;
-	struct ata_device *dev;
 	enum ata_lpm_policy policy;
 	unsigned long flags;
 
@@ -924,13 +962,9 @@ static ssize_t ata_scsi_lpm_store(struct device *device,
 
 	spin_lock_irqsave(ap->lock, flags);
 
-	ata_for_each_link(link, ap, EDGE) {
-		ata_for_each_dev(dev, &ap->link, ENABLED) {
-			if (dev->quirks & ATA_QUIRK_NOLPM) {
-				count = -EOPNOTSUPP;
-				goto out_unlock;
-			}
-		}
+	if (!ata_scsi_lpm_supported(ap)) {
+		count = -EOPNOTSUPP;
+		goto out_unlock;
 	}
 
 	ap->target_lpm_policy = policy;
@@ -1510,6 +1544,8 @@ int ata_eh_get_ncq_success_sense(struct ata_link *link)
 	unsigned int err_mask, tag;
 	u8 *sense, sk = 0, asc = 0, ascq = 0;
 	u64 sense_valid, val;
+	u16 extended_sense;
+	bool aux_icc_valid;
 	int ret = 0;
 
 	err_mask = ata_read_log_page(dev, ATA_LOG_SENSE_NCQ, 0, buf, 2);
@@ -1529,6 +1565,8 @@ int ata_eh_get_ncq_success_sense(struct ata_link *link)
 
 	sense_valid = (u64)buf[8] | ((u64)buf[9] << 8) |
 		((u64)buf[10] << 16) | ((u64)buf[11] << 24);
+	extended_sense = get_unaligned_le16(&buf[14]);
+	aux_icc_valid = extended_sense & BIT(15);
 
 	ata_qc_for_each_raw(ap, qc, tag) {
 		if (!(qc->flags & ATA_QCFLAG_EH) ||
@@ -1556,6 +1594,17 @@ int ata_eh_get_ncq_success_sense(struct ata_link *link)
 			continue;
 		}
 
+		qc->result_tf.nsect = sense[6];
+		qc->result_tf.hob_nsect = sense[7];
+		qc->result_tf.lbal = sense[8];
+		qc->result_tf.lbam = sense[9];
+		qc->result_tf.lbah = sense[10];
+		qc->result_tf.hob_lbal = sense[11];
+		qc->result_tf.hob_lbam = sense[12];
+		qc->result_tf.hob_lbah = sense[13];
+		if (aux_icc_valid)
+			qc->result_tf.auxiliary = get_unaligned_le32(&sense[16]);
+
 		/* Set sense without also setting scsicmd->result */
 		scsi_build_sense_buffer(dev->flags & ATA_DFLAG_D_SENSE,
 					qc->scsicmd->sense_buffer, sk,
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index f915e3df57a9..1660f46dc08b 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -2325,8 +2325,8 @@ static unsigned int ata_msense_control_ata_feature(struct ata_device *dev,
 	 */
 	put_unaligned_be16(ATA_FEATURE_SUB_MPAGE_LEN - 4, &buf[2]);
 
-	if (dev->flags & ATA_DFLAG_CDL)
-		buf[4] = 0x02; /* Support T2A and T2B pages */
+	if (dev->flags & ATA_DFLAG_CDL_ENABLED)
+		buf[4] = 0x02; /* T2A and T2B pages enabled */
 	else
 		buf[4] = 0;
 
@@ -3734,12 +3734,11 @@ static int ata_mselect_control_spg0(struct ata_queued_cmd *qc,
 }
 
 /*
- * Translate MODE SELECT control mode page, sub-pages f2h (ATA feature mode
+ * Translate MODE SELECT control mode page, sub-page f2h (ATA feature mode
  * page) into a SET FEATURES command.
  */
-static unsigned int ata_mselect_control_ata_feature(struct ata_queued_cmd *qc,
-						    const u8 *buf, int len,
-						    u16 *fp)
+static int ata_mselect_control_ata_feature(struct ata_queued_cmd *qc,
+					   const u8 *buf, int len, u16 *fp)
 {
 	struct ata_device *dev = qc->dev;
 	struct ata_taskfile *tf = &qc->tf;
@@ -3757,17 +3756,27 @@ static unsigned int ata_mselect_control_ata_feature(struct ata_queued_cmd *qc,
 	/* Check cdl_ctrl */
 	switch (buf[0] & 0x03) {
 	case 0:
-		/* Disable CDL */
+		/* Disable CDL if it is enabled */
+		if (!(dev->flags & ATA_DFLAG_CDL_ENABLED))
+			return 0;
+		ata_dev_dbg(dev, "Disabling CDL\n");
 		cdl_action = 0;
 		dev->flags &= ~ATA_DFLAG_CDL_ENABLED;
 		break;
 	case 0x02:
-		/* Enable CDL T2A/T2B: NCQ priority must be disabled */
+		/*
+		 * Enable CDL if not already enabled. Since this is mutually
+		 * exclusive with NCQ priority, allow this only if NCQ priority
+		 * is disabled.
+		 */
+		if (dev->flags & ATA_DFLAG_CDL_ENABLED)
+			return 0;
 		if (dev->flags & ATA_DFLAG_NCQ_PRIO_ENABLED) {
 			ata_dev_err(dev,
 				"NCQ priority must be disabled to enable CDL\n");
 			return -EINVAL;
 		}
+		ata_dev_dbg(dev, "Enabling CDL\n");
 		cdl_action = 1;
 		dev->flags |= ATA_DFLAG_CDL_ENABLED;
 		break;
diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c
index 67f277e1c3bf..5a46c066abc3 100644
--- a/drivers/ata/libata-sff.c
+++ b/drivers/ata/libata-sff.c
@@ -601,7 +601,7 @@ static void ata_pio_sector(struct ata_queued_cmd *qc)
 {
 	struct ata_port *ap = qc->ap;
 	struct page *page;
-	unsigned int offset;
+	unsigned int offset, count;
 
 	if (!qc->cursg) {
 		qc->curbytes = qc->nbytes;
@@ -617,25 +617,27 @@ static void ata_pio_sector(struct ata_queued_cmd *qc)
 	page = nth_page(page, (offset >> PAGE_SHIFT));
 	offset %= PAGE_SIZE;
 
-	trace_ata_sff_pio_transfer_data(qc, offset, qc->sect_size);
+	/* don't overrun current sg */
+	count = min(qc->cursg->length - qc->cursg_ofs, qc->sect_size);
+
+	trace_ata_sff_pio_transfer_data(qc, offset, count);
 
 	/*
 	 * Split the transfer when it splits a page boundary.  Note that the
 	 * split still has to be dword aligned like all ATA data transfers.
 	 */
 	WARN_ON_ONCE(offset % 4);
-	if (offset + qc->sect_size > PAGE_SIZE) {
+	if (offset + count > PAGE_SIZE) {
 		unsigned int split_len = PAGE_SIZE - offset;
 
 		ata_pio_xfer(qc, page, offset, split_len);
-		ata_pio_xfer(qc, nth_page(page, 1), 0,
-			     qc->sect_size - split_len);
+		ata_pio_xfer(qc, nth_page(page, 1), 0, count - split_len);
 	} else {
-		ata_pio_xfer(qc, page, offset, qc->sect_size);
+		ata_pio_xfer(qc, page, offset, count);
 	}
 
-	qc->curbytes += qc->sect_size;
-	qc->cursg_ofs += qc->sect_size;
+	qc->curbytes += count;
+	qc->cursg_ofs += count;
 
 	if (qc->cursg_ofs == qc->cursg->length) {
 		qc->cursg = sg_next(qc->cursg);
diff --git a/drivers/ata/pata_cs5536.c b/drivers/ata/pata_cs5536.c
index b811efd2cc34..73e81e160c91 100644
--- a/drivers/ata/pata_cs5536.c
+++ b/drivers/ata/pata_cs5536.c
@@ -27,7 +27,7 @@
 #include <scsi/scsi_host.h>
 #include <linux/dmi.h>
 
-#ifdef CONFIG_X86_32
+#if defined(CONFIG_X86) && defined(CONFIG_X86_32)
 #include <asm/msr.h>
 static int use_msr;
 module_param_named(msr, use_msr, int, 0644);
diff --git a/drivers/ata/pata_pxa.c b/drivers/ata/pata_pxa.c
index 538bd3423d85..1bdcd6ee741d 100644
--- a/drivers/ata/pata_pxa.c
+++ b/drivers/ata/pata_pxa.c
@@ -223,10 +223,16 @@ static int pxa_ata_probe(struct platform_device *pdev)
 
 	ap->ioaddr.cmd_addr	= devm_ioremap(&pdev->dev, cmd_res->start,
 						resource_size(cmd_res));
+	if (!ap->ioaddr.cmd_addr)
+		return -ENOMEM;
 	ap->ioaddr.ctl_addr	= devm_ioremap(&pdev->dev, ctl_res->start,
 						resource_size(ctl_res));
+	if (!ap->ioaddr.ctl_addr)
+		return -ENOMEM;
 	ap->ioaddr.bmdma_addr	= devm_ioremap(&pdev->dev, dma_res->start,
 						resource_size(dma_res));
+	if (!ap->ioaddr.bmdma_addr)
+		return -ENOMEM;
 
 	/*
 	 * Adjust register offsets
diff --git a/drivers/ata/pata_via.c b/drivers/ata/pata_via.c
index 696b99720dcb..bb80e7800dcb 100644
--- a/drivers/ata/pata_via.c
+++ b/drivers/ata/pata_via.c
@@ -201,11 +201,9 @@ static int via_cable_detect(struct ata_port *ap) {
 	   two drives */
 	if (ata66 & (0x10100000 >> (16 * ap->port_no)))
 		return ATA_CBL_PATA80;
+
 	/* Check with ACPI so we can spot BIOS reported SATA bridges */
-	if (ata_acpi_init_gtm(ap) &&
-	    ata_acpi_cbl_80wire(ap, ata_acpi_init_gtm(ap)))
-		return ATA_CBL_PATA80;
-	return ATA_CBL_PATA40;
+	return ata_acpi_cbl_pata_type(ap);
 }
 
 static int via_pre_reset(struct ata_link *link, unsigned long deadline)
@@ -368,7 +366,8 @@ static unsigned int via_mode_filter(struct ata_device *dev, unsigned int mask)
 	}
 
 	if (dev->class == ATA_DEV_ATAPI &&
-	    dmi_check_system(no_atapi_dma_dmi_table)) {
+	    (dmi_check_system(no_atapi_dma_dmi_table) ||
+	     config->id == PCI_DEVICE_ID_VIA_6415)) {
 		ata_dev_warn(dev, "controller locks up on ATAPI DMA, forcing PIO\n");
 		mask &= ATA_MASK_PIO;
 	}
diff --git a/drivers/ata/sata_sx4.c b/drivers/ata/sata_sx4.c
index a482741eb181..c3042eca6332 100644
--- a/drivers/ata/sata_sx4.c
+++ b/drivers/ata/sata_sx4.c
@@ -1117,9 +1117,14 @@ static int pdc20621_prog_dimm0(struct ata_host *host)
 	mmio += PDC_CHIP0_OFS;
 
 	for (i = 0; i < ARRAY_SIZE(pdc_i2c_read_data); i++)
-		pdc20621_i2c_read(host, PDC_DIMM0_SPD_DEV_ADDRESS,
-				  pdc_i2c_read_data[i].reg,
-				  &spd0[pdc_i2c_read_data[i].ofs]);
+		if (!pdc20621_i2c_read(host, PDC_DIMM0_SPD_DEV_ADDRESS,
+				       pdc_i2c_read_data[i].reg,
+				       &spd0[pdc_i2c_read_data[i].ofs])) {
+			dev_err(host->dev,
+				"Failed in i2c read at index %d: device=%#x, reg=%#x\n",
+				i, PDC_DIMM0_SPD_DEV_ADDRESS, pdc_i2c_read_data[i].reg);
+			return -EIO;
+		}
 
 	data |= (spd0[4] - 8) | ((spd0[21] != 0) << 3) | ((spd0[3]-11) << 4);
 	data |= ((spd0[17] / 4) << 6) | ((spd0[5] / 2) << 7) |
@@ -1284,6 +1289,8 @@ static unsigned int pdc20621_dimm_init(struct ata_host *host)
 
 	/* Programming DIMM0 Module Control Register (index_CID0:80h) */
 	size = pdc20621_prog_dimm0(host);
+	if (size < 0)
+		return size;
 	dev_dbg(host->dev, "Local DIMM Size = %dMB\n", size);
 
 	/* Programming DIMM Module Global Control Register (index_CID0:88h) */
diff --git a/drivers/atm/atmtcp.c b/drivers/atm/atmtcp.c
index d4aa0f353b6c..eeae160c898d 100644
--- a/drivers/atm/atmtcp.c
+++ b/drivers/atm/atmtcp.c
@@ -288,7 +288,9 @@ static int atmtcp_c_send(struct atm_vcc *vcc,struct sk_buff *skb)
 	struct sk_buff *new_skb;
 	int result = 0;
 
-	if (!skb->len) return 0;
+	if (skb->len < sizeof(struct atmtcp_hdr))
+		goto done;
+
 	dev = vcc->dev_data;
 	hdr = (struct atmtcp_hdr *) skb->data;
 	if (hdr->length == ATMTCP_HDR_MAGIC) {
diff --git a/drivers/atm/idt77252.c b/drivers/atm/idt77252.c
index a876024d8a05..63d41320cd5c 100644
--- a/drivers/atm/idt77252.c
+++ b/drivers/atm/idt77252.c
@@ -852,6 +852,8 @@ queue_skb(struct idt77252_dev *card, struct vc_map *vc,
 
 	IDT77252_PRV_PADDR(skb) = dma_map_single(&card->pcidev->dev, skb->data,
 						 skb->len, DMA_TO_DEVICE);
+	if (dma_mapping_error(&card->pcidev->dev, IDT77252_PRV_PADDR(skb)))
+		return -ENOMEM;
 
 	error = -EINVAL;
 
@@ -1857,6 +1859,8 @@ add_rx_skb(struct idt77252_dev *card, int queue,
 		paddr = dma_map_single(&card->pcidev->dev, skb->data,
 				       skb_end_pointer(skb) - skb->data,
 				       DMA_FROM_DEVICE);
+		if (dma_mapping_error(&card->pcidev->dev, paddr))
+			goto outpoolrm;
 		IDT77252_PRV_PADDR(skb) = paddr;
 
 		if (push_rx_skb(card, skb, queue)) {
@@ -1871,6 +1875,7 @@ outunmap:
 	dma_unmap_single(&card->pcidev->dev, IDT77252_PRV_PADDR(skb),
 			 skb_end_pointer(skb) - skb->data, DMA_FROM_DEVICE);
 
+outpoolrm:
 	handle = IDT77252_PRV_POOL(skb);
 	card->sbpool[POOL_QUEUE(handle)].skb[POOL_INDEX(handle)] = NULL;
 
diff --git a/drivers/auxdisplay/Kconfig b/drivers/auxdisplay/Kconfig
index 21545ffba065..2a9bb31633a7 100644
--- a/drivers/auxdisplay/Kconfig
+++ b/drivers/auxdisplay/Kconfig
@@ -503,6 +503,7 @@ config HT16K33
 config MAX6959
 	tristate "Maxim MAX6958/6959 7-segment LED controller"
 	depends on I2C
+	select BITREVERSE
 	select REGMAP_I2C
 	select LINEDISP
 	help
diff --git a/drivers/auxdisplay/charlcd.c b/drivers/auxdisplay/charlcd.c
index 19b619376d48..09020bb8ad15 100644
--- a/drivers/auxdisplay/charlcd.c
+++ b/drivers/auxdisplay/charlcd.c
@@ -595,18 +595,19 @@ static int charlcd_init(struct charlcd *lcd)
 	return 0;
 }
 
-struct charlcd *charlcd_alloc(void)
+struct charlcd *charlcd_alloc(unsigned int drvdata_size)
 {
 	struct charlcd_priv *priv;
 	struct charlcd *lcd;
 
-	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+	priv = kzalloc(sizeof(*priv) + drvdata_size, GFP_KERNEL);
 	if (!priv)
 		return NULL;
 
 	priv->esc_seq.len = -1;
 
 	lcd = &priv->lcd;
+	lcd->drvdata = priv->drvdata;
 
 	return lcd;
 }
diff --git a/drivers/auxdisplay/charlcd.h b/drivers/auxdisplay/charlcd.h
index 4d4287209d04..d10b89740bca 100644
--- a/drivers/auxdisplay/charlcd.h
+++ b/drivers/auxdisplay/charlcd.h
@@ -51,7 +51,7 @@ struct charlcd {
 		unsigned long y;
 	} addr;
 
-	void *drvdata;
+	void *drvdata;			/* Set by charlcd_alloc() */
 };
 
 /**
@@ -95,7 +95,8 @@ struct charlcd_ops {
 };
 
 void charlcd_backlight(struct charlcd *lcd, enum charlcd_onoff on);
-struct charlcd *charlcd_alloc(void);
+
+struct charlcd *charlcd_alloc(unsigned int drvdata_size);
 void charlcd_free(struct charlcd *lcd);
 
 int charlcd_register(struct charlcd *lcd);
diff --git a/drivers/auxdisplay/hd44780.c b/drivers/auxdisplay/hd44780.c
index 025dc6855cb2..9428f951c9bf 100644
--- a/drivers/auxdisplay/hd44780.c
+++ b/drivers/auxdisplay/hd44780.c
@@ -226,7 +226,7 @@ static int hd44780_probe(struct platform_device *pdev)
 	if (!hdc)
 		return -ENOMEM;
 
-	lcd = charlcd_alloc();
+	lcd = charlcd_alloc(0);
 	if (!lcd)
 		goto fail1;
 
@@ -313,7 +313,7 @@ static int hd44780_probe(struct platform_device *pdev)
 fail3:
 	kfree(hd);
 fail2:
-	kfree(lcd);
+	charlcd_free(lcd);
 fail1:
 	kfree(hdc);
 	return ret;
@@ -328,7 +328,7 @@ static void hd44780_remove(struct platform_device *pdev)
 	kfree(hdc->hd44780);
 	kfree(lcd->drvdata);
 
-	kfree(lcd);
+	charlcd_free(lcd);
 }
 
 static const struct of_device_id hd44780_of_match[] = {
diff --git a/drivers/auxdisplay/lcd2s.c b/drivers/auxdisplay/lcd2s.c
index 6422be0dfe20..0ecf6a9469f2 100644
--- a/drivers/auxdisplay/lcd2s.c
+++ b/drivers/auxdisplay/lcd2s.c
@@ -307,7 +307,7 @@ static int lcd2s_i2c_probe(struct i2c_client *i2c)
 	if (err < 0)
 		return err;
 
-	lcd = charlcd_alloc();
+	lcd = charlcd_alloc(0);
 	if (!lcd)
 		return -ENOMEM;
 
diff --git a/drivers/auxdisplay/panel.c b/drivers/auxdisplay/panel.c
index a731f28455b4..4da142692d55 100644
--- a/drivers/auxdisplay/panel.c
+++ b/drivers/auxdisplay/panel.c
@@ -835,7 +835,7 @@ static void lcd_init(void)
 	if (!hdc)
 		return;
 
-	charlcd = charlcd_alloc();
+	charlcd = charlcd_alloc(0);
 	if (!charlcd) {
 		kfree(hdc);
 		return;
@@ -1664,7 +1664,7 @@ err_lcd_unreg:
 	if (lcd.enabled)
 		charlcd_unregister(lcd.charlcd);
 err_unreg_device:
-	kfree(lcd.charlcd);
+	charlcd_free(lcd.charlcd);
 	lcd.charlcd = NULL;
 	parport_unregister_device(pprt);
 	pprt = NULL;
@@ -1692,7 +1692,7 @@ static void panel_detach(struct parport *port)
 		charlcd_unregister(lcd.charlcd);
 		lcd.initialized = false;
 		kfree(lcd.charlcd->drvdata);
-		kfree(lcd.charlcd);
+		charlcd_free(lcd.charlcd);
 		lcd.charlcd = NULL;
 	}
 
diff --git a/drivers/base/base.h b/drivers/base/base.h
index 8cf04a557bdb..c4ffd0995043 100644
--- a/drivers/base/base.h
+++ b/drivers/base/base.h
@@ -73,6 +73,7 @@ static inline void subsys_put(struct subsys_private *sp)
 		kset_put(&sp->subsys);
 }
 
+struct subsys_private *bus_to_subsys(const struct bus_type *bus);
 struct subsys_private *class_to_subsys(const struct class *class);
 
 struct driver_private {
@@ -179,6 +180,22 @@ int driver_add_groups(const struct device_driver *drv, const struct attribute_gr
 void driver_remove_groups(const struct device_driver *drv, const struct attribute_group **groups);
 void device_driver_detach(struct device *dev);
 
+static inline void device_set_driver(struct device *dev, const struct device_driver *drv)
+{
+	/*
+	 * Majority (all?) read accesses to dev->driver happens either
+	 * while holding device lock or in bus/driver code that is only
+	 * invoked when the device is bound to a driver and there is no
+	 * concern of the pointer being changed while it is being read.
+	 * However when reading device's uevent file we read driver pointer
+	 * without taking device lock (so we do not block there for
+	 * arbitrary amount of time). We use WRITE_ONCE() here to prevent
+	 * tearing so that READ_ONCE() can safely be used in uevent code.
+	 */
+	// FIXME - this cast should not be needed "soon"
+	WRITE_ONCE(dev->driver, (struct device_driver *)drv);
+}
+
 int devres_release_all(struct device *dev);
 void device_block_probing(void);
 void device_unblock_probing(void);
diff --git a/drivers/base/bus.c b/drivers/base/bus.c
index 657c93c38b0d..eaf38a6f6091 100644
--- a/drivers/base/bus.c
+++ b/drivers/base/bus.c
@@ -57,7 +57,7 @@ static int __must_check bus_rescan_devices_helper(struct device *dev,
  * NULL.  A call to subsys_put() must be done when finished with the pointer in
  * order for it to be properly freed.
  */
-static struct subsys_private *bus_to_subsys(const struct bus_type *bus)
+struct subsys_private *bus_to_subsys(const struct bus_type *bus)
 {
 	struct subsys_private *sp = NULL;
 	struct kobject *kobj;
diff --git a/drivers/base/class.c b/drivers/base/class.c
index cb5359235c70..ce460e1ab137 100644
--- a/drivers/base/class.c
+++ b/drivers/base/class.c
@@ -323,8 +323,12 @@ void class_dev_iter_init(struct class_dev_iter *iter, const struct class *class,
 	struct subsys_private *sp = class_to_subsys(class);
 	struct klist_node *start_knode = NULL;
 
-	if (!sp)
+	memset(iter, 0, sizeof(*iter));
+	if (!sp) {
+		pr_crit("%s: class %p was not registered yet\n",
+			__func__, class);
 		return;
+	}
 
 	if (start)
 		start_knode = &start->p->knode_class;
@@ -351,6 +355,9 @@ struct device *class_dev_iter_next(struct class_dev_iter *iter)
 	struct klist_node *knode;
 	struct device *dev;
 
+	if (!iter->sp)
+		return NULL;
+
 	while (1) {
 		knode = klist_next(&iter->ki);
 		if (!knode)
diff --git a/drivers/base/core.c b/drivers/base/core.c
index d922cefc1e66..ba9b4cbef9e0 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -2079,6 +2079,7 @@ static bool __fw_devlink_relax_cycles(struct fwnode_handle *con_handle,
 out:
 	sup_handle->flags &= ~FWNODE_FLAG_VISITED;
 	put_device(sup_dev);
+	put_device(con_dev);
 	put_device(par_dev);
 	return ret;
 }
@@ -2623,6 +2624,35 @@ static const char *dev_uevent_name(const struct kobject *kobj)
 	return NULL;
 }
 
+/*
+ * Try filling "DRIVER=<name>" uevent variable for a device. Because this
+ * function may race with binding and unbinding the device from a driver,
+ * we need to be careful. Binding is generally safe, at worst we miss the
+ * fact that the device is already bound to a driver (but the driver
+ * information that is delivered through uevents is best-effort, it may
+ * become obsolete as soon as it is generated anyways). Unbinding is more
+ * risky as driver pointer is transitioning to NULL, so READ_ONCE() should
+ * be used to make sure we are dealing with the same pointer, and to
+ * ensure that driver structure is not going to disappear from under us
+ * we take bus' drivers klist lock. The assumption that only registered
+ * driver can be bound to a device, and to unregister a driver bus code
+ * will take the same lock.
+ */
+static void dev_driver_uevent(const struct device *dev, struct kobj_uevent_env *env)
+{
+	struct subsys_private *sp = bus_to_subsys(dev->bus);
+
+	if (sp) {
+		scoped_guard(spinlock, &sp->klist_drivers.k_lock) {
+			struct device_driver *drv = READ_ONCE(dev->driver);
+			if (drv)
+				add_uevent_var(env, "DRIVER=%s", drv->name);
+		}
+
+		subsys_put(sp);
+	}
+}
+
 static int dev_uevent(const struct kobject *kobj, struct kobj_uevent_env *env)
 {
 	const struct device *dev = kobj_to_dev(kobj);
@@ -2654,8 +2684,8 @@ static int dev_uevent(const struct kobject *kobj, struct kobj_uevent_env *env)
 	if (dev->type && dev->type->name)
 		add_uevent_var(env, "DEVTYPE=%s", dev->type->name);
 
-	if (dev->driver)
-		add_uevent_var(env, "DRIVER=%s", dev->driver->name);
+	/* Add "DRIVER=%s" variable if the device is bound to a driver */
+	dev_driver_uevent(dev, env);
 
 	/* Add common DT information about the device */
 	of_device_uevent(dev, env);
@@ -2725,11 +2755,8 @@ static ssize_t uevent_show(struct device *dev, struct device_attribute *attr,
 	if (!env)
 		return -ENOMEM;
 
-	/* Synchronize with really_probe() */
-	device_lock(dev);
 	/* let the kset specific function add its keys */
 	retval = kset->uevent_ops->uevent(&dev->kobj, env);
-	device_unlock(dev);
 	if (retval)
 		goto out;
 
@@ -3699,7 +3726,7 @@ done:
 	device_pm_remove(dev);
 	dpm_sysfs_remove(dev);
  DPMError:
-	dev->driver = NULL;
+	device_set_driver(dev, NULL);
 	bus_remove_device(dev);
  BusError:
 	device_remove_attrs(dev);
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index fdaa24bb641a..02870e70ed59 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -599,6 +599,8 @@ CPU_SHOW_VULN_FALLBACK(retbleed);
 CPU_SHOW_VULN_FALLBACK(spec_rstack_overflow);
 CPU_SHOW_VULN_FALLBACK(gds);
 CPU_SHOW_VULN_FALLBACK(reg_file_data_sampling);
+CPU_SHOW_VULN_FALLBACK(indirect_target_selection);
+CPU_SHOW_VULN_FALLBACK(tsa);
 
 static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL);
 static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL);
@@ -614,6 +616,8 @@ static DEVICE_ATTR(retbleed, 0444, cpu_show_retbleed, NULL);
 static DEVICE_ATTR(spec_rstack_overflow, 0444, cpu_show_spec_rstack_overflow, NULL);
 static DEVICE_ATTR(gather_data_sampling, 0444, cpu_show_gds, NULL);
 static DEVICE_ATTR(reg_file_data_sampling, 0444, cpu_show_reg_file_data_sampling, NULL);
+static DEVICE_ATTR(indirect_target_selection, 0444, cpu_show_indirect_target_selection, NULL);
+static DEVICE_ATTR(tsa, 0444, cpu_show_tsa, NULL);
 
 static struct attribute *cpu_root_vulnerabilities_attrs[] = {
 	&dev_attr_meltdown.attr,
@@ -630,6 +634,8 @@ static struct attribute *cpu_root_vulnerabilities_attrs[] = {
 	&dev_attr_spec_rstack_overflow.attr,
 	&dev_attr_gather_data_sampling.attr,
 	&dev_attr_reg_file_data_sampling.attr,
+	&dev_attr_indirect_target_selection.attr,
+	&dev_attr_tsa.attr,
 	NULL
 };
 
diff --git a/drivers/base/dd.c b/drivers/base/dd.c
index f0e4b4aba885..b526e0e0f52d 100644
--- a/drivers/base/dd.c
+++ b/drivers/base/dd.c
@@ -550,7 +550,7 @@ static void device_unbind_cleanup(struct device *dev)
 	arch_teardown_dma_ops(dev);
 	kfree(dev->dma_range_map);
 	dev->dma_range_map = NULL;
-	dev->driver = NULL;
+	device_set_driver(dev, NULL);
 	dev_set_drvdata(dev, NULL);
 	if (dev->pm_domain && dev->pm_domain->dismiss)
 		dev->pm_domain->dismiss(dev);
@@ -629,8 +629,7 @@ static int really_probe(struct device *dev, const struct device_driver *drv)
 	}
 
 re_probe:
-	// FIXME - this cast should not be needed "soon"
-	dev->driver = (struct device_driver *)drv;
+	device_set_driver(dev, drv);
 
 	/* If using pinctrl, bind pins now before probing */
 	ret = pinctrl_bind_pins(dev);
@@ -1014,7 +1013,7 @@ static int __device_attach(struct device *dev, bool allow_async)
 		if (ret == 0)
 			ret = 1;
 		else {
-			dev->driver = NULL;
+			device_set_driver(dev, NULL);
 			ret = 0;
 		}
 	} else {
diff --git a/drivers/base/devres.c b/drivers/base/devres.c
index 2152eec0c135..68224f2f83ff 100644
--- a/drivers/base/devres.c
+++ b/drivers/base/devres.c
@@ -687,6 +687,13 @@ int devres_release_group(struct device *dev, void *id)
 		spin_unlock_irqrestore(&dev->devres_lock, flags);
 
 		release_nodes(dev, &todo);
+	} else if (list_empty(&dev->devres_head)) {
+		/*
+		 * dev is probably dying via devres_release_all(): groups
+		 * have already been removed and are on the process of
+		 * being released - don't touch and don't warn.
+		 */
+		spin_unlock_irqrestore(&dev->devres_lock, flags);
 	} else {
 		WARN_ON(1);
 		spin_unlock_irqrestore(&dev->devres_lock, flags);
diff --git a/drivers/base/module.c b/drivers/base/module.c
index 5bc71bea883a..218aaa096455 100644
--- a/drivers/base/module.c
+++ b/drivers/base/module.c
@@ -42,16 +42,13 @@ int module_add_driver(struct module *mod, const struct device_driver *drv)
 	if (mod)
 		mk = &mod->mkobj;
 	else if (drv->mod_name) {
-		struct kobject *mkobj;
-
-		/* Lookup built-in module entry in /sys/modules */
-		mkobj = kset_find_obj(module_kset, drv->mod_name);
-		if (mkobj) {
-			mk = container_of(mkobj, struct module_kobject, kobj);
+		/* Lookup or create built-in module entry in /sys/modules */
+		mk = lookup_or_create_module_kobject(drv->mod_name);
+		if (mk) {
 			/* remember our module structure */
 			drv->p->mkobj = mk;
-			/* kset_find_obj took a reference */
-			kobject_put(mkobj);
+			/* lookup_or_create_module_kobject took a reference */
+			kobject_put(&mk->kobj);
 		}
 	}
 
diff --git a/drivers/base/platform-msi.c b/drivers/base/platform-msi.c
index 0e60dd650b5e..70db08f3ac6f 100644
--- a/drivers/base/platform-msi.c
+++ b/drivers/base/platform-msi.c
@@ -95,5 +95,6 @@ EXPORT_SYMBOL_GPL(platform_device_msi_init_and_alloc_irqs);
 void platform_device_msi_free_irqs_all(struct device *dev)
 {
 	msi_domain_free_irqs_all(dev, MSI_DEFAULT_DOMAIN);
+	msi_remove_device_irq_domain(dev, MSI_DEFAULT_DOMAIN);
 }
 EXPORT_SYMBOL_GPL(platform_device_msi_free_irqs_all);
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index 4a67e83300e1..faf4cdec23f0 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -913,6 +913,11 @@ static void device_resume(struct device *dev, pm_message_t state, bool async)
 	if (dev->power.syscore)
 		goto Complete;
 
+	if (!dev->power.is_suspended)
+		goto Complete;
+
+	dev->power.is_suspended = false;
+
 	if (dev->power.direct_complete) {
 		/* Match the pm_runtime_disable() in __device_suspend(). */
 		pm_runtime_enable(dev);
@@ -931,9 +936,6 @@ static void device_resume(struct device *dev, pm_message_t state, bool async)
 	 */
 	dev->power.is_prepared = false;
 
-	if (!dev->power.is_suspended)
-		goto Unlock;
-
 	if (dev->pm_domain) {
 		info = "power domain ";
 		callback = pm_op(&dev->pm_domain->ops, state);
@@ -971,9 +973,7 @@ static void device_resume(struct device *dev, pm_message_t state, bool async)
 
  End:
 	error = dpm_run_callback(callback, dev, state, info);
-	dev->power.is_suspended = false;
 
- Unlock:
 	device_unlock(dev);
 	dpm_watchdog_clear(&wd);
 
@@ -1254,14 +1254,13 @@ Skip:
 	dev->power.is_noirq_suspended = true;
 
 	/*
-	 * Skipping the resume of devices that were in use right before the
-	 * system suspend (as indicated by their PM-runtime usage counters)
-	 * would be suboptimal.  Also resume them if doing that is not allowed
-	 * to be skipped.
+	 * Devices must be resumed unless they are explicitly allowed to be left
+	 * in suspend, but even in that case skipping the resume of devices that
+	 * were in use right before the system suspend (as indicated by their
+	 * runtime PM usage counters and child counters) would be suboptimal.
 	 */
-	if (atomic_read(&dev->power.usage_count) > 1 ||
-	    !(dev_pm_test_driver_flags(dev, DPM_FLAG_MAY_SKIP_RESUME) &&
-	      dev->power.may_skip_resume))
+	if (!(dev_pm_test_driver_flags(dev, DPM_FLAG_MAY_SKIP_RESUME) &&
+	      dev->power.may_skip_resume) || !pm_runtime_need_not_resume(dev))
 		dev->power.must_resume = true;
 
 	if (dev->power.must_resume)
@@ -1628,6 +1627,7 @@ static int device_suspend(struct device *dev, pm_message_t state, bool async)
 			pm_runtime_disable(dev);
 			if (pm_runtime_status_suspended(dev)) {
 				pm_dev_dbg(dev, state, "direct-complete ");
+				dev->power.is_suspended = true;
 				goto Complete;
 			}
 
diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index 2ee45841486b..317505eab126 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -1003,7 +1003,7 @@ static enum hrtimer_restart  pm_suspend_timer_fn(struct hrtimer *timer)
 	 * If 'expires' is after the current time, we've been called
 	 * too early.
 	 */
-	if (expires > 0 && expires < ktime_get_mono_fast_ns()) {
+	if (expires > 0 && expires <= ktime_get_mono_fast_ns()) {
 		dev->power.timer_expires = 0;
 		rpm_suspend(dev, dev->power.timer_autosuspends ?
 		    (RPM_ASYNC | RPM_AUTO) : RPM_ASYNC);
@@ -1787,6 +1787,11 @@ void pm_runtime_reinit(struct device *dev)
 				pm_runtime_put(dev->parent);
 		}
 	}
+	/*
+	 * Clear power.needs_force_resume in case it has been set by
+	 * pm_runtime_force_suspend() invoked from a driver remove callback.
+	 */
+	dev->power.needs_force_resume = false;
 }
 
 /**
@@ -1874,7 +1879,7 @@ void pm_runtime_drop_link(struct device_link *link)
 	pm_request_idle(link->supplier);
 }
 
-static bool pm_runtime_need_not_resume(struct device *dev)
+bool pm_runtime_need_not_resume(struct device *dev)
 {
 	return atomic_read(&dev->power.usage_count) <= 1 &&
 		(atomic_read(&dev->power.child_count) == 0 ||
diff --git a/drivers/base/regmap/regmap-irq.c b/drivers/base/regmap/regmap-irq.c
index 6981e5f974e9..ff7d0b14a646 100644
--- a/drivers/base/regmap/regmap-irq.c
+++ b/drivers/base/regmap/regmap-irq.c
@@ -909,6 +909,7 @@ err_alloc:
 	kfree(d->wake_buf);
 	kfree(d->mask_buf_def);
 	kfree(d->mask_buf);
+	kfree(d->main_status_buf);
 	kfree(d->status_buf);
 	kfree(d->status_reg_buf);
 	if (d->config_buf) {
@@ -984,6 +985,7 @@ void regmap_del_irq_chip(int irq, struct regmap_irq_chip_data *d)
 	kfree(d->wake_buf);
 	kfree(d->mask_buf_def);
 	kfree(d->mask_buf);
+	kfree(d->main_status_buf);
 	kfree(d->status_reg_buf);
 	kfree(d->status_buf);
 	if (d->config_buf) {
diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c
index 5962ea1230a1..de4e2f3db942 100644
--- a/drivers/base/regmap/regmap.c
+++ b/drivers/base/regmap/regmap.c
@@ -1174,6 +1174,8 @@ err_name:
 err_map:
 	kfree(map);
 err:
+	if (bus && bus->free_on_exit)
+		kfree(bus);
 	return ERR_PTR(ret);
 }
 EXPORT_SYMBOL_GPL(__regmap_init);
diff --git a/drivers/base/swnode.c b/drivers/base/swnode.c
index eb6eb25b343b..53b3f0061ad1 100644
--- a/drivers/base/swnode.c
+++ b/drivers/base/swnode.c
@@ -529,7 +529,7 @@ software_node_get_reference_args(const struct fwnode_handle *fwnode,
 	if (prop->is_inline)
 		return -EINVAL;
 
-	if (index * sizeof(*ref) >= prop->length)
+	if ((index + 1) * sizeof(*ref) > prop->length)
 		return -ENOENT;
 
 	ref_array = prop->pointer;
diff --git a/drivers/block/aoe/aoe.h b/drivers/block/aoe/aoe.h
index 749ae1246f4c..d35caa3c69e1 100644
--- a/drivers/block/aoe/aoe.h
+++ b/drivers/block/aoe/aoe.h
@@ -80,6 +80,7 @@ enum {
 	DEVFL_NEWSIZE = (1<<6),	/* need to update dev size in block layer */
 	DEVFL_FREEING = (1<<7),	/* set when device is being cleaned up */
 	DEVFL_FREED = (1<<8),	/* device has been cleaned up */
+	DEVFL_DEAD = (1<<9),	/* device has timed out of aoe_deadsecs */
 };
 
 enum {
diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c
index 92b06d1de4cc..6c94cfd1c480 100644
--- a/drivers/block/aoe/aoecmd.c
+++ b/drivers/block/aoe/aoecmd.c
@@ -754,7 +754,7 @@ rexmit_timer(struct timer_list *timer)
 
 	utgts = count_targets(d, NULL);
 
-	if (d->flags & DEVFL_TKILL) {
+	if (d->flags & (DEVFL_TKILL | DEVFL_DEAD)) {
 		spin_unlock_irqrestore(&d->lock, flags);
 		return;
 	}
@@ -786,7 +786,8 @@ rexmit_timer(struct timer_list *timer)
 			 * to clean up.
 			 */
 			list_splice(&flist, &d->factive[0]);
-			aoedev_downdev(d);
+			d->flags |= DEVFL_DEAD;
+			queue_work(aoe_wq, &d->work);
 			goto out;
 		}
 
@@ -898,6 +899,9 @@ aoecmd_sleepwork(struct work_struct *work)
 {
 	struct aoedev *d = container_of(work, struct aoedev, work);
 
+	if (d->flags & DEVFL_DEAD)
+		aoedev_downdev(d);
+
 	if (d->flags & DEVFL_GDALLOC)
 		aoeblk_gdalloc(d);
 
diff --git a/drivers/block/aoe/aoedev.c b/drivers/block/aoe/aoedev.c
index 3523dd82d7a0..4240e11adfb7 100644
--- a/drivers/block/aoe/aoedev.c
+++ b/drivers/block/aoe/aoedev.c
@@ -198,9 +198,13 @@ aoedev_downdev(struct aoedev *d)
 {
 	struct aoetgt *t, **tt, **te;
 	struct list_head *head, *pos, *nx;
+	struct request *rq, *rqnext;
 	int i;
+	unsigned long flags;
 
-	d->flags &= ~DEVFL_UP;
+	spin_lock_irqsave(&d->lock, flags);
+	d->flags &= ~(DEVFL_UP | DEVFL_DEAD);
+	spin_unlock_irqrestore(&d->lock, flags);
 
 	/* clean out active and to-be-retransmitted buffers */
 	for (i = 0; i < NFACTIVE; i++) {
@@ -223,6 +227,13 @@ aoedev_downdev(struct aoedev *d)
 	/* clean out the in-process request (if any) */
 	aoe_failip(d);
 
+	/* clean out any queued block requests */
+	list_for_each_entry_safe(rq, rqnext, &d->rq_list, queuelist) {
+		list_del_init(&rq->queuelist);
+		blk_mq_start_request(rq);
+		blk_mq_end_request(rq, BLK_STS_IOERR);
+	}
+
 	/* fast fail all pending I/O */
 	if (d->blkq) {
 		/* UP is cleared, freeze+quiesce to insure all are errored */
diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index 292f127cae0a..02fa8106ef54 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -224,19 +224,22 @@ out:
 
 static void brd_do_discard(struct brd_device *brd, sector_t sector, u32 size)
 {
-	sector_t aligned_sector = (sector + PAGE_SECTORS) & ~PAGE_SECTORS;
+	sector_t aligned_sector = round_up(sector, PAGE_SECTORS);
+	sector_t aligned_end = round_down(
+			sector + (size >> SECTOR_SHIFT), PAGE_SECTORS);
 	struct page *page;
 
-	size -= (aligned_sector - sector) * SECTOR_SIZE;
+	if (aligned_end <= aligned_sector)
+		return;
+
 	xa_lock(&brd->brd_pages);
-	while (size >= PAGE_SIZE && aligned_sector < rd_size * 2) {
+	while (aligned_sector < aligned_end && aligned_sector < rd_size * 2) {
 		page = __xa_erase(&brd->brd_pages, aligned_sector >> PAGE_SECTORS_SHIFT);
 		if (page) {
 			__free_page(page);
 			brd->brd_nr_pages--;
 		}
 		aligned_sector += PAGE_SECTORS;
-		size -= PAGE_SIZE;
 	}
 	xa_unlock(&brd->brd_pages);
 }
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index 0c9f54197768..ac18d36b0ea8 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -2500,7 +2500,11 @@ static int handle_write_conflicts(struct drbd_device *device,
 			peer_req->w.cb = superseded ? e_send_superseded :
 						   e_send_retry_write;
 			list_add_tail(&peer_req->w.list, &device->done_ee);
-			queue_work(connection->ack_sender, &peer_req->peer_device->send_acks_work);
+			/* put is in drbd_send_acks_wf() */
+			kref_get(&device->kref);
+			if (!queue_work(connection->ack_sender,
+					&peer_req->peer_device->send_acks_work))
+				kref_put(&device->kref, drbd_destroy_device);
 
 			err = -ENOENT;
 			goto out;
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 86cc3b19faae..db9b5164ccca 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -233,72 +233,6 @@ static void loop_set_size(struct loop_device *lo, loff_t size)
 		kobject_uevent(&disk_to_dev(lo->lo_disk)->kobj, KOBJ_CHANGE);
 }
 
-static int lo_write_bvec(struct file *file, struct bio_vec *bvec, loff_t *ppos)
-{
-	struct iov_iter i;
-	ssize_t bw;
-
-	iov_iter_bvec(&i, ITER_SOURCE, bvec, 1, bvec->bv_len);
-
-	bw = vfs_iter_write(file, &i, ppos, 0);
-
-	if (likely(bw ==  bvec->bv_len))
-		return 0;
-
-	printk_ratelimited(KERN_ERR
-		"loop: Write error at byte offset %llu, length %i.\n",
-		(unsigned long long)*ppos, bvec->bv_len);
-	if (bw >= 0)
-		bw = -EIO;
-	return bw;
-}
-
-static int lo_write_simple(struct loop_device *lo, struct request *rq,
-		loff_t pos)
-{
-	struct bio_vec bvec;
-	struct req_iterator iter;
-	int ret = 0;
-
-	rq_for_each_segment(bvec, rq, iter) {
-		ret = lo_write_bvec(lo->lo_backing_file, &bvec, &pos);
-		if (ret < 0)
-			break;
-		cond_resched();
-	}
-
-	return ret;
-}
-
-static int lo_read_simple(struct loop_device *lo, struct request *rq,
-		loff_t pos)
-{
-	struct bio_vec bvec;
-	struct req_iterator iter;
-	struct iov_iter i;
-	ssize_t len;
-
-	rq_for_each_segment(bvec, rq, iter) {
-		iov_iter_bvec(&i, ITER_DEST, &bvec, 1, bvec.bv_len);
-		len = vfs_iter_read(lo->lo_backing_file, &i, &pos, 0);
-		if (len < 0)
-			return len;
-
-		flush_dcache_page(bvec.bv_page);
-
-		if (len != bvec.bv_len) {
-			struct bio *bio;
-
-			__rq_for_each_bio(bio, rq)
-				zero_fill_bio(bio);
-			break;
-		}
-		cond_resched();
-	}
-
-	return 0;
-}
-
 static void loop_clear_limits(struct loop_device *lo, int mode)
 {
 	struct queue_limits lim = queue_limits_start_update(lo->lo_queue);
@@ -357,7 +291,7 @@ static void lo_complete_rq(struct request *rq)
 	struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq);
 	blk_status_t ret = BLK_STS_OK;
 
-	if (!cmd->use_aio || cmd->ret < 0 || cmd->ret == blk_rq_bytes(rq) ||
+	if (cmd->ret < 0 || cmd->ret == blk_rq_bytes(rq) ||
 	    req_op(rq) != REQ_OP_READ) {
 		if (cmd->ret < 0)
 			ret = errno_to_blk_status(cmd->ret);
@@ -373,14 +307,13 @@ static void lo_complete_rq(struct request *rq)
 		cmd->ret = 0;
 		blk_mq_requeue_request(rq, true);
 	} else {
-		if (cmd->use_aio) {
-			struct bio *bio = rq->bio;
+		struct bio *bio = rq->bio;
 
-			while (bio) {
-				zero_fill_bio(bio);
-				bio = bio->bi_next;
-			}
+		while (bio) {
+			zero_fill_bio(bio);
+			bio = bio->bi_next;
 		}
+
 		ret = BLK_STS_IOERR;
 end_io:
 		blk_mq_end_request(rq, ret);
@@ -395,6 +328,8 @@ static void lo_rw_aio_do_completion(struct loop_cmd *cmd)
 		return;
 	kfree(cmd->bvec);
 	cmd->bvec = NULL;
+	if (req_op(rq) == REQ_OP_WRITE)
+		kiocb_end_write(&cmd->iocb);
 	if (likely(!blk_should_fake_timeout(rq->q)))
 		blk_mq_complete_request(rq);
 }
@@ -460,20 +395,26 @@ static int lo_rw_aio(struct loop_device *lo, struct loop_cmd *cmd,
 
 	cmd->iocb.ki_pos = pos;
 	cmd->iocb.ki_filp = file;
-	cmd->iocb.ki_complete = lo_rw_aio_complete;
-	cmd->iocb.ki_flags = IOCB_DIRECT;
-	cmd->iocb.ki_ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_NONE, 0);
+	cmd->iocb.ki_ioprio = req_get_ioprio(rq);
+	if (cmd->use_aio) {
+		cmd->iocb.ki_complete = lo_rw_aio_complete;
+		cmd->iocb.ki_flags = IOCB_DIRECT;
+	} else {
+		cmd->iocb.ki_complete = NULL;
+		cmd->iocb.ki_flags = 0;
+	}
 
-	if (rw == ITER_SOURCE)
+	if (rw == ITER_SOURCE) {
+		kiocb_start_write(&cmd->iocb);
 		ret = file->f_op->write_iter(&cmd->iocb, &iter);
-	else
+	} else
 		ret = file->f_op->read_iter(&cmd->iocb, &iter);
 
 	lo_rw_aio_do_completion(cmd);
 
 	if (ret != -EIOCBQUEUED)
 		lo_rw_aio_complete(&cmd->iocb, ret);
-	return 0;
+	return -EIOCBQUEUED;
 }
 
 static int do_req_filebacked(struct loop_device *lo, struct request *rq)
@@ -481,15 +422,6 @@ static int do_req_filebacked(struct loop_device *lo, struct request *rq)
 	struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq);
 	loff_t pos = ((loff_t) blk_rq_pos(rq) << 9) + lo->lo_offset;
 
-	/*
-	 * lo_write_simple and lo_read_simple should have been covered
-	 * by io submit style function like lo_rw_aio(), one blocker
-	 * is that lo_read_simple() need to call flush_dcache_page after
-	 * the page is written from kernel, and it isn't easy to handle
-	 * this in io submit style function which submits all segments
-	 * of the req at one time. And direct read IO doesn't need to
-	 * run flush_dcache_page().
-	 */
 	switch (req_op(rq)) {
 	case REQ_OP_FLUSH:
 		return lo_req_flush(lo, rq);
@@ -505,15 +437,9 @@ static int do_req_filebacked(struct loop_device *lo, struct request *rq)
 	case REQ_OP_DISCARD:
 		return lo_fallocate(lo, rq, pos, FALLOC_FL_PUNCH_HOLE);
 	case REQ_OP_WRITE:
-		if (cmd->use_aio)
-			return lo_rw_aio(lo, cmd, pos, ITER_SOURCE);
-		else
-			return lo_write_simple(lo, rq, pos);
+		return lo_rw_aio(lo, cmd, pos, ITER_SOURCE);
 	case REQ_OP_READ:
-		if (cmd->use_aio)
-			return lo_rw_aio(lo, cmd, pos, ITER_DEST);
-		else
-			return lo_read_simple(lo, rq, pos);
+		return lo_rw_aio(lo, cmd, pos, ITER_DEST);
 	default:
 		WARN_ON_ONCE(1);
 		return -EIO;
@@ -570,6 +496,25 @@ static int loop_validate_file(struct file *file, struct block_device *bdev)
 	return 0;
 }
 
+static void loop_assign_backing_file(struct loop_device *lo, struct file *file)
+{
+	lo->lo_backing_file = file;
+	lo->old_gfp_mask = mapping_gfp_mask(file->f_mapping);
+	mapping_set_gfp_mask(file->f_mapping,
+			lo->old_gfp_mask & ~(__GFP_IO | __GFP_FS));
+}
+
+static int loop_check_backing_file(struct file *file)
+{
+	if (!file->f_op->read_iter)
+		return -EINVAL;
+
+	if ((file->f_mode & FMODE_WRITE) && !file->f_op->write_iter)
+		return -EINVAL;
+
+	return 0;
+}
+
 /*
  * loop_change_fd switched the backing store of a loopback device to
  * a new file. This is useful for operating system installers to free up
@@ -590,6 +535,10 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
 	if (!file)
 		return -EBADF;
 
+	error = loop_check_backing_file(file);
+	if (error)
+		return error;
+
 	/* suppress uevents while reconfiguring the device */
 	dev_set_uevent_suppress(disk_to_dev(lo->lo_disk), 1);
 
@@ -622,10 +571,7 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
 	disk_force_media_change(lo->lo_disk);
 	blk_mq_freeze_queue(lo->lo_queue);
 	mapping_set_gfp_mask(old_file->f_mapping, lo->old_gfp_mask);
-	lo->lo_backing_file = file;
-	lo->old_gfp_mask = mapping_gfp_mask(file->f_mapping);
-	mapping_set_gfp_mask(file->f_mapping,
-			     lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS));
+	loop_assign_backing_file(lo, file);
 	loop_update_dio(lo);
 	blk_mq_unfreeze_queue(lo->lo_queue);
 	partscan = lo->lo_flags & LO_FLAGS_PARTSCAN;
@@ -645,19 +591,20 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
 	 * dependency.
 	 */
 	fput(old_file);
+	dev_set_uevent_suppress(disk_to_dev(lo->lo_disk), 0);
 	if (partscan)
 		loop_reread_partitions(lo);
 
 	error = 0;
 done:
-	/* enable and uncork uevent now that we are done */
-	dev_set_uevent_suppress(disk_to_dev(lo->lo_disk), 0);
+	kobject_uevent(&disk_to_dev(lo->lo_disk)->kobj, KOBJ_CHANGE);
 	return error;
 
 out_err:
 	loop_global_unlock(lo, is_loop);
 out_putf:
 	fput(file);
+	dev_set_uevent_suppress(disk_to_dev(lo->lo_disk), 0);
 	goto done;
 }
 
@@ -770,12 +717,11 @@ static void loop_sysfs_exit(struct loop_device *lo)
 				   &loop_attribute_group);
 }
 
-static void loop_config_discard(struct loop_device *lo,
-		struct queue_limits *lim)
+static void loop_get_discard_config(struct loop_device *lo,
+				    u32 *granularity, u32 *max_discard_sectors)
 {
 	struct file *file = lo->lo_backing_file;
 	struct inode *inode = file->f_mapping->host;
-	u32 granularity = 0, max_discard_sectors = 0;
 	struct kstatfs sbuf;
 
 	/*
@@ -786,27 +732,19 @@ static void loop_config_discard(struct loop_device *lo,
 	 * file-backed loop devices: discarded regions read back as zero.
 	 */
 	if (S_ISBLK(inode->i_mode)) {
-		struct request_queue *backingq = bdev_get_queue(I_BDEV(inode));
+		struct block_device *bdev = I_BDEV(inode);
 
-		max_discard_sectors = backingq->limits.max_write_zeroes_sectors;
-		granularity = bdev_discard_granularity(I_BDEV(inode)) ?:
-			queue_physical_block_size(backingq);
+		*max_discard_sectors = bdev_write_zeroes_sectors(bdev);
+		*granularity = bdev_discard_granularity(bdev);
 
 	/*
 	 * We use punch hole to reclaim the free space used by the
 	 * image a.k.a. discard.
 	 */
 	} else if (file->f_op->fallocate && !vfs_statfs(&file->f_path, &sbuf)) {
-		max_discard_sectors = UINT_MAX >> 9;
-		granularity = sbuf.f_bsize;
+		*max_discard_sectors = UINT_MAX >> 9;
+		*granularity = sbuf.f_bsize;
 	}
-
-	lim->max_hw_discard_sectors = max_discard_sectors;
-	lim->max_write_zeroes_sectors = max_discard_sectors;
-	if (max_discard_sectors)
-		lim->discard_granularity = granularity;
-	else
-		lim->discard_granularity = 0;
 }
 
 struct loop_worker {
@@ -981,17 +919,18 @@ static unsigned int loop_default_blocksize(struct loop_device *lo,
 		struct block_device *backing_bdev)
 {
 	/* In case of direct I/O, match underlying block size */
-	if ((lo->lo_backing_file->f_flags & O_DIRECT) && backing_bdev)
+	if ((lo->lo_flags & LO_FLAGS_DIRECT_IO) && backing_bdev)
 		return bdev_logical_block_size(backing_bdev);
 	return SECTOR_SIZE;
 }
 
-static int loop_reconfigure_limits(struct loop_device *lo, unsigned int bsize)
+static void loop_update_limits(struct loop_device *lo, struct queue_limits *lim,
+		unsigned int bsize)
 {
 	struct file *file = lo->lo_backing_file;
 	struct inode *inode = file->f_mapping->host;
 	struct block_device *backing_bdev = NULL;
-	struct queue_limits lim;
+	u32 granularity = 0, max_discard_sectors = 0;
 
 	if (S_ISBLK(inode->i_mode))
 		backing_bdev = I_BDEV(inode);
@@ -1001,17 +940,22 @@ static int loop_reconfigure_limits(struct loop_device *lo, unsigned int bsize)
 	if (!bsize)
 		bsize = loop_default_blocksize(lo, backing_bdev);
 
-	lim = queue_limits_start_update(lo->lo_queue);
-	lim.logical_block_size = bsize;
-	lim.physical_block_size = bsize;
-	lim.io_min = bsize;
-	lim.features &= ~(BLK_FEAT_WRITE_CACHE | BLK_FEAT_ROTATIONAL);
+	loop_get_discard_config(lo, &granularity, &max_discard_sectors);
+
+	lim->logical_block_size = bsize;
+	lim->physical_block_size = bsize;
+	lim->io_min = bsize;
+	lim->features &= ~(BLK_FEAT_WRITE_CACHE | BLK_FEAT_ROTATIONAL);
 	if (file->f_op->fsync && !(lo->lo_flags & LO_FLAGS_READ_ONLY))
-		lim.features |= BLK_FEAT_WRITE_CACHE;
+		lim->features |= BLK_FEAT_WRITE_CACHE;
 	if (backing_bdev && !bdev_nonrot(backing_bdev))
-		lim.features |= BLK_FEAT_ROTATIONAL;
-	loop_config_discard(lo, &lim);
-	return queue_limits_commit_update(lo->lo_queue, &lim);
+		lim->features |= BLK_FEAT_ROTATIONAL;
+	lim->max_hw_discard_sectors = max_discard_sectors;
+	lim->max_write_zeroes_sectors = max_discard_sectors;
+	if (max_discard_sectors)
+		lim->discard_granularity = granularity;
+	else
+		lim->discard_granularity = 0;
 }
 
 static int loop_configure(struct loop_device *lo, blk_mode_t mode,
@@ -1019,7 +963,7 @@ static int loop_configure(struct loop_device *lo, blk_mode_t mode,
 			  const struct loop_config *config)
 {
 	struct file *file = fget(config->fd);
-	struct address_space *mapping;
+	struct queue_limits lim;
 	int error;
 	loff_t size;
 	bool partscan;
@@ -1027,6 +971,11 @@ static int loop_configure(struct loop_device *lo, blk_mode_t mode,
 
 	if (!file)
 		return -EBADF;
+
+	error = loop_check_backing_file(file);
+	if (error)
+		return error;
+
 	is_loop = is_loop_device(file);
 
 	/* This is safe, since we have a reference from open(). */
@@ -1054,8 +1003,6 @@ static int loop_configure(struct loop_device *lo, blk_mode_t mode,
 	if (error)
 		goto out_unlock;
 
-	mapping = file->f_mapping;
-
 	if ((config->info.lo_flags & ~LOOP_CONFIGURE_SETTABLE_FLAGS) != 0) {
 		error = -EINVAL;
 		goto out_unlock;
@@ -1087,11 +1034,11 @@ static int loop_configure(struct loop_device *lo, blk_mode_t mode,
 
 	lo->use_dio = lo->lo_flags & LO_FLAGS_DIRECT_IO;
 	lo->lo_device = bdev;
-	lo->lo_backing_file = file;
-	lo->old_gfp_mask = mapping_gfp_mask(mapping);
-	mapping_set_gfp_mask(mapping, lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS));
+	loop_assign_backing_file(lo, file);
 
-	error = loop_reconfigure_limits(lo, config->block_size);
+	lim = queue_limits_start_update(lo->lo_queue);
+	loop_update_limits(lo, &lim, config->block_size);
+	error = queue_limits_commit_update(lo->lo_queue, &lim);
 	if (error)
 		goto out_unlock;
 
@@ -1111,8 +1058,8 @@ static int loop_configure(struct loop_device *lo, blk_mode_t mode,
 	if (partscan)
 		clear_bit(GD_SUPPRESS_PART_SCAN, &lo->lo_disk->state);
 
-	/* enable and uncork uevent now that we are done */
 	dev_set_uevent_suppress(disk_to_dev(lo->lo_disk), 0);
+	kobject_uevent(&disk_to_dev(lo->lo_disk)->kobj, KOBJ_CHANGE);
 
 	loop_global_unlock(lo, is_loop);
 	if (partscan)
@@ -1457,24 +1404,49 @@ static int loop_set_dio(struct loop_device *lo, unsigned long arg)
 	return error;
 }
 
-static int loop_set_block_size(struct loop_device *lo, unsigned long arg)
+static int loop_set_block_size(struct loop_device *lo, blk_mode_t mode,
+			       struct block_device *bdev, unsigned long arg)
 {
+	struct queue_limits lim;
 	int err = 0;
 
-	if (lo->lo_state != Lo_bound)
-		return -ENXIO;
+	/*
+	 * If we don't hold exclusive handle for the device, upgrade to it
+	 * here to avoid changing device under exclusive owner.
+	 */
+	if (!(mode & BLK_OPEN_EXCL)) {
+		err = bd_prepare_to_claim(bdev, loop_set_block_size, NULL);
+		if (err)
+			return err;
+	}
+
+	err = mutex_lock_killable(&lo->lo_mutex);
+	if (err)
+		goto abort_claim;
+
+	if (lo->lo_state != Lo_bound) {
+		err = -ENXIO;
+		goto unlock;
+	}
 
 	if (lo->lo_queue->limits.logical_block_size == arg)
-		return 0;
+		goto unlock;
 
 	sync_blockdev(lo->lo_device);
 	invalidate_bdev(lo->lo_device);
 
 	blk_mq_freeze_queue(lo->lo_queue);
-	err = loop_reconfigure_limits(lo, arg);
+	lim = queue_limits_start_update(lo->lo_queue);
+	loop_update_limits(lo, &lim, arg);
+	err = queue_limits_commit_update(lo->lo_queue, &lim);
 	loop_update_dio(lo);
 	blk_mq_unfreeze_queue(lo->lo_queue);
 
+unlock:
+	mutex_unlock(&lo->lo_mutex);
+abort_claim:
+	if (!(mode & BLK_OPEN_EXCL))
+		bd_abort_claiming(bdev, loop_set_block_size);
 	return err;
 }
 
@@ -1493,9 +1465,6 @@ static int lo_simple_ioctl(struct loop_device *lo, unsigned int cmd,
 	case LOOP_SET_DIRECT_IO:
 		err = loop_set_dio(lo, arg);
 		break;
-	case LOOP_SET_BLOCK_SIZE:
-		err = loop_set_block_size(lo, arg);
-		break;
 	default:
 		err = -EINVAL;
 	}
@@ -1550,9 +1519,12 @@ static int lo_ioctl(struct block_device *bdev, blk_mode_t mode,
 		break;
 	case LOOP_GET_STATUS64:
 		return loop_get_status64(lo, argp);
+	case LOOP_SET_BLOCK_SIZE:
+		if (!(mode & BLK_OPEN_WRITE) && !capable(CAP_SYS_ADMIN))
+			return -EPERM;
+		return loop_set_block_size(lo, mode, bdev, arg);
 	case LOOP_SET_CAPACITY:
 	case LOOP_SET_DIRECT_IO:
-	case LOOP_SET_BLOCK_SIZE:
 		if (!(mode & BLK_OPEN_WRITE) && !capable(CAP_SYS_ADMIN))
 			return -EPERM;
 		fallthrough;
@@ -1888,7 +1860,6 @@ static void loop_handle_cmd(struct loop_cmd *cmd)
 	struct loop_device *lo = rq->q->queuedata;
 	int ret = 0;
 	struct mem_cgroup *old_memcg = NULL;
-	const bool use_aio = cmd->use_aio;
 
 	if (write && (lo->lo_flags & LO_FLAGS_READ_ONLY)) {
 		ret = -EIO;
@@ -1918,7 +1889,7 @@ static void loop_handle_cmd(struct loop_cmd *cmd)
 	}
  failed:
 	/* complete non-aio request */
-	if (!use_aio || ret) {
+	if (ret != -EIOCBQUEUED) {
 		if (ret == -EOPNOTSUPP)
 			cmd->ret = ret;
 		else
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index b852050d8a96..c705acc4d6f4 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -2136,9 +2136,7 @@ again:
 				goto out;
 		}
 	}
-	ret = nbd_start_device(nbd);
-	if (ret)
-		goto out;
+
 	if (info->attrs[NBD_ATTR_BACKEND_IDENTIFIER]) {
 		nbd->backend = nla_strdup(info->attrs[NBD_ATTR_BACKEND_IDENTIFIER],
 					  GFP_KERNEL);
@@ -2154,6 +2152,8 @@ again:
 		goto out;
 	}
 	set_bit(NBD_RT_HAS_BACKEND_FILE, &config->runtime_flags);
+
+	ret = nbd_start_device(nbd);
 out:
 	mutex_unlock(&nbd->config_lock);
 	if (!ret) {
@@ -2180,6 +2180,7 @@ static void nbd_disconnect_and_put(struct nbd_device *nbd)
 	flush_workqueue(nbd->recv_workq);
 	nbd_clear_que(nbd);
 	nbd->task_setup = NULL;
+	clear_bit(NBD_RT_BOUND, &nbd->config->runtime_flags);
 	mutex_unlock(&nbd->config_lock);
 
 	if (test_and_clear_bit(NBD_RT_HAS_CONFIG_REF,
diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c
index 2f0431e42c49..f10369ad90f7 100644
--- a/drivers/block/null_blk/main.c
+++ b/drivers/block/null_blk/main.c
@@ -1541,8 +1541,8 @@ static int null_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob)
 		cmd = blk_mq_rq_to_pdu(req);
 		cmd->error = null_process_cmd(cmd, req_op(req), blk_rq_pos(req),
 						blk_rq_sectors(req));
-		if (!blk_mq_add_to_batch(req, iob, (__force int) cmd->error,
-					blk_mq_end_request_batch))
+		if (!blk_mq_add_to_batch(req, iob, cmd->error != BLK_STS_OK,
+					 blk_mq_end_request_batch))
 			blk_mq_end_request(req, cmd->error);
 		nr++;
 	}
@@ -1638,10 +1638,9 @@ static blk_status_t null_queue_rq(struct blk_mq_hw_ctx *hctx,
 	return BLK_STS_OK;
 }
 
-static void null_queue_rqs(struct request **rqlist)
+static void null_queue_rqs(struct rq_list *rqlist)
 {
-	struct request *requeue_list = NULL;
-	struct request **requeue_lastp = &requeue_list;
+	struct rq_list requeue_list = {};
 	struct blk_mq_queue_data bd = { };
 	blk_status_t ret;
 
@@ -1651,8 +1650,8 @@ static void null_queue_rqs(struct request **rqlist)
 		bd.rq = rq;
 		ret = null_queue_rq(rq->mq_hctx, &bd);
 		if (ret != BLK_STS_OK)
-			rq_list_add_tail(&requeue_lastp, rq);
-	} while (!rq_list_empty(*rqlist));
+			rq_list_add_tail(&requeue_list, rq);
+	} while (!rq_list_empty(rqlist));
 
 	*rqlist = requeue_list;
 }
diff --git a/drivers/block/ps3disk.c b/drivers/block/ps3disk.c
index ff45ed766469..226ffc743238 100644
--- a/drivers/block/ps3disk.c
+++ b/drivers/block/ps3disk.c
@@ -384,9 +384,9 @@ static int ps3disk_probe(struct ps3_system_bus_device *_dev)
 	unsigned int devidx;
 	struct queue_limits lim = {
 		.logical_block_size	= dev->blk_size,
-		.max_hw_sectors		= dev->bounce_size >> 9,
+		.max_hw_sectors		= BOUNCE_SIZE >> 9,
 		.max_segments		= -1,
-		.max_segment_size	= dev->bounce_size,
+		.max_segment_size	= BOUNCE_SIZE,
 		.dma_alignment		= dev->blk_size - 1,
 		.features		= BLK_FEAT_WRITE_CACHE |
 					  BLK_FEAT_ROTATIONAL,
diff --git a/drivers/block/rnull.rs b/drivers/block/rnull.rs
index b0227cf9ddd3..5de7223beb4d 100644
--- a/drivers/block/rnull.rs
+++ b/drivers/block/rnull.rs
@@ -32,7 +32,7 @@ module! {
 }
 
 struct NullBlkModule {
-    _disk: Pin<Box<Mutex<GenDisk<NullBlkDevice>>>>,
+    _disk: Pin<KBox<Mutex<GenDisk<NullBlkDevice>>>>,
 }
 
 impl kernel::Module for NullBlkModule {
@@ -47,7 +47,7 @@ impl kernel::Module for NullBlkModule {
             .rotational(false)
             .build(format_args!("rnullb{}", 0), tagset)?;
 
-        let disk = Box::pin_init(new_mutex!(disk, "nullb:disk"), flags::GFP_KERNEL)?;
+        let disk = KBox::pin_init(new_mutex!(disk, "nullb:disk"), flags::GFP_KERNEL)?;
 
         Ok(Self { _disk: disk })
     }
diff --git a/drivers/block/sunvdc.c b/drivers/block/sunvdc.c
index 2d38331ee667..2b249703dc68 100644
--- a/drivers/block/sunvdc.c
+++ b/drivers/block/sunvdc.c
@@ -957,8 +957,10 @@ static bool vdc_port_mpgroup_check(struct vio_dev *vdev)
 	dev = device_find_child(vdev->dev.parent, &port_data,
 				vdc_device_probed);
 
-	if (dev)
+	if (dev) {
+		put_device(dev);
 		return true;
+	}
 
 	return false;
 }
diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
index 458ac54e7b20..defcc964ecab 100644
--- a/drivers/block/ublk_drv.c
+++ b/drivers/block/ublk_drv.c
@@ -484,15 +484,17 @@ static wait_queue_head_t ublk_idr_wq;	/* wait until one idr is freed */
 
 static DEFINE_MUTEX(ublk_ctl_mutex);
 
+
+#define UBLK_MAX_UBLKS UBLK_MINORS
+
 /*
- * Max ublk devices allowed to add
+ * Max unprivileged ublk devices allowed to add
  *
  * It can be extended to one per-user limit in future or even controlled
  * by cgroup.
  */
-#define UBLK_MAX_UBLKS UBLK_MINORS
-static unsigned int ublks_max = 64;
-static unsigned int ublks_added;	/* protected by ublk_ctl_mutex */
+static unsigned int unprivileged_ublks_max = 64;
+static unsigned int unprivileged_ublks_added; /* protected by ublk_ctl_mutex */
 
 static struct miscdevice ublk_misc;
 
@@ -681,22 +683,44 @@ static int ublk_max_cmd_buf_size(void)
 	return __ublk_queue_cmd_buf_size(UBLK_MAX_QUEUE_DEPTH);
 }
 
-static inline bool ublk_queue_can_use_recovery_reissue(
-		struct ublk_queue *ubq)
+/*
+ * Should I/O outstanding to the ublk server when it exits be reissued?
+ * If not, outstanding I/O will get errors.
+ */
+static inline bool ublk_nosrv_should_reissue_outstanding(struct ublk_device *ub)
 {
-	return (ubq->flags & UBLK_F_USER_RECOVERY) &&
-			(ubq->flags & UBLK_F_USER_RECOVERY_REISSUE);
+	return (ub->dev_info.flags & UBLK_F_USER_RECOVERY) &&
+	       (ub->dev_info.flags & UBLK_F_USER_RECOVERY_REISSUE);
 }
 
-static inline bool ublk_queue_can_use_recovery(
-		struct ublk_queue *ubq)
+/*
+ * Should I/O issued while there is no ublk server queue? If not, I/O
+ * issued while there is no ublk server will get errors.
+ */
+static inline bool ublk_nosrv_dev_should_queue_io(struct ublk_device *ub)
+{
+	return ub->dev_info.flags & UBLK_F_USER_RECOVERY;
+}
+
+/*
+ * Same as ublk_nosrv_dev_should_queue_io, but uses a queue-local copy
+ * of the device flags for smaller cache footprint - better for fast
+ * paths.
+ */
+static inline bool ublk_nosrv_should_queue_io(struct ublk_queue *ubq)
 {
 	return ubq->flags & UBLK_F_USER_RECOVERY;
 }
 
-static inline bool ublk_can_use_recovery(struct ublk_device *ub)
+/*
+ * Should ublk devices be stopped (i.e. no recovery possible) when the
+ * ublk server exits? If not, devices can be used again by a future
+ * incarnation of a ublk server via the start_recovery/end_recovery
+ * commands.
+ */
+static inline bool ublk_nosrv_should_stop_dev(struct ublk_device *ub)
 {
-	return ub->dev_info.flags & UBLK_F_USER_RECOVERY;
+	return !(ub->dev_info.flags & UBLK_F_USER_RECOVERY);
 }
 
 static void ublk_free_disk(struct gendisk *disk)
@@ -1059,6 +1083,25 @@ static void ublk_complete_rq(struct kref *ref)
 	__ublk_complete_rq(req);
 }
 
+static void ublk_do_fail_rq(struct request *req)
+{
+	struct ublk_queue *ubq = req->mq_hctx->driver_data;
+
+	if (ublk_nosrv_should_reissue_outstanding(ubq->dev))
+		blk_mq_requeue_request(req, false);
+	else
+		__ublk_complete_rq(req);
+}
+
+static void ublk_fail_rq_fn(struct kref *ref)
+{
+	struct ublk_rq_data *data = container_of(ref, struct ublk_rq_data,
+			ref);
+	struct request *req = blk_mq_rq_from_pdu(data);
+
+	ublk_do_fail_rq(req);
+}
+
 /*
  * Since __ublk_rq_task_work always fails requests immediately during
  * exiting, __ublk_fail_req() is only called from abort context during
@@ -1072,10 +1115,13 @@ static void __ublk_fail_req(struct ublk_queue *ubq, struct ublk_io *io,
 {
 	WARN_ON_ONCE(io->flags & UBLK_IO_FLAG_ACTIVE);
 
-	if (ublk_queue_can_use_recovery_reissue(ubq))
-		blk_mq_requeue_request(req, false);
-	else
-		ublk_put_req_ref(ubq, req);
+	if (ublk_need_req_ref(ubq)) {
+		struct ublk_rq_data *data = blk_mq_rq_to_pdu(req);
+
+		kref_put(&data->ref, ublk_fail_rq_fn);
+	} else {
+		ublk_do_fail_rq(req);
+	}
 }
 
 static void ubq_complete_io_cmd(struct ublk_io *io, int res,
@@ -1100,7 +1146,7 @@ static inline void __ublk_abort_rq(struct ublk_queue *ubq,
 		struct request *rq)
 {
 	/* We cannot process this rq so just requeue it. */
-	if (ublk_queue_can_use_recovery(ubq))
+	if (ublk_nosrv_dev_should_queue_io(ubq->dev))
 		blk_mq_requeue_request(rq, false);
 	else
 		blk_mq_end_request(rq, BLK_STS_IOERR);
@@ -1245,10 +1291,10 @@ static enum blk_eh_timer_return ublk_timeout(struct request *rq)
 		struct ublk_device *ub = ubq->dev;
 
 		if (ublk_abort_requests(ub, ubq)) {
-			if (ublk_can_use_recovery(ub))
-				schedule_work(&ub->quiesce_work);
-			else
+			if (ublk_nosrv_should_stop_dev(ub))
 				schedule_work(&ub->stop_work);
+			else
+				schedule_work(&ub->quiesce_work);
 		}
 		return BLK_EH_DONE;
 	}
@@ -1277,7 +1323,7 @@ static blk_status_t ublk_queue_rq(struct blk_mq_hw_ctx *hctx,
 	 * Note: force_abort is guaranteed to be seen because it is set
 	 * before request queue is unqiuesced.
 	 */
-	if (ublk_queue_can_use_recovery(ubq) && unlikely(ubq->force_abort))
+	if (ublk_nosrv_should_queue_io(ubq) && unlikely(ubq->force_abort))
 		return BLK_STS_IOERR;
 
 	if (unlikely(ubq->canceling)) {
@@ -1416,17 +1462,27 @@ static void ublk_abort_queue(struct ublk_device *ub, struct ublk_queue *ubq)
 	}
 }
 
+/* Must be called when queue is frozen */
+static bool ublk_mark_queue_canceling(struct ublk_queue *ubq)
+{
+	bool canceled;
+
+	spin_lock(&ubq->cancel_lock);
+	canceled = ubq->canceling;
+	if (!canceled)
+		ubq->canceling = true;
+	spin_unlock(&ubq->cancel_lock);
+
+	return canceled;
+}
+
 static bool ublk_abort_requests(struct ublk_device *ub, struct ublk_queue *ubq)
 {
+	bool was_canceled = ubq->canceling;
 	struct gendisk *disk;
 
-	spin_lock(&ubq->cancel_lock);
-	if (ubq->canceling) {
-		spin_unlock(&ubq->cancel_lock);
+	if (was_canceled)
 		return false;
-	}
-	ubq->canceling = true;
-	spin_unlock(&ubq->cancel_lock);
 
 	spin_lock(&ub->lock);
 	disk = ub->ub_disk;
@@ -1438,14 +1494,23 @@ static bool ublk_abort_requests(struct ublk_device *ub, struct ublk_queue *ubq)
 	if (!disk)
 		return false;
 
-	/* Now we are serialized with ublk_queue_rq() */
+	/*
+	 * Now we are serialized with ublk_queue_rq()
+	 *
+	 * Make sure that ubq->canceling is set when queue is frozen,
+	 * because ublk_queue_rq() has to rely on this flag for avoiding to
+	 * touch completed uring_cmd
+	 */
 	blk_mq_quiesce_queue(disk->queue);
-	/* abort queue is for making forward progress */
-	ublk_abort_queue(ub, ubq);
+	was_canceled = ublk_mark_queue_canceling(ubq);
+	if (!was_canceled) {
+		/* abort queue is for making forward progress */
+		ublk_abort_queue(ub, ubq);
+	}
 	blk_mq_unquiesce_queue(disk->queue);
 	put_device(disk_to_dev(disk));
 
-	return true;
+	return !was_canceled;
 }
 
 static void ublk_cancel_cmd(struct ublk_queue *ubq, struct ublk_io *io,
@@ -1498,10 +1563,10 @@ static void ublk_uring_cmd_cancel_fn(struct io_uring_cmd *cmd,
 	ublk_cancel_cmd(ubq, io, issue_flags);
 
 	if (need_schedule) {
-		if (ublk_can_use_recovery(ub))
-			schedule_work(&ub->quiesce_work);
-		else
+		if (ublk_nosrv_should_stop_dev(ub))
 			schedule_work(&ub->stop_work);
+		else
+			schedule_work(&ub->quiesce_work);
 	}
 }
 
@@ -1621,7 +1686,7 @@ static void ublk_stop_dev(struct ublk_device *ub)
 	mutex_lock(&ub->mutex);
 	if (ub->dev_info.state == UBLK_S_DEV_DEAD)
 		goto unlock;
-	if (ublk_can_use_recovery(ub)) {
+	if (ublk_nosrv_dev_should_queue_io(ub)) {
 		if (ub->dev_info.state == UBLK_S_DEV_LIVE)
 			__ublk_quiesce_dev(ub);
 		ublk_unquiesce_dev(ub);
@@ -1816,10 +1881,9 @@ static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd,
 	return -EIOCBQUEUED;
 
  out:
-	io_uring_cmd_done(cmd, ret, 0, issue_flags);
 	pr_devel("%s: complete: cmd op %d, tag %d ret %x io_flags %x\n",
 			__func__, cmd_op, tag, ret, io->flags);
-	return -EIOCBQUEUED;
+	return ret;
 }
 
 static inline struct request *__ublk_check_and_get_req(struct ublk_device *ub,
@@ -1875,7 +1939,10 @@ static inline int ublk_ch_uring_cmd_local(struct io_uring_cmd *cmd,
 static void ublk_ch_uring_cmd_cb(struct io_uring_cmd *cmd,
 		unsigned int issue_flags)
 {
-	ublk_ch_uring_cmd_local(cmd, issue_flags);
+	int ret = ublk_ch_uring_cmd_local(cmd, issue_flags);
+
+	if (ret != -EIOCBQUEUED)
+		io_uring_cmd_done(cmd, ret, 0, issue_flags);
 }
 
 static int ublk_ch_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags)
@@ -2049,7 +2116,7 @@ static void ublk_deinit_queues(struct ublk_device *ub)
 
 	for (i = 0; i < nr_queues; i++)
 		ublk_deinit_queue(ub, i);
-	kfree(ub->__queues);
+	kvfree(ub->__queues);
 }
 
 static int ublk_init_queues(struct ublk_device *ub)
@@ -2060,7 +2127,7 @@ static int ublk_init_queues(struct ublk_device *ub)
 	int i, ret = -ENOMEM;
 
 	ub->queue_size = ubq_size;
-	ub->__queues = kcalloc(nr_queues, ubq_size, GFP_KERNEL);
+	ub->__queues = kvcalloc(nr_queues, ubq_size, GFP_KERNEL);
 	if (!ub->__queues)
 		return ret;
 
@@ -2140,7 +2207,8 @@ static int ublk_add_chdev(struct ublk_device *ub)
 	if (ret)
 		goto fail;
 
-	ublks_added++;
+	if (ub->dev_info.flags & UBLK_F_UNPRIVILEGED_DEV)
+		unprivileged_ublks_added++;
 	return 0;
  fail:
 	put_device(dev);
@@ -2178,12 +2246,17 @@ static int ublk_add_tag_set(struct ublk_device *ub)
 
 static void ublk_remove(struct ublk_device *ub)
 {
+	bool unprivileged;
+
 	ublk_stop_dev(ub);
 	cancel_work_sync(&ub->stop_work);
 	cancel_work_sync(&ub->quiesce_work);
 	cdev_device_del(&ub->cdev, &ub->cdev_dev);
+	unprivileged = ub->dev_info.flags & UBLK_F_UNPRIVILEGED_DEV;
 	ublk_put_device(ub);
-	ublks_added--;
+
+	if (unprivileged)
+		unprivileged_ublks_added--;
 }
 
 static struct ublk_device *ublk_get_device_from_id(int idx)
@@ -2384,6 +2457,10 @@ static int ublk_ctrl_add_dev(struct io_uring_cmd *cmd)
 	if (copy_from_user(&info, argp, sizeof(info)))
 		return -EFAULT;
 
+	if (info.queue_depth > UBLK_MAX_QUEUE_DEPTH || !info.queue_depth ||
+	    info.nr_hw_queues > UBLK_MAX_NR_QUEUES || !info.nr_hw_queues)
+		return -EINVAL;
+
 	if (capable(CAP_SYS_ADMIN))
 		info.flags &= ~UBLK_F_UNPRIVILEGED_DEV;
 	else if (!(info.flags & UBLK_F_UNPRIVILEGED_DEV))
@@ -2432,7 +2509,8 @@ static int ublk_ctrl_add_dev(struct io_uring_cmd *cmd)
 		return ret;
 
 	ret = -EACCES;
-	if (ublks_added >= ublks_max)
+	if ((info.flags & UBLK_F_UNPRIVILEGED_DEV) &&
+	    unprivileged_ublks_added >= unprivileged_ublks_max)
 		goto out_unlock;
 
 	ret = -ENOMEM;
@@ -2665,9 +2743,12 @@ static int ublk_ctrl_set_params(struct ublk_device *ub,
 	if (ph.len > sizeof(struct ublk_params))
 		ph.len = sizeof(struct ublk_params);
 
-	/* parameters can only be changed when device isn't live */
 	mutex_lock(&ub->mutex);
-	if (ub->dev_info.state == UBLK_S_DEV_LIVE) {
+	if (test_bit(UB_STATE_USED, &ub->state)) {
+		/*
+		 * Parameters can only be changed when device hasn't
+		 * been started yet
+		 */
 		ret = -EACCES;
 	} else if (copy_from_user(&ub->params, argp, ph.len)) {
 		ret = -EFAULT;
@@ -2716,7 +2797,7 @@ static int ublk_ctrl_start_recovery(struct ublk_device *ub,
 	int i;
 
 	mutex_lock(&ub->mutex);
-	if (!ublk_can_use_recovery(ub))
+	if (ublk_nosrv_should_stop_dev(ub))
 		goto out_unlock;
 	if (!ub->nr_queues_ready)
 		goto out_unlock;
@@ -2769,7 +2850,7 @@ static int ublk_ctrl_end_recovery(struct ublk_device *ub,
 			__func__, ub->dev_info.nr_hw_queues, header->dev_id);
 
 	mutex_lock(&ub->mutex);
-	if (!ublk_can_use_recovery(ub))
+	if (ublk_nosrv_should_stop_dev(ub))
 		goto out_unlock;
 
 	if (ub->dev_info.state != UBLK_S_DEV_QUIESCED) {
@@ -2990,10 +3071,9 @@ static int ublk_ctrl_uring_cmd(struct io_uring_cmd *cmd,
 	if (ub)
 		ublk_put_device(ub);
  out:
-	io_uring_cmd_done(cmd, ret, 0, issue_flags);
 	pr_devel("%s: cmd done ret %d cmd_op %x, dev id %d qid %d\n",
 			__func__, ret, cmd->cmd_op, header->dev_id, header->queue_id);
-	return -EIOCBQUEUED;
+	return ret;
 }
 
 static const struct file_operations ublk_ctl_fops = {
@@ -3057,23 +3137,26 @@ static void __exit ublk_exit(void)
 module_init(ublk_init);
 module_exit(ublk_exit);
 
-static int ublk_set_max_ublks(const char *buf, const struct kernel_param *kp)
+static int ublk_set_max_unprivileged_ublks(const char *buf,
+					   const struct kernel_param *kp)
 {
 	return param_set_uint_minmax(buf, kp, 0, UBLK_MAX_UBLKS);
 }
 
-static int ublk_get_max_ublks(char *buf, const struct kernel_param *kp)
+static int ublk_get_max_unprivileged_ublks(char *buf,
+					   const struct kernel_param *kp)
 {
-	return sysfs_emit(buf, "%u\n", ublks_max);
+	return sysfs_emit(buf, "%u\n", unprivileged_ublks_max);
 }
 
-static const struct kernel_param_ops ublk_max_ublks_ops = {
-	.set = ublk_set_max_ublks,
-	.get = ublk_get_max_ublks,
+static const struct kernel_param_ops ublk_max_unprivileged_ublks_ops = {
+	.set = ublk_set_max_unprivileged_ublks,
+	.get = ublk_get_max_unprivileged_ublks,
 };
 
-module_param_cb(ublks_max, &ublk_max_ublks_ops, &ublks_max, 0644);
-MODULE_PARM_DESC(ublks_max, "max number of ublk devices allowed to add(default: 64)");
+module_param_cb(ublks_max, &ublk_max_unprivileged_ublks_ops,
+		&unprivileged_ublks_max, 0644);
+MODULE_PARM_DESC(ublks_max, "max number of unprivileged ublk devices allowed to add(default: 64)");
 
 MODULE_AUTHOR("Ming Lei <ming.lei@redhat.com>");
 MODULE_DESCRIPTION("Userspace block device");
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 0e50b65e1dbf..fd6c565f8a50 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -472,7 +472,7 @@ static bool virtblk_prep_rq_batch(struct request *req)
 }
 
 static void virtblk_add_req_batch(struct virtio_blk_vq *vq,
-					struct request **rqlist)
+		struct rq_list *rqlist)
 {
 	struct request *req;
 	unsigned long flags;
@@ -499,11 +499,10 @@ static void virtblk_add_req_batch(struct virtio_blk_vq *vq,
 		virtqueue_notify(vq->vq);
 }
 
-static void virtio_queue_rqs(struct request **rqlist)
+static void virtio_queue_rqs(struct rq_list *rqlist)
 {
-	struct request *submit_list = NULL;
-	struct request *requeue_list = NULL;
-	struct request **requeue_lastp = &requeue_list;
+	struct rq_list submit_list = { };
+	struct rq_list requeue_list = { };
 	struct virtio_blk_vq *vq = NULL;
 	struct request *req;
 
@@ -515,9 +514,9 @@ static void virtio_queue_rqs(struct request **rqlist)
 		vq = this_vq;
 
 		if (virtblk_prep_rq_batch(req))
-			rq_list_add(&submit_list, req); /* reverse order */
+			rq_list_add_tail(&submit_list, req);
 		else
-			rq_list_add_tail(&requeue_lastp, req);
+			rq_list_add_tail(&requeue_list, req);
 	}
 
 	if (vq)
@@ -1210,11 +1209,12 @@ static int virtblk_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob)
 
 	while ((vbr = virtqueue_get_buf(vq->vq, &len)) != NULL) {
 		struct request *req = blk_mq_rq_from_pdu(vbr);
+		u8 status = virtblk_vbr_status(vbr);
 
 		found++;
 		if (!blk_mq_complete_request_remote(req) &&
-		    !blk_mq_add_to_batch(req, iob, virtblk_vbr_status(vbr),
-						virtblk_complete_batch))
+		    !blk_mq_add_to_batch(req, iob, status != VIRTIO_BLK_S_OK,
+					 virtblk_complete_batch))
 			virtblk_request_done(req);
 	}
 
diff --git a/drivers/bluetooth/btbcm.c b/drivers/bluetooth/btbcm.c
index a1153ada74d2..0a60660fc8ce 100644
--- a/drivers/bluetooth/btbcm.c
+++ b/drivers/bluetooth/btbcm.c
@@ -553,6 +553,9 @@ static const char *btbcm_get_board_name(struct device *dev)
 
 	/* get rid of any '/' in the compatible string */
 	board_type = devm_kstrdup(dev, tmp, GFP_KERNEL);
+	if (!board_type)
+		return NULL;
+
 	strreplace(board_type, '/', '-');
 
 	return board_type;
diff --git a/drivers/bluetooth/btintel.c b/drivers/bluetooth/btintel.c
index 645047fb92fd..85df941afb6c 100644
--- a/drivers/bluetooth/btintel.c
+++ b/drivers/bluetooth/btintel.c
@@ -2656,7 +2656,7 @@ static u8 btintel_classify_pkt_type(struct hci_dev *hdev, struct sk_buff *skb)
 	 * Distinguish ISO data packets form ACL data packets
 	 * based on their connection handle value range.
 	 */
-	if (hci_skb_pkt_type(skb) == HCI_ACLDATA_PKT) {
+	if (iso_capable(hdev) && hci_skb_pkt_type(skb) == HCI_ACLDATA_PKT) {
 		__u16 handle = __le16_to_cpu(hci_acl_hdr(skb)->handle);
 
 		if (hci_handle(handle) >= BTINTEL_ISODATA_HANDLE_BASE)
@@ -2705,7 +2705,7 @@ static int btintel_uefi_get_dsbr(u32 *dsbr_var)
 	} __packed data;
 
 	efi_status_t status;
-	unsigned long data_size = 0;
+	unsigned long data_size = sizeof(data);
 	efi_guid_t guid = EFI_GUID(0xe65d8884, 0xd4af, 0x4b20, 0x8d, 0x03,
 				   0x77, 0x2e, 0xcc, 0x3d, 0xa5, 0x31);
 
@@ -2716,15 +2716,9 @@ static int btintel_uefi_get_dsbr(u32 *dsbr_var)
 		return -EOPNOTSUPP;
 
 	status = efi.get_variable(BTINTEL_EFI_DSBR, &guid, NULL, &data_size,
-				  NULL);
-
-	if (status != EFI_BUFFER_TOO_SMALL || !data_size)
-		return -EIO;
-
-	status = efi.get_variable(BTINTEL_EFI_DSBR, &guid, NULL, &data_size,
 				  &data);
 
-	if (status != EFI_SUCCESS)
+	if (status != EFI_SUCCESS || data_size != sizeof(data))
 		return -ENXIO;
 
 	*dsbr_var = data.dsbr;
diff --git a/drivers/bluetooth/btintel_pcie.c b/drivers/bluetooth/btintel_pcie.c
index 8bd663f4bac1..34812bf7587d 100644
--- a/drivers/bluetooth/btintel_pcie.c
+++ b/drivers/bluetooth/btintel_pcie.c
@@ -36,6 +36,7 @@
 /* Intel Bluetooth PCIe device id table */
 static const struct pci_device_id btintel_pcie_table[] = {
 	{ BTINTEL_PCI_DEVICE(0xA876, PCI_ANY_ID) },
+	{ BTINTEL_PCI_DEVICE(0xE476, PCI_ANY_ID) },
 	{ 0 }
 };
 MODULE_DEVICE_TABLE(pci, btintel_pcie_table);
@@ -230,8 +231,13 @@ static int btintel_pcie_submit_rx(struct btintel_pcie_data *data)
 static int btintel_pcie_start_rx(struct btintel_pcie_data *data)
 {
 	int i, ret;
+	struct rxq *rxq = &data->rxq;
+
+	/* Post (BTINTEL_PCIE_RX_DESCS_COUNT - 3) buffers to overcome the
+	 * hardware issues leading to race condition at the firmware.
+	 */
 
-	for (i = 0; i < BTINTEL_PCIE_RX_MAX_QUEUE; i++) {
+	for (i = 0; i < rxq->count - 3; i++) {
 		ret = btintel_pcie_submit_rx(data);
 		if (ret)
 			return ret;
@@ -580,8 +586,10 @@ static int btintel_pcie_recv_event(struct hci_dev *hdev, struct sk_buff *skb)
 		/* This is a debug event that comes from IML and OP image when it
 		 * starts execution. There is no need pass this event to stack.
 		 */
-		if (skb->data[2] == 0x97)
+		if (skb->data[2] == 0x97) {
+			hci_recv_diag(hdev, skb);
 			return 0;
+		}
 	}
 
 	return hci_recv_frame(hdev, skb);
@@ -597,7 +605,6 @@ static int btintel_pcie_recv_frame(struct btintel_pcie_data *data,
 	u8 pkt_type;
 	u16 plen;
 	u32 pcie_pkt_type;
-	struct sk_buff *new_skb;
 	void *pdata;
 	struct hci_dev *hdev = data->hdev;
 
@@ -674,24 +681,20 @@ static int btintel_pcie_recv_frame(struct btintel_pcie_data *data,
 
 	bt_dev_dbg(hdev, "pkt_type: 0x%2.2x len: %u", pkt_type, plen);
 
-	new_skb = bt_skb_alloc(plen, GFP_ATOMIC);
-	if (!new_skb) {
-		bt_dev_err(hdev, "Failed to allocate memory for skb of len: %u",
-			   skb->len);
-		ret = -ENOMEM;
-		goto exit_error;
-	}
-
-	hci_skb_pkt_type(new_skb) = pkt_type;
-	skb_put_data(new_skb, skb->data, plen);
+	hci_skb_pkt_type(skb) = pkt_type;
 	hdev->stat.byte_rx += plen;
+	skb_trim(skb, plen);
 
 	if (pcie_pkt_type == BTINTEL_PCIE_HCI_EVT_PKT)
-		ret = btintel_pcie_recv_event(hdev, new_skb);
+		ret = btintel_pcie_recv_event(hdev, skb);
 	else
-		ret = hci_recv_frame(hdev, new_skb);
+		ret = hci_recv_frame(hdev, skb);
+	skb = NULL; /* skb is freed in the callee  */
 
 exit_error:
+	if (skb)
+		kfree_skb(skb);
+
 	if (ret)
 		hdev->stat.err_rx++;
 
@@ -705,16 +708,10 @@ static void btintel_pcie_rx_work(struct work_struct *work)
 	struct btintel_pcie_data *data = container_of(work,
 					struct btintel_pcie_data, rx_work);
 	struct sk_buff *skb;
-	int err;
-	struct hci_dev *hdev = data->hdev;
 
 	/* Process the sk_buf in queue and send to the HCI layer */
 	while ((skb = skb_dequeue(&data->rx_skb_q))) {
-		err = btintel_pcie_recv_frame(data, skb);
-		if (err)
-			bt_dev_err(hdev, "Failed to send received frame: %d",
-				   err);
-		kfree_skb(skb);
+		btintel_pcie_recv_frame(data, skb);
 	}
 }
 
@@ -769,10 +766,8 @@ static void btintel_pcie_msix_rx_handle(struct btintel_pcie_data *data)
 	bt_dev_dbg(hdev, "RXQ: cr_hia: %u  cr_tia: %u", cr_hia, cr_tia);
 
 	/* Check CR_TIA and CR_HIA for change */
-	if (cr_tia == cr_hia) {
-		bt_dev_warn(hdev, "RXQ: no new CD found");
+	if (cr_tia == cr_hia)
 		return;
-	}
 
 	rxq = &data->rxq;
 
@@ -808,6 +803,16 @@ static irqreturn_t btintel_pcie_msix_isr(int irq, void *data)
 	return IRQ_WAKE_THREAD;
 }
 
+static inline bool btintel_pcie_is_rxq_empty(struct btintel_pcie_data *data)
+{
+	return data->ia.cr_hia[BTINTEL_PCIE_RXQ_NUM] == data->ia.cr_tia[BTINTEL_PCIE_RXQ_NUM];
+}
+
+static inline bool btintel_pcie_is_txackq_empty(struct btintel_pcie_data *data)
+{
+	return data->ia.cr_tia[BTINTEL_PCIE_TXQ_NUM] == data->ia.cr_hia[BTINTEL_PCIE_TXQ_NUM];
+}
+
 static irqreturn_t btintel_pcie_irq_msix_handler(int irq, void *dev_id)
 {
 	struct msix_entry *entry = dev_id;
@@ -835,12 +840,18 @@ static irqreturn_t btintel_pcie_irq_msix_handler(int irq, void *dev_id)
 		btintel_pcie_msix_gp0_handler(data);
 
 	/* For TX */
-	if (intr_fh & BTINTEL_PCIE_MSIX_FH_INT_CAUSES_0)
+	if (intr_fh & BTINTEL_PCIE_MSIX_FH_INT_CAUSES_0) {
 		btintel_pcie_msix_tx_handle(data);
+		if (!btintel_pcie_is_rxq_empty(data))
+			btintel_pcie_msix_rx_handle(data);
+	}
 
 	/* For RX */
-	if (intr_fh & BTINTEL_PCIE_MSIX_FH_INT_CAUSES_1)
+	if (intr_fh & BTINTEL_PCIE_MSIX_FH_INT_CAUSES_1) {
 		btintel_pcie_msix_rx_handle(data);
+		if (!btintel_pcie_is_txackq_empty(data))
+			btintel_pcie_msix_tx_handle(data);
+	}
 
 	/*
 	 * Before sending the interrupt the HW disables it to prevent a nested
@@ -1141,8 +1152,8 @@ static int btintel_pcie_alloc(struct btintel_pcie_data *data)
 	 *  + size of index * Number of queues(2) * type of index array(4)
 	 *  + size of context information
 	 */
-	total = (sizeof(struct tfd) + sizeof(struct urbd0) + sizeof(struct frbd)
-		+ sizeof(struct urbd1)) * BTINTEL_DESCS_COUNT;
+	total = (sizeof(struct tfd) + sizeof(struct urbd0)) * BTINTEL_PCIE_TX_DESCS_COUNT;
+	total += (sizeof(struct frbd) + sizeof(struct urbd1)) * BTINTEL_PCIE_RX_DESCS_COUNT;
 
 	/* Add the sum of size of index array and size of ci struct */
 	total += (sizeof(u16) * BTINTEL_PCIE_NUM_QUEUES * 4) + sizeof(struct ctx_info);
@@ -1167,36 +1178,36 @@ static int btintel_pcie_alloc(struct btintel_pcie_data *data)
 	data->dma_v_addr = v_addr;
 
 	/* Setup descriptor count */
-	data->txq.count = BTINTEL_DESCS_COUNT;
-	data->rxq.count = BTINTEL_DESCS_COUNT;
+	data->txq.count = BTINTEL_PCIE_TX_DESCS_COUNT;
+	data->rxq.count = BTINTEL_PCIE_RX_DESCS_COUNT;
 
 	/* Setup tfds */
 	data->txq.tfds_p_addr = p_addr;
 	data->txq.tfds = v_addr;
 
-	p_addr += (sizeof(struct tfd) * BTINTEL_DESCS_COUNT);
-	v_addr += (sizeof(struct tfd) * BTINTEL_DESCS_COUNT);
+	p_addr += (sizeof(struct tfd) * BTINTEL_PCIE_TX_DESCS_COUNT);
+	v_addr += (sizeof(struct tfd) * BTINTEL_PCIE_TX_DESCS_COUNT);
 
 	/* Setup urbd0 */
 	data->txq.urbd0s_p_addr = p_addr;
 	data->txq.urbd0s = v_addr;
 
-	p_addr += (sizeof(struct urbd0) * BTINTEL_DESCS_COUNT);
-	v_addr += (sizeof(struct urbd0) * BTINTEL_DESCS_COUNT);
+	p_addr += (sizeof(struct urbd0) * BTINTEL_PCIE_TX_DESCS_COUNT);
+	v_addr += (sizeof(struct urbd0) * BTINTEL_PCIE_TX_DESCS_COUNT);
 
 	/* Setup FRBD*/
 	data->rxq.frbds_p_addr = p_addr;
 	data->rxq.frbds = v_addr;
 
-	p_addr += (sizeof(struct frbd) * BTINTEL_DESCS_COUNT);
-	v_addr += (sizeof(struct frbd) * BTINTEL_DESCS_COUNT);
+	p_addr += (sizeof(struct frbd) * BTINTEL_PCIE_RX_DESCS_COUNT);
+	v_addr += (sizeof(struct frbd) * BTINTEL_PCIE_RX_DESCS_COUNT);
 
 	/* Setup urbd1 */
 	data->rxq.urbd1s_p_addr = p_addr;
 	data->rxq.urbd1s = v_addr;
 
-	p_addr += (sizeof(struct urbd1) * BTINTEL_DESCS_COUNT);
-	v_addr += (sizeof(struct urbd1) * BTINTEL_DESCS_COUNT);
+	p_addr += (sizeof(struct urbd1) * BTINTEL_PCIE_RX_DESCS_COUNT);
+	v_addr += (sizeof(struct urbd1) * BTINTEL_PCIE_RX_DESCS_COUNT);
 
 	/* Setup data buffers for txq */
 	err = btintel_pcie_setup_txq_bufs(data, &data->txq);
@@ -1312,6 +1323,10 @@ static int btintel_pcie_send_frame(struct hci_dev *hdev,
 			if (opcode == 0xfc01)
 				btintel_pcie_inject_cmd_complete(hdev, opcode);
 		}
+		/* Firmware raises alive interrupt on HCI_OP_RESET */
+		if (opcode == HCI_OP_RESET)
+			data->gp0_received = false;
+
 		hdev->stat.cmd_tx++;
 		break;
 	case HCI_ACLDATA_PKT:
@@ -1349,7 +1364,6 @@ static int btintel_pcie_send_frame(struct hci_dev *hdev,
 			   opcode, btintel_pcie_alivectxt_state2str(old_ctxt),
 			   btintel_pcie_alivectxt_state2str(data->alive_intr_ctxt));
 		if (opcode == HCI_OP_RESET) {
-			data->gp0_received = false;
 			ret = wait_event_timeout(data->gp0_wait_q,
 						 data->gp0_received,
 						 msecs_to_jiffies(BTINTEL_DEFAULT_INTR_TIMEOUT_MS));
diff --git a/drivers/bluetooth/btintel_pcie.h b/drivers/bluetooth/btintel_pcie.h
index 8b7824ad005a..ee0eec0237af 100644
--- a/drivers/bluetooth/btintel_pcie.h
+++ b/drivers/bluetooth/btintel_pcie.h
@@ -81,8 +81,11 @@ enum {
 /* Default interrupt timeout in msec */
 #define BTINTEL_DEFAULT_INTR_TIMEOUT_MS	3000
 
-/* The number of descriptors in TX/RX queues */
-#define BTINTEL_DESCS_COUNT	16
+/* The number of descriptors in TX queues */
+#define BTINTEL_PCIE_TX_DESCS_COUNT	32
+
+/* The number of descriptors in RX queues */
+#define BTINTEL_PCIE_RX_DESCS_COUNT	64
 
 /* Number of Queue for TX and RX
  * It indicates the index of the IA(Index Array)
@@ -104,9 +107,6 @@ enum {
 /* Doorbell vector for TFD */
 #define BTINTEL_PCIE_TX_DB_VEC	0
 
-/* Number of pending RX requests for downlink */
-#define BTINTEL_PCIE_RX_MAX_QUEUE	6
-
 /* Doorbell vector for FRBD */
 #define BTINTEL_PCIE_RX_DB_VEC	513
 
diff --git a/drivers/bluetooth/btmtk.c b/drivers/bluetooth/btmtk.c
index af487abe9932..05de2e6f563d 100644
--- a/drivers/bluetooth/btmtk.c
+++ b/drivers/bluetooth/btmtk.c
@@ -1329,15 +1329,8 @@ int btmtk_usb_setup(struct hci_dev *hdev)
 		fwname = FIRMWARE_MT7668;
 		break;
 	case 0x7922:
-	case 0x7961:
 	case 0x7925:
-		/* Reset the device to ensure it's in the initial state before
-		 * downloading the firmware to ensure.
-		 */
-
-		if (!test_bit(BTMTK_FIRMWARE_LOADED, &btmtk_data->flags))
-			btmtk_usb_subsys_reset(hdev, dev_id);
-
+	case 0x7961:
 		btmtk_fw_get_filename(fw_bin_name, sizeof(fw_bin_name), dev_id,
 				      fw_version, fw_flavor);
 
@@ -1345,12 +1338,9 @@ int btmtk_usb_setup(struct hci_dev *hdev)
 						btmtk_usb_hci_wmt_sync);
 		if (err < 0) {
 			bt_dev_err(hdev, "Failed to set up firmware (%d)", err);
-			clear_bit(BTMTK_FIRMWARE_LOADED, &btmtk_data->flags);
 			return err;
 		}
 
-		set_bit(BTMTK_FIRMWARE_LOADED, &btmtk_data->flags);
-
 		/* It's Device EndPoint Reset Option Register */
 		err = btmtk_usb_uhw_reg_write(hdev, MTK_EP_RST_OPT,
 					      MTK_EP_RST_IN_OUT_OPT);
diff --git a/drivers/bluetooth/btmtksdio.c b/drivers/bluetooth/btmtksdio.c
index 11d33cd7b08f..13dcc0077732 100644
--- a/drivers/bluetooth/btmtksdio.c
+++ b/drivers/bluetooth/btmtksdio.c
@@ -610,7 +610,8 @@ static void btmtksdio_txrx_work(struct work_struct *work)
 	} while (int_status || time_is_before_jiffies(txrx_timeout));
 
 	/* Enable interrupt */
-	sdio_writel(bdev->func, C_INT_EN_SET, MTK_REG_CHLPCR, NULL);
+	if (bdev->func->irq_handler)
+		sdio_writel(bdev->func, C_INT_EN_SET, MTK_REG_CHLPCR, NULL);
 
 	sdio_release_host(bdev->func);
 
@@ -722,6 +723,10 @@ static int btmtksdio_close(struct hci_dev *hdev)
 {
 	struct btmtksdio_dev *bdev = hci_get_drvdata(hdev);
 
+	/* Skip btmtksdio_close if BTMTKSDIO_FUNC_ENABLED isn't set */
+	if (!test_bit(BTMTKSDIO_FUNC_ENABLED, &bdev->tx_state))
+		return 0;
+
 	sdio_claim_host(bdev->func);
 
 	/* Disable interrupt */
@@ -1429,11 +1434,15 @@ static void btmtksdio_remove(struct sdio_func *func)
 	if (!bdev)
 		return;
 
+	hdev = bdev->hdev;
+
+	/* Make sure to call btmtksdio_close before removing sdio card */
+	if (test_bit(BTMTKSDIO_FUNC_ENABLED, &bdev->tx_state))
+		btmtksdio_close(hdev);
+
 	/* Be consistent the state in btmtksdio_probe */
 	pm_runtime_get_noresume(bdev->dev);
 
-	hdev = bdev->hdev;
-
 	sdio_set_drvdata(func, NULL);
 	hci_unregister_dev(hdev);
 	hci_free_dev(hdev);
diff --git a/drivers/bluetooth/btnxpuart.c b/drivers/bluetooth/btnxpuart.c
index a028984f2782..56b875a6b1fb 100644
--- a/drivers/bluetooth/btnxpuart.c
+++ b/drivers/bluetooth/btnxpuart.c
@@ -612,8 +612,10 @@ static int nxp_download_firmware(struct hci_dev *hdev)
 							 &nxpdev->tx_state),
 					       msecs_to_jiffies(60000));
 
-	release_firmware(nxpdev->fw);
-	memset(nxpdev->fw_name, 0, sizeof(nxpdev->fw_name));
+	if (nxpdev->fw && strlen(nxpdev->fw_name)) {
+		release_firmware(nxpdev->fw);
+		memset(nxpdev->fw_name, 0, sizeof(nxpdev->fw_name));
+	}
 
 	if (err == 0) {
 		bt_dev_err(hdev, "FW Download Timeout. offset: %d",
@@ -1336,13 +1338,12 @@ static void btnxpuart_tx_work(struct work_struct *work)
 
 	while ((skb = nxp_dequeue(nxpdev))) {
 		len = serdev_device_write_buf(serdev, skb->data, skb->len);
-		serdev_device_wait_until_sent(serdev, 0);
 		hdev->stat.byte_tx += len;
 
 		skb_pull(skb, len);
 		if (skb->len > 0) {
 			skb_queue_head(&nxpdev->txq, skb);
-			break;
+			continue;
 		}
 
 		switch (hci_skb_pkt_type(skb)) {
diff --git a/drivers/bluetooth/btqca.c b/drivers/bluetooth/btqca.c
index dfbbac92242a..dd2c0485b984 100644
--- a/drivers/bluetooth/btqca.c
+++ b/drivers/bluetooth/btqca.c
@@ -272,6 +272,39 @@ int qca_send_pre_shutdown_cmd(struct hci_dev *hdev)
 }
 EXPORT_SYMBOL_GPL(qca_send_pre_shutdown_cmd);
 
+static bool qca_filename_has_extension(const char *filename)
+{
+	const char *suffix = strrchr(filename, '.');
+
+	/* File extensions require a dot, but not as the first or last character */
+	if (!suffix || suffix == filename || *(suffix + 1) == '\0')
+		return 0;
+
+	/* Avoid matching directories with names that look like files with extensions */
+	return !strchr(suffix, '/');
+}
+
+static bool qca_get_alt_nvm_file(char *filename, size_t max_size)
+{
+	char fwname[64];
+	const char *suffix;
+
+	/* nvm file name has an extension, replace with .bin */
+	if (qca_filename_has_extension(filename)) {
+		suffix = strrchr(filename, '.');
+		strscpy(fwname, filename, suffix - filename + 1);
+		snprintf(fwname + (suffix - filename),
+		       sizeof(fwname) - (suffix - filename), ".bin");
+		/* If nvm file is already the default one, return false to skip the retry. */
+		if (strcmp(fwname, filename) == 0)
+			return false;
+
+		snprintf(filename, max_size, "%s", fwname);
+		return true;
+	}
+	return false;
+}
+
 static int qca_tlv_check_data(struct hci_dev *hdev,
 			       struct qca_fw_config *config,
 			       u8 *fw_data, size_t fw_size,
@@ -564,6 +597,19 @@ static int qca_download_firmware(struct hci_dev *hdev,
 					   config->fwname, ret);
 				return ret;
 			}
+		}
+		/* If the board-specific file is missing, try loading the default
+		 * one, unless that was attempted already.
+		 */
+		else if (config->type == TLV_TYPE_NVM &&
+			 qca_get_alt_nvm_file(config->fwname, sizeof(config->fwname))) {
+			bt_dev_info(hdev, "QCA Downloading %s", config->fwname);
+			ret = request_firmware(&fw, config->fwname, &hdev->dev);
+			if (ret) {
+				bt_dev_err(hdev, "QCA Failed to request file: %s (%d)",
+					   config->fwname, ret);
+				return ret;
+			}
 		} else {
 			bt_dev_err(hdev, "QCA Failed to request file: %s (%d)",
 				   config->fwname, ret);
@@ -700,34 +746,38 @@ static int qca_check_bdaddr(struct hci_dev *hdev, const struct qca_fw_config *co
 	return 0;
 }
 
-static void qca_generate_hsp_nvm_name(char *fwname, size_t max_size,
+static void qca_get_nvm_name_by_board(char *fwname, size_t max_size,
+		const char *stem, enum qca_btsoc_type soc_type,
 		struct qca_btsoc_version ver, u8 rom_ver, u16 bid)
 {
 	const char *variant;
+	const char *prefix;
 
-	/* hsp gf chip */
-	if ((le32_to_cpu(ver.soc_id) & QCA_HSP_GF_SOC_MASK) == QCA_HSP_GF_SOC_ID)
-		variant = "g";
-	else
-		variant = "";
+	/* Set the default value to variant and prefix */
+	variant = "";
+	prefix = "b";
 
-	if (bid == 0x0)
-		snprintf(fwname, max_size, "qca/hpnv%02x%s.bin", rom_ver, variant);
-	else
-		snprintf(fwname, max_size, "qca/hpnv%02x%s.%x", rom_ver, variant, bid);
-}
+	if (soc_type == QCA_QCA2066)
+		prefix = "";
 
-static inline void qca_get_nvm_name_generic(struct qca_fw_config *cfg,
-					    const char *stem, u8 rom_ver, u16 bid)
-{
-	if (bid == 0x0)
-		snprintf(cfg->fwname, sizeof(cfg->fwname), "qca/%snv%02x.bin", stem, rom_ver);
-	else if (bid & 0xff00)
-		snprintf(cfg->fwname, sizeof(cfg->fwname),
-			 "qca/%snv%02x.b%x", stem, rom_ver, bid);
-	else
-		snprintf(cfg->fwname, sizeof(cfg->fwname),
-			 "qca/%snv%02x.b%02x", stem, rom_ver, bid);
+	if (soc_type == QCA_WCN6855 || soc_type == QCA_QCA2066) {
+		/* If the chip is manufactured by GlobalFoundries */
+		if ((le32_to_cpu(ver.soc_id) & QCA_HSP_GF_SOC_MASK) == QCA_HSP_GF_SOC_ID)
+			variant = "g";
+	}
+
+	if (rom_ver != 0) {
+		if (bid == 0x0 || bid == 0xffff)
+			snprintf(fwname, max_size, "qca/%s%02x%s.bin", stem, rom_ver, variant);
+		else
+			snprintf(fwname, max_size, "qca/%s%02x%s.%s%02x", stem, rom_ver,
+						variant, prefix, bid);
+	} else {
+		if (bid == 0x0 || bid == 0xffff)
+			snprintf(fwname, max_size, "qca/%s%s.bin", stem, variant);
+		else
+			snprintf(fwname, max_size, "qca/%s%s.%s%02x", stem, variant, prefix, bid);
+	}
 }
 
 int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate,
@@ -735,6 +785,7 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate,
 		   const char *firmware_name)
 {
 	struct qca_fw_config config = {};
+	const char *variant = "";
 	int err;
 	u8 rom_ver = 0;
 	u32 soc_ver;
@@ -816,28 +867,33 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate,
 	/* Download NVM configuration */
 	config.type = TLV_TYPE_NVM;
 	if (firmware_name) {
-		snprintf(config.fwname, sizeof(config.fwname),
-			 "qca/%s", firmware_name);
+		/* The firmware name has an extension, use it directly */
+		if (qca_filename_has_extension(firmware_name)) {
+			snprintf(config.fwname, sizeof(config.fwname), "qca/%s", firmware_name);
+		} else {
+			qca_read_fw_board_id(hdev, &boardid);
+			qca_get_nvm_name_by_board(config.fwname, sizeof(config.fwname),
+				 firmware_name, soc_type, ver, 0, boardid);
+		}
 	} else {
 		switch (soc_type) {
 		case QCA_WCN3990:
 		case QCA_WCN3991:
 		case QCA_WCN3998:
-			if (le32_to_cpu(ver.soc_id) == QCA_WCN3991_SOC_ID) {
-				snprintf(config.fwname, sizeof(config.fwname),
-					 "qca/crnv%02xu.bin", rom_ver);
-			} else {
-				snprintf(config.fwname, sizeof(config.fwname),
-					 "qca/crnv%02x.bin", rom_ver);
-			}
+			if (le32_to_cpu(ver.soc_id) == QCA_WCN3991_SOC_ID)
+				variant = "u";
+
+			snprintf(config.fwname, sizeof(config.fwname),
+				 "qca/crnv%02x%s.bin", rom_ver, variant);
 			break;
 		case QCA_WCN3988:
 			snprintf(config.fwname, sizeof(config.fwname),
 				 "qca/apnv%02x.bin", rom_ver);
 			break;
 		case QCA_QCA2066:
-			qca_generate_hsp_nvm_name(config.fwname,
-				sizeof(config.fwname), ver, rom_ver, boardid);
+			qca_get_nvm_name_by_board(config.fwname,
+				sizeof(config.fwname), "hpnv", soc_type, ver,
+				rom_ver, boardid);
 			break;
 		case QCA_QCA6390:
 			snprintf(config.fwname, sizeof(config.fwname),
@@ -848,13 +904,14 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate,
 				 "qca/msnv%02x.bin", rom_ver);
 			break;
 		case QCA_WCN6855:
-			snprintf(config.fwname, sizeof(config.fwname),
-				 "qca/hpnv%02x.bin", rom_ver);
+			qca_read_fw_board_id(hdev, &boardid);
+			qca_get_nvm_name_by_board(config.fwname, sizeof(config.fwname),
+						  "hpnv", soc_type, ver, rom_ver, boardid);
 			break;
 		case QCA_WCN7850:
-			qca_get_nvm_name_generic(&config, "hmt", rom_ver, boardid);
+			qca_get_nvm_name_by_board(config.fwname, sizeof(config.fwname),
+				 "hmtnv", soc_type, ver, rom_ver, boardid);
 			break;
-
 		default:
 			snprintf(config.fwname, sizeof(config.fwname),
 				 "qca/nvm_%08x.bin", soc_ver);
diff --git a/drivers/bluetooth/btrtl.c b/drivers/bluetooth/btrtl.c
index 0bcb44cf7b31..59eb94866422 100644
--- a/drivers/bluetooth/btrtl.c
+++ b/drivers/bluetooth/btrtl.c
@@ -1215,6 +1215,8 @@ next:
 			rtl_dev_err(hdev, "mandatory config file %s not found",
 				    btrtl_dev->ic_info->cfg_name);
 			ret = btrtl_dev->cfg_len;
+			if (!ret)
+				ret = -EINVAL;
 			goto err_free;
 		}
 	}
@@ -1351,12 +1353,14 @@ int btrtl_setup_realtek(struct hci_dev *hdev)
 
 	btrtl_set_quirks(hdev, btrtl_dev);
 
-	hci_set_hw_info(hdev,
+	if (btrtl_dev->ic_info) {
+		hci_set_hw_info(hdev,
 			"RTL lmp_subver=%u hci_rev=%u hci_ver=%u hci_bus=%u",
 			btrtl_dev->ic_info->lmp_subver,
 			btrtl_dev->ic_info->hci_rev,
 			btrtl_dev->ic_info->hci_ver,
 			btrtl_dev->ic_info->hci_bus);
+	}
 
 	btrtl_free(btrtl_dev);
 	return ret;
diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index 0c85c981a833..d7aaaeb4fe32 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -371,6 +371,42 @@ static const struct usb_device_id quirks_table[] = {
 	/* QCA WCN785x chipset */
 	{ USB_DEVICE(0x0cf3, 0xe700), .driver_info = BTUSB_QCA_WCN6855 |
 						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x0489, 0xe0fc), .driver_info = BTUSB_QCA_WCN6855 |
+						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x0489, 0xe0f3), .driver_info = BTUSB_QCA_WCN6855 |
+						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x0489, 0xe100), .driver_info = BTUSB_QCA_WCN6855 |
+						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x0489, 0xe103), .driver_info = BTUSB_QCA_WCN6855 |
+						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x0489, 0xe10a), .driver_info = BTUSB_QCA_WCN6855 |
+						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x0489, 0xe10d), .driver_info = BTUSB_QCA_WCN6855 |
+						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x0489, 0xe11b), .driver_info = BTUSB_QCA_WCN6855 |
+						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x0489, 0xe11c), .driver_info = BTUSB_QCA_WCN6855 |
+						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x0489, 0xe11f), .driver_info = BTUSB_QCA_WCN6855 |
+						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x0489, 0xe141), .driver_info = BTUSB_QCA_WCN6855 |
+						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x0489, 0xe14a), .driver_info = BTUSB_QCA_WCN6855 |
+						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x0489, 0xe14b), .driver_info = BTUSB_QCA_WCN6855 |
+						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x0489, 0xe14d), .driver_info = BTUSB_QCA_WCN6855 |
+						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x13d3, 0x3623), .driver_info = BTUSB_QCA_WCN6855 |
+						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x13d3, 0x3624), .driver_info = BTUSB_QCA_WCN6855 |
+						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x2c7c, 0x0130), .driver_info = BTUSB_QCA_WCN6855 |
+						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x2c7c, 0x0131), .driver_info = BTUSB_QCA_WCN6855 |
+						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x2c7c, 0x0132), .driver_info = BTUSB_QCA_WCN6855 |
+						     BTUSB_WIDEBAND_SPEECH },
 
 	/* Broadcom BCM2035 */
 	{ USB_DEVICE(0x0a5c, 0x2009), .driver_info = BTUSB_BCM92035 },
@@ -475,6 +511,10 @@ static const struct usb_device_id quirks_table[] = {
 	{ USB_DEVICE(0x13d3, 0x3549), .driver_info = BTUSB_REALTEK |
 						     BTUSB_WIDEBAND_SPEECH },
 
+	/* Realtek 8851BU Bluetooth devices */
+	{ USB_DEVICE(0x3625, 0x010b), .driver_info = BTUSB_REALTEK |
+						     BTUSB_WIDEBAND_SPEECH },
+
 	/* Realtek 8852AE Bluetooth devices */
 	{ USB_DEVICE(0x0bda, 0x2852), .driver_info = BTUSB_REALTEK |
 						     BTUSB_WIDEBAND_SPEECH },
@@ -604,6 +644,8 @@ static const struct usb_device_id quirks_table[] = {
 	/* MediaTek MT7922 Bluetooth devices */
 	{ USB_DEVICE(0x13d3, 0x3585), .driver_info = BTUSB_MEDIATEK |
 						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x13d3, 0x3610), .driver_info = BTUSB_MEDIATEK |
+						     BTUSB_WIDEBAND_SPEECH },
 
 	/* MediaTek MT7922A Bluetooth devices */
 	{ USB_DEVICE(0x0489, 0xe0d8), .driver_info = BTUSB_MEDIATEK |
@@ -624,12 +666,18 @@ static const struct usb_device_id quirks_table[] = {
 						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x0489, 0xe102), .driver_info = BTUSB_MEDIATEK |
 						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x0489, 0xe152), .driver_info = BTUSB_MEDIATEK |
+						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x0489, 0xe153), .driver_info = BTUSB_MEDIATEK |
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x04ca, 0x3804), .driver_info = BTUSB_MEDIATEK |
 						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x04ca, 0x38e4), .driver_info = BTUSB_MEDIATEK |
 						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x13d3, 0x3568), .driver_info = BTUSB_MEDIATEK |
 						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x13d3, 0x3584), .driver_info = BTUSB_MEDIATEK |
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x13d3, 0x3605), .driver_info = BTUSB_MEDIATEK |
 						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x13d3, 0x3607), .driver_info = BTUSB_MEDIATEK |
@@ -654,6 +702,8 @@ static const struct usb_device_id quirks_table[] = {
 						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x0489, 0xe139), .driver_info = BTUSB_MEDIATEK |
 						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x0489, 0xe14e), .driver_info = BTUSB_MEDIATEK |
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x0489, 0xe14f), .driver_info = BTUSB_MEDIATEK |
 						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x0489, 0xe150), .driver_info = BTUSB_MEDIATEK |
@@ -668,6 +718,10 @@ static const struct usb_device_id quirks_table[] = {
 						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x13d3, 0x3608), .driver_info = BTUSB_MEDIATEK |
 						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x13d3, 0x3628), .driver_info = BTUSB_MEDIATEK |
+						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x13d3, 0x3630), .driver_info = BTUSB_MEDIATEK |
+						     BTUSB_WIDEBAND_SPEECH },
 
 	/* Additional Realtek 8723AE Bluetooth devices */
 	{ USB_DEVICE(0x0930, 0x021d), .driver_info = BTUSB_REALTEK },
@@ -2632,8 +2686,15 @@ static void btusb_mtk_claim_iso_intf(struct btusb_data *data)
 	struct btmtk_data *btmtk_data = hci_get_priv(data->hdev);
 	int err;
 
+	/*
+	 * The function usb_driver_claim_interface() is documented to need
+	 * locks held if it's not called from a probe routine. The code here
+	 * is called from the hci_power_on workqueue, so grab the lock.
+	 */
+	device_lock(&btmtk_data->isopkt_intf->dev);
 	err = usb_driver_claim_interface(&btusb_driver,
 					 btmtk_data->isopkt_intf, data);
+	device_unlock(&btmtk_data->isopkt_intf->dev);
 	if (err < 0) {
 		btmtk_data->isopkt_intf = NULL;
 		bt_dev_err(data->hdev, "Failed to claim iso interface");
@@ -2924,55 +2985,27 @@ static void btusb_coredump_qca(struct hci_dev *hdev)
 		bt_dev_err(hdev, "%s: triggle crash failed (%d)", __func__, err);
 }
 
-/*
- * ==0: not a dump pkt.
- * < 0: fails to handle a dump pkt
- * > 0: otherwise.
- */
+/* Return: 0 on success, negative errno on failure. */
 static int handle_dump_pkt_qca(struct hci_dev *hdev, struct sk_buff *skb)
 {
-	int ret = 1;
+	int ret = 0;
+	unsigned int skip = 0;
 	u8 pkt_type;
-	u8 *sk_ptr;
-	unsigned int sk_len;
 	u16 seqno;
 	u32 dump_size;
 
-	struct hci_event_hdr *event_hdr;
-	struct hci_acl_hdr *acl_hdr;
 	struct qca_dump_hdr *dump_hdr;
 	struct btusb_data *btdata = hci_get_drvdata(hdev);
 	struct usb_device *udev = btdata->udev;
 
 	pkt_type = hci_skb_pkt_type(skb);
-	sk_ptr = skb->data;
-	sk_len = skb->len;
-
-	if (pkt_type == HCI_ACLDATA_PKT) {
-		acl_hdr = hci_acl_hdr(skb);
-		if (le16_to_cpu(acl_hdr->handle) != QCA_MEMDUMP_ACL_HANDLE)
-			return 0;
-		sk_ptr += HCI_ACL_HDR_SIZE;
-		sk_len -= HCI_ACL_HDR_SIZE;
-		event_hdr = (struct hci_event_hdr *)sk_ptr;
-	} else {
-		event_hdr = hci_event_hdr(skb);
-	}
-
-	if ((event_hdr->evt != HCI_VENDOR_PKT)
-		|| (event_hdr->plen != (sk_len - HCI_EVENT_HDR_SIZE)))
-		return 0;
+	skip = sizeof(struct hci_event_hdr);
+	if (pkt_type == HCI_ACLDATA_PKT)
+		skip += sizeof(struct hci_acl_hdr);
 
-	sk_ptr += HCI_EVENT_HDR_SIZE;
-	sk_len -= HCI_EVENT_HDR_SIZE;
+	skb_pull(skb, skip);
+	dump_hdr = (struct qca_dump_hdr *)skb->data;
 
-	dump_hdr = (struct qca_dump_hdr *)sk_ptr;
-	if ((sk_len < offsetof(struct qca_dump_hdr, data))
-		|| (dump_hdr->vse_class != QCA_MEMDUMP_VSE_CLASS)
-	    || (dump_hdr->msg_type != QCA_MEMDUMP_MSG_TYPE))
-		return 0;
-
-	/*it is dump pkt now*/
 	seqno = le16_to_cpu(dump_hdr->seqno);
 	if (seqno == 0) {
 		set_bit(BTUSB_HW_SSR_ACTIVE, &btdata->flags);
@@ -2992,16 +3025,15 @@ static int handle_dump_pkt_qca(struct hci_dev *hdev, struct sk_buff *skb)
 
 		btdata->qca_dump.ram_dump_size = dump_size;
 		btdata->qca_dump.ram_dump_seqno = 0;
-		sk_ptr += offsetof(struct qca_dump_hdr, data0);
-		sk_len -= offsetof(struct qca_dump_hdr, data0);
+
+		skb_pull(skb, offsetof(struct qca_dump_hdr, data0));
 
 		usb_disable_autosuspend(udev);
 		bt_dev_info(hdev, "%s memdump size(%u)\n",
 			    (pkt_type == HCI_ACLDATA_PKT) ? "ACL" : "event",
 			    dump_size);
 	} else {
-		sk_ptr += offsetof(struct qca_dump_hdr, data);
-		sk_len -= offsetof(struct qca_dump_hdr, data);
+		skb_pull(skb, offsetof(struct qca_dump_hdr, data));
 	}
 
 	if (!btdata->qca_dump.ram_dump_size) {
@@ -3021,7 +3053,6 @@ static int handle_dump_pkt_qca(struct hci_dev *hdev, struct sk_buff *skb)
 		return ret;
 	}
 
-	skb_pull(skb, skb->len - sk_len);
 	hci_devcd_append(hdev, skb);
 	btdata->qca_dump.ram_dump_seqno++;
 	if (seqno == QCA_LAST_SEQUENCE_NUM) {
@@ -3046,17 +3077,74 @@ out:
 	return ret;
 }
 
+/* Return: true if the ACL packet is a dump packet, false otherwise. */
+static bool acl_pkt_is_dump_qca(struct hci_dev *hdev, struct sk_buff *skb)
+{
+	struct hci_event_hdr *event_hdr;
+	struct hci_acl_hdr *acl_hdr;
+	struct qca_dump_hdr *dump_hdr;
+	struct sk_buff *clone = skb_clone(skb, GFP_ATOMIC);
+	bool is_dump = false;
+
+	if (!clone)
+		return false;
+
+	acl_hdr = skb_pull_data(clone, sizeof(*acl_hdr));
+	if (!acl_hdr || (le16_to_cpu(acl_hdr->handle) != QCA_MEMDUMP_ACL_HANDLE))
+		goto out;
+
+	event_hdr = skb_pull_data(clone, sizeof(*event_hdr));
+	if (!event_hdr || (event_hdr->evt != HCI_VENDOR_PKT))
+		goto out;
+
+	dump_hdr = skb_pull_data(clone, sizeof(*dump_hdr));
+	if (!dump_hdr || (dump_hdr->vse_class != QCA_MEMDUMP_VSE_CLASS) ||
+	   (dump_hdr->msg_type != QCA_MEMDUMP_MSG_TYPE))
+		goto out;
+
+	is_dump = true;
+out:
+	consume_skb(clone);
+	return is_dump;
+}
+
+/* Return: true if the event packet is a dump packet, false otherwise. */
+static bool evt_pkt_is_dump_qca(struct hci_dev *hdev, struct sk_buff *skb)
+{
+	struct hci_event_hdr *event_hdr;
+	struct qca_dump_hdr *dump_hdr;
+	struct sk_buff *clone = skb_clone(skb, GFP_ATOMIC);
+	bool is_dump = false;
+
+	if (!clone)
+		return false;
+
+	event_hdr = skb_pull_data(clone, sizeof(*event_hdr));
+	if (!event_hdr || (event_hdr->evt != HCI_VENDOR_PKT))
+		goto out;
+
+	dump_hdr = skb_pull_data(clone, sizeof(*dump_hdr));
+	if (!dump_hdr || (dump_hdr->vse_class != QCA_MEMDUMP_VSE_CLASS) ||
+	   (dump_hdr->msg_type != QCA_MEMDUMP_MSG_TYPE))
+		goto out;
+
+	is_dump = true;
+out:
+	consume_skb(clone);
+	return is_dump;
+}
+
 static int btusb_recv_acl_qca(struct hci_dev *hdev, struct sk_buff *skb)
 {
-	if (handle_dump_pkt_qca(hdev, skb))
-		return 0;
+	if (acl_pkt_is_dump_qca(hdev, skb))
+		return handle_dump_pkt_qca(hdev, skb);
 	return hci_recv_frame(hdev, skb);
 }
 
 static int btusb_recv_evt_qca(struct hci_dev *hdev, struct sk_buff *skb)
 {
-	if (handle_dump_pkt_qca(hdev, skb))
-		return 0;
+	if (evt_pkt_is_dump_qca(hdev, skb))
+		return handle_dump_pkt_qca(hdev, skb);
 	return hci_recv_frame(hdev, skb);
 }
 
@@ -3112,6 +3200,32 @@ static const struct qca_device_info qca_devices_table[] = {
 	{ 0x00190200, 40, 4, 16 }, /* WCN785x 2.0 */
 };
 
+static u16 qca_extract_board_id(const struct qca_version *ver)
+{
+	u16 flag = le16_to_cpu(ver->flag);
+	u16 board_id = 0;
+
+	if (((flag >> 8) & 0xff) == QCA_FLAG_MULTI_NVM) {
+		/* The board_id should be split into two bytes
+		 * The 1st byte is chip ID, and the 2nd byte is platform ID
+		 * For example, board ID 0x010A, 0x01 is platform ID. 0x0A is chip ID
+		 * we have several platforms, and platform IDs are continuously added
+		 * Platform ID:
+		 * 0x00 is for Mobile
+		 * 0x01 is for X86
+		 * 0x02 is for Automotive
+		 * 0x03 is for Consumer electronic
+		 */
+		board_id = (ver->chip_id << 8) + ver->platform_id;
+	}
+
+	/* Take 0xffff as invalid board ID */
+	if (board_id == 0xffff)
+		board_id = 0;
+
+	return board_id;
+}
+
 static int btusb_qca_send_vendor_req(struct usb_device *udev, u8 request,
 				     void *data, u16 size)
 {
@@ -3268,44 +3382,28 @@ static void btusb_generate_qca_nvm_name(char *fwname, size_t max_size,
 					const struct qca_version *ver)
 {
 	u32 rom_version = le32_to_cpu(ver->rom_version);
-	u16 flag = le16_to_cpu(ver->flag);
-
-	if (((flag >> 8) & 0xff) == QCA_FLAG_MULTI_NVM) {
-		/* The board_id should be split into two bytes
-		 * The 1st byte is chip ID, and the 2nd byte is platform ID
-		 * For example, board ID 0x010A, 0x01 is platform ID. 0x0A is chip ID
-		 * we have several platforms, and platform IDs are continuously added
-		 * Platform ID:
-		 * 0x00 is for Mobile
-		 * 0x01 is for X86
-		 * 0x02 is for Automotive
-		 * 0x03 is for Consumer electronic
-		 */
-		u16 board_id = (ver->chip_id << 8) + ver->platform_id;
-		const char *variant;
+	const char *variant;
+	int len;
+	u16 board_id;
 
-		switch (le32_to_cpu(ver->ram_version)) {
-		case WCN6855_2_0_RAM_VERSION_GF:
-		case WCN6855_2_1_RAM_VERSION_GF:
-			variant = "_gf";
-			break;
-		default:
-			variant = "";
-			break;
-		}
+	board_id = qca_extract_board_id(ver);
 
-		if (board_id == 0) {
-			snprintf(fwname, max_size, "qca/nvm_usb_%08x%s.bin",
-				rom_version, variant);
-		} else {
-			snprintf(fwname, max_size, "qca/nvm_usb_%08x%s_%04x.bin",
-				rom_version, variant, board_id);
-		}
-	} else {
-		snprintf(fwname, max_size, "qca/nvm_usb_%08x.bin",
-			rom_version);
+	switch (le32_to_cpu(ver->ram_version)) {
+	case WCN6855_2_0_RAM_VERSION_GF:
+	case WCN6855_2_1_RAM_VERSION_GF:
+		variant = "_gf";
+		break;
+	default:
+		variant = NULL;
+		break;
 	}
 
+	len = snprintf(fwname, max_size, "qca/nvm_usb_%08x", rom_version);
+	if (variant)
+		len += snprintf(fwname + len, max_size - len, "%s", variant);
+	if (board_id)
+		len += snprintf(fwname + len, max_size - len, "_%04x", board_id);
+	len += snprintf(fwname + len, max_size - len, ".bin");
 }
 
 static int btusb_setup_qca_load_nvm(struct hci_dev *hdev,
@@ -3633,6 +3731,7 @@ static ssize_t force_poll_sync_write(struct file *file,
 }
 
 static const struct file_operations force_poll_sync_fops = {
+	.owner		= THIS_MODULE,
 	.open		= simple_open,
 	.read		= force_poll_sync_read,
 	.write		= force_poll_sync_write,
diff --git a/drivers/bluetooth/hci_ldisc.c b/drivers/bluetooth/hci_ldisc.c
index 395d66e32a2e..2f322f890b81 100644
--- a/drivers/bluetooth/hci_ldisc.c
+++ b/drivers/bluetooth/hci_ldisc.c
@@ -102,7 +102,8 @@ static inline struct sk_buff *hci_uart_dequeue(struct hci_uart *hu)
 	if (!skb) {
 		percpu_down_read(&hu->proto_lock);
 
-		if (test_bit(HCI_UART_PROTO_READY, &hu->flags))
+		if (test_bit(HCI_UART_PROTO_READY, &hu->flags) ||
+		    test_bit(HCI_UART_PROTO_INIT, &hu->flags))
 			skb = hu->proto->dequeue(hu);
 
 		percpu_up_read(&hu->proto_lock);
@@ -124,7 +125,8 @@ int hci_uart_tx_wakeup(struct hci_uart *hu)
 	if (!percpu_down_read_trylock(&hu->proto_lock))
 		return 0;
 
-	if (!test_bit(HCI_UART_PROTO_READY, &hu->flags))
+	if (!test_bit(HCI_UART_PROTO_READY, &hu->flags) &&
+	    !test_bit(HCI_UART_PROTO_INIT, &hu->flags))
 		goto no_schedule;
 
 	set_bit(HCI_UART_TX_WAKEUP, &hu->tx_state);
@@ -278,7 +280,8 @@ static int hci_uart_send_frame(struct hci_dev *hdev, struct sk_buff *skb)
 
 	percpu_down_read(&hu->proto_lock);
 
-	if (!test_bit(HCI_UART_PROTO_READY, &hu->flags)) {
+	if (!test_bit(HCI_UART_PROTO_READY, &hu->flags) &&
+	    !test_bit(HCI_UART_PROTO_INIT, &hu->flags)) {
 		percpu_up_read(&hu->proto_lock);
 		return -EUNATCH;
 	}
@@ -585,7 +588,8 @@ static void hci_uart_tty_wakeup(struct tty_struct *tty)
 	if (tty != hu->tty)
 		return;
 
-	if (test_bit(HCI_UART_PROTO_READY, &hu->flags))
+	if (test_bit(HCI_UART_PROTO_READY, &hu->flags) ||
+	    test_bit(HCI_UART_PROTO_INIT, &hu->flags))
 		hci_uart_tx_wakeup(hu);
 }
 
@@ -611,7 +615,8 @@ static void hci_uart_tty_receive(struct tty_struct *tty, const u8 *data,
 
 	percpu_down_read(&hu->proto_lock);
 
-	if (!test_bit(HCI_UART_PROTO_READY, &hu->flags)) {
+	if (!test_bit(HCI_UART_PROTO_READY, &hu->flags) &&
+	    !test_bit(HCI_UART_PROTO_INIT, &hu->flags)) {
 		percpu_up_read(&hu->proto_lock);
 		return;
 	}
@@ -707,12 +712,16 @@ static int hci_uart_set_proto(struct hci_uart *hu, int id)
 
 	hu->proto = p;
 
+	set_bit(HCI_UART_PROTO_INIT, &hu->flags);
+
 	err = hci_uart_register_dev(hu);
 	if (err) {
 		return err;
 	}
 
 	set_bit(HCI_UART_PROTO_READY, &hu->flags);
+	clear_bit(HCI_UART_PROTO_INIT, &hu->flags);
+
 	return 0;
 }
 
diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c
index 37fddf6055be..e6ad01d5e1d5 100644
--- a/drivers/bluetooth/hci_qca.c
+++ b/drivers/bluetooth/hci_qca.c
@@ -2353,6 +2353,7 @@ static int qca_serdev_probe(struct serdev_device *serdev)
 	switch (qcadev->btsoc_type) {
 	case QCA_WCN6855:
 	case QCA_WCN7850:
+	case QCA_WCN6750:
 		if (!device_property_present(&serdev->dev, "enable-gpios")) {
 			/*
 			 * Backward compatibility with old DT sources. If the
@@ -2362,17 +2363,23 @@ static int qca_serdev_probe(struct serdev_device *serdev)
 			 */
 			qcadev->bt_power->pwrseq = devm_pwrseq_get(&serdev->dev,
 								   "bluetooth");
-			if (IS_ERR(qcadev->bt_power->pwrseq))
-				return PTR_ERR(qcadev->bt_power->pwrseq);
 
-			break;
+			/*
+			 * Some modules have BT_EN enabled via a hardware pull-up,
+			 * meaning it is not defined in the DTS and is not controlled
+			 * through the power sequence. In such cases, fall through
+			 * to follow the legacy flow.
+			 */
+			if (IS_ERR(qcadev->bt_power->pwrseq))
+				qcadev->bt_power->pwrseq = NULL;
+			else
+				break;
 		}
 		fallthrough;
 	case QCA_WCN3988:
 	case QCA_WCN3990:
 	case QCA_WCN3991:
 	case QCA_WCN3998:
-	case QCA_WCN6750:
 		qcadev->bt_power->dev = &serdev->dev;
 		err = qca_init_regulators(qcadev->bt_power, data->vregs,
 					  data->num_vregs);
@@ -2385,14 +2392,14 @@ static int qca_serdev_probe(struct serdev_device *serdev)
 
 		qcadev->bt_en = devm_gpiod_get_optional(&serdev->dev, "enable",
 					       GPIOD_OUT_LOW);
-		if (IS_ERR(qcadev->bt_en) &&
-		    (data->soc_type == QCA_WCN6750 ||
-		     data->soc_type == QCA_WCN6855)) {
-			dev_err(&serdev->dev, "failed to acquire BT_EN gpio\n");
-			return PTR_ERR(qcadev->bt_en);
-		}
+		if (IS_ERR(qcadev->bt_en))
+			return dev_err_probe(&serdev->dev,
+					     PTR_ERR(qcadev->bt_en),
+					     "failed to acquire BT_EN gpio\n");
 
-		if (!qcadev->bt_en)
+		if (!qcadev->bt_en &&
+		    (data->soc_type == QCA_WCN6750 ||
+		     data->soc_type == QCA_WCN6855))
 			power_ctrl_enabled = false;
 
 		qcadev->sw_ctrl = devm_gpiod_get_optional(&serdev->dev, "swctrl",
diff --git a/drivers/bluetooth/hci_uart.h b/drivers/bluetooth/hci_uart.h
index fbf3079b92a5..5ea5dd80e297 100644
--- a/drivers/bluetooth/hci_uart.h
+++ b/drivers/bluetooth/hci_uart.h
@@ -90,6 +90,7 @@ struct hci_uart {
 #define HCI_UART_REGISTERED		1
 #define HCI_UART_PROTO_READY		2
 #define HCI_UART_NO_SUSPEND_NOTIFIER	3
+#define HCI_UART_PROTO_INIT		4
 
 /* TX states  */
 #define HCI_UART_SENDING	1
diff --git a/drivers/bluetooth/hci_vhci.c b/drivers/bluetooth/hci_vhci.c
index 7651321d351c..9ac22e4a070b 100644
--- a/drivers/bluetooth/hci_vhci.c
+++ b/drivers/bluetooth/hci_vhci.c
@@ -289,18 +289,18 @@ static void vhci_coredump(struct hci_dev *hdev)
 
 static void vhci_coredump_hdr(struct hci_dev *hdev, struct sk_buff *skb)
 {
-	char buf[80];
+	const char *buf;
 
-	snprintf(buf, sizeof(buf), "Controller Name: vhci_ctrl\n");
+	buf = "Controller Name: vhci_ctrl\n";
 	skb_put_data(skb, buf, strlen(buf));
 
-	snprintf(buf, sizeof(buf), "Firmware Version: vhci_fw\n");
+	buf = "Firmware Version: vhci_fw\n";
 	skb_put_data(skb, buf, strlen(buf));
 
-	snprintf(buf, sizeof(buf), "Driver: vhci_drv\n");
+	buf = "Driver: vhci_drv\n";
 	skb_put_data(skb, buf, strlen(buf));
 
-	snprintf(buf, sizeof(buf), "Vendor: vhci\n");
+	buf = "Vendor: vhci\n";
 	skb_put_data(skb, buf, strlen(buf));
 }
 
diff --git a/drivers/bus/fsl-mc/fsl-mc-bus.c b/drivers/bus/fsl-mc/fsl-mc-bus.c
index 930d8a3ba722..4575d9a4e5ed 100644
--- a/drivers/bus/fsl-mc/fsl-mc-bus.c
+++ b/drivers/bus/fsl-mc/fsl-mc-bus.c
@@ -905,8 +905,10 @@ int fsl_mc_device_add(struct fsl_mc_obj_desc *obj_desc,
 
 error_cleanup_dev:
 	kfree(mc_dev->regions);
-	kfree(mc_bus);
-	kfree(mc_dev);
+	if (mc_bus)
+		kfree(mc_bus);
+	else
+		kfree(mc_dev);
 
 	return error;
 }
@@ -940,6 +942,7 @@ struct fsl_mc_device *fsl_mc_get_endpoint(struct fsl_mc_device *mc_dev,
 	struct fsl_mc_obj_desc endpoint_desc = {{ 0 }};
 	struct dprc_endpoint endpoint1 = {{ 0 }};
 	struct dprc_endpoint endpoint2 = {{ 0 }};
+	struct fsl_mc_bus *mc_bus;
 	int state, err;
 
 	mc_bus_dev = to_fsl_mc_device(mc_dev->dev.parent);
@@ -963,6 +966,8 @@ struct fsl_mc_device *fsl_mc_get_endpoint(struct fsl_mc_device *mc_dev,
 	strcpy(endpoint_desc.type, endpoint2.type);
 	endpoint_desc.id = endpoint2.id;
 	endpoint = fsl_mc_device_lookup(&endpoint_desc, mc_bus_dev);
+	if (endpoint)
+		return endpoint;
 
 	/*
 	 * We know that the device has an endpoint because we verified by
@@ -970,17 +975,13 @@ struct fsl_mc_device *fsl_mc_get_endpoint(struct fsl_mc_device *mc_dev,
 	 * yet discovered by the fsl-mc bus, thus the lookup returned NULL.
 	 * Force a rescan of the devices in this container and retry the lookup.
 	 */
-	if (!endpoint) {
-		struct fsl_mc_bus *mc_bus = to_fsl_mc_bus(mc_bus_dev);
-
-		if (mutex_trylock(&mc_bus->scan_mutex)) {
-			err = dprc_scan_objects(mc_bus_dev, true);
-			mutex_unlock(&mc_bus->scan_mutex);
-		}
-
-		if (err < 0)
-			return ERR_PTR(err);
+	mc_bus = to_fsl_mc_bus(mc_bus_dev);
+	if (mutex_trylock(&mc_bus->scan_mutex)) {
+		err = dprc_scan_objects(mc_bus_dev, true);
+		mutex_unlock(&mc_bus->scan_mutex);
 	}
+	if (err < 0)
+		return ERR_PTR(err);
 
 	endpoint = fsl_mc_device_lookup(&endpoint_desc, mc_bus_dev);
 	/*
diff --git a/drivers/bus/fsl-mc/fsl-mc-uapi.c b/drivers/bus/fsl-mc/fsl-mc-uapi.c
index 9c4c1395fcdb..a376ec661653 100644
--- a/drivers/bus/fsl-mc/fsl-mc-uapi.c
+++ b/drivers/bus/fsl-mc/fsl-mc-uapi.c
@@ -275,13 +275,13 @@ static struct fsl_mc_cmd_desc fsl_mc_accepted_cmds[] = {
 		.size = 8,
 	},
 	[DPSW_GET_TAILDROP] = {
-		.cmdid_value = 0x0A80,
+		.cmdid_value = 0x0A90,
 		.cmdid_mask = 0xFFF0,
 		.token = true,
 		.size = 14,
 	},
 	[DPSW_SET_TAILDROP] = {
-		.cmdid_value = 0x0A90,
+		.cmdid_value = 0x0A80,
 		.cmdid_mask = 0xFFF0,
 		.token = true,
 		.size = 24,
diff --git a/drivers/bus/fsl-mc/mc-io.c b/drivers/bus/fsl-mc/mc-io.c
index 95b10a6cf307..8b7a34f4db94 100644
--- a/drivers/bus/fsl-mc/mc-io.c
+++ b/drivers/bus/fsl-mc/mc-io.c
@@ -214,12 +214,19 @@ int __must_check fsl_mc_portal_allocate(struct fsl_mc_device *mc_dev,
 	if (error < 0)
 		goto error_cleanup_resource;
 
-	dpmcp_dev->consumer_link = device_link_add(&mc_dev->dev,
-						   &dpmcp_dev->dev,
-						   DL_FLAG_AUTOREMOVE_CONSUMER);
-	if (!dpmcp_dev->consumer_link) {
-		error = -EINVAL;
-		goto error_cleanup_mc_io;
+	/* If the DPRC device itself tries to allocate a portal (usually for
+	 * UAPI interaction), don't add a device link between them since the
+	 * DPMCP device is an actual child device of the DPRC and a reverse
+	 * dependency is not allowed.
+	 */
+	if (mc_dev != mc_bus_dev) {
+		dpmcp_dev->consumer_link = device_link_add(&mc_dev->dev,
+							   &dpmcp_dev->dev,
+							   DL_FLAG_AUTOREMOVE_CONSUMER);
+		if (!dpmcp_dev->consumer_link) {
+			error = -EINVAL;
+			goto error_cleanup_mc_io;
+		}
 	}
 
 	*new_mc_io = mc_io;
diff --git a/drivers/bus/fsl-mc/mc-sys.c b/drivers/bus/fsl-mc/mc-sys.c
index f2052cd0a051..b22c59d57c8f 100644
--- a/drivers/bus/fsl-mc/mc-sys.c
+++ b/drivers/bus/fsl-mc/mc-sys.c
@@ -19,7 +19,7 @@
 /*
  * Timeout in milliseconds to wait for the completion of an MC command
  */
-#define MC_CMD_COMPLETION_TIMEOUT_MS	500
+#define MC_CMD_COMPLETION_TIMEOUT_MS	15000
 
 /*
  * usleep_range() min and max values used to throttle down polling
diff --git a/drivers/bus/mhi/ep/ring.c b/drivers/bus/mhi/ep/ring.c
index aeb53b2c34a8..26357ee68dee 100644
--- a/drivers/bus/mhi/ep/ring.c
+++ b/drivers/bus/mhi/ep/ring.c
@@ -131,19 +131,23 @@ int mhi_ep_ring_add_element(struct mhi_ep_ring *ring, struct mhi_ring_element *e
 	}
 
 	old_offset = ring->rd_offset;
-	mhi_ep_ring_inc_index(ring);
 
 	dev_dbg(dev, "Adding an element to ring at offset (%zu)\n", ring->rd_offset);
+	buf_info.host_addr = ring->rbase + (old_offset * sizeof(*el));
+	buf_info.dev_addr = el;
+	buf_info.size = sizeof(*el);
+
+	ret = mhi_cntrl->write_sync(mhi_cntrl, &buf_info);
+	if (ret)
+		return ret;
+
+	mhi_ep_ring_inc_index(ring);
 
 	/* Update rp in ring context */
 	rp = cpu_to_le64(ring->rd_offset * sizeof(*el) + ring->rbase);
 	memcpy_toio((void __iomem *) &ring->ring_ctx->generic.rp, &rp, sizeof(u64));
 
-	buf_info.host_addr = ring->rbase + (old_offset * sizeof(*el));
-	buf_info.dev_addr = el;
-	buf_info.size = sizeof(*el);
-
-	return mhi_cntrl->write_sync(mhi_cntrl, &buf_info);
+	return ret;
 }
 
 void mhi_ep_ring_init(struct mhi_ep_ring *ring, enum mhi_ep_ring_type type, u32 id)
diff --git a/drivers/bus/mhi/host/main.c b/drivers/bus/mhi/host/main.c
index 4de75674f193..aa8a0ef697c7 100644
--- a/drivers/bus/mhi/host/main.c
+++ b/drivers/bus/mhi/host/main.c
@@ -1207,11 +1207,16 @@ int mhi_gen_tre(struct mhi_controller *mhi_cntrl, struct mhi_chan *mhi_chan,
 	struct mhi_ring_element *mhi_tre;
 	struct mhi_buf_info *buf_info;
 	int eot, eob, chain, bei;
-	int ret;
+	int ret = 0;
 
 	/* Protect accesses for reading and incrementing WP */
 	write_lock_bh(&mhi_chan->lock);
 
+	if (mhi_chan->ch_state != MHI_CH_STATE_ENABLED) {
+		ret = -ENODEV;
+		goto out;
+	}
+
 	buf_ring = &mhi_chan->buf_ring;
 	tre_ring = &mhi_chan->tre_ring;
 
@@ -1229,10 +1234,8 @@ int mhi_gen_tre(struct mhi_controller *mhi_cntrl, struct mhi_chan *mhi_chan,
 
 	if (!info->pre_mapped) {
 		ret = mhi_cntrl->map_single(mhi_cntrl, buf_info);
-		if (ret) {
-			write_unlock_bh(&mhi_chan->lock);
-			return ret;
-		}
+		if (ret)
+			goto out;
 	}
 
 	eob = !!(flags & MHI_EOB);
@@ -1250,9 +1253,10 @@ int mhi_gen_tre(struct mhi_controller *mhi_cntrl, struct mhi_chan *mhi_chan,
 	mhi_add_ring_element(mhi_cntrl, tre_ring);
 	mhi_add_ring_element(mhi_cntrl, buf_ring);
 
+out:
 	write_unlock_bh(&mhi_chan->lock);
 
-	return 0;
+	return ret;
 }
 
 int mhi_queue_buf(struct mhi_device *mhi_dev, enum dma_data_direction dir,
diff --git a/drivers/bus/mhi/host/pci_generic.c b/drivers/bus/mhi/host/pci_generic.c
index 9938bb034c1c..6505ce6ab1a2 100644
--- a/drivers/bus/mhi/host/pci_generic.c
+++ b/drivers/bus/mhi/host/pci_generic.c
@@ -509,8 +509,8 @@ static const struct mhi_pci_dev_info mhi_foxconn_dw5932e_info = {
 	.sideband_wake = false,
 };
 
-static const struct mhi_pci_dev_info mhi_foxconn_t99w515_info = {
-	.name = "foxconn-t99w515",
+static const struct mhi_pci_dev_info mhi_foxconn_t99w640_info = {
+	.name = "foxconn-t99w640",
 	.edl = "qcom/sdx72m/foxconn/edl.mbn",
 	.edl_trigger = true,
 	.config = &modem_foxconn_sdx72_config,
@@ -792,9 +792,9 @@ static const struct pci_device_id mhi_pci_id_table[] = {
 	/* DW5932e (sdx62), Non-eSIM */
 	{ PCI_DEVICE(PCI_VENDOR_ID_FOXCONN, 0xe0f9),
 		.driver_data = (kernel_ulong_t) &mhi_foxconn_dw5932e_info },
-	/* T99W515 (sdx72) */
+	/* T99W640 (sdx72) */
 	{ PCI_DEVICE(PCI_VENDOR_ID_FOXCONN, 0xe118),
-		.driver_data = (kernel_ulong_t) &mhi_foxconn_t99w515_info },
+		.driver_data = (kernel_ulong_t) &mhi_foxconn_t99w640_info },
 	/* DW5934e(sdx72), With eSIM */
 	{ PCI_DEVICE(PCI_VENDOR_ID_FOXCONN, 0xe11d),
 		.driver_data = (kernel_ulong_t) &mhi_foxconn_dw5934e_info },
@@ -1040,8 +1040,9 @@ static void mhi_pci_recovery_work(struct work_struct *work)
 err_unprepare:
 	mhi_unprepare_after_power_down(mhi_cntrl);
 err_try_reset:
-	if (pci_reset_function(pdev))
-		dev_err(&pdev->dev, "Recovery failed\n");
+	err = pci_try_reset_function(pdev);
+	if (err)
+		dev_err(&pdev->dev, "Recovery failed: %d\n", err);
 }
 
 static void health_check(struct timer_list *t)
diff --git a/drivers/bus/mhi/host/pm.c b/drivers/bus/mhi/host/pm.c
index 11c0e751f223..0ccbcb717955 100644
--- a/drivers/bus/mhi/host/pm.c
+++ b/drivers/bus/mhi/host/pm.c
@@ -602,6 +602,7 @@ static void mhi_pm_sys_error_transition(struct mhi_controller *mhi_cntrl)
 	struct mhi_cmd *mhi_cmd;
 	struct mhi_event_ctxt *er_ctxt;
 	struct device *dev = &mhi_cntrl->mhi_dev->dev;
+	bool reset_device = false;
 	int ret, i;
 
 	dev_dbg(dev, "Transitioning from PM state: %s to: %s\n",
@@ -630,8 +631,23 @@ static void mhi_pm_sys_error_transition(struct mhi_controller *mhi_cntrl)
 	/* Wake up threads waiting for state transition */
 	wake_up_all(&mhi_cntrl->state_event);
 
-	/* Trigger MHI RESET so that the device will not access host memory */
 	if (MHI_REG_ACCESS_VALID(prev_state)) {
+		/*
+		 * If the device is in PBL or SBL, it will only respond to
+		 * RESET if the device is in SYSERR state. SYSERR might
+		 * already be cleared at this point.
+		 */
+		enum mhi_state cur_state = mhi_get_mhi_state(mhi_cntrl);
+		enum mhi_ee_type cur_ee = mhi_get_exec_env(mhi_cntrl);
+
+		if (cur_state == MHI_STATE_SYS_ERR)
+			reset_device = true;
+		else if (cur_ee != MHI_EE_PBL && cur_ee != MHI_EE_SBL)
+			reset_device = true;
+	}
+
+	/* Trigger MHI RESET so that the device will not access host memory */
+	if (reset_device) {
 		u32 in_reset = -1;
 		unsigned long timeout = msecs_to_jiffies(mhi_cntrl->timeout_ms);
 
diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c
index 270a94a06e05..f715c8d28129 100644
--- a/drivers/bus/ti-sysc.c
+++ b/drivers/bus/ti-sysc.c
@@ -677,51 +677,6 @@ static int sysc_parse_and_check_child_range(struct sysc *ddata)
 	return 0;
 }
 
-/* Interconnect instances to probe before l4_per instances */
-static struct resource early_bus_ranges[] = {
-	/* am3/4 l4_wkup */
-	{ .start = 0x44c00000, .end = 0x44c00000 + 0x300000, },
-	/* omap4/5 and dra7 l4_cfg */
-	{ .start = 0x4a000000, .end = 0x4a000000 + 0x300000, },
-	/* omap4 l4_wkup */
-	{ .start = 0x4a300000, .end = 0x4a300000 + 0x30000,  },
-	/* omap5 and dra7 l4_wkup without dra7 dcan segment */
-	{ .start = 0x4ae00000, .end = 0x4ae00000 + 0x30000,  },
-};
-
-static atomic_t sysc_defer = ATOMIC_INIT(10);
-
-/**
- * sysc_defer_non_critical - defer non_critical interconnect probing
- * @ddata: device driver data
- *
- * We want to probe l4_cfg and l4_wkup interconnect instances before any
- * l4_per instances as l4_per instances depend on resources on l4_cfg and
- * l4_wkup interconnects.
- */
-static int sysc_defer_non_critical(struct sysc *ddata)
-{
-	struct resource *res;
-	int i;
-
-	if (!atomic_read(&sysc_defer))
-		return 0;
-
-	for (i = 0; i < ARRAY_SIZE(early_bus_ranges); i++) {
-		res = &early_bus_ranges[i];
-		if (ddata->module_pa >= res->start &&
-		    ddata->module_pa <= res->end) {
-			atomic_set(&sysc_defer, 0);
-
-			return 0;
-		}
-	}
-
-	atomic_dec_if_positive(&sysc_defer);
-
-	return -EPROBE_DEFER;
-}
-
 static struct device_node *stdout_path;
 
 static void sysc_init_stdout_path(struct sysc *ddata)
@@ -947,10 +902,6 @@ static int sysc_map_and_check_registers(struct sysc *ddata)
 	if (error)
 		return error;
 
-	error = sysc_defer_non_critical(ddata);
-	if (error)
-		return error;
-
 	sysc_check_children(ddata);
 
 	if (!of_property_present(np, "reg"))
diff --git a/drivers/cdx/Makefile b/drivers/cdx/Makefile
index 749a3295c2bd..3ca7068a3052 100644
--- a/drivers/cdx/Makefile
+++ b/drivers/cdx/Makefile
@@ -5,7 +5,7 @@
 # Copyright (C) 2022-2023, Advanced Micro Devices, Inc.
 #
 
-ccflags-y += -DDEFAULT_SYMBOL_NAMESPACE=CDX_BUS
+ccflags-y += -DDEFAULT_SYMBOL_NAMESPACE='"CDX_BUS"'
 
 obj-$(CONFIG_CDX_BUS) += cdx.o controller/
 
diff --git a/drivers/cdx/cdx.c b/drivers/cdx/cdx.c
index 07371cb653d3..4af1901c9d52 100644
--- a/drivers/cdx/cdx.c
+++ b/drivers/cdx/cdx.c
@@ -470,8 +470,12 @@ static ssize_t driver_override_show(struct device *dev,
 				    struct device_attribute *attr, char *buf)
 {
 	struct cdx_device *cdx_dev = to_cdx_device(dev);
+	ssize_t len;
 
-	return sysfs_emit(buf, "%s\n", cdx_dev->driver_override);
+	device_lock(dev);
+	len = sysfs_emit(buf, "%s\n", cdx_dev->driver_override);
+	device_unlock(dev);
+	return len;
 }
 static DEVICE_ATTR_RW(driver_override);
 
diff --git a/drivers/char/hw_random/mtk-rng.c b/drivers/char/hw_random/mtk-rng.c
index 1e3048f2bb38..6c4e40d0365f 100644
--- a/drivers/char/hw_random/mtk-rng.c
+++ b/drivers/char/hw_random/mtk-rng.c
@@ -142,7 +142,9 @@ static int mtk_rng_probe(struct platform_device *pdev)
 	dev_set_drvdata(&pdev->dev, priv);
 	pm_runtime_set_autosuspend_delay(&pdev->dev, RNG_AUTOSUSPEND_TIMEOUT);
 	pm_runtime_use_autosuspend(&pdev->dev);
-	devm_pm_runtime_enable(&pdev->dev);
+	ret = devm_pm_runtime_enable(&pdev->dev);
+	if (ret)
+		return ret;
 
 	dev_info(&pdev->dev, "registered RNG driver\n");
 
diff --git a/drivers/char/ipmi/ipmb_dev_int.c b/drivers/char/ipmi/ipmb_dev_int.c
index 7296127181ec..8a14fd0291d8 100644
--- a/drivers/char/ipmi/ipmb_dev_int.c
+++ b/drivers/char/ipmi/ipmb_dev_int.c
@@ -321,6 +321,9 @@ static int ipmb_probe(struct i2c_client *client)
 	ipmb_dev->miscdev.name = devm_kasprintf(&client->dev, GFP_KERNEL,
 						"%s%d", "ipmb-",
 						client->adapter->nr);
+	if (!ipmb_dev->miscdev.name)
+		return -ENOMEM;
+
 	ipmb_dev->miscdev.fops = &ipmb_fops;
 	ipmb_dev->miscdev.parent = &client->dev;
 	ret = misc_register(&ipmb_dev->miscdev);
diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c
index e12b531f5c2f..09405668ebb3 100644
--- a/drivers/char/ipmi/ipmi_msghandler.c
+++ b/drivers/char/ipmi/ipmi_msghandler.c
@@ -1241,7 +1241,7 @@ int ipmi_create_user(unsigned int          if_num,
 	}
 	/* Not found, return an error */
 	rv = -EINVAL;
-	goto out_kfree;
+	goto out_unlock;
 
  found:
 	if (atomic_add_return(1, &intf->nr_users) > max_users) {
@@ -1283,6 +1283,7 @@ int ipmi_create_user(unsigned int          if_num,
 
 out_kfree:
 	atomic_dec(&intf->nr_users);
+out_unlock:
 	srcu_read_unlock(&ipmi_interfaces_srcu, index);
 	vfree(new_user);
 	return rv;
@@ -4616,10 +4617,10 @@ return_unspecified:
 		 * The NetFN and Command in the response is not even
 		 * marginally correct.
 		 */
-		dev_warn(intf->si_dev,
-			 "BMC returned incorrect response, expected netfn %x cmd %x, got netfn %x cmd %x\n",
-			 (msg->data[0] >> 2) | 1, msg->data[1],
-			 msg->rsp[0] >> 2, msg->rsp[1]);
+		dev_warn_ratelimited(intf->si_dev,
+				     "BMC returned incorrect response, expected netfn %x cmd %x, got netfn %x cmd %x\n",
+				     (msg->data[0] >> 2) | 1, msg->data[1],
+				     msg->rsp[0] >> 2, msg->rsp[1]);
 
 		goto return_unspecified;
 	}
diff --git a/drivers/char/ipmi/ipmi_watchdog.c b/drivers/char/ipmi/ipmi_watchdog.c
index 335eea80054e..37ab5806b1a4 100644
--- a/drivers/char/ipmi/ipmi_watchdog.c
+++ b/drivers/char/ipmi/ipmi_watchdog.c
@@ -1189,14 +1189,8 @@ static struct ipmi_smi_watcher smi_watcher = {
 	.smi_gone = ipmi_smi_gone
 };
 
-static int action_op(const char *inval, char *outval)
+static int action_op_set_val(const char *inval)
 {
-	if (outval)
-		strcpy(outval, action);
-
-	if (!inval)
-		return 0;
-
 	if (strcmp(inval, "reset") == 0)
 		action_val = WDOG_TIMEOUT_RESET;
 	else if (strcmp(inval, "none") == 0)
@@ -1207,18 +1201,26 @@ static int action_op(const char *inval, char *outval)
 		action_val = WDOG_TIMEOUT_POWER_DOWN;
 	else
 		return -EINVAL;
-	strcpy(action, inval);
 	return 0;
 }
 
-static int preaction_op(const char *inval, char *outval)
+static int action_op(const char *inval, char *outval)
 {
+	int rv;
+
 	if (outval)
-		strcpy(outval, preaction);
+		strcpy(outval, action);
 
 	if (!inval)
 		return 0;
+	rv = action_op_set_val(inval);
+	if (!rv)
+		strcpy(action, inval);
+	return rv;
+}
 
+static int preaction_op_set_val(const char *inval)
+{
 	if (strcmp(inval, "pre_none") == 0)
 		preaction_val = WDOG_PRETIMEOUT_NONE;
 	else if (strcmp(inval, "pre_smi") == 0)
@@ -1231,18 +1233,26 @@ static int preaction_op(const char *inval, char *outval)
 		preaction_val = WDOG_PRETIMEOUT_MSG_INT;
 	else
 		return -EINVAL;
-	strcpy(preaction, inval);
 	return 0;
 }
 
-static int preop_op(const char *inval, char *outval)
+static int preaction_op(const char *inval, char *outval)
 {
+	int rv;
+
 	if (outval)
-		strcpy(outval, preop);
+		strcpy(outval, preaction);
 
 	if (!inval)
 		return 0;
+	rv = preaction_op_set_val(inval);
+	if (!rv)
+		strcpy(preaction, inval);
+	return 0;
+}
 
+static int preop_op_set_val(const char *inval)
+{
 	if (strcmp(inval, "preop_none") == 0)
 		preop_val = WDOG_PREOP_NONE;
 	else if (strcmp(inval, "preop_panic") == 0)
@@ -1251,7 +1261,22 @@ static int preop_op(const char *inval, char *outval)
 		preop_val = WDOG_PREOP_GIVE_DATA;
 	else
 		return -EINVAL;
-	strcpy(preop, inval);
+	return 0;
+}
+
+static int preop_op(const char *inval, char *outval)
+{
+	int rv;
+
+	if (outval)
+		strcpy(outval, preop);
+
+	if (!inval)
+		return 0;
+
+	rv = preop_op_set_val(inval);
+	if (!rv)
+		strcpy(preop, inval);
 	return 0;
 }
 
@@ -1288,18 +1313,18 @@ static int __init ipmi_wdog_init(void)
 {
 	int rv;
 
-	if (action_op(action, NULL)) {
+	if (action_op_set_val(action)) {
 		action_op("reset", NULL);
 		pr_info("Unknown action '%s', defaulting to reset\n", action);
 	}
 
-	if (preaction_op(preaction, NULL)) {
+	if (preaction_op_set_val(preaction)) {
 		preaction_op("pre_none", NULL);
 		pr_info("Unknown preaction '%s', defaulting to none\n",
 			preaction);
 	}
 
-	if (preop_op(preop, NULL)) {
+	if (preop_op_set_val(preop)) {
 		preop_op("preop_none", NULL);
 		pr_info("Unknown preop '%s', defaulting to none\n", preop);
 	}
diff --git a/drivers/char/ipmi/ssif_bmc.c b/drivers/char/ipmi/ssif_bmc.c
index a14fafc583d4..310f17dd9511 100644
--- a/drivers/char/ipmi/ssif_bmc.c
+++ b/drivers/char/ipmi/ssif_bmc.c
@@ -292,7 +292,6 @@ static void complete_response(struct ssif_bmc_ctx *ssif_bmc)
 	ssif_bmc->nbytes_processed = 0;
 	ssif_bmc->remain_len = 0;
 	ssif_bmc->busy = false;
-	memset(&ssif_bmc->part_buf, 0, sizeof(struct ssif_part_buffer));
 	wake_up_all(&ssif_bmc->wait_queue);
 }
 
@@ -744,9 +743,11 @@ static void on_stop_event(struct ssif_bmc_ctx *ssif_bmc, u8 *val)
 			ssif_bmc->aborting = true;
 		}
 	} else if (ssif_bmc->state == SSIF_RES_SENDING) {
-		if (ssif_bmc->is_singlepart_read || ssif_bmc->block_num == 0xFF)
+		if (ssif_bmc->is_singlepart_read || ssif_bmc->block_num == 0xFF) {
+			memset(&ssif_bmc->part_buf, 0, sizeof(struct ssif_part_buffer));
 			/* Invalidate response buffer to denote it is sent */
 			complete_response(ssif_bmc);
+		}
 		ssif_bmc->state = SSIF_READY;
 	}
 
diff --git a/drivers/char/misc.c b/drivers/char/misc.c
index 541edc26ec89..30178e20d962 100644
--- a/drivers/char/misc.c
+++ b/drivers/char/misc.c
@@ -63,16 +63,30 @@ static DEFINE_MUTEX(misc_mtx);
 #define DYNAMIC_MINORS 128 /* like dynamic majors */
 static DEFINE_IDA(misc_minors_ida);
 
-static int misc_minor_alloc(void)
+static int misc_minor_alloc(int minor)
 {
-	int ret;
-
-	ret = ida_alloc_max(&misc_minors_ida, DYNAMIC_MINORS - 1, GFP_KERNEL);
-	if (ret >= 0) {
-		ret = DYNAMIC_MINORS - ret - 1;
+	int ret = 0;
+
+	if (minor == MISC_DYNAMIC_MINOR) {
+		/* allocate free id */
+		ret = ida_alloc_max(&misc_minors_ida, DYNAMIC_MINORS - 1, GFP_KERNEL);
+		if (ret >= 0) {
+			ret = DYNAMIC_MINORS - ret - 1;
+		} else {
+			ret = ida_alloc_range(&misc_minors_ida, MISC_DYNAMIC_MINOR + 1,
+					      MINORMASK, GFP_KERNEL);
+		}
 	} else {
-		ret = ida_alloc_range(&misc_minors_ida, MISC_DYNAMIC_MINOR + 1,
-				      MINORMASK, GFP_KERNEL);
+		/* specific minor, check if it is in dynamic or misc dynamic range  */
+		if (minor < DYNAMIC_MINORS) {
+			minor = DYNAMIC_MINORS - minor - 1;
+			ret = ida_alloc_range(&misc_minors_ida, minor, minor, GFP_KERNEL);
+		} else if (minor > MISC_DYNAMIC_MINOR) {
+			ret = ida_alloc_range(&misc_minors_ida, minor, minor, GFP_KERNEL);
+		} else {
+			/* case of non-dynamic minors, no need to allocate id */
+			ret = 0;
+		}
 	}
 	return ret;
 }
@@ -219,7 +233,7 @@ int misc_register(struct miscdevice *misc)
 	mutex_lock(&misc_mtx);
 
 	if (is_dynamic) {
-		int i = misc_minor_alloc();
+		int i = misc_minor_alloc(misc->minor);
 
 		if (i < 0) {
 			err = -EBUSY;
@@ -228,6 +242,7 @@ int misc_register(struct miscdevice *misc)
 		misc->minor = i;
 	} else {
 		struct miscdevice *c;
+		int i;
 
 		list_for_each_entry(c, &misc_list, list) {
 			if (c->minor == misc->minor) {
@@ -235,6 +250,12 @@ int misc_register(struct miscdevice *misc)
 				goto out;
 			}
 		}
+
+		i = misc_minor_alloc(misc->minor);
+		if (i < 0) {
+			err = -EBUSY;
+			goto out;
+		}
 	}
 
 	dev = MKDEV(MISC_MAJOR, misc->minor);
@@ -243,8 +264,8 @@ int misc_register(struct miscdevice *misc)
 		device_create_with_groups(&misc_class, misc->parent, dev,
 					  misc, misc->groups, "%s", misc->name);
 	if (IS_ERR(misc->this_device)) {
+		misc_minor_free(misc->minor);
 		if (is_dynamic) {
-			misc_minor_free(misc->minor);
 			misc->minor = MISC_DYNAMIC_MINOR;
 		}
 		err = PTR_ERR(misc->this_device);
@@ -293,8 +314,8 @@ static int __init misc_init(void)
 	if (err)
 		goto fail_remove;
 
-	err = -EIO;
-	if (register_chrdev(MISC_MAJOR, "misc", &misc_fops))
+	err = __register_chrdev(MISC_MAJOR, 0, MINORMASK + 1, "misc", &misc_fops);
+	if (err < 0)
 		goto fail_printk;
 	return 0;
 
diff --git a/drivers/char/tpm/eventlog/acpi.c b/drivers/char/tpm/eventlog/acpi.c
index 69533d0bfb51..cf02ec646f46 100644
--- a/drivers/char/tpm/eventlog/acpi.c
+++ b/drivers/char/tpm/eventlog/acpi.c
@@ -63,6 +63,11 @@ static bool tpm_is_tpm2_log(void *bios_event_log, u64 len)
 	return n == 0;
 }
 
+static void tpm_bios_log_free(void *data)
+{
+	kvfree(data);
+}
+
 /* read binary bios log */
 int tpm_read_log_acpi(struct tpm_chip *chip)
 {
@@ -136,7 +141,7 @@ int tpm_read_log_acpi(struct tpm_chip *chip)
 	}
 
 	/* malloc EventLog space */
-	log->bios_event_log = devm_kmalloc(&chip->dev, len, GFP_KERNEL);
+	log->bios_event_log = kvmalloc(len, GFP_KERNEL);
 	if (!log->bios_event_log)
 		return -ENOMEM;
 
@@ -161,10 +166,16 @@ int tpm_read_log_acpi(struct tpm_chip *chip)
 		goto err;
 	}
 
+	ret = devm_add_action(&chip->dev, tpm_bios_log_free, log->bios_event_log);
+	if (ret) {
+		log->bios_event_log = NULL;
+		goto err;
+	}
+
 	return format;
 
 err:
-	devm_kfree(&chip->dev, log->bios_event_log);
+	tpm_bios_log_free(log->bios_event_log);
 	log->bios_event_log = NULL;
 	return ret;
 }
diff --git a/drivers/char/tpm/tpm-buf.c b/drivers/char/tpm/tpm-buf.c
index e49a19fea3bd..dc882fc9fa9e 100644
--- a/drivers/char/tpm/tpm-buf.c
+++ b/drivers/char/tpm/tpm-buf.c
@@ -201,7 +201,7 @@ static void tpm_buf_read(struct tpm_buf *buf, off_t *offset, size_t count, void
  */
 u8 tpm_buf_read_u8(struct tpm_buf *buf, off_t *offset)
 {
-	u8 value;
+	u8 value = 0;
 
 	tpm_buf_read(buf, offset, sizeof(value), &value);
 
@@ -218,7 +218,7 @@ EXPORT_SYMBOL_GPL(tpm_buf_read_u8);
  */
 u16 tpm_buf_read_u16(struct tpm_buf *buf, off_t *offset)
 {
-	u16 value;
+	u16 value = 0;
 
 	tpm_buf_read(buf, offset, sizeof(value), &value);
 
@@ -235,7 +235,7 @@ EXPORT_SYMBOL_GPL(tpm_buf_read_u16);
  */
 u32 tpm_buf_read_u32(struct tpm_buf *buf, off_t *offset)
 {
-	u32 value;
+	u32 value = 0;
 
 	tpm_buf_read(buf, offset, sizeof(value), &value);
 
diff --git a/drivers/char/tpm/tpm-chip.c b/drivers/char/tpm/tpm-chip.c
index 7df7abaf3e52..e25daf2396d3 100644
--- a/drivers/char/tpm/tpm-chip.c
+++ b/drivers/char/tpm/tpm-chip.c
@@ -168,6 +168,11 @@ int tpm_try_get_ops(struct tpm_chip *chip)
 		goto out_ops;
 
 	mutex_lock(&chip->tpm_mutex);
+
+	/* tmp_chip_start may issue IO that is denied while suspended */
+	if (chip->flags & TPM_CHIP_FLAG_SUSPENDED)
+		goto out_lock;
+
 	rc = tpm_chip_start(chip);
 	if (rc)
 		goto out_lock;
@@ -300,6 +305,7 @@ int tpm_class_shutdown(struct device *dev)
 	down_write(&chip->ops_sem);
 	if (chip->flags & TPM_CHIP_FLAG_TPM2) {
 		if (!tpm_chip_start(chip)) {
+			tpm2_end_auth_session(chip);
 			tpm2_shutdown(chip, TPM2_SU_CLEAR);
 			tpm_chip_stop(chip);
 		}
diff --git a/drivers/char/tpm/tpm-interface.c b/drivers/char/tpm/tpm-interface.c
index b1daa0d7b341..f62f7871edbd 100644
--- a/drivers/char/tpm/tpm-interface.c
+++ b/drivers/char/tpm/tpm-interface.c
@@ -445,18 +445,11 @@ int tpm_get_random(struct tpm_chip *chip, u8 *out, size_t max)
 	if (!chip)
 		return -ENODEV;
 
-	/* Give back zero bytes, as TPM chip has not yet fully resumed: */
-	if (chip->flags & TPM_CHIP_FLAG_SUSPENDED) {
-		rc = 0;
-		goto out;
-	}
-
 	if (chip->flags & TPM_CHIP_FLAG_TPM2)
 		rc = tpm2_get_random(chip, out, max);
 	else
 		rc = tpm1_get_random(chip, out, max);
 
-out:
 	tpm_put_ops(chip);
 	return rc;
 }
diff --git a/drivers/char/tpm/tpm2-sessions.c b/drivers/char/tpm/tpm2-sessions.c
index b0f13c8ea79c..cf0b83154044 100644
--- a/drivers/char/tpm/tpm2-sessions.c
+++ b/drivers/char/tpm/tpm2-sessions.c
@@ -40,11 +40,6 @@
  *
  * These are the usage functions:
  *
- * tpm2_start_auth_session() which allocates the opaque auth structure
- *	and gets a session from the TPM.  This must be called before
- *	any of the following functions.  The session is protected by a
- *	session_key which is derived from a random salt value
- *	encrypted to the NULL seed.
  * tpm2_end_auth_session() kills the session and frees the resources.
  *	Under normal operation this function is done by
  *	tpm_buf_check_hmac_response(), so this is only to be used on
@@ -963,16 +958,13 @@ err:
 }
 
 /**
- * tpm2_start_auth_session() - create a HMAC authentication session with the TPM
- * @chip: the TPM chip structure to create the session with
+ * tpm2_start_auth_session() - Create an a HMAC authentication session
+ * @chip:	A TPM chip
  *
- * This function loads the NULL seed from its saved context and starts
- * an authentication session on the null seed, fills in the
- * @chip->auth structure to contain all the session details necessary
- * for performing the HMAC, encrypt and decrypt operations and
- * returns.  The NULL seed is flushed before this function returns.
+ * Loads the ephemeral key (null seed), and starts an HMAC authenticated
+ * session. The null seed is flushed before the return.
  *
- * Return: zero on success or actual error encountered.
+ * Returns zero on success, or a POSIX error code.
  */
 int tpm2_start_auth_session(struct tpm_chip *chip)
 {
@@ -982,7 +974,7 @@ int tpm2_start_auth_session(struct tpm_chip *chip)
 	int rc;
 
 	if (chip->auth) {
-		dev_warn_once(&chip->dev, "auth session is active\n");
+		dev_dbg_once(&chip->dev, "auth session is active\n");
 		return 0;
 	}
 
@@ -1024,7 +1016,7 @@ int tpm2_start_auth_session(struct tpm_chip *chip)
 	/* hash algorithm for session */
 	tpm_buf_append_u16(&buf, TPM_ALG_SHA256);
 
-	rc = tpm_transmit_cmd(chip, &buf, 0, "start auth session");
+	rc = tpm_ret_to_err(tpm_transmit_cmd(chip, &buf, 0, "StartAuthSession"));
 	tpm2_flush_context(chip, null_key);
 
 	if (rc == TPM2_RC_SUCCESS)
diff --git a/drivers/char/tpm/tpm_tis_core.c b/drivers/char/tpm/tpm_tis_core.c
index fdef214b9f6b..ed0d3d8449b3 100644
--- a/drivers/char/tpm/tpm_tis_core.c
+++ b/drivers/char/tpm/tpm_tis_core.c
@@ -114,11 +114,10 @@ again:
 		return 0;
 	/* process status changes without irq support */
 	do {
+		usleep_range(priv->timeout_min, priv->timeout_max);
 		status = chip->ops->status(chip);
 		if ((status & mask) == mask)
 			return 0;
-		usleep_range(priv->timeout_min,
-			     priv->timeout_max);
 	} while (time_before(jiffies, stop));
 	return -ETIME;
 }
@@ -464,7 +463,10 @@ static int tpm_tis_send_data(struct tpm_chip *chip, const u8 *buf, size_t len)
 
 		if (wait_for_tpm_stat(chip, TPM_STS_VALID, chip->timeout_c,
 					&priv->int_queue, false) < 0) {
-			rc = -ETIME;
+			if (test_bit(TPM_TIS_STATUS_VALID_RETRY, &priv->flags))
+				rc = -EAGAIN;
+			else
+				rc = -ETIME;
 			goto out_err;
 		}
 		status = tpm_tis_status(chip);
@@ -481,7 +483,10 @@ static int tpm_tis_send_data(struct tpm_chip *chip, const u8 *buf, size_t len)
 
 	if (wait_for_tpm_stat(chip, TPM_STS_VALID, chip->timeout_c,
 				&priv->int_queue, false) < 0) {
-		rc = -ETIME;
+		if (test_bit(TPM_TIS_STATUS_VALID_RETRY, &priv->flags))
+			rc = -EAGAIN;
+		else
+			rc = -ETIME;
 		goto out_err;
 	}
 	status = tpm_tis_status(chip);
@@ -546,9 +551,11 @@ static int tpm_tis_send_main(struct tpm_chip *chip, const u8 *buf, size_t len)
 		if (rc >= 0)
 			/* Data transfer done successfully */
 			break;
-		else if (rc != -EIO)
+		else if (rc != -EAGAIN && rc != -EIO)
 			/* Data transfer failed, not recoverable */
 			return rc;
+
+		usleep_range(priv->timeout_min, priv->timeout_max);
 	}
 
 	/* go and do it */
@@ -1144,6 +1151,9 @@ int tpm_tis_core_init(struct device *dev, struct tpm_tis_data *priv, int irq,
 		priv->timeout_max = TIS_TIMEOUT_MAX_ATML;
 	}
 
+	if (priv->manufacturer_id == TPM_VID_IFX)
+		set_bit(TPM_TIS_STATUS_VALID_RETRY, &priv->flags);
+
 	if (is_bsw()) {
 		priv->ilb_base_addr = ioremap(INTEL_LEGACY_BLK_BASE_ADDR,
 					ILB_REMAP_SIZE);
diff --git a/drivers/char/tpm/tpm_tis_core.h b/drivers/char/tpm/tpm_tis_core.h
index 690ad8e9b731..6c3aa480396b 100644
--- a/drivers/char/tpm/tpm_tis_core.h
+++ b/drivers/char/tpm/tpm_tis_core.h
@@ -54,7 +54,7 @@ enum tis_int_flags {
 enum tis_defaults {
 	TIS_MEM_LEN = 0x5000,
 	TIS_SHORT_TIMEOUT = 750,	/* ms */
-	TIS_LONG_TIMEOUT = 2000,	/* 2 sec */
+	TIS_LONG_TIMEOUT = 4000,	/* 4 secs */
 	TIS_TIMEOUT_MIN_ATML = 14700,	/* usecs */
 	TIS_TIMEOUT_MAX_ATML = 15000,	/* usecs */
 };
@@ -89,6 +89,7 @@ enum tpm_tis_flags {
 	TPM_TIS_INVALID_STATUS		= 1,
 	TPM_TIS_DEFAULT_CANCELLATION	= 2,
 	TPM_TIS_IRQ_TESTED		= 3,
+	TPM_TIS_STATUS_VALID_RETRY	= 4,
 };
 
 struct tpm_tis_data {
diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index c62b208b42f1..abcfdd3c2918 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -1579,8 +1579,8 @@ static void handle_control_message(struct virtio_device *vdev,
 		break;
 	case VIRTIO_CONSOLE_RESIZE: {
 		struct {
-			__u16 rows;
-			__u16 cols;
+			__virtio16 rows;
+			__virtio16 cols;
 		} size;
 
 		if (!is_console_port(port))
@@ -1588,7 +1588,8 @@ static void handle_control_message(struct virtio_device *vdev,
 
 		memcpy(&size, buf->buf + buf->offset + sizeof(*cpkt),
 		       sizeof(size));
-		set_console_size(port, size.rows, size.cols);
+		set_console_size(port, virtio16_to_cpu(vdev, size.rows),
+				 virtio16_to_cpu(vdev, size.cols));
 
 		port->cons.hvc->irq_requested = 1;
 		resize_console(port);
diff --git a/drivers/clk/analogbits/wrpll-cln28hpc.c b/drivers/clk/analogbits/wrpll-cln28hpc.c
index 65d422a588e1..9d178afc73bd 100644
--- a/drivers/clk/analogbits/wrpll-cln28hpc.c
+++ b/drivers/clk/analogbits/wrpll-cln28hpc.c
@@ -292,7 +292,7 @@ int wrpll_configure_for_rate(struct wrpll_cfg *c, u32 target_rate,
 			vco = vco_pre * f;
 		}
 
-		delta = abs(target_rate - vco);
+		delta = abs(target_vco_rate - vco);
 		if (delta < best_delta) {
 			best_delta = delta;
 			best_r = r;
diff --git a/drivers/clk/at91/sam9x7.c b/drivers/clk/at91/sam9x7.c
index cbb8b220f16b..ffab32b047a0 100644
--- a/drivers/clk/at91/sam9x7.c
+++ b/drivers/clk/at91/sam9x7.c
@@ -61,44 +61,44 @@ static const struct clk_master_layout sam9x7_master_layout = {
 
 /* Fractional PLL core output range. */
 static const struct clk_range plla_core_outputs[] = {
-	{ .min = 375000000, .max = 1600000000 },
+	{ .min = 800000000, .max = 1600000000 },
 };
 
 static const struct clk_range upll_core_outputs[] = {
-	{ .min = 600000000, .max = 1200000000 },
+	{ .min = 600000000, .max = 960000000 },
 };
 
 static const struct clk_range lvdspll_core_outputs[] = {
-	{ .min = 400000000, .max = 800000000 },
+	{ .min = 600000000, .max = 1200000000 },
 };
 
 static const struct clk_range audiopll_core_outputs[] = {
-	{ .min = 400000000, .max = 800000000 },
+	{ .min = 600000000, .max = 1200000000 },
 };
 
 static const struct clk_range plladiv2_core_outputs[] = {
-	{ .min = 375000000, .max = 1600000000 },
+	{ .min = 800000000, .max = 1600000000 },
 };
 
 /* Fractional PLL output range. */
 static const struct clk_range plla_outputs[] = {
-	{ .min = 732421, .max = 800000000 },
+	{ .min = 400000000, .max = 800000000 },
 };
 
 static const struct clk_range upll_outputs[] = {
-	{ .min = 300000000, .max = 600000000 },
+	{ .min = 300000000, .max = 480000000 },
 };
 
 static const struct clk_range lvdspll_outputs[] = {
-	{ .min = 10000000, .max = 800000000 },
+	{ .min = 175000000, .max = 550000000 },
 };
 
 static const struct clk_range audiopll_outputs[] = {
-	{ .min = 10000000, .max = 800000000 },
+	{ .min = 0, .max = 300000000 },
 };
 
 static const struct clk_range plladiv2_outputs[] = {
-	{ .min = 366210, .max = 400000000 },
+	{ .min = 200000000, .max = 400000000 },
 };
 
 /* PLL characteristics. */
diff --git a/drivers/clk/bcm/clk-raspberrypi.c b/drivers/clk/bcm/clk-raspberrypi.c
index a18a8768feb4..6cb26b6e7347 100644
--- a/drivers/clk/bcm/clk-raspberrypi.c
+++ b/drivers/clk/bcm/clk-raspberrypi.c
@@ -271,6 +271,8 @@ static struct clk_hw *raspberrypi_clk_register(struct raspberrypi_clk *rpi,
 	init.name = devm_kasprintf(rpi->dev, GFP_KERNEL,
 				   "fw-clk-%s",
 				   rpi_firmware_clk_names[id]);
+	if (!init.name)
+		return ERR_PTR(-ENOMEM);
 	init.ops = &raspberrypi_firmware_clk_ops;
 	init.flags = CLK_GET_RATE_NOCACHE;
 
diff --git a/drivers/clk/clk-axi-clkgen.c b/drivers/clk/clk-axi-clkgen.c
index 934e53a96ddd..00bf799964c6 100644
--- a/drivers/clk/clk-axi-clkgen.c
+++ b/drivers/clk/clk-axi-clkgen.c
@@ -118,7 +118,7 @@ static const struct axi_clkgen_limits axi_clkgen_zynqmp_default_limits = {
 
 static const struct axi_clkgen_limits axi_clkgen_zynq_default_limits = {
 	.fpfd_min = 10000,
-	.fpfd_max = 300000,
+	.fpfd_max = 450000,
 	.fvco_min = 600000,
 	.fvco_max = 1200000,
 };
diff --git a/drivers/clk/clk-loongson2.c b/drivers/clk/clk-loongson2.c
index 7082b4309c6f..0d9485e83938 100644
--- a/drivers/clk/clk-loongson2.c
+++ b/drivers/clk/clk-loongson2.c
@@ -294,7 +294,7 @@ static int loongson2_clk_probe(struct platform_device *pdev)
 		return -EINVAL;
 
 	for (p = data; p->name; p++)
-		clks_num++;
+		clks_num = max(clks_num, p->id + 1);
 
 	clp = devm_kzalloc(dev, struct_size(clp, clk_data.hws, clks_num),
 			   GFP_KERNEL);
@@ -309,6 +309,9 @@ static int loongson2_clk_probe(struct platform_device *pdev)
 	clp->clk_data.num = clks_num;
 	clp->dev = dev;
 
+	/* Avoid returning NULL for unused id */
+	memset_p((void **)clp->clk_data.hws, ERR_PTR(-ENOENT), clks_num);
+
 	for (i = 0; i < clks_num; i++) {
 		p = &data[i];
 		switch (p->type) {
diff --git a/drivers/clk/clk-s2mps11.c b/drivers/clk/clk-s2mps11.c
index 014db6386624..8ddf3a9a53df 100644
--- a/drivers/clk/clk-s2mps11.c
+++ b/drivers/clk/clk-s2mps11.c
@@ -137,6 +137,8 @@ static int s2mps11_clk_probe(struct platform_device *pdev)
 	if (!clk_data)
 		return -ENOMEM;
 
+	clk_data->num = S2MPS11_CLKS_NUM;
+
 	switch (hwid) {
 	case S2MPS11X:
 		s2mps11_reg = S2MPS11_REG_RTC_CTRL;
@@ -186,7 +188,6 @@ static int s2mps11_clk_probe(struct platform_device *pdev)
 		clk_data->hws[i] = &s2mps11_clks[i].hw;
 	}
 
-	clk_data->num = S2MPS11_CLKS_NUM;
 	of_clk_add_hw_provider(s2mps11_clks->clk_np, of_clk_hw_onecell_get,
 			       clk_data);
 
diff --git a/drivers/clk/clk-scmi.c b/drivers/clk/clk-scmi.c
index 15510c2ff21c..1b1561c84127 100644
--- a/drivers/clk/clk-scmi.c
+++ b/drivers/clk/clk-scmi.c
@@ -404,6 +404,7 @@ static int scmi_clocks_probe(struct scmi_device *sdev)
 	const struct scmi_handle *handle = sdev->handle;
 	struct scmi_protocol_handle *ph;
 	const struct clk_ops *scmi_clk_ops_db[SCMI_MAX_CLK_OPS] = {};
+	struct scmi_clk *sclks;
 
 	if (!handle)
 		return -ENODEV;
@@ -430,18 +431,21 @@ static int scmi_clocks_probe(struct scmi_device *sdev)
 	transport_is_atomic = handle->is_transport_atomic(handle,
 							  &atomic_threshold_us);
 
+	sclks = devm_kcalloc(dev, count, sizeof(*sclks), GFP_KERNEL);
+	if (!sclks)
+		return -ENOMEM;
+
+	for (idx = 0; idx < count; idx++)
+		hws[idx] = &sclks[idx].hw;
+
 	for (idx = 0; idx < count; idx++) {
-		struct scmi_clk *sclk;
+		struct scmi_clk *sclk = &sclks[idx];
 		const struct clk_ops *scmi_ops;
 
-		sclk = devm_kzalloc(dev, sizeof(*sclk), GFP_KERNEL);
-		if (!sclk)
-			return -ENOMEM;
-
 		sclk->info = scmi_proto_clk_ops->info_get(ph, idx);
 		if (!sclk->info) {
 			dev_dbg(dev, "invalid clock info for idx %d\n", idx);
-			devm_kfree(dev, sclk);
+			hws[idx] = NULL;
 			continue;
 		}
 
@@ -479,13 +483,11 @@ static int scmi_clocks_probe(struct scmi_device *sdev)
 		if (err) {
 			dev_err(dev, "failed to register clock %d\n", idx);
 			devm_kfree(dev, sclk->parent_data);
-			devm_kfree(dev, sclk);
 			hws[idx] = NULL;
 		} else {
 			dev_dbg(dev, "Registered clock:%s%s\n",
 				sclk->info->name,
 				scmi_ops->enable ? " (atomic ops)" : "");
-			hws[idx] = &sclk->hw;
 		}
 	}
 
diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index d02451f951cf..7de3dfdae4b5 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -5264,6 +5264,10 @@ of_clk_get_hw_from_clkspec(struct of_phandle_args *clkspec)
 	if (!clkspec)
 		return ERR_PTR(-EINVAL);
 
+	/* Check if node in clkspec is in disabled/fail state */
+	if (!of_device_is_available(clkspec->np))
+		return ERR_PTR(-ENOENT);
+
 	mutex_lock(&of_clk_mutex);
 	list_for_each_entry(provider, &of_clk_providers, link) {
 		if (provider->node == clkspec->np) {
@@ -5391,8 +5395,10 @@ const char *of_clk_get_parent_name(const struct device_node *np, int index)
 		count++;
 	}
 	/* We went off the end of 'clock-indices' without finding it */
-	if (of_property_present(clkspec.np, "clock-indices") && !found)
+	if (of_property_present(clkspec.np, "clock-indices") && !found) {
+		of_node_put(clkspec.np);
 		return NULL;
+	}
 
 	if (of_property_read_string_index(clkspec.np, "clock-output-names",
 					  index,
diff --git a/drivers/clk/davinci/psc.c b/drivers/clk/davinci/psc.c
index 355d1be0b5d8..a37fea7542b2 100644
--- a/drivers/clk/davinci/psc.c
+++ b/drivers/clk/davinci/psc.c
@@ -277,6 +277,11 @@ davinci_lpsc_clk_register(struct device *dev, const char *name,
 
 	lpsc->pm_domain.name = devm_kasprintf(dev, GFP_KERNEL, "%s: %s",
 					      best_dev_name(dev), name);
+	if (!lpsc->pm_domain.name) {
+		clk_hw_unregister(&lpsc->hw);
+		kfree(lpsc);
+		return ERR_PTR(-ENOMEM);
+	}
 	lpsc->pm_domain.attach_dev = davinci_psc_genpd_attach_dev;
 	lpsc->pm_domain.detach_dev = davinci_psc_genpd_detach_dev;
 	lpsc->pm_domain.flags = GENPD_FLAG_PM_CLK;
diff --git a/drivers/clk/imx/clk-imx8mp-audiomix.c b/drivers/clk/imx/clk-imx8mp-audiomix.c
index c409fc7e0618..775f62dddb11 100644
--- a/drivers/clk/imx/clk-imx8mp-audiomix.c
+++ b/drivers/clk/imx/clk-imx8mp-audiomix.c
@@ -180,14 +180,14 @@ static struct clk_imx8mp_audiomix_sel sels[] = {
 	CLK_GATE("asrc", ASRC_IPG),
 	CLK_GATE("pdm", PDM_IPG),
 	CLK_GATE("earc", EARC_IPG),
-	CLK_GATE("ocrama", OCRAMA_IPG),
+	CLK_GATE_PARENT("ocrama", OCRAMA_IPG, "axi"),
 	CLK_GATE("aud2htx", AUD2HTX_IPG),
 	CLK_GATE_PARENT("earc_phy", EARC_PHY, "sai_pll_out_div2"),
 	CLK_GATE("sdma2", SDMA2_ROOT),
 	CLK_GATE("sdma3", SDMA3_ROOT),
 	CLK_GATE("spba2", SPBA2_ROOT),
-	CLK_GATE("dsp", DSP_ROOT),
-	CLK_GATE("dspdbg", DSPDBG_ROOT),
+	CLK_GATE_PARENT("dsp", DSP_ROOT, "axi"),
+	CLK_GATE_PARENT("dspdbg", DSPDBG_ROOT, "axi"),
 	CLK_GATE("edma", EDMA_ROOT),
 	CLK_GATE_PARENT("audpll", AUDPLL_ROOT, "osc_24m"),
 	CLK_GATE("mu2", MU2_ROOT),
diff --git a/drivers/clk/imx/clk-imx8mp.c b/drivers/clk/imx/clk-imx8mp.c
index 516dbd170c8a..fe6dac70f1a1 100644
--- a/drivers/clk/imx/clk-imx8mp.c
+++ b/drivers/clk/imx/clk-imx8mp.c
@@ -8,6 +8,7 @@
 #include <linux/err.h>
 #include <linux/io.h>
 #include <linux/module.h>
+#include <linux/units.h>
 #include <linux/of_address.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
@@ -399,17 +400,158 @@ static const char * const imx8mp_dram_core_sels[] = {"dram_pll_out", "dram_alt_r
 
 static const char * const imx8mp_clkout_sels[] = {"audio_pll1_out", "audio_pll2_out", "video_pll1_out",
 						  "dummy", "dummy", "gpu_pll_out", "vpu_pll_out",
-						  "arm_pll_out", "sys_pll1", "sys_pll2", "sys_pll3",
-						  "dummy", "dummy", "osc_24m", "dummy", "osc_32k"};
+						  "arm_pll_out", "sys_pll1_out", "sys_pll2_out",
+						  "sys_pll3_out", "dummy", "dummy", "osc_24m",
+						  "dummy", "osc_32k"};
 
 static struct clk_hw **hws;
 static struct clk_hw_onecell_data *clk_hw_data;
 
+struct imx8mp_clock_constraints {
+	unsigned int clkid;
+	u32 maxrate;
+};
+
+/*
+ * Below tables are taken from IMX8MPCEC Rev. 2.1, 07/2023
+ * Table 13. Maximum frequency of modules.
+ * Probable typos fixed are marked with a comment.
+ */
+static const struct imx8mp_clock_constraints imx8mp_clock_common_constraints[] = {
+	{ IMX8MP_CLK_A53_DIV,             1000 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_ENET_AXI,             266666667 }, /* Datasheet claims 266MHz */
+	{ IMX8MP_CLK_NAND_USDHC_BUS,       266666667 }, /* Datasheet claims 266MHz */
+	{ IMX8MP_CLK_MEDIA_APB,            200 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_HDMI_APB,             133333333 }, /* Datasheet claims 133MHz */
+	{ IMX8MP_CLK_ML_AXI,               800 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_AHB,                  133333333 },
+	{ IMX8MP_CLK_IPG_ROOT,              66666667 },
+	{ IMX8MP_CLK_AUDIO_AHB,            400 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_MEDIA_DISP2_PIX,      170 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_DRAM_ALT,             666666667 },
+	{ IMX8MP_CLK_DRAM_APB,             200 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_CAN1,                  80 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_CAN2,                  80 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_PCIE_AUX,              10 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_I2C5,                  66666667 }, /* Datasheet claims 66MHz */
+	{ IMX8MP_CLK_I2C6,                  66666667 }, /* Datasheet claims 66MHz */
+	{ IMX8MP_CLK_SAI1,                  66666667 }, /* Datasheet claims 66MHz */
+	{ IMX8MP_CLK_SAI2,                  66666667 }, /* Datasheet claims 66MHz */
+	{ IMX8MP_CLK_SAI3,                  66666667 }, /* Datasheet claims 66MHz */
+	{ IMX8MP_CLK_SAI5,                  66666667 }, /* Datasheet claims 66MHz */
+	{ IMX8MP_CLK_SAI6,                  66666667 }, /* Datasheet claims 66MHz */
+	{ IMX8MP_CLK_ENET_QOS,             125 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_ENET_QOS_TIMER,       200 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_ENET_REF,             125 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_ENET_TIMER,           125 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_ENET_PHY_REF,         125 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_NAND,                 500 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_QSPI,                 400 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_USDHC1,               400 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_USDHC2,               400 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_I2C1,                  66666667 }, /* Datasheet claims 66MHz */
+	{ IMX8MP_CLK_I2C2,                  66666667 }, /* Datasheet claims 66MHz */
+	{ IMX8MP_CLK_I2C3,                  66666667 }, /* Datasheet claims 66MHz */
+	{ IMX8MP_CLK_I2C4,                  66666667 }, /* Datasheet claims 66MHz */
+	{ IMX8MP_CLK_UART1,                 80 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_UART2,                 80 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_UART3,                 80 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_UART4,                 80 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_ECSPI1,                80 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_ECSPI2,                80 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_PWM1,                  66666667 }, /* Datasheet claims 66MHz */
+	{ IMX8MP_CLK_PWM2,                  66666667 }, /* Datasheet claims 66MHz */
+	{ IMX8MP_CLK_PWM3,                  66666667 }, /* Datasheet claims 66MHz */
+	{ IMX8MP_CLK_PWM4,                  66666667 }, /* Datasheet claims 66MHz */
+	{ IMX8MP_CLK_GPT1,                 100 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_GPT2,                 100 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_GPT3,                 100 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_GPT4,                 100 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_GPT5,                 100 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_GPT6,                 100 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_WDOG,                  66666667 }, /* Datasheet claims 66MHz */
+	{ IMX8MP_CLK_IPP_DO_CLKO1,         200 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_IPP_DO_CLKO2,         200 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_HDMI_REF_266M,        266 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_USDHC3,               400 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_MEDIA_MIPI_PHY1_REF,  300 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_MEDIA_DISP1_PIX,      250 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_MEDIA_CAM2_PIX,       277 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_MEDIA_LDB,            595 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_MEDIA_MIPI_TEST_BYTE, 200 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_ECSPI3,                80 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_PDM,                  200 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_SAI7,                  66666667 }, /* Datasheet claims 66MHz */
+	{ IMX8MP_CLK_MAIN_AXI,             400 * HZ_PER_MHZ },
+	{ /* Sentinel */ }
+};
+
+static const struct imx8mp_clock_constraints imx8mp_clock_nominal_constraints[] = {
+	{ IMX8MP_CLK_M7_CORE,           600 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_ML_CORE,           800 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_GPU3D_CORE,        800 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_GPU3D_SHADER_CORE, 800 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_GPU2D_CORE,        800 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_AUDIO_AXI_SRC,     600 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_HSIO_AXI,          400 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_MEDIA_ISP,         400 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_VPU_BUS,           600 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_MEDIA_AXI,         400 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_HDMI_AXI,          400 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_GPU_AXI,           600 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_GPU_AHB,           300 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_NOC,               800 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_NOC_IO,            600 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_ML_AHB,            300 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_VPU_G1,            600 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_VPU_G2,            500 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_MEDIA_CAM1_PIX,    400 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_VPU_VC8000E,       400 * HZ_PER_MHZ }, /* Datasheet claims 500MHz */
+	{ IMX8MP_CLK_DRAM_CORE,         800 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_GIC,               400 * HZ_PER_MHZ },
+	{ /* Sentinel */ }
+};
+
+static const struct imx8mp_clock_constraints imx8mp_clock_overdrive_constraints[] = {
+	{ IMX8MP_CLK_M7_CORE,            800 * HZ_PER_MHZ},
+	{ IMX8MP_CLK_ML_CORE,           1000 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_GPU3D_CORE,        1000 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_GPU3D_SHADER_CORE, 1000 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_GPU2D_CORE,        1000 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_AUDIO_AXI_SRC,      800 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_HSIO_AXI,           500 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_MEDIA_ISP,          500 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_VPU_BUS,            800 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_MEDIA_AXI,          500 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_HDMI_AXI,           500 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_GPU_AXI,            800 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_GPU_AHB,            400 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_NOC,               1000 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_NOC_IO,             800 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_ML_AHB,             400 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_VPU_G1,             800 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_VPU_G2,             700 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_MEDIA_CAM1_PIX,     500 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_VPU_VC8000E,        500 * HZ_PER_MHZ }, /* Datasheet claims 400MHz */
+	{ IMX8MP_CLK_DRAM_CORE,         1000 * HZ_PER_MHZ },
+	{ IMX8MP_CLK_GIC,                500 * HZ_PER_MHZ },
+	{ /* Sentinel */ }
+};
+
+static void imx8mp_clocks_apply_constraints(const struct imx8mp_clock_constraints constraints[])
+{
+	const struct imx8mp_clock_constraints *constr;
+
+	for (constr = constraints; constr->clkid; constr++)
+		clk_hw_set_rate_range(hws[constr->clkid], 0, constr->maxrate);
+}
+
 static int imx8mp_clocks_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct device_node *np;
 	void __iomem *anatop_base, *ccm_base;
+	const char *opmode;
 	int err;
 
 	np = of_find_compatible_node(NULL, NULL, "fsl,imx8mp-anatop");
@@ -714,6 +856,16 @@ static int imx8mp_clocks_probe(struct platform_device *pdev)
 
 	imx_check_clk_hws(hws, IMX8MP_CLK_END);
 
+	imx8mp_clocks_apply_constraints(imx8mp_clock_common_constraints);
+
+	err = of_property_read_string(np, "fsl,operating-mode", &opmode);
+	if (!err) {
+		if (!strcmp(opmode, "nominal"))
+			imx8mp_clocks_apply_constraints(imx8mp_clock_nominal_constraints);
+		else if (!strcmp(opmode, "overdrive"))
+			imx8mp_clocks_apply_constraints(imx8mp_clock_overdrive_constraints);
+	}
+
 	err = of_clk_add_hw_provider(np, of_clk_hw_onecell_get, clk_hw_data);
 	if (err < 0) {
 		dev_err(dev, "failed to register hws for i.MX8MP\n");
diff --git a/drivers/clk/imx/clk-imx93.c b/drivers/clk/imx/clk-imx93.c
index c6a9bc8ecc1f..c5f358a75f30 100644
--- a/drivers/clk/imx/clk-imx93.c
+++ b/drivers/clk/imx/clk-imx93.c
@@ -15,6 +15,11 @@
 
 #include "clk.h"
 
+#define IMX93_CLK_END 208
+
+#define PLAT_IMX93 BIT(0)
+#define PLAT_IMX91 BIT(1)
+
 enum clk_sel {
 	LOW_SPEED_IO_SEL,
 	NON_IO_SEL,
@@ -33,6 +38,7 @@ static u32 share_count_sai2;
 static u32 share_count_sai3;
 static u32 share_count_mub;
 static u32 share_count_pdm;
+static u32 share_count_spdif;
 
 static const char * const a55_core_sels[] = {"a55_alt", "arm_pll"};
 static const char *parent_names[MAX_SEL][4] = {
@@ -53,6 +59,7 @@ static const struct imx93_clk_root {
 	u32 off;
 	enum clk_sel sel;
 	unsigned long flags;
+	unsigned long plat;
 } root_array[] = {
 	/* a55/m33/bus critical clk for system run */
 	{ IMX93_CLK_A55_PERIPH,		"a55_periph_root",	0x0000,	FAST_SEL, CLK_IS_CRITICAL },
@@ -63,9 +70,9 @@ static const struct imx93_clk_root {
 	{ IMX93_CLK_BUS_AON,		"bus_aon_root",		0x0300,	LOW_SPEED_IO_SEL, CLK_IS_CRITICAL },
 	{ IMX93_CLK_WAKEUP_AXI,		"wakeup_axi_root",	0x0380,	FAST_SEL, CLK_IS_CRITICAL },
 	{ IMX93_CLK_SWO_TRACE,		"swo_trace_root",	0x0400,	LOW_SPEED_IO_SEL, },
-	{ IMX93_CLK_M33_SYSTICK,	"m33_systick_root",	0x0480,	LOW_SPEED_IO_SEL, },
-	{ IMX93_CLK_FLEXIO1,		"flexio1_root",		0x0500,	LOW_SPEED_IO_SEL, },
-	{ IMX93_CLK_FLEXIO2,		"flexio2_root",		0x0580,	LOW_SPEED_IO_SEL, },
+	{ IMX93_CLK_M33_SYSTICK,	"m33_systick_root",	0x0480,	LOW_SPEED_IO_SEL, 0, PLAT_IMX93, },
+	{ IMX93_CLK_FLEXIO1,		"flexio1_root",		0x0500,	LOW_SPEED_IO_SEL, 0, PLAT_IMX93, },
+	{ IMX93_CLK_FLEXIO2,		"flexio2_root",		0x0580,	LOW_SPEED_IO_SEL, 0, PLAT_IMX93, },
 	{ IMX93_CLK_LPTMR1,		"lptmr1_root",		0x0700,	LOW_SPEED_IO_SEL, },
 	{ IMX93_CLK_LPTMR2,		"lptmr2_root",		0x0780,	LOW_SPEED_IO_SEL, },
 	{ IMX93_CLK_TPM2,		"tpm2_root",		0x0880,	TPM_SEL, },
@@ -120,15 +127,15 @@ static const struct imx93_clk_root {
 	{ IMX93_CLK_HSIO_ACSCAN_80M,	"hsio_acscan_80m_root",	0x1f80,	LOW_SPEED_IO_SEL, },
 	{ IMX93_CLK_HSIO_ACSCAN_480M,	"hsio_acscan_480m_root", 0x2000, MISC_SEL, },
 	{ IMX93_CLK_NIC_AXI,		"nic_axi_root",		0x2080, FAST_SEL, CLK_IS_CRITICAL, },
-	{ IMX93_CLK_ML_APB,		"ml_apb_root",		0x2180,	LOW_SPEED_IO_SEL, },
-	{ IMX93_CLK_ML,			"ml_root",		0x2200,	FAST_SEL, },
+	{ IMX93_CLK_ML_APB,		"ml_apb_root",		0x2180,	LOW_SPEED_IO_SEL, 0, PLAT_IMX93, },
+	{ IMX93_CLK_ML,			"ml_root",		0x2200,	FAST_SEL, 0, PLAT_IMX93, },
 	{ IMX93_CLK_MEDIA_AXI,		"media_axi_root",	0x2280,	FAST_SEL, },
 	{ IMX93_CLK_MEDIA_APB,		"media_apb_root",	0x2300,	LOW_SPEED_IO_SEL, },
-	{ IMX93_CLK_MEDIA_LDB,		"media_ldb_root",	0x2380,	VIDEO_SEL, },
+	{ IMX93_CLK_MEDIA_LDB,		"media_ldb_root",	0x2380,	VIDEO_SEL, 0, PLAT_IMX93, },
 	{ IMX93_CLK_MEDIA_DISP_PIX,	"media_disp_pix_root",	0x2400,	VIDEO_SEL, },
 	{ IMX93_CLK_CAM_PIX,		"cam_pix_root",		0x2480,	VIDEO_SEL, },
-	{ IMX93_CLK_MIPI_TEST_BYTE,	"mipi_test_byte_root",	0x2500,	VIDEO_SEL, },
-	{ IMX93_CLK_MIPI_PHY_CFG,	"mipi_phy_cfg_root",	0x2580,	VIDEO_SEL, },
+	{ IMX93_CLK_MIPI_TEST_BYTE,	"mipi_test_byte_root",	0x2500,	VIDEO_SEL, 0, PLAT_IMX93, },
+	{ IMX93_CLK_MIPI_PHY_CFG,	"mipi_phy_cfg_root",	0x2580,	VIDEO_SEL, 0, PLAT_IMX93, },
 	{ IMX93_CLK_ADC,		"adc_root",		0x2700,	LOW_SPEED_IO_SEL, },
 	{ IMX93_CLK_PDM,		"pdm_root",		0x2780,	AUDIO_SEL, },
 	{ IMX93_CLK_TSTMR1,		"tstmr1_root",		0x2800,	LOW_SPEED_IO_SEL, },
@@ -137,13 +144,16 @@ static const struct imx93_clk_root {
 	{ IMX93_CLK_MQS2,		"mqs2_root",		0x2980,	AUDIO_SEL, },
 	{ IMX93_CLK_AUDIO_XCVR,		"audio_xcvr_root",	0x2a00,	NON_IO_SEL, },
 	{ IMX93_CLK_SPDIF,		"spdif_root",		0x2a80,	AUDIO_SEL, },
-	{ IMX93_CLK_ENET,		"enet_root",		0x2b00,	NON_IO_SEL, },
-	{ IMX93_CLK_ENET_TIMER1,	"enet_timer1_root",	0x2b80,	LOW_SPEED_IO_SEL, },
-	{ IMX93_CLK_ENET_TIMER2,	"enet_timer2_root",	0x2c00,	LOW_SPEED_IO_SEL, },
-	{ IMX93_CLK_ENET_REF,		"enet_ref_root",	0x2c80,	NON_IO_SEL, },
-	{ IMX93_CLK_ENET_REF_PHY,	"enet_ref_phy_root",	0x2d00,	LOW_SPEED_IO_SEL, },
-	{ IMX93_CLK_I3C1_SLOW,		"i3c1_slow_root",	0x2d80,	LOW_SPEED_IO_SEL, },
-	{ IMX93_CLK_I3C2_SLOW,		"i3c2_slow_root",	0x2e00,	LOW_SPEED_IO_SEL, },
+	{ IMX93_CLK_ENET,		"enet_root",		0x2b00,	NON_IO_SEL, 0, PLAT_IMX93, },
+	{ IMX93_CLK_ENET_TIMER1,	"enet_timer1_root",	0x2b80,	LOW_SPEED_IO_SEL, 0, PLAT_IMX93, },
+	{ IMX93_CLK_ENET_TIMER2,	"enet_timer2_root",	0x2c00,	LOW_SPEED_IO_SEL, 0, PLAT_IMX93, },
+	{ IMX93_CLK_ENET_REF,		"enet_ref_root",	0x2c80,	NON_IO_SEL, 0, PLAT_IMX93, },
+	{ IMX93_CLK_ENET_REF_PHY,	"enet_ref_phy_root",	0x2d00,	LOW_SPEED_IO_SEL, 0, PLAT_IMX93, },
+	{ IMX91_CLK_ENET1_QOS_TSN,	"enet1_qos_tsn_root",   0x2b00, NON_IO_SEL, 0, PLAT_IMX91, },
+	{ IMX91_CLK_ENET_TIMER,		"enet_timer_root",      0x2b80, LOW_SPEED_IO_SEL, 0, PLAT_IMX91, },
+	{ IMX91_CLK_ENET2_REGULAR,	"enet2_regular_root",   0x2c80, NON_IO_SEL, 0, PLAT_IMX91, },
+	{ IMX93_CLK_I3C1_SLOW,		"i3c1_slow_root",	0x2d80,	LOW_SPEED_IO_SEL, 0, PLAT_IMX93, },
+	{ IMX93_CLK_I3C2_SLOW,		"i3c2_slow_root",	0x2e00,	LOW_SPEED_IO_SEL, 0, PLAT_IMX93, },
 	{ IMX93_CLK_USB_PHY_BURUNIN,	"usb_phy_root",		0x2e80,	LOW_SPEED_IO_SEL, },
 	{ IMX93_CLK_PAL_CAME_SCAN,	"pal_came_scan_root",	0x2f00,	MISC_SEL, }
 };
@@ -155,6 +165,7 @@ static const struct imx93_clk_ccgr {
 	u32 off;
 	unsigned long flags;
 	u32 *shared_count;
+	unsigned long plat;
 } ccgr_array[] = {
 	{ IMX93_CLK_A55_GATE,		"a55_alt",	"a55_alt_root",		0x8000, },
 	/* M33 critical clk for system run */
@@ -167,10 +178,10 @@ static const struct imx93_clk_ccgr {
 	{ IMX93_CLK_WDOG5_GATE,		"wdog5",	"osc_24m",		0x8400, },
 	{ IMX93_CLK_SEMA1_GATE,		"sema1",	"bus_aon_root",		0x8440, },
 	{ IMX93_CLK_SEMA2_GATE,		"sema2",	"bus_wakeup_root",	0x8480, },
-	{ IMX93_CLK_MU1_A_GATE,		"mu1_a",	"bus_aon_root",		0x84c0, CLK_IGNORE_UNUSED },
-	{ IMX93_CLK_MU2_A_GATE,		"mu2_a",	"bus_wakeup_root",	0x84c0, CLK_IGNORE_UNUSED },
-	{ IMX93_CLK_MU1_B_GATE,		"mu1_b",	"bus_aon_root",		0x8500, 0, &share_count_mub },
-	{ IMX93_CLK_MU2_B_GATE,		"mu2_b",	"bus_wakeup_root",	0x8500, 0, &share_count_mub },
+	{ IMX93_CLK_MU1_A_GATE,		"mu1_a",	"bus_aon_root",		0x84c0, CLK_IGNORE_UNUSED, NULL, PLAT_IMX93 },
+	{ IMX93_CLK_MU2_A_GATE,		"mu2_a",	"bus_wakeup_root",	0x84c0, CLK_IGNORE_UNUSED, NULL, PLAT_IMX93 },
+	{ IMX93_CLK_MU1_B_GATE,		"mu1_b",	"bus_aon_root",		0x8500, 0, &share_count_mub, PLAT_IMX93 },
+	{ IMX93_CLK_MU2_B_GATE,		"mu2_b",	"bus_wakeup_root",	0x8500, 0, &share_count_mub, PLAT_IMX93 },
 	{ IMX93_CLK_EDMA1_GATE,		"edma1",	"m33_root",		0x8540, },
 	{ IMX93_CLK_EDMA2_GATE,		"edma2",	"wakeup_axi_root",	0x8580, },
 	{ IMX93_CLK_FLEXSPI1_GATE,	"flexspi1",	"flexspi1_root",	0x8640, },
@@ -178,8 +189,8 @@ static const struct imx93_clk_ccgr {
 	{ IMX93_CLK_GPIO2_GATE,		"gpio2",	"bus_wakeup_root",	0x88c0, },
 	{ IMX93_CLK_GPIO3_GATE,		"gpio3",	"bus_wakeup_root",	0x8900, },
 	{ IMX93_CLK_GPIO4_GATE,		"gpio4",	"bus_wakeup_root",	0x8940, },
-	{ IMX93_CLK_FLEXIO1_GATE,	"flexio1",	"flexio1_root",		0x8980, },
-	{ IMX93_CLK_FLEXIO2_GATE,	"flexio2",	"flexio2_root",		0x89c0, },
+	{ IMX93_CLK_FLEXIO1_GATE,	"flexio1",	"flexio1_root",		0x8980, 0, NULL, PLAT_IMX93},
+	{ IMX93_CLK_FLEXIO2_GATE,	"flexio2",	"flexio2_root",		0x89c0, 0, NULL, PLAT_IMX93},
 	{ IMX93_CLK_LPIT1_GATE,		"lpit1",	"bus_aon_root",		0x8a00, },
 	{ IMX93_CLK_LPIT2_GATE,		"lpit2",	"bus_wakeup_root",	0x8a40, },
 	{ IMX93_CLK_LPTMR1_GATE,	"lptmr1",	"lptmr1_root",		0x8a80, },
@@ -228,10 +239,10 @@ static const struct imx93_clk_ccgr {
 	{ IMX93_CLK_SAI3_GATE,          "sai3",         "sai3_root",            0x94c0, 0, &share_count_sai3},
 	{ IMX93_CLK_SAI3_IPG,		"sai3_ipg_clk", "bus_wakeup_root",	0x94c0, 0, &share_count_sai3},
 	{ IMX93_CLK_MIPI_CSI_GATE,	"mipi_csi",	"media_apb_root",	0x9580, },
-	{ IMX93_CLK_MIPI_DSI_GATE,	"mipi_dsi",	"media_apb_root",	0x95c0, },
-	{ IMX93_CLK_LVDS_GATE,		"lvds",		"media_ldb_root",	0x9600, },
+	{ IMX93_CLK_MIPI_DSI_GATE,	"mipi_dsi",	"media_apb_root",	0x95c0, 0, NULL, PLAT_IMX93 },
+	{ IMX93_CLK_LVDS_GATE,		"lvds",		"media_ldb_root",	0x9600, 0, NULL, PLAT_IMX93 },
 	{ IMX93_CLK_LCDIF_GATE,		"lcdif",	"media_apb_root",	0x9640, },
-	{ IMX93_CLK_PXP_GATE,		"pxp",		"media_apb_root",	0x9680, },
+	{ IMX93_CLK_PXP_GATE,		"pxp",		"media_apb_root",	0x9680, 0, NULL, PLAT_IMX93 },
 	{ IMX93_CLK_ISI_GATE,		"isi",		"media_apb_root",	0x96c0, },
 	{ IMX93_CLK_NIC_MEDIA_GATE,	"nic_media",	"media_axi_root",	0x9700, },
 	{ IMX93_CLK_USB_CONTROLLER_GATE, "usb_controller", "hsio_root",		0x9a00, },
@@ -242,10 +253,13 @@ static const struct imx93_clk_ccgr {
 	{ IMX93_CLK_MQS1_GATE,		"mqs1",		"sai1_root",		0x9b00, },
 	{ IMX93_CLK_MQS2_GATE,		"mqs2",		"sai3_root",		0x9b40, },
 	{ IMX93_CLK_AUD_XCVR_GATE,	"aud_xcvr",	"audio_xcvr_root",	0x9b80, },
-	{ IMX93_CLK_SPDIF_GATE,		"spdif",	"spdif_root",		0x9c00, },
+	{ IMX93_CLK_SPDIF_IPG,		"spdif_ipg_clk", "bus_wakeup_root",	0x9c00, 0, &share_count_spdif},
+	{ IMX93_CLK_SPDIF_GATE,		"spdif",	"spdif_root",		0x9c00, 0, &share_count_spdif},
 	{ IMX93_CLK_HSIO_32K_GATE,	"hsio_32k",	"osc_32k",		0x9dc0, },
-	{ IMX93_CLK_ENET1_GATE,		"enet1",	"wakeup_axi_root",	0x9e00, },
-	{ IMX93_CLK_ENET_QOS_GATE,	"enet_qos",	"wakeup_axi_root",	0x9e40, },
+	{ IMX93_CLK_ENET1_GATE,		"enet1",	"wakeup_axi_root",	0x9e00, 0, NULL, PLAT_IMX93, },
+	{ IMX93_CLK_ENET_QOS_GATE,	"enet_qos",	"wakeup_axi_root",	0x9e40, 0, NULL, PLAT_IMX93, },
+	{ IMX91_CLK_ENET2_REGULAR_GATE, "enet2_regular", "wakeup_axi_root",	0x9e00, 0, NULL, PLAT_IMX91, },
+	{ IMX91_CLK_ENET1_QOS_TSN_GATE, "enet1_qos_tsn", "wakeup_axi_root",	0x9e40, 0, NULL, PLAT_IMX91, },
 	/* Critical because clk accessed during CPU idle */
 	{ IMX93_CLK_SYS_CNT_GATE,	"sys_cnt",	"osc_24m",		0x9e80, CLK_IS_CRITICAL},
 	{ IMX93_CLK_TSTMR1_GATE,	"tstmr1",	"bus_aon_root",		0x9ec0, },
@@ -265,6 +279,7 @@ static int imx93_clocks_probe(struct platform_device *pdev)
 	const struct imx93_clk_ccgr *ccgr;
 	void __iomem *base, *anatop_base;
 	int i, ret;
+	const unsigned long plat = (unsigned long)device_get_match_data(&pdev->dev);
 
 	clk_hw_data = devm_kzalloc(dev, struct_size(clk_hw_data, hws,
 					  IMX93_CLK_END), GFP_KERNEL);
@@ -314,17 +329,20 @@ static int imx93_clocks_probe(struct platform_device *pdev)
 
 	for (i = 0; i < ARRAY_SIZE(root_array); i++) {
 		root = &root_array[i];
-		clks[root->clk] = imx93_clk_composite_flags(root->name,
-							    parent_names[root->sel],
-							    4, base + root->off, 3,
-							    root->flags);
+		if (!root->plat || root->plat & plat)
+			clks[root->clk] = imx93_clk_composite_flags(root->name,
+								    parent_names[root->sel],
+								    4, base + root->off, 3,
+								    root->flags);
 	}
 
 	for (i = 0; i < ARRAY_SIZE(ccgr_array); i++) {
 		ccgr = &ccgr_array[i];
-		clks[ccgr->clk] = imx93_clk_gate(NULL, ccgr->name, ccgr->parent_name,
-						 ccgr->flags, base + ccgr->off, 0, 1, 1, 3,
-						 ccgr->shared_count);
+		if (!ccgr->plat || ccgr->plat & plat)
+			clks[ccgr->clk] = imx93_clk_gate(NULL,
+							 ccgr->name, ccgr->parent_name,
+							 ccgr->flags, base + ccgr->off, 0, 1, 1, 3,
+							 ccgr->shared_count);
 	}
 
 	clks[IMX93_CLK_A55_SEL] = imx_clk_hw_mux2("a55_sel", base + 0x4820, 0, 1, a55_core_sels,
@@ -354,7 +372,8 @@ unregister_hws:
 }
 
 static const struct of_device_id imx93_clk_of_match[] = {
-	{ .compatible = "fsl,imx93-ccm" },
+	{ .compatible = "fsl,imx93-ccm", .data = (void *)PLAT_IMX93 },
+	{ .compatible = "fsl,imx91-ccm", .data = (void *)PLAT_IMX91 },
 	{ /* Sentinel */ },
 };
 MODULE_DEVICE_TABLE(of, imx93_clk_of_match);
diff --git a/drivers/clk/imx/clk-imx95-blk-ctl.c b/drivers/clk/imx/clk-imx95-blk-ctl.c
index 19a62da74be4..5030e6e60b66 100644
--- a/drivers/clk/imx/clk-imx95-blk-ctl.c
+++ b/drivers/clk/imx/clk-imx95-blk-ctl.c
@@ -219,11 +219,15 @@ static const struct imx95_blk_ctl_dev_data lvds_csr_dev_data = {
 	.clk_reg_offset = 0,
 };
 
+static const char * const disp_engine_parents[] = {
+	"videopll1", "dsi_pll", "ldb_pll_div7"
+};
+
 static const struct imx95_blk_ctl_clk_dev_data dispmix_csr_clk_dev_data[] = {
 	[IMX95_CLK_DISPMIX_ENG0_SEL] = {
 		.name = "disp_engine0_sel",
-		.parent_names = (const char *[]){"videopll1", "dsi_pll", "ldb_pll_div7", },
-		.num_parents = 4,
+		.parent_names = disp_engine_parents,
+		.num_parents = ARRAY_SIZE(disp_engine_parents),
 		.reg = 0,
 		.bit_idx = 0,
 		.bit_width = 2,
@@ -232,8 +236,8 @@ static const struct imx95_blk_ctl_clk_dev_data dispmix_csr_clk_dev_data[] = {
 	},
 	[IMX95_CLK_DISPMIX_ENG1_SEL] = {
 		.name = "disp_engine1_sel",
-		.parent_names = (const char *[]){"videopll1", "dsi_pll", "ldb_pll_div7", },
-		.num_parents = 4,
+		.parent_names = disp_engine_parents,
+		.num_parents = ARRAY_SIZE(disp_engine_parents),
 		.reg = 0,
 		.bit_idx = 2,
 		.bit_width = 2,
@@ -319,8 +323,10 @@ static int imx95_bc_probe(struct platform_device *pdev)
 	if (!clk_hw_data)
 		return -ENOMEM;
 
-	if (bc_data->rpm_enabled)
-		pm_runtime_enable(&pdev->dev);
+	if (bc_data->rpm_enabled) {
+		devm_pm_runtime_enable(&pdev->dev);
+		pm_runtime_resume_and_get(&pdev->dev);
+	}
 
 	clk_hw_data->num = bc_data->num_clks;
 	hws = clk_hw_data->hws;
@@ -360,8 +366,10 @@ static int imx95_bc_probe(struct platform_device *pdev)
 		goto cleanup;
 	}
 
-	if (pm_runtime_enabled(bc->dev))
+	if (pm_runtime_enabled(bc->dev)) {
+		pm_runtime_put_sync(&pdev->dev);
 		clk_disable_unprepare(bc->clk_apb);
+	}
 
 	return 0;
 
@@ -372,9 +380,6 @@ cleanup:
 		clk_hw_unregister(hws[i]);
 	}
 
-	if (bc_data->rpm_enabled)
-		pm_runtime_disable(&pdev->dev);
-
 	return ret;
 }
 
diff --git a/drivers/clk/mediatek/clk-mt2701-aud.c b/drivers/clk/mediatek/clk-mt2701-aud.c
index 425c69cfb105..e103121cf58e 100644
--- a/drivers/clk/mediatek/clk-mt2701-aud.c
+++ b/drivers/clk/mediatek/clk-mt2701-aud.c
@@ -55,10 +55,16 @@ static const struct mtk_gate audio_clks[] = {
 	GATE_DUMMY(CLK_DUMMY, "aud_dummy"),
 	/* AUDIO0 */
 	GATE_AUDIO0(CLK_AUD_AFE, "audio_afe", "aud_intbus_sel", 2),
+	GATE_DUMMY(CLK_AUD_LRCK_DETECT, "audio_lrck_detect_dummy"),
+	GATE_DUMMY(CLK_AUD_I2S, "audio_i2c_dummy"),
+	GATE_DUMMY(CLK_AUD_APLL_TUNER, "audio_apll_tuner_dummy"),
 	GATE_AUDIO0(CLK_AUD_HDMI, "audio_hdmi", "audpll_sel", 20),
 	GATE_AUDIO0(CLK_AUD_SPDF, "audio_spdf", "audpll_sel", 21),
 	GATE_AUDIO0(CLK_AUD_SPDF2, "audio_spdf2", "audpll_sel", 22),
 	GATE_AUDIO0(CLK_AUD_APLL, "audio_apll", "audpll_sel", 23),
+	GATE_DUMMY(CLK_AUD_TML, "audio_tml_dummy"),
+	GATE_DUMMY(CLK_AUD_AHB_IDLE_EXT, "audio_ahb_idle_ext_dummy"),
+	GATE_DUMMY(CLK_AUD_AHB_IDLE_INT, "audio_ahb_idle_int_dummy"),
 	/* AUDIO1 */
 	GATE_AUDIO1(CLK_AUD_I2SIN1, "audio_i2sin1", "aud_mux1_sel", 0),
 	GATE_AUDIO1(CLK_AUD_I2SIN2, "audio_i2sin2", "aud_mux1_sel", 1),
@@ -76,10 +82,12 @@ static const struct mtk_gate audio_clks[] = {
 	GATE_AUDIO1(CLK_AUD_ASRCI2, "audio_asrci2", "asm_h_sel", 13),
 	GATE_AUDIO1(CLK_AUD_ASRCO1, "audio_asrco1", "asm_h_sel", 14),
 	GATE_AUDIO1(CLK_AUD_ASRCO2, "audio_asrco2", "asm_h_sel", 15),
+	GATE_DUMMY(CLK_AUD_HDMIRX, "audio_hdmirx_dummy"),
 	GATE_AUDIO1(CLK_AUD_INTDIR, "audio_intdir", "intdir_sel", 20),
 	GATE_AUDIO1(CLK_AUD_A1SYS, "audio_a1sys", "aud_mux1_sel", 21),
 	GATE_AUDIO1(CLK_AUD_A2SYS, "audio_a2sys", "aud_mux2_sel", 22),
 	GATE_AUDIO1(CLK_AUD_AFE_CONN, "audio_afe_conn", "aud_mux1_sel", 23),
+	GATE_DUMMY(CLK_AUD_AFE_PCMIF, "audio_afe_pcmif_dummy"),
 	GATE_AUDIO1(CLK_AUD_AFE_MRGIF, "audio_afe_mrgif", "aud_mux1_sel", 25),
 	/* AUDIO2 */
 	GATE_AUDIO2(CLK_AUD_MMIF_UL1, "audio_ul1", "aud_mux1_sel", 0),
@@ -100,6 +108,8 @@ static const struct mtk_gate audio_clks[] = {
 	GATE_AUDIO2(CLK_AUD_MMIF_AWB2, "audio_awb2", "aud_mux1_sel", 15),
 	GATE_AUDIO2(CLK_AUD_MMIF_DAI, "audio_dai", "aud_mux1_sel", 16),
 	/* AUDIO3 */
+	GATE_DUMMY(CLK_AUD_DMIC1, "audio_dmic1_dummy"),
+	GATE_DUMMY(CLK_AUD_DMIC2, "audio_dmic2_dummy"),
 	GATE_AUDIO3(CLK_AUD_ASRCI3, "audio_asrci3", "asm_h_sel", 2),
 	GATE_AUDIO3(CLK_AUD_ASRCI4, "audio_asrci4", "asm_h_sel", 3),
 	GATE_AUDIO3(CLK_AUD_ASRCI5, "audio_asrci5", "asm_h_sel", 4),
diff --git a/drivers/clk/mediatek/clk-mt2701-bdp.c b/drivers/clk/mediatek/clk-mt2701-bdp.c
index 5da3eabffd3e..f11c7a4fa37b 100644
--- a/drivers/clk/mediatek/clk-mt2701-bdp.c
+++ b/drivers/clk/mediatek/clk-mt2701-bdp.c
@@ -31,6 +31,7 @@ static const struct mtk_gate_regs bdp1_cg_regs = {
 	GATE_MTK(_id, _name, _parent, &bdp1_cg_regs, _shift, &mtk_clk_gate_ops_setclr_inv)
 
 static const struct mtk_gate bdp_clks[] = {
+	GATE_DUMMY(CLK_DUMMY, "bdp_dummy"),
 	GATE_BDP0(CLK_BDP_BRG_BA, "brg_baclk", "mm_sel", 0),
 	GATE_BDP0(CLK_BDP_BRG_DRAM, "brg_dram", "mm_sel", 1),
 	GATE_BDP0(CLK_BDP_LARB_DRAM, "larb_dram", "mm_sel", 2),
diff --git a/drivers/clk/mediatek/clk-mt2701-img.c b/drivers/clk/mediatek/clk-mt2701-img.c
index 875594bc9dcb..c158e54c4652 100644
--- a/drivers/clk/mediatek/clk-mt2701-img.c
+++ b/drivers/clk/mediatek/clk-mt2701-img.c
@@ -22,6 +22,7 @@ static const struct mtk_gate_regs img_cg_regs = {
 	GATE_MTK(_id, _name, _parent, &img_cg_regs, _shift, &mtk_clk_gate_ops_setclr)
 
 static const struct mtk_gate img_clks[] = {
+	GATE_DUMMY(CLK_DUMMY, "img_dummy"),
 	GATE_IMG(CLK_IMG_SMI_COMM, "img_smi_comm", "mm_sel", 0),
 	GATE_IMG(CLK_IMG_RESZ, "img_resz", "mm_sel", 1),
 	GATE_IMG(CLK_IMG_JPGDEC_SMI, "img_jpgdec_smi", "mm_sel", 5),
diff --git a/drivers/clk/mediatek/clk-mt2701-mm.c b/drivers/clk/mediatek/clk-mt2701-mm.c
index bc68fa718878..474d87d62e83 100644
--- a/drivers/clk/mediatek/clk-mt2701-mm.c
+++ b/drivers/clk/mediatek/clk-mt2701-mm.c
@@ -31,6 +31,7 @@ static const struct mtk_gate_regs disp1_cg_regs = {
 	GATE_MTK(_id, _name, _parent, &disp1_cg_regs, _shift, &mtk_clk_gate_ops_setclr)
 
 static const struct mtk_gate mm_clks[] = {
+	GATE_DUMMY(CLK_DUMMY, "mm_dummy"),
 	GATE_DISP0(CLK_MM_SMI_COMMON, "mm_smi_comm", "mm_sel", 0),
 	GATE_DISP0(CLK_MM_SMI_LARB0, "mm_smi_larb0", "mm_sel", 1),
 	GATE_DISP0(CLK_MM_CMDQ, "mm_cmdq", "mm_sel", 2),
diff --git a/drivers/clk/mediatek/clk-mt2701-vdec.c b/drivers/clk/mediatek/clk-mt2701-vdec.c
index 94db86f8d0a4..5299d92f3aba 100644
--- a/drivers/clk/mediatek/clk-mt2701-vdec.c
+++ b/drivers/clk/mediatek/clk-mt2701-vdec.c
@@ -31,6 +31,7 @@ static const struct mtk_gate_regs vdec1_cg_regs = {
 	GATE_MTK(_id, _name, _parent, &vdec1_cg_regs, _shift, &mtk_clk_gate_ops_setclr_inv)
 
 static const struct mtk_gate vdec_clks[] = {
+	GATE_DUMMY(CLK_DUMMY, "vdec_dummy"),
 	GATE_VDEC0(CLK_VDEC_CKGEN, "vdec_cken", "vdec_sel", 0),
 	GATE_VDEC1(CLK_VDEC_LARB, "vdec_larb_cken", "mm_sel", 0),
 };
diff --git a/drivers/clk/meson/g12a.c b/drivers/clk/meson/g12a.c
index 02dda57105b1..b72eebd0fa47 100644
--- a/drivers/clk/meson/g12a.c
+++ b/drivers/clk/meson/g12a.c
@@ -1139,8 +1139,18 @@ static struct clk_regmap g12a_cpu_clk_div16_en = {
 	.hw.init = &(struct clk_init_data) {
 		.name = "cpu_clk_div16_en",
 		.ops = &clk_regmap_gate_ro_ops,
-		.parent_hws = (const struct clk_hw *[]) {
-			&g12a_cpu_clk.hw
+		.parent_data = &(const struct clk_parent_data) {
+			/*
+			 * Note:
+			 * G12A and G12B have different cpu clocks (with
+			 * different struct clk_hw). We fallback to the global
+			 * naming string mechanism so this clock picks
+			 * up the appropriate one. Same goes for the other
+			 * clock using cpu cluster A clock output and present
+			 * on both G12 variant.
+			 */
+			.name = "cpu_clk",
+			.index = -1,
 		},
 		.num_parents = 1,
 		/*
@@ -1205,7 +1215,10 @@ static struct clk_regmap g12a_cpu_clk_apb_div = {
 	.hw.init = &(struct clk_init_data){
 		.name = "cpu_clk_apb_div",
 		.ops = &clk_regmap_divider_ro_ops,
-		.parent_hws = (const struct clk_hw *[]) { &g12a_cpu_clk.hw },
+		.parent_data = &(const struct clk_parent_data) {
+			.name = "cpu_clk",
+			.index = -1,
+		},
 		.num_parents = 1,
 	},
 };
@@ -1239,7 +1252,10 @@ static struct clk_regmap g12a_cpu_clk_atb_div = {
 	.hw.init = &(struct clk_init_data){
 		.name = "cpu_clk_atb_div",
 		.ops = &clk_regmap_divider_ro_ops,
-		.parent_hws = (const struct clk_hw *[]) { &g12a_cpu_clk.hw },
+		.parent_data = &(const struct clk_parent_data) {
+			.name = "cpu_clk",
+			.index = -1,
+		},
 		.num_parents = 1,
 	},
 };
@@ -1273,7 +1289,10 @@ static struct clk_regmap g12a_cpu_clk_axi_div = {
 	.hw.init = &(struct clk_init_data){
 		.name = "cpu_clk_axi_div",
 		.ops = &clk_regmap_divider_ro_ops,
-		.parent_hws = (const struct clk_hw *[]) { &g12a_cpu_clk.hw },
+		.parent_data = &(const struct clk_parent_data) {
+			.name = "cpu_clk",
+			.index = -1,
+		},
 		.num_parents = 1,
 	},
 };
@@ -1308,13 +1327,6 @@ static struct clk_regmap g12a_cpu_clk_trace_div = {
 		.name = "cpu_clk_trace_div",
 		.ops = &clk_regmap_divider_ro_ops,
 		.parent_data = &(const struct clk_parent_data) {
-			/*
-			 * Note:
-			 * G12A and G12B have different cpu_clks (with
-			 * different struct clk_hw). We fallback to the global
-			 * naming string mechanism so cpu_clk_trace_div picks
-			 * up the appropriate one.
-			 */
 			.name = "cpu_clk",
 			.index = -1,
 		},
@@ -4087,6 +4099,7 @@ static const struct clk_parent_data spicc_sclk_parent_data[] = {
 	{ .hw = &g12a_clk81.hw },
 	{ .hw = &g12a_fclk_div4.hw },
 	{ .hw = &g12a_fclk_div3.hw },
+	{ .hw = &g12a_fclk_div2.hw },
 	{ .hw = &g12a_fclk_div5.hw },
 	{ .hw = &g12a_fclk_div7.hw },
 };
@@ -4317,7 +4330,7 @@ static MESON_GATE(g12a_spicc_1,			HHI_GCLK_MPEG0,	14);
 static MESON_GATE(g12a_hiu_reg,			HHI_GCLK_MPEG0,	19);
 static MESON_GATE(g12a_mipi_dsi_phy,		HHI_GCLK_MPEG0,	20);
 static MESON_GATE(g12a_assist_misc,		HHI_GCLK_MPEG0,	23);
-static MESON_GATE(g12a_emmc_a,			HHI_GCLK_MPEG0,	4);
+static MESON_GATE(g12a_emmc_a,			HHI_GCLK_MPEG0,	24);
 static MESON_GATE(g12a_emmc_b,			HHI_GCLK_MPEG0,	25);
 static MESON_GATE(g12a_emmc_c,			HHI_GCLK_MPEG0,	26);
 static MESON_GATE(g12a_audio_codec,		HHI_GCLK_MPEG0,	28);
diff --git a/drivers/clk/meson/gxbb.c b/drivers/clk/meson/gxbb.c
index f071faad1ebb..d9529de200ae 100644
--- a/drivers/clk/meson/gxbb.c
+++ b/drivers/clk/meson/gxbb.c
@@ -1272,14 +1272,13 @@ static struct clk_regmap gxbb_cts_i958 = {
 	},
 };
 
+/*
+ * This table skips a clock named 'cts_slow_oscin' in the documentation
+ * This clock does not exist yet in this controller or the AO one
+ */
+static u32 gxbb_32k_clk_parents_val_table[] = { 0, 2, 3 };
 static const struct clk_parent_data gxbb_32k_clk_parent_data[] = {
 	{ .fw_name = "xtal", },
-	/*
-	 * FIXME: This clock is provided by the ao clock controller but the
-	 * clock is not yet part of the binding of this controller, so string
-	 * name must be use to set this parent.
-	 */
-	{ .name = "cts_slow_oscin", .index = -1 },
 	{ .hw = &gxbb_fclk_div3.hw },
 	{ .hw = &gxbb_fclk_div5.hw },
 };
@@ -1289,6 +1288,7 @@ static struct clk_regmap gxbb_32k_clk_sel = {
 		.offset = HHI_32K_CLK_CNTL,
 		.mask = 0x3,
 		.shift = 16,
+		.table = gxbb_32k_clk_parents_val_table,
 		},
 	.hw.init = &(struct clk_init_data){
 		.name = "32k_clk_sel",
@@ -1312,7 +1312,7 @@ static struct clk_regmap gxbb_32k_clk_div = {
 			&gxbb_32k_clk_sel.hw
 		},
 		.num_parents = 1,
-		.flags = CLK_SET_RATE_PARENT | CLK_DIVIDER_ROUND_CLOSEST,
+		.flags = CLK_SET_RATE_PARENT,
 	},
 };
 
diff --git a/drivers/clk/mmp/pwr-island.c b/drivers/clk/mmp/pwr-island.c
index edaa2433a472..eaf5d2c5e593 100644
--- a/drivers/clk/mmp/pwr-island.c
+++ b/drivers/clk/mmp/pwr-island.c
@@ -106,10 +106,10 @@ struct generic_pm_domain *mmp_pm_domain_register(const char *name,
 	pm_domain->flags = flags;
 	pm_domain->lock = lock;
 
-	pm_genpd_init(&pm_domain->genpd, NULL, true);
 	pm_domain->genpd.name = name;
 	pm_domain->genpd.power_on = mmp_pm_domain_power_on;
 	pm_domain->genpd.power_off = mmp_pm_domain_power_off;
+	pm_genpd_init(&pm_domain->genpd, NULL, true);
 
 	return &pm_domain->genpd;
 }
diff --git a/drivers/clk/qcom/Kconfig b/drivers/clk/qcom/Kconfig
index 9ba675f229b1..fd605bccf48d 100644
--- a/drivers/clk/qcom/Kconfig
+++ b/drivers/clk/qcom/Kconfig
@@ -199,7 +199,7 @@ config IPQ_GCC_4019
 
 config IPQ_GCC_5018
 	tristate "IPQ5018 Global Clock Controller"
-	depends on ARM64 || COMPILE_TEST
+	depends on ARM || ARM64 || COMPILE_TEST
 	help
 	  Support for global clock controller on ipq5018 devices.
 	  Say Y if you want to use peripheral devices such as UART, SPI,
@@ -1022,6 +1022,7 @@ config SM_GCC_7150
 config SM_GCC_8150
 	tristate "SM8150 Global Clock Controller"
 	depends on ARM64 || COMPILE_TEST
+	select QCOM_GDSC
 	help
 	  Support for the global clock controller on SM8150 devices.
 	  Say Y if you want to use peripheral devices such as UART,
diff --git a/drivers/clk/qcom/camcc-sm6350.c b/drivers/clk/qcom/camcc-sm6350.c
index f6634cc8663e..418668184ec3 100644
--- a/drivers/clk/qcom/camcc-sm6350.c
+++ b/drivers/clk/qcom/camcc-sm6350.c
@@ -1694,6 +1694,9 @@ static struct clk_branch camcc_sys_tmr_clk = {
 
 static struct gdsc bps_gdsc = {
 	.gdscr = 0x6004,
+	.en_rest_wait_val = 0x2,
+	.en_few_wait_val = 0x2,
+	.clk_dis_wait_val = 0xf,
 	.pd = {
 		.name = "bps_gdsc",
 	},
@@ -1703,6 +1706,9 @@ static struct gdsc bps_gdsc = {
 
 static struct gdsc ipe_0_gdsc = {
 	.gdscr = 0x7004,
+	.en_rest_wait_val = 0x2,
+	.en_few_wait_val = 0x2,
+	.clk_dis_wait_val = 0xf,
 	.pd = {
 		.name = "ipe_0_gdsc",
 	},
@@ -1712,6 +1718,9 @@ static struct gdsc ipe_0_gdsc = {
 
 static struct gdsc ife_0_gdsc = {
 	.gdscr = 0x9004,
+	.en_rest_wait_val = 0x2,
+	.en_few_wait_val = 0x2,
+	.clk_dis_wait_val = 0xf,
 	.pd = {
 		.name = "ife_0_gdsc",
 	},
@@ -1720,6 +1729,9 @@ static struct gdsc ife_0_gdsc = {
 
 static struct gdsc ife_1_gdsc = {
 	.gdscr = 0xa004,
+	.en_rest_wait_val = 0x2,
+	.en_few_wait_val = 0x2,
+	.clk_dis_wait_val = 0xf,
 	.pd = {
 		.name = "ife_1_gdsc",
 	},
@@ -1728,6 +1740,9 @@ static struct gdsc ife_1_gdsc = {
 
 static struct gdsc ife_2_gdsc = {
 	.gdscr = 0xb004,
+	.en_rest_wait_val = 0x2,
+	.en_few_wait_val = 0x2,
+	.clk_dis_wait_val = 0xf,
 	.pd = {
 		.name = "ife_2_gdsc",
 	},
@@ -1736,6 +1751,9 @@ static struct gdsc ife_2_gdsc = {
 
 static struct gdsc titan_top_gdsc = {
 	.gdscr = 0x14004,
+	.en_rest_wait_val = 0x2,
+	.en_few_wait_val = 0x2,
+	.clk_dis_wait_val = 0xf,
 	.pd = {
 		.name = "titan_top_gdsc",
 	},
diff --git a/drivers/clk/qcom/camcc-sm8250.c b/drivers/clk/qcom/camcc-sm8250.c
index 34d2f17520dc..450ddbebd35f 100644
--- a/drivers/clk/qcom/camcc-sm8250.c
+++ b/drivers/clk/qcom/camcc-sm8250.c
@@ -411,7 +411,7 @@ static struct clk_rcg2 cam_cc_bps_clk_src = {
 		.parent_data = cam_cc_parent_data_0,
 		.num_parents = ARRAY_SIZE(cam_cc_parent_data_0),
 		.flags = CLK_SET_RATE_PARENT,
-		.ops = &clk_rcg2_ops,
+		.ops = &clk_rcg2_shared_ops,
 	},
 };
 
@@ -433,7 +433,7 @@ static struct clk_rcg2 cam_cc_camnoc_axi_clk_src = {
 		.parent_data = cam_cc_parent_data_0,
 		.num_parents = ARRAY_SIZE(cam_cc_parent_data_0),
 		.flags = CLK_SET_RATE_PARENT,
-		.ops = &clk_rcg2_ops,
+		.ops = &clk_rcg2_shared_ops,
 	},
 };
 
@@ -454,7 +454,7 @@ static struct clk_rcg2 cam_cc_cci_0_clk_src = {
 		.parent_data = cam_cc_parent_data_0,
 		.num_parents = ARRAY_SIZE(cam_cc_parent_data_0),
 		.flags = CLK_SET_RATE_PARENT,
-		.ops = &clk_rcg2_ops,
+		.ops = &clk_rcg2_shared_ops,
 	},
 };
 
@@ -469,7 +469,7 @@ static struct clk_rcg2 cam_cc_cci_1_clk_src = {
 		.parent_data = cam_cc_parent_data_0,
 		.num_parents = ARRAY_SIZE(cam_cc_parent_data_0),
 		.flags = CLK_SET_RATE_PARENT,
-		.ops = &clk_rcg2_ops,
+		.ops = &clk_rcg2_shared_ops,
 	},
 };
 
@@ -490,7 +490,7 @@ static struct clk_rcg2 cam_cc_cphy_rx_clk_src = {
 		.parent_data = cam_cc_parent_data_0,
 		.num_parents = ARRAY_SIZE(cam_cc_parent_data_0),
 		.flags = CLK_SET_RATE_PARENT,
-		.ops = &clk_rcg2_ops,
+		.ops = &clk_rcg2_shared_ops,
 	},
 };
 
@@ -511,7 +511,7 @@ static struct clk_rcg2 cam_cc_csi0phytimer_clk_src = {
 		.parent_data = cam_cc_parent_data_0,
 		.num_parents = ARRAY_SIZE(cam_cc_parent_data_0),
 		.flags = CLK_SET_RATE_PARENT,
-		.ops = &clk_rcg2_ops,
+		.ops = &clk_rcg2_shared_ops,
 	},
 };
 
@@ -526,7 +526,7 @@ static struct clk_rcg2 cam_cc_csi1phytimer_clk_src = {
 		.parent_data = cam_cc_parent_data_0,
 		.num_parents = ARRAY_SIZE(cam_cc_parent_data_0),
 		.flags = CLK_SET_RATE_PARENT,
-		.ops = &clk_rcg2_ops,
+		.ops = &clk_rcg2_shared_ops,
 	},
 };
 
@@ -556,7 +556,7 @@ static struct clk_rcg2 cam_cc_csi3phytimer_clk_src = {
 		.parent_data = cam_cc_parent_data_0,
 		.num_parents = ARRAY_SIZE(cam_cc_parent_data_0),
 		.flags = CLK_SET_RATE_PARENT,
-		.ops = &clk_rcg2_ops,
+		.ops = &clk_rcg2_shared_ops,
 	},
 };
 
@@ -571,7 +571,7 @@ static struct clk_rcg2 cam_cc_csi4phytimer_clk_src = {
 		.parent_data = cam_cc_parent_data_0,
 		.num_parents = ARRAY_SIZE(cam_cc_parent_data_0),
 		.flags = CLK_SET_RATE_PARENT,
-		.ops = &clk_rcg2_ops,
+		.ops = &clk_rcg2_shared_ops,
 	},
 };
 
@@ -586,7 +586,7 @@ static struct clk_rcg2 cam_cc_csi5phytimer_clk_src = {
 		.parent_data = cam_cc_parent_data_0,
 		.num_parents = ARRAY_SIZE(cam_cc_parent_data_0),
 		.flags = CLK_SET_RATE_PARENT,
-		.ops = &clk_rcg2_ops,
+		.ops = &clk_rcg2_shared_ops,
 	},
 };
 
@@ -611,7 +611,7 @@ static struct clk_rcg2 cam_cc_fast_ahb_clk_src = {
 		.parent_data = cam_cc_parent_data_0,
 		.num_parents = ARRAY_SIZE(cam_cc_parent_data_0),
 		.flags = CLK_SET_RATE_PARENT,
-		.ops = &clk_rcg2_ops,
+		.ops = &clk_rcg2_shared_ops,
 	},
 };
 
@@ -634,7 +634,7 @@ static struct clk_rcg2 cam_cc_fd_core_clk_src = {
 		.parent_data = cam_cc_parent_data_0,
 		.num_parents = ARRAY_SIZE(cam_cc_parent_data_0),
 		.flags = CLK_SET_RATE_PARENT,
-		.ops = &clk_rcg2_ops,
+		.ops = &clk_rcg2_shared_ops,
 	},
 };
 
@@ -649,7 +649,7 @@ static struct clk_rcg2 cam_cc_icp_clk_src = {
 		.parent_data = cam_cc_parent_data_0,
 		.num_parents = ARRAY_SIZE(cam_cc_parent_data_0),
 		.flags = CLK_SET_RATE_PARENT,
-		.ops = &clk_rcg2_ops,
+		.ops = &clk_rcg2_shared_ops,
 	},
 };
 
@@ -673,7 +673,7 @@ static struct clk_rcg2 cam_cc_ife_0_clk_src = {
 		.parent_data = cam_cc_parent_data_2,
 		.num_parents = ARRAY_SIZE(cam_cc_parent_data_2),
 		.flags = CLK_SET_RATE_PARENT,
-		.ops = &clk_rcg2_ops,
+		.ops = &clk_rcg2_shared_ops,
 	},
 };
 
@@ -710,7 +710,7 @@ static struct clk_rcg2 cam_cc_ife_0_csid_clk_src = {
 		.parent_data = cam_cc_parent_data_0,
 		.num_parents = ARRAY_SIZE(cam_cc_parent_data_0),
 		.flags = CLK_SET_RATE_PARENT,
-		.ops = &clk_rcg2_ops,
+		.ops = &clk_rcg2_shared_ops,
 	},
 };
 
@@ -734,7 +734,7 @@ static struct clk_rcg2 cam_cc_ife_1_clk_src = {
 		.parent_data = cam_cc_parent_data_3,
 		.num_parents = ARRAY_SIZE(cam_cc_parent_data_3),
 		.flags = CLK_SET_RATE_PARENT,
-		.ops = &clk_rcg2_ops,
+		.ops = &clk_rcg2_shared_ops,
 	},
 };
 
@@ -749,7 +749,7 @@ static struct clk_rcg2 cam_cc_ife_1_csid_clk_src = {
 		.parent_data = cam_cc_parent_data_0,
 		.num_parents = ARRAY_SIZE(cam_cc_parent_data_0),
 		.flags = CLK_SET_RATE_PARENT,
-		.ops = &clk_rcg2_ops,
+		.ops = &clk_rcg2_shared_ops,
 	},
 };
 
@@ -771,7 +771,7 @@ static struct clk_rcg2 cam_cc_ife_lite_clk_src = {
 		.parent_data = cam_cc_parent_data_0,
 		.num_parents = ARRAY_SIZE(cam_cc_parent_data_0),
 		.flags = CLK_SET_RATE_PARENT,
-		.ops = &clk_rcg2_ops,
+		.ops = &clk_rcg2_shared_ops,
 	},
 };
 
@@ -786,7 +786,7 @@ static struct clk_rcg2 cam_cc_ife_lite_csid_clk_src = {
 		.parent_data = cam_cc_parent_data_0,
 		.num_parents = ARRAY_SIZE(cam_cc_parent_data_0),
 		.flags = CLK_SET_RATE_PARENT,
-		.ops = &clk_rcg2_ops,
+		.ops = &clk_rcg2_shared_ops,
 	},
 };
 
@@ -810,7 +810,7 @@ static struct clk_rcg2 cam_cc_ipe_0_clk_src = {
 		.parent_data = cam_cc_parent_data_4,
 		.num_parents = ARRAY_SIZE(cam_cc_parent_data_4),
 		.flags = CLK_SET_RATE_PARENT,
-		.ops = &clk_rcg2_ops,
+		.ops = &clk_rcg2_shared_ops,
 	},
 };
 
@@ -825,7 +825,7 @@ static struct clk_rcg2 cam_cc_jpeg_clk_src = {
 		.parent_data = cam_cc_parent_data_0,
 		.num_parents = ARRAY_SIZE(cam_cc_parent_data_0),
 		.flags = CLK_SET_RATE_PARENT,
-		.ops = &clk_rcg2_ops,
+		.ops = &clk_rcg2_shared_ops,
 	},
 };
 
@@ -847,7 +847,7 @@ static struct clk_rcg2 cam_cc_mclk0_clk_src = {
 		.parent_data = cam_cc_parent_data_1,
 		.num_parents = ARRAY_SIZE(cam_cc_parent_data_1),
 		.flags = CLK_SET_RATE_PARENT,
-		.ops = &clk_rcg2_ops,
+		.ops = &clk_rcg2_shared_ops,
 	},
 };
 
@@ -862,7 +862,7 @@ static struct clk_rcg2 cam_cc_mclk1_clk_src = {
 		.parent_data = cam_cc_parent_data_1,
 		.num_parents = ARRAY_SIZE(cam_cc_parent_data_1),
 		.flags = CLK_SET_RATE_PARENT,
-		.ops = &clk_rcg2_ops,
+		.ops = &clk_rcg2_shared_ops,
 	},
 };
 
@@ -877,7 +877,7 @@ static struct clk_rcg2 cam_cc_mclk2_clk_src = {
 		.parent_data = cam_cc_parent_data_1,
 		.num_parents = ARRAY_SIZE(cam_cc_parent_data_1),
 		.flags = CLK_SET_RATE_PARENT,
-		.ops = &clk_rcg2_ops,
+		.ops = &clk_rcg2_shared_ops,
 	},
 };
 
@@ -892,7 +892,7 @@ static struct clk_rcg2 cam_cc_mclk3_clk_src = {
 		.parent_data = cam_cc_parent_data_1,
 		.num_parents = ARRAY_SIZE(cam_cc_parent_data_1),
 		.flags = CLK_SET_RATE_PARENT,
-		.ops = &clk_rcg2_ops,
+		.ops = &clk_rcg2_shared_ops,
 	},
 };
 
@@ -907,7 +907,7 @@ static struct clk_rcg2 cam_cc_mclk4_clk_src = {
 		.parent_data = cam_cc_parent_data_1,
 		.num_parents = ARRAY_SIZE(cam_cc_parent_data_1),
 		.flags = CLK_SET_RATE_PARENT,
-		.ops = &clk_rcg2_ops,
+		.ops = &clk_rcg2_shared_ops,
 	},
 };
 
@@ -922,7 +922,7 @@ static struct clk_rcg2 cam_cc_mclk5_clk_src = {
 		.parent_data = cam_cc_parent_data_1,
 		.num_parents = ARRAY_SIZE(cam_cc_parent_data_1),
 		.flags = CLK_SET_RATE_PARENT,
-		.ops = &clk_rcg2_ops,
+		.ops = &clk_rcg2_shared_ops,
 	},
 };
 
@@ -993,7 +993,7 @@ static struct clk_rcg2 cam_cc_slow_ahb_clk_src = {
 		.parent_data = cam_cc_parent_data_0,
 		.num_parents = ARRAY_SIZE(cam_cc_parent_data_0),
 		.flags = CLK_SET_RATE_PARENT,
-		.ops = &clk_rcg2_ops,
+		.ops = &clk_rcg2_shared_ops,
 	},
 };
 
diff --git a/drivers/clk/qcom/camcc-x1e80100.c b/drivers/clk/qcom/camcc-x1e80100.c
index 85e76c7712ad..b73524ae64b1 100644
--- a/drivers/clk/qcom/camcc-x1e80100.c
+++ b/drivers/clk/qcom/camcc-x1e80100.c
@@ -2212,6 +2212,8 @@ static struct clk_branch cam_cc_sfe_0_fast_ahb_clk = {
 	},
 };
 
+static struct gdsc cam_cc_titan_top_gdsc;
+
 static struct gdsc cam_cc_bps_gdsc = {
 	.gdscr = 0x10004,
 	.en_rest_wait_val = 0x2,
@@ -2221,6 +2223,7 @@ static struct gdsc cam_cc_bps_gdsc = {
 		.name = "cam_cc_bps_gdsc",
 	},
 	.pwrsts = PWRSTS_OFF_ON,
+	.parent = &cam_cc_titan_top_gdsc.pd,
 	.flags = POLL_CFG_GDSCR | RETAIN_FF_ENABLE,
 };
 
@@ -2233,6 +2236,7 @@ static struct gdsc cam_cc_ife_0_gdsc = {
 		.name = "cam_cc_ife_0_gdsc",
 	},
 	.pwrsts = PWRSTS_OFF_ON,
+	.parent = &cam_cc_titan_top_gdsc.pd,
 	.flags = POLL_CFG_GDSCR | RETAIN_FF_ENABLE,
 };
 
@@ -2245,6 +2249,7 @@ static struct gdsc cam_cc_ife_1_gdsc = {
 		.name = "cam_cc_ife_1_gdsc",
 	},
 	.pwrsts = PWRSTS_OFF_ON,
+	.parent = &cam_cc_titan_top_gdsc.pd,
 	.flags = POLL_CFG_GDSCR | RETAIN_FF_ENABLE,
 };
 
@@ -2257,6 +2262,7 @@ static struct gdsc cam_cc_ipe_0_gdsc = {
 		.name = "cam_cc_ipe_0_gdsc",
 	},
 	.pwrsts = PWRSTS_OFF_ON,
+	.parent = &cam_cc_titan_top_gdsc.pd,
 	.flags = POLL_CFG_GDSCR | RETAIN_FF_ENABLE,
 };
 
@@ -2269,6 +2275,7 @@ static struct gdsc cam_cc_sfe_0_gdsc = {
 		.name = "cam_cc_sfe_0_gdsc",
 	},
 	.pwrsts = PWRSTS_OFF_ON,
+	.parent = &cam_cc_titan_top_gdsc.pd,
 	.flags = POLL_CFG_GDSCR | RETAIN_FF_ENABLE,
 };
 
diff --git a/drivers/clk/qcom/clk-alpha-pll.c b/drivers/clk/qcom/clk-alpha-pll.c
index 49687512184b..e76ecc466351 100644
--- a/drivers/clk/qcom/clk-alpha-pll.c
+++ b/drivers/clk/qcom/clk-alpha-pll.c
@@ -432,6 +432,8 @@ void clk_alpha_pll_configure(struct clk_alpha_pll *pll, struct regmap *regmap,
 	mask |= config->pre_div_mask;
 	mask |= config->post_div_mask;
 	mask |= config->vco_mask;
+	mask |= config->alpha_en_mask;
+	mask |= config->alpha_mode_mask;
 
 	regmap_update_bits(regmap, PLL_USER_CTL(pll), mask, val);
 
@@ -668,14 +670,19 @@ clk_alpha_pll_recalc_rate(struct clk_hw *hw, unsigned long parent_rate)
 	struct clk_alpha_pll *pll = to_clk_alpha_pll(hw);
 	u32 alpha_width = pll_alpha_width(pll);
 
-	regmap_read(pll->clkr.regmap, PLL_L_VAL(pll), &l);
+	if (regmap_read(pll->clkr.regmap, PLL_L_VAL(pll), &l))
+		return 0;
+
+	if (regmap_read(pll->clkr.regmap, PLL_USER_CTL(pll), &ctl))
+		return 0;
 
-	regmap_read(pll->clkr.regmap, PLL_USER_CTL(pll), &ctl);
 	if (ctl & PLL_ALPHA_EN) {
-		regmap_read(pll->clkr.regmap, PLL_ALPHA_VAL(pll), &low);
+		if (regmap_read(pll->clkr.regmap, PLL_ALPHA_VAL(pll), &low))
+			return 0;
 		if (alpha_width > 32) {
-			regmap_read(pll->clkr.regmap, PLL_ALPHA_VAL_U(pll),
-				    &high);
+			if (regmap_read(pll->clkr.regmap, PLL_ALPHA_VAL_U(pll),
+					&high))
+				return 0;
 			a = (u64)high << 32 | low;
 		} else {
 			a = low & GENMASK(alpha_width - 1, 0);
@@ -901,8 +908,11 @@ alpha_pll_huayra_recalc_rate(struct clk_hw *hw, unsigned long parent_rate)
 	struct clk_alpha_pll *pll = to_clk_alpha_pll(hw);
 	u32 l, alpha = 0, ctl, alpha_m, alpha_n;
 
-	regmap_read(pll->clkr.regmap, PLL_L_VAL(pll), &l);
-	regmap_read(pll->clkr.regmap, PLL_USER_CTL(pll), &ctl);
+	if (regmap_read(pll->clkr.regmap, PLL_L_VAL(pll), &l))
+		return 0;
+
+	if (regmap_read(pll->clkr.regmap, PLL_USER_CTL(pll), &ctl))
+		return 0;
 
 	if (ctl & PLL_ALPHA_EN) {
 		regmap_read(pll->clkr.regmap, PLL_ALPHA_VAL(pll), &alpha);
@@ -1096,8 +1106,11 @@ clk_trion_pll_recalc_rate(struct clk_hw *hw, unsigned long parent_rate)
 	struct clk_alpha_pll *pll = to_clk_alpha_pll(hw);
 	u32 l, frac, alpha_width = pll_alpha_width(pll);
 
-	regmap_read(pll->clkr.regmap, PLL_L_VAL(pll), &l);
-	regmap_read(pll->clkr.regmap, PLL_ALPHA_VAL(pll), &frac);
+	if (regmap_read(pll->clkr.regmap, PLL_L_VAL(pll), &l))
+		return 0;
+
+	if (regmap_read(pll->clkr.regmap, PLL_ALPHA_VAL(pll), &frac))
+		return 0;
 
 	return alpha_pll_calc_rate(parent_rate, l, frac, alpha_width);
 }
@@ -1155,7 +1168,8 @@ clk_alpha_pll_postdiv_recalc_rate(struct clk_hw *hw, unsigned long parent_rate)
 	struct clk_alpha_pll_postdiv *pll = to_clk_alpha_pll_postdiv(hw);
 	u32 ctl;
 
-	regmap_read(pll->clkr.regmap, PLL_USER_CTL(pll), &ctl);
+	if (regmap_read(pll->clkr.regmap, PLL_USER_CTL(pll), &ctl))
+		return 0;
 
 	ctl >>= PLL_POST_DIV_SHIFT;
 	ctl &= PLL_POST_DIV_MASK(pll);
@@ -1371,8 +1385,11 @@ static unsigned long alpha_pll_fabia_recalc_rate(struct clk_hw *hw,
 	struct clk_alpha_pll *pll = to_clk_alpha_pll(hw);
 	u32 l, frac, alpha_width = pll_alpha_width(pll);
 
-	regmap_read(pll->clkr.regmap, PLL_L_VAL(pll), &l);
-	regmap_read(pll->clkr.regmap, PLL_FRAC(pll), &frac);
+	if (regmap_read(pll->clkr.regmap, PLL_L_VAL(pll), &l))
+		return 0;
+
+	if (regmap_read(pll->clkr.regmap, PLL_FRAC(pll), &frac))
+		return 0;
 
 	return alpha_pll_calc_rate(parent_rate, l, frac, alpha_width);
 }
@@ -1522,7 +1539,8 @@ clk_trion_pll_postdiv_recalc_rate(struct clk_hw *hw, unsigned long parent_rate)
 	struct regmap *regmap = pll->clkr.regmap;
 	u32 i, div = 1, val;
 
-	regmap_read(regmap, PLL_USER_CTL(pll), &val);
+	if (regmap_read(regmap, PLL_USER_CTL(pll), &val))
+		return 0;
 
 	val >>= pll->post_div_shift;
 	val &= PLL_POST_DIV_MASK(pll);
@@ -2449,9 +2467,12 @@ static unsigned long alpha_pll_lucid_evo_recalc_rate(struct clk_hw *hw,
 	struct regmap *regmap = pll->clkr.regmap;
 	u32 l, frac;
 
-	regmap_read(regmap, PLL_L_VAL(pll), &l);
+	if (regmap_read(regmap, PLL_L_VAL(pll), &l))
+		return 0;
 	l &= LUCID_EVO_PLL_L_VAL_MASK;
-	regmap_read(regmap, PLL_ALPHA_VAL(pll), &frac);
+
+	if (regmap_read(regmap, PLL_ALPHA_VAL(pll), &frac))
+		return 0;
 
 	return alpha_pll_calc_rate(parent_rate, l, frac, pll_alpha_width(pll));
 }
@@ -2526,7 +2547,8 @@ static unsigned long clk_rivian_evo_pll_recalc_rate(struct clk_hw *hw,
 	struct clk_alpha_pll *pll = to_clk_alpha_pll(hw);
 	u32 l;
 
-	regmap_read(pll->clkr.regmap, PLL_L_VAL(pll), &l);
+	if (regmap_read(pll->clkr.regmap, PLL_L_VAL(pll), &l))
+		return 0;
 
 	return parent_rate * l;
 }
diff --git a/drivers/clk/qcom/clk-branch.c b/drivers/clk/qcom/clk-branch.c
index 229480c5b075..0f10090d4ae6 100644
--- a/drivers/clk/qcom/clk-branch.c
+++ b/drivers/clk/qcom/clk-branch.c
@@ -28,7 +28,7 @@ static bool clk_branch_in_hwcg_mode(const struct clk_branch *br)
 
 static bool clk_branch_check_halt(const struct clk_branch *br, bool enabling)
 {
-	bool invert = (br->halt_check == BRANCH_HALT_ENABLE);
+	bool invert = (br->halt_check & BRANCH_HALT_ENABLE);
 	u32 val;
 
 	regmap_read(br->clkr.regmap, br->halt_reg, &val);
@@ -44,7 +44,7 @@ static bool clk_branch2_check_halt(const struct clk_branch *br, bool enabling)
 {
 	u32 val;
 	u32 mask;
-	bool invert = (br->halt_check == BRANCH_HALT_ENABLE);
+	bool invert = (br->halt_check & BRANCH_HALT_ENABLE);
 
 	mask = CBCR_NOC_FSM_STATUS;
 	mask |= CBCR_CLK_OFF;
diff --git a/drivers/clk/qcom/clk-rpmh.c b/drivers/clk/qcom/clk-rpmh.c
index eefc322ce367..e6c33010cfbf 100644
--- a/drivers/clk/qcom/clk-rpmh.c
+++ b/drivers/clk/qcom/clk-rpmh.c
@@ -329,7 +329,7 @@ static unsigned long clk_rpmh_bcm_recalc_rate(struct clk_hw *hw,
 {
 	struct clk_rpmh *c = to_clk_rpmh(hw);
 
-	return c->aggr_state * c->unit;
+	return (unsigned long)c->aggr_state * c->unit;
 }
 
 static const struct clk_ops clk_rpmh_bcm_ops = {
diff --git a/drivers/clk/qcom/dispcc-sm6350.c b/drivers/clk/qcom/dispcc-sm6350.c
index 50facb36701a..d52fd4b49a02 100644
--- a/drivers/clk/qcom/dispcc-sm6350.c
+++ b/drivers/clk/qcom/dispcc-sm6350.c
@@ -187,13 +187,12 @@ static struct clk_rcg2 disp_cc_mdss_dp_aux_clk_src = {
 	.cmd_rcgr = 0x1144,
 	.mnd_width = 0,
 	.hid_width = 5,
+	.parent_map = disp_cc_parent_map_6,
 	.freq_tbl = ftbl_disp_cc_mdss_dp_aux_clk_src,
 	.clkr.hw.init = &(struct clk_init_data){
 		.name = "disp_cc_mdss_dp_aux_clk_src",
-		.parent_data = &(const struct clk_parent_data){
-			.fw_name = "bi_tcxo",
-		},
-		.num_parents = 1,
+		.parent_data = disp_cc_parent_data_6,
+		.num_parents = ARRAY_SIZE(disp_cc_parent_data_6),
 		.ops = &clk_rcg2_ops,
 	},
 };
@@ -681,6 +680,9 @@ static struct clk_branch disp_cc_xo_clk = {
 
 static struct gdsc mdss_gdsc = {
 	.gdscr = 0x1004,
+	.en_rest_wait_val = 0x2,
+	.en_few_wait_val = 0x2,
+	.clk_dis_wait_val = 0xf,
 	.pd = {
 		.name = "mdss_gdsc",
 	},
diff --git a/drivers/clk/qcom/gcc-ipq5018.c b/drivers/clk/qcom/gcc-ipq5018.c
index 70f5dcb96700..24eb4c40da63 100644
--- a/drivers/clk/qcom/gcc-ipq5018.c
+++ b/drivers/clk/qcom/gcc-ipq5018.c
@@ -1371,7 +1371,7 @@ static struct clk_branch gcc_xo_clk = {
 				&gcc_xo_clk_src.clkr.hw,
 			},
 			.num_parents = 1,
-			.flags = CLK_SET_RATE_PARENT,
+			.flags = CLK_SET_RATE_PARENT | CLK_IS_CRITICAL,
 			.ops = &clk_branch2_ops,
 		},
 	},
diff --git a/drivers/clk/qcom/gcc-ipq8074.c b/drivers/clk/qcom/gcc-ipq8074.c
index 7258ba5c0900..1329ea28d703 100644
--- a/drivers/clk/qcom/gcc-ipq8074.c
+++ b/drivers/clk/qcom/gcc-ipq8074.c
@@ -1895,10 +1895,10 @@ static const struct freq_conf ftbl_nss_port6_tx_clk_src_125[] = {
 static const struct freq_multi_tbl ftbl_nss_port6_tx_clk_src[] = {
 	FMS(19200000, P_XO, 1, 0, 0),
 	FM(25000000, ftbl_nss_port6_tx_clk_src_25),
-	FMS(78125000, P_UNIPHY1_RX, 4, 0, 0),
+	FMS(78125000, P_UNIPHY2_TX, 4, 0, 0),
 	FM(125000000, ftbl_nss_port6_tx_clk_src_125),
-	FMS(156250000, P_UNIPHY1_RX, 2, 0, 0),
-	FMS(312500000, P_UNIPHY1_RX, 1, 0, 0),
+	FMS(156250000, P_UNIPHY2_TX, 2, 0, 0),
+	FMS(312500000, P_UNIPHY2_TX, 1, 0, 0),
 	{ }
 };
 
diff --git a/drivers/clk/qcom/gcc-mdm9607.c b/drivers/clk/qcom/gcc-mdm9607.c
index 6e6068b168e6..07f1b78d737a 100644
--- a/drivers/clk/qcom/gcc-mdm9607.c
+++ b/drivers/clk/qcom/gcc-mdm9607.c
@@ -535,7 +535,7 @@ static struct clk_rcg2 blsp1_uart5_apps_clk_src = {
 };
 
 static struct clk_rcg2 blsp1_uart6_apps_clk_src = {
-	.cmd_rcgr = 0x6044,
+	.cmd_rcgr = 0x7044,
 	.mnd_width = 16,
 	.hid_width = 5,
 	.parent_map = gcc_xo_gpll0_map,
diff --git a/drivers/clk/qcom/gcc-msm8939.c b/drivers/clk/qcom/gcc-msm8939.c
index 7431c9a65044..45193b3d714b 100644
--- a/drivers/clk/qcom/gcc-msm8939.c
+++ b/drivers/clk/qcom/gcc-msm8939.c
@@ -432,7 +432,7 @@ static const struct parent_map gcc_xo_gpll0_gpll1a_gpll6_sleep_map[] = {
 	{ P_XO, 0 },
 	{ P_GPLL0, 1 },
 	{ P_GPLL1_AUX, 2 },
-	{ P_GPLL6, 2 },
+	{ P_GPLL6, 3 },
 	{ P_SLEEP_CLK, 6 },
 };
 
@@ -1113,7 +1113,7 @@ static struct clk_rcg2 jpeg0_clk_src = {
 };
 
 static const struct freq_tbl ftbl_gcc_camss_mclk0_1_clk[] = {
-	F(24000000, P_GPLL0, 1, 1, 45),
+	F(24000000, P_GPLL6, 1, 1, 45),
 	F(66670000, P_GPLL0, 12, 0, 0),
 	{ }
 };
diff --git a/drivers/clk/qcom/gcc-msm8953.c b/drivers/clk/qcom/gcc-msm8953.c
index 855a61966f3e..8f29ecc74c50 100644
--- a/drivers/clk/qcom/gcc-msm8953.c
+++ b/drivers/clk/qcom/gcc-msm8953.c
@@ -3770,7 +3770,7 @@ static struct clk_branch gcc_venus0_axi_clk = {
 
 static struct clk_branch gcc_venus0_core0_vcodec0_clk = {
 	.halt_reg = 0x4c02c,
-	.halt_check = BRANCH_HALT,
+	.halt_check = BRANCH_HALT_SKIP,
 	.clkr = {
 		.enable_reg = 0x4c02c,
 		.enable_mask = BIT(0),
diff --git a/drivers/clk/qcom/gcc-sdm845.c b/drivers/clk/qcom/gcc-sdm845.c
index dc3aa7014c3e..c6692808a822 100644
--- a/drivers/clk/qcom/gcc-sdm845.c
+++ b/drivers/clk/qcom/gcc-sdm845.c
@@ -454,7 +454,7 @@ static struct clk_init_data gcc_qupv3_wrap0_s0_clk_src_init = {
 	.name = "gcc_qupv3_wrap0_s0_clk_src",
 	.parent_data = gcc_parent_data_0,
 	.num_parents = ARRAY_SIZE(gcc_parent_data_0),
-	.ops = &clk_rcg2_shared_ops,
+	.ops = &clk_rcg2_ops,
 };
 
 static struct clk_rcg2 gcc_qupv3_wrap0_s0_clk_src = {
@@ -470,7 +470,7 @@ static struct clk_init_data gcc_qupv3_wrap0_s1_clk_src_init = {
 	.name = "gcc_qupv3_wrap0_s1_clk_src",
 	.parent_data = gcc_parent_data_0,
 	.num_parents = ARRAY_SIZE(gcc_parent_data_0),
-	.ops = &clk_rcg2_shared_ops,
+	.ops = &clk_rcg2_ops,
 };
 
 static struct clk_rcg2 gcc_qupv3_wrap0_s1_clk_src = {
@@ -486,7 +486,7 @@ static struct clk_init_data gcc_qupv3_wrap0_s2_clk_src_init = {
 	.name = "gcc_qupv3_wrap0_s2_clk_src",
 	.parent_data = gcc_parent_data_0,
 	.num_parents = ARRAY_SIZE(gcc_parent_data_0),
-	.ops = &clk_rcg2_shared_ops,
+	.ops = &clk_rcg2_ops,
 };
 
 static struct clk_rcg2 gcc_qupv3_wrap0_s2_clk_src = {
@@ -502,7 +502,7 @@ static struct clk_init_data gcc_qupv3_wrap0_s3_clk_src_init = {
 	.name = "gcc_qupv3_wrap0_s3_clk_src",
 	.parent_data = gcc_parent_data_0,
 	.num_parents = ARRAY_SIZE(gcc_parent_data_0),
-	.ops = &clk_rcg2_shared_ops,
+	.ops = &clk_rcg2_ops,
 };
 
 static struct clk_rcg2 gcc_qupv3_wrap0_s3_clk_src = {
@@ -518,7 +518,7 @@ static struct clk_init_data gcc_qupv3_wrap0_s4_clk_src_init = {
 	.name = "gcc_qupv3_wrap0_s4_clk_src",
 	.parent_data = gcc_parent_data_0,
 	.num_parents = ARRAY_SIZE(gcc_parent_data_0),
-	.ops = &clk_rcg2_shared_ops,
+	.ops = &clk_rcg2_ops,
 };
 
 static struct clk_rcg2 gcc_qupv3_wrap0_s4_clk_src = {
@@ -534,7 +534,7 @@ static struct clk_init_data gcc_qupv3_wrap0_s5_clk_src_init = {
 	.name = "gcc_qupv3_wrap0_s5_clk_src",
 	.parent_data = gcc_parent_data_0,
 	.num_parents = ARRAY_SIZE(gcc_parent_data_0),
-	.ops = &clk_rcg2_shared_ops,
+	.ops = &clk_rcg2_ops,
 };
 
 static struct clk_rcg2 gcc_qupv3_wrap0_s5_clk_src = {
@@ -550,7 +550,7 @@ static struct clk_init_data gcc_qupv3_wrap0_s6_clk_src_init = {
 	.name = "gcc_qupv3_wrap0_s6_clk_src",
 	.parent_data = gcc_parent_data_0,
 	.num_parents = ARRAY_SIZE(gcc_parent_data_0),
-	.ops = &clk_rcg2_shared_ops,
+	.ops = &clk_rcg2_ops,
 };
 
 static struct clk_rcg2 gcc_qupv3_wrap0_s6_clk_src = {
@@ -566,7 +566,7 @@ static struct clk_init_data gcc_qupv3_wrap0_s7_clk_src_init = {
 	.name = "gcc_qupv3_wrap0_s7_clk_src",
 	.parent_data = gcc_parent_data_0,
 	.num_parents = ARRAY_SIZE(gcc_parent_data_0),
-	.ops = &clk_rcg2_shared_ops,
+	.ops = &clk_rcg2_ops,
 };
 
 static struct clk_rcg2 gcc_qupv3_wrap0_s7_clk_src = {
@@ -582,7 +582,7 @@ static struct clk_init_data gcc_qupv3_wrap1_s0_clk_src_init = {
 	.name = "gcc_qupv3_wrap1_s0_clk_src",
 	.parent_data = gcc_parent_data_0,
 	.num_parents = ARRAY_SIZE(gcc_parent_data_0),
-	.ops = &clk_rcg2_shared_ops,
+	.ops = &clk_rcg2_ops,
 };
 
 static struct clk_rcg2 gcc_qupv3_wrap1_s0_clk_src = {
@@ -598,7 +598,7 @@ static struct clk_init_data gcc_qupv3_wrap1_s1_clk_src_init = {
 	.name = "gcc_qupv3_wrap1_s1_clk_src",
 	.parent_data = gcc_parent_data_0,
 	.num_parents = ARRAY_SIZE(gcc_parent_data_0),
-	.ops = &clk_rcg2_shared_ops,
+	.ops = &clk_rcg2_ops,
 };
 
 static struct clk_rcg2 gcc_qupv3_wrap1_s1_clk_src = {
@@ -614,7 +614,7 @@ static struct clk_init_data gcc_qupv3_wrap1_s2_clk_src_init = {
 	.name = "gcc_qupv3_wrap1_s2_clk_src",
 	.parent_data = gcc_parent_data_0,
 	.num_parents = ARRAY_SIZE(gcc_parent_data_0),
-	.ops = &clk_rcg2_shared_ops,
+	.ops = &clk_rcg2_ops,
 };
 
 static struct clk_rcg2 gcc_qupv3_wrap1_s2_clk_src = {
@@ -630,7 +630,7 @@ static struct clk_init_data gcc_qupv3_wrap1_s3_clk_src_init = {
 	.name = "gcc_qupv3_wrap1_s3_clk_src",
 	.parent_data = gcc_parent_data_0,
 	.num_parents = ARRAY_SIZE(gcc_parent_data_0),
-	.ops = &clk_rcg2_shared_ops,
+	.ops = &clk_rcg2_ops,
 };
 
 static struct clk_rcg2 gcc_qupv3_wrap1_s3_clk_src = {
@@ -646,7 +646,7 @@ static struct clk_init_data gcc_qupv3_wrap1_s4_clk_src_init = {
 	.name = "gcc_qupv3_wrap1_s4_clk_src",
 	.parent_data = gcc_parent_data_0,
 	.num_parents = ARRAY_SIZE(gcc_parent_data_0),
-	.ops = &clk_rcg2_shared_ops,
+	.ops = &clk_rcg2_ops,
 };
 
 static struct clk_rcg2 gcc_qupv3_wrap1_s4_clk_src = {
@@ -662,7 +662,7 @@ static struct clk_init_data gcc_qupv3_wrap1_s5_clk_src_init = {
 	.name = "gcc_qupv3_wrap1_s5_clk_src",
 	.parent_data = gcc_parent_data_0,
 	.num_parents = ARRAY_SIZE(gcc_parent_data_0),
-	.ops = &clk_rcg2_shared_ops,
+	.ops = &clk_rcg2_ops,
 };
 
 static struct clk_rcg2 gcc_qupv3_wrap1_s5_clk_src = {
@@ -678,7 +678,7 @@ static struct clk_init_data gcc_qupv3_wrap1_s6_clk_src_init = {
 	.name = "gcc_qupv3_wrap1_s6_clk_src",
 	.parent_data = gcc_parent_data_0,
 	.num_parents = ARRAY_SIZE(gcc_parent_data_0),
-	.ops = &clk_rcg2_shared_ops,
+	.ops = &clk_rcg2_ops,
 };
 
 static struct clk_rcg2 gcc_qupv3_wrap1_s6_clk_src = {
@@ -694,7 +694,7 @@ static struct clk_init_data gcc_qupv3_wrap1_s7_clk_src_init = {
 	.name = "gcc_qupv3_wrap1_s7_clk_src",
 	.parent_data = gcc_parent_data_0,
 	.num_parents = ARRAY_SIZE(gcc_parent_data_0),
-	.ops = &clk_rcg2_shared_ops,
+	.ops = &clk_rcg2_ops,
 };
 
 static struct clk_rcg2 gcc_qupv3_wrap1_s7_clk_src = {
diff --git a/drivers/clk/qcom/gcc-sm6350.c b/drivers/clk/qcom/gcc-sm6350.c
index a811fad2aa27..a4d6dff9d0f7 100644
--- a/drivers/clk/qcom/gcc-sm6350.c
+++ b/drivers/clk/qcom/gcc-sm6350.c
@@ -182,6 +182,14 @@ static const struct clk_parent_data gcc_parent_data_2_ao[] = {
 	{ .hw = &gpll0_out_odd.clkr.hw },
 };
 
+static const struct parent_map gcc_parent_map_3[] = {
+	{ P_BI_TCXO, 0 },
+};
+
+static const struct clk_parent_data gcc_parent_data_3[] = {
+	{ .fw_name = "bi_tcxo" },
+};
+
 static const struct parent_map gcc_parent_map_4[] = {
 	{ P_BI_TCXO, 0 },
 	{ P_GPLL0_OUT_MAIN, 1 },
@@ -701,13 +709,12 @@ static struct clk_rcg2 gcc_ufs_phy_phy_aux_clk_src = {
 	.cmd_rcgr = 0x3a0b0,
 	.mnd_width = 0,
 	.hid_width = 5,
+	.parent_map = gcc_parent_map_3,
 	.freq_tbl = ftbl_gcc_ufs_phy_phy_aux_clk_src,
 	.clkr.hw.init = &(struct clk_init_data){
 		.name = "gcc_ufs_phy_phy_aux_clk_src",
-		.parent_data = &(const struct clk_parent_data){
-			.fw_name = "bi_tcxo",
-		},
-		.num_parents = 1,
+		.parent_data = gcc_parent_data_3,
+		.num_parents = ARRAY_SIZE(gcc_parent_data_3),
 		.ops = &clk_rcg2_ops,
 	},
 };
@@ -764,13 +771,12 @@ static struct clk_rcg2 gcc_usb30_prim_mock_utmi_clk_src = {
 	.cmd_rcgr = 0x1a034,
 	.mnd_width = 0,
 	.hid_width = 5,
+	.parent_map = gcc_parent_map_3,
 	.freq_tbl = ftbl_gcc_usb30_prim_mock_utmi_clk_src,
 	.clkr.hw.init = &(struct clk_init_data){
 		.name = "gcc_usb30_prim_mock_utmi_clk_src",
-		.parent_data = &(const struct clk_parent_data){
-			.fw_name = "bi_tcxo",
-		},
-		.num_parents = 1,
+		.parent_data = gcc_parent_data_3,
+		.num_parents = ARRAY_SIZE(gcc_parent_data_3),
 		.ops = &clk_rcg2_ops,
 	},
 };
@@ -2314,6 +2320,9 @@ static struct clk_branch gcc_video_xo_clk = {
 
 static struct gdsc usb30_prim_gdsc = {
 	.gdscr = 0x1a004,
+	.en_rest_wait_val = 0x2,
+	.en_few_wait_val = 0x2,
+	.clk_dis_wait_val = 0xf,
 	.pd = {
 		.name = "usb30_prim_gdsc",
 	},
@@ -2322,6 +2331,9 @@ static struct gdsc usb30_prim_gdsc = {
 
 static struct gdsc ufs_phy_gdsc = {
 	.gdscr = 0x3a004,
+	.en_rest_wait_val = 0x2,
+	.en_few_wait_val = 0x2,
+	.clk_dis_wait_val = 0xf,
 	.pd = {
 		.name = "ufs_phy_gdsc",
 	},
diff --git a/drivers/clk/qcom/gcc-sm8550.c b/drivers/clk/qcom/gcc-sm8550.c
index 5abaeddd6afc..862a9bf73bcb 100644
--- a/drivers/clk/qcom/gcc-sm8550.c
+++ b/drivers/clk/qcom/gcc-sm8550.c
@@ -3003,7 +3003,7 @@ static struct gdsc pcie_0_gdsc = {
 	.pd = {
 		.name = "pcie_0_gdsc",
 	},
-	.pwrsts = PWRSTS_OFF_ON,
+	.pwrsts = PWRSTS_RET_ON,
 	.flags = VOTABLE | POLL_CFG_GDSCR | RETAIN_FF_ENABLE,
 };
 
@@ -3014,7 +3014,7 @@ static struct gdsc pcie_0_phy_gdsc = {
 	.pd = {
 		.name = "pcie_0_phy_gdsc",
 	},
-	.pwrsts = PWRSTS_OFF_ON,
+	.pwrsts = PWRSTS_RET_ON,
 	.flags = VOTABLE | POLL_CFG_GDSCR | RETAIN_FF_ENABLE,
 };
 
@@ -3025,7 +3025,7 @@ static struct gdsc pcie_1_gdsc = {
 	.pd = {
 		.name = "pcie_1_gdsc",
 	},
-	.pwrsts = PWRSTS_OFF_ON,
+	.pwrsts = PWRSTS_RET_ON,
 	.flags = VOTABLE | POLL_CFG_GDSCR | RETAIN_FF_ENABLE,
 };
 
@@ -3036,7 +3036,7 @@ static struct gdsc pcie_1_phy_gdsc = {
 	.pd = {
 		.name = "pcie_1_phy_gdsc",
 	},
-	.pwrsts = PWRSTS_OFF_ON,
+	.pwrsts = PWRSTS_RET_ON,
 	.flags = VOTABLE | POLL_CFG_GDSCR | RETAIN_FF_ENABLE,
 };
 
diff --git a/drivers/clk/qcom/gcc-sm8650.c b/drivers/clk/qcom/gcc-sm8650.c
index fd9d6544bdd5..fa1672c4e7d8 100644
--- a/drivers/clk/qcom/gcc-sm8650.c
+++ b/drivers/clk/qcom/gcc-sm8650.c
@@ -3437,7 +3437,7 @@ static struct gdsc pcie_0_gdsc = {
 	.pd = {
 		.name = "pcie_0_gdsc",
 	},
-	.pwrsts = PWRSTS_OFF_ON,
+	.pwrsts = PWRSTS_RET_ON,
 	.flags = POLL_CFG_GDSCR | RETAIN_FF_ENABLE | VOTABLE,
 };
 
@@ -3448,7 +3448,7 @@ static struct gdsc pcie_0_phy_gdsc = {
 	.pd = {
 		.name = "pcie_0_phy_gdsc",
 	},
-	.pwrsts = PWRSTS_OFF_ON,
+	.pwrsts = PWRSTS_RET_ON,
 	.flags = POLL_CFG_GDSCR | RETAIN_FF_ENABLE | VOTABLE,
 };
 
@@ -3459,7 +3459,7 @@ static struct gdsc pcie_1_gdsc = {
 	.pd = {
 		.name = "pcie_1_gdsc",
 	},
-	.pwrsts = PWRSTS_OFF_ON,
+	.pwrsts = PWRSTS_RET_ON,
 	.flags = POLL_CFG_GDSCR | RETAIN_FF_ENABLE | VOTABLE,
 };
 
@@ -3470,7 +3470,7 @@ static struct gdsc pcie_1_phy_gdsc = {
 	.pd = {
 		.name = "pcie_1_phy_gdsc",
 	},
-	.pwrsts = PWRSTS_OFF_ON,
+	.pwrsts = PWRSTS_RET_ON,
 	.flags = POLL_CFG_GDSCR | RETAIN_FF_ENABLE | VOTABLE,
 };
 
@@ -3497,7 +3497,7 @@ static struct gdsc usb30_prim_gdsc = {
 	.pd = {
 		.name = "usb30_prim_gdsc",
 	},
-	.pwrsts = PWRSTS_OFF_ON,
+	.pwrsts = PWRSTS_RET_ON,
 	.flags = POLL_CFG_GDSCR | RETAIN_FF_ENABLE,
 };
 
@@ -3506,7 +3506,7 @@ static struct gdsc usb3_phy_gdsc = {
 	.pd = {
 		.name = "usb3_phy_gdsc",
 	},
-	.pwrsts = PWRSTS_OFF_ON,
+	.pwrsts = PWRSTS_RET_ON,
 	.flags = POLL_CFG_GDSCR | RETAIN_FF_ENABLE,
 };
 
diff --git a/drivers/clk/qcom/gcc-x1e80100.c b/drivers/clk/qcom/gcc-x1e80100.c
index 8ea25aa25dff..3e44757e25d3 100644
--- a/drivers/clk/qcom/gcc-x1e80100.c
+++ b/drivers/clk/qcom/gcc-x1e80100.c
@@ -2564,19 +2564,6 @@ static struct clk_branch gcc_disp_hf_axi_clk = {
 	},
 };
 
-static struct clk_branch gcc_disp_xo_clk = {
-	.halt_reg = 0x27018,
-	.halt_check = BRANCH_HALT,
-	.clkr = {
-		.enable_reg = 0x27018,
-		.enable_mask = BIT(0),
-		.hw.init = &(const struct clk_init_data) {
-			.name = "gcc_disp_xo_clk",
-			.ops = &clk_branch2_ops,
-		},
-	},
-};
-
 static struct clk_branch gcc_gp1_clk = {
 	.halt_reg = 0x64000,
 	.halt_check = BRANCH_HALT,
@@ -2631,21 +2618,6 @@ static struct clk_branch gcc_gp3_clk = {
 	},
 };
 
-static struct clk_branch gcc_gpu_cfg_ahb_clk = {
-	.halt_reg = 0x71004,
-	.halt_check = BRANCH_HALT_VOTED,
-	.hwcg_reg = 0x71004,
-	.hwcg_bit = 1,
-	.clkr = {
-		.enable_reg = 0x71004,
-		.enable_mask = BIT(0),
-		.hw.init = &(const struct clk_init_data) {
-			.name = "gcc_gpu_cfg_ahb_clk",
-			.ops = &clk_branch2_ops,
-		},
-	},
-};
-
 static struct clk_branch gcc_gpu_gpll0_cph_clk_src = {
 	.halt_check = BRANCH_HALT_DELAY,
 	.clkr = {
@@ -6083,7 +6055,7 @@ static struct gdsc gcc_usb20_prim_gdsc = {
 	.pd = {
 		.name = "gcc_usb20_prim_gdsc",
 	},
-	.pwrsts = PWRSTS_OFF_ON,
+	.pwrsts = PWRSTS_RET_ON,
 	.flags = POLL_CFG_GDSCR | RETAIN_FF_ENABLE,
 };
 
@@ -6268,7 +6240,6 @@ static struct clk_regmap *gcc_x1e80100_clocks[] = {
 	[GCC_CNOC_PCIE_TUNNEL_CLK] = &gcc_cnoc_pcie_tunnel_clk.clkr,
 	[GCC_DDRSS_GPU_AXI_CLK] = &gcc_ddrss_gpu_axi_clk.clkr,
 	[GCC_DISP_HF_AXI_CLK] = &gcc_disp_hf_axi_clk.clkr,
-	[GCC_DISP_XO_CLK] = &gcc_disp_xo_clk.clkr,
 	[GCC_GP1_CLK] = &gcc_gp1_clk.clkr,
 	[GCC_GP1_CLK_SRC] = &gcc_gp1_clk_src.clkr,
 	[GCC_GP2_CLK] = &gcc_gp2_clk.clkr,
@@ -6281,7 +6252,6 @@ static struct clk_regmap *gcc_x1e80100_clocks[] = {
 	[GCC_GPLL7] = &gcc_gpll7.clkr,
 	[GCC_GPLL8] = &gcc_gpll8.clkr,
 	[GCC_GPLL9] = &gcc_gpll9.clkr,
-	[GCC_GPU_CFG_AHB_CLK] = &gcc_gpu_cfg_ahb_clk.clkr,
 	[GCC_GPU_GPLL0_CPH_CLK_SRC] = &gcc_gpu_gpll0_cph_clk_src.clkr,
 	[GCC_GPU_GPLL0_DIV_CPH_CLK_SRC] = &gcc_gpu_gpll0_div_cph_clk_src.clkr,
 	[GCC_GPU_MEMNOC_GFX_CLK] = &gcc_gpu_memnoc_gfx_clk.clkr,
@@ -6783,6 +6753,10 @@ static int gcc_x1e80100_probe(struct platform_device *pdev)
 	/* Clear GDSC_SLEEP_ENA_VOTE to stop votes being auto-removed in sleep. */
 	regmap_write(regmap, 0x52224, 0x0);
 
+	/* FORCE_MEM_CORE_ON for ufs phy ice core and gcc ufs phy axi clocks  */
+	qcom_branch_set_force_mem_core(regmap, gcc_ufs_phy_ice_core_clk, true);
+	qcom_branch_set_force_mem_core(regmap, gcc_ufs_phy_axi_clk, true);
+
 	return qcom_cc_really_probe(&pdev->dev, &gcc_x1e80100_desc, regmap);
 }
 
diff --git a/drivers/clk/qcom/gdsc.c b/drivers/clk/qcom/gdsc.c
index fa5fe4c2a2ee..208fc430ec98 100644
--- a/drivers/clk/qcom/gdsc.c
+++ b/drivers/clk/qcom/gdsc.c
@@ -292,6 +292,9 @@ static int gdsc_enable(struct generic_pm_domain *domain)
 	 */
 	udelay(1);
 
+	if (sc->flags & RETAIN_FF_ENABLE)
+		gdsc_retain_ff_on(sc);
+
 	/* Turn on HW trigger mode if supported */
 	if (sc->flags & HW_CTRL) {
 		ret = gdsc_hwctrl(sc, true);
@@ -308,9 +311,6 @@ static int gdsc_enable(struct generic_pm_domain *domain)
 		udelay(1);
 	}
 
-	if (sc->flags & RETAIN_FF_ENABLE)
-		gdsc_retain_ff_on(sc);
-
 	return 0;
 }
 
@@ -457,13 +457,6 @@ static int gdsc_init(struct gdsc *sc)
 				goto err_disable_supply;
 		}
 
-		/* Turn on HW trigger mode if supported */
-		if (sc->flags & HW_CTRL) {
-			ret = gdsc_hwctrl(sc, true);
-			if (ret < 0)
-				goto err_disable_supply;
-		}
-
 		/*
 		 * Make sure the retain bit is set if the GDSC is already on,
 		 * otherwise we end up turning off the GDSC and destroying all
@@ -471,6 +464,14 @@ static int gdsc_init(struct gdsc *sc)
 		 */
 		if (sc->flags & RETAIN_FF_ENABLE)
 			gdsc_retain_ff_on(sc);
+
+		/* Turn on HW trigger mode if supported */
+		if (sc->flags & HW_CTRL) {
+			ret = gdsc_hwctrl(sc, true);
+			if (ret < 0)
+				goto err_disable_supply;
+		}
+
 	} else if (sc->flags & ALWAYS_ON) {
 		/* If ALWAYS_ON GDSCs are not ON, turn them ON */
 		gdsc_enable(&sc->pd);
@@ -506,6 +507,23 @@ err_disable_supply:
 	return ret;
 }
 
+static void gdsc_pm_subdomain_remove(struct gdsc_desc *desc, size_t num)
+{
+	struct device *dev = desc->dev;
+	struct gdsc **scs = desc->scs;
+	int i;
+
+	/* Remove subdomains */
+	for (i = num - 1; i >= 0; i--) {
+		if (!scs[i])
+			continue;
+		if (scs[i]->parent)
+			pm_genpd_remove_subdomain(scs[i]->parent, &scs[i]->pd);
+		else if (!IS_ERR_OR_NULL(dev->pm_domain))
+			pm_genpd_remove_subdomain(pd_to_genpd(dev->pm_domain), &scs[i]->pd);
+	}
+}
+
 int gdsc_register(struct gdsc_desc *desc,
 		  struct reset_controller_dev *rcdev, struct regmap *regmap)
 {
@@ -555,30 +573,27 @@ int gdsc_register(struct gdsc_desc *desc,
 		if (!scs[i])
 			continue;
 		if (scs[i]->parent)
-			pm_genpd_add_subdomain(scs[i]->parent, &scs[i]->pd);
+			ret = pm_genpd_add_subdomain(scs[i]->parent, &scs[i]->pd);
 		else if (!IS_ERR_OR_NULL(dev->pm_domain))
-			pm_genpd_add_subdomain(pd_to_genpd(dev->pm_domain), &scs[i]->pd);
+			ret = pm_genpd_add_subdomain(pd_to_genpd(dev->pm_domain), &scs[i]->pd);
+		if (ret)
+			goto err_pm_subdomain_remove;
 	}
 
 	return of_genpd_add_provider_onecell(dev->of_node, data);
+
+err_pm_subdomain_remove:
+	gdsc_pm_subdomain_remove(desc, i);
+
+	return ret;
 }
 
 void gdsc_unregister(struct gdsc_desc *desc)
 {
-	int i;
 	struct device *dev = desc->dev;
-	struct gdsc **scs = desc->scs;
 	size_t num = desc->num;
 
-	/* Remove subdomains */
-	for (i = 0; i < num; i++) {
-		if (!scs[i])
-			continue;
-		if (scs[i]->parent)
-			pm_genpd_remove_subdomain(scs[i]->parent, &scs[i]->pd);
-		else if (!IS_ERR_OR_NULL(dev->pm_domain))
-			pm_genpd_remove_subdomain(pd_to_genpd(dev->pm_domain), &scs[i]->pd);
-	}
+	gdsc_pm_subdomain_remove(desc, num);
 	of_genpd_del_provider(dev->of_node);
 }
 
diff --git a/drivers/clk/qcom/gpucc-sm6350.c b/drivers/clk/qcom/gpucc-sm6350.c
index 1e12ad8948db..644bdc41892c 100644
--- a/drivers/clk/qcom/gpucc-sm6350.c
+++ b/drivers/clk/qcom/gpucc-sm6350.c
@@ -412,6 +412,9 @@ static struct clk_branch gpu_cc_gx_vsense_clk = {
 static struct gdsc gpu_cx_gdsc = {
 	.gdscr = 0x106c,
 	.gds_hw_ctrl = 0x1540,
+	.en_rest_wait_val = 0x2,
+	.en_few_wait_val = 0x2,
+	.clk_dis_wait_val = 0x8,
 	.pd = {
 		.name = "gpu_cx_gdsc",
 	},
@@ -422,6 +425,9 @@ static struct gdsc gpu_cx_gdsc = {
 static struct gdsc gpu_gx_gdsc = {
 	.gdscr = 0x100c,
 	.clamp_io_ctrl = 0x1508,
+	.en_rest_wait_val = 0x2,
+	.en_few_wait_val = 0x2,
+	.clk_dis_wait_val = 0x2,
 	.pd = {
 		.name = "gpu_gx_gdsc",
 		.power_on = gdsc_gx_do_nothing_enable,
diff --git a/drivers/clk/qcom/lpassaudiocc-sc7280.c b/drivers/clk/qcom/lpassaudiocc-sc7280.c
index 45e726477086..22169da08a51 100644
--- a/drivers/clk/qcom/lpassaudiocc-sc7280.c
+++ b/drivers/clk/qcom/lpassaudiocc-sc7280.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (c) 2021, The Linux Foundation. All rights reserved.
+ * Copyright (c) 2025, Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include <linux/clk-provider.h>
@@ -713,14 +714,24 @@ static const struct qcom_reset_map lpass_audio_cc_sc7280_resets[] = {
 	[LPASS_AUDIO_SWR_WSA_CGCR] = { 0xb0, 1 },
 };
 
+static const struct regmap_config lpass_audio_cc_sc7280_reset_regmap_config = {
+	.name = "lpassaudio_cc_reset",
+	.reg_bits = 32,
+	.reg_stride = 4,
+	.val_bits = 32,
+	.fast_io = true,
+	.max_register = 0xc8,
+};
+
 static const struct qcom_cc_desc lpass_audio_cc_reset_sc7280_desc = {
-	.config = &lpass_audio_cc_sc7280_regmap_config,
+	.config = &lpass_audio_cc_sc7280_reset_regmap_config,
 	.resets = lpass_audio_cc_sc7280_resets,
 	.num_resets = ARRAY_SIZE(lpass_audio_cc_sc7280_resets),
 };
 
 static const struct of_device_id lpass_audio_cc_sc7280_match_table[] = {
-	{ .compatible = "qcom,sc7280-lpassaudiocc" },
+	{ .compatible = "qcom,qcm6490-lpassaudiocc", .data = &lpass_audio_cc_reset_sc7280_desc },
+	{ .compatible = "qcom,sc7280-lpassaudiocc", .data = &lpass_audio_cc_sc7280_desc },
 	{ }
 };
 MODULE_DEVICE_TABLE(of, lpass_audio_cc_sc7280_match_table);
@@ -752,13 +763,17 @@ static int lpass_audio_cc_sc7280_probe(struct platform_device *pdev)
 	struct regmap *regmap;
 	int ret;
 
+	desc = device_get_match_data(&pdev->dev);
+
+	if (of_device_is_compatible(pdev->dev.of_node, "qcom,qcm6490-lpassaudiocc"))
+		return qcom_cc_probe_by_index(pdev, 1, desc);
+
 	ret = lpass_audio_setup_runtime_pm(pdev);
 	if (ret)
 		return ret;
 
 	lpass_audio_cc_sc7280_regmap_config.name = "lpassaudio_cc";
 	lpass_audio_cc_sc7280_regmap_config.max_register = 0x2f000;
-	desc = &lpass_audio_cc_sc7280_desc;
 
 	regmap = qcom_cc_map(pdev, desc);
 	if (IS_ERR(regmap)) {
@@ -772,7 +787,7 @@ static int lpass_audio_cc_sc7280_probe(struct platform_device *pdev)
 	regmap_write(regmap, 0x4, 0x3b);
 	regmap_write(regmap, 0x8, 0xff05);
 
-	ret = qcom_cc_really_probe(&pdev->dev, &lpass_audio_cc_sc7280_desc, regmap);
+	ret = qcom_cc_really_probe(&pdev->dev, desc, regmap);
 	if (ret) {
 		dev_err(&pdev->dev, "Failed to register LPASS AUDIO CC clocks\n");
 		goto exit;
diff --git a/drivers/clk/qcom/mmcc-sdm660.c b/drivers/clk/qcom/mmcc-sdm660.c
index 98ba5b4518fb..b9f02d91004e 100644
--- a/drivers/clk/qcom/mmcc-sdm660.c
+++ b/drivers/clk/qcom/mmcc-sdm660.c
@@ -2544,7 +2544,7 @@ static struct clk_branch video_core_clk = {
 
 static struct clk_branch video_subcore0_clk = {
 	.halt_reg = 0x1048,
-	.halt_check = BRANCH_HALT,
+	.halt_check = BRANCH_HALT_SKIP,
 	.clkr = {
 		.enable_reg = 0x1048,
 		.enable_mask = BIT(0),
diff --git a/drivers/clk/ralink/clk-mtmips.c b/drivers/clk/ralink/clk-mtmips.c
index 76285fbbdeaa..4b5d8b741e4e 100644
--- a/drivers/clk/ralink/clk-mtmips.c
+++ b/drivers/clk/ralink/clk-mtmips.c
@@ -264,7 +264,6 @@ err_clk_unreg:
 	}
 
 static struct mtmips_clk_fixed rt3883_fixed_clocks[] = {
-	CLK_FIXED("xtal", NULL, 40000000),
 	CLK_FIXED("periph", "xtal", 40000000)
 };
 
diff --git a/drivers/clk/renesas/r9a07g043-cpg.c b/drivers/clk/renesas/r9a07g043-cpg.c
index c3c2b0c43983..fce2eecfa8c0 100644
--- a/drivers/clk/renesas/r9a07g043-cpg.c
+++ b/drivers/clk/renesas/r9a07g043-cpg.c
@@ -89,7 +89,9 @@ static const struct clk_div_table dtable_1_32[] = {
 
 /* Mux clock tables */
 static const char * const sel_pll3_3[] = { ".pll3_533", ".pll3_400" };
+#ifdef CONFIG_ARM64
 static const char * const sel_pll6_2[]	= { ".pll6_250", ".pll5_250" };
+#endif
 static const char * const sel_sdhi[] = { ".clk_533", ".clk_400", ".clk_266" };
 
 static const u32 mtable_sdhi[] = { 1, 2, 3 };
@@ -137,7 +139,12 @@ static const struct cpg_core_clk r9a07g043_core_clks[] __initconst = {
 	DEF_DIV("P2", R9A07G043_CLK_P2, CLK_PLL3_DIV2_4_2, DIVPL3A, dtable_1_32),
 	DEF_FIXED("M0", R9A07G043_CLK_M0, CLK_PLL3_DIV2_4, 1, 1),
 	DEF_FIXED("ZT", R9A07G043_CLK_ZT, CLK_PLL3_DIV2_4_2, 1, 1),
+#ifdef CONFIG_ARM64
 	DEF_MUX("HP", R9A07G043_CLK_HP, SEL_PLL6_2, sel_pll6_2),
+#endif
+#ifdef CONFIG_RISCV
+	DEF_FIXED("HP", R9A07G043_CLK_HP, CLK_PLL6_250, 1, 1),
+#endif
 	DEF_FIXED("SPI0", R9A07G043_CLK_SPI0, CLK_DIV_PLL3_C, 1, 2),
 	DEF_FIXED("SPI1", R9A07G043_CLK_SPI1, CLK_DIV_PLL3_C, 1, 4),
 	DEF_SD_MUX("SD0", R9A07G043_CLK_SD0, SEL_SDHI0, SEL_SDHI0_STS, sel_sdhi,
diff --git a/drivers/clk/renesas/r9a08g045-cpg.c b/drivers/clk/renesas/r9a08g045-cpg.c
index 1ce40fb51f13..a1f961d5b856 100644
--- a/drivers/clk/renesas/r9a08g045-cpg.c
+++ b/drivers/clk/renesas/r9a08g045-cpg.c
@@ -50,7 +50,7 @@
 #define G3S_SEL_SDHI2		SEL_PLL_PACK(G3S_CPG_SDHI_DSEL, 8, 2)
 
 /* PLL 1/4/6 configuration registers macro. */
-#define G3S_PLL146_CONF(clk1, clk2)	((clk1) << 22 | (clk2) << 12)
+#define G3S_PLL146_CONF(clk1, clk2, setting)	((clk1) << 22 | (clk2) << 12 | (setting))
 
 #define DEF_G3S_MUX(_name, _id, _conf, _parent_names, _mux_flags, _clk_flags) \
 	DEF_TYPE(_name, _id, CLK_TYPE_MUX, .conf = (_conf), \
@@ -133,7 +133,8 @@ static const struct cpg_core_clk r9a08g045_core_clks[] __initconst = {
 
 	/* Internal Core Clocks */
 	DEF_FIXED(".osc_div1000", CLK_OSC_DIV1000, CLK_EXTAL, 1, 1000),
-	DEF_G3S_PLL(".pll1", CLK_PLL1, CLK_EXTAL, G3S_PLL146_CONF(0x4, 0x8)),
+	DEF_G3S_PLL(".pll1", CLK_PLL1, CLK_EXTAL, G3S_PLL146_CONF(0x4, 0x8, 0x100),
+		    1100000000UL),
 	DEF_FIXED(".pll2", CLK_PLL2, CLK_EXTAL, 200, 3),
 	DEF_FIXED(".pll3", CLK_PLL3, CLK_EXTAL, 200, 3),
 	DEF_FIXED(".pll4", CLK_PLL4, CLK_EXTAL, 100, 3),
diff --git a/drivers/clk/renesas/renesas-cpg-mssr.c b/drivers/clk/renesas/renesas-cpg-mssr.c
index 1b421b809796..0f27c33192e1 100644
--- a/drivers/clk/renesas/renesas-cpg-mssr.c
+++ b/drivers/clk/renesas/renesas-cpg-mssr.c
@@ -981,7 +981,7 @@ static void __init cpg_mssr_reserved_exit(struct cpg_mssr_priv *priv)
 static int __init cpg_mssr_reserved_init(struct cpg_mssr_priv *priv,
 					 const struct cpg_mssr_info *info)
 {
-	struct device_node *soc = of_find_node_by_path("/soc");
+	struct device_node *soc __free(device_node) = of_find_node_by_path("/soc");
 	struct device_node *node;
 	uint32_t args[MAX_PHANDLE_ARGS];
 	unsigned int *ids = NULL;
diff --git a/drivers/clk/renesas/rzg2l-cpg.c b/drivers/clk/renesas/rzg2l-cpg.c
index b43b763dfe18..e2ecc9d36e05 100644
--- a/drivers/clk/renesas/rzg2l-cpg.c
+++ b/drivers/clk/renesas/rzg2l-cpg.c
@@ -51,6 +51,7 @@
 #define RZG3S_DIV_M		GENMASK(25, 22)
 #define RZG3S_DIV_NI		GENMASK(21, 13)
 #define RZG3S_DIV_NF		GENMASK(12, 1)
+#define RZG3S_SEL_PLL		BIT(0)
 
 #define CLK_ON_R(reg)		(reg)
 #define CLK_MON_R(reg)		(0x180 + (reg))
@@ -60,6 +61,7 @@
 #define GET_REG_OFFSET(val)		((val >> 20) & 0xfff)
 #define GET_REG_SAMPLL_CLK1(val)	((val >> 22) & 0xfff)
 #define GET_REG_SAMPLL_CLK2(val)	((val >> 12) & 0xfff)
+#define GET_REG_SAMPLL_SETTING(val)	((val) & 0xfff)
 
 #define CPG_WEN_BIT		BIT(16)
 
@@ -943,6 +945,7 @@ rzg2l_cpg_sipll5_register(const struct cpg_core_clk *core,
 
 struct pll_clk {
 	struct clk_hw hw;
+	unsigned long default_rate;
 	unsigned int conf;
 	unsigned int type;
 	void __iomem *base;
@@ -980,12 +983,19 @@ static unsigned long rzg3s_cpg_pll_clk_recalc_rate(struct clk_hw *hw,
 {
 	struct pll_clk *pll_clk = to_pll(hw);
 	struct rzg2l_cpg_priv *priv = pll_clk->priv;
-	u32 nir, nfr, mr, pr, val;
+	u32 nir, nfr, mr, pr, val, setting;
 	u64 rate;
 
 	if (pll_clk->type != CLK_TYPE_G3S_PLL)
 		return parent_rate;
 
+	setting = GET_REG_SAMPLL_SETTING(pll_clk->conf);
+	if (setting) {
+		val = readl(priv->base + setting);
+		if (val & RZG3S_SEL_PLL)
+			return pll_clk->default_rate;
+	}
+
 	val = readl(priv->base + GET_REG_SAMPLL_CLK1(pll_clk->conf));
 
 	pr = 1 << FIELD_GET(RZG3S_DIV_P, val);
@@ -1038,6 +1048,7 @@ rzg2l_cpg_pll_clk_register(const struct cpg_core_clk *core,
 	pll_clk->base = priv->base;
 	pll_clk->priv = priv;
 	pll_clk->type = core->type;
+	pll_clk->default_rate = core->default_rate;
 
 	ret = devm_clk_hw_register(dev, &pll_clk->hw);
 	if (ret)
@@ -1387,10 +1398,6 @@ rzg2l_cpg_register_mod_clk(const struct rzg2l_mod_clk *mod,
 		goto fail;
 	}
 
-	clk = clock->hw.clk;
-	dev_dbg(dev, "Module clock %pC at %lu Hz\n", clk, clk_get_rate(clk));
-	priv->clks[id] = clk;
-
 	if (mod->is_coupled) {
 		struct mstp_clock *sibling;
 
@@ -1402,6 +1409,10 @@ rzg2l_cpg_register_mod_clk(const struct rzg2l_mod_clk *mod,
 		}
 	}
 
+	clk = clock->hw.clk;
+	dev_dbg(dev, "Module clock %pC at %lu Hz\n", clk, clk_get_rate(clk));
+	priv->clks[id] = clk;
+
 	return;
 
 fail:
@@ -1538,28 +1549,6 @@ static int rzg2l_cpg_reset_controller_register(struct rzg2l_cpg_priv *priv)
 	return devm_reset_controller_register(priv->dev, &priv->rcdev);
 }
 
-static bool rzg2l_cpg_is_pm_clk(struct rzg2l_cpg_priv *priv,
-				const struct of_phandle_args *clkspec)
-{
-	const struct rzg2l_cpg_info *info = priv->info;
-	unsigned int id;
-	unsigned int i;
-
-	if (clkspec->args_count != 2)
-		return false;
-
-	if (clkspec->args[0] != CPG_MOD)
-		return false;
-
-	id = clkspec->args[1] + info->num_total_core_clks;
-	for (i = 0; i < info->num_no_pm_mod_clks; i++) {
-		if (info->no_pm_mod_clks[i] == id)
-			return false;
-	}
-
-	return true;
-}
-
 /**
  * struct rzg2l_cpg_pm_domains - RZ/G2L PM domains data structure
  * @onecell_data: cell data
@@ -1584,45 +1573,73 @@ struct rzg2l_cpg_pd {
 	u16 id;
 };
 
+static bool rzg2l_cpg_is_pm_clk(struct rzg2l_cpg_pd *pd,
+				const struct of_phandle_args *clkspec)
+{
+	if (clkspec->np != pd->genpd.dev.of_node || clkspec->args_count != 2)
+		return false;
+
+	switch (clkspec->args[0]) {
+	case CPG_MOD: {
+		struct rzg2l_cpg_priv *priv = pd->priv;
+		const struct rzg2l_cpg_info *info = priv->info;
+		unsigned int id = clkspec->args[1];
+
+		if (id >= priv->num_mod_clks)
+			return false;
+
+		id += info->num_total_core_clks;
+
+		for (unsigned int i = 0; i < info->num_no_pm_mod_clks; i++) {
+			if (info->no_pm_mod_clks[i] == id)
+				return false;
+		}
+
+		return true;
+	}
+
+	case CPG_CORE:
+	default:
+		return false;
+	}
+}
+
 static int rzg2l_cpg_attach_dev(struct generic_pm_domain *domain, struct device *dev)
 {
 	struct rzg2l_cpg_pd *pd = container_of(domain, struct rzg2l_cpg_pd, genpd);
-	struct rzg2l_cpg_priv *priv = pd->priv;
 	struct device_node *np = dev->of_node;
 	struct of_phandle_args clkspec;
 	bool once = true;
 	struct clk *clk;
+	unsigned int i;
 	int error;
-	int i = 0;
-
-	while (!of_parse_phandle_with_args(np, "clocks", "#clock-cells", i,
-					   &clkspec)) {
-		if (rzg2l_cpg_is_pm_clk(priv, &clkspec)) {
-			if (once) {
-				once = false;
-				error = pm_clk_create(dev);
-				if (error) {
-					of_node_put(clkspec.np);
-					goto err;
-				}
-			}
-			clk = of_clk_get_from_provider(&clkspec);
+
+	for (i = 0; !of_parse_phandle_with_args(np, "clocks", "#clock-cells", i, &clkspec); i++) {
+		if (!rzg2l_cpg_is_pm_clk(pd, &clkspec)) {
 			of_node_put(clkspec.np);
-			if (IS_ERR(clk)) {
-				error = PTR_ERR(clk);
-				goto fail_destroy;
-			}
+			continue;
+		}
 
-			error = pm_clk_add_clk(dev, clk);
+		if (once) {
+			once = false;
+			error = pm_clk_create(dev);
 			if (error) {
-				dev_err(dev, "pm_clk_add_clk failed %d\n",
-					error);
-				goto fail_put;
+				of_node_put(clkspec.np);
+				goto err;
 			}
-		} else {
-			of_node_put(clkspec.np);
 		}
-		i++;
+		clk = of_clk_get_from_provider(&clkspec);
+		of_node_put(clkspec.np);
+		if (IS_ERR(clk)) {
+			error = PTR_ERR(clk);
+			goto fail_destroy;
+		}
+
+		error = pm_clk_add_clk(dev, clk);
+		if (error) {
+			dev_err(dev, "pm_clk_add_clk failed %d\n", error);
+			goto fail_put;
+		}
 	}
 
 	return 0;
diff --git a/drivers/clk/renesas/rzg2l-cpg.h b/drivers/clk/renesas/rzg2l-cpg.h
index ecfe7e7ea8a1..019efe00ffd9 100644
--- a/drivers/clk/renesas/rzg2l-cpg.h
+++ b/drivers/clk/renesas/rzg2l-cpg.h
@@ -102,7 +102,10 @@ struct cpg_core_clk {
 	const struct clk_div_table *dtable;
 	const u32 *mtable;
 	const unsigned long invalid_rate;
-	const unsigned long max_rate;
+	union {
+		const unsigned long max_rate;
+		const unsigned long default_rate;
+	};
 	const char * const *parent_names;
 	notifier_fn_t notifier;
 	u32 flag;
@@ -144,8 +147,9 @@ enum clk_types {
 	DEF_TYPE(_name, _id, _type, .parent = _parent)
 #define DEF_SAMPLL(_name, _id, _parent, _conf) \
 	DEF_TYPE(_name, _id, CLK_TYPE_SAM_PLL, .parent = _parent, .conf = _conf)
-#define DEF_G3S_PLL(_name, _id, _parent, _conf) \
-	DEF_TYPE(_name, _id, CLK_TYPE_G3S_PLL, .parent = _parent, .conf = _conf)
+#define DEF_G3S_PLL(_name, _id, _parent, _conf, _default_rate) \
+	DEF_TYPE(_name, _id, CLK_TYPE_G3S_PLL, .parent = _parent, .conf = _conf, \
+		 .default_rate = _default_rate)
 #define DEF_INPUT(_name, _id) \
 	DEF_TYPE(_name, _id, CLK_TYPE_IN)
 #define DEF_FIXED(_name, _id, _parent, _mult, _div) \
diff --git a/drivers/clk/renesas/rzv2h-cpg.c b/drivers/clk/renesas/rzv2h-cpg.c
index b524a9d33610..5f8116e39e22 100644
--- a/drivers/clk/renesas/rzv2h-cpg.c
+++ b/drivers/clk/renesas/rzv2h-cpg.c
@@ -312,6 +312,7 @@ rzv2h_cpg_ddiv_clk_register(const struct cpg_core_clk *core,
 	init.ops = &rzv2h_ddiv_clk_divider_ops;
 	init.parent_names = &parent_name;
 	init.num_parents = 1;
+	init.flags = CLK_SET_RATE_PARENT;
 
 	ddiv->priv = priv;
 	ddiv->mon = cfg_ddiv.monbit;
diff --git a/drivers/clk/rockchip/clk-rk3036.c b/drivers/clk/rockchip/clk-rk3036.c
index d341ce0708aa..e4af3a928637 100644
--- a/drivers/clk/rockchip/clk-rk3036.c
+++ b/drivers/clk/rockchip/clk-rk3036.c
@@ -431,6 +431,7 @@ static const char *const rk3036_critical_clocks[] __initconst = {
 	"hclk_peri",
 	"pclk_peri",
 	"pclk_ddrupctl",
+	"ddrphy",
 };
 
 static void __init rk3036_clk_init(struct device_node *np)
diff --git a/drivers/clk/rockchip/clk-rk3328.c b/drivers/clk/rockchip/clk-rk3328.c
index 3bb87b27b662..cf60fcf2fa5c 100644
--- a/drivers/clk/rockchip/clk-rk3328.c
+++ b/drivers/clk/rockchip/clk-rk3328.c
@@ -201,7 +201,7 @@ PNAME(mux_aclk_peri_pre_p)	= { "cpll_peri",
 				    "gpll_peri",
 				    "hdmiphy_peri" };
 PNAME(mux_ref_usb3otg_src_p)	= { "xin24m",
-				    "clk_usb3otg_ref" };
+				    "clk_ref_usb3otg_src" };
 PNAME(mux_xin24m_32k_p)		= { "xin24m",
 				    "clk_rtc32k" };
 PNAME(mux_mac2io_src_p)		= { "clk_mac2io_src",
diff --git a/drivers/clk/samsung/clk-exynos850.c b/drivers/clk/samsung/clk-exynos850.c
index e00e213b1201..e2a63ea7d4cb 100644
--- a/drivers/clk/samsung/clk-exynos850.c
+++ b/drivers/clk/samsung/clk-exynos850.c
@@ -1360,7 +1360,7 @@ static const unsigned long cpucl1_clk_regs[] __initconst = {
 	CLK_CON_GAT_GATE_CLK_CPUCL1_CPU,
 };
 
-/* List of parent clocks for Muxes in CMU_CPUCL0 */
+/* List of parent clocks for Muxes in CMU_CPUCL1 */
 PNAME(mout_pll_cpucl1_p)		 = { "oscclk", "fout_cpucl1_pll" };
 PNAME(mout_cpucl1_switch_user_p)	 = { "oscclk", "dout_cpucl1_switch" };
 PNAME(mout_cpucl1_dbg_user_p)		 = { "oscclk", "dout_cpucl1_dbg" };
diff --git a/drivers/clk/samsung/clk-gs101.c b/drivers/clk/samsung/clk-gs101.c
index 85098c61c15e..fa628fab28ac 100644
--- a/drivers/clk/samsung/clk-gs101.c
+++ b/drivers/clk/samsung/clk-gs101.c
@@ -382,17 +382,9 @@ static const unsigned long cmu_top_clk_regs[] __initconst = {
 	EARLY_WAKEUP_DPU_DEST,
 	EARLY_WAKEUP_CSIS_DEST,
 	EARLY_WAKEUP_SW_TRIG_APM,
-	EARLY_WAKEUP_SW_TRIG_APM_SET,
-	EARLY_WAKEUP_SW_TRIG_APM_CLEAR,
 	EARLY_WAKEUP_SW_TRIG_CLUSTER0,
-	EARLY_WAKEUP_SW_TRIG_CLUSTER0_SET,
-	EARLY_WAKEUP_SW_TRIG_CLUSTER0_CLEAR,
 	EARLY_WAKEUP_SW_TRIG_DPU,
-	EARLY_WAKEUP_SW_TRIG_DPU_SET,
-	EARLY_WAKEUP_SW_TRIG_DPU_CLEAR,
 	EARLY_WAKEUP_SW_TRIG_CSIS,
-	EARLY_WAKEUP_SW_TRIG_CSIS_SET,
-	EARLY_WAKEUP_SW_TRIG_CSIS_CLEAR,
 	CLK_CON_MUX_MUX_CLKCMU_BO_BUS,
 	CLK_CON_MUX_MUX_CLKCMU_BUS0_BUS,
 	CLK_CON_MUX_MUX_CLKCMU_BUS1_BUS,
@@ -1162,7 +1154,7 @@ static const struct samsung_div_clock cmu_top_div_clks[] __initconst = {
 	    CLK_CON_DIV_CLKCMU_G2D_MSCL, 0, 4),
 	DIV(CLK_DOUT_CMU_G3AA_G3AA, "dout_cmu_g3aa_g3aa", "gout_cmu_g3aa_g3aa",
 	    CLK_CON_DIV_CLKCMU_G3AA_G3AA, 0, 4),
-	DIV(CLK_DOUT_CMU_G3D_SWITCH, "dout_cmu_g3d_busd", "gout_cmu_g3d_busd",
+	DIV(CLK_DOUT_CMU_G3D_BUSD, "dout_cmu_g3d_busd", "gout_cmu_g3d_busd",
 	    CLK_CON_DIV_CLKCMU_G3D_BUSD, 0, 4),
 	DIV(CLK_DOUT_CMU_G3D_GLB, "dout_cmu_g3d_glb", "gout_cmu_g3d_glb",
 	    CLK_CON_DIV_CLKCMU_G3D_GLB, 0, 4),
@@ -2137,7 +2129,7 @@ PNAME(mout_hsi0_usbdpdbg_user_p)	= { "oscclk",
 					    "dout_cmu_hsi0_usbdpdbg" };
 PNAME(mout_hsi0_bus_p)			= { "mout_hsi0_bus_user",
 					    "mout_hsi0_alt_user" };
-PNAME(mout_hsi0_usb20_ref_p)		= { "fout_usb_pll",
+PNAME(mout_hsi0_usb20_ref_p)		= { "mout_pll_usb",
 					    "mout_hsi0_tcxo_user" };
 PNAME(mout_hsi0_usb31drd_p)		= { "fout_usb_pll",
 					    "mout_hsi0_usb31drd_user",
diff --git a/drivers/clk/samsung/clk-pll.c b/drivers/clk/samsung/clk-pll.c
index cca3e630922c..68a72f5fd9a5 100644
--- a/drivers/clk/samsung/clk-pll.c
+++ b/drivers/clk/samsung/clk-pll.c
@@ -206,6 +206,7 @@ static const struct clk_ops samsung_pll3000_clk_ops = {
  */
 /* Maximum lock time can be 270 * PDIV cycles */
 #define PLL35XX_LOCK_FACTOR	(270)
+#define PLL142XX_LOCK_FACTOR	(150)
 
 #define PLL35XX_MDIV_MASK       (0x3FF)
 #define PLL35XX_PDIV_MASK       (0x3F)
@@ -272,7 +273,11 @@ static int samsung_pll35xx_set_rate(struct clk_hw *hw, unsigned long drate,
 	}
 
 	/* Set PLL lock time. */
-	writel_relaxed(rate->pdiv * PLL35XX_LOCK_FACTOR,
+	if (pll->type == pll_142xx)
+		writel_relaxed(rate->pdiv * PLL142XX_LOCK_FACTOR,
+			pll->lock_reg);
+	else
+		writel_relaxed(rate->pdiv * PLL35XX_LOCK_FACTOR,
 			pll->lock_reg);
 
 	/* Change PLL PMS values */
diff --git a/drivers/clk/samsung/clk.c b/drivers/clk/samsung/clk.c
index afa5760ed3a1..e6533513f8ac 100644
--- a/drivers/clk/samsung/clk.c
+++ b/drivers/clk/samsung/clk.c
@@ -74,12 +74,12 @@ struct samsung_clk_provider * __init samsung_clk_init(struct device *dev,
 	if (!ctx)
 		panic("could not allocate clock provider context.\n");
 
+	ctx->clk_data.num = nr_clks;
 	for (i = 0; i < nr_clks; ++i)
 		ctx->clk_data.hws[i] = ERR_PTR(-ENOENT);
 
 	ctx->dev = dev;
 	ctx->reg_base = base;
-	ctx->clk_data.num = nr_clks;
 	spin_lock_init(&ctx->lock);
 
 	return ctx;
diff --git a/drivers/clk/sunxi-ng/ccu-sun20i-d1.c b/drivers/clk/sunxi-ng/ccu-sun20i-d1.c
index 3f095515f54f..54d2c7f0ed63 100644
--- a/drivers/clk/sunxi-ng/ccu-sun20i-d1.c
+++ b/drivers/clk/sunxi-ng/ccu-sun20i-d1.c
@@ -412,19 +412,23 @@ static const struct clk_parent_data mmc0_mmc1_parents[] = {
 	{ .hw = &pll_periph0_2x_clk.common.hw },
 	{ .hw = &pll_audio1_div2_clk.common.hw },
 };
-static SUNXI_CCU_MP_DATA_WITH_MUX_GATE(mmc0_clk, "mmc0", mmc0_mmc1_parents, 0x830,
-				       0, 4,	/* M */
-				       8, 2,	/* P */
-				       24, 3,	/* mux */
-				       BIT(31),	/* gate */
-				       0);
-
-static SUNXI_CCU_MP_DATA_WITH_MUX_GATE(mmc1_clk, "mmc1", mmc0_mmc1_parents, 0x834,
-				       0, 4,	/* M */
-				       8, 2,	/* P */
-				       24, 3,	/* mux */
-				       BIT(31),	/* gate */
-				       0);
+static SUNXI_CCU_MP_DATA_WITH_MUX_GATE_POSTDIV(mmc0_clk, "mmc0",
+					       mmc0_mmc1_parents, 0x830,
+					       0, 4,		/* M */
+					       8, 2,		/* P */
+					       24, 3,		/* mux */
+					       BIT(31),		/* gate */
+					       2,		/* post-div */
+					       0);
+
+static SUNXI_CCU_MP_DATA_WITH_MUX_GATE_POSTDIV(mmc1_clk, "mmc1",
+					       mmc0_mmc1_parents, 0x834,
+					       0, 4,		/* M */
+					       8, 2,		/* P */
+					       24, 3,		/* mux */
+					       BIT(31),		/* gate */
+					       2,		/* post-div */
+					       0);
 
 static const struct clk_parent_data mmc2_parents[] = {
 	{ .fw_name = "hosc" },
@@ -433,12 +437,14 @@ static const struct clk_parent_data mmc2_parents[] = {
 	{ .hw = &pll_periph0_800M_clk.common.hw },
 	{ .hw = &pll_audio1_div2_clk.common.hw },
 };
-static SUNXI_CCU_MP_DATA_WITH_MUX_GATE(mmc2_clk, "mmc2", mmc2_parents, 0x838,
-				       0, 4,	/* M */
-				       8, 2,	/* P */
-				       24, 3,	/* mux */
-				       BIT(31),	/* gate */
-				       0);
+static SUNXI_CCU_MP_DATA_WITH_MUX_GATE_POSTDIV(mmc2_clk, "mmc2", mmc2_parents,
+					       0x838,
+					       0, 4,		/* M */
+					       8, 2,		/* P */
+					       24, 3,		/* mux */
+					       BIT(31),		/* gate */
+					       2,		/* post-div */
+					       0);
 
 static SUNXI_CCU_GATE_HWS(bus_mmc0_clk, "bus-mmc0", psi_ahb_hws,
 			  0x84c, BIT(0), 0);
diff --git a/drivers/clk/sunxi-ng/ccu-sun50i-a100.c b/drivers/clk/sunxi-ng/ccu-sun50i-a100.c
index bbaa82978716..a59e420b195d 100644
--- a/drivers/clk/sunxi-ng/ccu-sun50i-a100.c
+++ b/drivers/clk/sunxi-ng/ccu-sun50i-a100.c
@@ -436,7 +436,7 @@ static SUNXI_CCU_MP_WITH_MUX_GATE_POSTDIV(mmc0_clk, "mmc0", mmc_parents, 0x830,
 					  24, 2,	/* mux */
 					  BIT(31),	/* gate */
 					  2,		/* post-div */
-					  CLK_SET_RATE_NO_REPARENT);
+					  0);
 
 static SUNXI_CCU_MP_WITH_MUX_GATE_POSTDIV(mmc1_clk, "mmc1", mmc_parents, 0x834,
 					  0, 4,		/* M */
@@ -444,7 +444,7 @@ static SUNXI_CCU_MP_WITH_MUX_GATE_POSTDIV(mmc1_clk, "mmc1", mmc_parents, 0x834,
 					  24, 2,	/* mux */
 					  BIT(31),	/* gate */
 					  2,		/* post-div */
-					  CLK_SET_RATE_NO_REPARENT);
+					  0);
 
 static SUNXI_CCU_MP_WITH_MUX_GATE_POSTDIV(mmc2_clk, "mmc2", mmc_parents, 0x838,
 					  0, 4,		/* M */
@@ -452,7 +452,7 @@ static SUNXI_CCU_MP_WITH_MUX_GATE_POSTDIV(mmc2_clk, "mmc2", mmc_parents, 0x838,
 					  24, 2,	/* mux */
 					  BIT(31),	/* gate */
 					  2,		/* post-div */
-					  CLK_SET_RATE_NO_REPARENT);
+					  0);
 
 static SUNXI_CCU_GATE(bus_mmc0_clk, "bus-mmc0", "ahb3", 0x84c, BIT(0), 0);
 static SUNXI_CCU_GATE(bus_mmc1_clk, "bus-mmc1", "ahb3", 0x84c, BIT(1), 0);
diff --git a/drivers/clk/sunxi-ng/ccu-sun50i-a64.c b/drivers/clk/sunxi-ng/ccu-sun50i-a64.c
index c255dba2c96d..6727a3e30a12 100644
--- a/drivers/clk/sunxi-ng/ccu-sun50i-a64.c
+++ b/drivers/clk/sunxi-ng/ccu-sun50i-a64.c
@@ -535,11 +535,11 @@ static SUNXI_CCU_M_WITH_MUX_GATE(de_clk, "de", de_parents,
 				 CLK_SET_RATE_PARENT);
 
 /*
- * DSI output seems to work only when PLL_MIPI selected. Set it and prevent
- * the mux from reparenting.
+ * Experiments showed that RGB output requires pll-video0-2x, while DSI
+ * requires pll-mipi. It will not work with incorrect clock, the screen will
+ * be blank.
+ * sun50i-a64.dtsi assigns pll-mipi as TCON0 parent by default
  */
-#define SUN50I_A64_TCON0_CLK_REG	0x118
-
 static const char * const tcon0_parents[] = { "pll-mipi", "pll-video0-2x" };
 static const u8 tcon0_table[] = { 0, 2, };
 static SUNXI_CCU_MUX_TABLE_WITH_GATE_CLOSEST(tcon0_clk, "tcon0", tcon0_parents,
@@ -959,11 +959,6 @@ static int sun50i_a64_ccu_probe(struct platform_device *pdev)
 
 	writel(0x515, reg + SUN50I_A64_PLL_MIPI_REG);
 
-	/* Set PLL MIPI as parent for TCON0 */
-	val = readl(reg + SUN50I_A64_TCON0_CLK_REG);
-	val &= ~GENMASK(26, 24);
-	writel(val | (0 << 24), reg + SUN50I_A64_TCON0_CLK_REG);
-
 	ret = devm_sunxi_ccu_probe(&pdev->dev, reg, &sun50i_a64_ccu_desc);
 	if (ret)
 		return ret;
diff --git a/drivers/clk/sunxi-ng/ccu-sun50i-a64.h b/drivers/clk/sunxi-ng/ccu-sun50i-a64.h
index a8c11c0b4e06..dfba88a5ad0f 100644
--- a/drivers/clk/sunxi-ng/ccu-sun50i-a64.h
+++ b/drivers/clk/sunxi-ng/ccu-sun50i-a64.h
@@ -21,7 +21,6 @@
 
 /* PLL_VIDEO0 exported for HDMI PHY */
 
-#define CLK_PLL_VIDEO0_2X		8
 #define CLK_PLL_VE			9
 #define CLK_PLL_DDR0			10
 
@@ -32,7 +31,6 @@
 #define CLK_PLL_PERIPH1_2X		14
 #define CLK_PLL_VIDEO1			15
 #define CLK_PLL_GPU			16
-#define CLK_PLL_MIPI			17
 #define CLK_PLL_HSIC			18
 #define CLK_PLL_DE			19
 #define CLK_PLL_DDR1			20
diff --git a/drivers/clk/sunxi-ng/ccu-sun8i-v3s.c b/drivers/clk/sunxi-ng/ccu-sun8i-v3s.c
index d24c0d8dfee4..3416e0020799 100644
--- a/drivers/clk/sunxi-ng/ccu-sun8i-v3s.c
+++ b/drivers/clk/sunxi-ng/ccu-sun8i-v3s.c
@@ -347,8 +347,7 @@ static SUNXI_CCU_GATE(dram_ohci_clk,	"dram-ohci",	"dram",
 
 static const char * const de_parents[] = { "pll-video", "pll-periph0" };
 static SUNXI_CCU_M_WITH_MUX_GATE(de_clk, "de", de_parents,
-				 0x104, 0, 4, 24, 2, BIT(31),
-				 CLK_SET_RATE_PARENT);
+				 0x104, 0, 4, 24, 3, BIT(31), 0);
 
 static const char * const tcon_parents[] = { "pll-video" };
 static SUNXI_CCU_M_WITH_MUX_GATE(tcon_clk, "tcon", tcon_parents,
diff --git a/drivers/clk/sunxi-ng/ccu_mp.h b/drivers/clk/sunxi-ng/ccu_mp.h
index 6e50f3728fb5..7d836a9fb3db 100644
--- a/drivers/clk/sunxi-ng/ccu_mp.h
+++ b/drivers/clk/sunxi-ng/ccu_mp.h
@@ -52,6 +52,28 @@ struct ccu_mp {
 		}							\
 	}
 
+#define SUNXI_CCU_MP_DATA_WITH_MUX_GATE_POSTDIV(_struct, _name, _parents, \
+						_reg,			\
+						_mshift, _mwidth,	\
+						_pshift, _pwidth,	\
+						_muxshift, _muxwidth,	\
+						_gate, _postdiv, _flags)\
+	struct ccu_mp _struct = {					\
+		.enable	= _gate,					\
+		.m	= _SUNXI_CCU_DIV(_mshift, _mwidth),		\
+		.p	= _SUNXI_CCU_DIV(_pshift, _pwidth),		\
+		.mux	= _SUNXI_CCU_MUX(_muxshift, _muxwidth),		\
+		.fixed_post_div	= _postdiv,				\
+		.common	= {						\
+			.reg		= _reg,				\
+			.features	= CCU_FEATURE_FIXED_POSTDIV,	\
+			.hw.init	= CLK_HW_INIT_PARENTS_DATA(_name, \
+							_parents,	\
+							&ccu_mp_ops,	\
+							_flags),	\
+		}							\
+	}
+
 #define SUNXI_CCU_MP_WITH_MUX_GATE(_struct, _name, _parents, _reg,	\
 				   _mshift, _mwidth,			\
 				   _pshift, _pwidth,			\
diff --git a/drivers/clk/tegra/clk-periph.c b/drivers/clk/tegra/clk-periph.c
index 0626650a7011..c9fc52a36fce 100644
--- a/drivers/clk/tegra/clk-periph.c
+++ b/drivers/clk/tegra/clk-periph.c
@@ -51,7 +51,7 @@ static int clk_periph_determine_rate(struct clk_hw *hw,
 	struct tegra_clk_periph *periph = to_clk_periph(hw);
 	const struct clk_ops *div_ops = periph->div_ops;
 	struct clk_hw *div_hw = &periph->divider.hw;
-	unsigned long rate;
+	long rate;
 
 	__clk_hw_set_clk(div_hw, hw);
 
@@ -59,7 +59,7 @@ static int clk_periph_determine_rate(struct clk_hw *hw,
 	if (rate < 0)
 		return rate;
 
-	req->rate = rate;
+	req->rate = (unsigned long)rate;
 	return 0;
 }
 
diff --git a/drivers/clk/thead/clk-th1520-ap.c b/drivers/clk/thead/clk-th1520-ap.c
index 1015fab95251..c8ebacc6934a 100644
--- a/drivers/clk/thead/clk-th1520-ap.c
+++ b/drivers/clk/thead/clk-th1520-ap.c
@@ -582,7 +582,14 @@ static const struct clk_parent_data peri2sys_apb_pclk_pd[] = {
 	{ .hw = &peri2sys_apb_pclk.common.hw }
 };
 
-static CLK_FIXED_FACTOR_FW_NAME(osc12m_clk, "osc_12m", "osc_24m", 2, 1, 0);
+static struct clk_fixed_factor osc12m_clk = {
+	.div		= 2,
+	.mult		= 1,
+	.hw.init	= CLK_HW_INIT_PARENTS_DATA("osc_12m",
+						   osc_24m_clk,
+						   &clk_fixed_factor_ops,
+						   0),
+};
 
 static const char * const out_parents[] = { "osc_24m", "osc_12m" };
 
@@ -657,7 +664,7 @@ static struct ccu_div apb_pclk = {
 		.hw.init	= CLK_HW_INIT_PARENTS_DATA("apb-pclk",
 						      apb_parents,
 						      &ccu_div_ops,
-						      0),
+						      CLK_IGNORE_UNUSED),
 	},
 };
 
@@ -792,15 +799,16 @@ static CCU_GATE(CLK_AON2CPU_A2X, aon2cpu_a2x_clk, "aon2cpu-a2x", axi4_cpusys2_ac
 		0x134, BIT(8), 0);
 static CCU_GATE(CLK_X2X_CPUSYS, x2x_cpusys_clk, "x2x-cpusys", axi4_cpusys2_aclk_pd,
 		0x134, BIT(7), 0);
-static CCU_GATE(CLK_CPU2AON_X2H, cpu2aon_x2h_clk, "cpu2aon-x2h", axi_aclk_pd, 0x138, BIT(8), 0);
+static CCU_GATE(CLK_CPU2AON_X2H, cpu2aon_x2h_clk, "cpu2aon-x2h", axi_aclk_pd,
+		0x138, BIT(8), CLK_IGNORE_UNUSED);
 static CCU_GATE(CLK_CPU2PERI_X2H, cpu2peri_x2h_clk, "cpu2peri-x2h", axi4_cpusys2_aclk_pd,
-		0x140, BIT(9), 0);
+		0x140, BIT(9), CLK_IGNORE_UNUSED);
 static CCU_GATE(CLK_PERISYS_APB1_HCLK, perisys_apb1_hclk, "perisys-apb1-hclk", perisys_ahb_hclk_pd,
-		0x150, BIT(9), 0);
+		0x150, BIT(9), CLK_IGNORE_UNUSED);
 static CCU_GATE(CLK_PERISYS_APB2_HCLK, perisys_apb2_hclk, "perisys-apb2-hclk", perisys_ahb_hclk_pd,
-		0x150, BIT(10), 0);
+		0x150, BIT(10), CLK_IGNORE_UNUSED);
 static CCU_GATE(CLK_PERISYS_APB3_HCLK, perisys_apb3_hclk, "perisys-apb3-hclk", perisys_ahb_hclk_pd,
-		0x150, BIT(11), 0);
+		0x150, BIT(11), CLK_IGNORE_UNUSED);
 static CCU_GATE(CLK_PERISYS_APB4_HCLK, perisys_apb4_hclk, "perisys-apb4-hclk", perisys_ahb_hclk_pd,
 		0x150, BIT(12), 0);
 static CCU_GATE(CLK_NPU_AXI, npu_axi_clk, "npu-axi", axi_aclk_pd, 0x1c8, BIT(5), 0);
@@ -896,7 +904,6 @@ static struct ccu_common *th1520_div_clks[] = {
 	&vo_axi_clk.common,
 	&vp_apb_clk.common,
 	&vp_axi_clk.common,
-	&cpu2vp_clk.common,
 	&venc_clk.common,
 	&dpu0_clk.common,
 	&dpu1_clk.common,
@@ -916,6 +923,7 @@ static struct ccu_common *th1520_gate_clks[] = {
 	&bmu_clk.common,
 	&cpu2aon_x2h_clk.common,
 	&cpu2peri_x2h_clk.common,
+	&cpu2vp_clk.common,
 	&perisys_apb1_hclk.common,
 	&perisys_apb2_hclk.common,
 	&perisys_apb3_hclk.common,
@@ -1048,7 +1056,8 @@ static int th1520_clk_probe(struct platform_device *pdev)
 		hw = devm_clk_hw_register_gate_parent_data(dev,
 							   cg->common.hw.init->name,
 							   cg->common.hw.init->parent_data,
-							   0, base + cg->common.cfg0,
+							   cg->common.hw.init->flags,
+							   base + cg->common.cfg0,
 							   ffs(cg->enable) - 1, 0, NULL);
 		if (IS_ERR(hw))
 			return PTR_ERR(hw);
diff --git a/drivers/clk/xilinx/xlnx_vcu.c b/drivers/clk/xilinx/xlnx_vcu.c
index 81501b48412e..88b3fd8250c2 100644
--- a/drivers/clk/xilinx/xlnx_vcu.c
+++ b/drivers/clk/xilinx/xlnx_vcu.c
@@ -587,8 +587,8 @@ static void xvcu_unregister_clock_provider(struct xvcu_device *xvcu)
 		xvcu_clk_hw_unregister_leaf(hws[CLK_XVCU_ENC_MCU]);
 	if (!IS_ERR_OR_NULL(hws[CLK_XVCU_ENC_CORE]))
 		xvcu_clk_hw_unregister_leaf(hws[CLK_XVCU_ENC_CORE]);
-
-	clk_hw_unregister_fixed_factor(xvcu->pll_post);
+	if (!IS_ERR_OR_NULL(xvcu->pll_post))
+		clk_hw_unregister_fixed_factor(xvcu->pll_post);
 }
 
 /**
diff --git a/drivers/clocksource/i8253.c b/drivers/clocksource/i8253.c
index 39f7c2d736d1..b603c25f3dfa 100644
--- a/drivers/clocksource/i8253.c
+++ b/drivers/clocksource/i8253.c
@@ -103,7 +103,7 @@ int __init clocksource_i8253_init(void)
 #ifdef CONFIG_CLKEVT_I8253
 void clockevent_i8253_disable(void)
 {
-	raw_spin_lock(&i8253_lock);
+	guard(raw_spinlock_irqsave)(&i8253_lock);
 
 	/*
 	 * Writing the MODE register should stop the counter, according to
@@ -132,8 +132,6 @@ void clockevent_i8253_disable(void)
 	outb_p(0, PIT_CH0);
 
 	outb_p(0x30, PIT_MODE);
-
-	raw_spin_unlock(&i8253_lock);
 }
 
 static int pit_shutdown(struct clock_event_device *evt)
diff --git a/drivers/clocksource/jcore-pit.c b/drivers/clocksource/jcore-pit.c
index a3fe98cd3838..82815428f8f9 100644
--- a/drivers/clocksource/jcore-pit.c
+++ b/drivers/clocksource/jcore-pit.c
@@ -114,6 +114,18 @@ static int jcore_pit_local_init(unsigned cpu)
 	pit->periodic_delta = DIV_ROUND_CLOSEST(NSEC_PER_SEC, HZ * buspd);
 
 	clockevents_config_and_register(&pit->ced, freq, 1, ULONG_MAX);
+	enable_percpu_irq(pit->ced.irq, IRQ_TYPE_NONE);
+
+	return 0;
+}
+
+static int jcore_pit_local_teardown(unsigned cpu)
+{
+	struct jcore_pit *pit = this_cpu_ptr(jcore_pit_percpu);
+
+	pr_info("Local J-Core PIT teardown on cpu %u\n", cpu);
+
+	disable_percpu_irq(pit->ced.irq);
 
 	return 0;
 }
@@ -168,6 +180,7 @@ static int __init jcore_pit_init(struct device_node *node)
 		return -ENOMEM;
 	}
 
+	irq_set_percpu_devid(pit_irq);
 	err = request_percpu_irq(pit_irq, jcore_timer_interrupt,
 				 "jcore_pit", jcore_pit_percpu);
 	if (err) {
@@ -237,7 +250,7 @@ static int __init jcore_pit_init(struct device_node *node)
 
 	cpuhp_setup_state(CPUHP_AP_JCORE_TIMER_STARTING,
 			  "clockevents/jcore:starting",
-			  jcore_pit_local_init, NULL);
+			  jcore_pit_local_init, jcore_pit_local_teardown);
 
 	return 0;
 }
diff --git a/drivers/clocksource/mips-gic-timer.c b/drivers/clocksource/mips-gic-timer.c
index 110347707ff9..8592910710d1 100644
--- a/drivers/clocksource/mips-gic-timer.c
+++ b/drivers/clocksource/mips-gic-timer.c
@@ -115,6 +115,9 @@ static void gic_update_frequency(void *data)
 
 static int gic_starting_cpu(unsigned int cpu)
 {
+	/* Ensure the GIC counter is running */
+	clear_gic_config(GIC_CONFIG_COUNTSTOP);
+
 	gic_clockevent_cpu_init(cpu, this_cpu_ptr(&gic_clockevent_device));
 	return 0;
 }
@@ -252,9 +255,6 @@ static int __init gic_clocksource_of_init(struct device_node *node)
 			pr_warn("Unable to register clock notifier\n");
 	}
 
-	/* And finally start the counter */
-	clear_gic_config(GIC_CONFIG_COUNTSTOP);
-
 	/*
 	 * It's safe to use the MIPS GIC timer as a sched clock source only if
 	 * its ticks are stable, which is true on either the platforms with
diff --git a/drivers/clocksource/timer-riscv.c b/drivers/clocksource/timer-riscv.c
index 48ce50c5f5e6..4d7cf338824a 100644
--- a/drivers/clocksource/timer-riscv.c
+++ b/drivers/clocksource/timer-riscv.c
@@ -126,7 +126,13 @@ static int riscv_timer_starting_cpu(unsigned int cpu)
 
 static int riscv_timer_dying_cpu(unsigned int cpu)
 {
+	/*
+	 * Stop the timer when the cpu is going to be offline otherwise
+	 * the timer interrupt may be pending while performing power-down.
+	 */
+	riscv_clock_event_stop();
 	disable_percpu_irq(riscv_clock_event_irq);
+
 	return 0;
 }
 
diff --git a/drivers/clocksource/timer-stm32-lp.c b/drivers/clocksource/timer-stm32-lp.c
index a4c95161cb22..193e4f643358 100644
--- a/drivers/clocksource/timer-stm32-lp.c
+++ b/drivers/clocksource/timer-stm32-lp.c
@@ -168,9 +168,7 @@ static int stm32_clkevent_lp_probe(struct platform_device *pdev)
 	}
 
 	if (of_property_read_bool(pdev->dev.parent->of_node, "wakeup-source")) {
-		ret = device_init_wakeup(&pdev->dev, true);
-		if (ret)
-			goto out_clk_disable;
+		device_set_wakeup_capable(&pdev->dev, true);
 
 		ret = dev_pm_set_wake_irq(&pdev->dev, irq);
 		if (ret)
diff --git a/drivers/comedi/comedi_fops.c b/drivers/comedi/comedi_fops.c
index b9df9b19d4bd..bd8a44ea62d2 100644
--- a/drivers/comedi/comedi_fops.c
+++ b/drivers/comedi/comedi_fops.c
@@ -787,6 +787,7 @@ static int is_device_busy(struct comedi_device *dev)
 	struct comedi_subdevice *s;
 	int i;
 
+	lockdep_assert_held_write(&dev->attach_lock);
 	lockdep_assert_held(&dev->mutex);
 	if (!dev->attached)
 		return 0;
@@ -795,7 +796,16 @@ static int is_device_busy(struct comedi_device *dev)
 		s = &dev->subdevices[i];
 		if (s->busy)
 			return 1;
-		if (s->async && comedi_buf_is_mmapped(s))
+		if (!s->async)
+			continue;
+		if (comedi_buf_is_mmapped(s))
+			return 1;
+		/*
+		 * There may be tasks still waiting on the subdevice's wait
+		 * queue, although they should already be about to be removed
+		 * from it since the subdevice has no active async command.
+		 */
+		if (wq_has_sleeper(&s->async->wait_head))
 			return 1;
 	}
 
@@ -825,15 +835,22 @@ static int do_devconfig_ioctl(struct comedi_device *dev,
 		return -EPERM;
 
 	if (!arg) {
-		if (is_device_busy(dev))
-			return -EBUSY;
+		int rc = 0;
+
 		if (dev->attached) {
-			struct module *driver_module = dev->driver->module;
+			down_write(&dev->attach_lock);
+			if (is_device_busy(dev)) {
+				rc = -EBUSY;
+			} else {
+				struct module *driver_module =
+					dev->driver->module;
 
-			comedi_device_detach(dev);
-			module_put(driver_module);
+				comedi_device_detach_locked(dev);
+				module_put(driver_module);
+			}
+			up_write(&dev->attach_lock);
 		}
-		return 0;
+		return rc;
 	}
 
 	if (copy_from_user(&it, arg, sizeof(it)))
@@ -1556,21 +1573,27 @@ static int do_insnlist_ioctl(struct comedi_device *dev,
 	}
 
 	for (i = 0; i < n_insns; ++i) {
+		unsigned int n = insns[i].n;
+
 		if (insns[i].insn & INSN_MASK_WRITE) {
 			if (copy_from_user(data, insns[i].data,
-					   insns[i].n * sizeof(unsigned int))) {
+					   n * sizeof(unsigned int))) {
 				dev_dbg(dev->class_dev,
 					"copy_from_user failed\n");
 				ret = -EFAULT;
 				goto error;
 			}
+			if (n < MIN_SAMPLES) {
+				memset(&data[n], 0, (MIN_SAMPLES - n) *
+						    sizeof(unsigned int));
+			}
 		}
 		ret = parse_insn(dev, insns + i, data, file);
 		if (ret < 0)
 			goto error;
 		if (insns[i].insn & INSN_MASK_READ) {
 			if (copy_to_user(insns[i].data, data,
-					 insns[i].n * sizeof(unsigned int))) {
+					 n * sizeof(unsigned int))) {
 				dev_dbg(dev->class_dev,
 					"copy_to_user failed\n");
 				ret = -EFAULT;
@@ -1589,6 +1612,16 @@ error:
 	return i;
 }
 
+#define MAX_INSNS   MAX_SAMPLES
+static int check_insnlist_len(struct comedi_device *dev, unsigned int n_insns)
+{
+	if (n_insns > MAX_INSNS) {
+		dev_dbg(dev->class_dev, "insnlist length too large\n");
+		return -EINVAL;
+	}
+	return 0;
+}
+
 /*
  * COMEDI_INSN ioctl
  * synchronous instruction
@@ -1633,6 +1666,10 @@ static int do_insn_ioctl(struct comedi_device *dev,
 			ret = -EFAULT;
 			goto error;
 		}
+		if (insn->n < MIN_SAMPLES) {
+			memset(&data[insn->n], 0,
+			       (MIN_SAMPLES - insn->n) * sizeof(unsigned int));
+		}
 	}
 	ret = parse_insn(dev, insn, data, file);
 	if (ret < 0)
@@ -2239,6 +2276,9 @@ static long comedi_unlocked_ioctl(struct file *file, unsigned int cmd,
 			rc = -EFAULT;
 			break;
 		}
+		rc = check_insnlist_len(dev, insnlist.n_insns);
+		if (rc)
+			break;
 		insns = kcalloc(insnlist.n_insns, sizeof(*insns), GFP_KERNEL);
 		if (!insns) {
 			rc = -ENOMEM;
@@ -3090,6 +3130,9 @@ static int compat_insnlist(struct file *file, unsigned long arg)
 	if (copy_from_user(&insnlist32, compat_ptr(arg), sizeof(insnlist32)))
 		return -EFAULT;
 
+	rc = check_insnlist_len(dev, insnlist32.n_insns);
+	if (rc)
+		return rc;
 	insns = kcalloc(insnlist32.n_insns, sizeof(*insns), GFP_KERNEL);
 	if (!insns)
 		return -ENOMEM;
diff --git a/drivers/comedi/comedi_internal.h b/drivers/comedi/comedi_internal.h
index 9b3631a654c8..cf10ba016ebc 100644
--- a/drivers/comedi/comedi_internal.h
+++ b/drivers/comedi/comedi_internal.h
@@ -50,6 +50,7 @@ extern struct mutex comedi_drivers_list_lock;
 int insn_inval(struct comedi_device *dev, struct comedi_subdevice *s,
 	       struct comedi_insn *insn, unsigned int *data);
 
+void comedi_device_detach_locked(struct comedi_device *dev);
 void comedi_device_detach(struct comedi_device *dev);
 int comedi_device_attach(struct comedi_device *dev,
 			 struct comedi_devconfig *it);
diff --git a/drivers/comedi/drivers.c b/drivers/comedi/drivers.c
index 376130bfba8a..f1dc854928c1 100644
--- a/drivers/comedi/drivers.c
+++ b/drivers/comedi/drivers.c
@@ -158,7 +158,7 @@ static void comedi_device_detach_cleanup(struct comedi_device *dev)
 	int i;
 	struct comedi_subdevice *s;
 
-	lockdep_assert_held(&dev->attach_lock);
+	lockdep_assert_held_write(&dev->attach_lock);
 	lockdep_assert_held(&dev->mutex);
 	if (dev->subdevices) {
 		for (i = 0; i < dev->n_subdevices; i++) {
@@ -196,16 +196,23 @@ static void comedi_device_detach_cleanup(struct comedi_device *dev)
 	comedi_clear_hw_dev(dev);
 }
 
-void comedi_device_detach(struct comedi_device *dev)
+void comedi_device_detach_locked(struct comedi_device *dev)
 {
+	lockdep_assert_held_write(&dev->attach_lock);
 	lockdep_assert_held(&dev->mutex);
 	comedi_device_cancel_all(dev);
-	down_write(&dev->attach_lock);
 	dev->attached = false;
 	dev->detach_count++;
 	if (dev->driver)
 		dev->driver->detach(dev);
 	comedi_device_detach_cleanup(dev);
+}
+
+void comedi_device_detach(struct comedi_device *dev)
+{
+	lockdep_assert_held(&dev->mutex);
+	down_write(&dev->attach_lock);
+	comedi_device_detach_locked(dev);
 	up_write(&dev->attach_lock);
 }
 
@@ -339,10 +346,10 @@ int comedi_dio_insn_config(struct comedi_device *dev,
 			   unsigned int *data,
 			   unsigned int mask)
 {
-	unsigned int chan_mask = 1 << CR_CHAN(insn->chanspec);
+	unsigned int chan = CR_CHAN(insn->chanspec);
 
-	if (!mask)
-		mask = chan_mask;
+	if (!mask && chan < 32)
+		mask = 1U << chan;
 
 	switch (data[0]) {
 	case INSN_CONFIG_DIO_INPUT:
@@ -382,7 +389,7 @@ EXPORT_SYMBOL_GPL(comedi_dio_insn_config);
 unsigned int comedi_dio_update_state(struct comedi_subdevice *s,
 				     unsigned int *data)
 {
-	unsigned int chanmask = (s->n_chan < 32) ? ((1 << s->n_chan) - 1)
+	unsigned int chanmask = (s->n_chan < 32) ? ((1U << s->n_chan) - 1)
 						 : 0xffffffff;
 	unsigned int mask = data[0] & chanmask;
 	unsigned int bits = data[1];
@@ -615,6 +622,9 @@ static int insn_rw_emulate_bits(struct comedi_device *dev,
 	unsigned int _data[2];
 	int ret;
 
+	if (insn->n == 0)
+		return 0;
+
 	memset(_data, 0, sizeof(_data));
 	memset(&_insn, 0, sizeof(_insn));
 	_insn.insn = INSN_BITS;
@@ -625,8 +635,8 @@ static int insn_rw_emulate_bits(struct comedi_device *dev,
 	if (insn->insn == INSN_WRITE) {
 		if (!(s->subdev_flags & SDF_WRITABLE))
 			return -EINVAL;
-		_data[0] = 1 << (chan - base_chan);		    /* mask */
-		_data[1] = data[0] ? (1 << (chan - base_chan)) : 0; /* bits */
+		_data[0] = 1U << (chan - base_chan);		     /* mask */
+		_data[1] = data[0] ? (1U << (chan - base_chan)) : 0; /* bits */
 	}
 
 	ret = s->insn_bits(dev, s, &_insn, _data);
@@ -709,7 +719,7 @@ static int __comedi_device_postconfig(struct comedi_device *dev)
 
 		if (s->type == COMEDI_SUBD_DO) {
 			if (s->n_chan < 32)
-				s->io_bits = (1 << s->n_chan) - 1;
+				s->io_bits = (1U << s->n_chan) - 1;
 			else
 				s->io_bits = 0xffffffff;
 		}
diff --git a/drivers/comedi/drivers/aio_iiro_16.c b/drivers/comedi/drivers/aio_iiro_16.c
index b00fab0b89d4..739cc4db52ac 100644
--- a/drivers/comedi/drivers/aio_iiro_16.c
+++ b/drivers/comedi/drivers/aio_iiro_16.c
@@ -177,7 +177,8 @@ static int aio_iiro_16_attach(struct comedi_device *dev,
 	 * Digital input change of state interrupts are optionally supported
 	 * using IRQ 2-7, 10-12, 14, or 15.
 	 */
-	if ((1 << it->options[1]) & 0xdcfc) {
+	if (it->options[1] > 0 && it->options[1] < 16 &&
+	    (1 << it->options[1]) & 0xdcfc) {
 		ret = request_irq(it->options[1], aio_iiro_16_cos, 0,
 				  dev->board_name, dev);
 		if (ret == 0)
diff --git a/drivers/comedi/drivers/comedi_test.c b/drivers/comedi/drivers/comedi_test.c
index 05ae9122823f..e713ef611434 100644
--- a/drivers/comedi/drivers/comedi_test.c
+++ b/drivers/comedi/drivers/comedi_test.c
@@ -790,7 +790,7 @@ static void waveform_detach(struct comedi_device *dev)
 {
 	struct waveform_private *devpriv = dev->private;
 
-	if (devpriv) {
+	if (devpriv && dev->n_subdevices) {
 		del_timer_sync(&devpriv->ai_timer);
 		del_timer_sync(&devpriv->ao_timer);
 	}
diff --git a/drivers/comedi/drivers/das16m1.c b/drivers/comedi/drivers/das16m1.c
index b8ea737ad3d1..1b638f5b5a4f 100644
--- a/drivers/comedi/drivers/das16m1.c
+++ b/drivers/comedi/drivers/das16m1.c
@@ -522,7 +522,8 @@ static int das16m1_attach(struct comedi_device *dev,
 	devpriv->extra_iobase = dev->iobase + DAS16M1_8255_IOBASE;
 
 	/* only irqs 2, 3, 4, 5, 6, 7, 10, 11, 12, 14, and 15 are valid */
-	if ((1 << it->options[1]) & 0xdcfc) {
+	if (it->options[1] >= 2 && it->options[1] <= 15 &&
+	    (1 << it->options[1]) & 0xdcfc) {
 		ret = request_irq(it->options[1], das16m1_interrupt, 0,
 				  dev->board_name, dev);
 		if (ret == 0)
diff --git a/drivers/comedi/drivers/das6402.c b/drivers/comedi/drivers/das6402.c
index 68f95330de45..7660487e563c 100644
--- a/drivers/comedi/drivers/das6402.c
+++ b/drivers/comedi/drivers/das6402.c
@@ -567,7 +567,8 @@ static int das6402_attach(struct comedi_device *dev,
 	das6402_reset(dev);
 
 	/* IRQs 2,3,5,6,7, 10,11,15 are valid for "enhanced" mode */
-	if ((1 << it->options[1]) & 0x8cec) {
+	if (it->options[1] > 0 && it->options[1] < 16 &&
+	    (1 << it->options[1]) & 0x8cec) {
 		ret = request_irq(it->options[1], das6402_interrupt, 0,
 				  dev->board_name, dev);
 		if (ret == 0) {
diff --git a/drivers/comedi/drivers/jr3_pci.c b/drivers/comedi/drivers/jr3_pci.c
index 951c23fa0369..75dce1ff2419 100644
--- a/drivers/comedi/drivers/jr3_pci.c
+++ b/drivers/comedi/drivers/jr3_pci.c
@@ -758,7 +758,7 @@ static void jr3_pci_detach(struct comedi_device *dev)
 	struct jr3_pci_dev_private *devpriv = dev->private;
 
 	if (devpriv)
-		del_timer_sync(&devpriv->timer);
+		timer_shutdown_sync(&devpriv->timer);
 
 	comedi_pci_detach(dev);
 }
diff --git a/drivers/comedi/drivers/pcl812.c b/drivers/comedi/drivers/pcl812.c
index 0df639c6a595..abca61a72cf7 100644
--- a/drivers/comedi/drivers/pcl812.c
+++ b/drivers/comedi/drivers/pcl812.c
@@ -1149,7 +1149,8 @@ static int pcl812_attach(struct comedi_device *dev, struct comedi_devconfig *it)
 		if (IS_ERR(dev->pacer))
 			return PTR_ERR(dev->pacer);
 
-		if ((1 << it->options[1]) & board->irq_bits) {
+		if (it->options[1] > 0 && it->options[1] < 16 &&
+		    (1 << it->options[1]) & board->irq_bits) {
 			ret = request_irq(it->options[1], pcl812_interrupt, 0,
 					  dev->board_name, dev);
 			if (ret == 0)
diff --git a/drivers/counter/interrupt-cnt.c b/drivers/counter/interrupt-cnt.c
index 229473855c5b..bc762ba87a19 100644
--- a/drivers/counter/interrupt-cnt.c
+++ b/drivers/counter/interrupt-cnt.c
@@ -3,12 +3,14 @@
  * Copyright (c) 2021 Pengutronix, Oleksij Rempel <kernel@pengutronix.de>
  */
 
+#include <linux/cleanup.h>
 #include <linux/counter.h>
 #include <linux/gpio/consumer.h>
 #include <linux/interrupt.h>
 #include <linux/irq.h>
 #include <linux/mod_devicetable.h>
 #include <linux/module.h>
+#include <linux/mutex.h>
 #include <linux/platform_device.h>
 #include <linux/types.h>
 
@@ -19,6 +21,7 @@ struct interrupt_cnt_priv {
 	struct gpio_desc *gpio;
 	int irq;
 	bool enabled;
+	struct mutex lock;
 	struct counter_signal signals;
 	struct counter_synapse synapses;
 	struct counter_count cnts;
@@ -41,6 +44,8 @@ static int interrupt_cnt_enable_read(struct counter_device *counter,
 {
 	struct interrupt_cnt_priv *priv = counter_priv(counter);
 
+	guard(mutex)(&priv->lock);
+
 	*enable = priv->enabled;
 
 	return 0;
@@ -51,6 +56,8 @@ static int interrupt_cnt_enable_write(struct counter_device *counter,
 {
 	struct interrupt_cnt_priv *priv = counter_priv(counter);
 
+	guard(mutex)(&priv->lock);
+
 	if (priv->enabled == enable)
 		return 0;
 
@@ -227,6 +234,8 @@ static int interrupt_cnt_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
+	mutex_init(&priv->lock);
+
 	ret = devm_counter_add(dev, counter);
 	if (ret < 0)
 		return dev_err_probe(dev, ret, "Failed to add counter\n");
diff --git a/drivers/counter/microchip-tcb-capture.c b/drivers/counter/microchip-tcb-capture.c
index b3e615cbd2ca..461f57f66631 100644
--- a/drivers/counter/microchip-tcb-capture.c
+++ b/drivers/counter/microchip-tcb-capture.c
@@ -368,6 +368,25 @@ static int mchp_tc_probe(struct platform_device *pdev)
 			channel);
 	}
 
+	/* Disable Quadrature Decoder and position measure */
+	ret = regmap_update_bits(regmap, ATMEL_TC_BMR, ATMEL_TC_QDEN | ATMEL_TC_POSEN, 0);
+	if (ret)
+		return ret;
+
+	/* Setup the period capture mode */
+	ret = regmap_update_bits(regmap, ATMEL_TC_REG(priv->channel[0], CMR),
+				 ATMEL_TC_WAVE | ATMEL_TC_ABETRG | ATMEL_TC_CMR_MASK |
+				 ATMEL_TC_TCCLKS,
+				 ATMEL_TC_CMR_MASK);
+	if (ret)
+		return ret;
+
+	/* Enable clock and trigger counter */
+	ret = regmap_write(regmap, ATMEL_TC_REG(priv->channel[0], CCR),
+			   ATMEL_TC_CLKEN | ATMEL_TC_SWTRG);
+	if (ret)
+		return ret;
+
 	priv->tc_cfg = tcb_config;
 	priv->regmap = regmap;
 	counter->name = dev_name(&pdev->dev);
diff --git a/drivers/counter/stm32-lptimer-cnt.c b/drivers/counter/stm32-lptimer-cnt.c
index 8439755559b2..537fe9b669f3 100644
--- a/drivers/counter/stm32-lptimer-cnt.c
+++ b/drivers/counter/stm32-lptimer-cnt.c
@@ -58,37 +58,43 @@ static int stm32_lptim_set_enable_state(struct stm32_lptim_cnt *priv,
 		return 0;
 	}
 
+	ret = clk_enable(priv->clk);
+	if (ret)
+		goto disable_cnt;
+
 	/* LP timer must be enabled before writing CMP & ARR */
 	ret = regmap_write(priv->regmap, STM32_LPTIM_ARR, priv->ceiling);
 	if (ret)
-		return ret;
+		goto disable_clk;
 
 	ret = regmap_write(priv->regmap, STM32_LPTIM_CMP, 0);
 	if (ret)
-		return ret;
+		goto disable_clk;
 
 	/* ensure CMP & ARR registers are properly written */
 	ret = regmap_read_poll_timeout(priv->regmap, STM32_LPTIM_ISR, val,
 				       (val & STM32_LPTIM_CMPOK_ARROK) == STM32_LPTIM_CMPOK_ARROK,
 				       100, 1000);
 	if (ret)
-		return ret;
+		goto disable_clk;
 
 	ret = regmap_write(priv->regmap, STM32_LPTIM_ICR,
 			   STM32_LPTIM_CMPOKCF_ARROKCF);
 	if (ret)
-		return ret;
+		goto disable_clk;
 
-	ret = clk_enable(priv->clk);
-	if (ret) {
-		regmap_write(priv->regmap, STM32_LPTIM_CR, 0);
-		return ret;
-	}
 	priv->enabled = true;
 
 	/* Start LP timer in continuous mode */
 	return regmap_update_bits(priv->regmap, STM32_LPTIM_CR,
 				  STM32_LPTIM_CNTSTRT, STM32_LPTIM_CNTSTRT);
+
+disable_clk:
+	clk_disable(priv->clk);
+disable_cnt:
+	regmap_write(priv->regmap, STM32_LPTIM_CR, 0);
+
+	return ret;
 }
 
 static int stm32_lptim_setup(struct stm32_lptim_cnt *priv, int enable)
diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig
index 588ab1cc6d55..f089a1b9c0c9 100644
--- a/drivers/cpufreq/Kconfig
+++ b/drivers/cpufreq/Kconfig
@@ -218,7 +218,7 @@ config CPUFREQ_DT
 	  If in doubt, say N.
 
 config CPUFREQ_DT_PLATDEV
-	tristate "Generic DT based cpufreq platdev driver"
+	bool "Generic DT based cpufreq platdev driver"
 	depends on OF
 	help
 	  This adds a generic DT based cpufreq platdev driver for frequency
diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm
index 5f7e13e60c80..71f4b612dd97 100644
--- a/drivers/cpufreq/Kconfig.arm
+++ b/drivers/cpufreq/Kconfig.arm
@@ -67,7 +67,7 @@ config ARM_VEXPRESS_SPC_CPUFREQ
 config ARM_BRCMSTB_AVS_CPUFREQ
 	tristate "Broadcom STB AVS CPUfreq driver"
 	depends on (ARCH_BRCMSTB && !ARM_SCMI_CPUFREQ) || COMPILE_TEST
-	default y
+	default y if ARCH_BRCMSTB && !ARM_SCMI_CPUFREQ
 	help
 	  Some Broadcom STB SoCs use a co-processor running proprietary firmware
 	  ("AVS") to handle voltage and frequency scaling. This driver provides
@@ -79,7 +79,7 @@ config ARM_HIGHBANK_CPUFREQ
 	tristate "Calxeda Highbank-based"
 	depends on ARCH_HIGHBANK || COMPILE_TEST
 	depends on CPUFREQ_DT && REGULATOR && PL320_MBOX
-	default m
+	default m if ARCH_HIGHBANK
 	help
 	  This adds the CPUFreq driver for Calxeda Highbank SoC
 	  based boards.
@@ -124,7 +124,7 @@ config ARM_MEDIATEK_CPUFREQ
 config ARM_MEDIATEK_CPUFREQ_HW
 	tristate "MediaTek CPUFreq HW driver"
 	depends on ARCH_MEDIATEK || COMPILE_TEST
-	default m
+	default m if ARCH_MEDIATEK
 	help
 	  Support for the CPUFreq HW driver.
 	  Some MediaTek chipsets have a HW engine to offload the steps
@@ -172,7 +172,7 @@ config ARM_RASPBERRYPI_CPUFREQ
 config ARM_S3C64XX_CPUFREQ
 	bool "Samsung S3C64XX"
 	depends on CPU_S3C6410 || COMPILE_TEST
-	default y
+	default CPU_S3C6410
 	help
 	  This adds the CPUFreq driver for Samsung S3C6410 SoC.
 
@@ -181,7 +181,7 @@ config ARM_S3C64XX_CPUFREQ
 config ARM_S5PV210_CPUFREQ
 	bool "Samsung S5PV210 and S5PC110"
 	depends on CPU_S5PV210 || COMPILE_TEST
-	default y
+	default CPU_S5PV210
 	help
 	  This adds the CPUFreq driver for Samsung S5PV210 and
 	  S5PC110 SoCs.
@@ -205,7 +205,7 @@ config ARM_SCMI_CPUFREQ
 config ARM_SPEAR_CPUFREQ
 	bool "SPEAr CPUFreq support"
 	depends on PLAT_SPEAR || COMPILE_TEST
-	default y
+	default PLAT_SPEAR
 	help
 	  This adds the CPUFreq driver support for SPEAr SOCs.
 
@@ -224,7 +224,7 @@ config ARM_TEGRA20_CPUFREQ
 	tristate "Tegra20/30 CPUFreq support"
 	depends on ARCH_TEGRA || COMPILE_TEST
 	depends on CPUFREQ_DT
-	default y
+	default ARCH_TEGRA
 	help
 	  This adds the CPUFreq driver support for Tegra20/30 SOCs.
 
@@ -232,7 +232,7 @@ config ARM_TEGRA124_CPUFREQ
 	bool "Tegra124 CPUFreq support"
 	depends on ARCH_TEGRA || COMPILE_TEST
 	depends on CPUFREQ_DT
-	default y
+	default ARCH_TEGRA
 	help
 	  This adds the CPUFreq driver support for Tegra124 SOCs.
 
@@ -245,16 +245,16 @@ config ARM_TEGRA186_CPUFREQ
 
 config ARM_TEGRA194_CPUFREQ
 	tristate "Tegra194 CPUFreq support"
-	depends on ARCH_TEGRA_194_SOC || (64BIT && COMPILE_TEST)
+	depends on ARCH_TEGRA_194_SOC || ARCH_TEGRA_234_SOC || (64BIT && COMPILE_TEST)
 	depends on TEGRA_BPMP
-	default y
+	default ARCH_TEGRA_194_SOC || ARCH_TEGRA_234_SOC
 	help
 	  This adds CPU frequency driver support for Tegra194 SOCs.
 
 config ARM_TI_CPUFREQ
 	bool "Texas Instruments CPUFreq support"
 	depends on ARCH_OMAP2PLUS || ARCH_K3 || COMPILE_TEST
-	default y
+	default ARCH_OMAP2PLUS || ARCH_K3
 	help
 	  This driver enables valid OPPs on the running platform based on
 	  values contained within the SoC in use. Enable this in order to
diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c
index 0f04feb6cafa..0f1679817682 100644
--- a/drivers/cpufreq/acpi-cpufreq.c
+++ b/drivers/cpufreq/acpi-cpufreq.c
@@ -626,7 +626,14 @@ static int acpi_cpufreq_blacklist(struct cpuinfo_x86 *c)
 #endif
 
 #ifdef CONFIG_ACPI_CPPC_LIB
-static u64 get_max_boost_ratio(unsigned int cpu)
+/*
+ * get_max_boost_ratio: Computes the max_boost_ratio as the ratio
+ * between the highest_perf and the nominal_perf.
+ *
+ * Returns the max_boost_ratio for @cpu. Returns the CPPC nominal
+ * frequency via @nominal_freq if it is non-NULL pointer.
+ */
+static u64 get_max_boost_ratio(unsigned int cpu, u64 *nominal_freq)
 {
 	struct cppc_perf_caps perf_caps;
 	u64 highest_perf, nominal_perf;
@@ -655,6 +662,9 @@ static u64 get_max_boost_ratio(unsigned int cpu)
 
 	nominal_perf = perf_caps.nominal_perf;
 
+	if (nominal_freq)
+		*nominal_freq = perf_caps.nominal_freq * 1000;
+
 	if (!highest_perf || !nominal_perf) {
 		pr_debug("CPU%d: highest or nominal performance missing\n", cpu);
 		return 0;
@@ -667,8 +677,12 @@ static u64 get_max_boost_ratio(unsigned int cpu)
 
 	return div_u64(highest_perf << SCHED_CAPACITY_SHIFT, nominal_perf);
 }
+
 #else
-static inline u64 get_max_boost_ratio(unsigned int cpu) { return 0; }
+static inline u64 get_max_boost_ratio(unsigned int cpu, u64 *nominal_freq)
+{
+	return 0;
+}
 #endif
 
 static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
@@ -678,9 +692,9 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	struct acpi_cpufreq_data *data;
 	unsigned int cpu = policy->cpu;
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
+	u64 max_boost_ratio, nominal_freq = 0;
 	unsigned int valid_states = 0;
 	unsigned int result = 0;
-	u64 max_boost_ratio;
 	unsigned int i;
 #ifdef CONFIG_SMP
 	static int blacklisted;
@@ -830,16 +844,20 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	}
 	freq_table[valid_states].frequency = CPUFREQ_TABLE_END;
 
-	max_boost_ratio = get_max_boost_ratio(cpu);
+	max_boost_ratio = get_max_boost_ratio(cpu, &nominal_freq);
 	if (max_boost_ratio) {
-		unsigned int freq = freq_table[0].frequency;
+		unsigned int freq = nominal_freq;
 
 		/*
-		 * Because the loop above sorts the freq_table entries in the
-		 * descending order, freq is the maximum frequency in the table.
-		 * Assume that it corresponds to the CPPC nominal frequency and
-		 * use it to set cpuinfo.max_freq.
+		 * The loop above sorts the freq_table entries in the
+		 * descending order. If ACPI CPPC has not advertised
+		 * the nominal frequency (this is possible in CPPC
+		 * revisions prior to 3), then use the first entry in
+		 * the pstate table as a proxy for nominal frequency.
 		 */
+		if (!freq)
+			freq = freq_table[0].frequency;
+
 		policy->cpuinfo.max_freq = freq * max_boost_ratio >> SCHED_CAPACITY_SHIFT;
 	} else {
 		/*
diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
index 91d3c3b1c2d3..62dbc5701e99 100644
--- a/drivers/cpufreq/amd-pstate.c
+++ b/drivers/cpufreq/amd-pstate.c
@@ -482,6 +482,9 @@ static void amd_pstate_update(struct amd_cpudata *cpudata, u32 min_perf,
 	u32 nominal_perf = READ_ONCE(cpudata->nominal_perf);
 	u64 value = prev;
 
+	if (!policy)
+		return;
+
 	min_perf = clamp_t(unsigned long, min_perf, cpudata->min_limit_perf,
 			cpudata->max_limit_perf);
 	max_perf = clamp_t(unsigned long, max_perf, cpudata->min_limit_perf,
@@ -696,12 +699,11 @@ static int amd_pstate_set_boost(struct cpufreq_policy *policy, int state)
 		pr_err("Boost mode is not supported by this processor or SBIOS\n");
 		return -EOPNOTSUPP;
 	}
-	mutex_lock(&amd_pstate_driver_lock);
+
 	ret = amd_pstate_cpu_boost_update(policy, state);
 	WRITE_ONCE(cpudata->boost_state, !ret ? state : false);
 	policy->boost_enabled = !ret ? state : false;
 	refresh_frequency_limits(policy);
-	mutex_unlock(&amd_pstate_driver_lock);
 
 	return ret;
 }
@@ -778,24 +780,28 @@ static void amd_pstate_init_prefcore(struct amd_cpudata *cpudata)
 
 static void amd_pstate_update_limits(unsigned int cpu)
 {
-	struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
+	struct cpufreq_policy *policy = NULL;
 	struct amd_cpudata *cpudata;
 	u32 prev_high = 0, cur_high = 0;
 	int ret;
 	bool highest_perf_changed = false;
 
+	if (!amd_pstate_prefcore)
+		return;
+
+	policy = cpufreq_cpu_get(cpu);
 	if (!policy)
 		return;
 
 	cpudata = policy->driver_data;
 
-	if (!amd_pstate_prefcore)
-		return;
+	guard(mutex)(&amd_pstate_driver_lock);
 
-	mutex_lock(&amd_pstate_driver_lock);
 	ret = amd_get_highest_perf(cpu, &cur_high);
-	if (ret)
-		goto free_cpufreq_put;
+	if (ret) {
+		cpufreq_cpu_put(policy);
+		return;
+	}
 
 	prev_high = READ_ONCE(cpudata->prefcore_ranking);
 	highest_perf_changed = (prev_high != cur_high);
@@ -805,14 +811,11 @@ static void amd_pstate_update_limits(unsigned int cpu)
 		if (cur_high < CPPC_MAX_PERF)
 			sched_set_itmt_core_prio((int)cur_high, cpu);
 	}
-
-free_cpufreq_put:
 	cpufreq_cpu_put(policy);
 
 	if (!highest_perf_changed)
 		cpufreq_update_policy(cpu);
 
-	mutex_unlock(&amd_pstate_driver_lock);
 }
 
 /*
@@ -1145,11 +1148,11 @@ static ssize_t store_energy_performance_preference(
 	if (ret < 0)
 		return -EINVAL;
 
-	mutex_lock(&amd_pstate_limits_lock);
+	guard(mutex)(&amd_pstate_limits_lock);
+
 	ret = amd_pstate_set_energy_pref_index(cpudata, ret);
-	mutex_unlock(&amd_pstate_limits_lock);
 
-	return ret ?: count;
+	return ret ? ret : count;
 }
 
 static ssize_t show_energy_performance_preference(
@@ -1297,13 +1300,10 @@ EXPORT_SYMBOL_GPL(amd_pstate_update_status);
 static ssize_t status_show(struct device *dev,
 			   struct device_attribute *attr, char *buf)
 {
-	ssize_t ret;
 
-	mutex_lock(&amd_pstate_driver_lock);
-	ret = amd_pstate_show_status(buf);
-	mutex_unlock(&amd_pstate_driver_lock);
+	guard(mutex)(&amd_pstate_driver_lock);
 
-	return ret;
+	return amd_pstate_show_status(buf);
 }
 
 static ssize_t status_store(struct device *a, struct device_attribute *b,
@@ -1312,9 +1312,8 @@ static ssize_t status_store(struct device *a, struct device_attribute *b,
 	char *p = memchr(buf, '\n', count);
 	int ret;
 
-	mutex_lock(&amd_pstate_driver_lock);
+	guard(mutex)(&amd_pstate_driver_lock);
 	ret = amd_pstate_update_status(buf, p ? p - buf : count);
-	mutex_unlock(&amd_pstate_driver_lock);
 
 	return ret < 0 ? ret : count;
 }
@@ -1579,24 +1578,17 @@ static int amd_pstate_epp_set_policy(struct cpufreq_policy *policy)
 
 static void amd_pstate_epp_reenable(struct amd_cpudata *cpudata)
 {
-	struct cppc_perf_ctrls perf_ctrls;
-	u64 value, max_perf;
+	u64 max_perf;
 	int ret;
 
 	ret = amd_pstate_enable(true);
 	if (ret)
 		pr_err("failed to enable amd pstate during resume, return %d\n", ret);
 
-	value = READ_ONCE(cpudata->cppc_req_cached);
 	max_perf = READ_ONCE(cpudata->highest_perf);
 
-	if (cpu_feature_enabled(X86_FEATURE_CPPC)) {
-		wrmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, value);
-	} else {
-		perf_ctrls.max_perf = max_perf;
-		perf_ctrls.energy_perf = AMD_CPPC_ENERGY_PERF_PREF(cpudata->epp_cached);
-		cppc_set_perf(cpudata->cpu, &perf_ctrls);
-	}
+	amd_pstate_update_perf(cpudata, 0, 0, max_perf, false);
+	amd_pstate_set_epp(cpudata, cpudata->epp_cached);
 }
 
 static int amd_pstate_epp_cpu_online(struct cpufreq_policy *policy)
@@ -1605,54 +1597,26 @@ static int amd_pstate_epp_cpu_online(struct cpufreq_policy *policy)
 
 	pr_debug("AMD CPU Core %d going online\n", cpudata->cpu);
 
-	if (cppc_state == AMD_PSTATE_ACTIVE) {
-		amd_pstate_epp_reenable(cpudata);
-		cpudata->suspended = false;
-	}
+	amd_pstate_epp_reenable(cpudata);
+	cpudata->suspended = false;
 
 	return 0;
 }
 
-static void amd_pstate_epp_offline(struct cpufreq_policy *policy)
-{
-	struct amd_cpudata *cpudata = policy->driver_data;
-	struct cppc_perf_ctrls perf_ctrls;
-	int min_perf;
-	u64 value;
-
-	min_perf = READ_ONCE(cpudata->lowest_perf);
-	value = READ_ONCE(cpudata->cppc_req_cached);
-
-	mutex_lock(&amd_pstate_limits_lock);
-	if (cpu_feature_enabled(X86_FEATURE_CPPC)) {
-		cpudata->epp_policy = CPUFREQ_POLICY_UNKNOWN;
-
-		/* Set max perf same as min perf */
-		value &= ~AMD_CPPC_MAX_PERF(~0L);
-		value |= AMD_CPPC_MAX_PERF(min_perf);
-		value &= ~AMD_CPPC_MIN_PERF(~0L);
-		value |= AMD_CPPC_MIN_PERF(min_perf);
-		wrmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, value);
-	} else {
-		perf_ctrls.desired_perf = 0;
-		perf_ctrls.max_perf = min_perf;
-		perf_ctrls.energy_perf = AMD_CPPC_ENERGY_PERF_PREF(HWP_EPP_BALANCE_POWERSAVE);
-		cppc_set_perf(cpudata->cpu, &perf_ctrls);
-	}
-	mutex_unlock(&amd_pstate_limits_lock);
-}
-
 static int amd_pstate_epp_cpu_offline(struct cpufreq_policy *policy)
 {
 	struct amd_cpudata *cpudata = policy->driver_data;
-
-	pr_debug("AMD CPU Core %d going offline\n", cpudata->cpu);
+	int min_perf;
 
 	if (cpudata->suspended)
 		return 0;
 
-	if (cppc_state == AMD_PSTATE_ACTIVE)
-		amd_pstate_epp_offline(policy);
+	min_perf = READ_ONCE(cpudata->lowest_perf);
+
+	guard(mutex)(&amd_pstate_limits_lock);
+
+	amd_pstate_update_perf(cpudata, min_perf, 0, min_perf, false);
+	amd_pstate_set_epp(cpudata, AMD_CPPC_EPP_BALANCE_POWERSAVE);
 
 	return 0;
 }
@@ -1689,13 +1653,11 @@ static int amd_pstate_epp_resume(struct cpufreq_policy *policy)
 	struct amd_cpudata *cpudata = policy->driver_data;
 
 	if (cpudata->suspended) {
-		mutex_lock(&amd_pstate_limits_lock);
+		guard(mutex)(&amd_pstate_limits_lock);
 
 		/* enable amd pstate from suspend state*/
 		amd_pstate_epp_reenable(cpudata);
 
-		mutex_unlock(&amd_pstate_limits_lock);
-
 		cpudata->suspended = false;
 	}
 
diff --git a/drivers/cpufreq/apple-soc-cpufreq.c b/drivers/cpufreq/apple-soc-cpufreq.c
index 4dcacab9b4bf..ddf7dcb3e9b0 100644
--- a/drivers/cpufreq/apple-soc-cpufreq.c
+++ b/drivers/cpufreq/apple-soc-cpufreq.c
@@ -103,11 +103,17 @@ static const struct of_device_id apple_soc_cpufreq_of_match[] __maybe_unused = {
 
 static unsigned int apple_soc_cpufreq_get_rate(unsigned int cpu)
 {
-	struct cpufreq_policy *policy = cpufreq_cpu_get_raw(cpu);
-	struct apple_cpu_priv *priv = policy->driver_data;
+	struct cpufreq_policy *policy;
+	struct apple_cpu_priv *priv;
 	struct cpufreq_frequency_table *p;
 	unsigned int pstate;
 
+	policy = cpufreq_cpu_get_raw(cpu);
+	if (unlikely(!policy))
+		return 0;
+
+	priv = policy->driver_data;
+
 	if (priv->info->cur_pstate_mask) {
 		u64 reg = readq_relaxed(priv->reg_base + APPLE_DVFS_STATUS);
 
diff --git a/drivers/cpufreq/armada-8k-cpufreq.c b/drivers/cpufreq/armada-8k-cpufreq.c
index 7a979db81f09..ccbc826cc4c0 100644
--- a/drivers/cpufreq/armada-8k-cpufreq.c
+++ b/drivers/cpufreq/armada-8k-cpufreq.c
@@ -132,7 +132,7 @@ static int __init armada_8k_cpufreq_init(void)
 	int ret = 0, opps_index = 0, cpu, nb_cpus;
 	struct freq_table *freq_tables;
 	struct device_node *node;
-	static struct cpumask cpus;
+	static struct cpumask cpus, shared_cpus;
 
 	node = of_find_matching_node_and_match(NULL, armada_8k_cpufreq_of_match,
 					       NULL);
@@ -154,7 +154,6 @@ static int __init armada_8k_cpufreq_init(void)
 	 * divisions of it).
 	 */
 	for_each_cpu(cpu, &cpus) {
-		struct cpumask shared_cpus;
 		struct device *cpu_dev;
 		struct clk *clk;
 
diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c
index c1cdf0f4d0dd..8d5279c21e6c 100644
--- a/drivers/cpufreq/cppc_cpufreq.c
+++ b/drivers/cpufreq/cppc_cpufreq.c
@@ -767,7 +767,7 @@ static unsigned int cppc_cpufreq_get_rate(unsigned int cpu)
 	int ret;
 
 	if (!policy)
-		return -ENODEV;
+		return 0;
 
 	cpu_data = policy->driver_data;
 
@@ -841,7 +841,7 @@ static struct freq_attr *cppc_cpufreq_attr[] = {
 };
 
 static struct cpufreq_driver cppc_cpufreq_driver = {
-	.flags = CPUFREQ_CONST_LOOPS,
+	.flags = CPUFREQ_CONST_LOOPS | CPUFREQ_NEED_UPDATE_LIMITS,
 	.verify = cppc_verify_policy,
 	.target = cppc_cpufreq_set_target,
 	.get = cppc_cpufreq_get_rate,
diff --git a/drivers/cpufreq/cpufreq-dt-platdev.c b/drivers/cpufreq/cpufreq-dt-platdev.c
index 18942bfe9c95..67bac12d4d55 100644
--- a/drivers/cpufreq/cpufreq-dt-platdev.c
+++ b/drivers/cpufreq/cpufreq-dt-platdev.c
@@ -172,6 +172,7 @@ static const struct of_device_id blocklist[] __initconst = {
 	{ .compatible = "qcom,sm8350", },
 	{ .compatible = "qcom,sm8450", },
 	{ .compatible = "qcom,sm8550", },
+	{ .compatible = "qcom,sm8650", },
 
 	{ .compatible = "st,stih407", },
 	{ .compatible = "st,stih410", },
@@ -234,5 +235,3 @@ create_pdev:
 			       sizeof(struct cpufreq_dt_platform_data)));
 }
 core_initcall(cpufreq_dt_platdev_init);
-MODULE_DESCRIPTION("Generic DT based cpufreq platdev driver");
-MODULE_LICENSE("GPL");
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index f98c9438760c..bd55c2356303 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -534,16 +534,18 @@ void cpufreq_disable_fast_switch(struct cpufreq_policy *policy)
 EXPORT_SYMBOL_GPL(cpufreq_disable_fast_switch);
 
 static unsigned int __resolve_freq(struct cpufreq_policy *policy,
-		unsigned int target_freq, unsigned int relation)
+				   unsigned int target_freq,
+				   unsigned int min, unsigned int max,
+				   unsigned int relation)
 {
 	unsigned int idx;
 
-	target_freq = clamp_val(target_freq, policy->min, policy->max);
+	target_freq = clamp_val(target_freq, min, max);
 
 	if (!policy->freq_table)
 		return target_freq;
 
-	idx = cpufreq_frequency_table_target(policy, target_freq, relation);
+	idx = cpufreq_frequency_table_target(policy, target_freq, min, max, relation);
 	policy->cached_resolved_idx = idx;
 	policy->cached_target_freq = target_freq;
 	return policy->freq_table[idx].frequency;
@@ -563,7 +565,21 @@ static unsigned int __resolve_freq(struct cpufreq_policy *policy,
 unsigned int cpufreq_driver_resolve_freq(struct cpufreq_policy *policy,
 					 unsigned int target_freq)
 {
-	return __resolve_freq(policy, target_freq, CPUFREQ_RELATION_LE);
+	unsigned int min = READ_ONCE(policy->min);
+	unsigned int max = READ_ONCE(policy->max);
+
+	/*
+	 * If this function runs in parallel with cpufreq_set_policy(), it may
+	 * read policy->min before the update and policy->max after the update
+	 * or the other way around, so there is no ordering guarantee.
+	 *
+	 * Resolve this by always honoring the max (in case it comes from
+	 * thermal throttling or similar).
+	 */
+	if (unlikely(min > max))
+		min = max;
+
+	return __resolve_freq(policy, target_freq, min, max, CPUFREQ_RELATION_LE);
 }
 EXPORT_SYMBOL_GPL(cpufreq_driver_resolve_freq);
 
@@ -1259,6 +1275,8 @@ static struct cpufreq_policy *cpufreq_policy_alloc(unsigned int cpu)
 		goto err_free_real_cpus;
 	}
 
+	init_rwsem(&policy->rwsem);
+
 	freq_constraints_init(&policy->constraints);
 
 	policy->nb_min.notifier_call = cpufreq_notifier_min;
@@ -1281,7 +1299,6 @@ static struct cpufreq_policy *cpufreq_policy_alloc(unsigned int cpu)
 	}
 
 	INIT_LIST_HEAD(&policy->policy_list);
-	init_rwsem(&policy->rwsem);
 	spin_lock_init(&policy->transition_lock);
 	init_waitqueue_head(&policy->transition_wait);
 	INIT_WORK(&policy->update, handle_update);
@@ -2323,7 +2340,8 @@ int __cpufreq_driver_target(struct cpufreq_policy *policy,
 	if (cpufreq_disabled())
 		return -ENODEV;
 
-	target_freq = __resolve_freq(policy, target_freq, relation);
+	target_freq = __resolve_freq(policy, target_freq, policy->min,
+				     policy->max, relation);
 
 	pr_debug("target for CPU %u: %u kHz, relation %u, requested %u kHz\n",
 		 policy->cpu, target_freq, relation, old_target_freq);
@@ -2647,11 +2665,18 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
 	 * Resolve policy min/max to available frequencies. It ensures
 	 * no frequency resolution will neither overshoot the requested maximum
 	 * nor undershoot the requested minimum.
+	 *
+	 * Avoid storing intermediate values in policy->max or policy->min and
+	 * compiler optimizations around them because they may be accessed
+	 * concurrently by cpufreq_driver_resolve_freq() during the update.
 	 */
-	policy->min = new_data.min;
-	policy->max = new_data.max;
-	policy->min = __resolve_freq(policy, policy->min, CPUFREQ_RELATION_L);
-	policy->max = __resolve_freq(policy, policy->max, CPUFREQ_RELATION_H);
+	WRITE_ONCE(policy->max, __resolve_freq(policy, new_data.max,
+					       new_data.min, new_data.max,
+					       CPUFREQ_RELATION_H));
+	new_data.min = __resolve_freq(policy, new_data.min, new_data.min,
+				      new_data.max, CPUFREQ_RELATION_L);
+	WRITE_ONCE(policy->min, new_data.min > policy->max ? policy->max : new_data.min);
+
 	trace_cpu_frequency_limits(policy);
 
 	cpufreq_update_pressure(policy);
@@ -2699,10 +2724,12 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
 	pr_debug("starting governor %s failed\n", policy->governor->name);
 	if (old_gov) {
 		policy->governor = old_gov;
-		if (cpufreq_init_governor(policy))
+		if (cpufreq_init_governor(policy)) {
+			policy->governor = NULL;
+		} else if (cpufreq_start_governor(policy)) {
+			cpufreq_exit_governor(policy);
 			policy->governor = NULL;
-		else
-			cpufreq_start_governor(policy);
+		}
 	}
 
 	return ret;
@@ -2748,10 +2775,18 @@ EXPORT_SYMBOL(cpufreq_update_policy);
  */
 void cpufreq_update_limits(unsigned int cpu)
 {
+	struct cpufreq_policy *policy;
+
+	policy = cpufreq_cpu_get(cpu);
+	if (!policy)
+		return;
+
 	if (cpufreq_driver->update_limits)
 		cpufreq_driver->update_limits(cpu);
 	else
 		cpufreq_update_policy(cpu);
+
+	cpufreq_cpu_put(policy);
 }
 EXPORT_SYMBOL_GPL(cpufreq_update_limits);
 
@@ -2929,15 +2964,6 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data)
 	cpufreq_driver = driver_data;
 	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
 
-	/*
-	 * Mark support for the scheduler's frequency invariance engine for
-	 * drivers that implement target(), target_index() or fast_switch().
-	 */
-	if (!cpufreq_driver->setpolicy) {
-		static_branch_enable_cpuslocked(&cpufreq_freq_invariance);
-		pr_debug("supports frequency invariance");
-	}
-
 	if (driver_data->setpolicy)
 		driver_data->flags |= CPUFREQ_CONST_LOOPS;
 
@@ -2968,6 +2994,15 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data)
 	hp_online = ret;
 	ret = 0;
 
+	/*
+	 * Mark support for the scheduler's frequency invariance engine for
+	 * drivers that implement target(), target_index() or fast_switch().
+	 */
+	if (!cpufreq_driver->setpolicy) {
+		static_branch_enable_cpuslocked(&cpufreq_freq_invariance);
+		pr_debug("supports frequency invariance");
+	}
+
 	pr_debug("driver %s up and running\n", driver_data->name);
 	goto out;
 
diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c
index af44ee6a6430..1a7fcaf39cc9 100644
--- a/drivers/cpufreq/cpufreq_governor.c
+++ b/drivers/cpufreq/cpufreq_governor.c
@@ -145,7 +145,23 @@ unsigned int dbs_update(struct cpufreq_policy *policy)
 		time_elapsed = update_time - j_cdbs->prev_update_time;
 		j_cdbs->prev_update_time = update_time;
 
-		idle_time = cur_idle_time - j_cdbs->prev_cpu_idle;
+		/*
+		 * cur_idle_time could be smaller than j_cdbs->prev_cpu_idle if
+		 * it's obtained from get_cpu_idle_time_jiffy() when NOHZ is
+		 * off, where idle_time is calculated by the difference between
+		 * time elapsed in jiffies and "busy time" obtained from CPU
+		 * statistics.  If a CPU is 100% busy, the time elapsed and busy
+		 * time should grow with the same amount in two consecutive
+		 * samples, but in practice there could be a tiny difference,
+		 * making the accumulated idle time decrease sometimes.  Hence,
+		 * in this case, idle_time should be regarded as 0 in order to
+		 * make the further process correct.
+		 */
+		if (cur_idle_time > j_cdbs->prev_cpu_idle)
+			idle_time = cur_idle_time - j_cdbs->prev_cpu_idle;
+		else
+			idle_time = 0;
+
 		j_cdbs->prev_cpu_idle = cur_idle_time;
 
 		if (ignore_nice) {
@@ -162,7 +178,7 @@ unsigned int dbs_update(struct cpufreq_policy *policy)
 			 * calls, so the previous load value can be used then.
 			 */
 			load = j_cdbs->prev_load;
-		} else if (unlikely((int)idle_time > 2 * sampling_rate &&
+		} else if (unlikely(idle_time > 2 * sampling_rate &&
 				    j_cdbs->prev_load)) {
 			/*
 			 * If the CPU had gone completely idle and a task has
@@ -189,30 +205,15 @@ unsigned int dbs_update(struct cpufreq_policy *policy)
 			load = j_cdbs->prev_load;
 			j_cdbs->prev_load = 0;
 		} else {
-			if (time_elapsed >= idle_time) {
+			if (time_elapsed > idle_time)
 				load = 100 * (time_elapsed - idle_time) / time_elapsed;
-			} else {
-				/*
-				 * That can happen if idle_time is returned by
-				 * get_cpu_idle_time_jiffy().  In that case
-				 * idle_time is roughly equal to the difference
-				 * between time_elapsed and "busy time" obtained
-				 * from CPU statistics.  Then, the "busy time"
-				 * can end up being greater than time_elapsed
-				 * (for example, if jiffies_64 and the CPU
-				 * statistics are updated by different CPUs),
-				 * so idle_time may in fact be negative.  That
-				 * means, though, that the CPU was busy all
-				 * the time (on the rough average) during the
-				 * last sampling interval and 100 can be
-				 * returned as the load.
-				 */
-				load = (int)idle_time < 0 ? 100 : 0;
-			}
+			else
+				load = 0;
+
 			j_cdbs->prev_load = load;
 		}
 
-		if (unlikely((int)idle_time > 2 * sampling_rate)) {
+		if (unlikely(idle_time > 2 * sampling_rate)) {
 			unsigned int periods = idle_time / sampling_rate;
 
 			if (periods < idle_periods)
diff --git a/drivers/cpufreq/cpufreq_ondemand.c b/drivers/cpufreq/cpufreq_ondemand.c
index a7c38b8b3e78..0e65d37c9231 100644
--- a/drivers/cpufreq/cpufreq_ondemand.c
+++ b/drivers/cpufreq/cpufreq_ondemand.c
@@ -76,7 +76,8 @@ static unsigned int generic_powersave_bias_target(struct cpufreq_policy *policy,
 		return freq_next;
 	}
 
-	index = cpufreq_frequency_table_target(policy, freq_next, relation);
+	index = cpufreq_frequency_table_target(policy, freq_next, policy->min,
+					       policy->max, relation);
 	freq_req = freq_table[index].frequency;
 	freq_reduc = freq_req * od_tuners->powersave_bias / 1000;
 	freq_avg = freq_req - freq_reduc;
diff --git a/drivers/cpufreq/freq_table.c b/drivers/cpufreq/freq_table.c
index 10e80d912b8d..178e17009a16 100644
--- a/drivers/cpufreq/freq_table.c
+++ b/drivers/cpufreq/freq_table.c
@@ -116,8 +116,8 @@ int cpufreq_generic_frequency_table_verify(struct cpufreq_policy_data *policy)
 EXPORT_SYMBOL_GPL(cpufreq_generic_frequency_table_verify);
 
 int cpufreq_table_index_unsorted(struct cpufreq_policy *policy,
-				 unsigned int target_freq,
-				 unsigned int relation)
+				 unsigned int target_freq, unsigned int min,
+				 unsigned int max, unsigned int relation)
 {
 	struct cpufreq_frequency_table optimal = {
 		.driver_data = ~0,
@@ -148,7 +148,7 @@ int cpufreq_table_index_unsorted(struct cpufreq_policy *policy,
 	cpufreq_for_each_valid_entry_idx(pos, table, i) {
 		freq = pos->frequency;
 
-		if ((freq < policy->min) || (freq > policy->max))
+		if (freq < min || freq > max)
 			continue;
 		if (freq == target_freq) {
 			optimal.driver_data = i;
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 400337f3b572..e90871092038 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -600,6 +600,9 @@ static bool turbo_is_disabled(void)
 {
 	u64 misc_en;
 
+	if (!cpu_feature_enabled(X86_FEATURE_IDA))
+		return true;
+
 	rdmsrl(MSR_IA32_MISC_ENABLE, misc_en);
 
 	return !!(misc_en & MSR_IA32_MISC_ENABLE_TURBO_DISABLE);
@@ -2651,6 +2654,8 @@ static const struct x86_cpu_id intel_pstate_cpu_ids[] = {
 	X86_MATCH(INTEL_TIGERLAKE,		core_funcs),
 	X86_MATCH(INTEL_SAPPHIRERAPIDS_X,	core_funcs),
 	X86_MATCH(INTEL_EMERALDRAPIDS_X,	core_funcs),
+	X86_MATCH(INTEL_GRANITERAPIDS_D,	core_funcs),
+	X86_MATCH(INTEL_GRANITERAPIDS_X,	core_funcs),
 	{}
 };
 MODULE_DEVICE_TABLE(x86cpu, intel_pstate_cpu_ids);
@@ -3125,8 +3130,8 @@ static int intel_cpufreq_update_pstate(struct cpufreq_policy *policy,
 		int max_pstate = policy->strict_target ?
 					target_pstate : cpu->max_perf_ratio;
 
-		intel_cpufreq_hwp_update(cpu, target_pstate, max_pstate, 0,
-					 fast_switch);
+		intel_cpufreq_hwp_update(cpu, target_pstate, max_pstate,
+					 target_pstate, fast_switch);
 	} else if (target_pstate != old_pstate) {
 		intel_cpufreq_perf_ctl_update(cpu, target_pstate, fast_switch);
 	}
diff --git a/drivers/cpufreq/qcom-cpufreq-hw.c b/drivers/cpufreq/qcom-cpufreq-hw.c
index 900d6844c43d..e73997806383 100644
--- a/drivers/cpufreq/qcom-cpufreq-hw.c
+++ b/drivers/cpufreq/qcom-cpufreq-hw.c
@@ -143,14 +143,12 @@ static unsigned long qcom_lmh_get_throttle_freq(struct qcom_cpufreq_data *data)
 }
 
 /* Get the frequency requested by the cpufreq core for the CPU */
-static unsigned int qcom_cpufreq_get_freq(unsigned int cpu)
+static unsigned int qcom_cpufreq_get_freq(struct cpufreq_policy *policy)
 {
 	struct qcom_cpufreq_data *data;
 	const struct qcom_cpufreq_soc_data *soc_data;
-	struct cpufreq_policy *policy;
 	unsigned int index;
 
-	policy = cpufreq_cpu_get_raw(cpu);
 	if (!policy)
 		return 0;
 
@@ -163,12 +161,10 @@ static unsigned int qcom_cpufreq_get_freq(unsigned int cpu)
 	return policy->freq_table[index].frequency;
 }
 
-static unsigned int qcom_cpufreq_hw_get(unsigned int cpu)
+static unsigned int __qcom_cpufreq_hw_get(struct cpufreq_policy *policy)
 {
 	struct qcom_cpufreq_data *data;
-	struct cpufreq_policy *policy;
 
-	policy = cpufreq_cpu_get_raw(cpu);
 	if (!policy)
 		return 0;
 
@@ -177,7 +173,12 @@ static unsigned int qcom_cpufreq_hw_get(unsigned int cpu)
 	if (data->throttle_irq >= 0)
 		return qcom_lmh_get_throttle_freq(data) / HZ_PER_KHZ;
 
-	return qcom_cpufreq_get_freq(cpu);
+	return qcom_cpufreq_get_freq(policy);
+}
+
+static unsigned int qcom_cpufreq_hw_get(unsigned int cpu)
+{
+	return __qcom_cpufreq_hw_get(cpufreq_cpu_get_raw(cpu));
 }
 
 static unsigned int qcom_cpufreq_hw_fast_switch(struct cpufreq_policy *policy,
@@ -363,7 +364,7 @@ static void qcom_lmh_dcvs_notify(struct qcom_cpufreq_data *data)
 	 * If h/w throttled frequency is higher than what cpufreq has requested
 	 * for, then stop polling and switch back to interrupt mechanism.
 	 */
-	if (throttled_freq >= qcom_cpufreq_get_freq(cpu))
+	if (throttled_freq >= qcom_cpufreq_get_freq(cpufreq_cpu_get_raw(cpu)))
 		enable_irq(data->throttle_irq);
 	else
 		mod_delayed_work(system_highpri_wq, &data->throttle_work,
@@ -441,7 +442,6 @@ static int qcom_cpufreq_hw_lmh_init(struct cpufreq_policy *policy, int index)
 		return data->throttle_irq;
 
 	data->cancel_throttle = false;
-	data->policy = policy;
 
 	mutex_init(&data->throttle_lock);
 	INIT_DEFERRABLE_WORK(&data->throttle_work, qcom_lmh_dcvs_poll);
@@ -552,6 +552,7 @@ static int qcom_cpufreq_hw_cpu_init(struct cpufreq_policy *policy)
 
 	policy->driver_data = data;
 	policy->dvfs_possible_from_any_cpu = true;
+	data->policy = policy;
 
 	ret = qcom_cpufreq_hw_read_lut(cpu_dev, policy);
 	if (ret) {
@@ -622,11 +623,24 @@ static unsigned long qcom_cpufreq_hw_recalc_rate(struct clk_hw *hw, unsigned lon
 {
 	struct qcom_cpufreq_data *data = container_of(hw, struct qcom_cpufreq_data, cpu_clk);
 
-	return qcom_lmh_get_throttle_freq(data);
+	return __qcom_cpufreq_hw_get(data->policy) * HZ_PER_KHZ;
+}
+
+/*
+ * Since we cannot determine the closest rate of the target rate, let's just
+ * return the actual rate at which the clock is running at. This is needed to
+ * make clk_set_rate() API work properly.
+ */
+static int qcom_cpufreq_hw_determine_rate(struct clk_hw *hw, struct clk_rate_request *req)
+{
+	req->rate = qcom_cpufreq_hw_recalc_rate(hw, 0);
+
+	return 0;
 }
 
 static const struct clk_ops qcom_cpufreq_hw_clk_ops = {
 	.recalc_rate = qcom_cpufreq_hw_recalc_rate,
+	.determine_rate = qcom_cpufreq_hw_determine_rate,
 };
 
 static int qcom_cpufreq_hw_driver_probe(struct platform_device *pdev)
diff --git a/drivers/cpufreq/s3c64xx-cpufreq.c b/drivers/cpufreq/s3c64xx-cpufreq.c
index c6bdfc308e99..9cef71528076 100644
--- a/drivers/cpufreq/s3c64xx-cpufreq.c
+++ b/drivers/cpufreq/s3c64xx-cpufreq.c
@@ -24,6 +24,7 @@ struct s3c64xx_dvfs {
 	unsigned int vddarm_max;
 };
 
+#ifdef CONFIG_REGULATOR
 static struct s3c64xx_dvfs s3c64xx_dvfs_table[] = {
 	[0] = { 1000000, 1150000 },
 	[1] = { 1050000, 1150000 },
@@ -31,6 +32,7 @@ static struct s3c64xx_dvfs s3c64xx_dvfs_table[] = {
 	[3] = { 1200000, 1350000 },
 	[4] = { 1300000, 1350000 },
 };
+#endif
 
 static struct cpufreq_frequency_table s3c64xx_freq_table[] = {
 	{ 0, 0,  66000 },
@@ -51,15 +53,16 @@ static struct cpufreq_frequency_table s3c64xx_freq_table[] = {
 static int s3c64xx_cpufreq_set_target(struct cpufreq_policy *policy,
 				      unsigned int index)
 {
-	struct s3c64xx_dvfs *dvfs;
-	unsigned int old_freq, new_freq;
+	unsigned int new_freq = s3c64xx_freq_table[index].frequency;
 	int ret;
 
+#ifdef CONFIG_REGULATOR
+	struct s3c64xx_dvfs *dvfs;
+	unsigned int old_freq;
+
 	old_freq = clk_get_rate(policy->clk) / 1000;
-	new_freq = s3c64xx_freq_table[index].frequency;
 	dvfs = &s3c64xx_dvfs_table[s3c64xx_freq_table[index].driver_data];
 
-#ifdef CONFIG_REGULATOR
 	if (vddarm && new_freq > old_freq) {
 		ret = regulator_set_voltage(vddarm,
 					    dvfs->vddarm_min,
diff --git a/drivers/cpufreq/scmi-cpufreq.c b/drivers/cpufreq/scmi-cpufreq.c
index 07d6f9a9b7c8..beb660ca240c 100644
--- a/drivers/cpufreq/scmi-cpufreq.c
+++ b/drivers/cpufreq/scmi-cpufreq.c
@@ -34,11 +34,17 @@ static struct cpufreq_driver scmi_cpufreq_driver;
 
 static unsigned int scmi_cpufreq_get_rate(unsigned int cpu)
 {
-	struct cpufreq_policy *policy = cpufreq_cpu_get_raw(cpu);
-	struct scmi_data *priv = policy->driver_data;
+	struct cpufreq_policy *policy;
+	struct scmi_data *priv;
 	unsigned long rate;
 	int ret;
 
+	policy = cpufreq_cpu_get_raw(cpu);
+	if (unlikely(!policy))
+		return 0;
+
+	priv = policy->driver_data;
+
 	ret = perf_ops->freq_get(ph, priv->domain_id, &rate, false);
 	if (ret)
 		return 0;
@@ -361,6 +367,40 @@ static struct cpufreq_driver scmi_cpufreq_driver = {
 	.register_em	= scmi_cpufreq_register_em,
 };
 
+static bool scmi_dev_used_by_cpus(struct device *scmi_dev)
+{
+	struct device_node *scmi_np = dev_of_node(scmi_dev);
+	struct device_node *cpu_np, *np;
+	struct device *cpu_dev;
+	int cpu, idx;
+
+	if (!scmi_np)
+		return false;
+
+	for_each_possible_cpu(cpu) {
+		cpu_dev = get_cpu_device(cpu);
+		if (!cpu_dev)
+			continue;
+
+		cpu_np = dev_of_node(cpu_dev);
+
+		np = of_parse_phandle(cpu_np, "clocks", 0);
+		of_node_put(np);
+
+		if (np == scmi_np)
+			return true;
+
+		idx = of_property_match_string(cpu_np, "power-domain-names", "perf");
+		np = of_parse_phandle(cpu_np, "power-domains", idx);
+		of_node_put(np);
+
+		if (np == scmi_np)
+			return true;
+	}
+
+	return false;
+}
+
 static int scmi_cpufreq_probe(struct scmi_device *sdev)
 {
 	int ret;
@@ -369,7 +409,7 @@ static int scmi_cpufreq_probe(struct scmi_device *sdev)
 
 	handle = sdev->handle;
 
-	if (!handle)
+	if (!handle || !scmi_dev_used_by_cpus(dev))
 		return -ENODEV;
 
 	perf_ops = handle->devm_protocol_get(sdev, SCMI_PROTOCOL_PERF, &ph);
diff --git a/drivers/cpufreq/scpi-cpufreq.c b/drivers/cpufreq/scpi-cpufreq.c
index 8d73e6e8be2a..a191d9bdf667 100644
--- a/drivers/cpufreq/scpi-cpufreq.c
+++ b/drivers/cpufreq/scpi-cpufreq.c
@@ -29,9 +29,16 @@ static struct scpi_ops *scpi_ops;
 
 static unsigned int scpi_cpufreq_get_rate(unsigned int cpu)
 {
-	struct cpufreq_policy *policy = cpufreq_cpu_get_raw(cpu);
-	struct scpi_data *priv = policy->driver_data;
-	unsigned long rate = clk_get_rate(priv->clk);
+	struct cpufreq_policy *policy;
+	struct scpi_data *priv;
+	unsigned long rate;
+
+	policy = cpufreq_cpu_get_raw(cpu);
+	if (unlikely(!policy))
+		return 0;
+
+	priv = policy->driver_data;
+	rate = clk_get_rate(priv->clk);
 
 	return rate / 1000;
 }
@@ -39,8 +46,9 @@ static unsigned int scpi_cpufreq_get_rate(unsigned int cpu)
 static int
 scpi_cpufreq_set_target(struct cpufreq_policy *policy, unsigned int index)
 {
-	u64 rate = policy->freq_table[index].frequency * 1000;
+	unsigned long freq_khz = policy->freq_table[index].frequency;
 	struct scpi_data *priv = policy->driver_data;
+	unsigned long rate = freq_khz * 1000;
 	int ret;
 
 	ret = clk_set_rate(priv->clk, rate);
@@ -48,7 +56,7 @@ scpi_cpufreq_set_target(struct cpufreq_policy *policy, unsigned int index)
 	if (ret)
 		return ret;
 
-	if (clk_get_rate(priv->clk) != rate)
+	if (clk_get_rate(priv->clk) / 1000 != freq_khz)
 		return -EIO;
 
 	return 0;
diff --git a/drivers/cpufreq/sun50i-cpufreq-nvmem.c b/drivers/cpufreq/sun50i-cpufreq-nvmem.c
index 293921acec93..0599dbf851eb 100644
--- a/drivers/cpufreq/sun50i-cpufreq-nvmem.c
+++ b/drivers/cpufreq/sun50i-cpufreq-nvmem.c
@@ -167,7 +167,9 @@ static int sun50i_cpufreq_get_efuse(void)
 	struct nvmem_cell *speedbin_nvmem;
 	const struct of_device_id *match;
 	struct device *cpu_dev;
-	u32 *speedbin;
+	void *speedbin_ptr;
+	u32 speedbin = 0;
+	size_t len;
 	int ret;
 
 	cpu_dev = get_cpu_device(0);
@@ -190,14 +192,18 @@ static int sun50i_cpufreq_get_efuse(void)
 		return dev_err_probe(cpu_dev, PTR_ERR(speedbin_nvmem),
 				     "Could not get nvmem cell\n");
 
-	speedbin = nvmem_cell_read(speedbin_nvmem, NULL);
+	speedbin_ptr = nvmem_cell_read(speedbin_nvmem, &len);
 	nvmem_cell_put(speedbin_nvmem);
-	if (IS_ERR(speedbin))
-		return PTR_ERR(speedbin);
+	if (IS_ERR(speedbin_ptr))
+		return PTR_ERR(speedbin_ptr);
 
-	ret = opp_data->efuse_xlate(*speedbin);
+	if (len <= 4)
+		memcpy(&speedbin, speedbin_ptr, len);
+	speedbin = le32_to_cpu(speedbin);
 
-	kfree(speedbin);
+	ret = opp_data->efuse_xlate(speedbin);
+
+	kfree(speedbin_ptr);
 
 	return ret;
 };
diff --git a/drivers/cpuidle/cpuidle-psci.c b/drivers/cpuidle/cpuidle-psci.c
index 2562dc001fc1..f3c30037dc8e 100644
--- a/drivers/cpuidle/cpuidle-psci.c
+++ b/drivers/cpuidle/cpuidle-psci.c
@@ -38,7 +38,6 @@ struct psci_cpuidle_data {
 static DEFINE_PER_CPU_READ_MOSTLY(struct psci_cpuidle_data, psci_cpuidle_data);
 static DEFINE_PER_CPU(u32, domain_state);
 static bool psci_cpuidle_use_syscore;
-static bool psci_cpuidle_use_cpuhp;
 
 void psci_set_domain_state(u32 state)
 {
@@ -105,8 +104,12 @@ static int psci_idle_cpuhp_up(unsigned int cpu)
 {
 	struct device *pd_dev = __this_cpu_read(psci_cpuidle_data.dev);
 
-	if (pd_dev)
-		pm_runtime_get_sync(pd_dev);
+	if (pd_dev) {
+		if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+			pm_runtime_get_sync(pd_dev);
+		else
+			dev_pm_genpd_resume(pd_dev);
+	}
 
 	return 0;
 }
@@ -116,7 +119,11 @@ static int psci_idle_cpuhp_down(unsigned int cpu)
 	struct device *pd_dev = __this_cpu_read(psci_cpuidle_data.dev);
 
 	if (pd_dev) {
-		pm_runtime_put_sync(pd_dev);
+		if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+			pm_runtime_put_sync(pd_dev);
+		else
+			dev_pm_genpd_suspend(pd_dev);
+
 		/* Clear domain state to start fresh at next online. */
 		psci_set_domain_state(0);
 	}
@@ -177,9 +184,6 @@ static void psci_idle_init_cpuhp(void)
 {
 	int err;
 
-	if (!psci_cpuidle_use_cpuhp)
-		return;
-
 	err = cpuhp_setup_state_nocalls(CPUHP_AP_CPU_PM_STARTING,
 					"cpuidle/psci:online",
 					psci_idle_cpuhp_up,
@@ -240,10 +244,8 @@ static int psci_dt_cpu_init_topology(struct cpuidle_driver *drv,
 	 * s2ram and s2idle.
 	 */
 	drv->states[state_count - 1].enter_s2idle = psci_enter_s2idle_domain_idle_state;
-	if (!IS_ENABLED(CONFIG_PREEMPT_RT)) {
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT))
 		drv->states[state_count - 1].enter = psci_enter_domain_idle_state;
-		psci_cpuidle_use_cpuhp = true;
-	}
 
 	return 0;
 }
@@ -320,7 +322,6 @@ static void psci_cpu_deinit_idle(int cpu)
 
 	dt_idle_detach_cpu(data->dev);
 	psci_cpuidle_use_syscore = false;
-	psci_cpuidle_use_cpuhp = false;
 }
 
 static int psci_idle_init_cpu(struct device *dev, int cpu)
diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c
index f3c9d49f0f2a..01322a905414 100644
--- a/drivers/cpuidle/governors/menu.c
+++ b/drivers/cpuidle/governors/menu.c
@@ -153,6 +153,14 @@ static inline int performance_multiplier(unsigned int nr_iowaiters)
 
 static DEFINE_PER_CPU(struct menu_device, menu_devices);
 
+static void menu_update_intervals(struct menu_device *data, unsigned int interval_us)
+{
+	/* Update the repeating-pattern data. */
+	data->intervals[data->interval_ptr++] = interval_us;
+	if (data->interval_ptr >= INTERVALS)
+		data->interval_ptr = 0;
+}
+
 static void menu_update(struct cpuidle_driver *drv, struct cpuidle_device *dev);
 
 /*
@@ -239,8 +247,19 @@ again:
 	 * This can deal with workloads that have long pauses interspersed
 	 * with sporadic activity with a bunch of short pauses.
 	 */
-	if ((divisor * 4) <= INTERVALS * 3)
+	if (divisor * 4 <= INTERVALS * 3) {
+		/*
+		 * If there are sufficiently many data points still under
+		 * consideration after the outliers have been eliminated,
+		 * returning without a prediction would be a mistake because it
+		 * is likely that the next interval will not exceed the current
+		 * maximum, so return the latter in that case.
+		 */
+		if (divisor >= INTERVALS / 2)
+			return max;
+
 		return UINT_MAX;
+	}
 
 	thresh = max - 1;
 	goto again;
@@ -266,6 +285,14 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 	if (data->needs_update) {
 		menu_update(drv, dev);
 		data->needs_update = 0;
+	} else if (!dev->last_residency_ns) {
+		/*
+		 * This happens when the driver rejects the previously selected
+		 * idle state and returns an error, so update the recent
+		 * intervals table to prevent invalid information from being
+		 * used going forward.
+		 */
+		menu_update_intervals(data, UINT_MAX);
 	}
 
 	nr_iowaiters = nr_iowait_cpu(dev->cpu);
@@ -535,10 +562,7 @@ static void menu_update(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 
 	data->correction_factor[data->bucket] = new_factor;
 
-	/* update the repeating-pattern data */
-	data->intervals[data->interval_ptr++] = ktime_to_us(measured_ns);
-	if (data->interval_ptr >= INTERVALS)
-		data->interval_ptr = 0;
+	menu_update_intervals(data, ktime_to_us(measured_ns));
 }
 
 /**
diff --git a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-cipher.c b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-cipher.c
index 19b7fb4a93e8..63e66a85477e 100644
--- a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-cipher.c
+++ b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-cipher.c
@@ -265,8 +265,8 @@ static int sun8i_ce_cipher_prepare(struct crypto_engine *engine, void *async_req
 	}
 
 	chan->timeout = areq->cryptlen;
-	rctx->nr_sgs = nr_sgs;
-	rctx->nr_sgd = nr_sgd;
+	rctx->nr_sgs = ns;
+	rctx->nr_sgd = nd;
 	return 0;
 
 theend_sgs:
@@ -275,13 +275,16 @@ theend_sgs:
 	} else {
 		if (nr_sgs > 0)
 			dma_unmap_sg(ce->dev, areq->src, ns, DMA_TO_DEVICE);
-		dma_unmap_sg(ce->dev, areq->dst, nd, DMA_FROM_DEVICE);
+
+		if (nr_sgd > 0)
+			dma_unmap_sg(ce->dev, areq->dst, nd, DMA_FROM_DEVICE);
 	}
 
 theend_iv:
 	if (areq->iv && ivsize > 0) {
-		if (rctx->addr_iv)
+		if (!dma_mapping_error(ce->dev, rctx->addr_iv))
 			dma_unmap_single(ce->dev, rctx->addr_iv, rctx->ivlen, DMA_TO_DEVICE);
+
 		offset = areq->cryptlen - ivsize;
 		if (rctx->op_dir & CE_DECRYPTION) {
 			memcpy(areq->iv, chan->backup_iv, ivsize);
diff --git a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-core.c b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-core.c
index e55e58e164db..fcc6832a065c 100644
--- a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-core.c
+++ b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-core.c
@@ -832,13 +832,12 @@ static int sun8i_ce_pm_init(struct sun8i_ce_dev *ce)
 	err = pm_runtime_set_suspended(ce->dev);
 	if (err)
 		return err;
-	pm_runtime_enable(ce->dev);
-	return err;
-}
 
-static void sun8i_ce_pm_exit(struct sun8i_ce_dev *ce)
-{
-	pm_runtime_disable(ce->dev);
+	err = devm_pm_runtime_enable(ce->dev);
+	if (err)
+		return err;
+
+	return 0;
 }
 
 static int sun8i_ce_get_clks(struct sun8i_ce_dev *ce)
@@ -1041,7 +1040,7 @@ static int sun8i_ce_probe(struct platform_device *pdev)
 			       "sun8i-ce-ns", ce);
 	if (err) {
 		dev_err(ce->dev, "Cannot request CryptoEngine Non-secure IRQ (err=%d)\n", err);
-		goto error_irq;
+		goto error_pm;
 	}
 
 	err = sun8i_ce_register_algs(ce);
@@ -1082,8 +1081,6 @@ static int sun8i_ce_probe(struct platform_device *pdev)
 	return 0;
 error_alg:
 	sun8i_ce_unregister_algs(ce);
-error_irq:
-	sun8i_ce_pm_exit(ce);
 error_pm:
 	sun8i_ce_free_chanlist(ce, MAXFLOW - 1);
 	return err;
@@ -1104,8 +1101,6 @@ static void sun8i_ce_remove(struct platform_device *pdev)
 #endif
 
 	sun8i_ce_free_chanlist(ce, MAXFLOW - 1);
-
-	sun8i_ce_pm_exit(ce);
 }
 
 static const struct of_device_id sun8i_ce_crypto_of_match_table[] = {
diff --git a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-hash.c b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-hash.c
index 6072dd9f390b..3f9d79ea01aa 100644
--- a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-hash.c
+++ b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-hash.c
@@ -343,9 +343,8 @@ int sun8i_ce_hash_run(struct crypto_engine *engine, void *breq)
 	u32 common;
 	u64 byte_count;
 	__le32 *bf;
-	void *buf = NULL;
+	void *buf, *result;
 	int j, i, todo;
-	void *result = NULL;
 	u64 bs;
 	int digestsize;
 	dma_addr_t addr_res, addr_pad;
@@ -365,14 +364,14 @@ int sun8i_ce_hash_run(struct crypto_engine *engine, void *breq)
 	buf = kcalloc(2, bs, GFP_KERNEL | GFP_DMA);
 	if (!buf) {
 		err = -ENOMEM;
-		goto theend;
+		goto err_out;
 	}
 	bf = (__le32 *)buf;
 
 	result = kzalloc(digestsize, GFP_KERNEL | GFP_DMA);
 	if (!result) {
 		err = -ENOMEM;
-		goto theend;
+		goto err_free_buf;
 	}
 
 	flow = rctx->flow;
@@ -398,7 +397,7 @@ int sun8i_ce_hash_run(struct crypto_engine *engine, void *breq)
 	if (nr_sgs <= 0 || nr_sgs > MAX_SG) {
 		dev_err(ce->dev, "Invalid sg number %d\n", nr_sgs);
 		err = -EINVAL;
-		goto theend;
+		goto err_free_result;
 	}
 
 	len = areq->nbytes;
@@ -411,7 +410,7 @@ int sun8i_ce_hash_run(struct crypto_engine *engine, void *breq)
 	if (len > 0) {
 		dev_err(ce->dev, "remaining len %d\n", len);
 		err = -EINVAL;
-		goto theend;
+		goto err_unmap_src;
 	}
 	addr_res = dma_map_single(ce->dev, result, digestsize, DMA_FROM_DEVICE);
 	cet->t_dst[0].addr = desc_addr_val_le32(ce, addr_res);
@@ -419,7 +418,7 @@ int sun8i_ce_hash_run(struct crypto_engine *engine, void *breq)
 	if (dma_mapping_error(ce->dev, addr_res)) {
 		dev_err(ce->dev, "DMA map dest\n");
 		err = -EINVAL;
-		goto theend;
+		goto err_unmap_src;
 	}
 
 	byte_count = areq->nbytes;
@@ -441,7 +440,7 @@ int sun8i_ce_hash_run(struct crypto_engine *engine, void *breq)
 	}
 	if (!j) {
 		err = -EINVAL;
-		goto theend;
+		goto err_unmap_result;
 	}
 
 	addr_pad = dma_map_single(ce->dev, buf, j * 4, DMA_TO_DEVICE);
@@ -450,7 +449,7 @@ int sun8i_ce_hash_run(struct crypto_engine *engine, void *breq)
 	if (dma_mapping_error(ce->dev, addr_pad)) {
 		dev_err(ce->dev, "DMA error on padding SG\n");
 		err = -EINVAL;
-		goto theend;
+		goto err_unmap_result;
 	}
 
 	if (ce->variant->hash_t_dlen_in_bits)
@@ -463,16 +462,25 @@ int sun8i_ce_hash_run(struct crypto_engine *engine, void *breq)
 	err = sun8i_ce_run_task(ce, flow, crypto_ahash_alg_name(tfm));
 
 	dma_unmap_single(ce->dev, addr_pad, j * 4, DMA_TO_DEVICE);
-	dma_unmap_sg(ce->dev, areq->src, ns, DMA_TO_DEVICE);
+
+err_unmap_result:
 	dma_unmap_single(ce->dev, addr_res, digestsize, DMA_FROM_DEVICE);
+	if (!err)
+		memcpy(areq->result, result, algt->alg.hash.base.halg.digestsize);
 
+err_unmap_src:
+	dma_unmap_sg(ce->dev, areq->src, ns, DMA_TO_DEVICE);
 
-	memcpy(areq->result, result, algt->alg.hash.base.halg.digestsize);
-theend:
-	kfree(buf);
+err_free_result:
 	kfree(result);
+
+err_free_buf:
+	kfree(buf);
+
+err_out:
 	local_bh_disable();
 	crypto_finalize_hash_request(engine, breq, err);
 	local_bh_enable();
+
 	return 0;
 }
diff --git a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce.h b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce.h
index 3b5c2af013d0..83df4d719053 100644
--- a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce.h
+++ b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce.h
@@ -308,8 +308,8 @@ struct sun8i_ce_hash_tfm_ctx {
  * @flow:	the flow to use for this request
  */
 struct sun8i_ce_hash_reqctx {
-	struct ahash_request fallback_req;
 	int flow;
+	struct ahash_request fallback_req; // keep at the end
 };
 
 /*
diff --git a/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-cipher.c b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-cipher.c
index 9b9605ce8ee6..8831bcb230c2 100644
--- a/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-cipher.c
+++ b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-cipher.c
@@ -141,7 +141,7 @@ static int sun8i_ss_setup_ivs(struct skcipher_request *areq)
 
 	/* we need to copy all IVs from source in case DMA is bi-directionnal */
 	while (sg && len) {
-		if (sg_dma_len(sg) == 0) {
+		if (sg->length == 0) {
 			sg = sg_next(sg);
 			continue;
 		}
diff --git a/drivers/crypto/atmel-sha204a.c b/drivers/crypto/atmel-sha204a.c
index a02d496f4c41..b9658e38cb03 100644
--- a/drivers/crypto/atmel-sha204a.c
+++ b/drivers/crypto/atmel-sha204a.c
@@ -163,6 +163,12 @@ static int atmel_sha204a_probe(struct i2c_client *client)
 	i2c_priv->hwrng.name = dev_name(&client->dev);
 	i2c_priv->hwrng.read = atmel_sha204a_rng_read;
 
+	/*
+	 * According to review by Bill Cox [1], this HWRNG has very low entropy.
+	 * [1] https://www.metzdowd.com/pipermail/cryptography/2014-December/023858.html
+	 */
+	i2c_priv->hwrng.quality = 1;
+
 	ret = devm_hwrng_register(&client->dev, &i2c_priv->hwrng);
 	if (ret)
 		dev_warn(&client->dev, "failed to register RNG (%d)\n", ret);
diff --git a/drivers/crypto/caam/blob_gen.c b/drivers/crypto/caam/blob_gen.c
index 87781c1534ee..079a22cc9f02 100644
--- a/drivers/crypto/caam/blob_gen.c
+++ b/drivers/crypto/caam/blob_gen.c
@@ -2,6 +2,7 @@
 /*
  * Copyright (C) 2015 Pengutronix, Steffen Trumtrar <kernel@pengutronix.de>
  * Copyright (C) 2021 Pengutronix, Ahmad Fatoum <kernel@pengutronix.de>
+ * Copyright 2024 NXP
  */
 
 #define pr_fmt(fmt) "caam blob_gen: " fmt
@@ -104,7 +105,7 @@ int caam_process_blob(struct caam_blob_priv *priv,
 	}
 
 	ctrlpriv = dev_get_drvdata(jrdev->parent);
-	moo = FIELD_GET(CSTA_MOO, rd_reg32(&ctrlpriv->ctrl->perfmon.status));
+	moo = FIELD_GET(CSTA_MOO, rd_reg32(&ctrlpriv->jr[0]->perfmon.status));
 	if (moo != CSTA_MOO_SECURE && moo != CSTA_MOO_TRUSTED)
 		dev_warn(jrdev,
 			 "using insecure test key, enable HAB to use unique device key!\n");
diff --git a/drivers/crypto/caam/qi.c b/drivers/crypto/caam/qi.c
index 8ed2bb01a619..448606300500 100644
--- a/drivers/crypto/caam/qi.c
+++ b/drivers/crypto/caam/qi.c
@@ -122,12 +122,12 @@ int caam_qi_enqueue(struct device *qidev, struct caam_drv_req *req)
 	qm_fd_addr_set64(&fd, addr);
 
 	do {
+		refcount_inc(&req->drv_ctx->refcnt);
 		ret = qman_enqueue(req->drv_ctx->req_fq, &fd);
-		if (likely(!ret)) {
-			refcount_inc(&req->drv_ctx->refcnt);
+		if (likely(!ret))
 			return 0;
-		}
 
+		refcount_dec(&req->drv_ctx->refcnt);
 		if (ret != -EBUSY)
 			break;
 		num_retries++;
diff --git a/drivers/crypto/ccp/ccp-debugfs.c b/drivers/crypto/ccp/ccp-debugfs.c
index a1055554b47a..dc26bc22c91d 100644
--- a/drivers/crypto/ccp/ccp-debugfs.c
+++ b/drivers/crypto/ccp/ccp-debugfs.c
@@ -319,5 +319,8 @@ void ccp5_debugfs_setup(struct ccp_device *ccp)
 
 void ccp5_debugfs_destroy(void)
 {
+	mutex_lock(&ccp_debugfs_lock);
 	debugfs_remove_recursive(ccp_debugfs_dir);
+	ccp_debugfs_dir = NULL;
+	mutex_unlock(&ccp_debugfs_lock);
 }
diff --git a/drivers/crypto/ccp/sev-dev.c b/drivers/crypto/ccp/sev-dev.c
index af018afd9cd7..4d072c084d7b 100644
--- a/drivers/crypto/ccp/sev-dev.c
+++ b/drivers/crypto/ccp/sev-dev.c
@@ -424,7 +424,7 @@ cleanup:
 	return rc;
 }
 
-static struct page *__snp_alloc_firmware_pages(gfp_t gfp_mask, int order)
+static struct page *__snp_alloc_firmware_pages(gfp_t gfp_mask, int order, bool locked)
 {
 	unsigned long npages = 1ul << order, paddr;
 	struct sev_device *sev;
@@ -443,7 +443,7 @@ static struct page *__snp_alloc_firmware_pages(gfp_t gfp_mask, int order)
 		return page;
 
 	paddr = __pa((unsigned long)page_address(page));
-	if (rmp_mark_pages_firmware(paddr, npages, false))
+	if (rmp_mark_pages_firmware(paddr, npages, locked))
 		return NULL;
 
 	return page;
@@ -453,7 +453,7 @@ void *snp_alloc_firmware_page(gfp_t gfp_mask)
 {
 	struct page *page;
 
-	page = __snp_alloc_firmware_pages(gfp_mask, 0);
+	page = __snp_alloc_firmware_pages(gfp_mask, 0, false);
 
 	return page ? page_address(page) : NULL;
 }
@@ -488,7 +488,7 @@ static void *sev_fw_alloc(unsigned long len)
 {
 	struct page *page;
 
-	page = __snp_alloc_firmware_pages(GFP_KERNEL, get_order(len));
+	page = __snp_alloc_firmware_pages(GFP_KERNEL, get_order(len), true);
 	if (!page)
 		return NULL;
 
diff --git a/drivers/crypto/ccp/sp-pci.c b/drivers/crypto/ccp/sp-pci.c
index 248d98fd8c48..224edaaa737b 100644
--- a/drivers/crypto/ccp/sp-pci.c
+++ b/drivers/crypto/ccp/sp-pci.c
@@ -189,14 +189,17 @@ static bool sp_pci_is_master(struct sp_device *sp)
 	pdev_new = to_pci_dev(dev_new);
 	pdev_cur = to_pci_dev(dev_cur);
 
-	if (pdev_new->bus->number < pdev_cur->bus->number)
-		return true;
+	if (pci_domain_nr(pdev_new->bus) != pci_domain_nr(pdev_cur->bus))
+		return pci_domain_nr(pdev_new->bus) < pci_domain_nr(pdev_cur->bus);
 
-	if (PCI_SLOT(pdev_new->devfn) < PCI_SLOT(pdev_cur->devfn))
-		return true;
+	if (pdev_new->bus->number != pdev_cur->bus->number)
+		return pdev_new->bus->number < pdev_cur->bus->number;
 
-	if (PCI_FUNC(pdev_new->devfn) < PCI_FUNC(pdev_cur->devfn))
-		return true;
+	if (PCI_SLOT(pdev_new->devfn) != PCI_SLOT(pdev_cur->devfn))
+		return PCI_SLOT(pdev_new->devfn) < PCI_SLOT(pdev_cur->devfn);
+
+	if (PCI_FUNC(pdev_new->devfn) != PCI_FUNC(pdev_cur->devfn))
+		return PCI_FUNC(pdev_new->devfn) < PCI_FUNC(pdev_cur->devfn);
 
 	return false;
 }
@@ -448,6 +451,7 @@ static const struct psp_vdata pspv6 = {
 	.cmdresp_reg		= 0x10944,	/* C2PMSG_17 */
 	.cmdbuff_addr_lo_reg	= 0x10948,	/* C2PMSG_18 */
 	.cmdbuff_addr_hi_reg	= 0x1094c,	/* C2PMSG_19 */
+	.bootloader_info_reg	= 0x109ec,	/* C2PMSG_59 */
 	.feature_reg            = 0x109fc,	/* C2PMSG_63 */
 	.inten_reg              = 0x10510,	/* P2CMSG_INTEN */
 	.intsts_reg             = 0x10514,	/* P2CMSG_INTSTS */
@@ -529,6 +533,7 @@ static const struct pci_device_id sp_pci_table[] = {
 	{ PCI_VDEVICE(AMD, 0x14CA), (kernel_ulong_t)&dev_vdata[5] },
 	{ PCI_VDEVICE(AMD, 0x15C7), (kernel_ulong_t)&dev_vdata[6] },
 	{ PCI_VDEVICE(AMD, 0x1649), (kernel_ulong_t)&dev_vdata[6] },
+	{ PCI_VDEVICE(AMD, 0x1134), (kernel_ulong_t)&dev_vdata[7] },
 	{ PCI_VDEVICE(AMD, 0x17E0), (kernel_ulong_t)&dev_vdata[7] },
 	{ PCI_VDEVICE(AMD, 0x156E), (kernel_ulong_t)&dev_vdata[8] },
 	/* Last entry must be zero */
diff --git a/drivers/crypto/hisilicon/hpre/hpre_crypto.c b/drivers/crypto/hisilicon/hpre/hpre_crypto.c
index c167dbd6c7d6..e71f1e459764 100644
--- a/drivers/crypto/hisilicon/hpre/hpre_crypto.c
+++ b/drivers/crypto/hisilicon/hpre/hpre_crypto.c
@@ -1487,11 +1487,13 @@ static void hpre_ecdh_cb(struct hpre_ctx *ctx, void *resp)
 	if (overtime_thrhld && hpre_is_bd_timeout(req, overtime_thrhld))
 		atomic64_inc(&dfx[HPRE_OVER_THRHLD_CNT].value);
 
+	/* Do unmap before data processing */
+	hpre_ecdh_hw_data_clr_all(ctx, req, areq->dst, areq->src);
+
 	p = sg_virt(areq->dst);
 	memmove(p, p + ctx->key_sz - curve_sz, curve_sz);
 	memmove(p + curve_sz, p + areq->dst_len - curve_sz, curve_sz);
 
-	hpre_ecdh_hw_data_clr_all(ctx, req, areq->dst, areq->src);
 	kpp_request_complete(areq, ret);
 
 	atomic64_inc(&dfx[HPRE_RECV_CNT].value);
@@ -1801,9 +1803,11 @@ static void hpre_curve25519_cb(struct hpre_ctx *ctx, void *resp)
 	if (overtime_thrhld && hpre_is_bd_timeout(req, overtime_thrhld))
 		atomic64_inc(&dfx[HPRE_OVER_THRHLD_CNT].value);
 
+	/* Do unmap before data processing */
+	hpre_curve25519_hw_data_clr_all(ctx, req, areq->dst, areq->src);
+
 	hpre_key_to_big_end(sg_virt(areq->dst), CURVE25519_KEY_SIZE);
 
-	hpre_curve25519_hw_data_clr_all(ctx, req, areq->dst, areq->src);
 	kpp_request_complete(areq, ret);
 
 	atomic64_inc(&dfx[HPRE_RECV_CNT].value);
diff --git a/drivers/crypto/hisilicon/sec2/sec.h b/drivers/crypto/hisilicon/sec2/sec.h
index 410c83712e28..2fc04e210bc4 100644
--- a/drivers/crypto/hisilicon/sec2/sec.h
+++ b/drivers/crypto/hisilicon/sec2/sec.h
@@ -90,9 +90,7 @@ struct sec_auth_ctx {
 	dma_addr_t a_key_dma;
 	u8 *a_key;
 	u8 a_key_len;
-	u8 mac_len;
 	u8 a_alg;
-	bool fallback;
 	struct crypto_shash *hash_tfm;
 	struct crypto_aead *fallback_aead_tfm;
 };
diff --git a/drivers/crypto/hisilicon/sec2/sec_crypto.c b/drivers/crypto/hisilicon/sec2/sec_crypto.c
index 0558f98e221f..8605cb3cae92 100644
--- a/drivers/crypto/hisilicon/sec2/sec_crypto.c
+++ b/drivers/crypto/hisilicon/sec2/sec_crypto.c
@@ -57,7 +57,6 @@
 #define SEC_TYPE_MASK		0x0F
 #define SEC_DONE_MASK		0x0001
 #define SEC_ICV_MASK		0x000E
-#define SEC_SQE_LEN_RATE_MASK	0x3
 
 #define SEC_TOTAL_IV_SZ(depth)	(SEC_IV_SIZE * (depth))
 #define SEC_SGL_SGE_NR		128
@@ -80,16 +79,16 @@
 #define SEC_TOTAL_PBUF_SZ(depth)	(PAGE_SIZE * SEC_PBUF_PAGE_NUM(depth) +	\
 				SEC_PBUF_LEFT_SZ(depth))
 
-#define SEC_SQE_LEN_RATE	4
 #define SEC_SQE_CFLAG		2
 #define SEC_SQE_AEAD_FLAG	3
 #define SEC_SQE_DONE		0x1
 #define SEC_ICV_ERR		0x2
-#define MIN_MAC_LEN		4
 #define MAC_LEN_MASK		0x1U
 #define MAX_INPUT_DATA_LEN	0xFFFE00
 #define BITS_MASK		0xFF
+#define WORD_MASK		0x3
 #define BYTE_BITS		0x8
+#define BYTES_TO_WORDS(bcount)	((bcount) >> 2)
 #define SEC_XTS_NAME_SZ		0x3
 #define IV_CM_CAL_NUM		2
 #define IV_CL_MASK		0x7
@@ -691,14 +690,10 @@ static int sec_skcipher_fbtfm_init(struct crypto_skcipher *tfm)
 
 	c_ctx->fallback = false;
 
-	/* Currently, only XTS mode need fallback tfm when using 192bit key */
-	if (likely(strncmp(alg, "xts", SEC_XTS_NAME_SZ)))
-		return 0;
-
 	c_ctx->fbtfm = crypto_alloc_sync_skcipher(alg, 0,
 						  CRYPTO_ALG_NEED_FALLBACK);
 	if (IS_ERR(c_ctx->fbtfm)) {
-		pr_err("failed to alloc xts mode fallback tfm!\n");
+		pr_err("failed to alloc fallback tfm for %s!\n", alg);
 		return PTR_ERR(c_ctx->fbtfm);
 	}
 
@@ -858,7 +853,7 @@ static int sec_skcipher_setkey(struct crypto_skcipher *tfm, const u8 *key,
 	}
 
 	memcpy(c_ctx->c_key, key, keylen);
-	if (c_ctx->fallback && c_ctx->fbtfm) {
+	if (c_ctx->fbtfm) {
 		ret = crypto_sync_skcipher_setkey(c_ctx->fbtfm, key, keylen);
 		if (ret) {
 			dev_err(dev, "failed to set fallback skcipher key!\n");
@@ -948,15 +943,14 @@ static int sec_aead_mac_init(struct sec_aead_req *req)
 	struct aead_request *aead_req = req->aead_req;
 	struct crypto_aead *tfm = crypto_aead_reqtfm(aead_req);
 	size_t authsize = crypto_aead_authsize(tfm);
-	u8 *mac_out = req->out_mac;
 	struct scatterlist *sgl = aead_req->src;
+	u8 *mac_out = req->out_mac;
 	size_t copy_size;
 	off_t skip_size;
 
 	/* Copy input mac */
 	skip_size = aead_req->assoclen + aead_req->cryptlen - authsize;
-	copy_size = sg_pcopy_to_buffer(sgl, sg_nents(sgl), mac_out,
-				       authsize, skip_size);
+	copy_size = sg_pcopy_to_buffer(sgl, sg_nents(sgl), mac_out, authsize, skip_size);
 	if (unlikely(copy_size != authsize))
 		return -EINVAL;
 
@@ -1091,11 +1085,6 @@ static int sec_aead_auth_set_key(struct sec_auth_ctx *ctx,
 	struct crypto_shash *hash_tfm = ctx->hash_tfm;
 	int blocksize, digestsize, ret;
 
-	if (!keys->authkeylen) {
-		pr_err("hisi_sec2: aead auth key error!\n");
-		return -EINVAL;
-	}
-
 	blocksize = crypto_shash_blocksize(hash_tfm);
 	digestsize = crypto_shash_digestsize(hash_tfm);
 	if (keys->authkeylen > blocksize) {
@@ -1107,7 +1096,8 @@ static int sec_aead_auth_set_key(struct sec_auth_ctx *ctx,
 		}
 		ctx->a_key_len = digestsize;
 	} else {
-		memcpy(ctx->a_key, keys->authkey, keys->authkeylen);
+		if (keys->authkeylen)
+			memcpy(ctx->a_key, keys->authkey, keys->authkeylen);
 		ctx->a_key_len = keys->authkeylen;
 	}
 
@@ -1120,10 +1110,7 @@ static int sec_aead_setauthsize(struct crypto_aead *aead, unsigned int authsize)
 	struct sec_ctx *ctx = crypto_tfm_ctx(tfm);
 	struct sec_auth_ctx *a_ctx = &ctx->a_ctx;
 
-	if (unlikely(a_ctx->fallback_aead_tfm))
-		return crypto_aead_setauthsize(a_ctx->fallback_aead_tfm, authsize);
-
-	return 0;
+	return crypto_aead_setauthsize(a_ctx->fallback_aead_tfm, authsize);
 }
 
 static int sec_aead_fallback_setkey(struct sec_auth_ctx *a_ctx,
@@ -1139,7 +1126,6 @@ static int sec_aead_fallback_setkey(struct sec_auth_ctx *a_ctx,
 static int sec_aead_setkey(struct crypto_aead *tfm, const u8 *key,
 			   const u32 keylen, const enum sec_hash_alg a_alg,
 			   const enum sec_calg c_alg,
-			   const enum sec_mac_len mac_len,
 			   const enum sec_cmode c_mode)
 {
 	struct sec_ctx *ctx = crypto_aead_ctx(tfm);
@@ -1151,7 +1137,6 @@ static int sec_aead_setkey(struct crypto_aead *tfm, const u8 *key,
 
 	ctx->a_ctx.a_alg = a_alg;
 	ctx->c_ctx.c_alg = c_alg;
-	ctx->a_ctx.mac_len = mac_len;
 	c_ctx->c_mode = c_mode;
 
 	if (c_mode == SEC_CMODE_CCM || c_mode == SEC_CMODE_GCM) {
@@ -1162,18 +1147,14 @@ static int sec_aead_setkey(struct crypto_aead *tfm, const u8 *key,
 		}
 		memcpy(c_ctx->c_key, key, keylen);
 
-		if (unlikely(a_ctx->fallback_aead_tfm)) {
-			ret = sec_aead_fallback_setkey(a_ctx, tfm, key, keylen);
-			if (ret)
-				return ret;
-		}
-
-		return 0;
+		return sec_aead_fallback_setkey(a_ctx, tfm, key, keylen);
 	}
 
 	ret = crypto_authenc_extractkeys(&keys, key, keylen);
-	if (ret)
+	if (ret) {
+		dev_err(dev, "sec extract aead keys err!\n");
 		goto bad_key;
+	}
 
 	ret = sec_aead_aes_set_key(c_ctx, &keys);
 	if (ret) {
@@ -1187,10 +1168,9 @@ static int sec_aead_setkey(struct crypto_aead *tfm, const u8 *key,
 		goto bad_key;
 	}
 
-	if ((ctx->a_ctx.mac_len & SEC_SQE_LEN_RATE_MASK)  ||
-	    (ctx->a_ctx.a_key_len & SEC_SQE_LEN_RATE_MASK)) {
-		ret = -EINVAL;
-		dev_err(dev, "MAC or AUTH key length error!\n");
+	ret = sec_aead_fallback_setkey(a_ctx, tfm, key, keylen);
+	if (ret) {
+		dev_err(dev, "set sec fallback key err!\n");
 		goto bad_key;
 	}
 
@@ -1202,27 +1182,19 @@ bad_key:
 }
 
 
-#define GEN_SEC_AEAD_SETKEY_FUNC(name, aalg, calg, maclen, cmode)	\
-static int sec_setkey_##name(struct crypto_aead *tfm, const u8 *key,	\
-	u32 keylen)							\
-{									\
-	return sec_aead_setkey(tfm, key, keylen, aalg, calg, maclen, cmode);\
-}
-
-GEN_SEC_AEAD_SETKEY_FUNC(aes_cbc_sha1, SEC_A_HMAC_SHA1,
-			 SEC_CALG_AES, SEC_HMAC_SHA1_MAC, SEC_CMODE_CBC)
-GEN_SEC_AEAD_SETKEY_FUNC(aes_cbc_sha256, SEC_A_HMAC_SHA256,
-			 SEC_CALG_AES, SEC_HMAC_SHA256_MAC, SEC_CMODE_CBC)
-GEN_SEC_AEAD_SETKEY_FUNC(aes_cbc_sha512, SEC_A_HMAC_SHA512,
-			 SEC_CALG_AES, SEC_HMAC_SHA512_MAC, SEC_CMODE_CBC)
-GEN_SEC_AEAD_SETKEY_FUNC(aes_ccm, 0, SEC_CALG_AES,
-			 SEC_HMAC_CCM_MAC, SEC_CMODE_CCM)
-GEN_SEC_AEAD_SETKEY_FUNC(aes_gcm, 0, SEC_CALG_AES,
-			 SEC_HMAC_GCM_MAC, SEC_CMODE_GCM)
-GEN_SEC_AEAD_SETKEY_FUNC(sm4_ccm, 0, SEC_CALG_SM4,
-			 SEC_HMAC_CCM_MAC, SEC_CMODE_CCM)
-GEN_SEC_AEAD_SETKEY_FUNC(sm4_gcm, 0, SEC_CALG_SM4,
-			 SEC_HMAC_GCM_MAC, SEC_CMODE_GCM)
+#define GEN_SEC_AEAD_SETKEY_FUNC(name, aalg, calg, cmode)				\
+static int sec_setkey_##name(struct crypto_aead *tfm, const u8 *key, u32 keylen)	\
+{											\
+	return sec_aead_setkey(tfm, key, keylen, aalg, calg, cmode);			\
+}
+
+GEN_SEC_AEAD_SETKEY_FUNC(aes_cbc_sha1, SEC_A_HMAC_SHA1, SEC_CALG_AES, SEC_CMODE_CBC)
+GEN_SEC_AEAD_SETKEY_FUNC(aes_cbc_sha256, SEC_A_HMAC_SHA256, SEC_CALG_AES, SEC_CMODE_CBC)
+GEN_SEC_AEAD_SETKEY_FUNC(aes_cbc_sha512, SEC_A_HMAC_SHA512, SEC_CALG_AES, SEC_CMODE_CBC)
+GEN_SEC_AEAD_SETKEY_FUNC(aes_ccm, 0, SEC_CALG_AES, SEC_CMODE_CCM)
+GEN_SEC_AEAD_SETKEY_FUNC(aes_gcm, 0, SEC_CALG_AES, SEC_CMODE_GCM)
+GEN_SEC_AEAD_SETKEY_FUNC(sm4_ccm, 0, SEC_CALG_SM4, SEC_CMODE_CCM)
+GEN_SEC_AEAD_SETKEY_FUNC(sm4_gcm, 0, SEC_CALG_SM4, SEC_CMODE_GCM)
 
 static int sec_aead_sgl_map(struct sec_ctx *ctx, struct sec_req *req)
 {
@@ -1470,9 +1442,10 @@ static void sec_skcipher_callback(struct sec_ctx *ctx, struct sec_req *req,
 static void set_aead_auth_iv(struct sec_ctx *ctx, struct sec_req *req)
 {
 	struct aead_request *aead_req = req->aead_req.aead_req;
-	struct sec_cipher_req *c_req = &req->c_req;
+	struct crypto_aead *tfm = crypto_aead_reqtfm(aead_req);
+	size_t authsize = crypto_aead_authsize(tfm);
 	struct sec_aead_req *a_req = &req->aead_req;
-	size_t authsize = ctx->a_ctx.mac_len;
+	struct sec_cipher_req *c_req = &req->c_req;
 	u32 data_size = aead_req->cryptlen;
 	u8 flage = 0;
 	u8 cm, cl;
@@ -1513,10 +1486,8 @@ static void set_aead_auth_iv(struct sec_ctx *ctx, struct sec_req *req)
 static void sec_aead_set_iv(struct sec_ctx *ctx, struct sec_req *req)
 {
 	struct aead_request *aead_req = req->aead_req.aead_req;
-	struct crypto_aead *tfm = crypto_aead_reqtfm(aead_req);
-	size_t authsize = crypto_aead_authsize(tfm);
-	struct sec_cipher_req *c_req = &req->c_req;
 	struct sec_aead_req *a_req = &req->aead_req;
+	struct sec_cipher_req *c_req = &req->c_req;
 
 	memcpy(c_req->c_ivin, aead_req->iv, ctx->c_ctx.ivsize);
 
@@ -1524,15 +1495,11 @@ static void sec_aead_set_iv(struct sec_ctx *ctx, struct sec_req *req)
 		/*
 		 * CCM 16Byte Cipher_IV: {1B_Flage,13B_IV,2B_counter},
 		 * the  counter must set to 0x01
+		 * CCM 16Byte Auth_IV: {1B_AFlage,13B_IV,2B_Ptext_length}
 		 */
-		ctx->a_ctx.mac_len = authsize;
-		/* CCM 16Byte Auth_IV: {1B_AFlage,13B_IV,2B_Ptext_length} */
 		set_aead_auth_iv(ctx, req);
-	}
-
-	/* GCM 12Byte Cipher_IV == Auth_IV */
-	if (ctx->c_ctx.c_mode == SEC_CMODE_GCM) {
-		ctx->a_ctx.mac_len = authsize;
+	} else if (ctx->c_ctx.c_mode == SEC_CMODE_GCM) {
+		/* GCM 12Byte Cipher_IV == Auth_IV */
 		memcpy(a_req->a_ivin, c_req->c_ivin, SEC_AIV_SIZE);
 	}
 }
@@ -1542,9 +1509,11 @@ static void sec_auth_bd_fill_xcm(struct sec_auth_ctx *ctx, int dir,
 {
 	struct sec_aead_req *a_req = &req->aead_req;
 	struct aead_request *aq = a_req->aead_req;
+	struct crypto_aead *tfm = crypto_aead_reqtfm(aq);
+	size_t authsize = crypto_aead_authsize(tfm);
 
 	/* C_ICV_Len is MAC size, 0x4 ~ 0x10 */
-	sec_sqe->type2.icvw_kmode |= cpu_to_le16((u16)ctx->mac_len);
+	sec_sqe->type2.icvw_kmode |= cpu_to_le16((u16)authsize);
 
 	/* mode set to CCM/GCM, don't set {A_Alg, AKey_Len, MAC_Len} */
 	sec_sqe->type2.a_key_addr = sec_sqe->type2.c_key_addr;
@@ -1568,9 +1537,11 @@ static void sec_auth_bd_fill_xcm_v3(struct sec_auth_ctx *ctx, int dir,
 {
 	struct sec_aead_req *a_req = &req->aead_req;
 	struct aead_request *aq = a_req->aead_req;
+	struct crypto_aead *tfm = crypto_aead_reqtfm(aq);
+	size_t authsize = crypto_aead_authsize(tfm);
 
 	/* C_ICV_Len is MAC size, 0x4 ~ 0x10 */
-	sqe3->c_icv_key |= cpu_to_le16((u16)ctx->mac_len << SEC_MAC_OFFSET_V3);
+	sqe3->c_icv_key |= cpu_to_le16((u16)authsize << SEC_MAC_OFFSET_V3);
 
 	/* mode set to CCM/GCM, don't set {A_Alg, AKey_Len, MAC_Len} */
 	sqe3->a_key_addr = sqe3->c_key_addr;
@@ -1594,15 +1565,15 @@ static void sec_auth_bd_fill_ex(struct sec_auth_ctx *ctx, int dir,
 	struct sec_aead_req *a_req = &req->aead_req;
 	struct sec_cipher_req *c_req = &req->c_req;
 	struct aead_request *aq = a_req->aead_req;
+	struct crypto_aead *tfm = crypto_aead_reqtfm(aq);
+	size_t authsize = crypto_aead_authsize(tfm);
 
 	sec_sqe->type2.a_key_addr = cpu_to_le64(ctx->a_key_dma);
 
-	sec_sqe->type2.mac_key_alg =
-			cpu_to_le32(ctx->mac_len / SEC_SQE_LEN_RATE);
+	sec_sqe->type2.mac_key_alg = cpu_to_le32(BYTES_TO_WORDS(authsize));
 
 	sec_sqe->type2.mac_key_alg |=
-			cpu_to_le32((u32)((ctx->a_key_len) /
-			SEC_SQE_LEN_RATE) << SEC_AKEY_OFFSET);
+			cpu_to_le32((u32)BYTES_TO_WORDS(ctx->a_key_len) << SEC_AKEY_OFFSET);
 
 	sec_sqe->type2.mac_key_alg |=
 			cpu_to_le32((u32)(ctx->a_alg) << SEC_AEAD_ALG_OFFSET);
@@ -1648,16 +1619,16 @@ static void sec_auth_bd_fill_ex_v3(struct sec_auth_ctx *ctx, int dir,
 	struct sec_aead_req *a_req = &req->aead_req;
 	struct sec_cipher_req *c_req = &req->c_req;
 	struct aead_request *aq = a_req->aead_req;
+	struct crypto_aead *tfm = crypto_aead_reqtfm(aq);
+	size_t authsize = crypto_aead_authsize(tfm);
 
 	sqe3->a_key_addr = cpu_to_le64(ctx->a_key_dma);
 
 	sqe3->auth_mac_key |=
-			cpu_to_le32((u32)(ctx->mac_len /
-			SEC_SQE_LEN_RATE) << SEC_MAC_OFFSET_V3);
+			cpu_to_le32(BYTES_TO_WORDS(authsize) << SEC_MAC_OFFSET_V3);
 
 	sqe3->auth_mac_key |=
-			cpu_to_le32((u32)(ctx->a_key_len /
-			SEC_SQE_LEN_RATE) << SEC_AKEY_OFFSET_V3);
+			cpu_to_le32((u32)BYTES_TO_WORDS(ctx->a_key_len) << SEC_AKEY_OFFSET_V3);
 
 	sqe3->auth_mac_key |=
 			cpu_to_le32((u32)(ctx->a_alg) << SEC_AUTH_ALG_OFFSET_V3);
@@ -1703,9 +1674,9 @@ static void sec_aead_callback(struct sec_ctx *c, struct sec_req *req, int err)
 {
 	struct aead_request *a_req = req->aead_req.aead_req;
 	struct crypto_aead *tfm = crypto_aead_reqtfm(a_req);
+	size_t authsize = crypto_aead_authsize(tfm);
 	struct sec_aead_req *aead_req = &req->aead_req;
 	struct sec_cipher_req *c_req = &req->c_req;
-	size_t authsize = crypto_aead_authsize(tfm);
 	struct sec_qp_ctx *qp_ctx = req->qp_ctx;
 	struct aead_request *backlog_aead_req;
 	struct sec_req *backlog_req;
@@ -1718,10 +1689,8 @@ static void sec_aead_callback(struct sec_ctx *c, struct sec_req *req, int err)
 	if (!err && c_req->encrypt) {
 		struct scatterlist *sgl = a_req->dst;
 
-		sz = sg_pcopy_from_buffer(sgl, sg_nents(sgl),
-					  aead_req->out_mac,
-					  authsize, a_req->cryptlen +
-					  a_req->assoclen);
+		sz = sg_pcopy_from_buffer(sgl, sg_nents(sgl), aead_req->out_mac,
+					  authsize, a_req->cryptlen + a_req->assoclen);
 		if (unlikely(sz != authsize)) {
 			dev_err(c->dev, "copy out mac err!\n");
 			err = -EINVAL;
@@ -1929,8 +1898,10 @@ static void sec_aead_exit(struct crypto_aead *tfm)
 
 static int sec_aead_ctx_init(struct crypto_aead *tfm, const char *hash_name)
 {
+	struct aead_alg *alg = crypto_aead_alg(tfm);
 	struct sec_ctx *ctx = crypto_aead_ctx(tfm);
-	struct sec_auth_ctx *auth_ctx = &ctx->a_ctx;
+	struct sec_auth_ctx *a_ctx = &ctx->a_ctx;
+	const char *aead_name = alg->base.cra_name;
 	int ret;
 
 	ret = sec_aead_init(tfm);
@@ -1939,11 +1910,20 @@ static int sec_aead_ctx_init(struct crypto_aead *tfm, const char *hash_name)
 		return ret;
 	}
 
-	auth_ctx->hash_tfm = crypto_alloc_shash(hash_name, 0, 0);
-	if (IS_ERR(auth_ctx->hash_tfm)) {
+	a_ctx->hash_tfm = crypto_alloc_shash(hash_name, 0, 0);
+	if (IS_ERR(a_ctx->hash_tfm)) {
 		dev_err(ctx->dev, "aead alloc shash error!\n");
 		sec_aead_exit(tfm);
-		return PTR_ERR(auth_ctx->hash_tfm);
+		return PTR_ERR(a_ctx->hash_tfm);
+	}
+
+	a_ctx->fallback_aead_tfm = crypto_alloc_aead(aead_name, 0,
+						     CRYPTO_ALG_NEED_FALLBACK | CRYPTO_ALG_ASYNC);
+	if (IS_ERR(a_ctx->fallback_aead_tfm)) {
+		dev_err(ctx->dev, "aead driver alloc fallback tfm error!\n");
+		crypto_free_shash(ctx->a_ctx.hash_tfm);
+		sec_aead_exit(tfm);
+		return PTR_ERR(a_ctx->fallback_aead_tfm);
 	}
 
 	return 0;
@@ -1953,6 +1933,7 @@ static void sec_aead_ctx_exit(struct crypto_aead *tfm)
 {
 	struct sec_ctx *ctx = crypto_aead_ctx(tfm);
 
+	crypto_free_aead(ctx->a_ctx.fallback_aead_tfm);
 	crypto_free_shash(ctx->a_ctx.hash_tfm);
 	sec_aead_exit(tfm);
 }
@@ -1979,7 +1960,6 @@ static int sec_aead_xcm_ctx_init(struct crypto_aead *tfm)
 		sec_aead_exit(tfm);
 		return PTR_ERR(a_ctx->fallback_aead_tfm);
 	}
-	a_ctx->fallback = false;
 
 	return 0;
 }
@@ -2007,8 +1987,7 @@ static int sec_aead_sha512_ctx_init(struct crypto_aead *tfm)
 	return sec_aead_ctx_init(tfm, "sha512");
 }
 
-static int sec_skcipher_cryptlen_check(struct sec_ctx *ctx,
-	struct sec_req *sreq)
+static int sec_skcipher_cryptlen_check(struct sec_ctx *ctx, struct sec_req *sreq)
 {
 	u32 cryptlen = sreq->c_req.sk_req->cryptlen;
 	struct device *dev = ctx->dev;
@@ -2030,10 +2009,6 @@ static int sec_skcipher_cryptlen_check(struct sec_ctx *ctx,
 		}
 		break;
 	case SEC_CMODE_CTR:
-		if (unlikely(ctx->sec->qm.ver < QM_HW_V3)) {
-			dev_err(dev, "skcipher HW version error!\n");
-			ret = -EINVAL;
-		}
 		break;
 	default:
 		ret = -EINVAL;
@@ -2042,17 +2017,21 @@ static int sec_skcipher_cryptlen_check(struct sec_ctx *ctx,
 	return ret;
 }
 
-static int sec_skcipher_param_check(struct sec_ctx *ctx, struct sec_req *sreq)
+static int sec_skcipher_param_check(struct sec_ctx *ctx,
+				    struct sec_req *sreq, bool *need_fallback)
 {
 	struct skcipher_request *sk_req = sreq->c_req.sk_req;
 	struct device *dev = ctx->dev;
 	u8 c_alg = ctx->c_ctx.c_alg;
 
-	if (unlikely(!sk_req->src || !sk_req->dst ||
-		     sk_req->cryptlen > MAX_INPUT_DATA_LEN)) {
+	if (unlikely(!sk_req->src || !sk_req->dst)) {
 		dev_err(dev, "skcipher input param error!\n");
 		return -EINVAL;
 	}
+
+	if (sk_req->cryptlen > MAX_INPUT_DATA_LEN)
+		*need_fallback = true;
+
 	sreq->c_req.c_len = sk_req->cryptlen;
 
 	if (ctx->pbuf_supported && sk_req->cryptlen <= SEC_PBUF_SZ)
@@ -2110,6 +2089,7 @@ static int sec_skcipher_crypto(struct skcipher_request *sk_req, bool encrypt)
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(sk_req);
 	struct sec_req *req = skcipher_request_ctx(sk_req);
 	struct sec_ctx *ctx = crypto_skcipher_ctx(tfm);
+	bool need_fallback = false;
 	int ret;
 
 	if (!sk_req->cryptlen) {
@@ -2123,11 +2103,11 @@ static int sec_skcipher_crypto(struct skcipher_request *sk_req, bool encrypt)
 	req->c_req.encrypt = encrypt;
 	req->ctx = ctx;
 
-	ret = sec_skcipher_param_check(ctx, req);
+	ret = sec_skcipher_param_check(ctx, req, &need_fallback);
 	if (unlikely(ret))
 		return -EINVAL;
 
-	if (unlikely(ctx->c_ctx.fallback))
+	if (unlikely(ctx->c_ctx.fallback || need_fallback))
 		return sec_skcipher_soft_crypto(ctx, sk_req, encrypt);
 
 	return ctx->req_op->process(ctx, req);
@@ -2233,55 +2213,37 @@ static int sec_aead_spec_check(struct sec_ctx *ctx, struct sec_req *sreq)
 {
 	struct aead_request *req = sreq->aead_req.aead_req;
 	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
-	size_t authsize = crypto_aead_authsize(tfm);
+	size_t sz = crypto_aead_authsize(tfm);
 	u8 c_mode = ctx->c_ctx.c_mode;
-	struct device *dev = ctx->dev;
 	int ret;
 
-	if (unlikely(req->cryptlen + req->assoclen > MAX_INPUT_DATA_LEN ||
-	    req->assoclen > SEC_MAX_AAD_LEN)) {
-		dev_err(dev, "aead input spec error!\n");
+	if (unlikely(ctx->sec->qm.ver == QM_HW_V2 && !sreq->c_req.c_len))
 		return -EINVAL;
-	}
 
-	if (unlikely((c_mode == SEC_CMODE_GCM && authsize < DES_BLOCK_SIZE) ||
-	   (c_mode == SEC_CMODE_CCM && (authsize < MIN_MAC_LEN ||
-		authsize & MAC_LEN_MASK)))) {
-		dev_err(dev, "aead input mac length error!\n");
+	if (unlikely(req->cryptlen + req->assoclen > MAX_INPUT_DATA_LEN ||
+		     req->assoclen > SEC_MAX_AAD_LEN))
 		return -EINVAL;
-	}
 
 	if (c_mode == SEC_CMODE_CCM) {
-		if (unlikely(req->assoclen > SEC_MAX_CCM_AAD_LEN)) {
-			dev_err_ratelimited(dev, "CCM input aad parameter is too long!\n");
+		if (unlikely(req->assoclen > SEC_MAX_CCM_AAD_LEN))
 			return -EINVAL;
-		}
-		ret = aead_iv_demension_check(req);
-		if (ret) {
-			dev_err(dev, "aead input iv param error!\n");
-			return ret;
-		}
-	}
 
-	if (sreq->c_req.encrypt)
-		sreq->c_req.c_len = req->cryptlen;
-	else
-		sreq->c_req.c_len = req->cryptlen - authsize;
-	if (c_mode == SEC_CMODE_CBC) {
-		if (unlikely(sreq->c_req.c_len & (AES_BLOCK_SIZE - 1))) {
-			dev_err(dev, "aead crypto length error!\n");
+		ret = aead_iv_demension_check(req);
+		if (unlikely(ret))
+			return -EINVAL;
+	} else if (c_mode == SEC_CMODE_CBC) {
+		if (unlikely(sz & WORD_MASK))
+			return -EINVAL;
+		if (unlikely(ctx->a_ctx.a_key_len & WORD_MASK))
 			return -EINVAL;
-		}
 	}
 
 	return 0;
 }
 
-static int sec_aead_param_check(struct sec_ctx *ctx, struct sec_req *sreq)
+static int sec_aead_param_check(struct sec_ctx *ctx, struct sec_req *sreq, bool *need_fallback)
 {
 	struct aead_request *req = sreq->aead_req.aead_req;
-	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
-	size_t authsize = crypto_aead_authsize(tfm);
 	struct device *dev = ctx->dev;
 	u8 c_alg = ctx->c_ctx.c_alg;
 
@@ -2290,12 +2252,10 @@ static int sec_aead_param_check(struct sec_ctx *ctx, struct sec_req *sreq)
 		return -EINVAL;
 	}
 
-	if (ctx->sec->qm.ver == QM_HW_V2) {
-		if (unlikely(!req->cryptlen || (!sreq->c_req.encrypt &&
-		    req->cryptlen <= authsize))) {
-			ctx->a_ctx.fallback = true;
-			return -EINVAL;
-		}
+	if (unlikely(ctx->c_ctx.c_mode == SEC_CMODE_CBC &&
+		     sreq->c_req.c_len & (AES_BLOCK_SIZE - 1))) {
+		dev_err(dev, "aead cbc mode input data length error!\n");
+		return -EINVAL;
 	}
 
 	/* Support AES or SM4 */
@@ -2304,8 +2264,10 @@ static int sec_aead_param_check(struct sec_ctx *ctx, struct sec_req *sreq)
 		return -EINVAL;
 	}
 
-	if (unlikely(sec_aead_spec_check(ctx, sreq)))
+	if (unlikely(sec_aead_spec_check(ctx, sreq))) {
+		*need_fallback = true;
 		return -EINVAL;
+	}
 
 	if (ctx->pbuf_supported && (req->cryptlen + req->assoclen) <=
 		SEC_PBUF_SZ)
@@ -2321,16 +2283,9 @@ static int sec_aead_soft_crypto(struct sec_ctx *ctx,
 				bool encrypt)
 {
 	struct sec_auth_ctx *a_ctx = &ctx->a_ctx;
-	struct device *dev = ctx->dev;
 	struct aead_request *subreq;
 	int ret;
 
-	/* Kunpeng920 aead mode not support input 0 size */
-	if (!a_ctx->fallback_aead_tfm) {
-		dev_err(dev, "aead fallback tfm is NULL!\n");
-		return -EINVAL;
-	}
-
 	subreq = aead_request_alloc(a_ctx->fallback_aead_tfm, GFP_KERNEL);
 	if (!subreq)
 		return -ENOMEM;
@@ -2356,16 +2311,19 @@ static int sec_aead_crypto(struct aead_request *a_req, bool encrypt)
 	struct crypto_aead *tfm = crypto_aead_reqtfm(a_req);
 	struct sec_req *req = aead_request_ctx(a_req);
 	struct sec_ctx *ctx = crypto_aead_ctx(tfm);
+	size_t sz = crypto_aead_authsize(tfm);
+	bool need_fallback = false;
 	int ret;
 
 	req->flag = a_req->base.flags;
 	req->aead_req.aead_req = a_req;
 	req->c_req.encrypt = encrypt;
 	req->ctx = ctx;
+	req->c_req.c_len = a_req->cryptlen - (req->c_req.encrypt ? 0 : sz);
 
-	ret = sec_aead_param_check(ctx, req);
+	ret = sec_aead_param_check(ctx, req, &need_fallback);
 	if (unlikely(ret)) {
-		if (ctx->a_ctx.fallback)
+		if (need_fallback)
 			return sec_aead_soft_crypto(ctx, a_req, encrypt);
 		return -EINVAL;
 	}
diff --git a/drivers/crypto/hisilicon/sec2/sec_crypto.h b/drivers/crypto/hisilicon/sec2/sec_crypto.h
index 27a0ee5ad913..04725b514382 100644
--- a/drivers/crypto/hisilicon/sec2/sec_crypto.h
+++ b/drivers/crypto/hisilicon/sec2/sec_crypto.h
@@ -23,17 +23,6 @@ enum sec_hash_alg {
 	SEC_A_HMAC_SHA512 = 0x15,
 };
 
-enum sec_mac_len {
-	SEC_HMAC_CCM_MAC   = 16,
-	SEC_HMAC_GCM_MAC   = 16,
-	SEC_SM3_MAC        = 32,
-	SEC_HMAC_SM3_MAC   = 32,
-	SEC_HMAC_MD5_MAC   = 16,
-	SEC_HMAC_SHA1_MAC   = 20,
-	SEC_HMAC_SHA256_MAC = 32,
-	SEC_HMAC_SHA512_MAC = 64,
-};
-
 enum sec_cmode {
 	SEC_CMODE_ECB    = 0x0,
 	SEC_CMODE_CBC    = 0x1,
diff --git a/drivers/crypto/img-hash.c b/drivers/crypto/img-hash.c
index 7e93159c3b6b..d5df3d2da50c 100644
--- a/drivers/crypto/img-hash.c
+++ b/drivers/crypto/img-hash.c
@@ -436,7 +436,7 @@ static int img_hash_write_via_dma_stop(struct img_hash_dev *hdev)
 	struct img_hash_request_ctx *ctx = ahash_request_ctx(hdev->req);
 
 	if (ctx->flags & DRIVER_FLAGS_SG)
-		dma_unmap_sg(hdev->dev, ctx->sg, ctx->dma_ct, DMA_TO_DEVICE);
+		dma_unmap_sg(hdev->dev, ctx->sg, 1, DMA_TO_DEVICE);
 
 	return 0;
 }
diff --git a/drivers/crypto/inside-secure/safexcel_hash.c b/drivers/crypto/inside-secure/safexcel_hash.c
index f44c08f5f5ec..af4b978189e5 100644
--- a/drivers/crypto/inside-secure/safexcel_hash.c
+++ b/drivers/crypto/inside-secure/safexcel_hash.c
@@ -249,7 +249,9 @@ static int safexcel_handle_req_result(struct safexcel_crypto_priv *priv,
 	safexcel_complete(priv, ring);
 
 	if (sreq->nents) {
-		dma_unmap_sg(priv->dev, areq->src, sreq->nents, DMA_TO_DEVICE);
+		dma_unmap_sg(priv->dev, areq->src,
+			     sg_nents_for_len(areq->src, areq->nbytes),
+			     DMA_TO_DEVICE);
 		sreq->nents = 0;
 	}
 
@@ -497,7 +499,9 @@ unmap_result:
 			 DMA_FROM_DEVICE);
 unmap_sg:
 	if (req->nents) {
-		dma_unmap_sg(priv->dev, areq->src, req->nents, DMA_TO_DEVICE);
+		dma_unmap_sg(priv->dev, areq->src,
+			     sg_nents_for_len(areq->src, areq->nbytes),
+			     DMA_TO_DEVICE);
 		req->nents = 0;
 	}
 cdesc_rollback:
diff --git a/drivers/crypto/intel/iaa/Makefile b/drivers/crypto/intel/iaa/Makefile
index b64b208d2344..55bda7770fac 100644
--- a/drivers/crypto/intel/iaa/Makefile
+++ b/drivers/crypto/intel/iaa/Makefile
@@ -3,7 +3,7 @@
 # Makefile for IAA crypto device drivers
 #
 
-ccflags-y += -I $(srctree)/drivers/dma/idxd -DDEFAULT_SYMBOL_NAMESPACE=IDXD
+ccflags-y += -I $(srctree)/drivers/dma/idxd -DDEFAULT_SYMBOL_NAMESPACE='"IDXD"'
 
 obj-$(CONFIG_CRYPTO_DEV_IAA_CRYPTO) := iaa_crypto.o
 
diff --git a/drivers/crypto/intel/iaa/iaa_crypto_main.c b/drivers/crypto/intel/iaa/iaa_crypto_main.c
index 237f87000070..df2728cccf8b 100644
--- a/drivers/crypto/intel/iaa/iaa_crypto_main.c
+++ b/drivers/crypto/intel/iaa/iaa_crypto_main.c
@@ -173,7 +173,7 @@ static int set_iaa_sync_mode(const char *name)
 		async_mode = false;
 		use_irq = false;
 	} else if (sysfs_streq(name, "async")) {
-		async_mode = true;
+		async_mode = false;
 		use_irq = false;
 	} else if (sysfs_streq(name, "async_irq")) {
 		async_mode = true;
@@ -1126,8 +1126,7 @@ static int iaa_compress(struct crypto_tfm *tfm,	struct acomp_req *req,
 			struct idxd_wq *wq,
 			dma_addr_t src_addr, unsigned int slen,
 			dma_addr_t dst_addr, unsigned int *dlen,
-			u32 *compression_crc,
-			bool disable_async)
+			u32 *compression_crc)
 {
 	struct iaa_device_compression_mode *active_compression_mode;
 	struct iaa_compression_ctx *ctx = crypto_tfm_ctx(tfm);
@@ -1170,7 +1169,7 @@ static int iaa_compress(struct crypto_tfm *tfm,	struct acomp_req *req,
 	desc->src2_size = sizeof(struct aecs_comp_table_record);
 	desc->completion_addr = idxd_desc->compl_dma;
 
-	if (ctx->use_irq && !disable_async) {
+	if (ctx->use_irq) {
 		desc->flags |= IDXD_OP_FLAG_RCI;
 
 		idxd_desc->crypto.req = req;
@@ -1183,8 +1182,7 @@ static int iaa_compress(struct crypto_tfm *tfm,	struct acomp_req *req,
 			" src_addr %llx, dst_addr %llx\n", __func__,
 			active_compression_mode->name,
 			src_addr, dst_addr);
-	} else if (ctx->async_mode && !disable_async)
-		req->base.data = idxd_desc;
+	}
 
 	dev_dbg(dev, "%s: compression mode %s,"
 		" desc->src1_addr %llx, desc->src1_size %d,"
@@ -1204,7 +1202,7 @@ static int iaa_compress(struct crypto_tfm *tfm,	struct acomp_req *req,
 	update_total_comp_calls();
 	update_wq_comp_calls(wq);
 
-	if (ctx->async_mode && !disable_async) {
+	if (ctx->async_mode) {
 		ret = -EINPROGRESS;
 		dev_dbg(dev, "%s: returning -EINPROGRESS\n", __func__);
 		goto out;
@@ -1224,7 +1222,7 @@ static int iaa_compress(struct crypto_tfm *tfm,	struct acomp_req *req,
 
 	*compression_crc = idxd_desc->iax_completion->crc;
 
-	if (!ctx->async_mode || disable_async)
+	if (!ctx->async_mode)
 		idxd_free_desc(wq, idxd_desc);
 out:
 	return ret;
@@ -1421,8 +1419,7 @@ static int iaa_decompress(struct crypto_tfm *tfm, struct acomp_req *req,
 			" src_addr %llx, dst_addr %llx\n", __func__,
 			active_compression_mode->name,
 			src_addr, dst_addr);
-	} else if (ctx->async_mode && !disable_async)
-		req->base.data = idxd_desc;
+	}
 
 	dev_dbg(dev, "%s: decompression mode %s,"
 		" desc->src1_addr %llx, desc->src1_size %d,"
@@ -1490,13 +1487,11 @@ static int iaa_comp_acompress(struct acomp_req *req)
 	struct iaa_compression_ctx *compression_ctx;
 	struct crypto_tfm *tfm = req->base.tfm;
 	dma_addr_t src_addr, dst_addr;
-	bool disable_async = false;
 	int nr_sgs, cpu, ret = 0;
 	struct iaa_wq *iaa_wq;
 	u32 compression_crc;
 	struct idxd_wq *wq;
 	struct device *dev;
-	int order = -1;
 
 	compression_ctx = crypto_tfm_ctx(tfm);
 
@@ -1526,21 +1521,6 @@ static int iaa_comp_acompress(struct acomp_req *req)
 
 	iaa_wq = idxd_wq_get_private(wq);
 
-	if (!req->dst) {
-		gfp_t flags = req->flags & CRYPTO_TFM_REQ_MAY_SLEEP ? GFP_KERNEL : GFP_ATOMIC;
-
-		/* incompressible data will always be < 2 * slen */
-		req->dlen = 2 * req->slen;
-		order = order_base_2(round_up(req->dlen, PAGE_SIZE) / PAGE_SIZE);
-		req->dst = sgl_alloc_order(req->dlen, order, false, flags, NULL);
-		if (!req->dst) {
-			ret = -ENOMEM;
-			order = -1;
-			goto out;
-		}
-		disable_async = true;
-	}
-
 	dev = &wq->idxd->pdev->dev;
 
 	nr_sgs = dma_map_sg(dev, req->src, sg_nents(req->src), DMA_TO_DEVICE);
@@ -1570,7 +1550,7 @@ static int iaa_comp_acompress(struct acomp_req *req)
 		req->dst, req->dlen, sg_dma_len(req->dst));
 
 	ret = iaa_compress(tfm, req, wq, src_addr, req->slen, dst_addr,
-			   &req->dlen, &compression_crc, disable_async);
+			   &req->dlen, &compression_crc);
 	if (ret == -EINPROGRESS)
 		return ret;
 
@@ -1601,100 +1581,6 @@ err_map_dst:
 out:
 	iaa_wq_put(wq);
 
-	if (order >= 0)
-		sgl_free_order(req->dst, order);
-
-	return ret;
-}
-
-static int iaa_comp_adecompress_alloc_dest(struct acomp_req *req)
-{
-	gfp_t flags = req->flags & CRYPTO_TFM_REQ_MAY_SLEEP ?
-		GFP_KERNEL : GFP_ATOMIC;
-	struct crypto_tfm *tfm = req->base.tfm;
-	dma_addr_t src_addr, dst_addr;
-	int nr_sgs, cpu, ret = 0;
-	struct iaa_wq *iaa_wq;
-	struct device *dev;
-	struct idxd_wq *wq;
-	int order = -1;
-
-	cpu = get_cpu();
-	wq = wq_table_next_wq(cpu);
-	put_cpu();
-	if (!wq) {
-		pr_debug("no wq configured for cpu=%d\n", cpu);
-		return -ENODEV;
-	}
-
-	ret = iaa_wq_get(wq);
-	if (ret) {
-		pr_debug("no wq available for cpu=%d\n", cpu);
-		return -ENODEV;
-	}
-
-	iaa_wq = idxd_wq_get_private(wq);
-
-	dev = &wq->idxd->pdev->dev;
-
-	nr_sgs = dma_map_sg(dev, req->src, sg_nents(req->src), DMA_TO_DEVICE);
-	if (nr_sgs <= 0 || nr_sgs > 1) {
-		dev_dbg(dev, "couldn't map src sg for iaa device %d,"
-			" wq %d: ret=%d\n", iaa_wq->iaa_device->idxd->id,
-			iaa_wq->wq->id, ret);
-		ret = -EIO;
-		goto out;
-	}
-	src_addr = sg_dma_address(req->src);
-	dev_dbg(dev, "dma_map_sg, src_addr %llx, nr_sgs %d, req->src %p,"
-		" req->slen %d, sg_dma_len(sg) %d\n", src_addr, nr_sgs,
-		req->src, req->slen, sg_dma_len(req->src));
-
-	req->dlen = 4 * req->slen; /* start with ~avg comp rato */
-alloc_dest:
-	order = order_base_2(round_up(req->dlen, PAGE_SIZE) / PAGE_SIZE);
-	req->dst = sgl_alloc_order(req->dlen, order, false, flags, NULL);
-	if (!req->dst) {
-		ret = -ENOMEM;
-		order = -1;
-		goto out;
-	}
-
-	nr_sgs = dma_map_sg(dev, req->dst, sg_nents(req->dst), DMA_FROM_DEVICE);
-	if (nr_sgs <= 0 || nr_sgs > 1) {
-		dev_dbg(dev, "couldn't map dst sg for iaa device %d,"
-			" wq %d: ret=%d\n", iaa_wq->iaa_device->idxd->id,
-			iaa_wq->wq->id, ret);
-		ret = -EIO;
-		goto err_map_dst;
-	}
-
-	dst_addr = sg_dma_address(req->dst);
-	dev_dbg(dev, "dma_map_sg, dst_addr %llx, nr_sgs %d, req->dst %p,"
-		" req->dlen %d, sg_dma_len(sg) %d\n", dst_addr, nr_sgs,
-		req->dst, req->dlen, sg_dma_len(req->dst));
-	ret = iaa_decompress(tfm, req, wq, src_addr, req->slen,
-			     dst_addr, &req->dlen, true);
-	if (ret == -EOVERFLOW) {
-		dma_unmap_sg(dev, req->dst, sg_nents(req->dst), DMA_FROM_DEVICE);
-		req->dlen *= 2;
-		if (req->dlen > CRYPTO_ACOMP_DST_MAX)
-			goto err_map_dst;
-		goto alloc_dest;
-	}
-
-	if (ret != 0)
-		dev_dbg(dev, "asynchronous decompress failed ret=%d\n", ret);
-
-	dma_unmap_sg(dev, req->dst, sg_nents(req->dst), DMA_FROM_DEVICE);
-err_map_dst:
-	dma_unmap_sg(dev, req->src, sg_nents(req->src), DMA_TO_DEVICE);
-out:
-	iaa_wq_put(wq);
-
-	if (order >= 0)
-		sgl_free_order(req->dst, order);
-
 	return ret;
 }
 
@@ -1717,9 +1603,6 @@ static int iaa_comp_adecompress(struct acomp_req *req)
 		return -EINVAL;
 	}
 
-	if (!req->dst)
-		return iaa_comp_adecompress_alloc_dest(req);
-
 	cpu = get_cpu();
 	wq = wq_table_next_wq(cpu);
 	put_cpu();
@@ -1800,19 +1683,10 @@ static int iaa_comp_init_fixed(struct crypto_acomp *acomp_tfm)
 	return 0;
 }
 
-static void dst_free(struct scatterlist *sgl)
-{
-	/*
-	 * Called for req->dst = NULL cases but we free elsewhere
-	 * using sgl_free_order().
-	 */
-}
-
 static struct acomp_alg iaa_acomp_fixed_deflate = {
 	.init			= iaa_comp_init_fixed,
 	.compress		= iaa_comp_acompress,
 	.decompress		= iaa_comp_adecompress,
-	.dst_free               = dst_free,
 	.base			= {
 		.cra_name		= "deflate",
 		.cra_driver_name	= "deflate-iaa",
diff --git a/drivers/crypto/intel/ixp4xx/ixp4xx_crypto.c b/drivers/crypto/intel/ixp4xx/ixp4xx_crypto.c
index f8a77bff8844..e43361392c83 100644
--- a/drivers/crypto/intel/ixp4xx/ixp4xx_crypto.c
+++ b/drivers/crypto/intel/ixp4xx/ixp4xx_crypto.c
@@ -471,6 +471,7 @@ static int init_ixp_crypto(struct device *dev)
 			return -ENODEV;
 		}
 		npe_id = npe_spec.args[0];
+		of_node_put(npe_spec.np);
 
 		ret = of_parse_phandle_with_fixed_args(np, "queue-rx", 1, 0,
 						       &queue_spec);
@@ -479,6 +480,7 @@ static int init_ixp_crypto(struct device *dev)
 			return -ENODEV;
 		}
 		recv_qid = queue_spec.args[0];
+		of_node_put(queue_spec.np);
 
 		ret = of_parse_phandle_with_fixed_args(np, "queue-txready", 1, 0,
 						       &queue_spec);
@@ -487,6 +489,7 @@ static int init_ixp_crypto(struct device *dev)
 			return -ENODEV;
 		}
 		send_qid = queue_spec.args[0];
+		of_node_put(queue_spec.np);
 	} else {
 		/*
 		 * Hardcoded engine when using platform data, this goes away
diff --git a/drivers/crypto/intel/keembay/keembay-ocs-hcu-core.c b/drivers/crypto/intel/keembay/keembay-ocs-hcu-core.c
index e54c79890d44..fdeca861933c 100644
--- a/drivers/crypto/intel/keembay/keembay-ocs-hcu-core.c
+++ b/drivers/crypto/intel/keembay/keembay-ocs-hcu-core.c
@@ -68,6 +68,7 @@ struct ocs_hcu_ctx {
  * @sg_data_total:  Total data in the SG list at any time.
  * @sg_data_offset: Offset into the data of the current individual SG node.
  * @sg_dma_nents:   Number of sg entries mapped in dma_list.
+ * @nents:          Number of entries in the scatterlist.
  */
 struct ocs_hcu_rctx {
 	struct ocs_hcu_dev	*hcu_dev;
@@ -91,6 +92,7 @@ struct ocs_hcu_rctx {
 	unsigned int		sg_data_total;
 	unsigned int		sg_data_offset;
 	unsigned int		sg_dma_nents;
+	unsigned int		nents;
 };
 
 /**
@@ -199,7 +201,7 @@ static void kmb_ocs_hcu_dma_cleanup(struct ahash_request *req,
 
 	/* Unmap req->src (if mapped). */
 	if (rctx->sg_dma_nents) {
-		dma_unmap_sg(dev, req->src, rctx->sg_dma_nents, DMA_TO_DEVICE);
+		dma_unmap_sg(dev, req->src, rctx->nents, DMA_TO_DEVICE);
 		rctx->sg_dma_nents = 0;
 	}
 
@@ -260,6 +262,10 @@ static int kmb_ocs_dma_prepare(struct ahash_request *req)
 			rc = -ENOMEM;
 			goto cleanup;
 		}
+
+		/* Save the value of nents to pass to dma_unmap_sg. */
+		rctx->nents = nents;
+
 		/*
 		 * The value returned by dma_map_sg() can be < nents; so update
 		 * nents accordingly.
diff --git a/drivers/crypto/intel/qat/qat_420xx/adf_420xx_hw_data.c b/drivers/crypto/intel/qat/qat_420xx/adf_420xx_hw_data.c
index 9faef33e54bd..ef5f03be4190 100644
--- a/drivers/crypto/intel/qat/qat_420xx/adf_420xx_hw_data.c
+++ b/drivers/crypto/intel/qat/qat_420xx/adf_420xx_hw_data.c
@@ -199,7 +199,6 @@ static u32 get_accel_cap(struct adf_accel_dev *accel_dev)
 			  ICP_ACCEL_CAPABILITIES_SM4 |
 			  ICP_ACCEL_CAPABILITIES_AES_V2 |
 			  ICP_ACCEL_CAPABILITIES_ZUC |
-			  ICP_ACCEL_CAPABILITIES_ZUC_256 |
 			  ICP_ACCEL_CAPABILITIES_WIRELESS_CRYPTO_EXT |
 			  ICP_ACCEL_CAPABILITIES_EXT_ALGCHAIN;
 
@@ -231,17 +230,11 @@ static u32 get_accel_cap(struct adf_accel_dev *accel_dev)
 
 	if (fusectl1 & ICP_ACCEL_GEN4_MASK_WCP_WAT_SLICE) {
 		capabilities_sym &= ~ICP_ACCEL_CAPABILITIES_ZUC;
-		capabilities_sym &= ~ICP_ACCEL_CAPABILITIES_ZUC_256;
 		capabilities_sym &= ~ICP_ACCEL_CAPABILITIES_WIRELESS_CRYPTO_EXT;
 	}
 
-	if (fusectl1 & ICP_ACCEL_GEN4_MASK_EIA3_SLICE) {
+	if (fusectl1 & ICP_ACCEL_GEN4_MASK_EIA3_SLICE)
 		capabilities_sym &= ~ICP_ACCEL_CAPABILITIES_ZUC;
-		capabilities_sym &= ~ICP_ACCEL_CAPABILITIES_ZUC_256;
-	}
-
-	if (fusectl1 & ICP_ACCEL_GEN4_MASK_ZUC_256_SLICE)
-		capabilities_sym &= ~ICP_ACCEL_CAPABILITIES_ZUC_256;
 
 	capabilities_asym = ICP_ACCEL_CAPABILITIES_CRYPTO_ASYMMETRIC |
 			  ICP_ACCEL_CAPABILITIES_SM2 |
@@ -420,6 +413,7 @@ static void adf_gen4_set_err_mask(struct adf_dev_err_mask *dev_err_mask)
 	dev_err_mask->parerr_cpr_xlt_mask = ADF_420XX_PARITYERRORMASK_CPR_XLT_MASK;
 	dev_err_mask->parerr_dcpr_ucs_mask = ADF_420XX_PARITYERRORMASK_DCPR_UCS_MASK;
 	dev_err_mask->parerr_pke_mask = ADF_420XX_PARITYERRORMASK_PKE_MASK;
+	dev_err_mask->parerr_wat_wcp_mask = ADF_420XX_PARITYERRORMASK_WAT_WCP_MASK;
 	dev_err_mask->ssmfeatren_mask = ADF_420XX_SSMFEATREN_MASK;
 }
 
diff --git a/drivers/crypto/intel/qat/qat_420xx/adf_drv.c b/drivers/crypto/intel/qat/qat_420xx/adf_drv.c
index f49818a13013..41420e349572 100644
--- a/drivers/crypto/intel/qat/qat_420xx/adf_drv.c
+++ b/drivers/crypto/intel/qat/qat_420xx/adf_drv.c
@@ -181,11 +181,19 @@ static void adf_remove(struct pci_dev *pdev)
 	adf_cleanup_accel(accel_dev);
 }
 
+static void adf_shutdown(struct pci_dev *pdev)
+{
+	struct adf_accel_dev *accel_dev = adf_devmgr_pci_to_accel_dev(pdev);
+
+	adf_dev_down(accel_dev);
+}
+
 static struct pci_driver adf_driver = {
 	.id_table = adf_pci_tbl,
 	.name = ADF_420XX_DEVICE_NAME,
 	.probe = adf_probe,
 	.remove = adf_remove,
+	.shutdown = adf_shutdown,
 	.sriov_configure = adf_sriov_configure,
 	.err_handler = &adf_err_handler,
 };
diff --git a/drivers/crypto/intel/qat/qat_4xxx/adf_drv.c b/drivers/crypto/intel/qat/qat_4xxx/adf_drv.c
index 659905e45950..01b34eda83e9 100644
--- a/drivers/crypto/intel/qat/qat_4xxx/adf_drv.c
+++ b/drivers/crypto/intel/qat/qat_4xxx/adf_drv.c
@@ -183,11 +183,19 @@ static void adf_remove(struct pci_dev *pdev)
 	adf_cleanup_accel(accel_dev);
 }
 
+static void adf_shutdown(struct pci_dev *pdev)
+{
+	struct adf_accel_dev *accel_dev = adf_devmgr_pci_to_accel_dev(pdev);
+
+	adf_dev_down(accel_dev);
+}
+
 static struct pci_driver adf_driver = {
 	.id_table = adf_pci_tbl,
 	.name = ADF_4XXX_DEVICE_NAME,
 	.probe = adf_probe,
 	.remove = adf_remove,
+	.shutdown = adf_shutdown,
 	.sriov_configure = adf_sriov_configure,
 	.err_handler = &adf_err_handler,
 };
diff --git a/drivers/crypto/intel/qat/qat_c3xxx/adf_drv.c b/drivers/crypto/intel/qat/qat_c3xxx/adf_drv.c
index 4d18057745d4..b776f7ea0dfb 100644
--- a/drivers/crypto/intel/qat/qat_c3xxx/adf_drv.c
+++ b/drivers/crypto/intel/qat/qat_c3xxx/adf_drv.c
@@ -19,6 +19,13 @@
 #include <adf_dbgfs.h>
 #include "adf_c3xxx_hw_data.h"
 
+static void adf_shutdown(struct pci_dev *pdev)
+{
+	struct adf_accel_dev *accel_dev = adf_devmgr_pci_to_accel_dev(pdev);
+
+	adf_dev_down(accel_dev);
+}
+
 static const struct pci_device_id adf_pci_tbl[] = {
 	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_QAT_C3XXX), },
 	{ }
@@ -33,6 +40,7 @@ static struct pci_driver adf_driver = {
 	.name = ADF_C3XXX_DEVICE_NAME,
 	.probe = adf_probe,
 	.remove = adf_remove,
+	.shutdown = adf_shutdown,
 	.sriov_configure = adf_sriov_configure,
 	.err_handler = &adf_err_handler,
 };
diff --git a/drivers/crypto/intel/qat/qat_c62x/adf_drv.c b/drivers/crypto/intel/qat/qat_c62x/adf_drv.c
index e6b5de55434e..5310149c311e 100644
--- a/drivers/crypto/intel/qat/qat_c62x/adf_drv.c
+++ b/drivers/crypto/intel/qat/qat_c62x/adf_drv.c
@@ -19,6 +19,13 @@
 #include <adf_dbgfs.h>
 #include "adf_c62x_hw_data.h"
 
+static void adf_shutdown(struct pci_dev *pdev)
+{
+	struct adf_accel_dev *accel_dev = adf_devmgr_pci_to_accel_dev(pdev);
+
+	adf_dev_down(accel_dev);
+}
+
 static const struct pci_device_id adf_pci_tbl[] = {
 	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_QAT_C62X), },
 	{ }
@@ -33,6 +40,7 @@ static struct pci_driver adf_driver = {
 	.name = ADF_C62X_DEVICE_NAME,
 	.probe = adf_probe,
 	.remove = adf_remove,
+	.shutdown = adf_shutdown,
 	.sriov_configure = adf_sriov_configure,
 	.err_handler = &adf_err_handler,
 };
diff --git a/drivers/crypto/intel/qat/qat_common/Makefile b/drivers/crypto/intel/qat/qat_common/Makefile
index eac73cbfdd38..7acf9c576149 100644
--- a/drivers/crypto/intel/qat/qat_common/Makefile
+++ b/drivers/crypto/intel/qat/qat_common/Makefile
@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 obj-$(CONFIG_CRYPTO_DEV_QAT) += intel_qat.o
-ccflags-y += -DDEFAULT_SYMBOL_NAMESPACE=CRYPTO_QAT
+ccflags-y += -DDEFAULT_SYMBOL_NAMESPACE='"CRYPTO_QAT"'
 intel_qat-objs := adf_cfg.o \
 	adf_isr.o \
 	adf_ctl_drv.o \
diff --git a/drivers/crypto/intel/qat/qat_common/adf_gen4_hw_data.c b/drivers/crypto/intel/qat/qat_common/adf_gen4_hw_data.c
index 41a0979e68c1..e70adb90e5e4 100644
--- a/drivers/crypto/intel/qat/qat_common/adf_gen4_hw_data.c
+++ b/drivers/crypto/intel/qat/qat_common/adf_gen4_hw_data.c
@@ -585,6 +585,28 @@ static int bank_state_restore(struct adf_hw_csr_ops *ops, void __iomem *base,
 	ops->write_csr_int_srcsel_w_val(base, bank, state->iaintflagsrcsel0);
 	ops->write_csr_exp_int_en(base, bank, state->ringexpintenable);
 	ops->write_csr_int_col_ctl(base, bank, state->iaintcolctl);
+
+	/*
+	 * Verify whether any exceptions were raised during the bank save process.
+	 * If exceptions occurred, the status and exception registers cannot
+	 * be directly restored. Consequently, further restoration is not
+	 * feasible, and the current state of the ring should be maintained.
+	 */
+	val = state->ringexpstat;
+	if (val) {
+		pr_info("QAT: Bank %u state not fully restored due to exception in saved state (%#x)\n",
+			bank, val);
+		return 0;
+	}
+
+	/* Ensure that the restoration process completed without exceptions */
+	tmp_val = ops->read_csr_exp_stat(base, bank);
+	if (tmp_val) {
+		pr_err("QAT: Bank %u restored with exception: %#x\n",
+		       bank, tmp_val);
+		return -EFAULT;
+	}
+
 	ops->write_csr_ring_srv_arb_en(base, bank, state->ringsrvarben);
 
 	/* Check that all ring statuses match the saved state. */
@@ -618,13 +640,6 @@ static int bank_state_restore(struct adf_hw_csr_ops *ops, void __iomem *base,
 	if (ret)
 		return ret;
 
-	tmp_val = ops->read_csr_exp_stat(base, bank);
-	val = state->ringexpstat;
-	if (tmp_val && !val) {
-		pr_err("QAT: Bank was restored with exception: 0x%x\n", val);
-		return -EINVAL;
-	}
-
 	return 0;
 }
 
diff --git a/drivers/crypto/intel/qat/qat_common/adf_gen4_ras.c b/drivers/crypto/intel/qat/qat_common/adf_gen4_ras.c
index 2dd3772bf58a..0f7f00a19e7d 100644
--- a/drivers/crypto/intel/qat/qat_common/adf_gen4_ras.c
+++ b/drivers/crypto/intel/qat/qat_common/adf_gen4_ras.c
@@ -695,7 +695,7 @@ static bool adf_handle_slice_hang_error(struct adf_accel_dev *accel_dev,
 	if (err_mask->parerr_wat_wcp_mask)
 		adf_poll_slicehang_csr(accel_dev, csr,
 				       ADF_GEN4_SLICEHANGSTATUS_WAT_WCP,
-				       "ath_cph");
+				       "wat_wcp");
 
 	return false;
 }
@@ -1043,63 +1043,16 @@ static bool adf_handle_ssmcpppar_err(struct adf_accel_dev *accel_dev,
 	return reset_required;
 }
 
-static bool adf_handle_rf_parr_err(struct adf_accel_dev *accel_dev,
+static void adf_handle_rf_parr_err(struct adf_accel_dev *accel_dev,
 				   void __iomem *csr, u32 iastatssm)
 {
-	struct adf_dev_err_mask *err_mask = GET_ERR_MASK(accel_dev);
-	u32 reg;
-
 	if (!(iastatssm & ADF_GEN4_IAINTSTATSSM_SSMSOFTERRORPARITY_BIT))
-		return false;
-
-	reg = ADF_CSR_RD(csr, ADF_GEN4_SSMSOFTERRORPARITY_SRC);
-	reg &= ADF_GEN4_SSMSOFTERRORPARITY_SRC_BIT;
-	if (reg) {
-		ADF_RAS_ERR_CTR_INC(accel_dev->ras_errors, ADF_RAS_UNCORR);
-		ADF_CSR_WR(csr, ADF_GEN4_SSMSOFTERRORPARITY_SRC, reg);
-	}
-
-	reg = ADF_CSR_RD(csr, ADF_GEN4_SSMSOFTERRORPARITY_ATH_CPH);
-	reg &= err_mask->parerr_ath_cph_mask;
-	if (reg) {
-		ADF_RAS_ERR_CTR_INC(accel_dev->ras_errors, ADF_RAS_UNCORR);
-		ADF_CSR_WR(csr, ADF_GEN4_SSMSOFTERRORPARITY_ATH_CPH, reg);
-	}
-
-	reg = ADF_CSR_RD(csr, ADF_GEN4_SSMSOFTERRORPARITY_CPR_XLT);
-	reg &= err_mask->parerr_cpr_xlt_mask;
-	if (reg) {
-		ADF_RAS_ERR_CTR_INC(accel_dev->ras_errors, ADF_RAS_UNCORR);
-		ADF_CSR_WR(csr, ADF_GEN4_SSMSOFTERRORPARITY_CPR_XLT, reg);
-	}
-
-	reg = ADF_CSR_RD(csr, ADF_GEN4_SSMSOFTERRORPARITY_DCPR_UCS);
-	reg &= err_mask->parerr_dcpr_ucs_mask;
-	if (reg) {
-		ADF_RAS_ERR_CTR_INC(accel_dev->ras_errors, ADF_RAS_UNCORR);
-		ADF_CSR_WR(csr, ADF_GEN4_SSMSOFTERRORPARITY_DCPR_UCS, reg);
-	}
-
-	reg = ADF_CSR_RD(csr, ADF_GEN4_SSMSOFTERRORPARITY_PKE);
-	reg &= err_mask->parerr_pke_mask;
-	if (reg) {
-		ADF_RAS_ERR_CTR_INC(accel_dev->ras_errors, ADF_RAS_UNCORR);
-		ADF_CSR_WR(csr, ADF_GEN4_SSMSOFTERRORPARITY_PKE, reg);
-	}
-
-	if (err_mask->parerr_wat_wcp_mask) {
-		reg = ADF_CSR_RD(csr, ADF_GEN4_SSMSOFTERRORPARITY_WAT_WCP);
-		reg &= err_mask->parerr_wat_wcp_mask;
-		if (reg) {
-			ADF_RAS_ERR_CTR_INC(accel_dev->ras_errors, ADF_RAS_UNCORR);
-			ADF_CSR_WR(csr, ADF_GEN4_SSMSOFTERRORPARITY_WAT_WCP,
-				   reg);
-		}
-	}
+		return;
 
+	ADF_RAS_ERR_CTR_INC(accel_dev->ras_errors, ADF_RAS_UNCORR);
 	dev_err(&GET_DEV(accel_dev), "Slice ssm soft parity error reported");
 
-	return false;
+	return;
 }
 
 static bool adf_handle_ser_err_ssmsh(struct adf_accel_dev *accel_dev,
@@ -1171,8 +1124,8 @@ static bool adf_handle_iaintstatssm(struct adf_accel_dev *accel_dev,
 	reset_required |= adf_handle_slice_hang_error(accel_dev, csr, iastatssm);
 	reset_required |= adf_handle_spppar_err(accel_dev, csr, iastatssm);
 	reset_required |= adf_handle_ssmcpppar_err(accel_dev, csr, iastatssm);
-	reset_required |= adf_handle_rf_parr_err(accel_dev, csr, iastatssm);
 	reset_required |= adf_handle_ser_err_ssmsh(accel_dev, csr, iastatssm);
+	adf_handle_rf_parr_err(accel_dev, csr, iastatssm);
 
 	ADF_CSR_WR(csr, ADF_GEN4_IAINTSTATSSM, iastatssm);
 
diff --git a/drivers/crypto/intel/qat/qat_common/adf_sriov.c b/drivers/crypto/intel/qat/qat_common/adf_sriov.c
index c75d0b6cb0ad..31d1ef0cb1f5 100644
--- a/drivers/crypto/intel/qat/qat_common/adf_sriov.c
+++ b/drivers/crypto/intel/qat/qat_common/adf_sriov.c
@@ -155,7 +155,6 @@ static int adf_do_enable_sriov(struct adf_accel_dev *accel_dev)
 	if (!device_iommu_mapped(&GET_DEV(accel_dev))) {
 		dev_warn(&GET_DEV(accel_dev),
 			 "IOMMU should be enabled for SR-IOV to work correctly\n");
-		return -EINVAL;
 	}
 
 	if (adf_dev_started(accel_dev)) {
diff --git a/drivers/crypto/intel/qat/qat_common/adf_transport_debug.c b/drivers/crypto/intel/qat/qat_common/adf_transport_debug.c
index e2dd568b87b5..621b5d3dfcef 100644
--- a/drivers/crypto/intel/qat/qat_common/adf_transport_debug.c
+++ b/drivers/crypto/intel/qat/qat_common/adf_transport_debug.c
@@ -31,8 +31,10 @@ static void *adf_ring_next(struct seq_file *sfile, void *v, loff_t *pos)
 	struct adf_etr_ring_data *ring = sfile->private;
 
 	if (*pos >= (ADF_SIZE_TO_RING_SIZE_IN_BYTES(ring->ring_size) /
-		     ADF_MSG_SIZE_TO_BYTES(ring->msg_size)))
+		     ADF_MSG_SIZE_TO_BYTES(ring->msg_size))) {
+		(*pos)++;
 		return NULL;
+	}
 
 	return ring->base_addr +
 		(ADF_MSG_SIZE_TO_BYTES(ring->msg_size) * (*pos)++);
diff --git a/drivers/crypto/intel/qat/qat_common/qat_bl.c b/drivers/crypto/intel/qat/qat_common/qat_bl.c
index 338acf29c487..5a7b43f9150d 100644
--- a/drivers/crypto/intel/qat/qat_common/qat_bl.c
+++ b/drivers/crypto/intel/qat/qat_common/qat_bl.c
@@ -38,7 +38,7 @@ void qat_bl_free_bufl(struct adf_accel_dev *accel_dev,
 		for (i = 0; i < blout->num_mapped_bufs; i++) {
 			dma_unmap_single(dev, blout->buffers[i].addr,
 					 blout->buffers[i].len,
-					 DMA_FROM_DEVICE);
+					 DMA_BIDIRECTIONAL);
 		}
 		dma_unmap_single(dev, blpout, sz_out, DMA_TO_DEVICE);
 
@@ -162,7 +162,7 @@ static int __qat_bl_sgl_to_bufl(struct adf_accel_dev *accel_dev,
 			}
 			buffers[y].addr = dma_map_single(dev, sg_virt(sg) + left,
 							 sg->length - left,
-							 DMA_FROM_DEVICE);
+							 DMA_BIDIRECTIONAL);
 			if (unlikely(dma_mapping_error(dev, buffers[y].addr)))
 				goto err_out;
 			buffers[y].len = sg->length;
@@ -204,7 +204,7 @@ err_out:
 		if (!dma_mapping_error(dev, buflout->buffers[i].addr))
 			dma_unmap_single(dev, buflout->buffers[i].addr,
 					 buflout->buffers[i].len,
-					 DMA_FROM_DEVICE);
+					 DMA_BIDIRECTIONAL);
 	}
 
 	if (!buf->sgl_dst_valid)
diff --git a/drivers/crypto/intel/qat/qat_common/qat_compression.c b/drivers/crypto/intel/qat/qat_common/qat_compression.c
index 7842a9f22178..cf94ba3011d5 100644
--- a/drivers/crypto/intel/qat/qat_common/qat_compression.c
+++ b/drivers/crypto/intel/qat/qat_common/qat_compression.c
@@ -197,7 +197,7 @@ static int qat_compression_alloc_dc_data(struct adf_accel_dev *accel_dev)
 	struct adf_dc_data *dc_data = NULL;
 	u8 *obuff = NULL;
 
-	dc_data = devm_kzalloc(dev, sizeof(*dc_data), GFP_KERNEL);
+	dc_data = kzalloc_node(sizeof(*dc_data), GFP_KERNEL, dev_to_node(dev));
 	if (!dc_data)
 		goto err;
 
@@ -205,7 +205,7 @@ static int qat_compression_alloc_dc_data(struct adf_accel_dev *accel_dev)
 	if (!obuff)
 		goto err;
 
-	obuff_p = dma_map_single(dev, obuff, ovf_buff_sz, DMA_FROM_DEVICE);
+	obuff_p = dma_map_single(dev, obuff, ovf_buff_sz, DMA_BIDIRECTIONAL);
 	if (unlikely(dma_mapping_error(dev, obuff_p)))
 		goto err;
 
@@ -233,9 +233,9 @@ static void qat_free_dc_data(struct adf_accel_dev *accel_dev)
 		return;
 
 	dma_unmap_single(dev, dc_data->ovf_buff_p, dc_data->ovf_buff_sz,
-			 DMA_FROM_DEVICE);
+			 DMA_BIDIRECTIONAL);
 	kfree_sensitive(dc_data->ovf_buff);
-	devm_kfree(dev, dc_data);
+	kfree(dc_data);
 	accel_dev->dc_data = NULL;
 }
 
diff --git a/drivers/crypto/intel/qat/qat_dh895xcc/adf_drv.c b/drivers/crypto/intel/qat/qat_dh895xcc/adf_drv.c
index 2a50cce41515..5ddf567ffcad 100644
--- a/drivers/crypto/intel/qat/qat_dh895xcc/adf_drv.c
+++ b/drivers/crypto/intel/qat/qat_dh895xcc/adf_drv.c
@@ -19,6 +19,13 @@
 #include <adf_dbgfs.h>
 #include "adf_dh895xcc_hw_data.h"
 
+static void adf_shutdown(struct pci_dev *pdev)
+{
+	struct adf_accel_dev *accel_dev = adf_devmgr_pci_to_accel_dev(pdev);
+
+	adf_dev_down(accel_dev);
+}
+
 static const struct pci_device_id adf_pci_tbl[] = {
 	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_QAT_DH895XCC), },
 	{ }
@@ -33,6 +40,7 @@ static struct pci_driver adf_driver = {
 	.name = ADF_DH895XCC_DEVICE_NAME,
 	.probe = adf_probe,
 	.remove = adf_remove,
+	.shutdown = adf_shutdown,
 	.sriov_configure = adf_sriov_configure,
 	.err_handler = &adf_err_handler,
 };
diff --git a/drivers/crypto/marvell/cesa/cesa.c b/drivers/crypto/marvell/cesa/cesa.c
index 5fd31ba715c2..24273cb082ba 100644
--- a/drivers/crypto/marvell/cesa/cesa.c
+++ b/drivers/crypto/marvell/cesa/cesa.c
@@ -94,7 +94,7 @@ static int mv_cesa_std_process(struct mv_cesa_engine *engine, u32 status)
 
 static int mv_cesa_int_process(struct mv_cesa_engine *engine, u32 status)
 {
-	if (engine->chain.first && engine->chain.last)
+	if (engine->chain_hw.first && engine->chain_hw.last)
 		return mv_cesa_tdma_process(engine, status);
 
 	return mv_cesa_std_process(engine, status);
diff --git a/drivers/crypto/marvell/cesa/cesa.h b/drivers/crypto/marvell/cesa/cesa.h
index d215a6bed6bc..50ca1039fdaa 100644
--- a/drivers/crypto/marvell/cesa/cesa.h
+++ b/drivers/crypto/marvell/cesa/cesa.h
@@ -440,8 +440,10 @@ struct mv_cesa_dev {
  *			SRAM
  * @queue:		fifo of the pending crypto requests
  * @load:		engine load counter, useful for load balancing
- * @chain:		list of the current tdma descriptors being processed
- *			by this engine.
+ * @chain_hw:		list of the current tdma descriptors being processed
+ *			by the hardware.
+ * @chain_sw:		list of the current tdma descriptors that will be
+ *			submitted to the hardware.
  * @complete_queue:	fifo of the processed requests by the engine
  *
  * Structure storing CESA engine information.
@@ -463,7 +465,8 @@ struct mv_cesa_engine {
 	struct gen_pool *pool;
 	struct crypto_queue queue;
 	atomic_t load;
-	struct mv_cesa_tdma_chain chain;
+	struct mv_cesa_tdma_chain chain_hw;
+	struct mv_cesa_tdma_chain chain_sw;
 	struct list_head complete_queue;
 	int irq;
 };
diff --git a/drivers/crypto/marvell/cesa/cipher.c b/drivers/crypto/marvell/cesa/cipher.c
index 0f37dfd42d85..eabed9d977df 100644
--- a/drivers/crypto/marvell/cesa/cipher.c
+++ b/drivers/crypto/marvell/cesa/cipher.c
@@ -75,9 +75,12 @@ mv_cesa_skcipher_dma_cleanup(struct skcipher_request *req)
 static inline void mv_cesa_skcipher_cleanup(struct skcipher_request *req)
 {
 	struct mv_cesa_skcipher_req *creq = skcipher_request_ctx(req);
+	struct mv_cesa_engine *engine = creq->base.engine;
 
 	if (mv_cesa_req_get_type(&creq->base) == CESA_DMA_REQ)
 		mv_cesa_skcipher_dma_cleanup(req);
+
+	atomic_sub(req->cryptlen, &engine->load);
 }
 
 static void mv_cesa_skcipher_std_step(struct skcipher_request *req)
@@ -212,7 +215,6 @@ mv_cesa_skcipher_complete(struct crypto_async_request *req)
 	struct mv_cesa_engine *engine = creq->base.engine;
 	unsigned int ivsize;
 
-	atomic_sub(skreq->cryptlen, &engine->load);
 	ivsize = crypto_skcipher_ivsize(crypto_skcipher_reqtfm(skreq));
 
 	if (mv_cesa_req_get_type(&creq->base) == CESA_DMA_REQ) {
@@ -459,6 +461,9 @@ static int mv_cesa_skcipher_queue_req(struct skcipher_request *req,
 	struct mv_cesa_skcipher_req *creq = skcipher_request_ctx(req);
 	struct mv_cesa_engine *engine;
 
+	if (!req->cryptlen)
+		return 0;
+
 	ret = mv_cesa_skcipher_req_init(req, tmpl);
 	if (ret)
 		return ret;
diff --git a/drivers/crypto/marvell/cesa/hash.c b/drivers/crypto/marvell/cesa/hash.c
index f150861ceaf6..e339ce7ad533 100644
--- a/drivers/crypto/marvell/cesa/hash.c
+++ b/drivers/crypto/marvell/cesa/hash.c
@@ -110,9 +110,12 @@ static inline void mv_cesa_ahash_dma_cleanup(struct ahash_request *req)
 static inline void mv_cesa_ahash_cleanup(struct ahash_request *req)
 {
 	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
+	struct mv_cesa_engine *engine = creq->base.engine;
 
 	if (mv_cesa_req_get_type(&creq->base) == CESA_DMA_REQ)
 		mv_cesa_ahash_dma_cleanup(req);
+
+	atomic_sub(req->nbytes, &engine->load);
 }
 
 static void mv_cesa_ahash_last_cleanup(struct ahash_request *req)
@@ -395,8 +398,6 @@ static void mv_cesa_ahash_complete(struct crypto_async_request *req)
 			}
 		}
 	}
-
-	atomic_sub(ahashreq->nbytes, &engine->load);
 }
 
 static void mv_cesa_ahash_prepare(struct crypto_async_request *req,
@@ -663,7 +664,7 @@ static int mv_cesa_ahash_dma_req_init(struct ahash_request *req)
 	if (ret)
 		goto err_free_tdma;
 
-	if (iter.src.sg) {
+	if (iter.base.len > iter.src.op_offset) {
 		/*
 		 * Add all the new data, inserting an operation block and
 		 * launch command between each full SRAM block-worth of
diff --git a/drivers/crypto/marvell/cesa/tdma.c b/drivers/crypto/marvell/cesa/tdma.c
index 388a06e180d6..243305354420 100644
--- a/drivers/crypto/marvell/cesa/tdma.c
+++ b/drivers/crypto/marvell/cesa/tdma.c
@@ -38,6 +38,15 @@ void mv_cesa_dma_step(struct mv_cesa_req *dreq)
 {
 	struct mv_cesa_engine *engine = dreq->engine;
 
+	spin_lock_bh(&engine->lock);
+	if (engine->chain_sw.first == dreq->chain.first) {
+		engine->chain_sw.first = NULL;
+		engine->chain_sw.last = NULL;
+	}
+	engine->chain_hw.first = dreq->chain.first;
+	engine->chain_hw.last = dreq->chain.last;
+	spin_unlock_bh(&engine->lock);
+
 	writel_relaxed(0, engine->regs + CESA_SA_CFG);
 
 	mv_cesa_set_int_mask(engine, CESA_SA_INT_ACC0_IDMA_DONE);
@@ -96,25 +105,27 @@ void mv_cesa_dma_prepare(struct mv_cesa_req *dreq,
 void mv_cesa_tdma_chain(struct mv_cesa_engine *engine,
 			struct mv_cesa_req *dreq)
 {
-	if (engine->chain.first == NULL && engine->chain.last == NULL) {
-		engine->chain.first = dreq->chain.first;
-		engine->chain.last  = dreq->chain.last;
-	} else {
-		struct mv_cesa_tdma_desc *last;
+	struct mv_cesa_tdma_desc *last = engine->chain_sw.last;
 
-		last = engine->chain.last;
+	/*
+	 * Break the DMA chain if the request being queued needs the IV
+	 * regs to be set before lauching the request.
+	 */
+	if (!last || dreq->chain.first->flags & CESA_TDMA_SET_STATE)
+		engine->chain_sw.first = dreq->chain.first;
+	else {
 		last->next = dreq->chain.first;
-		engine->chain.last = dreq->chain.last;
-
-		/*
-		 * Break the DMA chain if the CESA_TDMA_BREAK_CHAIN is set on
-		 * the last element of the current chain, or if the request
-		 * being queued needs the IV regs to be set before lauching
-		 * the request.
-		 */
-		if (!(last->flags & CESA_TDMA_BREAK_CHAIN) &&
-		    !(dreq->chain.first->flags & CESA_TDMA_SET_STATE))
-			last->next_dma = cpu_to_le32(dreq->chain.first->cur_dma);
+		last->next_dma = cpu_to_le32(dreq->chain.first->cur_dma);
+	}
+	last = dreq->chain.last;
+	engine->chain_sw.last = last;
+	/*
+	 * Break the DMA chain if the CESA_TDMA_BREAK_CHAIN is set on
+	 * the last element of the current chain.
+	 */
+	if (last->flags & CESA_TDMA_BREAK_CHAIN) {
+		engine->chain_sw.first = NULL;
+		engine->chain_sw.last = NULL;
 	}
 }
 
@@ -127,7 +138,7 @@ int mv_cesa_tdma_process(struct mv_cesa_engine *engine, u32 status)
 
 	tdma_cur = readl(engine->regs + CESA_TDMA_CUR);
 
-	for (tdma = engine->chain.first; tdma; tdma = next) {
+	for (tdma = engine->chain_hw.first; tdma; tdma = next) {
 		spin_lock_bh(&engine->lock);
 		next = tdma->next;
 		spin_unlock_bh(&engine->lock);
@@ -149,12 +160,12 @@ int mv_cesa_tdma_process(struct mv_cesa_engine *engine, u32 status)
 								 &backlog);
 
 			/* Re-chaining to the next request */
-			engine->chain.first = tdma->next;
+			engine->chain_hw.first = tdma->next;
 			tdma->next = NULL;
 
 			/* If this is the last request, clear the chain */
-			if (engine->chain.first == NULL)
-				engine->chain.last  = NULL;
+			if (engine->chain_hw.first == NULL)
+				engine->chain_hw.last  = NULL;
 			spin_unlock_bh(&engine->lock);
 
 			ctx = crypto_tfm_ctx(req->tfm);
diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.c b/drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.c
index 5c9484646172..357a7c6ac837 100644
--- a/drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.c
+++ b/drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.c
@@ -1493,6 +1493,7 @@ int otx2_cpt_discover_eng_capabilities(struct otx2_cptpf_dev *cptpf)
 	dma_addr_t rptr_baddr;
 	struct pci_dev *pdev;
 	u32 len, compl_rlen;
+	int timeout = 10000;
 	int ret, etype;
 	void *rptr;
 
@@ -1555,16 +1556,27 @@ int otx2_cpt_discover_eng_capabilities(struct otx2_cptpf_dev *cptpf)
 							 etype);
 		otx2_cpt_fill_inst(&inst, &iq_cmd, rptr_baddr);
 		lfs->ops->send_cmd(&inst, 1, &cptpf->lfs.lf[0]);
+		timeout = 10000;
 
 		while (lfs->ops->cpt_get_compcode(result) ==
-						OTX2_CPT_COMPLETION_CODE_INIT)
+						OTX2_CPT_COMPLETION_CODE_INIT) {
 			cpu_relax();
+			udelay(1);
+			timeout--;
+			if (!timeout) {
+				ret = -ENODEV;
+				cptpf->is_eng_caps_discovered = false;
+				dev_warn(&pdev->dev, "Timeout on CPT load_fvc completion poll\n");
+				goto error_no_response;
+			}
+		}
 
 		cptpf->eng_caps[etype].u = be64_to_cpup(rptr);
 	}
-	dma_unmap_single(&pdev->dev, rptr_baddr, len, DMA_BIDIRECTIONAL);
 	cptpf->is_eng_caps_discovered = true;
 
+error_no_response:
+	dma_unmap_single(&pdev->dev, rptr_baddr, len, DMA_BIDIRECTIONAL);
 free_result:
 	kfree(result);
 lf_cleanup:
diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptvf_reqmgr.c b/drivers/crypto/marvell/octeontx2/otx2_cptvf_reqmgr.c
index 5387c68f3c9d..426244107037 100644
--- a/drivers/crypto/marvell/octeontx2/otx2_cptvf_reqmgr.c
+++ b/drivers/crypto/marvell/octeontx2/otx2_cptvf_reqmgr.c
@@ -264,9 +264,10 @@ static int cpt_process_ccode(struct otx2_cptlfs_info *lfs,
 				break;
 			}
 
-			dev_err(&pdev->dev,
-				"Request failed with software error code 0x%x\n",
-				cpt_status->s.uc_compcode);
+			pr_debug("Request failed with software error code 0x%x: algo = %s driver = %s\n",
+				 cpt_status->s.uc_compcode,
+				 info->req->areq->tfm->__crt_alg->cra_name,
+				 info->req->areq->tfm->__crt_alg->cra_driver_name);
 			otx2_cpt_dump_sg_list(pdev, info->req);
 			break;
 		}
diff --git a/drivers/crypto/mxs-dcp.c b/drivers/crypto/mxs-dcp.c
index 77a6301f37f0..29c0c69d5905 100644
--- a/drivers/crypto/mxs-dcp.c
+++ b/drivers/crypto/mxs-dcp.c
@@ -265,12 +265,12 @@ static int mxs_dcp_run_aes(struct dcp_async_ctx *actx,
 		    MXS_DCP_CONTROL0_INTERRUPT |
 		    MXS_DCP_CONTROL0_ENABLE_CIPHER;
 
-	if (key_referenced)
-		/* Set OTP key bit to select the key via KEY_SELECT. */
-		desc->control0 |= MXS_DCP_CONTROL0_OTP_KEY;
-	else
+	if (!key_referenced)
 		/* Payload contains the key. */
 		desc->control0 |= MXS_DCP_CONTROL0_PAYLOAD_KEY;
+	else if (actx->key[0] == DCP_PAES_KEY_OTP)
+		/* Set OTP key bit to select the key via KEY_SELECT. */
+		desc->control0 |= MXS_DCP_CONTROL0_OTP_KEY;
 
 	if (rctx->enc)
 		desc->control0 |= MXS_DCP_CONTROL0_CIPHER_ENCRYPT;
diff --git a/drivers/crypto/nx/nx-common-pseries.c b/drivers/crypto/nx/nx-common-pseries.c
index 35f2d0d8507e..7e98f174f69b 100644
--- a/drivers/crypto/nx/nx-common-pseries.c
+++ b/drivers/crypto/nx/nx-common-pseries.c
@@ -1144,6 +1144,7 @@ static void __init nxcop_get_capabilities(void)
 {
 	struct hv_vas_all_caps *hv_caps;
 	struct hv_nx_cop_caps *hv_nxc;
+	u64 feat;
 	int rc;
 
 	hv_caps = kmalloc(sizeof(*hv_caps), GFP_KERNEL);
@@ -1154,27 +1155,26 @@ static void __init nxcop_get_capabilities(void)
 	 */
 	rc = h_query_vas_capabilities(H_QUERY_NX_CAPABILITIES, 0,
 					  (u64)virt_to_phys(hv_caps));
+	if (!rc)
+		feat = be64_to_cpu(hv_caps->feat_type);
+	kfree(hv_caps);
 	if (rc)
-		goto out;
+		return;
+	if (!(feat & VAS_NX_GZIP_FEAT_BIT))
+		return;
 
-	caps_feat = be64_to_cpu(hv_caps->feat_type);
 	/*
 	 * NX-GZIP feature available
 	 */
-	if (caps_feat & VAS_NX_GZIP_FEAT_BIT) {
-		hv_nxc = kmalloc(sizeof(*hv_nxc), GFP_KERNEL);
-		if (!hv_nxc)
-			goto out;
-		/*
-		 * Get capabilities for NX-GZIP feature
-		 */
-		rc = h_query_vas_capabilities(H_QUERY_NX_CAPABILITIES,
-						  VAS_NX_GZIP_FEAT,
-						  (u64)virt_to_phys(hv_nxc));
-	} else {
-		pr_err("NX-GZIP feature is not available\n");
-		rc = -EINVAL;
-	}
+	hv_nxc = kmalloc(sizeof(*hv_nxc), GFP_KERNEL);
+	if (!hv_nxc)
+		return;
+	/*
+	 * Get capabilities for NX-GZIP feature
+	 */
+	rc = h_query_vas_capabilities(H_QUERY_NX_CAPABILITIES,
+					  VAS_NX_GZIP_FEAT,
+					  (u64)virt_to_phys(hv_nxc));
 
 	if (!rc) {
 		nx_cop_caps.descriptor = be64_to_cpu(hv_nxc->descriptor);
@@ -1184,13 +1184,10 @@ static void __init nxcop_get_capabilities(void)
 				be64_to_cpu(hv_nxc->min_compress_len);
 		nx_cop_caps.min_decompress_len =
 				be64_to_cpu(hv_nxc->min_decompress_len);
-	} else {
-		caps_feat = 0;
+		caps_feat = feat;
 	}
 
 	kfree(hv_nxc);
-out:
-	kfree(hv_caps);
 }
 
 static const struct vio_device_id nx842_vio_driver_ids[] = {
diff --git a/drivers/crypto/qce/aead.c b/drivers/crypto/qce/aead.c
index 7d811728f047..97b56e92ea33 100644
--- a/drivers/crypto/qce/aead.c
+++ b/drivers/crypto/qce/aead.c
@@ -786,7 +786,7 @@ static int qce_aead_register_one(const struct qce_aead_def *def, struct qce_devi
 	alg->init			= qce_aead_init;
 	alg->exit			= qce_aead_exit;
 
-	alg->base.cra_priority		= 300;
+	alg->base.cra_priority		= 275;
 	alg->base.cra_flags		= CRYPTO_ALG_ASYNC |
 					  CRYPTO_ALG_ALLOCATES_MEMORY |
 					  CRYPTO_ALG_KERN_DRIVER_ONLY |
diff --git a/drivers/crypto/qce/core.c b/drivers/crypto/qce/core.c
index 28b5fd823827..3ec8297ed3ff 100644
--- a/drivers/crypto/qce/core.c
+++ b/drivers/crypto/qce/core.c
@@ -51,16 +51,19 @@ static void qce_unregister_algs(struct qce_device *qce)
 static int qce_register_algs(struct qce_device *qce)
 {
 	const struct qce_algo_ops *ops;
-	int i, ret = -ENODEV;
+	int i, j, ret = -ENODEV;
 
 	for (i = 0; i < ARRAY_SIZE(qce_ops); i++) {
 		ops = qce_ops[i];
 		ret = ops->register_algs(qce);
-		if (ret)
-			break;
+		if (ret) {
+			for (j = i - 1; j >= 0; j--)
+				ops->unregister_algs(qce);
+			return ret;
+		}
 	}
 
-	return ret;
+	return 0;
 }
 
 static int qce_handle_request(struct crypto_async_request *async_req)
@@ -247,7 +250,7 @@ static int qce_crypto_probe(struct platform_device *pdev)
 
 	ret = qce_check_version(qce);
 	if (ret)
-		goto err_clks;
+		goto err_dma;
 
 	spin_lock_init(&qce->lock);
 	tasklet_init(&qce->done_tasklet, qce_tasklet_req_done,
diff --git a/drivers/crypto/qce/sha.c b/drivers/crypto/qce/sha.c
index fc72af8aa9a7..71b748183cfa 100644
--- a/drivers/crypto/qce/sha.c
+++ b/drivers/crypto/qce/sha.c
@@ -482,7 +482,7 @@ static int qce_ahash_register_one(const struct qce_ahash_def *def,
 
 	base = &alg->halg.base;
 	base->cra_blocksize = def->blocksize;
-	base->cra_priority = 300;
+	base->cra_priority = 175;
 	base->cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_KERN_DRIVER_ONLY;
 	base->cra_ctxsize = sizeof(struct qce_sha_ctx);
 	base->cra_alignmask = 0;
diff --git a/drivers/crypto/qce/skcipher.c b/drivers/crypto/qce/skcipher.c
index 5b493fdc1e74..ffb334eb5b34 100644
--- a/drivers/crypto/qce/skcipher.c
+++ b/drivers/crypto/qce/skcipher.c
@@ -461,7 +461,7 @@ static int qce_skcipher_register_one(const struct qce_skcipher_def *def,
 	alg->encrypt			= qce_skcipher_encrypt;
 	alg->decrypt			= qce_skcipher_decrypt;
 
-	alg->base.cra_priority		= 300;
+	alg->base.cra_priority		= 275;
 	alg->base.cra_flags		= CRYPTO_ALG_ASYNC |
 					  CRYPTO_ALG_ALLOCATES_MEMORY |
 					  CRYPTO_ALG_KERN_DRIVER_ONLY;
diff --git a/drivers/crypto/tegra/tegra-se-aes.c b/drivers/crypto/tegra/tegra-se-aes.c
index ae7a0f8435fc..cd52807e76af 100644
--- a/drivers/crypto/tegra/tegra-se-aes.c
+++ b/drivers/crypto/tegra/tegra-se-aes.c
@@ -263,13 +263,7 @@ static int tegra_aes_do_one_req(struct crypto_engine *engine, void *areq)
 	unsigned int cmdlen;
 	int ret;
 
-	rctx->datbuf.buf = dma_alloc_coherent(se->dev, SE_AES_BUFLEN,
-					      &rctx->datbuf.addr, GFP_KERNEL);
-	if (!rctx->datbuf.buf)
-		return -ENOMEM;
-
-	rctx->datbuf.size = SE_AES_BUFLEN;
-	rctx->iv = (u32 *)req->iv;
+	rctx->iv = (ctx->alg == SE_ALG_ECB) ? NULL : (u32 *)req->iv;
 	rctx->len = req->cryptlen;
 
 	/* Pad input to AES Block size */
@@ -278,18 +272,24 @@ static int tegra_aes_do_one_req(struct crypto_engine *engine, void *areq)
 			rctx->len += AES_BLOCK_SIZE - (rctx->len % AES_BLOCK_SIZE);
 	}
 
+	rctx->datbuf.size = rctx->len;
+	rctx->datbuf.buf = dma_alloc_coherent(se->dev, rctx->datbuf.size,
+					      &rctx->datbuf.addr, GFP_KERNEL);
+	if (!rctx->datbuf.buf)
+		return -ENOMEM;
+
 	scatterwalk_map_and_copy(rctx->datbuf.buf, req->src, 0, req->cryptlen, 0);
 
 	/* Prepare the command and submit for execution */
 	cmdlen = tegra_aes_prep_cmd(ctx, rctx);
-	ret = tegra_se_host1x_submit(se, cmdlen);
+	ret = tegra_se_host1x_submit(se, se->cmdbuf, cmdlen);
 
 	/* Copy the result */
 	tegra_aes_update_iv(req, ctx);
 	scatterwalk_map_and_copy(rctx->datbuf.buf, req->dst, 0, req->cryptlen, 1);
 
 	/* Free the buffer */
-	dma_free_coherent(ctx->se->dev, SE_AES_BUFLEN,
+	dma_free_coherent(ctx->se->dev, rctx->datbuf.size,
 			  rctx->datbuf.buf, rctx->datbuf.addr);
 
 	crypto_finalize_skcipher_request(se->engine, req, ret);
@@ -719,7 +719,7 @@ static int tegra_gcm_do_gmac(struct tegra_aead_ctx *ctx, struct tegra_aead_reqct
 
 	cmdlen = tegra_gmac_prep_cmd(ctx, rctx);
 
-	return tegra_se_host1x_submit(se, cmdlen);
+	return tegra_se_host1x_submit(se, se->cmdbuf, cmdlen);
 }
 
 static int tegra_gcm_do_crypt(struct tegra_aead_ctx *ctx, struct tegra_aead_reqctx *rctx)
@@ -736,7 +736,7 @@ static int tegra_gcm_do_crypt(struct tegra_aead_ctx *ctx, struct tegra_aead_reqc
 
 	/* Prepare command and submit */
 	cmdlen = tegra_gcm_crypt_prep_cmd(ctx, rctx);
-	ret = tegra_se_host1x_submit(se, cmdlen);
+	ret = tegra_se_host1x_submit(se, se->cmdbuf, cmdlen);
 	if (ret)
 		return ret;
 
@@ -759,7 +759,7 @@ static int tegra_gcm_do_final(struct tegra_aead_ctx *ctx, struct tegra_aead_reqc
 
 	/* Prepare command and submit */
 	cmdlen = tegra_gcm_prep_final_cmd(se, cpuvaddr, rctx);
-	ret = tegra_se_host1x_submit(se, cmdlen);
+	ret = tegra_se_host1x_submit(se, se->cmdbuf, cmdlen);
 	if (ret)
 		return ret;
 
@@ -891,7 +891,7 @@ static int tegra_ccm_do_cbcmac(struct tegra_aead_ctx *ctx, struct tegra_aead_req
 	/* Prepare command and submit */
 	cmdlen = tegra_cbcmac_prep_cmd(ctx, rctx);
 
-	return tegra_se_host1x_submit(se, cmdlen);
+	return tegra_se_host1x_submit(se, se->cmdbuf, cmdlen);
 }
 
 static int tegra_ccm_set_msg_len(u8 *block, unsigned int msglen, int csize)
@@ -1098,7 +1098,7 @@ static int tegra_ccm_do_ctr(struct tegra_aead_ctx *ctx, struct tegra_aead_reqctx
 
 	/* Prepare command and submit */
 	cmdlen = tegra_ctr_prep_cmd(ctx, rctx);
-	ret = tegra_se_host1x_submit(se, cmdlen);
+	ret = tegra_se_host1x_submit(se, se->cmdbuf, cmdlen);
 	if (ret)
 		return ret;
 
@@ -1117,6 +1117,11 @@ static int tegra_ccm_crypt_init(struct aead_request *req, struct tegra_se *se,
 	rctx->assoclen = req->assoclen;
 	rctx->authsize = crypto_aead_authsize(tfm);
 
+	if (rctx->encrypt)
+		rctx->cryptlen = req->cryptlen;
+	else
+		rctx->cryptlen = req->cryptlen - rctx->authsize;
+
 	memcpy(iv, req->iv, 16);
 
 	ret = tegra_ccm_check_iv(iv);
@@ -1145,30 +1150,26 @@ static int tegra_ccm_do_one_req(struct crypto_engine *engine, void *areq)
 	struct tegra_se *se = ctx->se;
 	int ret;
 
+	ret = tegra_ccm_crypt_init(req, se, rctx);
+	if (ret)
+		return ret;
+
 	/* Allocate buffers required */
-	rctx->inbuf.buf = dma_alloc_coherent(ctx->se->dev, SE_AES_BUFLEN,
+	rctx->inbuf.size = rctx->assoclen + rctx->authsize + rctx->cryptlen + 100;
+	rctx->inbuf.buf = dma_alloc_coherent(ctx->se->dev, rctx->inbuf.size,
 					     &rctx->inbuf.addr, GFP_KERNEL);
 	if (!rctx->inbuf.buf)
 		return -ENOMEM;
 
-	rctx->inbuf.size = SE_AES_BUFLEN;
-
-	rctx->outbuf.buf = dma_alloc_coherent(ctx->se->dev, SE_AES_BUFLEN,
+	rctx->outbuf.size = rctx->assoclen + rctx->authsize + rctx->cryptlen + 100;
+	rctx->outbuf.buf = dma_alloc_coherent(ctx->se->dev, rctx->outbuf.size,
 					      &rctx->outbuf.addr, GFP_KERNEL);
 	if (!rctx->outbuf.buf) {
 		ret = -ENOMEM;
 		goto outbuf_err;
 	}
 
-	rctx->outbuf.size = SE_AES_BUFLEN;
-
-	ret = tegra_ccm_crypt_init(req, se, rctx);
-	if (ret)
-		goto out;
-
 	if (rctx->encrypt) {
-		rctx->cryptlen = req->cryptlen;
-
 		/* CBC MAC Operation */
 		ret = tegra_ccm_compute_auth(ctx, rctx);
 		if (ret)
@@ -1179,10 +1180,6 @@ static int tegra_ccm_do_one_req(struct crypto_engine *engine, void *areq)
 		if (ret)
 			goto out;
 	} else {
-		rctx->cryptlen = req->cryptlen - ctx->authsize;
-		if (ret)
-			goto out;
-
 		/* CTR operation */
 		ret = tegra_ccm_do_ctr(ctx, rctx);
 		if (ret)
@@ -1195,11 +1192,11 @@ static int tegra_ccm_do_one_req(struct crypto_engine *engine, void *areq)
 	}
 
 out:
-	dma_free_coherent(ctx->se->dev, SE_AES_BUFLEN,
+	dma_free_coherent(ctx->se->dev, rctx->inbuf.size,
 			  rctx->outbuf.buf, rctx->outbuf.addr);
 
 outbuf_err:
-	dma_free_coherent(ctx->se->dev, SE_AES_BUFLEN,
+	dma_free_coherent(ctx->se->dev, rctx->outbuf.size,
 			  rctx->inbuf.buf, rctx->inbuf.addr);
 
 	crypto_finalize_aead_request(ctx->se->engine, req, ret);
@@ -1215,23 +1212,6 @@ static int tegra_gcm_do_one_req(struct crypto_engine *engine, void *areq)
 	struct tegra_aead_reqctx *rctx = aead_request_ctx(req);
 	int ret;
 
-	/* Allocate buffers required */
-	rctx->inbuf.buf = dma_alloc_coherent(ctx->se->dev, SE_AES_BUFLEN,
-					     &rctx->inbuf.addr, GFP_KERNEL);
-	if (!rctx->inbuf.buf)
-		return -ENOMEM;
-
-	rctx->inbuf.size = SE_AES_BUFLEN;
-
-	rctx->outbuf.buf = dma_alloc_coherent(ctx->se->dev, SE_AES_BUFLEN,
-					      &rctx->outbuf.addr, GFP_KERNEL);
-	if (!rctx->outbuf.buf) {
-		ret = -ENOMEM;
-		goto outbuf_err;
-	}
-
-	rctx->outbuf.size = SE_AES_BUFLEN;
-
 	rctx->src_sg = req->src;
 	rctx->dst_sg = req->dst;
 	rctx->assoclen = req->assoclen;
@@ -1245,6 +1225,21 @@ static int tegra_gcm_do_one_req(struct crypto_engine *engine, void *areq)
 	memcpy(rctx->iv, req->iv, GCM_AES_IV_SIZE);
 	rctx->iv[3] = (1 << 24);
 
+	/* Allocate buffers required */
+	rctx->inbuf.size = rctx->assoclen + rctx->authsize + rctx->cryptlen;
+	rctx->inbuf.buf = dma_alloc_coherent(ctx->se->dev, rctx->inbuf.size,
+					     &rctx->inbuf.addr, GFP_KERNEL);
+	if (!rctx->inbuf.buf)
+		return -ENOMEM;
+
+	rctx->outbuf.size = rctx->assoclen + rctx->authsize + rctx->cryptlen;
+	rctx->outbuf.buf = dma_alloc_coherent(ctx->se->dev, rctx->outbuf.size,
+					      &rctx->outbuf.addr, GFP_KERNEL);
+	if (!rctx->outbuf.buf) {
+		ret = -ENOMEM;
+		goto outbuf_err;
+	}
+
 	/* If there is associated data perform GMAC operation */
 	if (rctx->assoclen) {
 		ret = tegra_gcm_do_gmac(ctx, rctx);
@@ -1268,11 +1263,11 @@ static int tegra_gcm_do_one_req(struct crypto_engine *engine, void *areq)
 		ret = tegra_gcm_do_verify(ctx->se, rctx);
 
 out:
-	dma_free_coherent(ctx->se->dev, SE_AES_BUFLEN,
+	dma_free_coherent(ctx->se->dev, rctx->outbuf.size,
 			  rctx->outbuf.buf, rctx->outbuf.addr);
 
 outbuf_err:
-	dma_free_coherent(ctx->se->dev, SE_AES_BUFLEN,
+	dma_free_coherent(ctx->se->dev, rctx->inbuf.size,
 			  rctx->inbuf.buf, rctx->inbuf.addr);
 
 	/* Finalize the request if there are no errors */
@@ -1499,6 +1494,11 @@ static int tegra_cmac_do_update(struct ahash_request *req)
 		return 0;
 	}
 
+	rctx->datbuf.buf = dma_alloc_coherent(se->dev, rctx->datbuf.size,
+					      &rctx->datbuf.addr, GFP_KERNEL);
+	if (!rctx->datbuf.buf)
+		return -ENOMEM;
+
 	/* Copy the previous residue first */
 	if (rctx->residue.size)
 		memcpy(rctx->datbuf.buf, rctx->residue.buf, rctx->residue.size);
@@ -1513,23 +1513,19 @@ static int tegra_cmac_do_update(struct ahash_request *req)
 	rctx->residue.size = nresidue;
 
 	/*
-	 * If this is not the first 'update' call, paste the previous copied
+	 * If this is not the first task, paste the previous copied
 	 * intermediate results to the registers so that it gets picked up.
-	 * This is to support the import/export functionality.
 	 */
 	if (!(rctx->task & SHA_FIRST))
 		tegra_cmac_paste_result(ctx->se, rctx);
 
 	cmdlen = tegra_cmac_prep_cmd(ctx, rctx);
+	ret = tegra_se_host1x_submit(se, se->cmdbuf, cmdlen);
 
-	ret = tegra_se_host1x_submit(se, cmdlen);
-	/*
-	 * If this is not the final update, copy the intermediate results
-	 * from the registers so that it can be used in the next 'update'
-	 * call. This is to support the import/export functionality.
-	 */
-	if (!(rctx->task & SHA_FINAL))
-		tegra_cmac_copy_result(ctx->se, rctx);
+	tegra_cmac_copy_result(ctx->se, rctx);
+
+	dma_free_coherent(ctx->se->dev, rctx->datbuf.size,
+			  rctx->datbuf.buf, rctx->datbuf.addr);
 
 	return ret;
 }
@@ -1545,17 +1541,34 @@ static int tegra_cmac_do_final(struct ahash_request *req)
 
 	if (!req->nbytes && !rctx->total_len && ctx->fallback_tfm) {
 		return crypto_shash_tfm_digest(ctx->fallback_tfm,
-					rctx->datbuf.buf, 0, req->result);
+					NULL, 0, req->result);
+	}
+
+	if (rctx->residue.size) {
+		rctx->datbuf.buf = dma_alloc_coherent(se->dev, rctx->residue.size,
+						      &rctx->datbuf.addr, GFP_KERNEL);
+		if (!rctx->datbuf.buf) {
+			ret = -ENOMEM;
+			goto out_free;
+		}
+
+		memcpy(rctx->datbuf.buf, rctx->residue.buf, rctx->residue.size);
 	}
 
-	memcpy(rctx->datbuf.buf, rctx->residue.buf, rctx->residue.size);
 	rctx->datbuf.size = rctx->residue.size;
 	rctx->total_len += rctx->residue.size;
 	rctx->config = tegra234_aes_cfg(SE_ALG_CMAC, 0);
 
+	/*
+	 * If this is not the first task, paste the previous copied
+	 * intermediate results to the registers so that it gets picked up.
+	 */
+	if (!(rctx->task & SHA_FIRST))
+		tegra_cmac_paste_result(ctx->se, rctx);
+
 	/* Prepare command and submit */
 	cmdlen = tegra_cmac_prep_cmd(ctx, rctx);
-	ret = tegra_se_host1x_submit(se, cmdlen);
+	ret = tegra_se_host1x_submit(se, se->cmdbuf, cmdlen);
 	if (ret)
 		goto out;
 
@@ -1567,8 +1580,10 @@ static int tegra_cmac_do_final(struct ahash_request *req)
 		writel(0, se->base + se->hw->regs->result + (i * 4));
 
 out:
-	dma_free_coherent(se->dev, SE_SHA_BUFLEN,
-			  rctx->datbuf.buf, rctx->datbuf.addr);
+	if (rctx->residue.size)
+		dma_free_coherent(se->dev, rctx->datbuf.size,
+				  rctx->datbuf.buf, rctx->datbuf.addr);
+out_free:
 	dma_free_coherent(se->dev, crypto_ahash_blocksize(tfm) * 2,
 			  rctx->residue.buf, rctx->residue.addr);
 	return ret;
@@ -1581,18 +1596,24 @@ static int tegra_cmac_do_one_req(struct crypto_engine *engine, void *areq)
 	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
 	struct tegra_cmac_ctx *ctx = crypto_ahash_ctx(tfm);
 	struct tegra_se *se = ctx->se;
-	int ret;
+	int ret = 0;
 
 	if (rctx->task & SHA_UPDATE) {
 		ret = tegra_cmac_do_update(req);
+		if (ret)
+			goto out;
+
 		rctx->task &= ~SHA_UPDATE;
 	}
 
 	if (rctx->task & SHA_FINAL) {
 		ret = tegra_cmac_do_final(req);
+		if (ret)
+			goto out;
+
 		rctx->task &= ~SHA_FINAL;
 	}
-
+out:
 	crypto_finalize_hash_request(se->engine, req, ret);
 
 	return 0;
@@ -1674,28 +1695,15 @@ static int tegra_cmac_init(struct ahash_request *req)
 	rctx->residue.buf = dma_alloc_coherent(se->dev, rctx->blk_size * 2,
 					       &rctx->residue.addr, GFP_KERNEL);
 	if (!rctx->residue.buf)
-		goto resbuf_fail;
+		return -ENOMEM;
 
 	rctx->residue.size = 0;
 
-	rctx->datbuf.buf = dma_alloc_coherent(se->dev, SE_SHA_BUFLEN,
-					      &rctx->datbuf.addr, GFP_KERNEL);
-	if (!rctx->datbuf.buf)
-		goto datbuf_fail;
-
-	rctx->datbuf.size = 0;
-
 	/* Clear any previous result */
 	for (i = 0; i < CMAC_RESULT_REG_COUNT; i++)
 		writel(0, se->base + se->hw->regs->result + (i * 4));
 
 	return 0;
-
-datbuf_fail:
-	dma_free_coherent(se->dev, rctx->blk_size, rctx->residue.buf,
-			  rctx->residue.addr);
-resbuf_fail:
-	return -ENOMEM;
 }
 
 static int tegra_cmac_setkey(struct crypto_ahash *tfm, const u8 *key,
@@ -1752,10 +1760,13 @@ static int tegra_cmac_digest(struct ahash_request *req)
 	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
 	struct tegra_cmac_ctx *ctx = crypto_ahash_ctx(tfm);
 	struct tegra_cmac_reqctx *rctx = ahash_request_ctx(req);
+	int ret;
 
-	tegra_cmac_init(req);
-	rctx->task |= SHA_UPDATE | SHA_FINAL;
+	ret = tegra_cmac_init(req);
+	if (ret)
+		return ret;
 
+	rctx->task |= SHA_UPDATE | SHA_FINAL;
 	return crypto_transfer_hash_request_to_engine(ctx->se->engine, req);
 }
 
diff --git a/drivers/crypto/tegra/tegra-se-hash.c b/drivers/crypto/tegra/tegra-se-hash.c
index 4d4bd727f498..451b8eaab16a 100644
--- a/drivers/crypto/tegra/tegra-se-hash.c
+++ b/drivers/crypto/tegra/tegra-se-hash.c
@@ -300,8 +300,9 @@ static int tegra_sha_do_update(struct ahash_request *req)
 {
 	struct tegra_sha_ctx *ctx = crypto_ahash_ctx(crypto_ahash_reqtfm(req));
 	struct tegra_sha_reqctx *rctx = ahash_request_ctx(req);
+	struct tegra_se *se = ctx->se;
 	unsigned int nblks, nresidue, size, ret;
-	u32 *cpuvaddr = ctx->se->cmdbuf->addr;
+	u32 *cpuvaddr = se->cmdbuf->addr;
 
 	nresidue = (req->nbytes + rctx->residue.size) % rctx->blk_size;
 	nblks = (req->nbytes + rctx->residue.size) / rctx->blk_size;
@@ -331,6 +332,11 @@ static int tegra_sha_do_update(struct ahash_request *req)
 		return 0;
 	}
 
+	rctx->datbuf.buf = dma_alloc_coherent(ctx->se->dev, rctx->datbuf.size,
+					      &rctx->datbuf.addr, GFP_KERNEL);
+	if (!rctx->datbuf.buf)
+		return -ENOMEM;
+
 	/* Copy the previous residue first */
 	if (rctx->residue.size)
 		memcpy(rctx->datbuf.buf, rctx->residue.buf, rctx->residue.size);
@@ -353,11 +359,11 @@ static int tegra_sha_do_update(struct ahash_request *req)
 	 * This is to support the import/export functionality.
 	 */
 	if (!(rctx->task & SHA_FIRST))
-		tegra_sha_paste_hash_result(ctx->se, rctx);
+		tegra_sha_paste_hash_result(se, rctx);
 
-	size = tegra_sha_prep_cmd(ctx->se, cpuvaddr, rctx);
+	size = tegra_sha_prep_cmd(se, cpuvaddr, rctx);
 
-	ret = tegra_se_host1x_submit(ctx->se, size);
+	ret = tegra_se_host1x_submit(se, se->cmdbuf, size);
 
 	/*
 	 * If this is not the final update, copy the intermediate results
@@ -365,7 +371,10 @@ static int tegra_sha_do_update(struct ahash_request *req)
 	 * call. This is to support the import/export functionality.
 	 */
 	if (!(rctx->task & SHA_FINAL))
-		tegra_sha_copy_hash_result(ctx->se, rctx);
+		tegra_sha_copy_hash_result(se, rctx);
+
+	dma_free_coherent(ctx->se->dev, rctx->datbuf.size,
+			  rctx->datbuf.buf, rctx->datbuf.addr);
 
 	return ret;
 }
@@ -379,7 +388,17 @@ static int tegra_sha_do_final(struct ahash_request *req)
 	u32 *cpuvaddr = se->cmdbuf->addr;
 	int size, ret = 0;
 
-	memcpy(rctx->datbuf.buf, rctx->residue.buf, rctx->residue.size);
+	if (rctx->residue.size) {
+		rctx->datbuf.buf = dma_alloc_coherent(se->dev, rctx->residue.size,
+						      &rctx->datbuf.addr, GFP_KERNEL);
+		if (!rctx->datbuf.buf) {
+			ret = -ENOMEM;
+			goto out_free;
+		}
+
+		memcpy(rctx->datbuf.buf, rctx->residue.buf, rctx->residue.size);
+	}
+
 	rctx->datbuf.size = rctx->residue.size;
 	rctx->total_len += rctx->residue.size;
 
@@ -388,7 +407,7 @@ static int tegra_sha_do_final(struct ahash_request *req)
 
 	size = tegra_sha_prep_cmd(se, cpuvaddr, rctx);
 
-	ret = tegra_se_host1x_submit(se, size);
+	ret = tegra_se_host1x_submit(se, se->cmdbuf, size);
 	if (ret)
 		goto out;
 
@@ -396,8 +415,10 @@ static int tegra_sha_do_final(struct ahash_request *req)
 	memcpy(req->result, rctx->digest.buf, rctx->digest.size);
 
 out:
-	dma_free_coherent(se->dev, SE_SHA_BUFLEN,
-			  rctx->datbuf.buf, rctx->datbuf.addr);
+	if (rctx->residue.size)
+		dma_free_coherent(se->dev, rctx->datbuf.size,
+				  rctx->datbuf.buf, rctx->datbuf.addr);
+out_free:
 	dma_free_coherent(se->dev, crypto_ahash_blocksize(tfm),
 			  rctx->residue.buf, rctx->residue.addr);
 	dma_free_coherent(se->dev, rctx->digest.size, rctx->digest.buf,
@@ -416,14 +437,21 @@ static int tegra_sha_do_one_req(struct crypto_engine *engine, void *areq)
 
 	if (rctx->task & SHA_UPDATE) {
 		ret = tegra_sha_do_update(req);
+		if (ret)
+			goto out;
+
 		rctx->task &= ~SHA_UPDATE;
 	}
 
 	if (rctx->task & SHA_FINAL) {
 		ret = tegra_sha_do_final(req);
+		if (ret)
+			goto out;
+
 		rctx->task &= ~SHA_FINAL;
 	}
 
+out:
 	crypto_finalize_hash_request(se->engine, req, ret);
 
 	return 0;
@@ -526,19 +554,11 @@ static int tegra_sha_init(struct ahash_request *req)
 	if (!rctx->residue.buf)
 		goto resbuf_fail;
 
-	rctx->datbuf.buf = dma_alloc_coherent(se->dev, SE_SHA_BUFLEN,
-					      &rctx->datbuf.addr, GFP_KERNEL);
-	if (!rctx->datbuf.buf)
-		goto datbuf_fail;
-
 	return 0;
 
-datbuf_fail:
-	dma_free_coherent(se->dev, rctx->blk_size, rctx->residue.buf,
-			  rctx->residue.addr);
 resbuf_fail:
-	dma_free_coherent(se->dev, SE_SHA_BUFLEN, rctx->datbuf.buf,
-			  rctx->datbuf.addr);
+	dma_free_coherent(se->dev, rctx->digest.size, rctx->digest.buf,
+			  rctx->digest.addr);
 digbuf_fail:
 	return -ENOMEM;
 }
@@ -559,13 +579,18 @@ static int tegra_hmac_setkey(struct crypto_ahash *tfm, const u8 *key,
 			     unsigned int keylen)
 {
 	struct tegra_sha_ctx *ctx = crypto_ahash_ctx(tfm);
+	int ret;
 
 	if (aes_check_keylen(keylen))
 		return tegra_hmac_fallback_setkey(ctx, key, keylen);
 
+	ret = tegra_key_submit(ctx->se, key, keylen, ctx->alg, &ctx->key_id);
+	if (ret)
+		return tegra_hmac_fallback_setkey(ctx, key, keylen);
+
 	ctx->fallback = false;
 
-	return tegra_key_submit(ctx->se, key, keylen, ctx->alg, &ctx->key_id);
+	return 0;
 }
 
 static int tegra_sha_update(struct ahash_request *req)
@@ -615,13 +640,16 @@ static int tegra_sha_digest(struct ahash_request *req)
 	struct tegra_sha_reqctx *rctx = ahash_request_ctx(req);
 	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
 	struct tegra_sha_ctx *ctx = crypto_ahash_ctx(tfm);
+	int ret;
 
 	if (ctx->fallback)
 		return tegra_sha_fallback_digest(req);
 
-	tegra_sha_init(req);
-	rctx->task |= SHA_UPDATE | SHA_FINAL;
+	ret = tegra_sha_init(req);
+	if (ret)
+		return ret;
 
+	rctx->task |= SHA_UPDATE | SHA_FINAL;
 	return crypto_transfer_hash_request_to_engine(ctx->se->engine, req);
 }
 
diff --git a/drivers/crypto/tegra/tegra-se-key.c b/drivers/crypto/tegra/tegra-se-key.c
index ac14678dbd30..276b261fb6df 100644
--- a/drivers/crypto/tegra/tegra-se-key.c
+++ b/drivers/crypto/tegra/tegra-se-key.c
@@ -115,11 +115,17 @@ static int tegra_key_insert(struct tegra_se *se, const u8 *key,
 			    u32 keylen, u16 slot, u32 alg)
 {
 	const u32 *keyval = (u32 *)key;
-	u32 *addr = se->cmdbuf->addr, size;
+	u32 *addr = se->keybuf->addr, size;
+	int ret;
+
+	mutex_lock(&kslt_lock);
 
 	size = tegra_key_prep_ins_cmd(se, addr, keyval, keylen, slot, alg);
+	ret = tegra_se_host1x_submit(se, se->keybuf, size);
 
-	return tegra_se_host1x_submit(se, size);
+	mutex_unlock(&kslt_lock);
+
+	return ret;
 }
 
 void tegra_key_invalidate(struct tegra_se *se, u32 keyid, u32 alg)
diff --git a/drivers/crypto/tegra/tegra-se-main.c b/drivers/crypto/tegra/tegra-se-main.c
index f94c0331b148..55690b044e41 100644
--- a/drivers/crypto/tegra/tegra-se-main.c
+++ b/drivers/crypto/tegra/tegra-se-main.c
@@ -141,7 +141,7 @@ static struct tegra_se_cmdbuf *tegra_se_host1x_bo_alloc(struct tegra_se *se, ssi
 	return cmdbuf;
 }
 
-int tegra_se_host1x_submit(struct tegra_se *se, u32 size)
+int tegra_se_host1x_submit(struct tegra_se *se, struct tegra_se_cmdbuf *cmdbuf, u32 size)
 {
 	struct host1x_job *job;
 	int ret;
@@ -160,9 +160,9 @@ int tegra_se_host1x_submit(struct tegra_se *se, u32 size)
 	job->engine_fallback_streamid = se->stream_id;
 	job->engine_streamid_offset = SE_STREAM_ID;
 
-	se->cmdbuf->words = size;
+	cmdbuf->words = size;
 
-	host1x_job_add_gather(job, &se->cmdbuf->bo, size, 0);
+	host1x_job_add_gather(job, &cmdbuf->bo, size, 0);
 
 	ret = host1x_job_pin(job, se->dev);
 	if (ret) {
@@ -220,14 +220,22 @@ static int tegra_se_client_init(struct host1x_client *client)
 		goto syncpt_put;
 	}
 
+	se->keybuf = tegra_se_host1x_bo_alloc(se, SZ_4K);
+	if (!se->keybuf) {
+		ret = -ENOMEM;
+		goto cmdbuf_put;
+	}
+
 	ret = se->hw->init_alg(se);
 	if (ret) {
 		dev_err(se->dev, "failed to register algorithms\n");
-		goto cmdbuf_put;
+		goto keybuf_put;
 	}
 
 	return 0;
 
+keybuf_put:
+	tegra_se_cmdbuf_put(&se->keybuf->bo);
 cmdbuf_put:
 	tegra_se_cmdbuf_put(&se->cmdbuf->bo);
 syncpt_put:
diff --git a/drivers/crypto/tegra/tegra-se.h b/drivers/crypto/tegra/tegra-se.h
index b9dd7ceb8783..e196a90eedb9 100644
--- a/drivers/crypto/tegra/tegra-se.h
+++ b/drivers/crypto/tegra/tegra-se.h
@@ -340,8 +340,6 @@
 #define SE_CRYPTO_CTR_REG_COUNT			4
 #define SE_MAX_KEYSLOT				15
 #define SE_MAX_MEM_ALLOC			SZ_4M
-#define SE_AES_BUFLEN				0x8000
-#define SE_SHA_BUFLEN				0x2000
 
 #define SHA_FIRST	BIT(0)
 #define SHA_UPDATE	BIT(1)
@@ -420,6 +418,7 @@ struct tegra_se {
 	struct host1x_client client;
 	struct host1x_channel *channel;
 	struct tegra_se_cmdbuf *cmdbuf;
+	struct tegra_se_cmdbuf *keybuf;
 	struct crypto_engine *engine;
 	struct host1x_syncpt *syncpt;
 	struct device *dev;
@@ -502,7 +501,7 @@ void tegra_deinit_hash(struct tegra_se *se);
 int tegra_key_submit(struct tegra_se *se, const u8 *key,
 		     u32 keylen, u32 alg, u32 *keyid);
 void tegra_key_invalidate(struct tegra_se *se, u32 keyid, u32 alg);
-int tegra_se_host1x_submit(struct tegra_se *se, u32 size);
+int tegra_se_host1x_submit(struct tegra_se *se, struct tegra_se_cmdbuf *cmdbuf, u32 size);
 
 /* HOST1x OPCODES */
 static inline u32 host1x_opcode_setpayload(unsigned int payload)
diff --git a/drivers/crypto/xilinx/zynqmp-sha.c b/drivers/crypto/xilinx/zynqmp-sha.c
index 1bcec6f46c9c..9b5345068604 100644
--- a/drivers/crypto/xilinx/zynqmp-sha.c
+++ b/drivers/crypto/xilinx/zynqmp-sha.c
@@ -3,18 +3,19 @@
  * Xilinx ZynqMP SHA Driver.
  * Copyright (c) 2022 Xilinx Inc.
  */
-#include <linux/cacheflush.h>
 #include <crypto/hash.h>
 #include <crypto/internal/hash.h>
 #include <crypto/sha3.h>
-#include <linux/crypto.h>
+#include <linux/cacheflush.h>
+#include <linux/cleanup.h>
 #include <linux/device.h>
 #include <linux/dma-mapping.h>
+#include <linux/err.h>
 #include <linux/firmware/xlnx-zynqmp.h>
-#include <linux/init.h>
 #include <linux/io.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/spinlock.h>
 #include <linux/platform_device.h>
 
 #define ZYNQMP_DMA_BIT_MASK		32U
@@ -43,6 +44,8 @@ struct zynqmp_sha_desc_ctx {
 static dma_addr_t update_dma_addr, final_dma_addr;
 static char *ubuf, *fbuf;
 
+static DEFINE_SPINLOCK(zynqmp_sha_lock);
+
 static int zynqmp_sha_init_tfm(struct crypto_shash *hash)
 {
 	const char *fallback_driver_name = crypto_shash_alg_name(hash);
@@ -124,7 +127,8 @@ static int zynqmp_sha_export(struct shash_desc *desc, void *out)
 	return crypto_shash_export(&dctx->fbk_req, out);
 }
 
-static int zynqmp_sha_digest(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out)
+static int __zynqmp_sha_digest(struct shash_desc *desc, const u8 *data,
+			       unsigned int len, u8 *out)
 {
 	unsigned int remaining_len = len;
 	int update_size;
@@ -159,6 +163,12 @@ static int zynqmp_sha_digest(struct shash_desc *desc, const u8 *data, unsigned i
 	return ret;
 }
 
+static int zynqmp_sha_digest(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out)
+{
+	scoped_guard(spinlock_bh, &zynqmp_sha_lock)
+		return __zynqmp_sha_digest(desc, data, len, out);
+}
+
 static struct zynqmp_sha_drv_ctx sha3_drv_ctx = {
 	.sha3_384 = {
 		.init = zynqmp_sha_init,
diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c
index a0d6e8d7f42c..f5429666822f 100644
--- a/drivers/cxl/core/region.c
+++ b/drivers/cxl/core/region.c
@@ -1781,6 +1781,13 @@ static int find_pos_and_ways(struct cxl_port *port, struct range *range,
 	}
 	put_device(dev);
 
+	if (rc)
+		dev_err(port->uport_dev,
+			"failed to find %s:%s in target list of %s\n",
+			dev_name(&port->dev),
+			dev_name(port->parent_dport->dport_dev),
+			dev_name(&cxlsd->cxld.dev));
+
 	return rc;
 }
 
diff --git a/drivers/cxl/core/regs.c b/drivers/cxl/core/regs.c
index e1082e749c69..a9c39025535f 100644
--- a/drivers/cxl/core/regs.c
+++ b/drivers/cxl/core/regs.c
@@ -513,7 +513,6 @@ resource_size_t __rcrb_to_component(struct device *dev, struct cxl_rcrb_info *ri
 	resource_size_t rcrb = ri->base;
 	void __iomem *addr;
 	u32 bar0, bar1;
-	u16 cmd;
 	u32 id;
 
 	if (which == CXL_RCRB_UPSTREAM)
@@ -535,7 +534,6 @@ resource_size_t __rcrb_to_component(struct device *dev, struct cxl_rcrb_info *ri
 	}
 
 	id = readl(addr + PCI_VENDOR_ID);
-	cmd = readw(addr + PCI_COMMAND);
 	bar0 = readl(addr + PCI_BASE_ADDRESS_0);
 	bar1 = readl(addr + PCI_BASE_ADDRESS_1);
 	iounmap(addr);
@@ -550,8 +548,6 @@ resource_size_t __rcrb_to_component(struct device *dev, struct cxl_rcrb_info *ri
 			dev_err(dev, "Failed to access Downstream Port RCRB\n");
 		return CXL_RESOURCE_NONE;
 	}
-	if (!(cmd & PCI_COMMAND_MEMORY))
-		return CXL_RESOURCE_NONE;
 	/* The RCRB is a Memory Window, and the MEM_TYPE_1M bit is obsolete */
 	if (bar0 & (PCI_BASE_ADDRESS_MEM_TYPE_1M | PCI_BASE_ADDRESS_SPACE_IO))
 		return CXL_RESOURCE_NONE;
diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index 98657d3b9435..0d9f3d3282ec 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -1382,15 +1382,11 @@ int devfreq_remove_governor(struct devfreq_governor *governor)
 		int ret;
 		struct device *dev = devfreq->dev.parent;
 
+		if (!devfreq->governor)
+			continue;
+
 		if (!strncmp(devfreq->governor->name, governor->name,
 			     DEVFREQ_NAME_LEN)) {
-			/* we should have a devfreq governor! */
-			if (!devfreq->governor) {
-				dev_warn(dev, "%s: Governor %s NOT present\n",
-					 __func__, governor->name);
-				continue;
-				/* Fall through */
-			}
 			ret = devfreq->governor->event_handler(devfreq,
 						DEVFREQ_GOV_STOP, NULL);
 			if (ret) {
@@ -1743,7 +1739,7 @@ static ssize_t trans_stat_show(struct device *dev,
 	for (i = 0; i < max_state; i++) {
 		if (len >= PAGE_SIZE - 1)
 			break;
-		if (df->freq_table[2] == df->previous_freq)
+		if (df->freq_table[i] == df->previous_freq)
 			len += sysfs_emit_at(buf, len, "*");
 		else
 			len += sysfs_emit_at(buf, len, " ");
diff --git a/drivers/devfreq/governor_userspace.c b/drivers/devfreq/governor_userspace.c
index d1aa6806b683..175de0c0b50e 100644
--- a/drivers/devfreq/governor_userspace.c
+++ b/drivers/devfreq/governor_userspace.c
@@ -9,6 +9,7 @@
 #include <linux/slab.h>
 #include <linux/device.h>
 #include <linux/devfreq.h>
+#include <linux/kstrtox.h>
 #include <linux/pm.h>
 #include <linux/mutex.h>
 #include <linux/module.h>
@@ -39,10 +40,13 @@ static ssize_t set_freq_store(struct device *dev, struct device_attribute *attr,
 	unsigned long wanted;
 	int err = 0;
 
+	err = kstrtoul(buf, 0, &wanted);
+	if (err)
+		return err;
+
 	mutex_lock(&devfreq->lock);
 	data = devfreq->governor_data;
 
-	sscanf(buf, "%lu", &wanted);
 	data->user_frequency = wanted;
 	data->valid = true;
 	err = update_devfreq(devfreq);
diff --git a/drivers/dma-buf/dma-resv.c b/drivers/dma-buf/dma-resv.c
index 5f8d010516f0..bea3e9858aca 100644
--- a/drivers/dma-buf/dma-resv.c
+++ b/drivers/dma-buf/dma-resv.c
@@ -320,8 +320,9 @@ void dma_resv_add_fence(struct dma_resv *obj, struct dma_fence *fence,
 	count++;
 
 	dma_resv_list_set(fobj, i, fence, usage);
-	/* pointer update must be visible before we extend the num_fences */
-	smp_store_mb(fobj->num_fences, count);
+	/* fence update must be visible before we extend the num_fences */
+	smp_wmb();
+	fobj->num_fences = count;
 }
 EXPORT_SYMBOL(dma_resv_add_fence);
 
@@ -684,11 +685,13 @@ long dma_resv_wait_timeout(struct dma_resv *obj, enum dma_resv_usage usage,
 	dma_resv_iter_begin(&cursor, obj, usage);
 	dma_resv_for_each_fence_unlocked(&cursor, fence) {
 
-		ret = dma_fence_wait_timeout(fence, intr, ret);
-		if (ret <= 0) {
-			dma_resv_iter_end(&cursor);
-			return ret;
-		}
+		ret = dma_fence_wait_timeout(fence, intr, timeout);
+		if (ret <= 0)
+			break;
+
+		/* Even for zero timeout the return value is 1 */
+		if (timeout)
+			timeout = ret;
 	}
 	dma_resv_iter_end(&cursor);
 
diff --git a/drivers/dma-buf/sw_sync.c b/drivers/dma-buf/sw_sync.c
index c353029789cf..1290886f065e 100644
--- a/drivers/dma-buf/sw_sync.c
+++ b/drivers/dma-buf/sw_sync.c
@@ -444,15 +444,17 @@ static int sw_sync_ioctl_get_deadline(struct sync_timeline *obj, unsigned long a
 		return -EINVAL;
 
 	pt = dma_fence_to_sync_pt(fence);
-	if (!pt)
-		return -EINVAL;
+	if (!pt) {
+		ret = -EINVAL;
+		goto put_fence;
+	}
 
 	spin_lock_irqsave(fence->lock, flags);
-	if (test_bit(SW_SYNC_HAS_DEADLINE_BIT, &fence->flags)) {
-		data.deadline_ns = ktime_to_ns(pt->deadline);
-	} else {
+	if (!test_bit(SW_SYNC_HAS_DEADLINE_BIT, &fence->flags)) {
 		ret = -ENOENT;
+		goto unlock;
 	}
+	data.deadline_ns = ktime_to_ns(pt->deadline);
 	spin_unlock_irqrestore(fence->lock, flags);
 
 	dma_fence_put(fence);
@@ -464,6 +466,13 @@ static int sw_sync_ioctl_get_deadline(struct sync_timeline *obj, unsigned long a
 		return -EFAULT;
 
 	return 0;
+
+unlock:
+	spin_unlock_irqrestore(fence->lock, flags);
+put_fence:
+	dma_fence_put(fence);
+
+	return ret;
 }
 
 static long sw_sync_ioctl(struct file *file, unsigned int cmd,
diff --git a/drivers/dma-buf/udmabuf.c b/drivers/dma-buf/udmabuf.c
index 5e836e4e5b44..959f690b1226 100644
--- a/drivers/dma-buf/udmabuf.c
+++ b/drivers/dma-buf/udmabuf.c
@@ -223,8 +223,7 @@ static int begin_cpu_udmabuf(struct dma_buf *buf,
 			ubuf->sg = NULL;
 		}
 	} else {
-		dma_sync_sg_for_cpu(dev, ubuf->sg->sgl, ubuf->sg->nents,
-				    direction);
+		dma_sync_sgtable_for_cpu(dev, ubuf->sg, direction);
 	}
 
 	return ret;
@@ -239,7 +238,7 @@ static int end_cpu_udmabuf(struct dma_buf *buf,
 	if (!ubuf->sg)
 		return -EINVAL;
 
-	dma_sync_sg_for_device(dev, ubuf->sg->sgl, ubuf->sg->nents, direction);
+	dma_sync_sgtable_for_device(dev, ubuf->sg, direction);
 	return 0;
 }
 
diff --git a/drivers/dma/fsl-edma-main.c b/drivers/dma/fsl-edma-main.c
index 70cb7fda757a..4794d58dab55 100644
--- a/drivers/dma/fsl-edma-main.c
+++ b/drivers/dma/fsl-edma-main.c
@@ -56,7 +56,7 @@ static irqreturn_t fsl_edma3_tx_handler(int irq, void *dev_id)
 
 	intr = edma_readl_chreg(fsl_chan, ch_int);
 	if (!intr)
-		return IRQ_HANDLED;
+		return IRQ_NONE;
 
 	edma_writel_chreg(fsl_chan, 1, ch_int);
 
@@ -303,6 +303,7 @@ fsl_edma2_irq_init(struct platform_device *pdev,
 
 		/* The last IRQ is for eDMA err */
 		if (i == count - 1) {
+			fsl_edma->errirq = irq;
 			ret = devm_request_irq(&pdev->dev, irq,
 						fsl_edma_err_handler,
 						0, "eDMA2-ERR", fsl_edma);
@@ -322,10 +323,13 @@ static void fsl_edma_irq_exit(
 		struct platform_device *pdev, struct fsl_edma_engine *fsl_edma)
 {
 	if (fsl_edma->txirq == fsl_edma->errirq) {
-		devm_free_irq(&pdev->dev, fsl_edma->txirq, fsl_edma);
+		if (fsl_edma->txirq >= 0)
+			devm_free_irq(&pdev->dev, fsl_edma->txirq, fsl_edma);
 	} else {
-		devm_free_irq(&pdev->dev, fsl_edma->txirq, fsl_edma);
-		devm_free_irq(&pdev->dev, fsl_edma->errirq, fsl_edma);
+		if (fsl_edma->txirq >= 0)
+			devm_free_irq(&pdev->dev, fsl_edma->txirq, fsl_edma);
+		if (fsl_edma->errirq >= 0)
+			devm_free_irq(&pdev->dev, fsl_edma->errirq, fsl_edma);
 	}
 }
 
@@ -513,6 +517,8 @@ static int fsl_edma_probe(struct platform_device *pdev)
 	if (!fsl_edma)
 		return -ENOMEM;
 
+	fsl_edma->errirq = -EINVAL;
+	fsl_edma->txirq = -EINVAL;
 	fsl_edma->drvdata = drvdata;
 	fsl_edma->n_chans = chans;
 	mutex_init(&fsl_edma->fsl_edma_mutex);
@@ -699,9 +705,9 @@ static void fsl_edma_remove(struct platform_device *pdev)
 	struct fsl_edma_engine *fsl_edma = platform_get_drvdata(pdev);
 
 	fsl_edma_irq_exit(pdev, fsl_edma);
-	fsl_edma_cleanup_vchan(&fsl_edma->dma_dev);
 	of_dma_controller_free(np);
 	dma_async_device_unregister(&fsl_edma->dma_dev);
+	fsl_edma_cleanup_vchan(&fsl_edma->dma_dev);
 	fsl_disable_clocks(fsl_edma, fsl_edma->drvdata->dmamuxs);
 }
 
diff --git a/drivers/dma/idxd/Makefile b/drivers/dma/idxd/Makefile
index 2b4a0d406e1e..9ff9d7b87b64 100644
--- a/drivers/dma/idxd/Makefile
+++ b/drivers/dma/idxd/Makefile
@@ -1,4 +1,4 @@
-ccflags-y += -DDEFAULT_SYMBOL_NAMESPACE=IDXD
+ccflags-y += -DDEFAULT_SYMBOL_NAMESPACE='"IDXD"'
 
 obj-$(CONFIG_INTEL_IDXD_BUS) += idxd_bus.o
 idxd_bus-y := bus.o
diff --git a/drivers/dma/idxd/cdev.c b/drivers/dma/idxd/cdev.c
index 57f1bf2ab20b..8b27bd545685 100644
--- a/drivers/dma/idxd/cdev.c
+++ b/drivers/dma/idxd/cdev.c
@@ -225,7 +225,7 @@ static int idxd_cdev_open(struct inode *inode, struct file *filp)
 	struct idxd_wq *wq;
 	struct device *dev, *fdev;
 	int rc = 0;
-	struct iommu_sva *sva;
+	struct iommu_sva *sva = NULL;
 	unsigned int pasid;
 	struct idxd_cdev *idxd_cdev;
 
@@ -322,7 +322,7 @@ failed_set_pasid:
 	if (device_user_pasid_enabled(idxd))
 		idxd_xa_pasid_remove(ctx);
 failed_get_pasid:
-	if (device_user_pasid_enabled(idxd))
+	if (device_user_pasid_enabled(idxd) && !IS_ERR_OR_NULL(sva))
 		iommu_sva_unbind_device(sva);
 failed:
 	mutex_unlock(&wq->wq_lock);
@@ -354,7 +354,9 @@ static void idxd_cdev_evl_drain_pasid(struct idxd_wq *wq, u32 pasid)
 			set_bit(h, evl->bmap);
 		h = (h + 1) % size;
 	}
-	drain_workqueue(wq->wq);
+	if (wq->wq)
+		drain_workqueue(wq->wq);
+
 	mutex_unlock(&evl->lock);
 }
 
@@ -412,6 +414,9 @@ static int idxd_cdev_mmap(struct file *filp, struct vm_area_struct *vma)
 	if (!idxd->user_submission_safe && !capable(CAP_SYS_RAWIO))
 		return -EPERM;
 
+	if (current->mm != ctx->mm)
+		return -EPERM;
+
 	rc = check_vma(wq, vma, __func__);
 	if (rc < 0)
 		return rc;
@@ -478,6 +483,9 @@ static ssize_t idxd_cdev_write(struct file *filp, const char __user *buf, size_t
 	ssize_t written = 0;
 	int i;
 
+	if (current->mm != ctx->mm)
+		return -EPERM;
+
 	for (i = 0; i < len/sizeof(struct dsa_hw_desc); i++) {
 		int rc = idxd_submit_user_descriptor(ctx, udesc + i);
 
@@ -498,6 +506,9 @@ static __poll_t idxd_cdev_poll(struct file *filp,
 	struct idxd_device *idxd = wq->idxd;
 	__poll_t out = 0;
 
+	if (current->mm != ctx->mm)
+		return POLLNVAL;
+
 	poll_wait(filp, &wq->err_queue, wait);
 	spin_lock(&idxd->dev_lock);
 	if (idxd->sw_err.valid)
diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c
index 234c1c658ec7..18997f80bdc9 100644
--- a/drivers/dma/idxd/init.c
+++ b/drivers/dma/idxd/init.c
@@ -153,6 +153,25 @@ static void idxd_cleanup_interrupts(struct idxd_device *idxd)
 	pci_free_irq_vectors(pdev);
 }
 
+static void idxd_clean_wqs(struct idxd_device *idxd)
+{
+	struct idxd_wq *wq;
+	struct device *conf_dev;
+	int i;
+
+	for (i = 0; i < idxd->max_wqs; i++) {
+		wq = idxd->wqs[i];
+		if (idxd->hw.wq_cap.op_config)
+			bitmap_free(wq->opcap_bmap);
+		kfree(wq->wqcfg);
+		conf_dev = wq_confdev(wq);
+		put_device(conf_dev);
+		kfree(wq);
+	}
+	bitmap_free(idxd->wq_enable_map);
+	kfree(idxd->wqs);
+}
+
 static int idxd_setup_wqs(struct idxd_device *idxd)
 {
 	struct device *dev = &idxd->pdev->dev;
@@ -167,8 +186,8 @@ static int idxd_setup_wqs(struct idxd_device *idxd)
 
 	idxd->wq_enable_map = bitmap_zalloc_node(idxd->max_wqs, GFP_KERNEL, dev_to_node(dev));
 	if (!idxd->wq_enable_map) {
-		kfree(idxd->wqs);
-		return -ENOMEM;
+		rc = -ENOMEM;
+		goto err_bitmap;
 	}
 
 	for (i = 0; i < idxd->max_wqs; i++) {
@@ -187,10 +206,8 @@ static int idxd_setup_wqs(struct idxd_device *idxd)
 		conf_dev->bus = &dsa_bus_type;
 		conf_dev->type = &idxd_wq_device_type;
 		rc = dev_set_name(conf_dev, "wq%d.%d", idxd->id, wq->id);
-		if (rc < 0) {
-			put_device(conf_dev);
+		if (rc < 0)
 			goto err;
-		}
 
 		mutex_init(&wq->wq_lock);
 		init_waitqueue_head(&wq->err_queue);
@@ -201,7 +218,6 @@ static int idxd_setup_wqs(struct idxd_device *idxd)
 		wq->enqcmds_retries = IDXD_ENQCMDS_RETRIES;
 		wq->wqcfg = kzalloc_node(idxd->wqcfg_size, GFP_KERNEL, dev_to_node(dev));
 		if (!wq->wqcfg) {
-			put_device(conf_dev);
 			rc = -ENOMEM;
 			goto err;
 		}
@@ -209,9 +225,8 @@ static int idxd_setup_wqs(struct idxd_device *idxd)
 		if (idxd->hw.wq_cap.op_config) {
 			wq->opcap_bmap = bitmap_zalloc(IDXD_MAX_OPCAP_BITS, GFP_KERNEL);
 			if (!wq->opcap_bmap) {
-				put_device(conf_dev);
 				rc = -ENOMEM;
-				goto err;
+				goto err_opcap_bmap;
 			}
 			bitmap_copy(wq->opcap_bmap, idxd->opcap_bmap, IDXD_MAX_OPCAP_BITS);
 		}
@@ -222,15 +237,46 @@ static int idxd_setup_wqs(struct idxd_device *idxd)
 
 	return 0;
 
- err:
+err_opcap_bmap:
+	kfree(wq->wqcfg);
+
+err:
+	put_device(conf_dev);
+	kfree(wq);
+
 	while (--i >= 0) {
 		wq = idxd->wqs[i];
+		if (idxd->hw.wq_cap.op_config)
+			bitmap_free(wq->opcap_bmap);
+		kfree(wq->wqcfg);
 		conf_dev = wq_confdev(wq);
 		put_device(conf_dev);
+		kfree(wq);
+
 	}
+	bitmap_free(idxd->wq_enable_map);
+
+err_bitmap:
+	kfree(idxd->wqs);
+
 	return rc;
 }
 
+static void idxd_clean_engines(struct idxd_device *idxd)
+{
+	struct idxd_engine *engine;
+	struct device *conf_dev;
+	int i;
+
+	for (i = 0; i < idxd->max_engines; i++) {
+		engine = idxd->engines[i];
+		conf_dev = engine_confdev(engine);
+		put_device(conf_dev);
+		kfree(engine);
+	}
+	kfree(idxd->engines);
+}
+
 static int idxd_setup_engines(struct idxd_device *idxd)
 {
 	struct idxd_engine *engine;
@@ -261,6 +307,7 @@ static int idxd_setup_engines(struct idxd_device *idxd)
 		rc = dev_set_name(conf_dev, "engine%d.%d", idxd->id, engine->id);
 		if (rc < 0) {
 			put_device(conf_dev);
+			kfree(engine);
 			goto err;
 		}
 
@@ -274,10 +321,26 @@ static int idxd_setup_engines(struct idxd_device *idxd)
 		engine = idxd->engines[i];
 		conf_dev = engine_confdev(engine);
 		put_device(conf_dev);
+		kfree(engine);
 	}
+	kfree(idxd->engines);
+
 	return rc;
 }
 
+static void idxd_clean_groups(struct idxd_device *idxd)
+{
+	struct idxd_group *group;
+	int i;
+
+	for (i = 0; i < idxd->max_groups; i++) {
+		group = idxd->groups[i];
+		put_device(group_confdev(group));
+		kfree(group);
+	}
+	kfree(idxd->groups);
+}
+
 static int idxd_setup_groups(struct idxd_device *idxd)
 {
 	struct device *dev = &idxd->pdev->dev;
@@ -308,6 +371,7 @@ static int idxd_setup_groups(struct idxd_device *idxd)
 		rc = dev_set_name(conf_dev, "group%d.%d", idxd->id, group->id);
 		if (rc < 0) {
 			put_device(conf_dev);
+			kfree(group);
 			goto err;
 		}
 
@@ -332,20 +396,18 @@ static int idxd_setup_groups(struct idxd_device *idxd)
 	while (--i >= 0) {
 		group = idxd->groups[i];
 		put_device(group_confdev(group));
+		kfree(group);
 	}
+	kfree(idxd->groups);
+
 	return rc;
 }
 
 static void idxd_cleanup_internals(struct idxd_device *idxd)
 {
-	int i;
-
-	for (i = 0; i < idxd->max_groups; i++)
-		put_device(group_confdev(idxd->groups[i]));
-	for (i = 0; i < idxd->max_engines; i++)
-		put_device(engine_confdev(idxd->engines[i]));
-	for (i = 0; i < idxd->max_wqs; i++)
-		put_device(wq_confdev(idxd->wqs[i]));
+	idxd_clean_groups(idxd);
+	idxd_clean_engines(idxd);
+	idxd_clean_wqs(idxd);
 	destroy_workqueue(idxd->wq);
 }
 
@@ -388,7 +450,7 @@ static int idxd_init_evl(struct idxd_device *idxd)
 static int idxd_setup_internals(struct idxd_device *idxd)
 {
 	struct device *dev = &idxd->pdev->dev;
-	int rc, i;
+	int rc;
 
 	init_waitqueue_head(&idxd->cmd_waitq);
 
@@ -419,14 +481,11 @@ static int idxd_setup_internals(struct idxd_device *idxd)
  err_evl:
 	destroy_workqueue(idxd->wq);
  err_wkq_create:
-	for (i = 0; i < idxd->max_groups; i++)
-		put_device(group_confdev(idxd->groups[i]));
+	idxd_clean_groups(idxd);
  err_group:
-	for (i = 0; i < idxd->max_engines; i++)
-		put_device(engine_confdev(idxd->engines[i]));
+	idxd_clean_engines(idxd);
  err_engine:
-	for (i = 0; i < idxd->max_wqs; i++)
-		put_device(wq_confdev(idxd->wqs[i]));
+	idxd_clean_wqs(idxd);
  err_wqs:
 	return rc;
 }
@@ -526,6 +585,17 @@ static void idxd_read_caps(struct idxd_device *idxd)
 		idxd->hw.iaa_cap.bits = ioread64(idxd->reg_base + IDXD_IAACAP_OFFSET);
 }
 
+static void idxd_free(struct idxd_device *idxd)
+{
+	if (!idxd)
+		return;
+
+	put_device(idxd_confdev(idxd));
+	bitmap_free(idxd->opcap_bmap);
+	ida_free(&idxd_ida, idxd->id);
+	kfree(idxd);
+}
+
 static struct idxd_device *idxd_alloc(struct pci_dev *pdev, struct idxd_driver_data *data)
 {
 	struct device *dev = &pdev->dev;
@@ -543,28 +613,34 @@ static struct idxd_device *idxd_alloc(struct pci_dev *pdev, struct idxd_driver_d
 	idxd_dev_set_type(&idxd->idxd_dev, idxd->data->type);
 	idxd->id = ida_alloc(&idxd_ida, GFP_KERNEL);
 	if (idxd->id < 0)
-		return NULL;
+		goto err_ida;
 
 	idxd->opcap_bmap = bitmap_zalloc_node(IDXD_MAX_OPCAP_BITS, GFP_KERNEL, dev_to_node(dev));
-	if (!idxd->opcap_bmap) {
-		ida_free(&idxd_ida, idxd->id);
-		return NULL;
-	}
+	if (!idxd->opcap_bmap)
+		goto err_opcap;
 
 	device_initialize(conf_dev);
 	conf_dev->parent = dev;
 	conf_dev->bus = &dsa_bus_type;
 	conf_dev->type = idxd->data->dev_type;
 	rc = dev_set_name(conf_dev, "%s%d", idxd->data->name_prefix, idxd->id);
-	if (rc < 0) {
-		put_device(conf_dev);
-		return NULL;
-	}
+	if (rc < 0)
+		goto err_name;
 
 	spin_lock_init(&idxd->dev_lock);
 	spin_lock_init(&idxd->cmd_lock);
 
 	return idxd;
+
+err_name:
+	put_device(conf_dev);
+	bitmap_free(idxd->opcap_bmap);
+err_opcap:
+	ida_free(&idxd_ida, idxd->id);
+err_ida:
+	kfree(idxd);
+
+	return NULL;
 }
 
 static int idxd_enable_system_pasid(struct idxd_device *idxd)
@@ -792,7 +868,7 @@ static int idxd_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
  err:
 	pci_iounmap(pdev, idxd->reg_base);
  err_iomap:
-	put_device(idxd_confdev(idxd));
+	idxd_free(idxd);
  err_idxd_alloc:
 	pci_disable_device(pdev);
 	return rc;
@@ -829,7 +905,6 @@ static void idxd_shutdown(struct pci_dev *pdev)
 static void idxd_remove(struct pci_dev *pdev)
 {
 	struct idxd_device *idxd = pci_get_drvdata(pdev);
-	struct idxd_irq_entry *irq_entry;
 
 	idxd_unregister_devices(idxd);
 	/*
@@ -842,20 +917,12 @@ static void idxd_remove(struct pci_dev *pdev)
 	get_device(idxd_confdev(idxd));
 	device_unregister(idxd_confdev(idxd));
 	idxd_shutdown(pdev);
-	if (device_pasid_enabled(idxd))
-		idxd_disable_system_pasid(idxd);
 	idxd_device_remove_debugfs(idxd);
-
-	irq_entry = idxd_get_ie(idxd, 0);
-	free_irq(irq_entry->vector, irq_entry);
-	pci_free_irq_vectors(pdev);
+	idxd_cleanup(idxd);
 	pci_iounmap(pdev, idxd->reg_base);
-	if (device_user_pasid_enabled(idxd))
-		idxd_disable_sva(pdev);
-	pci_disable_device(pdev);
-	destroy_workqueue(idxd->wq);
-	perfmon_pmu_remove(idxd);
 	put_device(idxd_confdev(idxd));
+	idxd_free(idxd);
+	pci_disable_device(pdev);
 }
 
 static struct pci_driver idxd_pci_driver = {
diff --git a/drivers/dma/mmp_tdma.c b/drivers/dma/mmp_tdma.c
index b76fe99e1151..f88792049be5 100644
--- a/drivers/dma/mmp_tdma.c
+++ b/drivers/dma/mmp_tdma.c
@@ -641,7 +641,7 @@ static int mmp_tdma_probe(struct platform_device *pdev)
 	int chan_num = TDMA_CHANNEL_NUM;
 	struct gen_pool *pool = NULL;
 
-	type = (enum mmp_tdma_type)device_get_match_data(&pdev->dev);
+	type = (kernel_ulong_t)device_get_match_data(&pdev->dev);
 
 	/* always have couple channels */
 	tdev = devm_kzalloc(&pdev->dev, sizeof(*tdev), GFP_KERNEL);
diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c
index 40b76b40bc30..184813766cd1 100644
--- a/drivers/dma/mv_xor.c
+++ b/drivers/dma/mv_xor.c
@@ -1061,8 +1061,16 @@ mv_xor_channel_add(struct mv_xor_device *xordev,
 	 */
 	mv_chan->dummy_src_addr = dma_map_single(dma_dev->dev,
 		mv_chan->dummy_src, MV_XOR_MIN_BYTE_COUNT, DMA_FROM_DEVICE);
+	if (dma_mapping_error(dma_dev->dev, mv_chan->dummy_src_addr))
+		return ERR_PTR(-ENOMEM);
+
 	mv_chan->dummy_dst_addr = dma_map_single(dma_dev->dev,
 		mv_chan->dummy_dst, MV_XOR_MIN_BYTE_COUNT, DMA_TO_DEVICE);
+	if (dma_mapping_error(dma_dev->dev, mv_chan->dummy_dst_addr)) {
+		ret = -ENOMEM;
+		goto err_unmap_src;
+	}
+
 
 	/* allocate coherent memory for hardware descriptors
 	 * note: writecombine gives slightly better performance, but
@@ -1071,8 +1079,10 @@ mv_xor_channel_add(struct mv_xor_device *xordev,
 	mv_chan->dma_desc_pool_virt =
 	  dma_alloc_wc(&pdev->dev, MV_XOR_POOL_SIZE, &mv_chan->dma_desc_pool,
 		       GFP_KERNEL);
-	if (!mv_chan->dma_desc_pool_virt)
-		return ERR_PTR(-ENOMEM);
+	if (!mv_chan->dma_desc_pool_virt) {
+		ret = -ENOMEM;
+		goto err_unmap_dst;
+	}
 
 	/* discover transaction capabilities from the platform data */
 	dma_dev->cap_mask = cap_mask;
@@ -1155,6 +1165,13 @@ err_free_irq:
 err_free_dma:
 	dma_free_coherent(&pdev->dev, MV_XOR_POOL_SIZE,
 			  mv_chan->dma_desc_pool_virt, mv_chan->dma_desc_pool);
+err_unmap_dst:
+	dma_unmap_single(dma_dev->dev, mv_chan->dummy_dst_addr,
+			 MV_XOR_MIN_BYTE_COUNT, DMA_TO_DEVICE);
+err_unmap_src:
+	dma_unmap_single(dma_dev->dev, mv_chan->dummy_src_addr,
+			 MV_XOR_MIN_BYTE_COUNT, DMA_FROM_DEVICE);
+
 	return ERR_PTR(ret);
 }
 
diff --git a/drivers/dma/nbpfaxi.c b/drivers/dma/nbpfaxi.c
index 3b011a91d48e..2fa6e90643d5 100644
--- a/drivers/dma/nbpfaxi.c
+++ b/drivers/dma/nbpfaxi.c
@@ -711,6 +711,9 @@ static int nbpf_desc_page_alloc(struct nbpf_channel *chan)
 		list_add_tail(&ldesc->node, &lhead);
 		ldesc->hwdesc_dma_addr = dma_map_single(dchan->device->dev,
 					hwdesc, sizeof(*hwdesc), DMA_TO_DEVICE);
+		if (dma_mapping_error(dchan->device->dev,
+				      ldesc->hwdesc_dma_addr))
+			goto unmap_error;
 
 		dev_dbg(dev, "%s(): mapped 0x%p to %pad\n", __func__,
 			hwdesc, &ldesc->hwdesc_dma_addr);
@@ -737,6 +740,16 @@ static int nbpf_desc_page_alloc(struct nbpf_channel *chan)
 	spin_unlock_irq(&chan->lock);
 
 	return ARRAY_SIZE(dpage->desc);
+
+unmap_error:
+	while (i--) {
+		ldesc--; hwdesc--;
+
+		dma_unmap_single(dchan->device->dev, ldesc->hwdesc_dma_addr,
+				 sizeof(hwdesc), DMA_TO_DEVICE);
+	}
+
+	return -ENOMEM;
 }
 
 static void nbpf_desc_put(struct nbpf_desc *desc)
@@ -1351,7 +1364,7 @@ static int nbpf_probe(struct platform_device *pdev)
 	if (irqs == 1) {
 		eirq = irqbuf[0];
 
-		for (i = 0; i <= num_channels; i++)
+		for (i = 0; i < num_channels; i++)
 			nbpf->chan[i].irq = irqbuf[0];
 	} else {
 		eirq = platform_get_irq_byname(pdev, "error");
@@ -1361,16 +1374,15 @@ static int nbpf_probe(struct platform_device *pdev)
 		if (irqs == num_channels + 1) {
 			struct nbpf_channel *chan;
 
-			for (i = 0, chan = nbpf->chan; i <= num_channels;
+			for (i = 0, chan = nbpf->chan; i < num_channels;
 			     i++, chan++) {
 				/* Skip the error IRQ */
 				if (irqbuf[i] == eirq)
 					i++;
+				if (i >= ARRAY_SIZE(irqbuf))
+					return -EINVAL;
 				chan->irq = irqbuf[i];
 			}
-
-			if (chan != nbpf->chan + num_channels)
-				return -EINVAL;
 		} else {
 			/* 2 IRQs and more than one channel */
 			if (irqbuf[0] == eirq)
@@ -1378,7 +1390,7 @@ static int nbpf_probe(struct platform_device *pdev)
 			else
 				irq = irqbuf[0];
 
-			for (i = 0; i <= num_channels; i++)
+			for (i = 0; i < num_channels; i++)
 				nbpf->chan[i].irq = irq;
 		}
 	}
diff --git a/drivers/dma/stm32/stm32-dma.c b/drivers/dma/stm32/stm32-dma.c
index 917f8e922373..0e39f99bce8b 100644
--- a/drivers/dma/stm32/stm32-dma.c
+++ b/drivers/dma/stm32/stm32-dma.c
@@ -744,7 +744,7 @@ static void stm32_dma_handle_chan_done(struct stm32_dma_chan *chan, u32 scr)
 		/* cyclic while CIRC/DBM disable => post resume reconfiguration needed */
 		if (!(scr & (STM32_DMA_SCR_CIRC | STM32_DMA_SCR_DBM)))
 			stm32_dma_post_resume_reconfigure(chan);
-		else if (scr & STM32_DMA_SCR_DBM)
+		else if (scr & STM32_DMA_SCR_DBM && chan->desc->num_sgs > 2)
 			stm32_dma_configure_next_sg(chan);
 	} else {
 		chan->busy = false;
diff --git a/drivers/dma/ti/edma.c b/drivers/dma/ti/edma.c
index 5f8d2e93ff3f..7f861fb07cb8 100644
--- a/drivers/dma/ti/edma.c
+++ b/drivers/dma/ti/edma.c
@@ -208,7 +208,6 @@ struct edma_desc {
 struct edma_cc;
 
 struct edma_tc {
-	struct device_node		*node;
 	u16				id;
 };
 
@@ -2466,13 +2465,13 @@ static int edma_probe(struct platform_device *pdev)
 			if (ret || i == ecc->num_tc)
 				break;
 
-			ecc->tc_list[i].node = tc_args.np;
 			ecc->tc_list[i].id = i;
 			queue_priority_mapping[i][1] = tc_args.args[0];
 			if (queue_priority_mapping[i][1] > lowest_priority) {
 				lowest_priority = queue_priority_mapping[i][1];
 				info->default_queue = i;
 			}
+			of_node_put(tc_args.np);
 		}
 
 		/* See if we have optional dma-channel-mask array */
diff --git a/drivers/dma/ti/k3-udma.c b/drivers/dma/ti/k3-udma.c
index b3f27b3f9209..38b54719587c 100644
--- a/drivers/dma/ti/k3-udma.c
+++ b/drivers/dma/ti/k3-udma.c
@@ -1091,8 +1091,11 @@ static void udma_check_tx_completion(struct work_struct *work)
 	u32 residue_diff;
 	ktime_t time_diff;
 	unsigned long delay;
+	unsigned long flags;
 
 	while (1) {
+		spin_lock_irqsave(&uc->vc.lock, flags);
+
 		if (uc->desc) {
 			/* Get previous residue and time stamp */
 			residue_diff = uc->tx_drain.residue;
@@ -1127,6 +1130,8 @@ static void udma_check_tx_completion(struct work_struct *work)
 				break;
 			}
 
+			spin_unlock_irqrestore(&uc->vc.lock, flags);
+
 			usleep_range(ktime_to_us(delay),
 				     ktime_to_us(delay) + 10);
 			continue;
@@ -1143,6 +1148,8 @@ static void udma_check_tx_completion(struct work_struct *work)
 
 		break;
 	}
+
+	spin_unlock_irqrestore(&uc->vc.lock, flags);
 }
 
 static irqreturn_t udma_ring_irq_handler(int irq, void *data)
@@ -4246,7 +4253,6 @@ static struct dma_chan *udma_of_xlate(struct of_phandle_args *dma_spec,
 				      struct of_dma *ofdma)
 {
 	struct udma_dev *ud = ofdma->of_dma_data;
-	dma_cap_mask_t mask = ud->ddev.cap_mask;
 	struct udma_filter_param filter_param;
 	struct dma_chan *chan;
 
@@ -4278,7 +4284,7 @@ static struct dma_chan *udma_of_xlate(struct of_phandle_args *dma_spec,
 		}
 	}
 
-	chan = __dma_request_channel(&mask, udma_dma_filter_fn, &filter_param,
+	chan = __dma_request_channel(&ud->ddev.cap_mask, udma_dma_filter_fn, &filter_param,
 				     ofdma->of_node);
 	if (!chan) {
 		dev_err(ud->dev, "get channel fail in %s.\n", __func__);
@@ -5566,7 +5572,8 @@ static int udma_probe(struct platform_device *pdev)
 		uc->config.dir = DMA_MEM_TO_MEM;
 		uc->name = devm_kasprintf(dev, GFP_KERNEL, "%s chan%d",
 					  dev_name(dev), i);
-
+		if (!uc->name)
+			return -ENOMEM;
 		vchan_init(&uc->vc, &ud->ddev);
 		/* Use custom vchan completion handling */
 		tasklet_setup(&uc->vc.task, udma_vchan_complete);
diff --git a/drivers/dma/xilinx/xilinx_dma.c b/drivers/dma/xilinx/xilinx_dma.c
index 5eb51ae93e89..aa59b62cd83f 100644
--- a/drivers/dma/xilinx/xilinx_dma.c
+++ b/drivers/dma/xilinx/xilinx_dma.c
@@ -2906,6 +2906,8 @@ static int xilinx_dma_chan_probe(struct xilinx_dma_device *xdev,
 		return -EINVAL;
 	}
 
+	xdev->common.directions |= chan->direction;
+
 	/* Request the interrupt */
 	chan->irq = of_irq_get(node, chan->tdest);
 	if (chan->irq < 0)
diff --git a/drivers/dpll/dpll_core.c b/drivers/dpll/dpll_core.c
index 32019dc33cca..20bdc52f63a5 100644
--- a/drivers/dpll/dpll_core.c
+++ b/drivers/dpll/dpll_core.c
@@ -443,8 +443,11 @@ static void dpll_pin_prop_free(struct dpll_pin_properties *prop)
 static int dpll_pin_prop_dup(const struct dpll_pin_properties *src,
 			     struct dpll_pin_properties *dst)
 {
+	if (WARN_ON(src->freq_supported && !src->freq_supported_num))
+		return -EINVAL;
+
 	memcpy(dst, src, sizeof(*dst));
-	if (src->freq_supported && src->freq_supported_num) {
+	if (src->freq_supported) {
 		size_t freq_size = src->freq_supported_num *
 				   sizeof(*src->freq_supported);
 		dst->freq_supported = kmemdup(src->freq_supported,
@@ -505,7 +508,7 @@ dpll_pin_alloc(u64 clock_id, u32 pin_idx, struct module *module,
 	xa_init_flags(&pin->parent_refs, XA_FLAGS_ALLOC);
 	ret = xa_alloc_cyclic(&dpll_pin_xa, &pin->id, pin, xa_limit_32b,
 			      &dpll_pin_xa_id, GFP_KERNEL);
-	if (ret)
+	if (ret < 0)
 		goto err_xa_alloc;
 	return pin;
 err_xa_alloc:
diff --git a/drivers/edac/altera_edac.c b/drivers/edac/altera_edac.c
index fe89f5c4837f..a059964b97f8 100644
--- a/drivers/edac/altera_edac.c
+++ b/drivers/edac/altera_edac.c
@@ -99,7 +99,7 @@ static irqreturn_t altr_sdram_mc_err_handler(int irq, void *dev_id)
 	if (status & priv->ecc_stat_ce_mask) {
 		regmap_read(drvdata->mc_vbase, priv->ecc_saddr_offset,
 			    &err_addr);
-		if (priv->ecc_uecnt_offset)
+		if (priv->ecc_cecnt_offset)
 			regmap_read(drvdata->mc_vbase,  priv->ecc_cecnt_offset,
 				    &err_count);
 		edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci, err_count,
@@ -1005,9 +1005,6 @@ altr_init_a10_ecc_block(struct device_node *np, u32 irq_mask,
 		}
 	}
 
-	/* Interrupt mode set to every SBERR */
-	regmap_write(ecc_mgr_map, ALTR_A10_ECC_INTMODE_OFST,
-		     ALTR_A10_ECC_INTMODE);
 	/* Enable ECC */
 	ecc_set_bits(ecc_ctrl_en_mask, (ecc_block_base +
 					ALTR_A10_ECC_CTRL_OFST));
@@ -1749,9 +1746,9 @@ altr_edac_a10_device_trig(struct file *file, const char __user *user_buf,
 
 	local_irq_save(flags);
 	if (trig_type == ALTR_UE_TRIGGER_CHAR)
-		writel(priv->ue_set_mask, set_addr);
+		writew(priv->ue_set_mask, set_addr);
 	else
-		writel(priv->ce_set_mask, set_addr);
+		writew(priv->ce_set_mask, set_addr);
 
 	/* Ensure the interrupt test bits are set */
 	wmb();
@@ -1781,7 +1778,7 @@ altr_edac_a10_device_trig2(struct file *file, const char __user *user_buf,
 
 	local_irq_save(flags);
 	if (trig_type == ALTR_UE_TRIGGER_CHAR) {
-		writel(priv->ue_set_mask, set_addr);
+		writew(priv->ue_set_mask, set_addr);
 	} else {
 		/* Setup read/write of 4 bytes */
 		writel(ECC_WORD_WRITE, drvdata->base + ECC_BLK_DBYTECTRL_OFST);
@@ -2127,6 +2124,10 @@ static int altr_edac_a10_probe(struct platform_device *pdev)
 		return PTR_ERR(edac->ecc_mgr_map);
 	}
 
+	/* Set irq mask for DDR SBE to avoid any pending irq before registration */
+	regmap_write(edac->ecc_mgr_map, A10_SYSMGR_ECC_INTMASK_SET_OFST,
+		     (A10_SYSMGR_ECC_INTMASK_SDMMCB | A10_SYSMGR_ECC_INTMASK_DDR0));
+
 	edac->irq_chip.name = pdev->dev.of_node->name;
 	edac->irq_chip.irq_mask = a10_eccmgr_irq_mask;
 	edac->irq_chip.irq_unmask = a10_eccmgr_irq_unmask;
diff --git a/drivers/edac/altera_edac.h b/drivers/edac/altera_edac.h
index 3727e72c8c2e..7248d24c4908 100644
--- a/drivers/edac/altera_edac.h
+++ b/drivers/edac/altera_edac.h
@@ -249,6 +249,8 @@ struct altr_sdram_mc_data {
 #define A10_SYSMGR_ECC_INTMASK_SET_OFST   0x94
 #define A10_SYSMGR_ECC_INTMASK_CLR_OFST   0x98
 #define A10_SYSMGR_ECC_INTMASK_OCRAM      BIT(1)
+#define A10_SYSMGR_ECC_INTMASK_SDMMCB     BIT(16)
+#define A10_SYSMGR_ECC_INTMASK_DDR0       BIT(17)
 
 #define A10_SYSMGR_ECC_INTSTAT_SERR_OFST  0x9C
 #define A10_SYSMGR_ECC_INTSTAT_DERR_OFST  0xA0
diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c
index 5d356b7c4589..322ba16b31bf 100644
--- a/drivers/edac/amd64_edac.c
+++ b/drivers/edac/amd64_edac.c
@@ -1208,7 +1208,9 @@ static int umc_get_cs_mode(int dimm, u8 ctrl, struct amd64_pvt *pvt)
 	if (csrow_enabled(2 * dimm + 1, ctrl, pvt))
 		cs_mode |= CS_ODD_PRIMARY;
 
-	/* Asymmetric dual-rank DIMM support. */
+	if (csrow_sec_enabled(2 * dimm, ctrl, pvt))
+		cs_mode |= CS_EVEN_SECONDARY;
+
 	if (csrow_sec_enabled(2 * dimm + 1, ctrl, pvt))
 		cs_mode |= CS_ODD_SECONDARY;
 
@@ -1229,12 +1231,13 @@ static int umc_get_cs_mode(int dimm, u8 ctrl, struct amd64_pvt *pvt)
 	return cs_mode;
 }
 
-static int __addr_mask_to_cs_size(u32 addr_mask_orig, unsigned int cs_mode,
-				  int csrow_nr, int dimm)
+static int calculate_cs_size(u32 mask, unsigned int cs_mode)
 {
-	u32 msb, weight, num_zero_bits;
-	u32 addr_mask_deinterleaved;
-	int size = 0;
+	int msb, weight, num_zero_bits;
+	u32 deinterleaved_mask;
+
+	if (!mask)
+		return 0;
 
 	/*
 	 * The number of zero bits in the mask is equal to the number of bits
@@ -1247,19 +1250,30 @@ static int __addr_mask_to_cs_size(u32 addr_mask_orig, unsigned int cs_mode,
 	 * without swapping with the most significant bit. This can be handled
 	 * by keeping the MSB where it is and ignoring the single zero bit.
 	 */
-	msb = fls(addr_mask_orig) - 1;
-	weight = hweight_long(addr_mask_orig);
+	msb = fls(mask) - 1;
+	weight = hweight_long(mask);
 	num_zero_bits = msb - weight - !!(cs_mode & CS_3R_INTERLEAVE);
 
 	/* Take the number of zero bits off from the top of the mask. */
-	addr_mask_deinterleaved = GENMASK_ULL(msb - num_zero_bits, 1);
+	deinterleaved_mask = GENMASK(msb - num_zero_bits, 1);
+	edac_dbg(1, "  Deinterleaved AddrMask: 0x%x\n", deinterleaved_mask);
+
+	return (deinterleaved_mask >> 2) + 1;
+}
+
+static int __addr_mask_to_cs_size(u32 addr_mask, u32 addr_mask_sec,
+				  unsigned int cs_mode, int csrow_nr, int dimm)
+{
+	int size;
 
 	edac_dbg(1, "CS%d DIMM%d AddrMasks:\n", csrow_nr, dimm);
-	edac_dbg(1, "  Original AddrMask: 0x%x\n", addr_mask_orig);
-	edac_dbg(1, "  Deinterleaved AddrMask: 0x%x\n", addr_mask_deinterleaved);
+	edac_dbg(1, "  Primary AddrMask: 0x%x\n", addr_mask);
 
 	/* Register [31:1] = Address [39:9]. Size is in kBs here. */
-	size = (addr_mask_deinterleaved >> 2) + 1;
+	size = calculate_cs_size(addr_mask, cs_mode);
+
+	edac_dbg(1, "  Secondary AddrMask: 0x%x\n", addr_mask_sec);
+	size += calculate_cs_size(addr_mask_sec, cs_mode);
 
 	/* Return size in MBs. */
 	return size >> 10;
@@ -1268,8 +1282,8 @@ static int __addr_mask_to_cs_size(u32 addr_mask_orig, unsigned int cs_mode,
 static int umc_addr_mask_to_cs_size(struct amd64_pvt *pvt, u8 umc,
 				    unsigned int cs_mode, int csrow_nr)
 {
+	u32 addr_mask = 0, addr_mask_sec = 0;
 	int cs_mask_nr = csrow_nr;
-	u32 addr_mask_orig;
 	int dimm, size = 0;
 
 	/* No Chip Selects are enabled. */
@@ -1307,13 +1321,13 @@ static int umc_addr_mask_to_cs_size(struct amd64_pvt *pvt, u8 umc,
 	if (!pvt->flags.zn_regs_v2)
 		cs_mask_nr >>= 1;
 
-	/* Asymmetric dual-rank DIMM support. */
-	if ((csrow_nr & 1) && (cs_mode & CS_ODD_SECONDARY))
-		addr_mask_orig = pvt->csels[umc].csmasks_sec[cs_mask_nr];
-	else
-		addr_mask_orig = pvt->csels[umc].csmasks[cs_mask_nr];
+	if (cs_mode & (CS_EVEN_PRIMARY | CS_ODD_PRIMARY))
+		addr_mask = pvt->csels[umc].csmasks[cs_mask_nr];
 
-	return __addr_mask_to_cs_size(addr_mask_orig, cs_mode, csrow_nr, dimm);
+	if (cs_mode & (CS_EVEN_SECONDARY | CS_ODD_SECONDARY))
+		addr_mask_sec = pvt->csels[umc].csmasks_sec[cs_mask_nr];
+
+	return __addr_mask_to_cs_size(addr_mask, addr_mask_sec, cs_mode, csrow_nr, dimm);
 }
 
 static void umc_debug_display_dimm_sizes(struct amd64_pvt *pvt, u8 ctrl)
@@ -3515,9 +3529,10 @@ static void gpu_get_err_info(struct mce *m, struct err_info *err)
 static int gpu_addr_mask_to_cs_size(struct amd64_pvt *pvt, u8 umc,
 				    unsigned int cs_mode, int csrow_nr)
 {
-	u32 addr_mask_orig = pvt->csels[umc].csmasks[csrow_nr];
+	u32 addr_mask		= pvt->csels[umc].csmasks[csrow_nr];
+	u32 addr_mask_sec	= pvt->csels[umc].csmasks_sec[csrow_nr];
 
-	return __addr_mask_to_cs_size(addr_mask_orig, cs_mode, csrow_nr, csrow_nr >> 1);
+	return __addr_mask_to_cs_size(addr_mask, addr_mask_sec, cs_mode, csrow_nr, csrow_nr >> 1);
 }
 
 static void gpu_debug_display_dimm_sizes(struct amd64_pvt *pvt, u8 ctrl)
@@ -3882,6 +3897,7 @@ static int per_family_init(struct amd64_pvt *pvt)
 			break;
 		case 0x70 ... 0x7f:
 			pvt->ctl_name			= "F19h_M70h";
+			pvt->max_mcs			= 4;
 			pvt->flags.zn_regs_v2		= 1;
 			break;
 		case 0x90 ... 0x9f:
diff --git a/drivers/edac/i10nm_base.c b/drivers/edac/i10nm_base.c
index 51556c72a967..ac4b3d95531c 100644
--- a/drivers/edac/i10nm_base.c
+++ b/drivers/edac/i10nm_base.c
@@ -95,7 +95,7 @@ static u32 offsets_demand2_spr[] = {0x22c70, 0x22d80, 0x22f18, 0x22d58, 0x22c64,
 static u32 offsets_demand_spr_hbm0[] = {0x2a54, 0x2a60, 0x2b10, 0x2a58, 0x2a5c, 0x0ee0};
 static u32 offsets_demand_spr_hbm1[] = {0x2e54, 0x2e60, 0x2f10, 0x2e58, 0x2e5c, 0x0fb0};
 
-static void __enable_retry_rd_err_log(struct skx_imc *imc, int chan, bool enable,
+static void __enable_retry_rd_err_log(struct skx_imc *imc, int chan, bool enable, u32 *rrl_ctl,
 				      u32 *offsets_scrub, u32 *offsets_demand,
 				      u32 *offsets_demand2)
 {
@@ -108,10 +108,10 @@ static void __enable_retry_rd_err_log(struct skx_imc *imc, int chan, bool enable
 
 	if (enable) {
 		/* Save default configurations */
-		imc->chan[chan].retry_rd_err_log_s = s;
-		imc->chan[chan].retry_rd_err_log_d = d;
+		rrl_ctl[0] = s;
+		rrl_ctl[1] = d;
 		if (offsets_demand2)
-			imc->chan[chan].retry_rd_err_log_d2 = d2;
+			rrl_ctl[2] = d2;
 
 		s &= ~RETRY_RD_ERR_LOG_NOOVER_UC;
 		s |=  RETRY_RD_ERR_LOG_EN;
@@ -125,25 +125,25 @@ static void __enable_retry_rd_err_log(struct skx_imc *imc, int chan, bool enable
 		}
 	} else {
 		/* Restore default configurations */
-		if (imc->chan[chan].retry_rd_err_log_s & RETRY_RD_ERR_LOG_UC)
+		if (rrl_ctl[0] & RETRY_RD_ERR_LOG_UC)
 			s |=  RETRY_RD_ERR_LOG_UC;
-		if (imc->chan[chan].retry_rd_err_log_s & RETRY_RD_ERR_LOG_NOOVER)
+		if (rrl_ctl[0] & RETRY_RD_ERR_LOG_NOOVER)
 			s |=  RETRY_RD_ERR_LOG_NOOVER;
-		if (!(imc->chan[chan].retry_rd_err_log_s & RETRY_RD_ERR_LOG_EN))
+		if (!(rrl_ctl[0] & RETRY_RD_ERR_LOG_EN))
 			s &= ~RETRY_RD_ERR_LOG_EN;
-		if (imc->chan[chan].retry_rd_err_log_d & RETRY_RD_ERR_LOG_UC)
+		if (rrl_ctl[1] & RETRY_RD_ERR_LOG_UC)
 			d |=  RETRY_RD_ERR_LOG_UC;
-		if (imc->chan[chan].retry_rd_err_log_d & RETRY_RD_ERR_LOG_NOOVER)
+		if (rrl_ctl[1] & RETRY_RD_ERR_LOG_NOOVER)
 			d |=  RETRY_RD_ERR_LOG_NOOVER;
-		if (!(imc->chan[chan].retry_rd_err_log_d & RETRY_RD_ERR_LOG_EN))
+		if (!(rrl_ctl[1] & RETRY_RD_ERR_LOG_EN))
 			d &= ~RETRY_RD_ERR_LOG_EN;
 
 		if (offsets_demand2) {
-			if (imc->chan[chan].retry_rd_err_log_d2 & RETRY_RD_ERR_LOG_UC)
+			if (rrl_ctl[2] & RETRY_RD_ERR_LOG_UC)
 				d2 |=  RETRY_RD_ERR_LOG_UC;
-			if (!(imc->chan[chan].retry_rd_err_log_d2 & RETRY_RD_ERR_LOG_NOOVER))
+			if (!(rrl_ctl[2] & RETRY_RD_ERR_LOG_NOOVER))
 				d2 &=  ~RETRY_RD_ERR_LOG_NOOVER;
-			if (!(imc->chan[chan].retry_rd_err_log_d2 & RETRY_RD_ERR_LOG_EN))
+			if (!(rrl_ctl[2] & RETRY_RD_ERR_LOG_EN))
 				d2 &= ~RETRY_RD_ERR_LOG_EN;
 		}
 	}
@@ -157,6 +157,7 @@ static void __enable_retry_rd_err_log(struct skx_imc *imc, int chan, bool enable
 static void enable_retry_rd_err_log(bool enable)
 {
 	int i, j, imc_num, chan_num;
+	struct skx_channel *chan;
 	struct skx_imc *imc;
 	struct skx_dev *d;
 
@@ -171,8 +172,9 @@ static void enable_retry_rd_err_log(bool enable)
 			if (!imc->mbase)
 				continue;
 
+			chan = d->imc[i].chan;
 			for (j = 0; j < chan_num; j++)
-				__enable_retry_rd_err_log(imc, j, enable,
+				__enable_retry_rd_err_log(imc, j, enable, chan[j].rrl_ctl[0],
 							  res_cfg->offsets_scrub,
 							  res_cfg->offsets_demand,
 							  res_cfg->offsets_demand2);
@@ -186,12 +188,13 @@ static void enable_retry_rd_err_log(bool enable)
 			if (!imc->mbase || !imc->hbm_mc)
 				continue;
 
+			chan = d->imc[i].chan;
 			for (j = 0; j < chan_num; j++) {
-				__enable_retry_rd_err_log(imc, j, enable,
+				__enable_retry_rd_err_log(imc, j, enable, chan[j].rrl_ctl[0],
 							  res_cfg->offsets_scrub_hbm0,
 							  res_cfg->offsets_demand_hbm0,
 							  NULL);
-				__enable_retry_rd_err_log(imc, j, enable,
+				__enable_retry_rd_err_log(imc, j, enable, chan[j].rrl_ctl[1],
 							  res_cfg->offsets_scrub_hbm1,
 							  res_cfg->offsets_demand_hbm1,
 							  NULL);
@@ -751,6 +754,8 @@ static int i10nm_get_ddr_munits(void)
 				continue;
 			} else {
 				d->imc[lmc].mdev = mdev;
+				if (res_cfg->type == SPR)
+					skx_set_mc_mapping(d, i, lmc);
 				lmc++;
 			}
 		}
diff --git a/drivers/edac/ie31200_edac.c b/drivers/edac/ie31200_edac.c
index 9ef13570f2e5..e3635fba63b4 100644
--- a/drivers/edac/ie31200_edac.c
+++ b/drivers/edac/ie31200_edac.c
@@ -91,8 +91,6 @@
 	 (((did) & PCI_DEVICE_ID_INTEL_IE31200_HB_CFL_MASK) ==                 \
 	  PCI_DEVICE_ID_INTEL_IE31200_HB_CFL_MASK))
 
-#define IE31200_DIMMS			4
-#define IE31200_RANKS			8
 #define IE31200_RANKS_PER_CHANNEL	4
 #define IE31200_DIMMS_PER_CHANNEL	2
 #define IE31200_CHANNELS		2
@@ -164,6 +162,7 @@
 #define IE31200_MAD_DIMM_0_OFFSET		0x5004
 #define IE31200_MAD_DIMM_0_OFFSET_SKL		0x500C
 #define IE31200_MAD_DIMM_SIZE			GENMASK_ULL(7, 0)
+#define IE31200_MAD_DIMM_SIZE_SKL		GENMASK_ULL(5, 0)
 #define IE31200_MAD_DIMM_A_RANK			BIT(17)
 #define IE31200_MAD_DIMM_A_RANK_SHIFT		17
 #define IE31200_MAD_DIMM_A_RANK_SKL		BIT(10)
@@ -377,7 +376,7 @@ static void __iomem *ie31200_map_mchbar(struct pci_dev *pdev)
 static void __skl_populate_dimm_info(struct dimm_data *dd, u32 addr_decode,
 				     int chan)
 {
-	dd->size = (addr_decode >> (chan << 4)) & IE31200_MAD_DIMM_SIZE;
+	dd->size = (addr_decode >> (chan << 4)) & IE31200_MAD_DIMM_SIZE_SKL;
 	dd->dual_rank = (addr_decode & (IE31200_MAD_DIMM_A_RANK_SKL << (chan << 4))) ? 1 : 0;
 	dd->x16_width = ((addr_decode & (IE31200_MAD_DIMM_A_WIDTH_SKL << (chan << 4))) >>
 				(IE31200_MAD_DIMM_A_WIDTH_SKL_SHIFT + (chan << 4)));
@@ -406,10 +405,9 @@ static int ie31200_probe1(struct pci_dev *pdev, int dev_idx)
 	int i, j, ret;
 	struct mem_ctl_info *mci = NULL;
 	struct edac_mc_layer layers[2];
-	struct dimm_data dimm_info[IE31200_CHANNELS][IE31200_DIMMS_PER_CHANNEL];
 	void __iomem *window;
 	struct ie31200_priv *priv;
-	u32 addr_decode, mad_offset;
+	u32 addr_decode[IE31200_CHANNELS], mad_offset;
 
 	/*
 	 * Kaby Lake, Coffee Lake seem to work like Skylake. Please re-visit
@@ -426,7 +424,7 @@ static int ie31200_probe1(struct pci_dev *pdev, int dev_idx)
 
 	nr_channels = how_many_channels(pdev);
 	layers[0].type = EDAC_MC_LAYER_CHIP_SELECT;
-	layers[0].size = IE31200_DIMMS;
+	layers[0].size = IE31200_RANKS_PER_CHANNEL;
 	layers[0].is_virt_csrow = true;
 	layers[1].type = EDAC_MC_LAYER_CHANNEL;
 	layers[1].size = nr_channels;
@@ -467,19 +465,10 @@ static int ie31200_probe1(struct pci_dev *pdev, int dev_idx)
 		mad_offset = IE31200_MAD_DIMM_0_OFFSET;
 	}
 
-	/* populate DIMM info */
 	for (i = 0; i < IE31200_CHANNELS; i++) {
-		addr_decode = readl(window + mad_offset +
+		addr_decode[i] = readl(window + mad_offset +
 					(i * 4));
-		edac_dbg(0, "addr_decode: 0x%x\n", addr_decode);
-		for (j = 0; j < IE31200_DIMMS_PER_CHANNEL; j++) {
-			populate_dimm_info(&dimm_info[i][j], addr_decode, j,
-					   skl);
-			edac_dbg(0, "size: 0x%x, rank: %d, width: %d\n",
-				 dimm_info[i][j].size,
-				 dimm_info[i][j].dual_rank,
-				 dimm_info[i][j].x16_width);
-		}
+		edac_dbg(0, "addr_decode: 0x%x\n", addr_decode[i]);
 	}
 
 	/*
@@ -490,14 +479,22 @@ static int ie31200_probe1(struct pci_dev *pdev, int dev_idx)
 	 */
 	for (i = 0; i < IE31200_DIMMS_PER_CHANNEL; i++) {
 		for (j = 0; j < IE31200_CHANNELS; j++) {
+			struct dimm_data dimm_info;
 			struct dimm_info *dimm;
 			unsigned long nr_pages;
 
-			nr_pages = IE31200_PAGES(dimm_info[j][i].size, skl);
+			populate_dimm_info(&dimm_info, addr_decode[j], i,
+					   skl);
+			edac_dbg(0, "size: 0x%x, rank: %d, width: %d\n",
+				 dimm_info.size,
+				 dimm_info.dual_rank,
+				 dimm_info.x16_width);
+
+			nr_pages = IE31200_PAGES(dimm_info.size, skl);
 			if (nr_pages == 0)
 				continue;
 
-			if (dimm_info[j][i].dual_rank) {
+			if (dimm_info.dual_rank) {
 				nr_pages = nr_pages / 2;
 				dimm = edac_get_dimm(mci, (i * 2) + 1, j, 0);
 				dimm->nr_pages = nr_pages;
@@ -618,7 +615,7 @@ static int __init ie31200_init(void)
 
 	pci_rc = pci_register_driver(&ie31200_driver);
 	if (pci_rc < 0)
-		goto fail0;
+		return pci_rc;
 
 	if (!mci_pdev) {
 		ie31200_registered = 0;
@@ -629,11 +626,13 @@ static int __init ie31200_init(void)
 			if (mci_pdev)
 				break;
 		}
+
 		if (!mci_pdev) {
 			edac_dbg(0, "ie31200 pci_get_device fail\n");
 			pci_rc = -ENODEV;
-			goto fail1;
+			goto fail0;
 		}
+
 		pci_rc = ie31200_init_one(mci_pdev, &ie31200_pci_tbl[i]);
 		if (pci_rc < 0) {
 			edac_dbg(0, "ie31200 init fail\n");
@@ -641,12 +640,12 @@ static int __init ie31200_init(void)
 			goto fail1;
 		}
 	}
-	return 0;
 
+	return 0;
 fail1:
-	pci_unregister_driver(&ie31200_driver);
-fail0:
 	pci_dev_put(mci_pdev);
+fail0:
+	pci_unregister_driver(&ie31200_driver);
 
 	return pci_rc;
 }
diff --git a/drivers/edac/qcom_edac.c b/drivers/edac/qcom_edac.c
index a9a8ba067007..0fd7a777fe7d 100644
--- a/drivers/edac/qcom_edac.c
+++ b/drivers/edac/qcom_edac.c
@@ -95,7 +95,7 @@ static int qcom_llcc_core_setup(struct llcc_drv_data *drv, struct regmap *llcc_b
 	 * Configure interrupt enable registers such that Tag, Data RAM related
 	 * interrupts are propagated to interrupt controller for servicing
 	 */
-	ret = regmap_update_bits(llcc_bcast_regmap, drv->edac_reg_offset->cmn_interrupt_2_enable,
+	ret = regmap_update_bits(llcc_bcast_regmap, drv->edac_reg_offset->cmn_interrupt_0_enable,
 				 TRP0_INTERRUPT_ENABLE,
 				 TRP0_INTERRUPT_ENABLE);
 	if (ret)
@@ -113,7 +113,7 @@ static int qcom_llcc_core_setup(struct llcc_drv_data *drv, struct regmap *llcc_b
 	if (ret)
 		return ret;
 
-	ret = regmap_update_bits(llcc_bcast_regmap, drv->edac_reg_offset->cmn_interrupt_2_enable,
+	ret = regmap_update_bits(llcc_bcast_regmap, drv->edac_reg_offset->cmn_interrupt_0_enable,
 				 DRP0_INTERRUPT_ENABLE,
 				 DRP0_INTERRUPT_ENABLE);
 	if (ret)
diff --git a/drivers/edac/skx_common.c b/drivers/edac/skx_common.c
index 6cf17af7d911..88f5ff249f2e 100644
--- a/drivers/edac/skx_common.c
+++ b/drivers/edac/skx_common.c
@@ -115,11 +115,41 @@ EXPORT_SYMBOL_GPL(skx_adxl_get);
 
 void skx_adxl_put(void)
 {
+	adxl_component_count = 0;
 	kfree(adxl_values);
 	kfree(adxl_msg);
 }
 EXPORT_SYMBOL_GPL(skx_adxl_put);
 
+static void skx_init_mc_mapping(struct skx_dev *d)
+{
+	/*
+	 * By default, the BIOS presents all memory controllers within each
+	 * socket to the EDAC driver. The physical indices are the same as
+	 * the logical indices of the memory controllers enumerated by the
+	 * EDAC driver.
+	 */
+	for (int i = 0; i < NUM_IMC; i++)
+		d->mc_mapping[i] = i;
+}
+
+void skx_set_mc_mapping(struct skx_dev *d, u8 pmc, u8 lmc)
+{
+	edac_dbg(0, "Set the mapping of mc phy idx to logical idx: %02d -> %02d\n",
+		 pmc, lmc);
+
+	d->mc_mapping[pmc] = lmc;
+}
+EXPORT_SYMBOL_GPL(skx_set_mc_mapping);
+
+static u8 skx_get_mc_mapping(struct skx_dev *d, u8 pmc)
+{
+	edac_dbg(0, "Get the mapping of mc phy idx to logical idx: %02d -> %02d\n",
+		 pmc, d->mc_mapping[pmc]);
+
+	return d->mc_mapping[pmc];
+}
+
 static bool skx_adxl_decode(struct decoded_addr *res, enum error_source err_src)
 {
 	struct skx_dev *d;
@@ -187,6 +217,8 @@ static bool skx_adxl_decode(struct decoded_addr *res, enum error_source err_src)
 		return false;
 	}
 
+	res->imc = skx_get_mc_mapping(d, res->imc);
+
 	for (i = 0; i < adxl_component_count; i++) {
 		if (adxl_values[i] == ~0x0ull)
 			continue;
@@ -307,6 +339,8 @@ int skx_get_all_bus_mappings(struct res_config *cfg, struct list_head **list)
 			 d->bus[0], d->bus[1], d->bus[2], d->bus[3]);
 		list_add_tail(&d->list, &dev_edac_list);
 		prev = pdev;
+
+		skx_init_mc_mapping(d);
 	}
 
 	if (list)
diff --git a/drivers/edac/skx_common.h b/drivers/edac/skx_common.h
index 54bba8a62f72..f40eb6e4f631 100644
--- a/drivers/edac/skx_common.h
+++ b/drivers/edac/skx_common.h
@@ -79,6 +79,9 @@
  */
 #define MCACOD_EXT_MEM_ERR	0x280
 
+/* Max RRL register sets per {,sub-,pseudo-}channel. */
+#define NUM_RRL_SET		3
+
 /*
  * Each cpu socket contains some pci devices that provide global
  * information, and also some that are local to each of the two
@@ -93,6 +96,16 @@ struct skx_dev {
 	struct pci_dev *uracu; /* for i10nm CPU */
 	struct pci_dev *pcu_cr3; /* for HBM memory detection */
 	u32 mcroute;
+	/*
+	 * Some server BIOS may hide certain memory controllers, and the
+	 * EDAC driver skips those hidden memory controllers. However, the
+	 * ADXL still decodes memory error address using physical memory
+	 * controller indices. The mapping table is used to convert the
+	 * physical indices (reported by ADXL) to the logical indices
+	 * (used the EDAC driver) of present memory controllers during the
+	 * error handling process.
+	 */
+	u8 mc_mapping[NUM_IMC];
 	struct skx_imc {
 		struct mem_ctl_info *mci;
 		struct pci_dev *mdev; /* for i10nm CPU */
@@ -107,9 +120,11 @@ struct skx_dev {
 		struct skx_channel {
 			struct pci_dev	*cdev;
 			struct pci_dev	*edev;
-			u32 retry_rd_err_log_s;
-			u32 retry_rd_err_log_d;
-			u32 retry_rd_err_log_d2;
+			/*
+			 * Two groups of RRL control registers per channel to save default RRL
+			 * settings of two {sub-,pseudo-}channels in Linux RRL control mode.
+			 */
+			u32 rrl_ctl[2][NUM_RRL_SET];
 			struct skx_dimm {
 				u8 close_pg;
 				u8 bank_xor_enable;
@@ -242,6 +257,7 @@ void skx_adxl_put(void);
 void skx_set_decode(skx_decode_f decode, skx_show_retry_log_f show_retry_log);
 void skx_set_mem_cfg(bool mem_cfg_2lm);
 void skx_set_res_cfg(struct res_config *cfg);
+void skx_set_mc_mapping(struct skx_dev *d, u8 pmc, u8 lmc);
 
 int skx_get_src_id(struct skx_dev *d, int off, u8 *id);
 int skx_get_node_id(struct skx_dev *d, u8 *id);
diff --git a/drivers/edac/synopsys_edac.c b/drivers/edac/synopsys_edac.c
index d7416166fd8a..ec3ed5e2b2d7 100644
--- a/drivers/edac/synopsys_edac.c
+++ b/drivers/edac/synopsys_edac.c
@@ -332,20 +332,26 @@ struct synps_edac_priv {
 #endif
 };
 
+enum synps_platform_type {
+	ZYNQ,
+	ZYNQMP,
+	SYNPS,
+};
+
 /**
  * struct synps_platform_data -  synps platform data structure.
+ * @platform:		Identifies the target hardware platform
  * @get_error_info:	Get EDAC error info.
  * @get_mtype:		Get mtype.
  * @get_dtype:		Get dtype.
- * @get_ecc_state:	Get ECC state.
  * @get_mem_info:	Get EDAC memory info
  * @quirks:		To differentiate IPs.
  */
 struct synps_platform_data {
+	enum synps_platform_type platform;
 	int (*get_error_info)(struct synps_edac_priv *priv);
 	enum mem_type (*get_mtype)(const void __iomem *base);
 	enum dev_type (*get_dtype)(const void __iomem *base);
-	bool (*get_ecc_state)(void __iomem *base);
 #ifdef CONFIG_EDAC_DEBUG
 	u64 (*get_mem_info)(struct synps_edac_priv *priv);
 #endif
@@ -720,51 +726,38 @@ static enum dev_type zynqmp_get_dtype(const void __iomem *base)
 	return dt;
 }
 
-/**
- * zynq_get_ecc_state - Return the controller ECC enable/disable status.
- * @base:	DDR memory controller base address.
- *
- * Get the ECC enable/disable status of the controller.
- *
- * Return: true if enabled, otherwise false.
- */
-static bool zynq_get_ecc_state(void __iomem *base)
+static bool get_ecc_state(struct synps_edac_priv *priv)
 {
+	u32 ecctype, clearval;
 	enum dev_type dt;
-	u32 ecctype;
-
-	dt = zynq_get_dtype(base);
-	if (dt == DEV_UNKNOWN)
-		return false;
 
-	ecctype = readl(base + SCRUB_OFST) & SCRUB_MODE_MASK;
-	if ((ecctype == SCRUB_MODE_SECDED) && (dt == DEV_X2))
-		return true;
-
-	return false;
-}
-
-/**
- * zynqmp_get_ecc_state - Return the controller ECC enable/disable status.
- * @base:	DDR memory controller base address.
- *
- * Get the ECC enable/disable status for the controller.
- *
- * Return: a ECC status boolean i.e true/false - enabled/disabled.
- */
-static bool zynqmp_get_ecc_state(void __iomem *base)
-{
-	enum dev_type dt;
-	u32 ecctype;
-
-	dt = zynqmp_get_dtype(base);
-	if (dt == DEV_UNKNOWN)
-		return false;
-
-	ecctype = readl(base + ECC_CFG0_OFST) & SCRUB_MODE_MASK;
-	if ((ecctype == SCRUB_MODE_SECDED) &&
-	    ((dt == DEV_X2) || (dt == DEV_X4) || (dt == DEV_X8)))
-		return true;
+	if (priv->p_data->platform == ZYNQ) {
+		dt = zynq_get_dtype(priv->baseaddr);
+		if (dt == DEV_UNKNOWN)
+			return false;
+
+		ecctype = readl(priv->baseaddr + SCRUB_OFST) & SCRUB_MODE_MASK;
+		if (ecctype == SCRUB_MODE_SECDED && dt == DEV_X2) {
+			clearval = ECC_CTRL_CLR_CE_ERR | ECC_CTRL_CLR_UE_ERR;
+			writel(clearval, priv->baseaddr + ECC_CTRL_OFST);
+			writel(0x0, priv->baseaddr + ECC_CTRL_OFST);
+			return true;
+		}
+	} else {
+		dt = zynqmp_get_dtype(priv->baseaddr);
+		if (dt == DEV_UNKNOWN)
+			return false;
+
+		ecctype = readl(priv->baseaddr + ECC_CFG0_OFST) & SCRUB_MODE_MASK;
+		if (ecctype == SCRUB_MODE_SECDED &&
+		    (dt == DEV_X2 || dt == DEV_X4 || dt == DEV_X8)) {
+			clearval = readl(priv->baseaddr + ECC_CLR_OFST) |
+			ECC_CTRL_CLR_CE_ERR | ECC_CTRL_CLR_CE_ERRCNT |
+			ECC_CTRL_CLR_UE_ERR | ECC_CTRL_CLR_UE_ERRCNT;
+			writel(clearval, priv->baseaddr + ECC_CLR_OFST);
+			return true;
+		}
+	}
 
 	return false;
 }
@@ -934,18 +927,18 @@ static int setup_irq(struct mem_ctl_info *mci,
 }
 
 static const struct synps_platform_data zynq_edac_def = {
+	.platform = ZYNQ,
 	.get_error_info	= zynq_get_error_info,
 	.get_mtype	= zynq_get_mtype,
 	.get_dtype	= zynq_get_dtype,
-	.get_ecc_state	= zynq_get_ecc_state,
 	.quirks		= 0,
 };
 
 static const struct synps_platform_data zynqmp_edac_def = {
+	.platform = ZYNQMP,
 	.get_error_info	= zynqmp_get_error_info,
 	.get_mtype	= zynqmp_get_mtype,
 	.get_dtype	= zynqmp_get_dtype,
-	.get_ecc_state	= zynqmp_get_ecc_state,
 #ifdef CONFIG_EDAC_DEBUG
 	.get_mem_info	= zynqmp_get_mem_info,
 #endif
@@ -957,10 +950,10 @@ static const struct synps_platform_data zynqmp_edac_def = {
 };
 
 static const struct synps_platform_data synopsys_edac_def = {
+	.platform = SYNPS,
 	.get_error_info	= zynqmp_get_error_info,
 	.get_mtype	= zynqmp_get_mtype,
 	.get_dtype	= zynqmp_get_dtype,
-	.get_ecc_state	= zynqmp_get_ecc_state,
 	.quirks         = (DDR_ECC_INTR_SUPPORT | DDR_ECC_INTR_SELF_CLEAR
 #ifdef CONFIG_EDAC_DEBUG
 			  | DDR_ECC_DATA_POISON_SUPPORT
@@ -1390,10 +1383,6 @@ static int mc_probe(struct platform_device *pdev)
 	if (!p_data)
 		return -ENODEV;
 
-	if (!p_data->get_ecc_state(baseaddr)) {
-		edac_printk(KERN_INFO, EDAC_MC, "ECC not enabled\n");
-		return -ENXIO;
-	}
 
 	layers[0].type = EDAC_MC_LAYER_CHIP_SELECT;
 	layers[0].size = SYNPS_EDAC_NR_CSROWS;
@@ -1413,6 +1402,12 @@ static int mc_probe(struct platform_device *pdev)
 	priv = mci->pvt_info;
 	priv->baseaddr = baseaddr;
 	priv->p_data = p_data;
+	if (!get_ecc_state(priv)) {
+		edac_printk(KERN_INFO, EDAC_MC, "ECC not enabled\n");
+		rc = -ENODEV;
+		goto free_edac_mc;
+	}
+
 	spin_lock_init(&priv->reglock);
 
 	mc_init(mci, pdev);
diff --git a/drivers/firewire/device-attribute-test.c b/drivers/firewire/device-attribute-test.c
index 2f123c6b0a16..97478a96d1c9 100644
--- a/drivers/firewire/device-attribute-test.c
+++ b/drivers/firewire/device-attribute-test.c
@@ -99,6 +99,7 @@ static void device_attr_simple_avc(struct kunit *test)
 	struct device *unit0_dev = (struct device *)&unit0.device;
 	static const int unit0_expected_ids[] = {0x00ffffff, 0x00ffffff, 0x0000a02d, 0x00010001};
 	char *buf = kunit_kzalloc(test, PAGE_SIZE, GFP_KERNEL);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, buf);
 	int ids[4] = {0, 0, 0, 0};
 
 	// Ensure associations for node and unit devices.
@@ -180,6 +181,7 @@ static void device_attr_legacy_avc(struct kunit *test)
 	struct device *unit0_dev = (struct device *)&unit0.device;
 	static const int unit0_expected_ids[] = {0x00012345, 0x00fedcba, 0x00abcdef, 0x00543210};
 	char *buf = kunit_kzalloc(test, PAGE_SIZE, GFP_KERNEL);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, buf);
 	int ids[4] = {0, 0, 0, 0};
 
 	// Ensure associations for node and unit devices.
diff --git a/drivers/firmware/Kconfig b/drivers/firmware/Kconfig
index 71d8b26c4103..f7044bf53d1f 100644
--- a/drivers/firmware/Kconfig
+++ b/drivers/firmware/Kconfig
@@ -31,7 +31,6 @@ config ARM_SCPI_PROTOCOL
 config ARM_SDE_INTERFACE
 	bool "ARM Software Delegated Exception Interface (SDEI)"
 	depends on ARM64
-	depends on ACPI_APEI_GHES
 	help
 	  The Software Delegated Exception Interface (SDEI) is an ARM
 	  standard for registering callbacks from the platform firmware
@@ -106,7 +105,7 @@ config ISCSI_IBFT
 	select ISCSI_BOOT_SYSFS
 	select ISCSI_IBFT_FIND if X86
 	depends on ACPI && SCSI && SCSI_LOWLEVEL
-	default	n
+	default n
 	help
 	  This option enables support for detection and exposing of iSCSI
 	  Boot Firmware Table (iBFT) via sysfs to userspace. If you wish to
diff --git a/drivers/firmware/arm_ffa/bus.c b/drivers/firmware/arm_ffa/bus.c
index dfda5ffc14db..dea3eb741d95 100644
--- a/drivers/firmware/arm_ffa/bus.c
+++ b/drivers/firmware/arm_ffa/bus.c
@@ -212,6 +212,7 @@ ffa_device_register(const struct ffa_partition_info *part_info,
 	dev = &ffa_dev->dev;
 	dev->bus = &ffa_bus_type;
 	dev->release = ffa_release_device;
+	dev->dma_mask = &dev->coherent_dma_mask;
 	dev_set_name(&ffa_dev->dev, "arm-ffa-%d", id);
 
 	ffa_dev->id = id;
diff --git a/drivers/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c
index 2c2ec3c35f15..9fdfccbc6479 100644
--- a/drivers/firmware/arm_ffa/driver.c
+++ b/drivers/firmware/arm_ffa/driver.c
@@ -110,7 +110,7 @@ struct ffa_drv_info {
 	struct work_struct sched_recv_irq_work;
 	struct xarray partition_info;
 	DECLARE_HASHTABLE(notifier_hash, ilog2(FFA_MAX_NOTIFICATIONS));
-	struct mutex notify_lock; /* lock to protect notifier hashtable  */
+	rwlock_t notify_lock; /* lock to protect notifier hashtable  */
 };
 
 static struct ffa_drv_info *drv_info;
@@ -150,6 +150,14 @@ static int ffa_version_check(u32 *version)
 		return -EOPNOTSUPP;
 	}
 
+	if (FFA_MAJOR_VERSION(ver.a0) > FFA_MAJOR_VERSION(FFA_DRIVER_VERSION)) {
+		pr_err("Incompatible v%d.%d! Latest supported v%d.%d\n",
+		       FFA_MAJOR_VERSION(ver.a0), FFA_MINOR_VERSION(ver.a0),
+		       FFA_MAJOR_VERSION(FFA_DRIVER_VERSION),
+		       FFA_MINOR_VERSION(FFA_DRIVER_VERSION));
+		return -EINVAL;
+	}
+
 	if (ver.a0 < FFA_MIN_VERSION) {
 		pr_err("Incompatible v%d.%d! Earliest supported v%d.%d\n",
 		       FFA_MAJOR_VERSION(ver.a0), FFA_MINOR_VERSION(ver.a0),
@@ -280,7 +288,8 @@ __ffa_partition_info_get(u32 uuid0, u32 uuid1, u32 uuid2, u32 uuid3,
 			memcpy(buffer + idx, drv_info->rx_buffer + idx * sz,
 			       buf_sz);
 
-	ffa_rx_release();
+	if (!(flags & PARTITION_INFO_GET_RETURN_COUNT_ONLY))
+		ffa_rx_release();
 
 	mutex_unlock(&drv_info->rx_lock);
 
@@ -1132,12 +1141,11 @@ notifier_hash_node_get(u16 notify_id, enum notify_type type)
 	return NULL;
 }
 
-static int
-update_notifier_cb(int notify_id, enum notify_type type, ffa_notifier_cb cb,
-		   void *cb_data, bool is_registration)
+static int update_notifier_cb(int notify_id, enum notify_type type,
+			      struct notifier_cb_info *cb)
 {
 	struct notifier_cb_info *cb_info = NULL;
-	bool cb_found;
+	bool cb_found, is_registration = !!cb;
 
 	cb_info = notifier_hash_node_get(notify_id, type);
 	cb_found = !!cb_info;
@@ -1146,17 +1154,10 @@ update_notifier_cb(int notify_id, enum notify_type type, ffa_notifier_cb cb,
 		return -EINVAL;
 
 	if (is_registration) {
-		cb_info = kzalloc(sizeof(*cb_info), GFP_KERNEL);
-		if (!cb_info)
-			return -ENOMEM;
-
-		cb_info->type = type;
-		cb_info->cb = cb;
-		cb_info->cb_data = cb_data;
-
-		hash_add(drv_info->notifier_hash, &cb_info->hnode, notify_id);
+		hash_add(drv_info->notifier_hash, &cb->hnode, notify_id);
 	} else {
 		hash_del(&cb_info->hnode);
+		kfree(cb_info);
 	}
 
 	return 0;
@@ -1181,18 +1182,18 @@ static int ffa_notify_relinquish(struct ffa_device *dev, int notify_id)
 	if (notify_id >= FFA_MAX_NOTIFICATIONS)
 		return -EINVAL;
 
-	mutex_lock(&drv_info->notify_lock);
+	write_lock(&drv_info->notify_lock);
 
-	rc = update_notifier_cb(notify_id, type, NULL, NULL, false);
+	rc = update_notifier_cb(notify_id, type, NULL);
 	if (rc) {
 		pr_err("Could not unregister notification callback\n");
-		mutex_unlock(&drv_info->notify_lock);
+		write_unlock(&drv_info->notify_lock);
 		return rc;
 	}
 
 	rc = ffa_notification_unbind(dev->vm_id, BIT(notify_id));
 
-	mutex_unlock(&drv_info->notify_lock);
+	write_unlock(&drv_info->notify_lock);
 
 	return rc;
 }
@@ -1202,6 +1203,7 @@ static int ffa_notify_request(struct ffa_device *dev, bool is_per_vcpu,
 {
 	int rc;
 	u32 flags = 0;
+	struct notifier_cb_info *cb_info = NULL;
 	enum notify_type type = ffa_notify_type_get(dev->vm_id);
 
 	if (ffa_notifications_disabled())
@@ -1210,24 +1212,34 @@ static int ffa_notify_request(struct ffa_device *dev, bool is_per_vcpu,
 	if (notify_id >= FFA_MAX_NOTIFICATIONS)
 		return -EINVAL;
 
-	mutex_lock(&drv_info->notify_lock);
+	cb_info = kzalloc(sizeof(*cb_info), GFP_KERNEL);
+	if (!cb_info)
+		return -ENOMEM;
+
+	cb_info->type = type;
+	cb_info->cb_data = cb_data;
+	cb_info->cb = cb;
+
+	write_lock(&drv_info->notify_lock);
 
 	if (is_per_vcpu)
 		flags = PER_VCPU_NOTIFICATION_FLAG;
 
 	rc = ffa_notification_bind(dev->vm_id, BIT(notify_id), flags);
-	if (rc) {
-		mutex_unlock(&drv_info->notify_lock);
-		return rc;
-	}
+	if (rc)
+		goto out_unlock_free;
 
-	rc = update_notifier_cb(notify_id, type, cb, cb_data, true);
+	rc = update_notifier_cb(notify_id, type, cb_info);
 	if (rc) {
 		pr_err("Failed to register callback for %d - %d\n",
 		       notify_id, rc);
 		ffa_notification_unbind(dev->vm_id, BIT(notify_id));
 	}
-	mutex_unlock(&drv_info->notify_lock);
+
+out_unlock_free:
+	write_unlock(&drv_info->notify_lock);
+	if (rc)
+		kfree(cb_info);
 
 	return rc;
 }
@@ -1257,9 +1269,9 @@ static void handle_notif_callbacks(u64 bitmap, enum notify_type type)
 		if (!(bitmap & 1))
 			continue;
 
-		mutex_lock(&drv_info->notify_lock);
+		read_lock(&drv_info->notify_lock);
 		cb_info = notifier_hash_node_get(notify_id, type);
-		mutex_unlock(&drv_info->notify_lock);
+		read_unlock(&drv_info->notify_lock);
 
 		if (cb_info && cb_info->cb)
 			cb_info->cb(notify_id, cb_info->cb_data);
@@ -1440,6 +1452,10 @@ static int ffa_setup_partitions(void)
 
 	kfree(pbuf);
 
+	/* Check if the host is already added as part of partition info */
+	if (xa_load(&drv_info->partition_info, drv_info->vm_id))
+		return 0;
+
 	/* Allocate for the host */
 	info = kzalloc(sizeof(*info), GFP_KERNEL);
 	if (!info) {
@@ -1705,7 +1721,7 @@ static void ffa_notifications_setup(void)
 		goto cleanup;
 
 	hash_init(drv_info->notifier_hash);
-	mutex_init(&drv_info->notify_lock);
+	rwlock_init(&drv_info->notify_lock);
 
 	drv_info->notif_enabled = true;
 	return;
@@ -1799,7 +1815,7 @@ free_drv_info:
 	kfree(drv_info);
 	return ret;
 }
-module_init(ffa_init);
+rootfs_initcall(ffa_init);
 
 static void __exit ffa_exit(void)
 {
diff --git a/drivers/firmware/arm_scmi/bus.c b/drivers/firmware/arm_scmi/bus.c
index 157172a5f2b5..73a6ab4a224d 100644
--- a/drivers/firmware/arm_scmi/bus.c
+++ b/drivers/firmware/arm_scmi/bus.c
@@ -42,7 +42,7 @@ static atomic_t scmi_syspower_registered = ATOMIC_INIT(0);
  * This helper let an SCMI driver request specific devices identified by the
  * @id_table to be created for each active SCMI instance.
  *
- * The requested device name MUST NOT be already existent for any protocol;
+ * The requested device name MUST NOT be already existent for this protocol;
  * at first the freshly requested @id_table is annotated in the IDR table
  * @scmi_requested_devices and then the requested device is advertised to any
  * registered party via the @scmi_requested_devices_nh notification chain.
@@ -52,7 +52,6 @@ static atomic_t scmi_syspower_registered = ATOMIC_INIT(0);
 static int scmi_protocol_device_request(const struct scmi_device_id *id_table)
 {
 	int ret = 0;
-	unsigned int id = 0;
 	struct list_head *head, *phead = NULL;
 	struct scmi_requested_dev *rdev;
 
@@ -67,19 +66,13 @@ static int scmi_protocol_device_request(const struct scmi_device_id *id_table)
 	}
 
 	/*
-	 * Search for the matching protocol rdev list and then search
-	 * of any existent equally named device...fails if any duplicate found.
+	 * Find the matching protocol rdev list and then search of any
+	 * existent equally named device...fails if any duplicate found.
 	 */
 	mutex_lock(&scmi_requested_devices_mtx);
-	idr_for_each_entry(&scmi_requested_devices, head, id) {
-		if (!phead) {
-			/* A list found registered in the IDR is never empty */
-			rdev = list_first_entry(head, struct scmi_requested_dev,
-						node);
-			if (rdev->id_table->protocol_id ==
-			    id_table->protocol_id)
-				phead = head;
-		}
+	phead = idr_find(&scmi_requested_devices, id_table->protocol_id);
+	if (phead) {
+		head = phead;
 		list_for_each_entry(rdev, head, node) {
 			if (!strcmp(rdev->id_table->name, id_table->name)) {
 				pr_err("Ignoring duplicate request [%d] %s\n",
@@ -260,6 +253,9 @@ static struct scmi_device *scmi_child_dev_find(struct device *parent,
 	if (!dev)
 		return NULL;
 
+	/* Drop the refcnt bumped implicitly by device_find_child */
+	put_device(dev);
+
 	return to_scmi_dev(dev);
 }
 
diff --git a/drivers/firmware/arm_scmi/driver.c b/drivers/firmware/arm_scmi/driver.c
index f8934d049d68..f1abe605865a 100644
--- a/drivers/firmware/arm_scmi/driver.c
+++ b/drivers/firmware/arm_scmi/driver.c
@@ -1219,7 +1219,8 @@ static void xfer_put(const struct scmi_protocol_handle *ph,
 }
 
 static bool scmi_xfer_done_no_timeout(struct scmi_chan_info *cinfo,
-				      struct scmi_xfer *xfer, ktime_t stop)
+				      struct scmi_xfer *xfer, ktime_t stop,
+				      bool *ooo)
 {
 	struct scmi_info *info = handle_to_scmi_info(cinfo->handle);
 
@@ -1228,7 +1229,7 @@ static bool scmi_xfer_done_no_timeout(struct scmi_chan_info *cinfo,
 	 * in case of out-of-order receptions of delayed responses
 	 */
 	return info->desc->ops->poll_done(cinfo, xfer) ||
-	       try_wait_for_completion(&xfer->done) ||
+	       (*ooo = try_wait_for_completion(&xfer->done)) ||
 	       ktime_after(ktime_get(), stop);
 }
 
@@ -1245,15 +1246,17 @@ static int scmi_wait_for_reply(struct device *dev, const struct scmi_desc *desc,
 		 * itself to support synchronous commands replies.
 		 */
 		if (!desc->sync_cmds_completed_on_ret) {
+			bool ooo = false;
+
 			/*
 			 * Poll on xfer using transport provided .poll_done();
 			 * assumes no completion interrupt was available.
 			 */
 			ktime_t stop = ktime_add_ms(ktime_get(), timeout_ms);
 
-			spin_until_cond(scmi_xfer_done_no_timeout(cinfo,
-								  xfer, stop));
-			if (ktime_after(ktime_get(), stop)) {
+			spin_until_cond(scmi_xfer_done_no_timeout(cinfo, xfer,
+								  stop, &ooo));
+			if (!ooo && !info->desc->ops->poll_done(cinfo, xfer)) {
 				dev_err(dev,
 					"timed out in resp(caller: %pS) - polling\n",
 					(void *)_RET_IP_);
@@ -1706,6 +1709,39 @@ static int scmi_common_get_max_msg_size(const struct scmi_protocol_handle *ph)
 }
 
 /**
+ * scmi_protocol_msg_check  - Check protocol message attributes
+ *
+ * @ph: A reference to the protocol handle.
+ * @message_id: The ID of the message to check.
+ * @attributes: A parameter to optionally return the retrieved message
+ *		attributes, in case of Success.
+ *
+ * An helper to check protocol message attributes for a specific protocol
+ * and message pair.
+ *
+ * Return: 0 on SUCCESS
+ */
+static int scmi_protocol_msg_check(const struct scmi_protocol_handle *ph,
+				   u32 message_id, u32 *attributes)
+{
+	int ret;
+	struct scmi_xfer *t;
+
+	ret = xfer_get_init(ph, PROTOCOL_MESSAGE_ATTRIBUTES,
+			    sizeof(__le32), 0, &t);
+	if (ret)
+		return ret;
+
+	put_unaligned_le32(message_id, t->tx.buf);
+	ret = do_xfer(ph, t);
+	if (!ret && attributes)
+		*attributes = get_unaligned_le32(t->rx.buf);
+	xfer_put(ph, t);
+
+	return ret;
+}
+
+/**
  * struct scmi_iterator  - Iterator descriptor
  * @msg: A reference to the message TX buffer; filled by @prepare_message with
  *	 a proper custom command payload for each multi-part command request.
@@ -1846,6 +1882,7 @@ scmi_common_fastchannel_init(const struct scmi_protocol_handle *ph,
 	int ret;
 	u32 flags;
 	u64 phys_addr;
+	u32 attributes;
 	u8 size;
 	void __iomem *addr;
 	struct scmi_xfer *t;
@@ -1854,6 +1891,15 @@ scmi_common_fastchannel_init(const struct scmi_protocol_handle *ph,
 	struct scmi_msg_resp_desc_fc *resp;
 	const struct scmi_protocol_instance *pi = ph_to_pi(ph);
 
+	/* Check if the MSG_ID supports fastchannel */
+	ret = scmi_protocol_msg_check(ph, message_id, &attributes);
+	if (ret || !MSG_SUPPORTS_FASTCHANNEL(attributes)) {
+		dev_dbg(ph->dev,
+			"Skip FC init for 0x%02X/%d  domain:%d - ret:%d\n",
+			pi->proto->id, message_id, domain, ret);
+		return;
+	}
+
 	if (!p_addr) {
 		ret = -EINVAL;
 		goto err_out;
@@ -1981,39 +2027,6 @@ static void scmi_common_fastchannel_db_ring(struct scmi_fc_db_info *db)
 #endif
 }
 
-/**
- * scmi_protocol_msg_check  - Check protocol message attributes
- *
- * @ph: A reference to the protocol handle.
- * @message_id: The ID of the message to check.
- * @attributes: A parameter to optionally return the retrieved message
- *		attributes, in case of Success.
- *
- * An helper to check protocol message attributes for a specific protocol
- * and message pair.
- *
- * Return: 0 on SUCCESS
- */
-static int scmi_protocol_msg_check(const struct scmi_protocol_handle *ph,
-				   u32 message_id, u32 *attributes)
-{
-	int ret;
-	struct scmi_xfer *t;
-
-	ret = xfer_get_init(ph, PROTOCOL_MESSAGE_ATTRIBUTES,
-			    sizeof(__le32), 0, &t);
-	if (ret)
-		return ret;
-
-	put_unaligned_le32(message_id, t->tx.buf);
-	ret = do_xfer(ph, t);
-	if (!ret && attributes)
-		*attributes = get_unaligned_le32(t->rx.buf);
-	xfer_put(ph, t);
-
-	return ret;
-}
-
 static const struct scmi_proto_helpers_ops helpers_ops = {
 	.extended_name_get = scmi_common_extended_name_get,
 	.get_max_msg_size = scmi_common_get_max_msg_size,
diff --git a/drivers/firmware/arm_scmi/perf.c b/drivers/firmware/arm_scmi/perf.c
index c7e5a34b254b..683fd9b85c5c 100644
--- a/drivers/firmware/arm_scmi/perf.c
+++ b/drivers/firmware/arm_scmi/perf.c
@@ -892,7 +892,7 @@ static int scmi_dvfs_device_opps_add(const struct scmi_protocol_handle *ph,
 			freq = dom->opp[idx].indicative_freq * dom->mult_factor;
 
 		/* All OPPs above the sustained frequency are treated as turbo */
-		data.turbo = freq > dom->sustained_freq_khz * 1000;
+		data.turbo = freq > dom->sustained_freq_khz * 1000UL;
 
 		data.level = dom->opp[idx].perf;
 		data.freq = freq;
diff --git a/drivers/firmware/arm_scmi/protocols.h b/drivers/firmware/arm_scmi/protocols.h
index aaee57cdcd55..d62c4469d1fd 100644
--- a/drivers/firmware/arm_scmi/protocols.h
+++ b/drivers/firmware/arm_scmi/protocols.h
@@ -31,6 +31,8 @@
 
 #define SCMI_PROTOCOL_VENDOR_BASE	0x80
 
+#define MSG_SUPPORTS_FASTCHANNEL(x)	((x) & BIT(0))
+
 enum scmi_common_cmd {
 	PROTOCOL_VERSION = 0x0,
 	PROTOCOL_ATTRIBUTES = 0x1,
diff --git a/drivers/firmware/arm_scmi/scmi_power_control.c b/drivers/firmware/arm_scmi/scmi_power_control.c
index 21f467a92942..955736336061 100644
--- a/drivers/firmware/arm_scmi/scmi_power_control.c
+++ b/drivers/firmware/arm_scmi/scmi_power_control.c
@@ -46,6 +46,7 @@
 #include <linux/math.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
+#include <linux/pm.h>
 #include <linux/printk.h>
 #include <linux/reboot.h>
 #include <linux/scmi_protocol.h>
@@ -324,12 +325,7 @@ static int scmi_userspace_notifier(struct notifier_block *nb,
 
 static void scmi_suspend_work_func(struct work_struct *work)
 {
-	struct scmi_syspower_conf *sc =
-		container_of(work, struct scmi_syspower_conf, suspend_work);
-
 	pm_suspend(PM_SUSPEND_MEM);
-
-	sc->state = SCMI_SYSPOWER_IDLE;
 }
 
 static int scmi_syspower_probe(struct scmi_device *sdev)
@@ -354,6 +350,7 @@ static int scmi_syspower_probe(struct scmi_device *sdev)
 	sc->required_transition = SCMI_SYSTEM_MAX;
 	sc->userspace_nb.notifier_call = &scmi_userspace_notifier;
 	sc->dev = &sdev->dev;
+	dev_set_drvdata(&sdev->dev, sc);
 
 	INIT_WORK(&sc->suspend_work, scmi_suspend_work_func);
 
@@ -363,6 +360,18 @@ static int scmi_syspower_probe(struct scmi_device *sdev)
 						       NULL, &sc->userspace_nb);
 }
 
+static int scmi_system_power_resume(struct device *dev)
+{
+	struct scmi_syspower_conf *sc = dev_get_drvdata(dev);
+
+	sc->state = SCMI_SYSPOWER_IDLE;
+	return 0;
+}
+
+static const struct dev_pm_ops scmi_system_power_pmops = {
+	SYSTEM_SLEEP_PM_OPS(NULL, scmi_system_power_resume)
+};
+
 static const struct scmi_device_id scmi_id_table[] = {
 	{ SCMI_PROTOCOL_SYSTEM, "syspower" },
 	{ },
@@ -370,6 +379,9 @@ static const struct scmi_device_id scmi_id_table[] = {
 MODULE_DEVICE_TABLE(scmi, scmi_id_table);
 
 static struct scmi_driver scmi_system_power_driver = {
+	.driver	= {
+		.pm = pm_sleep_ptr(&scmi_system_power_pmops),
+	},
 	.name = "scmi-system-power",
 	.probe = scmi_syspower_probe,
 	.id_table = scmi_id_table,
diff --git a/drivers/firmware/arm_scmi/vendors/imx/imx-sm-misc.c b/drivers/firmware/arm_scmi/vendors/imx/imx-sm-misc.c
index a86ab9b35953..2641faa329cd 100644
--- a/drivers/firmware/arm_scmi/vendors/imx/imx-sm-misc.c
+++ b/drivers/firmware/arm_scmi/vendors/imx/imx-sm-misc.c
@@ -254,8 +254,8 @@ static int scmi_imx_misc_ctrl_set(const struct scmi_protocol_handle *ph,
 	if (num > max_num)
 		return -EINVAL;
 
-	ret = ph->xops->xfer_get_init(ph, SCMI_IMX_MISC_CTRL_SET, sizeof(*in),
-				      0, &t);
+	ret = ph->xops->xfer_get_init(ph, SCMI_IMX_MISC_CTRL_SET,
+				      sizeof(*in) + num * sizeof(__le32), 0, &t);
 	if (ret)
 		return ret;
 
diff --git a/drivers/firmware/arm_sdei.c b/drivers/firmware/arm_sdei.c
index 3e8051fe8296..71e2a9a89f6a 100644
--- a/drivers/firmware/arm_sdei.c
+++ b/drivers/firmware/arm_sdei.c
@@ -1062,13 +1062,12 @@ static bool __init sdei_present_acpi(void)
 	return true;
 }
 
-void __init sdei_init(void)
+void __init acpi_sdei_init(void)
 {
 	struct platform_device *pdev;
 	int ret;
 
-	ret = platform_driver_register(&sdei_driver);
-	if (ret || !sdei_present_acpi())
+	if (!sdei_present_acpi())
 		return;
 
 	pdev = platform_device_register_simple(sdei_driver.driver.name,
@@ -1081,6 +1080,12 @@ void __init sdei_init(void)
 	}
 }
 
+static int __init sdei_init(void)
+{
+	return platform_driver_register(&sdei_driver);
+}
+arch_initcall(sdei_init);
+
 int sdei_event_handler(struct pt_regs *regs,
 		       struct sdei_registered_event *arg)
 {
diff --git a/drivers/firmware/cirrus/cs_dsp.c b/drivers/firmware/cirrus/cs_dsp.c
index 419220fa42fd..ea452f190854 100644
--- a/drivers/firmware/cirrus/cs_dsp.c
+++ b/drivers/firmware/cirrus/cs_dsp.c
@@ -1609,8 +1609,8 @@ static int cs_dsp_load(struct cs_dsp *dsp, const struct firmware *firmware,
 				goto out_fw;
 			}
 
-			ret = regmap_raw_write_async(regmap, reg, buf->buf,
-						     le32_to_cpu(region->len));
+			ret = regmap_raw_write(regmap, reg, buf->buf,
+					       le32_to_cpu(region->len));
 			if (ret != 0) {
 				cs_dsp_err(dsp,
 					   "%s.%d: Failed to write %d bytes at %d in %s: %d\n",
@@ -1625,20 +1625,14 @@ static int cs_dsp_load(struct cs_dsp *dsp, const struct firmware *firmware,
 		regions++;
 	}
 
-	ret = regmap_async_complete(regmap);
-	if (ret != 0) {
-		cs_dsp_err(dsp, "Failed to complete async write: %d\n", ret);
-		goto out_fw;
-	}
-
 	if (pos > firmware->size)
 		cs_dsp_warn(dsp, "%s.%d: %zu bytes at end of file\n",
 			    file, regions, pos - firmware->size);
 
 	cs_dsp_debugfs_save_wmfwname(dsp, file);
 
+	ret = 0;
 out_fw:
-	regmap_async_complete(regmap);
 	cs_dsp_buf_free(&buf_list);
 
 	if (ret == -EOVERFLOW)
@@ -2326,8 +2320,8 @@ static int cs_dsp_load_coeff(struct cs_dsp *dsp, const struct firmware *firmware
 			cs_dsp_dbg(dsp, "%s.%d: Writing %d bytes at %x\n",
 				   file, blocks, le32_to_cpu(blk->len),
 				   reg);
-			ret = regmap_raw_write_async(regmap, reg, buf->buf,
-						     le32_to_cpu(blk->len));
+			ret = regmap_raw_write(regmap, reg, buf->buf,
+					       le32_to_cpu(blk->len));
 			if (ret != 0) {
 				cs_dsp_err(dsp,
 					   "%s.%d: Failed to write to %x in %s: %d\n",
@@ -2339,18 +2333,14 @@ static int cs_dsp_load_coeff(struct cs_dsp *dsp, const struct firmware *firmware
 		blocks++;
 	}
 
-	ret = regmap_async_complete(regmap);
-	if (ret != 0)
-		cs_dsp_err(dsp, "Failed to complete async write: %d\n", ret);
-
 	if (pos > firmware->size)
 		cs_dsp_warn(dsp, "%s.%d: %zu bytes at end of file\n",
 			    file, blocks, pos - firmware->size);
 
 	cs_dsp_debugfs_save_binname(dsp, file);
 
+	ret = 0;
 out_fw:
-	regmap_async_complete(regmap);
 	cs_dsp_buf_free(&buf_list);
 
 	if (ret == -EOVERFLOW)
@@ -2561,8 +2551,8 @@ static int cs_dsp_adsp2_enable_core(struct cs_dsp *dsp)
 {
 	int ret;
 
-	ret = regmap_update_bits_async(dsp->regmap, dsp->base + ADSP2_CONTROL,
-				       ADSP2_SYS_ENA, ADSP2_SYS_ENA);
+	ret = regmap_update_bits(dsp->regmap, dsp->base + ADSP2_CONTROL,
+				 ADSP2_SYS_ENA, ADSP2_SYS_ENA);
 	if (ret != 0)
 		return ret;
 
diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index 70490bf2697b..acabc856fe8a 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -922,13 +922,15 @@ char * __init efi_md_typeattr_format(char *buf, size_t size,
 		     EFI_MEMORY_WB | EFI_MEMORY_UCE | EFI_MEMORY_RO |
 		     EFI_MEMORY_WP | EFI_MEMORY_RP | EFI_MEMORY_XP |
 		     EFI_MEMORY_NV | EFI_MEMORY_SP | EFI_MEMORY_CPU_CRYPTO |
-		     EFI_MEMORY_RUNTIME | EFI_MEMORY_MORE_RELIABLE))
+		     EFI_MEMORY_MORE_RELIABLE | EFI_MEMORY_HOT_PLUGGABLE |
+		     EFI_MEMORY_RUNTIME))
 		snprintf(pos, size, "|attr=0x%016llx]",
 			 (unsigned long long)attr);
 	else
 		snprintf(pos, size,
-			 "|%3s|%2s|%2s|%2s|%2s|%2s|%2s|%2s|%2s|%3s|%2s|%2s|%2s|%2s]",
+			 "|%3s|%2s|%2s|%2s|%2s|%2s|%2s|%2s|%2s|%2s|%3s|%2s|%2s|%2s|%2s]",
 			 attr & EFI_MEMORY_RUNTIME		? "RUN" : "",
+			 attr & EFI_MEMORY_HOT_PLUGGABLE	? "HP"  : "",
 			 attr & EFI_MEMORY_MORE_RELIABLE	? "MR"  : "",
 			 attr & EFI_MEMORY_CPU_CRYPTO   	? "CC"  : "",
 			 attr & EFI_MEMORY_SP			? "SP"  : "",
diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile
index ed4e8ddbe76a..1141cd06011f 100644
--- a/drivers/firmware/efi/libstub/Makefile
+++ b/drivers/firmware/efi/libstub/Makefile
@@ -11,7 +11,7 @@ cflags-y			:= $(KBUILD_CFLAGS)
 
 cflags-$(CONFIG_X86_32)		:= -march=i386
 cflags-$(CONFIG_X86_64)		:= -mcmodel=small
-cflags-$(CONFIG_X86)		+= -m$(BITS) -D__KERNEL__ \
+cflags-$(CONFIG_X86)		+= -m$(BITS) -D__KERNEL__ -std=gnu11 \
 				   -fPIC -fno-strict-aliasing -mno-red-zone \
 				   -mno-mmx -mno-sse -fshort-wchar \
 				   -Wno-pointer-sign \
diff --git a/drivers/firmware/efi/libstub/efi-stub-helper.c b/drivers/firmware/efi/libstub/efi-stub-helper.c
index de659f6a815f..1ad414da9920 100644
--- a/drivers/firmware/efi/libstub/efi-stub-helper.c
+++ b/drivers/firmware/efi/libstub/efi-stub-helper.c
@@ -603,6 +603,7 @@ efi_status_t efi_load_initrd_cmdline(efi_loaded_image_t *image,
  * @image:	EFI loaded image protocol
  * @soft_limit:	preferred address for loading the initrd
  * @hard_limit:	upper limit address for loading the initrd
+ * @out:	pointer to store the address of the initrd table
  *
  * Return:	status code
  */
diff --git a/drivers/firmware/efi/libstub/efistub.h b/drivers/firmware/efi/libstub/efistub.h
index 685098f9626f..eebcdf653d07 100644
--- a/drivers/firmware/efi/libstub/efistub.h
+++ b/drivers/firmware/efi/libstub/efistub.h
@@ -171,7 +171,7 @@ void efi_set_u64_split(u64 data, u32 *lo, u32 *hi)
  * the EFI memory map. Other related structures, e.g. x86 e820ext, need
  * to factor in this headroom requirement as well.
  */
-#define EFI_MMAP_NR_SLACK_SLOTS	8
+#define EFI_MMAP_NR_SLACK_SLOTS	32
 
 typedef struct efi_generic_dev_path efi_device_path_protocol_t;
 
diff --git a/drivers/firmware/efi/libstub/randomalloc.c b/drivers/firmware/efi/libstub/randomalloc.c
index c41e7b2091cd..593e98e3b993 100644
--- a/drivers/firmware/efi/libstub/randomalloc.c
+++ b/drivers/firmware/efi/libstub/randomalloc.c
@@ -25,6 +25,9 @@ static unsigned long get_entry_num_slots(efi_memory_desc_t *md,
 	if (md->type != EFI_CONVENTIONAL_MEMORY)
 		return 0;
 
+	if (md->attribute & EFI_MEMORY_HOT_PLUGGABLE)
+		return 0;
+
 	if (efi_soft_reserve_enabled() &&
 	    (md->attribute & EFI_MEMORY_SP))
 		return 0;
@@ -72,6 +75,10 @@ efi_status_t efi_random_alloc(unsigned long size,
 	if (align < EFI_ALLOC_ALIGN)
 		align = EFI_ALLOC_ALIGN;
 
+	/* Avoid address 0x0, as it can be mistaken for NULL */
+	if (alloc_min == 0)
+		alloc_min = align;
+
 	size = round_up(size, EFI_ALLOC_ALIGN);
 
 	/* count the suitable slots in each memory map entry */
diff --git a/drivers/firmware/efi/libstub/relocate.c b/drivers/firmware/efi/libstub/relocate.c
index d694bcfa1074..bf676dd127a1 100644
--- a/drivers/firmware/efi/libstub/relocate.c
+++ b/drivers/firmware/efi/libstub/relocate.c
@@ -53,6 +53,9 @@ efi_status_t efi_low_alloc_above(unsigned long size, unsigned long align,
 		if (desc->type != EFI_CONVENTIONAL_MEMORY)
 			continue;
 
+		if (desc->attribute & EFI_MEMORY_HOT_PLUGGABLE)
+			continue;
+
 		if (efi_soft_reserve_enabled() &&
 		    (desc->attribute & EFI_MEMORY_SP))
 			continue;
diff --git a/drivers/firmware/efi/mokvar-table.c b/drivers/firmware/efi/mokvar-table.c
index 5ed0602c2f75..4eb0dff4dfaf 100644
--- a/drivers/firmware/efi/mokvar-table.c
+++ b/drivers/firmware/efi/mokvar-table.c
@@ -103,9 +103,7 @@ void __init efi_mokvar_table_init(void)
 	void *va = NULL;
 	unsigned long cur_offset = 0;
 	unsigned long offset_limit;
-	unsigned long map_size = 0;
 	unsigned long map_size_needed = 0;
-	unsigned long size;
 	struct efi_mokvar_table_entry *mokvar_entry;
 	int err;
 
@@ -134,48 +132,34 @@ void __init efi_mokvar_table_init(void)
 	 */
 	err = -EINVAL;
 	while (cur_offset + sizeof(*mokvar_entry) <= offset_limit) {
-		mokvar_entry = va + cur_offset;
-		map_size_needed = cur_offset + sizeof(*mokvar_entry);
-		if (map_size_needed > map_size) {
-			if (va)
-				early_memunmap(va, map_size);
-			/*
-			 * Map a little more than the fixed size entry
-			 * header, anticipating some data. It's safe to
-			 * do so as long as we stay within current memory
-			 * descriptor.
-			 */
-			map_size = min(map_size_needed + 2*EFI_PAGE_SIZE,
-				       offset_limit);
-			va = early_memremap(efi.mokvar_table, map_size);
-			if (!va) {
-				pr_err("Failed to map EFI MOKvar config table pa=0x%lx, size=%lu.\n",
-				       efi.mokvar_table, map_size);
-				return;
-			}
-			mokvar_entry = va + cur_offset;
+		if (va)
+			early_memunmap(va, sizeof(*mokvar_entry));
+		va = early_memremap(efi.mokvar_table + cur_offset, sizeof(*mokvar_entry));
+		if (!va) {
+			pr_err("Failed to map EFI MOKvar config table pa=0x%lx, size=%zu.\n",
+			       efi.mokvar_table + cur_offset, sizeof(*mokvar_entry));
+			return;
 		}
+		mokvar_entry = va;
 
 		/* Check for last sentinel entry */
 		if (mokvar_entry->name[0] == '\0') {
 			if (mokvar_entry->data_size != 0)
 				break;
 			err = 0;
+			map_size_needed = cur_offset + sizeof(*mokvar_entry);
 			break;
 		}
 
-		/* Sanity check that the name is null terminated */
-		size = strnlen(mokvar_entry->name,
-			       sizeof(mokvar_entry->name));
-		if (size >= sizeof(mokvar_entry->name))
-			break;
+		/* Enforce that the name is NUL terminated */
+		mokvar_entry->name[sizeof(mokvar_entry->name) - 1] = '\0';
 
 		/* Advance to the next entry */
-		cur_offset = map_size_needed + mokvar_entry->data_size;
+		cur_offset += sizeof(*mokvar_entry) + mokvar_entry->data_size;
 	}
 
 	if (va)
-		early_memunmap(va, map_size);
+		early_memunmap(va, sizeof(*mokvar_entry));
 	if (err) {
 		pr_err("EFI MOKvar config table is not valid\n");
 		return;
diff --git a/drivers/firmware/efi/sysfb_efi.c b/drivers/firmware/efi/sysfb_efi.c
index cc807ed35aed..1e509595ac03 100644
--- a/drivers/firmware/efi/sysfb_efi.c
+++ b/drivers/firmware/efi/sysfb_efi.c
@@ -91,6 +91,7 @@ void efifb_setup_from_dmi(struct screen_info *si, const char *opt)
 		_ret_;						\
 	})
 
+#ifdef CONFIG_EFI
 static int __init efifb_set_system(const struct dmi_system_id *id)
 {
 	struct efifb_dmi_info *info = id->driver_data;
@@ -346,7 +347,6 @@ static const struct fwnode_operations efifb_fwnode_ops = {
 	.add_links = efifb_add_links,
 };
 
-#ifdef CONFIG_EFI
 static struct fwnode_handle efifb_fwnode;
 
 __init void sysfb_apply_efi_quirks(void)
diff --git a/drivers/firmware/imx/Kconfig b/drivers/firmware/imx/Kconfig
index 907cd149c40a..c964f4924359 100644
--- a/drivers/firmware/imx/Kconfig
+++ b/drivers/firmware/imx/Kconfig
@@ -25,6 +25,7 @@ config IMX_SCU
 
 config IMX_SCMI_MISC_DRV
 	tristate "IMX SCMI MISC Protocol driver"
+	depends on ARCH_MXC || COMPILE_TEST
 	default y if ARCH_MXC
 	help
 	  The System Controller Management Interface firmware (SCMI FW) is
diff --git a/drivers/firmware/imx/imx-scu.c b/drivers/firmware/imx/imx-scu.c
index 1dd4362ef9a3..8c28e25ddc8a 100644
--- a/drivers/firmware/imx/imx-scu.c
+++ b/drivers/firmware/imx/imx-scu.c
@@ -280,6 +280,7 @@ static int imx_scu_probe(struct platform_device *pdev)
 		return ret;
 
 	sc_ipc->fast_ipc = of_device_is_compatible(args.np, "fsl,imx8-mu-scu");
+	of_node_put(args.np);
 
 	num_channel = sc_ipc->fast_ipc ? 2 : SCU_MU_CHAN_NUM;
 	for (i = 0; i < num_channel; i++) {
diff --git a/drivers/firmware/iscsi_ibft.c b/drivers/firmware/iscsi_ibft.c
index 6e9788324fea..371f24569b3b 100644
--- a/drivers/firmware/iscsi_ibft.c
+++ b/drivers/firmware/iscsi_ibft.c
@@ -310,7 +310,10 @@ static ssize_t ibft_attr_show_nic(void *data, int type, char *buf)
 		str += sprintf_ipaddr(str, nic->ip_addr);
 		break;
 	case ISCSI_BOOT_ETH_SUBNET_MASK:
-		val = cpu_to_be32(~((1 << (32-nic->subnet_mask_prefix))-1));
+		if (nic->subnet_mask_prefix > 32)
+			val = cpu_to_be32(~0);
+		else
+			val = cpu_to_be32(~((1 << (32-nic->subnet_mask_prefix))-1));
 		str += sprintf(str, "%pI4", &val);
 		break;
 	case ISCSI_BOOT_ETH_PREFIX_LEN:
diff --git a/drivers/firmware/psci/psci.c b/drivers/firmware/psci/psci.c
index 2328ca58bba6..d6701d81cf68 100644
--- a/drivers/firmware/psci/psci.c
+++ b/drivers/firmware/psci/psci.c
@@ -759,8 +759,10 @@ int __init psci_dt_init(void)
 
 	np = of_find_matching_node_and_match(NULL, psci_of_match, &matched_np);
 
-	if (!np || !of_device_is_available(np))
+	if (!np || !of_device_is_available(np)) {
+		of_node_put(np);
 		return -ENODEV;
+	}
 
 	init_fn = (psci_initcall_t)matched_np->data;
 	ret = init_fn(np);
diff --git a/drivers/firmware/qcom/qcom_qseecom_uefisecapp.c b/drivers/firmware/qcom/qcom_qseecom_uefisecapp.c
index 447246bd04be..98a463e9774b 100644
--- a/drivers/firmware/qcom/qcom_qseecom_uefisecapp.c
+++ b/drivers/firmware/qcom/qcom_qseecom_uefisecapp.c
@@ -814,15 +814,6 @@ static int qcom_uefisecapp_probe(struct auxiliary_device *aux_dev,
 
 	qcuefi->client = container_of(aux_dev, struct qseecom_client, aux_dev);
 
-	auxiliary_set_drvdata(aux_dev, qcuefi);
-	status = qcuefi_set_reference(qcuefi);
-	if (status)
-		return status;
-
-	status = efivars_register(&qcuefi->efivars, &qcom_efivar_ops);
-	if (status)
-		qcuefi_set_reference(NULL);
-
 	memset(&pool_config, 0, sizeof(pool_config));
 	pool_config.initial_size = SZ_4K;
 	pool_config.policy = QCOM_TZMEM_POLICY_MULTIPLIER;
@@ -833,6 +824,15 @@ static int qcom_uefisecapp_probe(struct auxiliary_device *aux_dev,
 	if (IS_ERR(qcuefi->mempool))
 		return PTR_ERR(qcuefi->mempool);
 
+	auxiliary_set_drvdata(aux_dev, qcuefi);
+	status = qcuefi_set_reference(qcuefi);
+	if (status)
+		return status;
+
+	status = efivars_register(&qcuefi->efivars, &qcom_efivar_ops);
+	if (status)
+		qcuefi_set_reference(NULL);
+
 	return status;
 }
 
diff --git a/drivers/firmware/qcom/qcom_scm-smc.c b/drivers/firmware/qcom/qcom_scm-smc.c
index 2b4c2826f572..3f10b23ec941 100644
--- a/drivers/firmware/qcom/qcom_scm-smc.c
+++ b/drivers/firmware/qcom/qcom_scm-smc.c
@@ -173,6 +173,9 @@ int __scm_smc_call(struct device *dev, const struct qcom_scm_desc *desc,
 		smc.args[i + SCM_SMC_FIRST_REG_IDX] = desc->args[i];
 
 	if (unlikely(arglen > SCM_SMC_N_REG_ARGS)) {
+		if (!mempool)
+			return -EINVAL;
+
 		args_virt = qcom_tzmem_alloc(mempool,
 					     SCM_SMC_N_EXT_ARGS * sizeof(u64),
 					     flag);
diff --git a/drivers/firmware/qcom/qcom_scm.c b/drivers/firmware/qcom/qcom_scm.c
index 14afd68664a9..23aefbf6fca5 100644
--- a/drivers/firmware/qcom/qcom_scm.c
+++ b/drivers/firmware/qcom/qcom_scm.c
@@ -217,7 +217,10 @@ static DEFINE_SPINLOCK(scm_query_lock);
 
 struct qcom_tzmem_pool *qcom_scm_get_tzmem_pool(void)
 {
-	return __scm ? __scm->mempool : NULL;
+	if (!qcom_scm_is_available())
+		return NULL;
+
+	return __scm->mempool;
 }
 
 static enum qcom_scm_convention __get_convention(void)
@@ -1839,7 +1842,8 @@ static int qcom_scm_qseecom_init(struct qcom_scm *scm)
  */
 bool qcom_scm_is_available(void)
 {
-	return !!READ_ONCE(__scm);
+	/* Paired with smp_store_release() in qcom_scm_probe */
+	return !!smp_load_acquire(&__scm);
 }
 EXPORT_SYMBOL_GPL(qcom_scm_is_available);
 
@@ -1996,18 +2000,22 @@ static int qcom_scm_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	/* Let all above stores be available after this */
+	/* Paired with smp_load_acquire() in qcom_scm_is_available(). */
 	smp_store_release(&__scm, scm);
 
 	irq = platform_get_irq_optional(pdev, 0);
 	if (irq < 0) {
-		if (irq != -ENXIO)
-			return irq;
+		if (irq != -ENXIO) {
+			ret = irq;
+			goto err;
+		}
 	} else {
 		ret = devm_request_threaded_irq(__scm->dev, irq, NULL, qcom_scm_irq_handler,
 						IRQF_ONESHOT, "qcom-scm", __scm);
-		if (ret < 0)
-			return dev_err_probe(scm->dev, ret, "Failed to request qcom-scm irq\n");
+		if (ret < 0) {
+			dev_err_probe(scm->dev, ret, "Failed to request qcom-scm irq\n");
+			goto err;
+		}
 	}
 
 	__get_convention();
@@ -2026,14 +2034,18 @@ static int qcom_scm_probe(struct platform_device *pdev)
 		qcom_scm_disable_sdi();
 
 	ret = of_reserved_mem_device_init(__scm->dev);
-	if (ret && ret != -ENODEV)
-		return dev_err_probe(__scm->dev, ret,
-				     "Failed to setup the reserved memory region for TZ mem\n");
+	if (ret && ret != -ENODEV) {
+		dev_err_probe(__scm->dev, ret,
+			      "Failed to setup the reserved memory region for TZ mem\n");
+		goto err;
+	}
 
 	ret = qcom_tzmem_enable(__scm->dev);
-	if (ret)
-		return dev_err_probe(__scm->dev, ret,
-				     "Failed to enable the TrustZone memory allocator\n");
+	if (ret) {
+		dev_err_probe(__scm->dev, ret,
+			      "Failed to enable the TrustZone memory allocator\n");
+		goto err;
+	}
 
 	memset(&pool_config, 0, sizeof(pool_config));
 	pool_config.initial_size = 0;
@@ -2041,9 +2053,11 @@ static int qcom_scm_probe(struct platform_device *pdev)
 	pool_config.max_size = SZ_256K;
 
 	__scm->mempool = devm_qcom_tzmem_pool_new(__scm->dev, &pool_config);
-	if (IS_ERR(__scm->mempool))
-		return dev_err_probe(__scm->dev, PTR_ERR(__scm->mempool),
-				     "Failed to create the SCM memory pool\n");
+	if (IS_ERR(__scm->mempool)) {
+		ret = dev_err_probe(__scm->dev, PTR_ERR(__scm->mempool),
+				    "Failed to create the SCM memory pool\n");
+		goto err;
+	}
 
 	/*
 	 * Initialize the QSEECOM interface.
@@ -2059,6 +2073,12 @@ static int qcom_scm_probe(struct platform_device *pdev)
 	WARN(ret < 0, "failed to initialize qseecom: %d\n", ret);
 
 	return 0;
+
+err:
+	/* Paired with smp_load_acquire() in qcom_scm_is_available(). */
+	smp_store_release(&__scm, NULL);
+
+	return ret;
 }
 
 static void qcom_scm_shutdown(struct platform_device *pdev)
diff --git a/drivers/firmware/stratix10-svc.c b/drivers/firmware/stratix10-svc.c
index 528f37417aea..f9429dd52fd9 100644
--- a/drivers/firmware/stratix10-svc.c
+++ b/drivers/firmware/stratix10-svc.c
@@ -1227,22 +1227,28 @@ static int stratix10_svc_drv_probe(struct platform_device *pdev)
 	if (!svc->intel_svc_fcs) {
 		dev_err(dev, "failed to allocate %s device\n", INTEL_FCS);
 		ret = -ENOMEM;
-		goto err_unregister_dev;
+		goto err_unregister_rsu_dev;
 	}
 
 	ret = platform_device_add(svc->intel_svc_fcs);
 	if (ret) {
 		platform_device_put(svc->intel_svc_fcs);
-		goto err_unregister_dev;
+		goto err_unregister_rsu_dev;
 	}
 
+	ret = of_platform_default_populate(dev_of_node(dev), NULL, dev);
+	if (ret)
+		goto err_unregister_fcs_dev;
+
 	dev_set_drvdata(dev, svc);
 
 	pr_info("Intel Service Layer Driver Initialized\n");
 
 	return 0;
 
-err_unregister_dev:
+err_unregister_fcs_dev:
+	platform_device_unregister(svc->intel_svc_fcs);
+err_unregister_rsu_dev:
 	platform_device_unregister(svc->stratix10_svc_rsu);
 err_free_kfifo:
 	kfifo_free(&controller->svc_fifo);
@@ -1256,6 +1262,8 @@ static void stratix10_svc_drv_remove(struct platform_device *pdev)
 	struct stratix10_svc *svc = dev_get_drvdata(&pdev->dev);
 	struct stratix10_svc_controller *ctrl = platform_get_drvdata(pdev);
 
+	of_platform_depopulate(ctrl->dev);
+
 	platform_device_unregister(svc->intel_svc_fcs);
 	platform_device_unregister(svc->stratix10_svc_rsu);
 
diff --git a/drivers/firmware/sysfb.c b/drivers/firmware/sysfb.c
index a3df782fa687..e919940c8bf9 100644
--- a/drivers/firmware/sysfb.c
+++ b/drivers/firmware/sysfb.c
@@ -124,6 +124,7 @@ static __init int sysfb_init(void)
 {
 	struct screen_info *si = &screen_info;
 	struct device *parent;
+	unsigned int type;
 	struct simplefb_platform_data mode;
 	const char *name;
 	bool compatible;
@@ -151,17 +152,26 @@ static __init int sysfb_init(void)
 			goto put_device;
 	}
 
+	type = screen_info_video_type(si);
+
 	/* if the FB is incompatible, create a legacy framebuffer device */
-	if (si->orig_video_isVGA == VIDEO_TYPE_EFI)
-		name = "efi-framebuffer";
-	else if (si->orig_video_isVGA == VIDEO_TYPE_VLFB)
-		name = "vesa-framebuffer";
-	else if (si->orig_video_isVGA == VIDEO_TYPE_VGAC)
-		name = "vga-framebuffer";
-	else if (si->orig_video_isVGA == VIDEO_TYPE_EGAC)
+	switch (type) {
+	case VIDEO_TYPE_EGAC:
 		name = "ega-framebuffer";
-	else
+		break;
+	case VIDEO_TYPE_VGAC:
+		name = "vga-framebuffer";
+		break;
+	case VIDEO_TYPE_VLFB:
+		name = "vesa-framebuffer";
+		break;
+	case VIDEO_TYPE_EFI:
+		name = "efi-framebuffer";
+		break;
+	default:
 		name = "platform-framebuffer";
+		break;
+	}
 
 	pd = platform_device_alloc(name, 0);
 	if (!pd) {
diff --git a/drivers/firmware/tegra/Kconfig b/drivers/firmware/tegra/Kconfig
index cde1ab8bd9d1..91f2320c0d0f 100644
--- a/drivers/firmware/tegra/Kconfig
+++ b/drivers/firmware/tegra/Kconfig
@@ -2,7 +2,7 @@
 menu "Tegra firmware driver"
 
 config TEGRA_IVC
-	bool "Tegra IVC protocol"
+	bool "Tegra IVC protocol" if COMPILE_TEST
 	depends on ARCH_TEGRA
 	help
 	  IVC (Inter-VM Communication) protocol is part of the IPC
@@ -13,8 +13,9 @@ config TEGRA_IVC
 
 config TEGRA_BPMP
 	bool "Tegra BPMP driver"
-	depends on ARCH_TEGRA && TEGRA_HSP_MBOX && TEGRA_IVC
+	depends on ARCH_TEGRA && TEGRA_HSP_MBOX
 	depends on !CPU_BIG_ENDIAN
+	select TEGRA_IVC
 	help
 	  BPMP (Boot and Power Management Processor) is designed to off-loading
 	  the PM functions which include clock/DVFS/thermal/power from the CPU.
diff --git a/drivers/firmware/xilinx/zynqmp.c b/drivers/firmware/xilinx/zynqmp.c
index add8acf66a9c..5578158f1375 100644
--- a/drivers/firmware/xilinx/zynqmp.c
+++ b/drivers/firmware/xilinx/zynqmp.c
@@ -1012,17 +1012,13 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_fpga_get_status);
 int zynqmp_pm_fpga_get_config_status(u32 *value)
 {
 	u32 ret_payload[PAYLOAD_ARG_CNT];
-	u32 buf, lower_addr, upper_addr;
 	int ret;
 
 	if (!value)
 		return -EINVAL;
 
-	lower_addr = lower_32_bits((u64)&buf);
-	upper_addr = upper_32_bits((u64)&buf);
-
 	ret = zynqmp_pm_invoke_fn(PM_FPGA_READ, ret_payload, 4,
-				  XILINX_ZYNQMP_PM_FPGA_CONFIG_STAT_OFFSET, lower_addr, upper_addr,
+				  XILINX_ZYNQMP_PM_FPGA_CONFIG_STAT_OFFSET, 0, 0,
 				  XILINX_ZYNQMP_PM_FPGA_READ_CONFIG_REG);
 
 	*value = ret_payload[1];
diff --git a/drivers/fpga/altera-cvp.c b/drivers/fpga/altera-cvp.c
index 6b0914432445..5af0bd33890c 100644
--- a/drivers/fpga/altera-cvp.c
+++ b/drivers/fpga/altera-cvp.c
@@ -52,7 +52,7 @@
 /* V2 Defines */
 #define VSE_CVP_TX_CREDITS		0x49	/* 8bit */
 
-#define V2_CREDIT_TIMEOUT_US		20000
+#define V2_CREDIT_TIMEOUT_US		40000
 #define V2_CHECK_CREDIT_US		10
 #define V2_POLL_TIMEOUT_US		1000000
 #define V2_USER_TIMEOUT_US		500000
diff --git a/drivers/fpga/tests/fpga-mgr-test.c b/drivers/fpga/tests/fpga-mgr-test.c
index 9cb37aefbac4..1902ebf5a298 100644
--- a/drivers/fpga/tests/fpga-mgr-test.c
+++ b/drivers/fpga/tests/fpga-mgr-test.c
@@ -263,6 +263,7 @@ static void fpga_mgr_test_img_load_sgt(struct kunit *test)
 	img_buf = init_test_buffer(test, IMAGE_SIZE);
 
 	sgt = kunit_kzalloc(test, sizeof(*sgt), GFP_KERNEL);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, sgt);
 	ret = sg_alloc_table(sgt, 1, GFP_KERNEL);
 	KUNIT_ASSERT_EQ(test, ret, 0);
 	sg_init_one(sgt->sgl, img_buf, IMAGE_SIZE);
diff --git a/drivers/gpio/gpio-aggregator.c b/drivers/gpio/gpio-aggregator.c
index 38e0fff9afe7..cc6ee4334602 100644
--- a/drivers/gpio/gpio-aggregator.c
+++ b/drivers/gpio/gpio-aggregator.c
@@ -121,10 +121,15 @@ static ssize_t new_device_store(struct device_driver *driver, const char *buf,
 	struct platform_device *pdev;
 	int res, id;
 
+	if (!try_module_get(THIS_MODULE))
+		return -ENOENT;
+
 	/* kernfs guarantees string termination, so count + 1 is safe */
 	aggr = kzalloc(sizeof(*aggr) + count + 1, GFP_KERNEL);
-	if (!aggr)
-		return -ENOMEM;
+	if (!aggr) {
+		res = -ENOMEM;
+		goto put_module;
+	}
 
 	memcpy(aggr->args, buf, count + 1);
 
@@ -163,6 +168,7 @@ static ssize_t new_device_store(struct device_driver *driver, const char *buf,
 	}
 
 	aggr->pdev = pdev;
+	module_put(THIS_MODULE);
 	return count;
 
 remove_table:
@@ -177,6 +183,8 @@ free_table:
 	kfree(aggr->lookups);
 free_ga:
 	kfree(aggr);
+put_module:
+	module_put(THIS_MODULE);
 	return res;
 }
 
@@ -205,13 +213,19 @@ static ssize_t delete_device_store(struct device_driver *driver,
 	if (error)
 		return error;
 
+	if (!try_module_get(THIS_MODULE))
+		return -ENOENT;
+
 	mutex_lock(&gpio_aggregator_lock);
 	aggr = idr_remove(&gpio_aggregator_idr, id);
 	mutex_unlock(&gpio_aggregator_lock);
-	if (!aggr)
+	if (!aggr) {
+		module_put(THIS_MODULE);
 		return -ENOENT;
+	}
 
 	gpio_aggregator_free(aggr);
+	module_put(THIS_MODULE);
 	return count;
 }
 static DRIVER_ATTR_WO(delete_device);
diff --git a/drivers/gpio/gpio-bcm-kona.c b/drivers/gpio/gpio-bcm-kona.c
index 5321ef98f442..64908f1a5e7f 100644
--- a/drivers/gpio/gpio-bcm-kona.c
+++ b/drivers/gpio/gpio-bcm-kona.c
@@ -69,6 +69,22 @@ struct bcm_kona_gpio {
 struct bcm_kona_gpio_bank {
 	int id;
 	int irq;
+	/*
+	 * Used to keep track of lock/unlock operations for each GPIO in the
+	 * bank.
+	 *
+	 * All GPIOs are locked by default (see bcm_kona_gpio_reset), and the
+	 * unlock count for all GPIOs is 0 by default. Each unlock increments
+	 * the counter, and each lock decrements the counter.
+	 *
+	 * The lock function only locks the GPIO once its unlock counter is
+	 * down to 0. This is necessary because the GPIO is unlocked in two
+	 * places in this driver: once for requested GPIOs, and once for
+	 * requested IRQs. Since it is possible for a GPIO to be requested
+	 * as both a GPIO and an IRQ, we need to ensure that we don't lock it
+	 * too early.
+	 */
+	u8 gpio_unlock_count[GPIO_PER_BANK];
 	/* Used in the interrupt handler */
 	struct bcm_kona_gpio *kona_gpio;
 };
@@ -86,14 +102,24 @@ static void bcm_kona_gpio_lock_gpio(struct bcm_kona_gpio *kona_gpio,
 	u32 val;
 	unsigned long flags;
 	int bank_id = GPIO_BANK(gpio);
+	int bit = GPIO_BIT(gpio);
+	struct bcm_kona_gpio_bank *bank = &kona_gpio->banks[bank_id];
 
-	raw_spin_lock_irqsave(&kona_gpio->lock, flags);
+	if (bank->gpio_unlock_count[bit] == 0) {
+		dev_err(kona_gpio->gpio_chip.parent,
+			"Unbalanced locks for GPIO %u\n", gpio);
+		return;
+	}
 
-	val = readl(kona_gpio->reg_base + GPIO_PWD_STATUS(bank_id));
-	val |= BIT(gpio);
-	bcm_kona_gpio_write_lock_regs(kona_gpio->reg_base, bank_id, val);
+	if (--bank->gpio_unlock_count[bit] == 0) {
+		raw_spin_lock_irqsave(&kona_gpio->lock, flags);
 
-	raw_spin_unlock_irqrestore(&kona_gpio->lock, flags);
+		val = readl(kona_gpio->reg_base + GPIO_PWD_STATUS(bank_id));
+		val |= BIT(bit);
+		bcm_kona_gpio_write_lock_regs(kona_gpio->reg_base, bank_id, val);
+
+		raw_spin_unlock_irqrestore(&kona_gpio->lock, flags);
+	}
 }
 
 static void bcm_kona_gpio_unlock_gpio(struct bcm_kona_gpio *kona_gpio,
@@ -102,14 +128,20 @@ static void bcm_kona_gpio_unlock_gpio(struct bcm_kona_gpio *kona_gpio,
 	u32 val;
 	unsigned long flags;
 	int bank_id = GPIO_BANK(gpio);
+	int bit = GPIO_BIT(gpio);
+	struct bcm_kona_gpio_bank *bank = &kona_gpio->banks[bank_id];
 
-	raw_spin_lock_irqsave(&kona_gpio->lock, flags);
+	if (bank->gpio_unlock_count[bit] == 0) {
+		raw_spin_lock_irqsave(&kona_gpio->lock, flags);
 
-	val = readl(kona_gpio->reg_base + GPIO_PWD_STATUS(bank_id));
-	val &= ~BIT(gpio);
-	bcm_kona_gpio_write_lock_regs(kona_gpio->reg_base, bank_id, val);
+		val = readl(kona_gpio->reg_base + GPIO_PWD_STATUS(bank_id));
+		val &= ~BIT(bit);
+		bcm_kona_gpio_write_lock_regs(kona_gpio->reg_base, bank_id, val);
 
-	raw_spin_unlock_irqrestore(&kona_gpio->lock, flags);
+		raw_spin_unlock_irqrestore(&kona_gpio->lock, flags);
+	}
+
+	++bank->gpio_unlock_count[bit];
 }
 
 static int bcm_kona_gpio_get_dir(struct gpio_chip *chip, unsigned gpio)
@@ -360,6 +392,7 @@ static void bcm_kona_gpio_irq_mask(struct irq_data *d)
 
 	kona_gpio = irq_data_get_irq_chip_data(d);
 	reg_base = kona_gpio->reg_base;
+
 	raw_spin_lock_irqsave(&kona_gpio->lock, flags);
 
 	val = readl(reg_base + GPIO_INT_MASK(bank_id));
@@ -382,6 +415,7 @@ static void bcm_kona_gpio_irq_unmask(struct irq_data *d)
 
 	kona_gpio = irq_data_get_irq_chip_data(d);
 	reg_base = kona_gpio->reg_base;
+
 	raw_spin_lock_irqsave(&kona_gpio->lock, flags);
 
 	val = readl(reg_base + GPIO_INT_MSKCLR(bank_id));
@@ -477,15 +511,26 @@ static void bcm_kona_gpio_irq_handler(struct irq_desc *desc)
 static int bcm_kona_gpio_irq_reqres(struct irq_data *d)
 {
 	struct bcm_kona_gpio *kona_gpio = irq_data_get_irq_chip_data(d);
+	unsigned int gpio = d->hwirq;
 
-	return gpiochip_reqres_irq(&kona_gpio->gpio_chip, d->hwirq);
+	/*
+	 * We need to unlock the GPIO before any other operations are performed
+	 * on the relevant GPIO configuration registers
+	 */
+	bcm_kona_gpio_unlock_gpio(kona_gpio, gpio);
+
+	return gpiochip_reqres_irq(&kona_gpio->gpio_chip, gpio);
 }
 
 static void bcm_kona_gpio_irq_relres(struct irq_data *d)
 {
 	struct bcm_kona_gpio *kona_gpio = irq_data_get_irq_chip_data(d);
+	unsigned int gpio = d->hwirq;
+
+	/* Once we no longer use it, lock the GPIO again */
+	bcm_kona_gpio_lock_gpio(kona_gpio, gpio);
 
-	gpiochip_relres_irq(&kona_gpio->gpio_chip, d->hwirq);
+	gpiochip_relres_irq(&kona_gpio->gpio_chip, gpio);
 }
 
 static struct irq_chip bcm_gpio_irq_chip = {
@@ -614,7 +659,7 @@ static int bcm_kona_gpio_probe(struct platform_device *pdev)
 		bank->irq = platform_get_irq(pdev, i);
 		bank->kona_gpio = kona_gpio;
 		if (bank->irq < 0) {
-			dev_err(dev, "Couldn't get IRQ for bank %d", i);
+			dev_err(dev, "Couldn't get IRQ for bank %d\n", i);
 			ret = -ENOENT;
 			goto err_irq_domain;
 		}
diff --git a/drivers/gpio/gpio-idio-16.c b/drivers/gpio/gpio-idio-16.c
index 53b1eb876a12..2c9512589297 100644
--- a/drivers/gpio/gpio-idio-16.c
+++ b/drivers/gpio/gpio-idio-16.c
@@ -14,7 +14,7 @@
 
 #include "gpio-idio-16.h"
 
-#define DEFAULT_SYMBOL_NAMESPACE GPIO_IDIO_16
+#define DEFAULT_SYMBOL_NAMESPACE "GPIO_IDIO_16"
 
 #define IDIO_16_DAT_BASE 0x0
 #define IDIO_16_OUT_BASE IDIO_16_DAT_BASE
diff --git a/drivers/gpio/gpio-mlxbf2.c b/drivers/gpio/gpio-mlxbf2.c
index 6abe01bc39c3..c03945af8538 100644
--- a/drivers/gpio/gpio-mlxbf2.c
+++ b/drivers/gpio/gpio-mlxbf2.c
@@ -397,7 +397,7 @@ mlxbf2_gpio_probe(struct platform_device *pdev)
 	gc->ngpio = npins;
 	gc->owner = THIS_MODULE;
 
-	irq = platform_get_irq(pdev, 0);
+	irq = platform_get_irq_optional(pdev, 0);
 	if (irq >= 0) {
 		girq = &gs->gc.irq;
 		gpio_irq_chip_set_chip(girq, &mlxbf2_gpio_irq_chip);
diff --git a/drivers/gpio/gpio-mlxbf3.c b/drivers/gpio/gpio-mlxbf3.c
index 10ea71273c89..ed29b07d16c1 100644
--- a/drivers/gpio/gpio-mlxbf3.c
+++ b/drivers/gpio/gpio-mlxbf3.c
@@ -227,7 +227,7 @@ static int mlxbf3_gpio_probe(struct platform_device *pdev)
 	gc->owner = THIS_MODULE;
 	gc->add_pin_ranges = mlxbf3_gpio_add_pin_ranges;
 
-	irq = platform_get_irq(pdev, 0);
+	irq = platform_get_irq_optional(pdev, 0);
 	if (irq >= 0) {
 		girq = &gs->gc.irq;
 		gpio_irq_chip_set_chip(girq, &gpio_mlxbf3_irqchip);
diff --git a/drivers/gpio/gpio-mxc.c b/drivers/gpio/gpio-mxc.c
index 4cb455b2bdee..619b6fb9d833 100644
--- a/drivers/gpio/gpio-mxc.c
+++ b/drivers/gpio/gpio-mxc.c
@@ -490,8 +490,7 @@ static int mxc_gpio_probe(struct platform_device *pdev)
 	port->gc.request = mxc_gpio_request;
 	port->gc.free = mxc_gpio_free;
 	port->gc.to_irq = mxc_gpio_to_irq;
-	port->gc.base = (pdev->id < 0) ? of_alias_get_id(np, "gpio") * 32 :
-					     pdev->id * 32;
+	port->gc.base = of_alias_get_id(np, "gpio") * 32;
 
 	err = devm_gpiochip_add_data(&pdev->dev, &port->gc, port);
 	if (err)
diff --git a/drivers/gpio/gpio-pca953x.c b/drivers/gpio/gpio-pca953x.c
index 3f2d33ee20cc..bb7c1bf5f856 100644
--- a/drivers/gpio/gpio-pca953x.c
+++ b/drivers/gpio/gpio-pca953x.c
@@ -841,25 +841,6 @@ static bool pca953x_irq_pending(struct pca953x_chip *chip, unsigned long *pendin
 	DECLARE_BITMAP(trigger, MAX_LINE);
 	int ret;
 
-	if (chip->driver_data & PCA_PCAL) {
-		/* Read the current interrupt status from the device */
-		ret = pca953x_read_regs(chip, PCAL953X_INT_STAT, trigger);
-		if (ret)
-			return false;
-
-		/* Check latched inputs and clear interrupt status */
-		ret = pca953x_read_regs(chip, chip->regs->input, cur_stat);
-		if (ret)
-			return false;
-
-		/* Apply filter for rising/falling edge selection */
-		bitmap_replace(new_stat, chip->irq_trig_fall, chip->irq_trig_raise, cur_stat, gc->ngpio);
-
-		bitmap_and(pending, new_stat, trigger, gc->ngpio);
-
-		return !bitmap_empty(pending, gc->ngpio);
-	}
-
 	ret = pca953x_read_regs(chip, chip->regs->input, cur_stat);
 	if (ret)
 		return false;
@@ -970,7 +951,7 @@ static int pca953x_irq_setup(struct pca953x_chip *chip, int irq_base)
 					IRQF_ONESHOT | IRQF_SHARED, dev_name(dev),
 					chip);
 	if (ret)
-		return dev_err_probe(dev, client->irq, "failed to request irq\n");
+		return dev_err_probe(dev, ret, "failed to request irq\n");
 
 	return 0;
 }
@@ -1088,7 +1069,8 @@ static int pca953x_probe(struct i2c_client *client)
 		 */
 		reset_gpio = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_LOW);
 		if (IS_ERR(reset_gpio))
-			return PTR_ERR(reset_gpio);
+			return dev_err_probe(dev, PTR_ERR(reset_gpio),
+					     "Failed to get reset gpio\n");
 	}
 
 	chip->client = client;
@@ -1221,6 +1203,8 @@ static int pca953x_restore_context(struct pca953x_chip *chip)
 
 	guard(mutex)(&chip->i2c_lock);
 
+	if (chip->client->irq > 0)
+		enable_irq(chip->client->irq);
 	regcache_cache_only(chip->regmap, false);
 	regcache_mark_dirty(chip->regmap);
 	ret = pca953x_regcache_sync(chip);
@@ -1233,6 +1217,10 @@ static int pca953x_restore_context(struct pca953x_chip *chip)
 static void pca953x_save_context(struct pca953x_chip *chip)
 {
 	guard(mutex)(&chip->i2c_lock);
+
+	/* Disable IRQ to prevent early triggering while regmap "cache only" is on */
+	if (chip->client->irq > 0)
+		disable_irq(chip->client->irq);
 	regcache_cache_only(chip->regmap, true);
 }
 
diff --git a/drivers/gpio/gpio-rcar.c b/drivers/gpio/gpio-rcar.c
index 6159fda38d5d..6641ed5cd8e1 100644
--- a/drivers/gpio/gpio-rcar.c
+++ b/drivers/gpio/gpio-rcar.c
@@ -40,7 +40,7 @@ struct gpio_rcar_info {
 
 struct gpio_rcar_priv {
 	void __iomem *base;
-	spinlock_t lock;
+	raw_spinlock_t lock;
 	struct device *dev;
 	struct gpio_chip gpio_chip;
 	unsigned int irq_parent;
@@ -123,7 +123,7 @@ static void gpio_rcar_config_interrupt_input_mode(struct gpio_rcar_priv *p,
 	 * "Setting Level-Sensitive Interrupt Input Mode"
 	 */
 
-	spin_lock_irqsave(&p->lock, flags);
+	raw_spin_lock_irqsave(&p->lock, flags);
 
 	/* Configure positive or negative logic in POSNEG */
 	gpio_rcar_modify_bit(p, POSNEG, hwirq, !active_high_rising_edge);
@@ -142,7 +142,7 @@ static void gpio_rcar_config_interrupt_input_mode(struct gpio_rcar_priv *p,
 	if (!level_trigger)
 		gpio_rcar_write(p, INTCLR, BIT(hwirq));
 
-	spin_unlock_irqrestore(&p->lock, flags);
+	raw_spin_unlock_irqrestore(&p->lock, flags);
 }
 
 static int gpio_rcar_irq_set_type(struct irq_data *d, unsigned int type)
@@ -246,7 +246,7 @@ static void gpio_rcar_config_general_input_output_mode(struct gpio_chip *chip,
 	 * "Setting General Input Mode"
 	 */
 
-	spin_lock_irqsave(&p->lock, flags);
+	raw_spin_lock_irqsave(&p->lock, flags);
 
 	/* Configure positive logic in POSNEG */
 	gpio_rcar_modify_bit(p, POSNEG, gpio, false);
@@ -261,7 +261,7 @@ static void gpio_rcar_config_general_input_output_mode(struct gpio_chip *chip,
 	if (p->info.has_outdtsel && output)
 		gpio_rcar_modify_bit(p, OUTDTSEL, gpio, false);
 
-	spin_unlock_irqrestore(&p->lock, flags);
+	raw_spin_unlock_irqrestore(&p->lock, flags);
 }
 
 static int gpio_rcar_request(struct gpio_chip *chip, unsigned offset)
@@ -347,7 +347,7 @@ static int gpio_rcar_get_multiple(struct gpio_chip *chip, unsigned long *mask,
 		return 0;
 	}
 
-	spin_lock_irqsave(&p->lock, flags);
+	raw_spin_lock_irqsave(&p->lock, flags);
 	outputs = gpio_rcar_read(p, INOUTSEL);
 	m = outputs & bankmask;
 	if (m)
@@ -356,7 +356,7 @@ static int gpio_rcar_get_multiple(struct gpio_chip *chip, unsigned long *mask,
 	m = ~outputs & bankmask;
 	if (m)
 		val |= gpio_rcar_read(p, INDT) & m;
-	spin_unlock_irqrestore(&p->lock, flags);
+	raw_spin_unlock_irqrestore(&p->lock, flags);
 
 	bits[0] = val;
 	return 0;
@@ -367,9 +367,9 @@ static void gpio_rcar_set(struct gpio_chip *chip, unsigned offset, int value)
 	struct gpio_rcar_priv *p = gpiochip_get_data(chip);
 	unsigned long flags;
 
-	spin_lock_irqsave(&p->lock, flags);
+	raw_spin_lock_irqsave(&p->lock, flags);
 	gpio_rcar_modify_bit(p, OUTDT, offset, value);
-	spin_unlock_irqrestore(&p->lock, flags);
+	raw_spin_unlock_irqrestore(&p->lock, flags);
 }
 
 static void gpio_rcar_set_multiple(struct gpio_chip *chip, unsigned long *mask,
@@ -386,12 +386,12 @@ static void gpio_rcar_set_multiple(struct gpio_chip *chip, unsigned long *mask,
 	if (!bankmask)
 		return;
 
-	spin_lock_irqsave(&p->lock, flags);
+	raw_spin_lock_irqsave(&p->lock, flags);
 	val = gpio_rcar_read(p, OUTDT);
 	val &= ~bankmask;
 	val |= (bankmask & bits[0]);
 	gpio_rcar_write(p, OUTDT, val);
-	spin_unlock_irqrestore(&p->lock, flags);
+	raw_spin_unlock_irqrestore(&p->lock, flags);
 }
 
 static int gpio_rcar_direction_output(struct gpio_chip *chip, unsigned offset,
@@ -468,7 +468,12 @@ static int gpio_rcar_parse_dt(struct gpio_rcar_priv *p, unsigned int *npins)
 	p->info = *info;
 
 	ret = of_parse_phandle_with_fixed_args(np, "gpio-ranges", 3, 0, &args);
-	*npins = ret == 0 ? args.args[2] : RCAR_MAX_GPIO_PER_BANK;
+	if (ret) {
+		*npins = RCAR_MAX_GPIO_PER_BANK;
+	} else {
+		*npins = args.args[2];
+		of_node_put(args.np);
+	}
 
 	if (*npins == 0 || *npins > RCAR_MAX_GPIO_PER_BANK) {
 		dev_warn(p->dev, "Invalid number of gpio lines %u, using %u\n",
@@ -505,7 +510,7 @@ static int gpio_rcar_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	p->dev = dev;
-	spin_lock_init(&p->lock);
+	raw_spin_lock_init(&p->lock);
 
 	/* Get device configuration from DT node */
 	ret = gpio_rcar_parse_dt(p, &npins);
diff --git a/drivers/gpio/gpio-sim.c b/drivers/gpio/gpio-sim.c
index deedacdeb239..f83a8b5a51d0 100644
--- a/drivers/gpio/gpio-sim.c
+++ b/drivers/gpio/gpio-sim.c
@@ -1036,20 +1036,23 @@ gpio_sim_device_lockup_configfs(struct gpio_sim_device *dev, bool lock)
 	struct configfs_subsystem *subsys = dev->group.cg_subsys;
 	struct gpio_sim_bank *bank;
 	struct gpio_sim_line *line;
+	struct config_item *item;
 
 	/*
-	 * The device only needs to depend on leaf line entries. This is
+	 * The device only needs to depend on leaf entries. This is
 	 * sufficient to lock up all the configfs entries that the
 	 * instantiated, alive device depends on.
 	 */
 	list_for_each_entry(bank, &dev->bank_list, siblings) {
 		list_for_each_entry(line, &bank->line_list, siblings) {
+			item = line->hog ? &line->hog->item
+					 : &line->group.cg_item;
+
 			if (lock)
-				WARN_ON(configfs_depend_item_unlocked(
-						subsys, &line->group.cg_item));
+				WARN_ON(configfs_depend_item_unlocked(subsys,
+								      item));
 			else
-				configfs_undepend_item_unlocked(
-						&line->group.cg_item);
+				configfs_undepend_item_unlocked(item);
 		}
 	}
 }
diff --git a/drivers/gpio/gpio-stmpe.c b/drivers/gpio/gpio-stmpe.c
index 75a3633ceddb..222279a9d82b 100644
--- a/drivers/gpio/gpio-stmpe.c
+++ b/drivers/gpio/gpio-stmpe.c
@@ -191,7 +191,7 @@ static void stmpe_gpio_irq_sync_unlock(struct irq_data *d)
 		[REG_IE][CSB] = STMPE_IDX_IEGPIOR_CSB,
 		[REG_IE][MSB] = STMPE_IDX_IEGPIOR_MSB,
 	};
-	int i, j;
+	int ret, i, j;
 
 	/*
 	 * STMPE1600: to be able to get IRQ from pins,
@@ -199,8 +199,16 @@ static void stmpe_gpio_irq_sync_unlock(struct irq_data *d)
 	 * GPSR or GPCR registers
 	 */
 	if (stmpe->partnum == STMPE1600) {
-		stmpe_reg_read(stmpe, stmpe->regs[STMPE_IDX_GPMR_LSB]);
-		stmpe_reg_read(stmpe, stmpe->regs[STMPE_IDX_GPMR_CSB]);
+		ret = stmpe_reg_read(stmpe, stmpe->regs[STMPE_IDX_GPMR_LSB]);
+		if (ret < 0) {
+			dev_err(stmpe->dev, "Failed to read GPMR_LSB: %d\n", ret);
+			goto err;
+		}
+		ret = stmpe_reg_read(stmpe, stmpe->regs[STMPE_IDX_GPMR_CSB]);
+		if (ret < 0) {
+			dev_err(stmpe->dev, "Failed to read GPMR_CSB: %d\n", ret);
+			goto err;
+		}
 	}
 
 	for (i = 0; i < CACHE_NR_REGS; i++) {
@@ -222,6 +230,7 @@ static void stmpe_gpio_irq_sync_unlock(struct irq_data *d)
 		}
 	}
 
+err:
 	mutex_unlock(&stmpe_gpio->irq_lock);
 }
 
diff --git a/drivers/gpio/gpio-tegra186.c b/drivers/gpio/gpio-tegra186.c
index 1ecb733a5e88..45543ab5073f 100644
--- a/drivers/gpio/gpio-tegra186.c
+++ b/drivers/gpio/gpio-tegra186.c
@@ -823,6 +823,7 @@ static int tegra186_gpio_probe(struct platform_device *pdev)
 	struct gpio_irq_chip *irq;
 	struct tegra_gpio *gpio;
 	struct device_node *np;
+	struct resource *res;
 	char **names;
 	int err;
 
@@ -842,19 +843,19 @@ static int tegra186_gpio_probe(struct platform_device *pdev)
 	gpio->num_banks++;
 
 	/* get register apertures */
-	gpio->secure = devm_platform_ioremap_resource_byname(pdev, "security");
-	if (IS_ERR(gpio->secure)) {
-		gpio->secure = devm_platform_ioremap_resource(pdev, 0);
-		if (IS_ERR(gpio->secure))
-			return PTR_ERR(gpio->secure);
-	}
-
-	gpio->base = devm_platform_ioremap_resource_byname(pdev, "gpio");
-	if (IS_ERR(gpio->base)) {
-		gpio->base = devm_platform_ioremap_resource(pdev, 1);
-		if (IS_ERR(gpio->base))
-			return PTR_ERR(gpio->base);
-	}
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "security");
+	if (!res)
+		res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	gpio->secure = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(gpio->secure))
+		return PTR_ERR(gpio->secure);
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "gpio");
+	if (!res)
+		res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+	gpio->base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(gpio->base))
+		return PTR_ERR(gpio->base);
 
 	err = platform_irq_count(pdev);
 	if (err < 0)
diff --git a/drivers/gpio/gpio-tps65912.c b/drivers/gpio/gpio-tps65912.c
index fab771cb6a87..bac757c191c2 100644
--- a/drivers/gpio/gpio-tps65912.c
+++ b/drivers/gpio/gpio-tps65912.c
@@ -49,10 +49,13 @@ static int tps65912_gpio_direction_output(struct gpio_chip *gc,
 					  unsigned offset, int value)
 {
 	struct tps65912_gpio *gpio = gpiochip_get_data(gc);
+	int ret;
 
 	/* Set the initial value */
-	regmap_update_bits(gpio->tps->regmap, TPS65912_GPIO1 + offset,
-			   GPIO_SET_MASK, value ? GPIO_SET_MASK : 0);
+	ret = regmap_update_bits(gpio->tps->regmap, TPS65912_GPIO1 + offset,
+				 GPIO_SET_MASK, value ? GPIO_SET_MASK : 0);
+	if (ret)
+		return ret;
 
 	return regmap_update_bits(gpio->tps->regmap, TPS65912_GPIO1 + offset,
 				  GPIO_CFG_MASK, GPIO_CFG_MASK);
diff --git a/drivers/gpio/gpio-vf610.c b/drivers/gpio/gpio-vf610.c
index 27eff741fe9a..c36a9dbccd4d 100644
--- a/drivers/gpio/gpio-vf610.c
+++ b/drivers/gpio/gpio-vf610.c
@@ -15,10 +15,9 @@
 #include <linux/io.h>
 #include <linux/ioport.h>
 #include <linux/irq.h>
-#include <linux/platform_device.h>
-#include <linux/of.h>
-#include <linux/of_irq.h>
 #include <linux/pinctrl/consumer.h>
+#include <linux/platform_device.h>
+#include <linux/property.h>
 
 #define VF610_GPIO_PER_PORT		32
 
@@ -37,6 +36,7 @@ struct vf610_gpio_port {
 	struct clk *clk_port;
 	struct clk *clk_gpio;
 	int irq;
+	spinlock_t lock; /* protect gpio direction registers */
 };
 
 #define GPIO_PDOR		0x00
@@ -125,6 +125,7 @@ static int vf610_gpio_direction_input(struct gpio_chip *chip, unsigned int gpio)
 	u32 val;
 
 	if (port->sdata->have_paddr) {
+		guard(spinlock_irqsave)(&port->lock);
 		val = vf610_gpio_readl(port->gpio_base + GPIO_PDDR);
 		val &= ~mask;
 		vf610_gpio_writel(val, port->gpio_base + GPIO_PDDR);
@@ -143,6 +144,7 @@ static int vf610_gpio_direction_output(struct gpio_chip *chip, unsigned int gpio
 	vf610_gpio_set(chip, gpio, value);
 
 	if (port->sdata->have_paddr) {
+		guard(spinlock_irqsave)(&port->lock);
 		val = vf610_gpio_readl(port->gpio_base + GPIO_PDDR);
 		val |= mask;
 		vf610_gpio_writel(val, port->gpio_base + GPIO_PDDR);
@@ -297,7 +299,8 @@ static int vf610_gpio_probe(struct platform_device *pdev)
 	if (!port)
 		return -ENOMEM;
 
-	port->sdata = of_device_get_match_data(dev);
+	port->sdata = device_get_match_data(dev);
+	spin_lock_init(&port->lock);
 
 	dual_base = port->sdata->have_dual_base;
 
diff --git a/drivers/gpio/gpio-virtio.c b/drivers/gpio/gpio-virtio.c
index 93544ff62513..5b56f3f61563 100644
--- a/drivers/gpio/gpio-virtio.c
+++ b/drivers/gpio/gpio-virtio.c
@@ -539,7 +539,6 @@ static const char **virtio_gpio_get_names(struct virtio_gpio *vgpio,
 
 static int virtio_gpio_probe(struct virtio_device *vdev)
 {
-	struct virtio_gpio_config config;
 	struct device *dev = &vdev->dev;
 	struct virtio_gpio *vgpio;
 	u32 gpio_names_size;
@@ -551,9 +550,11 @@ static int virtio_gpio_probe(struct virtio_device *vdev)
 		return -ENOMEM;
 
 	/* Read configuration */
-	virtio_cread_bytes(vdev, 0, &config, sizeof(config));
-	gpio_names_size = le32_to_cpu(config.gpio_names_size);
-	ngpio = le16_to_cpu(config.ngpio);
+	gpio_names_size =
+		virtio_cread32(vdev, offsetof(struct virtio_gpio_config,
+					      gpio_names_size));
+	ngpio =  virtio_cread16(vdev, offsetof(struct virtio_gpio_config,
+					       ngpio));
 	if (!ngpio) {
 		dev_err(dev, "Number of GPIOs can't be zero\n");
 		return -EINVAL;
diff --git a/drivers/gpio/gpio-virtuser.c b/drivers/gpio/gpio-virtuser.c
index e89f299f2140..dcecb7a25911 100644
--- a/drivers/gpio/gpio-virtuser.c
+++ b/drivers/gpio/gpio-virtuser.c
@@ -400,10 +400,15 @@ static ssize_t gpio_virtuser_direction_do_write(struct file *file,
 	char buf[32], *trimmed;
 	int ret, dir, val = 0;
 
-	ret = simple_write_to_buffer(buf, sizeof(buf), ppos, user_buf, count);
+	if (count >= sizeof(buf))
+		return -EINVAL;
+
+	ret = simple_write_to_buffer(buf, sizeof(buf) - 1, ppos, user_buf, count);
 	if (ret < 0)
 		return ret;
 
+	buf[ret] = '\0';
+
 	trimmed = strim(buf);
 
 	if (strcmp(trimmed, "input") == 0) {
@@ -622,12 +627,15 @@ static ssize_t gpio_virtuser_consumer_write(struct file *file,
 	char buf[GPIO_VIRTUSER_NAME_BUF_LEN + 2];
 	int ret;
 
+	if (count >= sizeof(buf))
+		return -EINVAL;
+
 	ret = simple_write_to_buffer(buf, GPIO_VIRTUSER_NAME_BUF_LEN, ppos,
 				     user_buf, count);
 	if (ret < 0)
 		return ret;
 
-	buf[strlen(buf) - 1] = '\0';
+	buf[ret] = '\0';
 
 	ret = gpiod_set_consumer_name(data->ad.desc, buf);
 	if (ret)
diff --git a/drivers/gpio/gpio-wcd934x.c b/drivers/gpio/gpio-wcd934x.c
index 2bba27b13947..cfa7b0a50c8e 100644
--- a/drivers/gpio/gpio-wcd934x.c
+++ b/drivers/gpio/gpio-wcd934x.c
@@ -46,9 +46,12 @@ static int wcd_gpio_direction_output(struct gpio_chip *chip, unsigned int pin,
 				     int val)
 {
 	struct wcd_gpio_data *data = gpiochip_get_data(chip);
+	int ret;
 
-	regmap_update_bits(data->map, WCD_REG_DIR_CTL_OFFSET,
-			   WCD_PIN_MASK(pin), WCD_PIN_MASK(pin));
+	ret = regmap_update_bits(data->map, WCD_REG_DIR_CTL_OFFSET,
+				 WCD_PIN_MASK(pin), WCD_PIN_MASK(pin));
+	if (ret)
+		return ret;
 
 	return regmap_update_bits(data->map, WCD_REG_VAL_CTL_OFFSET,
 				  WCD_PIN_MASK(pin),
diff --git a/drivers/gpio/gpio-zynq.c b/drivers/gpio/gpio-zynq.c
index 1a42336dfc1d..cc53e6940ad7 100644
--- a/drivers/gpio/gpio-zynq.c
+++ b/drivers/gpio/gpio-zynq.c
@@ -1011,6 +1011,7 @@ static void zynq_gpio_remove(struct platform_device *pdev)
 	ret = pm_runtime_get_sync(&pdev->dev);
 	if (ret < 0)
 		dev_warn(&pdev->dev, "pm_runtime_get_sync() Failed\n");
+	device_init_wakeup(&pdev->dev, 0);
 	gpiochip_remove(&gpio->chip);
 	device_set_wakeup_capable(&pdev->dev, 0);
 	pm_runtime_disable(&pdev->dev);
diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c
index 78ecd56123a3..148b4d1788a2 100644
--- a/drivers/gpio/gpiolib-acpi.c
+++ b/drivers/gpio/gpiolib-acpi.c
@@ -1691,6 +1691,20 @@ static const struct dmi_system_id gpiolib_acpi_quirks[] __initconst = {
 			.ignore_wake = "PNP0C50:00@8",
 		},
 	},
+	{
+		/*
+		 * Spurious wakeups from GPIO 11
+		 * Found in BIOS 1.04
+		 * https://gitlab.freedesktop.org/drm/amd/-/issues/3954
+		 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+			DMI_MATCH(DMI_PRODUCT_FAMILY, "Acer Nitro V 14"),
+		},
+		.driver_data = &(struct acpi_gpiolib_dmi_quirk) {
+			.ignore_interrupt = "AMDI0030:00@11",
+		},
+	},
 	{} /* Terminating entry */
 };
 
diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c
index 880f1efcaca5..36f8c7bb79d8 100644
--- a/drivers/gpio/gpiolib-of.c
+++ b/drivers/gpio/gpiolib-of.c
@@ -193,6 +193,8 @@ static void of_gpio_try_fixup_polarity(const struct device_node *np,
 		 */
 		{ "himax,hx8357",	"gpios-reset",	false },
 		{ "himax,hx8369",	"gpios-reset",	false },
+#endif
+#if IS_ENABLED(CONFIG_MTD_NAND_JZ4780)
 		/*
 		 * The rb-gpios semantics was undocumented and qi,lb60 (along with
 		 * the ingenic driver) got it wrong. The active state encodes the
@@ -213,6 +215,15 @@ static void of_gpio_try_fixup_polarity(const struct device_node *np,
 		 */
 		{ "lantiq,pci-xway",	"gpio-reset",	false },
 #endif
+#if IS_ENABLED(CONFIG_REGULATOR_S5M8767)
+		/*
+		 * According to S5M8767, the DVS and DS pin are
+		 * active-high signals. However, exynos5250-spring.dts use
+		 * active-low setting.
+		 */
+		{ "samsung,s5m8767-pmic", "s5m8767,pmic-buck-dvs-gpios", true },
+		{ "samsung,s5m8767-pmic", "s5m8767,pmic-buck-ds-gpios", true },
+#endif
 #if IS_ENABLED(CONFIG_TOUCHSCREEN_TSC2005)
 		/*
 		 * DTS for Nokia N900 incorrectly specified "active high"
@@ -257,6 +268,9 @@ static void of_gpio_set_polarity_by_property(const struct device_node *np,
 		{ "fsl,imx8qm-fec",  "phy-reset-gpios", "phy-reset-active-high" },
 		{ "fsl,s32v234-fec", "phy-reset-gpios", "phy-reset-active-high" },
 #endif
+#if IS_ENABLED(CONFIG_MMC_ATMELMCI)
+		{ "atmel,hsmci",       "cd-gpios",     "cd-inverted" },
+#endif
 #if IS_ENABLED(CONFIG_PCI_IMX6)
 		{ "fsl,imx6q-pcie",  "reset-gpio", "reset-gpio-active-high" },
 		{ "fsl,imx6sx-pcie", "reset-gpio", "reset-gpio-active-high" },
@@ -283,9 +297,6 @@ static void of_gpio_set_polarity_by_property(const struct device_node *np,
 		{ "regulator-gpio",    "enable-gpio",  "enable-active-high" },
 		{ "regulator-gpio",    "enable-gpios", "enable-active-high" },
 #endif
-#if IS_ENABLED(CONFIG_MMC_ATMELMCI)
-		{ "atmel,hsmci",       "cd-gpios",     "cd-inverted" },
-#endif
 	};
 	unsigned int i;
 	bool active_high;
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 44372f8647d5..209871c219d6 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -905,13 +905,13 @@ int gpiochip_get_ngpios(struct gpio_chip *gc, struct device *dev)
 	}
 
 	if (gc->ngpio == 0) {
-		chip_err(gc, "tried to insert a GPIO chip with zero lines\n");
+		dev_err(dev, "tried to insert a GPIO chip with zero lines\n");
 		return -EINVAL;
 	}
 
 	if (gc->ngpio > FASTPATH_NGPIO)
-		chip_warn(gc, "line cnt %u is greater than fast path cnt %u\n",
-			gc->ngpio, FASTPATH_NGPIO);
+		dev_warn(dev, "line cnt %u is greater than fast path cnt %u\n",
+			 gc->ngpio, FASTPATH_NGPIO);
 
 	return 0;
 }
@@ -3068,6 +3068,8 @@ static int gpiod_get_raw_value_commit(const struct gpio_desc *desc)
 static int gpio_chip_get_multiple(struct gpio_chip *gc,
 				  unsigned long *mask, unsigned long *bits)
 {
+	lockdep_assert_held(&gc->gpiodev->srcu);
+
 	if (gc->get_multiple)
 		return gc->get_multiple(gc, mask, bits);
 	if (gc->get) {
@@ -3098,6 +3100,7 @@ int gpiod_get_array_value_complex(bool raw, bool can_sleep,
 				  struct gpio_array *array_info,
 				  unsigned long *value_bitmap)
 {
+	struct gpio_chip *gc;
 	int ret, i = 0;
 
 	/*
@@ -3109,10 +3112,15 @@ int gpiod_get_array_value_complex(bool raw, bool can_sleep,
 	    array_size <= array_info->size &&
 	    (void *)array_info == desc_array + array_info->size) {
 		if (!can_sleep)
-			WARN_ON(array_info->chip->can_sleep);
+			WARN_ON(array_info->gdev->can_sleep);
+
+		guard(srcu)(&array_info->gdev->srcu);
+		gc = srcu_dereference(array_info->gdev->chip,
+				      &array_info->gdev->srcu);
+		if (!gc)
+			return -ENODEV;
 
-		ret = gpio_chip_get_multiple(array_info->chip,
-					     array_info->get_mask,
+		ret = gpio_chip_get_multiple(gc, array_info->get_mask,
 					     value_bitmap);
 		if (ret)
 			return ret;
@@ -3393,6 +3401,8 @@ static void gpiod_set_raw_value_commit(struct gpio_desc *desc, bool value)
 static void gpio_chip_set_multiple(struct gpio_chip *gc,
 				   unsigned long *mask, unsigned long *bits)
 {
+	lockdep_assert_held(&gc->gpiodev->srcu);
+
 	if (gc->set_multiple) {
 		gc->set_multiple(gc, mask, bits);
 	} else {
@@ -3410,6 +3420,7 @@ int gpiod_set_array_value_complex(bool raw, bool can_sleep,
 				  struct gpio_array *array_info,
 				  unsigned long *value_bitmap)
 {
+	struct gpio_chip *gc;
 	int i = 0;
 
 	/*
@@ -3421,14 +3432,19 @@ int gpiod_set_array_value_complex(bool raw, bool can_sleep,
 	    array_size <= array_info->size &&
 	    (void *)array_info == desc_array + array_info->size) {
 		if (!can_sleep)
-			WARN_ON(array_info->chip->can_sleep);
+			WARN_ON(array_info->gdev->can_sleep);
+
+		guard(srcu)(&array_info->gdev->srcu);
+		gc = srcu_dereference(array_info->gdev->chip,
+				      &array_info->gdev->srcu);
+		if (!gc)
+			return -ENODEV;
 
 		if (!raw && !bitmap_empty(array_info->invert_mask, array_size))
 			bitmap_xor(value_bitmap, value_bitmap,
 				   array_info->invert_mask, array_size);
 
-		gpio_chip_set_multiple(array_info->chip, array_info->set_mask,
-				       value_bitmap);
+		gpio_chip_set_multiple(gc, array_info->set_mask, value_bitmap);
 
 		i = find_first_zero_bit(array_info->set_mask, array_size);
 		if (i == array_size)
@@ -4684,9 +4700,10 @@ struct gpio_descs *__must_check gpiod_get_array(struct device *dev,
 {
 	struct gpio_desc *desc;
 	struct gpio_descs *descs;
+	struct gpio_device *gdev;
 	struct gpio_array *array_info = NULL;
-	struct gpio_chip *gc;
 	int count, bitmap_size;
+	unsigned long dflags;
 	size_t descs_size;
 
 	count = gpiod_count(dev, con_id);
@@ -4707,7 +4724,7 @@ struct gpio_descs *__must_check gpiod_get_array(struct device *dev,
 
 		descs->desc[descs->ndescs] = desc;
 
-		gc = gpiod_to_chip(desc);
+		gdev = gpiod_to_gpio_device(desc);
 		/*
 		 * If pin hardware number of array member 0 is also 0, select
 		 * its chip as a candidate for fast bitmap processing path.
@@ -4715,8 +4732,8 @@ struct gpio_descs *__must_check gpiod_get_array(struct device *dev,
 		if (descs->ndescs == 0 && gpio_chip_hwgpio(desc) == 0) {
 			struct gpio_descs *array;
 
-			bitmap_size = BITS_TO_LONGS(gc->ngpio > count ?
-						    gc->ngpio : count);
+			bitmap_size = BITS_TO_LONGS(gdev->ngpio > count ?
+						    gdev->ngpio : count);
 
 			array = krealloc(descs, descs_size +
 					 struct_size(array_info, invert_mask, 3 * bitmap_size),
@@ -4736,7 +4753,7 @@ struct gpio_descs *__must_check gpiod_get_array(struct device *dev,
 
 			array_info->desc = descs->desc;
 			array_info->size = count;
-			array_info->chip = gc;
+			array_info->gdev = gdev;
 			bitmap_set(array_info->get_mask, descs->ndescs,
 				   count - descs->ndescs);
 			bitmap_set(array_info->set_mask, descs->ndescs,
@@ -4749,7 +4766,7 @@ struct gpio_descs *__must_check gpiod_get_array(struct device *dev,
 			continue;
 
 		/* Unmark array members which don't belong to the 'fast' chip */
-		if (array_info->chip != gc) {
+		if (array_info->gdev != gdev) {
 			__clear_bit(descs->ndescs, array_info->get_mask);
 			__clear_bit(descs->ndescs, array_info->set_mask);
 		}
@@ -4772,9 +4789,10 @@ struct gpio_descs *__must_check gpiod_get_array(struct device *dev,
 					    array_info->set_mask);
 			}
 		} else {
+			dflags = READ_ONCE(desc->flags);
 			/* Exclude open drain or open source from fast output */
-			if (gpiochip_line_is_open_drain(gc, descs->ndescs) ||
-			    gpiochip_line_is_open_source(gc, descs->ndescs))
+			if (test_bit(FLAG_OPEN_DRAIN, &dflags) ||
+			    test_bit(FLAG_OPEN_SOURCE, &dflags))
 				__clear_bit(descs->ndescs,
 					    array_info->set_mask);
 			/* Identify 'fast' pins which require invertion */
@@ -4786,7 +4804,7 @@ struct gpio_descs *__must_check gpiod_get_array(struct device *dev,
 	if (array_info)
 		dev_dbg(dev,
 			"GPIO array info: chip=%s, size=%d, get_mask=%lx, set_mask=%lx, invert_mask=%lx\n",
-			array_info->chip->label, array_info->size,
+			array_info->gdev->label, array_info->size,
 			*array_info->get_mask, *array_info->set_mask,
 			*array_info->invert_mask);
 	return descs;
diff --git a/drivers/gpio/gpiolib.h b/drivers/gpio/gpiolib.h
index 067197d61d57..87ce3753500e 100644
--- a/drivers/gpio/gpiolib.h
+++ b/drivers/gpio/gpiolib.h
@@ -110,7 +110,7 @@ extern const char *const gpio_suffixes[];
  *
  * @desc:		Array of pointers to the GPIO descriptors
  * @size:		Number of elements in desc
- * @chip:		Parent GPIO chip
+ * @gdev:		Parent GPIO device
  * @get_mask:		Get mask used in fastpath
  * @set_mask:		Set mask used in fastpath
  * @invert_mask:	Invert mask used in fastpath
@@ -122,7 +122,7 @@ extern const char *const gpio_suffixes[];
 struct gpio_array {
 	struct gpio_desc	**desc;
 	unsigned int		size;
-	struct gpio_chip	*chip;
+	struct gpio_device	*gdev;
 	unsigned long		*get_mask;
 	unsigned long		*set_mask;
 	unsigned long		invert_mask[];
diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig
index 610e159d362a..1160a439e92a 100644
--- a/drivers/gpu/drm/Kconfig
+++ b/drivers/gpu/drm/Kconfig
@@ -185,7 +185,7 @@ config DRM_DEBUG_DP_MST_TOPOLOGY_REFS
         bool "Enable refcount backtrace history in the DP MST helpers"
 	depends on STACKTRACE_SUPPORT
         select STACKDEPOT
-        depends on DRM_KMS_HELPER
+        select DRM_KMS_HELPER
         depends on DEBUG_KERNEL
         depends on EXPERT
         help
@@ -211,6 +211,18 @@ config DRM_DEBUG_MODESET_LOCK
 
 	  If in doubt, say "N".
 
+config DRM_CLIENT_SELECTION
+	bool
+	depends on DRM
+	select DRM_CLIENT_SETUP if DRM_FBDEV_EMULATION
+	help
+	  Drivers that support in-kernel DRM clients have to select this
+	  option.
+
+config DRM_CLIENT_SETUP
+	bool
+	depends on DRM_CLIENT_SELECTION
+
 config DRM_FBDEV_EMULATION
 	bool "Enable legacy fbdev support for your modesetting driver"
 	depends on DRM
@@ -486,6 +498,10 @@ config DRM_HYPERV
 config DRM_EXPORT_FOR_TESTS
 	bool
 
+# Separate option as not all DRM drivers use it
+config DRM_PANEL_BACKLIGHT_QUIRKS
+	tristate
+
 config DRM_LIB_RANDOM
 	bool
 	default n
diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile
index 784229d4504d..1ec44529447a 100644
--- a/drivers/gpu/drm/Makefile
+++ b/drivers/gpu/drm/Makefile
@@ -93,6 +93,7 @@ drm-$(CONFIG_DRM_PANIC_SCREEN_QR_CODE) += drm_panic_qr.o
 obj-$(CONFIG_DRM)	+= drm.o
 
 obj-$(CONFIG_DRM_PANEL_ORIENTATION_QUIRKS) += drm_panel_orientation_quirks.o
+obj-$(CONFIG_DRM_PANEL_BACKLIGHT_QUIRKS) += drm_panel_backlight_quirks.o
 
 #
 # Memory-management helpers
@@ -143,8 +144,12 @@ drm_kms_helper-y := \
 	drm_rect.o \
 	drm_self_refresh_helper.o \
 	drm_simple_kms_helper.o
+drm_kms_helper-$(CONFIG_DRM_CLIENT_SETUP) += \
+	drm_client_setup.o
 drm_kms_helper-$(CONFIG_DRM_PANEL_BRIDGE) += bridge/panel.o
-drm_kms_helper-$(CONFIG_DRM_FBDEV_EMULATION) += drm_fb_helper.o
+drm_kms_helper-$(CONFIG_DRM_FBDEV_EMULATION) += \
+	drm_fbdev_client.o \
+	drm_fb_helper.o
 obj-$(CONFIG_DRM_KMS_HELPER) += drm_kms_helper.o
 
 #
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 9b1e0ede05a4..7edf8d67a0fa 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -350,7 +350,6 @@ enum amdgpu_kiq_irq {
 	AMDGPU_CP_KIQ_IRQ_DRIVER0 = 0,
 	AMDGPU_CP_KIQ_IRQ_LAST
 };
-#define SRIOV_USEC_TIMEOUT  1200000 /* wait 12 * 100ms for SRIOV */
 #define MAX_KIQ_REG_WAIT       5000 /* in usecs, 5ms */
 #define MAX_KIQ_REG_BAILOUT_INTERVAL   5 /* in msecs, 5ms */
 #define MAX_KIQ_REG_TRY 1000
@@ -854,6 +853,7 @@ struct amdgpu_device {
 	bool				need_swiotlb;
 	bool				accel_working;
 	struct notifier_block		acpi_nb;
+	struct notifier_block		pm_nb;
 	struct amdgpu_i2c_chan		*i2c_bus[AMDGPU_MAX_I2C_BUS];
 	struct debugfs_blob_wrapper     debugfs_vbios_blob;
 	struct debugfs_blob_wrapper     debugfs_discovery_blob;
@@ -1571,11 +1571,9 @@ static inline void amdgpu_acpi_get_backlight_caps(struct amdgpu_dm_backlight_cap
 #if defined(CONFIG_ACPI) && defined(CONFIG_SUSPEND)
 bool amdgpu_acpi_is_s3_active(struct amdgpu_device *adev);
 bool amdgpu_acpi_is_s0ix_active(struct amdgpu_device *adev);
-void amdgpu_choose_low_power_state(struct amdgpu_device *adev);
 #else
 static inline bool amdgpu_acpi_is_s0ix_active(struct amdgpu_device *adev) { return false; }
 static inline bool amdgpu_acpi_is_s3_active(struct amdgpu_device *adev) { return false; }
-static inline void amdgpu_choose_low_power_state(struct amdgpu_device *adev) { }
 #endif
 
 void amdgpu_register_gpu_instance(struct amdgpu_device *adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
index b8d4e07d2043..bebfbc1497d8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
@@ -1533,22 +1533,4 @@ bool amdgpu_acpi_is_s0ix_active(struct amdgpu_device *adev)
 #endif /* CONFIG_AMD_PMC */
 }
 
-/**
- * amdgpu_choose_low_power_state
- *
- * @adev: amdgpu_device_pointer
- *
- * Choose the target low power state for the GPU
- */
-void amdgpu_choose_low_power_state(struct amdgpu_device *adev)
-{
-	if (adev->in_runpm)
-		return;
-
-	if (amdgpu_acpi_is_s0ix_active(adev))
-		adev->in_s0ix = true;
-	else if (amdgpu_acpi_is_s3_active(adev))
-		adev->in_s3 = true;
-}
-
 #endif /* CONFIG_SUSPEND */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
index f9d119448442..581fe1a48f37 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@@ -192,7 +192,7 @@ int kfd_debugfs_kfd_mem_limits(struct seq_file *m, void *data);
 #if IS_ENABLED(CONFIG_HSA_AMD)
 bool amdkfd_fence_check_mm(struct dma_fence *f, struct mm_struct *mm);
 struct amdgpu_amdkfd_fence *to_amdgpu_amdkfd_fence(struct dma_fence *f);
-int amdgpu_amdkfd_remove_fence_on_pt_pd_bos(struct amdgpu_bo *bo);
+void amdgpu_amdkfd_remove_all_eviction_fences(struct amdgpu_bo *bo);
 int amdgpu_amdkfd_evict_userptr(struct mmu_interval_notifier *mni,
 				unsigned long cur_seq, struct kgd_mem *mem);
 int amdgpu_amdkfd_bo_validate_and_fence(struct amdgpu_bo *bo,
@@ -212,9 +212,8 @@ struct amdgpu_amdkfd_fence *to_amdgpu_amdkfd_fence(struct dma_fence *f)
 }
 
 static inline
-int amdgpu_amdkfd_remove_fence_on_pt_pd_bos(struct amdgpu_bo *bo)
+void amdgpu_amdkfd_remove_all_eviction_fences(struct amdgpu_bo *bo)
 {
-	return 0;
 }
 
 static inline
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
index 3bc0cbf45bc5..a46d6dd6de32 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
@@ -1133,8 +1133,7 @@ uint64_t kgd_gfx_v9_hqd_get_pq_addr(struct amdgpu_device *adev,
 	uint32_t low, high;
 	uint64_t queue_addr = 0;
 
-	if (!adev->debug_exp_resets &&
-	    !adev->gfx.num_gfx_rings)
+	if (!amdgpu_gpu_recovery)
 		return 0;
 
 	kgd_gfx_v9_acquire_queue(adev, pipe_id, queue_id, inst);
@@ -1185,6 +1184,9 @@ uint64_t kgd_gfx_v9_hqd_reset(struct amdgpu_device *adev,
 	uint32_t low, high, pipe_reset_data = 0;
 	uint64_t queue_addr = 0;
 
+	if (!amdgpu_gpu_recovery)
+		return 0;
+
 	kgd_gfx_v9_acquire_queue(adev, pipe_id, queue_id, inst);
 	amdgpu_gfx_rlc_enter_safe_mode(adev, inst);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index fa572ba7f9fc..1465b3adacb0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -370,40 +370,32 @@ static int amdgpu_amdkfd_remove_eviction_fence(struct amdgpu_bo *bo,
 	return 0;
 }
 
-int amdgpu_amdkfd_remove_fence_on_pt_pd_bos(struct amdgpu_bo *bo)
+/**
+ * amdgpu_amdkfd_remove_all_eviction_fences - Remove all eviction fences
+ * @bo: the BO where to remove the evictions fences from.
+ *
+ * This functions should only be used on release when all references to the BO
+ * are already dropped. We remove the eviction fence from the private copy of
+ * the dma_resv object here since that is what is used during release to
+ * determine of the BO is idle or not.
+ */
+void amdgpu_amdkfd_remove_all_eviction_fences(struct amdgpu_bo *bo)
 {
-	struct amdgpu_bo *root = bo;
-	struct amdgpu_vm_bo_base *vm_bo;
-	struct amdgpu_vm *vm;
-	struct amdkfd_process_info *info;
-	struct amdgpu_amdkfd_fence *ef;
-	int ret;
-
-	/* we can always get vm_bo from root PD bo.*/
-	while (root->parent)
-		root = root->parent;
+	struct dma_resv *resv = &bo->tbo.base._resv;
+	struct dma_fence *fence, *stub;
+	struct dma_resv_iter cursor;
 
-	vm_bo = root->vm_bo;
-	if (!vm_bo)
-		return 0;
+	dma_resv_assert_held(resv);
 
-	vm = vm_bo->vm;
-	if (!vm)
-		return 0;
-
-	info = vm->process_info;
-	if (!info || !info->eviction_fence)
-		return 0;
-
-	ef = container_of(dma_fence_get(&info->eviction_fence->base),
-			struct amdgpu_amdkfd_fence, base);
-
-	BUG_ON(!dma_resv_trylock(bo->tbo.base.resv));
-	ret = amdgpu_amdkfd_remove_eviction_fence(bo, ef);
-	dma_resv_unlock(bo->tbo.base.resv);
+	stub = dma_fence_get_stub();
+	dma_resv_for_each_fence(&cursor, resv, DMA_RESV_USAGE_BOOKKEEP, fence) {
+		if (!to_amdgpu_amdkfd_fence(fence))
+			continue;
 
-	dma_fence_put(&ef->base);
-	return ret;
+		dma_resv_replace_fences(resv, fence->context, stub,
+					DMA_RESV_USAGE_BOOKKEEP);
+	}
+	dma_fence_put(stub);
 }
 
 static int amdgpu_amdkfd_bo_validate(struct amdgpu_bo *bo, uint32_t domain,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c
index 45affc02548c..a3a7d20ab4fe 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c
@@ -437,6 +437,13 @@ success:
 	return true;
 }
 
+static bool amdgpu_prefer_rom_resource(struct amdgpu_device *adev)
+{
+	struct resource *res = &adev->pdev->resource[PCI_ROM_RESOURCE];
+
+	return (res->flags & IORESOURCE_ROM_SHADOW);
+}
+
 static bool amdgpu_get_bios_dgpu(struct amdgpu_device *adev)
 {
 	if (amdgpu_atrm_get_bios(adev)) {
@@ -455,14 +462,27 @@ static bool amdgpu_get_bios_dgpu(struct amdgpu_device *adev)
 		goto success;
 	}
 
-	if (amdgpu_read_platform_bios(adev)) {
-		dev_info(adev->dev, "Fetched VBIOS from platform\n");
-		goto success;
-	}
+	if (amdgpu_prefer_rom_resource(adev)) {
+		if (amdgpu_read_bios(adev)) {
+			dev_info(adev->dev, "Fetched VBIOS from ROM BAR\n");
+			goto success;
+		}
 
-	if (amdgpu_read_bios(adev)) {
-		dev_info(adev->dev, "Fetched VBIOS from ROM BAR\n");
-		goto success;
+		if (amdgpu_read_platform_bios(adev)) {
+			dev_info(adev->dev, "Fetched VBIOS from platform\n");
+			goto success;
+		}
+
+	} else {
+		if (amdgpu_read_platform_bios(adev)) {
+			dev_info(adev->dev, "Fetched VBIOS from platform\n");
+			goto success;
+		}
+
+		if (amdgpu_read_bios(adev)) {
+			dev_info(adev->dev, "Fetched VBIOS from ROM BAR\n");
+			goto success;
+		}
 	}
 
 	if (amdgpu_read_bios_from_rom(adev)) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c
index cfdf558b48b6..dfb6cfd83760 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c
@@ -88,8 +88,8 @@ int amdgpu_map_static_csa(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	}
 
 	r = amdgpu_vm_bo_map(adev, *bo_va, csa_addr, 0, size,
-			     AMDGPU_PTE_READABLE | AMDGPU_PTE_WRITEABLE |
-			     AMDGPU_PTE_EXECUTABLE);
+			     AMDGPU_VM_PAGE_READABLE | AMDGPU_VM_PAGE_WRITEABLE |
+			     AMDGPU_VM_PAGE_EXECUTABLE);
 
 	if (r) {
 		DRM_ERROR("failed to do bo_map on static CSA, err=%d\n", r);
@@ -109,7 +109,7 @@ int amdgpu_unmap_static_csa(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	struct drm_exec exec;
 	int r;
 
-	drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT, 0);
+	drm_exec_init(&exec, 0, 0);
 	drm_exec_until_all_locked(&exec) {
 		r = amdgpu_vm_lock_pd(vm, &exec, 0);
 		if (likely(!r))
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
index 9da4414de617..81f16e4447f8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
@@ -1902,7 +1902,7 @@ no_preempt:
 			continue;
 		}
 		job = to_amdgpu_job(s_job);
-		if (preempted && (&job->hw_fence) == fence)
+		if (preempted && (&job->hw_fence.base) == fence)
 			/* mark the job as preempted */
 			job->preemption_status |= AMDGPU_IB_PREEMPTED;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 45e28726e148..8cf224fd4ff2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -145,6 +145,8 @@ const char *amdgpu_asic_name[] = {
 };
 
 static inline void amdgpu_device_stop_pending_resets(struct amdgpu_device *adev);
+static int amdgpu_device_pm_notifier(struct notifier_block *nb, unsigned long mode,
+				     void *data);
 
 /**
  * DOC: pcie_replay_count
@@ -168,6 +170,24 @@ static ssize_t amdgpu_device_get_pcie_replay_count(struct device *dev,
 static DEVICE_ATTR(pcie_replay_count, 0444,
 		amdgpu_device_get_pcie_replay_count, NULL);
 
+static int amdgpu_device_attr_sysfs_init(struct amdgpu_device *adev)
+{
+	int ret = 0;
+
+	if (!amdgpu_sriov_vf(adev))
+		ret = sysfs_create_file(&adev->dev->kobj,
+					&dev_attr_pcie_replay_count.attr);
+
+	return ret;
+}
+
+static void amdgpu_device_attr_sysfs_fini(struct amdgpu_device *adev)
+{
+	if (!amdgpu_sriov_vf(adev))
+		sysfs_remove_file(&adev->dev->kobj,
+				  &dev_attr_pcie_replay_count.attr);
+}
+
 static ssize_t amdgpu_sysfs_reg_state_get(struct file *f, struct kobject *kobj,
 					  struct bin_attribute *attr, char *buf,
 					  loff_t ppos, size_t count)
@@ -1542,6 +1562,13 @@ int amdgpu_device_resize_fb_bar(struct amdgpu_device *adev)
 	if (amdgpu_sriov_vf(adev))
 		return 0;
 
+	/* resizing on Dell G5 SE platforms causes problems with runtime pm */
+	if ((amdgpu_runtime_pm != 0) &&
+	    adev->pdev->vendor == PCI_VENDOR_ID_ATI &&
+	    adev->pdev->device == 0x731f &&
+	    adev->pdev->subsystem_vendor == PCI_VENDOR_ID_DELL)
+		return 0;
+
 	/* PCI_EXT_CAP_ID_VNDR extended capability is located at 0x100 */
 	if (!pci_find_ext_capability(adev->pdev, PCI_EXT_CAP_ID_VNDR))
 		DRM_WARN("System can't access extended configuration space, please check!!\n");
@@ -3315,6 +3342,7 @@ static int amdgpu_device_ip_fini(struct amdgpu_device *adev)
 			amdgpu_device_mem_scratch_fini(adev);
 			amdgpu_ib_pool_fini(adev);
 			amdgpu_seq64_fini(adev);
+			amdgpu_doorbell_fini(adev);
 		}
 
 		r = adev->ip_blocks[i].version->funcs->sw_fini((void *)adev);
@@ -4020,11 +4048,6 @@ static bool amdgpu_device_check_iommu_remap(struct amdgpu_device *adev)
 }
 #endif
 
-static const struct attribute *amdgpu_dev_attributes[] = {
-	&dev_attr_pcie_replay_count.attr,
-	NULL
-};
-
 static void amdgpu_device_set_mcbp(struct amdgpu_device *adev)
 {
 	if (amdgpu_mcbp == 1)
@@ -4121,7 +4144,6 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	mutex_init(&adev->grbm_idx_mutex);
 	mutex_init(&adev->mn_lock);
 	mutex_init(&adev->virt.vf_errors.lock);
-	mutex_init(&adev->virt.rlcg_reg_lock);
 	hash_init(adev->mn_hash);
 	mutex_init(&adev->psp.mutex);
 	mutex_init(&adev->notifier_lock);
@@ -4147,6 +4169,7 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	spin_lock_init(&adev->se_cac_idx_lock);
 	spin_lock_init(&adev->audio_endpt_idx_lock);
 	spin_lock_init(&adev->mm_stats.lock);
+	spin_lock_init(&adev->virt.rlcg_reg_lock);
 	spin_lock_init(&adev->wb.lock);
 
 	INIT_LIST_HEAD(&adev->reset_list);
@@ -4467,7 +4490,7 @@ fence_driver_init:
 	} else
 		adev->ucode_sysfs_en = true;
 
-	r = sysfs_create_files(&adev->dev->kobj, amdgpu_dev_attributes);
+	r = amdgpu_device_attr_sysfs_init(adev);
 	if (r)
 		dev_err(adev->dev, "Could not create amdgpu device attr\n");
 
@@ -4511,6 +4534,11 @@ fence_driver_init:
 
 	amdgpu_device_check_iommu_direct_map(adev);
 
+	adev->pm_nb.notifier_call = amdgpu_device_pm_notifier;
+	r = register_pm_notifier(&adev->pm_nb);
+	if (r)
+		goto failed;
+
 	return 0;
 
 release_ras_con:
@@ -4575,6 +4603,8 @@ void amdgpu_device_fini_hw(struct amdgpu_device *adev)
 		drain_workqueue(adev->mman.bdev.wq);
 	adev->shutdown = true;
 
+	unregister_pm_notifier(&adev->pm_nb);
+
 	/* make sure IB test finished before entering exclusive mode
 	 * to avoid preemption on IB test
 	 */
@@ -4597,7 +4627,7 @@ void amdgpu_device_fini_hw(struct amdgpu_device *adev)
 		amdgpu_pm_sysfs_fini(adev);
 	if (adev->ucode_sysfs_en)
 		amdgpu_ucode_sysfs_fini(adev);
-	sysfs_remove_files(&adev->dev->kobj, amdgpu_dev_attributes);
+	amdgpu_device_attr_sysfs_fini(adev);
 	amdgpu_fru_sysfs_fini(adev);
 
 	amdgpu_reg_state_sysfs_fini(adev);
@@ -4647,6 +4677,9 @@ void amdgpu_device_fini_sw(struct amdgpu_device *adev)
 	kfree(adev->fru_info);
 	adev->fru_info = NULL;
 
+	kfree(adev->xcp_mgr);
+	adev->xcp_mgr = NULL;
+
 	px = amdgpu_device_supports_px(adev_to_drm(adev));
 
 	if (px || (!dev_is_removable(&adev->pdev->dev) &&
@@ -4663,7 +4696,6 @@ void amdgpu_device_fini_sw(struct amdgpu_device *adev)
 
 		iounmap(adev->rmmio);
 		adev->rmmio = NULL;
-		amdgpu_doorbell_fini(adev);
 		drm_dev_exit(idx);
 	}
 
@@ -4706,6 +4738,33 @@ static int amdgpu_device_evict_resources(struct amdgpu_device *adev)
  * Suspend & resume.
  */
 /**
+ * amdgpu_device_pm_notifier - Notification block for Suspend/Hibernate events
+ * @nb: notifier block
+ * @mode: suspend mode
+ * @data: data
+ *
+ * This function is called when the system is about to suspend or hibernate.
+ * It is used to set the appropriate flags so that eviction can be optimized
+ * in the pm prepare callback.
+ */
+static int amdgpu_device_pm_notifier(struct notifier_block *nb, unsigned long mode,
+				     void *data)
+{
+	struct amdgpu_device *adev = container_of(nb, struct amdgpu_device, pm_nb);
+
+	switch (mode) {
+	case PM_HIBERNATION_PREPARE:
+		adev->in_s4 = true;
+		break;
+	case PM_POST_HIBERNATION:
+		adev->in_s4 = false;
+		break;
+	}
+
+	return NOTIFY_DONE;
+}
+
+/**
  * amdgpu_device_prepare - prepare for device suspend
  *
  * @dev: drm dev pointer
@@ -4719,15 +4778,13 @@ int amdgpu_device_prepare(struct drm_device *dev)
 	struct amdgpu_device *adev = drm_to_adev(dev);
 	int i, r;
 
-	amdgpu_choose_low_power_state(adev);
-
 	if (dev->switch_power_state == DRM_SWITCH_POWER_OFF)
 		return 0;
 
 	/* Evict the majority of BOs before starting suspend sequence */
 	r = amdgpu_device_evict_resources(adev);
 	if (r)
-		goto unprepare;
+		return r;
 
 	flush_delayed_work(&adev->gfx.gfx_off_delay_work);
 
@@ -4738,15 +4795,10 @@ int amdgpu_device_prepare(struct drm_device *dev)
 			continue;
 		r = adev->ip_blocks[i].version->funcs->prepare_suspend((void *)adev);
 		if (r)
-			goto unprepare;
+			return r;
 	}
 
 	return 0;
-
-unprepare:
-	adev->in_s0ix = adev->in_s3 = false;
-
-	return r;
 }
 
 /**
@@ -4902,6 +4954,8 @@ exit:
 		dev->dev->power.disable_depth--;
 #endif
 	}
+
+	amdgpu_vram_mgr_clear_reset_blocks(adev);
 	adev->in_suspend = false;
 
 	if (adev->enable_mes)
@@ -5809,7 +5863,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 	 *
 	 * job->base holds a reference to parent fence
 	 */
-	if (job && dma_fence_is_signaled(&job->hw_fence)) {
+	if (job && dma_fence_is_signaled(&job->hw_fence.base)) {
 		job_signaled = true;
 		dev_info(adev->dev, "Guilty job already signaled, skipping HW reset");
 		goto skip_hw_reset;
@@ -6568,18 +6622,26 @@ struct dma_fence *amdgpu_device_switch_gang(struct amdgpu_device *adev,
 {
 	struct dma_fence *old = NULL;
 
+	dma_fence_get(gang);
 	do {
 		dma_fence_put(old);
 		old = amdgpu_device_get_gang(adev);
 		if (old == gang)
 			break;
 
-		if (!dma_fence_is_signaled(old))
+		if (!dma_fence_is_signaled(old)) {
+			dma_fence_put(gang);
 			return old;
+		}
 
 	} while (cmpxchg((struct dma_fence __force **)&adev->gang_submit,
 			 old, gang) != old);
 
+	/*
+	 * Drop it once for the exchanged reference in adev and once for the
+	 * thread local reference acquired in amdgpu_device_get_gang().
+	 */
+	dma_fence_put(old);
 	dma_fence_put(old);
 	return NULL;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
index ca8091fd3a24..eee434743deb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
@@ -111,8 +111,15 @@
 #include "amdgpu_isp.h"
 #endif
 
-#define FIRMWARE_IP_DISCOVERY "amdgpu/ip_discovery.bin"
-MODULE_FIRMWARE(FIRMWARE_IP_DISCOVERY);
+MODULE_FIRMWARE("amdgpu/ip_discovery.bin");
+MODULE_FIRMWARE("amdgpu/vega10_ip_discovery.bin");
+MODULE_FIRMWARE("amdgpu/vega12_ip_discovery.bin");
+MODULE_FIRMWARE("amdgpu/vega20_ip_discovery.bin");
+MODULE_FIRMWARE("amdgpu/raven_ip_discovery.bin");
+MODULE_FIRMWARE("amdgpu/raven2_ip_discovery.bin");
+MODULE_FIRMWARE("amdgpu/picasso_ip_discovery.bin");
+MODULE_FIRMWARE("amdgpu/arcturus_ip_discovery.bin");
+MODULE_FIRMWARE("amdgpu/aldebaran_ip_discovery.bin");
 
 #define mmIP_DISCOVERY_VERSION  0x16A00
 #define mmRCC_CONFIG_MEMSIZE	0xde3
@@ -295,25 +302,19 @@ static int amdgpu_discovery_read_binary_from_mem(struct amdgpu_device *adev,
 	return ret;
 }
 
-static int amdgpu_discovery_read_binary_from_file(struct amdgpu_device *adev, uint8_t *binary)
+static int amdgpu_discovery_read_binary_from_file(struct amdgpu_device *adev,
+							uint8_t *binary,
+							const char *fw_name)
 {
 	const struct firmware *fw;
-	const char *fw_name;
 	int r;
 
-	switch (amdgpu_discovery) {
-	case 2:
-		fw_name = FIRMWARE_IP_DISCOVERY;
-		break;
-	default:
-		dev_warn(adev->dev, "amdgpu_discovery is not set properly\n");
-		return -EINVAL;
-	}
-
-	r = request_firmware(&fw, fw_name, adev->dev);
+	r = firmware_request_nowarn(&fw, fw_name, adev->dev);
 	if (r) {
-		dev_err(adev->dev, "can't load firmware \"%s\"\n",
-			fw_name);
+		if (amdgpu_discovery == 2)
+			dev_err(adev->dev, "can't load firmware \"%s\"\n", fw_name);
+		else
+			drm_info(&adev->ddev, "Optional firmware \"%s\" was not found\n", fw_name);
 		return r;
 	}
 
@@ -402,10 +403,39 @@ static int amdgpu_discovery_verify_npsinfo(struct amdgpu_device *adev,
 	return 0;
 }
 
+static const char *amdgpu_discovery_get_fw_name(struct amdgpu_device *adev)
+{
+	if (amdgpu_discovery == 2)
+		return "amdgpu/ip_discovery.bin";
+
+	switch (adev->asic_type) {
+	case CHIP_VEGA10:
+		return "amdgpu/vega10_ip_discovery.bin";
+	case CHIP_VEGA12:
+		return "amdgpu/vega12_ip_discovery.bin";
+	case CHIP_RAVEN:
+		if (adev->apu_flags & AMD_APU_IS_RAVEN2)
+			return "amdgpu/raven2_ip_discovery.bin";
+		else if (adev->apu_flags & AMD_APU_IS_PICASSO)
+			return "amdgpu/picasso_ip_discovery.bin";
+		else
+			return "amdgpu/raven_ip_discovery.bin";
+	case CHIP_VEGA20:
+		return "amdgpu/vega20_ip_discovery.bin";
+	case CHIP_ARCTURUS:
+		return "amdgpu/arcturus_ip_discovery.bin";
+	case CHIP_ALDEBARAN:
+		return "amdgpu/aldebaran_ip_discovery.bin";
+	default:
+		return NULL;
+	}
+}
+
 static int amdgpu_discovery_init(struct amdgpu_device *adev)
 {
 	struct table_info *info;
 	struct binary_header *bhdr;
+	const char *fw_name;
 	uint16_t offset;
 	uint16_t size;
 	uint16_t checksum;
@@ -417,17 +447,14 @@ static int amdgpu_discovery_init(struct amdgpu_device *adev)
 		return -ENOMEM;
 
 	/* Read from file if it is the preferred option */
-	if (amdgpu_discovery == 2) {
-		dev_info(adev->dev, "use ip discovery information from file");
-		r = amdgpu_discovery_read_binary_from_file(adev, adev->mman.discovery_bin);
-
-		if (r) {
-			dev_err(adev->dev, "failed to read ip discovery binary from file\n");
-			r = -EINVAL;
+	fw_name = amdgpu_discovery_get_fw_name(adev);
+	if (fw_name != NULL) {
+		drm_dbg(&adev->ddev, "use ip discovery information from file");
+		r = amdgpu_discovery_read_binary_from_file(adev, adev->mman.discovery_bin, fw_name);
+		if (r)
 			goto out;
-		}
-
 	} else {
+		drm_dbg(&adev->ddev, "use ip discovery information from memory");
 		r = amdgpu_discovery_read_binary_from_mem(
 			adev, adev->mman.discovery_bin);
 		if (r)
@@ -1285,10 +1312,8 @@ static int amdgpu_discovery_reg_base_init(struct amdgpu_device *adev)
 	int r;
 
 	r = amdgpu_discovery_init(adev);
-	if (r) {
-		DRM_ERROR("amdgpu_discovery_init failed\n");
+	if (r)
 		return r;
-	}
 
 	adev->gfx.xcc_mask = 0;
 	adev->sdma.sdma_mask = 0;
@@ -2430,6 +2455,40 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev)
 
 	switch (adev->asic_type) {
 	case CHIP_VEGA10:
+	case CHIP_VEGA12:
+	case CHIP_RAVEN:
+	case CHIP_VEGA20:
+	case CHIP_ARCTURUS:
+	case CHIP_ALDEBARAN:
+		/* this is not fatal.  We have a fallback below
+		 * if the new firmwares are not present. some of
+		 * this will be overridden below to keep things
+		 * consistent with the current behavior.
+		 */
+		r = amdgpu_discovery_reg_base_init(adev);
+		if (!r) {
+			amdgpu_discovery_harvest_ip(adev);
+			amdgpu_discovery_get_gfx_info(adev);
+			amdgpu_discovery_get_mall_info(adev);
+			amdgpu_discovery_get_vcn_info(adev);
+		}
+		break;
+	default:
+		r = amdgpu_discovery_reg_base_init(adev);
+		if (r) {
+			drm_err(&adev->ddev, "discovery failed: %d\n", r);
+			return r;
+		}
+
+		amdgpu_discovery_harvest_ip(adev);
+		amdgpu_discovery_get_gfx_info(adev);
+		amdgpu_discovery_get_mall_info(adev);
+		amdgpu_discovery_get_vcn_info(adev);
+		break;
+	}
+
+	switch (adev->asic_type) {
+	case CHIP_VEGA10:
 		vega10_reg_base_init(adev);
 		adev->sdma.num_instances = 2;
 		adev->gmc.num_umc = 4;
@@ -2590,14 +2649,6 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev)
 		adev->ip_versions[XGMI_HWIP][0] = IP_VERSION(6, 1, 0);
 		break;
 	default:
-		r = amdgpu_discovery_reg_base_init(adev);
-		if (r)
-			return -EINVAL;
-
-		amdgpu_discovery_harvest_ip(adev);
-		amdgpu_discovery_get_gfx_info(adev);
-		amdgpu_discovery_get_mall_info(adev);
-		amdgpu_discovery_get_vcn_info(adev);
 		break;
 	}
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
index 8e81a83d37d8..e63a32c21447 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
@@ -42,6 +42,29 @@
 #include <linux/dma-fence-array.h>
 #include <linux/pci-p2pdma.h>
 
+static const struct dma_buf_attach_ops amdgpu_dma_buf_attach_ops;
+
+/**
+ * dma_buf_attach_adev - Helper to get adev of an attachment
+ *
+ * @attach: attachment
+ *
+ * Returns:
+ * A struct amdgpu_device * if the attaching device is an amdgpu device or
+ * partition, NULL otherwise.
+ */
+static struct amdgpu_device *dma_buf_attach_adev(struct dma_buf_attachment *attach)
+{
+	if (attach->importer_ops == &amdgpu_dma_buf_attach_ops) {
+		struct drm_gem_object *obj = attach->importer_priv;
+		struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
+
+		return amdgpu_ttm_adev(bo->tbo.bdev);
+	}
+
+	return NULL;
+}
+
 /**
  * amdgpu_dma_buf_attach - &dma_buf_ops.attach implementation
  *
@@ -53,11 +76,13 @@
 static int amdgpu_dma_buf_attach(struct dma_buf *dmabuf,
 				 struct dma_buf_attachment *attach)
 {
+	struct amdgpu_device *attach_adev = dma_buf_attach_adev(attach);
 	struct drm_gem_object *obj = dmabuf->priv;
 	struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
 
-	if (pci_p2pdma_distance(adev->pdev, attach->dev, false) < 0)
+	if (!amdgpu_dmabuf_is_xgmi_accessible(attach_adev, bo) &&
+	    pci_p2pdma_distance(adev->pdev, attach->dev, false) < 0)
 		attach->peer2peer = false;
 
 	return 0;
@@ -181,7 +206,7 @@ static void amdgpu_dma_buf_unmap(struct dma_buf_attachment *attach,
 				 struct sg_table *sgt,
 				 enum dma_data_direction dir)
 {
-	if (sgt->sgl->page_link) {
+	if (sg_page(sgt->sgl)) {
 		dma_unmap_sgtable(attach->dev, sgt, dir, 0);
 		sg_free_table(sgt);
 		kfree(sgt);
@@ -456,6 +481,9 @@ bool amdgpu_dmabuf_is_xgmi_accessible(struct amdgpu_device *adev,
 	struct drm_gem_object *obj = &bo->tbo.base;
 	struct drm_gem_object *gobj;
 
+	if (!adev)
+		return false;
+
 	if (obj->import_attach) {
 		struct dma_buf *dma_buf = obj->import_attach->dmabuf;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 81d9877c8735..93c3de2d27d3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -118,9 +118,11 @@
  * - 3.57.0 - Compute tunneling on GFX10+
  * - 3.58.0 - Add GFX12 DCC support
  * - 3.59.0 - Cleared VRAM
+ * - 3.60.0 - Add AMDGPU_TILING_GFX12_DCC_WRITE_COMPRESS_DISABLE (Vulkan requirement)
+ * - 3.61.0 - Contains fix for RV/PCO compute queues
  */
 #define KMS_DRIVER_MAJOR	3
-#define KMS_DRIVER_MINOR	59
+#define KMS_DRIVER_MINOR	61
 #define KMS_DRIVER_PATCHLEVEL	0
 
 /*
@@ -170,6 +172,7 @@ uint amdgpu_sdma_phase_quantum = 32;
 char *amdgpu_disable_cu;
 char *amdgpu_virtual_display;
 bool enforce_isolation;
+int amdgpu_modeset = -1;
 
 /* Specifies the default granularity for SVM, used in buffer
  * migration and restoration of backing memory when handling
@@ -1036,6 +1039,13 @@ module_param(enforce_isolation, bool, 0444);
 MODULE_PARM_DESC(enforce_isolation, "enforce process isolation between graphics and compute . enforce_isolation = on");
 
 /**
+ * DOC: modeset (int)
+ * Override nomodeset (1 = override, -1 = auto). The default is -1 (auto).
+ */
+MODULE_PARM_DESC(modeset, "Override nomodeset (1 = enable, -1 = auto)");
+module_param_named(modeset, amdgpu_modeset, int, 0444);
+
+/**
  * DOC: seamless (int)
  * Seamless boot will keep the image on the screen during the boot process.
  */
@@ -1793,7 +1803,6 @@ static const u16 amdgpu_unsupported_pciidlist[] = {
 };
 
 static const struct pci_device_id pciidlist[] = {
-#ifdef CONFIG_DRM_AMDGPU_SI
 	{0x1002, 0x6780, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TAHITI},
 	{0x1002, 0x6784, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TAHITI},
 	{0x1002, 0x6788, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TAHITI},
@@ -1866,8 +1875,6 @@ static const struct pci_device_id pciidlist[] = {
 	{0x1002, 0x6665, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_HAINAN|AMD_IS_MOBILITY},
 	{0x1002, 0x6667, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_HAINAN|AMD_IS_MOBILITY},
 	{0x1002, 0x666F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_HAINAN|AMD_IS_MOBILITY},
-#endif
-#ifdef CONFIG_DRM_AMDGPU_CIK
 	/* Kaveri */
 	{0x1002, 0x1304, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_KAVERI|AMD_IS_MOBILITY|AMD_IS_APU},
 	{0x1002, 0x1305, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_KAVERI|AMD_IS_APU},
@@ -1950,7 +1957,6 @@ static const struct pci_device_id pciidlist[] = {
 	{0x1002, 0x985D, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_MULLINS|AMD_IS_MOBILITY|AMD_IS_APU},
 	{0x1002, 0x985E, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_MULLINS|AMD_IS_MOBILITY|AMD_IS_APU},
 	{0x1002, 0x985F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_MULLINS|AMD_IS_MOBILITY|AMD_IS_APU},
-#endif
 	/* topaz */
 	{0x1002, 0x6900, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TOPAZ},
 	{0x1002, 0x6901, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TOPAZ},
@@ -2250,6 +2256,12 @@ static int amdgpu_pci_probe(struct pci_dev *pdev,
 	int ret, retry = 0, i;
 	bool supports_atomic = false;
 
+	if ((pdev->class >> 8) == PCI_CLASS_DISPLAY_VGA ||
+	    (pdev->class >> 8) == PCI_CLASS_DISPLAY_OTHER) {
+		if (drm_firmware_drivers_only() && amdgpu_modeset == -1)
+			return -EINVAL;
+	}
+
 	/* skip devices which are owned by radeon */
 	for (i = 0; i < ARRAY_SIZE(amdgpu_unsupported_pciidlist); i++) {
 		if (amdgpu_unsupported_pciidlist[i] == pdev->device)
@@ -2282,14 +2294,14 @@ static int amdgpu_pci_probe(struct pci_dev *pdev,
 		return -ENOTSUPP;
 	}
 
+	switch (flags & AMD_ASIC_MASK) {
+	case CHIP_TAHITI:
+	case CHIP_PITCAIRN:
+	case CHIP_VERDE:
+	case CHIP_OLAND:
+	case CHIP_HAINAN:
 #ifdef CONFIG_DRM_AMDGPU_SI
-	if (!amdgpu_si_support) {
-		switch (flags & AMD_ASIC_MASK) {
-		case CHIP_TAHITI:
-		case CHIP_PITCAIRN:
-		case CHIP_VERDE:
-		case CHIP_OLAND:
-		case CHIP_HAINAN:
+		if (!amdgpu_si_support) {
 			dev_info(&pdev->dev,
 				 "SI support provided by radeon.\n");
 			dev_info(&pdev->dev,
@@ -2297,16 +2309,18 @@ static int amdgpu_pci_probe(struct pci_dev *pdev,
 				);
 			return -ENODEV;
 		}
-	}
+		break;
+#else
+		dev_info(&pdev->dev, "amdgpu is built without SI support.\n");
+		return -ENODEV;
 #endif
+	case CHIP_KAVERI:
+	case CHIP_BONAIRE:
+	case CHIP_HAWAII:
+	case CHIP_KABINI:
+	case CHIP_MULLINS:
 #ifdef CONFIG_DRM_AMDGPU_CIK
-	if (!amdgpu_cik_support) {
-		switch (flags & AMD_ASIC_MASK) {
-		case CHIP_KAVERI:
-		case CHIP_BONAIRE:
-		case CHIP_HAWAII:
-		case CHIP_KABINI:
-		case CHIP_MULLINS:
+		if (!amdgpu_cik_support) {
 			dev_info(&pdev->dev,
 				 "CIK support provided by radeon.\n");
 			dev_info(&pdev->dev,
@@ -2314,8 +2328,14 @@ static int amdgpu_pci_probe(struct pci_dev *pdev,
 				);
 			return -ENODEV;
 		}
-	}
+		break;
+#else
+		dev_info(&pdev->dev, "amdgpu is built without CIK support.\n");
+		return -ENODEV;
 #endif
+	default:
+		break;
+	}
 
 	adev = devm_drm_dev_alloc(&pdev->dev, &amdgpu_kms_driver, typeof(*adev), ddev);
 	if (IS_ERR(adev))
@@ -2629,9 +2649,7 @@ static int amdgpu_pmops_freeze(struct device *dev)
 	struct amdgpu_device *adev = drm_to_adev(drm_dev);
 	int r;
 
-	adev->in_s4 = true;
 	r = amdgpu_device_suspend(drm_dev, true);
-	adev->in_s4 = false;
 	if (r)
 		return r;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index 2f24a6aa13bf..569e0e537392 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -41,22 +41,6 @@
 #include "amdgpu_trace.h"
 #include "amdgpu_reset.h"
 
-/*
- * Fences mark an event in the GPUs pipeline and are used
- * for GPU/CPU synchronization.  When the fence is written,
- * it is expected that all buffers associated with that fence
- * are no longer in use by the associated ring on the GPU and
- * that the relevant GPU caches have been flushed.
- */
-
-struct amdgpu_fence {
-	struct dma_fence base;
-
-	/* RB, DMA, etc. */
-	struct amdgpu_ring		*ring;
-	ktime_t				start_timestamp;
-};
-
 static struct kmem_cache *amdgpu_fence_slab;
 
 int amdgpu_fence_slab_init(void)
@@ -151,12 +135,12 @@ int amdgpu_fence_emit(struct amdgpu_ring *ring, struct dma_fence **f, struct amd
 		am_fence = kmem_cache_alloc(amdgpu_fence_slab, GFP_ATOMIC);
 		if (am_fence == NULL)
 			return -ENOMEM;
-		fence = &am_fence->base;
-		am_fence->ring = ring;
 	} else {
 		/* take use of job-embedded fence */
-		fence = &job->hw_fence;
+		am_fence = &job->hw_fence;
 	}
+	fence = &am_fence->base;
+	am_fence->ring = ring;
 
 	seq = ++ring->fence_drv.sync_seq;
 	if (job && job->job_run_counter) {
@@ -718,7 +702,7 @@ void amdgpu_fence_driver_clear_job_fences(struct amdgpu_ring *ring)
 			 * it right here or we won't be able to track them in fence_drv
 			 * and they will remain unsignaled during sa_bo free.
 			 */
-			job = container_of(old, struct amdgpu_job, hw_fence);
+			job = container_of(old, struct amdgpu_job, hw_fence.base);
 			if (!job->base.s_fence && !dma_fence_is_signaled(old))
 				dma_fence_signal(old);
 			RCU_INIT_POINTER(*ptr, NULL);
@@ -780,7 +764,7 @@ static const char *amdgpu_fence_get_timeline_name(struct dma_fence *f)
 
 static const char *amdgpu_job_fence_get_timeline_name(struct dma_fence *f)
 {
-	struct amdgpu_job *job = container_of(f, struct amdgpu_job, hw_fence);
+	struct amdgpu_job *job = container_of(f, struct amdgpu_job, hw_fence.base);
 
 	return (const char *)to_amdgpu_ring(job->base.sched)->name;
 }
@@ -810,7 +794,7 @@ static bool amdgpu_fence_enable_signaling(struct dma_fence *f)
  */
 static bool amdgpu_job_fence_enable_signaling(struct dma_fence *f)
 {
-	struct amdgpu_job *job = container_of(f, struct amdgpu_job, hw_fence);
+	struct amdgpu_job *job = container_of(f, struct amdgpu_job, hw_fence.base);
 
 	if (!timer_pending(&to_amdgpu_ring(job->base.sched)->fence_drv.fallback_timer))
 		amdgpu_fence_schedule_fallback(to_amdgpu_ring(job->base.sched));
@@ -845,7 +829,7 @@ static void amdgpu_job_fence_free(struct rcu_head *rcu)
 	struct dma_fence *f = container_of(rcu, struct dma_fence, rcu);
 
 	/* free job if fence has a parent job */
-	kfree(container_of(f, struct amdgpu_job, hw_fence));
+	kfree(container_of(f, struct amdgpu_job, hw_fence.base));
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
index 156abd2ba5a6..3c2ac5f4e814 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
@@ -1426,9 +1426,11 @@ static int amdgpu_gfx_run_cleaner_shader_job(struct amdgpu_ring *ring)
 	struct amdgpu_device *adev = ring->adev;
 	struct drm_gpu_scheduler *sched = &ring->sched;
 	struct drm_sched_entity entity;
+	static atomic_t counter;
 	struct dma_fence *f;
 	struct amdgpu_job *job;
 	struct amdgpu_ib *ib;
+	void *owner;
 	int i, r;
 
 	/* Initialize the scheduler entity */
@@ -1439,9 +1441,15 @@ static int amdgpu_gfx_run_cleaner_shader_job(struct amdgpu_ring *ring)
 		goto err;
 	}
 
-	r = amdgpu_job_alloc_with_ib(ring->adev, &entity, NULL,
-				     64, 0,
-				     &job);
+	/*
+	 * Use some unique dummy value as the owner to make sure we execute
+	 * the cleaner shader on each submission. The value just need to change
+	 * for each submission and is otherwise meaningless.
+	 */
+	owner = (void *)(unsigned long)atomic_inc_return(&counter);
+
+	r = amdgpu_job_alloc_with_ib(ring->adev, &entity, owner,
+				     64, 0, &job);
 	if (r)
 		goto err;
 
@@ -1837,6 +1845,7 @@ void amdgpu_gfx_enforce_isolation_ring_begin_use(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
 	u32 idx;
+	bool sched_work = false;
 
 	if (!adev->gfx.enable_cleaner_shader)
 		return;
@@ -1852,15 +1861,19 @@ void amdgpu_gfx_enforce_isolation_ring_begin_use(struct amdgpu_ring *ring)
 	mutex_lock(&adev->enforce_isolation_mutex);
 	if (adev->enforce_isolation[idx]) {
 		if (adev->kfd.init_complete)
-			amdgpu_gfx_kfd_sch_ctrl(adev, idx, false);
+			sched_work = true;
 	}
 	mutex_unlock(&adev->enforce_isolation_mutex);
+
+	if (sched_work)
+		amdgpu_gfx_kfd_sch_ctrl(adev, idx, false);
 }
 
 void amdgpu_gfx_enforce_isolation_ring_end_use(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
 	u32 idx;
+	bool sched_work = false;
 
 	if (!adev->gfx.enable_cleaner_shader)
 		return;
@@ -1876,7 +1889,10 @@ void amdgpu_gfx_enforce_isolation_ring_end_use(struct amdgpu_ring *ring)
 	mutex_lock(&adev->enforce_isolation_mutex);
 	if (adev->enforce_isolation[idx]) {
 		if (adev->kfd.init_complete)
-			amdgpu_gfx_kfd_sch_ctrl(adev, idx, true);
+			sched_work = true;
 	}
 	mutex_unlock(&adev->enforce_isolation_mutex);
+
+	if (sched_work)
+		amdgpu_gfx_kfd_sch_ctrl(adev, idx, true);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
index 17a19d49d30a..9d130d3af0b3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
@@ -678,12 +678,10 @@ int amdgpu_gmc_flush_gpu_tlb_pasid(struct amdgpu_device *adev, uint16_t pasid,
 				   uint32_t flush_type, bool all_hub,
 				   uint32_t inst)
 {
-	u32 usec_timeout = amdgpu_sriov_vf(adev) ? SRIOV_USEC_TIMEOUT :
-		adev->usec_timeout;
 	struct amdgpu_ring *ring = &adev->gfx.kiq[inst].ring;
 	struct amdgpu_kiq *kiq = &adev->gfx.kiq[inst];
 	unsigned int ndw;
-	int r;
+	int r, cnt = 0;
 	uint32_t seq;
 
 	/*
@@ -740,10 +738,21 @@ int amdgpu_gmc_flush_gpu_tlb_pasid(struct amdgpu_device *adev, uint16_t pasid,
 
 		amdgpu_ring_commit(ring);
 		spin_unlock(&adev->gfx.kiq[inst].ring_lock);
-		if (amdgpu_fence_wait_polling(ring, seq, usec_timeout) < 1) {
+
+		r = amdgpu_fence_wait_polling(ring, seq, MAX_KIQ_REG_WAIT);
+
+		might_sleep();
+		while (r < 1 && cnt++ < MAX_KIQ_REG_TRY &&
+		       !amdgpu_reset_pending(adev->reset_domain)) {
+			msleep(MAX_KIQ_REG_BAILOUT_INTERVAL);
+			r = amdgpu_fence_wait_polling(ring, seq, MAX_KIQ_REG_WAIT);
+		}
+
+		if (cnt > MAX_KIQ_REG_TRY) {
 			dev_err(adev->dev, "timeout waiting for kiq fence\n");
 			r = -ETIME;
-		}
+		} else
+			r = 0;
 	}
 
 error_unlock_reset:
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.h
index 508f02eb0cf8..7de10208e8dd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.h
@@ -78,6 +78,9 @@ struct amdgpu_ih_ring {
 #define amdgpu_ih_ts_after(t1, t2) \
 		(((int64_t)((t2) << 16) - (int64_t)((t1) << 16)) > 0LL)
 
+#define amdgpu_ih_ts_after_or_equal(t1, t2) \
+		(((int64_t)((t2) << 16) - (int64_t)((t1) << 16)) >= 0LL)
+
 /* provided by the ih block */
 struct amdgpu_ih_funcs {
 	/* ring read/write ptr handling, called from interrupt context */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index 1ce20a19be8b..7e6057a6e7f1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -259,8 +259,8 @@ void amdgpu_job_free_resources(struct amdgpu_job *job)
 	/* Check if any fences where initialized */
 	if (job->base.s_fence && job->base.s_fence->finished.ops)
 		f = &job->base.s_fence->finished;
-	else if (job->hw_fence.ops)
-		f = &job->hw_fence;
+	else if (job->hw_fence.base.ops)
+		f = &job->hw_fence.base;
 	else
 		f = NULL;
 
@@ -277,10 +277,10 @@ static void amdgpu_job_free_cb(struct drm_sched_job *s_job)
 	amdgpu_sync_free(&job->explicit_sync);
 
 	/* only put the hw fence if has embedded fence */
-	if (!job->hw_fence.ops)
+	if (!job->hw_fence.base.ops)
 		kfree(job);
 	else
-		dma_fence_put(&job->hw_fence);
+		dma_fence_put(&job->hw_fence.base);
 }
 
 void amdgpu_job_set_gang_leader(struct amdgpu_job *job,
@@ -309,10 +309,10 @@ void amdgpu_job_free(struct amdgpu_job *job)
 	if (job->gang_submit != &job->base.s_fence->scheduled)
 		dma_fence_put(job->gang_submit);
 
-	if (!job->hw_fence.ops)
+	if (!job->hw_fence.base.ops)
 		kfree(job);
 	else
-		dma_fence_put(&job->hw_fence);
+		dma_fence_put(&job->hw_fence.base);
 }
 
 struct dma_fence *amdgpu_job_submit(struct amdgpu_job *job)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h
index ce6b9ba967ff..4fe033d8f356 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h
@@ -48,7 +48,7 @@ struct amdgpu_job {
 	struct drm_sched_job    base;
 	struct amdgpu_vm	*vm;
 	struct amdgpu_sync	explicit_sync;
-	struct dma_fence	hw_fence;
+	struct amdgpu_fence	hw_fence;
 	struct dma_fence	*gang_submit;
 	uint32_t		preamble_status;
 	uint32_t                preemption_status;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
index 7d4b540340e0..41b88e0ea98b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
@@ -860,7 +860,9 @@ int amdgpu_mes_map_legacy_queue(struct amdgpu_device *adev,
 	queue_input.mqd_addr = amdgpu_bo_gpu_offset(ring->mqd_obj);
 	queue_input.wptr_addr = ring->wptr_gpu_addr;
 
+	amdgpu_mes_lock(&adev->mes);
 	r = adev->mes.funcs->map_legacy_queue(&adev->mes, &queue_input);
+	amdgpu_mes_unlock(&adev->mes);
 	if (r)
 		DRM_ERROR("failed to map legacy queue\n");
 
@@ -883,7 +885,9 @@ int amdgpu_mes_unmap_legacy_queue(struct amdgpu_device *adev,
 	queue_input.trail_fence_addr = gpu_addr;
 	queue_input.trail_fence_data = seq;
 
+	amdgpu_mes_lock(&adev->mes);
 	r = adev->mes.funcs->unmap_legacy_queue(&adev->mes, &queue_input);
+	amdgpu_mes_unlock(&adev->mes);
 	if (r)
 		DRM_ERROR("failed to unmap legacy queue\n");
 
@@ -910,7 +914,9 @@ int amdgpu_mes_reset_legacy_queue(struct amdgpu_device *adev,
 	queue_input.vmid = vmid;
 	queue_input.use_mmio = use_mmio;
 
+	amdgpu_mes_lock(&adev->mes);
 	r = adev->mes.funcs->reset_legacy_queue(&adev->mes, &queue_input);
+	amdgpu_mes_unlock(&adev->mes);
 	if (r)
 		DRM_ERROR("failed to reset legacy queue\n");
 
@@ -931,7 +937,9 @@ uint32_t amdgpu_mes_rreg(struct amdgpu_device *adev, uint32_t reg)
 		goto error;
 	}
 
+	amdgpu_mes_lock(&adev->mes);
 	r = adev->mes.funcs->misc_op(&adev->mes, &op_input);
+	amdgpu_mes_unlock(&adev->mes);
 	if (r)
 		DRM_ERROR("failed to read reg (0x%x)\n", reg);
 	else
@@ -957,7 +965,9 @@ int amdgpu_mes_wreg(struct amdgpu_device *adev,
 		goto error;
 	}
 
+	amdgpu_mes_lock(&adev->mes);
 	r = adev->mes.funcs->misc_op(&adev->mes, &op_input);
+	amdgpu_mes_unlock(&adev->mes);
 	if (r)
 		DRM_ERROR("failed to write reg (0x%x)\n", reg);
 
@@ -984,7 +994,9 @@ int amdgpu_mes_reg_write_reg_wait(struct amdgpu_device *adev,
 		goto error;
 	}
 
+	amdgpu_mes_lock(&adev->mes);
 	r = adev->mes.funcs->misc_op(&adev->mes, &op_input);
+	amdgpu_mes_unlock(&adev->mes);
 	if (r)
 		DRM_ERROR("failed to reg_write_reg_wait\n");
 
@@ -1009,7 +1021,9 @@ int amdgpu_mes_reg_wait(struct amdgpu_device *adev, uint32_t reg,
 		goto error;
 	}
 
+	amdgpu_mes_lock(&adev->mes);
 	r = adev->mes.funcs->misc_op(&adev->mes, &op_input);
+	amdgpu_mes_unlock(&adev->mes);
 	if (r)
 		DRM_ERROR("failed to reg_write_reg_wait\n");
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 971419e3a9bb..fc588ef598c0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -161,8 +161,8 @@ 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 &&
-		    !(adev->flags & AMD_IS_APU))
+		if (abo->tbo.resource && !(adev->flags & AMD_IS_APU) &&
+		    domain & abo->preferred_domains & AMDGPU_GEM_DOMAIN_VRAM)
 			places[c].flags |= TTM_PL_FLAG_FALLBACK;
 		c++;
 	}
@@ -1246,28 +1246,36 @@ void amdgpu_bo_release_notify(struct ttm_buffer_object *bo)
 	if (abo->kfd_bo)
 		amdgpu_amdkfd_release_notify(abo);
 
-	/* We only remove the fence if the resv has individualized. */
-	WARN_ON_ONCE(bo->type == ttm_bo_type_kernel
-			&& bo->base.resv != &bo->base._resv);
-	if (bo->base.resv == &bo->base._resv)
-		amdgpu_amdkfd_remove_fence_on_pt_pd_bos(abo);
+	/*
+	 * We lock the private dma_resv object here and since the BO is about to
+	 * be released nobody else should have a pointer to it.
+	 * So when this locking here fails something is wrong with the reference
+	 * counting.
+	 */
+	if (WARN_ON_ONCE(!dma_resv_trylock(&bo->base._resv)))
+		return;
+
+	amdgpu_amdkfd_remove_all_eviction_fences(abo);
 
 	if (!bo->resource || bo->resource->mem_type != TTM_PL_VRAM ||
 	    !(abo->flags & AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE) ||
 	    adev->in_suspend || drm_dev_is_unplugged(adev_to_drm(adev)))
-		return;
+		goto out;
 
-	if (WARN_ON_ONCE(!dma_resv_trylock(bo->base.resv)))
-		return;
+	r = dma_resv_reserve_fences(&bo->base._resv, 1);
+	if (r)
+		goto out;
 
-	r = amdgpu_fill_buffer(abo, 0, bo->base.resv, &fence, true);
-	if (!WARN_ON(r)) {
-		amdgpu_vram_mgr_set_cleared(bo->resource);
-		amdgpu_bo_fence(abo, fence, false);
-		dma_fence_put(fence);
-	}
+	r = amdgpu_fill_buffer(abo, 0, &bo->base._resv, &fence, true);
+	if (WARN_ON(r))
+		goto out;
+
+	amdgpu_vram_mgr_set_cleared(bo->resource);
+	dma_resv_add_fence(&bo->base._resv, fence, DMA_RESV_USAGE_KERNEL);
+	dma_fence_put(fence);
 
-	dma_resv_unlock(bo->base.resv);
+out:
+	dma_resv_unlock(&bo->base._resv);
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 0b28b2cf1517..3d42f6c3308e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -44,7 +44,7 @@
 #include "amdgpu_securedisplay.h"
 #include "amdgpu_atomfirmware.h"
 
-#define AMD_VBIOS_FILE_MAX_SIZE_B      (1024*1024*3)
+#define AMD_VBIOS_FILE_MAX_SIZE_B      (1024*1024*16)
 
 static int psp_load_smu_fw(struct psp_context *psp);
 static int psp_rap_terminate(struct psp_context *psp);
@@ -531,7 +531,6 @@ static int psp_sw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 	struct psp_context *psp = &adev->psp;
-	struct psp_gfx_cmd_resp *cmd = psp->cmd;
 
 	psp_memory_training_fini(psp);
 
@@ -541,8 +540,8 @@ static int psp_sw_fini(void *handle)
 	amdgpu_ucode_release(&psp->cap_fw);
 	amdgpu_ucode_release(&psp->toc_fw);
 
-	kfree(cmd);
-	cmd = NULL;
+	kfree(psp->cmd);
+	psp->cmd = NULL;
 
 	psp_free_shared_bufs(psp);
 
@@ -3431,7 +3430,10 @@ int psp_init_sos_microcode(struct psp_context *psp, const char *chip_name)
 	uint8_t *ucode_array_start_addr;
 	int err = 0;
 
-	err = amdgpu_ucode_request(adev, &adev->psp.sos_fw, "amdgpu/%s_sos.bin", chip_name);
+	if (amdgpu_is_kicker_fw(adev))
+		err = amdgpu_ucode_request(adev, &adev->psp.sos_fw, "amdgpu/%s_sos_kicker.bin", chip_name);
+	else
+		err = amdgpu_ucode_request(adev, &adev->psp.sos_fw, "amdgpu/%s_sos.bin", chip_name);
 	if (err)
 		goto out;
 
@@ -3673,7 +3675,10 @@ int psp_init_ta_microcode(struct psp_context *psp, const char *chip_name)
 	struct amdgpu_device *adev = psp->adev;
 	int err;
 
-	err = amdgpu_ucode_request(adev, &adev->psp.ta_fw, "amdgpu/%s_ta.bin", chip_name);
+	if (amdgpu_is_kicker_fw(adev))
+		err = amdgpu_ucode_request(adev, &adev->psp.ta_fw, "amdgpu/%s_ta_kicker.bin", chip_name);
+	else
+		err = amdgpu_ucode_request(adev, &adev->psp.ta_fw, "amdgpu/%s_ta.bin", chip_name);
 	if (err)
 		return err;
 
@@ -3713,9 +3718,10 @@ int psp_init_cap_microcode(struct psp_context *psp, const char *chip_name)
 		if (err == -ENODEV) {
 			dev_warn(adev->dev, "cap microcode does not exist, skip\n");
 			err = 0;
-			goto out;
+		} else {
+			dev_err(adev->dev, "fail to initialize cap microcode\n");
 		}
-		dev_err(adev->dev, "fail to initialize cap microcode\n");
+		goto out;
 	}
 
 	info = &adev->firmware.ucode[AMDGPU_UCODE_ID_CAP];
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
index 690976665cf6..10da6e550d76 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
@@ -439,6 +439,7 @@ bool amdgpu_ring_soft_recovery(struct amdgpu_ring *ring, unsigned int vmid,
 {
 	unsigned long flags;
 	ktime_t deadline;
+	bool ret;
 
 	if (unlikely(ring->adev->debug_disable_soft_recovery))
 		return false;
@@ -453,12 +454,16 @@ bool amdgpu_ring_soft_recovery(struct amdgpu_ring *ring, unsigned int vmid,
 		dma_fence_set_error(fence, -ENODATA);
 	spin_unlock_irqrestore(fence->lock, flags);
 
-	atomic_inc(&ring->adev->gpu_reset_counter);
 	while (!dma_fence_is_signaled(fence) &&
 	       ktime_to_ns(ktime_sub(deadline, ktime_get())) > 0)
 		ring->funcs->soft_recovery(ring, vmid);
 
-	return dma_fence_is_signaled(fence);
+	ret = dma_fence_is_signaled(fence);
+	/* increment the counter only if soft reset worked */
+	if (ret)
+		atomic_inc(&ring->adev->gpu_reset_counter);
+
+	return ret;
 }
 
 /*
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
index f93f51002201..9af2cda676ad 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
@@ -126,6 +126,22 @@ struct amdgpu_fence_driver {
 	struct dma_fence		**fences;
 };
 
+/*
+ * Fences mark an event in the GPUs pipeline and are used
+ * for GPU/CPU synchronization.  When the fence is written,
+ * it is expected that all buffers associated with that fence
+ * are no longer in use by the associated ring on the GPU and
+ * that the relevant GPU caches have been flushed.
+ */
+
+struct amdgpu_fence {
+	struct dma_fence base;
+
+	/* RB, DMA, etc. */
+	struct amdgpu_ring		*ring;
+	ktime_t				start_timestamp;
+};
+
 extern const struct drm_sched_backend_ops amdgpu_sched_ops;
 
 void amdgpu_fence_driver_clear_job_fences(struct amdgpu_ring *ring);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_seq64.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_seq64.c
index e22cb2b5cd92..dba8051b8c14 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_seq64.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_seq64.c
@@ -133,7 +133,7 @@ void amdgpu_seq64_unmap(struct amdgpu_device *adev, struct amdgpu_fpriv *fpriv)
 
 	vm = &fpriv->vm;
 
-	drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT, 0);
+	drm_exec_init(&exec, 0, 0);
 	drm_exec_until_all_locked(&exec) {
 		r = amdgpu_vm_lock_pd(vm, &exec, 0);
 		if (likely(!r))
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 9f922ec50ea2..1c8ac4cf08c5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -309,7 +309,7 @@ int amdgpu_ttm_copy_mem_to_mem(struct amdgpu_device *adev,
 	mutex_lock(&adev->mman.gtt_window_lock);
 	while (src_mm.remaining) {
 		uint64_t from, to, cur_size, tiling_flags;
-		uint32_t num_type, data_format, max_com;
+		uint32_t num_type, data_format, max_com, write_compress_disable;
 		struct dma_fence *next;
 
 		/* Never copy more than 256MiB at once to avoid a timeout */
@@ -340,9 +340,13 @@ int amdgpu_ttm_copy_mem_to_mem(struct amdgpu_device *adev,
 			max_com = AMDGPU_TILING_GET(tiling_flags, GFX12_DCC_MAX_COMPRESSED_BLOCK);
 			num_type = AMDGPU_TILING_GET(tiling_flags, GFX12_DCC_NUMBER_TYPE);
 			data_format = AMDGPU_TILING_GET(tiling_flags, GFX12_DCC_DATA_FORMAT);
+			write_compress_disable =
+				AMDGPU_TILING_GET(tiling_flags, GFX12_DCC_WRITE_COMPRESS_DISABLE);
 			copy_flags |= (AMDGPU_COPY_FLAGS_SET(MAX_COMPRESSED, max_com) |
 				       AMDGPU_COPY_FLAGS_SET(NUMBER_TYPE, num_type) |
-				       AMDGPU_COPY_FLAGS_SET(DATA_FORMAT, data_format));
+				       AMDGPU_COPY_FLAGS_SET(DATA_FORMAT, data_format) |
+				       AMDGPU_COPY_FLAGS_SET(WRITE_COMPRESS_DISABLE,
+							     write_compress_disable));
 		}
 
 		r = amdgpu_copy_buffer(ring, from, to, cur_size, resv,
@@ -2065,6 +2069,7 @@ void amdgpu_ttm_fini(struct amdgpu_device *adev)
 	ttm_range_man_fini(&adev->mman.bdev, AMDGPU_PL_GDS);
 	ttm_range_man_fini(&adev->mman.bdev, AMDGPU_PL_GWS);
 	ttm_range_man_fini(&adev->mman.bdev, AMDGPU_PL_OA);
+	ttm_range_man_fini(&adev->mman.bdev, AMDGPU_PL_DOORBELL);
 	ttm_device_fini(&adev->mman.bdev);
 	adev->mman.initialized = false;
 	DRM_INFO("amdgpu: ttm finalized\n");
@@ -2275,7 +2280,7 @@ int amdgpu_ttm_clear_buffer(struct amdgpu_bo *bo,
 	struct amdgpu_ring *ring = adev->mman.buffer_funcs_ring;
 	struct amdgpu_res_cursor cursor;
 	u64 addr;
-	int r;
+	int r = 0;
 
 	if (!adev->mman.buffer_funcs_enabled)
 		return -EINVAL;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
index 138d80017f35..3c883f1cf068 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
@@ -118,6 +118,8 @@ struct amdgpu_copy_mem {
 #define AMDGPU_COPY_FLAGS_NUMBER_TYPE_MASK		0x07
 #define AMDGPU_COPY_FLAGS_DATA_FORMAT_SHIFT		8
 #define AMDGPU_COPY_FLAGS_DATA_FORMAT_MASK		0x3f
+#define AMDGPU_COPY_FLAGS_WRITE_COMPRESS_DISABLE_SHIFT	14
+#define AMDGPU_COPY_FLAGS_WRITE_COMPRESS_DISABLE_MASK	0x1
 
 #define AMDGPU_COPY_FLAGS_SET(field, value) \
 	(((__u32)(value) & AMDGPU_COPY_FLAGS_##field##_MASK) << AMDGPU_COPY_FLAGS_##field##_SHIFT)
@@ -151,6 +153,7 @@ int amdgpu_vram_mgr_reserve_range(struct amdgpu_vram_mgr *mgr,
 				  uint64_t start, uint64_t size);
 int amdgpu_vram_mgr_query_page_status(struct amdgpu_vram_mgr *mgr,
 				      uint64_t start);
+void amdgpu_vram_mgr_clear_reset_blocks(struct amdgpu_device *adev);
 
 bool amdgpu_res_cpu_visible(struct amdgpu_device *adev,
 			    struct ttm_resource *res);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
index 4c7b53648a50..eb83d7c1f784 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
@@ -30,6 +30,10 @@
 
 #define AMDGPU_UCODE_NAME_MAX		(128)
 
+static const struct kicker_device kicker_device_list[] = {
+	{0x744B, 0x00},
+};
+
 static void amdgpu_ucode_print_common_hdr(const struct common_firmware_header *hdr)
 {
 	DRM_DEBUG("size_bytes: %u\n", le32_to_cpu(hdr->size_bytes));
@@ -1383,6 +1387,19 @@ static const char *amdgpu_ucode_legacy_naming(struct amdgpu_device *adev, int bl
 	return NULL;
 }
 
+bool amdgpu_is_kicker_fw(struct amdgpu_device *adev)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(kicker_device_list); i++) {
+		if (adev->pdev->device == kicker_device_list[i].device &&
+			adev->pdev->revision == kicker_device_list[i].revision)
+		return true;
+	}
+
+	return false;
+}
+
 void amdgpu_ucode_ip_version_decode(struct amdgpu_device *adev, int block_type, char *ucode_prefix, int len)
 {
 	int maj, min, rev;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h
index 4e23419b92d4..fd08b015b2a7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h
@@ -595,6 +595,11 @@ struct amdgpu_firmware {
 	uint64_t fw_buf_mc;
 };
 
+struct kicker_device{
+	unsigned short device;
+	u8 revision;
+};
+
 void amdgpu_ucode_print_mc_hdr(const struct common_firmware_header *hdr);
 void amdgpu_ucode_print_smc_hdr(const struct common_firmware_header *hdr);
 void amdgpu_ucode_print_imu_hdr(const struct common_firmware_header *hdr);
@@ -622,5 +627,6 @@ amdgpu_ucode_get_load_type(struct amdgpu_device *adev, int load_type);
 const char *amdgpu_ucode_name(enum AMDGPU_UCODE_ID ucode_id);
 
 void amdgpu_ucode_ip_version_decode(struct amdgpu_device *adev, int block_type, char *ucode_prefix, int len);
+bool amdgpu_is_kicker_fw(struct amdgpu_device *adev);
 
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c
index bb7b9b2eaac1..8da0bddab3d2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c
@@ -383,6 +383,45 @@ int amdgpu_umc_fill_error_record(struct ras_err_data *err_data,
 	return 0;
 }
 
+static int amdgpu_umc_loop_all_aid(struct amdgpu_device *adev, umc_func func,
+				   void *data)
+{
+	uint32_t umc_node_inst;
+	uint32_t node_inst;
+	uint32_t umc_inst;
+	uint32_t ch_inst;
+	int ret;
+
+	/*
+	 * This loop is done based on the following -
+	 * umc.active mask = mask of active umc instances across all nodes
+	 * umc.umc_inst_num = maximum number of umc instancess per node
+	 * umc.node_inst_num = maximum number of node instances
+	 * Channel instances are not assumed to be harvested.
+	 */
+	dev_dbg(adev->dev, "active umcs :%lx umc_inst per node: %d",
+		adev->umc.active_mask, adev->umc.umc_inst_num);
+	for_each_set_bit(umc_node_inst, &(adev->umc.active_mask),
+			 adev->umc.node_inst_num * adev->umc.umc_inst_num) {
+		node_inst = umc_node_inst / adev->umc.umc_inst_num;
+		umc_inst = umc_node_inst % adev->umc.umc_inst_num;
+		LOOP_UMC_CH_INST(ch_inst) {
+			dev_dbg(adev->dev,
+				"node_inst :%d umc_inst: %d ch_inst: %d",
+				node_inst, umc_inst, ch_inst);
+			ret = func(adev, node_inst, umc_inst, ch_inst, data);
+			if (ret) {
+				dev_err(adev->dev,
+					"Node %d umc %d ch %d func returns %d\n",
+					node_inst, umc_inst, ch_inst, ret);
+				return ret;
+			}
+		}
+	}
+
+	return 0;
+}
+
 int amdgpu_umc_loop_channels(struct amdgpu_device *adev,
 			umc_func func, void *data)
 {
@@ -391,6 +430,9 @@ int amdgpu_umc_loop_channels(struct amdgpu_device *adev,
 	uint32_t ch_inst         = 0;
 	int ret = 0;
 
+	if (adev->aid_mask)
+		return amdgpu_umc_loop_all_aid(adev, func, data);
+
 	if (adev->umc.node_inst_num) {
 		LOOP_UMC_EACH_NODE_INST_AND_CH(node_inst, umc_inst, ch_inst) {
 			ret = func(adev, node_inst, umc_inst, ch_inst, data);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c
index 6162582d0aa2..d5125523bfa7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c
@@ -584,7 +584,7 @@ int amdgpu_umsch_mm_init_microcode(struct amdgpu_umsch_mm *umsch)
 		fw_name = "amdgpu/umsch_mm_4_0_0.bin";
 		break;
 	default:
-		break;
+		return -EINVAL;
 	}
 
 	r = amdgpu_ucode_request(adev, &adev->umsch_mm.fw, "%s", fw_name);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
index 2a1f3dbb14d3..3b6254de2c0e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
@@ -66,7 +66,6 @@
 #define VCN_ENC_CMD_REG_WAIT		0x0000000c
 
 #define VCN_AON_SOC_ADDRESS_2_0 	0x1f800
-#define VCN1_AON_SOC_ADDRESS_3_0 	0x48000
 #define VCN_VID_IP_ADDRESS_2_0		0x0
 #define VCN_AON_IP_ADDRESS_2_0		0x30000
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
index b6397d3229e1..01dccd489a80 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
@@ -1010,6 +1010,7 @@ u32 amdgpu_virt_rlcg_reg_rw(struct amdgpu_device *adev, u32 offset, u32 v, u32 f
 	void *scratch_reg2;
 	void *scratch_reg3;
 	void *spare_int;
+	unsigned long flags;
 
 	if (!adev->gfx.rlc.rlcg_reg_access_supported) {
 		dev_err(adev->dev,
@@ -1031,7 +1032,7 @@ u32 amdgpu_virt_rlcg_reg_rw(struct amdgpu_device *adev, u32 offset, u32 v, u32 f
 	scratch_reg2 = (void __iomem *)adev->rmmio + 4 * reg_access_ctrl->scratch_reg2;
 	scratch_reg3 = (void __iomem *)adev->rmmio + 4 * reg_access_ctrl->scratch_reg3;
 
-	mutex_lock(&adev->virt.rlcg_reg_lock);
+	spin_lock_irqsave(&adev->virt.rlcg_reg_lock, flags);
 
 	if (reg_access_ctrl->spare_int)
 		spare_int = (void __iomem *)adev->rmmio + 4 * reg_access_ctrl->spare_int;
@@ -1090,7 +1091,7 @@ u32 amdgpu_virt_rlcg_reg_rw(struct amdgpu_device *adev, u32 offset, u32 v, u32 f
 
 	ret = readl(scratch_reg0);
 
-	mutex_unlock(&adev->virt.rlcg_reg_lock);
+	spin_unlock_irqrestore(&adev->virt.rlcg_reg_lock, flags);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
index b650a2032c42..6a2087abfb7e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
@@ -275,7 +275,8 @@ struct amdgpu_virt {
 	/* the ucode id to signal the autoload */
 	uint32_t autoload_ucode_id;
 
-	struct mutex rlcg_reg_lock;
+	/* Spinlock to protect access to the RLCG register interface */
+	spinlock_t rlcg_reg_lock;
 };
 
 struct amdgpu_video_codec_info;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 73e02141a6e2..37d53578825b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -2434,8 +2434,6 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	spin_lock_init(&vm->status_lock);
 	INIT_LIST_HEAD(&vm->freed);
 	INIT_LIST_HEAD(&vm->done);
-	INIT_LIST_HEAD(&vm->pt_freed);
-	INIT_WORK(&vm->pt_free_work, amdgpu_vm_pt_free_work);
 	INIT_KFIFO(vm->faults);
 
 	r = amdgpu_vm_init_entities(adev, vm);
@@ -2607,8 +2605,6 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 
 	amdgpu_amdkfd_gpuvm_destroy_cb(adev, vm);
 
-	flush_work(&vm->pt_free_work);
-
 	root = amdgpu_bo_ref(vm->root.bo);
 	amdgpu_bo_reserve(root, true);
 	amdgpu_vm_put_task_info(vm->task_info);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
index 52dd7cdfdc81..ee893527a4f1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
@@ -360,10 +360,6 @@ struct amdgpu_vm {
 	/* BOs which are invalidated, has been updated in the PTs */
 	struct list_head        done;
 
-	/* PT BOs scheduled to free and fill with zero if vm_resv is not hold */
-	struct list_head	pt_freed;
-	struct work_struct	pt_free_work;
-
 	/* contains the page directory */
 	struct amdgpu_vm_bo_base     root;
 	struct dma_fence	*last_update;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c
index f78a0434a48f..54ae0e9bc6d7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c
@@ -546,27 +546,6 @@ static void amdgpu_vm_pt_free(struct amdgpu_vm_bo_base *entry)
 	amdgpu_bo_unref(&entry->bo);
 }
 
-void amdgpu_vm_pt_free_work(struct work_struct *work)
-{
-	struct amdgpu_vm_bo_base *entry, *next;
-	struct amdgpu_vm *vm;
-	LIST_HEAD(pt_freed);
-
-	vm = container_of(work, struct amdgpu_vm, pt_free_work);
-
-	spin_lock(&vm->status_lock);
-	list_splice_init(&vm->pt_freed, &pt_freed);
-	spin_unlock(&vm->status_lock);
-
-	/* flush_work in amdgpu_vm_fini ensure vm->root.bo is valid. */
-	amdgpu_bo_reserve(vm->root.bo, true);
-
-	list_for_each_entry_safe(entry, next, &pt_freed, vm_status)
-		amdgpu_vm_pt_free(entry);
-
-	amdgpu_bo_unreserve(vm->root.bo);
-}
-
 /**
  * amdgpu_vm_pt_free_list - free PD/PT levels
  *
@@ -579,19 +558,15 @@ void amdgpu_vm_pt_free_list(struct amdgpu_device *adev,
 			    struct amdgpu_vm_update_params *params)
 {
 	struct amdgpu_vm_bo_base *entry, *next;
-	struct amdgpu_vm *vm = params->vm;
 	bool unlocked = params->unlocked;
 
 	if (list_empty(&params->tlb_flush_waitlist))
 		return;
 
-	if (unlocked) {
-		spin_lock(&vm->status_lock);
-		list_splice_init(&params->tlb_flush_waitlist, &vm->pt_freed);
-		spin_unlock(&vm->status_lock);
-		schedule_work(&vm->pt_free_work);
-		return;
-	}
+	/*
+	 * unlocked unmap clear page table leaves, warning to free the page entry.
+	 */
+	WARN_ON(unlocked);
 
 	list_for_each_entry_safe(entry, next, &params->tlb_flush_waitlist, vm_status)
 		amdgpu_vm_pt_free(entry);
@@ -899,7 +874,15 @@ int amdgpu_vm_ptes_update(struct amdgpu_vm_update_params *params,
 		incr = (uint64_t)AMDGPU_GPU_PAGE_SIZE << shift;
 		mask = amdgpu_vm_pt_entries_mask(adev, cursor.level);
 		pe_start = ((cursor.pfn >> shift) & mask) * 8;
-		entry_end = ((uint64_t)mask + 1) << shift;
+
+		if (cursor.level < AMDGPU_VM_PTB && params->unlocked)
+			/*
+			 * MMU notifier callback unlocked unmap huge page, leave is PDE entry,
+			 * only clear one entry. Next entry search again for PDE or PTE leave.
+			 */
+			entry_end = 1ULL << shift;
+		else
+			entry_end = ((uint64_t)mask + 1) << shift;
 		entry_end += cursor.pfn & ~(entry_end - 1);
 		entry_end = min(entry_end, end);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
index ff5e52025266..ea4df412decf 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
@@ -463,7 +463,7 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man,
 	int r;
 
 	lpfn = (u64)place->lpfn << PAGE_SHIFT;
-	if (!lpfn)
+	if (!lpfn || lpfn > man->size)
 		lpfn = man->size;
 
 	fpfn = (u64)place->fpfn << PAGE_SHIFT;
@@ -648,9 +648,8 @@ static void amdgpu_vram_mgr_del(struct ttm_resource_manager *man,
 	list_for_each_entry(block, &vres->blocks, link)
 		vis_usage += amdgpu_vram_mgr_vis_size(adev, block);
 
-	amdgpu_vram_mgr_do_reserve(man);
-
 	drm_buddy_free_list(mm, &vres->blocks, vres->flags);
+	amdgpu_vram_mgr_do_reserve(man);
 	mutex_unlock(&mgr->lock);
 
 	atomic64_sub(vis_usage, &mgr->vis_usage);
@@ -783,6 +782,23 @@ uint64_t amdgpu_vram_mgr_vis_usage(struct amdgpu_vram_mgr *mgr)
 }
 
 /**
+ * amdgpu_vram_mgr_clear_reset_blocks - reset clear blocks
+ *
+ * @adev: amdgpu device pointer
+ *
+ * Reset the cleared drm buddy blocks.
+ */
+void amdgpu_vram_mgr_clear_reset_blocks(struct amdgpu_device *adev)
+{
+	struct amdgpu_vram_mgr *mgr = &adev->mman.vram_mgr;
+	struct drm_buddy *mm = &mgr->mm;
+
+	mutex_lock(&mgr->lock);
+	drm_buddy_reset_clear(mm, false);
+	mutex_unlock(&mgr->lock);
+}
+
+/**
  * amdgpu_vram_mgr_intersects - test each drm buddy block for intersection
  *
  * @man: TTM memory type manager
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index 45ed97038df0..9a1c9dbad126 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -5998,7 +5998,7 @@ static int gfx_v10_0_cp_gfx_load_pfp_microcode(struct amdgpu_device *adev)
 	}
 
 	if (amdgpu_emu_mode == 1)
-		adev->hdp.funcs->flush_hdp(adev, NULL);
+		amdgpu_device_flush_hdp(adev, NULL);
 
 	tmp = RREG32_SOC15(GC, 0, mmCP_PFP_IC_BASE_CNTL);
 	tmp = REG_SET_FIELD(tmp, CP_PFP_IC_BASE_CNTL, VMID, 0);
@@ -6076,7 +6076,7 @@ static int gfx_v10_0_cp_gfx_load_ce_microcode(struct amdgpu_device *adev)
 	}
 
 	if (amdgpu_emu_mode == 1)
-		adev->hdp.funcs->flush_hdp(adev, NULL);
+		amdgpu_device_flush_hdp(adev, NULL);
 
 	tmp = RREG32_SOC15(GC, 0, mmCP_CE_IC_BASE_CNTL);
 	tmp = REG_SET_FIELD(tmp, CP_CE_IC_BASE_CNTL, VMID, 0);
@@ -6153,7 +6153,7 @@ static int gfx_v10_0_cp_gfx_load_me_microcode(struct amdgpu_device *adev)
 	}
 
 	if (amdgpu_emu_mode == 1)
-		adev->hdp.funcs->flush_hdp(adev, NULL);
+		amdgpu_device_flush_hdp(adev, NULL);
 
 	tmp = RREG32_SOC15(GC, 0, mmCP_ME_IC_BASE_CNTL);
 	tmp = REG_SET_FIELD(tmp, CP_ME_IC_BASE_CNTL, VMID, 0);
@@ -6528,7 +6528,7 @@ static int gfx_v10_0_cp_compute_load_microcode(struct amdgpu_device *adev)
 	}
 
 	if (amdgpu_emu_mode == 1)
-		adev->hdp.funcs->flush_hdp(adev, NULL);
+		amdgpu_device_flush_hdp(adev, NULL);
 
 	tmp = RREG32_SOC15(GC, 0, mmCP_CPC_IC_BASE_CNTL);
 	tmp = REG_SET_FIELD(tmp, CP_CPC_IC_BASE_CNTL, CACHE_POLICY, 0);
@@ -9510,9 +9510,8 @@ static int gfx_v10_0_reset_kcq(struct amdgpu_ring *ring,
 	kiq->pmf->kiq_unmap_queues(kiq_ring, ring, RESET_QUEUES,
 				   0, 0);
 	amdgpu_ring_commit(kiq_ring);
-	spin_unlock_irqrestore(&kiq->ring_lock, flags);
-
 	r = amdgpu_ring_test_ring(kiq_ring);
+	spin_unlock_irqrestore(&kiq->ring_lock, flags);
 	if (r)
 		return r;
 
@@ -9559,9 +9558,8 @@ static int gfx_v10_0_reset_kcq(struct amdgpu_ring *ring,
 	}
 	kiq->pmf->kiq_map_queues(kiq_ring, ring);
 	amdgpu_ring_commit(kiq_ring);
-	spin_unlock_irqrestore(&kiq->ring_lock, flags);
-
 	r = amdgpu_ring_test_ring(kiq_ring);
+	spin_unlock_irqrestore(&kiq->ring_lock, flags);
 	if (r)
 		return r;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
index d3e8be82a172..96e5c520af31 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
@@ -63,10 +63,28 @@
 #define regPC_CONFIG_CNTL_1		0x194d
 #define regPC_CONFIG_CNTL_1_BASE_IDX	1
 
+#define regCP_GFX_MQD_CONTROL_DEFAULT                                             0x00000100
+#define regCP_GFX_HQD_VMID_DEFAULT                                                0x00000000
+#define regCP_GFX_HQD_QUEUE_PRIORITY_DEFAULT                                      0x00000000
+#define regCP_GFX_HQD_QUANTUM_DEFAULT                                             0x00000a01
+#define regCP_GFX_HQD_CNTL_DEFAULT                                                0x00a00000
+#define regCP_RB_DOORBELL_CONTROL_DEFAULT                                         0x00000000
+#define regCP_GFX_HQD_RPTR_DEFAULT                                                0x00000000
+
+#define regCP_HQD_EOP_CONTROL_DEFAULT                                             0x00000006
+#define regCP_HQD_PQ_DOORBELL_CONTROL_DEFAULT                                     0x00000000
+#define regCP_MQD_CONTROL_DEFAULT                                                 0x00000100
+#define regCP_HQD_PQ_CONTROL_DEFAULT                                              0x00308509
+#define regCP_HQD_PQ_DOORBELL_CONTROL_DEFAULT                                     0x00000000
+#define regCP_HQD_PQ_RPTR_DEFAULT                                                 0x00000000
+#define regCP_HQD_PERSISTENT_STATE_DEFAULT                                        0x0be05501
+#define regCP_HQD_IB_CONTROL_DEFAULT                                              0x00300000
+
 MODULE_FIRMWARE("amdgpu/gc_11_0_0_pfp.bin");
 MODULE_FIRMWARE("amdgpu/gc_11_0_0_me.bin");
 MODULE_FIRMWARE("amdgpu/gc_11_0_0_mec.bin");
 MODULE_FIRMWARE("amdgpu/gc_11_0_0_rlc.bin");
+MODULE_FIRMWARE("amdgpu/gc_11_0_0_rlc_kicker.bin");
 MODULE_FIRMWARE("amdgpu/gc_11_0_0_rlc_1.bin");
 MODULE_FIRMWARE("amdgpu/gc_11_0_0_toc.bin");
 MODULE_FIRMWARE("amdgpu/gc_11_0_1_pfp.bin");
@@ -717,6 +735,9 @@ static int gfx_v11_0_init_microcode(struct amdgpu_device *adev)
 		    adev->pdev->revision == 0xCE)
 			err = amdgpu_ucode_request(adev, &adev->gfx.rlc_fw,
 						   "amdgpu/gc_11_0_0_rlc_1.bin");
+		else if (amdgpu_is_kicker_fw(adev))
+			err = amdgpu_ucode_request(adev, &adev->gfx.rlc_fw,
+						   "amdgpu/%s_rlc_kicker.bin", ucode_prefix);
 		else
 			err = amdgpu_ucode_request(adev, &adev->gfx.rlc_fw,
 						   "amdgpu/%s_rlc.bin", ucode_prefix);
@@ -1549,7 +1570,7 @@ static int gfx_v11_0_sw_init(void *handle)
 		adev->gfx.me.num_me = 1;
 		adev->gfx.me.num_pipe_per_me = 1;
 		adev->gfx.me.num_queue_per_pipe = 1;
-		adev->gfx.mec.num_mec = 2;
+		adev->gfx.mec.num_mec = 1;
 		adev->gfx.mec.num_pipe_per_mec = 4;
 		adev->gfx.mec.num_queue_per_pipe = 4;
 		break;
@@ -2327,7 +2348,7 @@ static int gfx_v11_0_config_me_cache(struct amdgpu_device *adev, uint64_t addr)
 	}
 
 	if (amdgpu_emu_mode == 1)
-		adev->hdp.funcs->flush_hdp(adev, NULL);
+		amdgpu_device_flush_hdp(adev, NULL);
 
 	tmp = RREG32_SOC15(GC, 0, regCP_ME_IC_BASE_CNTL);
 	tmp = REG_SET_FIELD(tmp, CP_ME_IC_BASE_CNTL, VMID, 0);
@@ -2371,7 +2392,7 @@ static int gfx_v11_0_config_pfp_cache(struct amdgpu_device *adev, uint64_t addr)
 	}
 
 	if (amdgpu_emu_mode == 1)
-		adev->hdp.funcs->flush_hdp(adev, NULL);
+		amdgpu_device_flush_hdp(adev, NULL);
 
 	tmp = RREG32_SOC15(GC, 0, regCP_PFP_IC_BASE_CNTL);
 	tmp = REG_SET_FIELD(tmp, CP_PFP_IC_BASE_CNTL, VMID, 0);
@@ -2416,7 +2437,7 @@ static int gfx_v11_0_config_mec_cache(struct amdgpu_device *adev, uint64_t addr)
 	}
 
 	if (amdgpu_emu_mode == 1)
-		adev->hdp.funcs->flush_hdp(adev, NULL);
+		amdgpu_device_flush_hdp(adev, NULL);
 
 	tmp = RREG32_SOC15(GC, 0, regCP_CPC_IC_BASE_CNTL);
 	tmp = REG_SET_FIELD(tmp, CP_CPC_IC_BASE_CNTL, CACHE_POLICY, 0);
@@ -3051,7 +3072,7 @@ static int gfx_v11_0_cp_gfx_load_pfp_microcode_rs64(struct amdgpu_device *adev)
 	amdgpu_bo_unreserve(adev->gfx.pfp.pfp_fw_data_obj);
 
 	if (amdgpu_emu_mode == 1)
-		adev->hdp.funcs->flush_hdp(adev, NULL);
+		amdgpu_device_flush_hdp(adev, NULL);
 
 	WREG32_SOC15(GC, 0, regCP_PFP_IC_BASE_LO,
 		lower_32_bits(adev->gfx.pfp.pfp_fw_gpu_addr));
@@ -3269,7 +3290,7 @@ static int gfx_v11_0_cp_gfx_load_me_microcode_rs64(struct amdgpu_device *adev)
 	amdgpu_bo_unreserve(adev->gfx.me.me_fw_data_obj);
 
 	if (amdgpu_emu_mode == 1)
-		adev->hdp.funcs->flush_hdp(adev, NULL);
+		amdgpu_device_flush_hdp(adev, NULL);
 
 	WREG32_SOC15(GC, 0, regCP_ME_IC_BASE_LO,
 		lower_32_bits(adev->gfx.me.me_fw_gpu_addr));
@@ -3896,7 +3917,7 @@ static void gfx_v11_0_gfx_mqd_set_priority(struct amdgpu_device *adev,
 	if (prop->hqd_pipe_priority == AMDGPU_GFX_PIPE_PRIO_HIGH)
 		priority = 1;
 
-	tmp = RREG32_SOC15(GC, 0, regCP_GFX_HQD_QUEUE_PRIORITY);
+	tmp = regCP_GFX_HQD_QUEUE_PRIORITY_DEFAULT;
 	tmp = REG_SET_FIELD(tmp, CP_GFX_HQD_QUEUE_PRIORITY, PRIORITY_LEVEL, priority);
 	mqd->cp_gfx_hqd_queue_priority = tmp;
 }
@@ -3918,14 +3939,14 @@ static int gfx_v11_0_gfx_mqd_init(struct amdgpu_device *adev, void *m,
 	mqd->cp_mqd_base_addr_hi = upper_32_bits(prop->mqd_gpu_addr);
 
 	/* set up mqd control */
-	tmp = RREG32_SOC15(GC, 0, regCP_GFX_MQD_CONTROL);
+	tmp = regCP_GFX_MQD_CONTROL_DEFAULT;
 	tmp = REG_SET_FIELD(tmp, CP_GFX_MQD_CONTROL, VMID, 0);
 	tmp = REG_SET_FIELD(tmp, CP_GFX_MQD_CONTROL, PRIV_STATE, 1);
 	tmp = REG_SET_FIELD(tmp, CP_GFX_MQD_CONTROL, CACHE_POLICY, 0);
 	mqd->cp_gfx_mqd_control = tmp;
 
 	/* set up gfx_hqd_vimd with 0x0 to indicate the ring buffer's vmid */
-	tmp = RREG32_SOC15(GC, 0, regCP_GFX_HQD_VMID);
+	tmp = regCP_GFX_HQD_VMID_DEFAULT;
 	tmp = REG_SET_FIELD(tmp, CP_GFX_HQD_VMID, VMID, 0);
 	mqd->cp_gfx_hqd_vmid = 0;
 
@@ -3933,7 +3954,7 @@ static int gfx_v11_0_gfx_mqd_init(struct amdgpu_device *adev, void *m,
 	gfx_v11_0_gfx_mqd_set_priority(adev, mqd, prop);
 
 	/* set up time quantum */
-	tmp = RREG32_SOC15(GC, 0, regCP_GFX_HQD_QUANTUM);
+	tmp = regCP_GFX_HQD_QUANTUM_DEFAULT;
 	tmp = REG_SET_FIELD(tmp, CP_GFX_HQD_QUANTUM, QUANTUM_EN, 1);
 	mqd->cp_gfx_hqd_quantum = tmp;
 
@@ -3955,7 +3976,7 @@ static int gfx_v11_0_gfx_mqd_init(struct amdgpu_device *adev, void *m,
 
 	/* set up the gfx_hqd_control, similar as CP_RB0_CNTL */
 	rb_bufsz = order_base_2(prop->queue_size / 4) - 1;
-	tmp = RREG32_SOC15(GC, 0, regCP_GFX_HQD_CNTL);
+	tmp = regCP_GFX_HQD_CNTL_DEFAULT;
 	tmp = REG_SET_FIELD(tmp, CP_GFX_HQD_CNTL, RB_BUFSZ, rb_bufsz);
 	tmp = REG_SET_FIELD(tmp, CP_GFX_HQD_CNTL, RB_BLKSZ, rb_bufsz - 2);
 #ifdef __BIG_ENDIAN
@@ -3964,7 +3985,7 @@ static int gfx_v11_0_gfx_mqd_init(struct amdgpu_device *adev, void *m,
 	mqd->cp_gfx_hqd_cntl = tmp;
 
 	/* set up cp_doorbell_control */
-	tmp = RREG32_SOC15(GC, 0, regCP_RB_DOORBELL_CONTROL);
+	tmp = regCP_RB_DOORBELL_CONTROL_DEFAULT;
 	if (prop->use_doorbell) {
 		tmp = REG_SET_FIELD(tmp, CP_RB_DOORBELL_CONTROL,
 				    DOORBELL_OFFSET, prop->doorbell_index);
@@ -3976,7 +3997,7 @@ static int gfx_v11_0_gfx_mqd_init(struct amdgpu_device *adev, void *m,
 	mqd->cp_rb_doorbell_control = tmp;
 
 	/* reset read and write pointers, similar to CP_RB0_WPTR/_RPTR */
-	mqd->cp_gfx_hqd_rptr = RREG32_SOC15(GC, 0, regCP_GFX_HQD_RPTR);
+	mqd->cp_gfx_hqd_rptr = regCP_GFX_HQD_RPTR_DEFAULT;
 
 	/* active the queue */
 	mqd->cp_gfx_hqd_active = 1;
@@ -4062,14 +4083,14 @@ static int gfx_v11_0_compute_mqd_init(struct amdgpu_device *adev, void *m,
 	mqd->cp_hqd_eop_base_addr_hi = upper_32_bits(eop_base_addr);
 
 	/* set the EOP size, register value is 2^(EOP_SIZE+1) dwords */
-	tmp = RREG32_SOC15(GC, 0, regCP_HQD_EOP_CONTROL);
+	tmp = regCP_HQD_EOP_CONTROL_DEFAULT;
 	tmp = REG_SET_FIELD(tmp, CP_HQD_EOP_CONTROL, EOP_SIZE,
 			(order_base_2(GFX11_MEC_HPD_SIZE / 4) - 1));
 
 	mqd->cp_hqd_eop_control = tmp;
 
 	/* enable doorbell? */
-	tmp = RREG32_SOC15(GC, 0, regCP_HQD_PQ_DOORBELL_CONTROL);
+	tmp = regCP_HQD_PQ_DOORBELL_CONTROL_DEFAULT;
 
 	if (prop->use_doorbell) {
 		tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_DOORBELL_CONTROL,
@@ -4098,7 +4119,7 @@ static int gfx_v11_0_compute_mqd_init(struct amdgpu_device *adev, void *m,
 	mqd->cp_mqd_base_addr_hi = upper_32_bits(prop->mqd_gpu_addr);
 
 	/* set MQD vmid to 0 */
-	tmp = RREG32_SOC15(GC, 0, regCP_MQD_CONTROL);
+	tmp = regCP_MQD_CONTROL_DEFAULT;
 	tmp = REG_SET_FIELD(tmp, CP_MQD_CONTROL, VMID, 0);
 	mqd->cp_mqd_control = tmp;
 
@@ -4108,7 +4129,7 @@ static int gfx_v11_0_compute_mqd_init(struct amdgpu_device *adev, void *m,
 	mqd->cp_hqd_pq_base_hi = upper_32_bits(hqd_gpu_addr);
 
 	/* set up the HQD, this is similar to CP_RB0_CNTL */
-	tmp = RREG32_SOC15(GC, 0, regCP_HQD_PQ_CONTROL);
+	tmp = regCP_HQD_PQ_CONTROL_DEFAULT;
 	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, QUEUE_SIZE,
 			    (order_base_2(prop->queue_size / 4) - 1));
 	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, RPTR_BLOCK_SIZE,
@@ -4134,7 +4155,7 @@ static int gfx_v11_0_compute_mqd_init(struct amdgpu_device *adev, void *m,
 	tmp = 0;
 	/* enable the doorbell if requested */
 	if (prop->use_doorbell) {
-		tmp = RREG32_SOC15(GC, 0, regCP_HQD_PQ_DOORBELL_CONTROL);
+		tmp = regCP_HQD_PQ_DOORBELL_CONTROL_DEFAULT;
 		tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_DOORBELL_CONTROL,
 				DOORBELL_OFFSET, prop->doorbell_index);
 
@@ -4149,17 +4170,17 @@ static int gfx_v11_0_compute_mqd_init(struct amdgpu_device *adev, void *m,
 	mqd->cp_hqd_pq_doorbell_control = tmp;
 
 	/* reset read and write pointers, similar to CP_RB0_WPTR/_RPTR */
-	mqd->cp_hqd_pq_rptr = RREG32_SOC15(GC, 0, regCP_HQD_PQ_RPTR);
+	mqd->cp_hqd_pq_rptr = regCP_HQD_PQ_RPTR_DEFAULT;
 
 	/* set the vmid for the queue */
 	mqd->cp_hqd_vmid = 0;
 
-	tmp = RREG32_SOC15(GC, 0, regCP_HQD_PERSISTENT_STATE);
+	tmp = regCP_HQD_PERSISTENT_STATE_DEFAULT;
 	tmp = REG_SET_FIELD(tmp, CP_HQD_PERSISTENT_STATE, PRELOAD_SIZE, 0x55);
 	mqd->cp_hqd_persistent_state = tmp;
 
 	/* set MIN_IB_AVAIL_SIZE */
-	tmp = RREG32_SOC15(GC, 0, regCP_HQD_IB_CONTROL);
+	tmp = regCP_HQD_IB_CONTROL_DEFAULT;
 	tmp = REG_SET_FIELD(tmp, CP_HQD_IB_CONTROL, MIN_IB_AVAIL_SIZE, 3);
 	mqd->cp_hqd_ib_control = tmp;
 
@@ -4487,7 +4508,7 @@ static int gfx_v11_0_gfxhub_enable(struct amdgpu_device *adev)
 	if (r)
 		return r;
 
-	adev->hdp.funcs->flush_hdp(adev, NULL);
+	amdgpu_device_flush_hdp(adev, NULL);
 
 	value = (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_ALWAYS) ?
 		false : true;
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
index 6c19626ec59e..adcfcf594286 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
@@ -52,6 +52,24 @@
 
 #define RLCG_UCODE_LOADING_START_ADDRESS	0x00002000L
 
+#define regCP_GFX_MQD_CONTROL_DEFAULT                                             0x00000100
+#define regCP_GFX_HQD_VMID_DEFAULT                                                0x00000000
+#define regCP_GFX_HQD_QUEUE_PRIORITY_DEFAULT                                      0x00000000
+#define regCP_GFX_HQD_QUANTUM_DEFAULT                                             0x00000a01
+#define regCP_GFX_HQD_CNTL_DEFAULT                                                0x00f00000
+#define regCP_RB_DOORBELL_CONTROL_DEFAULT                                         0x00000000
+#define regCP_GFX_HQD_RPTR_DEFAULT                                                0x00000000
+
+#define regCP_HQD_EOP_CONTROL_DEFAULT                                             0x00000006
+#define regCP_HQD_PQ_DOORBELL_CONTROL_DEFAULT                                     0x00000000
+#define regCP_MQD_CONTROL_DEFAULT                                                 0x00000100
+#define regCP_HQD_PQ_CONTROL_DEFAULT                                              0x00308509
+#define regCP_HQD_PQ_DOORBELL_CONTROL_DEFAULT                                     0x00000000
+#define regCP_HQD_PQ_RPTR_DEFAULT                                                 0x00000000
+#define regCP_HQD_PERSISTENT_STATE_DEFAULT                                        0x0be05501
+#define regCP_HQD_IB_CONTROL_DEFAULT                                              0x00300000
+
+
 MODULE_FIRMWARE("amdgpu/gc_12_0_0_pfp.bin");
 MODULE_FIRMWARE("amdgpu/gc_12_0_0_me.bin");
 MODULE_FIRMWARE("amdgpu/gc_12_0_0_mec.bin");
@@ -1332,7 +1350,7 @@ static int gfx_v12_0_sw_init(void *handle)
 		adev->gfx.me.num_me = 1;
 		adev->gfx.me.num_pipe_per_me = 1;
 		adev->gfx.me.num_queue_per_pipe = 1;
-		adev->gfx.mec.num_mec = 2;
+		adev->gfx.mec.num_mec = 1;
 		adev->gfx.mec.num_pipe_per_mec = 2;
 		adev->gfx.mec.num_queue_per_pipe = 4;
 		break;
@@ -2264,7 +2282,7 @@ static int gfx_v12_0_cp_gfx_load_pfp_microcode_rs64(struct amdgpu_device *adev)
 	amdgpu_bo_unreserve(adev->gfx.pfp.pfp_fw_data_obj);
 
 	if (amdgpu_emu_mode == 1)
-		adev->hdp.funcs->flush_hdp(adev, NULL);
+		amdgpu_device_flush_hdp(adev, NULL);
 
 	WREG32_SOC15(GC, 0, regCP_PFP_IC_BASE_LO,
 		lower_32_bits(adev->gfx.pfp.pfp_fw_gpu_addr));
@@ -2395,7 +2413,7 @@ static int gfx_v12_0_cp_gfx_load_me_microcode_rs64(struct amdgpu_device *adev)
 				      (void **)&adev->gfx.me.me_fw_data_ptr);
 	if (r) {
 		dev_err(adev->dev, "(%d) failed to create me data bo\n", r);
-		gfx_v12_0_pfp_fini(adev);
+		gfx_v12_0_me_fini(adev);
 		return r;
 	}
 
@@ -2408,7 +2426,7 @@ static int gfx_v12_0_cp_gfx_load_me_microcode_rs64(struct amdgpu_device *adev)
 	amdgpu_bo_unreserve(adev->gfx.me.me_fw_data_obj);
 
 	if (amdgpu_emu_mode == 1)
-		adev->hdp.funcs->flush_hdp(adev, NULL);
+		amdgpu_device_flush_hdp(adev, NULL);
 
 	WREG32_SOC15(GC, 0, regCP_ME_IC_BASE_LO,
 		lower_32_bits(adev->gfx.me.me_fw_gpu_addr));
@@ -2851,25 +2869,25 @@ static int gfx_v12_0_gfx_mqd_init(struct amdgpu_device *adev, void *m,
 	mqd->cp_mqd_base_addr_hi = upper_32_bits(prop->mqd_gpu_addr);
 
 	/* set up mqd control */
-	tmp = RREG32_SOC15(GC, 0, regCP_GFX_MQD_CONTROL);
+	tmp = regCP_GFX_MQD_CONTROL_DEFAULT;
 	tmp = REG_SET_FIELD(tmp, CP_GFX_MQD_CONTROL, VMID, 0);
 	tmp = REG_SET_FIELD(tmp, CP_GFX_MQD_CONTROL, PRIV_STATE, 1);
 	tmp = REG_SET_FIELD(tmp, CP_GFX_MQD_CONTROL, CACHE_POLICY, 0);
 	mqd->cp_gfx_mqd_control = tmp;
 
 	/* set up gfx_hqd_vimd with 0x0 to indicate the ring buffer's vmid */
-	tmp = RREG32_SOC15(GC, 0, regCP_GFX_HQD_VMID);
+	tmp = regCP_GFX_HQD_VMID_DEFAULT;
 	tmp = REG_SET_FIELD(tmp, CP_GFX_HQD_VMID, VMID, 0);
 	mqd->cp_gfx_hqd_vmid = 0;
 
 	/* set up default queue priority level
 	 * 0x0 = low priority, 0x1 = high priority */
-	tmp = RREG32_SOC15(GC, 0, regCP_GFX_HQD_QUEUE_PRIORITY);
+	tmp = regCP_GFX_HQD_QUEUE_PRIORITY_DEFAULT;
 	tmp = REG_SET_FIELD(tmp, CP_GFX_HQD_QUEUE_PRIORITY, PRIORITY_LEVEL, 0);
 	mqd->cp_gfx_hqd_queue_priority = tmp;
 
 	/* set up time quantum */
-	tmp = RREG32_SOC15(GC, 0, regCP_GFX_HQD_QUANTUM);
+	tmp = regCP_GFX_HQD_QUANTUM_DEFAULT;
 	tmp = REG_SET_FIELD(tmp, CP_GFX_HQD_QUANTUM, QUANTUM_EN, 1);
 	mqd->cp_gfx_hqd_quantum = tmp;
 
@@ -2891,7 +2909,7 @@ static int gfx_v12_0_gfx_mqd_init(struct amdgpu_device *adev, void *m,
 
 	/* set up the gfx_hqd_control, similar as CP_RB0_CNTL */
 	rb_bufsz = order_base_2(prop->queue_size / 4) - 1;
-	tmp = RREG32_SOC15(GC, 0, regCP_GFX_HQD_CNTL);
+	tmp = regCP_GFX_HQD_CNTL_DEFAULT;
 	tmp = REG_SET_FIELD(tmp, CP_GFX_HQD_CNTL, RB_BUFSZ, rb_bufsz);
 	tmp = REG_SET_FIELD(tmp, CP_GFX_HQD_CNTL, RB_BLKSZ, rb_bufsz - 2);
 #ifdef __BIG_ENDIAN
@@ -2900,7 +2918,7 @@ static int gfx_v12_0_gfx_mqd_init(struct amdgpu_device *adev, void *m,
 	mqd->cp_gfx_hqd_cntl = tmp;
 
 	/* set up cp_doorbell_control */
-	tmp = RREG32_SOC15(GC, 0, regCP_RB_DOORBELL_CONTROL);
+	tmp = regCP_RB_DOORBELL_CONTROL_DEFAULT;
 	if (prop->use_doorbell) {
 		tmp = REG_SET_FIELD(tmp, CP_RB_DOORBELL_CONTROL,
 				    DOORBELL_OFFSET, prop->doorbell_index);
@@ -2912,7 +2930,7 @@ static int gfx_v12_0_gfx_mqd_init(struct amdgpu_device *adev, void *m,
 	mqd->cp_rb_doorbell_control = tmp;
 
 	/* reset read and write pointers, similar to CP_RB0_WPTR/_RPTR */
-	mqd->cp_gfx_hqd_rptr = RREG32_SOC15(GC, 0, regCP_GFX_HQD_RPTR);
+	mqd->cp_gfx_hqd_rptr = regCP_GFX_HQD_RPTR_DEFAULT;
 
 	/* active the queue */
 	mqd->cp_gfx_hqd_active = 1;
@@ -3007,14 +3025,14 @@ static int gfx_v12_0_compute_mqd_init(struct amdgpu_device *adev, void *m,
 	mqd->cp_hqd_eop_base_addr_hi = upper_32_bits(eop_base_addr);
 
 	/* set the EOP size, register value is 2^(EOP_SIZE+1) dwords */
-	tmp = RREG32_SOC15(GC, 0, regCP_HQD_EOP_CONTROL);
+	tmp = regCP_HQD_EOP_CONTROL_DEFAULT;
 	tmp = REG_SET_FIELD(tmp, CP_HQD_EOP_CONTROL, EOP_SIZE,
 			(order_base_2(GFX12_MEC_HPD_SIZE / 4) - 1));
 
 	mqd->cp_hqd_eop_control = tmp;
 
 	/* enable doorbell? */
-	tmp = RREG32_SOC15(GC, 0, regCP_HQD_PQ_DOORBELL_CONTROL);
+	tmp = regCP_HQD_PQ_DOORBELL_CONTROL_DEFAULT;
 
 	if (prop->use_doorbell) {
 		tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_DOORBELL_CONTROL,
@@ -3043,7 +3061,7 @@ static int gfx_v12_0_compute_mqd_init(struct amdgpu_device *adev, void *m,
 	mqd->cp_mqd_base_addr_hi = upper_32_bits(prop->mqd_gpu_addr);
 
 	/* set MQD vmid to 0 */
-	tmp = RREG32_SOC15(GC, 0, regCP_MQD_CONTROL);
+	tmp = regCP_MQD_CONTROL_DEFAULT;
 	tmp = REG_SET_FIELD(tmp, CP_MQD_CONTROL, VMID, 0);
 	mqd->cp_mqd_control = tmp;
 
@@ -3053,7 +3071,7 @@ static int gfx_v12_0_compute_mqd_init(struct amdgpu_device *adev, void *m,
 	mqd->cp_hqd_pq_base_hi = upper_32_bits(hqd_gpu_addr);
 
 	/* set up the HQD, this is similar to CP_RB0_CNTL */
-	tmp = RREG32_SOC15(GC, 0, regCP_HQD_PQ_CONTROL);
+	tmp = regCP_HQD_PQ_CONTROL_DEFAULT;
 	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, QUEUE_SIZE,
 			    (order_base_2(prop->queue_size / 4) - 1));
 	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, RPTR_BLOCK_SIZE,
@@ -3078,7 +3096,7 @@ static int gfx_v12_0_compute_mqd_init(struct amdgpu_device *adev, void *m,
 	tmp = 0;
 	/* enable the doorbell if requested */
 	if (prop->use_doorbell) {
-		tmp = RREG32_SOC15(GC, 0, regCP_HQD_PQ_DOORBELL_CONTROL);
+		tmp = regCP_HQD_PQ_DOORBELL_CONTROL_DEFAULT;
 		tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_DOORBELL_CONTROL,
 				DOORBELL_OFFSET, prop->doorbell_index);
 
@@ -3093,17 +3111,17 @@ static int gfx_v12_0_compute_mqd_init(struct amdgpu_device *adev, void *m,
 	mqd->cp_hqd_pq_doorbell_control = tmp;
 
 	/* reset read and write pointers, similar to CP_RB0_WPTR/_RPTR */
-	mqd->cp_hqd_pq_rptr = RREG32_SOC15(GC, 0, regCP_HQD_PQ_RPTR);
+	mqd->cp_hqd_pq_rptr = regCP_HQD_PQ_RPTR_DEFAULT;
 
 	/* set the vmid for the queue */
 	mqd->cp_hqd_vmid = 0;
 
-	tmp = RREG32_SOC15(GC, 0, regCP_HQD_PERSISTENT_STATE);
+	tmp = regCP_HQD_PERSISTENT_STATE_DEFAULT;
 	tmp = REG_SET_FIELD(tmp, CP_HQD_PERSISTENT_STATE, PRELOAD_SIZE, 0x55);
 	mqd->cp_hqd_persistent_state = tmp;
 
 	/* set MIN_IB_AVAIL_SIZE */
-	tmp = RREG32_SOC15(GC, 0, regCP_HQD_IB_CONTROL);
+	tmp = regCP_HQD_IB_CONTROL_DEFAULT;
 	tmp = REG_SET_FIELD(tmp, CP_HQD_IB_CONTROL, MIN_IB_AVAIL_SIZE, 3);
 	mqd->cp_hqd_ib_control = tmp;
 
@@ -3429,7 +3447,7 @@ static int gfx_v12_0_gfxhub_enable(struct amdgpu_device *adev)
 	if (r)
 		return r;
 
-	adev->hdp.funcs->flush_hdp(adev, NULL);
+	amdgpu_device_flush_hdp(adev, NULL);
 
 	value = (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_ALWAYS) ?
 		false : true;
@@ -3981,17 +3999,6 @@ static void gfx_v12_0_update_coarse_grain_clock_gating(struct amdgpu_device *ade
 
 		if (def != data)
 			WREG32_SOC15(GC, 0, regRLC_CGCG_CGLS_CTRL_3D, data);
-
-		data = RREG32_SOC15(GC, 0, regSDMA0_RLC_CGCG_CTRL);
-		data &= ~SDMA0_RLC_CGCG_CTRL__CGCG_INT_ENABLE_MASK;
-		WREG32_SOC15(GC, 0, regSDMA0_RLC_CGCG_CTRL, data);
-
-		/* Some ASICs only have one SDMA instance, not need to configure SDMA1 */
-		if (adev->sdma.num_instances > 1) {
-			data = RREG32_SOC15(GC, 0, regSDMA1_RLC_CGCG_CTRL);
-			data &= ~SDMA1_RLC_CGCG_CTRL__CGCG_INT_ENABLE_MASK;
-			WREG32_SOC15(GC, 0, regSDMA1_RLC_CGCG_CTRL, data);
-		}
 	}
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index 9d741695ca07..1f675d67a1a7 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -4652,6 +4652,7 @@ static int gfx_v8_0_kcq_init_queue(struct amdgpu_ring *ring)
 			memcpy(mqd, adev->gfx.mec.mqd_backup[mqd_idx], sizeof(struct vi_mqd_allocation));
 		/* reset ring buffer */
 		ring->wptr = 0;
+		atomic64_set((atomic64_t *)ring->wptr_cpu_addr, 0);
 		amdgpu_ring_clear_ring(ring);
 	}
 	return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index e7cd51c95141..91af1adbf5e8 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -1269,6 +1269,7 @@ static void gfx_v9_0_check_fw_write_wait(struct amdgpu_device *adev)
 	adev->gfx.mec_fw_write_wait = false;
 
 	if ((amdgpu_ip_version(adev, GC_HWIP, 0) != IP_VERSION(9, 4, 1)) &&
+	    (amdgpu_ip_version(adev, GC_HWIP, 0) != IP_VERSION(9, 4, 2)) &&
 	    ((adev->gfx.mec_fw_version < 0x000001a5) ||
 	     (adev->gfx.mec_feature_version < 46) ||
 	     (adev->gfx.pfp_fw_version < 0x000000b7) ||
@@ -7251,10 +7252,6 @@ static int gfx_v9_0_reset_kcq(struct amdgpu_ring *ring,
 	unsigned long flags;
 	int i, r;
 
-	if (!adev->debug_exp_resets &&
-	    !adev->gfx.num_gfx_rings)
-		return -EINVAL;
-
 	if (amdgpu_sriov_vf(adev))
 		return -EINVAL;
 
@@ -7321,8 +7318,8 @@ static int gfx_v9_0_reset_kcq(struct amdgpu_ring *ring,
 	}
 	kiq->pmf->kiq_map_queues(kiq_ring, ring);
 	amdgpu_ring_commit(kiq_ring);
-	spin_unlock_irqrestore(&kiq->ring_lock, flags);
 	r = amdgpu_ring_test_ring(kiq_ring);
+	spin_unlock_irqrestore(&kiq->ring_lock, flags);
 	if (r) {
 		DRM_ERROR("fail to remap queue\n");
 		return r;
@@ -7419,6 +7416,34 @@ static void gfx_v9_0_ring_emit_cleaner_shader(struct amdgpu_ring *ring)
 	amdgpu_ring_write(ring, 0);  /* RESERVED field, programmed to zero */
 }
 
+static void gfx_v9_0_ring_begin_use_compute(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+
+	amdgpu_gfx_enforce_isolation_ring_begin_use(ring);
+
+	/* Raven and PCO APUs seem to have stability issues
+	 * with compute and gfxoff and gfx pg.  Disable gfx pg during
+	 * submission and allow again afterwards.
+	 */
+	if (amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 1, 0))
+		gfx_v9_0_set_powergating_state(adev, AMD_PG_STATE_UNGATE);
+}
+
+static void gfx_v9_0_ring_end_use_compute(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+
+	/* Raven and PCO APUs seem to have stability issues
+	 * with compute and gfxoff and gfx pg.  Disable gfx pg during
+	 * submission and allow again afterwards.
+	 */
+	if (amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 1, 0))
+		gfx_v9_0_set_powergating_state(adev, AMD_PG_STATE_GATE);
+
+	amdgpu_gfx_enforce_isolation_ring_end_use(ring);
+}
+
 static const struct amd_ip_funcs gfx_v9_0_ip_funcs = {
 	.name = "gfx_v9_0",
 	.early_init = gfx_v9_0_early_init,
@@ -7595,8 +7620,8 @@ static const struct amdgpu_ring_funcs gfx_v9_0_ring_funcs_compute = {
 	.emit_wave_limit = gfx_v9_0_emit_wave_limit,
 	.reset = gfx_v9_0_reset_kcq,
 	.emit_cleaner_shader = gfx_v9_0_ring_emit_cleaner_shader,
-	.begin_use = amdgpu_gfx_enforce_isolation_ring_begin_use,
-	.end_use = amdgpu_gfx_enforce_isolation_ring_end_use,
+	.begin_use = gfx_v9_0_ring_begin_use_compute,
+	.end_use = gfx_v9_0_ring_end_use_compute,
 };
 
 static const struct amdgpu_ring_funcs gfx_v9_0_ring_funcs_kiq = {
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
index ffdb966c4127..f27ccb8f3c8c 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
@@ -3062,9 +3062,6 @@ static void gfx_v9_4_3_ring_soft_recovery(struct amdgpu_ring *ring,
 	struct amdgpu_device *adev = ring->adev;
 	uint32_t value = 0;
 
-	if (!adev->debug_exp_resets)
-		return;
-
 	value = REG_SET_FIELD(value, SQ_CMD, CMD, 0x03);
 	value = REG_SET_FIELD(value, SQ_CMD, MODE, 0x01);
 	value = REG_SET_FIELD(value, SQ_CMD, CHECK_VMID, 1);
@@ -3580,9 +3577,6 @@ static int gfx_v9_4_3_reset_kcq(struct amdgpu_ring *ring,
 	unsigned long flags;
 	int r;
 
-	if (!adev->debug_exp_resets)
-		return -EINVAL;
-
 	if (amdgpu_sriov_vf(adev))
 		return -EINVAL;
 
@@ -3646,9 +3640,8 @@ pipe_reset:
 	}
 	kiq->pmf->kiq_map_queues(kiq_ring, ring);
 	amdgpu_ring_commit(kiq_ring);
-	spin_unlock_irqrestore(&kiq->ring_lock, flags);
-
 	r = amdgpu_ring_test_ring(kiq_ring);
+	spin_unlock_irqrestore(&kiq->ring_lock, flags);
 	if (r) {
 		dev_err(adev->dev, "fail to remap queue\n");
 		return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c
index 0e3ddea7b8e0..a7bfc9f41d0e 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c
@@ -92,12 +92,12 @@ static void gfxhub_v1_0_init_system_aperture_regs(struct amdgpu_device *adev)
 {
 	uint64_t value;
 
-	/* Program the AGP BAR */
-	WREG32_SOC15_RLC(GC, 0, mmMC_VM_AGP_BASE, 0);
-	WREG32_SOC15_RLC(GC, 0, mmMC_VM_AGP_BOT, adev->gmc.agp_start >> 24);
-	WREG32_SOC15_RLC(GC, 0, mmMC_VM_AGP_TOP, adev->gmc.agp_end >> 24);
-
 	if (!amdgpu_sriov_vf(adev) || adev->asic_type <= CHIP_VEGA10) {
+		/* Program the AGP BAR */
+		WREG32_SOC15_RLC(GC, 0, mmMC_VM_AGP_BASE, 0);
+		WREG32_SOC15_RLC(GC, 0, mmMC_VM_AGP_BOT, adev->gmc.agp_start >> 24);
+		WREG32_SOC15_RLC(GC, 0, mmMC_VM_AGP_TOP, adev->gmc.agp_end >> 24);
+
 		/* Program the system aperture low logical page number. */
 		WREG32_SOC15_RLC(GC, 0, mmMC_VM_SYSTEM_APERTURE_LOW_ADDR,
 			min(adev->gmc.fb_start, adev->gmc.agp_start) >> 18);
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
index 9784a2892185..c6e742921282 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
@@ -265,7 +265,7 @@ static void gmc_v10_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
 	ack = hub->vm_inv_eng0_ack + hub->eng_distance * eng;
 
 	/* flush hdp cache */
-	adev->hdp.funcs->flush_hdp(adev, NULL);
+	amdgpu_device_flush_hdp(adev, NULL);
 
 	/* This is necessary for SRIOV as well as for GFXOFF to function
 	 * properly under bare metal
@@ -966,7 +966,7 @@ static int gmc_v10_0_gart_enable(struct amdgpu_device *adev)
 	adev->hdp.funcs->init_registers(adev);
 
 	/* Flush HDP after it is initialized */
-	adev->hdp.funcs->flush_hdp(adev, NULL);
+	amdgpu_device_flush_hdp(adev, NULL);
 
 	value = (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_ALWAYS) ?
 		false : true;
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c
index 2797fd84432b..87aaf5f1224f 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c
@@ -226,7 +226,7 @@ static void gmc_v11_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
 	ack = hub->vm_inv_eng0_ack + hub->eng_distance * eng;
 
 	/* flush hdp cache */
-	adev->hdp.funcs->flush_hdp(adev, NULL);
+	amdgpu_device_flush_hdp(adev, NULL);
 
 	/* This is necessary for SRIOV as well as for GFXOFF to function
 	 * properly under bare metal
@@ -747,6 +747,18 @@ static int gmc_v11_0_sw_init(void *handle)
 	adev->gmc.vram_type = vram_type;
 	adev->gmc.vram_vendor = vram_vendor;
 
+	/* The mall_size is already calculated as mall_size_per_umc * num_umc.
+	 * However, for gfx1151, which features a 2-to-1 UMC mapping,
+	 * the result must be multiplied by 2 to determine the actual mall size.
+	 */
+	switch (amdgpu_ip_version(adev, GC_HWIP, 0)) {
+	case IP_VERSION(11, 5, 1):
+		adev->gmc.mall_size *= 2;
+		break;
+	default:
+		break;
+	}
+
 	switch (amdgpu_ip_version(adev, GC_HWIP, 0)) {
 	case IP_VERSION(11, 0, 0):
 	case IP_VERSION(11, 0, 1):
@@ -893,7 +905,7 @@ static int gmc_v11_0_gart_enable(struct amdgpu_device *adev)
 		return r;
 
 	/* Flush HDP after it is initialized */
-	adev->hdp.funcs->flush_hdp(adev, NULL);
+	amdgpu_device_flush_hdp(adev, NULL);
 
 	value = (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_ALWAYS) ?
 		false : true;
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c
index edcb5351f8cc..525e435ee22d 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c
@@ -294,7 +294,7 @@ static void gmc_v12_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
 		return;
 
 	/* flush hdp cache */
-	adev->hdp.funcs->flush_hdp(adev, NULL);
+	amdgpu_device_flush_hdp(adev, NULL);
 
 	/* This is necessary for SRIOV as well as for GFXOFF to function
 	 * properly under bare metal
@@ -498,9 +498,6 @@ static void gmc_v12_0_get_vm_pte(struct amdgpu_device *adev,
 				 uint64_t *flags)
 {
 	struct amdgpu_bo *bo = mapping->bo_va->base.bo;
-	struct amdgpu_device *bo_adev;
-	bool coherent, is_system;
-
 
 	*flags &= ~AMDGPU_PTE_EXECUTABLE;
 	*flags |= mapping->flags & AMDGPU_PTE_EXECUTABLE;
@@ -516,25 +513,11 @@ static void gmc_v12_0_get_vm_pte(struct amdgpu_device *adev,
 		*flags &= ~AMDGPU_PTE_VALID;
 	}
 
-	if (!bo)
-		return;
-
-	if (bo->flags & (AMDGPU_GEM_CREATE_COHERENT |
-			       AMDGPU_GEM_CREATE_UNCACHED))
-		*flags = AMDGPU_PTE_MTYPE_GFX12(*flags, MTYPE_UC);
-
-	bo_adev = amdgpu_ttm_adev(bo->tbo.bdev);
-	coherent = bo->flags & AMDGPU_GEM_CREATE_COHERENT;
-	is_system = (bo->tbo.resource->mem_type == TTM_PL_TT) ||
-		(bo->tbo.resource->mem_type == AMDGPU_PL_PREEMPT);
-
 	if (bo && bo->flags & AMDGPU_GEM_CREATE_GFX12_DCC)
 		*flags |= AMDGPU_PTE_DCC;
 
-	/* WA for HW bug */
-	if (is_system || ((bo_adev != adev) && coherent))
-		*flags = AMDGPU_PTE_MTYPE_GFX12(*flags, MTYPE_NC);
-
+	if (bo && bo->flags & AMDGPU_GEM_CREATE_UNCACHED)
+		*flags = AMDGPU_PTE_MTYPE_GFX12(*flags, MTYPE_UC);
 }
 
 static unsigned gmc_v12_0_get_vbios_fb_size(struct amdgpu_device *adev)
@@ -879,7 +862,7 @@ static int gmc_v12_0_gart_enable(struct amdgpu_device *adev)
 		return r;
 
 	/* Flush HDP after it is initialized */
-	adev->hdp.funcs->flush_hdp(adev, NULL);
+	amdgpu_device_flush_hdp(adev, NULL);
 
 	value = (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_ALWAYS) ?
 		false : true;
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index 7a45f3fdc734..78c527b56f7c 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -1461,7 +1461,6 @@ static void gmc_v9_0_set_umc_funcs(struct amdgpu_device *adev)
 		adev->umc.umc_inst_num = UMC_V12_0_UMC_INSTANCE_NUM;
 		adev->umc.node_inst_num /= UMC_V12_0_UMC_INSTANCE_NUM;
 		adev->umc.channel_offs = UMC_V12_0_PER_CHANNEL_OFFSET;
-		adev->umc.active_mask = adev->aid_mask;
 		adev->umc.retire_unit = UMC_V12_0_BAD_PAGE_NUM_PER_CHANNEL;
 		if (!adev->gmc.xgmi.connected_to_cpu && !adev->gmc.is_app_apu)
 			adev->umc.ras = &umc_v12_0_ras;
@@ -2351,7 +2350,7 @@ static int gmc_v9_0_hw_init(void *handle)
 	adev->hdp.funcs->init_registers(adev);
 
 	/* After HDP is initialized, flush HDP.*/
-	adev->hdp.funcs->flush_hdp(adev, NULL);
+	amdgpu_device_flush_hdp(adev, NULL);
 
 	if (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_ALWAYS)
 		value = false;
diff --git a/drivers/gpu/drm/amd/amdgpu/hdp_v4_0.c b/drivers/gpu/drm/amd/amdgpu/hdp_v4_0.c
index 194026e9be33..1ca1bbe7784e 100644
--- a/drivers/gpu/drm/amd/amdgpu/hdp_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/hdp_v4_0.c
@@ -42,7 +42,12 @@ static void hdp_v4_0_flush_hdp(struct amdgpu_device *adev,
 {
 	if (!ring || !ring->funcs->emit_wreg) {
 		WREG32((adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2, 0);
-		RREG32((adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2);
+		/* We just need to read back a register to post the write.
+		 * Reading back the remapped register causes problems on
+		 * some platforms so just read back the memory size register.
+		 */
+		if (adev->nbio.funcs->get_memsize)
+			adev->nbio.funcs->get_memsize(adev);
 	} else {
 		amdgpu_ring_emit_wreg(ring, (adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2, 0);
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/hdp_v5_0.c b/drivers/gpu/drm/amd/amdgpu/hdp_v5_0.c
index d3962d469088..40705e13ca56 100644
--- a/drivers/gpu/drm/amd/amdgpu/hdp_v5_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/hdp_v5_0.c
@@ -33,7 +33,12 @@ static void hdp_v5_0_flush_hdp(struct amdgpu_device *adev,
 {
 	if (!ring || !ring->funcs->emit_wreg) {
 		WREG32((adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2, 0);
-		RREG32((adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2);
+		/* We just need to read back a register to post the write.
+		 * Reading back the remapped register causes problems on
+		 * some platforms so just read back the memory size register.
+		 */
+		if (adev->nbio.funcs->get_memsize)
+			adev->nbio.funcs->get_memsize(adev);
 	} else {
 		amdgpu_ring_emit_wreg(ring, (adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2, 0);
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/hdp_v5_2.c b/drivers/gpu/drm/amd/amdgpu/hdp_v5_2.c
index f52552c5fa27..6b9f2e1d9d69 100644
--- a/drivers/gpu/drm/amd/amdgpu/hdp_v5_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/hdp_v5_2.c
@@ -34,7 +34,17 @@ static void hdp_v5_2_flush_hdp(struct amdgpu_device *adev,
 	if (!ring || !ring->funcs->emit_wreg) {
 		WREG32_NO_KIQ((adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2,
 			0);
-		RREG32_NO_KIQ((adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2);
+		if (amdgpu_sriov_vf(adev)) {
+			/* this is fine because SR_IOV doesn't remap the register */
+			RREG32_NO_KIQ((adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2);
+		} else {
+			/* We just need to read back a register to post the write.
+			 * Reading back the remapped register causes problems on
+			 * some platforms so just read back the memory size register.
+			 */
+			if (adev->nbio.funcs->get_memsize)
+				adev->nbio.funcs->get_memsize(adev);
+		}
 	} else {
 		amdgpu_ring_emit_wreg(ring,
 			(adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2,
diff --git a/drivers/gpu/drm/amd/amdgpu/hdp_v6_0.c b/drivers/gpu/drm/amd/amdgpu/hdp_v6_0.c
index 6948fe9956ce..20da813299f0 100644
--- a/drivers/gpu/drm/amd/amdgpu/hdp_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/hdp_v6_0.c
@@ -36,7 +36,12 @@ static void hdp_v6_0_flush_hdp(struct amdgpu_device *adev,
 {
 	if (!ring || !ring->funcs->emit_wreg) {
 		WREG32((adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2, 0);
-		RREG32((adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2);
+		/* We just need to read back a register to post the write.
+		 * Reading back the remapped register causes problems on
+		 * some platforms so just read back the memory size register.
+		 */
+		if (adev->nbio.funcs->get_memsize)
+			adev->nbio.funcs->get_memsize(adev);
 	} else {
 		amdgpu_ring_emit_wreg(ring, (adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2, 0);
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/hdp_v7_0.c b/drivers/gpu/drm/amd/amdgpu/hdp_v7_0.c
index 63820329f67e..f7ecdd15d528 100644
--- a/drivers/gpu/drm/amd/amdgpu/hdp_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/hdp_v7_0.c
@@ -33,7 +33,12 @@ static void hdp_v7_0_flush_hdp(struct amdgpu_device *adev,
 {
 	if (!ring || !ring->funcs->emit_wreg) {
 		WREG32((adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2, 0);
-		RREG32((adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2);
+		/* We just need to read back a register to post the write.
+		 * Reading back the remapped register causes problems on
+		 * some platforms so just read back the memory size register.
+		 */
+		if (adev->nbio.funcs->get_memsize)
+			adev->nbio.funcs->get_memsize(adev);
 	} else {
 		amdgpu_ring_emit_wreg(ring, (adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2, 0);
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c b/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c
index d4f72e47ae9e..c4f5cbf1ecd7 100644
--- a/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c
@@ -32,6 +32,7 @@
 #include "gc/gc_11_0_0_sh_mask.h"
 
 MODULE_FIRMWARE("amdgpu/gc_11_0_0_imu.bin");
+MODULE_FIRMWARE("amdgpu/gc_11_0_0_imu_kicker.bin");
 MODULE_FIRMWARE("amdgpu/gc_11_0_1_imu.bin");
 MODULE_FIRMWARE("amdgpu/gc_11_0_2_imu.bin");
 MODULE_FIRMWARE("amdgpu/gc_11_0_3_imu.bin");
@@ -50,7 +51,10 @@ static int imu_v11_0_init_microcode(struct amdgpu_device *adev)
 	DRM_DEBUG("\n");
 
 	amdgpu_ucode_ip_version_decode(adev, GC_HWIP, ucode_prefix, sizeof(ucode_prefix));
-	err = amdgpu_ucode_request(adev, &adev->gfx.imu_fw, "amdgpu/%s_imu.bin", ucode_prefix);
+	if (amdgpu_is_kicker_fw(adev))
+		err = amdgpu_ucode_request(adev, &adev->gfx.imu_fw, "amdgpu/%s_imu_kicker.bin", ucode_prefix);
+	else
+		err = amdgpu_ucode_request(adev, &adev->gfx.imu_fw, "amdgpu/%s_imu.bin", ucode_prefix);
 	if (err)
 		goto out;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
index 231a3d490ea8..49113df8baef 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
@@ -690,7 +690,7 @@ static int mes_v11_0_set_hw_resources(struct amdgpu_mes *mes)
 
 static int mes_v11_0_set_hw_resources_1(struct amdgpu_mes *mes)
 {
-	int size = 128 * PAGE_SIZE;
+	int size = 128 * AMDGPU_GPU_PAGE_SIZE;
 	int ret = 0;
 	struct amdgpu_device *adev = mes->adev;
 	union MESAPI_SET_HW_RESOURCES_1 mes_set_hw_res_pkt;
@@ -859,6 +859,10 @@ static void mes_v11_0_get_fw_version(struct amdgpu_device *adev)
 {
 	int pipe;
 
+	/* return early if we have already fetched these */
+	if (adev->mes.sched_version && adev->mes.kiq_version)
+		return;
+
 	/* get MES scheduler/KIQ versions */
 	mutex_lock(&adev->srbm_mutex);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
index b3175ff676f3..459f7b8d72b4 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
@@ -1225,17 +1225,20 @@ static int mes_v12_0_queue_init(struct amdgpu_device *adev,
 		mes_v12_0_queue_init_register(ring);
 	}
 
-	/* get MES scheduler/KIQ versions */
-	mutex_lock(&adev->srbm_mutex);
-	soc21_grbm_select(adev, 3, pipe, 0, 0);
+	if (((pipe == AMDGPU_MES_SCHED_PIPE) && !adev->mes.sched_version) ||
+	    ((pipe == AMDGPU_MES_KIQ_PIPE) && !adev->mes.kiq_version)) {
+		/* get MES scheduler/KIQ versions */
+		mutex_lock(&adev->srbm_mutex);
+		soc21_grbm_select(adev, 3, pipe, 0, 0);
 
-	if (pipe == AMDGPU_MES_SCHED_PIPE)
-		adev->mes.sched_version = RREG32_SOC15(GC, 0, regCP_MES_GP3_LO);
-	else if (pipe == AMDGPU_MES_KIQ_PIPE && adev->enable_mes_kiq)
-		adev->mes.kiq_version = RREG32_SOC15(GC, 0, regCP_MES_GP3_LO);
+		if (pipe == AMDGPU_MES_SCHED_PIPE)
+			adev->mes.sched_version = RREG32_SOC15(GC, 0, regCP_MES_GP3_LO);
+		else if (pipe == AMDGPU_MES_KIQ_PIPE && adev->enable_mes_kiq)
+			adev->mes.kiq_version = RREG32_SOC15(GC, 0, regCP_MES_GP3_LO);
 
-	soc21_grbm_select(adev, 0, 0, 0, 0);
-	mutex_unlock(&adev->srbm_mutex);
+		soc21_grbm_select(adev, 0, 0, 0, 0);
+		mutex_unlock(&adev->srbm_mutex);
+	}
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_7.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_7.c
index 9689e2b5d4e5..2adee2b94c37 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_7.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_7.c
@@ -172,6 +172,30 @@ static void mmhub_v1_7_init_tlb_regs(struct amdgpu_device *adev)
 	WREG32_SOC15(MMHUB, 0, regMC_VM_MX_L1_TLB_CNTL, tmp);
 }
 
+/* Set snoop bit for SDMA so that SDMA writes probe-invalidates RW lines */
+static void mmhub_v1_7_init_snoop_override_regs(struct amdgpu_device *adev)
+{
+	uint32_t tmp;
+	int i;
+	uint32_t distance = regDAGB1_WRCLI_GPU_SNOOP_OVERRIDE -
+			    regDAGB0_WRCLI_GPU_SNOOP_OVERRIDE;
+
+	for (i = 0; i < 5; i++) { /* DAGB instances */
+		tmp = RREG32_SOC15_OFFSET(MMHUB, 0,
+			regDAGB0_WRCLI_GPU_SNOOP_OVERRIDE, i * distance);
+		tmp |= (1 << 15); /* SDMA client is BIT15 */
+		WREG32_SOC15_OFFSET(MMHUB, 0,
+			regDAGB0_WRCLI_GPU_SNOOP_OVERRIDE, i * distance, tmp);
+
+		tmp = RREG32_SOC15_OFFSET(MMHUB, 0,
+			regDAGB0_WRCLI_GPU_SNOOP_OVERRIDE_VALUE, i * distance);
+		tmp |= (1 << 15);
+		WREG32_SOC15_OFFSET(MMHUB, 0,
+			regDAGB0_WRCLI_GPU_SNOOP_OVERRIDE_VALUE, i * distance, tmp);
+	}
+
+}
+
 static void mmhub_v1_7_init_cache_regs(struct amdgpu_device *adev)
 {
 	uint32_t tmp;
@@ -337,6 +361,7 @@ static int mmhub_v1_7_gart_enable(struct amdgpu_device *adev)
 	mmhub_v1_7_init_system_aperture_regs(adev);
 	mmhub_v1_7_init_tlb_regs(adev);
 	mmhub_v1_7_init_cache_regs(adev);
+	mmhub_v1_7_init_snoop_override_regs(adev);
 
 	mmhub_v1_7_enable_system_domain(adev);
 	mmhub_v1_7_disable_identity_aperture(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_8.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_8.c
index b01bb759d0f4..2276c644a697 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_8.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_8.c
@@ -214,6 +214,32 @@ static void mmhub_v1_8_init_tlb_regs(struct amdgpu_device *adev)
 	}
 }
 
+/* Set snoop bit for SDMA so that SDMA writes probe-invalidates RW lines */
+static void mmhub_v1_8_init_snoop_override_regs(struct amdgpu_device *adev)
+{
+	uint32_t tmp, inst_mask;
+	int i, j;
+	uint32_t distance = regDAGB1_WRCLI_GPU_SNOOP_OVERRIDE -
+			    regDAGB0_WRCLI_GPU_SNOOP_OVERRIDE;
+
+	inst_mask = adev->aid_mask;
+	for_each_inst(i, inst_mask) {
+		for (j = 0; j < 5; j++) { /* DAGB instances */
+			tmp = RREG32_SOC15_OFFSET(MMHUB, i,
+				regDAGB0_WRCLI_GPU_SNOOP_OVERRIDE, j * distance);
+			tmp |= (1 << 15); /* SDMA client is BIT15 */
+			WREG32_SOC15_OFFSET(MMHUB, i,
+				regDAGB0_WRCLI_GPU_SNOOP_OVERRIDE, j * distance, tmp);
+
+			tmp = RREG32_SOC15_OFFSET(MMHUB, i,
+				regDAGB0_WRCLI_GPU_SNOOP_OVERRIDE_VALUE, j * distance);
+			tmp |= (1 << 15);
+			WREG32_SOC15_OFFSET(MMHUB, i,
+				regDAGB0_WRCLI_GPU_SNOOP_OVERRIDE_VALUE, j * distance, tmp);
+		}
+	}
+}
+
 static void mmhub_v1_8_init_cache_regs(struct amdgpu_device *adev)
 {
 	uint32_t tmp, inst_mask;
@@ -419,6 +445,7 @@ static int mmhub_v1_8_gart_enable(struct amdgpu_device *adev)
 	mmhub_v1_8_init_system_aperture_regs(adev);
 	mmhub_v1_8_init_tlb_regs(adev);
 	mmhub_v1_8_init_cache_regs(adev);
+	mmhub_v1_8_init_snoop_override_regs(adev);
 
 	mmhub_v1_8_enable_system_domain(adev);
 	mmhub_v1_8_disable_identity_aperture(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c
index ff1b58e44689..fe0710b55c3a 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c
@@ -198,6 +198,36 @@ static void mmhub_v9_4_init_tlb_regs(struct amdgpu_device *adev, int hubid)
 			    hubid * MMHUB_INSTANCE_REGISTER_OFFSET, tmp);
 }
 
+/* Set snoop bit for SDMA so that SDMA writes probe-invalidates RW lines */
+static void mmhub_v9_4_init_snoop_override_regs(struct amdgpu_device *adev, int hubid)
+{
+	uint32_t tmp;
+	int i;
+	uint32_t distance = mmDAGB1_WRCLI_GPU_SNOOP_OVERRIDE -
+			    mmDAGB0_WRCLI_GPU_SNOOP_OVERRIDE;
+	uint32_t huboffset = hubid * MMHUB_INSTANCE_REGISTER_OFFSET;
+
+	for (i = 0; i < 5 - (2 * hubid); i++) {
+		/* DAGB instances 0 to 4 are in hub0 and 5 to 7 are in hub1 */
+		tmp = RREG32_SOC15_OFFSET(MMHUB, 0,
+			mmDAGB0_WRCLI_GPU_SNOOP_OVERRIDE,
+			huboffset + i * distance);
+		tmp |= (1 << 15); /* SDMA client is BIT15 */
+		WREG32_SOC15_OFFSET(MMHUB, 0,
+			mmDAGB0_WRCLI_GPU_SNOOP_OVERRIDE,
+			huboffset + i * distance, tmp);
+
+		tmp = RREG32_SOC15_OFFSET(MMHUB, 0,
+			mmDAGB0_WRCLI_GPU_SNOOP_OVERRIDE_VALUE,
+			huboffset + i * distance);
+		tmp |= (1 << 15);
+		WREG32_SOC15_OFFSET(MMHUB, 0,
+			mmDAGB0_WRCLI_GPU_SNOOP_OVERRIDE_VALUE,
+			huboffset + i * distance, tmp);
+	}
+
+}
+
 static void mmhub_v9_4_init_cache_regs(struct amdgpu_device *adev, int hubid)
 {
 	uint32_t tmp;
@@ -392,6 +422,7 @@ static int mmhub_v9_4_gart_enable(struct amdgpu_device *adev)
 		if (!amdgpu_sriov_vf(adev))
 			mmhub_v9_4_init_cache_regs(adev, i);
 
+		mmhub_v9_4_init_snoop_override_regs(adev, i);
 		mmhub_v9_4_enable_system_domain(adev, i);
 		if (!amdgpu_sriov_vf(adev))
 			mmhub_v9_4_disable_identity_aperture(adev, i);
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_11.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_11.c
index 41421da63a08..a11f556b3ff1 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_11.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_11.c
@@ -361,7 +361,7 @@ static void nbio_v7_11_get_clockgating_state(struct amdgpu_device *adev,
 		*flags |= AMD_CG_SUPPORT_BIF_LS;
 }
 
-#define MMIO_REG_HOLE_OFFSET (0x80000 - PAGE_SIZE)
+#define MMIO_REG_HOLE_OFFSET 0x44000
 
 static void nbio_v7_11_set_reg_remap(struct amdgpu_device *adev)
 {
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c
index d1bd79bbae53..8e401f8b2a05 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c
@@ -32,9 +32,6 @@
 
 #define NPS_MODE_MASK 0x000000FFL
 
-/* Core 0 Port 0 counter */
-#define smnPCIEP_NAK_COUNTER 0x1A340218
-
 static void nbio_v7_9_remap_hdp_registers(struct amdgpu_device *adev)
 {
 	WREG32_SOC15(NBIO, 0, regBIF_BX0_REMAP_HDP_MEM_FLUSH_CNTL,
@@ -453,22 +450,6 @@ static void nbio_v7_9_init_registers(struct amdgpu_device *adev)
 	}
 }
 
-static u64 nbio_v7_9_get_pcie_replay_count(struct amdgpu_device *adev)
-{
-	u32 val, nak_r, nak_g;
-
-	if (adev->flags & AMD_IS_APU)
-		return 0;
-
-	/* Get the number of NAKs received and generated */
-	val = RREG32_PCIE(smnPCIEP_NAK_COUNTER);
-	nak_r = val & 0xFFFF;
-	nak_g = val >> 16;
-
-	/* Add the total number of NAKs, i.e the number of replays */
-	return (nak_r + nak_g);
-}
-
 #define MMIO_REG_HOLE_OFFSET 0x1A000
 
 static void nbio_v7_9_set_reg_remap(struct amdgpu_device *adev)
@@ -509,7 +490,6 @@ const struct amdgpu_nbio_funcs nbio_v7_9_funcs = {
 	.get_compute_partition_mode = nbio_v7_9_get_compute_partition_mode,
 	.get_memory_partition_mode = nbio_v7_9_get_memory_partition_mode,
 	.init_registers = nbio_v7_9_init_registers,
-	.get_pcie_replay_count = nbio_v7_9_get_pcie_replay_count,
 	.set_reg_remap = nbio_v7_9_set_reg_remap,
 };
 
diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c
index 73065a85e0d2..ab0eecbab412 100644
--- a/drivers/gpu/drm/amd/amdgpu/nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/nv.c
@@ -78,12 +78,12 @@ static const struct amdgpu_video_codecs nv_video_codecs_encode = {
 
 /* Navi1x */
 static const struct amdgpu_video_codec_info nv_video_codecs_decode_array[] = {
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4096, 3)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4096, 5)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 1920, 1088, 3)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 1920, 1088, 5)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 52)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4096, 4)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 1920, 1088, 4)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 8192, 8192, 0)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)},
 };
 
@@ -104,10 +104,10 @@ static const struct amdgpu_video_codecs sc_video_codecs_encode = {
 };
 
 static const struct amdgpu_video_codec_info sc_video_codecs_decode_array_vcn0[] = {
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4096, 3)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4096, 5)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 1920, 1088, 3)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 1920, 1088, 5)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 52)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4096, 4)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 1920, 1088, 4)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 16384, 16384, 0)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)},
@@ -115,10 +115,10 @@ static const struct amdgpu_video_codec_info sc_video_codecs_decode_array_vcn0[]
 };
 
 static const struct amdgpu_video_codec_info sc_video_codecs_decode_array_vcn1[] = {
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4096, 3)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4096, 5)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 1920, 1088, 3)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 1920, 1088, 5)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 52)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4096, 4)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 1920, 1088, 4)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 16384, 16384, 0)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)},
@@ -141,23 +141,23 @@ static struct amdgpu_video_codec_info sriov_sc_video_codecs_encode_array[] = {
 };
 
 static struct amdgpu_video_codec_info sriov_sc_video_codecs_decode_array_vcn0[] = {
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4096, 3)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4096, 5)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 1920, 1088, 3)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 1920, 1088, 5)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 52)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4096, 4)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 1920, 1088, 4)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 16384, 16384, 0)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_AV1, 8192, 4352, 0)},
 };
 
 static struct amdgpu_video_codec_info sriov_sc_video_codecs_decode_array_vcn1[] = {
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4096, 3)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4096, 5)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 1920, 1088, 3)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 1920, 1088, 5)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 52)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4096, 4)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 1920, 1088, 4)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 16384, 16384, 0)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)},
 };
 
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
index 2395f1856962..e77a467af7ac 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
@@ -532,7 +532,7 @@ static int psp_v11_0_memory_training(struct psp_context *psp, uint32_t ops)
 			}
 
 			memcpy_toio(adev->mman.aper_base_kaddr, buf, sz);
-			adev->hdp.funcs->flush_hdp(adev, NULL);
+			amdgpu_device_flush_hdp(adev, NULL);
 			vfree(buf);
 			drm_dev_exit(idx);
 		} else {
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c
index 51e470e8d67d..124f74e862d7 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c
@@ -42,7 +42,9 @@ MODULE_FIRMWARE("amdgpu/psp_13_0_5_ta.bin");
 MODULE_FIRMWARE("amdgpu/psp_13_0_8_toc.bin");
 MODULE_FIRMWARE("amdgpu/psp_13_0_8_ta.bin");
 MODULE_FIRMWARE("amdgpu/psp_13_0_0_sos.bin");
+MODULE_FIRMWARE("amdgpu/psp_13_0_0_sos_kicker.bin");
 MODULE_FIRMWARE("amdgpu/psp_13_0_0_ta.bin");
+MODULE_FIRMWARE("amdgpu/psp_13_0_0_ta_kicker.bin");
 MODULE_FIRMWARE("amdgpu/psp_13_0_7_sos.bin");
 MODULE_FIRMWARE("amdgpu/psp_13_0_7_ta.bin");
 MODULE_FIRMWARE("amdgpu/psp_13_0_10_sos.bin");
@@ -600,7 +602,7 @@ static int psp_v13_0_memory_training(struct psp_context *psp, uint32_t ops)
 			}
 
 			memcpy_toio(adev->mman.aper_base_kaddr, buf, sz);
-			adev->hdp.funcs->flush_hdp(adev, NULL);
+			amdgpu_device_flush_hdp(adev, NULL);
 			vfree(buf);
 			drm_dev_exit(idx);
 		} else {
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v14_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v14_0.c
index 4d33c95a5116..89f6c06946c5 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v14_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v14_0.c
@@ -488,7 +488,7 @@ static int psp_v14_0_memory_training(struct psp_context *psp, uint32_t ops)
 			}
 
 			memcpy_toio(adev->mman.aper_base_kaddr, buf, sz);
-			adev->hdp.funcs->flush_hdp(adev, NULL);
+			amdgpu_device_flush_hdp(adev, NULL);
 			vfree(buf);
 			drm_dev_exit(idx);
 		} else {
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
index c77889040760..1e4ce06f5f2c 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
@@ -485,7 +485,7 @@ static void sdma_v4_4_2_inst_gfx_stop(struct amdgpu_device *adev,
 {
 	struct amdgpu_ring *sdma[AMDGPU_MAX_SDMA_INSTANCES];
 	u32 doorbell_offset, doorbell;
-	u32 rb_cntl, ib_cntl;
+	u32 rb_cntl, ib_cntl, sdma_cntl;
 	int i;
 
 	for_each_inst(i, inst_mask) {
@@ -497,6 +497,9 @@ static void sdma_v4_4_2_inst_gfx_stop(struct amdgpu_device *adev,
 		ib_cntl = RREG32_SDMA(i, regSDMA_GFX_IB_CNTL);
 		ib_cntl = REG_SET_FIELD(ib_cntl, SDMA_GFX_IB_CNTL, IB_ENABLE, 0);
 		WREG32_SDMA(i, regSDMA_GFX_IB_CNTL, ib_cntl);
+		sdma_cntl = RREG32_SDMA(i, regSDMA_CNTL);
+		sdma_cntl = REG_SET_FIELD(sdma_cntl, SDMA_CNTL, UTC_L1_ENABLE, 0);
+		WREG32_SDMA(i, regSDMA_CNTL, sdma_cntl);
 
 		if (sdma[i]->use_doorbell) {
 			doorbell = RREG32_SDMA(i, regSDMA_GFX_DOORBELL);
@@ -953,10 +956,13 @@ static int sdma_v4_4_2_inst_start(struct amdgpu_device *adev,
 		/* set utc l1 enable flag always to 1 */
 		temp = RREG32_SDMA(i, regSDMA_CNTL);
 		temp = REG_SET_FIELD(temp, SDMA_CNTL, UTC_L1_ENABLE, 1);
-		/* enable context empty interrupt during initialization */
-		temp = REG_SET_FIELD(temp, SDMA_CNTL, CTXEMPTY_INT_ENABLE, 1);
 		WREG32_SDMA(i, regSDMA_CNTL, temp);
 
+		if (amdgpu_ip_version(adev, SDMA0_HWIP, 0) < IP_VERSION(4, 4, 5)) {
+			/* enable context empty interrupt during initialization */
+			temp = REG_SET_FIELD(temp, SDMA_CNTL, CTXEMPTY_INT_ENABLE, 1);
+			WREG32_SDMA(i, regSDMA_CNTL, temp);
+		}
 		if (!amdgpu_sriov_vf(adev)) {
 			if (adev->firmware.load_type != AMDGPU_FW_LOAD_PSP) {
 				/* unhalt engine */
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c
index 9288f37a3cc5..843e6b46deee 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c
@@ -1688,11 +1688,12 @@ static void sdma_v7_0_emit_copy_buffer(struct amdgpu_ib *ib,
 				       uint32_t byte_count,
 				       uint32_t copy_flags)
 {
-	uint32_t num_type, data_format, max_com;
+	uint32_t num_type, data_format, max_com, write_cm;
 
 	max_com = AMDGPU_COPY_FLAGS_GET(copy_flags, MAX_COMPRESSED);
 	data_format = AMDGPU_COPY_FLAGS_GET(copy_flags, DATA_FORMAT);
 	num_type = AMDGPU_COPY_FLAGS_GET(copy_flags, NUMBER_TYPE);
+	write_cm = AMDGPU_COPY_FLAGS_GET(copy_flags, WRITE_COMPRESS_DISABLE) ? 2 : 1;
 
 	ib->ptr[ib->length_dw++] = SDMA_PKT_COPY_LINEAR_HEADER_OP(SDMA_OP_COPY) |
 		SDMA_PKT_COPY_LINEAR_HEADER_SUB_OP(SDMA_SUBOP_COPY_LINEAR) |
@@ -1709,7 +1710,7 @@ static void sdma_v7_0_emit_copy_buffer(struct amdgpu_ib *ib,
 	if ((copy_flags & (AMDGPU_COPY_FLAGS_READ_DECOMPRESSED | AMDGPU_COPY_FLAGS_WRITE_COMPRESSED)))
 		ib->ptr[ib->length_dw++] = SDMA_DCC_DATA_FORMAT(data_format) | SDMA_DCC_NUM_TYPE(num_type) |
 			((copy_flags & AMDGPU_COPY_FLAGS_READ_DECOMPRESSED) ? SDMA_DCC_READ_CM(2) : 0) |
-			((copy_flags & AMDGPU_COPY_FLAGS_WRITE_COMPRESSED) ? SDMA_DCC_WRITE_CM(1) : 0) |
+			((copy_flags & AMDGPU_COPY_FLAGS_WRITE_COMPRESSED) ? SDMA_DCC_WRITE_CM(write_cm) : 0) |
 			SDMA_DCC_MAX_COM(max_com) | SDMA_DCC_MAX_UCOM(1);
 	else
 		ib->ptr[ib->length_dw++] = 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index 307185c0e1b8..4cbe0da100d8 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -103,12 +103,11 @@ static const struct amdgpu_video_codecs vega_video_codecs_encode =
 /* Vega */
 static const struct amdgpu_video_codec_info vega_video_codecs_decode_array[] =
 {
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4096, 3)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4096, 5)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 1920, 1088, 3)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 1920, 1088, 5)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 52)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4096, 4)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 1920, 1088, 4)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 4096, 186)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)},
 };
 
 static const struct amdgpu_video_codecs vega_video_codecs_decode =
@@ -120,12 +119,12 @@ static const struct amdgpu_video_codecs vega_video_codecs_decode =
 /* Raven */
 static const struct amdgpu_video_codec_info rv_video_codecs_decode_array[] =
 {
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4096, 3)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4096, 5)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 1920, 1088, 3)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 1920, 1088, 5)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 52)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4096, 4)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 1920, 1088, 4)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 4096, 186)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 8192, 8192, 0)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 4096, 4096, 0)},
 };
 
@@ -138,10 +137,10 @@ static const struct amdgpu_video_codecs rv_video_codecs_decode =
 /* Renoir, Arcturus */
 static const struct amdgpu_video_codec_info rn_video_codecs_decode_array[] =
 {
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4096, 3)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4096, 5)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 1920, 1088, 3)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 1920, 1088, 5)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 52)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4096, 4)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 1920, 1088, 4)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 16384, 16384, 0)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)},
diff --git a/drivers/gpu/drm/amd/amdgpu/soc21.c b/drivers/gpu/drm/amd/amdgpu/soc21.c
index bba35880badb..04a1b2a46368 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc21.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc21.c
@@ -117,23 +117,17 @@ static struct amdgpu_video_codecs sriov_vcn_4_0_0_video_codecs_encode_vcn1 = {
 };
 
 static struct amdgpu_video_codec_info sriov_vcn_4_0_0_video_codecs_decode_array_vcn0[] = {
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4096, 3)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4096, 5)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 52)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4096, 4)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 16384, 16384, 0)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 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_decode_array_vcn1[] = {
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4096, 3)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4096, 5)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 52)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4096, 4)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 16384, 16384, 0)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)},
 };
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
index bfd067e2d2f1..f0edaabdcde5 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
@@ -39,6 +39,7 @@
 
 #define VCN_VID_SOC_ADDRESS_2_0					0x1fa00
 #define VCN1_VID_SOC_ADDRESS_3_0				0x48200
+#define VCN1_AON_SOC_ADDRESS_3_0				0x48000
 
 #define mmUVD_CONTEXT_ID_INTERNAL_OFFSET			0x1fd
 #define mmUVD_GPCOM_VCPU_CMD_INTERNAL_OFFSET			0x503
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
index 04e9e806e318..e4d0c0310e76 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
@@ -39,6 +39,7 @@
 
 #define VCN_VID_SOC_ADDRESS_2_0					0x1fa00
 #define VCN1_VID_SOC_ADDRESS_3_0				0x48200
+#define VCN1_AON_SOC_ADDRESS_3_0				0x48000
 
 #define mmUVD_CONTEXT_ID_INTERNAL_OFFSET			0x27
 #define mmUVD_GPCOM_VCPU_CMD_INTERNAL_OFFSET			0x0f
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
index 65dd68b32280..be86f86b49e9 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
@@ -40,6 +40,7 @@
 
 #define VCN_VID_SOC_ADDRESS_2_0					0x1fa00
 #define VCN1_VID_SOC_ADDRESS_3_0				0x48200
+#define VCN1_AON_SOC_ADDRESS_3_0				0x48000
 
 #define mmUVD_CONTEXT_ID_INTERNAL_OFFSET			0x27
 #define mmUVD_GPCOM_VCPU_CMD_INTERNAL_OFFSET			0x0f
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
index 26c6f10a8c8f..f391f0c54043 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
@@ -46,6 +46,7 @@
 
 #define VCN_VID_SOC_ADDRESS_2_0							0x1fb00
 #define VCN1_VID_SOC_ADDRESS_3_0						0x48300
+#define VCN1_AON_SOC_ADDRESS_3_0						0x48000
 
 #define VCN_HARVEST_MMSCH								0
 
@@ -575,7 +576,8 @@ static void vcn_v4_0_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_idx
 
 	/* VCN global tiling registers */
 	WREG32_SOC15_DPG_MODE(inst_idx, SOC15_DPG_MODE_OFFSET(
-		VCN, 0, regUVD_GFX10_ADDR_CONFIG), adev->gfx.config.gb_addr_config, 0, indirect);
+			VCN, inst_idx, regUVD_GFX10_ADDR_CONFIG),
+			adev->gfx.config.gb_addr_config, 0, indirect);
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
index 6fca2915ea8f..77542dabec59 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
@@ -44,6 +44,7 @@
 
 #define VCN_VID_SOC_ADDRESS_2_0		0x1fb00
 #define VCN1_VID_SOC_ADDRESS_3_0	0x48300
+#define VCN1_AON_SOC_ADDRESS_3_0	0x48000
 
 static const struct amdgpu_hwip_reg_entry vcn_reg_list_4_0_3[] = {
 	SOC15_REG_ENTRY_STR(VCN, 0, regUVD_POWER_STATUS),
@@ -943,6 +944,8 @@ static int vcn_v4_0_3_start_sriov(struct amdgpu_device *adev)
 	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
 		vcn_inst = GET_INST(VCN, i);
 
+		vcn_v4_0_3_fw_shared_init(adev, vcn_inst);
+
 		memset(&header, 0, sizeof(struct mmsch_v4_0_3_init_header));
 		header.version = MMSCH_VERSION;
 		header.total_size = sizeof(struct mmsch_v4_0_3_init_header) >> 2;
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
index 9d4f5352a62c..3d114ea7049f 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
@@ -46,6 +46,7 @@
 
 #define VCN_VID_SOC_ADDRESS_2_0						0x1fb00
 #define VCN1_VID_SOC_ADDRESS_3_0					(0x48300 + 0x38000)
+#define VCN1_AON_SOC_ADDRESS_3_0					(0x48000 + 0x38000)
 
 #define VCN_HARVEST_MMSCH							0
 
@@ -984,6 +985,10 @@ static int vcn_v4_0_5_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, b
 			ring->doorbell_index << VCN_RB1_DB_CTRL__OFFSET__SHIFT |
 			VCN_RB1_DB_CTRL__EN_MASK);
 
+	/* Keeping one read-back to ensure all register writes are done, otherwise
+	 * it may introduce race conditions */
+	RREG32_SOC15(VCN, inst_idx, regVCN_RB1_DB_CTRL);
+
 	return 0;
 }
 
@@ -1166,6 +1171,10 @@ static int vcn_v4_0_5_start(struct amdgpu_device *adev)
 		tmp |= VCN_RB_ENABLE__RB1_EN_MASK;
 		WREG32_SOC15(VCN, i, regVCN_RB_ENABLE, tmp);
 		fw_shared->sq.queue_mode &= ~(FW_QUEUE_RING_RESET | FW_QUEUE_DPG_HOLD_OFF);
+
+		/* Keeping one read-back to ensure all register writes are done, otherwise
+		 * it may introduce race conditions */
+		RREG32_SOC15(VCN, i, regVCN_RB_ENABLE);
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
index c305386358b4..d19eec4d4790 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
@@ -488,7 +488,8 @@ static void vcn_v5_0_0_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_i
 
 	/* VCN global tiling registers */
 	WREG32_SOC24_DPG_MODE(inst_idx, SOC24_DPG_MODE_OFFSET(
-		VCN, 0, regUVD_GFX10_ADDR_CONFIG), adev->gfx.config.gb_addr_config, 0, indirect);
+		VCN, inst_idx, regUVD_GFX10_ADDR_CONFIG),
+		adev->gfx.config.gb_addr_config, 0, indirect);
 
 	return;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c
new file mode 100644
index 000000000000..cdefd7fcb0da
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c
@@ -0,0 +1,1624 @@
+/*
+ * Copyright 2024 Advanced Micro Devices, Inc. All rights reserved.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+#include <linux/firmware.h>
+#include "amdgpu.h"
+#include "amdgpu_vcn.h"
+#include "amdgpu_pm.h"
+#include "soc15.h"
+#include "soc15d.h"
+#include "soc15_hw_ip.h"
+#include "vcn_v2_0.h"
+#include "vcn_v4_0_3.h"
+#include "mmsch_v5_0.h"
+
+#include "vcn/vcn_5_0_0_offset.h"
+#include "vcn/vcn_5_0_0_sh_mask.h"
+#include "ivsrcid/vcn/irqsrcs_vcn_5_0.h"
+#include "vcn_v5_0_0.h"
+#include "vcn_v5_0_1.h"
+
+#include <drm/drm_drv.h>
+
+static int vcn_v5_0_1_start_sriov(struct amdgpu_device *adev);
+static void vcn_v5_0_1_set_unified_ring_funcs(struct amdgpu_device *adev);
+static void vcn_v5_0_1_set_irq_funcs(struct amdgpu_device *adev);
+static int vcn_v5_0_1_set_pg_state(struct amdgpu_vcn_inst *vinst,
+				   enum amd_powergating_state state);
+static void vcn_v5_0_1_unified_ring_set_wptr(struct amdgpu_ring *ring);
+static void vcn_v5_0_1_set_ras_funcs(struct amdgpu_device *adev);
+/**
+ * vcn_v5_0_1_early_init - set function pointers and load microcode
+ *
+ * @ip_block: Pointer to the amdgpu_ip_block for this hw instance.
+ *
+ * Set ring and irq function pointers
+ * Load microcode from filesystem
+ */
+static int vcn_v5_0_1_early_init(struct amdgpu_ip_block *ip_block)
+{
+	struct amdgpu_device *adev = ip_block->adev;
+	int i, r;
+
+	for (i = 0; i < adev->vcn.num_vcn_inst; ++i)
+		/* re-use enc ring as unified ring */
+		adev->vcn.inst[i].num_enc_rings = 1;
+
+	vcn_v5_0_1_set_unified_ring_funcs(adev);
+	vcn_v5_0_1_set_irq_funcs(adev);
+	vcn_v5_0_1_set_ras_funcs(adev);
+
+	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
+		adev->vcn.inst[i].set_pg_state = vcn_v5_0_1_set_pg_state;
+
+		r = amdgpu_vcn_early_init(adev, i);
+		if (r)
+			return r;
+	}
+
+	return 0;
+}
+
+static void vcn_v5_0_1_fw_shared_init(struct amdgpu_device *adev, int inst_idx)
+{
+	struct amdgpu_vcn5_fw_shared *fw_shared;
+
+	fw_shared = adev->vcn.inst[inst_idx].fw_shared.cpu_addr;
+
+	if (fw_shared->sq.is_enabled)
+		return;
+	fw_shared->present_flag_0 =
+		cpu_to_le32(AMDGPU_FW_SHARED_FLAG_0_UNIFIED_QUEUE);
+	fw_shared->sq.is_enabled = 1;
+
+	if (amdgpu_vcnfw_log)
+		amdgpu_vcn_fwlog_init(&adev->vcn.inst[inst_idx]);
+}
+
+/**
+ * vcn_v5_0_1_sw_init - sw init for VCN block
+ *
+ * @ip_block: Pointer to the amdgpu_ip_block for this hw instance.
+ *
+ * Load firmware and sw initialization
+ */
+static int vcn_v5_0_1_sw_init(struct amdgpu_ip_block *ip_block)
+{
+	struct amdgpu_device *adev = ip_block->adev;
+	struct amdgpu_ring *ring;
+	int i, r, vcn_inst;
+
+	/* VCN UNIFIED TRAP */
+	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VCN,
+		VCN_5_0__SRCID__UVD_ENC_GENERAL_PURPOSE, &adev->vcn.inst->irq);
+	if (r)
+		return r;
+
+	/* VCN POISON TRAP */
+	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VCN,
+		VCN_5_0__SRCID_UVD_POISON, &adev->vcn.inst->ras_poison_irq);
+
+	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
+		vcn_inst = GET_INST(VCN, i);
+
+		r = amdgpu_vcn_sw_init(adev, i);
+		if (r)
+			return r;
+
+		amdgpu_vcn_setup_ucode(adev, i);
+
+		r = amdgpu_vcn_resume(adev, i);
+		if (r)
+			return r;
+
+		ring = &adev->vcn.inst[i].ring_enc[0];
+		ring->use_doorbell = true;
+		if (!amdgpu_sriov_vf(adev))
+			ring->doorbell_index =
+				(adev->doorbell_index.vcn.vcn_ring0_1 << 1) +
+				11 * vcn_inst;
+		else
+			ring->doorbell_index =
+				(adev->doorbell_index.vcn.vcn_ring0_1 << 1) +
+				32 * vcn_inst;
+
+		ring->vm_hub = AMDGPU_MMHUB0(adev->vcn.inst[i].aid_id);
+		sprintf(ring->name, "vcn_unified_%d", adev->vcn.inst[i].aid_id);
+
+		r = amdgpu_ring_init(adev, ring, 512, &adev->vcn.inst[i].irq, 0,
+					AMDGPU_RING_PRIO_DEFAULT, &adev->vcn.inst[i].sched_score);
+		if (r)
+			return r;
+
+		vcn_v5_0_1_fw_shared_init(adev, i);
+	}
+
+	/* TODO: Add queue reset mask when FW fully supports it */
+	adev->vcn.supported_reset =
+		amdgpu_get_soft_full_reset_mask(&adev->vcn.inst[0].ring_enc[0]);
+
+	if (amdgpu_sriov_vf(adev)) {
+		r = amdgpu_virt_alloc_mm_table(adev);
+		if (r)
+			return r;
+	}
+
+	vcn_v5_0_0_alloc_ip_dump(adev);
+
+	return amdgpu_vcn_sysfs_reset_mask_init(adev);
+}
+
+/**
+ * vcn_v5_0_1_sw_fini - sw fini for VCN block
+ *
+ * @ip_block: Pointer to the amdgpu_ip_block for this hw instance.
+ *
+ * VCN suspend and free up sw allocation
+ */
+static int vcn_v5_0_1_sw_fini(struct amdgpu_ip_block *ip_block)
+{
+	struct amdgpu_device *adev = ip_block->adev;
+	int i, r, idx;
+
+	if (drm_dev_enter(adev_to_drm(adev), &idx)) {
+		for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
+			volatile struct amdgpu_vcn5_fw_shared *fw_shared;
+
+			fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
+			fw_shared->present_flag_0 = 0;
+			fw_shared->sq.is_enabled = 0;
+		}
+
+		drm_dev_exit(idx);
+	}
+
+	if (amdgpu_sriov_vf(adev))
+		amdgpu_virt_free_mm_table(adev);
+
+	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
+		r = amdgpu_vcn_suspend(adev, i);
+		if (r)
+			return r;
+	}
+
+	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
+		r = amdgpu_vcn_sw_fini(adev, i);
+		if (r)
+			return r;
+	}
+
+	amdgpu_vcn_sysfs_reset_mask_fini(adev);
+
+	kfree(adev->vcn.ip_dump);
+
+	return 0;
+}
+
+/**
+ * vcn_v5_0_1_hw_init - start and test VCN block
+ *
+ * @ip_block: Pointer to the amdgpu_ip_block for this hw instance.
+ *
+ * Initialize the hardware, boot up the VCPU and do some testing
+ */
+static int vcn_v5_0_1_hw_init(struct amdgpu_ip_block *ip_block)
+{
+	struct amdgpu_device *adev = ip_block->adev;
+	struct amdgpu_ring *ring;
+	int i, r, vcn_inst;
+
+	if (amdgpu_sriov_vf(adev)) {
+		r = vcn_v5_0_1_start_sriov(adev);
+		if (r)
+			return r;
+
+		for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
+			ring = &adev->vcn.inst[i].ring_enc[0];
+			ring->wptr = 0;
+			ring->wptr_old = 0;
+			vcn_v5_0_1_unified_ring_set_wptr(ring);
+			ring->sched.ready = true;
+		}
+	} else {
+		if (RREG32_SOC15(VCN, GET_INST(VCN, 0), regVCN_RRMT_CNTL) & 0x100)
+			adev->vcn.caps |= AMDGPU_VCN_CAPS(RRMT_ENABLED);
+		for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
+			vcn_inst = GET_INST(VCN, i);
+			ring = &adev->vcn.inst[i].ring_enc[0];
+
+			if (ring->use_doorbell)
+				adev->nbio.funcs->vcn_doorbell_range(adev, ring->use_doorbell,
+					((adev->doorbell_index.vcn.vcn_ring0_1 << 1) +
+					11 * vcn_inst),
+					adev->vcn.inst[i].aid_id);
+
+			/* Re-init fw_shared, if required */
+			vcn_v5_0_1_fw_shared_init(adev, i);
+
+			r = amdgpu_ring_test_helper(ring);
+			if (r)
+				return r;
+		}
+	}
+
+	return 0;
+}
+
+/**
+ * vcn_v5_0_1_hw_fini - stop the hardware block
+ *
+ * @ip_block: Pointer to the amdgpu_ip_block for this hw instance.
+ *
+ * Stop the VCN block, mark ring as not ready any more
+ */
+static int vcn_v5_0_1_hw_fini(struct amdgpu_ip_block *ip_block)
+{
+	struct amdgpu_device *adev = ip_block->adev;
+	int i;
+
+	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
+		struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[i];
+
+		cancel_delayed_work_sync(&adev->vcn.inst[i].idle_work);
+		if (vinst->cur_state != AMD_PG_STATE_GATE)
+			vinst->set_pg_state(vinst, AMD_PG_STATE_GATE);
+	}
+
+	if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__VCN))
+		amdgpu_irq_put(adev, &adev->vcn.inst->ras_poison_irq, 0);
+
+	return 0;
+}
+
+/**
+ * vcn_v5_0_1_suspend - suspend VCN block
+ *
+ * @ip_block: Pointer to the amdgpu_ip_block for this hw instance.
+ *
+ * HW fini and suspend VCN block
+ */
+static int vcn_v5_0_1_suspend(struct amdgpu_ip_block *ip_block)
+{
+	struct amdgpu_device *adev = ip_block->adev;
+	int r, i;
+
+	r = vcn_v5_0_1_hw_fini(ip_block);
+	if (r)
+		return r;
+
+	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
+		r = amdgpu_vcn_suspend(ip_block->adev, i);
+		if (r)
+			return r;
+	}
+
+	return r;
+}
+
+/**
+ * vcn_v5_0_1_resume - resume VCN block
+ *
+ * @ip_block: Pointer to the amdgpu_ip_block for this hw instance.
+ *
+ * Resume firmware and hw init VCN block
+ */
+static int vcn_v5_0_1_resume(struct amdgpu_ip_block *ip_block)
+{
+	struct amdgpu_device *adev = ip_block->adev;
+	int r, i;
+
+	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
+		struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[i];
+
+		if (amdgpu_in_reset(adev))
+			vinst->cur_state = AMD_PG_STATE_GATE;
+
+		r = amdgpu_vcn_resume(ip_block->adev, i);
+		if (r)
+			return r;
+	}
+
+	r = vcn_v5_0_1_hw_init(ip_block);
+
+	return r;
+}
+
+/**
+ * vcn_v5_0_1_mc_resume - memory controller programming
+ *
+ * @vinst: VCN instance
+ *
+ * Let the VCN memory controller know it's offsets
+ */
+static void vcn_v5_0_1_mc_resume(struct amdgpu_vcn_inst *vinst)
+{
+	struct amdgpu_device *adev = vinst->adev;
+	int inst = vinst->inst;
+	uint32_t offset, size, vcn_inst;
+	const struct common_firmware_header *hdr;
+
+	hdr = (const struct common_firmware_header *)adev->vcn.inst[inst].fw->data;
+	size = AMDGPU_GPU_PAGE_ALIGN(le32_to_cpu(hdr->ucode_size_bytes) + 8);
+
+	vcn_inst = GET_INST(VCN, inst);
+	/* cache window 0: fw */
+	if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) {
+		WREG32_SOC15(VCN, vcn_inst, regUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW,
+			(adev->firmware.ucode[AMDGPU_UCODE_ID_VCN + inst].tmr_mc_addr_lo));
+		WREG32_SOC15(VCN, vcn_inst, regUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH,
+			(adev->firmware.ucode[AMDGPU_UCODE_ID_VCN + inst].tmr_mc_addr_hi));
+		WREG32_SOC15(VCN, vcn_inst, regUVD_VCPU_CACHE_OFFSET0, 0);
+		offset = 0;
+	} else {
+		WREG32_SOC15(VCN, vcn_inst, regUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW,
+			lower_32_bits(adev->vcn.inst[inst].gpu_addr));
+		WREG32_SOC15(VCN, vcn_inst, regUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH,
+			upper_32_bits(adev->vcn.inst[inst].gpu_addr));
+		offset = size;
+		WREG32_SOC15(VCN, vcn_inst, regUVD_VCPU_CACHE_OFFSET0,
+				AMDGPU_UVD_FIRMWARE_OFFSET >> 3);
+	}
+	WREG32_SOC15(VCN, vcn_inst, regUVD_VCPU_CACHE_SIZE0, size);
+
+	/* cache window 1: stack */
+	WREG32_SOC15(VCN, vcn_inst, regUVD_LMI_VCPU_CACHE1_64BIT_BAR_LOW,
+		lower_32_bits(adev->vcn.inst[inst].gpu_addr + offset));
+	WREG32_SOC15(VCN, vcn_inst, regUVD_LMI_VCPU_CACHE1_64BIT_BAR_HIGH,
+		upper_32_bits(adev->vcn.inst[inst].gpu_addr + offset));
+	WREG32_SOC15(VCN, vcn_inst, regUVD_VCPU_CACHE_OFFSET1, 0);
+	WREG32_SOC15(VCN, vcn_inst, regUVD_VCPU_CACHE_SIZE1, AMDGPU_VCN_STACK_SIZE);
+
+	/* cache window 2: context */
+	WREG32_SOC15(VCN, vcn_inst, regUVD_LMI_VCPU_CACHE2_64BIT_BAR_LOW,
+		lower_32_bits(adev->vcn.inst[inst].gpu_addr + offset + AMDGPU_VCN_STACK_SIZE));
+	WREG32_SOC15(VCN, vcn_inst, regUVD_LMI_VCPU_CACHE2_64BIT_BAR_HIGH,
+		upper_32_bits(adev->vcn.inst[inst].gpu_addr + offset + AMDGPU_VCN_STACK_SIZE));
+	WREG32_SOC15(VCN, vcn_inst, regUVD_VCPU_CACHE_OFFSET2, 0);
+	WREG32_SOC15(VCN, vcn_inst, regUVD_VCPU_CACHE_SIZE2, AMDGPU_VCN_CONTEXT_SIZE);
+
+	/* non-cache window */
+	WREG32_SOC15(VCN, vcn_inst, regUVD_LMI_VCPU_NC0_64BIT_BAR_LOW,
+		lower_32_bits(adev->vcn.inst[inst].fw_shared.gpu_addr));
+	WREG32_SOC15(VCN, vcn_inst, regUVD_LMI_VCPU_NC0_64BIT_BAR_HIGH,
+		upper_32_bits(adev->vcn.inst[inst].fw_shared.gpu_addr));
+	WREG32_SOC15(VCN, vcn_inst, regUVD_VCPU_NONCACHE_OFFSET0, 0);
+	WREG32_SOC15(VCN, vcn_inst, regUVD_VCPU_NONCACHE_SIZE0,
+		AMDGPU_GPU_PAGE_ALIGN(sizeof(struct amdgpu_vcn5_fw_shared)));
+}
+
+/**
+ * vcn_v5_0_1_mc_resume_dpg_mode - memory controller programming for dpg mode
+ *
+ * @vinst: VCN instance
+ * @indirect: indirectly write sram
+ *
+ * Let the VCN memory controller know it's offsets with dpg mode
+ */
+static void vcn_v5_0_1_mc_resume_dpg_mode(struct amdgpu_vcn_inst *vinst,
+					  bool indirect)
+{
+	struct amdgpu_device *adev = vinst->adev;
+	int inst_idx = vinst->inst;
+	uint32_t offset, size;
+	const struct common_firmware_header *hdr;
+
+	hdr = (const struct common_firmware_header *)adev->vcn.inst[inst_idx].fw->data;
+	size = AMDGPU_GPU_PAGE_ALIGN(le32_to_cpu(hdr->ucode_size_bytes) + 8);
+
+	/* cache window 0: fw */
+	if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) {
+		if (!indirect) {
+			WREG32_SOC24_DPG_MODE(inst_idx, SOC24_DPG_MODE_OFFSET(
+				VCN, 0, regUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW),
+				(adev->firmware.ucode[AMDGPU_UCODE_ID_VCN +
+				 inst_idx].tmr_mc_addr_lo), 0, indirect);
+			WREG32_SOC24_DPG_MODE(inst_idx, SOC24_DPG_MODE_OFFSET(
+				VCN, 0, regUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH),
+				(adev->firmware.ucode[AMDGPU_UCODE_ID_VCN +
+				 inst_idx].tmr_mc_addr_hi), 0, indirect);
+			WREG32_SOC24_DPG_MODE(inst_idx, SOC24_DPG_MODE_OFFSET(
+				VCN, 0, regUVD_VCPU_CACHE_OFFSET0), 0, 0, indirect);
+		} else {
+			WREG32_SOC24_DPG_MODE(inst_idx, SOC24_DPG_MODE_OFFSET(
+				VCN, 0, regUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW), 0, 0, indirect);
+			WREG32_SOC24_DPG_MODE(inst_idx, SOC24_DPG_MODE_OFFSET(
+				VCN, 0, regUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH), 0, 0, indirect);
+			WREG32_SOC24_DPG_MODE(inst_idx, SOC24_DPG_MODE_OFFSET(
+				VCN, 0, regUVD_VCPU_CACHE_OFFSET0), 0, 0, indirect);
+		}
+		offset = 0;
+	} else {
+		WREG32_SOC24_DPG_MODE(inst_idx, SOC24_DPG_MODE_OFFSET(
+			VCN, 0, regUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW),
+			lower_32_bits(adev->vcn.inst[inst_idx].gpu_addr), 0, indirect);
+		WREG32_SOC24_DPG_MODE(inst_idx, SOC24_DPG_MODE_OFFSET(
+			VCN, 0, regUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH),
+			upper_32_bits(adev->vcn.inst[inst_idx].gpu_addr), 0, indirect);
+		offset = size;
+		WREG32_SOC24_DPG_MODE(inst_idx, SOC24_DPG_MODE_OFFSET(
+			VCN, 0, regUVD_VCPU_CACHE_OFFSET0),
+			AMDGPU_UVD_FIRMWARE_OFFSET >> 3, 0, indirect);
+	}
+
+	if (!indirect)
+		WREG32_SOC24_DPG_MODE(inst_idx, SOC24_DPG_MODE_OFFSET(
+			VCN, 0, regUVD_VCPU_CACHE_SIZE0), size, 0, indirect);
+	else
+		WREG32_SOC24_DPG_MODE(inst_idx, SOC24_DPG_MODE_OFFSET(
+			VCN, 0, regUVD_VCPU_CACHE_SIZE0), 0, 0, indirect);
+
+	/* cache window 1: stack */
+	if (!indirect) {
+		WREG32_SOC24_DPG_MODE(inst_idx, SOC24_DPG_MODE_OFFSET(
+			VCN, 0, regUVD_LMI_VCPU_CACHE1_64BIT_BAR_LOW),
+			lower_32_bits(adev->vcn.inst[inst_idx].gpu_addr + offset), 0, indirect);
+		WREG32_SOC24_DPG_MODE(inst_idx, SOC24_DPG_MODE_OFFSET(
+			VCN, 0, regUVD_LMI_VCPU_CACHE1_64BIT_BAR_HIGH),
+			upper_32_bits(adev->vcn.inst[inst_idx].gpu_addr + offset), 0, indirect);
+		WREG32_SOC24_DPG_MODE(inst_idx, SOC24_DPG_MODE_OFFSET(
+			VCN, 0, regUVD_VCPU_CACHE_OFFSET1), 0, 0, indirect);
+	} else {
+		WREG32_SOC24_DPG_MODE(inst_idx, SOC24_DPG_MODE_OFFSET(
+			VCN, 0, regUVD_LMI_VCPU_CACHE1_64BIT_BAR_LOW), 0, 0, indirect);
+		WREG32_SOC24_DPG_MODE(inst_idx, SOC24_DPG_MODE_OFFSET(
+			VCN, 0, regUVD_LMI_VCPU_CACHE1_64BIT_BAR_HIGH), 0, 0, indirect);
+		WREG32_SOC24_DPG_MODE(inst_idx, SOC24_DPG_MODE_OFFSET(
+			VCN, 0, regUVD_VCPU_CACHE_OFFSET1), 0, 0, indirect);
+	}
+	WREG32_SOC24_DPG_MODE(inst_idx, SOC24_DPG_MODE_OFFSET(
+			VCN, 0, regUVD_VCPU_CACHE_SIZE1), AMDGPU_VCN_STACK_SIZE, 0, indirect);
+
+	/* cache window 2: context */
+	WREG32_SOC24_DPG_MODE(inst_idx, SOC24_DPG_MODE_OFFSET(
+		VCN, 0, regUVD_LMI_VCPU_CACHE2_64BIT_BAR_LOW),
+		lower_32_bits(adev->vcn.inst[inst_idx].gpu_addr + offset +
+			AMDGPU_VCN_STACK_SIZE), 0, indirect);
+	WREG32_SOC24_DPG_MODE(inst_idx, SOC24_DPG_MODE_OFFSET(
+		VCN, 0, regUVD_LMI_VCPU_CACHE2_64BIT_BAR_HIGH),
+		upper_32_bits(adev->vcn.inst[inst_idx].gpu_addr + offset +
+			AMDGPU_VCN_STACK_SIZE), 0, indirect);
+	WREG32_SOC24_DPG_MODE(inst_idx, SOC24_DPG_MODE_OFFSET(
+		VCN, 0, regUVD_VCPU_CACHE_OFFSET2), 0, 0, indirect);
+	WREG32_SOC24_DPG_MODE(inst_idx, SOC24_DPG_MODE_OFFSET(
+		VCN, 0, regUVD_VCPU_CACHE_SIZE2), AMDGPU_VCN_CONTEXT_SIZE, 0, indirect);
+
+	/* non-cache window */
+	WREG32_SOC24_DPG_MODE(inst_idx, SOC24_DPG_MODE_OFFSET(
+		VCN, 0, regUVD_LMI_VCPU_NC0_64BIT_BAR_LOW),
+		lower_32_bits(adev->vcn.inst[inst_idx].fw_shared.gpu_addr), 0, indirect);
+	WREG32_SOC24_DPG_MODE(inst_idx, SOC24_DPG_MODE_OFFSET(
+		VCN, 0, regUVD_LMI_VCPU_NC0_64BIT_BAR_HIGH),
+		upper_32_bits(adev->vcn.inst[inst_idx].fw_shared.gpu_addr), 0, indirect);
+	WREG32_SOC24_DPG_MODE(inst_idx, SOC24_DPG_MODE_OFFSET(
+		VCN, 0, regUVD_VCPU_NONCACHE_OFFSET0), 0, 0, indirect);
+	WREG32_SOC24_DPG_MODE(inst_idx, SOC24_DPG_MODE_OFFSET(
+		VCN, 0, regUVD_VCPU_NONCACHE_SIZE0),
+		AMDGPU_GPU_PAGE_ALIGN(sizeof(struct amdgpu_vcn5_fw_shared)), 0, indirect);
+
+	/* VCN global tiling registers */
+	WREG32_SOC24_DPG_MODE(inst_idx, SOC24_DPG_MODE_OFFSET(
+		VCN, 0, regUVD_GFX10_ADDR_CONFIG), adev->gfx.config.gb_addr_config, 0, indirect);
+}
+
+/**
+ * vcn_v5_0_1_disable_clock_gating - disable VCN clock gating
+ *
+ * @vinst: VCN instance
+ *
+ * Disable clock gating for VCN block
+ */
+static void vcn_v5_0_1_disable_clock_gating(struct amdgpu_vcn_inst *vinst)
+{
+}
+
+/**
+ * vcn_v5_0_1_enable_clock_gating - enable VCN clock gating
+ *
+ * @vinst: VCN instance
+ *
+ * Enable clock gating for VCN block
+ */
+static void vcn_v5_0_1_enable_clock_gating(struct amdgpu_vcn_inst *vinst)
+{
+}
+
+/**
+ * vcn_v5_0_1_pause_dpg_mode - VCN pause with dpg mode
+ *
+ * @vinst: VCN instance
+ * @new_state: pause state
+ *
+ * Pause dpg mode for VCN block
+ */
+static int vcn_v5_0_1_pause_dpg_mode(struct amdgpu_vcn_inst *vinst,
+				     struct dpg_pause_state *new_state)
+{
+	struct amdgpu_device *adev = vinst->adev;
+	uint32_t reg_data = 0;
+	int vcn_inst;
+
+	vcn_inst = GET_INST(VCN, vinst->inst);
+
+	/* pause/unpause if state is changed */
+	if (vinst->pause_state.fw_based != new_state->fw_based) {
+		DRM_DEV_DEBUG(adev->dev, "dpg pause state changed %d -> %d %s\n",
+			vinst->pause_state.fw_based, new_state->fw_based,
+			new_state->fw_based ? "VCN_DPG_STATE__PAUSE" : "VCN_DPG_STATE__UNPAUSE");
+		reg_data = RREG32_SOC15(VCN, vcn_inst, regUVD_DPG_PAUSE) &
+			(~UVD_DPG_PAUSE__NJ_PAUSE_DPG_ACK_MASK);
+
+		if (new_state->fw_based == VCN_DPG_STATE__PAUSE) {
+			/* pause DPG */
+			reg_data |= UVD_DPG_PAUSE__NJ_PAUSE_DPG_REQ_MASK;
+			WREG32_SOC15(VCN, vcn_inst, regUVD_DPG_PAUSE, reg_data);
+
+			/* wait for ACK */
+			SOC15_WAIT_ON_RREG(VCN, vcn_inst, regUVD_DPG_PAUSE,
+					UVD_DPG_PAUSE__NJ_PAUSE_DPG_ACK_MASK,
+					UVD_DPG_PAUSE__NJ_PAUSE_DPG_ACK_MASK);
+		} else {
+			/* unpause DPG, no need to wait */
+			reg_data &= ~UVD_DPG_PAUSE__NJ_PAUSE_DPG_REQ_MASK;
+			WREG32_SOC15(VCN, vcn_inst, regUVD_DPG_PAUSE, reg_data);
+		}
+		vinst->pause_state.fw_based = new_state->fw_based;
+	}
+
+	return 0;
+}
+
+
+/**
+ * vcn_v5_0_1_start_dpg_mode - VCN start with dpg mode
+ *
+ * @vinst: VCN instance
+ * @indirect: indirectly write sram
+ *
+ * Start VCN block with dpg mode
+ */
+static int vcn_v5_0_1_start_dpg_mode(struct amdgpu_vcn_inst *vinst,
+				     bool indirect)
+{
+	struct amdgpu_device *adev = vinst->adev;
+	int inst_idx = vinst->inst;
+	volatile struct amdgpu_vcn5_fw_shared *fw_shared =
+		adev->vcn.inst[inst_idx].fw_shared.cpu_addr;
+	struct amdgpu_ring *ring;
+	struct dpg_pause_state state = {.fw_based = VCN_DPG_STATE__PAUSE};
+	int vcn_inst;
+	uint32_t tmp;
+
+	vcn_inst = GET_INST(VCN, inst_idx);
+
+	/* disable register anti-hang mechanism */
+	WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_POWER_STATUS), 1,
+		~UVD_POWER_STATUS__UVD_POWER_STATUS_MASK);
+
+	/* enable dynamic power gating mode */
+	tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_POWER_STATUS);
+	tmp |= UVD_POWER_STATUS__UVD_PG_MODE_MASK;
+	WREG32_SOC15(VCN, vcn_inst, regUVD_POWER_STATUS, tmp);
+
+	if (indirect) {
+		adev->vcn.inst[inst_idx].dpg_sram_curr_addr =
+			(uint32_t *)adev->vcn.inst[inst_idx].dpg_sram_cpu_addr;
+		/* Use dummy register 0xDEADBEEF passing AID selection to PSP FW */
+		WREG32_SOC24_DPG_MODE(inst_idx, 0xDEADBEEF,
+				adev->vcn.inst[inst_idx].aid_id, 0, true);
+	}
+
+	/* enable VCPU clock */
+	tmp = (0xFF << UVD_VCPU_CNTL__PRB_TIMEOUT_VAL__SHIFT);
+	tmp |= UVD_VCPU_CNTL__CLK_EN_MASK | UVD_VCPU_CNTL__BLK_RST_MASK;
+	WREG32_SOC24_DPG_MODE(inst_idx, SOC24_DPG_MODE_OFFSET(
+		VCN, 0, regUVD_VCPU_CNTL), tmp, 0, indirect);
+
+	/* disable master interrupt */
+	WREG32_SOC24_DPG_MODE(inst_idx, SOC24_DPG_MODE_OFFSET(
+		VCN, 0, regUVD_MASTINT_EN), 0, 0, indirect);
+
+	/* setup regUVD_LMI_CTRL */
+	tmp = (UVD_LMI_CTRL__WRITE_CLEAN_TIMER_EN_MASK |
+		UVD_LMI_CTRL__REQ_MODE_MASK |
+		UVD_LMI_CTRL__CRC_RESET_MASK |
+		UVD_LMI_CTRL__MASK_MC_URGENT_MASK |
+		UVD_LMI_CTRL__DATA_COHERENCY_EN_MASK |
+		UVD_LMI_CTRL__VCPU_DATA_COHERENCY_EN_MASK |
+		(8 << UVD_LMI_CTRL__WRITE_CLEAN_TIMER__SHIFT) |
+		0x00100000L);
+	WREG32_SOC24_DPG_MODE(inst_idx, SOC24_DPG_MODE_OFFSET(
+		VCN, 0, regUVD_LMI_CTRL), tmp, 0, indirect);
+
+	vcn_v5_0_1_mc_resume_dpg_mode(vinst, indirect);
+
+	tmp = (0xFF << UVD_VCPU_CNTL__PRB_TIMEOUT_VAL__SHIFT);
+	tmp |= UVD_VCPU_CNTL__CLK_EN_MASK;
+	WREG32_SOC24_DPG_MODE(inst_idx, SOC24_DPG_MODE_OFFSET(
+		VCN, 0, regUVD_VCPU_CNTL), tmp, 0, indirect);
+
+	/* enable LMI MC and UMC channels */
+	tmp = 0x1f << UVD_LMI_CTRL2__RE_OFLD_MIF_WR_REQ_NUM__SHIFT;
+	WREG32_SOC24_DPG_MODE(inst_idx, SOC24_DPG_MODE_OFFSET(
+		VCN, 0, regUVD_LMI_CTRL2), tmp, 0, indirect);
+
+	/* enable master interrupt */
+	WREG32_SOC24_DPG_MODE(inst_idx, SOC24_DPG_MODE_OFFSET(
+		VCN, 0, regUVD_MASTINT_EN),
+		UVD_MASTINT_EN__VCPU_EN_MASK, 0, indirect);
+
+	if (indirect)
+		amdgpu_vcn_psp_update_sram(adev, inst_idx, AMDGPU_UCODE_ID_VCN0_RAM);
+
+	/* resetting ring, fw should not check RB ring */
+	fw_shared->sq.queue_mode |= FW_QUEUE_RING_RESET;
+
+	/* Pause dpg */
+	vcn_v5_0_1_pause_dpg_mode(vinst, &state);
+
+	ring = &adev->vcn.inst[inst_idx].ring_enc[0];
+
+	WREG32_SOC15(VCN, vcn_inst, regUVD_RB_BASE_LO, lower_32_bits(ring->gpu_addr));
+	WREG32_SOC15(VCN, vcn_inst, regUVD_RB_BASE_HI, upper_32_bits(ring->gpu_addr));
+	WREG32_SOC15(VCN, vcn_inst, regUVD_RB_SIZE, ring->ring_size / sizeof(uint32_t));
+
+	tmp = RREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE);
+	tmp &= ~(VCN_RB_ENABLE__RB1_EN_MASK);
+	WREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE, tmp);
+
+	WREG32_SOC15(VCN, vcn_inst, regUVD_RB_RPTR, 0);
+	WREG32_SOC15(VCN, vcn_inst, regUVD_RB_WPTR, 0);
+
+	tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_RB_RPTR);
+	WREG32_SOC15(VCN, vcn_inst, regUVD_RB_WPTR, tmp);
+	ring->wptr = RREG32_SOC15(VCN, vcn_inst, regUVD_RB_WPTR);
+
+	tmp = RREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE);
+	tmp |= VCN_RB_ENABLE__RB1_EN_MASK;
+	WREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE, tmp);
+	/* resetting done, fw can check RB ring */
+	fw_shared->sq.queue_mode &= ~(FW_QUEUE_RING_RESET | FW_QUEUE_DPG_HOLD_OFF);
+
+	WREG32_SOC15(VCN, vcn_inst, regVCN_RB1_DB_CTRL,
+		ring->doorbell_index << VCN_RB1_DB_CTRL__OFFSET__SHIFT |
+		VCN_RB1_DB_CTRL__EN_MASK);
+	/* Read DB_CTRL to flush the write DB_CTRL command. */
+	RREG32_SOC15(VCN, vcn_inst, regVCN_RB1_DB_CTRL);
+
+	return 0;
+}
+
+static int vcn_v5_0_1_start_sriov(struct amdgpu_device *adev)
+{
+	int i, vcn_inst;
+	struct amdgpu_ring *ring_enc;
+	uint64_t cache_addr;
+	uint64_t rb_enc_addr;
+	uint64_t ctx_addr;
+	uint32_t param, resp, expected;
+	uint32_t offset, cache_size;
+	uint32_t tmp, timeout;
+
+	struct amdgpu_mm_table *table = &adev->virt.mm_table;
+	uint32_t *table_loc;
+	uint32_t table_size;
+	uint32_t size, size_dw;
+	uint32_t init_status;
+	uint32_t enabled_vcn;
+
+	struct mmsch_v5_0_cmd_direct_write
+		direct_wt = { {0} };
+	struct mmsch_v5_0_cmd_direct_read_modify_write
+		direct_rd_mod_wt = { {0} };
+	struct mmsch_v5_0_cmd_end end = { {0} };
+	struct mmsch_v5_0_init_header header;
+
+	volatile struct amdgpu_vcn5_fw_shared *fw_shared;
+	volatile struct amdgpu_fw_shared_rb_setup *rb_setup;
+
+	direct_wt.cmd_header.command_type =
+		MMSCH_COMMAND__DIRECT_REG_WRITE;
+	direct_rd_mod_wt.cmd_header.command_type =
+		MMSCH_COMMAND__DIRECT_REG_READ_MODIFY_WRITE;
+	end.cmd_header.command_type = MMSCH_COMMAND__END;
+
+	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
+		vcn_inst = GET_INST(VCN, i);
+
+		vcn_v5_0_1_fw_shared_init(adev, vcn_inst);
+
+		memset(&header, 0, sizeof(struct mmsch_v5_0_init_header));
+		header.version = MMSCH_VERSION;
+		header.total_size = sizeof(struct mmsch_v5_0_init_header) >> 2;
+
+		table_loc = (uint32_t *)table->cpu_addr;
+		table_loc += header.total_size;
+
+		table_size = 0;
+
+		MMSCH_V5_0_INSERT_DIRECT_RD_MOD_WT(SOC15_REG_OFFSET(VCN, 0, regUVD_STATUS),
+			~UVD_STATUS__UVD_BUSY, UVD_STATUS__UVD_BUSY);
+
+		cache_size = AMDGPU_GPU_PAGE_ALIGN(adev->vcn.inst[i].fw->size + 4);
+
+		if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) {
+			MMSCH_V5_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCN, 0,
+				regUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW),
+				adev->firmware.ucode[AMDGPU_UCODE_ID_VCN + i].tmr_mc_addr_lo);
+
+			MMSCH_V5_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCN, 0,
+				regUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH),
+				adev->firmware.ucode[AMDGPU_UCODE_ID_VCN + i].tmr_mc_addr_hi);
+
+			offset = 0;
+			MMSCH_V5_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCN, 0,
+				regUVD_VCPU_CACHE_OFFSET0), 0);
+		} else {
+			MMSCH_V5_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCN, 0,
+				regUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW),
+				lower_32_bits(adev->vcn.inst[i].gpu_addr));
+			MMSCH_V5_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCN, 0,
+				regUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH),
+				upper_32_bits(adev->vcn.inst[i].gpu_addr));
+			offset = cache_size;
+			MMSCH_V5_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCN, 0,
+				regUVD_VCPU_CACHE_OFFSET0),
+				AMDGPU_UVD_FIRMWARE_OFFSET >> 3);
+		}
+
+		MMSCH_V5_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCN, 0,
+			regUVD_VCPU_CACHE_SIZE0),
+			cache_size);
+
+		cache_addr = adev->vcn.inst[vcn_inst].gpu_addr + offset;
+		MMSCH_V5_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCN, 0,
+			regUVD_LMI_VCPU_CACHE1_64BIT_BAR_LOW), lower_32_bits(cache_addr));
+		MMSCH_V5_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCN, 0,
+			regUVD_LMI_VCPU_CACHE1_64BIT_BAR_HIGH), upper_32_bits(cache_addr));
+		MMSCH_V5_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCN, 0,
+			regUVD_VCPU_CACHE_OFFSET1), 0);
+		MMSCH_V5_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCN, 0,
+			regUVD_VCPU_CACHE_SIZE1), AMDGPU_VCN_STACK_SIZE);
+
+		cache_addr = adev->vcn.inst[vcn_inst].gpu_addr + offset +
+			AMDGPU_VCN_STACK_SIZE;
+
+		MMSCH_V5_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCN, 0,
+			regUVD_LMI_VCPU_CACHE2_64BIT_BAR_LOW), lower_32_bits(cache_addr));
+
+		MMSCH_V5_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCN, 0,
+			regUVD_LMI_VCPU_CACHE2_64BIT_BAR_HIGH), upper_32_bits(cache_addr));
+
+		MMSCH_V5_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCN, 0,
+			regUVD_VCPU_CACHE_OFFSET2), 0);
+
+		MMSCH_V5_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCN, 0,
+			regUVD_VCPU_CACHE_SIZE2), AMDGPU_VCN_CONTEXT_SIZE);
+
+		fw_shared = adev->vcn.inst[vcn_inst].fw_shared.cpu_addr;
+		rb_setup = &fw_shared->rb_setup;
+
+		ring_enc = &adev->vcn.inst[vcn_inst].ring_enc[0];
+		ring_enc->wptr = 0;
+		rb_enc_addr = ring_enc->gpu_addr;
+
+		rb_setup->is_rb_enabled_flags |= RB_ENABLED;
+		rb_setup->rb_addr_lo = lower_32_bits(rb_enc_addr);
+		rb_setup->rb_addr_hi = upper_32_bits(rb_enc_addr);
+		rb_setup->rb_size = ring_enc->ring_size / 4;
+		fw_shared->present_flag_0 |= cpu_to_le32(AMDGPU_VCN_VF_RB_SETUP_FLAG);
+
+		MMSCH_V5_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCN, 0,
+			regUVD_LMI_VCPU_NC0_64BIT_BAR_LOW),
+			lower_32_bits(adev->vcn.inst[vcn_inst].fw_shared.gpu_addr));
+		MMSCH_V5_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCN, 0,
+			regUVD_LMI_VCPU_NC0_64BIT_BAR_HIGH),
+			upper_32_bits(adev->vcn.inst[vcn_inst].fw_shared.gpu_addr));
+		MMSCH_V5_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCN, 0,
+			regUVD_VCPU_NONCACHE_SIZE0),
+			AMDGPU_GPU_PAGE_ALIGN(sizeof(struct amdgpu_vcn4_fw_shared)));
+		MMSCH_V5_0_INSERT_END();
+
+		header.vcn0.init_status = 0;
+		header.vcn0.table_offset = header.total_size;
+		header.vcn0.table_size = table_size;
+		header.total_size += table_size;
+
+		/* Send init table to mmsch */
+		size = sizeof(struct mmsch_v5_0_init_header);
+		table_loc = (uint32_t *)table->cpu_addr;
+		memcpy((void *)table_loc, &header, size);
+
+		ctx_addr = table->gpu_addr;
+		WREG32_SOC15(VCN, vcn_inst, regMMSCH_VF_CTX_ADDR_LO, lower_32_bits(ctx_addr));
+		WREG32_SOC15(VCN, vcn_inst, regMMSCH_VF_CTX_ADDR_HI, upper_32_bits(ctx_addr));
+
+		tmp = RREG32_SOC15(VCN, vcn_inst, regMMSCH_VF_VMID);
+		tmp &= ~MMSCH_VF_VMID__VF_CTX_VMID_MASK;
+		tmp |= (0 << MMSCH_VF_VMID__VF_CTX_VMID__SHIFT);
+		WREG32_SOC15(VCN, vcn_inst, regMMSCH_VF_VMID, tmp);
+
+		size = header.total_size;
+		WREG32_SOC15(VCN, vcn_inst, regMMSCH_VF_CTX_SIZE, size);
+
+		WREG32_SOC15(VCN, vcn_inst, regMMSCH_VF_MAILBOX_RESP, 0);
+
+		param = 0x00000001;
+		WREG32_SOC15(VCN, vcn_inst, regMMSCH_VF_MAILBOX_HOST, param);
+		tmp = 0;
+		timeout = 1000;
+		resp = 0;
+		expected = MMSCH_VF_MAILBOX_RESP__OK;
+		while (resp != expected) {
+			resp = RREG32_SOC15(VCN, vcn_inst, regMMSCH_VF_MAILBOX_RESP);
+			if (resp != 0)
+				break;
+
+			udelay(10);
+			tmp = tmp + 10;
+			if (tmp >= timeout) {
+				DRM_ERROR("failed to init MMSCH. TIME-OUT after %d usec"\
+					" waiting for regMMSCH_VF_MAILBOX_RESP "\
+					"(expected=0x%08x, readback=0x%08x)\n",
+					tmp, expected, resp);
+				return -EBUSY;
+			}
+		}
+
+		enabled_vcn = amdgpu_vcn_is_disabled_vcn(adev, VCN_DECODE_RING, 0) ? 1 : 0;
+		init_status = ((struct mmsch_v5_0_init_header *)(table_loc))->vcn0.init_status;
+		if (resp != expected && resp != MMSCH_VF_MAILBOX_RESP__INCOMPLETE
+					&& init_status != MMSCH_VF_ENGINE_STATUS__PASS) {
+			DRM_ERROR("MMSCH init status is incorrect! readback=0x%08x, header init "\
+				"status for VCN%x: 0x%x\n", resp, enabled_vcn, init_status);
+		}
+	}
+
+	return 0;
+}
+
+/**
+ * vcn_v5_0_1_start - VCN start
+ *
+ * @vinst: VCN instance
+ *
+ * Start VCN block
+ */
+static int vcn_v5_0_1_start(struct amdgpu_vcn_inst *vinst)
+{
+	struct amdgpu_device *adev = vinst->adev;
+	int i = vinst->inst;
+	volatile struct amdgpu_vcn5_fw_shared *fw_shared;
+	struct amdgpu_ring *ring;
+	uint32_t tmp;
+	int j, k, r, vcn_inst;
+
+	fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
+
+	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)
+		return vcn_v5_0_1_start_dpg_mode(vinst, adev->vcn.inst[i].indirect_sram);
+
+	vcn_inst = GET_INST(VCN, i);
+
+	/* set VCN status busy */
+	tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_STATUS) | UVD_STATUS__UVD_BUSY;
+	WREG32_SOC15(VCN, vcn_inst, regUVD_STATUS, tmp);
+
+	/* enable VCPU clock */
+	WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_VCPU_CNTL),
+		 UVD_VCPU_CNTL__CLK_EN_MASK, ~UVD_VCPU_CNTL__CLK_EN_MASK);
+
+	/* disable master interrupt */
+	WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_MASTINT_EN), 0,
+		 ~UVD_MASTINT_EN__VCPU_EN_MASK);
+
+	/* enable LMI MC and UMC channels */
+	WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_LMI_CTRL2), 0,
+		 ~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK);
+
+	tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET);
+	tmp &= ~UVD_SOFT_RESET__LMI_SOFT_RESET_MASK;
+	tmp &= ~UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK;
+	WREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET, tmp);
+
+	/* setup regUVD_LMI_CTRL */
+	tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_LMI_CTRL);
+	WREG32_SOC15(VCN, vcn_inst, regUVD_LMI_CTRL, tmp |
+		     UVD_LMI_CTRL__WRITE_CLEAN_TIMER_EN_MASK |
+		     UVD_LMI_CTRL__MASK_MC_URGENT_MASK |
+		     UVD_LMI_CTRL__DATA_COHERENCY_EN_MASK |
+		     UVD_LMI_CTRL__VCPU_DATA_COHERENCY_EN_MASK);
+
+	vcn_v5_0_1_mc_resume(vinst);
+
+	/* VCN global tiling registers */
+	WREG32_SOC15(VCN, vcn_inst, regUVD_GFX10_ADDR_CONFIG,
+		     adev->gfx.config.gb_addr_config);
+
+	/* unblock VCPU register access */
+	WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_RB_ARB_CTRL), 0,
+		 ~UVD_RB_ARB_CTRL__VCPU_DIS_MASK);
+
+	/* release VCPU reset to boot */
+	WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_VCPU_CNTL), 0,
+		 ~UVD_VCPU_CNTL__BLK_RST_MASK);
+
+	for (j = 0; j < 10; ++j) {
+		uint32_t status;
+
+		for (k = 0; k < 100; ++k) {
+			status = RREG32_SOC15(VCN, vcn_inst, regUVD_STATUS);
+			if (status & 2)
+				break;
+			mdelay(100);
+			if (amdgpu_emu_mode == 1)
+				msleep(20);
+		}
+
+		if (amdgpu_emu_mode == 1) {
+			r = -1;
+			if (status & 2) {
+				r = 0;
+				break;
+			}
+		} else {
+			r = 0;
+			if (status & 2)
+				break;
+
+			dev_err(adev->dev,
+				"VCN[%d] is not responding, trying to reset the VCPU!!!\n", i);
+			WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_VCPU_CNTL),
+				 UVD_VCPU_CNTL__BLK_RST_MASK,
+				 ~UVD_VCPU_CNTL__BLK_RST_MASK);
+			mdelay(10);
+			WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_VCPU_CNTL), 0,
+				 ~UVD_VCPU_CNTL__BLK_RST_MASK);
+
+			mdelay(10);
+			r = -1;
+		}
+	}
+
+	if (r) {
+		dev_err(adev->dev, "VCN[%d] is not responding, giving up!!!\n", i);
+		return r;
+	}
+
+	/* enable master interrupt */
+	WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_MASTINT_EN),
+		 UVD_MASTINT_EN__VCPU_EN_MASK,
+		 ~UVD_MASTINT_EN__VCPU_EN_MASK);
+
+	/* clear the busy bit of VCN_STATUS */
+	WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_STATUS), 0,
+		 ~(2 << UVD_STATUS__VCPU_REPORT__SHIFT));
+
+	ring = &adev->vcn.inst[i].ring_enc[0];
+
+	WREG32_SOC15(VCN, vcn_inst, regVCN_RB1_DB_CTRL,
+		     ring->doorbell_index << VCN_RB1_DB_CTRL__OFFSET__SHIFT |
+		     VCN_RB1_DB_CTRL__EN_MASK);
+
+	/* Read DB_CTRL to flush the write DB_CTRL command. */
+	RREG32_SOC15(VCN, vcn_inst, regVCN_RB1_DB_CTRL);
+
+	WREG32_SOC15(VCN, vcn_inst, regUVD_RB_BASE_LO, ring->gpu_addr);
+	WREG32_SOC15(VCN, vcn_inst, regUVD_RB_BASE_HI, upper_32_bits(ring->gpu_addr));
+	WREG32_SOC15(VCN, vcn_inst, regUVD_RB_SIZE, ring->ring_size / 4);
+
+	tmp = RREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE);
+	tmp &= ~(VCN_RB_ENABLE__RB1_EN_MASK);
+	WREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE, tmp);
+	fw_shared->sq.queue_mode |= FW_QUEUE_RING_RESET;
+	WREG32_SOC15(VCN, vcn_inst, regUVD_RB_RPTR, 0);
+	WREG32_SOC15(VCN, vcn_inst, regUVD_RB_WPTR, 0);
+
+	tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_RB_RPTR);
+	WREG32_SOC15(VCN, vcn_inst, regUVD_RB_WPTR, tmp);
+	ring->wptr = RREG32_SOC15(VCN, vcn_inst, regUVD_RB_WPTR);
+
+	tmp = RREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE);
+	tmp |= VCN_RB_ENABLE__RB1_EN_MASK;
+	WREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE, tmp);
+	fw_shared->sq.queue_mode &= ~(FW_QUEUE_RING_RESET | FW_QUEUE_DPG_HOLD_OFF);
+
+	/* Keeping one read-back to ensure all register writes are done,
+	 * otherwise it may introduce race conditions.
+	 */
+	RREG32_SOC15(VCN, vcn_inst, regUVD_STATUS);
+
+	return 0;
+}
+
+/**
+ * vcn_v5_0_1_stop_dpg_mode - VCN stop with dpg mode
+ *
+ * @vinst: VCN instance
+ *
+ * Stop VCN block with dpg mode
+ */
+static void vcn_v5_0_1_stop_dpg_mode(struct amdgpu_vcn_inst *vinst)
+{
+	struct amdgpu_device *adev = vinst->adev;
+	int inst_idx = vinst->inst;
+	uint32_t tmp;
+	int vcn_inst;
+	struct dpg_pause_state state = {.fw_based = VCN_DPG_STATE__UNPAUSE};
+
+	vcn_inst = GET_INST(VCN, inst_idx);
+
+	/* Unpause dpg */
+	vcn_v5_0_1_pause_dpg_mode(vinst, &state);
+
+	/* Wait for power status to be 1 */
+	SOC15_WAIT_ON_RREG(VCN, vcn_inst, regUVD_POWER_STATUS, 1,
+		UVD_POWER_STATUS__UVD_POWER_STATUS_MASK);
+
+	/* wait for read ptr to be equal to write ptr */
+	tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_RB_WPTR);
+	SOC15_WAIT_ON_RREG(VCN, vcn_inst, regUVD_RB_RPTR, tmp, 0xFFFFFFFF);
+
+	/* disable dynamic power gating mode */
+	WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_POWER_STATUS), 0,
+		~UVD_POWER_STATUS__UVD_PG_MODE_MASK);
+
+	/* Keeping one read-back to ensure all register writes are done,
+	 * otherwise it may introduce race conditions.
+	 */
+	RREG32_SOC15(VCN, vcn_inst, regUVD_STATUS);
+}
+
+/**
+ * vcn_v5_0_1_stop - VCN stop
+ *
+ * @vinst: VCN instance
+ *
+ * Stop VCN block
+ */
+static int vcn_v5_0_1_stop(struct amdgpu_vcn_inst *vinst)
+{
+	struct amdgpu_device *adev = vinst->adev;
+	int i = vinst->inst;
+	volatile struct amdgpu_vcn5_fw_shared *fw_shared;
+	uint32_t tmp;
+	int r = 0, vcn_inst;
+
+	vcn_inst = GET_INST(VCN, i);
+
+	fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
+	fw_shared->sq.queue_mode |= FW_QUEUE_DPG_HOLD_OFF;
+
+	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
+		vcn_v5_0_1_stop_dpg_mode(vinst);
+		return 0;
+	}
+
+	/* wait for vcn idle */
+	r = SOC15_WAIT_ON_RREG(VCN, vcn_inst, regUVD_STATUS, UVD_STATUS__IDLE, 0x7);
+	if (r)
+		return r;
+
+	tmp = UVD_LMI_STATUS__VCPU_LMI_WRITE_CLEAN_MASK |
+		UVD_LMI_STATUS__READ_CLEAN_MASK |
+		UVD_LMI_STATUS__WRITE_CLEAN_MASK |
+		UVD_LMI_STATUS__WRITE_CLEAN_RAW_MASK;
+	r = SOC15_WAIT_ON_RREG(VCN, vcn_inst, regUVD_LMI_STATUS, tmp, tmp);
+	if (r)
+		return r;
+
+	/* disable LMI UMC channel */
+	tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_LMI_CTRL2);
+	tmp |= UVD_LMI_CTRL2__STALL_ARB_UMC_MASK;
+	WREG32_SOC15(VCN, vcn_inst, regUVD_LMI_CTRL2, tmp);
+	tmp = UVD_LMI_STATUS__UMC_READ_CLEAN_RAW_MASK |
+		UVD_LMI_STATUS__UMC_WRITE_CLEAN_RAW_MASK;
+	r = SOC15_WAIT_ON_RREG(VCN, vcn_inst, regUVD_LMI_STATUS, tmp, tmp);
+	if (r)
+		return r;
+
+	/* block VCPU register access */
+	WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_RB_ARB_CTRL),
+		 UVD_RB_ARB_CTRL__VCPU_DIS_MASK,
+		 ~UVD_RB_ARB_CTRL__VCPU_DIS_MASK);
+
+	/* reset VCPU */
+	WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_VCPU_CNTL),
+		 UVD_VCPU_CNTL__BLK_RST_MASK,
+		 ~UVD_VCPU_CNTL__BLK_RST_MASK);
+
+	/* disable VCPU clock */
+	WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_VCPU_CNTL), 0,
+		 ~(UVD_VCPU_CNTL__CLK_EN_MASK));
+
+	/* apply soft reset */
+	tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET);
+	tmp |= UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK;
+	WREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET, tmp);
+	tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET);
+	tmp |= UVD_SOFT_RESET__LMI_SOFT_RESET_MASK;
+	WREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET, tmp);
+
+	/* clear status */
+	WREG32_SOC15(VCN, vcn_inst, regUVD_STATUS, 0);
+
+	/* Keeping one read-back to ensure all register writes are done,
+	 * otherwise it may introduce race conditions.
+	 */
+	RREG32_SOC15(VCN, vcn_inst, regUVD_STATUS);
+
+	return 0;
+}
+
+/**
+ * vcn_v5_0_1_unified_ring_get_rptr - get unified read pointer
+ *
+ * @ring: amdgpu_ring pointer
+ *
+ * Returns the current hardware unified read pointer
+ */
+static uint64_t vcn_v5_0_1_unified_ring_get_rptr(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+
+	if (ring != &adev->vcn.inst[ring->me].ring_enc[0])
+		DRM_ERROR("wrong ring id is identified in %s", __func__);
+
+	return RREG32_SOC15(VCN, GET_INST(VCN, ring->me), regUVD_RB_RPTR);
+}
+
+/**
+ * vcn_v5_0_1_unified_ring_get_wptr - get unified write pointer
+ *
+ * @ring: amdgpu_ring pointer
+ *
+ * Returns the current hardware unified write pointer
+ */
+static uint64_t vcn_v5_0_1_unified_ring_get_wptr(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+
+	if (ring != &adev->vcn.inst[ring->me].ring_enc[0])
+		DRM_ERROR("wrong ring id is identified in %s", __func__);
+
+	if (ring->use_doorbell)
+		return *ring->wptr_cpu_addr;
+	else
+		return RREG32_SOC15(VCN, GET_INST(VCN, ring->me), regUVD_RB_WPTR);
+}
+
+/**
+ * vcn_v5_0_1_unified_ring_set_wptr - set enc write pointer
+ *
+ * @ring: amdgpu_ring pointer
+ *
+ * Commits the enc write pointer to the hardware
+ */
+static void vcn_v5_0_1_unified_ring_set_wptr(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+
+	if (ring != &adev->vcn.inst[ring->me].ring_enc[0])
+		DRM_ERROR("wrong ring id is identified in %s", __func__);
+
+	if (ring->use_doorbell) {
+		*ring->wptr_cpu_addr = lower_32_bits(ring->wptr);
+		WDOORBELL32(ring->doorbell_index, lower_32_bits(ring->wptr));
+	} else {
+		WREG32_SOC15(VCN, GET_INST(VCN, ring->me), regUVD_RB_WPTR,
+				lower_32_bits(ring->wptr));
+	}
+}
+
+static const struct amdgpu_ring_funcs vcn_v5_0_1_unified_ring_vm_funcs = {
+	.type = AMDGPU_RING_TYPE_VCN_ENC,
+	.align_mask = 0x3f,
+	.nop = VCN_ENC_CMD_NO_OP,
+	.get_rptr = vcn_v5_0_1_unified_ring_get_rptr,
+	.get_wptr = vcn_v5_0_1_unified_ring_get_wptr,
+	.set_wptr = vcn_v5_0_1_unified_ring_set_wptr,
+	.emit_frame_size = SOC15_FLUSH_GPU_TLB_NUM_WREG * 3 +
+			   SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 4 +
+			   4 + /* vcn_v2_0_enc_ring_emit_vm_flush */
+			   5 +
+			   5 + /* vcn_v2_0_enc_ring_emit_fence x2 vm fence */
+			   1, /* vcn_v2_0_enc_ring_insert_end */
+	.emit_ib_size = 5, /* vcn_v2_0_enc_ring_emit_ib */
+	.emit_ib = vcn_v2_0_enc_ring_emit_ib,
+	.emit_fence = vcn_v2_0_enc_ring_emit_fence,
+	.emit_vm_flush = vcn_v4_0_3_enc_ring_emit_vm_flush,
+	.emit_hdp_flush = vcn_v4_0_3_ring_emit_hdp_flush,
+	.test_ring = amdgpu_vcn_enc_ring_test_ring,
+	.test_ib = amdgpu_vcn_unified_ring_test_ib,
+	.insert_nop = amdgpu_ring_insert_nop,
+	.insert_end = vcn_v2_0_enc_ring_insert_end,
+	.pad_ib = amdgpu_ring_generic_pad_ib,
+	.begin_use = amdgpu_vcn_ring_begin_use,
+	.end_use = amdgpu_vcn_ring_end_use,
+	.emit_wreg = vcn_v4_0_3_enc_ring_emit_wreg,
+	.emit_reg_wait = vcn_v4_0_3_enc_ring_emit_reg_wait,
+	.emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper,
+};
+
+/**
+ * vcn_v5_0_1_set_unified_ring_funcs - set unified ring functions
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * Set unified ring functions
+ */
+static void vcn_v5_0_1_set_unified_ring_funcs(struct amdgpu_device *adev)
+{
+	int i, vcn_inst;
+
+	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
+		adev->vcn.inst[i].ring_enc[0].funcs = &vcn_v5_0_1_unified_ring_vm_funcs;
+		adev->vcn.inst[i].ring_enc[0].me = i;
+		vcn_inst = GET_INST(VCN, i);
+		adev->vcn.inst[i].aid_id = vcn_inst / adev->vcn.num_inst_per_aid;
+	}
+}
+
+/**
+ * vcn_v5_0_1_is_idle - check VCN block is idle
+ *
+ * @ip_block: Pointer to the amdgpu_ip_block structure
+ *
+ * Check whether VCN block is idle
+ */
+static bool vcn_v5_0_1_is_idle(struct amdgpu_ip_block *ip_block)
+{
+	struct amdgpu_device *adev = ip_block->adev;
+	int i, ret = 1;
+
+	for (i = 0; i < adev->vcn.num_vcn_inst; ++i)
+		ret &= (RREG32_SOC15(VCN, GET_INST(VCN, i), regUVD_STATUS) == UVD_STATUS__IDLE);
+
+	return ret;
+}
+
+/**
+ * vcn_v5_0_1_wait_for_idle - wait for VCN block idle
+ *
+ * @ip_block: Pointer to the amdgpu_ip_block for this hw instance.
+ *
+ * Wait for VCN block idle
+ */
+static int vcn_v5_0_1_wait_for_idle(struct amdgpu_ip_block *ip_block)
+{
+	struct amdgpu_device *adev = ip_block->adev;
+	int i, ret = 0;
+
+	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
+		ret = SOC15_WAIT_ON_RREG(VCN, GET_INST(VCN, i), regUVD_STATUS, UVD_STATUS__IDLE,
+			UVD_STATUS__IDLE);
+		if (ret)
+			return ret;
+	}
+
+	return ret;
+}
+
+/**
+ * vcn_v5_0_1_set_clockgating_state - set VCN block clockgating state
+ *
+ * @ip_block: Pointer to the amdgpu_ip_block for this hw instance.
+ * @state: clock gating state
+ *
+ * Set VCN block clockgating state
+ */
+static int vcn_v5_0_1_set_clockgating_state(struct amdgpu_ip_block *ip_block,
+					    enum amd_clockgating_state state)
+{
+	struct amdgpu_device *adev = ip_block->adev;
+	bool enable = state == AMD_CG_STATE_GATE;
+	int i;
+
+	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
+		struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[i];
+
+		if (enable) {
+			if (RREG32_SOC15(VCN, GET_INST(VCN, i), regUVD_STATUS) != UVD_STATUS__IDLE)
+				return -EBUSY;
+			vcn_v5_0_1_enable_clock_gating(vinst);
+		} else {
+			vcn_v5_0_1_disable_clock_gating(vinst);
+		}
+	}
+
+	return 0;
+}
+
+static int vcn_v5_0_1_set_pg_state(struct amdgpu_vcn_inst *vinst,
+				   enum amd_powergating_state state)
+{
+	struct amdgpu_device *adev = vinst->adev;
+	int ret = 0;
+
+	/* for SRIOV, guest should not control VCN Power-gating
+	 * MMSCH FW should control Power-gating and clock-gating
+	 * guest should avoid touching CGC and PG
+	 */
+	if (amdgpu_sriov_vf(adev)) {
+		vinst->cur_state = AMD_PG_STATE_UNGATE;
+		return 0;
+	}
+
+	if (state == vinst->cur_state)
+		return 0;
+
+	if (state == AMD_PG_STATE_GATE)
+		ret = vcn_v5_0_1_stop(vinst);
+	else
+		ret = vcn_v5_0_1_start(vinst);
+
+	if (!ret)
+		vinst->cur_state = state;
+
+	return ret;
+}
+
+/**
+ * vcn_v5_0_1_process_interrupt - process VCN block interrupt
+ *
+ * @adev: amdgpu_device pointer
+ * @source: interrupt sources
+ * @entry: interrupt entry from clients and sources
+ *
+ * Process VCN block interrupt
+ */
+static int vcn_v5_0_1_process_interrupt(struct amdgpu_device *adev, struct amdgpu_irq_src *source,
+	struct amdgpu_iv_entry *entry)
+{
+	uint32_t i, inst;
+
+	i = node_id_to_phys_map[entry->node_id];
+
+	DRM_DEV_DEBUG(adev->dev, "IH: VCN TRAP\n");
+
+	for (inst = 0; inst < adev->vcn.num_vcn_inst; ++inst)
+		if (adev->vcn.inst[inst].aid_id == i)
+			break;
+	if (inst >= adev->vcn.num_vcn_inst) {
+		dev_WARN_ONCE(adev->dev, 1,
+				"Interrupt received for unknown VCN instance %d",
+				entry->node_id);
+		return 0;
+	}
+
+	switch (entry->src_id) {
+	case VCN_5_0__SRCID__UVD_ENC_GENERAL_PURPOSE:
+		amdgpu_fence_process(&adev->vcn.inst[inst].ring_enc[0]);
+		break;
+	default:
+		DRM_DEV_ERROR(adev->dev, "Unhandled interrupt: %d %d\n",
+			  entry->src_id, entry->src_data[0]);
+		break;
+	}
+
+	return 0;
+}
+
+static int vcn_v5_0_1_set_ras_interrupt_state(struct amdgpu_device *adev,
+					struct amdgpu_irq_src *source,
+					unsigned int type,
+					enum amdgpu_interrupt_state state)
+{
+	return 0;
+}
+
+static const struct amdgpu_irq_src_funcs vcn_v5_0_1_irq_funcs = {
+	.process = vcn_v5_0_1_process_interrupt,
+};
+
+static const struct amdgpu_irq_src_funcs vcn_v5_0_1_ras_irq_funcs = {
+	.set = vcn_v5_0_1_set_ras_interrupt_state,
+	.process = amdgpu_vcn_process_poison_irq,
+};
+
+
+/**
+ * vcn_v5_0_1_set_irq_funcs - set VCN block interrupt irq functions
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * Set VCN block interrupt irq functions
+ */
+static void vcn_v5_0_1_set_irq_funcs(struct amdgpu_device *adev)
+{
+	int i;
+
+	for (i = 0; i < adev->vcn.num_vcn_inst; ++i)
+		adev->vcn.inst->irq.num_types++;
+
+	adev->vcn.inst->irq.funcs = &vcn_v5_0_1_irq_funcs;
+
+	adev->vcn.inst->ras_poison_irq.num_types = 1;
+	adev->vcn.inst->ras_poison_irq.funcs = &vcn_v5_0_1_ras_irq_funcs;
+
+}
+
+static const struct amd_ip_funcs vcn_v5_0_1_ip_funcs = {
+	.name = "vcn_v5_0_1",
+	.early_init = vcn_v5_0_1_early_init,
+	.late_init = NULL,
+	.sw_init = vcn_v5_0_1_sw_init,
+	.sw_fini = vcn_v5_0_1_sw_fini,
+	.hw_init = vcn_v5_0_1_hw_init,
+	.hw_fini = vcn_v5_0_1_hw_fini,
+	.suspend = vcn_v5_0_1_suspend,
+	.resume = vcn_v5_0_1_resume,
+	.is_idle = vcn_v5_0_1_is_idle,
+	.wait_for_idle = vcn_v5_0_1_wait_for_idle,
+	.check_soft_reset = NULL,
+	.pre_soft_reset = NULL,
+	.soft_reset = NULL,
+	.post_soft_reset = NULL,
+	.set_clockgating_state = vcn_v5_0_1_set_clockgating_state,
+	.set_powergating_state = vcn_set_powergating_state,
+	.dump_ip_state = vcn_v5_0_0_dump_ip_state,
+	.print_ip_state = vcn_v5_0_0_print_ip_state,
+};
+
+const struct amdgpu_ip_block_version vcn_v5_0_1_ip_block = {
+	.type = AMD_IP_BLOCK_TYPE_VCN,
+	.major = 5,
+	.minor = 0,
+	.rev = 1,
+	.funcs = &vcn_v5_0_1_ip_funcs,
+};
+
+static uint32_t vcn_v5_0_1_query_poison_by_instance(struct amdgpu_device *adev,
+			uint32_t instance, uint32_t sub_block)
+{
+	uint32_t poison_stat = 0, reg_value = 0;
+
+	switch (sub_block) {
+	case AMDGPU_VCN_V5_0_1_VCPU_VCODEC:
+		reg_value = RREG32_SOC15(VCN, instance, regUVD_RAS_VCPU_VCODEC_STATUS);
+		poison_stat = REG_GET_FIELD(reg_value, UVD_RAS_VCPU_VCODEC_STATUS, POISONED_PF);
+		break;
+	default:
+		break;
+	}
+
+	if (poison_stat)
+		dev_info(adev->dev, "Poison detected in VCN%d, sub_block%d\n",
+			instance, sub_block);
+
+	return poison_stat;
+}
+
+static bool vcn_v5_0_1_query_poison_status(struct amdgpu_device *adev)
+{
+	uint32_t inst, sub;
+	uint32_t poison_stat = 0;
+
+	for (inst = 0; inst < adev->vcn.num_vcn_inst; inst++)
+		for (sub = 0; sub < AMDGPU_VCN_V5_0_1_MAX_SUB_BLOCK; sub++)
+			poison_stat +=
+			vcn_v5_0_1_query_poison_by_instance(adev, inst, sub);
+
+	return !!poison_stat;
+}
+
+static const struct amdgpu_ras_block_hw_ops vcn_v5_0_1_ras_hw_ops = {
+	.query_poison_status = vcn_v5_0_1_query_poison_status,
+};
+
+static int vcn_v5_0_1_aca_bank_parser(struct aca_handle *handle, struct aca_bank *bank,
+				      enum aca_smu_type type, void *data)
+{
+	struct aca_bank_info info;
+	u64 misc0;
+	int ret;
+
+	ret = aca_bank_info_decode(bank, &info);
+	if (ret)
+		return ret;
+
+	misc0 = bank->regs[ACA_REG_IDX_MISC0];
+	switch (type) {
+	case ACA_SMU_TYPE_UE:
+		bank->aca_err_type = ACA_ERROR_TYPE_UE;
+		ret = aca_error_cache_log_bank_error(handle, &info, ACA_ERROR_TYPE_UE,
+						     1ULL);
+		break;
+	case ACA_SMU_TYPE_CE:
+		bank->aca_err_type = ACA_ERROR_TYPE_CE;
+		ret = aca_error_cache_log_bank_error(handle, &info, bank->aca_err_type,
+						     ACA_REG__MISC0__ERRCNT(misc0));
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return ret;
+}
+
+/* reference to smu driver if header file */
+static int vcn_v5_0_1_err_codes[] = {
+	14, 15, /* VCN */
+};
+
+static bool vcn_v5_0_1_aca_bank_is_valid(struct aca_handle *handle, struct aca_bank *bank,
+					 enum aca_smu_type type, void *data)
+{
+	u32 instlo;
+
+	instlo = ACA_REG__IPID__INSTANCEIDLO(bank->regs[ACA_REG_IDX_IPID]);
+	instlo &= GENMASK(31, 1);
+
+	if (instlo != mmSMNAID_AID0_MCA_SMU)
+		return false;
+
+	if (aca_bank_check_error_codes(handle->adev, bank,
+				       vcn_v5_0_1_err_codes,
+				       ARRAY_SIZE(vcn_v5_0_1_err_codes)))
+		return false;
+
+	return true;
+}
+
+static const struct aca_bank_ops vcn_v5_0_1_aca_bank_ops = {
+	.aca_bank_parser = vcn_v5_0_1_aca_bank_parser,
+	.aca_bank_is_valid = vcn_v5_0_1_aca_bank_is_valid,
+};
+
+static const struct aca_info vcn_v5_0_1_aca_info = {
+	.hwip = ACA_HWIP_TYPE_SMU,
+	.mask = ACA_ERROR_UE_MASK,
+	.bank_ops = &vcn_v5_0_1_aca_bank_ops,
+};
+
+static int vcn_v5_0_1_ras_late_init(struct amdgpu_device *adev, struct ras_common_if *ras_block)
+{
+	int r;
+
+	r = amdgpu_ras_block_late_init(adev, ras_block);
+	if (r)
+		return r;
+
+	r = amdgpu_ras_bind_aca(adev, AMDGPU_RAS_BLOCK__VCN,
+				&vcn_v5_0_1_aca_info, NULL);
+	if (r)
+		goto late_fini;
+
+	return 0;
+
+late_fini:
+	amdgpu_ras_block_late_fini(adev, ras_block);
+
+	return r;
+}
+
+static struct amdgpu_vcn_ras vcn_v5_0_1_ras = {
+	.ras_block = {
+		.hw_ops = &vcn_v5_0_1_ras_hw_ops,
+		.ras_late_init = vcn_v5_0_1_ras_late_init,
+	},
+};
+
+static void vcn_v5_0_1_set_ras_funcs(struct amdgpu_device *adev)
+{
+	adev->vcn.ras = &vcn_v5_0_1_ras;
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c
index 792b2eb6bbac..48ab93e715c8 100644
--- a/drivers/gpu/drm/amd/amdgpu/vi.c
+++ b/drivers/gpu/drm/amd/amdgpu/vi.c
@@ -167,16 +167,16 @@ static const struct amdgpu_video_codec_info tonga_video_codecs_decode_array[] =
 {
 	{
 		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
+		.max_width = 1920,
+		.max_height = 1088,
+		.max_pixels_per_frame = 1920 * 1088,
 		.max_level = 3,
 	},
 	{
 		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
+		.max_width = 1920,
+		.max_height = 1088,
+		.max_pixels_per_frame = 1920 * 1088,
 		.max_level = 5,
 	},
 	{
@@ -188,9 +188,9 @@ static const struct amdgpu_video_codec_info tonga_video_codecs_decode_array[] =
 	},
 	{
 		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
+		.max_width = 1920,
+		.max_height = 1088,
+		.max_pixels_per_frame = 1920 * 1088,
 		.max_level = 4,
 	},
 };
@@ -206,16 +206,16 @@ static const struct amdgpu_video_codec_info cz_video_codecs_decode_array[] =
 {
 	{
 		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
+		.max_width = 1920,
+		.max_height = 1088,
+		.max_pixels_per_frame = 1920 * 1088,
 		.max_level = 3,
 	},
 	{
 		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
+		.max_width = 1920,
+		.max_height = 1088,
+		.max_pixels_per_frame = 1920 * 1088,
 		.max_level = 5,
 	},
 	{
@@ -227,9 +227,9 @@ static const struct amdgpu_video_codec_info cz_video_codecs_decode_array[] =
 	},
 	{
 		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
+		.max_width = 1920,
+		.max_height = 1088,
+		.max_pixels_per_frame = 1920 * 1088,
 		.max_level = 4,
 	},
 	{
@@ -239,13 +239,6 @@ static const struct amdgpu_video_codec_info cz_video_codecs_decode_array[] =
 		.max_pixels_per_frame = 4096 * 4096,
 		.max_level = 186,
 	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 0,
-	},
 };
 
 static const struct amdgpu_video_codecs cz_video_codecs_decode =
diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h
index 02f7ba8c93cd..6c8c9935a0f2 100644
--- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h
+++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h
@@ -3640,7 +3640,7 @@ static const uint32_t cwsr_trap_gfx9_4_3_hex[] = {
 };
 
 static const uint32_t cwsr_trap_gfx12_hex[] = {
-	0xbfa00001, 0xbfa0024b,
+	0xbfa00001, 0xbfa002a2,
 	0xb0804009, 0xb8f8f804,
 	0x9178ff78, 0x00008c00,
 	0xb8fbf811, 0x8b6eff78,
@@ -3714,7 +3714,15 @@ static const uint32_t cwsr_trap_gfx12_hex[] = {
 	0x00011677, 0xd7610000,
 	0x00011a79, 0xd7610000,
 	0x00011c7e, 0xd7610000,
-	0x00011e7f, 0xbefe00ff,
+	0x00011e7f, 0xd8500000,
+	0x00000000, 0xd8500000,
+	0x00000000, 0xd8500000,
+	0x00000000, 0xd8500000,
+	0x00000000, 0xd8500000,
+	0x00000000, 0xd8500000,
+	0x00000000, 0xd8500000,
+	0x00000000, 0xd8500000,
+	0x00000000, 0xbefe00ff,
 	0x00003fff, 0xbeff0080,
 	0xee0a407a, 0x000c0000,
 	0x00004000, 0xd760007a,
@@ -3751,38 +3759,46 @@ static const uint32_t cwsr_trap_gfx12_hex[] = {
 	0x00000200, 0xbef600ff,
 	0x01000000, 0x7e000280,
 	0x7e020280, 0x7e040280,
-	0xbefd0080, 0xbe804ec2,
-	0xbf94fffe, 0xb8faf804,
-	0x8b7a847a, 0x91788478,
-	0x8c787a78, 0xd7610002,
-	0x0000fa71, 0x807d817d,
-	0xd7610002, 0x0000fa6c,
-	0x807d817d, 0x917aff6d,
-	0x80000000, 0xd7610002,
-	0x0000fa7a, 0x807d817d,
-	0xd7610002, 0x0000fa6e,
-	0x807d817d, 0xd7610002,
-	0x0000fa6f, 0x807d817d,
-	0xd7610002, 0x0000fa78,
-	0x807d817d, 0xb8faf811,
-	0xd7610002, 0x0000fa7a,
-	0x807d817d, 0xd7610002,
-	0x0000fa7b, 0x807d817d,
-	0xb8f1f801, 0xd7610002,
-	0x0000fa71, 0x807d817d,
-	0xb8f1f814, 0xd7610002,
-	0x0000fa71, 0x807d817d,
-	0xb8f1f815, 0xd7610002,
-	0x0000fa71, 0x807d817d,
-	0xb8f1f812, 0xd7610002,
-	0x0000fa71, 0x807d817d,
-	0xb8f1f813, 0xd7610002,
-	0x0000fa71, 0x807d817d,
+	0xbe804ec2, 0xbf94fffe,
+	0xb8faf804, 0x8b7a847a,
+	0x91788478, 0x8c787a78,
+	0x917aff6d, 0x80000000,
+	0xd7610002, 0x00010071,
+	0xd7610002, 0x0001026c,
+	0xd7610002, 0x0001047a,
+	0xd7610002, 0x0001066e,
+	0xd7610002, 0x0001086f,
+	0xd7610002, 0x00010a78,
+	0xd7610002, 0x00010e7b,
+	0xd8500000, 0x00000000,
+	0xd8500000, 0x00000000,
+	0xd8500000, 0x00000000,
+	0xd8500000, 0x00000000,
+	0xd8500000, 0x00000000,
+	0xd8500000, 0x00000000,
+	0xd8500000, 0x00000000,
+	0xd8500000, 0x00000000,
+	0xb8faf811, 0xd7610002,
+	0x00010c7a, 0xb8faf801,
+	0xd7610002, 0x0001107a,
+	0xb8faf814, 0xd7610002,
+	0x0001127a, 0xb8faf815,
+	0xd7610002, 0x0001147a,
+	0xb8faf812, 0xd7610002,
+	0x0001167a, 0xb8faf813,
+	0xd7610002, 0x0001187a,
 	0xb8faf802, 0xd7610002,
-	0x0000fa7a, 0x807d817d,
-	0xbefa50c1, 0xbfc70000,
-	0xd7610002, 0x0000fa7a,
-	0x807d817d, 0xbefe00ff,
+	0x00011a7a, 0xbefa50c1,
+	0xbfc70000, 0xd7610002,
+	0x00011c7a, 0xd8500000,
+	0x00000000, 0xd8500000,
+	0x00000000, 0xd8500000,
+	0x00000000, 0xd8500000,
+	0x00000000, 0xd8500000,
+	0x00000000, 0xd8500000,
+	0x00000000, 0xd8500000,
+	0x00000000, 0xd8500000,
+	0x00000000, 0xbefe00ff,
 	0x0000ffff, 0xbeff0080,
 	0xc4068070, 0x008ce802,
 	0x00000000, 0xbefe00c1,
@@ -3797,328 +3813,356 @@ static const uint32_t cwsr_trap_gfx12_hex[] = {
 	0xbe824102, 0xbe844104,
 	0xbe864106, 0xbe884108,
 	0xbe8a410a, 0xbe8c410c,
-	0xbe8e410e, 0xd7610002,
-	0x0000f200, 0x80798179,
-	0xd7610002, 0x0000f201,
-	0x80798179, 0xd7610002,
-	0x0000f202, 0x80798179,
-	0xd7610002, 0x0000f203,
-	0x80798179, 0xd7610002,
-	0x0000f204, 0x80798179,
-	0xd7610002, 0x0000f205,
-	0x80798179, 0xd7610002,
-	0x0000f206, 0x80798179,
-	0xd7610002, 0x0000f207,
-	0x80798179, 0xd7610002,
-	0x0000f208, 0x80798179,
-	0xd7610002, 0x0000f209,
-	0x80798179, 0xd7610002,
-	0x0000f20a, 0x80798179,
-	0xd7610002, 0x0000f20b,
-	0x80798179, 0xd7610002,
-	0x0000f20c, 0x80798179,
-	0xd7610002, 0x0000f20d,
-	0x80798179, 0xd7610002,
-	0x0000f20e, 0x80798179,
-	0xd7610002, 0x0000f20f,
-	0x80798179, 0xbf06a079,
-	0xbfa10007, 0xc4068070,
+	0xbe8e410e, 0xbf068079,
+	0xbfa10032, 0xd7610002,
+	0x00010000, 0xd7610002,
+	0x00010201, 0xd7610002,
+	0x00010402, 0xd7610002,
+	0x00010603, 0xd7610002,
+	0x00010804, 0xd7610002,
+	0x00010a05, 0xd7610002,
+	0x00010c06, 0xd7610002,
+	0x00010e07, 0xd7610002,
+	0x00011008, 0xd7610002,
+	0x00011209, 0xd7610002,
+	0x0001140a, 0xd7610002,
+	0x0001160b, 0xd7610002,
+	0x0001180c, 0xd7610002,
+	0x00011a0d, 0xd7610002,
+	0x00011c0e, 0xd7610002,
+	0x00011e0f, 0xd8500000,
+	0x00000000, 0xd8500000,
+	0x00000000, 0xd8500000,
+	0x00000000, 0xd8500000,
+	0x00000000, 0xd8500000,
+	0x00000000, 0xd8500000,
+	0x00000000, 0xd8500000,
+	0x00000000, 0xd8500000,
+	0x00000000, 0x80799079,
+	0xbfa00038, 0xd7610002,
+	0x00012000, 0xd7610002,
+	0x00012201, 0xd7610002,
+	0x00012402, 0xd7610002,
+	0x00012603, 0xd7610002,
+	0x00012804, 0xd7610002,
+	0x00012a05, 0xd7610002,
+	0x00012c06, 0xd7610002,
+	0x00012e07, 0xd7610002,
+	0x00013008, 0xd7610002,
+	0x00013209, 0xd7610002,
+	0x0001340a, 0xd7610002,
+	0x0001360b, 0xd7610002,
+	0x0001380c, 0xd7610002,
+	0x00013a0d, 0xd7610002,
+	0x00013c0e, 0xd7610002,
+	0x00013e0f, 0xd8500000,
+	0x00000000, 0xd8500000,
+	0x00000000, 0xd8500000,
+	0x00000000, 0xd8500000,
+	0x00000000, 0xd8500000,
+	0x00000000, 0xd8500000,
+	0x00000000, 0xd8500000,
+	0x00000000, 0xd8500000,
+	0x00000000, 0x80799079,
+	0xc4068070, 0x008ce802,
+	0x00000000, 0x8070ff70,
+	0x00000080, 0xbef90080,
+	0x7e040280, 0x807d907d,
+	0xbf0aff7d, 0x00000060,
+	0xbfa2ff88, 0xbe804100,
+	0xbe824102, 0xbe844104,
+	0xbe864106, 0xbe884108,
+	0xbe8a410a, 0xd7610002,
+	0x00010000, 0xd7610002,
+	0x00010201, 0xd7610002,
+	0x00010402, 0xd7610002,
+	0x00010603, 0xd7610002,
+	0x00010804, 0xd7610002,
+	0x00010a05, 0xd7610002,
+	0x00010c06, 0xd7610002,
+	0x00010e07, 0xd7610002,
+	0x00011008, 0xd7610002,
+	0x00011209, 0xd7610002,
+	0x0001140a, 0xd7610002,
+	0x0001160b, 0xd8500000,
+	0x00000000, 0xd8500000,
+	0x00000000, 0xd8500000,
+	0x00000000, 0xd8500000,
+	0x00000000, 0xd8500000,
+	0x00000000, 0xd8500000,
+	0x00000000, 0xd8500000,
+	0x00000000, 0xd8500000,
+	0x00000000, 0xc4068070,
 	0x008ce802, 0x00000000,
+	0xbefe00c1, 0x857d9973,
+	0x8b7d817d, 0xbf06817d,
+	0xbfa20002, 0xbeff0080,
+	0xbfa00001, 0xbeff00c1,
+	0xb8fb4306, 0x8b7bc17b,
+	0xbfa10044, 0x8b7aff6d,
+	0x80000000, 0xbfa10041,
+	0x847b897b, 0xbef6007b,
+	0xb8f03b05, 0x80708170,
+	0xbf0d9973, 0xbfa20002,
+	0x84708970, 0xbfa00001,
+	0x84708a70, 0xb8fa1e06,
+	0x847a8a7a, 0x80707a70,
+	0x8070ff70, 0x00000200,
 	0x8070ff70, 0x00000080,
-	0xbef90080, 0x7e040280,
-	0x807d907d, 0xbf0aff7d,
-	0x00000060, 0xbfa2ffbb,
-	0xbe804100, 0xbe824102,
-	0xbe844104, 0xbe864106,
-	0xbe884108, 0xbe8a410a,
-	0xd7610002, 0x0000f200,
-	0x80798179, 0xd7610002,
-	0x0000f201, 0x80798179,
-	0xd7610002, 0x0000f202,
-	0x80798179, 0xd7610002,
-	0x0000f203, 0x80798179,
-	0xd7610002, 0x0000f204,
-	0x80798179, 0xd7610002,
-	0x0000f205, 0x80798179,
-	0xd7610002, 0x0000f206,
-	0x80798179, 0xd7610002,
-	0x0000f207, 0x80798179,
-	0xd7610002, 0x0000f208,
-	0x80798179, 0xd7610002,
-	0x0000f209, 0x80798179,
-	0xd7610002, 0x0000f20a,
-	0x80798179, 0xd7610002,
-	0x0000f20b, 0x80798179,
-	0xc4068070, 0x008ce802,
-	0x00000000, 0xbefe00c1,
-	0x857d9973, 0x8b7d817d,
-	0xbf06817d, 0xbfa20002,
-	0xbeff0080, 0xbfa00001,
-	0xbeff00c1, 0xb8fb4306,
-	0x8b7bc17b, 0xbfa10044,
-	0x8b7aff6d, 0x80000000,
-	0xbfa10041, 0x847b897b,
-	0xbef6007b, 0xb8f03b05,
-	0x80708170, 0xbf0d9973,
-	0xbfa20002, 0x84708970,
-	0xbfa00001, 0x84708a70,
-	0xb8fa1e06, 0x847a8a7a,
-	0x80707a70, 0x8070ff70,
-	0x00000200, 0x8070ff70,
-	0x00000080, 0xbef600ff,
-	0x01000000, 0xd71f0000,
-	0x000100c1, 0xd7200000,
-	0x000200c1, 0x16000084,
-	0x857d9973, 0x8b7d817d,
-	0xbf06817d, 0xbefd0080,
-	0xbfa20013, 0xbe8300ff,
-	0x00000080, 0xbf800000,
-	0xbf800000, 0xbf800000,
-	0xd8d80000, 0x01000000,
-	0xbf8a0000, 0xc4068070,
-	0x008ce801, 0x00000000,
-	0x807d037d, 0x80700370,
-	0xd5250000, 0x0001ff00,
-	0x00000080, 0xbf0a7b7d,
-	0xbfa2fff3, 0xbfa00012,
-	0xbe8300ff, 0x00000100,
+	0xbef600ff, 0x01000000,
+	0xd71f0000, 0x000100c1,
+	0xd7200000, 0x000200c1,
+	0x16000084, 0x857d9973,
+	0x8b7d817d, 0xbf06817d,
+	0xbefd0080, 0xbfa20013,
+	0xbe8300ff, 0x00000080,
 	0xbf800000, 0xbf800000,
 	0xbf800000, 0xd8d80000,
 	0x01000000, 0xbf8a0000,
 	0xc4068070, 0x008ce801,
 	0x00000000, 0x807d037d,
 	0x80700370, 0xd5250000,
-	0x0001ff00, 0x00000100,
+	0x0001ff00, 0x00000080,
 	0xbf0a7b7d, 0xbfa2fff3,
-	0xbefe00c1, 0x857d9973,
-	0x8b7d817d, 0xbf06817d,
-	0xbfa20004, 0xbef000ff,
-	0x00000200, 0xbeff0080,
-	0xbfa00003, 0xbef000ff,
-	0x00000400, 0xbeff00c1,
-	0xb8fb3b05, 0x807b817b,
-	0x847b827b, 0x857d9973,
-	0x8b7d817d, 0xbf06817d,
-	0xbfa2001b, 0xbef600ff,
-	0x01000000, 0xbefd0084,
-	0xbf0a7b7d, 0xbfa10040,
-	0x7e008700, 0x7e028701,
-	0x7e048702, 0x7e068703,
-	0xc4068070, 0x008ce800,
-	0x00000000, 0xc4068070,
-	0x008ce801, 0x00008000,
-	0xc4068070, 0x008ce802,
-	0x00010000, 0xc4068070,
-	0x008ce803, 0x00018000,
-	0x807d847d, 0x8070ff70,
-	0x00000200, 0xbf0a7b7d,
-	0xbfa2ffeb, 0xbfa0002a,
+	0xbfa00012, 0xbe8300ff,
+	0x00000100, 0xbf800000,
+	0xbf800000, 0xbf800000,
+	0xd8d80000, 0x01000000,
+	0xbf8a0000, 0xc4068070,
+	0x008ce801, 0x00000000,
+	0x807d037d, 0x80700370,
+	0xd5250000, 0x0001ff00,
+	0x00000100, 0xbf0a7b7d,
+	0xbfa2fff3, 0xbefe00c1,
+	0x857d9973, 0x8b7d817d,
+	0xbf06817d, 0xbfa20004,
+	0xbef000ff, 0x00000200,
+	0xbeff0080, 0xbfa00003,
+	0xbef000ff, 0x00000400,
+	0xbeff00c1, 0xb8fb3b05,
+	0x807b817b, 0x847b827b,
+	0x857d9973, 0x8b7d817d,
+	0xbf06817d, 0xbfa2001b,
 	0xbef600ff, 0x01000000,
 	0xbefd0084, 0xbf0a7b7d,
-	0xbfa10015, 0x7e008700,
+	0xbfa10040, 0x7e008700,
 	0x7e028701, 0x7e048702,
 	0x7e068703, 0xc4068070,
 	0x008ce800, 0x00000000,
 	0xc4068070, 0x008ce801,
-	0x00010000, 0xc4068070,
-	0x008ce802, 0x00020000,
+	0x00008000, 0xc4068070,
+	0x008ce802, 0x00010000,
 	0xc4068070, 0x008ce803,
-	0x00030000, 0x807d847d,
-	0x8070ff70, 0x00000400,
+	0x00018000, 0x807d847d,
+	0x8070ff70, 0x00000200,
 	0xbf0a7b7d, 0xbfa2ffeb,
-	0xb8fb1e06, 0x8b7bc17b,
-	0xbfa1000d, 0x847b837b,
-	0x807b7d7b, 0xbefe00c1,
-	0xbeff0080, 0x7e008700,
+	0xbfa0002a, 0xbef600ff,
+	0x01000000, 0xbefd0084,
+	0xbf0a7b7d, 0xbfa10015,
+	0x7e008700, 0x7e028701,
+	0x7e048702, 0x7e068703,
 	0xc4068070, 0x008ce800,
-	0x00000000, 0x807d817d,
-	0x8070ff70, 0x00000080,
-	0xbf0a7b7d, 0xbfa2fff7,
-	0xbfa0016e, 0xbef4007e,
-	0x8b75ff7f, 0x0000ffff,
-	0x8c75ff75, 0x00040000,
-	0xbef60080, 0xbef700ff,
-	0x10807fac, 0xbef1007f,
-	0xb8f20742, 0x84729972,
-	0x8b6eff7f, 0x04000000,
-	0xbfa1003b, 0xbefe00c1,
-	0x857d9972, 0x8b7d817d,
-	0xbf06817d, 0xbfa20002,
-	0xbeff0080, 0xbfa00001,
-	0xbeff00c1, 0xb8ef4306,
-	0x8b6fc16f, 0xbfa10030,
-	0x846f896f, 0xbef6006f,
+	0x00000000, 0xc4068070,
+	0x008ce801, 0x00010000,
+	0xc4068070, 0x008ce802,
+	0x00020000, 0xc4068070,
+	0x008ce803, 0x00030000,
+	0x807d847d, 0x8070ff70,
+	0x00000400, 0xbf0a7b7d,
+	0xbfa2ffeb, 0xb8fb1e06,
+	0x8b7bc17b, 0xbfa1000d,
+	0x847b837b, 0x807b7d7b,
+	0xbefe00c1, 0xbeff0080,
+	0x7e008700, 0xc4068070,
+	0x008ce800, 0x00000000,
+	0x807d817d, 0x8070ff70,
+	0x00000080, 0xbf0a7b7d,
+	0xbfa2fff7, 0xbfa0016e,
+	0xbef4007e, 0x8b75ff7f,
+	0x0000ffff, 0x8c75ff75,
+	0x00040000, 0xbef60080,
+	0xbef700ff, 0x10807fac,
+	0xbef1007f, 0xb8f20742,
+	0x84729972, 0x8b6eff7f,
+	0x04000000, 0xbfa1003b,
+	0xbefe00c1, 0x857d9972,
+	0x8b7d817d, 0xbf06817d,
+	0xbfa20002, 0xbeff0080,
+	0xbfa00001, 0xbeff00c1,
+	0xb8ef4306, 0x8b6fc16f,
+	0xbfa10030, 0x846f896f,
+	0xbef6006f, 0xb8f83b05,
+	0x80788178, 0xbf0d9972,
+	0xbfa20002, 0x84788978,
+	0xbfa00001, 0x84788a78,
+	0xb8ee1e06, 0x846e8a6e,
+	0x80786e78, 0x8078ff78,
+	0x00000200, 0x8078ff78,
+	0x00000080, 0xbef600ff,
+	0x01000000, 0x857d9972,
+	0x8b7d817d, 0xbf06817d,
+	0xbefd0080, 0xbfa2000d,
+	0xc4050078, 0x0080e800,
+	0x00000000, 0xbf8a0000,
+	0xdac00000, 0x00000000,
+	0x807dff7d, 0x00000080,
+	0x8078ff78, 0x00000080,
+	0xbf0a6f7d, 0xbfa2fff4,
+	0xbfa0000c, 0xc4050078,
+	0x0080e800, 0x00000000,
+	0xbf8a0000, 0xdac00000,
+	0x00000000, 0x807dff7d,
+	0x00000100, 0x8078ff78,
+	0x00000100, 0xbf0a6f7d,
+	0xbfa2fff4, 0xbef80080,
+	0xbefe00c1, 0x857d9972,
+	0x8b7d817d, 0xbf06817d,
+	0xbfa20002, 0xbeff0080,
+	0xbfa00001, 0xbeff00c1,
+	0xb8ef3b05, 0x806f816f,
+	0x846f826f, 0x857d9972,
+	0x8b7d817d, 0xbf06817d,
+	0xbfa2002c, 0xbef600ff,
+	0x01000000, 0xbeee0078,
+	0x8078ff78, 0x00000200,
+	0xbefd0084, 0xbf0a6f7d,
+	0xbfa10061, 0xc4050078,
+	0x008ce800, 0x00000000,
+	0xc4050078, 0x008ce801,
+	0x00008000, 0xc4050078,
+	0x008ce802, 0x00010000,
+	0xc4050078, 0x008ce803,
+	0x00018000, 0xbf8a0000,
+	0x7e008500, 0x7e028501,
+	0x7e048502, 0x7e068503,
+	0x807d847d, 0x8078ff78,
+	0x00000200, 0xbf0a6f7d,
+	0xbfa2ffea, 0xc405006e,
+	0x008ce800, 0x00000000,
+	0xc405006e, 0x008ce801,
+	0x00008000, 0xc405006e,
+	0x008ce802, 0x00010000,
+	0xc405006e, 0x008ce803,
+	0x00018000, 0xbf8a0000,
+	0xbfa0003d, 0xbef600ff,
+	0x01000000, 0xbeee0078,
+	0x8078ff78, 0x00000400,
+	0xbefd0084, 0xbf0a6f7d,
+	0xbfa10016, 0xc4050078,
+	0x008ce800, 0x00000000,
+	0xc4050078, 0x008ce801,
+	0x00010000, 0xc4050078,
+	0x008ce802, 0x00020000,
+	0xc4050078, 0x008ce803,
+	0x00030000, 0xbf8a0000,
+	0x7e008500, 0x7e028501,
+	0x7e048502, 0x7e068503,
+	0x807d847d, 0x8078ff78,
+	0x00000400, 0xbf0a6f7d,
+	0xbfa2ffea, 0xb8ef1e06,
+	0x8b6fc16f, 0xbfa1000f,
+	0x846f836f, 0x806f7d6f,
+	0xbefe00c1, 0xbeff0080,
+	0xc4050078, 0x008ce800,
+	0x00000000, 0xbf8a0000,
+	0x7e008500, 0x807d817d,
+	0x8078ff78, 0x00000080,
+	0xbf0a6f7d, 0xbfa2fff6,
+	0xbeff00c1, 0xc405006e,
+	0x008ce800, 0x00000000,
+	0xc405006e, 0x008ce801,
+	0x00010000, 0xc405006e,
+	0x008ce802, 0x00020000,
+	0xc405006e, 0x008ce803,
+	0x00030000, 0xbf8a0000,
 	0xb8f83b05, 0x80788178,
 	0xbf0d9972, 0xbfa20002,
 	0x84788978, 0xbfa00001,
 	0x84788a78, 0xb8ee1e06,
 	0x846e8a6e, 0x80786e78,
 	0x8078ff78, 0x00000200,
-	0x8078ff78, 0x00000080,
-	0xbef600ff, 0x01000000,
-	0x857d9972, 0x8b7d817d,
-	0xbf06817d, 0xbefd0080,
-	0xbfa2000d, 0xc4050078,
-	0x0080e800, 0x00000000,
-	0xbf8a0000, 0xdac00000,
-	0x00000000, 0x807dff7d,
-	0x00000080, 0x8078ff78,
-	0x00000080, 0xbf0a6f7d,
-	0xbfa2fff4, 0xbfa0000c,
-	0xc4050078, 0x0080e800,
-	0x00000000, 0xbf8a0000,
-	0xdac00000, 0x00000000,
-	0x807dff7d, 0x00000100,
-	0x8078ff78, 0x00000100,
-	0xbf0a6f7d, 0xbfa2fff4,
-	0xbef80080, 0xbefe00c1,
-	0x857d9972, 0x8b7d817d,
-	0xbf06817d, 0xbfa20002,
-	0xbeff0080, 0xbfa00001,
-	0xbeff00c1, 0xb8ef3b05,
-	0x806f816f, 0x846f826f,
-	0x857d9972, 0x8b7d817d,
-	0xbf06817d, 0xbfa2002c,
+	0x80f8ff78, 0x00000050,
 	0xbef600ff, 0x01000000,
-	0xbeee0078, 0x8078ff78,
-	0x00000200, 0xbefd0084,
-	0xbf0a6f7d, 0xbfa10061,
-	0xc4050078, 0x008ce800,
-	0x00000000, 0xc4050078,
-	0x008ce801, 0x00008000,
-	0xc4050078, 0x008ce802,
-	0x00010000, 0xc4050078,
-	0x008ce803, 0x00018000,
-	0xbf8a0000, 0x7e008500,
-	0x7e028501, 0x7e048502,
-	0x7e068503, 0x807d847d,
+	0xbefd00ff, 0x0000006c,
+	0x80f89078, 0xf462403a,
+	0xf0000000, 0xbf8a0000,
+	0x80fd847d, 0xbf800000,
+	0xbe804300, 0xbe824302,
+	0x80f8a078, 0xf462603a,
+	0xf0000000, 0xbf8a0000,
+	0x80fd887d, 0xbf800000,
+	0xbe804300, 0xbe824302,
+	0xbe844304, 0xbe864306,
+	0x80f8c078, 0xf462803a,
+	0xf0000000, 0xbf8a0000,
+	0x80fd907d, 0xbf800000,
+	0xbe804300, 0xbe824302,
+	0xbe844304, 0xbe864306,
+	0xbe884308, 0xbe8a430a,
+	0xbe8c430c, 0xbe8e430e,
+	0xbf06807d, 0xbfa1fff0,
+	0xb980f801, 0x00000000,
+	0xb8f83b05, 0x80788178,
+	0xbf0d9972, 0xbfa20002,
+	0x84788978, 0xbfa00001,
+	0x84788a78, 0xb8ee1e06,
+	0x846e8a6e, 0x80786e78,
 	0x8078ff78, 0x00000200,
-	0xbf0a6f7d, 0xbfa2ffea,
-	0xc405006e, 0x008ce800,
-	0x00000000, 0xc405006e,
-	0x008ce801, 0x00008000,
-	0xc405006e, 0x008ce802,
-	0x00010000, 0xc405006e,
-	0x008ce803, 0x00018000,
-	0xbf8a0000, 0xbfa0003d,
 	0xbef600ff, 0x01000000,
-	0xbeee0078, 0x8078ff78,
-	0x00000400, 0xbefd0084,
-	0xbf0a6f7d, 0xbfa10016,
-	0xc4050078, 0x008ce800,
-	0x00000000, 0xc4050078,
-	0x008ce801, 0x00010000,
-	0xc4050078, 0x008ce802,
-	0x00020000, 0xc4050078,
-	0x008ce803, 0x00030000,
-	0xbf8a0000, 0x7e008500,
-	0x7e028501, 0x7e048502,
-	0x7e068503, 0x807d847d,
-	0x8078ff78, 0x00000400,
-	0xbf0a6f7d, 0xbfa2ffea,
-	0xb8ef1e06, 0x8b6fc16f,
-	0xbfa1000f, 0x846f836f,
-	0x806f7d6f, 0xbefe00c1,
-	0xbeff0080, 0xc4050078,
-	0x008ce800, 0x00000000,
-	0xbf8a0000, 0x7e008500,
-	0x807d817d, 0x8078ff78,
-	0x00000080, 0xbf0a6f7d,
-	0xbfa2fff6, 0xbeff00c1,
-	0xc405006e, 0x008ce800,
-	0x00000000, 0xc405006e,
-	0x008ce801, 0x00010000,
-	0xc405006e, 0x008ce802,
-	0x00020000, 0xc405006e,
-	0x008ce803, 0x00030000,
-	0xbf8a0000, 0xb8f83b05,
-	0x80788178, 0xbf0d9972,
-	0xbfa20002, 0x84788978,
-	0xbfa00001, 0x84788a78,
-	0xb8ee1e06, 0x846e8a6e,
-	0x80786e78, 0x8078ff78,
-	0x00000200, 0x80f8ff78,
-	0x00000050, 0xbef600ff,
-	0x01000000, 0xbefd00ff,
-	0x0000006c, 0x80f89078,
-	0xf462403a, 0xf0000000,
-	0xbf8a0000, 0x80fd847d,
-	0xbf800000, 0xbe804300,
-	0xbe824302, 0x80f8a078,
-	0xf462603a, 0xf0000000,
-	0xbf8a0000, 0x80fd887d,
-	0xbf800000, 0xbe804300,
-	0xbe824302, 0xbe844304,
-	0xbe864306, 0x80f8c078,
-	0xf462803a, 0xf0000000,
-	0xbf8a0000, 0x80fd907d,
-	0xbf800000, 0xbe804300,
-	0xbe824302, 0xbe844304,
-	0xbe864306, 0xbe884308,
-	0xbe8a430a, 0xbe8c430c,
-	0xbe8e430e, 0xbf06807d,
-	0xbfa1fff0, 0xb980f801,
-	0x00000000, 0xb8f83b05,
-	0x80788178, 0xbf0d9972,
-	0xbfa20002, 0x84788978,
-	0xbfa00001, 0x84788a78,
-	0xb8ee1e06, 0x846e8a6e,
-	0x80786e78, 0x8078ff78,
-	0x00000200, 0xbef600ff,
-	0x01000000, 0xbeff0071,
-	0xf4621bfa, 0xf0000000,
-	0x80788478, 0xf4621b3a,
+	0xbeff0071, 0xf4621bfa,
 	0xf0000000, 0x80788478,
-	0xf4621b7a, 0xf0000000,
-	0x80788478, 0xf4621c3a,
+	0xf4621b3a, 0xf0000000,
+	0x80788478, 0xf4621b7a,
 	0xf0000000, 0x80788478,
-	0xf4621c7a, 0xf0000000,
-	0x80788478, 0xf4621eba,
+	0xf4621c3a, 0xf0000000,
+	0x80788478, 0xf4621c7a,
 	0xf0000000, 0x80788478,
-	0xf4621efa, 0xf0000000,
-	0x80788478, 0xf4621e7a,
+	0xf4621eba, 0xf0000000,
+	0x80788478, 0xf4621efa,
 	0xf0000000, 0x80788478,
-	0xf4621cfa, 0xf0000000,
-	0x80788478, 0xf4621bba,
+	0xf4621e7a, 0xf0000000,
+	0x80788478, 0xf4621cfa,
 	0xf0000000, 0x80788478,
-	0xbf8a0000, 0xb96ef814,
 	0xf4621bba, 0xf0000000,
 	0x80788478, 0xbf8a0000,
-	0xb96ef815, 0xf4621bba,
+	0xb96ef814, 0xf4621bba,
 	0xf0000000, 0x80788478,
-	0xbf8a0000, 0xb96ef812,
+	0xbf8a0000, 0xb96ef815,
 	0xf4621bba, 0xf0000000,
 	0x80788478, 0xbf8a0000,
-	0xb96ef813, 0x8b6eff7f,
-	0x04000000, 0xbfa1000d,
-	0x80788478, 0xf4621bba,
+	0xb96ef812, 0xf4621bba,
 	0xf0000000, 0x80788478,
-	0xbf8a0000, 0xbf0d806e,
-	0xbfa10006, 0x856e906e,
-	0x8b6e6e6e, 0xbfa10003,
-	0xbe804ec1, 0x816ec16e,
-	0xbfa0fffb, 0xbefd006f,
-	0xbefe0070, 0xbeff0071,
-	0xb97b2011, 0x857b867b,
-	0xb97b0191, 0x857b827b,
-	0xb97bba11, 0xb973f801,
-	0xb8ee3b05, 0x806e816e,
-	0xbf0d9972, 0xbfa20002,
-	0x846e896e, 0xbfa00001,
-	0x846e8a6e, 0xb8ef1e06,
-	0x846f8a6f, 0x806e6f6e,
-	0x806eff6e, 0x00000200,
-	0x806e746e, 0x826f8075,
-	0x8b6fff6f, 0x0000ffff,
-	0xf4605c37, 0xf8000050,
-	0xf4605d37, 0xf8000060,
-	0xf4601e77, 0xf8000074,
-	0xbf8a0000, 0x8b6dff6d,
-	0x0000ffff, 0x8bfe7e7e,
-	0x8bea6a6a, 0xb97af804,
+	0xbf8a0000, 0xb96ef813,
+	0x8b6eff7f, 0x04000000,
+	0xbfa1000d, 0x80788478,
+	0xf4621bba, 0xf0000000,
+	0x80788478, 0xbf8a0000,
+	0xbf0d806e, 0xbfa10006,
+	0x856e906e, 0x8b6e6e6e,
+	0xbfa10003, 0xbe804ec1,
+	0x816ec16e, 0xbfa0fffb,
+	0xbefd006f, 0xbefe0070,
+	0xbeff0071, 0xb97b2011,
+	0x857b867b, 0xb97b0191,
+	0x857b827b, 0xb97bba11,
+	0xb973f801, 0xb8ee3b05,
+	0x806e816e, 0xbf0d9972,
+	0xbfa20002, 0x846e896e,
+	0xbfa00001, 0x846e8a6e,
+	0xb8ef1e06, 0x846f8a6f,
+	0x806e6f6e, 0x806eff6e,
+	0x00000200, 0x806e746e,
+	0x826f8075, 0x8b6fff6f,
+	0x0000ffff, 0xf4605c37,
+	0xf8000050, 0xf4605d37,
+	0xf8000060, 0xf4601e77,
+	0xf8000074, 0xbf8a0000,
+	0x8b6dff6d, 0x0000ffff,
+	0x8bfe7e7e, 0x8bea6a6a,
+	0xb97af804, 0xbe804ec2,
+	0xbf94fffe, 0xbe804a6c,
 	0xbe804ec2, 0xbf94fffe,
-	0xbe804a6c, 0xbfb10000,
+	0xbfb10000, 0xbf9f0000,
 	0xbf9f0000, 0xbf9f0000,
 	0xbf9f0000, 0xbf9f0000,
-	0xbf9f0000, 0x00000000,
 };
diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm
index 44772eec9ef4..96fbb16ceb21 100644
--- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm
+++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm
@@ -34,41 +34,24 @@
  *   cpp -DASIC_FAMILY=CHIP_PLUM_BONITO cwsr_trap_handler_gfx10.asm -P -o gfx11.sp3
  *   sp3 gfx11.sp3 -hex gfx11.hex
  *
- * gfx12:
- *   cpp -DASIC_FAMILY=CHIP_GFX12 cwsr_trap_handler_gfx10.asm -P -o gfx12.sp3
- *   sp3 gfx12.sp3 -hex gfx12.hex
  */
 
 #define CHIP_NAVI10 26
 #define CHIP_SIENNA_CICHLID 30
 #define CHIP_PLUM_BONITO 36
-#define CHIP_GFX12 37
 
 #define NO_SQC_STORE (ASIC_FAMILY >= CHIP_SIENNA_CICHLID)
 #define HAVE_XNACK (ASIC_FAMILY < CHIP_SIENNA_CICHLID)
 #define HAVE_SENDMSG_RTN (ASIC_FAMILY >= CHIP_PLUM_BONITO)
 #define HAVE_BUFFER_LDS_LOAD (ASIC_FAMILY < CHIP_PLUM_BONITO)
-#define SW_SA_TRAP (ASIC_FAMILY >= CHIP_PLUM_BONITO && ASIC_FAMILY < CHIP_GFX12)
+#define SW_SA_TRAP (ASIC_FAMILY == CHIP_PLUM_BONITO)
 #define SAVE_AFTER_XNACK_ERROR (HAVE_XNACK && !NO_SQC_STORE) // workaround for TCP store failure after XNACK error when ALLOW_REPLAY=0, for debugger
 #define SINGLE_STEP_MISSED_WORKAROUND 1	//workaround for lost MODE.DEBUG_EN exception when SAVECTX raised
 
-#if ASIC_FAMILY < CHIP_GFX12
 #define S_COHERENCE glc:1
 #define V_COHERENCE slc:1 glc:1
 #define S_WAITCNT_0 s_waitcnt 0
-#else
-#define S_COHERENCE scope:SCOPE_SYS
-#define V_COHERENCE scope:SCOPE_SYS
-#define S_WAITCNT_0 s_wait_idle
-
-#define HW_REG_SHADER_FLAT_SCRATCH_LO HW_REG_WAVE_SCRATCH_BASE_LO
-#define HW_REG_SHADER_FLAT_SCRATCH_HI HW_REG_WAVE_SCRATCH_BASE_HI
-#define HW_REG_GPR_ALLOC HW_REG_WAVE_GPR_ALLOC
-#define HW_REG_LDS_ALLOC HW_REG_WAVE_LDS_ALLOC
-#define HW_REG_MODE HW_REG_WAVE_MODE
-#endif
 
-#if ASIC_FAMILY < CHIP_GFX12
 var SQ_WAVE_STATUS_SPI_PRIO_MASK		= 0x00000006
 var SQ_WAVE_STATUS_HALT_MASK			= 0x2000
 var SQ_WAVE_STATUS_ECC_ERR_MASK			= 0x20000
@@ -81,21 +64,6 @@ var S_STATUS_ALWAYS_CLEAR_MASK			= SQ_WAVE_STATUS_SPI_PRIO_MASK|SQ_WAVE_STATUS_E
 var S_STATUS_HALT_MASK				= SQ_WAVE_STATUS_HALT_MASK
 var S_SAVE_PC_HI_TRAP_ID_MASK			= 0x00FF0000
 var S_SAVE_PC_HI_HT_MASK			= 0x01000000
-#else
-var SQ_WAVE_STATE_PRIV_BARRIER_COMPLETE_MASK	= 0x4
-var SQ_WAVE_STATE_PRIV_SCC_SHIFT		= 9
-var SQ_WAVE_STATE_PRIV_SYS_PRIO_MASK		= 0xC00
-var SQ_WAVE_STATE_PRIV_HALT_MASK		= 0x4000
-var SQ_WAVE_STATE_PRIV_POISON_ERR_MASK		= 0x8000
-var SQ_WAVE_STATE_PRIV_POISON_ERR_SHIFT		= 15
-var SQ_WAVE_STATUS_WAVE64_SHIFT			= 29
-var SQ_WAVE_STATUS_WAVE64_SIZE			= 1
-var SQ_WAVE_LDS_ALLOC_GRANULARITY		= 9
-var S_STATUS_HWREG				= HW_REG_WAVE_STATE_PRIV
-var S_STATUS_ALWAYS_CLEAR_MASK			= SQ_WAVE_STATE_PRIV_SYS_PRIO_MASK|SQ_WAVE_STATE_PRIV_POISON_ERR_MASK
-var S_STATUS_HALT_MASK				= SQ_WAVE_STATE_PRIV_HALT_MASK
-var S_SAVE_PC_HI_TRAP_ID_MASK			= 0xF0000000
-#endif
 
 var SQ_WAVE_STATUS_NO_VGPRS_SHIFT		= 24
 var SQ_WAVE_LDS_ALLOC_LDS_SIZE_SHIFT		= 12
@@ -110,7 +78,6 @@ var SQ_WAVE_GPR_ALLOC_VGPR_SIZE_SHIFT		= 8
 var SQ_WAVE_GPR_ALLOC_VGPR_SIZE_SHIFT		= 12
 #endif
 
-#if ASIC_FAMILY < CHIP_GFX12
 var SQ_WAVE_TRAPSTS_SAVECTX_MASK		= 0x400
 var SQ_WAVE_TRAPSTS_EXCP_MASK			= 0x1FF
 var SQ_WAVE_TRAPSTS_SAVECTX_SHIFT		= 10
@@ -161,39 +128,6 @@ var S_TRAPSTS_RESTORE_PART_3_SIZE		= 32 - S_TRAPSTS_RESTORE_PART_3_SHIFT
 var S_TRAPSTS_HWREG				= HW_REG_TRAPSTS
 var S_TRAPSTS_SAVE_CONTEXT_MASK			= SQ_WAVE_TRAPSTS_SAVECTX_MASK
 var S_TRAPSTS_SAVE_CONTEXT_SHIFT		= SQ_WAVE_TRAPSTS_SAVECTX_SHIFT
-#else
-var SQ_WAVE_EXCP_FLAG_PRIV_ADDR_WATCH_MASK	= 0xF
-var SQ_WAVE_EXCP_FLAG_PRIV_MEM_VIOL_MASK	= 0x10
-var SQ_WAVE_EXCP_FLAG_PRIV_SAVE_CONTEXT_SHIFT	= 5
-var SQ_WAVE_EXCP_FLAG_PRIV_SAVE_CONTEXT_MASK	= 0x20
-var SQ_WAVE_EXCP_FLAG_PRIV_ILLEGAL_INST_MASK	= 0x40
-var SQ_WAVE_EXCP_FLAG_PRIV_ILLEGAL_INST_SHIFT	= 6
-var SQ_WAVE_EXCP_FLAG_PRIV_HOST_TRAP_MASK	= 0x80
-var SQ_WAVE_EXCP_FLAG_PRIV_HOST_TRAP_SHIFT	= 7
-var SQ_WAVE_EXCP_FLAG_PRIV_WAVE_START_MASK	= 0x100
-var SQ_WAVE_EXCP_FLAG_PRIV_WAVE_START_SHIFT	= 8
-var SQ_WAVE_EXCP_FLAG_PRIV_WAVE_END_MASK	= 0x200
-var SQ_WAVE_EXCP_FLAG_PRIV_TRAP_AFTER_INST_MASK	= 0x800
-var SQ_WAVE_TRAP_CTRL_ADDR_WATCH_MASK		= 0x80
-var SQ_WAVE_TRAP_CTRL_TRAP_AFTER_INST_MASK	= 0x200
-
-var S_TRAPSTS_HWREG				= HW_REG_WAVE_EXCP_FLAG_PRIV
-var S_TRAPSTS_SAVE_CONTEXT_MASK			= SQ_WAVE_EXCP_FLAG_PRIV_SAVE_CONTEXT_MASK
-var S_TRAPSTS_SAVE_CONTEXT_SHIFT		= SQ_WAVE_EXCP_FLAG_PRIV_SAVE_CONTEXT_SHIFT
-var S_TRAPSTS_NON_MASKABLE_EXCP_MASK		= SQ_WAVE_EXCP_FLAG_PRIV_MEM_VIOL_MASK		|\
-						  SQ_WAVE_EXCP_FLAG_PRIV_ILLEGAL_INST_MASK	|\
-						  SQ_WAVE_EXCP_FLAG_PRIV_HOST_TRAP_MASK		|\
-						  SQ_WAVE_EXCP_FLAG_PRIV_WAVE_START_MASK	|\
-						  SQ_WAVE_EXCP_FLAG_PRIV_WAVE_END_MASK		|\
-						  SQ_WAVE_EXCP_FLAG_PRIV_TRAP_AFTER_INST_MASK
-var S_TRAPSTS_RESTORE_PART_1_SIZE		= SQ_WAVE_EXCP_FLAG_PRIV_SAVE_CONTEXT_SHIFT
-var S_TRAPSTS_RESTORE_PART_2_SHIFT		= SQ_WAVE_EXCP_FLAG_PRIV_ILLEGAL_INST_SHIFT
-var S_TRAPSTS_RESTORE_PART_2_SIZE		= SQ_WAVE_EXCP_FLAG_PRIV_HOST_TRAP_SHIFT - SQ_WAVE_EXCP_FLAG_PRIV_ILLEGAL_INST_SHIFT
-var S_TRAPSTS_RESTORE_PART_3_SHIFT		= SQ_WAVE_EXCP_FLAG_PRIV_WAVE_START_SHIFT
-var S_TRAPSTS_RESTORE_PART_3_SIZE		= 32 - S_TRAPSTS_RESTORE_PART_3_SHIFT
-var BARRIER_STATE_SIGNAL_OFFSET			= 16
-var BARRIER_STATE_VALID_OFFSET			= 0
-#endif
 
 // bits [31:24] unused by SPI debug data
 var TTMP11_SAVE_REPLAY_W64H_SHIFT		= 31
@@ -305,11 +239,7 @@ L_TRAP_NO_BARRIER:
 
 L_HALTED:
 	// Host trap may occur while wave is halted.
-#if ASIC_FAMILY < CHIP_GFX12
 	s_and_b32	ttmp2, s_save_pc_hi, S_SAVE_PC_HI_TRAP_ID_MASK
-#else
-	s_and_b32	ttmp2, s_save_trapsts, SQ_WAVE_EXCP_FLAG_PRIV_HOST_TRAP_MASK
-#endif
 	s_cbranch_scc1	L_FETCH_2ND_TRAP
 
 L_CHECK_SAVE:
@@ -336,7 +266,6 @@ L_NOT_HALTED:
 	// Check for maskable exceptions in trapsts.excp and trapsts.excp_hi.
 	// Maskable exceptions only cause the wave to enter the trap handler if
 	// their respective bit in mode.excp_en is set.
-#if ASIC_FAMILY < CHIP_GFX12
 	s_and_b32	ttmp2, s_save_trapsts, SQ_WAVE_TRAPSTS_EXCP_MASK|SQ_WAVE_TRAPSTS_EXCP_HI_MASK
 	s_cbranch_scc0	L_CHECK_TRAP_ID
 
@@ -349,17 +278,6 @@ L_NOT_ADDR_WATCH:
 	s_lshl_b32	ttmp2, ttmp2, SQ_WAVE_MODE_EXCP_EN_SHIFT
 	s_and_b32	ttmp2, ttmp2, ttmp3
 	s_cbranch_scc1	L_FETCH_2ND_TRAP
-#else
-	s_getreg_b32	ttmp2, hwreg(HW_REG_WAVE_EXCP_FLAG_USER)
-	s_and_b32	ttmp3, s_save_trapsts, SQ_WAVE_EXCP_FLAG_PRIV_ADDR_WATCH_MASK
-	s_cbranch_scc0	L_NOT_ADDR_WATCH
-	s_or_b32	ttmp2, ttmp2, SQ_WAVE_TRAP_CTRL_ADDR_WATCH_MASK
-
-L_NOT_ADDR_WATCH:
-	s_getreg_b32	ttmp3, hwreg(HW_REG_WAVE_TRAP_CTRL)
-	s_and_b32	ttmp2, ttmp3, ttmp2
-	s_cbranch_scc1	L_FETCH_2ND_TRAP
-#endif
 
 L_CHECK_TRAP_ID:
 	// Check trap_id != 0
@@ -369,13 +287,8 @@ L_CHECK_TRAP_ID:
 #if SINGLE_STEP_MISSED_WORKAROUND
 	// Prioritize single step exception over context save.
 	// Second-level trap will halt wave and RFE, re-entering for SAVECTX.
-#if ASIC_FAMILY < CHIP_GFX12
 	s_getreg_b32	ttmp2, hwreg(HW_REG_MODE)
 	s_and_b32	ttmp2, ttmp2, SQ_WAVE_MODE_DEBUG_EN_MASK
-#else
-	// WAVE_TRAP_CTRL is already in ttmp3.
-	s_and_b32	ttmp3, ttmp3, SQ_WAVE_TRAP_CTRL_TRAP_AFTER_INST_MASK
-#endif
 	s_cbranch_scc1	L_FETCH_2ND_TRAP
 #endif
 
@@ -425,12 +338,7 @@ L_NO_NEXT_TRAP:
 	s_cbranch_scc1	L_TRAP_CASE
 
 	// Host trap will not cause trap re-entry.
-#if ASIC_FAMILY < CHIP_GFX12
 	s_and_b32	ttmp2, s_save_pc_hi, S_SAVE_PC_HI_HT_MASK
-#else
-	s_getreg_b32	ttmp2, hwreg(HW_REG_WAVE_EXCP_FLAG_PRIV)
-	s_and_b32	ttmp2, ttmp2, SQ_WAVE_EXCP_FLAG_PRIV_HOST_TRAP_MASK
-#endif
 	s_cbranch_scc1	L_EXIT_TRAP
 	s_or_b32	s_save_status, s_save_status, S_STATUS_HALT_MASK
 
@@ -457,16 +365,7 @@ L_EXIT_TRAP:
 	s_and_b64	exec, exec, exec					// Restore STATUS.EXECZ, not writable by s_setreg_b32
 	s_and_b64	vcc, vcc, vcc						// Restore STATUS.VCCZ, not writable by s_setreg_b32
 
-#if ASIC_FAMILY < CHIP_GFX12
 	s_setreg_b32	hwreg(S_STATUS_HWREG), s_save_status
-#else
-	// STATE_PRIV.BARRIER_COMPLETE may have changed since we read it.
-	// Only restore fields which the trap handler changes.
-	s_lshr_b32	s_save_status, s_save_status, SQ_WAVE_STATE_PRIV_SCC_SHIFT
-	s_setreg_b32	hwreg(S_STATUS_HWREG, SQ_WAVE_STATE_PRIV_SCC_SHIFT, \
-		SQ_WAVE_STATE_PRIV_POISON_ERR_SHIFT - SQ_WAVE_STATE_PRIV_SCC_SHIFT + 1), s_save_status
-#endif
-
 	s_rfe_b64	[ttmp0, ttmp1]
 
 L_SAVE:
@@ -478,14 +377,6 @@ L_SAVE:
 	s_endpgm
 L_HAVE_VGPRS:
 #endif
-#if ASIC_FAMILY >= CHIP_GFX12
-	s_getreg_b32	s_save_tmp, hwreg(HW_REG_WAVE_STATUS)
-	s_bitcmp1_b32	s_save_tmp, SQ_WAVE_STATUS_NO_VGPRS_SHIFT
-	s_cbranch_scc0	L_HAVE_VGPRS
-	s_endpgm
-L_HAVE_VGPRS:
-#endif
-
 	s_and_b32	s_save_pc_hi, s_save_pc_hi, 0x0000ffff			//pc[47:32]
 	s_mov_b32	s_save_tmp, 0
 	s_setreg_b32	hwreg(S_TRAPSTS_HWREG, S_TRAPSTS_SAVE_CONTEXT_SHIFT, 1), s_save_tmp	//clear saveCtx bit
@@ -671,19 +562,6 @@ L_SAVE_HWREG:
 	s_mov_b32	m0, 0x0							//Next lane of v2 to write to
 #endif
 
-#if ASIC_FAMILY >= CHIP_GFX12
-	// Ensure no further changes to barrier or LDS state.
-	// STATE_PRIV.BARRIER_COMPLETE may change up to this point.
-	s_barrier_signal	-2
-	s_barrier_wait	-2
-
-	// Re-read final state of BARRIER_COMPLETE field for save.
-	s_getreg_b32	s_save_tmp, hwreg(S_STATUS_HWREG)
-	s_and_b32	s_save_tmp, s_save_tmp, SQ_WAVE_STATE_PRIV_BARRIER_COMPLETE_MASK
-	s_andn2_b32	s_save_status, s_save_status, SQ_WAVE_STATE_PRIV_BARRIER_COMPLETE_MASK
-	s_or_b32	s_save_status, s_save_status, s_save_tmp
-#endif
-
 	write_hwreg_to_mem(s_save_m0, s_save_buf_rsrc0, s_save_mem_offset)
 	write_hwreg_to_mem(s_save_pc_lo, s_save_buf_rsrc0, s_save_mem_offset)
 	s_andn2_b32	s_save_tmp, s_save_pc_hi, S_SAVE_PC_HI_FIRST_WAVE_MASK
@@ -707,21 +585,6 @@ L_SAVE_HWREG:
 	s_getreg_b32	s_save_m0, hwreg(HW_REG_SHADER_FLAT_SCRATCH_HI)
 	write_hwreg_to_mem(s_save_m0, s_save_buf_rsrc0, s_save_mem_offset)
 
-#if ASIC_FAMILY >= CHIP_GFX12
-	s_getreg_b32	s_save_m0, hwreg(HW_REG_WAVE_EXCP_FLAG_USER)
-	write_hwreg_to_mem(s_save_m0, s_save_buf_rsrc0, s_save_mem_offset)
-
-	s_getreg_b32	s_save_m0, hwreg(HW_REG_WAVE_TRAP_CTRL)
-	write_hwreg_to_mem(s_save_m0, s_save_buf_rsrc0, s_save_mem_offset)
-
-	s_getreg_b32	s_save_tmp, hwreg(HW_REG_WAVE_STATUS)
-	write_hwreg_to_mem(s_save_tmp, s_save_buf_rsrc0, s_save_mem_offset)
-
-	s_get_barrier_state s_save_tmp, -1
-	s_wait_kmcnt (0)
-	write_hwreg_to_mem(s_save_tmp, s_save_buf_rsrc0, s_save_mem_offset)
-#endif
-
 #if NO_SQC_STORE
 	// Write HWREGs with 16 VGPR lanes. TTMPs occupy space after this.
 	s_mov_b32       exec_lo, 0xFFFF
@@ -814,9 +677,7 @@ L_SAVE_LDS_NORMAL:
 	s_and_b32	s_save_alloc_size, s_save_alloc_size, 0xFFFFFFFF	//lds_size is zero?
 	s_cbranch_scc0	L_SAVE_LDS_DONE						//no lds used? jump to L_SAVE_DONE
 
-#if ASIC_FAMILY < CHIP_GFX12
 	s_barrier								//LDS is used? wait for other waves in the same TG
-#endif
 	s_and_b32	s_save_tmp, s_save_pc_hi, S_SAVE_PC_HI_FIRST_WAVE_MASK
 	s_cbranch_scc0	L_SAVE_LDS_DONE
 
@@ -1081,11 +942,6 @@ L_RESTORE:
 	s_mov_b32	s_restore_buf_rsrc2, 0					//NUM_RECORDS initial value = 0 (in bytes)
 	s_mov_b32	s_restore_buf_rsrc3, S_RESTORE_BUF_RSRC_WORD3_MISC
 
-#if ASIC_FAMILY >= CHIP_GFX12
-	// Save s_restore_spi_init_hi for later use.
-	s_mov_b32 s_restore_spi_init_hi_save, s_restore_spi_init_hi
-#endif
-
 	//determine it is wave32 or wave64
 	get_wave_size2(s_restore_size)
 
@@ -1320,9 +1176,7 @@ L_RESTORE_SGPR:
 	// s_barrier with MODE.DEBUG_EN=1, STATUS.PRIV=1 incorrectly asserts debug exception.
 	// Clear DEBUG_EN before and restore MODE after the barrier.
 	s_setreg_imm32_b32	hwreg(HW_REG_MODE), 0
-#if ASIC_FAMILY < CHIP_GFX12
 	s_barrier								//barrier to ensure the readiness of LDS before access attemps from any other wave in the same TG
-#endif
 
 	/* restore HW registers */
 L_RESTORE_HWREG:
@@ -1334,11 +1188,6 @@ L_RESTORE_HWREG:
 
 	s_mov_b32	s_restore_buf_rsrc2, 0x1000000				//NUM_RECORDS in bytes
 
-#if ASIC_FAMILY >= CHIP_GFX12
-	// Restore s_restore_spi_init_hi before the saved value gets clobbered.
-	s_mov_b32 s_restore_spi_init_hi, s_restore_spi_init_hi_save
-#endif
-
 	read_hwreg_from_mem(s_restore_m0, s_restore_buf_rsrc0, s_restore_mem_offset)
 	read_hwreg_from_mem(s_restore_pc_lo, s_restore_buf_rsrc0, s_restore_mem_offset)
 	read_hwreg_from_mem(s_restore_pc_hi, s_restore_buf_rsrc0, s_restore_mem_offset)
@@ -1358,44 +1207,6 @@ L_RESTORE_HWREG:
 
 	s_setreg_b32	hwreg(HW_REG_SHADER_FLAT_SCRATCH_HI), s_restore_flat_scratch
 
-#if ASIC_FAMILY >= CHIP_GFX12
-	read_hwreg_from_mem(s_restore_tmp, s_restore_buf_rsrc0, s_restore_mem_offset)
-	S_WAITCNT_0
-	s_setreg_b32	hwreg(HW_REG_WAVE_EXCP_FLAG_USER), s_restore_tmp
-
-	read_hwreg_from_mem(s_restore_tmp, s_restore_buf_rsrc0, s_restore_mem_offset)
-	S_WAITCNT_0
-	s_setreg_b32	hwreg(HW_REG_WAVE_TRAP_CTRL), s_restore_tmp
-
-	// Only the first wave needs to restore the workgroup barrier.
-	s_and_b32	s_restore_tmp, s_restore_spi_init_hi, S_RESTORE_SPI_INIT_FIRST_WAVE_MASK
-	s_cbranch_scc0	L_SKIP_BARRIER_RESTORE
-
-	// Skip over WAVE_STATUS, since there is no state to restore from it
-	s_add_u32	s_restore_mem_offset, s_restore_mem_offset, 4
-
-	read_hwreg_from_mem(s_restore_tmp, s_restore_buf_rsrc0, s_restore_mem_offset)
-	S_WAITCNT_0
-
-	s_bitcmp1_b32	s_restore_tmp, BARRIER_STATE_VALID_OFFSET
-	s_cbranch_scc0	L_SKIP_BARRIER_RESTORE
-
-	// extract the saved signal count from s_restore_tmp
-	s_lshr_b32	s_restore_tmp, s_restore_tmp, BARRIER_STATE_SIGNAL_OFFSET
-
-	// We need to call s_barrier_signal repeatedly to restore the signal
-	// count of the work group barrier.  The member count is already
-	// initialized with the number of waves in the work group.
-L_BARRIER_RESTORE_LOOP:
-	s_and_b32	s_restore_tmp, s_restore_tmp, s_restore_tmp
-	s_cbranch_scc0	L_SKIP_BARRIER_RESTORE
-	s_barrier_signal	-1
-	s_add_i32	s_restore_tmp, s_restore_tmp, -1
-	s_branch	L_BARRIER_RESTORE_LOOP
-
-L_SKIP_BARRIER_RESTORE:
-#endif
-
 	s_mov_b32	m0, s_restore_m0
 	s_mov_b32	exec_lo, s_restore_exec_lo
 	s_mov_b32	exec_hi, s_restore_exec_hi
@@ -1453,13 +1264,6 @@ L_RETURN_WITHOUT_PRIV:
 
 	s_setreg_b32	hwreg(S_STATUS_HWREG), s_restore_status			// SCC is included, which is changed by previous salu
 
-#if ASIC_FAMILY >= CHIP_GFX12
-	// Make barrier and LDS state visible to all waves in the group.
-	// STATE_PRIV.BARRIER_COMPLETE may change after this point.
-	s_barrier_signal	-2
-	s_barrier_wait	-2
-#endif
-
 	s_rfe_b64	s_restore_pc_lo						//Return to the main shader program and resume execution
 
 L_END_PGM:
@@ -1598,11 +1402,7 @@ function get_hwreg_size_bytes
 end
 
 function get_wave_size2(s_reg)
-#if ASIC_FAMILY < CHIP_GFX12
 	s_getreg_b32	s_reg, hwreg(HW_REG_IB_STS2,SQ_WAVE_IB_STS2_WAVE64_SHIFT,SQ_WAVE_IB_STS2_WAVE64_SIZE)
-#else
-	s_getreg_b32	s_reg, hwreg(HW_REG_WAVE_STATUS,SQ_WAVE_STATUS_WAVE64_SHIFT,SQ_WAVE_STATUS_WAVE64_SIZE)
-#endif
 	s_lshl_b32	s_reg, s_reg, S_WAVE_SIZE
 end
 
diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx12.asm b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx12.asm
new file mode 100644
index 000000000000..5a1a1b1f897f
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx12.asm
@@ -0,0 +1,1136 @@
+/*
+ * Copyright 2018 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+/* To compile this assembly code:
+ *
+ * gfx12:
+ *   cpp -DASIC_FAMILY=CHIP_GFX12 cwsr_trap_handler_gfx12.asm -P -o gfx12.sp3
+ *   sp3 gfx12.sp3 -hex gfx12.hex
+ */
+
+#define CHIP_GFX12 37
+
+#define SINGLE_STEP_MISSED_WORKAROUND 1	//workaround for lost TRAP_AFTER_INST exception when SAVECTX raised
+#define HAVE_VALU_SGPR_HAZARD (ASIC_FAMILY == CHIP_GFX12)
+
+var SQ_WAVE_STATE_PRIV_BARRIER_COMPLETE_MASK	= 0x4
+var SQ_WAVE_STATE_PRIV_SCC_SHIFT		= 9
+var SQ_WAVE_STATE_PRIV_SYS_PRIO_MASK		= 0xC00
+var SQ_WAVE_STATE_PRIV_HALT_MASK		= 0x4000
+var SQ_WAVE_STATE_PRIV_POISON_ERR_MASK		= 0x8000
+var SQ_WAVE_STATE_PRIV_POISON_ERR_SHIFT		= 15
+var SQ_WAVE_STATUS_WAVE64_SHIFT			= 29
+var SQ_WAVE_STATUS_WAVE64_SIZE			= 1
+var SQ_WAVE_STATUS_NO_VGPRS_SHIFT		= 24
+var SQ_WAVE_STATE_PRIV_ALWAYS_CLEAR_MASK	= SQ_WAVE_STATE_PRIV_SYS_PRIO_MASK|SQ_WAVE_STATE_PRIV_POISON_ERR_MASK
+var S_SAVE_PC_HI_TRAP_ID_MASK			= 0xF0000000
+
+var SQ_WAVE_LDS_ALLOC_LDS_SIZE_SHIFT		= 12
+var SQ_WAVE_LDS_ALLOC_LDS_SIZE_SIZE		= 9
+var SQ_WAVE_GPR_ALLOC_VGPR_SIZE_SIZE		= 8
+var SQ_WAVE_GPR_ALLOC_VGPR_SIZE_SHIFT		= 12
+var SQ_WAVE_LDS_ALLOC_VGPR_SHARED_SIZE_SHIFT	= 24
+var SQ_WAVE_LDS_ALLOC_VGPR_SHARED_SIZE_SIZE	= 4
+var SQ_WAVE_LDS_ALLOC_GRANULARITY		= 9
+
+var SQ_WAVE_EXCP_FLAG_PRIV_ADDR_WATCH_MASK	= 0xF
+var SQ_WAVE_EXCP_FLAG_PRIV_MEM_VIOL_MASK	= 0x10
+var SQ_WAVE_EXCP_FLAG_PRIV_SAVE_CONTEXT_SHIFT	= 5
+var SQ_WAVE_EXCP_FLAG_PRIV_SAVE_CONTEXT_MASK	= 0x20
+var SQ_WAVE_EXCP_FLAG_PRIV_ILLEGAL_INST_MASK	= 0x40
+var SQ_WAVE_EXCP_FLAG_PRIV_ILLEGAL_INST_SHIFT	= 6
+var SQ_WAVE_EXCP_FLAG_PRIV_HOST_TRAP_MASK	= 0x80
+var SQ_WAVE_EXCP_FLAG_PRIV_HOST_TRAP_SHIFT	= 7
+var SQ_WAVE_EXCP_FLAG_PRIV_WAVE_START_MASK	= 0x100
+var SQ_WAVE_EXCP_FLAG_PRIV_WAVE_START_SHIFT	= 8
+var SQ_WAVE_EXCP_FLAG_PRIV_WAVE_END_MASK	= 0x200
+var SQ_WAVE_EXCP_FLAG_PRIV_TRAP_AFTER_INST_MASK	= 0x800
+var SQ_WAVE_TRAP_CTRL_ADDR_WATCH_MASK		= 0x80
+var SQ_WAVE_TRAP_CTRL_TRAP_AFTER_INST_MASK	= 0x200
+
+var SQ_WAVE_EXCP_FLAG_PRIV_NON_MASKABLE_EXCP_MASK= SQ_WAVE_EXCP_FLAG_PRIV_MEM_VIOL_MASK		|\
+						  SQ_WAVE_EXCP_FLAG_PRIV_ILLEGAL_INST_MASK	|\
+						  SQ_WAVE_EXCP_FLAG_PRIV_HOST_TRAP_MASK		|\
+						  SQ_WAVE_EXCP_FLAG_PRIV_WAVE_START_MASK	|\
+						  SQ_WAVE_EXCP_FLAG_PRIV_WAVE_END_MASK		|\
+						  SQ_WAVE_EXCP_FLAG_PRIV_TRAP_AFTER_INST_MASK
+var SQ_WAVE_EXCP_FLAG_PRIV_RESTORE_PART_1_SIZE	= SQ_WAVE_EXCP_FLAG_PRIV_SAVE_CONTEXT_SHIFT
+var SQ_WAVE_EXCP_FLAG_PRIV_RESTORE_PART_2_SHIFT	= SQ_WAVE_EXCP_FLAG_PRIV_ILLEGAL_INST_SHIFT
+var SQ_WAVE_EXCP_FLAG_PRIV_RESTORE_PART_2_SIZE	= SQ_WAVE_EXCP_FLAG_PRIV_HOST_TRAP_SHIFT - SQ_WAVE_EXCP_FLAG_PRIV_ILLEGAL_INST_SHIFT
+var SQ_WAVE_EXCP_FLAG_PRIV_RESTORE_PART_3_SHIFT	= SQ_WAVE_EXCP_FLAG_PRIV_WAVE_START_SHIFT
+var SQ_WAVE_EXCP_FLAG_PRIV_RESTORE_PART_3_SIZE	= 32 - SQ_WAVE_EXCP_FLAG_PRIV_RESTORE_PART_3_SHIFT
+var BARRIER_STATE_SIGNAL_OFFSET			= 16
+var BARRIER_STATE_VALID_OFFSET			= 0
+
+var TTMP11_DEBUG_TRAP_ENABLED_SHIFT		= 23
+var TTMP11_DEBUG_TRAP_ENABLED_MASK		= 0x800000
+
+// SQ_SEL_X/Y/Z/W, BUF_NUM_FORMAT_FLOAT, (0 for MUBUF stride[17:14]
+// when ADD_TID_ENABLE and BUF_DATA_FORMAT_32 for MTBUF), ADD_TID_ENABLE
+var S_SAVE_BUF_RSRC_WORD1_STRIDE		= 0x00040000
+var S_SAVE_BUF_RSRC_WORD3_MISC			= 0x10807FAC
+var S_SAVE_SPI_INIT_FIRST_WAVE_MASK		= 0x04000000
+var S_SAVE_SPI_INIT_FIRST_WAVE_SHIFT		= 26
+
+var S_SAVE_PC_HI_FIRST_WAVE_MASK		= 0x80000000
+var S_SAVE_PC_HI_FIRST_WAVE_SHIFT		= 31
+
+var s_sgpr_save_num				= 108
+
+var s_save_spi_init_lo				= exec_lo
+var s_save_spi_init_hi				= exec_hi
+var s_save_pc_lo				= ttmp0
+var s_save_pc_hi				= ttmp1
+var s_save_exec_lo				= ttmp2
+var s_save_exec_hi				= ttmp3
+var s_save_state_priv				= ttmp12
+var s_save_excp_flag_priv			= ttmp15
+var s_save_xnack_mask				= s_save_excp_flag_priv
+var s_wave_size					= ttmp7
+var s_save_buf_rsrc0				= ttmp8
+var s_save_buf_rsrc1				= ttmp9
+var s_save_buf_rsrc2				= ttmp10
+var s_save_buf_rsrc3				= ttmp11
+var s_save_mem_offset				= ttmp4
+var s_save_alloc_size				= s_save_excp_flag_priv
+var s_save_tmp					= ttmp14
+var s_save_m0					= ttmp5
+var s_save_ttmps_lo				= s_save_tmp
+var s_save_ttmps_hi				= s_save_excp_flag_priv
+
+var S_RESTORE_BUF_RSRC_WORD1_STRIDE		= S_SAVE_BUF_RSRC_WORD1_STRIDE
+var S_RESTORE_BUF_RSRC_WORD3_MISC		= S_SAVE_BUF_RSRC_WORD3_MISC
+
+var S_RESTORE_SPI_INIT_FIRST_WAVE_MASK		= 0x04000000
+var S_RESTORE_SPI_INIT_FIRST_WAVE_SHIFT		= 26
+var S_WAVE_SIZE					= 25
+
+var s_restore_spi_init_lo			= exec_lo
+var s_restore_spi_init_hi			= exec_hi
+var s_restore_mem_offset			= ttmp12
+var s_restore_alloc_size			= ttmp3
+var s_restore_tmp				= ttmp2
+var s_restore_mem_offset_save			= s_restore_tmp
+var s_restore_m0				= s_restore_alloc_size
+var s_restore_mode				= ttmp7
+var s_restore_flat_scratch			= s_restore_tmp
+var s_restore_pc_lo				= ttmp0
+var s_restore_pc_hi				= ttmp1
+var s_restore_exec_lo				= ttmp4
+var s_restore_exec_hi				= ttmp5
+var s_restore_state_priv			= ttmp14
+var s_restore_excp_flag_priv			= ttmp15
+var s_restore_xnack_mask			= ttmp13
+var s_restore_buf_rsrc0				= ttmp8
+var s_restore_buf_rsrc1				= ttmp9
+var s_restore_buf_rsrc2				= ttmp10
+var s_restore_buf_rsrc3				= ttmp11
+var s_restore_size				= ttmp6
+var s_restore_ttmps_lo				= s_restore_tmp
+var s_restore_ttmps_hi				= s_restore_alloc_size
+var s_restore_spi_init_hi_save			= s_restore_exec_hi
+
+shader main
+	asic(DEFAULT)
+	type(CS)
+	wave_size(32)
+
+	s_branch	L_SKIP_RESTORE						//NOT restore. might be a regular trap or save
+
+L_JUMP_TO_RESTORE:
+	s_branch	L_RESTORE
+
+L_SKIP_RESTORE:
+	s_getreg_b32	s_save_state_priv, hwreg(HW_REG_WAVE_STATE_PRIV)	//save STATUS since we will change SCC
+
+	// Clear SPI_PRIO: do not save with elevated priority.
+	// Clear ECC_ERR: prevents SQC store and triggers FATAL_HALT if setreg'd.
+	s_andn2_b32	s_save_state_priv, s_save_state_priv, SQ_WAVE_STATE_PRIV_ALWAYS_CLEAR_MASK
+
+	s_getreg_b32	s_save_excp_flag_priv, hwreg(HW_REG_WAVE_EXCP_FLAG_PRIV)
+
+	s_and_b32       ttmp2, s_save_state_priv, SQ_WAVE_STATE_PRIV_HALT_MASK
+	s_cbranch_scc0	L_NOT_HALTED
+
+L_HALTED:
+	// Host trap may occur while wave is halted.
+	s_and_b32	ttmp2, s_save_excp_flag_priv, SQ_WAVE_EXCP_FLAG_PRIV_HOST_TRAP_MASK
+	s_cbranch_scc1	L_FETCH_2ND_TRAP
+
+L_CHECK_SAVE:
+	s_and_b32	ttmp2, s_save_excp_flag_priv, SQ_WAVE_EXCP_FLAG_PRIV_SAVE_CONTEXT_MASK
+	s_cbranch_scc1	L_SAVE
+
+	// Wave is halted but neither host trap nor SAVECTX is raised.
+	// Caused by instruction fetch memory violation.
+	// Spin wait until context saved to prevent interrupt storm.
+	s_sleep		0x10
+	s_getreg_b32	s_save_excp_flag_priv, hwreg(HW_REG_WAVE_EXCP_FLAG_PRIV)
+	s_branch	L_CHECK_SAVE
+
+L_NOT_HALTED:
+	// Let second-level handle non-SAVECTX exception or trap.
+	// Any concurrent SAVECTX will be handled upon re-entry once halted.
+
+	// Check non-maskable exceptions. memory_violation, illegal_instruction
+	// and xnack_error exceptions always cause the wave to enter the trap
+	// handler.
+	s_and_b32	ttmp2, s_save_excp_flag_priv, SQ_WAVE_EXCP_FLAG_PRIV_NON_MASKABLE_EXCP_MASK
+	s_cbranch_scc1	L_FETCH_2ND_TRAP
+
+	// Check for maskable exceptions in trapsts.excp and trapsts.excp_hi.
+	// Maskable exceptions only cause the wave to enter the trap handler if
+	// their respective bit in mode.excp_en is set.
+	s_getreg_b32	ttmp2, hwreg(HW_REG_WAVE_EXCP_FLAG_USER)
+	s_and_b32	ttmp3, s_save_excp_flag_priv, SQ_WAVE_EXCP_FLAG_PRIV_ADDR_WATCH_MASK
+	s_cbranch_scc0	L_NOT_ADDR_WATCH
+	s_or_b32	ttmp2, ttmp2, SQ_WAVE_TRAP_CTRL_ADDR_WATCH_MASK
+
+L_NOT_ADDR_WATCH:
+	s_getreg_b32	ttmp3, hwreg(HW_REG_WAVE_TRAP_CTRL)
+	s_and_b32	ttmp2, ttmp3, ttmp2
+	s_cbranch_scc1	L_FETCH_2ND_TRAP
+
+L_CHECK_TRAP_ID:
+	// Check trap_id != 0
+	s_and_b32	ttmp2, s_save_pc_hi, S_SAVE_PC_HI_TRAP_ID_MASK
+	s_cbranch_scc1	L_FETCH_2ND_TRAP
+
+#if SINGLE_STEP_MISSED_WORKAROUND
+	// Prioritize single step exception over context save.
+	// Second-level trap will halt wave and RFE, re-entering for SAVECTX.
+	// WAVE_TRAP_CTRL is already in ttmp3.
+	s_and_b32	ttmp3, ttmp3, SQ_WAVE_TRAP_CTRL_TRAP_AFTER_INST_MASK
+	s_cbranch_scc1	L_FETCH_2ND_TRAP
+#endif
+
+	s_and_b32	ttmp2, s_save_excp_flag_priv, SQ_WAVE_EXCP_FLAG_PRIV_SAVE_CONTEXT_MASK
+	s_cbranch_scc1	L_SAVE
+
+L_FETCH_2ND_TRAP:
+	// Read second-level TBA/TMA from first-level TMA and jump if available.
+	// ttmp[2:5] and ttmp12 can be used (others hold SPI-initialized debug data)
+	// ttmp12 holds SQ_WAVE_STATUS
+	s_sendmsg_rtn_b64       [ttmp14, ttmp15], sendmsg(MSG_RTN_GET_TMA)
+	s_wait_idle
+	s_lshl_b64	[ttmp14, ttmp15], [ttmp14, ttmp15], 0x8
+
+	s_bitcmp1_b32	ttmp15, 0xF
+	s_cbranch_scc0	L_NO_SIGN_EXTEND_TMA
+	s_or_b32	ttmp15, ttmp15, 0xFFFF0000
+L_NO_SIGN_EXTEND_TMA:
+
+	s_load_dword    ttmp2, [ttmp14, ttmp15], 0x10 scope:SCOPE_SYS		// debug trap enabled flag
+	s_wait_idle
+	s_lshl_b32      ttmp2, ttmp2, TTMP11_DEBUG_TRAP_ENABLED_SHIFT
+	s_andn2_b32     ttmp11, ttmp11, TTMP11_DEBUG_TRAP_ENABLED_MASK
+	s_or_b32        ttmp11, ttmp11, ttmp2
+
+	s_load_dwordx2	[ttmp2, ttmp3], [ttmp14, ttmp15], 0x0 scope:SCOPE_SYS	// second-level TBA
+	s_wait_idle
+	s_load_dwordx2	[ttmp14, ttmp15], [ttmp14, ttmp15], 0x8 scope:SCOPE_SYS	// second-level TMA
+	s_wait_idle
+
+	s_and_b64	[ttmp2, ttmp3], [ttmp2, ttmp3], [ttmp2, ttmp3]
+	s_cbranch_scc0	L_NO_NEXT_TRAP						// second-level trap handler not been set
+	s_setpc_b64	[ttmp2, ttmp3]						// jump to second-level trap handler
+
+L_NO_NEXT_TRAP:
+	// If not caused by trap then halt wave to prevent re-entry.
+	s_and_b32	ttmp2, s_save_pc_hi, S_SAVE_PC_HI_TRAP_ID_MASK
+	s_cbranch_scc1	L_TRAP_CASE
+
+	// Host trap will not cause trap re-entry.
+	s_getreg_b32	ttmp2, hwreg(HW_REG_WAVE_EXCP_FLAG_PRIV)
+	s_and_b32	ttmp2, ttmp2, SQ_WAVE_EXCP_FLAG_PRIV_HOST_TRAP_MASK
+	s_cbranch_scc1	L_EXIT_TRAP
+	s_or_b32	s_save_state_priv, s_save_state_priv, SQ_WAVE_STATE_PRIV_HALT_MASK
+
+	// If the PC points to S_ENDPGM then context save will fail if STATE_PRIV.HALT is set.
+	// Rewind the PC to prevent this from occurring.
+	s_sub_u32	ttmp0, ttmp0, 0x8
+	s_subb_u32	ttmp1, ttmp1, 0x0
+
+	s_branch	L_EXIT_TRAP
+
+L_TRAP_CASE:
+	// Advance past trap instruction to prevent re-entry.
+	s_add_u32	ttmp0, ttmp0, 0x4
+	s_addc_u32	ttmp1, ttmp1, 0x0
+
+L_EXIT_TRAP:
+	s_and_b32	ttmp1, ttmp1, 0xFFFF
+
+	// Restore SQ_WAVE_STATUS.
+	s_and_b64	exec, exec, exec					// Restore STATUS.EXECZ, not writable by s_setreg_b32
+	s_and_b64	vcc, vcc, vcc						// Restore STATUS.VCCZ, not writable by s_setreg_b32
+
+	// STATE_PRIV.BARRIER_COMPLETE may have changed since we read it.
+	// Only restore fields which the trap handler changes.
+	s_lshr_b32	s_save_state_priv, s_save_state_priv, SQ_WAVE_STATE_PRIV_SCC_SHIFT
+	s_setreg_b32	hwreg(HW_REG_WAVE_STATE_PRIV, SQ_WAVE_STATE_PRIV_SCC_SHIFT, \
+		SQ_WAVE_STATE_PRIV_POISON_ERR_SHIFT - SQ_WAVE_STATE_PRIV_SCC_SHIFT + 1), s_save_state_priv
+
+	s_rfe_b64	[ttmp0, ttmp1]
+
+L_SAVE:
+	// If VGPRs have been deallocated then terminate the wavefront.
+	// It has no remaining program to run and cannot save without VGPRs.
+	s_getreg_b32	s_save_tmp, hwreg(HW_REG_WAVE_STATUS)
+	s_bitcmp1_b32	s_save_tmp, SQ_WAVE_STATUS_NO_VGPRS_SHIFT
+	s_cbranch_scc0	L_HAVE_VGPRS
+	s_endpgm
+L_HAVE_VGPRS:
+
+	s_and_b32	s_save_pc_hi, s_save_pc_hi, 0x0000ffff			//pc[47:32]
+	s_mov_b32	s_save_tmp, 0
+	s_setreg_b32	hwreg(HW_REG_WAVE_EXCP_FLAG_PRIV, SQ_WAVE_EXCP_FLAG_PRIV_SAVE_CONTEXT_SHIFT, 1), s_save_tmp	//clear saveCtx bit
+
+	/* inform SPI the readiness and wait for SPI's go signal */
+	s_mov_b32	s_save_exec_lo, exec_lo					//save EXEC and use EXEC for the go signal from SPI
+	s_mov_b32	s_save_exec_hi, exec_hi
+	s_mov_b64	exec, 0x0						//clear EXEC to get ready to receive
+
+	s_sendmsg_rtn_b64       [exec_lo, exec_hi], sendmsg(MSG_RTN_SAVE_WAVE)
+	s_wait_idle
+
+	// Save first_wave flag so we can clear high bits of save address.
+	s_and_b32	s_save_tmp, s_save_spi_init_hi, S_SAVE_SPI_INIT_FIRST_WAVE_MASK
+	s_lshl_b32	s_save_tmp, s_save_tmp, (S_SAVE_PC_HI_FIRST_WAVE_SHIFT - S_SAVE_SPI_INIT_FIRST_WAVE_SHIFT)
+	s_or_b32	s_save_pc_hi, s_save_pc_hi, s_save_tmp
+
+	// Trap temporaries must be saved via VGPR but all VGPRs are in use.
+	// There is no ttmp space to hold the resource constant for VGPR save.
+	// Save v0 by itself since it requires only two SGPRs.
+	s_mov_b32	s_save_ttmps_lo, exec_lo
+	s_and_b32	s_save_ttmps_hi, exec_hi, 0xFFFF
+	s_mov_b32	exec_lo, 0xFFFFFFFF
+	s_mov_b32	exec_hi, 0xFFFFFFFF
+	global_store_dword_addtid	v0, [s_save_ttmps_lo, s_save_ttmps_hi] scope:SCOPE_SYS
+	v_mov_b32	v0, 0x0
+	s_mov_b32	exec_lo, s_save_ttmps_lo
+	s_mov_b32	exec_hi, s_save_ttmps_hi
+
+	// Save trap temporaries 4-11, 13 initialized by SPI debug dispatch logic
+	// ttmp SR memory offset : size(VGPR)+size(SVGPR)+size(SGPR)+0x40
+	get_wave_size2(s_save_ttmps_hi)
+	get_vgpr_size_bytes(s_save_ttmps_lo, s_save_ttmps_hi)
+	get_svgpr_size_bytes(s_save_ttmps_hi)
+	s_add_u32	s_save_ttmps_lo, s_save_ttmps_lo, s_save_ttmps_hi
+	s_and_b32	s_save_ttmps_hi, s_save_spi_init_hi, 0xFFFF
+	s_add_u32	s_save_ttmps_lo, s_save_ttmps_lo, get_sgpr_size_bytes()
+	s_add_u32	s_save_ttmps_lo, s_save_ttmps_lo, s_save_spi_init_lo
+	s_addc_u32	s_save_ttmps_hi, s_save_ttmps_hi, 0x0
+
+	v_writelane_b32	v0, ttmp4, 0x4
+	v_writelane_b32	v0, ttmp5, 0x5
+	v_writelane_b32	v0, ttmp6, 0x6
+	v_writelane_b32	v0, ttmp7, 0x7
+	v_writelane_b32	v0, ttmp8, 0x8
+	v_writelane_b32	v0, ttmp9, 0x9
+	v_writelane_b32	v0, ttmp10, 0xA
+	v_writelane_b32	v0, ttmp11, 0xB
+	v_writelane_b32	v0, ttmp13, 0xD
+	v_writelane_b32	v0, exec_lo, 0xE
+	v_writelane_b32	v0, exec_hi, 0xF
+	valu_sgpr_hazard()
+
+	s_mov_b32	exec_lo, 0x3FFF
+	s_mov_b32	exec_hi, 0x0
+	global_store_dword_addtid	v0, [s_save_ttmps_lo, s_save_ttmps_hi] offset:0x40 scope:SCOPE_SYS
+	v_readlane_b32	ttmp14, v0, 0xE
+	v_readlane_b32	ttmp15, v0, 0xF
+	s_mov_b32	exec_lo, ttmp14
+	s_mov_b32	exec_hi, ttmp15
+
+	/* setup Resource Contants */
+	s_mov_b32	s_save_buf_rsrc0, s_save_spi_init_lo			//base_addr_lo
+	s_and_b32	s_save_buf_rsrc1, s_save_spi_init_hi, 0x0000FFFF	//base_addr_hi
+	s_or_b32	s_save_buf_rsrc1, s_save_buf_rsrc1, S_SAVE_BUF_RSRC_WORD1_STRIDE
+	s_mov_b32	s_save_buf_rsrc2, 0					//NUM_RECORDS initial value = 0 (in bytes) although not neccessarily inited
+	s_mov_b32	s_save_buf_rsrc3, S_SAVE_BUF_RSRC_WORD3_MISC
+
+	s_mov_b32	s_save_m0, m0
+
+	/* global mem offset */
+	s_mov_b32	s_save_mem_offset, 0x0
+	get_wave_size2(s_wave_size)
+
+	/* save first 4 VGPRs, needed for SGPR save */
+	s_mov_b32	exec_lo, 0xFFFFFFFF					//need every thread from now on
+	s_lshr_b32	m0, s_wave_size, S_WAVE_SIZE
+	s_and_b32	m0, m0, 1
+	s_cmp_eq_u32	m0, 1
+	s_cbranch_scc1	L_ENABLE_SAVE_4VGPR_EXEC_HI
+	s_mov_b32	exec_hi, 0x00000000
+	s_branch	L_SAVE_4VGPR_WAVE32
+L_ENABLE_SAVE_4VGPR_EXEC_HI:
+	s_mov_b32	exec_hi, 0xFFFFFFFF
+	s_branch	L_SAVE_4VGPR_WAVE64
+L_SAVE_4VGPR_WAVE32:
+	s_mov_b32	s_save_buf_rsrc2, 0x1000000				//NUM_RECORDS in bytes
+
+	// VGPR Allocated in 4-GPR granularity
+
+	buffer_store_dword	v1, v0, s_save_buf_rsrc0, s_save_mem_offset scope:SCOPE_SYS offset:128
+	buffer_store_dword	v2, v0, s_save_buf_rsrc0, s_save_mem_offset scope:SCOPE_SYS offset:128*2
+	buffer_store_dword	v3, v0, s_save_buf_rsrc0, s_save_mem_offset scope:SCOPE_SYS offset:128*3
+	s_branch	L_SAVE_HWREG
+
+L_SAVE_4VGPR_WAVE64:
+	s_mov_b32	s_save_buf_rsrc2, 0x1000000				//NUM_RECORDS in bytes
+
+	// VGPR Allocated in 4-GPR granularity
+
+	buffer_store_dword	v1, v0, s_save_buf_rsrc0, s_save_mem_offset scope:SCOPE_SYS offset:256
+	buffer_store_dword	v2, v0, s_save_buf_rsrc0, s_save_mem_offset scope:SCOPE_SYS offset:256*2
+	buffer_store_dword	v3, v0, s_save_buf_rsrc0, s_save_mem_offset scope:SCOPE_SYS offset:256*3
+
+	/* save HW registers */
+
+L_SAVE_HWREG:
+	// HWREG SR memory offset : size(VGPR)+size(SVGPR)+size(SGPR)
+	get_vgpr_size_bytes(s_save_mem_offset, s_wave_size)
+	get_svgpr_size_bytes(s_save_tmp)
+	s_add_u32	s_save_mem_offset, s_save_mem_offset, s_save_tmp
+	s_add_u32	s_save_mem_offset, s_save_mem_offset, get_sgpr_size_bytes()
+
+	s_mov_b32	s_save_buf_rsrc2, 0x1000000				//NUM_RECORDS in bytes
+
+	v_mov_b32	v0, 0x0							//Offset[31:0] from buffer resource
+	v_mov_b32	v1, 0x0							//Offset[63:32] from buffer resource
+	v_mov_b32	v2, 0x0							//Set of SGPRs for TCP store
+
+	// Ensure no further changes to barrier or LDS state.
+	// STATE_PRIV.BARRIER_COMPLETE may change up to this point.
+	s_barrier_signal	-2
+	s_barrier_wait	-2
+
+	// Re-read final state of BARRIER_COMPLETE field for save.
+	s_getreg_b32	s_save_tmp, hwreg(HW_REG_WAVE_STATE_PRIV)
+	s_and_b32	s_save_tmp, s_save_tmp, SQ_WAVE_STATE_PRIV_BARRIER_COMPLETE_MASK
+	s_andn2_b32	s_save_state_priv, s_save_state_priv, SQ_WAVE_STATE_PRIV_BARRIER_COMPLETE_MASK
+	s_or_b32	s_save_state_priv, s_save_state_priv, s_save_tmp
+
+	s_andn2_b32	s_save_tmp, s_save_pc_hi, S_SAVE_PC_HI_FIRST_WAVE_MASK
+	v_writelane_b32	v2, s_save_m0, 0x0
+	v_writelane_b32	v2, s_save_pc_lo, 0x1
+	v_writelane_b32	v2, s_save_tmp, 0x2
+	v_writelane_b32	v2, s_save_exec_lo, 0x3
+	v_writelane_b32	v2, s_save_exec_hi, 0x4
+	v_writelane_b32	v2, s_save_state_priv, 0x5
+	v_writelane_b32	v2, s_save_xnack_mask, 0x7
+	valu_sgpr_hazard()
+
+	s_getreg_b32	s_save_tmp, hwreg(HW_REG_WAVE_EXCP_FLAG_PRIV)
+	v_writelane_b32	v2, s_save_tmp, 0x6
+
+	s_getreg_b32	s_save_tmp, hwreg(HW_REG_WAVE_MODE)
+	v_writelane_b32	v2, s_save_tmp, 0x8
+
+	s_getreg_b32	s_save_tmp, hwreg(HW_REG_WAVE_SCRATCH_BASE_LO)
+	v_writelane_b32	v2, s_save_tmp, 0x9
+
+	s_getreg_b32	s_save_tmp, hwreg(HW_REG_WAVE_SCRATCH_BASE_HI)
+	v_writelane_b32	v2, s_save_tmp, 0xA
+
+	s_getreg_b32	s_save_tmp, hwreg(HW_REG_WAVE_EXCP_FLAG_USER)
+	v_writelane_b32	v2, s_save_tmp, 0xB
+
+	s_getreg_b32	s_save_tmp, hwreg(HW_REG_WAVE_TRAP_CTRL)
+	v_writelane_b32	v2, s_save_tmp, 0xC
+
+	s_getreg_b32	s_save_tmp, hwreg(HW_REG_WAVE_STATUS)
+	v_writelane_b32	v2, s_save_tmp, 0xD
+
+	s_get_barrier_state s_save_tmp, -1
+	s_wait_kmcnt (0)
+	v_writelane_b32	v2, s_save_tmp, 0xE
+	valu_sgpr_hazard()
+
+	// Write HWREGs with 16 VGPR lanes. TTMPs occupy space after this.
+	s_mov_b32       exec_lo, 0xFFFF
+	s_mov_b32	exec_hi, 0x0
+	buffer_store_dword	v2, v0, s_save_buf_rsrc0, s_save_mem_offset scope:SCOPE_SYS
+
+	// Write SGPRs with 32 VGPR lanes. This works in wave32 and wave64 mode.
+	s_mov_b32       exec_lo, 0xFFFFFFFF
+
+	/* save SGPRs */
+	// Save SGPR before LDS save, then the s0 to s4 can be used during LDS save...
+
+	// SGPR SR memory offset : size(VGPR)+size(SVGPR)
+	get_vgpr_size_bytes(s_save_mem_offset, s_wave_size)
+	get_svgpr_size_bytes(s_save_tmp)
+	s_add_u32	s_save_mem_offset, s_save_mem_offset, s_save_tmp
+	s_mov_b32	s_save_buf_rsrc2, 0x1000000				//NUM_RECORDS in bytes
+
+	s_mov_b32	ttmp13, 0x0						//next VGPR lane to copy SGPR into
+
+	s_mov_b32	m0, 0x0							//SGPR initial index value =0
+	s_nop		0x0							//Manually inserted wait states
+L_SAVE_SGPR_LOOP:
+	// SGPR is allocated in 16 SGPR granularity
+	s_movrels_b64	s0, s0							//s0 = s[0+m0], s1 = s[1+m0]
+	s_movrels_b64	s2, s2							//s2 = s[2+m0], s3 = s[3+m0]
+	s_movrels_b64	s4, s4							//s4 = s[4+m0], s5 = s[5+m0]
+	s_movrels_b64	s6, s6							//s6 = s[6+m0], s7 = s[7+m0]
+	s_movrels_b64	s8, s8							//s8 = s[8+m0], s9 = s[9+m0]
+	s_movrels_b64	s10, s10						//s10 = s[10+m0], s11 = s[11+m0]
+	s_movrels_b64	s12, s12						//s12 = s[12+m0], s13 = s[13+m0]
+	s_movrels_b64	s14, s14						//s14 = s[14+m0], s15 = s[15+m0]
+
+	s_cmp_eq_u32	ttmp13, 0x0
+	s_cbranch_scc0	L_WRITE_V2_SECOND_HALF
+	write_16sgpr_to_v2(s0, 0x0)
+	s_branch	L_SAVE_SGPR_SKIP_TCP_STORE
+L_WRITE_V2_SECOND_HALF:
+	write_16sgpr_to_v2(s0, 0x10)
+
+	buffer_store_dword	v2, v0, s_save_buf_rsrc0, s_save_mem_offset scope:SCOPE_SYS
+	s_add_u32	s_save_mem_offset, s_save_mem_offset, 0x80
+	s_mov_b32	ttmp13, 0x0
+	v_mov_b32	v2, 0x0
+L_SAVE_SGPR_SKIP_TCP_STORE:
+
+	s_add_u32	m0, m0, 16						//next sgpr index
+	s_cmp_lt_u32	m0, 96							//scc = (m0 < first 96 SGPR) ? 1 : 0
+	s_cbranch_scc1	L_SAVE_SGPR_LOOP					//first 96 SGPR save is complete?
+
+	//save the rest 12 SGPR
+	s_movrels_b64	s0, s0							//s0 = s[0+m0], s1 = s[1+m0]
+	s_movrels_b64	s2, s2							//s2 = s[2+m0], s3 = s[3+m0]
+	s_movrels_b64	s4, s4							//s4 = s[4+m0], s5 = s[5+m0]
+	s_movrels_b64	s6, s6							//s6 = s[6+m0], s7 = s[7+m0]
+	s_movrels_b64	s8, s8							//s8 = s[8+m0], s9 = s[9+m0]
+	s_movrels_b64	s10, s10						//s10 = s[10+m0], s11 = s[11+m0]
+	write_12sgpr_to_v2(s0)
+
+	buffer_store_dword	v2, v0, s_save_buf_rsrc0, s_save_mem_offset scope:SCOPE_SYS
+
+	/* save LDS */
+
+L_SAVE_LDS:
+	// Change EXEC to all threads...
+	s_mov_b32	exec_lo, 0xFFFFFFFF					//need every thread from now on
+	s_lshr_b32	m0, s_wave_size, S_WAVE_SIZE
+	s_and_b32	m0, m0, 1
+	s_cmp_eq_u32	m0, 1
+	s_cbranch_scc1	L_ENABLE_SAVE_LDS_EXEC_HI
+	s_mov_b32	exec_hi, 0x00000000
+	s_branch	L_SAVE_LDS_NORMAL
+L_ENABLE_SAVE_LDS_EXEC_HI:
+	s_mov_b32	exec_hi, 0xFFFFFFFF
+L_SAVE_LDS_NORMAL:
+	s_getreg_b32	s_save_alloc_size, hwreg(HW_REG_WAVE_LDS_ALLOC,SQ_WAVE_LDS_ALLOC_LDS_SIZE_SHIFT,SQ_WAVE_LDS_ALLOC_LDS_SIZE_SIZE)
+	s_and_b32	s_save_alloc_size, s_save_alloc_size, 0xFFFFFFFF	//lds_size is zero?
+	s_cbranch_scc0	L_SAVE_LDS_DONE						//no lds used? jump to L_SAVE_DONE
+
+	s_and_b32	s_save_tmp, s_save_pc_hi, S_SAVE_PC_HI_FIRST_WAVE_MASK
+	s_cbranch_scc0	L_SAVE_LDS_DONE
+
+	// first wave do LDS save;
+
+	s_lshl_b32	s_save_alloc_size, s_save_alloc_size, SQ_WAVE_LDS_ALLOC_GRANULARITY
+	s_mov_b32	s_save_buf_rsrc2, s_save_alloc_size			//NUM_RECORDS in bytes
+
+	// LDS at offset: size(VGPR)+size(SVGPR)+SIZE(SGPR)+SIZE(HWREG)
+	//
+	get_vgpr_size_bytes(s_save_mem_offset, s_wave_size)
+	get_svgpr_size_bytes(s_save_tmp)
+	s_add_u32	s_save_mem_offset, s_save_mem_offset, s_save_tmp
+	s_add_u32	s_save_mem_offset, s_save_mem_offset, get_sgpr_size_bytes()
+	s_add_u32	s_save_mem_offset, s_save_mem_offset, get_hwreg_size_bytes()
+
+	s_mov_b32	s_save_buf_rsrc2, 0x1000000				//NUM_RECORDS in bytes
+
+	//load 0~63*4(byte address) to vgpr v0
+	v_mbcnt_lo_u32_b32	v0, -1, 0
+	v_mbcnt_hi_u32_b32	v0, -1, v0
+	v_mul_u32_u24	v0, 4, v0
+
+	s_lshr_b32	m0, s_wave_size, S_WAVE_SIZE
+	s_and_b32	m0, m0, 1
+	s_cmp_eq_u32	m0, 1
+	s_mov_b32	m0, 0x0
+	s_cbranch_scc1	L_SAVE_LDS_W64
+
+L_SAVE_LDS_W32:
+	s_mov_b32	s3, 128
+	s_nop		0
+	s_nop		0
+	s_nop		0
+L_SAVE_LDS_LOOP_W32:
+	ds_read_b32	v1, v0
+	s_wait_idle
+	buffer_store_dword	v1, v0, s_save_buf_rsrc0, s_save_mem_offset scope:SCOPE_SYS
+
+	s_add_u32	m0, m0, s3						//every buffer_store_lds does 128 bytes
+	s_add_u32	s_save_mem_offset, s_save_mem_offset, s3
+	v_add_nc_u32	v0, v0, 128						//mem offset increased by 128 bytes
+	s_cmp_lt_u32	m0, s_save_alloc_size					//scc=(m0 < s_save_alloc_size) ? 1 : 0
+	s_cbranch_scc1	L_SAVE_LDS_LOOP_W32					//LDS save is complete?
+
+	s_branch	L_SAVE_LDS_DONE
+
+L_SAVE_LDS_W64:
+	s_mov_b32	s3, 256
+	s_nop		0
+	s_nop		0
+	s_nop		0
+L_SAVE_LDS_LOOP_W64:
+	ds_read_b32	v1, v0
+	s_wait_idle
+	buffer_store_dword	v1, v0, s_save_buf_rsrc0, s_save_mem_offset scope:SCOPE_SYS
+
+	s_add_u32	m0, m0, s3						//every buffer_store_lds does 256 bytes
+	s_add_u32	s_save_mem_offset, s_save_mem_offset, s3
+	v_add_nc_u32	v0, v0, 256						//mem offset increased by 256 bytes
+	s_cmp_lt_u32	m0, s_save_alloc_size					//scc=(m0 < s_save_alloc_size) ? 1 : 0
+	s_cbranch_scc1	L_SAVE_LDS_LOOP_W64					//LDS save is complete?
+
+L_SAVE_LDS_DONE:
+	/* save VGPRs  - set the Rest VGPRs */
+L_SAVE_VGPR:
+	// VGPR SR memory offset: 0
+	s_mov_b32	exec_lo, 0xFFFFFFFF					//need every thread from now on
+	s_lshr_b32	m0, s_wave_size, S_WAVE_SIZE
+	s_and_b32	m0, m0, 1
+	s_cmp_eq_u32	m0, 1
+	s_cbranch_scc1	L_ENABLE_SAVE_VGPR_EXEC_HI
+	s_mov_b32	s_save_mem_offset, (0+128*4)				// for the rest VGPRs
+	s_mov_b32	exec_hi, 0x00000000
+	s_branch	L_SAVE_VGPR_NORMAL
+L_ENABLE_SAVE_VGPR_EXEC_HI:
+	s_mov_b32	s_save_mem_offset, (0+256*4)				// for the rest VGPRs
+	s_mov_b32	exec_hi, 0xFFFFFFFF
+L_SAVE_VGPR_NORMAL:
+	s_getreg_b32	s_save_alloc_size, hwreg(HW_REG_WAVE_GPR_ALLOC,SQ_WAVE_GPR_ALLOC_VGPR_SIZE_SHIFT,SQ_WAVE_GPR_ALLOC_VGPR_SIZE_SIZE)
+	s_add_u32	s_save_alloc_size, s_save_alloc_size, 1
+	s_lshl_b32	s_save_alloc_size, s_save_alloc_size, 2			//Number of VGPRs = (vgpr_size + 1) * 4    (non-zero value)
+	//determine it is wave32 or wave64
+	s_lshr_b32	m0, s_wave_size, S_WAVE_SIZE
+	s_and_b32	m0, m0, 1
+	s_cmp_eq_u32	m0, 1
+	s_cbranch_scc1	L_SAVE_VGPR_WAVE64
+
+	s_mov_b32	s_save_buf_rsrc2, 0x1000000				//NUM_RECORDS in bytes
+
+	// VGPR Allocated in 4-GPR granularity
+
+	// VGPR store using dw burst
+	s_mov_b32	m0, 0x4							//VGPR initial index value =4
+	s_cmp_lt_u32	m0, s_save_alloc_size
+	s_cbranch_scc0	L_SAVE_VGPR_END
+
+L_SAVE_VGPR_W32_LOOP:
+	v_movrels_b32	v0, v0							//v0 = v[0+m0]
+	v_movrels_b32	v1, v1							//v1 = v[1+m0]
+	v_movrels_b32	v2, v2							//v2 = v[2+m0]
+	v_movrels_b32	v3, v3							//v3 = v[3+m0]
+
+	buffer_store_dword	v0, v0, s_save_buf_rsrc0, s_save_mem_offset scope:SCOPE_SYS
+	buffer_store_dword	v1, v0, s_save_buf_rsrc0, s_save_mem_offset scope:SCOPE_SYS offset:128
+	buffer_store_dword	v2, v0, s_save_buf_rsrc0, s_save_mem_offset scope:SCOPE_SYS offset:128*2
+	buffer_store_dword	v3, v0, s_save_buf_rsrc0, s_save_mem_offset scope:SCOPE_SYS offset:128*3
+
+	s_add_u32	m0, m0, 4						//next vgpr index
+	s_add_u32	s_save_mem_offset, s_save_mem_offset, 128*4		//every buffer_store_dword does 128 bytes
+	s_cmp_lt_u32	m0, s_save_alloc_size					//scc = (m0 < s_save_alloc_size) ? 1 : 0
+	s_cbranch_scc1	L_SAVE_VGPR_W32_LOOP					//VGPR save is complete?
+
+	s_branch	L_SAVE_VGPR_END
+
+L_SAVE_VGPR_WAVE64:
+	s_mov_b32	s_save_buf_rsrc2, 0x1000000				//NUM_RECORDS in bytes
+
+	// VGPR store using dw burst
+	s_mov_b32	m0, 0x4							//VGPR initial index value =4
+	s_cmp_lt_u32	m0, s_save_alloc_size
+	s_cbranch_scc0	L_SAVE_SHARED_VGPR
+
+L_SAVE_VGPR_W64_LOOP:
+	v_movrels_b32	v0, v0							//v0 = v[0+m0]
+	v_movrels_b32	v1, v1							//v1 = v[1+m0]
+	v_movrels_b32	v2, v2							//v2 = v[2+m0]
+	v_movrels_b32	v3, v3							//v3 = v[3+m0]
+
+	buffer_store_dword	v0, v0, s_save_buf_rsrc0, s_save_mem_offset scope:SCOPE_SYS
+	buffer_store_dword	v1, v0, s_save_buf_rsrc0, s_save_mem_offset scope:SCOPE_SYS offset:256
+	buffer_store_dword	v2, v0, s_save_buf_rsrc0, s_save_mem_offset scope:SCOPE_SYS offset:256*2
+	buffer_store_dword	v3, v0, s_save_buf_rsrc0, s_save_mem_offset scope:SCOPE_SYS offset:256*3
+
+	s_add_u32	m0, m0, 4						//next vgpr index
+	s_add_u32	s_save_mem_offset, s_save_mem_offset, 256*4		//every buffer_store_dword does 256 bytes
+	s_cmp_lt_u32	m0, s_save_alloc_size					//scc = (m0 < s_save_alloc_size) ? 1 : 0
+	s_cbranch_scc1	L_SAVE_VGPR_W64_LOOP					//VGPR save is complete?
+
+L_SAVE_SHARED_VGPR:
+	s_getreg_b32	s_save_alloc_size, hwreg(HW_REG_WAVE_LDS_ALLOC,SQ_WAVE_LDS_ALLOC_VGPR_SHARED_SIZE_SHIFT,SQ_WAVE_LDS_ALLOC_VGPR_SHARED_SIZE_SIZE)
+	s_and_b32	s_save_alloc_size, s_save_alloc_size, 0xFFFFFFFF	//shared_vgpr_size is zero?
+	s_cbranch_scc0	L_SAVE_VGPR_END						//no shared_vgpr used? jump to L_SAVE_LDS
+	s_lshl_b32	s_save_alloc_size, s_save_alloc_size, 3			//Number of SHARED_VGPRs = shared_vgpr_size * 8    (non-zero value)
+	//m0 now has the value of normal vgpr count, just add the m0 with shared_vgpr count to get the total count.
+	//save shared_vgpr will start from the index of m0
+	s_add_u32	s_save_alloc_size, s_save_alloc_size, m0
+	s_mov_b32	exec_lo, 0xFFFFFFFF
+	s_mov_b32	exec_hi, 0x00000000
+
+L_SAVE_SHARED_VGPR_WAVE64_LOOP:
+	v_movrels_b32	v0, v0							//v0 = v[0+m0]
+	buffer_store_dword	v0, v0, s_save_buf_rsrc0, s_save_mem_offset scope:SCOPE_SYS
+	s_add_u32	m0, m0, 1						//next vgpr index
+	s_add_u32	s_save_mem_offset, s_save_mem_offset, 128
+	s_cmp_lt_u32	m0, s_save_alloc_size					//scc = (m0 < s_save_alloc_size) ? 1 : 0
+	s_cbranch_scc1	L_SAVE_SHARED_VGPR_WAVE64_LOOP				//SHARED_VGPR save is complete?
+
+L_SAVE_VGPR_END:
+	s_branch	L_END_PGM
+
+L_RESTORE:
+	/* Setup Resource Contants */
+	s_mov_b32	s_restore_buf_rsrc0, s_restore_spi_init_lo		//base_addr_lo
+	s_and_b32	s_restore_buf_rsrc1, s_restore_spi_init_hi, 0x0000FFFF	//base_addr_hi
+	s_or_b32	s_restore_buf_rsrc1, s_restore_buf_rsrc1, S_RESTORE_BUF_RSRC_WORD1_STRIDE
+	s_mov_b32	s_restore_buf_rsrc2, 0					//NUM_RECORDS initial value = 0 (in bytes)
+	s_mov_b32	s_restore_buf_rsrc3, S_RESTORE_BUF_RSRC_WORD3_MISC
+
+	// Save s_restore_spi_init_hi for later use.
+	s_mov_b32 s_restore_spi_init_hi_save, s_restore_spi_init_hi
+
+	//determine it is wave32 or wave64
+	get_wave_size2(s_restore_size)
+
+	s_and_b32	s_restore_tmp, s_restore_spi_init_hi, S_RESTORE_SPI_INIT_FIRST_WAVE_MASK
+	s_cbranch_scc0	L_RESTORE_VGPR
+
+	/* restore LDS */
+L_RESTORE_LDS:
+	s_mov_b32	exec_lo, 0xFFFFFFFF					//need every thread from now on
+	s_lshr_b32	m0, s_restore_size, S_WAVE_SIZE
+	s_and_b32	m0, m0, 1
+	s_cmp_eq_u32	m0, 1
+	s_cbranch_scc1	L_ENABLE_RESTORE_LDS_EXEC_HI
+	s_mov_b32	exec_hi, 0x00000000
+	s_branch	L_RESTORE_LDS_NORMAL
+L_ENABLE_RESTORE_LDS_EXEC_HI:
+	s_mov_b32	exec_hi, 0xFFFFFFFF
+L_RESTORE_LDS_NORMAL:
+	s_getreg_b32	s_restore_alloc_size, hwreg(HW_REG_WAVE_LDS_ALLOC,SQ_WAVE_LDS_ALLOC_LDS_SIZE_SHIFT,SQ_WAVE_LDS_ALLOC_LDS_SIZE_SIZE)
+	s_and_b32	s_restore_alloc_size, s_restore_alloc_size, 0xFFFFFFFF	//lds_size is zero?
+	s_cbranch_scc0	L_RESTORE_VGPR						//no lds used? jump to L_RESTORE_VGPR
+	s_lshl_b32	s_restore_alloc_size, s_restore_alloc_size, SQ_WAVE_LDS_ALLOC_GRANULARITY
+	s_mov_b32	s_restore_buf_rsrc2, s_restore_alloc_size		//NUM_RECORDS in bytes
+
+	// LDS at offset: size(VGPR)+size(SVGPR)+SIZE(SGPR)+SIZE(HWREG)
+	//
+	get_vgpr_size_bytes(s_restore_mem_offset, s_restore_size)
+	get_svgpr_size_bytes(s_restore_tmp)
+	s_add_u32	s_restore_mem_offset, s_restore_mem_offset, s_restore_tmp
+	s_add_u32	s_restore_mem_offset, s_restore_mem_offset, get_sgpr_size_bytes()
+	s_add_u32	s_restore_mem_offset, s_restore_mem_offset, get_hwreg_size_bytes()
+
+	s_mov_b32	s_restore_buf_rsrc2, 0x1000000				//NUM_RECORDS in bytes
+
+	s_lshr_b32	m0, s_restore_size, S_WAVE_SIZE
+	s_and_b32	m0, m0, 1
+	s_cmp_eq_u32	m0, 1
+	s_mov_b32	m0, 0x0
+	s_cbranch_scc1	L_RESTORE_LDS_LOOP_W64
+
+L_RESTORE_LDS_LOOP_W32:
+	buffer_load_dword       v0, v0, s_restore_buf_rsrc0, s_restore_mem_offset
+	s_wait_idle
+	ds_store_addtid_b32     v0
+	s_add_u32	m0, m0, 128						// 128 DW
+	s_add_u32	s_restore_mem_offset, s_restore_mem_offset, 128		//mem offset increased by 128DW
+	s_cmp_lt_u32	m0, s_restore_alloc_size				//scc=(m0 < s_restore_alloc_size) ? 1 : 0
+	s_cbranch_scc1	L_RESTORE_LDS_LOOP_W32					//LDS restore is complete?
+	s_branch	L_RESTORE_VGPR
+
+L_RESTORE_LDS_LOOP_W64:
+	buffer_load_dword       v0, v0, s_restore_buf_rsrc0, s_restore_mem_offset
+	s_wait_idle
+	ds_store_addtid_b32     v0
+	s_add_u32	m0, m0, 256						// 256 DW
+	s_add_u32	s_restore_mem_offset, s_restore_mem_offset, 256		//mem offset increased by 256DW
+	s_cmp_lt_u32	m0, s_restore_alloc_size				//scc=(m0 < s_restore_alloc_size) ? 1 : 0
+	s_cbranch_scc1	L_RESTORE_LDS_LOOP_W64					//LDS restore is complete?
+
+	/* restore VGPRs */
+L_RESTORE_VGPR:
+	// VGPR SR memory offset : 0
+	s_mov_b32	s_restore_mem_offset, 0x0
+	s_mov_b32	exec_lo, 0xFFFFFFFF					//need every thread from now on
+	s_lshr_b32	m0, s_restore_size, S_WAVE_SIZE
+	s_and_b32	m0, m0, 1
+	s_cmp_eq_u32	m0, 1
+	s_cbranch_scc1	L_ENABLE_RESTORE_VGPR_EXEC_HI
+	s_mov_b32	exec_hi, 0x00000000
+	s_branch	L_RESTORE_VGPR_NORMAL
+L_ENABLE_RESTORE_VGPR_EXEC_HI:
+	s_mov_b32	exec_hi, 0xFFFFFFFF
+L_RESTORE_VGPR_NORMAL:
+	s_getreg_b32	s_restore_alloc_size, hwreg(HW_REG_WAVE_GPR_ALLOC,SQ_WAVE_GPR_ALLOC_VGPR_SIZE_SHIFT,SQ_WAVE_GPR_ALLOC_VGPR_SIZE_SIZE)
+	s_add_u32	s_restore_alloc_size, s_restore_alloc_size, 1
+	s_lshl_b32	s_restore_alloc_size, s_restore_alloc_size, 2		//Number of VGPRs = (vgpr_size + 1) * 4    (non-zero value)
+	//determine it is wave32 or wave64
+	s_lshr_b32	m0, s_restore_size, S_WAVE_SIZE
+	s_and_b32	m0, m0, 1
+	s_cmp_eq_u32	m0, 1
+	s_cbranch_scc1	L_RESTORE_VGPR_WAVE64
+
+	s_mov_b32	s_restore_buf_rsrc2, 0x1000000				//NUM_RECORDS in bytes
+
+	// VGPR load using dw burst
+	s_mov_b32	s_restore_mem_offset_save, s_restore_mem_offset		// restore start with v1, v0 will be the last
+	s_add_u32	s_restore_mem_offset, s_restore_mem_offset, 128*4
+	s_mov_b32	m0, 4							//VGPR initial index value = 4
+	s_cmp_lt_u32	m0, s_restore_alloc_size
+	s_cbranch_scc0	L_RESTORE_SGPR
+
+L_RESTORE_VGPR_WAVE32_LOOP:
+	buffer_load_dword	v0, v0, s_restore_buf_rsrc0, s_restore_mem_offset scope:SCOPE_SYS
+	buffer_load_dword	v1, v0, s_restore_buf_rsrc0, s_restore_mem_offset scope:SCOPE_SYS offset:128
+	buffer_load_dword	v2, v0, s_restore_buf_rsrc0, s_restore_mem_offset scope:SCOPE_SYS offset:128*2
+	buffer_load_dword	v3, v0, s_restore_buf_rsrc0, s_restore_mem_offset scope:SCOPE_SYS offset:128*3
+	s_wait_idle
+	v_movreld_b32	v0, v0							//v[0+m0] = v0
+	v_movreld_b32	v1, v1
+	v_movreld_b32	v2, v2
+	v_movreld_b32	v3, v3
+	s_add_u32	m0, m0, 4						//next vgpr index
+	s_add_u32	s_restore_mem_offset, s_restore_mem_offset, 128*4	//every buffer_load_dword does 128 bytes
+	s_cmp_lt_u32	m0, s_restore_alloc_size				//scc = (m0 < s_restore_alloc_size) ? 1 : 0
+	s_cbranch_scc1	L_RESTORE_VGPR_WAVE32_LOOP				//VGPR restore (except v0) is complete?
+
+	/* VGPR restore on v0 */
+	buffer_load_dword	v0, v0, s_restore_buf_rsrc0, s_restore_mem_offset_save scope:SCOPE_SYS
+	buffer_load_dword	v1, v0, s_restore_buf_rsrc0, s_restore_mem_offset_save scope:SCOPE_SYS offset:128
+	buffer_load_dword	v2, v0, s_restore_buf_rsrc0, s_restore_mem_offset_save scope:SCOPE_SYS offset:128*2
+	buffer_load_dword	v3, v0, s_restore_buf_rsrc0, s_restore_mem_offset_save scope:SCOPE_SYS offset:128*3
+	s_wait_idle
+
+	s_branch	L_RESTORE_SGPR
+
+L_RESTORE_VGPR_WAVE64:
+	s_mov_b32	s_restore_buf_rsrc2, 0x1000000				//NUM_RECORDS in bytes
+
+	// VGPR load using dw burst
+	s_mov_b32	s_restore_mem_offset_save, s_restore_mem_offset		// restore start with v4, v0 will be the last
+	s_add_u32	s_restore_mem_offset, s_restore_mem_offset, 256*4
+	s_mov_b32	m0, 4							//VGPR initial index value = 4
+	s_cmp_lt_u32	m0, s_restore_alloc_size
+	s_cbranch_scc0	L_RESTORE_SHARED_VGPR
+
+L_RESTORE_VGPR_WAVE64_LOOP:
+	buffer_load_dword	v0, v0, s_restore_buf_rsrc0, s_restore_mem_offset scope:SCOPE_SYS
+	buffer_load_dword	v1, v0, s_restore_buf_rsrc0, s_restore_mem_offset scope:SCOPE_SYS offset:256
+	buffer_load_dword	v2, v0, s_restore_buf_rsrc0, s_restore_mem_offset scope:SCOPE_SYS offset:256*2
+	buffer_load_dword	v3, v0, s_restore_buf_rsrc0, s_restore_mem_offset scope:SCOPE_SYS offset:256*3
+	s_wait_idle
+	v_movreld_b32	v0, v0							//v[0+m0] = v0
+	v_movreld_b32	v1, v1
+	v_movreld_b32	v2, v2
+	v_movreld_b32	v3, v3
+	s_add_u32	m0, m0, 4						//next vgpr index
+	s_add_u32	s_restore_mem_offset, s_restore_mem_offset, 256*4	//every buffer_load_dword does 256 bytes
+	s_cmp_lt_u32	m0, s_restore_alloc_size				//scc = (m0 < s_restore_alloc_size) ? 1 : 0
+	s_cbranch_scc1	L_RESTORE_VGPR_WAVE64_LOOP				//VGPR restore (except v0) is complete?
+
+L_RESTORE_SHARED_VGPR:
+	s_getreg_b32	s_restore_alloc_size, hwreg(HW_REG_WAVE_LDS_ALLOC,SQ_WAVE_LDS_ALLOC_VGPR_SHARED_SIZE_SHIFT,SQ_WAVE_LDS_ALLOC_VGPR_SHARED_SIZE_SIZE)	//shared_vgpr_size
+	s_and_b32	s_restore_alloc_size, s_restore_alloc_size, 0xFFFFFFFF	//shared_vgpr_size is zero?
+	s_cbranch_scc0	L_RESTORE_V0						//no shared_vgpr used?
+	s_lshl_b32	s_restore_alloc_size, s_restore_alloc_size, 3		//Number of SHARED_VGPRs = shared_vgpr_size * 8    (non-zero value)
+	//m0 now has the value of normal vgpr count, just add the m0 with shared_vgpr count to get the total count.
+	//restore shared_vgpr will start from the index of m0
+	s_add_u32	s_restore_alloc_size, s_restore_alloc_size, m0
+	s_mov_b32	exec_lo, 0xFFFFFFFF
+	s_mov_b32	exec_hi, 0x00000000
+L_RESTORE_SHARED_VGPR_WAVE64_LOOP:
+	buffer_load_dword	v0, v0, s_restore_buf_rsrc0, s_restore_mem_offset scope:SCOPE_SYS
+	s_wait_idle
+	v_movreld_b32	v0, v0							//v[0+m0] = v0
+	s_add_u32	m0, m0, 1						//next vgpr index
+	s_add_u32	s_restore_mem_offset, s_restore_mem_offset, 128
+	s_cmp_lt_u32	m0, s_restore_alloc_size				//scc = (m0 < s_restore_alloc_size) ? 1 : 0
+	s_cbranch_scc1	L_RESTORE_SHARED_VGPR_WAVE64_LOOP			//VGPR restore (except v0) is complete?
+
+	s_mov_b32	exec_hi, 0xFFFFFFFF					//restore back exec_hi before restoring V0!!
+
+	/* VGPR restore on v0 */
+L_RESTORE_V0:
+	buffer_load_dword	v0, v0, s_restore_buf_rsrc0, s_restore_mem_offset_save scope:SCOPE_SYS
+	buffer_load_dword	v1, v0, s_restore_buf_rsrc0, s_restore_mem_offset_save scope:SCOPE_SYS offset:256
+	buffer_load_dword	v2, v0, s_restore_buf_rsrc0, s_restore_mem_offset_save scope:SCOPE_SYS offset:256*2
+	buffer_load_dword	v3, v0, s_restore_buf_rsrc0, s_restore_mem_offset_save scope:SCOPE_SYS offset:256*3
+	s_wait_idle
+
+	/* restore SGPRs */
+	//will be 2+8+16*6
+	// SGPR SR memory offset : size(VGPR)+size(SVGPR)
+L_RESTORE_SGPR:
+	get_vgpr_size_bytes(s_restore_mem_offset, s_restore_size)
+	get_svgpr_size_bytes(s_restore_tmp)
+	s_add_u32	s_restore_mem_offset, s_restore_mem_offset, s_restore_tmp
+	s_add_u32	s_restore_mem_offset, s_restore_mem_offset, get_sgpr_size_bytes()
+	s_sub_u32	s_restore_mem_offset, s_restore_mem_offset, 20*4	//s108~s127 is not saved
+
+	s_mov_b32	s_restore_buf_rsrc2, 0x1000000				//NUM_RECORDS in bytes
+
+	s_mov_b32	m0, s_sgpr_save_num
+
+	read_4sgpr_from_mem(s0, s_restore_buf_rsrc0, s_restore_mem_offset)
+	s_wait_idle
+
+	s_sub_u32	m0, m0, 4						// Restore from S[0] to S[104]
+	s_nop		0							// hazard SALU M0=> S_MOVREL
+
+	s_movreld_b64	s0, s0							//s[0+m0] = s0
+	s_movreld_b64	s2, s2
+
+	read_8sgpr_from_mem(s0, s_restore_buf_rsrc0, s_restore_mem_offset)
+	s_wait_idle
+
+	s_sub_u32	m0, m0, 8						// Restore from S[0] to S[96]
+	s_nop		0							// hazard SALU M0=> S_MOVREL
+
+	s_movreld_b64	s0, s0							//s[0+m0] = s0
+	s_movreld_b64	s2, s2
+	s_movreld_b64	s4, s4
+	s_movreld_b64	s6, s6
+
+ L_RESTORE_SGPR_LOOP:
+	read_16sgpr_from_mem(s0, s_restore_buf_rsrc0, s_restore_mem_offset)
+	s_wait_idle
+
+	s_sub_u32	m0, m0, 16						// Restore from S[n] to S[0]
+	s_nop		0							// hazard SALU M0=> S_MOVREL
+
+	s_movreld_b64	s0, s0							//s[0+m0] = s0
+	s_movreld_b64	s2, s2
+	s_movreld_b64	s4, s4
+	s_movreld_b64	s6, s6
+	s_movreld_b64	s8, s8
+	s_movreld_b64	s10, s10
+	s_movreld_b64	s12, s12
+	s_movreld_b64	s14, s14
+
+	s_cmp_eq_u32	m0, 0							//scc = (m0 < s_sgpr_save_num) ? 1 : 0
+	s_cbranch_scc0	L_RESTORE_SGPR_LOOP
+
+	// s_barrier with STATE_PRIV.TRAP_AFTER_INST=1, STATUS.PRIV=1 incorrectly asserts debug exception.
+	// Clear DEBUG_EN before and restore MODE after the barrier.
+	s_setreg_imm32_b32	hwreg(HW_REG_WAVE_MODE), 0
+
+	/* restore HW registers */
+L_RESTORE_HWREG:
+	// HWREG SR memory offset : size(VGPR)+size(SVGPR)+size(SGPR)
+	get_vgpr_size_bytes(s_restore_mem_offset, s_restore_size)
+	get_svgpr_size_bytes(s_restore_tmp)
+	s_add_u32	s_restore_mem_offset, s_restore_mem_offset, s_restore_tmp
+	s_add_u32	s_restore_mem_offset, s_restore_mem_offset, get_sgpr_size_bytes()
+
+	s_mov_b32	s_restore_buf_rsrc2, 0x1000000				//NUM_RECORDS in bytes
+
+	// Restore s_restore_spi_init_hi before the saved value gets clobbered.
+	s_mov_b32 s_restore_spi_init_hi, s_restore_spi_init_hi_save
+
+	read_hwreg_from_mem(s_restore_m0, s_restore_buf_rsrc0, s_restore_mem_offset)
+	read_hwreg_from_mem(s_restore_pc_lo, s_restore_buf_rsrc0, s_restore_mem_offset)
+	read_hwreg_from_mem(s_restore_pc_hi, s_restore_buf_rsrc0, s_restore_mem_offset)
+	read_hwreg_from_mem(s_restore_exec_lo, s_restore_buf_rsrc0, s_restore_mem_offset)
+	read_hwreg_from_mem(s_restore_exec_hi, s_restore_buf_rsrc0, s_restore_mem_offset)
+	read_hwreg_from_mem(s_restore_state_priv, s_restore_buf_rsrc0, s_restore_mem_offset)
+	read_hwreg_from_mem(s_restore_excp_flag_priv, s_restore_buf_rsrc0, s_restore_mem_offset)
+	read_hwreg_from_mem(s_restore_xnack_mask, s_restore_buf_rsrc0, s_restore_mem_offset)
+	read_hwreg_from_mem(s_restore_mode, s_restore_buf_rsrc0, s_restore_mem_offset)
+	read_hwreg_from_mem(s_restore_flat_scratch, s_restore_buf_rsrc0, s_restore_mem_offset)
+	s_wait_idle
+
+	s_setreg_b32	hwreg(HW_REG_WAVE_SCRATCH_BASE_LO), s_restore_flat_scratch
+
+	read_hwreg_from_mem(s_restore_flat_scratch, s_restore_buf_rsrc0, s_restore_mem_offset)
+	s_wait_idle
+
+	s_setreg_b32	hwreg(HW_REG_WAVE_SCRATCH_BASE_HI), s_restore_flat_scratch
+
+	read_hwreg_from_mem(s_restore_tmp, s_restore_buf_rsrc0, s_restore_mem_offset)
+	s_wait_idle
+	s_setreg_b32	hwreg(HW_REG_WAVE_EXCP_FLAG_USER), s_restore_tmp
+
+	read_hwreg_from_mem(s_restore_tmp, s_restore_buf_rsrc0, s_restore_mem_offset)
+	s_wait_idle
+	s_setreg_b32	hwreg(HW_REG_WAVE_TRAP_CTRL), s_restore_tmp
+
+	// Only the first wave needs to restore the workgroup barrier.
+	s_and_b32	s_restore_tmp, s_restore_spi_init_hi, S_RESTORE_SPI_INIT_FIRST_WAVE_MASK
+	s_cbranch_scc0	L_SKIP_BARRIER_RESTORE
+
+	// Skip over WAVE_STATUS, since there is no state to restore from it
+	s_add_u32	s_restore_mem_offset, s_restore_mem_offset, 4
+
+	read_hwreg_from_mem(s_restore_tmp, s_restore_buf_rsrc0, s_restore_mem_offset)
+	s_wait_idle
+
+	s_bitcmp1_b32	s_restore_tmp, BARRIER_STATE_VALID_OFFSET
+	s_cbranch_scc0	L_SKIP_BARRIER_RESTORE
+
+	// extract the saved signal count from s_restore_tmp
+	s_lshr_b32	s_restore_tmp, s_restore_tmp, BARRIER_STATE_SIGNAL_OFFSET
+
+	// We need to call s_barrier_signal repeatedly to restore the signal
+	// count of the work group barrier.  The member count is already
+	// initialized with the number of waves in the work group.
+L_BARRIER_RESTORE_LOOP:
+	s_and_b32	s_restore_tmp, s_restore_tmp, s_restore_tmp
+	s_cbranch_scc0	L_SKIP_BARRIER_RESTORE
+	s_barrier_signal	-1
+	s_add_i32	s_restore_tmp, s_restore_tmp, -1
+	s_branch	L_BARRIER_RESTORE_LOOP
+
+L_SKIP_BARRIER_RESTORE:
+
+	s_mov_b32	m0, s_restore_m0
+	s_mov_b32	exec_lo, s_restore_exec_lo
+	s_mov_b32	exec_hi, s_restore_exec_hi
+
+	// EXCP_FLAG_PRIV.SAVE_CONTEXT and HOST_TRAP may have changed.
+	// Only restore the other fields to avoid clobbering them.
+	s_setreg_b32	hwreg(HW_REG_WAVE_EXCP_FLAG_PRIV, 0, SQ_WAVE_EXCP_FLAG_PRIV_RESTORE_PART_1_SIZE), s_restore_excp_flag_priv
+	s_lshr_b32	s_restore_excp_flag_priv, s_restore_excp_flag_priv, SQ_WAVE_EXCP_FLAG_PRIV_RESTORE_PART_2_SHIFT
+	s_setreg_b32	hwreg(HW_REG_WAVE_EXCP_FLAG_PRIV, SQ_WAVE_EXCP_FLAG_PRIV_RESTORE_PART_2_SHIFT, SQ_WAVE_EXCP_FLAG_PRIV_RESTORE_PART_2_SIZE), s_restore_excp_flag_priv
+	s_lshr_b32	s_restore_excp_flag_priv, s_restore_excp_flag_priv, SQ_WAVE_EXCP_FLAG_PRIV_RESTORE_PART_3_SHIFT - SQ_WAVE_EXCP_FLAG_PRIV_RESTORE_PART_2_SHIFT
+	s_setreg_b32	hwreg(HW_REG_WAVE_EXCP_FLAG_PRIV, SQ_WAVE_EXCP_FLAG_PRIV_RESTORE_PART_3_SHIFT, SQ_WAVE_EXCP_FLAG_PRIV_RESTORE_PART_3_SIZE), s_restore_excp_flag_priv
+
+	s_setreg_b32	hwreg(HW_REG_WAVE_MODE), s_restore_mode
+
+	// Restore trap temporaries 4-11, 13 initialized by SPI debug dispatch logic
+	// ttmp SR memory offset : size(VGPR)+size(SVGPR)+size(SGPR)+0x40
+	get_vgpr_size_bytes(s_restore_ttmps_lo, s_restore_size)
+	get_svgpr_size_bytes(s_restore_ttmps_hi)
+	s_add_u32	s_restore_ttmps_lo, s_restore_ttmps_lo, s_restore_ttmps_hi
+	s_add_u32	s_restore_ttmps_lo, s_restore_ttmps_lo, get_sgpr_size_bytes()
+	s_add_u32	s_restore_ttmps_lo, s_restore_ttmps_lo, s_restore_buf_rsrc0
+	s_addc_u32	s_restore_ttmps_hi, s_restore_buf_rsrc1, 0x0
+	s_and_b32	s_restore_ttmps_hi, s_restore_ttmps_hi, 0xFFFF
+	s_load_dwordx4	[ttmp4, ttmp5, ttmp6, ttmp7], [s_restore_ttmps_lo, s_restore_ttmps_hi], 0x50 scope:SCOPE_SYS
+	s_load_dwordx4	[ttmp8, ttmp9, ttmp10, ttmp11], [s_restore_ttmps_lo, s_restore_ttmps_hi], 0x60 scope:SCOPE_SYS
+	s_load_dword	ttmp13, [s_restore_ttmps_lo, s_restore_ttmps_hi], 0x74 scope:SCOPE_SYS
+	s_wait_idle
+
+	s_and_b32	s_restore_pc_hi, s_restore_pc_hi, 0x0000ffff		//pc[47:32] //Do it here in order not to affect STATUS
+	s_and_b64	exec, exec, exec					// Restore STATUS.EXECZ, not writable by s_setreg_b32
+	s_and_b64	vcc, vcc, vcc						// Restore STATUS.VCCZ, not writable by s_setreg_b32
+
+	s_setreg_b32	hwreg(HW_REG_WAVE_STATE_PRIV), s_restore_state_priv	// SCC is included, which is changed by previous salu
+
+	// Make barrier and LDS state visible to all waves in the group.
+	// STATE_PRIV.BARRIER_COMPLETE may change after this point.
+	s_barrier_signal	-2
+	s_barrier_wait	-2
+
+	s_rfe_b64	s_restore_pc_lo						//Return to the main shader program and resume execution
+
+L_END_PGM:
+	// Make sure that no wave of the workgroup can exit the trap handler
+	// before the workgroup barrier state is saved.
+	s_barrier_signal	-2
+	s_barrier_wait	-2
+	s_endpgm_saved
+end
+
+function write_16sgpr_to_v2(s, lane_offset)
+	// Copy into VGPR for later TCP store.
+	for var sgpr_idx = 0; sgpr_idx < 16; sgpr_idx ++
+		v_writelane_b32	v2, s[sgpr_idx], sgpr_idx + lane_offset
+	end
+	valu_sgpr_hazard()
+	s_add_u32	ttmp13, ttmp13, 0x10
+end
+
+function write_12sgpr_to_v2(s)
+	// Copy into VGPR for later TCP store.
+	for var sgpr_idx = 0; sgpr_idx < 12; sgpr_idx ++
+		v_writelane_b32	v2, s[sgpr_idx], sgpr_idx
+	end
+	valu_sgpr_hazard()
+end
+
+function read_hwreg_from_mem(s, s_rsrc, s_mem_offset)
+	s_buffer_load_dword	s, s_rsrc, s_mem_offset scope:SCOPE_SYS
+	s_add_u32	s_mem_offset, s_mem_offset, 4
+end
+
+function read_16sgpr_from_mem(s, s_rsrc, s_mem_offset)
+	s_sub_u32	s_mem_offset, s_mem_offset, 4*16
+	s_buffer_load_dwordx16	s, s_rsrc, s_mem_offset scope:SCOPE_SYS
+end
+
+function read_8sgpr_from_mem(s, s_rsrc, s_mem_offset)
+	s_sub_u32	s_mem_offset, s_mem_offset, 4*8
+	s_buffer_load_dwordx8	s, s_rsrc, s_mem_offset scope:SCOPE_SYS
+end
+
+function read_4sgpr_from_mem(s, s_rsrc, s_mem_offset)
+	s_sub_u32	s_mem_offset, s_mem_offset, 4*4
+	s_buffer_load_dwordx4	s, s_rsrc, s_mem_offset scope:SCOPE_SYS
+end
+
+function get_vgpr_size_bytes(s_vgpr_size_byte, s_size)
+	s_getreg_b32	s_vgpr_size_byte, hwreg(HW_REG_WAVE_GPR_ALLOC,SQ_WAVE_GPR_ALLOC_VGPR_SIZE_SHIFT,SQ_WAVE_GPR_ALLOC_VGPR_SIZE_SIZE)
+	s_add_u32	s_vgpr_size_byte, s_vgpr_size_byte, 1
+	s_bitcmp1_b32	s_size, S_WAVE_SIZE
+	s_cbranch_scc1	L_ENABLE_SHIFT_W64
+	s_lshl_b32	s_vgpr_size_byte, s_vgpr_size_byte, (2+7)		//Number of VGPRs = (vgpr_size + 1) * 4 * 32 * 4   (non-zero value)
+	s_branch	L_SHIFT_DONE
+L_ENABLE_SHIFT_W64:
+	s_lshl_b32	s_vgpr_size_byte, s_vgpr_size_byte, (2+8)		//Number of VGPRs = (vgpr_size + 1) * 4 * 64 * 4   (non-zero value)
+L_SHIFT_DONE:
+end
+
+function get_svgpr_size_bytes(s_svgpr_size_byte)
+	s_getreg_b32	s_svgpr_size_byte, hwreg(HW_REG_WAVE_LDS_ALLOC,SQ_WAVE_LDS_ALLOC_VGPR_SHARED_SIZE_SHIFT,SQ_WAVE_LDS_ALLOC_VGPR_SHARED_SIZE_SIZE)
+	s_lshl_b32	s_svgpr_size_byte, s_svgpr_size_byte, (3+7)
+end
+
+function get_sgpr_size_bytes
+	return 512
+end
+
+function get_hwreg_size_bytes
+	return 128
+end
+
+function get_wave_size2(s_reg)
+	s_getreg_b32	s_reg, hwreg(HW_REG_WAVE_STATUS,SQ_WAVE_STATUS_WAVE64_SHIFT,SQ_WAVE_STATUS_WAVE64_SIZE)
+	s_lshl_b32	s_reg, s_reg, S_WAVE_SIZE
+end
+
+function valu_sgpr_hazard
+#if HAVE_VALU_SGPR_HAZARD
+	for var rep = 0; rep < 8; rep ++
+		ds_nop
+	end
+#endif
+end
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index 3e6b4736a7fe..67b5f3d7ff8e 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -212,6 +212,11 @@ static int set_queue_properties_from_user(struct queue_properties *q_properties,
 		return -EINVAL;
 	}
 
+	if (args->ring_size < KFD_MIN_QUEUE_RING_SIZE) {
+		args->ring_size = KFD_MIN_QUEUE_RING_SIZE;
+		pr_debug("Size lower. clamped to KFD_MIN_QUEUE_RING_SIZE");
+	}
+
 	if (!access_ok((const void __user *) args->read_pointer_address,
 			sizeof(uint32_t))) {
 		pr_err("Can't access read pointer\n");
@@ -461,6 +466,11 @@ static int kfd_ioctl_update_queue(struct file *filp, struct kfd_process *p,
 		return -EINVAL;
 	}
 
+	if (args->ring_size < KFD_MIN_QUEUE_RING_SIZE) {
+		args->ring_size = KFD_MIN_QUEUE_RING_SIZE;
+		pr_debug("Size lower. clamped to KFD_MIN_QUEUE_RING_SIZE");
+	}
+
 	properties.queue_address = args->ring_base_address;
 	properties.queue_size = args->ring_size;
 	properties.queue_percent = args->queue_percentage & 0xFF;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index b05be24531e1..07eadab4c1c4 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -537,7 +537,8 @@ static void kfd_cwsr_init(struct kfd_dev *kfd)
 			kfd->cwsr_isa = cwsr_trap_gfx11_hex;
 			kfd->cwsr_isa_size = sizeof(cwsr_trap_gfx11_hex);
 		} else {
-			BUILD_BUG_ON(sizeof(cwsr_trap_gfx12_hex) > PAGE_SIZE);
+			BUILD_BUG_ON(sizeof(cwsr_trap_gfx12_hex)
+					     > KFD_CWSR_TMA_OFFSET);
 			kfd->cwsr_isa = cwsr_trap_gfx12_hex;
 			kfd->cwsr_isa_size = sizeof(cwsr_trap_gfx12_hex);
 		}
@@ -637,6 +638,14 @@ static void kfd_cleanup_nodes(struct kfd_dev *kfd, unsigned int num_nodes)
 	struct kfd_node *knode;
 	unsigned int i;
 
+	/*
+	 * flush_work ensures that there are no outstanding
+	 * work-queue items that will access interrupt_ring. New work items
+	 * can't be created because we stopped interrupt handling above.
+	 */
+	flush_workqueue(kfd->ih_wq);
+	destroy_workqueue(kfd->ih_wq);
+
 	for (i = 0; i < num_nodes; i++) {
 		knode = kfd->nodes[i];
 		device_queue_manager_uninit(knode->dqm);
@@ -1058,21 +1067,6 @@ static int kfd_resume(struct kfd_node *node)
 	return err;
 }
 
-static inline void kfd_queue_work(struct workqueue_struct *wq,
-				  struct work_struct *work)
-{
-	int cpu, new_cpu;
-
-	cpu = new_cpu = smp_processor_id();
-	do {
-		new_cpu = cpumask_next(new_cpu, cpu_online_mask) % nr_cpu_ids;
-		if (cpu_to_node(new_cpu) == numa_node_id())
-			break;
-	} while (cpu != new_cpu);
-
-	queue_work_on(new_cpu, wq, work);
-}
-
 /* This is called directly from KGD at ISR. */
 void kgd2kfd_interrupt(struct kfd_dev *kfd, const void *ih_ring_entry)
 {
@@ -1098,7 +1092,7 @@ void kgd2kfd_interrupt(struct kfd_dev *kfd, const void *ih_ring_entry)
 			    	patched_ihre, &is_patched)
 		    && enqueue_ih_ring_entry(node,
 			    	is_patched ? patched_ihre : ih_ring_entry)) {
-			kfd_queue_work(node->ih_wq, &node->interrupt_work);
+			queue_work(node->kfd->ih_wq, &node->interrupt_work);
 			spin_unlock_irqrestore(&node->interrupt_lock, flags);
 			return;
 		}
@@ -1500,6 +1494,11 @@ int kfd_debugfs_hang_hws(struct kfd_node *dev)
 		return -EINVAL;
 	}
 
+	if (dev->kfd->shared_resources.enable_mes) {
+		dev_err(dev->adev->dev, "Inducing MES hang is not supported\n");
+		return -EINVAL;
+	}
+
 	return dqm_debugfs_hang_hws(dev->dqm);
 }
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index f5b3ed20e891..6a58dd8d2130 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -205,21 +205,6 @@ static int add_queue_mes(struct device_queue_manager *dqm, struct queue *q,
 	if (!down_read_trylock(&adev->reset_domain->sem))
 		return -EIO;
 
-	if (!pdd->proc_ctx_cpu_ptr) {
-		r = amdgpu_amdkfd_alloc_gtt_mem(adev,
-				AMDGPU_MES_PROC_CTX_SIZE,
-				&pdd->proc_ctx_bo,
-				&pdd->proc_ctx_gpu_addr,
-				&pdd->proc_ctx_cpu_ptr,
-				false);
-		if (r) {
-			dev_err(adev->dev,
-				"failed to allocate process context bo\n");
-			return r;
-		}
-		memset(pdd->proc_ctx_cpu_ptr, 0, AMDGPU_MES_PROC_CTX_SIZE);
-	}
-
 	memset(&queue_input, 0x0, sizeof(struct mes_add_queue_input));
 	queue_input.process_id = qpd->pqm->process->pasid;
 	queue_input.page_table_base_addr =  qpd->page_table_base;
@@ -1199,11 +1184,13 @@ static int evict_process_queues_cpsch(struct device_queue_manager *dqm,
 		decrement_queue_count(dqm, qpd, q);
 
 		if (dqm->dev->kfd->shared_resources.enable_mes) {
-			retval = remove_queue_mes(dqm, q, qpd);
-			if (retval) {
+			int err;
+
+			err = remove_queue_mes(dqm, q, qpd);
+			if (err) {
 				dev_err(dev, "Failed to evict queue %d\n",
 					q->properties.queue_id);
-				goto out;
+				retval = err;
 			}
 		}
 	}
@@ -2290,9 +2277,9 @@ static int unmap_queues_cpsch(struct device_queue_manager *dqm,
 	 */
 	mqd_mgr = dqm->mqd_mgrs[KFD_MQD_TYPE_HIQ];
 	if (mqd_mgr->check_preemption_failed(mqd_mgr, dqm->packet_mgr.priv_queue->queue->mqd)) {
+		while (halt_if_hws_hang)
+			schedule();
 		if (reset_queues_on_hws_hang(dqm)) {
-			while (halt_if_hws_hang)
-				schedule();
 			dqm->is_hws_hang = true;
 			kfd_hws_hang(dqm);
 			retval = -ETIME;
@@ -2466,14 +2453,6 @@ failed_try_destroy_debugged_queue:
 	return retval;
 }
 
-/*
- * Low bits must be 0000/FFFF as required by HW, high bits must be 0 to
- * stay in user mode.
- */
-#define APE1_FIXED_BITS_MASK 0xFFFF80000000FFFFULL
-/* APE1 limit is inclusive and 64K aligned. */
-#define APE1_LIMIT_ALIGNMENT 0xFFFF
-
 static bool set_cache_memory_policy(struct device_queue_manager *dqm,
 				   struct qcm_process_device *qpd,
 				   enum cache_policy default_policy,
@@ -2488,34 +2467,6 @@ static bool set_cache_memory_policy(struct device_queue_manager *dqm,
 
 	dqm_lock(dqm);
 
-	if (alternate_aperture_size == 0) {
-		/* base > limit disables APE1 */
-		qpd->sh_mem_ape1_base = 1;
-		qpd->sh_mem_ape1_limit = 0;
-	} else {
-		/*
-		 * In FSA64, APE1_Base[63:0] = { 16{SH_MEM_APE1_BASE[31]},
-		 *			SH_MEM_APE1_BASE[31:0], 0x0000 }
-		 * APE1_Limit[63:0] = { 16{SH_MEM_APE1_LIMIT[31]},
-		 *			SH_MEM_APE1_LIMIT[31:0], 0xFFFF }
-		 * Verify that the base and size parameters can be
-		 * represented in this format and convert them.
-		 * Additionally restrict APE1 to user-mode addresses.
-		 */
-
-		uint64_t base = (uintptr_t)alternate_aperture_base;
-		uint64_t limit = base + alternate_aperture_size - 1;
-
-		if (limit <= base || (base & APE1_FIXED_BITS_MASK) != 0 ||
-		   (limit & APE1_FIXED_BITS_MASK) != APE1_LIMIT_ALIGNMENT) {
-			retval = false;
-			goto out;
-		}
-
-		qpd->sh_mem_ape1_base = base >> 16;
-		qpd->sh_mem_ape1_limit = limit >> 16;
-	}
-
 	retval = dqm->asic_ops.set_cache_memory_policy(
 			dqm,
 			qpd,
@@ -2524,6 +2475,9 @@ static bool set_cache_memory_policy(struct device_queue_manager *dqm,
 			alternate_aperture_base,
 			alternate_aperture_size);
 
+	if (retval)
+		goto out;
+
 	if ((dqm->sched_policy == KFD_SCHED_POLICY_NO_HWS) && (qpd->vmid != 0))
 		program_sh_mem_settings(dqm, qpd);
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_cik.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_cik.c
index d4d95c7f2e5d..32bedef912b3 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_cik.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_cik.c
@@ -27,6 +27,14 @@
 #include "oss/oss_2_4_sh_mask.h"
 #include "gca/gfx_7_2_sh_mask.h"
 
+/*
+ * Low bits must be 0000/FFFF as required by HW, high bits must be 0 to
+ * stay in user mode.
+ */
+#define APE1_FIXED_BITS_MASK 0xFFFF80000000FFFFULL
+/* APE1 limit is inclusive and 64K aligned. */
+#define APE1_LIMIT_ALIGNMENT 0xFFFF
+
 static bool set_cache_memory_policy_cik(struct device_queue_manager *dqm,
 				   struct qcm_process_device *qpd,
 				   enum cache_policy default_policy,
@@ -84,6 +92,36 @@ static bool set_cache_memory_policy_cik(struct device_queue_manager *dqm,
 {
 	uint32_t default_mtype;
 	uint32_t ape1_mtype;
+	unsigned int temp;
+	bool retval = true;
+
+	if (alternate_aperture_size == 0) {
+		/* base > limit disables APE1 */
+		qpd->sh_mem_ape1_base = 1;
+		qpd->sh_mem_ape1_limit = 0;
+	} else {
+		/*
+		 * In FSA64, APE1_Base[63:0] = { 16{SH_MEM_APE1_BASE[31]},
+		 *			SH_MEM_APE1_BASE[31:0], 0x0000 }
+		 * APE1_Limit[63:0] = { 16{SH_MEM_APE1_LIMIT[31]},
+		 *			SH_MEM_APE1_LIMIT[31:0], 0xFFFF }
+		 * Verify that the base and size parameters can be
+		 * represented in this format and convert them.
+		 * Additionally restrict APE1 to user-mode addresses.
+		 */
+
+		uint64_t base = (uintptr_t)alternate_aperture_base;
+		uint64_t limit = base + alternate_aperture_size - 1;
+
+		if (limit <= base || (base & APE1_FIXED_BITS_MASK) != 0 ||
+		   (limit & APE1_FIXED_BITS_MASK) != APE1_LIMIT_ALIGNMENT) {
+			retval = false;
+			goto out;
+		}
+
+		qpd->sh_mem_ape1_base = base >> 16;
+		qpd->sh_mem_ape1_limit = limit >> 16;
+	}
 
 	default_mtype = (default_policy == cache_policy_coherent) ?
 			MTYPE_NONCACHED :
@@ -97,37 +135,22 @@ static bool set_cache_memory_policy_cik(struct device_queue_manager *dqm,
 			| ALIGNMENT_MODE(SH_MEM_ALIGNMENT_MODE_UNALIGNED)
 			| DEFAULT_MTYPE(default_mtype)
 			| APE1_MTYPE(ape1_mtype);
-
-	return true;
-}
-
-static int update_qpd_cik(struct device_queue_manager *dqm,
-			  struct qcm_process_device *qpd)
-{
-	struct kfd_process_device *pdd;
-	unsigned int temp;
-
-	pdd = qpd_to_pdd(qpd);
-
-	/* check if sh_mem_config register already configured */
-	if (qpd->sh_mem_config == 0) {
-		qpd->sh_mem_config =
-			ALIGNMENT_MODE(SH_MEM_ALIGNMENT_MODE_UNALIGNED) |
-			DEFAULT_MTYPE(MTYPE_NONCACHED) |
-			APE1_MTYPE(MTYPE_NONCACHED);
-		qpd->sh_mem_ape1_limit = 0;
-		qpd->sh_mem_ape1_base = 0;
-	}
-
 	/* On dGPU we're always in GPUVM64 addressing mode with 64-bit
 	 * aperture addresses.
 	 */
-	temp = get_sh_mem_bases_nybble_64(pdd);
+	temp = get_sh_mem_bases_nybble_64(qpd_to_pdd(qpd));
 	qpd->sh_mem_bases = compute_sh_mem_bases_64bit(temp);
 
 	pr_debug("is32bit process: %d sh_mem_bases nybble: 0x%X and register 0x%X\n",
 		qpd->pqm->process->is_32bit_user_mode, temp, qpd->sh_mem_bases);
 
+out:
+	return retval;
+}
+
+static int update_qpd_cik(struct device_queue_manager *dqm,
+			  struct qcm_process_device *qpd)
+{
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v10.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v10.c
index 245a90dfc2f6..b5f5f141353b 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v10.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v10.c
@@ -31,10 +31,17 @@ static int update_qpd_v10(struct device_queue_manager *dqm,
 			 struct qcm_process_device *qpd);
 static void init_sdma_vm_v10(struct device_queue_manager *dqm, struct queue *q,
 			    struct qcm_process_device *qpd);
+static bool set_cache_memory_policy_v10(struct device_queue_manager *dqm,
+				   struct qcm_process_device *qpd,
+				   enum cache_policy default_policy,
+				   enum cache_policy alternate_policy,
+				   void __user *alternate_aperture_base,
+				   uint64_t alternate_aperture_size);
 
 void device_queue_manager_init_v10(
 	struct device_queue_manager_asic_ops *asic_ops)
 {
+	asic_ops->set_cache_memory_policy = set_cache_memory_policy_v10;
 	asic_ops->update_qpd = update_qpd_v10;
 	asic_ops->init_sdma_vm = init_sdma_vm_v10;
 	asic_ops->mqd_manager_init = mqd_manager_init_v10;
@@ -49,27 +56,27 @@ static uint32_t compute_sh_mem_bases_64bit(struct kfd_process_device *pdd)
 		private_base;
 }
 
-static int update_qpd_v10(struct device_queue_manager *dqm,
-			 struct qcm_process_device *qpd)
+static bool set_cache_memory_policy_v10(struct device_queue_manager *dqm,
+				   struct qcm_process_device *qpd,
+				   enum cache_policy default_policy,
+				   enum cache_policy alternate_policy,
+				   void __user *alternate_aperture_base,
+				   uint64_t alternate_aperture_size)
 {
-	struct kfd_process_device *pdd;
-
-	pdd = qpd_to_pdd(qpd);
-
-	/* check if sh_mem_config register already configured */
-	if (qpd->sh_mem_config == 0) {
-		qpd->sh_mem_config =
-			(SH_MEM_ALIGNMENT_MODE_UNALIGNED <<
-				SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT) |
-			(3 << SH_MEM_CONFIG__INITIAL_INST_PREFETCH__SHIFT);
-		qpd->sh_mem_ape1_limit = 0;
-		qpd->sh_mem_ape1_base = 0;
-	}
-
-	qpd->sh_mem_bases = compute_sh_mem_bases_64bit(pdd);
+	qpd->sh_mem_config = (SH_MEM_ALIGNMENT_MODE_UNALIGNED <<
+			      SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT) |
+			      (3 << SH_MEM_CONFIG__INITIAL_INST_PREFETCH__SHIFT);
+	qpd->sh_mem_ape1_limit = 0;
+	qpd->sh_mem_ape1_base = 0;
+	qpd->sh_mem_bases = compute_sh_mem_bases_64bit(qpd_to_pdd(qpd));
 
 	pr_debug("sh_mem_bases 0x%X\n", qpd->sh_mem_bases);
+	return true;
+}
 
+static int update_qpd_v10(struct device_queue_manager *dqm,
+			 struct qcm_process_device *qpd)
+{
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v11.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v11.c
index 2e129da7acb4..f436878d0d62 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v11.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v11.c
@@ -30,10 +30,17 @@ static int update_qpd_v11(struct device_queue_manager *dqm,
 			 struct qcm_process_device *qpd);
 static void init_sdma_vm_v11(struct device_queue_manager *dqm, struct queue *q,
 			    struct qcm_process_device *qpd);
+static bool set_cache_memory_policy_v11(struct device_queue_manager *dqm,
+				   struct qcm_process_device *qpd,
+				   enum cache_policy default_policy,
+				   enum cache_policy alternate_policy,
+				   void __user *alternate_aperture_base,
+				   uint64_t alternate_aperture_size);
 
 void device_queue_manager_init_v11(
 	struct device_queue_manager_asic_ops *asic_ops)
 {
+	asic_ops->set_cache_memory_policy = set_cache_memory_policy_v11;
 	asic_ops->update_qpd = update_qpd_v11;
 	asic_ops->init_sdma_vm = init_sdma_vm_v11;
 	asic_ops->mqd_manager_init = mqd_manager_init_v11;
@@ -48,28 +55,28 @@ static uint32_t compute_sh_mem_bases_64bit(struct kfd_process_device *pdd)
 		private_base;
 }
 
-static int update_qpd_v11(struct device_queue_manager *dqm,
-			 struct qcm_process_device *qpd)
+static bool set_cache_memory_policy_v11(struct device_queue_manager *dqm,
+				   struct qcm_process_device *qpd,
+				   enum cache_policy default_policy,
+				   enum cache_policy alternate_policy,
+				   void __user *alternate_aperture_base,
+				   uint64_t alternate_aperture_size)
 {
-	struct kfd_process_device *pdd;
-
-	pdd = qpd_to_pdd(qpd);
-
-	/* check if sh_mem_config register already configured */
-	if (qpd->sh_mem_config == 0) {
-		qpd->sh_mem_config =
-			(SH_MEM_ALIGNMENT_MODE_UNALIGNED <<
-				SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT) |
-			(3 << SH_MEM_CONFIG__INITIAL_INST_PREFETCH__SHIFT);
-
-		qpd->sh_mem_ape1_limit = 0;
-		qpd->sh_mem_ape1_base = 0;
-	}
+	qpd->sh_mem_config = (SH_MEM_ALIGNMENT_MODE_UNALIGNED <<
+			      SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT) |
+			      (3 << SH_MEM_CONFIG__INITIAL_INST_PREFETCH__SHIFT);
 
-	qpd->sh_mem_bases = compute_sh_mem_bases_64bit(pdd);
+	qpd->sh_mem_ape1_limit = 0;
+	qpd->sh_mem_ape1_base = 0;
+	qpd->sh_mem_bases = compute_sh_mem_bases_64bit(qpd_to_pdd(qpd));
 
 	pr_debug("sh_mem_bases 0x%X\n", qpd->sh_mem_bases);
+	return true;
+}
 
+static int update_qpd_v11(struct device_queue_manager *dqm,
+			 struct qcm_process_device *qpd)
+{
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v12.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v12.c
index 4f3295b29dfb..62ca1c8fcbaf 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v12.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v12.c
@@ -30,10 +30,17 @@ static int update_qpd_v12(struct device_queue_manager *dqm,
 			 struct qcm_process_device *qpd);
 static void init_sdma_vm_v12(struct device_queue_manager *dqm, struct queue *q,
 			    struct qcm_process_device *qpd);
+static bool set_cache_memory_policy_v12(struct device_queue_manager *dqm,
+				   struct qcm_process_device *qpd,
+				   enum cache_policy default_policy,
+				   enum cache_policy alternate_policy,
+				   void __user *alternate_aperture_base,
+				   uint64_t alternate_aperture_size);
 
 void device_queue_manager_init_v12(
 	struct device_queue_manager_asic_ops *asic_ops)
 {
+	asic_ops->set_cache_memory_policy = set_cache_memory_policy_v12;
 	asic_ops->update_qpd = update_qpd_v12;
 	asic_ops->init_sdma_vm = init_sdma_vm_v12;
 	asic_ops->mqd_manager_init = mqd_manager_init_v12;
@@ -48,28 +55,28 @@ static uint32_t compute_sh_mem_bases_64bit(struct kfd_process_device *pdd)
 		private_base;
 }
 
-static int update_qpd_v12(struct device_queue_manager *dqm,
-			 struct qcm_process_device *qpd)
+static bool set_cache_memory_policy_v12(struct device_queue_manager *dqm,
+				   struct qcm_process_device *qpd,
+				   enum cache_policy default_policy,
+				   enum cache_policy alternate_policy,
+				   void __user *alternate_aperture_base,
+				   uint64_t alternate_aperture_size)
 {
-	struct kfd_process_device *pdd;
-
-	pdd = qpd_to_pdd(qpd);
-
-	/* check if sh_mem_config register already configured */
-	if (qpd->sh_mem_config == 0) {
-		qpd->sh_mem_config =
-			(SH_MEM_ALIGNMENT_MODE_UNALIGNED <<
-				SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT) |
-			(3 << SH_MEM_CONFIG__INITIAL_INST_PREFETCH__SHIFT);
-
-		qpd->sh_mem_ape1_limit = 0;
-		qpd->sh_mem_ape1_base = 0;
-	}
+	qpd->sh_mem_config = (SH_MEM_ALIGNMENT_MODE_UNALIGNED <<
+			      SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT) |
+			      (3 << SH_MEM_CONFIG__INITIAL_INST_PREFETCH__SHIFT);
 
-	qpd->sh_mem_bases = compute_sh_mem_bases_64bit(pdd);
+	qpd->sh_mem_ape1_limit = 0;
+	qpd->sh_mem_ape1_base = 0;
+	qpd->sh_mem_bases = compute_sh_mem_bases_64bit(qpd_to_pdd(qpd));
 
 	pr_debug("sh_mem_bases 0x%X\n", qpd->sh_mem_bases);
+	return true;
+}
 
+static int update_qpd_v12(struct device_queue_manager *dqm,
+			 struct qcm_process_device *qpd)
+{
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v9.c
index 210bcc048f4c..d85eadaa1e11 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v9.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v9.c
@@ -30,10 +30,17 @@ static int update_qpd_v9(struct device_queue_manager *dqm,
 			 struct qcm_process_device *qpd);
 static void init_sdma_vm_v9(struct device_queue_manager *dqm, struct queue *q,
 			    struct qcm_process_device *qpd);
+static bool set_cache_memory_policy_v9(struct device_queue_manager *dqm,
+				   struct qcm_process_device *qpd,
+				   enum cache_policy default_policy,
+				   enum cache_policy alternate_policy,
+				   void __user *alternate_aperture_base,
+				   uint64_t alternate_aperture_size);
 
 void device_queue_manager_init_v9(
 	struct device_queue_manager_asic_ops *asic_ops)
 {
+	asic_ops->set_cache_memory_policy = set_cache_memory_policy_v9;
 	asic_ops->update_qpd = update_qpd_v9;
 	asic_ops->init_sdma_vm = init_sdma_vm_v9;
 	asic_ops->mqd_manager_init = mqd_manager_init_v9;
@@ -48,10 +55,36 @@ static uint32_t compute_sh_mem_bases_64bit(struct kfd_process_device *pdd)
 		private_base;
 }
 
+static bool set_cache_memory_policy_v9(struct device_queue_manager *dqm,
+				   struct qcm_process_device *qpd,
+				   enum cache_policy default_policy,
+				   enum cache_policy alternate_policy,
+				   void __user *alternate_aperture_base,
+				   uint64_t alternate_aperture_size)
+{
+	qpd->sh_mem_config = SH_MEM_ALIGNMENT_MODE_UNALIGNED <<
+				SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT;
+
+	if (dqm->dev->kfd->noretry)
+		qpd->sh_mem_config |= 1 << SH_MEM_CONFIG__RETRY_DISABLE__SHIFT;
+
+	if (KFD_GC_VERSION(dqm->dev->kfd) == IP_VERSION(9, 4, 3) ||
+		KFD_GC_VERSION(dqm->dev->kfd) == IP_VERSION(9, 4, 4))
+		qpd->sh_mem_config |= (1 << SH_MEM_CONFIG__F8_MODE__SHIFT);
+
+	qpd->sh_mem_ape1_limit = 0;
+	qpd->sh_mem_ape1_base = 0;
+	qpd->sh_mem_bases = compute_sh_mem_bases_64bit(qpd_to_pdd(qpd));
+
+	pr_debug("sh_mem_bases 0x%X sh_mem_config 0x%X\n", qpd->sh_mem_bases,
+		 qpd->sh_mem_config);
+	return true;
+}
+
 static int update_qpd_v9(struct device_queue_manager *dqm,
 			 struct qcm_process_device *qpd)
 {
-	struct kfd_process_device *pdd;
+	struct kfd_process_device *pdd = qpd_to_pdd(qpd);
 
 	pdd = qpd_to_pdd(qpd);
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_vi.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_vi.c
index b291ee0fab94..320518f41890 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_vi.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_vi.c
@@ -27,6 +27,14 @@
 #include "gca/gfx_8_0_sh_mask.h"
 #include "oss/oss_3_0_sh_mask.h"
 
+/*
+ * Low bits must be 0000/FFFF as required by HW, high bits must be 0 to
+ * stay in user mode.
+ */
+#define APE1_FIXED_BITS_MASK 0xFFFF80000000FFFFULL
+/* APE1 limit is inclusive and 64K aligned. */
+#define APE1_LIMIT_ALIGNMENT 0xFFFF
+
 static bool set_cache_memory_policy_vi(struct device_queue_manager *dqm,
 				       struct qcm_process_device *qpd,
 				       enum cache_policy default_policy,
@@ -85,6 +93,36 @@ static bool set_cache_memory_policy_vi(struct device_queue_manager *dqm,
 {
 	uint32_t default_mtype;
 	uint32_t ape1_mtype;
+	unsigned int temp;
+	bool retval = true;
+
+	if (alternate_aperture_size == 0) {
+		/* base > limit disables APE1 */
+		qpd->sh_mem_ape1_base = 1;
+		qpd->sh_mem_ape1_limit = 0;
+	} else {
+		/*
+		 * In FSA64, APE1_Base[63:0] = { 16{SH_MEM_APE1_BASE[31]},
+		 *			SH_MEM_APE1_BASE[31:0], 0x0000 }
+		 * APE1_Limit[63:0] = { 16{SH_MEM_APE1_LIMIT[31]},
+		 *			SH_MEM_APE1_LIMIT[31:0], 0xFFFF }
+		 * Verify that the base and size parameters can be
+		 * represented in this format and convert them.
+		 * Additionally restrict APE1 to user-mode addresses.
+		 */
+
+		uint64_t base = (uintptr_t)alternate_aperture_base;
+		uint64_t limit = base + alternate_aperture_size - 1;
+
+		if (limit <= base || (base & APE1_FIXED_BITS_MASK) != 0 ||
+		   (limit & APE1_FIXED_BITS_MASK) != APE1_LIMIT_ALIGNMENT) {
+			retval = false;
+			goto out;
+		}
+
+		qpd->sh_mem_ape1_base = base >> 16;
+		qpd->sh_mem_ape1_limit = limit >> 16;
+	}
 
 	default_mtype = (default_policy == cache_policy_coherent) ?
 			MTYPE_UC :
@@ -100,40 +138,21 @@ static bool set_cache_memory_policy_vi(struct device_queue_manager *dqm,
 			default_mtype << SH_MEM_CONFIG__DEFAULT_MTYPE__SHIFT |
 			ape1_mtype << SH_MEM_CONFIG__APE1_MTYPE__SHIFT;
 
-	return true;
-}
-
-static int update_qpd_vi(struct device_queue_manager *dqm,
-			 struct qcm_process_device *qpd)
-{
-	struct kfd_process_device *pdd;
-	unsigned int temp;
-
-	pdd = qpd_to_pdd(qpd);
-
-	/* check if sh_mem_config register already configured */
-	if (qpd->sh_mem_config == 0) {
-		qpd->sh_mem_config =
-				SH_MEM_ALIGNMENT_MODE_UNALIGNED <<
-					SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT |
-				MTYPE_UC <<
-					SH_MEM_CONFIG__DEFAULT_MTYPE__SHIFT |
-				MTYPE_UC <<
-					SH_MEM_CONFIG__APE1_MTYPE__SHIFT;
-
-		qpd->sh_mem_ape1_limit = 0;
-		qpd->sh_mem_ape1_base = 0;
-	}
-
 	/* On dGPU we're always in GPUVM64 addressing mode with 64-bit
 	 * aperture addresses.
 	 */
-	temp = get_sh_mem_bases_nybble_64(pdd);
+	temp = get_sh_mem_bases_nybble_64(qpd_to_pdd(qpd));
 	qpd->sh_mem_bases = compute_sh_mem_bases_64bit(temp);
 
 	pr_debug("sh_mem_bases nybble: 0x%X and register 0x%X\n",
 		temp, qpd->sh_mem_bases);
+out:
+	return retval;
+}
 
+static int update_qpd_vi(struct device_queue_manager *dqm,
+			 struct qcm_process_device *qpd)
+{
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
index ea3792249209..6798510c4a70 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_events.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
@@ -1315,6 +1315,7 @@ void kfd_signal_poison_consumed_event(struct kfd_node *dev, u32 pasid)
 	user_gpu_id = kfd_process_get_user_gpu_id(p, dev->id);
 	if (unlikely(user_gpu_id == -EINVAL)) {
 		WARN_ONCE(1, "Could not get user_gpu_id from dev->id:%x\n", dev->id);
+		kfd_unref_process(p);
 		return;
 	}
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_interrupt.c b/drivers/gpu/drm/amd/amdkfd/kfd_interrupt.c
index 9b6b6e882593..15b4b70cf199 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_interrupt.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_interrupt.c
@@ -62,11 +62,14 @@ int kfd_interrupt_init(struct kfd_node *node)
 		return r;
 	}
 
-	node->ih_wq = alloc_workqueue("KFD IH", WQ_HIGHPRI, 1);
-	if (unlikely(!node->ih_wq)) {
-		kfifo_free(&node->ih_fifo);
-		dev_err(node->adev->dev, "Failed to allocate KFD IH workqueue\n");
-		return -ENOMEM;
+	if (!node->kfd->ih_wq) {
+		node->kfd->ih_wq = alloc_workqueue("KFD IH", WQ_HIGHPRI | WQ_UNBOUND,
+						   node->kfd->num_nodes);
+		if (unlikely(!node->kfd->ih_wq)) {
+			kfifo_free(&node->ih_fifo);
+			dev_err(node->adev->dev, "Failed to allocate KFD IH workqueue\n");
+			return -ENOMEM;
+		}
 	}
 	spin_lock_init(&node->interrupt_lock);
 
@@ -96,16 +99,6 @@ void kfd_interrupt_exit(struct kfd_node *node)
 	spin_lock_irqsave(&node->interrupt_lock, flags);
 	node->interrupts_active = false;
 	spin_unlock_irqrestore(&node->interrupt_lock, flags);
-
-	/*
-	 * flush_work ensures that there are no outstanding
-	 * work-queue items that will access interrupt_ring. New work items
-	 * can't be created because we stopped interrupt handling above.
-	 */
-	flush_workqueue(node->ih_wq);
-
-	destroy_workqueue(node->ih_wq);
-
 	kfifo_free(&node->ih_fifo);
 }
 
@@ -162,7 +155,7 @@ static void interrupt_wq(struct work_struct *work)
 			/* If we spent more than a second processing signals,
 			 * reschedule the worker to avoid soft-lockup warnings
 			 */
-			queue_work(dev->ih_wq, &dev->interrupt_work);
+			queue_work(dev->kfd->ih_wq, &dev->interrupt_work);
 			break;
 		}
 	}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c
index 2eff37aaf827..1695dd78ede8 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c
@@ -107,6 +107,8 @@ static void init_mqd(struct mqd_manager *mm, void **mqd,
 	m->cp_hqd_persistent_state = CP_HQD_PERSISTENT_STATE__PRELOAD_REQ_MASK |
 			0x53 << CP_HQD_PERSISTENT_STATE__PRELOAD_SIZE__SHIFT;
 
+	m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT;
+	m->cp_hqd_pq_control |= CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK;
 	m->cp_mqd_control = 1 << CP_MQD_CONTROL__PRIV_STATE__SHIFT;
 
 	m->cp_mqd_base_addr_lo        = lower_32_bits(addr);
@@ -167,10 +169,10 @@ static void update_mqd(struct mqd_manager *mm, void *mqd,
 
 	m = get_mqd(mqd);
 
-	m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT;
+	m->cp_hqd_pq_control &= ~CP_HQD_PQ_CONTROL__QUEUE_SIZE_MASK;
 	m->cp_hqd_pq_control |=
 			ffs(q->queue_size / sizeof(unsigned int)) - 1 - 1;
-	m->cp_hqd_pq_control |= CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK;
+
 	pr_debug("cp_hqd_pq_control 0x%x\n", m->cp_hqd_pq_control);
 
 	m->cp_hqd_pq_base_lo = lower_32_bits((uint64_t)q->queue_address >> 8);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c
index 68dbc0399c87..3c0ae28c5923 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c
@@ -154,6 +154,8 @@ static void init_mqd(struct mqd_manager *mm, void **mqd,
 	m->cp_hqd_persistent_state = CP_HQD_PERSISTENT_STATE__PRELOAD_REQ_MASK |
 			0x55 << CP_HQD_PERSISTENT_STATE__PRELOAD_SIZE__SHIFT;
 
+	m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT;
+	m->cp_hqd_pq_control |= CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK;
 	m->cp_mqd_control = 1 << CP_MQD_CONTROL__PRIV_STATE__SHIFT;
 
 	m->cp_mqd_base_addr_lo        = lower_32_bits(addr);
@@ -221,10 +223,9 @@ static void update_mqd(struct mqd_manager *mm, void *mqd,
 
 	m = get_mqd(mqd);
 
-	m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT;
+	m->cp_hqd_pq_control &= ~CP_HQD_PQ_CONTROL__QUEUE_SIZE_MASK;
 	m->cp_hqd_pq_control |=
 			ffs(q->queue_size / sizeof(unsigned int)) - 1 - 1;
-	m->cp_hqd_pq_control |= CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK;
 	pr_debug("cp_hqd_pq_control 0x%x\n", m->cp_hqd_pq_control);
 
 	m->cp_hqd_pq_base_lo = lower_32_bits((uint64_t)q->queue_address >> 8);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v12.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v12.c
index 2b72d5b4949b..565858b9044d 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v12.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v12.c
@@ -121,6 +121,8 @@ static void init_mqd(struct mqd_manager *mm, void **mqd,
 	m->cp_hqd_persistent_state = CP_HQD_PERSISTENT_STATE__PRELOAD_REQ_MASK |
 			0x55 << CP_HQD_PERSISTENT_STATE__PRELOAD_SIZE__SHIFT;
 
+	m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT;
+	m->cp_hqd_pq_control |= CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK;
 	m->cp_mqd_control = 1 << CP_MQD_CONTROL__PRIV_STATE__SHIFT;
 
 	m->cp_mqd_base_addr_lo        = lower_32_bits(addr);
@@ -184,10 +186,9 @@ static void update_mqd(struct mqd_manager *mm, void *mqd,
 
 	m = get_mqd(mqd);
 
-	m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT;
+	m->cp_hqd_pq_control &= ~CP_HQD_PQ_CONTROL__QUEUE_SIZE_MASK;
 	m->cp_hqd_pq_control |=
 			ffs(q->queue_size / sizeof(unsigned int)) - 1 - 1;
-	m->cp_hqd_pq_control |= CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK;
 	pr_debug("cp_hqd_pq_control 0x%x\n", m->cp_hqd_pq_control);
 
 	m->cp_hqd_pq_base_lo = lower_32_bits((uint64_t)q->queue_address >> 8);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
index 84e8ea3a8a0c..217af36dc097 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
@@ -182,6 +182,9 @@ static void init_mqd(struct mqd_manager *mm, void **mqd,
 	m->cp_hqd_persistent_state = CP_HQD_PERSISTENT_STATE__PRELOAD_REQ_MASK |
 			0x53 << CP_HQD_PERSISTENT_STATE__PRELOAD_SIZE__SHIFT;
 
+	m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT;
+	m->cp_hqd_pq_control |= CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK;
+
 	m->cp_mqd_control = 1 << CP_MQD_CONTROL__PRIV_STATE__SHIFT;
 
 	m->cp_mqd_base_addr_lo        = lower_32_bits(addr);
@@ -244,7 +247,7 @@ static void update_mqd(struct mqd_manager *mm, void *mqd,
 
 	m = get_mqd(mqd);
 
-	m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT;
+	m->cp_hqd_pq_control &= ~CP_HQD_PQ_CONTROL__QUEUE_SIZE_MASK;
 	m->cp_hqd_pq_control |= order_base_2(q->queue_size / 4) - 1;
 	pr_debug("cp_hqd_pq_control 0x%x\n", m->cp_hqd_pq_control);
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_v9.c
index 1f9f5bfeaf86..d87b895660c2 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_v9.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_v9.c
@@ -237,7 +237,7 @@ static int pm_map_queues_v9(struct packet_manager *pm, uint32_t *buffer,
 
 	packet->bitfields2.engine_sel =
 		engine_sel__mes_map_queues__compute_vi;
-	packet->bitfields2.gws_control_queue = q->gws ? 1 : 0;
+	packet->bitfields2.gws_control_queue = q->properties.is_gws ? 1 : 0;
 	packet->bitfields2.extended_engine_sel =
 		extended_engine_sel__mes_map_queues__legacy_engine_sel;
 	packet->bitfields2.queue_type =
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 26e48fdc8728..75523f30cd38 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -273,7 +273,6 @@ struct kfd_node {
 
 	/* Interrupts */
 	struct kfifo ih_fifo;
-	struct workqueue_struct *ih_wq;
 	struct work_struct interrupt_work;
 	spinlock_t interrupt_lock;
 
@@ -366,6 +365,8 @@ struct kfd_dev {
 	struct kfd_node *nodes[MAX_KFD_NODES];
 	unsigned int num_nodes;
 
+	struct workqueue_struct *ih_wq;
+
 	/* Kernel doorbells for KFD device */
 	struct amdgpu_bo *doorbells;
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index 264bd764f6f2..45923da7709f 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -35,6 +35,7 @@
 #include <linux/pm_runtime.h>
 #include "amdgpu_amdkfd.h"
 #include "amdgpu.h"
+#include "amdgpu_reset.h"
 
 struct mm_struct;
 
@@ -841,6 +842,14 @@ struct kfd_process *kfd_create_process(struct task_struct *thread)
 		return ERR_PTR(-EINVAL);
 	}
 
+	/* If the process just called exec(3), it is possible that the
+	 * cleanup of the kfd_process (following the release of the mm
+	 * of the old process image) is still in the cleanup work queue.
+	 * Make sure to drain any job before trying to recreate any
+	 * resource for this process.
+	 */
+	flush_workqueue(kfd_process_wq);
+
 	/*
 	 * take kfd processes mutex before starting of process creation
 	 * so there won't be a case where two threads of the same process
@@ -859,14 +868,6 @@ struct kfd_process *kfd_create_process(struct task_struct *thread)
 	if (process) {
 		pr_debug("Process already found\n");
 	} else {
-		/* If the process just called exec(3), it is possible that the
-		 * cleanup of the kfd_process (following the release of the mm
-		 * of the old process image) is still in the cleanup work queue.
-		 * Make sure to drain any job before trying to recreate any
-		 * resource for this process.
-		 */
-		flush_workqueue(kfd_process_wq);
-
 		process = create_process(thread);
 		if (IS_ERR(process))
 			goto out;
@@ -1140,6 +1141,17 @@ static void kfd_process_remove_sysfs(struct kfd_process *p)
 	p->kobj = NULL;
 }
 
+/*
+ * If any GPU is ongoing reset, wait for reset complete.
+ */
+static void kfd_process_wait_gpu_reset_complete(struct kfd_process *p)
+{
+	int i;
+
+	for (i = 0; i < p->n_pdds; i++)
+		flush_workqueue(p->pdds[i]->dev->adev->reset_domain->wq);
+}
+
 /* No process locking is needed in this function, because the process
  * is not findable any more. We must assume that no other thread is
  * using it any more, otherwise we couldn't safely free the process
@@ -1154,6 +1166,11 @@ static void kfd_process_wq_release(struct work_struct *work)
 	kfd_process_dequeue_from_all_devices(p);
 	pqm_uninit(&p->pqm);
 
+	/*
+	 * If GPU in reset, user queues may still running, wait for reset complete.
+	 */
+	kfd_process_wait_gpu_reset_complete(p);
+
 	/* Signal the eviction fence after user mode queues are
 	 * destroyed. This allows any BOs to be freed without
 	 * triggering pointless evictions or waiting for fences.
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
index ead4317a2168..4078a8176187 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
@@ -86,9 +86,12 @@ void kfd_process_dequeue_from_device(struct kfd_process_device *pdd)
 
 	if (pdd->already_dequeued)
 		return;
-
+	/* The MES context flush needs to filter out the case which the
+	 * KFD process is created without setting up the MES context and
+	 * queue for creating a compute queue.
+	 */
 	dev->dqm->ops.process_termination(dev->dqm, &pdd->qpd);
-	if (dev->kfd->shared_resources.enable_mes &&
+	if (dev->kfd->shared_resources.enable_mes && !!pdd->proc_ctx_gpu_addr &&
 	    down_read_trylock(&dev->adev->reset_domain->sem)) {
 		amdgpu_mes_flush_shader_debugger(dev->adev,
 						 pdd->proc_ctx_gpu_addr);
@@ -295,7 +298,7 @@ static int init_user_queue(struct process_queue_manager *pqm,
 	return 0;
 
 free_gang_ctx_bo:
-	amdgpu_amdkfd_free_gtt_mem(dev->adev, (*q)->gang_ctx_bo);
+	amdgpu_amdkfd_free_gtt_mem(dev->adev, &(*q)->gang_ctx_bo);
 cleanup:
 	uninit_queue(*q);
 	*q = NULL;
@@ -358,10 +361,26 @@ int pqm_create_queue(struct process_queue_manager *pqm,
 	if (retval != 0)
 		return retval;
 
+	/* Register process if this is the first queue */
 	if (list_empty(&pdd->qpd.queues_list) &&
 	    list_empty(&pdd->qpd.priv_queue_list))
 		dev->dqm->ops.register_process(dev->dqm, &pdd->qpd);
 
+	/* Allocate proc_ctx_bo only if MES is enabled and this is the first queue */
+	if (!pdd->proc_ctx_cpu_ptr && dev->kfd->shared_resources.enable_mes) {
+		retval = amdgpu_amdkfd_alloc_gtt_mem(dev->adev,
+						     AMDGPU_MES_PROC_CTX_SIZE,
+						     &pdd->proc_ctx_bo,
+						     &pdd->proc_ctx_gpu_addr,
+						     &pdd->proc_ctx_cpu_ptr,
+						     false);
+		if (retval) {
+			dev_err(dev->adev->dev, "failed to allocate process context bo\n");
+			return retval;
+		}
+		memset(pdd->proc_ctx_cpu_ptr, 0, AMDGPU_MES_PROC_CTX_SIZE);
+	}
+
 	pqn = kzalloc(sizeof(*pqn), GFP_KERNEL);
 	if (!pqn) {
 		retval = -ENOMEM;
@@ -527,7 +546,7 @@ int pqm_destroy_queue(struct process_queue_manager *pqm, unsigned int qid)
 			pr_err("Pasid 0x%x destroy queue %d failed, ret %d\n",
 				pqm->process->pasid,
 				pqn->q->properties.queue_id, retval);
-			if (retval != -ETIME)
+			if (retval != -ETIME && retval != -EIO)
 				goto err_destroy_queue;
 		}
 		kfd_procfs_del_queue(pqn->q);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_queue.c b/drivers/gpu/drm/amd/amdkfd/kfd_queue.c
index ad29634f8b44..29d7cb4cfe69 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_queue.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_queue.c
@@ -233,6 +233,7 @@ void kfd_queue_buffer_put(struct amdgpu_bo **bo)
 int kfd_queue_acquire_buffers(struct kfd_process_device *pdd, struct queue_properties *properties)
 {
 	struct kfd_topology_device *topo_dev;
+	u64 expected_queue_size;
 	struct amdgpu_vm *vm;
 	u32 total_cwsr_size;
 	int err;
@@ -241,6 +242,15 @@ int kfd_queue_acquire_buffers(struct kfd_process_device *pdd, struct queue_prope
 	if (!topo_dev)
 		return -EINVAL;
 
+	/* AQL queues on GFX7 and GFX8 appear twice their actual size */
+	if (properties->type == KFD_QUEUE_TYPE_COMPUTE &&
+	    properties->format == KFD_QUEUE_FORMAT_AQL &&
+	    topo_dev->node_props.gfx_target_version >= 70000 &&
+	    topo_dev->node_props.gfx_target_version < 90000)
+		expected_queue_size = properties->queue_size / 2;
+	else
+		expected_queue_size = properties->queue_size;
+
 	vm = drm_priv_to_vm(pdd->drm_priv);
 	err = amdgpu_bo_reserve(vm->root.bo, false);
 	if (err)
@@ -255,7 +265,7 @@ int kfd_queue_acquire_buffers(struct kfd_process_device *pdd, struct queue_prope
 		goto out_err_unreserve;
 
 	err = kfd_queue_buffer_get(vm, (void *)properties->queue_address,
-				   &properties->ring_bo, properties->queue_size);
+				   &properties->ring_bo, expected_queue_size);
 	if (err)
 		goto out_err_unreserve;
 
@@ -266,8 +276,8 @@ int kfd_queue_acquire_buffers(struct kfd_process_device *pdd, struct queue_prope
 	/* EOP buffer is not required for all ASICs */
 	if (properties->eop_ring_buffer_address) {
 		if (properties->eop_ring_buffer_size != topo_dev->node_props.eop_buffer_size) {
-			pr_debug("queue eop bo size 0x%lx not equal to node eop buf size 0x%x\n",
-				properties->eop_buf_bo->tbo.base.size,
+			pr_debug("queue eop bo size 0x%x not equal to node eop buf size 0x%x\n",
+				properties->eop_ring_buffer_size,
 				topo_dev->node_props.eop_buffer_size);
 			err = -EINVAL;
 			goto out_err_unreserve;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index 1893c27746a5..3e9e0f36cd3f 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -1170,13 +1170,12 @@ svm_range_split_head(struct svm_range *prange, uint64_t new_start,
 }
 
 static void
-svm_range_add_child(struct svm_range *prange, struct mm_struct *mm,
-		    struct svm_range *pchild, enum svm_work_list_ops op)
+svm_range_add_child(struct svm_range *prange, struct svm_range *pchild, enum svm_work_list_ops op)
 {
 	pr_debug("add child 0x%p [0x%lx 0x%lx] to prange 0x%p child list %d\n",
 		 pchild, pchild->start, pchild->last, prange, op);
 
-	pchild->work_item.mm = mm;
+	pchild->work_item.mm = NULL;
 	pchild->work_item.op = op;
 	list_add_tail(&pchild->child_list, &prange->child_list);
 }
@@ -1276,13 +1275,7 @@ svm_range_get_pte_flags(struct kfd_node *node,
 		break;
 	case IP_VERSION(12, 0, 0):
 	case IP_VERSION(12, 0, 1):
-		if (domain == SVM_RANGE_VRAM_DOMAIN) {
-			if (bo_node != node)
-				mapping_flags |= AMDGPU_VM_MTYPE_NC;
-		} else {
-			mapping_flags |= coherent ?
-				AMDGPU_VM_MTYPE_UC : AMDGPU_VM_MTYPE_NC;
-		}
+		mapping_flags |= AMDGPU_VM_MTYPE_NC;
 		break;
 	default:
 		mapping_flags |= coherent ?
@@ -2390,15 +2383,17 @@ svm_range_add_list_work(struct svm_range_list *svms, struct svm_range *prange,
 		    prange->work_item.op != SVM_OP_UNMAP_RANGE)
 			prange->work_item.op = op;
 	} else {
-		prange->work_item.op = op;
-
-		/* Pairs with mmput in deferred_list_work */
-		mmget(mm);
-		prange->work_item.mm = mm;
-		list_add_tail(&prange->deferred_list,
-			      &prange->svms->deferred_range_list);
-		pr_debug("add prange 0x%p [0x%lx 0x%lx] to work list op %d\n",
-			 prange, prange->start, prange->last, op);
+		/* Pairs with mmput in deferred_list_work.
+		 * If process is exiting and mm is gone, don't update mmu notifier.
+		 */
+		if (mmget_not_zero(mm)) {
+			prange->work_item.mm = mm;
+			prange->work_item.op = op;
+			list_add_tail(&prange->deferred_list,
+				      &prange->svms->deferred_range_list);
+			pr_debug("add prange 0x%p [0x%lx 0x%lx] to work list op %d\n",
+				 prange, prange->start, prange->last, op);
+		}
 	}
 	spin_unlock(&svms->deferred_list_lock);
 }
@@ -2412,8 +2407,7 @@ void schedule_deferred_list_work(struct svm_range_list *svms)
 }
 
 static void
-svm_range_unmap_split(struct mm_struct *mm, struct svm_range *parent,
-		      struct svm_range *prange, unsigned long start,
+svm_range_unmap_split(struct svm_range *parent, struct svm_range *prange, unsigned long start,
 		      unsigned long last)
 {
 	struct svm_range *head;
@@ -2434,12 +2428,12 @@ svm_range_unmap_split(struct mm_struct *mm, struct svm_range *parent,
 		svm_range_split(tail, last + 1, tail->last, &head);
 
 	if (head != prange && tail != prange) {
-		svm_range_add_child(parent, mm, head, SVM_OP_UNMAP_RANGE);
-		svm_range_add_child(parent, mm, tail, SVM_OP_ADD_RANGE);
+		svm_range_add_child(parent, head, SVM_OP_UNMAP_RANGE);
+		svm_range_add_child(parent, tail, SVM_OP_ADD_RANGE);
 	} else if (tail != prange) {
-		svm_range_add_child(parent, mm, tail, SVM_OP_UNMAP_RANGE);
+		svm_range_add_child(parent, tail, SVM_OP_UNMAP_RANGE);
 	} else if (head != prange) {
-		svm_range_add_child(parent, mm, head, SVM_OP_UNMAP_RANGE);
+		svm_range_add_child(parent, head, SVM_OP_UNMAP_RANGE);
 	} else if (parent != prange) {
 		prange->work_item.op = SVM_OP_UNMAP_RANGE;
 	}
@@ -2516,14 +2510,14 @@ svm_range_unmap_from_cpu(struct mm_struct *mm, struct svm_range *prange,
 		l = min(last, pchild->last);
 		if (l >= s)
 			svm_range_unmap_from_gpus(pchild, s, l, trigger);
-		svm_range_unmap_split(mm, prange, pchild, start, last);
+		svm_range_unmap_split(prange, pchild, start, last);
 		mutex_unlock(&pchild->lock);
 	}
 	s = max(start, prange->start);
 	l = min(last, prange->last);
 	if (l >= s)
 		svm_range_unmap_from_gpus(prange, s, l, trigger);
-	svm_range_unmap_split(mm, prange, prange, start, last);
+	svm_range_unmap_split(prange, prange, start, last);
 
 	if (unmap_parent)
 		svm_range_add_list_work(svms, prange, mm, SVM_OP_UNMAP_RANGE);
@@ -2566,8 +2560,6 @@ svm_range_cpu_invalidate_pagetables(struct mmu_interval_notifier *mni,
 
 	if (range->event == MMU_NOTIFY_RELEASE)
 		return true;
-	if (!mmget_not_zero(mni->mm))
-		return true;
 
 	start = mni->interval_tree.start;
 	last = mni->interval_tree.last;
@@ -2594,7 +2586,6 @@ svm_range_cpu_invalidate_pagetables(struct mmu_interval_notifier *mni,
 	}
 
 	svm_range_unlock(prange);
-	mmput(mni->mm);
 
 	return true;
 }
@@ -2998,19 +2989,6 @@ svm_range_restore_pages(struct amdgpu_device *adev, unsigned int pasid,
 		goto out;
 	}
 
-	/* check if this page fault time stamp is before svms->checkpoint_ts */
-	if (svms->checkpoint_ts[gpuidx] != 0) {
-		if (amdgpu_ih_ts_after(ts,  svms->checkpoint_ts[gpuidx])) {
-			pr_debug("draining retry fault, drop fault 0x%llx\n", addr);
-			r = 0;
-			goto out;
-		} else
-			/* ts is after svms->checkpoint_ts now, reset svms->checkpoint_ts
-			 * to zero to avoid following ts wrap around give wrong comparing
-			 */
-			svms->checkpoint_ts[gpuidx] = 0;
-	}
-
 	if (!p->xnack_enabled) {
 		pr_debug("XNACK not enabled for pasid 0x%x\n", pasid);
 		r = -EFAULT;
@@ -3030,6 +3008,21 @@ svm_range_restore_pages(struct amdgpu_device *adev, unsigned int pasid,
 	mmap_read_lock(mm);
 retry_write_locked:
 	mutex_lock(&svms->lock);
+
+	/* check if this page fault time stamp is before svms->checkpoint_ts */
+	if (svms->checkpoint_ts[gpuidx] != 0) {
+		if (amdgpu_ih_ts_after_or_equal(ts,  svms->checkpoint_ts[gpuidx])) {
+			pr_debug("draining retry fault, drop fault 0x%llx\n", addr);
+			r = -EAGAIN;
+			goto out_unlock_svms;
+		} else {
+			/* ts is after svms->checkpoint_ts now, reset svms->checkpoint_ts
+			 * to zero to avoid following ts wrap around give wrong comparing
+			 */
+			svms->checkpoint_ts[gpuidx] = 0;
+		}
+	}
+
 	prange = svm_range_from_addr(svms, addr, NULL);
 	if (!prange) {
 		pr_debug("failed to find prange svms 0x%p address [0x%llx]\n",
@@ -3154,7 +3147,8 @@ out_unlock_svms:
 	mutex_unlock(&svms->lock);
 	mmap_read_unlock(mm);
 
-	svm_range_count_fault(node, p, gpuidx);
+	if (r != -EAGAIN)
+		svm_range_count_fault(node, p, gpuidx);
 
 	mmput(mm);
 out:
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
index 3871591c9aec..82da568604b6 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
@@ -1683,17 +1683,32 @@ static int fill_in_l2_l3_pcache(struct kfd_cache_properties **props_ext,
 				int cache_type, unsigned int cu_processor_id,
 				struct kfd_node *knode)
 {
-	unsigned int cu_sibling_map_mask;
+	unsigned int cu_sibling_map_mask = 0;
 	int first_active_cu;
 	int i, j, k, xcc, start, end;
 	int num_xcc = NUM_XCC(knode->xcc_mask);
 	struct kfd_cache_properties *pcache = NULL;
 	enum amdgpu_memory_partition mode;
 	struct amdgpu_device *adev = knode->adev;
+	bool found = false;
 
 	start = ffs(knode->xcc_mask) - 1;
 	end = start + num_xcc;
-	cu_sibling_map_mask = cu_info->bitmap[start][0][0];
+
+	/* To find the bitmap in the first active cu in the first
+	 * xcc, it is based on the assumption that evrey xcc must
+	 * have at least one active cu.
+	 */
+	for (i = 0; i < gfx_info->max_shader_engines && !found; i++) {
+		for (j = 0; j < gfx_info->max_sh_per_se && !found; j++) {
+			if (cu_info->bitmap[start][i % 4][j % 4]) {
+				cu_sibling_map_mask =
+					cu_info->bitmap[start][i % 4][j % 4];
+				found = true;
+			}
+		}
+	}
+
 	cu_sibling_map_mask &=
 		((1 << pcache_info[cache_type].num_cu_shared) - 1);
 	first_active_cu = ffs(cu_sibling_map_mask);
@@ -2002,10 +2017,6 @@ static void kfd_topology_set_capabilities(struct kfd_topology_device *dev)
 		dev->node_props.debug_prop |= HSA_DBG_WATCH_ADDR_MASK_LO_BIT_GFX10 |
 					HSA_DBG_WATCH_ADDR_MASK_HI_BIT;
 
-		if (KFD_GC_VERSION(dev->gpu) >= IP_VERSION(11, 0, 0))
-			dev->node_props.capability |=
-				HSA_CAP_TRAP_DEBUG_PRECISE_MEMORY_OPERATIONS_SUPPORTED;
-
 		if (KFD_GC_VERSION(dev->gpu) >= IP_VERSION(12, 0, 0))
 			dev->node_props.capability |=
 				HSA_CAP_TRAP_DEBUG_PRECISE_ALU_OPERATIONS_SUPPORTED;
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 08c58d0315de..33a3e5e28fbc 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -243,6 +243,10 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev,
 static void handle_hpd_irq_helper(struct amdgpu_dm_connector *aconnector);
 static void handle_hpd_rx_irq(void *param);
 
+static void amdgpu_dm_backlight_set_level(struct amdgpu_display_manager *dm,
+					 int bl_idx,
+					 u32 user_brightness);
+
 static bool
 is_timing_unchanged_for_freesync(struct drm_crtc_state *old_crtc_state,
 				 struct drm_crtc_state *new_crtc_state);
@@ -361,6 +365,8 @@ get_crtc_by_otg_inst(struct amdgpu_device *adev,
 static inline bool is_dc_timing_adjust_needed(struct dm_crtc_state *old_state,
 					      struct dm_crtc_state *new_state)
 {
+	if (new_state->stream->adjust.timing_adjust_pending)
+		return true;
 	if (new_state->freesync_config.state ==  VRR_STATE_ACTIVE_FIXED)
 		return true;
 	else if (amdgpu_dm_crtc_vrr_active(old_state) != amdgpu_dm_crtc_vrr_active(new_state))
@@ -1036,8 +1042,10 @@ static int amdgpu_dm_audio_component_get_eld(struct device *kdev, int port,
 			continue;
 
 		*enabled = true;
+		mutex_lock(&connector->eld_mutex);
 		ret = drm_eld_size(connector->eld);
 		memcpy(buf, connector->eld, min(max_bytes, ret));
+		mutex_unlock(&connector->eld_mutex);
 
 		break;
 	}
@@ -1591,75 +1599,151 @@ static bool dm_should_disable_stutter(struct pci_dev *pdev)
 	return false;
 }
 
-static const struct dmi_system_id hpd_disconnect_quirk_table[] = {
+struct amdgpu_dm_quirks {
+	bool aux_hpd_discon;
+	bool support_edp0_on_dp1;
+};
+
+static struct amdgpu_dm_quirks quirk_entries = {
+	.aux_hpd_discon = false,
+	.support_edp0_on_dp1 = false
+};
+
+static int edp0_on_dp1_callback(const struct dmi_system_id *id)
+{
+	quirk_entries.support_edp0_on_dp1 = true;
+	return 0;
+}
+
+static int aux_hpd_discon_callback(const struct dmi_system_id *id)
+{
+	quirk_entries.aux_hpd_discon = true;
+	return 0;
+}
+
+static const struct dmi_system_id dmi_quirk_table[] = {
 	{
+		.callback = aux_hpd_discon_callback,
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
 			DMI_MATCH(DMI_PRODUCT_NAME, "Precision 3660"),
 		},
 	},
 	{
+		.callback = aux_hpd_discon_callback,
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
 			DMI_MATCH(DMI_PRODUCT_NAME, "Precision 3260"),
 		},
 	},
 	{
+		.callback = aux_hpd_discon_callback,
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
 			DMI_MATCH(DMI_PRODUCT_NAME, "Precision 3460"),
 		},
 	},
 	{
+		.callback = aux_hpd_discon_callback,
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
 			DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex Tower Plus 7010"),
 		},
 	},
 	{
+		.callback = aux_hpd_discon_callback,
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
 			DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex Tower 7010"),
 		},
 	},
 	{
+		.callback = aux_hpd_discon_callback,
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
 			DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex SFF Plus 7010"),
 		},
 	},
 	{
+		.callback = aux_hpd_discon_callback,
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
 			DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex SFF 7010"),
 		},
 	},
 	{
+		.callback = aux_hpd_discon_callback,
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
 			DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex Micro Plus 7010"),
 		},
 	},
 	{
+		.callback = aux_hpd_discon_callback,
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
 			DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex Micro 7010"),
 		},
 	},
+	{
+		.callback = edp0_on_dp1_callback,
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "HP"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "HP Elite mt645 G8 Mobile Thin Client"),
+		},
+	},
+	{
+		.callback = edp0_on_dp1_callback,
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "HP"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "HP EliteBook 645 14 inch G11 Notebook PC"),
+		},
+	},
+	{
+		.callback = edp0_on_dp1_callback,
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "HP"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "HP EliteBook 665 16 inch G11 Notebook PC"),
+		},
+	},
+	{
+		.callback = edp0_on_dp1_callback,
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "HP"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "HP ProBook 445 14 inch G11 Notebook PC"),
+		},
+	},
+	{
+		.callback = edp0_on_dp1_callback,
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "HP"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "HP ProBook 465 16 inch G11 Notebook PC"),
+		},
+	},
 	{}
 	/* TODO: refactor this from a fixed table to a dynamic option */
 };
 
-static void retrieve_dmi_info(struct amdgpu_display_manager *dm)
+static void retrieve_dmi_info(struct amdgpu_display_manager *dm, struct dc_init_data *init_data)
 {
-	const struct dmi_system_id *dmi_id;
+	int dmi_id;
+	struct drm_device *dev = dm->ddev;
 
 	dm->aux_hpd_discon_quirk = false;
+	init_data->flags.support_edp0_on_dp1 = false;
+
+	dmi_id = dmi_check_system(dmi_quirk_table);
+
+	if (!dmi_id)
+		return;
 
-	dmi_id = dmi_first_match(hpd_disconnect_quirk_table);
-	if (dmi_id) {
+	if (quirk_entries.aux_hpd_discon) {
 		dm->aux_hpd_discon_quirk = true;
-		DRM_INFO("aux_hpd_discon_quirk attached\n");
+		drm_info(dev, "aux_hpd_discon_quirk attached\n");
+	}
+	if (quirk_entries.support_edp0_on_dp1) {
+		init_data->flags.support_edp0_on_dp1 = true;
+		drm_info(dev, "support_edp0_on_dp1 attached\n");
 	}
 }
 
@@ -1805,26 +1889,6 @@ static enum dmub_ips_disable_type dm_get_default_ips_mode(
 
 	switch (amdgpu_ip_version(adev, DCE_HWIP, 0)) {
 	case IP_VERSION(3, 5, 0):
-		/*
-		 * On DCN35 systems with Z8 enabled, it's possible for IPS2 + Z8 to
-		 * cause a hard hang. A fix exists for newer PMFW.
-		 *
-		 * As a workaround, for non-fixed PMFW, force IPS1+RCG as the deepest
-		 * IPS state in all cases, except for s0ix and all displays off (DPMS),
-		 * where IPS2 is allowed.
-		 *
-		 * When checking pmfw version, use the major and minor only.
-		 */
-		if ((adev->pm.fw_version & 0x00FFFF00) < 0x005D6300)
-			ret = DMUB_IPS_RCG_IN_ACTIVE_IPS2_IN_OFF;
-		else if (amdgpu_ip_version(adev, GC_HWIP, 0) > IP_VERSION(11, 5, 0))
-			/*
-			 * Other ASICs with DCN35 that have residency issues with
-			 * IPS2 in idle.
-			 * We want them to use IPS2 only in display off cases.
-			 */
-			ret =  DMUB_IPS_RCG_IN_ACTIVE_IPS2_IN_OFF;
-		break;
 	case IP_VERSION(3, 5, 1):
 		ret =  DMUB_IPS_RCG_IN_ACTIVE_IPS2_IN_OFF;
 		break;
@@ -1967,7 +2031,7 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
 	if (amdgpu_ip_version(adev, DCE_HWIP, 0) >= IP_VERSION(3, 0, 0))
 		init_data.num_virtual_links = 1;
 
-	retrieve_dmi_info(&adev->dm);
+	retrieve_dmi_info(&adev->dm, &init_data);
 
 	if (adev->dm.bb_from_dmub)
 		init_data.bb_from_dmub = adev->dm.bb_from_dmub;
@@ -3134,16 +3198,16 @@ static void dm_gpureset_commit_state(struct dc_state *dc_state,
 	for (k = 0; k < dc_state->stream_count; k++) {
 		bundle->stream_update.stream = dc_state->streams[k];
 
-		for (m = 0; m < dc_state->stream_status->plane_count; m++) {
+		for (m = 0; m < dc_state->stream_status[k].plane_count; m++) {
 			bundle->surface_updates[m].surface =
-				dc_state->stream_status->plane_states[m];
+				dc_state->stream_status[k].plane_states[m];
 			bundle->surface_updates[m].surface->force_full_update =
 				true;
 		}
 
 		update_planes_and_stream_adapter(dm->dc,
 					 UPDATE_TYPE_FULL,
-					 dc_state->stream_status->plane_count,
+					 dc_state->stream_status[k].plane_count,
 					 dc_state->streams[k],
 					 &bundle->stream_update,
 					 bundle->surface_updates);
@@ -3170,8 +3234,7 @@ static int dm_resume(void *handle)
 	struct dm_atomic_state *dm_state = to_dm_atomic_state(dm->atomic_obj.state);
 	enum dc_connection_type new_connection_type = dc_connection_none;
 	struct dc_state *dc_state;
-	int i, r, j, ret;
-	bool need_hotplug = false;
+	int i, r, j;
 	struct dc_commit_streams_params commit_params = {};
 
 	if (dm->dc->caps.ips_support) {
@@ -3238,6 +3301,12 @@ static int dm_resume(void *handle)
 
 		mutex_unlock(&dm->dc_lock);
 
+		/* set the backlight after a reset */
+		for (i = 0; i < dm->num_of_edps; i++) {
+			if (dm->backlight_dev[i])
+				amdgpu_dm_backlight_set_level(dm, i, dm->brightness[i]);
+		}
+
 		return 0;
 	}
 	/* Recreate dc_state - DC invalidates it when setting power state to S3. */
@@ -3360,23 +3429,16 @@ static int dm_resume(void *handle)
 		    aconnector->mst_root)
 			continue;
 
-		ret = drm_dp_mst_topology_mgr_resume(&aconnector->mst_mgr, true);
-
-		if (ret < 0) {
-			dm_helpers_dp_mst_stop_top_mgr(aconnector->dc_link->ctx,
-					aconnector->dc_link);
-			need_hotplug = true;
-		}
+		drm_dp_mst_topology_queue_probe(&aconnector->mst_mgr);
 	}
 	drm_connector_list_iter_end(&iter);
 
-	if (need_hotplug)
-		drm_kms_helper_hotplug_event(ddev);
-
 	amdgpu_dm_irq_resume_late(adev);
 
 	amdgpu_dm_smu_write_watermarks_table(adev);
 
+	drm_kms_helper_hotplug_event(ddev);
+
 	return 0;
 }
 
@@ -4765,6 +4827,7 @@ amdgpu_dm_register_backlight_device(struct amdgpu_dm_connector *aconnector)
 	dm->backlight_dev[aconnector->bl_idx] =
 		backlight_device_register(bl_name, aconnector->base.kdev, dm,
 					  &amdgpu_dm_backlight_ops, &props);
+	dm->brightness[aconnector->bl_idx] = props.brightness;
 
 	if (IS_ERR(dm->backlight_dev[aconnector->bl_idx])) {
 		DRM_ERROR("DM: Backlight registration failed!\n");
@@ -4832,7 +4895,6 @@ static void setup_backlight_device(struct amdgpu_display_manager *dm,
 	aconnector->bl_idx = bl_idx;
 
 	amdgpu_dm_update_backlight_caps(dm, bl_idx);
-	dm->brightness[bl_idx] = AMDGPU_MAX_BL_LEVEL;
 	dm->backlight_link[bl_idx] = link;
 	dm->num_of_edps++;
 
@@ -5161,7 +5223,8 @@ fail:
 
 static void amdgpu_dm_destroy_drm_device(struct amdgpu_display_manager *dm)
 {
-	drm_atomic_private_obj_fini(&dm->atomic_obj);
+	if (dm->atomic_obj.state)
+		drm_atomic_private_obj_fini(&dm->atomic_obj);
 }
 
 /******************************************************************************
@@ -5479,9 +5542,9 @@ fill_plane_color_attributes(const struct drm_plane_state *plane_state,
 
 	case DRM_COLOR_YCBCR_BT2020:
 		if (full_range)
-			*color_space = COLOR_SPACE_2020_YCBCR;
+			*color_space = COLOR_SPACE_2020_YCBCR_FULL;
 		else
-			return -EINVAL;
+			*color_space = COLOR_SPACE_2020_YCBCR_LIMITED;
 		break;
 
 	default:
@@ -5497,8 +5560,7 @@ fill_dc_plane_info_and_addr(struct amdgpu_device *adev,
 			    const u64 tiling_flags,
 			    struct dc_plane_info *plane_info,
 			    struct dc_plane_address *address,
-			    bool tmz_surface,
-			    bool force_disable_dcc)
+			    bool tmz_surface)
 {
 	const struct drm_framebuffer *fb = plane_state->fb;
 	const struct amdgpu_framebuffer *afb =
@@ -5597,7 +5659,7 @@ fill_dc_plane_info_and_addr(struct amdgpu_device *adev,
 					   &plane_info->tiling_info,
 					   &plane_info->plane_size,
 					   &plane_info->dcc, address,
-					   tmz_surface, force_disable_dcc);
+					   tmz_surface);
 	if (ret)
 		return ret;
 
@@ -5618,7 +5680,6 @@ static int fill_dc_plane_attributes(struct amdgpu_device *adev,
 	struct dc_scaling_info scaling_info;
 	struct dc_plane_info plane_info;
 	int ret;
-	bool force_disable_dcc = false;
 
 	ret = amdgpu_dm_plane_fill_dc_scaling_info(adev, plane_state, &scaling_info);
 	if (ret)
@@ -5629,13 +5690,11 @@ static int fill_dc_plane_attributes(struct amdgpu_device *adev,
 	dc_plane_state->clip_rect = scaling_info.clip_rect;
 	dc_plane_state->scaling_quality = scaling_info.scaling_quality;
 
-	force_disable_dcc = adev->asic_type == CHIP_RAVEN && adev->in_suspend;
 	ret = fill_dc_plane_info_and_addr(adev, plane_state,
 					  afb->tiling_flags,
 					  &plane_info,
 					  &dc_plane_state->address,
-					  afb->tmz_surface,
-					  force_disable_dcc);
+					  afb->tmz_surface);
 	if (ret)
 		return ret;
 
@@ -5981,7 +6040,7 @@ get_output_color_space(const struct dc_crtc_timing *dc_crtc_timing,
 		if (dc_crtc_timing->pixel_encoding == PIXEL_ENCODING_RGB)
 			color_space = COLOR_SPACE_2020_RGB_FULLRANGE;
 		else
-			color_space = COLOR_SPACE_2020_YCBCR;
+			color_space = COLOR_SPACE_2020_YCBCR_LIMITED;
 		break;
 	case DRM_MODE_COLORIMETRY_DEFAULT: // ITU601
 	default:
@@ -7330,12 +7389,12 @@ cleanup:
 }
 
 struct dc_stream_state *
-create_validate_stream_for_sink(struct amdgpu_dm_connector *aconnector,
+create_validate_stream_for_sink(struct drm_connector *connector,
 				const struct drm_display_mode *drm_mode,
 				const struct dm_connector_state *dm_state,
 				const struct dc_stream_state *old_stream)
 {
-	struct drm_connector *connector = &aconnector->base;
+	struct amdgpu_dm_connector *aconnector = NULL;
 	struct amdgpu_device *adev = drm_to_adev(connector->dev);
 	struct dc_stream_state *stream;
 	const struct drm_connector_state *drm_state = dm_state ? &dm_state->base : NULL;
@@ -7346,8 +7405,12 @@ create_validate_stream_for_sink(struct amdgpu_dm_connector *aconnector,
 	if (!dm_state)
 		return NULL;
 
-	if (aconnector->dc_link->connector_signal == SIGNAL_TYPE_HDMI_TYPE_A ||
-	    aconnector->dc_link->dpcd_caps.dongle_type == DISPLAY_DONGLE_DP_HDMI_CONVERTER)
+	if (connector->connector_type != DRM_MODE_CONNECTOR_WRITEBACK)
+		aconnector = to_amdgpu_dm_connector(connector);
+
+	if (aconnector &&
+	    (aconnector->dc_link->connector_signal == SIGNAL_TYPE_HDMI_TYPE_A ||
+	     aconnector->dc_link->dpcd_caps.dongle_type == DISPLAY_DONGLE_DP_HDMI_CONVERTER))
 		bpc_limit = 8;
 
 	do {
@@ -7359,10 +7422,11 @@ create_validate_stream_for_sink(struct amdgpu_dm_connector *aconnector,
 			break;
 		}
 
-		if (aconnector->base.connector_type == DRM_MODE_CONNECTOR_WRITEBACK)
+		dc_result = dc_validate_stream(adev->dm.dc, stream);
+
+		if (!aconnector) /* writeback connector */
 			return stream;
 
-		dc_result = dc_validate_stream(adev->dm.dc, stream);
 		if (dc_result == DC_OK && stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST)
 			dc_result = dm_dp_mst_is_port_support_mode(aconnector, stream);
 
@@ -7392,7 +7456,7 @@ create_validate_stream_for_sink(struct amdgpu_dm_connector *aconnector,
 				     __func__, __LINE__);
 
 		aconnector->force_yuv420_output = true;
-		stream = create_validate_stream_for_sink(aconnector, drm_mode,
+		stream = create_validate_stream_for_sink(connector, drm_mode,
 						dm_state, old_stream);
 		aconnector->force_yuv420_output = false;
 	}
@@ -7407,6 +7471,9 @@ enum drm_mode_status amdgpu_dm_connector_mode_valid(struct drm_connector *connec
 	struct dc_sink *dc_sink;
 	/* TODO: Unhardcode stream count */
 	struct dc_stream_state *stream;
+	/* we always have an amdgpu_dm_connector here since we got
+	 * here via the amdgpu_dm_connector_helper_funcs
+	 */
 	struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector);
 
 	if ((mode->flags & DRM_MODE_FLAG_INTERLACE) ||
@@ -7431,7 +7498,7 @@ enum drm_mode_status amdgpu_dm_connector_mode_valid(struct drm_connector *connec
 
 	drm_mode_set_crtcinfo(mode, 0);
 
-	stream = create_validate_stream_for_sink(aconnector, mode,
+	stream = create_validate_stream_for_sink(connector, mode,
 						 to_dm_connector_state(connector->state),
 						 NULL);
 	if (stream) {
@@ -8211,7 +8278,7 @@ static int amdgpu_dm_i2c_xfer(struct i2c_adapter *i2c_adap,
 	int i;
 	int result = -EIO;
 
-	if (!ddc_service->ddc_pin || !ddc_service->ddc_pin->hw_info.hw_supported)
+	if (!ddc_service->ddc_pin)
 		return result;
 
 	cmd.payloads = kcalloc(num, sizeof(struct i2c_payload), GFP_KERNEL);
@@ -8398,14 +8465,39 @@ static void manage_dm_interrupts(struct amdgpu_device *adev,
 	int offdelay;
 
 	if (acrtc_state) {
-		if (amdgpu_ip_version(adev, DCE_HWIP, 0) <
-		    IP_VERSION(3, 5, 0) ||
-		    acrtc_state->stream->link->psr_settings.psr_version <
-		    DC_PSR_VERSION_UNSUPPORTED ||
-		    !(adev->flags & AMD_IS_APU)) {
-			timing = &acrtc_state->stream->timing;
-
-			/* at least 2 frames */
+		timing = &acrtc_state->stream->timing;
+
+		/*
+		 * Depending on when the HW latching event of double-buffered
+		 * registers happen relative to the PSR SDP deadline, and how
+		 * bad the Panel clock has drifted since the last ALPM off
+		 * event, there can be up to 3 frames of delay between sending
+		 * the PSR exit cmd to DMUB fw, and when the panel starts
+		 * displaying live frames.
+		 *
+		 * We can set:
+		 *
+		 * 20/100 * offdelay_ms = 3_frames_ms
+		 * => offdelay_ms = 5 * 3_frames_ms
+		 *
+		 * This ensures that `3_frames_ms` will only be experienced as a
+		 * 20% delay on top how long the display has been static, and
+		 * thus make the delay less perceivable.
+		 */
+		if (acrtc_state->stream->link->psr_settings.psr_version <
+		    DC_PSR_VERSION_UNSUPPORTED) {
+			offdelay = DIV64_U64_ROUND_UP((u64)5 * 3 * 10 *
+						      timing->v_total *
+						      timing->h_total,
+						      timing->pix_clk_100hz);
+			config.offdelay_ms = offdelay ?: 30;
+		} else if (amdgpu_ip_version(adev, DCE_HWIP, 0) <
+			   IP_VERSION(3, 5, 0) ||
+			   !(adev->flags & AMD_IS_APU)) {
+			/*
+			 * Older HW and DGPU have issues with instant off;
+			 * use a 2 frame offdelay.
+			 */
 			offdelay = DIV64_U64_ROUND_UP((u64)20 *
 						      timing->v_total *
 						      timing->h_total,
@@ -8413,6 +8505,8 @@ static void manage_dm_interrupts(struct amdgpu_device *adev,
 
 			config.offdelay_ms = offdelay ?: 30;
 		} else {
+			/* offdelay_ms = 0 will never disable vblank */
+			config.offdelay_ms = 1;
 			config.disable_immediate = true;
 		}
 
@@ -9061,7 +9155,7 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 			afb->tiling_flags,
 			&bundle->plane_infos[planes_count],
 			&bundle->flip_addrs[planes_count].address,
-			afb->tmz_surface, false);
+			afb->tmz_surface);
 
 		drm_dbg_state(state->dev, "plane: id=%d dcc_en=%d\n",
 				 new_plane_state->plane->index,
@@ -10424,7 +10518,7 @@ static int dm_update_crtc_state(struct amdgpu_display_manager *dm,
 		if (!drm_atomic_crtc_needs_modeset(new_crtc_state))
 			goto skip_modeset;
 
-		new_stream = create_validate_stream_for_sink(aconnector,
+		new_stream = create_validate_stream_for_sink(connector,
 							     &new_crtc_state->mode,
 							     dm_new_conn_state,
 							     dm_old_crtc_state->stream);
@@ -10667,6 +10761,9 @@ static bool should_reset_plane(struct drm_atomic_state *state,
 	    state->allow_modeset)
 		return true;
 
+	if (amdgpu_in_reset(adev) && state->allow_modeset)
+		return true;
+
 	/* Exit early if we know that we're adding or removing the plane. */
 	if (old_plane_state->crtc != new_plane_state->crtc)
 		return true;
@@ -12435,7 +12532,7 @@ int amdgpu_dm_process_dmub_aux_transfer_sync(
 		 * Transient states before tunneling is enabled could
 		 * lead to this error. We can ignore this for now.
 		 */
-		if (p_notify->result != AUX_RET_ERROR_PROTOCOL_ERROR) {
+		if (p_notify->result == AUX_RET_ERROR_PROTOCOL_ERROR) {
 			DRM_WARN("DPIA AUX failed on 0x%x(%d), error %d\n",
 					payload->address, payload->length,
 					p_notify->result);
@@ -12444,22 +12541,15 @@ int amdgpu_dm_process_dmub_aux_transfer_sync(
 		goto out;
 	}
 
+	payload->reply[0] = adev->dm.dmub_notify->aux_reply.command & 0xF;
+	if (adev->dm.dmub_notify->aux_reply.command & 0xF0)
+		/* The reply is stored in the top nibble of the command. */
+		payload->reply[0] = (adev->dm.dmub_notify->aux_reply.command >> 4) & 0xF;
 
-	payload->reply[0] = adev->dm.dmub_notify->aux_reply.command;
-	if (!payload->write && p_notify->aux_reply.length &&
-			(payload->reply[0] == AUX_TRANSACTION_REPLY_AUX_ACK)) {
-
-		if (payload->length != p_notify->aux_reply.length) {
-			DRM_WARN("invalid read length %d from DPIA AUX 0x%x(%d)!\n",
-				p_notify->aux_reply.length,
-					payload->address, payload->length);
-			*operation_result = AUX_RET_ERROR_INVALID_REPLY;
-			goto out;
-		}
-
+	/*write req may receive a byte indicating partially written number as well*/
+	if (p_notify->aux_reply.length)
 		memcpy(payload->data, p_notify->aux_reply.data,
 				p_notify->aux_reply.length);
-	}
 
 	/* success */
 	ret = p_notify->aux_reply.length;
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 a0bc2c0ac04d..9603352ee094 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
@@ -697,6 +697,8 @@ struct amdgpu_dm_connector {
 	struct drm_dp_mst_port *mst_output_port;
 	struct amdgpu_dm_connector *mst_root;
 	struct drm_dp_aux *dsc_aux;
+	uint32_t mst_local_bw;
+	uint16_t vc_full_pbn;
 	struct mutex handle_mst_msg_ready;
 
 	/* TODO see if we can merge with ddc_bus or make a dm_connector */
@@ -985,7 +987,7 @@ int amdgpu_dm_process_dmub_set_config_sync(struct dc_context *ctx, unsigned int
 					struct set_config_cmd_payload *payload, enum set_config_status *operation_result);
 
 struct dc_stream_state *
-	create_validate_stream_for_sink(struct amdgpu_dm_connector *aconnector,
+	create_validate_stream_for_sink(struct drm_connector *connector,
 					const struct drm_display_mode *drm_mode,
 					const struct dm_connector_state *dm_state,
 					const struct dc_stream_state *old_stream);
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 70fcfae8e4c5..9a31e5da3687 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
@@ -113,6 +113,7 @@ bool amdgpu_dm_crtc_vrr_active(const struct dm_crtc_state *dm_state)
  *
  * Panel Replay and PSR SU
  * - Enable when:
+ *      - VRR is disabled
  *      - vblank counter is disabled
  *      - entry is allowed: usermode demonstrates an adequate number of fast
  *        commits)
@@ -131,19 +132,20 @@ static void amdgpu_dm_crtc_set_panel_sr_feature(
 	bool is_sr_active = (link->replay_settings.replay_allow_active ||
 				 link->psr_settings.psr_allow_active);
 	bool is_crc_window_active = false;
+	bool vrr_active = amdgpu_dm_crtc_vrr_active_irq(vblank_work->acrtc);
 
 #ifdef CONFIG_DRM_AMD_SECURE_DISPLAY
 	is_crc_window_active =
 		amdgpu_dm_crc_window_is_activated(&vblank_work->acrtc->base);
 #endif
 
-	if (link->replay_settings.replay_feature_enabled &&
+	if (link->replay_settings.replay_feature_enabled && !vrr_active &&
 		allow_sr_entry && !is_sr_active && !is_crc_window_active) {
 		amdgpu_dm_replay_enable(vblank_work->stream, true);
 	} else if (vblank_enabled) {
 		if (link->psr_settings.psr_version < DC_PSR_VERSION_SU_1 && is_sr_active)
 			amdgpu_dm_psr_disable(vblank_work->stream, false);
-	} else if (link->psr_settings.psr_feature_enabled &&
+	} else if (link->psr_settings.psr_feature_enabled && !vrr_active &&
 		allow_sr_entry && !is_sr_active && !is_crc_window_active) {
 
 		struct amdgpu_dm_connector *aconn =
@@ -729,7 +731,16 @@ int amdgpu_dm_crtc_init(struct amdgpu_display_manager *dm,
 	 * support programmable degamma anywhere.
 	 */
 	is_dcn = dm->adev->dm.dc->caps.color.dpp.dcn_arch;
-	drm_crtc_enable_color_mgmt(&acrtc->base, is_dcn ? MAX_COLOR_LUT_ENTRIES : 0,
+	/* Dont't enable DRM CRTC degamma property for DCN401 since the
+	 * pre-blending degamma LUT doesn't apply to cursor, and therefore
+	 * can't work similar to a post-blending degamma LUT as in other hw
+	 * versions.
+	 * TODO: revisit it once KMS plane color API is merged.
+	 */
+	drm_crtc_enable_color_mgmt(&acrtc->base,
+				   (is_dcn &&
+				    dm->adev->dm.dc->ctx->dce_version != DCN_VERSION_4_01) ?
+				     MAX_COLOR_LUT_ENTRIES : 0,
 				   true, MAX_COLOR_LUT_ENTRIES);
 
 	drm_mode_crtc_set_gamma_size(&acrtc->base, MAX_COLOR_LEGACY_LUT_ENTRIES);
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
index 98e88903d07d..15d94d2a0e2f 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
@@ -1145,7 +1145,7 @@ static int amdgpu_current_colorspace_show(struct seq_file *m, void *data)
 	case COLOR_SPACE_2020_RGB_FULLRANGE:
 		seq_puts(m, "BT2020_RGB");
 		break;
-	case COLOR_SPACE_2020_YCBCR:
+	case COLOR_SPACE_2020_YCBCR_LIMITED:
 		seq_puts(m, "BT2020_YCC");
 		break;
 	default:
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c
index e339c7a8d541..10ba4d7bf632 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c
@@ -172,7 +172,10 @@ void hdcp_update_display(struct hdcp_workqueue *hdcp_work,
 	struct mod_hdcp_display_adjustment display_adjust;
 	unsigned int conn_index = aconnector->base.index;
 
-	mutex_lock(&hdcp_w->mutex);
+	guard(mutex)(&hdcp_w->mutex);
+	drm_connector_get(&aconnector->base);
+	if (hdcp_w->aconnector[conn_index])
+		drm_connector_put(&hdcp_w->aconnector[conn_index]->base);
 	hdcp_w->aconnector[conn_index] = aconnector;
 
 	memset(&link_adjust, 0, sizeof(link_adjust));
@@ -209,7 +212,6 @@ void hdcp_update_display(struct hdcp_workqueue *hdcp_work,
 	mod_hdcp_update_display(&hdcp_w->hdcp, conn_index, &link_adjust, &display_adjust, &hdcp_w->output);
 
 	process_output(hdcp_w);
-	mutex_unlock(&hdcp_w->mutex);
 }
 
 static void hdcp_remove_display(struct hdcp_workqueue *hdcp_work,
@@ -220,8 +222,7 @@ static void hdcp_remove_display(struct hdcp_workqueue *hdcp_work,
 	struct drm_connector_state *conn_state = aconnector->base.state;
 	unsigned int conn_index = aconnector->base.index;
 
-	mutex_lock(&hdcp_w->mutex);
-	hdcp_w->aconnector[conn_index] = aconnector;
+	guard(mutex)(&hdcp_w->mutex);
 
 	/* the removal of display will invoke auth reset -> hdcp destroy and
 	 * we'd expect the Content Protection (CP) property changed back to
@@ -237,9 +238,11 @@ static void hdcp_remove_display(struct hdcp_workqueue *hdcp_work,
 	}
 
 	mod_hdcp_remove_display(&hdcp_w->hdcp, aconnector->base.index, &hdcp_w->output);
-
+	if (hdcp_w->aconnector[conn_index]) {
+		drm_connector_put(&hdcp_w->aconnector[conn_index]->base);
+		hdcp_w->aconnector[conn_index] = NULL;
+	}
 	process_output(hdcp_w);
-	mutex_unlock(&hdcp_w->mutex);
 }
 
 void hdcp_reset_display(struct hdcp_workqueue *hdcp_work, unsigned int link_index)
@@ -247,7 +250,7 @@ void hdcp_reset_display(struct hdcp_workqueue *hdcp_work, unsigned int link_inde
 	struct hdcp_workqueue *hdcp_w = &hdcp_work[link_index];
 	unsigned int conn_index;
 
-	mutex_lock(&hdcp_w->mutex);
+	guard(mutex)(&hdcp_w->mutex);
 
 	mod_hdcp_reset_connection(&hdcp_w->hdcp,  &hdcp_w->output);
 
@@ -256,11 +259,13 @@ void hdcp_reset_display(struct hdcp_workqueue *hdcp_work, unsigned int link_inde
 	for (conn_index = 0; conn_index < AMDGPU_DM_MAX_DISPLAY_INDEX; conn_index++) {
 		hdcp_w->encryption_status[conn_index] =
 			MOD_HDCP_ENCRYPTION_STATUS_HDCP_OFF;
+		if (hdcp_w->aconnector[conn_index]) {
+			drm_connector_put(&hdcp_w->aconnector[conn_index]->base);
+			hdcp_w->aconnector[conn_index] = NULL;
+		}
 	}
 
 	process_output(hdcp_w);
-
-	mutex_unlock(&hdcp_w->mutex);
 }
 
 void hdcp_handle_cpirq(struct hdcp_workqueue *hdcp_work, unsigned int link_index)
@@ -277,7 +282,7 @@ static void event_callback(struct work_struct *work)
 	hdcp_work = container_of(to_delayed_work(work), struct hdcp_workqueue,
 				 callback_dwork);
 
-	mutex_lock(&hdcp_work->mutex);
+	guard(mutex)(&hdcp_work->mutex);
 
 	cancel_delayed_work(&hdcp_work->callback_dwork);
 
@@ -285,8 +290,6 @@ static void event_callback(struct work_struct *work)
 			       &hdcp_work->output);
 
 	process_output(hdcp_work);
-
-	mutex_unlock(&hdcp_work->mutex);
 }
 
 static void event_property_update(struct work_struct *work)
@@ -323,7 +326,7 @@ static void event_property_update(struct work_struct *work)
 			continue;
 
 		drm_modeset_lock(&dev->mode_config.connection_mutex, NULL);
-		mutex_lock(&hdcp_work->mutex);
+		guard(mutex)(&hdcp_work->mutex);
 
 		if (conn_state->commit) {
 			ret = wait_for_completion_interruptible_timeout(&conn_state->commit->hw_done,
@@ -355,7 +358,6 @@ static void event_property_update(struct work_struct *work)
 			drm_hdcp_update_content_protection(connector,
 							   DRM_MODE_CONTENT_PROTECTION_DESIRED);
 		}
-		mutex_unlock(&hdcp_work->mutex);
 		drm_modeset_unlock(&dev->mode_config.connection_mutex);
 	}
 }
@@ -368,7 +370,7 @@ static void event_property_validate(struct work_struct *work)
 	struct amdgpu_dm_connector *aconnector;
 	unsigned int conn_index;
 
-	mutex_lock(&hdcp_work->mutex);
+	guard(mutex)(&hdcp_work->mutex);
 
 	for (conn_index = 0; conn_index < AMDGPU_DM_MAX_DISPLAY_INDEX;
 	     conn_index++) {
@@ -408,8 +410,6 @@ static void event_property_validate(struct work_struct *work)
 			schedule_work(&hdcp_work->property_update_work);
 		}
 	}
-
-	mutex_unlock(&hdcp_work->mutex);
 }
 
 static void event_watchdog_timer(struct work_struct *work)
@@ -420,7 +420,7 @@ static void event_watchdog_timer(struct work_struct *work)
 				 struct hdcp_workqueue,
 				      watchdog_timer_dwork);
 
-	mutex_lock(&hdcp_work->mutex);
+	guard(mutex)(&hdcp_work->mutex);
 
 	cancel_delayed_work(&hdcp_work->watchdog_timer_dwork);
 
@@ -429,8 +429,6 @@ static void event_watchdog_timer(struct work_struct *work)
 			       &hdcp_work->output);
 
 	process_output(hdcp_work);
-
-	mutex_unlock(&hdcp_work->mutex);
 }
 
 static void event_cpirq(struct work_struct *work)
@@ -439,13 +437,11 @@ static void event_cpirq(struct work_struct *work)
 
 	hdcp_work = container_of(work, struct hdcp_workqueue, cpirq_work);
 
-	mutex_lock(&hdcp_work->mutex);
+	guard(mutex)(&hdcp_work->mutex);
 
 	mod_hdcp_process_event(&hdcp_work->hdcp, MOD_HDCP_EVENT_CPIRQ, &hdcp_work->output);
 
 	process_output(hdcp_work);
-
-	mutex_unlock(&hdcp_work->mutex);
 }
 
 void hdcp_destroy(struct kobject *kobj, struct hdcp_workqueue *hdcp_work)
@@ -455,6 +451,7 @@ void hdcp_destroy(struct kobject *kobj, struct hdcp_workqueue *hdcp_work)
 	for (i = 0; i < hdcp_work->max_link; i++) {
 		cancel_delayed_work_sync(&hdcp_work[i].callback_dwork);
 		cancel_delayed_work_sync(&hdcp_work[i].watchdog_timer_dwork);
+		cancel_delayed_work_sync(&hdcp_work[i].property_validate_dwork);
 	}
 
 	sysfs_remove_bin_file(kobj, &hdcp_work[0].attr);
@@ -478,7 +475,7 @@ static bool enable_assr(void *handle, struct dc_link *link)
 
 	dtm_cmd = (struct ta_dtm_shared_memory *)psp->dtm_context.context.mem_context.shared_buf;
 
-	mutex_lock(&psp->dtm_context.mutex);
+	guard(mutex)(&psp->dtm_context.mutex);
 	memset(dtm_cmd, 0, sizeof(struct ta_dtm_shared_memory));
 
 	dtm_cmd->cmd_id = TA_DTM_COMMAND__TOPOLOGY_ASSR_ENABLE;
@@ -493,8 +490,6 @@ static bool enable_assr(void *handle, struct dc_link *link)
 		res = false;
 	}
 
-	mutex_unlock(&psp->dtm_context.mutex);
-
 	return res;
 }
 
@@ -503,6 +498,7 @@ static void update_config(void *handle, struct cp_psp_stream_config *config)
 	struct hdcp_workqueue *hdcp_work = handle;
 	struct amdgpu_dm_connector *aconnector = config->dm_stream_ctx;
 	int link_index = aconnector->dc_link->link_index;
+	unsigned int conn_index = aconnector->base.index;
 	struct mod_hdcp_display *display = &hdcp_work[link_index].display;
 	struct mod_hdcp_link *link = &hdcp_work[link_index].link;
 	struct hdcp_workqueue *hdcp_w = &hdcp_work[link_index];
@@ -556,13 +552,14 @@ static void update_config(void *handle, struct cp_psp_stream_config *config)
 			 (!!aconnector->base.state) ?
 			 aconnector->base.state->hdcp_content_type : -1);
 
-	mutex_lock(&hdcp_w->mutex);
+	guard(mutex)(&hdcp_w->mutex);
 
 	mod_hdcp_add_display(&hdcp_w->hdcp, link, display, &hdcp_w->output);
-
+	drm_connector_get(&aconnector->base);
+	if (hdcp_w->aconnector[conn_index])
+		drm_connector_put(&hdcp_w->aconnector[conn_index]->base);
+	hdcp_w->aconnector[conn_index] = aconnector;
 	process_output(hdcp_w);
-	mutex_unlock(&hdcp_w->mutex);
-
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c
index 3390f0d8420a..a215234151ac 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c
@@ -894,6 +894,15 @@ void amdgpu_dm_hpd_init(struct amdgpu_device *adev)
 	struct drm_device *dev = adev_to_drm(adev);
 	struct drm_connector *connector;
 	struct drm_connector_list_iter iter;
+	int irq_type;
+	int i;
+
+	/* First, clear all hpd and hpdrx interrupts */
+	for (i = DC_IRQ_SOURCE_HPD1; i <= DC_IRQ_SOURCE_HPD6RX; i++) {
+		if (!dc_interrupt_set(adev->dm.dc, i, false))
+			drm_err(dev, "Failed to clear hpd(rx) source=%d on init\n",
+				i);
+	}
 
 	drm_connector_list_iter_begin(dev, &iter);
 	drm_for_each_connector_iter(connector, &iter) {
@@ -907,10 +916,31 @@ void amdgpu_dm_hpd_init(struct amdgpu_device *adev)
 
 		dc_link = amdgpu_dm_connector->dc_link;
 
+		/*
+		 * Get a base driver irq reference for hpd ints for the lifetime
+		 * of dm. Note that only hpd interrupt types are registered with
+		 * base driver; hpd_rx types aren't. IOW, amdgpu_irq_get/put on
+		 * hpd_rx isn't available. DM currently controls hpd_rx
+		 * explicitly with dc_interrupt_set()
+		 */
 		if (dc_link->irq_source_hpd != DC_IRQ_SOURCE_INVALID) {
-			dc_interrupt_set(adev->dm.dc,
-					dc_link->irq_source_hpd,
-					true);
+			irq_type = dc_link->irq_source_hpd - DC_IRQ_SOURCE_HPD1;
+			/*
+			 * TODO: There's a mismatch between mode_info.num_hpd
+			 * and what bios reports as the # of connectors with hpd
+			 * sources. Since the # of hpd source types registered
+			 * with base driver == mode_info.num_hpd, we have to
+			 * fallback to dc_interrupt_set for the remaining types.
+			 */
+			if (irq_type < adev->mode_info.num_hpd) {
+				if (amdgpu_irq_get(adev, &adev->hpd_irq, irq_type))
+					drm_err(dev, "DM_IRQ: Failed get HPD for source=%d)!\n",
+						dc_link->irq_source_hpd);
+			} else {
+				dc_interrupt_set(adev->dm.dc,
+						 dc_link->irq_source_hpd,
+						 true);
+			}
 		}
 
 		if (dc_link->irq_source_hpd_rx != DC_IRQ_SOURCE_INVALID) {
@@ -935,6 +965,7 @@ void amdgpu_dm_hpd_fini(struct amdgpu_device *adev)
 	struct drm_device *dev = adev_to_drm(adev);
 	struct drm_connector *connector;
 	struct drm_connector_list_iter iter;
+	int irq_type;
 
 	drm_connector_list_iter_begin(dev, &iter);
 	drm_for_each_connector_iter(connector, &iter) {
@@ -948,9 +979,18 @@ void amdgpu_dm_hpd_fini(struct amdgpu_device *adev)
 		dc_link = amdgpu_dm_connector->dc_link;
 
 		if (dc_link->irq_source_hpd != DC_IRQ_SOURCE_INVALID) {
-			dc_interrupt_set(adev->dm.dc,
-					dc_link->irq_source_hpd,
-					false);
+			irq_type = dc_link->irq_source_hpd - DC_IRQ_SOURCE_HPD1;
+
+			/* TODO: See same TODO in amdgpu_dm_hpd_init() */
+			if (irq_type < adev->mode_info.num_hpd) {
+				if (amdgpu_irq_put(adev, &adev->hpd_irq, irq_type))
+					drm_err(dev, "DM_IRQ: Failed put HPD for source=%d!\n",
+						dc_link->irq_source_hpd);
+			} else {
+				dc_interrupt_set(adev->dm.dc,
+						 dc_link->irq_source_hpd,
+						 false);
+			}
 		}
 
 		if (dc_link->irq_source_hpd_rx != DC_IRQ_SOURCE_INVALID) {
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
index 3d624ae6d9bd..92158009cfa7 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
@@ -51,6 +51,9 @@
 
 #define PEAK_FACTOR_X1000 1006
 
+/*
+ * This function handles both native AUX and I2C-Over-AUX transactions.
+ */
 static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux,
 				  struct drm_dp_aux_msg *msg)
 {
@@ -59,6 +62,7 @@ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux,
 	enum aux_return_code_type operation_result;
 	struct amdgpu_device *adev;
 	struct ddc_service *ddc;
+	uint8_t copy[16];
 
 	if (WARN_ON(msg->size > 16))
 		return -E2BIG;
@@ -74,6 +78,11 @@ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux,
 			(msg->request & DP_AUX_I2C_WRITE_STATUS_UPDATE) != 0;
 	payload.defer_delay = 0;
 
+	if (payload.write) {
+		memcpy(copy, msg->buffer, msg->size);
+		payload.data = copy;
+	}
+
 	result = dc_link_aux_transfer_raw(TO_DM_AUX(aux)->ddc_service, &payload,
 				      &operation_result);
 
@@ -87,15 +96,25 @@ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux,
 	if (adev->dm.aux_hpd_discon_quirk) {
 		if (msg->address == DP_SIDEBAND_MSG_DOWN_REQ_BASE &&
 			operation_result == AUX_RET_ERROR_HPD_DISCON) {
-			result = 0;
+			result = msg->size;
 			operation_result = AUX_RET_SUCCESS;
 		}
 	}
 
-	if (payload.write && result >= 0)
-		result = msg->size;
+	/*
+	 * result equals to 0 includes the cases of AUX_DEFER/I2C_DEFER
+	 */
+	if (payload.write && result >= 0) {
+		if (result) {
+			/*one byte indicating partially written bytes*/
+			drm_dbg_dp(adev_to_drm(adev), "amdgpu: AUX partially written\n");
+			result = payload.data[0];
+		} else if (!payload.reply[0])
+			/*I2C_ACK|AUX_ACK*/
+			result = msg->size;
+	}
 
-	if (result < 0)
+	if (result < 0) {
 		switch (operation_result) {
 		case AUX_RET_SUCCESS:
 			break;
@@ -114,6 +133,13 @@ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux,
 			break;
 		}
 
+		drm_dbg_dp(adev_to_drm(adev), "amdgpu: DP AUX transfer fail:%d\n", operation_result);
+	}
+
+	if (payload.reply[0])
+		drm_dbg_dp(adev_to_drm(adev), "amdgpu: AUX reply command not ACK: 0x%02x.",
+			payload.reply[0]);
+
 	return result;
 }
 
@@ -155,6 +181,17 @@ amdgpu_dm_mst_connector_late_register(struct drm_connector *connector)
 	return 0;
 }
 
+
+static inline void
+amdgpu_dm_mst_reset_mst_connector_setting(struct amdgpu_dm_connector *aconnector)
+{
+	aconnector->edid = NULL;
+	aconnector->dsc_aux = NULL;
+	aconnector->mst_output_port->passthrough_aux = NULL;
+	aconnector->mst_local_bw = 0;
+	aconnector->vc_full_pbn = 0;
+}
+
 static void
 amdgpu_dm_mst_connector_early_unregister(struct drm_connector *connector)
 {
@@ -182,9 +219,7 @@ amdgpu_dm_mst_connector_early_unregister(struct drm_connector *connector)
 
 		dc_sink_release(dc_sink);
 		aconnector->dc_sink = NULL;
-		aconnector->edid = NULL;
-		aconnector->dsc_aux = NULL;
-		port->passthrough_aux = NULL;
+		amdgpu_dm_mst_reset_mst_connector_setting(aconnector);
 	}
 
 	aconnector->mst_status = MST_STATUS_DEFAULT;
@@ -500,9 +535,7 @@ dm_dp_mst_detect(struct drm_connector *connector,
 
 		dc_sink_release(aconnector->dc_sink);
 		aconnector->dc_sink = NULL;
-		aconnector->edid = NULL;
-		aconnector->dsc_aux = NULL;
-		port->passthrough_aux = NULL;
+		amdgpu_dm_mst_reset_mst_connector_setting(aconnector);
 
 		amdgpu_dm_set_mst_status(&aconnector->mst_status,
 			MST_REMOTE_EDID | MST_ALLOCATE_NEW_PAYLOAD | MST_CLEAR_ALLOCATED_PAYLOAD,
@@ -1613,7 +1646,6 @@ int pre_validate_dsc(struct drm_atomic_state *state,
 
 		if (ind >= 0) {
 			struct drm_connector *connector;
-			struct amdgpu_dm_connector *aconnector;
 			struct drm_connector_state *drm_new_conn_state;
 			struct dm_connector_state *dm_new_conn_state;
 			struct dm_crtc_state *dm_old_crtc_state;
@@ -1621,15 +1653,14 @@ int pre_validate_dsc(struct drm_atomic_state *state,
 			connector =
 				amdgpu_dm_find_first_crtc_matching_connector(state,
 									     state->crtcs[ind].ptr);
-			aconnector = to_amdgpu_dm_connector(connector);
 			drm_new_conn_state =
 				drm_atomic_get_new_connector_state(state,
-								   &aconnector->base);
+								   connector);
 			dm_new_conn_state = to_dm_connector_state(drm_new_conn_state);
 			dm_old_crtc_state = to_dm_crtc_state(state->crtcs[ind].old_state);
 
 			local_dc_state->streams[i] =
-				create_validate_stream_for_sink(aconnector,
+				create_validate_stream_for_sink(connector,
 								&state->crtcs[ind].new_state->mode,
 								dm_new_conn_state,
 								dm_old_crtc_state->stream);
@@ -1684,16 +1715,16 @@ clean_exit:
 	return ret;
 }
 
-static unsigned int kbps_from_pbn(unsigned int pbn)
+static uint32_t kbps_from_pbn(unsigned int pbn)
 {
-	unsigned int kbps = pbn;
+	uint64_t kbps = (uint64_t)pbn;
 
 	kbps *= (1000000 / PEAK_FACTOR_X1000);
 	kbps *= 8;
 	kbps *= 54;
 	kbps /= 64;
 
-	return kbps;
+	return (uint32_t)kbps;
 }
 
 static bool is_dsc_common_config_possible(struct dc_stream_state *stream,
@@ -1815,9 +1846,18 @@ enum dc_status dm_dp_mst_is_port_support_mode(
 			struct drm_dp_mst_port *immediate_upstream_port = NULL;
 			uint32_t end_link_bw = 0;
 
-			/*Get last DP link BW capability*/
-			if (dp_get_link_current_set_bw(&aconnector->mst_output_port->aux, &end_link_bw)) {
-				if (stream_kbps > end_link_bw) {
+			/*Get last DP link BW capability. Mode shall be supported by Legacy peer*/
+			if (aconnector->mst_output_port->pdt != DP_PEER_DEVICE_DP_LEGACY_CONV &&
+				aconnector->mst_output_port->pdt != DP_PEER_DEVICE_NONE) {
+				if (aconnector->vc_full_pbn != aconnector->mst_output_port->full_pbn) {
+					dp_get_link_current_set_bw(&aconnector->mst_output_port->aux, &end_link_bw);
+					aconnector->vc_full_pbn = aconnector->mst_output_port->full_pbn;
+					aconnector->mst_local_bw = end_link_bw;
+				} else {
+					end_link_bw = aconnector->mst_local_bw;
+				}
+
+				if (end_link_bw > 0 && stream_kbps > end_link_bw) {
 					DRM_DEBUG_DRIVER("MST_DSC dsc decode at last link."
 							 "Mode required bw can't fit into last link\n");
 					return DC_FAIL_BANDWIDTH_VALIDATE;
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
index 495e3cd70426..62e30942f735 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
@@ -275,8 +275,11 @@ static int amdgpu_dm_plane_validate_dcc(struct amdgpu_device *adev,
 	if (!dcc->enable)
 		return 0;
 
-	if (format >= SURFACE_PIXEL_FORMAT_VIDEO_BEGIN ||
-	    !dc->cap_funcs.get_dcc_compression_cap)
+	if (adev->family < AMDGPU_FAMILY_GC_12_0_0 &&
+	    format >= SURFACE_PIXEL_FORMAT_VIDEO_BEGIN)
+		return -EINVAL;
+
+	if (!dc->cap_funcs.get_dcc_compression_cap)
 		return -EINVAL;
 
 	input.format = format;
@@ -309,8 +312,7 @@ static int amdgpu_dm_plane_fill_gfx9_plane_attributes_from_modifiers(struct amdg
 								     const struct plane_size *plane_size,
 								     union dc_tiling_info *tiling_info,
 								     struct dc_plane_dcc_param *dcc,
-								     struct dc_plane_address *address,
-								     const bool force_disable_dcc)
+								     struct dc_plane_address *address)
 {
 	const uint64_t modifier = afb->base.modifier;
 	int ret = 0;
@@ -318,7 +320,7 @@ static int amdgpu_dm_plane_fill_gfx9_plane_attributes_from_modifiers(struct amdg
 	amdgpu_dm_plane_fill_gfx9_tiling_info_from_modifier(adev, tiling_info, modifier);
 	tiling_info->gfx9.swizzle = amdgpu_dm_plane_modifier_gfx9_swizzle_mode(modifier);
 
-	if (amdgpu_dm_plane_modifier_has_dcc(modifier) && !force_disable_dcc) {
+	if (amdgpu_dm_plane_modifier_has_dcc(modifier)) {
 		uint64_t dcc_address = afb->address + afb->base.offsets[1];
 		bool independent_64b_blks = AMD_FMT_MOD_GET(DCC_INDEPENDENT_64B, modifier);
 		bool independent_128b_blks = AMD_FMT_MOD_GET(DCC_INDEPENDENT_128B, modifier);
@@ -360,8 +362,7 @@ static int amdgpu_dm_plane_fill_gfx12_plane_attributes_from_modifiers(struct amd
 								      const struct plane_size *plane_size,
 								      union dc_tiling_info *tiling_info,
 								      struct dc_plane_dcc_param *dcc,
-								      struct dc_plane_address *address,
-								      const bool force_disable_dcc)
+								      struct dc_plane_address *address)
 {
 	const uint64_t modifier = afb->base.modifier;
 	int ret = 0;
@@ -371,7 +372,7 @@ static int amdgpu_dm_plane_fill_gfx12_plane_attributes_from_modifiers(struct amd
 
 	tiling_info->gfx9.swizzle = amdgpu_dm_plane_modifier_gfx9_swizzle_mode(modifier);
 
-	if (amdgpu_dm_plane_modifier_has_dcc(modifier) && !force_disable_dcc) {
+	if (amdgpu_dm_plane_modifier_has_dcc(modifier)) {
 		int max_compressed_block = AMD_FMT_MOD_GET(DCC_MAX_COMPRESSED_BLOCK, modifier);
 
 		dcc->enable = 1;
@@ -839,8 +840,7 @@ int amdgpu_dm_plane_fill_plane_buffer_attributes(struct amdgpu_device *adev,
 			     struct plane_size *plane_size,
 			     struct dc_plane_dcc_param *dcc,
 			     struct dc_plane_address *address,
-			     bool tmz_surface,
-			     bool force_disable_dcc)
+			     bool tmz_surface)
 {
 	const struct drm_framebuffer *fb = &afb->base;
 	int ret;
@@ -900,16 +900,14 @@ int amdgpu_dm_plane_fill_plane_buffer_attributes(struct amdgpu_device *adev,
 		ret = amdgpu_dm_plane_fill_gfx12_plane_attributes_from_modifiers(adev, afb, format,
 										 rotation, plane_size,
 										 tiling_info, dcc,
-										 address,
-										 force_disable_dcc);
+										 address);
 		if (ret)
 			return ret;
 	} else if (adev->family >= AMDGPU_FAMILY_AI) {
 		ret = amdgpu_dm_plane_fill_gfx9_plane_attributes_from_modifiers(adev, afb, format,
 										rotation, plane_size,
 										tiling_info, dcc,
-										address,
-										force_disable_dcc);
+										address);
 		if (ret)
 			return ret;
 	} else {
@@ -1000,14 +998,13 @@ static int amdgpu_dm_plane_helper_prepare_fb(struct drm_plane *plane,
 	    dm_plane_state_old->dc_state != dm_plane_state_new->dc_state) {
 		struct dc_plane_state *plane_state =
 			dm_plane_state_new->dc_state;
-		bool force_disable_dcc = !plane_state->dcc.enable;
 
 		amdgpu_dm_plane_fill_plane_buffer_attributes(
 			adev, afb, plane_state->format, plane_state->rotation,
 			afb->tiling_flags,
 			&plane_state->tiling_info, &plane_state->plane_size,
 			&plane_state->dcc, &plane_state->address,
-			afb->tmz_surface, force_disable_dcc);
+			afb->tmz_surface);
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.h
index 6498359bff6f..2eef13b1c05a 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.h
@@ -51,8 +51,7 @@ int amdgpu_dm_plane_fill_plane_buffer_attributes(struct amdgpu_device *adev,
 				 struct plane_size *plane_size,
 				 struct dc_plane_dcc_param *dcc,
 				 struct dc_plane_address *address,
-				 bool tmz_surface,
-				 bool force_disable_dcc);
+				 bool tmz_surface);
 
 int amdgpu_dm_plane_init(struct amdgpu_display_manager *dm,
 			 struct drm_plane *plane,
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c
index 45858bf1523d..d63038ec4ec7 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c
@@ -54,7 +54,8 @@ static bool link_supports_psrsu(struct dc_link *link)
 	if (amdgpu_dc_debug_mask & DC_DISABLE_PSR_SU)
 		return false;
 
-	return dc_dmub_check_min_version(dc->ctx->dmub_srv->dmub);
+	/* Temporarily disable PSR-SU to avoid glitches */
+	return false;
 }
 
 /*
@@ -126,8 +127,10 @@ bool amdgpu_dm_link_setup_psr(struct dc_stream_state *stream)
 		psr_config.allow_multi_disp_optimizations =
 			(amdgpu_dc_feature_mask & DC_PSR_ALLOW_MULTI_DISP_OPT);
 
-		if (!psr_su_set_dsc_slice_height(dc, link, stream, &psr_config))
-			return false;
+		if (link->psr_settings.psr_version == DC_PSR_VERSION_SU_1) {
+			if (!psr_su_set_dsc_slice_height(dc, link, stream, &psr_config))
+				return false;
+		}
 
 		ret = dc_link_setup_psr(link, stream, &psr_config, &psr_context);
 
diff --git a/drivers/gpu/drm/amd/display/dc/basics/dc_common.c b/drivers/gpu/drm/amd/display/dc/basics/dc_common.c
index b2fc4f8e6482..a51c2701da24 100644
--- a/drivers/gpu/drm/amd/display/dc/basics/dc_common.c
+++ b/drivers/gpu/drm/amd/display/dc/basics/dc_common.c
@@ -40,7 +40,8 @@ bool is_rgb_cspace(enum dc_color_space output_color_space)
 	case COLOR_SPACE_YCBCR709:
 	case COLOR_SPACE_YCBCR601_LIMITED:
 	case COLOR_SPACE_YCBCR709_LIMITED:
-	case COLOR_SPACE_2020_YCBCR:
+	case COLOR_SPACE_2020_YCBCR_LIMITED:
+	case COLOR_SPACE_2020_YCBCR_FULL:
 		return false;
 	default:
 		/* Add a case to switch */
diff --git a/drivers/gpu/drm/amd/display/dc/bios/command_table2.c b/drivers/gpu/drm/amd/display/dc/bios/command_table2.c
index 7d18f372ce7a..6bc59b7ef007 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/command_table2.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/command_table2.c
@@ -101,7 +101,6 @@ static void init_dig_encoder_control(struct bios_parser *bp)
 		bp->cmd_tbl.dig_encoder_control = encoder_control_digx_v1_5;
 		break;
 	default:
-		dm_output_to_console("Don't have dig_encoder_control for v%d\n", version);
 		bp->cmd_tbl.dig_encoder_control = encoder_control_fallback;
 		break;
 	}
@@ -238,7 +237,6 @@ static void init_transmitter_control(struct bios_parser *bp)
 		bp->cmd_tbl.transmitter_control = transmitter_control_v1_7;
 		break;
 	default:
-		dm_output_to_console("Don't have transmitter_control for v%d\n", crev);
 		bp->cmd_tbl.transmitter_control = transmitter_control_fallback;
 		break;
 	}
@@ -408,8 +406,6 @@ static void init_set_pixel_clock(struct bios_parser *bp)
 		bp->cmd_tbl.set_pixel_clock = set_pixel_clock_v7;
 		break;
 	default:
-		dm_output_to_console("Don't have set_pixel_clock for v%d\n",
-			 BIOS_CMD_TABLE_PARA_REVISION(setpixelclock));
 		bp->cmd_tbl.set_pixel_clock = set_pixel_clock_fallback;
 		break;
 	}
@@ -554,7 +550,6 @@ static void init_set_crtc_timing(struct bios_parser *bp)
 			set_crtc_using_dtd_timing_v3;
 		break;
 	default:
-		dm_output_to_console("Don't have set_crtc_timing for v%d\n", dtd_version);
 		bp->cmd_tbl.set_crtc_timing = NULL;
 		break;
 	}
@@ -671,8 +666,6 @@ static void init_enable_crtc(struct bios_parser *bp)
 		bp->cmd_tbl.enable_crtc = enable_crtc_v1;
 		break;
 	default:
-		dm_output_to_console("Don't have enable_crtc for v%d\n",
-			 BIOS_CMD_TABLE_PARA_REVISION(enablecrtc));
 		bp->cmd_tbl.enable_crtc = NULL;
 		break;
 	}
@@ -864,8 +857,6 @@ static void init_set_dce_clock(struct bios_parser *bp)
 		bp->cmd_tbl.set_dce_clock = set_dce_clock_v2_1;
 		break;
 	default:
-		dm_output_to_console("Don't have set_dce_clock for v%d\n",
-			 BIOS_CMD_TABLE_PARA_REVISION(setdceclock));
 		bp->cmd_tbl.set_dce_clock = NULL;
 		break;
 	}
diff --git a/drivers/gpu/drm/amd/display/dc/bios/command_table_helper2.c b/drivers/gpu/drm/amd/display/dc/bios/command_table_helper2.c
index 73458e295103..df8139bda142 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/command_table_helper2.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/command_table_helper2.c
@@ -87,8 +87,7 @@ bool dal_bios_parser_init_cmd_tbl_helper2(
 		return true;
 
 	default:
-		/* Unsupported DCE */
-		BREAK_TO_DEBUGGER();
+		*h = dal_cmd_tbl_helper_dce112_get_table2();
 		return false;
 	}
 }
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/Makefile b/drivers/gpu/drm/amd/display/dc/clk_mgr/Makefile
index ab1132bc896a..d9955c5d2e5e 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/Makefile
@@ -174,7 +174,7 @@ AMD_DISPLAY_FILES += $(AMD_DAL_CLK_MGR_DCN32)
 ###############################################################################
 # DCN35
 ###############################################################################
-CLK_MGR_DCN35 = dcn35_smu.o dcn35_clk_mgr.o
+CLK_MGR_DCN35 = dcn35_smu.o dcn351_clk_mgr.o dcn35_clk_mgr.o
 
 AMD_DAL_CLK_MGR_DCN35 = $(addprefix $(AMDDALPATH)/dc/clk_mgr/dcn35/,$(CLK_MGR_DCN35))
 
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c
index 0e243f4344d0..4c3e58c730b1 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c
@@ -355,8 +355,11 @@ struct clk_mgr *dc_clk_mgr_create(struct dc_context *ctx, struct pp_smu_funcs *p
 			BREAK_TO_DEBUGGER();
 			return NULL;
 		}
+		if (ctx->dce_version == DCN_VERSION_3_51)
+			dcn351_clk_mgr_construct(ctx, clk_mgr, pp_smu, dccg);
+		else
+			dcn35_clk_mgr_construct(ctx, clk_mgr, pp_smu, dccg);
 
-		dcn35_clk_mgr_construct(ctx, clk_mgr, pp_smu, dccg);
 		return &clk_mgr->base.base;
 	}
 	break;
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c
index e93df3d6222e..bc123f1884da 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c
@@ -50,12 +50,13 @@
 #include "link.h"
 
 #include "logger_types.h"
+
+
+#include "yellow_carp_offset.h"
 #undef DC_LOGGER
 #define DC_LOGGER \
 	clk_mgr->base.base.ctx->logger
 
-#include "yellow_carp_offset.h"
-
 #define regCLK1_CLK_PLL_REQ			0x0237
 #define regCLK1_CLK_PLL_REQ_BASE_IDX		0
 
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c
index 29eff386505a..91d872d6d392 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c
@@ -53,9 +53,6 @@
 
 
 #include "logger_types.h"
-#undef DC_LOGGER
-#define DC_LOGGER \
-	clk_mgr->base.base.ctx->logger
 
 
 #define MAX_INSTANCE                                        7
@@ -77,6 +74,9 @@ static const struct IP_BASE CLK_BASE = { { { { 0x00016C00, 0x02401800, 0, 0, 0,
 					{ { 0x0001B200, 0x0242DC00, 0, 0, 0, 0, 0, 0 } },
 					{ { 0x0001B400, 0x0242E000, 0, 0, 0, 0, 0, 0 } } } };
 
+#undef DC_LOGGER
+#define DC_LOGGER \
+	clk_mgr->base.base.ctx->logger
 #define regCLK1_CLK_PLL_REQ			0x0237
 #define regCLK1_CLK_PLL_REQ_BASE_IDX		0
 
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c
index a0fb4481d2f1..e4d22f74f986 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c
@@ -130,7 +130,7 @@ static void dcn315_update_clocks(struct clk_mgr *clk_mgr_base,
 	struct clk_mgr_internal *clk_mgr = TO_CLK_MGR_INTERNAL(clk_mgr_base);
 	struct dc_clocks *new_clocks = &context->bw_ctx.bw.dcn.clk;
 	struct dc *dc = clk_mgr_base->ctx->dc;
-	int display_count;
+	int display_count = 0;
 	bool update_dppclk = false;
 	bool update_dispclk = false;
 	bool dpp_clock_lowered = false;
@@ -194,8 +194,6 @@ static void dcn315_update_clocks(struct clk_mgr *clk_mgr_base,
 	// workaround: Limit dppclk to 100Mhz to avoid lower eDP panel switch to plus 4K monitor underflow.
 	if (new_clocks->dppclk_khz < MIN_DPP_DISP_CLK)
 		new_clocks->dppclk_khz = MIN_DPP_DISP_CLK;
-	if (new_clocks->dispclk_khz < MIN_DPP_DISP_CLK)
-		new_clocks->dispclk_khz = MIN_DPP_DISP_CLK;
 
 	if (should_set_clock(safe_to_lower, new_clocks->dppclk_khz, clk_mgr->base.clks.dppclk_khz)) {
 		if (clk_mgr->base.clks.dppclk_khz > new_clocks->dppclk_khz)
@@ -204,15 +202,19 @@ static void dcn315_update_clocks(struct clk_mgr *clk_mgr_base,
 		update_dppclk = true;
 	}
 
-	if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, clk_mgr_base->clks.dispclk_khz)) {
-		/* No need to apply the w/a if we haven't taken over from bios yet */
-		if (clk_mgr_base->clks.dispclk_khz)
-			dcn315_disable_otg_wa(clk_mgr_base, context, true);
+	if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, clk_mgr_base->clks.dispclk_khz) &&
+	    (new_clocks->dispclk_khz > 0 || (safe_to_lower && display_count == 0))) {
+		int requested_dispclk_khz = new_clocks->dispclk_khz;
 
+		dcn315_disable_otg_wa(clk_mgr_base, context, true);
+
+		/* Clamp the requested clock to PMFW based on their limit. */
+		if (dc->debug.min_disp_clk_khz > 0 && requested_dispclk_khz < dc->debug.min_disp_clk_khz)
+			requested_dispclk_khz = dc->debug.min_disp_clk_khz;
+
+		dcn315_smu_set_dispclk(clk_mgr, requested_dispclk_khz);
 		clk_mgr_base->clks.dispclk_khz = new_clocks->dispclk_khz;
-		dcn315_smu_set_dispclk(clk_mgr, clk_mgr_base->clks.dispclk_khz);
-		if (clk_mgr_base->clks.dispclk_khz)
-			dcn315_disable_otg_wa(clk_mgr_base, context, false);
+		dcn315_disable_otg_wa(clk_mgr_base, context, false);
 
 		update_dispclk = true;
 	}
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c
index c3e50c3aaa60..49efea0c8fcf 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c
@@ -140,7 +140,7 @@ static void dcn316_update_clocks(struct clk_mgr *clk_mgr_base,
 	struct clk_mgr_internal *clk_mgr = TO_CLK_MGR_INTERNAL(clk_mgr_base);
 	struct dc_clocks *new_clocks = &context->bw_ctx.bw.dcn.clk;
 	struct dc *dc = clk_mgr_base->ctx->dc;
-	int display_count;
+	int display_count = 0;
 	bool update_dppclk = false;
 	bool update_dispclk = false;
 	bool dpp_clock_lowered = false;
@@ -201,8 +201,6 @@ static void dcn316_update_clocks(struct clk_mgr *clk_mgr_base,
 	// workaround: Limit dppclk to 100Mhz to avoid lower eDP panel switch to plus 4K monitor underflow.
 	if (new_clocks->dppclk_khz < 100000)
 		new_clocks->dppclk_khz = 100000;
-	if (new_clocks->dispclk_khz < 100000)
-		new_clocks->dispclk_khz = 100000;
 
 	if (should_set_clock(safe_to_lower, new_clocks->dppclk_khz, clk_mgr->base.clks.dppclk_khz)) {
 		if (clk_mgr->base.clks.dppclk_khz > new_clocks->dppclk_khz)
@@ -211,11 +209,18 @@ static void dcn316_update_clocks(struct clk_mgr *clk_mgr_base,
 		update_dppclk = true;
 	}
 
-	if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, clk_mgr_base->clks.dispclk_khz)) {
+	if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, clk_mgr_base->clks.dispclk_khz) &&
+	    (new_clocks->dispclk_khz > 0 || (safe_to_lower && display_count == 0))) {
+		int requested_dispclk_khz = new_clocks->dispclk_khz;
+
 		dcn316_disable_otg_wa(clk_mgr_base, context, safe_to_lower, true);
 
+		/* Clamp the requested clock to PMFW based on their limit. */
+		if (dc->debug.min_disp_clk_khz > 0 && requested_dispclk_khz < dc->debug.min_disp_clk_khz)
+			requested_dispclk_khz = dc->debug.min_disp_clk_khz;
+
+		dcn316_smu_set_dispclk(clk_mgr, requested_dispclk_khz);
 		clk_mgr_base->clks.dispclk_khz = new_clocks->dispclk_khz;
-		dcn316_smu_set_dispclk(clk_mgr, clk_mgr_base->clks.dispclk_khz);
 		dcn316_disable_otg_wa(clk_mgr_base, context, safe_to_lower, false);
 
 		update_dispclk = true;
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn351_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn351_clk_mgr.c
new file mode 100644
index 000000000000..6a6ae618650b
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn351_clk_mgr.c
@@ -0,0 +1,140 @@
+/*
+ * Copyright 2024 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#include "core_types.h"
+#include "dcn35_clk_mgr.h"
+
+#define DCN_BASE__INST0_SEG1 0x000000C0
+#define mmCLK1_CLK_PLL_REQ 0x16E37
+
+#define mmCLK1_CLK0_DFS_CNTL 0x16E69
+#define mmCLK1_CLK1_DFS_CNTL 0x16E6C
+#define mmCLK1_CLK2_DFS_CNTL 0x16E6F
+#define mmCLK1_CLK3_DFS_CNTL 0x16E72
+#define mmCLK1_CLK4_DFS_CNTL 0x16E75
+#define mmCLK1_CLK5_DFS_CNTL 0x16E78
+
+#define mmCLK1_CLK0_CURRENT_CNT 0x16EFC
+#define mmCLK1_CLK1_CURRENT_CNT 0x16EFD
+#define mmCLK1_CLK2_CURRENT_CNT 0x16EFE
+#define mmCLK1_CLK3_CURRENT_CNT 0x16EFF
+#define mmCLK1_CLK4_CURRENT_CNT 0x16F00
+#define mmCLK1_CLK5_CURRENT_CNT 0x16F01
+
+#define mmCLK1_CLK0_BYPASS_CNTL 0x16E8A
+#define mmCLK1_CLK1_BYPASS_CNTL 0x16E93
+#define mmCLK1_CLK2_BYPASS_CNTL 0x16E9C
+#define mmCLK1_CLK3_BYPASS_CNTL 0x16EA5
+#define mmCLK1_CLK4_BYPASS_CNTL 0x16EAE
+#define mmCLK1_CLK5_BYPASS_CNTL 0x16EB7
+
+#define mmCLK1_CLK0_DS_CNTL 0x16E83
+#define mmCLK1_CLK1_DS_CNTL 0x16E8C
+#define mmCLK1_CLK2_DS_CNTL 0x16E95
+#define mmCLK1_CLK3_DS_CNTL 0x16E9E
+#define mmCLK1_CLK4_DS_CNTL 0x16EA7
+#define mmCLK1_CLK5_DS_CNTL 0x16EB0
+
+#define mmCLK1_CLK0_ALLOW_DS 0x16E84
+#define mmCLK1_CLK1_ALLOW_DS 0x16E8D
+#define mmCLK1_CLK2_ALLOW_DS 0x16E96
+#define mmCLK1_CLK3_ALLOW_DS 0x16E9F
+#define mmCLK1_CLK4_ALLOW_DS 0x16EA8
+#define mmCLK1_CLK5_ALLOW_DS 0x16EB1
+
+#define mmCLK5_spll_field_8 0x1B04B
+#define mmDENTIST_DISPCLK_CNTL 0x0124
+#define regDENTIST_DISPCLK_CNTL 0x0064
+#define regDENTIST_DISPCLK_CNTL_BASE_IDX 1
+
+#define CLK1_CLK_PLL_REQ__FbMult_int__SHIFT 0x0
+#define CLK1_CLK_PLL_REQ__PllSpineDiv__SHIFT 0xc
+#define CLK1_CLK_PLL_REQ__FbMult_frac__SHIFT 0x10
+#define CLK1_CLK_PLL_REQ__FbMult_int_MASK 0x000001FFL
+#define CLK1_CLK_PLL_REQ__PllSpineDiv_MASK 0x0000F000L
+#define CLK1_CLK_PLL_REQ__FbMult_frac_MASK 0xFFFF0000L
+
+#define CLK1_CLK2_BYPASS_CNTL__CLK2_BYPASS_SEL_MASK 0x00000007L
+
+// DENTIST_DISPCLK_CNTL
+#define DENTIST_DISPCLK_CNTL__DENTIST_DISPCLK_WDIVIDER__SHIFT 0x0
+#define DENTIST_DISPCLK_CNTL__DENTIST_DISPCLK_RDIVIDER__SHIFT 0x8
+#define DENTIST_DISPCLK_CNTL__DENTIST_DISPCLK_CHG_DONE__SHIFT 0x13
+#define DENTIST_DISPCLK_CNTL__DENTIST_DPPCLK_CHG_DONE__SHIFT 0x14
+#define DENTIST_DISPCLK_CNTL__DENTIST_DPPCLK_WDIVIDER__SHIFT 0x18
+#define DENTIST_DISPCLK_CNTL__DENTIST_DISPCLK_WDIVIDER_MASK 0x0000007FL
+#define DENTIST_DISPCLK_CNTL__DENTIST_DISPCLK_RDIVIDER_MASK 0x00007F00L
+#define DENTIST_DISPCLK_CNTL__DENTIST_DISPCLK_CHG_DONE_MASK 0x00080000L
+#define DENTIST_DISPCLK_CNTL__DENTIST_DPPCLK_CHG_DONE_MASK 0x00100000L
+#define DENTIST_DISPCLK_CNTL__DENTIST_DPPCLK_WDIVIDER_MASK 0x7F000000L
+
+#define CLK5_spll_field_8__spll_ssc_en_MASK 0x00002000L
+
+#define REG(reg) \
+	(clk_mgr->regs->reg)
+
+#define BASE_INNER(seg) DCN_BASE__INST0_SEG ## seg
+
+#define BASE(seg) BASE_INNER(seg)
+
+#define SR(reg_name)\
+		.reg_name = BASE(reg ## reg_name ## _BASE_IDX) +  \
+					reg ## reg_name
+
+#define CLK_SR_DCN35(reg_name)\
+	.reg_name = mm ## reg_name
+
+static const struct clk_mgr_registers clk_mgr_regs_dcn351 = {
+	CLK_REG_LIST_DCN35()
+};
+
+static const struct clk_mgr_shift clk_mgr_shift_dcn351 = {
+	CLK_COMMON_MASK_SH_LIST_DCN32(__SHIFT)
+};
+
+static const struct clk_mgr_mask clk_mgr_mask_dcn351 = {
+	CLK_COMMON_MASK_SH_LIST_DCN32(_MASK)
+};
+
+#define TO_CLK_MGR_DCN35(clk_mgr)\
+	container_of(clk_mgr, struct clk_mgr_dcn35, base)
+
+
+void dcn351_clk_mgr_construct(
+		struct dc_context *ctx,
+		struct clk_mgr_dcn35 *clk_mgr,
+		struct pp_smu_funcs *pp_smu,
+		struct dccg *dccg)
+{
+	/*register offset changed*/
+	clk_mgr->base.regs = &clk_mgr_regs_dcn351;
+	clk_mgr->base.clk_mgr_shift = &clk_mgr_shift_dcn351;
+	clk_mgr->base.clk_mgr_mask = &clk_mgr_mask_dcn351;
+
+	dcn35_clk_mgr_construct(ctx,  clk_mgr, pp_smu, dccg);
+
+}
+
+
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c
index 3bd0d46c1701..a4ac601a30c3 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c
@@ -36,15 +36,11 @@
 #include "dcn20/dcn20_clk_mgr.h"
 
 
-
-
 #include "reg_helper.h"
 #include "core_types.h"
 #include "dcn35_smu.h"
 #include "dm_helpers.h"
 
-/* TODO: remove this include once we ported over remaining clk mgr functions*/
-#include "dcn30/dcn30_clk_mgr.h"
 #include "dcn31/dcn31_clk_mgr.h"
 
 #include "dc_dmub_srv.h"
@@ -55,34 +51,102 @@
 #define DC_LOGGER \
 	clk_mgr->base.base.ctx->logger
 
-#define regCLK1_CLK_PLL_REQ			0x0237
-#define regCLK1_CLK_PLL_REQ_BASE_IDX		0
+#define DCN_BASE__INST0_SEG1 0x000000C0
+#define mmCLK1_CLK_PLL_REQ 0x16E37
+
+#define mmCLK1_CLK0_DFS_CNTL 0x16E69
+#define mmCLK1_CLK1_DFS_CNTL 0x16E6C
+#define mmCLK1_CLK2_DFS_CNTL 0x16E6F
+#define mmCLK1_CLK3_DFS_CNTL 0x16E72
+#define mmCLK1_CLK4_DFS_CNTL 0x16E75
+#define mmCLK1_CLK5_DFS_CNTL 0x16E78
+
+#define mmCLK1_CLK0_CURRENT_CNT 0x16EFB
+#define mmCLK1_CLK1_CURRENT_CNT 0x16EFC
+#define mmCLK1_CLK2_CURRENT_CNT 0x16EFD
+#define mmCLK1_CLK3_CURRENT_CNT 0x16EFE
+#define mmCLK1_CLK4_CURRENT_CNT 0x16EFF
+#define mmCLK1_CLK5_CURRENT_CNT 0x16F00
+
+#define mmCLK1_CLK0_BYPASS_CNTL 0x16E8A
+#define mmCLK1_CLK1_BYPASS_CNTL 0x16E93
+#define mmCLK1_CLK2_BYPASS_CNTL 0x16E9C
+#define mmCLK1_CLK3_BYPASS_CNTL 0x16EA5
+#define mmCLK1_CLK4_BYPASS_CNTL 0x16EAE
+#define mmCLK1_CLK5_BYPASS_CNTL 0x16EB7
+
+#define mmCLK1_CLK0_DS_CNTL 0x16E83
+#define mmCLK1_CLK1_DS_CNTL 0x16E8C
+#define mmCLK1_CLK2_DS_CNTL 0x16E95
+#define mmCLK1_CLK3_DS_CNTL 0x16E9E
+#define mmCLK1_CLK4_DS_CNTL 0x16EA7
+#define mmCLK1_CLK5_DS_CNTL 0x16EB0
+
+#define mmCLK1_CLK0_ALLOW_DS 0x16E84
+#define mmCLK1_CLK1_ALLOW_DS 0x16E8D
+#define mmCLK1_CLK2_ALLOW_DS 0x16E96
+#define mmCLK1_CLK3_ALLOW_DS 0x16E9F
+#define mmCLK1_CLK4_ALLOW_DS 0x16EA8
+#define mmCLK1_CLK5_ALLOW_DS 0x16EB1
+
+#define mmCLK5_spll_field_8 0x1B24B
+#define mmDENTIST_DISPCLK_CNTL 0x0124
+#define regDENTIST_DISPCLK_CNTL 0x0064
+#define regDENTIST_DISPCLK_CNTL_BASE_IDX 1
+
+#define CLK1_CLK_PLL_REQ__FbMult_int__SHIFT 0x0
+#define CLK1_CLK_PLL_REQ__PllSpineDiv__SHIFT 0xc
+#define CLK1_CLK_PLL_REQ__FbMult_frac__SHIFT 0x10
+#define CLK1_CLK_PLL_REQ__FbMult_int_MASK 0x000001FFL
+#define CLK1_CLK_PLL_REQ__PllSpineDiv_MASK 0x0000F000L
+#define CLK1_CLK_PLL_REQ__FbMult_frac_MASK 0xFFFF0000L
+
+#define CLK1_CLK2_BYPASS_CNTL__CLK2_BYPASS_SEL_MASK 0x00000007L
+#define CLK1_CLK2_BYPASS_CNTL__CLK2_BYPASS_DIV_MASK 0x000F0000L
+// DENTIST_DISPCLK_CNTL
+#define DENTIST_DISPCLK_CNTL__DENTIST_DISPCLK_WDIVIDER__SHIFT 0x0
+#define DENTIST_DISPCLK_CNTL__DENTIST_DISPCLK_RDIVIDER__SHIFT 0x8
+#define DENTIST_DISPCLK_CNTL__DENTIST_DISPCLK_CHG_DONE__SHIFT 0x13
+#define DENTIST_DISPCLK_CNTL__DENTIST_DPPCLK_CHG_DONE__SHIFT 0x14
+#define DENTIST_DISPCLK_CNTL__DENTIST_DPPCLK_WDIVIDER__SHIFT 0x18
+#define DENTIST_DISPCLK_CNTL__DENTIST_DISPCLK_WDIVIDER_MASK 0x0000007FL
+#define DENTIST_DISPCLK_CNTL__DENTIST_DISPCLK_RDIVIDER_MASK 0x00007F00L
+#define DENTIST_DISPCLK_CNTL__DENTIST_DISPCLK_CHG_DONE_MASK 0x00080000L
+#define DENTIST_DISPCLK_CNTL__DENTIST_DPPCLK_CHG_DONE_MASK 0x00100000L
+#define DENTIST_DISPCLK_CNTL__DENTIST_DPPCLK_WDIVIDER_MASK 0x7F000000L
+
+#define CLK5_spll_field_8__spll_ssc_en_MASK 0x00002000L
 
-#define CLK1_CLK_PLL_REQ__FbMult_int__SHIFT	0x0
-#define CLK1_CLK_PLL_REQ__PllSpineDiv__SHIFT	0xc
-#define CLK1_CLK_PLL_REQ__FbMult_frac__SHIFT	0x10
-#define CLK1_CLK_PLL_REQ__FbMult_int_MASK	0x000001FFL
-#define CLK1_CLK_PLL_REQ__PllSpineDiv_MASK	0x0000F000L
-#define CLK1_CLK_PLL_REQ__FbMult_frac_MASK	0xFFFF0000L
+#define SMU_VER_THRESHOLD 0x5D4A00 //93.74.0
+#undef FN
+#define FN(reg_name, field_name) \
+	clk_mgr->clk_mgr_shift->field_name, clk_mgr->clk_mgr_mask->field_name
 
-#define regCLK1_CLK2_BYPASS_CNTL			0x029c
-#define regCLK1_CLK2_BYPASS_CNTL_BASE_IDX	0
+#define REG(reg) \
+	(clk_mgr->regs->reg)
 
-#define CLK1_CLK2_BYPASS_CNTL__CLK2_BYPASS_SEL__SHIFT	0x0
-#define CLK1_CLK2_BYPASS_CNTL__CLK2_BYPASS_DIV__SHIFT	0x10
-#define CLK1_CLK2_BYPASS_CNTL__CLK2_BYPASS_SEL_MASK		0x00000007L
-#define CLK1_CLK2_BYPASS_CNTL__CLK2_BYPASS_DIV_MASK		0x000F0000L
+#define BASE_INNER(seg) DCN_BASE__INST0_SEG ## seg
 
-#define regCLK5_0_CLK5_spll_field_8				0x464b
-#define regCLK5_0_CLK5_spll_field_8_BASE_IDX	0
+#define BASE(seg) BASE_INNER(seg)
 
-#define CLK5_0_CLK5_spll_field_8__spll_ssc_en__SHIFT	0xd
-#define CLK5_0_CLK5_spll_field_8__spll_ssc_en_MASK		0x00002000L
+#define SR(reg_name)\
+		.reg_name = BASE(reg ## reg_name ## _BASE_IDX) +  \
+					reg ## reg_name
 
-#define SMU_VER_THRESHOLD 0x5D4A00 //93.74.0
+#define CLK_SR_DCN35(reg_name)\
+	.reg_name = mm ## reg_name
 
-#define REG(reg_name) \
-	(ctx->clk_reg_offsets[reg ## reg_name ## _BASE_IDX] + reg ## reg_name)
+static const struct clk_mgr_registers clk_mgr_regs_dcn35 = {
+	CLK_REG_LIST_DCN35()
+};
+
+static const struct clk_mgr_shift clk_mgr_shift_dcn35 = {
+	CLK_COMMON_MASK_SH_LIST_DCN32(__SHIFT)
+};
+
+static const struct clk_mgr_mask clk_mgr_mask_dcn35 = {
+	CLK_COMMON_MASK_SH_LIST_DCN32(_MASK)
+};
 
 #define TO_CLK_MGR_DCN35(clk_mgr)\
 	container_of(clk_mgr, struct clk_mgr_dcn35, base)
@@ -388,14 +452,19 @@ void dcn35_update_clocks(struct clk_mgr *clk_mgr_base,
 		update_dppclk = true;
 	}
 
-	if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, clk_mgr_base->clks.dispclk_khz)) {
+	if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, clk_mgr_base->clks.dispclk_khz) &&
+	    (new_clocks->dispclk_khz > 0 || (safe_to_lower && display_count == 0))) {
+		int requested_dispclk_khz = new_clocks->dispclk_khz;
+
 		dcn35_disable_otg_wa(clk_mgr_base, context, safe_to_lower, true);
 
-		if (dc->debug.min_disp_clk_khz > 0 && new_clocks->dispclk_khz < dc->debug.min_disp_clk_khz)
-			new_clocks->dispclk_khz = dc->debug.min_disp_clk_khz;
+		/* Clamp the requested clock to PMFW based on their limit. */
+		if (dc->debug.min_disp_clk_khz > 0 && requested_dispclk_khz < dc->debug.min_disp_clk_khz)
+			requested_dispclk_khz = dc->debug.min_disp_clk_khz;
 
+		dcn35_smu_set_dispclk(clk_mgr, requested_dispclk_khz);
 		clk_mgr_base->clks.dispclk_khz = new_clocks->dispclk_khz;
-		dcn35_smu_set_dispclk(clk_mgr, clk_mgr_base->clks.dispclk_khz);
+
 		dcn35_disable_otg_wa(clk_mgr_base, context, safe_to_lower, false);
 
 		update_dispclk = true;
@@ -443,7 +512,6 @@ static int get_vco_frequency_from_reg(struct clk_mgr_internal *clk_mgr)
 	struct fixed31_32 pll_req;
 	unsigned int fbmult_frac_val = 0;
 	unsigned int fbmult_int_val = 0;
-	struct dc_context *ctx = clk_mgr->base.ctx;
 
 	/*
 	 * Register value of fbmult is in 8.16 format, we are converting to 314.32
@@ -503,12 +571,12 @@ static void dcn35_dump_clk_registers(struct clk_state_registers_and_bypass *regs
 static bool dcn35_is_spll_ssc_enabled(struct clk_mgr *clk_mgr_base)
 {
 	struct clk_mgr_internal *clk_mgr = TO_CLK_MGR_INTERNAL(clk_mgr_base);
-	struct dc_context *ctx = clk_mgr->base.ctx;
+
 	uint32_t ssc_enable;
 
-	REG_GET(CLK5_0_CLK5_spll_field_8, spll_ssc_en, &ssc_enable);
+	ssc_enable = REG_READ(CLK5_spll_field_8) & CLK5_spll_field_8__spll_ssc_en_MASK;
 
-	return ssc_enable == 1;
+	return ssc_enable != 0;
 }
 
 static void init_clk_states(struct clk_mgr *clk_mgr)
@@ -633,10 +701,10 @@ static struct dcn35_ss_info_table ss_info_table = {
 
 static void dcn35_read_ss_info_from_lut(struct clk_mgr_internal *clk_mgr)
 {
-	struct dc_context *ctx = clk_mgr->base.ctx;
-	uint32_t clock_source;
+	uint32_t clock_source = 0;
+
+	clock_source = REG_READ(CLK1_CLK2_BYPASS_CNTL) & CLK1_CLK2_BYPASS_CNTL__CLK2_BYPASS_SEL_MASK;
 
-	REG_GET(CLK1_CLK2_BYPASS_CNTL, CLK2_BYPASS_SEL, &clock_source);
 	// If it's DFS mode, clock_source is 0.
 	if (dcn35_is_spll_ssc_enabled(&clk_mgr->base) && (clock_source < ARRAY_SIZE(ss_info_table.ss_percentage))) {
 		clk_mgr->dprefclk_ss_percentage = ss_info_table.ss_percentage[clock_source];
@@ -1106,6 +1174,12 @@ void dcn35_clk_mgr_construct(
 	clk_mgr->base.dprefclk_ss_divider = 1000;
 	clk_mgr->base.ss_on_dprefclk = false;
 	clk_mgr->base.dfs_ref_freq_khz = 48000;
+	if (ctx->dce_version == DCN_VERSION_3_5) {
+		clk_mgr->base.regs = &clk_mgr_regs_dcn35;
+		clk_mgr->base.clk_mgr_shift = &clk_mgr_shift_dcn35;
+		clk_mgr->base.clk_mgr_mask = &clk_mgr_mask_dcn35;
+	}
+
 
 	clk_mgr->smu_wm_set.wm_set = (struct dcn35_watermarks *)dm_helpers_allocate_gpu_mem(
 				clk_mgr->base.base.ctx,
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.h b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.h
index 1203dc605b12..a12a9bf90806 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.h
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.h
@@ -60,4 +60,8 @@ void dcn35_clk_mgr_construct(struct dc_context *ctx,
 
 void dcn35_clk_mgr_destroy(struct clk_mgr_internal *clk_mgr_int);
 
+void dcn351_clk_mgr_construct(struct dc_context *ctx,
+		struct clk_mgr_dcn35 *clk_mgr,
+		struct pp_smu_funcs *pp_smu,
+		struct dccg *dccg);
 #endif //__DCN35_CLK_MGR_H__
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn401/dcn401_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn401/dcn401_clk_mgr.c
index 8cfc5f435937..2ee034879f9f 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn401/dcn401_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn401/dcn401_clk_mgr.c
@@ -24,6 +24,8 @@
 
 #include "dml/dcn401/dcn401_fpu.h"
 
+#define DCN_BASE__INST0_SEG1                       0x000000C0
+
 #define mmCLK01_CLK0_CLK_PLL_REQ                        0x16E37
 #define mmCLK01_CLK0_CLK0_DFS_CNTL                      0x16E69
 #define mmCLK01_CLK0_CLK1_DFS_CNTL                      0x16E6C
@@ -1698,7 +1700,7 @@ struct clk_mgr_internal *dcn401_clk_mgr_construct(
 	clk_mgr->base.bw_params = kzalloc(sizeof(*clk_mgr->base.bw_params), GFP_KERNEL);
 	if (!clk_mgr->base.bw_params) {
 		BREAK_TO_DEBUGGER();
-		kfree(clk_mgr);
+		kfree(clk_mgr401);
 		return NULL;
 	}
 
@@ -1709,6 +1711,7 @@ struct clk_mgr_internal *dcn401_clk_mgr_construct(
 	if (!clk_mgr->wm_range_table) {
 		BREAK_TO_DEBUGGER();
 		kfree(clk_mgr->base.bw_params);
+		kfree(clk_mgr401);
 		return NULL;
 	}
 
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index 6d4ee8fe615c..f5d938b9504c 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -276,6 +276,7 @@ static bool create_links(
 		link->link_id.type = OBJECT_TYPE_CONNECTOR;
 		link->link_id.id = CONNECTOR_ID_VIRTUAL;
 		link->link_id.enum_id = ENUM_ID_1;
+		link->psr_settings.psr_version = DC_PSR_VERSION_UNSUPPORTED;
 		link->link_enc = kzalloc(sizeof(*link->link_enc), GFP_KERNEL);
 
 		if (!link->link_enc) {
@@ -438,9 +439,12 @@ bool dc_stream_adjust_vmin_vmax(struct dc *dc,
 	 * Don't adjust DRR while there's bandwidth optimizations pending to
 	 * avoid conflicting with firmware updates.
 	 */
-	if (dc->ctx->dce_version > DCE_VERSION_MAX)
-		if (dc->optimized_required || dc->wm_optimized_required)
+	if (dc->ctx->dce_version > DCE_VERSION_MAX) {
+		if (dc->optimized_required || dc->wm_optimized_required) {
+			stream->adjust.timing_adjust_pending = true;
 			return false;
+		}
+	}
 
 	dc_exit_ips_for_hw_access(dc);
 
@@ -452,6 +456,7 @@ bool dc_stream_adjust_vmin_vmax(struct dc *dc,
 
 	if (dc->caps.max_v_total != 0 &&
 		(adjust->v_total_max > dc->caps.max_v_total || adjust->v_total_min > dc->caps.max_v_total)) {
+		stream->adjust.timing_adjust_pending = false;
 		if (adjust->allow_otg_v_count_halt)
 			return set_long_vtotal(dc, stream, adjust);
 		else
@@ -465,7 +470,7 @@ bool dc_stream_adjust_vmin_vmax(struct dc *dc,
 			dc->hwss.set_drr(&pipe,
 					1,
 					*adjust);
-
+			stream->adjust.timing_adjust_pending = false;
 			return true;
 		}
 	}
@@ -2032,7 +2037,7 @@ static enum dc_status dc_commit_state_no_check(struct dc *dc, struct dc_state *c
 
 	dc_enable_stereo(dc, context, dc_streams, context->stream_count);
 
-	if (context->stream_count > get_seamless_boot_stream_count(context) ||
+	if (get_seamless_boot_stream_count(context) == 0 ||
 		context->stream_count == 0) {
 		/* Must wait for no flips to be pending before doing optimize bw */
 		hwss_wait_for_no_pipes_pending(dc, context);
@@ -2975,8 +2980,14 @@ static void copy_stream_update_to_stream(struct dc *dc,
 	if (update->vrr_active_fixed)
 		stream->vrr_active_fixed = *update->vrr_active_fixed;
 
-	if (update->crtc_timing_adjust)
+	if (update->crtc_timing_adjust) {
+		if (stream->adjust.v_total_min != update->crtc_timing_adjust->v_total_min ||
+			stream->adjust.v_total_max != update->crtc_timing_adjust->v_total_max ||
+			stream->adjust.timing_adjust_pending)
+			update->crtc_timing_adjust->timing_adjust_pending = true;
 		stream->adjust = *update->crtc_timing_adjust;
+		update->crtc_timing_adjust->timing_adjust_pending = false;
+	}
 
 	if (update->dpms_off)
 		stream->dpms_off = *update->dpms_off;
@@ -4734,7 +4745,8 @@ static bool full_update_required(struct dc *dc,
 			stream_update->lut3d_func ||
 			stream_update->pending_test_pattern ||
 			stream_update->crtc_timing_adjust ||
-			stream_update->scaler_sharpener_update))
+			stream_update->scaler_sharpener_update ||
+			stream_update->hw_cursor_req))
 		return true;
 
 	if (stream) {
@@ -5109,8 +5121,8 @@ bool dc_update_planes_and_stream(struct dc *dc,
 	else
 		ret = update_planes_and_stream_v2(dc, srf_updates,
 			surface_count, stream, stream_update);
-
-	if (ret)
+	if (ret && (dc->ctx->dce_version >= DCN_VERSION_3_2 ||
+		dc->ctx->dce_version == DCN_VERSION_3_01))
 		clear_update_flags(srf_updates, surface_count, stream);
 
 	return ret;
@@ -5141,7 +5153,7 @@ void dc_commit_updates_for_stream(struct dc *dc,
 		ret = update_planes_and_stream_v1(dc, srf_updates, surface_count, stream,
 				stream_update, state);
 
-	if (ret)
+	if (ret && dc->ctx->dce_version >= DCN_VERSION_3_2)
 		clear_update_flags(srf_updates, surface_count, stream);
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c
index bb766c2a7417..d62b00314682 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c
@@ -176,7 +176,7 @@ static bool is_ycbcr2020_type(
 {
 	bool ret = false;
 
-	if (color_space == COLOR_SPACE_2020_YCBCR)
+	if (color_space == COLOR_SPACE_2020_YCBCR_LIMITED || color_space == COLOR_SPACE_2020_YCBCR_FULL)
 		ret = true;
 	return ret;
 }
@@ -247,7 +247,8 @@ void color_space_to_black_color(
 	case COLOR_SPACE_YCBCR709_BLACK:
 	case COLOR_SPACE_YCBCR601_LIMITED:
 	case COLOR_SPACE_YCBCR709_LIMITED:
-	case COLOR_SPACE_2020_YCBCR:
+	case COLOR_SPACE_2020_YCBCR_LIMITED:
+	case COLOR_SPACE_2020_YCBCR_FULL:
 		*black_color = black_color_format[BLACK_COLOR_FORMAT_YUV_CV];
 		break;
 
@@ -508,6 +509,7 @@ void set_p_state_switch_method(
 	if (!dc->ctx || !dc->ctx->dmub_srv || !pipe_ctx || !vba)
 		return;
 
+	pipe_ctx->p_state_type = P_STATE_UNKNOWN;
 	if (vba->DRAMClockChangeSupport[vba->VoltageLevel][vba->maxMpcComb] !=
 			dm_dram_clock_change_unsupported) {
 		/* MCLK switching is supported */
@@ -554,6 +556,21 @@ void set_p_state_switch_method(
 	}
 }
 
+void set_drr_and_clear_adjust_pending(
+		struct pipe_ctx *pipe_ctx,
+		struct dc_stream_state *stream,
+		struct drr_params *params)
+{
+	/* params can be null.*/
+	if (pipe_ctx && pipe_ctx->stream_res.tg &&
+			pipe_ctx->stream_res.tg->funcs->set_drr)
+		pipe_ctx->stream_res.tg->funcs->set_drr(
+				pipe_ctx->stream_res.tg, params);
+
+	if (stream)
+		stream->adjust.timing_adjust_pending = false;
+}
+
 void get_fams2_visual_confirm_color(
 		struct dc *dc,
 		struct dc_state *context,
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
index d915020a4295..6dbf139c51f7 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
@@ -1455,7 +1455,8 @@ bool resource_build_scaling_params(struct pipe_ctx *pipe_ctx)
 	DC_LOGGER_INIT(pipe_ctx->stream->ctx->logger);
 
 	/* Invalid input */
-	if (!plane_state->dst_rect.width ||
+	if (!plane_state ||
+			!plane_state->dst_rect.width ||
 			!plane_state->dst_rect.height ||
 			!plane_state->src_rect.width ||
 			!plane_state->src_rect.height) {
@@ -3387,10 +3388,13 @@ static int get_norm_pix_clk(const struct dc_crtc_timing *timing)
 			break;
 		case COLOR_DEPTH_121212:
 			normalized_pix_clk = (pix_clk * 36) / 24;
-		break;
+			break;
+		case COLOR_DEPTH_141414:
+			normalized_pix_clk = (pix_clk * 42) / 24;
+			break;
 		case COLOR_DEPTH_161616:
 			normalized_pix_clk = (pix_clk * 48) / 24;
-		break;
+			break;
 		default:
 			ASSERT(0);
 		break;
@@ -4211,7 +4215,7 @@ static void set_avi_info_frame(
 		break;
 	case COLOR_SPACE_2020_RGB_FULLRANGE:
 	case COLOR_SPACE_2020_RGB_LIMITEDRANGE:
-	case COLOR_SPACE_2020_YCBCR:
+	case COLOR_SPACE_2020_YCBCR_LIMITED:
 		hdmi_info.bits.EC0_EC2 = COLORIMETRYEX_BT2020RGBYCBCR;
 		hdmi_info.bits.C0_C1   = COLORIMETRY_EXTENDED;
 		break;
@@ -4225,7 +4229,7 @@ static void set_avi_info_frame(
 		break;
 	}
 
-	if (pixel_encoding && color_space == COLOR_SPACE_2020_YCBCR &&
+	if (pixel_encoding && color_space == COLOR_SPACE_2020_YCBCR_LIMITED &&
 			stream->out_transfer_func.tf == TRANSFER_FUNCTION_GAMMA22) {
 		hdmi_info.bits.EC0_EC2 = 0;
 		hdmi_info.bits.C0_C1 = COLORIMETRY_ITU709;
diff --git a/drivers/gpu/drm/amd/display/dc/dc_dp_types.h b/drivers/gpu/drm/amd/display/dc/dc_dp_types.h
index 41bd95e9177a..223c3d55544b 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_dp_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_dp_types.h
@@ -959,6 +959,14 @@ union dp_128b_132b_supported_lttpr_link_rates {
 	uint8_t raw;
 };
 
+union dp_alpm_lttpr_cap {
+	struct {
+		uint8_t AUX_LESS_ALPM_SUPPORTED	:1;
+		uint8_t RESERVED				:7;
+	} bits;
+	uint8_t raw;
+};
+
 union dp_sink_video_fallback_formats {
 	struct {
 		uint8_t dp_1024x768_60Hz_24bpp_support	:1;
@@ -1103,6 +1111,7 @@ struct dc_lttpr_caps {
 	uint8_t max_ext_timeout;
 	union dp_main_link_channel_coding_lttpr_cap main_link_channel_coding;
 	union dp_128b_132b_supported_lttpr_link_rates supported_128b_132b_rates;
+	union dp_alpm_lttpr_cap alpm;
 	uint8_t aux_rd_interval[MAX_REPEATER_CNT - 1];
 };
 
@@ -1352,6 +1361,9 @@ struct dp_trace {
 #ifndef DPCD_MAX_UNCOMPRESSED_PIXEL_RATE_CAP
 #define DPCD_MAX_UNCOMPRESSED_PIXEL_RATE_CAP    0x221c
 #endif
+#ifndef DP_LTTPR_ALPM_CAPABILITIES
+#define DP_LTTPR_ALPM_CAPABILITIES              0xF0009
+#endif
 #ifndef DP_REPEATER_CONFIGURATION_AND_STATUS_SIZE
 #define DP_REPEATER_CONFIGURATION_AND_STATUS_SIZE	0x50
 #endif
diff --git a/drivers/gpu/drm/amd/display/dc/dc_hw_types.h b/drivers/gpu/drm/amd/display/dc/dc_hw_types.h
index c10567ec1c81..6fd94c5f6da5 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_hw_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_hw_types.h
@@ -641,7 +641,8 @@ enum dc_color_space {
 	COLOR_SPACE_YCBCR709_LIMITED,
 	COLOR_SPACE_2020_RGB_FULLRANGE,
 	COLOR_SPACE_2020_RGB_LIMITEDRANGE,
-	COLOR_SPACE_2020_YCBCR,
+	COLOR_SPACE_2020_YCBCR_LIMITED,
+	COLOR_SPACE_2020_YCBCR_FULL,
 	COLOR_SPACE_ADOBERGB,
 	COLOR_SPACE_DCIP3,
 	COLOR_SPACE_DISPLAYNATIVE,
@@ -649,6 +650,7 @@ enum dc_color_space {
 	COLOR_SPACE_APPCTRL,
 	COLOR_SPACE_CUSTOMPOINTS,
 	COLOR_SPACE_YCBCR709_BLACK,
+	COLOR_SPACE_2020_YCBCR = COLOR_SPACE_2020_YCBCR_LIMITED,
 };
 
 enum dc_dither_option {
@@ -1000,6 +1002,7 @@ struct dc_crtc_timing_adjust {
 	uint32_t v_total_mid;
 	uint32_t v_total_mid_frame_num;
 	uint32_t allow_otg_v_count_halt;
+	uint8_t timing_adjust_pending;
 };
 
 
diff --git a/drivers/gpu/drm/amd/display/dc/dc_types.h b/drivers/gpu/drm/amd/display/dc/dc_types.h
index c8bdbbba44ef..1aca9e96c474 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_types.h
@@ -1009,6 +1009,13 @@ struct psr_settings {
 	unsigned int psr_sdp_transmit_line_num_deadline;
 	uint8_t force_ffu_mode;
 	unsigned int psr_power_opt;
+
+	/**
+	 * Some panels cannot handle idle pattern during PSR entry.
+	 * To power down phy before disable stream to avoid sending
+	 * idle pattern.
+	 */
+	uint8_t power_down_phy_before_disable_stream;
 };
 
 enum replay_coasting_vtotal_type {
diff --git a/drivers/gpu/drm/amd/display/dc/dccg/dcn401/dcn401_dccg.c b/drivers/gpu/drm/amd/display/dc/dccg/dcn401/dcn401_dccg.c
index 0b889004509a..62402c7be0a5 100644
--- a/drivers/gpu/drm/amd/display/dc/dccg/dcn401/dcn401_dccg.c
+++ b/drivers/gpu/drm/amd/display/dc/dccg/dcn401/dcn401_dccg.c
@@ -580,9 +580,6 @@ static void dccg401_set_dpstreamclk(
 		int otg_inst,
 		int dp_hpo_inst)
 {
-	/* set the dtbclk_p source */
-	dccg401_set_dtbclk_p_src(dccg, src, otg_inst);
-
 	/* enabled to select one of the DTBCLKs for pipe */
 	if (src == REFCLK)
 		dccg401_disable_dpstreamclk(dccg, dp_hpo_inst);
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dce/dce_stream_encoder.c
index 5c2825bc9a87..654b919465f0 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_stream_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_stream_encoder.c
@@ -420,7 +420,7 @@ static void dce110_stream_encoder_dp_set_stream_attribute(
 			dynamic_range_rgb = 1; /*limited range*/
 			break;
 		case COLOR_SPACE_2020_RGB_FULLRANGE:
-		case COLOR_SPACE_2020_YCBCR:
+		case COLOR_SPACE_2020_YCBCR_LIMITED:
 		case COLOR_SPACE_XR_RGB:
 		case COLOR_SPACE_MSREF_SCRGB:
 		case COLOR_SPACE_ADOBERGB:
@@ -432,6 +432,7 @@ static void dce110_stream_encoder_dp_set_stream_attribute(
 		case COLOR_SPACE_APPCTRL:
 		case COLOR_SPACE_CUSTOMPOINTS:
 		case COLOR_SPACE_UNKNOWN:
+		default:
 			/* do nothing */
 			break;
 		}
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dmub_hw_lock_mgr.c b/drivers/gpu/drm/amd/display/dc/dce/dmub_hw_lock_mgr.c
index bf636b28e3e1..d37ecfdde4f1 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dmub_hw_lock_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dmub_hw_lock_mgr.c
@@ -63,11 +63,26 @@ void dmub_hw_lock_mgr_inbox0_cmd(struct dc_dmub_srv *dmub_srv,
 
 bool should_use_dmub_lock(struct dc_link *link)
 {
+	/* ASIC doesn't support DMUB */
+	if (!link->ctx->dmub_srv)
+		return false;
+
 	if (link->psr_settings.psr_version == DC_PSR_VERSION_SU_1)
 		return true;
 
 	if (link->replay_settings.replay_feature_enabled)
 		return true;
 
+	/* only use HW lock for PSR1 on single eDP */
+	if (link->psr_settings.psr_version == DC_PSR_VERSION_1) {
+		struct dc_link *edp_links[MAX_NUM_EDP];
+		int edp_num;
+
+		dc_get_edp_links(link->dc, edp_links, &edp_num);
+
+		if (edp_num == 1)
+			return true;
+	}
+
 	return false;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c b/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c
index cae18f8c1c9a..8821153d0ac3 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c
@@ -419,6 +419,10 @@ static bool dmub_psr_copy_settings(struct dmub_psr *dmub,
 	copy_settings_data->relock_delay_frame_cnt = 0;
 	if (link->dpcd_caps.sink_dev_id == DP_BRANCH_DEVICE_ID_001CF8)
 		copy_settings_data->relock_delay_frame_cnt = 2;
+
+	copy_settings_data->power_down_phy_before_disable_stream =
+		link->psr_settings.power_down_phy_before_disable_stream;
+
 	copy_settings_data->dsc_slice_height = psr_context->dsc_slice_height;
 
 	dc_wake_and_execute_dmub_cmd(dc, &cmd, DM_DMUB_WAIT_TYPE_WAIT);
diff --git a/drivers/gpu/drm/amd/display/dc/dce60/dce60_timing_generator.c b/drivers/gpu/drm/amd/display/dc/dce60/dce60_timing_generator.c
index e5fb0e8333e4..e691a1cf3356 100644
--- a/drivers/gpu/drm/amd/display/dc/dce60/dce60_timing_generator.c
+++ b/drivers/gpu/drm/amd/display/dc/dce60/dce60_timing_generator.c
@@ -239,6 +239,7 @@ static const struct timing_generator_funcs dce60_tg_funcs = {
 				dce60_timing_generator_enable_advanced_request,
 		.configure_crc = dce60_configure_crc,
 		.get_crc = dce110_get_crc,
+		.is_two_pixels_per_container = dce110_is_two_pixels_per_container,
 };
 
 void dce60_timing_generator_construct(
diff --git a/drivers/gpu/drm/amd/display/dc/dio/dcn10/dcn10_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dio/dcn10/dcn10_stream_encoder.c
index f496e952ceec..f8f1e98f646e 100644
--- a/drivers/gpu/drm/amd/display/dc/dio/dcn10/dcn10_stream_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dio/dcn10/dcn10_stream_encoder.c
@@ -393,7 +393,7 @@ void enc1_stream_encoder_dp_set_stream_attribute(
 		break;
 	case COLOR_SPACE_2020_RGB_LIMITEDRANGE:
 	case COLOR_SPACE_2020_RGB_FULLRANGE:
-	case COLOR_SPACE_2020_YCBCR:
+	case COLOR_SPACE_2020_YCBCR_LIMITED:
 	case COLOR_SPACE_XR_RGB:
 	case COLOR_SPACE_MSREF_SCRGB:
 	case COLOR_SPACE_ADOBERGB:
@@ -406,6 +406,7 @@ void enc1_stream_encoder_dp_set_stream_attribute(
 	case COLOR_SPACE_CUSTOMPOINTS:
 	case COLOR_SPACE_UNKNOWN:
 	case COLOR_SPACE_YCBCR709_BLACK:
+	default:
 		/* do nothing */
 		break;
 	}
diff --git a/drivers/gpu/drm/amd/display/dc/dio/dcn401/dcn401_dio_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dio/dcn401/dcn401_dio_stream_encoder.c
index 0a27e0942a12..0008816cf155 100644
--- a/drivers/gpu/drm/amd/display/dc/dio/dcn401/dcn401_dio_stream_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dio/dcn401/dcn401_dio_stream_encoder.c
@@ -634,7 +634,7 @@ void enc401_stream_encoder_dp_set_stream_attribute(
 		break;
 	case COLOR_SPACE_2020_RGB_LIMITEDRANGE:
 	case COLOR_SPACE_2020_RGB_FULLRANGE:
-	case COLOR_SPACE_2020_YCBCR:
+	case COLOR_SPACE_2020_YCBCR_LIMITED:
 	case COLOR_SPACE_XR_RGB:
 	case COLOR_SPACE_MSREF_SCRGB:
 	case COLOR_SPACE_ADOBERGB:
@@ -647,6 +647,7 @@ void enc401_stream_encoder_dp_set_stream_attribute(
 	case COLOR_SPACE_CUSTOMPOINTS:
 	case COLOR_SPACE_UNKNOWN:
 	case COLOR_SPACE_YCBCR709_BLACK:
+	default:
 		/* do nothing */
 		break;
 	}
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c
index 1c10ba4dcdde..abe51cf3aab2 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c
@@ -281,10 +281,10 @@ static void CalculateDynamicMetadataParameters(
 		double DISPCLK,
 		double DCFClkDeepSleep,
 		double PixelClock,
-		long HTotal,
-		long VBlank,
-		long DynamicMetadataTransmittedBytes,
-		long DynamicMetadataLinesBeforeActiveRequired,
+		unsigned int HTotal,
+		unsigned int VBlank,
+		unsigned int DynamicMetadataTransmittedBytes,
+		int DynamicMetadataLinesBeforeActiveRequired,
 		int InterlaceEnable,
 		bool ProgressiveToInterlaceUnitInOPP,
 		double *Tsetup,
@@ -3277,8 +3277,8 @@ static double CalculateWriteBackDelay(
 
 
 static void CalculateDynamicMetadataParameters(int MaxInterDCNTileRepeaters, double DPPCLK, double DISPCLK,
-		double DCFClkDeepSleep, double PixelClock, long HTotal, long VBlank, long DynamicMetadataTransmittedBytes,
-		long DynamicMetadataLinesBeforeActiveRequired, int InterlaceEnable, bool ProgressiveToInterlaceUnitInOPP,
+		double DCFClkDeepSleep, double PixelClock, unsigned int HTotal, unsigned int VBlank, unsigned int DynamicMetadataTransmittedBytes,
+		int DynamicMetadataLinesBeforeActiveRequired, int InterlaceEnable, bool ProgressiveToInterlaceUnitInOPP,
 		double *Tsetup, double *Tdmbf, double *Tdmec, double *Tdmsks)
 {
 	double TotalRepeaterDelayTime = 0;
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c
index 47d785204f29..c90dee4e9116 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c
@@ -195,9 +195,9 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_5_soc = {
 	.dcn_downspread_percent = 0.5,
 	.gpuvm_min_page_size_bytes = 4096,
 	.hostvm_min_page_size_bytes = 4096,
-	.do_urgent_latency_adjustment = 0,
+	.do_urgent_latency_adjustment = 1,
 	.urgent_latency_adjustment_fabric_clock_component_us = 0,
-	.urgent_latency_adjustment_fabric_clock_reference_mhz = 0,
+	.urgent_latency_adjustment_fabric_clock_reference_mhz = 3000,
 };
 
 void dcn35_build_wm_range_table_fpu(struct clk_mgr *clk_mgr)
@@ -367,6 +367,8 @@ void dcn35_update_bw_bounding_box_fpu(struct dc *dc,
 				clock_limits[i].socclk_mhz;
 			dc->dml2_options.bbox_overrides.clks_table.clk_entries[i].memclk_mhz =
 				clk_table->entries[i].memclk_mhz * clk_table->entries[i].wck_ratio;
+
+			dc->dml2_options.bbox_overrides.clks_table.clk_entries[i].dram_speed_mts = clock_limits[i].dram_speed_mts;
 			dc->dml2_options.bbox_overrides.clks_table.clk_entries[i].dtbclk_mhz =
 				clock_limits[i].dtbclk_mhz;
 			dc->dml2_options.bbox_overrides.clks_table.num_entries_per_clk.num_dcfclk_levels =
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn351/dcn351_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn351/dcn351_fpu.c
index a201dbb743d7..79d921adc215 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn351/dcn351_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn351/dcn351_fpu.c
@@ -401,6 +401,7 @@ void dcn351_update_bw_bounding_box_fpu(struct dc *dc,
 				clock_limits[i].socclk_mhz;
 			dc->dml2_options.bbox_overrides.clks_table.clk_entries[i].memclk_mhz =
 				clk_table->entries[i].memclk_mhz * clk_table->entries[i].wck_ratio;
+			dc->dml2_options.bbox_overrides.clks_table.clk_entries[i].dram_speed_mts = clock_limits[i].dram_speed_mts;
 			dc->dml2_options.bbox_overrides.clks_table.clk_entries[i].dtbclk_mhz =
 				clock_limits[i].dtbclk_mhz;
 			dc->dml2_options.bbox_overrides.clks_table.num_entries_per_clk.num_dcfclk_levels =
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/Makefile b/drivers/gpu/drm/amd/display/dc/dml2/Makefile
index c4378e620cbf..986a69c5bd4b 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dml2/Makefile
@@ -29,7 +29,11 @@ dml2_rcflags := $(CC_FLAGS_NO_FPU)
 
 ifneq ($(CONFIG_FRAME_WARN),0)
 ifeq ($(filter y,$(CONFIG_KASAN)$(CONFIG_KCSAN)),y)
+ifeq ($(CONFIG_CC_IS_CLANG)$(CONFIG_COMPILE_TEST),yy)
+frame_warn_flag := -Wframe-larger-than=4096
+else
 frame_warn_flag := -Wframe-larger-than=3072
+endif
 else
 frame_warn_flag := -Wframe-larger-than=2048
 endif
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c b/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c
index 8dabb1ac0b68..6822b0795120 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c
@@ -6301,9 +6301,9 @@ static void dml_prefetch_check(struct display_mode_lib_st *mode_lib)
 			mode_lib->ms.meta_row_bandwidth_this_state,
 			mode_lib->ms.dpte_row_bandwidth_this_state,
 			mode_lib->ms.NoOfDPPThisState,
-			mode_lib->ms.UrgentBurstFactorLuma,
-			mode_lib->ms.UrgentBurstFactorChroma,
-			mode_lib->ms.UrgentBurstFactorCursor);
+			mode_lib->ms.UrgentBurstFactorLuma[j],
+			mode_lib->ms.UrgentBurstFactorChroma[j],
+			mode_lib->ms.UrgentBurstFactorCursor[j]);
 
 		s->VMDataOnlyReturnBWPerState = dml_get_return_bw_mbps_vm_only(
 																	&mode_lib->ms.soc,
@@ -6434,7 +6434,7 @@ static void dml_prefetch_check(struct display_mode_lib_st *mode_lib)
 							/* Output */
 							&mode_lib->ms.UrgentBurstFactorCursorPre[k],
 							&mode_lib->ms.UrgentBurstFactorLumaPre[k],
-							&mode_lib->ms.UrgentBurstFactorChroma[k],
+							&mode_lib->ms.UrgentBurstFactorChromaPre[k],
 							&mode_lib->ms.NotUrgentLatencyHidingPre[k]);
 
 					mode_lib->ms.cursor_bw_pre[k] = mode_lib->ms.cache_display_cfg.plane.NumberOfCursors[k] * mode_lib->ms.cache_display_cfg.plane.CursorWidth[k] *
@@ -6458,9 +6458,9 @@ static void dml_prefetch_check(struct display_mode_lib_st *mode_lib)
 				mode_lib->ms.cursor_bw_pre,
 				mode_lib->ms.prefetch_vmrow_bw,
 				mode_lib->ms.NoOfDPPThisState,
-				mode_lib->ms.UrgentBurstFactorLuma,
-				mode_lib->ms.UrgentBurstFactorChroma,
-				mode_lib->ms.UrgentBurstFactorCursor,
+				mode_lib->ms.UrgentBurstFactorLuma[j],
+				mode_lib->ms.UrgentBurstFactorChroma[j],
+				mode_lib->ms.UrgentBurstFactorCursor[j],
 				mode_lib->ms.UrgentBurstFactorLumaPre,
 				mode_lib->ms.UrgentBurstFactorChromaPre,
 				mode_lib->ms.UrgentBurstFactorCursorPre,
@@ -6517,9 +6517,9 @@ static void dml_prefetch_check(struct display_mode_lib_st *mode_lib)
 						mode_lib->ms.cursor_bw,
 						mode_lib->ms.cursor_bw_pre,
 						mode_lib->ms.NoOfDPPThisState,
-						mode_lib->ms.UrgentBurstFactorLuma,
-						mode_lib->ms.UrgentBurstFactorChroma,
-						mode_lib->ms.UrgentBurstFactorCursor,
+						mode_lib->ms.UrgentBurstFactorLuma[j],
+						mode_lib->ms.UrgentBurstFactorChroma[j],
+						mode_lib->ms.UrgentBurstFactorCursor[j],
 						mode_lib->ms.UrgentBurstFactorLumaPre,
 						mode_lib->ms.UrgentBurstFactorChromaPre,
 						mode_lib->ms.UrgentBurstFactorCursorPre);
@@ -6586,9 +6586,9 @@ static void dml_prefetch_check(struct display_mode_lib_st *mode_lib)
 													mode_lib->ms.cursor_bw_pre,
 													mode_lib->ms.prefetch_vmrow_bw,
 													mode_lib->ms.NoOfDPP[j], // VBA_ERROR DPPPerSurface is not assigned at this point, should use NoOfDpp here
-													mode_lib->ms.UrgentBurstFactorLuma,
-													mode_lib->ms.UrgentBurstFactorChroma,
-													mode_lib->ms.UrgentBurstFactorCursor,
+													mode_lib->ms.UrgentBurstFactorLuma[j],
+													mode_lib->ms.UrgentBurstFactorChroma[j],
+													mode_lib->ms.UrgentBurstFactorCursor[j],
 													mode_lib->ms.UrgentBurstFactorLumaPre,
 													mode_lib->ms.UrgentBurstFactorChromaPre,
 													mode_lib->ms.UrgentBurstFactorCursorPre,
@@ -7809,9 +7809,9 @@ dml_bool_t dml_core_mode_support(struct display_mode_lib_st *mode_lib)
 				mode_lib->ms.DETBufferSizeYThisState[k],
 				mode_lib->ms.DETBufferSizeCThisState[k],
 				/* Output */
-				&mode_lib->ms.UrgentBurstFactorCursor[k],
-				&mode_lib->ms.UrgentBurstFactorLuma[k],
-				&mode_lib->ms.UrgentBurstFactorChroma[k],
+				&mode_lib->ms.UrgentBurstFactorCursor[j][k],
+				&mode_lib->ms.UrgentBurstFactorLuma[j][k],
+				&mode_lib->ms.UrgentBurstFactorChroma[j][k],
 				&mode_lib->ms.NotUrgentLatencyHiding[k]);
 		}
 
@@ -9190,6 +9190,8 @@ void dml_core_mode_programming(struct display_mode_lib_st *mode_lib, const struc
 			&locals->FractionOfUrgentBandwidth,
 			&s->dummy_boolean[0]); // dml_bool_t *PrefetchBandwidthSupport
 
+
+
 		if (s->VRatioPrefetchMoreThanMax != false || s->DestinationLineTimesForPrefetchLessThan2 != false) {
 			dml_print("DML::%s: VRatioPrefetchMoreThanMax                   = %u\n", __func__, s->VRatioPrefetchMoreThanMax);
 			dml_print("DML::%s: DestinationLineTimesForPrefetchLessThan2    = %u\n", __func__, s->DestinationLineTimesForPrefetchLessThan2);
@@ -9204,6 +9206,7 @@ void dml_core_mode_programming(struct display_mode_lib_st *mode_lib, const struc
 			}
 		}
 
+
 		if (locals->PrefetchModeSupported == true && mode_lib->ms.support.ImmediateFlipSupport == true) {
 			locals->BandwidthAvailableForImmediateFlip = CalculateBandwidthAvailableForImmediateFlip(
 																	mode_lib->ms.num_active_planes,
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core_structs.h b/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core_structs.h
index f951936bb579..504c427b3b31 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core_structs.h
+++ b/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core_structs.h
@@ -884,11 +884,11 @@ struct mode_support_st {
 	dml_uint_t meta_row_height[__DML_NUM_PLANES__];
 	dml_uint_t meta_row_height_chroma[__DML_NUM_PLANES__];
 	dml_float_t UrgLatency;
-	dml_float_t UrgentBurstFactorCursor[__DML_NUM_PLANES__];
+	dml_float_t UrgentBurstFactorCursor[2][__DML_NUM_PLANES__];
 	dml_float_t UrgentBurstFactorCursorPre[__DML_NUM_PLANES__];
-	dml_float_t UrgentBurstFactorLuma[__DML_NUM_PLANES__];
+	dml_float_t UrgentBurstFactorLuma[2][__DML_NUM_PLANES__];
 	dml_float_t UrgentBurstFactorLumaPre[__DML_NUM_PLANES__];
-	dml_float_t UrgentBurstFactorChroma[__DML_NUM_PLANES__];
+	dml_float_t UrgentBurstFactorChroma[2][__DML_NUM_PLANES__];
 	dml_float_t UrgentBurstFactorChromaPre[__DML_NUM_PLANES__];
 	dml_float_t MaximumSwathWidthInLineBufferLuma;
 	dml_float_t MaximumSwathWidthInLineBufferChroma;
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c
index 8dee0d397e03..f3aa93ddbf9c 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c
@@ -762,6 +762,7 @@ static void populate_dml21_plane_config_from_plane_state(struct dml2_context *dm
 		plane->pixel_format = dml2_420_10;
 		break;
 	case SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616:
+	case SURFACE_PIXEL_FORMAT_GRPH_ABGR16161616:
 	case SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616F:
 	case SURFACE_PIXEL_FORMAT_GRPH_ABGR16161616F:
 		plane->pixel_format = dml2_444_64;
@@ -887,7 +888,7 @@ static void populate_dml21_plane_config_from_plane_state(struct dml2_context *dm
 }
 
 //TODO : Could be possibly moved to a common helper layer.
-static bool dml21_wrapper_get_plane_id(const struct dc_state *context, const struct dc_plane_state *plane, unsigned int *plane_id)
+static bool dml21_wrapper_get_plane_id(const struct dc_state *context, unsigned int stream_id, const struct dc_plane_state *plane, unsigned int *plane_id)
 {
 	int i, j;
 
@@ -895,10 +896,12 @@ static bool dml21_wrapper_get_plane_id(const struct dc_state *context, const str
 		return false;
 
 	for (i = 0; i < context->stream_count; i++) {
-		for (j = 0; j < context->stream_status[i].plane_count; j++) {
-			if (context->stream_status[i].plane_states[j] == plane) {
-				*plane_id = (i << 16) | j;
-				return true;
+		if (context->streams[i]->stream_id == stream_id) {
+			for (j = 0; j < context->stream_status[i].plane_count; j++) {
+				if (context->stream_status[i].plane_states[j] == plane) {
+					*plane_id = (i << 16) | j;
+					return true;
+				}
 			}
 		}
 	}
@@ -921,14 +924,14 @@ static unsigned int map_stream_to_dml21_display_cfg(const struct dml2_context *d
 	return location;
 }
 
-static unsigned int map_plane_to_dml21_display_cfg(const struct dml2_context *dml_ctx,
+static unsigned int map_plane_to_dml21_display_cfg(const struct dml2_context *dml_ctx, unsigned int stream_id,
 		const struct dc_plane_state *plane, const struct dc_state *context)
 {
 	unsigned int plane_id;
 	int i = 0;
 	int location = -1;
 
-	if (!dml21_wrapper_get_plane_id(context, plane, &plane_id)) {
+	if (!dml21_wrapper_get_plane_id(context, stream_id, plane, &plane_id)) {
 		ASSERT(false);
 		return -1;
 	}
@@ -994,7 +997,7 @@ bool dml21_map_dc_state_into_dml_display_cfg(const struct dc *in_dc, struct dc_s
 		if (disp_cfg_stream_location < 0)
 			disp_cfg_stream_location = dml_dispcfg->num_streams++;
 
-		ASSERT(disp_cfg_stream_location >= 0 && disp_cfg_stream_location <= __DML2_WRAPPER_MAX_STREAMS_PLANES__);
+		ASSERT(disp_cfg_stream_location >= 0 && disp_cfg_stream_location < __DML2_WRAPPER_MAX_STREAMS_PLANES__);
 		populate_dml21_timing_config_from_stream_state(&dml_dispcfg->stream_descriptors[disp_cfg_stream_location].timing, context->streams[stream_index], dml_ctx);
 		populate_dml21_output_config_from_stream_state(&dml_dispcfg->stream_descriptors[disp_cfg_stream_location].output, context->streams[stream_index], &context->res_ctx.pipe_ctx[stream_index]);
 		populate_dml21_stream_overrides_from_stream_state(&dml_dispcfg->stream_descriptors[disp_cfg_stream_location], context->streams[stream_index]);
@@ -1013,18 +1016,18 @@ bool dml21_map_dc_state_into_dml_display_cfg(const struct dc *in_dc, struct dc_s
 			dml_dispcfg->plane_descriptors[disp_cfg_plane_location].stream_index = disp_cfg_stream_location;
 		} else {
 			for (plane_index = 0; plane_index < context->stream_status[stream_index].plane_count; plane_index++) {
-				disp_cfg_plane_location = map_plane_to_dml21_display_cfg(dml_ctx, context->stream_status[stream_index].plane_states[plane_index], context);
+				disp_cfg_plane_location = map_plane_to_dml21_display_cfg(dml_ctx, context->streams[stream_index]->stream_id, context->stream_status[stream_index].plane_states[plane_index], context);
 
 				if (disp_cfg_plane_location < 0)
 					disp_cfg_plane_location = dml_dispcfg->num_planes++;
 
-				ASSERT(disp_cfg_plane_location >= 0 && disp_cfg_plane_location <= __DML2_WRAPPER_MAX_STREAMS_PLANES__);
+				ASSERT(disp_cfg_plane_location >= 0 && disp_cfg_plane_location < __DML2_WRAPPER_MAX_STREAMS_PLANES__);
 
 				populate_dml21_surface_config_from_plane_state(in_dc, &dml_dispcfg->plane_descriptors[disp_cfg_plane_location].surface, context->stream_status[stream_index].plane_states[plane_index]);
 				populate_dml21_plane_config_from_plane_state(dml_ctx, &dml_dispcfg->plane_descriptors[disp_cfg_plane_location], context->stream_status[stream_index].plane_states[plane_index], context, stream_index);
 				dml_dispcfg->plane_descriptors[disp_cfg_plane_location].stream_index = disp_cfg_stream_location;
 
-				if (dml21_wrapper_get_plane_id(context, context->stream_status[stream_index].plane_states[plane_index], &dml_ctx->v21.dml_to_dc_pipe_mapping.disp_cfg_to_plane_id[disp_cfg_plane_location]))
+				if (dml21_wrapper_get_plane_id(context, context->streams[stream_index]->stream_id, context->stream_status[stream_index].plane_states[plane_index], &dml_ctx->v21.dml_to_dc_pipe_mapping.disp_cfg_to_plane_id[disp_cfg_plane_location]))
 					dml_ctx->v21.dml_to_dc_pipe_mapping.disp_cfg_to_plane_id_valid[disp_cfg_plane_location] = true;
 
 				/* apply forced pstate policy */
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_wrapper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_wrapper.c
index d35dd507cb9f..dcbe327209d5 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_wrapper.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_wrapper.c
@@ -2,6 +2,7 @@
 //
 // Copyright 2024 Advanced Micro Devices, Inc.
 
+#include <linux/vmalloc.h>
 
 #include "dml2_internal_types.h"
 #include "dml_top.h"
@@ -13,11 +14,11 @@
 
 static bool dml21_allocate_memory(struct dml2_context **dml_ctx)
 {
-	*dml_ctx = (struct dml2_context *)kzalloc(sizeof(struct dml2_context), GFP_KERNEL);
+	*dml_ctx = vzalloc(sizeof(struct dml2_context));
 	if (!(*dml_ctx))
 		return false;
 
-	(*dml_ctx)->v21.dml_init.dml2_instance = (struct dml2_instance *)kzalloc(sizeof(struct dml2_instance), GFP_KERNEL);
+	(*dml_ctx)->v21.dml_init.dml2_instance = vzalloc(sizeof(struct dml2_instance));
 	if (!((*dml_ctx)->v21.dml_init.dml2_instance))
 		return false;
 
@@ -27,7 +28,7 @@ static bool dml21_allocate_memory(struct dml2_context **dml_ctx)
 	(*dml_ctx)->v21.mode_support.display_config = &(*dml_ctx)->v21.display_config;
 	(*dml_ctx)->v21.mode_programming.display_config = (*dml_ctx)->v21.mode_support.display_config;
 
-	(*dml_ctx)->v21.mode_programming.programming = (struct dml2_display_cfg_programming *)kzalloc(sizeof(struct dml2_display_cfg_programming), GFP_KERNEL);
+	(*dml_ctx)->v21.mode_programming.programming = vzalloc(sizeof(struct dml2_display_cfg_programming));
 	if (!((*dml_ctx)->v21.mode_programming.programming))
 		return false;
 
@@ -87,6 +88,8 @@ static void dml21_init(const struct dc *in_dc, struct dml2_context **dml_ctx, co
 	/* Store configuration options */
 	(*dml_ctx)->config = *config;
 
+	DC_FP_START();
+
 	/*Initialize SOCBB and DCNIP params */
 	dml21_initialize_soc_bb_params(&(*dml_ctx)->v21.dml_init, config, in_dc);
 	dml21_initialize_ip_params(&(*dml_ctx)->v21.dml_init, config, in_dc);
@@ -97,6 +100,8 @@ static void dml21_init(const struct dc *in_dc, struct dml2_context **dml_ctx, co
 
 	/*Initialize DML21 instance */
 	dml2_initialize_instance(&(*dml_ctx)->v21.dml_init);
+
+	DC_FP_END();
 }
 
 bool dml21_create(const struct dc *in_dc, struct dml2_context **dml_ctx, const struct dml2_configuration_options *config)
@@ -112,8 +117,8 @@ bool dml21_create(const struct dc *in_dc, struct dml2_context **dml_ctx, const s
 
 void dml21_destroy(struct dml2_context *dml2)
 {
-	kfree(dml2->v21.dml_init.dml2_instance);
-	kfree(dml2->v21.mode_programming.programming);
+	vfree(dml2->v21.dml_init.dml2_instance);
+	vfree(dml2->v21.mode_programming.programming);
 }
 
 static void dml21_calculate_rq_and_dlg_params(const struct dc *dc, struct dc_state *context, struct resource_context *out_new_hw_state,
@@ -216,7 +221,9 @@ static bool dml21_mode_check_and_programming(const struct dc *in_dc, struct dc_s
 	if (!result)
 		return false;
 
+	DC_FP_START();
 	result = dml2_build_mode_programming(mode_programming);
+	DC_FP_END();
 	if (!result)
 		return false;
 
@@ -266,7 +273,9 @@ static bool dml21_check_mode_support(const struct dc *in_dc, struct dc_state *co
 	mode_support->dml2_instance = dml_init->dml2_instance;
 	dml21_map_dc_state_into_dml_display_cfg(in_dc, context, dml_ctx);
 	dml_ctx->v21.mode_programming.dml2_instance->scratch.build_mode_programming_locals.mode_programming_params.programming = dml_ctx->v21.mode_programming.programming;
+	DC_FP_START();
 	is_supported = dml2_check_mode_supported(mode_support);
+	DC_FP_END();
 	if (!is_supported)
 		return false;
 
@@ -278,10 +287,11 @@ bool dml21_validate(const struct dc *in_dc, struct dc_state *context, struct dml
 	bool out = false;
 
 	/* Use dml_validate_only for fast_validate path */
-	if (fast_validate) {
+	if (fast_validate)
 		out = dml21_check_mode_support(in_dc, context, dml_ctx);
-	} else
+	else
 		out = dml21_mode_check_and_programming(in_dc, context, dml_ctx);
+
 	return out;
 }
 
@@ -420,8 +430,12 @@ void dml21_copy(struct dml2_context *dst_dml_ctx,
 
 	dst_dml_ctx->v21.mode_programming.programming = dst_dml2_programming;
 
+	DC_FP_START();
+
 	/* need to initialize copied instance for internal references to be correct */
 	dml2_initialize_instance(&dst_dml_ctx->v21.dml_init);
+
+	DC_FP_END();
 }
 
 bool dml21_create_copy(struct dml2_context **dst_dml_ctx,
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_dcn4.c b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_dcn4.c
index 0aa4e4d343b0..2c1316d1b6eb 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_dcn4.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_dcn4.c
@@ -139,9 +139,8 @@ bool core_dcn4_initialize(struct dml2_core_initialize_in_out *in_out)
 		core->clean_me_up.mode_lib.ip.subvp_fw_processing_delay_us = core_dcn4_ip_caps_base.subvp_pstate_allow_width_us;
 		core->clean_me_up.mode_lib.ip.subvp_swath_height_margin_lines = core_dcn4_ip_caps_base.subvp_swath_height_margin_lines;
 	} else {
-			memcpy(&core->clean_me_up.mode_lib.ip, &core_dcn4_ip_caps_base, sizeof(struct dml2_core_ip_params));
+		memcpy(&core->clean_me_up.mode_lib.ip, &core_dcn4_ip_caps_base, sizeof(struct dml2_core_ip_params));
 		patch_ip_params_with_ip_caps(&core->clean_me_up.mode_lib.ip, in_out->ip_caps);
-
 		core->clean_me_up.mode_lib.ip.imall_supported = false;
 	}
 
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_dcn4_calcs.c b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_dcn4_calcs.c
index 3ea54fd52e46..157903115f3b 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_dcn4_calcs.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_dcn4_calcs.c
@@ -578,8 +578,8 @@ static void CalculateBytePerPixelAndBlockSizes(
 {
 	*BytePerPixelDETY = 0;
 	*BytePerPixelDETC = 0;
-	*BytePerPixelY = 0;
-	*BytePerPixelC = 0;
+	*BytePerPixelY = 1;
+	*BytePerPixelC = 1;
 
 	if (SourcePixelFormat == dml2_444_64) {
 		*BytePerPixelDETY = 8;
@@ -3630,13 +3630,12 @@ static unsigned int CalculateMaxVStartup(
 	double line_time_us = (double)timing->h_total / ((double)timing->pixel_clock_khz / 1000);
 	unsigned int vblank_actual = timing->v_total - timing->v_active;
 	unsigned int vblank_nom_default_in_line = (unsigned int)math_floor2((double)vblank_nom_default_us / line_time_us, 1.0);
-	unsigned int vblank_nom_input = (unsigned int)math_min2(timing->vblank_nom, vblank_nom_default_in_line);
-	unsigned int vblank_avail = (vblank_nom_input == 0) ? vblank_nom_default_in_line : vblank_nom_input;
+	unsigned int vblank_avail = (timing->vblank_nom == 0) ? vblank_nom_default_in_line : (unsigned int)timing->vblank_nom;
 
 	vblank_size = (unsigned int)math_min2(vblank_actual, vblank_avail);
 
 	if (timing->interlaced && !ptoi_supported)
-		max_vstartup_lines = (unsigned int)(math_floor2(vblank_size / 2.0, 1.0));
+		max_vstartup_lines = (unsigned int)(math_floor2((vblank_size - 1) / 2.0, 1.0));
 	else
 		max_vstartup_lines = vblank_size - (unsigned int)math_max2(1.0, math_ceil2(write_back_delay_us / line_time_us, 1.0));
 #ifdef __DML_VBA_DEBUG__
@@ -4652,7 +4651,10 @@ static void calculate_tdlut_setting(
 	//the tdlut is fetched during the 2 row times of prefetch.
 	if (p->setup_for_tdlut) {
 		*p->tdlut_groups_per_2row_ub = (unsigned int)math_ceil2((double) *p->tdlut_bytes_per_frame / *p->tdlut_bytes_per_group, 1);
-		*p->tdlut_opt_time = (*p->tdlut_bytes_per_frame - p->cursor_buffer_size * 1024) / tdlut_drain_rate;
+		if (*p->tdlut_bytes_per_frame > p->cursor_buffer_size * 1024)
+			*p->tdlut_opt_time = (*p->tdlut_bytes_per_frame - p->cursor_buffer_size * 1024) / tdlut_drain_rate;
+		else
+			*p->tdlut_opt_time = 0;
 		*p->tdlut_drain_time = p->cursor_buffer_size * 1024 / tdlut_drain_rate;
 	}
 
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_dc_resource_mgmt.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_dc_resource_mgmt.c
index 1ed21c1b86a5..a966abd40788 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_dc_resource_mgmt.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_dc_resource_mgmt.c
@@ -532,26 +532,6 @@ static void calculate_odm_slices(const struct dc_stream_state *stream, unsigned
 	odm_slice_end_x[odm_factor - 1] = stream->src.width - 1;
 }
 
-static bool is_plane_in_odm_slice(const struct dc_plane_state *plane, unsigned int slice_index, unsigned int *odm_slice_end_x, unsigned int num_slices)
-{
-	unsigned int slice_start_x, slice_end_x;
-
-	if (slice_index == 0)
-		slice_start_x = 0;
-	else
-		slice_start_x = odm_slice_end_x[slice_index - 1] + 1;
-
-	slice_end_x = odm_slice_end_x[slice_index];
-
-	if (plane->clip_rect.x + plane->clip_rect.width < slice_start_x)
-		return false;
-
-	if (plane->clip_rect.x > slice_end_x)
-		return false;
-
-	return true;
-}
-
 static void add_odm_slice_to_odm_tree(struct dml2_context *ctx,
 		struct dc_state *state,
 		struct dc_pipe_mapping_scratch *scratch,
@@ -791,12 +771,6 @@ static void map_pipes_for_plane(struct dml2_context *ctx, struct dc_state *state
 	sort_pipes_for_splitting(&scratch->pipe_pool);
 
 	for (odm_slice_index = 0; odm_slice_index < scratch->odm_info.odm_factor; odm_slice_index++) {
-		// We build the tree for one ODM slice at a time.
-		// Each ODM slice shares a common OPP
-		if (!is_plane_in_odm_slice(plane, odm_slice_index, scratch->odm_info.odm_slice_end_x, scratch->odm_info.odm_factor)) {
-			continue;
-		}
-
 		// Now we have a list of all pipes to be used for this plane/stream, now setup the tree.
 		scratch->odm_info.next_higher_pipe_for_odm_slice[odm_slice_index] = add_plane_to_blend_tree(ctx, state,
 				plane,
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
index bde4250853b1..405aefd14d9b 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
@@ -746,7 +746,7 @@ static void populate_dml_output_cfg_from_stream_state(struct dml_output_cfg_st *
 	case SIGNAL_TYPE_DISPLAY_PORT_MST:
 	case SIGNAL_TYPE_DISPLAY_PORT:
 		out->OutputEncoder[location] = dml_dp;
-		if (dml2->v20.scratch.hpo_stream_to_link_encoder_mapping[location] != -1)
+		if (location < MAX_HPO_DP2_ENCODERS && dml2->v20.scratch.hpo_stream_to_link_encoder_mapping[location] != -1)
 			out->OutputEncoder[dml2->v20.scratch.hpo_stream_to_link_encoder_mapping[location]] = dml_dp2p0;
 		break;
 	case SIGNAL_TYPE_EDP:
@@ -909,6 +909,7 @@ static void populate_dml_surface_cfg_from_plane_state(enum dml_project_id dml2_p
 		out->SourcePixelFormat[location] = dml_420_10;
 		break;
 	case SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616:
+	case SURFACE_PIXEL_FORMAT_GRPH_ABGR16161616:
 	case SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616F:
 	case SURFACE_PIXEL_FORMAT_GRPH_ABGR16161616F:
 		out->SourcePixelFormat[location] = dml_444_64;
@@ -929,7 +930,9 @@ static void populate_dml_surface_cfg_from_plane_state(enum dml_project_id dml2_p
 	}
 }
 
-static void get_scaler_data_for_plane(const struct dc_plane_state *in, struct dc_state *context, struct scaler_data *out)
+static struct scaler_data *get_scaler_data_for_plane(
+		const struct dc_plane_state *in,
+		struct dc_state *context)
 {
 	int i;
 	struct pipe_ctx *temp_pipe = &context->res_ctx.temp_pipe;
@@ -950,7 +953,7 @@ static void get_scaler_data_for_plane(const struct dc_plane_state *in, struct dc
 	}
 
 	ASSERT(i < MAX_PIPES);
-	memcpy(out, &temp_pipe->plane_res.scl_data, sizeof(*out));
+	return &temp_pipe->plane_res.scl_data;
 }
 
 static void populate_dummy_dml_plane_cfg(struct dml_plane_cfg_st *out, unsigned int location,
@@ -1013,11 +1016,7 @@ static void populate_dml_plane_cfg_from_plane_state(struct dml_plane_cfg_st *out
 						    const struct dc_plane_state *in, struct dc_state *context,
 						    const struct soc_bounding_box_st *soc)
 {
-	struct scaler_data *scaler_data = kzalloc(sizeof(*scaler_data), GFP_KERNEL);
-	if (!scaler_data)
-		return;
-
-	get_scaler_data_for_plane(in, context, scaler_data);
+	struct scaler_data *scaler_data = get_scaler_data_for_plane(in, context);
 
 	out->CursorBPP[location] = dml_cur_32bit;
 	out->CursorWidth[location] = 256;
@@ -1082,8 +1081,6 @@ static void populate_dml_plane_cfg_from_plane_state(struct dml_plane_cfg_st *out
 	out->DynamicMetadataTransmittedBytes[location] = 0;
 
 	out->NumberOfCursors[location] = 1;
-
-	kfree(scaler_data);
 }
 
 static unsigned int map_stream_to_dml_display_cfg(const struct dml2_context *dml2,
@@ -1303,7 +1300,7 @@ void map_dc_state_into_dml_display_cfg(struct dml2_context *dml2, struct dc_stat
 		if (disp_cfg_stream_location < 0)
 			disp_cfg_stream_location = dml_dispcfg->num_timings++;
 
-		ASSERT(disp_cfg_stream_location >= 0 && disp_cfg_stream_location <= __DML2_WRAPPER_MAX_STREAMS_PLANES__);
+		ASSERT(disp_cfg_stream_location >= 0 && disp_cfg_stream_location < __DML2_WRAPPER_MAX_STREAMS_PLANES__);
 
 		populate_dml_timing_cfg_from_stream_state(&dml_dispcfg->timing, disp_cfg_stream_location, context->streams[i]);
 		populate_dml_output_cfg_from_stream_state(&dml_dispcfg->output, disp_cfg_stream_location, context->streams[i], current_pipe_context, dml2);
@@ -1343,7 +1340,7 @@ void map_dc_state_into_dml_display_cfg(struct dml2_context *dml2, struct dc_stat
 				if (disp_cfg_plane_location < 0)
 					disp_cfg_plane_location = dml_dispcfg->num_surfaces++;
 
-				ASSERT(disp_cfg_plane_location >= 0 && disp_cfg_plane_location <= __DML2_WRAPPER_MAX_STREAMS_PLANES__);
+				ASSERT(disp_cfg_plane_location >= 0 && disp_cfg_plane_location < __DML2_WRAPPER_MAX_STREAMS_PLANES__);
 
 				populate_dml_surface_cfg_from_plane_state(dml2->v20.dml_core_ctx.project, &dml_dispcfg->surface, disp_cfg_plane_location, context->stream_status[i].plane_states[j]);
 				populate_dml_plane_cfg_from_plane_state(
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c
index 866b0abcff1b..03812f862b3d 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c
@@ -24,6 +24,8 @@
  *
  */
 
+#include <linux/vmalloc.h>
+
 #include "display_mode_core.h"
 #include "dml2_internal_types.h"
 #include "dml2_utils.h"
@@ -533,14 +535,21 @@ static bool optimize_pstate_with_svp_and_drr(struct dml2_context *dml2, struct d
 static bool call_dml_mode_support_and_programming(struct dc_state *context)
 {
 	unsigned int result = 0;
-	unsigned int min_state;
+	unsigned int min_state = 0;
 	int min_state_for_g6_temp_read = 0;
+
+
+	if (!context)
+		return false;
+
 	struct dml2_context *dml2 = context->bw_ctx.dml2;
 	struct dml2_wrapper_scratch *s = &dml2->v20.scratch;
 
-	min_state_for_g6_temp_read = calculate_lowest_supported_state_for_temp_read(dml2, context);
+	if (!context->streams[0]->sink->link->dc->caps.is_apu) {
+		min_state_for_g6_temp_read = calculate_lowest_supported_state_for_temp_read(dml2, context);
 
-	ASSERT(min_state_for_g6_temp_read >= 0);
+		ASSERT(min_state_for_g6_temp_read >= 0);
+	}
 
 	if (!dml2->config.use_native_pstate_optimization) {
 		result = optimize_pstate_with_svp_and_drr(dml2, context);
@@ -551,14 +560,20 @@ static bool call_dml_mode_support_and_programming(struct dc_state *context)
 	/* Upon trying to sett certain frequencies in FRL, min_state_for_g6_temp_read is reported as -1. This leads to an invalid value of min_state causing crashes later on.
 	 * Use the default logic for min_state only when min_state_for_g6_temp_read is a valid value. In other cases, use the value calculated by the DML directly.
 	 */
-	if (min_state_for_g6_temp_read >= 0)
-		min_state = min_state_for_g6_temp_read > s->mode_support_params.out_lowest_state_idx ? min_state_for_g6_temp_read : s->mode_support_params.out_lowest_state_idx;
-	else
-		min_state = s->mode_support_params.out_lowest_state_idx;
-
-	if (result)
-		result = dml_mode_programming(&dml2->v20.dml_core_ctx, min_state, &s->cur_display_config, true);
+	if (!context->streams[0]->sink->link->dc->caps.is_apu) {
+		if (min_state_for_g6_temp_read >= 0)
+			min_state = min_state_for_g6_temp_read > s->mode_support_params.out_lowest_state_idx ? min_state_for_g6_temp_read : s->mode_support_params.out_lowest_state_idx;
+		else
+			min_state = s->mode_support_params.out_lowest_state_idx;
+	}
 
+	if (result) {
+		if (!context->streams[0]->sink->link->dc->caps.is_apu) {
+			result = dml_mode_programming(&dml2->v20.dml_core_ctx, min_state, &s->cur_display_config, true);
+		} else {
+			result = dml_mode_programming(&dml2->v20.dml_core_ctx, s->mode_support_params.out_lowest_state_idx, &s->cur_display_config, true);
+		}
+	}
 	return result;
 }
 
@@ -687,6 +702,8 @@ static bool dml2_validate_only(struct dc_state *context)
 	build_unoptimized_policy_settings(dml2->v20.dml_core_ctx.project, &dml2->v20.dml_core_ctx.policy);
 
 	map_dc_state_into_dml_display_cfg(dml2, context, &dml2->v20.scratch.cur_display_config);
+	 if (!dml2->config.skip_hw_state_mapping)
+		 dml2_apply_det_buffer_allocation_policy(dml2, &dml2->v20.scratch.cur_display_config);
 
 	result = pack_and_call_dml_mode_support_ex(dml2,
 		&dml2->v20.scratch.cur_display_config,
@@ -719,17 +736,22 @@ bool dml2_validate(const struct dc *in_dc, struct dc_state *context, struct dml2
 		return out;
 	}
 
+	DC_FP_START();
+
 	/* Use dml_validate_only for fast_validate path */
 	if (fast_validate)
 		out = dml2_validate_only(context);
 	else
 		out = dml2_validate_and_build_resource(in_dc, context);
+
+	DC_FP_END();
+
 	return out;
 }
 
 static inline struct dml2_context *dml2_allocate_memory(void)
 {
-	return (struct dml2_context *) kzalloc(sizeof(struct dml2_context), GFP_KERNEL);
+	return (struct dml2_context *) vzalloc(sizeof(struct dml2_context));
 }
 
 static void dml2_init(const struct dc *in_dc, const struct dml2_configuration_options *config, struct dml2_context **dml2)
@@ -764,11 +786,15 @@ static void dml2_init(const struct dc *in_dc, const struct dml2_configuration_op
 		break;
 	}
 
+	DC_FP_START();
+
 	initialize_dml2_ip_params(*dml2, in_dc, &(*dml2)->v20.dml_core_ctx.ip);
 
 	initialize_dml2_soc_bbox(*dml2, in_dc, &(*dml2)->v20.dml_core_ctx.soc);
 
 	initialize_dml2_soc_states(*dml2, in_dc, &(*dml2)->v20.dml_core_ctx.soc, &(*dml2)->v20.dml_core_ctx.states);
+
+	DC_FP_END();
 }
 
 bool dml2_create(const struct dc *in_dc, const struct dml2_configuration_options *config, struct dml2_context **dml2)
@@ -796,7 +822,7 @@ void dml2_destroy(struct dml2_context *dml2)
 
 	if (dml2->architecture == dml2_architecture_21)
 		dml21_destroy(dml2);
-	kfree(dml2);
+	vfree(dml2);
 }
 
 void dml2_extract_dram_and_fclk_change_support(struct dml2_context *dml2,
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.h b/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.h
index 0f944fcfd5a5..785226945699 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.h
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.h
@@ -159,6 +159,7 @@ struct dml2_clks_table_entry {
 	unsigned int dtbclk_mhz;
 	unsigned int dispclk_mhz;
 	unsigned int dppclk_mhz;
+	unsigned int dram_speed_mts; /*which is based on wck_ratio*/
 };
 
 struct dml2_clks_num_entries {
diff --git a/drivers/gpu/drm/amd/display/dc/dpp/dcn10/dcn10_dpp.c b/drivers/gpu/drm/amd/display/dc/dpp/dcn10/dcn10_dpp.c
index e1da48b05d00..75fb77bca83b 100644
--- a/drivers/gpu/drm/amd/display/dc/dpp/dcn10/dcn10_dpp.c
+++ b/drivers/gpu/drm/amd/display/dc/dpp/dcn10/dcn10_dpp.c
@@ -194,6 +194,9 @@ void dpp_reset(struct dpp *dpp_base)
 	dpp->filter_h = NULL;
 	dpp->filter_v = NULL;
 
+	memset(&dpp_base->pos, 0, sizeof(dpp_base->pos));
+	memset(&dpp_base->att, 0, sizeof(dpp_base->att));
+
 	memset(&dpp->scl_data, 0, sizeof(dpp->scl_data));
 	memset(&dpp->pwl_data, 0, sizeof(dpp->pwl_data));
 }
@@ -480,10 +483,11 @@ void dpp1_set_cursor_position(
 	if (src_y_offset + cursor_height <= 0)
 		cur_en = 0;  /* not visible beyond top edge*/
 
-	REG_UPDATE(CURSOR0_CONTROL,
-			CUR0_ENABLE, cur_en);
+	if (dpp_base->pos.cur0_ctl.bits.cur0_enable != cur_en) {
+		REG_UPDATE(CURSOR0_CONTROL, CUR0_ENABLE, cur_en);
 
-	dpp_base->pos.cur0_ctl.bits.cur0_enable = cur_en;
+		dpp_base->pos.cur0_ctl.bits.cur0_enable = cur_en;
+	}
 }
 
 void dpp1_cnv_set_optional_cursor_attributes(
diff --git a/drivers/gpu/drm/amd/display/dc/dpp/dcn30/dcn30_dpp.c b/drivers/gpu/drm/amd/display/dc/dpp/dcn30/dcn30_dpp.c
index 40acebd13e46..abf439e743f2 100644
--- a/drivers/gpu/drm/amd/display/dc/dpp/dcn30/dcn30_dpp.c
+++ b/drivers/gpu/drm/amd/display/dc/dpp/dcn30/dcn30_dpp.c
@@ -425,11 +425,6 @@ bool dpp3_get_optimal_number_of_taps(
 	int min_taps_y, min_taps_c;
 	enum lb_memory_config lb_config;
 
-	if (scl_data->viewport.width > scl_data->h_active &&
-		dpp->ctx->dc->debug.max_downscale_src_width != 0 &&
-		scl_data->viewport.width > dpp->ctx->dc->debug.max_downscale_src_width)
-		return false;
-
 	/*
 	 * Set default taps if none are provided
 	 * From programming guide: taps = min{ ceil(2*H_RATIO,1), 8} for downscaling
@@ -467,6 +462,12 @@ bool dpp3_get_optimal_number_of_taps(
 	else
 		scl_data->taps.h_taps_c = in_taps->h_taps_c;
 
+	// Avoid null data in the scl data with this early return, proceed non-adaptive calcualtion first
+	if (scl_data->viewport.width > scl_data->h_active &&
+		dpp->ctx->dc->debug.max_downscale_src_width != 0 &&
+		scl_data->viewport.width > dpp->ctx->dc->debug.max_downscale_src_width)
+		return false;
+
 	/*Ensure we can support the requested number of vtaps*/
 	min_taps_y = dc_fixpt_ceil(scl_data->ratios.vert);
 	min_taps_c = dc_fixpt_ceil(scl_data->ratios.vert_c);
diff --git a/drivers/gpu/drm/amd/display/dc/dpp/dcn401/dcn401_dpp_cm.c b/drivers/gpu/drm/amd/display/dc/dpp/dcn401/dcn401_dpp_cm.c
index 3b6ca7974e18..712aff7e17f7 100644
--- a/drivers/gpu/drm/amd/display/dc/dpp/dcn401/dcn401_dpp_cm.c
+++ b/drivers/gpu/drm/amd/display/dc/dpp/dcn401/dcn401_dpp_cm.c
@@ -120,10 +120,11 @@ void dpp401_set_cursor_attributes(
 	enum dc_cursor_color_format color_format = cursor_attributes->color_format;
 	int cur_rom_en = 0;
 
-	// DCN4 should always do Cursor degamma for Cursor Color modes
 	if (color_format == CURSOR_MODE_COLOR_PRE_MULTIPLIED_ALPHA ||
 		color_format == CURSOR_MODE_COLOR_UN_PRE_MULTIPLIED_ALPHA) {
-		cur_rom_en = 1;
+		if (cursor_attributes->attribute_flags.bits.ENABLE_CURSOR_DEGAMMA) {
+			cur_rom_en = 1;
+		}
 	}
 
 	REG_UPDATE_3(CURSOR0_CONTROL,
@@ -154,9 +155,11 @@ void dpp401_set_cursor_position(
 	struct dcn401_dpp *dpp = TO_DCN401_DPP(dpp_base);
 	uint32_t cur_en = pos->enable ? 1 : 0;
 
-	REG_UPDATE(CURSOR0_CONTROL, CUR0_ENABLE, cur_en);
+	if (dpp_base->pos.cur0_ctl.bits.cur0_enable != cur_en) {
+		REG_UPDATE(CURSOR0_CONTROL, CUR0_ENABLE, cur_en);
 
-	dpp_base->pos.cur0_ctl.bits.cur0_enable = cur_en;
+		dpp_base->pos.cur0_ctl.bits.cur0_enable = cur_en;
+	}
 }
 
 void dpp401_set_optional_cursor_attributes(
diff --git a/drivers/gpu/drm/amd/display/dc/hpo/dcn31/dcn31_hpo_dp_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/hpo/dcn31/dcn31_hpo_dp_stream_encoder.c
index 678db949cfe3..759b453385c4 100644
--- a/drivers/gpu/drm/amd/display/dc/hpo/dcn31/dcn31_hpo_dp_stream_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/hpo/dcn31/dcn31_hpo_dp_stream_encoder.c
@@ -323,7 +323,7 @@ static void dcn31_hpo_dp_stream_enc_set_stream_attribute(
 		break;
 	case COLOR_SPACE_2020_RGB_LIMITEDRANGE:
 	case COLOR_SPACE_2020_RGB_FULLRANGE:
-	case COLOR_SPACE_2020_YCBCR:
+	case COLOR_SPACE_2020_YCBCR_LIMITED:
 	case COLOR_SPACE_XR_RGB:
 	case COLOR_SPACE_MSREF_SCRGB:
 	case COLOR_SPACE_ADOBERGB:
@@ -336,6 +336,7 @@ static void dcn31_hpo_dp_stream_enc_set_stream_attribute(
 	case COLOR_SPACE_CUSTOMPOINTS:
 	case COLOR_SPACE_UNKNOWN:
 	case COLOR_SPACE_YCBCR709_BLACK:
+	default:
 		/* do nothing */
 		break;
 	}
diff --git a/drivers/gpu/drm/amd/display/dc/hubbub/dcn30/dcn30_hubbub.c b/drivers/gpu/drm/amd/display/dc/hubbub/dcn30/dcn30_hubbub.c
index fe741100c0f8..d347bb06577a 100644
--- a/drivers/gpu/drm/amd/display/dc/hubbub/dcn30/dcn30_hubbub.c
+++ b/drivers/gpu/drm/amd/display/dc/hubbub/dcn30/dcn30_hubbub.c
@@ -129,7 +129,8 @@ bool hubbub3_program_watermarks(
 	REG_UPDATE(DCHUBBUB_ARB_DF_REQ_OUTSTAND,
 			DCHUBBUB_ARB_MIN_REQ_OUTSTAND, 0x1FF);
 
-	hubbub1_allow_self_refresh_control(hubbub, !hubbub->ctx->dc->debug.disable_stutter);
+	if (safe_to_lower || hubbub->ctx->dc->debug.disable_stutter)
+		hubbub1_allow_self_refresh_control(hubbub, !hubbub->ctx->dc->debug.disable_stutter);
 
 	return wm_pending;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/hubbub/dcn31/dcn31_hubbub.c b/drivers/gpu/drm/amd/display/dc/hubbub/dcn31/dcn31_hubbub.c
index 7fb5523f9722..b98505b240a7 100644
--- a/drivers/gpu/drm/amd/display/dc/hubbub/dcn31/dcn31_hubbub.c
+++ b/drivers/gpu/drm/amd/display/dc/hubbub/dcn31/dcn31_hubbub.c
@@ -750,7 +750,8 @@ static bool hubbub31_program_watermarks(
 	REG_UPDATE(DCHUBBUB_ARB_DF_REQ_OUTSTAND,
 			DCHUBBUB_ARB_MIN_REQ_OUTSTAND, 0x1FF);*/
 
-	hubbub1_allow_self_refresh_control(hubbub, !hubbub->ctx->dc->debug.disable_stutter);
+	if (safe_to_lower || hubbub->ctx->dc->debug.disable_stutter)
+		hubbub1_allow_self_refresh_control(hubbub, !hubbub->ctx->dc->debug.disable_stutter);
 	return wm_pending;
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/hubbub/dcn32/dcn32_hubbub.c b/drivers/gpu/drm/amd/display/dc/hubbub/dcn32/dcn32_hubbub.c
index 5264dc26cce1..32a6be543105 100644
--- a/drivers/gpu/drm/amd/display/dc/hubbub/dcn32/dcn32_hubbub.c
+++ b/drivers/gpu/drm/amd/display/dc/hubbub/dcn32/dcn32_hubbub.c
@@ -786,7 +786,8 @@ static bool hubbub32_program_watermarks(
 	REG_UPDATE(DCHUBBUB_ARB_DF_REQ_OUTSTAND,
 			DCHUBBUB_ARB_MIN_REQ_OUTSTAND, 0x1FF);*/
 
-	hubbub1_allow_self_refresh_control(hubbub, !hubbub->ctx->dc->debug.disable_stutter);
+	if (safe_to_lower || hubbub->ctx->dc->debug.disable_stutter)
+		hubbub1_allow_self_refresh_control(hubbub, !hubbub->ctx->dc->debug.disable_stutter);
 
 	hubbub32_force_usr_retraining_allow(hubbub, hubbub->ctx->dc->debug.force_usr_allow);
 
diff --git a/drivers/gpu/drm/amd/display/dc/hubbub/dcn35/dcn35_hubbub.c b/drivers/gpu/drm/amd/display/dc/hubbub/dcn35/dcn35_hubbub.c
index 5eb3da8d5206..dce7269959ce 100644
--- a/drivers/gpu/drm/amd/display/dc/hubbub/dcn35/dcn35_hubbub.c
+++ b/drivers/gpu/drm/amd/display/dc/hubbub/dcn35/dcn35_hubbub.c
@@ -326,7 +326,8 @@ static bool hubbub35_program_watermarks(
 			DCHUBBUB_ARB_MIN_REQ_OUTSTAND_COMMIT_THRESHOLD, 0xA);/*hw delta*/
 	REG_UPDATE(DCHUBBUB_ARB_HOSTVM_CNTL, DCHUBBUB_ARB_MAX_QOS_COMMIT_THRESHOLD, 0xF);
 
-	hubbub1_allow_self_refresh_control(hubbub, !hubbub->ctx->dc->debug.disable_stutter);
+	if (safe_to_lower || hubbub->ctx->dc->debug.disable_stutter)
+		hubbub1_allow_self_refresh_control(hubbub, !hubbub->ctx->dc->debug.disable_stutter);
 
 	hubbub32_force_usr_retraining_allow(hubbub, hubbub->ctx->dc->debug.force_usr_allow);
 
diff --git a/drivers/gpu/drm/amd/display/dc/hubp/dcn10/dcn10_hubp.c b/drivers/gpu/drm/amd/display/dc/hubp/dcn10/dcn10_hubp.c
index 22ac2b7e49ae..da963f73829f 100644
--- a/drivers/gpu/drm/amd/display/dc/hubp/dcn10/dcn10_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/hubp/dcn10/dcn10_hubp.c
@@ -532,6 +532,12 @@ void hubp1_dcc_control(struct hubp *hubp, bool enable,
 			SECONDARY_SURFACE_DCC_IND_64B_BLK, dcc_ind_64b_blk);
 }
 
+void hubp_reset(struct hubp *hubp)
+{
+	memset(&hubp->pos, 0, sizeof(hubp->pos));
+	memset(&hubp->att, 0, sizeof(hubp->att));
+}
+
 void hubp1_program_surface_config(
 	struct hubp *hubp,
 	enum surface_pixel_format format,
@@ -1337,8 +1343,9 @@ static void hubp1_wait_pipe_read_start(struct hubp *hubp)
 
 void hubp1_init(struct hubp *hubp)
 {
-	//do nothing
+	hubp_reset(hubp);
 }
+
 static const struct hubp_funcs dcn10_hubp_funcs = {
 	.hubp_program_surface_flip_and_addr =
 			hubp1_program_surface_flip_and_addr,
@@ -1351,6 +1358,7 @@ static const struct hubp_funcs dcn10_hubp_funcs = {
 	.hubp_set_vm_context0_settings = hubp1_set_vm_context0_settings,
 	.set_blank = hubp1_set_blank,
 	.dcc_control = hubp1_dcc_control,
+	.hubp_reset = hubp_reset,
 	.mem_program_viewport = min_set_viewport,
 	.set_hubp_blank_en = hubp1_set_hubp_blank_en,
 	.set_cursor_attributes	= hubp1_cursor_set_attributes,
diff --git a/drivers/gpu/drm/amd/display/dc/hubp/dcn10/dcn10_hubp.h b/drivers/gpu/drm/amd/display/dc/hubp/dcn10/dcn10_hubp.h
index 69119b2fdce2..193e48b440ef 100644
--- a/drivers/gpu/drm/amd/display/dc/hubp/dcn10/dcn10_hubp.h
+++ b/drivers/gpu/drm/amd/display/dc/hubp/dcn10/dcn10_hubp.h
@@ -746,6 +746,8 @@ void hubp1_dcc_control(struct hubp *hubp,
 		bool enable,
 		enum hubp_ind_block_size independent_64b_blks);
 
+void hubp_reset(struct hubp *hubp);
+
 bool hubp1_program_surface_flip_and_addr(
 	struct hubp *hubp,
 	const struct dc_plane_address *address,
diff --git a/drivers/gpu/drm/amd/display/dc/hubp/dcn20/dcn20_hubp.c b/drivers/gpu/drm/amd/display/dc/hubp/dcn20/dcn20_hubp.c
index 0637e4c552d8..c74ee2d50a69 100644
--- a/drivers/gpu/drm/amd/display/dc/hubp/dcn20/dcn20_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/hubp/dcn20/dcn20_hubp.c
@@ -1044,11 +1044,13 @@ void hubp2_cursor_set_position(
 	if (src_y_offset + cursor_height <= 0)
 		cur_en = 0;  /* not visible beyond top edge*/
 
-	if (cur_en && REG_READ(CURSOR_SURFACE_ADDRESS) == 0)
-		hubp->funcs->set_cursor_attributes(hubp, &hubp->curs_attr);
+	if (hubp->pos.cur_ctl.bits.cur_enable != cur_en) {
+		if (cur_en && REG_READ(CURSOR_SURFACE_ADDRESS) == 0)
+			hubp->funcs->set_cursor_attributes(hubp, &hubp->curs_attr);
 
-	REG_UPDATE(CURSOR_CONTROL,
+		REG_UPDATE(CURSOR_CONTROL,
 			CURSOR_ENABLE, cur_en);
+	}
 
 	REG_SET_2(CURSOR_POSITION, 0,
 			CURSOR_X_POSITION, pos->x,
@@ -1660,6 +1662,7 @@ static struct hubp_funcs dcn20_hubp_funcs = {
 	.set_blank = hubp2_set_blank,
 	.set_blank_regs = hubp2_set_blank_regs,
 	.dcc_control = hubp2_dcc_control,
+	.hubp_reset = hubp_reset,
 	.mem_program_viewport = min_set_viewport,
 	.set_cursor_attributes	= hubp2_cursor_set_attributes,
 	.set_cursor_position	= hubp2_cursor_set_position,
diff --git a/drivers/gpu/drm/amd/display/dc/hubp/dcn201/dcn201_hubp.c b/drivers/gpu/drm/amd/display/dc/hubp/dcn201/dcn201_hubp.c
index cd2bfcc51276..6efcb10abf3d 100644
--- a/drivers/gpu/drm/amd/display/dc/hubp/dcn201/dcn201_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/hubp/dcn201/dcn201_hubp.c
@@ -121,6 +121,7 @@ static struct hubp_funcs dcn201_hubp_funcs = {
 	.set_cursor_position	= hubp1_cursor_set_position,
 	.set_blank = hubp1_set_blank,
 	.dcc_control = hubp1_dcc_control,
+	.hubp_reset = hubp_reset,
 	.mem_program_viewport = min_set_viewport,
 	.hubp_clk_cntl = hubp1_clk_cntl,
 	.hubp_vtg_sel = hubp1_vtg_sel,
diff --git a/drivers/gpu/drm/amd/display/dc/hubp/dcn21/dcn21_hubp.c b/drivers/gpu/drm/amd/display/dc/hubp/dcn21/dcn21_hubp.c
index e13d69a22c1c..4e2d9d381db3 100644
--- a/drivers/gpu/drm/amd/display/dc/hubp/dcn21/dcn21_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/hubp/dcn21/dcn21_hubp.c
@@ -811,6 +811,8 @@ static void hubp21_init(struct hubp *hubp)
 	struct dcn21_hubp *hubp21 = TO_DCN21_HUBP(hubp);
 	//hubp[i].HUBPREQ_DEBUG.HUBPREQ_DEBUG[26] = 1;
 	REG_WRITE(HUBPREQ_DEBUG, 1 << 26);
+
+	hubp_reset(hubp);
 }
 static struct hubp_funcs dcn21_hubp_funcs = {
 	.hubp_enable_tripleBuffer = hubp2_enable_triplebuffer,
@@ -823,6 +825,7 @@ static struct hubp_funcs dcn21_hubp_funcs = {
 	.hubp_set_vm_system_aperture_settings = hubp21_set_vm_system_aperture_settings,
 	.set_blank = hubp1_set_blank,
 	.dcc_control = hubp1_dcc_control,
+	.hubp_reset = hubp_reset,
 	.mem_program_viewport = hubp21_set_viewport,
 	.set_cursor_attributes	= hubp2_cursor_set_attributes,
 	.set_cursor_position	= hubp1_cursor_set_position,
diff --git a/drivers/gpu/drm/amd/display/dc/hubp/dcn30/dcn30_hubp.c b/drivers/gpu/drm/amd/display/dc/hubp/dcn30/dcn30_hubp.c
index 60a64d290352..5cf7e6771cb4 100644
--- a/drivers/gpu/drm/amd/display/dc/hubp/dcn30/dcn30_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/hubp/dcn30/dcn30_hubp.c
@@ -483,6 +483,10 @@ void hubp3_init(struct hubp *hubp)
 	struct dcn20_hubp *hubp2 = TO_DCN20_HUBP(hubp);
 	//hubp[i].HUBPREQ_DEBUG.HUBPREQ_DEBUG[26] = 1;
 	REG_WRITE(HUBPREQ_DEBUG, 1 << 26);
+
+	REG_UPDATE(DCHUBP_CNTL, HUBP_TTU_DISABLE, 0);
+
+	hubp_reset(hubp);
 }
 
 static struct hubp_funcs dcn30_hubp_funcs = {
@@ -497,6 +501,7 @@ static struct hubp_funcs dcn30_hubp_funcs = {
 	.set_blank = hubp2_set_blank,
 	.set_blank_regs = hubp2_set_blank_regs,
 	.dcc_control = hubp3_dcc_control,
+	.hubp_reset = hubp_reset,
 	.mem_program_viewport = min_set_viewport,
 	.set_cursor_attributes	= hubp2_cursor_set_attributes,
 	.set_cursor_position	= hubp2_cursor_set_position,
diff --git a/drivers/gpu/drm/amd/display/dc/hubp/dcn31/dcn31_hubp.c b/drivers/gpu/drm/amd/display/dc/hubp/dcn31/dcn31_hubp.c
index 8394e8c06919..c671908ba7d0 100644
--- a/drivers/gpu/drm/amd/display/dc/hubp/dcn31/dcn31_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/hubp/dcn31/dcn31_hubp.c
@@ -44,7 +44,7 @@ void hubp31_set_unbounded_requesting(struct hubp *hubp, bool enable)
 	struct dcn20_hubp *hubp2 = TO_DCN20_HUBP(hubp);
 
 	REG_UPDATE(DCHUBP_CNTL, HUBP_UNBOUNDED_REQ_MODE, enable);
-	REG_UPDATE(CURSOR_CONTROL, CURSOR_REQ_MODE, enable);
+	REG_UPDATE(CURSOR_CONTROL, CURSOR_REQ_MODE, 1);
 }
 
 void hubp31_soft_reset(struct hubp *hubp, bool reset)
@@ -79,6 +79,7 @@ static struct hubp_funcs dcn31_hubp_funcs = {
 	.hubp_set_vm_system_aperture_settings = hubp3_set_vm_system_aperture_settings,
 	.set_blank = hubp2_set_blank,
 	.dcc_control = hubp3_dcc_control,
+	.hubp_reset = hubp_reset,
 	.mem_program_viewport = min_set_viewport,
 	.set_cursor_attributes	= hubp2_cursor_set_attributes,
 	.set_cursor_position	= hubp2_cursor_set_position,
diff --git a/drivers/gpu/drm/amd/display/dc/hubp/dcn32/dcn32_hubp.c b/drivers/gpu/drm/amd/display/dc/hubp/dcn32/dcn32_hubp.c
index ca5b4b28a664..c4f41350d1b3 100644
--- a/drivers/gpu/drm/amd/display/dc/hubp/dcn32/dcn32_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/hubp/dcn32/dcn32_hubp.c
@@ -168,6 +168,8 @@ void hubp32_init(struct hubp *hubp)
 {
 	struct dcn20_hubp *hubp2 = TO_DCN20_HUBP(hubp);
 	REG_WRITE(HUBPREQ_DEBUG_DB, 1 << 8);
+
+	REG_UPDATE(DCHUBP_CNTL, HUBP_TTU_DISABLE, 0);
 }
 static struct hubp_funcs dcn32_hubp_funcs = {
 	.hubp_enable_tripleBuffer = hubp2_enable_triplebuffer,
@@ -181,6 +183,7 @@ static struct hubp_funcs dcn32_hubp_funcs = {
 	.set_blank = hubp2_set_blank,
 	.set_blank_regs = hubp2_set_blank_regs,
 	.dcc_control = hubp3_dcc_control,
+	.hubp_reset = hubp_reset,
 	.mem_program_viewport = min_set_viewport,
 	.set_cursor_attributes	= hubp32_cursor_set_attributes,
 	.set_cursor_position	= hubp2_cursor_set_position,
diff --git a/drivers/gpu/drm/amd/display/dc/hubp/dcn35/dcn35_hubp.c b/drivers/gpu/drm/amd/display/dc/hubp/dcn35/dcn35_hubp.c
index d1f05b82b3dd..e7625290c0e4 100644
--- a/drivers/gpu/drm/amd/display/dc/hubp/dcn35/dcn35_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/hubp/dcn35/dcn35_hubp.c
@@ -199,6 +199,7 @@ static struct hubp_funcs dcn35_hubp_funcs = {
 	.hubp_set_vm_system_aperture_settings = hubp3_set_vm_system_aperture_settings,
 	.set_blank = hubp2_set_blank,
 	.dcc_control = hubp3_dcc_control,
+	.hubp_reset = hubp_reset,
 	.mem_program_viewport = min_set_viewport,
 	.set_cursor_attributes	= hubp2_cursor_set_attributes,
 	.set_cursor_position	= hubp2_cursor_set_position,
diff --git a/drivers/gpu/drm/amd/display/dc/hubp/dcn401/dcn401_hubp.c b/drivers/gpu/drm/amd/display/dc/hubp/dcn401/dcn401_hubp.c
index b1ebf5053b4f..7013c124efcf 100644
--- a/drivers/gpu/drm/amd/display/dc/hubp/dcn401/dcn401_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/hubp/dcn401/dcn401_hubp.c
@@ -141,7 +141,7 @@ void hubp401_update_mall_sel(struct hubp *hubp, uint32_t mall_sel, bool c_cursor
 
 void hubp401_init(struct hubp *hubp)
 {
-	//For now nothing to do, HUBPREQ_DEBUG_DB register is removed on DCN4x.
+	hubp_reset(hubp);
 }
 
 void hubp401_vready_at_or_After_vsync(struct hubp *hubp,
@@ -718,11 +718,13 @@ void hubp401_cursor_set_position(
 			dc_fixpt_from_int(dst_x_offset),
 			param->h_scale_ratio));
 
-	if (cur_en && REG_READ(CURSOR_SURFACE_ADDRESS) == 0)
-		hubp->funcs->set_cursor_attributes(hubp, &hubp->curs_attr);
+	if (hubp->pos.cur_ctl.bits.cur_enable != cur_en) {
+		if (cur_en && REG_READ(CURSOR_SURFACE_ADDRESS) == 0)
+			hubp->funcs->set_cursor_attributes(hubp, &hubp->curs_attr);
 
-	REG_UPDATE(CURSOR_CONTROL,
-		CURSOR_ENABLE, cur_en);
+		REG_UPDATE(CURSOR_CONTROL,
+			CURSOR_ENABLE, cur_en);
+	}
 
 	REG_SET_2(CURSOR_POSITION, 0,
 		CURSOR_X_POSITION, x_pos,
@@ -974,6 +976,7 @@ static struct hubp_funcs dcn401_hubp_funcs = {
 	.hubp_set_vm_system_aperture_settings = hubp3_set_vm_system_aperture_settings,
 	.set_blank = hubp2_set_blank,
 	.set_blank_regs = hubp2_set_blank_regs,
+	.hubp_reset = hubp_reset,
 	.mem_program_viewport = hubp401_set_viewport,
 	.set_cursor_attributes	= hubp32_cursor_set_attributes,
 	.set_cursor_position	= hubp401_cursor_set_position,
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c
index 4fbed0298adf..03b22e9115ea 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c
@@ -951,8 +951,8 @@ void dce110_edp_backlight_control(
 	struct dc_context *ctx = link->ctx;
 	struct bp_transmitter_control cntl = { 0 };
 	uint8_t pwrseq_instance = 0;
-	unsigned int pre_T11_delay = OLED_PRE_T11_DELAY;
-	unsigned int post_T7_delay = OLED_POST_T7_DELAY;
+	unsigned int pre_T11_delay = (link->dpcd_sink_ext_caps.bits.oled ? OLED_PRE_T11_DELAY : 0);
+	unsigned int post_T7_delay = (link->dpcd_sink_ext_caps.bits.oled ? OLED_POST_T7_DELAY : 0);
 
 	if (dal_graphics_object_id_get_connector_id(link->link_enc->connector)
 		!= CONNECTOR_ID_EDP) {
@@ -1064,9 +1064,11 @@ void dce110_edp_backlight_control(
 			DC_LOG_DC("edp_receiver_ready_T9 skipped\n");
 	}
 
-	if (!enable && link->dpcd_sink_ext_caps.bits.oled) {
+	if (!enable) {
+		/*follow oem panel config's requirement*/
 		pre_T11_delay += link->panel_config.pps.extra_pre_t11_ms;
-		msleep(pre_T11_delay);
+		if (pre_T11_delay)
+			msleep(pre_T11_delay);
 	}
 }
 
@@ -1215,7 +1217,7 @@ void dce110_blank_stream(struct pipe_ctx *pipe_ctx)
 	struct dce_hwseq *hws = link->dc->hwseq;
 
 	if (link->local_sink && link->local_sink->sink_signal == SIGNAL_TYPE_EDP) {
-		if (!link->skip_implict_edp_power_control)
+		if (!link->skip_implict_edp_power_control && hws)
 			hws->funcs.edp_backlight_control(link, false);
 		link->dc->hwss.set_abm_immediate_disable(pipe_ctx);
 	}
@@ -1653,9 +1655,7 @@ enum dc_status dce110_apply_single_controller_ctx_to_hw(
 
 	params.vertical_total_min = stream->adjust.v_total_min;
 	params.vertical_total_max = stream->adjust.v_total_max;
-	if (pipe_ctx->stream_res.tg->funcs->set_drr)
-		pipe_ctx->stream_res.tg->funcs->set_drr(
-			pipe_ctx->stream_res.tg, &params);
+	set_drr_and_clear_adjust_pending(pipe_ctx, stream, &params);
 
 	// DRR should set trigger event to monitor surface update event
 	if (stream->adjust.v_total_min != 0 && stream->adjust.v_total_max != 0)
@@ -2103,8 +2103,7 @@ static void set_drr(struct pipe_ctx **pipe_ctx,
 		struct timing_generator *tg = pipe_ctx[i]->stream_res.tg;
 
 		if ((tg != NULL) && tg->funcs) {
-			if (tg->funcs->set_drr)
-				tg->funcs->set_drr(tg, &params);
+			set_drr_and_clear_adjust_pending(pipe_ctx[i], pipe_ctx[i]->stream, &params);
 			if (adjust.v_total_max != 0 && adjust.v_total_min != 0)
 				if (tg->funcs->set_static_screen_control)
 					tg->funcs->set_static_screen_control(
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c
index a6a1db5ba8ba..00be0b26689d 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c
@@ -1112,9 +1112,7 @@ static void dcn10_reset_back_end_for_pipe(
 		pipe_ctx->stream_res.tg->funcs->disable_crtc(pipe_ctx->stream_res.tg);
 
 		pipe_ctx->stream_res.tg->funcs->enable_optc_clock(pipe_ctx->stream_res.tg, false);
-		if (pipe_ctx->stream_res.tg->funcs->set_drr)
-			pipe_ctx->stream_res.tg->funcs->set_drr(
-					pipe_ctx->stream_res.tg, NULL);
+		set_drr_and_clear_adjust_pending(pipe_ctx, pipe_ctx->stream, NULL);
 		if (dc_is_hdmi_tmds_signal(pipe_ctx->stream->signal))
 			pipe_ctx->stream->link->phy_state.symclk_ref_cnts.otg = 0;
 	}
@@ -1286,6 +1284,7 @@ void dcn10_plane_atomic_power_down(struct dc *dc,
 		if (hws->funcs.hubp_pg_control)
 			hws->funcs.hubp_pg_control(hws, hubp->inst, false);
 
+		hubp->funcs->hubp_reset(hubp);
 		dpp->funcs->dpp_reset(dpp);
 
 		REG_SET(DC_IP_REQUEST_CNTL, 0,
@@ -1447,6 +1446,7 @@ void dcn10_init_pipes(struct dc *dc, struct dc_state *context)
 		/* Disable on the current state so the new one isn't cleared. */
 		pipe_ctx = &dc->current_state->res_ctx.pipe_ctx[i];
 
+		hubp->funcs->hubp_reset(hubp);
 		dpp->funcs->dpp_reset(dpp);
 
 		pipe_ctx->stream_res.tg = tg;
@@ -1990,20 +1990,11 @@ static void delay_cursor_until_vupdate(struct dc *dc, struct pipe_ctx *pipe_ctx)
 	dc->hwss.get_position(&pipe_ctx, 1, &position);
 	vpos = position.vertical_count;
 
-	/* Avoid wraparound calculation issues */
-	vupdate_start += stream->timing.v_total;
-	vupdate_end += stream->timing.v_total;
-	vpos += stream->timing.v_total;
-
 	if (vpos <= vupdate_start) {
 		/* VPOS is in VACTIVE or back porch. */
 		lines_to_vupdate = vupdate_start - vpos;
-	} else if (vpos > vupdate_end) {
-		/* VPOS is in the front porch. */
-		return;
 	} else {
-		/* VPOS is in VUPDATE. */
-		lines_to_vupdate = 0;
+		lines_to_vupdate = stream->timing.v_total - vpos + vupdate_start;
 	}
 
 	/* Calculate time until VUPDATE in microseconds. */
@@ -2011,13 +2002,18 @@ static void delay_cursor_until_vupdate(struct dc *dc, struct pipe_ctx *pipe_ctx)
 		stream->timing.h_total * 10000u / stream->timing.pix_clk_100hz;
 	us_to_vupdate = lines_to_vupdate * us_per_line;
 
+	/* Stall out until the cursor update completes. */
+	if (vupdate_end < vupdate_start)
+		vupdate_end += stream->timing.v_total;
+
+	/* Position is in the range of vupdate start and end*/
+	if (lines_to_vupdate > stream->timing.v_total - vupdate_end + vupdate_start)
+		us_to_vupdate = 0;
+
 	/* 70 us is a conservative estimate of cursor update time*/
 	if (us_to_vupdate > 70)
 		return;
 
-	/* Stall out until the cursor update completes. */
-	if (vupdate_end < vupdate_start)
-		vupdate_end += stream->timing.v_total;
 	us_vupdate = (vupdate_end - vupdate_start + 1) * us_per_line;
 	udelay(us_to_vupdate + us_vupdate);
 }
@@ -3219,8 +3215,7 @@ void dcn10_set_drr(struct pipe_ctx **pipe_ctx,
 		struct timing_generator *tg = pipe_ctx[i]->stream_res.tg;
 
 		if ((tg != NULL) && tg->funcs) {
-			if (tg->funcs->set_drr)
-				tg->funcs->set_drr(tg, &params);
+			set_drr_and_clear_adjust_pending(pipe_ctx[i], pipe_ctx[i]->stream, &params);
 			if (adjust.v_total_max != 0 && adjust.v_total_min != 0)
 				if (tg->funcs->set_static_screen_control)
 					tg->funcs->set_static_screen_control(
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c
index 36d12db8d022..08fc2a2c399f 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c
@@ -273,14 +273,13 @@ void dcn20_setup_gsl_group_as_lock(
 	}
 
 	/* at this point we want to program whether it's to enable or disable */
-	if (pipe_ctx->stream_res.tg->funcs->set_gsl != NULL &&
-		pipe_ctx->stream_res.tg->funcs->set_gsl_source_select != NULL) {
+	if (pipe_ctx->stream_res.tg->funcs->set_gsl != NULL) {
 		pipe_ctx->stream_res.tg->funcs->set_gsl(
 			pipe_ctx->stream_res.tg,
 			&gsl);
-
-		pipe_ctx->stream_res.tg->funcs->set_gsl_source_select(
-			pipe_ctx->stream_res.tg, group_idx,	enable ? 4 : 0);
+		if (pipe_ctx->stream_res.tg->funcs->set_gsl_source_select != NULL)
+			pipe_ctx->stream_res.tg->funcs->set_gsl_source_select(
+				pipe_ctx->stream_res.tg, group_idx, enable ? 4 : 0);
 	} else
 		BREAK_TO_DEBUGGER();
 }
@@ -946,15 +945,13 @@ enum dc_status dcn20_enable_stream_timing(
 		return DC_ERROR_UNEXPECTED;
 	}
 
-	hws->funcs.wait_for_blank_complete(pipe_ctx->stream_res.opp);
+	fsleep(stream->timing.v_total * (stream->timing.h_total * 10000u / stream->timing.pix_clk_100hz));
 
 	params.vertical_total_min = stream->adjust.v_total_min;
 	params.vertical_total_max = stream->adjust.v_total_max;
 	params.vertical_total_mid = stream->adjust.v_total_mid;
 	params.vertical_total_mid_frame_num = stream->adjust.v_total_mid_frame_num;
-	if (pipe_ctx->stream_res.tg->funcs->set_drr)
-		pipe_ctx->stream_res.tg->funcs->set_drr(
-			pipe_ctx->stream_res.tg, &params);
+	set_drr_and_clear_adjust_pending(pipe_ctx, stream, &params);
 
 	// DRR should set trigger event to monitor surface update event
 	if (stream->adjust.v_total_min != 0 && stream->adjust.v_total_max != 0)
@@ -2822,9 +2819,7 @@ void dcn20_reset_back_end_for_pipe(
 			pipe_ctx->stream_res.tg->funcs->set_odm_bypass(
 					pipe_ctx->stream_res.tg, &pipe_ctx->stream->timing);
 
-		if (pipe_ctx->stream_res.tg->funcs->set_drr)
-			pipe_ctx->stream_res.tg->funcs->set_drr(
-					pipe_ctx->stream_res.tg, NULL);
+		set_drr_and_clear_adjust_pending(pipe_ctx, pipe_ctx->stream, NULL);
 		/* TODO - convert symclk_ref_cnts for otg to a bit map to solve
 		 * the case where the same symclk is shared across multiple otg
 		 * instances
@@ -3003,7 +2998,11 @@ void dcn20_enable_stream(struct pipe_ctx *pipe_ctx)
 		dccg->funcs->set_dpstreamclk(dccg, DTBCLK0, tg->inst, dp_hpo_inst);
 
 		phyd32clk = get_phyd32clk_src(link);
-		dccg->funcs->enable_symclk32_se(dccg, dp_hpo_inst, phyd32clk);
+		if (link->cur_link_settings.link_rate == LINK_RATE_UNKNOWN) {
+			dccg->funcs->disable_symclk32_se(dccg, dp_hpo_inst);
+		} else {
+			dccg->funcs->enable_symclk32_se(dccg, dp_hpo_inst, phyd32clk);
+		}
 	} else {
 		if (dccg->funcs->enable_symclk_se)
 			dccg->funcs->enable_symclk_se(dccg, stream_enc->stream_enc_inst,
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn31/dcn31_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn31/dcn31_hwseq.c
index 3d4b31bd9946..9aa925a0b3b4 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn31/dcn31_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn31/dcn31_hwseq.c
@@ -528,9 +528,7 @@ static void dcn31_reset_back_end_for_pipe(
 	if (dc_is_hdmi_tmds_signal(pipe_ctx->stream->signal))
 		pipe_ctx->stream->link->phy_state.symclk_ref_cnts.otg = 0;
 
-	if (pipe_ctx->stream_res.tg->funcs->set_drr)
-		pipe_ctx->stream_res.tg->funcs->set_drr(
-				pipe_ctx->stream_res.tg, NULL);
+	set_drr_and_clear_adjust_pending(pipe_ctx, pipe_ctx->stream, NULL);
 
 	link = pipe_ctx->stream->link;
 	/* DPMS may already disable or */
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c
index bd309dbdf7b2..21aff7fa6375 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c
@@ -236,7 +236,8 @@ void dcn35_init_hw(struct dc *dc)
 		}
 
 		hws->funcs.init_pipes(dc, dc->current_state);
-		if (dc->res_pool->hubbub->funcs->allow_self_refresh_control)
+		if (dc->res_pool->hubbub->funcs->allow_self_refresh_control &&
+			!dc->res_pool->hubbub->ctx->dc->debug.disable_stutter)
 			dc->res_pool->hubbub->funcs->allow_self_refresh_control(dc->res_pool->hubbub,
 					!dc->res_pool->hubbub->ctx->dc->debug.disable_stutter);
 	}
@@ -787,6 +788,7 @@ void dcn35_init_pipes(struct dc *dc, struct dc_state *context)
 		/* Disable on the current state so the new one isn't cleared. */
 		pipe_ctx = &dc->current_state->res_ctx.pipe_ctx[i];
 
+		hubp->funcs->hubp_reset(hubp);
 		dpp->funcs->dpp_reset(dpp);
 
 		pipe_ctx->stream_res.tg = tg;
@@ -940,6 +942,7 @@ void dcn35_plane_atomic_disable(struct dc *dc, struct pipe_ctx *pipe_ctx)
 /*to do, need to support both case*/
 	hubp->power_gated = true;
 
+	hubp->funcs->hubp_reset(hubp);
 	dpp->funcs->dpp_reset(dpp);
 
 	pipe_ctx->stream = NULL;
@@ -1016,8 +1019,22 @@ void dcn35_calc_blocks_to_gate(struct dc *dc, struct dc_state *context,
 		if (pipe_ctx->plane_res.dpp || pipe_ctx->stream_res.opp)
 			update_state->pg_pipe_res_update[PG_MPCC][pipe_ctx->plane_res.mpcc_inst] = false;
 
-		if (pipe_ctx->stream_res.dsc)
+		if (pipe_ctx->stream_res.dsc) {
 			update_state->pg_pipe_res_update[PG_DSC][pipe_ctx->stream_res.dsc->inst] = false;
+			if (dc->caps.sequential_ono) {
+				update_state->pg_pipe_res_update[PG_HUBP][pipe_ctx->stream_res.dsc->inst] = false;
+				update_state->pg_pipe_res_update[PG_DPP][pipe_ctx->stream_res.dsc->inst] = false;
+
+				/* All HUBP/DPP instances must be powered if the DSC inst != HUBP inst */
+				if (!pipe_ctx->top_pipe && pipe_ctx->plane_res.hubp &&
+				    pipe_ctx->plane_res.hubp->inst != pipe_ctx->stream_res.dsc->inst) {
+					for (j = 0; j < dc->res_pool->pipe_count; ++j) {
+						update_state->pg_pipe_res_update[PG_HUBP][j] = false;
+						update_state->pg_pipe_res_update[PG_DPP][j] = false;
+					}
+				}
+			}
+		}
 
 		if (pipe_ctx->stream_res.opp)
 			update_state->pg_pipe_res_update[PG_OPP][pipe_ctx->stream_res.opp->inst] = false;
@@ -1162,6 +1179,25 @@ void dcn35_calc_blocks_to_ungate(struct dc *dc, struct dc_state *context,
 		update_state->pg_pipe_res_update[PG_HDMISTREAM][0] = true;
 
 	if (dc->caps.sequential_ono) {
+		for (i = 0; i < dc->res_pool->pipe_count; i++) {
+			struct pipe_ctx *new_pipe = &context->res_ctx.pipe_ctx[i];
+
+			if (new_pipe->stream_res.dsc && !new_pipe->top_pipe &&
+			    update_state->pg_pipe_res_update[PG_DSC][new_pipe->stream_res.dsc->inst]) {
+				update_state->pg_pipe_res_update[PG_HUBP][new_pipe->stream_res.dsc->inst] = true;
+				update_state->pg_pipe_res_update[PG_DPP][new_pipe->stream_res.dsc->inst] = true;
+
+				/* All HUBP/DPP instances must be powered if the DSC inst != HUBP inst */
+				if (new_pipe->plane_res.hubp &&
+				    new_pipe->plane_res.hubp->inst != new_pipe->stream_res.dsc->inst) {
+					for (j = 0; j < dc->res_pool->pipe_count; ++j) {
+						update_state->pg_pipe_res_update[PG_HUBP][j] = true;
+						update_state->pg_pipe_res_update[PG_DPP][j] = true;
+					}
+				}
+			}
+		}
+
 		for (i = dc->res_pool->pipe_count - 1; i >= 0; i--) {
 			if (update_state->pg_pipe_res_update[PG_HUBP][i] &&
 			    update_state->pg_pipe_res_update[PG_DPP][i]) {
@@ -1449,8 +1485,7 @@ void dcn35_set_drr(struct pipe_ctx **pipe_ctx,
 					num_frames = 2 * (frame_rate % 60);
 				}
 			}
-			if (tg->funcs->set_drr)
-				tg->funcs->set_drr(tg, &params);
+			set_drr_and_clear_adjust_pending(pipe_ctx[i], pipe_ctx[i]->stream, &params);
 			if (adjust.v_total_max != 0 && adjust.v_total_min != 0)
 				if (tg->funcs->set_static_screen_control)
 					tg->funcs->set_static_screen_control(
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c
index 0b743669f23b..3279f347660c 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c
@@ -844,6 +844,13 @@ enum dc_status dcn401_enable_stream_timing(
 				odm_slice_width, last_odm_slice_width);
 	}
 
+	/* set DTBCLK_P */
+	if (dc->res_pool->dccg->funcs->set_dtbclk_p_src) {
+		if (dc_is_dp_signal(stream->signal) || dc_is_virtual_signal(stream->signal)) {
+			dc->res_pool->dccg->funcs->set_dtbclk_p_src(dc->res_pool->dccg, DPREFCLK, pipe_ctx->stream_res.tg->inst);
+		}
+	}
+
 	/* HW program guide assume display already disable
 	 * by unplug sequence. OTG assume stop.
 	 */
@@ -895,10 +902,7 @@ enum dc_status dcn401_enable_stream_timing(
 	}
 
 	hws->funcs.wait_for_blank_complete(pipe_ctx->stream_res.opp);
-
-	if (pipe_ctx->stream_res.tg->funcs->set_drr)
-		pipe_ctx->stream_res.tg->funcs->set_drr(
-			pipe_ctx->stream_res.tg, &params);
+	set_drr_and_clear_adjust_pending(pipe_ctx, stream, &params);
 
 	/* Event triggers and num frames initialized for DRR, but can be
 	 * later updated for PSR use. Note DRR trigger events are generated
@@ -1001,11 +1005,12 @@ void dcn401_enable_stream(struct pipe_ctx *pipe_ctx)
 	if (dc_is_dp_signal(pipe_ctx->stream->signal) || dc_is_virtual_signal(pipe_ctx->stream->signal)) {
 		if (dc->link_srv->dp_is_128b_132b_signal(pipe_ctx)) {
 			dccg->funcs->set_dpstreamclk(dccg, DPREFCLK, tg->inst, dp_hpo_inst);
-
-			dccg->funcs->enable_symclk32_se(dccg, dp_hpo_inst, phyd32clk);
+			if (link->cur_link_settings.link_rate == LINK_RATE_UNKNOWN) {
+				dccg->funcs->disable_symclk32_se(dccg, dp_hpo_inst);
+			} else {
+				dccg->funcs->enable_symclk32_se(dccg, dp_hpo_inst, phyd32clk);
+			}
 		} else {
-			/* need to set DTBCLK_P source to DPREFCLK for DP8B10B */
-			dccg->funcs->set_dtbclk_p_src(dccg, DPREFCLK, tg->inst);
 			dccg->funcs->enable_symclk_se(dccg, stream_enc->stream_enc_inst,
 					link_enc->transmitter - TRANSMITTER_UNIPHY_A);
 		}
@@ -1770,3 +1775,128 @@ void dcn401_program_outstanding_updates(struct dc *dc,
 	if (hubbub->funcs->program_compbuf_segments)
 		hubbub->funcs->program_compbuf_segments(hubbub, context->bw_ctx.bw.dcn.arb_regs.compbuf_size, true);
 }
+
+void dcn401_reset_back_end_for_pipe(
+		struct dc *dc,
+		struct pipe_ctx *pipe_ctx,
+		struct dc_state *context)
+{
+	int i;
+	struct dc_link *link = pipe_ctx->stream->link;
+	const struct link_hwss *link_hwss = get_link_hwss(link, &pipe_ctx->link_res);
+
+	DC_LOGGER_INIT(dc->ctx->logger);
+	if (pipe_ctx->stream_res.stream_enc == NULL) {
+		pipe_ctx->stream = NULL;
+		return;
+	}
+
+	/* DPMS may already disable or */
+	/* dpms_off status is incorrect due to fastboot
+	 * feature. When system resume from S4 with second
+	 * screen only, the dpms_off would be true but
+	 * VBIOS lit up eDP, so check link status too.
+	 */
+	if (!pipe_ctx->stream->dpms_off || link->link_status.link_active)
+		dc->link_srv->set_dpms_off(pipe_ctx);
+	else if (pipe_ctx->stream_res.audio)
+		dc->hwss.disable_audio_stream(pipe_ctx);
+
+	/* free acquired resources */
+	if (pipe_ctx->stream_res.audio) {
+		/*disable az_endpoint*/
+		pipe_ctx->stream_res.audio->funcs->az_disable(pipe_ctx->stream_res.audio);
+
+		/*free audio*/
+		if (dc->caps.dynamic_audio == true) {
+			/*we have to dynamic arbitrate the audio endpoints*/
+			/*we free the resource, need reset is_audio_acquired*/
+			update_audio_usage(&dc->current_state->res_ctx, dc->res_pool,
+					pipe_ctx->stream_res.audio, false);
+			pipe_ctx->stream_res.audio = NULL;
+		}
+	}
+
+	/* by upper caller loop, parent pipe: pipe0, will be reset last.
+	 * back end share by all pipes and will be disable only when disable
+	 * parent pipe.
+	 */
+	if (pipe_ctx->top_pipe == NULL) {
+
+		dc->hwss.set_abm_immediate_disable(pipe_ctx);
+
+		pipe_ctx->stream_res.tg->funcs->disable_crtc(pipe_ctx->stream_res.tg);
+
+		pipe_ctx->stream_res.tg->funcs->enable_optc_clock(pipe_ctx->stream_res.tg, false);
+		if (pipe_ctx->stream_res.tg->funcs->set_odm_bypass)
+			pipe_ctx->stream_res.tg->funcs->set_odm_bypass(
+					pipe_ctx->stream_res.tg, &pipe_ctx->stream->timing);
+
+		set_drr_and_clear_adjust_pending(pipe_ctx, pipe_ctx->stream, NULL);
+
+		/* TODO - convert symclk_ref_cnts for otg to a bit map to solve
+		 * the case where the same symclk is shared across multiple otg
+		 * instances
+		 */
+		if (dc_is_hdmi_tmds_signal(pipe_ctx->stream->signal))
+			link->phy_state.symclk_ref_cnts.otg = 0;
+		if (link->phy_state.symclk_state == SYMCLK_ON_TX_OFF) {
+			link_hwss->disable_link_output(link,
+					&pipe_ctx->link_res, pipe_ctx->stream->signal);
+			link->phy_state.symclk_state = SYMCLK_OFF_TX_OFF;
+		}
+
+		/* reset DTBCLK_P */
+		if (dc->res_pool->dccg->funcs->set_dtbclk_p_src)
+			dc->res_pool->dccg->funcs->set_dtbclk_p_src(dc->res_pool->dccg, REFCLK, pipe_ctx->stream_res.tg->inst);
+	}
+
+	for (i = 0; i < dc->res_pool->pipe_count; i++)
+		if (&dc->current_state->res_ctx.pipe_ctx[i] == pipe_ctx)
+			break;
+
+	if (i == dc->res_pool->pipe_count)
+		return;
+
+/*
+ * In case of a dangling plane, setting this to NULL unconditionally
+ * causes failures during reset hw ctx where, if stream is NULL,
+ * it is expected that the pipe_ctx pointers to pipes and plane are NULL.
+ */
+	pipe_ctx->stream = NULL;
+	DC_LOG_DEBUG("Reset back end for pipe %d, tg:%d\n",
+					pipe_ctx->pipe_idx, pipe_ctx->stream_res.tg->inst);
+}
+
+void dcn401_reset_hw_ctx_wrap(
+		struct dc *dc,
+		struct dc_state *context)
+{
+	int i;
+	struct dce_hwseq *hws = dc->hwseq;
+
+	/* Reset Back End*/
+	for (i = dc->res_pool->pipe_count - 1; i >= 0 ; i--) {
+		struct pipe_ctx *pipe_ctx_old =
+			&dc->current_state->res_ctx.pipe_ctx[i];
+		struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
+
+		if (!pipe_ctx_old->stream)
+			continue;
+
+		if (pipe_ctx_old->top_pipe || pipe_ctx_old->prev_odm_pipe)
+			continue;
+
+		if (!pipe_ctx->stream ||
+				pipe_need_reprogram(pipe_ctx_old, pipe_ctx)) {
+			struct clock_source *old_clk = pipe_ctx_old->clock_source;
+
+			if (hws->funcs.reset_back_end_for_pipe)
+				hws->funcs.reset_back_end_for_pipe(dc, pipe_ctx_old, dc->current_state);
+			if (hws->funcs.enable_stream_gating)
+				hws->funcs.enable_stream_gating(dc, pipe_ctx_old);
+			if (old_clk)
+				old_clk->funcs->cs_power_down(old_clk);
+		}
+	}
+}
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.h b/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.h
index a27e62081685..6256429c8a4f 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.h
@@ -84,4 +84,11 @@ void adjust_hotspot_between_slices_for_2x_magnify(uint32_t cursor_width, struct
 void dcn401_wait_for_det_buffer_update(struct dc *dc, struct dc_state *context, struct pipe_ctx *otg_master);
 void dcn401_interdependent_update_lock(struct dc *dc, struct dc_state *context, bool lock);
 void dcn401_program_outstanding_updates(struct dc *dc, struct dc_state *context);
+void dcn401_reset_back_end_for_pipe(
+		struct dc *dc,
+		struct pipe_ctx *pipe_ctx,
+		struct dc_state *context);
+void dcn401_reset_hw_ctx_wrap(
+		struct dc *dc,
+		struct dc_state *context);
 #endif /* __DC_HWSS_DCN401_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_init.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_init.c
index a2ca07235c83..d6f36b8e1a26 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_init.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_init.c
@@ -111,7 +111,7 @@ static const struct hwseq_private_funcs dcn401_private_funcs = {
 	.power_down = dce110_power_down,
 	.enable_display_power_gating = dcn10_dummy_display_power_gating,
 	.blank_pixel_data = dcn20_blank_pixel_data,
-	.reset_hw_ctx_wrap = dcn20_reset_hw_ctx_wrap,
+	.reset_hw_ctx_wrap = dcn401_reset_hw_ctx_wrap,
 	.enable_stream_timing = dcn401_enable_stream_timing,
 	.edp_backlight_control = dce110_edp_backlight_control,
 	.setup_vupdate_interrupt = dcn20_setup_vupdate_interrupt,
@@ -136,7 +136,7 @@ static const struct hwseq_private_funcs dcn401_private_funcs = {
 	.update_mall_sel = dcn32_update_mall_sel,
 	.calculate_dccg_k1_k2_values = NULL,
 	.apply_single_controller_ctx_to_hw = dce110_apply_single_controller_ctx_to_hw,
-	.reset_back_end_for_pipe = dcn20_reset_back_end_for_pipe,
+	.reset_back_end_for_pipe = dcn401_reset_back_end_for_pipe,
 	.populate_mcm_luts = NULL,
 };
 
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer.h
index ac9205625623..9ae6259f2db1 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer.h
+++ b/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer.h
@@ -46,6 +46,7 @@ struct dce_hwseq;
 struct link_resource;
 struct dc_dmub_cmd;
 struct pg_block_update;
+struct drr_params;
 
 struct subvp_pipe_control_lock_fast_params {
 	struct dc *dc;
@@ -509,6 +510,11 @@ void set_p_state_switch_method(
 		struct dc_state *context,
 		struct pipe_ctx *pipe_ctx);
 
+void set_drr_and_clear_adjust_pending(
+		struct pipe_ctx *pipe_ctx,
+		struct dc_stream_state *stream,
+		struct drr_params *params);
+
 void hwss_execute_sequence(struct dc *dc,
 		struct block_sequence block_sequence[],
 		int num_steps);
diff --git a/drivers/gpu/drm/amd/display/dc/inc/core_types.h b/drivers/gpu/drm/amd/display/dc/inc/core_types.h
index e1e3142cdc00..62fb2009b302 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/core_types.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/core_types.h
@@ -621,7 +621,7 @@ struct dc_state {
 	 */
 	struct bw_context bw_ctx;
 
-	struct block_sequence block_sequence[50];
+	struct block_sequence block_sequence[100];
 	unsigned int block_sequence_steps;
 	struct dc_dmub_cmd dc_dmub_cmd[10];
 	unsigned int dmub_cmd_count;
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr_internal.h b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr_internal.h
index c2dd061892f4..221645c023b5 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr_internal.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr_internal.h
@@ -166,6 +166,41 @@ enum dentist_divider_range {
     CLK_SR_DCN32(CLK1_CLK4_CURRENT_CNT), \
     CLK_SR_DCN32(CLK4_CLK0_CURRENT_CNT)
 
+#define CLK_REG_LIST_DCN35()	  \
+	CLK_SR_DCN35(CLK1_CLK_PLL_REQ), \
+	CLK_SR_DCN35(CLK1_CLK0_DFS_CNTL), \
+	CLK_SR_DCN35(CLK1_CLK1_DFS_CNTL), \
+	CLK_SR_DCN35(CLK1_CLK2_DFS_CNTL), \
+	CLK_SR_DCN35(CLK1_CLK3_DFS_CNTL), \
+	CLK_SR_DCN35(CLK1_CLK4_DFS_CNTL), \
+	CLK_SR_DCN35(CLK1_CLK5_DFS_CNTL), \
+	CLK_SR_DCN35(CLK1_CLK0_CURRENT_CNT), \
+	CLK_SR_DCN35(CLK1_CLK1_CURRENT_CNT), \
+	CLK_SR_DCN35(CLK1_CLK2_CURRENT_CNT), \
+	CLK_SR_DCN35(CLK1_CLK3_CURRENT_CNT), \
+	CLK_SR_DCN35(CLK1_CLK4_CURRENT_CNT), \
+	CLK_SR_DCN35(CLK1_CLK5_CURRENT_CNT), \
+	CLK_SR_DCN35(CLK1_CLK0_BYPASS_CNTL), \
+	CLK_SR_DCN35(CLK1_CLK1_BYPASS_CNTL), \
+	CLK_SR_DCN35(CLK1_CLK2_BYPASS_CNTL), \
+	CLK_SR_DCN35(CLK1_CLK3_BYPASS_CNTL), \
+	CLK_SR_DCN35(CLK1_CLK4_BYPASS_CNTL),\
+	CLK_SR_DCN35(CLK1_CLK5_BYPASS_CNTL), \
+	CLK_SR_DCN35(CLK1_CLK0_DS_CNTL), \
+	CLK_SR_DCN35(CLK1_CLK1_DS_CNTL), \
+	CLK_SR_DCN35(CLK1_CLK2_DS_CNTL), \
+	CLK_SR_DCN35(CLK1_CLK3_DS_CNTL), \
+	CLK_SR_DCN35(CLK1_CLK4_DS_CNTL), \
+	CLK_SR_DCN35(CLK1_CLK5_DS_CNTL), \
+	CLK_SR_DCN35(CLK1_CLK0_ALLOW_DS), \
+	CLK_SR_DCN35(CLK1_CLK1_ALLOW_DS), \
+	CLK_SR_DCN35(CLK1_CLK2_ALLOW_DS), \
+	CLK_SR_DCN35(CLK1_CLK3_ALLOW_DS), \
+	CLK_SR_DCN35(CLK1_CLK4_ALLOW_DS), \
+	CLK_SR_DCN35(CLK1_CLK5_ALLOW_DS), \
+	CLK_SR_DCN35(CLK5_spll_field_8), \
+	SR(DENTIST_DISPCLK_CNTL), \
+
 #define CLK_COMMON_MASK_SH_LIST_DCN32(mask_sh) \
 	CLK_COMMON_MASK_SH_LIST_DCN20_BASE(mask_sh),\
 	CLK_SF(CLK1_CLK_PLL_REQ, FbMult_int, mask_sh),\
@@ -186,6 +221,7 @@ enum dentist_divider_range {
 	CLK_SF(CLK0_CLK_PLL_REQ, FbMult_frac, mask_sh)
 
 #define CLK_REG_LIST_DCN401()	  \
+	SR(DENTIST_DISPCLK_CNTL), \
 	CLK_SR_DCN401(CLK0_CLK_PLL_REQ,   CLK01, 0), \
 	CLK_SR_DCN401(CLK0_CLK0_DFS_CNTL, CLK01, 0), \
 	CLK_SR_DCN401(CLK0_CLK1_DFS_CNTL,  CLK01, 0), \
@@ -236,6 +272,7 @@ struct clk_mgr_registers {
 	uint32_t CLK1_CLK2_DFS_CNTL;
 	uint32_t CLK1_CLK3_DFS_CNTL;
 	uint32_t CLK1_CLK4_DFS_CNTL;
+	uint32_t CLK1_CLK5_DFS_CNTL;
 	uint32_t CLK2_CLK2_DFS_CNTL;
 
 	uint32_t CLK1_CLK0_CURRENT_CNT;
@@ -243,11 +280,34 @@ struct clk_mgr_registers {
     uint32_t CLK1_CLK2_CURRENT_CNT;
     uint32_t CLK1_CLK3_CURRENT_CNT;
     uint32_t CLK1_CLK4_CURRENT_CNT;
+	uint32_t CLK1_CLK5_CURRENT_CNT;
 
 	uint32_t CLK0_CLK0_DFS_CNTL;
 	uint32_t CLK0_CLK1_DFS_CNTL;
 	uint32_t CLK0_CLK3_DFS_CNTL;
 	uint32_t CLK0_CLK4_DFS_CNTL;
+	uint32_t CLK1_CLK0_BYPASS_CNTL;
+	uint32_t CLK1_CLK1_BYPASS_CNTL;
+	uint32_t CLK1_CLK2_BYPASS_CNTL;
+	uint32_t CLK1_CLK3_BYPASS_CNTL;
+	uint32_t CLK1_CLK4_BYPASS_CNTL;
+	uint32_t CLK1_CLK5_BYPASS_CNTL;
+
+	uint32_t CLK1_CLK0_DS_CNTL;
+	uint32_t CLK1_CLK1_DS_CNTL;
+	uint32_t CLK1_CLK2_DS_CNTL;
+	uint32_t CLK1_CLK3_DS_CNTL;
+	uint32_t CLK1_CLK4_DS_CNTL;
+	uint32_t CLK1_CLK5_DS_CNTL;
+
+	uint32_t CLK1_CLK0_ALLOW_DS;
+	uint32_t CLK1_CLK1_ALLOW_DS;
+	uint32_t CLK1_CLK2_ALLOW_DS;
+	uint32_t CLK1_CLK3_ALLOW_DS;
+	uint32_t CLK1_CLK4_ALLOW_DS;
+	uint32_t CLK1_CLK5_ALLOW_DS;
+	uint32_t CLK5_spll_field_8;
+
 };
 
 struct clk_mgr_shift {
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h b/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h
index 0150f2581ee4..0c5675d1c593 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h
@@ -119,10 +119,14 @@ static const struct dpp_input_csc_matrix __maybe_unused dpp_input_csc_matrix[] =
 		{ 0x39a6, 0x2568, 0,      0xe0d6,
 		  0xeedd, 0x2568, 0xf925, 0x9a8,
 		  0,      0x2568, 0x43ee, 0xdbb2 } },
-	{ COLOR_SPACE_2020_YCBCR,
+	{ COLOR_SPACE_2020_YCBCR_FULL,
 		{ 0x2F30, 0x2000, 0,      0xE869,
 		  0xEDB7, 0x2000, 0xFABC, 0xBC6,
 		  0,      0x2000, 0x3C34, 0xE1E6 } },
+	{ COLOR_SPACE_2020_YCBCR_LIMITED,
+		{ 0x35B9, 0x2543, 0,      0xE2B2,
+		  0xEB2F, 0x2543, 0xFA01, 0x0B1F,
+		  0,      0x2543, 0x4489, 0xDB42 } },
 	{ COLOR_SPACE_2020_RGB_LIMITEDRANGE,
 		{ 0x35E0, 0x255F, 0,      0xE2B3,
 		  0xEB20, 0x255F, 0xF9FD, 0xB1E,
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h b/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h
index 16580d624278..eec16b0a199d 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h
@@ -152,6 +152,8 @@ struct hubp_funcs {
 	void (*dcc_control)(struct hubp *hubp, bool enable,
 			enum hubp_ind_block_size blk_size);
 
+	void (*hubp_reset)(struct hubp *hubp);
+
 	void (*mem_program_viewport)(
 			struct hubp *hubp,
 			const struct rect *viewport,
diff --git a/drivers/gpu/drm/amd/display/dc/link/link_dpms.c b/drivers/gpu/drm/amd/display/dc/link/link_dpms.c
index c4e03482ba9a..9d740659521a 100644
--- a/drivers/gpu/drm/amd/display/dc/link/link_dpms.c
+++ b/drivers/gpu/drm/amd/display/dc/link/link_dpms.c
@@ -140,7 +140,8 @@ void link_blank_dp_stream(struct dc_link *link, bool hw_init)
 				}
 		}
 
-		if ((!link->wa_flags.dp_keep_receiver_powered) || hw_init)
+		if (((!link->wa_flags.dp_keep_receiver_powered) || hw_init) &&
+			(link->type != dc_connection_none))
 			dpcd_write_rx_power_ctrl(link, false);
 	}
 }
@@ -148,6 +149,7 @@ void link_blank_dp_stream(struct dc_link *link, bool hw_init)
 void link_set_all_streams_dpms_off_for_link(struct dc_link *link)
 {
 	struct pipe_ctx *pipes[MAX_PIPES];
+	struct dc_stream_state *streams[MAX_PIPES];
 	struct dc_state *state = link->dc->current_state;
 	uint8_t count;
 	int i;
@@ -160,10 +162,18 @@ void link_set_all_streams_dpms_off_for_link(struct dc_link *link)
 
 	link_get_master_pipes_with_dpms_on(link, state, &count, pipes);
 
+	/* The subsequent call to dc_commit_updates_for_stream for a full update
+	 * will release the current state and swap to a new state. Releasing the
+	 * current state results in the stream pointers in the pipe_ctx structs
+	 * to be zero'd. Hence, cache all streams prior to dc_commit_updates_for_stream.
+	 */
+	for (i = 0; i < count; i++)
+		streams[i] = pipes[i]->stream;
+
 	for (i = 0; i < count; i++) {
-		stream_update.stream = pipes[i]->stream;
+		stream_update.stream = streams[i];
 		dc_commit_updates_for_stream(link->ctx->dc, NULL, 0,
-				pipes[i]->stream, &stream_update,
+				streams[i], &stream_update,
 				state);
 	}
 
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c
index d78c8ec4de79..842636c7922b 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c
@@ -51,9 +51,10 @@
 #include "dc_dmub_srv.h"
 #include "gpio_service_interface.h"
 
+#define DC_TRACE_LEVEL_MESSAGE(...) /* do nothing */
+
 #define DC_LOGGER \
 	link->ctx->logger
-#define DC_TRACE_LEVEL_MESSAGE(...) /* do nothing */
 
 #ifndef MAX
 #define MAX(X, Y) ((X) > (Y) ? (X) : (Y))
@@ -249,21 +250,21 @@ static uint32_t intersect_frl_link_bw_support(
 {
 	uint32_t supported_bw_in_kbps = max_supported_frl_bw_in_kbps;
 
-	// HDMI_ENCODED_LINK_BW bits are only valid if HDMI Link Configuration bit is 1 (FRL mode)
-	if (hdmi_encoded_link_bw.bits.FRL_MODE) {
-		if (hdmi_encoded_link_bw.bits.BW_48Gbps)
-			supported_bw_in_kbps = 48000000;
-		else if (hdmi_encoded_link_bw.bits.BW_40Gbps)
-			supported_bw_in_kbps = 40000000;
-		else if (hdmi_encoded_link_bw.bits.BW_32Gbps)
-			supported_bw_in_kbps = 32000000;
-		else if (hdmi_encoded_link_bw.bits.BW_24Gbps)
-			supported_bw_in_kbps = 24000000;
-		else if (hdmi_encoded_link_bw.bits.BW_18Gbps)
-			supported_bw_in_kbps = 18000000;
-		else if (hdmi_encoded_link_bw.bits.BW_9Gbps)
-			supported_bw_in_kbps = 9000000;
-	}
+	/* Skip checking FRL_MODE bit, as certain PCON will clear
+	 * it despite supporting the link BW indicated in the other bits.
+	 */
+	if (hdmi_encoded_link_bw.bits.BW_48Gbps)
+		supported_bw_in_kbps = 48000000;
+	else if (hdmi_encoded_link_bw.bits.BW_40Gbps)
+		supported_bw_in_kbps = 40000000;
+	else if (hdmi_encoded_link_bw.bits.BW_32Gbps)
+		supported_bw_in_kbps = 32000000;
+	else if (hdmi_encoded_link_bw.bits.BW_24Gbps)
+		supported_bw_in_kbps = 24000000;
+	else if (hdmi_encoded_link_bw.bits.BW_18Gbps)
+		supported_bw_in_kbps = 18000000;
+	else if (hdmi_encoded_link_bw.bits.BW_9Gbps)
+		supported_bw_in_kbps = 9000000;
 
 	return supported_bw_in_kbps;
 }
@@ -944,6 +945,9 @@ bool link_decide_link_settings(struct dc_stream_state *stream,
 		 * TODO: add MST specific link training routine
 		 */
 		decide_mst_link_settings(link, link_setting);
+	} else if (stream->signal == SIGNAL_TYPE_VIRTUAL) {
+		link_setting->lane_count = LANE_COUNT_FOUR;
+		link_setting->link_rate = LINK_RATE_HIGH3;
 	} else if (link->connector_signal == SIGNAL_TYPE_EDP) {
 		/* enable edp link optimization for DSC eDP case */
 		if (stream->timing.flags.DSC) {
@@ -966,9 +970,6 @@ bool link_decide_link_settings(struct dc_stream_state *stream,
 		} else {
 			edp_decide_link_settings(link, link_setting, req_bw);
 		}
-	} else if (stream->signal == SIGNAL_TYPE_VIRTUAL) {
-		link_setting->lane_count = LANE_COUNT_FOUR;
-		link_setting->link_rate = LINK_RATE_HIGH3;
 	} else {
 		decide_dp_link_settings(link, link_setting, req_bw);
 	}
@@ -1494,7 +1495,7 @@ static bool dpcd_read_sink_ext_caps(struct dc_link *link)
 
 enum dc_status dp_retrieve_lttpr_cap(struct dc_link *link)
 {
-	uint8_t lttpr_dpcd_data[8] = {0};
+	uint8_t lttpr_dpcd_data[10] = {0};
 	enum dc_status status;
 	bool is_lttpr_present;
 
@@ -1544,6 +1545,10 @@ enum dc_status dp_retrieve_lttpr_cap(struct dc_link *link)
 			lttpr_dpcd_data[DP_PHY_REPEATER_128B132B_RATES -
 							DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV];
 
+	link->dpcd_caps.lttpr_caps.alpm.raw =
+			lttpr_dpcd_data[DP_LTTPR_ALPM_CAPABILITIES -
+							DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV];
+
 	/* If this chip cap is set, at least one retimer must exist in the chain
 	 * Override count to 1 if we receive a known bad count (0 or an invalid value) */
 	if ((link->chip_caps & EXT_DISPLAY_PATH_CAPS__DP_FIXED_VS_EN) &&
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_phy.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_phy.c
index bafa52a0165a..17c57cf98ec5 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_phy.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_phy.c
@@ -75,7 +75,8 @@ void dp_disable_link_phy(struct dc_link *link,
 	struct dc  *dc = link->ctx->dc;
 
 	if (!link->wa_flags.dp_keep_receiver_powered &&
-		!link->skip_implict_edp_power_control)
+			!link->skip_implict_edp_power_control &&
+			link->type != dc_connection_none)
 		dpcd_write_rx_power_ctrl(link, false);
 
 	dc->hwss.disable_link_output(link, link_res, signal);
@@ -163,8 +164,9 @@ enum dc_status dp_set_fec_ready(struct dc_link *link, const struct link_resource
 	} else {
 		if (link->fec_state == dc_link_fec_ready) {
 			fec_config = 0;
-			core_link_write_dpcd(link, DP_FEC_CONFIGURATION,
-				&fec_config, sizeof(fec_config));
+			if (link->type != dc_connection_none)
+				core_link_write_dpcd(link, DP_FEC_CONFIGURATION,
+					&fec_config, sizeof(fec_config));
 
 			link_enc->funcs->fec_set_ready(link_enc, false);
 			link->fec_state = dc_link_fec_not_ready;
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c
index 27b881f947e8..9385a32a471b 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c
@@ -1769,13 +1769,10 @@ bool perform_link_training_with_retries(
 			is_link_bw_min = ((cur_link_settings.link_rate <= LINK_RATE_LOW) &&
 				(cur_link_settings.lane_count <= LANE_COUNT_ONE));
 
-			if (is_link_bw_low) {
+			if (is_link_bw_low)
 				DC_LOG_WARNING(
 					"%s: Link(%d) bandwidth too low after fallback req_bw(%d) > link_bw(%d)\n",
 					__func__, link->link_index, req_bw, link_bw);
-
-				return false;
-			}
 		}
 
 		msleep(delay_between_attempts);
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_8b_10b.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_8b_10b.c
index 3bdce32a85e3..ae95ec48e572 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_8b_10b.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_8b_10b.c
@@ -36,7 +36,8 @@
 	link->ctx->logger
 
 static int32_t get_cr_training_aux_rd_interval(struct dc_link *link,
-		const struct dc_link_settings *link_settings)
+		const struct dc_link_settings *link_settings,
+		enum lttpr_mode lttpr_mode)
 {
 	union training_aux_rd_interval training_rd_interval;
 	uint32_t wait_in_micro_secs = 100;
@@ -49,6 +50,8 @@ static int32_t get_cr_training_aux_rd_interval(struct dc_link *link,
 				DP_TRAINING_AUX_RD_INTERVAL,
 				(uint8_t *)&training_rd_interval,
 				sizeof(training_rd_interval));
+		if (lttpr_mode != LTTPR_MODE_NON_TRANSPARENT)
+			wait_in_micro_secs = 400;
 		if (training_rd_interval.bits.TRAINIG_AUX_RD_INTERVAL)
 			wait_in_micro_secs = training_rd_interval.bits.TRAINIG_AUX_RD_INTERVAL * 4000;
 	}
@@ -110,7 +113,6 @@ void decide_8b_10b_training_settings(
 	 */
 	lt_settings->link_settings.link_spread = link->dp_ss_off ?
 			LINK_SPREAD_DISABLED : LINK_SPREAD_05_DOWNSPREAD_30KHZ;
-	lt_settings->cr_pattern_time = get_cr_training_aux_rd_interval(link, link_setting);
 	lt_settings->eq_pattern_time = get_eq_training_aux_rd_interval(link, link_setting);
 	lt_settings->pattern_for_cr = decide_cr_training_pattern(link_setting);
 	lt_settings->pattern_for_eq = decide_eq_training_pattern(link, link_setting);
@@ -119,6 +121,7 @@ void decide_8b_10b_training_settings(
 	lt_settings->disallow_per_lane_settings = true;
 	lt_settings->always_match_dpcd_with_hw_lane_settings = true;
 	lt_settings->lttpr_mode = dp_decide_8b_10b_lttpr_mode(link);
+	lt_settings->cr_pattern_time = get_cr_training_aux_rd_interval(link, link_setting, lt_settings->lttpr_mode);
 	dp_hw_to_dpcd_lane_settings(lt_settings, lt_settings->hw_lane_settings, lt_settings->dpcd_lane_settings);
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c
index 3aa05a2be6c0..fa642f4b88c2 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c
@@ -674,6 +674,18 @@ bool edp_setup_psr(struct dc_link *link,
 	if (!link)
 		return false;
 
+	//Clear PSR cfg
+	memset(&psr_configuration, 0, sizeof(psr_configuration));
+	dm_helpers_dp_write_dpcd(
+		link->ctx,
+		link,
+		DP_PSR_EN_CFG,
+		&psr_configuration.raw,
+		sizeof(psr_configuration.raw));
+
+	if (link->psr_settings.psr_version == DC_PSR_VERSION_UNSUPPORTED)
+		return false;
+
 	dc = link->ctx->dc;
 	dmcu = dc->res_pool->dmcu;
 	psr = dc->res_pool->psr;
@@ -684,9 +696,6 @@ bool edp_setup_psr(struct dc_link *link,
 	if (!dc_get_edp_link_panel_inst(dc, link, &panel_inst))
 		return false;
 
-
-	memset(&psr_configuration, 0, sizeof(psr_configuration));
-
 	psr_configuration.bits.ENABLE                    = 1;
 	psr_configuration.bits.CRC_VERIFICATION          = 1;
 	psr_configuration.bits.FRAME_CAPTURE_INDICATION  =
@@ -950,6 +959,16 @@ bool edp_setup_replay(struct dc_link *link, const struct dc_stream_state *stream
 	if (!link)
 		return false;
 
+	//Clear Replay config
+	dm_helpers_dp_write_dpcd(link->ctx, link,
+		DP_SINK_PR_ENABLE_AND_CONFIGURATION,
+		(uint8_t *)&(replay_config.raw), sizeof(uint8_t));
+
+	if (!(link->replay_settings.config.replay_supported))
+		return false;
+
+	link->replay_settings.config.replay_error_status.raw = 0;
+
 	dc = link->ctx->dc;
 
 	replay = dc->res_pool->replay;
diff --git a/drivers/gpu/drm/amd/display/dc/mpc/dcn401/dcn401_mpc.c b/drivers/gpu/drm/amd/display/dc/mpc/dcn401/dcn401_mpc.c
index 37ab5a4eefc7..0f531cfd3c49 100644
--- a/drivers/gpu/drm/amd/display/dc/mpc/dcn401/dcn401_mpc.c
+++ b/drivers/gpu/drm/amd/display/dc/mpc/dcn401/dcn401_mpc.c
@@ -571,7 +571,7 @@ void mpc401_get_gamut_remap(struct mpc *mpc,
 	struct mpc_grph_gamut_adjustment *adjust)
 {
 	uint16_t arr_reg_val[12] = {0};
-	uint32_t mode_select;
+	uint32_t mode_select = MPCC_GAMUT_REMAP_MODE_SELECT_0;
 
 	read_gamut_remap(mpc, mpcc_id, arr_reg_val, adjust->mpcc_gamut_remap_block_id, &mode_select);
 
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn301/dcn301_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn301/dcn301_resource.c
index 7d04739c3ba1..4bbbe07ecde7 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn301/dcn301_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn301/dcn301_resource.c
@@ -671,9 +671,9 @@ static const struct dc_plane_cap plane_cap = {
 
 	/* 6:1 downscaling ratio: 1000/6 = 166.666 */
 	.max_downscale_factor = {
-			.argb8888 = 167,
-			.nv12 = 167,
-			.fp16 = 167 
+			.argb8888 = 358,
+			.nv12 = 358,
+			.fp16 = 358
 	},
 	64,
 	64
@@ -694,7 +694,7 @@ static const struct dc_debug_options debug_defaults_drv = {
 	.disable_dcc = DCC_ENABLE,
 	.vsr_support = true,
 	.performance_trace = false,
-	.max_downscale_src_width = 7680,/*upto 8K*/
+	.max_downscale_src_width = 4096,/*upto true 4k*/
 	.scl_reset_length10 = true,
 	.sanity_checks = false,
 	.underflow_assert_delay_us = 0xFFFFFFFF,
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn31/dcn31_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn31/dcn31_resource.c
index 80386f698ae4..0ca6358a9782 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn31/dcn31_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn31/dcn31_resource.c
@@ -891,7 +891,7 @@ static const struct dc_debug_options debug_defaults_drv = {
 	.disable_z10 = true,
 	.enable_legacy_fast_update = true,
 	.enable_z9_disable_interface = true, /* Allow support for the PMFW interface for disable Z9*/
-	.dml_hostvm_override = DML_HOSTVM_NO_OVERRIDE,
+	.dml_hostvm_override = DML_HOSTVM_OVERRIDE_FALSE,
 	.using_dml2 = false,
 };
 
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn314/dcn314_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn314/dcn314_resource.c
index 01d95108ce66..585c3e8a2194 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn314/dcn314_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn314/dcn314_resource.c
@@ -927,6 +927,7 @@ static const struct dc_debug_options debug_defaults_drv = {
 	.seamless_boot_odm_combine = true,
 	.enable_legacy_fast_update = true,
 	.using_dml2 = false,
+	.disable_dsc_power_gate = true,
 };
 
 static const struct dc_panel_config panel_config_defaults = {
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn315/dcn315_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn315/dcn315_resource.c
index f2ce687c0e03..9cb72805b8d1 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn315/dcn315_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn315/dcn315_resource.c
@@ -1699,7 +1699,7 @@ static int dcn315_populate_dml_pipes_from_context(
 		pipes[pipe_cnt].dout.dsc_input_bpc = 0;
 		DC_FP_START();
 		dcn31_zero_pipe_dcc_fraction(pipes, pipe_cnt);
-		if (pixel_rate_crb && !pipe->top_pipe && !pipe->prev_odm_pipe) {
+		if (pixel_rate_crb) {
 			int bpp = source_format_to_bpp(pipes[pipe_cnt].pipe.src.source_format);
 			/* Ceil to crb segment size */
 			int approx_det_segs_required_for_pstate = dcn_get_approx_det_segs_required_for_pstate(
@@ -1756,28 +1756,26 @@ static int dcn315_populate_dml_pipes_from_context(
 				continue;
 			}
 
-			if (!pipe->top_pipe && !pipe->prev_odm_pipe) {
-				bool split_required = pipe->stream->timing.pix_clk_100hz >= dcn_get_max_non_odm_pix_rate_100hz(&dc->dml.soc)
-						|| (pipe->plane_state && pipe->plane_state->src_rect.width > 5120);
-
-				if (remaining_det_segs > MIN_RESERVED_DET_SEGS && crb_pipes != 0)
-					pipes[pipe_cnt].pipe.src.det_size_override += (remaining_det_segs - MIN_RESERVED_DET_SEGS) / crb_pipes +
-							(crb_idx < (remaining_det_segs - MIN_RESERVED_DET_SEGS) % crb_pipes ? 1 : 0);
-				if (pipes[pipe_cnt].pipe.src.det_size_override > 2 * DCN3_15_MAX_DET_SEGS) {
-					/* Clamp to 2 pipe split max det segments */
-					remaining_det_segs += pipes[pipe_cnt].pipe.src.det_size_override - 2 * (DCN3_15_MAX_DET_SEGS);
-					pipes[pipe_cnt].pipe.src.det_size_override = 2 * DCN3_15_MAX_DET_SEGS;
-				}
-				if (pipes[pipe_cnt].pipe.src.det_size_override > DCN3_15_MAX_DET_SEGS || split_required) {
-					/* If we are splitting we must have an even number of segments */
-					remaining_det_segs += pipes[pipe_cnt].pipe.src.det_size_override % 2;
-					pipes[pipe_cnt].pipe.src.det_size_override -= pipes[pipe_cnt].pipe.src.det_size_override % 2;
-				}
-				/* Convert segments into size for DML use */
-				pipes[pipe_cnt].pipe.src.det_size_override *= DCN3_15_CRB_SEGMENT_SIZE_KB;
-
-				crb_idx++;
+			bool split_required = pipe->stream->timing.pix_clk_100hz >= dcn_get_max_non_odm_pix_rate_100hz(&dc->dml.soc)
+					|| (pipe->plane_state && pipe->plane_state->src_rect.width > 5120);
+
+			if (remaining_det_segs > MIN_RESERVED_DET_SEGS && crb_pipes != 0)
+				pipes[pipe_cnt].pipe.src.det_size_override += (remaining_det_segs - MIN_RESERVED_DET_SEGS) / crb_pipes +
+						(crb_idx < (remaining_det_segs - MIN_RESERVED_DET_SEGS) % crb_pipes ? 1 : 0);
+			if (pipes[pipe_cnt].pipe.src.det_size_override > 2 * DCN3_15_MAX_DET_SEGS) {
+				/* Clamp to 2 pipe split max det segments */
+				remaining_det_segs += pipes[pipe_cnt].pipe.src.det_size_override - 2 * (DCN3_15_MAX_DET_SEGS);
+				pipes[pipe_cnt].pipe.src.det_size_override = 2 * DCN3_15_MAX_DET_SEGS;
+			}
+			if (pipes[pipe_cnt].pipe.src.det_size_override > DCN3_15_MAX_DET_SEGS || split_required) {
+				/* If we are splitting we must have an even number of segments */
+				remaining_det_segs += pipes[pipe_cnt].pipe.src.det_size_override % 2;
+				pipes[pipe_cnt].pipe.src.det_size_override -= pipes[pipe_cnt].pipe.src.det_size_override % 2;
 			}
+			/* Convert segments into size for DML use */
+			pipes[pipe_cnt].pipe.src.det_size_override *= DCN3_15_CRB_SEGMENT_SIZE_KB;
+
+			crb_idx++;
 			pipe_cnt++;
 		}
 	}
diff --git a/drivers/gpu/drm/amd/display/dc/spl/dc_spl.c b/drivers/gpu/drm/amd/display/dc/spl/dc_spl.c
index 014e8a296f0c..54c7d6aecf51 100644
--- a/drivers/gpu/drm/amd/display/dc/spl/dc_spl.c
+++ b/drivers/gpu/drm/amd/display/dc/spl/dc_spl.c
@@ -875,8 +875,8 @@ static bool spl_get_optimal_number_of_taps(
 	  bool *enable_isharp)
 {
 	int num_part_y, num_part_c;
-	int max_taps_y, max_taps_c;
-	int min_taps_y, min_taps_c;
+	unsigned int max_taps_y, max_taps_c;
+	unsigned int min_taps_y, min_taps_c;
 	enum lb_memory_config lb_config;
 	bool skip_easf = false;
 
diff --git a/drivers/gpu/drm/amd/display/dc/spl/dc_spl_types.h b/drivers/gpu/drm/amd/display/dc/spl/dc_spl_types.h
index 2a74ff5fdfdb..a2c28949ec47 100644
--- a/drivers/gpu/drm/amd/display/dc/spl/dc_spl_types.h
+++ b/drivers/gpu/drm/amd/display/dc/spl/dc_spl_types.h
@@ -479,7 +479,7 @@ struct spl_sharpness_range {
 };
 struct adaptive_sharpness {
 	bool enable;
-	int sharpness_level;
+	unsigned int sharpness_level;
 	struct spl_sharpness_range sharpness_range;
 };
 enum linear_light_scaling	{	// convert it in translation logic
diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
index 7835100b37c4..d74336830368 100644
--- a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
+++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
@@ -2869,6 +2869,12 @@ struct dmub_cmd_psr_copy_settings_data {
 	 * Some panels request main link off before xth vertical line
 	 */
 	uint16_t poweroff_before_vertical_line;
+	/**
+	 * Some panels cannot handle idle pattern during PSR entry.
+	 * To power down phy before disable stream to avoid sending
+	 * idle pattern.
+	 */
+	uint8_t power_down_phy_before_disable_stream;
 };
 
 /**
diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c
index d9f31b191c69..1a68b5782cac 100644
--- a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c
+++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c
@@ -83,8 +83,8 @@ static inline void dmub_dcn31_translate_addr(const union dmub_addr *addr_in,
 void dmub_dcn31_reset(struct dmub_srv *dmub)
 {
 	union dmub_gpint_data_register cmd;
-	const uint32_t timeout = 100;
-	uint32_t in_reset, scratch, i, pwait_mode;
+	const uint32_t timeout = 100000;
+	uint32_t in_reset, is_enabled, scratch, i, pwait_mode;
 
 	REG_GET(DMCUB_CNTL2, DMCUB_SOFT_RESET, &in_reset);
 
@@ -108,7 +108,7 @@ void dmub_dcn31_reset(struct dmub_srv *dmub)
 		}
 
 		for (i = 0; i < timeout; ++i) {
-			scratch = dmub->hw_funcs.get_gpint_response(dmub);
+			scratch = REG_READ(DMCUB_SCRATCH7);
 			if (scratch == DMUB_GPINT__STOP_FW_RESPONSE)
 				break;
 
@@ -125,9 +125,14 @@ void dmub_dcn31_reset(struct dmub_srv *dmub)
 		/* Force reset in case we timed out, DMCUB is likely hung. */
 	}
 
-	REG_UPDATE(DMCUB_CNTL2, DMCUB_SOFT_RESET, 1);
-	REG_UPDATE(DMCUB_CNTL, DMCUB_ENABLE, 0);
-	REG_UPDATE(MMHUBBUB_SOFT_RESET, DMUIF_SOFT_RESET, 1);
+	REG_GET(DMCUB_CNTL, DMCUB_ENABLE, &is_enabled);
+
+	if (is_enabled) {
+		REG_UPDATE(DMCUB_CNTL2, DMCUB_SOFT_RESET, 1);
+		REG_UPDATE(MMHUBBUB_SOFT_RESET, DMUIF_SOFT_RESET, 1);
+		REG_UPDATE(DMCUB_CNTL, DMCUB_ENABLE, 0);
+	}
+
 	REG_WRITE(DMCUB_INBOX1_RPTR, 0);
 	REG_WRITE(DMCUB_INBOX1_WPTR, 0);
 	REG_WRITE(DMCUB_OUTBOX1_RPTR, 0);
diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn35.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn35.c
index 2ccad79053c5..01e83c6ce701 100644
--- a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn35.c
+++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn35.c
@@ -88,23 +88,19 @@ static inline void dmub_dcn35_translate_addr(const union dmub_addr *addr_in,
 void dmub_dcn35_reset(struct dmub_srv *dmub)
 {
 	union dmub_gpint_data_register cmd;
-	const uint32_t timeout = 100;
+	const uint32_t timeout = 100000;
 	uint32_t in_reset, is_enabled, scratch, i, pwait_mode;
 
 	REG_GET(DMCUB_CNTL2, DMCUB_SOFT_RESET, &in_reset);
+	REG_GET(DMCUB_CNTL, DMCUB_ENABLE, &is_enabled);
 
-	if (in_reset == 0) {
+	if (in_reset == 0 && is_enabled != 0) {
 		cmd.bits.status = 1;
 		cmd.bits.command_code = DMUB_GPINT__STOP_FW;
 		cmd.bits.param = 0;
 
 		dmub->hw_funcs.set_gpint(dmub, cmd);
 
-		/**
-		 * Timeout covers both the ACK and the wait
-		 * for remaining work to finish.
-		 */
-
 		for (i = 0; i < timeout; ++i) {
 			if (dmub->hw_funcs.is_gpint_acked(dmub, cmd))
 				break;
@@ -113,7 +109,7 @@ void dmub_dcn35_reset(struct dmub_srv *dmub)
 		}
 
 		for (i = 0; i < timeout; ++i) {
-			scratch = dmub->hw_funcs.get_gpint_response(dmub);
+			scratch = REG_READ(DMCUB_SCRATCH7);
 			if (scratch == DMUB_GPINT__STOP_FW_RESPONSE)
 				break;
 
@@ -130,11 +126,9 @@ void dmub_dcn35_reset(struct dmub_srv *dmub)
 		/* Force reset in case we timed out, DMCUB is likely hung. */
 	}
 
-	REG_GET(DMCUB_CNTL, DMCUB_ENABLE, &is_enabled);
-
 	if (is_enabled) {
 		REG_UPDATE(DMCUB_CNTL2, DMCUB_SOFT_RESET, 1);
-		REG_UPDATE(MMHUBBUB_SOFT_RESET, DMUIF_SOFT_RESET, 1);
+		udelay(1);
 		REG_UPDATE(DMCUB_CNTL, DMCUB_ENABLE, 0);
 	}
 
@@ -160,11 +154,7 @@ void dmub_dcn35_reset_release(struct dmub_srv *dmub)
 		     LONO_SOCCLK_GATE_DISABLE, 1,
 		     LONO_DMCUBCLK_GATE_DISABLE, 1);
 
-	REG_UPDATE(MMHUBBUB_SOFT_RESET, DMUIF_SOFT_RESET, 1);
-	udelay(1);
 	REG_UPDATE_2(DMCUB_CNTL, DMCUB_ENABLE, 1, DMCUB_TRACEPORT_EN, 1);
-	REG_UPDATE(DMCUB_CNTL2, DMCUB_SOFT_RESET, 1);
-	udelay(1);
 	REG_UPDATE(MMHUBBUB_SOFT_RESET, DMUIF_SOFT_RESET, 0);
 	REG_UPDATE(DMCUB_CNTL2, DMCUB_SOFT_RESET, 0);
 }
diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn401.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn401.c
index 39a8cb6d7523..e1c4fe1c6e3e 100644
--- a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn401.c
+++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn401.c
@@ -63,8 +63,10 @@ static inline void dmub_dcn401_translate_addr(const union dmub_addr *addr_in,
 void dmub_dcn401_reset(struct dmub_srv *dmub)
 {
 	union dmub_gpint_data_register cmd;
-	const uint32_t timeout = 30;
-	uint32_t in_reset, scratch, i;
+	const uint32_t timeout_us = 1 * 1000 * 1000; //1s
+	const uint32_t poll_delay_us = 1; //1us
+	uint32_t i = 0;
+	uint32_t in_reset, scratch, pwait_mode;
 
 	REG_GET(DMCUB_CNTL2, DMCUB_SOFT_RESET, &in_reset);
 
@@ -75,32 +77,35 @@ void dmub_dcn401_reset(struct dmub_srv *dmub)
 
 		dmub->hw_funcs.set_gpint(dmub, cmd);
 
-		/**
-		 * Timeout covers both the ACK and the wait
-		 * for remaining work to finish.
-		 *
-		 * This is mostly bound by the PHY disable sequence.
-		 * Each register check will be greater than 1us, so
-		 * don't bother using udelay.
-		 */
-
-		for (i = 0; i < timeout; ++i) {
+		for (i = 0; i < timeout_us; i++) {
 			if (dmub->hw_funcs.is_gpint_acked(dmub, cmd))
 				break;
+
+			udelay(poll_delay_us);
 		}
 
-		for (i = 0; i < timeout; ++i) {
+		for (; i < timeout_us; i++) {
 			scratch = dmub->hw_funcs.get_gpint_response(dmub);
 			if (scratch == DMUB_GPINT__STOP_FW_RESPONSE)
 				break;
+
+			udelay(poll_delay_us);
 		}
 
-		/* Force reset in case we timed out, DMCUB is likely hung. */
+		for (; i < timeout_us; i++) {
+			REG_GET(DMCUB_CNTL, DMCUB_PWAIT_MODE_STATUS, &pwait_mode);
+			if (pwait_mode & (1 << 0))
+				break;
+
+			udelay(poll_delay_us);
+		}
+	}
+
+	if (i >= timeout_us) {
+		/* timeout should never occur */
+		BREAK_TO_DEBUGGER();
 	}
 
-	REG_UPDATE(DMCUB_CNTL2, DMCUB_SOFT_RESET, 1);
-	REG_UPDATE(DMCUB_CNTL, DMCUB_ENABLE, 0);
-	REG_UPDATE(MMHUBBUB_SOFT_RESET, DMUIF_SOFT_RESET, 1);
 	REG_WRITE(DMCUB_INBOX1_RPTR, 0);
 	REG_WRITE(DMCUB_INBOX1_WPTR, 0);
 	REG_WRITE(DMCUB_OUTBOX1_RPTR, 0);
@@ -131,7 +136,10 @@ void dmub_dcn401_backdoor_load(struct dmub_srv *dmub,
 
 	dmub_dcn401_get_fb_base_offset(dmub, &fb_base, &fb_offset);
 
+	/* reset and disable DMCUB and MMHUBBUB DMUIF */
 	REG_UPDATE(DMCUB_SEC_CNTL, DMCUB_SEC_RESET, 1);
+	REG_UPDATE(MMHUBBUB_SOFT_RESET, DMUIF_SOFT_RESET, 1);
+	REG_UPDATE(DMCUB_CNTL, DMCUB_ENABLE, 0);
 
 	dmub_dcn401_translate_addr(&cw0->offset, fb_base, fb_offset, &offset);
 
@@ -151,6 +159,7 @@ void dmub_dcn401_backdoor_load(struct dmub_srv *dmub,
 			DMCUB_REGION3_CW1_TOP_ADDRESS, cw1->region.top,
 			DMCUB_REGION3_CW1_ENABLE, 1);
 
+	/* release DMCUB reset only to prevent premature execution */
 	REG_UPDATE_2(DMCUB_SEC_CNTL, DMCUB_SEC_RESET, 0, DMCUB_MEM_UNIT_ID,
 			0x20);
 }
@@ -161,7 +170,10 @@ void dmub_dcn401_backdoor_load_zfb_mode(struct dmub_srv *dmub,
 {
 	union dmub_addr offset;
 
+	/* reset and disable DMCUB and MMHUBBUB DMUIF */
 	REG_UPDATE(DMCUB_SEC_CNTL, DMCUB_SEC_RESET, 1);
+	REG_UPDATE(MMHUBBUB_SOFT_RESET, DMUIF_SOFT_RESET, 1);
+	REG_UPDATE(DMCUB_CNTL, DMCUB_ENABLE, 0);
 
 	offset = cw0->offset;
 
@@ -181,6 +193,7 @@ void dmub_dcn401_backdoor_load_zfb_mode(struct dmub_srv *dmub,
 			DMCUB_REGION3_CW1_TOP_ADDRESS, cw1->region.top,
 			DMCUB_REGION3_CW1_ENABLE, 1);
 
+	/* release DMCUB reset only to prevent premature execution */
 	REG_UPDATE_2(DMCUB_SEC_CNTL, DMCUB_SEC_RESET, 0, DMCUB_MEM_UNIT_ID,
 			0x20);
 }
diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn401.h b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn401.h
index 4c8843b79695..31f95b27e227 100644
--- a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn401.h
+++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn401.h
@@ -169,7 +169,8 @@ struct dmub_srv;
 	DMUB_SF(HOST_INTERRUPT_CSR, HOST_REG_INBOX0_RSP_INT_EN) \
 	DMUB_SF(HOST_INTERRUPT_CSR, HOST_REG_OUTBOX0_RDY_INT_ACK) \
 	DMUB_SF(HOST_INTERRUPT_CSR, HOST_REG_OUTBOX0_RDY_INT_STAT) \
-	DMUB_SF(HOST_INTERRUPT_CSR, HOST_REG_OUTBOX0_RDY_INT_EN)
+	DMUB_SF(HOST_INTERRUPT_CSR, HOST_REG_OUTBOX0_RDY_INT_EN) \
+	DMUB_SF(DMCUB_CNTL, DMCUB_PWAIT_MODE_STATUS)
 
 struct dmub_srv_dcn401_reg_offset {
 #define DMUB_SR(reg) uint32_t reg;
diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c
index 8c137d7c032e..e58e7b93810b 100644
--- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c
+++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c
@@ -368,6 +368,9 @@ enum mod_hdcp_status mod_hdcp_hdcp1_enable_encryption(struct mod_hdcp *hdcp)
 	struct mod_hdcp_display *display = get_first_active_display(hdcp);
 	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
 
+	if (!display)
+		return MOD_HDCP_STATUS_DISPLAY_NOT_FOUND;
+
 	mutex_lock(&psp->hdcp_context.mutex);
 	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.context.mem_context.shared_buf;
 	memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory));
diff --git a/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c b/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c
index a344e2e49b0e..b3d55cac3569 100644
--- a/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c
+++ b/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c
@@ -383,10 +383,10 @@ void mod_build_vsc_infopacket(const struct dc_stream_state *stream,
 				colorimetryFormat = ColorimetryYCC_DP_ITU709;
 			else if (cs == COLOR_SPACE_ADOBERGB)
 				colorimetryFormat = ColorimetryYCC_DP_AdobeYCC;
-			else if (cs == COLOR_SPACE_2020_YCBCR)
+			else if (cs == COLOR_SPACE_2020_YCBCR_LIMITED)
 				colorimetryFormat = ColorimetryYCC_DP_ITU2020YCbCr;
 
-			if (cs == COLOR_SPACE_2020_YCBCR && tf == TRANSFER_FUNC_GAMMA_22)
+			if (cs == COLOR_SPACE_2020_YCBCR_LIMITED && tf == TRANSFER_FUNC_GAMMA_22)
 				colorimetryFormat = ColorimetryYCC_DP_ITU709;
 			break;
 
diff --git a/drivers/gpu/drm/amd/include/asic_reg/mmhub/mmhub_9_4_1_offset.h b/drivers/gpu/drm/amd/include/asic_reg/mmhub/mmhub_9_4_1_offset.h
index c488d4a50cf4..b2252deabc17 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/mmhub/mmhub_9_4_1_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/mmhub/mmhub_9_4_1_offset.h
@@ -203,6 +203,10 @@
 #define mmDAGB0_WR_DATA_CREDIT_BASE_IDX                                                                1
 #define mmDAGB0_WR_MISC_CREDIT                                                                         0x0058
 #define mmDAGB0_WR_MISC_CREDIT_BASE_IDX                                                                1
+#define mmDAGB0_WRCLI_GPU_SNOOP_OVERRIDE                                                               0x005b
+#define mmDAGB0_WRCLI_GPU_SNOOP_OVERRIDE_BASE_IDX                                                      1
+#define mmDAGB0_WRCLI_GPU_SNOOP_OVERRIDE_VALUE                                                         0x005c
+#define mmDAGB0_WRCLI_GPU_SNOOP_OVERRIDE_VALUE_BASE_IDX                                                1
 #define mmDAGB0_WRCLI_ASK_PENDING                                                                      0x005d
 #define mmDAGB0_WRCLI_ASK_PENDING_BASE_IDX                                                             1
 #define mmDAGB0_WRCLI_GO_PENDING                                                                       0x005e
@@ -455,6 +459,10 @@
 #define mmDAGB1_WR_DATA_CREDIT_BASE_IDX                                                                1
 #define mmDAGB1_WR_MISC_CREDIT                                                                         0x00d8
 #define mmDAGB1_WR_MISC_CREDIT_BASE_IDX                                                                1
+#define mmDAGB1_WRCLI_GPU_SNOOP_OVERRIDE                                                               0x00db
+#define mmDAGB1_WRCLI_GPU_SNOOP_OVERRIDE_BASE_IDX                                                      1
+#define mmDAGB1_WRCLI_GPU_SNOOP_OVERRIDE_VALUE                                                         0x00dc
+#define mmDAGB1_WRCLI_GPU_SNOOP_OVERRIDE_VALUE_BASE_IDX                                                1
 #define mmDAGB1_WRCLI_ASK_PENDING                                                                      0x00dd
 #define mmDAGB1_WRCLI_ASK_PENDING_BASE_IDX                                                             1
 #define mmDAGB1_WRCLI_GO_PENDING                                                                       0x00de
@@ -707,6 +715,10 @@
 #define mmDAGB2_WR_DATA_CREDIT_BASE_IDX                                                                1
 #define mmDAGB2_WR_MISC_CREDIT                                                                         0x0158
 #define mmDAGB2_WR_MISC_CREDIT_BASE_IDX                                                                1
+#define mmDAGB2_WRCLI_GPU_SNOOP_OVERRIDE                                                               0x015b
+#define mmDAGB2_WRCLI_GPU_SNOOP_OVERRIDE_BASE_IDX                                                      1
+#define mmDAGB2_WRCLI_GPU_SNOOP_OVERRIDE_VALUE                                                         0x015c
+#define mmDAGB2_WRCLI_GPU_SNOOP_OVERRIDE_VALUE_BASE_IDX                                                1
 #define mmDAGB2_WRCLI_ASK_PENDING                                                                      0x015d
 #define mmDAGB2_WRCLI_ASK_PENDING_BASE_IDX                                                             1
 #define mmDAGB2_WRCLI_GO_PENDING                                                                       0x015e
@@ -959,6 +971,10 @@
 #define mmDAGB3_WR_DATA_CREDIT_BASE_IDX                                                                1
 #define mmDAGB3_WR_MISC_CREDIT                                                                         0x01d8
 #define mmDAGB3_WR_MISC_CREDIT_BASE_IDX                                                                1
+#define mmDAGB3_WRCLI_GPU_SNOOP_OVERRIDE                                                               0x01db
+#define mmDAGB3_WRCLI_GPU_SNOOP_OVERRIDE_BASE_IDX                                                      1
+#define mmDAGB3_WRCLI_GPU_SNOOP_OVERRIDE_VALUE                                                         0x01dc
+#define mmDAGB3_WRCLI_GPU_SNOOP_OVERRIDE_VALUE_BASE_IDX                                                1
 #define mmDAGB3_WRCLI_ASK_PENDING                                                                      0x01dd
 #define mmDAGB3_WRCLI_ASK_PENDING_BASE_IDX                                                             1
 #define mmDAGB3_WRCLI_GO_PENDING                                                                       0x01de
@@ -1211,6 +1227,10 @@
 #define mmDAGB4_WR_DATA_CREDIT_BASE_IDX                                                                1
 #define mmDAGB4_WR_MISC_CREDIT                                                                         0x0258
 #define mmDAGB4_WR_MISC_CREDIT_BASE_IDX                                                                1
+#define mmDAGB4_WRCLI_GPU_SNOOP_OVERRIDE                                                               0x025b
+#define mmDAGB4_WRCLI_GPU_SNOOP_OVERRIDE_BASE_IDX                                                      1
+#define mmDAGB4_WRCLI_GPU_SNOOP_OVERRIDE_VALUE                                                         0x025c
+#define mmDAGB4_WRCLI_GPU_SNOOP_OVERRIDE_VALUE_BASE_IDX                                                1
 #define mmDAGB4_WRCLI_ASK_PENDING                                                                      0x025d
 #define mmDAGB4_WRCLI_ASK_PENDING_BASE_IDX                                                             1
 #define mmDAGB4_WRCLI_GO_PENDING                                                                       0x025e
@@ -4793,6 +4813,10 @@
 #define mmDAGB5_WR_DATA_CREDIT_BASE_IDX                                                                1
 #define mmDAGB5_WR_MISC_CREDIT                                                                         0x3058
 #define mmDAGB5_WR_MISC_CREDIT_BASE_IDX                                                                1
+#define mmDAGB5_WRCLI_GPU_SNOOP_OVERRIDE                                                               0x305b
+#define mmDAGB5_WRCLI_GPU_SNOOP_OVERRIDE_BASE_IDX                                                      1
+#define mmDAGB5_WRCLI_GPU_SNOOP_OVERRIDE_VALUE                                                         0x305c
+#define mmDAGB5_WRCLI_GPU_SNOOP_OVERRIDE_VALUE_BASE_IDX                                                1
 #define mmDAGB5_WRCLI_ASK_PENDING                                                                      0x305d
 #define mmDAGB5_WRCLI_ASK_PENDING_BASE_IDX                                                             1
 #define mmDAGB5_WRCLI_GO_PENDING                                                                       0x305e
@@ -5045,6 +5069,10 @@
 #define mmDAGB6_WR_DATA_CREDIT_BASE_IDX                                                                1
 #define mmDAGB6_WR_MISC_CREDIT                                                                         0x30d8
 #define mmDAGB6_WR_MISC_CREDIT_BASE_IDX                                                                1
+#define mmDAGB6_WRCLI_GPU_SNOOP_OVERRIDE                                                               0x30db
+#define mmDAGB6_WRCLI_GPU_SNOOP_OVERRIDE_BASE_IDX                                                      1
+#define mmDAGB6_WRCLI_GPU_SNOOP_OVERRIDE_VALUE                                                         0x30dc
+#define mmDAGB6_WRCLI_GPU_SNOOP_OVERRIDE_VALUE_BASE_IDX                                                1
 #define mmDAGB6_WRCLI_ASK_PENDING                                                                      0x30dd
 #define mmDAGB6_WRCLI_ASK_PENDING_BASE_IDX                                                             1
 #define mmDAGB6_WRCLI_GO_PENDING                                                                       0x30de
@@ -5297,6 +5325,10 @@
 #define mmDAGB7_WR_DATA_CREDIT_BASE_IDX                                                                1
 #define mmDAGB7_WR_MISC_CREDIT                                                                         0x3158
 #define mmDAGB7_WR_MISC_CREDIT_BASE_IDX                                                                1
+#define mmDAGB7_WRCLI_GPU_SNOOP_OVERRIDE                                                               0x315b
+#define mmDAGB7_WRCLI_GPU_SNOOP_OVERRIDE_BASE_IDX                                                      1
+#define mmDAGB7_WRCLI_GPU_SNOOP_OVERRIDE_VALUE                                                         0x315c
+#define mmDAGB7_WRCLI_GPU_SNOOP_OVERRIDE_VALUE_BASE_IDX                                                1
 #define mmDAGB7_WRCLI_ASK_PENDING                                                                      0x315d
 #define mmDAGB7_WRCLI_ASK_PENDING_BASE_IDX                                                             1
 #define mmDAGB7_WRCLI_GO_PENDING                                                                       0x315e
diff --git a/drivers/gpu/drm/amd/include/asic_reg/mmhub/mmhub_9_4_1_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/mmhub/mmhub_9_4_1_sh_mask.h
index 2969fbf282b7..5069d2fd467f 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/mmhub/mmhub_9_4_1_sh_mask.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/mmhub/mmhub_9_4_1_sh_mask.h
@@ -1532,6 +1532,12 @@
 //DAGB0_WRCLI_DBUS_GO_PENDING
 #define DAGB0_WRCLI_DBUS_GO_PENDING__BUSY__SHIFT                                                              0x0
 #define DAGB0_WRCLI_DBUS_GO_PENDING__BUSY_MASK                                                                0xFFFFFFFFL
+//DAGB0_WRCLI_GPU_SNOOP_OVERRIDE
+#define DAGB0_WRCLI_GPU_SNOOP_OVERRIDE__ENABLE__SHIFT                                                         0x0
+#define DAGB0_WRCLI_GPU_SNOOP_OVERRIDE__ENABLE_MASK                                                           0xFFFFFFFFL
+//DAGB0_WRCLI_GPU_SNOOP_OVERRIDE_VALUE
+#define DAGB0_WRCLI_GPU_SNOOP_OVERRIDE_VALUE__ENABLE__SHIFT                                                   0x0
+#define DAGB0_WRCLI_GPU_SNOOP_OVERRIDE_VALUE__ENABLE_MASK                                                     0xFFFFFFFFL
 //DAGB0_DAGB_DLY
 #define DAGB0_DAGB_DLY__DLY__SHIFT                                                                            0x0
 #define DAGB0_DAGB_DLY__CLI__SHIFT                                                                            0x8
@@ -3207,6 +3213,12 @@
 //DAGB1_WRCLI_DBUS_GO_PENDING
 #define DAGB1_WRCLI_DBUS_GO_PENDING__BUSY__SHIFT                                                              0x0
 #define DAGB1_WRCLI_DBUS_GO_PENDING__BUSY_MASK                                                                0xFFFFFFFFL
+//DAGB1_WRCLI_GPU_SNOOP_OVERRIDE
+#define DAGB1_WRCLI_GPU_SNOOP_OVERRIDE__ENABLE__SHIFT                                                         0x0
+#define DAGB1_WRCLI_GPU_SNOOP_OVERRIDE__ENABLE_MASK                                                           0xFFFFFFFFL
+//DAGB1_WRCLI_GPU_SNOOP_OVERRIDE_VALUE
+#define DAGB1_WRCLI_GPU_SNOOP_OVERRIDE_VALUE__ENABLE__SHIFT                                                   0x0
+#define DAGB1_WRCLI_GPU_SNOOP_OVERRIDE_VALUE__ENABLE_MASK                                                     0xFFFFFFFFL
 //DAGB1_DAGB_DLY
 #define DAGB1_DAGB_DLY__DLY__SHIFT                                                                            0x0
 #define DAGB1_DAGB_DLY__CLI__SHIFT                                                                            0x8
@@ -4882,6 +4894,12 @@
 //DAGB2_WRCLI_DBUS_GO_PENDING
 #define DAGB2_WRCLI_DBUS_GO_PENDING__BUSY__SHIFT                                                              0x0
 #define DAGB2_WRCLI_DBUS_GO_PENDING__BUSY_MASK                                                                0xFFFFFFFFL
+//DAGB2_WRCLI_GPU_SNOOP_OVERRIDE
+#define DAGB2_WRCLI_GPU_SNOOP_OVERRIDE__ENABLE__SHIFT                                                         0x0
+#define DAGB2_WRCLI_GPU_SNOOP_OVERRIDE__ENABLE_MASK                                                           0xFFFFFFFFL
+//DAGB2_WRCLI_GPU_SNOOP_OVERRIDE_VALUE
+#define DAGB2_WRCLI_GPU_SNOOP_OVERRIDE_VALUE__ENABLE__SHIFT                                                   0x0
+#define DAGB2_WRCLI_GPU_SNOOP_OVERRIDE_VALUE__ENABLE_MASK                                                     0xFFFFFFFFL
 //DAGB2_DAGB_DLY
 #define DAGB2_DAGB_DLY__DLY__SHIFT                                                                            0x0
 #define DAGB2_DAGB_DLY__CLI__SHIFT                                                                            0x8
@@ -6557,6 +6575,12 @@
 //DAGB3_WRCLI_DBUS_GO_PENDING
 #define DAGB3_WRCLI_DBUS_GO_PENDING__BUSY__SHIFT                                                              0x0
 #define DAGB3_WRCLI_DBUS_GO_PENDING__BUSY_MASK                                                                0xFFFFFFFFL
+//DAGB3_WRCLI_GPU_SNOOP_OVERRIDE
+#define DAGB3_WRCLI_GPU_SNOOP_OVERRIDE__ENABLE__SHIFT                                                         0x0
+#define DAGB3_WRCLI_GPU_SNOOP_OVERRIDE__ENABLE_MASK                                                           0xFFFFFFFFL
+//DAGB3_WRCLI_GPU_SNOOP_OVERRIDE_VALUE
+#define DAGB3_WRCLI_GPU_SNOOP_OVERRIDE_VALUE__ENABLE__SHIFT                                                   0x0
+#define DAGB3_WRCLI_GPU_SNOOP_OVERRIDE_VALUE__ENABLE_MASK                                                     0xFFFFFFFFL
 //DAGB3_DAGB_DLY
 #define DAGB3_DAGB_DLY__DLY__SHIFT                                                                            0x0
 #define DAGB3_DAGB_DLY__CLI__SHIFT                                                                            0x8
@@ -8232,6 +8256,12 @@
 //DAGB4_WRCLI_DBUS_GO_PENDING
 #define DAGB4_WRCLI_DBUS_GO_PENDING__BUSY__SHIFT                                                              0x0
 #define DAGB4_WRCLI_DBUS_GO_PENDING__BUSY_MASK                                                                0xFFFFFFFFL
+//DAGB4_WRCLI_GPU_SNOOP_OVERRIDE
+#define DAGB4_WRCLI_GPU_SNOOP_OVERRIDE__ENABLE__SHIFT                                                         0x0
+#define DAGB4_WRCLI_GPU_SNOOP_OVERRIDE__ENABLE_MASK                                                           0xFFFFFFFFL
+//DAGB4_WRCLI_GPU_SNOOP_OVERRIDE_VALUE
+#define DAGB4_WRCLI_GPU_SNOOP_OVERRIDE_VALUE__ENABLE__SHIFT                                                   0x0
+#define DAGB4_WRCLI_GPU_SNOOP_OVERRIDE_VALUE__ENABLE_MASK                                                     0xFFFFFFFFL
 //DAGB4_DAGB_DLY
 #define DAGB4_DAGB_DLY__DLY__SHIFT                                                                            0x0
 #define DAGB4_DAGB_DLY__CLI__SHIFT                                                                            0x8
@@ -28737,6 +28767,12 @@
 //DAGB5_WRCLI_DBUS_GO_PENDING
 #define DAGB5_WRCLI_DBUS_GO_PENDING__BUSY__SHIFT                                                              0x0
 #define DAGB5_WRCLI_DBUS_GO_PENDING__BUSY_MASK                                                                0xFFFFFFFFL
+//DAGB5_WRCLI_GPU_SNOOP_OVERRIDE
+#define DAGB5_WRCLI_GPU_SNOOP_OVERRIDE__ENABLE__SHIFT                                                         0x0
+#define DAGB5_WRCLI_GPU_SNOOP_OVERRIDE__ENABLE_MASK                                                           0xFFFFFFFFL
+//DAGB5_WRCLI_GPU_SNOOP_OVERRIDE_VALUE
+#define DAGB5_WRCLI_GPU_SNOOP_OVERRIDE_VALUE__ENABLE__SHIFT                                                   0x0
+#define DAGB5_WRCLI_GPU_SNOOP_OVERRIDE_VALUE__ENABLE_MASK                                                     0xFFFFFFFFL
 //DAGB5_DAGB_DLY
 #define DAGB5_DAGB_DLY__DLY__SHIFT                                                                            0x0
 #define DAGB5_DAGB_DLY__CLI__SHIFT                                                                            0x8
@@ -30412,6 +30448,12 @@
 //DAGB6_WRCLI_DBUS_GO_PENDING
 #define DAGB6_WRCLI_DBUS_GO_PENDING__BUSY__SHIFT                                                              0x0
 #define DAGB6_WRCLI_DBUS_GO_PENDING__BUSY_MASK                                                                0xFFFFFFFFL
+//DAGB6_WRCLI_GPU_SNOOP_OVERRIDE
+#define DAGB6_WRCLI_GPU_SNOOP_OVERRIDE__ENABLE__SHIFT                                                         0x0
+#define DAGB6_WRCLI_GPU_SNOOP_OVERRIDE__ENABLE_MASK                                                           0xFFFFFFFFL
+//DAGB6_WRCLI_GPU_SNOOP_OVERRIDE_VALUE
+#define DAGB6_WRCLI_GPU_SNOOP_OVERRIDE_VALUE__ENABLE__SHIFT                                                   0x0
+#define DAGB6_WRCLI_GPU_SNOOP_OVERRIDE_VALUE__ENABLE_MASK                                                     0xFFFFFFFFL
 //DAGB6_DAGB_DLY
 #define DAGB6_DAGB_DLY__DLY__SHIFT                                                                            0x0
 #define DAGB6_DAGB_DLY__CLI__SHIFT                                                                            0x8
@@ -32087,6 +32129,12 @@
 //DAGB7_WRCLI_DBUS_GO_PENDING
 #define DAGB7_WRCLI_DBUS_GO_PENDING__BUSY__SHIFT                                                              0x0
 #define DAGB7_WRCLI_DBUS_GO_PENDING__BUSY_MASK                                                                0xFFFFFFFFL
+//DAGB7_WRCLI_GPU_SNOOP_OVERRIDE
+#define DAGB7_WRCLI_GPU_SNOOP_OVERRIDE__ENABLE__SHIFT                                                         0x0
+#define DAGB7_WRCLI_GPU_SNOOP_OVERRIDE__ENABLE_MASK                                                           0xFFFFFFFFL
+//DAGB7_WRCLI_GPU_SNOOP_OVERRIDE_VALUE
+#define DAGB7_WRCLI_GPU_SNOOP_OVERRIDE_VALUE__ENABLE__SHIFT                                                   0x0
+#define DAGB7_WRCLI_GPU_SNOOP_OVERRIDE_VALUE__ENABLE_MASK                                                     0xFFFFFFFFL
 //DAGB7_DAGB_DLY
 #define DAGB7_DAGB_DLY__DLY__SHIFT                                                                            0x0
 #define DAGB7_DAGB_DLY__CLI__SHIFT                                                                            0x8
diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
index 0fa6fbee1978..c4fdd82a0042 100644
--- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
@@ -1490,6 +1490,8 @@ static ssize_t amdgpu_set_pp_power_profile_mode(struct device *dev,
 			if (ret)
 				return -EINVAL;
 			parameter_size++;
+			if (!tmp_str)
+				break;
 			while (isspace(*tmp_str))
 				tmp_str++;
 		}
@@ -2493,6 +2495,8 @@ static int default_attr_update(struct amdgpu_device *adev, struct amdgpu_device_
 		case IP_VERSION(11, 0, 1):
 		case IP_VERSION(11, 0, 2):
 		case IP_VERSION(11, 0, 3):
+		case IP_VERSION(12, 0, 0):
+		case IP_VERSION(12, 0, 1):
 			*states = ATTR_STATE_SUPPORTED;
 			break;
 		default:
@@ -3851,6 +3855,9 @@ static int parse_input_od_command_lines(const char *buf,
 			return -EINVAL;
 		parameter_size++;
 
+		if (!tmp_str)
+			break;
+
 		while (isspace(*tmp_str))
 			tmp_str++;
 	}
diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c
index e8b6989a40f3..6b34a33d788f 100644
--- a/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c
+++ b/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c
@@ -3043,6 +3043,7 @@ static int kv_dpm_hw_init(void *handle)
 	if (!amdgpu_dpm)
 		return 0;
 
+	mutex_lock(&adev->pm.mutex);
 	kv_dpm_setup_asic(adev);
 	ret = kv_dpm_enable(adev);
 	if (ret)
@@ -3050,6 +3051,8 @@ static int kv_dpm_hw_init(void *handle)
 	else
 		adev->pm.dpm_enabled = true;
 	amdgpu_legacy_dpm_compute_clocks(adev);
+	mutex_unlock(&adev->pm.mutex);
+
 	return ret;
 }
 
@@ -3067,32 +3070,42 @@ static int kv_dpm_suspend(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	cancel_work_sync(&adev->pm.dpm.thermal.work);
+
 	if (adev->pm.dpm_enabled) {
+		mutex_lock(&adev->pm.mutex);
+		adev->pm.dpm_enabled = false;
 		/* disable dpm */
 		kv_dpm_disable(adev);
 		/* reset the power state */
 		adev->pm.dpm.current_ps = adev->pm.dpm.requested_ps = adev->pm.dpm.boot_ps;
+		mutex_unlock(&adev->pm.mutex);
 	}
 	return 0;
 }
 
 static int kv_dpm_resume(void *handle)
 {
-	int ret;
+	int ret = 0;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	if (adev->pm.dpm_enabled) {
+	if (!amdgpu_dpm)
+		return 0;
+
+	if (!adev->pm.dpm_enabled) {
+		mutex_lock(&adev->pm.mutex);
 		/* asic init will reset to the boot state */
 		kv_dpm_setup_asic(adev);
 		ret = kv_dpm_enable(adev);
-		if (ret)
+		if (ret) {
 			adev->pm.dpm_enabled = false;
-		else
+		} else {
 			adev->pm.dpm_enabled = true;
-		if (adev->pm.dpm_enabled)
 			amdgpu_legacy_dpm_compute_clocks(adev);
+		}
+		mutex_unlock(&adev->pm.mutex);
 	}
-	return 0;
+	return ret;
 }
 
 static bool kv_dpm_is_idle(void *handle)
diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c
index e861355ebd75..c7518b13e787 100644
--- a/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c
+++ b/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c
@@ -1009,9 +1009,12 @@ void amdgpu_dpm_thermal_work_handler(struct work_struct *work)
 	enum amd_pm_state_type dpm_state = POWER_STATE_TYPE_INTERNAL_THERMAL;
 	int temp, size = sizeof(temp);
 
-	if (!adev->pm.dpm_enabled)
-		return;
+	mutex_lock(&adev->pm.mutex);
 
+	if (!adev->pm.dpm_enabled) {
+		mutex_unlock(&adev->pm.mutex);
+		return;
+	}
 	if (!pp_funcs->read_sensor(adev->powerplay.pp_handle,
 				   AMDGPU_PP_SENSOR_GPU_TEMP,
 				   (void *)&temp,
@@ -1033,4 +1036,5 @@ void amdgpu_dpm_thermal_work_handler(struct work_struct *work)
 	adev->pm.dpm.state = dpm_state;
 
 	amdgpu_legacy_dpm_compute_clocks(adev->powerplay.pp_handle);
+	mutex_unlock(&adev->pm.mutex);
 }
diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c
index a1baa13ab2c2..a5ad1b60597e 100644
--- a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c
+++ b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c
@@ -7783,6 +7783,7 @@ static int si_dpm_hw_init(void *handle)
 	if (!amdgpu_dpm)
 		return 0;
 
+	mutex_lock(&adev->pm.mutex);
 	si_dpm_setup_asic(adev);
 	ret = si_dpm_enable(adev);
 	if (ret)
@@ -7790,6 +7791,7 @@ static int si_dpm_hw_init(void *handle)
 	else
 		adev->pm.dpm_enabled = true;
 	amdgpu_legacy_dpm_compute_clocks(adev);
+	mutex_unlock(&adev->pm.mutex);
 	return ret;
 }
 
@@ -7807,32 +7809,44 @@ static int si_dpm_suspend(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	cancel_work_sync(&adev->pm.dpm.thermal.work);
+
 	if (adev->pm.dpm_enabled) {
+		mutex_lock(&adev->pm.mutex);
+		adev->pm.dpm_enabled = false;
 		/* disable dpm */
 		si_dpm_disable(adev);
 		/* reset the power state */
 		adev->pm.dpm.current_ps = adev->pm.dpm.requested_ps = adev->pm.dpm.boot_ps;
+		mutex_unlock(&adev->pm.mutex);
 	}
+
 	return 0;
 }
 
 static int si_dpm_resume(void *handle)
 {
-	int ret;
+	int ret = 0;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	if (adev->pm.dpm_enabled) {
+	if (!amdgpu_dpm)
+		return 0;
+
+	if (!adev->pm.dpm_enabled) {
 		/* asic init will reset to the boot state */
+		mutex_lock(&adev->pm.mutex);
 		si_dpm_setup_asic(adev);
 		ret = si_dpm_enable(adev);
-		if (ret)
+		if (ret) {
 			adev->pm.dpm_enabled = false;
-		else
+		} else {
 			adev->pm.dpm_enabled = true;
-		if (adev->pm.dpm_enabled)
 			amdgpu_legacy_dpm_compute_clocks(adev);
+		}
+		mutex_unlock(&adev->pm.mutex);
 	}
-	return 0;
+
+	return ret;
 }
 
 static bool si_dpm_is_idle(void *handle)
diff --git a/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c
index a71c6117d7e5..0115d26b5af9 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c
@@ -51,6 +51,11 @@ static int amd_powerplay_create(struct amdgpu_device *adev)
 	hwmgr->adev = adev;
 	hwmgr->not_vf = !amdgpu_sriov_vf(adev);
 	hwmgr->device = amdgpu_cgs_create_device(adev);
+	if (!hwmgr->device) {
+		kfree(hwmgr);
+		return -ENOMEM;
+	}
+
 	mutex_init(&hwmgr->msg_lock);
 	hwmgr->chip_family = adev->family;
 	hwmgr->chip_id = adev->asic_type;
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomctrl.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomctrl.c
index b56298d9da98..a76fc15a55f5 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomctrl.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomctrl.c
@@ -144,6 +144,10 @@ int atomctrl_initialize_mc_reg_table(
 	vram_info = (ATOM_VRAM_INFO_HEADER_V2_1 *)
 		smu_atom_get_data_table(hwmgr->adev,
 				GetIndexIntoMasterTable(DATA, VRAM_Info), &size, &frev, &crev);
+	if (!vram_info) {
+		pr_err("Could not retrieve the VramInfo table!");
+		return -EINVAL;
+	}
 
 	if (module_index >= vram_info->ucNumOfVRAMModule) {
 		pr_err("Invalid VramInfo table.");
@@ -181,6 +185,10 @@ int atomctrl_initialize_mc_reg_table_v2_2(
 	vram_info = (ATOM_VRAM_INFO_HEADER_V2_2 *)
 		smu_atom_get_data_table(hwmgr->adev,
 				GetIndexIntoMasterTable(DATA, VRAM_Info), &size, &frev, &crev);
+	if (!vram_info) {
+		pr_err("Could not retrieve the VramInfo table!");
+		return -EINVAL;
+	}
 
 	if (module_index >= vram_info->ucNumOfVRAMModule) {
 		pr_err("Invalid VramInfo table.");
@@ -1420,6 +1428,8 @@ int atomctrl_get_smc_sclk_range_table(struct pp_hwmgr *hwmgr, struct pp_atom_ctr
 			GetIndexIntoMasterTable(DATA, SMU_Info),
 			&size, &frev, &crev);
 
+	if (!psmu_info)
+		return -EINVAL;
 
 	for (i = 0; i < psmu_info->ucSclkEntryNum; i++) {
 		table->entry[i].ucVco_setting = psmu_info->asSclkFcwRangeEntry[i].ucVco_setting;
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_thermal.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_thermal.c
index a8fc0fa44db6..ba5c1237fcfe 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_thermal.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_thermal.c
@@ -267,10 +267,10 @@ int smu7_fan_ctrl_set_fan_speed_rpm(struct pp_hwmgr *hwmgr, uint32_t speed)
 	if (hwmgr->thermal_controller.fanInfo.bNoFan ||
 			(hwmgr->thermal_controller.fanInfo.
 			ucTachometerPulsesPerRevolution == 0) ||
-			speed == 0 ||
+			(!speed || speed > UINT_MAX/8) ||
 			(speed < hwmgr->thermal_controller.fanInfo.ulMinRPM) ||
 			(speed > hwmgr->thermal_controller.fanInfo.ulMaxRPM))
-		return 0;
+		return -EINVAL;
 
 	if (PP_CAP(PHM_PlatformCaps_MicrocodeFanControl))
 		smu7_fan_ctrl_stop_smc_fan_control(hwmgr);
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu_helper.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu_helper.c
index 79a566f3564a..c305ea4ec17d 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu_helper.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu_helper.c
@@ -149,7 +149,7 @@ int phm_wait_on_indirect_register(struct pp_hwmgr *hwmgr,
 	}
 
 	cgs_write_register(hwmgr->device, indirect_port, index);
-	return phm_wait_on_register(hwmgr, indirect_port + 1, mask, value);
+	return phm_wait_on_register(hwmgr, indirect_port + 1, value, mask);
 }
 
 int phm_wait_for_register_unequal(struct pp_hwmgr *hwmgr,
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_powertune.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_powertune.c
index 3007b054c873..776d58ea63ae 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_powertune.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_powertune.c
@@ -1120,13 +1120,14 @@ static int vega10_enable_se_edc_force_stall_config(struct pp_hwmgr *hwmgr)
 	result = vega10_program_didt_config_registers(hwmgr, SEEDCForceStallPatternConfig_Vega10, VEGA10_CONFIGREG_DIDT);
 	result |= vega10_program_didt_config_registers(hwmgr, SEEDCCtrlForceStallConfig_Vega10, VEGA10_CONFIGREG_DIDT);
 	if (0 != result)
-		return result;
+		goto exit_safe_mode;
 
 	vega10_didt_set_mask(hwmgr, false);
 
+exit_safe_mode:
 	amdgpu_gfx_rlc_exit_safe_mode(adev, 0);
 
-	return 0;
+	return result;
 }
 
 static int vega10_disable_se_edc_force_stall_config(struct pp_hwmgr *hwmgr)
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_thermal.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_thermal.c
index 379012494da5..56423aedf3fa 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_thermal.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_thermal.c
@@ -307,10 +307,10 @@ int vega10_fan_ctrl_set_fan_speed_rpm(struct pp_hwmgr *hwmgr, uint32_t speed)
 	int result = 0;
 
 	if (hwmgr->thermal_controller.fanInfo.bNoFan ||
-	    speed == 0 ||
+	    (!speed || speed > UINT_MAX/8) ||
 	    (speed < hwmgr->thermal_controller.fanInfo.ulMinRPM) ||
 	    (speed > hwmgr->thermal_controller.fanInfo.ulMaxRPM))
-		return -1;
+		return -EINVAL;
 
 	if (PP_CAP(PHM_PlatformCaps_MicrocodeFanControl))
 		result = vega10_fan_ctrl_stop_smc_fan_control(hwmgr);
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_thermal.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_thermal.c
index a3331ffb2daf..1b1c88590156 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_thermal.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_thermal.c
@@ -191,7 +191,7 @@ int vega20_fan_ctrl_set_fan_speed_rpm(struct pp_hwmgr *hwmgr, uint32_t speed)
 	uint32_t tach_period, crystal_clock_freq;
 	int result = 0;
 
-	if (!speed)
+	if (!speed || speed > UINT_MAX/8)
 		return -EINVAL;
 
 	if (PP_CAP(PHM_PlatformCaps_MicrocodeFanControl)) {
diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
index 0c0b9aa44dfa..3fd8da5dc761 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
@@ -607,7 +607,8 @@ static int smu_sys_set_pp_table(void *handle,
 		return -EIO;
 	}
 
-	if (!smu_table->hardcode_pptable) {
+	if (!smu_table->hardcode_pptable || smu_table->power_play_table_size < size) {
+		kfree(smu_table->hardcode_pptable);
 		smu_table->hardcode_pptable = kzalloc(size, GFP_KERNEL);
 		if (!smu_table->hardcode_pptable)
 			return -ENOMEM;
@@ -2771,6 +2772,7 @@ int smu_get_power_limit(void *handle,
 			switch (amdgpu_ip_version(adev, MP1_HWIP, 0)) {
 			case IP_VERSION(13, 0, 2):
 			case IP_VERSION(13, 0, 6):
+			case IP_VERSION(13, 0, 12):
 			case IP_VERSION(13, 0, 14):
 			case IP_VERSION(11, 0, 7):
 			case IP_VERSION(11, 0, 11):
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 fc1297fecc62..d4b954b22441 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c
@@ -1267,6 +1267,9 @@ static int arcturus_set_fan_speed_rpm(struct smu_context *smu,
 	uint32_t crystal_clock_freq = 2500;
 	uint32_t tach_period;
 
+	if (!speed || speed > UINT_MAX/8)
+		return -EINVAL;
+
 	tach_period = 60 * crystal_clock_freq * 10000 / (8 * speed);
 	WREG32_SOC15(THM, 0, mmCG_TACH_CTRL_ARCT,
 		     REG_SET_FIELD(RREG32_SOC15(THM, 0, mmCG_TACH_CTRL_ARCT),
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
index 16fcd9dcd202..6c61e87359dd 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
@@ -1199,7 +1199,7 @@ int smu_v11_0_set_fan_speed_rpm(struct smu_context *smu,
 	uint32_t crystal_clock_freq = 2500;
 	uint32_t tach_period;
 
-	if (speed == 0)
+	if (!speed || speed > UINT_MAX/8)
 		return -EINVAL;
 	/*
 	 * To prevent from possible overheat, some ASICs may have requirement
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 9bca748ac2e9..3d3765815e24 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
@@ -664,7 +664,6 @@ static int vangogh_print_clk_levels(struct smu_context *smu,
 {
 	DpmClocks_t *clk_table = smu->smu_table.clocks_table;
 	SmuMetrics_t metrics;
-	struct smu_dpm_context *smu_dpm_ctx = &(smu->smu_dpm);
 	int i, idx, size = 0, ret = 0;
 	uint32_t cur_value = 0, value = 0, count = 0;
 	bool cur_value_match_level = false;
@@ -680,31 +679,25 @@ static int vangogh_print_clk_levels(struct smu_context *smu,
 
 	switch (clk_type) {
 	case SMU_OD_SCLK:
-		if (smu_dpm_ctx->dpm_level == AMD_DPM_FORCED_LEVEL_MANUAL) {
-			size += sysfs_emit_at(buf, size, "%s:\n", "OD_SCLK");
-			size += sysfs_emit_at(buf, size, "0: %10uMhz\n",
-			(smu->gfx_actual_hard_min_freq > 0) ? smu->gfx_actual_hard_min_freq : smu->gfx_default_hard_min_freq);
-			size += sysfs_emit_at(buf, size, "1: %10uMhz\n",
-			(smu->gfx_actual_soft_max_freq > 0) ? smu->gfx_actual_soft_max_freq : smu->gfx_default_soft_max_freq);
-		}
+		size += sysfs_emit_at(buf, size, "%s:\n", "OD_SCLK");
+		size += sysfs_emit_at(buf, size, "0: %10uMhz\n",
+		(smu->gfx_actual_hard_min_freq > 0) ? smu->gfx_actual_hard_min_freq : smu->gfx_default_hard_min_freq);
+		size += sysfs_emit_at(buf, size, "1: %10uMhz\n",
+		(smu->gfx_actual_soft_max_freq > 0) ? smu->gfx_actual_soft_max_freq : smu->gfx_default_soft_max_freq);
 		break;
 	case SMU_OD_CCLK:
-		if (smu_dpm_ctx->dpm_level == AMD_DPM_FORCED_LEVEL_MANUAL) {
-			size += sysfs_emit_at(buf, size, "CCLK_RANGE in Core%d:\n",  smu->cpu_core_id_select);
-			size += sysfs_emit_at(buf, size, "0: %10uMhz\n",
-			(smu->cpu_actual_soft_min_freq > 0) ? smu->cpu_actual_soft_min_freq : smu->cpu_default_soft_min_freq);
-			size += sysfs_emit_at(buf, size, "1: %10uMhz\n",
-			(smu->cpu_actual_soft_max_freq > 0) ? smu->cpu_actual_soft_max_freq : smu->cpu_default_soft_max_freq);
-		}
+		size += sysfs_emit_at(buf, size, "CCLK_RANGE in Core%d:\n",  smu->cpu_core_id_select);
+		size += sysfs_emit_at(buf, size, "0: %10uMhz\n",
+		(smu->cpu_actual_soft_min_freq > 0) ? smu->cpu_actual_soft_min_freq : smu->cpu_default_soft_min_freq);
+		size += sysfs_emit_at(buf, size, "1: %10uMhz\n",
+		(smu->cpu_actual_soft_max_freq > 0) ? smu->cpu_actual_soft_max_freq : smu->cpu_default_soft_max_freq);
 		break;
 	case SMU_OD_RANGE:
-		if (smu_dpm_ctx->dpm_level == AMD_DPM_FORCED_LEVEL_MANUAL) {
-			size += sysfs_emit_at(buf, size, "%s:\n", "OD_RANGE");
-			size += sysfs_emit_at(buf, size, "SCLK: %7uMhz %10uMhz\n",
-				smu->gfx_default_hard_min_freq, smu->gfx_default_soft_max_freq);
-			size += sysfs_emit_at(buf, size, "CCLK: %7uMhz %10uMhz\n",
-				smu->cpu_default_soft_min_freq, smu->cpu_default_soft_max_freq);
-		}
+		size += sysfs_emit_at(buf, size, "%s:\n", "OD_RANGE");
+		size += sysfs_emit_at(buf, size, "SCLK: %7uMhz %10uMhz\n",
+			smu->gfx_default_hard_min_freq, smu->gfx_default_soft_max_freq);
+		size += sysfs_emit_at(buf, size, "CCLK: %7uMhz %10uMhz\n",
+			smu->cpu_default_soft_min_freq, smu->cpu_default_soft_max_freq);
 		break;
 	case SMU_SOCCLK:
 		/* the level 3 ~ 6 of socclk use the same frequency for vangogh */
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
index 2c35eb31475a..5a1f24438e47 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
@@ -1731,7 +1731,6 @@ static ssize_t aldebaran_get_gpu_metrics(struct smu_context *smu,
 
 	gpu_metrics->average_gfx_activity = metrics.AverageGfxActivity;
 	gpu_metrics->average_umc_activity = metrics.AverageUclkActivity;
-	gpu_metrics->average_mm_activity = 0;
 
 	/* Valid power data is available only from primary die */
 	if (aldebaran_is_primary(smu)) {
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
index 2024a85fa11b..c5bca3019de0 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
@@ -58,6 +58,7 @@
 
 MODULE_FIRMWARE("amdgpu/aldebaran_smc.bin");
 MODULE_FIRMWARE("amdgpu/smu_13_0_0.bin");
+MODULE_FIRMWARE("amdgpu/smu_13_0_0_kicker.bin");
 MODULE_FIRMWARE("amdgpu/smu_13_0_7.bin");
 MODULE_FIRMWARE("amdgpu/smu_13_0_10.bin");
 
@@ -92,7 +93,7 @@ const int pmfw_decoded_link_width[7] = {0, 1, 2, 4, 8, 12, 16};
 int smu_v13_0_init_microcode(struct smu_context *smu)
 {
 	struct amdgpu_device *adev = smu->adev;
-	char ucode_prefix[15];
+	char ucode_prefix[30];
 	int err = 0;
 	const struct smc_firmware_header_v1_0 *hdr;
 	const struct common_firmware_header *header;
@@ -103,7 +104,10 @@ int smu_v13_0_init_microcode(struct smu_context *smu)
 		return 0;
 
 	amdgpu_ucode_ip_version_decode(adev, MP1_HWIP, ucode_prefix, sizeof(ucode_prefix));
-	err = amdgpu_ucode_request(adev, &adev->pm.fw, "amdgpu/%s.bin", ucode_prefix);
+	if (amdgpu_is_kicker_fw(adev))
+		err = amdgpu_ucode_request(adev, &adev->pm.fw, "amdgpu/%s_kicker.bin", ucode_prefix);
+	else
+		err = amdgpu_ucode_request(adev, &adev->pm.fw, "amdgpu/%s.bin", ucode_prefix);
 	if (err)
 		goto out;
 
@@ -1228,7 +1232,7 @@ int smu_v13_0_set_fan_speed_rpm(struct smu_context *smu,
 	uint32_t tach_period;
 	int ret;
 
-	if (!speed)
+	if (!speed || speed > UINT_MAX/8)
 		return -EINVAL;
 
 	ret = smu_v13_0_auto_fan_control(smu, 0);
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
index 55ed6247eb61..9ac694c4f1f7 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
@@ -275,8 +275,9 @@ static int smu_v13_0_6_init_microcode(struct smu_context *smu)
 	int var = (adev->pdev->device & 0xF);
 	char ucode_prefix[15];
 
-	/* No need to load P2S tables in IOV mode */
-	if (amdgpu_sriov_vf(adev))
+	/* No need to load P2S tables in IOV mode or for smu v13.0.12 */
+	if (amdgpu_sriov_vf(adev) ||
+	    (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(13, 0, 12)))
 		return 0;
 
 	if (!(adev->flags & AMD_IS_APU)) {
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c
index 452589adaf04..e5f619c979d8 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c
@@ -1883,16 +1883,6 @@ static int smu_v14_0_allow_ih_interrupt(struct smu_context *smu)
 				    NULL);
 }
 
-static int smu_v14_0_process_pending_interrupt(struct smu_context *smu)
-{
-	int ret = 0;
-
-	if (smu_cmn_feature_is_enabled(smu, SMU_FEATURE_ACDC_BIT))
-		ret = smu_v14_0_allow_ih_interrupt(smu);
-
-	return ret;
-}
-
 int smu_v14_0_enable_thermal_alert(struct smu_context *smu)
 {
 	int ret = 0;
@@ -1904,7 +1894,7 @@ int smu_v14_0_enable_thermal_alert(struct smu_context *smu)
 	if (ret)
 		return ret;
 
-	return smu_v14_0_process_pending_interrupt(smu);
+	return smu_v14_0_allow_ih_interrupt(smu);
 }
 
 int smu_v14_0_disable_thermal_alert(struct smu_context *smu)
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 9ec53431f2c3..e98a6a2f3e6a 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
@@ -1206,16 +1206,9 @@ static int smu_v14_0_2_print_clk_levels(struct smu_context *smu,
 							 PP_OD_FEATURE_GFXCLK_BIT))
 			break;
 
-		PPTable_t *pptable = smu->smu_table.driver_pptable;
-		const OverDriveLimits_t * const overdrive_upperlimits =
-					&pptable->SkuTable.OverDriveLimitsBasicMax;
-		const OverDriveLimits_t * const overdrive_lowerlimits =
-					&pptable->SkuTable.OverDriveLimitsBasicMin;
-
 		size += sysfs_emit_at(buf, size, "OD_SCLK_OFFSET:\n");
-		size += sysfs_emit_at(buf, size, "0: %dMhz\n1: %uMhz\n",
-					overdrive_lowerlimits->GfxclkFoffset,
-					overdrive_upperlimits->GfxclkFoffset);
+		size += sysfs_emit_at(buf, size, "%dMhz\n",
+					od_table->OverDriveTable.GfxclkFoffset);
 		break;
 
 	case SMU_OD_MCLK:
@@ -1350,12 +1343,8 @@ static int smu_v14_0_2_print_clk_levels(struct smu_context *smu,
 
 		if (smu_v14_0_2_is_od_feature_supported(smu, PP_OD_FEATURE_GFXCLK_BIT)) {
 			smu_v14_0_2_get_od_setting_limits(smu,
-							  PP_OD_FEATURE_GFXCLK_FMIN,
-							  &min_value,
-							  NULL);
-			smu_v14_0_2_get_od_setting_limits(smu,
 							  PP_OD_FEATURE_GFXCLK_FMAX,
-							  NULL,
+							  &min_value,
 							  &max_value);
 			size += sysfs_emit_at(buf, size, "SCLK_OFFSET: %7dMhz %10uMhz\n",
 					      min_value, max_value);
@@ -1639,6 +1628,39 @@ out:
 	adev->unique_id = ((uint64_t)upper32 << 32) | lower32;
 }
 
+static int smu_v14_0_2_get_fan_speed_pwm(struct smu_context *smu,
+					 uint32_t *speed)
+{
+	int ret;
+
+	if (!speed)
+		return -EINVAL;
+
+	ret = smu_v14_0_2_get_smu_metrics_data(smu,
+					       METRICS_CURR_FANPWM,
+					       speed);
+	if (ret) {
+		dev_err(smu->adev->dev, "Failed to get fan speed(PWM)!");
+		return ret;
+	}
+
+	/* Convert the PMFW output which is in percent to pwm(255) based */
+	*speed = min(*speed * 255 / 100, (uint32_t)255);
+
+	return 0;
+}
+
+static int smu_v14_0_2_get_fan_speed_rpm(struct smu_context *smu,
+					 uint32_t *speed)
+{
+	if (!speed)
+		return -EINVAL;
+
+	return smu_v14_0_2_get_smu_metrics_data(smu,
+						METRICS_CURR_FANSPEED,
+						speed);
+}
+
 static int smu_v14_0_2_get_power_limit(struct smu_context *smu,
 				       uint32_t *current_power_limit,
 				       uint32_t *default_power_limit,
@@ -2429,36 +2451,24 @@ static int smu_v14_0_2_od_edit_dpm_table(struct smu_context *smu,
 			return -ENOTSUPP;
 		}
 
-		for (i = 0; i < size; i += 2) {
-			if (i + 2 > size) {
-				dev_info(adev->dev, "invalid number of input parameters %d\n", size);
-				return -EINVAL;
-			}
-
-			switch (input[i]) {
-			case 1:
-				smu_v14_0_2_get_od_setting_limits(smu,
-								  PP_OD_FEATURE_GFXCLK_FMAX,
-								  &minimum,
-								  &maximum);
-				if (input[i + 1] < minimum ||
-				    input[i + 1] > maximum) {
-					dev_info(adev->dev, "GfxclkFmax (%ld) must be within [%u, %u]!\n",
-						input[i + 1], minimum, maximum);
-					return -EINVAL;
-				}
-
-				od_table->OverDriveTable.GfxclkFoffset = input[i + 1];
-				od_table->OverDriveTable.FeatureCtrlMask |= 1U << PP_OD_FEATURE_GFXCLK_BIT;
-				break;
+		if (size != 1) {
+			dev_info(adev->dev, "invalid number of input parameters %d\n", size);
+			return -EINVAL;
+		}
 
-			default:
-				dev_info(adev->dev, "Invalid SCLK_VDDC_TABLE index: %ld\n", input[i]);
-				dev_info(adev->dev, "Supported indices: [0:min,1:max]\n");
-				return -EINVAL;
-			}
+		smu_v14_0_2_get_od_setting_limits(smu,
+						  PP_OD_FEATURE_GFXCLK_FMAX,
+						  &minimum,
+						  &maximum);
+		if (input[0] < minimum ||
+		    input[0] > maximum) {
+			dev_info(adev->dev, "GfxclkFoffset must be within [%d, %u]!\n",
+				 minimum, maximum);
+			return -EINVAL;
 		}
 
+		od_table->OverDriveTable.GfxclkFoffset = input[0];
+		od_table->OverDriveTable.FeatureCtrlMask |= 1U << PP_OD_FEATURE_GFXCLK_BIT;
 		break;
 
 	case PP_OD_EDIT_MCLK_VDDC_TABLE:
@@ -2817,6 +2827,8 @@ static const struct pptable_funcs smu_v14_0_2_ppt_funcs = {
 	.set_performance_level = smu_v14_0_set_performance_level,
 	.gfx_off_control = smu_v14_0_gfx_off_control,
 	.get_unique_id = smu_v14_0_2_get_unique_id,
+	.get_fan_speed_pwm = smu_v14_0_2_get_fan_speed_pwm,
+	.get_fan_speed_rpm = smu_v14_0_2_get_fan_speed_rpm,
 	.get_power_limit = smu_v14_0_2_get_power_limit,
 	.set_power_limit = smu_v14_0_2_set_power_limit,
 	.get_power_profile_mode = smu_v14_0_2_get_power_profile_mode,
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
index 0d71db7be325..0ce1766c859f 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
@@ -459,8 +459,7 @@ int smu_cmn_send_smc_msg_with_param(struct smu_context *smu,
 	}
 	if (read_arg) {
 		smu_cmn_read_arg(smu, read_arg);
-		dev_dbg(adev->dev, "smu send message: %s(%d) param: 0x%08x, resp: 0x%08x,\
-			readval: 0x%08x\n",
+		dev_dbg(adev->dev, "smu send message: %s(%d) param: 0x%08x, resp: 0x%08x, readval: 0x%08x\n",
 			smu_get_message_name(smu, msg), index, param, reg, *read_arg);
 	} else {
 		dev_dbg(adev->dev, "smu send message: %s(%d) param: 0x%08x, resp: 0x%08x\n",
diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_wb_connector.c b/drivers/gpu/drm/arm/display/komeda/komeda_wb_connector.c
index ebccb74306a7..f30b3d5eeca5 100644
--- a/drivers/gpu/drm/arm/display/komeda/komeda_wb_connector.c
+++ b/drivers/gpu/drm/arm/display/komeda/komeda_wb_connector.c
@@ -160,6 +160,10 @@ static int komeda_wb_connector_add(struct komeda_kms_dev *kms,
 	formats = komeda_get_layer_fourcc_list(&mdev->fmt_tbl,
 					       kwb_conn->wb_layer->layer_type,
 					       &n_formats);
+	if (!formats) {
+		kfree(kwb_conn);
+		return -ENOMEM;
+	}
 
 	err = drm_writeback_connector_init(&kms->base, wb_conn,
 					   &komeda_wb_connector_funcs,
diff --git a/drivers/gpu/drm/ast/ast_dp.c b/drivers/gpu/drm/ast/ast_dp.c
index 00b364f9a71e..5dadc895e7f2 100644
--- a/drivers/gpu/drm/ast/ast_dp.c
+++ b/drivers/gpu/drm/ast/ast_dp.c
@@ -17,6 +17,12 @@ static bool ast_astdp_is_connected(struct ast_device *ast)
 {
 	if (!ast_get_index_reg_mask(ast, AST_IO_VGACRI, 0xDF, AST_IO_VGACRDF_HPD))
 		return false;
+	/*
+	 * HPD might be set even if no monitor is connected, so also check that
+	 * the link training was successful.
+	 */
+	if (!ast_get_index_reg_mask(ast, AST_IO_VGACRI, 0xDC, AST_IO_VGACRDC_LINK_SUCCESS))
+		return false;
 	return true;
 }
 
diff --git a/drivers/gpu/drm/ast/ast_mode.c b/drivers/gpu/drm/ast/ast_mode.c
index ed496fb32bf3..162dc0698f4a 100644
--- a/drivers/gpu/drm/ast/ast_mode.c
+++ b/drivers/gpu/drm/ast/ast_mode.c
@@ -131,7 +131,7 @@ static bool ast_get_vbios_mode_info(const struct drm_format_info *format,
 		return false;
 	}
 
-	switch (mode->crtc_hdisplay) {
+	switch (mode->hdisplay) {
 	case 640:
 		vbios_mode->enh_table = &res_640x480[refresh_rate_index];
 		break;
@@ -145,7 +145,7 @@ static bool ast_get_vbios_mode_info(const struct drm_format_info *format,
 		vbios_mode->enh_table = &res_1152x864[refresh_rate_index];
 		break;
 	case 1280:
-		if (mode->crtc_vdisplay == 800)
+		if (mode->vdisplay == 800)
 			vbios_mode->enh_table = &res_1280x800[refresh_rate_index];
 		else
 			vbios_mode->enh_table = &res_1280x1024[refresh_rate_index];
@@ -157,7 +157,7 @@ static bool ast_get_vbios_mode_info(const struct drm_format_info *format,
 		vbios_mode->enh_table = &res_1440x900[refresh_rate_index];
 		break;
 	case 1600:
-		if (mode->crtc_vdisplay == 900)
+		if (mode->vdisplay == 900)
 			vbios_mode->enh_table = &res_1600x900[refresh_rate_index];
 		else
 			vbios_mode->enh_table = &res_1600x1200[refresh_rate_index];
@@ -166,7 +166,7 @@ static bool ast_get_vbios_mode_info(const struct drm_format_info *format,
 		vbios_mode->enh_table = &res_1680x1050[refresh_rate_index];
 		break;
 	case 1920:
-		if (mode->crtc_vdisplay == 1080)
+		if (mode->vdisplay == 1080)
 			vbios_mode->enh_table = &res_1920x1080[refresh_rate_index];
 		else
 			vbios_mode->enh_table = &res_1920x1200[refresh_rate_index];
@@ -210,6 +210,7 @@ static bool ast_get_vbios_mode_info(const struct drm_format_info *format,
 	hborder = (vbios_mode->enh_table->flags & HBorder) ? 8 : 0;
 	vborder = (vbios_mode->enh_table->flags & VBorder) ? 8 : 0;
 
+	adjusted_mode->crtc_hdisplay = vbios_mode->enh_table->hde;
 	adjusted_mode->crtc_htotal = vbios_mode->enh_table->ht;
 	adjusted_mode->crtc_hblank_start = vbios_mode->enh_table->hde + hborder;
 	adjusted_mode->crtc_hblank_end = vbios_mode->enh_table->ht - hborder;
@@ -219,6 +220,7 @@ static bool ast_get_vbios_mode_info(const struct drm_format_info *format,
 					 vbios_mode->enh_table->hfp +
 					 vbios_mode->enh_table->hsync);
 
+	adjusted_mode->crtc_vdisplay = vbios_mode->enh_table->vde;
 	adjusted_mode->crtc_vtotal = vbios_mode->enh_table->vt;
 	adjusted_mode->crtc_vblank_start = vbios_mode->enh_table->vde + vborder;
 	adjusted_mode->crtc_vblank_end = vbios_mode->enh_table->vt - vborder;
@@ -1317,9 +1319,9 @@ static void ast_mode_config_helper_atomic_commit_tail(struct drm_atomic_state *s
 
 	/*
 	 * Concurrent operations could possibly trigger a call to
-	 * drm_connector_helper_funcs.get_modes by trying to read the
-	 * display modes. Protect access to I/O registers by acquiring
-	 * the I/O-register lock. Released in atomic_flush().
+	 * drm_connector_helper_funcs.get_modes by reading the display
+	 * modes. Protect access to registers by acquiring the modeset
+	 * lock.
 	 */
 	mutex_lock(&ast->modeset_lock);
 	drm_atomic_helper_commit_tail(state);
diff --git a/drivers/gpu/drm/bridge/adv7511/adv7511_audio.c b/drivers/gpu/drm/bridge/adv7511/adv7511_audio.c
index 8f786592143b..24e1e11acf69 100644
--- a/drivers/gpu/drm/bridge/adv7511/adv7511_audio.c
+++ b/drivers/gpu/drm/bridge/adv7511/adv7511_audio.c
@@ -244,7 +244,9 @@ static const struct hdmi_codec_pdata codec_data = {
 	.ops = &adv7511_codec_ops,
 	.max_i2s_channels = 2,
 	.i2s = 1,
+	.no_i2s_capture = 1,
 	.spdif = 1,
+	.no_spdif_capture = 1,
 };
 
 int adv7511_audio_init(struct device *dev, struct adv7511 *adv7511)
diff --git a/drivers/gpu/drm/bridge/analogix/anx7625.c b/drivers/gpu/drm/bridge/analogix/anx7625.c
index a2675b121fe4..c036bbc92ba9 100644
--- a/drivers/gpu/drm/bridge/analogix/anx7625.c
+++ b/drivers/gpu/drm/bridge/analogix/anx7625.c
@@ -2002,8 +2002,10 @@ static int anx7625_audio_get_eld(struct device *dev, void *data,
 		memset(buf, 0, len);
 	} else {
 		dev_dbg(dev, "audio copy eld\n");
+		mutex_lock(&ctx->connector->eld_mutex);
 		memcpy(buf, ctx->connector->eld,
 		       min(sizeof(ctx->connector->eld), len));
+		mutex_unlock(&ctx->connector->eld_mutex);
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/bridge/aux-hpd-bridge.c b/drivers/gpu/drm/bridge/aux-hpd-bridge.c
index 6886db2d9e00..8e889a38fad0 100644
--- a/drivers/gpu/drm/bridge/aux-hpd-bridge.c
+++ b/drivers/gpu/drm/bridge/aux-hpd-bridge.c
@@ -64,10 +64,11 @@ struct auxiliary_device *devm_drm_dp_hpd_bridge_alloc(struct device *parent, str
 	adev->id = ret;
 	adev->name = "dp_hpd_bridge";
 	adev->dev.parent = parent;
-	adev->dev.of_node = of_node_get(parent->of_node);
 	adev->dev.release = drm_aux_hpd_bridge_release;
 	adev->dev.platform_data = of_node_get(np);
 
+	device_set_of_node_from_dev(&adev->dev, parent);
+
 	ret = auxiliary_device_init(adev);
 	if (ret) {
 		of_node_put(adev->dev.platform_data);
diff --git a/drivers/gpu/drm/bridge/cadence/cdns-dsi-core.c b/drivers/gpu/drm/bridge/cadence/cdns-dsi-core.c
index 7457d38622b0..89eed0668bfb 100644
--- a/drivers/gpu/drm/bridge/cadence/cdns-dsi-core.c
+++ b/drivers/gpu/drm/bridge/cadence/cdns-dsi-core.c
@@ -568,15 +568,18 @@ static int cdns_dsi_check_conf(struct cdns_dsi *dsi,
 	struct phy_configure_opts_mipi_dphy *phy_cfg = &output->phy_opts.mipi_dphy;
 	unsigned long dsi_hss_hsa_hse_hbp;
 	unsigned int nlanes = output->dev->lanes;
+	int mode_clock = (mode_valid_check ? mode->clock : mode->crtc_clock);
 	int ret;
 
 	ret = cdns_dsi_mode2cfg(dsi, mode, dsi_cfg, mode_valid_check);
 	if (ret)
 		return ret;
 
-	phy_mipi_dphy_get_default_config(mode->crtc_clock * 1000,
-					 mipi_dsi_pixel_format_to_bpp(output->dev->format),
-					 nlanes, phy_cfg);
+	ret = phy_mipi_dphy_get_default_config(mode_clock * 1000,
+					       mipi_dsi_pixel_format_to_bpp(output->dev->format),
+					       nlanes, phy_cfg);
+	if (ret)
+		return ret;
 
 	ret = cdns_dsi_adjust_phy_config(dsi, dsi_cfg, phy_cfg, mode, mode_valid_check);
 	if (ret)
@@ -680,6 +683,11 @@ static void cdns_dsi_bridge_post_disable(struct drm_bridge *bridge)
 	struct cdns_dsi_input *input = bridge_to_cdns_dsi_input(bridge);
 	struct cdns_dsi *dsi = input_to_dsi(input);
 
+	dsi->phy_initialized = false;
+	dsi->link_initialized = false;
+	phy_power_off(dsi->dphy);
+	phy_exit(dsi->dphy);
+
 	pm_runtime_put(dsi->base.dev);
 }
 
@@ -761,7 +769,7 @@ static void cdns_dsi_bridge_enable(struct drm_bridge *bridge)
 	struct phy_configure_opts_mipi_dphy *phy_cfg = &output->phy_opts.mipi_dphy;
 	unsigned long tx_byte_period;
 	struct cdns_dsi_cfg dsi_cfg;
-	u32 tmp, reg_wakeup, div;
+	u32 tmp, reg_wakeup, div, status;
 	int nlanes;
 
 	if (WARN_ON(pm_runtime_get_sync(dsi->base.dev) < 0))
@@ -778,6 +786,19 @@ static void cdns_dsi_bridge_enable(struct drm_bridge *bridge)
 	cdns_dsi_hs_init(dsi);
 	cdns_dsi_init_link(dsi);
 
+	/*
+	 * Now that the DSI Link and DSI Phy are initialized,
+	 * wait for the CLK and Data Lanes to be ready.
+	 */
+	tmp = CLK_LANE_RDY;
+	for (int i = 0; i < nlanes; i++)
+		tmp |= DATA_LANE_RDY(i);
+
+	if (readl_poll_timeout(dsi->regs + MCTL_MAIN_STS, status,
+			       (tmp == (status & tmp)), 100, 500000))
+		dev_err(dsi->base.dev,
+			"Timed Out: DSI-DPhy Clock and Data Lanes not ready.\n");
+
 	writel(HBP_LEN(dsi_cfg.hbp) | HSA_LEN(dsi_cfg.hsa),
 	       dsi->regs + VID_HSIZE1);
 	writel(HFP_LEN(dsi_cfg.hfp) | HACT_LEN(dsi_cfg.hact),
@@ -952,7 +973,7 @@ static int cdns_dsi_attach(struct mipi_dsi_host *host,
 		bridge = drm_panel_bridge_add_typed(panel,
 						    DRM_MODE_CONNECTOR_DSI);
 	} else {
-		bridge = of_drm_find_bridge(dev->dev.of_node);
+		bridge = of_drm_find_bridge(np);
 		if (!bridge)
 			bridge = ERR_PTR(-EINVAL);
 	}
@@ -1152,7 +1173,6 @@ static int __maybe_unused cdns_dsi_suspend(struct device *dev)
 	clk_disable_unprepare(dsi->dsi_sys_clk);
 	clk_disable_unprepare(dsi->dsi_p_clk);
 	reset_control_assert(dsi->dsi_p_rst);
-	dsi->link_initialized = false;
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.c b/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.c
index 41f72d458487..9ba2a667a1f3 100644
--- a/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.c
+++ b/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.c
@@ -2463,9 +2463,9 @@ static int cdns_mhdp_probe(struct platform_device *pdev)
 	if (!mhdp)
 		return -ENOMEM;
 
-	clk = devm_clk_get(dev, NULL);
+	clk = devm_clk_get_enabled(dev, NULL);
 	if (IS_ERR(clk)) {
-		dev_err(dev, "couldn't get clk: %ld\n", PTR_ERR(clk));
+		dev_err(dev, "couldn't get and enable clk: %ld\n", PTR_ERR(clk));
 		return PTR_ERR(clk);
 	}
 
@@ -2504,14 +2504,12 @@ static int cdns_mhdp_probe(struct platform_device *pdev)
 
 	mhdp->info = of_device_get_match_data(dev);
 
-	clk_prepare_enable(clk);
-
 	pm_runtime_enable(dev);
 	ret = pm_runtime_resume_and_get(dev);
 	if (ret < 0) {
 		dev_err(dev, "pm_runtime_resume_and_get failed\n");
 		pm_runtime_disable(dev);
-		goto clk_disable;
+		return ret;
 	}
 
 	if (mhdp->info && mhdp->info->ops && mhdp->info->ops->init) {
@@ -2590,8 +2588,6 @@ plat_fini:
 runtime_put:
 	pm_runtime_put_sync(dev);
 	pm_runtime_disable(dev);
-clk_disable:
-	clk_disable_unprepare(mhdp->clk);
 
 	return ret;
 }
@@ -2632,8 +2628,6 @@ static void cdns_mhdp_remove(struct platform_device *pdev)
 	cancel_work_sync(&mhdp->modeset_retry_work);
 	flush_work(&mhdp->hpd_work);
 	/* Ignoring mhdp->hdcp.check_work and mhdp->hdcp.prop_work here. */
-
-	clk_disable_unprepare(mhdp->clk);
 }
 
 static const struct of_device_id mhdp_ids[] = {
diff --git a/drivers/gpu/drm/bridge/ite-it6505.c b/drivers/gpu/drm/bridge/ite-it6505.c
index 008d86cc562a..967aa24b7c53 100644
--- a/drivers/gpu/drm/bridge/ite-it6505.c
+++ b/drivers/gpu/drm/bridge/ite-it6505.c
@@ -296,11 +296,11 @@
 #define MAX_LANE_COUNT 4
 #define MAX_LINK_RATE HBR
 #define AUTO_TRAIN_RETRY 3
-#define MAX_HDCP_DOWN_STREAM_COUNT 10
+#define MAX_HDCP_DOWN_STREAM_COUNT 127
 #define MAX_CR_LEVEL 0x03
 #define MAX_EQ_LEVEL 0x03
 #define AUX_WAIT_TIMEOUT_MS 15
-#define AUX_FIFO_MAX_SIZE 32
+#define AUX_FIFO_MAX_SIZE 16
 #define PIXEL_CLK_DELAY 1
 #define PIXEL_CLK_INVERSE 0
 #define ADJUST_PHASE_THRESHOLD 80000
@@ -2023,7 +2023,7 @@ static bool it6505_hdcp_part2_ksvlist_check(struct it6505 *it6505)
 {
 	struct device *dev = it6505->dev;
 	u8 av[5][4], bv[5][4];
-	int i, err;
+	int i, err, retry;
 
 	i = it6505_setup_sha1_input(it6505, it6505->sha1_input);
 	if (i <= 0) {
@@ -2032,22 +2032,29 @@ static bool it6505_hdcp_part2_ksvlist_check(struct it6505 *it6505)
 	}
 
 	it6505_sha1_digest(it6505, it6505->sha1_input, i, (u8 *)av);
+	/*1B-05 V' must retry 3 times */
+	for (retry = 0; retry < 3; retry++) {
+		err = it6505_get_dpcd(it6505, DP_AUX_HDCP_V_PRIME(0), (u8 *)bv,
+				      sizeof(bv));
 
-	err = it6505_get_dpcd(it6505, DP_AUX_HDCP_V_PRIME(0), (u8 *)bv,
-			      sizeof(bv));
+		if (err < 0) {
+			dev_err(dev, "Read V' value Fail %d", retry);
+			continue;
+		}
 
-	if (err < 0) {
-		dev_err(dev, "Read V' value Fail");
-		return false;
-	}
+		for (i = 0; i < 5; i++)
+			if (bv[i][3] != av[i][0] || bv[i][2] != av[i][1] ||
+			    bv[i][1] != av[i][2] || bv[i][0] != av[i][3])
+				break;
 
-	for (i = 0; i < 5; i++)
-		if (bv[i][3] != av[i][0] || bv[i][2] != av[i][1] ||
-		    bv[i][1] != av[i][2] || bv[i][0] != av[i][3])
-			return false;
+		if (i == 5) {
+			DRM_DEV_DEBUG_DRIVER(dev, "V' all match!! %d", retry);
+			return true;
+		}
+	}
 
-	DRM_DEV_DEBUG_DRIVER(dev, "V' all match!!");
-	return true;
+	DRM_DEV_DEBUG_DRIVER(dev, "V' NOT match!! %d", retry);
+	return false;
 }
 
 static void it6505_hdcp_wait_ksv_list(struct work_struct *work)
@@ -2055,12 +2062,13 @@ static void it6505_hdcp_wait_ksv_list(struct work_struct *work)
 	struct it6505 *it6505 = container_of(work, struct it6505,
 					     hdcp_wait_ksv_list);
 	struct device *dev = it6505->dev;
-	unsigned int timeout = 5000;
-	u8 bstatus = 0;
+	u8 bstatus;
 	bool ksv_list_check;
+	/* 1B-04 wait ksv list for 5s */
+	unsigned long timeout = jiffies +
+				msecs_to_jiffies(5000) + 1;
 
-	timeout /= 20;
-	while (timeout > 0) {
+	for (;;) {
 		if (!it6505_get_sink_hpd_status(it6505))
 			return;
 
@@ -2069,27 +2077,23 @@ static void it6505_hdcp_wait_ksv_list(struct work_struct *work)
 		if (bstatus & DP_BSTATUS_READY)
 			break;
 
-		msleep(20);
-		timeout--;
-	}
+		if (time_after(jiffies, timeout)) {
+			DRM_DEV_DEBUG_DRIVER(dev, "KSV list wait timeout");
+			goto timeout;
+		}
 
-	if (timeout == 0) {
-		DRM_DEV_DEBUG_DRIVER(dev, "timeout and ksv list wait failed");
-		goto timeout;
+		msleep(20);
 	}
 
 	ksv_list_check = it6505_hdcp_part2_ksvlist_check(it6505);
 	DRM_DEV_DEBUG_DRIVER(dev, "ksv list ready, ksv list check %s",
 			     ksv_list_check ? "pass" : "fail");
-	if (ksv_list_check) {
-		it6505_set_bits(it6505, REG_HDCP_TRIGGER,
-				HDCP_TRIGGER_KSV_DONE, HDCP_TRIGGER_KSV_DONE);
+
+	if (ksv_list_check)
 		return;
-	}
+
 timeout:
-	it6505_set_bits(it6505, REG_HDCP_TRIGGER,
-			HDCP_TRIGGER_KSV_DONE | HDCP_TRIGGER_KSV_FAIL,
-			HDCP_TRIGGER_KSV_DONE | HDCP_TRIGGER_KSV_FAIL);
+	it6505_start_hdcp(it6505);
 }
 
 static void it6505_hdcp_work(struct work_struct *work)
@@ -2312,14 +2316,20 @@ static int it6505_process_hpd_irq(struct it6505 *it6505)
 	DRM_DEV_DEBUG_DRIVER(dev, "dp_irq_vector = 0x%02x", dp_irq_vector);
 
 	if (dp_irq_vector & DP_CP_IRQ) {
-		it6505_set_bits(it6505, REG_HDCP_TRIGGER, HDCP_TRIGGER_CPIRQ,
-				HDCP_TRIGGER_CPIRQ);
-
 		bstatus = it6505_dpcd_read(it6505, DP_AUX_HDCP_BSTATUS);
 		if (bstatus < 0)
 			return bstatus;
 
 		DRM_DEV_DEBUG_DRIVER(dev, "Bstatus = 0x%02x", bstatus);
+
+		/*Check BSTATUS when recive CP_IRQ */
+		if (bstatus & DP_BSTATUS_R0_PRIME_READY &&
+		    it6505->hdcp_status == HDCP_AUTH_GOING)
+			it6505_set_bits(it6505, REG_HDCP_TRIGGER, HDCP_TRIGGER_CPIRQ,
+					HDCP_TRIGGER_CPIRQ);
+		else if (bstatus & (DP_BSTATUS_REAUTH_REQ | DP_BSTATUS_LINK_FAILURE) &&
+			 it6505->hdcp_status == HDCP_AUTH_DONE)
+			it6505_start_hdcp(it6505);
 	}
 
 	ret = drm_dp_dpcd_read_link_status(&it6505->aux, link_status);
@@ -2456,7 +2466,11 @@ static void it6505_irq_hdcp_ksv_check(struct it6505 *it6505)
 {
 	struct device *dev = it6505->dev;
 
-	DRM_DEV_DEBUG_DRIVER(dev, "HDCP event Interrupt");
+	DRM_DEV_DEBUG_DRIVER(dev, "HDCP repeater R0 event Interrupt");
+	/* 1B01 HDCP encription should start when R0 is ready*/
+	it6505_set_bits(it6505, REG_HDCP_TRIGGER,
+			HDCP_TRIGGER_KSV_DONE, HDCP_TRIGGER_KSV_DONE);
+
 	schedule_work(&it6505->hdcp_wait_ksv_list);
 }
 
diff --git a/drivers/gpu/drm/bridge/ite-it66121.c b/drivers/gpu/drm/bridge/ite-it66121.c
index 925e42f46cd8..0f8d3ab30daa 100644
--- a/drivers/gpu/drm/bridge/ite-it66121.c
+++ b/drivers/gpu/drm/bridge/ite-it66121.c
@@ -1452,8 +1452,10 @@ static int it66121_audio_get_eld(struct device *dev, void *data,
 		dev_dbg(dev, "No connector present, passing empty EDID data");
 		memset(buf, 0, len);
 	} else {
+		mutex_lock(&ctx->connector->eld_mutex);
 		memcpy(buf, ctx->connector->eld,
 		       min(sizeof(ctx->connector->eld), len));
+		mutex_unlock(&ctx->connector->eld_mutex);
 	}
 	mutex_unlock(&ctx->lock);
 
diff --git a/drivers/gpu/drm/bridge/lontium-lt9611uxc.c b/drivers/gpu/drm/bridge/lontium-lt9611uxc.c
index 4d1d40e1f1b4..748bed8acd2d 100644
--- a/drivers/gpu/drm/bridge/lontium-lt9611uxc.c
+++ b/drivers/gpu/drm/bridge/lontium-lt9611uxc.c
@@ -879,7 +879,11 @@ retry:
 		}
 	}
 
-	return lt9611uxc_audio_init(dev, lt9611uxc);
+	ret = lt9611uxc_audio_init(dev, lt9611uxc);
+	if (ret)
+		goto err_remove_bridge;
+
+	return 0;
 
 err_remove_bridge:
 	free_irq(client->irq, lt9611uxc);
diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi86.c b/drivers/gpu/drm/bridge/ti-sn65dsi86.c
index 582cf4f73a74..4d17d1e1c38b 100644
--- a/drivers/gpu/drm/bridge/ti-sn65dsi86.c
+++ b/drivers/gpu/drm/bridge/ti-sn65dsi86.c
@@ -331,12 +331,18 @@ static void ti_sn65dsi86_enable_comms(struct ti_sn65dsi86 *pdata)
 	 * 200 ms.  We'll assume that the panel driver will have the hardcoded
 	 * delay in its prepare and always disable HPD.
 	 *
-	 * If HPD somehow makes sense on some future panel we'll have to
-	 * change this to be conditional on someone specifying that HPD should
-	 * be used.
+	 * For DisplayPort bridge type, we need HPD. So we use the bridge type
+	 * to conditionally disable HPD.
+	 * NOTE: The bridge type is set in ti_sn_bridge_probe() but enable_comms()
+	 * can be called before. So for DisplayPort, HPD will be enabled once
+	 * bridge type is set. We are using bridge type instead of "no-hpd"
+	 * property because it is not used properly in devicetree description
+	 * and hence is unreliable.
 	 */
-	regmap_update_bits(pdata->regmap, SN_HPD_DISABLE_REG, HPD_DISABLE,
-			   HPD_DISABLE);
+
+	if (pdata->bridge.type != DRM_MODE_CONNECTOR_DisplayPort)
+		regmap_update_bits(pdata->regmap, SN_HPD_DISABLE_REG, HPD_DISABLE,
+				   HPD_DISABLE);
 
 	pdata->comms_enabled = true;
 
@@ -424,36 +430,8 @@ static int status_show(struct seq_file *s, void *data)
 
 	return 0;
 }
-
 DEFINE_SHOW_ATTRIBUTE(status);
 
-static void ti_sn65dsi86_debugfs_remove(void *data)
-{
-	debugfs_remove_recursive(data);
-}
-
-static void ti_sn65dsi86_debugfs_init(struct ti_sn65dsi86 *pdata)
-{
-	struct device *dev = pdata->dev;
-	struct dentry *debugfs;
-	int ret;
-
-	debugfs = debugfs_create_dir(dev_name(dev), NULL);
-
-	/*
-	 * We might get an error back if debugfs wasn't enabled in the kernel
-	 * so let's just silently return upon failure.
-	 */
-	if (IS_ERR_OR_NULL(debugfs))
-		return;
-
-	ret = devm_add_action_or_reset(dev, ti_sn65dsi86_debugfs_remove, debugfs);
-	if (ret)
-		return;
-
-	debugfs_create_file("status", 0600, debugfs, pdata, &status_fops);
-}
-
 /* -----------------------------------------------------------------------------
  * Auxiliary Devices (*not* AUX)
  */
@@ -480,6 +458,7 @@ static int ti_sn65dsi86_add_aux_device(struct ti_sn65dsi86 *pdata,
 				       const char *name)
 {
 	struct device *dev = pdata->dev;
+	const struct i2c_client *client = to_i2c_client(dev);
 	struct auxiliary_device *aux;
 	int ret;
 
@@ -488,6 +467,7 @@ static int ti_sn65dsi86_add_aux_device(struct ti_sn65dsi86 *pdata,
 		return -ENOMEM;
 
 	aux->name = name;
+	aux->id = (client->adapter->nr << 10) | client->addr;
 	aux->dev.parent = dev;
 	aux->dev.release = ti_sn65dsi86_aux_device_release;
 	device_set_of_node_from_dev(&aux->dev, dev);
@@ -1199,9 +1179,14 @@ static enum drm_connector_status ti_sn_bridge_detect(struct drm_bridge *bridge)
 	struct ti_sn65dsi86 *pdata = bridge_to_ti_sn65dsi86(bridge);
 	int val = 0;
 
-	pm_runtime_get_sync(pdata->dev);
+	/*
+	 * Runtime reference is grabbed in ti_sn_bridge_hpd_enable()
+	 * as the chip won't report HPD just after being powered on.
+	 * HPD_DEBOUNCED_STATE reflects correct state only after the
+	 * debounce time (~100-400 ms).
+	 */
+
 	regmap_read(pdata->regmap, SN_HPD_DISABLE_REG, &val);
-	pm_runtime_put_autosuspend(pdata->dev);
 
 	return val & HPD_DEBOUNCED_STATE ? connector_status_connected
 					 : connector_status_disconnected;
@@ -1215,6 +1200,35 @@ static const struct drm_edid *ti_sn_bridge_edid_read(struct drm_bridge *bridge,
 	return drm_edid_read_ddc(connector, &pdata->aux.ddc);
 }
 
+static void ti_sn65dsi86_debugfs_init(struct drm_bridge *bridge, struct dentry *root)
+{
+	struct ti_sn65dsi86 *pdata = bridge_to_ti_sn65dsi86(bridge);
+	struct dentry *debugfs;
+
+	debugfs = debugfs_create_dir(dev_name(pdata->dev), root);
+	debugfs_create_file("status", 0600, debugfs, pdata, &status_fops);
+}
+
+static void ti_sn_bridge_hpd_enable(struct drm_bridge *bridge)
+{
+	struct ti_sn65dsi86 *pdata = bridge_to_ti_sn65dsi86(bridge);
+
+	/*
+	 * Device needs to be powered on before reading the HPD state
+	 * for reliable hpd detection in ti_sn_bridge_detect() due to
+	 * the high debounce time.
+	 */
+
+	pm_runtime_get_sync(pdata->dev);
+}
+
+static void ti_sn_bridge_hpd_disable(struct drm_bridge *bridge)
+{
+	struct ti_sn65dsi86 *pdata = bridge_to_ti_sn65dsi86(bridge);
+
+	pm_runtime_put_autosuspend(pdata->dev);
+}
+
 static const struct drm_bridge_funcs ti_sn_bridge_funcs = {
 	.attach = ti_sn_bridge_attach,
 	.detach = ti_sn_bridge_detach,
@@ -1228,6 +1242,9 @@ static const struct drm_bridge_funcs ti_sn_bridge_funcs = {
 	.atomic_reset = drm_atomic_helper_bridge_reset,
 	.atomic_duplicate_state = drm_atomic_helper_bridge_duplicate_state,
 	.atomic_destroy_state = drm_atomic_helper_bridge_destroy_state,
+	.debugfs_init = ti_sn65dsi86_debugfs_init,
+	.hpd_enable = ti_sn_bridge_hpd_enable,
+	.hpd_disable = ti_sn_bridge_hpd_disable,
 };
 
 static void ti_sn_bridge_parse_lanes(struct ti_sn65dsi86 *pdata,
@@ -1316,8 +1333,26 @@ static int ti_sn_bridge_probe(struct auxiliary_device *adev,
 	pdata->bridge.type = pdata->next_bridge->type == DRM_MODE_CONNECTOR_DisplayPort
 			   ? DRM_MODE_CONNECTOR_DisplayPort : DRM_MODE_CONNECTOR_eDP;
 
-	if (pdata->bridge.type == DRM_MODE_CONNECTOR_DisplayPort)
-		pdata->bridge.ops = DRM_BRIDGE_OP_EDID | DRM_BRIDGE_OP_DETECT;
+	if (pdata->bridge.type == DRM_MODE_CONNECTOR_DisplayPort) {
+		pdata->bridge.ops = DRM_BRIDGE_OP_EDID | DRM_BRIDGE_OP_DETECT |
+				    DRM_BRIDGE_OP_HPD;
+		/*
+		 * If comms were already enabled they would have been enabled
+		 * with the wrong value of HPD_DISABLE. Update it now. Comms
+		 * could be enabled if anyone is holding a pm_runtime reference
+		 * (like if a GPIO is in use). Note that in most cases nobody
+		 * is doing AUX channel xfers before the bridge is added so
+		 * HPD doesn't _really_ matter then. The only exception is in
+		 * the eDP case where the panel wants to read the EDID before
+		 * the bridge is added. We always consistently have HPD disabled
+		 * for eDP.
+		 */
+		mutex_lock(&pdata->comms_mutex);
+		if (pdata->comms_enabled)
+			regmap_update_bits(pdata->regmap, SN_HPD_DISABLE_REG,
+					   HPD_DISABLE, 0);
+		mutex_unlock(&pdata->comms_mutex);
+	}
 
 	drm_bridge_add(&pdata->bridge);
 
@@ -1936,8 +1971,6 @@ static int ti_sn65dsi86_probe(struct i2c_client *client)
 	if (ret)
 		return ret;
 
-	ti_sn65dsi86_debugfs_init(pdata);
-
 	/*
 	 * Break ourselves up into a collection of aux devices. The only real
 	 * motiviation here is to solve the chicken-and-egg problem of probe
diff --git a/drivers/gpu/drm/display/drm_dp_cec.c b/drivers/gpu/drm/display/drm_dp_cec.c
index 007ceb281d00..56a4965e518c 100644
--- a/drivers/gpu/drm/display/drm_dp_cec.c
+++ b/drivers/gpu/drm/display/drm_dp_cec.c
@@ -311,16 +311,6 @@ void drm_dp_cec_attach(struct drm_dp_aux *aux, u16 source_physical_address)
 	if (!aux->transfer)
 		return;
 
-#ifndef CONFIG_MEDIA_CEC_RC
-	/*
-	 * CEC_CAP_RC is part of CEC_CAP_DEFAULTS, but it is stripped by
-	 * cec_allocate_adapter() if CONFIG_MEDIA_CEC_RC is undefined.
-	 *
-	 * Do this here as well to ensure the tests against cec_caps are
-	 * correct.
-	 */
-	cec_caps &= ~CEC_CAP_RC;
-#endif
 	cancel_delayed_work_sync(&aux->cec.unregister_work);
 
 	mutex_lock(&aux->cec.lock);
@@ -337,7 +327,9 @@ void drm_dp_cec_attach(struct drm_dp_aux *aux, u16 source_physical_address)
 		num_las = CEC_MAX_LOG_ADDRS;
 
 	if (aux->cec.adap) {
-		if (aux->cec.adap->capabilities == cec_caps &&
+		/* Check if the adapter properties have changed */
+		if ((aux->cec.adap->capabilities & CEC_CAP_MONITOR_ALL) ==
+		    (cec_caps & CEC_CAP_MONITOR_ALL) &&
 		    aux->cec.adap->available_log_addrs == num_las) {
 			/* Unchanged, so just set the phys addr */
 			cec_s_phys_addr(aux->cec.adap, source_physical_address, false);
diff --git a/drivers/gpu/drm/display/drm_dp_helper.c b/drivers/gpu/drm/display/drm_dp_helper.c
index 6ee51003de3c..9fa13da513d2 100644
--- a/drivers/gpu/drm/display/drm_dp_helper.c
+++ b/drivers/gpu/drm/display/drm_dp_helper.c
@@ -2421,7 +2421,7 @@ u8 drm_dp_dsc_sink_bpp_incr(const u8 dsc_dpcd[DP_DSC_RECEIVER_CAP_SIZE])
 {
 	u8 bpp_increment_dpcd = dsc_dpcd[DP_DSC_BITS_PER_PIXEL_INC - DP_DSC_SUPPORT];
 
-	switch (bpp_increment_dpcd) {
+	switch (bpp_increment_dpcd & DP_DSC_BITS_PER_PIXEL_MASK) {
 	case DP_DSC_BITS_PER_PIXEL_1_16:
 		return 16;
 	case DP_DSC_BITS_PER_PIXEL_1_8:
diff --git a/drivers/gpu/drm/display/drm_dp_mst_topology.c b/drivers/gpu/drm/display/drm_dp_mst_topology.c
index f0c6d50d8c33..3e5f721d7540 100644
--- a/drivers/gpu/drm/display/drm_dp_mst_topology.c
+++ b/drivers/gpu/drm/display/drm_dp_mst_topology.c
@@ -179,13 +179,13 @@ static int
 drm_dp_mst_rad_to_str(const u8 rad[8], u8 lct, char *out, size_t len)
 {
 	int i;
-	u8 unpacked_rad[16];
+	u8 unpacked_rad[16] = {};
 
-	for (i = 0; i < lct; i++) {
+	for (i = 1; i < lct; i++) {
 		if (i % 2)
-			unpacked_rad[i] = rad[i / 2] >> 4;
+			unpacked_rad[i] = rad[(i - 1) / 2] >> 4;
 		else
-			unpacked_rad[i] = rad[i / 2] & BIT_MASK(4);
+			unpacked_rad[i] = rad[(i - 1) / 2] & 0xF;
 	}
 
 	/* TODO: Eventually add something to printk so we can format the rad
@@ -4034,6 +4034,22 @@ out:
 	return 0;
 }
 
+static bool primary_mstb_probing_is_done(struct drm_dp_mst_topology_mgr *mgr)
+{
+	bool probing_done = false;
+
+	mutex_lock(&mgr->lock);
+
+	if (mgr->mst_primary && drm_dp_mst_topology_try_get_mstb(mgr->mst_primary)) {
+		probing_done = mgr->mst_primary->link_address_sent;
+		drm_dp_mst_topology_put_mstb(mgr->mst_primary);
+	}
+
+	mutex_unlock(&mgr->lock);
+
+	return probing_done;
+}
+
 static inline bool
 drm_dp_mst_process_up_req(struct drm_dp_mst_topology_mgr *mgr,
 			  struct drm_dp_pending_up_req *up_req)
@@ -4064,8 +4080,12 @@ drm_dp_mst_process_up_req(struct drm_dp_mst_topology_mgr *mgr,
 
 	/* TODO: Add missing handler for DP_RESOURCE_STATUS_NOTIFY events */
 	if (msg->req_type == DP_CONNECTION_STATUS_NOTIFY) {
-		dowork = drm_dp_mst_handle_conn_stat(mstb, &msg->u.conn_stat);
-		hotplug = true;
+		if (!primary_mstb_probing_is_done(mgr)) {
+			drm_dbg_kms(mgr->dev, "Got CSN before finish topology probing. Skip it.\n");
+		} else {
+			dowork = drm_dp_mst_handle_conn_stat(mstb, &msg->u.conn_stat);
+			hotplug = true;
+		}
 	}
 
 	drm_dp_mst_topology_put_mstb(mstb);
@@ -4144,10 +4164,11 @@ static int drm_dp_mst_handle_up_req(struct drm_dp_mst_topology_mgr *mgr)
 	drm_dp_send_up_ack_reply(mgr, mst_primary, up_req->msg.req_type,
 				 false);
 
+	drm_dp_mst_topology_put_mstb(mst_primary);
+
 	if (up_req->msg.req_type == DP_CONNECTION_STATUS_NOTIFY) {
 		const struct drm_dp_connection_status_notify *conn_stat =
 			&up_req->msg.u.conn_stat;
-		bool handle_csn;
 
 		drm_dbg_kms(mgr->dev, "Got CSN: pn: %d ldps:%d ddps: %d mcs: %d ip: %d pdt: %d\n",
 			    conn_stat->port_number,
@@ -4156,16 +4177,6 @@ static int drm_dp_mst_handle_up_req(struct drm_dp_mst_topology_mgr *mgr)
 			    conn_stat->message_capability_status,
 			    conn_stat->input_port,
 			    conn_stat->peer_device_type);
-
-		mutex_lock(&mgr->probe_lock);
-		handle_csn = mst_primary->link_address_sent;
-		mutex_unlock(&mgr->probe_lock);
-
-		if (!handle_csn) {
-			drm_dbg_kms(mgr->dev, "Got CSN before finish topology probing. Skip it.");
-			kfree(up_req);
-			goto out_put_primary;
-		}
 	} else if (up_req->msg.req_type == DP_RESOURCE_STATUS_NOTIFY) {
 		const struct drm_dp_resource_status_notify *res_stat =
 			&up_req->msg.u.resource_stat;
@@ -4180,9 +4191,6 @@ static int drm_dp_mst_handle_up_req(struct drm_dp_mst_topology_mgr *mgr)
 	list_add_tail(&up_req->next, &mgr->up_req_list);
 	mutex_unlock(&mgr->up_req_lock);
 	queue_work(system_long_wq, &mgr->up_req_work);
-
-out_put_primary:
-	drm_dp_mst_topology_put_mstb(mst_primary);
 out_clear_reply:
 	memset(&mgr->up_req_recv, 0, sizeof(struct drm_dp_sideband_msg_rx));
 	return 0;
diff --git a/drivers/gpu/drm/display/drm_hdmi_state_helper.c b/drivers/gpu/drm/display/drm_hdmi_state_helper.c
index feb7a3a75981..936a8f95d80f 100644
--- a/drivers/gpu/drm/display/drm_hdmi_state_helper.c
+++ b/drivers/gpu/drm/display/drm_hdmi_state_helper.c
@@ -347,6 +347,8 @@ static int hdmi_generate_avi_infoframe(const struct drm_connector *connector,
 		is_limited_range ? HDMI_QUANTIZATION_RANGE_LIMITED : HDMI_QUANTIZATION_RANGE_FULL;
 	int ret;
 
+	infoframe->set = false;
+
 	ret = drm_hdmi_avi_infoframe_from_display_mode(frame, connector, mode);
 	if (ret)
 		return ret;
@@ -376,6 +378,8 @@ static int hdmi_generate_spd_infoframe(const struct drm_connector *connector,
 		&infoframe->data.spd;
 	int ret;
 
+	infoframe->set = false;
+
 	ret = hdmi_spd_infoframe_init(frame,
 				      connector->hdmi.vendor,
 				      connector->hdmi.product);
@@ -398,6 +402,8 @@ static int hdmi_generate_hdr_infoframe(const struct drm_connector *connector,
 		&infoframe->data.drm;
 	int ret;
 
+	infoframe->set = false;
+
 	if (connector->max_bpc < 10)
 		return 0;
 
@@ -425,6 +431,8 @@ static int hdmi_generate_hdmi_vendor_infoframe(const struct drm_connector *conne
 		&infoframe->data.vendor.hdmi;
 	int ret;
 
+	infoframe->set = false;
+
 	if (!info->has_hdmi_infoframe)
 		return 0;
 
diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c
index 5186d2114a50..40e4e1b6c911 100644
--- a/drivers/gpu/drm/drm_atomic_helper.c
+++ b/drivers/gpu/drm/drm_atomic_helper.c
@@ -574,6 +574,30 @@ mode_valid(struct drm_atomic_state *state)
 	return 0;
 }
 
+static int drm_atomic_check_valid_clones(struct drm_atomic_state *state,
+					 struct drm_crtc *crtc)
+{
+	struct drm_encoder *drm_enc;
+	struct drm_crtc_state *crtc_state = drm_atomic_get_new_crtc_state(state,
+									  crtc);
+
+	drm_for_each_encoder_mask(drm_enc, crtc->dev, crtc_state->encoder_mask) {
+		if (!drm_enc->possible_clones) {
+			DRM_DEBUG("enc%d possible_clones is 0\n", drm_enc->base.id);
+			continue;
+		}
+
+		if ((crtc_state->encoder_mask & drm_enc->possible_clones) !=
+		    crtc_state->encoder_mask) {
+			DRM_DEBUG("crtc%d failed valid clone check for mask 0x%x\n",
+				  crtc->base.id, crtc_state->encoder_mask);
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
 /**
  * drm_atomic_helper_check_modeset - validate state object for modeset changes
  * @dev: DRM device
@@ -745,6 +769,10 @@ drm_atomic_helper_check_modeset(struct drm_device *dev,
 		ret = drm_atomic_add_affected_planes(state, crtc);
 		if (ret != 0)
 			return ret;
+
+		ret = drm_atomic_check_valid_clones(state, crtc);
+		if (ret != 0)
+			return ret;
 	}
 
 	/*
@@ -1376,7 +1404,7 @@ crtc_set_mode(struct drm_device *dev, struct drm_atomic_state *old_state)
 		mode = &new_crtc_state->mode;
 		adjusted_mode = &new_crtc_state->adjusted_mode;
 
-		if (!new_crtc_state->mode_changed)
+		if (!new_crtc_state->mode_changed && !new_crtc_state->connectors_changed)
 			continue;
 
 		drm_dbg_atomic(dev, "modeset on [ENCODER:%d:%s]\n",
diff --git a/drivers/gpu/drm/drm_atomic_uapi.c b/drivers/gpu/drm/drm_atomic_uapi.c
index 370dc676e3aa..fd36b8fd54e9 100644
--- a/drivers/gpu/drm/drm_atomic_uapi.c
+++ b/drivers/gpu/drm/drm_atomic_uapi.c
@@ -956,6 +956,10 @@ int drm_atomic_connector_commit_dpms(struct drm_atomic_state *state,
 
 	if (mode != DRM_MODE_DPMS_ON)
 		mode = DRM_MODE_DPMS_OFF;
+
+	if (connector->dpms == mode)
+		goto out;
+
 	connector->dpms = mode;
 
 	crtc = connector->state->crtc;
diff --git a/drivers/gpu/drm/drm_buddy.c b/drivers/gpu/drm/drm_buddy.c
index 103c185bb1c8..16dea3f2fb11 100644
--- a/drivers/gpu/drm/drm_buddy.c
+++ b/drivers/gpu/drm/drm_buddy.c
@@ -324,7 +324,7 @@ EXPORT_SYMBOL(drm_buddy_init);
  */
 void drm_buddy_fini(struct drm_buddy *mm)
 {
-	u64 root_size, size;
+	u64 root_size, size, start;
 	unsigned int order;
 	int i;
 
@@ -332,7 +332,8 @@ void drm_buddy_fini(struct drm_buddy *mm)
 
 	for (i = 0; i < mm->n_roots; ++i) {
 		order = ilog2(size) - ilog2(mm->chunk_size);
-		__force_merge(mm, 0, size, order);
+		start = drm_buddy_block_offset(mm->roots[i]);
+		__force_merge(mm, start, start + size, order);
 
 		WARN_ON(!drm_buddy_block_is_free(mm->roots[i]));
 		drm_block_free(mm, mm->roots[i]);
@@ -400,6 +401,49 @@ drm_get_buddy(struct drm_buddy_block *block)
 EXPORT_SYMBOL(drm_get_buddy);
 
 /**
+ * drm_buddy_reset_clear - reset blocks clear state
+ *
+ * @mm: DRM buddy manager
+ * @is_clear: blocks clear state
+ *
+ * Reset the clear state based on @is_clear value for each block
+ * in the freelist.
+ */
+void drm_buddy_reset_clear(struct drm_buddy *mm, bool is_clear)
+{
+	u64 root_size, size, start;
+	unsigned int order;
+	int i;
+
+	size = mm->size;
+	for (i = 0; i < mm->n_roots; ++i) {
+		order = ilog2(size) - ilog2(mm->chunk_size);
+		start = drm_buddy_block_offset(mm->roots[i]);
+		__force_merge(mm, start, start + size, order);
+
+		root_size = mm->chunk_size << order;
+		size -= root_size;
+	}
+
+	for (i = 0; i <= mm->max_order; ++i) {
+		struct drm_buddy_block *block;
+
+		list_for_each_entry_reverse(block, &mm->free_list[i], link) {
+			if (is_clear != drm_buddy_block_is_clear(block)) {
+				if (is_clear) {
+					mark_cleared(block);
+					mm->clear_avail += drm_buddy_block_size(mm, block);
+				} else {
+					clear_reset(block);
+					mm->clear_avail -= drm_buddy_block_size(mm, block);
+				}
+			}
+		}
+	}
+}
+EXPORT_SYMBOL(drm_buddy_reset_clear);
+
+/**
  * drm_buddy_free_block - free a block
  *
  * @mm: DRM buddy manager
diff --git a/drivers/gpu/drm/drm_client_modeset.c b/drivers/gpu/drm/drm_client_modeset.c
index cee5eafbfb81..fd620f7db0dd 100644
--- a/drivers/gpu/drm/drm_client_modeset.c
+++ b/drivers/gpu/drm/drm_client_modeset.c
@@ -741,6 +741,15 @@ retry:
 	if ((conn_configured & mask) != mask && conn_configured != conn_seq)
 		goto retry;
 
+	for (i = 0; i < count; i++) {
+		struct drm_connector *connector = connectors[i];
+
+		if (connector->has_tile)
+			drm_client_get_tile_offsets(dev, connectors, connector_count,
+						    modes, offsets, i,
+						    connector->tile_h_loc, connector->tile_v_loc);
+	}
+
 	/*
 	 * If the BIOS didn't enable everything it could, fall back to have the
 	 * same user experiencing of lighting up as much as possible like the
diff --git a/drivers/gpu/drm/drm_client_setup.c b/drivers/gpu/drm/drm_client_setup.c
new file mode 100644
index 000000000000..5969c4ffe31b
--- /dev/null
+++ b/drivers/gpu/drm/drm_client_setup.c
@@ -0,0 +1,66 @@
+// SPDX-License-Identifier: MIT
+
+#include <drm/drm_client_setup.h>
+#include <drm/drm_device.h>
+#include <drm/drm_fbdev_client.h>
+#include <drm/drm_fourcc.h>
+#include <drm/drm_print.h>
+
+/**
+ * drm_client_setup() - Setup in-kernel DRM clients
+ * @dev: DRM device
+ * @format: Preferred pixel format for the device. Use NULL, unless
+ *          there is clearly a driver-preferred format.
+ *
+ * This function sets up the in-kernel DRM clients. Restore, hotplug
+ * events and teardown are all taken care of.
+ *
+ * Drivers should call drm_client_setup() after registering the new
+ * DRM device with drm_dev_register(). This function is safe to call
+ * even when there are no connectors present. Setup will be retried
+ * on the next hotplug event.
+ *
+ * The clients are destroyed by drm_dev_unregister().
+ */
+void drm_client_setup(struct drm_device *dev, const struct drm_format_info *format)
+{
+	int ret;
+
+	ret = drm_fbdev_client_setup(dev, format);
+	if (ret)
+		drm_warn(dev, "Failed to set up DRM client; error %d\n", ret);
+}
+EXPORT_SYMBOL(drm_client_setup);
+
+/**
+ * drm_client_setup_with_fourcc() - Setup in-kernel DRM clients for color mode
+ * @dev: DRM device
+ * @fourcc: Preferred pixel format as 4CC code for the device
+ *
+ * This function sets up the in-kernel DRM clients. It is equivalent
+ * to drm_client_setup(), but expects a 4CC code as second argument.
+ */
+void drm_client_setup_with_fourcc(struct drm_device *dev, u32 fourcc)
+{
+	drm_client_setup(dev, drm_format_info(fourcc));
+}
+EXPORT_SYMBOL(drm_client_setup_with_fourcc);
+
+/**
+ * drm_client_setup_with_color_mode() - Setup in-kernel DRM clients for color mode
+ * @dev: DRM device
+ * @color_mode: Preferred color mode for the device
+ *
+ * This function sets up the in-kernel DRM clients. It is equivalent
+ * to drm_client_setup(), but expects a color mode as second argument.
+ *
+ * Do not use this function in new drivers. Prefer drm_client_setup() with a
+ * format of NULL.
+ */
+void drm_client_setup_with_color_mode(struct drm_device *dev, unsigned int color_mode)
+{
+	u32 fourcc = drm_driver_color_mode_format(dev, color_mode);
+
+	drm_client_setup_with_fourcc(dev, fourcc);
+}
+EXPORT_SYMBOL(drm_client_setup_with_color_mode);
diff --git a/drivers/gpu/drm/drm_connector.c b/drivers/gpu/drm/drm_connector.c
index fc35f47e2849..994afa5a0ffb 100644
--- a/drivers/gpu/drm/drm_connector.c
+++ b/drivers/gpu/drm/drm_connector.c
@@ -277,6 +277,7 @@ static int __drm_connector_init(struct drm_device *dev,
 	INIT_LIST_HEAD(&connector->probed_modes);
 	INIT_LIST_HEAD(&connector->modes);
 	mutex_init(&connector->mutex);
+	mutex_init(&connector->eld_mutex);
 	mutex_init(&connector->edid_override_mutex);
 	mutex_init(&connector->hdmi.infoframes.lock);
 	connector->edid_blob_ptr = NULL;
@@ -507,6 +508,9 @@ int drmm_connector_hdmi_init(struct drm_device *dev,
 	if (!supported_formats || !(supported_formats & BIT(HDMI_COLORSPACE_RGB)))
 		return -EINVAL;
 
+	if (connector->ycbcr_420_allowed != !!(supported_formats & BIT(HDMI_COLORSPACE_YUV420)))
+		return -EINVAL;
+
 	if (!(max_bpc == 8 || max_bpc == 10 || max_bpc == 12))
 		return -EINVAL;
 
@@ -1304,6 +1308,10 @@ EXPORT_SYMBOL(drm_hdmi_connector_get_output_format_name);
  * 	callback. For atomic drivers the remapping to the "ACTIVE" property is
  * 	implemented in the DRM core.
  *
+ * 	On atomic drivers any DPMS setproperty ioctl where the value does not
+ * 	change is completely skipped, otherwise a full atomic commit will occur.
+ * 	On legacy drivers the exact behavior is driver specific.
+ *
  * 	Note that this property cannot be set through the MODE_ATOMIC ioctl,
  * 	userspace must use "ACTIVE" on the CRTC instead.
  *
diff --git a/drivers/gpu/drm/drm_debugfs.c b/drivers/gpu/drm/drm_debugfs.c
index 9d3e6dd68810..98a37dc3324e 100644
--- a/drivers/gpu/drm/drm_debugfs.c
+++ b/drivers/gpu/drm/drm_debugfs.c
@@ -743,7 +743,7 @@ static int bridges_show(struct seq_file *m, void *data)
 	unsigned int idx = 0;
 
 	drm_for_each_bridge_in_chain(encoder, bridge) {
-		drm_printf(&p, "bridge[%d]: %ps\n", idx++, bridge->funcs);
+		drm_printf(&p, "bridge[%u]: %ps\n", idx++, bridge->funcs);
 		drm_printf(&p, "\ttype: [%d] %s\n",
 			   bridge->type,
 			   drm_get_connector_type_name(bridge->type));
diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c
index 855beafb76ff..9edb3247c767 100644
--- a/drivers/gpu/drm/drm_edid.c
+++ b/drivers/gpu/drm/drm_edid.c
@@ -5605,7 +5605,9 @@ EXPORT_SYMBOL(drm_edid_get_monitor_name);
 
 static void clear_eld(struct drm_connector *connector)
 {
+	mutex_lock(&connector->eld_mutex);
 	memset(connector->eld, 0, sizeof(connector->eld));
+	mutex_unlock(&connector->eld_mutex);
 
 	connector->latency_present[0] = false;
 	connector->latency_present[1] = false;
@@ -5657,6 +5659,8 @@ static void drm_edid_to_eld(struct drm_connector *connector,
 	if (!drm_edid)
 		return;
 
+	mutex_lock(&connector->eld_mutex);
+
 	mnl = get_monitor_name(drm_edid, &eld[DRM_ELD_MONITOR_NAME_STRING]);
 	drm_dbg_kms(connector->dev, "[CONNECTOR:%d:%s] ELD monitor %s\n",
 		    connector->base.id, connector->name,
@@ -5717,6 +5721,8 @@ static void drm_edid_to_eld(struct drm_connector *connector,
 	drm_dbg_kms(connector->dev, "[CONNECTOR:%d:%s] ELD size %d, SAD count %d\n",
 		    connector->base.id, connector->name,
 		    drm_eld_size(eld), total_sad_count);
+
+	mutex_unlock(&connector->eld_mutex);
 }
 
 static int _drm_edid_to_sad(const struct drm_edid *drm_edid,
@@ -6590,6 +6596,7 @@ static void drm_reset_display_info(struct drm_connector *connector)
 	info->has_hdmi_infoframe = false;
 	info->rgb_quant_range_selectable = false;
 	memset(&info->hdmi, 0, sizeof(info->hdmi));
+	memset(&connector->hdr_sink_metadata, 0, sizeof(connector->hdr_sink_metadata));
 
 	info->edid_hdmi_rgb444_dc_modes = 0;
 	info->edid_hdmi_ycbcr444_dc_modes = 0;
diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
index 29c53f9f449c..b15ddbd65e7b 100644
--- a/drivers/gpu/drm/drm_fb_helper.c
+++ b/drivers/gpu/drm/drm_fb_helper.c
@@ -492,8 +492,8 @@ EXPORT_SYMBOL(drm_fb_helper_init);
  * @fb_helper: driver-allocated fbdev helper
  *
  * A helper to alloc fb_info and the member cmap. Called by the driver
- * within the fb_probe fb_helper callback function. Drivers do not
- * need to release the allocated fb_info structure themselves, this is
+ * within the struct &drm_driver.fbdev_probe callback function. Drivers do
+ * not need to release the allocated fb_info structure themselves, this is
  * automatically done when calling drm_fb_helper_fini().
  *
  * RETURNS:
@@ -1348,14 +1348,14 @@ int drm_fb_helper_set_par(struct fb_info *info)
 }
 EXPORT_SYMBOL(drm_fb_helper_set_par);
 
-static void pan_set(struct drm_fb_helper *fb_helper, int x, int y)
+static void pan_set(struct drm_fb_helper *fb_helper, int dx, int dy)
 {
 	struct drm_mode_set *mode_set;
 
 	mutex_lock(&fb_helper->client.modeset_mutex);
 	drm_client_for_each_modeset(mode_set, &fb_helper->client) {
-		mode_set->x = x;
-		mode_set->y = y;
+		mode_set->x += dx;
+		mode_set->y += dy;
 	}
 	mutex_unlock(&fb_helper->client.modeset_mutex);
 }
@@ -1364,16 +1364,18 @@ static int pan_display_atomic(struct fb_var_screeninfo *var,
 			      struct fb_info *info)
 {
 	struct drm_fb_helper *fb_helper = info->par;
-	int ret;
+	int ret, dx, dy;
 
-	pan_set(fb_helper, var->xoffset, var->yoffset);
+	dx = var->xoffset - info->var.xoffset;
+	dy = var->yoffset - info->var.yoffset;
+	pan_set(fb_helper, dx, dy);
 
 	ret = drm_client_modeset_commit_locked(&fb_helper->client);
 	if (!ret) {
 		info->var.xoffset = var->xoffset;
 		info->var.yoffset = var->yoffset;
 	} else
-		pan_set(fb_helper, info->var.xoffset, info->var.yoffset);
+		pan_set(fb_helper, -dx, -dy);
 
 	return ret;
 }
@@ -1441,67 +1443,27 @@ unlock:
 EXPORT_SYMBOL(drm_fb_helper_pan_display);
 
 static uint32_t drm_fb_helper_find_format(struct drm_fb_helper *fb_helper, const uint32_t *formats,
-					  size_t format_count, uint32_t bpp, uint32_t depth)
+					  size_t format_count, unsigned int color_mode)
 {
 	struct drm_device *dev = fb_helper->dev;
 	uint32_t format;
 	size_t i;
 
-	/*
-	 * Do not consider YUV or other complicated formats
-	 * for framebuffers. This means only legacy formats
-	 * are supported (fmt->depth is a legacy field), but
-	 * the framebuffer emulation can only deal with such
-	 * formats, specifically RGB/BGA formats.
-	 */
-	format = drm_mode_legacy_fb_format(bpp, depth);
-	if (!format)
-		goto err;
+	format = drm_driver_color_mode_format(dev, color_mode);
+	if (!format) {
+		drm_info(dev, "unsupported color mode of %d\n", color_mode);
+		return DRM_FORMAT_INVALID;
+	}
 
 	for (i = 0; i < format_count; ++i) {
 		if (formats[i] == format)
 			return format;
 	}
-
-err:
-	/* We found nothing. */
-	drm_warn(dev, "bpp/depth value of %u/%u not supported\n", bpp, depth);
+	drm_warn(dev, "format %p4cc not supported\n", &format);
 
 	return DRM_FORMAT_INVALID;
 }
 
-static uint32_t drm_fb_helper_find_color_mode_format(struct drm_fb_helper *fb_helper,
-						     const uint32_t *formats, size_t format_count,
-						     unsigned int color_mode)
-{
-	struct drm_device *dev = fb_helper->dev;
-	uint32_t bpp, depth;
-
-	switch (color_mode) {
-	case 1:
-	case 2:
-	case 4:
-	case 8:
-	case 16:
-	case 24:
-		bpp = depth = color_mode;
-		break;
-	case 15:
-		bpp = 16;
-		depth = 15;
-		break;
-	case 32:
-		bpp = 32;
-		depth = 24;
-		break;
-	default:
-		drm_info(dev, "unsupported color mode of %d\n", color_mode);
-		return DRM_FORMAT_INVALID;
-	}
-
-	return drm_fb_helper_find_format(fb_helper, formats, format_count, bpp, depth);
-}
-
 static int __drm_fb_helper_find_sizes(struct drm_fb_helper *fb_helper,
 				      struct drm_fb_helper_surface_size *sizes)
 {
@@ -1531,10 +1493,10 @@ static int __drm_fb_helper_find_sizes(struct drm_fb_helper *fb_helper,
 			if (!cmdline_mode->bpp_specified)
 				continue;
 
-			surface_format = drm_fb_helper_find_color_mode_format(fb_helper,
-									      plane->format_types,
-									      plane->format_count,
-									      cmdline_mode->bpp);
+			surface_format = drm_fb_helper_find_format(fb_helper,
+								   plane->format_types,
+								   plane->format_count,
+								   cmdline_mode->bpp);
 			if (surface_format != DRM_FORMAT_INVALID)
 				break; /* found supported format */
 		}
@@ -1544,10 +1506,10 @@ static int __drm_fb_helper_find_sizes(struct drm_fb_helper *fb_helper,
 			break; /* found supported format */
 
 		/* try preferred color mode */
-		surface_format = drm_fb_helper_find_color_mode_format(fb_helper,
-								      plane->format_types,
-								      plane->format_count,
-								      fb_helper->preferred_bpp);
+		surface_format = drm_fb_helper_find_format(fb_helper,
+							   plane->format_types,
+							   plane->format_count,
+							   fb_helper->preferred_bpp);
 		if (surface_format != DRM_FORMAT_INVALID)
 			break; /* found supported format */
 	}
@@ -1648,7 +1610,7 @@ static int drm_fb_helper_find_sizes(struct drm_fb_helper *fb_helper,
 
 /*
  * Allocates the backing storage and sets up the fbdev info structure through
- * the ->fb_probe callback.
+ * the ->fbdev_probe callback.
  */
 static int drm_fb_helper_single_fb_probe(struct drm_fb_helper *fb_helper)
 {
@@ -1666,7 +1628,10 @@ static int drm_fb_helper_single_fb_probe(struct drm_fb_helper *fb_helper)
 	}
 
 	/* push down into drivers */
-	ret = (*fb_helper->funcs->fb_probe)(fb_helper, &sizes);
+	if (dev->driver->fbdev_probe)
+		ret = dev->driver->fbdev_probe(fb_helper, &sizes);
+	else if (fb_helper->funcs)
+		ret = fb_helper->funcs->fb_probe(fb_helper, &sizes);
 	if (ret < 0)
 		return ret;
 
@@ -1738,7 +1703,7 @@ static void drm_fb_helper_fill_var(struct fb_info *info,
  * instance and the drm framebuffer allocated in &drm_fb_helper.fb.
  *
  * Drivers should call this (or their equivalent setup code) from their
- * &drm_fb_helper_funcs.fb_probe callback after having allocated the fbdev
+ * &drm_driver.fbdev_probe callback after having allocated the fbdev
  * backing storage framebuffer.
  */
 void drm_fb_helper_fill_info(struct fb_info *info,
@@ -1894,7 +1859,7 @@ __drm_fb_helper_initial_config_and_unlock(struct drm_fb_helper *fb_helper)
  * Note that this also registers the fbdev and so allows userspace to call into
  * the driver through the fbdev interfaces.
  *
- * This function will call down into the &drm_fb_helper_funcs.fb_probe callback
+ * This function will call down into the &drm_driver.fbdev_probe callback
  * to let the driver allocate and initialize the fbdev info structure and the
  * drm framebuffer used to back the fbdev. drm_fb_helper_fill_info() is provided
  * as a helper to setup simple default values for the fbdev info structure.
diff --git a/drivers/gpu/drm/drm_fbdev_client.c b/drivers/gpu/drm/drm_fbdev_client.c
new file mode 100644
index 000000000000..a09382afe2fb
--- /dev/null
+++ b/drivers/gpu/drm/drm_fbdev_client.c
@@ -0,0 +1,141 @@
+// SPDX-License-Identifier: MIT
+
+#include <drm/drm_client.h>
+#include <drm/drm_crtc_helper.h>
+#include <drm/drm_drv.h>
+#include <drm/drm_fbdev_client.h>
+#include <drm/drm_fb_helper.h>
+#include <drm/drm_fourcc.h>
+#include <drm/drm_print.h>
+
+/*
+ * struct drm_client_funcs
+ */
+
+static void drm_fbdev_client_unregister(struct drm_client_dev *client)
+{
+	struct drm_fb_helper *fb_helper = drm_fb_helper_from_client(client);
+
+	if (fb_helper->info) {
+		drm_fb_helper_unregister_info(fb_helper);
+	} else {
+		drm_client_release(&fb_helper->client);
+		drm_fb_helper_unprepare(fb_helper);
+		kfree(fb_helper);
+	}
+}
+
+static int drm_fbdev_client_restore(struct drm_client_dev *client)
+{
+	drm_fb_helper_lastclose(client->dev);
+
+	return 0;
+}
+
+static int drm_fbdev_client_hotplug(struct drm_client_dev *client)
+{
+	struct drm_fb_helper *fb_helper = drm_fb_helper_from_client(client);
+	struct drm_device *dev = client->dev;
+	int ret;
+
+	if (dev->fb_helper)
+		return drm_fb_helper_hotplug_event(dev->fb_helper);
+
+	ret = drm_fb_helper_init(dev, fb_helper);
+	if (ret)
+		goto err_drm_err;
+
+	if (!drm_drv_uses_atomic_modeset(dev))
+		drm_helper_disable_unused_functions(dev);
+
+	ret = drm_fb_helper_initial_config(fb_helper);
+	if (ret)
+		goto err_drm_fb_helper_fini;
+
+	return 0;
+
+err_drm_fb_helper_fini:
+	drm_fb_helper_fini(fb_helper);
+err_drm_err:
+	drm_err(dev, "fbdev: Failed to setup emulation (ret=%d)\n", ret);
+	return ret;
+}
+
+static const struct drm_client_funcs drm_fbdev_client_funcs = {
+	.owner		= THIS_MODULE,
+	.unregister	= drm_fbdev_client_unregister,
+	.restore	= drm_fbdev_client_restore,
+	.hotplug	= drm_fbdev_client_hotplug,
+};
+
+/**
+ * drm_fbdev_client_setup() - Setup fbdev emulation
+ * @dev: DRM device
+ * @format: Preferred color format for the device. DRM_FORMAT_XRGB8888
+ *          is used if this is zero.
+ *
+ * This function sets up fbdev emulation. Restore, hotplug events and
+ * teardown are all taken care of. Drivers that do suspend/resume need
+ * to call drm_fb_helper_set_suspend_unlocked() themselves. Simple
+ * drivers might use drm_mode_config_helper_suspend().
+ *
+ * This function is safe to call even when there are no connectors present.
+ * Setup will be retried on the next hotplug event.
+ *
+ * The fbdev client is destroyed by drm_dev_unregister().
+ *
+ * Returns:
+ * 0 on success, or a negative errno code otherwise.
+ */
+int drm_fbdev_client_setup(struct drm_device *dev, const struct drm_format_info *format)
+{
+	struct drm_fb_helper *fb_helper;
+	unsigned int color_mode;
+	int ret;
+
+	/* TODO: Use format info throughout DRM */
+	if (format) {
+		unsigned int bpp = drm_format_info_bpp(format, 0);
+
+		switch (bpp) {
+		case 16:
+			color_mode = format->depth; // could also be 15
+			break;
+		default:
+			color_mode = bpp;
+		}
+	} else {
+		switch (dev->mode_config.preferred_depth) {
+		case 0:
+		case 24:
+			color_mode = 32;
+			break;
+		default:
+			color_mode = dev->mode_config.preferred_depth;
+		}
+	}
+
+	drm_WARN(dev, !dev->registered, "Device has not been registered.\n");
+	drm_WARN(dev, dev->fb_helper, "fb_helper is already set!\n");
+
+	fb_helper = kzalloc(sizeof(*fb_helper), GFP_KERNEL);
+	if (!fb_helper)
+		return -ENOMEM;
+	drm_fb_helper_prepare(dev, fb_helper, color_mode, NULL);
+
+	ret = drm_client_init(dev, &fb_helper->client, "fbdev", &drm_fbdev_client_funcs);
+	if (ret) {
+		drm_err(dev, "Failed to register client: %d\n", ret);
+		goto err_drm_client_init;
+	}
+
+	drm_client_register(&fb_helper->client);
+
+	return 0;
+
+err_drm_client_init:
+	drm_fb_helper_unprepare(fb_helper);
+	kfree(fb_helper);
+	return ret;
+}
+EXPORT_SYMBOL(drm_fbdev_client_setup);
diff --git a/drivers/gpu/drm/drm_fbdev_dma.c b/drivers/gpu/drm/drm_fbdev_dma.c
index 51c2d742d199..6fcf2a8bf676 100644
--- a/drivers/gpu/drm/drm_fbdev_dma.c
+++ b/drivers/gpu/drm/drm_fbdev_dma.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: MIT
 
 #include <linux/fb.h>
+#include <linux/vmalloc.h>
 
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_drv.h>
@@ -72,45 +73,214 @@ static const struct fb_ops drm_fbdev_dma_fb_ops = {
 	.fb_destroy = drm_fbdev_dma_fb_destroy,
 };
 
-FB_GEN_DEFAULT_DEFERRED_DMAMEM_OPS(drm_fbdev_dma,
+FB_GEN_DEFAULT_DEFERRED_DMAMEM_OPS(drm_fbdev_dma_shadowed,
 				   drm_fb_helper_damage_range,
 				   drm_fb_helper_damage_area);
 
-static int drm_fbdev_dma_deferred_fb_mmap(struct fb_info *info, struct vm_area_struct *vma)
+static void drm_fbdev_dma_shadowed_fb_destroy(struct fb_info *info)
 {
 	struct drm_fb_helper *fb_helper = info->par;
-	struct drm_framebuffer *fb = fb_helper->fb;
-	struct drm_gem_dma_object *dma = drm_fb_dma_get_gem_obj(fb, 0);
+	void *shadow = info->screen_buffer;
 
-	if (!dma->map_noncoherent)
-		vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
+	if (!fb_helper->dev)
+		return;
+
+	if (info->fbdefio)
+		fb_deferred_io_cleanup(info);
+	drm_fb_helper_fini(fb_helper);
+	vfree(shadow);
 
-	return fb_deferred_io_mmap(info, vma);
+	drm_client_buffer_vunmap(fb_helper->buffer);
+	drm_client_framebuffer_delete(fb_helper->buffer);
+	drm_client_release(&fb_helper->client);
+	drm_fb_helper_unprepare(fb_helper);
+	kfree(fb_helper);
 }
 
-static const struct fb_ops drm_fbdev_dma_deferred_fb_ops = {
+static const struct fb_ops drm_fbdev_dma_shadowed_fb_ops = {
 	.owner = THIS_MODULE,
 	.fb_open = drm_fbdev_dma_fb_open,
 	.fb_release = drm_fbdev_dma_fb_release,
-	__FB_DEFAULT_DEFERRED_OPS_RDWR(drm_fbdev_dma),
+	FB_DEFAULT_DEFERRED_OPS(drm_fbdev_dma_shadowed),
 	DRM_FB_HELPER_DEFAULT_OPS,
-	__FB_DEFAULT_DEFERRED_OPS_DRAW(drm_fbdev_dma),
-	.fb_mmap = drm_fbdev_dma_deferred_fb_mmap,
-	.fb_destroy = drm_fbdev_dma_fb_destroy,
+	.fb_destroy = drm_fbdev_dma_shadowed_fb_destroy,
 };
 
 /*
  * struct drm_fb_helper
  */
 
+static void drm_fbdev_dma_damage_blit_real(struct drm_fb_helper *fb_helper,
+					   struct drm_clip_rect *clip,
+					   struct iosys_map *dst)
+{
+	struct drm_framebuffer *fb = fb_helper->fb;
+	size_t offset = clip->y1 * fb->pitches[0];
+	size_t len = clip->x2 - clip->x1;
+	unsigned int y;
+	void *src;
+
+	switch (drm_format_info_bpp(fb->format, 0)) {
+	case 1:
+		offset += clip->x1 / 8;
+		len = DIV_ROUND_UP(len + clip->x1 % 8, 8);
+		break;
+	case 2:
+		offset += clip->x1 / 4;
+		len = DIV_ROUND_UP(len + clip->x1 % 4, 4);
+		break;
+	case 4:
+		offset += clip->x1 / 2;
+		len = DIV_ROUND_UP(len + clip->x1 % 2, 2);
+		break;
+	default:
+		offset += clip->x1 * fb->format->cpp[0];
+		len *= fb->format->cpp[0];
+		break;
+	}
+
+	src = fb_helper->info->screen_buffer + offset;
+	iosys_map_incr(dst, offset); /* go to first pixel within clip rect */
+
+	for (y = clip->y1; y < clip->y2; y++) {
+		iosys_map_memcpy_to(dst, 0, src, len);
+		iosys_map_incr(dst, fb->pitches[0]);
+		src += fb->pitches[0];
+	}
+}
+
+static int drm_fbdev_dma_damage_blit(struct drm_fb_helper *fb_helper,
+				     struct drm_clip_rect *clip)
+{
+	struct drm_client_buffer *buffer = fb_helper->buffer;
+	struct iosys_map dst;
+
+	/*
+	 * For fbdev emulation, we only have to protect against fbdev modeset
+	 * operations. Nothing else will involve the client buffer's BO. So it
+	 * is sufficient to acquire struct drm_fb_helper.lock here.
+	 */
+	mutex_lock(&fb_helper->lock);
+
+	dst = buffer->map;
+	drm_fbdev_dma_damage_blit_real(fb_helper, clip, &dst);
+
+	mutex_unlock(&fb_helper->lock);
+
+	return 0;
+}
+
 static int drm_fbdev_dma_helper_fb_probe(struct drm_fb_helper *fb_helper,
 					 struct drm_fb_helper_surface_size *sizes)
 {
+	return drm_fbdev_dma_driver_fbdev_probe(fb_helper, sizes);
+}
+static int drm_fbdev_dma_helper_fb_dirty(struct drm_fb_helper *helper,
+					 struct drm_clip_rect *clip)
+{
+	struct drm_device *dev = helper->dev;
+	int ret;
+
+	/* Call damage handlers only if necessary */
+	if (!(clip->x1 < clip->x2 && clip->y1 < clip->y2))
+		return 0;
+
+	if (helper->fb->funcs->dirty) {
+		ret = drm_fbdev_dma_damage_blit(helper, clip);
+		if (drm_WARN_ONCE(dev, ret, "Damage blitter failed: ret=%d\n", ret))
+			return ret;
+
+		ret = helper->fb->funcs->dirty(helper->fb, NULL, 0, 0, clip, 1);
+		if (drm_WARN_ONCE(dev, ret, "Dirty helper failed: ret=%d\n", ret))
+			return ret;
+	}
+
+	return 0;
+}
+
+static const struct drm_fb_helper_funcs drm_fbdev_dma_helper_funcs = {
+	.fb_probe = drm_fbdev_dma_helper_fb_probe,
+	.fb_dirty = drm_fbdev_dma_helper_fb_dirty,
+};
+
+/*
+ * struct drm_fb_helper
+ */
+
+static int drm_fbdev_dma_driver_fbdev_probe_tail(struct drm_fb_helper *fb_helper,
+						 struct drm_fb_helper_surface_size *sizes)
+{
+	struct drm_device *dev = fb_helper->dev;
+	struct drm_client_buffer *buffer = fb_helper->buffer;
+	struct drm_gem_dma_object *dma_obj = to_drm_gem_dma_obj(buffer->gem);
+	struct drm_framebuffer *fb = fb_helper->fb;
+	struct fb_info *info = fb_helper->info;
+	struct iosys_map map = buffer->map;
+
+	info->fbops = &drm_fbdev_dma_fb_ops;
+
+	/* screen */
+	info->flags |= FBINFO_VIRTFB; /* system memory */
+	if (dma_obj->map_noncoherent)
+		info->flags |= FBINFO_READS_FAST; /* signal caching */
+	info->screen_size = sizes->surface_height * fb->pitches[0];
+	info->screen_buffer = map.vaddr;
+	if (!(info->flags & FBINFO_HIDE_SMEM_START)) {
+		if (!drm_WARN_ON(dev, is_vmalloc_addr(info->screen_buffer)))
+			info->fix.smem_start = page_to_phys(virt_to_page(info->screen_buffer));
+	}
+	info->fix.smem_len = info->screen_size;
+
+	return 0;
+}
+
+static int drm_fbdev_dma_driver_fbdev_probe_tail_shadowed(struct drm_fb_helper *fb_helper,
+							  struct drm_fb_helper_surface_size *sizes)
+{
+	struct drm_client_buffer *buffer = fb_helper->buffer;
+	struct fb_info *info = fb_helper->info;
+	size_t screen_size = buffer->gem->size;
+	void *screen_buffer;
+	int ret;
+
+	/*
+	 * Deferred I/O requires struct page for framebuffer memory,
+	 * which is not guaranteed for all DMA ranges. We thus create
+	 * a shadow buffer in system memory.
+	 */
+	screen_buffer = vzalloc(screen_size);
+	if (!screen_buffer)
+		return -ENOMEM;
+
+	info->fbops = &drm_fbdev_dma_shadowed_fb_ops;
+
+	/* screen */
+	info->flags |= FBINFO_VIRTFB; /* system memory */
+	info->flags |= FBINFO_READS_FAST; /* signal caching */
+	info->screen_buffer = screen_buffer;
+	info->fix.smem_len = screen_size;
+
+	fb_helper->fbdefio.delay = HZ / 20;
+	fb_helper->fbdefio.deferred_io = drm_fb_helper_deferred_io;
+
+	info->fbdefio = &fb_helper->fbdefio;
+	ret = fb_deferred_io_init(info);
+	if (ret)
+		goto err_vfree;
+
+	return 0;
+
+err_vfree:
+	vfree(screen_buffer);
+	return ret;
+}
+
+int drm_fbdev_dma_driver_fbdev_probe(struct drm_fb_helper *fb_helper,
+				     struct drm_fb_helper_surface_size *sizes)
+{
 	struct drm_client_dev *client = &fb_helper->client;
 	struct drm_device *dev = fb_helper->dev;
-	bool use_deferred_io = false;
 	struct drm_client_buffer *buffer;
-	struct drm_gem_dma_object *dma_obj;
 	struct drm_framebuffer *fb;
 	struct fb_info *info;
 	u32 format;
@@ -127,19 +297,9 @@ static int drm_fbdev_dma_helper_fb_probe(struct drm_fb_helper *fb_helper,
 					       sizes->surface_height, format);
 	if (IS_ERR(buffer))
 		return PTR_ERR(buffer);
-	dma_obj = to_drm_gem_dma_obj(buffer->gem);
 
 	fb = buffer->fb;
 
-	/*
-	 * Deferred I/O requires struct page for framebuffer memory,
-	 * which is not guaranteed for all DMA ranges. We thus only
-	 * install deferred I/O if we have a framebuffer that requires
-	 * it.
-	 */
-	if (fb->funcs->dirty)
-		use_deferred_io = true;
-
 	ret = drm_client_buffer_vmap(buffer, &map);
 	if (ret) {
 		goto err_drm_client_buffer_delete;
@@ -148,6 +308,7 @@ static int drm_fbdev_dma_helper_fb_probe(struct drm_fb_helper *fb_helper,
 		goto err_drm_client_buffer_delete;
 	}
 
+	fb_helper->funcs = &drm_fbdev_dma_helper_funcs;
 	fb_helper->buffer = buffer;
 	fb_helper->fb = fb;
 
@@ -159,45 +320,12 @@ static int drm_fbdev_dma_helper_fb_probe(struct drm_fb_helper *fb_helper,
 
 	drm_fb_helper_fill_info(info, fb_helper, sizes);
 
-	if (use_deferred_io)
-		info->fbops = &drm_fbdev_dma_deferred_fb_ops;
+	if (fb->funcs->dirty)
+		ret = drm_fbdev_dma_driver_fbdev_probe_tail_shadowed(fb_helper, sizes);
 	else
-		info->fbops = &drm_fbdev_dma_fb_ops;
-
-	/* screen */
-	info->flags |= FBINFO_VIRTFB; /* system memory */
-	if (dma_obj->map_noncoherent)
-		info->flags |= FBINFO_READS_FAST; /* signal caching */
-	info->screen_size = sizes->surface_height * fb->pitches[0];
-	info->screen_buffer = map.vaddr;
-	if (!(info->flags & FBINFO_HIDE_SMEM_START)) {
-		if (!drm_WARN_ON(dev, is_vmalloc_addr(info->screen_buffer)))
-			info->fix.smem_start = page_to_phys(virt_to_page(info->screen_buffer));
-	}
-	info->fix.smem_len = info->screen_size;
-
-	/*
-	 * Only set up deferred I/O if the screen buffer supports
-	 * it. If this disagrees with the previous test for ->dirty,
-	 * mmap on the /dev/fb file might not work correctly.
-	 */
-	if (!is_vmalloc_addr(info->screen_buffer) && info->fix.smem_start) {
-		unsigned long pfn = info->fix.smem_start >> PAGE_SHIFT;
-
-		if (drm_WARN_ON(dev, !pfn_to_page(pfn)))
-			use_deferred_io = false;
-	}
-
-	/* deferred I/O */
-	if (use_deferred_io) {
-		fb_helper->fbdefio.delay = HZ / 20;
-		fb_helper->fbdefio.deferred_io = drm_fb_helper_deferred_io;
-
-		info->fbdefio = &fb_helper->fbdefio;
-		ret = fb_deferred_io_init(info);
-		if (ret)
-			goto err_drm_fb_helper_release_info;
-	}
+		ret = drm_fbdev_dma_driver_fbdev_probe_tail(fb_helper, sizes);
+	if (ret)
+		goto err_drm_fb_helper_release_info;
 
 	return 0;
 
@@ -211,30 +339,7 @@ err_drm_client_buffer_delete:
 	drm_client_framebuffer_delete(buffer);
 	return ret;
 }
-
-static int drm_fbdev_dma_helper_fb_dirty(struct drm_fb_helper *helper,
-					 struct drm_clip_rect *clip)
-{
-	struct drm_device *dev = helper->dev;
-	int ret;
-
-	/* Call damage handlers only if necessary */
-	if (!(clip->x1 < clip->x2 && clip->y1 < clip->y2))
-		return 0;
-
-	if (helper->fb->funcs->dirty) {
-		ret = helper->fb->funcs->dirty(helper->fb, NULL, 0, 0, clip, 1);
-		if (drm_WARN_ONCE(dev, ret, "Dirty helper failed: ret=%d\n", ret))
-			return ret;
-	}
-
-	return 0;
-}
-
-static const struct drm_fb_helper_funcs drm_fbdev_dma_helper_funcs = {
-	.fb_probe = drm_fbdev_dma_helper_fb_probe,
-	.fb_dirty = drm_fbdev_dma_helper_fb_dirty,
-};
+EXPORT_SYMBOL(drm_fbdev_dma_driver_fbdev_probe);
 
 /*
  * struct drm_client_funcs
diff --git a/drivers/gpu/drm/drm_fbdev_ttm.c b/drivers/gpu/drm/drm_fbdev_ttm.c
index 119ffb28aaf9..d799cbe944cd 100644
--- a/drivers/gpu/drm/drm_fbdev_ttm.c
+++ b/drivers/gpu/drm/drm_fbdev_ttm.c
@@ -71,71 +71,7 @@ static const struct fb_ops drm_fbdev_ttm_fb_ops = {
 static int drm_fbdev_ttm_helper_fb_probe(struct drm_fb_helper *fb_helper,
 					     struct drm_fb_helper_surface_size *sizes)
 {
-	struct drm_client_dev *client = &fb_helper->client;
-	struct drm_device *dev = fb_helper->dev;
-	struct drm_client_buffer *buffer;
-	struct fb_info *info;
-	size_t screen_size;
-	void *screen_buffer;
-	u32 format;
-	int ret;
-
-	drm_dbg_kms(dev, "surface width(%d), height(%d) and bpp(%d)\n",
-		    sizes->surface_width, sizes->surface_height,
-		    sizes->surface_bpp);
-
-	format = drm_driver_legacy_fb_format(dev, sizes->surface_bpp,
-					     sizes->surface_depth);
-	buffer = drm_client_framebuffer_create(client, sizes->surface_width,
-					       sizes->surface_height, format);
-	if (IS_ERR(buffer))
-		return PTR_ERR(buffer);
-
-	fb_helper->buffer = buffer;
-	fb_helper->fb = buffer->fb;
-
-	screen_size = buffer->gem->size;
-	screen_buffer = vzalloc(screen_size);
-	if (!screen_buffer) {
-		ret = -ENOMEM;
-		goto err_drm_client_framebuffer_delete;
-	}
-
-	info = drm_fb_helper_alloc_info(fb_helper);
-	if (IS_ERR(info)) {
-		ret = PTR_ERR(info);
-		goto err_vfree;
-	}
-
-	drm_fb_helper_fill_info(info, fb_helper, sizes);
-
-	info->fbops = &drm_fbdev_ttm_fb_ops;
-
-	/* screen */
-	info->flags |= FBINFO_VIRTFB | FBINFO_READS_FAST;
-	info->screen_buffer = screen_buffer;
-	info->fix.smem_len = screen_size;
-
-	/* deferred I/O */
-	fb_helper->fbdefio.delay = HZ / 20;
-	fb_helper->fbdefio.deferred_io = drm_fb_helper_deferred_io;
-
-	info->fbdefio = &fb_helper->fbdefio;
-	ret = fb_deferred_io_init(info);
-	if (ret)
-		goto err_drm_fb_helper_release_info;
-
-	return 0;
-
-err_drm_fb_helper_release_info:
-	drm_fb_helper_release_info(fb_helper);
-err_vfree:
-	vfree(screen_buffer);
-err_drm_client_framebuffer_delete:
-	fb_helper->fb = NULL;
-	fb_helper->buffer = NULL;
-	drm_client_framebuffer_delete(buffer);
-	return ret;
+	return drm_fbdev_ttm_driver_fbdev_probe(fb_helper, sizes);
 }
 
 static void drm_fbdev_ttm_damage_blit_real(struct drm_fb_helper *fb_helper,
@@ -240,6 +176,82 @@ static const struct drm_fb_helper_funcs drm_fbdev_ttm_helper_funcs = {
 	.fb_dirty = drm_fbdev_ttm_helper_fb_dirty,
 };
 
+/*
+ * struct drm_driver
+ */
+
+int drm_fbdev_ttm_driver_fbdev_probe(struct drm_fb_helper *fb_helper,
+				     struct drm_fb_helper_surface_size *sizes)
+{
+	struct drm_client_dev *client = &fb_helper->client;
+	struct drm_device *dev = fb_helper->dev;
+	struct drm_client_buffer *buffer;
+	struct fb_info *info;
+	size_t screen_size;
+	void *screen_buffer;
+	u32 format;
+	int ret;
+
+	drm_dbg_kms(dev, "surface width(%d), height(%d) and bpp(%d)\n",
+		    sizes->surface_width, sizes->surface_height,
+		    sizes->surface_bpp);
+
+	format = drm_driver_legacy_fb_format(dev, sizes->surface_bpp,
+					     sizes->surface_depth);
+	buffer = drm_client_framebuffer_create(client, sizes->surface_width,
+					       sizes->surface_height, format);
+	if (IS_ERR(buffer))
+		return PTR_ERR(buffer);
+
+	fb_helper->funcs = &drm_fbdev_ttm_helper_funcs;
+	fb_helper->buffer = buffer;
+	fb_helper->fb = buffer->fb;
+
+	screen_size = buffer->gem->size;
+	screen_buffer = vzalloc(screen_size);
+	if (!screen_buffer) {
+		ret = -ENOMEM;
+		goto err_drm_client_framebuffer_delete;
+	}
+
+	info = drm_fb_helper_alloc_info(fb_helper);
+	if (IS_ERR(info)) {
+		ret = PTR_ERR(info);
+		goto err_vfree;
+	}
+
+	drm_fb_helper_fill_info(info, fb_helper, sizes);
+
+	info->fbops = &drm_fbdev_ttm_fb_ops;
+
+	/* screen */
+	info->flags |= FBINFO_VIRTFB | FBINFO_READS_FAST;
+	info->screen_buffer = screen_buffer;
+	info->fix.smem_len = screen_size;
+
+	/* deferred I/O */
+	fb_helper->fbdefio.delay = HZ / 20;
+	fb_helper->fbdefio.deferred_io = drm_fb_helper_deferred_io;
+
+	info->fbdefio = &fb_helper->fbdefio;
+	ret = fb_deferred_io_init(info);
+	if (ret)
+		goto err_drm_fb_helper_release_info;
+
+	return 0;
+
+err_drm_fb_helper_release_info:
+	drm_fb_helper_release_info(fb_helper);
+err_vfree:
+	vfree(screen_buffer);
+err_drm_client_framebuffer_delete:
+	fb_helper->fb = NULL;
+	fb_helper->buffer = NULL;
+	drm_client_framebuffer_delete(buffer);
+	return ret;
+}
+EXPORT_SYMBOL(drm_fbdev_ttm_driver_fbdev_probe);
+
 static void drm_fbdev_ttm_client_unregister(struct drm_client_dev *client)
 {
 	struct drm_fb_helper *fb_helper = drm_fb_helper_from_client(client);
diff --git a/drivers/gpu/drm/drm_file.c b/drivers/gpu/drm/drm_file.c
index ce82c9451dfe..e2cf118ff01d 100644
--- a/drivers/gpu/drm/drm_file.c
+++ b/drivers/gpu/drm/drm_file.c
@@ -938,6 +938,10 @@ void drm_show_fdinfo(struct seq_file *m, struct file *f)
 	struct drm_file *file = f->private_data;
 	struct drm_device *dev = file->minor->dev;
 	struct drm_printer p = drm_seq_file_printer(m);
+	int idx;
+
+	if (!drm_dev_enter(dev, &idx))
+		return;
 
 	drm_printf(&p, "drm-driver:\t%s\n", dev->driver->name);
 	drm_printf(&p, "drm-client-id:\t%llu\n", file->client_id);
@@ -952,6 +956,8 @@ void drm_show_fdinfo(struct seq_file *m, struct file *f)
 
 	if (dev->driver->show_fdinfo)
 		dev->driver->show_fdinfo(&p, file);
+
+	drm_dev_exit(idx);
 }
 EXPORT_SYMBOL(drm_show_fdinfo);
 
diff --git a/drivers/gpu/drm/drm_fourcc.c b/drivers/gpu/drm/drm_fourcc.c
index 193cf8ed7912..3a94ca211f9c 100644
--- a/drivers/gpu/drm/drm_fourcc.c
+++ b/drivers/gpu/drm/drm_fourcc.c
@@ -36,7 +36,6 @@
  * @depth: bit depth per pixel
  *
  * Computes a drm fourcc pixel format code for the given @bpp/@depth values.
- * Useful in fbdev emulation code, since that deals in those values.
  */
 uint32_t drm_mode_legacy_fb_format(uint32_t bpp, uint32_t depth)
 {
@@ -140,6 +139,35 @@ uint32_t drm_driver_legacy_fb_format(struct drm_device *dev,
 }
 EXPORT_SYMBOL(drm_driver_legacy_fb_format);
 
+/**
+ * drm_driver_color_mode_format - Compute DRM 4CC code from color mode
+ * @dev: DRM device
+ * @color_mode: command-line color mode
+ *
+ * Computes a DRM 4CC pixel format code for the given color mode using
+ * drm_driver_color_mode(). The color mode is in the format used and the
+ * kernel command line. It specifies the number of bits per pixel
+ * and color depth in a single value.
+ *
+ * Useful in fbdev emulation code, since that deals in those values. The
+ * helper does not consider YUV or other complicated formats. This means
+ * only legacy formats are supported (fmt->depth is a legacy field), but
+ * the framebuffer emulation can only deal with such formats, specifically
+ * RGB/BGA formats.
+ */
+uint32_t drm_driver_color_mode_format(struct drm_device *dev, unsigned int color_mode)
+{
+	switch (color_mode) {
+	case 15:
+		return drm_driver_legacy_fb_format(dev, 16, 15);
+	case 32:
+		return drm_driver_legacy_fb_format(dev, 32, 24);
+	default:
+		return drm_driver_legacy_fb_format(dev, color_mode, color_mode);
+	}
+}
+EXPORT_SYMBOL(drm_driver_color_mode_format);
+
 /*
  * Internal function to query information for a given format. See
  * drm_format_info() for the public API.
diff --git a/drivers/gpu/drm/drm_framebuffer.c b/drivers/gpu/drm/drm_framebuffer.c
index 888aadb6a4ac..d6550b54fac1 100644
--- a/drivers/gpu/drm/drm_framebuffer.c
+++ b/drivers/gpu/drm/drm_framebuffer.c
@@ -860,11 +860,23 @@ void drm_framebuffer_free(struct kref *kref)
 int drm_framebuffer_init(struct drm_device *dev, struct drm_framebuffer *fb,
 			 const struct drm_framebuffer_funcs *funcs)
 {
+	unsigned int i;
 	int ret;
+	bool exists;
 
 	if (WARN_ON_ONCE(fb->dev != dev || !fb->format))
 		return -EINVAL;
 
+	for (i = 0; i < fb->format->num_planes; i++) {
+		if (drm_WARN_ON_ONCE(dev, fb->internal_flags & DRM_FRAMEBUFFER_HAS_HANDLE_REF(i)))
+			fb->internal_flags &= ~DRM_FRAMEBUFFER_HAS_HANDLE_REF(i);
+		if (fb->obj[i]) {
+			exists = drm_gem_object_handle_get_if_exists_unlocked(fb->obj[i]);
+			if (exists)
+				fb->internal_flags |= DRM_FRAMEBUFFER_HAS_HANDLE_REF(i);
+		}
+	}
+
 	INIT_LIST_HEAD(&fb->filp_head);
 
 	fb->funcs = funcs;
@@ -873,7 +885,7 @@ int drm_framebuffer_init(struct drm_device *dev, struct drm_framebuffer *fb,
 	ret = __drm_mode_object_add(dev, &fb->base, DRM_MODE_OBJECT_FB,
 				    false, drm_framebuffer_free);
 	if (ret)
-		goto out;
+		goto err;
 
 	mutex_lock(&dev->mode_config.fb_lock);
 	dev->mode_config.num_fb++;
@@ -881,7 +893,16 @@ int drm_framebuffer_init(struct drm_device *dev, struct drm_framebuffer *fb,
 	mutex_unlock(&dev->mode_config.fb_lock);
 
 	drm_mode_object_register(dev, &fb->base);
-out:
+
+	return 0;
+
+err:
+	for (i = 0; i < fb->format->num_planes; i++) {
+		if (fb->internal_flags & DRM_FRAMEBUFFER_HAS_HANDLE_REF(i)) {
+			drm_gem_object_handle_put_unlocked(fb->obj[i]);
+			fb->internal_flags &= ~DRM_FRAMEBUFFER_HAS_HANDLE_REF(i);
+		}
+	}
 	return ret;
 }
 EXPORT_SYMBOL(drm_framebuffer_init);
@@ -958,6 +979,12 @@ EXPORT_SYMBOL(drm_framebuffer_unregister_private);
 void drm_framebuffer_cleanup(struct drm_framebuffer *fb)
 {
 	struct drm_device *dev = fb->dev;
+	unsigned int i;
+
+	for (i = 0; i < fb->format->num_planes; i++) {
+		if (fb->internal_flags & DRM_FRAMEBUFFER_HAS_HANDLE_REF(i))
+			drm_gem_object_handle_put_unlocked(fb->obj[i]);
+	}
 
 	mutex_lock(&dev->mode_config.fb_lock);
 	list_del(&fb->head);
diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c
index 149b8e25da5b..9e8a4da313a0 100644
--- a/drivers/gpu/drm/drm_gem.c
+++ b/drivers/gpu/drm/drm_gem.c
@@ -186,6 +186,46 @@ void drm_gem_private_object_fini(struct drm_gem_object *obj)
 }
 EXPORT_SYMBOL(drm_gem_private_object_fini);
 
+static void drm_gem_object_handle_get(struct drm_gem_object *obj)
+{
+	struct drm_device *dev = obj->dev;
+
+	drm_WARN_ON(dev, !mutex_is_locked(&dev->object_name_lock));
+
+	if (obj->handle_count++ == 0)
+		drm_gem_object_get(obj);
+}
+
+/**
+ * drm_gem_object_handle_get_if_exists_unlocked - acquire reference on user-space handle, if any
+ * @obj: GEM object
+ *
+ * Acquires a reference on the GEM buffer object's handle. Required to keep
+ * the GEM object alive. Call drm_gem_object_handle_put_if_exists_unlocked()
+ * to release the reference. Does nothing if the buffer object has no handle.
+ *
+ * Returns:
+ * True if a handle exists, or false otherwise
+ */
+bool drm_gem_object_handle_get_if_exists_unlocked(struct drm_gem_object *obj)
+{
+	struct drm_device *dev = obj->dev;
+
+	guard(mutex)(&dev->object_name_lock);
+
+	/*
+	 * First ref taken during GEM object creation, if any. Some
+	 * drivers set up internal framebuffers with GEM objects that
+	 * do not have a GEM handle. Hence, this counter can be zero.
+	 */
+	if (!obj->handle_count)
+		return false;
+
+	drm_gem_object_handle_get(obj);
+
+	return true;
+}
+
 /**
  * drm_gem_object_handle_free - release resources bound to userspace handles
  * @obj: GEM object to clean up.
@@ -216,20 +256,26 @@ static void drm_gem_object_exported_dma_buf_free(struct drm_gem_object *obj)
 	}
 }
 
-static void
-drm_gem_object_handle_put_unlocked(struct drm_gem_object *obj)
+/**
+ * drm_gem_object_handle_put_unlocked - releases reference on user-space handle
+ * @obj: GEM object
+ *
+ * Releases a reference on the GEM buffer object's handle. Possibly releases
+ * the GEM buffer object and associated dma-buf objects.
+ */
+void drm_gem_object_handle_put_unlocked(struct drm_gem_object *obj)
 {
 	struct drm_device *dev = obj->dev;
 	bool final = false;
 
-	if (WARN_ON(READ_ONCE(obj->handle_count) == 0))
+	if (drm_WARN_ON(dev, READ_ONCE(obj->handle_count) == 0))
 		return;
 
 	/*
-	* Must bump handle count first as this may be the last
-	* ref, in which case the object would disappear before we
-	* checked for a name
-	*/
+	 * Must bump handle count first as this may be the last
+	 * ref, in which case the object would disappear before
+	 * we checked for a name.
+	 */
 
 	mutex_lock(&dev->object_name_lock);
 	if (--obj->handle_count == 0) {
@@ -253,6 +299,9 @@ drm_gem_object_release_handle(int id, void *ptr, void *data)
 	struct drm_file *file_priv = data;
 	struct drm_gem_object *obj = ptr;
 
+	if (drm_WARN_ON(obj->dev, !data))
+		return 0;
+
 	if (obj->funcs->close)
 		obj->funcs->close(obj, file_priv);
 
@@ -322,7 +371,7 @@ int drm_gem_dumb_map_offset(struct drm_file *file, struct drm_device *dev,
 		return -ENOENT;
 
 	/* Don't allow imported objects to be mapped */
-	if (obj->import_attach) {
+	if (drm_gem_is_imported(obj)) {
 		ret = -EINVAL;
 		goto out;
 	}
@@ -363,8 +412,8 @@ drm_gem_handle_create_tail(struct drm_file *file_priv,
 	int ret;
 
 	WARN_ON(!mutex_is_locked(&dev->object_name_lock));
-	if (obj->handle_count++ == 0)
-		drm_gem_object_get(obj);
+
+	drm_gem_object_handle_get(obj);
 
 	/*
 	 * Get the user-visible handle using idr.  Preload and perform
@@ -373,7 +422,7 @@ drm_gem_handle_create_tail(struct drm_file *file_priv,
 	idr_preload(GFP_KERNEL);
 	spin_lock(&file_priv->table_lock);
 
-	ret = idr_alloc(&file_priv->object_idr, obj, 1, 0, GFP_NOWAIT);
+	ret = idr_alloc(&file_priv->object_idr, NULL, 1, 0, GFP_NOWAIT);
 
 	spin_unlock(&file_priv->table_lock);
 	idr_preload_end();
@@ -394,6 +443,11 @@ drm_gem_handle_create_tail(struct drm_file *file_priv,
 			goto err_revoke;
 	}
 
+	/* mirrors drm_gem_handle_delete to avoid races */
+	spin_lock(&file_priv->table_lock);
+	obj = idr_replace(&file_priv->object_idr, obj, handle);
+	WARN_ON(obj != NULL);
+	spin_unlock(&file_priv->table_lock);
 	*handlep = handle;
 	return 0;
 
@@ -1152,7 +1206,7 @@ void drm_gem_print_info(struct drm_printer *p, unsigned int indent,
 			  drm_vma_node_start(&obj->vma_node));
 	drm_printf_indent(p, indent, "size=%zu\n", obj->size);
 	drm_printf_indent(p, indent, "imported=%s\n",
-			  str_yes_no(obj->import_attach));
+			  str_yes_no(drm_gem_is_imported(obj)));
 
 	if (obj->funcs->print_info)
 		obj->funcs->print_info(p, indent, obj);
diff --git a/drivers/gpu/drm/drm_internal.h b/drivers/gpu/drm/drm_internal.h
index 1705bfc90b1e..98b73c581c42 100644
--- a/drivers/gpu/drm/drm_internal.h
+++ b/drivers/gpu/drm/drm_internal.h
@@ -153,6 +153,8 @@ void drm_sysfs_lease_event(struct drm_device *dev);
 
 /* drm_gem.c */
 int drm_gem_init(struct drm_device *dev);
+bool drm_gem_object_handle_get_if_exists_unlocked(struct drm_gem_object *obj);
+void drm_gem_object_handle_put_unlocked(struct drm_gem_object *obj);
 int drm_gem_handle_create_tail(struct drm_file *file_priv,
 			       struct drm_gem_object *obj,
 			       u32 *handlep);
diff --git a/drivers/gpu/drm/drm_mipi_dbi.c b/drivers/gpu/drm/drm_mipi_dbi.c
index 34bca7567576..3ea9f23b4f67 100644
--- a/drivers/gpu/drm/drm_mipi_dbi.c
+++ b/drivers/gpu/drm/drm_mipi_dbi.c
@@ -404,12 +404,16 @@ static void mipi_dbi_blank(struct mipi_dbi_dev *dbidev)
 	u16 height = drm->mode_config.min_height;
 	u16 width = drm->mode_config.min_width;
 	struct mipi_dbi *dbi = &dbidev->dbi;
-	size_t len = width * height * 2;
+	const struct drm_format_info *dst_format;
+	size_t len;
 	int idx;
 
 	if (!drm_dev_enter(drm, &idx))
 		return;
 
+	dst_format = drm_format_info(dbidev->pixel_format);
+	len = drm_format_info_min_pitch(dst_format, 0, width) * height;
+
 	memset(dbidev->tx_buf, 0, len);
 
 	mipi_dbi_set_window_address(dbidev, 0, width - 1, 0, height - 1);
diff --git a/drivers/gpu/drm/drm_panel.c b/drivers/gpu/drm/drm_panel.c
index 19ab0a794add..fd8fa2e0ef6f 100644
--- a/drivers/gpu/drm/drm_panel.c
+++ b/drivers/gpu/drm/drm_panel.c
@@ -49,7 +49,7 @@ static LIST_HEAD(panel_list);
  * @dev: parent device of the panel
  * @funcs: panel operations
  * @connector_type: the connector type (DRM_MODE_CONNECTOR_*) corresponding to
- *	the panel interface
+ *	the panel interface (must NOT be DRM_MODE_CONNECTOR_Unknown)
  *
  * Initialize the panel structure for subsequent registration with
  * drm_panel_add().
@@ -57,6 +57,9 @@ static LIST_HEAD(panel_list);
 void drm_panel_init(struct drm_panel *panel, struct device *dev,
 		    const struct drm_panel_funcs *funcs, int connector_type)
 {
+	if (connector_type == DRM_MODE_CONNECTOR_Unknown)
+		DRM_WARN("%s: %s: a valid connector type is required!\n", __func__, dev_name(dev));
+
 	INIT_LIST_HEAD(&panel->list);
 	INIT_LIST_HEAD(&panel->followers);
 	mutex_init(&panel->follower_lock);
diff --git a/drivers/gpu/drm/drm_panel_backlight_quirks.c b/drivers/gpu/drm/drm_panel_backlight_quirks.c
new file mode 100644
index 000000000000..c477d98ade2b
--- /dev/null
+++ b/drivers/gpu/drm/drm_panel_backlight_quirks.c
@@ -0,0 +1,94 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/array_size.h>
+#include <linux/dmi.h>
+#include <linux/mod_devicetable.h>
+#include <linux/module.h>
+#include <drm/drm_edid.h>
+#include <drm/drm_utils.h>
+
+struct drm_panel_min_backlight_quirk {
+	struct {
+		enum dmi_field field;
+		const char * const value;
+	} dmi_match;
+	struct drm_edid_ident ident;
+	u8 min_brightness;
+};
+
+static const struct drm_panel_min_backlight_quirk drm_panel_min_backlight_quirks[] = {
+	/* 13 inch matte panel */
+	{
+		.dmi_match.field = DMI_BOARD_VENDOR,
+		.dmi_match.value = "Framework",
+		.ident.panel_id = drm_edid_encode_panel_id('B', 'O', 'E', 0x0bca),
+		.ident.name = "NE135FBM-N41",
+		.min_brightness = 0,
+	},
+	/* 13 inch glossy panel */
+	{
+		.dmi_match.field = DMI_BOARD_VENDOR,
+		.dmi_match.value = "Framework",
+		.ident.panel_id = drm_edid_encode_panel_id('B', 'O', 'E', 0x095f),
+		.ident.name = "NE135FBM-N41",
+		.min_brightness = 0,
+	},
+	/* 13 inch 2.8k panel */
+	{
+		.dmi_match.field = DMI_BOARD_VENDOR,
+		.dmi_match.value = "Framework",
+		.ident.panel_id = drm_edid_encode_panel_id('B', 'O', 'E', 0x0cb4),
+		.ident.name = "NE135A1M-NY1",
+		.min_brightness = 0,
+	},
+};
+
+static bool drm_panel_min_backlight_quirk_matches(const struct drm_panel_min_backlight_quirk *quirk,
+						  const struct drm_edid *edid)
+{
+	if (!dmi_match(quirk->dmi_match.field, quirk->dmi_match.value))
+		return false;
+
+	if (!drm_edid_match(edid, &quirk->ident))
+		return false;
+
+	return true;
+}
+
+/**
+ * drm_get_panel_min_brightness_quirk - Get minimum supported brightness level for a panel.
+ * @edid: EDID of the panel to check
+ *
+ * This function checks for platform specific (e.g. DMI based) quirks
+ * providing info on the minimum backlight brightness for systems where this
+ * cannot be probed correctly from the hard-/firm-ware.
+ *
+ * Returns:
+ * A negative error value or
+ * an override value in the range [0, 255] representing 0-100% to be scaled to
+ * the drivers target range.
+ */
+int drm_get_panel_min_brightness_quirk(const struct drm_edid *edid)
+{
+	const struct drm_panel_min_backlight_quirk *quirk;
+	size_t i;
+
+	if (!IS_ENABLED(CONFIG_DMI))
+		return -ENODATA;
+
+	if (!edid)
+		return -EINVAL;
+
+	for (i = 0; i < ARRAY_SIZE(drm_panel_min_backlight_quirks); i++) {
+		quirk = &drm_panel_min_backlight_quirks[i];
+
+		if (drm_panel_min_backlight_quirk_matches(quirk, edid))
+			return quirk->min_brightness;
+	}
+
+	return -ENODATA;
+}
+EXPORT_SYMBOL(drm_get_panel_min_brightness_quirk);
+
+MODULE_DESCRIPTION("Quirks for panel backlight overrides");
+MODULE_LICENSE("GPL");
diff --git a/drivers/gpu/drm/drm_panel_orientation_quirks.c b/drivers/gpu/drm/drm_panel_orientation_quirks.c
index 4a73821b81f6..c554ad8f246b 100644
--- a/drivers/gpu/drm/drm_panel_orientation_quirks.c
+++ b/drivers/gpu/drm/drm_panel_orientation_quirks.c
@@ -93,6 +93,12 @@ static const struct drm_dmi_panel_orientation_data onegx1_pro = {
 	.orientation = DRM_MODE_PANEL_ORIENTATION_RIGHT_UP,
 };
 
+static const struct drm_dmi_panel_orientation_data lcd640x960_leftside_up = {
+	.width = 640,
+	.height = 960,
+	.orientation = DRM_MODE_PANEL_ORIENTATION_LEFT_UP,
+};
+
 static const struct drm_dmi_panel_orientation_data lcd720x1280_rightside_up = {
 	.width = 720,
 	.height = 1280,
@@ -123,6 +129,12 @@ static const struct drm_dmi_panel_orientation_data lcd1080x1920_rightside_up = {
 	.orientation = DRM_MODE_PANEL_ORIENTATION_RIGHT_UP,
 };
 
+static const struct drm_dmi_panel_orientation_data lcd1200x1920_leftside_up = {
+	.width = 1200,
+	.height = 1920,
+	.orientation = DRM_MODE_PANEL_ORIENTATION_LEFT_UP,
+};
+
 static const struct drm_dmi_panel_orientation_data lcd1200x1920_rightside_up = {
 	.width = 1200,
 	.height = 1920,
@@ -184,10 +196,10 @@ static const struct dmi_system_id orientation_data[] = {
 		  DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "T103HAF"),
 		},
 		.driver_data = (void *)&lcd800x1280_rightside_up,
-	}, {	/* AYA NEO AYANEO 2 */
+	}, {	/* AYA NEO AYANEO 2/2S */
 		.matches = {
 		  DMI_EXACT_MATCH(DMI_SYS_VENDOR, "AYANEO"),
-		  DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "AYANEO 2"),
+		  DMI_MATCH(DMI_PRODUCT_NAME, "AYANEO 2"),
 		},
 		.driver_data = (void *)&lcd1200x1920_rightside_up,
 	}, {	/* AYA NEO 2021 */
@@ -202,6 +214,18 @@ static const struct dmi_system_id orientation_data[] = {
 		  DMI_MATCH(DMI_PRODUCT_NAME, "AIR"),
 		},
 		.driver_data = (void *)&lcd1080x1920_leftside_up,
+	}, {    /* AYA NEO Flip DS Bottom Screen */
+		.matches = {
+		  DMI_EXACT_MATCH(DMI_SYS_VENDOR, "AYANEO"),
+		  DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "FLIP DS"),
+		},
+		.driver_data = (void *)&lcd640x960_leftside_up,
+	}, {    /* AYA NEO Flip KB/DS Top Screen */
+		.matches = {
+		  DMI_EXACT_MATCH(DMI_SYS_VENDOR, "AYANEO"),
+		  DMI_MATCH(DMI_PRODUCT_NAME, "FLIP"),
+		},
+		.driver_data = (void *)&lcd1080x1920_leftside_up,
 	}, {	/* AYA NEO Founder */
 		.matches = {
 		  DMI_EXACT_MATCH(DMI_SYS_VENDOR, "AYA NEO"),
@@ -226,6 +250,12 @@ static const struct dmi_system_id orientation_data[] = {
 		  DMI_MATCH(DMI_BOARD_NAME, "KUN"),
 		},
 		.driver_data = (void *)&lcd1600x2560_rightside_up,
+	}, {	/* AYA NEO SLIDE */
+		.matches = {
+		  DMI_EXACT_MATCH(DMI_SYS_VENDOR, "AYANEO"),
+		  DMI_MATCH(DMI_PRODUCT_NAME, "SLIDE"),
+		},
+		.driver_data = (void *)&lcd1080x1920_leftside_up,
 	}, {    /* AYN Loki Max */
 		.matches = {
 			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ayn"),
@@ -315,6 +345,12 @@ static const struct dmi_system_id orientation_data[] = {
 		  DMI_EXACT_MATCH(DMI_BOARD_NAME, "Default string"),
 		},
 		.driver_data = (void *)&gpd_win2,
+	}, {	/* GPD Win 2 (correct DMI strings) */
+		.matches = {
+		  DMI_EXACT_MATCH(DMI_SYS_VENDOR, "GPD"),
+		  DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "WIN2")
+		},
+		.driver_data = (void *)&lcd720x1280_rightside_up,
 	}, {	/* GPD Win 3 */
 		.matches = {
 		  DMI_EXACT_MATCH(DMI_SYS_VENDOR, "GPD"),
@@ -443,6 +479,12 @@ static const struct dmi_system_id orientation_data[] = {
 		  DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "ONE XPLAYER"),
 		},
 		.driver_data = (void *)&lcd1600x2560_leftside_up,
+	}, {	/* OneXPlayer Mini (Intel) */
+		.matches = {
+		  DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ONE-NETBOOK TECHNOLOGY CO., LTD."),
+		  DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "ONE XPLAYER"),
+		},
+		.driver_data = (void *)&lcd1200x1920_leftside_up,
 	}, {	/* OrangePi Neo */
 		.matches = {
 		  DMI_EXACT_MATCH(DMI_SYS_VENDOR, "OrangePi"),
diff --git a/drivers/gpu/drm/drm_panic_qr.rs b/drivers/gpu/drm/drm_panic_qr.rs
index 447740d79d3d..6903e2010cb9 100644
--- a/drivers/gpu/drm/drm_panic_qr.rs
+++ b/drivers/gpu/drm/drm_panic_qr.rs
@@ -209,12 +209,9 @@ const FORMAT_INFOS_QR_L: [u16; 8] = [
 impl Version {
     /// Returns the smallest QR version than can hold these segments.
     fn from_segments(segments: &[&Segment<'_>]) -> Option<Version> {
-        for v in (1..=40).map(|k| Version(k)) {
-            if v.max_data() * 8 >= segments.iter().map(|s| s.total_size_bits(v)).sum() {
-                return Some(v);
-            }
-        }
-        None
+        (1..=40)
+            .map(Version)
+            .find(|&v| v.max_data() * 8 >= segments.iter().map(|s| s.total_size_bits(v)).sum())
     }
 
     fn width(&self) -> u8 {
@@ -242,7 +239,7 @@ impl Version {
     }
 
     fn alignment_pattern(&self) -> &'static [u8] {
-        &ALIGNMENT_PATTERNS[self.0 - 1]
+        ALIGNMENT_PATTERNS[self.0 - 1]
     }
 
     fn poly(&self) -> &'static [u8] {
@@ -479,7 +476,7 @@ struct EncodedMsg<'a> {
 /// Data to be put in the QR code, with correct segment encoding, padding, and
 /// Error Code Correction.
 impl EncodedMsg<'_> {
-    fn new<'a, 'b>(segments: &[&Segment<'b>], data: &'a mut [u8]) -> Option<EncodedMsg<'a>> {
+    fn new<'a>(segments: &[&Segment<'_>], data: &'a mut [u8]) -> Option<EncodedMsg<'a>> {
         let version = Version::from_segments(segments)?;
         let ec_size = version.ec_size();
         let g1_blocks = version.g1_blocks();
@@ -492,7 +489,7 @@ impl EncodedMsg<'_> {
         data.fill(0);
 
         let mut em = EncodedMsg {
-            data: data,
+            data,
             ec_size,
             g1_blocks,
             g2_blocks,
@@ -548,7 +545,7 @@ impl EncodedMsg<'_> {
         }
         self.push(&mut offset, (MODE_STOP, 4));
 
-        let pad_offset = (offset + 7) / 8;
+        let pad_offset = offset.div_ceil(8);
         for i in pad_offset..self.version.max_data() {
             self.data[i] = PADDING[(i & 1) ^ (pad_offset & 1)];
         }
@@ -662,7 +659,7 @@ struct QrImage<'a> {
 impl QrImage<'_> {
     fn new<'a, 'b>(em: &'b EncodedMsg<'b>, qrdata: &'a mut [u8]) -> QrImage<'a> {
         let width = em.version.width();
-        let stride = (width + 7) / 8;
+        let stride = width.div_ceil(8);
         let data = qrdata;
 
         let mut qr_image = QrImage {
@@ -722,7 +719,10 @@ impl QrImage<'_> {
 
     fn is_finder(&self, x: u8, y: u8) -> bool {
         let end = self.width - 8;
-        (x < 8 && y < 8) || (x < 8 && y >= end) || (x >= end && y < 8)
+        #[expect(clippy::nonminimal_bool)]
+        {
+            (x < 8 && y < 8) || (x < 8 && y >= end) || (x >= end && y < 8)
+        }
     }
 
     // Alignment pattern: 5x5 squares in a grid.
@@ -911,16 +911,16 @@ impl QrImage<'_> {
 ///
 /// * `url`: The base URL of the QR code. It will be encoded as Binary segment.
 /// * `data`: A pointer to the binary data, to be encoded. if URL is NULL, it
-///    will be encoded as binary segment, otherwise it will be encoded
-///    efficiently as a numeric segment, and appended to the URL.
+///   will be encoded as binary segment, otherwise it will be encoded
+///   efficiently as a numeric segment, and appended to the URL.
 /// * `data_len`: Length of the data, that needs to be encoded, must be less
-///    than data_size.
+///   than data_size.
 /// * `data_size`: Size of data buffer, it should be at least 4071 bytes to hold
-///    a V40 QR code. It will then be overwritten with the QR code image.
+///   a V40 QR code. It will then be overwritten with the QR code image.
 /// * `tmp`: A temporary buffer that the QR code encoder will use, to write the
-///    segments and ECC.
+///   segments and ECC.
 /// * `tmp_size`: Size of the temporary buffer, it must be at least 3706 bytes
-///    long for V40.
+///   long for V40.
 ///
 /// # Safety
 ///
@@ -931,7 +931,7 @@ impl QrImage<'_> {
 /// They must remain valid for the duration of the function call.
 #[no_mangle]
 pub unsafe extern "C" fn drm_panic_qr_generate(
-    url: *const i8,
+    url: *const kernel::ffi::c_char,
     data: *mut u8,
     data_len: usize,
     data_size: usize,
@@ -978,10 +978,11 @@ pub unsafe extern "C" fn drm_panic_qr_generate(
 /// * `url_len`: Length of the URL.
 ///
 /// * If `url_len` > 0, remove the 2 segments header/length and also count the
-/// conversion to numeric segments.
+///   conversion to numeric segments.
 /// * If `url_len` = 0, only removes 3 bytes for 1 binary segment.
 #[no_mangle]
 pub extern "C" fn drm_panic_qr_max_data_size(version: u8, url_len: usize) -> usize {
+    #[expect(clippy::manual_range_contains)]
     if version < 1 || version > 40 {
         return 0;
     }
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.c b/drivers/gpu/drm/etnaviv/etnaviv_gem.c
index 5c0c9d4e3be1..d3f6df047f5a 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gem.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.c
@@ -342,6 +342,7 @@ void *etnaviv_gem_vmap(struct drm_gem_object *obj)
 static void *etnaviv_gem_vmap_impl(struct etnaviv_gem_object *obj)
 {
 	struct page **pages;
+	pgprot_t prot;
 
 	lockdep_assert_held(&obj->lock);
 
@@ -349,8 +350,19 @@ static void *etnaviv_gem_vmap_impl(struct etnaviv_gem_object *obj)
 	if (IS_ERR(pages))
 		return NULL;
 
-	return vmap(pages, obj->base.size >> PAGE_SHIFT,
-			VM_MAP, pgprot_writecombine(PAGE_KERNEL));
+	switch (obj->flags & ETNA_BO_CACHE_MASK) {
+	case ETNA_BO_CACHED:
+		prot = PAGE_KERNEL;
+		break;
+	case ETNA_BO_UNCACHED:
+		prot = pgprot_noncached(PAGE_KERNEL);
+		break;
+	case ETNA_BO_WC:
+	default:
+		prot = pgprot_writecombine(PAGE_KERNEL);
+	}
+
+	return vmap(pages, obj->base.size >> PAGE_SHIFT, VM_MAP, prot);
 }
 
 static inline enum dma_data_direction etnaviv_op_to_dma_dir(u32 op)
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_sched.c b/drivers/gpu/drm/etnaviv/etnaviv_sched.c
index ab9ca4824b62..e60288af3502 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_sched.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_sched.c
@@ -34,6 +34,7 @@ static enum drm_gpu_sched_stat etnaviv_sched_timedout_job(struct drm_sched_job
 							  *sched_job)
 {
 	struct etnaviv_gem_submit *submit = to_etnaviv_submit(sched_job);
+	struct drm_gpu_scheduler *sched = sched_job->sched;
 	struct etnaviv_gpu *gpu = submit->gpu;
 	u32 dma_addr;
 	int change;
@@ -76,7 +77,9 @@ static enum drm_gpu_sched_stat etnaviv_sched_timedout_job(struct drm_sched_job
 	return DRM_GPU_SCHED_STAT_NOMINAL;
 
 out_no_timeout:
-	list_add(&sched_job->list, &sched_job->sched->pending_list);
+	spin_lock(&sched->job_list_lock);
+	list_add(&sched_job->list, &sched->pending_list);
+	spin_unlock(&sched->job_list_lock);
 	return DRM_GPU_SCHED_STAT_NOMINAL;
 }
 
diff --git a/drivers/gpu/drm/exynos/exynos7_drm_decon.c b/drivers/gpu/drm/exynos/exynos7_drm_decon.c
index 0d185c0564b9..9eeba254cf45 100644
--- a/drivers/gpu/drm/exynos/exynos7_drm_decon.c
+++ b/drivers/gpu/drm/exynos/exynos7_drm_decon.c
@@ -601,6 +601,10 @@ static irqreturn_t decon_irq_handler(int irq, void *dev_id)
 	if (!ctx->drm_dev)
 		goto out;
 
+	/* check if crtc and vblank have been initialized properly */
+	if (!drm_dev_has_vblank(ctx->drm_dev))
+		goto out;
+
 	if (!ctx->i80_if) {
 		drm_crtc_handle_vblank(&ctx->crtc->base);
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimd.c b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
index f57df8c48139..05e4a5a63f5d 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fimd.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
@@ -187,6 +187,7 @@ struct fimd_context {
 	u32				i80ifcon;
 	bool				i80_if;
 	bool				suspended;
+	bool				dp_clk_enabled;
 	wait_queue_head_t		wait_vsync_queue;
 	atomic_t			wait_vsync_event;
 	atomic_t			win_updated;
@@ -1047,7 +1048,18 @@ static void fimd_dp_clock_enable(struct exynos_drm_clk *clk, bool enable)
 	struct fimd_context *ctx = container_of(clk, struct fimd_context,
 						dp_clk);
 	u32 val = enable ? DP_MIE_CLK_DP_ENABLE : DP_MIE_CLK_DISABLE;
+
+	if (enable == ctx->dp_clk_enabled)
+		return;
+
+	if (enable)
+		pm_runtime_resume_and_get(ctx->dev);
+
+	ctx->dp_clk_enabled = enable;
 	writel(val, ctx->regs + DP_MIE_CLKCON);
+
+	if (!enable)
+		pm_runtime_put(ctx->dev);
 }
 
 static const struct exynos_drm_crtc_ops fimd_crtc_ops = {
diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c
index 1e26cd4f8347..52059cfff4f0 100644
--- a/drivers/gpu/drm/exynos/exynos_hdmi.c
+++ b/drivers/gpu/drm/exynos/exynos_hdmi.c
@@ -1643,7 +1643,9 @@ static int hdmi_audio_get_eld(struct device *dev, void *data, uint8_t *buf,
 	struct hdmi_context *hdata = dev_get_drvdata(dev);
 	struct drm_connector *connector = &hdata->connector;
 
+	mutex_lock(&connector->eld_mutex);
 	memcpy(buf, connector->eld, min(sizeof(connector->eld), len));
+	mutex_unlock(&connector->eld_mutex);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/gma500/mid_bios.c b/drivers/gpu/drm/gma500/mid_bios.c
index 7e76790c6a81..cba97d7db131 100644
--- a/drivers/gpu/drm/gma500/mid_bios.c
+++ b/drivers/gpu/drm/gma500/mid_bios.c
@@ -279,6 +279,11 @@ static void mid_get_vbt_data(struct drm_psb_private *dev_priv)
 					    0, PCI_DEVFN(2, 0));
 	int ret = -1;
 
+	if (pci_gfx_root == NULL) {
+		WARN_ON(1);
+		return;
+	}
+
 	/* Get the address of the platform config vbt */
 	pci_read_config_dword(pci_gfx_root, 0xFC, &addr);
 	pci_dev_put(pci_gfx_root);
diff --git a/drivers/gpu/drm/hyperv/hyperv_drm_drv.c b/drivers/gpu/drm/hyperv/hyperv_drm_drv.c
index ff93e08d5036..5f02a5a39ab4 100644
--- a/drivers/gpu/drm/hyperv/hyperv_drm_drv.c
+++ b/drivers/gpu/drm/hyperv/hyperv_drm_drv.c
@@ -154,6 +154,7 @@ static int hyperv_vmbus_probe(struct hv_device *hdev,
 	return 0;
 
 err_free_mmio:
+	iounmap(hv->vram);
 	vmbus_free_mmio(hv->mem->start, hv->fb_size);
 err_vmbus_close:
 	vmbus_close(hdev->channel);
@@ -172,6 +173,7 @@ static void hyperv_vmbus_remove(struct hv_device *hdev)
 	vmbus_close(hdev->channel);
 	hv_set_drvdata(hdev, NULL);
 
+	iounmap(hv->vram);
 	vmbus_free_mmio(hv->mem->start, hv->fb_size);
 }
 
diff --git a/drivers/gpu/drm/i915/display/g4x_hdmi.c b/drivers/gpu/drm/i915/display/g4x_hdmi.c
index 46f23bdb4c17..b89a364a3924 100644
--- a/drivers/gpu/drm/i915/display/g4x_hdmi.c
+++ b/drivers/gpu/drm/i915/display/g4x_hdmi.c
@@ -683,7 +683,7 @@ static bool assert_hdmi_port_valid(struct drm_i915_private *i915, enum port port
 			 "Platform does not support HDMI %c\n", port_name(port));
 }
 
-void g4x_hdmi_init(struct drm_i915_private *dev_priv,
+bool g4x_hdmi_init(struct drm_i915_private *dev_priv,
 		   i915_reg_t hdmi_reg, enum port port)
 {
 	struct intel_display *display = &dev_priv->display;
@@ -693,10 +693,10 @@ void g4x_hdmi_init(struct drm_i915_private *dev_priv,
 	struct intel_connector *intel_connector;
 
 	if (!assert_port_valid(dev_priv, port))
-		return;
+		return false;
 
 	if (!assert_hdmi_port_valid(dev_priv, port))
-		return;
+		return false;
 
 	devdata = intel_bios_encoder_data_lookup(display, port);
 
@@ -707,15 +707,13 @@ void g4x_hdmi_init(struct drm_i915_private *dev_priv,
 
 	dig_port = kzalloc(sizeof(*dig_port), GFP_KERNEL);
 	if (!dig_port)
-		return;
+		return false;
 
 	dig_port->aux_ch = AUX_CH_NONE;
 
 	intel_connector = intel_connector_alloc();
-	if (!intel_connector) {
-		kfree(dig_port);
-		return;
-	}
+	if (!intel_connector)
+		goto err_connector_alloc;
 
 	intel_encoder = &dig_port->base;
 
@@ -723,9 +721,10 @@ void g4x_hdmi_init(struct drm_i915_private *dev_priv,
 
 	mutex_init(&dig_port->hdcp_mutex);
 
-	drm_encoder_init(&dev_priv->drm, &intel_encoder->base,
-			 &intel_hdmi_enc_funcs, DRM_MODE_ENCODER_TMDS,
-			 "HDMI %c", port_name(port));
+	if (drm_encoder_init(&dev_priv->drm, &intel_encoder->base,
+			     &intel_hdmi_enc_funcs, DRM_MODE_ENCODER_TMDS,
+			     "HDMI %c", port_name(port)))
+		goto err_encoder_init;
 
 	intel_encoder->hotplug = intel_hdmi_hotplug;
 	intel_encoder->compute_config = g4x_hdmi_compute_config;
@@ -788,5 +787,17 @@ void g4x_hdmi_init(struct drm_i915_private *dev_priv,
 
 	intel_infoframe_init(dig_port);
 
-	intel_hdmi_init_connector(dig_port, intel_connector);
+	if (!intel_hdmi_init_connector(dig_port, intel_connector))
+		goto err_init_connector;
+
+	return true;
+
+err_init_connector:
+	drm_encoder_cleanup(&intel_encoder->base);
+err_encoder_init:
+	kfree(intel_connector);
+err_connector_alloc:
+	kfree(dig_port);
+
+	return false;
 }
diff --git a/drivers/gpu/drm/i915/display/g4x_hdmi.h b/drivers/gpu/drm/i915/display/g4x_hdmi.h
index 817f55c7a3a1..a52e8986ec7a 100644
--- a/drivers/gpu/drm/i915/display/g4x_hdmi.h
+++ b/drivers/gpu/drm/i915/display/g4x_hdmi.h
@@ -16,14 +16,15 @@ struct drm_connector;
 struct drm_i915_private;
 
 #ifdef I915
-void g4x_hdmi_init(struct drm_i915_private *dev_priv,
+bool g4x_hdmi_init(struct drm_i915_private *dev_priv,
 		   i915_reg_t hdmi_reg, enum port port);
 int g4x_hdmi_connector_atomic_check(struct drm_connector *connector,
 				    struct drm_atomic_state *state);
 #else
-static inline void g4x_hdmi_init(struct drm_i915_private *dev_priv,
+static inline bool g4x_hdmi_init(struct drm_i915_private *dev_priv,
 				 i915_reg_t hdmi_reg, int port)
 {
+	return false;
 }
 static inline int g4x_hdmi_connector_atomic_check(struct drm_connector *connector,
 						  struct drm_atomic_state *state)
diff --git a/drivers/gpu/drm/i915/display/i9xx_plane.c b/drivers/gpu/drm/i915/display/i9xx_plane.c
index 9447f7229b60..17a1e3801a85 100644
--- a/drivers/gpu/drm/i915/display/i9xx_plane.c
+++ b/drivers/gpu/drm/i915/display/i9xx_plane.c
@@ -416,7 +416,8 @@ static int i9xx_plane_min_cdclk(const struct intel_crtc_state *crtc_state,
 	return DIV_ROUND_UP(pixel_rate * num, den);
 }
 
-static void i9xx_plane_update_noarm(struct intel_plane *plane,
+static void i9xx_plane_update_noarm(struct intel_dsb *dsb,
+				    struct intel_plane *plane,
 				    const struct intel_crtc_state *crtc_state,
 				    const struct intel_plane_state *plane_state)
 {
@@ -444,7 +445,8 @@ static void i9xx_plane_update_noarm(struct intel_plane *plane,
 	}
 }
 
-static void i9xx_plane_update_arm(struct intel_plane *plane,
+static void i9xx_plane_update_arm(struct intel_dsb *dsb,
+				  struct intel_plane *plane,
 				  const struct intel_crtc_state *crtc_state,
 				  const struct intel_plane_state *plane_state)
 {
@@ -507,7 +509,8 @@ static void i9xx_plane_update_arm(struct intel_plane *plane,
 				  intel_plane_ggtt_offset(plane_state) + dspaddr_offset);
 }
 
-static void i830_plane_update_arm(struct intel_plane *plane,
+static void i830_plane_update_arm(struct intel_dsb *dsb,
+				  struct intel_plane *plane,
 				  const struct intel_crtc_state *crtc_state,
 				  const struct intel_plane_state *plane_state)
 {
@@ -517,11 +520,12 @@ static void i830_plane_update_arm(struct intel_plane *plane,
 	 * Additional breakage on i830 causes register reads to return
 	 * the last latched value instead of the last written value [ALM026].
 	 */
-	i9xx_plane_update_noarm(plane, crtc_state, plane_state);
-	i9xx_plane_update_arm(plane, crtc_state, plane_state);
+	i9xx_plane_update_noarm(dsb, plane, crtc_state, plane_state);
+	i9xx_plane_update_arm(dsb, plane, crtc_state, plane_state);
 }
 
-static void i9xx_plane_disable_arm(struct intel_plane *plane,
+static void i9xx_plane_disable_arm(struct intel_dsb *dsb,
+				   struct intel_plane *plane,
 				   const struct intel_crtc_state *crtc_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
@@ -549,7 +553,8 @@ static void i9xx_plane_disable_arm(struct intel_plane *plane,
 }
 
 static void
-g4x_primary_async_flip(struct intel_plane *plane,
+g4x_primary_async_flip(struct intel_dsb *dsb,
+		       struct intel_plane *plane,
 		       const struct intel_crtc_state *crtc_state,
 		       const struct intel_plane_state *plane_state,
 		       bool async_flip)
@@ -569,7 +574,8 @@ g4x_primary_async_flip(struct intel_plane *plane,
 }
 
 static void
-vlv_primary_async_flip(struct intel_plane *plane,
+vlv_primary_async_flip(struct intel_dsb *dsb,
+		       struct intel_plane *plane,
 		       const struct intel_crtc_state *crtc_state,
 		       const struct intel_plane_state *plane_state,
 		       bool async_flip)
diff --git a/drivers/gpu/drm/i915/display/icl_dsi.c b/drivers/gpu/drm/i915/display/icl_dsi.c
index 293efc1f841d..4e95b8eda23f 100644
--- a/drivers/gpu/drm/i915/display/icl_dsi.c
+++ b/drivers/gpu/drm/i915/display/icl_dsi.c
@@ -50,38 +50,38 @@
 #include "skl_scaler.h"
 #include "skl_universal_plane.h"
 
-static int header_credits_available(struct drm_i915_private *dev_priv,
+static int header_credits_available(struct intel_display *display,
 				    enum transcoder dsi_trans)
 {
-	return (intel_de_read(dev_priv, DSI_CMD_TXCTL(dsi_trans)) & FREE_HEADER_CREDIT_MASK)
+	return (intel_de_read(display, DSI_CMD_TXCTL(dsi_trans)) & FREE_HEADER_CREDIT_MASK)
 		>> FREE_HEADER_CREDIT_SHIFT;
 }
 
-static int payload_credits_available(struct drm_i915_private *dev_priv,
+static int payload_credits_available(struct intel_display *display,
 				     enum transcoder dsi_trans)
 {
-	return (intel_de_read(dev_priv, DSI_CMD_TXCTL(dsi_trans)) & FREE_PLOAD_CREDIT_MASK)
+	return (intel_de_read(display, DSI_CMD_TXCTL(dsi_trans)) & FREE_PLOAD_CREDIT_MASK)
 		>> FREE_PLOAD_CREDIT_SHIFT;
 }
 
-static bool wait_for_header_credits(struct drm_i915_private *dev_priv,
+static bool wait_for_header_credits(struct intel_display *display,
 				    enum transcoder dsi_trans, int hdr_credit)
 {
-	if (wait_for_us(header_credits_available(dev_priv, dsi_trans) >=
+	if (wait_for_us(header_credits_available(display, dsi_trans) >=
 			hdr_credit, 100)) {
-		drm_err(&dev_priv->drm, "DSI header credits not released\n");
+		drm_err(display->drm, "DSI header credits not released\n");
 		return false;
 	}
 
 	return true;
 }
 
-static bool wait_for_payload_credits(struct drm_i915_private *dev_priv,
+static bool wait_for_payload_credits(struct intel_display *display,
 				     enum transcoder dsi_trans, int payld_credit)
 {
-	if (wait_for_us(payload_credits_available(dev_priv, dsi_trans) >=
+	if (wait_for_us(payload_credits_available(display, dsi_trans) >=
 			payld_credit, 100)) {
-		drm_err(&dev_priv->drm, "DSI payload credits not released\n");
+		drm_err(display->drm, "DSI payload credits not released\n");
 		return false;
 	}
 
@@ -98,7 +98,7 @@ static enum transcoder dsi_port_to_transcoder(enum port port)
 
 static void wait_for_cmds_dispatched_to_panel(struct intel_encoder *encoder)
 {
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct intel_display *display = to_intel_display(encoder);
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	struct mipi_dsi_device *dsi;
 	enum port port;
@@ -108,8 +108,8 @@ static void wait_for_cmds_dispatched_to_panel(struct intel_encoder *encoder)
 	/* wait for header/payload credits to be released */
 	for_each_dsi_port(port, intel_dsi->ports) {
 		dsi_trans = dsi_port_to_transcoder(port);
-		wait_for_header_credits(dev_priv, dsi_trans, MAX_HEADER_CREDIT);
-		wait_for_payload_credits(dev_priv, dsi_trans, MAX_PLOAD_CREDIT);
+		wait_for_header_credits(display, dsi_trans, MAX_HEADER_CREDIT);
+		wait_for_payload_credits(display, dsi_trans, MAX_PLOAD_CREDIT);
 	}
 
 	/* send nop DCS command */
@@ -119,22 +119,22 @@ static void wait_for_cmds_dispatched_to_panel(struct intel_encoder *encoder)
 		dsi->channel = 0;
 		ret = mipi_dsi_dcs_nop(dsi);
 		if (ret < 0)
-			drm_err(&dev_priv->drm,
+			drm_err(display->drm,
 				"error sending DCS NOP command\n");
 	}
 
 	/* wait for header credits to be released */
 	for_each_dsi_port(port, intel_dsi->ports) {
 		dsi_trans = dsi_port_to_transcoder(port);
-		wait_for_header_credits(dev_priv, dsi_trans, MAX_HEADER_CREDIT);
+		wait_for_header_credits(display, dsi_trans, MAX_HEADER_CREDIT);
 	}
 
 	/* wait for LP TX in progress bit to be cleared */
 	for_each_dsi_port(port, intel_dsi->ports) {
 		dsi_trans = dsi_port_to_transcoder(port);
-		if (wait_for_us(!(intel_de_read(dev_priv, DSI_LP_MSG(dsi_trans)) &
+		if (wait_for_us(!(intel_de_read(display, DSI_LP_MSG(dsi_trans)) &
 				  LPTX_IN_PROGRESS), 20))
-			drm_err(&dev_priv->drm, "LPTX bit not cleared\n");
+			drm_err(display->drm, "LPTX bit not cleared\n");
 	}
 }
 
@@ -142,7 +142,7 @@ static int dsi_send_pkt_payld(struct intel_dsi_host *host,
 			      const struct mipi_dsi_packet *packet)
 {
 	struct intel_dsi *intel_dsi = host->intel_dsi;
-	struct drm_i915_private *i915 = to_i915(intel_dsi->base.base.dev);
+	struct intel_display *display = to_intel_display(&intel_dsi->base);
 	enum transcoder dsi_trans = dsi_port_to_transcoder(host->port);
 	const u8 *data = packet->payload;
 	u32 len = packet->payload_length;
@@ -150,20 +150,20 @@ static int dsi_send_pkt_payld(struct intel_dsi_host *host,
 
 	/* payload queue can accept *256 bytes*, check limit */
 	if (len > MAX_PLOAD_CREDIT * 4) {
-		drm_err(&i915->drm, "payload size exceeds max queue limit\n");
+		drm_err(display->drm, "payload size exceeds max queue limit\n");
 		return -EINVAL;
 	}
 
 	for (i = 0; i < len; i += 4) {
 		u32 tmp = 0;
 
-		if (!wait_for_payload_credits(i915, dsi_trans, 1))
+		if (!wait_for_payload_credits(display, dsi_trans, 1))
 			return -EBUSY;
 
 		for (j = 0; j < min_t(u32, len - i, 4); j++)
 			tmp |= *data++ << 8 * j;
 
-		intel_de_write(i915, DSI_CMD_TXPYLD(dsi_trans), tmp);
+		intel_de_write(display, DSI_CMD_TXPYLD(dsi_trans), tmp);
 	}
 
 	return 0;
@@ -174,14 +174,14 @@ static int dsi_send_pkt_hdr(struct intel_dsi_host *host,
 			    bool enable_lpdt)
 {
 	struct intel_dsi *intel_dsi = host->intel_dsi;
-	struct drm_i915_private *dev_priv = to_i915(intel_dsi->base.base.dev);
+	struct intel_display *display = to_intel_display(&intel_dsi->base);
 	enum transcoder dsi_trans = dsi_port_to_transcoder(host->port);
 	u32 tmp;
 
-	if (!wait_for_header_credits(dev_priv, dsi_trans, 1))
+	if (!wait_for_header_credits(display, dsi_trans, 1))
 		return -EBUSY;
 
-	tmp = intel_de_read(dev_priv, DSI_CMD_TXHDR(dsi_trans));
+	tmp = intel_de_read(display, DSI_CMD_TXHDR(dsi_trans));
 
 	if (packet->payload)
 		tmp |= PAYLOAD_PRESENT;
@@ -200,15 +200,14 @@ static int dsi_send_pkt_hdr(struct intel_dsi_host *host,
 	tmp |= ((packet->header[0] & DT_MASK) << DT_SHIFT);
 	tmp |= (packet->header[1] << PARAM_WC_LOWER_SHIFT);
 	tmp |= (packet->header[2] << PARAM_WC_UPPER_SHIFT);
-	intel_de_write(dev_priv, DSI_CMD_TXHDR(dsi_trans), tmp);
+	intel_de_write(display, DSI_CMD_TXHDR(dsi_trans), tmp);
 
 	return 0;
 }
 
 void icl_dsi_frame_update(struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
-	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	struct intel_display *display = to_intel_display(crtc_state);
 	u32 mode_flags;
 	enum port port;
 
@@ -226,12 +225,13 @@ void icl_dsi_frame_update(struct intel_crtc_state *crtc_state)
 	else
 		return;
 
-	intel_de_rmw(dev_priv, DSI_CMD_FRMCTL(port), 0, DSI_FRAME_UPDATE_REQUEST);
+	intel_de_rmw(display, DSI_CMD_FRMCTL(port), 0,
+		     DSI_FRAME_UPDATE_REQUEST);
 }
 
 static void dsi_program_swing_and_deemphasis(struct intel_encoder *encoder)
 {
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct intel_display *display = to_intel_display(encoder);
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum phy phy;
 	u32 tmp, mask, val;
@@ -245,31 +245,31 @@ static void dsi_program_swing_and_deemphasis(struct intel_encoder *encoder)
 		mask = SCALING_MODE_SEL_MASK | RTERM_SELECT_MASK;
 		val = SCALING_MODE_SEL(0x2) | TAP2_DISABLE | TAP3_DISABLE |
 		      RTERM_SELECT(0x6);
-		tmp = intel_de_read(dev_priv, ICL_PORT_TX_DW5_LN(0, phy));
+		tmp = intel_de_read(display, ICL_PORT_TX_DW5_LN(0, phy));
 		tmp &= ~mask;
 		tmp |= val;
-		intel_de_write(dev_priv, ICL_PORT_TX_DW5_GRP(phy), tmp);
-		intel_de_rmw(dev_priv, ICL_PORT_TX_DW5_AUX(phy), mask, val);
+		intel_de_write(display, ICL_PORT_TX_DW5_GRP(phy), tmp);
+		intel_de_rmw(display, ICL_PORT_TX_DW5_AUX(phy), mask, val);
 
 		mask = SWING_SEL_LOWER_MASK | SWING_SEL_UPPER_MASK |
 		       RCOMP_SCALAR_MASK;
 		val = SWING_SEL_UPPER(0x2) | SWING_SEL_LOWER(0x2) |
 		      RCOMP_SCALAR(0x98);
-		tmp = intel_de_read(dev_priv, ICL_PORT_TX_DW2_LN(0, phy));
+		tmp = intel_de_read(display, ICL_PORT_TX_DW2_LN(0, phy));
 		tmp &= ~mask;
 		tmp |= val;
-		intel_de_write(dev_priv, ICL_PORT_TX_DW2_GRP(phy), tmp);
-		intel_de_rmw(dev_priv, ICL_PORT_TX_DW2_AUX(phy), mask, val);
+		intel_de_write(display, ICL_PORT_TX_DW2_GRP(phy), tmp);
+		intel_de_rmw(display, ICL_PORT_TX_DW2_AUX(phy), mask, val);
 
 		mask = POST_CURSOR_1_MASK | POST_CURSOR_2_MASK |
 		       CURSOR_COEFF_MASK;
 		val = POST_CURSOR_1(0x0) | POST_CURSOR_2(0x0) |
 		      CURSOR_COEFF(0x3f);
-		intel_de_rmw(dev_priv, ICL_PORT_TX_DW4_AUX(phy), mask, val);
+		intel_de_rmw(display, ICL_PORT_TX_DW4_AUX(phy), mask, val);
 
 		/* Bspec: must not use GRP register for write */
 		for (lane = 0; lane <= 3; lane++)
-			intel_de_rmw(dev_priv, ICL_PORT_TX_DW4_LN(lane, phy),
+			intel_de_rmw(display, ICL_PORT_TX_DW4_LN(lane, phy),
 				     mask, val);
 	}
 }
@@ -277,13 +277,13 @@ static void dsi_program_swing_and_deemphasis(struct intel_encoder *encoder)
 static void configure_dual_link_mode(struct intel_encoder *encoder,
 				     const struct intel_crtc_state *pipe_config)
 {
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct intel_display *display = to_intel_display(encoder);
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	i915_reg_t dss_ctl1_reg, dss_ctl2_reg;
 	u32 dss_ctl1;
 
 	/* FIXME: Move all DSS handling to intel_vdsc.c */
-	if (DISPLAY_VER(dev_priv) >= 12) {
+	if (DISPLAY_VER(display) >= 12) {
 		struct intel_crtc *crtc = to_intel_crtc(pipe_config->uapi.crtc);
 
 		dss_ctl1_reg = ICL_PIPE_DSS_CTL1(crtc->pipe);
@@ -293,7 +293,7 @@ static void configure_dual_link_mode(struct intel_encoder *encoder,
 		dss_ctl2_reg = DSS_CTL2;
 	}
 
-	dss_ctl1 = intel_de_read(dev_priv, dss_ctl1_reg);
+	dss_ctl1 = intel_de_read(display, dss_ctl1_reg);
 	dss_ctl1 |= SPLITTER_ENABLE;
 	dss_ctl1 &= ~OVERLAP_PIXELS_MASK;
 	dss_ctl1 |= OVERLAP_PIXELS(intel_dsi->pixel_overlap);
@@ -308,19 +308,19 @@ static void configure_dual_link_mode(struct intel_encoder *encoder,
 		dl_buffer_depth = hactive / 2 + intel_dsi->pixel_overlap;
 
 		if (dl_buffer_depth > MAX_DL_BUFFER_TARGET_DEPTH)
-			drm_err(&dev_priv->drm,
+			drm_err(display->drm,
 				"DL buffer depth exceed max value\n");
 
 		dss_ctl1 &= ~LEFT_DL_BUF_TARGET_DEPTH_MASK;
 		dss_ctl1 |= LEFT_DL_BUF_TARGET_DEPTH(dl_buffer_depth);
-		intel_de_rmw(dev_priv, dss_ctl2_reg, RIGHT_DL_BUF_TARGET_DEPTH_MASK,
+		intel_de_rmw(display, dss_ctl2_reg, RIGHT_DL_BUF_TARGET_DEPTH_MASK,
 			     RIGHT_DL_BUF_TARGET_DEPTH(dl_buffer_depth));
 	} else {
 		/* Interleave */
 		dss_ctl1 |= DUAL_LINK_MODE_INTERLEAVE;
 	}
 
-	intel_de_write(dev_priv, dss_ctl1_reg, dss_ctl1);
+	intel_de_write(display, dss_ctl1_reg, dss_ctl1);
 }
 
 /* aka DSI 8X clock */
@@ -341,6 +341,7 @@ static int afe_clk(struct intel_encoder *encoder,
 static void gen11_dsi_program_esc_clk_div(struct intel_encoder *encoder,
 					  const struct intel_crtc_state *crtc_state)
 {
+	struct intel_display *display = to_intel_display(encoder);
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum port port;
@@ -360,33 +361,34 @@ static void gen11_dsi_program_esc_clk_div(struct intel_encoder *encoder,
 	}
 
 	for_each_dsi_port(port, intel_dsi->ports) {
-		intel_de_write(dev_priv, ICL_DSI_ESC_CLK_DIV(port),
+		intel_de_write(display, ICL_DSI_ESC_CLK_DIV(port),
 			       esc_clk_div_m & ICL_ESC_CLK_DIV_MASK);
-		intel_de_posting_read(dev_priv, ICL_DSI_ESC_CLK_DIV(port));
+		intel_de_posting_read(display, ICL_DSI_ESC_CLK_DIV(port));
 	}
 
 	for_each_dsi_port(port, intel_dsi->ports) {
-		intel_de_write(dev_priv, ICL_DPHY_ESC_CLK_DIV(port),
+		intel_de_write(display, ICL_DPHY_ESC_CLK_DIV(port),
 			       esc_clk_div_m & ICL_ESC_CLK_DIV_MASK);
-		intel_de_posting_read(dev_priv, ICL_DPHY_ESC_CLK_DIV(port));
+		intel_de_posting_read(display, ICL_DPHY_ESC_CLK_DIV(port));
 	}
 
 	if (IS_ALDERLAKE_S(dev_priv) || IS_ALDERLAKE_P(dev_priv)) {
 		for_each_dsi_port(port, intel_dsi->ports) {
-			intel_de_write(dev_priv, ADL_MIPIO_DW(port, 8),
+			intel_de_write(display, ADL_MIPIO_DW(port, 8),
 				       esc_clk_div_m_phy & TX_ESC_CLK_DIV_PHY);
-			intel_de_posting_read(dev_priv, ADL_MIPIO_DW(port, 8));
+			intel_de_posting_read(display, ADL_MIPIO_DW(port, 8));
 		}
 	}
 }
 
-static void get_dsi_io_power_domains(struct drm_i915_private *dev_priv,
-				     struct intel_dsi *intel_dsi)
+static void get_dsi_io_power_domains(struct intel_dsi *intel_dsi)
 {
+	struct intel_display *display = to_intel_display(&intel_dsi->base);
+	struct drm_i915_private *dev_priv = to_i915(display->drm);
 	enum port port;
 
 	for_each_dsi_port(port, intel_dsi->ports) {
-		drm_WARN_ON(&dev_priv->drm, intel_dsi->io_wakeref[port]);
+		drm_WARN_ON(display->drm, intel_dsi->io_wakeref[port]);
 		intel_dsi->io_wakeref[port] =
 			intel_display_power_get(dev_priv,
 						port == PORT_A ?
@@ -397,15 +399,15 @@ static void get_dsi_io_power_domains(struct drm_i915_private *dev_priv,
 
 static void gen11_dsi_enable_io_power(struct intel_encoder *encoder)
 {
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct intel_display *display = to_intel_display(encoder);
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum port port;
 
 	for_each_dsi_port(port, intel_dsi->ports)
-		intel_de_rmw(dev_priv, ICL_DSI_IO_MODECTL(port),
+		intel_de_rmw(display, ICL_DSI_IO_MODECTL(port),
 			     0, COMBO_PHY_MODE_DSI);
 
-	get_dsi_io_power_domains(dev_priv, intel_dsi);
+	get_dsi_io_power_domains(intel_dsi);
 }
 
 static void gen11_dsi_power_up_lanes(struct intel_encoder *encoder)
@@ -421,6 +423,7 @@ static void gen11_dsi_power_up_lanes(struct intel_encoder *encoder)
 
 static void gen11_dsi_config_phy_lanes_sequence(struct intel_encoder *encoder)
 {
+	struct intel_display *display = to_intel_display(encoder);
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum phy phy;
@@ -429,32 +432,33 @@ static void gen11_dsi_config_phy_lanes_sequence(struct intel_encoder *encoder)
 
 	/* Step 4b(i) set loadgen select for transmit and aux lanes */
 	for_each_dsi_phy(phy, intel_dsi->phys) {
-		intel_de_rmw(dev_priv, ICL_PORT_TX_DW4_AUX(phy), LOADGEN_SELECT, 0);
+		intel_de_rmw(display, ICL_PORT_TX_DW4_AUX(phy),
+			     LOADGEN_SELECT, 0);
 		for (lane = 0; lane <= 3; lane++)
-			intel_de_rmw(dev_priv, ICL_PORT_TX_DW4_LN(lane, phy),
+			intel_de_rmw(display, ICL_PORT_TX_DW4_LN(lane, phy),
 				     LOADGEN_SELECT, lane != 2 ? LOADGEN_SELECT : 0);
 	}
 
 	/* Step 4b(ii) set latency optimization for transmit and aux lanes */
 	for_each_dsi_phy(phy, intel_dsi->phys) {
-		intel_de_rmw(dev_priv, ICL_PORT_TX_DW2_AUX(phy),
+		intel_de_rmw(display, ICL_PORT_TX_DW2_AUX(phy),
 			     FRC_LATENCY_OPTIM_MASK, FRC_LATENCY_OPTIM_VAL(0x5));
-		tmp = intel_de_read(dev_priv, ICL_PORT_TX_DW2_LN(0, phy));
+		tmp = intel_de_read(display, ICL_PORT_TX_DW2_LN(0, phy));
 		tmp &= ~FRC_LATENCY_OPTIM_MASK;
 		tmp |= FRC_LATENCY_OPTIM_VAL(0x5);
-		intel_de_write(dev_priv, ICL_PORT_TX_DW2_GRP(phy), tmp);
+		intel_de_write(display, ICL_PORT_TX_DW2_GRP(phy), tmp);
 
 		/* For EHL, TGL, set latency optimization for PCS_DW1 lanes */
 		if (IS_JASPERLAKE(dev_priv) || IS_ELKHARTLAKE(dev_priv) ||
-		    (DISPLAY_VER(dev_priv) >= 12)) {
-			intel_de_rmw(dev_priv, ICL_PORT_PCS_DW1_AUX(phy),
+		    (DISPLAY_VER(display) >= 12)) {
+			intel_de_rmw(display, ICL_PORT_PCS_DW1_AUX(phy),
 				     LATENCY_OPTIM_MASK, LATENCY_OPTIM_VAL(0));
 
-			tmp = intel_de_read(dev_priv,
+			tmp = intel_de_read(display,
 					    ICL_PORT_PCS_DW1_LN(0, phy));
 			tmp &= ~LATENCY_OPTIM_MASK;
 			tmp |= LATENCY_OPTIM_VAL(0x1);
-			intel_de_write(dev_priv, ICL_PORT_PCS_DW1_GRP(phy),
+			intel_de_write(display, ICL_PORT_PCS_DW1_GRP(phy),
 				       tmp);
 		}
 	}
@@ -463,17 +467,17 @@ static void gen11_dsi_config_phy_lanes_sequence(struct intel_encoder *encoder)
 
 static void gen11_dsi_voltage_swing_program_seq(struct intel_encoder *encoder)
 {
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct intel_display *display = to_intel_display(encoder);
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	u32 tmp;
 	enum phy phy;
 
 	/* clear common keeper enable bit */
 	for_each_dsi_phy(phy, intel_dsi->phys) {
-		tmp = intel_de_read(dev_priv, ICL_PORT_PCS_DW1_LN(0, phy));
+		tmp = intel_de_read(display, ICL_PORT_PCS_DW1_LN(0, phy));
 		tmp &= ~COMMON_KEEPER_EN;
-		intel_de_write(dev_priv, ICL_PORT_PCS_DW1_GRP(phy), tmp);
-		intel_de_rmw(dev_priv, ICL_PORT_PCS_DW1_AUX(phy), COMMON_KEEPER_EN, 0);
+		intel_de_write(display, ICL_PORT_PCS_DW1_GRP(phy), tmp);
+		intel_de_rmw(display, ICL_PORT_PCS_DW1_AUX(phy), COMMON_KEEPER_EN, 0);
 	}
 
 	/*
@@ -482,14 +486,15 @@ static void gen11_dsi_voltage_swing_program_seq(struct intel_encoder *encoder)
 	 * as part of lane phy sequence configuration
 	 */
 	for_each_dsi_phy(phy, intel_dsi->phys)
-		intel_de_rmw(dev_priv, ICL_PORT_CL_DW5(phy), 0, SUS_CLOCK_CONFIG);
+		intel_de_rmw(display, ICL_PORT_CL_DW5(phy), 0,
+			     SUS_CLOCK_CONFIG);
 
 	/* Clear training enable to change swing values */
 	for_each_dsi_phy(phy, intel_dsi->phys) {
-		tmp = intel_de_read(dev_priv, ICL_PORT_TX_DW5_LN(0, phy));
+		tmp = intel_de_read(display, ICL_PORT_TX_DW5_LN(0, phy));
 		tmp &= ~TX_TRAINING_EN;
-		intel_de_write(dev_priv, ICL_PORT_TX_DW5_GRP(phy), tmp);
-		intel_de_rmw(dev_priv, ICL_PORT_TX_DW5_AUX(phy), TX_TRAINING_EN, 0);
+		intel_de_write(display, ICL_PORT_TX_DW5_GRP(phy), tmp);
+		intel_de_rmw(display, ICL_PORT_TX_DW5_AUX(phy), TX_TRAINING_EN, 0);
 	}
 
 	/* Program swing and de-emphasis */
@@ -497,26 +502,26 @@ static void gen11_dsi_voltage_swing_program_seq(struct intel_encoder *encoder)
 
 	/* Set training enable to trigger update */
 	for_each_dsi_phy(phy, intel_dsi->phys) {
-		tmp = intel_de_read(dev_priv, ICL_PORT_TX_DW5_LN(0, phy));
+		tmp = intel_de_read(display, ICL_PORT_TX_DW5_LN(0, phy));
 		tmp |= TX_TRAINING_EN;
-		intel_de_write(dev_priv, ICL_PORT_TX_DW5_GRP(phy), tmp);
-		intel_de_rmw(dev_priv, ICL_PORT_TX_DW5_AUX(phy), 0, TX_TRAINING_EN);
+		intel_de_write(display, ICL_PORT_TX_DW5_GRP(phy), tmp);
+		intel_de_rmw(display, ICL_PORT_TX_DW5_AUX(phy), 0, TX_TRAINING_EN);
 	}
 }
 
 static void gen11_dsi_enable_ddi_buffer(struct intel_encoder *encoder)
 {
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct intel_display *display = to_intel_display(encoder);
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum port port;
 
 	for_each_dsi_port(port, intel_dsi->ports) {
-		intel_de_rmw(dev_priv, DDI_BUF_CTL(port), 0, DDI_BUF_CTL_ENABLE);
+		intel_de_rmw(display, DDI_BUF_CTL(port), 0, DDI_BUF_CTL_ENABLE);
 
-		if (wait_for_us(!(intel_de_read(dev_priv, DDI_BUF_CTL(port)) &
+		if (wait_for_us(!(intel_de_read(display, DDI_BUF_CTL(port)) &
 				  DDI_BUF_IS_IDLE),
 				  500))
-			drm_err(&dev_priv->drm, "DDI port:%c buffer idle\n",
+			drm_err(display->drm, "DDI port:%c buffer idle\n",
 				port_name(port));
 	}
 }
@@ -525,6 +530,7 @@ static void
 gen11_dsi_setup_dphy_timings(struct intel_encoder *encoder,
 			     const struct intel_crtc_state *crtc_state)
 {
+	struct intel_display *display = to_intel_display(encoder);
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum port port;
@@ -532,12 +538,12 @@ gen11_dsi_setup_dphy_timings(struct intel_encoder *encoder,
 
 	/* Program DPHY clock lanes timings */
 	for_each_dsi_port(port, intel_dsi->ports)
-		intel_de_write(dev_priv, DPHY_CLK_TIMING_PARAM(port),
+		intel_de_write(display, DPHY_CLK_TIMING_PARAM(port),
 			       intel_dsi->dphy_reg);
 
 	/* Program DPHY data lanes timings */
 	for_each_dsi_port(port, intel_dsi->ports)
-		intel_de_write(dev_priv, DPHY_DATA_TIMING_PARAM(port),
+		intel_de_write(display, DPHY_DATA_TIMING_PARAM(port),
 			       intel_dsi->dphy_data_lane_reg);
 
 	/*
@@ -546,10 +552,10 @@ gen11_dsi_setup_dphy_timings(struct intel_encoder *encoder,
 	 * a value '0' inside TA_PARAM_REGISTERS otherwise
 	 * leave all fields at HW default values.
 	 */
-	if (DISPLAY_VER(dev_priv) == 11) {
+	if (DISPLAY_VER(display) == 11) {
 		if (afe_clk(encoder, crtc_state) <= 800000) {
 			for_each_dsi_port(port, intel_dsi->ports)
-				intel_de_rmw(dev_priv, DPHY_TA_TIMING_PARAM(port),
+				intel_de_rmw(display, DPHY_TA_TIMING_PARAM(port),
 					     TA_SURE_MASK,
 					     TA_SURE_OVERRIDE | TA_SURE(0));
 		}
@@ -557,7 +563,7 @@ gen11_dsi_setup_dphy_timings(struct intel_encoder *encoder,
 
 	if (IS_JASPERLAKE(dev_priv) || IS_ELKHARTLAKE(dev_priv)) {
 		for_each_dsi_phy(phy, intel_dsi->phys)
-			intel_de_rmw(dev_priv, ICL_DPHY_CHKN(phy),
+			intel_de_rmw(display, ICL_DPHY_CHKN(phy),
 				     0, ICL_DPHY_CHKN_AFE_OVER_PPI_STRAP);
 	}
 }
@@ -566,30 +572,30 @@ static void
 gen11_dsi_setup_timings(struct intel_encoder *encoder,
 			const struct intel_crtc_state *crtc_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct intel_display *display = to_intel_display(encoder);
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum port port;
 
 	/* Program T-INIT master registers */
 	for_each_dsi_port(port, intel_dsi->ports)
-		intel_de_rmw(dev_priv, ICL_DSI_T_INIT_MASTER(port),
+		intel_de_rmw(display, ICL_DSI_T_INIT_MASTER(port),
 			     DSI_T_INIT_MASTER_MASK, intel_dsi->init_count);
 
 	/* shadow register inside display core */
 	for_each_dsi_port(port, intel_dsi->ports)
-		intel_de_write(dev_priv, DSI_CLK_TIMING_PARAM(port),
+		intel_de_write(display, DSI_CLK_TIMING_PARAM(port),
 			       intel_dsi->dphy_reg);
 
 	/* shadow register inside display core */
 	for_each_dsi_port(port, intel_dsi->ports)
-		intel_de_write(dev_priv, DSI_DATA_TIMING_PARAM(port),
+		intel_de_write(display, DSI_DATA_TIMING_PARAM(port),
 			       intel_dsi->dphy_data_lane_reg);
 
 	/* shadow register inside display core */
-	if (DISPLAY_VER(dev_priv) == 11) {
+	if (DISPLAY_VER(display) == 11) {
 		if (afe_clk(encoder, crtc_state) <= 800000) {
 			for_each_dsi_port(port, intel_dsi->ports) {
-				intel_de_rmw(dev_priv, DSI_TA_TIMING_PARAM(port),
+				intel_de_rmw(display, DSI_TA_TIMING_PARAM(port),
 					     TA_SURE_MASK,
 					     TA_SURE_OVERRIDE | TA_SURE(0));
 			}
@@ -599,45 +605,45 @@ gen11_dsi_setup_timings(struct intel_encoder *encoder,
 
 static void gen11_dsi_gate_clocks(struct intel_encoder *encoder)
 {
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct intel_display *display = to_intel_display(encoder);
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	u32 tmp;
 	enum phy phy;
 
-	mutex_lock(&dev_priv->display.dpll.lock);
-	tmp = intel_de_read(dev_priv, ICL_DPCLKA_CFGCR0);
+	mutex_lock(&display->dpll.lock);
+	tmp = intel_de_read(display, ICL_DPCLKA_CFGCR0);
 	for_each_dsi_phy(phy, intel_dsi->phys)
 		tmp |= ICL_DPCLKA_CFGCR0_DDI_CLK_OFF(phy);
 
-	intel_de_write(dev_priv, ICL_DPCLKA_CFGCR0, tmp);
-	mutex_unlock(&dev_priv->display.dpll.lock);
+	intel_de_write(display, ICL_DPCLKA_CFGCR0, tmp);
+	mutex_unlock(&display->dpll.lock);
 }
 
 static void gen11_dsi_ungate_clocks(struct intel_encoder *encoder)
 {
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct intel_display *display = to_intel_display(encoder);
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	u32 tmp;
 	enum phy phy;
 
-	mutex_lock(&dev_priv->display.dpll.lock);
-	tmp = intel_de_read(dev_priv, ICL_DPCLKA_CFGCR0);
+	mutex_lock(&display->dpll.lock);
+	tmp = intel_de_read(display, ICL_DPCLKA_CFGCR0);
 	for_each_dsi_phy(phy, intel_dsi->phys)
 		tmp &= ~ICL_DPCLKA_CFGCR0_DDI_CLK_OFF(phy);
 
-	intel_de_write(dev_priv, ICL_DPCLKA_CFGCR0, tmp);
-	mutex_unlock(&dev_priv->display.dpll.lock);
+	intel_de_write(display, ICL_DPCLKA_CFGCR0, tmp);
+	mutex_unlock(&display->dpll.lock);
 }
 
 static bool gen11_dsi_is_clock_enabled(struct intel_encoder *encoder)
 {
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct intel_display *display = to_intel_display(encoder);
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	bool clock_enabled = false;
 	enum phy phy;
 	u32 tmp;
 
-	tmp = intel_de_read(dev_priv, ICL_DPCLKA_CFGCR0);
+	tmp = intel_de_read(display, ICL_DPCLKA_CFGCR0);
 
 	for_each_dsi_phy(phy, intel_dsi->phys) {
 		if (!(tmp & ICL_DPCLKA_CFGCR0_DDI_CLK_OFF(phy)))
@@ -650,36 +656,36 @@ static bool gen11_dsi_is_clock_enabled(struct intel_encoder *encoder)
 static void gen11_dsi_map_pll(struct intel_encoder *encoder,
 			      const struct intel_crtc_state *crtc_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct intel_display *display = to_intel_display(encoder);
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	struct intel_shared_dpll *pll = crtc_state->shared_dpll;
 	enum phy phy;
 	u32 val;
 
-	mutex_lock(&dev_priv->display.dpll.lock);
+	mutex_lock(&display->dpll.lock);
 
-	val = intel_de_read(dev_priv, ICL_DPCLKA_CFGCR0);
+	val = intel_de_read(display, ICL_DPCLKA_CFGCR0);
 	for_each_dsi_phy(phy, intel_dsi->phys) {
 		val &= ~ICL_DPCLKA_CFGCR0_DDI_CLK_SEL_MASK(phy);
 		val |= ICL_DPCLKA_CFGCR0_DDI_CLK_SEL(pll->info->id, phy);
 	}
-	intel_de_write(dev_priv, ICL_DPCLKA_CFGCR0, val);
+	intel_de_write(display, ICL_DPCLKA_CFGCR0, val);
 
 	for_each_dsi_phy(phy, intel_dsi->phys) {
 		val &= ~ICL_DPCLKA_CFGCR0_DDI_CLK_OFF(phy);
 	}
-	intel_de_write(dev_priv, ICL_DPCLKA_CFGCR0, val);
+	intel_de_write(display, ICL_DPCLKA_CFGCR0, val);
 
-	intel_de_posting_read(dev_priv, ICL_DPCLKA_CFGCR0);
+	intel_de_posting_read(display, ICL_DPCLKA_CFGCR0);
 
-	mutex_unlock(&dev_priv->display.dpll.lock);
+	mutex_unlock(&display->dpll.lock);
 }
 
 static void
 gen11_dsi_configure_transcoder(struct intel_encoder *encoder,
 			       const struct intel_crtc_state *pipe_config)
 {
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct intel_display *display = to_intel_display(encoder);
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	struct intel_crtc *crtc = to_intel_crtc(pipe_config->uapi.crtc);
 	enum pipe pipe = crtc->pipe;
@@ -689,7 +695,7 @@ gen11_dsi_configure_transcoder(struct intel_encoder *encoder,
 
 	for_each_dsi_port(port, intel_dsi->ports) {
 		dsi_trans = dsi_port_to_transcoder(port);
-		tmp = intel_de_read(dev_priv, DSI_TRANS_FUNC_CONF(dsi_trans));
+		tmp = intel_de_read(display, DSI_TRANS_FUNC_CONF(dsi_trans));
 
 		if (intel_dsi->eotp_pkt)
 			tmp &= ~EOTP_DISABLED;
@@ -745,7 +751,7 @@ gen11_dsi_configure_transcoder(struct intel_encoder *encoder,
 			}
 		}
 
-		if (DISPLAY_VER(dev_priv) >= 12) {
+		if (DISPLAY_VER(display) >= 12) {
 			if (is_vid_mode(intel_dsi))
 				tmp |= BLANKING_PACKET_ENABLE;
 		}
@@ -778,15 +784,15 @@ gen11_dsi_configure_transcoder(struct intel_encoder *encoder,
 			tmp |= TE_SOURCE_GPIO;
 		}
 
-		intel_de_write(dev_priv, DSI_TRANS_FUNC_CONF(dsi_trans), tmp);
+		intel_de_write(display, DSI_TRANS_FUNC_CONF(dsi_trans), tmp);
 	}
 
 	/* enable port sync mode if dual link */
 	if (intel_dsi->dual_link) {
 		for_each_dsi_port(port, intel_dsi->ports) {
 			dsi_trans = dsi_port_to_transcoder(port);
-			intel_de_rmw(dev_priv,
-				     TRANS_DDI_FUNC_CTL2(dev_priv, dsi_trans),
+			intel_de_rmw(display,
+				     TRANS_DDI_FUNC_CTL2(display, dsi_trans),
 				     0, PORT_SYNC_MODE_ENABLE);
 		}
 
@@ -798,10 +804,10 @@ gen11_dsi_configure_transcoder(struct intel_encoder *encoder,
 		dsi_trans = dsi_port_to_transcoder(port);
 
 		/* select data lane width */
-		tmp = intel_de_read(dev_priv,
-				    TRANS_DDI_FUNC_CTL(dev_priv, dsi_trans));
-		tmp &= ~DDI_PORT_WIDTH_MASK;
-		tmp |= DDI_PORT_WIDTH(intel_dsi->lane_count);
+		tmp = intel_de_read(display,
+				    TRANS_DDI_FUNC_CTL(display, dsi_trans));
+		tmp &= ~TRANS_DDI_PORT_WIDTH_MASK;
+		tmp |= TRANS_DDI_PORT_WIDTH(intel_dsi->lane_count);
 
 		/* select input pipe */
 		tmp &= ~TRANS_DDI_EDP_INPUT_MASK;
@@ -825,16 +831,16 @@ gen11_dsi_configure_transcoder(struct intel_encoder *encoder,
 
 		/* enable DDI buffer */
 		tmp |= TRANS_DDI_FUNC_ENABLE;
-		intel_de_write(dev_priv,
-			       TRANS_DDI_FUNC_CTL(dev_priv, dsi_trans), tmp);
+		intel_de_write(display,
+			       TRANS_DDI_FUNC_CTL(display, dsi_trans), tmp);
 	}
 
 	/* wait for link ready */
 	for_each_dsi_port(port, intel_dsi->ports) {
 		dsi_trans = dsi_port_to_transcoder(port);
-		if (wait_for_us((intel_de_read(dev_priv, DSI_TRANS_FUNC_CONF(dsi_trans)) &
+		if (wait_for_us((intel_de_read(display, DSI_TRANS_FUNC_CONF(dsi_trans)) &
 				 LINK_READY), 2500))
-			drm_err(&dev_priv->drm, "DSI link not ready\n");
+			drm_err(display->drm, "DSI link not ready\n");
 	}
 }
 
@@ -842,7 +848,7 @@ static void
 gen11_dsi_set_transcoder_timings(struct intel_encoder *encoder,
 				 const struct intel_crtc_state *crtc_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct intel_display *display = to_intel_display(encoder);
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	const struct drm_display_mode *adjusted_mode =
 		&crtc_state->hw.adjusted_mode;
@@ -909,17 +915,17 @@ gen11_dsi_set_transcoder_timings(struct intel_encoder *encoder,
 
 	/* minimum hactive as per bspec: 256 pixels */
 	if (adjusted_mode->crtc_hdisplay < 256)
-		drm_err(&dev_priv->drm, "hactive is less then 256 pixels\n");
+		drm_err(display->drm, "hactive is less then 256 pixels\n");
 
 	/* if RGB666 format, then hactive must be multiple of 4 pixels */
 	if (intel_dsi->pixel_format == MIPI_DSI_FMT_RGB666 && hactive % 4 != 0)
-		drm_err(&dev_priv->drm,
+		drm_err(display->drm,
 			"hactive pixels are not multiple of 4\n");
 
 	/* program TRANS_HTOTAL register */
 	for_each_dsi_port(port, intel_dsi->ports) {
 		dsi_trans = dsi_port_to_transcoder(port);
-		intel_de_write(dev_priv, TRANS_HTOTAL(dev_priv, dsi_trans),
+		intel_de_write(display, TRANS_HTOTAL(display, dsi_trans),
 			       HACTIVE(hactive - 1) | HTOTAL(htotal - 1));
 	}
 
@@ -928,12 +934,12 @@ gen11_dsi_set_transcoder_timings(struct intel_encoder *encoder,
 		if (intel_dsi->video_mode == NON_BURST_SYNC_PULSE) {
 			/* BSPEC: hsync size should be atleast 16 pixels */
 			if (hsync_size < 16)
-				drm_err(&dev_priv->drm,
+				drm_err(display->drm,
 					"hsync size < 16 pixels\n");
 		}
 
 		if (hback_porch < 16)
-			drm_err(&dev_priv->drm, "hback porch < 16 pixels\n");
+			drm_err(display->drm, "hback porch < 16 pixels\n");
 
 		if (intel_dsi->dual_link) {
 			hsync_start /= 2;
@@ -942,8 +948,8 @@ gen11_dsi_set_transcoder_timings(struct intel_encoder *encoder,
 
 		for_each_dsi_port(port, intel_dsi->ports) {
 			dsi_trans = dsi_port_to_transcoder(port);
-			intel_de_write(dev_priv,
-				       TRANS_HSYNC(dev_priv, dsi_trans),
+			intel_de_write(display,
+				       TRANS_HSYNC(display, dsi_trans),
 				       HSYNC_START(hsync_start - 1) | HSYNC_END(hsync_end - 1));
 		}
 	}
@@ -957,22 +963,22 @@ gen11_dsi_set_transcoder_timings(struct intel_encoder *encoder,
 		 * struct drm_display_mode.
 		 * For interlace mode: program required pixel minus 2
 		 */
-		intel_de_write(dev_priv, TRANS_VTOTAL(dev_priv, dsi_trans),
+		intel_de_write(display, TRANS_VTOTAL(display, dsi_trans),
 			       VACTIVE(vactive - 1) | VTOTAL(vtotal - 1));
 	}
 
 	if (vsync_end < vsync_start || vsync_end > vtotal)
-		drm_err(&dev_priv->drm, "Invalid vsync_end value\n");
+		drm_err(display->drm, "Invalid vsync_end value\n");
 
 	if (vsync_start < vactive)
-		drm_err(&dev_priv->drm, "vsync_start less than vactive\n");
+		drm_err(display->drm, "vsync_start less than vactive\n");
 
 	/* program TRANS_VSYNC register for video mode only */
 	if (is_vid_mode(intel_dsi)) {
 		for_each_dsi_port(port, intel_dsi->ports) {
 			dsi_trans = dsi_port_to_transcoder(port);
-			intel_de_write(dev_priv,
-				       TRANS_VSYNC(dev_priv, dsi_trans),
+			intel_de_write(display,
+				       TRANS_VSYNC(display, dsi_trans),
 				       VSYNC_START(vsync_start - 1) | VSYNC_END(vsync_end - 1));
 		}
 	}
@@ -986,8 +992,8 @@ gen11_dsi_set_transcoder_timings(struct intel_encoder *encoder,
 	if (is_vid_mode(intel_dsi)) {
 		for_each_dsi_port(port, intel_dsi->ports) {
 			dsi_trans = dsi_port_to_transcoder(port);
-			intel_de_write(dev_priv,
-				       TRANS_VSYNCSHIFT(dev_priv, dsi_trans),
+			intel_de_write(display,
+				       TRANS_VSYNCSHIFT(display, dsi_trans),
 				       vsync_shift);
 		}
 	}
@@ -998,11 +1004,11 @@ gen11_dsi_set_transcoder_timings(struct intel_encoder *encoder,
 	 * FIXME get rid of these local hacks and do it right,
 	 * this will not handle eg. delayed vblank correctly.
 	 */
-	if (DISPLAY_VER(dev_priv) >= 12) {
+	if (DISPLAY_VER(display) >= 12) {
 		for_each_dsi_port(port, intel_dsi->ports) {
 			dsi_trans = dsi_port_to_transcoder(port);
-			intel_de_write(dev_priv,
-				       TRANS_VBLANK(dev_priv, dsi_trans),
+			intel_de_write(display,
+				       TRANS_VBLANK(display, dsi_trans),
 				       VBLANK_START(vactive - 1) | VBLANK_END(vtotal - 1));
 		}
 	}
@@ -1010,20 +1016,20 @@ gen11_dsi_set_transcoder_timings(struct intel_encoder *encoder,
 
 static void gen11_dsi_enable_transcoder(struct intel_encoder *encoder)
 {
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct intel_display *display = to_intel_display(encoder);
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum port port;
 	enum transcoder dsi_trans;
 
 	for_each_dsi_port(port, intel_dsi->ports) {
 		dsi_trans = dsi_port_to_transcoder(port);
-		intel_de_rmw(dev_priv, TRANSCONF(dev_priv, dsi_trans), 0,
+		intel_de_rmw(display, TRANSCONF(display, dsi_trans), 0,
 			     TRANSCONF_ENABLE);
 
 		/* wait for transcoder to be enabled */
-		if (intel_de_wait_for_set(dev_priv, TRANSCONF(dev_priv, dsi_trans),
+		if (intel_de_wait_for_set(display, TRANSCONF(display, dsi_trans),
 					  TRANSCONF_STATE_ENABLE, 10))
-			drm_err(&dev_priv->drm,
+			drm_err(display->drm,
 				"DSI transcoder not enabled\n");
 	}
 }
@@ -1031,7 +1037,7 @@ static void gen11_dsi_enable_transcoder(struct intel_encoder *encoder)
 static void gen11_dsi_setup_timeouts(struct intel_encoder *encoder,
 				     const struct intel_crtc_state *crtc_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct intel_display *display = to_intel_display(encoder);
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum port port;
 	enum transcoder dsi_trans;
@@ -1055,21 +1061,21 @@ static void gen11_dsi_setup_timeouts(struct intel_encoder *encoder,
 		dsi_trans = dsi_port_to_transcoder(port);
 
 		/* program hst_tx_timeout */
-		intel_de_rmw(dev_priv, DSI_HSTX_TO(dsi_trans),
+		intel_de_rmw(display, DSI_HSTX_TO(dsi_trans),
 			     HSTX_TIMEOUT_VALUE_MASK,
 			     HSTX_TIMEOUT_VALUE(hs_tx_timeout));
 
 		/* FIXME: DSI_CALIB_TO */
 
 		/* program lp_rx_host timeout */
-		intel_de_rmw(dev_priv, DSI_LPRX_HOST_TO(dsi_trans),
+		intel_de_rmw(display, DSI_LPRX_HOST_TO(dsi_trans),
 			     LPRX_TIMEOUT_VALUE_MASK,
 			     LPRX_TIMEOUT_VALUE(lp_rx_timeout));
 
 		/* FIXME: DSI_PWAIT_TO */
 
 		/* program turn around timeout */
-		intel_de_rmw(dev_priv, DSI_TA_TO(dsi_trans),
+		intel_de_rmw(display, DSI_TA_TO(dsi_trans),
 			     TA_TIMEOUT_VALUE_MASK,
 			     TA_TIMEOUT_VALUE(ta_timeout));
 	}
@@ -1078,7 +1084,7 @@ static void gen11_dsi_setup_timeouts(struct intel_encoder *encoder,
 static void gen11_dsi_config_util_pin(struct intel_encoder *encoder,
 				      bool enable)
 {
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct intel_display *display = to_intel_display(encoder);
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	u32 tmp;
 
@@ -1090,7 +1096,7 @@ static void gen11_dsi_config_util_pin(struct intel_encoder *encoder,
 	if (is_vid_mode(intel_dsi) || (intel_dsi->ports & BIT(PORT_B)))
 		return;
 
-	tmp = intel_de_read(dev_priv, UTIL_PIN_CTL);
+	tmp = intel_de_read(display, UTIL_PIN_CTL);
 
 	if (enable) {
 		tmp |= UTIL_PIN_DIRECTION_INPUT;
@@ -1098,7 +1104,7 @@ static void gen11_dsi_config_util_pin(struct intel_encoder *encoder,
 	} else {
 		tmp &= ~UTIL_PIN_ENABLE;
 	}
-	intel_de_write(dev_priv, UTIL_PIN_CTL, tmp);
+	intel_de_write(display, UTIL_PIN_CTL, tmp);
 }
 
 static void
@@ -1136,7 +1142,7 @@ gen11_dsi_enable_port_and_phy(struct intel_encoder *encoder,
 
 static void gen11_dsi_powerup_panel(struct intel_encoder *encoder)
 {
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct intel_display *display = to_intel_display(encoder);
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	struct mipi_dsi_device *dsi;
 	enum port port;
@@ -1152,14 +1158,14 @@ static void gen11_dsi_powerup_panel(struct intel_encoder *encoder)
 		 * FIXME: This uses the number of DW's currently in the payload
 		 * receive queue. This is probably not what we want here.
 		 */
-		tmp = intel_de_read(dev_priv, DSI_CMD_RXCTL(dsi_trans));
+		tmp = intel_de_read(display, DSI_CMD_RXCTL(dsi_trans));
 		tmp &= NUMBER_RX_PLOAD_DW_MASK;
 		/* multiply "Number Rx Payload DW" by 4 to get max value */
 		tmp = tmp * 4;
 		dsi = intel_dsi->dsi_hosts[port]->device;
 		ret = mipi_dsi_set_maximum_return_packet_size(dsi, tmp);
 		if (ret < 0)
-			drm_err(&dev_priv->drm,
+			drm_err(display->drm,
 				"error setting max return pkt size%d\n", tmp);
 	}
 
@@ -1219,10 +1225,10 @@ static void gen11_dsi_pre_enable(struct intel_atomic_state *state,
 static void icl_apply_kvmr_pipe_a_wa(struct intel_encoder *encoder,
 				     enum pipe pipe, bool enable)
 {
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct intel_display *display = to_intel_display(encoder);
 
-	if (DISPLAY_VER(dev_priv) == 11 && pipe == PIPE_B)
-		intel_de_rmw(dev_priv, CHICKEN_PAR1_1,
+	if (DISPLAY_VER(display) == 11 && pipe == PIPE_B)
+		intel_de_rmw(display, CHICKEN_PAR1_1,
 			     IGNORE_KVMR_PIPE_A,
 			     enable ? IGNORE_KVMR_PIPE_A : 0);
 }
@@ -1235,13 +1241,13 @@ static void icl_apply_kvmr_pipe_a_wa(struct intel_encoder *encoder,
  */
 static void adlp_set_lp_hs_wakeup_gb(struct intel_encoder *encoder)
 {
-	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
+	struct intel_display *display = to_intel_display(encoder);
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum port port;
 
-	if (DISPLAY_VER(i915) == 13) {
+	if (DISPLAY_VER(display) == 13) {
 		for_each_dsi_port(port, intel_dsi->ports)
-			intel_de_rmw(i915, TGL_DSI_CHKN_REG(port),
+			intel_de_rmw(display, TGL_DSI_CHKN_REG(port),
 				     TGL_DSI_CHKN_LSHS_GB_MASK,
 				     TGL_DSI_CHKN_LSHS_GB(4));
 	}
@@ -1275,7 +1281,7 @@ static void gen11_dsi_enable(struct intel_atomic_state *state,
 
 static void gen11_dsi_disable_transcoder(struct intel_encoder *encoder)
 {
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct intel_display *display = to_intel_display(encoder);
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum port port;
 	enum transcoder dsi_trans;
@@ -1284,13 +1290,13 @@ static void gen11_dsi_disable_transcoder(struct intel_encoder *encoder)
 		dsi_trans = dsi_port_to_transcoder(port);
 
 		/* disable transcoder */
-		intel_de_rmw(dev_priv, TRANSCONF(dev_priv, dsi_trans),
+		intel_de_rmw(display, TRANSCONF(display, dsi_trans),
 			     TRANSCONF_ENABLE, 0);
 
 		/* wait for transcoder to be disabled */
-		if (intel_de_wait_for_clear(dev_priv, TRANSCONF(dev_priv, dsi_trans),
+		if (intel_de_wait_for_clear(display, TRANSCONF(display, dsi_trans),
 					    TRANSCONF_STATE_ENABLE, 50))
-			drm_err(&dev_priv->drm,
+			drm_err(display->drm,
 				"DSI trancoder not disabled\n");
 	}
 }
@@ -1307,7 +1313,7 @@ static void gen11_dsi_powerdown_panel(struct intel_encoder *encoder)
 
 static void gen11_dsi_deconfigure_trancoder(struct intel_encoder *encoder)
 {
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct intel_display *display = to_intel_display(encoder);
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum port port;
 	enum transcoder dsi_trans;
@@ -1316,29 +1322,29 @@ static void gen11_dsi_deconfigure_trancoder(struct intel_encoder *encoder)
 	/* disable periodic update mode */
 	if (is_cmd_mode(intel_dsi)) {
 		for_each_dsi_port(port, intel_dsi->ports)
-			intel_de_rmw(dev_priv, DSI_CMD_FRMCTL(port),
+			intel_de_rmw(display, DSI_CMD_FRMCTL(port),
 				     DSI_PERIODIC_FRAME_UPDATE_ENABLE, 0);
 	}
 
 	/* put dsi link in ULPS */
 	for_each_dsi_port(port, intel_dsi->ports) {
 		dsi_trans = dsi_port_to_transcoder(port);
-		tmp = intel_de_read(dev_priv, DSI_LP_MSG(dsi_trans));
+		tmp = intel_de_read(display, DSI_LP_MSG(dsi_trans));
 		tmp |= LINK_ENTER_ULPS;
 		tmp &= ~LINK_ULPS_TYPE_LP11;
-		intel_de_write(dev_priv, DSI_LP_MSG(dsi_trans), tmp);
+		intel_de_write(display, DSI_LP_MSG(dsi_trans), tmp);
 
-		if (wait_for_us((intel_de_read(dev_priv, DSI_LP_MSG(dsi_trans)) &
+		if (wait_for_us((intel_de_read(display, DSI_LP_MSG(dsi_trans)) &
 				 LINK_IN_ULPS),
 				10))
-			drm_err(&dev_priv->drm, "DSI link not in ULPS\n");
+			drm_err(display->drm, "DSI link not in ULPS\n");
 	}
 
 	/* disable ddi function */
 	for_each_dsi_port(port, intel_dsi->ports) {
 		dsi_trans = dsi_port_to_transcoder(port);
-		intel_de_rmw(dev_priv,
-			     TRANS_DDI_FUNC_CTL(dev_priv, dsi_trans),
+		intel_de_rmw(display,
+			     TRANS_DDI_FUNC_CTL(display, dsi_trans),
 			     TRANS_DDI_FUNC_ENABLE, 0);
 	}
 
@@ -1346,8 +1352,8 @@ static void gen11_dsi_deconfigure_trancoder(struct intel_encoder *encoder)
 	if (intel_dsi->dual_link) {
 		for_each_dsi_port(port, intel_dsi->ports) {
 			dsi_trans = dsi_port_to_transcoder(port);
-			intel_de_rmw(dev_priv,
-				     TRANS_DDI_FUNC_CTL2(dev_priv, dsi_trans),
+			intel_de_rmw(display,
+				     TRANS_DDI_FUNC_CTL2(display, dsi_trans),
 				     PORT_SYNC_MODE_ENABLE, 0);
 		}
 	}
@@ -1355,18 +1361,18 @@ static void gen11_dsi_deconfigure_trancoder(struct intel_encoder *encoder)
 
 static void gen11_dsi_disable_port(struct intel_encoder *encoder)
 {
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct intel_display *display = to_intel_display(encoder);
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum port port;
 
 	gen11_dsi_ungate_clocks(encoder);
 	for_each_dsi_port(port, intel_dsi->ports) {
-		intel_de_rmw(dev_priv, DDI_BUF_CTL(port), DDI_BUF_CTL_ENABLE, 0);
+		intel_de_rmw(display, DDI_BUF_CTL(port), DDI_BUF_CTL_ENABLE, 0);
 
-		if (wait_for_us((intel_de_read(dev_priv, DDI_BUF_CTL(port)) &
+		if (wait_for_us((intel_de_read(display, DDI_BUF_CTL(port)) &
 				 DDI_BUF_IS_IDLE),
 				 8))
-			drm_err(&dev_priv->drm,
+			drm_err(display->drm,
 				"DDI port:%c buffer not idle\n",
 				port_name(port));
 	}
@@ -1375,6 +1381,7 @@ static void gen11_dsi_disable_port(struct intel_encoder *encoder)
 
 static void gen11_dsi_disable_io_power(struct intel_encoder *encoder)
 {
+	struct intel_display *display = to_intel_display(encoder);
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum port port;
@@ -1392,7 +1399,7 @@ static void gen11_dsi_disable_io_power(struct intel_encoder *encoder)
 
 	/* set mode to DDI */
 	for_each_dsi_port(port, intel_dsi->ports)
-		intel_de_rmw(dev_priv, ICL_DSI_IO_MODECTL(port),
+		intel_de_rmw(display, ICL_DSI_IO_MODECTL(port),
 			     COMBO_PHY_MODE_DSI, 0);
 }
 
@@ -1504,8 +1511,7 @@ static void gen11_dsi_get_timings(struct intel_encoder *encoder,
 
 static bool gen11_dsi_is_periodic_cmd_mode(struct intel_dsi *intel_dsi)
 {
-	struct drm_device *dev = intel_dsi->base.base.dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct intel_display *display = to_intel_display(&intel_dsi->base);
 	enum transcoder dsi_trans;
 	u32 val;
 
@@ -1514,7 +1520,7 @@ static bool gen11_dsi_is_periodic_cmd_mode(struct intel_dsi *intel_dsi)
 	else
 		dsi_trans = TRANSCODER_DSI_0;
 
-	val = intel_de_read(dev_priv, DSI_TRANS_FUNC_CONF(dsi_trans));
+	val = intel_de_read(display, DSI_TRANS_FUNC_CONF(dsi_trans));
 	return (val & DSI_PERIODIC_FRAME_UPDATE_ENABLE);
 }
 
@@ -1557,7 +1563,7 @@ static void gen11_dsi_get_config(struct intel_encoder *encoder,
 static void gen11_dsi_sync_state(struct intel_encoder *encoder,
 				 const struct intel_crtc_state *crtc_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct intel_display *display = to_intel_display(encoder);
 	struct intel_crtc *intel_crtc;
 	enum pipe pipe;
 
@@ -1568,9 +1574,9 @@ static void gen11_dsi_sync_state(struct intel_encoder *encoder,
 	pipe = intel_crtc->pipe;
 
 	/* wa verify 1409054076:icl,jsl,ehl */
-	if (DISPLAY_VER(dev_priv) == 11 && pipe == PIPE_B &&
-	    !(intel_de_read(dev_priv, CHICKEN_PAR1_1) & IGNORE_KVMR_PIPE_A))
-		drm_dbg_kms(&dev_priv->drm,
+	if (DISPLAY_VER(display) == 11 && pipe == PIPE_B &&
+	    !(intel_de_read(display, CHICKEN_PAR1_1) & IGNORE_KVMR_PIPE_A))
+		drm_dbg_kms(display->drm,
 			    "[ENCODER:%d:%s] BIOS left IGNORE_KVMR_PIPE_A cleared with pipe B enabled\n",
 			    encoder->base.base.id,
 			    encoder->base.name);
@@ -1579,9 +1585,9 @@ static void gen11_dsi_sync_state(struct intel_encoder *encoder,
 static int gen11_dsi_dsc_compute_config(struct intel_encoder *encoder,
 					struct intel_crtc_state *crtc_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct intel_display *display = to_intel_display(encoder);
 	struct drm_dsc_config *vdsc_cfg = &crtc_state->dsc.config;
-	int dsc_max_bpc = DISPLAY_VER(dev_priv) >= 12 ? 12 : 10;
+	int dsc_max_bpc = DISPLAY_VER(display) >= 12 ? 12 : 10;
 	bool use_dsc;
 	int ret;
 
@@ -1606,12 +1612,12 @@ static int gen11_dsi_dsc_compute_config(struct intel_encoder *encoder,
 		return ret;
 
 	/* DSI specific sanity checks on the common code */
-	drm_WARN_ON(&dev_priv->drm, vdsc_cfg->vbr_enable);
-	drm_WARN_ON(&dev_priv->drm, vdsc_cfg->simple_422);
-	drm_WARN_ON(&dev_priv->drm,
+	drm_WARN_ON(display->drm, vdsc_cfg->vbr_enable);
+	drm_WARN_ON(display->drm, vdsc_cfg->simple_422);
+	drm_WARN_ON(display->drm,
 		    vdsc_cfg->pic_width % vdsc_cfg->slice_width);
-	drm_WARN_ON(&dev_priv->drm, vdsc_cfg->slice_height < 8);
-	drm_WARN_ON(&dev_priv->drm,
+	drm_WARN_ON(display->drm, vdsc_cfg->slice_height < 8);
+	drm_WARN_ON(display->drm,
 		    vdsc_cfg->pic_height % vdsc_cfg->slice_height);
 
 	ret = drm_dsc_compute_rc_parameters(vdsc_cfg);
@@ -1627,7 +1633,7 @@ static int gen11_dsi_compute_config(struct intel_encoder *encoder,
 				    struct intel_crtc_state *pipe_config,
 				    struct drm_connector_state *conn_state)
 {
-	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
+	struct intel_display *display = to_intel_display(encoder);
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	struct intel_connector *intel_connector = intel_dsi->attached_connector;
 	struct drm_display_mode *adjusted_mode =
@@ -1661,7 +1667,7 @@ static int gen11_dsi_compute_config(struct intel_encoder *encoder,
 	pipe_config->clock_set = true;
 
 	if (gen11_dsi_dsc_compute_config(encoder, pipe_config))
-		drm_dbg_kms(&i915->drm, "Attempting to use DSC failed\n");
+		drm_dbg_kms(display->drm, "Attempting to use DSC failed\n");
 
 	pipe_config->port_clock = afe_clk(encoder, pipe_config) / 5;
 
@@ -1679,15 +1685,13 @@ static int gen11_dsi_compute_config(struct intel_encoder *encoder,
 static void gen11_dsi_get_power_domains(struct intel_encoder *encoder,
 					struct intel_crtc_state *crtc_state)
 {
-	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
-
-	get_dsi_io_power_domains(i915,
-				 enc_to_intel_dsi(encoder));
+	get_dsi_io_power_domains(enc_to_intel_dsi(encoder));
 }
 
 static bool gen11_dsi_get_hw_state(struct intel_encoder *encoder,
 				   enum pipe *pipe)
 {
+	struct intel_display *display = to_intel_display(encoder);
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum transcoder dsi_trans;
@@ -1703,8 +1707,8 @@ static bool gen11_dsi_get_hw_state(struct intel_encoder *encoder,
 
 	for_each_dsi_port(port, intel_dsi->ports) {
 		dsi_trans = dsi_port_to_transcoder(port);
-		tmp = intel_de_read(dev_priv,
-				    TRANS_DDI_FUNC_CTL(dev_priv, dsi_trans));
+		tmp = intel_de_read(display,
+				    TRANS_DDI_FUNC_CTL(display, dsi_trans));
 		switch (tmp & TRANS_DDI_EDP_INPUT_MASK) {
 		case TRANS_DDI_EDP_INPUT_A_ON:
 			*pipe = PIPE_A;
@@ -1719,11 +1723,11 @@ static bool gen11_dsi_get_hw_state(struct intel_encoder *encoder,
 			*pipe = PIPE_D;
 			break;
 		default:
-			drm_err(&dev_priv->drm, "Invalid PIPE input\n");
+			drm_err(display->drm, "Invalid PIPE input\n");
 			goto out;
 		}
 
-		tmp = intel_de_read(dev_priv, TRANSCONF(dev_priv, dsi_trans));
+		tmp = intel_de_read(display, TRANSCONF(display, dsi_trans));
 		ret = tmp & TRANSCONF_ENABLE;
 	}
 out:
@@ -1833,8 +1837,7 @@ static const struct mipi_dsi_host_ops gen11_dsi_host_ops = {
 
 static void icl_dphy_param_init(struct intel_dsi *intel_dsi)
 {
-	struct drm_device *dev = intel_dsi->base.base.dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct intel_display *display = to_intel_display(&intel_dsi->base);
 	struct intel_connector *connector = intel_dsi->attached_connector;
 	struct mipi_config *mipi_config = connector->panel.vbt.dsi.config;
 	u32 tlpx_ns;
@@ -1858,7 +1861,7 @@ static void icl_dphy_param_init(struct intel_dsi *intel_dsi)
 	 */
 	prepare_cnt = DIV_ROUND_UP(ths_prepare_ns * 4, tlpx_ns);
 	if (prepare_cnt > ICL_PREPARE_CNT_MAX) {
-		drm_dbg_kms(&dev_priv->drm, "prepare_cnt out of range (%d)\n",
+		drm_dbg_kms(display->drm, "prepare_cnt out of range (%d)\n",
 			    prepare_cnt);
 		prepare_cnt = ICL_PREPARE_CNT_MAX;
 	}
@@ -1867,7 +1870,7 @@ static void icl_dphy_param_init(struct intel_dsi *intel_dsi)
 	clk_zero_cnt = DIV_ROUND_UP(mipi_config->tclk_prepare_clkzero -
 				    ths_prepare_ns, tlpx_ns);
 	if (clk_zero_cnt > ICL_CLK_ZERO_CNT_MAX) {
-		drm_dbg_kms(&dev_priv->drm,
+		drm_dbg_kms(display->drm,
 			    "clk_zero_cnt out of range (%d)\n", clk_zero_cnt);
 		clk_zero_cnt = ICL_CLK_ZERO_CNT_MAX;
 	}
@@ -1875,7 +1878,7 @@ static void icl_dphy_param_init(struct intel_dsi *intel_dsi)
 	/* trail cnt in escape clocks*/
 	trail_cnt = DIV_ROUND_UP(tclk_trail_ns, tlpx_ns);
 	if (trail_cnt > ICL_TRAIL_CNT_MAX) {
-		drm_dbg_kms(&dev_priv->drm, "trail_cnt out of range (%d)\n",
+		drm_dbg_kms(display->drm, "trail_cnt out of range (%d)\n",
 			    trail_cnt);
 		trail_cnt = ICL_TRAIL_CNT_MAX;
 	}
@@ -1883,7 +1886,7 @@ static void icl_dphy_param_init(struct intel_dsi *intel_dsi)
 	/* tclk pre count in escape clocks */
 	tclk_pre_cnt = DIV_ROUND_UP(mipi_config->tclk_pre, tlpx_ns);
 	if (tclk_pre_cnt > ICL_TCLK_PRE_CNT_MAX) {
-		drm_dbg_kms(&dev_priv->drm,
+		drm_dbg_kms(display->drm,
 			    "tclk_pre_cnt out of range (%d)\n", tclk_pre_cnt);
 		tclk_pre_cnt = ICL_TCLK_PRE_CNT_MAX;
 	}
@@ -1892,7 +1895,7 @@ static void icl_dphy_param_init(struct intel_dsi *intel_dsi)
 	hs_zero_cnt = DIV_ROUND_UP(mipi_config->ths_prepare_hszero -
 				   ths_prepare_ns, tlpx_ns);
 	if (hs_zero_cnt > ICL_HS_ZERO_CNT_MAX) {
-		drm_dbg_kms(&dev_priv->drm, "hs_zero_cnt out of range (%d)\n",
+		drm_dbg_kms(display->drm, "hs_zero_cnt out of range (%d)\n",
 			    hs_zero_cnt);
 		hs_zero_cnt = ICL_HS_ZERO_CNT_MAX;
 	}
@@ -1900,7 +1903,7 @@ static void icl_dphy_param_init(struct intel_dsi *intel_dsi)
 	/* hs exit zero cnt in escape clocks */
 	exit_zero_cnt = DIV_ROUND_UP(mipi_config->ths_exit, tlpx_ns);
 	if (exit_zero_cnt > ICL_EXIT_ZERO_CNT_MAX) {
-		drm_dbg_kms(&dev_priv->drm,
+		drm_dbg_kms(display->drm,
 			    "exit_zero_cnt out of range (%d)\n",
 			    exit_zero_cnt);
 		exit_zero_cnt = ICL_EXIT_ZERO_CNT_MAX;
@@ -1942,10 +1945,9 @@ static void icl_dsi_add_properties(struct intel_connector *connector)
 						       fixed_mode->vdisplay);
 }
 
-void icl_dsi_init(struct drm_i915_private *dev_priv,
+void icl_dsi_init(struct intel_display *display,
 		  const struct intel_bios_encoder_data *devdata)
 {
-	struct intel_display *display = &dev_priv->display;
 	struct intel_dsi *intel_dsi;
 	struct intel_encoder *encoder;
 	struct intel_connector *intel_connector;
@@ -1973,7 +1975,8 @@ void icl_dsi_init(struct drm_i915_private *dev_priv,
 	encoder->devdata = devdata;
 
 	/* register DSI encoder with DRM subsystem */
-	drm_encoder_init(&dev_priv->drm, &encoder->base, &gen11_dsi_encoder_funcs,
+	drm_encoder_init(display->drm, &encoder->base,
+			 &gen11_dsi_encoder_funcs,
 			 DRM_MODE_ENCODER_DSI, "DSI %c", port_name(port));
 
 	encoder->pre_pll_enable = gen11_dsi_pre_pll_enable;
@@ -1998,7 +2001,8 @@ void icl_dsi_init(struct drm_i915_private *dev_priv,
 	encoder->shutdown = intel_dsi_shutdown;
 
 	/* register DSI connector with DRM subsystem */
-	drm_connector_init(&dev_priv->drm, connector, &gen11_dsi_connector_funcs,
+	drm_connector_init(display->drm, connector,
+			   &gen11_dsi_connector_funcs,
 			   DRM_MODE_CONNECTOR_DSI);
 	drm_connector_helper_add(connector, &gen11_dsi_connector_helper_funcs);
 	connector->display_info.subpixel_order = SubPixelHorizontalRGB;
@@ -2011,12 +2015,12 @@ void icl_dsi_init(struct drm_i915_private *dev_priv,
 
 	intel_bios_init_panel_late(display, &intel_connector->panel, encoder->devdata, NULL);
 
-	mutex_lock(&dev_priv->drm.mode_config.mutex);
+	mutex_lock(&display->drm->mode_config.mutex);
 	intel_panel_add_vbt_lfp_fixed_mode(intel_connector);
-	mutex_unlock(&dev_priv->drm.mode_config.mutex);
+	mutex_unlock(&display->drm->mode_config.mutex);
 
 	if (!intel_panel_preferred_fixed_mode(intel_connector)) {
-		drm_err(&dev_priv->drm, "DSI fixed mode info missing\n");
+		drm_err(display->drm, "DSI fixed mode info missing\n");
 		goto err;
 	}
 
@@ -2029,10 +2033,10 @@ void icl_dsi_init(struct drm_i915_private *dev_priv,
 	else
 		intel_dsi->ports = BIT(port);
 
-	if (drm_WARN_ON(&dev_priv->drm, intel_connector->panel.vbt.dsi.bl_ports & ~intel_dsi->ports))
+	if (drm_WARN_ON(display->drm, intel_connector->panel.vbt.dsi.bl_ports & ~intel_dsi->ports))
 		intel_connector->panel.vbt.dsi.bl_ports &= intel_dsi->ports;
 
-	if (drm_WARN_ON(&dev_priv->drm, intel_connector->panel.vbt.dsi.cabc_ports & ~intel_dsi->ports))
+	if (drm_WARN_ON(display->drm, intel_connector->panel.vbt.dsi.cabc_ports & ~intel_dsi->ports))
 		intel_connector->panel.vbt.dsi.cabc_ports &= intel_dsi->ports;
 
 	for_each_dsi_port(port, intel_dsi->ports) {
@@ -2046,7 +2050,7 @@ void icl_dsi_init(struct drm_i915_private *dev_priv,
 	}
 
 	if (!intel_dsi_vbt_init(intel_dsi, MIPI_DSI_GENERIC_PANEL_ID)) {
-		drm_dbg_kms(&dev_priv->drm, "no device found\n");
+		drm_dbg_kms(display->drm, "no device found\n");
 		goto err;
 	}
 
diff --git a/drivers/gpu/drm/i915/display/icl_dsi.h b/drivers/gpu/drm/i915/display/icl_dsi.h
index 43fa7d72eeb1..099fc50e35b4 100644
--- a/drivers/gpu/drm/i915/display/icl_dsi.h
+++ b/drivers/gpu/drm/i915/display/icl_dsi.h
@@ -6,11 +6,11 @@
 #ifndef __ICL_DSI_H__
 #define __ICL_DSI_H__
 
-struct drm_i915_private;
 struct intel_bios_encoder_data;
 struct intel_crtc_state;
+struct intel_display;
 
-void icl_dsi_init(struct drm_i915_private *dev_priv,
+void icl_dsi_init(struct intel_display *display,
 		  const struct intel_bios_encoder_data *devdata);
 void icl_dsi_frame_update(struct intel_crtc_state *crtc_state);
 
diff --git a/drivers/gpu/drm/i915/display/intel_atomic_plane.c b/drivers/gpu/drm/i915/display/intel_atomic_plane.c
index e979786aa5cf..5c2a7987cccb 100644
--- a/drivers/gpu/drm/i915/display/intel_atomic_plane.c
+++ b/drivers/gpu/drm/i915/display/intel_atomic_plane.c
@@ -790,7 +790,8 @@ skl_next_plane_to_commit(struct intel_atomic_state *state,
 	return NULL;
 }
 
-void intel_plane_update_noarm(struct intel_plane *plane,
+void intel_plane_update_noarm(struct intel_dsb *dsb,
+			      struct intel_plane *plane,
 			      const struct intel_crtc_state *crtc_state,
 			      const struct intel_plane_state *plane_state)
 {
@@ -799,10 +800,11 @@ void intel_plane_update_noarm(struct intel_plane *plane,
 	trace_intel_plane_update_noarm(plane, crtc);
 
 	if (plane->update_noarm)
-		plane->update_noarm(plane, crtc_state, plane_state);
+		plane->update_noarm(dsb, plane, crtc_state, plane_state);
 }
 
-void intel_plane_async_flip(struct intel_plane *plane,
+void intel_plane_async_flip(struct intel_dsb *dsb,
+			    struct intel_plane *plane,
 			    const struct intel_crtc_state *crtc_state,
 			    const struct intel_plane_state *plane_state,
 			    bool async_flip)
@@ -810,34 +812,37 @@ void intel_plane_async_flip(struct intel_plane *plane,
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 
 	trace_intel_plane_async_flip(plane, crtc, async_flip);
-	plane->async_flip(plane, crtc_state, plane_state, async_flip);
+	plane->async_flip(dsb, plane, crtc_state, plane_state, async_flip);
 }
 
-void intel_plane_update_arm(struct intel_plane *plane,
+void intel_plane_update_arm(struct intel_dsb *dsb,
+			    struct intel_plane *plane,
 			    const struct intel_crtc_state *crtc_state,
 			    const struct intel_plane_state *plane_state)
 {
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 
 	if (crtc_state->do_async_flip && plane->async_flip) {
-		intel_plane_async_flip(plane, crtc_state, plane_state, true);
+		intel_plane_async_flip(dsb, plane, crtc_state, plane_state, true);
 		return;
 	}
 
 	trace_intel_plane_update_arm(plane, crtc);
-	plane->update_arm(plane, crtc_state, plane_state);
+	plane->update_arm(dsb, plane, crtc_state, plane_state);
 }
 
-void intel_plane_disable_arm(struct intel_plane *plane,
+void intel_plane_disable_arm(struct intel_dsb *dsb,
+			     struct intel_plane *plane,
 			     const struct intel_crtc_state *crtc_state)
 {
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 
 	trace_intel_plane_disable_arm(plane, crtc);
-	plane->disable_arm(plane, crtc_state);
+	plane->disable_arm(dsb, plane, crtc_state);
 }
 
-void intel_crtc_planes_update_noarm(struct intel_atomic_state *state,
+void intel_crtc_planes_update_noarm(struct intel_dsb *dsb,
+				    struct intel_atomic_state *state,
 				    struct intel_crtc *crtc)
 {
 	struct intel_crtc_state *new_crtc_state =
@@ -862,11 +867,13 @@ void intel_crtc_planes_update_noarm(struct intel_atomic_state *state,
 		/* TODO: for mailbox updates this should be skipped */
 		if (new_plane_state->uapi.visible ||
 		    new_plane_state->planar_slave)
-			intel_plane_update_noarm(plane, new_crtc_state, new_plane_state);
+			intel_plane_update_noarm(dsb, plane,
+						 new_crtc_state, new_plane_state);
 	}
 }
 
-static void skl_crtc_planes_update_arm(struct intel_atomic_state *state,
+static void skl_crtc_planes_update_arm(struct intel_dsb *dsb,
+				       struct intel_atomic_state *state,
 				       struct intel_crtc *crtc)
 {
 	struct intel_crtc_state *old_crtc_state =
@@ -893,13 +900,14 @@ static void skl_crtc_planes_update_arm(struct intel_atomic_state *state,
 		 */
 		if (new_plane_state->uapi.visible ||
 		    new_plane_state->planar_slave)
-			intel_plane_update_arm(plane, new_crtc_state, new_plane_state);
+			intel_plane_update_arm(dsb, plane, new_crtc_state, new_plane_state);
 		else
-			intel_plane_disable_arm(plane, new_crtc_state);
+			intel_plane_disable_arm(dsb, plane, new_crtc_state);
 	}
 }
 
-static void i9xx_crtc_planes_update_arm(struct intel_atomic_state *state,
+static void i9xx_crtc_planes_update_arm(struct intel_dsb *dsb,
+					struct intel_atomic_state *state,
 					struct intel_crtc *crtc)
 {
 	struct intel_crtc_state *new_crtc_state =
@@ -919,21 +927,22 @@ static void i9xx_crtc_planes_update_arm(struct intel_atomic_state *state,
 		 * would have to be called here as well.
 		 */
 		if (new_plane_state->uapi.visible)
-			intel_plane_update_arm(plane, new_crtc_state, new_plane_state);
+			intel_plane_update_arm(dsb, plane, new_crtc_state, new_plane_state);
 		else
-			intel_plane_disable_arm(plane, new_crtc_state);
+			intel_plane_disable_arm(dsb, plane, new_crtc_state);
 	}
 }
 
-void intel_crtc_planes_update_arm(struct intel_atomic_state *state,
+void intel_crtc_planes_update_arm(struct intel_dsb *dsb,
+				  struct intel_atomic_state *state,
 				  struct intel_crtc *crtc)
 {
 	struct drm_i915_private *i915 = to_i915(state->base.dev);
 
 	if (DISPLAY_VER(i915) >= 9)
-		skl_crtc_planes_update_arm(state, crtc);
+		skl_crtc_planes_update_arm(dsb, state, crtc);
 	else
-		i9xx_crtc_planes_update_arm(state, crtc);
+		i9xx_crtc_planes_update_arm(dsb, state, crtc);
 }
 
 int intel_atomic_plane_check_clipping(struct intel_plane_state *plane_state,
diff --git a/drivers/gpu/drm/i915/display/intel_atomic_plane.h b/drivers/gpu/drm/i915/display/intel_atomic_plane.h
index 6c4fe3596465..0f982f452ff3 100644
--- a/drivers/gpu/drm/i915/display/intel_atomic_plane.h
+++ b/drivers/gpu/drm/i915/display/intel_atomic_plane.h
@@ -14,6 +14,7 @@ struct drm_rect;
 struct intel_atomic_state;
 struct intel_crtc;
 struct intel_crtc_state;
+struct intel_dsb;
 struct intel_plane;
 struct intel_plane_state;
 enum plane_id;
@@ -32,26 +33,32 @@ void intel_plane_copy_uapi_to_hw_state(struct intel_plane_state *plane_state,
 				       struct intel_crtc *crtc);
 void intel_plane_copy_hw_state(struct intel_plane_state *plane_state,
 			       const struct intel_plane_state *from_plane_state);
-void intel_plane_async_flip(struct intel_plane *plane,
+void intel_plane_async_flip(struct intel_dsb *dsb,
+			    struct intel_plane *plane,
 			    const struct intel_crtc_state *crtc_state,
 			    const struct intel_plane_state *plane_state,
 			    bool async_flip);
-void intel_plane_update_noarm(struct intel_plane *plane,
+void intel_plane_update_noarm(struct intel_dsb *dsb,
+			      struct intel_plane *plane,
 			      const struct intel_crtc_state *crtc_state,
 			      const struct intel_plane_state *plane_state);
-void intel_plane_update_arm(struct intel_plane *plane,
+void intel_plane_update_arm(struct intel_dsb *dsb,
+			    struct intel_plane *plane,
 			    const struct intel_crtc_state *crtc_state,
 			    const struct intel_plane_state *plane_state);
-void intel_plane_disable_arm(struct intel_plane *plane,
+void intel_plane_disable_arm(struct intel_dsb *dsb,
+			     struct intel_plane *plane,
 			     const struct intel_crtc_state *crtc_state);
 struct intel_plane *intel_plane_alloc(void);
 void intel_plane_free(struct intel_plane *plane);
 struct drm_plane_state *intel_plane_duplicate_state(struct drm_plane *plane);
 void intel_plane_destroy_state(struct drm_plane *plane,
 			       struct drm_plane_state *state);
-void intel_crtc_planes_update_noarm(struct intel_atomic_state *state,
+void intel_crtc_planes_update_noarm(struct intel_dsb *dsb,
+				    struct intel_atomic_state *state,
 				    struct intel_crtc *crtc);
-void intel_crtc_planes_update_arm(struct intel_atomic_state *state,
+void intel_crtc_planes_update_arm(struct intel_dsb *dsbx,
+				  struct intel_atomic_state *state,
 				  struct intel_crtc *crtc);
 int intel_plane_atomic_check_with_state(const struct intel_crtc_state *old_crtc_state,
 					struct intel_crtc_state *crtc_state,
diff --git a/drivers/gpu/drm/i915/display/intel_color.c b/drivers/gpu/drm/i915/display/intel_color.c
index ec55cb651d44..1fbe3cd452c1 100644
--- a/drivers/gpu/drm/i915/display/intel_color.c
+++ b/drivers/gpu/drm/i915/display/intel_color.c
@@ -1912,6 +1912,23 @@ void intel_color_post_update(const struct intel_crtc_state *crtc_state)
 		i915->display.funcs.color->color_post_update(crtc_state);
 }
 
+void intel_color_modeset(const struct intel_crtc_state *crtc_state)
+{
+	struct intel_display *display = to_intel_display(crtc_state);
+
+	intel_color_load_luts(crtc_state);
+	intel_color_commit_noarm(crtc_state);
+	intel_color_commit_arm(crtc_state);
+
+	if (DISPLAY_VER(display) < 9) {
+		struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+		struct intel_plane *plane = to_intel_plane(crtc->base.primary);
+
+		/* update DSPCNTR to configure gamma/csc for pipe bottom color */
+		plane->disable_arm(NULL, plane, crtc_state);
+	}
+}
+
 void intel_color_prepare_commit(struct intel_atomic_state *state,
 				struct intel_crtc *crtc)
 {
diff --git a/drivers/gpu/drm/i915/display/intel_color.h b/drivers/gpu/drm/i915/display/intel_color.h
index 79f230a1709a..ab3aaec06a2a 100644
--- a/drivers/gpu/drm/i915/display/intel_color.h
+++ b/drivers/gpu/drm/i915/display/intel_color.h
@@ -28,6 +28,7 @@ void intel_color_commit_noarm(const struct intel_crtc_state *crtc_state);
 void intel_color_commit_arm(const struct intel_crtc_state *crtc_state);
 void intel_color_post_update(const struct intel_crtc_state *crtc_state);
 void intel_color_load_luts(const struct intel_crtc_state *crtc_state);
+void intel_color_modeset(const struct intel_crtc_state *crtc_state);
 void intel_color_get_config(struct intel_crtc_state *crtc_state);
 bool intel_color_lut_equal(const struct intel_crtc_state *crtc_state,
 			   const struct drm_property_blob *blob1,
diff --git a/drivers/gpu/drm/i915/display/intel_cursor.c b/drivers/gpu/drm/i915/display/intel_cursor.c
index 9ad53e1cbbd0..aeadb834d332 100644
--- a/drivers/gpu/drm/i915/display/intel_cursor.c
+++ b/drivers/gpu/drm/i915/display/intel_cursor.c
@@ -275,7 +275,8 @@ static int i845_check_cursor(struct intel_crtc_state *crtc_state,
 }
 
 /* TODO: split into noarm+arm pair */
-static void i845_cursor_update_arm(struct intel_plane *plane,
+static void i845_cursor_update_arm(struct intel_dsb *dsb,
+				   struct intel_plane *plane,
 				   const struct intel_crtc_state *crtc_state,
 				   const struct intel_plane_state *plane_state)
 {
@@ -315,10 +316,11 @@ static void i845_cursor_update_arm(struct intel_plane *plane,
 	}
 }
 
-static void i845_cursor_disable_arm(struct intel_plane *plane,
+static void i845_cursor_disable_arm(struct intel_dsb *dsb,
+				    struct intel_plane *plane,
 				    const struct intel_crtc_state *crtc_state)
 {
-	i845_cursor_update_arm(plane, crtc_state, NULL);
+	i845_cursor_update_arm(dsb, plane, crtc_state, NULL);
 }
 
 static bool i845_cursor_get_hw_state(struct intel_plane *plane,
@@ -527,22 +529,25 @@ static int i9xx_check_cursor(struct intel_crtc_state *crtc_state,
 	return 0;
 }
 
-static void i9xx_cursor_disable_sel_fetch_arm(struct intel_plane *plane,
+static void i9xx_cursor_disable_sel_fetch_arm(struct intel_dsb *dsb,
+					      struct intel_plane *plane,
 					      const struct intel_crtc_state *crtc_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
+	struct intel_display *display = to_intel_display(plane->base.dev);
 	enum pipe pipe = plane->pipe;
 
 	if (!crtc_state->enable_psr2_sel_fetch)
 		return;
 
-	intel_de_write_fw(dev_priv, SEL_FETCH_CUR_CTL(pipe), 0);
+	intel_de_write_dsb(display, dsb, SEL_FETCH_CUR_CTL(pipe), 0);
 }
 
-static void wa_16021440873(struct intel_plane *plane,
+static void wa_16021440873(struct intel_dsb *dsb,
+			   struct intel_plane *plane,
 			   const struct intel_crtc_state *crtc_state,
 			   const struct intel_plane_state *plane_state)
 {
+	struct intel_display *display = to_intel_display(plane->base.dev);
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
 	u32 ctl = plane_state->ctl;
 	int et_y_position = drm_rect_height(&crtc_state->pipe_src) + 1;
@@ -551,16 +556,18 @@ static void wa_16021440873(struct intel_plane *plane,
 	ctl &= ~MCURSOR_MODE_MASK;
 	ctl |= MCURSOR_MODE_64_2B;
 
-	intel_de_write_fw(dev_priv, SEL_FETCH_CUR_CTL(pipe), ctl);
+	intel_de_write_dsb(display, dsb, SEL_FETCH_CUR_CTL(pipe), ctl);
 
-	intel_de_write(dev_priv, CURPOS_ERLY_TPT(dev_priv, pipe),
-		       CURSOR_POS_Y(et_y_position));
+	intel_de_write_dsb(display, dsb, CURPOS_ERLY_TPT(dev_priv, pipe),
+			   CURSOR_POS_Y(et_y_position));
 }
 
-static void i9xx_cursor_update_sel_fetch_arm(struct intel_plane *plane,
+static void i9xx_cursor_update_sel_fetch_arm(struct intel_dsb *dsb,
+					     struct intel_plane *plane,
 					     const struct intel_crtc_state *crtc_state,
 					     const struct intel_plane_state *plane_state)
 {
+	struct intel_display *display = to_intel_display(plane->base.dev);
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
 	enum pipe pipe = plane->pipe;
 
@@ -571,19 +578,17 @@ static void i9xx_cursor_update_sel_fetch_arm(struct intel_plane *plane,
 		if (crtc_state->enable_psr2_su_region_et) {
 			u32 val = intel_cursor_position(crtc_state, plane_state,
 				true);
-			intel_de_write_fw(dev_priv,
-					  CURPOS_ERLY_TPT(dev_priv, pipe),
-					  val);
+
+			intel_de_write_dsb(display, dsb, CURPOS_ERLY_TPT(dev_priv, pipe), val);
 		}
 
-		intel_de_write_fw(dev_priv, SEL_FETCH_CUR_CTL(pipe),
-				  plane_state->ctl);
+		intel_de_write_dsb(display, dsb, SEL_FETCH_CUR_CTL(pipe), plane_state->ctl);
 	} else {
 		/* Wa_16021440873 */
 		if (crtc_state->enable_psr2_su_region_et)
-			wa_16021440873(plane, crtc_state, plane_state);
+			wa_16021440873(dsb, plane, crtc_state, plane_state);
 		else
-			i9xx_cursor_disable_sel_fetch_arm(plane, crtc_state);
+			i9xx_cursor_disable_sel_fetch_arm(dsb, plane, crtc_state);
 	}
 }
 
@@ -610,9 +615,11 @@ static u32 skl_cursor_wm_reg_val(const struct skl_wm_level *level)
 	return val;
 }
 
-static void skl_write_cursor_wm(struct intel_plane *plane,
+static void skl_write_cursor_wm(struct intel_dsb *dsb,
+				struct intel_plane *plane,
 				const struct intel_crtc_state *crtc_state)
 {
+	struct intel_display *display = to_intel_display(plane->base.dev);
 	struct drm_i915_private *i915 = to_i915(plane->base.dev);
 	enum plane_id plane_id = plane->id;
 	enum pipe pipe = plane->pipe;
@@ -622,30 +629,32 @@ static void skl_write_cursor_wm(struct intel_plane *plane,
 	int level;
 
 	for (level = 0; level < i915->display.wm.num_levels; level++)
-		intel_de_write_fw(i915, CUR_WM(pipe, level),
-				  skl_cursor_wm_reg_val(skl_plane_wm_level(pipe_wm, plane_id, level)));
+		intel_de_write_dsb(display, dsb, CUR_WM(pipe, level),
+				   skl_cursor_wm_reg_val(skl_plane_wm_level(pipe_wm, plane_id, level)));
 
-	intel_de_write_fw(i915, CUR_WM_TRANS(pipe),
-			  skl_cursor_wm_reg_val(skl_plane_trans_wm(pipe_wm, plane_id)));
+	intel_de_write_dsb(display, dsb, CUR_WM_TRANS(pipe),
+			   skl_cursor_wm_reg_val(skl_plane_trans_wm(pipe_wm, plane_id)));
 
 	if (HAS_HW_SAGV_WM(i915)) {
 		const struct skl_plane_wm *wm = &pipe_wm->planes[plane_id];
 
-		intel_de_write_fw(i915, CUR_WM_SAGV(pipe),
-				  skl_cursor_wm_reg_val(&wm->sagv.wm0));
-		intel_de_write_fw(i915, CUR_WM_SAGV_TRANS(pipe),
-				  skl_cursor_wm_reg_val(&wm->sagv.trans_wm));
+		intel_de_write_dsb(display, dsb, CUR_WM_SAGV(pipe),
+				   skl_cursor_wm_reg_val(&wm->sagv.wm0));
+		intel_de_write_dsb(display, dsb, CUR_WM_SAGV_TRANS(pipe),
+				   skl_cursor_wm_reg_val(&wm->sagv.trans_wm));
 	}
 
-	intel_de_write_fw(i915, CUR_BUF_CFG(pipe),
-			  skl_cursor_ddb_reg_val(ddb));
+	intel_de_write_dsb(display, dsb, CUR_BUF_CFG(pipe),
+			   skl_cursor_ddb_reg_val(ddb));
 }
 
 /* TODO: split into noarm+arm pair */
-static void i9xx_cursor_update_arm(struct intel_plane *plane,
+static void i9xx_cursor_update_arm(struct intel_dsb *dsb,
+				   struct intel_plane *plane,
 				   const struct intel_crtc_state *crtc_state,
 				   const struct intel_plane_state *plane_state)
 {
+	struct intel_display *display = to_intel_display(plane->base.dev);
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
 	enum pipe pipe = plane->pipe;
 	u32 cntl = 0, base = 0, pos = 0, fbc_ctl = 0;
@@ -685,38 +694,36 @@ static void i9xx_cursor_update_arm(struct intel_plane *plane,
 	 */
 
 	if (DISPLAY_VER(dev_priv) >= 9)
-		skl_write_cursor_wm(plane, crtc_state);
+		skl_write_cursor_wm(dsb, plane, crtc_state);
 
 	if (plane_state)
-		i9xx_cursor_update_sel_fetch_arm(plane, crtc_state,
-						 plane_state);
+		i9xx_cursor_update_sel_fetch_arm(dsb, plane, crtc_state, plane_state);
 	else
-		i9xx_cursor_disable_sel_fetch_arm(plane, crtc_state);
+		i9xx_cursor_disable_sel_fetch_arm(dsb, plane, crtc_state);
 
 	if (plane->cursor.base != base ||
 	    plane->cursor.size != fbc_ctl ||
 	    plane->cursor.cntl != cntl) {
 		if (HAS_CUR_FBC(dev_priv))
-			intel_de_write_fw(dev_priv,
-					  CUR_FBC_CTL(dev_priv, pipe),
-					  fbc_ctl);
-		intel_de_write_fw(dev_priv, CURCNTR(dev_priv, pipe), cntl);
-		intel_de_write_fw(dev_priv, CURPOS(dev_priv, pipe), pos);
-		intel_de_write_fw(dev_priv, CURBASE(dev_priv, pipe), base);
+			intel_de_write_dsb(display, dsb, CUR_FBC_CTL(dev_priv, pipe), fbc_ctl);
+		intel_de_write_dsb(display, dsb, CURCNTR(dev_priv, pipe), cntl);
+		intel_de_write_dsb(display, dsb, CURPOS(dev_priv, pipe), pos);
+		intel_de_write_dsb(display, dsb, CURBASE(dev_priv, pipe), base);
 
 		plane->cursor.base = base;
 		plane->cursor.size = fbc_ctl;
 		plane->cursor.cntl = cntl;
 	} else {
-		intel_de_write_fw(dev_priv, CURPOS(dev_priv, pipe), pos);
-		intel_de_write_fw(dev_priv, CURBASE(dev_priv, pipe), base);
+		intel_de_write_dsb(display, dsb, CURPOS(dev_priv, pipe), pos);
+		intel_de_write_dsb(display, dsb, CURBASE(dev_priv, pipe), base);
 	}
 }
 
-static void i9xx_cursor_disable_arm(struct intel_plane *plane,
+static void i9xx_cursor_disable_arm(struct intel_dsb *dsb,
+				    struct intel_plane *plane,
 				    const struct intel_crtc_state *crtc_state)
 {
-	i9xx_cursor_update_arm(plane, crtc_state, NULL);
+	i9xx_cursor_update_arm(dsb, plane, crtc_state, NULL);
 }
 
 static bool i9xx_cursor_get_hw_state(struct intel_plane *plane,
@@ -905,10 +912,10 @@ intel_legacy_cursor_update(struct drm_plane *_plane,
 	}
 
 	if (new_plane_state->uapi.visible) {
-		intel_plane_update_noarm(plane, crtc_state, new_plane_state);
-		intel_plane_update_arm(plane, crtc_state, new_plane_state);
+		intel_plane_update_noarm(NULL, plane, crtc_state, new_plane_state);
+		intel_plane_update_arm(NULL, plane, crtc_state, new_plane_state);
 	} else {
-		intel_plane_disable_arm(plane, crtc_state);
+		intel_plane_disable_arm(NULL, plane, crtc_state);
 	}
 
 	local_irq_enable();
diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c
index b1c294236cc8..5b24460c0134 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi.c
@@ -3363,7 +3363,7 @@ static void intel_enable_ddi_hdmi(struct intel_atomic_state *state,
 		intel_de_rmw(dev_priv, XELPDP_PORT_BUF_CTL1(dev_priv, port),
 			     XELPDP_PORT_WIDTH_MASK | XELPDP_PORT_REVERSAL, port_buf);
 
-		buf_ctl |= DDI_PORT_WIDTH(lane_count);
+		buf_ctl |= DDI_PORT_WIDTH(crtc_state->lane_count);
 
 		if (DISPLAY_VER(dev_priv) >= 20)
 			buf_ctl |= XE2LPD_DDI_BUF_D2D_LINK_ENABLE;
@@ -4413,8 +4413,7 @@ static const struct drm_encoder_funcs intel_ddi_funcs = {
 	.late_register = intel_ddi_encoder_late_register,
 };
 
-static struct intel_connector *
-intel_ddi_init_dp_connector(struct intel_digital_port *dig_port)
+static int intel_ddi_init_dp_connector(struct intel_digital_port *dig_port)
 {
 	struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev);
 	struct intel_connector *connector;
@@ -4422,7 +4421,7 @@ intel_ddi_init_dp_connector(struct intel_digital_port *dig_port)
 
 	connector = intel_connector_alloc();
 	if (!connector)
-		return NULL;
+		return -ENOMEM;
 
 	dig_port->dp.output_reg = DDI_BUF_CTL(port);
 	if (DISPLAY_VER(i915) >= 14)
@@ -4437,7 +4436,7 @@ intel_ddi_init_dp_connector(struct intel_digital_port *dig_port)
 
 	if (!intel_dp_init_connector(dig_port, connector)) {
 		kfree(connector);
-		return NULL;
+		return -EINVAL;
 	}
 
 	if (dig_port->base.type == INTEL_OUTPUT_EDP) {
@@ -4453,7 +4452,7 @@ intel_ddi_init_dp_connector(struct intel_digital_port *dig_port)
 		}
 	}
 
-	return connector;
+	return 0;
 }
 
 static int intel_hdmi_reset_link(struct intel_encoder *encoder,
@@ -4623,20 +4622,28 @@ static bool bdw_digital_port_connected(struct intel_encoder *encoder)
 	return intel_de_read(dev_priv, GEN8_DE_PORT_ISR) & bit;
 }
 
-static struct intel_connector *
-intel_ddi_init_hdmi_connector(struct intel_digital_port *dig_port)
+static int intel_ddi_init_hdmi_connector(struct intel_digital_port *dig_port)
 {
 	struct intel_connector *connector;
 	enum port port = dig_port->base.port;
 
 	connector = intel_connector_alloc();
 	if (!connector)
-		return NULL;
+		return -ENOMEM;
 
 	dig_port->hdmi.hdmi_reg = DDI_BUF_CTL(port);
-	intel_hdmi_init_connector(dig_port, connector);
 
-	return connector;
+	if (!intel_hdmi_init_connector(dig_port, connector)) {
+		/*
+		 * HDMI connector init failures may just mean conflicting DDC
+		 * pins or not having enough lanes. Handle them gracefully, but
+		 * don't fail the entire DDI init.
+		 */
+		dig_port->hdmi.hdmi_reg = INVALID_MMIO_REG;
+		kfree(connector);
+	}
+
+	return 0;
 }
 
 static bool intel_ddi_a_force_4_lanes(struct intel_digital_port *dig_port)
@@ -4791,8 +4798,10 @@ static void intel_ddi_tc_encoder_suspend_complete(struct intel_encoder *encoder)
 
 static void intel_ddi_encoder_shutdown(struct intel_encoder *encoder)
 {
-	intel_dp_encoder_shutdown(encoder);
-	intel_hdmi_encoder_shutdown(encoder);
+	if (intel_encoder_is_dp(encoder))
+		intel_dp_encoder_shutdown(encoder);
+	if (intel_encoder_is_hdmi(encoder))
+		intel_hdmi_encoder_shutdown(encoder);
 }
 
 static void intel_ddi_tc_encoder_shutdown_complete(struct intel_encoder *encoder)
@@ -4888,7 +4897,7 @@ void intel_ddi_init(struct intel_display *display,
 		if (!assert_has_icl_dsi(dev_priv))
 			return;
 
-		icl_dsi_init(dev_priv, devdata);
+		icl_dsi_init(display, devdata);
 		return;
 	}
 
@@ -5185,7 +5194,7 @@ void intel_ddi_init(struct intel_display *display,
 	intel_infoframe_init(dig_port);
 
 	if (init_dp) {
-		if (!intel_ddi_init_dp_connector(dig_port))
+		if (intel_ddi_init_dp_connector(dig_port))
 			goto err;
 
 		dig_port->hpd_pulse = intel_dp_hpd_pulse;
@@ -5199,7 +5208,7 @@ void intel_ddi_init(struct intel_display *display,
 	 * but leave it just in case we have some really bad VBTs...
 	 */
 	if (encoder->type != INTEL_OUTPUT_EDP && init_hdmi) {
-		if (!intel_ddi_init_hdmi_connector(dig_port))
+		if (intel_ddi_init_hdmi_connector(dig_port))
 			goto err;
 	}
 
diff --git a/drivers/gpu/drm/i915/display/intel_de.h b/drivers/gpu/drm/i915/display/intel_de.h
index e881bfeafb47..e017cd4a8168 100644
--- a/drivers/gpu/drm/i915/display/intel_de.h
+++ b/drivers/gpu/drm/i915/display/intel_de.h
@@ -8,6 +8,7 @@
 
 #include "i915_drv.h"
 #include "i915_trace.h"
+#include "intel_dsb.h"
 #include "intel_uncore.h"
 
 static inline struct intel_uncore *__to_uncore(struct intel_display *display)
@@ -233,4 +234,14 @@ __intel_de_write_notrace(struct intel_display *display, i915_reg_t reg,
 }
 #define intel_de_write_notrace(p,...) __intel_de_write_notrace(__to_intel_display(p), __VA_ARGS__)
 
+static __always_inline void
+intel_de_write_dsb(struct intel_display *display, struct intel_dsb *dsb,
+		   i915_reg_t reg, u32 val)
+{
+	if (dsb)
+		intel_dsb_reg_write(dsb, reg, val);
+	else
+		intel_de_write_fw(display, reg, val);
+}
+
 #endif /* __INTEL_DE_H__ */
diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index b4ef4d59da1a..4f8899cd125d 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -135,7 +135,8 @@
 static void intel_set_transcoder_timings(const struct intel_crtc_state *crtc_state);
 static void intel_set_pipe_src_size(const struct intel_crtc_state *crtc_state);
 static void hsw_set_transconf(const struct intel_crtc_state *crtc_state);
-static void bdw_set_pipe_misc(const struct intel_crtc_state *crtc_state);
+static void bdw_set_pipe_misc(struct intel_dsb *dsb,
+			      const struct intel_crtc_state *crtc_state);
 
 /* returns HPLL frequency in kHz */
 int vlv_get_hpll_vco(struct drm_i915_private *dev_priv)
@@ -715,7 +716,7 @@ void intel_plane_disable_noatomic(struct intel_crtc *crtc,
 	if (DISPLAY_VER(dev_priv) == 2 && !crtc_state->active_planes)
 		intel_set_cpu_fifo_underrun_reporting(dev_priv, crtc->pipe, false);
 
-	intel_plane_disable_arm(plane, crtc_state);
+	intel_plane_disable_arm(NULL, plane, crtc_state);
 	intel_crtc_wait_for_next_vblank(crtc);
 }
 
@@ -1005,7 +1006,9 @@ static bool vrr_params_changed(const struct intel_crtc_state *old_crtc_state,
 		old_crtc_state->vrr.vmin != new_crtc_state->vrr.vmin ||
 		old_crtc_state->vrr.vmax != new_crtc_state->vrr.vmax ||
 		old_crtc_state->vrr.guardband != new_crtc_state->vrr.guardband ||
-		old_crtc_state->vrr.pipeline_full != new_crtc_state->vrr.pipeline_full;
+		old_crtc_state->vrr.pipeline_full != new_crtc_state->vrr.pipeline_full ||
+		old_crtc_state->vrr.vsync_start != new_crtc_state->vrr.vsync_start ||
+		old_crtc_state->vrr.vsync_end != new_crtc_state->vrr.vsync_end;
 }
 
 static bool cmrr_params_changed(const struct intel_crtc_state *old_crtc_state,
@@ -1172,8 +1175,8 @@ static void intel_crtc_async_flip_disable_wa(struct intel_atomic_state *state,
 			 * Apart from the async flip bit we want to
 			 * preserve the old state for the plane.
 			 */
-			intel_plane_async_flip(plane, old_crtc_state,
-					       old_plane_state, false);
+			intel_plane_async_flip(NULL, plane,
+					       old_crtc_state, old_plane_state, false);
 			need_vbl_wait = true;
 		}
 	}
@@ -1315,7 +1318,7 @@ static void intel_crtc_disable_planes(struct intel_atomic_state *state,
 		    !(update_mask & BIT(plane->id)))
 			continue;
 
-		intel_plane_disable_arm(plane, new_crtc_state);
+		intel_plane_disable_arm(NULL, plane, new_crtc_state);
 
 		if (old_plane_state->uapi.visible)
 			fb_bits |= plane->frontbuffer_bit;
@@ -1502,14 +1505,6 @@ static void intel_encoders_update_pipe(struct intel_atomic_state *state,
 	}
 }
 
-static void intel_disable_primary_plane(const struct intel_crtc_state *crtc_state)
-{
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
-	struct intel_plane *plane = to_intel_plane(crtc->base.primary);
-
-	plane->disable_arm(plane, crtc_state);
-}
-
 static void ilk_configure_cpu_transcoder(const struct intel_crtc_state *crtc_state)
 {
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
@@ -1575,11 +1570,7 @@ static void ilk_crtc_enable(struct intel_atomic_state *state,
 	 * On ILK+ LUT must be loaded before the pipe is running but with
 	 * clocks enabled
 	 */
-	intel_color_load_luts(new_crtc_state);
-	intel_color_commit_noarm(new_crtc_state);
-	intel_color_commit_arm(new_crtc_state);
-	/* update DSPCNTR to configure gamma for pipe bottom color */
-	intel_disable_primary_plane(new_crtc_state);
+	intel_color_modeset(new_crtc_state);
 
 	intel_initial_watermarks(state, crtc);
 	intel_enable_transcoder(new_crtc_state);
@@ -1716,7 +1707,7 @@ static void hsw_crtc_enable(struct intel_atomic_state *state,
 		intel_set_pipe_src_size(pipe_crtc_state);
 
 		if (DISPLAY_VER(dev_priv) >= 9 || IS_BROADWELL(dev_priv))
-			bdw_set_pipe_misc(pipe_crtc_state);
+			bdw_set_pipe_misc(NULL, pipe_crtc_state);
 	}
 
 	if (!transcoder_is_dsi(cpu_transcoder))
@@ -1741,12 +1732,7 @@ static void hsw_crtc_enable(struct intel_atomic_state *state,
 		 * On ILK+ LUT must be loaded before the pipe is running but with
 		 * clocks enabled
 		 */
-		intel_color_load_luts(pipe_crtc_state);
-		intel_color_commit_noarm(pipe_crtc_state);
-		intel_color_commit_arm(pipe_crtc_state);
-		/* update DSPCNTR to configure gamma/csc for pipe bottom color */
-		if (DISPLAY_VER(dev_priv) < 9)
-			intel_disable_primary_plane(pipe_crtc_state);
+		intel_color_modeset(pipe_crtc_state);
 
 		hsw_set_linetime_wm(pipe_crtc_state);
 
@@ -2147,11 +2133,7 @@ static void valleyview_crtc_enable(struct intel_atomic_state *state,
 
 	i9xx_pfit_enable(new_crtc_state);
 
-	intel_color_load_luts(new_crtc_state);
-	intel_color_commit_noarm(new_crtc_state);
-	intel_color_commit_arm(new_crtc_state);
-	/* update DSPCNTR to configure gamma for pipe bottom color */
-	intel_disable_primary_plane(new_crtc_state);
+	intel_color_modeset(new_crtc_state);
 
 	intel_initial_watermarks(state, crtc);
 	intel_enable_transcoder(new_crtc_state);
@@ -2187,11 +2169,7 @@ static void i9xx_crtc_enable(struct intel_atomic_state *state,
 
 	i9xx_pfit_enable(new_crtc_state);
 
-	intel_color_load_luts(new_crtc_state);
-	intel_color_commit_noarm(new_crtc_state);
-	intel_color_commit_arm(new_crtc_state);
-	/* update DSPCNTR to configure gamma for pipe bottom color */
-	intel_disable_primary_plane(new_crtc_state);
+	intel_color_modeset(new_crtc_state);
 
 	if (!intel_initial_watermarks(state, crtc))
 		intel_update_watermarks(dev_priv);
@@ -3246,9 +3224,11 @@ static void hsw_set_transconf(const struct intel_crtc_state *crtc_state)
 	intel_de_posting_read(dev_priv, TRANSCONF(dev_priv, cpu_transcoder));
 }
 
-static void bdw_set_pipe_misc(const struct intel_crtc_state *crtc_state)
+static void bdw_set_pipe_misc(struct intel_dsb *dsb,
+			      const struct intel_crtc_state *crtc_state)
 {
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	struct intel_display *display = to_intel_display(crtc->base.dev);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	u32 val = 0;
 
@@ -3293,7 +3273,7 @@ static void bdw_set_pipe_misc(const struct intel_crtc_state *crtc_state)
 	if (IS_BROADWELL(dev_priv))
 		val |= PIPE_MISC_PSR_MASK_SPRITE_ENABLE;
 
-	intel_de_write(dev_priv, PIPE_MISC(crtc->pipe), val);
+	intel_de_write_dsb(display, dsb, PIPE_MISC(crtc->pipe), val);
 }
 
 int bdw_get_pipe_misc_bpp(struct intel_crtc *crtc)
@@ -6369,12 +6349,30 @@ static int intel_async_flip_check_hw(struct intel_atomic_state *state, struct in
 static int intel_joiner_add_affected_crtcs(struct intel_atomic_state *state)
 {
 	struct drm_i915_private *i915 = to_i915(state->base.dev);
+	const struct intel_plane_state *plane_state;
 	struct intel_crtc_state *crtc_state;
+	struct intel_plane *plane;
 	struct intel_crtc *crtc;
 	u8 affected_pipes = 0;
 	u8 modeset_pipes = 0;
 	int i;
 
+	/*
+	 * Any plane which is in use by the joiner needs its crtc.
+	 * Pull those in first as this will not have happened yet
+	 * if the plane remains disabled according to uapi.
+	 */
+	for_each_new_intel_plane_in_state(state, plane, plane_state, i) {
+		crtc = to_intel_crtc(plane_state->hw.crtc);
+		if (!crtc)
+			continue;
+
+		crtc_state = intel_atomic_get_crtc_state(&state->base, crtc);
+		if (IS_ERR(crtc_state))
+			return PTR_ERR(crtc_state);
+	}
+
+	/* Now pull in all joined crtcs */
 	for_each_new_intel_crtc_in_state(state, crtc, crtc_state, i) {
 		affected_pipes |= crtc_state->joiner_pipes;
 		if (intel_crtc_needs_modeset(crtc_state))
@@ -6828,7 +6826,7 @@ static void commit_pipe_pre_planes(struct intel_atomic_state *state,
 			intel_color_commit_arm(new_crtc_state);
 
 		if (DISPLAY_VER(dev_priv) >= 9 || IS_BROADWELL(dev_priv))
-			bdw_set_pipe_misc(new_crtc_state);
+			bdw_set_pipe_misc(NULL, new_crtc_state);
 
 		if (intel_crtc_needs_fastset(new_crtc_state))
 			intel_pipe_fastset(old_crtc_state, new_crtc_state);
@@ -6928,7 +6926,7 @@ static void intel_pre_update_crtc(struct intel_atomic_state *state,
 	    intel_crtc_needs_color_update(new_crtc_state))
 		intel_color_commit_noarm(new_crtc_state);
 
-	intel_crtc_planes_update_noarm(state, crtc);
+	intel_crtc_planes_update_noarm(NULL, state, crtc);
 }
 
 static void intel_update_crtc(struct intel_atomic_state *state,
@@ -6944,7 +6942,7 @@ static void intel_update_crtc(struct intel_atomic_state *state,
 
 	commit_pipe_pre_planes(state, crtc);
 
-	intel_crtc_planes_update_arm(state, crtc);
+	intel_crtc_planes_update_arm(NULL, state, crtc);
 
 	commit_pipe_post_planes(state, crtc);
 
@@ -7442,9 +7440,6 @@ static void intel_atomic_commit_tail(struct intel_atomic_state *state)
 	/* Now enable the clocks, plane, pipe, and connectors that we set up. */
 	dev_priv->display.funcs.display->commit_modeset_enables(state);
 
-	if (state->modeset)
-		intel_set_cdclk_post_plane_update(state);
-
 	intel_wait_for_vblank_workers(state);
 
 	/* FIXME: We should call drm_atomic_helper_commit_hw_done() here
@@ -7525,6 +7520,8 @@ static void intel_atomic_commit_tail(struct intel_atomic_state *state)
 		intel_verify_planes(state);
 
 	intel_sagv_post_plane_update(state);
+	if (state->modeset)
+		intel_set_cdclk_post_plane_update(state);
 	intel_pmdemand_post_plane_update(state);
 
 	drm_atomic_helper_commit_hw_done(&state->base);
diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h
index f29e5dc3db91..9812191e7ef2 100644
--- a/drivers/gpu/drm/i915/display/intel_display_types.h
+++ b/drivers/gpu/drm/i915/display/intel_display_types.h
@@ -1036,6 +1036,10 @@ struct intel_csc_matrix {
 	u16 postoff[3];
 };
 
+void intel_io_mmio_fw_write(void *ctx, i915_reg_t reg, u32 val);
+
+typedef void (*intel_io_reg_write)(void *ctx, i915_reg_t reg, u32 val);
+
 struct intel_crtc_state {
 	/*
 	 * uapi (drm) state. This is the software state shown to userspace.
@@ -1578,22 +1582,26 @@ struct intel_plane {
 				   u32 pixel_format, u64 modifier,
 				   unsigned int rotation);
 	/* Write all non-self arming plane registers */
-	void (*update_noarm)(struct intel_plane *plane,
+	void (*update_noarm)(struct intel_dsb *dsb,
+			     struct intel_plane *plane,
 			     const struct intel_crtc_state *crtc_state,
 			     const struct intel_plane_state *plane_state);
 	/* Write all self-arming plane registers */
-	void (*update_arm)(struct intel_plane *plane,
+	void (*update_arm)(struct intel_dsb *dsb,
+			   struct intel_plane *plane,
 			   const struct intel_crtc_state *crtc_state,
 			   const struct intel_plane_state *plane_state);
 	/* Disable the plane, must arm */
-	void (*disable_arm)(struct intel_plane *plane,
+	void (*disable_arm)(struct intel_dsb *dsb,
+			    struct intel_plane *plane,
 			    const struct intel_crtc_state *crtc_state);
 	bool (*get_hw_state)(struct intel_plane *plane, enum pipe *pipe);
 	int (*check_plane)(struct intel_crtc_state *crtc_state,
 			   struct intel_plane_state *plane_state);
 	int (*min_cdclk)(const struct intel_crtc_state *crtc_state,
 			 const struct intel_plane_state *plane_state);
-	void (*async_flip)(struct intel_plane *plane,
+	void (*async_flip)(struct intel_dsb *dsb,
+			   struct intel_plane *plane,
 			   const struct intel_crtc_state *crtc_state,
 			   const struct intel_plane_state *plane_state,
 			   bool async_flip);
@@ -2067,6 +2075,19 @@ static inline bool intel_encoder_is_dp(struct intel_encoder *encoder)
 	}
 }
 
+static inline bool intel_encoder_is_hdmi(struct intel_encoder *encoder)
+{
+	switch (encoder->type) {
+	case INTEL_OUTPUT_HDMI:
+		return true;
+	case INTEL_OUTPUT_DDI:
+		/* See if the HDMI encoder is valid. */
+		return i915_mmio_reg_valid(enc_to_intel_hdmi(encoder)->hdmi_reg);
+	default:
+		return false;
+	}
+}
+
 static inline struct intel_lspcon *
 enc_to_intel_lspcon(struct intel_encoder *encoder)
 {
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index 90fa73575feb..af80f1ac8880 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -1506,6 +1506,12 @@ int intel_dp_rate_select(struct intel_dp *intel_dp, int rate)
 void intel_dp_compute_rate(struct intel_dp *intel_dp, int port_clock,
 			   u8 *link_bw, u8 *rate_select)
 {
+	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
+
+	/* FIXME g4x can't generate an exact 2.7GHz with the 96MHz non-SSC refclk */
+	if (IS_G4X(i915) && port_clock == 268800)
+		port_clock = 270000;
+
 	/* eDP 1.4 rate select method. */
 	if (intel_dp->use_rate_select) {
 		*link_bw = 0;
@@ -2022,11 +2028,10 @@ icl_dsc_compute_link_config(struct intel_dp *intel_dp,
 	/* Compressed BPP should be less than the Input DSC bpp */
 	dsc_max_bpp = min(dsc_max_bpp, pipe_bpp - 1);
 
-	for (i = 0; i < ARRAY_SIZE(valid_dsc_bpp); i++) {
-		if (valid_dsc_bpp[i] < dsc_min_bpp)
+	for (i = ARRAY_SIZE(valid_dsc_bpp) - 1; i >= 0; i--) {
+		if (valid_dsc_bpp[i] < dsc_min_bpp ||
+		    valid_dsc_bpp[i] > dsc_max_bpp)
 			continue;
-		if (valid_dsc_bpp[i] > dsc_max_bpp)
-			break;
 
 		ret = dsc_compute_link_config(intel_dp,
 					      pipe_config,
@@ -2738,7 +2743,6 @@ static void intel_dp_compute_as_sdp(struct intel_dp *intel_dp,
 
 	crtc_state->infoframes.enable |= intel_hdmi_infoframe_enable(DP_SDP_ADAPTIVE_SYNC);
 
-	/* Currently only DP_AS_SDP_AVT_FIXED_VTOTAL mode supported */
 	as_sdp->sdp_type = DP_SDP_ADAPTIVE_SYNC;
 	as_sdp->length = 0x9;
 	as_sdp->duration_incr_ms = 0;
@@ -2750,7 +2754,7 @@ static void intel_dp_compute_as_sdp(struct intel_dp *intel_dp,
 		as_sdp->target_rr = drm_mode_vrefresh(adjusted_mode);
 		as_sdp->target_rr_divider = true;
 	} else {
-		as_sdp->mode = DP_AS_SDP_AVT_FIXED_VTOTAL;
+		as_sdp->mode = DP_AS_SDP_AVT_DYNAMIC_VTOTAL;
 		as_sdp->vtotal = adjusted_mode->vtotal;
 		as_sdp->target_rr = 0;
 	}
@@ -4302,6 +4306,24 @@ intel_dp_mst_disconnect(struct intel_dp *intel_dp)
 static bool
 intel_dp_get_sink_irq_esi(struct intel_dp *intel_dp, u8 *esi)
 {
+	struct intel_display *display = to_intel_display(intel_dp);
+	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
+
+	/*
+	 * Display WA for HSD #13013007775: mtl/arl/lnl
+	 * Read the sink count and link service IRQ registers in separate
+	 * transactions to prevent disconnecting the sink on a TBT link
+	 * inadvertently.
+	 */
+	if (IS_DISPLAY_VER(display, 14, 20) && !IS_BATTLEMAGE(i915)) {
+		if (drm_dp_dpcd_read(&intel_dp->aux, DP_SINK_COUNT_ESI, esi, 3) != 3)
+			return false;
+
+		/* DP_SINK_COUNT_ESI + 3 == DP_LINK_SERVICE_IRQ_VECTOR_ESI0 */
+		return drm_dp_dpcd_readb(&intel_dp->aux, DP_LINK_SERVICE_IRQ_VECTOR_ESI0,
+					 &esi[3]) == 1;
+	}
+
 	return drm_dp_dpcd_read(&intel_dp->aux, DP_SINK_COUNT_ESI, esi, 4) == 4;
 }
 
diff --git a/drivers/gpu/drm/i915/display/intel_dp_link_training.c b/drivers/gpu/drm/i915/display/intel_dp_link_training.c
index 40bedc31d6bf..5d8f93d4cdc6 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_link_training.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_link_training.c
@@ -1561,7 +1561,7 @@ intel_dp_128b132b_link_train(struct intel_dp *intel_dp,
 
 	if (wait_for(intel_dp_128b132b_intra_hop(intel_dp, crtc_state) == 0, 500)) {
 		lt_err(intel_dp, DP_PHY_DPRX, "128b/132b intra-hop not clear\n");
-		return false;
+		goto out;
 	}
 
 	if (intel_dp_128b132b_lane_eq(intel_dp, crtc_state) &&
@@ -1573,6 +1573,19 @@ intel_dp_128b132b_link_train(struct intel_dp *intel_dp,
 	       passed ? "passed" : "failed",
 	       crtc_state->port_clock, crtc_state->lane_count);
 
+out:
+	/*
+	 * Ensure that the training pattern does get set to TPS2 even in case
+	 * of a failure, as is the case at the end of a passing link training
+	 * and what is expected by the transcoder. Leaving TPS1 set (and
+	 * disabling the link train mode in DP_TP_CTL later from TPS1 directly)
+	 * would result in a stuck transcoder HW state and flip-done timeouts
+	 * later in the modeset sequence.
+	 */
+	if (!passed)
+		intel_dp_program_link_training_pattern(intel_dp, crtc_state,
+						       DP_PHY_DPRX, DP_TRAINING_PATTERN_2);
+
 	return passed;
 }
 
diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.c b/drivers/gpu/drm/i915/display/intel_hdmi.c
index cd9ee171e0df..c5b2fbaeff89 100644
--- a/drivers/gpu/drm/i915/display/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/display/intel_hdmi.c
@@ -3015,7 +3015,7 @@ void intel_infoframe_init(struct intel_digital_port *dig_port)
 	}
 }
 
-void intel_hdmi_init_connector(struct intel_digital_port *dig_port,
+bool intel_hdmi_init_connector(struct intel_digital_port *dig_port,
 			       struct intel_connector *intel_connector)
 {
 	struct intel_display *display = to_intel_display(dig_port);
@@ -3033,17 +3033,17 @@ void intel_hdmi_init_connector(struct intel_digital_port *dig_port,
 		    intel_encoder->base.base.id, intel_encoder->base.name);
 
 	if (DISPLAY_VER(display) < 12 && drm_WARN_ON(dev, port == PORT_A))
-		return;
+		return false;
 
 	if (drm_WARN(dev, dig_port->max_lanes < 4,
 		     "Not enough lanes (%d) for HDMI on [ENCODER:%d:%s]\n",
 		     dig_port->max_lanes, intel_encoder->base.base.id,
 		     intel_encoder->base.name))
-		return;
+		return false;
 
 	ddc_pin = intel_hdmi_ddc_pin(intel_encoder);
 	if (!ddc_pin)
-		return;
+		return false;
 
 	drm_connector_init_with_ddc(dev, connector,
 				    &intel_hdmi_connector_funcs,
@@ -3088,6 +3088,8 @@ void intel_hdmi_init_connector(struct intel_digital_port *dig_port,
 					   &conn_info);
 	if (!intel_hdmi->cec_notifier)
 		drm_dbg_kms(display->drm, "CEC notifier get failed\n");
+
+	return true;
 }
 
 /*
diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.h b/drivers/gpu/drm/i915/display/intel_hdmi.h
index 9b97623665c5..fc64a3affc71 100644
--- a/drivers/gpu/drm/i915/display/intel_hdmi.h
+++ b/drivers/gpu/drm/i915/display/intel_hdmi.h
@@ -22,7 +22,7 @@ struct intel_encoder;
 struct intel_hdmi;
 union hdmi_infoframe;
 
-void intel_hdmi_init_connector(struct intel_digital_port *dig_port,
+bool intel_hdmi_init_connector(struct intel_digital_port *dig_port,
 			       struct intel_connector *intel_connector);
 bool intel_hdmi_compute_has_hdmi_sink(struct intel_encoder *encoder,
 				      const struct intel_crtc_state *crtc_state,
diff --git a/drivers/gpu/drm/i915/display/intel_psr_regs.h b/drivers/gpu/drm/i915/display/intel_psr_regs.h
index 642bb15fb547..25c0424e34db 100644
--- a/drivers/gpu/drm/i915/display/intel_psr_regs.h
+++ b/drivers/gpu/drm/i915/display/intel_psr_regs.h
@@ -314,8 +314,8 @@
 #define  PORT_ALPM_LFPS_CTL_LFPS_HALF_CYCLE_DURATION_MASK	REG_GENMASK(20, 16)
 #define  PORT_ALPM_LFPS_CTL_LFPS_HALF_CYCLE_DURATION(val)	REG_FIELD_PREP(PORT_ALPM_LFPS_CTL_LFPS_HALF_CYCLE_DURATION_MASK, val)
 #define  PORT_ALPM_LFPS_CTL_FIRST_LFPS_HALF_CYCLE_DURATION_MASK	REG_GENMASK(12, 8)
-#define  PORT_ALPM_LFPS_CTL_FIRST_LFPS_HALF_CYCLE_DURATION(val)	REG_FIELD_PREP(PORT_ALPM_LFPS_CTL_LFPS_HALF_CYCLE_DURATION_MASK, val)
+#define  PORT_ALPM_LFPS_CTL_FIRST_LFPS_HALF_CYCLE_DURATION(val)	REG_FIELD_PREP(PORT_ALPM_LFPS_CTL_FIRST_LFPS_HALF_CYCLE_DURATION_MASK, val)
 #define  PORT_ALPM_LFPS_CTL_LAST_LFPS_HALF_CYCLE_DURATION_MASK	REG_GENMASK(4, 0)
-#define  PORT_ALPM_LFPS_CTL_LAST_LFPS_HALF_CYCLE_DURATION(val)	REG_FIELD_PREP(PORT_ALPM_LFPS_CTL_LFPS_HALF_CYCLE_DURATION_MASK, val)
+#define  PORT_ALPM_LFPS_CTL_LAST_LFPS_HALF_CYCLE_DURATION(val)	REG_FIELD_PREP(PORT_ALPM_LFPS_CTL_LAST_LFPS_HALF_CYCLE_DURATION_MASK, val)
 
 #endif /* __INTEL_PSR_REGS_H__ */
diff --git a/drivers/gpu/drm/i915/display/intel_sprite.c b/drivers/gpu/drm/i915/display/intel_sprite.c
index e657b09ede99..e6fadcef58e0 100644
--- a/drivers/gpu/drm/i915/display/intel_sprite.c
+++ b/drivers/gpu/drm/i915/display/intel_sprite.c
@@ -378,7 +378,8 @@ static void vlv_sprite_update_gamma(const struct intel_plane_state *plane_state)
 }
 
 static void
-vlv_sprite_update_noarm(struct intel_plane *plane,
+vlv_sprite_update_noarm(struct intel_dsb *dsb,
+			struct intel_plane *plane,
 			const struct intel_crtc_state *crtc_state,
 			const struct intel_plane_state *plane_state)
 {
@@ -399,7 +400,8 @@ vlv_sprite_update_noarm(struct intel_plane *plane,
 }
 
 static void
-vlv_sprite_update_arm(struct intel_plane *plane,
+vlv_sprite_update_arm(struct intel_dsb *dsb,
+		      struct intel_plane *plane,
 		      const struct intel_crtc_state *crtc_state,
 		      const struct intel_plane_state *plane_state)
 {
@@ -449,7 +451,8 @@ vlv_sprite_update_arm(struct intel_plane *plane,
 }
 
 static void
-vlv_sprite_disable_arm(struct intel_plane *plane,
+vlv_sprite_disable_arm(struct intel_dsb *dsb,
+		       struct intel_plane *plane,
 		       const struct intel_crtc_state *crtc_state)
 {
 	struct intel_display *display = to_intel_display(plane->base.dev);
@@ -795,7 +798,8 @@ static void ivb_sprite_update_gamma(const struct intel_plane_state *plane_state)
 }
 
 static void
-ivb_sprite_update_noarm(struct intel_plane *plane,
+ivb_sprite_update_noarm(struct intel_dsb *dsb,
+			struct intel_plane *plane,
 			const struct intel_crtc_state *crtc_state,
 			const struct intel_plane_state *plane_state)
 {
@@ -826,7 +830,8 @@ ivb_sprite_update_noarm(struct intel_plane *plane,
 }
 
 static void
-ivb_sprite_update_arm(struct intel_plane *plane,
+ivb_sprite_update_arm(struct intel_dsb *dsb,
+		      struct intel_plane *plane,
 		      const struct intel_crtc_state *crtc_state,
 		      const struct intel_plane_state *plane_state)
 {
@@ -874,7 +879,8 @@ ivb_sprite_update_arm(struct intel_plane *plane,
 }
 
 static void
-ivb_sprite_disable_arm(struct intel_plane *plane,
+ivb_sprite_disable_arm(struct intel_dsb *dsb,
+		       struct intel_plane *plane,
 		       const struct intel_crtc_state *crtc_state)
 {
 	struct intel_display *display = to_intel_display(plane->base.dev);
@@ -1133,7 +1139,8 @@ static void ilk_sprite_update_gamma(const struct intel_plane_state *plane_state)
 }
 
 static void
-g4x_sprite_update_noarm(struct intel_plane *plane,
+g4x_sprite_update_noarm(struct intel_dsb *dsb,
+			struct intel_plane *plane,
 			const struct intel_crtc_state *crtc_state,
 			const struct intel_plane_state *plane_state)
 {
@@ -1162,7 +1169,8 @@ g4x_sprite_update_noarm(struct intel_plane *plane,
 }
 
 static void
-g4x_sprite_update_arm(struct intel_plane *plane,
+g4x_sprite_update_arm(struct intel_dsb *dsb,
+		      struct intel_plane *plane,
 		      const struct intel_crtc_state *crtc_state,
 		      const struct intel_plane_state *plane_state)
 {
@@ -1206,7 +1214,8 @@ g4x_sprite_update_arm(struct intel_plane *plane,
 }
 
 static void
-g4x_sprite_disable_arm(struct intel_plane *plane,
+g4x_sprite_disable_arm(struct intel_dsb *dsb,
+		       struct intel_plane *plane,
 		       const struct intel_crtc_state *crtc_state)
 {
 	struct intel_display *display = to_intel_display(plane->base.dev);
diff --git a/drivers/gpu/drm/i915/display/skl_universal_plane.c b/drivers/gpu/drm/i915/display/skl_universal_plane.c
index c8720d31d101..7f77a76309bd 100644
--- a/drivers/gpu/drm/i915/display/skl_universal_plane.c
+++ b/drivers/gpu/drm/i915/display/skl_universal_plane.c
@@ -105,8 +105,6 @@ static const u32 icl_sdr_y_plane_formats[] = {
 	DRM_FORMAT_Y216,
 	DRM_FORMAT_XYUV8888,
 	DRM_FORMAT_XVYU2101010,
-	DRM_FORMAT_XVYU12_16161616,
-	DRM_FORMAT_XVYU16161616,
 };
 
 static const u32 icl_sdr_uv_plane_formats[] = {
@@ -133,8 +131,6 @@ static const u32 icl_sdr_uv_plane_formats[] = {
 	DRM_FORMAT_Y216,
 	DRM_FORMAT_XYUV8888,
 	DRM_FORMAT_XVYU2101010,
-	DRM_FORMAT_XVYU12_16161616,
-	DRM_FORMAT_XVYU16161616,
 };
 
 static const u32 icl_hdr_plane_formats[] = {
@@ -593,11 +589,11 @@ static u32 skl_plane_min_alignment(struct intel_plane *plane,
  * in full-range YCbCr.
  */
 static void
-icl_program_input_csc(struct intel_plane *plane,
-		      const struct intel_crtc_state *crtc_state,
+icl_program_input_csc(struct intel_dsb *dsb,
+		      struct intel_plane *plane,
 		      const struct intel_plane_state *plane_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
+	struct intel_display *display = to_intel_display(plane->base.dev);
 	enum pipe pipe = plane->pipe;
 	enum plane_id plane_id = plane->id;
 
@@ -641,31 +637,31 @@ icl_program_input_csc(struct intel_plane *plane,
 	};
 	const u16 *csc = input_csc_matrix[plane_state->hw.color_encoding];
 
-	intel_de_write_fw(dev_priv, PLANE_INPUT_CSC_COEFF(pipe, plane_id, 0),
-			  ROFF(csc[0]) | GOFF(csc[1]));
-	intel_de_write_fw(dev_priv, PLANE_INPUT_CSC_COEFF(pipe, plane_id, 1),
-			  BOFF(csc[2]));
-	intel_de_write_fw(dev_priv, PLANE_INPUT_CSC_COEFF(pipe, plane_id, 2),
-			  ROFF(csc[3]) | GOFF(csc[4]));
-	intel_de_write_fw(dev_priv, PLANE_INPUT_CSC_COEFF(pipe, plane_id, 3),
-			  BOFF(csc[5]));
-	intel_de_write_fw(dev_priv, PLANE_INPUT_CSC_COEFF(pipe, plane_id, 4),
-			  ROFF(csc[6]) | GOFF(csc[7]));
-	intel_de_write_fw(dev_priv, PLANE_INPUT_CSC_COEFF(pipe, plane_id, 5),
-			  BOFF(csc[8]));
-
-	intel_de_write_fw(dev_priv, PLANE_INPUT_CSC_PREOFF(pipe, plane_id, 0),
-			  PREOFF_YUV_TO_RGB_HI);
-	intel_de_write_fw(dev_priv, PLANE_INPUT_CSC_PREOFF(pipe, plane_id, 1),
-			  PREOFF_YUV_TO_RGB_ME);
-	intel_de_write_fw(dev_priv, PLANE_INPUT_CSC_PREOFF(pipe, plane_id, 2),
-			  PREOFF_YUV_TO_RGB_LO);
-	intel_de_write_fw(dev_priv,
-			  PLANE_INPUT_CSC_POSTOFF(pipe, plane_id, 0), 0x0);
-	intel_de_write_fw(dev_priv,
-			  PLANE_INPUT_CSC_POSTOFF(pipe, plane_id, 1), 0x0);
-	intel_de_write_fw(dev_priv,
-			  PLANE_INPUT_CSC_POSTOFF(pipe, plane_id, 2), 0x0);
+	intel_de_write_dsb(display, dsb, PLANE_INPUT_CSC_COEFF(pipe, plane_id, 0),
+			   ROFF(csc[0]) | GOFF(csc[1]));
+	intel_de_write_dsb(display, dsb, PLANE_INPUT_CSC_COEFF(pipe, plane_id, 1),
+			   BOFF(csc[2]));
+	intel_de_write_dsb(display, dsb, PLANE_INPUT_CSC_COEFF(pipe, plane_id, 2),
+			   ROFF(csc[3]) | GOFF(csc[4]));
+	intel_de_write_dsb(display, dsb, PLANE_INPUT_CSC_COEFF(pipe, plane_id, 3),
+			   BOFF(csc[5]));
+	intel_de_write_dsb(display, dsb, PLANE_INPUT_CSC_COEFF(pipe, plane_id, 4),
+			   ROFF(csc[6]) | GOFF(csc[7]));
+	intel_de_write_dsb(display, dsb, PLANE_INPUT_CSC_COEFF(pipe, plane_id, 5),
+			   BOFF(csc[8]));
+
+	intel_de_write_dsb(display, dsb, PLANE_INPUT_CSC_PREOFF(pipe, plane_id, 0),
+			   PREOFF_YUV_TO_RGB_HI);
+	intel_de_write_dsb(display, dsb, PLANE_INPUT_CSC_PREOFF(pipe, plane_id, 1),
+			   PREOFF_YUV_TO_RGB_ME);
+	intel_de_write_dsb(display, dsb, PLANE_INPUT_CSC_PREOFF(pipe, plane_id, 2),
+			   PREOFF_YUV_TO_RGB_LO);
+	intel_de_write_dsb(display, dsb,
+			   PLANE_INPUT_CSC_POSTOFF(pipe, plane_id, 0), 0x0);
+	intel_de_write_dsb(display, dsb,
+			   PLANE_INPUT_CSC_POSTOFF(pipe, plane_id, 1), 0x0);
+	intel_de_write_dsb(display, dsb,
+			   PLANE_INPUT_CSC_POSTOFF(pipe, plane_id, 2), 0x0);
 }
 
 static unsigned int skl_plane_stride_mult(const struct drm_framebuffer *fb,
@@ -719,9 +715,11 @@ static u32 skl_plane_wm_reg_val(const struct skl_wm_level *level)
 	return val;
 }
 
-static void skl_write_plane_wm(struct intel_plane *plane,
+static void skl_write_plane_wm(struct intel_dsb *dsb,
+			       struct intel_plane *plane,
 			       const struct intel_crtc_state *crtc_state)
 {
+	struct intel_display *display = to_intel_display(plane->base.dev);
 	struct drm_i915_private *i915 = to_i915(plane->base.dev);
 	enum plane_id plane_id = plane->id;
 	enum pipe pipe = plane->pipe;
@@ -733,71 +731,75 @@ static void skl_write_plane_wm(struct intel_plane *plane,
 	int level;
 
 	for (level = 0; level < i915->display.wm.num_levels; level++)
-		intel_de_write_fw(i915, PLANE_WM(pipe, plane_id, level),
-				  skl_plane_wm_reg_val(skl_plane_wm_level(pipe_wm, plane_id, level)));
+		intel_de_write_dsb(display, dsb, PLANE_WM(pipe, plane_id, level),
+				   skl_plane_wm_reg_val(skl_plane_wm_level(pipe_wm, plane_id, level)));
 
-	intel_de_write_fw(i915, PLANE_WM_TRANS(pipe, plane_id),
-			  skl_plane_wm_reg_val(skl_plane_trans_wm(pipe_wm, plane_id)));
+	intel_de_write_dsb(display, dsb, PLANE_WM_TRANS(pipe, plane_id),
+			   skl_plane_wm_reg_val(skl_plane_trans_wm(pipe_wm, plane_id)));
 
 	if (HAS_HW_SAGV_WM(i915)) {
 		const struct skl_plane_wm *wm = &pipe_wm->planes[plane_id];
 
-		intel_de_write_fw(i915, PLANE_WM_SAGV(pipe, plane_id),
-				  skl_plane_wm_reg_val(&wm->sagv.wm0));
-		intel_de_write_fw(i915, PLANE_WM_SAGV_TRANS(pipe, plane_id),
-				  skl_plane_wm_reg_val(&wm->sagv.trans_wm));
+		intel_de_write_dsb(display, dsb, PLANE_WM_SAGV(pipe, plane_id),
+				   skl_plane_wm_reg_val(&wm->sagv.wm0));
+		intel_de_write_dsb(display, dsb, PLANE_WM_SAGV_TRANS(pipe, plane_id),
+				   skl_plane_wm_reg_val(&wm->sagv.trans_wm));
 	}
 
-	intel_de_write_fw(i915, PLANE_BUF_CFG(pipe, plane_id),
-			  skl_plane_ddb_reg_val(ddb));
+	intel_de_write_dsb(display, dsb, PLANE_BUF_CFG(pipe, plane_id),
+			   skl_plane_ddb_reg_val(ddb));
 
 	if (DISPLAY_VER(i915) < 11)
-		intel_de_write_fw(i915, PLANE_NV12_BUF_CFG(pipe, plane_id),
-				  skl_plane_ddb_reg_val(ddb_y));
+		intel_de_write_dsb(display, dsb, PLANE_NV12_BUF_CFG(pipe, plane_id),
+				   skl_plane_ddb_reg_val(ddb_y));
 }
 
 static void
-skl_plane_disable_arm(struct intel_plane *plane,
+skl_plane_disable_arm(struct intel_dsb *dsb,
+		      struct intel_plane *plane,
 		      const struct intel_crtc_state *crtc_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
+	struct intel_display *display = to_intel_display(plane->base.dev);
 	enum plane_id plane_id = plane->id;
 	enum pipe pipe = plane->pipe;
 
-	skl_write_plane_wm(plane, crtc_state);
+	skl_write_plane_wm(dsb, plane, crtc_state);
 
-	intel_de_write_fw(dev_priv, PLANE_CTL(pipe, plane_id), 0);
-	intel_de_write_fw(dev_priv, PLANE_SURF(pipe, plane_id), 0);
+	intel_de_write_dsb(display, dsb, PLANE_CTL(pipe, plane_id), 0);
+	intel_de_write_dsb(display, dsb, PLANE_SURF(pipe, plane_id), 0);
 }
 
-static void icl_plane_disable_sel_fetch_arm(struct intel_plane *plane,
+static void icl_plane_disable_sel_fetch_arm(struct intel_dsb *dsb,
+					    struct intel_plane *plane,
 					    const struct intel_crtc_state *crtc_state)
 {
-	struct drm_i915_private *i915 = to_i915(plane->base.dev);
+	struct intel_display *display = to_intel_display(plane->base.dev);
 	enum pipe pipe = plane->pipe;
 
 	if (!crtc_state->enable_psr2_sel_fetch)
 		return;
 
-	intel_de_write_fw(i915, SEL_FETCH_PLANE_CTL(pipe, plane->id), 0);
+	intel_de_write_dsb(display, dsb, SEL_FETCH_PLANE_CTL(pipe, plane->id), 0);
 }
 
 static void
-icl_plane_disable_arm(struct intel_plane *plane,
+icl_plane_disable_arm(struct intel_dsb *dsb,
+		      struct intel_plane *plane,
 		      const struct intel_crtc_state *crtc_state)
 {
+	struct intel_display *display = to_intel_display(plane->base.dev);
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
 	enum plane_id plane_id = plane->id;
 	enum pipe pipe = plane->pipe;
 
 	if (icl_is_hdr_plane(dev_priv, plane_id))
-		intel_de_write_fw(dev_priv, PLANE_CUS_CTL(pipe, plane_id), 0);
+		intel_de_write_dsb(display, dsb, PLANE_CUS_CTL(pipe, plane_id), 0);
 
-	skl_write_plane_wm(plane, crtc_state);
+	skl_write_plane_wm(dsb, plane, crtc_state);
 
-	icl_plane_disable_sel_fetch_arm(plane, crtc_state);
-	intel_de_write_fw(dev_priv, PLANE_CTL(pipe, plane_id), 0);
-	intel_de_write_fw(dev_priv, PLANE_SURF(pipe, plane_id), 0);
+	icl_plane_disable_sel_fetch_arm(dsb, plane, crtc_state);
+	intel_de_write_dsb(display, dsb, PLANE_CTL(pipe, plane_id), 0);
+	intel_de_write_dsb(display, dsb, PLANE_SURF(pipe, plane_id), 0);
 }
 
 static bool
@@ -1234,28 +1236,30 @@ static u32 skl_plane_keymsk(const struct intel_plane_state *plane_state)
 	return keymsk;
 }
 
-static void icl_plane_csc_load_black(struct intel_plane *plane)
+static void icl_plane_csc_load_black(struct intel_dsb *dsb,
+				     struct intel_plane *plane,
+				     const struct intel_crtc_state *crtc_state)
 {
-	struct drm_i915_private *i915 = to_i915(plane->base.dev);
+	struct intel_display *display = to_intel_display(plane->base.dev);
 	enum plane_id plane_id = plane->id;
 	enum pipe pipe = plane->pipe;
 
-	intel_de_write_fw(i915, PLANE_CSC_COEFF(pipe, plane_id, 0), 0);
-	intel_de_write_fw(i915, PLANE_CSC_COEFF(pipe, plane_id, 1), 0);
+	intel_de_write_dsb(display, dsb, PLANE_CSC_COEFF(pipe, plane_id, 0), 0);
+	intel_de_write_dsb(display, dsb, PLANE_CSC_COEFF(pipe, plane_id, 1), 0);
 
-	intel_de_write_fw(i915, PLANE_CSC_COEFF(pipe, plane_id, 2), 0);
-	intel_de_write_fw(i915, PLANE_CSC_COEFF(pipe, plane_id, 3), 0);
+	intel_de_write_dsb(display, dsb, PLANE_CSC_COEFF(pipe, plane_id, 2), 0);
+	intel_de_write_dsb(display, dsb, PLANE_CSC_COEFF(pipe, plane_id, 3), 0);
 
-	intel_de_write_fw(i915, PLANE_CSC_COEFF(pipe, plane_id, 4), 0);
-	intel_de_write_fw(i915, PLANE_CSC_COEFF(pipe, plane_id, 5), 0);
+	intel_de_write_dsb(display, dsb, PLANE_CSC_COEFF(pipe, plane_id, 4), 0);
+	intel_de_write_dsb(display, dsb, PLANE_CSC_COEFF(pipe, plane_id, 5), 0);
 
-	intel_de_write_fw(i915, PLANE_CSC_PREOFF(pipe, plane_id, 0), 0);
-	intel_de_write_fw(i915, PLANE_CSC_PREOFF(pipe, plane_id, 1), 0);
-	intel_de_write_fw(i915, PLANE_CSC_PREOFF(pipe, plane_id, 2), 0);
+	intel_de_write_dsb(display, dsb, PLANE_CSC_PREOFF(pipe, plane_id, 0), 0);
+	intel_de_write_dsb(display, dsb, PLANE_CSC_PREOFF(pipe, plane_id, 1), 0);
+	intel_de_write_dsb(display, dsb, PLANE_CSC_PREOFF(pipe, plane_id, 2), 0);
 
-	intel_de_write_fw(i915, PLANE_CSC_POSTOFF(pipe, plane_id, 0), 0);
-	intel_de_write_fw(i915, PLANE_CSC_POSTOFF(pipe, plane_id, 1), 0);
-	intel_de_write_fw(i915, PLANE_CSC_POSTOFF(pipe, plane_id, 2), 0);
+	intel_de_write_dsb(display, dsb, PLANE_CSC_POSTOFF(pipe, plane_id, 0), 0);
+	intel_de_write_dsb(display, dsb, PLANE_CSC_POSTOFF(pipe, plane_id, 1), 0);
+	intel_de_write_dsb(display, dsb, PLANE_CSC_POSTOFF(pipe, plane_id, 2), 0);
 }
 
 static int icl_plane_color_plane(const struct intel_plane_state *plane_state)
@@ -1268,11 +1272,12 @@ static int icl_plane_color_plane(const struct intel_plane_state *plane_state)
 }
 
 static void
-skl_plane_update_noarm(struct intel_plane *plane,
+skl_plane_update_noarm(struct intel_dsb *dsb,
+		       struct intel_plane *plane,
 		       const struct intel_crtc_state *crtc_state,
 		       const struct intel_plane_state *plane_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
+	struct intel_display *display = to_intel_display(plane->base.dev);
 	enum plane_id plane_id = plane->id;
 	enum pipe pipe = plane->pipe;
 	u32 stride = skl_plane_stride(plane_state, 0);
@@ -1287,21 +1292,23 @@ skl_plane_update_noarm(struct intel_plane *plane,
 		crtc_y = 0;
 	}
 
-	intel_de_write_fw(dev_priv, PLANE_STRIDE(pipe, plane_id),
-			  PLANE_STRIDE_(stride));
-	intel_de_write_fw(dev_priv, PLANE_POS(pipe, plane_id),
-			  PLANE_POS_Y(crtc_y) | PLANE_POS_X(crtc_x));
-	intel_de_write_fw(dev_priv, PLANE_SIZE(pipe, plane_id),
-			  PLANE_HEIGHT(src_h - 1) | PLANE_WIDTH(src_w - 1));
+	intel_de_write_dsb(display, dsb, PLANE_STRIDE(pipe, plane_id),
+			   PLANE_STRIDE_(stride));
+	intel_de_write_dsb(display, dsb, PLANE_POS(pipe, plane_id),
+			   PLANE_POS_Y(crtc_y) | PLANE_POS_X(crtc_x));
+	intel_de_write_dsb(display, dsb, PLANE_SIZE(pipe, plane_id),
+			   PLANE_HEIGHT(src_h - 1) | PLANE_WIDTH(src_w - 1));
 
-	skl_write_plane_wm(plane, crtc_state);
+	skl_write_plane_wm(dsb, plane, crtc_state);
 }
 
 static void
-skl_plane_update_arm(struct intel_plane *plane,
+skl_plane_update_arm(struct intel_dsb *dsb,
+		     struct intel_plane *plane,
 		     const struct intel_crtc_state *crtc_state,
 		     const struct intel_plane_state *plane_state)
 {
+	struct intel_display *display = to_intel_display(plane->base.dev);
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
 	enum plane_id plane_id = plane->id;
 	enum pipe pipe = plane->pipe;
@@ -1321,22 +1328,26 @@ skl_plane_update_arm(struct intel_plane *plane,
 		plane_color_ctl = plane_state->color_ctl |
 			glk_plane_color_ctl_crtc(crtc_state);
 
-	intel_de_write_fw(dev_priv, PLANE_KEYVAL(pipe, plane_id), skl_plane_keyval(plane_state));
-	intel_de_write_fw(dev_priv, PLANE_KEYMSK(pipe, plane_id), skl_plane_keymsk(plane_state));
-	intel_de_write_fw(dev_priv, PLANE_KEYMAX(pipe, plane_id), skl_plane_keymax(plane_state));
+	intel_de_write_dsb(display, dsb, PLANE_KEYVAL(pipe, plane_id),
+			   skl_plane_keyval(plane_state));
+	intel_de_write_dsb(display, dsb, PLANE_KEYMSK(pipe, plane_id),
+			   skl_plane_keymsk(plane_state));
+	intel_de_write_dsb(display, dsb, PLANE_KEYMAX(pipe, plane_id),
+			   skl_plane_keymax(plane_state));
 
-	intel_de_write_fw(dev_priv, PLANE_OFFSET(pipe, plane_id),
-			  PLANE_OFFSET_Y(y) | PLANE_OFFSET_X(x));
+	intel_de_write_dsb(display, dsb, PLANE_OFFSET(pipe, plane_id),
+			   PLANE_OFFSET_Y(y) | PLANE_OFFSET_X(x));
 
-	intel_de_write_fw(dev_priv, PLANE_AUX_DIST(pipe, plane_id),
-			  skl_plane_aux_dist(plane_state, 0));
+	intel_de_write_dsb(display, dsb, PLANE_AUX_DIST(pipe, plane_id),
+			   skl_plane_aux_dist(plane_state, 0));
 
-	intel_de_write_fw(dev_priv, PLANE_AUX_OFFSET(pipe, plane_id),
-			  PLANE_OFFSET_Y(plane_state->view.color_plane[1].y) |
-			  PLANE_OFFSET_X(plane_state->view.color_plane[1].x));
+	intel_de_write_dsb(display, dsb, PLANE_AUX_OFFSET(pipe, plane_id),
+			   PLANE_OFFSET_Y(plane_state->view.color_plane[1].y) |
+			   PLANE_OFFSET_X(plane_state->view.color_plane[1].x));
 
 	if (DISPLAY_VER(dev_priv) >= 10)
-		intel_de_write_fw(dev_priv, PLANE_COLOR_CTL(pipe, plane_id), plane_color_ctl);
+		intel_de_write_dsb(display, dsb, PLANE_COLOR_CTL(pipe, plane_id),
+				   plane_color_ctl);
 
 	/*
 	 * Enable the scaler before the plane so that we don't
@@ -1353,17 +1364,19 @@ skl_plane_update_arm(struct intel_plane *plane,
 	 * disabled. Try to make the plane enable atomic by writing
 	 * the control register just before the surface register.
 	 */
-	intel_de_write_fw(dev_priv, PLANE_CTL(pipe, plane_id), plane_ctl);
-	intel_de_write_fw(dev_priv, PLANE_SURF(pipe, plane_id),
-			  skl_plane_surf(plane_state, 0));
+	intel_de_write_dsb(display, dsb, PLANE_CTL(pipe, plane_id),
+			   plane_ctl);
+	intel_de_write_dsb(display, dsb, PLANE_SURF(pipe, plane_id),
+			   skl_plane_surf(plane_state, 0));
 }
 
-static void icl_plane_update_sel_fetch_noarm(struct intel_plane *plane,
+static void icl_plane_update_sel_fetch_noarm(struct intel_dsb *dsb,
+					     struct intel_plane *plane,
 					     const struct intel_crtc_state *crtc_state,
 					     const struct intel_plane_state *plane_state,
 					     int color_plane)
 {
-	struct drm_i915_private *i915 = to_i915(plane->base.dev);
+	struct intel_display *display = to_intel_display(plane->base.dev);
 	enum pipe pipe = plane->pipe;
 	const struct drm_rect *clip;
 	u32 val;
@@ -1380,7 +1393,7 @@ static void icl_plane_update_sel_fetch_noarm(struct intel_plane *plane,
 		y = (clip->y1 + plane_state->uapi.dst.y1);
 	val = y << 16;
 	val |= plane_state->uapi.dst.x1;
-	intel_de_write_fw(i915, SEL_FETCH_PLANE_POS(pipe, plane->id), val);
+	intel_de_write_dsb(display, dsb, SEL_FETCH_PLANE_POS(pipe, plane->id), val);
 
 	x = plane_state->view.color_plane[color_plane].x;
 
@@ -1395,20 +1408,21 @@ static void icl_plane_update_sel_fetch_noarm(struct intel_plane *plane,
 
 	val = y << 16 | x;
 
-	intel_de_write_fw(i915, SEL_FETCH_PLANE_OFFSET(pipe, plane->id),
-			  val);
+	intel_de_write_dsb(display, dsb, SEL_FETCH_PLANE_OFFSET(pipe, plane->id), val);
 
 	/* Sizes are 0 based */
 	val = (drm_rect_height(clip) - 1) << 16;
 	val |= (drm_rect_width(&plane_state->uapi.src) >> 16) - 1;
-	intel_de_write_fw(i915, SEL_FETCH_PLANE_SIZE(pipe, plane->id), val);
+	intel_de_write_dsb(display, dsb, SEL_FETCH_PLANE_SIZE(pipe, plane->id), val);
 }
 
 static void
-icl_plane_update_noarm(struct intel_plane *plane,
+icl_plane_update_noarm(struct intel_dsb *dsb,
+		       struct intel_plane *plane,
 		       const struct intel_crtc_state *crtc_state,
 		       const struct intel_plane_state *plane_state)
 {
+	struct intel_display *display = to_intel_display(plane->base.dev);
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
 	enum plane_id plane_id = plane->id;
 	enum pipe pipe = plane->pipe;
@@ -1432,76 +1446,82 @@ icl_plane_update_noarm(struct intel_plane *plane,
 		crtc_y = 0;
 	}
 
-	intel_de_write_fw(dev_priv, PLANE_STRIDE(pipe, plane_id),
-			  PLANE_STRIDE_(stride));
-	intel_de_write_fw(dev_priv, PLANE_POS(pipe, plane_id),
-			  PLANE_POS_Y(crtc_y) | PLANE_POS_X(crtc_x));
-	intel_de_write_fw(dev_priv, PLANE_SIZE(pipe, plane_id),
-			  PLANE_HEIGHT(src_h - 1) | PLANE_WIDTH(src_w - 1));
+	intel_de_write_dsb(display, dsb, PLANE_STRIDE(pipe, plane_id),
+			   PLANE_STRIDE_(stride));
+	intel_de_write_dsb(display, dsb, PLANE_POS(pipe, plane_id),
+			   PLANE_POS_Y(crtc_y) | PLANE_POS_X(crtc_x));
+	intel_de_write_dsb(display, dsb, PLANE_SIZE(pipe, plane_id),
+			   PLANE_HEIGHT(src_h - 1) | PLANE_WIDTH(src_w - 1));
 
-	intel_de_write_fw(dev_priv, PLANE_KEYVAL(pipe, plane_id), skl_plane_keyval(plane_state));
-	intel_de_write_fw(dev_priv, PLANE_KEYMSK(pipe, plane_id), skl_plane_keymsk(plane_state));
-	intel_de_write_fw(dev_priv, PLANE_KEYMAX(pipe, plane_id), skl_plane_keymax(plane_state));
+	intel_de_write_dsb(display, dsb, PLANE_KEYVAL(pipe, plane_id),
+			   skl_plane_keyval(plane_state));
+	intel_de_write_dsb(display, dsb, PLANE_KEYMSK(pipe, plane_id),
+			   skl_plane_keymsk(plane_state));
+	intel_de_write_dsb(display, dsb, PLANE_KEYMAX(pipe, plane_id),
+			   skl_plane_keymax(plane_state));
 
-	intel_de_write_fw(dev_priv, PLANE_OFFSET(pipe, plane_id),
-			  PLANE_OFFSET_Y(y) | PLANE_OFFSET_X(x));
+	intel_de_write_dsb(display, dsb, PLANE_OFFSET(pipe, plane_id),
+			   PLANE_OFFSET_Y(y) | PLANE_OFFSET_X(x));
 
 	if (intel_fb_is_rc_ccs_cc_modifier(fb->modifier)) {
-		intel_de_write_fw(dev_priv, PLANE_CC_VAL(pipe, plane_id, 0),
-				  lower_32_bits(plane_state->ccval));
-		intel_de_write_fw(dev_priv, PLANE_CC_VAL(pipe, plane_id, 1),
-				  upper_32_bits(plane_state->ccval));
+		intel_de_write_dsb(display, dsb, PLANE_CC_VAL(pipe, plane_id, 0),
+				   lower_32_bits(plane_state->ccval));
+		intel_de_write_dsb(display, dsb, PLANE_CC_VAL(pipe, plane_id, 1),
+				   upper_32_bits(plane_state->ccval));
 	}
 
 	/* FLAT CCS doesn't need to program AUX_DIST */
 	if (!HAS_FLAT_CCS(dev_priv) && DISPLAY_VER(dev_priv) < 20)
-		intel_de_write_fw(dev_priv, PLANE_AUX_DIST(pipe, plane_id),
-				  skl_plane_aux_dist(plane_state, color_plane));
+		intel_de_write_dsb(display, dsb, PLANE_AUX_DIST(pipe, plane_id),
+				   skl_plane_aux_dist(plane_state, color_plane));
 
 	if (icl_is_hdr_plane(dev_priv, plane_id))
-		intel_de_write_fw(dev_priv, PLANE_CUS_CTL(pipe, plane_id),
-				  plane_state->cus_ctl);
+		intel_de_write_dsb(display, dsb, PLANE_CUS_CTL(pipe, plane_id),
+				   plane_state->cus_ctl);
 
-	intel_de_write_fw(dev_priv, PLANE_COLOR_CTL(pipe, plane_id), plane_color_ctl);
+	intel_de_write_dsb(display, dsb, PLANE_COLOR_CTL(pipe, plane_id),
+			   plane_color_ctl);
 
 	if (fb->format->is_yuv && icl_is_hdr_plane(dev_priv, plane_id))
-		icl_program_input_csc(plane, crtc_state, plane_state);
+		icl_program_input_csc(dsb, plane, plane_state);
 
-	skl_write_plane_wm(plane, crtc_state);
+	skl_write_plane_wm(dsb, plane, crtc_state);
 
 	/*
 	 * FIXME: pxp session invalidation can hit any time even at time of commit
 	 * or after the commit, display content will be garbage.
 	 */
 	if (plane_state->force_black)
-		icl_plane_csc_load_black(plane);
+		icl_plane_csc_load_black(dsb, plane, crtc_state);
 
-	icl_plane_update_sel_fetch_noarm(plane, crtc_state, plane_state, color_plane);
+	icl_plane_update_sel_fetch_noarm(dsb, plane, crtc_state, plane_state, color_plane);
 }
 
-static void icl_plane_update_sel_fetch_arm(struct intel_plane *plane,
+static void icl_plane_update_sel_fetch_arm(struct intel_dsb *dsb,
+					   struct intel_plane *plane,
 					   const struct intel_crtc_state *crtc_state,
 					   const struct intel_plane_state *plane_state)
 {
-	struct drm_i915_private *i915 = to_i915(plane->base.dev);
+	struct intel_display *display = to_intel_display(plane->base.dev);
 	enum pipe pipe = plane->pipe;
 
 	if (!crtc_state->enable_psr2_sel_fetch)
 		return;
 
 	if (drm_rect_height(&plane_state->psr2_sel_fetch_area) > 0)
-		intel_de_write_fw(i915, SEL_FETCH_PLANE_CTL(pipe, plane->id),
-				  SEL_FETCH_PLANE_CTL_ENABLE);
+		intel_de_write_dsb(display, dsb, SEL_FETCH_PLANE_CTL(pipe, plane->id),
+				   SEL_FETCH_PLANE_CTL_ENABLE);
 	else
-		icl_plane_disable_sel_fetch_arm(plane, crtc_state);
+		icl_plane_disable_sel_fetch_arm(dsb, plane, crtc_state);
 }
 
 static void
-icl_plane_update_arm(struct intel_plane *plane,
+icl_plane_update_arm(struct intel_dsb *dsb,
+		     struct intel_plane *plane,
 		     const struct intel_crtc_state *crtc_state,
 		     const struct intel_plane_state *plane_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
+	struct intel_display *display = to_intel_display(plane->base.dev);
 	enum plane_id plane_id = plane->id;
 	enum pipe pipe = plane->pipe;
 	int color_plane = icl_plane_color_plane(plane_state);
@@ -1520,25 +1540,27 @@ icl_plane_update_arm(struct intel_plane *plane,
 	if (plane_state->scaler_id >= 0)
 		skl_program_plane_scaler(plane, crtc_state, plane_state);
 
-	icl_plane_update_sel_fetch_arm(plane, crtc_state, plane_state);
+	icl_plane_update_sel_fetch_arm(dsb, plane, crtc_state, plane_state);
 
 	/*
 	 * The control register self-arms if the plane was previously
 	 * disabled. Try to make the plane enable atomic by writing
 	 * the control register just before the surface register.
 	 */
-	intel_de_write_fw(dev_priv, PLANE_CTL(pipe, plane_id), plane_ctl);
-	intel_de_write_fw(dev_priv, PLANE_SURF(pipe, plane_id),
-			  skl_plane_surf(plane_state, color_plane));
+	intel_de_write_dsb(display, dsb, PLANE_CTL(pipe, plane_id),
+			   plane_ctl);
+	intel_de_write_dsb(display, dsb, PLANE_SURF(pipe, plane_id),
+			   skl_plane_surf(plane_state, color_plane));
 }
 
 static void
-skl_plane_async_flip(struct intel_plane *plane,
+skl_plane_async_flip(struct intel_dsb *dsb,
+		     struct intel_plane *plane,
 		     const struct intel_crtc_state *crtc_state,
 		     const struct intel_plane_state *plane_state,
 		     bool async_flip)
 {
-	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
+	struct intel_display *display = to_intel_display(plane->base.dev);
 	enum plane_id plane_id = plane->id;
 	enum pipe pipe = plane->pipe;
 	u32 plane_ctl = plane_state->ctl;
@@ -1548,9 +1570,10 @@ skl_plane_async_flip(struct intel_plane *plane,
 	if (async_flip)
 		plane_ctl |= PLANE_CTL_ASYNC_FLIP;
 
-	intel_de_write_fw(dev_priv, PLANE_CTL(pipe, plane_id), plane_ctl);
-	intel_de_write_fw(dev_priv, PLANE_SURF(pipe, plane_id),
-			  skl_plane_surf(plane_state, 0));
+	intel_de_write_dsb(display, dsb, PLANE_CTL(pipe, plane_id),
+			   plane_ctl);
+	intel_de_write_dsb(display, dsb, PLANE_SURF(pipe, plane_id),
+			   skl_plane_surf(plane_state, 0));
 }
 
 static bool intel_format_is_p01x(u32 format)
diff --git a/drivers/gpu/drm/i915/display/vlv_dsi.c b/drivers/gpu/drm/i915/display/vlv_dsi.c
index d21f3fb39706..3c7789ca6207 100644
--- a/drivers/gpu/drm/i915/display/vlv_dsi.c
+++ b/drivers/gpu/drm/i915/display/vlv_dsi.c
@@ -1059,7 +1059,7 @@ static void bxt_dsi_get_pipe_config(struct intel_encoder *encoder,
 				              BXT_MIPI_TRANS_VACTIVE(port));
 	adjusted_mode->crtc_vtotal =
 				intel_de_read(display,
-				              BXT_MIPI_TRANS_VTOTAL(port));
+				              BXT_MIPI_TRANS_VTOTAL(port)) + 1;
 
 	hactive = adjusted_mode->crtc_hdisplay;
 	hfp = intel_de_read(display, MIPI_HFP_COUNT(display, port));
@@ -1264,7 +1264,7 @@ static void set_dsi_timings(struct intel_encoder *encoder,
 			intel_de_write(display, BXT_MIPI_TRANS_VACTIVE(port),
 				       adjusted_mode->crtc_vdisplay);
 			intel_de_write(display, BXT_MIPI_TRANS_VTOTAL(port),
-				       adjusted_mode->crtc_vtotal);
+				       adjusted_mode->crtc_vtotal - 1);
 		}
 
 		intel_de_write(display, MIPI_HACTIVE_AREA_COUNT(display, port),
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
index 21274aa9bddd..c3dabb857960 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
@@ -164,6 +164,9 @@ static unsigned int tile_row_pages(const struct drm_i915_gem_object *obj)
  * 4 - Support multiple fault handlers per object depending on object's
  *     backing storage (a.k.a. MMAP_OFFSET).
  *
+ * 5 - Support multiple partial mmaps(mmap part of BO + unmap a offset, multiple
+ *     times with different size and offset).
+ *
  * Restrictions:
  *
  *  * snoopable objects cannot be accessed via the GTT. It can cause machine
@@ -191,7 +194,7 @@ static unsigned int tile_row_pages(const struct drm_i915_gem_object *obj)
  */
 int i915_gem_mmap_gtt_version(void)
 {
-	return 4;
+	return 5;
 }
 
 static inline struct i915_gtt_view
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
index fe69f2c8527d..ae3343c81a64 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
@@ -209,8 +209,6 @@ static int shmem_get_pages(struct drm_i915_gem_object *obj)
 	struct address_space *mapping = obj->base.filp->f_mapping;
 	unsigned int max_segment = i915_sg_segment_size(i915->drm.dev);
 	struct sg_table *st;
-	struct sgt_iter sgt_iter;
-	struct page *page;
 	int ret;
 
 	/*
@@ -239,9 +237,7 @@ rebuild_st:
 		 * for PAGE_SIZE chunks instead may be helpful.
 		 */
 		if (max_segment > PAGE_SIZE) {
-			for_each_sgt_page(page, sgt_iter, st)
-				put_page(page);
-			sg_free_table(st);
+			shmem_sg_free_table(st, mapping, false, false);
 			kfree(st);
 
 			max_segment = PAGE_SIZE;
diff --git a/drivers/gpu/drm/i915/gt/intel_gsc.c b/drivers/gpu/drm/i915/gt/intel_gsc.c
index 1e925c75fb08..c43febc862dc 100644
--- a/drivers/gpu/drm/i915/gt/intel_gsc.c
+++ b/drivers/gpu/drm/i915/gt/intel_gsc.c
@@ -284,7 +284,7 @@ static void gsc_irq_handler(struct intel_gt *gt, unsigned int intf_id)
 	if (gt->gsc.intf[intf_id].irq < 0)
 		return;
 
-	ret = generic_handle_irq(gt->gsc.intf[intf_id].irq);
+	ret = generic_handle_irq_safe(gt->gsc.intf[intf_id].irq);
 	if (ret)
 		gt_err_ratelimited(gt, "error handling GSC irq: %d\n", ret);
 }
diff --git a/drivers/gpu/drm/i915/gt/intel_rc6.c b/drivers/gpu/drm/i915/gt/intel_rc6.c
index 9378d5901c49..9ca42589da4d 100644
--- a/drivers/gpu/drm/i915/gt/intel_rc6.c
+++ b/drivers/gpu/drm/i915/gt/intel_rc6.c
@@ -117,21 +117,10 @@ static void gen11_rc6_enable(struct intel_rc6 *rc6)
 			GEN6_RC_CTL_RC6_ENABLE |
 			GEN6_RC_CTL_EI_MODE(1);
 
-	/*
-	 * BSpec 52698 - Render powergating must be off.
-	 * FIXME BSpec is outdated, disabling powergating for MTL is just
-	 * temporary wa and should be removed after fixing real cause
-	 * of forcewake timeouts.
-	 */
-	if (IS_GFX_GT_IP_RANGE(gt, IP_VER(12, 70), IP_VER(12, 74)))
-		pg_enable =
-			GEN9_MEDIA_PG_ENABLE |
-			GEN11_MEDIA_SAMPLER_PG_ENABLE;
-	else
-		pg_enable =
-			GEN9_RENDER_PG_ENABLE |
-			GEN9_MEDIA_PG_ENABLE |
-			GEN11_MEDIA_SAMPLER_PG_ENABLE;
+	pg_enable =
+		GEN9_RENDER_PG_ENABLE |
+		GEN9_MEDIA_PG_ENABLE |
+		GEN11_MEDIA_SAMPLER_PG_ENABLE;
 
 	if (GRAPHICS_VER(gt->i915) >= 12 && !IS_DG1(gt->i915)) {
 		for (i = 0; i < I915_MAX_VCS; i++)
diff --git a/drivers/gpu/drm/i915/gt/intel_ring_submission.c b/drivers/gpu/drm/i915/gt/intel_ring_submission.c
index 72277bc8322e..f84fa09cdb33 100644
--- a/drivers/gpu/drm/i915/gt/intel_ring_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_ring_submission.c
@@ -575,7 +575,6 @@ static int ring_context_alloc(struct intel_context *ce)
 	/* One ringbuffer to rule them all */
 	GEM_BUG_ON(!engine->legacy.ring);
 	ce->ring = engine->legacy.ring;
-	ce->timeline = intel_timeline_get(engine->legacy.timeline);
 
 	GEM_BUG_ON(ce->state);
 	if (engine->context_size) {
@@ -588,6 +587,8 @@ static int ring_context_alloc(struct intel_context *ce)
 		ce->state = vma;
 	}
 
+	ce->timeline = intel_timeline_get(engine->legacy.timeline);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
index ee12ee0ed418..b48373b16677 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -633,7 +633,7 @@ static int guc_submission_send_busy_loop(struct intel_guc *guc,
 		atomic_inc(&guc->outstanding_submission_g2h);
 
 	ret = intel_guc_send_busy_loop(guc, action, len, g2h_len_dw, loop);
-	if (ret)
+	if (ret && g2h_len_dw)
 		atomic_dec(&guc->outstanding_submission_g2h);
 
 	return ret;
@@ -3422,18 +3422,29 @@ static inline int guc_lrc_desc_unpin(struct intel_context *ce)
 	 * GuC is active, lets destroy this context, but at this point we can still be racing
 	 * with suspend, so we undo everything if the H2G fails in deregister_context so
 	 * that GuC reset will find this context during clean up.
+	 *
+	 * There is a race condition where the reset code could have altered
+	 * this context's state and done a wakeref put before we try to
+	 * deregister it here. So check if the context is still set to be
+	 * destroyed before undoing earlier changes, to avoid two wakeref puts
+	 * on the same context.
 	 */
 	ret = deregister_context(ce, ce->guc_id.id);
 	if (ret) {
-		spin_lock(&ce->guc_state.lock);
-		set_context_registered(ce);
-		clr_context_destroyed(ce);
-		spin_unlock(&ce->guc_state.lock);
+		bool pending_destroyed;
+		spin_lock_irqsave(&ce->guc_state.lock, flags);
+		pending_destroyed = context_destroyed(ce);
+		if (pending_destroyed) {
+			set_context_registered(ce);
+			clr_context_destroyed(ce);
+		}
+		spin_unlock_irqrestore(&ce->guc_state.lock, flags);
 		/*
 		 * As gt-pm is awake at function entry, intel_wakeref_put_async merely decrements
 		 * the wakeref immediately but per function spec usage call this after unlock.
 		 */
-		intel_wakeref_put_async(&gt->wakeref);
+		if (pending_destroyed)
+			intel_wakeref_put_async(&gt->wakeref);
 	}
 
 	return ret;
@@ -5511,12 +5522,20 @@ static inline void guc_log_context(struct drm_printer *p,
 {
 	drm_printf(p, "GuC lrc descriptor %u:\n", ce->guc_id.id);
 	drm_printf(p, "\tHW Context Desc: 0x%08x\n", ce->lrc.lrca);
-	drm_printf(p, "\t\tLRC Head: Internal %u, Memory %u\n",
-		   ce->ring->head,
-		   ce->lrc_reg_state[CTX_RING_HEAD]);
-	drm_printf(p, "\t\tLRC Tail: Internal %u, Memory %u\n",
-		   ce->ring->tail,
-		   ce->lrc_reg_state[CTX_RING_TAIL]);
+	if (intel_context_pin_if_active(ce)) {
+		drm_printf(p, "\t\tLRC Head: Internal %u, Memory %u\n",
+			   ce->ring->head,
+			   ce->lrc_reg_state[CTX_RING_HEAD]);
+		drm_printf(p, "\t\tLRC Tail: Internal %u, Memory %u\n",
+			   ce->ring->tail,
+			   ce->lrc_reg_state[CTX_RING_TAIL]);
+		intel_context_unpin(ce);
+	} else {
+		drm_printf(p, "\t\tLRC Head: Internal %u, Memory not pinned\n",
+			   ce->ring->head);
+		drm_printf(p, "\t\tLRC Tail: Internal %u, Memory not pinned\n",
+			   ce->ring->tail);
+	}
 	drm_printf(p, "\t\tContext Pin Count: %u\n",
 		   atomic_read(&ce->pin_count));
 	drm_printf(p, "\t\tGuC ID Ref Count: %u\n",
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc.c b/drivers/gpu/drm/i915/gt/uc/intel_huc.c
index 2d9152eb7282..24fdce844d9e 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_huc.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_huc.c
@@ -317,6 +317,11 @@ void intel_huc_init_early(struct intel_huc *huc)
 	}
 }
 
+void intel_huc_fini_late(struct intel_huc *huc)
+{
+	delayed_huc_load_fini(huc);
+}
+
 #define HUC_LOAD_MODE_STRING(x) (x ? "GSC" : "legacy")
 static int check_huc_loading_mode(struct intel_huc *huc)
 {
@@ -414,12 +419,6 @@ out:
 
 void intel_huc_fini(struct intel_huc *huc)
 {
-	/*
-	 * the fence is initialized in init_early, so we need to clean it up
-	 * even if HuC loading is off.
-	 */
-	delayed_huc_load_fini(huc);
-
 	if (huc->heci_pkt)
 		i915_vma_unpin_and_release(&huc->heci_pkt, 0);
 
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc.h b/drivers/gpu/drm/i915/gt/uc/intel_huc.h
index ba5cb08e9e7b..09aff3148f7d 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_huc.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_huc.h
@@ -55,6 +55,7 @@ struct intel_huc {
 
 int intel_huc_sanitize(struct intel_huc *huc);
 void intel_huc_init_early(struct intel_huc *huc);
+void intel_huc_fini_late(struct intel_huc *huc);
 int intel_huc_init(struct intel_huc *huc);
 void intel_huc_fini(struct intel_huc *huc);
 void intel_huc_suspend(struct intel_huc *huc);
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc.c b/drivers/gpu/drm/i915/gt/uc/intel_uc.c
index 5b8080ec5315..4f751ce74214 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_uc.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_uc.c
@@ -136,6 +136,7 @@ void intel_uc_init_late(struct intel_uc *uc)
 
 void intel_uc_driver_late_release(struct intel_uc *uc)
 {
+	intel_huc_fini_late(&uc->huc);
 }
 
 /**
diff --git a/drivers/gpu/drm/i915/gvt/opregion.c b/drivers/gpu/drm/i915/gvt/opregion.c
index 908f910420c2..4ef45520e199 100644
--- a/drivers/gpu/drm/i915/gvt/opregion.c
+++ b/drivers/gpu/drm/i915/gvt/opregion.c
@@ -222,7 +222,6 @@ int intel_vgpu_init_opregion(struct intel_vgpu *vgpu)
 	u8 *buf;
 	struct opregion_header *header;
 	struct vbt v;
-	const char opregion_signature[16] = OPREGION_SIGNATURE;
 
 	gvt_dbg_core("init vgpu%d opregion\n", vgpu->id);
 	vgpu_opregion(vgpu)->va = (void *)__get_free_pages(GFP_KERNEL |
@@ -236,8 +235,10 @@ int intel_vgpu_init_opregion(struct intel_vgpu *vgpu)
 	/* emulated opregion with VBT mailbox only */
 	buf = (u8 *)vgpu_opregion(vgpu)->va;
 	header = (struct opregion_header *)buf;
-	memcpy(header->signature, opregion_signature,
-	       sizeof(opregion_signature));
+
+	static_assert(sizeof(header->signature) == sizeof(OPREGION_SIGNATURE) - 1);
+	memcpy(header->signature, OPREGION_SIGNATURE, sizeof(header->signature));
+
 	header->size = 0x8;
 	header->opregion_ver = 0x02000000;
 	header->mboxes = MBOX_VBT;
diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c
index 21eb0c5b320d..5cc302ad13e1 100644
--- a/drivers/gpu/drm/i915/i915_pmu.c
+++ b/drivers/gpu/drm/i915/i915_pmu.c
@@ -111,11 +111,11 @@ static unsigned int config_bit(const u64 config)
 		return other_bit(config);
 }
 
-static u32 config_mask(const u64 config)
+static __always_inline u32 config_mask(const u64 config)
 {
 	unsigned int bit = config_bit(config);
 
-	if (__builtin_constant_p(config))
+	if (__builtin_constant_p(bit))
 		BUILD_BUG_ON(bit >
 			     BITS_PER_TYPE(typeof_member(struct i915_pmu,
 							 enable)) - 1);
@@ -124,7 +124,7 @@ static u32 config_mask(const u64 config)
 			     BITS_PER_TYPE(typeof_member(struct i915_pmu,
 							 enable)) - 1);
 
-	return BIT(config_bit(config));
+	return BIT(bit);
 }
 
 static bool is_engine_event(struct perf_event *event)
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 41f4350a7c6c..b7f521a9b337 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -3869,7 +3869,7 @@ enum skl_power_gate {
 #define  DDI_BUF_IS_IDLE			(1 << 7)
 #define  DDI_BUF_CTL_TC_PHY_OWNERSHIP		REG_BIT(6)
 #define  DDI_A_4_LANES				(1 << 4)
-#define  DDI_PORT_WIDTH(width)			(((width) - 1) << 1)
+#define  DDI_PORT_WIDTH(width)			(((width) == 3 ? 4 : ((width) - 1)) << 1)
 #define  DDI_PORT_WIDTH_MASK			(7 << 1)
 #define  DDI_PORT_WIDTH_SHIFT			1
 #define  DDI_INIT_DISPLAY_DETECTED		(1 << 0)
diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_gsccs.h b/drivers/gpu/drm/i915/pxp/intel_pxp_gsccs.h
index 9aae779c4da3..4969d3de2bac 100644
--- a/drivers/gpu/drm/i915/pxp/intel_pxp_gsccs.h
+++ b/drivers/gpu/drm/i915/pxp/intel_pxp_gsccs.h
@@ -23,6 +23,7 @@ int intel_pxp_gsccs_init(struct intel_pxp *pxp);
 
 int intel_pxp_gsccs_create_session(struct intel_pxp *pxp, int arb_session_id);
 void intel_pxp_gsccs_end_arb_fw_session(struct intel_pxp *pxp, u32 arb_session_id);
+bool intel_pxp_gsccs_is_ready_for_sessions(struct intel_pxp *pxp);
 
 #else
 static inline void intel_pxp_gsccs_fini(struct intel_pxp *pxp)
@@ -34,8 +35,11 @@ static inline int intel_pxp_gsccs_init(struct intel_pxp *pxp)
 	return 0;
 }
 
-#endif
+static inline bool intel_pxp_gsccs_is_ready_for_sessions(struct intel_pxp *pxp)
+{
+	return false;
+}
 
-bool intel_pxp_gsccs_is_ready_for_sessions(struct intel_pxp *pxp);
+#endif
 
 #endif /*__INTEL_PXP_GSCCS_H__ */
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
index 5c397a2df70e..5d27e1c733c5 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
@@ -168,7 +168,7 @@ static int igt_ppgtt_alloc(void *arg)
 		return PTR_ERR(ppgtt);
 
 	if (!ppgtt->vm.allocate_va_range)
-		goto err_ppgtt_cleanup;
+		goto ppgtt_vm_put;
 
 	/*
 	 * While we only allocate the page tables here and so we could
@@ -236,7 +236,7 @@ err_ppgtt_cleanup:
 			goto retry;
 	}
 	i915_gem_ww_ctx_fini(&ww);
-
+ppgtt_vm_put:
 	i915_vm_put(&ppgtt->vm);
 	return err;
 }
diff --git a/drivers/gpu/drm/i915/selftests/i915_request.c b/drivers/gpu/drm/i915/selftests/i915_request.c
index acae30a04a94..0122719ee921 100644
--- a/drivers/gpu/drm/i915/selftests/i915_request.c
+++ b/drivers/gpu/drm/i915/selftests/i915_request.c
@@ -73,8 +73,8 @@ static int igt_add_request(void *arg)
 	/* Basic preliminary test to create a request and let it loose! */
 
 	request = mock_request(rcs0(i915)->kernel_context, HZ / 10);
-	if (!request)
-		return -ENOMEM;
+	if (IS_ERR(request))
+		return PTR_ERR(request);
 
 	i915_request_add(request);
 
@@ -91,8 +91,8 @@ static int igt_wait_request(void *arg)
 	/* Submit a request, then wait upon it */
 
 	request = mock_request(rcs0(i915)->kernel_context, T);
-	if (!request)
-		return -ENOMEM;
+	if (IS_ERR(request))
+		return PTR_ERR(request);
 
 	i915_request_get(request);
 
@@ -160,8 +160,8 @@ static int igt_fence_wait(void *arg)
 	/* Submit a request, treat it as a fence and wait upon it */
 
 	request = mock_request(rcs0(i915)->kernel_context, T);
-	if (!request)
-		return -ENOMEM;
+	if (IS_ERR(request))
+		return PTR_ERR(request);
 
 	if (dma_fence_wait_timeout(&request->fence, false, T) != -ETIME) {
 		pr_err("fence wait success before submit (expected timeout)!\n");
@@ -219,8 +219,8 @@ static int igt_request_rewind(void *arg)
 	GEM_BUG_ON(IS_ERR(ce));
 	request = mock_request(ce, 2 * HZ);
 	intel_context_put(ce);
-	if (!request) {
-		err = -ENOMEM;
+	if (IS_ERR(request)) {
+		err = PTR_ERR(request);
 		goto err_context_0;
 	}
 
@@ -237,8 +237,8 @@ static int igt_request_rewind(void *arg)
 	GEM_BUG_ON(IS_ERR(ce));
 	vip = mock_request(ce, 0);
 	intel_context_put(ce);
-	if (!vip) {
-		err = -ENOMEM;
+	if (IS_ERR(vip)) {
+		err = PTR_ERR(vip);
 		goto err_context_1;
 	}
 
diff --git a/drivers/gpu/drm/i915/selftests/i915_selftest.c b/drivers/gpu/drm/i915/selftests/i915_selftest.c
index fee76c1d2f45..889281819c5b 100644
--- a/drivers/gpu/drm/i915/selftests/i915_selftest.c
+++ b/drivers/gpu/drm/i915/selftests/i915_selftest.c
@@ -23,7 +23,9 @@
 
 #include <linux/random.h>
 
+#include "gt/intel_gt.h"
 #include "gt/intel_gt_pm.h"
+#include "gt/intel_gt_regs.h"
 #include "gt/uc/intel_gsc_fw.h"
 
 #include "i915_driver.h"
@@ -253,11 +255,27 @@ int i915_mock_selftests(void)
 int i915_live_selftests(struct pci_dev *pdev)
 {
 	struct drm_i915_private *i915 = pdev_to_i915(pdev);
+	struct intel_uncore *uncore = &i915->uncore;
 	int err;
+	u32 pg_enable;
+	intel_wakeref_t wakeref;
 
 	if (!i915_selftest.live)
 		return 0;
 
+	/*
+	 * FIXME Disable render powergating, this is temporary wa and should be removed
+	 * after fixing real cause of forcewake timeouts.
+	 */
+	with_intel_runtime_pm(uncore->rpm, wakeref) {
+		if (IS_GFX_GT_IP_RANGE(to_gt(i915), IP_VER(12, 00), IP_VER(12, 74))) {
+			pg_enable = intel_uncore_read(uncore, GEN9_PG_ENABLE);
+			if (pg_enable & GEN9_RENDER_PG_ENABLE)
+				intel_uncore_write_fw(uncore, GEN9_PG_ENABLE,
+						      pg_enable & ~GEN9_RENDER_PG_ENABLE);
+		}
+	}
+
 	__wait_gsc_proxy_completed(i915);
 	__wait_gsc_huc_load_completed(i915);
 
diff --git a/drivers/gpu/drm/i915/selftests/mock_request.c b/drivers/gpu/drm/i915/selftests/mock_request.c
index 09f747228dff..1b0cf073e964 100644
--- a/drivers/gpu/drm/i915/selftests/mock_request.c
+++ b/drivers/gpu/drm/i915/selftests/mock_request.c
@@ -35,7 +35,7 @@ mock_request(struct intel_context *ce, unsigned long delay)
 	/* NB the i915->requests slab cache is enlarged to fit mock_request */
 	request = intel_context_create_request(ce);
 	if (IS_ERR(request))
-		return NULL;
+		return request;
 
 	request->mock.delay = delay;
 	return request;
diff --git a/drivers/gpu/drm/imagination/pvr_fw.c b/drivers/gpu/drm/imagination/pvr_fw.c
index 3debc9870a82..d09c4c684116 100644
--- a/drivers/gpu/drm/imagination/pvr_fw.c
+++ b/drivers/gpu/drm/imagination/pvr_fw.c
@@ -732,7 +732,7 @@ pvr_fw_process(struct pvr_device *pvr_dev)
 					       fw_mem->core_data, fw_mem->core_code_alloc_size);
 
 	if (err)
-		goto err_free_fw_core_data_obj;
+		goto err_free_kdata;
 
 	memcpy(fw_code_ptr, fw_mem->code, fw_mem->code_alloc_size);
 	memcpy(fw_data_ptr, fw_mem->data, fw_mem->data_alloc_size);
@@ -742,10 +742,14 @@ pvr_fw_process(struct pvr_device *pvr_dev)
 		memcpy(fw_core_data_ptr, fw_mem->core_data, fw_mem->core_data_alloc_size);
 
 	/* We're finished with the firmware section memory on the CPU, unmap. */
-	if (fw_core_data_ptr)
+	if (fw_core_data_ptr) {
 		pvr_fw_object_vunmap(fw_mem->core_data_obj);
-	if (fw_core_code_ptr)
+		fw_core_data_ptr = NULL;
+	}
+	if (fw_core_code_ptr) {
 		pvr_fw_object_vunmap(fw_mem->core_code_obj);
+		fw_core_code_ptr = NULL;
+	}
 	pvr_fw_object_vunmap(fw_mem->data_obj);
 	fw_data_ptr = NULL;
 	pvr_fw_object_vunmap(fw_mem->code_obj);
@@ -753,7 +757,7 @@ pvr_fw_process(struct pvr_device *pvr_dev)
 
 	err = pvr_fw_create_fwif_connection_ctl(pvr_dev);
 	if (err)
-		goto err_free_fw_core_data_obj;
+		goto err_free_kdata;
 
 	return 0;
 
@@ -763,13 +767,16 @@ err_free_kdata:
 	kfree(fw_mem->data);
 	kfree(fw_mem->code);
 
-err_free_fw_core_data_obj:
 	if (fw_core_data_ptr)
-		pvr_fw_object_unmap_and_destroy(fw_mem->core_data_obj);
+		pvr_fw_object_vunmap(fw_mem->core_data_obj);
+	if (fw_mem->core_data_obj)
+		pvr_fw_object_destroy(fw_mem->core_data_obj);
 
 err_free_fw_core_code_obj:
 	if (fw_core_code_ptr)
-		pvr_fw_object_unmap_and_destroy(fw_mem->core_code_obj);
+		pvr_fw_object_vunmap(fw_mem->core_code_obj);
+	if (fw_mem->core_code_obj)
+		pvr_fw_object_destroy(fw_mem->core_code_obj);
 
 err_free_fw_data_obj:
 	if (fw_data_ptr)
@@ -836,6 +843,12 @@ pvr_fw_cleanup(struct pvr_device *pvr_dev)
 	struct pvr_fw_mem *fw_mem = &pvr_dev->fw_dev.mem;
 
 	pvr_fw_fini_fwif_connection_ctl(pvr_dev);
+
+	kfree(fw_mem->core_data);
+	kfree(fw_mem->core_code);
+	kfree(fw_mem->data);
+	kfree(fw_mem->code);
+
 	if (fw_mem->core_code_obj)
 		pvr_fw_object_destroy(fw_mem->core_code_obj);
 	if (fw_mem->core_data_obj)
diff --git a/drivers/gpu/drm/imagination/pvr_fw_meta.c b/drivers/gpu/drm/imagination/pvr_fw_meta.c
index c39beb70c317..6d13864851fc 100644
--- a/drivers/gpu/drm/imagination/pvr_fw_meta.c
+++ b/drivers/gpu/drm/imagination/pvr_fw_meta.c
@@ -527,8 +527,10 @@ pvr_meta_vm_map(struct pvr_device *pvr_dev, struct pvr_fw_object *fw_obj)
 static void
 pvr_meta_vm_unmap(struct pvr_device *pvr_dev, struct pvr_fw_object *fw_obj)
 {
-	pvr_vm_unmap(pvr_dev->kernel_vm_ctx, fw_obj->fw_mm_node.start,
-		     fw_obj->fw_mm_node.size);
+	struct pvr_gem_object *pvr_obj = fw_obj->gem;
+
+	pvr_vm_unmap_obj(pvr_dev->kernel_vm_ctx, pvr_obj,
+			 fw_obj->fw_mm_node.start, fw_obj->fw_mm_node.size);
 }
 
 static bool
diff --git a/drivers/gpu/drm/imagination/pvr_fw_trace.c b/drivers/gpu/drm/imagination/pvr_fw_trace.c
index 73707daa4e52..5dbb636d7d4f 100644
--- a/drivers/gpu/drm/imagination/pvr_fw_trace.c
+++ b/drivers/gpu/drm/imagination/pvr_fw_trace.c
@@ -333,8 +333,8 @@ static int fw_trace_seq_show(struct seq_file *s, void *v)
 	if (sf_id == ROGUE_FW_SF_LAST)
 		return -EINVAL;
 
-	timestamp = read_fw_trace(trace_seq_data, 1) |
-		((u64)read_fw_trace(trace_seq_data, 2) << 32);
+	timestamp = ((u64)read_fw_trace(trace_seq_data, 1) << 32) |
+		read_fw_trace(trace_seq_data, 2);
 	timestamp = (timestamp & ~ROGUE_FWT_TIMESTAMP_TIME_CLRMSK) >>
 		ROGUE_FWT_TIMESTAMP_TIME_SHIFT;
 
diff --git a/drivers/gpu/drm/imagination/pvr_job.c b/drivers/gpu/drm/imagination/pvr_job.c
index 78c2f3c6dce0..6a15c1d2d871 100644
--- a/drivers/gpu/drm/imagination/pvr_job.c
+++ b/drivers/gpu/drm/imagination/pvr_job.c
@@ -684,6 +684,13 @@ pvr_jobs_link_geom_frag(struct pvr_job_data *job_data, u32 *job_count)
 		geom_job->paired_job = frag_job;
 		frag_job->paired_job = geom_job;
 
+		/* The geometry job pvr_job structure is used when the fragment
+		 * job is being prepared by the GPU scheduler. Have the fragment
+		 * job hold a reference on the geometry job to prevent it being
+		 * freed until the fragment job has finished with it.
+		 */
+		pvr_job_get(geom_job);
+
 		/* Skip the fragment job we just paired to the geometry job. */
 		i++;
 	}
diff --git a/drivers/gpu/drm/imagination/pvr_power.c b/drivers/gpu/drm/imagination/pvr_power.c
index ba7816fd28ec..d97613c6a0a9 100644
--- a/drivers/gpu/drm/imagination/pvr_power.c
+++ b/drivers/gpu/drm/imagination/pvr_power.c
@@ -317,6 +317,63 @@ pvr_power_device_idle(struct device *dev)
 	return pvr_power_is_idle(pvr_dev) ? 0 : -EBUSY;
 }
 
+static int
+pvr_power_clear_error(struct pvr_device *pvr_dev)
+{
+	struct device *dev = from_pvr_device(pvr_dev)->dev;
+	int err;
+
+	/* Ensure the device state is known and nothing is happening past this point */
+	pm_runtime_disable(dev);
+
+	/* Attempt to clear the runtime PM error by setting the current state again */
+	if (pm_runtime_status_suspended(dev))
+		err = pm_runtime_set_suspended(dev);
+	else
+		err = pm_runtime_set_active(dev);
+
+	if (err) {
+		drm_err(from_pvr_device(pvr_dev),
+			"%s: Failed to clear runtime PM error (new error %d)\n",
+			__func__, err);
+	}
+
+	pm_runtime_enable(dev);
+
+	return err;
+}
+
+/**
+ * pvr_power_get_clear() - Acquire a power reference, correcting any errors
+ * @pvr_dev: Device pointer
+ *
+ * Attempt to acquire a power reference on the device. If the runtime PM
+ * is in error state, attempt to clear the error and retry.
+ *
+ * Returns:
+ *  * 0 on success, or
+ *  * Any error code returned by pvr_power_get() or the runtime PM API.
+ */
+static int
+pvr_power_get_clear(struct pvr_device *pvr_dev)
+{
+	int err;
+
+	err = pvr_power_get(pvr_dev);
+	if (err == 0)
+		return err;
+
+	drm_warn(from_pvr_device(pvr_dev),
+		 "%s: pvr_power_get returned error %d, attempting recovery\n",
+		 __func__, err);
+
+	err = pvr_power_clear_error(pvr_dev);
+	if (err)
+		return err;
+
+	return pvr_power_get(pvr_dev);
+}
+
 /**
  * pvr_power_reset() - Reset the GPU
  * @pvr_dev: Device pointer
@@ -341,7 +398,7 @@ pvr_power_reset(struct pvr_device *pvr_dev, bool hard_reset)
 	 * Take a power reference during the reset. This should prevent any interference with the
 	 * power state during reset.
 	 */
-	WARN_ON(pvr_power_get(pvr_dev));
+	WARN_ON(pvr_power_get_clear(pvr_dev));
 
 	down_write(&pvr_dev->reset_sem);
 
@@ -363,13 +420,13 @@ pvr_power_reset(struct pvr_device *pvr_dev, bool hard_reset)
 		if (!err) {
 			if (hard_reset) {
 				pvr_dev->fw_dev.booted = false;
-				WARN_ON(pm_runtime_force_suspend(from_pvr_device(pvr_dev)->dev));
+				WARN_ON(pvr_power_device_suspend(from_pvr_device(pvr_dev)->dev));
 
 				err = pvr_fw_hard_reset(pvr_dev);
 				if (err)
 					goto err_device_lost;
 
-				err = pm_runtime_force_resume(from_pvr_device(pvr_dev)->dev);
+				err = pvr_power_device_resume(from_pvr_device(pvr_dev)->dev);
 				pvr_dev->fw_dev.booted = true;
 				if (err)
 					goto err_device_lost;
diff --git a/drivers/gpu/drm/imagination/pvr_queue.c b/drivers/gpu/drm/imagination/pvr_queue.c
index 20cb46012082..130473cfdfc9 100644
--- a/drivers/gpu/drm/imagination/pvr_queue.c
+++ b/drivers/gpu/drm/imagination/pvr_queue.c
@@ -109,12 +109,20 @@ pvr_queue_fence_get_driver_name(struct dma_fence *f)
 	return PVR_DRIVER_NAME;
 }
 
+static void pvr_queue_fence_release_work(struct work_struct *w)
+{
+	struct pvr_queue_fence *fence = container_of(w, struct pvr_queue_fence, release_work);
+
+	pvr_context_put(fence->queue->ctx);
+	dma_fence_free(&fence->base);
+}
+
 static void pvr_queue_fence_release(struct dma_fence *f)
 {
 	struct pvr_queue_fence *fence = container_of(f, struct pvr_queue_fence, base);
+	struct pvr_device *pvr_dev = fence->queue->ctx->pvr_dev;
 
-	pvr_context_put(fence->queue->ctx);
-	dma_fence_free(f);
+	queue_work(pvr_dev->sched_wq, &fence->release_work);
 }
 
 static const char *
@@ -268,6 +276,7 @@ pvr_queue_fence_init(struct dma_fence *f,
 
 	pvr_context_get(queue->ctx);
 	fence->queue = queue;
+	INIT_WORK(&fence->release_work, pvr_queue_fence_release_work);
 	dma_fence_init(&fence->base, fence_ops,
 		       &fence_ctx->lock, fence_ctx->id,
 		       atomic_inc_return(&fence_ctx->seqno));
@@ -304,8 +313,9 @@ pvr_queue_cccb_fence_init(struct dma_fence *fence, struct pvr_queue *queue)
 static void
 pvr_queue_job_fence_init(struct dma_fence *fence, struct pvr_queue *queue)
 {
-	pvr_queue_fence_init(fence, queue, &pvr_queue_job_fence_ops,
-			     &queue->job_fence_ctx);
+	if (!fence->ops)
+		pvr_queue_fence_init(fence, queue, &pvr_queue_job_fence_ops,
+				     &queue->job_fence_ctx);
 }
 
 /**
@@ -856,6 +866,10 @@ static void pvr_queue_free_job(struct drm_sched_job *sched_job)
 	struct pvr_job *job = container_of(sched_job, struct pvr_job, base);
 
 	drm_sched_job_cleanup(sched_job);
+
+	if (job->type == DRM_PVR_JOB_TYPE_FRAGMENT && job->paired_job)
+		pvr_job_put(job->paired_job);
+
 	job->paired_job = NULL;
 	pvr_job_put(job);
 }
diff --git a/drivers/gpu/drm/imagination/pvr_queue.h b/drivers/gpu/drm/imagination/pvr_queue.h
index e06ced69302f..93fe9ac9f58c 100644
--- a/drivers/gpu/drm/imagination/pvr_queue.h
+++ b/drivers/gpu/drm/imagination/pvr_queue.h
@@ -5,6 +5,7 @@
 #define PVR_QUEUE_H
 
 #include <drm/gpu_scheduler.h>
+#include <linux/workqueue.h>
 
 #include "pvr_cccb.h"
 #include "pvr_device.h"
@@ -63,6 +64,9 @@ struct pvr_queue_fence {
 
 	/** @queue: Queue that created this fence. */
 	struct pvr_queue *queue;
+
+	/** @release_work: Fence release work structure. */
+	struct work_struct release_work;
 };
 
 /**
diff --git a/drivers/gpu/drm/imagination/pvr_vm.c b/drivers/gpu/drm/imagination/pvr_vm.c
index 363f885a7098..2896fa7501b1 100644
--- a/drivers/gpu/drm/imagination/pvr_vm.c
+++ b/drivers/gpu/drm/imagination/pvr_vm.c
@@ -293,8 +293,9 @@ err_bind_op_fini:
 
 static int
 pvr_vm_bind_op_unmap_init(struct pvr_vm_bind_op *bind_op,
-			  struct pvr_vm_context *vm_ctx, u64 device_addr,
-			  u64 size)
+			  struct pvr_vm_context *vm_ctx,
+			  struct pvr_gem_object *pvr_obj,
+			  u64 device_addr, u64 size)
 {
 	int err;
 
@@ -318,6 +319,7 @@ pvr_vm_bind_op_unmap_init(struct pvr_vm_bind_op *bind_op,
 		goto err_bind_op_fini;
 	}
 
+	bind_op->pvr_obj = pvr_obj;
 	bind_op->vm_ctx = vm_ctx;
 	bind_op->device_addr = device_addr;
 	bind_op->size = size;
@@ -598,20 +600,6 @@ err_free:
 }
 
 /**
- * pvr_vm_unmap_all() - Unmap all mappings associated with a VM context.
- * @vm_ctx: Target VM context.
- *
- * This function ensures that no mappings are left dangling by unmapping them
- * all in order of ascending device-virtual address.
- */
-void
-pvr_vm_unmap_all(struct pvr_vm_context *vm_ctx)
-{
-	WARN_ON(pvr_vm_unmap(vm_ctx, vm_ctx->gpuvm_mgr.mm_start,
-			     vm_ctx->gpuvm_mgr.mm_range));
-}
-
-/**
  * pvr_vm_context_release() - Teardown a VM context.
  * @ref_count: Pointer to reference counter of the VM context.
  *
@@ -703,11 +691,7 @@ pvr_vm_lock_extra(struct drm_gpuvm_exec *vm_exec)
 	struct pvr_vm_bind_op *bind_op = vm_exec->extra.priv;
 	struct pvr_gem_object *pvr_obj = bind_op->pvr_obj;
 
-	/* Unmap operations don't have an object to lock. */
-	if (!pvr_obj)
-		return 0;
-
-	/* Acquire lock on the GEM being mapped. */
+	/* Acquire lock on the GEM object being mapped/unmapped. */
 	return drm_exec_lock_obj(&vm_exec->exec, gem_from_pvr_gem(pvr_obj));
 }
 
@@ -772,8 +756,10 @@ err_cleanup:
 }
 
 /**
- * pvr_vm_unmap() - Unmap an already mapped section of device-virtual memory.
+ * pvr_vm_unmap_obj_locked() - Unmap an already mapped section of device-virtual
+ * memory.
  * @vm_ctx: Target VM context.
+ * @pvr_obj: Target PowerVR memory object.
  * @device_addr: Virtual device address at the start of the target mapping.
  * @size: Size of the target mapping.
  *
@@ -784,9 +770,13 @@ err_cleanup:
  *  * Any error encountered while performing internal operations required to
  *    destroy the mapping (returned from pvr_vm_gpuva_unmap or
  *    pvr_vm_gpuva_remap).
+ *
+ * The vm_ctx->lock must be held when calling this function.
  */
-int
-pvr_vm_unmap(struct pvr_vm_context *vm_ctx, u64 device_addr, u64 size)
+static int
+pvr_vm_unmap_obj_locked(struct pvr_vm_context *vm_ctx,
+			struct pvr_gem_object *pvr_obj,
+			u64 device_addr, u64 size)
 {
 	struct pvr_vm_bind_op bind_op = {0};
 	struct drm_gpuvm_exec vm_exec = {
@@ -799,11 +789,13 @@ pvr_vm_unmap(struct pvr_vm_context *vm_ctx, u64 device_addr, u64 size)
 		},
 	};
 
-	int err = pvr_vm_bind_op_unmap_init(&bind_op, vm_ctx, device_addr,
-					    size);
+	int err = pvr_vm_bind_op_unmap_init(&bind_op, vm_ctx, pvr_obj,
+					    device_addr, size);
 	if (err)
 		return err;
 
+	pvr_gem_object_get(pvr_obj);
+
 	err = drm_gpuvm_exec_lock(&vm_exec);
 	if (err)
 		goto err_cleanup;
@@ -818,6 +810,96 @@ err_cleanup:
 	return err;
 }
 
+/**
+ * pvr_vm_unmap_obj() - Unmap an already mapped section of device-virtual
+ * memory.
+ * @vm_ctx: Target VM context.
+ * @pvr_obj: Target PowerVR memory object.
+ * @device_addr: Virtual device address at the start of the target mapping.
+ * @size: Size of the target mapping.
+ *
+ * Return:
+ *  * 0 on success,
+ *  * Any error encountered by pvr_vm_unmap_obj_locked.
+ */
+int
+pvr_vm_unmap_obj(struct pvr_vm_context *vm_ctx, struct pvr_gem_object *pvr_obj,
+		 u64 device_addr, u64 size)
+{
+	int err;
+
+	mutex_lock(&vm_ctx->lock);
+	err = pvr_vm_unmap_obj_locked(vm_ctx, pvr_obj, device_addr, size);
+	mutex_unlock(&vm_ctx->lock);
+
+	return err;
+}
+
+/**
+ * pvr_vm_unmap() - Unmap an already mapped section of device-virtual memory.
+ * @vm_ctx: Target VM context.
+ * @device_addr: Virtual device address at the start of the target mapping.
+ * @size: Size of the target mapping.
+ *
+ * Return:
+ *  * 0 on success,
+ *  * Any error encountered by drm_gpuva_find,
+ *  * Any error encountered by pvr_vm_unmap_obj_locked.
+ */
+int
+pvr_vm_unmap(struct pvr_vm_context *vm_ctx, u64 device_addr, u64 size)
+{
+	struct pvr_gem_object *pvr_obj;
+	struct drm_gpuva *va;
+	int err;
+
+	mutex_lock(&vm_ctx->lock);
+
+	va = drm_gpuva_find(&vm_ctx->gpuvm_mgr, device_addr, size);
+	if (va) {
+		pvr_obj = gem_to_pvr_gem(va->gem.obj);
+		err = pvr_vm_unmap_obj_locked(vm_ctx, pvr_obj,
+					      va->va.addr, va->va.range);
+	} else {
+		err = -ENOENT;
+	}
+
+	mutex_unlock(&vm_ctx->lock);
+
+	return err;
+}
+
+/**
+ * pvr_vm_unmap_all() - Unmap all mappings associated with a VM context.
+ * @vm_ctx: Target VM context.
+ *
+ * This function ensures that no mappings are left dangling by unmapping them
+ * all in order of ascending device-virtual address.
+ */
+void
+pvr_vm_unmap_all(struct pvr_vm_context *vm_ctx)
+{
+	mutex_lock(&vm_ctx->lock);
+
+	for (;;) {
+		struct pvr_gem_object *pvr_obj;
+		struct drm_gpuva *va;
+
+		va = drm_gpuva_find_first(&vm_ctx->gpuvm_mgr,
+					  vm_ctx->gpuvm_mgr.mm_start,
+					  vm_ctx->gpuvm_mgr.mm_range);
+		if (!va)
+			break;
+
+		pvr_obj = gem_to_pvr_gem(va->gem.obj);
+
+		WARN_ON(pvr_vm_unmap_obj_locked(vm_ctx, pvr_obj,
+						va->va.addr, va->va.range));
+	}
+
+	mutex_unlock(&vm_ctx->lock);
+}
+
 /* Static data areas are determined by firmware. */
 static const struct drm_pvr_static_data_area static_data_areas[] = {
 	{
diff --git a/drivers/gpu/drm/imagination/pvr_vm.h b/drivers/gpu/drm/imagination/pvr_vm.h
index 79406243617c..b0528dffa7f1 100644
--- a/drivers/gpu/drm/imagination/pvr_vm.h
+++ b/drivers/gpu/drm/imagination/pvr_vm.h
@@ -38,6 +38,9 @@ struct pvr_vm_context *pvr_vm_create_context(struct pvr_device *pvr_dev,
 int pvr_vm_map(struct pvr_vm_context *vm_ctx,
 	       struct pvr_gem_object *pvr_obj, u64 pvr_obj_offset,
 	       u64 device_addr, u64 size);
+int pvr_vm_unmap_obj(struct pvr_vm_context *vm_ctx,
+		     struct pvr_gem_object *pvr_obj,
+		     u64 device_addr, u64 size);
 int pvr_vm_unmap(struct pvr_vm_context *vm_ctx, u64 device_addr, u64 size);
 void pvr_vm_unmap_all(struct pvr_vm_context *vm_ctx);
 
diff --git a/drivers/gpu/drm/mediatek/mtk_crtc.c b/drivers/gpu/drm/mediatek/mtk_crtc.c
index 5674f5707cca..bc7527542fdc 100644
--- a/drivers/gpu/drm/mediatek/mtk_crtc.c
+++ b/drivers/gpu/drm/mediatek/mtk_crtc.c
@@ -620,13 +620,16 @@ static void mtk_crtc_update_config(struct mtk_crtc *mtk_crtc, bool needs_vblank)
 
 		mbox_send_message(mtk_crtc->cmdq_client.chan, cmdq_handle);
 		mbox_client_txdone(mtk_crtc->cmdq_client.chan, 0);
+		goto update_config_out;
 	}
-#else
+#endif
 	spin_lock_irqsave(&mtk_crtc->config_lock, flags);
 	mtk_crtc->config_updating = false;
 	spin_unlock_irqrestore(&mtk_crtc->config_lock, flags);
-#endif
 
+#if IS_REACHABLE(CONFIG_MTK_CMDQ)
+update_config_out:
+#endif
 	mutex_unlock(&mtk_crtc->hw_lock);
 }
 
@@ -716,6 +719,39 @@ int mtk_crtc_plane_check(struct drm_crtc *crtc, struct drm_plane *plane,
 	return 0;
 }
 
+void mtk_crtc_plane_disable(struct drm_crtc *crtc, struct drm_plane *plane)
+{
+#if IS_REACHABLE(CONFIG_MTK_CMDQ)
+	struct mtk_crtc *mtk_crtc = to_mtk_crtc(crtc);
+	struct mtk_plane_state *plane_state = to_mtk_plane_state(plane->state);
+	int i;
+
+	/* no need to wait for disabling the plane by CPU */
+	if (!mtk_crtc->cmdq_client.chan)
+		return;
+
+	if (!mtk_crtc->enabled)
+		return;
+
+	/* set pending plane state to disabled */
+	for (i = 0; i < mtk_crtc->layer_nr; i++) {
+		struct drm_plane *mtk_plane = &mtk_crtc->planes[i];
+		struct mtk_plane_state *mtk_plane_state = to_mtk_plane_state(mtk_plane->state);
+
+		if (mtk_plane->index == plane->index) {
+			memcpy(mtk_plane_state, plane_state, sizeof(*plane_state));
+			break;
+		}
+	}
+	mtk_crtc_update_config(mtk_crtc, false);
+
+	/* wait for planes to be disabled by CMDQ */
+	wait_event_timeout(mtk_crtc->cb_blocking_queue,
+			   mtk_crtc->cmdq_vblank_cnt == 0,
+			   msecs_to_jiffies(500));
+#endif
+}
+
 void mtk_crtc_async_update(struct drm_crtc *crtc, struct drm_plane *plane,
 			   struct drm_atomic_state *state)
 {
@@ -927,7 +963,8 @@ static int mtk_crtc_init_comp_planes(struct drm_device *drm_dev,
 				mtk_ddp_comp_supported_rotations(comp),
 				mtk_ddp_comp_get_blend_modes(comp),
 				mtk_ddp_comp_get_formats(comp),
-				mtk_ddp_comp_get_num_formats(comp), i);
+				mtk_ddp_comp_get_num_formats(comp),
+				mtk_ddp_comp_is_afbc_supported(comp), i);
 		if (ret)
 			return ret;
 
diff --git a/drivers/gpu/drm/mediatek/mtk_crtc.h b/drivers/gpu/drm/mediatek/mtk_crtc.h
index 388e900b6f4d..828f109b83e7 100644
--- a/drivers/gpu/drm/mediatek/mtk_crtc.h
+++ b/drivers/gpu/drm/mediatek/mtk_crtc.h
@@ -21,6 +21,7 @@ int mtk_crtc_create(struct drm_device *drm_dev, const unsigned int *path,
 		    unsigned int num_conn_routes);
 int mtk_crtc_plane_check(struct drm_crtc *crtc, struct drm_plane *plane,
 			 struct mtk_plane_state *state);
+void mtk_crtc_plane_disable(struct drm_crtc *crtc, struct drm_plane *plane);
 void mtk_crtc_async_update(struct drm_crtc *crtc, struct drm_plane *plane,
 			   struct drm_atomic_state *plane_state);
 struct device *mtk_crtc_dma_dev_get(struct drm_crtc *crtc);
diff --git a/drivers/gpu/drm/mediatek/mtk_ddp_comp.c b/drivers/gpu/drm/mediatek/mtk_ddp_comp.c
index edc6417639e6..ac6620e10262 100644
--- a/drivers/gpu/drm/mediatek/mtk_ddp_comp.c
+++ b/drivers/gpu/drm/mediatek/mtk_ddp_comp.c
@@ -366,6 +366,7 @@ static const struct mtk_ddp_comp_funcs ddp_ovl = {
 	.get_blend_modes = mtk_ovl_get_blend_modes,
 	.get_formats = mtk_ovl_get_formats,
 	.get_num_formats = mtk_ovl_get_num_formats,
+	.is_afbc_supported = mtk_ovl_is_afbc_supported,
 };
 
 static const struct mtk_ddp_comp_funcs ddp_postmask = {
diff --git a/drivers/gpu/drm/mediatek/mtk_ddp_comp.h b/drivers/gpu/drm/mediatek/mtk_ddp_comp.h
index 39720b27f4e9..7289b3dcf22f 100644
--- a/drivers/gpu/drm/mediatek/mtk_ddp_comp.h
+++ b/drivers/gpu/drm/mediatek/mtk_ddp_comp.h
@@ -83,6 +83,7 @@ struct mtk_ddp_comp_funcs {
 	u32 (*get_blend_modes)(struct device *dev);
 	const u32 *(*get_formats)(struct device *dev);
 	size_t (*get_num_formats)(struct device *dev);
+	bool (*is_afbc_supported)(struct device *dev);
 	void (*connect)(struct device *dev, struct device *mmsys_dev, unsigned int next);
 	void (*disconnect)(struct device *dev, struct device *mmsys_dev, unsigned int next);
 	void (*add)(struct device *dev, struct mtk_mutex *mutex);
@@ -294,6 +295,14 @@ size_t mtk_ddp_comp_get_num_formats(struct mtk_ddp_comp *comp)
 	return 0;
 }
 
+static inline bool mtk_ddp_comp_is_afbc_supported(struct mtk_ddp_comp *comp)
+{
+	if (comp->funcs && comp->funcs->is_afbc_supported)
+		return comp->funcs->is_afbc_supported(comp->dev);
+
+	return false;
+}
+
 static inline bool mtk_ddp_comp_add(struct mtk_ddp_comp *comp, struct mtk_mutex *mutex)
 {
 	if (comp->funcs && comp->funcs->add) {
diff --git a/drivers/gpu/drm/mediatek/mtk_disp_drv.h b/drivers/gpu/drm/mediatek/mtk_disp_drv.h
index 04154db9085c..c0f7f77e0574 100644
--- a/drivers/gpu/drm/mediatek/mtk_disp_drv.h
+++ b/drivers/gpu/drm/mediatek/mtk_disp_drv.h
@@ -106,6 +106,7 @@ void mtk_ovl_disable_vblank(struct device *dev);
 u32 mtk_ovl_get_blend_modes(struct device *dev);
 const u32 *mtk_ovl_get_formats(struct device *dev);
 size_t mtk_ovl_get_num_formats(struct device *dev);
+bool mtk_ovl_is_afbc_supported(struct device *dev);
 
 void mtk_ovl_adaptor_add_comp(struct device *dev, struct mtk_mutex *mutex);
 void mtk_ovl_adaptor_remove_comp(struct device *dev, struct mtk_mutex *mutex);
diff --git a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
index 19b0d5083981..ca4a9a60b890 100644
--- a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
+++ b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
@@ -236,6 +236,13 @@ size_t mtk_ovl_get_num_formats(struct device *dev)
 	return ovl->data->num_formats;
 }
 
+bool mtk_ovl_is_afbc_supported(struct device *dev)
+{
+	struct mtk_disp_ovl *ovl = dev_get_drvdata(dev);
+
+	return ovl->data->supports_afbc;
+}
+
 int mtk_ovl_clk_enable(struct device *dev)
 {
 	struct mtk_disp_ovl *ovl = dev_get_drvdata(dev);
diff --git a/drivers/gpu/drm/mediatek/mtk_dp.c b/drivers/gpu/drm/mediatek/mtk_dp.c
index cad65ea851ed..4979d49ae25a 100644
--- a/drivers/gpu/drm/mediatek/mtk_dp.c
+++ b/drivers/gpu/drm/mediatek/mtk_dp.c
@@ -1746,7 +1746,7 @@ static int mtk_dp_parse_capabilities(struct mtk_dp *mtk_dp)
 
 	ret = drm_dp_dpcd_readb(&mtk_dp->aux, DP_MSTM_CAP, &val);
 	if (ret < 1) {
-		drm_err(mtk_dp->drm_dev, "Read mstm cap failed\n");
+		dev_err(mtk_dp->dev, "Read mstm cap failed: %zd\n", ret);
 		return ret == 0 ? -EIO : ret;
 	}
 
@@ -1756,7 +1756,7 @@ static int mtk_dp_parse_capabilities(struct mtk_dp *mtk_dp)
 					DP_DEVICE_SERVICE_IRQ_VECTOR_ESI0,
 					&val);
 		if (ret < 1) {
-			drm_err(mtk_dp->drm_dev, "Read irq vector failed\n");
+			dev_err(mtk_dp->dev, "Read irq vector failed: %zd\n", ret);
 			return ret == 0 ? -EIO : ret;
 		}
 
@@ -2039,7 +2039,7 @@ static int mtk_dp_wait_hpd_asserted(struct drm_dp_aux *mtk_aux, unsigned long wa
 
 	ret = mtk_dp_parse_capabilities(mtk_dp);
 	if (ret) {
-		drm_err(mtk_dp->drm_dev, "Can't parse capabilities\n");
+		dev_err(mtk_dp->dev, "Can't parse capabilities: %d\n", ret);
 		return ret;
 	}
 
diff --git a/drivers/gpu/drm/mediatek/mtk_dpi.c b/drivers/gpu/drm/mediatek/mtk_dpi.c
index a08d20654954..20a50180d4d4 100644
--- a/drivers/gpu/drm/mediatek/mtk_dpi.c
+++ b/drivers/gpu/drm/mediatek/mtk_dpi.c
@@ -127,14 +127,14 @@ struct mtk_dpi_yc_limit {
  * @is_ck_de_pol: Support CK/DE polarity.
  * @swap_input_support: Support input swap function.
  * @support_direct_pin: IP supports direct connection to dpi panels.
- * @input_2pixel: Input pixel of dp_intf is 2 pixel per round, so enable this
- *		  config to enable this feature.
  * @dimension_mask: Mask used for HWIDTH, HPORCH, VSYNC_WIDTH and VSYNC_PORCH
  *		    (no shift).
  * @hvsize_mask: Mask of HSIZE and VSIZE mask (no shift).
  * @channel_swap_shift: Shift value of channel swap.
  * @yuv422_en_bit: Enable bit of yuv422.
  * @csc_enable_bit: Enable bit of CSC.
+ * @input_2p_en_bit: Enable bit for input two pixel per round feature.
+ *		     If present, implies that the feature must be enabled.
  * @pixels_per_iter: Quantity of transferred pixels per iteration.
  * @edge_cfg_in_mmsys: If the edge configuration for DPI's output needs to be set in MMSYS.
  */
@@ -148,12 +148,12 @@ struct mtk_dpi_conf {
 	bool is_ck_de_pol;
 	bool swap_input_support;
 	bool support_direct_pin;
-	bool input_2pixel;
 	u32 dimension_mask;
 	u32 hvsize_mask;
 	u32 channel_swap_shift;
 	u32 yuv422_en_bit;
 	u32 csc_enable_bit;
+	u32 input_2p_en_bit;
 	u32 pixels_per_iter;
 	bool edge_cfg_in_mmsys;
 };
@@ -410,12 +410,13 @@ static void mtk_dpi_config_swap_input(struct mtk_dpi *dpi, bool enable)
 
 static void mtk_dpi_config_2n_h_fre(struct mtk_dpi *dpi)
 {
-	mtk_dpi_mask(dpi, dpi->conf->reg_h_fre_con, H_FRE_2N, H_FRE_2N);
+	if (dpi->conf->reg_h_fre_con)
+		mtk_dpi_mask(dpi, dpi->conf->reg_h_fre_con, H_FRE_2N, H_FRE_2N);
 }
 
 static void mtk_dpi_config_disable_edge(struct mtk_dpi *dpi)
 {
-	if (dpi->conf->edge_sel_en)
+	if (dpi->conf->edge_sel_en && dpi->conf->reg_h_fre_con)
 		mtk_dpi_mask(dpi, dpi->conf->reg_h_fre_con, 0, EDGE_SEL_EN);
 }
 
@@ -471,6 +472,7 @@ static void mtk_dpi_power_off(struct mtk_dpi *dpi)
 
 	mtk_dpi_disable(dpi);
 	clk_disable_unprepare(dpi->pixel_clk);
+	clk_disable_unprepare(dpi->tvd_clk);
 	clk_disable_unprepare(dpi->engine_clk);
 }
 
@@ -487,6 +489,12 @@ static int mtk_dpi_power_on(struct mtk_dpi *dpi)
 		goto err_refcount;
 	}
 
+	ret = clk_prepare_enable(dpi->tvd_clk);
+	if (ret) {
+		dev_err(dpi->dev, "Failed to enable tvd pll: %d\n", ret);
+		goto err_engine;
+	}
+
 	ret = clk_prepare_enable(dpi->pixel_clk);
 	if (ret) {
 		dev_err(dpi->dev, "Failed to enable pixel clock: %d\n", ret);
@@ -496,6 +504,8 @@ static int mtk_dpi_power_on(struct mtk_dpi *dpi)
 	return 0;
 
 err_pixel:
+	clk_disable_unprepare(dpi->tvd_clk);
+err_engine:
 	clk_disable_unprepare(dpi->engine_clk);
 err_refcount:
 	dpi->refcount--;
@@ -610,9 +620,9 @@ static int mtk_dpi_set_display_mode(struct mtk_dpi *dpi,
 		mtk_dpi_dual_edge(dpi);
 		mtk_dpi_config_disable_edge(dpi);
 	}
-	if (dpi->conf->input_2pixel) {
-		mtk_dpi_mask(dpi, DPI_CON, DPINTF_INPUT_2P_EN,
-			     DPINTF_INPUT_2P_EN);
+	if (dpi->conf->input_2p_en_bit) {
+		mtk_dpi_mask(dpi, DPI_CON, dpi->conf->input_2p_en_bit,
+			     dpi->conf->input_2p_en_bit);
 	}
 	mtk_dpi_sw_reset(dpi, false);
 
@@ -992,12 +1002,12 @@ static const struct mtk_dpi_conf mt8195_dpintf_conf = {
 	.output_fmts = mt8195_output_fmts,
 	.num_output_fmts = ARRAY_SIZE(mt8195_output_fmts),
 	.pixels_per_iter = 4,
-	.input_2pixel = true,
 	.dimension_mask = DPINTF_HPW_MASK,
 	.hvsize_mask = DPINTF_HSIZE_MASK,
 	.channel_swap_shift = DPINTF_CH_SWAP,
 	.yuv422_en_bit = DPINTF_YUV422_EN,
 	.csc_enable_bit = DPINTF_CSC_ENABLE,
+	.input_2p_en_bit = DPINTF_INPUT_2P_EN,
 };
 
 static int mtk_dpi_probe(struct platform_device *pdev)
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
index 4e93fd075e03..42e62b040961 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
@@ -463,7 +463,7 @@ static int mtk_drm_kms_init(struct drm_device *drm)
 
 	ret = drmm_mode_config_init(drm);
 	if (ret)
-		goto put_mutex_dev;
+		return ret;
 
 	drm->mode_config.min_width = 64;
 	drm->mode_config.min_height = 64;
@@ -481,8 +481,11 @@ static int mtk_drm_kms_init(struct drm_device *drm)
 	for (i = 0; i < private->data->mmsys_dev_num; i++) {
 		drm->dev_private = private->all_drm_private[i];
 		ret = component_bind_all(private->all_drm_private[i]->dev, drm);
-		if (ret)
-			goto put_mutex_dev;
+		if (ret) {
+			while (--i >= 0)
+				component_unbind_all(private->all_drm_private[i]->dev, drm);
+			return ret;
+		}
 	}
 
 	/*
@@ -575,9 +578,6 @@ static int mtk_drm_kms_init(struct drm_device *drm)
 err_component_unbind:
 	for (i = 0; i < private->data->mmsys_dev_num; i++)
 		component_unbind_all(private->all_drm_private[i]->dev, drm);
-put_mutex_dev:
-	for (i = 0; i < private->data->mmsys_dev_num; i++)
-		put_device(private->all_drm_private[i]->mutex_dev);
 
 	return ret;
 }
@@ -648,8 +648,10 @@ static int mtk_drm_bind(struct device *dev)
 		return 0;
 
 	drm = drm_dev_alloc(&mtk_drm_driver, dev);
-	if (IS_ERR(drm))
-		return PTR_ERR(drm);
+	if (IS_ERR(drm)) {
+		ret = PTR_ERR(drm);
+		goto err_put_dev;
+	}
 
 	private->drm_master = true;
 	drm->dev_private = private;
@@ -675,18 +677,31 @@ err_free:
 	drm_dev_put(drm);
 	for (i = 0; i < private->data->mmsys_dev_num; i++)
 		private->all_drm_private[i]->drm = NULL;
+err_put_dev:
+	for (i = 0; i < private->data->mmsys_dev_num; i++) {
+		/* For device_find_child in mtk_drm_get_all_priv() */
+		put_device(private->all_drm_private[i]->dev);
+	}
+	put_device(private->mutex_dev);
 	return ret;
 }
 
 static void mtk_drm_unbind(struct device *dev)
 {
 	struct mtk_drm_private *private = dev_get_drvdata(dev);
+	int i;
 
 	/* for multi mmsys dev, unregister drm dev in mmsys master */
 	if (private->drm_master) {
 		drm_dev_unregister(private->drm);
 		mtk_drm_kms_deinit(private->drm);
 		drm_dev_put(private->drm);
+
+		for (i = 0; i < private->data->mmsys_dev_num; i++) {
+			/* For device_find_child in mtk_drm_get_all_priv() */
+			put_device(private->all_drm_private[i]->dev);
+		}
+		put_device(private->mutex_dev);
 	}
 	private->mtk_drm_bound = false;
 	private->drm_master = false;
diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c
index b9b7fd08b7d7..88f3dfeb4731 100644
--- a/drivers/gpu/drm/mediatek/mtk_dsi.c
+++ b/drivers/gpu/drm/mediatek/mtk_dsi.c
@@ -1108,12 +1108,12 @@ static ssize_t mtk_dsi_host_transfer(struct mipi_dsi_host *host,
 				     const struct mipi_dsi_msg *msg)
 {
 	struct mtk_dsi *dsi = host_to_dsi(host);
-	u32 recv_cnt, i;
+	ssize_t recv_cnt;
 	u8 read_data[16];
 	void *src_addr;
 	u8 irq_flag = CMD_DONE_INT_FLAG;
 	u32 dsi_mode;
-	int ret;
+	int ret, i;
 
 	dsi_mode = readl(dsi->regs + DSI_MODE_CTRL);
 	if (dsi_mode & MODE) {
@@ -1162,7 +1162,7 @@ static ssize_t mtk_dsi_host_transfer(struct mipi_dsi_host *host,
 	if (recv_cnt)
 		memcpy(msg->rx_buf, src_addr, recv_cnt);
 
-	DRM_INFO("dsi get %d byte data from the panel address(0x%x)\n",
+	DRM_INFO("dsi get %zd byte data from the panel address(0x%x)\n",
 		 recv_cnt, *((u8 *)(msg->tx_buf)));
 
 restore_dsi_mode:
diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi.c b/drivers/gpu/drm/mediatek/mtk_hdmi.c
index 7687f673964e..1aad8e6cf52e 100644
--- a/drivers/gpu/drm/mediatek/mtk_hdmi.c
+++ b/drivers/gpu/drm/mediatek/mtk_hdmi.c
@@ -137,7 +137,7 @@ enum hdmi_aud_channel_swap_type {
 
 struct hdmi_audio_param {
 	enum hdmi_audio_coding_type aud_codec;
-	enum hdmi_audio_sample_size aud_sampe_size;
+	enum hdmi_audio_sample_size aud_sample_size;
 	enum hdmi_aud_input_type aud_input_type;
 	enum hdmi_aud_i2s_fmt aud_i2s_fmt;
 	enum hdmi_aud_mclk aud_mclk;
@@ -173,6 +173,7 @@ struct mtk_hdmi {
 	unsigned int sys_offset;
 	void __iomem *regs;
 	enum hdmi_colorspace csp;
+	struct platform_device *audio_pdev;
 	struct hdmi_audio_param aud_param;
 	bool audio_enable;
 	bool powered;
@@ -1074,7 +1075,7 @@ static int mtk_hdmi_output_init(struct mtk_hdmi *hdmi)
 
 	hdmi->csp = HDMI_COLORSPACE_RGB;
 	aud_param->aud_codec = HDMI_AUDIO_CODING_TYPE_PCM;
-	aud_param->aud_sampe_size = HDMI_AUDIO_SAMPLE_SIZE_16;
+	aud_param->aud_sample_size = HDMI_AUDIO_SAMPLE_SIZE_16;
 	aud_param->aud_input_type = HDMI_AUD_INPUT_I2S;
 	aud_param->aud_i2s_fmt = HDMI_I2S_MODE_I2S_24BIT;
 	aud_param->aud_mclk = HDMI_AUD_MCLK_128FS;
@@ -1572,14 +1573,14 @@ static int mtk_hdmi_audio_hw_params(struct device *dev, void *data,
 	switch (daifmt->fmt) {
 	case HDMI_I2S:
 		hdmi_params.aud_codec = HDMI_AUDIO_CODING_TYPE_PCM;
-		hdmi_params.aud_sampe_size = HDMI_AUDIO_SAMPLE_SIZE_16;
+		hdmi_params.aud_sample_size = HDMI_AUDIO_SAMPLE_SIZE_16;
 		hdmi_params.aud_input_type = HDMI_AUD_INPUT_I2S;
 		hdmi_params.aud_i2s_fmt = HDMI_I2S_MODE_I2S_24BIT;
 		hdmi_params.aud_mclk = HDMI_AUD_MCLK_128FS;
 		break;
 	case HDMI_SPDIF:
 		hdmi_params.aud_codec = HDMI_AUDIO_CODING_TYPE_PCM;
-		hdmi_params.aud_sampe_size = HDMI_AUDIO_SAMPLE_SIZE_16;
+		hdmi_params.aud_sample_size = HDMI_AUDIO_SAMPLE_SIZE_16;
 		hdmi_params.aud_input_type = HDMI_AUD_INPUT_SPDIF;
 		break;
 	default:
@@ -1663,6 +1664,11 @@ static const struct hdmi_codec_ops mtk_hdmi_audio_codec_ops = {
 	.no_capture_mute = 1,
 };
 
+static void mtk_hdmi_unregister_audio_driver(void *data)
+{
+	platform_device_unregister(data);
+}
+
 static int mtk_hdmi_register_audio_driver(struct device *dev)
 {
 	struct mtk_hdmi *hdmi = dev_get_drvdata(dev);
@@ -1672,13 +1678,20 @@ static int mtk_hdmi_register_audio_driver(struct device *dev)
 		.i2s = 1,
 		.data = hdmi,
 	};
-	struct platform_device *pdev;
+	int ret;
 
-	pdev = platform_device_register_data(dev, HDMI_CODEC_DRV_NAME,
-					     PLATFORM_DEVID_AUTO, &codec_data,
-					     sizeof(codec_data));
-	if (IS_ERR(pdev))
-		return PTR_ERR(pdev);
+	hdmi->audio_pdev = platform_device_register_data(dev,
+							 HDMI_CODEC_DRV_NAME,
+							 PLATFORM_DEVID_AUTO,
+							 &codec_data,
+							 sizeof(codec_data));
+	if (IS_ERR(hdmi->audio_pdev))
+		return PTR_ERR(hdmi->audio_pdev);
+
+	ret = devm_add_action_or_reset(dev, mtk_hdmi_unregister_audio_driver,
+				       hdmi->audio_pdev);
+	if (ret)
+		return ret;
 
 	DRM_INFO("%s driver bound to HDMI\n", HDMI_CODEC_DRV_NAME);
 	return 0;
diff --git a/drivers/gpu/drm/mediatek/mtk_plane.c b/drivers/gpu/drm/mediatek/mtk_plane.c
index 8a48b3b0a956..74c2704efb66 100644
--- a/drivers/gpu/drm/mediatek/mtk_plane.c
+++ b/drivers/gpu/drm/mediatek/mtk_plane.c
@@ -285,9 +285,14 @@ static void mtk_plane_atomic_disable(struct drm_plane *plane,
 	struct drm_plane_state *new_state = drm_atomic_get_new_plane_state(state,
 									   plane);
 	struct mtk_plane_state *mtk_plane_state = to_mtk_plane_state(new_state);
+	struct drm_plane_state *old_state = drm_atomic_get_old_plane_state(state,
+									   plane);
+
 	mtk_plane_state->pending.enable = false;
 	wmb(); /* Make sure the above parameter is set before update */
 	mtk_plane_state->pending.dirty = true;
+
+	mtk_crtc_plane_disable(old_state->crtc, plane);
 }
 
 static void mtk_plane_atomic_update(struct drm_plane *plane,
@@ -321,7 +326,8 @@ static const struct drm_plane_helper_funcs mtk_plane_helper_funcs = {
 int mtk_plane_init(struct drm_device *dev, struct drm_plane *plane,
 		   unsigned long possible_crtcs, enum drm_plane_type type,
 		   unsigned int supported_rotations, const u32 blend_modes,
-		   const u32 *formats, size_t num_formats, unsigned int plane_idx)
+		   const u32 *formats, size_t num_formats,
+		   bool supports_afbc, unsigned int plane_idx)
 {
 	int err;
 
@@ -332,7 +338,9 @@ int mtk_plane_init(struct drm_device *dev, struct drm_plane *plane,
 
 	err = drm_universal_plane_init(dev, plane, possible_crtcs,
 				       &mtk_plane_funcs, formats,
-				       num_formats, modifiers, type, NULL);
+				       num_formats,
+				       supports_afbc ? modifiers : NULL,
+				       type, NULL);
 	if (err) {
 		DRM_ERROR("failed to initialize plane\n");
 		return err;
diff --git a/drivers/gpu/drm/mediatek/mtk_plane.h b/drivers/gpu/drm/mediatek/mtk_plane.h
index 3b13b89989c7..95c5fa5295d8 100644
--- a/drivers/gpu/drm/mediatek/mtk_plane.h
+++ b/drivers/gpu/drm/mediatek/mtk_plane.h
@@ -49,5 +49,6 @@ to_mtk_plane_state(struct drm_plane_state *state)
 int mtk_plane_init(struct drm_device *dev, struct drm_plane *plane,
 		   unsigned long possible_crtcs, enum drm_plane_type type,
 		   unsigned int supported_rotations, const u32 blend_modes,
-		   const u32 *formats, size_t num_formats, unsigned int plane_idx);
+		   const u32 *formats, size_t num_formats,
+		   bool supports_afbc, unsigned int plane_idx);
 #endif
diff --git a/drivers/gpu/drm/meson/meson_drv.c b/drivers/gpu/drm/meson/meson_drv.c
index 4bd0baa2a4f5..f59452e8fa6f 100644
--- a/drivers/gpu/drm/meson/meson_drv.c
+++ b/drivers/gpu/drm/meson/meson_drv.c
@@ -168,7 +168,7 @@ static const struct meson_drm_soc_attr meson_drm_soc_attrs[] = {
 	/* S805X/S805Y HDMI PLL won't lock for HDMI PHY freq > 1,65GHz */
 	{
 		.limits = {
-			.max_hdmi_phy_freq = 1650000,
+			.max_hdmi_phy_freq = 1650000000,
 		},
 		.attrs = (const struct soc_device_attribute []) {
 			{ .soc_id = "GXL (S805*)", },
diff --git a/drivers/gpu/drm/meson/meson_drv.h b/drivers/gpu/drm/meson/meson_drv.h
index 3f9345c14f31..be4b0e4df6e1 100644
--- a/drivers/gpu/drm/meson/meson_drv.h
+++ b/drivers/gpu/drm/meson/meson_drv.h
@@ -37,7 +37,7 @@ struct meson_drm_match_data {
 };
 
 struct meson_drm_soc_limits {
-	unsigned int max_hdmi_phy_freq;
+	unsigned long long max_hdmi_phy_freq;
 };
 
 struct meson_drm {
diff --git a/drivers/gpu/drm/meson/meson_encoder_hdmi.c b/drivers/gpu/drm/meson/meson_encoder_hdmi.c
index 0593a1cde906..2ad8383fcaed 100644
--- a/drivers/gpu/drm/meson/meson_encoder_hdmi.c
+++ b/drivers/gpu/drm/meson/meson_encoder_hdmi.c
@@ -70,12 +70,12 @@ static void meson_encoder_hdmi_set_vclk(struct meson_encoder_hdmi *encoder_hdmi,
 {
 	struct meson_drm *priv = encoder_hdmi->priv;
 	int vic = drm_match_cea_mode(mode);
-	unsigned int phy_freq;
-	unsigned int vclk_freq;
-	unsigned int venc_freq;
-	unsigned int hdmi_freq;
+	unsigned long long phy_freq;
+	unsigned long long vclk_freq;
+	unsigned long long venc_freq;
+	unsigned long long hdmi_freq;
 
-	vclk_freq = mode->clock;
+	vclk_freq = mode->clock * 1000ULL;
 
 	/* For 420, pixel clock is half unlike venc clock */
 	if (encoder_hdmi->output_bus_fmt == MEDIA_BUS_FMT_UYYVYY8_0_5X24)
@@ -107,7 +107,8 @@ static void meson_encoder_hdmi_set_vclk(struct meson_encoder_hdmi *encoder_hdmi,
 	if (mode->flags & DRM_MODE_FLAG_DBLCLK)
 		venc_freq /= 2;
 
-	dev_dbg(priv->dev, "vclk:%d phy=%d venc=%d hdmi=%d enci=%d\n",
+	dev_dbg(priv->dev,
+		"phy:%lluHz vclk=%lluHz venc=%lluHz hdmi=%lluHz enci=%d\n",
 		phy_freq, vclk_freq, venc_freq, hdmi_freq,
 		priv->venc.hdmi_use_enci);
 
@@ -122,10 +123,11 @@ static enum drm_mode_status meson_encoder_hdmi_mode_valid(struct drm_bridge *bri
 	struct meson_encoder_hdmi *encoder_hdmi = bridge_to_meson_encoder_hdmi(bridge);
 	struct meson_drm *priv = encoder_hdmi->priv;
 	bool is_hdmi2_sink = display_info->hdmi.scdc.supported;
-	unsigned int phy_freq;
-	unsigned int vclk_freq;
-	unsigned int venc_freq;
-	unsigned int hdmi_freq;
+	unsigned long long clock = mode->clock * 1000ULL;
+	unsigned long long phy_freq;
+	unsigned long long vclk_freq;
+	unsigned long long venc_freq;
+	unsigned long long hdmi_freq;
 	int vic = drm_match_cea_mode(mode);
 	enum drm_mode_status status;
 
@@ -144,12 +146,12 @@ static enum drm_mode_status meson_encoder_hdmi_mode_valid(struct drm_bridge *bri
 		if (status != MODE_OK)
 			return status;
 
-		return meson_vclk_dmt_supported_freq(priv, mode->clock);
+		return meson_vclk_dmt_supported_freq(priv, clock);
 	/* Check against supported VIC modes */
 	} else if (!meson_venc_hdmi_supported_vic(vic))
 		return MODE_BAD;
 
-	vclk_freq = mode->clock;
+	vclk_freq = clock;
 
 	/* For 420, pixel clock is half unlike venc clock */
 	if (drm_mode_is_420_only(display_info, mode) ||
@@ -179,7 +181,8 @@ static enum drm_mode_status meson_encoder_hdmi_mode_valid(struct drm_bridge *bri
 	if (mode->flags & DRM_MODE_FLAG_DBLCLK)
 		venc_freq /= 2;
 
-	dev_dbg(priv->dev, "%s: vclk:%d phy=%d venc=%d hdmi=%d\n",
+	dev_dbg(priv->dev,
+		"%s: vclk:%lluHz phy=%lluHz venc=%lluHz hdmi=%lluHz\n",
 		__func__, phy_freq, vclk_freq, venc_freq, hdmi_freq);
 
 	return meson_vclk_vic_supported_freq(priv, phy_freq, vclk_freq);
diff --git a/drivers/gpu/drm/meson/meson_vclk.c b/drivers/gpu/drm/meson/meson_vclk.c
index 2a942dc6a6dc..dfe0c28a0f05 100644
--- a/drivers/gpu/drm/meson/meson_vclk.c
+++ b/drivers/gpu/drm/meson/meson_vclk.c
@@ -110,7 +110,7 @@
 #define HDMI_PLL_LOCK		BIT(31)
 #define HDMI_PLL_LOCK_G12A	(3 << 30)
 
-#define FREQ_1000_1001(_freq)	DIV_ROUND_CLOSEST(_freq * 1000, 1001)
+#define FREQ_1000_1001(_freq)	DIV_ROUND_CLOSEST_ULL((_freq) * 1000ULL, 1001ULL)
 
 /* VID PLL Dividers */
 enum {
@@ -360,11 +360,11 @@ enum {
 };
 
 struct meson_vclk_params {
-	unsigned int pll_freq;
-	unsigned int phy_freq;
-	unsigned int vclk_freq;
-	unsigned int venc_freq;
-	unsigned int pixel_freq;
+	unsigned long long pll_freq;
+	unsigned long long phy_freq;
+	unsigned long long vclk_freq;
+	unsigned long long venc_freq;
+	unsigned long long pixel_freq;
 	unsigned int pll_od1;
 	unsigned int pll_od2;
 	unsigned int pll_od3;
@@ -372,11 +372,11 @@ struct meson_vclk_params {
 	unsigned int vclk_div;
 } params[] = {
 	[MESON_VCLK_HDMI_ENCI_54000] = {
-		.pll_freq = 4320000,
-		.phy_freq = 270000,
-		.vclk_freq = 54000,
-		.venc_freq = 54000,
-		.pixel_freq = 54000,
+		.pll_freq = 4320000000,
+		.phy_freq = 270000000,
+		.vclk_freq = 54000000,
+		.venc_freq = 54000000,
+		.pixel_freq = 54000000,
 		.pll_od1 = 4,
 		.pll_od2 = 4,
 		.pll_od3 = 1,
@@ -384,11 +384,11 @@ struct meson_vclk_params {
 		.vclk_div = 1,
 	},
 	[MESON_VCLK_HDMI_DDR_54000] = {
-		.pll_freq = 4320000,
-		.phy_freq = 270000,
-		.vclk_freq = 54000,
-		.venc_freq = 54000,
-		.pixel_freq = 27000,
+		.pll_freq = 4320000000,
+		.phy_freq = 270000000,
+		.vclk_freq = 54000000,
+		.venc_freq = 54000000,
+		.pixel_freq = 27000000,
 		.pll_od1 = 4,
 		.pll_od2 = 4,
 		.pll_od3 = 1,
@@ -396,11 +396,11 @@ struct meson_vclk_params {
 		.vclk_div = 1,
 	},
 	[MESON_VCLK_HDMI_DDR_148500] = {
-		.pll_freq = 2970000,
-		.phy_freq = 742500,
-		.vclk_freq = 148500,
-		.venc_freq = 148500,
-		.pixel_freq = 74250,
+		.pll_freq = 2970000000,
+		.phy_freq = 742500000,
+		.vclk_freq = 148500000,
+		.venc_freq = 148500000,
+		.pixel_freq = 74250000,
 		.pll_od1 = 4,
 		.pll_od2 = 1,
 		.pll_od3 = 1,
@@ -408,11 +408,11 @@ struct meson_vclk_params {
 		.vclk_div = 1,
 	},
 	[MESON_VCLK_HDMI_74250] = {
-		.pll_freq = 2970000,
-		.phy_freq = 742500,
-		.vclk_freq = 74250,
-		.venc_freq = 74250,
-		.pixel_freq = 74250,
+		.pll_freq = 2970000000,
+		.phy_freq = 742500000,
+		.vclk_freq = 74250000,
+		.venc_freq = 74250000,
+		.pixel_freq = 74250000,
 		.pll_od1 = 2,
 		.pll_od2 = 2,
 		.pll_od3 = 2,
@@ -420,11 +420,11 @@ struct meson_vclk_params {
 		.vclk_div = 1,
 	},
 	[MESON_VCLK_HDMI_148500] = {
-		.pll_freq = 2970000,
-		.phy_freq = 1485000,
-		.vclk_freq = 148500,
-		.venc_freq = 148500,
-		.pixel_freq = 148500,
+		.pll_freq = 2970000000,
+		.phy_freq = 1485000000,
+		.vclk_freq = 148500000,
+		.venc_freq = 148500000,
+		.pixel_freq = 148500000,
 		.pll_od1 = 1,
 		.pll_od2 = 2,
 		.pll_od3 = 2,
@@ -432,11 +432,11 @@ struct meson_vclk_params {
 		.vclk_div = 1,
 	},
 	[MESON_VCLK_HDMI_297000] = {
-		.pll_freq = 5940000,
-		.phy_freq = 2970000,
-		.venc_freq = 297000,
-		.vclk_freq = 297000,
-		.pixel_freq = 297000,
+		.pll_freq = 5940000000,
+		.phy_freq = 2970000000,
+		.venc_freq = 297000000,
+		.vclk_freq = 297000000,
+		.pixel_freq = 297000000,
 		.pll_od1 = 2,
 		.pll_od2 = 1,
 		.pll_od3 = 1,
@@ -444,11 +444,11 @@ struct meson_vclk_params {
 		.vclk_div = 2,
 	},
 	[MESON_VCLK_HDMI_594000] = {
-		.pll_freq = 5940000,
-		.phy_freq = 5940000,
-		.venc_freq = 594000,
-		.vclk_freq = 594000,
-		.pixel_freq = 594000,
+		.pll_freq = 5940000000,
+		.phy_freq = 5940000000,
+		.venc_freq = 594000000,
+		.vclk_freq = 594000000,
+		.pixel_freq = 594000000,
 		.pll_od1 = 1,
 		.pll_od2 = 1,
 		.pll_od3 = 2,
@@ -456,11 +456,11 @@ struct meson_vclk_params {
 		.vclk_div = 1,
 	},
 	[MESON_VCLK_HDMI_594000_YUV420] = {
-		.pll_freq = 5940000,
-		.phy_freq = 2970000,
-		.venc_freq = 594000,
-		.vclk_freq = 594000,
-		.pixel_freq = 297000,
+		.pll_freq = 5940000000,
+		.phy_freq = 2970000000,
+		.venc_freq = 594000000,
+		.vclk_freq = 594000000,
+		.pixel_freq = 297000000,
 		.pll_od1 = 2,
 		.pll_od2 = 1,
 		.pll_od3 = 1,
@@ -617,16 +617,16 @@ static void meson_hdmi_pll_set_params(struct meson_drm *priv, unsigned int m,
 				3 << 20, pll_od_to_reg(od3) << 20);
 }
 
-#define XTAL_FREQ 24000
+#define XTAL_FREQ (24 * 1000 * 1000)
 
 static unsigned int meson_hdmi_pll_get_m(struct meson_drm *priv,
-					 unsigned int pll_freq)
+					 unsigned long long pll_freq)
 {
 	/* The GXBB PLL has a /2 pre-multiplier */
 	if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_GXBB))
-		pll_freq /= 2;
+		pll_freq = DIV_ROUND_DOWN_ULL(pll_freq, 2);
 
-	return pll_freq / XTAL_FREQ;
+	return DIV_ROUND_DOWN_ULL(pll_freq, XTAL_FREQ);
 }
 
 #define HDMI_FRAC_MAX_GXBB	4096
@@ -635,12 +635,13 @@ static unsigned int meson_hdmi_pll_get_m(struct meson_drm *priv,
 
 static unsigned int meson_hdmi_pll_get_frac(struct meson_drm *priv,
 					    unsigned int m,
-					    unsigned int pll_freq)
+					    unsigned long long pll_freq)
 {
-	unsigned int parent_freq = XTAL_FREQ;
+	unsigned long long parent_freq = XTAL_FREQ;
 	unsigned int frac_max = HDMI_FRAC_MAX_GXL;
 	unsigned int frac_m;
 	unsigned int frac;
+	u32 remainder;
 
 	/* The GXBB PLL has a /2 pre-multiplier and a larger FRAC width */
 	if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_GXBB)) {
@@ -652,11 +653,11 @@ static unsigned int meson_hdmi_pll_get_frac(struct meson_drm *priv,
 		frac_max = HDMI_FRAC_MAX_G12A;
 
 	/* We can have a perfect match !*/
-	if (pll_freq / m == parent_freq &&
-	    pll_freq % m == 0)
+	if (div_u64_rem(pll_freq, m, &remainder) == parent_freq &&
+	    remainder == 0)
 		return 0;
 
-	frac = div_u64((u64)pll_freq * (u64)frac_max, parent_freq);
+	frac = mul_u64_u64_div_u64(pll_freq, frac_max, parent_freq);
 	frac_m = m * frac_max;
 	if (frac_m > frac)
 		return frac_max;
@@ -666,7 +667,7 @@ static unsigned int meson_hdmi_pll_get_frac(struct meson_drm *priv,
 }
 
 static bool meson_hdmi_pll_validate_params(struct meson_drm *priv,
-					   unsigned int m,
+					   unsigned long long m,
 					   unsigned int frac)
 {
 	if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_GXBB)) {
@@ -694,7 +695,7 @@ static bool meson_hdmi_pll_validate_params(struct meson_drm *priv,
 }
 
 static bool meson_hdmi_pll_find_params(struct meson_drm *priv,
-				       unsigned int freq,
+				       unsigned long long freq,
 				       unsigned int *m,
 				       unsigned int *frac,
 				       unsigned int *od)
@@ -706,7 +707,7 @@ static bool meson_hdmi_pll_find_params(struct meson_drm *priv,
 			continue;
 		*frac = meson_hdmi_pll_get_frac(priv, *m, freq * *od);
 
-		DRM_DEBUG_DRIVER("PLL params for %dkHz: m=%x frac=%x od=%d\n",
+		DRM_DEBUG_DRIVER("PLL params for %lluHz: m=%x frac=%x od=%d\n",
 				 freq, *m, *frac, *od);
 
 		if (meson_hdmi_pll_validate_params(priv, *m, *frac))
@@ -718,7 +719,7 @@ static bool meson_hdmi_pll_find_params(struct meson_drm *priv,
 
 /* pll_freq is the frequency after the OD dividers */
 enum drm_mode_status
-meson_vclk_dmt_supported_freq(struct meson_drm *priv, unsigned int freq)
+meson_vclk_dmt_supported_freq(struct meson_drm *priv, unsigned long long freq)
 {
 	unsigned int od, m, frac;
 
@@ -741,7 +742,7 @@ EXPORT_SYMBOL_GPL(meson_vclk_dmt_supported_freq);
 
 /* pll_freq is the frequency after the OD dividers */
 static void meson_hdmi_pll_generic_set(struct meson_drm *priv,
-				       unsigned int pll_freq)
+				       unsigned long long pll_freq)
 {
 	unsigned int od, m, frac, od1, od2, od3;
 
@@ -756,7 +757,7 @@ static void meson_hdmi_pll_generic_set(struct meson_drm *priv,
 			od1 = od / od2;
 		}
 
-		DRM_DEBUG_DRIVER("PLL params for %dkHz: m=%x frac=%x od=%d/%d/%d\n",
+		DRM_DEBUG_DRIVER("PLL params for %lluHz: m=%x frac=%x od=%d/%d/%d\n",
 				 pll_freq, m, frac, od1, od2, od3);
 
 		meson_hdmi_pll_set_params(priv, m, frac, od1, od2, od3);
@@ -764,17 +765,48 @@ static void meson_hdmi_pll_generic_set(struct meson_drm *priv,
 		return;
 	}
 
-	DRM_ERROR("Fatal, unable to find parameters for PLL freq %d\n",
+	DRM_ERROR("Fatal, unable to find parameters for PLL freq %lluHz\n",
 		  pll_freq);
 }
 
+static bool meson_vclk_freqs_are_matching_param(unsigned int idx,
+						unsigned long long phy_freq,
+						unsigned long long vclk_freq)
+{
+	DRM_DEBUG_DRIVER("i = %d vclk_freq = %lluHz alt = %lluHz\n",
+			 idx, params[idx].vclk_freq,
+			 FREQ_1000_1001(params[idx].vclk_freq));
+	DRM_DEBUG_DRIVER("i = %d phy_freq = %lluHz alt = %lluHz\n",
+			 idx, params[idx].phy_freq,
+			 FREQ_1000_1001(params[idx].phy_freq));
+
+	/* Match strict frequency */
+	if (phy_freq == params[idx].phy_freq &&
+	    vclk_freq == params[idx].vclk_freq)
+		return true;
+
+	/* Match 1000/1001 variant: vclk deviation has to be less than 1kHz
+	 * (drm EDID is defined in 1kHz steps, so everything smaller must be
+	 * rounding error) and the PHY freq deviation has to be less than
+	 * 10kHz (as the TMDS clock is 10 times the pixel clock, so anything
+	 * smaller must be rounding error as well).
+	 */
+	if (abs(vclk_freq - FREQ_1000_1001(params[idx].vclk_freq)) < 1000 &&
+	    abs(phy_freq - FREQ_1000_1001(params[idx].phy_freq)) < 10000)
+		return true;
+
+	/* no match */
+	return false;
+}
+
 enum drm_mode_status
-meson_vclk_vic_supported_freq(struct meson_drm *priv, unsigned int phy_freq,
-			      unsigned int vclk_freq)
+meson_vclk_vic_supported_freq(struct meson_drm *priv,
+			      unsigned long long phy_freq,
+			      unsigned long long vclk_freq)
 {
 	int i;
 
-	DRM_DEBUG_DRIVER("phy_freq = %d vclk_freq = %d\n",
+	DRM_DEBUG_DRIVER("phy_freq = %lluHz vclk_freq = %lluHz\n",
 			 phy_freq, vclk_freq);
 
 	/* Check against soc revision/package limits */
@@ -785,19 +817,7 @@ meson_vclk_vic_supported_freq(struct meson_drm *priv, unsigned int phy_freq,
 	}
 
 	for (i = 0 ; params[i].pixel_freq ; ++i) {
-		DRM_DEBUG_DRIVER("i = %d pixel_freq = %d alt = %d\n",
-				 i, params[i].pixel_freq,
-				 FREQ_1000_1001(params[i].pixel_freq));
-		DRM_DEBUG_DRIVER("i = %d phy_freq = %d alt = %d\n",
-				 i, params[i].phy_freq,
-				 FREQ_1000_1001(params[i].phy_freq/1000)*1000);
-		/* Match strict frequency */
-		if (phy_freq == params[i].phy_freq &&
-		    vclk_freq == params[i].vclk_freq)
-			return MODE_OK;
-		/* Match 1000/1001 variant */
-		if (phy_freq == (FREQ_1000_1001(params[i].phy_freq/1000)*1000) &&
-		    vclk_freq == FREQ_1000_1001(params[i].vclk_freq))
+		if (meson_vclk_freqs_are_matching_param(i, phy_freq, vclk_freq))
 			return MODE_OK;
 	}
 
@@ -805,8 +825,9 @@ meson_vclk_vic_supported_freq(struct meson_drm *priv, unsigned int phy_freq,
 }
 EXPORT_SYMBOL_GPL(meson_vclk_vic_supported_freq);
 
-static void meson_vclk_set(struct meson_drm *priv, unsigned int pll_base_freq,
-			   unsigned int od1, unsigned int od2, unsigned int od3,
+static void meson_vclk_set(struct meson_drm *priv,
+			   unsigned long long pll_base_freq, unsigned int od1,
+			   unsigned int od2, unsigned int od3,
 			   unsigned int vid_pll_div, unsigned int vclk_div,
 			   unsigned int hdmi_tx_div, unsigned int venc_div,
 			   bool hdmi_use_enci, bool vic_alternate_clock)
@@ -826,15 +847,15 @@ static void meson_vclk_set(struct meson_drm *priv, unsigned int pll_base_freq,
 		meson_hdmi_pll_generic_set(priv, pll_base_freq);
 	} else if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_GXBB)) {
 		switch (pll_base_freq) {
-		case 2970000:
+		case 2970000000:
 			m = 0x3d;
 			frac = vic_alternate_clock ? 0xd02 : 0xe00;
 			break;
-		case 4320000:
+		case 4320000000:
 			m = vic_alternate_clock ? 0x59 : 0x5a;
 			frac = vic_alternate_clock ? 0xe8f : 0;
 			break;
-		case 5940000:
+		case 5940000000:
 			m = 0x7b;
 			frac = vic_alternate_clock ? 0xa05 : 0xc00;
 			break;
@@ -844,15 +865,15 @@ static void meson_vclk_set(struct meson_drm *priv, unsigned int pll_base_freq,
 	} else if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_GXM) ||
 		   meson_vpu_is_compatible(priv, VPU_COMPATIBLE_GXL)) {
 		switch (pll_base_freq) {
-		case 2970000:
+		case 2970000000:
 			m = 0x7b;
 			frac = vic_alternate_clock ? 0x281 : 0x300;
 			break;
-		case 4320000:
+		case 4320000000:
 			m = vic_alternate_clock ? 0xb3 : 0xb4;
 			frac = vic_alternate_clock ? 0x347 : 0;
 			break;
-		case 5940000:
+		case 5940000000:
 			m = 0xf7;
 			frac = vic_alternate_clock ? 0x102 : 0x200;
 			break;
@@ -861,15 +882,15 @@ static void meson_vclk_set(struct meson_drm *priv, unsigned int pll_base_freq,
 		meson_hdmi_pll_set_params(priv, m, frac, od1, od2, od3);
 	} else if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_G12A)) {
 		switch (pll_base_freq) {
-		case 2970000:
+		case 2970000000:
 			m = 0x7b;
 			frac = vic_alternate_clock ? 0x140b4 : 0x18000;
 			break;
-		case 4320000:
+		case 4320000000:
 			m = vic_alternate_clock ? 0xb3 : 0xb4;
 			frac = vic_alternate_clock ? 0x1a3ee : 0;
 			break;
-		case 5940000:
+		case 5940000000:
 			m = 0xf7;
 			frac = vic_alternate_clock ? 0x8148 : 0x10000;
 			break;
@@ -1025,14 +1046,14 @@ static void meson_vclk_set(struct meson_drm *priv, unsigned int pll_base_freq,
 }
 
 void meson_vclk_setup(struct meson_drm *priv, unsigned int target,
-		      unsigned int phy_freq, unsigned int vclk_freq,
-		      unsigned int venc_freq, unsigned int dac_freq,
+		      unsigned long long phy_freq, unsigned long long vclk_freq,
+		      unsigned long long venc_freq, unsigned long long dac_freq,
 		      bool hdmi_use_enci)
 {
 	bool vic_alternate_clock = false;
-	unsigned int freq;
-	unsigned int hdmi_tx_div;
-	unsigned int venc_div;
+	unsigned long long freq;
+	unsigned long long hdmi_tx_div;
+	unsigned long long venc_div;
 
 	if (target == MESON_VCLK_TARGET_CVBS) {
 		meson_venci_cvbs_clock_config(priv);
@@ -1052,27 +1073,25 @@ void meson_vclk_setup(struct meson_drm *priv, unsigned int target,
 		return;
 	}
 
-	hdmi_tx_div = vclk_freq / dac_freq;
+	hdmi_tx_div = DIV_ROUND_DOWN_ULL(vclk_freq, dac_freq);
 
 	if (hdmi_tx_div == 0) {
-		pr_err("Fatal Error, invalid HDMI-TX freq %d\n",
+		pr_err("Fatal Error, invalid HDMI-TX freq %lluHz\n",
 		       dac_freq);
 		return;
 	}
 
-	venc_div = vclk_freq / venc_freq;
+	venc_div = DIV_ROUND_DOWN_ULL(vclk_freq, venc_freq);
 
 	if (venc_div == 0) {
-		pr_err("Fatal Error, invalid HDMI venc freq %d\n",
+		pr_err("Fatal Error, invalid HDMI venc freq %lluHz\n",
 		       venc_freq);
 		return;
 	}
 
 	for (freq = 0 ; params[freq].pixel_freq ; ++freq) {
-		if ((phy_freq == params[freq].phy_freq ||
-		     phy_freq == FREQ_1000_1001(params[freq].phy_freq/1000)*1000) &&
-		    (vclk_freq == params[freq].vclk_freq ||
-		     vclk_freq == FREQ_1000_1001(params[freq].vclk_freq))) {
+		if (meson_vclk_freqs_are_matching_param(freq, phy_freq,
+							vclk_freq)) {
 			if (vclk_freq != params[freq].vclk_freq)
 				vic_alternate_clock = true;
 			else
@@ -1098,7 +1117,8 @@ void meson_vclk_setup(struct meson_drm *priv, unsigned int target,
 	}
 
 	if (!params[freq].pixel_freq) {
-		pr_err("Fatal Error, invalid HDMI vclk freq %d\n", vclk_freq);
+		pr_err("Fatal Error, invalid HDMI vclk freq %lluHz\n",
+		       vclk_freq);
 		return;
 	}
 
diff --git a/drivers/gpu/drm/meson/meson_vclk.h b/drivers/gpu/drm/meson/meson_vclk.h
index 60617aaf18dd..7ac55744e574 100644
--- a/drivers/gpu/drm/meson/meson_vclk.h
+++ b/drivers/gpu/drm/meson/meson_vclk.h
@@ -20,17 +20,18 @@ enum {
 };
 
 /* 27MHz is the CVBS Pixel Clock */
-#define MESON_VCLK_CVBS			27000
+#define MESON_VCLK_CVBS			(27 * 1000 * 1000)
 
 enum drm_mode_status
-meson_vclk_dmt_supported_freq(struct meson_drm *priv, unsigned int freq);
+meson_vclk_dmt_supported_freq(struct meson_drm *priv, unsigned long long freq);
 enum drm_mode_status
-meson_vclk_vic_supported_freq(struct meson_drm *priv, unsigned int phy_freq,
-			      unsigned int vclk_freq);
+meson_vclk_vic_supported_freq(struct meson_drm *priv,
+			      unsigned long long phy_freq,
+			      unsigned long long vclk_freq);
 
 void meson_vclk_setup(struct meson_drm *priv, unsigned int target,
-		      unsigned int phy_freq, unsigned int vclk_freq,
-		      unsigned int venc_freq, unsigned int dac_freq,
+		      unsigned long long phy_freq, unsigned long long vclk_freq,
+		      unsigned long long venc_freq, unsigned long long dac_freq,
 		      bool hdmi_use_enci);
 
 #endif /* __MESON_VCLK_H */
diff --git a/drivers/gpu/drm/mgag200/mgag200_mode.c b/drivers/gpu/drm/mgag200/mgag200_mode.c
index fb71658c3117..6067d08aeee3 100644
--- a/drivers/gpu/drm/mgag200/mgag200_mode.c
+++ b/drivers/gpu/drm/mgag200/mgag200_mode.c
@@ -223,7 +223,7 @@ void mgag200_set_mode_regs(struct mga_device *mdev, const struct drm_display_mod
 	vsyncstr = mode->crtc_vsync_start - 1;
 	vsyncend = mode->crtc_vsync_end - 1;
 	vtotal = mode->crtc_vtotal - 2;
-	vblkstr = mode->crtc_vblank_start;
+	vblkstr = mode->crtc_vblank_start - 1;
 	vblkend = vtotal + 1;
 
 	linecomp = vdispend;
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
index 14db7376c712..67fa528f546d 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
@@ -1126,49 +1126,50 @@ static void a6xx_gmu_shutdown(struct a6xx_gmu *gmu)
 	struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu);
 	struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
 	u32 val;
+	int ret;
 
 	/*
-	 * The GMU may still be in slumber unless the GPU started so check and
-	 * skip putting it back into slumber if so
+	 * GMU firmware's internal power state gets messed up if we send "prepare_slumber" hfi when
+	 * oob_gpu handshake wasn't done after the last wake up. So do a dummy handshake here when
+	 * required
 	 */
-	val = gmu_read(gmu, REG_A6XX_GPU_GMU_CX_GMU_RPMH_POWER_STATE);
+	if (adreno_gpu->base.needs_hw_init) {
+		if (a6xx_gmu_set_oob(&a6xx_gpu->gmu, GMU_OOB_GPU_SET))
+			goto force_off;
 
-	if (val != 0xf) {
-		int ret = a6xx_gmu_wait_for_idle(gmu);
+		a6xx_gmu_clear_oob(&a6xx_gpu->gmu, GMU_OOB_GPU_SET);
+	}
 
-		/* If the GMU isn't responding assume it is hung */
-		if (ret) {
-			a6xx_gmu_force_off(gmu);
-			return;
-		}
+	ret = a6xx_gmu_wait_for_idle(gmu);
 
-		a6xx_bus_clear_pending_transactions(adreno_gpu, a6xx_gpu->hung);
+	/* If the GMU isn't responding assume it is hung */
+	if (ret)
+		goto force_off;
 
-		/* tell the GMU we want to slumber */
-		ret = a6xx_gmu_notify_slumber(gmu);
-		if (ret) {
-			a6xx_gmu_force_off(gmu);
-			return;
-		}
+	a6xx_bus_clear_pending_transactions(adreno_gpu, a6xx_gpu->hung);
 
-		ret = gmu_poll_timeout(gmu,
-			REG_A6XX_GPU_GMU_AO_GPU_CX_BUSY_STATUS, val,
-			!(val & A6XX_GPU_GMU_AO_GPU_CX_BUSY_STATUS_GPUBUSYIGNAHB),
-			100, 10000);
+	/* tell the GMU we want to slumber */
+	ret = a6xx_gmu_notify_slumber(gmu);
+	if (ret)
+		goto force_off;
 
-		/*
-		 * Let the user know we failed to slumber but don't worry too
-		 * much because we are powering down anyway
-		 */
+	ret = gmu_poll_timeout(gmu,
+		REG_A6XX_GPU_GMU_AO_GPU_CX_BUSY_STATUS, val,
+		!(val & A6XX_GPU_GMU_AO_GPU_CX_BUSY_STATUS_GPUBUSYIGNAHB),
+		100, 10000);
 
-		if (ret)
-			DRM_DEV_ERROR(gmu->dev,
-				"Unable to slumber GMU: status = 0%x/0%x\n",
-				gmu_read(gmu,
-					REG_A6XX_GPU_GMU_AO_GPU_CX_BUSY_STATUS),
-				gmu_read(gmu,
-					REG_A6XX_GPU_GMU_AO_GPU_CX_BUSY_STATUS2));
-	}
+	/*
+	 * Let the user know we failed to slumber but don't worry too
+	 * much because we are powering down anyway
+	 */
+
+	if (ret)
+		DRM_DEV_ERROR(gmu->dev,
+			"Unable to slumber GMU: status = 0%x/0%x\n",
+			gmu_read(gmu,
+				REG_A6XX_GPU_GMU_AO_GPU_CX_BUSY_STATUS),
+			gmu_read(gmu,
+				REG_A6XX_GPU_GMU_AO_GPU_CX_BUSY_STATUS2));
 
 	/* Turn off HFI */
 	a6xx_hfi_stop(gmu);
@@ -1178,6 +1179,11 @@ static void a6xx_gmu_shutdown(struct a6xx_gmu *gmu)
 
 	/* Tell RPMh to power off the GPU */
 	a6xx_rpmh_stop(gmu);
+
+	return;
+
+force_off:
+	a6xx_gmu_force_off(gmu);
 }
 
 
@@ -1603,7 +1609,9 @@ int a6xx_gmu_wrapper_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node)
 
 	gmu->dev = &pdev->dev;
 
-	of_dma_configure(gmu->dev, node, true);
+	ret = of_dma_configure(gmu->dev, node, true);
+	if (ret)
+		return ret;
 
 	pm_runtime_enable(gmu->dev);
 
@@ -1668,7 +1676,9 @@ int a6xx_gmu_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node)
 
 	gmu->dev = &pdev->dev;
 
-	of_dma_configure(gmu->dev, node, true);
+	ret = of_dma_configure(gmu->dev, node, true);
+	if (ret)
+		return ret;
 
 	/* Fow now, don't do anything fancy until we get our feet under us */
 	gmu->idle_level = GMU_IDLE_STATE_ACTIVE;
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index 702b8d4b3497..80c78aff9643 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -123,6 +123,20 @@ static void a6xx_set_pagetable(struct a6xx_gpu *a6xx_gpu,
 		OUT_RING(ring, lower_32_bits(rbmemptr(ring, fence)));
 		OUT_RING(ring, upper_32_bits(rbmemptr(ring, fence)));
 		OUT_RING(ring, submit->seqno - 1);
+
+		OUT_PKT7(ring, CP_THREAD_CONTROL, 1);
+		OUT_RING(ring, CP_SET_THREAD_BOTH);
+
+		/* Reset state used to synchronize BR and BV */
+		OUT_PKT7(ring, CP_RESET_CONTEXT_STATE, 1);
+		OUT_RING(ring,
+			 CP_RESET_CONTEXT_STATE_0_CLEAR_ON_CHIP_TS |
+			 CP_RESET_CONTEXT_STATE_0_CLEAR_RESOURCE_TABLE |
+			 CP_RESET_CONTEXT_STATE_0_CLEAR_BV_BR_COUNTER |
+			 CP_RESET_CONTEXT_STATE_0_RESET_GLOBAL_LOCAL_TS);
+
+		OUT_PKT7(ring, CP_THREAD_CONTROL, 1);
+		OUT_RING(ring, CP_SET_THREAD_BR);
 	}
 
 	if (!sysprof) {
@@ -233,10 +247,10 @@ static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
 				break;
 			fallthrough;
 		case MSM_SUBMIT_CMD_BUF:
-			OUT_PKT7(ring, CP_INDIRECT_BUFFER_PFE, 3);
+			OUT_PKT7(ring, CP_INDIRECT_BUFFER, 3);
 			OUT_RING(ring, lower_32_bits(submit->cmd[i].iova));
 			OUT_RING(ring, upper_32_bits(submit->cmd[i].iova));
-			OUT_RING(ring, submit->cmd[i].size);
+			OUT_RING(ring, A5XX_CP_INDIRECT_BUFFER_2_IB_SIZE(submit->cmd[i].size));
 			ibs++;
 			break;
 		}
@@ -319,10 +333,10 @@ static void a7xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
 				break;
 			fallthrough;
 		case MSM_SUBMIT_CMD_BUF:
-			OUT_PKT7(ring, CP_INDIRECT_BUFFER_PFE, 3);
+			OUT_PKT7(ring, CP_INDIRECT_BUFFER, 3);
 			OUT_RING(ring, lower_32_bits(submit->cmd[i].iova));
 			OUT_RING(ring, upper_32_bits(submit->cmd[i].iova));
-			OUT_RING(ring, submit->cmd[i].size);
+			OUT_RING(ring, A5XX_CP_INDIRECT_BUFFER_2_IB_SIZE(submit->cmd[i].size));
 			ibs++;
 			break;
 		}
@@ -554,7 +568,6 @@ static void a6xx_calc_ubwc_config(struct adreno_gpu *gpu)
 	if (adreno_is_7c3(gpu)) {
 		gpu->ubwc_config.highest_bank_bit = 14;
 		gpu->ubwc_config.amsbc = 1;
-		gpu->ubwc_config.rgb565_predicator = 1;
 		gpu->ubwc_config.uavflagprd_inv = 2;
 		gpu->ubwc_config.macrotile_mode = 1;
 	}
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
index 0fcae53c0b14..159665cb6b14 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
@@ -1507,6 +1507,8 @@ static void a6xx_get_indexed_registers(struct msm_gpu *gpu,
 
 	/* Restore the size in the hardware */
 	gpu_write(gpu, REG_A6XX_CP_MEM_POOL_SIZE, mempool_size);
+
+	a6xx_state->nr_indexed_regs = count;
 }
 
 static void a7xx_get_indexed_registers(struct msm_gpu *gpu,
diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_10_0_sm8650.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_10_0_sm8650.h
index eb5dfff2ec4f..e187e7b1cef1 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_10_0_sm8650.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_10_0_sm8650.h
@@ -160,6 +160,7 @@ static const struct dpu_lm_cfg sm8650_lm[] = {
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_3,
 		.pingpong = PINGPONG_2,
+		.dspp = DSPP_2,
 	}, {
 		.name = "lm_3", .id = LM_3,
 		.base = 0x47000, .len = 0x400,
@@ -167,6 +168,7 @@ static const struct dpu_lm_cfg sm8650_lm[] = {
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_2,
 		.pingpong = PINGPONG_3,
+		.dspp = DSPP_3,
 	}, {
 		.name = "lm_4", .id = LM_4,
 		.base = 0x48000, .len = 0x400,
diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_4_1_sdm670.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_4_1_sdm670.h
index cbbdaebe357e..daef07924886 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_4_1_sdm670.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_4_1_sdm670.h
@@ -65,6 +65,54 @@ static const struct dpu_sspp_cfg sdm670_sspp[] = {
 	},
 };
 
+static const struct dpu_lm_cfg sdm670_lm[] = {
+	{
+		.name = "lm_0", .id = LM_0,
+		.base = 0x44000, .len = 0x320,
+		.features = MIXER_SDM845_MASK,
+		.sblk = &sdm845_lm_sblk,
+		.lm_pair = LM_1,
+		.pingpong = PINGPONG_0,
+		.dspp = DSPP_0,
+	}, {
+		.name = "lm_1", .id = LM_1,
+		.base = 0x45000, .len = 0x320,
+		.features = MIXER_SDM845_MASK,
+		.sblk = &sdm845_lm_sblk,
+		.lm_pair = LM_0,
+		.pingpong = PINGPONG_1,
+		.dspp = DSPP_1,
+	}, {
+		.name = "lm_2", .id = LM_2,
+		.base = 0x46000, .len = 0x320,
+		.features = MIXER_SDM845_MASK,
+		.sblk = &sdm845_lm_sblk,
+		.lm_pair = LM_5,
+		.pingpong = PINGPONG_2,
+	}, {
+		.name = "lm_5", .id = LM_5,
+		.base = 0x49000, .len = 0x320,
+		.features = MIXER_SDM845_MASK,
+		.sblk = &sdm845_lm_sblk,
+		.lm_pair = LM_2,
+		.pingpong = PINGPONG_3,
+	},
+};
+
+static const struct dpu_dspp_cfg sdm670_dspp[] = {
+	{
+		.name = "dspp_0", .id = DSPP_0,
+		.base = 0x54000, .len = 0x1800,
+		.features = DSPP_SC7180_MASK,
+		.sblk = &sdm845_dspp_sblk,
+	}, {
+		.name = "dspp_1", .id = DSPP_1,
+		.base = 0x56000, .len = 0x1800,
+		.features = DSPP_SC7180_MASK,
+		.sblk = &sdm845_dspp_sblk,
+	},
+};
+
 static const struct dpu_dsc_cfg sdm670_dsc[] = {
 	{
 		.name = "dsc_0", .id = DSC_0,
@@ -88,8 +136,10 @@ const struct dpu_mdss_cfg dpu_sdm670_cfg = {
 	.ctl = sdm845_ctl,
 	.sspp_count = ARRAY_SIZE(sdm670_sspp),
 	.sspp = sdm670_sspp,
-	.mixer_count = ARRAY_SIZE(sdm845_lm),
-	.mixer = sdm845_lm,
+	.mixer_count = ARRAY_SIZE(sdm670_lm),
+	.mixer = sdm670_lm,
+	.dspp_count = ARRAY_SIZE(sdm670_dspp),
+	.dspp = sdm670_dspp,
 	.pingpong_count = ARRAY_SIZE(sdm845_pp),
 	.pingpong = sdm845_pp,
 	.dsc_count = ARRAY_SIZE(sdm670_dsc),
diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_0_sm8150.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_0_sm8150.h
index 6ccfde82fecd..d8d5a91c00ec 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_0_sm8150.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_0_sm8150.h
@@ -76,7 +76,7 @@ static const struct dpu_sspp_cfg sm8150_sspp[] = {
 	{
 		.name = "sspp_0", .id = SSPP_VIG0,
 		.base = 0x4000, .len = 0x1f0,
-		.features = VIG_SDM845_MASK,
+		.features = VIG_SDM845_MASK_SDMA,
 		.sblk = &dpu_vig_sblk_qseed3_1_4,
 		.xin_id = 0,
 		.type = SSPP_TYPE_VIG,
@@ -84,7 +84,7 @@ static const struct dpu_sspp_cfg sm8150_sspp[] = {
 	}, {
 		.name = "sspp_1", .id = SSPP_VIG1,
 		.base = 0x6000, .len = 0x1f0,
-		.features = VIG_SDM845_MASK,
+		.features = VIG_SDM845_MASK_SDMA,
 		.sblk = &dpu_vig_sblk_qseed3_1_4,
 		.xin_id = 4,
 		.type = SSPP_TYPE_VIG,
@@ -92,7 +92,7 @@ static const struct dpu_sspp_cfg sm8150_sspp[] = {
 	}, {
 		.name = "sspp_2", .id = SSPP_VIG2,
 		.base = 0x8000, .len = 0x1f0,
-		.features = VIG_SDM845_MASK,
+		.features = VIG_SDM845_MASK_SDMA,
 		.sblk = &dpu_vig_sblk_qseed3_1_4,
 		.xin_id = 8,
 		.type = SSPP_TYPE_VIG,
@@ -100,7 +100,7 @@ static const struct dpu_sspp_cfg sm8150_sspp[] = {
 	}, {
 		.name = "sspp_3", .id = SSPP_VIG3,
 		.base = 0xa000, .len = 0x1f0,
-		.features = VIG_SDM845_MASK,
+		.features = VIG_SDM845_MASK_SDMA,
 		.sblk = &dpu_vig_sblk_qseed3_1_4,
 		.xin_id = 12,
 		.type = SSPP_TYPE_VIG,
@@ -108,7 +108,7 @@ static const struct dpu_sspp_cfg sm8150_sspp[] = {
 	}, {
 		.name = "sspp_8", .id = SSPP_DMA0,
 		.base = 0x24000, .len = 0x1f0,
-		.features = DMA_SDM845_MASK,
+		.features = DMA_SDM845_MASK_SDMA,
 		.sblk = &dpu_dma_sblk,
 		.xin_id = 1,
 		.type = SSPP_TYPE_DMA,
@@ -116,7 +116,7 @@ static const struct dpu_sspp_cfg sm8150_sspp[] = {
 	}, {
 		.name = "sspp_9", .id = SSPP_DMA1,
 		.base = 0x26000, .len = 0x1f0,
-		.features = DMA_SDM845_MASK,
+		.features = DMA_SDM845_MASK_SDMA,
 		.sblk = &dpu_dma_sblk,
 		.xin_id = 5,
 		.type = SSPP_TYPE_DMA,
@@ -124,7 +124,7 @@ static const struct dpu_sspp_cfg sm8150_sspp[] = {
 	}, {
 		.name = "sspp_10", .id = SSPP_DMA2,
 		.base = 0x28000, .len = 0x1f0,
-		.features = DMA_CURSOR_SDM845_MASK,
+		.features = DMA_CURSOR_SDM845_MASK_SDMA,
 		.sblk = &dpu_dma_sblk,
 		.xin_id = 9,
 		.type = SSPP_TYPE_DMA,
@@ -132,7 +132,7 @@ static const struct dpu_sspp_cfg sm8150_sspp[] = {
 	}, {
 		.name = "sspp_11", .id = SSPP_DMA3,
 		.base = 0x2a000, .len = 0x1f0,
-		.features = DMA_CURSOR_SDM845_MASK,
+		.features = DMA_CURSOR_SDM845_MASK_SDMA,
 		.sblk = &dpu_dma_sblk,
 		.xin_id = 13,
 		.type = SSPP_TYPE_DMA,
@@ -164,6 +164,7 @@ static const struct dpu_lm_cfg sm8150_lm[] = {
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_3,
 		.pingpong = PINGPONG_2,
+		.dspp = DSPP_2,
 	}, {
 		.name = "lm_3", .id = LM_3,
 		.base = 0x47000, .len = 0x320,
@@ -171,6 +172,7 @@ static const struct dpu_lm_cfg sm8150_lm[] = {
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_2,
 		.pingpong = PINGPONG_3,
+		.dspp = DSPP_3,
 	}, {
 		.name = "lm_4", .id = LM_4,
 		.base = 0x48000, .len = 0x320,
@@ -295,7 +297,7 @@ static const struct dpu_wb_cfg sm8150_wb[] = {
 	{
 		.name = "wb_2", .id = WB_2,
 		.base = 0x65000, .len = 0x2c8,
-		.features = WB_SDM845_MASK,
+		.features = WB_SM8250_MASK,
 		.format_list = wb2_formats_rgb,
 		.num_formats = ARRAY_SIZE(wb2_formats_rgb),
 		.clk_ctrl = DPU_CLK_CTRL_WB2,
diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_1_sc8180x.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_1_sc8180x.h
index bab19ddd1d4f..67f0694a2f10 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_1_sc8180x.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_1_sc8180x.h
@@ -75,7 +75,7 @@ static const struct dpu_sspp_cfg sc8180x_sspp[] = {
 	{
 		.name = "sspp_0", .id = SSPP_VIG0,
 		.base = 0x4000, .len = 0x1f0,
-		.features = VIG_SDM845_MASK,
+		.features = VIG_SDM845_MASK_SDMA,
 		.sblk = &dpu_vig_sblk_qseed3_1_4,
 		.xin_id = 0,
 		.type = SSPP_TYPE_VIG,
@@ -83,7 +83,7 @@ static const struct dpu_sspp_cfg sc8180x_sspp[] = {
 	}, {
 		.name = "sspp_1", .id = SSPP_VIG1,
 		.base = 0x6000, .len = 0x1f0,
-		.features = VIG_SDM845_MASK,
+		.features = VIG_SDM845_MASK_SDMA,
 		.sblk = &dpu_vig_sblk_qseed3_1_4,
 		.xin_id = 4,
 		.type = SSPP_TYPE_VIG,
@@ -91,7 +91,7 @@ static const struct dpu_sspp_cfg sc8180x_sspp[] = {
 	}, {
 		.name = "sspp_2", .id = SSPP_VIG2,
 		.base = 0x8000, .len = 0x1f0,
-		.features = VIG_SDM845_MASK,
+		.features = VIG_SDM845_MASK_SDMA,
 		.sblk = &dpu_vig_sblk_qseed3_1_4,
 		.xin_id = 8,
 		.type = SSPP_TYPE_VIG,
@@ -99,7 +99,7 @@ static const struct dpu_sspp_cfg sc8180x_sspp[] = {
 	}, {
 		.name = "sspp_3", .id = SSPP_VIG3,
 		.base = 0xa000, .len = 0x1f0,
-		.features = VIG_SDM845_MASK,
+		.features = VIG_SDM845_MASK_SDMA,
 		.sblk = &dpu_vig_sblk_qseed3_1_4,
 		.xin_id = 12,
 		.type = SSPP_TYPE_VIG,
@@ -107,7 +107,7 @@ static const struct dpu_sspp_cfg sc8180x_sspp[] = {
 	}, {
 		.name = "sspp_8", .id = SSPP_DMA0,
 		.base = 0x24000, .len = 0x1f0,
-		.features = DMA_SDM845_MASK,
+		.features = DMA_SDM845_MASK_SDMA,
 		.sblk = &dpu_dma_sblk,
 		.xin_id = 1,
 		.type = SSPP_TYPE_DMA,
@@ -115,7 +115,7 @@ static const struct dpu_sspp_cfg sc8180x_sspp[] = {
 	}, {
 		.name = "sspp_9", .id = SSPP_DMA1,
 		.base = 0x26000, .len = 0x1f0,
-		.features = DMA_SDM845_MASK,
+		.features = DMA_SDM845_MASK_SDMA,
 		.sblk = &dpu_dma_sblk,
 		.xin_id = 5,
 		.type = SSPP_TYPE_DMA,
@@ -123,7 +123,7 @@ static const struct dpu_sspp_cfg sc8180x_sspp[] = {
 	}, {
 		.name = "sspp_10", .id = SSPP_DMA2,
 		.base = 0x28000, .len = 0x1f0,
-		.features = DMA_CURSOR_SDM845_MASK,
+		.features = DMA_CURSOR_SDM845_MASK_SDMA,
 		.sblk = &dpu_dma_sblk,
 		.xin_id = 9,
 		.type = SSPP_TYPE_DMA,
@@ -131,7 +131,7 @@ static const struct dpu_sspp_cfg sc8180x_sspp[] = {
 	}, {
 		.name = "sspp_11", .id = SSPP_DMA3,
 		.base = 0x2a000, .len = 0x1f0,
-		.features = DMA_CURSOR_SDM845_MASK,
+		.features = DMA_CURSOR_SDM845_MASK_SDMA,
 		.sblk = &dpu_dma_sblk,
 		.xin_id = 13,
 		.type = SSPP_TYPE_DMA,
@@ -163,6 +163,7 @@ static const struct dpu_lm_cfg sc8180x_lm[] = {
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_3,
 		.pingpong = PINGPONG_2,
+		.dspp = DSPP_2,
 	}, {
 		.name = "lm_3", .id = LM_3,
 		.base = 0x47000, .len = 0x320,
@@ -170,6 +171,7 @@ static const struct dpu_lm_cfg sc8180x_lm[] = {
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_2,
 		.pingpong = PINGPONG_3,
+		.dspp = DSPP_3,
 	}, {
 		.name = "lm_4", .id = LM_4,
 		.base = 0x48000, .len = 0x320,
@@ -302,7 +304,7 @@ static const struct dpu_wb_cfg sc8180x_wb[] = {
 	{
 		.name = "wb_2", .id = WB_2,
 		.base = 0x65000, .len = 0x2c8,
-		.features = WB_SDM845_MASK,
+		.features = WB_SM8250_MASK,
 		.format_list = wb2_formats_rgb,
 		.num_formats = ARRAY_SIZE(wb2_formats_rgb),
 		.clk_ctrl = DPU_CLK_CTRL_WB2,
@@ -381,6 +383,7 @@ static const struct dpu_perf_cfg sc8180x_perf_data = {
 	.min_core_ib = 2400000,
 	.min_llcc_ib = 800000,
 	.min_dram_ib = 800000,
+	.min_prefill_lines = 24,
 	.danger_lut_tbl = {0xf, 0xffff, 0x0},
 	.safe_lut_tbl = {0xfff0, 0xf000, 0xffff},
 	.qos_lut_tbl = {
diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_4_sm6125.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_4_sm6125.h
index d039b96beb97..76f60a2df7a8 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_4_sm6125.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_4_sm6125.h
@@ -144,7 +144,7 @@ static const struct dpu_wb_cfg sm6125_wb[] = {
 	{
 		.name = "wb_2", .id = WB_2,
 		.base = 0x65000, .len = 0x2c8,
-		.features = WB_SDM845_MASK,
+		.features = WB_SM8250_MASK,
 		.format_list = wb2_formats_rgb,
 		.num_formats = ARRAY_SIZE(wb2_formats_rgb),
 		.clk_ctrl = DPU_CLK_CTRL_WB2,
diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_0_sm8250.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_0_sm8250.h
index a57d50b1f028..e8916ae826a6 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_0_sm8250.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_0_sm8250.h
@@ -162,6 +162,7 @@ static const struct dpu_lm_cfg sm8250_lm[] = {
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_3,
 		.pingpong = PINGPONG_2,
+		.dspp = DSPP_2,
 	}, {
 		.name = "lm_3", .id = LM_3,
 		.base = 0x47000, .len = 0x320,
@@ -169,6 +170,7 @@ static const struct dpu_lm_cfg sm8250_lm[] = {
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_2,
 		.pingpong = PINGPONG_3,
+		.dspp = DSPP_3,
 	}, {
 		.name = "lm_4", .id = LM_4,
 		.base = 0x48000, .len = 0x320,
diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h
index aced16e350da..f7c08e89c882 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h
@@ -162,6 +162,7 @@ static const struct dpu_lm_cfg sm8350_lm[] = {
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_3,
 		.pingpong = PINGPONG_2,
+		.dspp = DSPP_2,
 	}, {
 		.name = "lm_3", .id = LM_3,
 		.base = 0x47000, .len = 0x320,
@@ -169,6 +170,7 @@ static const struct dpu_lm_cfg sm8350_lm[] = {
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_2,
 		.pingpong = PINGPONG_3,
+		.dspp = DSPP_3,
 	}, {
 		.name = "lm_4", .id = LM_4,
 		.base = 0x48000, .len = 0x320,
diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_0_sm8550.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_0_sm8550.h
index ad48defa154f..a1dbbf5c652f 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_0_sm8550.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_0_sm8550.h
@@ -160,6 +160,7 @@ static const struct dpu_lm_cfg sm8550_lm[] = {
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_3,
 		.pingpong = PINGPONG_2,
+		.dspp = DSPP_2,
 	}, {
 		.name = "lm_3", .id = LM_3,
 		.base = 0x47000, .len = 0x320,
@@ -167,6 +168,7 @@ static const struct dpu_lm_cfg sm8550_lm[] = {
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_2,
 		.pingpong = PINGPONG_3,
+		.dspp = DSPP_3,
 	}, {
 		.name = "lm_4", .id = LM_4,
 		.base = 0x48000, .len = 0x320,
diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_2_x1e80100.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_2_x1e80100.h
index a3e60ac70689..4f110be6b750 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_2_x1e80100.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_2_x1e80100.h
@@ -159,6 +159,7 @@ static const struct dpu_lm_cfg x1e80100_lm[] = {
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_3,
 		.pingpong = PINGPONG_2,
+		.dspp = DSPP_2,
 	}, {
 		.name = "lm_3", .id = LM_3,
 		.base = 0x47000, .len = 0x320,
@@ -166,6 +167,7 @@ static const struct dpu_lm_cfg x1e80100_lm[] = {
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_2,
 		.pingpong = PINGPONG_3,
+		.dspp = DSPP_3,
 	}, {
 		.name = "lm_4", .id = LM_4,
 		.base = 0x48000, .len = 0x320,
@@ -389,8 +391,8 @@ static const struct dpu_intf_cfg x1e80100_intf[] = {
 		.type = INTF_DP,
 		.controller_id = MSM_DP_CONTROLLER_2,
 		.prog_fetch_lines_worst_case = 24,
-		.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 17),
-		.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 16),
+		.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 16),
+		.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 17),
 	}, {
 		.name = "intf_7", .id = INTF_7,
 		.base = 0x3b000, .len = 0x280,
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
index db6c57900781..ecd595215a6b 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
@@ -1191,10 +1191,6 @@ static int dpu_crtc_atomic_check(struct drm_crtc *crtc,
 
 	DRM_DEBUG_ATOMIC("%s: check\n", dpu_crtc->name);
 
-	/* force a full mode set if active state changed */
-	if (crtc_state->active_changed)
-		crtc_state->mode_changed = true;
-
 	if (cstate->num_mixers) {
 		rc = _dpu_crtc_check_and_setup_lm_bounds(crtc, crtc_state);
 		if (rc)
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
index bd3698bf0cf7..47b514c89ce6 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
@@ -718,12 +718,11 @@ static int dpu_encoder_virt_atomic_check(
 		crtc_state->mode_changed = true;
 	/*
 	 * Release and Allocate resources on every modeset
-	 * Dont allocate when active is false.
 	 */
 	if (drm_atomic_crtc_needs_modeset(crtc_state)) {
 		dpu_rm_release(global_state, drm_enc);
 
-		if (!crtc_state->active_changed || crtc_state->enable)
+		if (crtc_state->enable)
 			ret = dpu_rm_reserve(&dpu_kms->rm, global_state,
 					drm_enc, crtc_state, topology);
 		if (!ret)
@@ -2125,6 +2124,9 @@ void dpu_encoder_helper_phys_cleanup(struct dpu_encoder_phys *phys_enc)
 		}
 	}
 
+	if (phys_enc->hw_pp && phys_enc->hw_pp->ops.setup_dither)
+		phys_enc->hw_pp->ops.setup_dither(phys_enc->hw_pp, NULL);
+
 	/* reset the merge 3D HW block */
 	if (phys_enc->hw_pp && phys_enc->hw_pp->merge_3d) {
 		phys_enc->hw_pp->merge_3d->ops.setup_3d_mode(phys_enc->hw_pp->merge_3d,
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c
index d8a2edebfe8c..b7699ca89dcc 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c
@@ -94,17 +94,21 @@ static void drm_mode_to_intf_timing_params(
 		timing->vsync_polarity = 0;
 	}
 
-	/* for DP/EDP, Shift timings to align it to bottom right */
-	if (phys_enc->hw_intf->cap->type == INTF_DP) {
+	timing->wide_bus_en = dpu_encoder_is_widebus_enabled(phys_enc->parent);
+	timing->compression_en = dpu_encoder_is_dsc_enabled(phys_enc->parent);
+
+	/*
+	 *  For DP/EDP, Shift timings to align it to bottom right.
+	 *  wide_bus_en is set for everything excluding SDM845 &
+	 *  porch changes cause DisplayPort failure and HDMI tearing.
+	 */
+	if (phys_enc->hw_intf->cap->type == INTF_DP && timing->wide_bus_en) {
 		timing->h_back_porch += timing->h_front_porch;
 		timing->h_front_porch = 0;
 		timing->v_back_porch += timing->v_front_porch;
 		timing->v_front_porch = 0;
 	}
 
-	timing->wide_bus_en = dpu_encoder_is_widebus_enabled(phys_enc->parent);
-	timing->compression_en = dpu_encoder_is_dsc_enabled(phys_enc->parent);
-
 	/*
 	 * for DP, divide the horizonal parameters by 2 when
 	 * widebus is enabled
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dsc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dsc.c
index 5e9aad1b2aa2..d1e0fb213976 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dsc.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dsc.c
@@ -52,6 +52,7 @@ static void dpu_hw_dsc_config(struct dpu_hw_dsc *hw_dsc,
 	u32 slice_last_group_size;
 	u32 det_thresh_flatness;
 	bool is_cmd_mode = !(mode & DSC_MODE_VIDEO);
+	bool input_10_bits = dsc->bits_per_component == 10;
 
 	DPU_REG_WRITE(c, DSC_COMMON_MODE, mode);
 
@@ -68,7 +69,7 @@ static void dpu_hw_dsc_config(struct dpu_hw_dsc *hw_dsc,
 	data |= (dsc->line_buf_depth << 3);
 	data |= (dsc->simple_422 << 2);
 	data |= (dsc->convert_rgb << 1);
-	data |= dsc->bits_per_component;
+	data |= input_10_bits;
 
 	DPU_REG_WRITE(c, DSC_ENC, data);
 
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.c
index 0f40eea7f5e2..2040bee8d512 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.c
@@ -272,7 +272,7 @@ static void _setup_mdp_ops(struct dpu_hw_mdp_ops *ops,
 
 	if (cap & BIT(DPU_MDP_VSYNC_SEL))
 		ops->setup_vsync_source = dpu_hw_setup_vsync_sel;
-	else
+	else if (!(cap & BIT(DPU_MDP_PERIPH_0_REMOVED)))
 		ops->setup_vsync_source = dpu_hw_setup_wd_timer;
 
 	ops->get_safe_status = dpu_hw_get_safe_status;
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_writeback.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_writeback.c
index 16f144cbc0c9..8ff496082902 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_writeback.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_writeback.c
@@ -42,9 +42,6 @@ static int dpu_wb_conn_atomic_check(struct drm_connector *connector,
 	if (!conn_state || !conn_state->connector) {
 		DPU_ERROR("invalid connector state\n");
 		return -EINVAL;
-	} else if (conn_state->connector->status != connector_status_connected) {
-		DPU_ERROR("connector not connected %d\n", conn_state->connector->status);
-		return -EINVAL;
 	}
 
 	crtc = conn_state->crtc;
diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_lcdc_encoder.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_lcdc_encoder.c
index 576995ddce37..8bbc7fb881d5 100644
--- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_lcdc_encoder.c
+++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_lcdc_encoder.c
@@ -389,7 +389,7 @@ struct drm_encoder *mdp4_lcdc_encoder_init(struct drm_device *dev,
 
 	/* TODO: different regulators in other cases? */
 	mdp4_lcdc_encoder->regs[0].supply = "lvds-vccs-3p3v";
-	mdp4_lcdc_encoder->regs[1].supply = "lvds-vccs-3p3v";
+	mdp4_lcdc_encoder->regs[1].supply = "lvds-pll-vdda";
 	mdp4_lcdc_encoder->regs[2].supply = "lvds-vdda";
 
 	ret = devm_regulator_bulk_get(dev->dev,
diff --git a/drivers/gpu/drm/msm/dp/dp_audio.c b/drivers/gpu/drm/msm/dp/dp_audio.c
index a599fc5d63c5..f4e01da5c55b 100644
--- a/drivers/gpu/drm/msm/dp/dp_audio.c
+++ b/drivers/gpu/drm/msm/dp/dp_audio.c
@@ -329,10 +329,10 @@ static void dp_audio_safe_to_exit_level(struct dp_audio_private *audio)
 		safe_to_exit_level = 5;
 		break;
 	default:
+		safe_to_exit_level = 14;
 		drm_dbg_dp(audio->drm_dev,
 				"setting the default safe_to_exit_level = %u\n",
 				safe_to_exit_level);
-		safe_to_exit_level = 14;
 		break;
 	}
 
diff --git a/drivers/gpu/drm/msm/dp/dp_display.c b/drivers/gpu/drm/msm/dp/dp_display.c
index e1228fb093ee..a5c1534eafdb 100644
--- a/drivers/gpu/drm/msm/dp/dp_display.c
+++ b/drivers/gpu/drm/msm/dp/dp_display.c
@@ -928,16 +928,17 @@ enum drm_mode_status dp_bridge_mode_valid(struct drm_bridge *bridge,
 		return -EINVAL;
 	}
 
-	if (mode->clock > DP_MAX_PIXEL_CLK_KHZ)
-		return MODE_CLOCK_HIGH;
-
 	dp_display = container_of(dp, struct dp_display_private, dp_display);
 	link_info = &dp_display->panel->link_info;
 
-	if (drm_mode_is_420_only(&dp->connector->display_info, mode) &&
-	    dp_display->panel->vsc_sdp_supported)
+	if ((drm_mode_is_420_only(&dp->connector->display_info, mode) &&
+	     dp_display->panel->vsc_sdp_supported) ||
+	     msm_dp_wide_bus_available(dp))
 		mode_pclk_khz /= 2;
 
+	if (mode_pclk_khz > DP_MAX_PIXEL_CLK_KHZ)
+		return MODE_CLOCK_HIGH;
+
 	mode_bpp = dp->connector->display_info.bpc * num_components;
 	if (!mode_bpp)
 		mode_bpp = default_bpp;
diff --git a/drivers/gpu/drm/msm/dp/dp_drm.c b/drivers/gpu/drm/msm/dp/dp_drm.c
index 1b9be5bd97f1..da0176eae3fe 100644
--- a/drivers/gpu/drm/msm/dp/dp_drm.c
+++ b/drivers/gpu/drm/msm/dp/dp_drm.c
@@ -257,7 +257,10 @@ static enum drm_mode_status edp_bridge_mode_valid(struct drm_bridge *bridge,
 		return -EINVAL;
 	}
 
-	if (mode->clock > DP_MAX_PIXEL_CLK_KHZ)
+	if (msm_dp_wide_bus_available(dp))
+		mode_pclk_khz /= 2;
+
+	if (mode_pclk_khz > DP_MAX_PIXEL_CLK_KHZ)
 		return MODE_CLOCK_HIGH;
 
 	/*
diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c
index a98d24b7cb00..d22e01751f5e 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_host.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_host.c
@@ -846,7 +846,7 @@ static void dsi_ctrl_enable(struct msm_dsi_host *msm_host,
 		dsi_write(msm_host, REG_DSI_CPHY_MODE_CTRL, BIT(0));
 }
 
-static void dsi_update_dsc_timing(struct msm_dsi_host *msm_host, bool is_cmd_mode, u32 hdisplay)
+static void dsi_update_dsc_timing(struct msm_dsi_host *msm_host, bool is_cmd_mode)
 {
 	struct drm_dsc_config *dsc = msm_host->dsc;
 	u32 reg, reg_ctrl, reg_ctrl2;
@@ -858,7 +858,7 @@ static void dsi_update_dsc_timing(struct msm_dsi_host *msm_host, bool is_cmd_mod
 	/* first calculate dsc parameters and then program
 	 * compress mode registers
 	 */
-	slice_per_intf = msm_dsc_get_slices_per_intf(dsc, hdisplay);
+	slice_per_intf = dsc->slice_count;
 
 	total_bytes_per_intf = dsc->slice_chunk_size * slice_per_intf;
 	bytes_per_pkt = dsc->slice_chunk_size; /* * slice_per_pkt; */
@@ -991,7 +991,7 @@ static void dsi_timing_setup(struct msm_dsi_host *msm_host, bool is_bonded_dsi)
 
 	if (msm_host->mode_flags & MIPI_DSI_MODE_VIDEO) {
 		if (msm_host->dsc)
-			dsi_update_dsc_timing(msm_host, false, mode->hdisplay);
+			dsi_update_dsc_timing(msm_host, false);
 
 		dsi_write(msm_host, REG_DSI_ACTIVE_H,
 			DSI_ACTIVE_H_START(ha_start) |
@@ -1012,7 +1012,7 @@ static void dsi_timing_setup(struct msm_dsi_host *msm_host, bool is_bonded_dsi)
 			DSI_ACTIVE_VSYNC_VPOS_END(vs_end));
 	} else {		/* command mode */
 		if (msm_host->dsc)
-			dsi_update_dsc_timing(msm_host, true, mode->hdisplay);
+			dsi_update_dsc_timing(msm_host, true);
 
 		/* image data and 1 byte write_memory_start cmd */
 		if (!msm_host->dsc)
@@ -1827,8 +1827,15 @@ static int dsi_host_parse_dt(struct msm_dsi_host *msm_host)
 			__func__, ret);
 		goto err;
 	}
-	if (!ret)
+	if (!ret) {
 		msm_dsi->te_source = devm_kstrdup(dev, te_source, GFP_KERNEL);
+		if (!msm_dsi->te_source) {
+			DRM_DEV_ERROR(dev, "%s: failed to allocate te_source\n",
+				__func__);
+			ret = -ENOMEM;
+			goto err;
+		}
+	}
 	ret = 0;
 
 	if (of_property_read_bool(np, "syscon-sfpb")) {
diff --git a/drivers/gpu/drm/msm/dsi/dsi_manager.c b/drivers/gpu/drm/msm/dsi/dsi_manager.c
index a210b7c9e5ca..4fabb01345aa 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_manager.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_manager.c
@@ -74,17 +74,35 @@ static int dsi_mgr_setup_components(int id)
 	int ret;
 
 	if (!IS_BONDED_DSI()) {
+		/*
+		 * Set the usecase before calling msm_dsi_host_register(), which would
+		 * already program the PLL source mux based on a default usecase.
+		 */
+		msm_dsi_phy_set_usecase(msm_dsi->phy, MSM_DSI_PHY_STANDALONE);
+		msm_dsi_host_set_phy_mode(msm_dsi->host, msm_dsi->phy);
+
 		ret = msm_dsi_host_register(msm_dsi->host);
 		if (ret)
 			return ret;
-
-		msm_dsi_phy_set_usecase(msm_dsi->phy, MSM_DSI_PHY_STANDALONE);
-		msm_dsi_host_set_phy_mode(msm_dsi->host, msm_dsi->phy);
 	} else if (other_dsi) {
 		struct msm_dsi *master_link_dsi = IS_MASTER_DSI_LINK(id) ?
 							msm_dsi : other_dsi;
 		struct msm_dsi *slave_link_dsi = IS_MASTER_DSI_LINK(id) ?
 							other_dsi : msm_dsi;
+
+		/*
+		 * PLL0 is to drive both DSI link clocks in bonded DSI mode.
+		 *
+		 * Set the usecase before calling msm_dsi_host_register(), which would
+		 * already program the PLL source mux based on a default usecase.
+		 */
+		msm_dsi_phy_set_usecase(clk_master_dsi->phy,
+					MSM_DSI_PHY_MASTER);
+		msm_dsi_phy_set_usecase(clk_slave_dsi->phy,
+					MSM_DSI_PHY_SLAVE);
+		msm_dsi_host_set_phy_mode(msm_dsi->host, msm_dsi->phy);
+		msm_dsi_host_set_phy_mode(other_dsi->host, other_dsi->phy);
+
 		/* Register slave host first, so that slave DSI device
 		 * has a chance to probe, and do not block the master
 		 * DSI device's probe.
@@ -98,14 +116,6 @@ static int dsi_mgr_setup_components(int id)
 		ret = msm_dsi_host_register(master_link_dsi->host);
 		if (ret)
 			return ret;
-
-		/* PLL0 is to drive both 2 DSI link clocks in bonded DSI mode. */
-		msm_dsi_phy_set_usecase(clk_master_dsi->phy,
-					MSM_DSI_PHY_MASTER);
-		msm_dsi_phy_set_usecase(clk_slave_dsi->phy,
-					MSM_DSI_PHY_SLAVE);
-		msm_dsi_host_set_phy_mode(msm_dsi->host, msm_dsi->phy);
-		msm_dsi_host_set_phy_mode(other_dsi->host, other_dsi->phy);
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c
index 677c62571811..28cc550e22a8 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c
@@ -703,6 +703,13 @@ static int dsi_pll_10nm_init(struct msm_dsi_phy *phy)
 	/* TODO: Remove this when we have proper display handover support */
 	msm_dsi_phy_pll_save_state(phy);
 
+	/*
+	 * Store also proper vco_current_rate, because its value will be used in
+	 * dsi_10nm_pll_restore_state().
+	 */
+	if (!dsi_pll_10nm_vco_recalc_rate(&pll_10nm->clk_hw, VCO_REF_CLK_RATE))
+		pll_10nm->vco_current_rate = pll_10nm->phy->cfg->min_pll_rate;
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c
index 031446c87dae..a2c87c84aa05 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c
@@ -83,6 +83,9 @@ struct dsi_pll_7nm {
 	/* protects REG_DSI_7nm_PHY_CMN_CLK_CFG0 register */
 	spinlock_t postdiv_lock;
 
+	/* protects REG_DSI_7nm_PHY_CMN_CLK_CFG1 register */
+	spinlock_t pclk_mux_lock;
+
 	struct pll_7nm_cached_state cached_state;
 
 	struct dsi_pll_7nm *slave;
@@ -302,7 +305,7 @@ static void dsi_pll_commit(struct dsi_pll_7nm *pll, struct dsi_pll_config *confi
 	writel(pll->phy->cphy_mode ? 0x00 : 0x10,
 	       base + REG_DSI_7nm_PHY_PLL_CMODE_1);
 	writel(config->pll_clock_inverters,
-	       base + REG_DSI_7nm_PHY_PLL_CLOCK_INVERTERS);
+	       base + REG_DSI_7nm_PHY_PLL_CLOCK_INVERTERS_1);
 }
 
 static int dsi_pll_7nm_vco_set_rate(struct clk_hw *hw, unsigned long rate,
@@ -372,22 +375,41 @@ static void dsi_pll_enable_pll_bias(struct dsi_pll_7nm *pll)
 	ndelay(250);
 }
 
-static void dsi_pll_disable_global_clk(struct dsi_pll_7nm *pll)
+static void dsi_pll_cmn_clk_cfg0_write(struct dsi_pll_7nm *pll, u32 val)
 {
+	unsigned long flags;
+
+	spin_lock_irqsave(&pll->postdiv_lock, flags);
+	writel(val, pll->phy->base + REG_DSI_7nm_PHY_CMN_CLK_CFG0);
+	spin_unlock_irqrestore(&pll->postdiv_lock, flags);
+}
+
+static void dsi_pll_cmn_clk_cfg1_update(struct dsi_pll_7nm *pll, u32 mask,
+					u32 val)
+{
+	unsigned long flags;
 	u32 data;
 
+	spin_lock_irqsave(&pll->pclk_mux_lock, flags);
 	data = readl(pll->phy->base + REG_DSI_7nm_PHY_CMN_CLK_CFG1);
-	writel(data & ~BIT(5), pll->phy->base + REG_DSI_7nm_PHY_CMN_CLK_CFG1);
+	data &= ~mask;
+	data |= val & mask;
+
+	writel(data, pll->phy->base + REG_DSI_7nm_PHY_CMN_CLK_CFG1);
+	spin_unlock_irqrestore(&pll->pclk_mux_lock, flags);
+}
+
+static void dsi_pll_disable_global_clk(struct dsi_pll_7nm *pll)
+{
+	dsi_pll_cmn_clk_cfg1_update(pll, DSI_7nm_PHY_CMN_CLK_CFG1_CLK_EN, 0);
 }
 
 static void dsi_pll_enable_global_clk(struct dsi_pll_7nm *pll)
 {
-	u32 data;
+	u32 cfg_1 = DSI_7nm_PHY_CMN_CLK_CFG1_CLK_EN | DSI_7nm_PHY_CMN_CLK_CFG1_CLK_EN_SEL;
 
 	writel(0x04, pll->phy->base + REG_DSI_7nm_PHY_CMN_CTRL_3);
-
-	data = readl(pll->phy->base + REG_DSI_7nm_PHY_CMN_CLK_CFG1);
-	writel(data | BIT(5) | BIT(4), pll->phy->base + REG_DSI_7nm_PHY_CMN_CLK_CFG1);
+	dsi_pll_cmn_clk_cfg1_update(pll, cfg_1, cfg_1);
 }
 
 static void dsi_pll_phy_dig_reset(struct dsi_pll_7nm *pll)
@@ -565,7 +587,6 @@ static int dsi_7nm_pll_restore_state(struct msm_dsi_phy *phy)
 {
 	struct dsi_pll_7nm *pll_7nm = to_pll_7nm(phy->vco_hw);
 	struct pll_7nm_cached_state *cached = &pll_7nm->cached_state;
-	void __iomem *phy_base = pll_7nm->phy->base;
 	u32 val;
 	int ret;
 
@@ -574,13 +595,10 @@ static int dsi_7nm_pll_restore_state(struct msm_dsi_phy *phy)
 	val |= cached->pll_out_div;
 	writel(val, pll_7nm->phy->pll_base + REG_DSI_7nm_PHY_PLL_PLL_OUTDIV_RATE);
 
-	writel(cached->bit_clk_div | (cached->pix_clk_div << 4),
-	       phy_base + REG_DSI_7nm_PHY_CMN_CLK_CFG0);
-
-	val = readl(phy_base + REG_DSI_7nm_PHY_CMN_CLK_CFG1);
-	val &= ~0x3;
-	val |= cached->pll_mux;
-	writel(val, phy_base + REG_DSI_7nm_PHY_CMN_CLK_CFG1);
+	dsi_pll_cmn_clk_cfg0_write(pll_7nm,
+				   DSI_7nm_PHY_CMN_CLK_CFG0_DIV_CTRL_3_0(cached->bit_clk_div) |
+				   DSI_7nm_PHY_CMN_CLK_CFG0_DIV_CTRL_7_4(cached->pix_clk_div));
+	dsi_pll_cmn_clk_cfg1_update(pll_7nm, 0x3, cached->pll_mux);
 
 	ret = dsi_pll_7nm_vco_set_rate(phy->vco_hw,
 			pll_7nm->vco_current_rate,
@@ -599,7 +617,6 @@ static int dsi_7nm_pll_restore_state(struct msm_dsi_phy *phy)
 static int dsi_7nm_set_usecase(struct msm_dsi_phy *phy)
 {
 	struct dsi_pll_7nm *pll_7nm = to_pll_7nm(phy->vco_hw);
-	void __iomem *base = phy->base;
 	u32 data = 0x0;	/* internal PLL */
 
 	DBG("DSI PLL%d", pll_7nm->phy->id);
@@ -618,7 +635,8 @@ static int dsi_7nm_set_usecase(struct msm_dsi_phy *phy)
 	}
 
 	/* set PLL src */
-	writel(data << 2, base + REG_DSI_7nm_PHY_CMN_CLK_CFG1);
+	dsi_pll_cmn_clk_cfg1_update(pll_7nm, DSI_7nm_PHY_CMN_CLK_CFG1_BITCLK_SEL__MASK,
+				    DSI_7nm_PHY_CMN_CLK_CFG1_BITCLK_SEL(data));
 
 	return 0;
 }
@@ -733,7 +751,7 @@ static int pll_7nm_register(struct dsi_pll_7nm *pll_7nm, struct clk_hw **provide
 					pll_by_2_bit,
 				}), 2, 0, pll_7nm->phy->base +
 					REG_DSI_7nm_PHY_CMN_CLK_CFG1,
-				0, 1, 0, NULL);
+				0, 1, 0, &pll_7nm->pclk_mux_lock);
 		if (IS_ERR(hw)) {
 			ret = PTR_ERR(hw);
 			goto fail;
@@ -778,6 +796,7 @@ static int dsi_pll_7nm_init(struct msm_dsi_phy *phy)
 	pll_7nm_list[phy->id] = pll_7nm;
 
 	spin_lock_init(&pll_7nm->postdiv_lock);
+	spin_lock_init(&pll_7nm->pclk_mux_lock);
 
 	pll_7nm->phy = phy;
 
diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_phy_8998.c b/drivers/gpu/drm/msm/hdmi/hdmi_phy_8998.c
index e6ffaf92d26d..1c4211cfa2a4 100644
--- a/drivers/gpu/drm/msm/hdmi/hdmi_phy_8998.c
+++ b/drivers/gpu/drm/msm/hdmi/hdmi_phy_8998.c
@@ -137,7 +137,7 @@ static inline u32 pll_get_integloop_gain(u64 frac_start, u64 bclk, u32 ref_clk,
 
 	base <<= (digclk_divsel == 2 ? 1 : 0);
 
-	return (base <= 2046 ? base : 2046);
+	return base;
 }
 
 static inline u32 pll_get_pll_cmp(u64 fdata, unsigned long ref_clk)
diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index 8c13b08708d2..197d8d9a421d 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -550,6 +550,7 @@ static int msm_ioctl_gem_info_set_metadata(struct drm_gem_object *obj,
 					   u32 metadata_size)
 {
 	struct msm_gem_object *msm_obj = to_msm_bo(obj);
+	void *new_metadata;
 	void *buf;
 	int ret;
 
@@ -567,8 +568,14 @@ static int msm_ioctl_gem_info_set_metadata(struct drm_gem_object *obj,
 	if (ret)
 		goto out;
 
-	msm_obj->metadata =
+	new_metadata =
 		krealloc(msm_obj->metadata, metadata_size, GFP_KERNEL);
+	if (!new_metadata) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	msm_obj->metadata = new_metadata;
 	msm_obj->metadata_size = metadata_size;
 	memcpy(msm_obj->metadata, buf, metadata_size);
 
diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h
index 2e28a1344636..9526b22038ab 100644
--- a/drivers/gpu/drm/msm/msm_drv.h
+++ b/drivers/gpu/drm/msm/msm_drv.h
@@ -543,15 +543,12 @@ static inline int align_pitch(int width, int bpp)
 static inline unsigned long timeout_to_jiffies(const ktime_t *timeout)
 {
 	ktime_t now = ktime_get();
-	s64 remaining_jiffies;
 
-	if (ktime_compare(*timeout, now) < 0) {
-		remaining_jiffies = 0;
-	} else {
-		ktime_t rem = ktime_sub(*timeout, now);
-		remaining_jiffies = ktime_divns(rem, NSEC_PER_SEC / HZ);
-	}
+	if (ktime_compare(*timeout, now) <= 0)
+		return 0;
 
+	ktime_t rem = ktime_sub(*timeout, now);
+	s64 remaining_jiffies = ktime_divns(rem, NSEC_PER_SEC / HZ);
 	return clamp(remaining_jiffies, 1LL, (s64)INT_MAX);
 }
 
diff --git a/drivers/gpu/drm/msm/msm_dsc_helper.h b/drivers/gpu/drm/msm/msm_dsc_helper.h
index b9049fe1e279..63f95523b2cb 100644
--- a/drivers/gpu/drm/msm/msm_dsc_helper.h
+++ b/drivers/gpu/drm/msm/msm_dsc_helper.h
@@ -13,17 +13,6 @@
 #include <drm/display/drm_dsc_helper.h>
 
 /**
- * msm_dsc_get_slices_per_intf() - calculate number of slices per interface
- * @dsc: Pointer to drm dsc config struct
- * @intf_width: interface width in pixels
- * Returns: Integer representing the number of slices for the given interface
- */
-static inline u32 msm_dsc_get_slices_per_intf(const struct drm_dsc_config *dsc, u32 intf_width)
-{
-	return DIV_ROUND_UP(intf_width, dsc->slice_width);
-}
-
-/**
  * msm_dsc_get_bytes_per_line() - calculate bytes per line
  * @dsc: Pointer to drm dsc config struct
  * Returns: Integer value representing bytes per line. DSI and DP need
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index ebc9ba66efb8..eeb3b65dd4d1 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -963,7 +963,8 @@ void msm_gem_describe(struct drm_gem_object *obj, struct seq_file *m,
 	uint64_t off = drm_vma_node_start(&obj->vma_node);
 	const char *madv;
 
-	msm_gem_lock(obj);
+	if (!msm_gem_trylock(obj))
+		return;
 
 	stats->all.count++;
 	stats->all.size += obj->size;
diff --git a/drivers/gpu/drm/msm/msm_gem.h b/drivers/gpu/drm/msm/msm_gem.h
index 85f0257e83da..748053f70ca7 100644
--- a/drivers/gpu/drm/msm/msm_gem.h
+++ b/drivers/gpu/drm/msm/msm_gem.h
@@ -188,6 +188,12 @@ msm_gem_lock(struct drm_gem_object *obj)
 	dma_resv_lock(obj->resv, NULL);
 }
 
+static inline bool __must_check
+msm_gem_trylock(struct drm_gem_object *obj)
+{
+	return dma_resv_trylock(obj->resv);
+}
+
 static inline int
 msm_gem_lock_interruptible(struct drm_gem_object *obj)
 {
diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c
index fba78193127d..4b3a8ee8e278 100644
--- a/drivers/gpu/drm/msm/msm_gem_submit.c
+++ b/drivers/gpu/drm/msm/msm_gem_submit.c
@@ -85,6 +85,15 @@ void __msm_gem_submit_destroy(struct kref *kref)
 			container_of(kref, struct msm_gem_submit, ref);
 	unsigned i;
 
+	/*
+	 * In error paths, we could unref the submit without calling
+	 * drm_sched_entity_push_job(), so msm_job_free() will never
+	 * get called.  Since drm_sched_job_cleanup() will NULL out
+	 * s_fence, we can use that to detect this case.
+	 */
+	if (submit->base.s_fence)
+		drm_sched_job_cleanup(&submit->base);
+
 	if (submit->fence_id) {
 		spin_lock(&submit->queue->idr_lock);
 		idr_remove(&submit->queue->fence_idr, submit->fence_id);
@@ -658,6 +667,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 	struct msm_ringbuffer *ring;
 	struct msm_submit_post_dep *post_deps = NULL;
 	struct drm_syncobj **syncobjs_to_reset = NULL;
+	struct sync_file *sync_file = NULL;
 	int out_fence_fd = -1;
 	unsigned i;
 	int ret;
@@ -787,8 +797,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 			goto out;
 
 		if (!submit->cmd[i].size ||
-			((submit->cmd[i].size + submit->cmd[i].offset) >
-				obj->size / 4)) {
+		    (size_add(submit->cmd[i].size, submit->cmd[i].offset) > obj->size / 4)) {
 			SUBMIT_ERROR(submit, "invalid cmdstream size: %u\n", submit->cmd[i].size * 4);
 			ret = -EINVAL;
 			goto out;
@@ -869,7 +878,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 	}
 
 	if (ret == 0 && args->flags & MSM_SUBMIT_FENCE_FD_OUT) {
-		struct sync_file *sync_file = sync_file_create(submit->user_fence);
+		sync_file = sync_file_create(submit->user_fence);
 		if (!sync_file) {
 			ret = -ENOMEM;
 		} else {
@@ -903,8 +912,11 @@ out:
 out_unlock:
 	mutex_unlock(&queue->lock);
 out_post_unlock:
-	if (ret && (out_fence_fd >= 0))
+	if (ret && (out_fence_fd >= 0)) {
 		put_unused_fd(out_fence_fd);
+		if (sync_file)
+			fput(sync_file->file);
+	}
 
 	if (!IS_ERR_OR_NULL(submit)) {
 		msm_gem_submit_put(submit);
diff --git a/drivers/gpu/drm/msm/msm_gpu_devfreq.c b/drivers/gpu/drm/msm/msm_gpu_devfreq.c
index 6970b0f7f457..2e1d5c343272 100644
--- a/drivers/gpu/drm/msm/msm_gpu_devfreq.c
+++ b/drivers/gpu/drm/msm/msm_gpu_devfreq.c
@@ -156,6 +156,7 @@ void msm_devfreq_init(struct msm_gpu *gpu)
 	priv->gpu_devfreq_config.downdifferential = 10;
 
 	mutex_init(&df->lock);
+	df->suspended = true;
 
 	ret = dev_pm_qos_add_request(&gpu->pdev->dev, &df->boost_freq,
 				     DEV_PM_QOS_MIN_FREQUENCY, 0);
diff --git a/drivers/gpu/drm/msm/msm_kms.c b/drivers/gpu/drm/msm/msm_kms.c
index af6a6fcb1173..6749f0fbca96 100644
--- a/drivers/gpu/drm/msm/msm_kms.c
+++ b/drivers/gpu/drm/msm/msm_kms.c
@@ -244,7 +244,6 @@ int msm_drm_kms_init(struct device *dev, const struct drm_driver *drv)
 	ret = priv->kms_init(ddev);
 	if (ret) {
 		DRM_DEV_ERROR(dev, "failed to load kms\n");
-		priv->kms = NULL;
 		return ret;
 	}
 
diff --git a/drivers/gpu/drm/msm/registers/adreno/adreno_pm4.xml b/drivers/gpu/drm/msm/registers/adreno/adreno_pm4.xml
index cab01af55d22..2ca0ad6efc96 100644
--- a/drivers/gpu/drm/msm/registers/adreno/adreno_pm4.xml
+++ b/drivers/gpu/drm/msm/registers/adreno/adreno_pm4.xml
@@ -2260,7 +2260,15 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords)
 	<reg32 offset="0" name="0">
 		<bitfield name="CLEAR_ON_CHIP_TS" pos="0" type="boolean"/>
 		<bitfield name="CLEAR_RESOURCE_TABLE" pos="1" type="boolean"/>
-		<bitfield name="CLEAR_GLOBAL_LOCAL_TS" pos="2" type="boolean"/>
+		<bitfield name="CLEAR_BV_BR_COUNTER" pos="2" type="boolean"/>
+		<bitfield name="RESET_GLOBAL_LOCAL_TS" pos="3" type="boolean"/>
+	</reg32>
+</domain>
+
+<domain name="CP_INDIRECT_BUFFER" width="32" varset="chip" prefix="chip" variants="A5XX-">
+	<reg64 offset="0" name="IB_BASE" type="address"/>
+	<reg32 offset="2" name="2">
+		<bitfield name="IB_SIZE" low="0" high="19"/>
 	</reg32>
 </domain>
 
diff --git a/drivers/gpu/drm/msm/registers/display/dsi_phy_7nm.xml b/drivers/gpu/drm/msm/registers/display/dsi_phy_7nm.xml
index d54b72f92449..35f7f40e405b 100644
--- a/drivers/gpu/drm/msm/registers/display/dsi_phy_7nm.xml
+++ b/drivers/gpu/drm/msm/registers/display/dsi_phy_7nm.xml
@@ -9,8 +9,15 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd">
 	<reg32 offset="0x00004" name="REVISION_ID1"/>
 	<reg32 offset="0x00008" name="REVISION_ID2"/>
 	<reg32 offset="0x0000c" name="REVISION_ID3"/>
-	<reg32 offset="0x00010" name="CLK_CFG0"/>
-	<reg32 offset="0x00014" name="CLK_CFG1"/>
+	<reg32 offset="0x00010" name="CLK_CFG0">
+		<bitfield name="DIV_CTRL_3_0" low="0" high="3" type="uint"/>
+		<bitfield name="DIV_CTRL_7_4" low="4" high="7" type="uint"/>
+	</reg32>
+	<reg32 offset="0x00014" name="CLK_CFG1">
+		<bitfield name="CLK_EN" pos="5" type="boolean"/>
+		<bitfield name="CLK_EN_SEL" pos="4" type="boolean"/>
+		<bitfield name="BITCLK_SEL" low="2" high="3" type="uint"/>
+	</reg32>
 	<reg32 offset="0x00018" name="GLBL_CTRL"/>
 	<reg32 offset="0x0001c" name="RBUF_CTRL"/>
 	<reg32 offset="0x00020" name="VREG_CTRL_0"/>
diff --git a/drivers/gpu/drm/nouveau/Kconfig b/drivers/gpu/drm/nouveau/Kconfig
index ceef470c9fbf..1050a4617fc1 100644
--- a/drivers/gpu/drm/nouveau/Kconfig
+++ b/drivers/gpu/drm/nouveau/Kconfig
@@ -4,6 +4,8 @@ config DRM_NOUVEAU
 	depends on DRM && PCI && MMU
 	select IOMMU_API
 	select FW_LOADER
+	select FW_CACHE if PM_SLEEP
+	select DRM_CLIENT_SELECTION
 	select DRM_DISPLAY_DP_HELPER
 	select DRM_DISPLAY_HDMI_HELPER
 	select DRM_DISPLAY_HELPER
diff --git a/drivers/gpu/drm/nouveau/nouveau_backlight.c b/drivers/gpu/drm/nouveau/nouveau_backlight.c
index d47442125fa1..9aae26eb7d8f 100644
--- a/drivers/gpu/drm/nouveau/nouveau_backlight.c
+++ b/drivers/gpu/drm/nouveau/nouveau_backlight.c
@@ -42,7 +42,7 @@
 #include "nouveau_acpi.h"
 
 static struct ida bl_ida;
-#define BL_NAME_SIZE 15 // 12 for name + 2 for digits + 1 for '\0'
+#define BL_NAME_SIZE 24 // 12 for name + 11 for digits + 1 for '\0'
 
 static bool
 nouveau_get_backlight_name(char backlight_name[BL_NAME_SIZE],
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index db961eade225..2016c1e7242f 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -144,6 +144,9 @@ nouveau_bo_del_ttm(struct ttm_buffer_object *bo)
 	nouveau_bo_del_io_reserve_lru(bo);
 	nv10_bo_put_tile_region(dev, nvbo->tile, NULL);
 
+	if (bo->base.import_attach)
+		drm_prime_gem_destroy(&bo->base, bo->sg);
+
 	/*
 	 * If nouveau_bo_new() allocated this buffer, the GEM object was never
 	 * initialized, so don't attempt to release it.
diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c
index b06aa473102b..5ab4201c981e 100644
--- a/drivers/gpu/drm/nouveau/nouveau_connector.c
+++ b/drivers/gpu/drm/nouveau/nouveau_connector.c
@@ -776,7 +776,6 @@ nouveau_connector_force(struct drm_connector *connector)
 	if (!nv_encoder) {
 		NV_ERROR(drm, "can't find encoder to force %s on!\n",
 			 connector->name);
-		connector->status = connector_status_disconnected;
 		return;
 	}
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c
index 34985771b2a2..6e5adab03471 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.c
@@ -31,6 +31,7 @@
 #include <linux/dynamic_debug.h>
 
 #include <drm/drm_aperture.h>
+#include <drm/drm_client_setup.h>
 #include <drm/drm_drv.h>
 #include <drm/drm_fbdev_ttm.h>
 #include <drm/drm_gem_ttm_helper.h>
@@ -836,6 +837,7 @@ static int nouveau_drm_probe(struct pci_dev *pdev,
 {
 	struct nvkm_device *device;
 	struct nouveau_drm *drm;
+	const struct drm_format_info *format;
 	int ret;
 
 	if (vga_switcheroo_client_probe_defer(pdev))
@@ -873,9 +875,11 @@ static int nouveau_drm_probe(struct pci_dev *pdev,
 		goto fail_pci;
 
 	if (drm->client.device.info.ram_size <= 32 * 1024 * 1024)
-		drm_fbdev_ttm_setup(drm->dev, 8);
+		format = drm_format_info(DRM_FORMAT_C8);
 	else
-		drm_fbdev_ttm_setup(drm->dev, 32);
+		format = NULL;
+
+	drm_client_setup(drm->dev, format);
 
 	quirk_broken_nv_runpm(pdev);
 	return 0;
@@ -1318,6 +1322,8 @@ driver_stub = {
 	.dumb_create = nouveau_display_dumb_create,
 	.dumb_map_offset = drm_gem_ttm_dumb_map_offset,
 
+	DRM_FBDEV_TTM_DRIVER_OPS,
+
 	.name = DRIVER_NAME,
 	.desc = DRIVER_DESC,
 #ifdef GIT_REVISION
diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c
index 7cc84472cece..edddfc036c6d 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fence.c
+++ b/drivers/gpu/drm/nouveau/nouveau_fence.c
@@ -90,7 +90,7 @@ nouveau_fence_context_kill(struct nouveau_fence_chan *fctx, int error)
 	while (!list_empty(&fctx->pending)) {
 		fence = list_entry(fctx->pending.next, typeof(*fence), head);
 
-		if (error)
+		if (error && !dma_fence_is_signaled_locked(&fence->base))
 			dma_fence_set_error(&fence->base, error);
 
 		if (nouveau_fence_signal(fence))
diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c
index 9ae2cee1c7c5..67e3c99de73a 100644
--- a/drivers/gpu/drm/nouveau/nouveau_gem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_gem.c
@@ -87,9 +87,6 @@ nouveau_gem_object_del(struct drm_gem_object *gem)
 		return;
 	}
 
-	if (gem->import_attach)
-		drm_prime_gem_destroy(gem, nvbo->bo.sg);
-
 	ttm_bo_put(&nvbo->bo);
 
 	pm_runtime_mark_last_busy(dev);
diff --git a/drivers/gpu/drm/nouveau/nouveau_svm.c b/drivers/gpu/drm/nouveau/nouveau_svm.c
index b4da82ddbb6b..8ea98f06d39a 100644
--- a/drivers/gpu/drm/nouveau/nouveau_svm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_svm.c
@@ -590,6 +590,7 @@ static int nouveau_atomic_range_fault(struct nouveau_svmm *svmm,
 	unsigned long timeout =
 		jiffies + msecs_to_jiffies(HMM_RANGE_DEFAULT_TIMEOUT);
 	struct mm_struct *mm = svmm->notifier.mm;
+	struct folio *folio;
 	struct page *page;
 	unsigned long start = args->p.addr;
 	unsigned long notifier_seq;
@@ -616,12 +617,16 @@ static int nouveau_atomic_range_fault(struct nouveau_svmm *svmm,
 			ret = -EINVAL;
 			goto out;
 		}
+		folio = page_folio(page);
 
 		mutex_lock(&svmm->mutex);
 		if (!mmu_interval_read_retry(&notifier->notifier,
 					     notifier_seq))
 			break;
 		mutex_unlock(&svmm->mutex);
+
+		folio_unlock(folio);
+		folio_put(folio);
 	}
 
 	/* Map the page on the GPU. */
@@ -637,8 +642,8 @@ static int nouveau_atomic_range_fault(struct nouveau_svmm *svmm,
 	ret = nvif_object_ioctl(&svmm->vmm->vmm.object, args, size, NULL);
 	mutex_unlock(&svmm->mutex);
 
-	unlock_page(page);
-	put_page(page);
+	folio_unlock(folio);
+	folio_put(folio);
 
 out:
 	mmu_interval_notifier_remove(&notifier->notifier);
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
index d586aea30898..3ad4f6e9a8ac 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
@@ -58,7 +58,7 @@
 #include <linux/parser.h>
 
 #define GSP_MSG_MIN_SIZE GSP_PAGE_SIZE
-#define GSP_MSG_MAX_SIZE GSP_PAGE_MIN_SIZE * 16
+#define GSP_MSG_MAX_SIZE (GSP_MSG_MIN_SIZE * 16)
 
 struct r535_gsp_msg {
 	u8 auth_tag_buffer[16];
@@ -121,6 +121,8 @@ r535_gsp_msgq_wait(struct nvkm_gsp *gsp, u32 repc, u32 *prepc, int *ptime)
 		return mqe->data;
 	}
 
+	size = ALIGN(repc + GSP_MSG_HDR_SIZE, GSP_PAGE_SIZE);
+
 	msg = kvmalloc(repc, GFP_KERNEL);
 	if (!msg)
 		return ERR_PTR(-ENOMEM);
@@ -129,19 +131,15 @@ r535_gsp_msgq_wait(struct nvkm_gsp *gsp, u32 repc, u32 *prepc, int *ptime)
 	len = min_t(u32, repc, len);
 	memcpy(msg, mqe->data, len);
 
-	rptr += DIV_ROUND_UP(len, GSP_PAGE_SIZE);
-	if (rptr == gsp->msgq.cnt)
-		rptr = 0;
-
 	repc -= len;
 
 	if (repc) {
 		mqe = (void *)((u8 *)gsp->shm.msgq.ptr + 0x1000 + 0 * 0x1000);
 		memcpy(msg + len, mqe, repc);
-
-		rptr += DIV_ROUND_UP(repc, GSP_PAGE_SIZE);
 	}
 
+	rptr = (rptr + DIV_ROUND_UP(size, GSP_PAGE_SIZE)) % gsp->msgq.cnt;
+
 	mb();
 	(*gsp->msgq.rptr) = rptr;
 	return msg;
@@ -163,7 +161,7 @@ r535_gsp_cmdq_push(struct nvkm_gsp *gsp, void *argv)
 	u64 *end;
 	u64 csum = 0;
 	int free, time = 1000000;
-	u32 wptr, size;
+	u32 wptr, size, step;
 	u32 off = 0;
 
 	argc = ALIGN(GSP_MSG_HDR_SIZE + argc, GSP_PAGE_SIZE);
@@ -197,7 +195,9 @@ r535_gsp_cmdq_push(struct nvkm_gsp *gsp, void *argv)
 		}
 
 		cqe = (void *)((u8 *)gsp->shm.cmdq.ptr + 0x1000 + wptr * 0x1000);
-		size = min_t(u32, argc, (gsp->cmdq.cnt - wptr) * GSP_PAGE_SIZE);
+		step = min_t(u32, free, (gsp->cmdq.cnt - wptr));
+		size = min_t(u32, argc, step * GSP_PAGE_SIZE);
+
 		memcpy(cqe, (u8 *)cmd + off, size);
 
 		wptr += DIV_ROUND_UP(size, 0x1000);
@@ -1454,7 +1454,6 @@ r535_gsp_acpi_caps(acpi_handle handle, CAPS_METHOD_DATA *caps)
 	union acpi_object argv4 = {
 		.buffer.type    = ACPI_TYPE_BUFFER,
 		.buffer.length  = 4,
-		.buffer.pointer = kmalloc(argv4.buffer.length, GFP_KERNEL),
 	}, *obj;
 
 	caps->status = 0xffff;
@@ -1462,17 +1461,22 @@ r535_gsp_acpi_caps(acpi_handle handle, CAPS_METHOD_DATA *caps)
 	if (!acpi_check_dsm(handle, &NVOP_DSM_GUID, NVOP_DSM_REV, BIT_ULL(0x1a)))
 		return;
 
+	argv4.buffer.pointer = kmalloc(argv4.buffer.length, GFP_KERNEL);
+	if (!argv4.buffer.pointer)
+		return;
+
 	obj = acpi_evaluate_dsm(handle, &NVOP_DSM_GUID, NVOP_DSM_REV, 0x1a, &argv4);
 	if (!obj)
-		return;
+		goto done;
 
 	if (WARN_ON(obj->type != ACPI_TYPE_BUFFER) ||
 	    WARN_ON(obj->buffer.length != 4))
-		return;
+		goto done;
 
 	caps->status = 0;
 	caps->optimusCaps = *(u32 *)obj->buffer.pointer;
 
+done:
 	ACPI_FREE(obj);
 
 	kfree(argv4.buffer.pointer);
@@ -1489,24 +1493,28 @@ r535_gsp_acpi_jt(acpi_handle handle, JT_METHOD_DATA *jt)
 	union acpi_object argv4 = {
 		.buffer.type    = ACPI_TYPE_BUFFER,
 		.buffer.length  = sizeof(caps),
-		.buffer.pointer = kmalloc(argv4.buffer.length, GFP_KERNEL),
 	}, *obj;
 
 	jt->status = 0xffff;
 
+	argv4.buffer.pointer = kmalloc(argv4.buffer.length, GFP_KERNEL);
+	if (!argv4.buffer.pointer)
+		return;
+
 	obj = acpi_evaluate_dsm(handle, &JT_DSM_GUID, JT_DSM_REV, 0x1, &argv4);
 	if (!obj)
-		return;
+		goto done;
 
 	if (WARN_ON(obj->type != ACPI_TYPE_BUFFER) ||
 	    WARN_ON(obj->buffer.length != 4))
-		return;
+		goto done;
 
 	jt->status = 0;
 	jt->jtCaps = *(u32 *)obj->buffer.pointer;
 	jt->jtRevId = (jt->jtCaps & 0xfff00000) >> 20;
 	jt->bSBIOSCaps = 0;
 
+done:
 	ACPI_FREE(obj);
 
 	kfree(argv4.buffer.pointer);
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp10b.c b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp10b.c
index a6f410ba60bc..d393bc540f86 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp10b.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp10b.c
@@ -75,7 +75,7 @@ gp10b_pmu_acr = {
 	.bootstrap_multiple_falcons = gp10b_pmu_acr_bootstrap_multiple_falcons,
 };
 
-#if IS_ENABLED(CONFIG_ARCH_TEGRA_210_SOC)
+#if IS_ENABLED(CONFIG_ARCH_TEGRA_186_SOC)
 MODULE_FIRMWARE("nvidia/gp10b/pmu/desc.bin");
 MODULE_FIRMWARE("nvidia/gp10b/pmu/image.bin");
 MODULE_FIRMWARE("nvidia/gp10b/pmu/sig.bin");
diff --git a/drivers/gpu/drm/panel/panel-edp.c b/drivers/gpu/drm/panel/panel-edp.c
index 767e47a2b0c1..663af985d1b3 100644
--- a/drivers/gpu/drm/panel/panel-edp.c
+++ b/drivers/gpu/drm/panel/panel-edp.c
@@ -1983,6 +1983,7 @@ static const struct edp_panel_entry edp_panels[] = {
 	EDP_PANEL_ENTRY('S', 'H', 'P', 0x153a, &delay_200_500_e50, "LQ140T1JH01"),
 	EDP_PANEL_ENTRY('S', 'H', 'P', 0x154c, &delay_200_500_p2e100, "LQ116M1JW10"),
 
+	EDP_PANEL_ENTRY('S', 'T', 'A', 0x0004, &delay_200_500_e200, "116KHD024006"),
 	EDP_PANEL_ENTRY('S', 'T', 'A', 0x0100, &delay_100_500_e200, "2081116HHD028001-51D"),
 
 	{ /* sentinal */ }
diff --git a/drivers/gpu/drm/panel/panel-ilitek-ili9882t.c b/drivers/gpu/drm/panel/panel-ilitek-ili9882t.c
index 266a087fe14c..3c24a63b6be8 100644
--- a/drivers/gpu/drm/panel/panel-ilitek-ili9882t.c
+++ b/drivers/gpu/drm/panel/panel-ilitek-ili9882t.c
@@ -607,7 +607,7 @@ static int ili9882t_add(struct ili9882t *ili)
 
 	ili->enable_gpio = devm_gpiod_get(dev, "enable", GPIOD_OUT_LOW);
 	if (IS_ERR(ili->enable_gpio)) {
-		dev_err(dev, "cannot get reset-gpios %ld\n",
+		dev_err(dev, "cannot get enable-gpios %ld\n",
 			PTR_ERR(ili->enable_gpio));
 		return PTR_ERR(ili->enable_gpio);
 	}
diff --git a/drivers/gpu/drm/panel/panel-jadard-jd9365da-h3.c b/drivers/gpu/drm/panel/panel-jadard-jd9365da-h3.c
index 45d09e6fa667..eb0f8373258c 100644
--- a/drivers/gpu/drm/panel/panel-jadard-jd9365da-h3.c
+++ b/drivers/gpu/drm/panel/panel-jadard-jd9365da-h3.c
@@ -109,13 +109,13 @@ static int jadard_prepare(struct drm_panel *panel)
 	if (jadard->desc->lp11_to_reset_delay_ms)
 		msleep(jadard->desc->lp11_to_reset_delay_ms);
 
-	gpiod_set_value(jadard->reset, 1);
+	gpiod_set_value(jadard->reset, 0);
 	msleep(5);
 
-	gpiod_set_value(jadard->reset, 0);
+	gpiod_set_value(jadard->reset, 1);
 	msleep(10);
 
-	gpiod_set_value(jadard->reset, 1);
+	gpiod_set_value(jadard->reset, 0);
 	msleep(130);
 
 	ret = jadard->desc->init(jadard);
@@ -129,11 +129,11 @@ static int jadard_unprepare(struct drm_panel *panel)
 {
 	struct jadard *jadard = panel_to_jadard(panel);
 
-	gpiod_set_value(jadard->reset, 1);
+	gpiod_set_value(jadard->reset, 0);
 	msleep(120);
 
 	if (jadard->desc->reset_before_power_off_vcioo) {
-		gpiod_set_value(jadard->reset, 0);
+		gpiod_set_value(jadard->reset, 1);
 
 		usleep_range(1000, 2000);
 	}
@@ -1130,7 +1130,7 @@ static int jadard_dsi_probe(struct mipi_dsi_device *dsi)
 	dsi->format = desc->format;
 	dsi->lanes = desc->lanes;
 
-	jadard->reset = devm_gpiod_get(dev, "reset", GPIOD_OUT_LOW);
+	jadard->reset = devm_gpiod_get(dev, "reset", GPIOD_OUT_HIGH);
 	if (IS_ERR(jadard->reset)) {
 		DRM_DEV_ERROR(&dsi->dev, "failed to get our reset GPIO\n");
 		return PTR_ERR(jadard->reset);
diff --git a/drivers/gpu/drm/panel/panel-samsung-sofef00.c b/drivers/gpu/drm/panel/panel-samsung-sofef00.c
index 04ce925b3d9d..49cfa84b34f0 100644
--- a/drivers/gpu/drm/panel/panel-samsung-sofef00.c
+++ b/drivers/gpu/drm/panel/panel-samsung-sofef00.c
@@ -22,7 +22,6 @@ struct sofef00_panel {
 	struct mipi_dsi_device *dsi;
 	struct regulator *supply;
 	struct gpio_desc *reset_gpio;
-	const struct drm_display_mode *mode;
 };
 
 static inline
@@ -159,26 +158,11 @@ static const struct drm_display_mode enchilada_panel_mode = {
 	.height_mm = 145,
 };
 
-static const struct drm_display_mode fajita_panel_mode = {
-	.clock = (1080 + 72 + 16 + 36) * (2340 + 32 + 4 + 18) * 60 / 1000,
-	.hdisplay = 1080,
-	.hsync_start = 1080 + 72,
-	.hsync_end = 1080 + 72 + 16,
-	.htotal = 1080 + 72 + 16 + 36,
-	.vdisplay = 2340,
-	.vsync_start = 2340 + 32,
-	.vsync_end = 2340 + 32 + 4,
-	.vtotal = 2340 + 32 + 4 + 18,
-	.width_mm = 68,
-	.height_mm = 145,
-};
-
 static int sofef00_panel_get_modes(struct drm_panel *panel, struct drm_connector *connector)
 {
 	struct drm_display_mode *mode;
-	struct sofef00_panel *ctx = to_sofef00_panel(panel);
 
-	mode = drm_mode_duplicate(connector->dev, ctx->mode);
+	mode = drm_mode_duplicate(connector->dev, &enchilada_panel_mode);
 	if (!mode)
 		return -ENOMEM;
 
@@ -239,13 +223,6 @@ static int sofef00_panel_probe(struct mipi_dsi_device *dsi)
 	if (!ctx)
 		return -ENOMEM;
 
-	ctx->mode = of_device_get_match_data(dev);
-
-	if (!ctx->mode) {
-		dev_err(dev, "Missing device mode\n");
-		return -ENODEV;
-	}
-
 	ctx->supply = devm_regulator_get(dev, "vddio");
 	if (IS_ERR(ctx->supply))
 		return dev_err_probe(dev, PTR_ERR(ctx->supply),
@@ -295,14 +272,7 @@ static void sofef00_panel_remove(struct mipi_dsi_device *dsi)
 }
 
 static const struct of_device_id sofef00_panel_of_match[] = {
-	{ // OnePlus 6 / enchilada
-		.compatible = "samsung,sofef00",
-		.data = &enchilada_panel_mode,
-	},
-	{ // OnePlus 6T / fajita
-		.compatible = "samsung,s6e3fc2x01",
-		.data = &fajita_panel_mode,
-	},
+	{ .compatible = "samsung,sofef00" },
 	{ /* sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, sofef00_panel_of_match);
diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c
index 06381c628209..82db3daf4f81 100644
--- a/drivers/gpu/drm/panel/panel-simple.c
+++ b/drivers/gpu/drm/panel/panel-simple.c
@@ -1027,27 +1027,28 @@ static const struct panel_desc auo_g070vvn01 = {
 	},
 };
 
-static const struct drm_display_mode auo_g101evn010_mode = {
-	.clock = 68930,
-	.hdisplay = 1280,
-	.hsync_start = 1280 + 82,
-	.hsync_end = 1280 + 82 + 2,
-	.htotal = 1280 + 82 + 2 + 84,
-	.vdisplay = 800,
-	.vsync_start = 800 + 8,
-	.vsync_end = 800 + 8 + 2,
-	.vtotal = 800 + 8 + 2 + 6,
+static const struct display_timing auo_g101evn010_timing = {
+	.pixelclock = { 64000000, 68930000, 85000000 },
+	.hactive = { 1280, 1280, 1280 },
+	.hfront_porch = { 8, 64, 256 },
+	.hback_porch = { 8, 64, 256 },
+	.hsync_len = { 40, 168, 767 },
+	.vactive = { 800, 800, 800 },
+	.vfront_porch = { 4, 8, 100 },
+	.vback_porch = { 4, 8, 100 },
+	.vsync_len = { 8, 16, 223 },
 };
 
 static const struct panel_desc auo_g101evn010 = {
-	.modes = &auo_g101evn010_mode,
-	.num_modes = 1,
+	.timings = &auo_g101evn010_timing,
+	.num_timings = 1,
 	.bpc = 6,
 	.size = {
 		.width = 216,
 		.height = 135,
 	},
 	.bus_format = MEDIA_BUS_FMT_RGB666_1X7X3_SPWG,
+	.bus_flags = DRM_BUS_FLAG_DE_HIGH,
 	.connector_type = DRM_MODE_CONNECTOR_LVDS,
 };
 
@@ -2140,13 +2141,14 @@ static const struct display_timing evervision_vgg644804_timing = {
 static const struct panel_desc evervision_vgg644804 = {
 	.timings = &evervision_vgg644804_timing,
 	.num_timings = 1,
-	.bpc = 8,
+	.bpc = 6,
 	.size = {
 		.width = 115,
 		.height = 86,
 	},
 	.bus_format = MEDIA_BUS_FMT_RGB666_1X7X3_SPWG,
-	.bus_flags = DRM_BUS_FLAG_DE_HIGH | DRM_BUS_FLAG_PIXDATA_SAMPLE_NEGEDGE,
+	.bus_flags = DRM_BUS_FLAG_DE_HIGH,
+	.connector_type = DRM_MODE_CONNECTOR_LVDS,
 };
 
 static const struct display_timing evervision_vgg804821_timing = {
diff --git a/drivers/gpu/drm/panfrost/panfrost_devfreq.c b/drivers/gpu/drm/panfrost/panfrost_devfreq.c
index 3385fd3ef41a..5d0dce10336b 100644
--- a/drivers/gpu/drm/panfrost/panfrost_devfreq.c
+++ b/drivers/gpu/drm/panfrost/panfrost_devfreq.c
@@ -29,7 +29,7 @@ static void panfrost_devfreq_update_utilization(struct panfrost_devfreq *pfdevfr
 static int panfrost_devfreq_target(struct device *dev, unsigned long *freq,
 				   u32 flags)
 {
-	struct panfrost_device *ptdev = dev_get_drvdata(dev);
+	struct panfrost_device *pfdev = dev_get_drvdata(dev);
 	struct dev_pm_opp *opp;
 	int err;
 
@@ -40,7 +40,7 @@ static int panfrost_devfreq_target(struct device *dev, unsigned long *freq,
 
 	err = dev_pm_opp_set_rate(dev, *freq);
 	if (!err)
-		ptdev->pfdevfreq.current_frequency = *freq;
+		pfdev->pfdevfreq.current_frequency = *freq;
 
 	return err;
 }
diff --git a/drivers/gpu/drm/panthor/panthor_device.c b/drivers/gpu/drm/panthor/panthor_device.c
index 6fbff516c1c1..01dff89bed4e 100644
--- a/drivers/gpu/drm/panthor/panthor_device.c
+++ b/drivers/gpu/drm/panthor/panthor_device.c
@@ -445,8 +445,8 @@ int panthor_device_resume(struct device *dev)
 	    drm_dev_enter(&ptdev->base, &cookie)) {
 		panthor_gpu_resume(ptdev);
 		panthor_mmu_resume(ptdev);
-		ret = drm_WARN_ON(&ptdev->base, panthor_fw_resume(ptdev));
-		if (!ret) {
+		ret = panthor_fw_resume(ptdev);
+		if (!drm_WARN_ON(&ptdev->base, ret)) {
 			panthor_sched_resume(ptdev);
 		} else {
 			panthor_mmu_suspend(ptdev);
diff --git a/drivers/gpu/drm/panthor/panthor_fw.h b/drivers/gpu/drm/panthor/panthor_fw.h
index 22448abde992..6598d96c6d2a 100644
--- a/drivers/gpu/drm/panthor/panthor_fw.h
+++ b/drivers/gpu/drm/panthor/panthor_fw.h
@@ -102,9 +102,9 @@ struct panthor_fw_cs_output_iface {
 #define CS_STATUS_BLOCKED_REASON_SB_WAIT	1
 #define CS_STATUS_BLOCKED_REASON_PROGRESS_WAIT	2
 #define CS_STATUS_BLOCKED_REASON_SYNC_WAIT	3
-#define CS_STATUS_BLOCKED_REASON_DEFERRED	5
-#define CS_STATUS_BLOCKED_REASON_RES		6
-#define CS_STATUS_BLOCKED_REASON_FLUSH		7
+#define CS_STATUS_BLOCKED_REASON_DEFERRED	4
+#define CS_STATUS_BLOCKED_REASON_RESOURCE	5
+#define CS_STATUS_BLOCKED_REASON_FLUSH		6
 #define CS_STATUS_BLOCKED_REASON_MASK		GENMASK(3, 0)
 	u32 status_blocked_reason;
 	u32 status_wait_sync_value_hi;
diff --git a/drivers/gpu/drm/panthor/panthor_mmu.c b/drivers/gpu/drm/panthor/panthor_mmu.c
index 0e6f94df690d..b57824abeb9e 100644
--- a/drivers/gpu/drm/panthor/panthor_mmu.c
+++ b/drivers/gpu/drm/panthor/panthor_mmu.c
@@ -780,6 +780,7 @@ out_enable_as:
 	if (ptdev->mmu->as.faulty_mask & panthor_mmu_as_fault_mask(ptdev, as)) {
 		gpu_write(ptdev, MMU_INT_CLEAR, panthor_mmu_as_fault_mask(ptdev, as));
 		ptdev->mmu->as.faulty_mask &= ~panthor_mmu_as_fault_mask(ptdev, as);
+		ptdev->mmu->irq.mask |= panthor_mmu_as_fault_mask(ptdev, as);
 		gpu_write(ptdev, MMU_INT_MASK, ~ptdev->mmu->as.faulty_mask);
 	}
 
diff --git a/drivers/gpu/drm/panthor/panthor_regs.h b/drivers/gpu/drm/panthor/panthor_regs.h
index b7b3b3add166..a7a323dc5cf9 100644
--- a/drivers/gpu/drm/panthor/panthor_regs.h
+++ b/drivers/gpu/drm/panthor/panthor_regs.h
@@ -133,8 +133,8 @@
 #define GPU_COHERENCY_PROT_BIT(name)			BIT(GPU_COHERENCY_  ## name)
 
 #define GPU_COHERENCY_PROTOCOL				0x304
-#define   GPU_COHERENCY_ACE				0
-#define   GPU_COHERENCY_ACE_LITE			1
+#define   GPU_COHERENCY_ACE_LITE			0
+#define   GPU_COHERENCY_ACE				1
 #define   GPU_COHERENCY_NONE				31
 
 #define MCU_CONTROL					0x700
diff --git a/drivers/gpu/drm/radeon/r300.c b/drivers/gpu/drm/radeon/r300.c
index 05c13102a8cb..d22889fbfa9c 100644
--- a/drivers/gpu/drm/radeon/r300.c
+++ b/drivers/gpu/drm/radeon/r300.c
@@ -359,7 +359,8 @@ int r300_mc_wait_for_idle(struct radeon_device *rdev)
 	return -1;
 }
 
-static void r300_gpu_init(struct radeon_device *rdev)
+/* rs400_gpu_init also calls this! */
+void r300_gpu_init(struct radeon_device *rdev)
 {
 	uint32_t gb_tile_config, tmp;
 
diff --git a/drivers/gpu/drm/radeon/radeon_asic.h b/drivers/gpu/drm/radeon/radeon_asic.h
index 1e00f6b99f94..8f5e07834fcc 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.h
+++ b/drivers/gpu/drm/radeon/radeon_asic.h
@@ -165,6 +165,7 @@ void r200_set_safe_registers(struct radeon_device *rdev);
  */
 extern int r300_init(struct radeon_device *rdev);
 extern void r300_fini(struct radeon_device *rdev);
+extern void r300_gpu_init(struct radeon_device *rdev);
 extern int r300_suspend(struct radeon_device *rdev);
 extern int r300_resume(struct radeon_device *rdev);
 extern int r300_asic_reset(struct radeon_device *rdev, bool hard);
diff --git a/drivers/gpu/drm/radeon/radeon_audio.c b/drivers/gpu/drm/radeon/radeon_audio.c
index 5b69cc8011b4..8d64ba18572e 100644
--- a/drivers/gpu/drm/radeon/radeon_audio.c
+++ b/drivers/gpu/drm/radeon/radeon_audio.c
@@ -775,8 +775,10 @@ static int radeon_audio_component_get_eld(struct device *kdev, int port,
 		if (!dig->pin || dig->pin->id != port)
 			continue;
 		*enabled = true;
+		mutex_lock(&connector->eld_mutex);
 		ret = drm_eld_size(connector->eld);
 		memcpy(buf, connector->eld, min(max_bytes, ret));
+		mutex_unlock(&connector->eld_mutex);
 		break;
 	}
 
diff --git a/drivers/gpu/drm/radeon/radeon_vce.c b/drivers/gpu/drm/radeon/radeon_vce.c
index d1871af967d4..2355a78e1b69 100644
--- a/drivers/gpu/drm/radeon/radeon_vce.c
+++ b/drivers/gpu/drm/radeon/radeon_vce.c
@@ -557,7 +557,7 @@ int radeon_vce_cs_parse(struct radeon_cs_parser *p)
 {
 	int session_idx = -1;
 	bool destroyed = false, created = false, allocated = false;
-	uint32_t tmp, handle = 0;
+	uint32_t tmp = 0, handle = 0;
 	uint32_t *size = &tmp;
 	int i, r = 0;
 
diff --git a/drivers/gpu/drm/radeon/rs400.c b/drivers/gpu/drm/radeon/rs400.c
index d6c18fd740ec..13cd0a688a65 100644
--- a/drivers/gpu/drm/radeon/rs400.c
+++ b/drivers/gpu/drm/radeon/rs400.c
@@ -256,8 +256,22 @@ int rs400_mc_wait_for_idle(struct radeon_device *rdev)
 
 static void rs400_gpu_init(struct radeon_device *rdev)
 {
-	/* FIXME: is this correct ? */
-	r420_pipes_init(rdev);
+	/* Earlier code was calling r420_pipes_init and then
+	 * rs400_mc_wait_for_idle(rdev). The problem is that
+	 * at least on my Mobility Radeon Xpress 200M RC410 card
+	 * that ends up in this code path ends up num_gb_pipes == 3
+	 * while the card seems to have only one pipe. With the
+	 * r420 pipe initialization method.
+	 *
+	 * Problems shown up as HyperZ glitches, see:
+	 * https://bugs.freedesktop.org/show_bug.cgi?id=110897
+	 *
+	 * Delegating initialization to r300 code seems to work
+	 * and results in proper pipe numbers. The rs400 cards
+	 * are said to be not r400, but r300 kind of cards.
+	 */
+	r300_gpu_init(rdev);
+
 	if (rs400_mc_wait_for_idle(rdev)) {
 		pr_warn("rs400: Failed to wait MC idle while programming pipes. Bad things might happen. %08x\n",
 			RREG32(RADEON_MC_STATUS));
diff --git a/drivers/gpu/drm/renesas/rcar-du/rcar_du_kms.c b/drivers/gpu/drm/renesas/rcar-du/rcar_du_kms.c
index 70d8ad065bfa..4c8fe83dd610 100644
--- a/drivers/gpu/drm/renesas/rcar-du/rcar_du_kms.c
+++ b/drivers/gpu/drm/renesas/rcar-du/rcar_du_kms.c
@@ -705,7 +705,7 @@ static int rcar_du_vsps_init(struct rcar_du_device *rcdu)
 		ret = of_parse_phandle_with_fixed_args(np, vsps_prop_name,
 						       cells, i, &args);
 		if (ret < 0)
-			goto error;
+			goto done;
 
 		/*
 		 * Add the VSP to the list or update the corresponding existing
@@ -743,13 +743,11 @@ static int rcar_du_vsps_init(struct rcar_du_device *rcdu)
 		vsp->dev = rcdu;
 
 		ret = rcar_du_vsp_init(vsp, vsps[i].np, vsps[i].crtcs_mask);
-		if (ret < 0)
-			goto error;
+		if (ret)
+			goto done;
 	}
 
-	return 0;
-
-error:
+done:
 	for (i = 0; i < ARRAY_SIZE(vsps); ++i)
 		of_node_put(vsps[i].np);
 
diff --git a/drivers/gpu/drm/renesas/rcar-du/rcar_mipi_dsi.c b/drivers/gpu/drm/renesas/rcar-du/rcar_mipi_dsi.c
index 2dba7c5ffd2c..92f4261305bd 100644
--- a/drivers/gpu/drm/renesas/rcar-du/rcar_mipi_dsi.c
+++ b/drivers/gpu/drm/renesas/rcar-du/rcar_mipi_dsi.c
@@ -587,7 +587,7 @@ static int rcar_mipi_dsi_startup(struct rcar_mipi_dsi *dsi,
 	for (timeout = 10; timeout > 0; --timeout) {
 		if ((rcar_mipi_dsi_read(dsi, PPICLSR) & PPICLSR_STPST) &&
 		    (rcar_mipi_dsi_read(dsi, PPIDLSR) & PPIDLSR_STPST) &&
-		    (rcar_mipi_dsi_read(dsi, CLOCKSET1) & CLOCKSET1_LOCK))
+		    (rcar_mipi_dsi_read(dsi, CLOCKSET1) & CLOCKSET1_LOCK_PHY))
 			break;
 
 		usleep_range(1000, 2000);
diff --git a/drivers/gpu/drm/renesas/rcar-du/rcar_mipi_dsi_regs.h b/drivers/gpu/drm/renesas/rcar-du/rcar_mipi_dsi_regs.h
index f8114d11f2d1..a6b276f1d6ee 100644
--- a/drivers/gpu/drm/renesas/rcar-du/rcar_mipi_dsi_regs.h
+++ b/drivers/gpu/drm/renesas/rcar-du/rcar_mipi_dsi_regs.h
@@ -142,7 +142,6 @@
 
 #define CLOCKSET1			0x101c
 #define CLOCKSET1_LOCK_PHY		(1 << 17)
-#define CLOCKSET1_LOCK			(1 << 16)
 #define CLOCKSET1_CLKSEL		(1 << 8)
 #define CLOCKSET1_CLKINSEL_EXTAL	(0 << 2)
 #define CLOCKSET1_CLKINSEL_DIG		(1 << 2)
diff --git a/drivers/gpu/drm/renesas/rz-du/rzg2l_du_kms.c b/drivers/gpu/drm/renesas/rz-du/rzg2l_du_kms.c
index b99217b4e05d..90c6269ccd29 100644
--- a/drivers/gpu/drm/renesas/rz-du/rzg2l_du_kms.c
+++ b/drivers/gpu/drm/renesas/rz-du/rzg2l_du_kms.c
@@ -311,11 +311,11 @@ int rzg2l_du_modeset_init(struct rzg2l_du_device *rcdu)
 	dev->mode_config.helper_private = &rzg2l_du_mode_config_helper;
 
 	/*
-	 * The RZ DU uses the VSP1 for memory access, and is limited
-	 * to frame sizes of 1920x1080.
+	 * The RZ DU was designed to support a frame size of 1920x1200 (landscape)
+	 * or 1200x1920 (portrait).
 	 */
 	dev->mode_config.max_width = 1920;
-	dev->mode_config.max_height = 1080;
+	dev->mode_config.max_height = 1920;
 
 	rcdu->num_crtcs = hweight8(rcdu->info->channels_mask);
 
diff --git a/drivers/gpu/drm/renesas/rz-du/rzg2l_mipi_dsi.c b/drivers/gpu/drm/renesas/rz-du/rzg2l_mipi_dsi.c
index 10febea473cd..6cec796dd463 100644
--- a/drivers/gpu/drm/renesas/rz-du/rzg2l_mipi_dsi.c
+++ b/drivers/gpu/drm/renesas/rz-du/rzg2l_mipi_dsi.c
@@ -585,6 +585,9 @@ rzg2l_mipi_dsi_bridge_mode_valid(struct drm_bridge *bridge,
 	if (mode->clock > 148500)
 		return MODE_CLOCK_HIGH;
 
+	if (mode->clock < 5803)
+		return MODE_CLOCK_LOW;
+
 	return MODE_OK;
 }
 
diff --git a/drivers/gpu/drm/rockchip/cdn-dp-core.c b/drivers/gpu/drm/rockchip/cdn-dp-core.c
index b04538907f95..f576b1aa86d1 100644
--- a/drivers/gpu/drm/rockchip/cdn-dp-core.c
+++ b/drivers/gpu/drm/rockchip/cdn-dp-core.c
@@ -947,9 +947,6 @@ static void cdn_dp_pd_event_work(struct work_struct *work)
 {
 	struct cdn_dp_device *dp = container_of(work, struct cdn_dp_device,
 						event_work);
-	struct drm_connector *connector = &dp->connector;
-	enum drm_connector_status old_status;
-
 	int ret;
 
 	mutex_lock(&dp->lock);
@@ -1009,11 +1006,7 @@ static void cdn_dp_pd_event_work(struct work_struct *work)
 
 out:
 	mutex_unlock(&dp->lock);
-
-	old_status = connector->status;
-	connector->status = connector->funcs->detect(connector, false);
-	if (old_status != connector->status)
-		drm_kms_helper_hotplug_event(dp->drm_dev);
+	drm_connector_helper_hpd_irq_event(&dp->connector);
 }
 
 static int cdn_dp_pd_event(struct notifier_block *nb,
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c
index cfe8b793d344..69ab8d4f289c 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c
@@ -52,16 +52,9 @@ rockchip_fb_create(struct drm_device *dev, struct drm_file *file,
 	}
 
 	if (drm_is_afbc(mode_cmd->modifier[0])) {
-		int ret, i;
-
 		ret = drm_gem_fb_afbc_init(dev, mode_cmd, afbc_fb);
 		if (ret) {
-			struct drm_gem_object **obj = afbc_fb->base.obj;
-
-			for (i = 0; i < info->num_planes; ++i)
-				drm_gem_object_put(obj[i]);
-
-			kfree(afbc_fb);
+			drm_framebuffer_put(&afbc_fb->base);
 			return ERR_PTR(ret);
 		}
 	}
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c
index 9873172e3fd3..5d7df4c3b08c 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c
@@ -33,7 +33,6 @@
 #include <uapi/linux/videodev2.h>
 #include <dt-bindings/soc/rockchip,vop2.h>
 
-#include "rockchip_drm_drv.h"
 #include "rockchip_drm_gem.h"
 #include "rockchip_drm_vop2.h"
 #include "rockchip_rgb.h"
@@ -158,6 +157,7 @@ struct vop2_video_port {
 	struct drm_crtc crtc;
 	struct vop2 *vop2;
 	struct clk *dclk;
+	struct clk *dclk_src;
 	unsigned int id;
 	const struct vop2_video_port_data *data;
 
@@ -212,6 +212,7 @@ struct vop2 {
 	struct clk *hclk;
 	struct clk *aclk;
 	struct clk *pclk;
+	struct clk *pll_hdmiphy0;
 
 	/* optional internal rgb encoder */
 	struct rockchip_rgb *rgb;
@@ -220,6 +221,8 @@ struct vop2 {
 	struct vop2_win win[];
 };
 
+#define VOP2_MAX_DCLK_RATE		600000000
+
 #define vop2_output_if_is_hdmi(x)	((x) == ROCKCHIP_VOP2_EP_HDMI0 || \
 					 (x) == ROCKCHIP_VOP2_EP_HDMI1)
 
@@ -550,6 +553,25 @@ static bool rockchip_vop2_mod_supported(struct drm_plane *plane, u32 format,
 	if (modifier == DRM_FORMAT_MOD_INVALID)
 		return false;
 
+	if (vop2->data->soc_id == 3568 || vop2->data->soc_id == 3566) {
+		if (vop2_cluster_window(win)) {
+			if (modifier == DRM_FORMAT_MOD_LINEAR) {
+				drm_dbg_kms(vop2->drm,
+					    "Cluster window only supports format with afbc\n");
+				return false;
+			}
+		}
+	}
+
+	if (format == DRM_FORMAT_XRGB2101010 || format == DRM_FORMAT_XBGR2101010) {
+		if (vop2->data->soc_id == 3588) {
+			if (!rockchip_afbc(plane, modifier)) {
+				drm_dbg_kms(vop2->drm, "Only support 32 bpp format with afbc\n");
+				return false;
+			}
+		}
+	}
+
 	if (modifier == DRM_FORMAT_MOD_LINEAR)
 		return true;
 
@@ -1033,6 +1055,9 @@ static void vop2_crtc_atomic_disable(struct drm_crtc *crtc,
 
 	vop2_crtc_disable_irq(vp, VP_INT_DSP_HOLD_VALID);
 
+	if (vp->dclk_src)
+		clk_set_parent(vp->dclk, vp->dclk_src);
+
 	clk_disable_unprepare(vp->dclk);
 
 	vop2->enable_count--;
@@ -1320,6 +1345,12 @@ static void vop2_plane_atomic_update(struct drm_plane *plane,
 		&fb->format->format,
 		afbc_en ? "AFBC" : "", &yrgb_mst);
 
+	if (vop2->data->soc_id > 3568) {
+		vop2_win_write(win, VOP2_WIN_AXI_BUS_ID, win->data->axi_bus_id);
+		vop2_win_write(win, VOP2_WIN_AXI_YRGB_R_ID, win->data->axi_yrgb_r_id);
+		vop2_win_write(win, VOP2_WIN_AXI_UV_R_ID, win->data->axi_uv_r_id);
+	}
+
 	if (vop2_cluster_window(win))
 		vop2_win_write(win, VOP2_WIN_AFBC_HALF_BLOCK_EN, half_block_en);
 
@@ -1408,10 +1439,8 @@ static void vop2_plane_atomic_update(struct drm_plane *plane,
 
 	rb_swap = vop2_win_rb_swap(fb->format->format);
 	vop2_win_write(win, VOP2_WIN_RB_SWAP, rb_swap);
-	if (!vop2_cluster_window(win)) {
-		uv_swap = vop2_win_uv_swap(fb->format->format);
-		vop2_win_write(win, VOP2_WIN_UV_SWAP, uv_swap);
-	}
+	uv_swap = vop2_win_uv_swap(fb->format->format);
+	vop2_win_write(win, VOP2_WIN_UV_SWAP, uv_swap);
 
 	if (fb->format->is_yuv) {
 		vop2_win_write(win, VOP2_WIN_UV_VIR, DIV_ROUND_UP(fb->pitches[1], 4));
@@ -1721,9 +1750,9 @@ static unsigned long rk3588_calc_cru_cfg(struct vop2_video_port *vp, int id,
 		else
 			dclk_out_rate = v_pixclk >> 2;
 
-		dclk_rate = rk3588_calc_dclk(dclk_out_rate, 600000);
+		dclk_rate = rk3588_calc_dclk(dclk_out_rate, 600000000);
 		if (!dclk_rate) {
-			drm_err(vop2->drm, "DP dclk_out_rate out of range, dclk_out_rate: %ld KHZ\n",
+			drm_err(vop2->drm, "DP dclk_out_rate out of range, dclk_out_rate: %ld Hz\n",
 				dclk_out_rate);
 			return 0;
 		}
@@ -1738,9 +1767,9 @@ static unsigned long rk3588_calc_cru_cfg(struct vop2_video_port *vp, int id,
 		 * dclk_rate = N * dclk_core_rate N = (1,2,4 ),
 		 * we get a little factor here
 		 */
-		dclk_rate = rk3588_calc_dclk(dclk_out_rate, 600000);
+		dclk_rate = rk3588_calc_dclk(dclk_out_rate, 600000000);
 		if (!dclk_rate) {
-			drm_err(vop2->drm, "MIPI dclk out of range, dclk_out_rate: %ld KHZ\n",
+			drm_err(vop2->drm, "MIPI dclk out of range, dclk_out_rate: %ld Hz\n",
 				dclk_out_rate);
 			return 0;
 		}
@@ -2049,6 +2078,27 @@ static void vop2_crtc_atomic_enable(struct drm_crtc *crtc,
 
 	vop2_vp_write(vp, RK3568_VP_MIPI_CTRL, 0);
 
+	/*
+	 * Switch to HDMI PHY PLL as DCLK source for display modes up
+	 * to 4K@60Hz, if available, otherwise keep using the system CRU.
+	 */
+	if (vop2->pll_hdmiphy0 && clock <= VOP2_MAX_DCLK_RATE) {
+		drm_for_each_encoder_mask(encoder, crtc->dev, crtc_state->encoder_mask) {
+			struct rockchip_encoder *rkencoder = to_rockchip_encoder(encoder);
+
+			if (rkencoder->crtc_endpoint_id == ROCKCHIP_VOP2_EP_HDMI0) {
+				if (!vp->dclk_src)
+					vp->dclk_src = clk_get_parent(vp->dclk);
+
+				ret = clk_set_parent(vp->dclk, vop2->pll_hdmiphy0);
+				if (ret < 0)
+					drm_warn(vop2->drm,
+						 "Could not switch to HDMI0 PHY PLL: %d\n", ret);
+				break;
+			}
+		}
+	}
+
 	clk_set_rate(vp->dclk, clock);
 
 	vop2_post_config(crtc);
@@ -2159,7 +2209,6 @@ static int vop2_find_start_mixer_id_for_vp(struct vop2 *vop2, u8 port_id)
 
 static void vop2_setup_cluster_alpha(struct vop2 *vop2, struct vop2_win *main_win)
 {
-	u32 offset = (main_win->data->phys_id * 0x10);
 	struct vop2_alpha_config alpha_config;
 	struct vop2_alpha alpha;
 	struct drm_plane_state *bottom_win_pstate;
@@ -2167,6 +2216,7 @@ static void vop2_setup_cluster_alpha(struct vop2 *vop2, struct vop2_win *main_wi
 	u16 src_glb_alpha_val, dst_glb_alpha_val;
 	bool premulti_en = false;
 	bool swap = false;
+	u32 offset = 0;
 
 	/* At one win mode, win0 is dst/bottom win, and win1 is a all zero src/top win */
 	bottom_win_pstate = main_win->base.state;
@@ -2185,6 +2235,22 @@ static void vop2_setup_cluster_alpha(struct vop2 *vop2, struct vop2_win *main_wi
 	vop2_parse_alpha(&alpha_config, &alpha);
 
 	alpha.src_color_ctrl.bits.src_dst_swap = swap;
+
+	switch (main_win->data->phys_id) {
+	case ROCKCHIP_VOP2_CLUSTER0:
+		offset = 0x0;
+		break;
+	case ROCKCHIP_VOP2_CLUSTER1:
+		offset = 0x10;
+		break;
+	case ROCKCHIP_VOP2_CLUSTER2:
+		offset = 0x20;
+		break;
+	case ROCKCHIP_VOP2_CLUSTER3:
+		offset = 0x30;
+		break;
+	}
+
 	vop2_writel(vop2, RK3568_CLUSTER0_MIX_SRC_COLOR_CTRL + offset,
 		    alpha.src_color_ctrl.val);
 	vop2_writel(vop2, RK3568_CLUSTER0_MIX_DST_COLOR_CTRL + offset,
@@ -2232,6 +2298,12 @@ static void vop2_setup_alpha(struct vop2_video_port *vp)
 		struct vop2_win *win = to_vop2_win(plane);
 		int zpos = plane->state->normalized_zpos;
 
+		/*
+		 * Need to configure alpha from second layer.
+		 */
+		if (zpos == 0)
+			continue;
+
 		if (plane->state->pixel_blend_mode == DRM_MODE_BLEND_PREMULTI)
 			premulti_en = 1;
 		else
@@ -2308,7 +2380,10 @@ static void vop2_setup_layer_mixer(struct vop2_video_port *vp)
 	struct drm_plane *plane;
 	u32 layer_sel = 0;
 	u32 port_sel;
-	unsigned int nlayer, ofs;
+	u8 layer_id;
+	u8 old_layer_id;
+	u8 layer_sel_id;
+	unsigned int ofs;
 	u32 ovl_ctrl;
 	int i;
 	struct vop2_video_port *vp0 = &vop2->vps[0];
@@ -2352,9 +2427,30 @@ static void vop2_setup_layer_mixer(struct vop2_video_port *vp)
 	for (i = 0; i < vp->id; i++)
 		ofs += vop2->vps[i].nlayers;
 
-	nlayer = 0;
 	drm_atomic_crtc_for_each_plane(plane, &vp->crtc) {
 		struct vop2_win *win = to_vop2_win(plane);
+		struct vop2_win *old_win;
+
+		layer_id = (u8)(plane->state->normalized_zpos + ofs);
+
+		/*
+		 * Find the layer this win bind in old state.
+		 */
+		for (old_layer_id = 0; old_layer_id < vop2->data->win_size; old_layer_id++) {
+			layer_sel_id = (layer_sel >> (4 * old_layer_id)) & 0xf;
+			if (layer_sel_id == win->data->layer_sel_id)
+				break;
+		}
+
+		/*
+		 * Find the win bind to this layer in old state
+		 */
+		for (i = 0; i < vop2->data->win_size; i++) {
+			old_win = &vop2->win[i];
+			layer_sel_id = (layer_sel >> (4 * layer_id)) & 0xf;
+			if (layer_sel_id == old_win->data->layer_sel_id)
+				break;
+		}
 
 		switch (win->data->phys_id) {
 		case ROCKCHIP_VOP2_CLUSTER0:
@@ -2399,17 +2495,14 @@ static void vop2_setup_layer_mixer(struct vop2_video_port *vp)
 			break;
 		}
 
-		layer_sel &= ~RK3568_OVL_LAYER_SEL__LAYER(plane->state->normalized_zpos + ofs,
-							  0x7);
-		layer_sel |= RK3568_OVL_LAYER_SEL__LAYER(plane->state->normalized_zpos + ofs,
-							 win->data->layer_sel_id);
-		nlayer++;
-	}
-
-	/* configure unused layers to 0x5 (reserved) */
-	for (; nlayer < vp->nlayers; nlayer++) {
-		layer_sel &= ~RK3568_OVL_LAYER_SEL__LAYER(nlayer + ofs, 0x7);
-		layer_sel |= RK3568_OVL_LAYER_SEL__LAYER(nlayer + ofs, 5);
+		layer_sel &= ~RK3568_OVL_LAYER_SEL__LAYER(layer_id, 0x7);
+		layer_sel |= RK3568_OVL_LAYER_SEL__LAYER(layer_id, win->data->layer_sel_id);
+		/*
+		 * When we bind a window from layerM to layerN, we also need to move the old
+		 * window on layerN to layerM to avoid one window selected by two or more layers.
+		 */
+		layer_sel &= ~RK3568_OVL_LAYER_SEL__LAYER(old_layer_id, 0x7);
+		layer_sel |= RK3568_OVL_LAYER_SEL__LAYER(old_layer_id, old_win->data->layer_sel_id);
 	}
 
 	vop2_writel(vop2, RK3568_OVL_LAYER_SEL, layer_sel);
@@ -2444,9 +2537,11 @@ static void vop2_setup_dly_for_windows(struct vop2 *vop2)
 			sdly |= FIELD_PREP(RK3568_SMART_DLY_NUM__ESMART1, dly);
 			break;
 		case ROCKCHIP_VOP2_SMART0:
+		case ROCKCHIP_VOP2_ESMART2:
 			sdly |= FIELD_PREP(RK3568_SMART_DLY_NUM__SMART0, dly);
 			break;
 		case ROCKCHIP_VOP2_SMART1:
+		case ROCKCHIP_VOP2_ESMART3:
 			sdly |= FIELD_PREP(RK3568_SMART_DLY_NUM__SMART1, dly);
 			break;
 		}
@@ -2865,6 +2960,10 @@ static struct reg_field vop2_cluster_regs[VOP2_WIN_MAX_REG] = {
 	[VOP2_WIN_Y2R_EN] = REG_FIELD(RK3568_CLUSTER_WIN_CTRL0, 8, 8),
 	[VOP2_WIN_R2Y_EN] = REG_FIELD(RK3568_CLUSTER_WIN_CTRL0, 9, 9),
 	[VOP2_WIN_CSC_MODE] = REG_FIELD(RK3568_CLUSTER_WIN_CTRL0, 10, 11),
+	[VOP2_WIN_AXI_YRGB_R_ID] = REG_FIELD(RK3568_CLUSTER_WIN_CTRL2, 0, 3),
+	[VOP2_WIN_AXI_UV_R_ID] = REG_FIELD(RK3568_CLUSTER_WIN_CTRL2, 5, 8),
+	/* RK3588 only, reserved bit on rk3568*/
+	[VOP2_WIN_AXI_BUS_ID] = REG_FIELD(RK3568_CLUSTER_CTRL, 13, 13),
 
 	/* Scale */
 	[VOP2_WIN_SCALE_YRGB_X] = REG_FIELD(RK3568_CLUSTER_WIN_SCL_FACTOR_YRGB, 0, 15),
@@ -2957,6 +3056,10 @@ static struct reg_field vop2_esmart_regs[VOP2_WIN_MAX_REG] = {
 	[VOP2_WIN_YMIRROR] = REG_FIELD(RK3568_SMART_CTRL1, 31, 31),
 	[VOP2_WIN_COLOR_KEY] = REG_FIELD(RK3568_SMART_COLOR_KEY_CTRL, 0, 29),
 	[VOP2_WIN_COLOR_KEY_EN] = REG_FIELD(RK3568_SMART_COLOR_KEY_CTRL, 31, 31),
+	[VOP2_WIN_AXI_YRGB_R_ID] = REG_FIELD(RK3568_SMART_CTRL1, 4, 8),
+	[VOP2_WIN_AXI_UV_R_ID] = REG_FIELD(RK3568_SMART_CTRL1, 12, 16),
+	/* RK3588 only, reserved register on rk3568 */
+	[VOP2_WIN_AXI_BUS_ID] = REG_FIELD(RK3588_SMART_AXI_CTRL, 1, 1),
 
 	/* Scale */
 	[VOP2_WIN_SCALE_YRGB_X] = REG_FIELD(RK3568_SMART_REGION0_SCL_FACTOR_YRGB, 0, 15),
@@ -3167,6 +3270,12 @@ static int vop2_bind(struct device *dev, struct device *master, void *data)
 		return PTR_ERR(vop2->pclk);
 	}
 
+	vop2->pll_hdmiphy0 = devm_clk_get_optional(vop2->dev, "pll_hdmiphy0");
+	if (IS_ERR(vop2->pll_hdmiphy0)) {
+		drm_err(vop2->drm, "failed to get pll_hdmiphy0\n");
+		return PTR_ERR(vop2->pll_hdmiphy0);
+	}
+
 	vop2->irq = platform_get_irq(pdev, 0);
 	if (vop2->irq < 0) {
 		drm_err(vop2->drm, "cannot find irq for vop2\n");
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.h b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.h
index 615a16196aff..130aaa40316d 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.h
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.h
@@ -9,6 +9,7 @@
 
 #include <linux/regmap.h>
 #include <drm/drm_modes.h>
+#include "rockchip_drm_drv.h"
 #include "rockchip_drm_vop.h"
 
 #define VOP2_VP_FEATURE_OUTPUT_10BIT        BIT(0)
@@ -78,6 +79,9 @@ enum vop2_win_regs {
 	VOP2_WIN_COLOR_KEY,
 	VOP2_WIN_COLOR_KEY_EN,
 	VOP2_WIN_DITHER_UP,
+	VOP2_WIN_AXI_BUS_ID,
+	VOP2_WIN_AXI_YRGB_R_ID,
+	VOP2_WIN_AXI_UV_R_ID,
 
 	/* scale regs */
 	VOP2_WIN_SCALE_YRGB_X,
@@ -140,6 +144,10 @@ struct vop2_win_data {
 	unsigned int layer_sel_id;
 	uint64_t feature;
 
+	uint8_t axi_bus_id;
+	uint8_t axi_yrgb_r_id;
+	uint8_t axi_uv_r_id;
+
 	unsigned int max_upscale_factor;
 	unsigned int max_downscale_factor;
 	const u8 dly[VOP2_DLY_MODE_MAX];
@@ -308,6 +316,7 @@ enum dst_factor_mode {
 
 #define RK3568_CLUSTER_WIN_CTRL0		0x00
 #define RK3568_CLUSTER_WIN_CTRL1		0x04
+#define RK3568_CLUSTER_WIN_CTRL2		0x08
 #define RK3568_CLUSTER_WIN_YRGB_MST		0x10
 #define RK3568_CLUSTER_WIN_CBR_MST		0x14
 #define RK3568_CLUSTER_WIN_VIR			0x18
@@ -330,6 +339,7 @@ enum dst_factor_mode {
 /* (E)smart register definition, offset relative to window base */
 #define RK3568_SMART_CTRL0			0x00
 #define RK3568_SMART_CTRL1			0x04
+#define RK3588_SMART_AXI_CTRL			0x08
 #define RK3568_SMART_REGION0_CTRL		0x10
 #define RK3568_SMART_REGION0_YRGB_MST		0x14
 #define RK3568_SMART_REGION0_CBR_MST		0x18
diff --git a/drivers/gpu/drm/rockchip/rockchip_vop2_reg.c b/drivers/gpu/drm/rockchip/rockchip_vop2_reg.c
index 18efb3fe1c00..e473a8f8fd32 100644
--- a/drivers/gpu/drm/rockchip/rockchip_vop2_reg.c
+++ b/drivers/gpu/drm/rockchip/rockchip_vop2_reg.c
@@ -313,7 +313,7 @@ static const struct vop2_video_port_data rk3588_vop_video_ports[] = {
  * AXI1 is a read only bus.
  *
  * Every window on a AXI bus must assigned two unique
- * read id(yrgb_id/uv_id, valid id are 0x1~0xe).
+ * read id(yrgb_r_id/uv_r_id, valid id are 0x1~0xe).
  *
  * AXI0:
  * Cluster0/1, Esmart0/1, WriteBack
@@ -333,6 +333,9 @@ static const struct vop2_win_data rk3588_vop_win_data[] = {
 		.layer_sel_id = 0,
 		.supported_rotations = DRM_MODE_ROTATE_90 | DRM_MODE_ROTATE_270 |
 				       DRM_MODE_REFLECT_X | DRM_MODE_REFLECT_Y,
+		.axi_bus_id = 0,
+		.axi_yrgb_r_id = 2,
+		.axi_uv_r_id = 3,
 		.max_upscale_factor = 4,
 		.max_downscale_factor = 4,
 		.dly = { 4, 26, 29 },
@@ -349,6 +352,9 @@ static const struct vop2_win_data rk3588_vop_win_data[] = {
 		.supported_rotations = DRM_MODE_ROTATE_90 | DRM_MODE_ROTATE_270 |
 				       DRM_MODE_REFLECT_X | DRM_MODE_REFLECT_Y,
 		.type = DRM_PLANE_TYPE_PRIMARY,
+		.axi_bus_id = 0,
+		.axi_yrgb_r_id = 6,
+		.axi_uv_r_id = 7,
 		.max_upscale_factor = 4,
 		.max_downscale_factor = 4,
 		.dly = { 4, 26, 29 },
@@ -364,6 +370,9 @@ static const struct vop2_win_data rk3588_vop_win_data[] = {
 		.supported_rotations = DRM_MODE_ROTATE_90 | DRM_MODE_ROTATE_270 |
 				       DRM_MODE_REFLECT_X | DRM_MODE_REFLECT_Y,
 		.type = DRM_PLANE_TYPE_PRIMARY,
+		.axi_bus_id = 1,
+		.axi_yrgb_r_id = 2,
+		.axi_uv_r_id = 3,
 		.max_upscale_factor = 4,
 		.max_downscale_factor = 4,
 		.dly = { 4, 26, 29 },
@@ -379,6 +388,9 @@ static const struct vop2_win_data rk3588_vop_win_data[] = {
 		.supported_rotations = DRM_MODE_ROTATE_90 | DRM_MODE_ROTATE_270 |
 				       DRM_MODE_REFLECT_X | DRM_MODE_REFLECT_Y,
 		.type = DRM_PLANE_TYPE_PRIMARY,
+		.axi_bus_id = 1,
+		.axi_yrgb_r_id = 6,
+		.axi_uv_r_id = 7,
 		.max_upscale_factor = 4,
 		.max_downscale_factor = 4,
 		.dly = { 4, 26, 29 },
@@ -393,6 +405,9 @@ static const struct vop2_win_data rk3588_vop_win_data[] = {
 		.layer_sel_id = 2,
 		.supported_rotations = DRM_MODE_REFLECT_Y,
 		.type = DRM_PLANE_TYPE_OVERLAY,
+		.axi_bus_id = 0,
+		.axi_yrgb_r_id = 0x0a,
+		.axi_uv_r_id = 0x0b,
 		.max_upscale_factor = 8,
 		.max_downscale_factor = 8,
 		.dly = { 23, 45, 48 },
@@ -406,6 +421,9 @@ static const struct vop2_win_data rk3588_vop_win_data[] = {
 		.layer_sel_id = 3,
 		.supported_rotations = DRM_MODE_REFLECT_Y,
 		.type = DRM_PLANE_TYPE_OVERLAY,
+		.axi_bus_id = 0,
+		.axi_yrgb_r_id = 0x0c,
+		.axi_uv_r_id = 0x01,
 		.max_upscale_factor = 8,
 		.max_downscale_factor = 8,
 		.dly = { 23, 45, 48 },
@@ -419,6 +437,9 @@ static const struct vop2_win_data rk3588_vop_win_data[] = {
 		.layer_sel_id = 6,
 		.supported_rotations = DRM_MODE_REFLECT_Y,
 		.type = DRM_PLANE_TYPE_OVERLAY,
+		.axi_bus_id = 1,
+		.axi_yrgb_r_id = 0x0a,
+		.axi_uv_r_id = 0x0b,
 		.max_upscale_factor = 8,
 		.max_downscale_factor = 8,
 		.dly = { 23, 45, 48 },
@@ -432,6 +453,9 @@ static const struct vop2_win_data rk3588_vop_win_data[] = {
 		.layer_sel_id = 7,
 		.supported_rotations = DRM_MODE_REFLECT_Y,
 		.type = DRM_PLANE_TYPE_OVERLAY,
+		.axi_bus_id = 1,
+		.axi_yrgb_r_id = 0x0c,
+		.axi_uv_r_id = 0x0d,
 		.max_upscale_factor = 8,
 		.max_downscale_factor = 8,
 		.dly = { 23, 45, 48 },
diff --git a/drivers/gpu/drm/scheduler/gpu_scheduler_trace.h b/drivers/gpu/drm/scheduler/gpu_scheduler_trace.h
index c75302ca3427..f56e77e7f6d0 100644
--- a/drivers/gpu/drm/scheduler/gpu_scheduler_trace.h
+++ b/drivers/gpu/drm/scheduler/gpu_scheduler_trace.h
@@ -21,7 +21,7 @@
  *
  */
 
-#if !defined(_GPU_SCHED_TRACE_H) || defined(TRACE_HEADER_MULTI_READ)
+#if !defined(_GPU_SCHED_TRACE_H_) || defined(TRACE_HEADER_MULTI_READ)
 #define _GPU_SCHED_TRACE_H_
 
 #include <linux/stringify.h>
@@ -106,7 +106,7 @@ TRACE_EVENT(drm_sched_job_wait_dep,
 		      __entry->seqno)
 );
 
-#endif
+#endif /* _GPU_SCHED_TRACE_H_ */
 
 /* This part must be outside protection */
 #undef TRACE_INCLUDE_PATH
diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c
index a75eede8bf8d..3e75fc1f6607 100644
--- a/drivers/gpu/drm/scheduler/sched_entity.c
+++ b/drivers/gpu/drm/scheduler/sched_entity.c
@@ -189,6 +189,7 @@ static void drm_sched_entity_kill_jobs_work(struct work_struct *wrk)
 {
 	struct drm_sched_job *job = container_of(wrk, typeof(*job), work);
 
+	drm_sched_fence_scheduled(job->s_fence, NULL);
 	drm_sched_fence_finished(job->s_fence, -ESRCH);
 	WARN_ON(job->s_fence->parent);
 	job->sched->ops->free_job(job);
@@ -259,9 +260,16 @@ static void drm_sched_entity_kill(struct drm_sched_entity *entity)
 		struct drm_sched_fence *s_fence = job->s_fence;
 
 		dma_fence_get(&s_fence->finished);
-		if (!prev || dma_fence_add_callback(prev, &job->finish_cb,
-					   drm_sched_entity_kill_jobs_cb))
+		if (!prev ||
+		    dma_fence_add_callback(prev, &job->finish_cb,
+					   drm_sched_entity_kill_jobs_cb)) {
+			/*
+			 * Adding callback above failed.
+			 * dma_fence_put() checks for NULL.
+			 */
+			dma_fence_put(prev);
 			drm_sched_entity_kill_jobs_cb(NULL, &job->finish_cb);
+		}
 
 		prev = &s_fence->finished;
 	}
@@ -360,17 +368,6 @@ void drm_sched_entity_destroy(struct drm_sched_entity *entity)
 }
 EXPORT_SYMBOL(drm_sched_entity_destroy);
 
-/* drm_sched_entity_clear_dep - callback to clear the entities dependency */
-static void drm_sched_entity_clear_dep(struct dma_fence *f,
-				       struct dma_fence_cb *cb)
-{
-	struct drm_sched_entity *entity =
-		container_of(cb, struct drm_sched_entity, cb);
-
-	entity->dependency = NULL;
-	dma_fence_put(f);
-}
-
 /*
  * drm_sched_entity_clear_dep - callback to clear the entities dependency and
  * wake up scheduler
@@ -381,7 +378,8 @@ static void drm_sched_entity_wakeup(struct dma_fence *f,
 	struct drm_sched_entity *entity =
 		container_of(cb, struct drm_sched_entity, cb);
 
-	drm_sched_entity_clear_dep(f, cb);
+	entity->dependency = NULL;
+	dma_fence_put(f);
 	drm_sched_wakeup(entity->rq->sched);
 }
 
@@ -434,13 +432,6 @@ static bool drm_sched_entity_add_dependency_cb(struct drm_sched_entity *entity)
 		fence = dma_fence_get(&s_fence->scheduled);
 		dma_fence_put(entity->dependency);
 		entity->dependency = fence;
-		if (!dma_fence_add_callback(fence, &entity->cb,
-					    drm_sched_entity_clear_dep))
-			return true;
-
-		/* Ignore it when it is already scheduled */
-		dma_fence_put(fence);
-		return false;
 	}
 
 	if (!dma_fence_add_callback(entity->dependency, &entity->cb,
diff --git a/drivers/gpu/drm/solomon/ssd130x-spi.c b/drivers/gpu/drm/solomon/ssd130x-spi.c
index 84bfde31d172..fd1b858dcb78 100644
--- a/drivers/gpu/drm/solomon/ssd130x-spi.c
+++ b/drivers/gpu/drm/solomon/ssd130x-spi.c
@@ -151,7 +151,6 @@ static const struct of_device_id ssd130x_of_match[] = {
 };
 MODULE_DEVICE_TABLE(of, ssd130x_of_match);
 
-#if IS_MODULE(CONFIG_DRM_SSD130X_SPI)
 /*
  * The SPI core always reports a MODALIAS uevent of the form "spi:<dev>", even
  * if the device was registered via OF. This means that the module will not be
@@ -160,7 +159,7 @@ MODULE_DEVICE_TABLE(of, ssd130x_of_match);
  * To workaround this issue, add a SPI device ID table. Even when this should
  * not be needed for this driver to match the registered SPI devices.
  */
-static const struct spi_device_id ssd130x_spi_table[] = {
+static const struct spi_device_id ssd130x_spi_id[] = {
 	/* ssd130x family */
 	{ "sh1106",  SH1106_ID },
 	{ "ssd1305", SSD1305_ID },
@@ -175,14 +174,14 @@ static const struct spi_device_id ssd130x_spi_table[] = {
 	{ "ssd1331", SSD1331_ID },
 	{ /* sentinel */ }
 };
-MODULE_DEVICE_TABLE(spi, ssd130x_spi_table);
-#endif
+MODULE_DEVICE_TABLE(spi, ssd130x_spi_id);
 
 static struct spi_driver ssd130x_spi_driver = {
 	.driver = {
 		.name = DRIVER_NAME,
 		.of_match_table = ssd130x_of_match,
 	},
+	.id_table = ssd130x_spi_id,
 	.probe = ssd130x_spi_probe,
 	.remove = ssd130x_spi_remove,
 	.shutdown = ssd130x_spi_shutdown,
diff --git a/drivers/gpu/drm/solomon/ssd130x.c b/drivers/gpu/drm/solomon/ssd130x.c
index 6f51bcf774e2..e0fc12d514d7 100644
--- a/drivers/gpu/drm/solomon/ssd130x.c
+++ b/drivers/gpu/drm/solomon/ssd130x.c
@@ -880,7 +880,7 @@ static int ssd132x_update_rect(struct ssd130x_device *ssd130x,
 			u8 n1 = buf[i * width + j];
 			u8 n2 = buf[i * width + j + 1];
 
-			data_array[array_idx++] = (n2 << 4) | n1;
+			data_array[array_idx++] = (n2 & 0xf0) | (n1 >> 4);
 		}
 	}
 
@@ -974,7 +974,7 @@ static void ssd130x_clear_screen(struct ssd130x_device *ssd130x, u8 *data_array)
 
 static void ssd132x_clear_screen(struct ssd130x_device *ssd130x, u8 *data_array)
 {
-	unsigned int columns = DIV_ROUND_UP(ssd130x->height, SSD132X_SEGMENT_WIDTH);
+	unsigned int columns = DIV_ROUND_UP(ssd130x->width, SSD132X_SEGMENT_WIDTH);
 	unsigned int height = ssd130x->height;
 
 	memset(data_array, 0, columns * height);
@@ -1037,7 +1037,7 @@ static int ssd132x_fb_blit_rect(struct drm_framebuffer *fb,
 				struct drm_format_conv_state *fmtcnv_state)
 {
 	struct ssd130x_device *ssd130x = drm_to_ssd130x(fb->dev);
-	unsigned int dst_pitch = drm_rect_width(rect);
+	unsigned int dst_pitch;
 	struct iosys_map dst;
 	int ret = 0;
 
@@ -1046,6 +1046,8 @@ static int ssd132x_fb_blit_rect(struct drm_framebuffer *fb,
 	rect->x2 = min_t(unsigned int, round_up(rect->x2, SSD132X_SEGMENT_WIDTH),
 			 ssd130x->width);
 
+	dst_pitch = drm_rect_width(rect);
+
 	ret = drm_gem_fb_begin_cpu_access(fb, DMA_FROM_DEVICE);
 	if (ret)
 		return ret;
diff --git a/drivers/gpu/drm/sti/Makefile b/drivers/gpu/drm/sti/Makefile
index f203ac5514ae..f778a4eee7c9 100644
--- a/drivers/gpu/drm/sti/Makefile
+++ b/drivers/gpu/drm/sti/Makefile
@@ -7,8 +7,6 @@ sti-drm-y := \
 	sti_compositor.o \
 	sti_crtc.o \
 	sti_plane.o \
-	sti_crtc.o \
-	sti_plane.o \
 	sti_hdmi.o \
 	sti_hdmi_tx3g4c28phy.o \
 	sti_dvo.o \
diff --git a/drivers/gpu/drm/sti/sti_hdmi.c b/drivers/gpu/drm/sti/sti_hdmi.c
index 847470f747c0..3c8f3532c797 100644
--- a/drivers/gpu/drm/sti/sti_hdmi.c
+++ b/drivers/gpu/drm/sti/sti_hdmi.c
@@ -1225,7 +1225,9 @@ static int hdmi_audio_get_eld(struct device *dev, void *data, uint8_t *buf, size
 	struct drm_connector *connector = hdmi->drm_connector;
 
 	DRM_DEBUG_DRIVER("\n");
+	mutex_lock(&connector->eld_mutex);
 	memcpy(buf, connector->eld, min(sizeof(connector->eld), len));
+	mutex_unlock(&connector->eld_mutex);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/tegra/dc.c b/drivers/gpu/drm/tegra/dc.c
index be61c9d1a4f0..51ca78551b57 100644
--- a/drivers/gpu/drm/tegra/dc.c
+++ b/drivers/gpu/drm/tegra/dc.c
@@ -1320,10 +1320,16 @@ static struct drm_plane *tegra_dc_add_shared_planes(struct drm_device *drm,
 		if (wgrp->dc == dc->pipe) {
 			for (j = 0; j < wgrp->num_windows; j++) {
 				unsigned int index = wgrp->windows[j];
+				enum drm_plane_type type;
+
+				if (primary)
+					type = DRM_PLANE_TYPE_OVERLAY;
+				else
+					type = DRM_PLANE_TYPE_PRIMARY;
 
 				plane = tegra_shared_plane_create(drm, dc,
 								  wgrp->index,
-								  index);
+								  index, type);
 				if (IS_ERR(plane))
 					return plane;
 
@@ -1331,10 +1337,8 @@ static struct drm_plane *tegra_dc_add_shared_planes(struct drm_device *drm,
 				 * Choose the first shared plane owned by this
 				 * head as the primary plane.
 				 */
-				if (!primary) {
-					plane->type = DRM_PLANE_TYPE_PRIMARY;
+				if (!primary)
 					primary = plane;
-				}
 			}
 		}
 	}
@@ -1388,7 +1392,10 @@ static void tegra_crtc_reset(struct drm_crtc *crtc)
 	if (crtc->state)
 		tegra_crtc_atomic_destroy_state(crtc, crtc->state);
 
-	__drm_atomic_helper_crtc_reset(crtc, &state->base);
+	if (state)
+		__drm_atomic_helper_crtc_reset(crtc, &state->base);
+	else
+		__drm_atomic_helper_crtc_reset(crtc, NULL);
 }
 
 static struct drm_crtc_state *
diff --git a/drivers/gpu/drm/tegra/hub.c b/drivers/gpu/drm/tegra/hub.c
index e0c2019a591b..3507dd6e9023 100644
--- a/drivers/gpu/drm/tegra/hub.c
+++ b/drivers/gpu/drm/tegra/hub.c
@@ -755,9 +755,9 @@ static const struct drm_plane_helper_funcs tegra_shared_plane_helper_funcs = {
 struct drm_plane *tegra_shared_plane_create(struct drm_device *drm,
 					    struct tegra_dc *dc,
 					    unsigned int wgrp,
-					    unsigned int index)
+					    unsigned int index,
+					    enum drm_plane_type type)
 {
-	enum drm_plane_type type = DRM_PLANE_TYPE_OVERLAY;
 	struct tegra_drm *tegra = drm->dev_private;
 	struct tegra_display_hub *hub = tegra->hub;
 	struct tegra_shared_plane *plane;
diff --git a/drivers/gpu/drm/tegra/hub.h b/drivers/gpu/drm/tegra/hub.h
index 23c4b2115ed1..a66f18c4facc 100644
--- a/drivers/gpu/drm/tegra/hub.h
+++ b/drivers/gpu/drm/tegra/hub.h
@@ -80,7 +80,8 @@ void tegra_display_hub_cleanup(struct tegra_display_hub *hub);
 struct drm_plane *tegra_shared_plane_create(struct drm_device *drm,
 					    struct tegra_dc *dc,
 					    unsigned int wgrp,
-					    unsigned int index);
+					    unsigned int index,
+					    enum drm_plane_type type);
 
 int tegra_display_hub_atomic_check(struct drm_device *drm,
 				   struct drm_atomic_state *state);
diff --git a/drivers/gpu/drm/tegra/nvdec.c b/drivers/gpu/drm/tegra/nvdec.c
index 4860790666af..14ef61b44f47 100644
--- a/drivers/gpu/drm/tegra/nvdec.c
+++ b/drivers/gpu/drm/tegra/nvdec.c
@@ -261,10 +261,8 @@ static int nvdec_load_falcon_firmware(struct nvdec *nvdec)
 
 	if (!client->group) {
 		virt = dma_alloc_coherent(nvdec->dev, size, &iova, GFP_KERNEL);
-
-		err = dma_mapping_error(nvdec->dev, iova);
-		if (err < 0)
-			return err;
+		if (!virt)
+			return -ENOMEM;
 	} else {
 		virt = tegra_drm_alloc(tegra, size, &iova);
 		if (IS_ERR(virt))
diff --git a/drivers/gpu/drm/tegra/rgb.c b/drivers/gpu/drm/tegra/rgb.c
index 1e8ec50b759e..ff5a749710db 100644
--- a/drivers/gpu/drm/tegra/rgb.c
+++ b/drivers/gpu/drm/tegra/rgb.c
@@ -200,6 +200,11 @@ static const struct drm_encoder_helper_funcs tegra_rgb_encoder_helper_funcs = {
 	.atomic_check = tegra_rgb_encoder_atomic_check,
 };
 
+static void tegra_dc_of_node_put(void *data)
+{
+	of_node_put(data);
+}
+
 int tegra_dc_rgb_probe(struct tegra_dc *dc)
 {
 	struct device_node *np;
@@ -207,7 +212,14 @@ int tegra_dc_rgb_probe(struct tegra_dc *dc)
 	int err;
 
 	np = of_get_child_by_name(dc->dev->of_node, "rgb");
-	if (!np || !of_device_is_available(np))
+	if (!np)
+		return -ENODEV;
+
+	err = devm_add_action_or_reset(dc->dev, tegra_dc_of_node_put, np);
+	if (err < 0)
+		return err;
+
+	if (!of_device_is_available(np))
 		return -ENODEV;
 
 	rgb = devm_kzalloc(dc->dev, sizeof(*rgb), GFP_KERNEL);
diff --git a/drivers/gpu/drm/tests/drm_client_modeset_test.c b/drivers/gpu/drm/tests/drm_client_modeset_test.c
index 7516f6cb36e4..3e9518d7b8b7 100644
--- a/drivers/gpu/drm/tests/drm_client_modeset_test.c
+++ b/drivers/gpu/drm/tests/drm_client_modeset_test.c
@@ -95,6 +95,9 @@ static void drm_test_pick_cmdline_res_1920_1080_60(struct kunit *test)
 	expected_mode = drm_mode_find_dmt(priv->drm, 1920, 1080, 60, false);
 	KUNIT_ASSERT_NOT_NULL(test, expected_mode);
 
+	ret = drm_kunit_add_mode_destroy_action(test, expected_mode);
+	KUNIT_ASSERT_EQ(test, ret, 0);
+
 	KUNIT_ASSERT_TRUE(test,
 			  drm_mode_parse_command_line_for_connector(cmdline,
 								    connector,
diff --git a/drivers/gpu/drm/tests/drm_cmdline_parser_test.c b/drivers/gpu/drm/tests/drm_cmdline_parser_test.c
index 59c8408c453c..1cfcb597b088 100644
--- a/drivers/gpu/drm/tests/drm_cmdline_parser_test.c
+++ b/drivers/gpu/drm/tests/drm_cmdline_parser_test.c
@@ -7,6 +7,7 @@
 #include <kunit/test.h>
 
 #include <drm/drm_connector.h>
+#include <drm/drm_kunit_helpers.h>
 #include <drm/drm_modes.h>
 
 static const struct drm_connector no_connector = {};
@@ -955,8 +956,15 @@ struct drm_cmdline_tv_option_test {
 static void drm_test_cmdline_tv_options(struct kunit *test)
 {
 	const struct drm_cmdline_tv_option_test *params = test->param_value;
-	const struct drm_display_mode *expected_mode = params->mode_fn(NULL);
+	struct drm_display_mode *expected_mode;
 	struct drm_cmdline_mode mode = { };
+	int ret;
+
+	expected_mode = params->mode_fn(NULL);
+	KUNIT_ASSERT_NOT_NULL(test, expected_mode);
+
+	ret = drm_kunit_add_mode_destroy_action(test, expected_mode);
+	KUNIT_ASSERT_EQ(test, ret, 0);
 
 	KUNIT_EXPECT_TRUE(test, drm_mode_parse_command_line_for_connector(params->cmdline,
 									  &no_connector, &mode));
diff --git a/drivers/gpu/drm/tests/drm_gem_shmem_test.c b/drivers/gpu/drm/tests/drm_gem_shmem_test.c
index fd4215e2f982..925fbc2cda70 100644
--- a/drivers/gpu/drm/tests/drm_gem_shmem_test.c
+++ b/drivers/gpu/drm/tests/drm_gem_shmem_test.c
@@ -216,6 +216,9 @@ static void drm_gem_shmem_test_get_pages_sgt(struct kunit *test)
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, sgt);
 	KUNIT_EXPECT_NULL(test, shmem->sgt);
 
+	ret = kunit_add_action_or_reset(test, kfree_wrapper, sgt);
+	KUNIT_ASSERT_EQ(test, ret, 0);
+
 	ret = kunit_add_action_or_reset(test, sg_free_table_wrapper, sgt);
 	KUNIT_ASSERT_EQ(test, ret, 0);
 
diff --git a/drivers/gpu/drm/tests/drm_hdmi_state_helper_test.c b/drivers/gpu/drm/tests/drm_hdmi_state_helper_test.c
index 294773342e71..383fbe128348 100644
--- a/drivers/gpu/drm/tests/drm_hdmi_state_helper_test.c
+++ b/drivers/gpu/drm/tests/drm_hdmi_state_helper_test.c
@@ -46,7 +46,7 @@ static struct drm_display_mode *find_preferred_mode(struct drm_connector *connec
 	struct drm_display_mode *mode, *preferred;
 
 	mutex_lock(&drm->mode_config.mutex);
-	preferred = list_first_entry(&connector->modes, struct drm_display_mode, head);
+	preferred = list_first_entry_or_null(&connector->modes, struct drm_display_mode, head);
 	list_for_each_entry(mode, &connector->modes, head)
 		if (mode->type & DRM_MODE_TYPE_PREFERRED)
 			preferred = mode;
@@ -70,10 +70,17 @@ static int light_up_connector(struct kunit *test,
 	state = drm_kunit_helper_atomic_state_alloc(test, drm, ctx);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, state);
 
+retry:
 	conn_state = drm_atomic_get_connector_state(state, connector);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, conn_state);
 
 	ret = drm_atomic_set_crtc_for_connector(conn_state, crtc);
+	if (ret == -EDEADLK) {
+		drm_atomic_state_clear(state);
+		ret = drm_modeset_backoff(ctx);
+		if (!ret)
+			goto retry;
+	}
 	KUNIT_EXPECT_EQ(test, ret, 0);
 
 	crtc_state = drm_atomic_get_crtc_state(state, crtc);
@@ -105,9 +112,8 @@ static int set_connector_edid(struct kunit *test, struct drm_connector *connecto
 	mutex_lock(&drm->mode_config.mutex);
 	ret = connector->funcs->fill_modes(connector, 4096, 4096);
 	mutex_unlock(&drm->mode_config.mutex);
-	KUNIT_ASSERT_GT(test, ret, 0);
 
-	return 0;
+	return ret;
 }
 
 static const struct drm_connector_hdmi_funcs dummy_connector_hdmi_funcs = {
@@ -223,7 +229,7 @@ drm_atomic_helper_connector_hdmi_init(struct kunit *test,
 	ret = set_connector_edid(test, conn,
 				 test_edid_hdmi_1080p_rgb_max_200mhz,
 				 ARRAY_SIZE(test_edid_hdmi_1080p_rgb_max_200mhz));
-	KUNIT_ASSERT_EQ(test, ret, 0);
+	KUNIT_ASSERT_GT(test, ret, 0);
 
 	return priv;
 }
@@ -252,15 +258,16 @@ static void drm_test_check_broadcast_rgb_crtc_mode_changed(struct kunit *test)
 						     8);
 	KUNIT_ASSERT_NOT_NULL(test, priv);
 
-	ctx = drm_kunit_helper_acquire_ctx_alloc(test);
-	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx);
-
+	drm = &priv->drm;
+	crtc = priv->crtc;
 	conn = &priv->connector;
+
 	preferred = find_preferred_mode(conn);
 	KUNIT_ASSERT_NOT_NULL(test, preferred);
 
-	drm = &priv->drm;
-	crtc = priv->crtc;
+	ctx = drm_kunit_helper_acquire_ctx_alloc(test);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx);
+
 	ret = light_up_connector(test, drm, crtc, conn, preferred, ctx);
 	KUNIT_ASSERT_EQ(test, ret, 0);
 
@@ -315,15 +322,16 @@ static void drm_test_check_broadcast_rgb_crtc_mode_not_changed(struct kunit *tes
 						     8);
 	KUNIT_ASSERT_NOT_NULL(test, priv);
 
-	ctx = drm_kunit_helper_acquire_ctx_alloc(test);
-	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx);
-
+	drm = &priv->drm;
+	crtc = priv->crtc;
 	conn = &priv->connector;
+
 	preferred = find_preferred_mode(conn);
 	KUNIT_ASSERT_NOT_NULL(test, preferred);
 
-	drm = &priv->drm;
-	crtc = priv->crtc;
+	ctx = drm_kunit_helper_acquire_ctx_alloc(test);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx);
+
 	ret = light_up_connector(test, drm, crtc, conn, preferred, ctx);
 	KUNIT_ASSERT_EQ(test, ret, 0);
 
@@ -378,18 +386,18 @@ static void drm_test_check_broadcast_rgb_auto_cea_mode(struct kunit *test)
 						     8);
 	KUNIT_ASSERT_NOT_NULL(test, priv);
 
+	drm = &priv->drm;
+	crtc = priv->crtc;
 	conn = &priv->connector;
 	KUNIT_ASSERT_TRUE(test, conn->display_info.is_hdmi);
 
-	ctx = drm_kunit_helper_acquire_ctx_alloc(test);
-	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx);
-
 	preferred = find_preferred_mode(conn);
 	KUNIT_ASSERT_NOT_NULL(test, preferred);
 	KUNIT_ASSERT_NE(test, drm_match_cea_mode(preferred), 1);
 
-	drm = &priv->drm;
-	crtc = priv->crtc;
+	ctx = drm_kunit_helper_acquire_ctx_alloc(test);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx);
+
 	ret = light_up_connector(test, drm, crtc, conn, preferred, ctx);
 	KUNIT_ASSERT_EQ(test, ret, 0);
 
@@ -444,7 +452,6 @@ static void drm_test_check_broadcast_rgb_auto_cea_mode_vic_1(struct kunit *test)
 	mode = drm_kunit_display_mode_from_cea_vic(test, drm, 1);
 	KUNIT_ASSERT_NOT_NULL(test, mode);
 
-	drm = &priv->drm;
 	crtc = priv->crtc;
 	ret = light_up_connector(test, drm, crtc, conn, mode, ctx);
 	KUNIT_ASSERT_EQ(test, ret, 0);
@@ -490,18 +497,18 @@ static void drm_test_check_broadcast_rgb_full_cea_mode(struct kunit *test)
 						     8);
 	KUNIT_ASSERT_NOT_NULL(test, priv);
 
+	drm = &priv->drm;
+	crtc = priv->crtc;
 	conn = &priv->connector;
 	KUNIT_ASSERT_TRUE(test, conn->display_info.is_hdmi);
 
-	ctx = drm_kunit_helper_acquire_ctx_alloc(test);
-	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx);
-
 	preferred = find_preferred_mode(conn);
 	KUNIT_ASSERT_NOT_NULL(test, preferred);
 	KUNIT_ASSERT_NE(test, drm_match_cea_mode(preferred), 1);
 
-	drm = &priv->drm;
-	crtc = priv->crtc;
+	ctx = drm_kunit_helper_acquire_ctx_alloc(test);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx);
+
 	ret = light_up_connector(test, drm, crtc, conn, preferred, ctx);
 	KUNIT_ASSERT_EQ(test, ret, 0);
 
@@ -558,7 +565,6 @@ static void drm_test_check_broadcast_rgb_full_cea_mode_vic_1(struct kunit *test)
 	mode = drm_kunit_display_mode_from_cea_vic(test, drm, 1);
 	KUNIT_ASSERT_NOT_NULL(test, mode);
 
-	drm = &priv->drm;
 	crtc = priv->crtc;
 	ret = light_up_connector(test, drm, crtc, conn, mode, ctx);
 	KUNIT_ASSERT_EQ(test, ret, 0);
@@ -606,18 +612,18 @@ static void drm_test_check_broadcast_rgb_limited_cea_mode(struct kunit *test)
 						     8);
 	KUNIT_ASSERT_NOT_NULL(test, priv);
 
+	drm = &priv->drm;
+	crtc = priv->crtc;
 	conn = &priv->connector;
 	KUNIT_ASSERT_TRUE(test, conn->display_info.is_hdmi);
 
-	ctx = drm_kunit_helper_acquire_ctx_alloc(test);
-	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx);
-
 	preferred = find_preferred_mode(conn);
 	KUNIT_ASSERT_NOT_NULL(test, preferred);
 	KUNIT_ASSERT_NE(test, drm_match_cea_mode(preferred), 1);
 
-	drm = &priv->drm;
-	crtc = priv->crtc;
+	ctx = drm_kunit_helper_acquire_ctx_alloc(test);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx);
+
 	ret = light_up_connector(test, drm, crtc, conn, preferred, ctx);
 	KUNIT_ASSERT_EQ(test, ret, 0);
 
@@ -674,7 +680,6 @@ static void drm_test_check_broadcast_rgb_limited_cea_mode_vic_1(struct kunit *te
 	mode = drm_kunit_display_mode_from_cea_vic(test, drm, 1);
 	KUNIT_ASSERT_NOT_NULL(test, mode);
 
-	drm = &priv->drm;
 	crtc = priv->crtc;
 	ret = light_up_connector(test, drm, crtc, conn, mode, ctx);
 	KUNIT_ASSERT_EQ(test, ret, 0);
@@ -724,20 +729,20 @@ static void drm_test_check_output_bpc_crtc_mode_changed(struct kunit *test)
 						     10);
 	KUNIT_ASSERT_NOT_NULL(test, priv);
 
+	drm = &priv->drm;
+	crtc = priv->crtc;
 	conn = &priv->connector;
 	ret = set_connector_edid(test, conn,
 				 test_edid_hdmi_1080p_rgb_yuv_dc_max_200mhz,
 				 ARRAY_SIZE(test_edid_hdmi_1080p_rgb_yuv_dc_max_200mhz));
-	KUNIT_ASSERT_EQ(test, ret, 0);
-
-	ctx = drm_kunit_helper_acquire_ctx_alloc(test);
-	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx);
+	KUNIT_ASSERT_GT(test, ret, 0);
 
 	preferred = find_preferred_mode(conn);
 	KUNIT_ASSERT_NOT_NULL(test, preferred);
 
-	drm = &priv->drm;
-	crtc = priv->crtc;
+	ctx = drm_kunit_helper_acquire_ctx_alloc(test);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx);
+
 	ret = light_up_connector(test, drm, crtc, conn, preferred, ctx);
 	KUNIT_ASSERT_EQ(test, ret, 0);
 
@@ -798,20 +803,20 @@ static void drm_test_check_output_bpc_crtc_mode_not_changed(struct kunit *test)
 						     10);
 	KUNIT_ASSERT_NOT_NULL(test, priv);
 
+	drm = &priv->drm;
+	crtc = priv->crtc;
 	conn = &priv->connector;
 	ret = set_connector_edid(test, conn,
 				 test_edid_hdmi_1080p_rgb_yuv_dc_max_200mhz,
 				 ARRAY_SIZE(test_edid_hdmi_1080p_rgb_yuv_dc_max_200mhz));
-	KUNIT_ASSERT_EQ(test, ret, 0);
-
-	ctx = drm_kunit_helper_acquire_ctx_alloc(test);
-	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx);
+	KUNIT_ASSERT_GT(test, ret, 0);
 
 	preferred = find_preferred_mode(conn);
 	KUNIT_ASSERT_NOT_NULL(test, preferred);
 
-	drm = &priv->drm;
-	crtc = priv->crtc;
+	ctx = drm_kunit_helper_acquire_ctx_alloc(test);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx);
+
 	ret = light_up_connector(test, drm, crtc, conn, preferred, ctx);
 	KUNIT_ASSERT_EQ(test, ret, 0);
 
@@ -869,23 +874,23 @@ static void drm_test_check_output_bpc_dvi(struct kunit *test)
 						     12);
 	KUNIT_ASSERT_NOT_NULL(test, priv);
 
+	drm = &priv->drm;
+	crtc = priv->crtc;
 	conn = &priv->connector;
 	ret = set_connector_edid(test, conn,
 				 test_edid_dvi_1080p,
 				 ARRAY_SIZE(test_edid_dvi_1080p));
-	KUNIT_ASSERT_EQ(test, ret, 0);
+	KUNIT_ASSERT_GT(test, ret, 0);
 
 	info = &conn->display_info;
 	KUNIT_ASSERT_FALSE(test, info->is_hdmi);
 
-	ctx = drm_kunit_helper_acquire_ctx_alloc(test);
-	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx);
-
 	preferred = find_preferred_mode(conn);
 	KUNIT_ASSERT_NOT_NULL(test, preferred);
 
-	drm = &priv->drm;
-	crtc = priv->crtc;
+	ctx = drm_kunit_helper_acquire_ctx_alloc(test);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx);
+
 	ret = light_up_connector(test, drm, crtc, conn, preferred, ctx);
 	KUNIT_ASSERT_EQ(test, ret, 0);
 
@@ -916,21 +921,21 @@ static void drm_test_check_tmds_char_rate_rgb_8bpc(struct kunit *test)
 						     8);
 	KUNIT_ASSERT_NOT_NULL(test, priv);
 
+	drm = &priv->drm;
+	crtc = priv->crtc;
 	conn = &priv->connector;
 	ret = set_connector_edid(test, conn,
 				 test_edid_hdmi_1080p_rgb_max_200mhz,
 				 ARRAY_SIZE(test_edid_hdmi_1080p_rgb_max_200mhz));
-	KUNIT_ASSERT_EQ(test, ret, 0);
-
-	ctx = drm_kunit_helper_acquire_ctx_alloc(test);
-	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx);
+	KUNIT_ASSERT_GT(test, ret, 0);
 
 	preferred = find_preferred_mode(conn);
 	KUNIT_ASSERT_NOT_NULL(test, preferred);
 	KUNIT_ASSERT_FALSE(test, preferred->flags & DRM_MODE_FLAG_DBLCLK);
 
-	drm = &priv->drm;
-	crtc = priv->crtc;
+	ctx = drm_kunit_helper_acquire_ctx_alloc(test);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx);
+
 	ret = light_up_connector(test, drm, crtc, conn, preferred, ctx);
 	KUNIT_ASSERT_EQ(test, ret, 0);
 
@@ -963,21 +968,21 @@ static void drm_test_check_tmds_char_rate_rgb_10bpc(struct kunit *test)
 						     10);
 	KUNIT_ASSERT_NOT_NULL(test, priv);
 
+	drm = &priv->drm;
+	crtc = priv->crtc;
 	conn = &priv->connector;
 	ret = set_connector_edid(test, conn,
 				 test_edid_hdmi_1080p_rgb_yuv_dc_max_340mhz,
 				 ARRAY_SIZE(test_edid_hdmi_1080p_rgb_yuv_dc_max_340mhz));
-	KUNIT_ASSERT_EQ(test, ret, 0);
-
-	ctx = drm_kunit_helper_acquire_ctx_alloc(test);
-	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx);
+	KUNIT_ASSERT_GT(test, ret, 0);
 
 	preferred = find_preferred_mode(conn);
 	KUNIT_ASSERT_NOT_NULL(test, preferred);
 	KUNIT_ASSERT_FALSE(test, preferred->flags & DRM_MODE_FLAG_DBLCLK);
 
-	drm = &priv->drm;
-	crtc = priv->crtc;
+	ctx = drm_kunit_helper_acquire_ctx_alloc(test);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx);
+
 	ret = light_up_connector(test, drm, crtc, conn, preferred, ctx);
 	KUNIT_ASSERT_EQ(test, ret, 0);
 
@@ -1010,21 +1015,21 @@ static void drm_test_check_tmds_char_rate_rgb_12bpc(struct kunit *test)
 						     12);
 	KUNIT_ASSERT_NOT_NULL(test, priv);
 
+	drm = &priv->drm;
+	crtc = priv->crtc;
 	conn = &priv->connector;
 	ret = set_connector_edid(test, conn,
 				 test_edid_hdmi_1080p_rgb_yuv_dc_max_340mhz,
 				 ARRAY_SIZE(test_edid_hdmi_1080p_rgb_yuv_dc_max_340mhz));
-	KUNIT_ASSERT_EQ(test, ret, 0);
-
-	ctx = drm_kunit_helper_acquire_ctx_alloc(test);
-	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx);
+	KUNIT_ASSERT_GT(test, ret, 0);
 
 	preferred = find_preferred_mode(conn);
 	KUNIT_ASSERT_NOT_NULL(test, preferred);
 	KUNIT_ASSERT_FALSE(test, preferred->flags & DRM_MODE_FLAG_DBLCLK);
 
-	drm = &priv->drm;
-	crtc = priv->crtc;
+	ctx = drm_kunit_helper_acquire_ctx_alloc(test);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx);
+
 	ret = light_up_connector(test, drm, crtc, conn, preferred, ctx);
 	KUNIT_ASSERT_EQ(test, ret, 0);
 
@@ -1061,15 +1066,16 @@ static void drm_test_check_hdmi_funcs_reject_rate(struct kunit *test)
 						     8);
 	KUNIT_ASSERT_NOT_NULL(test, priv);
 
-	ctx = drm_kunit_helper_acquire_ctx_alloc(test);
-	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx);
-
+	drm = &priv->drm;
+	crtc = priv->crtc;
 	conn = &priv->connector;
+
 	preferred = find_preferred_mode(conn);
 	KUNIT_ASSERT_NOT_NULL(test, preferred);
 
-	drm = &priv->drm;
-	crtc = priv->crtc;
+	ctx = drm_kunit_helper_acquire_ctx_alloc(test);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx);
+
 	ret = light_up_connector(test, drm, crtc, conn, preferred, ctx);
 	KUNIT_ASSERT_EQ(test, ret, 0);
 
@@ -1117,19 +1123,18 @@ static void drm_test_check_max_tmds_rate_bpc_fallback(struct kunit *test)
 						     12);
 	KUNIT_ASSERT_NOT_NULL(test, priv);
 
+	drm = &priv->drm;
+	crtc = priv->crtc;
 	conn = &priv->connector;
 	ret = set_connector_edid(test, conn,
 				 test_edid_hdmi_1080p_rgb_yuv_dc_max_200mhz,
 				 ARRAY_SIZE(test_edid_hdmi_1080p_rgb_yuv_dc_max_200mhz));
-	KUNIT_ASSERT_EQ(test, ret, 0);
+	KUNIT_ASSERT_GT(test, ret, 0);
 
 	info = &conn->display_info;
 	KUNIT_ASSERT_TRUE(test, info->is_hdmi);
 	KUNIT_ASSERT_GT(test, info->max_tmds_clock, 0);
 
-	ctx = drm_kunit_helper_acquire_ctx_alloc(test);
-	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx);
-
 	preferred = find_preferred_mode(conn);
 	KUNIT_ASSERT_NOT_NULL(test, preferred);
 	KUNIT_ASSERT_FALSE(test, preferred->flags & DRM_MODE_FLAG_DBLCLK);
@@ -1140,8 +1145,9 @@ static void drm_test_check_max_tmds_rate_bpc_fallback(struct kunit *test)
 	rate = drm_hdmi_compute_mode_clock(preferred, 10, HDMI_COLORSPACE_RGB);
 	KUNIT_ASSERT_LT(test, rate, info->max_tmds_clock * 1000);
 
-	drm = &priv->drm;
-	crtc = priv->crtc;
+	ctx = drm_kunit_helper_acquire_ctx_alloc(test);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx);
+
 	ret = light_up_connector(test, drm, crtc, conn, preferred, ctx);
 	KUNIT_EXPECT_EQ(test, ret, 0);
 
@@ -1186,19 +1192,18 @@ static void drm_test_check_max_tmds_rate_format_fallback(struct kunit *test)
 						     12);
 	KUNIT_ASSERT_NOT_NULL(test, priv);
 
+	drm = &priv->drm;
+	crtc = priv->crtc;
 	conn = &priv->connector;
 	ret = set_connector_edid(test, conn,
 				 test_edid_hdmi_1080p_rgb_yuv_dc_max_200mhz,
 				 ARRAY_SIZE(test_edid_hdmi_1080p_rgb_yuv_dc_max_200mhz));
-	KUNIT_ASSERT_EQ(test, ret, 0);
+	KUNIT_ASSERT_GT(test, ret, 0);
 
 	info = &conn->display_info;
 	KUNIT_ASSERT_TRUE(test, info->is_hdmi);
 	KUNIT_ASSERT_GT(test, info->max_tmds_clock, 0);
 
-	ctx = drm_kunit_helper_acquire_ctx_alloc(test);
-	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx);
-
 	preferred = find_preferred_mode(conn);
 	KUNIT_ASSERT_NOT_NULL(test, preferred);
 	KUNIT_ASSERT_FALSE(test, preferred->flags & DRM_MODE_FLAG_DBLCLK);
@@ -1212,8 +1217,9 @@ static void drm_test_check_max_tmds_rate_format_fallback(struct kunit *test)
 	rate = drm_hdmi_compute_mode_clock(preferred, 12, HDMI_COLORSPACE_YUV422);
 	KUNIT_ASSERT_LT(test, rate, info->max_tmds_clock * 1000);
 
-	drm = &priv->drm;
-	crtc = priv->crtc;
+	ctx = drm_kunit_helper_acquire_ctx_alloc(test);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx);
+
 	ret = light_up_connector(test, drm, crtc, conn, preferred, ctx);
 	KUNIT_EXPECT_EQ(test, ret, 0);
 
@@ -1254,15 +1260,12 @@ static void drm_test_check_output_bpc_format_vic_1(struct kunit *test)
 	ret = set_connector_edid(test, conn,
 				 test_edid_hdmi_1080p_rgb_yuv_dc_max_200mhz,
 				 ARRAY_SIZE(test_edid_hdmi_1080p_rgb_yuv_dc_max_200mhz));
-	KUNIT_ASSERT_EQ(test, ret, 0);
+	KUNIT_ASSERT_GT(test, ret, 0);
 
 	info = &conn->display_info;
 	KUNIT_ASSERT_TRUE(test, info->is_hdmi);
 	KUNIT_ASSERT_GT(test, info->max_tmds_clock, 0);
 
-	ctx = drm_kunit_helper_acquire_ctx_alloc(test);
-	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx);
-
 	mode = drm_kunit_display_mode_from_cea_vic(test, drm, 1);
 	KUNIT_ASSERT_NOT_NULL(test, mode);
 
@@ -1276,7 +1279,9 @@ static void drm_test_check_output_bpc_format_vic_1(struct kunit *test)
 	rate = mode->clock * 1500;
 	KUNIT_ASSERT_LT(test, rate, info->max_tmds_clock * 1000);
 
-	drm = &priv->drm;
+	ctx = drm_kunit_helper_acquire_ctx_alloc(test);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx);
+
 	crtc = priv->crtc;
 	ret = light_up_connector(test, drm, crtc, conn, mode, ctx);
 	KUNIT_EXPECT_EQ(test, ret, 0);
@@ -1310,19 +1315,18 @@ static void drm_test_check_output_bpc_format_driver_rgb_only(struct kunit *test)
 						     12);
 	KUNIT_ASSERT_NOT_NULL(test, priv);
 
+	drm = &priv->drm;
+	crtc = priv->crtc;
 	conn = &priv->connector;
 	ret = set_connector_edid(test, conn,
 				 test_edid_hdmi_1080p_rgb_yuv_dc_max_200mhz,
 				 ARRAY_SIZE(test_edid_hdmi_1080p_rgb_yuv_dc_max_200mhz));
-	KUNIT_ASSERT_EQ(test, ret, 0);
+	KUNIT_ASSERT_GT(test, ret, 0);
 
 	info = &conn->display_info;
 	KUNIT_ASSERT_TRUE(test, info->is_hdmi);
 	KUNIT_ASSERT_GT(test, info->max_tmds_clock, 0);
 
-	ctx = drm_kunit_helper_acquire_ctx_alloc(test);
-	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx);
-
 	preferred = find_preferred_mode(conn);
 	KUNIT_ASSERT_NOT_NULL(test, preferred);
 
@@ -1341,8 +1345,9 @@ static void drm_test_check_output_bpc_format_driver_rgb_only(struct kunit *test)
 	rate = drm_hdmi_compute_mode_clock(preferred, 12, HDMI_COLORSPACE_YUV422);
 	KUNIT_ASSERT_LT(test, rate, info->max_tmds_clock * 1000);
 
-	drm = &priv->drm;
-	crtc = priv->crtc;
+	ctx = drm_kunit_helper_acquire_ctx_alloc(test);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx);
+
 	ret = light_up_connector(test, drm, crtc, conn, preferred, ctx);
 	KUNIT_EXPECT_EQ(test, ret, 0);
 
@@ -1377,19 +1382,18 @@ static void drm_test_check_output_bpc_format_display_rgb_only(struct kunit *test
 						     12);
 	KUNIT_ASSERT_NOT_NULL(test, priv);
 
+	drm = &priv->drm;
+	crtc = priv->crtc;
 	conn = &priv->connector;
 	ret = set_connector_edid(test, conn,
 				 test_edid_hdmi_1080p_rgb_max_200mhz,
 				 ARRAY_SIZE(test_edid_hdmi_1080p_rgb_max_200mhz));
-	KUNIT_ASSERT_EQ(test, ret, 0);
+	KUNIT_ASSERT_GT(test, ret, 0);
 
 	info = &conn->display_info;
 	KUNIT_ASSERT_TRUE(test, info->is_hdmi);
 	KUNIT_ASSERT_GT(test, info->max_tmds_clock, 0);
 
-	ctx = drm_kunit_helper_acquire_ctx_alloc(test);
-	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx);
-
 	preferred = find_preferred_mode(conn);
 	KUNIT_ASSERT_NOT_NULL(test, preferred);
 
@@ -1408,8 +1412,9 @@ static void drm_test_check_output_bpc_format_display_rgb_only(struct kunit *test
 	rate = drm_hdmi_compute_mode_clock(preferred, 12, HDMI_COLORSPACE_YUV422);
 	KUNIT_ASSERT_LT(test, rate, info->max_tmds_clock * 1000);
 
-	drm = &priv->drm;
-	crtc = priv->crtc;
+	ctx = drm_kunit_helper_acquire_ctx_alloc(test);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx);
+
 	ret = light_up_connector(test, drm, crtc, conn, preferred, ctx);
 	KUNIT_EXPECT_EQ(test, ret, 0);
 
@@ -1443,19 +1448,18 @@ static void drm_test_check_output_bpc_format_driver_8bpc_only(struct kunit *test
 						     8);
 	KUNIT_ASSERT_NOT_NULL(test, priv);
 
+	drm = &priv->drm;
+	crtc = priv->crtc;
 	conn = &priv->connector;
 	ret = set_connector_edid(test, conn,
 				 test_edid_hdmi_1080p_rgb_yuv_dc_max_340mhz,
 				 ARRAY_SIZE(test_edid_hdmi_1080p_rgb_yuv_dc_max_340mhz));
-	KUNIT_ASSERT_EQ(test, ret, 0);
+	KUNIT_ASSERT_GT(test, ret, 0);
 
 	info = &conn->display_info;
 	KUNIT_ASSERT_TRUE(test, info->is_hdmi);
 	KUNIT_ASSERT_GT(test, info->max_tmds_clock, 0);
 
-	ctx = drm_kunit_helper_acquire_ctx_alloc(test);
-	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx);
-
 	preferred = find_preferred_mode(conn);
 	KUNIT_ASSERT_NOT_NULL(test, preferred);
 
@@ -1466,8 +1470,9 @@ static void drm_test_check_output_bpc_format_driver_8bpc_only(struct kunit *test
 	rate = drm_hdmi_compute_mode_clock(preferred, 12, HDMI_COLORSPACE_RGB);
 	KUNIT_ASSERT_LT(test, rate, info->max_tmds_clock * 1000);
 
-	drm = &priv->drm;
-	crtc = priv->crtc;
+	ctx = drm_kunit_helper_acquire_ctx_alloc(test);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx);
+
 	ret = light_up_connector(test, drm, crtc, conn, preferred, ctx);
 	KUNIT_EXPECT_EQ(test, ret, 0);
 
@@ -1503,19 +1508,18 @@ static void drm_test_check_output_bpc_format_display_8bpc_only(struct kunit *tes
 						     12);
 	KUNIT_ASSERT_NOT_NULL(test, priv);
 
+	drm = &priv->drm;
+	crtc = priv->crtc;
 	conn = &priv->connector;
 	ret = set_connector_edid(test, conn,
 				 test_edid_hdmi_1080p_rgb_max_340mhz,
 				 ARRAY_SIZE(test_edid_hdmi_1080p_rgb_max_340mhz));
-	KUNIT_ASSERT_EQ(test, ret, 0);
+	KUNIT_ASSERT_GT(test, ret, 0);
 
 	info = &conn->display_info;
 	KUNIT_ASSERT_TRUE(test, info->is_hdmi);
 	KUNIT_ASSERT_GT(test, info->max_tmds_clock, 0);
 
-	ctx = drm_kunit_helper_acquire_ctx_alloc(test);
-	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx);
-
 	preferred = find_preferred_mode(conn);
 	KUNIT_ASSERT_NOT_NULL(test, preferred);
 
@@ -1526,8 +1530,9 @@ static void drm_test_check_output_bpc_format_display_8bpc_only(struct kunit *tes
 	rate = drm_hdmi_compute_mode_clock(preferred, 12, HDMI_COLORSPACE_RGB);
 	KUNIT_ASSERT_LT(test, rate, info->max_tmds_clock * 1000);
 
-	drm = &priv->drm;
-	crtc = priv->crtc;
+	ctx = drm_kunit_helper_acquire_ctx_alloc(test);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx);
+
 	ret = light_up_connector(test, drm, crtc, conn, preferred, ctx);
 	KUNIT_EXPECT_EQ(test, ret, 0);
 
diff --git a/drivers/gpu/drm/tests/drm_kunit_helpers.c b/drivers/gpu/drm/tests/drm_kunit_helpers.c
index 3c0b7824c0be..922c4b6ed1dc 100644
--- a/drivers/gpu/drm/tests/drm_kunit_helpers.c
+++ b/drivers/gpu/drm/tests/drm_kunit_helpers.c
@@ -320,6 +320,28 @@ static void kunit_action_drm_mode_destroy(void *ptr)
 }
 
 /**
+ * drm_kunit_add_mode_destroy_action() - Add a drm_destroy_mode kunit action
+ * @test: The test context object
+ * @mode: The drm_display_mode to destroy eventually
+ *
+ * Registers a kunit action that will destroy the drm_display_mode at
+ * the end of the test.
+ *
+ * If an error occurs, the drm_display_mode will be destroyed.
+ *
+ * Returns:
+ * 0 on success, an error code otherwise.
+ */
+int drm_kunit_add_mode_destroy_action(struct kunit *test,
+				      struct drm_display_mode *mode)
+{
+	return kunit_add_action_or_reset(test,
+					 kunit_action_drm_mode_destroy,
+					 mode);
+}
+EXPORT_SYMBOL_GPL(drm_kunit_add_mode_destroy_action);
+
+/**
  * drm_kunit_display_mode_from_cea_vic() - return a mode for CEA VIC for a KUnit test
  * @test: The test context object
  * @dev: DRM device
diff --git a/drivers/gpu/drm/tests/drm_modes_test.c b/drivers/gpu/drm/tests/drm_modes_test.c
index 6ed51f99e133..7ba646d87856 100644
--- a/drivers/gpu/drm/tests/drm_modes_test.c
+++ b/drivers/gpu/drm/tests/drm_modes_test.c
@@ -40,6 +40,7 @@ static void drm_test_modes_analog_tv_ntsc_480i(struct kunit *test)
 {
 	struct drm_test_modes_priv *priv = test->priv;
 	struct drm_display_mode *mode;
+	int ret;
 
 	mode = drm_analog_tv_mode(priv->drm,
 				  DRM_MODE_TV_MODE_NTSC,
@@ -47,6 +48,9 @@ static void drm_test_modes_analog_tv_ntsc_480i(struct kunit *test)
 				  true);
 	KUNIT_ASSERT_NOT_NULL(test, mode);
 
+	ret = drm_kunit_add_mode_destroy_action(test, mode);
+	KUNIT_ASSERT_EQ(test, ret, 0);
+
 	KUNIT_EXPECT_EQ(test, drm_mode_vrefresh(mode), 60);
 	KUNIT_EXPECT_EQ(test, mode->hdisplay, 720);
 
@@ -70,6 +74,7 @@ static void drm_test_modes_analog_tv_ntsc_480i_inlined(struct kunit *test)
 {
 	struct drm_test_modes_priv *priv = test->priv;
 	struct drm_display_mode *expected, *mode;
+	int ret;
 
 	expected = drm_analog_tv_mode(priv->drm,
 				      DRM_MODE_TV_MODE_NTSC,
@@ -77,9 +82,15 @@ static void drm_test_modes_analog_tv_ntsc_480i_inlined(struct kunit *test)
 				      true);
 	KUNIT_ASSERT_NOT_NULL(test, expected);
 
+	ret = drm_kunit_add_mode_destroy_action(test, expected);
+	KUNIT_ASSERT_EQ(test, ret, 0);
+
 	mode = drm_mode_analog_ntsc_480i(priv->drm);
 	KUNIT_ASSERT_NOT_NULL(test, mode);
 
+	ret = drm_kunit_add_mode_destroy_action(test, mode);
+	KUNIT_ASSERT_EQ(test, ret, 0);
+
 	KUNIT_EXPECT_TRUE(test, drm_mode_equal(expected, mode));
 }
 
@@ -87,6 +98,7 @@ static void drm_test_modes_analog_tv_pal_576i(struct kunit *test)
 {
 	struct drm_test_modes_priv *priv = test->priv;
 	struct drm_display_mode *mode;
+	int ret;
 
 	mode = drm_analog_tv_mode(priv->drm,
 				  DRM_MODE_TV_MODE_PAL,
@@ -94,6 +106,9 @@ static void drm_test_modes_analog_tv_pal_576i(struct kunit *test)
 				  true);
 	KUNIT_ASSERT_NOT_NULL(test, mode);
 
+	ret = drm_kunit_add_mode_destroy_action(test, mode);
+	KUNIT_ASSERT_EQ(test, ret, 0);
+
 	KUNIT_EXPECT_EQ(test, drm_mode_vrefresh(mode), 50);
 	KUNIT_EXPECT_EQ(test, mode->hdisplay, 720);
 
@@ -117,6 +132,7 @@ static void drm_test_modes_analog_tv_pal_576i_inlined(struct kunit *test)
 {
 	struct drm_test_modes_priv *priv = test->priv;
 	struct drm_display_mode *expected, *mode;
+	int ret;
 
 	expected = drm_analog_tv_mode(priv->drm,
 				      DRM_MODE_TV_MODE_PAL,
@@ -124,9 +140,15 @@ static void drm_test_modes_analog_tv_pal_576i_inlined(struct kunit *test)
 				      true);
 	KUNIT_ASSERT_NOT_NULL(test, expected);
 
+	ret = drm_kunit_add_mode_destroy_action(test, expected);
+	KUNIT_ASSERT_EQ(test, ret, 0);
+
 	mode = drm_mode_analog_pal_576i(priv->drm);
 	KUNIT_ASSERT_NOT_NULL(test, mode);
 
+	ret = drm_kunit_add_mode_destroy_action(test, mode);
+	KUNIT_ASSERT_EQ(test, ret, 0);
+
 	KUNIT_EXPECT_TRUE(test, drm_mode_equal(expected, mode));
 }
 
diff --git a/drivers/gpu/drm/tests/drm_probe_helper_test.c b/drivers/gpu/drm/tests/drm_probe_helper_test.c
index bc09ff38aca1..db0e4f5df275 100644
--- a/drivers/gpu/drm/tests/drm_probe_helper_test.c
+++ b/drivers/gpu/drm/tests/drm_probe_helper_test.c
@@ -98,7 +98,7 @@ drm_test_connector_helper_tv_get_modes_check(struct kunit *test)
 	struct drm_connector *connector = &priv->connector;
 	struct drm_cmdline_mode *cmdline = &connector->cmdline_mode;
 	struct drm_display_mode *mode;
-	const struct drm_display_mode *expected;
+	struct drm_display_mode *expected;
 	size_t len;
 	int ret;
 
@@ -134,6 +134,9 @@ drm_test_connector_helper_tv_get_modes_check(struct kunit *test)
 
 		KUNIT_EXPECT_TRUE(test, drm_mode_equal(mode, expected));
 		KUNIT_EXPECT_TRUE(test, mode->type & DRM_MODE_TYPE_PREFERRED);
+
+		ret = drm_kunit_add_mode_destroy_action(test, expected);
+		KUNIT_ASSERT_EQ(test, ret, 0);
 	}
 
 	if (params->num_expected_modes >= 2) {
@@ -145,6 +148,9 @@ drm_test_connector_helper_tv_get_modes_check(struct kunit *test)
 
 		KUNIT_EXPECT_TRUE(test, drm_mode_equal(mode, expected));
 		KUNIT_EXPECT_FALSE(test, mode->type & DRM_MODE_TYPE_PREFERRED);
+
+		ret = drm_kunit_add_mode_destroy_action(test, expected);
+		KUNIT_ASSERT_EQ(test, ret, 0);
 	}
 
 	mutex_unlock(&priv->drm->mode_config.mutex);
diff --git a/drivers/gpu/drm/tidss/tidss_dispc.c b/drivers/gpu/drm/tidss/tidss_dispc.c
index 1ad711f8d2a8..45f22ead3e61 100644
--- a/drivers/gpu/drm/tidss/tidss_dispc.c
+++ b/drivers/gpu/drm/tidss/tidss_dispc.c
@@ -700,7 +700,7 @@ void dispc_k2g_set_irqenable(struct dispc_device *dispc, dispc_irq_t mask)
 {
 	dispc_irq_t old_mask = dispc_k2g_read_irqenable(dispc);
 
-	/* clear the irqstatus for newly enabled irqs */
+	/* clear the irqstatus for irqs that will be enabled */
 	dispc_k2g_clear_irqstatus(dispc, (mask ^ old_mask) & mask);
 
 	dispc_k2g_vp_set_irqenable(dispc, 0, mask);
@@ -708,6 +708,9 @@ void dispc_k2g_set_irqenable(struct dispc_device *dispc, dispc_irq_t mask)
 
 	dispc_write(dispc, DISPC_IRQENABLE_SET, (1 << 0) | (1 << 7));
 
+	/* clear the irqstatus for irqs that were disabled */
+	dispc_k2g_clear_irqstatus(dispc, (mask ^ old_mask) & old_mask);
+
 	/* flush posted write */
 	dispc_k2g_read_irqenable(dispc);
 }
@@ -780,24 +783,20 @@ static
 void dispc_k3_clear_irqstatus(struct dispc_device *dispc, dispc_irq_t clearmask)
 {
 	unsigned int i;
-	u32 top_clear = 0;
 
 	for (i = 0; i < dispc->feat->num_vps; ++i) {
-		if (clearmask & DSS_IRQ_VP_MASK(i)) {
+		if (clearmask & DSS_IRQ_VP_MASK(i))
 			dispc_k3_vp_write_irqstatus(dispc, i, clearmask);
-			top_clear |= BIT(i);
-		}
 	}
 	for (i = 0; i < dispc->feat->num_planes; ++i) {
-		if (clearmask & DSS_IRQ_PLANE_MASK(i)) {
+		if (clearmask & DSS_IRQ_PLANE_MASK(i))
 			dispc_k3_vid_write_irqstatus(dispc, i, clearmask);
-			top_clear |= BIT(4 + i);
-		}
 	}
 	if (dispc->feat->subrev == DISPC_K2G)
 		return;
 
-	dispc_write(dispc, DISPC_IRQSTATUS, top_clear);
+	/* always clear the top level irqstatus */
+	dispc_write(dispc, DISPC_IRQSTATUS, dispc_read(dispc, DISPC_IRQSTATUS));
 
 	/* Flush posted writes */
 	dispc_read(dispc, DISPC_IRQSTATUS);
@@ -843,7 +842,7 @@ static void dispc_k3_set_irqenable(struct dispc_device *dispc,
 
 	old_mask = dispc_k3_read_irqenable(dispc);
 
-	/* clear the irqstatus for newly enabled irqs */
+	/* clear the irqstatus for irqs that will be enabled */
 	dispc_k3_clear_irqstatus(dispc, (old_mask ^ mask) & mask);
 
 	for (i = 0; i < dispc->feat->num_vps; ++i) {
@@ -868,6 +867,9 @@ static void dispc_k3_set_irqenable(struct dispc_device *dispc,
 	if (main_disable)
 		dispc_write(dispc, DISPC_IRQENABLE_CLR, main_disable);
 
+	/* clear the irqstatus for irqs that were disabled */
+	dispc_k3_clear_irqstatus(dispc, (old_mask ^ mask) & old_mask);
+
 	/* Flush posted writes */
 	dispc_read(dispc, DISPC_IRQENABLE_SET);
 }
@@ -2767,8 +2769,12 @@ static void dispc_init_errata(struct dispc_device *dispc)
  */
 static void dispc_softreset_k2g(struct dispc_device *dispc)
 {
+	unsigned long flags;
+
+	spin_lock_irqsave(&dispc->tidss->wait_lock, flags);
 	dispc_set_irqenable(dispc, 0);
 	dispc_read_and_clear_irqstatus(dispc);
+	spin_unlock_irqrestore(&dispc->tidss->wait_lock, flags);
 
 	for (unsigned int vp_idx = 0; vp_idx < dispc->feat->num_vps; ++vp_idx)
 		VP_REG_FLD_MOD(dispc, vp_idx, DISPC_VP_CONTROL, 0, 0, 0);
diff --git a/drivers/gpu/drm/tidss/tidss_irq.c b/drivers/gpu/drm/tidss/tidss_irq.c
index 604334ef526a..d053dbb9d28c 100644
--- a/drivers/gpu/drm/tidss/tidss_irq.c
+++ b/drivers/gpu/drm/tidss/tidss_irq.c
@@ -60,7 +60,9 @@ static irqreturn_t tidss_irq_handler(int irq, void *arg)
 	unsigned int id;
 	dispc_irq_t irqstatus;
 
+	spin_lock(&tidss->wait_lock);
 	irqstatus = dispc_read_and_clear_irqstatus(tidss->dispc);
+	spin_unlock(&tidss->wait_lock);
 
 	for (id = 0; id < tidss->num_crtcs; id++) {
 		struct drm_crtc *crtc = tidss->crtcs[id];
diff --git a/drivers/gpu/drm/tiny/Kconfig b/drivers/gpu/drm/tiny/Kconfig
index f6889f649bc1..ce17143d47a8 100644
--- a/drivers/gpu/drm/tiny/Kconfig
+++ b/drivers/gpu/drm/tiny/Kconfig
@@ -67,6 +67,7 @@ config DRM_OFDRM
 config DRM_PANEL_MIPI_DBI
 	tristate "DRM support for MIPI DBI compatible panels"
 	depends on DRM && SPI
+	select DRM_CLIENT_SELECTION
 	select DRM_KMS_HELPER
 	select DRM_GEM_DMA_HELPER
 	select DRM_MIPI_DBI
diff --git a/drivers/gpu/drm/tiny/cirrus.c b/drivers/gpu/drm/tiny/cirrus.c
index 751326e3d9c3..c7e81f2610f8 100644
--- a/drivers/gpu/drm/tiny/cirrus.c
+++ b/drivers/gpu/drm/tiny/cirrus.c
@@ -318,7 +318,6 @@ static void cirrus_pitch_set(struct cirrus_device *cirrus, unsigned int pitch)
 	/* Enable extended blanking and pitch bits, and enable full memory */
 	cr1b = 0x22;
 	cr1b |= (pitch >> 7) & 0x10;
-	cr1b |= (pitch >> 6) & 0x40;
 	wreg_crt(cirrus, 0x1b, cr1b);
 
 	cirrus_set_start_address(cirrus, 0);
diff --git a/drivers/gpu/drm/tiny/panel-mipi-dbi.c b/drivers/gpu/drm/tiny/panel-mipi-dbi.c
index f753cdffe6f8..ac159e8127d5 100644
--- a/drivers/gpu/drm/tiny/panel-mipi-dbi.c
+++ b/drivers/gpu/drm/tiny/panel-mipi-dbi.c
@@ -15,6 +15,7 @@
 #include <linux/spi/spi.h>
 
 #include <drm/drm_atomic_helper.h>
+#include <drm/drm_client_setup.h>
 #include <drm/drm_drv.h>
 #include <drm/drm_fbdev_dma.h>
 #include <drm/drm_gem_atomic_helper.h>
@@ -264,6 +265,7 @@ static const struct drm_driver panel_mipi_dbi_driver = {
 	.driver_features	= DRIVER_GEM | DRIVER_MODESET | DRIVER_ATOMIC,
 	.fops			= &panel_mipi_dbi_fops,
 	DRM_GEM_DMA_DRIVER_OPS_VMAP,
+	DRM_FBDEV_DMA_DRIVER_OPS,
 	.debugfs_init		= mipi_dbi_debugfs_init,
 	.name			= "panel-mipi-dbi",
 	.desc			= "MIPI DBI compatible display panel",
@@ -388,7 +390,10 @@ static int panel_mipi_dbi_spi_probe(struct spi_device *spi)
 
 	spi_set_drvdata(spi, drm);
 
-	drm_fbdev_dma_setup(drm, 0);
+	if (bpp == 16)
+		drm_client_setup_with_fourcc(drm, DRM_FORMAT_RGB565);
+	else
+		drm_client_setup_with_fourcc(drm, DRM_FORMAT_RGB888);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/tiny/repaper.c b/drivers/gpu/drm/tiny/repaper.c
index 1f78aa3d26bb..768dfea15aec 100644
--- a/drivers/gpu/drm/tiny/repaper.c
+++ b/drivers/gpu/drm/tiny/repaper.c
@@ -455,7 +455,7 @@ static void repaper_frame_fixed_repeat(struct repaper_epd *epd, u8 fixed_value,
 				       enum repaper_stage stage)
 {
 	u64 start = local_clock();
-	u64 end = start + (epd->factored_stage_time * 1000 * 1000);
+	u64 end = start + ((u64)epd->factored_stage_time * 1000 * 1000);
 
 	do {
 		repaper_frame_fixed(epd, fixed_value, stage);
@@ -466,7 +466,7 @@ static void repaper_frame_data_repeat(struct repaper_epd *epd, const u8 *image,
 				      const u8 *mask, enum repaper_stage stage)
 {
 	u64 start = local_clock();
-	u64 end = start + (epd->factored_stage_time * 1000 * 1000);
+	u64 end = start + ((u64)epd->factored_stage_time * 1000 * 1000);
 
 	do {
 		repaper_frame_data(epd, image, mask, stage);
diff --git a/drivers/gpu/drm/tiny/simpledrm.c b/drivers/gpu/drm/tiny/simpledrm.c
index d19e10289428..07abaf27315f 100644
--- a/drivers/gpu/drm/tiny/simpledrm.c
+++ b/drivers/gpu/drm/tiny/simpledrm.c
@@ -284,7 +284,7 @@ static struct simpledrm_device *simpledrm_device_of_dev(struct drm_device *dev)
 
 static void simpledrm_device_release_clocks(void *res)
 {
-	struct simpledrm_device *sdev = simpledrm_device_of_dev(res);
+	struct simpledrm_device *sdev = res;
 	unsigned int i;
 
 	for (i = 0; i < sdev->clk_count; ++i) {
@@ -382,7 +382,7 @@ static int simpledrm_device_init_clocks(struct simpledrm_device *sdev)
 
 static void simpledrm_device_release_regulators(void *res)
 {
-	struct simpledrm_device *sdev = simpledrm_device_of_dev(res);
+	struct simpledrm_device *sdev = res;
 	unsigned int i;
 
 	for (i = 0; i < sdev->regulator_count; ++i) {
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index 3c07f4712d5c..b600be2a5c84 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -254,6 +254,13 @@ static int ttm_buffer_object_transfer(struct ttm_buffer_object *bo,
 	ret = dma_resv_trylock(&fbo->base.base._resv);
 	WARN_ON(!ret);
 
+	ret = dma_resv_reserve_fences(&fbo->base.base._resv, 1);
+	if (ret) {
+		dma_resv_unlock(&fbo->base.base._resv);
+		kfree(fbo);
+		return ret;
+	}
+
 	if (fbo->base.resource) {
 		ttm_resource_set_bo(fbo->base.resource, &fbo->base);
 		bo->resource = NULL;
@@ -262,12 +269,6 @@ static int ttm_buffer_object_transfer(struct ttm_buffer_object *bo,
 		fbo->base.bulk_move = NULL;
 	}
 
-	ret = dma_resv_reserve_fences(&fbo->base.base._resv, 1);
-	if (ret) {
-		kfree(fbo);
-		return ret;
-	}
-
 	ttm_bo_get(bo);
 	fbo->bo = bo;
 
diff --git a/drivers/gpu/drm/ttm/ttm_pool.c b/drivers/gpu/drm/ttm/ttm_pool.c
index 8504dbe19c1a..4ae9d33cf485 100644
--- a/drivers/gpu/drm/ttm/ttm_pool.c
+++ b/drivers/gpu/drm/ttm/ttm_pool.c
@@ -630,7 +630,6 @@ void ttm_pool_fini(struct ttm_pool *pool)
 }
 EXPORT_SYMBOL(ttm_pool_fini);
 
-/* As long as pages are available make sure to release at least one */
 static unsigned long ttm_pool_shrinker_scan(struct shrinker *shrink,
 					    struct shrink_control *sc)
 {
@@ -638,9 +637,12 @@ static unsigned long ttm_pool_shrinker_scan(struct shrinker *shrink,
 
 	do
 		num_freed += ttm_pool_shrink();
-	while (!num_freed && atomic_long_read(&allocated_pages));
+	while (num_freed < sc->nr_to_scan &&
+	       atomic_long_read(&allocated_pages));
 
-	return num_freed;
+	sc->nr_scanned = num_freed;
+
+	return num_freed ?: SHRINK_STOP;
 }
 
 /* Return the number of pages available or SHRINK_EMPTY if we have none */
diff --git a/drivers/gpu/drm/ttm/ttm_resource.c b/drivers/gpu/drm/ttm/ttm_resource.c
index 6d764ba88aab..53f258f39ceb 100644
--- a/drivers/gpu/drm/ttm/ttm_resource.c
+++ b/drivers/gpu/drm/ttm/ttm_resource.c
@@ -501,6 +501,9 @@ int ttm_resource_manager_evict_all(struct ttm_device *bdev,
 		cond_resched();
 	} while (!ret);
 
+	if (ret && ret != -ENOENT)
+		return ret;
+
 	spin_lock(&man->move_lock);
 	fence = dma_fence_get(man->move);
 	spin_unlock(&man->move_lock);
diff --git a/drivers/gpu/drm/udl/udl_drv.c b/drivers/gpu/drm/udl/udl_drv.c
index 280a09a6e2ad..0f712eb685ba 100644
--- a/drivers/gpu/drm/udl/udl_drv.c
+++ b/drivers/gpu/drm/udl/udl_drv.c
@@ -126,9 +126,9 @@ static void udl_usb_disconnect(struct usb_interface *interface)
 {
 	struct drm_device *dev = usb_get_intfdata(interface);
 
+	drm_dev_unplug(dev);
 	drm_kms_helper_poll_fini(dev);
 	udl_drop_usb(dev);
-	drm_dev_unplug(dev);
 }
 
 /*
diff --git a/drivers/gpu/drm/v3d/v3d_debugfs.c b/drivers/gpu/drm/v3d/v3d_debugfs.c
index 19e3ee7ac897..76816f2551c1 100644
--- a/drivers/gpu/drm/v3d/v3d_debugfs.c
+++ b/drivers/gpu/drm/v3d/v3d_debugfs.c
@@ -237,8 +237,8 @@ static int v3d_measure_clock(struct seq_file *m, void *unused)
 	if (v3d->ver >= 40) {
 		int cycle_count_reg = V3D_PCTR_CYCLE_COUNT(v3d->ver);
 		V3D_CORE_WRITE(core, V3D_V4_PCTR_0_SRC_0_3,
-			       V3D_SET_FIELD(cycle_count_reg,
-					     V3D_PCTR_S0));
+			       V3D_SET_FIELD_VER(cycle_count_reg,
+						 V3D_PCTR_S0, v3d->ver));
 		V3D_CORE_WRITE(core, V3D_V4_PCTR_0_CLR, 1);
 		V3D_CORE_WRITE(core, V3D_V4_PCTR_0_EN, 1);
 	} else {
diff --git a/drivers/gpu/drm/v3d/v3d_drv.c b/drivers/gpu/drm/v3d/v3d_drv.c
index d7ff1f5fa481..7c17108da7d2 100644
--- a/drivers/gpu/drm/v3d/v3d_drv.c
+++ b/drivers/gpu/drm/v3d/v3d_drv.c
@@ -286,11 +286,21 @@ static int v3d_platform_drm_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
+	v3d->clk = devm_clk_get_optional(dev, NULL);
+	if (IS_ERR(v3d->clk))
+		return dev_err_probe(dev, PTR_ERR(v3d->clk), "Failed to get V3D clock\n");
+
+	ret = clk_prepare_enable(v3d->clk);
+	if (ret) {
+		dev_err(&pdev->dev, "Couldn't enable the V3D clock\n");
+		return ret;
+	}
+
 	mmu_debug = V3D_READ(V3D_MMU_DEBUG_INFO);
 	mask = DMA_BIT_MASK(30 + V3D_GET_FIELD(mmu_debug, V3D_MMU_PA_WIDTH));
 	ret = dma_set_mask_and_coherent(dev, mask);
 	if (ret)
-		return ret;
+		goto clk_disable;
 
 	v3d->va_width = 30 + V3D_GET_FIELD(mmu_debug, V3D_MMU_VA_WIDTH);
 
@@ -310,28 +320,29 @@ static int v3d_platform_drm_probe(struct platform_device *pdev)
 		ret = PTR_ERR(v3d->reset);
 
 		if (ret == -EPROBE_DEFER)
-			return ret;
+			goto clk_disable;
 
 		v3d->reset = NULL;
 		ret = map_regs(v3d, &v3d->bridge_regs, "bridge");
 		if (ret) {
 			dev_err(dev,
 				"Failed to get reset control or bridge regs\n");
-			return ret;
+			goto clk_disable;
 		}
 	}
 
 	if (v3d->ver < 41) {
 		ret = map_regs(v3d, &v3d->gca_regs, "gca");
 		if (ret)
-			return ret;
+			goto clk_disable;
 	}
 
 	v3d->mmu_scratch = dma_alloc_wc(dev, 4096, &v3d->mmu_scratch_paddr,
 					GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO);
 	if (!v3d->mmu_scratch) {
 		dev_err(dev, "Failed to allocate MMU scratch page\n");
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto clk_disable;
 	}
 
 	ret = v3d_gem_init(drm);
@@ -360,6 +371,8 @@ gem_destroy:
 	v3d_gem_destroy(drm);
 dma_free:
 	dma_free_wc(dev, 4096, v3d->mmu_scratch, v3d->mmu_scratch_paddr);
+clk_disable:
+	clk_disable_unprepare(v3d->clk);
 	return ret;
 }
 
@@ -377,6 +390,8 @@ static void v3d_platform_drm_remove(struct platform_device *pdev)
 
 	dma_free_wc(v3d->drm.dev, 4096, v3d->mmu_scratch,
 		    v3d->mmu_scratch_paddr);
+
+	clk_disable_unprepare(v3d->clk);
 }
 
 static struct platform_driver v3d_platform_driver = {
diff --git a/drivers/gpu/drm/v3d/v3d_drv.h b/drivers/gpu/drm/v3d/v3d_drv.h
index 75b4725d49c7..d4b0549205c2 100644
--- a/drivers/gpu/drm/v3d/v3d_drv.h
+++ b/drivers/gpu/drm/v3d/v3d_drv.h
@@ -95,6 +95,12 @@ struct v3d_perfmon {
 	u64 values[] __counted_by(ncounters);
 };
 
+enum v3d_irq {
+	V3D_CORE_IRQ,
+	V3D_HUB_IRQ,
+	V3D_MAX_IRQS,
+};
+
 struct v3d_dev {
 	struct drm_device drm;
 
@@ -106,6 +112,8 @@ struct v3d_dev {
 
 	bool single_irq_line;
 
+	int irq[V3D_MAX_IRQS];
+
 	struct v3d_perfmon_info perfmon_info;
 
 	void __iomem *hub_regs;
diff --git a/drivers/gpu/drm/v3d/v3d_gem.c b/drivers/gpu/drm/v3d/v3d_gem.c
index da8faf3b9011..6b6ba7a68fcb 100644
--- a/drivers/gpu/drm/v3d/v3d_gem.c
+++ b/drivers/gpu/drm/v3d/v3d_gem.c
@@ -118,6 +118,8 @@ v3d_reset(struct v3d_dev *v3d)
 	if (false)
 		v3d_idle_axi(v3d, 0);
 
+	v3d_irq_disable(v3d);
+
 	v3d_idle_gca(v3d);
 	v3d_reset_v3d(v3d);
 
diff --git a/drivers/gpu/drm/v3d/v3d_irq.c b/drivers/gpu/drm/v3d/v3d_irq.c
index da203045df9b..b98e1a4b33c7 100644
--- a/drivers/gpu/drm/v3d/v3d_irq.c
+++ b/drivers/gpu/drm/v3d/v3d_irq.c
@@ -107,8 +107,10 @@ v3d_irq(int irq, void *arg)
 
 		v3d_job_update_stats(&v3d->bin_job->base, V3D_BIN);
 		trace_v3d_bcl_irq(&v3d->drm, fence->seqno);
-		dma_fence_signal(&fence->base);
+
 		v3d->bin_job = NULL;
+		dma_fence_signal(&fence->base);
+
 		status = IRQ_HANDLED;
 	}
 
@@ -118,8 +120,10 @@ v3d_irq(int irq, void *arg)
 
 		v3d_job_update_stats(&v3d->render_job->base, V3D_RENDER);
 		trace_v3d_rcl_irq(&v3d->drm, fence->seqno);
-		dma_fence_signal(&fence->base);
+
 		v3d->render_job = NULL;
+		dma_fence_signal(&fence->base);
+
 		status = IRQ_HANDLED;
 	}
 
@@ -129,8 +133,10 @@ v3d_irq(int irq, void *arg)
 
 		v3d_job_update_stats(&v3d->csd_job->base, V3D_CSD);
 		trace_v3d_csd_irq(&v3d->drm, fence->seqno);
-		dma_fence_signal(&fence->base);
+
 		v3d->csd_job = NULL;
+		dma_fence_signal(&fence->base);
+
 		status = IRQ_HANDLED;
 	}
 
@@ -167,8 +173,10 @@ v3d_hub_irq(int irq, void *arg)
 
 		v3d_job_update_stats(&v3d->tfu_job->base, V3D_TFU);
 		trace_v3d_tfu_irq(&v3d->drm, fence->seqno);
-		dma_fence_signal(&fence->base);
+
 		v3d->tfu_job = NULL;
+		dma_fence_signal(&fence->base);
+
 		status = IRQ_HANDLED;
 	}
 
@@ -220,7 +228,7 @@ v3d_hub_irq(int irq, void *arg)
 int
 v3d_irq_init(struct v3d_dev *v3d)
 {
-	int irq1, ret, core;
+	int irq, ret, core;
 
 	INIT_WORK(&v3d->overflow_mem_work, v3d_overflow_mem_work);
 
@@ -231,17 +239,24 @@ v3d_irq_init(struct v3d_dev *v3d)
 		V3D_CORE_WRITE(core, V3D_CTL_INT_CLR, V3D_CORE_IRQS(v3d->ver));
 	V3D_WRITE(V3D_HUB_INT_CLR, V3D_HUB_IRQS(v3d->ver));
 
-	irq1 = platform_get_irq_optional(v3d_to_pdev(v3d), 1);
-	if (irq1 == -EPROBE_DEFER)
-		return irq1;
-	if (irq1 > 0) {
-		ret = devm_request_irq(v3d->drm.dev, irq1,
+	irq = platform_get_irq_optional(v3d_to_pdev(v3d), 1);
+	if (irq == -EPROBE_DEFER)
+		return irq;
+	if (irq > 0) {
+		v3d->irq[V3D_CORE_IRQ] = irq;
+
+		ret = devm_request_irq(v3d->drm.dev, v3d->irq[V3D_CORE_IRQ],
 				       v3d_irq, IRQF_SHARED,
 				       "v3d_core0", v3d);
 		if (ret)
 			goto fail;
-		ret = devm_request_irq(v3d->drm.dev,
-				       platform_get_irq(v3d_to_pdev(v3d), 0),
+
+		irq = platform_get_irq(v3d_to_pdev(v3d), 0);
+		if (irq < 0)
+			return irq;
+		v3d->irq[V3D_HUB_IRQ] = irq;
+
+		ret = devm_request_irq(v3d->drm.dev, v3d->irq[V3D_HUB_IRQ],
 				       v3d_hub_irq, IRQF_SHARED,
 				       "v3d_hub", v3d);
 		if (ret)
@@ -249,8 +264,12 @@ v3d_irq_init(struct v3d_dev *v3d)
 	} else {
 		v3d->single_irq_line = true;
 
-		ret = devm_request_irq(v3d->drm.dev,
-				       platform_get_irq(v3d_to_pdev(v3d), 0),
+		irq = platform_get_irq(v3d_to_pdev(v3d), 0);
+		if (irq < 0)
+			return irq;
+		v3d->irq[V3D_CORE_IRQ] = irq;
+
+		ret = devm_request_irq(v3d->drm.dev, v3d->irq[V3D_CORE_IRQ],
 				       v3d_irq, IRQF_SHARED,
 				       "v3d", v3d);
 		if (ret)
@@ -291,6 +310,12 @@ v3d_irq_disable(struct v3d_dev *v3d)
 		V3D_CORE_WRITE(core, V3D_CTL_INT_MSK_SET, ~0);
 	V3D_WRITE(V3D_HUB_INT_MSK_SET, ~0);
 
+	/* Finish any interrupt handler still in flight. */
+	for (int i = 0; i < V3D_MAX_IRQS; i++) {
+		if (v3d->irq[i])
+			synchronize_irq(v3d->irq[i]);
+	}
+
 	/* Clear any pending interrupts we might have left. */
 	for (core = 0; core < v3d->cores; core++)
 		V3D_CORE_WRITE(core, V3D_CTL_INT_CLR, V3D_CORE_IRQS(v3d->ver));
diff --git a/drivers/gpu/drm/v3d/v3d_perfmon.c b/drivers/gpu/drm/v3d/v3d_perfmon.c
index 6ee56cbd3f1b..1abfd738a601 100644
--- a/drivers/gpu/drm/v3d/v3d_perfmon.c
+++ b/drivers/gpu/drm/v3d/v3d_perfmon.c
@@ -240,17 +240,18 @@ void v3d_perfmon_start(struct v3d_dev *v3d, struct v3d_perfmon *perfmon)
 
 	for (i = 0; i < ncounters; i++) {
 		u32 source = i / 4;
-		u32 channel = V3D_SET_FIELD(perfmon->counters[i], V3D_PCTR_S0);
+		u32 channel = V3D_SET_FIELD_VER(perfmon->counters[i], V3D_PCTR_S0,
+						v3d->ver);
 
 		i++;
-		channel |= V3D_SET_FIELD(i < ncounters ? perfmon->counters[i] : 0,
-					 V3D_PCTR_S1);
+		channel |= V3D_SET_FIELD_VER(i < ncounters ? perfmon->counters[i] : 0,
+					     V3D_PCTR_S1, v3d->ver);
 		i++;
-		channel |= V3D_SET_FIELD(i < ncounters ? perfmon->counters[i] : 0,
-					 V3D_PCTR_S2);
+		channel |= V3D_SET_FIELD_VER(i < ncounters ? perfmon->counters[i] : 0,
+					     V3D_PCTR_S2, v3d->ver);
 		i++;
-		channel |= V3D_SET_FIELD(i < ncounters ? perfmon->counters[i] : 0,
-					 V3D_PCTR_S3);
+		channel |= V3D_SET_FIELD_VER(i < ncounters ? perfmon->counters[i] : 0,
+					     V3D_PCTR_S3, v3d->ver);
 		V3D_CORE_WRITE(0, V3D_V4_PCTR_0_SRC_X(source), channel);
 	}
 
@@ -383,6 +384,7 @@ int v3d_perfmon_destroy_ioctl(struct drm_device *dev, void *data,
 {
 	struct v3d_file_priv *v3d_priv = file_priv->driver_priv;
 	struct drm_v3d_perfmon_destroy *req = data;
+	struct v3d_dev *v3d = v3d_priv->v3d;
 	struct v3d_perfmon *perfmon;
 
 	mutex_lock(&v3d_priv->perfmon.lock);
@@ -392,6 +394,10 @@ int v3d_perfmon_destroy_ioctl(struct drm_device *dev, void *data,
 	if (!perfmon)
 		return -EINVAL;
 
+	/* If the active perfmon is being destroyed, stop it first */
+	if (perfmon == v3d->active_perfmon)
+		v3d_perfmon_stop(v3d, perfmon, false);
+
 	v3d_perfmon_put(perfmon);
 
 	return 0;
diff --git a/drivers/gpu/drm/v3d/v3d_regs.h b/drivers/gpu/drm/v3d/v3d_regs.h
index 1b1a62ad9585..6da3c69082bd 100644
--- a/drivers/gpu/drm/v3d/v3d_regs.h
+++ b/drivers/gpu/drm/v3d/v3d_regs.h
@@ -15,6 +15,14 @@
 		fieldval & field##_MASK;				\
 	 })
 
+#define V3D_SET_FIELD_VER(value, field, ver)				\
+	({								\
+		typeof(ver) _ver = (ver);				\
+		u32 fieldval = (value) << field##_SHIFT(_ver);		\
+		WARN_ON((fieldval & ~field##_MASK(_ver)) != 0);		\
+		fieldval & field##_MASK(_ver);				\
+	 })
+
 #define V3D_GET_FIELD(word, field) (((word) & field##_MASK) >>		\
 				    field##_SHIFT)
 
@@ -354,18 +362,15 @@
 #define V3D_V4_PCTR_0_SRC_28_31                        0x0067c
 #define V3D_V4_PCTR_0_SRC_X(x)                         (V3D_V4_PCTR_0_SRC_0_3 + \
 							4 * (x))
-# define V3D_PCTR_S0_MASK                              V3D_MASK(6, 0)
-# define V3D_V7_PCTR_S0_MASK                           V3D_MASK(7, 0)
-# define V3D_PCTR_S0_SHIFT                             0
-# define V3D_PCTR_S1_MASK                              V3D_MASK(14, 8)
-# define V3D_V7_PCTR_S1_MASK                           V3D_MASK(15, 8)
-# define V3D_PCTR_S1_SHIFT                             8
-# define V3D_PCTR_S2_MASK                              V3D_MASK(22, 16)
-# define V3D_V7_PCTR_S2_MASK                           V3D_MASK(23, 16)
-# define V3D_PCTR_S2_SHIFT                             16
-# define V3D_PCTR_S3_MASK                              V3D_MASK(30, 24)
-# define V3D_V7_PCTR_S3_MASK                           V3D_MASK(31, 24)
-# define V3D_PCTR_S3_SHIFT                             24
+# define V3D_PCTR_S0_MASK(ver) (((ver) >= 71) ? V3D_MASK(7, 0) : V3D_MASK(6, 0))
+# define V3D_PCTR_S0_SHIFT(ver)                        0
+# define V3D_PCTR_S1_MASK(ver) (((ver) >= 71) ? V3D_MASK(15, 8) : V3D_MASK(14, 8))
+# define V3D_PCTR_S1_SHIFT(ver)                        8
+# define V3D_PCTR_S2_MASK(ver) (((ver) >= 71) ? V3D_MASK(23, 16) : V3D_MASK(22, 16))
+# define V3D_PCTR_S2_SHIFT(ver)                        16
+# define V3D_PCTR_S3_MASK(ver) (((ver) >= 71) ? V3D_MASK(31, 24) : V3D_MASK(30, 24))
+# define V3D_PCTR_S3_SHIFT(ver)                        24
+
 #define V3D_PCTR_CYCLE_COUNT(ver) ((ver >= 71) ? 0 : 32)
 
 /* Output values of the counters. */
diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c
index 4f935f1d50a9..c9c88d3ad669 100644
--- a/drivers/gpu/drm/v3d/v3d_sched.c
+++ b/drivers/gpu/drm/v3d/v3d_sched.c
@@ -191,7 +191,6 @@ v3d_job_update_stats(struct v3d_job *job, enum v3d_queue queue)
 	struct v3d_dev *v3d = job->v3d;
 	struct v3d_file_priv *file = job->file->driver_priv;
 	struct v3d_stats *global_stats = &v3d->queue[queue].stats;
-	struct v3d_stats *local_stats = &file->stats[queue];
 	u64 now = local_clock();
 	unsigned long flags;
 
@@ -201,7 +200,12 @@ v3d_job_update_stats(struct v3d_job *job, enum v3d_queue queue)
 	else
 		preempt_disable();
 
-	v3d_stats_update(local_stats, now);
+	/* Don't update the local stats if the file context has already closed */
+	if (file)
+		v3d_stats_update(&file->stats[queue], now);
+	else
+		drm_dbg(&v3d->drm, "The file descriptor was closed before job completion\n");
+
 	v3d_stats_update(global_stats, now);
 
 	if (IS_ENABLED(CONFIG_LOCKDEP))
@@ -319,11 +323,15 @@ v3d_tfu_job_run(struct drm_sched_job *sched_job)
 	struct drm_device *dev = &v3d->drm;
 	struct dma_fence *fence;
 
+	if (unlikely(job->base.base.s_fence->finished.error))
+		return NULL;
+
+	v3d->tfu_job = job;
+
 	fence = v3d_fence_create(v3d, V3D_TFU);
 	if (IS_ERR(fence))
 		return NULL;
 
-	v3d->tfu_job = job;
 	if (job->base.irq_fence)
 		dma_fence_put(job->base.irq_fence);
 	job->base.irq_fence = dma_fence_get(fence);
@@ -361,6 +369,9 @@ v3d_csd_job_run(struct drm_sched_job *sched_job)
 	struct dma_fence *fence;
 	int i, csd_cfg0_reg;
 
+	if (unlikely(job->base.base.s_fence->finished.error))
+		return NULL;
+
 	v3d->csd_job = job;
 
 	v3d_invalidate_caches(v3d);
@@ -403,7 +414,8 @@ v3d_rewrite_csd_job_wg_counts_from_indirect(struct v3d_cpu_job *job)
 	struct v3d_bo *bo = to_v3d_bo(job->base.bo[0]);
 	struct v3d_bo *indirect = to_v3d_bo(indirect_csd->indirect);
 	struct drm_v3d_submit_csd *args = &indirect_csd->job->args;
-	u32 *wg_counts;
+	struct v3d_dev *v3d = job->base.v3d;
+	u32 num_batches, *wg_counts;
 
 	v3d_get_bo_vaddr(bo);
 	v3d_get_bo_vaddr(indirect);
@@ -416,8 +428,17 @@ v3d_rewrite_csd_job_wg_counts_from_indirect(struct v3d_cpu_job *job)
 	args->cfg[0] = wg_counts[0] << V3D_CSD_CFG012_WG_COUNT_SHIFT;
 	args->cfg[1] = wg_counts[1] << V3D_CSD_CFG012_WG_COUNT_SHIFT;
 	args->cfg[2] = wg_counts[2] << V3D_CSD_CFG012_WG_COUNT_SHIFT;
-	args->cfg[4] = DIV_ROUND_UP(indirect_csd->wg_size, 16) *
-		       (wg_counts[0] * wg_counts[1] * wg_counts[2]) - 1;
+
+	num_batches = DIV_ROUND_UP(indirect_csd->wg_size, 16) *
+		      (wg_counts[0] * wg_counts[1] * wg_counts[2]);
+
+	/* V3D 7.1.6 and later don't subtract 1 from the number of batches */
+	if (v3d->ver < 71 || (v3d->ver == 71 && v3d->rev < 6))
+		args->cfg[4] = num_batches - 1;
+	else
+		args->cfg[4] = num_batches;
+
+	WARN_ON(args->cfg[4] == ~0);
 
 	for (int i = 0; i < 3; i++) {
 		/* 0xffffffff indicates that the uniform rewrite is not needed */
@@ -711,11 +732,16 @@ v3d_gpu_reset_for_timeout(struct v3d_dev *v3d, struct drm_sched_job *sched_job)
 	return DRM_GPU_SCHED_STAT_NOMINAL;
 }
 
-/* If the current address or return address have changed, then the GPU
- * has probably made progress and we should delay the reset.  This
- * could fail if the GPU got in an infinite loop in the CL, but that
- * is pretty unlikely outside of an i-g-t testcase.
- */
+static void
+v3d_sched_skip_reset(struct drm_sched_job *sched_job)
+{
+	struct drm_gpu_scheduler *sched = sched_job->sched;
+
+	spin_lock(&sched->job_list_lock);
+	list_add(&sched_job->list, &sched->pending_list);
+	spin_unlock(&sched->job_list_lock);
+}
+
 static enum drm_gpu_sched_stat
 v3d_cl_job_timedout(struct drm_sched_job *sched_job, enum v3d_queue q,
 		    u32 *timedout_ctca, u32 *timedout_ctra)
@@ -725,9 +751,16 @@ v3d_cl_job_timedout(struct drm_sched_job *sched_job, enum v3d_queue q,
 	u32 ctca = V3D_CORE_READ(0, V3D_CLE_CTNCA(q));
 	u32 ctra = V3D_CORE_READ(0, V3D_CLE_CTNRA(q));
 
+	/* If the current address or return address have changed, then the GPU
+	 * has probably made progress and we should delay the reset. This
+	 * could fail if the GPU got in an infinite loop in the CL, but that
+	 * is pretty unlikely outside of an i-g-t testcase.
+	 */
 	if (*timedout_ctca != ctca || *timedout_ctra != ctra) {
 		*timedout_ctca = ctca;
 		*timedout_ctra = ctra;
+
+		v3d_sched_skip_reset(sched_job);
 		return DRM_GPU_SCHED_STAT_NOMINAL;
 	}
 
@@ -767,11 +800,13 @@ v3d_csd_job_timedout(struct drm_sched_job *sched_job)
 	struct v3d_dev *v3d = job->base.v3d;
 	u32 batches = V3D_CORE_READ(0, V3D_CSD_CURRENT_CFG4(v3d->ver));
 
-	/* If we've made progress, skip reset and let the timer get
-	 * rearmed.
+	/* If we've made progress, skip reset, add the job to the pending
+	 * list, and let the timer get rearmed.
 	 */
 	if (job->timedout_batches != batches) {
 		job->timedout_batches = batches;
+
+		v3d_sched_skip_reset(sched_job);
 		return DRM_GPU_SCHED_STAT_NOMINAL;
 	}
 
diff --git a/drivers/gpu/drm/vc4/tests/vc4_mock_output.c b/drivers/gpu/drm/vc4/tests/vc4_mock_output.c
index e70d7c3076ac..f0ddc223c1f8 100644
--- a/drivers/gpu/drm/vc4/tests/vc4_mock_output.c
+++ b/drivers/gpu/drm/vc4/tests/vc4_mock_output.c
@@ -75,24 +75,30 @@ int vc4_mock_atomic_add_output(struct kunit *test,
 	int ret;
 
 	encoder = vc4_find_encoder_by_type(drm, type);
-	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, encoder);
+	if (!encoder)
+		return -ENODEV;
 
 	crtc = vc4_find_crtc_for_encoder(test, drm, encoder);
-	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, crtc);
+	if (!crtc)
+		return -ENODEV;
 
 	output = encoder_to_vc4_dummy_output(encoder);
 	conn = &output->connector;
 	conn_state = drm_atomic_get_connector_state(state, conn);
-	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, conn_state);
+	if (IS_ERR(conn_state))
+		return PTR_ERR(conn_state);
 
 	ret = drm_atomic_set_crtc_for_connector(conn_state, crtc);
-	KUNIT_EXPECT_EQ(test, ret, 0);
+	if (ret)
+		return ret;
 
 	crtc_state = drm_atomic_get_crtc_state(state, crtc);
-	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, crtc_state);
+	if (IS_ERR(crtc_state))
+		return PTR_ERR(crtc_state);
 
 	ret = drm_atomic_set_mode_for_crtc(crtc_state, &default_mode);
-	KUNIT_EXPECT_EQ(test, ret, 0);
+	if (ret)
+		return ret;
 
 	crtc_state->active = true;
 
@@ -113,26 +119,32 @@ int vc4_mock_atomic_del_output(struct kunit *test,
 	int ret;
 
 	encoder = vc4_find_encoder_by_type(drm, type);
-	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, encoder);
+	if (!encoder)
+		return -ENODEV;
 
 	crtc = vc4_find_crtc_for_encoder(test, drm, encoder);
-	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, crtc);
+	if (!crtc)
+		return -ENODEV;
 
 	crtc_state = drm_atomic_get_crtc_state(state, crtc);
-	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, crtc_state);
+	if (IS_ERR(crtc_state))
+		return PTR_ERR(crtc_state);
 
 	crtc_state->active = false;
 
 	ret = drm_atomic_set_mode_for_crtc(crtc_state, NULL);
-	KUNIT_ASSERT_EQ(test, ret, 0);
+	if (ret)
+		return ret;
 
 	output = encoder_to_vc4_dummy_output(encoder);
 	conn = &output->connector;
 	conn_state = drm_atomic_get_connector_state(state, conn);
-	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, conn_state);
+	if (IS_ERR(conn_state))
+		return PTR_ERR(conn_state);
 
 	ret = drm_atomic_set_crtc_for_connector(conn_state, NULL);
-	KUNIT_ASSERT_EQ(test, ret, 0);
+	if (ret)
+		return ret;
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c
index 7e0a5ea7ab85..6b83d02b5d62 100644
--- a/drivers/gpu/drm/vc4/vc4_hdmi.c
+++ b/drivers/gpu/drm/vc4/vc4_hdmi.c
@@ -2192,9 +2192,9 @@ static int vc4_hdmi_audio_get_eld(struct device *dev, void *data,
 	struct vc4_hdmi *vc4_hdmi = dev_get_drvdata(dev);
 	struct drm_connector *connector = &vc4_hdmi->connector;
 
-	mutex_lock(&vc4_hdmi->mutex);
+	mutex_lock(&connector->eld_mutex);
 	memcpy(buf, connector->eld, min(sizeof(connector->eld), len));
-	mutex_unlock(&vc4_hdmi->mutex);
+	mutex_unlock(&connector->eld_mutex);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.h b/drivers/gpu/drm/virtio/virtgpu_drv.h
index 64c236169db8..5dc8eeaf7123 100644
--- a/drivers/gpu/drm/virtio/virtgpu_drv.h
+++ b/drivers/gpu/drm/virtio/virtgpu_drv.h
@@ -194,6 +194,13 @@ struct virtio_gpu_framebuffer {
 #define to_virtio_gpu_framebuffer(x) \
 	container_of(x, struct virtio_gpu_framebuffer, base)
 
+struct virtio_gpu_plane_state {
+	struct drm_plane_state base;
+	struct virtio_gpu_fence *fence;
+};
+#define to_virtio_gpu_plane_state(x) \
+	container_of(x, struct virtio_gpu_plane_state, base)
+
 struct virtio_gpu_queue {
 	struct virtqueue *vq;
 	spinlock_t qlock;
diff --git a/drivers/gpu/drm/virtio/virtgpu_plane.c b/drivers/gpu/drm/virtio/virtgpu_plane.c
index a72a2dbda031..7acd38b962c6 100644
--- a/drivers/gpu/drm/virtio/virtgpu_plane.c
+++ b/drivers/gpu/drm/virtio/virtgpu_plane.c
@@ -66,11 +66,28 @@ uint32_t virtio_gpu_translate_format(uint32_t drm_fourcc)
 	return format;
 }
 
+static struct
+drm_plane_state *virtio_gpu_plane_duplicate_state(struct drm_plane *plane)
+{
+	struct virtio_gpu_plane_state *new;
+
+	if (WARN_ON(!plane->state))
+		return NULL;
+
+	new = kzalloc(sizeof(*new), GFP_KERNEL);
+	if (!new)
+		return NULL;
+
+	__drm_atomic_helper_plane_duplicate_state(plane, &new->base);
+
+	return &new->base;
+}
+
 static const struct drm_plane_funcs virtio_gpu_plane_funcs = {
 	.update_plane		= drm_atomic_helper_update_plane,
 	.disable_plane		= drm_atomic_helper_disable_plane,
 	.reset			= drm_atomic_helper_plane_reset,
-	.atomic_duplicate_state = drm_atomic_helper_plane_duplicate_state,
+	.atomic_duplicate_state = virtio_gpu_plane_duplicate_state,
 	.atomic_destroy_state	= drm_atomic_helper_plane_destroy_state,
 };
 
@@ -138,11 +155,13 @@ static void virtio_gpu_resource_flush(struct drm_plane *plane,
 	struct drm_device *dev = plane->dev;
 	struct virtio_gpu_device *vgdev = dev->dev_private;
 	struct virtio_gpu_framebuffer *vgfb;
+	struct virtio_gpu_plane_state *vgplane_st;
 	struct virtio_gpu_object *bo;
 
 	vgfb = to_virtio_gpu_framebuffer(plane->state->fb);
+	vgplane_st = to_virtio_gpu_plane_state(plane->state);
 	bo = gem_to_virtio_gpu_obj(vgfb->base.obj[0]);
-	if (vgfb->fence) {
+	if (vgplane_st->fence) {
 		struct virtio_gpu_object_array *objs;
 
 		objs = virtio_gpu_array_alloc(1);
@@ -151,13 +170,11 @@ static void virtio_gpu_resource_flush(struct drm_plane *plane,
 		virtio_gpu_array_add_obj(objs, vgfb->base.obj[0]);
 		virtio_gpu_array_lock_resv(objs);
 		virtio_gpu_cmd_resource_flush(vgdev, bo->hw_res_handle, x, y,
-					      width, height, objs, vgfb->fence);
+					      width, height, objs,
+					      vgplane_st->fence);
 		virtio_gpu_notify(vgdev);
-
-		dma_fence_wait_timeout(&vgfb->fence->f, true,
+		dma_fence_wait_timeout(&vgplane_st->fence->f, true,
 				       msecs_to_jiffies(50));
-		dma_fence_put(&vgfb->fence->f);
-		vgfb->fence = NULL;
 	} else {
 		virtio_gpu_cmd_resource_flush(vgdev, bo->hw_res_handle, x, y,
 					      width, height, NULL, NULL);
@@ -247,20 +264,23 @@ static int virtio_gpu_plane_prepare_fb(struct drm_plane *plane,
 	struct drm_device *dev = plane->dev;
 	struct virtio_gpu_device *vgdev = dev->dev_private;
 	struct virtio_gpu_framebuffer *vgfb;
+	struct virtio_gpu_plane_state *vgplane_st;
 	struct virtio_gpu_object *bo;
 
 	if (!new_state->fb)
 		return 0;
 
 	vgfb = to_virtio_gpu_framebuffer(new_state->fb);
+	vgplane_st = to_virtio_gpu_plane_state(new_state);
 	bo = gem_to_virtio_gpu_obj(vgfb->base.obj[0]);
 	if (!bo || (plane->type == DRM_PLANE_TYPE_PRIMARY && !bo->guest_blob))
 		return 0;
 
-	if (bo->dumb && (plane->state->fb != new_state->fb)) {
-		vgfb->fence = virtio_gpu_fence_alloc(vgdev, vgdev->fence_drv.context,
+	if (bo->dumb) {
+		vgplane_st->fence = virtio_gpu_fence_alloc(vgdev,
+						     vgdev->fence_drv.context,
 						     0);
-		if (!vgfb->fence)
+		if (!vgplane_st->fence)
 			return -ENOMEM;
 	}
 
@@ -270,15 +290,15 @@ static int virtio_gpu_plane_prepare_fb(struct drm_plane *plane,
 static void virtio_gpu_plane_cleanup_fb(struct drm_plane *plane,
 					struct drm_plane_state *state)
 {
-	struct virtio_gpu_framebuffer *vgfb;
+	struct virtio_gpu_plane_state *vgplane_st;
 
 	if (!state->fb)
 		return;
 
-	vgfb = to_virtio_gpu_framebuffer(state->fb);
-	if (vgfb->fence) {
-		dma_fence_put(&vgfb->fence->f);
-		vgfb->fence = NULL;
+	vgplane_st = to_virtio_gpu_plane_state(state);
+	if (vgplane_st->fence) {
+		dma_fence_put(&vgplane_st->fence->f);
+		vgplane_st->fence = NULL;
 	}
 }
 
@@ -291,6 +311,7 @@ static void virtio_gpu_cursor_plane_update(struct drm_plane *plane,
 	struct virtio_gpu_device *vgdev = dev->dev_private;
 	struct virtio_gpu_output *output = NULL;
 	struct virtio_gpu_framebuffer *vgfb;
+	struct virtio_gpu_plane_state *vgplane_st;
 	struct virtio_gpu_object *bo = NULL;
 	uint32_t handle;
 
@@ -303,6 +324,7 @@ static void virtio_gpu_cursor_plane_update(struct drm_plane *plane,
 
 	if (plane->state->fb) {
 		vgfb = to_virtio_gpu_framebuffer(plane->state->fb);
+		vgplane_st = to_virtio_gpu_plane_state(plane->state);
 		bo = gem_to_virtio_gpu_obj(vgfb->base.obj[0]);
 		handle = bo->hw_res_handle;
 	} else {
@@ -322,11 +344,9 @@ static void virtio_gpu_cursor_plane_update(struct drm_plane *plane,
 			(vgdev, 0,
 			 plane->state->crtc_w,
 			 plane->state->crtc_h,
-			 0, 0, objs, vgfb->fence);
+			 0, 0, objs, vgplane_st->fence);
 		virtio_gpu_notify(vgdev);
-		dma_fence_wait(&vgfb->fence->f, true);
-		dma_fence_put(&vgfb->fence->f);
-		vgfb->fence = NULL;
+		dma_fence_wait(&vgplane_st->fence->f, true);
 	}
 
 	if (plane->state->fb != old_state->fb) {
diff --git a/drivers/gpu/drm/vkms/vkms_composer.c b/drivers/gpu/drm/vkms/vkms_composer.c
index e7441b227b3c..3d6785d081f2 100644
--- a/drivers/gpu/drm/vkms/vkms_composer.c
+++ b/drivers/gpu/drm/vkms/vkms_composer.c
@@ -98,7 +98,7 @@ static u16 lerp_u16(u16 a, u16 b, s64 t)
 
 	s64 delta = drm_fixp_mul(b_fp - a_fp,  t);
 
-	return drm_fixp2int(a_fp + delta);
+	return drm_fixp2int_round(a_fp + delta);
 }
 
 static s64 get_lut_index(const struct vkms_color_lut *lut, u16 channel_value)
diff --git a/drivers/gpu/drm/vkms/vkms_crtc.c b/drivers/gpu/drm/vkms/vkms_crtc.c
index 40b4d084e3ce..91b589a497d0 100644
--- a/drivers/gpu/drm/vkms/vkms_crtc.c
+++ b/drivers/gpu/drm/vkms/vkms_crtc.c
@@ -198,7 +198,7 @@ static int vkms_crtc_atomic_check(struct drm_crtc *crtc,
 		i++;
 	}
 
-	vkms_state->active_planes = kcalloc(i, sizeof(plane), GFP_KERNEL);
+	vkms_state->active_planes = kcalloc(i, sizeof(*vkms_state->active_planes), GFP_KERNEL);
 	if (!vkms_state->active_planes)
 		return -ENOMEM;
 	vkms_state->num_active_planes = i;
diff --git a/drivers/gpu/drm/vkms/vkms_drv.c b/drivers/gpu/drm/vkms/vkms_drv.c
index 0c1a713b7b7b..be642ee739c4 100644
--- a/drivers/gpu/drm/vkms/vkms_drv.c
+++ b/drivers/gpu/drm/vkms/vkms_drv.c
@@ -245,17 +245,19 @@ static int __init vkms_init(void)
 	if (!config)
 		return -ENOMEM;
 
-	default_config = config;
-
 	config->cursor = enable_cursor;
 	config->writeback = enable_writeback;
 	config->overlay = enable_overlay;
 
 	ret = vkms_create(config);
-	if (ret)
+	if (ret) {
 		kfree(config);
+		return ret;
+	}
 
-	return ret;
+	default_config = config;
+
+	return 0;
 }
 
 static void vkms_destroy(struct vkms_config *config)
@@ -279,9 +281,10 @@ static void vkms_destroy(struct vkms_config *config)
 
 static void __exit vkms_exit(void)
 {
-	if (default_config->dev)
-		vkms_destroy(default_config);
+	if (!default_config)
+		return;
 
+	vkms_destroy(default_config);
 	kfree(default_config);
 }
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c
index 183cda50094c..e8e49f13cfa2 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c
@@ -51,11 +51,13 @@ static void vmw_bo_release(struct vmw_bo *vbo)
 			mutex_lock(&res->dev_priv->cmdbuf_mutex);
 			(void)vmw_resource_reserve(res, false, true);
 			vmw_resource_mob_detach(res);
+			if (res->dirty)
+				res->func->dirty_free(res);
 			if (res->coherent)
 				vmw_bo_dirty_release(res->guest_memory_bo);
 			res->guest_memory_bo = NULL;
 			res->guest_memory_offset = 0;
-			vmw_resource_unreserve(res, false, false, false, NULL,
+			vmw_resource_unreserve(res, true, false, false, NULL,
 					       0);
 			mutex_unlock(&res->dev_priv->cmdbuf_mutex);
 		}
@@ -73,9 +75,9 @@ static void vmw_bo_free(struct ttm_buffer_object *bo)
 {
 	struct vmw_bo *vbo = to_vmw_bo(&bo->base);
 
-	WARN_ON(vbo->dirty);
 	WARN_ON(!RB_EMPTY_ROOT(&vbo->res_tree));
 	vmw_bo_release(vbo);
+	WARN_ON(vbo->dirty);
 	kfree(vbo);
 }
 
@@ -849,9 +851,9 @@ void vmw_bo_placement_set_default_accelerated(struct vmw_bo *bo)
 	vmw_bo_placement_set(bo, domain, domain);
 }
 
-void vmw_bo_add_detached_resource(struct vmw_bo *vbo, struct vmw_resource *res)
+int vmw_bo_add_detached_resource(struct vmw_bo *vbo, struct vmw_resource *res)
 {
-	xa_store(&vbo->detached_resources, (unsigned long)res, res, GFP_KERNEL);
+	return xa_err(xa_store(&vbo->detached_resources, (unsigned long)res, res, GFP_KERNEL));
 }
 
 void vmw_bo_del_detached_resource(struct vmw_bo *vbo, struct vmw_resource *res)
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.h b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.h
index c21ba7ff7736..940c0a0b9c45 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.h
@@ -142,7 +142,7 @@ void vmw_bo_move_notify(struct ttm_buffer_object *bo,
 			struct ttm_resource *mem);
 void vmw_bo_swap_notify(struct ttm_buffer_object *bo);
 
-void vmw_bo_add_detached_resource(struct vmw_bo *vbo, struct vmw_resource *res);
+int vmw_bo_add_detached_resource(struct vmw_bo *vbo, struct vmw_resource *res);
 void vmw_bo_del_detached_resource(struct vmw_bo *vbo, struct vmw_resource *res);
 struct vmw_surface *vmw_bo_surface(struct vmw_bo *vbo);
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
index 2e52d73eba48..ea741bc4ac3f 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
@@ -4086,6 +4086,23 @@ static int vmw_execbuf_tie_context(struct vmw_private *dev_priv,
 	return 0;
 }
 
+/*
+ * DMA fence callback to remove a seqno_waiter
+ */
+struct seqno_waiter_rm_context {
+	struct dma_fence_cb base;
+	struct vmw_private *dev_priv;
+};
+
+static void seqno_waiter_rm_cb(struct dma_fence *f, struct dma_fence_cb *cb)
+{
+	struct seqno_waiter_rm_context *ctx =
+		container_of(cb, struct seqno_waiter_rm_context, base);
+
+	vmw_seqno_waiter_remove(ctx->dev_priv);
+	kfree(ctx);
+}
+
 int vmw_execbuf_process(struct drm_file *file_priv,
 			struct vmw_private *dev_priv,
 			void __user *user_commands, void *kernel_commands,
@@ -4266,6 +4283,15 @@ int vmw_execbuf_process(struct drm_file *file_priv,
 		} else {
 			/* Link the fence with the FD created earlier */
 			fd_install(out_fence_fd, sync_file->file);
+			struct seqno_waiter_rm_context *ctx =
+				kmalloc(sizeof(*ctx), GFP_KERNEL);
+			ctx->dev_priv = dev_priv;
+			vmw_seqno_waiter_add(dev_priv);
+			if (dma_fence_add_callback(&fence->base, &ctx->base,
+						   seqno_waiter_rm_cb) < 0) {
+				vmw_seqno_waiter_remove(dev_priv);
+				kfree(ctx);
+			}
 		}
 	}
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
index a73af8a355fb..c4d5fe5f330f 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
@@ -273,7 +273,7 @@ int vmw_user_resource_lookup_handle(struct vmw_private *dev_priv,
 		goto out_bad_resource;
 
 	res = converter->base_obj_to_res(base);
-	kref_get(&res->kref);
+	vmw_resource_reference(res);
 
 	*p_res = res;
 	ret = 0;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c b/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c
index 7fb1c88bcc47..69dfe69ce0f8 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c
@@ -896,7 +896,7 @@ int vmw_compat_shader_add(struct vmw_private *dev_priv,
 		.busy_domain = VMW_BO_DOMAIN_SYS,
 		.bo_type = ttm_bo_type_device,
 		.size = size,
-		.pin = true,
+		.pin = false,
 		.keep_resv = true,
 	};
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
index 5721c74da3e0..d7a8070330ba 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
@@ -658,7 +658,7 @@ static void vmw_user_surface_free(struct vmw_resource *res)
 	struct vmw_user_surface *user_srf =
 	    container_of(srf, struct vmw_user_surface, srf);
 
-	WARN_ON_ONCE(res->dirty);
+	WARN_ON(res->dirty);
 	if (user_srf->master)
 		drm_master_put(&user_srf->master);
 	kfree(srf->offsets);
@@ -689,8 +689,7 @@ static void vmw_user_surface_base_release(struct ttm_base_object **p_base)
 	 * Dumb buffers own the resource and they'll unref the
 	 * resource themselves
 	 */
-	if (res && res->guest_memory_bo && res->guest_memory_bo->is_dumb)
-		return;
+	WARN_ON(res && res->guest_memory_bo && res->guest_memory_bo->is_dumb);
 
 	vmw_resource_unreference(&res);
 }
@@ -871,7 +870,12 @@ int vmw_surface_define_ioctl(struct drm_device *dev, void *data,
 			vmw_resource_unreference(&res);
 			goto out_unlock;
 		}
-		vmw_bo_add_detached_resource(res->guest_memory_bo, res);
+
+		ret = vmw_bo_add_detached_resource(res->guest_memory_bo, res);
+		if (unlikely(ret != 0)) {
+			vmw_resource_unreference(&res);
+			goto out_unlock;
+		}
 	}
 
 	tmp = vmw_resource_reference(&srf->res);
@@ -1670,6 +1674,14 @@ vmw_gb_surface_define_internal(struct drm_device *dev,
 
 	}
 
+	if (res->guest_memory_bo) {
+		ret = vmw_bo_add_detached_resource(res->guest_memory_bo, res);
+		if (unlikely(ret != 0)) {
+			vmw_resource_unreference(&res);
+			goto out_unlock;
+		}
+	}
+
 	tmp = vmw_resource_reference(res);
 	ret = ttm_prime_object_init(tfile, res->guest_memory_size, &user_srf->prime,
 				    VMW_RES_SURFACE,
@@ -1684,7 +1696,6 @@ vmw_gb_surface_define_internal(struct drm_device *dev,
 	rep->handle      = user_srf->prime.base.handle;
 	rep->backup_size = res->guest_memory_size;
 	if (res->guest_memory_bo) {
-		vmw_bo_add_detached_resource(res->guest_memory_bo, res);
 		rep->buffer_map_handle =
 			drm_vma_node_offset_addr(&res->guest_memory_bo->tbo.base.vma_node);
 		rep->buffer_size = res->guest_memory_bo->tbo.base.size;
@@ -2358,12 +2369,19 @@ int vmw_dumb_create(struct drm_file *file_priv,
 	vbo = res->guest_memory_bo;
 	vbo->is_dumb = true;
 	vbo->dumb_surface = vmw_res_to_srf(res);
-
+	drm_gem_object_put(&vbo->tbo.base);
+	/*
+	 * Unset the user surface dtor since this in not actually exposed
+	 * to userspace. The suface is owned via the dumb_buffer's GEM handle
+	 */
+	struct vmw_user_surface *usurf = container_of(vbo->dumb_surface,
+						struct vmw_user_surface, srf);
+	usurf->prime.base.refcount_release = NULL;
 err:
 	if (res)
 		vmw_resource_unreference(&res);
-	if (ret)
-		ttm_ref_object_base_unref(tfile, arg.rep.handle);
+
+	ttm_ref_object_base_unref(tfile, arg.rep.handle);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/xe/Kconfig b/drivers/gpu/drm/xe/Kconfig
index 7bbe46a98ff1..93e742c1f21e 100644
--- a/drivers/gpu/drm/xe/Kconfig
+++ b/drivers/gpu/drm/xe/Kconfig
@@ -1,7 +1,8 @@
 # SPDX-License-Identifier: GPL-2.0-only
 config DRM_XE
 	tristate "Intel Xe Graphics"
-	depends on DRM && PCI && MMU && (m || (y && KUNIT=y))
+	depends on DRM && PCI && MMU
+	depends on KUNIT || !KUNIT
 	select INTERVAL_TREE
 	# we need shmfs for the swappable backing store, and in particular
 	# the shmem_readpage() which depends upon tmpfs
diff --git a/drivers/gpu/drm/xe/abi/guc_communication_ctb_abi.h b/drivers/gpu/drm/xe/abi/guc_communication_ctb_abi.h
index 8f86a16dc577..f58198cf2cf6 100644
--- a/drivers/gpu/drm/xe/abi/guc_communication_ctb_abi.h
+++ b/drivers/gpu/drm/xe/abi/guc_communication_ctb_abi.h
@@ -52,6 +52,7 @@ struct guc_ct_buffer_desc {
 #define GUC_CTB_STATUS_OVERFLOW				(1 << 0)
 #define GUC_CTB_STATUS_UNDERFLOW			(1 << 1)
 #define GUC_CTB_STATUS_MISMATCH				(1 << 2)
+#define GUC_CTB_STATUS_DISABLED				(1 << 3)
 	u32 reserved[13];
 } __packed;
 static_assert(sizeof(struct guc_ct_buffer_desc) == 64);
diff --git a/drivers/gpu/drm/xe/compat-i915-headers/gem/i915_gem_stolen.h b/drivers/gpu/drm/xe/compat-i915-headers/gem/i915_gem_stolen.h
index cb6c7598824b..9c4cf050059a 100644
--- a/drivers/gpu/drm/xe/compat-i915-headers/gem/i915_gem_stolen.h
+++ b/drivers/gpu/drm/xe/compat-i915-headers/gem/i915_gem_stolen.h
@@ -29,7 +29,7 @@ static inline int i915_gem_stolen_insert_node_in_range(struct xe_device *xe,
 
 	bo = xe_bo_create_locked_range(xe, xe_device_get_root_tile(xe),
 				       NULL, size, start, end,
-				       ttm_bo_type_kernel, flags);
+				       ttm_bo_type_kernel, flags, 0);
 	if (IS_ERR(bo)) {
 		err = PTR_ERR(bo);
 		bo = NULL;
diff --git a/drivers/gpu/drm/xe/display/xe_display.c b/drivers/gpu/drm/xe/display/xe_display.c
index c6e0c8d77a70..e164e2d71e11 100644
--- a/drivers/gpu/drm/xe/display/xe_display.c
+++ b/drivers/gpu/drm/xe/display/xe_display.c
@@ -96,6 +96,8 @@ int xe_display_create(struct xe_device *xe)
 	spin_lock_init(&xe->display.fb_tracking.lock);
 
 	xe->display.hotplug.dp_wq = alloc_ordered_workqueue("xe-dp", 0);
+	if (!xe->display.hotplug.dp_wq)
+		return -ENOMEM;
 
 	return drmm_add_action_or_reset(&xe->drm, display_destroy, NULL);
 }
@@ -352,6 +354,36 @@ void xe_display_pm_suspend(struct xe_device *xe)
 	__xe_display_pm_suspend(xe, false);
 }
 
+void xe_display_pm_shutdown(struct xe_device *xe)
+{
+	struct intel_display *display = &xe->display;
+
+	if (!xe->info.probe_display)
+		return;
+
+	intel_power_domains_disable(xe);
+	intel_fbdev_set_suspend(&xe->drm, FBINFO_STATE_SUSPENDED, true);
+	if (has_display(xe)) {
+		drm_kms_helper_poll_disable(&xe->drm);
+		intel_display_driver_disable_user_access(xe);
+		intel_display_driver_suspend(xe);
+	}
+
+	xe_display_flush_cleanup_work(xe);
+	intel_dp_mst_suspend(xe);
+	intel_hpd_cancel_work(xe);
+
+	if (has_display(xe))
+		intel_display_driver_suspend_access(xe);
+
+	intel_encoder_suspend_all(display);
+	intel_encoder_shutdown_all(display);
+
+	intel_opregion_suspend(display, PCI_D3cold);
+
+	intel_dmc_suspend(xe);
+}
+
 void xe_display_pm_runtime_suspend(struct xe_device *xe)
 {
 	if (!xe->info.probe_display)
@@ -376,6 +408,19 @@ void xe_display_pm_suspend_late(struct xe_device *xe)
 	intel_display_power_suspend_late(xe);
 }
 
+void xe_display_pm_shutdown_late(struct xe_device *xe)
+{
+	if (!xe->info.probe_display)
+		return;
+
+	/*
+	 * The only requirement is to reboot with display DC states disabled,
+	 * for now leaving all display power wells in the INIT power domain
+	 * enabled.
+	 */
+	intel_power_domains_driver_remove(xe);
+}
+
 void xe_display_pm_resume_early(struct xe_device *xe)
 {
 	if (!xe->info.probe_display)
diff --git a/drivers/gpu/drm/xe/display/xe_display.h b/drivers/gpu/drm/xe/display/xe_display.h
index bed55fd26f30..17afa537aee5 100644
--- a/drivers/gpu/drm/xe/display/xe_display.h
+++ b/drivers/gpu/drm/xe/display/xe_display.h
@@ -35,7 +35,9 @@ void xe_display_irq_reset(struct xe_device *xe);
 void xe_display_irq_postinstall(struct xe_device *xe, struct xe_gt *gt);
 
 void xe_display_pm_suspend(struct xe_device *xe);
+void xe_display_pm_shutdown(struct xe_device *xe);
 void xe_display_pm_suspend_late(struct xe_device *xe);
+void xe_display_pm_shutdown_late(struct xe_device *xe);
 void xe_display_pm_resume_early(struct xe_device *xe);
 void xe_display_pm_resume(struct xe_device *xe);
 void xe_display_pm_runtime_suspend(struct xe_device *xe);
@@ -66,7 +68,9 @@ static inline void xe_display_irq_reset(struct xe_device *xe) {}
 static inline void xe_display_irq_postinstall(struct xe_device *xe, struct xe_gt *gt) {}
 
 static inline void xe_display_pm_suspend(struct xe_device *xe) {}
+static inline void xe_display_pm_shutdown(struct xe_device *xe) {}
 static inline void xe_display_pm_suspend_late(struct xe_device *xe) {}
+static inline void xe_display_pm_shutdown_late(struct xe_device *xe) {}
 static inline void xe_display_pm_resume_early(struct xe_device *xe) {}
 static inline void xe_display_pm_resume(struct xe_device *xe) {}
 static inline void xe_display_pm_runtime_suspend(struct xe_device *xe) {}
diff --git a/drivers/gpu/drm/xe/display/xe_dsb_buffer.c b/drivers/gpu/drm/xe/display/xe_dsb_buffer.c
index f99d901a3214..9f941fc2e36b 100644
--- a/drivers/gpu/drm/xe/display/xe_dsb_buffer.c
+++ b/drivers/gpu/drm/xe/display/xe_dsb_buffer.c
@@ -17,10 +17,7 @@ u32 intel_dsb_buffer_ggtt_offset(struct intel_dsb_buffer *dsb_buf)
 
 void intel_dsb_buffer_write(struct intel_dsb_buffer *dsb_buf, u32 idx, u32 val)
 {
-	struct xe_device *xe = dsb_buf->vma->bo->tile->xe;
-
 	iosys_map_wr(&dsb_buf->vma->bo->vmap, idx * 4, u32, val);
-	xe_device_l2_flush(xe);
 }
 
 u32 intel_dsb_buffer_read(struct intel_dsb_buffer *dsb_buf, u32 idx)
@@ -30,12 +27,9 @@ u32 intel_dsb_buffer_read(struct intel_dsb_buffer *dsb_buf, u32 idx)
 
 void intel_dsb_buffer_memset(struct intel_dsb_buffer *dsb_buf, u32 idx, u32 val, size_t size)
 {
-	struct xe_device *xe = dsb_buf->vma->bo->tile->xe;
-
 	WARN_ON(idx > (dsb_buf->buf_size - size) / sizeof(*dsb_buf->cmd_buf));
 
 	iosys_map_memset(&dsb_buf->vma->bo->vmap, idx * 4, val, size);
-	xe_device_l2_flush(xe);
 }
 
 bool intel_dsb_buffer_create(struct intel_crtc *crtc, struct intel_dsb_buffer *dsb_buf, size_t size)
@@ -48,11 +42,12 @@ bool intel_dsb_buffer_create(struct intel_crtc *crtc, struct intel_dsb_buffer *d
 	if (!vma)
 		return false;
 
+	/* Set scanout flag for WC mapping */
 	obj = xe_bo_create_pin_map(xe, xe_device_get_root_tile(xe),
 				   NULL, PAGE_ALIGN(size),
 				   ttm_bo_type_kernel,
 				   XE_BO_FLAG_VRAM_IF_DGFX(xe_device_get_root_tile(xe)) |
-				   XE_BO_FLAG_GGTT);
+				   XE_BO_FLAG_SCANOUT | XE_BO_FLAG_GGTT);
 	if (IS_ERR(obj)) {
 		kfree(vma);
 		return false;
@@ -73,5 +68,12 @@ void intel_dsb_buffer_cleanup(struct intel_dsb_buffer *dsb_buf)
 
 void intel_dsb_buffer_flush_map(struct intel_dsb_buffer *dsb_buf)
 {
-	/* TODO: add xe specific flush_map() for dsb buffer object. */
+	struct xe_device *xe = dsb_buf->vma->bo->tile->xe;
+
+	/*
+	 * The memory barrier here is to ensure coherency of DSB vs MMIO,
+	 * both for weak ordering archs and discrete cards.
+	 */
+	xe_device_wmb(xe);
+	xe_device_l2_flush(xe);
 }
diff --git a/drivers/gpu/drm/xe/display/xe_fb_pin.c b/drivers/gpu/drm/xe/display/xe_fb_pin.c
index b58fc4ba2aac..0558b106f8b6 100644
--- a/drivers/gpu/drm/xe/display/xe_fb_pin.c
+++ b/drivers/gpu/drm/xe/display/xe_fb_pin.c
@@ -153,7 +153,10 @@ static int __xe_pin_fb_vma_dpt(const struct intel_framebuffer *fb,
 	}
 
 	vma->dpt = dpt;
-	vma->node = dpt->ggtt_node;
+	vma->node = dpt->ggtt_node[tile0->id];
+
+	/* Ensure DPT writes are flushed */
+	xe_device_l2_flush(xe);
 	return 0;
 }
 
@@ -203,8 +206,8 @@ static int __xe_pin_fb_vma_ggtt(const struct intel_framebuffer *fb,
 	if (xe_bo_is_vram(bo) && ggtt->flags & XE_GGTT_FLAGS_64K)
 		align = max_t(u32, align, SZ_64K);
 
-	if (bo->ggtt_node && view->type == I915_GTT_VIEW_NORMAL) {
-		vma->node = bo->ggtt_node;
+	if (bo->ggtt_node[ggtt->tile->id] && view->type == I915_GTT_VIEW_NORMAL) {
+		vma->node = bo->ggtt_node[ggtt->tile->id];
 	} else if (view->type == I915_GTT_VIEW_NORMAL) {
 		u32 x, size = bo->ttm.base.size;
 
@@ -318,8 +321,6 @@ static struct i915_vma *__xe_pin_fb_vma(const struct intel_framebuffer *fb,
 	if (ret)
 		goto err_unpin;
 
-	/* Ensure DPT writes are flushed */
-	xe_device_l2_flush(xe);
 	return vma;
 
 err_unpin:
@@ -333,10 +334,12 @@ err:
 
 static void __xe_unpin_fb_vma(struct i915_vma *vma)
 {
+	u8 tile_id = vma->node->ggtt->tile->id;
+
 	if (vma->dpt)
 		xe_bo_unpin_map_no_vm(vma->dpt);
-	else if (!xe_ggtt_node_allocated(vma->bo->ggtt_node) ||
-		 vma->bo->ggtt_node->base.start != vma->node->base.start)
+	else if (!xe_ggtt_node_allocated(vma->bo->ggtt_node[tile_id]) ||
+		 vma->bo->ggtt_node[tile_id]->base.start != vma->node->base.start)
 		xe_ggtt_node_remove(vma->node, false);
 
 	ttm_bo_reserve(&vma->bo->ttm, false, false, NULL);
diff --git a/drivers/gpu/drm/xe/display/xe_plane_initial.c b/drivers/gpu/drm/xe/display/xe_plane_initial.c
index a50ab9eae40a..f99d38cc5d8e 100644
--- a/drivers/gpu/drm/xe/display/xe_plane_initial.c
+++ b/drivers/gpu/drm/xe/display/xe_plane_initial.c
@@ -194,8 +194,6 @@ intel_find_initial_plane_obj(struct intel_crtc *crtc,
 		to_intel_plane(crtc->base.primary);
 	struct intel_plane_state *plane_state =
 		to_intel_plane_state(plane->base.state);
-	struct intel_crtc_state *crtc_state =
-		to_intel_crtc_state(crtc->base.state);
 	struct drm_framebuffer *fb;
 	struct i915_vma *vma;
 
@@ -241,14 +239,6 @@ intel_find_initial_plane_obj(struct intel_crtc *crtc,
 	atomic_or(plane->frontbuffer_bit, &to_intel_frontbuffer(fb)->bits);
 
 	plane_config->vma = vma;
-
-	/*
-	 * Flip to the newly created mapping ASAP, so we can re-use the
-	 * first part of GGTT for WOPCM, prevent flickering, and prevent
-	 * the lookup of sysmem scratch pages.
-	 */
-	plane->check_plane(crtc_state, plane_state);
-	plane->async_flip(plane, crtc_state, plane_state, true);
 	return;
 
 nofb:
diff --git a/drivers/gpu/drm/xe/instructions/xe_mi_commands.h b/drivers/gpu/drm/xe/instructions/xe_mi_commands.h
index 10ec2920d31b..d4033278be9f 100644
--- a/drivers/gpu/drm/xe/instructions/xe_mi_commands.h
+++ b/drivers/gpu/drm/xe/instructions/xe_mi_commands.h
@@ -47,6 +47,10 @@
 #define   MI_LRI_FORCE_POSTED		REG_BIT(12)
 #define   MI_LRI_LEN(x)			(((x) & 0xff) + 1)
 
+#define MI_STORE_REGISTER_MEM		(__MI_INSTR(0x24) | XE_INSTR_NUM_DW(4))
+#define   MI_SRM_USE_GGTT		REG_BIT(22)
+#define   MI_SRM_ADD_CS_OFFSET		REG_BIT(19)
+
 #define MI_FLUSH_DW			__MI_INSTR(0x26)
 #define   MI_FLUSH_DW_STORE_INDEX	REG_BIT(21)
 #define   MI_INVALIDATE_TLB		REG_BIT(18)
diff --git a/drivers/gpu/drm/xe/regs/xe_engine_regs.h b/drivers/gpu/drm/xe/regs/xe_engine_regs.h
index 7c78496e6213..192e571348f6 100644
--- a/drivers/gpu/drm/xe/regs/xe_engine_regs.h
+++ b/drivers/gpu/drm/xe/regs/xe_engine_regs.h
@@ -53,7 +53,6 @@
 
 #define RING_CTL(base)				XE_REG((base) + 0x3c)
 #define   RING_CTL_SIZE(size)			((size) - PAGE_SIZE) /* in bytes -> pages */
-#define   RING_CTL_SIZE(size)			((size) - PAGE_SIZE) /* in bytes -> pages */
 
 #define RING_START_UDW(base)			XE_REG((base) + 0x48)
 
diff --git a/drivers/gpu/drm/xe/regs/xe_gt_regs.h b/drivers/gpu/drm/xe/regs/xe_gt_regs.h
index 5404de2aea54..c160b015d178 100644
--- a/drivers/gpu/drm/xe/regs/xe_gt_regs.h
+++ b/drivers/gpu/drm/xe/regs/xe_gt_regs.h
@@ -157,6 +157,7 @@
 #define XEHPG_SC_INSTDONE_EXTRA2		XE_REG_MCR(0x7108)
 
 #define COMMON_SLICE_CHICKEN4			XE_REG(0x7300, XE_REG_OPTION_MASKED)
+#define   SBE_PUSH_CONSTANT_BEHIND_FIX_ENABLE	REG_BIT(12)
 #define   DISABLE_TDC_LOAD_BALANCING_CALC	REG_BIT(6)
 
 #define COMMON_SLICE_CHICKEN3				XE_REG(0x7304, XE_REG_OPTION_MASKED)
diff --git a/drivers/gpu/drm/xe/regs/xe_reg_defs.h b/drivers/gpu/drm/xe/regs/xe_reg_defs.h
index 23f7dc5bbe99..51fd40ffafcb 100644
--- a/drivers/gpu/drm/xe/regs/xe_reg_defs.h
+++ b/drivers/gpu/drm/xe/regs/xe_reg_defs.h
@@ -128,7 +128,7 @@ struct xe_reg_mcr {
  *       options.
  */
 #define XE_REG_MCR(r_, ...)	((const struct xe_reg_mcr){					\
-				 .__reg = XE_REG_INITIALIZER(r_,  ##__VA_ARGS__, .mcr = 1)	\
+				 .__reg = XE_REG_INITIALIZER(r_, ##__VA_ARGS__, .mcr = 1)	\
 				 })
 
 static inline bool xe_reg_is_valid(struct xe_reg r)
diff --git a/drivers/gpu/drm/xe/tests/xe_mocs.c b/drivers/gpu/drm/xe/tests/xe_mocs.c
index 79be73b4a02b..bf3f97d0c9c7 100644
--- a/drivers/gpu/drm/xe/tests/xe_mocs.c
+++ b/drivers/gpu/drm/xe/tests/xe_mocs.c
@@ -47,7 +47,7 @@ static void read_l3cc_table(struct xe_gt *gt,
 	u32 reg_val;
 	u32 ret;
 
-	ret = xe_force_wake_get(gt_to_fw(gt), XE_FW_GT);
+	ret = xe_force_wake_get(gt_to_fw(gt), XE_FORCEWAKE_ALL);
 	KUNIT_ASSERT_EQ_MSG(test, ret, 0, "Forcewake Failed.\n");
 
 	for (i = 0; i < info->num_mocs_regs; i++) {
@@ -72,7 +72,7 @@ static void read_l3cc_table(struct xe_gt *gt,
 		KUNIT_EXPECT_EQ_MSG(test, l3cc_expected, l3cc,
 				    "l3cc idx=%u has incorrect val.\n", i);
 	}
-	xe_force_wake_put(gt_to_fw(gt), XE_FW_GT);
+	xe_force_wake_put(gt_to_fw(gt), XE_FORCEWAKE_ALL);
 }
 
 static void read_mocs_table(struct xe_gt *gt,
diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c
index 84e327b56925..5f745d9ed6cc 100644
--- a/drivers/gpu/drm/xe/xe_bo.c
+++ b/drivers/gpu/drm/xe/xe_bo.c
@@ -702,6 +702,21 @@ static int xe_bo_move(struct ttm_buffer_object *ttm_bo, bool evict,
 		goto out;
 	}
 
+	/* Reject BO eviction if BO is bound to current VM. */
+	if (evict && ctx->resv) {
+		struct drm_gpuvm_bo *vm_bo;
+
+		drm_gem_for_each_gpuvm_bo(vm_bo, &bo->ttm.base) {
+			struct xe_vm *vm = gpuvm_to_vm(vm_bo->vm);
+
+			if (xe_vm_resv(vm) == ctx->resv &&
+			    xe_vm_in_preempt_fence_mode(vm)) {
+				ret = -EBUSY;
+				goto out;
+			}
+		}
+	}
+
 	/*
 	 * Failed multi-hop where the old_mem is still marked as
 	 * TTM_PL_FLAG_TEMPORARY, should just be a dummy move.
@@ -1115,6 +1130,8 @@ static void xe_ttm_bo_destroy(struct ttm_buffer_object *ttm_bo)
 {
 	struct xe_bo *bo = ttm_to_xe_bo(ttm_bo);
 	struct xe_device *xe = ttm_to_xe_device(ttm_bo->bdev);
+	struct xe_tile *tile;
+	u8 id;
 
 	if (bo->ttm.base.import_attach)
 		drm_prime_gem_destroy(&bo->ttm.base, NULL);
@@ -1122,8 +1139,9 @@ static void xe_ttm_bo_destroy(struct ttm_buffer_object *ttm_bo)
 
 	xe_assert(xe, list_empty(&ttm_bo->base.gpuva.list));
 
-	if (bo->ggtt_node && bo->ggtt_node->base.size)
-		xe_ggtt_remove_bo(bo->tile->mem.ggtt, bo);
+	for_each_tile(tile, xe, id)
+		if (bo->ggtt_node[id] && bo->ggtt_node[id]->base.size)
+			xe_ggtt_remove_bo(tile->mem.ggtt, bo);
 
 #ifdef CONFIG_PROC_FS
 	if (bo->client)
@@ -1293,6 +1311,10 @@ struct xe_bo *___xe_bo_create_locked(struct xe_device *xe, struct xe_bo *bo,
 		return ERR_PTR(-EINVAL);
 	}
 
+	/* XE_BO_FLAG_GGTTx requires XE_BO_FLAG_GGTT also be set */
+	if ((flags & XE_BO_FLAG_GGTT_ALL) && !(flags & XE_BO_FLAG_GGTT))
+		return ERR_PTR(-EINVAL);
+
 	if (flags & (XE_BO_FLAG_VRAM_MASK | XE_BO_FLAG_STOLEN) &&
 	    !(flags & XE_BO_FLAG_IGNORE_MIN_PAGE_SIZE) &&
 	    ((xe->info.vram_flags & XE_VRAM_FLAGS_NEED64K) ||
@@ -1439,7 +1461,8 @@ static struct xe_bo *
 __xe_bo_create_locked(struct xe_device *xe,
 		      struct xe_tile *tile, struct xe_vm *vm,
 		      size_t size, u64 start, u64 end,
-		      u16 cpu_caching, enum ttm_bo_type type, u32 flags)
+		      u16 cpu_caching, enum ttm_bo_type type, u32 flags,
+		      u64 alignment)
 {
 	struct xe_bo *bo = NULL;
 	int err;
@@ -1468,6 +1491,8 @@ __xe_bo_create_locked(struct xe_device *xe,
 	if (IS_ERR(bo))
 		return bo;
 
+	bo->min_align = alignment;
+
 	/*
 	 * Note that instead of taking a reference no the drm_gpuvm_resv_bo(),
 	 * to ensure the shared resv doesn't disappear under the bo, the bo
@@ -1480,19 +1505,29 @@ __xe_bo_create_locked(struct xe_device *xe,
 	bo->vm = vm;
 
 	if (bo->flags & XE_BO_FLAG_GGTT) {
-		if (!tile && flags & XE_BO_FLAG_STOLEN)
-			tile = xe_device_get_root_tile(xe);
+		struct xe_tile *t;
+		u8 id;
 
-		xe_assert(xe, tile);
+		if (!(bo->flags & XE_BO_FLAG_GGTT_ALL)) {
+			if (!tile && flags & XE_BO_FLAG_STOLEN)
+				tile = xe_device_get_root_tile(xe);
 
-		if (flags & XE_BO_FLAG_FIXED_PLACEMENT) {
-			err = xe_ggtt_insert_bo_at(tile->mem.ggtt, bo,
-						   start + bo->size, U64_MAX);
-		} else {
-			err = xe_ggtt_insert_bo(tile->mem.ggtt, bo);
+			xe_assert(xe, tile);
+		}
+
+		for_each_tile(t, xe, id) {
+			if (t != tile && !(bo->flags & XE_BO_FLAG_GGTTx(t)))
+				continue;
+
+			if (flags & XE_BO_FLAG_FIXED_PLACEMENT) {
+				err = xe_ggtt_insert_bo_at(t->mem.ggtt, bo,
+							   start + bo->size, U64_MAX);
+			} else {
+				err = xe_ggtt_insert_bo(t->mem.ggtt, bo);
+			}
+			if (err)
+				goto err_unlock_put_bo;
 		}
-		if (err)
-			goto err_unlock_put_bo;
 	}
 
 	return bo;
@@ -1508,16 +1543,18 @@ struct xe_bo *
 xe_bo_create_locked_range(struct xe_device *xe,
 			  struct xe_tile *tile, struct xe_vm *vm,
 			  size_t size, u64 start, u64 end,
-			  enum ttm_bo_type type, u32 flags)
+			  enum ttm_bo_type type, u32 flags, u64 alignment)
 {
-	return __xe_bo_create_locked(xe, tile, vm, size, start, end, 0, type, flags);
+	return __xe_bo_create_locked(xe, tile, vm, size, start, end, 0, type,
+				     flags, alignment);
 }
 
 struct xe_bo *xe_bo_create_locked(struct xe_device *xe, struct xe_tile *tile,
 				  struct xe_vm *vm, size_t size,
 				  enum ttm_bo_type type, u32 flags)
 {
-	return __xe_bo_create_locked(xe, tile, vm, size, 0, ~0ULL, 0, type, flags);
+	return __xe_bo_create_locked(xe, tile, vm, size, 0, ~0ULL, 0, type,
+				     flags, 0);
 }
 
 struct xe_bo *xe_bo_create_user(struct xe_device *xe, struct xe_tile *tile,
@@ -1527,7 +1564,7 @@ struct xe_bo *xe_bo_create_user(struct xe_device *xe, struct xe_tile *tile,
 {
 	struct xe_bo *bo = __xe_bo_create_locked(xe, tile, vm, size, 0, ~0ULL,
 						 cpu_caching, ttm_bo_type_device,
-						 flags | XE_BO_FLAG_USER);
+						 flags | XE_BO_FLAG_USER, 0);
 	if (!IS_ERR(bo))
 		xe_bo_unlock_vm_held(bo);
 
@@ -1551,6 +1588,17 @@ struct xe_bo *xe_bo_create_pin_map_at(struct xe_device *xe, struct xe_tile *tile
 				      size_t size, u64 offset,
 				      enum ttm_bo_type type, u32 flags)
 {
+	return xe_bo_create_pin_map_at_aligned(xe, tile, vm, size, offset,
+					       type, flags, 0);
+}
+
+struct xe_bo *xe_bo_create_pin_map_at_aligned(struct xe_device *xe,
+					      struct xe_tile *tile,
+					      struct xe_vm *vm,
+					      size_t size, u64 offset,
+					      enum ttm_bo_type type, u32 flags,
+					      u64 alignment)
+{
 	struct xe_bo *bo;
 	int err;
 	u64 start = offset == ~0ull ? 0 : offset;
@@ -1561,7 +1609,8 @@ struct xe_bo *xe_bo_create_pin_map_at(struct xe_device *xe, struct xe_tile *tile
 		flags |= XE_BO_FLAG_GGTT;
 
 	bo = xe_bo_create_locked_range(xe, tile, vm, size, start, end, type,
-				       flags | XE_BO_FLAG_NEEDS_CPU_ACCESS);
+				       flags | XE_BO_FLAG_NEEDS_CPU_ACCESS,
+				       alignment);
 	if (IS_ERR(bo))
 		return bo;
 
@@ -1975,6 +2024,7 @@ int xe_gem_create_ioctl(struct drm_device *dev, void *data,
 	struct xe_file *xef = to_xe_file(file);
 	struct drm_xe_gem_create *args = data;
 	struct xe_vm *vm = NULL;
+	ktime_t end = 0;
 	struct xe_bo *bo;
 	unsigned int bo_flags;
 	u32 handle;
@@ -2047,6 +2097,10 @@ int xe_gem_create_ioctl(struct drm_device *dev, void *data,
 		vm = xe_vm_lookup(xef, args->vm_id);
 		if (XE_IOCTL_DBG(xe, !vm))
 			return -ENOENT;
+	}
+
+retry:
+	if (vm) {
 		err = xe_vm_lock(vm, true);
 		if (err)
 			goto out_vm;
@@ -2060,6 +2114,8 @@ int xe_gem_create_ioctl(struct drm_device *dev, void *data,
 
 	if (IS_ERR(bo)) {
 		err = PTR_ERR(bo);
+		if (xe_vm_validate_should_retry(NULL, err, &end))
+			goto retry;
 		goto out_vm;
 	}
 
@@ -2333,14 +2389,18 @@ void xe_bo_put_commit(struct llist_head *deferred)
 
 void xe_bo_put(struct xe_bo *bo)
 {
+	struct xe_tile *tile;
+	u8 id;
+
 	might_sleep();
 	if (bo) {
 #ifdef CONFIG_PROC_FS
 		if (bo->client)
 			might_lock(&bo->client->bos_lock);
 #endif
-		if (bo->ggtt_node && bo->ggtt_node->ggtt)
-			might_lock(&bo->ggtt_node->ggtt->lock);
+		for_each_tile(tile, xe_bo_device(bo), id)
+			if (bo->ggtt_node[id] && bo->ggtt_node[id]->ggtt)
+				might_lock(&bo->ggtt_node[id]->ggtt->lock);
 		drm_gem_object_put(&bo->ttm.base);
 	}
 }
diff --git a/drivers/gpu/drm/xe/xe_bo.h b/drivers/gpu/drm/xe/xe_bo.h
index 6e4be52306df..d04159c59846 100644
--- a/drivers/gpu/drm/xe/xe_bo.h
+++ b/drivers/gpu/drm/xe/xe_bo.h
@@ -39,10 +39,22 @@
 #define XE_BO_FLAG_NEEDS_64K		BIT(15)
 #define XE_BO_FLAG_NEEDS_2M		BIT(16)
 #define XE_BO_FLAG_GGTT_INVALIDATE	BIT(17)
+#define XE_BO_FLAG_GGTT0                BIT(18)
+#define XE_BO_FLAG_GGTT1                BIT(19)
+#define XE_BO_FLAG_GGTT2                BIT(20)
+#define XE_BO_FLAG_GGTT3                BIT(21)
+#define XE_BO_FLAG_GGTT_ALL             (XE_BO_FLAG_GGTT0 | \
+					 XE_BO_FLAG_GGTT1 | \
+					 XE_BO_FLAG_GGTT2 | \
+					 XE_BO_FLAG_GGTT3)
+
 /* this one is trigger internally only */
 #define XE_BO_FLAG_INTERNAL_TEST	BIT(30)
 #define XE_BO_FLAG_INTERNAL_64K		BIT(31)
 
+#define XE_BO_FLAG_GGTTx(tile) \
+	(XE_BO_FLAG_GGTT0 << (tile)->id)
+
 #define XE_PTE_SHIFT			12
 #define XE_PAGE_SIZE			(1 << XE_PTE_SHIFT)
 #define XE_PTE_MASK			(XE_PAGE_SIZE - 1)
@@ -77,7 +89,7 @@ struct xe_bo *
 xe_bo_create_locked_range(struct xe_device *xe,
 			  struct xe_tile *tile, struct xe_vm *vm,
 			  size_t size, u64 start, u64 end,
-			  enum ttm_bo_type type, u32 flags);
+			  enum ttm_bo_type type, u32 flags, u64 alignment);
 struct xe_bo *xe_bo_create_locked(struct xe_device *xe, struct xe_tile *tile,
 				  struct xe_vm *vm, size_t size,
 				  enum ttm_bo_type type, u32 flags);
@@ -94,6 +106,12 @@ struct xe_bo *xe_bo_create_pin_map(struct xe_device *xe, struct xe_tile *tile,
 struct xe_bo *xe_bo_create_pin_map_at(struct xe_device *xe, struct xe_tile *tile,
 				      struct xe_vm *vm, size_t size, u64 offset,
 				      enum ttm_bo_type type, u32 flags);
+struct xe_bo *xe_bo_create_pin_map_at_aligned(struct xe_device *xe,
+					      struct xe_tile *tile,
+					      struct xe_vm *vm,
+					      size_t size, u64 offset,
+					      enum ttm_bo_type type, u32 flags,
+					      u64 alignment);
 struct xe_bo *xe_bo_create_from_data(struct xe_device *xe, struct xe_tile *tile,
 				     const void *data, size_t size,
 				     enum ttm_bo_type type, u32 flags);
@@ -188,14 +206,24 @@ xe_bo_main_addr(struct xe_bo *bo, size_t page_size)
 }
 
 static inline u32
-xe_bo_ggtt_addr(struct xe_bo *bo)
+__xe_bo_ggtt_addr(struct xe_bo *bo, u8 tile_id)
 {
-	if (XE_WARN_ON(!bo->ggtt_node))
+	struct xe_ggtt_node *ggtt_node = bo->ggtt_node[tile_id];
+
+	if (XE_WARN_ON(!ggtt_node))
 		return 0;
 
-	XE_WARN_ON(bo->ggtt_node->base.size > bo->size);
-	XE_WARN_ON(bo->ggtt_node->base.start + bo->ggtt_node->base.size > (1ull << 32));
-	return bo->ggtt_node->base.start;
+	XE_WARN_ON(ggtt_node->base.size > bo->size);
+	XE_WARN_ON(ggtt_node->base.start + ggtt_node->base.size > (1ull << 32));
+	return ggtt_node->base.start;
+}
+
+static inline u32
+xe_bo_ggtt_addr(struct xe_bo *bo)
+{
+	xe_assert(xe_bo_device(bo), bo->tile);
+
+	return __xe_bo_ggtt_addr(bo, bo->tile->id);
 }
 
 int xe_bo_vmap(struct xe_bo *bo);
@@ -314,7 +342,6 @@ static inline unsigned int xe_sg_segment_size(struct device *dev)
 
 #define i915_gem_object_flush_if_display(obj)		((void)(obj))
 
-#if IS_ENABLED(CONFIG_DRM_XE_KUNIT_TEST)
 /**
  * xe_bo_is_mem_type - Whether the bo currently resides in the given
  * TTM memory type
@@ -329,4 +356,3 @@ static inline bool xe_bo_is_mem_type(struct xe_bo *bo, u32 mem_type)
 	return bo->ttm.resource->mem_type == mem_type;
 }
 #endif
-#endif
diff --git a/drivers/gpu/drm/xe/xe_bo_evict.c b/drivers/gpu/drm/xe/xe_bo_evict.c
index 8fb2be061003..6a40eedd9db1 100644
--- a/drivers/gpu/drm/xe/xe_bo_evict.c
+++ b/drivers/gpu/drm/xe/xe_bo_evict.c
@@ -152,11 +152,17 @@ int xe_bo_restore_kernel(struct xe_device *xe)
 		}
 
 		if (bo->flags & XE_BO_FLAG_GGTT) {
-			struct xe_tile *tile = bo->tile;
+			struct xe_tile *tile;
+			u8 id;
 
-			mutex_lock(&tile->mem.ggtt->lock);
-			xe_ggtt_map_bo(tile->mem.ggtt, bo);
-			mutex_unlock(&tile->mem.ggtt->lock);
+			for_each_tile(tile, xe, id) {
+				if (tile != bo->tile && !(bo->flags & XE_BO_FLAG_GGTTx(tile)))
+					continue;
+
+				mutex_lock(&tile->mem.ggtt->lock);
+				xe_ggtt_map_bo(tile->mem.ggtt, bo);
+				mutex_unlock(&tile->mem.ggtt->lock);
+			}
 		}
 
 		/*
diff --git a/drivers/gpu/drm/xe/xe_bo_types.h b/drivers/gpu/drm/xe/xe_bo_types.h
index 2ed558ac2264..aa298d33c250 100644
--- a/drivers/gpu/drm/xe/xe_bo_types.h
+++ b/drivers/gpu/drm/xe/xe_bo_types.h
@@ -13,6 +13,7 @@
 #include <drm/ttm/ttm_execbuf_util.h>
 #include <drm/ttm/ttm_placement.h>
 
+#include "xe_device_types.h"
 #include "xe_ggtt_types.h"
 
 struct xe_device;
@@ -39,8 +40,8 @@ struct xe_bo {
 	struct ttm_place placements[XE_BO_MAX_PLACEMENTS];
 	/** @placement: current placement for this BO */
 	struct ttm_placement placement;
-	/** @ggtt_node: GGTT node if this BO is mapped in the GGTT */
-	struct xe_ggtt_node *ggtt_node;
+	/** @ggtt_node: Array of GGTT nodes if this BO is mapped in the GGTTs */
+	struct xe_ggtt_node *ggtt_node[XE_MAX_TILES_PER_DEVICE];
 	/** @vmap: iosys map of this buffer */
 	struct iosys_map vmap;
 	/** @ttm_kmap: TTM bo kmap object for internal use only. Keep off. */
@@ -76,6 +77,11 @@ struct xe_bo {
 
 	/** @vram_userfault_link: Link into @mem_access.vram_userfault.list */
 		struct list_head vram_userfault_link;
+
+	/** @min_align: minimum alignment needed for this BO if different
+	 * from default
+	 */
+	u64 min_align;
 };
 
 #define intel_bo_to_drm_bo(bo) (&(bo)->ttm.base)
diff --git a/drivers/gpu/drm/xe/xe_debugfs.c b/drivers/gpu/drm/xe/xe_debugfs.c
index fe4319eb13fd..278ce1c37b39 100644
--- a/drivers/gpu/drm/xe/xe_debugfs.c
+++ b/drivers/gpu/drm/xe/xe_debugfs.c
@@ -147,7 +147,7 @@ static ssize_t wedged_mode_set(struct file *f, const char __user *ubuf,
 		return -EINVAL;
 
 	if (xe->wedged.mode == wedged_mode)
-		return 0;
+		return size;
 
 	xe->wedged.mode = wedged_mode;
 
@@ -156,6 +156,7 @@ static ssize_t wedged_mode_set(struct file *f, const char __user *ubuf,
 		ret = xe_guc_ads_scheduler_policy_toggle_reset(&gt->uc.guc.ads);
 		if (ret) {
 			xe_gt_err(gt, "Failed to update GuC ADS scheduler policy. GuC may still cause engine reset even with wedged_mode=2\n");
+			xe_pm_runtime_put(xe);
 			return -EIO;
 		}
 	}
diff --git a/drivers/gpu/drm/xe/xe_devcoredump.c b/drivers/gpu/drm/xe/xe_devcoredump.c
index 85aa3ab0da3b..e412a70323cc 100644
--- a/drivers/gpu/drm/xe/xe_devcoredump.c
+++ b/drivers/gpu/drm/xe/xe_devcoredump.c
@@ -104,11 +104,7 @@ static ssize_t __xe_devcoredump_read(char *buffer, size_t count,
 	drm_puts(&p, "\n**** GuC CT ****\n");
 	xe_guc_ct_snapshot_print(ss->ct, &p);
 
-	/*
-	 * Don't add a new section header here because the mesa debug decoder
-	 * tool expects the context information to be in the 'GuC CT' section.
-	 */
-	/* drm_puts(&p, "\n**** Contexts ****\n"); */
+	drm_puts(&p, "\n**** Contexts ****\n");
 	xe_guc_exec_queue_snapshot_print(ss->ge, &p);
 
 	drm_puts(&p, "\n**** Job ****\n");
@@ -201,7 +197,6 @@ static void xe_devcoredump_deferred_snap_work(struct work_struct *work)
 	struct xe_devcoredump_snapshot *ss = container_of(work, typeof(*ss), work);
 	struct xe_devcoredump *coredump = container_of(ss, typeof(*coredump), snapshot);
 	struct xe_device *xe = coredump_to_xe(coredump);
-	unsigned int fw_ref;
 
 	/*
 	 * NB: Despite passing a GFP_ flags parameter here, more allocations are done
@@ -215,12 +210,11 @@ static void xe_devcoredump_deferred_snap_work(struct work_struct *work)
 	xe_pm_runtime_get(xe);
 
 	/* keep going if fw fails as we still want to save the memory and SW data */
-	fw_ref = xe_force_wake_get(gt_to_fw(ss->gt), XE_FORCEWAKE_ALL);
-	if (!xe_force_wake_ref_has_domain(fw_ref, XE_FORCEWAKE_ALL))
+	if (xe_force_wake_get(gt_to_fw(ss->gt), XE_FORCEWAKE_ALL))
 		xe_gt_info(ss->gt, "failed to get forcewake for coredump capture\n");
 	xe_vm_snapshot_capture_delayed(ss->vm);
 	xe_guc_exec_queue_snapshot_capture_delayed(ss->ge);
-	xe_force_wake_put(gt_to_fw(ss->gt), fw_ref);
+	xe_force_wake_put(gt_to_fw(ss->gt), XE_FORCEWAKE_ALL);
 
 	xe_pm_runtime_put(xe);
 
@@ -247,9 +241,8 @@ static void devcoredump_snapshot(struct xe_devcoredump *coredump,
 	u32 width_mask = (0x1 << q->width) - 1;
 	const char *process_name = "no process";
 
-	unsigned int fw_ref;
-	bool cookie;
 	int i;
+	bool cookie;
 
 	ss->snapshot_time = ktime_get_real();
 	ss->boot_time = ktime_get_boottime();
@@ -272,7 +265,8 @@ static void devcoredump_snapshot(struct xe_devcoredump *coredump,
 	}
 
 	/* keep going if fw fails as we still want to save the memory and SW data */
-	fw_ref = xe_force_wake_get(gt_to_fw(q->gt), XE_FORCEWAKE_ALL);
+	if (xe_force_wake_get(gt_to_fw(q->gt), XE_FORCEWAKE_ALL))
+		xe_gt_info(ss->gt, "failed to get forcewake for coredump capture\n");
 
 	ss->ct = xe_guc_ct_snapshot_capture(&guc->ct, true);
 	ss->ge = xe_guc_exec_queue_snapshot_capture(q);
@@ -290,7 +284,7 @@ static void devcoredump_snapshot(struct xe_devcoredump *coredump,
 
 	queue_work(system_unbound_wq, &ss->work);
 
-	xe_force_wake_put(gt_to_fw(q->gt), fw_ref);
+	xe_force_wake_put(gt_to_fw(q->gt), XE_FORCEWAKE_ALL);
 	dma_fence_end_signalling(cookie);
 }
 
@@ -337,42 +331,34 @@ int xe_devcoredump_init(struct xe_device *xe)
 /**
  * xe_print_blob_ascii85 - print a BLOB to some useful location in ASCII85
  *
- * The output is split to multiple lines because some print targets, e.g. dmesg
- * cannot handle arbitrarily long lines. Note also that printing to dmesg in
- * piece-meal fashion is not possible, each separate call to drm_puts() has a
- * line-feed automatically added! Therefore, the entire output line must be
- * constructed in a local buffer first, then printed in one atomic output call.
+ * The output is split into multiple calls to drm_puts() because some print
+ * targets, e.g. dmesg, cannot handle arbitrarily long lines. These targets may
+ * add newlines, as is the case with dmesg: each drm_puts() call creates a
+ * separate line.
  *
  * There is also a scheduler yield call to prevent the 'task has been stuck for
  * 120s' kernel hang check feature from firing when printing to a slow target
  * such as dmesg over a serial port.
  *
- * TODO: Add compression prior to the ASCII85 encoding to shrink huge buffers down.
- *
  * @p: the printer object to output to
  * @prefix: optional prefix to add to output string
+ * @suffix: optional suffix to add at the end. 0 disables it and is
+ *          not added to the output, which is useful when using multiple calls
+ *          to dump data to @p
  * @blob: the Binary Large OBject to dump out
  * @offset: offset in bytes to skip from the front of the BLOB, must be a multiple of sizeof(u32)
  * @size: the size in bytes of the BLOB, must be a multiple of sizeof(u32)
  */
-void xe_print_blob_ascii85(struct drm_printer *p, const char *prefix,
+void xe_print_blob_ascii85(struct drm_printer *p, const char *prefix, char suffix,
 			   const void *blob, size_t offset, size_t size)
 {
 	const u32 *blob32 = (const u32 *)blob;
 	char buff[ASCII85_BUFSZ], *line_buff;
 	size_t line_pos = 0;
 
-	/*
-	 * Splitting blobs across multiple lines is not compatible with the mesa
-	 * debug decoder tool. Note that even dropping the explicit '\n' below
-	 * doesn't help because the GuC log is so big some underlying implementation
-	 * still splits the lines at 512K characters. So just bail completely for
-	 * the moment.
-	 */
-	return;
-
 #define DMESG_MAX_LINE_LEN	800
-#define MIN_SPACE		(ASCII85_BUFSZ + 2)		/* 85 + "\n\0" */
+	/* Always leave space for the suffix char and the \0 */
+#define MIN_SPACE		(ASCII85_BUFSZ + 2)	/* 85 + "<suffix>\0" */
 
 	if (size & 3)
 		drm_printf(p, "Size not word aligned: %zu", size);
@@ -404,7 +390,6 @@ void xe_print_blob_ascii85(struct drm_printer *p, const char *prefix,
 		line_pos += strlen(line_buff + line_pos);
 
 		if ((line_pos + MIN_SPACE) >= DMESG_MAX_LINE_LEN) {
-			line_buff[line_pos++] = '\n';
 			line_buff[line_pos++] = 0;
 
 			drm_puts(p, line_buff);
@@ -416,10 +401,11 @@ void xe_print_blob_ascii85(struct drm_printer *p, const char *prefix,
 		}
 	}
 
+	if (suffix)
+		line_buff[line_pos++] = suffix;
+
 	if (line_pos) {
-		line_buff[line_pos++] = '\n';
 		line_buff[line_pos++] = 0;
-
 		drm_puts(p, line_buff);
 	}
 
diff --git a/drivers/gpu/drm/xe/xe_devcoredump.h b/drivers/gpu/drm/xe/xe_devcoredump.h
index a4eebc285fc8..b231c8ad799f 100644
--- a/drivers/gpu/drm/xe/xe_devcoredump.h
+++ b/drivers/gpu/drm/xe/xe_devcoredump.h
@@ -26,7 +26,7 @@ static inline int xe_devcoredump_init(struct xe_device *xe)
 }
 #endif
 
-void xe_print_blob_ascii85(struct drm_printer *p, const char *prefix,
+void xe_print_blob_ascii85(struct drm_printer *p, const char *prefix, char suffix,
 			   const void *blob, size_t offset, size_t size);
 
 #endif
diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
index bb85208cf1a9..2e1d6d248d2e 100644
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@@ -37,6 +37,7 @@
 #include "xe_gt_printk.h"
 #include "xe_gt_sriov_vf.h"
 #include "xe_guc.h"
+#include "xe_guc_pc.h"
 #include "xe_hw_engine_group.h"
 #include "xe_hwmon.h"
 #include "xe_irq.h"
@@ -374,6 +375,11 @@ err:
 	return ERR_PTR(err);
 }
 
+static bool xe_driver_flr_disabled(struct xe_device *xe)
+{
+	return xe_mmio_read32(xe_root_mmio_gt(xe), GU_CNTL_PROTECTED) & DRIVERINT_FLR_DIS;
+}
+
 /*
  * The driver-initiated FLR is the highest level of reset that we can trigger
  * from within the driver. It is different from the PCI FLR in that it doesn't
@@ -387,17 +393,12 @@ err:
  * if/when a new instance of i915 is bound to the device it will do a full
  * re-init anyway.
  */
-static void xe_driver_flr(struct xe_device *xe)
+static void __xe_driver_flr(struct xe_device *xe)
 {
 	const unsigned int flr_timeout = 3 * MICRO; /* specs recommend a 3s wait */
 	struct xe_gt *gt = xe_root_mmio_gt(xe);
 	int ret;
 
-	if (xe_mmio_read32(gt, GU_CNTL_PROTECTED) & DRIVERINT_FLR_DIS) {
-		drm_info_once(&xe->drm, "BIOS Disabled Driver-FLR\n");
-		return;
-	}
-
 	drm_dbg(&xe->drm, "Triggering Driver-FLR\n");
 
 	/*
@@ -438,6 +439,16 @@ static void xe_driver_flr(struct xe_device *xe)
 	xe_mmio_write32(gt, GU_DEBUG, DRIVERFLR_STATUS);
 }
 
+static void xe_driver_flr(struct xe_device *xe)
+{
+	if (xe_driver_flr_disabled(xe)) {
+		drm_info_once(&xe->drm, "BIOS Disabled Driver-FLR\n");
+		return;
+	}
+
+	__xe_driver_flr(xe);
+}
+
 static void xe_driver_flr_fini(void *arg)
 {
 	struct xe_device *xe = arg;
@@ -538,6 +549,7 @@ static void update_device_info(struct xe_device *xe)
 	/* disable features that are not available/applicable to VFs */
 	if (IS_SRIOV_VF(xe)) {
 		xe->info.probe_display = 0;
+		xe->info.has_heci_cscfi = 0;
 		xe->info.has_heci_gscfi = 0;
 		xe->info.skip_guc_pc = 1;
 		xe->info.skip_pcode = 1;
@@ -694,7 +706,9 @@ int xe_device_probe(struct xe_device *xe)
 	}
 
 	/* Allocate and map stolen after potential VRAM resize */
-	xe_ttm_stolen_mgr_init(xe);
+	err = xe_ttm_stolen_mgr_init(xe);
+	if (err)
+		return err;
 
 	/*
 	 * Now that GT is initialized (TTM in particular),
@@ -706,6 +720,12 @@ int xe_device_probe(struct xe_device *xe)
 	if (err)
 		goto err;
 
+	for_each_tile(tile, xe, id) {
+		err = xe_tile_init(tile);
+		if (err)
+			goto err;
+	}
+
 	for_each_gt(gt, xe, id) {
 		last_gt = id;
 
@@ -789,6 +809,24 @@ void xe_device_remove(struct xe_device *xe)
 
 void xe_device_shutdown(struct xe_device *xe)
 {
+	struct xe_gt *gt;
+	u8 id;
+
+	drm_dbg(&xe->drm, "Shutting down device\n");
+
+	if (xe_driver_flr_disabled(xe)) {
+		xe_display_pm_shutdown(xe);
+
+		xe_irq_suspend(xe);
+
+		for_each_gt(gt, xe, id)
+			xe_gt_shutdown(gt);
+
+		xe_display_pm_shutdown_late(xe);
+	} else {
+		/* BOOM! */
+		__xe_driver_flr(xe);
+	}
 }
 
 /**
@@ -835,31 +873,37 @@ void xe_device_td_flush(struct xe_device *xe)
 	if (!IS_DGFX(xe) || GRAPHICS_VER(xe) < 20)
 		return;
 
-	if (XE_WA(xe_root_mmio_gt(xe), 16023588340)) {
+	gt = xe_root_mmio_gt(xe);
+	if (XE_WA(gt, 16023588340)) {
+		/* A transient flush is not sufficient: flush the L2 */
 		xe_device_l2_flush(xe);
-		return;
-	}
-
-	for_each_gt(gt, xe, id) {
-		if (xe_gt_is_media_type(gt))
-			continue;
-
-		if (xe_force_wake_get(gt_to_fw(gt), XE_FW_GT))
-			return;
-
-		xe_mmio_write32(gt, XE2_TDF_CTRL, TRANSIENT_FLUSH_REQUEST);
-		/*
-		 * FIXME: We can likely do better here with our choice of
-		 * timeout. Currently we just assume the worst case, i.e. 150us,
-		 * which is believed to be sufficient to cover the worst case
-		 * scenario on current platforms if all cache entries are
-		 * transient and need to be flushed..
-		 */
-		if (xe_mmio_wait32(gt, XE2_TDF_CTRL, TRANSIENT_FLUSH_REQUEST, 0,
-				   150, NULL, false))
-			xe_gt_err_once(gt, "TD flush timeout\n");
-
-		xe_force_wake_put(gt_to_fw(gt), XE_FW_GT);
+	} else {
+		xe_guc_pc_apply_flush_freq_limit(&gt->uc.guc.pc);
+		
+		/* Execute TDF flush on all graphics GTs */
+		for_each_gt(gt, xe, id) {
+			if (xe_gt_is_media_type(gt))
+				continue;
+
+			if (xe_force_wake_get(gt_to_fw(gt), XE_FW_GT))
+				return;
+
+			xe_mmio_write32(gt, XE2_TDF_CTRL, TRANSIENT_FLUSH_REQUEST);
+			/*
+			 * FIXME: We can likely do better here with our choice of
+			 * timeout. Currently we just assume the worst case, i.e. 150us,
+			 * which is believed to be sufficient to cover the worst case
+			 * scenario on current platforms if all cache entries are
+			 * transient and need to be flushed..
+			 */
+			if (xe_mmio_wait32(gt, XE2_TDF_CTRL, TRANSIENT_FLUSH_REQUEST, 0,
+					   150, NULL, false))
+				xe_gt_err_once(gt, "TD flush timeout\n");
+
+			xe_force_wake_put(gt_to_fw(gt), XE_FW_GT);
+		}
+		
+		xe_guc_pc_remove_flush_freq_limit(&xe_root_mmio_gt(xe)->uc.guc.pc);
 	}
 }
 
diff --git a/drivers/gpu/drm/xe/xe_dma_buf.c b/drivers/gpu/drm/xe/xe_dma_buf.c
index 68f309f5e981..78204578443f 100644
--- a/drivers/gpu/drm/xe/xe_dma_buf.c
+++ b/drivers/gpu/drm/xe/xe_dma_buf.c
@@ -58,7 +58,7 @@ static int xe_dma_buf_pin(struct dma_buf_attachment *attach)
 	 * 1) Avoid pinning in a placement not accessible to some importers.
 	 * 2) Pinning in VRAM requires PIN accounting which is a to-do.
 	 */
-	if (xe_bo_is_pinned(bo) && bo->ttm.resource->placement != XE_PL_TT) {
+	if (xe_bo_is_pinned(bo) && !xe_bo_is_mem_type(bo, XE_PL_TT)) {
 		drm_dbg(&xe->drm, "Can't migrate pinned bo for dma-buf pin.\n");
 		return -EINVAL;
 	}
@@ -145,10 +145,7 @@ static void xe_dma_buf_unmap(struct dma_buf_attachment *attach,
 			     struct sg_table *sgt,
 			     enum dma_data_direction dir)
 {
-	struct dma_buf *dma_buf = attach->dmabuf;
-	struct xe_bo *bo = gem_to_xe_bo(dma_buf->priv);
-
-	if (!xe_bo_is_vram(bo)) {
+	if (sg_page(sgt->sgl)) {
 		dma_unmap_sgtable(attach->dev, sgt, dir, 0);
 		sg_free_table(sgt);
 		kfree(sgt);
diff --git a/drivers/gpu/drm/xe/xe_drm_client.c b/drivers/gpu/drm/xe/xe_drm_client.c
index fb52a23e28f8..a89fbfbdab32 100644
--- a/drivers/gpu/drm/xe/xe_drm_client.c
+++ b/drivers/gpu/drm/xe/xe_drm_client.c
@@ -135,8 +135,8 @@ void xe_drm_client_add_bo(struct xe_drm_client *client,
 	XE_WARN_ON(bo->client);
 	XE_WARN_ON(!list_empty(&bo->client_link));
 
-	spin_lock(&client->bos_lock);
 	bo->client = xe_drm_client_get(client);
+	spin_lock(&client->bos_lock);
 	list_add_tail(&bo->client_link, &client->bos_list);
 	spin_unlock(&client->bos_lock);
 }
diff --git a/drivers/gpu/drm/xe/xe_force_wake.h b/drivers/gpu/drm/xe/xe_force_wake.h
index 1608a55edc84..a2577672f4e3 100644
--- a/drivers/gpu/drm/xe/xe_force_wake.h
+++ b/drivers/gpu/drm/xe/xe_force_wake.h
@@ -46,20 +46,4 @@ xe_force_wake_assert_held(struct xe_force_wake *fw,
 	xe_gt_assert(fw->gt, fw->awake_domains & domain);
 }
 
-/**
- * xe_force_wake_ref_has_domain - verifies if the domains are in fw_ref
- * @fw_ref : the force_wake reference
- * @domain : forcewake domain to verify
- *
- * This function confirms whether the @fw_ref includes a reference to the
- * specified @domain.
- *
- * Return: true if domain is refcounted.
- */
-static inline bool
-xe_force_wake_ref_has_domain(unsigned int fw_ref, enum xe_force_wake_domains domain)
-{
-	return fw_ref & domain;
-}
-
 #endif
diff --git a/drivers/gpu/drm/xe/xe_gen_wa_oob.c b/drivers/gpu/drm/xe/xe_gen_wa_oob.c
index 904cf47925aa..ed9183599e31 100644
--- a/drivers/gpu/drm/xe/xe_gen_wa_oob.c
+++ b/drivers/gpu/drm/xe/xe_gen_wa_oob.c
@@ -28,10 +28,10 @@
 	"\n" \
 	"#endif\n"
 
-static void print_usage(FILE *f)
+static void print_usage(FILE *f, const char *progname)
 {
 	fprintf(f, "usage: %s <input-rule-file> <generated-c-source-file> <generated-c-header-file>\n",
-		program_invocation_short_name);
+		progname);
 }
 
 static void print_parse_error(const char *err_msg, const char *line,
@@ -144,7 +144,7 @@ int main(int argc, const char *argv[])
 
 	if (argc < 3) {
 		fprintf(stderr, "ERROR: wrong arguments\n");
-		print_usage(stderr);
+		print_usage(stderr, argv[0]);
 		return 1;
 	}
 
diff --git a/drivers/gpu/drm/xe/xe_ggtt.c b/drivers/gpu/drm/xe/xe_ggtt.c
index ff19eca5d358..76e1092f51d9 100644
--- a/drivers/gpu/drm/xe/xe_ggtt.c
+++ b/drivers/gpu/drm/xe/xe_ggtt.c
@@ -198,6 +198,13 @@ static const struct xe_ggtt_pt_ops xelpg_pt_wa_ops = {
 	.ggtt_set_pte = xe_ggtt_set_pte_and_flush,
 };
 
+static void dev_fini_ggtt(void *arg)
+{
+	struct xe_ggtt *ggtt = arg;
+
+	drain_workqueue(ggtt->wq);
+}
+
 /**
  * xe_ggtt_init_early - Early GGTT initialization
  * @ggtt: the &xe_ggtt to be initialized
@@ -254,6 +261,10 @@ int xe_ggtt_init_early(struct xe_ggtt *ggtt)
 	if (err)
 		return err;
 
+	err = devm_add_action_or_reset(xe->drm.dev, dev_fini_ggtt, ggtt);
+	if (err)
+		return err;
+
 	if (IS_SRIOV_VF(xe)) {
 		err = xe_gt_sriov_vf_prepare_ggtt(xe_tile_get_gt(ggtt->tile, 0));
 		if (err)
@@ -594,10 +605,10 @@ void xe_ggtt_map_bo(struct xe_ggtt *ggtt, struct xe_bo *bo)
 	u64 start;
 	u64 offset, pte;
 
-	if (XE_WARN_ON(!bo->ggtt_node))
+	if (XE_WARN_ON(!bo->ggtt_node[ggtt->tile->id]))
 		return;
 
-	start = bo->ggtt_node->base.start;
+	start = bo->ggtt_node[ggtt->tile->id]->base.start;
 
 	for (offset = 0; offset < bo->size; offset += XE_PAGE_SIZE) {
 		pte = ggtt->pt_ops->pte_encode_bo(bo, offset, pat_index);
@@ -608,15 +619,16 @@ void xe_ggtt_map_bo(struct xe_ggtt *ggtt, struct xe_bo *bo)
 static int __xe_ggtt_insert_bo_at(struct xe_ggtt *ggtt, struct xe_bo *bo,
 				  u64 start, u64 end)
 {
+	u64 alignment = bo->min_align > 0 ? bo->min_align : XE_PAGE_SIZE;
+	u8 tile_id = ggtt->tile->id;
 	int err;
-	u64 alignment = XE_PAGE_SIZE;
 
 	if (xe_bo_is_vram(bo) && ggtt->flags & XE_GGTT_FLAGS_64K)
 		alignment = SZ_64K;
 
-	if (XE_WARN_ON(bo->ggtt_node)) {
+	if (XE_WARN_ON(bo->ggtt_node[tile_id])) {
 		/* Someone's already inserted this BO in the GGTT */
-		xe_tile_assert(ggtt->tile, bo->ggtt_node->base.size == bo->size);
+		xe_tile_assert(ggtt->tile, bo->ggtt_node[tile_id]->base.size == bo->size);
 		return 0;
 	}
 
@@ -626,19 +638,19 @@ static int __xe_ggtt_insert_bo_at(struct xe_ggtt *ggtt, struct xe_bo *bo,
 
 	xe_pm_runtime_get_noresume(tile_to_xe(ggtt->tile));
 
-	bo->ggtt_node = xe_ggtt_node_init(ggtt);
-	if (IS_ERR(bo->ggtt_node)) {
-		err = PTR_ERR(bo->ggtt_node);
-		bo->ggtt_node = NULL;
+	bo->ggtt_node[tile_id] = xe_ggtt_node_init(ggtt);
+	if (IS_ERR(bo->ggtt_node[tile_id])) {
+		err = PTR_ERR(bo->ggtt_node[tile_id]);
+		bo->ggtt_node[tile_id] = NULL;
 		goto out;
 	}
 
 	mutex_lock(&ggtt->lock);
-	err = drm_mm_insert_node_in_range(&ggtt->mm, &bo->ggtt_node->base, bo->size,
-					  alignment, 0, start, end, 0);
+	err = drm_mm_insert_node_in_range(&ggtt->mm, &bo->ggtt_node[tile_id]->base,
+					  bo->size, alignment, 0, start, end, 0);
 	if (err) {
-		xe_ggtt_node_fini(bo->ggtt_node);
-		bo->ggtt_node = NULL;
+		xe_ggtt_node_fini(bo->ggtt_node[tile_id]);
+		bo->ggtt_node[tile_id] = NULL;
 	} else {
 		xe_ggtt_map_bo(ggtt, bo);
 	}
@@ -687,13 +699,15 @@ int xe_ggtt_insert_bo(struct xe_ggtt *ggtt, struct xe_bo *bo)
  */
 void xe_ggtt_remove_bo(struct xe_ggtt *ggtt, struct xe_bo *bo)
 {
-	if (XE_WARN_ON(!bo->ggtt_node))
+	u8 tile_id = ggtt->tile->id;
+
+	if (XE_WARN_ON(!bo->ggtt_node[tile_id]))
 		return;
 
 	/* This BO is not currently in the GGTT */
-	xe_tile_assert(ggtt->tile, bo->ggtt_node->base.size == bo->size);
+	xe_tile_assert(ggtt->tile, bo->ggtt_node[tile_id]->base.size == bo->size);
 
-	xe_ggtt_node_remove(bo->ggtt_node,
+	xe_ggtt_node_remove(bo->ggtt_node[tile_id],
 			    bo->flags & XE_BO_FLAG_GGTT_INVALIDATE);
 }
 
diff --git a/drivers/gpu/drm/xe/xe_gpu_scheduler.h b/drivers/gpu/drm/xe/xe_gpu_scheduler.h
index 64b2ae6839db..400b2e9e89ab 100644
--- a/drivers/gpu/drm/xe/xe_gpu_scheduler.h
+++ b/drivers/gpu/drm/xe/xe_gpu_scheduler.h
@@ -51,7 +51,15 @@ static inline void xe_sched_tdr_queue_imm(struct xe_gpu_scheduler *sched)
 
 static inline void xe_sched_resubmit_jobs(struct xe_gpu_scheduler *sched)
 {
-	drm_sched_resubmit_jobs(&sched->base);
+	struct drm_sched_job *s_job;
+
+	list_for_each_entry(s_job, &sched->base.pending_list, list) {
+		struct drm_sched_fence *s_fence = s_job->s_fence;
+		struct dma_fence *hw_fence = s_fence->parent;
+
+		if (hw_fence && !dma_fence_is_signaled(hw_fence))
+			sched->base.ops->run_job(s_job);
+	}
 }
 
 static inline bool
diff --git a/drivers/gpu/drm/xe/xe_gsc.c b/drivers/gpu/drm/xe/xe_gsc.c
index 6fbea70d3d36..feb680d127e6 100644
--- a/drivers/gpu/drm/xe/xe_gsc.c
+++ b/drivers/gpu/drm/xe/xe_gsc.c
@@ -564,6 +564,28 @@ void xe_gsc_remove(struct xe_gsc *gsc)
 	xe_gsc_proxy_remove(gsc);
 }
 
+void xe_gsc_stop_prepare(struct xe_gsc *gsc)
+{
+	struct xe_gt *gt = gsc_to_gt(gsc);
+	int ret;
+
+	if (!xe_uc_fw_is_loadable(&gsc->fw) || xe_uc_fw_is_in_error_state(&gsc->fw))
+		return;
+
+	xe_force_wake_assert_held(gt_to_fw(gt), XE_FW_GSC);
+
+	/*
+	 * If the GSC FW load or the proxy init are interrupted, the only way
+	 * to recover it is to do an FLR and reload the GSC from scratch.
+	 * Therefore, let's wait for the init to complete before stopping
+	 * operations. The proxy init is the last step, so we can just wait on
+	 * that
+	 */
+	ret = xe_gsc_wait_for_proxy_init_done(gsc);
+	if (ret)
+		xe_gt_err(gt, "failed to wait for GSC init completion before uc stop\n");
+}
+
 /*
  * wa_14015076503: if the GSC FW is loaded, we need to alert it before doing a
  * GSC engine reset by writing a notification bit in the GS1 register and then
diff --git a/drivers/gpu/drm/xe/xe_gsc.h b/drivers/gpu/drm/xe/xe_gsc.h
index e282b9ef6ec4..c31fe24c4b66 100644
--- a/drivers/gpu/drm/xe/xe_gsc.h
+++ b/drivers/gpu/drm/xe/xe_gsc.h
@@ -16,6 +16,7 @@ struct xe_hw_engine;
 int xe_gsc_init(struct xe_gsc *gsc);
 int xe_gsc_init_post_hwconfig(struct xe_gsc *gsc);
 void xe_gsc_wait_for_worker_completion(struct xe_gsc *gsc);
+void xe_gsc_stop_prepare(struct xe_gsc *gsc);
 void xe_gsc_load_start(struct xe_gsc *gsc);
 void xe_gsc_remove(struct xe_gsc *gsc);
 void xe_gsc_hwe_irq_handler(struct xe_hw_engine *hwe, u16 intr_vec);
diff --git a/drivers/gpu/drm/xe/xe_gsc_proxy.c b/drivers/gpu/drm/xe/xe_gsc_proxy.c
index 2d6ea8c01445..85801de4fab1 100644
--- a/drivers/gpu/drm/xe/xe_gsc_proxy.c
+++ b/drivers/gpu/drm/xe/xe_gsc_proxy.c
@@ -71,6 +71,17 @@ bool xe_gsc_proxy_init_done(struct xe_gsc *gsc)
 	       HECI1_FWSTS1_PROXY_STATE_NORMAL;
 }
 
+int xe_gsc_wait_for_proxy_init_done(struct xe_gsc *gsc)
+{
+	struct xe_gt *gt = gsc_to_gt(gsc);
+
+	/* Proxy init can take up to 500ms, so wait double that for safety */
+	return xe_mmio_wait32(gt, HECI_FWSTS1(MTL_GSC_HECI1_BASE),
+			      HECI1_FWSTS1_CURRENT_STATE,
+			      HECI1_FWSTS1_PROXY_STATE_NORMAL,
+			      USEC_PER_SEC, NULL, false);
+}
+
 static void __gsc_proxy_irq_rmw(struct xe_gsc *gsc, u32 clr, u32 set)
 {
 	struct xe_gt *gt = gsc_to_gt(gsc);
diff --git a/drivers/gpu/drm/xe/xe_gsc_proxy.h b/drivers/gpu/drm/xe/xe_gsc_proxy.h
index c511ade6b863..e2498aa6de18 100644
--- a/drivers/gpu/drm/xe/xe_gsc_proxy.h
+++ b/drivers/gpu/drm/xe/xe_gsc_proxy.h
@@ -13,6 +13,7 @@ struct xe_gsc;
 int xe_gsc_proxy_init(struct xe_gsc *gsc);
 bool xe_gsc_proxy_init_done(struct xe_gsc *gsc);
 void xe_gsc_proxy_remove(struct xe_gsc *gsc);
+int xe_gsc_wait_for_proxy_init_done(struct xe_gsc *gsc);
 int xe_gsc_proxy_start(struct xe_gsc *gsc);
 
 int xe_gsc_proxy_request_handler(struct xe_gsc *gsc);
diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c
index b940688c3613..3b53d46aad54 100644
--- a/drivers/gpu/drm/xe/xe_gt.c
+++ b/drivers/gpu/drm/xe/xe_gt.c
@@ -32,6 +32,7 @@
 #include "xe_gt_pagefault.h"
 #include "xe_gt_printk.h"
 #include "xe_gt_sriov_pf.h"
+#include "xe_gt_sriov_vf.h"
 #include "xe_gt_sysfs.h"
 #include "xe_gt_tlb_invalidation.h"
 #include "xe_gt_topology.h"
@@ -113,7 +114,7 @@ static void xe_gt_enable_host_l2_vram(struct xe_gt *gt)
 		xe_gt_mcr_multicast_write(gt, XE2_GAMREQSTRM_CTRL, reg);
 	}
 
-	xe_gt_mcr_multicast_write(gt, XEHPC_L3CLOS_MASK(3), 0x3);
+	xe_gt_mcr_multicast_write(gt, XEHPC_L3CLOS_MASK(3), 0xF);
 	xe_force_wake_put(gt_to_fw(gt), XE_FW_GT);
 }
 
@@ -379,9 +380,7 @@ int xe_gt_init_early(struct xe_gt *gt)
 	if (err)
 		return err;
 
-	xe_wa_process_gt(gt);
 	xe_wa_process_oob(gt);
-	xe_tuning_process_gt(gt);
 
 	xe_force_wake_init_gt(gt, gt_to_fw(gt));
 	spin_lock_init(&gt->global_invl_lock);
@@ -390,6 +389,8 @@ int xe_gt_init_early(struct xe_gt *gt)
 	if (err)
 		return err;
 
+	xe_mocs_init_early(gt);
+
 	return 0;
 }
 
@@ -469,6 +470,8 @@ static int all_fw_domain_init(struct xe_gt *gt)
 		goto err_hw_fence_irq;
 
 	xe_gt_mcr_set_implicit_defaults(gt);
+	xe_wa_process_gt(gt);
+	xe_tuning_process_gt(gt);
 	xe_reg_sr_apply_mmio(&gt->reg_sr, gt);
 
 	err = xe_gt_clock_init(gt);
@@ -589,17 +592,15 @@ int xe_gt_init(struct xe_gt *gt)
 		xe_hw_fence_irq_init(&gt->fence_irq[i]);
 	}
 
-	err = xe_gt_pagefault_init(gt);
+	err = xe_gt_sysfs_init(gt);
 	if (err)
 		return err;
 
-	xe_mocs_init_early(gt);
-
-	err = xe_gt_sysfs_init(gt);
+	err = gt_fw_domain_init(gt);
 	if (err)
 		return err;
 
-	err = gt_fw_domain_init(gt);
+	err = xe_gt_pagefault_init(gt);
 	if (err)
 		return err;
 
@@ -647,6 +648,9 @@ static int do_gt_reset(struct xe_gt *gt)
 {
 	int err;
 
+	if (IS_SRIOV_VF(gt_to_xe(gt)))
+		return xe_gt_sriov_vf_reset(gt);
+
 	xe_gsc_wa_14015076503(gt, true);
 
 	xe_mmio_write32(gt, GDRST, GRDOM_FULL);
@@ -764,6 +768,9 @@ static int gt_reset(struct xe_gt *gt)
 	if (err)
 		goto err_msg;
 
+	if (IS_SRIOV_PF(gt_to_xe(gt)))
+		xe_gt_sriov_pf_stop_prepare(gt);
+
 	xe_uc_gucrc_disable(&gt->uc);
 	xe_uc_stop_prepare(&gt->uc);
 	xe_gt_pagefault_reset(gt);
@@ -824,7 +831,7 @@ void xe_gt_suspend_prepare(struct xe_gt *gt)
 {
 	XE_WARN_ON(xe_force_wake_get(gt_to_fw(gt), XE_FORCEWAKE_ALL));
 
-	xe_uc_stop_prepare(&gt->uc);
+	xe_uc_suspend_prepare(&gt->uc);
 
 	XE_WARN_ON(xe_force_wake_put(gt_to_fw(gt), XE_FORCEWAKE_ALL));
 }
@@ -861,6 +868,13 @@ err_msg:
 	return err;
 }
 
+void xe_gt_shutdown(struct xe_gt *gt)
+{
+	xe_force_wake_get(gt_to_fw(gt), XE_FORCEWAKE_ALL);
+	do_gt_reset(gt);
+	xe_force_wake_put(gt_to_fw(gt), XE_FORCEWAKE_ALL);
+}
+
 /**
  * xe_gt_sanitize_freq() - Restore saved frequencies if necessary.
  * @gt: the GT object
diff --git a/drivers/gpu/drm/xe/xe_gt.h b/drivers/gpu/drm/xe/xe_gt.h
index ee138e9768a2..881f1cbc2c49 100644
--- a/drivers/gpu/drm/xe/xe_gt.h
+++ b/drivers/gpu/drm/xe/xe_gt.h
@@ -48,6 +48,7 @@ void xe_gt_record_user_engines(struct xe_gt *gt);
 
 void xe_gt_suspend_prepare(struct xe_gt *gt);
 int xe_gt_suspend(struct xe_gt *gt);
+void xe_gt_shutdown(struct xe_gt *gt);
 int xe_gt_resume(struct xe_gt *gt);
 void xe_gt_reset_async(struct xe_gt *gt);
 void xe_gt_sanitize(struct xe_gt *gt);
diff --git a/drivers/gpu/drm/xe/xe_gt_freq.c b/drivers/gpu/drm/xe/xe_gt_freq.c
index ab76973f3e1e..a05fde2c7b12 100644
--- a/drivers/gpu/drm/xe/xe_gt_freq.c
+++ b/drivers/gpu/drm/xe/xe_gt_freq.c
@@ -32,6 +32,7 @@
  * Xe's Freq provides a sysfs API for frequency management:
  *
  * device/tile#/gt#/freq0/<item>_freq *read-only* files:
+ *
  * - act_freq: The actual resolved frequency decided by PCODE.
  * - cur_freq: The current one requested by GuC PC to the PCODE.
  * - rpn_freq: The Render Performance (RP) N level, which is the minimal one.
@@ -39,6 +40,7 @@
  * - rp0_freq: The Render Performance (RP) 0 level, which is the maximum one.
  *
  * device/tile#/gt#/freq0/<item>_freq *read-write* files:
+ *
  * - min_freq: Min frequency request.
  * - max_freq: Max frequency request.
  *             If max <= min, then freq_min becomes a fixed frequency request.
diff --git a/drivers/gpu/drm/xe/xe_gt_pagefault.c b/drivers/gpu/drm/xe/xe_gt_pagefault.c
index 79c426dc2505..656c2ab6ca9f 100644
--- a/drivers/gpu/drm/xe/xe_gt_pagefault.c
+++ b/drivers/gpu/drm/xe/xe_gt_pagefault.c
@@ -423,9 +423,17 @@ static int xe_alloc_pf_queue(struct xe_gt *gt, struct pf_queue *pf_queue)
 	num_eus = bitmap_weight(gt->fuse_topo.eu_mask_per_dss,
 				XE_MAX_EU_FUSE_BITS) * num_dss;
 
-	/* user can issue separate page faults per EU and per CS */
+	/*
+	 * user can issue separate page faults per EU and per CS
+	 *
+	 * XXX: Multiplier required as compute UMD are getting PF queue errors
+	 * without it. Follow on why this multiplier is required.
+	 */
+#define PF_MULTIPLIER	8
 	pf_queue->num_dw =
-		(num_eus + XE_NUM_HW_ENGINES) * PF_MSG_LEN_DW;
+		(num_eus + XE_NUM_HW_ENGINES) * PF_MSG_LEN_DW * PF_MULTIPLIER;
+	pf_queue->num_dw = roundup_pow_of_two(pf_queue->num_dw);
+#undef PF_MULTIPLIER
 
 	pf_queue->gt = gt;
 	pf_queue->data = devm_kcalloc(xe->drm.dev, pf_queue->num_dw,
diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf.c b/drivers/gpu/drm/xe/xe_gt_sriov_pf.c
index 905f409db74b..57e9eddc092e 100644
--- a/drivers/gpu/drm/xe/xe_gt_sriov_pf.c
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf.c
@@ -5,14 +5,20 @@
 
 #include <drm/drm_managed.h>
 
+#include "regs/xe_guc_regs.h"
 #include "regs/xe_regs.h"
 
+#include "xe_gt.h"
 #include "xe_gt_sriov_pf.h"
 #include "xe_gt_sriov_pf_config.h"
 #include "xe_gt_sriov_pf_control.h"
 #include "xe_gt_sriov_pf_helpers.h"
 #include "xe_gt_sriov_pf_service.h"
+#include "xe_gt_sriov_printk.h"
 #include "xe_mmio.h"
+#include "xe_pm.h"
+
+static void pf_worker_restart_func(struct work_struct *w);
 
 /*
  * VF's metadata is maintained in the flexible array where:
@@ -38,6 +44,11 @@ static int pf_alloc_metadata(struct xe_gt *gt)
 	return 0;
 }
 
+static void pf_init_workers(struct xe_gt *gt)
+{
+	INIT_WORK(&gt->sriov.pf.workers.restart, pf_worker_restart_func);
+}
+
 /**
  * xe_gt_sriov_pf_init_early - Prepare SR-IOV PF data structures on PF.
  * @gt: the &xe_gt to initialize
@@ -62,6 +73,8 @@ int xe_gt_sriov_pf_init_early(struct xe_gt *gt)
 	if (err)
 		return err;
 
+	pf_init_workers(gt);
+
 	return 0;
 }
 
@@ -89,14 +102,111 @@ void xe_gt_sriov_pf_init_hw(struct xe_gt *gt)
 	xe_gt_sriov_pf_service_update(gt);
 }
 
+static u32 pf_get_vf_regs_stride(struct xe_device *xe)
+{
+	return GRAPHICS_VERx100(xe) > 1200 ? 0x400 : 0x1000;
+}
+
+static struct xe_reg xe_reg_vf_to_pf(struct xe_reg vf_reg, unsigned int vfid, u32 stride)
+{
+	struct xe_reg pf_reg = vf_reg;
+
+	pf_reg.vf = 0;
+	pf_reg.addr += stride * vfid;
+
+	return pf_reg;
+}
+
+static void pf_clear_vf_scratch_regs(struct xe_gt *gt, unsigned int vfid)
+{
+	u32 stride = pf_get_vf_regs_stride(gt_to_xe(gt));
+	struct xe_reg scratch;
+	int n, count;
+
+	if (xe_gt_is_media_type(gt)) {
+		count = MED_VF_SW_FLAG_COUNT;
+		for (n = 0; n < count; n++) {
+			scratch = xe_reg_vf_to_pf(MED_VF_SW_FLAG(n), vfid, stride);
+			xe_mmio_write32(gt, scratch, 0);
+		}
+	} else {
+		count = VF_SW_FLAG_COUNT;
+		for (n = 0; n < count; n++) {
+			scratch = xe_reg_vf_to_pf(VF_SW_FLAG(n), vfid, stride);
+			xe_mmio_write32(gt, scratch, 0);
+		}
+	}
+}
+
 /**
- * xe_gt_sriov_pf_restart - Restart SR-IOV support after a GT reset.
+ * xe_gt_sriov_pf_sanitize_hw() - Reset hardware state related to a VF.
  * @gt: the &xe_gt
+ * @vfid: the VF identifier
  *
  * This function can only be called on PF.
  */
-void xe_gt_sriov_pf_restart(struct xe_gt *gt)
+void xe_gt_sriov_pf_sanitize_hw(struct xe_gt *gt, unsigned int vfid)
+{
+	xe_gt_assert(gt, IS_SRIOV_PF(gt_to_xe(gt)));
+
+	pf_clear_vf_scratch_regs(gt, vfid);
+}
+
+static void pf_cancel_restart(struct xe_gt *gt)
+{
+	xe_gt_assert(gt, IS_SRIOV_PF(gt_to_xe(gt)));
+
+	if (cancel_work_sync(&gt->sriov.pf.workers.restart))
+		xe_gt_sriov_dbg_verbose(gt, "pending restart canceled!\n");
+}
+
+/**
+ * xe_gt_sriov_pf_stop_prepare() - Prepare to stop SR-IOV support.
+ * @gt: the &xe_gt
+ *
+ * This function can only be called on the PF.
+ */
+void xe_gt_sriov_pf_stop_prepare(struct xe_gt *gt)
 {
+	pf_cancel_restart(gt);
+}
+
+static void pf_restart(struct xe_gt *gt)
+{
+	struct xe_device *xe = gt_to_xe(gt);
+
+	xe_pm_runtime_get(xe);
 	xe_gt_sriov_pf_config_restart(gt);
 	xe_gt_sriov_pf_control_restart(gt);
+	xe_pm_runtime_put(xe);
+
+	xe_gt_sriov_dbg(gt, "restart completed\n");
+}
+
+static void pf_worker_restart_func(struct work_struct *w)
+{
+	struct xe_gt *gt = container_of(w, typeof(*gt), sriov.pf.workers.restart);
+
+	pf_restart(gt);
+}
+
+static void pf_queue_restart(struct xe_gt *gt)
+{
+	struct xe_device *xe = gt_to_xe(gt);
+
+	xe_gt_assert(gt, IS_SRIOV_PF(xe));
+
+	if (!queue_work(xe->sriov.wq, &gt->sriov.pf.workers.restart))
+		xe_gt_sriov_dbg(gt, "restart already in queue!\n");
+}
+
+/**
+ * xe_gt_sriov_pf_restart - Restart SR-IOV support after a GT reset.
+ * @gt: the &xe_gt
+ *
+ * This function can only be called on PF.
+ */
+void xe_gt_sriov_pf_restart(struct xe_gt *gt)
+{
+	pf_queue_restart(gt);
 }
diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf.h b/drivers/gpu/drm/xe/xe_gt_sriov_pf.h
index f0cb726a6919..165ba31d0391 100644
--- a/drivers/gpu/drm/xe/xe_gt_sriov_pf.h
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf.h
@@ -11,6 +11,8 @@ struct xe_gt;
 #ifdef CONFIG_PCI_IOV
 int xe_gt_sriov_pf_init_early(struct xe_gt *gt);
 void xe_gt_sriov_pf_init_hw(struct xe_gt *gt);
+void xe_gt_sriov_pf_sanitize_hw(struct xe_gt *gt, unsigned int vfid);
+void xe_gt_sriov_pf_stop_prepare(struct xe_gt *gt);
 void xe_gt_sriov_pf_restart(struct xe_gt *gt);
 #else
 static inline int xe_gt_sriov_pf_init_early(struct xe_gt *gt)
@@ -22,6 +24,10 @@ static inline void xe_gt_sriov_pf_init_hw(struct xe_gt *gt)
 {
 }
 
+static inline void xe_gt_sriov_pf_stop_prepare(struct xe_gt *gt)
+{
+}
+
 static inline void xe_gt_sriov_pf_restart(struct xe_gt *gt)
 {
 }
diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
index c9ed996b9cb0..786f0dba4143 100644
--- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
@@ -323,6 +323,26 @@ static int pf_push_full_vf_config(struct xe_gt *gt, unsigned int vfid)
 	return err;
 }
 
+static int pf_push_vf_cfg(struct xe_gt *gt, unsigned int vfid, bool reset)
+{
+	int err = 0;
+
+	xe_gt_assert(gt, vfid);
+	lockdep_assert_held(xe_gt_sriov_pf_master_mutex(gt));
+
+	if (reset)
+		err = pf_send_vf_cfg_reset(gt, vfid);
+	if (!err)
+		err = pf_push_full_vf_config(gt, vfid);
+
+	return err;
+}
+
+static int pf_refresh_vf_cfg(struct xe_gt *gt, unsigned int vfid)
+{
+	return pf_push_vf_cfg(gt, vfid, true);
+}
+
 static u64 pf_get_ggtt_alignment(struct xe_gt *gt)
 {
 	struct xe_device *xe = gt_to_xe(gt);
@@ -419,6 +439,10 @@ static int pf_provision_vf_ggtt(struct xe_gt *gt, unsigned int vfid, u64 size)
 			return err;
 
 		pf_release_vf_config_ggtt(gt, config);
+
+		err = pf_refresh_vf_cfg(gt, vfid);
+		if (unlikely(err))
+			return err;
 	}
 	xe_gt_assert(gt, !xe_ggtt_node_allocated(config->ggtt_region));
 
@@ -744,6 +768,10 @@ static int pf_provision_vf_ctxs(struct xe_gt *gt, unsigned int vfid, u32 num_ctx
 			return ret;
 
 		pf_release_config_ctxs(gt, config);
+
+		ret = pf_refresh_vf_cfg(gt, vfid);
+		if (unlikely(ret))
+			return ret;
 	}
 
 	if (!num_ctxs)
@@ -1041,6 +1069,10 @@ static int pf_provision_vf_dbs(struct xe_gt *gt, unsigned int vfid, u32 num_dbs)
 			return ret;
 
 		pf_release_config_dbs(gt, config);
+
+		ret = pf_refresh_vf_cfg(gt, vfid);
+		if (unlikely(ret))
+			return ret;
 	}
 
 	if (!num_dbs)
@@ -2003,10 +2035,7 @@ int xe_gt_sriov_pf_config_push(struct xe_gt *gt, unsigned int vfid, bool refresh
 	xe_gt_assert(gt, vfid);
 
 	mutex_lock(xe_gt_sriov_pf_master_mutex(gt));
-	if (refresh)
-		err = pf_send_vf_cfg_reset(gt, vfid);
-	if (!err)
-		err = pf_push_full_vf_config(gt, vfid);
+	err = pf_push_vf_cfg(gt, vfid, refresh);
 	mutex_unlock(xe_gt_sriov_pf_master_mutex(gt));
 
 	if (unlikely(err)) {
diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf_control.c b/drivers/gpu/drm/xe/xe_gt_sriov_pf_control.c
index 02f7328bd6ce..b4fd5a81aff1 100644
--- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_control.c
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_control.c
@@ -9,6 +9,7 @@
 
 #include "xe_device.h"
 #include "xe_gt.h"
+#include "xe_gt_sriov_pf.h"
 #include "xe_gt_sriov_pf_config.h"
 #include "xe_gt_sriov_pf_control.h"
 #include "xe_gt_sriov_pf_helpers.h"
@@ -1008,7 +1009,7 @@ static bool pf_exit_vf_flr_reset_mmio(struct xe_gt *gt, unsigned int vfid)
 	if (!pf_exit_vf_state(gt, vfid, XE_GT_SRIOV_STATE_FLR_RESET_MMIO))
 		return false;
 
-	/* XXX: placeholder */
+	xe_gt_sriov_pf_sanitize_hw(gt, vfid);
 
 	pf_enter_vf_flr_send_finish(gt, vfid);
 	return true;
diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf_types.h b/drivers/gpu/drm/xe/xe_gt_sriov_pf_types.h
index 28e1b130bf87..a69d128c4f45 100644
--- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_types.h
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_types.h
@@ -32,7 +32,16 @@ struct xe_gt_sriov_metadata {
 };
 
 /**
+ * struct xe_gt_sriov_pf_workers - GT level workers used by the PF.
+ */
+struct xe_gt_sriov_pf_workers {
+	/** @restart: worker that executes actions post GT reset */
+	struct work_struct restart;
+};
+
+/**
  * struct xe_gt_sriov_pf - GT level PF virtualization data.
+ * @workers: workers data.
  * @service: service data.
  * @control: control data.
  * @policy: policy data.
@@ -40,6 +49,7 @@ struct xe_gt_sriov_metadata {
  * @vfs: metadata for all VFs.
  */
 struct xe_gt_sriov_pf {
+	struct xe_gt_sriov_pf_workers workers;
 	struct xe_gt_sriov_pf_service service;
 	struct xe_gt_sriov_pf_control control;
 	struct xe_gt_sriov_pf_policy policy;
diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_vf.c b/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
index 4ebc82e607af..29badbd829ab 100644
--- a/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
@@ -46,17 +46,40 @@ static int guc_action_vf_reset(struct xe_guc *guc)
 	return ret > 0 ? -EPROTO : ret;
 }
 
+#define GUC_RESET_VF_STATE_RETRY_MAX	10
 static int vf_reset_guc_state(struct xe_gt *gt)
 {
+	unsigned int retry = GUC_RESET_VF_STATE_RETRY_MAX;
 	struct xe_guc *guc = &gt->uc.guc;
 	int err;
 
-	err = guc_action_vf_reset(guc);
+	do {
+		err = guc_action_vf_reset(guc);
+		if (!err || err != -ETIMEDOUT)
+			break;
+	} while (--retry);
+
 	if (unlikely(err))
 		xe_gt_sriov_err(gt, "Failed to reset GuC state (%pe)\n", ERR_PTR(err));
 	return err;
 }
 
+/**
+ * xe_gt_sriov_vf_reset - Reset GuC VF internal state.
+ * @gt: the &xe_gt
+ *
+ * It requires functional `GuC MMIO based communication`_.
+ *
+ * Return: 0 on success or a negative error code on failure.
+ */
+int xe_gt_sriov_vf_reset(struct xe_gt *gt)
+{
+	if (!xe_device_uc_enabled(gt_to_xe(gt)))
+		return -ENODEV;
+
+	return vf_reset_guc_state(gt);
+}
+
 static int guc_action_match_version(struct xe_guc *guc,
 				    u32 wanted_branch, u32 wanted_major, u32 wanted_minor,
 				    u32 *branch, u32 *major, u32 *minor, u32 *patch)
@@ -212,6 +235,9 @@ int xe_gt_sriov_vf_bootstrap(struct xe_gt *gt)
 {
 	int err;
 
+	if (!xe_device_uc_enabled(gt_to_xe(gt)))
+		return -ENODEV;
+
 	err = vf_reset_guc_state(gt);
 	if (unlikely(err))
 		return err;
diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_vf.h b/drivers/gpu/drm/xe/xe_gt_sriov_vf.h
index e541ce57bec2..576ff5e795a8 100644
--- a/drivers/gpu/drm/xe/xe_gt_sriov_vf.h
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_vf.h
@@ -12,6 +12,7 @@ struct drm_printer;
 struct xe_gt;
 struct xe_reg;
 
+int xe_gt_sriov_vf_reset(struct xe_gt *gt);
 int xe_gt_sriov_vf_bootstrap(struct xe_gt *gt);
 int xe_gt_sriov_vf_query_config(struct xe_gt *gt);
 int xe_gt_sriov_vf_connect(struct xe_gt *gt);
diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
index ace1fe831a7b..9deb9b44c3c3 100644
--- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
+++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
@@ -138,6 +138,14 @@ void xe_gt_tlb_invalidation_reset(struct xe_gt *gt)
 	int pending_seqno;
 
 	/*
+	 * we can get here before the CTs are even initialized if we're wedging
+	 * very early, in which case there are not going to be any pending
+	 * fences so we can bail immediately.
+	 */
+	if (!xe_guc_ct_initialized(&gt->uc.guc.ct))
+		return;
+
+	/*
 	 * CT channel is already disabled at this point. No new TLB requests can
 	 * appear.
 	 */
@@ -310,6 +318,13 @@ int xe_gt_tlb_invalidation_ggtt(struct xe_gt *gt)
 	return 0;
 }
 
+/*
+ * Ensure that roundup_pow_of_two(length) doesn't overflow.
+ * Note that roundup_pow_of_two() operates on unsigned long,
+ * not on u64.
+ */
+#define MAX_RANGE_TLB_INVALIDATION_LENGTH (rounddown_pow_of_two(ULONG_MAX))
+
 /**
  * xe_gt_tlb_invalidation_range - Issue a TLB invalidation on this GT for an
  * address range
@@ -334,6 +349,7 @@ int xe_gt_tlb_invalidation_range(struct xe_gt *gt,
 	struct xe_device *xe = gt_to_xe(gt);
 #define MAX_TLB_INVALIDATION_LEN	7
 	u32 action[MAX_TLB_INVALIDATION_LEN];
+	u64 length = end - start;
 	int len = 0;
 
 	xe_gt_assert(gt, fence);
@@ -346,11 +362,11 @@ int xe_gt_tlb_invalidation_range(struct xe_gt *gt,
 
 	action[len++] = XE_GUC_ACTION_TLB_INVALIDATION;
 	action[len++] = 0; /* seqno, replaced in send_tlb_invalidation */
-	if (!xe->info.has_range_tlb_invalidation) {
+	if (!xe->info.has_range_tlb_invalidation ||
+	    length > MAX_RANGE_TLB_INVALIDATION_LENGTH) {
 		action[len++] = MAKE_INVAL_OP(XE_GUC_TLB_INVAL_FULL);
 	} else {
 		u64 orig_start = start;
-		u64 length = end - start;
 		u64 align;
 
 		if (length < SZ_4K)
@@ -399,6 +415,28 @@ int xe_gt_tlb_invalidation_range(struct xe_gt *gt,
 }
 
 /**
+ * xe_gt_tlb_invalidation_vm - Issue a TLB invalidation on this GT for a VM
+ * @gt: graphics tile
+ * @vm: VM to invalidate
+ *
+ * Invalidate entire VM's address space
+ */
+void xe_gt_tlb_invalidation_vm(struct xe_gt *gt, struct xe_vm *vm)
+{
+	struct xe_gt_tlb_invalidation_fence fence;
+	u64 range = 1ull << vm->xe->info.va_bits;
+	int ret;
+
+	xe_gt_tlb_invalidation_fence_init(gt, &fence, true);
+
+	ret = xe_gt_tlb_invalidation_range(gt, &fence, 0, range, vm->usm.asid);
+	if (ret < 0)
+		return;
+
+	xe_gt_tlb_invalidation_fence_wait(&fence);
+}
+
+/**
  * xe_gt_tlb_invalidation_vma - Issue a TLB invalidation on this GT for a VMA
  * @gt: graphics tile
  * @fence: invalidation fence which will be signal on TLB invalidation
diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h
index 672acfcdf0d7..abe9b03d543e 100644
--- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h
+++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h
@@ -12,6 +12,7 @@
 
 struct xe_gt;
 struct xe_guc;
+struct xe_vm;
 struct xe_vma;
 
 int xe_gt_tlb_invalidation_init_early(struct xe_gt *gt);
@@ -21,6 +22,7 @@ int xe_gt_tlb_invalidation_ggtt(struct xe_gt *gt);
 int xe_gt_tlb_invalidation_vma(struct xe_gt *gt,
 			       struct xe_gt_tlb_invalidation_fence *fence,
 			       struct xe_vma *vma);
+void xe_gt_tlb_invalidation_vm(struct xe_gt *gt, struct xe_vm *vm);
 int xe_gt_tlb_invalidation_range(struct xe_gt *gt,
 				 struct xe_gt_tlb_invalidation_fence *fence,
 				 u64 start, u64 end, u32 asid);
diff --git a/drivers/gpu/drm/xe/xe_guc.c b/drivers/gpu/drm/xe/xe_guc.c
index 52df28032a6f..96373cdb366b 100644
--- a/drivers/gpu/drm/xe/xe_guc.c
+++ b/drivers/gpu/drm/xe/xe_guc.c
@@ -985,7 +985,7 @@ timeout:
 		BUILD_BUG_ON(FIELD_MAX(GUC_HXG_MSG_0_TYPE) != GUC_HXG_TYPE_RESPONSE_SUCCESS);
 		BUILD_BUG_ON((GUC_HXG_TYPE_RESPONSE_SUCCESS ^ GUC_HXG_TYPE_RESPONSE_FAILURE) != 1);
 
-		ret = xe_mmio_wait32(gt, reply_reg,  resp_mask, resp_mask,
+		ret = xe_mmio_wait32(gt, reply_reg, resp_mask, resp_mask,
 				     1000000, &header, false);
 
 		if (unlikely(FIELD_GET(GUC_HXG_MSG_0_ORIGIN, header) !=
@@ -1175,7 +1175,7 @@ void xe_guc_print_info(struct xe_guc *guc, struct drm_printer *p)
 
 	xe_force_wake_put(gt_to_fw(gt), XE_FW_GT);
 
-	xe_guc_ct_print(&guc->ct, p, false);
+	xe_guc_ct_print(&guc->ct, p);
 	xe_guc_submit_print(guc, p);
 }
 
diff --git a/drivers/gpu/drm/xe/xe_guc_ads.c b/drivers/gpu/drm/xe/xe_guc_ads.c
index d1902a8581ca..e144fd41c0a7 100644
--- a/drivers/gpu/drm/xe/xe_guc_ads.c
+++ b/drivers/gpu/drm/xe/xe_guc_ads.c
@@ -483,24 +483,52 @@ static void fill_engine_enable_masks(struct xe_gt *gt,
 		       engine_enable_mask(gt, XE_ENGINE_CLASS_OTHER));
 }
 
-static void guc_prep_golden_lrc_null(struct xe_guc_ads *ads)
+/*
+ * Write the offsets corresponding to the golden LRCs. The actual data is
+ * populated later by guc_golden_lrc_populate()
+ */
+static void guc_golden_lrc_init(struct xe_guc_ads *ads)
 {
 	struct xe_device *xe = ads_to_xe(ads);
+	struct xe_gt *gt = ads_to_gt(ads);
 	struct iosys_map info_map = IOSYS_MAP_INIT_OFFSET(ads_to_map(ads),
 			offsetof(struct __guc_ads_blob, system_info));
-	u8 guc_class;
+	size_t alloc_size, real_size;
+	u32 addr_ggtt, offset;
+	int class;
+
+	offset = guc_ads_golden_lrc_offset(ads);
+	addr_ggtt = xe_bo_ggtt_addr(ads->bo) + offset;
+
+	for (class = 0; class < XE_ENGINE_CLASS_MAX; ++class) {
+		u8 guc_class;
+
+		guc_class = xe_engine_class_to_guc_class(class);
 
-	for (guc_class = 0; guc_class <= GUC_MAX_ENGINE_CLASSES; ++guc_class) {
 		if (!info_map_read(xe, &info_map,
 				   engine_enabled_masks[guc_class]))
 			continue;
 
+		real_size = xe_gt_lrc_size(gt, class);
+		alloc_size = PAGE_ALIGN(real_size);
+
+		/*
+		 * This interface is slightly confusing. We need to pass the
+		 * base address of the full golden context and the size of just
+		 * the engine state, which is the section of the context image
+		 * that starts after the execlists LRC registers. This is
+		 * required to allow the GuC to restore just the engine state
+		 * when a watchdog reset occurs.
+		 * We calculate the engine state size by removing the size of
+		 * what comes before it in the context image (which is identical
+		 * on all engines).
+		 */
 		ads_blob_write(ads, ads.eng_state_size[guc_class],
-			       guc_ads_golden_lrc_size(ads) -
-			       xe_lrc_skip_size(xe));
+			       real_size - xe_lrc_skip_size(xe));
 		ads_blob_write(ads, ads.golden_context_lrca[guc_class],
-			       xe_bo_ggtt_addr(ads->bo) +
-			       guc_ads_golden_lrc_offset(ads));
+			       addr_ggtt);
+
+		addr_ggtt += alloc_size;
 	}
 }
 
@@ -710,7 +738,7 @@ void xe_guc_ads_populate_minimal(struct xe_guc_ads *ads)
 
 	xe_map_memset(ads_to_xe(ads), ads_to_map(ads), 0, 0, ads->bo->size);
 	guc_policies_init(ads);
-	guc_prep_golden_lrc_null(ads);
+	guc_golden_lrc_init(ads);
 	guc_mapping_table_init_invalid(gt, &info_map);
 	guc_doorbell_init(ads);
 
@@ -736,7 +764,7 @@ void xe_guc_ads_populate(struct xe_guc_ads *ads)
 	guc_policies_init(ads);
 	fill_engine_enable_masks(gt, &info_map);
 	guc_mmio_reg_state_init(ads);
-	guc_prep_golden_lrc_null(ads);
+	guc_golden_lrc_init(ads);
 	guc_mapping_table_init(gt, &info_map);
 	guc_capture_list_init(ads);
 	guc_doorbell_init(ads);
@@ -756,18 +784,22 @@ void xe_guc_ads_populate(struct xe_guc_ads *ads)
 		       guc_ads_private_data_offset(ads));
 }
 
-static void guc_populate_golden_lrc(struct xe_guc_ads *ads)
+/*
+ * After the golden LRC's are recorded for each engine class by the first
+ * submission, copy them to the ADS, as initialized earlier by
+ * guc_golden_lrc_init().
+ */
+static void guc_golden_lrc_populate(struct xe_guc_ads *ads)
 {
 	struct xe_device *xe = ads_to_xe(ads);
 	struct xe_gt *gt = ads_to_gt(ads);
 	struct iosys_map info_map = IOSYS_MAP_INIT_OFFSET(ads_to_map(ads),
 			offsetof(struct __guc_ads_blob, system_info));
 	size_t total_size = 0, alloc_size, real_size;
-	u32 addr_ggtt, offset;
+	u32 offset;
 	int class;
 
 	offset = guc_ads_golden_lrc_offset(ads);
-	addr_ggtt = xe_bo_ggtt_addr(ads->bo) + offset;
 
 	for (class = 0; class < XE_ENGINE_CLASS_MAX; ++class) {
 		u8 guc_class;
@@ -784,26 +816,9 @@ static void guc_populate_golden_lrc(struct xe_guc_ads *ads)
 		alloc_size = PAGE_ALIGN(real_size);
 		total_size += alloc_size;
 
-		/*
-		 * This interface is slightly confusing. We need to pass the
-		 * base address of the full golden context and the size of just
-		 * the engine state, which is the section of the context image
-		 * that starts after the execlists LRC registers. This is
-		 * required to allow the GuC to restore just the engine state
-		 * when a watchdog reset occurs.
-		 * We calculate the engine state size by removing the size of
-		 * what comes before it in the context image (which is identical
-		 * on all engines).
-		 */
-		ads_blob_write(ads, ads.eng_state_size[guc_class],
-			       real_size - xe_lrc_skip_size(xe));
-		ads_blob_write(ads, ads.golden_context_lrca[guc_class],
-			       addr_ggtt);
-
 		xe_map_memcpy_to(xe, ads_to_map(ads), offset,
 				 gt->default_lrc[class], real_size);
 
-		addr_ggtt += alloc_size;
 		offset += alloc_size;
 	}
 
@@ -812,7 +827,7 @@ static void guc_populate_golden_lrc(struct xe_guc_ads *ads)
 
 void xe_guc_ads_populate_post_load(struct xe_guc_ads *ads)
 {
-	guc_populate_golden_lrc(ads);
+	guc_golden_lrc_populate(ads);
 }
 
 static int guc_ads_action_update_policies(struct xe_guc_ads *ads, u32 policy_offset)
diff --git a/drivers/gpu/drm/xe/xe_guc_ct.c b/drivers/gpu/drm/xe/xe_guc_ct.c
index cd6a5f09d631..f1ce4e14dcb5 100644
--- a/drivers/gpu/drm/xe/xe_guc_ct.c
+++ b/drivers/gpu/drm/xe/xe_guc_ct.c
@@ -25,12 +25,53 @@
 #include "xe_gt_sriov_pf_monitor.h"
 #include "xe_gt_tlb_invalidation.h"
 #include "xe_guc.h"
+#include "xe_guc_log.h"
 #include "xe_guc_relay.h"
 #include "xe_guc_submit.h"
 #include "xe_map.h"
 #include "xe_pm.h"
 #include "xe_trace_guc.h"
 
+static void receive_g2h(struct xe_guc_ct *ct);
+static void g2h_worker_func(struct work_struct *w);
+static void safe_mode_worker_func(struct work_struct *w);
+static void ct_exit_safe_mode(struct xe_guc_ct *ct);
+
+#if IS_ENABLED(CONFIG_DRM_XE_DEBUG)
+enum {
+	/* Internal states, not error conditions */
+	CT_DEAD_STATE_REARM,			/* 0x0001 */
+	CT_DEAD_STATE_CAPTURE,			/* 0x0002 */
+
+	/* Error conditions */
+	CT_DEAD_SETUP,				/* 0x0004 */
+	CT_DEAD_H2G_WRITE,			/* 0x0008 */
+	CT_DEAD_H2G_HAS_ROOM,			/* 0x0010 */
+	CT_DEAD_G2H_READ,			/* 0x0020 */
+	CT_DEAD_G2H_RECV,			/* 0x0040 */
+	CT_DEAD_G2H_RELEASE,			/* 0x0080 */
+	CT_DEAD_DEADLOCK,			/* 0x0100 */
+	CT_DEAD_PROCESS_FAILED,			/* 0x0200 */
+	CT_DEAD_FAST_G2H,			/* 0x0400 */
+	CT_DEAD_PARSE_G2H_RESPONSE,		/* 0x0800 */
+	CT_DEAD_PARSE_G2H_UNKNOWN,		/* 0x1000 */
+	CT_DEAD_PARSE_G2H_ORIGIN,		/* 0x2000 */
+	CT_DEAD_PARSE_G2H_TYPE,			/* 0x4000 */
+};
+
+static void ct_dead_worker_func(struct work_struct *w);
+static void ct_dead_capture(struct xe_guc_ct *ct, struct guc_ctb *ctb, u32 reason_code);
+
+#define CT_DEAD(ct, ctb, reason_code)		ct_dead_capture((ct), (ctb), CT_DEAD_##reason_code)
+#else
+#define CT_DEAD(ct, ctb, reason)			\
+	do {						\
+		struct guc_ctb *_ctb = (ctb);		\
+		if (_ctb)				\
+			_ctb->info.broken = true;	\
+	} while (0)
+#endif
+
 /* Used when a CT send wants to block and / or receive data */
 struct g2h_fence {
 	u32 *response_buffer;
@@ -147,14 +188,11 @@ static void guc_ct_fini(struct drm_device *drm, void *arg)
 {
 	struct xe_guc_ct *ct = arg;
 
+	ct_exit_safe_mode(ct);
 	destroy_workqueue(ct->g2h_wq);
 	xa_destroy(&ct->fence_lookup);
 }
 
-static void receive_g2h(struct xe_guc_ct *ct);
-static void g2h_worker_func(struct work_struct *w);
-static void safe_mode_worker_func(struct work_struct *w);
-
 static void primelockdep(struct xe_guc_ct *ct)
 {
 	if (!IS_ENABLED(CONFIG_LOCKDEP))
@@ -182,7 +220,11 @@ int xe_guc_ct_init(struct xe_guc_ct *ct)
 	spin_lock_init(&ct->fast_lock);
 	xa_init(&ct->fence_lookup);
 	INIT_WORK(&ct->g2h_worker, g2h_worker_func);
-	INIT_DELAYED_WORK(&ct->safe_mode_worker,  safe_mode_worker_func);
+	INIT_DELAYED_WORK(&ct->safe_mode_worker, safe_mode_worker_func);
+#if IS_ENABLED(CONFIG_DRM_XE_DEBUG)
+	spin_lock_init(&ct->dead.lock);
+	INIT_WORK(&ct->dead.worker, ct_dead_worker_func);
+#endif
 	init_waitqueue_head(&ct->wq);
 	init_waitqueue_head(&ct->g2h_fence_wq);
 
@@ -419,10 +461,22 @@ int xe_guc_ct_enable(struct xe_guc_ct *ct)
 	if (ct_needs_safe_mode(ct))
 		ct_enter_safe_mode(ct);
 
+#if IS_ENABLED(CONFIG_DRM_XE_DEBUG)
+	/*
+	 * The CT has now been reset so the dumper can be re-armed
+	 * after any existing dead state has been dumped.
+	 */
+	spin_lock_irq(&ct->dead.lock);
+	if (ct->dead.reason)
+		ct->dead.reason |= (1 << CT_DEAD_STATE_REARM);
+	spin_unlock_irq(&ct->dead.lock);
+#endif
+
 	return 0;
 
 err_out:
 	xe_gt_err(gt, "Failed to enable GuC CT (%pe)\n", ERR_PTR(err));
+	CT_DEAD(ct, NULL, SETUP);
 
 	return err;
 }
@@ -454,6 +508,9 @@ void xe_guc_ct_disable(struct xe_guc_ct *ct)
  */
 void xe_guc_ct_stop(struct xe_guc_ct *ct)
 {
+	if (!xe_guc_ct_initialized(ct))
+		return;
+
 	xe_guc_ct_set_state(ct, XE_GUC_CT_STATE_STOPPED);
 	stop_g2h_handler(ct);
 }
@@ -466,6 +523,19 @@ static bool h2g_has_room(struct xe_guc_ct *ct, u32 cmd_len)
 
 	if (cmd_len > h2g->info.space) {
 		h2g->info.head = desc_read(ct_to_xe(ct), h2g, head);
+
+		if (h2g->info.head > h2g->info.size) {
+			struct xe_device *xe = ct_to_xe(ct);
+			u32 desc_status = desc_read(xe, h2g, status);
+
+			desc_write(xe, h2g, status, desc_status | GUC_CTB_STATUS_OVERFLOW);
+
+			xe_gt_err(ct_to_gt(ct), "CT: invalid head offset %u >= %u)\n",
+				  h2g->info.head, h2g->info.size);
+			CT_DEAD(ct, h2g, H2G_HAS_ROOM);
+			return false;
+		}
+
 		h2g->info.space = CIRC_SPACE(h2g->info.tail, h2g->info.head,
 					     h2g->info.size) -
 				  h2g->info.resv_space;
@@ -521,10 +591,24 @@ static void __g2h_reserve_space(struct xe_guc_ct *ct, u32 g2h_len, u32 num_g2h)
 
 static void __g2h_release_space(struct xe_guc_ct *ct, u32 g2h_len)
 {
+	bool bad = false;
+
 	lockdep_assert_held(&ct->fast_lock);
-	xe_gt_assert(ct_to_gt(ct), ct->ctbs.g2h.info.space + g2h_len <=
-		     ct->ctbs.g2h.info.size - ct->ctbs.g2h.info.resv_space);
-	xe_gt_assert(ct_to_gt(ct), ct->g2h_outstanding);
+
+	bad = ct->ctbs.g2h.info.space + g2h_len >
+		     ct->ctbs.g2h.info.size - ct->ctbs.g2h.info.resv_space;
+	bad |= !ct->g2h_outstanding;
+
+	if (bad) {
+		xe_gt_err(ct_to_gt(ct), "Invalid G2H release: %d + %d vs %d - %d -> %d vs %d, outstanding = %d!\n",
+			  ct->ctbs.g2h.info.space, g2h_len,
+			  ct->ctbs.g2h.info.size, ct->ctbs.g2h.info.resv_space,
+			  ct->ctbs.g2h.info.space + g2h_len,
+			  ct->ctbs.g2h.info.size - ct->ctbs.g2h.info.resv_space,
+			  ct->g2h_outstanding);
+		CT_DEAD(ct, &ct->ctbs.g2h, G2H_RELEASE);
+		return;
+	}
 
 	ct->ctbs.g2h.info.space += g2h_len;
 	if (!--ct->g2h_outstanding)
@@ -551,12 +635,43 @@ static int h2g_write(struct xe_guc_ct *ct, const u32 *action, u32 len,
 	u32 full_len;
 	struct iosys_map map = IOSYS_MAP_INIT_OFFSET(&h2g->cmds,
 							 tail * sizeof(u32));
+	u32 desc_status;
 
 	full_len = len + GUC_CTB_HDR_LEN;
 
 	lockdep_assert_held(&ct->lock);
 	xe_gt_assert(gt, full_len <= GUC_CTB_MSG_MAX_LEN);
-	xe_gt_assert(gt, tail <= h2g->info.size);
+
+	desc_status = desc_read(xe, h2g, status);
+	if (desc_status) {
+		xe_gt_err(gt, "CT write: non-zero status: %u\n", desc_status);
+		goto corrupted;
+	}
+
+	if (IS_ENABLED(CONFIG_DRM_XE_DEBUG)) {
+		u32 desc_tail = desc_read(xe, h2g, tail);
+		u32 desc_head = desc_read(xe, h2g, head);
+
+		if (tail != desc_tail) {
+			desc_write(xe, h2g, status, desc_status | GUC_CTB_STATUS_MISMATCH);
+			xe_gt_err(gt, "CT write: tail was modified %u != %u\n", desc_tail, tail);
+			goto corrupted;
+		}
+
+		if (tail > h2g->info.size) {
+			desc_write(xe, h2g, status, desc_status | GUC_CTB_STATUS_OVERFLOW);
+			xe_gt_err(gt, "CT write: tail out of range: %u vs %u\n",
+				  tail, h2g->info.size);
+			goto corrupted;
+		}
+
+		if (desc_head >= h2g->info.size) {
+			desc_write(xe, h2g, status, desc_status | GUC_CTB_STATUS_OVERFLOW);
+			xe_gt_err(gt, "CT write: invalid head offset %u >= %u)\n",
+				  desc_head, h2g->info.size);
+			goto corrupted;
+		}
+	}
 
 	/* Command will wrap, zero fill (NOPs), return and check credits again */
 	if (tail + full_len > h2g->info.size) {
@@ -609,6 +724,10 @@ static int h2g_write(struct xe_guc_ct *ct, const u32 *action, u32 len,
 			     desc_read(xe, h2g, head), h2g->info.tail);
 
 	return 0;
+
+corrupted:
+	CT_DEAD(ct, &ct->ctbs.h2g, H2G_WRITE);
+	return -EPIPE;
 }
 
 /*
@@ -638,7 +757,7 @@ static int __guc_ct_send_locked(struct xe_guc_ct *ct, const u32 *action,
 	u16 seqno;
 	int ret;
 
-	xe_gt_assert(gt, ct->state != XE_GUC_CT_STATE_NOT_INITIALIZED);
+	xe_gt_assert(gt, xe_guc_ct_initialized(ct));
 	xe_gt_assert(gt, !g2h_len || !g2h_fence);
 	xe_gt_assert(gt, !num_g2h || !g2h_fence);
 	xe_gt_assert(gt, !g2h_len || num_g2h);
@@ -716,7 +835,6 @@ static int guc_ct_send_locked(struct xe_guc_ct *ct, const u32 *action, u32 len,
 {
 	struct xe_device *xe = ct_to_xe(ct);
 	struct xe_gt *gt = ct_to_gt(ct);
-	struct drm_printer p = xe_gt_info_printer(gt);
 	unsigned int sleep_period_ms = 1;
 	int ret;
 
@@ -769,8 +887,13 @@ try_again:
 			goto broken;
 #undef g2h_avail
 
-		if (dequeue_one_g2h(ct) < 0)
+		ret = dequeue_one_g2h(ct);
+		if (ret < 0) {
+			if (ret != -ECANCELED)
+				xe_gt_err(ct_to_gt(ct), "CTB receive failed (%pe)",
+					  ERR_PTR(ret));
 			goto broken;
+		}
 
 		goto try_again;
 	}
@@ -779,8 +902,7 @@ try_again:
 
 broken:
 	xe_gt_err(gt, "No forward process on H2G, reset required\n");
-	xe_guc_ct_print(ct, &p, true);
-	ct->ctbs.h2g.info.broken = true;
+	CT_DEAD(ct, &ct->ctbs.h2g, DEADLOCK);
 
 	return -EDEADLK;
 }
@@ -848,7 +970,7 @@ static bool retry_failure(struct xe_guc_ct *ct, int ret)
 #define ct_alive(ct)	\
 	(xe_guc_ct_enabled(ct) && !ct->ctbs.h2g.info.broken && \
 	 !ct->ctbs.g2h.info.broken)
-	if (!wait_event_interruptible_timeout(ct->wq, ct_alive(ct),  HZ * 5))
+	if (!wait_event_interruptible_timeout(ct->wq, ct_alive(ct), HZ * 5))
 		return false;
 #undef ct_alive
 
@@ -1046,6 +1168,7 @@ static int parse_g2h_response(struct xe_guc_ct *ct, u32 *msg, u32 len)
 		else
 			xe_gt_err(gt, "unexpected response %u for FAST_REQ H2G fence 0x%x!\n",
 				  type, fence);
+		CT_DEAD(ct, NULL, PARSE_G2H_RESPONSE);
 
 		return -EPROTO;
 	}
@@ -1053,6 +1176,7 @@ static int parse_g2h_response(struct xe_guc_ct *ct, u32 *msg, u32 len)
 	g2h_fence = xa_erase(&ct->fence_lookup, fence);
 	if (unlikely(!g2h_fence)) {
 		/* Don't tear down channel, as send could've timed out */
+		/* CT_DEAD(ct, NULL, PARSE_G2H_UNKNOWN); */
 		xe_gt_warn(gt, "G2H fence (%u) not found!\n", fence);
 		g2h_release_space(ct, GUC_CTB_HXG_MSG_MAX_LEN);
 		return 0;
@@ -1097,7 +1221,7 @@ static int parse_g2h_msg(struct xe_guc_ct *ct, u32 *msg, u32 len)
 	if (unlikely(origin != GUC_HXG_ORIGIN_GUC)) {
 		xe_gt_err(gt, "G2H channel broken on read, origin=%u, reset required\n",
 			  origin);
-		ct->ctbs.g2h.info.broken = true;
+		CT_DEAD(ct, &ct->ctbs.g2h, PARSE_G2H_ORIGIN);
 
 		return -EPROTO;
 	}
@@ -1115,7 +1239,7 @@ static int parse_g2h_msg(struct xe_guc_ct *ct, u32 *msg, u32 len)
 	default:
 		xe_gt_err(gt, "G2H channel broken on read, type=%u, reset required\n",
 			  type);
-		ct->ctbs.g2h.info.broken = true;
+		CT_DEAD(ct, &ct->ctbs.g2h, PARSE_G2H_TYPE);
 
 		ret = -EOPNOTSUPP;
 	}
@@ -1192,9 +1316,11 @@ static int process_g2h_msg(struct xe_guc_ct *ct, u32 *msg, u32 len)
 		xe_gt_err(gt, "unexpected G2H action 0x%04x\n", action);
 	}
 
-	if (ret)
+	if (ret) {
 		xe_gt_err(gt, "G2H action 0x%04x failed (%pe)\n",
 			  action, ERR_PTR(ret));
+		CT_DEAD(ct, NULL, PROCESS_FAILED);
+	}
 
 	return 0;
 }
@@ -1204,12 +1330,12 @@ static int g2h_read(struct xe_guc_ct *ct, u32 *msg, bool fast_path)
 	struct xe_device *xe = ct_to_xe(ct);
 	struct xe_gt *gt = ct_to_gt(ct);
 	struct guc_ctb *g2h = &ct->ctbs.g2h;
-	u32 tail, head, len;
+	u32 tail, head, len, desc_status;
 	s32 avail;
 	u32 action;
 	u32 *hxg;
 
-	xe_gt_assert(gt, ct->state != XE_GUC_CT_STATE_NOT_INITIALIZED);
+	xe_gt_assert(gt, xe_guc_ct_initialized(ct));
 	lockdep_assert_held(&ct->fast_lock);
 
 	if (ct->state == XE_GUC_CT_STATE_DISABLED)
@@ -1223,6 +1349,63 @@ static int g2h_read(struct xe_guc_ct *ct, u32 *msg, bool fast_path)
 
 	xe_gt_assert(gt, xe_guc_ct_enabled(ct));
 
+	desc_status = desc_read(xe, g2h, status);
+	if (desc_status) {
+		if (desc_status & GUC_CTB_STATUS_DISABLED) {
+			/*
+			 * Potentially valid if a CLIENT_RESET request resulted in
+			 * contexts/engines being reset. But should never happen as
+			 * no contexts should be active when CLIENT_RESET is sent.
+			 */
+			xe_gt_err(gt, "CT read: unexpected G2H after GuC has stopped!\n");
+			desc_status &= ~GUC_CTB_STATUS_DISABLED;
+		}
+
+		if (desc_status) {
+			xe_gt_err(gt, "CT read: non-zero status: %u\n", desc_status);
+			goto corrupted;
+		}
+	}
+
+	if (IS_ENABLED(CONFIG_DRM_XE_DEBUG)) {
+		u32 desc_tail = desc_read(xe, g2h, tail);
+		/*
+		u32 desc_head = desc_read(xe, g2h, head);
+
+		 * info.head and desc_head are updated back-to-back at the end of
+		 * this function and nowhere else. Hence, they cannot be different
+		 * unless two g2h_read calls are running concurrently. Which is not
+		 * possible because it is guarded by ct->fast_lock. And yet, some
+		 * discrete platforms are reguarly hitting this error :(.
+		 *
+		 * desc_head rolling backwards shouldn't cause any noticeable
+		 * problems - just a delay in GuC being allowed to proceed past that
+		 * point in the queue. So for now, just disable the error until it
+		 * can be root caused.
+		 *
+		if (g2h->info.head != desc_head) {
+			desc_write(xe, g2h, status, desc_status | GUC_CTB_STATUS_MISMATCH);
+			xe_gt_err(gt, "CT read: head was modified %u != %u\n",
+				  desc_head, g2h->info.head);
+			goto corrupted;
+		}
+		 */
+
+		if (g2h->info.head > g2h->info.size) {
+			desc_write(xe, g2h, status, desc_status | GUC_CTB_STATUS_OVERFLOW);
+			xe_gt_err(gt, "CT read: head out of range: %u vs %u\n",
+				  g2h->info.head, g2h->info.size);
+			goto corrupted;
+		}
+
+		if (desc_tail >= g2h->info.size) {
+			desc_write(xe, g2h, status, desc_status | GUC_CTB_STATUS_OVERFLOW);
+			xe_gt_err(gt, "CT read: invalid tail offset %u >= %u)\n",
+				  desc_tail, g2h->info.size);
+			goto corrupted;
+		}
+	}
+
 	/* Calculate DW available to read */
 	tail = desc_read(xe, g2h, tail);
 	avail = tail - g2h->info.head;
@@ -1239,9 +1422,7 @@ static int g2h_read(struct xe_guc_ct *ct, u32 *msg, bool fast_path)
 	if (len > avail) {
 		xe_gt_err(gt, "G2H channel broken on read, avail=%d, len=%d, reset required\n",
 			  avail, len);
-		g2h->info.broken = true;
-
-		return -EPROTO;
+		goto corrupted;
 	}
 
 	head = (g2h->info.head + 1) % g2h->info.size;
@@ -1287,6 +1468,10 @@ static int g2h_read(struct xe_guc_ct *ct, u32 *msg, bool fast_path)
 			     action, len, g2h->info.head, tail);
 
 	return len;
+
+corrupted:
+	CT_DEAD(ct, &ct->ctbs.g2h, G2H_READ);
+	return -EPROTO;
 }
 
 static void g2h_fast_path(struct xe_guc_ct *ct, u32 *msg, u32 len)
@@ -1313,9 +1498,11 @@ static void g2h_fast_path(struct xe_guc_ct *ct, u32 *msg, u32 len)
 		xe_gt_warn(gt, "NOT_POSSIBLE");
 	}
 
-	if (ret)
+	if (ret) {
 		xe_gt_err(gt, "G2H action 0x%04x failed (%pe)\n",
 			  action, ERR_PTR(ret));
+		CT_DEAD(ct, NULL, FAST_G2H);
+	}
 }
 
 /**
@@ -1375,7 +1562,6 @@ static int dequeue_one_g2h(struct xe_guc_ct *ct)
 
 static void receive_g2h(struct xe_guc_ct *ct)
 {
-	struct xe_gt *gt = ct_to_gt(ct);
 	bool ongoing;
 	int ret;
 
@@ -1412,9 +1598,8 @@ static void receive_g2h(struct xe_guc_ct *ct)
 		mutex_unlock(&ct->lock);
 
 		if (unlikely(ret == -EPROTO || ret == -EOPNOTSUPP)) {
-			struct drm_printer p = xe_gt_info_printer(gt);
-
-			xe_guc_ct_print(ct, &p, false);
+			xe_gt_err(ct_to_gt(ct), "CT dequeue failed: %d", ret);
+			CT_DEAD(ct, NULL, G2H_RECV);
 			kick_reset(ct);
 		}
 	} while (ret == 1);
@@ -1442,9 +1627,8 @@ static void guc_ctb_snapshot_capture(struct xe_device *xe, struct guc_ctb *ctb,
 
 	snapshot->cmds = kmalloc_array(ctb->info.size, sizeof(u32),
 				       atomic ? GFP_ATOMIC : GFP_KERNEL);
-
 	if (!snapshot->cmds) {
-		drm_err(&xe->drm, "Skipping CTB commands snapshot. Only CTB info will be available.\n");
+		drm_err(&xe->drm, "Skipping CTB commands snapshot. Only CT info will be available.\n");
 		return;
 	}
 
@@ -1525,7 +1709,7 @@ struct xe_guc_ct_snapshot *xe_guc_ct_snapshot_capture(struct xe_guc_ct *ct,
 			   atomic ? GFP_ATOMIC : GFP_KERNEL);
 
 	if (!snapshot) {
-		drm_err(&xe->drm, "Skipping CTB snapshot entirely.\n");
+		xe_gt_err(ct_to_gt(ct), "Skipping CTB snapshot entirely.\n");
 		return NULL;
 	}
 
@@ -1589,16 +1773,119 @@ void xe_guc_ct_snapshot_free(struct xe_guc_ct_snapshot *snapshot)
  * xe_guc_ct_print - GuC CT Print.
  * @ct: GuC CT.
  * @p: drm_printer where it will be printed out.
- * @atomic: Boolean to indicate if this is called from atomic context like
- * reset or CTB handler or from some regular path like debugfs.
  *
  * This function quickly capture a snapshot and immediately print it out.
  */
-void xe_guc_ct_print(struct xe_guc_ct *ct, struct drm_printer *p, bool atomic)
+void xe_guc_ct_print(struct xe_guc_ct *ct, struct drm_printer *p)
 {
 	struct xe_guc_ct_snapshot *snapshot;
 
-	snapshot = xe_guc_ct_snapshot_capture(ct, atomic);
+	snapshot = xe_guc_ct_snapshot_capture(ct, false);
 	xe_guc_ct_snapshot_print(snapshot, p);
 	xe_guc_ct_snapshot_free(snapshot);
 }
+
+#if IS_ENABLED(CONFIG_DRM_XE_DEBUG)
+static void ct_dead_capture(struct xe_guc_ct *ct, struct guc_ctb *ctb, u32 reason_code)
+{
+	struct xe_guc_log_snapshot *snapshot_log;
+	struct xe_guc_ct_snapshot *snapshot_ct;
+	struct xe_guc *guc = ct_to_guc(ct);
+	unsigned long flags;
+	bool have_capture;
+
+	if (ctb)
+		ctb->info.broken = true;
+
+	/* Ignore further errors after the first dump until a reset */
+	if (ct->dead.reported)
+		return;
+
+	spin_lock_irqsave(&ct->dead.lock, flags);
+
+	/* And only capture one dump at a time */
+	have_capture = ct->dead.reason & (1 << CT_DEAD_STATE_CAPTURE);
+	ct->dead.reason |= (1 << reason_code) |
+			   (1 << CT_DEAD_STATE_CAPTURE);
+
+	spin_unlock_irqrestore(&ct->dead.lock, flags);
+
+	if (have_capture)
+		return;
+
+	snapshot_log = xe_guc_log_snapshot_capture(&guc->log, true);
+	snapshot_ct = xe_guc_ct_snapshot_capture((ct), true);
+
+	spin_lock_irqsave(&ct->dead.lock, flags);
+
+	if (ct->dead.snapshot_log || ct->dead.snapshot_ct) {
+		xe_gt_err(ct_to_gt(ct), "Got unexpected dead CT capture!\n");
+		xe_guc_log_snapshot_free(snapshot_log);
+		xe_guc_ct_snapshot_free(snapshot_ct);
+	} else {
+		ct->dead.snapshot_log = snapshot_log;
+		ct->dead.snapshot_ct = snapshot_ct;
+	}
+
+	spin_unlock_irqrestore(&ct->dead.lock, flags);
+
+	queue_work(system_unbound_wq, &(ct)->dead.worker);
+}
+
+static void ct_dead_print(struct xe_dead_ct *dead)
+{
+	struct xe_guc_ct *ct = container_of(dead, struct xe_guc_ct, dead);
+	struct xe_device *xe = ct_to_xe(ct);
+	struct xe_gt *gt = ct_to_gt(ct);
+	static int g_count;
+	struct drm_printer ip = xe_gt_info_printer(gt);
+	struct drm_printer lp = drm_line_printer(&ip, "Capture", ++g_count);
+
+	if (!dead->reason) {
+		xe_gt_err(gt, "CTB is dead for no reason!?\n");
+		return;
+	}
+
+	drm_printf(&lp, "CTB is dead - reason=0x%X\n", dead->reason);
+
+	/* Can't generate a genuine core dump at this point, so just do the good bits */
+	drm_puts(&lp, "**** Xe Device Coredump ****\n");
+	xe_device_snapshot_print(xe, &lp);
+
+	drm_printf(&lp, "**** GT #%d ****\n", gt->info.id);
+	drm_printf(&lp, "\tTile: %d\n", gt->tile->id);
+
+	drm_puts(&lp, "**** GuC Log ****\n");
+	xe_guc_log_snapshot_print(dead->snapshot_log, &lp);
+
+	drm_puts(&lp, "**** GuC CT ****\n");
+	xe_guc_ct_snapshot_print(dead->snapshot_ct, &lp);
+
+	drm_puts(&lp, "Done.\n");
+}
+
+static void ct_dead_worker_func(struct work_struct *w)
+{
+	struct xe_guc_ct *ct = container_of(w, struct xe_guc_ct, dead.worker);
+
+	if (!ct->dead.reported) {
+		ct->dead.reported = true;
+		ct_dead_print(&ct->dead);
+	}
+
+	spin_lock_irq(&ct->dead.lock);
+
+	xe_guc_log_snapshot_free(ct->dead.snapshot_log);
+	ct->dead.snapshot_log = NULL;
+	xe_guc_ct_snapshot_free(ct->dead.snapshot_ct);
+	ct->dead.snapshot_ct = NULL;
+
+	if (ct->dead.reason & (1 << CT_DEAD_STATE_REARM)) {
+		/* A reset has occurred so re-arm the error reporting */
+		ct->dead.reason = 0;
+		ct->dead.reported = false;
+	}
+
+	spin_unlock_irq(&ct->dead.lock);
+}
+#endif
diff --git a/drivers/gpu/drm/xe/xe_guc_ct.h b/drivers/gpu/drm/xe/xe_guc_ct.h
index 190202fce2d0..c7ac9407b861 100644
--- a/drivers/gpu/drm/xe/xe_guc_ct.h
+++ b/drivers/gpu/drm/xe/xe_guc_ct.h
@@ -21,7 +21,12 @@ xe_guc_ct_snapshot_capture(struct xe_guc_ct *ct, bool atomic);
 void xe_guc_ct_snapshot_print(struct xe_guc_ct_snapshot *snapshot,
 			      struct drm_printer *p);
 void xe_guc_ct_snapshot_free(struct xe_guc_ct_snapshot *snapshot);
-void xe_guc_ct_print(struct xe_guc_ct *ct, struct drm_printer *p, bool atomic);
+void xe_guc_ct_print(struct xe_guc_ct *ct, struct drm_printer *p);
+
+static inline bool xe_guc_ct_initialized(struct xe_guc_ct *ct)
+{
+	return ct->state != XE_GUC_CT_STATE_NOT_INITIALIZED;
+}
 
 static inline bool xe_guc_ct_enabled(struct xe_guc_ct *ct)
 {
diff --git a/drivers/gpu/drm/xe/xe_guc_ct_types.h b/drivers/gpu/drm/xe/xe_guc_ct_types.h
index 761cb9031298..85e127ec91d7 100644
--- a/drivers/gpu/drm/xe/xe_guc_ct_types.h
+++ b/drivers/gpu/drm/xe/xe_guc_ct_types.h
@@ -86,6 +86,24 @@ enum xe_guc_ct_state {
 	XE_GUC_CT_STATE_ENABLED,
 };
 
+#if IS_ENABLED(CONFIG_DRM_XE_DEBUG)
+/** struct xe_dead_ct - Information for debugging a dead CT */
+struct xe_dead_ct {
+	/** @lock: protects memory allocation/free operations, and @reason updates */
+	spinlock_t lock;
+	/** @reason: bit mask of CT_DEAD_* reason codes */
+	unsigned int reason;
+	/** @reported: for preventing multiple dumps per error sequence */
+	bool reported;
+	/** @worker: worker thread to get out of interrupt context before dumping */
+	struct work_struct worker;
+	/** snapshot_ct: copy of CT state and CTB content at point of error */
+	struct xe_guc_ct_snapshot *snapshot_ct;
+	/** snapshot_log: copy of GuC log at point of error */
+	struct xe_guc_log_snapshot *snapshot_log;
+};
+#endif
+
 /**
  * struct xe_guc_ct - GuC command transport (CT) layer
  *
@@ -128,6 +146,11 @@ struct xe_guc_ct {
 	u32 msg[GUC_CTB_MSG_MAX_LEN];
 	/** @fast_msg: Message buffer */
 	u32 fast_msg[GUC_CTB_MSG_MAX_LEN];
+
+#if IS_ENABLED(CONFIG_DRM_XE_DEBUG)
+	/** @dead: information for debugging dead CTs */
+	struct xe_dead_ct dead;
+#endif
 };
 
 #endif
diff --git a/drivers/gpu/drm/xe/xe_guc_exec_queue_types.h b/drivers/gpu/drm/xe/xe_guc_exec_queue_types.h
index 4c39f01e4f52..a3f421e2adc0 100644
--- a/drivers/gpu/drm/xe/xe_guc_exec_queue_types.h
+++ b/drivers/gpu/drm/xe/xe_guc_exec_queue_types.h
@@ -20,6 +20,8 @@ struct xe_exec_queue;
 struct xe_guc_exec_queue {
 	/** @q: Backpointer to parent xe_exec_queue */
 	struct xe_exec_queue *q;
+	/** @rcu: For safe freeing of exported dma fences */
+	struct rcu_head rcu;
 	/** @sched: GPU scheduler for this xe_exec_queue */
 	struct xe_gpu_scheduler sched;
 	/** @entity: Scheduler entity for this xe_exec_queue */
diff --git a/drivers/gpu/drm/xe/xe_guc_log.c b/drivers/gpu/drm/xe/xe_guc_log.c
index be47780ec2a7..50851638003b 100644
--- a/drivers/gpu/drm/xe/xe_guc_log.c
+++ b/drivers/gpu/drm/xe/xe_guc_log.c
@@ -78,7 +78,7 @@ void xe_guc_log_print(struct xe_guc_log *log, struct drm_printer *p)
 
 	xe_map_memcpy_from(xe, copy, &log->bo->vmap, 0, size);
 
-	xe_print_blob_ascii85(p, "Log data", copy, 0, size);
+	xe_print_blob_ascii85(p, "Log data", '\n', copy, 0, size);
 
 	vfree(copy);
 }
diff --git a/drivers/gpu/drm/xe/xe_guc_pc.c b/drivers/gpu/drm/xe/xe_guc_pc.c
index 034b29984d5e..af02803c145b 100644
--- a/drivers/gpu/drm/xe/xe_guc_pc.c
+++ b/drivers/gpu/drm/xe/xe_guc_pc.c
@@ -6,6 +6,9 @@
 #include "xe_guc_pc.h"
 
 #include <linux/delay.h>
+#include <linux/jiffies.h>
+#include <linux/ktime.h>
+#include <linux/wait_bit.h>
 
 #include <drm/drm_managed.h>
 #include <generated/xe_wa_oob.h>
@@ -47,6 +50,12 @@
 
 #define LNL_MERT_FREQ_CAP	800
 #define BMG_MERT_FREQ_CAP	2133
+#define BMG_MIN_FREQ		1200
+#define BMG_MERT_FLUSH_FREQ_CAP	2600
+
+#define SLPC_RESET_TIMEOUT_MS 5 /* roughly 5ms, but no need for precision */
+#define SLPC_RESET_EXTENDED_TIMEOUT_MS 1000 /* To be used only at pc_start */
+#define SLPC_ACT_FREQ_TIMEOUT_MS 100
 
 /**
  * DOC: GuC Power Conservation (PC)
@@ -133,6 +142,36 @@ static int wait_for_pc_state(struct xe_guc_pc *pc,
 	return -ETIMEDOUT;
 }
 
+static int wait_for_flush_complete(struct xe_guc_pc *pc)
+{
+	const unsigned long timeout = msecs_to_jiffies(30);
+
+	if (!wait_var_event_timeout(&pc->flush_freq_limit,
+				    !atomic_read(&pc->flush_freq_limit),
+				    timeout))
+		return -ETIMEDOUT;
+
+	return 0;
+}
+
+static int wait_for_act_freq_limit(struct xe_guc_pc *pc, u32 freq)
+{
+	int timeout_us = SLPC_ACT_FREQ_TIMEOUT_MS * USEC_PER_MSEC;
+	int slept, wait = 10;
+
+	for (slept = 0; slept < timeout_us;) {
+		if (xe_guc_pc_get_act_freq(pc) <= freq)
+			return 0;
+
+		usleep_range(wait, wait << 1);
+		slept += wait;
+		wait <<= 1;
+		if (slept + wait > timeout_us)
+			wait = timeout_us - slept;
+	}
+
+	return -ETIMEDOUT;
+}
 static int pc_action_reset(struct xe_guc_pc *pc)
 {
 	struct xe_guc_ct *ct = pc_to_ct(pc);
@@ -584,6 +623,11 @@ int xe_guc_pc_set_max_freq(struct xe_guc_pc *pc, u32 freq)
 {
 	int ret;
 
+	if (XE_WA(pc_to_gt(pc), 22019338487)) {
+		if (wait_for_flush_complete(pc) != 0)
+			return -EAGAIN;
+	}
+
 	mutex_lock(&pc->freq_lock);
 	if (!pc->freq_ready) {
 		/* Might be in the middle of a gt reset */
@@ -793,6 +837,106 @@ static int pc_adjust_requested_freq(struct xe_guc_pc *pc)
 	return ret;
 }
 
+static bool needs_flush_freq_limit(struct xe_guc_pc *pc)
+{
+	struct xe_gt *gt = pc_to_gt(pc);
+
+	return  XE_WA(gt, 22019338487) &&
+		pc->rp0_freq > BMG_MERT_FLUSH_FREQ_CAP;
+}
+
+/**
+ * xe_guc_pc_apply_flush_freq_limit() - Limit max GT freq during L2 flush
+ * @pc: the xe_guc_pc object
+ *
+ * As per the WA, reduce max GT frequency during L2 cache flush
+ */
+void xe_guc_pc_apply_flush_freq_limit(struct xe_guc_pc *pc)
+{
+	struct xe_gt *gt = pc_to_gt(pc);
+	u32 max_freq;
+	int ret;
+
+	if (!needs_flush_freq_limit(pc))
+		return;
+
+	mutex_lock(&pc->freq_lock);
+
+	if (!pc->freq_ready) {
+		mutex_unlock(&pc->freq_lock);
+		return;
+	}
+
+	ret = pc_action_query_task_state(pc);
+	if (ret) {
+		mutex_unlock(&pc->freq_lock);
+		return;
+	}
+
+	max_freq = pc_get_max_freq(pc);
+	if (max_freq > BMG_MERT_FLUSH_FREQ_CAP) {
+		ret = pc_set_max_freq(pc, BMG_MERT_FLUSH_FREQ_CAP);
+		if (ret) {
+			xe_gt_err_once(gt, "Failed to cap max freq on flush to %u, %pe\n",
+				       BMG_MERT_FLUSH_FREQ_CAP, ERR_PTR(ret));
+			mutex_unlock(&pc->freq_lock);
+			return;
+		}
+
+		atomic_set(&pc->flush_freq_limit, 1);
+
+		/*
+		 * If user has previously changed max freq, stash that value to
+		 * restore later, otherwise use the current max. New user
+		 * requests wait on flush.
+		 */
+		if (pc->user_requested_max != 0)
+			pc->stashed_max_freq = pc->user_requested_max;
+		else
+			pc->stashed_max_freq = max_freq;
+	}
+
+	mutex_unlock(&pc->freq_lock);
+
+	/*
+	 * Wait for actual freq to go below the flush cap: even if the previous
+	 * max was below cap, the current one might still be above it
+	 */
+	ret = wait_for_act_freq_limit(pc, BMG_MERT_FLUSH_FREQ_CAP);
+	if (ret)
+		xe_gt_err_once(gt, "Actual freq did not reduce to %u, %pe\n",
+			       BMG_MERT_FLUSH_FREQ_CAP, ERR_PTR(ret));
+}
+
+/**
+ * xe_guc_pc_remove_flush_freq_limit() - Remove max GT freq limit after L2 flush completes.
+ * @pc: the xe_guc_pc object
+ *
+ * Retrieve the previous GT max frequency value.
+ */
+void xe_guc_pc_remove_flush_freq_limit(struct xe_guc_pc *pc)
+{
+	struct xe_gt *gt = pc_to_gt(pc);
+	int ret = 0;
+
+	if (!needs_flush_freq_limit(pc))
+		return;
+
+	if (!atomic_read(&pc->flush_freq_limit))
+		return;
+
+	mutex_lock(&pc->freq_lock);
+
+	ret = pc_set_max_freq(&gt->uc.guc.pc, pc->stashed_max_freq);
+	if (ret)
+		xe_gt_err_once(gt, "Failed to restore max freq %u:%d",
+			       pc->stashed_max_freq, ret);
+
+	atomic_set(&pc->flush_freq_limit, 0);
+	mutex_unlock(&pc->freq_lock);
+	wake_up_var(&pc->flush_freq_limit);
+}
+
 static int pc_set_mert_freq_cap(struct xe_guc_pc *pc)
 {
 	int ret = 0;
@@ -975,7 +1119,7 @@ int xe_guc_pc_start(struct xe_guc_pc *pc)
 		goto out;
 	}
 
-	memset(pc->bo->vmap.vaddr, 0, size);
+	xe_map_memset(xe, &pc->bo->vmap, 0, 0, size);
 	slpc_shared_data_write(pc, header.size, size);
 
 	ret = pc_action_reset(pc);
diff --git a/drivers/gpu/drm/xe/xe_guc_pc.h b/drivers/gpu/drm/xe/xe_guc_pc.h
index efda432fadfc..7154b3aab0d8 100644
--- a/drivers/gpu/drm/xe/xe_guc_pc.h
+++ b/drivers/gpu/drm/xe/xe_guc_pc.h
@@ -34,5 +34,7 @@ u64 xe_guc_pc_mc6_residency(struct xe_guc_pc *pc);
 void xe_guc_pc_init_early(struct xe_guc_pc *pc);
 int xe_guc_pc_restore_stashed_freq(struct xe_guc_pc *pc);
 void xe_guc_pc_raise_unslice(struct xe_guc_pc *pc);
+void xe_guc_pc_apply_flush_freq_limit(struct xe_guc_pc *pc);
+void xe_guc_pc_remove_flush_freq_limit(struct xe_guc_pc *pc);
 
 #endif /* _XE_GUC_PC_H_ */
diff --git a/drivers/gpu/drm/xe/xe_guc_pc_types.h b/drivers/gpu/drm/xe/xe_guc_pc_types.h
index 13810be015db..5b86d91296cb 100644
--- a/drivers/gpu/drm/xe/xe_guc_pc_types.h
+++ b/drivers/gpu/drm/xe/xe_guc_pc_types.h
@@ -15,6 +15,8 @@
 struct xe_guc_pc {
 	/** @bo: GGTT buffer object that is shared with GuC PC */
 	struct xe_bo *bo;
+	/** @flush_freq_limit: 1 when max freq changes are limited by driver */
+	atomic_t flush_freq_limit;
 	/** @rp0_freq: HW RP0 frequency - The Maximum one */
 	u32 rp0_freq;
 	/** @rpe_freq: HW RPe frequency - The Efficient one */
diff --git a/drivers/gpu/drm/xe/xe_guc_relay.c b/drivers/gpu/drm/xe/xe_guc_relay.c
index ade6162dc259..0e5b43e1518e 100644
--- a/drivers/gpu/drm/xe/xe_guc_relay.c
+++ b/drivers/gpu/drm/xe/xe_guc_relay.c
@@ -224,7 +224,7 @@ __relay_get_transaction(struct xe_guc_relay *relay, bool incoming, u32 remote, u
 	 * with CTB lock held which is marked as used in the reclaim path.
 	 * Btw, that's one of the reason why we use mempool here!
 	 */
-	txn = mempool_alloc(&relay->pool, incoming ? GFP_ATOMIC : GFP_KERNEL);
+	txn = mempool_alloc(&relay->pool, incoming ? GFP_ATOMIC : GFP_NOWAIT);
 	if (!txn)
 		return ERR_PTR(-ENOMEM);
 
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index fed23304e4da..cf6946424fc3 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -227,6 +227,17 @@ static bool exec_queue_killed_or_banned_or_wedged(struct xe_exec_queue *q)
 static void guc_submit_fini(struct drm_device *drm, void *arg)
 {
 	struct xe_guc *guc = arg;
+	struct xe_device *xe = guc_to_xe(guc);
+	struct xe_gt *gt = guc_to_gt(guc);
+	int ret;
+
+	ret = wait_event_timeout(guc->submission_state.fini_wq,
+				 xa_empty(&guc->submission_state.exec_queue_lookup),
+				 HZ * 5);
+
+	drain_workqueue(xe->destroy_wq);
+
+	xe_gt_assert(gt, ret);
 
 	xa_destroy(&guc->submission_state.exec_queue_lookup);
 }
@@ -298,6 +309,8 @@ int xe_guc_submit_init(struct xe_guc *guc, unsigned int num_ids)
 
 	primelockdep(guc);
 
+	guc->submission_state.initialized = true;
+
 	return drmm_add_action_or_reset(&xe->drm, guc_submit_fini, guc);
 }
 
@@ -826,6 +839,13 @@ void xe_guc_submit_wedge(struct xe_guc *guc)
 
 	xe_gt_assert(guc_to_gt(guc), guc_to_xe(guc)->wedged.mode);
 
+	/*
+	 * If device is being wedged even before submission_state is
+	 * initialized, there's nothing to do here.
+	 */
+	if (!guc->submission_state.initialized)
+		return;
+
 	err = devm_add_action_or_reset(guc_to_xe(guc)->drm.dev,
 				       guc_submit_wedged_fini, guc);
 	if (err) {
@@ -1213,13 +1233,19 @@ static void __guc_exec_queue_fini_async(struct work_struct *w)
 	xe_pm_runtime_get(guc_to_xe(guc));
 	trace_xe_exec_queue_destroy(q);
 
+	release_guc_id(guc, q);
 	if (xe_exec_queue_is_lr(q))
 		cancel_work_sync(&ge->lr_tdr);
-	release_guc_id(guc, q);
+	/* Confirm no work left behind accessing device structures */
+	cancel_delayed_work_sync(&ge->sched.base.work_tdr);
 	xe_sched_entity_fini(&ge->entity);
 	xe_sched_fini(&ge->sched);
 
-	kfree(ge);
+	/*
+	 * RCU free due sched being exported via DRM scheduler fences
+	 * (timeline name).
+	 */
+	kfree_rcu(ge, rcu);
 	xe_exec_queue_fini(q);
 	xe_pm_runtime_put(guc_to_xe(guc));
 }
@@ -1405,6 +1431,7 @@ static int guc_exec_queue_init(struct xe_exec_queue *q)
 
 	q->guc = ge;
 	ge->q = q;
+	init_rcu_head(&ge->rcu);
 	init_waitqueue_head(&ge->suspend_wait);
 
 	for (i = 0; i < MAX_STATIC_MSG_TYPE; ++i)
@@ -1700,6 +1727,9 @@ int xe_guc_submit_reset_prepare(struct xe_guc *guc)
 {
 	int ret;
 
+	if (!guc->submission_state.initialized)
+		return 0;
+
 	/*
 	 * Using an atomic here rather than submission_state.lock as this
 	 * function can be called while holding the CT lock (engine reset
diff --git a/drivers/gpu/drm/xe/xe_guc_types.h b/drivers/gpu/drm/xe/xe_guc_types.h
index ed150fc09ad0..7842b71e68be 100644
--- a/drivers/gpu/drm/xe/xe_guc_types.h
+++ b/drivers/gpu/drm/xe/xe_guc_types.h
@@ -74,6 +74,11 @@ struct xe_guc {
 		struct mutex lock;
 		/** @submission_state.enabled: submission is enabled */
 		bool enabled;
+		/**
+		 * @submission_state.initialized: mark when submission state is
+		 * even initialized - before that not even the lock is valid
+		 */
+		bool initialized;
 		/** @submission_state.fini_wq: submit fini wait queue */
 		wait_queue_head_t fini_wq;
 	} submission_state;
diff --git a/drivers/gpu/drm/xe/xe_hmm.c b/drivers/gpu/drm/xe/xe_hmm.c
index 2c32dc46f7d4..3d0278c3db93 100644
--- a/drivers/gpu/drm/xe/xe_hmm.c
+++ b/drivers/gpu/drm/xe/xe_hmm.c
@@ -19,39 +19,51 @@ static u64 xe_npages_in_range(unsigned long start, unsigned long end)
 	return (end - start) >> PAGE_SHIFT;
 }
 
-/*
- * xe_mark_range_accessed() - mark a range is accessed, so core mm
- * have such information for memory eviction or write back to
- * hard disk
- *
- * @range: the range to mark
- * @write: if write to this range, we mark pages in this range
- * as dirty
- */
-static void xe_mark_range_accessed(struct hmm_range *range, bool write)
+static int xe_alloc_sg(struct xe_device *xe, struct sg_table *st,
+		       struct hmm_range *range, struct rw_semaphore *notifier_sem)
 {
-	struct page *page;
-	u64 i, npages;
+	unsigned long i, npages, hmm_pfn;
+	unsigned long num_chunks = 0;
+	int ret;
+
+	/* HMM docs says this is needed. */
+	ret = down_read_interruptible(notifier_sem);
+	if (ret)
+		return ret;
+
+	if (mmu_interval_read_retry(range->notifier, range->notifier_seq)) {
+		up_read(notifier_sem);
+		return -EAGAIN;
+	}
 
 	npages = xe_npages_in_range(range->start, range->end);
-	for (i = 0; i < npages; i++) {
-		page = hmm_pfn_to_page(range->hmm_pfns[i]);
-		if (write)
-			set_page_dirty_lock(page);
+	for (i = 0; i < npages;) {
+		unsigned long len;
+
+		hmm_pfn = range->hmm_pfns[i];
+		xe_assert(xe, hmm_pfn & HMM_PFN_VALID);
 
-		mark_page_accessed(page);
+		len = 1UL << hmm_pfn_to_map_order(hmm_pfn);
+
+		/* If order > 0 the page may extend beyond range->start */
+		len -= (hmm_pfn & ~HMM_PFN_FLAGS) & (len - 1);
+		i += len;
+		num_chunks++;
 	}
+	up_read(notifier_sem);
+
+	return sg_alloc_table(st, num_chunks, GFP_KERNEL);
 }
 
-/*
+/**
  * xe_build_sg() - build a scatter gather table for all the physical pages/pfn
  * in a hmm_range. dma-map pages if necessary. dma-address is save in sg table
  * and will be used to program GPU page table later.
- *
  * @xe: the xe device who will access the dma-address in sg table
  * @range: the hmm range that we build the sg table from. range->hmm_pfns[]
  * has the pfn numbers of pages that back up this hmm address range.
  * @st: pointer to the sg table.
+ * @notifier_sem: The xe notifier lock.
  * @write: whether we write to this range. This decides dma map direction
  * for system pages. If write we map it bi-diretional; otherwise
  * DMA_TO_DEVICE
@@ -78,43 +90,88 @@ static void xe_mark_range_accessed(struct hmm_range *range, bool write)
  * Returns 0 if successful; -ENOMEM if fails to allocate memory
  */
 static int xe_build_sg(struct xe_device *xe, struct hmm_range *range,
-		       struct sg_table *st, bool write)
+		       struct sg_table *st,
+		       struct rw_semaphore *notifier_sem,
+		       bool write)
 {
+	unsigned long npages = xe_npages_in_range(range->start, range->end);
 	struct device *dev = xe->drm.dev;
-	struct page **pages;
-	u64 i, npages;
-	int ret;
+	struct scatterlist *sgl;
+	struct page *page;
+	unsigned long i, j;
 
-	npages = xe_npages_in_range(range->start, range->end);
-	pages = kvmalloc_array(npages, sizeof(*pages), GFP_KERNEL);
-	if (!pages)
-		return -ENOMEM;
+	lockdep_assert_held(notifier_sem);
+
+	i = 0;
+	for_each_sg(st->sgl, sgl, st->nents, j) {
+		unsigned long hmm_pfn, size;
+
+		hmm_pfn = range->hmm_pfns[i];
+		page = hmm_pfn_to_page(hmm_pfn);
+		xe_assert(xe, !is_device_private_page(page));
+
+		size = 1UL << hmm_pfn_to_map_order(hmm_pfn);
+		size -= page_to_pfn(page) & (size - 1);
+		i += size;
 
-	for (i = 0; i < npages; i++) {
-		pages[i] = hmm_pfn_to_page(range->hmm_pfns[i]);
-		xe_assert(xe, !is_device_private_page(pages[i]));
+		if (unlikely(j == st->nents - 1)) {
+			xe_assert(xe, i >= npages);
+			if (i > npages)
+				size -= (i - npages);
+
+			sg_mark_end(sgl);
+		} else {
+			xe_assert(xe, i < npages);
+		}
+
+		sg_set_page(sgl, page, size << PAGE_SHIFT, 0);
 	}
 
-	ret = sg_alloc_table_from_pages_segment(st, pages, npages, 0, npages << PAGE_SHIFT,
-						xe_sg_segment_size(dev), GFP_KERNEL);
-	if (ret)
-		goto free_pages;
+	return dma_map_sgtable(dev, st, write ? DMA_BIDIRECTIONAL : DMA_TO_DEVICE,
+			       DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_NO_KERNEL_MAPPING);
+}
+
+static void xe_hmm_userptr_set_mapped(struct xe_userptr_vma *uvma)
+{
+	struct xe_userptr *userptr = &uvma->userptr;
+	struct xe_vm *vm = xe_vma_vm(&uvma->vma);
+
+	lockdep_assert_held_write(&vm->lock);
+	lockdep_assert_held(&vm->userptr.notifier_lock);
+
+	mutex_lock(&userptr->unmap_mutex);
+	xe_assert(vm->xe, !userptr->mapped);
+	userptr->mapped = true;
+	mutex_unlock(&userptr->unmap_mutex);
+}
 
-	ret = dma_map_sgtable(dev, st, write ? DMA_BIDIRECTIONAL : DMA_TO_DEVICE,
-			      DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_NO_KERNEL_MAPPING);
-	if (ret) {
-		sg_free_table(st);
-		st = NULL;
+void xe_hmm_userptr_unmap(struct xe_userptr_vma *uvma)
+{
+	struct xe_userptr *userptr = &uvma->userptr;
+	struct xe_vma *vma = &uvma->vma;
+	bool write = !xe_vma_read_only(vma);
+	struct xe_vm *vm = xe_vma_vm(vma);
+	struct xe_device *xe = vm->xe;
+
+	if (!lockdep_is_held_type(&vm->userptr.notifier_lock, 0) &&
+	    !lockdep_is_held_type(&vm->lock, 0) &&
+	    !(vma->gpuva.flags & XE_VMA_DESTROYED)) {
+		/* Don't unmap in exec critical section. */
+		xe_vm_assert_held(vm);
+		/* Don't unmap while mapping the sg. */
+		lockdep_assert_held(&vm->lock);
 	}
 
-free_pages:
-	kvfree(pages);
-	return ret;
+	mutex_lock(&userptr->unmap_mutex);
+	if (userptr->sg && userptr->mapped)
+		dma_unmap_sgtable(xe->drm.dev, userptr->sg,
+				  write ? DMA_BIDIRECTIONAL : DMA_TO_DEVICE, 0);
+	userptr->mapped = false;
+	mutex_unlock(&userptr->unmap_mutex);
 }
 
-/*
+/**
  * xe_hmm_userptr_free_sg() - Free the scatter gather table of userptr
- *
  * @uvma: the userptr vma which hold the scatter gather table
  *
  * With function xe_userptr_populate_range, we allocate storage of
@@ -124,16 +181,9 @@ free_pages:
 void xe_hmm_userptr_free_sg(struct xe_userptr_vma *uvma)
 {
 	struct xe_userptr *userptr = &uvma->userptr;
-	struct xe_vma *vma = &uvma->vma;
-	bool write = !xe_vma_read_only(vma);
-	struct xe_vm *vm = xe_vma_vm(vma);
-	struct xe_device *xe = vm->xe;
-	struct device *dev = xe->drm.dev;
-
-	xe_assert(xe, userptr->sg);
-	dma_unmap_sgtable(dev, userptr->sg,
-			  write ? DMA_BIDIRECTIONAL : DMA_TO_DEVICE, 0);
 
+	xe_assert(xe_vma_vm(&uvma->vma)->xe, userptr->sg);
+	xe_hmm_userptr_unmap(uvma);
 	sg_free_table(userptr->sg);
 	userptr->sg = NULL;
 }
@@ -166,13 +216,20 @@ int xe_hmm_userptr_populate_range(struct xe_userptr_vma *uvma,
 {
 	unsigned long timeout =
 		jiffies + msecs_to_jiffies(HMM_RANGE_DEFAULT_TIMEOUT);
-	unsigned long *pfns, flags = HMM_PFN_REQ_FAULT;
+	unsigned long *pfns;
 	struct xe_userptr *userptr;
 	struct xe_vma *vma = &uvma->vma;
 	u64 userptr_start = xe_vma_userptr(vma);
 	u64 userptr_end = userptr_start + xe_vma_size(vma);
 	struct xe_vm *vm = xe_vma_vm(vma);
-	struct hmm_range hmm_range;
+	struct hmm_range hmm_range = {
+		.pfn_flags_mask = 0, /* ignore pfns */
+		.default_flags = HMM_PFN_REQ_FAULT,
+		.start = userptr_start,
+		.end = userptr_end,
+		.notifier = &uvma->userptr.notifier,
+		.dev_private_owner = vm->xe,
+	};
 	bool write = !xe_vma_read_only(vma);
 	unsigned long notifier_seq;
 	u64 npages;
@@ -199,19 +256,14 @@ int xe_hmm_userptr_populate_range(struct xe_userptr_vma *uvma,
 		return -ENOMEM;
 
 	if (write)
-		flags |= HMM_PFN_REQ_WRITE;
+		hmm_range.default_flags |= HMM_PFN_REQ_WRITE;
 
 	if (!mmget_not_zero(userptr->notifier.mm)) {
 		ret = -EFAULT;
 		goto free_pfns;
 	}
 
-	hmm_range.default_flags = flags;
 	hmm_range.hmm_pfns = pfns;
-	hmm_range.notifier = &userptr->notifier;
-	hmm_range.start = userptr_start;
-	hmm_range.end = userptr_end;
-	hmm_range.dev_private_owner = vm->xe;
 
 	while (true) {
 		hmm_range.notifier_seq = mmu_interval_read_begin(&userptr->notifier);
@@ -238,16 +290,36 @@ int xe_hmm_userptr_populate_range(struct xe_userptr_vma *uvma,
 	if (ret)
 		goto free_pfns;
 
-	ret = xe_build_sg(vm->xe, &hmm_range, &userptr->sgt, write);
+	ret = xe_alloc_sg(vm->xe, &userptr->sgt, &hmm_range, &vm->userptr.notifier_lock);
 	if (ret)
 		goto free_pfns;
 
-	xe_mark_range_accessed(&hmm_range, write);
+	ret = down_read_interruptible(&vm->userptr.notifier_lock);
+	if (ret)
+		goto free_st;
+
+	if (mmu_interval_read_retry(hmm_range.notifier, hmm_range.notifier_seq)) {
+		ret = -EAGAIN;
+		goto out_unlock;
+	}
+
+	ret = xe_build_sg(vm->xe, &hmm_range, &userptr->sgt,
+			  &vm->userptr.notifier_lock, write);
+	if (ret)
+		goto out_unlock;
+
 	userptr->sg = &userptr->sgt;
+	xe_hmm_userptr_set_mapped(uvma);
 	userptr->notifier_seq = hmm_range.notifier_seq;
+	up_read(&vm->userptr.notifier_lock);
+	kvfree(pfns);
+	return 0;
 
+out_unlock:
+	up_read(&vm->userptr.notifier_lock);
+free_st:
+	sg_free_table(&userptr->sgt);
 free_pfns:
 	kvfree(pfns);
 	return ret;
 }
-
diff --git a/drivers/gpu/drm/xe/xe_hmm.h b/drivers/gpu/drm/xe/xe_hmm.h
index 909dc2bdcd97..0ea98d8e7bbc 100644
--- a/drivers/gpu/drm/xe/xe_hmm.h
+++ b/drivers/gpu/drm/xe/xe_hmm.h
@@ -3,9 +3,16 @@
  * Copyright © 2024 Intel Corporation
  */
 
+#ifndef _XE_HMM_H_
+#define _XE_HMM_H_
+
 #include <linux/types.h>
 
 struct xe_userptr_vma;
 
 int xe_hmm_userptr_populate_range(struct xe_userptr_vma *uvma, bool is_mm_mmap_locked);
+
 void xe_hmm_userptr_free_sg(struct xe_userptr_vma *uvma);
+
+void xe_hmm_userptr_unmap(struct xe_userptr_vma *uvma);
+#endif
diff --git a/drivers/gpu/drm/xe/xe_hw_engine.c b/drivers/gpu/drm/xe/xe_hw_engine.c
index b11bc0f00dfd..0248597c6269 100644
--- a/drivers/gpu/drm/xe/xe_hw_engine.c
+++ b/drivers/gpu/drm/xe/xe_hw_engine.c
@@ -381,12 +381,6 @@ xe_hw_engine_setup_default_lrc_state(struct xe_hw_engine *hwe)
 				 blit_cctl_val,
 				 XE_RTP_ACTION_FLAG(ENGINE_BASE)))
 		},
-		/* Use Fixed slice CCS mode */
-		{ XE_RTP_NAME("RCU_MODE_FIXED_SLICE_CCS_MODE"),
-		  XE_RTP_RULES(FUNC(xe_hw_engine_match_fixed_cslice_mode)),
-		  XE_RTP_ACTIONS(FIELD_SET(RCU_MODE, RCU_MODE_FIXED_SLICE_CCS_MODE,
-					   RCU_MODE_FIXED_SLICE_CCS_MODE))
-		},
 		/* Disable WMTP if HW doesn't support it */
 		{ XE_RTP_NAME("DISABLE_WMTP_ON_UNSUPPORTED_HW"),
 		  XE_RTP_RULES(FUNC(xe_rtp_cfeg_wmtp_disabled)),
@@ -454,6 +448,12 @@ hw_engine_setup_default_state(struct xe_hw_engine *hwe)
 		  XE_RTP_ACTIONS(SET(CSFE_CHICKEN1(0), CS_PRIORITY_MEM_READ,
 				     XE_RTP_ACTION_FLAG(ENGINE_BASE)))
 		},
+		/* Use Fixed slice CCS mode */
+		{ XE_RTP_NAME("RCU_MODE_FIXED_SLICE_CCS_MODE"),
+		  XE_RTP_RULES(FUNC(xe_hw_engine_match_fixed_cslice_mode)),
+		  XE_RTP_ACTIONS(FIELD_SET(RCU_MODE, RCU_MODE_FIXED_SLICE_CCS_MODE,
+					   RCU_MODE_FIXED_SLICE_CCS_MODE))
+		},
 		{}
 	};
 
diff --git a/drivers/gpu/drm/xe/xe_hw_engine_class_sysfs.c b/drivers/gpu/drm/xe/xe_hw_engine_class_sysfs.c
index b53e8d2accdb..a440442b4d72 100644
--- a/drivers/gpu/drm/xe/xe_hw_engine_class_sysfs.c
+++ b/drivers/gpu/drm/xe/xe_hw_engine_class_sysfs.c
@@ -32,14 +32,61 @@ bool xe_hw_engine_timeout_in_range(u64 timeout, u64 min, u64 max)
 	return timeout >= min && timeout <= max;
 }
 
-static void kobj_xe_hw_engine_release(struct kobject *kobj)
+static void xe_hw_engine_sysfs_kobj_release(struct kobject *kobj)
 {
 	kfree(kobj);
 }
 
+static ssize_t xe_hw_engine_class_sysfs_attr_show(struct kobject *kobj,
+						  struct attribute *attr,
+						  char *buf)
+{
+	struct xe_device *xe = kobj_to_xe(kobj);
+	struct kobj_attribute *kattr;
+	ssize_t ret = -EIO;
+
+	kattr = container_of(attr, struct kobj_attribute, attr);
+	if (kattr->show) {
+		xe_pm_runtime_get(xe);
+		ret = kattr->show(kobj, kattr, buf);
+		xe_pm_runtime_put(xe);
+	}
+
+	return ret;
+}
+
+static ssize_t xe_hw_engine_class_sysfs_attr_store(struct kobject *kobj,
+						   struct attribute *attr,
+						   const char *buf,
+						   size_t count)
+{
+	struct xe_device *xe = kobj_to_xe(kobj);
+	struct kobj_attribute *kattr;
+	ssize_t ret = -EIO;
+
+	kattr = container_of(attr, struct kobj_attribute, attr);
+	if (kattr->store) {
+		xe_pm_runtime_get(xe);
+		ret = kattr->store(kobj, kattr, buf, count);
+		xe_pm_runtime_put(xe);
+	}
+
+	return ret;
+}
+
+static const struct sysfs_ops xe_hw_engine_class_sysfs_ops = {
+	.show = xe_hw_engine_class_sysfs_attr_show,
+	.store = xe_hw_engine_class_sysfs_attr_store,
+};
+
 static const struct kobj_type kobj_xe_hw_engine_type = {
-	.release = kobj_xe_hw_engine_release,
-	.sysfs_ops = &kobj_sysfs_ops
+	.release = xe_hw_engine_sysfs_kobj_release,
+	.sysfs_ops = &xe_hw_engine_class_sysfs_ops,
+};
+
+static const struct kobj_type kobj_xe_hw_engine_type_def = {
+	.release = xe_hw_engine_sysfs_kobj_release,
+	.sysfs_ops = &kobj_sysfs_ops,
 };
 
 static ssize_t job_timeout_max_store(struct kobject *kobj,
@@ -543,7 +590,7 @@ static int xe_add_hw_engine_class_defaults(struct xe_device *xe,
 	if (!kobj)
 		return -ENOMEM;
 
-	kobject_init(kobj, &kobj_xe_hw_engine_type);
+	kobject_init(kobj, &kobj_xe_hw_engine_type_def);
 	err = kobject_add(kobj, parent, "%s", ".defaults");
 	if (err)
 		goto err_object;
@@ -559,57 +606,6 @@ err_object:
 	return err;
 }
 
-static void xe_hw_engine_sysfs_kobj_release(struct kobject *kobj)
-{
-	kfree(kobj);
-}
-
-static ssize_t xe_hw_engine_class_sysfs_attr_show(struct kobject *kobj,
-						  struct attribute *attr,
-						  char *buf)
-{
-	struct xe_device *xe = kobj_to_xe(kobj);
-	struct kobj_attribute *kattr;
-	ssize_t ret = -EIO;
-
-	kattr = container_of(attr, struct kobj_attribute, attr);
-	if (kattr->show) {
-		xe_pm_runtime_get(xe);
-		ret = kattr->show(kobj, kattr, buf);
-		xe_pm_runtime_put(xe);
-	}
-
-	return ret;
-}
-
-static ssize_t xe_hw_engine_class_sysfs_attr_store(struct kobject *kobj,
-						   struct attribute *attr,
-						   const char *buf,
-						   size_t count)
-{
-	struct xe_device *xe = kobj_to_xe(kobj);
-	struct kobj_attribute *kattr;
-	ssize_t ret = -EIO;
-
-	kattr = container_of(attr, struct kobj_attribute, attr);
-	if (kattr->store) {
-		xe_pm_runtime_get(xe);
-		ret = kattr->store(kobj, kattr, buf, count);
-		xe_pm_runtime_put(xe);
-	}
-
-	return ret;
-}
-
-static const struct sysfs_ops xe_hw_engine_class_sysfs_ops = {
-	.show = xe_hw_engine_class_sysfs_attr_show,
-	.store = xe_hw_engine_class_sysfs_attr_store,
-};
-
-static const struct kobj_type xe_hw_engine_sysfs_kobj_type = {
-	.release = xe_hw_engine_sysfs_kobj_release,
-	.sysfs_ops = &xe_hw_engine_class_sysfs_ops,
-};
 
 static void hw_engine_class_sysfs_fini(void *arg)
 {
@@ -640,7 +636,7 @@ int xe_hw_engine_class_sysfs_init(struct xe_gt *gt)
 	if (!kobj)
 		return -ENOMEM;
 
-	kobject_init(kobj, &xe_hw_engine_sysfs_kobj_type);
+	kobject_init(kobj, &kobj_xe_hw_engine_type);
 
 	err = kobject_add(kobj, gt->sysfs, "engines");
 	if (err)
diff --git a/drivers/gpu/drm/xe/xe_hw_fence.c b/drivers/gpu/drm/xe/xe_hw_fence.c
index 0b4f12be3692..6e2221b60688 100644
--- a/drivers/gpu/drm/xe/xe_hw_fence.c
+++ b/drivers/gpu/drm/xe/xe_hw_fence.c
@@ -100,6 +100,9 @@ void xe_hw_fence_irq_finish(struct xe_hw_fence_irq *irq)
 		spin_unlock_irqrestore(&irq->lock, flags);
 		dma_fence_end_signalling(tmp);
 	}
+
+	/* Safe release of the irq->lock used in dma_fence_init. */
+	synchronize_rcu();
 }
 
 void xe_hw_fence_irq_run(struct xe_hw_fence_irq *irq)
diff --git a/drivers/gpu/drm/xe/xe_irq.c b/drivers/gpu/drm/xe/xe_irq.c
index 5f2c368c35ad..14c3a476597a 100644
--- a/drivers/gpu/drm/xe/xe_irq.c
+++ b/drivers/gpu/drm/xe/xe_irq.c
@@ -173,7 +173,7 @@ void xe_irq_enable_hwe(struct xe_gt *gt)
 		if (ccs_mask & (BIT(0)|BIT(1)))
 			xe_mmio_write32(gt, CCS0_CCS1_INTR_MASK, ~dmask);
 		if (ccs_mask & (BIT(2)|BIT(3)))
-			xe_mmio_write32(gt,  CCS2_CCS3_INTR_MASK, ~dmask);
+			xe_mmio_write32(gt, CCS2_CCS3_INTR_MASK, ~dmask);
 	}
 
 	if (xe_gt_is_media_type(gt) || MEDIA_VER(xe) < 13) {
@@ -504,7 +504,7 @@ static void gt_irq_reset(struct xe_tile *tile)
 	if (ccs_mask & (BIT(0)|BIT(1)))
 		xe_mmio_write32(mmio, CCS0_CCS1_INTR_MASK, ~0);
 	if (ccs_mask & (BIT(2)|BIT(3)))
-		xe_mmio_write32(mmio,  CCS2_CCS3_INTR_MASK, ~0);
+		xe_mmio_write32(mmio, CCS2_CCS3_INTR_MASK, ~0);
 
 	if ((tile->media_gt &&
 	     xe_hw_engine_mask_per_class(tile->media_gt, XE_ENGINE_CLASS_OTHER)) ||
diff --git a/drivers/gpu/drm/xe/xe_lmtt.c b/drivers/gpu/drm/xe/xe_lmtt.c
index 8999ac511555..485658f69fba 100644
--- a/drivers/gpu/drm/xe/xe_lmtt.c
+++ b/drivers/gpu/drm/xe/xe_lmtt.c
@@ -78,6 +78,9 @@ static struct xe_lmtt_pt *lmtt_pt_alloc(struct xe_lmtt *lmtt, unsigned int level
 	}
 
 	lmtt_assert(lmtt, xe_bo_is_vram(bo));
+	lmtt_debug(lmtt, "level=%u addr=%#llx\n", level, (u64)xe_bo_main_addr(bo, XE_PAGE_SIZE));
+
+	xe_map_memset(lmtt_to_xe(lmtt), &bo->vmap, 0, 0, bo->size);
 
 	pt->level = level;
 	pt->bo = bo;
@@ -91,6 +94,9 @@ out:
 
 static void lmtt_pt_free(struct xe_lmtt_pt *pt)
 {
+	lmtt_debug(&pt->bo->tile->sriov.pf.lmtt, "level=%u addr=%llx\n",
+		   pt->level, (u64)xe_bo_main_addr(pt->bo, XE_PAGE_SIZE));
+
 	xe_bo_unpin_map_no_vm(pt->bo);
 	kfree(pt);
 }
@@ -226,9 +232,14 @@ static void lmtt_write_pte(struct xe_lmtt *lmtt, struct xe_lmtt_pt *pt,
 
 	switch (lmtt->ops->lmtt_pte_size(level)) {
 	case sizeof(u32):
+		lmtt_assert(lmtt, !overflows_type(pte, u32));
+		lmtt_assert(lmtt, !pte || !iosys_map_rd(&pt->bo->vmap, idx * sizeof(u32), u32));
+
 		xe_map_wr(lmtt_to_xe(lmtt), &pt->bo->vmap, idx * sizeof(u32), u32, pte);
 		break;
 	case sizeof(u64):
+		lmtt_assert(lmtt, !pte || !iosys_map_rd(&pt->bo->vmap, idx * sizeof(u64), u64));
+
 		xe_map_wr(lmtt_to_xe(lmtt), &pt->bo->vmap, idx * sizeof(u64), u64, pte);
 		break;
 	default:
diff --git a/drivers/gpu/drm/xe/xe_lrc.c b/drivers/gpu/drm/xe/xe_lrc.c
index aec7db39c061..ce6d2167b94a 100644
--- a/drivers/gpu/drm/xe/xe_lrc.c
+++ b/drivers/gpu/drm/xe/xe_lrc.c
@@ -694,7 +694,7 @@ static inline u32 __xe_lrc_start_seqno_offset(struct xe_lrc *lrc)
 
 static u32 __xe_lrc_ctx_job_timestamp_offset(struct xe_lrc *lrc)
 {
-	/* The start seqno is stored in the driver-defined portion of PPHWSP */
+	/* This is stored in the driver-defined portion of PPHWSP */
 	return xe_lrc_pphwsp_offset(lrc) + LRC_CTX_JOB_TIMESTAMP_OFFSET;
 }
 
@@ -874,7 +874,7 @@ static void *empty_lrc_data(struct xe_hw_engine *hwe)
 
 static void xe_lrc_set_ppgtt(struct xe_lrc *lrc, struct xe_vm *vm)
 {
-	u64 desc = xe_vm_pdp4_descriptor(vm, lrc->tile);
+	u64 desc = xe_vm_pdp4_descriptor(vm, gt_to_tile(lrc->gt));
 
 	xe_lrc_write_ctx_reg(lrc, CTX_PDP0_UDW, upper_32_bits(desc));
 	xe_lrc_write_ctx_reg(lrc, CTX_PDP0_LDW, lower_32_bits(desc));
@@ -905,6 +905,7 @@ static int xe_lrc_init(struct xe_lrc *lrc, struct xe_hw_engine *hwe,
 	int err;
 
 	kref_init(&lrc->refcount);
+	lrc->gt = gt;
 	lrc->flags = 0;
 	lrc_size = ring_size + xe_gt_lrc_size(gt, hwe->class);
 	if (xe_gt_has_indirect_ring_state(gt))
@@ -923,7 +924,6 @@ static int xe_lrc_init(struct xe_lrc *lrc, struct xe_hw_engine *hwe,
 		return PTR_ERR(lrc->bo);
 
 	lrc->size = lrc_size;
-	lrc->tile = gt_to_tile(hwe->gt);
 	lrc->ring.size = ring_size;
 	lrc->ring.tail = 0;
 	lrc->ctx_timestamp = 0;
diff --git a/drivers/gpu/drm/xe/xe_lrc_types.h b/drivers/gpu/drm/xe/xe_lrc_types.h
index 71ecb453f811..cd38586ae989 100644
--- a/drivers/gpu/drm/xe/xe_lrc_types.h
+++ b/drivers/gpu/drm/xe/xe_lrc_types.h
@@ -25,8 +25,8 @@ struct xe_lrc {
 	/** @size: size of lrc including any indirect ring state page */
 	u32 size;
 
-	/** @tile: tile which this LRC belongs to */
-	struct xe_tile *tile;
+	/** @gt: gt which this LRC belongs to */
+	struct xe_gt *gt;
 
 	/** @flags: LRC flags */
 #define XE_LRC_FLAG_INDIRECT_RING_STATE		0x1
diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c
index 1b97d90aadda..c2da2691fd2b 100644
--- a/drivers/gpu/drm/xe/xe_migrate.c
+++ b/drivers/gpu/drm/xe/xe_migrate.c
@@ -860,7 +860,7 @@ struct dma_fence *xe_migrate_copy(struct xe_migrate *m,
 		if (src_is_vram && xe_migrate_allow_identity(src_L0, &src_it))
 			xe_res_next(&src_it, src_L0);
 		else
-			emit_pte(m, bb, src_L0_pt, src_is_vram, copy_system_ccs,
+			emit_pte(m, bb, src_L0_pt, src_is_vram, copy_system_ccs || use_comp_pat,
 				 &src_it, src_L0, src);
 
 		if (dst_is_vram && xe_migrate_allow_identity(src_L0, &dst_it))
@@ -1177,7 +1177,7 @@ err:
 err_sync:
 		/* Sync partial copies if any. FIXME: job_mutex? */
 		if (fence) {
-			dma_fence_wait(m->fence, false);
+			dma_fence_wait(fence, false);
 			dma_fence_put(fence);
 		}
 
diff --git a/drivers/gpu/drm/xe/xe_oa.c b/drivers/gpu/drm/xe/xe_oa.c
index 6fc00d63b285..d306ed0a0443 100644
--- a/drivers/gpu/drm/xe/xe_oa.c
+++ b/drivers/gpu/drm/xe/xe_oa.c
@@ -36,11 +36,22 @@
 #include "xe_pm.h"
 #include "xe_sched_job.h"
 #include "xe_sriov.h"
+#include "xe_sync.h"
 
 #define DEFAULT_POLL_FREQUENCY_HZ 200
 #define DEFAULT_POLL_PERIOD_NS (NSEC_PER_SEC / DEFAULT_POLL_FREQUENCY_HZ)
 #define XE_OA_UNIT_INVALID U32_MAX
 
+enum xe_oa_submit_deps {
+	XE_OA_SUBMIT_NO_DEPS,
+	XE_OA_SUBMIT_ADD_DEPS,
+};
+
+enum xe_oa_user_extn_from {
+	XE_OA_USER_EXTN_FROM_OPEN,
+	XE_OA_USER_EXTN_FROM_CONFIG,
+};
+
 struct xe_oa_reg {
 	struct xe_reg addr;
 	u32 value;
@@ -63,13 +74,8 @@ struct xe_oa_config {
 	struct rcu_head rcu;
 };
 
-struct flex {
-	struct xe_reg reg;
-	u32 offset;
-	u32 value;
-};
-
 struct xe_oa_open_param {
+	struct xe_file *xef;
 	u32 oa_unit_id;
 	bool sample;
 	u32 metric_set;
@@ -81,6 +87,9 @@ struct xe_oa_open_param {
 	struct xe_exec_queue *exec_q;
 	struct xe_hw_engine *hwe;
 	bool no_preempt;
+	struct drm_xe_sync __user *syncs_user;
+	int num_syncs;
+	struct xe_sync_entry *syncs;
 };
 
 struct xe_oa_config_bo {
@@ -90,6 +99,17 @@ struct xe_oa_config_bo {
 	struct xe_bb *bb;
 };
 
+struct xe_oa_fence {
+	/* @base: dma fence base */
+	struct dma_fence base;
+	/* @lock: lock for the fence */
+	spinlock_t lock;
+	/* @work: work to signal @base */
+	struct delayed_work work;
+	/* @cb: callback to schedule @work */
+	struct dma_fence_cb cb;
+};
+
 #define DRM_FMT(x) DRM_XE_OA_FMT_TYPE_##x
 
 static const struct xe_oa_format oa_formats[] = {
@@ -162,10 +182,10 @@ static struct xe_oa_config *xe_oa_get_oa_config(struct xe_oa *oa, int metrics_se
 	return oa_config;
 }
 
-static void free_oa_config_bo(struct xe_oa_config_bo *oa_bo)
+static void free_oa_config_bo(struct xe_oa_config_bo *oa_bo, struct dma_fence *last_fence)
 {
 	xe_oa_config_put(oa_bo->oa_config);
-	xe_bb_free(oa_bo->bb, NULL);
+	xe_bb_free(oa_bo->bb, last_fence);
 	kfree(oa_bo);
 }
 
@@ -515,6 +535,7 @@ static ssize_t xe_oa_read(struct file *file, char __user *buf,
 			mutex_unlock(&stream->stream_lock);
 		} while (!offset && !ret);
 	} else {
+		xe_oa_buffer_check_unlocked(stream);
 		mutex_lock(&stream->stream_lock);
 		ret = __xe_oa_read(stream, buf, count, &offset);
 		mutex_unlock(&stream->stream_lock);
@@ -567,32 +588,60 @@ static __poll_t xe_oa_poll(struct file *file, poll_table *wait)
 	return ret;
 }
 
-static int xe_oa_submit_bb(struct xe_oa_stream *stream, struct xe_bb *bb)
+static void xe_oa_lock_vma(struct xe_exec_queue *q)
+{
+	if (q->vm) {
+		down_read(&q->vm->lock);
+		xe_vm_lock(q->vm, false);
+	}
+}
+
+static void xe_oa_unlock_vma(struct xe_exec_queue *q)
+{
+	if (q->vm) {
+		xe_vm_unlock(q->vm);
+		up_read(&q->vm->lock);
+	}
+}
+
+static struct dma_fence *xe_oa_submit_bb(struct xe_oa_stream *stream, enum xe_oa_submit_deps deps,
+					 struct xe_bb *bb)
 {
+	struct xe_exec_queue *q = stream->exec_q ?: stream->k_exec_q;
 	struct xe_sched_job *job;
 	struct dma_fence *fence;
-	long timeout;
 	int err = 0;
 
-	/* Kernel configuration is issued on stream->k_exec_q, not stream->exec_q */
-	job = xe_bb_create_job(stream->k_exec_q, bb);
+	xe_oa_lock_vma(q);
+
+	job = xe_bb_create_job(q, bb);
 	if (IS_ERR(job)) {
 		err = PTR_ERR(job);
 		goto exit;
 	}
+	job->ggtt = true;
+
+	if (deps == XE_OA_SUBMIT_ADD_DEPS) {
+		for (int i = 0; i < stream->num_syncs && !err; i++)
+			err = xe_sync_entry_add_deps(&stream->syncs[i], job);
+		if (err) {
+			drm_dbg(&stream->oa->xe->drm, "xe_sync_entry_add_deps err %d\n", err);
+			goto err_put_job;
+		}
+	}
 
 	xe_sched_job_arm(job);
 	fence = dma_fence_get(&job->drm.s_fence->finished);
 	xe_sched_job_push(job);
 
-	timeout = dma_fence_wait_timeout(fence, false, HZ);
-	dma_fence_put(fence);
-	if (timeout < 0)
-		err = timeout;
-	else if (!timeout)
-		err = -ETIME;
+	xe_oa_unlock_vma(q);
+
+	return fence;
+err_put_job:
+	xe_sched_job_put(job);
 exit:
-	return err;
+	xe_oa_unlock_vma(q);
+	return ERR_PTR(err);
 }
 
 static void write_cs_mi_lri(struct xe_bb *bb, const struct xe_oa_reg *reg_data, u32 n_regs)
@@ -636,57 +685,34 @@ static void xe_oa_free_configs(struct xe_oa_stream *stream)
 
 	xe_oa_config_put(stream->oa_config);
 	llist_for_each_entry_safe(oa_bo, tmp, stream->oa_config_bos.first, node)
-		free_oa_config_bo(oa_bo);
-}
-
-static void xe_oa_store_flex(struct xe_oa_stream *stream, struct xe_lrc *lrc,
-			     struct xe_bb *bb, const struct flex *flex, u32 count)
-{
-	u32 offset = xe_bo_ggtt_addr(lrc->bo);
-
-	do {
-		bb->cs[bb->len++] = MI_STORE_DATA_IMM | MI_SDI_GGTT | MI_SDI_NUM_DW(1);
-		bb->cs[bb->len++] = offset + flex->offset * sizeof(u32);
-		bb->cs[bb->len++] = 0;
-		bb->cs[bb->len++] = flex->value;
-
-	} while (flex++, --count);
+		free_oa_config_bo(oa_bo, stream->last_fence);
+	dma_fence_put(stream->last_fence);
 }
 
-static int xe_oa_modify_ctx_image(struct xe_oa_stream *stream, struct xe_lrc *lrc,
-				  const struct flex *flex, u32 count)
+static int xe_oa_load_with_lri(struct xe_oa_stream *stream, struct xe_oa_reg *reg_lri, u32 count)
 {
+	struct dma_fence *fence;
 	struct xe_bb *bb;
 	int err;
 
-	bb = xe_bb_new(stream->gt, 4 * count, false);
+	bb = xe_bb_new(stream->gt, 2 * count + 1, false);
 	if (IS_ERR(bb)) {
 		err = PTR_ERR(bb);
 		goto exit;
 	}
 
-	xe_oa_store_flex(stream, lrc, bb, flex, count);
-
-	err = xe_oa_submit_bb(stream, bb);
-	xe_bb_free(bb, NULL);
-exit:
-	return err;
-}
+	write_cs_mi_lri(bb, reg_lri, count);
 
-static int xe_oa_load_with_lri(struct xe_oa_stream *stream, struct xe_oa_reg *reg_lri)
-{
-	struct xe_bb *bb;
-	int err;
-
-	bb = xe_bb_new(stream->gt, 3, false);
-	if (IS_ERR(bb)) {
-		err = PTR_ERR(bb);
-		goto exit;
+	fence = xe_oa_submit_bb(stream, XE_OA_SUBMIT_NO_DEPS, bb);
+	if (IS_ERR(fence)) {
+		err = PTR_ERR(fence);
+		goto free_bb;
 	}
+	xe_bb_free(bb, fence);
+	dma_fence_put(fence);
 
-	write_cs_mi_lri(bb, reg_lri, 1);
-
-	err = xe_oa_submit_bb(stream, bb);
+	return 0;
+free_bb:
 	xe_bb_free(bb, NULL);
 exit:
 	return err;
@@ -695,70 +721,54 @@ exit:
 static int xe_oa_configure_oar_context(struct xe_oa_stream *stream, bool enable)
 {
 	const struct xe_oa_format *format = stream->oa_buffer.format;
-	struct xe_lrc *lrc = stream->exec_q->lrc[0];
-	u32 regs_offset = xe_lrc_regs_offset(lrc) / sizeof(u32);
 	u32 oacontrol = __format_to_oactrl(format, OAR_OACONTROL_COUNTER_SEL_MASK) |
 		(enable ? OAR_OACONTROL_COUNTER_ENABLE : 0);
 
-	struct flex regs_context[] = {
+	struct xe_oa_reg reg_lri[] = {
 		{
 			OACTXCONTROL(stream->hwe->mmio_base),
-			stream->oa->ctx_oactxctrl_offset[stream->hwe->class] + 1,
 			enable ? OA_COUNTER_RESUME : 0,
 		},
 		{
+			OAR_OACONTROL,
+			oacontrol,
+		},
+		{
 			RING_CONTEXT_CONTROL(stream->hwe->mmio_base),
-			regs_offset + CTX_CONTEXT_CONTROL,
-			_MASKED_BIT_ENABLE(CTX_CTRL_OAC_CONTEXT_ENABLE),
+			_MASKED_FIELD(CTX_CTRL_OAC_CONTEXT_ENABLE,
+				      enable ? CTX_CTRL_OAC_CONTEXT_ENABLE : 0)
 		},
 	};
-	struct xe_oa_reg reg_lri = { OAR_OACONTROL, oacontrol };
-	int err;
-
-	/* Modify stream hwe context image with regs_context */
-	err = xe_oa_modify_ctx_image(stream, stream->exec_q->lrc[0],
-				     regs_context, ARRAY_SIZE(regs_context));
-	if (err)
-		return err;
 
-	/* Apply reg_lri using LRI */
-	return xe_oa_load_with_lri(stream, &reg_lri);
+	return xe_oa_load_with_lri(stream, reg_lri, ARRAY_SIZE(reg_lri));
 }
 
 static int xe_oa_configure_oac_context(struct xe_oa_stream *stream, bool enable)
 {
 	const struct xe_oa_format *format = stream->oa_buffer.format;
-	struct xe_lrc *lrc = stream->exec_q->lrc[0];
-	u32 regs_offset = xe_lrc_regs_offset(lrc) / sizeof(u32);
 	u32 oacontrol = __format_to_oactrl(format, OAR_OACONTROL_COUNTER_SEL_MASK) |
 		(enable ? OAR_OACONTROL_COUNTER_ENABLE : 0);
-	struct flex regs_context[] = {
+	struct xe_oa_reg reg_lri[] = {
 		{
 			OACTXCONTROL(stream->hwe->mmio_base),
-			stream->oa->ctx_oactxctrl_offset[stream->hwe->class] + 1,
 			enable ? OA_COUNTER_RESUME : 0,
 		},
 		{
+			OAC_OACONTROL,
+			oacontrol
+		},
+		{
 			RING_CONTEXT_CONTROL(stream->hwe->mmio_base),
-			regs_offset + CTX_CONTEXT_CONTROL,
-			_MASKED_BIT_ENABLE(CTX_CTRL_OAC_CONTEXT_ENABLE) |
+			_MASKED_FIELD(CTX_CTRL_OAC_CONTEXT_ENABLE,
+				      enable ? CTX_CTRL_OAC_CONTEXT_ENABLE : 0) |
 			_MASKED_FIELD(CTX_CTRL_RUN_ALONE, enable ? CTX_CTRL_RUN_ALONE : 0),
 		},
 	};
-	struct xe_oa_reg reg_lri = { OAC_OACONTROL, oacontrol };
-	int err;
 
 	/* Set ccs select to enable programming of OAC_OACONTROL */
 	xe_mmio_write32(stream->gt, __oa_regs(stream)->oa_ctrl, __oa_ccs_select(stream));
 
-	/* Modify stream hwe context image with regs_context */
-	err = xe_oa_modify_ctx_image(stream, stream->exec_q->lrc[0],
-				     regs_context, ARRAY_SIZE(regs_context));
-	if (err)
-		return err;
-
-	/* Apply reg_lri using LRI */
-	return xe_oa_load_with_lri(stream, &reg_lri);
+	return xe_oa_load_with_lri(stream, reg_lri, ARRAY_SIZE(reg_lri));
 }
 
 static int xe_oa_configure_oa_context(struct xe_oa_stream *stream, bool enable)
@@ -840,6 +850,7 @@ static void xe_oa_stream_destroy(struct xe_oa_stream *stream)
 		xe_gt_WARN_ON(gt, xe_guc_pc_unset_gucrc_mode(&gt->uc.guc.pc));
 
 	xe_oa_free_configs(stream);
+	xe_file_put(stream->xef);
 }
 
 static int xe_oa_alloc_oa_buffer(struct xe_oa_stream *stream)
@@ -910,11 +921,62 @@ out:
 	return oa_bo;
 }
 
+static void xe_oa_update_last_fence(struct xe_oa_stream *stream, struct dma_fence *fence)
+{
+	dma_fence_put(stream->last_fence);
+	stream->last_fence = dma_fence_get(fence);
+}
+
+static void xe_oa_fence_work_fn(struct work_struct *w)
+{
+	struct xe_oa_fence *ofence = container_of(w, typeof(*ofence), work.work);
+
+	/* Signal fence to indicate new OA configuration is active */
+	dma_fence_signal(&ofence->base);
+	dma_fence_put(&ofence->base);
+}
+
+static void xe_oa_config_cb(struct dma_fence *fence, struct dma_fence_cb *cb)
+{
+	/* Additional empirical delay needed for NOA programming after registers are written */
+#define NOA_PROGRAM_ADDITIONAL_DELAY_US 500
+
+	struct xe_oa_fence *ofence = container_of(cb, typeof(*ofence), cb);
+
+	INIT_DELAYED_WORK(&ofence->work, xe_oa_fence_work_fn);
+	queue_delayed_work(system_unbound_wq, &ofence->work,
+			   usecs_to_jiffies(NOA_PROGRAM_ADDITIONAL_DELAY_US));
+	dma_fence_put(fence);
+}
+
+static const char *xe_oa_get_driver_name(struct dma_fence *fence)
+{
+	return "xe_oa";
+}
+
+static const char *xe_oa_get_timeline_name(struct dma_fence *fence)
+{
+	return "unbound";
+}
+
+static const struct dma_fence_ops xe_oa_fence_ops = {
+	.get_driver_name = xe_oa_get_driver_name,
+	.get_timeline_name = xe_oa_get_timeline_name,
+};
+
 static int xe_oa_emit_oa_config(struct xe_oa_stream *stream, struct xe_oa_config *config)
 {
 #define NOA_PROGRAM_ADDITIONAL_DELAY_US 500
 	struct xe_oa_config_bo *oa_bo;
-	int err, us = NOA_PROGRAM_ADDITIONAL_DELAY_US;
+	struct xe_oa_fence *ofence;
+	int i, err, num_signal = 0;
+	struct dma_fence *fence;
+
+	ofence = kzalloc(sizeof(*ofence), GFP_KERNEL);
+	if (!ofence) {
+		err = -ENOMEM;
+		goto exit;
+	}
 
 	oa_bo = xe_oa_alloc_config_buffer(stream, config);
 	if (IS_ERR(oa_bo)) {
@@ -922,11 +984,50 @@ static int xe_oa_emit_oa_config(struct xe_oa_stream *stream, struct xe_oa_config
 		goto exit;
 	}
 
-	err = xe_oa_submit_bb(stream, oa_bo->bb);
+	/* Emit OA configuration batch */
+	fence = xe_oa_submit_bb(stream, XE_OA_SUBMIT_ADD_DEPS, oa_bo->bb);
+	if (IS_ERR(fence)) {
+		err = PTR_ERR(fence);
+		goto exit;
+	}
 
-	/* Additional empirical delay needed for NOA programming after registers are written */
-	usleep_range(us, 2 * us);
+	/* Point of no return: initialize and set fence to signal */
+	spin_lock_init(&ofence->lock);
+	dma_fence_init(&ofence->base, &xe_oa_fence_ops, &ofence->lock, 0, 0);
+
+	for (i = 0; i < stream->num_syncs; i++) {
+		if (stream->syncs[i].flags & DRM_XE_SYNC_FLAG_SIGNAL)
+			num_signal++;
+		xe_sync_entry_signal(&stream->syncs[i], &ofence->base);
+	}
+
+	/* Additional dma_fence_get in case we dma_fence_wait */
+	if (!num_signal)
+		dma_fence_get(&ofence->base);
+
+	/* Update last fence too before adding callback */
+	xe_oa_update_last_fence(stream, fence);
+
+	/* Add job fence callback to schedule work to signal ofence->base */
+	err = dma_fence_add_callback(fence, &ofence->cb, xe_oa_config_cb);
+	xe_gt_assert(stream->gt, !err || err == -ENOENT);
+	if (err == -ENOENT)
+		xe_oa_config_cb(fence, &ofence->cb);
+
+	/* If nothing needs to be signaled we wait synchronously */
+	if (!num_signal) {
+		dma_fence_wait(&ofence->base, false);
+		dma_fence_put(&ofence->base);
+	}
+
+	/* Done with syncs */
+	for (i = 0; i < stream->num_syncs; i++)
+		xe_sync_entry_cleanup(&stream->syncs[i]);
+	kfree(stream->syncs);
+
+	return 0;
 exit:
+	kfree(ofence);
 	return err;
 }
 
@@ -997,6 +1098,262 @@ static int xe_oa_enable_metric_set(struct xe_oa_stream *stream)
 	return xe_oa_emit_oa_config(stream, stream->oa_config);
 }
 
+static int decode_oa_format(struct xe_oa *oa, u64 fmt, enum xe_oa_format_name *name)
+{
+	u32 counter_size = FIELD_GET(DRM_XE_OA_FORMAT_MASK_COUNTER_SIZE, fmt);
+	u32 counter_sel = FIELD_GET(DRM_XE_OA_FORMAT_MASK_COUNTER_SEL, fmt);
+	u32 bc_report = FIELD_GET(DRM_XE_OA_FORMAT_MASK_BC_REPORT, fmt);
+	u32 type = FIELD_GET(DRM_XE_OA_FORMAT_MASK_FMT_TYPE, fmt);
+	int idx;
+
+	for_each_set_bit(idx, oa->format_mask, __XE_OA_FORMAT_MAX) {
+		const struct xe_oa_format *f = &oa->oa_formats[idx];
+
+		if (counter_size == f->counter_size && bc_report == f->bc_report &&
+		    type == f->type && counter_sel == f->counter_select) {
+			*name = idx;
+			return 0;
+		}
+	}
+
+	return -EINVAL;
+}
+
+static int xe_oa_set_prop_oa_unit_id(struct xe_oa *oa, u64 value,
+				     struct xe_oa_open_param *param)
+{
+	if (value >= oa->oa_unit_ids) {
+		drm_dbg(&oa->xe->drm, "OA unit ID out of range %lld\n", value);
+		return -EINVAL;
+	}
+	param->oa_unit_id = value;
+	return 0;
+}
+
+static int xe_oa_set_prop_sample_oa(struct xe_oa *oa, u64 value,
+				    struct xe_oa_open_param *param)
+{
+	param->sample = value;
+	return 0;
+}
+
+static int xe_oa_set_prop_metric_set(struct xe_oa *oa, u64 value,
+				     struct xe_oa_open_param *param)
+{
+	param->metric_set = value;
+	return 0;
+}
+
+static int xe_oa_set_prop_oa_format(struct xe_oa *oa, u64 value,
+				    struct xe_oa_open_param *param)
+{
+	int ret = decode_oa_format(oa, value, &param->oa_format);
+
+	if (ret) {
+		drm_dbg(&oa->xe->drm, "Unsupported OA report format %#llx\n", value);
+		return ret;
+	}
+	return 0;
+}
+
+static int xe_oa_set_prop_oa_exponent(struct xe_oa *oa, u64 value,
+				      struct xe_oa_open_param *param)
+{
+#define OA_EXPONENT_MAX 31
+
+	if (value > OA_EXPONENT_MAX) {
+		drm_dbg(&oa->xe->drm, "OA timer exponent too high (> %u)\n", OA_EXPONENT_MAX);
+		return -EINVAL;
+	}
+	param->period_exponent = value;
+	return 0;
+}
+
+static int xe_oa_set_prop_disabled(struct xe_oa *oa, u64 value,
+				   struct xe_oa_open_param *param)
+{
+	param->disabled = value;
+	return 0;
+}
+
+static int xe_oa_set_prop_exec_queue_id(struct xe_oa *oa, u64 value,
+					struct xe_oa_open_param *param)
+{
+	param->exec_queue_id = value;
+	return 0;
+}
+
+static int xe_oa_set_prop_engine_instance(struct xe_oa *oa, u64 value,
+					  struct xe_oa_open_param *param)
+{
+	param->engine_instance = value;
+	return 0;
+}
+
+static int xe_oa_set_no_preempt(struct xe_oa *oa, u64 value,
+				struct xe_oa_open_param *param)
+{
+	param->no_preempt = value;
+	return 0;
+}
+
+static int xe_oa_set_prop_num_syncs(struct xe_oa *oa, u64 value,
+				    struct xe_oa_open_param *param)
+{
+	param->num_syncs = value;
+	return 0;
+}
+
+static int xe_oa_set_prop_syncs_user(struct xe_oa *oa, u64 value,
+				     struct xe_oa_open_param *param)
+{
+	param->syncs_user = u64_to_user_ptr(value);
+	return 0;
+}
+
+static int xe_oa_set_prop_ret_inval(struct xe_oa *oa, u64 value,
+				    struct xe_oa_open_param *param)
+{
+	return -EINVAL;
+}
+
+typedef int (*xe_oa_set_property_fn)(struct xe_oa *oa, u64 value,
+				     struct xe_oa_open_param *param);
+static const xe_oa_set_property_fn xe_oa_set_property_funcs_open[] = {
+	[DRM_XE_OA_PROPERTY_OA_UNIT_ID] = xe_oa_set_prop_oa_unit_id,
+	[DRM_XE_OA_PROPERTY_SAMPLE_OA] = xe_oa_set_prop_sample_oa,
+	[DRM_XE_OA_PROPERTY_OA_METRIC_SET] = xe_oa_set_prop_metric_set,
+	[DRM_XE_OA_PROPERTY_OA_FORMAT] = xe_oa_set_prop_oa_format,
+	[DRM_XE_OA_PROPERTY_OA_PERIOD_EXPONENT] = xe_oa_set_prop_oa_exponent,
+	[DRM_XE_OA_PROPERTY_OA_DISABLED] = xe_oa_set_prop_disabled,
+	[DRM_XE_OA_PROPERTY_EXEC_QUEUE_ID] = xe_oa_set_prop_exec_queue_id,
+	[DRM_XE_OA_PROPERTY_OA_ENGINE_INSTANCE] = xe_oa_set_prop_engine_instance,
+	[DRM_XE_OA_PROPERTY_NO_PREEMPT] = xe_oa_set_no_preempt,
+	[DRM_XE_OA_PROPERTY_NUM_SYNCS] = xe_oa_set_prop_num_syncs,
+	[DRM_XE_OA_PROPERTY_SYNCS] = xe_oa_set_prop_syncs_user,
+};
+
+static const xe_oa_set_property_fn xe_oa_set_property_funcs_config[] = {
+	[DRM_XE_OA_PROPERTY_OA_UNIT_ID] = xe_oa_set_prop_ret_inval,
+	[DRM_XE_OA_PROPERTY_SAMPLE_OA] = xe_oa_set_prop_ret_inval,
+	[DRM_XE_OA_PROPERTY_OA_METRIC_SET] = xe_oa_set_prop_metric_set,
+	[DRM_XE_OA_PROPERTY_OA_FORMAT] = xe_oa_set_prop_ret_inval,
+	[DRM_XE_OA_PROPERTY_OA_PERIOD_EXPONENT] = xe_oa_set_prop_ret_inval,
+	[DRM_XE_OA_PROPERTY_OA_DISABLED] = xe_oa_set_prop_ret_inval,
+	[DRM_XE_OA_PROPERTY_EXEC_QUEUE_ID] = xe_oa_set_prop_ret_inval,
+	[DRM_XE_OA_PROPERTY_OA_ENGINE_INSTANCE] = xe_oa_set_prop_ret_inval,
+	[DRM_XE_OA_PROPERTY_NO_PREEMPT] = xe_oa_set_prop_ret_inval,
+	[DRM_XE_OA_PROPERTY_NUM_SYNCS] = xe_oa_set_prop_num_syncs,
+	[DRM_XE_OA_PROPERTY_SYNCS] = xe_oa_set_prop_syncs_user,
+};
+
+static int xe_oa_user_ext_set_property(struct xe_oa *oa, enum xe_oa_user_extn_from from,
+				       u64 extension, struct xe_oa_open_param *param)
+{
+	u64 __user *address = u64_to_user_ptr(extension);
+	struct drm_xe_ext_set_property ext;
+	int err;
+	u32 idx;
+
+	err = __copy_from_user(&ext, address, sizeof(ext));
+	if (XE_IOCTL_DBG(oa->xe, err))
+		return -EFAULT;
+
+	BUILD_BUG_ON(ARRAY_SIZE(xe_oa_set_property_funcs_open) !=
+		     ARRAY_SIZE(xe_oa_set_property_funcs_config));
+
+	if (XE_IOCTL_DBG(oa->xe, ext.property >= ARRAY_SIZE(xe_oa_set_property_funcs_open)) ||
+	    XE_IOCTL_DBG(oa->xe, ext.pad))
+		return -EINVAL;
+
+	idx = array_index_nospec(ext.property, ARRAY_SIZE(xe_oa_set_property_funcs_open));
+
+	if (from == XE_OA_USER_EXTN_FROM_CONFIG)
+		return xe_oa_set_property_funcs_config[idx](oa, ext.value, param);
+	else
+		return xe_oa_set_property_funcs_open[idx](oa, ext.value, param);
+}
+
+typedef int (*xe_oa_user_extension_fn)(struct xe_oa *oa,  enum xe_oa_user_extn_from from,
+				       u64 extension, struct xe_oa_open_param *param);
+static const xe_oa_user_extension_fn xe_oa_user_extension_funcs[] = {
+	[DRM_XE_OA_EXTENSION_SET_PROPERTY] = xe_oa_user_ext_set_property,
+};
+
+#define MAX_USER_EXTENSIONS	16
+static int xe_oa_user_extensions(struct xe_oa *oa, enum xe_oa_user_extn_from from, u64 extension,
+				 int ext_number, struct xe_oa_open_param *param)
+{
+	u64 __user *address = u64_to_user_ptr(extension);
+	struct drm_xe_user_extension ext;
+	int err;
+	u32 idx;
+
+	if (XE_IOCTL_DBG(oa->xe, ext_number >= MAX_USER_EXTENSIONS))
+		return -E2BIG;
+
+	err = __copy_from_user(&ext, address, sizeof(ext));
+	if (XE_IOCTL_DBG(oa->xe, err))
+		return -EFAULT;
+
+	if (XE_IOCTL_DBG(oa->xe, ext.pad) ||
+	    XE_IOCTL_DBG(oa->xe, ext.name >= ARRAY_SIZE(xe_oa_user_extension_funcs)))
+		return -EINVAL;
+
+	idx = array_index_nospec(ext.name, ARRAY_SIZE(xe_oa_user_extension_funcs));
+	err = xe_oa_user_extension_funcs[idx](oa, from, extension, param);
+	if (XE_IOCTL_DBG(oa->xe, err))
+		return err;
+
+	if (ext.next_extension)
+		return xe_oa_user_extensions(oa, from, ext.next_extension, ++ext_number, param);
+
+	return 0;
+}
+
+static int xe_oa_parse_syncs(struct xe_oa *oa, struct xe_oa_open_param *param)
+{
+	int ret, num_syncs, num_ufence = 0;
+
+	if (param->num_syncs && !param->syncs_user) {
+		drm_dbg(&oa->xe->drm, "num_syncs specified without sync array\n");
+		ret = -EINVAL;
+		goto exit;
+	}
+
+	if (param->num_syncs) {
+		param->syncs = kcalloc(param->num_syncs, sizeof(*param->syncs), GFP_KERNEL);
+		if (!param->syncs) {
+			ret = -ENOMEM;
+			goto exit;
+		}
+	}
+
+	for (num_syncs = 0; num_syncs < param->num_syncs; num_syncs++) {
+		ret = xe_sync_entry_parse(oa->xe, param->xef, &param->syncs[num_syncs],
+					  &param->syncs_user[num_syncs], 0);
+		if (ret)
+			goto err_syncs;
+
+		if (xe_sync_is_ufence(&param->syncs[num_syncs]))
+			num_ufence++;
+	}
+
+	if (XE_IOCTL_DBG(oa->xe, num_ufence > 1)) {
+		ret = -EINVAL;
+		goto err_syncs;
+	}
+
+	return 0;
+
+err_syncs:
+	while (num_syncs--)
+		xe_sync_entry_cleanup(&param->syncs[num_syncs]);
+	kfree(param->syncs);
+exit:
+	return ret;
+}
+
 static void xe_oa_stream_enable(struct xe_oa_stream *stream)
 {
 	stream->pollin = false;
@@ -1090,36 +1447,38 @@ static int xe_oa_disable_locked(struct xe_oa_stream *stream)
 
 static long xe_oa_config_locked(struct xe_oa_stream *stream, u64 arg)
 {
-	struct drm_xe_ext_set_property ext;
+	struct xe_oa_open_param param = {};
 	long ret = stream->oa_config->id;
 	struct xe_oa_config *config;
 	int err;
 
-	err = __copy_from_user(&ext, u64_to_user_ptr(arg), sizeof(ext));
-	if (XE_IOCTL_DBG(stream->oa->xe, err))
-		return -EFAULT;
-
-	if (XE_IOCTL_DBG(stream->oa->xe, ext.pad) ||
-	    XE_IOCTL_DBG(stream->oa->xe, ext.base.name != DRM_XE_OA_EXTENSION_SET_PROPERTY) ||
-	    XE_IOCTL_DBG(stream->oa->xe, ext.base.next_extension) ||
-	    XE_IOCTL_DBG(stream->oa->xe, ext.property != DRM_XE_OA_PROPERTY_OA_METRIC_SET))
-		return -EINVAL;
+	err = xe_oa_user_extensions(stream->oa, XE_OA_USER_EXTN_FROM_CONFIG, arg, 0, &param);
+	if (err)
+		return err;
 
-	config = xe_oa_get_oa_config(stream->oa, ext.value);
+	config = xe_oa_get_oa_config(stream->oa, param.metric_set);
 	if (!config)
 		return -ENODEV;
 
-	if (config != stream->oa_config) {
-		err = xe_oa_emit_oa_config(stream, config);
-		if (!err)
-			config = xchg(&stream->oa_config, config);
-		else
-			ret = err;
+	param.xef = stream->xef;
+	err = xe_oa_parse_syncs(stream->oa, &param);
+	if (err)
+		goto err_config_put;
+
+	stream->num_syncs = param.num_syncs;
+	stream->syncs = param.syncs;
+
+	err = xe_oa_emit_oa_config(stream, config);
+	if (!err) {
+		config = xchg(&stream->oa_config, config);
+		drm_dbg(&stream->oa->xe->drm, "changed to oa config uuid=%s\n",
+			stream->oa_config->uuid);
 	}
 
+err_config_put:
 	xe_oa_config_put(config);
 
-	return ret;
+	return err ?: ret;
 }
 
 static long xe_oa_status_locked(struct xe_oa_stream *stream, unsigned long arg)
@@ -1358,10 +1717,14 @@ static int xe_oa_stream_init(struct xe_oa_stream *stream,
 	stream->oa_buffer.format = &stream->oa->oa_formats[param->oa_format];
 
 	stream->sample = param->sample;
-	stream->periodic = param->period_exponent > 0;
+	stream->periodic = param->period_exponent >= 0;
 	stream->period_exponent = param->period_exponent;
 	stream->no_preempt = param->no_preempt;
 
+	stream->xef = xe_file_get(param->xef);
+	stream->num_syncs = param->num_syncs;
+	stream->syncs = param->syncs;
+
 	/*
 	 * For Xe2+, when overrun mode is enabled, there are no partial reports at the end
 	 * of buffer, making the OA buffer effectively a non-power-of-2 size circular
@@ -1458,6 +1821,7 @@ err_fw_put:
 err_free_configs:
 	xe_oa_free_configs(stream);
 exit:
+	xe_file_put(stream->xef);
 	return ret;
 }
 
@@ -1567,27 +1931,6 @@ static bool engine_supports_oa_format(const struct xe_hw_engine *hwe, int type)
 	}
 }
 
-static int decode_oa_format(struct xe_oa *oa, u64 fmt, enum xe_oa_format_name *name)
-{
-	u32 counter_size = FIELD_GET(DRM_XE_OA_FORMAT_MASK_COUNTER_SIZE, fmt);
-	u32 counter_sel = FIELD_GET(DRM_XE_OA_FORMAT_MASK_COUNTER_SEL, fmt);
-	u32 bc_report = FIELD_GET(DRM_XE_OA_FORMAT_MASK_BC_REPORT, fmt);
-	u32 type = FIELD_GET(DRM_XE_OA_FORMAT_MASK_FMT_TYPE, fmt);
-	int idx;
-
-	for_each_set_bit(idx, oa->format_mask, __XE_OA_FORMAT_MAX) {
-		const struct xe_oa_format *f = &oa->oa_formats[idx];
-
-		if (counter_size == f->counter_size && bc_report == f->bc_report &&
-		    type == f->type && counter_sel == f->counter_select) {
-			*name = idx;
-			return 0;
-		}
-	}
-
-	return -EINVAL;
-}
-
 /**
  * xe_oa_unit_id - Return OA unit ID for a hardware engine
  * @hwe: @xe_hw_engine
@@ -1634,155 +1977,6 @@ out:
 	return ret;
 }
 
-static int xe_oa_set_prop_oa_unit_id(struct xe_oa *oa, u64 value,
-				     struct xe_oa_open_param *param)
-{
-	if (value >= oa->oa_unit_ids) {
-		drm_dbg(&oa->xe->drm, "OA unit ID out of range %lld\n", value);
-		return -EINVAL;
-	}
-	param->oa_unit_id = value;
-	return 0;
-}
-
-static int xe_oa_set_prop_sample_oa(struct xe_oa *oa, u64 value,
-				    struct xe_oa_open_param *param)
-{
-	param->sample = value;
-	return 0;
-}
-
-static int xe_oa_set_prop_metric_set(struct xe_oa *oa, u64 value,
-				     struct xe_oa_open_param *param)
-{
-	param->metric_set = value;
-	return 0;
-}
-
-static int xe_oa_set_prop_oa_format(struct xe_oa *oa, u64 value,
-				    struct xe_oa_open_param *param)
-{
-	int ret = decode_oa_format(oa, value, &param->oa_format);
-
-	if (ret) {
-		drm_dbg(&oa->xe->drm, "Unsupported OA report format %#llx\n", value);
-		return ret;
-	}
-	return 0;
-}
-
-static int xe_oa_set_prop_oa_exponent(struct xe_oa *oa, u64 value,
-				      struct xe_oa_open_param *param)
-{
-#define OA_EXPONENT_MAX 31
-
-	if (value > OA_EXPONENT_MAX) {
-		drm_dbg(&oa->xe->drm, "OA timer exponent too high (> %u)\n", OA_EXPONENT_MAX);
-		return -EINVAL;
-	}
-	param->period_exponent = value;
-	return 0;
-}
-
-static int xe_oa_set_prop_disabled(struct xe_oa *oa, u64 value,
-				   struct xe_oa_open_param *param)
-{
-	param->disabled = value;
-	return 0;
-}
-
-static int xe_oa_set_prop_exec_queue_id(struct xe_oa *oa, u64 value,
-					struct xe_oa_open_param *param)
-{
-	param->exec_queue_id = value;
-	return 0;
-}
-
-static int xe_oa_set_prop_engine_instance(struct xe_oa *oa, u64 value,
-					  struct xe_oa_open_param *param)
-{
-	param->engine_instance = value;
-	return 0;
-}
-
-static int xe_oa_set_no_preempt(struct xe_oa *oa, u64 value,
-				struct xe_oa_open_param *param)
-{
-	param->no_preempt = value;
-	return 0;
-}
-
-typedef int (*xe_oa_set_property_fn)(struct xe_oa *oa, u64 value,
-				     struct xe_oa_open_param *param);
-static const xe_oa_set_property_fn xe_oa_set_property_funcs[] = {
-	[DRM_XE_OA_PROPERTY_OA_UNIT_ID] = xe_oa_set_prop_oa_unit_id,
-	[DRM_XE_OA_PROPERTY_SAMPLE_OA] = xe_oa_set_prop_sample_oa,
-	[DRM_XE_OA_PROPERTY_OA_METRIC_SET] = xe_oa_set_prop_metric_set,
-	[DRM_XE_OA_PROPERTY_OA_FORMAT] = xe_oa_set_prop_oa_format,
-	[DRM_XE_OA_PROPERTY_OA_PERIOD_EXPONENT] = xe_oa_set_prop_oa_exponent,
-	[DRM_XE_OA_PROPERTY_OA_DISABLED] = xe_oa_set_prop_disabled,
-	[DRM_XE_OA_PROPERTY_EXEC_QUEUE_ID] = xe_oa_set_prop_exec_queue_id,
-	[DRM_XE_OA_PROPERTY_OA_ENGINE_INSTANCE] = xe_oa_set_prop_engine_instance,
-	[DRM_XE_OA_PROPERTY_NO_PREEMPT] = xe_oa_set_no_preempt,
-};
-
-static int xe_oa_user_ext_set_property(struct xe_oa *oa, u64 extension,
-				       struct xe_oa_open_param *param)
-{
-	u64 __user *address = u64_to_user_ptr(extension);
-	struct drm_xe_ext_set_property ext;
-	int err;
-	u32 idx;
-
-	err = __copy_from_user(&ext, address, sizeof(ext));
-	if (XE_IOCTL_DBG(oa->xe, err))
-		return -EFAULT;
-
-	if (XE_IOCTL_DBG(oa->xe, ext.property >= ARRAY_SIZE(xe_oa_set_property_funcs)) ||
-	    XE_IOCTL_DBG(oa->xe, ext.pad))
-		return -EINVAL;
-
-	idx = array_index_nospec(ext.property, ARRAY_SIZE(xe_oa_set_property_funcs));
-	return xe_oa_set_property_funcs[idx](oa, ext.value, param);
-}
-
-typedef int (*xe_oa_user_extension_fn)(struct xe_oa *oa, u64 extension,
-				       struct xe_oa_open_param *param);
-static const xe_oa_user_extension_fn xe_oa_user_extension_funcs[] = {
-	[DRM_XE_OA_EXTENSION_SET_PROPERTY] = xe_oa_user_ext_set_property,
-};
-
-#define MAX_USER_EXTENSIONS	16
-static int xe_oa_user_extensions(struct xe_oa *oa, u64 extension, int ext_number,
-				 struct xe_oa_open_param *param)
-{
-	u64 __user *address = u64_to_user_ptr(extension);
-	struct drm_xe_user_extension ext;
-	int err;
-	u32 idx;
-
-	if (XE_IOCTL_DBG(oa->xe, ext_number >= MAX_USER_EXTENSIONS))
-		return -E2BIG;
-
-	err = __copy_from_user(&ext, address, sizeof(ext));
-	if (XE_IOCTL_DBG(oa->xe, err))
-		return -EFAULT;
-
-	if (XE_IOCTL_DBG(oa->xe, ext.pad) ||
-	    XE_IOCTL_DBG(oa->xe, ext.name >= ARRAY_SIZE(xe_oa_user_extension_funcs)))
-		return -EINVAL;
-
-	idx = array_index_nospec(ext.name, ARRAY_SIZE(xe_oa_user_extension_funcs));
-	err = xe_oa_user_extension_funcs[idx](oa, extension, param);
-	if (XE_IOCTL_DBG(oa->xe, err))
-		return err;
-
-	if (ext.next_extension)
-		return xe_oa_user_extensions(oa, ext.next_extension, ++ext_number, param);
-
-	return 0;
-}
-
 /**
  * xe_oa_stream_open_ioctl - Opens an OA stream
  * @dev: @drm_device
@@ -1808,7 +2002,9 @@ int xe_oa_stream_open_ioctl(struct drm_device *dev, u64 data, struct drm_file *f
 		return -ENODEV;
 	}
 
-	ret = xe_oa_user_extensions(oa, data, 0, &param);
+	param.xef = xef;
+	param.period_exponent = -1;
+	ret = xe_oa_user_extensions(oa, XE_OA_USER_EXTN_FROM_OPEN, data, 0, &param);
 	if (ret)
 		return ret;
 
@@ -1817,8 +2013,8 @@ int xe_oa_stream_open_ioctl(struct drm_device *dev, u64 data, struct drm_file *f
 		if (XE_IOCTL_DBG(oa->xe, !param.exec_q))
 			return -ENOENT;
 
-		if (param.exec_q->width > 1)
-			drm_dbg(&oa->xe->drm, "exec_q->width > 1, programming only exec_q->lrc[0]\n");
+		if (XE_IOCTL_DBG(oa->xe, param.exec_q->width > 1))
+			return -EOPNOTSUPP;
 	}
 
 	/*
@@ -1862,7 +2058,7 @@ int xe_oa_stream_open_ioctl(struct drm_device *dev, u64 data, struct drm_file *f
 		goto err_exec_q;
 	}
 
-	if (param.period_exponent > 0) {
+	if (param.period_exponent >= 0) {
 		u64 oa_period, oa_freq_hz;
 
 		/* Requesting samples from OAG buffer is a privileged operation */
@@ -1876,11 +2072,24 @@ int xe_oa_stream_open_ioctl(struct drm_device *dev, u64 data, struct drm_file *f
 		drm_dbg(&oa->xe->drm, "Using periodic sampling freq %lld Hz\n", oa_freq_hz);
 	}
 
+	ret = xe_oa_parse_syncs(oa, &param);
+	if (ret)
+		goto err_exec_q;
+
 	mutex_lock(&param.hwe->gt->oa.gt_lock);
 	ret = xe_oa_stream_open_ioctl_locked(oa, &param);
 	mutex_unlock(&param.hwe->gt->oa.gt_lock);
+	if (ret < 0)
+		goto err_sync_cleanup;
+
+	return ret;
+
+err_sync_cleanup:
+	while (param.num_syncs--)
+		xe_sync_entry_cleanup(&param.syncs[param.num_syncs]);
+	kfree(param.syncs);
 err_exec_q:
-	if (ret < 0 && param.exec_q)
+	if (param.exec_q)
 		xe_exec_queue_put(param.exec_q);
 	return ret;
 }
diff --git a/drivers/gpu/drm/xe/xe_oa_types.h b/drivers/gpu/drm/xe/xe_oa_types.h
index 8862eca73fbe..fea9d981e414 100644
--- a/drivers/gpu/drm/xe/xe_oa_types.h
+++ b/drivers/gpu/drm/xe/xe_oa_types.h
@@ -238,5 +238,17 @@ struct xe_oa_stream {
 
 	/** @no_preempt: Whether preemption and timeslicing is disabled for stream exec_q */
 	u32 no_preempt;
+
+	/** @xef: xe_file with which the stream was opened */
+	struct xe_file *xef;
+
+	/** @last_fence: fence to use in stream destroy when needed */
+	struct dma_fence *last_fence;
+
+	/** @num_syncs: size of @syncs array */
+	u32 num_syncs;
+
+	/** @syncs: syncs to wait on and to signal */
+	struct xe_sync_entry *syncs;
 };
 #endif
diff --git a/drivers/gpu/drm/xe/xe_pci.c b/drivers/gpu/drm/xe/xe_pci.c
index 025d64943467..da09c26249f5 100644
--- a/drivers/gpu/drm/xe/xe_pci.c
+++ b/drivers/gpu/drm/xe/xe_pci.c
@@ -164,7 +164,6 @@ static const struct xe_graphics_desc graphics_xelpg = {
 	.has_asid = 1, \
 	.has_atomic_enable_pte_bit = 1, \
 	.has_flat_ccs = 1, \
-	.has_indirect_ring_state = 1, \
 	.has_range_tlb_invalidation = 1, \
 	.has_usm = 1, \
 	.va_bits = 48, \
@@ -910,6 +909,7 @@ static int xe_pci_suspend(struct device *dev)
 
 	pci_save_state(pdev);
 	pci_disable_device(pdev);
+	pci_set_power_state(pdev, PCI_D3cold);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/xe/xe_pci_sriov.c b/drivers/gpu/drm/xe/xe_pci_sriov.c
index aaceee748287..09ee8a06fe2e 100644
--- a/drivers/gpu/drm/xe/xe_pci_sriov.c
+++ b/drivers/gpu/drm/xe/xe_pci_sriov.c
@@ -62,6 +62,55 @@ static void pf_reset_vfs(struct xe_device *xe, unsigned int num_vfs)
 			xe_gt_sriov_pf_control_trigger_flr(gt, n);
 }
 
+static struct pci_dev *xe_pci_pf_get_vf_dev(struct xe_device *xe, unsigned int vf_id)
+{
+	struct pci_dev *pdev = to_pci_dev(xe->drm.dev);
+
+	xe_assert(xe, IS_SRIOV_PF(xe));
+
+	/* caller must use pci_dev_put() */
+	return pci_get_domain_bus_and_slot(pci_domain_nr(pdev->bus),
+			pdev->bus->number,
+			pci_iov_virtfn_devfn(pdev, vf_id));
+}
+
+static void pf_link_vfs(struct xe_device *xe, int num_vfs)
+{
+	struct pci_dev *pdev_pf = to_pci_dev(xe->drm.dev);
+	struct device_link *link;
+	struct pci_dev *pdev_vf;
+	unsigned int n;
+
+	/*
+	 * When both PF and VF devices are enabled on the host, during system
+	 * resume they are resuming in parallel.
+	 *
+	 * But PF has to complete the provision of VF first to allow any VFs to
+	 * successfully resume.
+	 *
+	 * Create a parent-child device link between PF and VF devices that will
+	 * enforce correct resume order.
+	 */
+	for (n = 1; n <= num_vfs; n++) {
+		pdev_vf = xe_pci_pf_get_vf_dev(xe, n - 1);
+
+		/* unlikely, something weird is happening, abort */
+		if (!pdev_vf) {
+			xe_sriov_err(xe, "Cannot find VF%u device, aborting link%s creation!\n",
+				     n, str_plural(num_vfs));
+			break;
+		}
+
+		link = device_link_add(&pdev_vf->dev, &pdev_pf->dev,
+				       DL_FLAG_AUTOREMOVE_CONSUMER);
+		/* unlikely and harmless, continue with other VFs */
+		if (!link)
+			xe_sriov_notice(xe, "Failed linking VF%u\n", n);
+
+		pci_dev_put(pdev_vf);
+	}
+}
+
 static int pf_enable_vfs(struct xe_device *xe, int num_vfs)
 {
 	struct pci_dev *pdev = to_pci_dev(xe->drm.dev);
@@ -92,6 +141,8 @@ static int pf_enable_vfs(struct xe_device *xe, int num_vfs)
 	if (err < 0)
 		goto failed;
 
+	pf_link_vfs(xe, num_vfs);
+
 	xe_sriov_info(xe, "Enabled %u of %u VF%s\n",
 		      num_vfs, total_vfs, str_plural(total_vfs));
 	return num_vfs;
diff --git a/drivers/gpu/drm/xe/xe_pm.c b/drivers/gpu/drm/xe/xe_pm.c
index 33eb039053e4..46c73ff10c74 100644
--- a/drivers/gpu/drm/xe/xe_pm.c
+++ b/drivers/gpu/drm/xe/xe_pm.c
@@ -264,6 +264,15 @@ int xe_pm_init_early(struct xe_device *xe)
 	return 0;
 }
 
+static u32 vram_threshold_value(struct xe_device *xe)
+{
+	/* FIXME: D3Cold temporarily disabled by default on BMG */
+	if (xe->info.platform == XE_BATTLEMAGE)
+		return 0;
+
+	return DEFAULT_VRAM_THRESHOLD;
+}
+
 /**
  * xe_pm_init - Initialize Xe Power Management
  * @xe: xe device instance
@@ -274,6 +283,7 @@ int xe_pm_init_early(struct xe_device *xe)
  */
 int xe_pm_init(struct xe_device *xe)
 {
+	u32 vram_threshold;
 	int err;
 
 	/* For now suspend/resume is only allowed with GuC */
@@ -287,7 +297,8 @@ int xe_pm_init(struct xe_device *xe)
 		if (err)
 			return err;
 
-		err = xe_pm_set_vram_threshold(xe, DEFAULT_VRAM_THRESHOLD);
+		vram_threshold = vram_threshold_value(xe);
+		err = xe_pm_set_vram_threshold(xe, vram_threshold);
 		if (err)
 			return err;
 	}
@@ -671,11 +682,13 @@ void xe_pm_assert_unbounded_bridge(struct xe_device *xe)
 }
 
 /**
- * xe_pm_set_vram_threshold - Set a vram threshold for allowing/blocking D3Cold
+ * xe_pm_set_vram_threshold - Set a VRAM threshold for allowing/blocking D3Cold
  * @xe: xe device instance
- * @threshold: VRAM size in bites for the D3cold threshold
+ * @threshold: VRAM size in MiB for the D3cold threshold
  *
- * Returns 0 for success, negative error code otherwise.
+ * Return:
+ * * 0		- success
+ * * -EINVAL	- invalid argument
  */
 int xe_pm_set_vram_threshold(struct xe_device *xe, u32 threshold)
 {
diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c
index 797576690356..fb94ff55c736 100644
--- a/drivers/gpu/drm/xe/xe_pt.c
+++ b/drivers/gpu/drm/xe/xe_pt.c
@@ -28,6 +28,8 @@ struct xe_pt_dir {
 	struct xe_pt pt;
 	/** @children: Array of page-table child nodes */
 	struct xe_ptw *children[XE_PDES];
+	/** @staging: Array of page-table staging nodes */
+	struct xe_ptw *staging[XE_PDES];
 };
 
 #if IS_ENABLED(CONFIG_DRM_XE_DEBUG_VM)
@@ -48,9 +50,10 @@ static struct xe_pt_dir *as_xe_pt_dir(struct xe_pt *pt)
 	return container_of(pt, struct xe_pt_dir, pt);
 }
 
-static struct xe_pt *xe_pt_entry(struct xe_pt_dir *pt_dir, unsigned int index)
+static struct xe_pt *
+xe_pt_entry_staging(struct xe_pt_dir *pt_dir, unsigned int index)
 {
-	return container_of(pt_dir->children[index], struct xe_pt, base);
+	return container_of(pt_dir->staging[index], struct xe_pt, base);
 }
 
 static u64 __xe_pt_empty_pte(struct xe_tile *tile, struct xe_vm *vm,
@@ -125,6 +128,7 @@ struct xe_pt *xe_pt_create(struct xe_vm *vm, struct xe_tile *tile,
 	}
 	pt->bo = bo;
 	pt->base.children = level ? as_xe_pt_dir(pt)->children : NULL;
+	pt->base.staging = level ? as_xe_pt_dir(pt)->staging : NULL;
 
 	if (vm->xef)
 		xe_drm_client_add_bo(vm->xef->client, pt->bo);
@@ -205,8 +209,8 @@ void xe_pt_destroy(struct xe_pt *pt, u32 flags, struct llist_head *deferred)
 		struct xe_pt_dir *pt_dir = as_xe_pt_dir(pt);
 
 		for (i = 0; i < XE_PDES; i++) {
-			if (xe_pt_entry(pt_dir, i))
-				xe_pt_destroy(xe_pt_entry(pt_dir, i), flags,
+			if (xe_pt_entry_staging(pt_dir, i))
+				xe_pt_destroy(xe_pt_entry_staging(pt_dir, i), flags,
 					      deferred);
 		}
 	}
@@ -214,6 +218,20 @@ void xe_pt_destroy(struct xe_pt *pt, u32 flags, struct llist_head *deferred)
 }
 
 /**
+ * xe_pt_clear() - Clear a page-table.
+ * @xe: xe device.
+ * @pt: The page-table.
+ *
+ * Clears page-table by setting to zero.
+ */
+void xe_pt_clear(struct xe_device *xe, struct xe_pt *pt)
+{
+	struct iosys_map *map = &pt->bo->vmap;
+
+	xe_map_memset(xe, map, 0, 0, SZ_4K);
+}
+
+/**
  * DOC: Pagetable building
  *
  * Below we use the term "page-table" for both page-directories, containing
@@ -375,8 +393,10 @@ xe_pt_insert_entry(struct xe_pt_stage_bind_walk *xe_walk, struct xe_pt *parent,
 		/* Continue building a non-connected subtree. */
 		struct iosys_map *map = &parent->bo->vmap;
 
-		if (unlikely(xe_child))
+		if (unlikely(xe_child)) {
 			parent->base.children[offset] = &xe_child->base;
+			parent->base.staging[offset] = &xe_child->base;
+		}
 
 		xe_pt_write(xe_walk->vm->xe, map, offset, pte);
 		parent->num_live++;
@@ -613,6 +633,7 @@ xe_pt_stage_bind(struct xe_tile *tile, struct xe_vma *vma,
 			.ops = &xe_pt_stage_bind_ops,
 			.shifts = xe_normal_pt_shifts,
 			.max_level = XE_PT_HIGHEST_LEVEL,
+			.staging = true,
 		},
 		.vm = xe_vma_vm(vma),
 		.tile = tile,
@@ -872,7 +893,7 @@ static void xe_pt_cancel_bind(struct xe_vma *vma,
 	}
 }
 
-static void xe_pt_commit_locks_assert(struct xe_vma *vma)
+static void xe_pt_commit_prepare_locks_assert(struct xe_vma *vma)
 {
 	struct xe_vm *vm = xe_vma_vm(vma);
 
@@ -884,6 +905,16 @@ static void xe_pt_commit_locks_assert(struct xe_vma *vma)
 	xe_vm_assert_held(vm);
 }
 
+static void xe_pt_commit_locks_assert(struct xe_vma *vma)
+{
+	struct xe_vm *vm = xe_vma_vm(vma);
+
+	xe_pt_commit_prepare_locks_assert(vma);
+
+	if (xe_vma_is_userptr(vma))
+		lockdep_assert_held_read(&vm->userptr.notifier_lock);
+}
+
 static void xe_pt_commit(struct xe_vma *vma,
 			 struct xe_vm_pgtable_update *entries,
 			 u32 num_entries, struct llist_head *deferred)
@@ -894,13 +925,17 @@ static void xe_pt_commit(struct xe_vma *vma,
 
 	for (i = 0; i < num_entries; i++) {
 		struct xe_pt *pt = entries[i].pt;
+		struct xe_pt_dir *pt_dir;
 
 		if (!pt->level)
 			continue;
 
+		pt_dir = as_xe_pt_dir(pt);
 		for (j = 0; j < entries[i].qwords; j++) {
 			struct xe_pt *oldpte = entries[i].pt_entries[j].pt;
+			int j_ = j + entries[i].ofs;
 
+			pt_dir->children[j_] = pt_dir->staging[j_];
 			xe_pt_destroy(oldpte, xe_vma_vm(vma)->flags, deferred);
 		}
 	}
@@ -912,7 +947,7 @@ static void xe_pt_abort_bind(struct xe_vma *vma,
 {
 	int i, j;
 
-	xe_pt_commit_locks_assert(vma);
+	xe_pt_commit_prepare_locks_assert(vma);
 
 	for (i = num_entries - 1; i >= 0; --i) {
 		struct xe_pt *pt = entries[i].pt;
@@ -927,10 +962,10 @@ static void xe_pt_abort_bind(struct xe_vma *vma,
 		pt_dir = as_xe_pt_dir(pt);
 		for (j = 0; j < entries[i].qwords; j++) {
 			u32 j_ = j + entries[i].ofs;
-			struct xe_pt *newpte = xe_pt_entry(pt_dir, j_);
+			struct xe_pt *newpte = xe_pt_entry_staging(pt_dir, j_);
 			struct xe_pt *oldpte = entries[i].pt_entries[j].pt;
 
-			pt_dir->children[j_] = oldpte ? &oldpte->base : 0;
+			pt_dir->staging[j_] = oldpte ? &oldpte->base : 0;
 			xe_pt_destroy(newpte, xe_vma_vm(vma)->flags, NULL);
 		}
 	}
@@ -942,7 +977,7 @@ static void xe_pt_commit_prepare_bind(struct xe_vma *vma,
 {
 	u32 i, j;
 
-	xe_pt_commit_locks_assert(vma);
+	xe_pt_commit_prepare_locks_assert(vma);
 
 	for (i = 0; i < num_entries; i++) {
 		struct xe_pt *pt = entries[i].pt;
@@ -960,10 +995,10 @@ static void xe_pt_commit_prepare_bind(struct xe_vma *vma,
 			struct xe_pt *newpte = entries[i].pt_entries[j].pt;
 			struct xe_pt *oldpte = NULL;
 
-			if (xe_pt_entry(pt_dir, j_))
-				oldpte = xe_pt_entry(pt_dir, j_);
+			if (xe_pt_entry_staging(pt_dir, j_))
+				oldpte = xe_pt_entry_staging(pt_dir, j_);
 
-			pt_dir->children[j_] = &newpte->base;
+			pt_dir->staging[j_] = &newpte->base;
 			entries[i].pt_entries[j].pt = oldpte;
 		}
 	}
@@ -1212,42 +1247,22 @@ static int vma_check_userptr(struct xe_vm *vm, struct xe_vma *vma,
 		return 0;
 
 	uvma = to_userptr_vma(vma);
-	notifier_seq = uvma->userptr.notifier_seq;
+	if (xe_pt_userptr_inject_eagain(uvma))
+		xe_vma_userptr_force_invalidate(uvma);
 
-	if (uvma->userptr.initial_bind && !xe_vm_in_fault_mode(vm))
-		return 0;
+	notifier_seq = uvma->userptr.notifier_seq;
 
 	if (!mmu_interval_read_retry(&uvma->userptr.notifier,
-				     notifier_seq) &&
-	    !xe_pt_userptr_inject_eagain(uvma))
+				     notifier_seq))
 		return 0;
 
-	if (xe_vm_in_fault_mode(vm)) {
+	if (xe_vm_in_fault_mode(vm))
 		return -EAGAIN;
-	} else {
-		spin_lock(&vm->userptr.invalidated_lock);
-		list_move_tail(&uvma->userptr.invalidate_link,
-			       &vm->userptr.invalidated);
-		spin_unlock(&vm->userptr.invalidated_lock);
-
-		if (xe_vm_in_preempt_fence_mode(vm)) {
-			struct dma_resv_iter cursor;
-			struct dma_fence *fence;
-			long err;
-
-			dma_resv_iter_begin(&cursor, xe_vm_resv(vm),
-					    DMA_RESV_USAGE_BOOKKEEP);
-			dma_resv_for_each_fence_unlocked(&cursor, fence)
-				dma_fence_enable_sw_signaling(fence);
-			dma_resv_iter_end(&cursor);
-
-			err = dma_resv_wait_timeout(xe_vm_resv(vm),
-						    DMA_RESV_USAGE_BOOKKEEP,
-						    false, MAX_SCHEDULE_TIMEOUT);
-			XE_WARN_ON(err <= 0);
-		}
-	}
 
+	/*
+	 * Just continue the operation since exec or rebind worker
+	 * will take care of rebinding.
+	 */
 	return 0;
 }
 
@@ -1513,6 +1528,7 @@ static unsigned int xe_pt_stage_unbind(struct xe_tile *tile, struct xe_vma *vma,
 			.ops = &xe_pt_stage_unbind_ops,
 			.shifts = xe_normal_pt_shifts,
 			.max_level = XE_PT_HIGHEST_LEVEL,
+			.staging = true,
 		},
 		.tile = tile,
 		.modified_start = xe_vma_start(vma),
@@ -1554,7 +1570,7 @@ static void xe_pt_abort_unbind(struct xe_vma *vma,
 {
 	int i, j;
 
-	xe_pt_commit_locks_assert(vma);
+	xe_pt_commit_prepare_locks_assert(vma);
 
 	for (i = num_entries - 1; i >= 0; --i) {
 		struct xe_vm_pgtable_update *entry = &entries[i];
@@ -1567,7 +1583,7 @@ static void xe_pt_abort_unbind(struct xe_vma *vma,
 			continue;
 
 		for (j = entry->ofs; j < entry->ofs + entry->qwords; j++)
-			pt_dir->children[j] =
+			pt_dir->staging[j] =
 				entries[i].pt_entries[j - entry->ofs].pt ?
 				&entries[i].pt_entries[j - entry->ofs].pt->base : NULL;
 	}
@@ -1580,7 +1596,7 @@ xe_pt_commit_prepare_unbind(struct xe_vma *vma,
 {
 	int i, j;
 
-	xe_pt_commit_locks_assert(vma);
+	xe_pt_commit_prepare_locks_assert(vma);
 
 	for (i = 0; i < num_entries; ++i) {
 		struct xe_vm_pgtable_update *entry = &entries[i];
@@ -1594,8 +1610,8 @@ xe_pt_commit_prepare_unbind(struct xe_vma *vma,
 		pt_dir = as_xe_pt_dir(pt);
 		for (j = entry->ofs; j < entry->ofs + entry->qwords; j++) {
 			entry->pt_entries[j - entry->ofs].pt =
-				xe_pt_entry(pt_dir, j);
-			pt_dir->children[j] = NULL;
+				xe_pt_entry_staging(pt_dir, j);
+			pt_dir->staging[j] = NULL;
 		}
 	}
 }
diff --git a/drivers/gpu/drm/xe/xe_pt.h b/drivers/gpu/drm/xe/xe_pt.h
index 9ab386431cad..8e43912ae8e9 100644
--- a/drivers/gpu/drm/xe/xe_pt.h
+++ b/drivers/gpu/drm/xe/xe_pt.h
@@ -13,6 +13,7 @@ struct dma_fence;
 struct xe_bo;
 struct xe_device;
 struct xe_exec_queue;
+struct xe_svm_range;
 struct xe_sync_entry;
 struct xe_tile;
 struct xe_vm;
@@ -35,6 +36,8 @@ void xe_pt_populate_empty(struct xe_tile *tile, struct xe_vm *vm,
 
 void xe_pt_destroy(struct xe_pt *pt, u32 flags, struct llist_head *deferred);
 
+void xe_pt_clear(struct xe_device *xe, struct xe_pt *pt);
+
 int xe_pt_update_ops_prepare(struct xe_tile *tile, struct xe_vma_ops *vops);
 struct dma_fence *xe_pt_update_ops_run(struct xe_tile *tile,
 				       struct xe_vma_ops *vops);
diff --git a/drivers/gpu/drm/xe/xe_pt_walk.c b/drivers/gpu/drm/xe/xe_pt_walk.c
index b8b3d2aea492..be602a763ff3 100644
--- a/drivers/gpu/drm/xe/xe_pt_walk.c
+++ b/drivers/gpu/drm/xe/xe_pt_walk.c
@@ -74,7 +74,8 @@ int xe_pt_walk_range(struct xe_ptw *parent, unsigned int level,
 		     u64 addr, u64 end, struct xe_pt_walk *walk)
 {
 	pgoff_t offset = xe_pt_offset(addr, level, walk);
-	struct xe_ptw **entries = parent->children ? parent->children : NULL;
+	struct xe_ptw **entries = walk->staging ? (parent->staging ?: NULL) :
+		(parent->children ?: NULL);
 	const struct xe_pt_walk_ops *ops = walk->ops;
 	enum page_walk_action action;
 	struct xe_ptw *child;
diff --git a/drivers/gpu/drm/xe/xe_pt_walk.h b/drivers/gpu/drm/xe/xe_pt_walk.h
index 5ecc4d2f0f65..5c02c244f7de 100644
--- a/drivers/gpu/drm/xe/xe_pt_walk.h
+++ b/drivers/gpu/drm/xe/xe_pt_walk.h
@@ -11,12 +11,14 @@
 /**
  * struct xe_ptw - base class for driver pagetable subclassing.
  * @children: Pointer to an array of children if any.
+ * @staging: Pointer to an array of staging if any.
  *
  * Drivers could subclass this, and if it's a page-directory, typically
  * embed an array of xe_ptw pointers.
  */
 struct xe_ptw {
 	struct xe_ptw **children;
+	struct xe_ptw **staging;
 };
 
 /**
@@ -41,6 +43,8 @@ struct xe_pt_walk {
 	 * as shared pagetables.
 	 */
 	bool shared_pt_mode;
+	/** @staging: Walk staging PT structure */
+	bool staging;
 };
 
 /**
diff --git a/drivers/gpu/drm/xe/xe_query.c b/drivers/gpu/drm/xe/xe_query.c
index 1c96375bd7df..6e7c940d7e22 100644
--- a/drivers/gpu/drm/xe/xe_query.c
+++ b/drivers/gpu/drm/xe/xe_query.c
@@ -366,6 +366,7 @@ static int query_gt_list(struct xe_device *xe, struct drm_xe_device_query *query
 	struct drm_xe_query_gt_list __user *query_ptr =
 		u64_to_user_ptr(query->data);
 	struct drm_xe_query_gt_list *gt_list;
+	int iter = 0;
 	u8 id;
 
 	if (query->size == 0) {
@@ -383,12 +384,12 @@ static int query_gt_list(struct xe_device *xe, struct drm_xe_device_query *query
 
 	for_each_gt(gt, xe, id) {
 		if (xe_gt_is_media_type(gt))
-			gt_list->gt_list[id].type = DRM_XE_QUERY_GT_TYPE_MEDIA;
+			gt_list->gt_list[iter].type = DRM_XE_QUERY_GT_TYPE_MEDIA;
 		else
-			gt_list->gt_list[id].type = DRM_XE_QUERY_GT_TYPE_MAIN;
-		gt_list->gt_list[id].tile_id = gt_to_tile(gt)->id;
-		gt_list->gt_list[id].gt_id = gt->info.id;
-		gt_list->gt_list[id].reference_clock = gt->info.reference_clock;
+			gt_list->gt_list[iter].type = DRM_XE_QUERY_GT_TYPE_MAIN;
+		gt_list->gt_list[iter].tile_id = gt_to_tile(gt)->id;
+		gt_list->gt_list[iter].gt_id = gt->info.id;
+		gt_list->gt_list[iter].reference_clock = gt->info.reference_clock;
 		/*
 		 * The mem_regions indexes in the mask below need to
 		 * directly identify the struct
@@ -404,19 +405,21 @@ static int query_gt_list(struct xe_device *xe, struct drm_xe_device_query *query
 		 * assumption.
 		 */
 		if (!IS_DGFX(xe))
-			gt_list->gt_list[id].near_mem_regions = 0x1;
+			gt_list->gt_list[iter].near_mem_regions = 0x1;
 		else
-			gt_list->gt_list[id].near_mem_regions =
+			gt_list->gt_list[iter].near_mem_regions =
 				BIT(gt_to_tile(gt)->id) << 1;
-		gt_list->gt_list[id].far_mem_regions = xe->info.mem_region_mask ^
-			gt_list->gt_list[id].near_mem_regions;
+		gt_list->gt_list[iter].far_mem_regions = xe->info.mem_region_mask ^
+			gt_list->gt_list[iter].near_mem_regions;
 
-		gt_list->gt_list[id].ip_ver_major =
+		gt_list->gt_list[iter].ip_ver_major =
 			REG_FIELD_GET(GMD_ID_ARCH_MASK, gt->info.gmdid);
-		gt_list->gt_list[id].ip_ver_minor =
+		gt_list->gt_list[iter].ip_ver_minor =
 			REG_FIELD_GET(GMD_ID_RELEASE_MASK, gt->info.gmdid);
-		gt_list->gt_list[id].ip_ver_rev =
+		gt_list->gt_list[iter].ip_ver_rev =
 			REG_FIELD_GET(GMD_ID_REVID, gt->info.gmdid);
+
+		iter++;
 	}
 
 	if (copy_to_user(query_ptr, gt_list, size)) {
@@ -679,7 +682,7 @@ static int query_oa_units(struct xe_device *xe,
 			du->oa_unit_id = u->oa_unit_id;
 			du->oa_unit_type = u->type;
 			du->oa_timestamp_freq = xe_oa_timestamp_frequency(gt);
-			du->capabilities = DRM_XE_OA_CAPS_BASE;
+			du->capabilities = DRM_XE_OA_CAPS_BASE | DRM_XE_OA_CAPS_SYNCS;
 
 			j = 0;
 			for_each_hw_engine(hwe, gt, hwe_id) {
diff --git a/drivers/gpu/drm/xe/xe_ring_ops.c b/drivers/gpu/drm/xe/xe_ring_ops.c
index 0be4f489d3e1..fb31e09acb51 100644
--- a/drivers/gpu/drm/xe/xe_ring_ops.c
+++ b/drivers/gpu/drm/xe/xe_ring_ops.c
@@ -221,18 +221,18 @@ static int emit_pipe_imm_ggtt(u32 addr, u32 value, bool stall_only, u32 *dw,
 
 static u32 get_ppgtt_flag(struct xe_sched_job *job)
 {
-	return job->q->vm ? BIT(8) : 0;
+	if (job->q->vm && !job->ggtt)
+		return BIT(8);
+
+	return 0;
 }
 
 static int emit_copy_timestamp(struct xe_lrc *lrc, u32 *dw, int i)
 {
-	dw[i++] = MI_COPY_MEM_MEM | MI_COPY_MEM_MEM_SRC_GGTT |
-		MI_COPY_MEM_MEM_DST_GGTT;
+	dw[i++] = MI_STORE_REGISTER_MEM | MI_SRM_USE_GGTT | MI_SRM_ADD_CS_OFFSET;
+	dw[i++] = RING_CTX_TIMESTAMP(0).addr;
 	dw[i++] = xe_lrc_ctx_job_timestamp_ggtt_addr(lrc);
 	dw[i++] = 0;
-	dw[i++] = xe_lrc_ctx_timestamp_ggtt_addr(lrc);
-	dw[i++] = 0;
-	dw[i++] = MI_NOOP;
 
 	return i;
 }
diff --git a/drivers/gpu/drm/xe/xe_sa.c b/drivers/gpu/drm/xe/xe_sa.c
index fe2cb2a96f78..1d4254759006 100644
--- a/drivers/gpu/drm/xe/xe_sa.c
+++ b/drivers/gpu/drm/xe/xe_sa.c
@@ -57,8 +57,6 @@ struct xe_sa_manager *xe_sa_bo_manager_init(struct xe_tile *tile, u32 size, u32
 	}
 	sa_manager->bo = bo;
 	sa_manager->is_iomem = bo->vmap.is_iomem;
-
-	drm_suballoc_manager_init(&sa_manager->base, managed_size, align);
 	sa_manager->gpu_addr = xe_bo_ggtt_addr(bo);
 
 	if (bo->vmap.is_iomem) {
@@ -72,6 +70,7 @@ struct xe_sa_manager *xe_sa_bo_manager_init(struct xe_tile *tile, u32 size, u32
 		memset(sa_manager->cpu_ptr, 0, bo->ttm.base.size);
 	}
 
+	drm_suballoc_manager_init(&sa_manager->base, managed_size, align);
 	ret = drmm_add_action_or_reset(&xe->drm, xe_sa_bo_manager_fini,
 				       sa_manager);
 	if (ret)
diff --git a/drivers/gpu/drm/xe/xe_sched_job_types.h b/drivers/gpu/drm/xe/xe_sched_job_types.h
index 0d3f76fb05ce..c207361bf43e 100644
--- a/drivers/gpu/drm/xe/xe_sched_job_types.h
+++ b/drivers/gpu/drm/xe/xe_sched_job_types.h
@@ -57,6 +57,8 @@ struct xe_sched_job {
 	u32 migrate_flush_flags;
 	/** @ring_ops_flush_tlb: The ring ops need to flush TLB before payload. */
 	bool ring_ops_flush_tlb;
+	/** @ggtt: mapped in ggtt. */
+	bool ggtt;
 	/** @ptrs: per instance pointers. */
 	struct xe_job_ptrs ptrs[];
 };
diff --git a/drivers/gpu/drm/xe/xe_tile.c b/drivers/gpu/drm/xe/xe_tile.c
index dda5268507d8..36c87d7c72fb 100644
--- a/drivers/gpu/drm/xe/xe_tile.c
+++ b/drivers/gpu/drm/xe/xe_tile.c
@@ -167,17 +167,19 @@ int xe_tile_init_noalloc(struct xe_tile *tile)
 	if (err)
 		return err;
 
+	xe_wa_apply_tile_workarounds(tile);
+
+	return xe_tile_sysfs_init(tile);
+}
+
+int xe_tile_init(struct xe_tile *tile)
+{
 	tile->mem.kernel_bb_pool = xe_sa_bo_manager_init(tile, SZ_1M, 16);
 	if (IS_ERR(tile->mem.kernel_bb_pool))
 		return PTR_ERR(tile->mem.kernel_bb_pool);
 
-	xe_wa_apply_tile_workarounds(tile);
-
-	err = xe_tile_sysfs_init(tile);
-
 	return 0;
 }
-
 void xe_tile_migrate_wait(struct xe_tile *tile)
 {
 	xe_migrate_wait(tile->migrate);
diff --git a/drivers/gpu/drm/xe/xe_tile.h b/drivers/gpu/drm/xe/xe_tile.h
index 1c9e42ade6b0..eb939316d55b 100644
--- a/drivers/gpu/drm/xe/xe_tile.h
+++ b/drivers/gpu/drm/xe/xe_tile.h
@@ -12,6 +12,7 @@ struct xe_tile;
 
 int xe_tile_init_early(struct xe_tile *tile, struct xe_device *xe, u8 id);
 int xe_tile_init_noalloc(struct xe_tile *tile);
+int xe_tile_init(struct xe_tile *tile);
 
 void xe_tile_migrate_wait(struct xe_tile *tile);
 
diff --git a/drivers/gpu/drm/xe/xe_trace_bo.h b/drivers/gpu/drm/xe/xe_trace_bo.h
index 9b1a1d4304ae..4ff023b5d040 100644
--- a/drivers/gpu/drm/xe/xe_trace_bo.h
+++ b/drivers/gpu/drm/xe/xe_trace_bo.h
@@ -55,8 +55,8 @@ TRACE_EVENT(xe_bo_move,
 	    TP_STRUCT__entry(
 		     __field(struct xe_bo *, bo)
 		     __field(size_t, size)
-		     __field(u32, new_placement)
-		     __field(u32, old_placement)
+		     __string(new_placement_name, xe_mem_type_to_name[new_placement])
+		     __string(old_placement_name, xe_mem_type_to_name[old_placement])
 		     __string(device_id, __dev_name_bo(bo))
 		     __field(bool, move_lacks_source)
 			),
@@ -64,15 +64,15 @@ TRACE_EVENT(xe_bo_move,
 	    TP_fast_assign(
 		   __entry->bo      = bo;
 		   __entry->size = bo->size;
-		   __entry->new_placement = new_placement;
-		   __entry->old_placement = old_placement;
+		   __assign_str(new_placement_name);
+		   __assign_str(old_placement_name);
 		   __assign_str(device_id);
 		   __entry->move_lacks_source = move_lacks_source;
 		   ),
 	    TP_printk("move_lacks_source:%s, migrate object %p [size %zu] from %s to %s device_id:%s",
 		      __entry->move_lacks_source ? "yes" : "no", __entry->bo, __entry->size,
-		      xe_mem_type_to_name[__entry->old_placement],
-		      xe_mem_type_to_name[__entry->new_placement], __get_str(device_id))
+		      __get_str(old_placement_name),
+		      __get_str(new_placement_name), __get_str(device_id))
 );
 
 DECLARE_EVENT_CLASS(xe_vma,
@@ -189,7 +189,7 @@ DECLARE_EVENT_CLASS(xe_vm,
 			   ),
 
 		    TP_printk("dev=%s, vm=%p, asid=0x%05x", __get_str(dev),
-			      __entry->vm,  __entry->asid)
+			      __entry->vm, __entry->asid)
 );
 
 DEFINE_EVENT(xe_vm, xe_vm_kill,
diff --git a/drivers/gpu/drm/xe/xe_ttm_stolen_mgr.c b/drivers/gpu/drm/xe/xe_ttm_stolen_mgr.c
index f7113cf6109d..34e38bb167ba 100644
--- a/drivers/gpu/drm/xe/xe_ttm_stolen_mgr.c
+++ b/drivers/gpu/drm/xe/xe_ttm_stolen_mgr.c
@@ -57,12 +57,35 @@ bool xe_ttm_stolen_cpu_access_needs_ggtt(struct xe_device *xe)
 	return GRAPHICS_VERx100(xe) < 1270 && !IS_DGFX(xe);
 }
 
+static u32 get_wopcm_size(struct xe_device *xe)
+{
+	u32 wopcm_size;
+	u64 val;
+
+	val = xe_mmio_read64_2x32(xe_root_mmio_gt(xe), STOLEN_RESERVED);
+	val = REG_FIELD_GET64(WOPCM_SIZE_MASK, val);
+
+	switch (val) {
+	case 0x5 ... 0x6:
+		val--;
+		fallthrough;
+	case 0x0 ... 0x3:
+		wopcm_size = (1U << val) * SZ_1M;
+		break;
+	default:
+		WARN(1, "Missing case wopcm_size=%llx\n", val);
+		wopcm_size = 0;
+	}
+
+	return wopcm_size;
+}
+
 static s64 detect_bar2_dgfx(struct xe_device *xe, struct xe_ttm_stolen_mgr *mgr)
 {
 	struct xe_tile *tile = xe_device_get_root_tile(xe);
 	struct xe_gt *mmio = xe_root_mmio_gt(xe);
 	struct pci_dev *pdev = to_pci_dev(xe->drm.dev);
-	u64 stolen_size;
+	u64 stolen_size, wopcm_size;
 	u64 tile_offset;
 	u64 tile_size;
 
@@ -74,7 +97,13 @@ static s64 detect_bar2_dgfx(struct xe_device *xe, struct xe_ttm_stolen_mgr *mgr)
 	if (drm_WARN_ON(&xe->drm, tile_size < mgr->stolen_base))
 		return 0;
 
+	/* Carve out the top of DSM as it contains the reserved WOPCM region */
+	wopcm_size = get_wopcm_size(xe);
+	if (drm_WARN_ON(&xe->drm, !wopcm_size))
+		return 0;
+
 	stolen_size = tile_size - mgr->stolen_base;
+	stolen_size -= wopcm_size;
 
 	/* Verify usage fits in the actual resource available */
 	if (mgr->stolen_base + stolen_size <= pci_resource_len(pdev, LMEM_BAR))
@@ -89,29 +118,6 @@ static s64 detect_bar2_dgfx(struct xe_device *xe, struct xe_ttm_stolen_mgr *mgr)
 	return ALIGN_DOWN(stolen_size, SZ_1M);
 }
 
-static u32 get_wopcm_size(struct xe_device *xe)
-{
-	u32 wopcm_size;
-	u64 val;
-
-	val = xe_mmio_read64_2x32(xe_root_mmio_gt(xe), STOLEN_RESERVED);
-	val = REG_FIELD_GET64(WOPCM_SIZE_MASK, val);
-
-	switch (val) {
-	case 0x5 ... 0x6:
-		val--;
-		fallthrough;
-	case 0x0 ... 0x3:
-		wopcm_size = (1U << val) * SZ_1M;
-		break;
-	default:
-		WARN(1, "Missing case wopcm_size=%llx\n", val);
-		wopcm_size = 0;
-	}
-
-	return wopcm_size;
-}
-
 static u32 detect_bar2_integrated(struct xe_device *xe, struct xe_ttm_stolen_mgr *mgr)
 {
 	struct pci_dev *pdev = to_pci_dev(xe->drm.dev);
@@ -201,17 +207,16 @@ static u64 detect_stolen(struct xe_device *xe, struct xe_ttm_stolen_mgr *mgr)
 #endif
 }
 
-void xe_ttm_stolen_mgr_init(struct xe_device *xe)
+int xe_ttm_stolen_mgr_init(struct xe_device *xe)
 {
-	struct xe_ttm_stolen_mgr *mgr = drmm_kzalloc(&xe->drm, sizeof(*mgr), GFP_KERNEL);
 	struct pci_dev *pdev = to_pci_dev(xe->drm.dev);
+	struct xe_ttm_stolen_mgr *mgr;
 	u64 stolen_size, io_size;
 	int err;
 
-	if (!mgr) {
-		drm_dbg_kms(&xe->drm, "Stolen mgr init failed\n");
-		return;
-	}
+	mgr = drmm_kzalloc(&xe->drm, sizeof(*mgr), GFP_KERNEL);
+	if (!mgr)
+		return -ENOMEM;
 
 	if (IS_SRIOV_VF(xe))
 		stolen_size = 0;
@@ -224,7 +229,7 @@ void xe_ttm_stolen_mgr_init(struct xe_device *xe)
 
 	if (!stolen_size) {
 		drm_dbg_kms(&xe->drm, "No stolen memory support\n");
-		return;
+		return 0;
 	}
 
 	/*
@@ -240,7 +245,7 @@ void xe_ttm_stolen_mgr_init(struct xe_device *xe)
 				     io_size, PAGE_SIZE);
 	if (err) {
 		drm_dbg_kms(&xe->drm, "Stolen mgr init failed: %i\n", err);
-		return;
+		return err;
 	}
 
 	drm_dbg_kms(&xe->drm, "Initialized stolen memory support with %llu bytes\n",
@@ -248,6 +253,8 @@ void xe_ttm_stolen_mgr_init(struct xe_device *xe)
 
 	if (io_size)
 		mgr->mapping = devm_ioremap_wc(&pdev->dev, mgr->io_base, io_size);
+
+	return 0;
 }
 
 u64 xe_ttm_stolen_io_offset(struct xe_bo *bo, u32 offset)
diff --git a/drivers/gpu/drm/xe/xe_ttm_stolen_mgr.h b/drivers/gpu/drm/xe/xe_ttm_stolen_mgr.h
index 1777245ff810..8e877d1e839b 100644
--- a/drivers/gpu/drm/xe/xe_ttm_stolen_mgr.h
+++ b/drivers/gpu/drm/xe/xe_ttm_stolen_mgr.h
@@ -12,7 +12,7 @@ struct ttm_resource;
 struct xe_bo;
 struct xe_device;
 
-void xe_ttm_stolen_mgr_init(struct xe_device *xe);
+int xe_ttm_stolen_mgr_init(struct xe_device *xe);
 int xe_ttm_stolen_io_mem_reserve(struct xe_device *xe, struct ttm_resource *mem);
 bool xe_ttm_stolen_cpu_access_needs_ggtt(struct xe_device *xe);
 u64 xe_ttm_stolen_io_offset(struct xe_bo *bo, u32 offset);
diff --git a/drivers/gpu/drm/xe/xe_tuning.c b/drivers/gpu/drm/xe/xe_tuning.c
index 0d5e04158917..1fb12da21c9e 100644
--- a/drivers/gpu/drm/xe/xe_tuning.c
+++ b/drivers/gpu/drm/xe/xe_tuning.c
@@ -97,14 +97,6 @@ static const struct xe_rtp_entry_sr engine_tunings[] = {
 };
 
 static const struct xe_rtp_entry_sr lrc_tunings[] = {
-	{ XE_RTP_NAME("Tuning: ganged timer, also known as 16011163337"),
-	  XE_RTP_RULES(GRAPHICS_VERSION_RANGE(1200, 1210), ENGINE_CLASS(RENDER)),
-	  /* read verification is ignored due to 1608008084. */
-	  XE_RTP_ACTIONS(FIELD_SET_NO_READ_MASK(FF_MODE2,
-						FF_MODE2_GS_TIMER_MASK,
-						FF_MODE2_GS_TIMER_224))
-	},
-
 	/* DG2 */
 
 	{ XE_RTP_NAME("Tuning: L3 cache"),
diff --git a/drivers/gpu/drm/xe/xe_uc.c b/drivers/gpu/drm/xe/xe_uc.c
index 0d073a9987c2..bb03c524613f 100644
--- a/drivers/gpu/drm/xe/xe_uc.c
+++ b/drivers/gpu/drm/xe/xe_uc.c
@@ -241,7 +241,7 @@ void xe_uc_gucrc_disable(struct xe_uc *uc)
 
 void xe_uc_stop_prepare(struct xe_uc *uc)
 {
-	xe_gsc_wait_for_worker_completion(&uc->gsc);
+	xe_gsc_stop_prepare(&uc->gsc);
 	xe_guc_stop_prepare(&uc->guc);
 }
 
@@ -275,6 +275,12 @@ again:
 		goto again;
 }
 
+void xe_uc_suspend_prepare(struct xe_uc *uc)
+{
+	xe_gsc_wait_for_worker_completion(&uc->gsc);
+	xe_guc_stop_prepare(&uc->guc);
+}
+
 int xe_uc_suspend(struct xe_uc *uc)
 {
 	/* GuC submission not enabled, nothing to do */
diff --git a/drivers/gpu/drm/xe/xe_uc.h b/drivers/gpu/drm/xe/xe_uc.h
index 506517c11333..ba2937ab94cf 100644
--- a/drivers/gpu/drm/xe/xe_uc.h
+++ b/drivers/gpu/drm/xe/xe_uc.h
@@ -18,6 +18,7 @@ int xe_uc_reset_prepare(struct xe_uc *uc);
 void xe_uc_stop_prepare(struct xe_uc *uc);
 void xe_uc_stop(struct xe_uc *uc);
 int xe_uc_start(struct xe_uc *uc);
+void xe_uc_suspend_prepare(struct xe_uc *uc);
 int xe_uc_suspend(struct xe_uc *uc);
 int xe_uc_sanitize_reset(struct xe_uc *uc);
 void xe_uc_remove(struct xe_uc *uc);
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index c99380271de6..15fd497c920c 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -8,6 +8,7 @@
 #include <linux/dma-fence-array.h>
 #include <linux/nospec.h>
 
+#include <drm/drm_drv.h>
 #include <drm/drm_exec.h>
 #include <drm/drm_print.h>
 #include <drm/ttm/ttm_execbuf_util.h>
@@ -580,51 +581,26 @@ out_unlock_outer:
 	trace_xe_vm_rebind_worker_exit(vm);
 }
 
-static bool vma_userptr_invalidate(struct mmu_interval_notifier *mni,
-				   const struct mmu_notifier_range *range,
-				   unsigned long cur_seq)
+static void __vma_userptr_invalidate(struct xe_vm *vm, struct xe_userptr_vma *uvma)
 {
-	struct xe_userptr *userptr = container_of(mni, typeof(*userptr), notifier);
-	struct xe_userptr_vma *uvma = container_of(userptr, typeof(*uvma), userptr);
+	struct xe_userptr *userptr = &uvma->userptr;
 	struct xe_vma *vma = &uvma->vma;
-	struct xe_vm *vm = xe_vma_vm(vma);
 	struct dma_resv_iter cursor;
 	struct dma_fence *fence;
 	long err;
 
-	xe_assert(vm->xe, xe_vma_is_userptr(vma));
-	trace_xe_vma_userptr_invalidate(vma);
-
-	if (!mmu_notifier_range_blockable(range))
-		return false;
-
-	vm_dbg(&xe_vma_vm(vma)->xe->drm,
-	       "NOTIFIER: addr=0x%016llx, range=0x%016llx",
-		xe_vma_start(vma), xe_vma_size(vma));
-
-	down_write(&vm->userptr.notifier_lock);
-	mmu_interval_set_seq(mni, cur_seq);
-
-	/* No need to stop gpu access if the userptr is not yet bound. */
-	if (!userptr->initial_bind) {
-		up_write(&vm->userptr.notifier_lock);
-		return true;
-	}
-
 	/*
 	 * Tell exec and rebind worker they need to repin and rebind this
 	 * userptr.
 	 */
 	if (!xe_vm_in_fault_mode(vm) &&
-	    !(vma->gpuva.flags & XE_VMA_DESTROYED) && vma->tile_present) {
+	    !(vma->gpuva.flags & XE_VMA_DESTROYED)) {
 		spin_lock(&vm->userptr.invalidated_lock);
 		list_move_tail(&userptr->invalidate_link,
 			       &vm->userptr.invalidated);
 		spin_unlock(&vm->userptr.invalidated_lock);
 	}
 
-	up_write(&vm->userptr.notifier_lock);
-
 	/*
 	 * Preempt fences turn into schedule disables, pipeline these.
 	 * Note that even in fault mode, we need to wait for binds and
@@ -642,11 +618,37 @@ static bool vma_userptr_invalidate(struct mmu_interval_notifier *mni,
 				    false, MAX_SCHEDULE_TIMEOUT);
 	XE_WARN_ON(err <= 0);
 
-	if (xe_vm_in_fault_mode(vm)) {
+	if (xe_vm_in_fault_mode(vm) && userptr->initial_bind) {
 		err = xe_vm_invalidate_vma(vma);
 		XE_WARN_ON(err);
 	}
 
+	xe_hmm_userptr_unmap(uvma);
+}
+
+static bool vma_userptr_invalidate(struct mmu_interval_notifier *mni,
+				   const struct mmu_notifier_range *range,
+				   unsigned long cur_seq)
+{
+	struct xe_userptr_vma *uvma = container_of(mni, typeof(*uvma), userptr.notifier);
+	struct xe_vma *vma = &uvma->vma;
+	struct xe_vm *vm = xe_vma_vm(vma);
+
+	xe_assert(vm->xe, xe_vma_is_userptr(vma));
+	trace_xe_vma_userptr_invalidate(vma);
+
+	if (!mmu_notifier_range_blockable(range))
+		return false;
+
+	vm_dbg(&xe_vma_vm(vma)->xe->drm,
+	       "NOTIFIER: addr=0x%016llx, range=0x%016llx",
+		xe_vma_start(vma), xe_vma_size(vma));
+
+	down_write(&vm->userptr.notifier_lock);
+	mmu_interval_set_seq(mni, cur_seq);
+
+	__vma_userptr_invalidate(vm, uvma);
+	up_write(&vm->userptr.notifier_lock);
 	trace_xe_vma_userptr_invalidate_complete(vma);
 
 	return true;
@@ -656,6 +658,34 @@ static const struct mmu_interval_notifier_ops vma_userptr_notifier_ops = {
 	.invalidate = vma_userptr_invalidate,
 };
 
+#if IS_ENABLED(CONFIG_DRM_XE_USERPTR_INVAL_INJECT)
+/**
+ * xe_vma_userptr_force_invalidate() - force invalidate a userptr
+ * @uvma: The userptr vma to invalidate
+ *
+ * Perform a forced userptr invalidation for testing purposes.
+ */
+void xe_vma_userptr_force_invalidate(struct xe_userptr_vma *uvma)
+{
+	struct xe_vm *vm = xe_vma_vm(&uvma->vma);
+
+	/* Protect against concurrent userptr pinning */
+	lockdep_assert_held(&vm->lock);
+	/* Protect against concurrent notifiers */
+	lockdep_assert_held(&vm->userptr.notifier_lock);
+	/*
+	 * Protect against concurrent instances of this function and
+	 * the critical exec sections
+	 */
+	xe_vm_assert_held(vm);
+
+	if (!mmu_interval_read_retry(&uvma->userptr.notifier,
+				     uvma->userptr.notifier_seq))
+		uvma->userptr.notifier_seq -= 2;
+	__vma_userptr_invalidate(vm, uvma);
+}
+#endif
+
 int xe_vm_userptr_pin(struct xe_vm *vm)
 {
 	struct xe_userptr_vma *uvma, *next;
@@ -667,20 +697,33 @@ int xe_vm_userptr_pin(struct xe_vm *vm)
 
 	/* Collect invalidated userptrs */
 	spin_lock(&vm->userptr.invalidated_lock);
+	xe_assert(vm->xe, list_empty(&vm->userptr.repin_list));
 	list_for_each_entry_safe(uvma, next, &vm->userptr.invalidated,
 				 userptr.invalidate_link) {
 		list_del_init(&uvma->userptr.invalidate_link);
-		list_move_tail(&uvma->userptr.repin_link,
-			       &vm->userptr.repin_list);
+		list_add_tail(&uvma->userptr.repin_link,
+			      &vm->userptr.repin_list);
 	}
 	spin_unlock(&vm->userptr.invalidated_lock);
 
-	/* Pin and move to temporary list */
+	/* Pin and move to bind list */
 	list_for_each_entry_safe(uvma, next, &vm->userptr.repin_list,
 				 userptr.repin_link) {
 		err = xe_vma_userptr_pin_pages(uvma);
 		if (err == -EFAULT) {
 			list_del_init(&uvma->userptr.repin_link);
+			/*
+			 * We might have already done the pin once already, but
+			 * then had to retry before the re-bind happened, due
+			 * some other condition in the caller, but in the
+			 * meantime the userptr got dinged by the notifier such
+			 * that we need to revalidate here, but this time we hit
+			 * the EFAULT. In such a case make sure we remove
+			 * ourselves from the rebind list to avoid going down in
+			 * flames.
+			 */
+			if (!list_empty(&uvma->vma.combined_links.rebind))
+				list_del_init(&uvma->vma.combined_links.rebind);
 
 			/* Wait for pending binds */
 			xe_vm_lock(vm, false);
@@ -691,10 +734,10 @@ int xe_vm_userptr_pin(struct xe_vm *vm)
 			err = xe_vm_invalidate_vma(&uvma->vma);
 			xe_vm_unlock(vm);
 			if (err)
-				return err;
+				break;
 		} else {
-			if (err < 0)
-				return err;
+			if (err)
+				break;
 
 			list_del_init(&uvma->userptr.repin_link);
 			list_move_tail(&uvma->vma.combined_links.rebind,
@@ -702,7 +745,19 @@ int xe_vm_userptr_pin(struct xe_vm *vm)
 		}
 	}
 
-	return 0;
+	if (err) {
+		down_write(&vm->userptr.notifier_lock);
+		spin_lock(&vm->userptr.invalidated_lock);
+		list_for_each_entry_safe(uvma, next, &vm->userptr.repin_list,
+					 userptr.repin_link) {
+			list_del_init(&uvma->userptr.repin_link);
+			list_move_tail(&uvma->userptr.invalidate_link,
+				       &vm->userptr.invalidated);
+		}
+		spin_unlock(&vm->userptr.invalidated_lock);
+		up_write(&vm->userptr.notifier_lock);
+	}
+	return err;
 }
 
 /**
@@ -987,6 +1042,7 @@ static struct xe_vma *xe_vma_create(struct xe_vm *vm,
 			INIT_LIST_HEAD(&userptr->invalidate_link);
 			INIT_LIST_HEAD(&userptr->repin_link);
 			vma->gpuva.gem.offset = bo_offset_or_userptr;
+			mutex_init(&userptr->unmap_mutex);
 
 			err = mmu_interval_notifier_insert(&userptr->notifier,
 							   current->mm,
@@ -1028,6 +1084,7 @@ static void xe_vma_destroy_late(struct xe_vma *vma)
 		 * them anymore
 		 */
 		mmu_interval_notifier_remove(&userptr->notifier);
+		mutex_destroy(&userptr->unmap_mutex);
 		xe_vm_put(vm);
 	} else if (xe_vma_is_null(vma)) {
 		xe_vm_put(vm);
@@ -1066,6 +1123,7 @@ static void xe_vma_destroy(struct xe_vma *vma, struct dma_fence *fence)
 		xe_assert(vm->xe, vma->gpuva.flags & XE_VMA_DESTROYED);
 
 		spin_lock(&vm->userptr.invalidated_lock);
+		xe_assert(vm->xe, list_empty(&to_userptr_vma(vma)->userptr.repin_link));
 		list_del(&to_userptr_vma(vma)->userptr.invalidate_link);
 		spin_unlock(&vm->userptr.invalidated_lock);
 	} else if (!xe_vma_is_null(vma)) {
@@ -1419,8 +1477,10 @@ struct xe_vm *xe_vm_create(struct xe_device *xe, u32 flags)
 	 * scheduler drops all the references of it, hence protecting the VM
 	 * for this case is necessary.
 	 */
-	if (flags & XE_VM_FLAG_LR_MODE)
+	if (flags & XE_VM_FLAG_LR_MODE) {
+		INIT_WORK(&vm->preempt.rebind_work, preempt_rebind_work_func);
 		xe_pm_runtime_get_noresume(xe);
+	}
 
 	vm_resv_obj = drm_gpuvm_resv_object_alloc(&xe->drm);
 	if (!vm_resv_obj) {
@@ -1465,10 +1525,8 @@ struct xe_vm *xe_vm_create(struct xe_device *xe, u32 flags)
 		vm->batch_invalidate_tlb = true;
 	}
 
-	if (vm->flags & XE_VM_FLAG_LR_MODE) {
-		INIT_WORK(&vm->preempt.rebind_work, preempt_rebind_work_func);
+	if (vm->flags & XE_VM_FLAG_LR_MODE)
 		vm->batch_invalidate_tlb = false;
-	}
 
 	/* Fill pt_root after allocating scratch tables */
 	for_each_tile(tile, xe, id) {
@@ -1524,9 +1582,40 @@ err_no_resv:
 
 static void xe_vm_close(struct xe_vm *vm)
 {
+	struct xe_device *xe = vm->xe;
+	bool bound;
+	int idx;
+
+	bound = drm_dev_enter(&xe->drm, &idx);
+
 	down_write(&vm->lock);
+
 	vm->size = 0;
+
+	if (!((vm->flags & XE_VM_FLAG_MIGRATION))) {
+		struct xe_tile *tile;
+		struct xe_gt *gt;
+		u8 id;
+
+		/* Wait for pending binds */
+		dma_resv_wait_timeout(xe_vm_resv(vm),
+				      DMA_RESV_USAGE_BOOKKEEP,
+				      false, MAX_SCHEDULE_TIMEOUT);
+
+		if (bound) {
+			for_each_tile(tile, xe, id)
+				if (vm->pt_root[id])
+					xe_pt_clear(xe, vm->pt_root[id]);
+
+			for_each_gt(gt, xe, id)
+				xe_gt_tlb_invalidation_vm(gt, vm);
+		}
+	}
+
 	up_write(&vm->lock);
+
+	if (bound)
+		drm_dev_exit(idx);
 }
 
 void xe_vm_close_and_put(struct xe_vm *vm)
@@ -2258,8 +2347,17 @@ static int vm_bind_ioctl_ops_parse(struct xe_vm *vm, struct drm_gpuva_ops *ops,
 			break;
 		}
 		case DRM_GPUVA_OP_UNMAP:
+			xe_vma_ops_incr_pt_update_ops(vops, op->tile_mask);
+			break;
 		case DRM_GPUVA_OP_PREFETCH:
-			/* FIXME: Need to skip some prefetch ops */
+			vma = gpuva_to_vma(op->base.prefetch.va);
+
+			if (xe_vma_is_userptr(vma)) {
+				err = xe_vma_userptr_pin_pages(to_userptr_vma(vma));
+				if (err)
+					return err;
+			}
+
 			xe_vma_ops_incr_pt_update_ops(vops, op->tile_mask);
 			break;
 		default:
diff --git a/drivers/gpu/drm/xe/xe_vm.h b/drivers/gpu/drm/xe/xe_vm.h
index c864dba35e1d..d2406532fcc5 100644
--- a/drivers/gpu/drm/xe/xe_vm.h
+++ b/drivers/gpu/drm/xe/xe_vm.h
@@ -275,9 +275,17 @@ static inline void vm_dbg(const struct drm_device *dev,
 			  const char *format, ...)
 { /* noop */ }
 #endif
-#endif
 
 struct xe_vm_snapshot *xe_vm_snapshot_capture(struct xe_vm *vm);
 void xe_vm_snapshot_capture_delayed(struct xe_vm_snapshot *snap);
 void xe_vm_snapshot_print(struct xe_vm_snapshot *snap, struct drm_printer *p);
 void xe_vm_snapshot_free(struct xe_vm_snapshot *snap);
+
+#if IS_ENABLED(CONFIG_DRM_XE_USERPTR_INVAL_INJECT)
+void xe_vma_userptr_force_invalidate(struct xe_userptr_vma *uvma);
+#else
+static inline void xe_vma_userptr_force_invalidate(struct xe_userptr_vma *uvma)
+{
+}
+#endif
+#endif
diff --git a/drivers/gpu/drm/xe/xe_vm_types.h b/drivers/gpu/drm/xe/xe_vm_types.h
index 7f9a303e51d8..a4b4091cfd0d 100644
--- a/drivers/gpu/drm/xe/xe_vm_types.h
+++ b/drivers/gpu/drm/xe/xe_vm_types.h
@@ -59,12 +59,16 @@ struct xe_userptr {
 	struct sg_table *sg;
 	/** @notifier_seq: notifier sequence number */
 	unsigned long notifier_seq;
+	/** @unmap_mutex: Mutex protecting dma-unmapping */
+	struct mutex unmap_mutex;
 	/**
 	 * @initial_bind: user pointer has been bound at least once.
 	 * write: vm->userptr.notifier_lock in read mode and vm->resv held.
 	 * read: vm->userptr.notifier_lock in write mode or vm->resv held.
 	 */
 	bool initial_bind;
+	/** @mapped: Whether the @sgt sg-table is dma-mapped. Protected by @unmap_mutex. */
+	bool mapped;
 #if IS_ENABLED(CONFIG_DRM_XE_USERPTR_INVAL_INJECT)
 	u32 divisor;
 #endif
@@ -227,8 +231,8 @@ struct xe_vm {
 		 * up for revalidation. Protected from access with the
 		 * @invalidated_lock. Removing items from the list
 		 * additionally requires @lock in write mode, and adding
-		 * items to the list requires the @userptr.notifer_lock in
-		 * write mode.
+		 * items to the list requires either the @userptr.notifer_lock in
+		 * write mode, OR @lock in write mode.
 		 */
 		struct list_head invalidated;
 	} userptr;
diff --git a/drivers/gpu/drm/xe/xe_wa.c b/drivers/gpu/drm/xe/xe_wa.c
index 37e592b2bf06..aea6034a8107 100644
--- a/drivers/gpu/drm/xe/xe_wa.c
+++ b/drivers/gpu/drm/xe/xe_wa.c
@@ -606,6 +606,13 @@ static const struct xe_rtp_entry_sr engine_was[] = {
 };
 
 static const struct xe_rtp_entry_sr lrc_was[] = {
+	{ XE_RTP_NAME("16011163337"),
+	  XE_RTP_RULES(GRAPHICS_VERSION_RANGE(1200, 1210), ENGINE_CLASS(RENDER)),
+	  /* read verification is ignored due to 1608008084. */
+	  XE_RTP_ACTIONS(FIELD_SET_NO_READ_MASK(FF_MODE2,
+						FF_MODE2_GS_TIMER_MASK,
+						FF_MODE2_GS_TIMER_224))
+	},
 	{ XE_RTP_NAME("1409342910, 14010698770, 14010443199, 1408979724, 1409178076, 1409207793, 1409217633, 1409252684, 1409347922, 1409142259"),
 	  XE_RTP_RULES(GRAPHICS_VERSION_RANGE(1200, 1210)),
 	  XE_RTP_ACTIONS(SET(COMMON_SLICE_CHICKEN3,
@@ -776,6 +783,10 @@ static const struct xe_rtp_entry_sr lrc_was[] = {
 	  XE_RTP_RULES(GRAPHICS_VERSION(2001), ENGINE_CLASS(RENDER)),
 	  XE_RTP_ACTIONS(SET(CHICKEN_RASTER_1, DIS_CLIP_NEGATIVE_BOUNDING_BOX))
 	},
+	{ XE_RTP_NAME("22021007897"),
+	  XE_RTP_RULES(GRAPHICS_VERSION(2001), ENGINE_CLASS(RENDER)),
+	  XE_RTP_ACTIONS(SET(COMMON_SLICE_CHICKEN4, SBE_PUSH_CONSTANT_BEHIND_FIX_ENABLE))
+	},
 
 	/* Xe3_LPG */
 	{ XE_RTP_NAME("14021490052"),
diff --git a/drivers/gpu/drm/xe/xe_wa_oob.rules b/drivers/gpu/drm/xe/xe_wa_oob.rules
index 264d6e116499..93fa2708ee37 100644
--- a/drivers/gpu/drm/xe/xe_wa_oob.rules
+++ b/drivers/gpu/drm/xe/xe_wa_oob.rules
@@ -29,8 +29,10 @@
 13011645652	GRAPHICS_VERSION(2004)
 14022293748	GRAPHICS_VERSION(2001)
 		GRAPHICS_VERSION(2004)
+		GRAPHICS_VERSION_RANGE(3000, 3001)
 22019794406	GRAPHICS_VERSION(2001)
 		GRAPHICS_VERSION(2004)
+		GRAPHICS_VERSION_RANGE(3000, 3001)
 22019338487	MEDIA_VERSION(2000)
 		GRAPHICS_VERSION(2001)
 		MEDIA_VERSION(3000), MEDIA_STEP(A0, B0)
diff --git a/drivers/gpu/drm/xlnx/zynqmp_dpsub.c b/drivers/gpu/drm/xlnx/zynqmp_dpsub.c
index f5781939de9c..a25b22238e3d 100644
--- a/drivers/gpu/drm/xlnx/zynqmp_dpsub.c
+++ b/drivers/gpu/drm/xlnx/zynqmp_dpsub.c
@@ -231,6 +231,8 @@ static int zynqmp_dpsub_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
+	dma_set_max_seg_size(&pdev->dev, DMA_BIT_MASK(32));
+
 	/* Try the reserved memory. Proceed if there's none. */
 	of_reserved_mem_device_init(&pdev->dev);
 
diff --git a/drivers/gpu/host1x/dev.c b/drivers/gpu/host1x/dev.c
index e98528777faa..3f23a7d91519 100644
--- a/drivers/gpu/host1x/dev.c
+++ b/drivers/gpu/host1x/dev.c
@@ -367,6 +367,10 @@ static bool host1x_wants_iommu(struct host1x *host1x)
 	return true;
 }
 
+/*
+ * Returns ERR_PTR on failure, NULL if the translation is IDENTITY, otherwise a
+ * valid paging domain.
+ */
 static struct iommu_domain *host1x_iommu_attach(struct host1x *host)
 {
 	struct iommu_domain *domain = iommu_get_domain_for_dev(host->dev);
@@ -391,6 +395,8 @@ static struct iommu_domain *host1x_iommu_attach(struct host1x *host)
 	 * Similarly, if host1x is already attached to an IOMMU (via the DMA
 	 * API), don't try to attach again.
 	 */
+	if (domain && domain->type == IOMMU_DOMAIN_IDENTITY)
+		domain = NULL;
 	if (!host1x_wants_iommu(host) || domain)
 		return domain;
 
@@ -625,6 +631,8 @@ static int host1x_probe(struct platform_device *pdev)
 		goto free_contexts;
 	}
 
+	mutex_init(&host->intr_mutex);
+
 	pm_runtime_enable(&pdev->dev);
 
 	err = devm_tegra_core_dev_init_opp_table_common(&pdev->dev);
diff --git a/drivers/gpu/host1x/intr.c b/drivers/gpu/host1x/intr.c
index b3285dd10180..f77a678949e9 100644
--- a/drivers/gpu/host1x/intr.c
+++ b/drivers/gpu/host1x/intr.c
@@ -104,8 +104,6 @@ int host1x_intr_init(struct host1x *host)
 	unsigned int id;
 	int i, err;
 
-	mutex_init(&host->intr_mutex);
-
 	for (id = 0; id < host1x_syncpt_nb_pts(host); ++id) {
 		struct host1x_syncpt *syncpt = &host->syncpt[id];
 
diff --git a/drivers/greybus/gb-beagleplay.c b/drivers/greybus/gb-beagleplay.c
index 473ac3f2d382..da31f1131afc 100644
--- a/drivers/greybus/gb-beagleplay.c
+++ b/drivers/greybus/gb-beagleplay.c
@@ -912,7 +912,9 @@ static enum fw_upload_err cc1352_prepare(struct fw_upload *fw_upload,
 		cc1352_bootloader_reset(bg);
 		WRITE_ONCE(bg->flashing_mode, false);
 		msleep(200);
-		gb_greybus_init(bg);
+		if (gb_greybus_init(bg) < 0)
+			return dev_err_probe(&bg->sd->dev, FW_UPLOAD_ERR_RW_ERROR,
+					     "Failed to initialize greybus");
 		gb_beagleplay_start_svc(bg);
 		return FW_UPLOAD_ERR_FW_INVALID;
 	}
diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig
index f8a56d631242..95a4ede27099 100644
--- a/drivers/hid/Kconfig
+++ b/drivers/hid/Kconfig
@@ -1154,7 +1154,8 @@ config HID_TOPRE
 	tristate "Topre REALFORCE keyboards"
 	depends on HID
 	help
-	  Say Y for N-key rollover support on Topre REALFORCE R2 108/87 key keyboards.
+	  Say Y for N-key rollover support on Topre REALFORCE R2 108/87 key and
+          Topre REALFORCE R3S 87 key keyboards.
 
 config HID_THINGM
 	tristate "ThingM blink(1) USB RGB LED"
@@ -1204,6 +1205,20 @@ config HID_U2FZERO
 	  allow setting the brightness to anything but 1, which will
 	  trigger a single blink and immediately reset back to 0.
 
+config HID_UNIVERSAL_PIDFF
+	tristate "universal-pidff: extended USB PID driver compatibility and usage"
+	depends on USB_HID
+	depends on HID_PID
+	help
+	  Extended PID support for selected devices.
+
+	  Contains report fixups, extended usable button range and
+	  pidff quirk management to extend compatibility with slightly
+	  non-compliant USB PID devices and better fuzz/flat values for
+	  high precision direct drive devices.
+
+	  Supports Moza Racing, Cammus, VRS, FFBeast and more.
+
 config HID_WACOM
 	tristate "Wacom Intuos/Graphire tablet support (USB)"
 	depends on USB_HID
diff --git a/drivers/hid/Makefile b/drivers/hid/Makefile
index 496dab54c73a..27ee02bf6f26 100644
--- a/drivers/hid/Makefile
+++ b/drivers/hid/Makefile
@@ -139,6 +139,7 @@ hid-uclogic-objs		:= hid-uclogic-core.o \
 				   hid-uclogic-params.o
 obj-$(CONFIG_HID_UCLOGIC)	+= hid-uclogic.o
 obj-$(CONFIG_HID_UDRAW_PS3)	+= hid-udraw-ps3.o
+obj-$(CONFIG_HID_UNIVERSAL_PIDFF)	+= hid-universal-pidff.o
 obj-$(CONFIG_HID_LED)		+= hid-led.o
 obj-$(CONFIG_HID_XIAOMI)	+= hid-xiaomi.o
 obj-$(CONFIG_HID_XINMO)		+= hid-xinmo.o
@@ -165,7 +166,6 @@ obj-$(CONFIG_USB_KBD)		+= usbhid/
 obj-$(CONFIG_I2C_HID_CORE)	+= i2c-hid/
 
 obj-$(CONFIG_INTEL_ISH_HID)	+= intel-ish-hid/
-obj-$(INTEL_ISH_FIRMWARE_DOWNLOADER)	+= intel-ish-hid/
 
 obj-$(CONFIG_AMD_SFH_HID)       += amd-sfh-hid/
 
diff --git a/drivers/hid/bpf/hid_bpf_dispatch.c b/drivers/hid/bpf/hid_bpf_dispatch.c
index 8420c227e21b..bd3cc5636648 100644
--- a/drivers/hid/bpf/hid_bpf_dispatch.c
+++ b/drivers/hid/bpf/hid_bpf_dispatch.c
@@ -38,6 +38,9 @@ dispatch_hid_bpf_device_event(struct hid_device *hdev, enum hid_report_type type
 	struct hid_bpf_ops *e;
 	int ret;
 
+	if (unlikely(hdev->bpf.destroyed))
+		return ERR_PTR(-ENODEV);
+
 	if (type >= HID_REPORT_TYPES)
 		return ERR_PTR(-EINVAL);
 
@@ -93,6 +96,9 @@ int dispatch_hid_bpf_raw_requests(struct hid_device *hdev,
 	struct hid_bpf_ops *e;
 	int ret, idx;
 
+	if (unlikely(hdev->bpf.destroyed))
+		return -ENODEV;
+
 	if (rtype >= HID_REPORT_TYPES)
 		return -EINVAL;
 
@@ -130,6 +136,9 @@ int dispatch_hid_bpf_output_report(struct hid_device *hdev,
 	struct hid_bpf_ops *e;
 	int ret, idx;
 
+	if (unlikely(hdev->bpf.destroyed))
+		return -ENODEV;
+
 	idx = srcu_read_lock(&hdev->bpf.srcu);
 	list_for_each_entry_srcu(e, &hdev->bpf.prog_list, list,
 				 srcu_read_lock_held(&hdev->bpf.srcu)) {
diff --git a/drivers/hid/hid-apple.c b/drivers/hid/hid-apple.c
index 7e1ae2a2bcc2..25d1edb6a210 100644
--- a/drivers/hid/hid-apple.c
+++ b/drivers/hid/hid-apple.c
@@ -378,6 +378,12 @@ static bool apple_is_non_apple_keyboard(struct hid_device *hdev)
 	return false;
 }
 
+static bool apple_is_omoton_kb066(struct hid_device *hdev)
+{
+	return hdev->product == USB_DEVICE_ID_APPLE_ALU_WIRELESS_ANSI &&
+		strcmp(hdev->name, "Bluetooth Keyboard") == 0;
+}
+
 static inline void apple_setup_key_translation(struct input_dev *input,
 		const struct apple_key_translation *table)
 {
@@ -474,6 +480,7 @@ static int hidinput_apple_event(struct hid_device *hid, struct input_dev *input,
 			 hid->product == USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_NUMPAD_2015)
 			table = magic_keyboard_2015_fn_keys;
 		else if (hid->product == USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_2021 ||
+			 hid->product == USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_2024 ||
 			 hid->product == USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_FINGERPRINT_2021 ||
 			 hid->product == USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_NUMPAD_2021)
 			table = apple2021_fn_keys;
@@ -724,7 +731,7 @@ static int apple_input_configured(struct hid_device *hdev,
 {
 	struct apple_sc *asc = hid_get_drvdata(hdev);
 
-	if ((asc->quirks & APPLE_HAS_FN) && !asc->fn_found) {
+	if (((asc->quirks & APPLE_HAS_FN) && !asc->fn_found) || apple_is_omoton_kb066(hdev)) {
 		hid_info(hdev, "Fn key not found (Apple Wireless Keyboard clone?), disabling Fn key handling\n");
 		asc->quirks &= ~APPLE_HAS_FN;
 	}
@@ -883,7 +890,8 @@ static int apple_magic_backlight_init(struct hid_device *hdev)
 	backlight->brightness = report_enum->report_id_hash[APPLE_MAGIC_REPORT_ID_BRIGHTNESS];
 	backlight->power = report_enum->report_id_hash[APPLE_MAGIC_REPORT_ID_POWER];
 
-	if (!backlight->brightness || !backlight->power)
+	if (!backlight->brightness || backlight->brightness->maxfield < 2 ||
+	    !backlight->power || backlight->power->maxfield < 2)
 		return -ENODEV;
 
 	backlight->cdev.name = ":white:" LED_FUNCTION_KBD_BACKLIGHT;
@@ -926,10 +934,12 @@ static int apple_probe(struct hid_device *hdev,
 		return ret;
 	}
 
-	timer_setup(&asc->battery_timer, apple_battery_timer_tick, 0);
-	mod_timer(&asc->battery_timer,
-		  jiffies + msecs_to_jiffies(APPLE_BATTERY_TIMEOUT_MS));
-	apple_fetch_battery(hdev);
+	if (quirks & APPLE_RDESC_BATTERY) {
+		timer_setup(&asc->battery_timer, apple_battery_timer_tick, 0);
+		mod_timer(&asc->battery_timer,
+			  jiffies + msecs_to_jiffies(APPLE_BATTERY_TIMEOUT_MS));
+		apple_fetch_battery(hdev);
+	}
 
 	if (quirks & APPLE_BACKLIGHT_CTL)
 		apple_backlight_init(hdev);
@@ -943,7 +953,9 @@ static int apple_probe(struct hid_device *hdev,
 	return 0;
 
 out_err:
-	del_timer_sync(&asc->battery_timer);
+	if (quirks & APPLE_RDESC_BATTERY)
+		del_timer_sync(&asc->battery_timer);
+
 	hid_hw_stop(hdev);
 	return ret;
 }
@@ -952,7 +964,8 @@ static void apple_remove(struct hid_device *hdev)
 {
 	struct apple_sc *asc = hid_get_drvdata(hdev);
 
-	del_timer_sync(&asc->battery_timer);
+	if (asc->quirks & APPLE_RDESC_BATTERY)
+		del_timer_sync(&asc->battery_timer);
 
 	hid_hw_stop(hdev);
 }
@@ -1150,6 +1163,10 @@ static const struct hid_device_id apple_devices[] = {
 		.driver_data = APPLE_HAS_FN | APPLE_ISO_TILDE_QUIRK | APPLE_RDESC_BATTERY },
 	{ HID_BLUETOOTH_DEVICE(BT_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_2021),
 		.driver_data = APPLE_HAS_FN | APPLE_ISO_TILDE_QUIRK },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_2024),
+		.driver_data = APPLE_HAS_FN | APPLE_ISO_TILDE_QUIRK | APPLE_RDESC_BATTERY },
+	{ HID_BLUETOOTH_DEVICE(BT_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_2024),
+		.driver_data = APPLE_HAS_FN | APPLE_ISO_TILDE_QUIRK },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_FINGERPRINT_2021),
 		.driver_data = APPLE_HAS_FN | APPLE_ISO_TILDE_QUIRK | APPLE_RDESC_BATTERY },
 	{ HID_BLUETOOTH_DEVICE(BT_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_FINGERPRINT_2021),
diff --git a/drivers/hid/hid-appleir.c b/drivers/hid/hid-appleir.c
index 8deded185725..c45e5aa569d2 100644
--- a/drivers/hid/hid-appleir.c
+++ b/drivers/hid/hid-appleir.c
@@ -188,7 +188,7 @@ static int appleir_raw_event(struct hid_device *hid, struct hid_report *report,
 	static const u8 flatbattery[] = { 0x25, 0x87, 0xe0 };
 	unsigned long flags;
 
-	if (len != 5)
+	if (len != 5 || !(hid->claimed & HID_CLAIMED_INPUT))
 		goto out;
 
 	if (!memcmp(data, keydown, sizeof(keydown))) {
diff --git a/drivers/hid/hid-asus.c b/drivers/hid/hid-asus.c
index a4b47319ad8e..c5bdf0f1b32f 100644
--- a/drivers/hid/hid-asus.c
+++ b/drivers/hid/hid-asus.c
@@ -52,6 +52,10 @@ MODULE_DESCRIPTION("Asus HID Keyboard and TouchPad");
 #define FEATURE_KBD_LED_REPORT_ID1 0x5d
 #define FEATURE_KBD_LED_REPORT_ID2 0x5e
 
+#define ROG_ALLY_REPORT_SIZE 64
+#define ROG_ALLY_X_MIN_MCU 313
+#define ROG_ALLY_MIN_MCU 319
+
 #define SUPPORT_KBD_BACKLIGHT BIT(0)
 
 #define MAX_TOUCH_MAJOR 8
@@ -84,6 +88,7 @@ MODULE_DESCRIPTION("Asus HID Keyboard and TouchPad");
 #define QUIRK_MEDION_E1239T		BIT(10)
 #define QUIRK_ROG_NKEY_KEYBOARD		BIT(11)
 #define QUIRK_ROG_CLAYMORE_II_KEYBOARD BIT(12)
+#define QUIRK_ROG_ALLY_XPAD		BIT(13)
 
 #define I2C_KEYBOARD_QUIRKS			(QUIRK_FIX_NOTEBOOK_REPORT | \
 						 QUIRK_NO_INIT_REPORTS | \
@@ -432,6 +437,26 @@ static int asus_kbd_get_functions(struct hid_device *hdev,
 	return ret;
 }
 
+static int asus_kbd_disable_oobe(struct hid_device *hdev)
+{
+	const u8 init[][6] = {
+		{ FEATURE_KBD_REPORT_ID, 0x05, 0x20, 0x31, 0x00, 0x08 },
+		{ FEATURE_KBD_REPORT_ID, 0xBA, 0xC5, 0xC4 },
+		{ FEATURE_KBD_REPORT_ID, 0xD0, 0x8F, 0x01 },
+		{ FEATURE_KBD_REPORT_ID, 0xD0, 0x85, 0xFF }
+	};
+	int ret;
+
+	for (size_t i = 0; i < ARRAY_SIZE(init); i++) {
+		ret = asus_kbd_set_report(hdev, init[i], sizeof(init[i]));
+		if (ret < 0)
+			return ret;
+	}
+
+	hid_info(hdev, "Disabled OOBE for keyboard\n");
+	return 0;
+}
+
 static void asus_schedule_work(struct asus_kbd_leds *led)
 {
 	unsigned long flags;
@@ -514,9 +539,99 @@ static bool asus_kbd_wmi_led_control_present(struct hid_device *hdev)
 	return !!(value & ASUS_WMI_DSTS_PRESENCE_BIT);
 }
 
+/*
+ * We don't care about any other part of the string except the version section.
+ * Example strings: FGA80100.RC72LA.312_T01, FGA80100.RC71LS.318_T01
+ * The bytes "5a 05 03 31 00 1a 13" and possibly more come before the version
+ * string, and there may be additional bytes after the version string such as
+ * "75 00 74 00 65 00" or a postfix such as "_T01"
+ */
+static int mcu_parse_version_string(const u8 *response, size_t response_size)
+{
+	const u8 *end = response + response_size;
+	const u8 *p = response;
+	int dots, err, version;
+	char buf[4];
+
+	dots = 0;
+	while (p < end && dots < 2) {
+		if (*p++ == '.')
+			dots++;
+	}
+
+	if (dots != 2 || p >= end || (p + 3) >= end)
+		return -EINVAL;
+
+	memcpy(buf, p, 3);
+	buf[3] = '\0';
+
+	err = kstrtoint(buf, 10, &version);
+	if (err || version < 0)
+		return -EINVAL;
+
+	return version;
+}
+
+static int mcu_request_version(struct hid_device *hdev)
+{
+	u8 *response __free(kfree) = kzalloc(ROG_ALLY_REPORT_SIZE, GFP_KERNEL);
+	const u8 request[] = { 0x5a, 0x05, 0x03, 0x31, 0x00, 0x20 };
+	int ret;
+
+	if (!response)
+		return -ENOMEM;
+
+	ret = asus_kbd_set_report(hdev, request, sizeof(request));
+	if (ret < 0)
+		return ret;
+
+	ret = hid_hw_raw_request(hdev, FEATURE_REPORT_ID, response,
+				ROG_ALLY_REPORT_SIZE, HID_FEATURE_REPORT,
+				HID_REQ_GET_REPORT);
+	if (ret < 0)
+		return ret;
+
+	ret = mcu_parse_version_string(response, ROG_ALLY_REPORT_SIZE);
+	if (ret < 0) {
+		pr_err("Failed to parse MCU version: %d\n", ret);
+		print_hex_dump(KERN_ERR, "MCU: ", DUMP_PREFIX_NONE,
+			      16, 1, response, ROG_ALLY_REPORT_SIZE, false);
+	}
+
+	return ret;
+}
+
+static void validate_mcu_fw_version(struct hid_device *hdev, int idProduct)
+{
+	int min_version, version;
+
+	version = mcu_request_version(hdev);
+	if (version < 0)
+		return;
+
+	switch (idProduct) {
+	case USB_DEVICE_ID_ASUSTEK_ROG_NKEY_ALLY:
+		min_version = ROG_ALLY_MIN_MCU;
+		break;
+	case USB_DEVICE_ID_ASUSTEK_ROG_NKEY_ALLY_X:
+		min_version = ROG_ALLY_X_MIN_MCU;
+		break;
+	default:
+		min_version = 0;
+	}
+
+	if (version < min_version) {
+		hid_warn(hdev,
+			"The MCU firmware version must be %d or greater to avoid issues with suspend.\n",
+			min_version);
+	}
+}
+
 static int asus_kbd_register_leds(struct hid_device *hdev)
 {
 	struct asus_drvdata *drvdata = hid_get_drvdata(hdev);
+	struct usb_interface *intf;
+	struct usb_device *udev;
 	unsigned char kbd_func;
 	int ret;
 
@@ -534,6 +649,20 @@ static int asus_kbd_register_leds(struct hid_device *hdev)
 		ret = asus_kbd_init(hdev, FEATURE_KBD_LED_REPORT_ID2);
 		if (ret < 0)
 			return ret;
+
+		if (dmi_match(DMI_PRODUCT_FAMILY, "ProArt P16")) {
+			ret = asus_kbd_disable_oobe(hdev);
+			if (ret < 0)
+				return ret;
+		}
+
+		if (drvdata->quirks & QUIRK_ROG_ALLY_XPAD) {
+			intf = to_usb_interface(hdev->dev.parent);
+			udev = interface_to_usbdev(intf);
+			validate_mcu_fw_version(hdev,
+				le16_to_cpu(udev->descriptor.idProduct));
+		}
+
 	} else {
 		/* Initialize keyboard */
 		ret = asus_kbd_init(hdev, FEATURE_KBD_REPORT_ID);
@@ -1254,10 +1383,10 @@ static const struct hid_device_id asus_devices[] = {
 	  QUIRK_USE_KBD_BACKLIGHT | QUIRK_ROG_NKEY_KEYBOARD },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ASUSTEK,
 	    USB_DEVICE_ID_ASUSTEK_ROG_NKEY_ALLY),
-	  QUIRK_USE_KBD_BACKLIGHT | QUIRK_ROG_NKEY_KEYBOARD },
+	  QUIRK_USE_KBD_BACKLIGHT | QUIRK_ROG_NKEY_KEYBOARD | QUIRK_ROG_ALLY_XPAD},
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ASUSTEK,
 	    USB_DEVICE_ID_ASUSTEK_ROG_NKEY_ALLY_X),
-	  QUIRK_USE_KBD_BACKLIGHT | QUIRK_ROG_NKEY_KEYBOARD },
+	  QUIRK_USE_KBD_BACKLIGHT | QUIRK_ROG_NKEY_KEYBOARD | QUIRK_ROG_ALLY_XPAD },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ASUSTEK,
 	    USB_DEVICE_ID_ASUSTEK_ROG_CLAYMORE_II_KEYBOARD),
 	  QUIRK_ROG_CLAYMORE_II_KEYBOARD },
diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index 935ccc38d129..c2783d04c6e0 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -1125,6 +1125,8 @@ static void hid_apply_multiplier(struct hid_device *hid,
 	while (multiplier_collection->parent_idx != -1 &&
 	       multiplier_collection->type != HID_COLLECTION_LOGICAL)
 		multiplier_collection = &hid->collection[multiplier_collection->parent_idx];
+	if (multiplier_collection->type != HID_COLLECTION_LOGICAL)
+		multiplier_collection = NULL;
 
 	effective_multiplier = hid_calculate_multiplier(hid, multiplier);
 
@@ -1871,9 +1873,12 @@ u8 *hid_alloc_report_buf(struct hid_report *report, gfp_t flags)
 	/*
 	 * 7 extra bytes are necessary to achieve proper functionality
 	 * of implement() working on 8 byte chunks
+	 * 1 extra byte for the report ID if it is null (not used) so
+	 * we can reserve that extra byte in the first position of the buffer
+	 * when sending it to .raw_request()
 	 */
 
-	u32 len = hid_report_len(report) + 7;
+	u32 len = hid_report_len(report) + 7 + (report->id == 0);
 
 	return kzalloc(len, flags);
 }
@@ -1961,7 +1966,7 @@ static struct hid_report *hid_get_report(struct hid_report_enum *report_enum,
 int __hid_request(struct hid_device *hid, struct hid_report *report,
 		enum hid_class_request reqtype)
 {
-	char *buf;
+	char *buf, *data_buf;
 	int ret;
 	u32 len;
 
@@ -1969,13 +1974,19 @@ int __hid_request(struct hid_device *hid, struct hid_report *report,
 	if (!buf)
 		return -ENOMEM;
 
+	data_buf = buf;
 	len = hid_report_len(report);
 
+	if (report->id == 0) {
+		/* reserve the first byte for the report ID */
+		data_buf++;
+		len++;
+	}
+
 	if (reqtype == HID_REQ_SET_REPORT)
-		hid_output_report(report, buf);
+		hid_output_report(report, data_buf);
 
-	ret = hid->ll_driver->raw_request(hid, report->id, buf, len,
-					  report->type, reqtype);
+	ret = hid_hw_raw_request(hid, report->id, buf, len, report->type, reqtype);
 	if (ret < 0) {
 		dbg_hid("unable to complete request: %d\n", ret);
 		goto out;
diff --git a/drivers/hid/hid-google-hammer.c b/drivers/hid/hid-google-hammer.c
index 22683ec819aa..646ba5b92e0b 100644
--- a/drivers/hid/hid-google-hammer.c
+++ b/drivers/hid/hid-google-hammer.c
@@ -268,11 +268,13 @@ static void cbas_ec_remove(struct platform_device *pdev)
 	mutex_unlock(&cbas_ec_reglock);
 }
 
+#ifdef CONFIG_ACPI
 static const struct acpi_device_id cbas_ec_acpi_ids[] = {
 	{ "GOOG000B", 0 },
 	{ }
 };
 MODULE_DEVICE_TABLE(acpi, cbas_ec_acpi_ids);
+#endif
 
 #ifdef CONFIG_OF
 static const struct of_device_id cbas_ec_of_match[] = {
diff --git a/drivers/hid/hid-hyperv.c b/drivers/hid/hid-hyperv.c
index 0fb210e40a41..9eafff0b6ea4 100644
--- a/drivers/hid/hid-hyperv.c
+++ b/drivers/hid/hid-hyperv.c
@@ -192,7 +192,7 @@ static void mousevsc_on_receive_device_info(struct mousevsc_dev *input_device,
 		goto cleanup;
 
 	input_device->report_desc_size = le16_to_cpu(
-					desc->desc[0].wDescriptorLength);
+					desc->rpt_desc.wDescriptorLength);
 	if (input_device->report_desc_size == 0) {
 		input_device->dev_info_status = -EINVAL;
 		goto cleanup;
@@ -210,7 +210,7 @@ static void mousevsc_on_receive_device_info(struct mousevsc_dev *input_device,
 
 	memcpy(input_device->report_desc,
 	       ((unsigned char *)desc) + desc->bLength,
-	       le16_to_cpu(desc->desc[0].wDescriptorLength));
+	       le16_to_cpu(desc->rpt_desc.wDescriptorLength));
 
 	/* Send the ack */
 	memset(&ack, 0, sizeof(struct mousevsc_prt_msg));
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index 0f23be98c56e..b472140421f5 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -41,6 +41,10 @@
 #define USB_VENDOR_ID_ACTIONSTAR	0x2101
 #define USB_DEVICE_ID_ACTIONSTAR_1011	0x1011
 
+#define USB_VENDOR_ID_ADATA_XPG 0x125f
+#define USB_VENDOR_ID_ADATA_XPG_WL_GAMING_MOUSE 0x7505
+#define USB_VENDOR_ID_ADATA_XPG_WL_GAMING_MOUSE_DONGLE 0x7506
+
 #define USB_VENDOR_ID_ADS_TECH		0x06e1
 #define USB_DEVICE_ID_ADS_TECH_RADIO_SI470X	0xa155
 
@@ -184,11 +188,18 @@
 #define USB_DEVICE_ID_APPLE_IRCONTROL4	0x8242
 #define USB_DEVICE_ID_APPLE_IRCONTROL5	0x8243
 #define USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_2021   0x029c
+#define USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_2024   0x0320
 #define USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_FINGERPRINT_2021   0x029a
 #define USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_NUMPAD_2021   0x029f
 #define USB_DEVICE_ID_APPLE_TOUCHBAR_BACKLIGHT 0x8102
 #define USB_DEVICE_ID_APPLE_TOUCHBAR_DISPLAY 0x8302
 
+#define USB_VENDOR_ID_ASETEK			0x2433
+#define USB_DEVICE_ID_ASETEK_INVICTA		0xf300
+#define USB_DEVICE_ID_ASETEK_FORTE		0xf301
+#define USB_DEVICE_ID_ASETEK_LA_PRIMA		0xf303
+#define USB_DEVICE_ID_ASETEK_TONY_KANAAN	0xf306
+
 #define USB_VENDOR_ID_ASUS		0x0486
 #define USB_DEVICE_ID_ASUS_T91MT	0x0185
 #define USB_DEVICE_ID_ASUSTEK_MULTITOUCH_YFO	0x0186
@@ -261,6 +272,10 @@
 #define USB_DEVICE_ID_BTC_EMPREX_REMOTE	0x5578
 #define USB_DEVICE_ID_BTC_EMPREX_REMOTE_2	0x5577
 
+#define USB_VENDOR_ID_CAMMUS		0x3416
+#define USB_DEVICE_ID_CAMMUS_C5		0x0301
+#define USB_DEVICE_ID_CAMMUS_C12	0x0302
+
 #define USB_VENDOR_ID_CANDO		0x2087
 #define USB_DEVICE_ID_CANDO_PIXCIR_MULTI_TOUCH 0x0703
 #define USB_DEVICE_ID_CANDO_MULTI_TOUCH	0x0a01
@@ -296,6 +311,8 @@
 #define USB_DEVICE_ID_ASUS_AK1D		0x1125
 #define USB_DEVICE_ID_CHICONY_TOSHIBA_WT10A	0x1408
 #define USB_DEVICE_ID_CHICONY_ACER_SWITCH12	0x1421
+#define USB_DEVICE_ID_CHICONY_HP_5MP_CAMERA	0xb824
+#define USB_DEVICE_ID_CHICONY_HP_5MP_CAMERA2	0xb82c
 
 #define USB_VENDOR_ID_CHUNGHWAT		0x2247
 #define USB_DEVICE_ID_CHUNGHWAT_MULTITOUCH	0x0001
@@ -452,6 +469,11 @@
 #define USB_VENDOR_ID_EVISION           0x320f
 #define USB_DEVICE_ID_EVISION_ICL01     0x5041
 
+#define USB_VENDOR_ID_FFBEAST		0x045b
+#define USB_DEVICE_ID_FFBEAST_JOYSTICK	0x58f9
+#define USB_DEVICE_ID_FFBEAST_RUDDER	0x5968
+#define USB_DEVICE_ID_FFBEAST_WHEEL	0x59d7
+
 #define USB_VENDOR_ID_FLATFROG		0x25b5
 #define USB_DEVICE_ID_MULTITOUCH_3200	0x0002
 
@@ -506,7 +528,6 @@
 #define USB_DEVICE_ID_GENERAL_TOUCH_WIN8_PIT_E100 0xe100
 
 #define I2C_VENDOR_ID_GOODIX		0x27c6
-#define I2C_DEVICE_ID_GOODIX_01E0	0x01e0
 #define I2C_DEVICE_ID_GOODIX_01E8	0x01e8
 #define I2C_DEVICE_ID_GOODIX_01E9	0x01e9
 #define I2C_DEVICE_ID_GOODIX_01F0	0x01f0
@@ -795,6 +816,7 @@
 #define USB_DEVICE_ID_LENOVO_TPPRODOCK	0x6067
 #define USB_DEVICE_ID_LENOVO_X1_COVER	0x6085
 #define USB_DEVICE_ID_LENOVO_X1_TAB	0x60a3
+#define USB_DEVICE_ID_LENOVO_X1_TAB2	0x60a4
 #define USB_DEVICE_ID_LENOVO_X1_TAB3	0x60b5
 #define USB_DEVICE_ID_LENOVO_X12_TAB	0x60fe
 #define USB_DEVICE_ID_LENOVO_X12_TAB2	0x61ae
@@ -813,6 +835,13 @@
 #define I2C_DEVICE_ID_LG_8001		0x8001
 #define I2C_DEVICE_ID_LG_7010		0x7010
 
+#define USB_VENDOR_ID_LITE_STAR		0x11ff
+#define USB_DEVICE_ID_PXN_V10		0x3245
+#define USB_DEVICE_ID_PXN_V12		0x1212
+#define USB_DEVICE_ID_PXN_V12_LITE	0x1112
+#define USB_DEVICE_ID_PXN_V12_LITE_2	0x1211
+#define USB_DEVICE_LITE_STAR_GT987_FF	0x2141
+
 #define USB_VENDOR_ID_LOGITECH		0x046d
 #define USB_DEVICE_ID_LOGITECH_Z_10_SPK	0x0a07
 #define USB_DEVICE_ID_LOGITECH_AUDIOHUB 0x0a0e
@@ -960,6 +989,18 @@
 #define USB_VENDOR_ID_MONTEREY		0x0566
 #define USB_DEVICE_ID_GENIUS_KB29E	0x3004
 
+#define USB_VENDOR_ID_MOZA		0x346e
+#define USB_DEVICE_ID_MOZA_R3		0x0005
+#define USB_DEVICE_ID_MOZA_R3_2		0x0015
+#define USB_DEVICE_ID_MOZA_R5		0x0004
+#define USB_DEVICE_ID_MOZA_R5_2		0x0014
+#define USB_DEVICE_ID_MOZA_R9		0x0002
+#define USB_DEVICE_ID_MOZA_R9_2		0x0012
+#define USB_DEVICE_ID_MOZA_R12		0x0006
+#define USB_DEVICE_ID_MOZA_R12_2	0x0016
+#define USB_DEVICE_ID_MOZA_R16_R21	0x0000
+#define USB_DEVICE_ID_MOZA_R16_R21_2	0x0010
+
 #define USB_VENDOR_ID_MSI		0x1770
 #define USB_DEVICE_ID_MSI_GT683R_LED_PANEL 0xff00
 
@@ -1090,6 +1131,7 @@
 #define USB_DEVICE_ID_QUANTA_OPTICAL_TOUCH_3001		0x3001
 #define USB_DEVICE_ID_QUANTA_OPTICAL_TOUCH_3003		0x3003
 #define USB_DEVICE_ID_QUANTA_OPTICAL_TOUCH_3008		0x3008
+#define USB_DEVICE_ID_QUANTA_HP_5MP_CAMERA_5473		0x5473
 
 #define I2C_VENDOR_ID_RAYDIUM		0x2386
 #define I2C_PRODUCT_ID_RAYDIUM_4B33	0x4b33
@@ -1296,6 +1338,7 @@
 #define USB_VENDOR_ID_TOPRE			0x0853
 #define USB_DEVICE_ID_TOPRE_REALFORCE_R2_108			0x0148
 #define USB_DEVICE_ID_TOPRE_REALFORCE_R2_87			0x0146
+#define USB_DEVICE_ID_TOPRE_REALFORCE_R3S_87			0x0313
 
 #define USB_VENDOR_ID_TOPSEED		0x0766
 #define USB_DEVICE_ID_TOPSEED_CYBERLINK	0x0204
@@ -1369,6 +1412,9 @@
 #define USB_DEVICE_ID_VELLEMAN_K8061_FIRST	0x8061
 #define USB_DEVICE_ID_VELLEMAN_K8061_LAST	0x8068
 
+#define USB_VENDOR_ID_VRS	0x0483
+#define USB_DEVICE_ID_VRS_DFP	0xa355
+
 #define USB_VENDOR_ID_VTL		0x0306
 #define USB_DEVICE_ID_VTL_MULTITOUCH_FF3F	0xff3f
 
@@ -1475,4 +1521,7 @@
 #define USB_VENDOR_ID_SIGNOTEC			0x2133
 #define USB_DEVICE_ID_SIGNOTEC_VIEWSONIC_PD1011	0x0018
 
+#define USB_VENDOR_ID_SMARTLINKTECHNOLOGY              0x4c4a
+#define USB_DEVICE_ID_SMARTLINKTECHNOLOGY_4155         0x4155
+
 #endif
diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c
index fda9dce3da99..9d80635a91eb 100644
--- a/drivers/hid/hid-input.c
+++ b/drivers/hid/hid-input.c
@@ -810,10 +810,23 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel
 			break;
 		}
 
-		if ((usage->hid & 0xf0) == 0x90) { /* SystemControl*/
-			switch (usage->hid & 0xf) {
-			case 0xb: map_key_clear(KEY_DO_NOT_DISTURB); break;
-			default: goto ignore;
+		if ((usage->hid & 0xf0) == 0x90) { /* SystemControl & D-pad */
+			switch (usage->hid) {
+			case HID_GD_UP:	   usage->hat_dir = 1; break;
+			case HID_GD_DOWN:  usage->hat_dir = 5; break;
+			case HID_GD_RIGHT: usage->hat_dir = 3; break;
+			case HID_GD_LEFT:  usage->hat_dir = 7; break;
+			case HID_GD_DO_NOT_DISTURB:
+				map_key_clear(KEY_DO_NOT_DISTURB); break;
+			default: goto unknown;
+			}
+
+			if (usage->hid <= HID_GD_LEFT) {
+				if (field->dpad) {
+					map_abs(field->dpad);
+					goto ignore;
+				}
+				map_abs(ABS_HAT0X);
 			}
 			break;
 		}
@@ -844,22 +857,6 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel
 		if (field->application == HID_GD_SYSTEM_CONTROL)
 			goto ignore;
 
-		if ((usage->hid & 0xf0) == 0x90) {	/* D-pad */
-			switch (usage->hid) {
-			case HID_GD_UP:	   usage->hat_dir = 1; break;
-			case HID_GD_DOWN:  usage->hat_dir = 5; break;
-			case HID_GD_RIGHT: usage->hat_dir = 3; break;
-			case HID_GD_LEFT:  usage->hat_dir = 7; break;
-			default: goto unknown;
-			}
-			if (field->dpad) {
-				map_abs(field->dpad);
-				goto ignore;
-			}
-			map_abs(ABS_HAT0X);
-			break;
-		}
-
 		switch (usage->hid) {
 		/* These usage IDs map directly to the usage codes. */
 		case HID_GD_X: case HID_GD_Y: case HID_GD_Z:
diff --git a/drivers/hid/hid-lenovo.c b/drivers/hid/hid-lenovo.c
index f66194fde891..8482852c662d 100644
--- a/drivers/hid/hid-lenovo.c
+++ b/drivers/hid/hid-lenovo.c
@@ -473,6 +473,7 @@ static int lenovo_input_mapping(struct hid_device *hdev,
 		return lenovo_input_mapping_tp10_ultrabook_kbd(hdev, hi, field,
 							       usage, bit, max);
 	case USB_DEVICE_ID_LENOVO_X1_TAB:
+	case USB_DEVICE_ID_LENOVO_X1_TAB2:
 	case USB_DEVICE_ID_LENOVO_X1_TAB3:
 		return lenovo_input_mapping_x1_tab_kbd(hdev, hi, field, usage, bit, max);
 	default:
@@ -529,11 +530,14 @@ static void lenovo_features_set_cptkbd(struct hid_device *hdev)
 
 	/*
 	 * Tell the keyboard a driver understands it, and turn F7, F9, F11 into
-	 * regular keys
+	 * regular keys (Compact only)
 	 */
-	ret = lenovo_send_cmd_cptkbd(hdev, 0x01, 0x03);
-	if (ret)
-		hid_warn(hdev, "Failed to switch F7/9/11 mode: %d\n", ret);
+	if (hdev->product == USB_DEVICE_ID_LENOVO_CUSBKBD ||
+	    hdev->product == USB_DEVICE_ID_LENOVO_CBTKBD) {
+		ret = lenovo_send_cmd_cptkbd(hdev, 0x01, 0x03);
+		if (ret)
+			hid_warn(hdev, "Failed to switch F7/9/11 mode: %d\n", ret);
+	}
 
 	/* Switch middle button to native mode */
 	ret = lenovo_send_cmd_cptkbd(hdev, 0x09, 0x01);
@@ -584,6 +588,7 @@ static ssize_t attr_fn_lock_store(struct device *dev,
 		break;
 	case USB_DEVICE_ID_LENOVO_TP10UBKBD:
 	case USB_DEVICE_ID_LENOVO_X1_TAB:
+	case USB_DEVICE_ID_LENOVO_X1_TAB2:
 	case USB_DEVICE_ID_LENOVO_X1_TAB3:
 		ret = lenovo_led_set_tp10ubkbd(hdev, TP10UBKBD_FN_LOCK_LED, value);
 		if (ret)
@@ -778,6 +783,7 @@ static int lenovo_event(struct hid_device *hdev, struct hid_field *field,
 		return lenovo_event_cptkbd(hdev, field, usage, value);
 	case USB_DEVICE_ID_LENOVO_TP10UBKBD:
 	case USB_DEVICE_ID_LENOVO_X1_TAB:
+	case USB_DEVICE_ID_LENOVO_X1_TAB2:
 	case USB_DEVICE_ID_LENOVO_X1_TAB3:
 		return lenovo_event_tp10ubkbd(hdev, field, usage, value);
 	default:
@@ -1059,6 +1065,7 @@ static int lenovo_led_brightness_set(struct led_classdev *led_cdev,
 		break;
 	case USB_DEVICE_ID_LENOVO_TP10UBKBD:
 	case USB_DEVICE_ID_LENOVO_X1_TAB:
+	case USB_DEVICE_ID_LENOVO_X1_TAB2:
 	case USB_DEVICE_ID_LENOVO_X1_TAB3:
 		ret = lenovo_led_set_tp10ubkbd(hdev, tp10ubkbd_led[led_nr], value);
 		break;
@@ -1290,6 +1297,7 @@ static int lenovo_probe(struct hid_device *hdev,
 		break;
 	case USB_DEVICE_ID_LENOVO_TP10UBKBD:
 	case USB_DEVICE_ID_LENOVO_X1_TAB:
+	case USB_DEVICE_ID_LENOVO_X1_TAB2:
 	case USB_DEVICE_ID_LENOVO_X1_TAB3:
 		ret = lenovo_probe_tp10ubkbd(hdev);
 		break;
@@ -1377,6 +1385,7 @@ static void lenovo_remove(struct hid_device *hdev)
 		break;
 	case USB_DEVICE_ID_LENOVO_TP10UBKBD:
 	case USB_DEVICE_ID_LENOVO_X1_TAB:
+	case USB_DEVICE_ID_LENOVO_X1_TAB2:
 	case USB_DEVICE_ID_LENOVO_X1_TAB3:
 		lenovo_remove_tp10ubkbd(hdev);
 		break;
@@ -1428,6 +1437,8 @@ static const struct hid_device_id lenovo_devices[] = {
 	{ HID_DEVICE(BUS_USB, HID_GROUP_GENERIC,
 		     USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_X1_TAB) },
 	{ HID_DEVICE(BUS_USB, HID_GROUP_GENERIC,
+		     USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_X1_TAB2) },
+	{ HID_DEVICE(BUS_USB, HID_GROUP_GENERIC,
 		     USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_X1_TAB3) },
 	{ }
 };
diff --git a/drivers/hid/hid-magicmouse.c b/drivers/hid/hid-magicmouse.c
index ec110dea8772..542b3e86d56f 100644
--- a/drivers/hid/hid-magicmouse.c
+++ b/drivers/hid/hid-magicmouse.c
@@ -775,16 +775,30 @@ static void magicmouse_enable_mt_work(struct work_struct *work)
 		hid_err(msc->hdev, "unable to request touch data (%d)\n", ret);
 }
 
+static bool is_usb_magicmouse2(__u32 vendor, __u32 product)
+{
+	if (vendor != USB_VENDOR_ID_APPLE)
+		return false;
+	return product == USB_DEVICE_ID_APPLE_MAGICMOUSE2;
+}
+
+static bool is_usb_magictrackpad2(__u32 vendor, __u32 product)
+{
+	if (vendor != USB_VENDOR_ID_APPLE)
+		return false;
+	return product == USB_DEVICE_ID_APPLE_MAGICTRACKPAD2 ||
+	       product == USB_DEVICE_ID_APPLE_MAGICTRACKPAD2_USBC;
+}
+
 static int magicmouse_fetch_battery(struct hid_device *hdev)
 {
 #ifdef CONFIG_HID_BATTERY_STRENGTH
 	struct hid_report_enum *report_enum;
 	struct hid_report *report;
 
-	if (!hdev->battery || hdev->vendor != USB_VENDOR_ID_APPLE ||
-	    (hdev->product != USB_DEVICE_ID_APPLE_MAGICMOUSE2 &&
-	     hdev->product != USB_DEVICE_ID_APPLE_MAGICTRACKPAD2 &&
-	     hdev->product != USB_DEVICE_ID_APPLE_MAGICTRACKPAD2_USBC))
+	if (!hdev->battery ||
+	    (!is_usb_magicmouse2(hdev->vendor, hdev->product) &&
+	     !is_usb_magictrackpad2(hdev->vendor, hdev->product)))
 		return -1;
 
 	report_enum = &hdev->report_enum[hdev->battery_report_type];
@@ -846,16 +860,17 @@ static int magicmouse_probe(struct hid_device *hdev,
 		return ret;
 	}
 
-	timer_setup(&msc->battery_timer, magicmouse_battery_timer_tick, 0);
-	mod_timer(&msc->battery_timer,
-		  jiffies + msecs_to_jiffies(USB_BATTERY_TIMEOUT_MS));
-	magicmouse_fetch_battery(hdev);
+	if (is_usb_magicmouse2(id->vendor, id->product) ||
+	    is_usb_magictrackpad2(id->vendor, id->product)) {
+		timer_setup(&msc->battery_timer, magicmouse_battery_timer_tick, 0);
+		mod_timer(&msc->battery_timer,
+			  jiffies + msecs_to_jiffies(USB_BATTERY_TIMEOUT_MS));
+		magicmouse_fetch_battery(hdev);
+	}
 
-	if (id->vendor == USB_VENDOR_ID_APPLE &&
-	    (id->product == USB_DEVICE_ID_APPLE_MAGICMOUSE2 ||
-	     ((id->product == USB_DEVICE_ID_APPLE_MAGICTRACKPAD2 ||
-	       id->product == USB_DEVICE_ID_APPLE_MAGICTRACKPAD2_USBC) &&
-	      hdev->type != HID_TYPE_USBMOUSE)))
+	if (is_usb_magicmouse2(id->vendor, id->product) ||
+	    (is_usb_magictrackpad2(id->vendor, id->product) &&
+	     hdev->type != HID_TYPE_USBMOUSE))
 		return 0;
 
 	if (!msc->input) {
@@ -911,7 +926,10 @@ static int magicmouse_probe(struct hid_device *hdev,
 
 	return 0;
 err_stop_hw:
-	del_timer_sync(&msc->battery_timer);
+	if (is_usb_magicmouse2(id->vendor, id->product) ||
+	    is_usb_magictrackpad2(id->vendor, id->product))
+		del_timer_sync(&msc->battery_timer);
+
 	hid_hw_stop(hdev);
 	return ret;
 }
@@ -922,7 +940,9 @@ static void magicmouse_remove(struct hid_device *hdev)
 
 	if (msc) {
 		cancel_delayed_work_sync(&msc->work);
-		del_timer_sync(&msc->battery_timer);
+		if (is_usb_magicmouse2(hdev->vendor, hdev->product) ||
+		    is_usb_magictrackpad2(hdev->vendor, hdev->product))
+			del_timer_sync(&msc->battery_timer);
 	}
 
 	hid_hw_stop(hdev);
@@ -939,10 +959,8 @@ static const __u8 *magicmouse_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 	 *   0x05, 0x01,       // Usage Page (Generic Desktop)        0
 	 *   0x09, 0x02,       // Usage (Mouse)                       2
 	 */
-	if (hdev->vendor == USB_VENDOR_ID_APPLE &&
-	    (hdev->product == USB_DEVICE_ID_APPLE_MAGICMOUSE2 ||
-	     hdev->product == USB_DEVICE_ID_APPLE_MAGICTRACKPAD2 ||
-	     hdev->product == USB_DEVICE_ID_APPLE_MAGICTRACKPAD2_USBC) &&
+	if ((is_usb_magicmouse2(hdev->vendor, hdev->product) ||
+	     is_usb_magictrackpad2(hdev->vendor, hdev->product)) &&
 	    *rsize == 83 && rdesc[46] == 0x84 && rdesc[58] == 0x85) {
 		hid_info(hdev,
 			 "fixing up magicmouse battery report descriptor\n");
diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c
index e936019d21fe..641292cfdaa6 100644
--- a/drivers/hid/hid-multitouch.c
+++ b/drivers/hid/hid-multitouch.c
@@ -1452,8 +1452,7 @@ static const __u8 *mt_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 {
 	if (hdev->vendor == I2C_VENDOR_ID_GOODIX &&
 	    (hdev->product == I2C_DEVICE_ID_GOODIX_01E8 ||
-	     hdev->product == I2C_DEVICE_ID_GOODIX_01E9 ||
-		 hdev->product == I2C_DEVICE_ID_GOODIX_01E0)) {
+	     hdev->product == I2C_DEVICE_ID_GOODIX_01E9)) {
 		if (rdesc[607] == 0x15) {
 			rdesc[607] = 0x25;
 			dev_info(
@@ -1674,9 +1673,12 @@ static int mt_input_configured(struct hid_device *hdev, struct hid_input *hi)
 		break;
 	}
 
-	if (suffix)
+	if (suffix) {
 		hi->input->name = devm_kasprintf(&hdev->dev, GFP_KERNEL,
 						 "%s %s", hdev->name, suffix);
+		if (!hi->input->name)
+			return -ENOMEM;
+	}
 
 	return 0;
 }
@@ -2080,9 +2082,6 @@ static const struct hid_device_id mt_devices[] = {
 	{ .driver_data = MT_CLS_WIN_8_FORCE_MULTI_INPUT_NSMU,
 	  HID_DEVICE(BUS_I2C, HID_GROUP_ANY, I2C_VENDOR_ID_GOODIX,
 		     I2C_DEVICE_ID_GOODIX_01E9) },
-	{ .driver_data = MT_CLS_WIN_8_FORCE_MULTI_INPUT_NSMU,
-	  HID_DEVICE(BUS_I2C, HID_GROUP_ANY, I2C_VENDOR_ID_GOODIX,
-		     I2C_DEVICE_ID_GOODIX_01E0) },
 
 	/* GoodTouch panels */
 	{ .driver_data = MT_CLS_NSMU,
@@ -2117,12 +2116,18 @@ static const struct hid_device_id mt_devices[] = {
 		HID_DEVICE(BUS_I2C, HID_GROUP_GENERIC,
 			USB_VENDOR_ID_LG, I2C_DEVICE_ID_LG_7010) },
 
-	/* Lenovo X1 TAB Gen 2 */
+	/* Lenovo X1 TAB Gen 1 */
 	{ .driver_data = MT_CLS_WIN_8_FORCE_MULTI_INPUT,
 		HID_DEVICE(BUS_USB, HID_GROUP_MULTITOUCH_WIN_8,
 			   USB_VENDOR_ID_LENOVO,
 			   USB_DEVICE_ID_LENOVO_X1_TAB) },
 
+	/* Lenovo X1 TAB Gen 2 */
+	{ .driver_data = MT_CLS_WIN_8_FORCE_MULTI_INPUT,
+		HID_DEVICE(BUS_USB, HID_GROUP_MULTITOUCH_WIN_8,
+			   USB_VENDOR_ID_LENOVO,
+			   USB_DEVICE_ID_LENOVO_X1_TAB2) },
+
 	/* Lenovo X1 TAB Gen 3 */
 	{ .driver_data = MT_CLS_WIN_8_FORCE_MULTI_INPUT,
 		HID_DEVICE(BUS_USB, HID_GROUP_MULTITOUCH_WIN_8,
@@ -2312,6 +2317,11 @@ static const struct hid_device_id mt_devices[] = {
 		HID_DEVICE(HID_BUS_ANY, HID_GROUP_ANY, USB_VENDOR_ID_SIS_TOUCH,
 			HID_ANY_ID) },
 
+	/* Hantick */
+	{ .driver_data = MT_CLS_NSMU,
+		HID_DEVICE(BUS_I2C, HID_GROUP_MULTITOUCH_WIN_8,
+			   I2C_VENDOR_ID_HANTICK, I2C_PRODUCT_ID_HANTICK_5288) },
+
 	/* Generic MT device */
 	{ HID_DEVICE(HID_BUS_ANY, HID_GROUP_MULTITOUCH, HID_ANY_ID, HID_ANY_ID) },
 
diff --git a/drivers/hid/hid-nintendo.c b/drivers/hid/hid-nintendo.c
index 55153a2f7988..2a3ae1068739 100644
--- a/drivers/hid/hid-nintendo.c
+++ b/drivers/hid/hid-nintendo.c
@@ -308,6 +308,7 @@ enum joycon_ctlr_state {
 	JOYCON_CTLR_STATE_INIT,
 	JOYCON_CTLR_STATE_READ,
 	JOYCON_CTLR_STATE_REMOVED,
+	JOYCON_CTLR_STATE_SUSPENDED,
 };
 
 /* Controller type received as part of device info */
@@ -2754,14 +2755,46 @@ static void nintendo_hid_remove(struct hid_device *hdev)
 
 static int nintendo_hid_resume(struct hid_device *hdev)
 {
-	int ret = joycon_init(hdev);
+	struct joycon_ctlr *ctlr = hid_get_drvdata(hdev);
+	int ret;
+
+	hid_dbg(hdev, "resume\n");
+	if (!joycon_using_usb(ctlr)) {
+		hid_dbg(hdev, "no-op resume for bt ctlr\n");
+		ctlr->ctlr_state = JOYCON_CTLR_STATE_READ;
+		return 0;
+	}
 
+	ret = joycon_init(hdev);
 	if (ret)
-		hid_err(hdev, "Failed to restore controller after resume");
+		hid_err(hdev,
+			"Failed to restore controller after resume: %d\n",
+			ret);
+	else
+		ctlr->ctlr_state = JOYCON_CTLR_STATE_READ;
 
 	return ret;
 }
 
+static int nintendo_hid_suspend(struct hid_device *hdev, pm_message_t message)
+{
+	struct joycon_ctlr *ctlr = hid_get_drvdata(hdev);
+
+	hid_dbg(hdev, "suspend: %d\n", message.event);
+	/*
+	 * Avoid any blocking loops in suspend/resume transitions.
+	 *
+	 * joycon_enforce_subcmd_rate() can result in repeated retries if for
+	 * whatever reason the controller stops providing input reports.
+	 *
+	 * This has been observed with bluetooth controllers which lose
+	 * connectivity prior to suspend (but not long enough to result in
+	 * complete disconnection).
+	 */
+	ctlr->ctlr_state = JOYCON_CTLR_STATE_SUSPENDED;
+	return 0;
+}
+
 #endif
 
 static const struct hid_device_id nintendo_hid_devices[] = {
@@ -2800,6 +2833,7 @@ static struct hid_driver nintendo_hid_driver = {
 
 #ifdef CONFIG_PM
 	.resume		= nintendo_hid_resume,
+	.suspend	= nintendo_hid_suspend,
 #endif
 };
 static int __init nintendo_init(void)
diff --git a/drivers/hid/hid-plantronics.c b/drivers/hid/hid-plantronics.c
index 25cfd964dc25..acb9eb18f7cc 100644
--- a/drivers/hid/hid-plantronics.c
+++ b/drivers/hid/hid-plantronics.c
@@ -6,9 +6,6 @@
  *  Copyright (c) 2015-2018 Terry Junge <terry.junge@plantronics.com>
  */
 
-/*
- */
-
 #include "hid-ids.h"
 
 #include <linux/hid.h>
@@ -23,30 +20,28 @@
 
 #define PLT_VOL_UP		0x00b1
 #define PLT_VOL_DOWN		0x00b2
+#define PLT_MIC_MUTE		0x00b5
 
 #define PLT1_VOL_UP		(PLT_HID_1_0_PAGE | PLT_VOL_UP)
 #define PLT1_VOL_DOWN		(PLT_HID_1_0_PAGE | PLT_VOL_DOWN)
+#define PLT1_MIC_MUTE		(PLT_HID_1_0_PAGE | PLT_MIC_MUTE)
 #define PLT2_VOL_UP		(PLT_HID_2_0_PAGE | PLT_VOL_UP)
 #define PLT2_VOL_DOWN		(PLT_HID_2_0_PAGE | PLT_VOL_DOWN)
+#define PLT2_MIC_MUTE		(PLT_HID_2_0_PAGE | PLT_MIC_MUTE)
+#define HID_TELEPHONY_MUTE	(HID_UP_TELEPHONY | 0x2f)
+#define HID_CONSUMER_MUTE	(HID_UP_CONSUMER | 0xe2)
 
 #define PLT_DA60		0xda60
 #define PLT_BT300_MIN		0x0413
 #define PLT_BT300_MAX		0x0418
 
-
-#define PLT_ALLOW_CONSUMER (field->application == HID_CP_CONSUMERCONTROL && \
-			    (usage->hid & HID_USAGE_PAGE) == HID_UP_CONSUMER)
-
-#define PLT_QUIRK_DOUBLE_VOLUME_KEYS BIT(0)
-#define PLT_QUIRK_FOLLOWED_OPPOSITE_VOLUME_KEYS BIT(1)
-
 #define PLT_DOUBLE_KEY_TIMEOUT 5 /* ms */
-#define PLT_FOLLOWED_OPPOSITE_KEY_TIMEOUT 220 /* ms */
 
 struct plt_drv_data {
 	unsigned long device_type;
-	unsigned long last_volume_key_ts;
-	u32 quirks;
+	unsigned long last_key_ts;
+	unsigned long double_key_to;
+	__u16 last_key;
 };
 
 static int plantronics_input_mapping(struct hid_device *hdev,
@@ -58,34 +53,43 @@ static int plantronics_input_mapping(struct hid_device *hdev,
 	unsigned short mapped_key;
 	struct plt_drv_data *drv_data = hid_get_drvdata(hdev);
 	unsigned long plt_type = drv_data->device_type;
+	int allow_mute = usage->hid == HID_TELEPHONY_MUTE;
+	int allow_consumer = field->application == HID_CP_CONSUMERCONTROL &&
+			(usage->hid & HID_USAGE_PAGE) == HID_UP_CONSUMER &&
+			usage->hid != HID_CONSUMER_MUTE;
 
 	/* special case for PTT products */
 	if (field->application == HID_GD_JOYSTICK)
 		goto defaulted;
 
-	/* handle volume up/down mapping */
 	/* non-standard types or multi-HID interfaces - plt_type is PID */
 	if (!(plt_type & HID_USAGE_PAGE)) {
 		switch (plt_type) {
 		case PLT_DA60:
-			if (PLT_ALLOW_CONSUMER)
+			if (allow_consumer)
 				goto defaulted;
-			goto ignored;
+			if (usage->hid == HID_CONSUMER_MUTE) {
+				mapped_key = KEY_MICMUTE;
+				goto mapped;
+			}
+			break;
 		default:
-			if (PLT_ALLOW_CONSUMER)
+			if (allow_consumer || allow_mute)
 				goto defaulted;
 		}
+		goto ignored;
 	}
-	/* handle standard types - plt_type is 0xffa0uuuu or 0xffa2uuuu */
-	/* 'basic telephony compliant' - allow default consumer page map */
-	else if ((plt_type & HID_USAGE) >= PLT_BASIC_TELEPHONY &&
-		 (plt_type & HID_USAGE) != PLT_BASIC_EXCEPTION) {
-		if (PLT_ALLOW_CONSUMER)
-			goto defaulted;
-	}
-	/* not 'basic telephony' - apply legacy mapping */
-	/* only map if the field is in the device's primary vendor page */
-	else if (!((field->application ^ plt_type) & HID_USAGE_PAGE)) {
+
+	/* handle standard consumer control mapping */
+	/* and standard telephony mic mute mapping */
+	if (allow_consumer || allow_mute)
+		goto defaulted;
+
+	/* handle vendor unique types - plt_type is 0xffa0uuuu or 0xffa2uuuu */
+	/* if not 'basic telephony compliant' - map vendor unique controls */
+	if (!((plt_type & HID_USAGE) >= PLT_BASIC_TELEPHONY &&
+	      (plt_type & HID_USAGE) != PLT_BASIC_EXCEPTION) &&
+	      !((field->application ^ plt_type) & HID_USAGE_PAGE))
 		switch (usage->hid) {
 		case PLT1_VOL_UP:
 		case PLT2_VOL_UP:
@@ -95,8 +99,11 @@ static int plantronics_input_mapping(struct hid_device *hdev,
 		case PLT2_VOL_DOWN:
 			mapped_key = KEY_VOLUMEDOWN;
 			goto mapped;
+		case PLT1_MIC_MUTE:
+		case PLT2_MIC_MUTE:
+			mapped_key = KEY_MICMUTE;
+			goto mapped;
 		}
-	}
 
 /*
  * Future mapping of call control or other usages,
@@ -105,6 +112,8 @@ static int plantronics_input_mapping(struct hid_device *hdev,
  */
 
 ignored:
+	hid_dbg(hdev, "usage: %08x (appl: %08x) - ignored\n",
+		usage->hid, field->application);
 	return -1;
 
 defaulted:
@@ -123,38 +132,26 @@ static int plantronics_event(struct hid_device *hdev, struct hid_field *field,
 			     struct hid_usage *usage, __s32 value)
 {
 	struct plt_drv_data *drv_data = hid_get_drvdata(hdev);
+	unsigned long prev_tsto, cur_ts;
+	__u16 prev_key, cur_key;
 
-	if (drv_data->quirks & PLT_QUIRK_DOUBLE_VOLUME_KEYS) {
-		unsigned long prev_ts, cur_ts;
+	/* Usages are filtered in plantronics_usages. */
 
-		/* Usages are filtered in plantronics_usages. */
+	/* HZ too low for ms resolution - double key detection disabled */
+	/* or it is a key release - handle key presses only. */
+	if (!drv_data->double_key_to || !value)
+		return 0;
 
-		if (!value) /* Handle key presses only. */
-			return 0;
+	prev_tsto = drv_data->last_key_ts + drv_data->double_key_to;
+	cur_ts = drv_data->last_key_ts = jiffies;
+	prev_key = drv_data->last_key;
+	cur_key = drv_data->last_key = usage->code;
 
-		prev_ts = drv_data->last_volume_key_ts;
-		cur_ts = jiffies;
-		if (jiffies_to_msecs(cur_ts - prev_ts) <= PLT_DOUBLE_KEY_TIMEOUT)
-			return 1; /* Ignore the repeated key. */
-
-		drv_data->last_volume_key_ts = cur_ts;
+	/* If the same key occurs in <= double_key_to -- ignore it */
+	if (prev_key == cur_key && time_before_eq(cur_ts, prev_tsto)) {
+		hid_dbg(hdev, "double key %d ignored\n", cur_key);
+		return 1; /* Ignore the repeated key. */
 	}
-	if (drv_data->quirks & PLT_QUIRK_FOLLOWED_OPPOSITE_VOLUME_KEYS) {
-		unsigned long prev_ts, cur_ts;
-
-		/* Usages are filtered in plantronics_usages. */
-
-		if (!value) /* Handle key presses only. */
-			return 0;
-
-		prev_ts = drv_data->last_volume_key_ts;
-		cur_ts = jiffies;
-		if (jiffies_to_msecs(cur_ts - prev_ts) <= PLT_FOLLOWED_OPPOSITE_KEY_TIMEOUT)
-			return 1; /* Ignore the followed opposite volume key. */
-
-		drv_data->last_volume_key_ts = cur_ts;
-	}
-
 	return 0;
 }
 
@@ -196,12 +193,16 @@ static int plantronics_probe(struct hid_device *hdev,
 	ret = hid_parse(hdev);
 	if (ret) {
 		hid_err(hdev, "parse failed\n");
-		goto err;
+		return ret;
 	}
 
 	drv_data->device_type = plantronics_device_type(hdev);
-	drv_data->quirks = id->driver_data;
-	drv_data->last_volume_key_ts = jiffies - msecs_to_jiffies(PLT_DOUBLE_KEY_TIMEOUT);
+	drv_data->double_key_to = msecs_to_jiffies(PLT_DOUBLE_KEY_TIMEOUT);
+	drv_data->last_key_ts = jiffies - drv_data->double_key_to;
+
+	/* if HZ does not allow ms resolution - disable double key detection */
+	if (drv_data->double_key_to < PLT_DOUBLE_KEY_TIMEOUT)
+		drv_data->double_key_to = 0;
 
 	hid_set_drvdata(hdev, drv_data);
 
@@ -210,29 +211,10 @@ static int plantronics_probe(struct hid_device *hdev,
 	if (ret)
 		hid_err(hdev, "hw start failed\n");
 
-err:
 	return ret;
 }
 
 static const struct hid_device_id plantronics_devices[] = {
-	{ HID_USB_DEVICE(USB_VENDOR_ID_PLANTRONICS,
-					 USB_DEVICE_ID_PLANTRONICS_BLACKWIRE_3210_SERIES),
-		.driver_data = PLT_QUIRK_DOUBLE_VOLUME_KEYS },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_PLANTRONICS,
-					 USB_DEVICE_ID_PLANTRONICS_BLACKWIRE_3220_SERIES),
-		.driver_data = PLT_QUIRK_DOUBLE_VOLUME_KEYS },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_PLANTRONICS,
-					 USB_DEVICE_ID_PLANTRONICS_BLACKWIRE_3215_SERIES),
-		.driver_data = PLT_QUIRK_DOUBLE_VOLUME_KEYS },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_PLANTRONICS,
-					 USB_DEVICE_ID_PLANTRONICS_BLACKWIRE_3225_SERIES),
-		.driver_data = PLT_QUIRK_DOUBLE_VOLUME_KEYS },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_PLANTRONICS,
-					 USB_DEVICE_ID_PLANTRONICS_BLACKWIRE_3325_SERIES),
-		.driver_data = PLT_QUIRK_FOLLOWED_OPPOSITE_VOLUME_KEYS },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_PLANTRONICS,
-					 USB_DEVICE_ID_PLANTRONICS_ENCOREPRO_500_SERIES),
-		.driver_data = PLT_QUIRK_FOLLOWED_OPPOSITE_VOLUME_KEYS },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_PLANTRONICS, HID_ANY_ID) },
 	{ }
 };
@@ -241,6 +223,14 @@ MODULE_DEVICE_TABLE(hid, plantronics_devices);
 static const struct hid_usage_id plantronics_usages[] = {
 	{ HID_CP_VOLUMEUP, EV_KEY, HID_ANY_ID },
 	{ HID_CP_VOLUMEDOWN, EV_KEY, HID_ANY_ID },
+	{ HID_TELEPHONY_MUTE, EV_KEY, HID_ANY_ID },
+	{ HID_CONSUMER_MUTE, EV_KEY, HID_ANY_ID },
+	{ PLT2_VOL_UP, EV_KEY, HID_ANY_ID },
+	{ PLT2_VOL_DOWN, EV_KEY, HID_ANY_ID },
+	{ PLT2_MIC_MUTE, EV_KEY, HID_ANY_ID },
+	{ PLT1_VOL_UP, EV_KEY, HID_ANY_ID },
+	{ PLT1_VOL_DOWN, EV_KEY, HID_ANY_ID },
+	{ PLT1_MIC_MUTE, EV_KEY, HID_ANY_ID },
 	{ HID_TERMINATOR, HID_TERMINATOR, HID_TERMINATOR }
 };
 
diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c
index e0bbf0c6345d..80372342c176 100644
--- a/drivers/hid/hid-quirks.c
+++ b/drivers/hid/hid-quirks.c
@@ -27,6 +27,8 @@
 static const struct hid_device_id hid_quirks[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_AASHIMA, USB_DEVICE_ID_AASHIMA_GAMEPAD), HID_QUIRK_BADPAD },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_AASHIMA, USB_DEVICE_ID_AASHIMA_PREDATOR), HID_QUIRK_BADPAD },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_ADATA_XPG, USB_VENDOR_ID_ADATA_XPG_WL_GAMING_MOUSE), HID_QUIRK_ALWAYS_POLL },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_ADATA_XPG, USB_VENDOR_ID_ADATA_XPG_WL_GAMING_MOUSE_DONGLE), HID_QUIRK_ALWAYS_POLL },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_AFATECH, USB_DEVICE_ID_AFATECH_AF9016), HID_QUIRK_FULLSPEED_INTERVAL },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_AIREN, USB_DEVICE_ID_AIREN_SLIMPLUS), HID_QUIRK_NOGET },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_AKAI_09E8, USB_DEVICE_ID_AKAI_09E8_MIDIMIX), HID_QUIRK_NO_INIT_REPORTS },
@@ -745,6 +747,8 @@ static const struct hid_device_id hid_ignore_list[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_AVERMEDIA, USB_DEVICE_ID_AVER_FM_MR800) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_AXENTIA, USB_DEVICE_ID_AXENTIA_FM_RADIO) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_BERKSHIRE, USB_DEVICE_ID_BERKSHIRE_PCWD) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_CHICONY, USB_DEVICE_ID_CHICONY_HP_5MP_CAMERA) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_CHICONY, USB_DEVICE_ID_CHICONY_HP_5MP_CAMERA2) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_CIDC, 0x0103) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_CYGNAL, USB_DEVICE_ID_CYGNAL_RADIO_SI470X) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_CYGNAL, USB_DEVICE_ID_CYGNAL_RADIO_SI4713) },
@@ -891,6 +895,8 @@ static const struct hid_device_id hid_ignore_list[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_DPAD) },
 #endif
 	{ HID_USB_DEVICE(USB_VENDOR_ID_YEALINK, USB_DEVICE_ID_YEALINK_P1K_P4K_B2K) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_QUANTA, USB_DEVICE_ID_QUANTA_HP_5MP_CAMERA_5473) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_SMARTLINKTECHNOLOGY, USB_DEVICE_ID_SMARTLINKTECHNOLOGY_4155) },
 	{ }
 };
 
diff --git a/drivers/hid/hid-sensor-hub.c b/drivers/hid/hid-sensor-hub.c
index 7bd86eef6ec7..4c94c03cb573 100644
--- a/drivers/hid/hid-sensor-hub.c
+++ b/drivers/hid/hid-sensor-hub.c
@@ -730,23 +730,30 @@ err_stop_hw:
 	return ret;
 }
 
+static int sensor_hub_finalize_pending_fn(struct device *dev, void *data)
+{
+	struct hid_sensor_hub_device *hsdev = dev->platform_data;
+
+	if (hsdev->pending.status)
+		complete(&hsdev->pending.ready);
+
+	return 0;
+}
+
 static void sensor_hub_remove(struct hid_device *hdev)
 {
 	struct sensor_hub_data *data = hid_get_drvdata(hdev);
 	unsigned long flags;
-	int i;
 
 	hid_dbg(hdev, " hardware removed\n");
 	hid_hw_close(hdev);
 	hid_hw_stop(hdev);
+
 	spin_lock_irqsave(&data->lock, flags);
-	for (i = 0; i < data->hid_sensor_client_cnt; ++i) {
-		struct hid_sensor_hub_device *hsdev =
-			data->hid_sensor_hub_client_devs[i].platform_data;
-		if (hsdev->pending.status)
-			complete(&hsdev->pending.ready);
-	}
+	device_for_each_child(&hdev->dev, NULL,
+			      sensor_hub_finalize_pending_fn);
 	spin_unlock_irqrestore(&data->lock, flags);
+
 	mfd_remove_devices(&hdev->dev);
 	mutex_destroy(&data->mutex);
 }
diff --git a/drivers/hid/hid-steam.c b/drivers/hid/hid-steam.c
index bf8b633114be..9de875f27c24 100644
--- a/drivers/hid/hid-steam.c
+++ b/drivers/hid/hid-steam.c
@@ -313,6 +313,7 @@ struct steam_device {
 	u16 rumble_left;
 	u16 rumble_right;
 	unsigned int sensor_timestamp_us;
+	struct work_struct unregister_work;
 };
 
 static int steam_recv_report(struct steam_device *steam,
@@ -1050,10 +1051,10 @@ static void steam_mode_switch_cb(struct work_struct *work)
 							struct steam_device, mode_switch);
 	unsigned long flags;
 	bool client_opened;
-	steam->gamepad_mode = !steam->gamepad_mode;
 	if (!lizard_mode)
 		return;
 
+	steam->gamepad_mode = !steam->gamepad_mode;
 	if (steam->gamepad_mode)
 		steam_set_lizard_mode(steam, false);
 	else {
@@ -1072,6 +1073,31 @@ static void steam_mode_switch_cb(struct work_struct *work)
 	}
 }
 
+static void steam_work_unregister_cb(struct work_struct *work)
+{
+	struct steam_device *steam = container_of(work, struct steam_device,
+							unregister_work);
+	unsigned long flags;
+	bool connected;
+	bool opened;
+
+	spin_lock_irqsave(&steam->lock, flags);
+	opened = steam->client_opened;
+	connected = steam->connected;
+	spin_unlock_irqrestore(&steam->lock, flags);
+
+	if (connected) {
+		if (opened) {
+			steam_sensors_unregister(steam);
+			steam_input_unregister(steam);
+		} else {
+			steam_set_lizard_mode(steam, lizard_mode);
+			steam_input_register(steam);
+			steam_sensors_register(steam);
+		}
+	}
+}
+
 static bool steam_is_valve_interface(struct hid_device *hdev)
 {
 	struct hid_report_enum *rep_enum;
@@ -1117,8 +1143,7 @@ static int steam_client_ll_open(struct hid_device *hdev)
 	steam->client_opened++;
 	spin_unlock_irqrestore(&steam->lock, flags);
 
-	steam_sensors_unregister(steam);
-	steam_input_unregister(steam);
+	schedule_work(&steam->unregister_work);
 
 	return 0;
 }
@@ -1135,11 +1160,7 @@ static void steam_client_ll_close(struct hid_device *hdev)
 	connected = steam->connected && !steam->client_opened;
 	spin_unlock_irqrestore(&steam->lock, flags);
 
-	if (connected) {
-		steam_set_lizard_mode(steam, lizard_mode);
-		steam_input_register(steam);
-		steam_sensors_register(steam);
-	}
+	schedule_work(&steam->unregister_work);
 }
 
 static int steam_client_ll_raw_request(struct hid_device *hdev,
@@ -1231,6 +1252,7 @@ static int steam_probe(struct hid_device *hdev,
 	INIT_LIST_HEAD(&steam->list);
 	INIT_WORK(&steam->rumble_work, steam_haptic_rumble_cb);
 	steam->sensor_timestamp_us = 0;
+	INIT_WORK(&steam->unregister_work, steam_work_unregister_cb);
 
 	/*
 	 * With the real steam controller interface, do not connect hidraw.
@@ -1291,6 +1313,7 @@ err_cancel_work:
 	cancel_work_sync(&steam->work_connect);
 	cancel_delayed_work_sync(&steam->mode_switch);
 	cancel_work_sync(&steam->rumble_work);
+	cancel_work_sync(&steam->unregister_work);
 
 	return ret;
 }
@@ -1304,9 +1327,11 @@ static void steam_remove(struct hid_device *hdev)
 		return;
 	}
 
+	hid_destroy_device(steam->client_hdev);
 	cancel_delayed_work_sync(&steam->mode_switch);
 	cancel_work_sync(&steam->work_connect);
-	hid_destroy_device(steam->client_hdev);
+	cancel_work_sync(&steam->rumble_work);
+	cancel_work_sync(&steam->unregister_work);
 	steam->client_hdev = NULL;
 	steam->client_opened = 0;
 	if (steam->quirks & STEAM_QUIRK_WIRELESS) {
@@ -1592,13 +1617,13 @@ static void steam_do_deck_input_event(struct steam_device *steam,
 
 	if (!(b9 & BIT(6)) && steam->did_mode_switch) {
 		steam->did_mode_switch = false;
-		cancel_delayed_work_sync(&steam->mode_switch);
+		cancel_delayed_work(&steam->mode_switch);
 	} else if (!steam->client_opened && (b9 & BIT(6)) && !steam->did_mode_switch) {
 		steam->did_mode_switch = true;
 		schedule_delayed_work(&steam->mode_switch, 45 * HZ / 100);
 	}
 
-	if (!steam->gamepad_mode)
+	if (!steam->gamepad_mode && lizard_mode)
 		return;
 
 	lpad_touched = b10 & BIT(3);
@@ -1668,7 +1693,7 @@ static void steam_do_deck_sensors_event(struct steam_device *steam,
 	 */
 	steam->sensor_timestamp_us += 4000;
 
-	if (!steam->gamepad_mode)
+	if (!steam->gamepad_mode && lizard_mode)
 		return;
 
 	input_event(sensors, EV_MSC, MSC_TIMESTAMP, steam->sensor_timestamp_us);
diff --git a/drivers/hid/hid-thrustmaster.c b/drivers/hid/hid-thrustmaster.c
index cf1679b0d4fb..0bf70664c35e 100644
--- a/drivers/hid/hid-thrustmaster.c
+++ b/drivers/hid/hid-thrustmaster.c
@@ -170,6 +170,15 @@ static void thrustmaster_interrupts(struct hid_device *hdev)
 	ep = &usbif->cur_altsetting->endpoint[1];
 	b_ep = ep->desc.bEndpointAddress;
 
+	/* Are the expected endpoints present? */
+	u8 ep_addr[2] = {b_ep, 0};
+
+	if (!usb_check_int_endpoints(usbif, ep_addr)) {
+		kfree(send_buf);
+		hid_err(hdev, "Unexpected non-int endpoint\n");
+		return;
+	}
+
 	for (i = 0; i < ARRAY_SIZE(setup_arr); ++i) {
 		memcpy(send_buf, setup_arr[i], setup_arr_sizes[i]);
 
diff --git a/drivers/hid/hid-topre.c b/drivers/hid/hid-topre.c
index 848361f6225d..ccedf8721722 100644
--- a/drivers/hid/hid-topre.c
+++ b/drivers/hid/hid-topre.c
@@ -29,6 +29,11 @@ static const __u8 *topre_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 		hid_info(hdev,
 			"fixing up Topre REALFORCE keyboard report descriptor\n");
 		rdesc[72] = 0x02;
+	} else if (*rsize >= 106 && rdesc[28] == 0x29 && rdesc[29] == 0xe7 &&
+				    rdesc[30] == 0x81 && rdesc[31] == 0x00) {
+		hid_info(hdev,
+			"fixing up Topre REALFORCE keyboard report descriptor\n");
+		rdesc[31] = 0x02;
 	}
 	return rdesc;
 }
@@ -38,6 +43,8 @@ static const struct hid_device_id topre_id_table[] = {
 			 USB_DEVICE_ID_TOPRE_REALFORCE_R2_108) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_TOPRE,
 			 USB_DEVICE_ID_TOPRE_REALFORCE_R2_87) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_TOPRE,
+			 USB_DEVICE_ID_TOPRE_REALFORCE_R3S_87) },
 	{ }
 };
 MODULE_DEVICE_TABLE(hid, topre_id_table);
diff --git a/drivers/hid/hid-uclogic-core.c b/drivers/hid/hid-uclogic-core.c
index d8008933c052..321c43fb06ae 100644
--- a/drivers/hid/hid-uclogic-core.c
+++ b/drivers/hid/hid-uclogic-core.c
@@ -142,11 +142,12 @@ static int uclogic_input_configured(struct hid_device *hdev,
 			suffix = "System Control";
 			break;
 		}
-	}
-
-	if (suffix)
+	} else {
 		hi->input->name = devm_kasprintf(&hdev->dev, GFP_KERNEL,
 						 "%s %s", hdev->name, suffix);
+		if (!hi->input->name)
+			return -ENOMEM;
+	}
 
 	return 0;
 }
diff --git a/drivers/hid/hid-universal-pidff.c b/drivers/hid/hid-universal-pidff.c
new file mode 100644
index 000000000000..5b89ec7b5c26
--- /dev/null
+++ b/drivers/hid/hid-universal-pidff.c
@@ -0,0 +1,202 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * HID UNIVERSAL PIDFF
+ * hid-pidff wrapper for PID-enabled devices
+ * Handles device reports, quirks and extends usable button range
+ *
+ * Copyright (c) 2024, 2025 Oleg Makarenko
+ * Copyright (c) 2024, 2025 Tomasz Pakuła
+ */
+
+#include <linux/device.h>
+#include <linux/hid.h>
+#include <linux/module.h>
+#include <linux/input-event-codes.h>
+#include "hid-ids.h"
+#include "usbhid/hid-pidff.h"
+
+#define JOY_RANGE (BTN_DEAD - BTN_JOYSTICK + 1)
+
+/*
+ * Map buttons manually to extend the default joystick button limit
+ */
+static int universal_pidff_input_mapping(struct hid_device *hdev,
+	struct hid_input *hi, struct hid_field *field, struct hid_usage *usage,
+	unsigned long **bit, int *max)
+{
+	if ((usage->hid & HID_USAGE_PAGE) != HID_UP_BUTTON)
+		return 0;
+
+	if (field->application != HID_GD_JOYSTICK)
+		return 0;
+
+	int button = ((usage->hid - 1) & HID_USAGE);
+	int code = button + BTN_JOYSTICK;
+
+	/* Detect the end of JOYSTICK buttons range */
+	if (code > BTN_DEAD)
+		code = button + KEY_NEXT_FAVORITE - JOY_RANGE;
+
+	/*
+	 * Map overflowing buttons to KEY_RESERVED to not ignore
+	 * them and let them still trigger MSC_SCAN
+	 */
+	if (code > KEY_MAX)
+		code = KEY_RESERVED;
+
+	hid_map_usage(hi, usage, bit, max, EV_KEY, code);
+	hid_dbg(hdev, "Button %d: usage %d", button, code);
+	return 1;
+}
+
+/*
+ * Check if the device is PID and initialize it
+ * Add quirks after initialisation
+ */
+static int universal_pidff_probe(struct hid_device *hdev,
+				 const struct hid_device_id *id)
+{
+	int i, error;
+	error = hid_parse(hdev);
+	if (error) {
+		hid_err(hdev, "HID parse failed\n");
+		goto err;
+	}
+
+	error = hid_hw_start(hdev, HID_CONNECT_DEFAULT & ~HID_CONNECT_FF);
+	if (error) {
+		hid_err(hdev, "HID hw start failed\n");
+		goto err;
+	}
+
+	/* Check if device contains PID usage page */
+	error = 1;
+	for (i = 0; i < hdev->collection_size; i++)
+		if ((hdev->collection[i].usage & HID_USAGE_PAGE) == HID_UP_PID) {
+			error = 0;
+			hid_dbg(hdev, "PID usage page found\n");
+			break;
+		}
+
+	/*
+	 * Do not fail as this might be the second "device"
+	 * just for additional buttons/axes. Exit cleanly if force
+	 * feedback usage page wasn't found (included devices were
+	 * tested and confirmed to be USB PID after all).
+	 */
+	if (error) {
+		hid_dbg(hdev, "PID usage page not found in the descriptor\n");
+		return 0;
+	}
+
+	/* Check if HID_PID support is enabled */
+	int (*init_function)(struct hid_device *, u32);
+	init_function = hid_pidff_init_with_quirks;
+
+	if (!init_function) {
+		hid_warn(hdev, "HID_PID support not enabled!\n");
+		return 0;
+	}
+
+	error = init_function(hdev, id->driver_data);
+	if (error) {
+		hid_warn(hdev, "Error initialising force feedback\n");
+		goto err;
+	}
+
+	hid_info(hdev, "Universal pidff driver loaded sucessfully!");
+
+	return 0;
+err:
+	return error;
+}
+
+static int universal_pidff_input_configured(struct hid_device *hdev,
+					    struct hid_input *hidinput)
+{
+	int axis;
+	struct input_dev *input = hidinput->input;
+
+	if (!input->absinfo)
+		return 0;
+
+	/* Decrease fuzz and deadzone on available axes */
+	for (axis = ABS_X; axis <= ABS_BRAKE; axis++) {
+		if (!test_bit(axis, input->absbit))
+			continue;
+
+		input_set_abs_params(input, axis,
+			input->absinfo[axis].minimum,
+			input->absinfo[axis].maximum,
+			axis == ABS_X ? 0 : 8, 0);
+	}
+
+	/* Remove fuzz and deadzone from the second joystick axis */
+	if (hdev->vendor == USB_VENDOR_ID_FFBEAST &&
+	    hdev->product == USB_DEVICE_ID_FFBEAST_JOYSTICK)
+		input_set_abs_params(input, ABS_Y,
+			input->absinfo[ABS_Y].minimum,
+			input->absinfo[ABS_Y].maximum, 0, 0);
+
+	return 0;
+}
+
+static const struct hid_device_id universal_pidff_devices[] = {
+	{ HID_USB_DEVICE(USB_VENDOR_ID_MOZA, USB_DEVICE_ID_MOZA_R3),
+		.driver_data = HID_PIDFF_QUIRK_FIX_WHEEL_DIRECTION },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_MOZA, USB_DEVICE_ID_MOZA_R3_2),
+		.driver_data = HID_PIDFF_QUIRK_FIX_WHEEL_DIRECTION },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_MOZA, USB_DEVICE_ID_MOZA_R5),
+		.driver_data = HID_PIDFF_QUIRK_FIX_WHEEL_DIRECTION },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_MOZA, USB_DEVICE_ID_MOZA_R5_2),
+		.driver_data = HID_PIDFF_QUIRK_FIX_WHEEL_DIRECTION },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_MOZA, USB_DEVICE_ID_MOZA_R9),
+		.driver_data = HID_PIDFF_QUIRK_FIX_WHEEL_DIRECTION },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_MOZA, USB_DEVICE_ID_MOZA_R9_2),
+		.driver_data = HID_PIDFF_QUIRK_FIX_WHEEL_DIRECTION },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_MOZA, USB_DEVICE_ID_MOZA_R12),
+		.driver_data = HID_PIDFF_QUIRK_FIX_WHEEL_DIRECTION },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_MOZA, USB_DEVICE_ID_MOZA_R12_2),
+		.driver_data = HID_PIDFF_QUIRK_FIX_WHEEL_DIRECTION },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_MOZA, USB_DEVICE_ID_MOZA_R16_R21),
+		.driver_data = HID_PIDFF_QUIRK_FIX_WHEEL_DIRECTION },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_MOZA, USB_DEVICE_ID_MOZA_R16_R21_2),
+		.driver_data = HID_PIDFF_QUIRK_FIX_WHEEL_DIRECTION },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_CAMMUS, USB_DEVICE_ID_CAMMUS_C5) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_CAMMUS, USB_DEVICE_ID_CAMMUS_C12) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_VRS, USB_DEVICE_ID_VRS_DFP),
+		.driver_data = HID_PIDFF_QUIRK_PERMISSIVE_CONTROL },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_FFBEAST, USB_DEVICE_ID_FFBEAST_JOYSTICK), },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_FFBEAST, USB_DEVICE_ID_FFBEAST_RUDDER), },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_FFBEAST, USB_DEVICE_ID_FFBEAST_WHEEL) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_LITE_STAR, USB_DEVICE_ID_PXN_V10),
+		.driver_data = HID_PIDFF_QUIRK_PERIODIC_SINE_ONLY },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_LITE_STAR, USB_DEVICE_ID_PXN_V12),
+		.driver_data = HID_PIDFF_QUIRK_PERIODIC_SINE_ONLY },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_LITE_STAR, USB_DEVICE_ID_PXN_V12_LITE),
+		.driver_data = HID_PIDFF_QUIRK_PERIODIC_SINE_ONLY },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_LITE_STAR, USB_DEVICE_ID_PXN_V12_LITE_2),
+		.driver_data = HID_PIDFF_QUIRK_PERIODIC_SINE_ONLY },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_LITE_STAR, USB_DEVICE_LITE_STAR_GT987_FF),
+		.driver_data = HID_PIDFF_QUIRK_PERIODIC_SINE_ONLY },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_ASETEK, USB_DEVICE_ID_ASETEK_INVICTA) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_ASETEK, USB_DEVICE_ID_ASETEK_FORTE) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_ASETEK, USB_DEVICE_ID_ASETEK_LA_PRIMA) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_ASETEK, USB_DEVICE_ID_ASETEK_TONY_KANAAN) },
+	{ }
+};
+MODULE_DEVICE_TABLE(hid, universal_pidff_devices);
+
+static struct hid_driver universal_pidff = {
+	.name = "hid-universal-pidff",
+	.id_table = universal_pidff_devices,
+	.input_mapping = universal_pidff_input_mapping,
+	.probe = universal_pidff_probe,
+	.input_configured = universal_pidff_input_configured
+};
+module_hid_driver(universal_pidff);
+
+MODULE_DESCRIPTION("Universal driver for USB PID Force Feedback devices");
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Oleg Makarenko <oleg@makarenk.ooo>");
+MODULE_AUTHOR("Tomasz Pakuła <tomasz.pakula.oficjalny@gmail.com>");
diff --git a/drivers/hid/hid-winwing.c b/drivers/hid/hid-winwing.c
index 831b760c66ea..d4afbbd27807 100644
--- a/drivers/hid/hid-winwing.c
+++ b/drivers/hid/hid-winwing.c
@@ -106,6 +106,8 @@ static int winwing_init_led(struct hid_device *hdev,
 						"%s::%s",
 						dev_name(&input->dev),
 						info->led_name);
+		if (!led->cdev.name)
+			return -ENOMEM;
 
 		ret = devm_led_classdev_register(&hdev->dev, &led->cdev);
 		if (ret)
diff --git a/drivers/hid/i2c-hid/i2c-hid-core.c b/drivers/hid/i2c-hid/i2c-hid-core.c
index 4e87380d3edd..bcca89ef7360 100644
--- a/drivers/hid/i2c-hid/i2c-hid-core.c
+++ b/drivers/hid/i2c-hid/i2c-hid-core.c
@@ -284,7 +284,7 @@ static int i2c_hid_get_report(struct i2c_hid *ihid,
 			     ihid->rawbuf, recv_len + sizeof(__le16));
 	if (error) {
 		dev_err(&ihid->client->dev,
-			"failed to set a report to device: %d\n", error);
+			"failed to get a report from device: %d\n", error);
 		return error;
 	}
 
diff --git a/drivers/hid/intel-ish-hid/ipc/hw-ish.h b/drivers/hid/intel-ish-hid/ipc/hw-ish.h
index cdd80c653918..07e90d51f073 100644
--- a/drivers/hid/intel-ish-hid/ipc/hw-ish.h
+++ b/drivers/hid/intel-ish-hid/ipc/hw-ish.h
@@ -36,6 +36,8 @@
 #define PCI_DEVICE_ID_INTEL_ISH_ARL_H		0x7745
 #define PCI_DEVICE_ID_INTEL_ISH_ARL_S		0x7F78
 #define PCI_DEVICE_ID_INTEL_ISH_LNL_M		0xA845
+#define PCI_DEVICE_ID_INTEL_ISH_PTL_H		0xE345
+#define PCI_DEVICE_ID_INTEL_ISH_PTL_P		0xE445
 
 #define	REVISION_ID_CHT_A0	0x6
 #define	REVISION_ID_CHT_Ax_SI	0x0
diff --git a/drivers/hid/intel-ish-hid/ipc/ipc.c b/drivers/hid/intel-ish-hid/ipc/ipc.c
index 3cd53fc80634..4c861119e97a 100644
--- a/drivers/hid/intel-ish-hid/ipc/ipc.c
+++ b/drivers/hid/intel-ish-hid/ipc/ipc.c
@@ -517,6 +517,10 @@ static int ish_fw_reset_handler(struct ishtp_device *dev)
 	/* ISH FW is dead */
 	if (!ish_is_input_ready(dev))
 		return	-EPIPE;
+
+	/* Send clock sync at once after reset */
+	ishtp_dev->prev_sync = 0;
+
 	/*
 	 * Set HOST2ISH.ILUP. Apparently we need this BEFORE sending
 	 * RESET_NOTIFY_ACK - FW will be checking for it
@@ -577,15 +581,14 @@ static void fw_reset_work_fn(struct work_struct *work)
  */
 static void _ish_sync_fw_clock(struct ishtp_device *dev)
 {
-	static unsigned long	prev_sync;
-	uint64_t	usec;
+	struct ipc_time_update_msg time = {};
 
-	if (prev_sync && time_before(jiffies, prev_sync + 20 * HZ))
+	if (dev->prev_sync && time_before(jiffies, dev->prev_sync + 20 * HZ))
 		return;
 
-	prev_sync = jiffies;
-	usec = ktime_to_us(ktime_get_boottime());
-	ipc_send_mng_msg(dev, MNG_SYNC_FW_CLOCK, &usec, sizeof(uint64_t));
+	dev->prev_sync = jiffies;
+	/* The fields of time would be updated while sending message */
+	ipc_send_mng_msg(dev, MNG_SYNC_FW_CLOCK, &time, sizeof(time));
 }
 
 /**
diff --git a/drivers/hid/intel-ish-hid/ipc/pci-ish.c b/drivers/hid/intel-ish-hid/ipc/pci-ish.c
index aae0d965b47b..1894743e8802 100644
--- a/drivers/hid/intel-ish-hid/ipc/pci-ish.c
+++ b/drivers/hid/intel-ish-hid/ipc/pci-ish.c
@@ -26,9 +26,11 @@
 enum ishtp_driver_data_index {
 	ISHTP_DRIVER_DATA_NONE,
 	ISHTP_DRIVER_DATA_LNL_M,
+	ISHTP_DRIVER_DATA_PTL,
 };
 
 #define ISH_FW_GEN_LNL_M "lnlm"
+#define ISH_FW_GEN_PTL "ptl"
 
 #define ISH_FIRMWARE_PATH(gen) "intel/ish/ish_" gen ".bin"
 #define ISH_FIRMWARE_PATH_ALL "intel/ish/ish_*.bin"
@@ -37,6 +39,9 @@ static struct ishtp_driver_data ishtp_driver_data[] = {
 	[ISHTP_DRIVER_DATA_LNL_M] = {
 		.fw_generation = ISH_FW_GEN_LNL_M,
 	},
+	[ISHTP_DRIVER_DATA_PTL] = {
+		.fw_generation = ISH_FW_GEN_PTL,
+	},
 };
 
 static const struct pci_device_id ish_pci_tbl[] = {
@@ -63,6 +68,8 @@ static const struct pci_device_id ish_pci_tbl[] = {
 	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ISH_ARL_H)},
 	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ISH_ARL_S)},
 	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ISH_LNL_M), .driver_data = ISHTP_DRIVER_DATA_LNL_M},
+	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ISH_PTL_H), .driver_data = ISHTP_DRIVER_DATA_PTL},
+	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ISH_PTL_P), .driver_data = ISHTP_DRIVER_DATA_PTL},
 	{}
 };
 MODULE_DEVICE_TABLE(pci, ish_pci_tbl);
diff --git a/drivers/hid/intel-ish-hid/ishtp-hid-client.c b/drivers/hid/intel-ish-hid/ishtp-hid-client.c
index fbd4f8ea1951..af6a5afc1a93 100644
--- a/drivers/hid/intel-ish-hid/ishtp-hid-client.c
+++ b/drivers/hid/intel-ish-hid/ishtp-hid-client.c
@@ -833,9 +833,9 @@ static void hid_ishtp_cl_remove(struct ishtp_cl_device *cl_device)
 			hid_ishtp_cl);
 
 	dev_dbg(ishtp_device(cl_device), "%s\n", __func__);
-	hid_ishtp_cl_deinit(hid_ishtp_cl);
 	ishtp_put_device(cl_device);
 	ishtp_hid_remove(client_data);
+	hid_ishtp_cl_deinit(hid_ishtp_cl);
 
 	hid_ishtp_cl = NULL;
 
diff --git a/drivers/hid/intel-ish-hid/ishtp-hid.c b/drivers/hid/intel-ish-hid/ishtp-hid.c
index 00c6f0ebf356..be2c62fc8251 100644
--- a/drivers/hid/intel-ish-hid/ishtp-hid.c
+++ b/drivers/hid/intel-ish-hid/ishtp-hid.c
@@ -261,12 +261,14 @@ err_hid_data:
  */
 void ishtp_hid_remove(struct ishtp_cl_data *client_data)
 {
+	void *data;
 	int i;
 
 	for (i = 0; i < client_data->num_hid_devices; ++i) {
 		if (client_data->hid_sensor_hubs[i]) {
-			kfree(client_data->hid_sensor_hubs[i]->driver_data);
+			data = client_data->hid_sensor_hubs[i]->driver_data;
 			hid_destroy_device(client_data->hid_sensor_hubs[i]);
+			kfree(data);
 			client_data->hid_sensor_hubs[i] = NULL;
 		}
 	}
diff --git a/drivers/hid/intel-ish-hid/ishtp/ishtp-dev.h b/drivers/hid/intel-ish-hid/ishtp/ishtp-dev.h
index cdacce0a4c9d..b35afefd036d 100644
--- a/drivers/hid/intel-ish-hid/ishtp/ishtp-dev.h
+++ b/drivers/hid/intel-ish-hid/ishtp/ishtp-dev.h
@@ -242,6 +242,8 @@ struct ishtp_device {
 	unsigned int	ipc_tx_cnt;
 	unsigned long long	ipc_tx_bytes_cnt;
 
+	/* Time of the last clock sync */
+	unsigned long prev_sync;
 	const struct ishtp_hw_ops *ops;
 	size_t	mtu;
 	uint32_t	ishtp_msg_hdr;
diff --git a/drivers/hid/usbhid/hid-core.c b/drivers/hid/usbhid/hid-core.c
index a9e85bdd4cc6..01625dbb28e8 100644
--- a/drivers/hid/usbhid/hid-core.c
+++ b/drivers/hid/usbhid/hid-core.c
@@ -35,6 +35,7 @@
 #include <linux/hid-debug.h>
 #include <linux/hidraw.h>
 #include "usbhid.h"
+#include "hid-pidff.h"
 
 /*
  * Version Information
@@ -983,12 +984,11 @@ static int usbhid_parse(struct hid_device *hid)
 	struct usb_host_interface *interface = intf->cur_altsetting;
 	struct usb_device *dev = interface_to_usbdev (intf);
 	struct hid_descriptor *hdesc;
+	struct hid_class_descriptor *hcdesc;
 	u32 quirks = 0;
 	unsigned int rsize = 0;
 	char *rdesc;
-	int ret, n;
-	int num_descriptors;
-	size_t offset = offsetof(struct hid_descriptor, desc);
+	int ret;
 
 	quirks = hid_lookup_quirk(hid);
 
@@ -1010,20 +1010,19 @@ static int usbhid_parse(struct hid_device *hid)
 		return -ENODEV;
 	}
 
-	if (hdesc->bLength < sizeof(struct hid_descriptor)) {
-		dbg_hid("hid descriptor is too short\n");
+	if (!hdesc->bNumDescriptors ||
+	    hdesc->bLength != sizeof(*hdesc) +
+			      (hdesc->bNumDescriptors - 1) * sizeof(*hcdesc)) {
+		dbg_hid("hid descriptor invalid, bLen=%hhu bNum=%hhu\n",
+			hdesc->bLength, hdesc->bNumDescriptors);
 		return -EINVAL;
 	}
 
 	hid->version = le16_to_cpu(hdesc->bcdHID);
 	hid->country = hdesc->bCountryCode;
 
-	num_descriptors = min_t(int, hdesc->bNumDescriptors,
-	       (hdesc->bLength - offset) / sizeof(struct hid_class_descriptor));
-
-	for (n = 0; n < num_descriptors; n++)
-		if (hdesc->desc[n].bDescriptorType == HID_DT_REPORT)
-			rsize = le16_to_cpu(hdesc->desc[n].wDescriptorLength);
+	if (hdesc->rpt_desc.bDescriptorType == HID_DT_REPORT)
+		rsize = le16_to_cpu(hdesc->rpt_desc.wDescriptorLength);
 
 	if (!rsize || rsize > HID_MAX_DESCRIPTOR_SIZE) {
 		dbg_hid("weird size of report descriptor (%u)\n", rsize);
@@ -1051,6 +1050,11 @@ static int usbhid_parse(struct hid_device *hid)
 		goto err;
 	}
 
+	if (hdesc->bNumDescriptors > 1)
+		hid_warn(intf,
+			"%u unsupported optional hid class descriptors\n",
+			(int)(hdesc->bNumDescriptors - 1));
+
 	hid->quirks |= quirks;
 
 	return 0;
diff --git a/drivers/hid/usbhid/hid-pidff.c b/drivers/hid/usbhid/hid-pidff.c
index 3b4ee21cd811..8dfd2c554a27 100644
--- a/drivers/hid/usbhid/hid-pidff.c
+++ b/drivers/hid/usbhid/hid-pidff.c
@@ -3,27 +3,27 @@
  *  Force feedback driver for USB HID PID compliant devices
  *
  *  Copyright (c) 2005, 2006 Anssi Hannula <anssi.hannula@gmail.com>
+ *  Upgraded 2025 by Oleg Makarenko and Tomasz Pakuła
  */
 
-/*
- */
-
-/* #define DEBUG */
-
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include "hid-pidff.h"
 #include <linux/input.h>
 #include <linux/slab.h>
 #include <linux/usb.h>
-
 #include <linux/hid.h>
+#include <linux/minmax.h>
 
-#include "usbhid.h"
 
 #define	PID_EFFECTS_MAX		64
+#define	PID_INFINITE		U16_MAX
 
-/* Report usage table used to put reports into an array */
+/* Linux Force Feedback API uses miliseconds as time unit */
+#define FF_TIME_EXPONENT	-3
+#define FF_INFINITE		0
 
+/* Report usage table used to put reports into an array */
 #define PID_SET_EFFECT		0
 #define PID_EFFECT_OPERATION	1
 #define PID_DEVICE_GAIN		2
@@ -44,12 +44,19 @@ static const u8 pidff_reports[] = {
 	0x21, 0x77, 0x7d, 0x7f, 0x89, 0x90, 0x96, 0xab,
 	0x5a, 0x5f, 0x6e, 0x73, 0x74
 };
+/*
+ * device_control is really 0x95, but 0x96 specified
+ * as it is the usage of the only field in that report.
+ */
 
-/* device_control is really 0x95, but 0x96 specified as it is the usage of
-the only field in that report */
+/* PID special fields */
+#define PID_EFFECT_TYPE			0x25
+#define PID_DIRECTION			0x57
+#define PID_EFFECT_OPERATION_ARRAY	0x78
+#define PID_BLOCK_LOAD_STATUS		0x8b
+#define PID_DEVICE_CONTROL_ARRAY	0x96
 
 /* Value usage tables used to put fields and values into arrays */
-
 #define PID_EFFECT_BLOCK_INDEX	0
 
 #define PID_DURATION		1
@@ -107,10 +114,13 @@ static const u8 pidff_device_gain[] = { 0x7e };
 static const u8 pidff_pool[] = { 0x80, 0x83, 0xa9 };
 
 /* Special field key tables used to put special field keys into arrays */
-
 #define PID_ENABLE_ACTUATORS	0
-#define PID_RESET		1
-static const u8 pidff_device_control[] = { 0x97, 0x9a };
+#define PID_DISABLE_ACTUATORS	1
+#define PID_STOP_ALL_EFFECTS	2
+#define PID_RESET		3
+#define PID_PAUSE		4
+#define PID_CONTINUE		5
+static const u8 pidff_device_control[] = { 0x97, 0x98, 0x99, 0x9a, 0x9b, 0x9c };
 
 #define PID_CONSTANT	0
 #define PID_RAMP	1
@@ -130,12 +140,16 @@ static const u8 pidff_effect_types[] = {
 
 #define PID_BLOCK_LOAD_SUCCESS	0
 #define PID_BLOCK_LOAD_FULL	1
-static const u8 pidff_block_load_status[] = { 0x8c, 0x8d };
+#define PID_BLOCK_LOAD_ERROR	2
+static const u8 pidff_block_load_status[] = { 0x8c, 0x8d, 0x8e};
 
 #define PID_EFFECT_START	0
 #define PID_EFFECT_STOP		1
 static const u8 pidff_effect_operation_status[] = { 0x79, 0x7b };
 
+/* Polar direction 90 degrees (East) */
+#define PIDFF_FIXED_WHEEL_DIRECTION	0x4000
+
 struct pidff_usage {
 	struct hid_field *field;
 	s32 *value;
@@ -159,8 +173,10 @@ struct pidff_device {
 	struct pidff_usage effect_operation[sizeof(pidff_effect_operation)];
 	struct pidff_usage block_free[sizeof(pidff_block_free)];
 
-	/* Special field is a field that is not composed of
-	   usage<->value pairs that pidff_usage values are */
+	/*
+	 * Special field is a field that is not composed of
+	 * usage<->value pairs that pidff_usage values are
+	 */
 
 	/* Special field in create_new_effect */
 	struct hid_field *create_new_effect_type;
@@ -184,30 +200,61 @@ struct pidff_device {
 	int operation_id[sizeof(pidff_effect_operation_status)];
 
 	int pid_id[PID_EFFECTS_MAX];
+
+	u32 quirks;
+	u8 effect_count;
 };
 
 /*
+ * Clamp value for a given field
+ */
+static s32 pidff_clamp(s32 i, struct hid_field *field)
+{
+	s32 clamped = clamp(i, field->logical_minimum, field->logical_maximum);
+	pr_debug("clamped from %d to %d", i, clamped);
+	return clamped;
+}
+
+/*
  * Scale an unsigned value with range 0..max for the given field
  */
 static int pidff_rescale(int i, int max, struct hid_field *field)
 {
 	return i * (field->logical_maximum - field->logical_minimum) / max +
-	    field->logical_minimum;
+		field->logical_minimum;
 }
 
 /*
- * Scale a signed value in range -0x8000..0x7fff for the given field
+ * Scale a signed value in range S16_MIN..S16_MAX for the given field
  */
 static int pidff_rescale_signed(int i, struct hid_field *field)
 {
-	return i == 0 ? 0 : i >
-	    0 ? i * field->logical_maximum / 0x7fff : i *
-	    field->logical_minimum / -0x8000;
+	if (i > 0) return i * field->logical_maximum / S16_MAX;
+	if (i < 0) return i * field->logical_minimum / S16_MIN;
+	return 0;
+}
+
+/*
+ * Scale time value from Linux default (ms) to field units
+ */
+static u32 pidff_rescale_time(u16 time, struct hid_field *field)
+{
+	u32 scaled_time = time;
+	int exponent = field->unit_exponent;
+	pr_debug("time field exponent: %d\n", exponent);
+
+	for (;exponent < FF_TIME_EXPONENT; exponent++)
+		scaled_time *= 10;
+	for (;exponent > FF_TIME_EXPONENT; exponent--)
+		scaled_time /= 10;
+
+	pr_debug("time calculated from %d to %d\n", time, scaled_time);
+	return scaled_time;
 }
 
 static void pidff_set(struct pidff_usage *usage, u16 value)
 {
-	usage->value[0] = pidff_rescale(value, 0xffff, usage->field);
+	usage->value[0] = pidff_rescale(value, U16_MAX, usage->field);
 	pr_debug("calculated from %d to %d\n", value, usage->value[0]);
 }
 
@@ -218,14 +265,35 @@ static void pidff_set_signed(struct pidff_usage *usage, s16 value)
 	else {
 		if (value < 0)
 			usage->value[0] =
-			    pidff_rescale(-value, 0x8000, usage->field);
+			    pidff_rescale(-value, -S16_MIN, usage->field);
 		else
 			usage->value[0] =
-			    pidff_rescale(value, 0x7fff, usage->field);
+			    pidff_rescale(value, S16_MAX, usage->field);
 	}
 	pr_debug("calculated from %d to %d\n", value, usage->value[0]);
 }
 
+static void pidff_set_time(struct pidff_usage *usage, u16 time)
+{
+	u32 modified_time = pidff_rescale_time(time, usage->field);
+	usage->value[0] = pidff_clamp(modified_time, usage->field);
+}
+
+static void pidff_set_duration(struct pidff_usage *usage, u16 duration)
+{
+	/* Infinite value conversion from Linux API -> PID */
+	if (duration == FF_INFINITE)
+		duration = PID_INFINITE;
+
+	/* PID defines INFINITE as the max possible value for duration field */
+	if (duration == PID_INFINITE) {
+		usage->value[0] = (1U << usage->field->report_size) - 1;
+		return;
+	}
+
+	pidff_set_time(usage, duration);
+}
+
 /*
  * Send envelope report to the device
  */
@@ -233,19 +301,21 @@ static void pidff_set_envelope_report(struct pidff_device *pidff,
 				      struct ff_envelope *envelope)
 {
 	pidff->set_envelope[PID_EFFECT_BLOCK_INDEX].value[0] =
-	    pidff->block_load[PID_EFFECT_BLOCK_INDEX].value[0];
+		pidff->block_load[PID_EFFECT_BLOCK_INDEX].value[0];
 
 	pidff->set_envelope[PID_ATTACK_LEVEL].value[0] =
-	    pidff_rescale(envelope->attack_level >
-			  0x7fff ? 0x7fff : envelope->attack_level, 0x7fff,
-			  pidff->set_envelope[PID_ATTACK_LEVEL].field);
+		pidff_rescale(envelope->attack_level >
+			S16_MAX ? S16_MAX : envelope->attack_level, S16_MAX,
+			pidff->set_envelope[PID_ATTACK_LEVEL].field);
 	pidff->set_envelope[PID_FADE_LEVEL].value[0] =
-	    pidff_rescale(envelope->fade_level >
-			  0x7fff ? 0x7fff : envelope->fade_level, 0x7fff,
-			  pidff->set_envelope[PID_FADE_LEVEL].field);
+		pidff_rescale(envelope->fade_level >
+			S16_MAX ? S16_MAX : envelope->fade_level, S16_MAX,
+			pidff->set_envelope[PID_FADE_LEVEL].field);
 
-	pidff->set_envelope[PID_ATTACK_TIME].value[0] = envelope->attack_length;
-	pidff->set_envelope[PID_FADE_TIME].value[0] = envelope->fade_length;
+	pidff_set_time(&pidff->set_envelope[PID_ATTACK_TIME],
+			envelope->attack_length);
+	pidff_set_time(&pidff->set_envelope[PID_FADE_TIME],
+			envelope->fade_length);
 
 	hid_dbg(pidff->hid, "attack %u => %d\n",
 		envelope->attack_level,
@@ -261,10 +331,22 @@ static void pidff_set_envelope_report(struct pidff_device *pidff,
 static int pidff_needs_set_envelope(struct ff_envelope *envelope,
 				    struct ff_envelope *old)
 {
-	return envelope->attack_level != old->attack_level ||
-	       envelope->fade_level != old->fade_level ||
+	bool needs_new_envelope;
+	needs_new_envelope = envelope->attack_level  != 0 ||
+			     envelope->fade_level    != 0 ||
+			     envelope->attack_length != 0 ||
+			     envelope->fade_length   != 0;
+
+	if (!needs_new_envelope)
+		return false;
+
+	if (!old)
+		return needs_new_envelope;
+
+	return envelope->attack_level  != old->attack_level  ||
+	       envelope->fade_level    != old->fade_level    ||
 	       envelope->attack_length != old->attack_length ||
-	       envelope->fade_length != old->fade_length;
+	       envelope->fade_length   != old->fade_length;
 }
 
 /*
@@ -301,17 +383,27 @@ static void pidff_set_effect_report(struct pidff_device *pidff,
 		pidff->block_load[PID_EFFECT_BLOCK_INDEX].value[0];
 	pidff->set_effect_type->value[0] =
 		pidff->create_new_effect_type->value[0];
-	pidff->set_effect[PID_DURATION].value[0] = effect->replay.length;
+
+	pidff_set_duration(&pidff->set_effect[PID_DURATION],
+		effect->replay.length);
+
 	pidff->set_effect[PID_TRIGGER_BUTTON].value[0] = effect->trigger.button;
-	pidff->set_effect[PID_TRIGGER_REPEAT_INT].value[0] =
-		effect->trigger.interval;
+	pidff_set_time(&pidff->set_effect[PID_TRIGGER_REPEAT_INT],
+			effect->trigger.interval);
 	pidff->set_effect[PID_GAIN].value[0] =
 		pidff->set_effect[PID_GAIN].field->logical_maximum;
 	pidff->set_effect[PID_DIRECTION_ENABLE].value[0] = 1;
-	pidff->effect_direction->value[0] =
-		pidff_rescale(effect->direction, 0xffff,
-				pidff->effect_direction);
-	pidff->set_effect[PID_START_DELAY].value[0] = effect->replay.delay;
+
+	/* Use fixed direction if needed */
+	pidff->effect_direction->value[0] = pidff_rescale(
+		pidff->quirks & HID_PIDFF_QUIRK_FIX_WHEEL_DIRECTION ?
+		PIDFF_FIXED_WHEEL_DIRECTION : effect->direction,
+		U16_MAX, pidff->effect_direction);
+
+	/* Omit setting delay field if it's missing */
+	if (!(pidff->quirks & HID_PIDFF_QUIRK_MISSING_DELAY))
+		pidff_set_time(&pidff->set_effect[PID_START_DELAY],
+				effect->replay.delay);
 
 	hid_hw_request(pidff->hid, pidff->reports[PID_SET_EFFECT],
 			HID_REQ_SET_REPORT);
@@ -343,11 +435,11 @@ static void pidff_set_periodic_report(struct pidff_device *pidff,
 	pidff_set_signed(&pidff->set_periodic[PID_OFFSET],
 			 effect->u.periodic.offset);
 	pidff_set(&pidff->set_periodic[PID_PHASE], effect->u.periodic.phase);
-	pidff->set_periodic[PID_PERIOD].value[0] = effect->u.periodic.period;
+	pidff_set_time(&pidff->set_periodic[PID_PERIOD],
+			effect->u.periodic.period);
 
 	hid_hw_request(pidff->hid, pidff->reports[PID_SET_PERIODIC],
 			HID_REQ_SET_REPORT);
-
 }
 
 /*
@@ -368,13 +460,19 @@ static int pidff_needs_set_periodic(struct ff_effect *effect,
 static void pidff_set_condition_report(struct pidff_device *pidff,
 				       struct ff_effect *effect)
 {
-	int i;
+	int i, max_axis;
+
+	/* Devices missing Parameter Block Offset can only have one axis */
+	max_axis = pidff->quirks & HID_PIDFF_QUIRK_MISSING_PBO ? 1 : 2;
 
 	pidff->set_condition[PID_EFFECT_BLOCK_INDEX].value[0] =
 		pidff->block_load[PID_EFFECT_BLOCK_INDEX].value[0];
 
-	for (i = 0; i < 2; i++) {
-		pidff->set_condition[PID_PARAM_BLOCK_OFFSET].value[0] = i;
+	for (i = 0; i < max_axis; i++) {
+		/* Omit Parameter Block Offset if missing */
+		if (!(pidff->quirks & HID_PIDFF_QUIRK_MISSING_PBO))
+			pidff->set_condition[PID_PARAM_BLOCK_OFFSET].value[0] = i;
+
 		pidff_set_signed(&pidff->set_condition[PID_CP_OFFSET],
 				 effect->u.condition[i].center);
 		pidff_set_signed(&pidff->set_condition[PID_POS_COEFFICIENT],
@@ -442,8 +540,103 @@ static int pidff_needs_set_ramp(struct ff_effect *effect, struct ff_effect *old)
 }
 
 /*
+ * Set device gain
+ */
+static void pidff_set_gain_report(struct pidff_device *pidff, u16 gain)
+{
+	if (!pidff->device_gain[PID_DEVICE_GAIN_FIELD].field)
+		return;
+
+	pidff_set(&pidff->device_gain[PID_DEVICE_GAIN_FIELD], gain);
+	hid_hw_request(pidff->hid, pidff->reports[PID_DEVICE_GAIN],
+			HID_REQ_SET_REPORT);
+}
+
+/*
+ * Send device control report to the device
+ */
+static void pidff_set_device_control(struct pidff_device *pidff, int field)
+{
+	int i, index;
+	int field_index = pidff->control_id[field];
+
+	if (field_index < 1)
+		return;
+
+	/* Detect if the field is a bitmask variable or an array */
+	if (pidff->device_control->flags & HID_MAIN_ITEM_VARIABLE) {
+		hid_dbg(pidff->hid, "DEVICE_CONTROL is a bitmask\n");
+
+		/* Clear current bitmask */
+		for(i = 0; i < sizeof(pidff_device_control); i++) {
+			index = pidff->control_id[i];
+			if (index < 1)
+				continue;
+
+			pidff->device_control->value[index - 1] = 0;
+		}
+
+		pidff->device_control->value[field_index - 1] = 1;
+	} else {
+		hid_dbg(pidff->hid, "DEVICE_CONTROL is an array\n");
+		pidff->device_control->value[0] = field_index;
+	}
+
+	hid_hw_request(pidff->hid, pidff->reports[PID_DEVICE_CONTROL], HID_REQ_SET_REPORT);
+	hid_hw_wait(pidff->hid);
+}
+
+/*
+ * Modify actuators state
+ */
+static void pidff_set_actuators(struct pidff_device *pidff, bool enable)
+{
+	hid_dbg(pidff->hid, "%s actuators\n", enable ? "Enable" : "Disable");
+	pidff_set_device_control(pidff,
+		enable ? PID_ENABLE_ACTUATORS : PID_DISABLE_ACTUATORS);
+}
+
+/*
+ * Reset the device, stop all effects, enable actuators
+ */
+static void pidff_reset(struct pidff_device *pidff)
+{
+	/* We reset twice as sometimes hid_wait_io isn't waiting long enough */
+	pidff_set_device_control(pidff, PID_RESET);
+	pidff_set_device_control(pidff, PID_RESET);
+	pidff->effect_count = 0;
+
+	pidff_set_device_control(pidff, PID_STOP_ALL_EFFECTS);
+	pidff_set_actuators(pidff, 1);
+}
+
+/*
+ * Fetch pool report
+ */
+static void pidff_fetch_pool(struct pidff_device *pidff)
+{
+	int i;
+	struct hid_device *hid = pidff->hid;
+
+	/* Repeat if PID_SIMULTANEOUS_MAX < 2 to make sure it's correct */
+	for(i = 0; i < 20; i++) {
+		hid_hw_request(hid, pidff->reports[PID_POOL], HID_REQ_GET_REPORT);
+		hid_hw_wait(hid);
+
+		if (!pidff->pool[PID_SIMULTANEOUS_MAX].value)
+			return;
+		if (pidff->pool[PID_SIMULTANEOUS_MAX].value[0] >= 2)
+			return;
+	}
+	hid_warn(hid, "device reports %d simultaneous effects\n",
+		 pidff->pool[PID_SIMULTANEOUS_MAX].value[0]);
+}
+
+/*
  * Send a request for effect upload to the device
  *
+ * Reset and enable actuators if no effects were present on the device
+ *
  * Returns 0 if device reported success, -ENOSPC if the device reported memory
  * is full. Upon unknown response the function will retry for 60 times, if
  * still unsuccessful -EIO is returned.
@@ -452,6 +645,9 @@ static int pidff_request_effect_upload(struct pidff_device *pidff, int efnum)
 {
 	int j;
 
+	if (!pidff->effect_count)
+		pidff_reset(pidff);
+
 	pidff->create_new_effect_type->value[0] = efnum;
 	hid_hw_request(pidff->hid, pidff->reports[PID_CREATE_NEW_EFFECT],
 			HID_REQ_SET_REPORT);
@@ -471,6 +667,8 @@ static int pidff_request_effect_upload(struct pidff_device *pidff, int efnum)
 			hid_dbg(pidff->hid, "device reported free memory: %d bytes\n",
 				 pidff->block_load[PID_RAM_POOL_AVAILABLE].value ?
 				 pidff->block_load[PID_RAM_POOL_AVAILABLE].value[0] : -1);
+
+			pidff->effect_count++;
 			return 0;
 		}
 		if (pidff->block_load_status->value[0] ==
@@ -480,6 +678,11 @@ static int pidff_request_effect_upload(struct pidff_device *pidff, int efnum)
 				pidff->block_load[PID_RAM_POOL_AVAILABLE].value[0] : -1);
 			return -ENOSPC;
 		}
+		if (pidff->block_load_status->value[0] ==
+		    pidff->status_id[PID_BLOCK_LOAD_ERROR]) {
+			hid_dbg(pidff->hid, "device error during effect creation\n");
+			return -EREMOTEIO;
+		}
 	}
 	hid_err(pidff->hid, "pid_block_load failed 60 times\n");
 	return -EIO;
@@ -498,7 +701,8 @@ static void pidff_playback_pid(struct pidff_device *pidff, int pid_id, int n)
 	} else {
 		pidff->effect_operation_status->value[0] =
 			pidff->operation_id[PID_EFFECT_START];
-		pidff->effect_operation[PID_LOOP_COUNT].value[0] = n;
+		pidff->effect_operation[PID_LOOP_COUNT].value[0] =
+			pidff_clamp(n, pidff->effect_operation[PID_LOOP_COUNT].field);
 	}
 
 	hid_hw_request(pidff->hid, pidff->reports[PID_EFFECT_OPERATION],
@@ -511,20 +715,22 @@ static void pidff_playback_pid(struct pidff_device *pidff, int pid_id, int n)
 static int pidff_playback(struct input_dev *dev, int effect_id, int value)
 {
 	struct pidff_device *pidff = dev->ff->private;
-
 	pidff_playback_pid(pidff, pidff->pid_id[effect_id], value);
-
 	return 0;
 }
 
 /*
  * Erase effect with PID id
+ * Decrease the device effect counter
  */
 static void pidff_erase_pid(struct pidff_device *pidff, int pid_id)
 {
 	pidff->block_free[PID_EFFECT_BLOCK_INDEX].value[0] = pid_id;
 	hid_hw_request(pidff->hid, pidff->reports[PID_BLOCK_FREE],
 			HID_REQ_SET_REPORT);
+
+	if (pidff->effect_count > 0)
+		pidff->effect_count--;
 }
 
 /*
@@ -537,8 +743,11 @@ static int pidff_erase_effect(struct input_dev *dev, int effect_id)
 
 	hid_dbg(pidff->hid, "starting to erase %d/%d\n",
 		effect_id, pidff->pid_id[effect_id]);
-	/* Wait for the queue to clear. We do not want a full fifo to
-	   prevent the effect removal. */
+
+	/*
+	 * Wait for the queue to clear. We do not want
+	 * a full fifo to prevent the effect removal.
+	 */
 	hid_hw_wait(pidff->hid);
 	pidff_playback_pid(pidff, pid_id, 0);
 	pidff_erase_pid(pidff, pid_id);
@@ -574,11 +783,9 @@ static int pidff_upload_effect(struct input_dev *dev, struct ff_effect *effect,
 			pidff_set_effect_report(pidff, effect);
 		if (!old || pidff_needs_set_constant(effect, old))
 			pidff_set_constant_force_report(pidff, effect);
-		if (!old ||
-		    pidff_needs_set_envelope(&effect->u.constant.envelope,
-					&old->u.constant.envelope))
-			pidff_set_envelope_report(pidff,
-					&effect->u.constant.envelope);
+		if (pidff_needs_set_envelope(&effect->u.constant.envelope,
+					old ? &old->u.constant.envelope : NULL))
+			pidff_set_envelope_report(pidff, &effect->u.constant.envelope);
 		break;
 
 	case FF_PERIODIC:
@@ -604,6 +811,9 @@ static int pidff_upload_effect(struct input_dev *dev, struct ff_effect *effect,
 				return -EINVAL;
 			}
 
+			if (pidff->quirks & HID_PIDFF_QUIRK_PERIODIC_SINE_ONLY)
+				type_id = PID_SINE;
+
 			error = pidff_request_effect_upload(pidff,
 					pidff->type_id[type_id]);
 			if (error)
@@ -613,11 +823,9 @@ static int pidff_upload_effect(struct input_dev *dev, struct ff_effect *effect,
 			pidff_set_effect_report(pidff, effect);
 		if (!old || pidff_needs_set_periodic(effect, old))
 			pidff_set_periodic_report(pidff, effect);
-		if (!old ||
-		    pidff_needs_set_envelope(&effect->u.periodic.envelope,
-					&old->u.periodic.envelope))
-			pidff_set_envelope_report(pidff,
-					&effect->u.periodic.envelope);
+		if (pidff_needs_set_envelope(&effect->u.periodic.envelope,
+					old ? &old->u.periodic.envelope : NULL))
+			pidff_set_envelope_report(pidff, &effect->u.periodic.envelope);
 		break;
 
 	case FF_RAMP:
@@ -631,56 +839,32 @@ static int pidff_upload_effect(struct input_dev *dev, struct ff_effect *effect,
 			pidff_set_effect_report(pidff, effect);
 		if (!old || pidff_needs_set_ramp(effect, old))
 			pidff_set_ramp_force_report(pidff, effect);
-		if (!old ||
-		    pidff_needs_set_envelope(&effect->u.ramp.envelope,
-					&old->u.ramp.envelope))
-			pidff_set_envelope_report(pidff,
-					&effect->u.ramp.envelope);
+		if (pidff_needs_set_envelope(&effect->u.ramp.envelope,
+					old ? &old->u.ramp.envelope : NULL))
+			pidff_set_envelope_report(pidff, &effect->u.ramp.envelope);
 		break;
 
 	case FF_SPRING:
-		if (!old) {
-			error = pidff_request_effect_upload(pidff,
-					pidff->type_id[PID_SPRING]);
-			if (error)
-				return error;
-		}
-		if (!old || pidff_needs_set_effect(effect, old))
-			pidff_set_effect_report(pidff, effect);
-		if (!old || pidff_needs_set_condition(effect, old))
-			pidff_set_condition_report(pidff, effect);
-		break;
-
-	case FF_FRICTION:
-		if (!old) {
-			error = pidff_request_effect_upload(pidff,
-					pidff->type_id[PID_FRICTION]);
-			if (error)
-				return error;
-		}
-		if (!old || pidff_needs_set_effect(effect, old))
-			pidff_set_effect_report(pidff, effect);
-		if (!old || pidff_needs_set_condition(effect, old))
-			pidff_set_condition_report(pidff, effect);
-		break;
-
 	case FF_DAMPER:
-		if (!old) {
-			error = pidff_request_effect_upload(pidff,
-					pidff->type_id[PID_DAMPER]);
-			if (error)
-				return error;
-		}
-		if (!old || pidff_needs_set_effect(effect, old))
-			pidff_set_effect_report(pidff, effect);
-		if (!old || pidff_needs_set_condition(effect, old))
-			pidff_set_condition_report(pidff, effect);
-		break;
-
 	case FF_INERTIA:
+	case FF_FRICTION:
 		if (!old) {
+			switch(effect->type) {
+			case FF_SPRING:
+				type_id = PID_SPRING;
+				break;
+			case FF_DAMPER:
+				type_id = PID_DAMPER;
+				break;
+			case FF_INERTIA:
+				type_id = PID_INERTIA;
+				break;
+			case FF_FRICTION:
+				type_id = PID_FRICTION;
+				break;
+			}
 			error = pidff_request_effect_upload(pidff,
-					pidff->type_id[PID_INERTIA]);
+					pidff->type_id[type_id]);
 			if (error)
 				return error;
 		}
@@ -709,11 +893,7 @@ static int pidff_upload_effect(struct input_dev *dev, struct ff_effect *effect,
  */
 static void pidff_set_gain(struct input_dev *dev, u16 gain)
 {
-	struct pidff_device *pidff = dev->ff->private;
-
-	pidff_set(&pidff->device_gain[PID_DEVICE_GAIN_FIELD], gain);
-	hid_hw_request(pidff->hid, pidff->reports[PID_DEVICE_GAIN],
-			HID_REQ_SET_REPORT);
+	pidff_set_gain_report(dev->ff->private, gain);
 }
 
 static void pidff_autocenter(struct pidff_device *pidff, u16 magnitude)
@@ -736,7 +916,10 @@ static void pidff_autocenter(struct pidff_device *pidff, u16 magnitude)
 	pidff->set_effect[PID_TRIGGER_REPEAT_INT].value[0] = 0;
 	pidff_set(&pidff->set_effect[PID_GAIN], magnitude);
 	pidff->set_effect[PID_DIRECTION_ENABLE].value[0] = 1;
-	pidff->set_effect[PID_START_DELAY].value[0] = 0;
+
+	/* Omit setting delay field if it's missing */
+	if (!(pidff->quirks & HID_PIDFF_QUIRK_MISSING_DELAY))
+		pidff->set_effect[PID_START_DELAY].value[0] = 0;
 
 	hid_hw_request(pidff->hid, pidff->reports[PID_SET_EFFECT],
 			HID_REQ_SET_REPORT);
@@ -747,9 +930,7 @@ static void pidff_autocenter(struct pidff_device *pidff, u16 magnitude)
  */
 static void pidff_set_autocenter(struct input_dev *dev, u16 magnitude)
 {
-	struct pidff_device *pidff = dev->ff->private;
-
-	pidff_autocenter(pidff, magnitude);
+	pidff_autocenter(dev->ff->private, magnitude);
 }
 
 /*
@@ -758,7 +939,13 @@ static void pidff_set_autocenter(struct input_dev *dev, u16 magnitude)
 static int pidff_find_fields(struct pidff_usage *usage, const u8 *table,
 			     struct hid_report *report, int count, int strict)
 {
+	if (!report) {
+		pr_debug("pidff_find_fields, null report\n");
+		return -1;
+	}
+
 	int i, j, k, found;
+	int return_value = 0;
 
 	for (k = 0; k < count; k++) {
 		found = 0;
@@ -783,12 +970,22 @@ static int pidff_find_fields(struct pidff_usage *usage, const u8 *table,
 			if (found)
 				break;
 		}
-		if (!found && strict) {
+		if (!found && table[k] == pidff_set_effect[PID_START_DELAY]) {
+			pr_debug("Delay field not found, but that's OK\n");
+			pr_debug("Setting MISSING_DELAY quirk\n");
+			return_value |= HID_PIDFF_QUIRK_MISSING_DELAY;
+		}
+		else if (!found && table[k] == pidff_set_condition[PID_PARAM_BLOCK_OFFSET]) {
+			pr_debug("PBO field not found, but that's OK\n");
+			pr_debug("Setting MISSING_PBO quirk\n");
+			return_value |= HID_PIDFF_QUIRK_MISSING_PBO;
+		}
+		else if (!found && strict) {
 			pr_debug("failed to locate %d\n", k);
 			return -1;
 		}
 	}
-	return 0;
+	return return_value;
 }
 
 /*
@@ -871,6 +1068,11 @@ static int pidff_reports_ok(struct pidff_device *pidff)
 static struct hid_field *pidff_find_special_field(struct hid_report *report,
 						  int usage, int enforce_min)
 {
+	if (!report) {
+		pr_debug("pidff_find_special_field, null report\n");
+		return NULL;
+	}
+
 	int i;
 
 	for (i = 0; i < report->maxfield; i++) {
@@ -923,22 +1125,24 @@ static int pidff_find_special_fields(struct pidff_device *pidff)
 
 	pidff->create_new_effect_type =
 		pidff_find_special_field(pidff->reports[PID_CREATE_NEW_EFFECT],
-					 0x25, 1);
+					 PID_EFFECT_TYPE, 1);
 	pidff->set_effect_type =
 		pidff_find_special_field(pidff->reports[PID_SET_EFFECT],
-					 0x25, 1);
+					 PID_EFFECT_TYPE, 1);
 	pidff->effect_direction =
 		pidff_find_special_field(pidff->reports[PID_SET_EFFECT],
-					 0x57, 0);
+					 PID_DIRECTION, 0);
 	pidff->device_control =
 		pidff_find_special_field(pidff->reports[PID_DEVICE_CONTROL],
-					 0x96, 1);
+			PID_DEVICE_CONTROL_ARRAY,
+			!(pidff->quirks & HID_PIDFF_QUIRK_PERMISSIVE_CONTROL));
+
 	pidff->block_load_status =
 		pidff_find_special_field(pidff->reports[PID_BLOCK_LOAD],
-					 0x8b, 1);
+					 PID_BLOCK_LOAD_STATUS, 1);
 	pidff->effect_operation_status =
 		pidff_find_special_field(pidff->reports[PID_EFFECT_OPERATION],
-					 0x78, 1);
+					 PID_EFFECT_OPERATION_ARRAY, 1);
 
 	hid_dbg(pidff->hid, "search done\n");
 
@@ -967,10 +1171,6 @@ static int pidff_find_special_fields(struct pidff_device *pidff)
 		return -1;
 	}
 
-	pidff_find_special_keys(pidff->control_id, pidff->device_control,
-				pidff_device_control,
-				sizeof(pidff_device_control));
-
 	PIDFF_FIND_SPECIAL_KEYS(control_id, device_control, device_control);
 
 	if (!PIDFF_FIND_SPECIAL_KEYS(type_id, create_new_effect_type,
@@ -1049,7 +1249,6 @@ static int pidff_find_effects(struct pidff_device *pidff,
 		set_bit(FF_FRICTION, dev->ffbit);
 
 	return 0;
-
 }
 
 #define PIDFF_FIND_FIELDS(name, report, strict) \
@@ -1062,12 +1261,19 @@ static int pidff_find_effects(struct pidff_device *pidff,
  */
 static int pidff_init_fields(struct pidff_device *pidff, struct input_dev *dev)
 {
-	int envelope_ok = 0;
+	int status = 0;
 
-	if (PIDFF_FIND_FIELDS(set_effect, PID_SET_EFFECT, 1)) {
+	/* Save info about the device not having the DELAY ffb field. */
+	status = PIDFF_FIND_FIELDS(set_effect, PID_SET_EFFECT, 1);
+	if (status == -1) {
 		hid_err(pidff->hid, "unknown set_effect report layout\n");
 		return -ENODEV;
 	}
+	pidff->quirks |= status;
+
+	if (status & HID_PIDFF_QUIRK_MISSING_DELAY)
+		hid_dbg(pidff->hid, "Adding MISSING_DELAY quirk\n");
+
 
 	PIDFF_FIND_FIELDS(block_load, PID_BLOCK_LOAD, 0);
 	if (!pidff->block_load[PID_EFFECT_BLOCK_INDEX].value) {
@@ -1085,13 +1291,10 @@ static int pidff_init_fields(struct pidff_device *pidff, struct input_dev *dev)
 		return -ENODEV;
 	}
 
-	if (!PIDFF_FIND_FIELDS(set_envelope, PID_SET_ENVELOPE, 1))
-		envelope_ok = 1;
-
 	if (pidff_find_special_fields(pidff) || pidff_find_effects(pidff, dev))
 		return -ENODEV;
 
-	if (!envelope_ok) {
+	if (PIDFF_FIND_FIELDS(set_envelope, PID_SET_ENVELOPE, 1)) {
 		if (test_and_clear_bit(FF_CONSTANT, dev->ffbit))
 			hid_warn(pidff->hid,
 				 "has constant effect but no envelope\n");
@@ -1116,16 +1319,20 @@ static int pidff_init_fields(struct pidff_device *pidff, struct input_dev *dev)
 		clear_bit(FF_RAMP, dev->ffbit);
 	}
 
-	if ((test_bit(FF_SPRING, dev->ffbit) ||
-	     test_bit(FF_DAMPER, dev->ffbit) ||
-	     test_bit(FF_FRICTION, dev->ffbit) ||
-	     test_bit(FF_INERTIA, dev->ffbit)) &&
-	    PIDFF_FIND_FIELDS(set_condition, PID_SET_CONDITION, 1)) {
-		hid_warn(pidff->hid, "unknown condition effect layout\n");
-		clear_bit(FF_SPRING, dev->ffbit);
-		clear_bit(FF_DAMPER, dev->ffbit);
-		clear_bit(FF_FRICTION, dev->ffbit);
-		clear_bit(FF_INERTIA, dev->ffbit);
+	if (test_bit(FF_SPRING, dev->ffbit) ||
+	    test_bit(FF_DAMPER, dev->ffbit) ||
+	    test_bit(FF_FRICTION, dev->ffbit) ||
+	    test_bit(FF_INERTIA, dev->ffbit)) {
+		status = PIDFF_FIND_FIELDS(set_condition, PID_SET_CONDITION, 1);
+
+		if (status < 0) {
+			hid_warn(pidff->hid, "unknown condition effect layout\n");
+			clear_bit(FF_SPRING, dev->ffbit);
+			clear_bit(FF_DAMPER, dev->ffbit);
+			clear_bit(FF_FRICTION, dev->ffbit);
+			clear_bit(FF_INERTIA, dev->ffbit);
+		}
+		pidff->quirks |= status;
 	}
 
 	if (test_bit(FF_PERIODIC, dev->ffbit) &&
@@ -1143,46 +1350,6 @@ static int pidff_init_fields(struct pidff_device *pidff, struct input_dev *dev)
 }
 
 /*
- * Reset the device
- */
-static void pidff_reset(struct pidff_device *pidff)
-{
-	struct hid_device *hid = pidff->hid;
-	int i = 0;
-
-	pidff->device_control->value[0] = pidff->control_id[PID_RESET];
-	/* We reset twice as sometimes hid_wait_io isn't waiting long enough */
-	hid_hw_request(hid, pidff->reports[PID_DEVICE_CONTROL], HID_REQ_SET_REPORT);
-	hid_hw_wait(hid);
-	hid_hw_request(hid, pidff->reports[PID_DEVICE_CONTROL], HID_REQ_SET_REPORT);
-	hid_hw_wait(hid);
-
-	pidff->device_control->value[0] =
-		pidff->control_id[PID_ENABLE_ACTUATORS];
-	hid_hw_request(hid, pidff->reports[PID_DEVICE_CONTROL], HID_REQ_SET_REPORT);
-	hid_hw_wait(hid);
-
-	/* pool report is sometimes messed up, refetch it */
-	hid_hw_request(hid, pidff->reports[PID_POOL], HID_REQ_GET_REPORT);
-	hid_hw_wait(hid);
-
-	if (pidff->pool[PID_SIMULTANEOUS_MAX].value) {
-		while (pidff->pool[PID_SIMULTANEOUS_MAX].value[0] < 2) {
-			if (i++ > 20) {
-				hid_warn(pidff->hid,
-					 "device reports %d simultaneous effects\n",
-					 pidff->pool[PID_SIMULTANEOUS_MAX].value[0]);
-				break;
-			}
-			hid_dbg(pidff->hid, "pid_pool requested again\n");
-			hid_hw_request(hid, pidff->reports[PID_POOL],
-					  HID_REQ_GET_REPORT);
-			hid_hw_wait(hid);
-		}
-	}
-}
-
-/*
  * Test if autocenter modification is using the supported method
  */
 static int pidff_check_autocenter(struct pidff_device *pidff,
@@ -1206,24 +1373,23 @@ static int pidff_check_autocenter(struct pidff_device *pidff,
 
 	if (pidff->block_load[PID_EFFECT_BLOCK_INDEX].value[0] ==
 	    pidff->block_load[PID_EFFECT_BLOCK_INDEX].field->logical_minimum + 1) {
-		pidff_autocenter(pidff, 0xffff);
+		pidff_autocenter(pidff, U16_MAX);
 		set_bit(FF_AUTOCENTER, dev->ffbit);
 	} else {
 		hid_notice(pidff->hid,
 			   "device has unknown autocenter control method\n");
 	}
-
 	pidff_erase_pid(pidff,
 			pidff->block_load[PID_EFFECT_BLOCK_INDEX].value[0]);
 
 	return 0;
-
 }
 
 /*
  * Check if the device is PID and initialize it
+ * Set initial quirks
  */
-int hid_pidff_init(struct hid_device *hid)
+int hid_pidff_init_with_quirks(struct hid_device *hid, u32 initial_quirks)
 {
 	struct pidff_device *pidff;
 	struct hid_input *hidinput = list_entry(hid->inputs.next,
@@ -1245,6 +1411,8 @@ int hid_pidff_init(struct hid_device *hid)
 		return -ENOMEM;
 
 	pidff->hid = hid;
+	pidff->quirks = initial_quirks;
+	pidff->effect_count = 0;
 
 	hid_device_io_start(hid);
 
@@ -1261,14 +1429,9 @@ int hid_pidff_init(struct hid_device *hid)
 	if (error)
 		goto fail;
 
-	pidff_reset(pidff);
-
-	if (test_bit(FF_GAIN, dev->ffbit)) {
-		pidff_set(&pidff->device_gain[PID_DEVICE_GAIN_FIELD], 0xffff);
-		hid_hw_request(hid, pidff->reports[PID_DEVICE_GAIN],
-				     HID_REQ_SET_REPORT);
-	}
-
+	/* pool report is sometimes messed up, refetch it */
+	pidff_fetch_pool(pidff);
+	pidff_set_gain_report(pidff, U16_MAX);
 	error = pidff_check_autocenter(pidff, dev);
 	if (error)
 		goto fail;
@@ -1311,6 +1474,7 @@ int hid_pidff_init(struct hid_device *hid)
 	ff->playback = pidff_playback;
 
 	hid_info(dev, "Force feedback for USB HID PID devices by Anssi Hannula <anssi.hannula@gmail.com>\n");
+	hid_dbg(dev, "Active quirks mask: 0x%x\n", pidff->quirks);
 
 	hid_device_io_stop(hid);
 
@@ -1322,3 +1486,14 @@ int hid_pidff_init(struct hid_device *hid)
 	kfree(pidff);
 	return error;
 }
+EXPORT_SYMBOL_GPL(hid_pidff_init_with_quirks);
+
+/*
+ * Check if the device is PID and initialize it
+ * Wrapper made to keep the compatibility with old
+ * init function
+ */
+int hid_pidff_init(struct hid_device *hid)
+{
+	return hid_pidff_init_with_quirks(hid, 0);
+}
diff --git a/drivers/hid/usbhid/hid-pidff.h b/drivers/hid/usbhid/hid-pidff.h
new file mode 100644
index 000000000000..dda571e0a5bd
--- /dev/null
+++ b/drivers/hid/usbhid/hid-pidff.h
@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef __HID_PIDFF_H
+#define __HID_PIDFF_H
+
+#include <linux/hid.h>
+
+/* HID PIDFF quirks */
+
+/* Delay field (0xA7) missing. Skip it during set effect report upload */
+#define HID_PIDFF_QUIRK_MISSING_DELAY		BIT(0)
+
+/* Missing Paramter block offset (0x23). Skip it during SET_CONDITION
+   report upload */
+#define HID_PIDFF_QUIRK_MISSING_PBO		BIT(1)
+
+/* Initialise device control field even if logical_minimum != 1 */
+#define HID_PIDFF_QUIRK_PERMISSIVE_CONTROL	BIT(2)
+
+/* Use fixed 0x4000 direction during SET_EFFECT report upload */
+#define HID_PIDFF_QUIRK_FIX_WHEEL_DIRECTION	BIT(3)
+
+/* Force all periodic effects to be uploaded as SINE */
+#define HID_PIDFF_QUIRK_PERIODIC_SINE_ONLY	BIT(4)
+
+#ifdef CONFIG_HID_PID
+int hid_pidff_init(struct hid_device *hid);
+int hid_pidff_init_with_quirks(struct hid_device *hid, u32 initial_quirks);
+#else
+#define hid_pidff_init NULL
+#define hid_pidff_init_with_quirks NULL
+#endif
+
+#endif
diff --git a/drivers/hid/usbhid/usbkbd.c b/drivers/hid/usbhid/usbkbd.c
index c439ed2f16db..af6bc76dbf64 100644
--- a/drivers/hid/usbhid/usbkbd.c
+++ b/drivers/hid/usbhid/usbkbd.c
@@ -160,7 +160,7 @@ static int usb_kbd_event(struct input_dev *dev, unsigned int type,
 		return -1;
 
 	spin_lock_irqsave(&kbd->leds_lock, flags);
-	kbd->newleds = (!!test_bit(LED_KANA,    dev->led) << 3) | (!!test_bit(LED_COMPOSE, dev->led) << 3) |
+	kbd->newleds = (!!test_bit(LED_KANA,    dev->led) << 4) | (!!test_bit(LED_COMPOSE, dev->led) << 3) |
 		       (!!test_bit(LED_SCROLLL, dev->led) << 2) | (!!test_bit(LED_CAPSL,   dev->led) << 1) |
 		       (!!test_bit(LED_NUML,    dev->led));
 
diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c
index 9843b52bd017..1b1112772777 100644
--- a/drivers/hid/wacom_sys.c
+++ b/drivers/hid/wacom_sys.c
@@ -1370,17 +1370,6 @@ static int wacom_led_register_one(struct device *dev, struct wacom *wacom,
 	if (!name)
 		return -ENOMEM;
 
-	if (!read_only) {
-		led->trigger.name = name;
-		error = devm_led_trigger_register(dev, &led->trigger);
-		if (error) {
-			hid_err(wacom->hdev,
-				"failed to register LED trigger %s: %d\n",
-				led->cdev.name, error);
-			return error;
-		}
-	}
-
 	led->group = group;
 	led->id = id;
 	led->wacom = wacom;
@@ -1397,6 +1386,19 @@ static int wacom_led_register_one(struct device *dev, struct wacom *wacom,
 		led->cdev.brightness_set = wacom_led_readonly_brightness_set;
 	}
 
+	if (!read_only) {
+		led->trigger.name = name;
+		if (id == wacom->led.groups[group].select)
+			led->trigger.brightness = wacom_leds_brightness_get(led);
+		error = devm_led_trigger_register(dev, &led->trigger);
+		if (error) {
+			hid_err(wacom->hdev,
+				"failed to register LED trigger %s: %d\n",
+				led->cdev.name, error);
+			return error;
+		}
+	}
+
 	error = devm_led_classdev_register(dev, &led->cdev);
 	if (error) {
 		hid_err(wacom->hdev,
@@ -2019,14 +2021,18 @@ static int wacom_initialize_remotes(struct wacom *wacom)
 
 	remote->remote_dir = kobject_create_and_add("wacom_remote",
 						    &wacom->hdev->dev.kobj);
-	if (!remote->remote_dir)
+	if (!remote->remote_dir) {
+		kfifo_free(&remote->remote_fifo);
 		return -ENOMEM;
+	}
 
 	error = sysfs_create_files(remote->remote_dir, remote_unpair_attrs);
 
 	if (error) {
 		hid_err(wacom->hdev,
 			"cannot create sysfs group err: %d\n", error);
+		kfifo_free(&remote->remote_fifo);
+		kobject_put(remote->remote_dir);
 		return error;
 	}
 
@@ -2872,6 +2878,7 @@ static void wacom_remove(struct hid_device *hdev)
 	hid_hw_stop(hdev);
 
 	cancel_delayed_work_sync(&wacom->init_work);
+	cancel_delayed_work_sync(&wacom->aes_battery_work);
 	cancel_work_sync(&wacom->wireless_work);
 	cancel_work_sync(&wacom->battery_work);
 	cancel_work_sync(&wacom->remote_work);
diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c
index 5a599c90e7a2..c7033ffaba39 100644
--- a/drivers/hid/wacom_wac.c
+++ b/drivers/hid/wacom_wac.c
@@ -4943,6 +4943,10 @@ static const struct wacom_features wacom_features_0x94 =
 	HID_DEVICE(BUS_I2C, HID_GROUP_WACOM, USB_VENDOR_ID_WACOM, prod),\
 	.driver_data = (kernel_ulong_t)&wacom_features_##prod
 
+#define PCI_DEVICE_WACOM(prod)						\
+	HID_DEVICE(BUS_PCI, HID_GROUP_WACOM, USB_VENDOR_ID_WACOM, prod),\
+	.driver_data = (kernel_ulong_t)&wacom_features_##prod
+
 #define USB_DEVICE_LENOVO(prod)					\
 	HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, prod),			\
 	.driver_data = (kernel_ulong_t)&wacom_features_##prod
@@ -5112,6 +5116,7 @@ const struct hid_device_id wacom_ids[] = {
 
 	{ USB_DEVICE_WACOM(HID_ANY_ID) },
 	{ I2C_DEVICE_WACOM(HID_ANY_ID) },
+	{ PCI_DEVICE_WACOM(HID_ANY_ID) },
 	{ BT_DEVICE_WACOM(HID_ANY_ID) },
 	{ }
 };
diff --git a/drivers/hsi/clients/ssi_protocol.c b/drivers/hsi/clients/ssi_protocol.c
index afe470f3661c..6105ea9a6c6a 100644
--- a/drivers/hsi/clients/ssi_protocol.c
+++ b/drivers/hsi/clients/ssi_protocol.c
@@ -401,6 +401,7 @@ static void ssip_reset(struct hsi_client *cl)
 	del_timer(&ssi->rx_wd);
 	del_timer(&ssi->tx_wd);
 	del_timer(&ssi->keep_alive);
+	cancel_work_sync(&ssi->work);
 	ssi->main_state = 0;
 	ssi->send_state = 0;
 	ssi->recv_state = 0;
diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c
index fb8cd8469328..35f26fa1ffe7 100644
--- a/drivers/hv/channel.c
+++ b/drivers/hv/channel.c
@@ -1077,68 +1077,10 @@ int vmbus_sendpacket(struct vmbus_channel *channel, void *buffer,
 EXPORT_SYMBOL(vmbus_sendpacket);
 
 /*
- * vmbus_sendpacket_pagebuffer - Send a range of single-page buffer
- * packets using a GPADL Direct packet type. This interface allows you
- * to control notifying the host. This will be useful for sending
- * batched data. Also the sender can control the send flags
- * explicitly.
- */
-int vmbus_sendpacket_pagebuffer(struct vmbus_channel *channel,
-				struct hv_page_buffer pagebuffers[],
-				u32 pagecount, void *buffer, u32 bufferlen,
-				u64 requestid)
-{
-	int i;
-	struct vmbus_channel_packet_page_buffer desc;
-	u32 descsize;
-	u32 packetlen;
-	u32 packetlen_aligned;
-	struct kvec bufferlist[3];
-	u64 aligned_data = 0;
-
-	if (pagecount > MAX_PAGE_BUFFER_COUNT)
-		return -EINVAL;
-
-	/*
-	 * Adjust the size down since vmbus_channel_packet_page_buffer is the
-	 * largest size we support
-	 */
-	descsize = sizeof(struct vmbus_channel_packet_page_buffer) -
-			  ((MAX_PAGE_BUFFER_COUNT - pagecount) *
-			  sizeof(struct hv_page_buffer));
-	packetlen = descsize + bufferlen;
-	packetlen_aligned = ALIGN(packetlen, sizeof(u64));
-
-	/* Setup the descriptor */
-	desc.type = VM_PKT_DATA_USING_GPA_DIRECT;
-	desc.flags = VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED;
-	desc.dataoffset8 = descsize >> 3; /* in 8-bytes granularity */
-	desc.length8 = (u16)(packetlen_aligned >> 3);
-	desc.transactionid = VMBUS_RQST_ERROR; /* will be updated in hv_ringbuffer_write() */
-	desc.reserved = 0;
-	desc.rangecount = pagecount;
-
-	for (i = 0; i < pagecount; i++) {
-		desc.range[i].len = pagebuffers[i].len;
-		desc.range[i].offset = pagebuffers[i].offset;
-		desc.range[i].pfn	 = pagebuffers[i].pfn;
-	}
-
-	bufferlist[0].iov_base = &desc;
-	bufferlist[0].iov_len = descsize;
-	bufferlist[1].iov_base = buffer;
-	bufferlist[1].iov_len = bufferlen;
-	bufferlist[2].iov_base = &aligned_data;
-	bufferlist[2].iov_len = (packetlen_aligned - packetlen);
-
-	return hv_ringbuffer_write(channel, bufferlist, 3, requestid, NULL);
-}
-EXPORT_SYMBOL_GPL(vmbus_sendpacket_pagebuffer);
-
-/*
- * vmbus_sendpacket_multipagebuffer - Send a multi-page buffer packet
+ * vmbus_sendpacket_mpb_desc - Send one or more multi-page buffer packets
  * using a GPADL Direct packet type.
- * The buffer includes the vmbus descriptor.
+ * The desc argument must include space for the VMBus descriptor. The
+ * rangecount field must already be set.
  */
 int vmbus_sendpacket_mpb_desc(struct vmbus_channel *channel,
 			      struct vmbus_packet_mpb_array *desc,
@@ -1160,7 +1102,6 @@ int vmbus_sendpacket_mpb_desc(struct vmbus_channel *channel,
 	desc->length8 = (u16)(packetlen_aligned >> 3);
 	desc->transactionid = VMBUS_RQST_ERROR; /* will be updated in hv_ringbuffer_write() */
 	desc->reserved = 0;
-	desc->rangecount = 1;
 
 	bufferlist[0].iov_base = desc;
 	bufferlist[0].iov_len = desc_size;
diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c
index f001ae880e1d..27306c17b0c4 100644
--- a/drivers/hv/connection.c
+++ b/drivers/hv/connection.c
@@ -207,10 +207,19 @@ int vmbus_connect(void)
 	mutex_init(&vmbus_connection.channel_mutex);
 
 	/*
+	 * The following Hyper-V interrupt and monitor pages can be used by
+	 * UIO for mapping to user-space, so they should always be allocated on
+	 * system page boundaries. The system page size must be >= the Hyper-V
+	 * page size.
+	 */
+	BUILD_BUG_ON(PAGE_SIZE < HV_HYP_PAGE_SIZE);
+
+	/*
 	 * Setup the vmbus event connection for channel interrupt
 	 * abstraction stuff
 	 */
-	vmbus_connection.int_page = hv_alloc_hyperv_zeroed_page();
+	vmbus_connection.int_page =
+		(void *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
 	if (vmbus_connection.int_page == NULL) {
 		ret = -ENOMEM;
 		goto cleanup;
@@ -225,8 +234,8 @@ int vmbus_connect(void)
 	 * Setup the monitor notification facility. The 1st page for
 	 * parent->child and the 2nd page for child->parent
 	 */
-	vmbus_connection.monitor_pages[0] = hv_alloc_hyperv_page();
-	vmbus_connection.monitor_pages[1] = hv_alloc_hyperv_page();
+	vmbus_connection.monitor_pages[0] = (void *)__get_free_page(GFP_KERNEL);
+	vmbus_connection.monitor_pages[1] = (void *)__get_free_page(GFP_KERNEL);
 	if ((vmbus_connection.monitor_pages[0] == NULL) ||
 	    (vmbus_connection.monitor_pages[1] == NULL)) {
 		ret = -ENOMEM;
@@ -342,21 +351,23 @@ void vmbus_disconnect(void)
 		destroy_workqueue(vmbus_connection.work_queue);
 
 	if (vmbus_connection.int_page) {
-		hv_free_hyperv_page(vmbus_connection.int_page);
+		free_page((unsigned long)vmbus_connection.int_page);
 		vmbus_connection.int_page = NULL;
 	}
 
 	if (vmbus_connection.monitor_pages[0]) {
 		if (!set_memory_encrypted(
 			(unsigned long)vmbus_connection.monitor_pages[0], 1))
-			hv_free_hyperv_page(vmbus_connection.monitor_pages[0]);
+			free_page((unsigned long)
+				vmbus_connection.monitor_pages[0]);
 		vmbus_connection.monitor_pages[0] = NULL;
 	}
 
 	if (vmbus_connection.monitor_pages[1]) {
 		if (!set_memory_encrypted(
 			(unsigned long)vmbus_connection.monitor_pages[1], 1))
-			hv_free_hyperv_page(vmbus_connection.monitor_pages[1]);
+			free_page((unsigned long)
+				vmbus_connection.monitor_pages[1]);
 		vmbus_connection.monitor_pages[1] = NULL;
 	}
 }
diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h
index 52cb744b4d7f..e4136cbaa4d4 100644
--- a/drivers/hv/hyperv_vmbus.h
+++ b/drivers/hv/hyperv_vmbus.h
@@ -485,4 +485,10 @@ static inline int hv_debug_add_dev_dir(struct hv_device *dev)
 
 #endif /* CONFIG_HYPERV_TESTING */
 
+/* Create and remove sysfs entry for memory mapped ring buffers for a channel */
+int hv_create_ring_sysfs(struct vmbus_channel *channel,
+			 int (*hv_mmap_ring_buffer)(struct vmbus_channel *channel,
+						    struct vm_area_struct *vma));
+int hv_remove_ring_sysfs(struct vmbus_channel *channel);
+
 #endif /* _HYPERV_VMBUS_H */
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 9b15f7daf505..616e63fb2f15 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -1792,6 +1792,26 @@ static ssize_t subchannel_id_show(struct vmbus_channel *channel,
 }
 static VMBUS_CHAN_ATTR_RO(subchannel_id);
 
+static int hv_mmap_ring_buffer_wrapper(struct file *filp, struct kobject *kobj,
+				       struct bin_attribute *attr,
+				       struct vm_area_struct *vma)
+{
+	struct vmbus_channel *channel = container_of(kobj, struct vmbus_channel, kobj);
+
+	/*
+	 * hv_(create|remove)_ring_sysfs implementation ensures that mmap_ring_buffer
+	 * is not NULL.
+	 */
+	return channel->mmap_ring_buffer(channel, vma);
+}
+
+static struct bin_attribute chan_attr_ring_buffer = {
+	.attr = {
+		.name = "ring",
+		.mode = 0600,
+	},
+	.mmap = hv_mmap_ring_buffer_wrapper,
+};
 static struct attribute *vmbus_chan_attrs[] = {
 	&chan_attr_out_mask.attr,
 	&chan_attr_in_mask.attr,
@@ -1811,6 +1831,11 @@ static struct attribute *vmbus_chan_attrs[] = {
 	NULL
 };
 
+static struct bin_attribute *vmbus_chan_bin_attrs[] = {
+	&chan_attr_ring_buffer,
+	NULL
+};
+
 /*
  * Channel-level attribute_group callback function. Returns the permission for
  * each attribute, and returns 0 if an attribute is not visible.
@@ -1831,9 +1856,25 @@ static umode_t vmbus_chan_attr_is_visible(struct kobject *kobj,
 	return attr->mode;
 }
 
+static umode_t vmbus_chan_bin_attr_is_visible(struct kobject *kobj,
+					      struct bin_attribute *attr, int idx)
+{
+	const struct vmbus_channel *channel =
+		container_of(kobj, struct vmbus_channel, kobj);
+
+	/* Hide ring attribute if channel's ring_sysfs_visible is set to false */
+	if (attr ==  &chan_attr_ring_buffer && !channel->ring_sysfs_visible)
+		return 0;
+	attr->size = channel->ringbuffer_pagecount << PAGE_SHIFT;
+
+	return attr->attr.mode;
+}
+
 static const struct attribute_group vmbus_chan_group = {
 	.attrs = vmbus_chan_attrs,
-	.is_visible = vmbus_chan_attr_is_visible
+	.bin_attrs = vmbus_chan_bin_attrs,
+	.is_visible = vmbus_chan_attr_is_visible,
+	.is_bin_visible = vmbus_chan_bin_attr_is_visible,
 };
 
 static const struct kobj_type vmbus_chan_ktype = {
@@ -1841,6 +1882,63 @@ static const struct kobj_type vmbus_chan_ktype = {
 	.release = vmbus_chan_release,
 };
 
+/**
+ * hv_create_ring_sysfs() - create "ring" sysfs entry corresponding to ring buffers for a channel.
+ * @channel: Pointer to vmbus_channel structure
+ * @hv_mmap_ring_buffer: function pointer for initializing the function to be called on mmap of
+ *                       channel's "ring" sysfs node, which is for the ring buffer of that channel.
+ *                       Function pointer is of below type:
+ *                       int (*hv_mmap_ring_buffer)(struct vmbus_channel *channel,
+ *                                                  struct vm_area_struct *vma))
+ *                       This has a pointer to the channel and a pointer to vm_area_struct,
+ *                       used for mmap, as arguments.
+ *
+ * Sysfs node for ring buffer of a channel is created along with other fields, however its
+ * visibility is disabled by default. Sysfs creation needs to be controlled when the use-case
+ * is running.
+ * For example, HV_NIC device is used either by uio_hv_generic or hv_netvsc at any given point of
+ * time, and "ring" sysfs is needed only when uio_hv_generic is bound to that device. To avoid
+ * exposing the ring buffer by default, this function is reponsible to enable visibility of
+ * ring for userspace to use.
+ * Note: Race conditions can happen with userspace and it is not encouraged to create new
+ * use-cases for this. This was added to maintain backward compatibility, while solving
+ * one of the race conditions in uio_hv_generic while creating sysfs.
+ *
+ * Returns 0 on success or error code on failure.
+ */
+int hv_create_ring_sysfs(struct vmbus_channel *channel,
+			 int (*hv_mmap_ring_buffer)(struct vmbus_channel *channel,
+						    struct vm_area_struct *vma))
+{
+	struct kobject *kobj = &channel->kobj;
+
+	channel->mmap_ring_buffer = hv_mmap_ring_buffer;
+	channel->ring_sysfs_visible = true;
+
+	return sysfs_update_group(kobj, &vmbus_chan_group);
+}
+EXPORT_SYMBOL_GPL(hv_create_ring_sysfs);
+
+/**
+ * hv_remove_ring_sysfs() - remove ring sysfs entry corresponding to ring buffers for a channel.
+ * @channel: Pointer to vmbus_channel structure
+ *
+ * Hide "ring" sysfs for a channel by changing its is_visible attribute and updating sysfs group.
+ *
+ * Returns 0 on success or error code on failure.
+ */
+int hv_remove_ring_sysfs(struct vmbus_channel *channel)
+{
+	struct kobject *kobj = &channel->kobj;
+	int ret;
+
+	channel->ring_sysfs_visible = false;
+	ret = sysfs_update_group(kobj, &vmbus_chan_group);
+	channel->mmap_ring_buffer = NULL;
+	return ret;
+}
+EXPORT_SYMBOL_GPL(hv_remove_ring_sysfs);
+
 /*
  * vmbus_add_channel_kobj - setup a sub-directory under device/channels
  */
@@ -2262,12 +2360,25 @@ void vmbus_free_mmio(resource_size_t start, resource_size_t size)
 	struct resource *iter;
 
 	mutex_lock(&hyperv_mmio_lock);
+
+	/*
+	 * If all bytes of the MMIO range to be released are within the
+	 * special case fb_mmio shadow region, skip releasing the shadow
+	 * region since no corresponding __request_region() was done
+	 * in vmbus_allocate_mmio().
+	 */
+	if (fb_mmio && start >= fb_mmio->start &&
+	    (start + size - 1 <= fb_mmio->end))
+		goto skip_shadow_release;
+
 	for (iter = hyperv_mmio; iter; iter = iter->sibling) {
 		if ((iter->start >= start + size) || (iter->end <= start))
 			continue;
 
 		__release_region(iter, start, size);
 	}
+
+skip_shadow_release:
 	release_mem_region(start, size);
 	mutex_unlock(&hyperv_mmio_lock);
 
diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig
index 08a3c863f80a..58480a3f4683 100644
--- a/drivers/hwmon/Kconfig
+++ b/drivers/hwmon/Kconfig
@@ -413,7 +413,7 @@ config SENSORS_ASPEED
 	  will be called aspeed_pwm_tacho.
 
 config SENSORS_ASPEED_G6
-	tristate "ASPEED g6 PWM and Fan tach driver"
+	tristate "ASPEED G6 PWM and Fan tach driver"
 	depends on ARCH_ASPEED || COMPILE_TEST
 	depends on PWM
 	help
@@ -421,7 +421,7 @@ config SENSORS_ASPEED_G6
 	  controllers.
 
 	  This driver can also be built as a module. If so, the module
-	  will be called aspeed_pwm_tacho.
+	  will be called aspeed_g6_pwm_tach.
 
 config SENSORS_ATXP1
 	tristate "Attansic ATXP1 VID controller"
diff --git a/drivers/hwmon/ad7314.c b/drivers/hwmon/ad7314.c
index 7802bbf5f958..59424103f634 100644
--- a/drivers/hwmon/ad7314.c
+++ b/drivers/hwmon/ad7314.c
@@ -22,11 +22,13 @@
  */
 #define AD7314_TEMP_MASK		0x7FE0
 #define AD7314_TEMP_SHIFT		5
+#define AD7314_LEADING_ZEROS_MASK	BIT(15)
 
 /*
  * ADT7301 and ADT7302 temperature masks
  */
 #define ADT7301_TEMP_MASK		0x3FFF
+#define ADT7301_LEADING_ZEROS_MASK	(BIT(15) | BIT(14))
 
 enum ad7314_variant {
 	adt7301,
@@ -65,12 +67,20 @@ static ssize_t ad7314_temperature_show(struct device *dev,
 		return ret;
 	switch (spi_get_device_id(chip->spi_dev)->driver_data) {
 	case ad7314:
+		if (ret & AD7314_LEADING_ZEROS_MASK) {
+			/* Invalid read-out, leading zero part is missing */
+			return -EIO;
+		}
 		data = (ret & AD7314_TEMP_MASK) >> AD7314_TEMP_SHIFT;
 		data = sign_extend32(data, 9);
 
 		return sprintf(buf, "%d\n", 250 * data);
 	case adt7301:
 	case adt7302:
+		if (ret & ADT7301_LEADING_ZEROS_MASK) {
+			/* Invalid read-out, leading zero part is missing */
+			return -EIO;
+		}
 		/*
 		 * Documented as a 13 bit twos complement register
 		 * with a sign bit - which is a 14 bit 2's complement
diff --git a/drivers/hwmon/asus-ec-sensors.c b/drivers/hwmon/asus-ec-sensors.c
index 9555366aeaf0..fdc157c7394d 100644
--- a/drivers/hwmon/asus-ec-sensors.c
+++ b/drivers/hwmon/asus-ec-sensors.c
@@ -910,6 +910,10 @@ static int asus_ec_hwmon_read_string(struct device *dev,
 {
 	struct ec_sensors_data *state = dev_get_drvdata(dev);
 	int sensor_index = find_ec_sensor_index(state, type, channel);
+
+	if (sensor_index < 0)
+		return sensor_index;
+
 	*str = get_sensor_info(state, sensor_index)->label;
 
 	return 0;
diff --git a/drivers/hwmon/corsair-cpro.c b/drivers/hwmon/corsair-cpro.c
index e1a7f7aa7f80..b7b911f8359c 100644
--- a/drivers/hwmon/corsair-cpro.c
+++ b/drivers/hwmon/corsair-cpro.c
@@ -89,6 +89,7 @@ struct ccp_device {
 	struct mutex mutex; /* whenever buffer is used, lock before send_usb_cmd */
 	u8 *cmd_buffer;
 	u8 *buffer;
+	int buffer_recv_size; /* number of received bytes in buffer */
 	int target[6];
 	DECLARE_BITMAP(temp_cnct, NUM_TEMP_SENSORS);
 	DECLARE_BITMAP(fan_cnct, NUM_FANS);
@@ -146,6 +147,9 @@ static int send_usb_cmd(struct ccp_device *ccp, u8 command, u8 byte1, u8 byte2,
 	if (!t)
 		return -ETIMEDOUT;
 
+	if (ccp->buffer_recv_size != IN_BUFFER_SIZE)
+		return -EPROTO;
+
 	return ccp_get_errno(ccp);
 }
 
@@ -157,6 +161,7 @@ static int ccp_raw_event(struct hid_device *hdev, struct hid_report *report, u8
 	spin_lock(&ccp->wait_input_report_lock);
 	if (!completion_done(&ccp->wait_input_report)) {
 		memcpy(ccp->buffer, data, min(IN_BUFFER_SIZE, size));
+		ccp->buffer_recv_size = size;
 		complete_all(&ccp->wait_input_report);
 	}
 	spin_unlock(&ccp->wait_input_report_lock);
diff --git a/drivers/hwmon/dell-smm-hwmon.c b/drivers/hwmon/dell-smm-hwmon.c
index f5bdf842040e..b043fbd15c9d 100644
--- a/drivers/hwmon/dell-smm-hwmon.c
+++ b/drivers/hwmon/dell-smm-hwmon.c
@@ -73,7 +73,7 @@
 #define DELL_SMM_LEGACY_EXECUTE	0x1
 
 #define DELL_SMM_NO_TEMP	10
-#define DELL_SMM_NO_FANS	3
+#define DELL_SMM_NO_FANS	4
 
 struct smm_regs {
 	unsigned int eax;
@@ -1074,11 +1074,14 @@ static const struct hwmon_channel_info * const dell_smm_info[] = {
 			   HWMON_F_INPUT | HWMON_F_LABEL | HWMON_F_MIN | HWMON_F_MAX |
 			   HWMON_F_TARGET,
 			   HWMON_F_INPUT | HWMON_F_LABEL | HWMON_F_MIN | HWMON_F_MAX |
+			   HWMON_F_TARGET,
+			   HWMON_F_INPUT | HWMON_F_LABEL | HWMON_F_MIN | HWMON_F_MAX |
 			   HWMON_F_TARGET
 			   ),
 	HWMON_CHANNEL_INFO(pwm,
 			   HWMON_PWM_INPUT | HWMON_PWM_ENABLE,
 			   HWMON_PWM_INPUT,
+			   HWMON_PWM_INPUT,
 			   HWMON_PWM_INPUT
 			   ),
 	NULL
diff --git a/drivers/hwmon/drivetemp.c b/drivers/hwmon/drivetemp.c
index 2a4ec55ddb47..291d91f68646 100644
--- a/drivers/hwmon/drivetemp.c
+++ b/drivers/hwmon/drivetemp.c
@@ -194,7 +194,7 @@ static int drivetemp_scsi_command(struct drivetemp_data *st,
 	scsi_cmd[14] = ata_command;
 
 	err = scsi_execute_cmd(st->sdev, scsi_cmd, op, st->smartdata,
-			       ATA_SECT_SIZE, HZ, 5, NULL);
+			       ATA_SECT_SIZE, 10 * HZ, 5, NULL);
 	if (err > 0)
 		err = -EIO;
 	return err;
diff --git a/drivers/hwmon/emc2305.c b/drivers/hwmon/emc2305.c
index 4d39fbd83769..5b5fccac9635 100644
--- a/drivers/hwmon/emc2305.c
+++ b/drivers/hwmon/emc2305.c
@@ -300,6 +300,12 @@ static int emc2305_set_single_tz(struct device *dev, int idx)
 		dev_err(dev, "Failed to register cooling device %s\n", emc2305_fan_name[idx]);
 		return PTR_ERR(data->cdev_data[cdev_idx].cdev);
 	}
+
+	if (data->cdev_data[cdev_idx].cur_state > 0)
+		/* Update pwm when temperature is above trips */
+		pwm = EMC2305_PWM_STATE2DUTY(data->cdev_data[cdev_idx].cur_state,
+					     data->max_state, EMC2305_FAN_MAX);
+
 	/* Set minimal PWM speed. */
 	if (data->pwm_separate) {
 		ret = emc2305_set_pwm(dev, pwm, cdev_idx);
@@ -313,10 +319,10 @@ static int emc2305_set_single_tz(struct device *dev, int idx)
 		}
 	}
 	data->cdev_data[cdev_idx].cur_state =
-		EMC2305_PWM_DUTY2STATE(data->pwm_min[cdev_idx], data->max_state,
+		EMC2305_PWM_DUTY2STATE(pwm, data->max_state,
 				       EMC2305_FAN_MAX);
 	data->cdev_data[cdev_idx].last_hwmon_state =
-		EMC2305_PWM_DUTY2STATE(data->pwm_min[cdev_idx], data->max_state,
+		EMC2305_PWM_DUTY2STATE(pwm, data->max_state,
 				       EMC2305_FAN_MAX);
 	return 0;
 }
diff --git a/drivers/hwmon/ftsteutates.c b/drivers/hwmon/ftsteutates.c
index a3a07662e491..8aeec16a7a90 100644
--- a/drivers/hwmon/ftsteutates.c
+++ b/drivers/hwmon/ftsteutates.c
@@ -423,13 +423,16 @@ static int fts_read(struct device *dev, enum hwmon_sensor_types type, u32 attr,
 		break;
 	case hwmon_pwm:
 		switch (attr) {
-		case hwmon_pwm_auto_channels_temp:
-			if (data->fan_source[channel] == FTS_FAN_SOURCE_INVALID)
+		case hwmon_pwm_auto_channels_temp: {
+			u8 fan_source = data->fan_source[channel];
+
+			if (fan_source == FTS_FAN_SOURCE_INVALID || fan_source >= BITS_PER_LONG)
 				*val = 0;
 			else
-				*val = BIT(data->fan_source[channel]);
+				*val = BIT(fan_source);
 
 			return 0;
+		}
 		default:
 			break;
 		}
diff --git a/drivers/hwmon/gpio-fan.c b/drivers/hwmon/gpio-fan.c
index d92c536be9af..b779240328d5 100644
--- a/drivers/hwmon/gpio-fan.c
+++ b/drivers/hwmon/gpio-fan.c
@@ -393,7 +393,12 @@ static int gpio_fan_set_cur_state(struct thermal_cooling_device *cdev,
 	if (state >= fan_data->num_speed)
 		return -EINVAL;
 
+	mutex_lock(&fan_data->lock);
+
 	set_fan_speed(fan_data, state);
+
+	mutex_unlock(&fan_data->lock);
+
 	return 0;
 }
 
@@ -489,7 +494,11 @@ MODULE_DEVICE_TABLE(of, of_gpio_fan_match);
 
 static void gpio_fan_stop(void *data)
 {
+	struct gpio_fan_data *fan_data = data;
+
+	mutex_lock(&fan_data->lock);
 	set_fan_speed(data, 0);
+	mutex_unlock(&fan_data->lock);
 }
 
 static int gpio_fan_probe(struct platform_device *pdev)
@@ -562,7 +571,9 @@ static int gpio_fan_suspend(struct device *dev)
 
 	if (fan_data->gpios) {
 		fan_data->resume_speed = fan_data->speed_index;
+		mutex_lock(&fan_data->lock);
 		set_fan_speed(fan_data, 0);
+		mutex_unlock(&fan_data->lock);
 	}
 
 	return 0;
@@ -572,8 +583,11 @@ static int gpio_fan_resume(struct device *dev)
 {
 	struct gpio_fan_data *fan_data = dev_get_drvdata(dev);
 
-	if (fan_data->gpios)
+	if (fan_data->gpios) {
+		mutex_lock(&fan_data->lock);
 		set_fan_speed(fan_data, fan_data->resume_speed);
+		mutex_unlock(&fan_data->lock);
+	}
 
 	return 0;
 }
diff --git a/drivers/hwmon/ltc4282.c b/drivers/hwmon/ltc4282.c
index 4f608a3790fb..953dfe2bd166 100644
--- a/drivers/hwmon/ltc4282.c
+++ b/drivers/hwmon/ltc4282.c
@@ -1512,13 +1512,6 @@ static int ltc4282_setup(struct ltc4282_state *st, struct device *dev)
 	}
 
 	if (device_property_read_bool(dev, "adi,fault-log-enable")) {
-		ret = regmap_set_bits(st->map, LTC4282_ADC_CTRL,
-				      LTC4282_FAULT_LOG_EN_MASK);
-		if (ret)
-			return ret;
-	}
-
-	if (device_property_read_bool(dev, "adi,fault-log-enable")) {
 		ret = regmap_set_bits(st->map, LTC4282_ADC_CTRL, LTC4282_FAULT_LOG_EN_MASK);
 		if (ret)
 			return ret;
diff --git a/drivers/hwmon/nct6775-core.c b/drivers/hwmon/nct6775-core.c
index ee04795b98aa..79bc67ffb998 100644
--- a/drivers/hwmon/nct6775-core.c
+++ b/drivers/hwmon/nct6775-core.c
@@ -42,6 +42,9 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#undef DEFAULT_SYMBOL_NAMESPACE
+#define DEFAULT_SYMBOL_NAMESPACE "HWMON_NCT6775"
+
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/slab.h>
@@ -56,9 +59,6 @@
 #include "lm75.h"
 #include "nct6775.h"
 
-#undef DEFAULT_SYMBOL_NAMESPACE
-#define DEFAULT_SYMBOL_NAMESPACE HWMON_NCT6775
-
 #define USE_ALTERNATE
 
 /* used to set data->name = nct6775_device_names[data->sio_kind] */
@@ -273,8 +273,8 @@ static const s8 NCT6776_BEEP_BITS[NUM_BEEP_BITS] = {
 static const u16 NCT6776_REG_TOLERANCE_H[] = {
 	0x10c, 0x20c, 0x30c, 0x80c, 0x90c, 0xa0c, 0xb0c };
 
-static const u8 NCT6776_REG_PWM_MODE[] = { 0x04, 0, 0, 0, 0, 0 };
-static const u8 NCT6776_PWM_MODE_MASK[] = { 0x01, 0, 0, 0, 0, 0 };
+static const u8 NCT6776_REG_PWM_MODE[] = { 0x04, 0, 0, 0, 0, 0, 0 };
+static const u8 NCT6776_PWM_MODE_MASK[] = { 0x01, 0, 0, 0, 0, 0, 0 };
 
 static const u16 NCT6776_REG_FAN_MIN[] = {
 	0x63a, 0x63c, 0x63e, 0x640, 0x642, 0x64a, 0x64c };
diff --git a/drivers/hwmon/ntc_thermistor.c b/drivers/hwmon/ntc_thermistor.c
index b5352900463f..0d29c8f97ba7 100644
--- a/drivers/hwmon/ntc_thermistor.c
+++ b/drivers/hwmon/ntc_thermistor.c
@@ -181,40 +181,40 @@ static const struct ntc_compensation ncpXXwf104[] = {
 };
 
 static const struct ntc_compensation ncpXXxh103[] = {
-	{ .temp_c	= -40, .ohm	= 247565 },
-	{ .temp_c	= -35, .ohm	= 181742 },
-	{ .temp_c	= -30, .ohm	= 135128 },
-	{ .temp_c	= -25, .ohm	= 101678 },
-	{ .temp_c	= -20, .ohm	= 77373 },
-	{ .temp_c	= -15, .ohm	= 59504 },
-	{ .temp_c	= -10, .ohm	= 46222 },
-	{ .temp_c	= -5, .ohm	= 36244 },
-	{ .temp_c	= 0, .ohm	= 28674 },
-	{ .temp_c	= 5, .ohm	= 22878 },
-	{ .temp_c	= 10, .ohm	= 18399 },
-	{ .temp_c	= 15, .ohm	= 14910 },
-	{ .temp_c	= 20, .ohm	= 12169 },
+	{ .temp_c	= -40, .ohm	= 195652 },
+	{ .temp_c	= -35, .ohm	= 148171 },
+	{ .temp_c	= -30, .ohm	= 113347 },
+	{ .temp_c	= -25, .ohm	= 87559 },
+	{ .temp_c	= -20, .ohm	= 68237 },
+	{ .temp_c	= -15, .ohm	= 53650 },
+	{ .temp_c	= -10, .ohm	= 42506 },
+	{ .temp_c	= -5, .ohm	= 33892 },
+	{ .temp_c	= 0, .ohm	= 27219 },
+	{ .temp_c	= 5, .ohm	= 22021 },
+	{ .temp_c	= 10, .ohm	= 17926 },
+	{ .temp_c	= 15, .ohm	= 14674 },
+	{ .temp_c	= 20, .ohm	= 12081 },
 	{ .temp_c	= 25, .ohm	= 10000 },
-	{ .temp_c	= 30, .ohm	= 8271 },
-	{ .temp_c	= 35, .ohm	= 6883 },
-	{ .temp_c	= 40, .ohm	= 5762 },
-	{ .temp_c	= 45, .ohm	= 4851 },
-	{ .temp_c	= 50, .ohm	= 4105 },
-	{ .temp_c	= 55, .ohm	= 3492 },
-	{ .temp_c	= 60, .ohm	= 2985 },
-	{ .temp_c	= 65, .ohm	= 2563 },
-	{ .temp_c	= 70, .ohm	= 2211 },
-	{ .temp_c	= 75, .ohm	= 1915 },
-	{ .temp_c	= 80, .ohm	= 1666 },
-	{ .temp_c	= 85, .ohm	= 1454 },
-	{ .temp_c	= 90, .ohm	= 1275 },
-	{ .temp_c	= 95, .ohm	= 1121 },
-	{ .temp_c	= 100, .ohm	= 990 },
-	{ .temp_c	= 105, .ohm	= 876 },
-	{ .temp_c	= 110, .ohm	= 779 },
-	{ .temp_c	= 115, .ohm	= 694 },
-	{ .temp_c	= 120, .ohm	= 620 },
-	{ .temp_c	= 125, .ohm	= 556 },
+	{ .temp_c	= 30, .ohm	= 8315 },
+	{ .temp_c	= 35, .ohm	= 6948 },
+	{ .temp_c	= 40, .ohm	= 5834 },
+	{ .temp_c	= 45, .ohm	= 4917 },
+	{ .temp_c	= 50, .ohm	= 4161 },
+	{ .temp_c	= 55, .ohm	= 3535 },
+	{ .temp_c	= 60, .ohm	= 3014 },
+	{ .temp_c	= 65, .ohm	= 2586 },
+	{ .temp_c	= 70, .ohm	= 2228 },
+	{ .temp_c	= 75, .ohm	= 1925 },
+	{ .temp_c	= 80, .ohm	= 1669 },
+	{ .temp_c	= 85, .ohm	= 1452 },
+	{ .temp_c	= 90, .ohm	= 1268 },
+	{ .temp_c	= 95, .ohm	= 1110 },
+	{ .temp_c	= 100, .ohm	= 974 },
+	{ .temp_c	= 105, .ohm	= 858 },
+	{ .temp_c	= 110, .ohm	= 758 },
+	{ .temp_c	= 115, .ohm	= 672 },
+	{ .temp_c	= 120, .ohm	= 596 },
+	{ .temp_c	= 125, .ohm	= 531 },
 };
 
 /*
diff --git a/drivers/hwmon/occ/common.c b/drivers/hwmon/occ/common.c
index 9486db249c64..b3694a4209b9 100644
--- a/drivers/hwmon/occ/common.c
+++ b/drivers/hwmon/occ/common.c
@@ -459,12 +459,10 @@ static ssize_t occ_show_power_1(struct device *dev,
 	return sysfs_emit(buf, "%llu\n", val);
 }
 
-static u64 occ_get_powr_avg(u64 *accum, u32 *samples)
+static u64 occ_get_powr_avg(u64 accum, u32 samples)
 {
-	u64 divisor = get_unaligned_be32(samples);
-
-	return (divisor == 0) ? 0 :
-		div64_u64(get_unaligned_be64(accum) * 1000000ULL, divisor);
+	return (samples == 0) ? 0 :
+		mul_u64_u32_div(accum, 1000000UL, samples);
 }
 
 static ssize_t occ_show_power_2(struct device *dev,
@@ -489,8 +487,8 @@ static ssize_t occ_show_power_2(struct device *dev,
 				  get_unaligned_be32(&power->sensor_id),
 				  power->function_id, power->apss_channel);
 	case 1:
-		val = occ_get_powr_avg(&power->accumulator,
-				       &power->update_tag);
+		val = occ_get_powr_avg(get_unaligned_be64(&power->accumulator),
+				       get_unaligned_be32(&power->update_tag));
 		break;
 	case 2:
 		val = (u64)get_unaligned_be32(&power->update_tag) *
@@ -527,8 +525,8 @@ static ssize_t occ_show_power_a0(struct device *dev,
 		return sysfs_emit(buf, "%u_system\n",
 				  get_unaligned_be32(&power->sensor_id));
 	case 1:
-		val = occ_get_powr_avg(&power->system.accumulator,
-				       &power->system.update_tag);
+		val = occ_get_powr_avg(get_unaligned_be64(&power->system.accumulator),
+				       get_unaligned_be32(&power->system.update_tag));
 		break;
 	case 2:
 		val = (u64)get_unaligned_be32(&power->system.update_tag) *
@@ -541,8 +539,8 @@ static ssize_t occ_show_power_a0(struct device *dev,
 		return sysfs_emit(buf, "%u_proc\n",
 				  get_unaligned_be32(&power->sensor_id));
 	case 5:
-		val = occ_get_powr_avg(&power->proc.accumulator,
-				       &power->proc.update_tag);
+		val = occ_get_powr_avg(get_unaligned_be64(&power->proc.accumulator),
+				       get_unaligned_be32(&power->proc.update_tag));
 		break;
 	case 6:
 		val = (u64)get_unaligned_be32(&power->proc.update_tag) *
@@ -555,8 +553,8 @@ static ssize_t occ_show_power_a0(struct device *dev,
 		return sysfs_emit(buf, "%u_vdd\n",
 				  get_unaligned_be32(&power->sensor_id));
 	case 9:
-		val = occ_get_powr_avg(&power->vdd.accumulator,
-				       &power->vdd.update_tag);
+		val = occ_get_powr_avg(get_unaligned_be64(&power->vdd.accumulator),
+				       get_unaligned_be32(&power->vdd.update_tag));
 		break;
 	case 10:
 		val = (u64)get_unaligned_be32(&power->vdd.update_tag) *
@@ -569,8 +567,8 @@ static ssize_t occ_show_power_a0(struct device *dev,
 		return sysfs_emit(buf, "%u_vdn\n",
 				  get_unaligned_be32(&power->sensor_id));
 	case 13:
-		val = occ_get_powr_avg(&power->vdn.accumulator,
-				       &power->vdn.update_tag);
+		val = occ_get_powr_avg(get_unaligned_be64(&power->vdn.accumulator),
+				       get_unaligned_be32(&power->vdn.update_tag));
 		break;
 	case 14:
 		val = (u64)get_unaligned_be32(&power->vdn.update_tag) *
@@ -747,29 +745,30 @@ static ssize_t occ_show_extended(struct device *dev,
 }
 
 /*
- * Some helper macros to make it easier to define an occ_attribute. Since these
- * are dynamically allocated, we shouldn't use the existing kernel macros which
+ * A helper to make it easier to define an occ_attribute. Since these
+ * are dynamically allocated, we cannot use the existing kernel macros which
  * stringify the name argument.
  */
-#define ATTR_OCC(_name, _mode, _show, _store) {				\
-	.attr	= {							\
-		.name = _name,						\
-		.mode = VERIFY_OCTAL_PERMISSIONS(_mode),		\
-	},								\
-	.show	= _show,						\
-	.store	= _store,						\
-}
-
-#define SENSOR_ATTR_OCC(_name, _mode, _show, _store, _nr, _index) {	\
-	.dev_attr	= ATTR_OCC(_name, _mode, _show, _store),	\
-	.index		= _index,					\
-	.nr		= _nr,						\
+static void occ_init_attribute(struct occ_attribute *attr, int mode,
+	ssize_t (*show)(struct device *dev, struct device_attribute *attr, char *buf),
+	ssize_t (*store)(struct device *dev, struct device_attribute *attr,
+				   const char *buf, size_t count),
+	int nr, int index, const char *fmt, ...)
+{
+	va_list args;
+
+	va_start(args, fmt);
+	vsnprintf(attr->name, sizeof(attr->name), fmt, args);
+	va_end(args);
+
+	attr->sensor.dev_attr.attr.name = attr->name;
+	attr->sensor.dev_attr.attr.mode = mode;
+	attr->sensor.dev_attr.show = show;
+	attr->sensor.dev_attr.store = store;
+	attr->sensor.index = index;
+	attr->sensor.nr = nr;
 }
 
-#define OCC_INIT_ATTR(_name, _mode, _show, _store, _nr, _index)		\
-	((struct sensor_device_attribute_2)				\
-		SENSOR_ATTR_OCC(_name, _mode, _show, _store, _nr, _index))
-
 /*
  * Allocate and instatiate sensor_device_attribute_2s. It's most efficient to
  * use our own instead of the built-in hwmon attribute types.
@@ -855,14 +854,15 @@ static int occ_setup_sensor_attrs(struct occ *occ)
 		sensors->extended.num_sensors = 0;
 	}
 
-	occ->attrs = devm_kzalloc(dev, sizeof(*occ->attrs) * num_attrs,
+	occ->attrs = devm_kcalloc(dev, num_attrs, sizeof(*occ->attrs),
 				  GFP_KERNEL);
 	if (!occ->attrs)
 		return -ENOMEM;
 
 	/* null-terminated list */
-	occ->group.attrs = devm_kzalloc(dev, sizeof(*occ->group.attrs) *
-					num_attrs + 1, GFP_KERNEL);
+	occ->group.attrs = devm_kcalloc(dev, num_attrs + 1,
+					sizeof(*occ->group.attrs),
+					GFP_KERNEL);
 	if (!occ->group.attrs)
 		return -ENOMEM;
 
@@ -872,43 +872,33 @@ static int occ_setup_sensor_attrs(struct occ *occ)
 		s = i + 1;
 		temp = ((struct temp_sensor_2 *)sensors->temp.data) + i;
 
-		snprintf(attr->name, sizeof(attr->name), "temp%d_label", s);
-		attr->sensor = OCC_INIT_ATTR(attr->name, 0444, show_temp, NULL,
-					     0, i);
+		occ_init_attribute(attr, 0444, show_temp, NULL,
+				   0, i, "temp%d_label", s);
 		attr++;
 
 		if (sensors->temp.version == 2 &&
 		    temp->fru_type == OCC_FRU_TYPE_VRM) {
-			snprintf(attr->name, sizeof(attr->name),
-				 "temp%d_alarm", s);
+			occ_init_attribute(attr, 0444, show_temp, NULL,
+					   1, i, "temp%d_alarm", s);
 		} else {
-			snprintf(attr->name, sizeof(attr->name),
-				 "temp%d_input", s);
+			occ_init_attribute(attr, 0444, show_temp, NULL,
+					   1, i, "temp%d_input", s);
 		}
 
-		attr->sensor = OCC_INIT_ATTR(attr->name, 0444, show_temp, NULL,
-					     1, i);
 		attr++;
 
 		if (sensors->temp.version > 1) {
-			snprintf(attr->name, sizeof(attr->name),
-				 "temp%d_fru_type", s);
-			attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
-						     show_temp, NULL, 2, i);
+			occ_init_attribute(attr, 0444, show_temp, NULL,
+					   2, i, "temp%d_fru_type", s);
 			attr++;
 
-			snprintf(attr->name, sizeof(attr->name),
-				 "temp%d_fault", s);
-			attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
-						     show_temp, NULL, 3, i);
+			occ_init_attribute(attr, 0444, show_temp, NULL,
+					   3, i, "temp%d_fault", s);
 			attr++;
 
 			if (sensors->temp.version == 0x10) {
-				snprintf(attr->name, sizeof(attr->name),
-					 "temp%d_max", s);
-				attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
-							     show_temp, NULL,
-							     4, i);
+				occ_init_attribute(attr, 0444, show_temp, NULL,
+						   4, i, "temp%d_max", s);
 				attr++;
 			}
 		}
@@ -917,14 +907,12 @@ static int occ_setup_sensor_attrs(struct occ *occ)
 	for (i = 0; i < sensors->freq.num_sensors; ++i) {
 		s = i + 1;
 
-		snprintf(attr->name, sizeof(attr->name), "freq%d_label", s);
-		attr->sensor = OCC_INIT_ATTR(attr->name, 0444, show_freq, NULL,
-					     0, i);
+		occ_init_attribute(attr, 0444, show_freq, NULL,
+				   0, i, "freq%d_label", s);
 		attr++;
 
-		snprintf(attr->name, sizeof(attr->name), "freq%d_input", s);
-		attr->sensor = OCC_INIT_ATTR(attr->name, 0444, show_freq, NULL,
-					     1, i);
+		occ_init_attribute(attr, 0444, show_freq, NULL,
+				   1, i, "freq%d_input", s);
 		attr++;
 	}
 
@@ -940,32 +928,24 @@ static int occ_setup_sensor_attrs(struct occ *occ)
 			s = (i * 4) + 1;
 
 			for (j = 0; j < 4; ++j) {
-				snprintf(attr->name, sizeof(attr->name),
-					 "power%d_label", s);
-				attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
-							     show_power, NULL,
-							     nr++, i);
+				occ_init_attribute(attr, 0444, show_power,
+						   NULL, nr++, i,
+						   "power%d_label", s);
 				attr++;
 
-				snprintf(attr->name, sizeof(attr->name),
-					 "power%d_average", s);
-				attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
-							     show_power, NULL,
-							     nr++, i);
+				occ_init_attribute(attr, 0444, show_power,
+						   NULL, nr++, i,
+						   "power%d_average", s);
 				attr++;
 
-				snprintf(attr->name, sizeof(attr->name),
-					 "power%d_average_interval", s);
-				attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
-							     show_power, NULL,
-							     nr++, i);
+				occ_init_attribute(attr, 0444, show_power,
+						   NULL, nr++, i,
+						   "power%d_average_interval", s);
 				attr++;
 
-				snprintf(attr->name, sizeof(attr->name),
-					 "power%d_input", s);
-				attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
-							     show_power, NULL,
-							     nr++, i);
+				occ_init_attribute(attr, 0444, show_power,
+						   NULL, nr++, i,
+						   "power%d_input", s);
 				attr++;
 
 				s++;
@@ -977,28 +957,20 @@ static int occ_setup_sensor_attrs(struct occ *occ)
 		for (i = 0; i < sensors->power.num_sensors; ++i) {
 			s = i + 1;
 
-			snprintf(attr->name, sizeof(attr->name),
-				 "power%d_label", s);
-			attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
-						     show_power, NULL, 0, i);
+			occ_init_attribute(attr, 0444, show_power, NULL,
+					   0, i, "power%d_label", s);
 			attr++;
 
-			snprintf(attr->name, sizeof(attr->name),
-				 "power%d_average", s);
-			attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
-						     show_power, NULL, 1, i);
+			occ_init_attribute(attr, 0444, show_power, NULL,
+					   1, i, "power%d_average", s);
 			attr++;
 
-			snprintf(attr->name, sizeof(attr->name),
-				 "power%d_average_interval", s);
-			attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
-						     show_power, NULL, 2, i);
+			occ_init_attribute(attr, 0444, show_power, NULL,
+					   2, i, "power%d_average_interval", s);
 			attr++;
 
-			snprintf(attr->name, sizeof(attr->name),
-				 "power%d_input", s);
-			attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
-						     show_power, NULL, 3, i);
+			occ_init_attribute(attr, 0444, show_power, NULL,
+					   3, i, "power%d_input", s);
 			attr++;
 		}
 
@@ -1006,56 +978,43 @@ static int occ_setup_sensor_attrs(struct occ *occ)
 	}
 
 	if (sensors->caps.num_sensors >= 1) {
-		snprintf(attr->name, sizeof(attr->name), "power%d_label", s);
-		attr->sensor = OCC_INIT_ATTR(attr->name, 0444, show_caps, NULL,
-					     0, 0);
+		occ_init_attribute(attr, 0444, show_caps, NULL,
+				   0, 0, "power%d_label", s);
 		attr++;
 
-		snprintf(attr->name, sizeof(attr->name), "power%d_cap", s);
-		attr->sensor = OCC_INIT_ATTR(attr->name, 0444, show_caps, NULL,
-					     1, 0);
+		occ_init_attribute(attr, 0444, show_caps, NULL,
+				   1, 0, "power%d_cap", s);
 		attr++;
 
-		snprintf(attr->name, sizeof(attr->name), "power%d_input", s);
-		attr->sensor = OCC_INIT_ATTR(attr->name, 0444, show_caps, NULL,
-					     2, 0);
+		occ_init_attribute(attr, 0444, show_caps, NULL,
+				   2, 0, "power%d_input", s);
 		attr++;
 
-		snprintf(attr->name, sizeof(attr->name),
-			 "power%d_cap_not_redundant", s);
-		attr->sensor = OCC_INIT_ATTR(attr->name, 0444, show_caps, NULL,
-					     3, 0);
+		occ_init_attribute(attr, 0444, show_caps, NULL,
+				   3, 0, "power%d_cap_not_redundant", s);
 		attr++;
 
-		snprintf(attr->name, sizeof(attr->name), "power%d_cap_max", s);
-		attr->sensor = OCC_INIT_ATTR(attr->name, 0444, show_caps, NULL,
-					     4, 0);
+		occ_init_attribute(attr, 0444, show_caps, NULL,
+				   4, 0, "power%d_cap_max", s);
 		attr++;
 
-		snprintf(attr->name, sizeof(attr->name), "power%d_cap_min", s);
-		attr->sensor = OCC_INIT_ATTR(attr->name, 0444, show_caps, NULL,
-					     5, 0);
+		occ_init_attribute(attr, 0444, show_caps, NULL,
+				   5, 0, "power%d_cap_min", s);
 		attr++;
 
-		snprintf(attr->name, sizeof(attr->name), "power%d_cap_user",
-			 s);
-		attr->sensor = OCC_INIT_ATTR(attr->name, 0644, show_caps,
-					     occ_store_caps_user, 6, 0);
+		occ_init_attribute(attr, 0644, show_caps, occ_store_caps_user,
+				   6, 0, "power%d_cap_user", s);
 		attr++;
 
 		if (sensors->caps.version > 1) {
-			snprintf(attr->name, sizeof(attr->name),
-				 "power%d_cap_user_source", s);
-			attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
-						     show_caps, NULL, 7, 0);
+			occ_init_attribute(attr, 0444, show_caps, NULL,
+					   7, 0, "power%d_cap_user_source", s);
 			attr++;
 
 			if (sensors->caps.version > 2) {
-				snprintf(attr->name, sizeof(attr->name),
-					 "power%d_cap_min_soft", s);
-				attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
-							     show_caps, NULL,
-							     8, 0);
+				occ_init_attribute(attr, 0444, show_caps, NULL,
+						   8, 0,
+						   "power%d_cap_min_soft", s);
 				attr++;
 			}
 		}
@@ -1064,19 +1023,16 @@ static int occ_setup_sensor_attrs(struct occ *occ)
 	for (i = 0; i < sensors->extended.num_sensors; ++i) {
 		s = i + 1;
 
-		snprintf(attr->name, sizeof(attr->name), "extn%d_label", s);
-		attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
-					     occ_show_extended, NULL, 0, i);
+		occ_init_attribute(attr, 0444, occ_show_extended, NULL,
+				   0, i, "extn%d_label", s);
 		attr++;
 
-		snprintf(attr->name, sizeof(attr->name), "extn%d_flags", s);
-		attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
-					     occ_show_extended, NULL, 1, i);
+		occ_init_attribute(attr, 0444, occ_show_extended, NULL,
+				   1, i, "extn%d_flags", s);
 		attr++;
 
-		snprintf(attr->name, sizeof(attr->name), "extn%d_input", s);
-		attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
-					     occ_show_extended, NULL, 2, i);
+		occ_init_attribute(attr, 0444, occ_show_extended, NULL,
+				   2, i, "extn%d_input", s);
 		attr++;
 	}
 
diff --git a/drivers/hwmon/peci/dimmtemp.c b/drivers/hwmon/peci/dimmtemp.c
index 4a72e9712408..b7b09780c7b0 100644
--- a/drivers/hwmon/peci/dimmtemp.c
+++ b/drivers/hwmon/peci/dimmtemp.c
@@ -127,8 +127,6 @@ static int update_thresholds(struct peci_dimmtemp *priv, int dimm_no)
 		return 0;
 
 	ret = priv->gen_info->read_thresholds(priv, dimm_order, chan_rank, &data);
-	if (ret == -ENODATA) /* Use default or previous value */
-		return 0;
 	if (ret)
 		return ret;
 
@@ -509,11 +507,11 @@ read_thresholds_icx(struct peci_dimmtemp *priv, int dimm_order, int chan_rank, u
 
 	ret = peci_ep_pci_local_read(priv->peci_dev, 0, 13, 0, 2, 0xd4, &reg_val);
 	if (ret || !(reg_val & BIT(31)))
-		return -ENODATA; /* Use default or previous value */
+		return -ENODATA;
 
 	ret = peci_ep_pci_local_read(priv->peci_dev, 0, 13, 0, 2, 0xd0, &reg_val);
 	if (ret)
-		return -ENODATA; /* Use default or previous value */
+		return -ENODATA;
 
 	/*
 	 * Device 26, Offset 224e0: IMC 0 channel 0 -> rank 0
@@ -546,11 +544,11 @@ read_thresholds_spr(struct peci_dimmtemp *priv, int dimm_order, int chan_rank, u
 
 	ret = peci_ep_pci_local_read(priv->peci_dev, 0, 30, 0, 2, 0xd4, &reg_val);
 	if (ret || !(reg_val & BIT(31)))
-		return -ENODATA; /* Use default or previous value */
+		return -ENODATA;
 
 	ret = peci_ep_pci_local_read(priv->peci_dev, 0, 30, 0, 2, 0xd0, &reg_val);
 	if (ret)
-		return -ENODATA; /* Use default or previous value */
+		return -ENODATA;
 
 	/*
 	 * Device 26, Offset 219a8: IMC 0 channel 0 -> rank 0
diff --git a/drivers/hwmon/pmbus/max34440.c b/drivers/hwmon/pmbus/max34440.c
index fe7f6b1b0985..e14be8ebaad3 100644
--- a/drivers/hwmon/pmbus/max34440.c
+++ b/drivers/hwmon/pmbus/max34440.c
@@ -34,16 +34,21 @@ enum chips { max34440, max34441, max34446, max34451, max34460, max34461 };
 /*
  * The whole max344* family have IOUT_OC_WARN_LIMIT and IOUT_OC_FAULT_LIMIT
  * swapped from the standard pmbus spec addresses.
+ * For max34451, version MAX34451ETNA6+ and later has this issue fixed.
  */
 #define MAX34440_IOUT_OC_WARN_LIMIT	0x46
 #define MAX34440_IOUT_OC_FAULT_LIMIT	0x4A
 
+#define MAX34451ETNA6_MFR_REV		0x0012
+
 #define MAX34451_MFR_CHANNEL_CONFIG	0xe4
 #define MAX34451_MFR_CHANNEL_CONFIG_SEL_MASK	0x3f
 
 struct max34440_data {
 	int id;
 	struct pmbus_driver_info info;
+	u8 iout_oc_warn_limit;
+	u8 iout_oc_fault_limit;
 };
 
 #define to_max34440_data(x)  container_of(x, struct max34440_data, info)
@@ -60,11 +65,11 @@ static int max34440_read_word_data(struct i2c_client *client, int page,
 	switch (reg) {
 	case PMBUS_IOUT_OC_FAULT_LIMIT:
 		ret = pmbus_read_word_data(client, page, phase,
-					   MAX34440_IOUT_OC_FAULT_LIMIT);
+					   data->iout_oc_fault_limit);
 		break;
 	case PMBUS_IOUT_OC_WARN_LIMIT:
 		ret = pmbus_read_word_data(client, page, phase,
-					   MAX34440_IOUT_OC_WARN_LIMIT);
+					   data->iout_oc_warn_limit);
 		break;
 	case PMBUS_VIRT_READ_VOUT_MIN:
 		ret = pmbus_read_word_data(client, page, phase,
@@ -133,11 +138,11 @@ static int max34440_write_word_data(struct i2c_client *client, int page,
 
 	switch (reg) {
 	case PMBUS_IOUT_OC_FAULT_LIMIT:
-		ret = pmbus_write_word_data(client, page, MAX34440_IOUT_OC_FAULT_LIMIT,
+		ret = pmbus_write_word_data(client, page, data->iout_oc_fault_limit,
 					    word);
 		break;
 	case PMBUS_IOUT_OC_WARN_LIMIT:
-		ret = pmbus_write_word_data(client, page, MAX34440_IOUT_OC_WARN_LIMIT,
+		ret = pmbus_write_word_data(client, page, data->iout_oc_warn_limit,
 					    word);
 		break;
 	case PMBUS_VIRT_RESET_POUT_HISTORY:
@@ -235,6 +240,25 @@ static int max34451_set_supported_funcs(struct i2c_client *client,
 	 */
 
 	int page, rv;
+	bool max34451_na6 = false;
+
+	rv = i2c_smbus_read_word_data(client, PMBUS_MFR_REVISION);
+	if (rv < 0)
+		return rv;
+
+	if (rv >= MAX34451ETNA6_MFR_REV) {
+		max34451_na6 = true;
+		data->info.format[PSC_VOLTAGE_IN] = direct;
+		data->info.format[PSC_CURRENT_IN] = direct;
+		data->info.m[PSC_VOLTAGE_IN] = 1;
+		data->info.b[PSC_VOLTAGE_IN] = 0;
+		data->info.R[PSC_VOLTAGE_IN] = 3;
+		data->info.m[PSC_CURRENT_IN] = 1;
+		data->info.b[PSC_CURRENT_IN] = 0;
+		data->info.R[PSC_CURRENT_IN] = 2;
+		data->iout_oc_fault_limit = PMBUS_IOUT_OC_FAULT_LIMIT;
+		data->iout_oc_warn_limit = PMBUS_IOUT_OC_WARN_LIMIT;
+	}
 
 	for (page = 0; page < 16; page++) {
 		rv = i2c_smbus_write_byte_data(client, PMBUS_PAGE, page);
@@ -251,16 +275,30 @@ static int max34451_set_supported_funcs(struct i2c_client *client,
 		case 0x20:
 			data->info.func[page] = PMBUS_HAVE_VOUT |
 				PMBUS_HAVE_STATUS_VOUT;
+
+			if (max34451_na6)
+				data->info.func[page] |= PMBUS_HAVE_VIN |
+					PMBUS_HAVE_STATUS_INPUT;
 			break;
 		case 0x21:
 			data->info.func[page] = PMBUS_HAVE_VOUT;
+
+			if (max34451_na6)
+				data->info.func[page] |= PMBUS_HAVE_VIN;
 			break;
 		case 0x22:
 			data->info.func[page] = PMBUS_HAVE_IOUT |
 				PMBUS_HAVE_STATUS_IOUT;
+
+			if (max34451_na6)
+				data->info.func[page] |= PMBUS_HAVE_IIN |
+					PMBUS_HAVE_STATUS_INPUT;
 			break;
 		case 0x23:
 			data->info.func[page] = PMBUS_HAVE_IOUT;
+
+			if (max34451_na6)
+				data->info.func[page] |= PMBUS_HAVE_IIN;
 			break;
 		default:
 			break;
@@ -494,6 +532,8 @@ static int max34440_probe(struct i2c_client *client)
 		return -ENOMEM;
 	data->id = i2c_match_id(max34440_id, client)->driver_data;
 	data->info = max34440_info[data->id];
+	data->iout_oc_fault_limit = MAX34440_IOUT_OC_FAULT_LIMIT;
+	data->iout_oc_warn_limit = MAX34440_IOUT_OC_WARN_LIMIT;
 
 	if (data->id == max34451) {
 		rv = max34451_set_supported_funcs(client, data);
diff --git a/drivers/hwmon/pmbus/pmbus.c b/drivers/hwmon/pmbus/pmbus.c
index ec40c5c59954..59424dc518c8 100644
--- a/drivers/hwmon/pmbus/pmbus.c
+++ b/drivers/hwmon/pmbus/pmbus.c
@@ -103,6 +103,8 @@ static int pmbus_identify(struct i2c_client *client,
 		if (pmbus_check_byte_register(client, 0, PMBUS_PAGE)) {
 			int page;
 
+			info->pages = PMBUS_PAGES;
+
 			for (page = 1; page < PMBUS_PAGES; page++) {
 				if (pmbus_set_page(client, page, 0xff) < 0)
 					break;
diff --git a/drivers/hwmon/xgene-hwmon.c b/drivers/hwmon/xgene-hwmon.c
index 5e0759a70f6d..4e05077e4256 100644
--- a/drivers/hwmon/xgene-hwmon.c
+++ b/drivers/hwmon/xgene-hwmon.c
@@ -105,7 +105,7 @@ struct xgene_hwmon_dev {
 
 	phys_addr_t		comm_base_addr;
 	void			*pcc_comm_addr;
-	u64			usecs_lat;
+	unsigned int		usecs_lat;
 };
 
 /*
@@ -706,7 +706,7 @@ static int xgene_hwmon_probe(struct platform_device *pdev)
 			goto out;
 		}
 
-		if (!ctx->pcc_comm_addr) {
+		if (IS_ERR_OR_NULL(ctx->pcc_comm_addr)) {
 			dev_err(&pdev->dev,
 				"Failed to ioremap PCC comm region\n");
 			rc = -ENOMEM;
diff --git a/drivers/hwtracing/coresight/coresight-catu.c b/drivers/hwtracing/coresight/coresight-catu.c
index bfea880d6dfb..25fd02955c38 100644
--- a/drivers/hwtracing/coresight/coresight-catu.c
+++ b/drivers/hwtracing/coresight/coresight-catu.c
@@ -269,7 +269,7 @@ catu_init_sg_table(struct device *catu_dev, int node,
 	 * Each table can address upto 1MB and we can have
 	 * CATU_PAGES_PER_SYSPAGE tables in a system page.
 	 */
-	nr_tpages = DIV_ROUND_UP(size, SZ_1M) / CATU_PAGES_PER_SYSPAGE;
+	nr_tpages = DIV_ROUND_UP(size, CATU_PAGES_PER_SYSPAGE * SZ_1M);
 	catu_table = tmc_alloc_sg_table(catu_dev, node, nr_tpages,
 					size >> PAGE_SHIFT, pages);
 	if (IS_ERR(catu_table))
@@ -458,12 +458,17 @@ static int catu_enable_hw(struct catu_drvdata *drvdata, enum cs_mode cs_mode,
 static int catu_enable(struct coresight_device *csdev, enum cs_mode mode,
 		       void *data)
 {
-	int rc;
+	int rc = 0;
 	struct catu_drvdata *catu_drvdata = csdev_to_catu_drvdata(csdev);
 
-	CS_UNLOCK(catu_drvdata->base);
-	rc = catu_enable_hw(catu_drvdata, mode, data);
-	CS_LOCK(catu_drvdata->base);
+	guard(raw_spinlock_irqsave)(&catu_drvdata->spinlock);
+	if (csdev->refcnt == 0) {
+		CS_UNLOCK(catu_drvdata->base);
+		rc = catu_enable_hw(catu_drvdata, mode, data);
+		CS_LOCK(catu_drvdata->base);
+	}
+	if (!rc)
+		csdev->refcnt++;
 	return rc;
 }
 
@@ -486,12 +491,15 @@ static int catu_disable_hw(struct catu_drvdata *drvdata)
 
 static int catu_disable(struct coresight_device *csdev, void *__unused)
 {
-	int rc;
+	int rc = 0;
 	struct catu_drvdata *catu_drvdata = csdev_to_catu_drvdata(csdev);
 
-	CS_UNLOCK(catu_drvdata->base);
-	rc = catu_disable_hw(catu_drvdata);
-	CS_LOCK(catu_drvdata->base);
+	guard(raw_spinlock_irqsave)(&catu_drvdata->spinlock);
+	if (--csdev->refcnt == 0) {
+		CS_UNLOCK(catu_drvdata->base);
+		rc = catu_disable_hw(catu_drvdata);
+		CS_LOCK(catu_drvdata->base);
+	}
 	return rc;
 }
 
@@ -550,6 +558,7 @@ static int __catu_probe(struct device *dev, struct resource *res)
 	dev->platform_data = pdata;
 
 	drvdata->base = base;
+	raw_spin_lock_init(&drvdata->spinlock);
 	catu_desc.access = CSDEV_ACCESS_IOMEM(base);
 	catu_desc.pdata = pdata;
 	catu_desc.dev = dev;
@@ -702,7 +711,7 @@ static int __init catu_init(void)
 {
 	int ret;
 
-	ret = coresight_init_driver("catu", &catu_driver, &catu_platform_driver);
+	ret = coresight_init_driver("catu", &catu_driver, &catu_platform_driver, THIS_MODULE);
 	tmc_etr_set_catu_ops(&etr_catu_buf_ops);
 	return ret;
 }
diff --git a/drivers/hwtracing/coresight/coresight-catu.h b/drivers/hwtracing/coresight/coresight-catu.h
index 141feac1c14b..755776cd19c5 100644
--- a/drivers/hwtracing/coresight/coresight-catu.h
+++ b/drivers/hwtracing/coresight/coresight-catu.h
@@ -65,6 +65,7 @@ struct catu_drvdata {
 	void __iomem *base;
 	struct coresight_device *csdev;
 	int irq;
+	raw_spinlock_t spinlock;
 };
 
 #define CATU_REG32(name, offset)					\
diff --git a/drivers/hwtracing/coresight/coresight-config.h b/drivers/hwtracing/coresight/coresight-config.h
index 6ba013975741..84cdde6f0e4d 100644
--- a/drivers/hwtracing/coresight/coresight-config.h
+++ b/drivers/hwtracing/coresight/coresight-config.h
@@ -228,7 +228,7 @@ struct cscfg_feature_csdev {
  * @feats_csdev:references to the device features to enable.
  */
 struct cscfg_config_csdev {
-	const struct cscfg_config_desc *config_desc;
+	struct cscfg_config_desc *config_desc;
 	struct coresight_device *csdev;
 	bool enabled;
 	struct list_head node;
diff --git a/drivers/hwtracing/coresight/coresight-core.c b/drivers/hwtracing/coresight/coresight-core.c
index ea38ecf26fcb..b7941d8abbfe 100644
--- a/drivers/hwtracing/coresight/coresight-core.c
+++ b/drivers/hwtracing/coresight/coresight-core.c
@@ -97,7 +97,8 @@ coresight_find_out_connection(struct coresight_device *src_dev,
 
 static inline u32 coresight_read_claim_tags(struct coresight_device *csdev)
 {
-	return csdev_access_relaxed_read32(&csdev->access, CORESIGHT_CLAIMCLR);
+	return FIELD_GET(CORESIGHT_CLAIM_MASK,
+			 csdev_access_relaxed_read32(&csdev->access, CORESIGHT_CLAIMCLR));
 }
 
 static inline bool coresight_is_claimed_self_hosted(struct coresight_device *csdev)
@@ -1017,18 +1018,20 @@ static void coresight_remove_conns(struct coresight_device *csdev)
 }
 
 /**
- * coresight_timeout - loop until a bit has changed to a specific register
- *			state.
+ * coresight_timeout_action - loop until a bit has changed to a specific register
+ *                  state, with a callback after every trial.
  * @csa: coresight device access for the device
  * @offset: Offset of the register from the base of the device.
  * @position: the position of the bit of interest.
  * @value: the value the bit should have.
+ * @cb: Call back after each trial.
  *
  * Return: 0 as soon as the bit has taken the desired state or -EAGAIN if
  * TIMEOUT_US has elapsed, which ever happens first.
  */
-int coresight_timeout(struct csdev_access *csa, u32 offset,
-		      int position, int value)
+int coresight_timeout_action(struct csdev_access *csa, u32 offset,
+		      int position, int value,
+			  coresight_timeout_cb_t cb)
 {
 	int i;
 	u32 val;
@@ -1044,7 +1047,8 @@ int coresight_timeout(struct csdev_access *csa, u32 offset,
 			if (!(val & BIT(position)))
 				return 0;
 		}
-
+		if (cb)
+			cb(csa, offset, position, value);
 		/*
 		 * Delay is arbitrary - the specification doesn't say how long
 		 * we are expected to wait.  Extra check required to make sure
@@ -1056,6 +1060,13 @@ int coresight_timeout(struct csdev_access *csa, u32 offset,
 
 	return -EAGAIN;
 }
+EXPORT_SYMBOL_GPL(coresight_timeout_action);
+
+int coresight_timeout(struct csdev_access *csa, u32 offset,
+		      int position, int value)
+{
+	return coresight_timeout_action(csa, offset, position, value, NULL);
+}
 EXPORT_SYMBOL_GPL(coresight_timeout);
 
 u32 coresight_relaxed_read32(struct coresight_device *csdev, u32 offset)
@@ -1412,17 +1423,17 @@ module_init(coresight_init);
 module_exit(coresight_exit);
 
 int coresight_init_driver(const char *drv, struct amba_driver *amba_drv,
-			  struct platform_driver *pdev_drv)
+			  struct platform_driver *pdev_drv, struct module *owner)
 {
 	int ret;
 
-	ret = amba_driver_register(amba_drv);
+	ret = __amba_driver_register(amba_drv, owner);
 	if (ret) {
 		pr_err("%s: error registering AMBA driver\n", drv);
 		return ret;
 	}
 
-	ret = platform_driver_register(pdev_drv);
+	ret = __platform_driver_register(pdev_drv, owner);
 	if (!ret)
 		return 0;
 
diff --git a/drivers/hwtracing/coresight/coresight-cpu-debug.c b/drivers/hwtracing/coresight/coresight-cpu-debug.c
index 75962dae9aa1..cc599c5ef4b2 100644
--- a/drivers/hwtracing/coresight/coresight-cpu-debug.c
+++ b/drivers/hwtracing/coresight/coresight-cpu-debug.c
@@ -774,7 +774,8 @@ static struct platform_driver debug_platform_driver = {
 
 static int __init debug_init(void)
 {
-	return coresight_init_driver("debug", &debug_driver, &debug_platform_driver);
+	return coresight_init_driver("debug", &debug_driver, &debug_platform_driver,
+				     THIS_MODULE);
 }
 
 static void __exit debug_exit(void)
diff --git a/drivers/hwtracing/coresight/coresight-etb10.c b/drivers/hwtracing/coresight/coresight-etb10.c
index aea9ac9c4bd0..7948597d483d 100644
--- a/drivers/hwtracing/coresight/coresight-etb10.c
+++ b/drivers/hwtracing/coresight/coresight-etb10.c
@@ -84,7 +84,7 @@ struct etb_drvdata {
 	struct clk		*atclk;
 	struct coresight_device	*csdev;
 	struct miscdevice	miscdev;
-	spinlock_t		spinlock;
+	raw_spinlock_t		spinlock;
 	local_t			reading;
 	pid_t			pid;
 	u8			*buf;
@@ -145,7 +145,7 @@ static int etb_enable_sysfs(struct coresight_device *csdev)
 	unsigned long flags;
 	struct etb_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
 
-	spin_lock_irqsave(&drvdata->spinlock, flags);
+	raw_spin_lock_irqsave(&drvdata->spinlock, flags);
 
 	/* Don't messup with perf sessions. */
 	if (coresight_get_mode(csdev) == CS_MODE_PERF) {
@@ -163,7 +163,7 @@ static int etb_enable_sysfs(struct coresight_device *csdev)
 
 	csdev->refcnt++;
 out:
-	spin_unlock_irqrestore(&drvdata->spinlock, flags);
+	raw_spin_unlock_irqrestore(&drvdata->spinlock, flags);
 	return ret;
 }
 
@@ -176,7 +176,7 @@ static int etb_enable_perf(struct coresight_device *csdev, void *data)
 	struct perf_output_handle *handle = data;
 	struct cs_buffers *buf = etm_perf_sink_config(handle);
 
-	spin_lock_irqsave(&drvdata->spinlock, flags);
+	raw_spin_lock_irqsave(&drvdata->spinlock, flags);
 
 	/* No need to continue if the component is already in used by sysFS. */
 	if (coresight_get_mode(drvdata->csdev) == CS_MODE_SYSFS) {
@@ -219,7 +219,7 @@ static int etb_enable_perf(struct coresight_device *csdev, void *data)
 	}
 
 out:
-	spin_unlock_irqrestore(&drvdata->spinlock, flags);
+	raw_spin_unlock_irqrestore(&drvdata->spinlock, flags);
 	return ret;
 }
 
@@ -352,11 +352,11 @@ static int etb_disable(struct coresight_device *csdev)
 	struct etb_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
 	unsigned long flags;
 
-	spin_lock_irqsave(&drvdata->spinlock, flags);
+	raw_spin_lock_irqsave(&drvdata->spinlock, flags);
 
 	csdev->refcnt--;
 	if (csdev->refcnt) {
-		spin_unlock_irqrestore(&drvdata->spinlock, flags);
+		raw_spin_unlock_irqrestore(&drvdata->spinlock, flags);
 		return -EBUSY;
 	}
 
@@ -366,7 +366,7 @@ static int etb_disable(struct coresight_device *csdev)
 	/* Dissociate from monitored process. */
 	drvdata->pid = -1;
 	coresight_set_mode(csdev, CS_MODE_DISABLED);
-	spin_unlock_irqrestore(&drvdata->spinlock, flags);
+	raw_spin_unlock_irqrestore(&drvdata->spinlock, flags);
 
 	dev_dbg(&csdev->dev, "ETB disabled\n");
 	return 0;
@@ -443,7 +443,7 @@ static unsigned long etb_update_buffer(struct coresight_device *csdev,
 
 	capacity = drvdata->buffer_depth * ETB_FRAME_SIZE_WORDS;
 
-	spin_lock_irqsave(&drvdata->spinlock, flags);
+	raw_spin_lock_irqsave(&drvdata->spinlock, flags);
 
 	/* Don't do anything if another tracer is using this sink */
 	if (csdev->refcnt != 1)
@@ -566,7 +566,7 @@ static unsigned long etb_update_buffer(struct coresight_device *csdev,
 	__etb_enable_hw(drvdata);
 	CS_LOCK(drvdata->base);
 out:
-	spin_unlock_irqrestore(&drvdata->spinlock, flags);
+	raw_spin_unlock_irqrestore(&drvdata->spinlock, flags);
 
 	return to_read;
 }
@@ -587,13 +587,13 @@ static void etb_dump(struct etb_drvdata *drvdata)
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&drvdata->spinlock, flags);
+	raw_spin_lock_irqsave(&drvdata->spinlock, flags);
 	if (coresight_get_mode(drvdata->csdev) == CS_MODE_SYSFS) {
 		__etb_disable_hw(drvdata);
 		etb_dump_hw(drvdata);
 		__etb_enable_hw(drvdata);
 	}
-	spin_unlock_irqrestore(&drvdata->spinlock, flags);
+	raw_spin_unlock_irqrestore(&drvdata->spinlock, flags);
 
 	dev_dbg(&drvdata->csdev->dev, "ETB dumped\n");
 }
@@ -746,7 +746,7 @@ static int etb_probe(struct amba_device *adev, const struct amba_id *id)
 	drvdata->base = base;
 	desc.access = CSDEV_ACCESS_IOMEM(base);
 
-	spin_lock_init(&drvdata->spinlock);
+	raw_spin_lock_init(&drvdata->spinlock);
 
 	drvdata->buffer_depth = etb_get_buffer_depth(drvdata);
 
diff --git a/drivers/hwtracing/coresight/coresight-etm4x-core.c b/drivers/hwtracing/coresight/coresight-etm4x-core.c
index 66d44a404ad0..be8b46f26ddc 100644
--- a/drivers/hwtracing/coresight/coresight-etm4x-core.c
+++ b/drivers/hwtracing/coresight/coresight-etm4x-core.c
@@ -399,6 +399,29 @@ static void etm4_check_arch_features(struct etmv4_drvdata *drvdata,
 }
 #endif /* CONFIG_ETM4X_IMPDEF_FEATURE */
 
+static void etm4x_sys_ins_barrier(struct csdev_access *csa, u32 offset, int pos, int val)
+{
+	if (!csa->io_mem)
+		isb();
+}
+
+/*
+ * etm4x_wait_status: Poll for TRCSTATR.<pos> == <val>. While using system
+ * instruction to access the trace unit, each access must be separated by a
+ * synchronization barrier. See ARM IHI0064H.b section "4.3.7 Synchronization of
+ * register updates", for system instructions section, in "Notes":
+ *
+ *   "In particular, whenever disabling or enabling the trace unit, a poll of
+ *    TRCSTATR needs explicit synchronization between each read of TRCSTATR"
+ */
+static int etm4x_wait_status(struct csdev_access *csa, int pos, int val)
+{
+	if (!csa->io_mem)
+		return coresight_timeout_action(csa, TRCSTATR, pos, val,
+						etm4x_sys_ins_barrier);
+	return coresight_timeout(csa, TRCSTATR, pos, val);
+}
+
 static int etm4_enable_hw(struct etmv4_drvdata *drvdata)
 {
 	int i, rc;
@@ -430,7 +453,7 @@ static int etm4_enable_hw(struct etmv4_drvdata *drvdata)
 		isb();
 
 	/* wait for TRCSTATR.IDLE to go up */
-	if (coresight_timeout(csa, TRCSTATR, TRCSTATR_IDLE_BIT, 1))
+	if (etm4x_wait_status(csa, TRCSTATR_IDLE_BIT, 1))
 		dev_err(etm_dev,
 			"timeout while waiting for Idle Trace Status\n");
 	if (drvdata->nr_pe)
@@ -523,7 +546,7 @@ static int etm4_enable_hw(struct etmv4_drvdata *drvdata)
 		isb();
 
 	/* wait for TRCSTATR.IDLE to go back down to '0' */
-	if (coresight_timeout(csa, TRCSTATR, TRCSTATR_IDLE_BIT, 0))
+	if (etm4x_wait_status(csa, TRCSTATR_IDLE_BIT, 0))
 		dev_err(etm_dev,
 			"timeout while waiting for Idle Trace Status\n");
 
@@ -906,10 +929,25 @@ static void etm4_disable_hw(void *info)
 	tsb_csync();
 	etm4x_relaxed_write32(csa, control, TRCPRGCTLR);
 
+	/*
+	 * As recommended by section 4.3.7 ("Synchronization when using system
+	 * instructions to progrom the trace unit") of ARM IHI 0064H.b, the
+	 * self-hosted trace analyzer must perform a Context synchronization
+	 * event between writing to the TRCPRGCTLR and reading the TRCSTATR.
+	 */
+	if (!csa->io_mem)
+		isb();
+
 	/* wait for TRCSTATR.PMSTABLE to go to '1' */
-	if (coresight_timeout(csa, TRCSTATR, TRCSTATR_PMSTABLE_BIT, 1))
+	if (etm4x_wait_status(csa, TRCSTATR_PMSTABLE_BIT, 1))
 		dev_err(etm_dev,
 			"timeout while waiting for PM stable Trace Status\n");
+	/*
+	 * As recommended by section 4.3.7 (Synchronization of register updates)
+	 * of ARM IHI 0064H.b.
+	 */
+	isb();
+
 	/* read the status of the single shot comparators */
 	for (i = 0; i < drvdata->nr_ss_cmp; i++) {
 		config->ss_status[i] =
@@ -1711,7 +1749,7 @@ static int __etm4_cpu_save(struct etmv4_drvdata *drvdata)
 	etm4_os_lock(drvdata);
 
 	/* wait for TRCSTATR.PMSTABLE to go up */
-	if (coresight_timeout(csa, TRCSTATR, TRCSTATR_PMSTABLE_BIT, 1)) {
+	if (etm4x_wait_status(csa, TRCSTATR_PMSTABLE_BIT, 1)) {
 		dev_err(etm_dev,
 			"timeout while waiting for PM Stable Status\n");
 		etm4_os_unlock(drvdata);
@@ -1802,7 +1840,7 @@ static int __etm4_cpu_save(struct etmv4_drvdata *drvdata)
 		state->trcpdcr = etm4x_read32(csa, TRCPDCR);
 
 	/* wait for TRCSTATR.IDLE to go up */
-	if (coresight_timeout(csa, TRCSTATR, TRCSTATR_IDLE_BIT, 1)) {
+	if (etm4x_wait_status(csa, TRCSTATR_PMSTABLE_BIT, 1)) {
 		dev_err(etm_dev,
 			"timeout while waiting for Idle Trace Status\n");
 		etm4_os_unlock(drvdata);
diff --git a/drivers/hwtracing/coresight/coresight-funnel.c b/drivers/hwtracing/coresight/coresight-funnel.c
index 5a819c8970fb..8f451b051ddc 100644
--- a/drivers/hwtracing/coresight/coresight-funnel.c
+++ b/drivers/hwtracing/coresight/coresight-funnel.c
@@ -433,7 +433,8 @@ static struct amba_driver dynamic_funnel_driver = {
 
 static int __init funnel_init(void)
 {
-	return coresight_init_driver("funnel", &dynamic_funnel_driver, &funnel_driver);
+	return coresight_init_driver("funnel", &dynamic_funnel_driver, &funnel_driver,
+				     THIS_MODULE);
 }
 
 static void __exit funnel_exit(void)
diff --git a/drivers/hwtracing/coresight/coresight-priv.h b/drivers/hwtracing/coresight/coresight-priv.h
index 05f891ca6b5c..cc7ff1e36ef4 100644
--- a/drivers/hwtracing/coresight/coresight-priv.h
+++ b/drivers/hwtracing/coresight/coresight-priv.h
@@ -35,6 +35,7 @@ extern const struct device_type coresight_dev_type[];
  * Coresight device CLAIM protocol.
  * See PSCI - ARM DEN 0022D, Section: 6.8.1 Debug and Trace save and restore.
  */
+#define CORESIGHT_CLAIM_MASK		GENMASK(1, 0)
 #define CORESIGHT_CLAIM_SELF_HOSTED	BIT(1)
 
 #define TIMEOUT_US		100
diff --git a/drivers/hwtracing/coresight/coresight-replicator.c b/drivers/hwtracing/coresight/coresight-replicator.c
index 3e55be9c8418..f7607c72857c 100644
--- a/drivers/hwtracing/coresight/coresight-replicator.c
+++ b/drivers/hwtracing/coresight/coresight-replicator.c
@@ -438,7 +438,8 @@ static struct amba_driver dynamic_replicator_driver = {
 
 static int __init replicator_init(void)
 {
-	return coresight_init_driver("replicator", &dynamic_replicator_driver, &replicator_driver);
+	return coresight_init_driver("replicator", &dynamic_replicator_driver, &replicator_driver,
+				     THIS_MODULE);
 }
 
 static void __exit replicator_exit(void)
diff --git a/drivers/hwtracing/coresight/coresight-stm.c b/drivers/hwtracing/coresight/coresight-stm.c
index cb3e04755c99..65bc50a6d3e9 100644
--- a/drivers/hwtracing/coresight/coresight-stm.c
+++ b/drivers/hwtracing/coresight/coresight-stm.c
@@ -1047,7 +1047,7 @@ static struct platform_driver stm_platform_driver = {
 
 static int __init stm_init(void)
 {
-	return coresight_init_driver("stm", &stm_driver, &stm_platform_driver);
+	return coresight_init_driver("stm", &stm_driver, &stm_platform_driver, THIS_MODULE);
 }
 
 static void __exit stm_exit(void)
diff --git a/drivers/hwtracing/coresight/coresight-syscfg.c b/drivers/hwtracing/coresight/coresight-syscfg.c
index 11138a9762b0..30a561d87481 100644
--- a/drivers/hwtracing/coresight/coresight-syscfg.c
+++ b/drivers/hwtracing/coresight/coresight-syscfg.c
@@ -867,6 +867,25 @@ unlock_exit:
 }
 EXPORT_SYMBOL_GPL(cscfg_csdev_reset_feats);
 
+static bool cscfg_config_desc_get(struct cscfg_config_desc *config_desc)
+{
+	if (!atomic_fetch_inc(&config_desc->active_cnt)) {
+		/* must ensure that config cannot be unloaded in use */
+		if (unlikely(cscfg_owner_get(config_desc->load_owner))) {
+			atomic_dec(&config_desc->active_cnt);
+			return false;
+		}
+	}
+
+	return true;
+}
+
+static void cscfg_config_desc_put(struct cscfg_config_desc *config_desc)
+{
+	if (!atomic_dec_return(&config_desc->active_cnt))
+		cscfg_owner_put(config_desc->load_owner);
+}
+
 /*
  * This activate configuration for either perf or sysfs. Perf can have multiple
  * active configs, selected per event, sysfs is limited to one.
@@ -890,22 +909,17 @@ static int _cscfg_activate_config(unsigned long cfg_hash)
 			if (config_desc->available == false)
 				return -EBUSY;
 
-			/* must ensure that config cannot be unloaded in use */
-			err = cscfg_owner_get(config_desc->load_owner);
-			if (err)
+			if (!cscfg_config_desc_get(config_desc)) {
+				err = -EINVAL;
 				break;
+			}
+
 			/*
 			 * increment the global active count - control changes to
 			 * active configurations
 			 */
 			atomic_inc(&cscfg_mgr->sys_active_cnt);
 
-			/*
-			 * mark the descriptor as active so enable config on a
-			 * device instance will use it
-			 */
-			atomic_inc(&config_desc->active_cnt);
-
 			err = 0;
 			dev_dbg(cscfg_device(), "Activate config %s.\n", config_desc->name);
 			break;
@@ -920,9 +934,8 @@ static void _cscfg_deactivate_config(unsigned long cfg_hash)
 
 	list_for_each_entry(config_desc, &cscfg_mgr->config_desc_list, item) {
 		if ((unsigned long)config_desc->event_ea->var == cfg_hash) {
-			atomic_dec(&config_desc->active_cnt);
 			atomic_dec(&cscfg_mgr->sys_active_cnt);
-			cscfg_owner_put(config_desc->load_owner);
+			cscfg_config_desc_put(config_desc);
 			dev_dbg(cscfg_device(), "Deactivate config %s.\n", config_desc->name);
 			break;
 		}
@@ -1047,7 +1060,7 @@ int cscfg_csdev_enable_active_config(struct coresight_device *csdev,
 				     unsigned long cfg_hash, int preset)
 {
 	struct cscfg_config_csdev *config_csdev_active = NULL, *config_csdev_item;
-	const struct cscfg_config_desc *config_desc;
+	struct cscfg_config_desc *config_desc;
 	unsigned long flags;
 	int err = 0;
 
@@ -1062,8 +1075,8 @@ int cscfg_csdev_enable_active_config(struct coresight_device *csdev,
 	spin_lock_irqsave(&csdev->cscfg_csdev_lock, flags);
 	list_for_each_entry(config_csdev_item, &csdev->config_csdev_list, node) {
 		config_desc = config_csdev_item->config_desc;
-		if ((atomic_read(&config_desc->active_cnt)) &&
-		    ((unsigned long)config_desc->event_ea->var == cfg_hash)) {
+		if (((unsigned long)config_desc->event_ea->var == cfg_hash) &&
+				cscfg_config_desc_get(config_desc)) {
 			config_csdev_active = config_csdev_item;
 			csdev->active_cscfg_ctxt = (void *)config_csdev_active;
 			break;
@@ -1097,7 +1110,11 @@ int cscfg_csdev_enable_active_config(struct coresight_device *csdev,
 				err = -EBUSY;
 			spin_unlock_irqrestore(&csdev->cscfg_csdev_lock, flags);
 		}
+
+		if (err)
+			cscfg_config_desc_put(config_desc);
 	}
+
 	return err;
 }
 EXPORT_SYMBOL_GPL(cscfg_csdev_enable_active_config);
@@ -1136,8 +1153,10 @@ void cscfg_csdev_disable_active_config(struct coresight_device *csdev)
 	spin_unlock_irqrestore(&csdev->cscfg_csdev_lock, flags);
 
 	/* true if there was an enabled active config */
-	if (config_csdev)
+	if (config_csdev) {
 		cscfg_csdev_disable_config(config_csdev);
+		cscfg_config_desc_put(config_csdev->config_desc);
+	}
 }
 EXPORT_SYMBOL_GPL(cscfg_csdev_disable_active_config);
 
diff --git a/drivers/hwtracing/coresight/coresight-tmc-core.c b/drivers/hwtracing/coresight/coresight-tmc-core.c
index 3a482fd2cb22..475fa4bb6813 100644
--- a/drivers/hwtracing/coresight/coresight-tmc-core.c
+++ b/drivers/hwtracing/coresight/coresight-tmc-core.c
@@ -741,7 +741,7 @@ static struct platform_driver tmc_platform_driver = {
 
 static int __init tmc_init(void)
 {
-	return coresight_init_driver("tmc", &tmc_driver, &tmc_platform_driver);
+	return coresight_init_driver("tmc", &tmc_driver, &tmc_platform_driver, THIS_MODULE);
 }
 
 static void __exit tmc_exit(void)
diff --git a/drivers/hwtracing/coresight/coresight-tpiu.c b/drivers/hwtracing/coresight/coresight-tpiu.c
index b048e146fbb1..f9ecd05cbe5c 100644
--- a/drivers/hwtracing/coresight/coresight-tpiu.c
+++ b/drivers/hwtracing/coresight/coresight-tpiu.c
@@ -318,7 +318,7 @@ static struct platform_driver tpiu_platform_driver = {
 
 static int __init tpiu_init(void)
 {
-	return coresight_init_driver("tpiu", &tpiu_driver, &tpiu_platform_driver);
+	return coresight_init_driver("tpiu", &tpiu_driver, &tpiu_platform_driver, THIS_MODULE);
 }
 
 static void __exit tpiu_exit(void)
diff --git a/drivers/hwtracing/intel_th/Kconfig b/drivers/hwtracing/intel_th/Kconfig
index 4b6359326ede..4f7d2b6d79e2 100644
--- a/drivers/hwtracing/intel_th/Kconfig
+++ b/drivers/hwtracing/intel_th/Kconfig
@@ -60,6 +60,7 @@ config INTEL_TH_STH
 
 config INTEL_TH_MSU
 	tristate "Intel(R) Trace Hub Memory Storage Unit"
+	depends on MMU
 	help
 	  Memory Storage Unit (MSU) trace output device enables
 	  storing STP traces to system memory. It supports single
diff --git a/drivers/hwtracing/intel_th/msu.c b/drivers/hwtracing/intel_th/msu.c
index 66123d684ac9..93b65a9731d7 100644
--- a/drivers/hwtracing/intel_th/msu.c
+++ b/drivers/hwtracing/intel_th/msu.c
@@ -19,6 +19,7 @@
 #include <linux/io.h>
 #include <linux/workqueue.h>
 #include <linux/dma-mapping.h>
+#include <linux/pfn_t.h>
 
 #ifdef CONFIG_X86
 #include <asm/set_memory.h>
@@ -967,7 +968,6 @@ static void msc_buffer_contig_free(struct msc *msc)
 	for (off = 0; off < msc->nr_pages << PAGE_SHIFT; off += PAGE_SIZE) {
 		struct page *page = virt_to_page(msc->base + off);
 
-		page->mapping = NULL;
 		__free_page(page);
 	}
 
@@ -1149,9 +1149,6 @@ static void __msc_buffer_win_free(struct msc *msc, struct msc_window *win)
 	int i;
 
 	for_each_sg(win->sgt->sgl, sg, win->nr_segs, i) {
-		struct page *page = msc_sg_page(sg);
-
-		page->mapping = NULL;
 		dma_free_coherent(msc_dev(win->msc)->parent->parent, PAGE_SIZE,
 				  sg_virt(sg), sg_dma_address(sg));
 	}
@@ -1592,22 +1589,10 @@ static void msc_mmap_close(struct vm_area_struct *vma)
 {
 	struct msc_iter *iter = vma->vm_file->private_data;
 	struct msc *msc = iter->msc;
-	unsigned long pg;
 
 	if (!atomic_dec_and_mutex_lock(&msc->mmap_count, &msc->buf_mutex))
 		return;
 
-	/* drop page _refcounts */
-	for (pg = 0; pg < msc->nr_pages; pg++) {
-		struct page *page = msc_buffer_get_page(msc, pg);
-
-		if (WARN_ON_ONCE(!page))
-			continue;
-
-		if (page->mapping)
-			page->mapping = NULL;
-	}
-
 	/* last mapping -- drop user_count */
 	atomic_dec(&msc->user_count);
 	mutex_unlock(&msc->buf_mutex);
@@ -1617,16 +1602,14 @@ static vm_fault_t msc_mmap_fault(struct vm_fault *vmf)
 {
 	struct msc_iter *iter = vmf->vma->vm_file->private_data;
 	struct msc *msc = iter->msc;
+	struct page *page;
 
-	vmf->page = msc_buffer_get_page(msc, vmf->pgoff);
-	if (!vmf->page)
+	page = msc_buffer_get_page(msc, vmf->pgoff);
+	if (!page)
 		return VM_FAULT_SIGBUS;
 
-	get_page(vmf->page);
-	vmf->page->mapping = vmf->vma->vm_file->f_mapping;
-	vmf->page->index = vmf->pgoff;
-
-	return 0;
+	get_page(page);
+	return vmf_insert_mixed(vmf->vma, vmf->address, page_to_pfn_t(page));
 }
 
 static const struct vm_operations_struct msc_mmap_ops = {
@@ -1667,7 +1650,7 @@ out:
 		atomic_dec(&msc->user_count);
 
 	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
-	vm_flags_set(vma, VM_DONTEXPAND | VM_DONTCOPY);
+	vm_flags_set(vma, VM_DONTEXPAND | VM_DONTCOPY | VM_MIXEDMAP);
 	vma->vm_ops = &msc_mmap_ops;
 	return ret;
 }
diff --git a/drivers/hwtracing/intel_th/pci.c b/drivers/hwtracing/intel_th/pci.c
index 0d7b9839e5b6..6bb6af0f96fa 100644
--- a/drivers/hwtracing/intel_th/pci.c
+++ b/drivers/hwtracing/intel_th/pci.c
@@ -330,6 +330,21 @@ static const struct pci_device_id intel_th_pci_id_table[] = {
 		.driver_data = (kernel_ulong_t)&intel_th_2x,
 	},
 	{
+		/* Arrow Lake */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7724),
+		.driver_data = (kernel_ulong_t)&intel_th_2x,
+	},
+	{
+		/* Panther Lake-H */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe324),
+		.driver_data = (kernel_ulong_t)&intel_th_2x,
+	},
+	{
+		/* Panther Lake-P/U */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe424),
+		.driver_data = (kernel_ulong_t)&intel_th_2x,
+	},
+	{
 		/* Alder Lake CPU */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x466f),
 		.driver_data = (kernel_ulong_t)&intel_th_2x,
diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig
index 2254abda5c46..0e679cc50148 100644
--- a/drivers/i2c/busses/Kconfig
+++ b/drivers/i2c/busses/Kconfig
@@ -937,6 +937,7 @@ config I2C_OMAP
 	tristate "OMAP I2C adapter"
 	depends on ARCH_OMAP || ARCH_K3 || COMPILE_TEST
 	default MACH_OMAP_OSK
+	select MULTIPLEXER
 	help
 	  If you say yes to this option, support will be included for the
 	  I2C interface on the Texas Instruments OMAP1/2 family of processors.
diff --git a/drivers/i2c/busses/i2c-ali1535.c b/drivers/i2c/busses/i2c-ali1535.c
index 544c94e86b89..1eac35838040 100644
--- a/drivers/i2c/busses/i2c-ali1535.c
+++ b/drivers/i2c/busses/i2c-ali1535.c
@@ -485,6 +485,8 @@ MODULE_DEVICE_TABLE(pci, ali1535_ids);
 
 static int ali1535_probe(struct pci_dev *dev, const struct pci_device_id *id)
 {
+	int ret;
+
 	if (ali1535_setup(dev)) {
 		dev_warn(&dev->dev,
 			"ALI1535 not detected, module not inserted.\n");
@@ -496,7 +498,15 @@ static int ali1535_probe(struct pci_dev *dev, const struct pci_device_id *id)
 
 	snprintf(ali1535_adapter.name, sizeof(ali1535_adapter.name),
 		"SMBus ALI1535 adapter at %04x", ali1535_offset);
-	return i2c_add_adapter(&ali1535_adapter);
+	ret = i2c_add_adapter(&ali1535_adapter);
+	if (ret)
+		goto release_region;
+
+	return 0;
+
+release_region:
+	release_region(ali1535_smba, ALI1535_SMB_IOSIZE);
+	return ret;
 }
 
 static void ali1535_remove(struct pci_dev *dev)
diff --git a/drivers/i2c/busses/i2c-ali15x3.c b/drivers/i2c/busses/i2c-ali15x3.c
index 4761c7208102..418d11266671 100644
--- a/drivers/i2c/busses/i2c-ali15x3.c
+++ b/drivers/i2c/busses/i2c-ali15x3.c
@@ -472,6 +472,8 @@ MODULE_DEVICE_TABLE (pci, ali15x3_ids);
 
 static int ali15x3_probe(struct pci_dev *dev, const struct pci_device_id *id)
 {
+	int ret;
+
 	if (ali15x3_setup(dev)) {
 		dev_err(&dev->dev,
 			"ALI15X3 not detected, module not inserted.\n");
@@ -483,7 +485,15 @@ static int ali15x3_probe(struct pci_dev *dev, const struct pci_device_id *id)
 
 	snprintf(ali15x3_adapter.name, sizeof(ali15x3_adapter.name),
 		"SMBus ALI15X3 adapter at %04x", ali15x3_smba);
-	return i2c_add_adapter(&ali15x3_adapter);
+	ret = i2c_add_adapter(&ali15x3_adapter);
+	if (ret)
+		goto release_region;
+
+	return 0;
+
+release_region:
+	release_region(ali15x3_smba, ALI15X3_SMB_IOSIZE);
+	return ret;
 }
 
 static void ali15x3_remove(struct pci_dev *dev)
diff --git a/drivers/i2c/busses/i2c-cros-ec-tunnel.c b/drivers/i2c/busses/i2c-cros-ec-tunnel.c
index ab2688bd4d33..e19cb62d6796 100644
--- a/drivers/i2c/busses/i2c-cros-ec-tunnel.c
+++ b/drivers/i2c/busses/i2c-cros-ec-tunnel.c
@@ -247,6 +247,9 @@ static int ec_i2c_probe(struct platform_device *pdev)
 	u32 remote_bus;
 	int err;
 
+	if (!ec)
+		return dev_err_probe(dev, -EPROBE_DEFER, "couldn't find parent EC device\n");
+
 	if (!ec->cmd_xfer) {
 		dev_err(dev, "Missing sendrecv\n");
 		return -EINVAL;
diff --git a/drivers/i2c/busses/i2c-designware-common.c b/drivers/i2c/busses/i2c-designware-common.c
index 9d88b4fa03e4..b3282785523d 100644
--- a/drivers/i2c/busses/i2c-designware-common.c
+++ b/drivers/i2c/busses/i2c-designware-common.c
@@ -8,6 +8,9 @@
  * Copyright (C) 2007 MontaVista Software Inc.
  * Copyright (C) 2009 Provigent Ltd.
  */
+
+#define DEFAULT_SYMBOL_NAMESPACE	"I2C_DW_COMMON"
+
 #include <linux/acpi.h>
 #include <linux/clk.h>
 #include <linux/delay.h>
@@ -29,8 +32,6 @@
 #include <linux/types.h>
 #include <linux/units.h>
 
-#define DEFAULT_SYMBOL_NAMESPACE	I2C_DW_COMMON
-
 #include "i2c-designware-core.h"
 
 static char *abort_sources[] = {
diff --git a/drivers/i2c/busses/i2c-designware-master.c b/drivers/i2c/busses/i2c-designware-master.c
index e8ac9a7bf0b3..52dc666c3ef4 100644
--- a/drivers/i2c/busses/i2c-designware-master.c
+++ b/drivers/i2c/busses/i2c-designware-master.c
@@ -8,6 +8,9 @@
  * Copyright (C) 2007 MontaVista Software Inc.
  * Copyright (C) 2009 Provigent Ltd.
  */
+
+#define DEFAULT_SYMBOL_NAMESPACE	"I2C_DW"
+
 #include <linux/delay.h>
 #include <linux/err.h>
 #include <linux/errno.h>
@@ -22,8 +25,6 @@
 #include <linux/regmap.h>
 #include <linux/reset.h>
 
-#define DEFAULT_SYMBOL_NAMESPACE	I2C_DW
-
 #include "i2c-designware-core.h"
 
 #define AMD_TIMEOUT_MIN_US	25
@@ -345,6 +346,7 @@ static int amd_i2c_dw_xfer_quirk(struct i2c_adapter *adap, struct i2c_msg *msgs,
 
 	dev->msgs = msgs;
 	dev->msgs_num = num_msgs;
+	dev->msg_write_idx = 0;
 	i2c_dw_xfer_init(dev);
 
 	/* Initiate messages read/write transaction */
diff --git a/drivers/i2c/busses/i2c-designware-pcidrv.c b/drivers/i2c/busses/i2c-designware-pcidrv.c
index 7b2c5d71a7fc..5ea6d40373e7 100644
--- a/drivers/i2c/busses/i2c-designware-pcidrv.c
+++ b/drivers/i2c/busses/i2c-designware-pcidrv.c
@@ -207,6 +207,7 @@ static const struct software_node dgpu_node = {
 static int i2c_dw_pci_probe(struct pci_dev *pdev,
 			    const struct pci_device_id *id)
 {
+	struct device *device = &pdev->dev;
 	struct dw_i2c_dev *dev;
 	struct i2c_adapter *adap;
 	int r;
@@ -214,25 +215,22 @@ static int i2c_dw_pci_probe(struct pci_dev *pdev,
 	struct dw_scl_sda_cfg *cfg;
 
 	if (id->driver_data >= ARRAY_SIZE(dw_pci_controllers))
-		return dev_err_probe(&pdev->dev, -EINVAL,
-				     "Invalid driver data %ld\n",
+		return dev_err_probe(device, -EINVAL, "Invalid driver data %ld\n",
 				     id->driver_data);
 
 	controller = &dw_pci_controllers[id->driver_data];
 
 	r = pcim_enable_device(pdev);
 	if (r)
-		return dev_err_probe(&pdev->dev, r,
-				     "Failed to enable I2C PCI device\n");
+		return dev_err_probe(device, r, "Failed to enable I2C PCI device\n");
 
 	pci_set_master(pdev);
 
 	r = pcim_iomap_regions(pdev, 1 << 0, pci_name(pdev));
 	if (r)
-		return dev_err_probe(&pdev->dev, r,
-				     "I/O memory remapping failed\n");
+		return dev_err_probe(device, r, "I/O memory remapping failed\n");
 
-	dev = devm_kzalloc(&pdev->dev, sizeof(*dev), GFP_KERNEL);
+	dev = devm_kzalloc(device, sizeof(*dev), GFP_KERNEL);
 	if (!dev)
 		return -ENOMEM;
 
@@ -242,7 +240,7 @@ static int i2c_dw_pci_probe(struct pci_dev *pdev,
 
 	dev->get_clk_rate_khz = controller->get_clk_rate_khz;
 	dev->base = pcim_iomap_table(pdev)[0];
-	dev->dev = &pdev->dev;
+	dev->dev = device;
 	dev->irq = pci_irq_vector(pdev, 0);
 	dev->flags |= controller->flags;
 
@@ -280,15 +278,17 @@ static int i2c_dw_pci_probe(struct pci_dev *pdev,
 
 	if ((dev->flags & MODEL_MASK) == MODEL_AMD_NAVI_GPU) {
 		dev->slave = i2c_new_ccgx_ucsi(&dev->adapter, dev->irq, &dgpu_node);
-		if (IS_ERR(dev->slave))
-			return dev_err_probe(dev->dev, PTR_ERR(dev->slave),
+		if (IS_ERR(dev->slave)) {
+			i2c_del_adapter(&dev->adapter);
+			return dev_err_probe(device, PTR_ERR(dev->slave),
 					     "register UCSI failed\n");
+		}
 	}
 
-	pm_runtime_set_autosuspend_delay(&pdev->dev, 1000);
-	pm_runtime_use_autosuspend(&pdev->dev);
-	pm_runtime_put_autosuspend(&pdev->dev);
-	pm_runtime_allow(&pdev->dev);
+	pm_runtime_set_autosuspend_delay(device, 1000);
+	pm_runtime_use_autosuspend(device);
+	pm_runtime_put_autosuspend(device);
+	pm_runtime_allow(device);
 
 	return 0;
 }
@@ -296,11 +296,12 @@ static int i2c_dw_pci_probe(struct pci_dev *pdev,
 static void i2c_dw_pci_remove(struct pci_dev *pdev)
 {
 	struct dw_i2c_dev *dev = pci_get_drvdata(pdev);
+	struct device *device = &pdev->dev;
 
 	i2c_dw_disable(dev);
 
-	pm_runtime_forbid(&pdev->dev);
-	pm_runtime_get_noresume(&pdev->dev);
+	pm_runtime_forbid(device);
+	pm_runtime_get_noresume(device);
 
 	i2c_del_adapter(&dev->adapter);
 }
diff --git a/drivers/i2c/busses/i2c-designware-platdrv.c b/drivers/i2c/busses/i2c-designware-platdrv.c
index 2d0c7348e491..a3e86930bf41 100644
--- a/drivers/i2c/busses/i2c-designware-platdrv.c
+++ b/drivers/i2c/busses/i2c-designware-platdrv.c
@@ -205,6 +205,7 @@ static void i2c_dw_remove_lock_support(struct dw_i2c_dev *dev)
 
 static int dw_i2c_plat_probe(struct platform_device *pdev)
 {
+	struct device *device = &pdev->dev;
 	struct i2c_adapter *adap;
 	struct dw_i2c_dev *dev;
 	int irq, ret;
@@ -213,15 +214,15 @@ static int dw_i2c_plat_probe(struct platform_device *pdev)
 	if (irq < 0)
 		return irq;
 
-	dev = devm_kzalloc(&pdev->dev, sizeof(struct dw_i2c_dev), GFP_KERNEL);
+	dev = devm_kzalloc(device, sizeof(*dev), GFP_KERNEL);
 	if (!dev)
 		return -ENOMEM;
 
-	dev->flags = (uintptr_t)device_get_match_data(&pdev->dev);
-	if (device_property_present(&pdev->dev, "wx,i2c-snps-model"))
+	dev->flags = (uintptr_t)device_get_match_data(device);
+	if (device_property_present(device, "wx,i2c-snps-model"))
 		dev->flags = MODEL_WANGXUN_SP | ACCESS_POLLING;
 
-	dev->dev = &pdev->dev;
+	dev->dev = device;
 	dev->irq = irq;
 	platform_set_drvdata(pdev, dev);
 
@@ -229,7 +230,7 @@ static int dw_i2c_plat_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	dev->rst = devm_reset_control_get_optional_exclusive(&pdev->dev, NULL);
+	dev->rst = devm_reset_control_get_optional_exclusive(device, NULL);
 	if (IS_ERR(dev->rst))
 		return PTR_ERR(dev->rst);
 
@@ -246,13 +247,13 @@ static int dw_i2c_plat_probe(struct platform_device *pdev)
 	i2c_dw_configure(dev);
 
 	/* Optional interface clock */
-	dev->pclk = devm_clk_get_optional(&pdev->dev, "pclk");
+	dev->pclk = devm_clk_get_optional(device, "pclk");
 	if (IS_ERR(dev->pclk)) {
 		ret = PTR_ERR(dev->pclk);
 		goto exit_reset;
 	}
 
-	dev->clk = devm_clk_get_optional(&pdev->dev, NULL);
+	dev->clk = devm_clk_get_optional(device, NULL);
 	if (IS_ERR(dev->clk)) {
 		ret = PTR_ERR(dev->clk);
 		goto exit_reset;
@@ -280,28 +281,24 @@ static int dw_i2c_plat_probe(struct platform_device *pdev)
 					I2C_CLASS_HWMON : I2C_CLASS_DEPRECATED;
 	adap->nr = -1;
 
-	if (dev->flags & ACCESS_NO_IRQ_SUSPEND) {
-		dev_pm_set_driver_flags(&pdev->dev,
-					DPM_FLAG_SMART_PREPARE);
-	} else {
-		dev_pm_set_driver_flags(&pdev->dev,
-					DPM_FLAG_SMART_PREPARE |
-					DPM_FLAG_SMART_SUSPEND);
-	}
+	if (dev->flags & ACCESS_NO_IRQ_SUSPEND)
+		dev_pm_set_driver_flags(device, DPM_FLAG_SMART_PREPARE);
+	else
+		dev_pm_set_driver_flags(device, DPM_FLAG_SMART_PREPARE | DPM_FLAG_SMART_SUSPEND);
 
-	device_enable_async_suspend(&pdev->dev);
+	device_enable_async_suspend(device);
 
 	/* The code below assumes runtime PM to be disabled. */
-	WARN_ON(pm_runtime_enabled(&pdev->dev));
+	WARN_ON(pm_runtime_enabled(device));
 
-	pm_runtime_set_autosuspend_delay(&pdev->dev, 1000);
-	pm_runtime_use_autosuspend(&pdev->dev);
-	pm_runtime_set_active(&pdev->dev);
+	pm_runtime_set_autosuspend_delay(device, 1000);
+	pm_runtime_use_autosuspend(device);
+	pm_runtime_set_active(device);
 
 	if (dev->shared_with_punit)
-		pm_runtime_get_noresume(&pdev->dev);
+		pm_runtime_get_noresume(device);
 
-	pm_runtime_enable(&pdev->dev);
+	pm_runtime_enable(device);
 
 	ret = i2c_dw_probe(dev);
 	if (ret)
@@ -319,15 +316,16 @@ exit_reset:
 static void dw_i2c_plat_remove(struct platform_device *pdev)
 {
 	struct dw_i2c_dev *dev = platform_get_drvdata(pdev);
+	struct device *device = &pdev->dev;
 
-	pm_runtime_get_sync(&pdev->dev);
+	pm_runtime_get_sync(device);
 
 	i2c_del_adapter(&dev->adapter);
 
 	i2c_dw_disable(dev);
 
-	pm_runtime_dont_use_autosuspend(&pdev->dev);
-	pm_runtime_put_sync(&pdev->dev);
+	pm_runtime_dont_use_autosuspend(device);
+	pm_runtime_put_sync(device);
 	dw_i2c_plat_pm_cleanup(dev);
 
 	i2c_dw_remove_lock_support(dev);
diff --git a/drivers/i2c/busses/i2c-designware-slave.c b/drivers/i2c/busses/i2c-designware-slave.c
index 7035296aa24c..602e98e61cc0 100644
--- a/drivers/i2c/busses/i2c-designware-slave.c
+++ b/drivers/i2c/busses/i2c-designware-slave.c
@@ -6,6 +6,9 @@
  *
  * Copyright (C) 2016 Synopsys Inc.
  */
+
+#define DEFAULT_SYMBOL_NAMESPACE	"I2C_DW"
+
 #include <linux/delay.h>
 #include <linux/err.h>
 #include <linux/errno.h>
@@ -16,8 +19,6 @@
 #include <linux/pm_runtime.h>
 #include <linux/regmap.h>
 
-#define DEFAULT_SYMBOL_NAMESPACE	I2C_DW
-
 #include "i2c-designware-core.h"
 
 static void i2c_dw_configure_fifo_slave(struct dw_i2c_dev *dev)
@@ -93,7 +94,7 @@ static int i2c_dw_unreg_slave(struct i2c_client *slave)
 	i2c_dw_disable(dev);
 	synchronize_irq(dev->irq);
 	dev->slave = NULL;
-	pm_runtime_put(dev->dev);
+	pm_runtime_put_sync_suspend(dev->dev);
 
 	return 0;
 }
diff --git a/drivers/i2c/busses/i2c-imx-lpi2c.c b/drivers/i2c/busses/i2c-imx-lpi2c.c
index 976d43f73f38..86b41cd48ad4 100644
--- a/drivers/i2c/busses/i2c-imx-lpi2c.c
+++ b/drivers/i2c/busses/i2c-imx-lpi2c.c
@@ -652,9 +652,9 @@ static int lpi2c_imx_probe(struct platform_device *pdev)
 	return 0;
 
 rpm_disable:
-	pm_runtime_put(&pdev->dev);
-	pm_runtime_disable(&pdev->dev);
 	pm_runtime_dont_use_autosuspend(&pdev->dev);
+	pm_runtime_put_sync(&pdev->dev);
+	pm_runtime_disable(&pdev->dev);
 
 	return ret;
 }
diff --git a/drivers/i2c/busses/i2c-ls2x.c b/drivers/i2c/busses/i2c-ls2x.c
index 8821cac3897b..b475dd27b7af 100644
--- a/drivers/i2c/busses/i2c-ls2x.c
+++ b/drivers/i2c/busses/i2c-ls2x.c
@@ -10,6 +10,7 @@
  * Rewritten for mainline by Binbin Zhou <zhoubinbin@loongson.cn>
  */
 
+#include <linux/bitfield.h>
 #include <linux/bits.h>
 #include <linux/completion.h>
 #include <linux/device.h>
@@ -26,7 +27,8 @@
 #include <linux/units.h>
 
 /* I2C Registers */
-#define I2C_LS2X_PRER		0x0 /* Freq Division Register(16 bits) */
+#define I2C_LS2X_PRER_LO	0x0 /* Freq Division Low Byte Register */
+#define I2C_LS2X_PRER_HI	0x1 /* Freq Division High Byte Register */
 #define I2C_LS2X_CTR		0x2 /* Control Register */
 #define I2C_LS2X_TXR		0x3 /* Transport Data Register */
 #define I2C_LS2X_RXR		0x3 /* Receive Data Register */
@@ -93,6 +95,7 @@ static irqreturn_t ls2x_i2c_isr(int this_irq, void *dev_id)
  */
 static void ls2x_i2c_adjust_bus_speed(struct ls2x_i2c_priv *priv)
 {
+	u16 val;
 	struct i2c_timings *t = &priv->i2c_t;
 	struct device *dev = priv->adapter.dev.parent;
 	u32 acpi_speed = i2c_acpi_find_bus_speed(dev);
@@ -104,9 +107,14 @@ static void ls2x_i2c_adjust_bus_speed(struct ls2x_i2c_priv *priv)
 	else
 		t->bus_freq_hz = LS2X_I2C_FREQ_STD;
 
-	/* Calculate and set i2c frequency. */
-	writew(LS2X_I2C_PCLK_FREQ / (5 * t->bus_freq_hz) - 1,
-	       priv->base + I2C_LS2X_PRER);
+	/*
+	 * According to the chip manual, we can only access the registers as bytes,
+	 * otherwise the high bits will be truncated.
+	 * So set the I2C frequency with a sequential writeb() instead of writew().
+	 */
+	val = LS2X_I2C_PCLK_FREQ / (5 * t->bus_freq_hz) - 1;
+	writeb(FIELD_GET(GENMASK(7, 0), val), priv->base + I2C_LS2X_PRER_LO);
+	writeb(FIELD_GET(GENMASK(15, 8), val), priv->base + I2C_LS2X_PRER_HI);
 }
 
 static void ls2x_i2c_init(struct ls2x_i2c_priv *priv)
diff --git a/drivers/i2c/busses/i2c-npcm7xx.c b/drivers/i2c/busses/i2c-npcm7xx.c
index bbcb4d6668ce..7b6eb2bfb412 100644
--- a/drivers/i2c/busses/i2c-npcm7xx.c
+++ b/drivers/i2c/busses/i2c-npcm7xx.c
@@ -1969,10 +1969,14 @@ static int npcm_i2c_init_module(struct npcm_i2c *bus, enum i2c_mode mode,
 
 	/* Check HW is OK: SDA and SCL should be high at this point. */
 	if ((npcm_i2c_get_SDA(&bus->adap) == 0) || (npcm_i2c_get_SCL(&bus->adap) == 0)) {
-		dev_err(bus->dev, "I2C%d init fail: lines are low\n", bus->num);
-		dev_err(bus->dev, "SDA=%d SCL=%d\n", npcm_i2c_get_SDA(&bus->adap),
-			npcm_i2c_get_SCL(&bus->adap));
-		return -ENXIO;
+		dev_warn(bus->dev, " I2C%d SDA=%d SCL=%d, attempting to recover\n", bus->num,
+				 npcm_i2c_get_SDA(&bus->adap), npcm_i2c_get_SCL(&bus->adap));
+		if (npcm_i2c_recovery_tgclk(&bus->adap)) {
+			dev_err(bus->dev, "I2C%d init fail: SDA=%d SCL=%d\n",
+				bus->num, npcm_i2c_get_SDA(&bus->adap),
+				npcm_i2c_get_SCL(&bus->adap));
+			return -ENXIO;
+		}
 	}
 
 	npcm_i2c_int_enable(bus, true);
@@ -2319,6 +2323,13 @@ static int npcm_i2c_probe_bus(struct platform_device *pdev)
 	if (irq < 0)
 		return irq;
 
+	/*
+	 * Disable the interrupt to avoid the interrupt handler being triggered
+	 * incorrectly by the asynchronous interrupt status since the machine
+	 * might do a warm reset during the last smbus/i2c transfer session.
+	 */
+	npcm_i2c_int_enable(bus, false);
+
 	ret = devm_request_irq(bus->dev, irq, npcm_i2c_bus_irq, 0,
 			       dev_name(bus->dev), bus);
 	if (ret)
diff --git a/drivers/i2c/busses/i2c-omap.c b/drivers/i2c/busses/i2c-omap.c
index 1d9ad25c89ae..0bdee43dc134 100644
--- a/drivers/i2c/busses/i2c-omap.c
+++ b/drivers/i2c/busses/i2c-omap.c
@@ -24,6 +24,7 @@
 #include <linux/platform_device.h>
 #include <linux/clk.h>
 #include <linux/io.h>
+#include <linux/mux/consumer.h>
 #include <linux/of.h>
 #include <linux/slab.h>
 #include <linux/platform_data/i2c-omap.h>
@@ -211,6 +212,7 @@ struct omap_i2c_dev {
 	u16			syscstate;
 	u16			westate;
 	u16			errata;
+	struct mux_state	*mux_state;
 };
 
 static const u8 reg_map_ip_v1[] = {
@@ -1048,23 +1050,6 @@ static int omap_i2c_transmit_data(struct omap_i2c_dev *omap, u8 num_bytes,
 	return 0;
 }
 
-static irqreturn_t
-omap_i2c_isr(int irq, void *dev_id)
-{
-	struct omap_i2c_dev *omap = dev_id;
-	irqreturn_t ret = IRQ_HANDLED;
-	u16 mask;
-	u16 stat;
-
-	stat = omap_i2c_read_reg(omap, OMAP_I2C_STAT_REG);
-	mask = omap_i2c_read_reg(omap, OMAP_I2C_IE_REG) & ~OMAP_I2C_STAT_NACK;
-
-	if (stat & mask)
-		ret = IRQ_WAKE_THREAD;
-
-	return ret;
-}
-
 static int omap_i2c_xfer_data(struct omap_i2c_dev *omap)
 {
 	u16 bits;
@@ -1095,8 +1080,13 @@ static int omap_i2c_xfer_data(struct omap_i2c_dev *omap)
 		}
 
 		if (stat & OMAP_I2C_STAT_NACK) {
-			err |= OMAP_I2C_STAT_NACK;
+			omap->cmd_err |= OMAP_I2C_STAT_NACK;
 			omap_i2c_ack_stat(omap, OMAP_I2C_STAT_NACK);
+
+			if (!(stat & ~OMAP_I2C_STAT_NACK)) {
+				err = -EAGAIN;
+				break;
+			}
 		}
 
 		if (stat & OMAP_I2C_STAT_AL) {
@@ -1464,15 +1454,34 @@ omap_i2c_probe(struct platform_device *pdev)
 				       (1000 * omap->speed / 8);
 	}
 
+	if (of_property_present(node, "mux-states")) {
+		struct mux_state *mux_state;
+
+		mux_state = devm_mux_state_get(&pdev->dev, NULL);
+		if (IS_ERR(mux_state)) {
+			r = PTR_ERR(mux_state);
+			dev_dbg(&pdev->dev, "failed to get I2C mux: %d\n", r);
+			goto err_put_pm;
+		}
+		omap->mux_state = mux_state;
+		r = mux_state_select(omap->mux_state);
+		if (r) {
+			dev_err(&pdev->dev, "failed to select I2C mux: %d\n", r);
+			goto err_put_pm;
+		}
+	}
+
 	/* reset ASAP, clearing any IRQs */
-	omap_i2c_init(omap);
+	r = omap_i2c_init(omap);
+	if (r)
+		goto err_mux_state_deselect;
 
 	if (omap->rev < OMAP_I2C_OMAP1_REV_2)
 		r = devm_request_irq(&pdev->dev, omap->irq, omap_i2c_omap1_isr,
 				IRQF_NO_SUSPEND, pdev->name, omap);
 	else
 		r = devm_request_threaded_irq(&pdev->dev, omap->irq,
-				omap_i2c_isr, omap_i2c_isr_thread,
+				NULL, omap_i2c_isr_thread,
 				IRQF_NO_SUSPEND | IRQF_ONESHOT,
 				pdev->name, omap);
 
@@ -1508,6 +1517,10 @@ omap_i2c_probe(struct platform_device *pdev)
 
 err_unuse_clocks:
 	omap_i2c_write_reg(omap, OMAP_I2C_CON_REG, 0);
+err_mux_state_deselect:
+	if (omap->mux_state)
+		mux_state_deselect(omap->mux_state);
+err_put_pm:
 	pm_runtime_dont_use_autosuspend(omap->dev);
 	pm_runtime_put_sync(omap->dev);
 err_disable_pm:
@@ -1523,6 +1536,9 @@ static void omap_i2c_remove(struct platform_device *pdev)
 
 	i2c_del_adapter(&omap->adapter);
 
+	if (omap->mux_state)
+		mux_state_deselect(omap->mux_state);
+
 	ret = pm_runtime_get_sync(&pdev->dev);
 	if (ret < 0)
 		dev_err(omap->dev, "Failed to resume hardware, skip disable\n");
diff --git a/drivers/i2c/busses/i2c-pxa.c b/drivers/i2c/busses/i2c-pxa.c
index 4d76e71cdd4b..afc1a8171f59 100644
--- a/drivers/i2c/busses/i2c-pxa.c
+++ b/drivers/i2c/busses/i2c-pxa.c
@@ -1503,7 +1503,10 @@ static int i2c_pxa_probe(struct platform_device *dev)
 				i2c->adap.name);
 	}
 
-	clk_prepare_enable(i2c->clk);
+	ret = clk_prepare_enable(i2c->clk);
+	if (ret)
+		return dev_err_probe(&dev->dev, ret,
+				     "failed to enable clock\n");
 
 	if (i2c->use_pio) {
 		i2c->adap.algo = &i2c_pxa_pio_algorithm;
diff --git a/drivers/i2c/busses/i2c-qup.c b/drivers/i2c/busses/i2c-qup.c
index d480162a4d39..592b754f48e9 100644
--- a/drivers/i2c/busses/i2c-qup.c
+++ b/drivers/i2c/busses/i2c-qup.c
@@ -14,6 +14,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/err.h>
 #include <linux/i2c.h>
+#include <linux/interconnect.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
 #include <linux/module.h>
@@ -150,6 +151,8 @@
 /* TAG length for DATA READ in RX FIFO  */
 #define READ_RX_TAGS_LEN		2
 
+#define QUP_BUS_WIDTH			8
+
 static unsigned int scl_freq;
 module_param_named(scl_freq, scl_freq, uint, 0444);
 MODULE_PARM_DESC(scl_freq, "SCL frequency override");
@@ -227,6 +230,7 @@ struct qup_i2c_dev {
 	int			irq;
 	struct clk		*clk;
 	struct clk		*pclk;
+	struct icc_path		*icc_path;
 	struct i2c_adapter	adap;
 
 	int			clk_ctl;
@@ -255,6 +259,10 @@ struct qup_i2c_dev {
 	/* To configure when bus is in run state */
 	u32			config_run;
 
+	/* bandwidth votes */
+	u32			src_clk_freq;
+	u32			cur_bw_clk_freq;
+
 	/* dma parameters */
 	bool			is_dma;
 	/* To check if the current transfer is using DMA */
@@ -444,8 +452,10 @@ static int qup_i2c_bus_active(struct qup_i2c_dev *qup, int len)
 		if (!(status & I2C_STATUS_BUS_ACTIVE))
 			break;
 
-		if (time_after(jiffies, timeout))
+		if (time_after(jiffies, timeout)) {
 			ret = -ETIMEDOUT;
+			break;
+		}
 
 		usleep_range(len, len * 2);
 	}
@@ -453,6 +463,23 @@ static int qup_i2c_bus_active(struct qup_i2c_dev *qup, int len)
 	return ret;
 }
 
+static int qup_i2c_vote_bw(struct qup_i2c_dev *qup, u32 clk_freq)
+{
+	u32 needed_peak_bw;
+	int ret;
+
+	if (qup->cur_bw_clk_freq == clk_freq)
+		return 0;
+
+	needed_peak_bw = Bps_to_icc(clk_freq * QUP_BUS_WIDTH);
+	ret = icc_set_bw(qup->icc_path, 0, needed_peak_bw);
+	if (ret)
+		return ret;
+
+	qup->cur_bw_clk_freq = clk_freq;
+	return 0;
+}
+
 static void qup_i2c_write_tx_fifo_v1(struct qup_i2c_dev *qup)
 {
 	struct qup_i2c_block *blk = &qup->blk;
@@ -838,6 +865,10 @@ static int qup_i2c_bam_xfer(struct i2c_adapter *adap, struct i2c_msg *msg,
 	int ret = 0;
 	int idx = 0;
 
+	ret = qup_i2c_vote_bw(qup, qup->src_clk_freq);
+	if (ret)
+		return ret;
+
 	enable_irq(qup->irq);
 	ret = qup_i2c_req_dma(qup);
 
@@ -1643,6 +1674,7 @@ static void qup_i2c_disable_clocks(struct qup_i2c_dev *qup)
 	config = readl(qup->base + QUP_CONFIG);
 	config |= QUP_CLOCK_AUTO_GATE;
 	writel(config, qup->base + QUP_CONFIG);
+	qup_i2c_vote_bw(qup, 0);
 	clk_disable_unprepare(qup->pclk);
 }
 
@@ -1743,6 +1775,11 @@ static int qup_i2c_probe(struct platform_device *pdev)
 			goto fail_dma;
 		}
 		qup->is_dma = true;
+
+		qup->icc_path = devm_of_icc_get(&pdev->dev, NULL);
+		if (IS_ERR(qup->icc_path))
+			return dev_err_probe(&pdev->dev, PTR_ERR(qup->icc_path),
+					     "failed to get interconnect path\n");
 	}
 
 nodma:
@@ -1791,6 +1828,7 @@ nodma:
 		qup_i2c_enable_clocks(qup);
 		src_clk_freq = clk_get_rate(qup->clk);
 	}
+	qup->src_clk_freq = src_clk_freq;
 
 	/*
 	 * Bootloaders might leave a pending interrupt on certain QUP's,
diff --git a/drivers/i2c/busses/i2c-robotfuzz-osif.c b/drivers/i2c/busses/i2c-robotfuzz-osif.c
index 80d45079b763..e0a76fb5bc31 100644
--- a/drivers/i2c/busses/i2c-robotfuzz-osif.c
+++ b/drivers/i2c/busses/i2c-robotfuzz-osif.c
@@ -111,6 +111,11 @@ static u32 osif_func(struct i2c_adapter *adapter)
 	return I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL;
 }
 
+/* prevent invalid 0-length usb_control_msg */
+static const struct i2c_adapter_quirks osif_quirks = {
+	.flags = I2C_AQ_NO_ZERO_LEN_READ,
+};
+
 static const struct i2c_algorithm osif_algorithm = {
 	.xfer = osif_xfer,
 	.functionality = osif_func,
@@ -143,6 +148,7 @@ static int osif_probe(struct usb_interface *interface,
 
 	priv->adapter.owner = THIS_MODULE;
 	priv->adapter.class = I2C_CLASS_HWMON;
+	priv->adapter.quirks = &osif_quirks;
 	priv->adapter.algo = &osif_algorithm;
 	priv->adapter.algo_data = priv;
 	snprintf(priv->adapter.name, sizeof(priv->adapter.name),
diff --git a/drivers/i2c/busses/i2c-sis630.c b/drivers/i2c/busses/i2c-sis630.c
index 3505cf29cedd..a19c3d251804 100644
--- a/drivers/i2c/busses/i2c-sis630.c
+++ b/drivers/i2c/busses/i2c-sis630.c
@@ -509,6 +509,8 @@ MODULE_DEVICE_TABLE(pci, sis630_ids);
 
 static int sis630_probe(struct pci_dev *dev, const struct pci_device_id *id)
 {
+	int ret;
+
 	if (sis630_setup(dev)) {
 		dev_err(&dev->dev,
 			"SIS630 compatible bus not detected, "
@@ -522,7 +524,15 @@ static int sis630_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	snprintf(sis630_adapter.name, sizeof(sis630_adapter.name),
 		 "SMBus SIS630 adapter at %04x", smbus_base + SMB_STS);
 
-	return i2c_add_adapter(&sis630_adapter);
+	ret = i2c_add_adapter(&sis630_adapter);
+	if (ret)
+		goto release_region;
+
+	return 0;
+
+release_region:
+	release_region(smbus_base + SMB_STS, SIS630_SMB_IOREGION);
+	return ret;
 }
 
 static void sis630_remove(struct pci_dev *dev)
diff --git a/drivers/i2c/busses/i2c-stm32.c b/drivers/i2c/busses/i2c-stm32.c
index 157c64e27d0b..f84ec056e36d 100644
--- a/drivers/i2c/busses/i2c-stm32.c
+++ b/drivers/i2c/busses/i2c-stm32.c
@@ -102,7 +102,6 @@ int stm32_i2c_prep_dma_xfer(struct device *dev, struct stm32_i2c_dma *dma,
 			    void *dma_async_param)
 {
 	struct dma_async_tx_descriptor *txdesc;
-	struct device *chan_dev;
 	int ret;
 
 	if (rd_wr) {
@@ -116,11 +115,10 @@ int stm32_i2c_prep_dma_xfer(struct device *dev, struct stm32_i2c_dma *dma,
 	}
 
 	dma->dma_len = len;
-	chan_dev = dma->chan_using->device->dev;
 
-	dma->dma_buf = dma_map_single(chan_dev, buf, dma->dma_len,
+	dma->dma_buf = dma_map_single(dev, buf, dma->dma_len,
 				      dma->dma_data_dir);
-	if (dma_mapping_error(chan_dev, dma->dma_buf)) {
+	if (dma_mapping_error(dev, dma->dma_buf)) {
 		dev_err(dev, "DMA mapping failed\n");
 		return -EINVAL;
 	}
@@ -150,7 +148,7 @@ int stm32_i2c_prep_dma_xfer(struct device *dev, struct stm32_i2c_dma *dma,
 	return 0;
 
 err:
-	dma_unmap_single(chan_dev, dma->dma_buf, dma->dma_len,
+	dma_unmap_single(dev, dma->dma_buf, dma->dma_len,
 			 dma->dma_data_dir);
 	return ret;
 }
diff --git a/drivers/i2c/busses/i2c-stm32f7.c b/drivers/i2c/busses/i2c-stm32f7.c
index 0174ead99de6..a4587f281216 100644
--- a/drivers/i2c/busses/i2c-stm32f7.c
+++ b/drivers/i2c/busses/i2c-stm32f7.c
@@ -739,12 +739,13 @@ static void stm32f7_i2c_disable_dma_req(struct stm32f7_i2c_dev *i2c_dev)
 
 static void stm32f7_i2c_dma_callback(void *arg)
 {
-	struct stm32f7_i2c_dev *i2c_dev = (struct stm32f7_i2c_dev *)arg;
+	struct stm32f7_i2c_dev *i2c_dev = arg;
 	struct stm32_i2c_dma *dma = i2c_dev->dma;
-	struct device *dev = dma->chan_using->device->dev;
 
 	stm32f7_i2c_disable_dma_req(i2c_dev);
-	dma_unmap_single(dev, dma->dma_buf, dma->dma_len, dma->dma_data_dir);
+	dmaengine_terminate_async(dma->chan_using);
+	dma_unmap_single(i2c_dev->dev, dma->dma_buf, dma->dma_len,
+			 dma->dma_data_dir);
 	complete(&dma->dma_complete);
 }
 
@@ -1510,7 +1511,6 @@ static irqreturn_t stm32f7_i2c_handle_isr_errs(struct stm32f7_i2c_dev *i2c_dev,
 	u16 addr = f7_msg->addr;
 	void __iomem *base = i2c_dev->base;
 	struct device *dev = i2c_dev->dev;
-	struct stm32_i2c_dma *dma = i2c_dev->dma;
 
 	/* Bus error */
 	if (status & STM32F7_I2C_ISR_BERR) {
@@ -1551,10 +1551,8 @@ static irqreturn_t stm32f7_i2c_handle_isr_errs(struct stm32f7_i2c_dev *i2c_dev,
 	}
 
 	/* Disable dma */
-	if (i2c_dev->use_dma) {
-		stm32f7_i2c_disable_dma_req(i2c_dev);
-		dmaengine_terminate_async(dma->chan_using);
-	}
+	if (i2c_dev->use_dma)
+		stm32f7_i2c_dma_callback(i2c_dev);
 
 	i2c_dev->master_mode = false;
 	complete(&i2c_dev->complete);
@@ -1600,7 +1598,6 @@ static irqreturn_t stm32f7_i2c_isr_event_thread(int irq, void *data)
 {
 	struct stm32f7_i2c_dev *i2c_dev = data;
 	struct stm32f7_i2c_msg *f7_msg = &i2c_dev->f7_msg;
-	struct stm32_i2c_dma *dma = i2c_dev->dma;
 	void __iomem *base = i2c_dev->base;
 	u32 status, mask;
 	int ret;
@@ -1619,10 +1616,8 @@ static irqreturn_t stm32f7_i2c_isr_event_thread(int irq, void *data)
 		dev_dbg(i2c_dev->dev, "<%s>: Receive NACK (addr %x)\n",
 			__func__, f7_msg->addr);
 		writel_relaxed(STM32F7_I2C_ICR_NACKCF, base + STM32F7_I2C_ICR);
-		if (i2c_dev->use_dma) {
-			stm32f7_i2c_disable_dma_req(i2c_dev);
-			dmaengine_terminate_async(dma->chan_using);
-		}
+		if (i2c_dev->use_dma)
+			stm32f7_i2c_dma_callback(i2c_dev);
 		f7_msg->result = -ENXIO;
 	}
 
@@ -1640,8 +1635,7 @@ static irqreturn_t stm32f7_i2c_isr_event_thread(int irq, void *data)
 			ret = wait_for_completion_timeout(&i2c_dev->dma->dma_complete, HZ);
 			if (!ret) {
 				dev_dbg(i2c_dev->dev, "<%s>: Timed out\n", __func__);
-				stm32f7_i2c_disable_dma_req(i2c_dev);
-				dmaengine_terminate_async(dma->chan_using);
+				stm32f7_i2c_dma_callback(i2c_dev);
 				f7_msg->result = -ETIMEDOUT;
 			}
 		}
diff --git a/drivers/i2c/busses/i2c-tegra.c b/drivers/i2c/busses/i2c-tegra.c
index 1df5b4204142..fbab82d457fb 100644
--- a/drivers/i2c/busses/i2c-tegra.c
+++ b/drivers/i2c/busses/i2c-tegra.c
@@ -607,7 +607,6 @@ static int tegra_i2c_wait_for_config_load(struct tegra_i2c_dev *i2c_dev)
 static int tegra_i2c_init(struct tegra_i2c_dev *i2c_dev)
 {
 	u32 val, clk_divisor, clk_multiplier, tsu_thd, tlow, thigh, non_hs_mode;
-	acpi_handle handle = ACPI_HANDLE(i2c_dev->dev);
 	struct i2c_timings *t = &i2c_dev->timings;
 	int err;
 
@@ -619,11 +618,7 @@ static int tegra_i2c_init(struct tegra_i2c_dev *i2c_dev)
 	 * emit a noisy warning on error, which won't stay unnoticed and
 	 * won't hose machine entirely.
 	 */
-	if (handle)
-		err = acpi_evaluate_object(handle, "_RST", NULL, NULL);
-	else
-		err = reset_control_reset(i2c_dev->rst);
-
+	err = device_reset(i2c_dev->dev);
 	WARN_ON_ONCE(err);
 
 	if (IS_DVC(i2c_dev))
@@ -1395,6 +1390,11 @@ static int tegra_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msgs[],
 			ret = tegra_i2c_xfer_msg(i2c_dev, &msgs[i], MSG_END_CONTINUE);
 			if (ret)
 				break;
+
+			/* Validate message length before proceeding */
+			if (msgs[i].buf[0] == 0 || msgs[i].buf[0] > I2C_SMBUS_BLOCK_MAX)
+				break;
+
 			/* Set the msg length from first byte */
 			msgs[i].len += msgs[i].buf[0];
 			dev_dbg(i2c_dev->dev, "reading %d bytes\n", msgs[i].len);
@@ -1661,19 +1661,6 @@ static void tegra_i2c_parse_dt(struct tegra_i2c_dev *i2c_dev)
 		i2c_dev->is_vi = true;
 }
 
-static int tegra_i2c_init_reset(struct tegra_i2c_dev *i2c_dev)
-{
-	if (ACPI_HANDLE(i2c_dev->dev))
-		return 0;
-
-	i2c_dev->rst = devm_reset_control_get_exclusive(i2c_dev->dev, "i2c");
-	if (IS_ERR(i2c_dev->rst))
-		return dev_err_probe(i2c_dev->dev, PTR_ERR(i2c_dev->rst),
-				      "failed to get reset control\n");
-
-	return 0;
-}
-
 static int tegra_i2c_init_clocks(struct tegra_i2c_dev *i2c_dev)
 {
 	int err;
@@ -1783,10 +1770,6 @@ static int tegra_i2c_probe(struct platform_device *pdev)
 
 	tegra_i2c_parse_dt(i2c_dev);
 
-	err = tegra_i2c_init_reset(i2c_dev);
-	if (err)
-		return err;
-
 	err = tegra_i2c_init_clocks(i2c_dev);
 	if (err)
 		return err;
diff --git a/drivers/i2c/busses/i2c-tiny-usb.c b/drivers/i2c/busses/i2c-tiny-usb.c
index 0f2ed181b266..0cc7c0a816fc 100644
--- a/drivers/i2c/busses/i2c-tiny-usb.c
+++ b/drivers/i2c/busses/i2c-tiny-usb.c
@@ -138,6 +138,11 @@ out:
 	return ret;
 }
 
+/* prevent invalid 0-length usb_control_msg */
+static const struct i2c_adapter_quirks usb_quirks = {
+	.flags = I2C_AQ_NO_ZERO_LEN_READ,
+};
+
 /* This is the actual algorithm we define */
 static const struct i2c_algorithm usb_algorithm = {
 	.xfer = usb_xfer,
@@ -246,6 +251,7 @@ static int i2c_tiny_usb_probe(struct usb_interface *interface,
 	/* setup i2c adapter description */
 	dev->adapter.owner = THIS_MODULE;
 	dev->adapter.class = I2C_CLASS_HWMON;
+	dev->adapter.quirks = &usb_quirks;
 	dev->adapter.algo = &usb_algorithm;
 	dev->adapter.algo_data = dev;
 	snprintf(dev->adapter.name, sizeof(dev->adapter.name),
diff --git a/drivers/i2c/busses/i2c-virtio.c b/drivers/i2c/busses/i2c-virtio.c
index 2a351f961b89..c8c40ff9765d 100644
--- a/drivers/i2c/busses/i2c-virtio.c
+++ b/drivers/i2c/busses/i2c-virtio.c
@@ -116,15 +116,16 @@ static int virtio_i2c_complete_reqs(struct virtqueue *vq,
 	for (i = 0; i < num; i++) {
 		struct virtio_i2c_req *req = &reqs[i];
 
-		wait_for_completion(&req->completion);
-
-		if (!failed && req->in_hdr.status != VIRTIO_I2C_MSG_OK)
-			failed = true;
+		if (!failed) {
+			if (wait_for_completion_interruptible(&req->completion))
+				failed = true;
+			else if (req->in_hdr.status != VIRTIO_I2C_MSG_OK)
+				failed = true;
+			else
+				j++;
+		}
 
 		i2c_put_dma_safe_msg_buf(reqs[i].buf, &msgs[i], !failed);
-
-		if (!failed)
-			j++;
 	}
 
 	return j;
diff --git a/drivers/i2c/i2c-atr.c b/drivers/i2c/i2c-atr.c
index 0d54d0b5e327..5342e934aa5e 100644
--- a/drivers/i2c/i2c-atr.c
+++ b/drivers/i2c/i2c-atr.c
@@ -8,12 +8,12 @@
  * Originally based on i2c-mux.c
  */
 
-#include <linux/fwnode.h>
 #include <linux/i2c-atr.h>
 #include <linux/i2c.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
+#include <linux/property.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 
diff --git a/drivers/i2c/i2c-core-acpi.c b/drivers/i2c/i2c-core-acpi.c
index 14ae0cfc325e..f43067f6797e 100644
--- a/drivers/i2c/i2c-core-acpi.c
+++ b/drivers/i2c/i2c-core-acpi.c
@@ -355,6 +355,26 @@ static const struct acpi_device_id i2c_acpi_force_400khz_device_ids[] = {
 	{}
 };
 
+static const struct acpi_device_id i2c_acpi_force_100khz_device_ids[] = {
+	/*
+	 * When a 400KHz freq is used on this model of ELAN touchpad in Linux,
+	 * excessive smoothing (similar to when the touchpad's firmware detects
+	 * a noisy signal) is sometimes applied. As some devices' (e.g, Lenovo
+	 * V15 G4) ACPI tables specify a 400KHz frequency for this device and
+	 * some I2C busses (e.g, Designware I2C) default to a 400KHz freq,
+	 * force the speed to 100KHz as a workaround.
+	 *
+	 * For future investigation: This problem may be related to the default
+	 * HCNT/LCNT values given by some busses' drivers, because they are not
+	 * specified in the aforementioned devices' ACPI tables, and because
+	 * the device works without issues on Windows at what is expected to be
+	 * a 400KHz frequency. The root cause of the issue is not known.
+	 */
+	{ "DLL0945", 0 },
+	{ "ELAN06FA", 0 },
+	{}
+};
+
 static acpi_status i2c_acpi_lookup_speed(acpi_handle handle, u32 level,
 					   void *data, void **return_value)
 {
@@ -373,6 +393,9 @@ static acpi_status i2c_acpi_lookup_speed(acpi_handle handle, u32 level,
 	if (acpi_match_device_ids(adev, i2c_acpi_force_400khz_device_ids) == 0)
 		lookup->force_speed = I2C_MAX_FAST_MODE_FREQ;
 
+	if (acpi_match_device_ids(adev, i2c_acpi_force_100khz_device_ids) == 0)
+		lookup->force_speed = I2C_MAX_STANDARD_MODE_FREQ;
+
 	return AE_OK;
 }
 
diff --git a/drivers/i2c/muxes/i2c-mux-mule.c b/drivers/i2c/muxes/i2c-mux-mule.c
index 284ff4afeeac..d3b32b794172 100644
--- a/drivers/i2c/muxes/i2c-mux-mule.c
+++ b/drivers/i2c/muxes/i2c-mux-mule.c
@@ -47,7 +47,6 @@ static int mule_i2c_mux_probe(struct platform_device *pdev)
 	struct mule_i2c_reg_mux *priv;
 	struct i2c_client *client;
 	struct i2c_mux_core *muxc;
-	struct device_node *dev;
 	unsigned int readback;
 	int ndev, ret;
 	bool old_fw;
@@ -95,7 +94,7 @@ static int mule_i2c_mux_probe(struct platform_device *pdev)
 				     "Failed to register mux remove\n");
 
 	/* Create device adapters */
-	for_each_child_of_node(mux_dev->of_node, dev) {
+	for_each_child_of_node_scoped(mux_dev->of_node, dev) {
 		u32 reg;
 
 		ret = of_property_read_u32(dev, "reg", &reg);
diff --git a/drivers/i3c/internals.h b/drivers/i3c/internals.h
index 433f6088b7ce..ce04aa4f269e 100644
--- a/drivers/i3c/internals.h
+++ b/drivers/i3c/internals.h
@@ -9,6 +9,7 @@
 #define I3C_INTERNALS_H
 
 #include <linux/i3c/master.h>
+#include <linux/io.h>
 
 void i3c_bus_normaluse_lock(struct i3c_bus *bus);
 void i3c_bus_normaluse_unlock(struct i3c_bus *bus);
diff --git a/drivers/i3c/master.c b/drivers/i3c/master.c
index 42310c9a00c2..c8e5c9291ea4 100644
--- a/drivers/i3c/master.c
+++ b/drivers/i3c/master.c
@@ -1439,7 +1439,7 @@ static int i3c_master_retrieve_dev_info(struct i3c_dev_desc *dev)
 
 	if (dev->info.bcr & I3C_BCR_HDR_CAP) {
 		ret = i3c_master_gethdrcap_locked(master, &dev->info);
-		if (ret)
+		if (ret && ret != -ENOTSUPP)
 			return ret;
 	}
 
@@ -1919,7 +1919,7 @@ static int i3c_master_bus_init(struct i3c_master_controller *master)
 		goto err_bus_cleanup;
 
 	if (master->ops->set_speed) {
-		master->ops->set_speed(master, I3C_OPEN_DRAIN_NORMAL_SPEED);
+		ret = master->ops->set_speed(master, I3C_OPEN_DRAIN_NORMAL_SPEED);
 		if (ret)
 			goto err_bus_cleanup;
 	}
@@ -2471,6 +2471,8 @@ static int i3c_i2c_notifier_call(struct notifier_block *nb, unsigned long action
 	case BUS_NOTIFY_DEL_DEVICE:
 		ret = i3c_master_i2c_detach(adap, client);
 		break;
+	default:
+		ret = -EINVAL;
 	}
 	i3c_bus_maintenance_unlock(&master->bus);
 
@@ -2553,6 +2555,9 @@ static void i3c_master_unregister_i3c_devs(struct i3c_master_controller *master)
  */
 void i3c_master_queue_ibi(struct i3c_dev_desc *dev, struct i3c_ibi_slot *slot)
 {
+	if (!dev->ibi || !slot)
+		return;
+
 	atomic_inc(&dev->ibi->pending_ibis);
 	queue_work(dev->ibi->wq, &slot->work);
 }
diff --git a/drivers/i3c/master/Kconfig b/drivers/i3c/master/Kconfig
index 90dee3ec5520..77da199c7413 100644
--- a/drivers/i3c/master/Kconfig
+++ b/drivers/i3c/master/Kconfig
@@ -57,3 +57,14 @@ config MIPI_I3C_HCI
 
 	  This driver can also be built as a module.  If so, the module will be
 	  called mipi-i3c-hci.
+
+config MIPI_I3C_HCI_PCI
+	tristate "MIPI I3C Host Controller Interface PCI support"
+	depends on MIPI_I3C_HCI
+	depends on PCI
+	help
+	  Support for MIPI I3C Host Controller Interface compatible hardware
+	  on the PCI bus.
+
+	  This driver can also be built as a module. If so, the module will be
+	  called mipi-i3c-hci-pci.
diff --git a/drivers/i3c/master/dw-i3c-master.c b/drivers/i3c/master/dw-i3c-master.c
index 8d694672c110..dbcd3984f257 100644
--- a/drivers/i3c/master/dw-i3c-master.c
+++ b/drivers/i3c/master/dw-i3c-master.c
@@ -1624,6 +1624,7 @@ EXPORT_SYMBOL_GPL(dw_i3c_common_probe);
 
 void dw_i3c_common_remove(struct dw_i3c_master *master)
 {
+	cancel_work_sync(&master->hj_work);
 	i3c_master_unregister(&master->base);
 
 	pm_runtime_disable(master->dev);
diff --git a/drivers/i3c/master/mipi-i3c-hci/Makefile b/drivers/i3c/master/mipi-i3c-hci/Makefile
index 1f8cd5c48fde..e3d3ef757035 100644
--- a/drivers/i3c/master/mipi-i3c-hci/Makefile
+++ b/drivers/i3c/master/mipi-i3c-hci/Makefile
@@ -5,3 +5,4 @@ mipi-i3c-hci-y				:= core.o ext_caps.o pio.o dma.o \
 					   cmd_v1.o cmd_v2.o \
 					   dat_v1.o dct_v1.o \
 					   hci_quirks.o
+obj-$(CONFIG_MIPI_I3C_HCI_PCI)		+= mipi-i3c-hci-pci.o
diff --git a/drivers/i3c/master/mipi-i3c-hci/dma.c b/drivers/i3c/master/mipi-i3c-hci/dma.c
index 13adc5840094..fe955703e59b 100644
--- a/drivers/i3c/master/mipi-i3c-hci/dma.c
+++ b/drivers/i3c/master/mipi-i3c-hci/dma.c
@@ -762,9 +762,26 @@ static bool hci_dma_irq_handler(struct i3c_hci *hci, unsigned int mask)
 			complete(&rh->op_done);
 
 		if (status & INTR_TRANSFER_ABORT) {
+			u32 ring_status;
+
 			dev_notice_ratelimited(&hci->master.dev,
 				"ring %d: Transfer Aborted\n", i);
 			mipi_i3c_hci_resume(hci);
+			ring_status = rh_reg_read(RING_STATUS);
+			if (!(ring_status & RING_STATUS_RUNNING) &&
+			    status & INTR_TRANSFER_COMPLETION &&
+			    status & INTR_TRANSFER_ERR) {
+				/*
+				 * Ring stop followed by run is an Intel
+				 * specific required quirk after resuming the
+				 * halted controller. Do it only when the ring
+				 * is not in running state after a transfer
+				 * error.
+				 */
+				rh_reg_write(RING_CONTROL, RING_CTRL_ENABLE);
+				rh_reg_write(RING_CONTROL, RING_CTRL_ENABLE |
+							   RING_CTRL_RUN_STOP);
+			}
 		}
 		if (status & INTR_WARN_INS_STOP_MODE)
 			dev_warn_ratelimited(&hci->master.dev,
diff --git a/drivers/i3c/master/mipi-i3c-hci/mipi-i3c-hci-pci.c b/drivers/i3c/master/mipi-i3c-hci/mipi-i3c-hci-pci.c
new file mode 100644
index 000000000000..c6c3a3ec11ea
--- /dev/null
+++ b/drivers/i3c/master/mipi-i3c-hci/mipi-i3c-hci-pci.c
@@ -0,0 +1,148 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * PCI glue code for MIPI I3C HCI driver
+ *
+ * Copyright (C) 2024 Intel Corporation
+ *
+ * Author: Jarkko Nikula <jarkko.nikula@linux.intel.com>
+ */
+#include <linux/acpi.h>
+#include <linux/idr.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/platform_device.h>
+
+struct mipi_i3c_hci_pci_info {
+	int (*init)(struct pci_dev *pci);
+};
+
+#define INTEL_PRIV_OFFSET		0x2b0
+#define INTEL_PRIV_SIZE			0x28
+#define INTEL_PRIV_RESETS		0x04
+#define INTEL_PRIV_RESETS_RESET		BIT(0)
+#define INTEL_PRIV_RESETS_RESET_DONE	BIT(1)
+
+static DEFINE_IDA(mipi_i3c_hci_pci_ida);
+
+static int mipi_i3c_hci_pci_intel_init(struct pci_dev *pci)
+{
+	unsigned long timeout;
+	void __iomem *priv;
+
+	priv = devm_ioremap(&pci->dev,
+			    pci_resource_start(pci, 0) + INTEL_PRIV_OFFSET,
+			    INTEL_PRIV_SIZE);
+	if (!priv)
+		return -ENOMEM;
+
+	/* Assert reset, wait for completion and release reset */
+	writel(0, priv + INTEL_PRIV_RESETS);
+	timeout = jiffies + msecs_to_jiffies(10);
+	while (!(readl(priv + INTEL_PRIV_RESETS) &
+		 INTEL_PRIV_RESETS_RESET_DONE)) {
+		if (time_after(jiffies, timeout))
+			break;
+		cpu_relax();
+	}
+	writel(INTEL_PRIV_RESETS_RESET, priv + INTEL_PRIV_RESETS);
+
+	return 0;
+}
+
+static struct mipi_i3c_hci_pci_info intel_info = {
+	.init = mipi_i3c_hci_pci_intel_init,
+};
+
+static int mipi_i3c_hci_pci_probe(struct pci_dev *pci,
+				  const struct pci_device_id *id)
+{
+	struct mipi_i3c_hci_pci_info *info;
+	struct platform_device *pdev;
+	struct resource res[2];
+	int dev_id, ret;
+
+	ret = pcim_enable_device(pci);
+	if (ret)
+		return ret;
+
+	pci_set_master(pci);
+
+	memset(&res, 0, sizeof(res));
+
+	res[0].flags = IORESOURCE_MEM;
+	res[0].start = pci_resource_start(pci, 0);
+	res[0].end = pci_resource_end(pci, 0);
+
+	res[1].flags = IORESOURCE_IRQ;
+	res[1].start = pci->irq;
+	res[1].end = pci->irq;
+
+	dev_id = ida_alloc(&mipi_i3c_hci_pci_ida, GFP_KERNEL);
+	if (dev_id < 0)
+		return dev_id;
+
+	pdev = platform_device_alloc("mipi-i3c-hci", dev_id);
+	if (!pdev)
+		return -ENOMEM;
+
+	pdev->dev.parent = &pci->dev;
+	device_set_node(&pdev->dev, dev_fwnode(&pci->dev));
+
+	ret = platform_device_add_resources(pdev, res, ARRAY_SIZE(res));
+	if (ret)
+		goto err;
+
+	info = (struct mipi_i3c_hci_pci_info *)id->driver_data;
+	if (info && info->init) {
+		ret = info->init(pci);
+		if (ret)
+			goto err;
+	}
+
+	ret = platform_device_add(pdev);
+	if (ret)
+		goto err;
+
+	pci_set_drvdata(pci, pdev);
+
+	return 0;
+
+err:
+	platform_device_put(pdev);
+	ida_free(&mipi_i3c_hci_pci_ida, dev_id);
+	return ret;
+}
+
+static void mipi_i3c_hci_pci_remove(struct pci_dev *pci)
+{
+	struct platform_device *pdev = pci_get_drvdata(pci);
+	int dev_id = pdev->id;
+
+	platform_device_unregister(pdev);
+	ida_free(&mipi_i3c_hci_pci_ida, dev_id);
+}
+
+static const struct pci_device_id mipi_i3c_hci_pci_devices[] = {
+	/* Panther Lake-H */
+	{ PCI_VDEVICE(INTEL, 0xe37c), (kernel_ulong_t)&intel_info},
+	{ PCI_VDEVICE(INTEL, 0xe36f), (kernel_ulong_t)&intel_info},
+	/* Panther Lake-P */
+	{ PCI_VDEVICE(INTEL, 0xe47c), (kernel_ulong_t)&intel_info},
+	{ PCI_VDEVICE(INTEL, 0xe46f), (kernel_ulong_t)&intel_info},
+	{ },
+};
+MODULE_DEVICE_TABLE(pci, mipi_i3c_hci_pci_devices);
+
+static struct pci_driver mipi_i3c_hci_pci_driver = {
+	.name = "mipi_i3c_hci_pci",
+	.id_table = mipi_i3c_hci_pci_devices,
+	.probe = mipi_i3c_hci_pci_probe,
+	.remove = mipi_i3c_hci_pci_remove,
+};
+
+module_pci_driver(mipi_i3c_hci_pci_driver);
+
+MODULE_AUTHOR("Jarkko Nikula <jarkko.nikula@intel.com>");
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("MIPI I3C HCI driver on PCI bus");
diff --git a/drivers/i3c/master/svc-i3c-master.c b/drivers/i3c/master/svc-i3c-master.c
index 565af3759813..474a96ebda22 100644
--- a/drivers/i3c/master/svc-i3c-master.c
+++ b/drivers/i3c/master/svc-i3c-master.c
@@ -158,6 +158,10 @@ struct svc_i3c_regs_save {
 	u32 mdynaddr;
 };
 
+struct svc_i3c_drvdata {
+	u32 quirks;
+};
+
 /**
  * struct svc_i3c_master - Silvaco I3C Master structure
  * @base: I3C master controller
@@ -183,6 +187,7 @@ struct svc_i3c_regs_save {
  * @ibi.tbq_slot: To be queued IBI slot
  * @ibi.lock: IBI lock
  * @lock: Transfer lock, protect between IBI work thread and callbacks from master
+ * @drvdata: Driver data
  * @enabled_events: Bit masks for enable events (IBI, HotJoin).
  * @mctrl_config: Configuration value in SVC_I3C_MCTRL for setting speed back.
  */
@@ -214,6 +219,7 @@ struct svc_i3c_master {
 		spinlock_t lock;
 	} ibi;
 	struct mutex lock;
+	const struct svc_i3c_drvdata *drvdata;
 	u32 enabled_events;
 	u32 mctrl_config;
 };
@@ -378,7 +384,7 @@ static int svc_i3c_master_handle_ibi(struct svc_i3c_master *master,
 	       slot->len < SVC_I3C_FIFO_SIZE) {
 		mdatactrl = readl(master->regs + SVC_I3C_MDATACTRL);
 		count = SVC_I3C_MDATACTRL_RXCOUNT(mdatactrl);
-		readsl(master->regs + SVC_I3C_MRDATAB, buf, count);
+		readsb(master->regs + SVC_I3C_MRDATAB, buf, count);
 		slot->len += count;
 		buf += count;
 	}
@@ -505,6 +511,8 @@ static void svc_i3c_master_ibi_work(struct work_struct *work)
 			queue_work(master->base.wq, &master->hj_work);
 		break;
 	case SVC_I3C_MSTATUS_IBITYPE_MASTER_REQUEST:
+		svc_i3c_master_emit_stop(master);
+		break;
 	default:
 		break;
 	}
@@ -853,6 +861,8 @@ static int svc_i3c_master_do_daa_locked(struct svc_i3c_master *master,
 	u32 reg;
 	int ret, i;
 
+	svc_i3c_master_flush_fifo(master);
+
 	while (true) {
 		/* SVC_I3C_MCTRL_REQUEST_PROC_DAA have two mode, ENTER DAA or PROCESS DAA.
 		 *
@@ -990,7 +1000,7 @@ static int svc_i3c_update_ibirules(struct svc_i3c_master *master)
 
 	/* Create the IBIRULES register for both cases */
 	i3c_bus_for_each_i3cdev(&master->base.bus, dev) {
-		if (I3C_BCR_DEVICE_ROLE(dev->info.bcr) == I3C_BCR_I3C_MASTER)
+		if (!(dev->info.bcr & I3C_BCR_IBI_REQ_CAP))
 			continue;
 
 		if (dev->info.bcr & I3C_BCR_IBI_PAYLOAD) {
@@ -1768,6 +1778,10 @@ static int svc_i3c_master_probe(struct platform_device *pdev)
 	if (!master)
 		return -ENOMEM;
 
+	master->drvdata = of_device_get_match_data(dev);
+	if (!master->drvdata)
+		return -EINVAL;
+
 	master->regs = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(master->regs))
 		return PTR_ERR(master->regs);
@@ -1909,8 +1923,13 @@ static const struct dev_pm_ops svc_i3c_pm_ops = {
 			   svc_i3c_runtime_resume, NULL)
 };
 
+static const struct svc_i3c_drvdata npcm845_drvdata = {};
+
+static const struct svc_i3c_drvdata svc_default_drvdata = {};
+
 static const struct of_device_id svc_i3c_master_of_match_tbl[] = {
-	{ .compatible = "silvaco,i3c-master-v1"},
+	{ .compatible = "nuvoton,npcm845-i3c", .data = &npcm845_drvdata },
+	{ .compatible = "silvaco,i3c-master-v1", .data = &svc_default_drvdata },
 	{ /* sentinel */ },
 };
 MODULE_DEVICE_TABLE(of, svc_i3c_master_of_match_tbl);
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index 67aebfe0fed6..4506e1cc4b65 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -55,6 +55,7 @@
 #include <asm/intel-family.h>
 #include <asm/mwait.h>
 #include <asm/spec-ctrl.h>
+#include <asm/tsc.h>
 #include <asm/fpu/api.h>
 
 #define INTEL_IDLE_VERSION "0.5.1"
@@ -1607,7 +1608,7 @@ static const struct x86_cpu_id intel_idle_ids[] __initconst = {
 };
 
 static const struct x86_cpu_id intel_mwait_ids[] __initconst = {
-	X86_MATCH_VENDOR_FAM_FEATURE(INTEL, 6, X86_FEATURE_MWAIT, NULL),
+	X86_MATCH_VENDOR_FAM_FEATURE(INTEL, X86_FAMILY_ANY, X86_FEATURE_MWAIT, NULL),
 	{}
 };
 
@@ -1749,6 +1750,9 @@ static void __init intel_idle_init_cstates_acpi(struct cpuidle_driver *drv)
 		if (intel_idle_state_needs_timer_stop(state))
 			state->flags |= CPUIDLE_FLAG_TIMER_STOP;
 
+		if (cx->type > ACPI_STATE_C1 && !boot_cpu_has(X86_FEATURE_NONSTOP_TSC))
+			mark_tsc_unstable("TSC halts in idle");
+
 		state->enter = intel_idle;
 		state->enter_s2idle = intel_idle_s2idle;
 	}
diff --git a/drivers/iio/accel/adis16201.c b/drivers/iio/accel/adis16201.c
index d054721859b3..99b05548b7bd 100644
--- a/drivers/iio/accel/adis16201.c
+++ b/drivers/iio/accel/adis16201.c
@@ -211,9 +211,9 @@ static const struct iio_chan_spec adis16201_channels[] = {
 			BIT(IIO_CHAN_INFO_CALIBBIAS), 0, 14),
 	ADIS_AUX_ADC_CHAN(ADIS16201_AUX_ADC_REG, ADIS16201_SCAN_AUX_ADC, 0, 12),
 	ADIS_INCLI_CHAN(X, ADIS16201_XINCL_OUT_REG, ADIS16201_SCAN_INCLI_X,
-			BIT(IIO_CHAN_INFO_CALIBBIAS), 0, 14),
+			BIT(IIO_CHAN_INFO_CALIBBIAS), 0, 12),
 	ADIS_INCLI_CHAN(Y, ADIS16201_YINCL_OUT_REG, ADIS16201_SCAN_INCLI_Y,
-			BIT(IIO_CHAN_INFO_CALIBBIAS), 0, 14),
+			BIT(IIO_CHAN_INFO_CALIBBIAS), 0, 12),
 	IIO_CHAN_SOFT_TIMESTAMP(7)
 };
 
diff --git a/drivers/iio/accel/adxl355_core.c b/drivers/iio/accel/adxl355_core.c
index eabaefa92f19..5e1946828b96 100644
--- a/drivers/iio/accel/adxl355_core.c
+++ b/drivers/iio/accel/adxl355_core.c
@@ -231,7 +231,7 @@ struct adxl355_data {
 		u8 transf_buf[3];
 		struct {
 			u8 buf[14];
-			s64 ts;
+			aligned_s64 ts;
 		} buffer;
 	} __aligned(IIO_DMA_MINALIGN);
 };
diff --git a/drivers/iio/accel/adxl367.c b/drivers/iio/accel/adxl367.c
index e790a66d86c7..d44d52e5a514 100644
--- a/drivers/iio/accel/adxl367.c
+++ b/drivers/iio/accel/adxl367.c
@@ -604,18 +604,14 @@ static int _adxl367_set_odr(struct adxl367_state *st, enum adxl367_odr odr)
 	if (ret)
 		return ret;
 
+	st->odr = odr;
+
 	/* Activity timers depend on ODR */
 	ret = _adxl367_set_act_time_ms(st, st->act_time_ms);
 	if (ret)
 		return ret;
 
-	ret = _adxl367_set_inact_time_ms(st, st->inact_time_ms);
-	if (ret)
-		return ret;
-
-	st->odr = odr;
-
-	return 0;
+	return _adxl367_set_inact_time_ms(st, st->inact_time_ms);
 }
 
 static int adxl367_set_odr(struct iio_dev *indio_dev, enum adxl367_odr odr)
diff --git a/drivers/iio/accel/fxls8962af-core.c b/drivers/iio/accel/fxls8962af-core.c
index acadabec4df7..a4e4e7964a1a 100644
--- a/drivers/iio/accel/fxls8962af-core.c
+++ b/drivers/iio/accel/fxls8962af-core.c
@@ -22,6 +22,7 @@
 #include <linux/property.h>
 #include <linux/regulator/consumer.h>
 #include <linux/regmap.h>
+#include <linux/units.h>
 
 #include <linux/iio/buffer.h>
 #include <linux/iio/events.h>
@@ -436,8 +437,16 @@ static int fxls8962af_read_raw(struct iio_dev *indio_dev,
 		*val = FXLS8962AF_TEMP_CENTER_VAL;
 		return IIO_VAL_INT;
 	case IIO_CHAN_INFO_SCALE:
-		*val = 0;
-		return fxls8962af_read_full_scale(data, val2);
+		switch (chan->type) {
+		case IIO_TEMP:
+			*val = MILLIDEGREE_PER_DEGREE;
+			return IIO_VAL_INT;
+		case IIO_ACCEL:
+			*val = 0;
+			return fxls8962af_read_full_scale(data, val2);
+		default:
+			return -EINVAL;
+		}
 	case IIO_CHAN_INFO_SAMP_FREQ:
 		return fxls8962af_read_samp_freq(data, val, val2);
 	default:
@@ -736,9 +745,11 @@ static const struct iio_event_spec fxls8962af_event[] = {
 	.type = IIO_TEMP, \
 	.address = FXLS8962AF_TEMP_OUT, \
 	.info_mask_separate = BIT(IIO_CHAN_INFO_RAW) | \
+			      BIT(IIO_CHAN_INFO_SCALE) | \
 			      BIT(IIO_CHAN_INFO_OFFSET),\
 	.scan_index = -1, \
 	.scan_type = { \
+		.sign = 's', \
 		.realbits = 8, \
 		.storagebits = 8, \
 	}, \
@@ -854,6 +865,8 @@ static int fxls8962af_buffer_predisable(struct iio_dev *indio_dev)
 	if (ret)
 		return ret;
 
+	synchronize_irq(data->irq);
+
 	ret = __fxls8962af_fifo_set_mode(data, false);
 
 	if (data->enable_event)
diff --git a/drivers/iio/accel/mma8452.c b/drivers/iio/accel/mma8452.c
index 62e6369e2269..de207526babe 100644
--- a/drivers/iio/accel/mma8452.c
+++ b/drivers/iio/accel/mma8452.c
@@ -711,7 +711,7 @@ static int mma8452_write_raw(struct iio_dev *indio_dev,
 			     int val, int val2, long mask)
 {
 	struct mma8452_data *data = iio_priv(indio_dev);
-	int i, ret;
+	int i, j, ret;
 
 	ret = iio_device_claim_direct_mode(indio_dev);
 	if (ret)
@@ -771,14 +771,18 @@ static int mma8452_write_raw(struct iio_dev *indio_dev,
 		break;
 
 	case IIO_CHAN_INFO_OVERSAMPLING_RATIO:
-		ret = mma8452_get_odr_index(data);
+		j = mma8452_get_odr_index(data);
 
 		for (i = 0; i < ARRAY_SIZE(mma8452_os_ratio); i++) {
-			if (mma8452_os_ratio[i][ret] == val) {
+			if (mma8452_os_ratio[i][j] == val) {
 				ret = mma8452_set_power_mode(data, i);
 				break;
 			}
 		}
+		if (i == ARRAY_SIZE(mma8452_os_ratio)) {
+			ret = -EINVAL;
+			break;
+		}
 		break;
 	default:
 		ret = -EINVAL;
diff --git a/drivers/iio/accel/msa311.c b/drivers/iio/accel/msa311.c
index 57025354c7cd..f484be27058d 100644
--- a/drivers/iio/accel/msa311.c
+++ b/drivers/iio/accel/msa311.c
@@ -593,23 +593,25 @@ static int msa311_read_raw_data(struct iio_dev *indio_dev,
 	__le16 axis;
 	int err;
 
-	err = pm_runtime_resume_and_get(dev);
+	err = iio_device_claim_direct_mode(indio_dev);
 	if (err)
 		return err;
 
-	err = iio_device_claim_direct_mode(indio_dev);
-	if (err)
+	err = pm_runtime_resume_and_get(dev);
+	if (err) {
+		iio_device_release_direct_mode(indio_dev);
 		return err;
+	}
 
 	mutex_lock(&msa311->lock);
 	err = msa311_get_axis(msa311, chan, &axis);
 	mutex_unlock(&msa311->lock);
 
-	iio_device_release_direct_mode(indio_dev);
-
 	pm_runtime_mark_last_busy(dev);
 	pm_runtime_put_autosuspend(dev);
 
+	iio_device_release_direct_mode(indio_dev);
+
 	if (err) {
 		dev_err(dev, "can't get axis %s (%pe)\n",
 			chan->datasheet_name, ERR_PTR(err));
@@ -755,10 +757,6 @@ static int msa311_write_samp_freq(struct iio_dev *indio_dev, int val, int val2)
 	unsigned int odr;
 	int err;
 
-	err = pm_runtime_resume_and_get(dev);
-	if (err)
-		return err;
-
 	/*
 	 * Sampling frequency changing is prohibited when buffer mode is
 	 * enabled, because sometimes MSA311 chip returns outliers during
@@ -768,6 +766,12 @@ static int msa311_write_samp_freq(struct iio_dev *indio_dev, int val, int val2)
 	if (err)
 		return err;
 
+	err = pm_runtime_resume_and_get(dev);
+	if (err) {
+		iio_device_release_direct_mode(indio_dev);
+		return err;
+	}
+
 	err = -EINVAL;
 	for (odr = 0; odr < ARRAY_SIZE(msa311_odr_table); odr++)
 		if (val == msa311_odr_table[odr].integral &&
@@ -778,11 +782,11 @@ static int msa311_write_samp_freq(struct iio_dev *indio_dev, int val, int val2)
 			break;
 		}
 
-	iio_device_release_direct_mode(indio_dev);
-
 	pm_runtime_mark_last_busy(dev);
 	pm_runtime_put_autosuspend(dev);
 
+	iio_device_release_direct_mode(indio_dev);
+
 	if (err)
 		dev_err(dev, "can't update frequency (%pe)\n", ERR_PTR(err));
 
diff --git a/drivers/iio/accel/st_accel_core.c b/drivers/iio/accel/st_accel_core.c
index 0e371efbda70..7394ea72948b 100644
--- a/drivers/iio/accel/st_accel_core.c
+++ b/drivers/iio/accel/st_accel_core.c
@@ -1353,6 +1353,7 @@ static int apply_acpi_orientation(struct iio_dev *indio_dev)
 	union acpi_object *ont;
 	union acpi_object *elements;
 	acpi_status status;
+	struct device *parent = indio_dev->dev.parent;
 	int ret = -EINVAL;
 	unsigned int val;
 	int i, j;
@@ -1371,7 +1372,7 @@ static int apply_acpi_orientation(struct iio_dev *indio_dev)
 	};
 
 
-	adev = ACPI_COMPANION(indio_dev->dev.parent);
+	adev = ACPI_COMPANION(parent);
 	if (!adev)
 		return -ENXIO;
 
@@ -1380,8 +1381,7 @@ static int apply_acpi_orientation(struct iio_dev *indio_dev)
 	if (status == AE_NOT_FOUND) {
 		return -ENXIO;
 	} else if (ACPI_FAILURE(status)) {
-		dev_warn(&indio_dev->dev, "failed to execute _ONT: %d\n",
-			 status);
+		dev_warn(parent, "failed to execute _ONT: %d\n", status);
 		return status;
 	}
 
@@ -1457,12 +1457,12 @@ static int apply_acpi_orientation(struct iio_dev *indio_dev)
 	}
 
 	ret = 0;
-	dev_info(&indio_dev->dev, "computed mount matrix from ACPI\n");
+	dev_info(parent, "computed mount matrix from ACPI\n");
 
 out:
 	kfree(buffer.pointer);
 	if (ret)
-		dev_dbg(&indio_dev->dev,
+		dev_dbg(parent,
 			"failed to apply ACPI orientation data: %d\n", ret);
 
 	return ret;
diff --git a/drivers/iio/adc/Kconfig b/drivers/iio/adc/Kconfig
index 6c4e74420fd2..216f3c9ce183 100644
--- a/drivers/iio/adc/Kconfig
+++ b/drivers/iio/adc/Kconfig
@@ -1452,6 +1452,7 @@ config TI_ADS1298
 	tristate "Texas Instruments ADS1298"
 	depends on SPI
 	select IIO_BUFFER
+	select IIO_KFIFO_BUF
 	help
 	  If you say yes here you get support for Texas Instruments ADS1298
 	  medical ADC chips
diff --git a/drivers/iio/adc/ad4130.c b/drivers/iio/adc/ad4130.c
index de32cc9d18c5..712f95f53c9e 100644
--- a/drivers/iio/adc/ad4130.c
+++ b/drivers/iio/adc/ad4130.c
@@ -223,6 +223,10 @@ enum ad4130_pin_function {
 	AD4130_PIN_FN_VBIAS = BIT(3),
 };
 
+/*
+ * If you make adaptations in this struct, you most likely also have to adapt
+ * ad4130_setup_info_eq(), too.
+ */
 struct ad4130_setup_info {
 	unsigned int			iout0_val;
 	unsigned int			iout1_val;
@@ -591,6 +595,40 @@ static irqreturn_t ad4130_irq_handler(int irq, void *private)
 	return IRQ_HANDLED;
 }
 
+static bool ad4130_setup_info_eq(struct ad4130_setup_info *a,
+				 struct ad4130_setup_info *b)
+{
+	/*
+	 * This is just to make sure that the comparison is adapted after
+	 * struct ad4130_setup_info was changed.
+	 */
+	static_assert(sizeof(*a) ==
+		      sizeof(struct {
+				     unsigned int iout0_val;
+				     unsigned int iout1_val;
+				     unsigned int burnout;
+				     unsigned int pga;
+				     unsigned int fs;
+				     u32 ref_sel;
+				     enum ad4130_filter_mode filter_mode;
+				     bool ref_bufp;
+				     bool ref_bufm;
+			     }));
+
+	if (a->iout0_val != b->iout0_val ||
+	    a->iout1_val != b->iout1_val ||
+	    a->burnout != b->burnout ||
+	    a->pga != b->pga ||
+	    a->fs != b->fs ||
+	    a->ref_sel != b->ref_sel ||
+	    a->filter_mode != b->filter_mode ||
+	    a->ref_bufp != b->ref_bufp ||
+	    a->ref_bufm != b->ref_bufm)
+		return false;
+
+	return true;
+}
+
 static int ad4130_find_slot(struct ad4130_state *st,
 			    struct ad4130_setup_info *target_setup_info,
 			    unsigned int *slot, bool *overwrite)
@@ -604,8 +642,7 @@ static int ad4130_find_slot(struct ad4130_state *st,
 		struct ad4130_slot_info *slot_info = &st->slots_info[i];
 
 		/* Immediately accept a matching setup info. */
-		if (!memcmp(target_setup_info, &slot_info->setup,
-			    sizeof(*target_setup_info))) {
+		if (ad4130_setup_info_eq(target_setup_info, &slot_info->setup)) {
 			*slot = i;
 			return 0;
 		}
diff --git a/drivers/iio/adc/ad7124.c b/drivers/iio/adc/ad7124.c
index 8d94bc2b1cac..9c9e0c950b42 100644
--- a/drivers/iio/adc/ad7124.c
+++ b/drivers/iio/adc/ad7124.c
@@ -147,7 +147,11 @@ struct ad7124_chip_info {
 struct ad7124_channel_config {
 	bool live;
 	unsigned int cfg_slot;
-	/* Following fields are used to compare equality. */
+	/*
+	 * Following fields are used to compare for equality. If you
+	 * make adaptations in it, you most likely also have to adapt
+	 * ad7124_find_similar_live_cfg(), too.
+	 */
 	struct_group(config_props,
 		enum ad7124_ref_sel refsel;
 		bool bipolar;
@@ -296,9 +300,9 @@ static int ad7124_get_3db_filter_freq(struct ad7124_state *st,
 
 	switch (st->channels[channel].cfg.filter_type) {
 	case AD7124_SINC3_FILTER:
-		return DIV_ROUND_CLOSEST(fadc * 230, 1000);
+		return DIV_ROUND_CLOSEST(fadc * 272, 1000);
 	case AD7124_SINC4_FILTER:
-		return DIV_ROUND_CLOSEST(fadc * 262, 1000);
+		return DIV_ROUND_CLOSEST(fadc * 230, 1000);
 	default:
 		return -EINVAL;
 	}
@@ -334,15 +338,38 @@ static struct ad7124_channel_config *ad7124_find_similar_live_cfg(struct ad7124_
 								  struct ad7124_channel_config *cfg)
 {
 	struct ad7124_channel_config *cfg_aux;
-	ptrdiff_t cmp_size;
 	int i;
 
-	cmp_size = sizeof_field(struct ad7124_channel_config, config_props);
+	/*
+	 * This is just to make sure that the comparison is adapted after
+	 * struct ad7124_channel_config was changed.
+	 */
+	static_assert(sizeof_field(struct ad7124_channel_config, config_props) ==
+		      sizeof(struct {
+				     enum ad7124_ref_sel refsel;
+				     bool bipolar;
+				     bool buf_positive;
+				     bool buf_negative;
+				     unsigned int vref_mv;
+				     unsigned int pga_bits;
+				     unsigned int odr;
+				     unsigned int odr_sel_bits;
+				     unsigned int filter_type;
+			     }));
+
 	for (i = 0; i < st->num_channels; i++) {
 		cfg_aux = &st->channels[i].cfg;
 
 		if (cfg_aux->live &&
-		    !memcmp(&cfg->config_props, &cfg_aux->config_props, cmp_size))
+		    cfg->refsel == cfg_aux->refsel &&
+		    cfg->bipolar == cfg_aux->bipolar &&
+		    cfg->buf_positive == cfg_aux->buf_positive &&
+		    cfg->buf_negative == cfg_aux->buf_negative &&
+		    cfg->vref_mv == cfg_aux->vref_mv &&
+		    cfg->pga_bits == cfg_aux->pga_bits &&
+		    cfg->odr == cfg_aux->odr &&
+		    cfg->odr_sel_bits == cfg_aux->odr_sel_bits &&
+		    cfg->filter_type == cfg_aux->filter_type)
 			return cfg_aux;
 	}
 
diff --git a/drivers/iio/adc/ad7173.c b/drivers/iio/adc/ad7173.c
index 5a65be00dd19..2eebc6f761a6 100644
--- a/drivers/iio/adc/ad7173.c
+++ b/drivers/iio/adc/ad7173.c
@@ -181,7 +181,11 @@ struct ad7173_channel_config {
 	u8 cfg_slot;
 	bool live;
 
-	/* Following fields are used to compare equality. */
+	/*
+	 * Following fields are used to compare equality. If you
+	 * make adaptations in it, you most likely also have to adapt
+	 * ad7173_find_live_config(), too.
+	 */
 	struct_group(config_props,
 		bool bipolar;
 		bool input_buf;
@@ -582,15 +586,28 @@ static struct ad7173_channel_config *
 ad7173_find_live_config(struct ad7173_state *st, struct ad7173_channel_config *cfg)
 {
 	struct ad7173_channel_config *cfg_aux;
-	ptrdiff_t cmp_size;
 	int i;
 
-	cmp_size = sizeof_field(struct ad7173_channel_config, config_props);
+	/*
+	 * This is just to make sure that the comparison is adapted after
+	 * struct ad7173_channel_config was changed.
+	 */
+	static_assert(sizeof_field(struct ad7173_channel_config, config_props) ==
+		      sizeof(struct {
+				     bool bipolar;
+				     bool input_buf;
+				     u8 odr;
+				     u8 ref_sel;
+			     }));
+
 	for (i = 0; i < st->num_channels; i++) {
 		cfg_aux = &st->channels[i].cfg;
 
 		if (cfg_aux->live &&
-		    !memcmp(&cfg->config_props, &cfg_aux->config_props, cmp_size))
+		    cfg->bipolar == cfg_aux->bipolar &&
+		    cfg->input_buf == cfg_aux->input_buf &&
+		    cfg->odr == cfg_aux->odr &&
+		    cfg->ref_sel == cfg_aux->ref_sel)
 			return cfg_aux;
 	}
 	return NULL;
diff --git a/drivers/iio/adc/ad7192.c b/drivers/iio/adc/ad7192.c
index 955e9eff0099..6fe32f866765 100644
--- a/drivers/iio/adc/ad7192.c
+++ b/drivers/iio/adc/ad7192.c
@@ -1082,7 +1082,7 @@ static int ad7192_update_scan_mode(struct iio_dev *indio_dev, const unsigned lon
 
 	conf &= ~AD7192_CONF_CHAN_MASK;
 	for_each_set_bit(i, scan_mask, 8)
-		conf |= FIELD_PREP(AD7192_CONF_CHAN_MASK, i);
+		conf |= FIELD_PREP(AD7192_CONF_CHAN_MASK, BIT(i));
 
 	ret = ad_sd_write_reg(&st->sd, AD7192_REG_CONF, 3, conf);
 	if (ret < 0)
diff --git a/drivers/iio/adc/ad7266.c b/drivers/iio/adc/ad7266.c
index 7949b076fb87..d4c9b85135f5 100644
--- a/drivers/iio/adc/ad7266.c
+++ b/drivers/iio/adc/ad7266.c
@@ -45,7 +45,7 @@ struct ad7266_state {
 	 */
 	struct {
 		__be16 sample[2];
-		s64 timestamp;
+		aligned_s64 timestamp;
 	} data __aligned(IIO_DMA_MINALIGN);
 };
 
diff --git a/drivers/iio/adc/ad7606_spi.c b/drivers/iio/adc/ad7606_spi.c
index 62ec12195307..42112f97fac1 100644
--- a/drivers/iio/adc/ad7606_spi.c
+++ b/drivers/iio/adc/ad7606_spi.c
@@ -127,7 +127,7 @@ static int ad7606_spi_reg_read(struct ad7606_state *st, unsigned int addr)
 		{
 			.tx_buf = &st->d16[0],
 			.len = 2,
-			.cs_change = 0,
+			.cs_change = 1,
 		}, {
 			.rx_buf = &st->d16[1],
 			.len = 2,
@@ -151,7 +151,7 @@ static int ad7606_spi_reg_write(struct ad7606_state *st,
 	struct spi_device *spi = to_spi_device(st->dev);
 
 	st->d16[0] = cpu_to_be16((st->bops->rd_wr_cmd(addr, 1) << 8) |
-				  (val & 0x1FF));
+				  (val & 0xFF));
 
 	return spi_write(spi, &st->d16[0], sizeof(st->d16[0]));
 }
diff --git a/drivers/iio/adc/ad7768-1.c b/drivers/iio/adc/ad7768-1.c
index 113703fb7245..7956948166ab 100644
--- a/drivers/iio/adc/ad7768-1.c
+++ b/drivers/iio/adc/ad7768-1.c
@@ -142,7 +142,7 @@ static const struct iio_chan_spec ad7768_channels[] = {
 		.channel = 0,
 		.scan_index = 0,
 		.scan_type = {
-			.sign = 'u',
+			.sign = 's',
 			.realbits = 24,
 			.storagebits = 32,
 			.shift = 8,
@@ -169,7 +169,7 @@ struct ad7768_state {
 	union {
 		struct {
 			__be32 chan;
-			s64 timestamp;
+			aligned_s64 timestamp;
 		} scan;
 		__be32 d32;
 		u8 d8[2];
@@ -203,6 +203,24 @@ static int ad7768_spi_reg_write(struct ad7768_state *st,
 	return spi_write(st->spi, st->data.d8, 2);
 }
 
+static int ad7768_send_sync_pulse(struct ad7768_state *st)
+{
+	/*
+	 * The datasheet specifies a minimum SYNC_IN pulse width of 1.5 × Tmclk,
+	 * where Tmclk is the MCLK period. The supported MCLK frequencies range
+	 * from 0.6 MHz to 17 MHz, which corresponds to a minimum SYNC_IN pulse
+	 * width of approximately 2.5 µs in the worst-case scenario (0.6 MHz).
+	 *
+	 * Add a delay to ensure the pulse width is always sufficient to
+	 * trigger synchronization.
+	 */
+	gpiod_set_value_cansleep(st->gpio_sync_in, 1);
+	fsleep(3);
+	gpiod_set_value_cansleep(st->gpio_sync_in, 0);
+
+	return 0;
+}
+
 static int ad7768_set_mode(struct ad7768_state *st,
 			   enum ad7768_conv_mode mode)
 {
@@ -288,10 +306,7 @@ static int ad7768_set_dig_fil(struct ad7768_state *st,
 		return ret;
 
 	/* A sync-in pulse is required every time the filter dec rate changes */
-	gpiod_set_value(st->gpio_sync_in, 1);
-	gpiod_set_value(st->gpio_sync_in, 0);
-
-	return 0;
+	return ad7768_send_sync_pulse(st);
 }
 
 static int ad7768_set_freq(struct ad7768_state *st,
@@ -370,12 +385,11 @@ static int ad7768_read_raw(struct iio_dev *indio_dev,
 			return ret;
 
 		ret = ad7768_scan_direct(indio_dev);
-		if (ret >= 0)
-			*val = ret;
 
 		iio_device_release_direct_mode(indio_dev);
 		if (ret < 0)
 			return ret;
+		*val = sign_extend32(ret, chan->scan_type.realbits - 1);
 
 		return IIO_VAL_INT;
 
@@ -574,6 +588,21 @@ static int ad7768_probe(struct spi_device *spi)
 		return -ENOMEM;
 
 	st = iio_priv(indio_dev);
+	/*
+	 * Datasheet recommends SDI line to be kept high when data is not being
+	 * clocked out of the controller and the spi clock is free running,
+	 * to prevent accidental reset.
+	 * Since many controllers do not support the SPI_MOSI_IDLE_HIGH flag
+	 * yet, only request the MOSI idle state to enable if the controller
+	 * supports it.
+	 */
+	if (spi->controller->mode_bits & SPI_MOSI_IDLE_HIGH) {
+		spi->mode |= SPI_MOSI_IDLE_HIGH;
+		ret = spi_setup(spi);
+		if (ret < 0)
+			return ret;
+	}
+
 	st->spi = spi;
 
 	st->vref = devm_regulator_get(&spi->dev, "vref");
diff --git a/drivers/iio/adc/ad7944.c b/drivers/iio/adc/ad7944.c
index 0f36138a7144..1e2cf512c2f5 100644
--- a/drivers/iio/adc/ad7944.c
+++ b/drivers/iio/adc/ad7944.c
@@ -98,6 +98,9 @@ struct ad7944_chip_info {
 	const struct iio_chan_spec channels[2];
 };
 
+/* get number of bytes for SPI xfer */
+#define AD7944_SPI_BYTES(scan_type) ((scan_type).realbits > 16 ? 4 : 2)
+
 /*
  * AD7944_DEFINE_CHIP_INFO - Define a chip info structure for a specific chip
  * @_name: The name of the chip
@@ -164,7 +167,7 @@ static int ad7944_3wire_cs_mode_init_msg(struct device *dev, struct ad7944_adc *
 
 	/* Then we can read the data during the acquisition phase */
 	xfers[2].rx_buf = &adc->sample.raw;
-	xfers[2].len = BITS_TO_BYTES(chan->scan_type.storagebits);
+	xfers[2].len = AD7944_SPI_BYTES(chan->scan_type);
 	xfers[2].bits_per_word = chan->scan_type.realbits;
 
 	spi_message_init_with_transfers(&adc->msg, xfers, 3);
@@ -193,7 +196,7 @@ static int ad7944_4wire_mode_init_msg(struct device *dev, struct ad7944_adc *adc
 	xfers[0].delay.unit = SPI_DELAY_UNIT_NSECS;
 
 	xfers[1].rx_buf = &adc->sample.raw;
-	xfers[1].len = BITS_TO_BYTES(chan->scan_type.storagebits);
+	xfers[1].len = AD7944_SPI_BYTES(chan->scan_type);
 	xfers[1].bits_per_word = chan->scan_type.realbits;
 
 	spi_message_init_with_transfers(&adc->msg, xfers, 2);
@@ -228,7 +231,7 @@ static int ad7944_chain_mode_init_msg(struct device *dev, struct ad7944_adc *adc
 	xfers[0].delay.unit = SPI_DELAY_UNIT_NSECS;
 
 	xfers[1].rx_buf = adc->chain_mode_buf;
-	xfers[1].len = BITS_TO_BYTES(chan->scan_type.storagebits) * n_chain_dev;
+	xfers[1].len = AD7944_SPI_BYTES(chan->scan_type) * n_chain_dev;
 	xfers[1].bits_per_word = chan->scan_type.realbits;
 
 	spi_message_init_with_transfers(&adc->msg, xfers, 2);
@@ -274,12 +277,12 @@ static int ad7944_single_conversion(struct ad7944_adc *adc,
 		return ret;
 
 	if (adc->spi_mode == AD7944_SPI_MODE_CHAIN) {
-		if (chan->scan_type.storagebits > 16)
+		if (chan->scan_type.realbits > 16)
 			*val = ((u32 *)adc->chain_mode_buf)[chan->scan_index];
 		else
 			*val = ((u16 *)adc->chain_mode_buf)[chan->scan_index];
 	} else {
-		if (chan->scan_type.storagebits > 16)
+		if (chan->scan_type.realbits > 16)
 			*val = adc->sample.raw.u32;
 		else
 			*val = adc->sample.raw.u16;
@@ -287,6 +290,8 @@ static int ad7944_single_conversion(struct ad7944_adc *adc,
 
 	if (chan->scan_type.sign == 's')
 		*val = sign_extend32(*val, chan->scan_type.realbits - 1);
+	else
+		*val &= GENMASK(chan->scan_type.realbits - 1, 0);
 
 	return IIO_VAL_INT;
 }
@@ -409,8 +414,7 @@ static int ad7944_chain_mode_alloc(struct device *dev,
 	/* 1 word for each voltage channel + aligned u64 for timestamp */
 
 	chain_mode_buf_size = ALIGN(n_chain_dev *
-		BITS_TO_BYTES(chan[0].scan_type.storagebits), sizeof(u64))
-		+ sizeof(u64);
+		AD7944_SPI_BYTES(chan[0].scan_type), sizeof(u64)) + sizeof(u64);
 	buf = devm_kzalloc(dev, chain_mode_buf_size, GFP_KERNEL);
 	if (!buf)
 		return -ENOMEM;
diff --git a/drivers/iio/adc/ad7949.c b/drivers/iio/adc/ad7949.c
index edd0c3a35ab7..202561cad401 100644
--- a/drivers/iio/adc/ad7949.c
+++ b/drivers/iio/adc/ad7949.c
@@ -308,7 +308,6 @@ static void ad7949_disable_reg(void *reg)
 
 static int ad7949_spi_probe(struct spi_device *spi)
 {
-	u32 spi_ctrl_mask = spi->controller->bits_per_word_mask;
 	struct device *dev = &spi->dev;
 	const struct ad7949_adc_spec *spec;
 	struct ad7949_adc_chip *ad7949_adc;
@@ -337,11 +336,11 @@ static int ad7949_spi_probe(struct spi_device *spi)
 	ad7949_adc->resolution = spec->resolution;
 
 	/* Set SPI bits per word */
-	if (spi_ctrl_mask & SPI_BPW_MASK(ad7949_adc->resolution)) {
+	if (spi_is_bpw_supported(spi, ad7949_adc->resolution)) {
 		spi->bits_per_word = ad7949_adc->resolution;
-	} else if (spi_ctrl_mask == SPI_BPW_MASK(16)) {
+	} else if (spi_is_bpw_supported(spi, 16)) {
 		spi->bits_per_word = 16;
-	} else if (spi_ctrl_mask == SPI_BPW_MASK(8)) {
+	} else if (spi_is_bpw_supported(spi, 8)) {
 		spi->bits_per_word = 8;
 	} else {
 		dev_err(dev, "unable to find common BPW with spi controller\n");
diff --git a/drivers/iio/adc/ad_sigma_delta.c b/drivers/iio/adc/ad_sigma_delta.c
index ea4aabd3960a..39196a2862cf 100644
--- a/drivers/iio/adc/ad_sigma_delta.c
+++ b/drivers/iio/adc/ad_sigma_delta.c
@@ -379,7 +379,7 @@ static int ad_sd_buffer_postenable(struct iio_dev *indio_dev)
 			return ret;
 	}
 
-	samples_buf_size = ALIGN(slot * indio_dev->channels[0].scan_type.storagebits, 8);
+	samples_buf_size = ALIGN(slot * indio_dev->channels[0].scan_type.storagebits / 8, 8);
 	samples_buf_size += sizeof(int64_t);
 	samples_buf = devm_krealloc(&sigma_delta->spi->dev, sigma_delta->samples_buf,
 				    samples_buf_size, GFP_KERNEL);
@@ -477,6 +477,10 @@ static irqreturn_t ad_sd_trigger_handler(int irq, void *p)
 		 * byte set to zero. */
 		ad_sd_read_reg_raw(sigma_delta, data_reg, transfer_size, &data[1]);
 		break;
+
+	default:
+		dev_err_ratelimited(&indio_dev->dev, "Unsupported reg_size: %u\n", reg_size);
+		goto irq_handled;
 	}
 
 	/*
diff --git a/drivers/iio/adc/at91-sama5d2_adc.c b/drivers/iio/adc/at91-sama5d2_adc.c
index d7fd21e7c6e2..3618e769b106 100644
--- a/drivers/iio/adc/at91-sama5d2_adc.c
+++ b/drivers/iio/adc/at91-sama5d2_adc.c
@@ -329,7 +329,7 @@ static const struct at91_adc_reg_layout sama7g5_layout = {
 #define AT91_HWFIFO_MAX_SIZE_STR	"128"
 #define AT91_HWFIFO_MAX_SIZE		128
 
-#define AT91_SAMA5D2_CHAN_SINGLE(index, num, addr)			\
+#define AT91_SAMA_CHAN_SINGLE(index, num, addr, rbits)			\
 	{								\
 		.type = IIO_VOLTAGE,					\
 		.channel = num,						\
@@ -337,7 +337,7 @@ static const struct at91_adc_reg_layout sama7g5_layout = {
 		.scan_index = index,					\
 		.scan_type = {						\
 			.sign = 'u',					\
-			.realbits = 14,					\
+			.realbits = rbits,				\
 			.storagebits = 16,				\
 		},							\
 		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),		\
@@ -350,7 +350,13 @@ static const struct at91_adc_reg_layout sama7g5_layout = {
 		.indexed = 1,						\
 	}
 
-#define AT91_SAMA5D2_CHAN_DIFF(index, num, num2, addr)			\
+#define AT91_SAMA5D2_CHAN_SINGLE(index, num, addr)			\
+	AT91_SAMA_CHAN_SINGLE(index, num, addr, 14)
+
+#define AT91_SAMA7G5_CHAN_SINGLE(index, num, addr)			\
+	AT91_SAMA_CHAN_SINGLE(index, num, addr, 16)
+
+#define AT91_SAMA_CHAN_DIFF(index, num, num2, addr, rbits)		\
 	{								\
 		.type = IIO_VOLTAGE,					\
 		.differential = 1,					\
@@ -360,7 +366,7 @@ static const struct at91_adc_reg_layout sama7g5_layout = {
 		.scan_index = index,					\
 		.scan_type = {						\
 			.sign = 's',					\
-			.realbits = 14,					\
+			.realbits = rbits,				\
 			.storagebits = 16,				\
 		},							\
 		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),		\
@@ -373,6 +379,12 @@ static const struct at91_adc_reg_layout sama7g5_layout = {
 		.indexed = 1,						\
 	}
 
+#define AT91_SAMA5D2_CHAN_DIFF(index, num, num2, addr)			\
+	AT91_SAMA_CHAN_DIFF(index, num, num2, addr, 14)
+
+#define AT91_SAMA7G5_CHAN_DIFF(index, num, num2, addr)			\
+	AT91_SAMA_CHAN_DIFF(index, num, num2, addr, 16)
+
 #define AT91_SAMA5D2_CHAN_TOUCH(num, name, mod)				\
 	{								\
 		.type = IIO_POSITIONRELATIVE,				\
@@ -666,30 +678,30 @@ static const struct iio_chan_spec at91_sama5d2_adc_channels[] = {
 };
 
 static const struct iio_chan_spec at91_sama7g5_adc_channels[] = {
-	AT91_SAMA5D2_CHAN_SINGLE(0, 0, 0x60),
-	AT91_SAMA5D2_CHAN_SINGLE(1, 1, 0x64),
-	AT91_SAMA5D2_CHAN_SINGLE(2, 2, 0x68),
-	AT91_SAMA5D2_CHAN_SINGLE(3, 3, 0x6c),
-	AT91_SAMA5D2_CHAN_SINGLE(4, 4, 0x70),
-	AT91_SAMA5D2_CHAN_SINGLE(5, 5, 0x74),
-	AT91_SAMA5D2_CHAN_SINGLE(6, 6, 0x78),
-	AT91_SAMA5D2_CHAN_SINGLE(7, 7, 0x7c),
-	AT91_SAMA5D2_CHAN_SINGLE(8, 8, 0x80),
-	AT91_SAMA5D2_CHAN_SINGLE(9, 9, 0x84),
-	AT91_SAMA5D2_CHAN_SINGLE(10, 10, 0x88),
-	AT91_SAMA5D2_CHAN_SINGLE(11, 11, 0x8c),
-	AT91_SAMA5D2_CHAN_SINGLE(12, 12, 0x90),
-	AT91_SAMA5D2_CHAN_SINGLE(13, 13, 0x94),
-	AT91_SAMA5D2_CHAN_SINGLE(14, 14, 0x98),
-	AT91_SAMA5D2_CHAN_SINGLE(15, 15, 0x9c),
-	AT91_SAMA5D2_CHAN_DIFF(16, 0, 1, 0x60),
-	AT91_SAMA5D2_CHAN_DIFF(17, 2, 3, 0x68),
-	AT91_SAMA5D2_CHAN_DIFF(18, 4, 5, 0x70),
-	AT91_SAMA5D2_CHAN_DIFF(19, 6, 7, 0x78),
-	AT91_SAMA5D2_CHAN_DIFF(20, 8, 9, 0x80),
-	AT91_SAMA5D2_CHAN_DIFF(21, 10, 11, 0x88),
-	AT91_SAMA5D2_CHAN_DIFF(22, 12, 13, 0x90),
-	AT91_SAMA5D2_CHAN_DIFF(23, 14, 15, 0x98),
+	AT91_SAMA7G5_CHAN_SINGLE(0, 0, 0x60),
+	AT91_SAMA7G5_CHAN_SINGLE(1, 1, 0x64),
+	AT91_SAMA7G5_CHAN_SINGLE(2, 2, 0x68),
+	AT91_SAMA7G5_CHAN_SINGLE(3, 3, 0x6c),
+	AT91_SAMA7G5_CHAN_SINGLE(4, 4, 0x70),
+	AT91_SAMA7G5_CHAN_SINGLE(5, 5, 0x74),
+	AT91_SAMA7G5_CHAN_SINGLE(6, 6, 0x78),
+	AT91_SAMA7G5_CHAN_SINGLE(7, 7, 0x7c),
+	AT91_SAMA7G5_CHAN_SINGLE(8, 8, 0x80),
+	AT91_SAMA7G5_CHAN_SINGLE(9, 9, 0x84),
+	AT91_SAMA7G5_CHAN_SINGLE(10, 10, 0x88),
+	AT91_SAMA7G5_CHAN_SINGLE(11, 11, 0x8c),
+	AT91_SAMA7G5_CHAN_SINGLE(12, 12, 0x90),
+	AT91_SAMA7G5_CHAN_SINGLE(13, 13, 0x94),
+	AT91_SAMA7G5_CHAN_SINGLE(14, 14, 0x98),
+	AT91_SAMA7G5_CHAN_SINGLE(15, 15, 0x9c),
+	AT91_SAMA7G5_CHAN_DIFF(16, 0, 1, 0x60),
+	AT91_SAMA7G5_CHAN_DIFF(17, 2, 3, 0x68),
+	AT91_SAMA7G5_CHAN_DIFF(18, 4, 5, 0x70),
+	AT91_SAMA7G5_CHAN_DIFF(19, 6, 7, 0x78),
+	AT91_SAMA7G5_CHAN_DIFF(20, 8, 9, 0x80),
+	AT91_SAMA7G5_CHAN_DIFF(21, 10, 11, 0x88),
+	AT91_SAMA7G5_CHAN_DIFF(22, 12, 13, 0x90),
+	AT91_SAMA7G5_CHAN_DIFF(23, 14, 15, 0x98),
 	IIO_CHAN_SOFT_TIMESTAMP(24),
 	AT91_SAMA5D2_CHAN_TEMP(AT91_SAMA7G5_ADC_TEMP_CHANNEL, "temp", 0xdc),
 };
diff --git a/drivers/iio/adc/axp20x_adc.c b/drivers/iio/adc/axp20x_adc.c
index 6c1a5d1b0a83..0226dfbcf4ae 100644
--- a/drivers/iio/adc/axp20x_adc.c
+++ b/drivers/iio/adc/axp20x_adc.c
@@ -217,6 +217,7 @@ static struct iio_map axp717_maps[] = {
 		.consumer_channel = "batt_chrg_i",
 		.adc_channel_label = "batt_chrg_i",
 	},
+	{ }
 };
 
 /*
diff --git a/drivers/iio/adc/dln2-adc.c b/drivers/iio/adc/dln2-adc.c
index de7252a10047..84c23d3def59 100644
--- a/drivers/iio/adc/dln2-adc.c
+++ b/drivers/iio/adc/dln2-adc.c
@@ -481,7 +481,7 @@ static irqreturn_t dln2_adc_trigger_h(int irq, void *p)
 	struct iio_dev *indio_dev = pf->indio_dev;
 	struct {
 		__le16 values[DLN2_ADC_MAX_CHANNELS];
-		int64_t timestamp_space;
+		aligned_s64 timestamp_space;
 	} data;
 	struct dln2_adc_get_all_vals dev_data;
 	struct dln2_adc *dln2 = iio_priv(indio_dev);
diff --git a/drivers/iio/adc/max1363.c b/drivers/iio/adc/max1363.c
index d0c6e94f7204..c9d531f233eb 100644
--- a/drivers/iio/adc/max1363.c
+++ b/drivers/iio/adc/max1363.c
@@ -504,10 +504,10 @@ static const struct iio_event_spec max1363_events[] = {
 	MAX1363_CHAN_U(1, _s1, 1, bits, ev_spec, num_ev_spec),		\
 	MAX1363_CHAN_U(2, _s2, 2, bits, ev_spec, num_ev_spec),		\
 	MAX1363_CHAN_U(3, _s3, 3, bits, ev_spec, num_ev_spec),		\
-	MAX1363_CHAN_B(0, 1, d0m1, 4, bits, ev_spec, num_ev_spec),	\
-	MAX1363_CHAN_B(2, 3, d2m3, 5, bits, ev_spec, num_ev_spec),	\
-	MAX1363_CHAN_B(1, 0, d1m0, 6, bits, ev_spec, num_ev_spec),	\
-	MAX1363_CHAN_B(3, 2, d3m2, 7, bits, ev_spec, num_ev_spec),	\
+	MAX1363_CHAN_B(0, 1, d0m1, 12, bits, ev_spec, num_ev_spec),	\
+	MAX1363_CHAN_B(2, 3, d2m3, 13, bits, ev_spec, num_ev_spec),	\
+	MAX1363_CHAN_B(1, 0, d1m0, 18, bits, ev_spec, num_ev_spec),	\
+	MAX1363_CHAN_B(3, 2, d3m2, 19, bits, ev_spec, num_ev_spec),	\
 	IIO_CHAN_SOFT_TIMESTAMP(8)					\
 	}
 
@@ -525,23 +525,23 @@ static const struct iio_chan_spec max1363_channels[] =
 /* Applies to max1236, max1237 */
 static const enum max1363_modes max1236_mode_list[] = {
 	_s0, _s1, _s2, _s3,
-	s0to1, s0to2, s0to3,
+	s0to1, s0to2, s2to3, s0to3,
 	d0m1, d2m3, d1m0, d3m2,
 	d0m1to2m3, d1m0to3m2,
-	s2to3,
 };
 
 /* Applies to max1238, max1239 */
 static const enum max1363_modes max1238_mode_list[] = {
 	_s0, _s1, _s2, _s3, _s4, _s5, _s6, _s7, _s8, _s9, _s10, _s11,
 	s0to1, s0to2, s0to3, s0to4, s0to5, s0to6,
+	s6to7, s6to8, s6to9, s6to10, s6to11,
 	s0to7, s0to8, s0to9, s0to10, s0to11,
 	d0m1, d2m3, d4m5, d6m7, d8m9, d10m11,
 	d1m0, d3m2, d5m4, d7m6, d9m8, d11m10,
-	d0m1to2m3, d0m1to4m5, d0m1to6m7, d0m1to8m9, d0m1to10m11,
-	d1m0to3m2, d1m0to5m4, d1m0to7m6, d1m0to9m8, d1m0to11m10,
-	s6to7, s6to8, s6to9, s6to10, s6to11,
-	d6m7to8m9, d6m7to10m11, d7m6to9m8, d7m6to11m10,
+	d0m1to2m3, d0m1to4m5, d0m1to6m7, d6m7to8m9,
+	d0m1to8m9, d6m7to10m11, d0m1to10m11, d1m0to3m2,
+	d1m0to5m4, d1m0to7m6, d7m6to9m8, d1m0to9m8,
+	d7m6to11m10, d1m0to11m10,
 };
 
 #define MAX1363_12X_CHANS(bits) {				\
@@ -577,16 +577,15 @@ static const struct iio_chan_spec max1238_channels[] = MAX1363_12X_CHANS(12);
 
 static const enum max1363_modes max11607_mode_list[] = {
 	_s0, _s1, _s2, _s3,
-	s0to1, s0to2, s0to3,
-	s2to3,
+	s0to1, s0to2, s2to3,
+	s0to3,
 	d0m1, d2m3, d1m0, d3m2,
 	d0m1to2m3, d1m0to3m2,
 };
 
 static const enum max1363_modes max11608_mode_list[] = {
 	_s0, _s1, _s2, _s3, _s4, _s5, _s6, _s7,
-	s0to1, s0to2, s0to3, s0to4, s0to5, s0to6, s0to7,
-	s6to7,
+	s0to1, s0to2, s0to3, s0to4, s0to5, s0to6, s6to7, s0to7,
 	d0m1, d2m3, d4m5, d6m7,
 	d1m0, d3m2, d5m4, d7m6,
 	d0m1to2m3, d0m1to4m5, d0m1to6m7,
@@ -602,14 +601,14 @@ static const enum max1363_modes max11608_mode_list[] = {
 	MAX1363_CHAN_U(5, _s5, 5, bits, NULL, 0),	\
 	MAX1363_CHAN_U(6, _s6, 6, bits, NULL, 0),	\
 	MAX1363_CHAN_U(7, _s7, 7, bits, NULL, 0),	\
-	MAX1363_CHAN_B(0, 1, d0m1, 8, bits, NULL, 0),	\
-	MAX1363_CHAN_B(2, 3, d2m3, 9, bits, NULL, 0),	\
-	MAX1363_CHAN_B(4, 5, d4m5, 10, bits, NULL, 0),	\
-	MAX1363_CHAN_B(6, 7, d6m7, 11, bits, NULL, 0),	\
-	MAX1363_CHAN_B(1, 0, d1m0, 12, bits, NULL, 0),	\
-	MAX1363_CHAN_B(3, 2, d3m2, 13, bits, NULL, 0),	\
-	MAX1363_CHAN_B(5, 4, d5m4, 14, bits, NULL, 0),	\
-	MAX1363_CHAN_B(7, 6, d7m6, 15, bits, NULL, 0),	\
+	MAX1363_CHAN_B(0, 1, d0m1, 12, bits, NULL, 0),	\
+	MAX1363_CHAN_B(2, 3, d2m3, 13, bits, NULL, 0),	\
+	MAX1363_CHAN_B(4, 5, d4m5, 14, bits, NULL, 0),	\
+	MAX1363_CHAN_B(6, 7, d6m7, 15, bits, NULL, 0),	\
+	MAX1363_CHAN_B(1, 0, d1m0, 18, bits, NULL, 0),	\
+	MAX1363_CHAN_B(3, 2, d3m2, 19, bits, NULL, 0),	\
+	MAX1363_CHAN_B(5, 4, d5m4, 20, bits, NULL, 0),	\
+	MAX1363_CHAN_B(7, 6, d7m6, 21, bits, NULL, 0),	\
 	IIO_CHAN_SOFT_TIMESTAMP(16)			\
 }
 static const struct iio_chan_spec max11602_channels[] = MAX1363_8X_CHANS(8);
diff --git a/drivers/iio/adc/mcp3911.c b/drivers/iio/adc/mcp3911.c
index b097f04172c8..4bd6b5aac4fe 100644
--- a/drivers/iio/adc/mcp3911.c
+++ b/drivers/iio/adc/mcp3911.c
@@ -6,7 +6,7 @@
  * Copyright (C) 2018 Kent Gustavsson <kent@minoris.se>
  */
 #include <linux/bitfield.h>
-#include <linux/bits.h>
+#include <linux/bitops.h>
 #include <linux/cleanup.h>
 #include <linux/clk.h>
 #include <linux/delay.h>
@@ -79,6 +79,8 @@
 #define MCP3910_CONFIG1_CLKEXT		BIT(6)
 #define MCP3910_CONFIG1_VREFEXT		BIT(7)
 
+#define MCP3910_CHANNEL(ch)		(MCP3911_REG_CHANNEL0 + (ch))
+
 #define MCP3910_REG_OFFCAL_CH0		0x0f
 #define MCP3910_OFFCAL(ch)		(MCP3910_REG_OFFCAL_CH0 + (ch) * 6)
 
@@ -110,6 +112,7 @@ struct mcp3911_chip_info {
 	int (*get_offset)(struct mcp3911 *adc, int channel, int *val);
 	int (*set_offset)(struct mcp3911 *adc, int channel, int val);
 	int (*set_scale)(struct mcp3911 *adc, int channel, u32 val);
+	int (*get_raw)(struct mcp3911 *adc, int channel, int *val);
 };
 
 struct mcp3911 {
@@ -170,6 +173,18 @@ static int mcp3911_update(struct mcp3911 *adc, u8 reg, u32 mask, u32 val, u8 len
 	return mcp3911_write(adc, reg, val, len);
 }
 
+static int mcp3911_read_s24(struct mcp3911 *const adc, u8 const reg, s32 *const val)
+{
+	u32 uval;
+	int const ret = mcp3911_read(adc, reg, &uval, 3);
+
+	if (ret)
+		return ret;
+
+	*val = sign_extend32(uval, 23);
+	return ret;
+}
+
 static int mcp3910_enable_offset(struct mcp3911 *adc, bool enable)
 {
 	unsigned int mask = MCP3910_CONFIG0_EN_OFFCAL;
@@ -194,6 +209,11 @@ static int mcp3910_set_offset(struct mcp3911 *adc, int channel, int val)
 	return adc->chip->enable_offset(adc, 1);
 }
 
+static int mcp3910_get_raw(struct mcp3911 *adc, int channel, s32 *val)
+{
+	return mcp3911_read_s24(adc, MCP3910_CHANNEL(channel), val);
+}
+
 static int mcp3911_enable_offset(struct mcp3911 *adc, bool enable)
 {
 	unsigned int mask = MCP3911_STATUSCOM_EN_OFFCAL;
@@ -218,6 +238,11 @@ static int mcp3911_set_offset(struct mcp3911 *adc, int channel, int val)
 	return adc->chip->enable_offset(adc, 1);
 }
 
+static int mcp3911_get_raw(struct mcp3911 *adc, int channel, s32 *val)
+{
+	return mcp3911_read_s24(adc, MCP3911_CHANNEL(channel), val);
+}
+
 static int mcp3910_get_osr(struct mcp3911 *adc, u32 *val)
 {
 	int ret;
@@ -321,12 +346,9 @@ static int mcp3911_read_raw(struct iio_dev *indio_dev,
 	guard(mutex)(&adc->lock);
 	switch (mask) {
 	case IIO_CHAN_INFO_RAW:
-		ret = mcp3911_read(adc,
-				   MCP3911_CHANNEL(channel->channel), val, 3);
+		ret = adc->chip->get_raw(adc, channel->channel, val);
 		if (ret)
 			return ret;
-
-		*val = sign_extend32(*val, 23);
 		return IIO_VAL_INT;
 	case IIO_CHAN_INFO_OFFSET:
 		ret = adc->chip->get_offset(adc, channel->channel, val);
@@ -799,6 +821,7 @@ static const struct mcp3911_chip_info mcp3911_chip_info[] = {
 		.get_offset = mcp3910_get_offset,
 		.set_offset = mcp3910_set_offset,
 		.set_scale = mcp3910_set_scale,
+		.get_raw = mcp3910_get_raw,
 	},
 	[MCP3911] = {
 		.channels = mcp3911_channels,
@@ -810,6 +833,7 @@ static const struct mcp3911_chip_info mcp3911_chip_info[] = {
 		.get_offset = mcp3911_get_offset,
 		.set_offset = mcp3911_set_offset,
 		.set_scale = mcp3911_set_scale,
+		.get_raw = mcp3911_get_raw,
 	},
 	[MCP3912] = {
 		.channels = mcp3912_channels,
@@ -821,6 +845,7 @@ static const struct mcp3911_chip_info mcp3911_chip_info[] = {
 		.get_offset = mcp3910_get_offset,
 		.set_offset = mcp3910_set_offset,
 		.set_scale = mcp3910_set_scale,
+		.get_raw = mcp3910_get_raw,
 	},
 	[MCP3913] = {
 		.channels = mcp3913_channels,
@@ -832,6 +857,7 @@ static const struct mcp3911_chip_info mcp3911_chip_info[] = {
 		.get_offset = mcp3910_get_offset,
 		.set_offset = mcp3910_set_offset,
 		.set_scale = mcp3910_set_scale,
+		.get_raw = mcp3910_get_raw,
 	},
 	[MCP3914] = {
 		.channels = mcp3914_channels,
@@ -843,6 +869,7 @@ static const struct mcp3911_chip_info mcp3911_chip_info[] = {
 		.get_offset = mcp3910_get_offset,
 		.set_offset = mcp3910_set_offset,
 		.set_scale = mcp3910_set_scale,
+		.get_raw = mcp3910_get_raw,
 	},
 	[MCP3918] = {
 		.channels = mcp3918_channels,
@@ -854,6 +881,7 @@ static const struct mcp3911_chip_info mcp3911_chip_info[] = {
 		.get_offset = mcp3910_get_offset,
 		.set_offset = mcp3910_set_offset,
 		.set_scale = mcp3910_set_scale,
+		.get_raw = mcp3910_get_raw,
 	},
 	[MCP3919] = {
 		.channels = mcp3919_channels,
@@ -865,6 +893,7 @@ static const struct mcp3911_chip_info mcp3911_chip_info[] = {
 		.get_offset = mcp3910_get_offset,
 		.set_offset = mcp3910_set_offset,
 		.set_scale = mcp3910_set_scale,
+		.get_raw = mcp3910_get_raw,
 	},
 };
 static const struct of_device_id mcp3911_dt_ids[] = {
diff --git a/drivers/iio/adc/pac1934.c b/drivers/iio/adc/pac1934.c
index 7ef249d83286..c3f9fa307b84 100644
--- a/drivers/iio/adc/pac1934.c
+++ b/drivers/iio/adc/pac1934.c
@@ -1081,7 +1081,7 @@ static int pac1934_chip_identify(struct pac1934_chip_info *info)
 
 /*
  * documentation related to the ACPI device definition
- * https://ww1.microchip.com/downloads/aemDocuments/documents/OTH/ApplicationNotes/ApplicationNotes/PAC1934-Integration-Notes-for-Microsoft-Windows-10-and-Windows-11-Driver-Support-DS00002534.pdf
+ * https://ww1.microchip.com/downloads/aemDocuments/documents/OTH/ApplicationNotes/ApplicationNotes/PAC193X-Integration-Notes-for-Microsoft-Windows-10-and-Windows-11-Driver-Support-DS00002534.pdf
  */
 static int pac1934_acpi_parse_channel_config(struct i2c_client *client,
 					     struct pac1934_chip_info *info)
diff --git a/drivers/iio/adc/rockchip_saradc.c b/drivers/iio/adc/rockchip_saradc.c
index dfd47a6e1f4a..e4dcd9e782af 100644
--- a/drivers/iio/adc/rockchip_saradc.c
+++ b/drivers/iio/adc/rockchip_saradc.c
@@ -480,15 +480,6 @@ static int rockchip_saradc_probe(struct platform_device *pdev)
 	if (info->reset)
 		rockchip_saradc_reset_controller(info->reset);
 
-	/*
-	 * Use a default value for the converter clock.
-	 * This may become user-configurable in the future.
-	 */
-	ret = clk_set_rate(info->clk, info->data->clk_rate);
-	if (ret < 0)
-		return dev_err_probe(&pdev->dev, ret,
-				     "failed to set adc clk rate\n");
-
 	ret = regulator_enable(info->vref);
 	if (ret < 0)
 		return dev_err_probe(&pdev->dev, ret,
@@ -515,6 +506,14 @@ static int rockchip_saradc_probe(struct platform_device *pdev)
 	if (IS_ERR(info->clk))
 		return dev_err_probe(&pdev->dev, PTR_ERR(info->clk),
 				     "failed to get adc clock\n");
+	/*
+	 * Use a default value for the converter clock.
+	 * This may become user-configurable in the future.
+	 */
+	ret = clk_set_rate(info->clk, info->data->clk_rate);
+	if (ret < 0)
+		return dev_err_probe(&pdev->dev, ret,
+				     "failed to set adc clk rate\n");
 
 	platform_set_drvdata(pdev, indio_dev);
 
diff --git a/drivers/iio/adc/stm32-adc-core.c b/drivers/iio/adc/stm32-adc-core.c
index 616dd729666a..97ea15cba9f7 100644
--- a/drivers/iio/adc/stm32-adc-core.c
+++ b/drivers/iio/adc/stm32-adc-core.c
@@ -429,10 +429,9 @@ static int stm32_adc_irq_probe(struct platform_device *pdev,
 		return -ENOMEM;
 	}
 
-	for (i = 0; i < priv->cfg->num_irqs; i++) {
-		irq_set_chained_handler(priv->irq[i], stm32_adc_irq_handler);
-		irq_set_handler_data(priv->irq[i], priv);
-	}
+	for (i = 0; i < priv->cfg->num_irqs; i++)
+		irq_set_chained_handler_and_data(priv->irq[i],
+						 stm32_adc_irq_handler, priv);
 
 	return 0;
 }
diff --git a/drivers/iio/chemical/pms7003.c b/drivers/iio/chemical/pms7003.c
index d0bd94912e0a..e05ce1f12065 100644
--- a/drivers/iio/chemical/pms7003.c
+++ b/drivers/iio/chemical/pms7003.c
@@ -5,7 +5,6 @@
  * Copyright (c) Tomasz Duszynski <tduszyns@gmail.com>
  */
 
-#include <linux/unaligned.h>
 #include <linux/completion.h>
 #include <linux/device.h>
 #include <linux/errno.h>
@@ -19,6 +18,8 @@
 #include <linux/module.h>
 #include <linux/mutex.h>
 #include <linux/serdev.h>
+#include <linux/types.h>
+#include <linux/unaligned.h>
 
 #define PMS7003_DRIVER_NAME "pms7003"
 
@@ -76,7 +77,7 @@ struct pms7003_state {
 	/* Used to construct scan to push to the IIO buffer */
 	struct {
 		u16 data[3]; /* PM1, PM2P5, PM10 */
-		s64 ts;
+		aligned_s64 ts;
 	} scan;
 };
 
diff --git a/drivers/iio/chemical/sps30.c b/drivers/iio/chemical/sps30.c
index 814ce0aad1cc..4085a36cd1db 100644
--- a/drivers/iio/chemical/sps30.c
+++ b/drivers/iio/chemical/sps30.c
@@ -108,7 +108,7 @@ static irqreturn_t sps30_trigger_handler(int irq, void *p)
 	int ret;
 	struct {
 		s32 data[4]; /* PM1, PM2P5, PM4, PM10 */
-		s64 ts;
+		aligned_s64 ts;
 	} scan;
 
 	mutex_lock(&state->lock);
diff --git a/drivers/iio/common/st_sensors/st_sensors_core.c b/drivers/iio/common/st_sensors/st_sensors_core.c
index 1b4287991d00..48a194b8e060 100644
--- a/drivers/iio/common/st_sensors/st_sensors_core.c
+++ b/drivers/iio/common/st_sensors/st_sensors_core.c
@@ -154,7 +154,7 @@ static int st_sensors_set_fullscale(struct iio_dev *indio_dev, unsigned int fs)
 	return err;
 
 st_accel_set_fullscale_error:
-	dev_err(&indio_dev->dev, "failed to set new fullscale.\n");
+	dev_err(indio_dev->dev.parent, "failed to set new fullscale.\n");
 	return err;
 }
 
@@ -231,8 +231,7 @@ int st_sensors_power_enable(struct iio_dev *indio_dev)
 					     ARRAY_SIZE(regulator_names),
 					     regulator_names);
 	if (err)
-		return dev_err_probe(&indio_dev->dev, err,
-				     "unable to enable supplies\n");
+		return dev_err_probe(parent, err, "unable to enable supplies\n");
 
 	return 0;
 }
@@ -241,13 +240,14 @@ EXPORT_SYMBOL_NS(st_sensors_power_enable, IIO_ST_SENSORS);
 static int st_sensors_set_drdy_int_pin(struct iio_dev *indio_dev,
 					struct st_sensors_platform_data *pdata)
 {
+	struct device *parent = indio_dev->dev.parent;
 	struct st_sensor_data *sdata = iio_priv(indio_dev);
 
 	/* Sensor does not support interrupts */
 	if (!sdata->sensor_settings->drdy_irq.int1.addr &&
 	    !sdata->sensor_settings->drdy_irq.int2.addr) {
 		if (pdata->drdy_int_pin)
-			dev_info(&indio_dev->dev,
+			dev_info(parent,
 				 "DRDY on pin INT%d specified, but sensor does not support interrupts\n",
 				 pdata->drdy_int_pin);
 		return 0;
@@ -256,29 +256,27 @@ static int st_sensors_set_drdy_int_pin(struct iio_dev *indio_dev,
 	switch (pdata->drdy_int_pin) {
 	case 1:
 		if (!sdata->sensor_settings->drdy_irq.int1.mask) {
-			dev_err(&indio_dev->dev,
-					"DRDY on INT1 not available.\n");
+			dev_err(parent, "DRDY on INT1 not available.\n");
 			return -EINVAL;
 		}
 		sdata->drdy_int_pin = 1;
 		break;
 	case 2:
 		if (!sdata->sensor_settings->drdy_irq.int2.mask) {
-			dev_err(&indio_dev->dev,
-					"DRDY on INT2 not available.\n");
+			dev_err(parent, "DRDY on INT2 not available.\n");
 			return -EINVAL;
 		}
 		sdata->drdy_int_pin = 2;
 		break;
 	default:
-		dev_err(&indio_dev->dev, "DRDY on pdata not valid.\n");
+		dev_err(parent, "DRDY on pdata not valid.\n");
 		return -EINVAL;
 	}
 
 	if (pdata->open_drain) {
 		if (!sdata->sensor_settings->drdy_irq.int1.addr_od &&
 		    !sdata->sensor_settings->drdy_irq.int2.addr_od)
-			dev_err(&indio_dev->dev,
+			dev_err(parent,
 				"open drain requested but unsupported.\n");
 		else
 			sdata->int_pin_open_drain = true;
@@ -336,6 +334,7 @@ EXPORT_SYMBOL_NS(st_sensors_dev_name_probe, IIO_ST_SENSORS);
 int st_sensors_init_sensor(struct iio_dev *indio_dev,
 					struct st_sensors_platform_data *pdata)
 {
+	struct device *parent = indio_dev->dev.parent;
 	struct st_sensor_data *sdata = iio_priv(indio_dev);
 	struct st_sensors_platform_data *of_pdata;
 	int err = 0;
@@ -343,7 +342,7 @@ int st_sensors_init_sensor(struct iio_dev *indio_dev,
 	mutex_init(&sdata->odr_lock);
 
 	/* If OF/DT pdata exists, it will take precedence of anything else */
-	of_pdata = st_sensors_dev_probe(indio_dev->dev.parent, pdata);
+	of_pdata = st_sensors_dev_probe(parent, pdata);
 	if (IS_ERR(of_pdata))
 		return PTR_ERR(of_pdata);
 	if (of_pdata)
@@ -370,7 +369,7 @@ int st_sensors_init_sensor(struct iio_dev *indio_dev,
 		if (err < 0)
 			return err;
 	} else
-		dev_info(&indio_dev->dev, "Full-scale not possible\n");
+		dev_info(parent, "Full-scale not possible\n");
 
 	err = st_sensors_set_odr(indio_dev, sdata->odr);
 	if (err < 0)
@@ -405,7 +404,7 @@ int st_sensors_init_sensor(struct iio_dev *indio_dev,
 			mask = sdata->sensor_settings->drdy_irq.int2.mask_od;
 		}
 
-		dev_info(&indio_dev->dev,
+		dev_info(parent,
 			 "set interrupt line to open drain mode on pin %d\n",
 			 sdata->drdy_int_pin);
 		err = st_sensors_write_data_with_mask(indio_dev, addr,
@@ -594,21 +593,20 @@ EXPORT_SYMBOL_NS(st_sensors_get_settings_index, IIO_ST_SENSORS);
 int st_sensors_verify_id(struct iio_dev *indio_dev)
 {
 	struct st_sensor_data *sdata = iio_priv(indio_dev);
+	struct device *parent = indio_dev->dev.parent;
 	int wai, err;
 
 	if (sdata->sensor_settings->wai_addr) {
 		err = regmap_read(sdata->regmap,
 				  sdata->sensor_settings->wai_addr, &wai);
 		if (err < 0) {
-			dev_err(&indio_dev->dev,
-				"failed to read Who-Am-I register.\n");
-			return err;
+			return dev_err_probe(parent, err,
+					     "failed to read Who-Am-I register.\n");
 		}
 
 		if (sdata->sensor_settings->wai != wai) {
-			dev_warn(&indio_dev->dev,
-				"%s: WhoAmI mismatch (0x%x).\n",
-				indio_dev->name, wai);
+			dev_warn(parent, "%s: WhoAmI mismatch (0x%x).\n",
+				 indio_dev->name, wai);
 		}
 	}
 
diff --git a/drivers/iio/common/st_sensors/st_sensors_trigger.c b/drivers/iio/common/st_sensors/st_sensors_trigger.c
index a0df9250a69f..b900acd471bd 100644
--- a/drivers/iio/common/st_sensors/st_sensors_trigger.c
+++ b/drivers/iio/common/st_sensors/st_sensors_trigger.c
@@ -127,7 +127,7 @@ int st_sensors_allocate_trigger(struct iio_dev *indio_dev,
 	sdata->trig = devm_iio_trigger_alloc(parent, "%s-trigger",
 					     indio_dev->name);
 	if (sdata->trig == NULL) {
-		dev_err(&indio_dev->dev, "failed to allocate iio trigger.\n");
+		dev_err(parent, "failed to allocate iio trigger.\n");
 		return -ENOMEM;
 	}
 
@@ -143,7 +143,7 @@ int st_sensors_allocate_trigger(struct iio_dev *indio_dev,
 	case IRQF_TRIGGER_FALLING:
 	case IRQF_TRIGGER_LOW:
 		if (!sdata->sensor_settings->drdy_irq.addr_ihl) {
-			dev_err(&indio_dev->dev,
+			dev_err(parent,
 				"falling/low specified for IRQ but hardware supports only rising/high: will request rising/high\n");
 			if (irq_trig == IRQF_TRIGGER_FALLING)
 				irq_trig = IRQF_TRIGGER_RISING;
@@ -156,21 +156,19 @@ int st_sensors_allocate_trigger(struct iio_dev *indio_dev,
 				sdata->sensor_settings->drdy_irq.mask_ihl, 1);
 			if (err < 0)
 				return err;
-			dev_info(&indio_dev->dev,
+			dev_info(parent,
 				 "interrupts on the falling edge or active low level\n");
 		}
 		break;
 	case IRQF_TRIGGER_RISING:
-		dev_info(&indio_dev->dev,
-			 "interrupts on the rising edge\n");
+		dev_info(parent, "interrupts on the rising edge\n");
 		break;
 	case IRQF_TRIGGER_HIGH:
-		dev_info(&indio_dev->dev,
-			 "interrupts active high level\n");
+		dev_info(parent, "interrupts active high level\n");
 		break;
 	default:
 		/* This is the most preferred mode, if possible */
-		dev_err(&indio_dev->dev,
+		dev_err(parent,
 			"unsupported IRQ trigger specified (%lx), enforce rising edge\n", irq_trig);
 		irq_trig = IRQF_TRIGGER_RISING;
 	}
@@ -179,7 +177,7 @@ int st_sensors_allocate_trigger(struct iio_dev *indio_dev,
 	if (irq_trig == IRQF_TRIGGER_FALLING ||
 	    irq_trig == IRQF_TRIGGER_RISING) {
 		if (!sdata->sensor_settings->drdy_irq.stat_drdy.addr) {
-			dev_err(&indio_dev->dev,
+			dev_err(parent,
 				"edge IRQ not supported w/o stat register.\n");
 			return -EOPNOTSUPP;
 		}
@@ -214,13 +212,13 @@ int st_sensors_allocate_trigger(struct iio_dev *indio_dev,
 					sdata->trig->name,
 					sdata->trig);
 	if (err) {
-		dev_err(&indio_dev->dev, "failed to request trigger IRQ.\n");
+		dev_err(parent, "failed to request trigger IRQ.\n");
 		return err;
 	}
 
 	err = devm_iio_trigger_register(parent, sdata->trig);
 	if (err < 0) {
-		dev_err(&indio_dev->dev, "failed to register iio trigger.\n");
+		dev_err(parent, "failed to register iio trigger.\n");
 		return err;
 	}
 	indio_dev->trig = iio_trigger_get(sdata->trig);
diff --git a/drivers/iio/dac/Makefile b/drivers/iio/dac/Makefile
index 2cf148f16306..56a125f56284 100644
--- a/drivers/iio/dac/Makefile
+++ b/drivers/iio/dac/Makefile
@@ -4,7 +4,7 @@
 #
 
 # When adding new entries keep the list in alphabetical order
-obj-$(CONFIG_AD3552R) += ad3552r.o
+obj-$(CONFIG_AD3552R) += ad3552r.o ad3552r-common.o
 obj-$(CONFIG_AD5360) += ad5360.o
 obj-$(CONFIG_AD5380) += ad5380.o
 obj-$(CONFIG_AD5421) += ad5421.o
diff --git a/drivers/iio/dac/ad3552r-common.c b/drivers/iio/dac/ad3552r-common.c
new file mode 100644
index 000000000000..94869ad15c27
--- /dev/null
+++ b/drivers/iio/dac/ad3552r-common.c
@@ -0,0 +1,248 @@
+// SPDX-License-Identifier: GPL-2.0+
+//
+// Copyright (c) 2010-2024 Analog Devices Inc.
+// Copyright (c) 2024 Baylibre, SAS
+
+#include <linux/bitfield.h>
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/property.h>
+#include <linux/regulator/consumer.h>
+
+#include "ad3552r.h"
+
+const s32 ad3552r_ch_ranges[AD3552R_MAX_RANGES][2] = {
+	[AD3552R_CH_OUTPUT_RANGE_0__2P5V]	= { 0, 2500 },
+	[AD3552R_CH_OUTPUT_RANGE_0__5V]		= { 0, 5000 },
+	[AD3552R_CH_OUTPUT_RANGE_0__10V]	= { 0, 10000 },
+	[AD3552R_CH_OUTPUT_RANGE_NEG_5__5V]	= { -5000, 5000 },
+	[AD3552R_CH_OUTPUT_RANGE_NEG_10__10V]	= { -10000, 10000 }
+};
+EXPORT_SYMBOL_NS_GPL(ad3552r_ch_ranges, IIO_AD3552R);
+
+const s32 ad3542r_ch_ranges[AD3542R_MAX_RANGES][2] = {
+	[AD3542R_CH_OUTPUT_RANGE_0__2P5V]	= { 0, 2500 },
+	[AD3542R_CH_OUTPUT_RANGE_0__5V]		= { 0, 5000 },
+	[AD3542R_CH_OUTPUT_RANGE_0__10V]	= { 0, 10000 },
+	[AD3542R_CH_OUTPUT_RANGE_NEG_5__5V]	= { -5000, 5000 },
+	[AD3542R_CH_OUTPUT_RANGE_NEG_2P5__7P5V]	= { -2500, 7500 }
+};
+EXPORT_SYMBOL_NS_GPL(ad3542r_ch_ranges, IIO_AD3552R);
+
+/* Gain * AD3552R_GAIN_SCALE */
+static const s32 gains_scaling_table[] = {
+	[AD3552R_CH_GAIN_SCALING_1]		= 1000,
+	[AD3552R_CH_GAIN_SCALING_0_5]		= 500,
+	[AD3552R_CH_GAIN_SCALING_0_25]		= 250,
+	[AD3552R_CH_GAIN_SCALING_0_125]		= 125
+};
+
+u16 ad3552r_calc_custom_gain(u8 p, u8 n, s16 goffs)
+{
+	return FIELD_PREP(AD3552R_MASK_CH_RANGE_OVERRIDE, 1) |
+	       FIELD_PREP(AD3552R_MASK_CH_GAIN_SCALING_P, p) |
+	       FIELD_PREP(AD3552R_MASK_CH_GAIN_SCALING_N, n) |
+	       FIELD_PREP(AD3552R_MASK_CH_OFFSET_BIT_8, abs(goffs)) |
+	       FIELD_PREP(AD3552R_MASK_CH_OFFSET_POLARITY, goffs < 0);
+}
+EXPORT_SYMBOL_NS_GPL(ad3552r_calc_custom_gain, IIO_AD3552R);
+
+static void ad3552r_get_custom_range(struct ad3552r_ch_data *ch_data,
+				     s32 *v_min, s32 *v_max)
+{
+	s64 vref, tmp, common, offset, gn, gp;
+	/*
+	 * From datasheet formula (In Volts):
+	 *	Vmin = 2.5 + [(GainN + Offset / 1024) * 2.5 * Rfb * 1.03]
+	 *	Vmax = 2.5 - [(GainP + Offset / 1024) * 2.5 * Rfb * 1.03]
+	 * Calculus are converted to milivolts
+	 */
+	vref = 2500;
+	/* 2.5 * 1.03 * 1000 (To mV) */
+	common = 2575 * ch_data->rfb;
+	offset = ch_data->gain_offset;
+
+	gn = gains_scaling_table[ch_data->n];
+	tmp = (1024 * gn + AD3552R_GAIN_SCALE * offset) * common;
+	tmp = div_s64(tmp, 1024  * AD3552R_GAIN_SCALE);
+	*v_max = vref + tmp;
+
+	gp = gains_scaling_table[ch_data->p];
+	tmp = (1024 * gp - AD3552R_GAIN_SCALE * offset) * common;
+	tmp = div_s64(tmp, 1024 * AD3552R_GAIN_SCALE);
+	*v_min = vref - tmp;
+}
+
+void ad3552r_calc_gain_and_offset(struct ad3552r_ch_data *ch_data,
+				  const struct ad3552r_model_data *model_data)
+{
+	s32 idx, v_max, v_min, span, rem;
+	s64 tmp;
+
+	if (ch_data->range_override) {
+		ad3552r_get_custom_range(ch_data, &v_min, &v_max);
+	} else {
+		/* Normal range */
+		idx = ch_data->range;
+		v_min = model_data->ranges_table[idx][0];
+		v_max = model_data->ranges_table[idx][1];
+	}
+
+	/*
+	 * From datasheet formula:
+	 *	Vout = Span * (D / 65536) + Vmin
+	 * Converted to scale and offset:
+	 *	Scale = Span / 65536
+	 *	Offset = 65536 * Vmin / Span
+	 *
+	 * Reminders are in micros in order to be printed as
+	 * IIO_VAL_INT_PLUS_MICRO
+	 */
+	span = v_max - v_min;
+	ch_data->scale_int = div_s64_rem(span, 65536, &rem);
+	/* Do operations in microvolts */
+	ch_data->scale_dec = DIV_ROUND_CLOSEST((s64)rem * 1000000, 65536);
+
+	ch_data->offset_int = div_s64_rem(v_min * 65536, span, &rem);
+	tmp = (s64)rem * 1000000;
+	ch_data->offset_dec = div_s64(tmp, span);
+}
+EXPORT_SYMBOL_NS_GPL(ad3552r_calc_gain_and_offset, IIO_AD3552R);
+
+int ad3552r_get_ref_voltage(struct device *dev, u32 *val)
+{
+	int voltage;
+	int delta = 100000;
+
+	voltage = devm_regulator_get_enable_read_voltage(dev, "vref");
+	if (voltage < 0 && voltage != -ENODEV)
+		return dev_err_probe(dev, voltage,
+				     "Error getting vref voltage\n");
+
+	if (voltage == -ENODEV) {
+		if (device_property_read_bool(dev, "adi,vref-out-en"))
+			*val = AD3552R_INTERNAL_VREF_PIN_2P5V;
+		else
+			*val = AD3552R_INTERNAL_VREF_PIN_FLOATING;
+
+		return 0;
+	}
+
+	if (voltage > 2500000 + delta || voltage < 2500000 - delta) {
+		dev_warn(dev, "vref-supply must be 2.5V");
+		return -EINVAL;
+	}
+
+	*val = AD3552R_EXTERNAL_VREF_PIN_INPUT;
+
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(ad3552r_get_ref_voltage, IIO_AD3552R);
+
+int ad3552r_get_drive_strength(struct device *dev, u32 *val)
+{
+	int err;
+	u32 drive_strength;
+
+	err = device_property_read_u32(dev, "adi,sdo-drive-strength",
+				       &drive_strength);
+	if (err)
+		return err;
+
+	if (drive_strength > 3) {
+		dev_err_probe(dev, -EINVAL,
+			      "adi,sdo-drive-strength must be less than 4\n");
+		return -EINVAL;
+	}
+
+	*val = drive_strength;
+
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(ad3552r_get_drive_strength, IIO_AD3552R);
+
+int ad3552r_get_custom_gain(struct device *dev, struct fwnode_handle *child,
+			    u8 *gs_p, u8 *gs_n, u16 *rfb, s16 *goffs)
+{
+	int err;
+	u32 val;
+	struct fwnode_handle *gain_child __free(fwnode_handle) =
+		fwnode_get_named_child_node(child,
+					    "custom-output-range-config");
+
+	if (!gain_child)
+		return dev_err_probe(dev, -EINVAL,
+				     "custom-output-range-config mandatory\n");
+
+	err = fwnode_property_read_u32(gain_child, "adi,gain-scaling-p", &val);
+	if (err)
+		return dev_err_probe(dev, err,
+				     "adi,gain-scaling-p mandatory\n");
+	*gs_p = val;
+
+	err = fwnode_property_read_u32(gain_child, "adi,gain-scaling-n", &val);
+	if (err)
+		return dev_err_probe(dev, err,
+				     "adi,gain-scaling-n property mandatory\n");
+	*gs_n = val;
+
+	err = fwnode_property_read_u32(gain_child, "adi,rfb-ohms", &val);
+	if (err)
+		return dev_err_probe(dev, err,
+				     "adi,rfb-ohms mandatory\n");
+	*rfb = val;
+
+	err = fwnode_property_read_u32(gain_child, "adi,gain-offset", &val);
+	if (err)
+		return dev_err_probe(dev, err,
+				     "adi,gain-offset mandatory\n");
+	*goffs = val;
+
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(ad3552r_get_custom_gain, IIO_AD3552R);
+
+static int ad3552r_find_range(const struct ad3552r_model_data *model_info,
+			      s32 *vals)
+{
+	int i;
+
+	for (i = 0; i < model_info->num_ranges; i++)
+		if (vals[0] == model_info->ranges_table[i][0] * 1000 &&
+		    vals[1] == model_info->ranges_table[i][1] * 1000)
+			return i;
+
+	return -EINVAL;
+}
+
+int ad3552r_get_output_range(struct device *dev,
+			     const struct ad3552r_model_data *model_info,
+			     struct fwnode_handle *child, u32 *val)
+{
+	int ret;
+	s32 vals[2];
+
+	/* This property is optional, so returning -ENOENT if missing */
+	if (!fwnode_property_present(child, "adi,output-range-microvolt"))
+		return -ENOENT;
+
+	ret = fwnode_property_read_u32_array(child,
+					     "adi,output-range-microvolt",
+					     vals, 2);
+	if (ret)
+		return dev_err_probe(dev, ret,
+				"invalid adi,output-range-microvolt\n");
+
+	ret = ad3552r_find_range(model_info, vals);
+	if (ret < 0)
+		return dev_err_probe(dev, ret,
+			"invalid adi,output-range-microvolt value\n");
+
+	*val = ret;
+
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(ad3552r_get_output_range, IIO_AD3552R);
+
+MODULE_DESCRIPTION("ad3552r common functions");
+MODULE_LICENSE("GPL");
diff --git a/drivers/iio/dac/ad3552r.c b/drivers/iio/dac/ad3552r.c
index 7d61b2fe6624..5b2ce2aa67a4 100644
--- a/drivers/iio/dac/ad3552r.c
+++ b/drivers/iio/dac/ad3552r.c
@@ -6,271 +6,15 @@
  * Copyright 2021 Analog Devices Inc.
  */
 #include <linux/unaligned.h>
+#include <linux/bitfield.h>
 #include <linux/device.h>
 #include <linux/iio/triggered_buffer.h>
 #include <linux/iio/trigger_consumer.h>
 #include <linux/iopoll.h>
 #include <linux/kernel.h>
-#include <linux/regulator/consumer.h>
 #include <linux/spi/spi.h>
 
-/* Register addresses */
-/* Primary address space */
-#define AD3552R_REG_ADDR_INTERFACE_CONFIG_A		0x00
-#define   AD3552R_MASK_SOFTWARE_RESET			(BIT(7) | BIT(0))
-#define   AD3552R_MASK_ADDR_ASCENSION			BIT(5)
-#define   AD3552R_MASK_SDO_ACTIVE			BIT(4)
-#define AD3552R_REG_ADDR_INTERFACE_CONFIG_B		0x01
-#define   AD3552R_MASK_SINGLE_INST			BIT(7)
-#define   AD3552R_MASK_SHORT_INSTRUCTION		BIT(3)
-#define AD3552R_REG_ADDR_DEVICE_CONFIG			0x02
-#define   AD3552R_MASK_DEVICE_STATUS(n)			BIT(4 + (n))
-#define   AD3552R_MASK_CUSTOM_MODES			GENMASK(3, 2)
-#define   AD3552R_MASK_OPERATING_MODES			GENMASK(1, 0)
-#define AD3552R_REG_ADDR_CHIP_TYPE			0x03
-#define   AD3552R_MASK_CLASS				GENMASK(7, 0)
-#define AD3552R_REG_ADDR_PRODUCT_ID_L			0x04
-#define AD3552R_REG_ADDR_PRODUCT_ID_H			0x05
-#define AD3552R_REG_ADDR_CHIP_GRADE			0x06
-#define   AD3552R_MASK_GRADE				GENMASK(7, 4)
-#define   AD3552R_MASK_DEVICE_REVISION			GENMASK(3, 0)
-#define AD3552R_REG_ADDR_SCRATCH_PAD			0x0A
-#define AD3552R_REG_ADDR_SPI_REVISION			0x0B
-#define AD3552R_REG_ADDR_VENDOR_L			0x0C
-#define AD3552R_REG_ADDR_VENDOR_H			0x0D
-#define AD3552R_REG_ADDR_STREAM_MODE			0x0E
-#define   AD3552R_MASK_LENGTH				GENMASK(7, 0)
-#define AD3552R_REG_ADDR_TRANSFER_REGISTER		0x0F
-#define   AD3552R_MASK_MULTI_IO_MODE			GENMASK(7, 6)
-#define   AD3552R_MASK_STREAM_LENGTH_KEEP_VALUE		BIT(2)
-#define AD3552R_REG_ADDR_INTERFACE_CONFIG_C		0x10
-#define   AD3552R_MASK_CRC_ENABLE			(GENMASK(7, 6) |\
-							 GENMASK(1, 0))
-#define   AD3552R_MASK_STRICT_REGISTER_ACCESS		BIT(5)
-#define AD3552R_REG_ADDR_INTERFACE_STATUS_A		0x11
-#define   AD3552R_MASK_INTERFACE_NOT_READY		BIT(7)
-#define   AD3552R_MASK_CLOCK_COUNTING_ERROR		BIT(5)
-#define   AD3552R_MASK_INVALID_OR_NO_CRC		BIT(3)
-#define   AD3552R_MASK_WRITE_TO_READ_ONLY_REGISTER	BIT(2)
-#define   AD3552R_MASK_PARTIAL_REGISTER_ACCESS		BIT(1)
-#define   AD3552R_MASK_REGISTER_ADDRESS_INVALID		BIT(0)
-#define AD3552R_REG_ADDR_INTERFACE_CONFIG_D		0x14
-#define   AD3552R_MASK_ALERT_ENABLE_PULLUP		BIT(6)
-#define   AD3552R_MASK_MEM_CRC_EN			BIT(4)
-#define   AD3552R_MASK_SDO_DRIVE_STRENGTH		GENMASK(3, 2)
-#define   AD3552R_MASK_DUAL_SPI_SYNCHROUNOUS_EN		BIT(1)
-#define   AD3552R_MASK_SPI_CONFIG_DDR			BIT(0)
-#define AD3552R_REG_ADDR_SH_REFERENCE_CONFIG		0x15
-#define   AD3552R_MASK_IDUMP_FAST_MODE			BIT(6)
-#define   AD3552R_MASK_SAMPLE_HOLD_DIFFERENTIAL_USER_EN	BIT(5)
-#define   AD3552R_MASK_SAMPLE_HOLD_USER_TRIM		GENMASK(4, 3)
-#define   AD3552R_MASK_SAMPLE_HOLD_USER_ENABLE		BIT(2)
-#define   AD3552R_MASK_REFERENCE_VOLTAGE_SEL		GENMASK(1, 0)
-#define AD3552R_REG_ADDR_ERR_ALARM_MASK			0x16
-#define   AD3552R_MASK_REF_RANGE_ALARM			BIT(6)
-#define   AD3552R_MASK_CLOCK_COUNT_ERR_ALARM		BIT(5)
-#define   AD3552R_MASK_MEM_CRC_ERR_ALARM		BIT(4)
-#define   AD3552R_MASK_SPI_CRC_ERR_ALARM		BIT(3)
-#define   AD3552R_MASK_WRITE_TO_READ_ONLY_ALARM		BIT(2)
-#define   AD3552R_MASK_PARTIAL_REGISTER_ACCESS_ALARM	BIT(1)
-#define   AD3552R_MASK_REGISTER_ADDRESS_INVALID_ALARM	BIT(0)
-#define AD3552R_REG_ADDR_ERR_STATUS			0x17
-#define   AD3552R_MASK_REF_RANGE_ERR_STATUS			BIT(6)
-#define   AD3552R_MASK_DUAL_SPI_STREAM_EXCEEDS_DAC_ERR_STATUS	BIT(5)
-#define   AD3552R_MASK_MEM_CRC_ERR_STATUS			BIT(4)
-#define   AD3552R_MASK_RESET_STATUS				BIT(0)
-#define AD3552R_REG_ADDR_POWERDOWN_CONFIG		0x18
-#define   AD3552R_MASK_CH_DAC_POWERDOWN(ch)		BIT(4 + (ch))
-#define   AD3552R_MASK_CH_AMPLIFIER_POWERDOWN(ch)	BIT(ch)
-#define AD3552R_REG_ADDR_CH0_CH1_OUTPUT_RANGE		0x19
-#define   AD3552R_MASK_CH_OUTPUT_RANGE_SEL(ch)		((ch) ? GENMASK(7, 4) :\
-							 GENMASK(3, 0))
-#define AD3552R_REG_ADDR_CH_OFFSET(ch)			(0x1B + (ch) * 2)
-#define   AD3552R_MASK_CH_OFFSET_BITS_0_7		GENMASK(7, 0)
-#define AD3552R_REG_ADDR_CH_GAIN(ch)			(0x1C + (ch) * 2)
-#define   AD3552R_MASK_CH_RANGE_OVERRIDE		BIT(7)
-#define   AD3552R_MASK_CH_GAIN_SCALING_N		GENMASK(6, 5)
-#define   AD3552R_MASK_CH_GAIN_SCALING_P		GENMASK(4, 3)
-#define   AD3552R_MASK_CH_OFFSET_POLARITY		BIT(2)
-#define   AD3552R_MASK_CH_OFFSET_BIT_8			BIT(0)
-/*
- * Secondary region
- * For multibyte registers specify the highest address because the access is
- * done in descending order
- */
-#define AD3552R_SECONDARY_REGION_START			0x28
-#define AD3552R_REG_ADDR_HW_LDAC_16B			0x28
-#define AD3552R_REG_ADDR_CH_DAC_16B(ch)			(0x2C - (1 - ch) * 2)
-#define AD3552R_REG_ADDR_DAC_PAGE_MASK_16B		0x2E
-#define AD3552R_REG_ADDR_CH_SELECT_16B			0x2F
-#define AD3552R_REG_ADDR_INPUT_PAGE_MASK_16B		0x31
-#define AD3552R_REG_ADDR_SW_LDAC_16B			0x32
-#define AD3552R_REG_ADDR_CH_INPUT_16B(ch)		(0x36 - (1 - ch) * 2)
-/* 3 bytes registers */
-#define AD3552R_REG_START_24B				0x37
-#define AD3552R_REG_ADDR_HW_LDAC_24B			0x37
-#define AD3552R_REG_ADDR_CH_DAC_24B(ch)			(0x3D - (1 - ch) * 3)
-#define AD3552R_REG_ADDR_DAC_PAGE_MASK_24B		0x40
-#define AD3552R_REG_ADDR_CH_SELECT_24B			0x41
-#define AD3552R_REG_ADDR_INPUT_PAGE_MASK_24B		0x44
-#define AD3552R_REG_ADDR_SW_LDAC_24B			0x45
-#define AD3552R_REG_ADDR_CH_INPUT_24B(ch)		(0x4B - (1 - ch) * 3)
-
-/* Useful defines */
-#define AD3552R_MAX_CH					2
-#define AD3552R_MASK_CH(ch)				BIT(ch)
-#define AD3552R_MASK_ALL_CH				GENMASK(1, 0)
-#define AD3552R_MAX_REG_SIZE				3
-#define AD3552R_READ_BIT				BIT(7)
-#define AD3552R_ADDR_MASK				GENMASK(6, 0)
-#define AD3552R_MASK_DAC_12B				0xFFF0
-#define AD3552R_DEFAULT_CONFIG_B_VALUE			0x8
-#define AD3552R_SCRATCH_PAD_TEST_VAL1			0x34
-#define AD3552R_SCRATCH_PAD_TEST_VAL2			0xB2
-#define AD3552R_GAIN_SCALE				1000
-#define AD3552R_LDAC_PULSE_US				100
-
-enum ad3552r_ch_vref_select {
-	/* Internal source with Vref I/O floating */
-	AD3552R_INTERNAL_VREF_PIN_FLOATING,
-	/* Internal source with Vref I/O at 2.5V */
-	AD3552R_INTERNAL_VREF_PIN_2P5V,
-	/* External source with Vref I/O as input */
-	AD3552R_EXTERNAL_VREF_PIN_INPUT
-};
-
-enum ad3552r_id {
-	AD3541R_ID = 0x400b,
-	AD3542R_ID = 0x4009,
-	AD3551R_ID = 0x400a,
-	AD3552R_ID = 0x4008,
-};
-
-enum ad3552r_ch_output_range {
-	/* Range from 0 V to 2.5 V. Requires Rfb1x connection */
-	AD3552R_CH_OUTPUT_RANGE_0__2P5V,
-	/* Range from 0 V to 5 V. Requires Rfb1x connection  */
-	AD3552R_CH_OUTPUT_RANGE_0__5V,
-	/* Range from 0 V to 10 V. Requires Rfb2x connection  */
-	AD3552R_CH_OUTPUT_RANGE_0__10V,
-	/* Range from -5 V to 5 V. Requires Rfb2x connection  */
-	AD3552R_CH_OUTPUT_RANGE_NEG_5__5V,
-	/* Range from -10 V to 10 V. Requires Rfb4x connection  */
-	AD3552R_CH_OUTPUT_RANGE_NEG_10__10V,
-};
-
-static const s32 ad3552r_ch_ranges[][2] = {
-	[AD3552R_CH_OUTPUT_RANGE_0__2P5V]	= {0, 2500},
-	[AD3552R_CH_OUTPUT_RANGE_0__5V]		= {0, 5000},
-	[AD3552R_CH_OUTPUT_RANGE_0__10V]	= {0, 10000},
-	[AD3552R_CH_OUTPUT_RANGE_NEG_5__5V]	= {-5000, 5000},
-	[AD3552R_CH_OUTPUT_RANGE_NEG_10__10V]	= {-10000, 10000}
-};
-
-enum ad3542r_ch_output_range {
-	/* Range from 0 V to 2.5 V. Requires Rfb1x connection */
-	AD3542R_CH_OUTPUT_RANGE_0__2P5V,
-	/* Range from 0 V to 3 V. Requires Rfb1x connection  */
-	AD3542R_CH_OUTPUT_RANGE_0__3V,
-	/* Range from 0 V to 5 V. Requires Rfb1x connection  */
-	AD3542R_CH_OUTPUT_RANGE_0__5V,
-	/* Range from 0 V to 10 V. Requires Rfb2x connection  */
-	AD3542R_CH_OUTPUT_RANGE_0__10V,
-	/* Range from -2.5 V to 7.5 V. Requires Rfb2x connection  */
-	AD3542R_CH_OUTPUT_RANGE_NEG_2P5__7P5V,
-	/* Range from -5 V to 5 V. Requires Rfb2x connection  */
-	AD3542R_CH_OUTPUT_RANGE_NEG_5__5V,
-};
-
-static const s32 ad3542r_ch_ranges[][2] = {
-	[AD3542R_CH_OUTPUT_RANGE_0__2P5V]	= {0, 2500},
-	[AD3542R_CH_OUTPUT_RANGE_0__3V]		= {0, 3000},
-	[AD3542R_CH_OUTPUT_RANGE_0__5V]		= {0, 5000},
-	[AD3542R_CH_OUTPUT_RANGE_0__10V]	= {0, 10000},
-	[AD3542R_CH_OUTPUT_RANGE_NEG_2P5__7P5V]	= {-2500, 7500},
-	[AD3542R_CH_OUTPUT_RANGE_NEG_5__5V]	= {-5000, 5000}
-};
-
-enum ad3552r_ch_gain_scaling {
-	/* Gain scaling of 1 */
-	AD3552R_CH_GAIN_SCALING_1,
-	/* Gain scaling of 0.5 */
-	AD3552R_CH_GAIN_SCALING_0_5,
-	/* Gain scaling of 0.25 */
-	AD3552R_CH_GAIN_SCALING_0_25,
-	/* Gain scaling of 0.125 */
-	AD3552R_CH_GAIN_SCALING_0_125,
-};
-
-/* Gain * AD3552R_GAIN_SCALE */
-static const s32 gains_scaling_table[] = {
-	[AD3552R_CH_GAIN_SCALING_1]		= 1000,
-	[AD3552R_CH_GAIN_SCALING_0_5]		= 500,
-	[AD3552R_CH_GAIN_SCALING_0_25]		= 250,
-	[AD3552R_CH_GAIN_SCALING_0_125]		= 125
-};
-
-enum ad3552r_dev_attributes {
-	/* - Direct register values */
-	/* From 0-3 */
-	AD3552R_SDO_DRIVE_STRENGTH,
-	/*
-	 * 0 -> Internal Vref, vref_io pin floating (default)
-	 * 1 -> Internal Vref, vref_io driven by internal vref
-	 * 2 or 3 -> External Vref
-	 */
-	AD3552R_VREF_SELECT,
-	/* Read registers in ascending order if set. Else descending */
-	AD3552R_ADDR_ASCENSION,
-};
-
-enum ad3552r_ch_attributes {
-	/* DAC powerdown */
-	AD3552R_CH_DAC_POWERDOWN,
-	/* DAC amplifier powerdown */
-	AD3552R_CH_AMPLIFIER_POWERDOWN,
-	/* Select the output range. Select from enum ad3552r_ch_output_range */
-	AD3552R_CH_OUTPUT_RANGE_SEL,
-	/*
-	 * Over-rider the range selector in order to manually set the output
-	 * voltage range
-	 */
-	AD3552R_CH_RANGE_OVERRIDE,
-	/* Manually set the offset voltage */
-	AD3552R_CH_GAIN_OFFSET,
-	/* Sets the polarity of the offset. */
-	AD3552R_CH_GAIN_OFFSET_POLARITY,
-	/* PDAC gain scaling */
-	AD3552R_CH_GAIN_SCALING_P,
-	/* NDAC gain scaling */
-	AD3552R_CH_GAIN_SCALING_N,
-	/* Rfb value */
-	AD3552R_CH_RFB,
-	/* Channel select. When set allow Input -> DAC and Mask -> DAC */
-	AD3552R_CH_SELECT,
-};
-
-struct ad3552r_ch_data {
-	s32	scale_int;
-	s32	scale_dec;
-	s32	offset_int;
-	s32	offset_dec;
-	s16	gain_offset;
-	u16	rfb;
-	u8	n;
-	u8	p;
-	u8	range;
-	bool	range_override;
-};
-
-struct ad3552r_model_data {
-	const char *model_name;
-	enum ad3552r_id chip_id;
-	unsigned int num_hw_channels;
-	const s32 (*ranges_table)[2];
-	int num_ranges;
-	bool requires_output_range;
-};
+#include "ad3552r.h"
 
 struct ad3552r_desc {
 	const struct ad3552r_model_data *model_data;
@@ -285,45 +29,6 @@ struct ad3552r_desc {
 	unsigned int		num_ch;
 };
 
-static const u16 addr_mask_map[][2] = {
-	[AD3552R_ADDR_ASCENSION] = {
-			AD3552R_REG_ADDR_INTERFACE_CONFIG_A,
-			AD3552R_MASK_ADDR_ASCENSION
-	},
-	[AD3552R_SDO_DRIVE_STRENGTH] = {
-			AD3552R_REG_ADDR_INTERFACE_CONFIG_D,
-			AD3552R_MASK_SDO_DRIVE_STRENGTH
-	},
-	[AD3552R_VREF_SELECT] = {
-			AD3552R_REG_ADDR_SH_REFERENCE_CONFIG,
-			AD3552R_MASK_REFERENCE_VOLTAGE_SEL
-	},
-};
-
-/* 0 -> reg addr, 1->ch0 mask, 2->ch1 mask */
-static const u16 addr_mask_map_ch[][3] = {
-	[AD3552R_CH_DAC_POWERDOWN] = {
-			AD3552R_REG_ADDR_POWERDOWN_CONFIG,
-			AD3552R_MASK_CH_DAC_POWERDOWN(0),
-			AD3552R_MASK_CH_DAC_POWERDOWN(1)
-	},
-	[AD3552R_CH_AMPLIFIER_POWERDOWN] = {
-			AD3552R_REG_ADDR_POWERDOWN_CONFIG,
-			AD3552R_MASK_CH_AMPLIFIER_POWERDOWN(0),
-			AD3552R_MASK_CH_AMPLIFIER_POWERDOWN(1)
-	},
-	[AD3552R_CH_OUTPUT_RANGE_SEL] = {
-			AD3552R_REG_ADDR_CH0_CH1_OUTPUT_RANGE,
-			AD3552R_MASK_CH_OUTPUT_RANGE_SEL(0),
-			AD3552R_MASK_CH_OUTPUT_RANGE_SEL(1)
-	},
-	[AD3552R_CH_SELECT] = {
-			AD3552R_REG_ADDR_CH_SELECT_16B,
-			AD3552R_MASK_CH(0),
-			AD3552R_MASK_CH(1)
-	}
-};
-
 static u8 _ad3552r_reg_len(u8 addr)
 {
 	switch (addr) {
@@ -399,11 +104,6 @@ static int ad3552r_read_reg(struct ad3552r_desc *dac, u8 addr, u16 *val)
 	return 0;
 }
 
-static u16 ad3552r_field_prep(u16 val, u16 mask)
-{
-	return (val << __ffs(mask)) & mask;
-}
-
 /* Update field of a register, shift val if needed */
 static int ad3552r_update_reg_field(struct ad3552r_desc *dac, u8 addr, u16 mask,
 				    u16 val)
@@ -416,21 +116,11 @@ static int ad3552r_update_reg_field(struct ad3552r_desc *dac, u8 addr, u16 mask,
 		return ret;
 
 	reg &= ~mask;
-	reg |= ad3552r_field_prep(val, mask);
+	reg |= val;
 
 	return ad3552r_write_reg(dac, addr, reg);
 }
 
-static int ad3552r_set_ch_value(struct ad3552r_desc *dac,
-				enum ad3552r_ch_attributes attr,
-				u8 ch,
-				u16 val)
-{
-	/* Update register related to attributes in chip */
-	return ad3552r_update_reg_field(dac, addr_mask_map_ch[attr][0],
-				       addr_mask_map_ch[attr][ch + 1], val);
-}
-
 #define AD3552R_CH_DAC(_idx) ((struct iio_chan_spec) {		\
 	.type = IIO_VOLTAGE,					\
 	.output = true,						\
@@ -510,8 +200,14 @@ static int ad3552r_write_raw(struct iio_dev *indio_dev,
 					val);
 		break;
 	case IIO_CHAN_INFO_ENABLE:
-		err = ad3552r_set_ch_value(dac, AD3552R_CH_DAC_POWERDOWN,
-					   chan->channel, !val);
+		if (chan->channel == 0)
+			val = FIELD_PREP(AD3552R_MASK_CH_DAC_POWERDOWN(0), !val);
+		else
+			val = FIELD_PREP(AD3552R_MASK_CH_DAC_POWERDOWN(1), !val);
+
+		err = ad3552r_update_reg_field(dac, AD3552R_REG_ADDR_POWERDOWN_CONFIG,
+					       AD3552R_MASK_CH_DAC_POWERDOWN(chan->channel),
+					       val);
 		break;
 	default:
 		err = -EINVAL;
@@ -714,84 +410,16 @@ static int ad3552r_reset(struct ad3552r_desc *dac)
 		return ret;
 	}
 
-	return ad3552r_update_reg_field(dac,
-					addr_mask_map[AD3552R_ADDR_ASCENSION][0],
-					addr_mask_map[AD3552R_ADDR_ASCENSION][1],
-					val);
-}
-
-static void ad3552r_get_custom_range(struct ad3552r_desc *dac, s32 i, s32 *v_min,
-				     s32 *v_max)
-{
-	s64 vref, tmp, common, offset, gn, gp;
-	/*
-	 * From datasheet formula (In Volts):
-	 *	Vmin = 2.5 + [(GainN + Offset / 1024) * 2.5 * Rfb * 1.03]
-	 *	Vmax = 2.5 - [(GainP + Offset / 1024) * 2.5 * Rfb * 1.03]
-	 * Calculus are converted to milivolts
-	 */
-	vref = 2500;
-	/* 2.5 * 1.03 * 1000 (To mV) */
-	common = 2575 * dac->ch_data[i].rfb;
-	offset = dac->ch_data[i].gain_offset;
-
-	gn = gains_scaling_table[dac->ch_data[i].n];
-	tmp = (1024 * gn + AD3552R_GAIN_SCALE * offset) * common;
-	tmp = div_s64(tmp, 1024  * AD3552R_GAIN_SCALE);
-	*v_max = vref + tmp;
-
-	gp = gains_scaling_table[dac->ch_data[i].p];
-	tmp = (1024 * gp - AD3552R_GAIN_SCALE * offset) * common;
-	tmp = div_s64(tmp, 1024 * AD3552R_GAIN_SCALE);
-	*v_min = vref - tmp;
-}
-
-static void ad3552r_calc_gain_and_offset(struct ad3552r_desc *dac, s32 ch)
-{
-	s32 idx, v_max, v_min, span, rem;
-	s64 tmp;
-
-	if (dac->ch_data[ch].range_override) {
-		ad3552r_get_custom_range(dac, ch, &v_min, &v_max);
-	} else {
-		/* Normal range */
-		idx = dac->ch_data[ch].range;
-		v_min = dac->model_data->ranges_table[idx][0];
-		v_max = dac->model_data->ranges_table[idx][1];
-	}
-
-	/*
-	 * From datasheet formula:
-	 *	Vout = Span * (D / 65536) + Vmin
-	 * Converted to scale and offset:
-	 *	Scale = Span / 65536
-	 *	Offset = 65536 * Vmin / Span
-	 *
-	 * Reminders are in micros in order to be printed as
-	 * IIO_VAL_INT_PLUS_MICRO
-	 */
-	span = v_max - v_min;
-	dac->ch_data[ch].scale_int = div_s64_rem(span, 65536, &rem);
-	/* Do operations in microvolts */
-	dac->ch_data[ch].scale_dec = DIV_ROUND_CLOSEST((s64)rem * 1000000,
-							65536);
-
-	dac->ch_data[ch].offset_int = div_s64_rem(v_min * 65536, span, &rem);
-	tmp = (s64)rem * 1000000;
-	dac->ch_data[ch].offset_dec = div_s64(tmp, span);
-}
-
-static int ad3552r_find_range(const struct ad3552r_model_data *model_data,
-			      s32 *vals)
-{
-	int i;
-
-	for (i = 0; i < model_data->num_ranges; i++)
-		if (vals[0] == model_data->ranges_table[i][0] * 1000 &&
-		    vals[1] == model_data->ranges_table[i][1] * 1000)
-			return i;
+	/* Clear reset error flag, see ad3552r manual, rev B table 38. */
+	ret = ad3552r_write_reg(dac, AD3552R_REG_ADDR_ERR_STATUS,
+				AD3552R_MASK_RESET_STATUS);
+	if (ret)
+		return ret;
 
-	return -EINVAL;
+	return ad3552r_update_reg_field(dac,
+					AD3552R_REG_ADDR_INTERFACE_CONFIG_A,
+					AD3552R_MASK_ADDR_ASCENSION,
+					FIELD_PREP(AD3552R_MASK_ADDR_ASCENSION, val));
 }
 
 static int ad3552r_configure_custom_gain(struct ad3552r_desc *dac,
@@ -799,57 +427,30 @@ static int ad3552r_configure_custom_gain(struct ad3552r_desc *dac,
 					 u32 ch)
 {
 	struct device *dev = &dac->spi->dev;
-	u32 val;
 	int err;
 	u8 addr;
-	u16 reg = 0, offset;
-
-	struct fwnode_handle *gain_child __free(fwnode_handle)
-		= fwnode_get_named_child_node(child,
-					      "custom-output-range-config");
-	if (!gain_child)
-		return dev_err_probe(dev, -EINVAL,
-				     "mandatory custom-output-range-config property missing\n");
-
-	dac->ch_data[ch].range_override = 1;
-	reg |= ad3552r_field_prep(1, AD3552R_MASK_CH_RANGE_OVERRIDE);
-
-	err = fwnode_property_read_u32(gain_child, "adi,gain-scaling-p", &val);
-	if (err)
-		return dev_err_probe(dev, err,
-				     "mandatory adi,gain-scaling-p property missing\n");
-	reg |= ad3552r_field_prep(val, AD3552R_MASK_CH_GAIN_SCALING_P);
-	dac->ch_data[ch].p = val;
-
-	err = fwnode_property_read_u32(gain_child, "adi,gain-scaling-n", &val);
-	if (err)
-		return dev_err_probe(dev, err,
-				     "mandatory adi,gain-scaling-n property missing\n");
-	reg |= ad3552r_field_prep(val, AD3552R_MASK_CH_GAIN_SCALING_N);
-	dac->ch_data[ch].n = val;
-
-	err = fwnode_property_read_u32(gain_child, "adi,rfb-ohms", &val);
-	if (err)
-		return dev_err_probe(dev, err,
-				     "mandatory adi,rfb-ohms property missing\n");
-	dac->ch_data[ch].rfb = val;
+	u16 reg;
 
-	err = fwnode_property_read_u32(gain_child, "adi,gain-offset", &val);
+	err = ad3552r_get_custom_gain(dev, child,
+				      &dac->ch_data[ch].p,
+				      &dac->ch_data[ch].n,
+				      &dac->ch_data[ch].rfb,
+				      &dac->ch_data[ch].gain_offset);
 	if (err)
-		return dev_err_probe(dev, err,
-				     "mandatory adi,gain-offset property missing\n");
-	dac->ch_data[ch].gain_offset = val;
+		return err;
 
-	offset = abs((s32)val);
-	reg |= ad3552r_field_prep((offset >> 8), AD3552R_MASK_CH_OFFSET_BIT_8);
+	dac->ch_data[ch].range_override = 1;
 
-	reg |= ad3552r_field_prep((s32)val < 0, AD3552R_MASK_CH_OFFSET_POLARITY);
 	addr = AD3552R_REG_ADDR_CH_GAIN(ch);
 	err = ad3552r_write_reg(dac, addr,
-				offset & AD3552R_MASK_CH_OFFSET_BITS_0_7);
+				abs((s32)dac->ch_data[ch].gain_offset) &
+				AD3552R_MASK_CH_OFFSET_BITS_0_7);
 	if (err)
 		return dev_err_probe(dev, err, "Error writing register\n");
 
+	reg = ad3552r_calc_custom_gain(dac->ch_data[ch].p, dac->ch_data[ch].n,
+				       dac->ch_data[ch].gain_offset);
+
 	err = ad3552r_write_reg(dac, addr, reg);
 	if (err)
 		return dev_err_probe(dev, err, "Error writing register\n");
@@ -860,49 +461,31 @@ static int ad3552r_configure_custom_gain(struct ad3552r_desc *dac,
 static int ad3552r_configure_device(struct ad3552r_desc *dac)
 {
 	struct device *dev = &dac->spi->dev;
-	int err, cnt = 0, voltage, delta = 100000;
-	u32 vals[2], val, ch;
+	int err, cnt = 0;
+	u32 val, ch;
 
 	dac->gpio_ldac = devm_gpiod_get_optional(dev, "ldac", GPIOD_OUT_HIGH);
 	if (IS_ERR(dac->gpio_ldac))
 		return dev_err_probe(dev, PTR_ERR(dac->gpio_ldac),
 				     "Error getting gpio ldac");
 
-	voltage = devm_regulator_get_enable_read_voltage(dev, "vref");
-	if (voltage < 0 && voltage != -ENODEV)
-		return dev_err_probe(dev, voltage, "Error getting vref voltage\n");
-
-	if (voltage == -ENODEV) {
-		if (device_property_read_bool(dev, "adi,vref-out-en"))
-			val = AD3552R_INTERNAL_VREF_PIN_2P5V;
-		else
-			val = AD3552R_INTERNAL_VREF_PIN_FLOATING;
-	} else {
-		if (voltage > 2500000 + delta || voltage < 2500000 - delta) {
-			dev_warn(dev, "vref-supply must be 2.5V");
-			return -EINVAL;
-		}
-		val = AD3552R_EXTERNAL_VREF_PIN_INPUT;
-	}
+	err = ad3552r_get_ref_voltage(dev, &val);
+	if (err < 0)
+		return err;
 
 	err = ad3552r_update_reg_field(dac,
-				       addr_mask_map[AD3552R_VREF_SELECT][0],
-				       addr_mask_map[AD3552R_VREF_SELECT][1],
-				       val);
+				       AD3552R_REG_ADDR_SH_REFERENCE_CONFIG,
+				       AD3552R_MASK_REFERENCE_VOLTAGE_SEL,
+				       FIELD_PREP(AD3552R_MASK_REFERENCE_VOLTAGE_SEL, val));
 	if (err)
 		return err;
 
-	err = device_property_read_u32(dev, "adi,sdo-drive-strength", &val);
+	err = ad3552r_get_drive_strength(dev, &val);
 	if (!err) {
-		if (val > 3) {
-			dev_err(dev, "adi,sdo-drive-strength must be less than 4\n");
-			return -EINVAL;
-		}
-
 		err = ad3552r_update_reg_field(dac,
-					       addr_mask_map[AD3552R_SDO_DRIVE_STRENGTH][0],
-					       addr_mask_map[AD3552R_SDO_DRIVE_STRENGTH][1],
-					       val);
+					       AD3552R_REG_ADDR_INTERFACE_CONFIG_D,
+					       AD3552R_MASK_SDO_DRIVE_STRENGTH,
+					       FIELD_PREP(AD3552R_MASK_SDO_DRIVE_STRENGTH, val));
 		if (err)
 			return err;
 	}
@@ -923,24 +506,21 @@ static int ad3552r_configure_device(struct ad3552r_desc *dac)
 					     "reg must be less than %d\n",
 					     dac->model_data->num_hw_channels);
 
-		if (fwnode_property_present(child, "adi,output-range-microvolt")) {
-			err = fwnode_property_read_u32_array(child,
-							     "adi,output-range-microvolt",
-							     vals,
-							     2);
-			if (err)
-				return dev_err_probe(dev, err,
-					"adi,output-range-microvolt property could not be parsed\n");
-
-			err = ad3552r_find_range(dac->model_data, vals);
-			if (err < 0)
-				return dev_err_probe(dev, err,
-						     "Invalid adi,output-range-microvolt value\n");
-
-			val = err;
-			err = ad3552r_set_ch_value(dac,
-						   AD3552R_CH_OUTPUT_RANGE_SEL,
-						   ch, val);
+		err = ad3552r_get_output_range(dev, dac->model_data,
+					       child, &val);
+		if (err && err != -ENOENT)
+			return err;
+
+		if (!err) {
+			if (ch == 0)
+				val = FIELD_PREP(AD3552R_MASK_CH_OUTPUT_RANGE_SEL(0), val);
+			else
+				val = FIELD_PREP(AD3552R_MASK_CH_OUTPUT_RANGE_SEL(1), val);
+
+			err = ad3552r_update_reg_field(dac,
+						       AD3552R_REG_ADDR_CH0_CH1_OUTPUT_RANGE,
+						       AD3552R_MASK_CH_OUTPUT_RANGE_SEL(ch),
+						       val);
 			if (err)
 				return err;
 
@@ -955,10 +535,17 @@ static int ad3552r_configure_device(struct ad3552r_desc *dac)
 				return err;
 		}
 
-		ad3552r_calc_gain_and_offset(dac, ch);
+		ad3552r_calc_gain_and_offset(&dac->ch_data[ch], dac->model_data);
 		dac->enabled_ch |= BIT(ch);
 
-		err = ad3552r_set_ch_value(dac, AD3552R_CH_SELECT, ch, 1);
+		if (ch == 0)
+			val = FIELD_PREP(AD3552R_MASK_CH(0), 1);
+		else
+			val = FIELD_PREP(AD3552R_MASK_CH(1), 1);
+
+		err = ad3552r_update_reg_field(dac,
+					       AD3552R_REG_ADDR_CH_SELECT_16B,
+					       AD3552R_MASK_CH(ch), val);
 		if (err < 0)
 			return err;
 
@@ -970,8 +557,15 @@ static int ad3552r_configure_device(struct ad3552r_desc *dac)
 	/* Disable unused channels */
 	for_each_clear_bit(ch, &dac->enabled_ch,
 			   dac->model_data->num_hw_channels) {
-		err = ad3552r_set_ch_value(dac, AD3552R_CH_AMPLIFIER_POWERDOWN,
-					   ch, 1);
+		if (ch == 0)
+			val = FIELD_PREP(AD3552R_MASK_CH_AMPLIFIER_POWERDOWN(0), 1);
+		else
+			val = FIELD_PREP(AD3552R_MASK_CH_AMPLIFIER_POWERDOWN(1), 1);
+
+		err = ad3552r_update_reg_field(dac,
+					       AD3552R_REG_ADDR_POWERDOWN_CONFIG,
+					       AD3552R_MASK_CH_AMPLIFIER_POWERDOWN(ch),
+					       val);
 		if (err)
 			return err;
 	}
@@ -1140,3 +734,4 @@ module_spi_driver(ad3552r_driver);
 MODULE_AUTHOR("Mihail Chindris <mihail.chindris@analog.com>");
 MODULE_DESCRIPTION("Analog Device AD3552R DAC");
 MODULE_LICENSE("GPL v2");
+MODULE_IMPORT_NS(IIO_AD3552R);
diff --git a/drivers/iio/dac/ad3552r.h b/drivers/iio/dac/ad3552r.h
new file mode 100644
index 000000000000..c20f64f80d5d
--- /dev/null
+++ b/drivers/iio/dac/ad3552r.h
@@ -0,0 +1,223 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * AD3552R Digital <-> Analog converters common header
+ *
+ * Copyright 2021-2024 Analog Devices Inc.
+ * Author: Angelo Dureghello <adureghello@baylibre.com>
+ */
+
+#ifndef __DRIVERS_IIO_DAC_AD3552R_H__
+#define __DRIVERS_IIO_DAC_AD3552R_H__
+
+/* Register addresses */
+/* Primary address space */
+#define AD3552R_REG_ADDR_INTERFACE_CONFIG_A		0x00
+#define   AD3552R_MASK_SOFTWARE_RESET			(BIT(7) | BIT(0))
+#define   AD3552R_MASK_ADDR_ASCENSION			BIT(5)
+#define   AD3552R_MASK_SDO_ACTIVE			BIT(4)
+#define AD3552R_REG_ADDR_INTERFACE_CONFIG_B		0x01
+#define   AD3552R_MASK_SINGLE_INST			BIT(7)
+#define   AD3552R_MASK_SHORT_INSTRUCTION		BIT(3)
+#define AD3552R_REG_ADDR_DEVICE_CONFIG			0x02
+#define   AD3552R_MASK_DEVICE_STATUS(n)			BIT(4 + (n))
+#define   AD3552R_MASK_CUSTOM_MODES			GENMASK(3, 2)
+#define   AD3552R_MASK_OPERATING_MODES			GENMASK(1, 0)
+#define AD3552R_REG_ADDR_CHIP_TYPE			0x03
+#define   AD3552R_MASK_CLASS				GENMASK(7, 0)
+#define AD3552R_REG_ADDR_PRODUCT_ID_L			0x04
+#define AD3552R_REG_ADDR_PRODUCT_ID_H			0x05
+#define AD3552R_REG_ADDR_CHIP_GRADE			0x06
+#define   AD3552R_MASK_GRADE				GENMASK(7, 4)
+#define   AD3552R_MASK_DEVICE_REVISION			GENMASK(3, 0)
+#define AD3552R_REG_ADDR_SCRATCH_PAD			0x0A
+#define AD3552R_REG_ADDR_SPI_REVISION			0x0B
+#define AD3552R_REG_ADDR_VENDOR_L			0x0C
+#define AD3552R_REG_ADDR_VENDOR_H			0x0D
+#define AD3552R_REG_ADDR_STREAM_MODE			0x0E
+#define   AD3552R_MASK_LENGTH				GENMASK(7, 0)
+#define AD3552R_REG_ADDR_TRANSFER_REGISTER		0x0F
+#define   AD3552R_MASK_MULTI_IO_MODE			GENMASK(7, 6)
+#define   AD3552R_MASK_STREAM_LENGTH_KEEP_VALUE		BIT(2)
+#define AD3552R_REG_ADDR_INTERFACE_CONFIG_C		0x10
+#define   AD3552R_MASK_CRC_ENABLE \
+		(GENMASK(7, 6) | GENMASK(1, 0))
+#define   AD3552R_MASK_STRICT_REGISTER_ACCESS		BIT(5)
+#define AD3552R_REG_ADDR_INTERFACE_STATUS_A		0x11
+#define   AD3552R_MASK_INTERFACE_NOT_READY		BIT(7)
+#define   AD3552R_MASK_CLOCK_COUNTING_ERROR		BIT(5)
+#define   AD3552R_MASK_INVALID_OR_NO_CRC		BIT(3)
+#define   AD3552R_MASK_WRITE_TO_READ_ONLY_REGISTER	BIT(2)
+#define   AD3552R_MASK_PARTIAL_REGISTER_ACCESS		BIT(1)
+#define   AD3552R_MASK_REGISTER_ADDRESS_INVALID		BIT(0)
+#define AD3552R_REG_ADDR_INTERFACE_CONFIG_D		0x14
+#define   AD3552R_MASK_ALERT_ENABLE_PULLUP		BIT(6)
+#define   AD3552R_MASK_MEM_CRC_EN			BIT(4)
+#define   AD3552R_MASK_SDO_DRIVE_STRENGTH		GENMASK(3, 2)
+#define   AD3552R_MASK_DUAL_SPI_SYNCHROUNOUS_EN		BIT(1)
+#define   AD3552R_MASK_SPI_CONFIG_DDR			BIT(0)
+#define AD3552R_REG_ADDR_SH_REFERENCE_CONFIG		0x15
+#define   AD3552R_MASK_IDUMP_FAST_MODE			BIT(6)
+#define   AD3552R_MASK_SAMPLE_HOLD_DIFF_USER_EN		BIT(5)
+#define   AD3552R_MASK_SAMPLE_HOLD_USER_TRIM		GENMASK(4, 3)
+#define   AD3552R_MASK_SAMPLE_HOLD_USER_ENABLE		BIT(2)
+#define   AD3552R_MASK_REFERENCE_VOLTAGE_SEL		GENMASK(1, 0)
+#define AD3552R_REG_ADDR_ERR_ALARM_MASK			0x16
+#define   AD3552R_MASK_REF_RANGE_ALARM			BIT(6)
+#define   AD3552R_MASK_CLOCK_COUNT_ERR_ALARM		BIT(5)
+#define   AD3552R_MASK_MEM_CRC_ERR_ALARM		BIT(4)
+#define   AD3552R_MASK_SPI_CRC_ERR_ALARM		BIT(3)
+#define   AD3552R_MASK_WRITE_TO_READ_ONLY_ALARM		BIT(2)
+#define   AD3552R_MASK_PARTIAL_REGISTER_ACCESS_ALARM	BIT(1)
+#define   AD3552R_MASK_REGISTER_ADDRESS_INVALID_ALARM	BIT(0)
+#define AD3552R_REG_ADDR_ERR_STATUS			0x17
+#define   AD3552R_MASK_REF_RANGE_ERR_STATUS		BIT(6)
+#define   AD3552R_MASK_STREAM_EXCEEDS_DAC_ERR_STATUS	BIT(5)
+#define   AD3552R_MASK_MEM_CRC_ERR_STATUS		BIT(4)
+#define   AD3552R_MASK_RESET_STATUS			BIT(0)
+#define AD3552R_REG_ADDR_POWERDOWN_CONFIG		0x18
+#define   AD3552R_MASK_CH_DAC_POWERDOWN(ch)		BIT(4 + (ch))
+#define   AD3552R_MASK_CH_AMPLIFIER_POWERDOWN(ch)	BIT(ch)
+#define AD3552R_REG_ADDR_CH0_CH1_OUTPUT_RANGE		0x19
+#define   AD3552R_MASK_CH0_RANGE			GENMASK(2, 0)
+#define   AD3552R_MASK_CH1_RANGE			GENMASK(6, 4)
+#define   AD3552R_MASK_CH_OUTPUT_RANGE			GENMASK(7, 0)
+#define   AD3552R_MASK_CH_OUTPUT_RANGE_SEL(ch) \
+		((ch) ? GENMASK(7, 4) : GENMASK(3, 0))
+#define AD3552R_REG_ADDR_CH_OFFSET(ch)			(0x1B + (ch) * 2)
+#define   AD3552R_MASK_CH_OFFSET_BITS_0_7		GENMASK(7, 0)
+#define AD3552R_REG_ADDR_CH_GAIN(ch)			(0x1C + (ch) * 2)
+#define   AD3552R_MASK_CH_RANGE_OVERRIDE		BIT(7)
+#define   AD3552R_MASK_CH_GAIN_SCALING_N		GENMASK(6, 5)
+#define   AD3552R_MASK_CH_GAIN_SCALING_P		GENMASK(4, 3)
+#define   AD3552R_MASK_CH_OFFSET_POLARITY		BIT(2)
+#define   AD3552R_MASK_CH_OFFSET_BIT_8			BIT(8)
+/*
+ * Secondary region
+ * For multibyte registers specify the highest address because the access is
+ * done in descending order
+ */
+#define AD3552R_SECONDARY_REGION_START			0x28
+#define AD3552R_REG_ADDR_HW_LDAC_16B			0x28
+#define AD3552R_REG_ADDR_CH_DAC_16B(ch)			(0x2C - (1 - (ch)) * 2)
+#define AD3552R_REG_ADDR_DAC_PAGE_MASK_16B		0x2E
+#define AD3552R_REG_ADDR_CH_SELECT_16B			0x2F
+#define AD3552R_REG_ADDR_INPUT_PAGE_MASK_16B		0x31
+#define AD3552R_REG_ADDR_SW_LDAC_16B			0x32
+#define AD3552R_REG_ADDR_CH_INPUT_16B(ch)		(0x36 - (1 - (ch)) * 2)
+/* 3 bytes registers */
+#define AD3552R_REG_START_24B				0x37
+#define AD3552R_REG_ADDR_HW_LDAC_24B			0x37
+#define AD3552R_REG_ADDR_CH_DAC_24B(ch)			(0x3D - (1 - (ch)) * 3)
+#define AD3552R_REG_ADDR_DAC_PAGE_MASK_24B		0x40
+#define AD3552R_REG_ADDR_CH_SELECT_24B			0x41
+#define AD3552R_REG_ADDR_INPUT_PAGE_MASK_24B		0x44
+#define AD3552R_REG_ADDR_SW_LDAC_24B			0x45
+#define AD3552R_REG_ADDR_CH_INPUT_24B(ch)		(0x4B - (1 - (ch)) * 3)
+
+#define AD3552R_MAX_CH					2
+#define AD3552R_MASK_CH(ch)				BIT(ch)
+#define AD3552R_MASK_ALL_CH				GENMASK(1, 0)
+#define AD3552R_MAX_REG_SIZE				3
+#define AD3552R_READ_BIT				BIT(7)
+#define AD3552R_ADDR_MASK				GENMASK(6, 0)
+#define AD3552R_MASK_DAC_12B				GENMASK(15, 4)
+#define AD3552R_DEFAULT_CONFIG_B_VALUE			0x8
+#define AD3552R_SCRATCH_PAD_TEST_VAL1			0x34
+#define AD3552R_SCRATCH_PAD_TEST_VAL2			0xB2
+#define AD3552R_GAIN_SCALE				1000
+#define AD3552R_LDAC_PULSE_US				100
+
+#define AD3552R_MAX_RANGES	5
+#define AD3542R_MAX_RANGES	5
+#define AD3552R_QUAD_SPI	2
+
+extern const s32 ad3552r_ch_ranges[AD3552R_MAX_RANGES][2];
+extern const s32 ad3542r_ch_ranges[AD3542R_MAX_RANGES][2];
+
+enum ad3552r_id {
+	AD3541R_ID = 0x400b,
+	AD3542R_ID = 0x4009,
+	AD3551R_ID = 0x400a,
+	AD3552R_ID = 0x4008,
+};
+
+struct ad3552r_model_data {
+	const char *model_name;
+	enum ad3552r_id chip_id;
+	unsigned int num_hw_channels;
+	const s32 (*ranges_table)[2];
+	int num_ranges;
+	bool requires_output_range;
+};
+
+struct ad3552r_ch_data {
+	s32	scale_int;
+	s32	scale_dec;
+	s32	offset_int;
+	s32	offset_dec;
+	s16	gain_offset;
+	u16	rfb;
+	u8	n;
+	u8	p;
+	u8	range;
+	bool	range_override;
+};
+
+enum ad3552r_ch_gain_scaling {
+	/* Gain scaling of 1 */
+	AD3552R_CH_GAIN_SCALING_1,
+	/* Gain scaling of 0.5 */
+	AD3552R_CH_GAIN_SCALING_0_5,
+	/* Gain scaling of 0.25 */
+	AD3552R_CH_GAIN_SCALING_0_25,
+	/* Gain scaling of 0.125 */
+	AD3552R_CH_GAIN_SCALING_0_125,
+};
+
+enum ad3552r_ch_vref_select {
+	/* Internal source with Vref I/O floating */
+	AD3552R_INTERNAL_VREF_PIN_FLOATING,
+	/* Internal source with Vref I/O at 2.5V */
+	AD3552R_INTERNAL_VREF_PIN_2P5V,
+	/* External source with Vref I/O as input */
+	AD3552R_EXTERNAL_VREF_PIN_INPUT
+};
+
+enum ad3542r_ch_output_range {
+	/* Range from 0 V to 2.5 V. Requires Rfb1x connection */
+	AD3542R_CH_OUTPUT_RANGE_0__2P5V,
+	/* Range from 0 V to 5 V. Requires Rfb1x connection  */
+	AD3542R_CH_OUTPUT_RANGE_0__5V,
+	/* Range from 0 V to 10 V. Requires Rfb2x connection  */
+	AD3542R_CH_OUTPUT_RANGE_0__10V,
+	/* Range from -5 V to 5 V. Requires Rfb2x connection  */
+	AD3542R_CH_OUTPUT_RANGE_NEG_5__5V,
+	/* Range from -2.5 V to 7.5 V. Requires Rfb2x connection  */
+	AD3542R_CH_OUTPUT_RANGE_NEG_2P5__7P5V,
+};
+
+enum ad3552r_ch_output_range {
+	/* Range from 0 V to 2.5 V. Requires Rfb1x connection */
+	AD3552R_CH_OUTPUT_RANGE_0__2P5V,
+	/* Range from 0 V to 5 V. Requires Rfb1x connection  */
+	AD3552R_CH_OUTPUT_RANGE_0__5V,
+	/* Range from 0 V to 10 V. Requires Rfb2x connection  */
+	AD3552R_CH_OUTPUT_RANGE_0__10V,
+	/* Range from -5 V to 5 V. Requires Rfb2x connection  */
+	AD3552R_CH_OUTPUT_RANGE_NEG_5__5V,
+	/* Range from -10 V to 10 V. Requires Rfb4x connection  */
+	AD3552R_CH_OUTPUT_RANGE_NEG_10__10V,
+};
+
+int ad3552r_get_output_range(struct device *dev,
+			     const struct ad3552r_model_data *model_info,
+			     struct fwnode_handle *child, u32 *val);
+int ad3552r_get_custom_gain(struct device *dev, struct fwnode_handle *child,
+			    u8 *gs_p, u8 *gs_n, u16 *rfb, s16 *goffs);
+u16 ad3552r_calc_custom_gain(u8 p, u8 n, s16 goffs);
+int ad3552r_get_ref_voltage(struct device *dev, u32 *val);
+int ad3552r_get_drive_strength(struct device *dev, u32 *val);
+void ad3552r_calc_gain_and_offset(struct ad3552r_ch_data *ch_data,
+				  const struct ad3552r_model_data *model_data);
+
+#endif /* __DRIVERS_IIO_DAC_AD3552R_H__ */
diff --git a/drivers/iio/filter/admv8818.c b/drivers/iio/filter/admv8818.c
index 848baa6e3bbf..cc8ce0fe74e7 100644
--- a/drivers/iio/filter/admv8818.c
+++ b/drivers/iio/filter/admv8818.c
@@ -14,6 +14,7 @@
 #include <linux/mod_devicetable.h>
 #include <linux/mutex.h>
 #include <linux/notifier.h>
+#include <linux/property.h>
 #include <linux/regmap.h>
 #include <linux/spi/spi.h>
 #include <linux/units.h>
@@ -70,6 +71,16 @@
 #define ADMV8818_HPF_WR0_MSK			GENMASK(7, 4)
 #define ADMV8818_LPF_WR0_MSK			GENMASK(3, 0)
 
+#define ADMV8818_BAND_BYPASS       0
+#define ADMV8818_BAND_MIN          1
+#define ADMV8818_BAND_MAX          4
+#define ADMV8818_BAND_CORNER_LOW   0
+#define ADMV8818_BAND_CORNER_HIGH  1
+
+#define ADMV8818_STATE_MIN   0
+#define ADMV8818_STATE_MAX   15
+#define ADMV8818_NUM_STATES  16
+
 enum {
 	ADMV8818_BW_FREQ,
 	ADMV8818_CENTER_FREQ
@@ -90,20 +101,24 @@ struct admv8818_state {
 	struct mutex		lock;
 	unsigned int		filter_mode;
 	u64			cf_hz;
+	u64			lpf_margin_hz;
+	u64			hpf_margin_hz;
 };
 
-static const unsigned long long freq_range_hpf[4][2] = {
+static const unsigned long long freq_range_hpf[5][2] = {
+	{0ULL, 0ULL}, /* bypass */
 	{1750000000ULL, 3550000000ULL},
 	{3400000000ULL, 7250000000ULL},
 	{6600000000, 12000000000},
 	{12500000000, 19900000000}
 };
 
-static const unsigned long long freq_range_lpf[4][2] = {
+static const unsigned long long freq_range_lpf[5][2] = {
+	{U64_MAX, U64_MAX}, /* bypass */
 	{2050000000ULL, 3850000000ULL},
 	{3350000000ULL, 7250000000ULL},
 	{7000000000, 13000000000},
-	{12550000000, 18500000000}
+	{12550000000, 18850000000}
 };
 
 static const struct regmap_config admv8818_regmap_config = {
@@ -121,44 +136,59 @@ static const char * const admv8818_modes[] = {
 
 static int __admv8818_hpf_select(struct admv8818_state *st, u64 freq)
 {
-	unsigned int hpf_step = 0, hpf_band = 0, i, j;
-	u64 freq_step;
-	int ret;
+	int band, state, ret;
+	unsigned int hpf_state = ADMV8818_STATE_MIN, hpf_band = ADMV8818_BAND_BYPASS;
+	u64 freq_error, min_freq_error, freq_corner, freq_step;
 
-	if (freq < freq_range_hpf[0][0])
+	if (freq < freq_range_hpf[ADMV8818_BAND_MIN][ADMV8818_BAND_CORNER_LOW])
 		goto hpf_write;
 
-	if (freq > freq_range_hpf[3][1]) {
-		hpf_step = 15;
-		hpf_band = 4;
-
+	if (freq >= freq_range_hpf[ADMV8818_BAND_MAX][ADMV8818_BAND_CORNER_HIGH]) {
+		hpf_state = ADMV8818_STATE_MAX;
+		hpf_band = ADMV8818_BAND_MAX;
 		goto hpf_write;
 	}
 
-	for (i = 0; i < 4; i++) {
-		freq_step = div_u64((freq_range_hpf[i][1] -
-			freq_range_hpf[i][0]), 15);
+	/* Close HPF frequency gap between 12 and 12.5 GHz */
+	if (freq >= 12000ULL * HZ_PER_MHZ && freq < 12500ULL * HZ_PER_MHZ) {
+		hpf_state = ADMV8818_STATE_MAX;
+		hpf_band = 3;
+		goto hpf_write;
+	}
 
-		if (freq > freq_range_hpf[i][0] &&
-		    (freq < freq_range_hpf[i][1] + freq_step)) {
-			hpf_band = i + 1;
+	min_freq_error = U64_MAX;
+	for (band = ADMV8818_BAND_MIN; band <= ADMV8818_BAND_MAX; band++) {
+		/*
+		 * This (and therefore all other ranges) have a corner
+		 * frequency higher than the target frequency.
+		 */
+		if (freq_range_hpf[band][ADMV8818_BAND_CORNER_LOW] > freq)
+			break;
 
-			for (j = 1; j <= 16; j++) {
-				if (freq < (freq_range_hpf[i][0] + (freq_step * j))) {
-					hpf_step = j - 1;
-					break;
-				}
+		freq_step = freq_range_hpf[band][ADMV8818_BAND_CORNER_HIGH] -
+			    freq_range_hpf[band][ADMV8818_BAND_CORNER_LOW];
+		freq_step = div_u64(freq_step, ADMV8818_NUM_STATES - 1);
+
+		for (state = ADMV8818_STATE_MIN; state <= ADMV8818_STATE_MAX; state++) {
+			freq_corner = freq_range_hpf[band][ADMV8818_BAND_CORNER_LOW] +
+				      freq_step * state;
+
+			/*
+			 * This (and therefore all other states) have a corner
+			 * frequency higher than the target frequency.
+			 */
+			if (freq_corner > freq)
+				break;
+
+			freq_error = freq - freq_corner;
+			if (freq_error < min_freq_error) {
+				min_freq_error = freq_error;
+				hpf_state = state;
+				hpf_band = band;
 			}
-			break;
 		}
 	}
 
-	/* Close HPF frequency gap between 12 and 12.5 GHz */
-	if (freq >= 12000 * HZ_PER_MHZ && freq <= 12500 * HZ_PER_MHZ) {
-		hpf_band = 3;
-		hpf_step = 15;
-	}
-
 hpf_write:
 	ret = regmap_update_bits(st->regmap, ADMV8818_REG_WR0_SW,
 				 ADMV8818_SW_IN_SET_WR0_MSK |
@@ -170,7 +200,7 @@ hpf_write:
 
 	return regmap_update_bits(st->regmap, ADMV8818_REG_WR0_FILTER,
 				  ADMV8818_HPF_WR0_MSK,
-				  FIELD_PREP(ADMV8818_HPF_WR0_MSK, hpf_step));
+				  FIELD_PREP(ADMV8818_HPF_WR0_MSK, hpf_state));
 }
 
 static int admv8818_hpf_select(struct admv8818_state *st, u64 freq)
@@ -186,31 +216,52 @@ static int admv8818_hpf_select(struct admv8818_state *st, u64 freq)
 
 static int __admv8818_lpf_select(struct admv8818_state *st, u64 freq)
 {
-	unsigned int lpf_step = 0, lpf_band = 0, i, j;
-	u64 freq_step;
-	int ret;
+	int band, state, ret;
+	unsigned int lpf_state = ADMV8818_STATE_MIN, lpf_band = ADMV8818_BAND_BYPASS;
+	u64 freq_error, min_freq_error, freq_corner, freq_step;
 
-	if (freq > freq_range_lpf[3][1])
+	if (freq > freq_range_lpf[ADMV8818_BAND_MAX][ADMV8818_BAND_CORNER_HIGH])
 		goto lpf_write;
 
-	if (freq < freq_range_lpf[0][0]) {
-		lpf_band = 1;
-
+	if (freq < freq_range_lpf[ADMV8818_BAND_MIN][ADMV8818_BAND_CORNER_LOW]) {
+		lpf_state = ADMV8818_STATE_MIN;
+		lpf_band = ADMV8818_BAND_MIN;
 		goto lpf_write;
 	}
 
-	for (i = 0; i < 4; i++) {
-		if (freq > freq_range_lpf[i][0] && freq < freq_range_lpf[i][1]) {
-			lpf_band = i + 1;
-			freq_step = div_u64((freq_range_lpf[i][1] - freq_range_lpf[i][0]), 15);
+	min_freq_error = U64_MAX;
+	for (band = ADMV8818_BAND_MAX; band >= ADMV8818_BAND_MIN; --band) {
+		/*
+		 * At this point the highest corner frequency of
+		 * all remaining ranges is below the target.
+		 * LPF corner should be >= the target.
+		 */
+		if (freq > freq_range_lpf[band][ADMV8818_BAND_CORNER_HIGH])
+			break;
+
+		freq_step = freq_range_lpf[band][ADMV8818_BAND_CORNER_HIGH] -
+			    freq_range_lpf[band][ADMV8818_BAND_CORNER_LOW];
+		freq_step = div_u64(freq_step, ADMV8818_NUM_STATES - 1);
+
+		for (state = ADMV8818_STATE_MAX; state >= ADMV8818_STATE_MIN; --state) {
+
+			freq_corner = freq_range_lpf[band][ADMV8818_BAND_CORNER_LOW] +
+				      state * freq_step;
 
-			for (j = 0; j <= 15; j++) {
-				if (freq < (freq_range_lpf[i][0] + (freq_step * j))) {
-					lpf_step = j;
-					break;
-				}
+			/*
+			 * At this point all other states in range will
+			 * place the corner frequency below the target
+			 * LPF corner should >= the target.
+			 */
+			if (freq > freq_corner)
+				break;
+
+			freq_error = freq_corner - freq;
+			if (freq_error < min_freq_error) {
+				min_freq_error = freq_error;
+				lpf_state = state;
+				lpf_band = band;
 			}
-			break;
 		}
 	}
 
@@ -225,7 +276,7 @@ lpf_write:
 
 	return regmap_update_bits(st->regmap, ADMV8818_REG_WR0_FILTER,
 				  ADMV8818_LPF_WR0_MSK,
-				  FIELD_PREP(ADMV8818_LPF_WR0_MSK, lpf_step));
+				  FIELD_PREP(ADMV8818_LPF_WR0_MSK, lpf_state));
 }
 
 static int admv8818_lpf_select(struct admv8818_state *st, u64 freq)
@@ -242,16 +293,28 @@ static int admv8818_lpf_select(struct admv8818_state *st, u64 freq)
 static int admv8818_rfin_band_select(struct admv8818_state *st)
 {
 	int ret;
+	u64 hpf_corner_target, lpf_corner_target;
 
 	st->cf_hz = clk_get_rate(st->clkin);
 
+	/* Check for underflow */
+	if (st->cf_hz > st->hpf_margin_hz)
+		hpf_corner_target = st->cf_hz - st->hpf_margin_hz;
+	else
+		hpf_corner_target = 0;
+
+	/* Check for overflow */
+	lpf_corner_target = st->cf_hz + st->lpf_margin_hz;
+	if (lpf_corner_target < st->cf_hz)
+		lpf_corner_target = U64_MAX;
+
 	mutex_lock(&st->lock);
 
-	ret = __admv8818_hpf_select(st, st->cf_hz);
+	ret = __admv8818_hpf_select(st, hpf_corner_target);
 	if (ret)
 		goto exit;
 
-	ret = __admv8818_lpf_select(st, st->cf_hz);
+	ret = __admv8818_lpf_select(st, lpf_corner_target);
 exit:
 	mutex_unlock(&st->lock);
 	return ret;
@@ -278,8 +341,11 @@ static int __admv8818_read_hpf_freq(struct admv8818_state *st, u64 *hpf_freq)
 
 	hpf_state = FIELD_GET(ADMV8818_HPF_WR0_MSK, data);
 
-	*hpf_freq = div_u64(freq_range_hpf[hpf_band - 1][1] - freq_range_hpf[hpf_band - 1][0], 15);
-	*hpf_freq = freq_range_hpf[hpf_band - 1][0] + (*hpf_freq * hpf_state);
+	*hpf_freq = freq_range_hpf[hpf_band][ADMV8818_BAND_CORNER_HIGH] -
+		    freq_range_hpf[hpf_band][ADMV8818_BAND_CORNER_LOW];
+	*hpf_freq = div_u64(*hpf_freq, ADMV8818_NUM_STATES - 1);
+	*hpf_freq = freq_range_hpf[hpf_band][ADMV8818_BAND_CORNER_LOW] +
+		    (*hpf_freq * hpf_state);
 
 	return ret;
 }
@@ -316,8 +382,11 @@ static int __admv8818_read_lpf_freq(struct admv8818_state *st, u64 *lpf_freq)
 
 	lpf_state = FIELD_GET(ADMV8818_LPF_WR0_MSK, data);
 
-	*lpf_freq = div_u64(freq_range_lpf[lpf_band - 1][1] - freq_range_lpf[lpf_band - 1][0], 15);
-	*lpf_freq = freq_range_lpf[lpf_band - 1][0] + (*lpf_freq * lpf_state);
+	*lpf_freq = freq_range_lpf[lpf_band][ADMV8818_BAND_CORNER_HIGH] -
+		    freq_range_lpf[lpf_band][ADMV8818_BAND_CORNER_LOW];
+	*lpf_freq = div_u64(*lpf_freq, ADMV8818_NUM_STATES - 1);
+	*lpf_freq = freq_range_lpf[lpf_band][ADMV8818_BAND_CORNER_LOW] +
+		    (*lpf_freq * lpf_state);
 
 	return ret;
 }
@@ -333,6 +402,19 @@ static int admv8818_read_lpf_freq(struct admv8818_state *st, u64 *lpf_freq)
 	return ret;
 }
 
+static int admv8818_write_raw_get_fmt(struct iio_dev *indio_dev,
+								struct iio_chan_spec const *chan,
+								long mask)
+{
+	switch (mask) {
+	case IIO_CHAN_INFO_LOW_PASS_FILTER_3DB_FREQUENCY:
+	case IIO_CHAN_INFO_HIGH_PASS_FILTER_3DB_FREQUENCY:
+		return IIO_VAL_INT_64;
+	default:
+		return -EINVAL;
+	}
+}
+
 static int admv8818_write_raw(struct iio_dev *indio_dev,
 			      struct iio_chan_spec const *chan,
 			      int val, int val2, long info)
@@ -341,6 +423,9 @@ static int admv8818_write_raw(struct iio_dev *indio_dev,
 
 	u64 freq = ((u64)val2 << 32 | (u32)val);
 
+	if ((s64)freq < 0)
+		return -EINVAL;
+
 	switch (info) {
 	case IIO_CHAN_INFO_LOW_PASS_FILTER_3DB_FREQUENCY:
 		return admv8818_lpf_select(st, freq);
@@ -502,6 +587,7 @@ set_mode:
 
 static const struct iio_info admv8818_info = {
 	.write_raw = admv8818_write_raw,
+	.write_raw_get_fmt = admv8818_write_raw_get_fmt,
 	.read_raw = admv8818_read_raw,
 	.debugfs_reg_access = &admv8818_reg_access,
 };
@@ -574,21 +660,15 @@ static int admv8818_init(struct admv8818_state *st)
 	struct spi_device *spi = st->spi;
 	unsigned int chip_id;
 
-	ret = regmap_update_bits(st->regmap, ADMV8818_REG_SPI_CONFIG_A,
-				 ADMV8818_SOFTRESET_N_MSK |
-				 ADMV8818_SOFTRESET_MSK,
-				 FIELD_PREP(ADMV8818_SOFTRESET_N_MSK, 1) |
-				 FIELD_PREP(ADMV8818_SOFTRESET_MSK, 1));
+	ret = regmap_write(st->regmap, ADMV8818_REG_SPI_CONFIG_A,
+			   ADMV8818_SOFTRESET_N_MSK | ADMV8818_SOFTRESET_MSK);
 	if (ret) {
 		dev_err(&spi->dev, "ADMV8818 Soft Reset failed.\n");
 		return ret;
 	}
 
-	ret = regmap_update_bits(st->regmap, ADMV8818_REG_SPI_CONFIG_A,
-				 ADMV8818_SDOACTIVE_N_MSK |
-				 ADMV8818_SDOACTIVE_MSK,
-				 FIELD_PREP(ADMV8818_SDOACTIVE_N_MSK, 1) |
-				 FIELD_PREP(ADMV8818_SDOACTIVE_MSK, 1));
+	ret = regmap_write(st->regmap, ADMV8818_REG_SPI_CONFIG_A,
+			   ADMV8818_SDOACTIVE_N_MSK | ADMV8818_SDOACTIVE_MSK);
 	if (ret) {
 		dev_err(&spi->dev, "ADMV8818 SDO Enable failed.\n");
 		return ret;
@@ -647,6 +727,32 @@ static int admv8818_clk_setup(struct admv8818_state *st)
 	return devm_add_action_or_reset(&spi->dev, admv8818_clk_notifier_unreg, st);
 }
 
+static int admv8818_read_properties(struct admv8818_state *st)
+{
+	struct spi_device *spi = st->spi;
+	u32 mhz;
+	int ret;
+
+	ret = device_property_read_u32(&spi->dev, "adi,lpf-margin-mhz", &mhz);
+	if (ret == 0)
+		st->lpf_margin_hz = (u64)mhz * HZ_PER_MHZ;
+	else if (ret == -EINVAL)
+		st->lpf_margin_hz = 0;
+	else
+		return ret;
+
+
+	ret = device_property_read_u32(&spi->dev, "adi,hpf-margin-mhz", &mhz);
+	if (ret == 0)
+		st->hpf_margin_hz = (u64)mhz * HZ_PER_MHZ;
+	else if (ret == -EINVAL)
+		st->hpf_margin_hz = 0;
+	else if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
 static int admv8818_probe(struct spi_device *spi)
 {
 	struct iio_dev *indio_dev;
@@ -678,6 +784,10 @@ static int admv8818_probe(struct spi_device *spi)
 
 	mutex_init(&st->lock);
 
+	ret = admv8818_read_properties(st);
+	if (ret)
+		return ret;
+
 	ret = admv8818_init(st);
 	if (ret)
 		return ret;
diff --git a/drivers/iio/imu/inv_icm42600/inv_icm42600_temp.c b/drivers/iio/imu/inv_icm42600/inv_icm42600_temp.c
index 213cce1c3111..91f0f381082b 100644
--- a/drivers/iio/imu/inv_icm42600/inv_icm42600_temp.c
+++ b/drivers/iio/imu/inv_icm42600/inv_icm42600_temp.c
@@ -67,16 +67,18 @@ int inv_icm42600_temp_read_raw(struct iio_dev *indio_dev,
 		return IIO_VAL_INT;
 	/*
 	 * T°C = (temp / 132.48) + 25
-	 * Tm°C = 1000 * ((temp * 100 / 13248) + 25)
+	 * Tm°C = 1000 * ((temp / 132.48) + 25)
+	 * Tm°C = 7.548309 * temp + 25000
+	 * Tm°C = (temp + 3312) * 7.548309
 	 * scale: 100000 / 13248 ~= 7.548309
-	 * offset: 25000
+	 * offset: 3312
 	 */
 	case IIO_CHAN_INFO_SCALE:
 		*val = 7;
 		*val2 = 548309;
 		return IIO_VAL_INT_PLUS_MICRO;
 	case IIO_CHAN_INFO_OFFSET:
-		*val = 25000;
+		*val = 3312;
 		return IIO_VAL_INT;
 	default:
 		return -EINVAL;
diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c
index 3d3b27f28c9d..273196e647a2 100644
--- a/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c
+++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c
@@ -50,7 +50,7 @@ irqreturn_t inv_mpu6050_read_fifo(int irq, void *p)
 	u16 fifo_count;
 	u32 fifo_period;
 	s64 timestamp;
-	u8 data[INV_MPU6050_OUTPUT_DATA_SIZE];
+	u8 data[INV_MPU6050_OUTPUT_DATA_SIZE] __aligned(8);
 	size_t i, nb;
 
 	mutex_lock(&st->lock);
diff --git a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c
index 0a7cd8c1aa33..8a9d2593576a 100644
--- a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c
+++ b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c
@@ -392,6 +392,9 @@ int st_lsm6dsx_read_fifo(struct st_lsm6dsx_hw *hw)
 	if (fifo_status & cpu_to_le16(ST_LSM6DSX_FIFO_EMPTY_MASK))
 		return 0;
 
+	if (!pattern_len)
+		pattern_len = ST_LSM6DSX_SAMPLE_SIZE;
+
 	fifo_len = (le16_to_cpu(fifo_status) & fifo_diff_mask) *
 		   ST_LSM6DSX_CHAN_SIZE;
 	fifo_len = (fifo_len / pattern_len) * pattern_len;
@@ -623,6 +626,9 @@ int st_lsm6dsx_read_tagged_fifo(struct st_lsm6dsx_hw *hw)
 	if (!fifo_len)
 		return 0;
 
+	if (!pattern_len)
+		pattern_len = ST_LSM6DSX_TAGGED_SAMPLE_SIZE;
+
 	for (read_len = 0; read_len < fifo_len; read_len += pattern_len) {
 		err = st_lsm6dsx_read_block(hw,
 					    ST_LSM6DSX_REG_FIFO_OUT_TAG_ADDR,
diff --git a/drivers/iio/industrialio-backend.c b/drivers/iio/industrialio-backend.c
index fb34a8e4d04e..a3abcdeb6281 100644
--- a/drivers/iio/industrialio-backend.c
+++ b/drivers/iio/industrialio-backend.c
@@ -155,10 +155,15 @@ static ssize_t iio_backend_debugfs_write_reg(struct file *file,
 	ssize_t rc;
 	int ret;
 
-	rc = simple_write_to_buffer(buf, sizeof(buf), ppos, userbuf, count);
+	if (count >= sizeof(buf))
+		return -ENOSPC;
+
+	rc = simple_write_to_buffer(buf, sizeof(buf) - 1, ppos, userbuf, count);
 	if (rc < 0)
 		return rc;
 
+	buf[rc] = '\0';
+
 	ret = sscanf(buf, "%i %i", &back->cached_reg_addr, &val);
 
 	switch (ret) {
diff --git a/drivers/iio/light/apds9306.c b/drivers/iio/light/apds9306.c
index 079e02be1005..7f9d6cac8adb 100644
--- a/drivers/iio/light/apds9306.c
+++ b/drivers/iio/light/apds9306.c
@@ -108,11 +108,11 @@ static const struct part_id_gts_multiplier apds9306_gts_mul[] = {
 	{
 		.part_id = 0xB1,
 		.max_scale_int = 16,
-		.max_scale_nano = 3264320,
+		.max_scale_nano = 326432000,
 	}, {
 		.part_id = 0xB3,
 		.max_scale_int = 14,
-		.max_scale_nano = 9712000,
+		.max_scale_nano = 97120000,
 	},
 };
 
diff --git a/drivers/iio/light/as73211.c b/drivers/iio/light/as73211.c
index be0068081ebb..11fbdcdd26d6 100644
--- a/drivers/iio/light/as73211.c
+++ b/drivers/iio/light/as73211.c
@@ -177,6 +177,12 @@ struct as73211_data {
 	BIT(AS73211_SCAN_INDEX_TEMP) | \
 	AS73211_SCAN_MASK_COLOR)
 
+static const unsigned long as73211_scan_masks[] = {
+	AS73211_SCAN_MASK_COLOR,
+	AS73211_SCAN_MASK_ALL,
+	0
+};
+
 static const struct iio_chan_spec as73211_channels[] = {
 	{
 		.type = IIO_TEMP,
@@ -672,9 +678,12 @@ static irqreturn_t as73211_trigger_handler(int irq __always_unused, void *p)
 
 		/* AS73211 starts reading at address 2 */
 		ret = i2c_master_recv(data->client,
-				(char *)&scan.chan[1], 3 * sizeof(scan.chan[1]));
+				(char *)&scan.chan[0], 3 * sizeof(scan.chan[0]));
 		if (ret < 0)
 			goto done;
+
+		/* Avoid pushing uninitialized data */
+		scan.chan[3] = 0;
 	}
 
 	if (data_result) {
@@ -682,9 +691,15 @@ static irqreturn_t as73211_trigger_handler(int irq __always_unused, void *p)
 		 * Saturate all channels (in case of overflows). Temperature channel
 		 * is not affected by overflows.
 		 */
-		scan.chan[1] = cpu_to_le16(U16_MAX);
-		scan.chan[2] = cpu_to_le16(U16_MAX);
-		scan.chan[3] = cpu_to_le16(U16_MAX);
+		if (*indio_dev->active_scan_mask == AS73211_SCAN_MASK_ALL) {
+			scan.chan[1] = cpu_to_le16(U16_MAX);
+			scan.chan[2] = cpu_to_le16(U16_MAX);
+			scan.chan[3] = cpu_to_le16(U16_MAX);
+		} else {
+			scan.chan[0] = cpu_to_le16(U16_MAX);
+			scan.chan[1] = cpu_to_le16(U16_MAX);
+			scan.chan[2] = cpu_to_le16(U16_MAX);
+		}
 	}
 
 	iio_push_to_buffers_with_timestamp(indio_dev, &scan, iio_get_time_ns(indio_dev));
@@ -758,6 +773,7 @@ static int as73211_probe(struct i2c_client *client)
 	indio_dev->channels = data->spec_dev->channels;
 	indio_dev->num_channels = data->spec_dev->num_channels;
 	indio_dev->modes = INDIO_DIRECT_MODE;
+	indio_dev->available_scan_masks = as73211_scan_masks;
 
 	ret = i2c_smbus_read_byte_data(data->client, AS73211_REG_OSR);
 	if (ret < 0)
diff --git a/drivers/iio/light/hid-sensor-prox.c b/drivers/iio/light/hid-sensor-prox.c
index 26c481d2998c..25901d91a613 100644
--- a/drivers/iio/light/hid-sensor-prox.c
+++ b/drivers/iio/light/hid-sensor-prox.c
@@ -102,8 +102,7 @@ static int prox_read_raw(struct iio_dev *indio_dev,
 		ret_type = prox_state->scale_precision;
 		break;
 	case IIO_CHAN_INFO_OFFSET:
-		*val = hid_sensor_convert_exponent(
-				prox_state->prox_attr.unit_expo);
+		*val = 0;
 		ret_type = IIO_VAL_INT;
 		break;
 	case IIO_CHAN_INFO_SAMP_FREQ:
@@ -227,6 +226,11 @@ static int prox_parse_report(struct platform_device *pdev,
 	dev_dbg(&pdev->dev, "prox %x:%x\n", st->prox_attr.index,
 			st->prox_attr.report_id);
 
+	st->scale_precision = hid_sensor_format_scale(hsdev->usage,
+						      &st->prox_attr,
+						      &st->scale_pre_decml,
+						      &st->scale_post_decml);
+
 	return ret;
 }
 
diff --git a/drivers/iio/light/opt3001.c b/drivers/iio/light/opt3001.c
index 176e54bb48c3..d5ca75b12883 100644
--- a/drivers/iio/light/opt3001.c
+++ b/drivers/iio/light/opt3001.c
@@ -692,8 +692,9 @@ static irqreturn_t opt3001_irq(int irq, void *_iio)
 	struct opt3001 *opt = iio_priv(iio);
 	int ret;
 	bool wake_result_ready_queue = false;
+	bool ok_to_ignore_lock = opt->ok_to_ignore_lock;
 
-	if (!opt->ok_to_ignore_lock)
+	if (!ok_to_ignore_lock)
 		mutex_lock(&opt->lock);
 
 	ret = i2c_smbus_read_word_swapped(opt->client, OPT3001_CONFIGURATION);
@@ -730,7 +731,7 @@ static irqreturn_t opt3001_irq(int irq, void *_iio)
 	}
 
 out:
-	if (!opt->ok_to_ignore_lock)
+	if (!ok_to_ignore_lock)
 		mutex_unlock(&opt->lock);
 
 	if (wake_result_ready_queue)
diff --git a/drivers/iio/light/veml6075.c b/drivers/iio/light/veml6075.c
index 05d4c0e9015d..859891e8f115 100644
--- a/drivers/iio/light/veml6075.c
+++ b/drivers/iio/light/veml6075.c
@@ -195,13 +195,17 @@ static int veml6075_read_uv_direct(struct veml6075_data *data, int chan,
 
 static int veml6075_read_int_time_index(struct veml6075_data *data)
 {
-	int ret, conf;
+	int ret, conf, int_index;
 
 	ret = regmap_read(data->regmap, VEML6075_CMD_CONF, &conf);
 	if (ret < 0)
 		return ret;
 
-	return FIELD_GET(VEML6075_CONF_IT, conf);
+	int_index = FIELD_GET(VEML6075_CONF_IT, conf);
+	if (int_index >= ARRAY_SIZE(veml6075_it_ms))
+		return -EINVAL;
+
+	return int_index;
 }
 
 static int veml6075_read_int_time_ms(struct veml6075_data *data, int *val)
diff --git a/drivers/iio/pressure/mprls0025pa.h b/drivers/iio/pressure/mprls0025pa.h
index 9d5c30afa9d6..d62a018eaff3 100644
--- a/drivers/iio/pressure/mprls0025pa.h
+++ b/drivers/iio/pressure/mprls0025pa.h
@@ -34,16 +34,6 @@ struct iio_dev;
 struct mpr_data;
 struct mpr_ops;
 
-/**
- * struct mpr_chan
- * @pres: pressure value
- * @ts: timestamp
- */
-struct mpr_chan {
-	s32 pres;
-	s64 ts;
-};
-
 enum mpr_func_id {
 	MPR_FUNCTION_A,
 	MPR_FUNCTION_B,
@@ -69,6 +59,8 @@ enum mpr_func_id {
  *       reading in a loop until data is ready
  * @completion: handshake from irq to read
  * @chan: channel values for buffered mode
+ * @chan.pres: pressure value
+ * @chan.ts: timestamp
  * @buffer: raw conversion data
  */
 struct mpr_data {
@@ -87,7 +79,10 @@ struct mpr_data {
 	struct gpio_desc	*gpiod_reset;
 	int			irq;
 	struct completion	completion;
-	struct mpr_chan		chan;
+	struct {
+		s32 pres;
+		aligned_s64 ts;
+	} chan;
 	u8	    buffer[MPR_MEASUREMENT_RD_SIZE] __aligned(IIO_DMA_MINALIGN);
 };
 
diff --git a/drivers/iio/pressure/zpa2326.c b/drivers/iio/pressure/zpa2326.c
index b4c6c7c47256..8fae58db1d63 100644
--- a/drivers/iio/pressure/zpa2326.c
+++ b/drivers/iio/pressure/zpa2326.c
@@ -582,7 +582,7 @@ static int zpa2326_fill_sample_buffer(struct iio_dev               *indio_dev,
 	struct {
 		u32 pressure;
 		u16 temperature;
-		u64 timestamp;
+		aligned_s64 timestamp;
 	}   sample;
 	int err;
 
diff --git a/drivers/iio/temperature/maxim_thermocouple.c b/drivers/iio/temperature/maxim_thermocouple.c
index c28a7a6dea5f..555a61e2f3fd 100644
--- a/drivers/iio/temperature/maxim_thermocouple.c
+++ b/drivers/iio/temperature/maxim_thermocouple.c
@@ -121,9 +121,9 @@ static const struct maxim_thermocouple_chip maxim_thermocouple_chips[] = {
 struct maxim_thermocouple_data {
 	struct spi_device *spi;
 	const struct maxim_thermocouple_chip *chip;
+	char tc_type;
 
 	u8 buffer[16] __aligned(IIO_DMA_MINALIGN);
-	char tc_type;
 };
 
 static int maxim_thermocouple_read(struct maxim_thermocouple_data *data,
diff --git a/drivers/infiniband/core/cache.c b/drivers/infiniband/core/cache.c
index b7c078b7f7cf..a1291f475466 100644
--- a/drivers/infiniband/core/cache.c
+++ b/drivers/infiniband/core/cache.c
@@ -582,8 +582,8 @@ static int __ib_cache_gid_add(struct ib_device *ib_dev, u32 port,
 out_unlock:
 	mutex_unlock(&table->lock);
 	if (ret)
-		pr_warn("%s: unable to add gid %pI6 error=%d\n",
-			__func__, gid->raw, ret);
+		pr_warn_ratelimited("%s: unable to add gid %pI6 error=%d\n",
+				    __func__, gid->raw, ret);
 	return ret;
 }
 
diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c
index 07fb8d3c037f..d45e3909dafe 100644
--- a/drivers/infiniband/core/cm.c
+++ b/drivers/infiniband/core/cm.c
@@ -166,7 +166,7 @@ struct cm_port {
 struct cm_device {
 	struct kref kref;
 	struct list_head list;
-	spinlock_t mad_agent_lock;
+	rwlock_t mad_agent_lock;
 	struct ib_device *ib_device;
 	u8 ack_delay;
 	int going_down;
@@ -284,7 +284,7 @@ static struct ib_mad_send_buf *cm_alloc_msg(struct cm_id_private *cm_id_priv)
 	if (!cm_id_priv->av.port)
 		return ERR_PTR(-EINVAL);
 
-	spin_lock(&cm_id_priv->av.port->cm_dev->mad_agent_lock);
+	read_lock(&cm_id_priv->av.port->cm_dev->mad_agent_lock);
 	mad_agent = cm_id_priv->av.port->mad_agent;
 	if (!mad_agent) {
 		m = ERR_PTR(-EINVAL);
@@ -315,7 +315,7 @@ static struct ib_mad_send_buf *cm_alloc_msg(struct cm_id_private *cm_id_priv)
 	m->context[0] = cm_id_priv;
 
 out:
-	spin_unlock(&cm_id_priv->av.port->cm_dev->mad_agent_lock);
+	read_unlock(&cm_id_priv->av.port->cm_dev->mad_agent_lock);
 	return m;
 }
 
@@ -1294,10 +1294,10 @@ static __be64 cm_form_tid(struct cm_id_private *cm_id_priv)
 	if (!cm_id_priv->av.port)
 		return cpu_to_be64(low_tid);
 
-	spin_lock(&cm_id_priv->av.port->cm_dev->mad_agent_lock);
+	read_lock(&cm_id_priv->av.port->cm_dev->mad_agent_lock);
 	if (cm_id_priv->av.port->mad_agent)
 		hi_tid = ((u64)cm_id_priv->av.port->mad_agent->hi_tid) << 32;
-	spin_unlock(&cm_id_priv->av.port->cm_dev->mad_agent_lock);
+	read_unlock(&cm_id_priv->av.port->cm_dev->mad_agent_lock);
 	return cpu_to_be64(hi_tid | low_tid);
 }
 
@@ -4374,7 +4374,7 @@ static int cm_add_one(struct ib_device *ib_device)
 		return -ENOMEM;
 
 	kref_init(&cm_dev->kref);
-	spin_lock_init(&cm_dev->mad_agent_lock);
+	rwlock_init(&cm_dev->mad_agent_lock);
 	cm_dev->ib_device = ib_device;
 	cm_dev->ack_delay = ib_device->attrs.local_ca_ack_delay;
 	cm_dev->going_down = 0;
@@ -4490,9 +4490,9 @@ static void cm_remove_one(struct ib_device *ib_device, void *client_data)
 		 * The above ensures no call paths from the work are running,
 		 * the remaining paths all take the mad_agent_lock.
 		 */
-		spin_lock(&cm_dev->mad_agent_lock);
+		write_lock(&cm_dev->mad_agent_lock);
 		port->mad_agent = NULL;
-		spin_unlock(&cm_dev->mad_agent_lock);
+		write_unlock(&cm_dev->mad_agent_lock);
 		ib_unregister_mad_agent(mad_agent);
 		ib_port_unregister_client_groups(ib_device, i,
 						 cm_counter_groups);
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 91db10515d74..81bc24a346d3 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -72,6 +72,8 @@ static const char * const cma_events[] = {
 static void cma_iboe_set_mgid(struct sockaddr *addr, union ib_gid *mgid,
 			      enum ib_gid_type gid_type);
 
+static void cma_netevent_work_handler(struct work_struct *_work);
+
 const char *__attribute_const__ rdma_event_msg(enum rdma_cm_event_type event)
 {
 	size_t index = event;
@@ -1033,6 +1035,7 @@ __rdma_create_id(struct net *net, rdma_cm_event_handler event_handler,
 	get_random_bytes(&id_priv->seq_num, sizeof id_priv->seq_num);
 	id_priv->id.route.addr.dev_addr.net = get_net(net);
 	id_priv->seq_num &= 0x00ffffff;
+	INIT_WORK(&id_priv->id.net_work, cma_netevent_work_handler);
 
 	rdma_restrack_new(&id_priv->res, RDMA_RESTRACK_CM_ID);
 	if (parent)
@@ -5227,9 +5230,9 @@ static int cma_netevent_callback(struct notifier_block *self,
 		if (!memcmp(current_id->id.route.addr.dev_addr.dst_dev_addr,
 			   neigh->ha, ETH_ALEN))
 			continue;
-		INIT_WORK(&current_id->id.net_work, cma_netevent_work_handler);
 		cma_id_get(current_id);
-		queue_work(cma_wq, &current_id->id.net_work);
+		if (!queue_work(cma_wq, &current_id->id.net_work))
+			cma_id_put(current_id);
 	}
 out:
 	spin_unlock_irqrestore(&id_table_lock, flags);
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index e029401b5680..df2aa15a5bc9 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -544,6 +544,8 @@ static struct class ib_class = {
 static void rdma_init_coredev(struct ib_core_device *coredev,
 			      struct ib_device *dev, struct net *net)
 {
+	bool is_full_dev = &dev->coredev == coredev;
+
 	/* This BUILD_BUG_ON is intended to catch layout change
 	 * of union of ib_core_device and device.
 	 * dev must be the first element as ib_core and providers
@@ -555,6 +557,13 @@ static void rdma_init_coredev(struct ib_core_device *coredev,
 
 	coredev->dev.class = &ib_class;
 	coredev->dev.groups = dev->groups;
+
+	/*
+	 * Don't expose hw counters outside of the init namespace.
+	 */
+	if (!is_full_dev && dev->hw_stats_attr_index)
+		coredev->dev.groups[dev->hw_stats_attr_index] = NULL;
+
 	device_initialize(&coredev->dev);
 	coredev->owner = dev;
 	INIT_LIST_HEAD(&coredev->port_list);
@@ -1357,9 +1366,14 @@ static void ib_device_notify_register(struct ib_device *device)
 	u32 port;
 	int ret;
 
+	down_read(&devices_rwsem);
+
+	/* Mark for userspace that device is ready */
+	kobject_uevent(&device->dev.kobj, KOBJ_ADD);
+
 	ret = rdma_nl_notify_event(device, 0, RDMA_REGISTER_EVENT);
 	if (ret)
-		return;
+		goto out;
 
 	rdma_for_each_port(device, port) {
 		netdev = ib_device_get_netdev(device, port);
@@ -1370,8 +1384,11 @@ static void ib_device_notify_register(struct ib_device *device)
 					   RDMA_NETDEV_ATTACH_EVENT);
 		dev_put(netdev);
 		if (ret)
-			return;
+			goto out;
 	}
+
+out:
+	up_read(&devices_rwsem);
 }
 
 /**
@@ -1470,10 +1487,9 @@ int ib_register_device(struct ib_device *device, const char *name,
 		return ret;
 	}
 	dev_set_uevent_suppress(&device->dev, false);
-	/* Mark for userspace that device is ready */
-	kobject_uevent(&device->dev.kobj, KOBJ_ADD);
 
 	ib_device_notify_register(device);
+
 	ib_device_put(device);
 
 	return 0;
diff --git a/drivers/infiniband/core/iwcm.c b/drivers/infiniband/core/iwcm.c
index 7e3a55349e10..96a678250e55 100644
--- a/drivers/infiniband/core/iwcm.c
+++ b/drivers/infiniband/core/iwcm.c
@@ -366,12 +366,9 @@ EXPORT_SYMBOL(iw_cm_disconnect);
 /*
  * CM_ID <-- DESTROYING
  *
- * Clean up all resources associated with the connection and release
- * the initial reference taken by iw_create_cm_id.
- *
- * Returns true if and only if the last cm_id_priv reference has been dropped.
+ * Clean up all resources associated with the connection.
  */
-static bool destroy_cm_id(struct iw_cm_id *cm_id)
+static void destroy_cm_id(struct iw_cm_id *cm_id)
 {
 	struct iwcm_id_private *cm_id_priv;
 	struct ib_qp *qp;
@@ -440,20 +437,22 @@ static bool destroy_cm_id(struct iw_cm_id *cm_id)
 		iwpm_remove_mapinfo(&cm_id->local_addr, &cm_id->m_local_addr);
 		iwpm_remove_mapping(&cm_id->local_addr, RDMA_NL_IWCM);
 	}
-
-	return iwcm_deref_id(cm_id_priv);
 }
 
 /*
- * This function is only called by the application thread and cannot
- * be called by the event thread. The function will wait for all
- * references to be released on the cm_id and then kfree the cm_id
- * object.
+ * Destroy cm_id. If the cm_id still has other references, wait for all
+ * references to be released on the cm_id and then release the initial
+ * reference taken by iw_create_cm_id.
  */
 void iw_destroy_cm_id(struct iw_cm_id *cm_id)
 {
-	if (!destroy_cm_id(cm_id))
+	struct iwcm_id_private *cm_id_priv;
+
+	cm_id_priv = container_of(cm_id, struct iwcm_id_private, id);
+	destroy_cm_id(cm_id);
+	if (refcount_read(&cm_id_priv->refcount) > 1)
 		flush_workqueue(iwcm_wq);
+	iwcm_deref_id(cm_id_priv);
 }
 EXPORT_SYMBOL(iw_destroy_cm_id);
 
@@ -1033,8 +1032,10 @@ static void cm_work_handler(struct work_struct *_work)
 
 		if (!test_bit(IWCM_F_DROP_EVENTS, &cm_id_priv->flags)) {
 			ret = process_event(cm_id_priv, &levent);
-			if (ret)
-				WARN_ON_ONCE(destroy_cm_id(&cm_id_priv->id));
+			if (ret) {
+				destroy_cm_id(&cm_id_priv->id);
+				WARN_ON_ONCE(iwcm_deref_id(cm_id_priv));
+			}
 		} else
 			pr_debug("dropping event %d\n", levent.event);
 		if (iwcm_deref_id(cm_id_priv))
diff --git a/drivers/infiniband/core/mad.c b/drivers/infiniband/core/mad.c
index 1fd54d5c4dd8..73f3a0b9a54b 100644
--- a/drivers/infiniband/core/mad.c
+++ b/drivers/infiniband/core/mad.c
@@ -2671,11 +2671,11 @@ static int ib_mad_post_receive_mads(struct ib_mad_qp_info *qp_info,
 				    struct ib_mad_private *mad)
 {
 	unsigned long flags;
-	int post, ret;
 	struct ib_mad_private *mad_priv;
 	struct ib_sge sg_list;
 	struct ib_recv_wr recv_wr;
 	struct ib_mad_queue *recv_queue = &qp_info->recv_queue;
+	int ret = 0;
 
 	/* Initialize common scatter list fields */
 	sg_list.lkey = qp_info->port_priv->pd->local_dma_lkey;
@@ -2685,7 +2685,7 @@ static int ib_mad_post_receive_mads(struct ib_mad_qp_info *qp_info,
 	recv_wr.sg_list = &sg_list;
 	recv_wr.num_sge = 1;
 
-	do {
+	while (true) {
 		/* Allocate and map receive buffer */
 		if (mad) {
 			mad_priv = mad;
@@ -2693,10 +2693,8 @@ static int ib_mad_post_receive_mads(struct ib_mad_qp_info *qp_info,
 		} else {
 			mad_priv = alloc_mad_private(port_mad_size(qp_info->port_priv),
 						     GFP_ATOMIC);
-			if (!mad_priv) {
-				ret = -ENOMEM;
-				break;
-			}
+			if (!mad_priv)
+				return -ENOMEM;
 		}
 		sg_list.length = mad_priv_dma_size(mad_priv);
 		sg_list.addr = ib_dma_map_single(qp_info->port_priv->device,
@@ -2705,37 +2703,41 @@ static int ib_mad_post_receive_mads(struct ib_mad_qp_info *qp_info,
 						 DMA_FROM_DEVICE);
 		if (unlikely(ib_dma_mapping_error(qp_info->port_priv->device,
 						  sg_list.addr))) {
-			kfree(mad_priv);
 			ret = -ENOMEM;
-			break;
+			goto free_mad_priv;
 		}
 		mad_priv->header.mapping = sg_list.addr;
 		mad_priv->header.mad_list.mad_queue = recv_queue;
 		mad_priv->header.mad_list.cqe.done = ib_mad_recv_done;
 		recv_wr.wr_cqe = &mad_priv->header.mad_list.cqe;
-
-		/* Post receive WR */
 		spin_lock_irqsave(&recv_queue->lock, flags);
-		post = (++recv_queue->count < recv_queue->max_active);
-		list_add_tail(&mad_priv->header.mad_list.list, &recv_queue->list);
+		if (recv_queue->count >= recv_queue->max_active) {
+			/* Fully populated the receive queue */
+			spin_unlock_irqrestore(&recv_queue->lock, flags);
+			break;
+		}
+		recv_queue->count++;
+		list_add_tail(&mad_priv->header.mad_list.list,
+			      &recv_queue->list);
 		spin_unlock_irqrestore(&recv_queue->lock, flags);
+
 		ret = ib_post_recv(qp_info->qp, &recv_wr, NULL);
 		if (ret) {
 			spin_lock_irqsave(&recv_queue->lock, flags);
 			list_del(&mad_priv->header.mad_list.list);
 			recv_queue->count--;
 			spin_unlock_irqrestore(&recv_queue->lock, flags);
-			ib_dma_unmap_single(qp_info->port_priv->device,
-					    mad_priv->header.mapping,
-					    mad_priv_dma_size(mad_priv),
-					    DMA_FROM_DEVICE);
-			kfree(mad_priv);
 			dev_err(&qp_info->port_priv->device->dev,
 				"ib_post_recv failed: %d\n", ret);
 			break;
 		}
-	} while (post);
+	}
 
+	ib_dma_unmap_single(qp_info->port_priv->device,
+			    mad_priv->header.mapping,
+			    mad_priv_dma_size(mad_priv), DMA_FROM_DEVICE);
+free_mad_priv:
+	kfree(mad_priv);
 	return ret;
 }
 
diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c
index f12189986303..fef11a80647c 100644
--- a/drivers/infiniband/core/nldev.c
+++ b/drivers/infiniband/core/nldev.c
@@ -1468,10 +1468,11 @@ static const struct nldev_fill_res_entry fill_entries[RDMA_RESTRACK_MAX] = {
 
 };
 
-static int res_get_common_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
-			       struct netlink_ext_ack *extack,
-			       enum rdma_restrack_type res_type,
-			       res_fill_func_t fill_func)
+static noinline_for_stack int
+res_get_common_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
+		    struct netlink_ext_ack *extack,
+		    enum rdma_restrack_type res_type,
+		    res_fill_func_t fill_func)
 {
 	const struct nldev_fill_res_entry *fe = &fill_entries[res_type];
 	struct nlattr *tb[RDMA_NLDEV_ATTR_MAX];
@@ -2256,10 +2257,10 @@ err:
 	return ret;
 }
 
-static int stat_get_doit_default_counter(struct sk_buff *skb,
-					 struct nlmsghdr *nlh,
-					 struct netlink_ext_ack *extack,
-					 struct nlattr *tb[])
+static noinline_for_stack int
+stat_get_doit_default_counter(struct sk_buff *skb, struct nlmsghdr *nlh,
+			      struct netlink_ext_ack *extack,
+			      struct nlattr *tb[])
 {
 	struct rdma_hw_stats *stats;
 	struct nlattr *table_attr;
@@ -2349,8 +2350,9 @@ err:
 	return ret;
 }
 
-static int stat_get_doit_qp(struct sk_buff *skb, struct nlmsghdr *nlh,
-			    struct netlink_ext_ack *extack, struct nlattr *tb[])
+static noinline_for_stack int
+stat_get_doit_qp(struct sk_buff *skb, struct nlmsghdr *nlh,
+		 struct netlink_ext_ack *extack, struct nlattr *tb[])
 
 {
 	static enum rdma_nl_counter_mode mode;
diff --git a/drivers/infiniband/core/sysfs.c b/drivers/infiniband/core/sysfs.c
index 9f97bef02149..210092b9bf17 100644
--- a/drivers/infiniband/core/sysfs.c
+++ b/drivers/infiniband/core/sysfs.c
@@ -988,6 +988,7 @@ int ib_setup_device_attrs(struct ib_device *ibdev)
 	for (i = 0; i != ARRAY_SIZE(ibdev->groups); i++)
 		if (!ibdev->groups[i]) {
 			ibdev->groups[i] = &data->group;
+			ibdev->hw_stats_attr_index = i;
 			return 0;
 		}
 	WARN(true, "struct ib_device->groups is too small");
diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c
index 07c571c7b699..c5b686394760 100644
--- a/drivers/infiniband/core/umem.c
+++ b/drivers/infiniband/core/umem.c
@@ -80,9 +80,12 @@ unsigned long ib_umem_find_best_pgsz(struct ib_umem *umem,
 				     unsigned long pgsz_bitmap,
 				     unsigned long virt)
 {
-	struct scatterlist *sg;
+	unsigned long curr_len = 0;
+	dma_addr_t curr_base = ~0;
 	unsigned long va, pgoff;
+	struct scatterlist *sg;
 	dma_addr_t mask;
+	dma_addr_t end;
 	int i;
 
 	umem->iova = va = virt;
@@ -107,17 +110,30 @@ unsigned long ib_umem_find_best_pgsz(struct ib_umem *umem,
 	pgoff = umem->address & ~PAGE_MASK;
 
 	for_each_sgtable_dma_sg(&umem->sgt_append.sgt, sg, i) {
-		/* Walk SGL and reduce max page size if VA/PA bits differ
-		 * for any address.
+		/* If the current entry is physically contiguous with the previous
+		 * one, no need to take its start addresses into consideration.
 		 */
-		mask |= (sg_dma_address(sg) + pgoff) ^ va;
+		if (check_add_overflow(curr_base, curr_len, &end) ||
+		    end != sg_dma_address(sg)) {
+
+			curr_base = sg_dma_address(sg);
+			curr_len = 0;
+
+			/* Reduce max page size if VA/PA bits differ */
+			mask |= (curr_base + pgoff) ^ va;
+
+			/* The alignment of any VA matching a discontinuity point
+			* in the physical memory sets the maximum possible page
+			* size as this must be a starting point of a new page that
+			* needs to be aligned.
+			*/
+			if (i != 0)
+				mask |= va;
+		}
+
+		curr_len += sg_dma_len(sg);
 		va += sg_dma_len(sg) - pgoff;
-		/* Except for the last entry, the ending iova alignment sets
-		 * the maximum possible page size as the low bits of the iova
-		 * must be zero when starting the next chunk.
-		 */
-		if (i != (umem->sgt_append.sgt.nents - 1))
-			mask |= va;
+
 		pgoff = 0;
 	}
 
diff --git a/drivers/infiniband/core/umem_odp.c b/drivers/infiniband/core/umem_odp.c
index e9fa22d31c23..c48ef6083020 100644
--- a/drivers/infiniband/core/umem_odp.c
+++ b/drivers/infiniband/core/umem_odp.c
@@ -76,12 +76,14 @@ static inline int ib_init_umem_odp(struct ib_umem_odp *umem_odp,
 
 		npfns = (end - start) >> PAGE_SHIFT;
 		umem_odp->pfn_list = kvcalloc(
-			npfns, sizeof(*umem_odp->pfn_list), GFP_KERNEL);
+			npfns, sizeof(*umem_odp->pfn_list),
+			GFP_KERNEL | __GFP_NOWARN);
 		if (!umem_odp->pfn_list)
 			return -ENOMEM;
 
 		umem_odp->dma_list = kvcalloc(
-			ndmas, sizeof(*umem_odp->dma_list), GFP_KERNEL);
+			ndmas, sizeof(*umem_odp->dma_list),
+			GFP_KERNEL | __GFP_NOWARN);
 		if (!umem_odp->dma_list) {
 			ret = -ENOMEM;
 			goto out_pfn_list;
diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index edef79daed3f..535bb99ed9f5 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -718,8 +718,8 @@ static int ib_uverbs_reg_mr(struct uverbs_attr_bundle *attrs)
 		goto err_free;
 
 	pd = uobj_get_obj_read(pd, UVERBS_OBJECT_PD, cmd.pd_handle, attrs);
-	if (!pd) {
-		ret = -EINVAL;
+	if (IS_ERR(pd)) {
+		ret = PTR_ERR(pd);
 		goto err_free;
 	}
 
@@ -809,8 +809,8 @@ static int ib_uverbs_rereg_mr(struct uverbs_attr_bundle *attrs)
 	if (cmd.flags & IB_MR_REREG_PD) {
 		new_pd = uobj_get_obj_read(pd, UVERBS_OBJECT_PD, cmd.pd_handle,
 					   attrs);
-		if (!new_pd) {
-			ret = -EINVAL;
+		if (IS_ERR(new_pd)) {
+			ret = PTR_ERR(new_pd);
 			goto put_uobjs;
 		}
 	} else {
@@ -919,8 +919,8 @@ static int ib_uverbs_alloc_mw(struct uverbs_attr_bundle *attrs)
 		return PTR_ERR(uobj);
 
 	pd = uobj_get_obj_read(pd, UVERBS_OBJECT_PD, cmd.pd_handle, attrs);
-	if (!pd) {
-		ret = -EINVAL;
+	if (IS_ERR(pd)) {
+		ret = PTR_ERR(pd);
 		goto err_free;
 	}
 
@@ -1127,8 +1127,8 @@ static int ib_uverbs_resize_cq(struct uverbs_attr_bundle *attrs)
 		return ret;
 
 	cq = uobj_get_obj_read(cq, UVERBS_OBJECT_CQ, cmd.cq_handle, attrs);
-	if (!cq)
-		return -EINVAL;
+	if (IS_ERR(cq))
+		return PTR_ERR(cq);
 
 	ret = cq->device->ops.resize_cq(cq, cmd.cqe, &attrs->driver_udata);
 	if (ret)
@@ -1189,8 +1189,8 @@ static int ib_uverbs_poll_cq(struct uverbs_attr_bundle *attrs)
 		return ret;
 
 	cq = uobj_get_obj_read(cq, UVERBS_OBJECT_CQ, cmd.cq_handle, attrs);
-	if (!cq)
-		return -EINVAL;
+	if (IS_ERR(cq))
+		return PTR_ERR(cq);
 
 	/* we copy a struct ib_uverbs_poll_cq_resp to user space */
 	header_ptr = attrs->ucore.outbuf;
@@ -1238,8 +1238,8 @@ static int ib_uverbs_req_notify_cq(struct uverbs_attr_bundle *attrs)
 		return ret;
 
 	cq = uobj_get_obj_read(cq, UVERBS_OBJECT_CQ, cmd.cq_handle, attrs);
-	if (!cq)
-		return -EINVAL;
+	if (IS_ERR(cq))
+		return PTR_ERR(cq);
 
 	ib_req_notify_cq(cq, cmd.solicited_only ?
 			 IB_CQ_SOLICITED : IB_CQ_NEXT_COMP);
@@ -1321,8 +1321,8 @@ static int create_qp(struct uverbs_attr_bundle *attrs,
 		ind_tbl = uobj_get_obj_read(rwq_ind_table,
 					    UVERBS_OBJECT_RWQ_IND_TBL,
 					    cmd->rwq_ind_tbl_handle, attrs);
-		if (!ind_tbl) {
-			ret = -EINVAL;
+		if (IS_ERR(ind_tbl)) {
+			ret = PTR_ERR(ind_tbl);
 			goto err_put;
 		}
 
@@ -1360,8 +1360,10 @@ static int create_qp(struct uverbs_attr_bundle *attrs,
 			if (cmd->is_srq) {
 				srq = uobj_get_obj_read(srq, UVERBS_OBJECT_SRQ,
 							cmd->srq_handle, attrs);
-				if (!srq || srq->srq_type == IB_SRQT_XRC) {
-					ret = -EINVAL;
+				if (IS_ERR(srq) ||
+				    srq->srq_type == IB_SRQT_XRC) {
+					ret = IS_ERR(srq) ? PTR_ERR(srq) :
+								  -EINVAL;
 					goto err_put;
 				}
 			}
@@ -1371,23 +1373,29 @@ static int create_qp(struct uverbs_attr_bundle *attrs,
 					rcq = uobj_get_obj_read(
 						cq, UVERBS_OBJECT_CQ,
 						cmd->recv_cq_handle, attrs);
-					if (!rcq) {
-						ret = -EINVAL;
+					if (IS_ERR(rcq)) {
+						ret = PTR_ERR(rcq);
 						goto err_put;
 					}
 				}
 			}
 		}
 
-		if (has_sq)
+		if (has_sq) {
 			scq = uobj_get_obj_read(cq, UVERBS_OBJECT_CQ,
 						cmd->send_cq_handle, attrs);
+			if (IS_ERR(scq)) {
+				ret = PTR_ERR(scq);
+				goto err_put;
+			}
+		}
+
 		if (!ind_tbl && cmd->qp_type != IB_QPT_XRC_INI)
 			rcq = rcq ?: scq;
 		pd = uobj_get_obj_read(pd, UVERBS_OBJECT_PD, cmd->pd_handle,
 				       attrs);
-		if (!pd || (!scq && has_sq)) {
-			ret = -EINVAL;
+		if (IS_ERR(pd)) {
+			ret = PTR_ERR(pd);
 			goto err_put;
 		}
 
@@ -1482,18 +1490,18 @@ static int create_qp(struct uverbs_attr_bundle *attrs,
 err_put:
 	if (!IS_ERR(xrcd_uobj))
 		uobj_put_read(xrcd_uobj);
-	if (pd)
+	if (!IS_ERR_OR_NULL(pd))
 		uobj_put_obj_read(pd);
-	if (scq)
+	if (!IS_ERR_OR_NULL(scq))
 		rdma_lookup_put_uobject(&scq->uobject->uevent.uobject,
 					UVERBS_LOOKUP_READ);
-	if (rcq && rcq != scq)
+	if (!IS_ERR_OR_NULL(rcq) && rcq != scq)
 		rdma_lookup_put_uobject(&rcq->uobject->uevent.uobject,
 					UVERBS_LOOKUP_READ);
-	if (srq)
+	if (!IS_ERR_OR_NULL(srq))
 		rdma_lookup_put_uobject(&srq->uobject->uevent.uobject,
 					UVERBS_LOOKUP_READ);
-	if (ind_tbl)
+	if (!IS_ERR_OR_NULL(ind_tbl))
 		uobj_put_obj_read(ind_tbl);
 
 	uobj_alloc_abort(&obj->uevent.uobject, attrs);
@@ -1655,8 +1663,8 @@ static int ib_uverbs_query_qp(struct uverbs_attr_bundle *attrs)
 	}
 
 	qp = uobj_get_obj_read(qp, UVERBS_OBJECT_QP, cmd.qp_handle, attrs);
-	if (!qp) {
-		ret = -EINVAL;
+	if (IS_ERR(qp)) {
+		ret = PTR_ERR(qp);
 		goto out;
 	}
 
@@ -1761,8 +1769,8 @@ static int modify_qp(struct uverbs_attr_bundle *attrs,
 
 	qp = uobj_get_obj_read(qp, UVERBS_OBJECT_QP, cmd->base.qp_handle,
 			       attrs);
-	if (!qp) {
-		ret = -EINVAL;
+	if (IS_ERR(qp)) {
+		ret = PTR_ERR(qp);
 		goto out;
 	}
 
@@ -2028,8 +2036,8 @@ static int ib_uverbs_post_send(struct uverbs_attr_bundle *attrs)
 		return -ENOMEM;
 
 	qp = uobj_get_obj_read(qp, UVERBS_OBJECT_QP, cmd.qp_handle, attrs);
-	if (!qp) {
-		ret = -EINVAL;
+	if (IS_ERR(qp)) {
+		ret = PTR_ERR(qp);
 		goto out;
 	}
 
@@ -2066,9 +2074,9 @@ static int ib_uverbs_post_send(struct uverbs_attr_bundle *attrs)
 
 			ud->ah = uobj_get_obj_read(ah, UVERBS_OBJECT_AH,
 						   user_wr->wr.ud.ah, attrs);
-			if (!ud->ah) {
+			if (IS_ERR(ud->ah)) {
+				ret = PTR_ERR(ud->ah);
 				kfree(ud);
-				ret = -EINVAL;
 				goto out_put;
 			}
 			ud->remote_qpn = user_wr->wr.ud.remote_qpn;
@@ -2305,8 +2313,8 @@ static int ib_uverbs_post_recv(struct uverbs_attr_bundle *attrs)
 		return PTR_ERR(wr);
 
 	qp = uobj_get_obj_read(qp, UVERBS_OBJECT_QP, cmd.qp_handle, attrs);
-	if (!qp) {
-		ret = -EINVAL;
+	if (IS_ERR(qp)) {
+		ret = PTR_ERR(qp);
 		goto out;
 	}
 
@@ -2356,8 +2364,8 @@ static int ib_uverbs_post_srq_recv(struct uverbs_attr_bundle *attrs)
 		return PTR_ERR(wr);
 
 	srq = uobj_get_obj_read(srq, UVERBS_OBJECT_SRQ, cmd.srq_handle, attrs);
-	if (!srq) {
-		ret = -EINVAL;
+	if (IS_ERR(srq)) {
+		ret = PTR_ERR(srq);
 		goto out;
 	}
 
@@ -2413,8 +2421,8 @@ static int ib_uverbs_create_ah(struct uverbs_attr_bundle *attrs)
 	}
 
 	pd = uobj_get_obj_read(pd, UVERBS_OBJECT_PD, cmd.pd_handle, attrs);
-	if (!pd) {
-		ret = -EINVAL;
+	if (IS_ERR(pd)) {
+		ret = PTR_ERR(pd);
 		goto err;
 	}
 
@@ -2483,8 +2491,8 @@ static int ib_uverbs_attach_mcast(struct uverbs_attr_bundle *attrs)
 		return ret;
 
 	qp = uobj_get_obj_read(qp, UVERBS_OBJECT_QP, cmd.qp_handle, attrs);
-	if (!qp)
-		return -EINVAL;
+	if (IS_ERR(qp))
+		return PTR_ERR(qp);
 
 	obj = qp->uobject;
 
@@ -2533,8 +2541,8 @@ static int ib_uverbs_detach_mcast(struct uverbs_attr_bundle *attrs)
 		return ret;
 
 	qp = uobj_get_obj_read(qp, UVERBS_OBJECT_QP, cmd.qp_handle, attrs);
-	if (!qp)
-		return -EINVAL;
+	if (IS_ERR(qp))
+		return PTR_ERR(qp);
 
 	obj = qp->uobject;
 	mutex_lock(&obj->mcast_lock);
@@ -2668,8 +2676,8 @@ static int kern_spec_to_ib_spec_action(struct uverbs_attr_bundle *attrs,
 							UVERBS_OBJECT_FLOW_ACTION,
 							kern_spec->action.handle,
 							attrs);
-		if (!ib_spec->action.act)
-			return -EINVAL;
+		if (IS_ERR(ib_spec->action.act))
+			return PTR_ERR(ib_spec->action.act);
 		ib_spec->action.size =
 			sizeof(struct ib_flow_spec_action_handle);
 		flow_resources_add(uflow_res,
@@ -2686,8 +2694,8 @@ static int kern_spec_to_ib_spec_action(struct uverbs_attr_bundle *attrs,
 					  UVERBS_OBJECT_COUNTERS,
 					  kern_spec->flow_count.handle,
 					  attrs);
-		if (!ib_spec->flow_count.counters)
-			return -EINVAL;
+		if (IS_ERR(ib_spec->flow_count.counters))
+			return PTR_ERR(ib_spec->flow_count.counters);
 		ib_spec->flow_count.size =
 				sizeof(struct ib_flow_spec_action_count);
 		flow_resources_add(uflow_res,
@@ -2905,14 +2913,14 @@ static int ib_uverbs_ex_create_wq(struct uverbs_attr_bundle *attrs)
 		return PTR_ERR(obj);
 
 	pd = uobj_get_obj_read(pd, UVERBS_OBJECT_PD, cmd.pd_handle, attrs);
-	if (!pd) {
-		err = -EINVAL;
+	if (IS_ERR(pd)) {
+		err = PTR_ERR(pd);
 		goto err_uobj;
 	}
 
 	cq = uobj_get_obj_read(cq, UVERBS_OBJECT_CQ, cmd.cq_handle, attrs);
-	if (!cq) {
-		err = -EINVAL;
+	if (IS_ERR(cq)) {
+		err = PTR_ERR(cq);
 		goto err_put_pd;
 	}
 
@@ -3013,8 +3021,8 @@ static int ib_uverbs_ex_modify_wq(struct uverbs_attr_bundle *attrs)
 		return -EINVAL;
 
 	wq = uobj_get_obj_read(wq, UVERBS_OBJECT_WQ, cmd.wq_handle, attrs);
-	if (!wq)
-		return -EINVAL;
+	if (IS_ERR(wq))
+		return PTR_ERR(wq);
 
 	if (cmd.attr_mask & IB_WQ_FLAGS) {
 		wq_attr.flags = cmd.flags;
@@ -3097,8 +3105,8 @@ static int ib_uverbs_ex_create_rwq_ind_table(struct uverbs_attr_bundle *attrs)
 			num_read_wqs++) {
 		wq = uobj_get_obj_read(wq, UVERBS_OBJECT_WQ,
 				       wqs_handles[num_read_wqs], attrs);
-		if (!wq) {
-			err = -EINVAL;
+		if (IS_ERR(wq)) {
+			err = PTR_ERR(wq);
 			goto put_wqs;
 		}
 
@@ -3253,8 +3261,8 @@ static int ib_uverbs_ex_create_flow(struct uverbs_attr_bundle *attrs)
 	}
 
 	qp = uobj_get_obj_read(qp, UVERBS_OBJECT_QP, cmd.qp_handle, attrs);
-	if (!qp) {
-		err = -EINVAL;
+	if (IS_ERR(qp)) {
+		err = PTR_ERR(qp);
 		goto err_uobj;
 	}
 
@@ -3400,15 +3408,15 @@ static int __uverbs_create_xsrq(struct uverbs_attr_bundle *attrs,
 	if (ib_srq_has_cq(cmd->srq_type)) {
 		attr.ext.cq = uobj_get_obj_read(cq, UVERBS_OBJECT_CQ,
 						cmd->cq_handle, attrs);
-		if (!attr.ext.cq) {
-			ret = -EINVAL;
+		if (IS_ERR(attr.ext.cq)) {
+			ret = PTR_ERR(attr.ext.cq);
 			goto err_put_xrcd;
 		}
 	}
 
 	pd = uobj_get_obj_read(pd, UVERBS_OBJECT_PD, cmd->pd_handle, attrs);
-	if (!pd) {
-		ret = -EINVAL;
+	if (IS_ERR(pd)) {
+		ret = PTR_ERR(pd);
 		goto err_put_cq;
 	}
 
@@ -3515,8 +3523,8 @@ static int ib_uverbs_modify_srq(struct uverbs_attr_bundle *attrs)
 		return ret;
 
 	srq = uobj_get_obj_read(srq, UVERBS_OBJECT_SRQ, cmd.srq_handle, attrs);
-	if (!srq)
-		return -EINVAL;
+	if (IS_ERR(srq))
+		return PTR_ERR(srq);
 
 	attr.max_wr    = cmd.max_wr;
 	attr.srq_limit = cmd.srq_limit;
@@ -3543,8 +3551,8 @@ static int ib_uverbs_query_srq(struct uverbs_attr_bundle *attrs)
 		return ret;
 
 	srq = uobj_get_obj_read(srq, UVERBS_OBJECT_SRQ, cmd.srq_handle, attrs);
-	if (!srq)
-		return -EINVAL;
+	if (IS_ERR(srq))
+		return PTR_ERR(srq);
 
 	ret = ib_query_srq(srq, &attr);
 
@@ -3669,8 +3677,8 @@ static int ib_uverbs_ex_modify_cq(struct uverbs_attr_bundle *attrs)
 		return -EOPNOTSUPP;
 
 	cq = uobj_get_obj_read(cq, UVERBS_OBJECT_CQ, cmd.cq_handle, attrs);
-	if (!cq)
-		return -EINVAL;
+	if (IS_ERR(cq))
+		return PTR_ERR(cq);
 
 	ret = rdma_set_cq_moderation(cq, cmd.attr.cq_count, cmd.attr.cq_period);
 
diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index 473ee0831307..dc40001072a5 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -3109,22 +3109,23 @@ EXPORT_SYMBOL(__rdma_block_iter_start);
 bool __rdma_block_iter_next(struct ib_block_iter *biter)
 {
 	unsigned int block_offset;
-	unsigned int sg_delta;
+	unsigned int delta;
 
 	if (!biter->__sg_nents || !biter->__sg)
 		return false;
 
 	biter->__dma_addr = sg_dma_address(biter->__sg) + biter->__sg_advance;
 	block_offset = biter->__dma_addr & (BIT_ULL(biter->__pg_bit) - 1);
-	sg_delta = BIT_ULL(biter->__pg_bit) - block_offset;
+	delta = BIT_ULL(biter->__pg_bit) - block_offset;
 
-	if (sg_dma_len(biter->__sg) - biter->__sg_advance > sg_delta) {
-		biter->__sg_advance += sg_delta;
-	} else {
+	while (biter->__sg_nents && biter->__sg &&
+	       sg_dma_len(biter->__sg) - biter->__sg_advance <= delta) {
+		delta -= sg_dma_len(biter->__sg) - biter->__sg_advance;
 		biter->__sg_advance = 0;
 		biter->__sg = sg_next(biter->__sg);
 		biter->__sg_nents--;
 	}
+	biter->__sg_advance += delta;
 
 	return true;
 }
diff --git a/drivers/infiniband/hw/Makefile b/drivers/infiniband/hw/Makefile
index 1211f4317a9f..aba96ca9bce5 100644
--- a/drivers/infiniband/hw/Makefile
+++ b/drivers/infiniband/hw/Makefile
@@ -11,7 +11,7 @@ obj-$(CONFIG_INFINIBAND_OCRDMA)		+= ocrdma/
 obj-$(CONFIG_INFINIBAND_VMWARE_PVRDMA)	+= vmw_pvrdma/
 obj-$(CONFIG_INFINIBAND_USNIC)		+= usnic/
 obj-$(CONFIG_INFINIBAND_HFI1)		+= hfi1/
-obj-$(CONFIG_INFINIBAND_HNS)		+= hns/
+obj-$(CONFIG_INFINIBAND_HNS_HIP08)	+= hns/
 obj-$(CONFIG_INFINIBAND_QEDR)		+= qedr/
 obj-$(CONFIG_INFINIBAND_BNXT_RE)	+= bnxt_re/
 obj-$(CONFIG_INFINIBAND_ERDMA)		+= erdma/
diff --git a/drivers/infiniband/hw/bnxt_re/bnxt_re.h b/drivers/infiniband/hw/bnxt_re/bnxt_re.h
index e94518b12f86..a316afc0139c 100644
--- a/drivers/infiniband/hw/bnxt_re/bnxt_re.h
+++ b/drivers/infiniband/hw/bnxt_re/bnxt_re.h
@@ -154,6 +154,14 @@ struct bnxt_re_pacing {
 
 #define BNXT_RE_GRC_FIFO_REG_BASE 0x2000
 
+#define BNXT_RE_MIN_MSIX		2
+#define BNXT_RE_MAX_MSIX		BNXT_MAX_ROCE_MSIX
+struct bnxt_re_nq_record {
+	struct bnxt_msix_entry	msix_entries[BNXT_RE_MAX_MSIX];
+	struct bnxt_qplib_nq	nq[BNXT_RE_MAX_MSIX];
+	int			num_msix;
+};
+
 #define MAX_CQ_HASH_BITS		(16)
 #define MAX_SRQ_HASH_BITS		(16)
 struct bnxt_re_dev {
@@ -174,24 +182,20 @@ struct bnxt_re_dev {
 	unsigned int			version, major, minor;
 	struct bnxt_qplib_chip_ctx	*chip_ctx;
 	struct bnxt_en_dev		*en_dev;
-	int				num_msix;
 
 	int				id;
 
 	struct delayed_work		worker;
 	u8				cur_prio_map;
 
-	/* FP Notification Queue (CQ & SRQ) */
-	struct tasklet_struct		nq_task;
-
 	/* RCFW Channel */
 	struct bnxt_qplib_rcfw		rcfw;
 
-	/* NQ */
-	struct bnxt_qplib_nq		nq[BNXT_MAX_ROCE_MSIX];
+	/* NQ record */
+	struct bnxt_re_nq_record	*nqr;
 
 	/* Device Resources */
-	struct bnxt_qplib_dev_attr	dev_attr;
+	struct bnxt_qplib_dev_attr	*dev_attr;
 	struct bnxt_qplib_ctx		qplib_ctx;
 	struct bnxt_qplib_res		qplib_res;
 	struct bnxt_qplib_dpi		dpi_privileged;
diff --git a/drivers/infiniband/hw/bnxt_re/hw_counters.c b/drivers/infiniband/hw/bnxt_re/hw_counters.c
index 1e63f8091748..f51adb0a97e6 100644
--- a/drivers/infiniband/hw/bnxt_re/hw_counters.c
+++ b/drivers/infiniband/hw/bnxt_re/hw_counters.c
@@ -357,8 +357,8 @@ int bnxt_re_ib_get_hw_stats(struct ib_device *ibdev,
 			goto done;
 		}
 		bnxt_re_copy_err_stats(rdev, stats, err_s);
-		if (_is_ext_stats_supported(rdev->dev_attr.dev_cap_flags) &&
-		    !rdev->is_virtfn) {
+		if (bnxt_ext_stats_supported(rdev->chip_ctx, rdev->dev_attr->dev_cap_flags,
+					     rdev->is_virtfn)) {
 			rc = bnxt_re_get_ext_stat(rdev, stats);
 			if (rc) {
 				clear_bit(BNXT_RE_FLAG_ISSUE_ROCE_STATS,
diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
index 14e434ff51ed..4a3ce61a3bba 100644
--- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c
+++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
@@ -118,7 +118,7 @@ static enum ib_access_flags __to_ib_access_flags(int qflags)
 static void bnxt_re_check_and_set_relaxed_ordering(struct bnxt_re_dev *rdev,
 						   struct bnxt_qplib_mrw *qplib_mr)
 {
-	if (_is_relaxed_ordering_supported(rdev->dev_attr.dev_cap_flags2) &&
+	if (_is_relaxed_ordering_supported(rdev->dev_attr->dev_cap_flags2) &&
 	    pcie_relaxed_ordering_enabled(rdev->en_dev->pdev))
 		qplib_mr->flags |= CMDQ_REGISTER_MR_FLAGS_ENABLE_RO;
 }
@@ -143,7 +143,7 @@ int bnxt_re_query_device(struct ib_device *ibdev,
 			 struct ib_udata *udata)
 {
 	struct bnxt_re_dev *rdev = to_bnxt_re_dev(ibdev, ibdev);
-	struct bnxt_qplib_dev_attr *dev_attr = &rdev->dev_attr;
+	struct bnxt_qplib_dev_attr *dev_attr = rdev->dev_attr;
 
 	memset(ib_attr, 0, sizeof(*ib_attr));
 	memcpy(&ib_attr->fw_ver, dev_attr->fw_ver,
@@ -216,7 +216,7 @@ int bnxt_re_query_port(struct ib_device *ibdev, u32 port_num,
 		       struct ib_port_attr *port_attr)
 {
 	struct bnxt_re_dev *rdev = to_bnxt_re_dev(ibdev, ibdev);
-	struct bnxt_qplib_dev_attr *dev_attr = &rdev->dev_attr;
+	struct bnxt_qplib_dev_attr *dev_attr = rdev->dev_attr;
 	int rc;
 
 	memset(port_attr, 0, sizeof(*port_attr));
@@ -274,8 +274,8 @@ void bnxt_re_query_fw_str(struct ib_device *ibdev, char *str)
 	struct bnxt_re_dev *rdev = to_bnxt_re_dev(ibdev, ibdev);
 
 	snprintf(str, IB_FW_VERSION_NAME_MAX, "%d.%d.%d.%d",
-		 rdev->dev_attr.fw_ver[0], rdev->dev_attr.fw_ver[1],
-		 rdev->dev_attr.fw_ver[2], rdev->dev_attr.fw_ver[3]);
+		 rdev->dev_attr->fw_ver[0], rdev->dev_attr->fw_ver[1],
+		 rdev->dev_attr->fw_ver[2], rdev->dev_attr->fw_ver[3]);
 }
 
 int bnxt_re_query_pkey(struct ib_device *ibdev, u32 port_num,
@@ -526,7 +526,7 @@ static int bnxt_re_create_fence_mr(struct bnxt_re_pd *pd)
 	mr->qplib_mr.pd = &pd->qplib_pd;
 	mr->qplib_mr.type = CMDQ_ALLOCATE_MRW_MRW_FLAGS_PMR;
 	mr->qplib_mr.access_flags = __from_ib_access_flags(mr_access_flags);
-	if (!_is_alloc_mr_unified(rdev->dev_attr.dev_cap_flags)) {
+	if (!_is_alloc_mr_unified(rdev->dev_attr->dev_cap_flags)) {
 		rc = bnxt_qplib_alloc_mrw(&rdev->qplib_res, &mr->qplib_mr);
 		if (rc) {
 			ibdev_err(&rdev->ibdev, "Failed to alloc fence-HW-MR\n");
@@ -1001,7 +1001,7 @@ static int bnxt_re_setup_swqe_size(struct bnxt_re_qp *qp,
 	rdev = qp->rdev;
 	qplqp = &qp->qplib_qp;
 	sq = &qplqp->sq;
-	dev_attr = &rdev->dev_attr;
+	dev_attr = rdev->dev_attr;
 
 	align = sizeof(struct sq_send_hdr);
 	ilsize = ALIGN(init_attr->cap.max_inline_data, align);
@@ -1221,7 +1221,7 @@ static int bnxt_re_init_rq_attr(struct bnxt_re_qp *qp,
 	rdev = qp->rdev;
 	qplqp = &qp->qplib_qp;
 	rq = &qplqp->rq;
-	dev_attr = &rdev->dev_attr;
+	dev_attr = rdev->dev_attr;
 
 	if (init_attr->srq) {
 		struct bnxt_re_srq *srq;
@@ -1258,7 +1258,7 @@ static void bnxt_re_adjust_gsi_rq_attr(struct bnxt_re_qp *qp)
 
 	rdev = qp->rdev;
 	qplqp = &qp->qplib_qp;
-	dev_attr = &rdev->dev_attr;
+	dev_attr = rdev->dev_attr;
 
 	if (!bnxt_qplib_is_chip_gen_p5_p7(rdev->chip_ctx)) {
 		qplqp->rq.max_sge = dev_attr->max_qp_sges;
@@ -1284,7 +1284,7 @@ static int bnxt_re_init_sq_attr(struct bnxt_re_qp *qp,
 	rdev = qp->rdev;
 	qplqp = &qp->qplib_qp;
 	sq = &qplqp->sq;
-	dev_attr = &rdev->dev_attr;
+	dev_attr = rdev->dev_attr;
 
 	sq->max_sge = init_attr->cap.max_send_sge;
 	entries = init_attr->cap.max_send_wr;
@@ -1337,7 +1337,7 @@ static void bnxt_re_adjust_gsi_sq_attr(struct bnxt_re_qp *qp,
 
 	rdev = qp->rdev;
 	qplqp = &qp->qplib_qp;
-	dev_attr = &rdev->dev_attr;
+	dev_attr = rdev->dev_attr;
 
 	if (!bnxt_qplib_is_chip_gen_p5_p7(rdev->chip_ctx)) {
 		entries = bnxt_re_init_depth(init_attr->cap.max_send_wr + 1, uctx);
@@ -1386,7 +1386,7 @@ static int bnxt_re_init_qp_attr(struct bnxt_re_qp *qp, struct bnxt_re_pd *pd,
 
 	rdev = qp->rdev;
 	qplqp = &qp->qplib_qp;
-	dev_attr = &rdev->dev_attr;
+	dev_attr = rdev->dev_attr;
 
 	/* Setup misc params */
 	ether_addr_copy(qplqp->smac, rdev->netdev->dev_addr);
@@ -1556,7 +1556,7 @@ int bnxt_re_create_qp(struct ib_qp *ib_qp, struct ib_qp_init_attr *qp_init_attr,
 	ib_pd = ib_qp->pd;
 	pd = container_of(ib_pd, struct bnxt_re_pd, ib_pd);
 	rdev = pd->rdev;
-	dev_attr = &rdev->dev_attr;
+	dev_attr = rdev->dev_attr;
 	qp = container_of(ib_qp, struct bnxt_re_qp, ib_qp);
 
 	uctx = rdma_udata_to_drv_context(udata, struct bnxt_re_ucontext, ib_uctx);
@@ -1783,7 +1783,7 @@ int bnxt_re_create_srq(struct ib_srq *ib_srq,
 	ib_pd = ib_srq->pd;
 	pd = container_of(ib_pd, struct bnxt_re_pd, ib_pd);
 	rdev = pd->rdev;
-	dev_attr = &rdev->dev_attr;
+	dev_attr = rdev->dev_attr;
 	srq = container_of(ib_srq, struct bnxt_re_srq, ib_srq);
 
 	if (srq_init_attr->attr.max_wr >= dev_attr->max_srq_wqes) {
@@ -1814,8 +1814,10 @@ int bnxt_re_create_srq(struct ib_srq *ib_srq,
 	srq->qplib_srq.wqe_size = bnxt_re_get_rwqe_size(dev_attr->max_srq_sges);
 	srq->qplib_srq.threshold = srq_init_attr->attr.srq_limit;
 	srq->srq_limit = srq_init_attr->attr.srq_limit;
-	srq->qplib_srq.eventq_hw_ring_id = rdev->nq[0].ring_id;
-	nq = &rdev->nq[0];
+	srq->qplib_srq.eventq_hw_ring_id = rdev->nqr->nq[0].ring_id;
+	srq->qplib_srq.sg_info.pgsize = PAGE_SIZE;
+	srq->qplib_srq.sg_info.pgshft = PAGE_SHIFT;
+	nq = &rdev->nqr->nq[0];
 
 	if (udata) {
 		rc = bnxt_re_init_user_srq(rdev, pd, srq, udata);
@@ -1987,7 +1989,7 @@ int bnxt_re_modify_qp(struct ib_qp *ib_qp, struct ib_qp_attr *qp_attr,
 {
 	struct bnxt_re_qp *qp = container_of(ib_qp, struct bnxt_re_qp, ib_qp);
 	struct bnxt_re_dev *rdev = qp->rdev;
-	struct bnxt_qplib_dev_attr *dev_attr = &rdev->dev_attr;
+	struct bnxt_qplib_dev_attr *dev_attr = rdev->dev_attr;
 	enum ib_qp_state curr_qp_state, new_qp_state;
 	int rc, entries;
 	unsigned int flags;
@@ -3011,7 +3013,7 @@ int bnxt_re_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
 	struct ib_udata *udata = &attrs->driver_udata;
 	struct bnxt_re_ucontext *uctx =
 		rdma_udata_to_drv_context(udata, struct bnxt_re_ucontext, ib_uctx);
-	struct bnxt_qplib_dev_attr *dev_attr = &rdev->dev_attr;
+	struct bnxt_qplib_dev_attr *dev_attr = rdev->dev_attr;
 	struct bnxt_qplib_chip_ctx *cctx;
 	struct bnxt_qplib_nq *nq = NULL;
 	unsigned int nq_alloc_cnt;
@@ -3070,7 +3072,7 @@ int bnxt_re_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
 	 * used for getting the NQ index.
 	 */
 	nq_alloc_cnt = atomic_inc_return(&rdev->nq_alloc_cnt);
-	nq = &rdev->nq[nq_alloc_cnt % (rdev->num_msix - 1)];
+	nq = &rdev->nqr->nq[nq_alloc_cnt % (rdev->nqr->num_msix - 1)];
 	cq->qplib_cq.max_wqe = entries;
 	cq->qplib_cq.cnq_hw_ring_id = nq->ring_id;
 	cq->qplib_cq.nq	= nq;
@@ -3154,7 +3156,7 @@ int bnxt_re_resize_cq(struct ib_cq *ibcq, int cqe, struct ib_udata *udata)
 
 	cq =  container_of(ibcq, struct bnxt_re_cq, ib_cq);
 	rdev = cq->rdev;
-	dev_attr = &rdev->dev_attr;
+	dev_attr = rdev->dev_attr;
 	if (!ibcq->uobject) {
 		ibdev_err(&rdev->ibdev, "Kernel CQ Resize not supported");
 		return -EOPNOTSUPP;
@@ -4127,7 +4129,7 @@ static struct ib_mr *__bnxt_re_user_reg_mr(struct ib_pd *ib_pd, u64 length, u64
 	mr->qplib_mr.access_flags = __from_ib_access_flags(mr_access_flags);
 	mr->qplib_mr.type = CMDQ_ALLOCATE_MRW_MRW_FLAGS_MR;
 
-	if (!_is_alloc_mr_unified(rdev->dev_attr.dev_cap_flags)) {
+	if (!_is_alloc_mr_unified(rdev->dev_attr->dev_cap_flags)) {
 		rc = bnxt_qplib_alloc_mrw(&rdev->qplib_res, &mr->qplib_mr);
 		if (rc) {
 			ibdev_err(&rdev->ibdev, "Failed to allocate MR rc = %d", rc);
@@ -4219,7 +4221,7 @@ int bnxt_re_alloc_ucontext(struct ib_ucontext *ctx, struct ib_udata *udata)
 	struct bnxt_re_ucontext *uctx =
 		container_of(ctx, struct bnxt_re_ucontext, ib_uctx);
 	struct bnxt_re_dev *rdev = to_bnxt_re_dev(ibdev, ibdev);
-	struct bnxt_qplib_dev_attr *dev_attr = &rdev->dev_attr;
+	struct bnxt_qplib_dev_attr *dev_attr = rdev->dev_attr;
 	struct bnxt_re_user_mmap_entry *entry;
 	struct bnxt_re_uctx_resp resp = {};
 	struct bnxt_re_uctx_req ureq = {};
@@ -4395,9 +4397,10 @@ int bnxt_re_mmap(struct ib_ucontext *ib_uctx, struct vm_area_struct *vma)
 	case BNXT_RE_MMAP_TOGGLE_PAGE:
 		/* Driver doesn't expect write access for user space */
 		if (vma->vm_flags & VM_WRITE)
-			return -EFAULT;
-		ret = vm_insert_page(vma, vma->vm_start,
-				     virt_to_page((void *)bnxt_entry->mem_offset));
+			ret = -EFAULT;
+		else
+			ret = vm_insert_page(vma, vma->vm_start,
+					     virt_to_page((void *)bnxt_entry->mem_offset));
 		break;
 	default:
 		ret = -EINVAL;
@@ -4639,7 +4642,7 @@ static int UVERBS_HANDLER(BNXT_RE_METHOD_GET_TOGGLE_MEM)(struct uverbs_attr_bund
 		return err;
 
 	err = uverbs_copy_to(attrs, BNXT_RE_TOGGLE_MEM_MMAP_OFFSET,
-			     &offset, sizeof(length));
+			     &offset, sizeof(offset));
 	if (err)
 		return err;
 
diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c
index 8abd1b723f8f..9bd837a5b8a1 100644
--- a/drivers/infiniband/hw/bnxt_re/main.c
+++ b/drivers/infiniband/hw/bnxt_re/main.c
@@ -152,6 +152,10 @@ static void bnxt_re_destroy_chip_ctx(struct bnxt_re_dev *rdev)
 
 	if (!rdev->chip_ctx)
 		return;
+
+	kfree(rdev->dev_attr);
+	rdev->dev_attr = NULL;
+
 	chip_ctx = rdev->chip_ctx;
 	rdev->chip_ctx = NULL;
 	rdev->rcfw.res = NULL;
@@ -165,7 +169,7 @@ static int bnxt_re_setup_chip_ctx(struct bnxt_re_dev *rdev)
 {
 	struct bnxt_qplib_chip_ctx *chip_ctx;
 	struct bnxt_en_dev *en_dev;
-	int rc;
+	int rc = -ENOMEM;
 
 	en_dev = rdev->en_dev;
 
@@ -181,23 +185,30 @@ static int bnxt_re_setup_chip_ctx(struct bnxt_re_dev *rdev)
 
 	rdev->qplib_res.cctx = rdev->chip_ctx;
 	rdev->rcfw.res = &rdev->qplib_res;
-	rdev->qplib_res.dattr = &rdev->dev_attr;
+	rdev->dev_attr = kzalloc(sizeof(*rdev->dev_attr), GFP_KERNEL);
+	if (!rdev->dev_attr)
+		goto free_chip_ctx;
+	rdev->qplib_res.dattr = rdev->dev_attr;
 	rdev->qplib_res.is_vf = BNXT_EN_VF(en_dev);
 
 	bnxt_re_set_drv_mode(rdev);
 
 	bnxt_re_set_db_offset(rdev);
 	rc = bnxt_qplib_map_db_bar(&rdev->qplib_res);
-	if (rc) {
-		kfree(rdev->chip_ctx);
-		rdev->chip_ctx = NULL;
-		return rc;
-	}
+	if (rc)
+		goto free_dev_attr;
 
 	if (bnxt_qplib_determine_atomics(en_dev->pdev))
 		ibdev_info(&rdev->ibdev,
 			   "platform doesn't support global atomics.");
 	return 0;
+free_dev_attr:
+	kfree(rdev->dev_attr);
+	rdev->dev_attr = NULL;
+free_chip_ctx:
+	kfree(rdev->chip_ctx);
+	rdev->chip_ctx = NULL;
+	return rc;
 }
 
 /* SR-IOV helper functions */
@@ -219,7 +230,7 @@ static void bnxt_re_limit_pf_res(struct bnxt_re_dev *rdev)
 	struct bnxt_qplib_ctx *ctx;
 	int i;
 
-	attr = &rdev->dev_attr;
+	attr = rdev->dev_attr;
 	ctx = &rdev->qplib_ctx;
 
 	ctx->qpc_count = min_t(u32, BNXT_RE_MAX_QPC_COUNT,
@@ -233,7 +244,7 @@ static void bnxt_re_limit_pf_res(struct bnxt_re_dev *rdev)
 	if (!bnxt_qplib_is_chip_gen_p5_p7(rdev->chip_ctx))
 		for (i = 0; i < MAX_TQM_ALLOC_REQ; i++)
 			rdev->qplib_ctx.tqm_ctx.qcount[i] =
-			rdev->dev_attr.tqm_alloc_reqs[i];
+			rdev->dev_attr->tqm_alloc_reqs[i];
 }
 
 static void bnxt_re_limit_vf_res(struct bnxt_qplib_ctx *qplib_ctx, u32 num_vf)
@@ -314,10 +325,12 @@ static void bnxt_re_stop_irq(void *handle)
 	int indx;
 
 	rdev = en_info->rdev;
+	if (!rdev)
+		return;
 	rcfw = &rdev->rcfw;
 
-	for (indx = BNXT_RE_NQ_IDX; indx < rdev->num_msix; indx++) {
-		nq = &rdev->nq[indx - 1];
+	for (indx = BNXT_RE_NQ_IDX; indx < rdev->nqr->num_msix; indx++) {
+		nq = &rdev->nqr->nq[indx - 1];
 		bnxt_qplib_nq_stop_irq(nq, false);
 	}
 
@@ -334,7 +347,9 @@ static void bnxt_re_start_irq(void *handle, struct bnxt_msix_entry *ent)
 	int indx, rc;
 
 	rdev = en_info->rdev;
-	msix_ent = rdev->en_dev->msix_entries;
+	if (!rdev)
+		return;
+	msix_ent = rdev->nqr->msix_entries;
 	rcfw = &rdev->rcfw;
 	if (!ent) {
 		/* Not setting the f/w timeout bit in rcfw.
@@ -349,8 +364,8 @@ static void bnxt_re_start_irq(void *handle, struct bnxt_msix_entry *ent)
 	/* Vectors may change after restart, so update with new vectors
 	 * in device sctructure.
 	 */
-	for (indx = 0; indx < rdev->num_msix; indx++)
-		rdev->en_dev->msix_entries[indx].vector = ent[indx].vector;
+	for (indx = 0; indx < rdev->nqr->num_msix; indx++)
+		rdev->nqr->msix_entries[indx].vector = ent[indx].vector;
 
 	rc = bnxt_qplib_rcfw_start_irq(rcfw, msix_ent[BNXT_RE_AEQ_IDX].vector,
 				       false);
@@ -358,8 +373,8 @@ static void bnxt_re_start_irq(void *handle, struct bnxt_msix_entry *ent)
 		ibdev_warn(&rdev->ibdev, "Failed to reinit CREQ\n");
 		return;
 	}
-	for (indx = BNXT_RE_NQ_IDX ; indx < rdev->num_msix; indx++) {
-		nq = &rdev->nq[indx - 1];
+	for (indx = BNXT_RE_NQ_IDX ; indx < rdev->nqr->num_msix; indx++) {
+		nq = &rdev->nqr->nq[indx - 1];
 		rc = bnxt_qplib_nq_start_irq(nq, indx - 1,
 					     msix_ent[indx].vector, false);
 		if (rc) {
@@ -943,7 +958,7 @@ static int bnxt_re_register_ib(struct bnxt_re_dev *rdev)
 
 	addrconf_addr_eui48((u8 *)&ibdev->node_guid, rdev->netdev->dev_addr);
 
-	ibdev->num_comp_vectors	= rdev->num_msix - 1;
+	ibdev->num_comp_vectors	= rdev->nqr->num_msix - 1;
 	ibdev->dev.parent = &rdev->en_dev->pdev->dev;
 	ibdev->local_dma_lkey = BNXT_QPLIB_RSVD_LKEY;
 
@@ -1276,8 +1291,8 @@ static void bnxt_re_cleanup_res(struct bnxt_re_dev *rdev)
 {
 	int i;
 
-	for (i = 1; i < rdev->num_msix; i++)
-		bnxt_qplib_disable_nq(&rdev->nq[i - 1]);
+	for (i = 1; i < rdev->nqr->num_msix; i++)
+		bnxt_qplib_disable_nq(&rdev->nqr->nq[i - 1]);
 
 	if (rdev->qplib_res.rcfw)
 		bnxt_qplib_cleanup_res(&rdev->qplib_res);
@@ -1291,10 +1306,10 @@ static int bnxt_re_init_res(struct bnxt_re_dev *rdev)
 
 	bnxt_qplib_init_res(&rdev->qplib_res);
 
-	for (i = 1; i < rdev->num_msix ; i++) {
-		db_offt = rdev->en_dev->msix_entries[i].db_offset;
-		rc = bnxt_qplib_enable_nq(rdev->en_dev->pdev, &rdev->nq[i - 1],
-					  i - 1, rdev->en_dev->msix_entries[i].vector,
+	for (i = 1; i < rdev->nqr->num_msix ; i++) {
+		db_offt = rdev->nqr->msix_entries[i].db_offset;
+		rc = bnxt_qplib_enable_nq(rdev->en_dev->pdev, &rdev->nqr->nq[i - 1],
+					  i - 1, rdev->nqr->msix_entries[i].vector,
 					  db_offt, &bnxt_re_cqn_handler,
 					  &bnxt_re_srqn_handler);
 		if (rc) {
@@ -1307,20 +1322,22 @@ static int bnxt_re_init_res(struct bnxt_re_dev *rdev)
 	return 0;
 fail:
 	for (i = num_vec_enabled; i >= 0; i--)
-		bnxt_qplib_disable_nq(&rdev->nq[i]);
+		bnxt_qplib_disable_nq(&rdev->nqr->nq[i]);
 	return rc;
 }
 
 static void bnxt_re_free_nq_res(struct bnxt_re_dev *rdev)
 {
+	struct bnxt_qplib_nq *nq;
 	u8 type;
 	int i;
 
-	for (i = 0; i < rdev->num_msix - 1; i++) {
+	for (i = 0; i < rdev->nqr->num_msix - 1; i++) {
 		type = bnxt_qplib_get_ring_type(rdev->chip_ctx);
-		bnxt_re_net_ring_free(rdev, rdev->nq[i].ring_id, type);
-		bnxt_qplib_free_nq(&rdev->nq[i]);
-		rdev->nq[i].res = NULL;
+		nq = &rdev->nqr->nq[i];
+		bnxt_re_net_ring_free(rdev, nq->ring_id, type);
+		bnxt_qplib_free_nq(nq);
+		nq->res = NULL;
 	}
 }
 
@@ -1347,12 +1364,11 @@ static int bnxt_re_alloc_res(struct bnxt_re_dev *rdev)
 
 	/* Configure and allocate resources for qplib */
 	rdev->qplib_res.rcfw = &rdev->rcfw;
-	rc = bnxt_qplib_get_dev_attr(&rdev->rcfw, &rdev->dev_attr);
+	rc = bnxt_qplib_get_dev_attr(&rdev->rcfw);
 	if (rc)
 		goto fail;
 
-	rc = bnxt_qplib_alloc_res(&rdev->qplib_res, rdev->en_dev->pdev,
-				  rdev->netdev, &rdev->dev_attr);
+	rc = bnxt_qplib_alloc_res(&rdev->qplib_res, rdev->netdev);
 	if (rc)
 		goto fail;
 
@@ -1362,12 +1378,12 @@ static int bnxt_re_alloc_res(struct bnxt_re_dev *rdev)
 	if (rc)
 		goto dealloc_res;
 
-	for (i = 0; i < rdev->num_msix - 1; i++) {
+	for (i = 0; i < rdev->nqr->num_msix - 1; i++) {
 		struct bnxt_qplib_nq *nq;
 
-		nq = &rdev->nq[i];
+		nq = &rdev->nqr->nq[i];
 		nq->hwq.max_elements = BNXT_QPLIB_NQE_MAX_CNT;
-		rc = bnxt_qplib_alloc_nq(&rdev->qplib_res, &rdev->nq[i]);
+		rc = bnxt_qplib_alloc_nq(&rdev->qplib_res, nq);
 		if (rc) {
 			ibdev_err(&rdev->ibdev, "Alloc Failed NQ%d rc:%#x",
 				  i, rc);
@@ -1375,17 +1391,17 @@ static int bnxt_re_alloc_res(struct bnxt_re_dev *rdev)
 		}
 		type = bnxt_qplib_get_ring_type(rdev->chip_ctx);
 		rattr.dma_arr = nq->hwq.pbl[PBL_LVL_0].pg_map_arr;
-		rattr.pages = nq->hwq.pbl[rdev->nq[i].hwq.level].pg_count;
+		rattr.pages = nq->hwq.pbl[rdev->nqr->nq[i].hwq.level].pg_count;
 		rattr.type = type;
 		rattr.mode = RING_ALLOC_REQ_INT_MODE_MSIX;
 		rattr.depth = BNXT_QPLIB_NQE_MAX_CNT - 1;
-		rattr.lrid = rdev->en_dev->msix_entries[i + 1].ring_idx;
+		rattr.lrid = rdev->nqr->msix_entries[i + 1].ring_idx;
 		rc = bnxt_re_net_ring_alloc(rdev, &rattr, &nq->ring_id);
 		if (rc) {
 			ibdev_err(&rdev->ibdev,
 				  "Failed to allocate NQ fw id with rc = 0x%x",
 				  rc);
-			bnxt_qplib_free_nq(&rdev->nq[i]);
+			bnxt_qplib_free_nq(nq);
 			goto free_nq;
 		}
 		num_vec_created++;
@@ -1394,8 +1410,8 @@ static int bnxt_re_alloc_res(struct bnxt_re_dev *rdev)
 free_nq:
 	for (i = num_vec_created - 1; i >= 0; i--) {
 		type = bnxt_qplib_get_ring_type(rdev->chip_ctx);
-		bnxt_re_net_ring_free(rdev, rdev->nq[i].ring_id, type);
-		bnxt_qplib_free_nq(&rdev->nq[i]);
+		bnxt_re_net_ring_free(rdev, rdev->nqr->nq[i].ring_id, type);
+		bnxt_qplib_free_nq(&rdev->nqr->nq[i]);
 	}
 	bnxt_qplib_dealloc_dpi(&rdev->qplib_res,
 			       &rdev->dpi_privileged);
@@ -1584,6 +1600,21 @@ static int bnxt_re_ib_init(struct bnxt_re_dev *rdev)
 	return rc;
 }
 
+static int bnxt_re_alloc_nqr_mem(struct bnxt_re_dev *rdev)
+{
+	rdev->nqr = kzalloc(sizeof(*rdev->nqr), GFP_KERNEL);
+	if (!rdev->nqr)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void bnxt_re_free_nqr_mem(struct bnxt_re_dev *rdev)
+{
+	kfree(rdev->nqr);
+	rdev->nqr = NULL;
+}
+
 static void bnxt_re_dev_uninit(struct bnxt_re_dev *rdev, u8 op_type)
 {
 	u8 type;
@@ -1611,11 +1642,12 @@ static void bnxt_re_dev_uninit(struct bnxt_re_dev *rdev, u8 op_type)
 		bnxt_qplib_free_rcfw_channel(&rdev->rcfw);
 	}
 
-	rdev->num_msix = 0;
+	rdev->nqr->num_msix = 0;
 
 	if (rdev->pacing.dbr_pacing)
 		bnxt_re_deinitialize_dbr_pacing(rdev);
 
+	bnxt_re_free_nqr_mem(rdev);
 	bnxt_re_destroy_chip_ctx(rdev);
 	if (op_type == BNXT_RE_COMPLETE_REMOVE) {
 		if (test_and_clear_bit(BNXT_RE_FLAG_NETDEV_REGISTERED, &rdev->flags))
@@ -1653,6 +1685,17 @@ static int bnxt_re_dev_init(struct bnxt_re_dev *rdev, u8 op_type)
 	}
 	set_bit(BNXT_RE_FLAG_NETDEV_REGISTERED, &rdev->flags);
 
+	if (rdev->en_dev->ulp_tbl->msix_requested < BNXT_RE_MIN_MSIX) {
+		ibdev_err(&rdev->ibdev,
+			  "RoCE requires minimum 2 MSI-X vectors, but only %d reserved\n",
+			  rdev->en_dev->ulp_tbl->msix_requested);
+		bnxt_unregister_dev(rdev->en_dev);
+		clear_bit(BNXT_RE_FLAG_NETDEV_REGISTERED, &rdev->flags);
+		return -EINVAL;
+	}
+	ibdev_dbg(&rdev->ibdev, "Got %d MSI-X vectors\n",
+		  rdev->en_dev->ulp_tbl->msix_requested);
+
 	rc = bnxt_re_setup_chip_ctx(rdev);
 	if (rc) {
 		bnxt_unregister_dev(rdev->en_dev);
@@ -1661,19 +1704,20 @@ static int bnxt_re_dev_init(struct bnxt_re_dev *rdev, u8 op_type)
 		return -EINVAL;
 	}
 
+	rc = bnxt_re_alloc_nqr_mem(rdev);
+	if (rc) {
+		bnxt_re_destroy_chip_ctx(rdev);
+		bnxt_unregister_dev(rdev->en_dev);
+		clear_bit(BNXT_RE_FLAG_NETDEV_REGISTERED, &rdev->flags);
+		return rc;
+	}
+	rdev->nqr->num_msix = rdev->en_dev->ulp_tbl->msix_requested;
+	memcpy(rdev->nqr->msix_entries, rdev->en_dev->msix_entries,
+	       sizeof(struct bnxt_msix_entry) * rdev->nqr->num_msix);
+
 	/* Check whether VF or PF */
 	bnxt_re_get_sriov_func_type(rdev);
 
-	if (!rdev->en_dev->ulp_tbl->msix_requested) {
-		ibdev_err(&rdev->ibdev,
-			  "Failed to get MSI-X vectors: %#x\n", rc);
-		rc = -EINVAL;
-		goto fail;
-	}
-	ibdev_dbg(&rdev->ibdev, "Got %d MSI-X vectors\n",
-		  rdev->en_dev->ulp_tbl->msix_requested);
-	rdev->num_msix = rdev->en_dev->ulp_tbl->msix_requested;
-
 	bnxt_re_query_hwrm_intf_version(rdev);
 
 	/* Establish RCFW Communication Channel to initialize the context
@@ -1695,14 +1739,14 @@ static int bnxt_re_dev_init(struct bnxt_re_dev *rdev, u8 op_type)
 	rattr.type = type;
 	rattr.mode = RING_ALLOC_REQ_INT_MODE_MSIX;
 	rattr.depth = BNXT_QPLIB_CREQE_MAX_CNT - 1;
-	rattr.lrid = rdev->en_dev->msix_entries[BNXT_RE_AEQ_IDX].ring_idx;
+	rattr.lrid = rdev->nqr->msix_entries[BNXT_RE_AEQ_IDX].ring_idx;
 	rc = bnxt_re_net_ring_alloc(rdev, &rattr, &creq->ring_id);
 	if (rc) {
 		ibdev_err(&rdev->ibdev, "Failed to allocate CREQ: %#x\n", rc);
 		goto free_rcfw;
 	}
-	db_offt = rdev->en_dev->msix_entries[BNXT_RE_AEQ_IDX].db_offset;
-	vid = rdev->en_dev->msix_entries[BNXT_RE_AEQ_IDX].vector;
+	db_offt = rdev->nqr->msix_entries[BNXT_RE_AEQ_IDX].db_offset;
+	vid = rdev->nqr->msix_entries[BNXT_RE_AEQ_IDX].vector;
 	rc = bnxt_qplib_enable_rcfw_channel(&rdev->rcfw,
 					    vid, db_offt,
 					    &bnxt_re_aeq_handler);
@@ -1722,7 +1766,7 @@ static int bnxt_re_dev_init(struct bnxt_re_dev *rdev, u8 op_type)
 			rdev->pacing.dbr_pacing = false;
 		}
 	}
-	rc = bnxt_qplib_get_dev_attr(&rdev->rcfw, &rdev->dev_attr);
+	rc = bnxt_qplib_get_dev_attr(&rdev->rcfw);
 	if (rc)
 		goto disable_rcfw;
 
@@ -2047,6 +2091,7 @@ static int bnxt_re_suspend(struct auxiliary_device *adev, pm_message_t state)
 	ibdev_info(&rdev->ibdev, "%s: L2 driver notified to stop en_state 0x%lx",
 		   __func__, en_dev->en_state);
 	bnxt_re_remove_device(rdev, BNXT_RE_PRE_RECOVERY_REMOVE, adev);
+	bnxt_re_update_en_info_rdev(NULL, en_info, adev);
 	mutex_unlock(&bnxt_re_mutex);
 
 	return 0;
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c
index 613b5fc70e13..7436ce551579 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c
@@ -1216,8 +1216,6 @@ static void __modify_flags_from_init_state(struct bnxt_qplib_qp *qp)
 			qp->path_mtu =
 				CMDQ_MODIFY_QP_PATH_MTU_MTU_2048;
 		}
-		qp->modify_flags &=
-			~CMDQ_MODIFY_QP_MODIFY_MASK_VLAN_ID;
 		/* Bono FW require the max_dest_rd_atomic to be >= 1 */
 		if (qp->max_dest_rd_atomic < 1)
 			qp->max_dest_rd_atomic = 1;
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h
index 07779aeb7575..a4deb45ec849 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h
+++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h
@@ -283,9 +283,10 @@ int bnxt_qplib_deinit_rcfw(struct bnxt_qplib_rcfw *rcfw);
 int bnxt_qplib_init_rcfw(struct bnxt_qplib_rcfw *rcfw,
 			 struct bnxt_qplib_ctx *ctx, int is_virtfn);
 void bnxt_qplib_mark_qp_error(void *qp_handle);
+
 static inline u32 map_qp_id_to_tbl_indx(u32 qid, struct bnxt_qplib_rcfw *rcfw)
 {
 	/* Last index of the qp_tbl is for QP1 ie. qp_tbl_size - 1*/
-	return (qid == 1) ? rcfw->qp_tbl_size - 1 : qid % rcfw->qp_tbl_size - 2;
+	return (qid == 1) ? rcfw->qp_tbl_size - 1 : (qid % (rcfw->qp_tbl_size - 2));
 }
 #endif /* __BNXT_QPLIB_RCFW_H__ */
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_res.c b/drivers/infiniband/hw/bnxt_re/qplib_res.c
index 96ceec1e8199..02922a0987ad 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_res.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_res.c
@@ -876,14 +876,13 @@ void bnxt_qplib_free_res(struct bnxt_qplib_res *res)
 	bnxt_qplib_free_dpi_tbl(res, &res->dpi_tbl);
 }
 
-int bnxt_qplib_alloc_res(struct bnxt_qplib_res *res, struct pci_dev *pdev,
-			 struct net_device *netdev,
-			 struct bnxt_qplib_dev_attr *dev_attr)
+int bnxt_qplib_alloc_res(struct bnxt_qplib_res *res, struct net_device *netdev)
 {
+	struct bnxt_qplib_dev_attr *dev_attr;
 	int rc;
 
-	res->pdev = pdev;
 	res->netdev = netdev;
+	dev_attr = res->dattr;
 
 	rc = bnxt_qplib_alloc_sgid_tbl(res, &res->sgid_tbl, dev_attr->max_sgid);
 	if (rc)
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_res.h b/drivers/infiniband/hw/bnxt_re/qplib_res.h
index c2f710364e0f..b40cff8252bc 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_res.h
+++ b/drivers/infiniband/hw/bnxt_re/qplib_res.h
@@ -421,9 +421,7 @@ int bnxt_qplib_dealloc_dpi(struct bnxt_qplib_res *res,
 void bnxt_qplib_cleanup_res(struct bnxt_qplib_res *res);
 int bnxt_qplib_init_res(struct bnxt_qplib_res *res);
 void bnxt_qplib_free_res(struct bnxt_qplib_res *res);
-int bnxt_qplib_alloc_res(struct bnxt_qplib_res *res, struct pci_dev *pdev,
-			 struct net_device *netdev,
-			 struct bnxt_qplib_dev_attr *dev_attr);
+int bnxt_qplib_alloc_res(struct bnxt_qplib_res *res, struct net_device *netdev);
 void bnxt_qplib_free_ctx(struct bnxt_qplib_res *res,
 			 struct bnxt_qplib_ctx *ctx);
 int bnxt_qplib_alloc_ctx(struct bnxt_qplib_res *res,
@@ -546,6 +544,14 @@ static inline bool _is_ext_stats_supported(u16 dev_cap_flags)
 		CREQ_QUERY_FUNC_RESP_SB_EXT_STATS;
 }
 
+static inline int bnxt_ext_stats_supported(struct bnxt_qplib_chip_ctx *ctx,
+					   u16 flags, bool virtfn)
+{
+	/* ext stats supported if cap flag is set AND is a PF OR a Thor2 VF */
+	return (_is_ext_stats_supported(flags) &&
+		((virtfn && bnxt_qplib_is_chip_gen_p7(ctx)) || (!virtfn)));
+}
+
 static inline bool _is_hw_retx_supported(u16 dev_cap_flags)
 {
 	return dev_cap_flags &
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_sp.c b/drivers/infiniband/hw/bnxt_re/qplib_sp.c
index 3cca7b1395f6..807439b1acb5 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_sp.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_sp.c
@@ -88,9 +88,9 @@ static void bnxt_qplib_query_version(struct bnxt_qplib_rcfw *rcfw,
 	fw_ver[3] = resp.fw_rsvd;
 }
 
-int bnxt_qplib_get_dev_attr(struct bnxt_qplib_rcfw *rcfw,
-			    struct bnxt_qplib_dev_attr *attr)
+int bnxt_qplib_get_dev_attr(struct bnxt_qplib_rcfw *rcfw)
 {
+	struct bnxt_qplib_dev_attr *attr = rcfw->res->dattr;
 	struct creq_query_func_resp resp = {};
 	struct bnxt_qplib_cmdqmsg msg = {};
 	struct creq_query_func_resp_sb *sb;
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_sp.h b/drivers/infiniband/hw/bnxt_re/qplib_sp.h
index ecf3f45fea74..de959b3c28e0 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_sp.h
+++ b/drivers/infiniband/hw/bnxt_re/qplib_sp.h
@@ -325,8 +325,7 @@ int bnxt_qplib_add_sgid(struct bnxt_qplib_sgid_tbl *sgid_tbl,
 int bnxt_qplib_update_sgid(struct bnxt_qplib_sgid_tbl *sgid_tbl,
 			   struct bnxt_qplib_gid *gid, u16 gid_idx,
 			   const u8 *smac);
-int bnxt_qplib_get_dev_attr(struct bnxt_qplib_rcfw *rcfw,
-			    struct bnxt_qplib_dev_attr *attr);
+int bnxt_qplib_get_dev_attr(struct bnxt_qplib_rcfw *rcfw);
 int bnxt_qplib_set_func_resources(struct bnxt_qplib_res *res,
 				  struct bnxt_qplib_rcfw *rcfw,
 				  struct bnxt_qplib_ctx *ctx);
diff --git a/drivers/infiniband/hw/cxgb4/device.c b/drivers/infiniband/hw/cxgb4/device.c
index 80970a1738f8..034b85c42255 100644
--- a/drivers/infiniband/hw/cxgb4/device.c
+++ b/drivers/infiniband/hw/cxgb4/device.c
@@ -1114,8 +1114,10 @@ static inline struct sk_buff *copy_gl_to_skb_pkt(const struct pkt_gl *gl,
 	 * The math here assumes sizeof cpl_pass_accept_req >= sizeof
 	 * cpl_rx_pkt.
 	 */
-	skb = alloc_skb(gl->tot_len + sizeof(struct cpl_pass_accept_req) +
-			sizeof(struct rss_header) - pktshift, GFP_ATOMIC);
+	skb = alloc_skb(size_add(gl->tot_len,
+				 sizeof(struct cpl_pass_accept_req) +
+				 sizeof(struct rss_header)) - pktshift,
+			GFP_ATOMIC);
 	if (unlikely(!skb))
 		return NULL;
 
diff --git a/drivers/infiniband/hw/cxgb4/qp.c b/drivers/infiniband/hw/cxgb4/qp.c
index 7b5c4522b426..955f061a55e9 100644
--- a/drivers/infiniband/hw/cxgb4/qp.c
+++ b/drivers/infiniband/hw/cxgb4/qp.c
@@ -1599,6 +1599,7 @@ static void __flush_qp(struct c4iw_qp *qhp, struct c4iw_cq *rchp,
 	int count;
 	int rq_flushed = 0, sq_flushed;
 	unsigned long flag;
+	struct ib_event ev;
 
 	pr_debug("qhp %p rchp %p schp %p\n", qhp, rchp, schp);
 
@@ -1607,6 +1608,13 @@ static void __flush_qp(struct c4iw_qp *qhp, struct c4iw_cq *rchp,
 	if (schp != rchp)
 		spin_lock(&schp->lock);
 	spin_lock(&qhp->lock);
+	if (qhp->srq && qhp->attr.state == C4IW_QP_STATE_ERROR &&
+	    qhp->ibqp.event_handler) {
+		ev.device = qhp->ibqp.device;
+		ev.element.qp = &qhp->ibqp;
+		ev.event = IB_EVENT_QP_LAST_WQE_REACHED;
+		qhp->ibqp.event_handler(&ev, qhp->ibqp.qp_context);
+	}
 
 	if (qhp->wq.flushed) {
 		spin_unlock(&qhp->lock);
diff --git a/drivers/infiniband/hw/efa/efa_main.c b/drivers/infiniband/hw/efa/efa_main.c
index ad225823e6f2..45a4564c670c 100644
--- a/drivers/infiniband/hw/efa/efa_main.c
+++ b/drivers/infiniband/hw/efa/efa_main.c
@@ -470,7 +470,6 @@ static void efa_ib_device_remove(struct efa_dev *dev)
 	ibdev_info(&dev->ibdev, "Unregister ib device\n");
 	ib_unregister_device(&dev->ibdev);
 	efa_destroy_eqs(dev);
-	efa_com_dev_reset(&dev->edev, EFA_REGS_RESET_NORMAL);
 	efa_release_doorbell_bar(dev);
 }
 
@@ -643,12 +642,14 @@ err_disable_device:
 	return ERR_PTR(err);
 }
 
-static void efa_remove_device(struct pci_dev *pdev)
+static void efa_remove_device(struct pci_dev *pdev,
+			      enum efa_regs_reset_reason_types reset_reason)
 {
 	struct efa_dev *dev = pci_get_drvdata(pdev);
 	struct efa_com_dev *edev;
 
 	edev = &dev->edev;
+	efa_com_dev_reset(edev, reset_reason);
 	efa_com_admin_destroy(edev);
 	efa_free_irq(dev, &dev->admin_irq);
 	efa_disable_msix(dev);
@@ -676,7 +677,7 @@ static int efa_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	return 0;
 
 err_remove_device:
-	efa_remove_device(pdev);
+	efa_remove_device(pdev, EFA_REGS_RESET_INIT_ERR);
 	return err;
 }
 
@@ -685,7 +686,7 @@ static void efa_remove(struct pci_dev *pdev)
 	struct efa_dev *dev = pci_get_drvdata(pdev);
 
 	efa_ib_device_remove(dev);
-	efa_remove_device(pdev);
+	efa_remove_device(pdev, EFA_REGS_RESET_NORMAL);
 }
 
 static void efa_shutdown(struct pci_dev *pdev)
diff --git a/drivers/infiniband/hw/erdma/erdma_cm.c b/drivers/infiniband/hw/erdma/erdma_cm.c
index 771059a8eb7d..e349e8d2fb50 100644
--- a/drivers/infiniband/hw/erdma/erdma_cm.c
+++ b/drivers/infiniband/hw/erdma/erdma_cm.c
@@ -705,7 +705,6 @@ error:
 		erdma_cancel_mpatimer(new_cep);
 
 		erdma_cep_put(new_cep);
-		new_cep->sock = NULL;
 	}
 
 	if (new_s) {
diff --git a/drivers/infiniband/hw/erdma/erdma_verbs.c b/drivers/infiniband/hw/erdma/erdma_verbs.c
index 51d619edb6c5..e56ba86d460e 100644
--- a/drivers/infiniband/hw/erdma/erdma_verbs.c
+++ b/drivers/infiniband/hw/erdma/erdma_verbs.c
@@ -597,7 +597,8 @@ err_free_mtt:
 static void erdma_destroy_mtt_buf_sg(struct erdma_dev *dev,
 				     struct erdma_mtt *mtt)
 {
-	dma_unmap_sg(&dev->pdev->dev, mtt->sglist, mtt->nsg, DMA_TO_DEVICE);
+	dma_unmap_sg(&dev->pdev->dev, mtt->sglist,
+		     DIV_ROUND_UP(mtt->size, PAGE_SIZE), DMA_TO_DEVICE);
 	vfree(mtt->sglist);
 }
 
diff --git a/drivers/infiniband/hw/hfi1/affinity.c b/drivers/infiniband/hw/hfi1/affinity.c
index 7ead8746b79b..f2c530ab85a5 100644
--- a/drivers/infiniband/hw/hfi1/affinity.c
+++ b/drivers/infiniband/hw/hfi1/affinity.c
@@ -964,31 +964,35 @@ static void find_hw_thread_mask(uint hw_thread_no, cpumask_var_t hw_thread_mask,
 				struct hfi1_affinity_node_list *affinity)
 {
 	int possible, curr_cpu, i;
-	uint num_cores_per_socket = node_affinity.num_online_cpus /
+	uint num_cores_per_socket;
+
+	cpumask_copy(hw_thread_mask, &affinity->proc.mask);
+
+	if (affinity->num_core_siblings == 0)
+		return;
+
+	num_cores_per_socket = node_affinity.num_online_cpus /
 					affinity->num_core_siblings /
 						node_affinity.num_online_nodes;
 
-	cpumask_copy(hw_thread_mask, &affinity->proc.mask);
-	if (affinity->num_core_siblings > 0) {
-		/* Removing other siblings not needed for now */
-		possible = cpumask_weight(hw_thread_mask);
-		curr_cpu = cpumask_first(hw_thread_mask);
-		for (i = 0;
-		     i < num_cores_per_socket * node_affinity.num_online_nodes;
-		     i++)
-			curr_cpu = cpumask_next(curr_cpu, hw_thread_mask);
-
-		for (; i < possible; i++) {
-			cpumask_clear_cpu(curr_cpu, hw_thread_mask);
-			curr_cpu = cpumask_next(curr_cpu, hw_thread_mask);
-		}
+	/* Removing other siblings not needed for now */
+	possible = cpumask_weight(hw_thread_mask);
+	curr_cpu = cpumask_first(hw_thread_mask);
+	for (i = 0;
+	     i < num_cores_per_socket * node_affinity.num_online_nodes;
+	     i++)
+		curr_cpu = cpumask_next(curr_cpu, hw_thread_mask);
 
-		/* Identifying correct HW threads within physical cores */
-		cpumask_shift_left(hw_thread_mask, hw_thread_mask,
-				   num_cores_per_socket *
-				   node_affinity.num_online_nodes *
-				   hw_thread_no);
+	for (; i < possible; i++) {
+		cpumask_clear_cpu(curr_cpu, hw_thread_mask);
+		curr_cpu = cpumask_next(curr_cpu, hw_thread_mask);
 	}
+
+	/* Identifying correct HW threads within physical cores */
+	cpumask_shift_left(hw_thread_mask, hw_thread_mask,
+			   num_cores_per_socket *
+			   node_affinity.num_online_nodes *
+			   hw_thread_no);
 }
 
 int hfi1_get_proc_affinity(int node)
diff --git a/drivers/infiniband/hw/hns/Kconfig b/drivers/infiniband/hw/hns/Kconfig
index ab3fbba70789..44cdb706fe27 100644
--- a/drivers/infiniband/hw/hns/Kconfig
+++ b/drivers/infiniband/hw/hns/Kconfig
@@ -1,21 +1,11 @@
 # SPDX-License-Identifier: GPL-2.0-only
-config INFINIBAND_HNS
-	tristate "HNS RoCE Driver"
-	depends on NET_VENDOR_HISILICON
-	depends on ARM64 || (COMPILE_TEST && 64BIT)
-	depends on (HNS_DSAF && HNS_ENET) || HNS3
-	help
-	  This is a RoCE/RDMA driver for the Hisilicon RoCE engine.
-
-	  To compile HIP08 driver as module, choose M here.
-
 config INFINIBAND_HNS_HIP08
-	bool "Hisilicon Hip08 Family RoCE support"
-	depends on INFINIBAND_HNS && PCI && HNS3
-	depends on INFINIBAND_HNS=m || HNS3=y
+	tristate "Hisilicon Hip08 Family RoCE support"
+	depends on ARM64 || (COMPILE_TEST && 64BIT)
+	depends on PCI && HNS3
 	help
 	  RoCE driver support for Hisilicon RoCE engine in Hisilicon Hip08 SoC.
 	  The RoCE engine is a PCI device.
 
-	  To compile this driver, choose Y here: if INFINIBAND_HNS is m, this
-	  module will be called hns-roce-hw-v2.
+	  To compile this driver, choose M here. This module will be called
+	  hns-roce-hw-v2.
diff --git a/drivers/infiniband/hw/hns/Makefile b/drivers/infiniband/hw/hns/Makefile
index be1e1cdbcfa8..7917af8e6380 100644
--- a/drivers/infiniband/hw/hns/Makefile
+++ b/drivers/infiniband/hw/hns/Makefile
@@ -5,12 +5,9 @@
 
 ccflags-y :=  -I $(srctree)/drivers/net/ethernet/hisilicon/hns3
 
-hns-roce-objs := hns_roce_main.o hns_roce_cmd.o hns_roce_pd.o \
+hns-roce-hw-v2-objs := hns_roce_main.o hns_roce_cmd.o hns_roce_pd.o \
 	hns_roce_ah.o hns_roce_hem.o hns_roce_mr.o hns_roce_qp.o \
 	hns_roce_cq.o hns_roce_alloc.o hns_roce_db.o hns_roce_srq.o hns_roce_restrack.o \
-	hns_roce_debugfs.o
+	hns_roce_debugfs.o hns_roce_hw_v2.o
 
-ifdef CONFIG_INFINIBAND_HNS_HIP08
-hns-roce-hw-v2-objs := hns_roce_hw_v2.o $(hns-roce-objs)
-obj-$(CONFIG_INFINIBAND_HNS) += hns-roce-hw-v2.o
-endif
+obj-$(CONFIG_INFINIBAND_HNS_HIP08) += hns-roce-hw-v2.o
diff --git a/drivers/infiniband/hw/hns/hns_roce_ah.c b/drivers/infiniband/hw/hns/hns_roce_ah.c
index 4fc5b9d5fea8..307c35888b30 100644
--- a/drivers/infiniband/hw/hns/hns_roce_ah.c
+++ b/drivers/infiniband/hw/hns/hns_roce_ah.c
@@ -33,7 +33,6 @@
 #include <linux/pci.h>
 #include <rdma/ib_addr.h>
 #include <rdma/ib_cache.h>
-#include "hnae3.h"
 #include "hns_roce_device.h"
 #include "hns_roce_hw_v2.h"
 
diff --git a/drivers/infiniband/hw/hns/hns_roce_alloc.c b/drivers/infiniband/hw/hns/hns_roce_alloc.c
index 950c133d4220..6ee911f6885b 100644
--- a/drivers/infiniband/hw/hns/hns_roce_alloc.c
+++ b/drivers/infiniband/hw/hns/hns_roce_alloc.c
@@ -175,8 +175,10 @@ void hns_roce_cleanup_bitmap(struct hns_roce_dev *hr_dev)
 	if (hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_XRC)
 		ida_destroy(&hr_dev->xrcd_ida.ida);
 
-	if (hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_SRQ)
+	if (hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_SRQ) {
 		ida_destroy(&hr_dev->srq_table.srq_ida.ida);
+		xa_destroy(&hr_dev->srq_table.xa);
+	}
 	hns_roce_cleanup_qp_table(hr_dev);
 	hns_roce_cleanup_cq_table(hr_dev);
 	ida_destroy(&hr_dev->mr_table.mtpt_ida.ida);
diff --git a/drivers/infiniband/hw/hns/hns_roce_cq.c b/drivers/infiniband/hw/hns/hns_roce_cq.c
index 4106423a1b39..3a5c93c9fb3e 100644
--- a/drivers/infiniband/hw/hns/hns_roce_cq.c
+++ b/drivers/infiniband/hw/hns/hns_roce_cq.c
@@ -537,5 +537,6 @@ void hns_roce_cleanup_cq_table(struct hns_roce_dev *hr_dev)
 
 	for (i = 0; i < HNS_ROCE_CQ_BANK_NUM; i++)
 		ida_destroy(&hr_dev->cq_table.bank[i].ida);
+	xa_destroy(&hr_dev->cq_table.array);
 	mutex_destroy(&hr_dev->cq_table.bank_mutex);
 }
diff --git a/drivers/infiniband/hw/hns/hns_roce_device.h b/drivers/infiniband/hw/hns/hns_roce_device.h
index 560a1d9de408..cbe73d9ad525 100644
--- a/drivers/infiniband/hw/hns/hns_roce_device.h
+++ b/drivers/infiniband/hw/hns/hns_roce_device.h
@@ -856,6 +856,7 @@ struct hns_roce_caps {
 	u16		default_ceq_arm_st;
 	u8		cong_cap;
 	enum hns_roce_cong_type default_cong_type;
+	u32             max_ack_req_msg_len;
 };
 
 enum hns_roce_device_state {
diff --git a/drivers/infiniband/hw/hns/hns_roce_hem.c b/drivers/infiniband/hw/hns/hns_roce_hem.c
index 605562122ecc..3d479c63b117 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hem.c
+++ b/drivers/infiniband/hw/hns/hns_roce_hem.c
@@ -249,15 +249,12 @@ int hns_roce_calc_hem_mhop(struct hns_roce_dev *hr_dev,
 }
 
 static struct hns_roce_hem *hns_roce_alloc_hem(struct hns_roce_dev *hr_dev,
-					       unsigned long hem_alloc_size,
-					       gfp_t gfp_mask)
+					       unsigned long hem_alloc_size)
 {
 	struct hns_roce_hem *hem;
 	int order;
 	void *buf;
 
-	WARN_ON(gfp_mask & __GFP_HIGHMEM);
-
 	order = get_order(hem_alloc_size);
 	if (PAGE_SIZE << order != hem_alloc_size) {
 		dev_err(hr_dev->dev, "invalid hem_alloc_size: %lu!\n",
@@ -265,13 +262,12 @@ static struct hns_roce_hem *hns_roce_alloc_hem(struct hns_roce_dev *hr_dev,
 		return NULL;
 	}
 
-	hem = kmalloc(sizeof(*hem),
-		      gfp_mask & ~(__GFP_HIGHMEM | __GFP_NOWARN));
+	hem = kmalloc(sizeof(*hem), GFP_KERNEL);
 	if (!hem)
 		return NULL;
 
 	buf = dma_alloc_coherent(hr_dev->dev, hem_alloc_size,
-				 &hem->dma, gfp_mask);
+				 &hem->dma, GFP_KERNEL);
 	if (!buf)
 		goto fail;
 
@@ -378,7 +374,6 @@ static int alloc_mhop_hem(struct hns_roce_dev *hr_dev,
 {
 	u32 bt_size = mhop->bt_chunk_size;
 	struct device *dev = hr_dev->dev;
-	gfp_t flag;
 	u64 bt_ba;
 	u32 size;
 	int ret;
@@ -417,8 +412,7 @@ static int alloc_mhop_hem(struct hns_roce_dev *hr_dev,
 	 * alloc bt space chunk for MTT/CQE.
 	 */
 	size = table->type < HEM_TYPE_MTT ? mhop->buf_chunk_size : bt_size;
-	flag = GFP_KERNEL | __GFP_NOWARN;
-	table->hem[index->buf] = hns_roce_alloc_hem(hr_dev, size, flag);
+	table->hem[index->buf] = hns_roce_alloc_hem(hr_dev, size);
 	if (!table->hem[index->buf]) {
 		ret = -ENOMEM;
 		goto err_alloc_hem;
@@ -546,9 +540,7 @@ int hns_roce_table_get(struct hns_roce_dev *hr_dev,
 		goto out;
 	}
 
-	table->hem[i] = hns_roce_alloc_hem(hr_dev,
-				       table->table_chunk_size,
-				       GFP_KERNEL | __GFP_NOWARN);
+	table->hem[i] = hns_roce_alloc_hem(hr_dev, table->table_chunk_size);
 	if (!table->hem[i]) {
 		ret = -ENOMEM;
 		goto out;
@@ -1361,6 +1353,11 @@ static int hem_list_alloc_root_bt(struct hns_roce_dev *hr_dev,
 	return ret;
 }
 
+/* This is the bottom bt pages number of a 100G MR on 4K OS, assuming
+ * the bt page size is not expanded by cal_best_bt_pg_sz()
+ */
+#define RESCHED_LOOP_CNT_THRESHOLD_ON_4K 12800
+
 /* construct the base address table and link them by address hop config */
 int hns_roce_hem_list_request(struct hns_roce_dev *hr_dev,
 			      struct hns_roce_hem_list *hem_list,
@@ -1369,6 +1366,7 @@ int hns_roce_hem_list_request(struct hns_roce_dev *hr_dev,
 {
 	const struct hns_roce_buf_region *r;
 	int ofs, end;
+	int loop;
 	int unit;
 	int ret;
 	int i;
@@ -1386,7 +1384,10 @@ int hns_roce_hem_list_request(struct hns_roce_dev *hr_dev,
 			continue;
 
 		end = r->offset + r->count;
-		for (ofs = r->offset; ofs < end; ofs += unit) {
+		for (ofs = r->offset, loop = 1; ofs < end; ofs += unit, loop++) {
+			if (!(loop % RESCHED_LOOP_CNT_THRESHOLD_ON_4K))
+				cond_resched();
+
 			ret = hem_list_alloc_mid_bt(hr_dev, r, unit, ofs,
 						    hem_list->mid_bt[i],
 						    &hem_list->btm_bt);
@@ -1443,9 +1444,14 @@ void *hns_roce_hem_list_find_mtt(struct hns_roce_dev *hr_dev,
 	struct list_head *head = &hem_list->btm_bt;
 	struct hns_roce_hem_item *hem, *temp_hem;
 	void *cpu_base = NULL;
+	int loop = 1;
 	int nr = 0;
 
 	list_for_each_entry_safe(hem, temp_hem, head, sibling) {
+		if (!(loop % RESCHED_LOOP_CNT_THRESHOLD_ON_4K))
+			cond_resched();
+		loop++;
+
 		if (hem_list_page_is_in_range(hem, offset)) {
 			nr = offset - hem->start;
 			cpu_base = hem->addr + nr * BA_BYTE_LEN;
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
index 0144e7210d05..53fe0ef3883d 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
@@ -43,7 +43,6 @@
 #include <rdma/ib_umem.h>
 #include <rdma/uverbs_ioctl.h>
 
-#include "hnae3.h"
 #include "hns_roce_common.h"
 #include "hns_roce_device.h"
 #include "hns_roce_cmd.h"
@@ -943,7 +942,7 @@ static void fill_wqe_idx(struct hns_roce_srq *srq, unsigned int wqe_idx)
 static void update_srq_db(struct hns_roce_srq *srq)
 {
 	struct hns_roce_dev *hr_dev = to_hr_dev(srq->ibsrq.device);
-	struct hns_roce_v2_db db;
+	struct hns_roce_v2_db db = {};
 
 	hr_reg_write(&db, DB_TAG, srq->srqn);
 	hr_reg_write(&db, DB_CMD, HNS_ROCE_V2_SRQ_DB);
@@ -1286,10 +1285,8 @@ static u32 hns_roce_cmdq_tx_timeout(u16 opcode, u32 tx_timeout)
 	return tx_timeout;
 }
 
-static void hns_roce_wait_csq_done(struct hns_roce_dev *hr_dev, u16 opcode)
+static void hns_roce_wait_csq_done(struct hns_roce_dev *hr_dev, u32 tx_timeout)
 {
-	struct hns_roce_v2_priv *priv = hr_dev->priv;
-	u32 tx_timeout = hns_roce_cmdq_tx_timeout(opcode, priv->cmq.tx_timeout);
 	u32 timeout = 0;
 
 	do {
@@ -1299,8 +1296,9 @@ static void hns_roce_wait_csq_done(struct hns_roce_dev *hr_dev, u16 opcode)
 	} while (++timeout < tx_timeout);
 }
 
-static int __hns_roce_cmq_send(struct hns_roce_dev *hr_dev,
-			       struct hns_roce_cmq_desc *desc, int num)
+static int __hns_roce_cmq_send_one(struct hns_roce_dev *hr_dev,
+				   struct hns_roce_cmq_desc *desc,
+				   int num, u32 tx_timeout)
 {
 	struct hns_roce_v2_priv *priv = hr_dev->priv;
 	struct hns_roce_v2_cmq_ring *csq = &priv->cmq.csq;
@@ -1309,8 +1307,6 @@ static int __hns_roce_cmq_send(struct hns_roce_dev *hr_dev,
 	int ret;
 	int i;
 
-	spin_lock_bh(&csq->lock);
-
 	tail = csq->head;
 
 	for (i = 0; i < num; i++) {
@@ -1324,22 +1320,17 @@ static int __hns_roce_cmq_send(struct hns_roce_dev *hr_dev,
 
 	atomic64_inc(&hr_dev->dfx_cnt[HNS_ROCE_DFX_CMDS_CNT]);
 
-	hns_roce_wait_csq_done(hr_dev, le16_to_cpu(desc->opcode));
+	hns_roce_wait_csq_done(hr_dev, tx_timeout);
 	if (hns_roce_cmq_csq_done(hr_dev)) {
 		ret = 0;
 		for (i = 0; i < num; i++) {
 			/* check the result of hardware write back */
-			desc[i] = csq->desc[tail++];
+			desc_ret = le16_to_cpu(csq->desc[tail++].retval);
 			if (tail == csq->desc_num)
 				tail = 0;
-
-			desc_ret = le16_to_cpu(desc[i].retval);
 			if (likely(desc_ret == CMD_EXEC_SUCCESS))
 				continue;
 
-			dev_err_ratelimited(hr_dev->dev,
-					    "Cmdq IO error, opcode = 0x%x, return = 0x%x.\n",
-					    desc->opcode, desc_ret);
 			ret = hns_roce_cmd_err_convert_errno(desc_ret);
 		}
 	} else {
@@ -1354,14 +1345,54 @@ static int __hns_roce_cmq_send(struct hns_roce_dev *hr_dev,
 		ret = -EAGAIN;
 	}
 
-	spin_unlock_bh(&csq->lock);
-
 	if (ret)
 		atomic64_inc(&hr_dev->dfx_cnt[HNS_ROCE_DFX_CMDS_ERR_CNT]);
 
 	return ret;
 }
 
+static int __hns_roce_cmq_send(struct hns_roce_dev *hr_dev,
+			       struct hns_roce_cmq_desc *desc, int num)
+{
+	struct hns_roce_v2_priv *priv = hr_dev->priv;
+	struct hns_roce_v2_cmq_ring *csq = &priv->cmq.csq;
+	u16 opcode = le16_to_cpu(desc->opcode);
+	u32 tx_timeout = hns_roce_cmdq_tx_timeout(opcode, priv->cmq.tx_timeout);
+	u8 try_cnt = HNS_ROCE_OPC_POST_MB_TRY_CNT;
+	u32 rsv_tail;
+	int ret;
+	int i;
+
+	while (try_cnt) {
+		try_cnt--;
+
+		spin_lock_bh(&csq->lock);
+		rsv_tail = csq->head;
+		ret = __hns_roce_cmq_send_one(hr_dev, desc, num, tx_timeout);
+		if (opcode == HNS_ROCE_OPC_POST_MB && ret == -ETIME &&
+		    try_cnt) {
+			spin_unlock_bh(&csq->lock);
+			mdelay(HNS_ROCE_OPC_POST_MB_RETRY_GAP_MSEC);
+			continue;
+		}
+
+		for (i = 0; i < num; i++) {
+			desc[i] = csq->desc[rsv_tail++];
+			if (rsv_tail == csq->desc_num)
+				rsv_tail = 0;
+		}
+		spin_unlock_bh(&csq->lock);
+		break;
+	}
+
+	if (ret)
+		dev_err_ratelimited(hr_dev->dev,
+				    "Cmdq IO error, opcode = 0x%x, return = %d.\n",
+				    opcode, ret);
+
+	return ret;
+}
+
 static int hns_roce_cmq_send(struct hns_roce_dev *hr_dev,
 			     struct hns_roce_cmq_desc *desc, int num)
 {
@@ -2150,31 +2181,36 @@ static void apply_func_caps(struct hns_roce_dev *hr_dev)
 
 static int hns_roce_query_caps(struct hns_roce_dev *hr_dev)
 {
-	struct hns_roce_cmq_desc desc[HNS_ROCE_QUERY_PF_CAPS_CMD_NUM];
+	struct hns_roce_cmq_desc desc[HNS_ROCE_QUERY_PF_CAPS_CMD_NUM] = {};
 	struct hns_roce_caps *caps = &hr_dev->caps;
 	struct hns_roce_query_pf_caps_a *resp_a;
 	struct hns_roce_query_pf_caps_b *resp_b;
 	struct hns_roce_query_pf_caps_c *resp_c;
 	struct hns_roce_query_pf_caps_d *resp_d;
 	struct hns_roce_query_pf_caps_e *resp_e;
+	struct hns_roce_query_pf_caps_f *resp_f;
 	enum hns_roce_opcode_type cmd;
 	int ctx_hop_num;
 	int pbl_hop_num;
+	int cmd_num;
 	int ret;
 	int i;
 
 	cmd = hr_dev->is_vf ? HNS_ROCE_OPC_QUERY_VF_CAPS_NUM :
 	      HNS_ROCE_OPC_QUERY_PF_CAPS_NUM;
+	cmd_num = hr_dev->pci_dev->revision == PCI_REVISION_ID_HIP08 ?
+		  HNS_ROCE_QUERY_PF_CAPS_CMD_NUM_HIP08 :
+		  HNS_ROCE_QUERY_PF_CAPS_CMD_NUM;
 
-	for (i = 0; i < HNS_ROCE_QUERY_PF_CAPS_CMD_NUM; i++) {
+	for (i = 0; i < cmd_num - 1; i++) {
 		hns_roce_cmq_setup_basic_desc(&desc[i], cmd, true);
-		if (i < (HNS_ROCE_QUERY_PF_CAPS_CMD_NUM - 1))
-			desc[i].flag |= cpu_to_le16(HNS_ROCE_CMD_FLAG_NEXT);
-		else
-			desc[i].flag &= ~cpu_to_le16(HNS_ROCE_CMD_FLAG_NEXT);
+		desc[i].flag |= cpu_to_le16(HNS_ROCE_CMD_FLAG_NEXT);
 	}
 
-	ret = hns_roce_cmq_send(hr_dev, desc, HNS_ROCE_QUERY_PF_CAPS_CMD_NUM);
+	hns_roce_cmq_setup_basic_desc(&desc[cmd_num - 1], cmd, true);
+	desc[cmd_num - 1].flag &= ~cpu_to_le16(HNS_ROCE_CMD_FLAG_NEXT);
+
+	ret = hns_roce_cmq_send(hr_dev, desc, cmd_num);
 	if (ret)
 		return ret;
 
@@ -2183,6 +2219,7 @@ static int hns_roce_query_caps(struct hns_roce_dev *hr_dev)
 	resp_c = (struct hns_roce_query_pf_caps_c *)desc[2].data;
 	resp_d = (struct hns_roce_query_pf_caps_d *)desc[3].data;
 	resp_e = (struct hns_roce_query_pf_caps_e *)desc[4].data;
+	resp_f = (struct hns_roce_query_pf_caps_f *)desc[5].data;
 
 	caps->local_ca_ack_delay = resp_a->local_ca_ack_delay;
 	caps->max_sq_sg = le16_to_cpu(resp_a->max_sq_sg);
@@ -2247,6 +2284,8 @@ static int hns_roce_query_caps(struct hns_roce_dev *hr_dev)
 	caps->reserved_srqs = hr_reg_read(resp_e, PF_CAPS_E_RSV_SRQS);
 	caps->reserved_lkey = hr_reg_read(resp_e, PF_CAPS_E_RSV_LKEYS);
 
+	caps->max_ack_req_msg_len = le32_to_cpu(resp_f->max_ack_req_msg_len);
+
 	caps->qpc_hop_num = ctx_hop_num;
 	caps->sccc_hop_num = ctx_hop_num;
 	caps->srqc_hop_num = ctx_hop_num;
@@ -2940,14 +2979,22 @@ static int hns_roce_v2_init(struct hns_roce_dev *hr_dev)
 {
 	int ret;
 
+	if (hr_dev->pci_dev->revision == PCI_REVISION_ID_HIP08) {
+		ret = free_mr_init(hr_dev);
+		if (ret) {
+			dev_err(hr_dev->dev, "failed to init free mr!\n");
+			return ret;
+		}
+	}
+
 	/* The hns ROCEE requires the extdb info to be cleared before using */
 	ret = hns_roce_clear_extdb_list_info(hr_dev);
 	if (ret)
-		return ret;
+		goto err_clear_extdb_failed;
 
 	ret = get_hem_table(hr_dev);
 	if (ret)
-		return ret;
+		goto err_get_hem_table_failed;
 
 	if (hr_dev->is_vf)
 		return 0;
@@ -2962,6 +3009,11 @@ static int hns_roce_v2_init(struct hns_roce_dev *hr_dev)
 
 err_llm_init_failed:
 	put_hem_table(hr_dev);
+err_get_hem_table_failed:
+	hns_roce_function_clear(hr_dev);
+err_clear_extdb_failed:
+	if (hr_dev->pci_dev->revision == PCI_REVISION_ID_HIP08)
+		free_mr_exit(hr_dev);
 
 	return ret;
 }
@@ -4515,7 +4567,9 @@ static int modify_qp_init_to_rtr(struct ib_qp *ibqp,
 	dma_addr_t trrl_ba;
 	dma_addr_t irrl_ba;
 	enum ib_mtu ib_mtu;
+	u8 ack_req_freq;
 	const u8 *smac;
+	int lp_msg_len;
 	u8 lp_pktn_ini;
 	u64 *mtts;
 	u8 *dmac;
@@ -4598,7 +4652,8 @@ static int modify_qp_init_to_rtr(struct ib_qp *ibqp,
 		return -EINVAL;
 #define MIN_LP_MSG_LEN 1024
 	/* mtu * (2 ^ lp_pktn_ini) should be in the range of 1024 to mtu */
-	lp_pktn_ini = ilog2(max(mtu, MIN_LP_MSG_LEN) / mtu);
+	lp_msg_len = max(mtu, MIN_LP_MSG_LEN);
+	lp_pktn_ini = ilog2(lp_msg_len / mtu);
 
 	if (attr_mask & IB_QP_PATH_MTU) {
 		hr_reg_write(context, QPC_MTU, ib_mtu);
@@ -4608,8 +4663,22 @@ static int modify_qp_init_to_rtr(struct ib_qp *ibqp,
 	hr_reg_write(context, QPC_LP_PKTN_INI, lp_pktn_ini);
 	hr_reg_clear(qpc_mask, QPC_LP_PKTN_INI);
 
-	/* ACK_REQ_FREQ should be larger than or equal to LP_PKTN_INI */
-	hr_reg_write(context, QPC_ACK_REQ_FREQ, lp_pktn_ini);
+	/*
+	 * There are several constraints for ACK_REQ_FREQ:
+	 * 1. mtu * (2 ^ ACK_REQ_FREQ) should not be too large, otherwise
+	 *    it may cause some unexpected retries when sending large
+	 *    payload.
+	 * 2. ACK_REQ_FREQ should be larger than or equal to LP_PKTN_INI.
+	 * 3. ACK_REQ_FREQ must be equal to LP_PKTN_INI when using LDCP
+	 *    or HC3 congestion control algorithm.
+	 */
+	if (hr_qp->cong_type == CONG_TYPE_LDCP ||
+	    hr_qp->cong_type == CONG_TYPE_HC3 ||
+	    hr_dev->caps.max_ack_req_msg_len < lp_msg_len)
+		ack_req_freq = lp_pktn_ini;
+	else
+		ack_req_freq = ilog2(hr_dev->caps.max_ack_req_msg_len / mtu);
+	hr_reg_write(context, QPC_ACK_REQ_FREQ, ack_req_freq);
 	hr_reg_clear(qpc_mask, QPC_ACK_REQ_FREQ);
 
 	hr_reg_clear(qpc_mask, QPC_RX_REQ_PSN_ERR);
@@ -5302,11 +5371,10 @@ static int hns_roce_v2_modify_qp(struct ib_qp *ibqp,
 {
 	struct hns_roce_dev *hr_dev = to_hr_dev(ibqp->device);
 	struct hns_roce_qp *hr_qp = to_hr_qp(ibqp);
-	struct hns_roce_v2_qp_context ctx[2];
-	struct hns_roce_v2_qp_context *context = ctx;
-	struct hns_roce_v2_qp_context *qpc_mask = ctx + 1;
+	struct hns_roce_v2_qp_context *context;
+	struct hns_roce_v2_qp_context *qpc_mask;
 	struct ib_device *ibdev = &hr_dev->ib_dev;
-	int ret;
+	int ret = -ENOMEM;
 
 	if (attr_mask & ~IB_QP_ATTR_STANDARD_BITS)
 		return -EOPNOTSUPP;
@@ -5317,7 +5385,11 @@ static int hns_roce_v2_modify_qp(struct ib_qp *ibqp,
 	 * we should set all bits of the relevant fields in context mask to
 	 * 0 at the same time, else set them to 0x1.
 	 */
-	memset(context, 0, hr_dev->caps.qpc_sz);
+	context = kvzalloc(sizeof(*context), GFP_KERNEL);
+	qpc_mask = kvzalloc(sizeof(*qpc_mask), GFP_KERNEL);
+	if (!context || !qpc_mask)
+		goto out;
+
 	memset(qpc_mask, 0xff, hr_dev->caps.qpc_sz);
 
 	ret = hns_roce_v2_set_abs_fields(ibqp, attr, attr_mask, cur_state,
@@ -5359,6 +5431,8 @@ static int hns_roce_v2_modify_qp(struct ib_qp *ibqp,
 		clear_qp(hr_qp);
 
 out:
+	kvfree(qpc_mask);
+	kvfree(context);
 	return ret;
 }
 
@@ -6996,21 +7070,11 @@ static int __hns_roce_hw_v2_init_instance(struct hnae3_handle *handle)
 		goto error_failed_roce_init;
 	}
 
-	if (hr_dev->pci_dev->revision == PCI_REVISION_ID_HIP08) {
-		ret = free_mr_init(hr_dev);
-		if (ret) {
-			dev_err(hr_dev->dev, "failed to init free mr!\n");
-			goto error_failed_free_mr_init;
-		}
-	}
 
 	handle->priv = hr_dev;
 
 	return 0;
 
-error_failed_free_mr_init:
-	hns_roce_exit(hr_dev);
-
 error_failed_roce_init:
 	kfree(hr_dev->priv);
 
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
index cbdbc9edbce6..1c2660305d27 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
@@ -34,6 +34,7 @@
 #define _HNS_ROCE_HW_V2_H
 
 #include <linux/bitops.h>
+#include "hnae3.h"
 
 #define HNS_ROCE_V2_MAX_RC_INL_INN_SZ		32
 #define HNS_ROCE_V2_MTT_ENTRY_SZ		64
@@ -230,6 +231,8 @@ enum hns_roce_opcode_type {
 };
 
 #define HNS_ROCE_OPC_POST_MB_TIMEOUT 35000
+#define HNS_ROCE_OPC_POST_MB_TRY_CNT 8
+#define HNS_ROCE_OPC_POST_MB_RETRY_GAP_MSEC 5
 struct hns_roce_cmdq_tx_timeout_map {
 	u16 opcode;
 	u32 tx_timeout;
@@ -1165,7 +1168,8 @@ struct hns_roce_cfg_gmv_tb_b {
 #define GMV_TB_B_SMAC_H GMV_TB_B_FIELD_LOC(47, 32)
 #define GMV_TB_B_SGID_IDX GMV_TB_B_FIELD_LOC(71, 64)
 
-#define HNS_ROCE_QUERY_PF_CAPS_CMD_NUM 5
+#define HNS_ROCE_QUERY_PF_CAPS_CMD_NUM_HIP08 5
+#define HNS_ROCE_QUERY_PF_CAPS_CMD_NUM 6
 struct hns_roce_query_pf_caps_a {
 	u8 number_ports;
 	u8 local_ca_ack_delay;
@@ -1277,6 +1281,11 @@ struct hns_roce_query_pf_caps_e {
 	__le16 aeq_period;
 };
 
+struct hns_roce_query_pf_caps_f {
+	__le32 max_ack_req_msg_len;
+	__le32 rsv[5];
+};
+
 #define PF_CAPS_E_FIELD_LOC(h, l) \
 	FIELD_LOC(struct hns_roce_query_pf_caps_e, h, l)
 
diff --git a/drivers/infiniband/hw/hns/hns_roce_main.c b/drivers/infiniband/hw/hns/hns_roce_main.c
index ae24c81c9812..11fa64044a8d 100644
--- a/drivers/infiniband/hw/hns/hns_roce_main.c
+++ b/drivers/infiniband/hw/hns/hns_roce_main.c
@@ -37,7 +37,6 @@
 #include <rdma/ib_smi.h>
 #include <rdma/ib_user_verbs.h>
 #include <rdma/ib_cache.h>
-#include "hnae3.h"
 #include "hns_roce_common.h"
 #include "hns_roce_device.h"
 #include "hns_roce_hem.h"
@@ -183,7 +182,7 @@ static int hns_roce_query_device(struct ib_device *ib_dev,
 				  IB_DEVICE_RC_RNR_NAK_GEN;
 	props->max_send_sge = hr_dev->caps.max_sq_sg;
 	props->max_recv_sge = hr_dev->caps.max_rq_sg;
-	props->max_sge_rd = 1;
+	props->max_sge_rd = hr_dev->caps.max_sq_sg;
 	props->max_cq = hr_dev->caps.num_cqs;
 	props->max_cqe = hr_dev->caps.max_cqes;
 	props->max_mr = hr_dev->caps.num_mtpts;
@@ -763,7 +762,7 @@ static int hns_roce_register_device(struct hns_roce_dev *hr_dev)
 		if (ret)
 			return ret;
 	}
-	dma_set_max_seg_size(dev, UINT_MAX);
+	dma_set_max_seg_size(dev, SZ_2G);
 	ret = ib_register_device(ib_dev, "hns_%d", dev);
 	if (ret) {
 		dev_err(dev, "ib_register_device failed!\n");
@@ -948,10 +947,7 @@ err_unmap_dmpt:
 static void hns_roce_teardown_hca(struct hns_roce_dev *hr_dev)
 {
 	hns_roce_cleanup_bitmap(hr_dev);
-
-	if (hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_CQ_RECORD_DB ||
-	    hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_QP_RECORD_DB)
-		mutex_destroy(&hr_dev->pgdir_mutex);
+	mutex_destroy(&hr_dev->pgdir_mutex);
 }
 
 /**
@@ -966,11 +962,11 @@ static int hns_roce_setup_hca(struct hns_roce_dev *hr_dev)
 
 	spin_lock_init(&hr_dev->sm_lock);
 
-	if (hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_CQ_RECORD_DB ||
-	    hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_QP_RECORD_DB) {
-		INIT_LIST_HEAD(&hr_dev->pgdir_list);
-		mutex_init(&hr_dev->pgdir_mutex);
-	}
+	INIT_LIST_HEAD(&hr_dev->qp_list);
+	spin_lock_init(&hr_dev->qp_list_lock);
+
+	INIT_LIST_HEAD(&hr_dev->pgdir_list);
+	mutex_init(&hr_dev->pgdir_mutex);
 
 	hns_roce_init_uar_table(hr_dev);
 
@@ -1002,9 +998,7 @@ static int hns_roce_setup_hca(struct hns_roce_dev *hr_dev)
 
 err_uar_table_free:
 	ida_destroy(&hr_dev->uar_ida.ida);
-	if (hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_CQ_RECORD_DB ||
-	    hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_QP_RECORD_DB)
-		mutex_destroy(&hr_dev->pgdir_mutex);
+	mutex_destroy(&hr_dev->pgdir_mutex);
 
 	return ret;
 }
@@ -1133,9 +1127,6 @@ int hns_roce_init(struct hns_roce_dev *hr_dev)
 		}
 	}
 
-	INIT_LIST_HEAD(&hr_dev->qp_list);
-	spin_lock_init(&hr_dev->qp_list_lock);
-
 	ret = hns_roce_register_device(hr_dev);
 	if (ret)
 		goto error_failed_register_device;
diff --git a/drivers/infiniband/hw/hns/hns_roce_qp.c b/drivers/infiniband/hw/hns/hns_roce_qp.c
index 9e2e76c59406..8901c142c1b6 100644
--- a/drivers/infiniband/hw/hns/hns_roce_qp.c
+++ b/drivers/infiniband/hw/hns/hns_roce_qp.c
@@ -868,12 +868,14 @@ static int alloc_user_qp_db(struct hns_roce_dev *hr_dev,
 			    struct hns_roce_ib_create_qp *ucmd,
 			    struct hns_roce_ib_create_qp_resp *resp)
 {
+	bool has_sdb = user_qp_has_sdb(hr_dev, init_attr, udata, resp, ucmd);
 	struct hns_roce_ucontext *uctx = rdma_udata_to_drv_context(udata,
 		struct hns_roce_ucontext, ibucontext);
+	bool has_rdb = user_qp_has_rdb(hr_dev, init_attr, udata, resp);
 	struct ib_device *ibdev = &hr_dev->ib_dev;
 	int ret;
 
-	if (user_qp_has_sdb(hr_dev, init_attr, udata, resp, ucmd)) {
+	if (has_sdb) {
 		ret = hns_roce_db_map_user(uctx, ucmd->sdb_addr, &hr_qp->sdb);
 		if (ret) {
 			ibdev_err(ibdev,
@@ -884,7 +886,7 @@ static int alloc_user_qp_db(struct hns_roce_dev *hr_dev,
 		hr_qp->en_flags |= HNS_ROCE_QP_CAP_SQ_RECORD_DB;
 	}
 
-	if (user_qp_has_rdb(hr_dev, init_attr, udata, resp)) {
+	if (has_rdb) {
 		ret = hns_roce_db_map_user(uctx, ucmd->db_addr, &hr_qp->rdb);
 		if (ret) {
 			ibdev_err(ibdev,
@@ -898,7 +900,7 @@ static int alloc_user_qp_db(struct hns_roce_dev *hr_dev,
 	return 0;
 
 err_sdb:
-	if (hr_qp->en_flags & HNS_ROCE_QP_CAP_SQ_RECORD_DB)
+	if (has_sdb)
 		hns_roce_db_unmap_user(uctx, &hr_qp->sdb);
 err_out:
 	return ret;
@@ -1119,24 +1121,23 @@ static int set_qp_param(struct hns_roce_dev *hr_dev, struct hns_roce_qp *hr_qp,
 						 ibucontext);
 		hr_qp->config = uctx->config;
 		ret = set_user_sq_size(hr_dev, &init_attr->cap, hr_qp, ucmd);
-		if (ret)
+		if (ret) {
 			ibdev_err(ibdev,
 				  "failed to set user SQ size, ret = %d.\n",
 				  ret);
+			return ret;
+		}
 
 		ret = set_congest_param(hr_dev, hr_qp, ucmd);
-		if (ret)
-			return ret;
 	} else {
 		if (hr_dev->pci_dev->revision >= PCI_REVISION_ID_HIP09)
 			hr_qp->config = HNS_ROCE_EXSGE_FLAGS;
+		default_congest_type(hr_dev, hr_qp);
 		ret = set_kernel_sq_size(hr_dev, &init_attr->cap, hr_qp);
 		if (ret)
 			ibdev_err(ibdev,
 				  "failed to set kernel SQ size, ret = %d.\n",
 				  ret);
-
-		default_congest_type(hr_dev, hr_qp);
 	}
 
 	return ret;
@@ -1219,7 +1220,7 @@ static int hns_roce_create_qp_common(struct hns_roce_dev *hr_dev,
 				       min(udata->outlen, sizeof(resp)));
 		if (ret) {
 			ibdev_err(ibdev, "copy qp resp failed!\n");
-			goto err_store;
+			goto err_flow_ctrl;
 		}
 	}
 
@@ -1602,6 +1603,7 @@ void hns_roce_cleanup_qp_table(struct hns_roce_dev *hr_dev)
 	for (i = 0; i < HNS_ROCE_QP_BANK_NUM; i++)
 		ida_destroy(&hr_dev->qp_table.bank[i].ida);
 	xa_destroy(&hr_dev->qp_table.dip_xa);
+	xa_destroy(&hr_dev->qp_table_xa);
 	mutex_destroy(&hr_dev->qp_table.bank_mutex);
 	mutex_destroy(&hr_dev->qp_table.scc_mutex);
 }
diff --git a/drivers/infiniband/hw/hns/hns_roce_restrack.c b/drivers/infiniband/hw/hns/hns_roce_restrack.c
index 356d98816949..f637b73b946e 100644
--- a/drivers/infiniband/hw/hns/hns_roce_restrack.c
+++ b/drivers/infiniband/hw/hns/hns_roce_restrack.c
@@ -4,7 +4,6 @@
 #include <rdma/rdma_cm.h>
 #include <rdma/restrack.h>
 #include <uapi/rdma/rdma_netlink.h>
-#include "hnae3.h"
 #include "hns_roce_common.h"
 #include "hns_roce_device.h"
 #include "hns_roce_hw_v2.h"
diff --git a/drivers/infiniband/hw/mana/main.c b/drivers/infiniband/hw/mana/main.c
index 67c2d43135a8..f6bf289041bf 100644
--- a/drivers/infiniband/hw/mana/main.c
+++ b/drivers/infiniband/hw/mana/main.c
@@ -174,7 +174,7 @@ static int mana_gd_allocate_doorbell_page(struct gdma_context *gc,
 
 	req.resource_type = GDMA_RESOURCE_DOORBELL_PAGE;
 	req.num_resources = 1;
-	req.alignment = 1;
+	req.alignment = PAGE_SIZE / MANA_PAGE_SIZE;
 
 	/* Have GDMA start searching from 0 */
 	req.allocated_resources = 0;
@@ -358,7 +358,7 @@ static int mana_ib_gd_create_dma_region(struct mana_ib_dev *dev, struct ib_umem
 	unsigned int tail = 0;
 	u64 *page_addr_list;
 	void *request_buf;
-	int err;
+	int err = 0;
 
 	gc = mdev_to_gc(dev);
 	hwc = gc->hwc.driver_data;
diff --git a/drivers/infiniband/hw/mana/qp.c b/drivers/infiniband/hw/mana/qp.c
index 73d67c853b6f..48fef989318b 100644
--- a/drivers/infiniband/hw/mana/qp.c
+++ b/drivers/infiniband/hw/mana/qp.c
@@ -561,7 +561,7 @@ static int mana_ib_gd_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 		req.ah_attr.dest_port = ROCE_V2_UDP_DPORT;
 		req.ah_attr.src_port = rdma_get_udp_sport(attr->ah_attr.grh.flow_label,
 							  ibqp->qp_num, attr->dest_qp_num);
-		req.ah_attr.traffic_class = attr->ah_attr.grh.traffic_class;
+		req.ah_attr.traffic_class = attr->ah_attr.grh.traffic_class >> 2;
 		req.ah_attr.hop_limit = attr->ah_attr.grh.hop_limit;
 	}
 
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 529db874d67c..b1bbdcff631d 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -351,7 +351,7 @@ static int mlx4_ib_del_gid(const struct ib_gid_attr *attr, void **context)
 	struct mlx4_port_gid_table   *port_gid_table;
 	int ret = 0;
 	int hw_update = 0;
-	struct gid_entry *gids;
+	struct gid_entry *gids = NULL;
 
 	if (!rdma_cap_roce_gid_table(attr->device, attr->port_num))
 		return -EINVAL;
@@ -389,10 +389,10 @@ static int mlx4_ib_del_gid(const struct ib_gid_attr *attr, void **context)
 	}
 	spin_unlock_bh(&iboe->lock);
 
-	if (!ret && hw_update) {
+	if (gids)
 		ret = mlx4_ib_update_gids(gids, ibdev, attr->port_num);
-		kfree(gids);
-	}
+
+	kfree(gids);
 	return ret;
 }
 
diff --git a/drivers/infiniband/hw/mlx5/ah.c b/drivers/infiniband/hw/mlx5/ah.c
index 505bc47fd575..531a57f9ee7e 100644
--- a/drivers/infiniband/hw/mlx5/ah.c
+++ b/drivers/infiniband/hw/mlx5/ah.c
@@ -50,11 +50,12 @@ static __be16 mlx5_ah_get_udp_sport(const struct mlx5_ib_dev *dev,
 	return sport;
 }
 
-static void create_ib_ah(struct mlx5_ib_dev *dev, struct mlx5_ib_ah *ah,
+static int create_ib_ah(struct mlx5_ib_dev *dev, struct mlx5_ib_ah *ah,
 			 struct rdma_ah_init_attr *init_attr)
 {
 	struct rdma_ah_attr *ah_attr = init_attr->ah_attr;
 	enum ib_gid_type gid_type;
+	int rate_val;
 
 	if (rdma_ah_get_ah_flags(ah_attr) & IB_AH_GRH) {
 		const struct ib_global_route *grh = rdma_ah_read_grh(ah_attr);
@@ -67,7 +68,10 @@ static void create_ib_ah(struct mlx5_ib_dev *dev, struct mlx5_ib_ah *ah,
 		ah->av.tclass = grh->traffic_class;
 	}
 
-	ah->av.stat_rate_sl = (rdma_ah_get_static_rate(ah_attr) << 4);
+	rate_val = mlx5r_ib_rate(dev, rdma_ah_get_static_rate(ah_attr));
+	if (rate_val < 0)
+		return rate_val;
+	ah->av.stat_rate_sl = rate_val << 4;
 
 	if (ah_attr->type == RDMA_AH_ATTR_TYPE_ROCE) {
 		if (init_attr->xmit_slave)
@@ -88,6 +92,8 @@ static void create_ib_ah(struct mlx5_ib_dev *dev, struct mlx5_ib_ah *ah,
 		ah->av.fl_mlid = rdma_ah_get_path_bits(ah_attr) & 0x7f;
 		ah->av.stat_rate_sl |= (rdma_ah_get_sl(ah_attr) & 0xf);
 	}
+
+	return 0;
 }
 
 int mlx5_ib_create_ah(struct ib_ah *ibah, struct rdma_ah_init_attr *init_attr,
@@ -120,8 +126,7 @@ int mlx5_ib_create_ah(struct ib_ah *ibah, struct rdma_ah_init_attr *init_attr,
 			return err;
 	}
 
-	create_ib_ah(dev, ah, init_attr);
-	return 0;
+	return create_ib_ah(dev, ah, init_attr);
 }
 
 int mlx5_ib_query_ah(struct ib_ah *ibah, struct rdma_ah_attr *ah_attr)
diff --git a/drivers/infiniband/hw/mlx5/counters.c b/drivers/infiniband/hw/mlx5/counters.c
index 4f6c1968a2ee..ad6c195d077b 100644
--- a/drivers/infiniband/hw/mlx5/counters.c
+++ b/drivers/infiniband/hw/mlx5/counters.c
@@ -391,7 +391,7 @@ static int do_get_hw_stats(struct ib_device *ibdev,
 		return ret;
 
 	/* We don't expose device counters over Vports */
-	if (is_mdev_switchdev_mode(dev->mdev) && port_num != 0)
+	if (is_mdev_switchdev_mode(dev->mdev) && dev->is_rep && port_num != 0)
 		goto done;
 
 	if (MLX5_CAP_PCAM_FEATURE(dev->mdev, rx_icrc_encapsulated_counter)) {
@@ -411,7 +411,7 @@ static int do_get_hw_stats(struct ib_device *ibdev,
 			 */
 			goto done;
 		}
-		ret = mlx5_lag_query_cong_counters(dev->mdev,
+		ret = mlx5_lag_query_cong_counters(mdev,
 						   stats->value +
 						   cnts->num_q_counters,
 						   cnts->num_cong_counters,
@@ -546,6 +546,7 @@ static int mlx5_ib_counter_bind_qp(struct rdma_counter *counter,
 				   struct ib_qp *qp)
 {
 	struct mlx5_ib_dev *dev = to_mdev(qp->device);
+	bool new = false;
 	int err;
 
 	if (!counter->id) {
@@ -560,6 +561,7 @@ static int mlx5_ib_counter_bind_qp(struct rdma_counter *counter,
 			return err;
 		counter->id =
 			MLX5_GET(alloc_q_counter_out, out, counter_set_id);
+		new = true;
 	}
 
 	err = mlx5_ib_qp_set_counter(qp, counter);
@@ -569,8 +571,10 @@ static int mlx5_ib_counter_bind_qp(struct rdma_counter *counter,
 	return 0;
 
 fail_set_counter:
-	mlx5_ib_counter_dealloc(counter);
-	counter->id = 0;
+	if (new) {
+		mlx5_ib_counter_dealloc(counter);
+		counter->id = 0;
+	}
 
 	return err;
 }
diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c
index 4c54dc578069..1aa5311b03e9 100644
--- a/drivers/infiniband/hw/mlx5/cq.c
+++ b/drivers/infiniband/hw/mlx5/cq.c
@@ -490,7 +490,7 @@ repoll:
 	}
 
 	qpn = ntohl(cqe64->sop_drop_qpn) & 0xffffff;
-	if (!*cur_qp || (qpn != (*cur_qp)->ibqp.qp_num)) {
+	if (!*cur_qp || (qpn != (*cur_qp)->trans_qp.base.mqp.qpn)) {
 		/* We do not have to take the QP table lock here,
 		 * because CQs will be locked while QPs are removed
 		 * from the table.
diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c
index 69999d8d24f3..f49f78b69ab9 100644
--- a/drivers/infiniband/hw/mlx5/devx.c
+++ b/drivers/infiniband/hw/mlx5/devx.c
@@ -1914,6 +1914,7 @@ subscribe_event_xa_alloc(struct mlx5_devx_event_table *devx_event_table,
 			/* Level1 is valid for future use, no need to free */
 			return -ENOMEM;
 
+		INIT_LIST_HEAD(&obj_event->obj_sub_list);
 		err = xa_insert(&event->object_ids,
 				key_level2,
 				obj_event,
@@ -1922,7 +1923,6 @@ subscribe_event_xa_alloc(struct mlx5_devx_event_table *devx_event_table,
 			kfree(obj_event);
 			return err;
 		}
-		INIT_LIST_HEAD(&obj_event->obj_sub_list);
 	}
 
 	return 0;
diff --git a/drivers/infiniband/hw/mlx5/dm.c b/drivers/infiniband/hw/mlx5/dm.c
index b4c97fb62abf..9ded2b7c1e31 100644
--- a/drivers/infiniband/hw/mlx5/dm.c
+++ b/drivers/infiniband/hw/mlx5/dm.c
@@ -282,7 +282,7 @@ static struct ib_dm *handle_alloc_dm_memic(struct ib_ucontext *ctx,
 	int err;
 	u64 address;
 
-	if (!MLX5_CAP_DEV_MEM(dm_db->dev, memic))
+	if (!dm_db || !MLX5_CAP_DEV_MEM(dm_db->dev, memic))
 		return ERR_PTR(-EOPNOTSUPP);
 
 	dm = kzalloc(sizeof(*dm), GFP_KERNEL);
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 8c47cb4edd0a..435c456a4fd5 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -1766,6 +1766,33 @@ static void deallocate_uars(struct mlx5_ib_dev *dev,
 					     context->devx_uid);
 }
 
+static int mlx5_ib_enable_lb_mp(struct mlx5_core_dev *master,
+				struct mlx5_core_dev *slave)
+{
+	int err;
+
+	err = mlx5_nic_vport_update_local_lb(master, true);
+	if (err)
+		return err;
+
+	err = mlx5_nic_vport_update_local_lb(slave, true);
+	if (err)
+		goto out;
+
+	return 0;
+
+out:
+	mlx5_nic_vport_update_local_lb(master, false);
+	return err;
+}
+
+static void mlx5_ib_disable_lb_mp(struct mlx5_core_dev *master,
+				  struct mlx5_core_dev *slave)
+{
+	mlx5_nic_vport_update_local_lb(slave, false);
+	mlx5_nic_vport_update_local_lb(master, false);
+}
+
 int mlx5_ib_enable_lb(struct mlx5_ib_dev *dev, bool td, bool qp)
 {
 	int err = 0;
@@ -3448,6 +3475,8 @@ static void mlx5_ib_unbind_slave_port(struct mlx5_ib_dev *ibdev,
 
 	lockdep_assert_held(&mlx5_ib_multiport_mutex);
 
+	mlx5_ib_disable_lb_mp(ibdev->mdev, mpi->mdev);
+
 	mlx5_core_mp_event_replay(ibdev->mdev,
 				  MLX5_DRIVER_EVENT_AFFILIATION_REMOVED,
 				  NULL);
@@ -3543,6 +3572,10 @@ static bool mlx5_ib_bind_slave_port(struct mlx5_ib_dev *ibdev,
 				  MLX5_DRIVER_EVENT_AFFILIATION_DONE,
 				  &key);
 
+	err = mlx5_ib_enable_lb_mp(ibdev->mdev, mpi->mdev);
+	if (err)
+		goto unbind;
+
 	return true;
 
 unbind:
diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index 45d9dc9c6c8f..726b81b6330c 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -56,7 +56,7 @@ static void
 create_mkey_callback(int status, struct mlx5_async_work *context);
 static struct mlx5_ib_mr *reg_create(struct ib_pd *pd, struct ib_umem *umem,
 				     u64 iova, int access_flags,
-				     unsigned int page_size, bool populate,
+				     unsigned long page_size, bool populate,
 				     int access_mode);
 static int __mlx5_ib_dereg_mr(struct ib_mr *ibmr);
 
@@ -919,6 +919,25 @@ mkeys_err:
 	return ERR_PTR(ret);
 }
 
+static void mlx5r_destroy_cache_entries(struct mlx5_ib_dev *dev)
+{
+	struct rb_root *root = &dev->cache.rb_root;
+	struct mlx5_cache_ent *ent;
+	struct rb_node *node;
+
+	mutex_lock(&dev->cache.rb_lock);
+	node = rb_first(root);
+	while (node) {
+		ent = rb_entry(node, struct mlx5_cache_ent, node);
+		node = rb_next(node);
+		clean_keys(dev, ent);
+		rb_erase(&ent->node, root);
+		mlx5r_mkeys_uninit(ent);
+		kfree(ent);
+	}
+	mutex_unlock(&dev->cache.rb_lock);
+}
+
 int mlx5_mkey_cache_init(struct mlx5_ib_dev *dev)
 {
 	struct mlx5_mkey_cache *cache = &dev->cache;
@@ -970,6 +989,8 @@ int mlx5_mkey_cache_init(struct mlx5_ib_dev *dev)
 err:
 	mutex_unlock(&cache->rb_lock);
 	mlx5_mkey_cache_debugfs_cleanup(dev);
+	mlx5r_destroy_cache_entries(dev);
+	destroy_workqueue(cache->wq);
 	mlx5_ib_warn(dev, "failed to create mkey cache entry\n");
 	return ret;
 }
@@ -1003,17 +1024,7 @@ void mlx5_mkey_cache_cleanup(struct mlx5_ib_dev *dev)
 	mlx5_cmd_cleanup_async_ctx(&dev->async_ctx);
 
 	/* At this point all entries are disabled and have no concurrent work. */
-	mutex_lock(&dev->cache.rb_lock);
-	node = rb_first(root);
-	while (node) {
-		ent = rb_entry(node, struct mlx5_cache_ent, node);
-		node = rb_next(node);
-		clean_keys(dev, ent);
-		rb_erase(&ent->node, root);
-		mlx5r_mkeys_uninit(ent);
-		kfree(ent);
-	}
-	mutex_unlock(&dev->cache.rb_lock);
+	mlx5r_destroy_cache_entries(dev);
 
 	destroy_workqueue(dev->cache.wq);
 	del_timer_sync(&dev->delay_timer);
@@ -1115,7 +1126,7 @@ static struct mlx5_ib_mr *alloc_cacheable_mr(struct ib_pd *pd,
 	struct mlx5r_cache_rb_key rb_key = {};
 	struct mlx5_cache_ent *ent;
 	struct mlx5_ib_mr *mr;
-	unsigned int page_size;
+	unsigned long page_size;
 
 	if (umem->is_dmabuf)
 		page_size = mlx5_umem_dmabuf_default_pgsz(umem, iova);
@@ -1219,7 +1230,7 @@ err_1:
  */
 static struct mlx5_ib_mr *reg_create(struct ib_pd *pd, struct ib_umem *umem,
 				     u64 iova, int access_flags,
-				     unsigned int page_size, bool populate,
+				     unsigned long page_size, bool populate,
 				     int access_mode)
 {
 	struct mlx5_ib_dev *dev = to_mdev(pd->device);
@@ -1425,7 +1436,7 @@ static struct ib_mr *create_real_mr(struct ib_pd *pd, struct ib_umem *umem,
 		mr = alloc_cacheable_mr(pd, umem, iova, access_flags,
 					MLX5_MKC_ACCESS_MODE_MTT);
 	} else {
-		unsigned int page_size =
+		unsigned long page_size =
 			mlx5_umem_mkc_find_best_pgsz(dev, umem, iova);
 
 		mutex_lock(&dev->slow_path_mutex);
@@ -1550,7 +1561,7 @@ static void mlx5_ib_dmabuf_invalidate_cb(struct dma_buf_attachment *attach)
 
 	dma_resv_assert_held(umem_dmabuf->attach->dmabuf->resv);
 
-	if (!umem_dmabuf->sgt)
+	if (!umem_dmabuf->sgt || !mr)
 		return;
 
 	mlx5r_umr_update_mr_pas(mr, MLX5_IB_UPD_XLT_ZAP);
@@ -1935,7 +1946,8 @@ err:
 static void
 mlx5_free_priv_descs(struct mlx5_ib_mr *mr)
 {
-	if (!mr->umem && !mr->data_direct && mr->descs) {
+	if (!mr->umem && !mr->data_direct &&
+	    mr->ibmr.type != IB_MR_TYPE_DM && mr->descs) {
 		struct ib_device *device = mr->ibmr.device;
 		int size = mr->max_descs * mr->desc_size;
 		struct mlx5_ib_dev *dev = to_mdev(device);
@@ -1956,7 +1968,6 @@ static int cache_ent_find_and_store(struct mlx5_ib_dev *dev,
 
 	if (mr->mmkey.cache_ent) {
 		spin_lock_irq(&mr->mmkey.cache_ent->mkeys_queue.lock);
-		mr->mmkey.cache_ent->in_use--;
 		goto end;
 	}
 
@@ -2017,15 +2028,55 @@ void mlx5_ib_revoke_data_direct_mrs(struct mlx5_ib_dev *dev)
 	}
 }
 
-static int mlx5_revoke_mr(struct mlx5_ib_mr *mr)
+static int mlx5_umr_revoke_mr_with_lock(struct mlx5_ib_mr *mr)
 {
+	bool is_odp_dma_buf = is_dmabuf_mr(mr) &&
+			      !to_ib_umem_dmabuf(mr->umem)->pinned;
+	bool is_odp = is_odp_mr(mr);
+	int ret;
+
+	if (is_odp)
+		mutex_lock(&to_ib_umem_odp(mr->umem)->umem_mutex);
+
+	if (is_odp_dma_buf)
+		dma_resv_lock(to_ib_umem_dmabuf(mr->umem)->attach->dmabuf->resv,
+			      NULL);
+
+	ret = mlx5r_umr_revoke_mr(mr);
+
+	if (is_odp) {
+		if (!ret)
+			to_ib_umem_odp(mr->umem)->private = NULL;
+		mutex_unlock(&to_ib_umem_odp(mr->umem)->umem_mutex);
+	}
+
+	if (is_odp_dma_buf) {
+		if (!ret)
+			to_ib_umem_dmabuf(mr->umem)->private = NULL;
+		dma_resv_unlock(
+			to_ib_umem_dmabuf(mr->umem)->attach->dmabuf->resv);
+	}
+
+	return ret;
+}
+
+static int mlx5r_handle_mkey_cleanup(struct mlx5_ib_mr *mr)
+{
+	bool is_odp_dma_buf = is_dmabuf_mr(mr) &&
+			      !to_ib_umem_dmabuf(mr->umem)->pinned;
 	struct mlx5_ib_dev *dev = to_mdev(mr->ibmr.device);
 	struct mlx5_cache_ent *ent = mr->mmkey.cache_ent;
+	bool is_odp = is_odp_mr(mr);
+	bool from_cache = !!ent;
+	int ret;
 
-	if (mr->mmkey.cacheable && !mlx5r_umr_revoke_mr(mr) && !cache_ent_find_and_store(dev, mr)) {
+	if (mr->mmkey.cacheable && !mlx5_umr_revoke_mr_with_lock(mr) &&
+	    !cache_ent_find_and_store(dev, mr)) {
 		ent = mr->mmkey.cache_ent;
 		/* upon storing to a clean temp entry - schedule its cleanup */
 		spin_lock_irq(&ent->mkeys_queue.lock);
+		if (from_cache)
+			ent->in_use--;
 		if (ent->is_tmp && !ent->tmp_cleanup_scheduled) {
 			mod_delayed_work(ent->dev->cache.wq, &ent->dwork,
 					 msecs_to_jiffies(30 * 1000));
@@ -2041,7 +2092,27 @@ static int mlx5_revoke_mr(struct mlx5_ib_mr *mr)
 		mr->mmkey.cache_ent = NULL;
 		spin_unlock_irq(&ent->mkeys_queue.lock);
 	}
-	return destroy_mkey(dev, mr);
+
+	if (is_odp)
+		mutex_lock(&to_ib_umem_odp(mr->umem)->umem_mutex);
+
+	if (is_odp_dma_buf)
+		dma_resv_lock(to_ib_umem_dmabuf(mr->umem)->attach->dmabuf->resv,
+			      NULL);
+	ret = destroy_mkey(dev, mr);
+	if (is_odp) {
+		if (!ret)
+			to_ib_umem_odp(mr->umem)->private = NULL;
+		mutex_unlock(&to_ib_umem_odp(mr->umem)->umem_mutex);
+	}
+
+	if (is_odp_dma_buf) {
+		if (!ret)
+			to_ib_umem_dmabuf(mr->umem)->private = NULL;
+		dma_resv_unlock(
+			to_ib_umem_dmabuf(mr->umem)->attach->dmabuf->resv);
+	}
+	return ret;
 }
 
 static int __mlx5_ib_dereg_mr(struct ib_mr *ibmr)
@@ -2089,7 +2160,7 @@ static int __mlx5_ib_dereg_mr(struct ib_mr *ibmr)
 	}
 
 	/* Stop DMA */
-	rc = mlx5_revoke_mr(mr);
+	rc = mlx5r_handle_mkey_cleanup(mr);
 	if (rc)
 		return rc;
 
diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c
index 4b37446758fd..98a76c9db7ab 100644
--- a/drivers/infiniband/hw/mlx5/odp.c
+++ b/drivers/infiniband/hw/mlx5/odp.c
@@ -228,13 +228,28 @@ static void destroy_unused_implicit_child_mr(struct mlx5_ib_mr *mr)
 	unsigned long idx = ib_umem_start(odp) >> MLX5_IMR_MTT_SHIFT;
 	struct mlx5_ib_mr *imr = mr->parent;
 
+	/*
+	 * If userspace is racing freeing the parent implicit ODP MR then we can
+	 * loose the race with parent destruction. In this case
+	 * mlx5_ib_free_odp_mr() will free everything in the implicit_children
+	 * xarray so NOP is fine. This child MR cannot be destroyed here because
+	 * we are under its umem_mutex.
+	 */
 	if (!refcount_inc_not_zero(&imr->mmkey.usecount))
 		return;
 
-	xa_erase(&imr->implicit_children, idx);
+	xa_lock(&imr->implicit_children);
+	if (__xa_cmpxchg(&imr->implicit_children, idx, mr, NULL, GFP_KERNEL) !=
+	    mr) {
+		xa_unlock(&imr->implicit_children);
+		mlx5r_deref_odp_mkey(&imr->mmkey);
+		return;
+	}
+
 	if (MLX5_CAP_ODP(mr_to_mdev(mr)->mdev, mem_page_fault))
 		xa_erase(&mr_to_mdev(mr)->odp_mkeys,
 			 mlx5_base_mkey(mr->mmkey.key));
+	xa_unlock(&imr->implicit_children);
 
 	/* Freeing a MR is a sleeping operation, so bounce to a work queue */
 	INIT_WORK(&mr->odp_destroy.work, free_implicit_child_mr_work);
@@ -268,6 +283,8 @@ static bool mlx5_ib_invalidate_range(struct mmu_interval_notifier *mni,
 	if (!umem_odp->npages)
 		goto out;
 	mr = umem_odp->private;
+	if (!mr)
+		goto out;
 
 	start = max_t(u64, ib_umem_start(umem_odp), range->start);
 	end = min_t(u64, ib_umem_end(umem_odp), range->end);
@@ -292,9 +309,6 @@ static bool mlx5_ib_invalidate_range(struct mmu_interval_notifier *mni,
 				blk_start_idx = idx;
 				in_block = 1;
 			}
-
-			/* Count page invalidations */
-			invalidations += idx - blk_start_idx + 1;
 		} else {
 			u64 umr_offset = idx & umr_block_mask;
 
@@ -304,14 +318,19 @@ static bool mlx5_ib_invalidate_range(struct mmu_interval_notifier *mni,
 						     MLX5_IB_UPD_XLT_ZAP |
 						     MLX5_IB_UPD_XLT_ATOMIC);
 				in_block = 0;
+				/* Count page invalidations */
+				invalidations += idx - blk_start_idx + 1;
 			}
 		}
 	}
-	if (in_block)
+	if (in_block) {
 		mlx5r_umr_update_xlt(mr, blk_start_idx,
 				     idx - blk_start_idx + 1, 0,
 				     MLX5_IB_UPD_XLT_ZAP |
 				     MLX5_IB_UPD_XLT_ATOMIC);
+		/* Count page invalidations */
+		invalidations += idx - blk_start_idx + 1;
+	}
 
 	mlx5_update_odp_stats(mr, invalidations, invalidations);
 
@@ -500,18 +519,18 @@ static struct mlx5_ib_mr *implicit_get_child_mr(struct mlx5_ib_mr *imr,
 		refcount_inc(&ret->mmkey.usecount);
 		goto out_lock;
 	}
-	xa_unlock(&imr->implicit_children);
 
 	if (MLX5_CAP_ODP(dev->mdev, mem_page_fault)) {
 		ret = xa_store(&dev->odp_mkeys, mlx5_base_mkey(mr->mmkey.key),
 			       &mr->mmkey, GFP_KERNEL);
 		if (xa_is_err(ret)) {
 			ret = ERR_PTR(xa_err(ret));
-			xa_erase(&imr->implicit_children, idx);
-			goto out_mr;
+			__xa_erase(&imr->implicit_children, idx);
+			goto out_lock;
 		}
 		mr->mmkey.type = MLX5_MKEY_IMPLICIT_CHILD;
 	}
+	xa_unlock(&imr->implicit_children);
 	mlx5_ib_dbg(mr_to_mdev(imr), "key %x mr %p\n", mr->mmkey.key, mr);
 	return mr;
 
@@ -944,8 +963,7 @@ out:
 /*
  * Handle a single data segment in a page-fault WQE or RDMA region.
  *
- * Returns number of OS pages retrieved on success. The caller may continue to
- * the next data segment.
+ * Returns zero on success. The caller may continue to the next data segment.
  * Can return the following error codes:
  * -EAGAIN to designate a temporary error. The caller will abort handling the
  *  page fault and resolve it.
@@ -958,7 +976,7 @@ static int pagefault_single_data_segment(struct mlx5_ib_dev *dev,
 					 u32 *bytes_committed,
 					 u32 *bytes_mapped)
 {
-	int npages = 0, ret, i, outlen, cur_outlen = 0, depth = 0;
+	int ret, i, outlen, cur_outlen = 0, depth = 0, pages_in_range;
 	struct pf_frame *head = NULL, *frame;
 	struct mlx5_ib_mkey *mmkey;
 	struct mlx5_ib_mr *mr;
@@ -993,13 +1011,20 @@ next_mr:
 	case MLX5_MKEY_MR:
 		mr = container_of(mmkey, struct mlx5_ib_mr, mmkey);
 
+		pages_in_range = (ALIGN(io_virt + bcnt, PAGE_SIZE) -
+				  (io_virt & PAGE_MASK)) >>
+				 PAGE_SHIFT;
 		ret = pagefault_mr(mr, io_virt, bcnt, bytes_mapped, 0, false);
 		if (ret < 0)
 			goto end;
 
 		mlx5_update_odp_stats(mr, faults, ret);
 
-		npages += ret;
+		if (ret < pages_in_range) {
+			ret = -EFAULT;
+			goto end;
+		}
+
 		ret = 0;
 		break;
 
@@ -1090,7 +1115,7 @@ end:
 	kfree(out);
 
 	*bytes_committed = 0;
-	return ret ? ret : npages;
+	return ret;
 }
 
 /*
@@ -1109,8 +1134,7 @@ end:
  *                   the committed bytes).
  * @receive_queue: receive WQE end of sg list
  *
- * Returns the number of pages loaded if positive, zero for an empty WQE, or a
- * negative error code.
+ * Returns zero for success or a negative error code.
  */
 static int pagefault_data_segments(struct mlx5_ib_dev *dev,
 				   struct mlx5_pagefault *pfault,
@@ -1118,7 +1142,7 @@ static int pagefault_data_segments(struct mlx5_ib_dev *dev,
 				   void *wqe_end, u32 *bytes_mapped,
 				   u32 *total_wqe_bytes, bool receive_queue)
 {
-	int ret = 0, npages = 0;
+	int ret = 0;
 	u64 io_virt;
 	__be32 key;
 	u32 byte_count;
@@ -1175,10 +1199,9 @@ static int pagefault_data_segments(struct mlx5_ib_dev *dev,
 						    bytes_mapped);
 		if (ret < 0)
 			break;
-		npages += ret;
 	}
 
-	return ret < 0 ? ret : npages;
+	return ret;
 }
 
 /*
@@ -1414,12 +1437,6 @@ resolve_page_fault:
 	free_page((unsigned long)wqe_start);
 }
 
-static int pages_in_range(u64 address, u32 length)
-{
-	return (ALIGN(address + length, PAGE_SIZE) -
-		(address & PAGE_MASK)) >> PAGE_SHIFT;
-}
-
 static void mlx5_ib_mr_rdma_pfault_handler(struct mlx5_ib_dev *dev,
 					   struct mlx5_pagefault *pfault)
 {
@@ -1458,7 +1475,7 @@ static void mlx5_ib_mr_rdma_pfault_handler(struct mlx5_ib_dev *dev,
 	if (ret == -EAGAIN) {
 		/* We're racing with an invalidation, don't prefetch */
 		prefetch_activated = 0;
-	} else if (ret < 0 || pages_in_range(address, length) > ret) {
+	} else if (ret < 0) {
 		mlx5_ib_page_fault_resume(dev, pfault, 1);
 		if (ret != -ENOENT)
 			mlx5_ib_dbg(dev, "PAGE FAULT error %d. QP 0x%llx, type: 0x%x\n",
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 10ce3b44f645..ded139b4e87a 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -3420,11 +3420,11 @@ static int ib_to_mlx5_rate_map(u8 rate)
 	return 0;
 }
 
-static int ib_rate_to_mlx5(struct mlx5_ib_dev *dev, u8 rate)
+int mlx5r_ib_rate(struct mlx5_ib_dev *dev, u8 rate)
 {
 	u32 stat_rate_support;
 
-	if (rate == IB_RATE_PORT_CURRENT)
+	if (rate == IB_RATE_PORT_CURRENT || rate == IB_RATE_800_GBPS)
 		return 0;
 
 	if (rate < IB_RATE_2_5_GBPS || rate > IB_RATE_800_GBPS)
@@ -3569,7 +3569,7 @@ static int mlx5_set_path(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 		       sizeof(grh->dgid.raw));
 	}
 
-	err = ib_rate_to_mlx5(dev, rdma_ah_get_static_rate(ah));
+	err = mlx5r_ib_rate(dev, rdma_ah_get_static_rate(ah));
 	if (err < 0)
 		return err;
 	MLX5_SET(ads, path, stat_rate, err);
@@ -4547,6 +4547,8 @@ static int mlx5_ib_modify_dct(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 
 		set_id = mlx5_ib_get_counters_id(dev, attr->port_num - 1);
 		MLX5_SET(dctc, dctc, counter_set_id, set_id);
+
+		qp->port = attr->port_num;
 	} else if (cur_state == IB_QPS_INIT && new_state == IB_QPS_RTR) {
 		struct mlx5_ib_modify_qp_resp resp = {};
 		u32 out[MLX5_ST_SZ_DW(create_dct_out)] = {};
@@ -5033,7 +5035,7 @@ static int mlx5_ib_dct_query_qp(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *mqp,
 	}
 
 	if (qp_attr_mask & IB_QP_PORT)
-		qp_attr->port_num = MLX5_GET(dctc, dctc, port);
+		qp_attr->port_num = mqp->port;
 	if (qp_attr_mask & IB_QP_MIN_RNR_TIMER)
 		qp_attr->min_rnr_timer = MLX5_GET(dctc, dctc, min_rnr_nak);
 	if (qp_attr_mask & IB_QP_AV) {
diff --git a/drivers/infiniband/hw/mlx5/qp.h b/drivers/infiniband/hw/mlx5/qp.h
index b6ee7c3ee1ca..2530e7730635 100644
--- a/drivers/infiniband/hw/mlx5/qp.h
+++ b/drivers/infiniband/hw/mlx5/qp.h
@@ -56,4 +56,5 @@ int mlx5_core_xrcd_dealloc(struct mlx5_ib_dev *dev, u32 xrcdn);
 int mlx5_ib_qp_set_counter(struct ib_qp *qp, struct rdma_counter *counter);
 int mlx5_ib_qp_event_init(void);
 void mlx5_ib_qp_event_cleanup(void);
+int mlx5r_ib_rate(struct mlx5_ib_dev *dev, u8 rate);
 #endif /* _MLX5_IB_QP_H */
diff --git a/drivers/infiniband/hw/mlx5/qpc.c b/drivers/infiniband/hw/mlx5/qpc.c
index d3dcc272200a..146d03ae40bd 100644
--- a/drivers/infiniband/hw/mlx5/qpc.c
+++ b/drivers/infiniband/hw/mlx5/qpc.c
@@ -21,8 +21,10 @@ mlx5_get_rsc(struct mlx5_qp_table *table, u32 rsn)
 	spin_lock_irqsave(&table->lock, flags);
 
 	common = radix_tree_lookup(&table->tree, rsn);
-	if (common)
+	if (common && !common->invalid)
 		refcount_inc(&common->refcount);
+	else
+		common = NULL;
 
 	spin_unlock_irqrestore(&table->lock, flags);
 
@@ -178,6 +180,18 @@ static int create_resource_common(struct mlx5_ib_dev *dev,
 	return 0;
 }
 
+static void modify_resource_common_state(struct mlx5_ib_dev *dev,
+					 struct mlx5_core_qp *qp,
+					 bool invalid)
+{
+	struct mlx5_qp_table *table = &dev->qp_table;
+	unsigned long flags;
+
+	spin_lock_irqsave(&table->lock, flags);
+	qp->common.invalid = invalid;
+	spin_unlock_irqrestore(&table->lock, flags);
+}
+
 static void destroy_resource_common(struct mlx5_ib_dev *dev,
 				    struct mlx5_core_qp *qp)
 {
@@ -609,8 +623,20 @@ err_destroy_rq:
 int mlx5_core_destroy_rq_tracked(struct mlx5_ib_dev *dev,
 				 struct mlx5_core_qp *rq)
 {
+	int ret;
+
+	/* The rq destruction can be called again in case it fails, hence we
+	 * mark the common resource as invalid and only once FW destruction
+	 * is completed successfully we actually destroy the resources.
+	 */
+	modify_resource_common_state(dev, rq, true);
+	ret = destroy_rq_tracked(dev, rq->qpn, rq->uid);
+	if (ret) {
+		modify_resource_common_state(dev, rq, false);
+		return ret;
+	}
 	destroy_resource_common(dev, rq);
-	return destroy_rq_tracked(dev, rq->qpn, rq->uid);
+	return 0;
 }
 
 static void destroy_sq_tracked(struct mlx5_ib_dev *dev, u32 sqn, u16 uid)
diff --git a/drivers/infiniband/hw/mlx5/umr.c b/drivers/infiniband/hw/mlx5/umr.c
index 887fd6fa3ba9..80c665d15218 100644
--- a/drivers/infiniband/hw/mlx5/umr.c
+++ b/drivers/infiniband/hw/mlx5/umr.c
@@ -32,13 +32,15 @@ static __be64 get_umr_disable_mr_mask(void)
 	return cpu_to_be64(result);
 }
 
-static __be64 get_umr_update_translation_mask(void)
+static __be64 get_umr_update_translation_mask(struct mlx5_ib_dev *dev)
 {
 	u64 result;
 
 	result = MLX5_MKEY_MASK_LEN |
 		 MLX5_MKEY_MASK_PAGE_SIZE |
 		 MLX5_MKEY_MASK_START_ADDR;
+	if (MLX5_CAP_GEN_2(dev->mdev, umr_log_entity_size_5))
+		result |= MLX5_MKEY_MASK_PAGE_SIZE_5;
 
 	return cpu_to_be64(result);
 }
@@ -231,30 +233,6 @@ void mlx5r_umr_cleanup(struct mlx5_ib_dev *dev)
 	ib_dealloc_pd(dev->umrc.pd);
 }
 
-static int mlx5r_umr_recover(struct mlx5_ib_dev *dev)
-{
-	struct umr_common *umrc = &dev->umrc;
-	struct ib_qp_attr attr;
-	int err;
-
-	attr.qp_state = IB_QPS_RESET;
-	err = ib_modify_qp(umrc->qp, &attr, IB_QP_STATE);
-	if (err) {
-		mlx5_ib_dbg(dev, "Couldn't modify UMR QP\n");
-		goto err;
-	}
-
-	err = mlx5r_umr_qp_rst2rts(dev, umrc->qp);
-	if (err)
-		goto err;
-
-	umrc->state = MLX5_UMR_STATE_ACTIVE;
-	return 0;
-
-err:
-	umrc->state = MLX5_UMR_STATE_ERR;
-	return err;
-}
 
 static int mlx5r_umr_post_send(struct ib_qp *ibqp, u32 mkey, struct ib_cqe *cqe,
 			       struct mlx5r_umr_wqe *wqe, bool with_data)
@@ -302,6 +280,61 @@ out:
 	return err;
 }
 
+static int mlx5r_umr_recover(struct mlx5_ib_dev *dev, u32 mkey,
+			     struct mlx5r_umr_context *umr_context,
+			     struct mlx5r_umr_wqe *wqe, bool with_data)
+{
+	struct umr_common *umrc = &dev->umrc;
+	struct ib_qp_attr attr;
+	int err;
+
+	mutex_lock(&umrc->lock);
+	/* Preventing any further WRs to be sent now */
+	if (umrc->state != MLX5_UMR_STATE_RECOVER) {
+		mlx5_ib_warn(dev, "UMR recovery encountered an unexpected state=%d\n",
+			     umrc->state);
+		umrc->state = MLX5_UMR_STATE_RECOVER;
+	}
+	mutex_unlock(&umrc->lock);
+
+	/* Sending a final/barrier WR (the failed one) and wait for its completion.
+	 * This will ensure that all the previous WRs got a completion before
+	 * we set the QP state to RESET.
+	 */
+	err = mlx5r_umr_post_send(umrc->qp, mkey, &umr_context->cqe, wqe,
+				  with_data);
+	if (err) {
+		mlx5_ib_warn(dev, "UMR recovery post send failed, err %d\n", err);
+		goto err;
+	}
+
+	/* Since the QP is in an error state, it will only receive
+	 * IB_WC_WR_FLUSH_ERR. However, as it serves only as a barrier
+	 * we don't care about its status.
+	 */
+	wait_for_completion(&umr_context->done);
+
+	attr.qp_state = IB_QPS_RESET;
+	err = ib_modify_qp(umrc->qp, &attr, IB_QP_STATE);
+	if (err) {
+		mlx5_ib_warn(dev, "Couldn't modify UMR QP to RESET, err=%d\n", err);
+		goto err;
+	}
+
+	err = mlx5r_umr_qp_rst2rts(dev, umrc->qp);
+	if (err) {
+		mlx5_ib_warn(dev, "Couldn't modify UMR QP to RTS, err=%d\n", err);
+		goto err;
+	}
+
+	umrc->state = MLX5_UMR_STATE_ACTIVE;
+	return 0;
+
+err:
+	umrc->state = MLX5_UMR_STATE_ERR;
+	return err;
+}
+
 static void mlx5r_umr_done(struct ib_cq *cq, struct ib_wc *wc)
 {
 	struct mlx5_ib_umr_context *context =
@@ -366,9 +399,7 @@ static int mlx5r_umr_post_send_wait(struct mlx5_ib_dev *dev, u32 mkey,
 		mlx5_ib_warn(dev,
 			"reg umr failed (%u). Trying to recover and resubmit the flushed WQEs, mkey = %u\n",
 			umr_context.status, mkey);
-		mutex_lock(&umrc->lock);
-		err = mlx5r_umr_recover(dev);
-		mutex_unlock(&umrc->lock);
+		err = mlx5r_umr_recover(dev, mkey, &umr_context, wqe, with_data);
 		if (err)
 			mlx5_ib_warn(dev, "couldn't recover UMR, err %d\n",
 				     err);
@@ -625,7 +656,7 @@ static void mlx5r_umr_final_update_xlt(struct mlx5_ib_dev *dev,
 		flags & MLX5_IB_UPD_XLT_ENABLE || flags & MLX5_IB_UPD_XLT_ADDR;
 
 	if (update_translation) {
-		wqe->ctrl_seg.mkey_mask |= get_umr_update_translation_mask();
+		wqe->ctrl_seg.mkey_mask |= get_umr_update_translation_mask(dev);
 		if (!mr->ibmr.length)
 			MLX5_SET(mkc, &wqe->mkey_seg, length64, 1);
 	}
diff --git a/drivers/infiniband/hw/qib/qib_fs.c b/drivers/infiniband/hw/qib/qib_fs.c
index b27791029fa9..b9f4a2937c3a 100644
--- a/drivers/infiniband/hw/qib/qib_fs.c
+++ b/drivers/infiniband/hw/qib/qib_fs.c
@@ -55,6 +55,7 @@ static int qibfs_mknod(struct inode *dir, struct dentry *dentry,
 	struct inode *inode = new_inode(dir->i_sb);
 
 	if (!inode) {
+		dput(dentry);
 		error = -EPERM;
 		goto bail;
 	}
diff --git a/drivers/infiniband/hw/usnic/usnic_ib_main.c b/drivers/infiniband/hw/usnic/usnic_ib_main.c
index 13b654ddd3cc..bcf7d8607d56 100644
--- a/drivers/infiniband/hw/usnic/usnic_ib_main.c
+++ b/drivers/infiniband/hw/usnic/usnic_ib_main.c
@@ -380,7 +380,7 @@ static void *usnic_ib_device_add(struct pci_dev *dev)
 	if (!us_ibdev) {
 		usnic_err("Device %s context alloc failed\n",
 				netdev_name(pci_get_drvdata(dev)));
-		return ERR_PTR(-EFAULT);
+		return NULL;
 	}
 
 	us_ibdev->ufdev = usnic_fwd_dev_alloc(dev);
@@ -500,8 +500,8 @@ static struct usnic_ib_dev *usnic_ib_discover_pf(struct usnic_vnic *vnic)
 	}
 
 	us_ibdev = usnic_ib_device_add(parent_pci);
-	if (IS_ERR_OR_NULL(us_ibdev)) {
-		us_ibdev = us_ibdev ? us_ibdev : ERR_PTR(-EFAULT);
+	if (!us_ibdev) {
+		us_ibdev = ERR_PTR(-EFAULT);
 		goto out;
 	}
 
@@ -569,10 +569,10 @@ static int usnic_ib_pci_probe(struct pci_dev *pdev,
 	}
 
 	pf = usnic_ib_discover_pf(vf->vnic);
-	if (IS_ERR_OR_NULL(pf)) {
-		usnic_err("Failed to discover pf of vnic %s with err%ld\n",
-				pci_name(pdev), PTR_ERR(pf));
-		err = pf ? PTR_ERR(pf) : -EFAULT;
+	if (IS_ERR(pf)) {
+		err = PTR_ERR(pf);
+		usnic_err("Failed to discover pf of vnic %s with err%d\n",
+				pci_name(pdev), err);
 		goto out_clean_vnic;
 	}
 
diff --git a/drivers/infiniband/sw/rxe/rxe.c b/drivers/infiniband/sw/rxe/rxe.c
index 1ba4a0c8726a..e27478fe9456 100644
--- a/drivers/infiniband/sw/rxe/rxe.c
+++ b/drivers/infiniband/sw/rxe/rxe.c
@@ -38,10 +38,8 @@ void rxe_dealloc(struct ib_device *ib_dev)
 }
 
 /* initialize rxe device parameters */
-static void rxe_init_device_param(struct rxe_dev *rxe)
+static void rxe_init_device_param(struct rxe_dev *rxe, struct net_device *ndev)
 {
-	struct net_device *ndev;
-
 	rxe->max_inline_data			= RXE_MAX_INLINE_DATA;
 
 	rxe->attr.vendor_id			= RXE_VENDOR_ID;
@@ -74,15 +72,9 @@ static void rxe_init_device_param(struct rxe_dev *rxe)
 	rxe->attr.max_pkeys			= RXE_MAX_PKEYS;
 	rxe->attr.local_ca_ack_delay		= RXE_LOCAL_CA_ACK_DELAY;
 
-	ndev = rxe_ib_device_get_netdev(&rxe->ib_dev);
-	if (!ndev)
-		return;
-
 	addrconf_addr_eui48((unsigned char *)&rxe->attr.sys_image_guid,
 			ndev->dev_addr);
 
-	dev_put(ndev);
-
 	rxe->max_ucontext			= RXE_MAX_UCONTEXT;
 }
 
@@ -115,18 +107,13 @@ static void rxe_init_port_param(struct rxe_port *port)
 /* initialize port state, note IB convention that HCA ports are always
  * numbered from 1
  */
-static void rxe_init_ports(struct rxe_dev *rxe)
+static void rxe_init_ports(struct rxe_dev *rxe, struct net_device *ndev)
 {
 	struct rxe_port *port = &rxe->port;
-	struct net_device *ndev;
 
 	rxe_init_port_param(port);
-	ndev = rxe_ib_device_get_netdev(&rxe->ib_dev);
-	if (!ndev)
-		return;
 	addrconf_addr_eui48((unsigned char *)&port->port_guid,
 			    ndev->dev_addr);
-	dev_put(ndev);
 	spin_lock_init(&port->port_lock);
 }
 
@@ -144,12 +131,12 @@ static void rxe_init_pools(struct rxe_dev *rxe)
 }
 
 /* initialize rxe device state */
-static void rxe_init(struct rxe_dev *rxe)
+static void rxe_init(struct rxe_dev *rxe, struct net_device *ndev)
 {
 	/* init default device parameters */
-	rxe_init_device_param(rxe);
+	rxe_init_device_param(rxe, ndev);
 
-	rxe_init_ports(rxe);
+	rxe_init_ports(rxe, ndev);
 	rxe_init_pools(rxe);
 
 	/* init pending mmap list */
@@ -184,7 +171,7 @@ void rxe_set_mtu(struct rxe_dev *rxe, unsigned int ndev_mtu)
 int rxe_add(struct rxe_dev *rxe, unsigned int mtu, const char *ibdev_name,
 			struct net_device *ndev)
 {
-	rxe_init(rxe);
+	rxe_init(rxe, ndev);
 	rxe_set_mtu(rxe, mtu);
 
 	return rxe_register_device(rxe, ibdev_name, ndev);
diff --git a/drivers/infiniband/sw/rxe/rxe_cq.c b/drivers/infiniband/sw/rxe/rxe_cq.c
index fec87c9030ab..fffd144d509e 100644
--- a/drivers/infiniband/sw/rxe/rxe_cq.c
+++ b/drivers/infiniband/sw/rxe/rxe_cq.c
@@ -56,11 +56,8 @@ int rxe_cq_from_init(struct rxe_dev *rxe, struct rxe_cq *cq, int cqe,
 
 	err = do_mmap_info(rxe, uresp ? &uresp->mi : NULL, udata,
 			   cq->queue->buf, cq->queue->buf_size, &cq->queue->ip);
-	if (err) {
-		vfree(cq->queue->buf);
-		kfree(cq->queue);
+	if (err)
 		return err;
-	}
 
 	cq->is_user = uresp;
 
diff --git a/drivers/infiniband/sw/rxe/rxe_param.h b/drivers/infiniband/sw/rxe/rxe_param.h
index d2f57ead78ad..003f681e5dc0 100644
--- a/drivers/infiniband/sw/rxe/rxe_param.h
+++ b/drivers/infiniband/sw/rxe/rxe_param.h
@@ -129,7 +129,7 @@ enum rxe_device_param {
 enum rxe_port_param {
 	RXE_PORT_GID_TBL_LEN		= 1024,
 	RXE_PORT_PORT_CAP_FLAGS		= IB_PORT_CM_SUP,
-	RXE_PORT_MAX_MSG_SZ		= 0x800000,
+	RXE_PORT_MAX_MSG_SZ		= (1UL << 31),
 	RXE_PORT_BAD_PKEY_CNTR		= 0,
 	RXE_PORT_QKEY_VIOL_CNTR		= 0,
 	RXE_PORT_LID			= 0,
diff --git a/drivers/infiniband/sw/rxe/rxe_pool.c b/drivers/infiniband/sw/rxe/rxe_pool.c
index 67567d62195e..d9cb682fd71f 100644
--- a/drivers/infiniband/sw/rxe/rxe_pool.c
+++ b/drivers/infiniband/sw/rxe/rxe_pool.c
@@ -178,7 +178,6 @@ int __rxe_cleanup(struct rxe_pool_elem *elem, bool sleepable)
 {
 	struct rxe_pool *pool = elem->pool;
 	struct xarray *xa = &pool->xa;
-	static int timeout = RXE_POOL_TIMEOUT;
 	int ret, err = 0;
 	void *xa_ret;
 
@@ -202,19 +201,19 @@ int __rxe_cleanup(struct rxe_pool_elem *elem, bool sleepable)
 	 * return to rdma-core
 	 */
 	if (sleepable) {
-		if (!completion_done(&elem->complete) && timeout) {
+		if (!completion_done(&elem->complete)) {
 			ret = wait_for_completion_timeout(&elem->complete,
-					timeout);
+					msecs_to_jiffies(50000));
 
 			/* Shouldn't happen. There are still references to
 			 * the object but, rather than deadlock, free the
 			 * object or pass back to rdma-core.
 			 */
 			if (WARN_ON(!ret))
-				err = -EINVAL;
+				err = -ETIMEDOUT;
 		}
 	} else {
-		unsigned long until = jiffies + timeout;
+		unsigned long until = jiffies + RXE_POOL_TIMEOUT;
 
 		/* AH objects are unique in that the destroy_ah verb
 		 * can be called in atomic context. This delay
@@ -226,7 +225,7 @@ int __rxe_cleanup(struct rxe_pool_elem *elem, bool sleepable)
 			mdelay(1);
 
 		if (WARN_ON(!completion_done(&elem->complete)))
-			err = -EINVAL;
+			err = -ETIMEDOUT;
 	}
 
 	if (pool->cleanup)
diff --git a/drivers/infiniband/sw/rxe/rxe_qp.c b/drivers/infiniband/sw/rxe/rxe_qp.c
index 91d329e90308..8b805b16136e 100644
--- a/drivers/infiniband/sw/rxe/rxe_qp.c
+++ b/drivers/infiniband/sw/rxe/rxe_qp.c
@@ -811,7 +811,12 @@ static void rxe_qp_do_cleanup(struct work_struct *work)
 	spin_unlock_irqrestore(&qp->state_lock, flags);
 	qp->qp_timeout_jiffies = 0;
 
-	if (qp_type(qp) == IB_QPT_RC) {
+	/* In the function timer_setup, .function is initialized. If .function
+	 * is NULL, it indicates the function timer_setup is not called, the
+	 * timer is not initialized. Or else, the timer is initialized.
+	 */
+	if (qp_type(qp) == IB_QPT_RC && qp->retrans_timer.function &&
+		qp->rnr_nak_timer.function) {
 		del_timer_sync(&qp->retrans_timer);
 		del_timer_sync(&qp->rnr_nak_timer);
 	}
diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c
index 8a5fc20fd186..589ac0d8489d 100644
--- a/drivers/infiniband/sw/rxe/rxe_verbs.c
+++ b/drivers/infiniband/sw/rxe/rxe_verbs.c
@@ -696,7 +696,7 @@ static int validate_send_wr(struct rxe_qp *qp, const struct ib_send_wr *ibwr,
 		for (i = 0; i < ibwr->num_sge; i++)
 			length += ibwr->sg_list[i].length;
 
-		if (length > (1UL << 31)) {
+		if (length > RXE_PORT_MAX_MSG_SZ) {
 			rxe_err_qp(qp, "message length too long\n");
 			break;
 		}
@@ -980,8 +980,7 @@ static int post_one_recv(struct rxe_rq *rq, const struct ib_recv_wr *ibwr)
 	for (i = 0; i < num_sge; i++)
 		length += ibwr->sg_list[i].length;
 
-	/* IBA max message size is 2^31 */
-	if (length >= (1UL<<31)) {
+	if (length > RXE_PORT_MAX_MSG_SZ) {
 		err = -EINVAL;
 		rxe_dbg("message length too long\n");
 		goto err_out;
diff --git a/drivers/infiniband/sw/siw/siw_qp_tx.c b/drivers/infiniband/sw/siw/siw_qp_tx.c
index a034264c5669..43ff1afd3d01 100644
--- a/drivers/infiniband/sw/siw/siw_qp_tx.c
+++ b/drivers/infiniband/sw/siw/siw_qp_tx.c
@@ -334,18 +334,17 @@ static int siw_tcp_sendpages(struct socket *s, struct page **page, int offset,
 		if (!sendpage_ok(page[i]))
 			msg.msg_flags &= ~MSG_SPLICE_PAGES;
 		bvec_set_page(&bvec, page[i], bytes, offset);
-		iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, size);
+		iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, bytes);
 
 try_page_again:
 		lock_sock(sk);
-		rv = tcp_sendmsg_locked(sk, &msg, size);
+		rv = tcp_sendmsg_locked(sk, &msg, bytes);
 		release_sock(sk);
 
 		if (rv > 0) {
 			size -= rv;
 			sent += rv;
 			if (rv != bytes) {
-				offset += rv;
 				bytes -= rv;
 				goto try_page_again;
 			}
diff --git a/drivers/infiniband/ulp/rtrs/rtrs.c b/drivers/infiniband/ulp/rtrs/rtrs.c
index 4e17d546d4cc..bf38ac6f87c4 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs.c
+++ b/drivers/infiniband/ulp/rtrs/rtrs.c
@@ -584,6 +584,9 @@ static void dev_free(struct kref *ref)
 	list_del(&dev->entry);
 	mutex_unlock(&pool->mutex);
 
+	if (pool->ops && pool->ops->deinit)
+		pool->ops->deinit(dev);
+
 	ib_dealloc_pd(dev->ib_pd);
 	kfree(dev);
 }
diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c
index 2916e77f589b..7289ae0b83ac 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.c
+++ b/drivers/infiniband/ulp/srp/ib_srp.c
@@ -3978,7 +3978,6 @@ static struct srp_host *srp_add_port(struct srp_device *device, u32 port)
 	return host;
 
 put_host:
-	device_del(&host->dev);
 	put_device(&host->dev);
 	return NULL;
 }
diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c
index 22ea58bf76cb..f0cab6870404 100644
--- a/drivers/input/joystick/xpad.c
+++ b/drivers/input/joystick/xpad.c
@@ -77,12 +77,13 @@
  * xbox d-pads should map to buttons, as is required for DDR pads
  * but we map them to axes when possible to simplify things
  */
-#define MAP_DPAD_TO_BUTTONS		(1 << 0)
-#define MAP_TRIGGERS_TO_BUTTONS		(1 << 1)
-#define MAP_STICKS_TO_NULL		(1 << 2)
-#define MAP_SELECT_BUTTON		(1 << 3)
-#define MAP_PADDLES			(1 << 4)
-#define MAP_PROFILE_BUTTON		(1 << 5)
+#define MAP_DPAD_TO_BUTTONS		BIT(0)
+#define MAP_TRIGGERS_TO_BUTTONS		BIT(1)
+#define MAP_STICKS_TO_NULL		BIT(2)
+#define MAP_SHARE_BUTTON		BIT(3)
+#define MAP_PADDLES			BIT(4)
+#define MAP_PROFILE_BUTTON		BIT(5)
+#define MAP_SHARE_OFFSET		BIT(6)
 
 #define DANCEPAD_MAP_CONFIG	(MAP_DPAD_TO_BUTTONS |			\
 				MAP_TRIGGERS_TO_BUTTONS | MAP_STICKS_TO_NULL)
@@ -135,11 +136,12 @@ static const struct xpad_device {
 	{ 0x03f0, 0x048D, "HyperX Clutch", 0, XTYPE_XBOX360 },			/* wireless */
 	{ 0x03f0, 0x0495, "HyperX Clutch Gladiate", 0, XTYPE_XBOXONE },
 	{ 0x03f0, 0x07A0, "HyperX Clutch Gladiate RGB", 0, XTYPE_XBOXONE },
-	{ 0x03f0, 0x08B6, "HyperX Clutch Gladiate", 0, XTYPE_XBOXONE },		/* v2 */
+	{ 0x03f0, 0x08B6, "HyperX Clutch Gladiate", MAP_SHARE_BUTTON, XTYPE_XBOXONE },		/* v2 */
 	{ 0x03f0, 0x09B4, "HyperX Clutch Tanto", 0, XTYPE_XBOXONE },
 	{ 0x044f, 0x0f00, "Thrustmaster Wheel", 0, XTYPE_XBOX },
 	{ 0x044f, 0x0f03, "Thrustmaster Wheel", 0, XTYPE_XBOX },
 	{ 0x044f, 0x0f07, "Thrustmaster, Inc. Controller", 0, XTYPE_XBOX },
+	{ 0x044f, 0xd01e, "ThrustMaster, Inc. ESWAP X 2 ELDEN RING EDITION", 0, XTYPE_XBOXONE },
 	{ 0x044f, 0x0f10, "Thrustmaster Modena GT Wheel", 0, XTYPE_XBOX },
 	{ 0x044f, 0xb326, "Thrustmaster Gamepad GP XID", 0, XTYPE_XBOX360 },
 	{ 0x045e, 0x0202, "Microsoft X-Box pad v1 (US)", 0, XTYPE_XBOX },
@@ -150,6 +152,7 @@ static const struct xpad_device {
 	{ 0x045e, 0x028e, "Microsoft X-Box 360 pad", 0, XTYPE_XBOX360 },
 	{ 0x045e, 0x028f, "Microsoft X-Box 360 pad v2", 0, XTYPE_XBOX360 },
 	{ 0x045e, 0x0291, "Xbox 360 Wireless Receiver (XBOX)", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX360W },
+	{ 0x045e, 0x02a9, "Xbox 360 Wireless Receiver (Unofficial)", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX360W },
 	{ 0x045e, 0x02d1, "Microsoft X-Box One pad", 0, XTYPE_XBOXONE },
 	{ 0x045e, 0x02dd, "Microsoft X-Box One pad (Firmware 2015)", 0, XTYPE_XBOXONE },
 	{ 0x045e, 0x02e3, "Microsoft X-Box One Elite pad", MAP_PADDLES, XTYPE_XBOXONE },
@@ -157,7 +160,7 @@ static const struct xpad_device {
 	{ 0x045e, 0x0719, "Xbox 360 Wireless Receiver", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX360W },
 	{ 0x045e, 0x0b00, "Microsoft X-Box One Elite 2 pad", MAP_PADDLES, XTYPE_XBOXONE },
 	{ 0x045e, 0x0b0a, "Microsoft X-Box Adaptive Controller", MAP_PROFILE_BUTTON, XTYPE_XBOXONE },
-	{ 0x045e, 0x0b12, "Microsoft Xbox Series S|X Controller", MAP_SELECT_BUTTON, XTYPE_XBOXONE },
+	{ 0x045e, 0x0b12, "Microsoft Xbox Series S|X Controller", MAP_SHARE_BUTTON | MAP_SHARE_OFFSET, XTYPE_XBOXONE },
 	{ 0x046d, 0xc21d, "Logitech Gamepad F310", 0, XTYPE_XBOX360 },
 	{ 0x046d, 0xc21e, "Logitech Gamepad F510", 0, XTYPE_XBOX360 },
 	{ 0x046d, 0xc21f, "Logitech Gamepad F710", 0, XTYPE_XBOX360 },
@@ -166,6 +169,7 @@ static const struct xpad_device {
 	{ 0x046d, 0xca88, "Logitech Compact Controller for Xbox", 0, XTYPE_XBOX },
 	{ 0x046d, 0xca8a, "Logitech Precision Vibration Feedback Wheel", 0, XTYPE_XBOX },
 	{ 0x046d, 0xcaa3, "Logitech DriveFx Racing Wheel", 0, XTYPE_XBOX360 },
+	{ 0x0502, 0x1305, "Acer NGR200", 0, XTYPE_XBOX360 },
 	{ 0x056e, 0x2004, "Elecom JC-U3613M", 0, XTYPE_XBOX360 },
 	{ 0x05fd, 0x1007, "Mad Catz Controller (unverified)", 0, XTYPE_XBOX },
 	{ 0x05fd, 0x107a, "InterAct 'PowerPad Pro' X-Box pad (Germany)", 0, XTYPE_XBOX },
@@ -176,6 +180,7 @@ static const struct xpad_device {
 	{ 0x06a3, 0x0200, "Saitek Racing Wheel", 0, XTYPE_XBOX },
 	{ 0x06a3, 0x0201, "Saitek Adrenalin", 0, XTYPE_XBOX },
 	{ 0x06a3, 0xf51a, "Saitek P3600", 0, XTYPE_XBOX360 },
+	{ 0x0738, 0x4503, "Mad Catz Racing Wheel", 0, XTYPE_XBOXONE },
 	{ 0x0738, 0x4506, "Mad Catz 4506 Wireless Controller", 0, XTYPE_XBOX },
 	{ 0x0738, 0x4516, "Mad Catz Control Pad", 0, XTYPE_XBOX },
 	{ 0x0738, 0x4520, "Mad Catz Control Pad Pro", 0, XTYPE_XBOX },
@@ -202,13 +207,13 @@ static const struct xpad_device {
 	{ 0x0738, 0x9871, "Mad Catz Portable Drum", 0, XTYPE_XBOX360 },
 	{ 0x0738, 0xb726, "Mad Catz Xbox controller - MW2", 0, XTYPE_XBOX360 },
 	{ 0x0738, 0xb738, "Mad Catz MVC2TE Stick 2", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOX360 },
-	{ 0x0738, 0xbeef, "Mad Catz JOYTECH NEO SE Advanced GamePad", XTYPE_XBOX360 },
+	{ 0x0738, 0xbeef, "Mad Catz JOYTECH NEO SE Advanced GamePad", 0, XTYPE_XBOX360 },
 	{ 0x0738, 0xcb02, "Saitek Cyborg Rumble Pad - PC/Xbox 360", 0, XTYPE_XBOX360 },
 	{ 0x0738, 0xcb03, "Saitek P3200 Rumble Pad - PC/Xbox 360", 0, XTYPE_XBOX360 },
 	{ 0x0738, 0xcb29, "Saitek Aviator Stick AV8R02", 0, XTYPE_XBOX360 },
 	{ 0x0738, 0xf738, "Super SFIV FightStick TE S", 0, XTYPE_XBOX360 },
 	{ 0x07ff, 0xffff, "Mad Catz GamePad", 0, XTYPE_XBOX360 },
-	{ 0x0b05, 0x1a38, "ASUS ROG RAIKIRI", 0, XTYPE_XBOXONE },
+	{ 0x0b05, 0x1a38, "ASUS ROG RAIKIRI", MAP_SHARE_BUTTON, XTYPE_XBOXONE },
 	{ 0x0b05, 0x1abb, "ASUS ROG RAIKIRI PRO", 0, XTYPE_XBOXONE },
 	{ 0x0c12, 0x0005, "Intec wireless", 0, XTYPE_XBOX },
 	{ 0x0c12, 0x8801, "Nyko Xbox Controller", 0, XTYPE_XBOX },
@@ -237,6 +242,7 @@ static const struct xpad_device {
 	{ 0x0e6f, 0x0146, "Rock Candy Wired Controller for Xbox One", 0, XTYPE_XBOXONE },
 	{ 0x0e6f, 0x0147, "PDP Marvel Xbox One Controller", 0, XTYPE_XBOXONE },
 	{ 0x0e6f, 0x015c, "PDP Xbox One Arcade Stick", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOXONE },
+	{ 0x0e6f, 0x015d, "PDP Mirror's Edge Official Wired Controller for Xbox One", 0, XTYPE_XBOXONE },
 	{ 0x0e6f, 0x0161, "PDP Xbox One Controller", 0, XTYPE_XBOXONE },
 	{ 0x0e6f, 0x0162, "PDP Xbox One Controller", 0, XTYPE_XBOXONE },
 	{ 0x0e6f, 0x0163, "PDP Xbox One Controller", 0, XTYPE_XBOXONE },
@@ -275,12 +281,17 @@ static const struct xpad_device {
 	{ 0x0f0d, 0x0078, "Hori Real Arcade Pro V Kai Xbox One", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOXONE },
 	{ 0x0f0d, 0x00c5, "Hori Fighting Commander ONE", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOXONE },
 	{ 0x0f0d, 0x00dc, "HORIPAD FPS for Nintendo Switch", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOX360 },
+	{ 0x0f0d, 0x0151, "Hori Racing Wheel Overdrive for Xbox Series X", 0, XTYPE_XBOXONE },
+	{ 0x0f0d, 0x0152, "Hori Racing Wheel Overdrive for Xbox Series X", 0, XTYPE_XBOXONE },
 	{ 0x0f30, 0x010b, "Philips Recoil", 0, XTYPE_XBOX },
 	{ 0x0f30, 0x0202, "Joytech Advanced Controller", 0, XTYPE_XBOX },
 	{ 0x0f30, 0x8888, "BigBen XBMiniPad Controller", 0, XTYPE_XBOX },
 	{ 0x102c, 0xff0c, "Joytech Wireless Advanced Controller", 0, XTYPE_XBOX },
 	{ 0x1038, 0x1430, "SteelSeries Stratus Duo", 0, XTYPE_XBOX360 },
 	{ 0x1038, 0x1431, "SteelSeries Stratus Duo", 0, XTYPE_XBOX360 },
+	{ 0x10f5, 0x7005, "Turtle Beach Recon Controller", 0, XTYPE_XBOXONE },
+	{ 0x10f5, 0x7008, "Turtle Beach Recon Controller", MAP_SHARE_BUTTON, XTYPE_XBOXONE },
+	{ 0x10f5, 0x7073, "Turtle Beach Stealth Ultra Controller", MAP_SHARE_BUTTON, XTYPE_XBOXONE },
 	{ 0x11c9, 0x55f0, "Nacon GC-100XF", 0, XTYPE_XBOX360 },
 	{ 0x11ff, 0x0511, "PXN V900", 0, XTYPE_XBOX360 },
 	{ 0x1209, 0x2882, "Ardwiino Controller", 0, XTYPE_XBOX360 },
@@ -305,6 +316,7 @@ static const struct xpad_device {
 	{ 0x1689, 0xfe00, "Razer Sabertooth", 0, XTYPE_XBOX360 },
 	{ 0x17ef, 0x6182, "Lenovo Legion Controller for Windows", 0, XTYPE_XBOX360 },
 	{ 0x1949, 0x041a, "Amazon Game Controller", 0, XTYPE_XBOX360 },
+	{ 0x1a86, 0xe310, "Legion Go S", 0, XTYPE_XBOX360 },
 	{ 0x1bad, 0x0002, "Harmonix Rock Band Guitar", 0, XTYPE_XBOX360 },
 	{ 0x1bad, 0x0003, "Harmonix Rock Band Drumkit", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX360 },
 	{ 0x1bad, 0x0130, "Ion Drum Rocker", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX360 },
@@ -341,8 +353,10 @@ static const struct xpad_device {
 	{ 0x1bad, 0xfa01, "MadCatz GamePad", 0, XTYPE_XBOX360 },
 	{ 0x1bad, 0xfd00, "Razer Onza TE", 0, XTYPE_XBOX360 },
 	{ 0x1bad, 0xfd01, "Razer Onza", 0, XTYPE_XBOX360 },
+	{ 0x1ee9, 0x1590, "ZOTAC Gaming Zone", 0, XTYPE_XBOX360 },
 	{ 0x20d6, 0x2001, "BDA Xbox Series X Wired Controller", 0, XTYPE_XBOXONE },
 	{ 0x20d6, 0x2009, "PowerA Enhanced Wired Controller for Xbox Series X|S", 0, XTYPE_XBOXONE },
+	{ 0x20d6, 0x2064, "PowerA Wired Controller for Xbox", MAP_SHARE_BUTTON, XTYPE_XBOXONE },
 	{ 0x20d6, 0x281f, "PowerA Wired Controller For Xbox 360", 0, XTYPE_XBOX360 },
 	{ 0x2345, 0xe00b, "Machenike G5 Pro Controller", 0, XTYPE_XBOX360 },
 	{ 0x24c6, 0x5000, "Razer Atrox Arcade Stick", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOX360 },
@@ -364,6 +378,7 @@ static const struct xpad_device {
 	{ 0x24c6, 0x5510, "Hori Fighting Commander ONE (Xbox 360/PC Mode)", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOX360 },
 	{ 0x24c6, 0x551a, "PowerA FUSION Pro Controller", 0, XTYPE_XBOXONE },
 	{ 0x24c6, 0x561a, "PowerA FUSION Controller", 0, XTYPE_XBOXONE },
+	{ 0x24c6, 0x581a, "ThrustMaster XB1 Classic Controller", 0, XTYPE_XBOXONE },
 	{ 0x24c6, 0x5b00, "ThrustMaster Ferrari 458 Racing Wheel", 0, XTYPE_XBOX360 },
 	{ 0x24c6, 0x5b02, "Thrustmaster, Inc. GPX Controller", 0, XTYPE_XBOX360 },
 	{ 0x24c6, 0x5b03, "Thrustmaster Ferrari 458 Racing Wheel", 0, XTYPE_XBOX360 },
@@ -372,19 +387,33 @@ static const struct xpad_device {
 	{ 0x2563, 0x058d, "OneXPlayer Gamepad", 0, XTYPE_XBOX360 },
 	{ 0x294b, 0x3303, "Snakebyte GAMEPAD BASE X", 0, XTYPE_XBOXONE },
 	{ 0x294b, 0x3404, "Snakebyte GAMEPAD RGB X", 0, XTYPE_XBOXONE },
+	{ 0x2993, 0x2001, "TECNO Pocket Go", 0, XTYPE_XBOX360 },
 	{ 0x2dc8, 0x2000, "8BitDo Pro 2 Wired Controller fox Xbox", 0, XTYPE_XBOXONE },
-	{ 0x2dc8, 0x3106, "8BitDo Pro 2 Wired Controller", 0, XTYPE_XBOX360 },
+	{ 0x2dc8, 0x3106, "8BitDo Ultimate Wireless / Pro 2 Wired Controller", 0, XTYPE_XBOX360 },
+	{ 0x2dc8, 0x3109, "8BitDo Ultimate Wireless Bluetooth", 0, XTYPE_XBOX360 },
 	{ 0x2dc8, 0x310a, "8BitDo Ultimate 2C Wireless Controller", 0, XTYPE_XBOX360 },
+	{ 0x2dc8, 0x310b, "8BitDo Ultimate 2 Wireless Controller", 0, XTYPE_XBOX360 },
+	{ 0x2dc8, 0x6001, "8BitDo SN30 Pro", 0, XTYPE_XBOX360 },
 	{ 0x2e24, 0x0652, "Hyperkin Duke X-Box One pad", 0, XTYPE_XBOXONE },
+	{ 0x2e24, 0x1688, "Hyperkin X91 X-Box One pad", 0, XTYPE_XBOXONE },
+	{ 0x2e95, 0x0504, "SCUF Gaming Controller", MAP_SHARE_BUTTON, XTYPE_XBOXONE },
 	{ 0x31e3, 0x1100, "Wooting One", 0, XTYPE_XBOX360 },
 	{ 0x31e3, 0x1200, "Wooting Two", 0, XTYPE_XBOX360 },
 	{ 0x31e3, 0x1210, "Wooting Lekker", 0, XTYPE_XBOX360 },
 	{ 0x31e3, 0x1220, "Wooting Two HE", 0, XTYPE_XBOX360 },
+	{ 0x31e3, 0x1230, "Wooting Two HE (ARM)", 0, XTYPE_XBOX360 },
 	{ 0x31e3, 0x1300, "Wooting 60HE (AVR)", 0, XTYPE_XBOX360 },
 	{ 0x31e3, 0x1310, "Wooting 60HE (ARM)", 0, XTYPE_XBOX360 },
+	{ 0x3285, 0x0603, "Nacon Pro Compact controller for Xbox", 0, XTYPE_XBOXONE },
 	{ 0x3285, 0x0607, "Nacon GC-100", 0, XTYPE_XBOX360 },
+	{ 0x3285, 0x0614, "Nacon Pro Compact", 0, XTYPE_XBOXONE },
+	{ 0x3285, 0x0646, "Nacon Pro Compact", 0, XTYPE_XBOXONE },
+	{ 0x3285, 0x0662, "Nacon Revolution5 Pro", 0, XTYPE_XBOX360 },
+	{ 0x3285, 0x0663, "Nacon Evol-X", 0, XTYPE_XBOXONE },
 	{ 0x3537, 0x1004, "GameSir T4 Kaleid", 0, XTYPE_XBOX360 },
+	{ 0x3537, 0x1010, "GameSir G7 SE", 0, XTYPE_XBOXONE },
 	{ 0x3767, 0x0101, "Fanatec Speedster 3 Forceshock Wheel", 0, XTYPE_XBOX },
+	{ 0x413d, 0x2104, "Black Shark Green Ghost Gamepad", 0, XTYPE_XBOX360 },
 	{ 0xffff, 0xffff, "Chinese-made Xbox Controller", 0, XTYPE_XBOX },
 	{ 0x0000, 0x0000, "Generic X-Box pad", 0, XTYPE_UNKNOWN }
 };
@@ -483,9 +512,11 @@ static const struct usb_device_id xpad_table[] = {
 	XPAD_XBOX360_VENDOR(0x03f0),		/* HP HyperX Xbox 360 controllers */
 	XPAD_XBOXONE_VENDOR(0x03f0),		/* HP HyperX Xbox One controllers */
 	XPAD_XBOX360_VENDOR(0x044f),		/* Thrustmaster Xbox 360 controllers */
+	XPAD_XBOXONE_VENDOR(0x044f),		/* Thrustmaster Xbox One controllers */
 	XPAD_XBOX360_VENDOR(0x045e),		/* Microsoft Xbox 360 controllers */
 	XPAD_XBOXONE_VENDOR(0x045e),		/* Microsoft Xbox One controllers */
 	XPAD_XBOX360_VENDOR(0x046d),		/* Logitech Xbox 360-style controllers */
+	XPAD_XBOX360_VENDOR(0x0502),		/* Acer Inc. Xbox 360 style controllers */
 	XPAD_XBOX360_VENDOR(0x056e),		/* Elecom JC-U3613M */
 	XPAD_XBOX360_VENDOR(0x06a3),		/* Saitek P3600 */
 	XPAD_XBOX360_VENDOR(0x0738),		/* Mad Catz Xbox 360 controllers */
@@ -514,7 +545,9 @@ static const struct usb_device_id xpad_table[] = {
 	XPAD_XBOX360_VENDOR(0x1689),		/* Razer Onza */
 	XPAD_XBOX360_VENDOR(0x17ef),		/* Lenovo */
 	XPAD_XBOX360_VENDOR(0x1949),		/* Amazon controllers */
+	XPAD_XBOX360_VENDOR(0x1a86),		/* Nanjing Qinheng Microelectronics (WCH) */
 	XPAD_XBOX360_VENDOR(0x1bad),		/* Harmonix Rock Band guitar and drums */
+	XPAD_XBOX360_VENDOR(0x1ee9),		/* ZOTAC Technology Limited */
 	XPAD_XBOX360_VENDOR(0x20d6),		/* PowerA controllers */
 	XPAD_XBOXONE_VENDOR(0x20d6),		/* PowerA controllers */
 	XPAD_XBOX360_VENDOR(0x2345),		/* Machenike Controllers */
@@ -522,16 +555,20 @@ static const struct usb_device_id xpad_table[] = {
 	XPAD_XBOXONE_VENDOR(0x24c6),		/* PowerA controllers */
 	XPAD_XBOX360_VENDOR(0x2563),		/* OneXPlayer Gamepad */
 	XPAD_XBOX360_VENDOR(0x260d),		/* Dareu H101 */
-       XPAD_XBOXONE_VENDOR(0x294b),            /* Snakebyte */
+	XPAD_XBOXONE_VENDOR(0x294b),		/* Snakebyte */
+	XPAD_XBOX360_VENDOR(0x2993),		/* TECNO Mobile */
 	XPAD_XBOX360_VENDOR(0x2c22),		/* Qanba Controllers */
-	XPAD_XBOX360_VENDOR(0x2dc8),            /* 8BitDo Pro 2 Wired Controller */
-	XPAD_XBOXONE_VENDOR(0x2dc8),		/* 8BitDo Pro 2 Wired Controller for Xbox */
-	XPAD_XBOXONE_VENDOR(0x2e24),		/* Hyperkin Duke Xbox One pad */
-	XPAD_XBOX360_VENDOR(0x2f24),		/* GameSir controllers */
+	XPAD_XBOX360_VENDOR(0x2dc8),		/* 8BitDo Controllers */
+	XPAD_XBOXONE_VENDOR(0x2dc8),		/* 8BitDo Controllers */
+	XPAD_XBOXONE_VENDOR(0x2e24),		/* Hyperkin Controllers */
+	XPAD_XBOX360_VENDOR(0x2f24),		/* GameSir Controllers */
+	XPAD_XBOXONE_VENDOR(0x2e95),		/* SCUF Gaming Controller */
 	XPAD_XBOX360_VENDOR(0x31e3),		/* Wooting Keyboards */
 	XPAD_XBOX360_VENDOR(0x3285),		/* Nacon GC-100 */
+	XPAD_XBOXONE_VENDOR(0x3285),		/* Nacon Evol-X */
 	XPAD_XBOX360_VENDOR(0x3537),		/* GameSir Controllers */
 	XPAD_XBOXONE_VENDOR(0x3537),		/* GameSir Controllers */
+	XPAD_XBOX360_VENDOR(0x413d),		/* Black Shark Green Ghost Controller */
 	{ }
 };
 
@@ -684,7 +721,9 @@ static const struct xboxone_init_packet xboxone_init_packets[] = {
 	XBOXONE_INIT_PKT(0x045e, 0x0b00, xboxone_s_init),
 	XBOXONE_INIT_PKT(0x045e, 0x0b00, extra_input_packet_init),
 	XBOXONE_INIT_PKT(0x0e6f, 0x0000, xboxone_pdp_led_on),
+	XBOXONE_INIT_PKT(0x20d6, 0xa01a, xboxone_pdp_led_on),
 	XBOXONE_INIT_PKT(0x0e6f, 0x0000, xboxone_pdp_auth),
+	XBOXONE_INIT_PKT(0x20d6, 0xa01a, xboxone_pdp_auth),
 	XBOXONE_INIT_PKT(0x24c6, 0x541a, xboxone_rumblebegin_init),
 	XBOXONE_INIT_PKT(0x24c6, 0x542a, xboxone_rumblebegin_init),
 	XBOXONE_INIT_PKT(0x24c6, 0x543a, xboxone_rumblebegin_init),
@@ -995,7 +1034,7 @@ static void xpad360w_process_packet(struct usb_xpad *xpad, u16 cmd, unsigned cha
  *	The report format was gleaned from
  *	https://github.com/kylelemons/xbox/blob/master/xbox.go
  */
-static void xpadone_process_packet(struct usb_xpad *xpad, u16 cmd, unsigned char *data)
+static void xpadone_process_packet(struct usb_xpad *xpad, u16 cmd, unsigned char *data, u32 len)
 {
 	struct input_dev *dev = xpad->dev;
 	bool do_sync = false;
@@ -1036,8 +1075,12 @@ static void xpadone_process_packet(struct usb_xpad *xpad, u16 cmd, unsigned char
 		/* menu/view buttons */
 		input_report_key(dev, BTN_START,  data[4] & BIT(2));
 		input_report_key(dev, BTN_SELECT, data[4] & BIT(3));
-		if (xpad->mapping & MAP_SELECT_BUTTON)
-			input_report_key(dev, KEY_RECORD, data[22] & BIT(0));
+		if (xpad->mapping & MAP_SHARE_BUTTON) {
+			if (xpad->mapping & MAP_SHARE_OFFSET)
+				input_report_key(dev, KEY_RECORD, data[len - 26] & BIT(0));
+			else
+				input_report_key(dev, KEY_RECORD, data[len - 18] & BIT(0));
+		}
 
 		/* buttons A,B,X,Y */
 		input_report_key(dev, BTN_A,	data[4] & BIT(4));
@@ -1185,7 +1228,7 @@ static void xpad_irq_in(struct urb *urb)
 		xpad360w_process_packet(xpad, 0, xpad->idata);
 		break;
 	case XTYPE_XBOXONE:
-		xpadone_process_packet(xpad, 0, xpad->idata);
+		xpadone_process_packet(xpad, 0, xpad->idata, urb->actual_length);
 		break;
 	default:
 		xpad_process_packet(xpad, 0, xpad->idata);
@@ -1942,7 +1985,7 @@ static int xpad_init_input(struct usb_xpad *xpad)
 	    xpad->xtype == XTYPE_XBOXONE) {
 		for (i = 0; xpad360_btn[i] >= 0; i++)
 			input_set_capability(input_dev, EV_KEY, xpad360_btn[i]);
-		if (xpad->mapping & MAP_SELECT_BUTTON)
+		if (xpad->mapping & MAP_SHARE_BUTTON)
 			input_set_capability(input_dev, EV_KEY, KEY_RECORD);
 	} else {
 		for (i = 0; xpad_btn[i] >= 0; i++)
diff --git a/drivers/input/keyboard/atkbd.c b/drivers/input/keyboard/atkbd.c
index 5855d4fc6e6a..f7b08b359c9c 100644
--- a/drivers/input/keyboard/atkbd.c
+++ b/drivers/input/keyboard/atkbd.c
@@ -89,7 +89,7 @@ static const unsigned short atkbd_set2_keycode[ATKBD_KEYMAP_SIZE] = {
 	  0, 46, 45, 32, 18,  5,  4, 95,  0, 57, 47, 33, 20, 19,  6,183,
 	  0, 49, 48, 35, 34, 21,  7,184,  0,  0, 50, 36, 22,  8,  9,185,
 	  0, 51, 37, 23, 24, 11, 10,  0,  0, 52, 53, 38, 39, 25, 12,  0,
-	  0, 89, 40,  0, 26, 13,  0,  0, 58, 54, 28, 27,  0, 43,  0, 85,
+	  0, 89, 40,  0, 26, 13,  0,193, 58, 54, 28, 27,  0, 43,  0, 85,
 	  0, 86, 91, 90, 92,  0, 14, 94,  0, 79,124, 75, 71,121,  0,  0,
 	 82, 83, 80, 76, 77, 72,  1, 69, 87, 78, 81, 74, 55, 73, 70, 99,
 
diff --git a/drivers/input/keyboard/gpio_keys.c b/drivers/input/keyboard/gpio_keys.c
index 380fe8dab3b0..cd14017e7df6 100644
--- a/drivers/input/keyboard/gpio_keys.c
+++ b/drivers/input/keyboard/gpio_keys.c
@@ -449,6 +449,8 @@ static enum hrtimer_restart gpio_keys_irq_timer(struct hrtimer *t)
 						      release_timer);
 	struct input_dev *input = bdata->input;
 
+	guard(spinlock_irqsave)(&bdata->lock);
+
 	if (bdata->key_pressed) {
 		input_report_key(input, *bdata->code, 0);
 		input_sync(input);
@@ -486,7 +488,7 @@ static irqreturn_t gpio_keys_irq_isr(int irq, void *dev_id)
 	if (bdata->release_delay)
 		hrtimer_start(&bdata->release_timer,
 			      ms_to_ktime(bdata->release_delay),
-			      HRTIMER_MODE_REL_HARD);
+			      HRTIMER_MODE_REL);
 out:
 	return IRQ_HANDLED;
 }
@@ -631,7 +633,7 @@ static int gpio_keys_setup_key(struct platform_device *pdev,
 
 		bdata->release_delay = button->debounce_interval;
 		hrtimer_init(&bdata->release_timer,
-			     CLOCK_REALTIME, HRTIMER_MODE_REL_HARD);
+			     CLOCK_REALTIME, HRTIMER_MODE_REL);
 		bdata->release_timer.function = gpio_keys_irq_timer;
 
 		isr = gpio_keys_irq_isr;
diff --git a/drivers/input/keyboard/mtk-pmic-keys.c b/drivers/input/keyboard/mtk-pmic-keys.c
index 4364c3401ff1..486ca8ff86f8 100644
--- a/drivers/input/keyboard/mtk-pmic-keys.c
+++ b/drivers/input/keyboard/mtk-pmic-keys.c
@@ -147,8 +147,8 @@ static void mtk_pmic_keys_lp_reset_setup(struct mtk_pmic_keys *keys,
 	u32 value, mask;
 	int error;
 
-	kregs_home = keys->keys[MTK_PMIC_HOMEKEY_INDEX].regs;
-	kregs_pwr = keys->keys[MTK_PMIC_PWRKEY_INDEX].regs;
+	kregs_home = &regs->keys_regs[MTK_PMIC_HOMEKEY_INDEX];
+	kregs_pwr = &regs->keys_regs[MTK_PMIC_PWRKEY_INDEX];
 
 	error = of_property_read_u32(keys->dev->of_node, "power-off-time-sec",
 				     &long_press_debounce);
diff --git a/drivers/input/misc/cs40l50-vibra.c b/drivers/input/misc/cs40l50-vibra.c
index dce3b0ec8cf3..330f09123631 100644
--- a/drivers/input/misc/cs40l50-vibra.c
+++ b/drivers/input/misc/cs40l50-vibra.c
@@ -238,6 +238,8 @@ static int cs40l50_upload_owt(struct cs40l50_work *work_data)
 	header.data_words = len / sizeof(u32);
 
 	new_owt_effect_data = kmalloc(sizeof(header) + len, GFP_KERNEL);
+	if (!new_owt_effect_data)
+		return -ENOMEM;
 
 	memcpy(new_owt_effect_data, &header, sizeof(header));
 	memcpy(new_owt_effect_data + sizeof(header), work_data->custom_data, len);
diff --git a/drivers/input/misc/ims-pcu.c b/drivers/input/misc/ims-pcu.c
index 4215f9b9c2b0..fc22cbb854a3 100644
--- a/drivers/input/misc/ims-pcu.c
+++ b/drivers/input/misc/ims-pcu.c
@@ -844,6 +844,12 @@ static int ims_pcu_flash_firmware(struct ims_pcu *pcu,
 		addr = be32_to_cpu(rec->addr) / 2;
 		len = be16_to_cpu(rec->len);
 
+		if (len > sizeof(pcu->cmd_buf) - 1 - sizeof(*fragment)) {
+			dev_err(pcu->dev,
+				"Invalid record length in firmware: %d\n", len);
+			return -EINVAL;
+		}
+
 		fragment = (void *)&pcu->cmd_buf[1];
 		put_unaligned_le32(addr, &fragment->addr);
 		fragment->len = len;
diff --git a/drivers/input/misc/iqs7222.c b/drivers/input/misc/iqs7222.c
index be80a31de9f8..846aac9a5c9d 100644
--- a/drivers/input/misc/iqs7222.c
+++ b/drivers/input/misc/iqs7222.c
@@ -100,11 +100,11 @@ enum iqs7222_reg_key_id {
 
 enum iqs7222_reg_grp_id {
 	IQS7222_REG_GRP_STAT,
-	IQS7222_REG_GRP_FILT,
 	IQS7222_REG_GRP_CYCLE,
 	IQS7222_REG_GRP_GLBL,
 	IQS7222_REG_GRP_BTN,
 	IQS7222_REG_GRP_CHAN,
+	IQS7222_REG_GRP_FILT,
 	IQS7222_REG_GRP_SLDR,
 	IQS7222_REG_GRP_TPAD,
 	IQS7222_REG_GRP_GPIO,
@@ -286,6 +286,7 @@ static const struct iqs7222_event_desc iqs7222_tp_events[] = {
 
 struct iqs7222_reg_grp_desc {
 	u16 base;
+	u16 val_len;
 	int num_row;
 	int num_col;
 };
@@ -300,6 +301,7 @@ struct iqs7222_dev_desc {
 	int allow_offset;
 	int event_offset;
 	int comms_offset;
+	int ext_chan;
 	bool legacy_gesture;
 	struct iqs7222_reg_grp_desc reg_grps[IQS7222_NUM_REG_GRPS];
 };
@@ -314,6 +316,7 @@ static const struct iqs7222_dev_desc iqs7222_devs[] = {
 		.allow_offset = 9,
 		.event_offset = 10,
 		.comms_offset = 12,
+		.ext_chan = 10,
 		.reg_grps = {
 			[IQS7222_REG_GRP_STAT] = {
 				.base = IQS7222_SYS_STATUS,
@@ -342,6 +345,7 @@ static const struct iqs7222_dev_desc iqs7222_devs[] = {
 			},
 			[IQS7222_REG_GRP_FILT] = {
 				.base = 0xAC00,
+				.val_len = 3,
 				.num_row = 1,
 				.num_col = 2,
 			},
@@ -371,6 +375,7 @@ static const struct iqs7222_dev_desc iqs7222_devs[] = {
 		.allow_offset = 9,
 		.event_offset = 10,
 		.comms_offset = 12,
+		.ext_chan = 10,
 		.legacy_gesture = true,
 		.reg_grps = {
 			[IQS7222_REG_GRP_STAT] = {
@@ -400,6 +405,7 @@ static const struct iqs7222_dev_desc iqs7222_devs[] = {
 			},
 			[IQS7222_REG_GRP_FILT] = {
 				.base = 0xAC00,
+				.val_len = 3,
 				.num_row = 1,
 				.num_col = 2,
 			},
@@ -454,6 +460,7 @@ static const struct iqs7222_dev_desc iqs7222_devs[] = {
 			},
 			[IQS7222_REG_GRP_FILT] = {
 				.base = 0xC400,
+				.val_len = 3,
 				.num_row = 1,
 				.num_col = 2,
 			},
@@ -496,6 +503,7 @@ static const struct iqs7222_dev_desc iqs7222_devs[] = {
 			},
 			[IQS7222_REG_GRP_FILT] = {
 				.base = 0xC400,
+				.val_len = 3,
 				.num_row = 1,
 				.num_col = 2,
 			},
@@ -543,6 +551,7 @@ static const struct iqs7222_dev_desc iqs7222_devs[] = {
 			},
 			[IQS7222_REG_GRP_FILT] = {
 				.base = 0xAA00,
+				.val_len = 3,
 				.num_row = 1,
 				.num_col = 2,
 			},
@@ -600,6 +609,7 @@ static const struct iqs7222_dev_desc iqs7222_devs[] = {
 			},
 			[IQS7222_REG_GRP_FILT] = {
 				.base = 0xAA00,
+				.val_len = 3,
 				.num_row = 1,
 				.num_col = 2,
 			},
@@ -656,6 +666,7 @@ static const struct iqs7222_dev_desc iqs7222_devs[] = {
 			},
 			[IQS7222_REG_GRP_FILT] = {
 				.base = 0xAE00,
+				.val_len = 3,
 				.num_row = 1,
 				.num_col = 2,
 			},
@@ -712,6 +723,7 @@ static const struct iqs7222_dev_desc iqs7222_devs[] = {
 			},
 			[IQS7222_REG_GRP_FILT] = {
 				.base = 0xAE00,
+				.val_len = 3,
 				.num_row = 1,
 				.num_col = 2,
 			},
@@ -768,6 +780,7 @@ static const struct iqs7222_dev_desc iqs7222_devs[] = {
 			},
 			[IQS7222_REG_GRP_FILT] = {
 				.base = 0xAE00,
+				.val_len = 3,
 				.num_row = 1,
 				.num_col = 2,
 			},
@@ -1604,7 +1617,7 @@ static int iqs7222_force_comms(struct iqs7222_private *iqs7222)
 }
 
 static int iqs7222_read_burst(struct iqs7222_private *iqs7222,
-			      u16 reg, void *val, u16 num_val)
+			      u16 reg, void *val, u16 val_len)
 {
 	u8 reg_buf[sizeof(__be16)];
 	int ret, i;
@@ -1619,7 +1632,7 @@ static int iqs7222_read_burst(struct iqs7222_private *iqs7222,
 		{
 			.addr = client->addr,
 			.flags = I2C_M_RD,
-			.len = num_val * sizeof(__le16),
+			.len = val_len,
 			.buf = (u8 *)val,
 		},
 	};
@@ -1675,7 +1688,7 @@ static int iqs7222_read_word(struct iqs7222_private *iqs7222, u16 reg, u16 *val)
 	__le16 val_buf;
 	int error;
 
-	error = iqs7222_read_burst(iqs7222, reg, &val_buf, 1);
+	error = iqs7222_read_burst(iqs7222, reg, &val_buf, sizeof(val_buf));
 	if (error)
 		return error;
 
@@ -1685,10 +1698,9 @@ static int iqs7222_read_word(struct iqs7222_private *iqs7222, u16 reg, u16 *val)
 }
 
 static int iqs7222_write_burst(struct iqs7222_private *iqs7222,
-			       u16 reg, const void *val, u16 num_val)
+			       u16 reg, const void *val, u16 val_len)
 {
 	int reg_len = reg > U8_MAX ? sizeof(reg) : sizeof(u8);
-	int val_len = num_val * sizeof(__le16);
 	int msg_len = reg_len + val_len;
 	int ret, i;
 	struct i2c_client *client = iqs7222->client;
@@ -1747,7 +1759,7 @@ static int iqs7222_write_word(struct iqs7222_private *iqs7222, u16 reg, u16 val)
 {
 	__le16 val_buf = cpu_to_le16(val);
 
-	return iqs7222_write_burst(iqs7222, reg, &val_buf, 1);
+	return iqs7222_write_burst(iqs7222, reg, &val_buf, sizeof(val_buf));
 }
 
 static int iqs7222_ati_trigger(struct iqs7222_private *iqs7222)
@@ -1831,30 +1843,14 @@ static int iqs7222_dev_init(struct iqs7222_private *iqs7222, int dir)
 
 	/*
 	 * Acknowledge reset before writing any registers in case the device
-	 * suffers a spurious reset during initialization. Because this step
-	 * may change the reserved fields of the second filter beta register,
-	 * its cache must be updated.
-	 *
-	 * Writing the second filter beta register, in turn, may clobber the
-	 * system status register. As such, the filter beta register pair is
-	 * written first to protect against this hazard.
+	 * suffers a spurious reset during initialization.
 	 */
 	if (dir == WRITE) {
-		u16 reg = dev_desc->reg_grps[IQS7222_REG_GRP_FILT].base + 1;
-		u16 filt_setup;
-
 		error = iqs7222_write_word(iqs7222, IQS7222_SYS_SETUP,
 					   iqs7222->sys_setup[0] |
 					   IQS7222_SYS_SETUP_ACK_RESET);
 		if (error)
 			return error;
-
-		error = iqs7222_read_word(iqs7222, reg, &filt_setup);
-		if (error)
-			return error;
-
-		iqs7222->filt_setup[1] &= GENMASK(7, 0);
-		iqs7222->filt_setup[1] |= (filt_setup & ~GENMASK(7, 0));
 	}
 
 	/*
@@ -1883,6 +1879,7 @@ static int iqs7222_dev_init(struct iqs7222_private *iqs7222, int dir)
 		int num_col = dev_desc->reg_grps[i].num_col;
 		u16 reg = dev_desc->reg_grps[i].base;
 		__le16 *val_buf;
+		u16 val_len = dev_desc->reg_grps[i].val_len ? : num_col * sizeof(*val_buf);
 		u16 *val;
 
 		if (!num_col)
@@ -1900,7 +1897,7 @@ static int iqs7222_dev_init(struct iqs7222_private *iqs7222, int dir)
 			switch (dir) {
 			case READ:
 				error = iqs7222_read_burst(iqs7222, reg,
-							   val_buf, num_col);
+							   val_buf, val_len);
 				for (k = 0; k < num_col; k++)
 					val[k] = le16_to_cpu(val_buf[k]);
 				break;
@@ -1909,7 +1906,7 @@ static int iqs7222_dev_init(struct iqs7222_private *iqs7222, int dir)
 				for (k = 0; k < num_col; k++)
 					val_buf[k] = cpu_to_le16(val[k]);
 				error = iqs7222_write_burst(iqs7222, reg,
-							    val_buf, num_col);
+							    val_buf, val_len);
 				break;
 
 			default:
@@ -1962,7 +1959,7 @@ static int iqs7222_dev_info(struct iqs7222_private *iqs7222)
 	int error, i;
 
 	error = iqs7222_read_burst(iqs7222, IQS7222_PROD_NUM, dev_id,
-				   ARRAY_SIZE(dev_id));
+				   sizeof(dev_id));
 	if (error)
 		return error;
 
@@ -2250,7 +2247,7 @@ static int iqs7222_parse_chan(struct iqs7222_private *iqs7222,
 	const struct iqs7222_dev_desc *dev_desc = iqs7222->dev_desc;
 	struct i2c_client *client = iqs7222->client;
 	int num_chan = dev_desc->reg_grps[IQS7222_REG_GRP_CHAN].num_row;
-	int ext_chan = rounddown(num_chan, 10);
+	int ext_chan = dev_desc->ext_chan ? : num_chan;
 	int error, i;
 	u16 *chan_setup = iqs7222->chan_setup[chan_index];
 	u16 *sys_setup = iqs7222->sys_setup;
@@ -2454,7 +2451,7 @@ static int iqs7222_parse_sldr(struct iqs7222_private *iqs7222,
 	const struct iqs7222_dev_desc *dev_desc = iqs7222->dev_desc;
 	struct i2c_client *client = iqs7222->client;
 	int num_chan = dev_desc->reg_grps[IQS7222_REG_GRP_CHAN].num_row;
-	int ext_chan = rounddown(num_chan, 10);
+	int ext_chan = dev_desc->ext_chan ? : num_chan;
 	int count, error, reg_offset, i;
 	u16 *event_mask = &iqs7222->sys_setup[dev_desc->event_offset];
 	u16 *sldr_setup = iqs7222->sldr_setup[sldr_index];
@@ -2917,7 +2914,7 @@ static int iqs7222_report(struct iqs7222_private *iqs7222)
 	__le16 status[IQS7222_MAX_COLS_STAT];
 
 	error = iqs7222_read_burst(iqs7222, IQS7222_SYS_STATUS, status,
-				   num_stat);
+				   num_stat * sizeof(*status));
 	if (error)
 		return error;
 
diff --git a/drivers/input/misc/nxp-bbnsm-pwrkey.c b/drivers/input/misc/nxp-bbnsm-pwrkey.c
index eb4173f9c820..7ba8d166d68c 100644
--- a/drivers/input/misc/nxp-bbnsm-pwrkey.c
+++ b/drivers/input/misc/nxp-bbnsm-pwrkey.c
@@ -187,6 +187,12 @@ static int bbnsm_pwrkey_probe(struct platform_device *pdev)
 	return 0;
 }
 
+static void bbnsm_pwrkey_remove(struct platform_device *pdev)
+{
+	dev_pm_clear_wake_irq(&pdev->dev);
+	device_init_wakeup(&pdev->dev, false);
+}
+
 static int __maybe_unused bbnsm_pwrkey_suspend(struct device *dev)
 {
 	struct platform_device *pdev = to_platform_device(dev);
@@ -223,6 +229,8 @@ static struct platform_driver bbnsm_pwrkey_driver = {
 		.of_match_table = bbnsm_pwrkey_ids,
 	},
 	.probe = bbnsm_pwrkey_probe,
+	.remove = bbnsm_pwrkey_remove,
+
 };
 module_platform_driver(bbnsm_pwrkey_driver);
 
diff --git a/drivers/input/misc/sparcspkr.c b/drivers/input/misc/sparcspkr.c
index 20020cbc0752..a94699f2bbc6 100644
--- a/drivers/input/misc/sparcspkr.c
+++ b/drivers/input/misc/sparcspkr.c
@@ -75,9 +75,14 @@ static int bbc_spkr_event(struct input_dev *dev, unsigned int type, unsigned int
 		return -1;
 
 	switch (code) {
-		case SND_BELL: if (value) value = 1000;
-		case SND_TONE: break;
-		default: return -1;
+	case SND_BELL:
+		if (value)
+			value = 1000;
+		break;
+	case SND_TONE:
+		break;
+	default:
+		return -1;
 	}
 
 	if (value > 20 && value < 32767)
@@ -113,9 +118,14 @@ static int grover_spkr_event(struct input_dev *dev, unsigned int type, unsigned
 		return -1;
 
 	switch (code) {
-		case SND_BELL: if (value) value = 1000;
-		case SND_TONE: break;
-		default: return -1;
+	case SND_BELL:
+		if (value)
+			value = 1000;
+		break;
+	case SND_TONE:
+		break;
+	default:
+		return -1;
 	}
 
 	if (value > 20 && value < 32767)
diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c
index 380aa1614442..2b8895368437 100644
--- a/drivers/input/mouse/synaptics.c
+++ b/drivers/input/mouse/synaptics.c
@@ -163,6 +163,7 @@ static const char * const topbuttonpad_pnp_ids[] = {
 
 static const char * const smbus_pnp_ids[] = {
 	/* all of the topbuttonpad_pnp_ids are valid, we just add some extras */
+	"DLL060d", /* Dell Precision M3800 */
 	"LEN0048", /* X1 Carbon 3 */
 	"LEN0046", /* X250 */
 	"LEN0049", /* Yoga 11e */
@@ -189,11 +190,15 @@ static const char * const smbus_pnp_ids[] = {
 	"LEN2054", /* E480 */
 	"LEN2055", /* E580 */
 	"LEN2068", /* T14 Gen 1 */
+	"SYN1221", /* TUXEDO InfinityBook Pro 14 v5 */
+	"SYN3003", /* HP EliteBook 850 G1 */
 	"SYN3015", /* HP EliteBook 840 G2 */
 	"SYN3052", /* HP EliteBook 840 G4 */
 	"SYN3221", /* HP 15-ay000 */
 	"SYN323d", /* HP Spectre X360 13-w013dx */
 	"SYN3257", /* HP Envy 13-ad105ng */
+	"TOS01f6", /* Dynabook Portege X30L-G */
+	"TOS0213", /* Dynabook Portege X30-D */
 	NULL
 };
 
@@ -667,23 +672,50 @@ static void synaptics_pt_stop(struct serio *serio)
 	serio_continue_rx(parent->ps2dev.serio);
 }
 
+static int synaptics_pt_open(struct serio *serio)
+{
+	struct psmouse *parent = psmouse_from_serio(serio->parent);
+	struct synaptics_data *priv = parent->private;
+
+	guard(serio_pause_rx)(parent->ps2dev.serio);
+	priv->pt_port_open = true;
+
+	return 0;
+}
+
+static void synaptics_pt_close(struct serio *serio)
+{
+	struct psmouse *parent = psmouse_from_serio(serio->parent);
+	struct synaptics_data *priv = parent->private;
+
+	guard(serio_pause_rx)(parent->ps2dev.serio);
+	priv->pt_port_open = false;
+}
+
 static int synaptics_is_pt_packet(u8 *buf)
 {
 	return (buf[0] & 0xFC) == 0x84 && (buf[3] & 0xCC) == 0xC4;
 }
 
-static void synaptics_pass_pt_packet(struct serio *ptport, u8 *packet)
+static void synaptics_pass_pt_packet(struct synaptics_data *priv, u8 *packet)
 {
-	struct psmouse *child = psmouse_from_serio(ptport);
+	struct serio *ptport;
 
-	if (child && child->state == PSMOUSE_ACTIVATED) {
-		serio_interrupt(ptport, packet[1], 0);
-		serio_interrupt(ptport, packet[4], 0);
-		serio_interrupt(ptport, packet[5], 0);
-		if (child->pktsize == 4)
-			serio_interrupt(ptport, packet[2], 0);
-	} else {
-		serio_interrupt(ptport, packet[1], 0);
+	ptport = priv->pt_port;
+	if (!ptport)
+		return;
+
+	serio_interrupt(ptport, packet[1], 0);
+
+	if (priv->pt_port_open) {
+		struct psmouse *child = psmouse_from_serio(ptport);
+
+		if (child->state == PSMOUSE_ACTIVATED) {
+			serio_interrupt(ptport, packet[4], 0);
+			serio_interrupt(ptport, packet[5], 0);
+			if (child->pktsize == 4)
+				serio_interrupt(ptport, packet[2], 0);
+		}
 	}
 }
 
@@ -722,6 +754,8 @@ static void synaptics_pt_create(struct psmouse *psmouse)
 	serio->write = synaptics_pt_write;
 	serio->start = synaptics_pt_start;
 	serio->stop = synaptics_pt_stop;
+	serio->open = synaptics_pt_open;
+	serio->close = synaptics_pt_close;
 	serio->parent = psmouse->ps2dev.serio;
 
 	psmouse->pt_activate = synaptics_pt_activate;
@@ -1218,11 +1252,10 @@ static psmouse_ret_t synaptics_process_byte(struct psmouse *psmouse)
 
 		if (SYN_CAP_PASS_THROUGH(priv->info.capabilities) &&
 		    synaptics_is_pt_packet(psmouse->packet)) {
-			if (priv->pt_port)
-				synaptics_pass_pt_packet(priv->pt_port,
-							 psmouse->packet);
-		} else
+			synaptics_pass_pt_packet(priv, psmouse->packet);
+		} else {
 			synaptics_process_packet(psmouse);
+		}
 
 		return PSMOUSE_FULL_PACKET;
 	}
diff --git a/drivers/input/mouse/synaptics.h b/drivers/input/mouse/synaptics.h
index 08533d1b1b16..4b34f13b9f76 100644
--- a/drivers/input/mouse/synaptics.h
+++ b/drivers/input/mouse/synaptics.h
@@ -188,6 +188,7 @@ struct synaptics_data {
 	bool disable_gesture;			/* disable gestures */
 
 	struct serio *pt_port;			/* Pass-through serio port */
+	bool pt_port_open;
 
 	/*
 	 * Last received Advanced Gesture Mode (AGM) packet. An AGM packet
diff --git a/drivers/input/rmi4/rmi_f34.c b/drivers/input/rmi4/rmi_f34.c
index e2468bc04a5c..c2516c754958 100644
--- a/drivers/input/rmi4/rmi_f34.c
+++ b/drivers/input/rmi4/rmi_f34.c
@@ -4,6 +4,7 @@
  * Copyright (C) 2016 Zodiac Inflight Innovations
  */
 
+#include "linux/device.h"
 #include <linux/kernel.h>
 #include <linux/rmi.h>
 #include <linux/firmware.h>
@@ -298,39 +299,30 @@ out:
 	return ret;
 }
 
-static int rmi_f34_status(struct rmi_function *fn)
-{
-	struct f34_data *f34 = dev_get_drvdata(&fn->dev);
-
-	/*
-	 * The status is the percentage complete, or once complete,
-	 * zero for success or a negative return code.
-	 */
-	return f34->update_status;
-}
-
 static ssize_t rmi_driver_bootloader_id_show(struct device *dev,
 					     struct device_attribute *dattr,
 					     char *buf)
 {
 	struct rmi_driver_data *data = dev_get_drvdata(dev);
-	struct rmi_function *fn = data->f34_container;
+	struct rmi_function *fn;
 	struct f34_data *f34;
 
-	if (fn) {
-		f34 = dev_get_drvdata(&fn->dev);
-
-		if (f34->bl_version == 5)
-			return sysfs_emit(buf, "%c%c\n",
-					  f34->bootloader_id[0],
-					  f34->bootloader_id[1]);
-		else
-			return sysfs_emit(buf, "V%d.%d\n",
-					  f34->bootloader_id[1],
-					  f34->bootloader_id[0]);
-	}
+	fn = data->f34_container;
+	if (!fn)
+		return -ENODEV;
 
-	return 0;
+	f34 = dev_get_drvdata(&fn->dev);
+	if (!f34)
+		return -ENODEV;
+
+	if (f34->bl_version == 5)
+		return sysfs_emit(buf, "%c%c\n",
+				  f34->bootloader_id[0],
+				  f34->bootloader_id[1]);
+	else
+		return sysfs_emit(buf, "V%d.%d\n",
+				  f34->bootloader_id[1],
+				  f34->bootloader_id[0]);
 }
 
 static DEVICE_ATTR(bootloader_id, 0444, rmi_driver_bootloader_id_show, NULL);
@@ -343,13 +335,16 @@ static ssize_t rmi_driver_configuration_id_show(struct device *dev,
 	struct rmi_function *fn = data->f34_container;
 	struct f34_data *f34;
 
-	if (fn) {
-		f34 = dev_get_drvdata(&fn->dev);
+	fn = data->f34_container;
+	if (!fn)
+		return -ENODEV;
 
-		return sysfs_emit(buf, "%s\n", f34->configuration_id);
-	}
+	f34 = dev_get_drvdata(&fn->dev);
+	if (!f34)
+		return -ENODEV;
 
-	return 0;
+
+	return sysfs_emit(buf, "%s\n", f34->configuration_id);
 }
 
 static DEVICE_ATTR(configuration_id, 0444,
@@ -365,10 +360,14 @@ static int rmi_firmware_update(struct rmi_driver_data *data,
 
 	if (!data->f34_container) {
 		dev_warn(dev, "%s: No F34 present!\n", __func__);
-		return -EINVAL;
+		return -ENODEV;
 	}
 
 	f34 = dev_get_drvdata(&data->f34_container->dev);
+	if (!f34) {
+		dev_warn(dev, "%s: No valid F34 present!\n", __func__);
+		return -ENODEV;
+	}
 
 	if (f34->bl_version >= 7) {
 		if (data->pdt_props & HAS_BSR) {
@@ -494,10 +493,18 @@ static ssize_t rmi_driver_update_fw_status_show(struct device *dev,
 						char *buf)
 {
 	struct rmi_driver_data *data = dev_get_drvdata(dev);
-	int update_status = 0;
+	struct f34_data *f34;
+	int update_status = -ENODEV;
 
-	if (data->f34_container)
-		update_status = rmi_f34_status(data->f34_container);
+	/*
+	 * The status is the percentage complete, or once complete,
+	 * zero for success or a negative return code.
+	 */
+	if (data->f34_container) {
+		f34 = dev_get_drvdata(&data->f34_container->dev);
+		if (f34)
+			update_status = f34->update_status;
+	}
 
 	return sysfs_emit(buf, "%d\n", update_status);
 }
@@ -517,33 +524,21 @@ static const struct attribute_group rmi_firmware_attr_group = {
 	.attrs = rmi_firmware_attrs,
 };
 
-static int rmi_f34_probe(struct rmi_function *fn)
+static int rmi_f34v5_probe(struct f34_data *f34)
 {
-	struct f34_data *f34;
-	unsigned char f34_queries[9];
+	struct rmi_function *fn = f34->fn;
+	u8 f34_queries[9];
 	bool has_config_id;
-	u8 version = fn->fd.function_version;
-	int ret;
-
-	f34 = devm_kzalloc(&fn->dev, sizeof(struct f34_data), GFP_KERNEL);
-	if (!f34)
-		return -ENOMEM;
-
-	f34->fn = fn;
-	dev_set_drvdata(&fn->dev, f34);
-
-	/* v5 code only supported version 0, try V7 probe */
-	if (version > 0)
-		return rmi_f34v7_probe(f34);
+	int error;
 
 	f34->bl_version = 5;
 
-	ret = rmi_read_block(fn->rmi_dev, fn->fd.query_base_addr,
-			     f34_queries, sizeof(f34_queries));
-	if (ret) {
+	error = rmi_read_block(fn->rmi_dev, fn->fd.query_base_addr,
+			       f34_queries, sizeof(f34_queries));
+	if (error) {
 		dev_err(&fn->dev, "%s: Failed to query properties\n",
 			__func__);
-		return ret;
+		return error;
 	}
 
 	snprintf(f34->bootloader_id, sizeof(f34->bootloader_id),
@@ -569,11 +564,11 @@ static int rmi_f34_probe(struct rmi_function *fn)
 		f34->v5.config_blocks);
 
 	if (has_config_id) {
-		ret = rmi_read_block(fn->rmi_dev, fn->fd.control_base_addr,
-				     f34_queries, sizeof(f34_queries));
-		if (ret) {
+		error = rmi_read_block(fn->rmi_dev, fn->fd.control_base_addr,
+				       f34_queries, sizeof(f34_queries));
+		if (error) {
 			dev_err(&fn->dev, "Failed to read F34 config ID\n");
-			return ret;
+			return error;
 		}
 
 		snprintf(f34->configuration_id, sizeof(f34->configuration_id),
@@ -582,12 +577,34 @@ static int rmi_f34_probe(struct rmi_function *fn)
 			 f34_queries[2], f34_queries[3]);
 
 		rmi_dbg(RMI_DEBUG_FN, &fn->dev, "Configuration ID: %s\n",
-			 f34->configuration_id);
+			f34->configuration_id);
 	}
 
 	return 0;
 }
 
+static int rmi_f34_probe(struct rmi_function *fn)
+{
+	struct f34_data *f34;
+	u8 version = fn->fd.function_version;
+	int error;
+
+	f34 = devm_kzalloc(&fn->dev, sizeof(struct f34_data), GFP_KERNEL);
+	if (!f34)
+		return -ENOMEM;
+
+	f34->fn = fn;
+
+	/* v5 code only supported version 0 */
+	error = version == 0 ? rmi_f34v5_probe(f34) : rmi_f34v7_probe(f34);
+	if (error)
+		return error;
+
+	dev_set_drvdata(&fn->dev, f34);
+
+	return 0;
+}
+
 int rmi_f34_create_sysfs(struct rmi_device *rmi_dev)
 {
 	return sysfs_create_group(&rmi_dev->dev.kobj, &rmi_firmware_attr_group);
diff --git a/drivers/input/serio/i8042-acpipnpio.h b/drivers/input/serio/i8042-acpipnpio.h
index 34d1f07ea4c3..8813db7eec39 100644
--- a/drivers/input/serio/i8042-acpipnpio.h
+++ b/drivers/input/serio/i8042-acpipnpio.h
@@ -1080,16 +1080,14 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "TUXEDO"),
 			DMI_MATCH(DMI_BOARD_NAME, "AURA1501"),
 		},
-		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
-					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
+		.driver_data = (void *)(SERIO_QUIRK_FORCENORESTORE)
 	},
 	{
 		.matches = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "TUXEDO"),
 			DMI_MATCH(DMI_BOARD_NAME, "EDUBOOK1502"),
 		},
-		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
-					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
+		.driver_data = (void *)(SERIO_QUIRK_FORCENORESTORE)
 	},
 	{
 		/* Mivvy M310 */
@@ -1159,9 +1157,7 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = {
 	},
 	/*
 	 * A lot of modern Clevo barebones have touchpad and/or keyboard issues
-	 * after suspend fixable with nomux + reset + noloop + nopnp. Luckily,
-	 * none of them have an external PS/2 port so this can safely be set for
-	 * all of them.
+	 * after suspend fixable with the forcenorestore quirk.
 	 * Clevo barebones come with board_vendor and/or system_vendor set to
 	 * either the very generic string "Notebook" and/or a different value
 	 * for each individual reseller. The only somewhat universal way to
@@ -1171,29 +1167,25 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = {
 		.matches = {
 			DMI_MATCH(DMI_BOARD_NAME, "LAPQC71A"),
 		},
-		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
-					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
+		.driver_data = (void *)(SERIO_QUIRK_FORCENORESTORE)
 	},
 	{
 		.matches = {
 			DMI_MATCH(DMI_BOARD_NAME, "LAPQC71B"),
 		},
-		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
-					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
+		.driver_data = (void *)(SERIO_QUIRK_FORCENORESTORE)
 	},
 	{
 		.matches = {
 			DMI_MATCH(DMI_BOARD_NAME, "N140CU"),
 		},
-		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
-					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
+		.driver_data = (void *)(SERIO_QUIRK_FORCENORESTORE)
 	},
 	{
 		.matches = {
 			DMI_MATCH(DMI_BOARD_NAME, "N141CU"),
 		},
-		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
-					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
+		.driver_data = (void *)(SERIO_QUIRK_FORCENORESTORE)
 	},
 	{
 		.matches = {
@@ -1205,29 +1197,19 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = {
 		.matches = {
 			DMI_MATCH(DMI_BOARD_NAME, "NH5xAx"),
 		},
-		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
-					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
+		.driver_data = (void *)(SERIO_QUIRK_FORCENORESTORE)
 	},
 	{
-		/*
-		 * Setting SERIO_QUIRK_NOMUX or SERIO_QUIRK_RESET_ALWAYS makes
-		 * the keyboard very laggy for ~5 seconds after boot and
-		 * sometimes also after resume.
-		 * However both are required for the keyboard to not fail
-		 * completely sometimes after boot or resume.
-		 */
 		.matches = {
 			DMI_MATCH(DMI_BOARD_NAME, "NHxxRZQ"),
 		},
-		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
-					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
+		.driver_data = (void *)(SERIO_QUIRK_FORCENORESTORE)
 	},
 	{
 		.matches = {
 			DMI_MATCH(DMI_BOARD_NAME, "NL5xRU"),
 		},
-		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
-					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
+		.driver_data = (void *)(SERIO_QUIRK_FORCENORESTORE)
 	},
 	/*
 	 * At least one modern Clevo barebone has the touchpad connected both
@@ -1243,17 +1225,15 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = {
 		.matches = {
 			DMI_MATCH(DMI_BOARD_NAME, "NS50MU"),
 		},
-		.driver_data = (void *)(SERIO_QUIRK_NOAUX | SERIO_QUIRK_NOMUX |
-					SERIO_QUIRK_RESET_ALWAYS | SERIO_QUIRK_NOLOOP |
-					SERIO_QUIRK_NOPNP)
+		.driver_data = (void *)(SERIO_QUIRK_NOAUX |
+					SERIO_QUIRK_FORCENORESTORE)
 	},
 	{
 		.matches = {
 			DMI_MATCH(DMI_BOARD_NAME, "NS50_70MU"),
 		},
-		.driver_data = (void *)(SERIO_QUIRK_NOAUX | SERIO_QUIRK_NOMUX |
-					SERIO_QUIRK_RESET_ALWAYS | SERIO_QUIRK_NOLOOP |
-					SERIO_QUIRK_NOPNP)
+		.driver_data = (void *)(SERIO_QUIRK_NOAUX |
+					SERIO_QUIRK_FORCENORESTORE)
 	},
 	{
 		.matches = {
@@ -1265,8 +1245,13 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = {
 		.matches = {
 			DMI_MATCH(DMI_BOARD_NAME, "NJ50_70CU"),
 		},
-		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
-					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
+		.driver_data = (void *)(SERIO_QUIRK_FORCENORESTORE)
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_BOARD_NAME, "P640RE"),
+		},
+		.driver_data = (void *)(SERIO_QUIRK_FORCENORESTORE)
 	},
 	{
 		/*
@@ -1277,16 +1262,14 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = {
 		.matches = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "P65xH"),
 		},
-		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
-					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
+		.driver_data = (void *)(SERIO_QUIRK_FORCENORESTORE)
 	},
 	{
 		/* Clevo P650RS, 650RP6, Sager NP8152-S, and others */
 		.matches = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "P65xRP"),
 		},
-		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
-					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
+		.driver_data = (void *)(SERIO_QUIRK_FORCENORESTORE)
 	},
 	{
 		/*
@@ -1297,8 +1280,7 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = {
 		.matches = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "P65_P67H"),
 		},
-		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
-					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
+		.driver_data = (void *)(SERIO_QUIRK_FORCENORESTORE)
 	},
 	{
 		/*
@@ -1309,8 +1291,7 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = {
 		.matches = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "P65_67RP"),
 		},
-		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
-					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
+		.driver_data = (void *)(SERIO_QUIRK_FORCENORESTORE)
 	},
 	{
 		/*
@@ -1321,8 +1302,7 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = {
 		.matches = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "P65_67RS"),
 		},
-		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
-					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
+		.driver_data = (void *)(SERIO_QUIRK_FORCENORESTORE)
 	},
 	{
 		/*
@@ -1333,22 +1313,43 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = {
 		.matches = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "P67xRP"),
 		},
-		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
-					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
+		.driver_data = (void *)(SERIO_QUIRK_FORCENORESTORE)
 	},
 	{
 		.matches = {
 			DMI_MATCH(DMI_BOARD_NAME, "PB50_70DFx,DDx"),
 		},
-		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
-					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
+		.driver_data = (void *)(SERIO_QUIRK_FORCENORESTORE)
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_BOARD_NAME, "PB51RF"),
+		},
+		.driver_data = (void *)(SERIO_QUIRK_FORCENORESTORE)
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_BOARD_NAME, "PB71RD"),
+		},
+		.driver_data = (void *)(SERIO_QUIRK_FORCENORESTORE)
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_BOARD_NAME, "PC70DR"),
+		},
+		.driver_data = (void *)(SERIO_QUIRK_FORCENORESTORE)
 	},
 	{
 		.matches = {
 			DMI_MATCH(DMI_BOARD_NAME, "PCX0DX"),
 		},
-		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
-					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
+		.driver_data = (void *)(SERIO_QUIRK_FORCENORESTORE)
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_BOARD_NAME, "PCX0DX_GN20"),
+		},
+		.driver_data = (void *)(SERIO_QUIRK_FORCENORESTORE)
 	},
 	/* See comment on TUXEDO InfinityBook S17 Gen6 / Clevo NS70MU above */
 	{
@@ -1361,15 +1362,13 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = {
 		.matches = {
 			DMI_MATCH(DMI_BOARD_NAME, "X170SM"),
 		},
-		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
-					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
+		.driver_data = (void *)(SERIO_QUIRK_FORCENORESTORE)
 	},
 	{
 		.matches = {
 			DMI_MATCH(DMI_BOARD_NAME, "X170KM-G"),
 		},
-		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
-					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
+		.driver_data = (void *)(SERIO_QUIRK_FORCENORESTORE)
 	},
 	{
 		/*
diff --git a/drivers/input/touchscreen/ads7846.c b/drivers/input/touchscreen/ads7846.c
index 607f18af7010..212dafa0bba2 100644
--- a/drivers/input/touchscreen/ads7846.c
+++ b/drivers/input/touchscreen/ads7846.c
@@ -1011,7 +1011,7 @@ static int ads7846_setup_pendown(struct spi_device *spi,
 	if (pdata->get_pendown_state) {
 		ts->get_pendown_state = pdata->get_pendown_state;
 	} else {
-		ts->gpio_pendown = gpiod_get(&spi->dev, "pendown", GPIOD_IN);
+		ts->gpio_pendown = devm_gpiod_get(&spi->dev, "pendown", GPIOD_IN);
 		if (IS_ERR(ts->gpio_pendown)) {
 			dev_err(&spi->dev, "failed to request pendown GPIO\n");
 			return PTR_ERR(ts->gpio_pendown);
diff --git a/drivers/input/touchscreen/cyttsp5.c b/drivers/input/touchscreen/cyttsp5.c
index eafe5a9b8964..071b7c9bf566 100644
--- a/drivers/input/touchscreen/cyttsp5.c
+++ b/drivers/input/touchscreen/cyttsp5.c
@@ -580,7 +580,7 @@ static int cyttsp5_power_control(struct cyttsp5 *ts, bool on)
 	int rc;
 
 	SET_CMD_REPORT_TYPE(cmd[0], 0);
-	SET_CMD_REPORT_ID(cmd[0], HID_POWER_SLEEP);
+	SET_CMD_REPORT_ID(cmd[0], state);
 	SET_CMD_OPCODE(cmd[1], HID_CMD_SET_POWER);
 
 	rc = cyttsp5_write(ts, HID_COMMAND_REG, cmd, sizeof(cmd));
@@ -870,13 +870,16 @@ static int cyttsp5_probe(struct device *dev, struct regmap *regmap, int irq,
 	ts->input->phys = ts->phys;
 	input_set_drvdata(ts->input, ts);
 
-	/* Reset the gpio to be in a reset state */
+	/* Assert gpio to be in a reset state */
 	ts->reset_gpio = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_HIGH);
 	if (IS_ERR(ts->reset_gpio)) {
 		error = PTR_ERR(ts->reset_gpio);
 		dev_err(dev, "Failed to request reset gpio, error %d\n", error);
 		return error;
 	}
+
+	fsleep(10); /* Ensure long-enough reset pulse (minimum 10us). */
+
 	gpiod_set_value_cansleep(ts->reset_gpio, 0);
 
 	/* Need a delay to have device up */
diff --git a/drivers/input/touchscreen/goodix_berlin_core.c b/drivers/input/touchscreen/goodix_berlin_core.c
index 3fc03cf0ca23..141c64675997 100644
--- a/drivers/input/touchscreen/goodix_berlin_core.c
+++ b/drivers/input/touchscreen/goodix_berlin_core.c
@@ -165,7 +165,7 @@ struct goodix_berlin_core {
 	struct device *dev;
 	struct regmap *regmap;
 	struct regulator *avdd;
-	struct regulator *iovdd;
+	struct regulator *vddio;
 	struct gpio_desc *reset_gpio;
 	struct touchscreen_properties props;
 	struct goodix_berlin_fw_version fw_version;
@@ -248,19 +248,19 @@ static int goodix_berlin_power_on(struct goodix_berlin_core *cd)
 {
 	int error;
 
-	error = regulator_enable(cd->iovdd);
+	error = regulator_enable(cd->vddio);
 	if (error) {
-		dev_err(cd->dev, "Failed to enable iovdd: %d\n", error);
+		dev_err(cd->dev, "Failed to enable vddio: %d\n", error);
 		return error;
 	}
 
-	/* Vendor waits 3ms for IOVDD to settle */
+	/* Vendor waits 3ms for VDDIO to settle */
 	usleep_range(3000, 3100);
 
 	error = regulator_enable(cd->avdd);
 	if (error) {
 		dev_err(cd->dev, "Failed to enable avdd: %d\n", error);
-		goto err_iovdd_disable;
+		goto err_vddio_disable;
 	}
 
 	/* Vendor waits 15ms for IOVDD to settle */
@@ -283,8 +283,8 @@ static int goodix_berlin_power_on(struct goodix_berlin_core *cd)
 err_dev_reset:
 	gpiod_set_value_cansleep(cd->reset_gpio, 1);
 	regulator_disable(cd->avdd);
-err_iovdd_disable:
-	regulator_disable(cd->iovdd);
+err_vddio_disable:
+	regulator_disable(cd->vddio);
 	return error;
 }
 
@@ -292,7 +292,7 @@ static void goodix_berlin_power_off(struct goodix_berlin_core *cd)
 {
 	gpiod_set_value_cansleep(cd->reset_gpio, 1);
 	regulator_disable(cd->avdd);
-	regulator_disable(cd->iovdd);
+	regulator_disable(cd->vddio);
 }
 
 static int goodix_berlin_read_version(struct goodix_berlin_core *cd)
@@ -744,10 +744,10 @@ int goodix_berlin_probe(struct device *dev, int irq, const struct input_id *id,
 		return dev_err_probe(dev, PTR_ERR(cd->avdd),
 				     "Failed to request avdd regulator\n");
 
-	cd->iovdd = devm_regulator_get(dev, "iovdd");
-	if (IS_ERR(cd->iovdd))
-		return dev_err_probe(dev, PTR_ERR(cd->iovdd),
-				     "Failed to request iovdd regulator\n");
+	cd->vddio = devm_regulator_get(dev, "vddio");
+	if (IS_ERR(cd->vddio))
+		return dev_err_probe(dev, PTR_ERR(cd->vddio),
+				     "Failed to request vddio regulator\n");
 
 	error = goodix_berlin_power_on(cd);
 	if (error) {
diff --git a/drivers/interconnect/qcom/sc7280.c b/drivers/interconnect/qcom/sc7280.c
index 167971f8e8be..fdb02a87e312 100644
--- a/drivers/interconnect/qcom/sc7280.c
+++ b/drivers/interconnect/qcom/sc7280.c
@@ -238,6 +238,7 @@ static struct qcom_icc_node xm_pcie3_1 = {
 	.id = SC7280_MASTER_PCIE_1,
 	.channels = 1,
 	.buswidth = 8,
+	.num_links = 1,
 	.links = { SC7280_SLAVE_ANOC_PCIE_GEM_NOC },
 };
 
diff --git a/drivers/interconnect/qcom/sc8180x.c b/drivers/interconnect/qcom/sc8180x.c
index 03d626776ba1..576f90a7d55f 100644
--- a/drivers/interconnect/qcom/sc8180x.c
+++ b/drivers/interconnect/qcom/sc8180x.c
@@ -1492,34 +1492,40 @@ static struct qcom_icc_bcm bcm_sh3 = {
 
 static struct qcom_icc_bcm bcm_sn0 = {
 	.name = "SN0",
+	.num_nodes = 1,
 	.nodes = { &slv_qns_gemnoc_sf }
 };
 
 static struct qcom_icc_bcm bcm_sn1 = {
 	.name = "SN1",
+	.num_nodes = 1,
 	.nodes = { &slv_qxs_imem }
 };
 
 static struct qcom_icc_bcm bcm_sn2 = {
 	.name = "SN2",
 	.keepalive = true,
+	.num_nodes = 1,
 	.nodes = { &slv_qns_gemnoc_gc }
 };
 
 static struct qcom_icc_bcm bcm_co2 = {
 	.name = "CO2",
+	.num_nodes = 1,
 	.nodes = { &mas_qnm_npu }
 };
 
 static struct qcom_icc_bcm bcm_sn3 = {
 	.name = "SN3",
 	.keepalive = true,
+	.num_nodes = 2,
 	.nodes = { &slv_srvc_aggre1_noc,
 		  &slv_qns_cnoc }
 };
 
 static struct qcom_icc_bcm bcm_sn4 = {
 	.name = "SN4",
+	.num_nodes = 1,
 	.nodes = { &slv_qxs_pimem }
 };
 
diff --git a/drivers/interconnect/qcom/sc8280xp.c b/drivers/interconnect/qcom/sc8280xp.c
index 7acd152bf0dd..fab5978ed9d3 100644
--- a/drivers/interconnect/qcom/sc8280xp.c
+++ b/drivers/interconnect/qcom/sc8280xp.c
@@ -48,6 +48,7 @@ static struct qcom_icc_node qnm_a1noc_cfg = {
 	.id = SC8280XP_MASTER_A1NOC_CFG,
 	.channels = 1,
 	.buswidth = 4,
+	.num_links = 1,
 	.links = { SC8280XP_SLAVE_SERVICE_A1NOC },
 };
 
diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
index b3aa1f5d5321..1469ad0794f2 100644
--- a/drivers/iommu/Kconfig
+++ b/drivers/iommu/Kconfig
@@ -199,7 +199,6 @@ source "drivers/iommu/iommufd/Kconfig"
 config IRQ_REMAP
 	bool "Support for Interrupt Remapping"
 	depends on X86_64 && X86_IO_APIC && PCI_MSI && ACPI
-	select DMAR_TABLE if INTEL_IOMMU
 	help
 	  Supports Interrupt remapping for IO-APIC and MSI devices.
 	  To use x2apic mode in the CPU's which support x2APIC enhancements or
diff --git a/drivers/iommu/amd/amd_iommu.h b/drivers/iommu/amd/amd_iommu.h
index 6386fa4556d9..6fac9ee8dd3e 100644
--- a/drivers/iommu/amd/amd_iommu.h
+++ b/drivers/iommu/amd/amd_iommu.h
@@ -87,7 +87,6 @@ int amd_iommu_complete_ppr(struct device *dev, u32 pasid, int status, int tag);
  */
 void amd_iommu_flush_all_caches(struct amd_iommu *iommu);
 void amd_iommu_update_and_flush_device_table(struct protection_domain *domain);
-void amd_iommu_domain_update(struct protection_domain *domain);
 void amd_iommu_domain_flush_pages(struct protection_domain *domain,
 				  u64 address, size_t size);
 void amd_iommu_dev_flush_pasid_pages(struct iommu_dev_data *dev_data,
diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h
index 601fb4ee6900..6fb2f2919ab1 100644
--- a/drivers/iommu/amd/amd_iommu_types.h
+++ b/drivers/iommu/amd/amd_iommu_types.h
@@ -175,6 +175,7 @@
 #define CONTROL_GAM_EN		25
 #define CONTROL_GALOG_EN	28
 #define CONTROL_GAINT_EN	29
+#define CONTROL_EPH_EN		45
 #define CONTROL_XT_EN		50
 #define CONTROL_INTCAPXT_EN	51
 #define CONTROL_IRTCACHEDIS	59
diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c
index 43131c3a2172..ff11cd7e5c06 100644
--- a/drivers/iommu/amd/init.c
+++ b/drivers/iommu/amd/init.c
@@ -2647,6 +2647,10 @@ static void iommu_init_flags(struct amd_iommu *iommu)
 
 	/* Set IOTLB invalidation timeout to 1s */
 	iommu_set_inv_tlb_timeout(iommu, CTRL_INV_TO_1S);
+
+	/* Enable Enhanced Peripheral Page Request Handling */
+	if (check_feature(FEATURE_EPHSUP))
+		iommu_feature_enable(iommu, CONTROL_EPH_EN);
 }
 
 static void iommu_apply_resume_quirks(struct amd_iommu *iommu)
@@ -3651,6 +3655,14 @@ found:
 	while (*uid == '0' && *(uid + 1))
 		uid++;
 
+	if (strlen(hid) >= ACPIHID_HID_LEN) {
+		pr_err("Invalid command line: hid is too long\n");
+		return 1;
+	} else if (strlen(uid) >= ACPIHID_UID_LEN) {
+		pr_err("Invalid command line: uid is too long\n");
+		return 1;
+	}
+
 	i = early_acpihid_map_size++;
 	memcpy(early_acpihid_map[i].hid, hid, strlen(hid));
 	memcpy(early_acpihid_map[i].uid, uid, strlen(uid));
diff --git a/drivers/iommu/amd/io_pgtable_v2.c b/drivers/iommu/amd/io_pgtable_v2.c
index c616de2c5926..a56a27396305 100644
--- a/drivers/iommu/amd/io_pgtable_v2.c
+++ b/drivers/iommu/amd/io_pgtable_v2.c
@@ -254,7 +254,7 @@ static int iommu_v2_map_pages(struct io_pgtable_ops *ops, unsigned long iova,
 		pte = v2_alloc_pte(cfg->amd.nid, pgtable->pgd,
 				   iova, map_size, gfp, &updated);
 		if (!pte) {
-			ret = -EINVAL;
+			ret = -ENOMEM;
 			goto out;
 		}
 
diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index 8364cd6fa47d..6a019670efc7 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -107,7 +107,9 @@ static inline int get_acpihid_device_id(struct device *dev,
 					struct acpihid_map_entry **entry)
 {
 	struct acpi_device *adev = ACPI_COMPANION(dev);
-	struct acpihid_map_entry *p;
+	struct acpihid_map_entry *p, *p1 = NULL;
+	int hid_count = 0;
+	bool fw_bug;
 
 	if (!adev)
 		return -ENODEV;
@@ -115,12 +117,33 @@ static inline int get_acpihid_device_id(struct device *dev,
 	list_for_each_entry(p, &acpihid_map, list) {
 		if (acpi_dev_hid_uid_match(adev, p->hid,
 					   p->uid[0] ? p->uid : NULL)) {
-			if (entry)
-				*entry = p;
-			return p->devid;
+			p1 = p;
+			fw_bug = false;
+			hid_count = 1;
+			break;
+		}
+
+		/*
+		 * Count HID matches w/o UID, raise FW_BUG but allow exactly one match
+		 */
+		if (acpi_dev_hid_match(adev, p->hid)) {
+			p1 = p;
+			hid_count++;
+			fw_bug = true;
 		}
 	}
-	return -EINVAL;
+
+	if (!p1)
+		return -EINVAL;
+	if (fw_bug)
+		dev_err_once(dev, FW_BUG "No ACPI device matched UID, but %d device%s matched HID.\n",
+			     hid_count, hid_count > 1 ? "s" : "");
+	if (hid_count > 1)
+		return -EINVAL;
+	if (entry)
+		*entry = p1;
+
+	return p1->devid;
 }
 
 static inline int get_device_sbdf_id(struct device *dev)
@@ -460,8 +483,8 @@ static inline void pdev_disable_cap_pasid(struct pci_dev *pdev)
 
 static void pdev_enable_caps(struct pci_dev *pdev)
 {
-	pdev_enable_cap_ats(pdev);
 	pdev_enable_cap_pasid(pdev);
+	pdev_enable_cap_ats(pdev);
 	pdev_enable_cap_pri(pdev);
 }
 
@@ -838,6 +861,14 @@ int amd_iommu_register_ga_log_notifier(int (*notifier)(u32))
 {
 	iommu_ga_log_notifier = notifier;
 
+	/*
+	 * Ensure all in-flight IRQ handlers run to completion before returning
+	 * to the caller, e.g. to ensure module code isn't unloaded while it's
+	 * being executed in the IRQ handler.
+	 */
+	if (!notifier)
+		synchronize_rcu();
+
 	return 0;
 }
 EXPORT_SYMBOL(amd_iommu_register_ga_log_notifier);
@@ -1606,15 +1637,6 @@ void amd_iommu_update_and_flush_device_table(struct protection_domain *domain)
 	domain_flush_complete(domain);
 }
 
-void amd_iommu_domain_update(struct protection_domain *domain)
-{
-	/* Update device table */
-	amd_iommu_update_and_flush_device_table(domain);
-
-	/* Flush domain TLB(s) and wait for completion */
-	amd_iommu_domain_flush_all(domain);
-}
-
 int amd_iommu_complete_ppr(struct device *dev, u32 pasid, int status, int tag)
 {
 	struct iommu_dev_data *dev_data;
@@ -2330,8 +2352,21 @@ static inline u64 dma_max_address(void)
 	if (amd_iommu_pgtable == AMD_IOMMU_V1)
 		return ~0ULL;
 
-	/* V2 with 4/5 level page table */
-	return ((1ULL << PM_LEVEL_SHIFT(amd_iommu_gpt_level)) - 1);
+	/*
+	 * V2 with 4/5 level page table. Note that "2.2.6.5 AMD64 4-Kbyte Page
+	 * Translation" shows that the V2 table sign extends the top of the
+	 * address space creating a reserved region in the middle of the
+	 * translation, just like the CPU does. Further Vasant says the docs are
+	 * incomplete and this only applies to non-zero PASIDs. If the AMDv2
+	 * page table is assigned to the 0 PASID then there is no sign extension
+	 * check.
+	 *
+	 * Since the IOMMU must have a fixed geometry, and the core code does
+	 * not understand sign extended addressing, we have to chop off the high
+	 * bit to get consistent behavior with attachments of the domain to any
+	 * PASID.
+	 */
+	return ((1ULL << (PM_LEVEL_SHIFT(amd_iommu_gpt_level) - 1)) - 1);
 }
 
 static bool amd_iommu_hd_support(struct amd_iommu *iommu)
@@ -3669,7 +3704,7 @@ static int amd_ir_set_vcpu_affinity(struct irq_data *data, void *vcpu_info)
 	 * we should not modify the IRTE
 	 */
 	if (!dev_data || !dev_data->use_vapic)
-		return 0;
+		return -EINVAL;
 
 	ir_data->cfg = irqd_cfg(data);
 	pi_data->ir_data = ir_data;
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
index a7c36654dee5..32f3e91a7d7f 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
@@ -397,6 +397,12 @@ struct iommu_domain *arm_smmu_sva_domain_alloc(struct device *dev,
 		return ERR_CAST(smmu_domain);
 	smmu_domain->domain.type = IOMMU_DOMAIN_SVA;
 	smmu_domain->domain.ops = &arm_smmu_sva_domain_ops;
+
+	/*
+	 * Choose page_size as the leaf page size for invalidation when
+	 * ARM_SMMU_FEAT_RANGE_INV is present
+	 */
+	smmu_domain->domain.pgsize_bitmap = PAGE_SIZE;
 	smmu_domain->smmu = smmu;
 
 	ret = xa_alloc(&arm_smmu_asid_xa, &asid, smmu_domain,
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
index 353fea58cd31..780e2d9e4ea8 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -2702,9 +2702,14 @@ static int arm_smmu_attach_prepare(struct arm_smmu_attach_state *state,
 		 * Translation Requests and Translated transactions are denied
 		 * as though ATS is disabled for the stream (STE.EATS == 0b00),
 		 * causing F_BAD_ATS_TREQ and F_TRANSL_FORBIDDEN events
-		 * (IHI0070Ea 5.2 Stream Table Entry). Thus ATS can only be
-		 * enabled if we have arm_smmu_domain, those always have page
-		 * tables.
+		 * (IHI0070Ea 5.2 Stream Table Entry).
+		 *
+		 * However, if we have installed a CD table and are using S1DSS
+		 * then ATS will work in S1DSS bypass. See "13.6.4 Full ATS
+		 * skipping stage 1".
+		 *
+		 * Disable ATS if we are going to create a normal 0b100 bypass
+		 * STE.
 		 */
 		state->ats_enabled = arm_smmu_ats_supported(master);
 	}
@@ -3017,8 +3022,10 @@ static void arm_smmu_attach_dev_ste(struct iommu_domain *domain,
 	if (arm_smmu_ssids_in_use(&master->cd_table)) {
 		/*
 		 * If a CD table has to be present then we need to run with ATS
-		 * on even though the RID will fail ATS queries with UR. This is
-		 * because we have no idea what the PASID's need.
+		 * on because we have to assume a PASID is using ATS. For
+		 * IDENTITY this will setup things so that S1DSS=bypass which
+		 * follows the explanation in "13.6.4 Full ATS skipping stage 1"
+		 * and allows for ATS on the RID to work.
 		 */
 		state.cd_needs_ats = true;
 		arm_smmu_attach_prepare(&state, domain);
@@ -3213,6 +3220,7 @@ static int arm_smmu_insert_master(struct arm_smmu_device *smmu,
 	mutex_lock(&smmu->streams_mutex);
 	for (i = 0; i < fwspec->num_ids; i++) {
 		struct arm_smmu_stream *new_stream = &master->streams[i];
+		struct rb_node *existing;
 		u32 sid = fwspec->ids[i];
 
 		new_stream->id = sid;
@@ -3223,10 +3231,20 @@ static int arm_smmu_insert_master(struct arm_smmu_device *smmu,
 			break;
 
 		/* Insert into SID tree */
-		if (rb_find_add(&new_stream->node, &smmu->streams,
-				arm_smmu_streams_cmp_node)) {
-			dev_warn(master->dev, "stream %u already in tree\n",
-				 sid);
+		existing = rb_find_add(&new_stream->node, &smmu->streams,
+				       arm_smmu_streams_cmp_node);
+		if (existing) {
+			struct arm_smmu_master *existing_master =
+				rb_entry(existing, struct arm_smmu_stream, node)
+					->master;
+
+			/* Bridged PCI devices may end up with duplicated IDs */
+			if (existing_master == master)
+				continue;
+
+			dev_warn(master->dev,
+				 "stream %u already in tree from dev %s\n", sid,
+				 dev_name(existing_master->dev));
 			ret = -EINVAL;
 			break;
 		}
@@ -4609,7 +4627,7 @@ static int arm_smmu_device_probe(struct platform_device *pdev)
 	/* Initialise in-memory data structures */
 	ret = arm_smmu_init_structures(smmu);
 	if (ret)
-		return ret;
+		goto err_free_iopf;
 
 	/* Record our private device structure */
 	platform_set_drvdata(pdev, smmu);
@@ -4620,22 +4638,29 @@ static int arm_smmu_device_probe(struct platform_device *pdev)
 	/* Reset the device */
 	ret = arm_smmu_device_reset(smmu);
 	if (ret)
-		return ret;
+		goto err_disable;
 
 	/* And we're up. Go go go! */
 	ret = iommu_device_sysfs_add(&smmu->iommu, dev, NULL,
 				     "smmu3.%pa", &ioaddr);
 	if (ret)
-		return ret;
+		goto err_disable;
 
 	ret = iommu_device_register(&smmu->iommu, &arm_smmu_ops, dev);
 	if (ret) {
 		dev_err(dev, "Failed to register iommu\n");
-		iommu_device_sysfs_remove(&smmu->iommu);
-		return ret;
+		goto err_free_sysfs;
 	}
 
 	return 0;
+
+err_free_sysfs:
+	iommu_device_sysfs_remove(&smmu->iommu);
+err_disable:
+	arm_smmu_device_disable(smmu);
+err_free_iopf:
+	iopf_queue_free(smmu->evtq.iopf);
+	return ret;
 }
 
 static void arm_smmu_device_remove(struct platform_device *pdev)
diff --git a/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c b/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c
index 6e41ddaa24d6..dd7d030d2e89 100644
--- a/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c
+++ b/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c
@@ -79,7 +79,6 @@
 #define TEGRA241_VCMDQ_PAGE1(q)		(TEGRA241_VCMDQ_PAGE1_BASE + 0x80*(q))
 #define  VCMDQ_ADDR			GENMASK(47, 5)
 #define  VCMDQ_LOG2SIZE			GENMASK(4, 0)
-#define  VCMDQ_LOG2SIZE_MAX		19
 
 #define TEGRA241_VCMDQ_BASE		0x00000
 #define TEGRA241_VCMDQ_CONS_INDX_BASE	0x00008
@@ -488,29 +487,21 @@ static int tegra241_cmdqv_hw_reset(struct arm_smmu_device *smmu)
 
 /* VCMDQ Resource Helpers */
 
-static void tegra241_vcmdq_free_smmu_cmdq(struct tegra241_vcmdq *vcmdq)
-{
-	struct arm_smmu_queue *q = &vcmdq->cmdq.q;
-	size_t nents = 1 << q->llq.max_n_shift;
-	size_t qsz = nents << CMDQ_ENT_SZ_SHIFT;
-
-	if (!q->base)
-		return;
-	dmam_free_coherent(vcmdq->cmdqv->smmu.dev, qsz, q->base, q->base_dma);
-}
-
 static int tegra241_vcmdq_alloc_smmu_cmdq(struct tegra241_vcmdq *vcmdq)
 {
 	struct arm_smmu_device *smmu = &vcmdq->cmdqv->smmu;
 	struct arm_smmu_cmdq *cmdq = &vcmdq->cmdq;
 	struct arm_smmu_queue *q = &cmdq->q;
 	char name[16];
+	u32 regval;
 	int ret;
 
 	snprintf(name, 16, "vcmdq%u", vcmdq->idx);
 
-	/* Queue size, capped to ensure natural alignment */
-	q->llq.max_n_shift = min_t(u32, CMDQ_MAX_SZ_SHIFT, VCMDQ_LOG2SIZE_MAX);
+	/* Cap queue size to SMMU's IDR1.CMDQS and ensure natural alignment */
+	regval = readl_relaxed(smmu->base + ARM_SMMU_IDR1);
+	q->llq.max_n_shift =
+		min_t(u32, CMDQ_MAX_SZ_SHIFT, FIELD_GET(IDR1_CMDQS, regval));
 
 	/* Use the common helper to init the VCMDQ, and then... */
 	ret = arm_smmu_init_one_queue(smmu, q, vcmdq->page0,
@@ -558,7 +549,8 @@ static void tegra241_vintf_free_lvcmdq(struct tegra241_vintf *vintf, u16 lidx)
 	struct tegra241_vcmdq *vcmdq = vintf->lvcmdqs[lidx];
 	char header[64];
 
-	tegra241_vcmdq_free_smmu_cmdq(vcmdq);
+	/* Note that the lvcmdq queue memory space is managed by devres */
+
 	tegra241_vintf_deinit_lvcmdq(vintf, lidx);
 
 	dev_dbg(vintf->cmdqv->dev,
@@ -766,13 +758,13 @@ static int tegra241_cmdqv_init_structures(struct arm_smmu_device *smmu)
 
 	vintf = kzalloc(sizeof(*vintf), GFP_KERNEL);
 	if (!vintf)
-		goto out_fallback;
+		return -ENOMEM;
 
 	/* Init VINTF0 for in-kernel use */
 	ret = tegra241_cmdqv_init_vintf(cmdqv, 0, vintf);
 	if (ret) {
 		dev_err(cmdqv->dev, "failed to init vintf0: %d\n", ret);
-		goto free_vintf;
+		return ret;
 	}
 
 	/* Preallocate logical VCMDQs to VINTF0 */
@@ -781,24 +773,12 @@ static int tegra241_cmdqv_init_structures(struct arm_smmu_device *smmu)
 
 		vcmdq = tegra241_vintf_alloc_lvcmdq(vintf, lidx);
 		if (IS_ERR(vcmdq))
-			goto free_lvcmdq;
+			return PTR_ERR(vcmdq);
 	}
 
 	/* Now, we are ready to run all the impl ops */
 	smmu->impl_ops = &tegra241_cmdqv_impl_ops;
 	return 0;
-
-free_lvcmdq:
-	for (lidx--; lidx >= 0; lidx--)
-		tegra241_vintf_free_lvcmdq(vintf, lidx);
-	tegra241_cmdqv_deinit_vintf(cmdqv, vintf->idx);
-free_vintf:
-	kfree(vintf);
-out_fallback:
-	dev_info(smmu->impl_dev, "Falling back to standard SMMU CMDQ\n");
-	smmu->options &= ~ARM_SMMU_OPT_TEGRA241_CMDQV;
-	tegra241_cmdqv_remove(smmu);
-	return 0;
 }
 
 #ifdef CONFIG_IOMMU_DEBUGFS
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
index 6372f3e25c4b..0c35a235ab6d 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
@@ -258,6 +258,7 @@ static const struct of_device_id qcom_smmu_client_of_match[] __maybe_unused = {
 	{ .compatible = "qcom,sdm670-mdss" },
 	{ .compatible = "qcom,sdm845-mdss" },
 	{ .compatible = "qcom,sdm845-mss-pil" },
+	{ .compatible = "qcom,sm6115-mdss" },
 	{ .compatible = "qcom,sm6350-mdss" },
 	{ .compatible = "qcom,sm6375-mdss" },
 	{ .compatible = "qcom,sm8150-mdss" },
@@ -567,6 +568,7 @@ static const struct of_device_id __maybe_unused qcom_smmu_impl_of_match[] = {
 	{ .compatible = "qcom,sc8180x-smmu-500", .data = &qcom_smmu_500_impl0_data },
 	{ .compatible = "qcom,sc8280xp-smmu-500", .data = &qcom_smmu_500_impl0_data },
 	{ .compatible = "qcom,sdm630-smmu-v2", .data = &qcom_smmu_v2_data },
+	{ .compatible = "qcom,sdm670-smmu-v2", .data = &qcom_smmu_v2_data },
 	{ .compatible = "qcom,sdm845-smmu-v2", .data = &qcom_smmu_v2_data },
 	{ .compatible = "qcom,sdm845-smmu-500", .data = &sdm845_smmu_500_data },
 	{ .compatible = "qcom,sm6115-smmu-500", .data = &qcom_smmu_500_impl0_data},
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 2a9fa0c8cc00..0f0caf59023c 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -1815,7 +1815,7 @@ int iommu_dma_prepare_msi(struct msi_desc *desc, phys_addr_t msi_addr)
 	static DEFINE_MUTEX(msi_prepare_lock); /* see below */
 
 	if (!domain || !domain->iova_cookie) {
-		desc->iommu_cookie = NULL;
+		msi_desc_set_iommu_msi_iova(desc, 0, 0);
 		return 0;
 	}
 
@@ -1827,11 +1827,12 @@ int iommu_dma_prepare_msi(struct msi_desc *desc, phys_addr_t msi_addr)
 	mutex_lock(&msi_prepare_lock);
 	msi_page = iommu_dma_get_msi_page(dev, msi_addr, domain);
 	mutex_unlock(&msi_prepare_lock);
-
-	msi_desc_set_iommu_cookie(desc, msi_page);
-
 	if (!msi_page)
 		return -ENOMEM;
+
+	msi_desc_set_iommu_msi_iova(
+		desc, msi_page->iova,
+		ilog2(cookie_msi_granule(domain->iova_cookie)));
 	return 0;
 }
 
@@ -1842,18 +1843,15 @@ int iommu_dma_prepare_msi(struct msi_desc *desc, phys_addr_t msi_addr)
  */
 void iommu_dma_compose_msi_msg(struct msi_desc *desc, struct msi_msg *msg)
 {
-	struct device *dev = msi_desc_to_dev(desc);
-	const struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
-	const struct iommu_dma_msi_page *msi_page;
+#ifdef CONFIG_IRQ_MSI_IOMMU
+	if (desc->iommu_msi_shift) {
+		u64 msi_iova = desc->iommu_msi_iova << desc->iommu_msi_shift;
 
-	msi_page = msi_desc_get_iommu_cookie(desc);
-
-	if (!domain || !domain->iova_cookie || WARN_ON(!msi_page))
-		return;
-
-	msg->address_hi = upper_32_bits(msi_page->iova);
-	msg->address_lo &= cookie_msi_granule(domain->iova_cookie) - 1;
-	msg->address_lo += lower_32_bits(msi_page->iova);
+		msg->address_hi = upper_32_bits(msi_iova);
+		msg->address_lo = lower_32_bits(msi_iova) |
+				  (msg->address_lo & ((1 << desc->iommu_msi_shift) - 1));
+	}
+#endif
 }
 
 static int iommu_dma_init(void)
diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c
index c666ecab955d..7465dbb6fa80 100644
--- a/drivers/iommu/exynos-iommu.c
+++ b/drivers/iommu/exynos-iommu.c
@@ -832,7 +832,7 @@ static int __maybe_unused exynos_sysmmu_suspend(struct device *dev)
 		struct exynos_iommu_owner *owner = dev_iommu_priv_get(master);
 
 		mutex_lock(&owner->rpm_lock);
-		if (&data->domain->domain != &exynos_identity_domain) {
+		if (data->domain) {
 			dev_dbg(data->sysmmu, "saving state\n");
 			__sysmmu_disable(data);
 		}
@@ -850,7 +850,7 @@ static int __maybe_unused exynos_sysmmu_resume(struct device *dev)
 		struct exynos_iommu_owner *owner = dev_iommu_priv_get(master);
 
 		mutex_lock(&owner->rpm_lock);
-		if (&data->domain->domain != &exynos_identity_domain) {
+		if (data->domain) {
 			dev_dbg(data->sysmmu, "restoring state\n");
 			__sysmmu_enable(data);
 		}
diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c
index eaf862e8dea1..7f553f7aa3cb 100644
--- a/drivers/iommu/intel/dmar.c
+++ b/drivers/iommu/intel/dmar.c
@@ -2056,6 +2056,7 @@ int enable_drhd_fault_handling(unsigned int cpu)
 	/*
 	 * Enable fault control interrupt.
 	 */
+	guard(rwsem_read)(&dmar_global_lock);
 	for_each_iommu(iommu, drhd) {
 		u32 fault_status;
 		int ret;
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index cc23cfcdeb2d..b300f72cf01e 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -1957,6 +1957,18 @@ static bool dev_is_real_dma_subdevice(struct device *dev)
 	       pci_real_dma_dev(to_pci_dev(dev)) != to_pci_dev(dev);
 }
 
+static bool domain_need_iotlb_sync_map(struct dmar_domain *domain,
+				       struct intel_iommu *iommu)
+{
+	if (cap_caching_mode(iommu->cap) && !domain->use_first_level)
+		return true;
+
+	if (rwbf_quirk || cap_rwbf(iommu->cap))
+		return true;
+
+	return false;
+}
+
 static int dmar_domain_attach_device(struct dmar_domain *domain,
 				     struct device *dev)
 {
@@ -1970,6 +1982,7 @@ static int dmar_domain_attach_device(struct dmar_domain *domain,
 		return ret;
 
 	info->domain = domain;
+	info->domain_attached = true;
 	spin_lock_irqsave(&domain->lock, flags);
 	list_add(&info->link, &domain->devices);
 	spin_unlock_irqrestore(&domain->lock, flags);
@@ -1993,6 +2006,8 @@ static int dmar_domain_attach_device(struct dmar_domain *domain,
 	if (ret)
 		goto out_block_translation;
 
+	domain->iotlb_sync_map |= domain_need_iotlb_sync_map(domain, iommu);
+
 	return 0;
 
 out_block_translation:
@@ -3174,6 +3189,7 @@ static int __init probe_acpi_namespace_devices(void)
 			if (dev->bus != &acpi_bus_type)
 				continue;
 
+			up_read(&dmar_global_lock);
 			adev = to_acpi_device(dev);
 			mutex_lock(&adev->physical_node_lock);
 			list_for_each_entry(pn,
@@ -3183,6 +3199,7 @@ static int __init probe_acpi_namespace_devices(void)
 					break;
 			}
 			mutex_unlock(&adev->physical_node_lock);
+			down_read(&dmar_global_lock);
 
 			if (ret)
 				return ret;
@@ -3307,7 +3324,14 @@ int __init intel_iommu_init(void)
 		iommu_device_sysfs_add(&iommu->iommu, NULL,
 				       intel_iommu_groups,
 				       "%s", iommu->name);
+		/*
+		 * The iommu device probe is protected by the iommu_probe_device_lock.
+		 * Release the dmar_global_lock before entering the device probe path
+		 * to avoid unnecessary lock order splat.
+		 */
+		up_read(&dmar_global_lock);
 		iommu_device_register(&iommu->iommu, &intel_iommu_ops, NULL);
+		down_read(&dmar_global_lock);
 
 		iommu_pmu_register(iommu);
 	}
@@ -3372,6 +3396,10 @@ void device_block_translation(struct device *dev)
 	struct intel_iommu *iommu = info->iommu;
 	unsigned long flags;
 
+	/* Device in DMA blocking state. Noting to do. */
+	if (!info->domain_attached)
+		return;
+
 	if (info->domain)
 		cache_tag_unassign_domain(info->domain, dev, IOMMU_NO_PASID);
 
@@ -3384,6 +3412,9 @@ void device_block_translation(struct device *dev)
 			domain_context_clear(info);
 	}
 
+	/* Device now in DMA blocking state. */
+	info->domain_attached = false;
+
 	if (!info->domain)
 		return;
 
@@ -4261,7 +4292,10 @@ static bool risky_device(struct pci_dev *pdev)
 static int intel_iommu_iotlb_sync_map(struct iommu_domain *domain,
 				      unsigned long iova, size_t size)
 {
-	cache_tag_flush_range_np(to_dmar_domain(domain), iova, iova + size - 1);
+	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
+
+	if (dmar_domain->iotlb_sync_map)
+		cache_tag_flush_range_np(dmar_domain, iova, iova + size - 1);
 
 	return 0;
 }
@@ -4547,9 +4581,6 @@ static int context_setup_pass_through_cb(struct pci_dev *pdev, u16 alias, void *
 {
 	struct device *dev = data;
 
-	if (dev != &pdev->dev)
-		return 0;
-
 	return context_setup_pass_through(dev, PCI_BUS_NUM(alias), alias & 0xff);
 }
 
@@ -4583,6 +4614,9 @@ static int identity_domain_attach_dev(struct iommu_domain *domain, struct device
 		ret = device_setup_pass_through(dev);
 	}
 
+	if (!ret)
+		info->domain_attached = true;
+
 	return ret;
 }
 
@@ -4660,6 +4694,9 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e30, quirk_iommu_igfx);
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e40, quirk_iommu_igfx);
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e90, quirk_iommu_igfx);
 
+/* QM57/QS57 integrated gfx malfunctions with dmar */
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x0044, quirk_iommu_igfx);
+
 /* Broadwell igfx malfunctions with dmar */
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x1606, quirk_iommu_igfx);
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x160B, quirk_iommu_igfx);
@@ -4737,7 +4774,6 @@ static void quirk_calpella_no_shadow_gtt(struct pci_dev *dev)
 	}
 }
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x0040, quirk_calpella_no_shadow_gtt);
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x0044, quirk_calpella_no_shadow_gtt);
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x0062, quirk_calpella_no_shadow_gtt);
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x006a, quirk_calpella_no_shadow_gtt);
 
diff --git a/drivers/iommu/intel/iommu.h b/drivers/iommu/intel/iommu.h
index 1497f3112b12..f521155fb793 100644
--- a/drivers/iommu/intel/iommu.h
+++ b/drivers/iommu/intel/iommu.h
@@ -614,6 +614,9 @@ struct dmar_domain {
 	u8 has_mappings:1;		/* Has mappings configured through
 					 * iommu_map() interface.
 					 */
+	u8 iotlb_sync_map:1;		/* Need to flush IOTLB cache or write
+					 * buffer when creating mappings.
+					 */
 
 	spinlock_t lock;		/* Protect device tracking lists */
 	struct list_head devices;	/* all devices' list */
@@ -776,6 +779,7 @@ struct device_domain_info {
 	u8 ats_supported:1;
 	u8 ats_enabled:1;
 	u8 dtlb_extra_inval:1;	/* Quirk for devices need extra flush */
+	u8 domain_attached:1;	/* Device has domain attached */
 	u8 ats_qdep;
 	struct device *dev; /* it's NULL for PCIe-to-PCI bridge */
 	struct intel_iommu *iommu; /* IOMMU used by this device */
diff --git a/drivers/iommu/intel/irq_remapping.c b/drivers/iommu/intel/irq_remapping.c
index 7a6d188e3bea..71b3383b7115 100644
--- a/drivers/iommu/intel/irq_remapping.c
+++ b/drivers/iommu/intel/irq_remapping.c
@@ -26,11 +26,6 @@
 #include "../iommu-pages.h"
 #include "cap_audit.h"
 
-enum irq_mode {
-	IRQ_REMAPPING,
-	IRQ_POSTING,
-};
-
 struct ioapic_scope {
 	struct intel_iommu *iommu;
 	unsigned int id;
@@ -50,8 +45,8 @@ struct irq_2_iommu {
 	u16 irte_index;
 	u16 sub_handle;
 	u8  irte_mask;
-	enum irq_mode mode;
 	bool posted_msi;
+	bool posted_vcpu;
 };
 
 struct intel_ir_data {
@@ -139,7 +134,6 @@ static int alloc_irte(struct intel_iommu *iommu,
 		irq_iommu->irte_index =  index;
 		irq_iommu->sub_handle = 0;
 		irq_iommu->irte_mask = mask;
-		irq_iommu->mode = IRQ_REMAPPING;
 	}
 	raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);
 
@@ -194,8 +188,6 @@ static int modify_irte(struct irq_2_iommu *irq_iommu,
 
 	rc = qi_flush_iec(iommu, index, 0);
 
-	/* Update iommu mode according to the IRTE mode */
-	irq_iommu->mode = irte->pst ? IRQ_POSTING : IRQ_REMAPPING;
 	raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);
 
 	return rc;
@@ -1173,7 +1165,26 @@ static void intel_ir_reconfigure_irte_posted(struct irq_data *irqd)
 static inline void intel_ir_reconfigure_irte_posted(struct irq_data *irqd) {}
 #endif
 
-static void intel_ir_reconfigure_irte(struct irq_data *irqd, bool force)
+static void __intel_ir_reconfigure_irte(struct irq_data *irqd, bool force_host)
+{
+	struct intel_ir_data *ir_data = irqd->chip_data;
+
+	/*
+	 * Don't modify IRTEs for IRQs that are being posted to vCPUs if the
+	 * host CPU affinity changes.
+	 */
+	if (ir_data->irq_2_iommu.posted_vcpu && !force_host)
+		return;
+
+	ir_data->irq_2_iommu.posted_vcpu = false;
+
+	if (ir_data->irq_2_iommu.posted_msi)
+		intel_ir_reconfigure_irte_posted(irqd);
+	else
+		modify_irte(&ir_data->irq_2_iommu, &ir_data->irte_entry);
+}
+
+static void intel_ir_reconfigure_irte(struct irq_data *irqd, bool force_host)
 {
 	struct intel_ir_data *ir_data = irqd->chip_data;
 	struct irte *irte = &ir_data->irte_entry;
@@ -1186,10 +1197,7 @@ static void intel_ir_reconfigure_irte(struct irq_data *irqd, bool force)
 	irte->vector = cfg->vector;
 	irte->dest_id = IRTE_DEST(cfg->dest_apicid);
 
-	if (ir_data->irq_2_iommu.posted_msi)
-		intel_ir_reconfigure_irte_posted(irqd);
-	else if (force || ir_data->irq_2_iommu.mode == IRQ_REMAPPING)
-		modify_irte(&ir_data->irq_2_iommu, irte);
+	__intel_ir_reconfigure_irte(irqd, force_host);
 }
 
 /*
@@ -1244,7 +1252,7 @@ static int intel_ir_set_vcpu_affinity(struct irq_data *data, void *info)
 
 	/* stop posting interrupts, back to the default mode */
 	if (!vcpu_pi_info) {
-		modify_irte(&ir_data->irq_2_iommu, &ir_data->irte_entry);
+		__intel_ir_reconfigure_irte(data, true);
 	} else {
 		struct irte irte_pi;
 
@@ -1267,6 +1275,7 @@ static int intel_ir_set_vcpu_affinity(struct irq_data *data, void *info)
 		irte_pi.pda_h = (vcpu_pi_info->pi_desc_addr >> 32) &
 				~(-1UL << PDA_HIGH_BIT);
 
+		ir_data->irq_2_iommu.posted_vcpu = true;
 		modify_irte(&ir_data->irq_2_iommu, &irte_pi);
 	}
 
@@ -1282,43 +1291,44 @@ static struct irq_chip intel_ir_chip = {
 };
 
 /*
- * With posted MSIs, all vectors are multiplexed into a single notification
- * vector. Devices MSIs are then dispatched in a demux loop where
- * EOIs can be coalesced as well.
+ * With posted MSIs, the MSI vectors are multiplexed into a single notification
+ * vector, and only the notification vector is sent to the APIC IRR.  Device
+ * MSIs are then dispatched in a demux loop that harvests the MSIs from the
+ * CPU's Posted Interrupt Request bitmap.  I.e. Posted MSIs never get sent to
+ * the APIC IRR, and thus do not need an EOI.  The notification handler instead
+ * performs a single EOI after processing the PIR.
  *
- * "INTEL-IR-POST" IRQ chip does not do EOI on ACK, thus the dummy irq_ack()
- * function. Instead EOI is performed by the posted interrupt notification
- * handler.
+ * Note!  Pending SMP/CPU affinity changes, which are per MSI, must still be
+ * honored, only the APIC EOI is omitted.
  *
  * For the example below, 3 MSIs are coalesced into one CPU notification. Only
- * one apic_eoi() is needed.
+ * one apic_eoi() is needed, but each MSI needs to process pending changes to
+ * its CPU affinity.
  *
  * __sysvec_posted_msi_notification()
  *	irq_enter();
  *		handle_edge_irq()
  *			irq_chip_ack_parent()
- *				dummy(); // No EOI
+ *				irq_move_irq(); // No EOI
  *			handle_irq_event()
  *				driver_handler()
  *		handle_edge_irq()
  *			irq_chip_ack_parent()
- *				dummy(); // No EOI
+ *				irq_move_irq(); // No EOI
  *			handle_irq_event()
  *				driver_handler()
  *		handle_edge_irq()
  *			irq_chip_ack_parent()
- *				dummy(); // No EOI
+ *				irq_move_irq(); // No EOI
  *			handle_irq_event()
  *				driver_handler()
  *	apic_eoi()
  *	irq_exit()
+ *
  */
-
-static void dummy_ack(struct irq_data *d) { }
-
 static struct irq_chip intel_ir_chip_post_msi = {
 	.name			= "INTEL-IR-POST",
-	.irq_ack		= dummy_ack,
+	.irq_ack		= irq_move_irq,
 	.irq_set_affinity	= intel_ir_set_affinity,
 	.irq_compose_msi_msg	= intel_ir_compose_msi_msg,
 	.irq_set_vcpu_affinity	= intel_ir_set_vcpu_affinity,
@@ -1494,6 +1504,9 @@ static void intel_irq_remapping_deactivate(struct irq_domain *domain,
 	struct intel_ir_data *data = irq_data->chip_data;
 	struct irte entry;
 
+	WARN_ON_ONCE(data->irq_2_iommu.posted_vcpu);
+	data->irq_2_iommu.posted_vcpu = false;
+
 	memset(&entry, 0, sizeof(entry));
 	modify_irte(&data->irq_2_iommu, &entry);
 }
diff --git a/drivers/iommu/intel/nested.c b/drivers/iommu/intel/nested.c
index 433c58944401..3b5251034a87 100644
--- a/drivers/iommu/intel/nested.c
+++ b/drivers/iommu/intel/nested.c
@@ -27,8 +27,7 @@ static int intel_nested_attach_dev(struct iommu_domain *domain,
 	unsigned long flags;
 	int ret = 0;
 
-	if (info->domain)
-		device_block_translation(dev);
+	device_block_translation(dev);
 
 	if (iommu->agaw < dmar_domain->s2_domain->agaw) {
 		dev_err_ratelimited(dev, "Adjusted guest address width not compatible\n");
@@ -62,6 +61,7 @@ static int intel_nested_attach_dev(struct iommu_domain *domain,
 		goto unassign_tag;
 
 	info->domain = dmar_domain;
+	info->domain_attached = true;
 	spin_lock_irqsave(&dmar_domain->lock, flags);
 	list_add(&info->link, &dmar_domain->devices);
 	spin_unlock_irqrestore(&dmar_domain->lock, flags);
diff --git a/drivers/iommu/io-pgfault.c b/drivers/iommu/io-pgfault.c
index 4674e618797c..8b5926c1452e 100644
--- a/drivers/iommu/io-pgfault.c
+++ b/drivers/iommu/io-pgfault.c
@@ -478,6 +478,7 @@ void iopf_queue_remove_device(struct iopf_queue *queue, struct device *dev)
 
 		ops->page_response(dev, iopf, &resp);
 		list_del_init(&group->pending_node);
+		iopf_free_group(group);
 	}
 	mutex_unlock(&fault_param->lock);
 
diff --git a/drivers/iommu/iommu-priv.h b/drivers/iommu/iommu-priv.h
index de5b54eaa8bf..a5913c0b02a0 100644
--- a/drivers/iommu/iommu-priv.h
+++ b/drivers/iommu/iommu-priv.h
@@ -17,6 +17,8 @@ static inline const struct iommu_ops *dev_iommu_ops(struct device *dev)
 	return dev->iommu->iommu_dev->ops;
 }
 
+void dev_iommu_free(struct device *dev);
+
 const struct iommu_ops *iommu_ops_from_fwnode(const struct fwnode_handle *fwnode);
 
 static inline const struct iommu_ops *iommu_fwspec_ops(struct iommu_fwspec *fwspec)
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 83c8e617a2c5..0ad55649e2d0 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -347,7 +347,7 @@ static struct dev_iommu *dev_iommu_get(struct device *dev)
 	return param;
 }
 
-static void dev_iommu_free(struct device *dev)
+void dev_iommu_free(struct device *dev)
 {
 	struct dev_iommu *param = dev->iommu;
 
@@ -503,6 +503,9 @@ static void iommu_deinit_device(struct device *dev)
 	dev->iommu_group = NULL;
 	module_put(ops->owner);
 	dev_iommu_free(dev);
+#ifdef CONFIG_IOMMU_DMA
+	dev->dma_iommu = false;
+#endif
 }
 
 DEFINE_MUTEX(iommu_probe_device_lock);
@@ -2391,6 +2394,7 @@ static size_t iommu_pgsize(struct iommu_domain *domain, unsigned long iova,
 	unsigned int pgsize_idx, pgsize_idx_next;
 	unsigned long pgsizes;
 	size_t offset, pgsize, pgsize_next;
+	size_t offset_end;
 	unsigned long addr_merge = paddr | iova;
 
 	/* Page sizes supported by the hardware and small enough for @size */
@@ -2431,7 +2435,8 @@ static size_t iommu_pgsize(struct iommu_domain *domain, unsigned long iova,
 	 * If size is big enough to accommodate the larger page, reduce
 	 * the number of smaller pages.
 	 */
-	if (offset + pgsize_next <= size)
+	if (!check_add_overflow(offset, pgsize_next, &offset_end) &&
+	    offset_end <= size)
 		size = offset;
 
 out_set_count:
@@ -3112,6 +3117,11 @@ int iommu_device_use_default_domain(struct device *dev)
 		return 0;
 
 	mutex_lock(&group->mutex);
+	/* We may race against bus_iommu_probe() finalising groups here */
+	if (!group->default_domain) {
+		ret = -EPROBE_DEFER;
+		goto unlock_out;
+	}
 	if (group->owner_cnt) {
 		if (group->domain != group->default_domain || group->owner ||
 		    !xa_empty(&group->pasid_array)) {
diff --git a/drivers/iommu/iommufd/device.c b/drivers/iommu/iommufd/device.c
index 5fd3dd420290..74480ae6bfc0 100644
--- a/drivers/iommu/iommufd/device.c
+++ b/drivers/iommu/iommufd/device.c
@@ -3,6 +3,7 @@
  */
 #include <linux/iommu.h>
 #include <linux/iommufd.h>
+#include <linux/pci-ats.h>
 #include <linux/slab.h>
 #include <uapi/linux/iommufd.h>
 
@@ -352,6 +353,122 @@ iommufd_device_attach_reserved_iova(struct iommufd_device *idev,
 	return 0;
 }
 
+/* The device attach/detach/replace helpers for attach_handle */
+
+/* Check if idev is attached to igroup->hwpt */
+static bool iommufd_device_is_attached(struct iommufd_device *idev)
+{
+	struct iommufd_device *cur;
+
+	list_for_each_entry(cur, &idev->igroup->device_list, group_item)
+		if (cur == idev)
+			return true;
+	return false;
+}
+
+static int iommufd_hwpt_attach_device(struct iommufd_hw_pagetable *hwpt,
+				      struct iommufd_device *idev)
+{
+	struct iommufd_attach_handle *handle;
+	int rc;
+
+	lockdep_assert_held(&idev->igroup->lock);
+
+	handle = kzalloc(sizeof(*handle), GFP_KERNEL);
+	if (!handle)
+		return -ENOMEM;
+
+	if (hwpt->fault) {
+		rc = iommufd_fault_iopf_enable(idev);
+		if (rc)
+			goto out_free_handle;
+	}
+
+	handle->idev = idev;
+	rc = iommu_attach_group_handle(hwpt->domain, idev->igroup->group,
+				       &handle->handle);
+	if (rc)
+		goto out_disable_iopf;
+
+	return 0;
+
+out_disable_iopf:
+	if (hwpt->fault)
+		iommufd_fault_iopf_disable(idev);
+out_free_handle:
+	kfree(handle);
+	return rc;
+}
+
+static struct iommufd_attach_handle *
+iommufd_device_get_attach_handle(struct iommufd_device *idev)
+{
+	struct iommu_attach_handle *handle;
+
+	lockdep_assert_held(&idev->igroup->lock);
+
+	handle =
+		iommu_attach_handle_get(idev->igroup->group, IOMMU_NO_PASID, 0);
+	if (IS_ERR(handle))
+		return NULL;
+	return to_iommufd_handle(handle);
+}
+
+static void iommufd_hwpt_detach_device(struct iommufd_hw_pagetable *hwpt,
+				       struct iommufd_device *idev)
+{
+	struct iommufd_attach_handle *handle;
+
+	handle = iommufd_device_get_attach_handle(idev);
+	iommu_detach_group_handle(hwpt->domain, idev->igroup->group);
+	if (hwpt->fault) {
+		iommufd_auto_response_faults(hwpt, handle);
+		iommufd_fault_iopf_disable(idev);
+	}
+	kfree(handle);
+}
+
+static int iommufd_hwpt_replace_device(struct iommufd_device *idev,
+				       struct iommufd_hw_pagetable *hwpt,
+				       struct iommufd_hw_pagetable *old)
+{
+	struct iommufd_attach_handle *handle, *old_handle =
+		iommufd_device_get_attach_handle(idev);
+	int rc;
+
+	handle = kzalloc(sizeof(*handle), GFP_KERNEL);
+	if (!handle)
+		return -ENOMEM;
+
+	if (hwpt->fault && !old->fault) {
+		rc = iommufd_fault_iopf_enable(idev);
+		if (rc)
+			goto out_free_handle;
+	}
+
+	handle->idev = idev;
+	rc = iommu_replace_group_handle(idev->igroup->group, hwpt->domain,
+					&handle->handle);
+	if (rc)
+		goto out_disable_iopf;
+
+	if (old->fault) {
+		iommufd_auto_response_faults(hwpt, old_handle);
+		if (!hwpt->fault)
+			iommufd_fault_iopf_disable(idev);
+	}
+	kfree(old_handle);
+
+	return 0;
+
+out_disable_iopf:
+	if (hwpt->fault && !old->fault)
+		iommufd_fault_iopf_disable(idev);
+out_free_handle:
+	kfree(handle);
+	return rc;
+}
+
 int iommufd_hw_pagetable_attach(struct iommufd_hw_pagetable *hwpt,
 				struct iommufd_device *idev)
 {
@@ -488,6 +605,11 @@ iommufd_device_do_replace(struct iommufd_device *idev,
 		goto err_unlock;
 	}
 
+	if (!iommufd_device_is_attached(idev)) {
+		rc = -EINVAL;
+		goto err_unlock;
+	}
+
 	if (hwpt == igroup->hwpt) {
 		mutex_unlock(&idev->igroup->lock);
 		return NULL;
@@ -1127,7 +1249,7 @@ int iommufd_access_rw(struct iommufd_access *access, unsigned long iova,
 	struct io_pagetable *iopt;
 	struct iopt_area *area;
 	unsigned long last_iova;
-	int rc;
+	int rc = -EINVAL;
 
 	if (!length)
 		return -EINVAL;
@@ -1183,7 +1305,8 @@ int iommufd_get_hw_info(struct iommufd_ucmd *ucmd)
 	void *data;
 	int rc;
 
-	if (cmd->flags || cmd->__reserved)
+	if (cmd->flags || cmd->__reserved[0] || cmd->__reserved[1] ||
+	    cmd->__reserved[2])
 		return -EOPNOTSUPP;
 
 	idev = iommufd_get_device(ucmd, cmd->dev_id);
@@ -1240,6 +1363,36 @@ int iommufd_get_hw_info(struct iommufd_ucmd *ucmd)
 	if (device_iommu_capable(idev->dev, IOMMU_CAP_DIRTY_TRACKING))
 		cmd->out_capabilities |= IOMMU_HW_CAP_DIRTY_TRACKING;
 
+	cmd->out_max_pasid_log2 = 0;
+	/*
+	 * Currently, all iommu drivers enable PASID in the probe_device()
+	 * op if iommu and device supports it. So the max_pasids stored in
+	 * dev->iommu indicates both PASID support and enable status. A
+	 * non-zero dev->iommu->max_pasids means PASID is supported and
+	 * enabled. The iommufd only reports PASID capability to userspace
+	 * if it's enabled.
+	 */
+	if (idev->dev->iommu->max_pasids) {
+		cmd->out_max_pasid_log2 = ilog2(idev->dev->iommu->max_pasids);
+
+		if (dev_is_pci(idev->dev)) {
+			struct pci_dev *pdev = to_pci_dev(idev->dev);
+			int ctrl;
+
+			ctrl = pci_pasid_status(pdev);
+
+			WARN_ON_ONCE(ctrl < 0 ||
+				     !(ctrl & PCI_PASID_CTRL_ENABLE));
+
+			if (ctrl & PCI_PASID_CTRL_EXEC)
+				cmd->out_capabilities |=
+						IOMMU_HW_CAP_PCI_PASID_EXEC;
+			if (ctrl & PCI_PASID_CTRL_PRIV)
+				cmd->out_capabilities |=
+						IOMMU_HW_CAP_PCI_PASID_PRIV;
+		}
+	}
+
 	rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd));
 out_free:
 	kfree(data);
diff --git a/drivers/iommu/iommufd/fault.c b/drivers/iommu/iommufd/fault.c
index b8393a8c0753..1b0812f8bf84 100644
--- a/drivers/iommu/iommufd/fault.c
+++ b/drivers/iommu/iommufd/fault.c
@@ -16,7 +16,7 @@
 #include "../iommu-priv.h"
 #include "iommufd_private.h"
 
-static int iommufd_fault_iopf_enable(struct iommufd_device *idev)
+int iommufd_fault_iopf_enable(struct iommufd_device *idev)
 {
 	struct device *dev = idev->dev;
 	int ret;
@@ -45,7 +45,7 @@ static int iommufd_fault_iopf_enable(struct iommufd_device *idev)
 	return ret;
 }
 
-static void iommufd_fault_iopf_disable(struct iommufd_device *idev)
+void iommufd_fault_iopf_disable(struct iommufd_device *idev)
 {
 	mutex_lock(&idev->iopf_lock);
 	if (!WARN_ON(idev->iopf_enabled == 0)) {
@@ -93,20 +93,28 @@ int iommufd_fault_domain_attach_dev(struct iommufd_hw_pagetable *hwpt,
 	return ret;
 }
 
-static void iommufd_auto_response_faults(struct iommufd_hw_pagetable *hwpt,
-					 struct iommufd_attach_handle *handle)
+void iommufd_auto_response_faults(struct iommufd_hw_pagetable *hwpt,
+				  struct iommufd_attach_handle *handle)
 {
 	struct iommufd_fault *fault = hwpt->fault;
 	struct iopf_group *group, *next;
+	struct list_head free_list;
 	unsigned long index;
 
 	if (!fault)
 		return;
+	INIT_LIST_HEAD(&free_list);
 
 	mutex_lock(&fault->mutex);
+	spin_lock(&fault->lock);
 	list_for_each_entry_safe(group, next, &fault->deliver, node) {
 		if (group->attach_handle != &handle->handle)
 			continue;
+		list_move(&group->node, &free_list);
+	}
+	spin_unlock(&fault->lock);
+
+	list_for_each_entry_safe(group, next, &free_list, node) {
 		list_del(&group->node);
 		iopf_group_response(group, IOMMU_PAGE_RESP_INVALID);
 		iopf_free_group(group);
@@ -208,6 +216,7 @@ void iommufd_fault_destroy(struct iommufd_object *obj)
 {
 	struct iommufd_fault *fault = container_of(obj, struct iommufd_fault, obj);
 	struct iopf_group *group, *next;
+	unsigned long index;
 
 	/*
 	 * The iommufd object's reference count is zero at this point.
@@ -220,6 +229,13 @@ void iommufd_fault_destroy(struct iommufd_object *obj)
 		iopf_group_response(group, IOMMU_PAGE_RESP_INVALID);
 		iopf_free_group(group);
 	}
+	xa_for_each(&fault->response, index, group) {
+		xa_erase(&fault->response, index);
+		iopf_group_response(group, IOMMU_PAGE_RESP_INVALID);
+		iopf_free_group(group);
+	}
+	xa_destroy(&fault->response);
+	mutex_destroy(&fault->mutex);
 }
 
 static void iommufd_compose_fault_message(struct iommu_fault *fault,
@@ -242,7 +258,7 @@ static ssize_t iommufd_fault_fops_read(struct file *filep, char __user *buf,
 {
 	size_t fault_size = sizeof(struct iommu_hwpt_pgfault);
 	struct iommufd_fault *fault = filep->private_data;
-	struct iommu_hwpt_pgfault data;
+	struct iommu_hwpt_pgfault data = {};
 	struct iommufd_device *idev;
 	struct iopf_group *group;
 	struct iopf_fault *iopf;
@@ -253,17 +269,19 @@ static ssize_t iommufd_fault_fops_read(struct file *filep, char __user *buf,
 		return -ESPIPE;
 
 	mutex_lock(&fault->mutex);
-	while (!list_empty(&fault->deliver) && count > done) {
-		group = list_first_entry(&fault->deliver,
-					 struct iopf_group, node);
-
-		if (group->fault_count * fault_size > count - done)
+	while ((group = iommufd_fault_deliver_fetch(fault))) {
+		if (done >= count ||
+		    group->fault_count * fault_size > count - done) {
+			iommufd_fault_deliver_restore(fault, group);
 			break;
+		}
 
 		rc = xa_alloc(&fault->response, &group->cookie, group,
 			      xa_limit_32b, GFP_KERNEL);
-		if (rc)
+		if (rc) {
+			iommufd_fault_deliver_restore(fault, group);
 			break;
+		}
 
 		idev = to_iommufd_handle(group->attach_handle)->idev;
 		list_for_each_entry(iopf, &group->faults, list) {
@@ -272,13 +290,12 @@ static ssize_t iommufd_fault_fops_read(struct file *filep, char __user *buf,
 						      group->cookie);
 			if (copy_to_user(buf + done, &data, fault_size)) {
 				xa_erase(&fault->response, group->cookie);
+				iommufd_fault_deliver_restore(fault, group);
 				rc = -EFAULT;
 				break;
 			}
 			done += fault_size;
 		}
-
-		list_del(&group->node);
 	}
 	mutex_unlock(&fault->mutex);
 
@@ -336,10 +353,10 @@ static __poll_t iommufd_fault_fops_poll(struct file *filep,
 	__poll_t pollflags = EPOLLOUT;
 
 	poll_wait(filep, &fault->wait_queue, wait);
-	mutex_lock(&fault->mutex);
+	spin_lock(&fault->lock);
 	if (!list_empty(&fault->deliver))
 		pollflags |= EPOLLIN | EPOLLRDNORM;
-	mutex_unlock(&fault->mutex);
+	spin_unlock(&fault->lock);
 
 	return pollflags;
 }
@@ -381,6 +398,7 @@ int iommufd_fault_alloc(struct iommufd_ucmd *ucmd)
 	INIT_LIST_HEAD(&fault->deliver);
 	xa_init_flags(&fault->response, XA_FLAGS_ALLOC1);
 	mutex_init(&fault->mutex);
+	spin_lock_init(&fault->lock);
 	init_waitqueue_head(&fault->wait_queue);
 
 	filep = anon_inode_getfile("[iommufd-pgfault]", &iommufd_fault_fops,
@@ -429,9 +447,9 @@ int iommufd_fault_iopf_handler(struct iopf_group *group)
 	hwpt = group->attach_handle->domain->fault_data;
 	fault = hwpt->fault;
 
-	mutex_lock(&fault->mutex);
+	spin_lock(&fault->lock);
 	list_add_tail(&group->node, &fault->deliver);
-	mutex_unlock(&fault->mutex);
+	spin_unlock(&fault->lock);
 
 	wake_up_interruptible(&fault->wait_queue);
 
diff --git a/drivers/iommu/iommufd/hw_pagetable.c b/drivers/iommu/iommufd/hw_pagetable.c
index d06bf6e6c19f..2454627a8b61 100644
--- a/drivers/iommu/iommufd/hw_pagetable.c
+++ b/drivers/iommu/iommufd/hw_pagetable.c
@@ -122,6 +122,9 @@ iommufd_hwpt_paging_alloc(struct iommufd_ctx *ictx, struct iommufd_ioas *ioas,
 	if ((flags & IOMMU_HWPT_ALLOC_DIRTY_TRACKING) &&
 	    !device_iommu_capable(idev->dev, IOMMU_CAP_DIRTY_TRACKING))
 		return ERR_PTR(-EOPNOTSUPP);
+	if ((flags & IOMMU_HWPT_FAULT_ID_VALID) &&
+	    (flags & IOMMU_HWPT_ALLOC_NEST_PARENT))
+		return ERR_PTR(-EOPNOTSUPP);
 
 	hwpt_paging = __iommufd_object_alloc(
 		ictx, hwpt_paging, IOMMUFD_OBJ_HWPT_PAGING, common.obj);
diff --git a/drivers/iommu/iommufd/io_pagetable.c b/drivers/iommu/iommufd/io_pagetable.c
index 4bf7ccd39d46..067222b238b7 100644
--- a/drivers/iommu/iommufd/io_pagetable.c
+++ b/drivers/iommu/iommufd/io_pagetable.c
@@ -70,36 +70,45 @@ struct iopt_area *iopt_area_contig_next(struct iopt_area_contig_iter *iter)
 	return iter->area;
 }
 
-static bool __alloc_iova_check_hole(struct interval_tree_double_span_iter *span,
-				    unsigned long length,
-				    unsigned long iova_alignment,
-				    unsigned long page_offset)
+static bool __alloc_iova_check_range(unsigned long *start, unsigned long last,
+				     unsigned long length,
+				     unsigned long iova_alignment,
+				     unsigned long page_offset)
 {
-	if (span->is_used || span->last_hole - span->start_hole < length - 1)
+	unsigned long aligned_start;
+
+	/* ALIGN_UP() */
+	if (check_add_overflow(*start, iova_alignment - 1, &aligned_start))
 		return false;
+	aligned_start &= ~(iova_alignment - 1);
+	aligned_start |= page_offset;
 
-	span->start_hole = ALIGN(span->start_hole, iova_alignment) |
-			   page_offset;
-	if (span->start_hole > span->last_hole ||
-	    span->last_hole - span->start_hole < length - 1)
+	if (aligned_start >= last || last - aligned_start < length - 1)
 		return false;
+	*start = aligned_start;
 	return true;
 }
 
-static bool __alloc_iova_check_used(struct interval_tree_span_iter *span,
+static bool __alloc_iova_check_hole(struct interval_tree_double_span_iter *span,
 				    unsigned long length,
 				    unsigned long iova_alignment,
 				    unsigned long page_offset)
 {
-	if (span->is_hole || span->last_used - span->start_used < length - 1)
+	if (span->is_used)
 		return false;
+	return __alloc_iova_check_range(&span->start_hole, span->last_hole,
+					length, iova_alignment, page_offset);
+}
 
-	span->start_used = ALIGN(span->start_used, iova_alignment) |
-			   page_offset;
-	if (span->start_used > span->last_used ||
-	    span->last_used - span->start_used < length - 1)
+static bool __alloc_iova_check_used(struct interval_tree_span_iter *span,
+				    unsigned long length,
+				    unsigned long iova_alignment,
+				    unsigned long page_offset)
+{
+	if (span->is_hole)
 		return false;
-	return true;
+	return __alloc_iova_check_range(&span->start_used, span->last_used,
+					length, iova_alignment, page_offset);
 }
 
 /*
@@ -696,8 +705,10 @@ again:
 			iommufd_access_notify_unmap(iopt, area_first, length);
 			/* Something is not responding to unmap requests. */
 			tries++;
-			if (WARN_ON(tries > 100))
-				return -EDEADLOCK;
+			if (WARN_ON(tries > 100)) {
+				rc = -EDEADLOCK;
+				goto out_unmapped;
+			}
 			goto again;
 		}
 
@@ -719,6 +730,7 @@ again:
 out_unlock_iova:
 	up_write(&iopt->iova_rwsem);
 	up_read(&iopt->domains_rwsem);
+out_unmapped:
 	if (unmapped)
 		*unmapped = unmapped_bytes;
 	return rc;
diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h
index f1d865e6fab6..18cdf1391a03 100644
--- a/drivers/iommu/iommufd/iommufd_private.h
+++ b/drivers/iommu/iommufd/iommufd_private.h
@@ -462,14 +462,39 @@ struct iommufd_fault {
 	struct iommufd_ctx *ictx;
 	struct file *filep;
 
-	/* The lists of outstanding faults protected by below mutex. */
-	struct mutex mutex;
+	spinlock_t lock; /* protects the deliver list */
 	struct list_head deliver;
+	struct mutex mutex; /* serializes response flows */
 	struct xarray response;
 
 	struct wait_queue_head wait_queue;
 };
 
+/* Fetch the first node out of the fault->deliver list */
+static inline struct iopf_group *
+iommufd_fault_deliver_fetch(struct iommufd_fault *fault)
+{
+	struct list_head *list = &fault->deliver;
+	struct iopf_group *group = NULL;
+
+	spin_lock(&fault->lock);
+	if (!list_empty(list)) {
+		group = list_first_entry(list, struct iopf_group, node);
+		list_del(&group->node);
+	}
+	spin_unlock(&fault->lock);
+	return group;
+}
+
+/* Restore a node back to the head of the fault->deliver list */
+static inline void iommufd_fault_deliver_restore(struct iommufd_fault *fault,
+						 struct iopf_group *group)
+{
+	spin_lock(&fault->lock);
+	list_add(&group->node, &fault->deliver);
+	spin_unlock(&fault->lock);
+}
+
 struct iommufd_attach_handle {
 	struct iommu_attach_handle handle;
 	struct iommufd_device *idev;
@@ -498,35 +523,10 @@ int iommufd_fault_domain_replace_dev(struct iommufd_device *idev,
 				     struct iommufd_hw_pagetable *hwpt,
 				     struct iommufd_hw_pagetable *old);
 
-static inline int iommufd_hwpt_attach_device(struct iommufd_hw_pagetable *hwpt,
-					     struct iommufd_device *idev)
-{
-	if (hwpt->fault)
-		return iommufd_fault_domain_attach_dev(hwpt, idev);
-
-	return iommu_attach_group(hwpt->domain, idev->igroup->group);
-}
-
-static inline void iommufd_hwpt_detach_device(struct iommufd_hw_pagetable *hwpt,
-					      struct iommufd_device *idev)
-{
-	if (hwpt->fault) {
-		iommufd_fault_domain_detach_dev(hwpt, idev);
-		return;
-	}
-
-	iommu_detach_group(hwpt->domain, idev->igroup->group);
-}
-
-static inline int iommufd_hwpt_replace_device(struct iommufd_device *idev,
-					      struct iommufd_hw_pagetable *hwpt,
-					      struct iommufd_hw_pagetable *old)
-{
-	if (old->fault || hwpt->fault)
-		return iommufd_fault_domain_replace_dev(idev, hwpt, old);
-
-	return iommu_group_replace_domain(idev->igroup->group, hwpt->domain);
-}
+int iommufd_fault_iopf_enable(struct iommufd_device *idev);
+void iommufd_fault_iopf_disable(struct iommufd_device *idev);
+void iommufd_auto_response_faults(struct iommufd_hw_pagetable *hwpt,
+				  struct iommufd_attach_handle *handle);
 
 #ifdef CONFIG_IOMMUFD_TEST
 int iommufd_test(struct iommufd_ucmd *ucmd);
diff --git a/drivers/iommu/iommufd/iova_bitmap.c b/drivers/iommu/iommufd/iova_bitmap.c
index d90b9e253412..2cdc4f542df4 100644
--- a/drivers/iommu/iommufd/iova_bitmap.c
+++ b/drivers/iommu/iommufd/iova_bitmap.c
@@ -130,7 +130,7 @@ struct iova_bitmap {
 static unsigned long iova_bitmap_offset_to_index(struct iova_bitmap *bitmap,
 						 unsigned long iova)
 {
-	unsigned long pgsize = 1 << bitmap->mapped.pgshift;
+	unsigned long pgsize = 1UL << bitmap->mapped.pgshift;
 
 	return iova / (BITS_PER_TYPE(*bitmap->bitmap) * pgsize);
 }
diff --git a/drivers/iommu/iommufd/main.c b/drivers/iommu/iommufd/main.c
index b5f5d27ee963..649fe79d0f0c 100644
--- a/drivers/iommu/iommufd/main.c
+++ b/drivers/iommu/iommufd/main.c
@@ -130,7 +130,7 @@ static int iommufd_object_dec_wait_shortterm(struct iommufd_ctx *ictx,
 	if (wait_event_timeout(ictx->destroy_wait,
 				refcount_read(&to_destroy->shortterm_users) ==
 					0,
-				msecs_to_jiffies(10000)))
+				msecs_to_jiffies(60000)))
 		return 0;
 
 	pr_crit("Time out waiting for iommufd object to become free\n");
diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c
index ff55b8c30712..ae69691471e9 100644
--- a/drivers/iommu/ipmmu-vmsa.c
+++ b/drivers/iommu/ipmmu-vmsa.c
@@ -1087,7 +1087,7 @@ static int ipmmu_probe(struct platform_device *pdev)
 	 * - R-Car Gen3 IPMMU (leaf devices only - skip root IPMMU-MM device)
 	 */
 	if (!mmu->features->has_cache_leaf_nodes || !ipmmu_is_root(mmu)) {
-		ret = iommu_device_sysfs_add(&mmu->iommu, &pdev->dev, NULL,
+		ret = iommu_device_sysfs_add(&mmu->iommu, &pdev->dev, NULL, "%s",
 					     dev_name(&pdev->dev));
 		if (ret)
 			return ret;
diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index 6a2707fe7a78..32deab732209 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -1371,15 +1371,6 @@ static int mtk_iommu_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, data);
 	mutex_init(&data->mutex);
 
-	ret = iommu_device_sysfs_add(&data->iommu, dev, NULL,
-				     "mtk-iommu.%pa", &ioaddr);
-	if (ret)
-		goto out_link_remove;
-
-	ret = iommu_device_register(&data->iommu, &mtk_iommu_ops, dev);
-	if (ret)
-		goto out_sysfs_remove;
-
 	if (MTK_IOMMU_HAS_FLAG(data->plat_data, SHARE_PGTABLE)) {
 		list_add_tail(&data->list, data->plat_data->hw_list);
 		data->hw_list = data->plat_data->hw_list;
@@ -1389,19 +1380,28 @@ static int mtk_iommu_probe(struct platform_device *pdev)
 		data->hw_list = &data->hw_list_head;
 	}
 
+	ret = iommu_device_sysfs_add(&data->iommu, dev, NULL,
+				     "mtk-iommu.%pa", &ioaddr);
+	if (ret)
+		goto out_list_del;
+
+	ret = iommu_device_register(&data->iommu, &mtk_iommu_ops, dev);
+	if (ret)
+		goto out_sysfs_remove;
+
 	if (MTK_IOMMU_IS_TYPE(data->plat_data, MTK_IOMMU_TYPE_MM)) {
 		ret = component_master_add_with_match(dev, &mtk_iommu_com_ops, match);
 		if (ret)
-			goto out_list_del;
+			goto out_device_unregister;
 	}
 	return ret;
 
-out_list_del:
-	list_del(&data->list);
+out_device_unregister:
 	iommu_device_unregister(&data->iommu);
 out_sysfs_remove:
 	iommu_device_sysfs_remove(&data->iommu);
-out_link_remove:
+out_list_del:
+	list_del(&data->list);
 	if (MTK_IOMMU_IS_TYPE(data->plat_data, MTK_IOMMU_TYPE_MM))
 		device_link_remove(data->smicomm_dev, dev);
 out_runtime_disable:
diff --git a/drivers/iommu/of_iommu.c b/drivers/iommu/of_iommu.c
index e7a6a1611d19..e3fcab925a54 100644
--- a/drivers/iommu/of_iommu.c
+++ b/drivers/iommu/of_iommu.c
@@ -118,6 +118,7 @@ static void of_pci_check_device_ats(struct device *dev, struct device_node *np)
 int of_iommu_configure(struct device *dev, struct device_node *master_np,
 		       const u32 *id)
 {
+	bool dev_iommu_present;
 	int err;
 
 	if (!master_np)
@@ -129,6 +130,7 @@ int of_iommu_configure(struct device *dev, struct device_node *master_np,
 		mutex_unlock(&iommu_probe_device_lock);
 		return 0;
 	}
+	dev_iommu_present = dev->iommu;
 
 	/*
 	 * We don't currently walk up the tree looking for a parent IOMMU.
@@ -149,8 +151,10 @@ int of_iommu_configure(struct device *dev, struct device_node *master_np,
 		err = of_iommu_configure_device(master_np, dev, id);
 	}
 
-	if (err)
+	if (err && dev_iommu_present)
 		iommu_fwspec_free(dev);
+	else if (err && dev->iommu)
+		dev_iommu_free(dev);
 	mutex_unlock(&iommu_probe_device_lock);
 
 	if (!err && dev->bus)
diff --git a/drivers/iommu/rockchip-iommu.c b/drivers/iommu/rockchip-iommu.c
index 4b369419b32c..4c7f470a4752 100644
--- a/drivers/iommu/rockchip-iommu.c
+++ b/drivers/iommu/rockchip-iommu.c
@@ -1154,7 +1154,6 @@ static int rk_iommu_of_xlate(struct device *dev,
 	iommu_dev = of_find_device_by_node(args->np);
 
 	data->iommu = platform_get_drvdata(iommu_dev);
-	data->iommu->domain = &rk_identity_domain;
 	dev_iommu_priv_set(dev, data);
 
 	platform_device_put(iommu_dev);
@@ -1192,6 +1191,8 @@ static int rk_iommu_probe(struct platform_device *pdev)
 	if (!iommu)
 		return -ENOMEM;
 
+	iommu->domain = &rk_identity_domain;
+
 	platform_set_drvdata(pdev, iommu);
 	iommu->dev = dev;
 	iommu->num_mmu = 0;
diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig
index 66ce15027f28..5d5b3cf381b9 100644
--- a/drivers/irqchip/Kconfig
+++ b/drivers/irqchip/Kconfig
@@ -71,6 +71,7 @@ config ARM_VIC_NR
 
 config IRQ_MSI_LIB
 	bool
+	select GENERIC_MSI_IRQ
 
 config ARMADA_370_XP_IRQ
 	bool
@@ -169,6 +170,7 @@ config IXP4XX_IRQ
 
 config LAN966X_OIC
 	tristate "Microchip LAN966x OIC Support"
+	depends on MCHP_LAN966X_PCI || COMPILE_TEST
 	select GENERIC_IRQ_CHIP
 	select IRQ_DOMAIN
 	help
@@ -504,6 +506,7 @@ config IMX_MU_MSI
 	tristate "i.MX MU used as MSI controller"
 	depends on OF && HAS_IOMEM
 	depends on ARCH_MXC || COMPILE_TEST
+	depends on ARM || ARM64
 	default m if ARCH_MXC
 	select IRQ_DOMAIN
 	select IRQ_DOMAIN_HIERARCHY
diff --git a/drivers/irqchip/irq-apple-aic.c b/drivers/irqchip/irq-apple-aic.c
index da5250f0155c..2b1684c60e3c 100644
--- a/drivers/irqchip/irq-apple-aic.c
+++ b/drivers/irqchip/irq-apple-aic.c
@@ -577,7 +577,8 @@ static void __exception_irq_entry aic_handle_fiq(struct pt_regs *regs)
 						  AIC_FIQ_HWIRQ(AIC_TMR_EL02_VIRT));
 	}
 
-	if (read_sysreg_s(SYS_IMP_APL_PMCR0_EL1) & PMCR0_IACT) {
+	if ((read_sysreg_s(SYS_IMP_APL_PMCR0_EL1) & (PMCR0_IMODE | PMCR0_IACT)) ==
+			(FIELD_PREP(PMCR0_IMODE, PMCR0_IMODE_FIQ) | PMCR0_IACT)) {
 		int irq;
 		if (cpumask_test_cpu(smp_processor_id(),
 				     &aic_irqc->fiq_aff[AIC_CPU_PMU_P]->aff))
diff --git a/drivers/irqchip/irq-gic-v2m.c b/drivers/irqchip/irq-gic-v2m.c
index be35c5349986..a1e370d0200f 100644
--- a/drivers/irqchip/irq-gic-v2m.c
+++ b/drivers/irqchip/irq-gic-v2m.c
@@ -423,7 +423,7 @@ static int __init gicv2m_of_init(struct fwnode_handle *parent_handle,
 #ifdef CONFIG_ACPI
 static int acpi_num_msi;
 
-static __init struct fwnode_handle *gicv2m_get_fwnode(struct device *dev)
+static struct fwnode_handle *gicv2m_get_fwnode(struct device *dev)
 {
 	struct v2m_data *data;
 
diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
index 8fdee511bc0f..cf469a672497 100644
--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -44,6 +44,7 @@ static u8 dist_prio_nmi __ro_after_init = GICV3_PRIO_NMI;
 #define FLAGS_WORKAROUND_GICR_WAKER_MSM8996	(1ULL << 0)
 #define FLAGS_WORKAROUND_CAVIUM_ERRATUM_38539	(1ULL << 1)
 #define FLAGS_WORKAROUND_ASR_ERRATUM_8601001	(1ULL << 2)
+#define FLAGS_WORKAROUND_INSECURE		(1ULL << 3)
 
 #define GIC_IRQ_TYPE_PARTITION	(GIC_IRQ_TYPE_LPI + 1)
 
@@ -83,6 +84,8 @@ static DEFINE_STATIC_KEY_TRUE(supports_deactivate_key);
 #define GIC_LINE_NR	min(GICD_TYPER_SPIS(gic_data.rdists.gicd_typer), 1020U)
 #define GIC_ESPI_NR	GICD_TYPER_ESPIS(gic_data.rdists.gicd_typer)
 
+static bool nmi_support_forbidden;
+
 /*
  * There are 16 SGIs, though we only actually use 8 in Linux. The other 8 SGIs
  * are potentially stolen by the secure side. Some code, especially code dealing
@@ -163,21 +166,27 @@ static void __init gic_prio_init(void)
 {
 	bool ds;
 
-	ds = gic_dist_security_disabled();
-	if (!ds) {
-		u32 val;
-
-		val = readl_relaxed(gic_data.dist_base + GICD_CTLR);
-		val |= GICD_CTLR_DS;
-		writel_relaxed(val, gic_data.dist_base + GICD_CTLR);
+	cpus_have_group0 = gic_has_group0();
 
-		ds = gic_dist_security_disabled();
-		if (ds)
-			pr_warn("Broken GIC integration, security disabled");
+	ds = gic_dist_security_disabled();
+	if ((gic_data.flags & FLAGS_WORKAROUND_INSECURE) && !ds) {
+		if (cpus_have_group0) {
+			u32 val;
+
+			val = readl_relaxed(gic_data.dist_base + GICD_CTLR);
+			val |= GICD_CTLR_DS;
+			writel_relaxed(val, gic_data.dist_base + GICD_CTLR);
+
+			ds = gic_dist_security_disabled();
+			if (ds)
+				pr_warn("Broken GIC integration, security disabled\n");
+		} else {
+			pr_warn("Broken GIC integration, pNMI forbidden\n");
+			nmi_support_forbidden = true;
+		}
 	}
 
 	cpus_have_security_disabled = ds;
-	cpus_have_group0 = gic_has_group0();
 
 	/*
 	 * How priority values are used by the GIC depends on two things:
@@ -209,7 +218,7 @@ static void __init gic_prio_init(void)
 	 * be in the non-secure range, we program the non-secure values into
 	 * the distributor to match the PMR values we want.
 	 */
-	if (cpus_have_group0 & !cpus_have_security_disabled) {
+	if (cpus_have_group0 && !cpus_have_security_disabled) {
 		dist_prio_irq = __gicv3_prio_to_ns(dist_prio_irq);
 		dist_prio_nmi = __gicv3_prio_to_ns(dist_prio_nmi);
 	}
@@ -1922,6 +1931,18 @@ static bool gic_enable_quirk_arm64_2941627(void *data)
 	return true;
 }
 
+static bool gic_enable_quirk_rk3399(void *data)
+{
+	struct gic_chip_data *d = data;
+
+	if (of_machine_is_compatible("rockchip,rk3399")) {
+		d->flags |= FLAGS_WORKAROUND_INSECURE;
+		return true;
+	}
+
+	return false;
+}
+
 static bool rd_set_non_coherent(void *data)
 {
 	struct gic_chip_data *d = data;
@@ -1997,6 +2018,12 @@ static const struct gic_quirk gic_quirks[] = {
 		.init   = rd_set_non_coherent,
 	},
 	{
+		.desc	= "GICv3: Insecure RK3399 integration",
+		.iidr	= 0x0000043b,
+		.mask	= 0xff000fff,
+		.init	= gic_enable_quirk_rk3399,
+	},
+	{
 	}
 };
 
@@ -2004,7 +2031,7 @@ static void gic_enable_nmi_support(void)
 {
 	int i;
 
-	if (!gic_prio_masking_enabled())
+	if (!gic_prio_masking_enabled() || nmi_support_forbidden)
 		return;
 
 	rdist_nmi_refs = kcalloc(gic_data.ppi_nr + SGI_NR,
diff --git a/drivers/irqchip/irq-jcore-aic.c b/drivers/irqchip/irq-jcore-aic.c
index b9dcc8e78c75..1f613eb7b7f0 100644
--- a/drivers/irqchip/irq-jcore-aic.c
+++ b/drivers/irqchip/irq-jcore-aic.c
@@ -38,7 +38,7 @@ static struct irq_chip jcore_aic;
 static void handle_jcore_irq(struct irq_desc *desc)
 {
 	if (irqd_is_per_cpu(irq_desc_get_irq_data(desc)))
-		handle_percpu_irq(desc);
+		handle_percpu_devid_irq(desc);
 	else
 		handle_simple_irq(desc);
 }
diff --git a/drivers/irqchip/irq-mvebu-icu.c b/drivers/irqchip/irq-mvebu-icu.c
index b337f6c05f18..4eebed39880a 100644
--- a/drivers/irqchip/irq-mvebu-icu.c
+++ b/drivers/irqchip/irq-mvebu-icu.c
@@ -68,7 +68,8 @@ static int mvebu_icu_translate(struct irq_domain *d, struct irq_fwspec *fwspec,
 			       unsigned long *hwirq, unsigned int *type)
 {
 	unsigned int param_count = static_branch_unlikely(&legacy_bindings) ? 3 : 2;
-	struct mvebu_icu_msi_data *msi_data = d->host_data;
+	struct msi_domain_info *info = d->host_data;
+	struct mvebu_icu_msi_data *msi_data = info->chip_data;
 	struct mvebu_icu *icu = msi_data->icu;
 
 	/* Check the count of the parameters in dt */
diff --git a/drivers/irqchip/irq-qcom-mpm.c b/drivers/irqchip/irq-qcom-mpm.c
index 7942d8eb3d00..f772deb9cba5 100644
--- a/drivers/irqchip/irq-qcom-mpm.c
+++ b/drivers/irqchip/irq-qcom-mpm.c
@@ -227,6 +227,9 @@ static int qcom_mpm_alloc(struct irq_domain *domain, unsigned int virq,
 	if (ret)
 		return ret;
 
+	if (pin == GPIO_NO_WAKE_IRQ)
+		return irq_domain_disconnect_hierarchy(domain, virq);
+
 	ret = irq_domain_set_hwirq_and_chip(domain, virq, pin,
 					    &qcom_mpm_chip, priv);
 	if (ret)
diff --git a/drivers/irqchip/irq-riscv-aplic-direct.c b/drivers/irqchip/irq-riscv-aplic-direct.c
index 7cd6b646774b..205ad61d15e4 100644
--- a/drivers/irqchip/irq-riscv-aplic-direct.c
+++ b/drivers/irqchip/irq-riscv-aplic-direct.c
@@ -31,7 +31,7 @@ struct aplic_direct {
 };
 
 struct aplic_idc {
-	unsigned int		hart_index;
+	u32			hart_index;
 	void __iomem		*regs;
 	struct aplic_direct	*direct;
 };
@@ -219,6 +219,20 @@ static int aplic_direct_parse_parent_hwirq(struct device *dev, u32 index,
 	return 0;
 }
 
+static int aplic_direct_get_hart_index(struct device *dev, u32 logical_index,
+				       u32 *hart_index)
+{
+	const char *prop_hart_index = "riscv,hart-indexes";
+	struct device_node *np = to_of_node(dev->fwnode);
+
+	if (!np || !of_property_present(np, prop_hart_index)) {
+		*hart_index = logical_index;
+		return 0;
+	}
+
+	return of_property_read_u32_index(np, prop_hart_index, logical_index, hart_index);
+}
+
 int aplic_direct_setup(struct device *dev, void __iomem *regs)
 {
 	int i, j, rc, cpu, current_cpu, setup_count = 0;
@@ -265,8 +279,12 @@ int aplic_direct_setup(struct device *dev, void __iomem *regs)
 		cpumask_set_cpu(cpu, &direct->lmask);
 
 		idc = per_cpu_ptr(&aplic_idcs, cpu);
-		idc->hart_index = i;
-		idc->regs = priv->regs + APLIC_IDC_BASE + i * APLIC_IDC_SIZE;
+		rc = aplic_direct_get_hart_index(dev, i, &idc->hart_index);
+		if (rc) {
+			dev_warn(dev, "hart index not found for IDC%d\n", i);
+			continue;
+		}
+		idc->regs = priv->regs + APLIC_IDC_BASE + idc->hart_index * APLIC_IDC_SIZE;
 		idc->direct = direct;
 
 		aplic_idc_set_delivery(idc, true);
diff --git a/drivers/irqchip/irq-riscv-imsic-early.c b/drivers/irqchip/irq-riscv-imsic-early.c
index c5c2e6929a2f..b5def6268936 100644
--- a/drivers/irqchip/irq-riscv-imsic-early.c
+++ b/drivers/irqchip/irq-riscv-imsic-early.c
@@ -77,6 +77,12 @@ static void imsic_handle_irq(struct irq_desc *desc)
 	struct imsic_vector *vec;
 	unsigned long local_id;
 
+	/*
+	 * Process pending local synchronization instead of waiting
+	 * for per-CPU local timer to expire.
+	 */
+	imsic_local_sync_all(false);
+
 	chained_irq_enter(chip, desc);
 
 	while ((local_id = csr_swap(CSR_TOPEI, 0))) {
@@ -120,7 +126,7 @@ static int imsic_starting_cpu(unsigned int cpu)
 	 * Interrupts identities might have been enabled/disabled while
 	 * this CPU was not running so sync-up local enable/disable state.
 	 */
-	imsic_local_sync_all();
+	imsic_local_sync_all(true);
 
 	/* Enable local interrupt delivery */
 	imsic_local_delivery(true);
diff --git a/drivers/irqchip/irq-riscv-imsic-platform.c b/drivers/irqchip/irq-riscv-imsic-platform.c
index c708780e8760..5d7c30ad8855 100644
--- a/drivers/irqchip/irq-riscv-imsic-platform.c
+++ b/drivers/irqchip/irq-riscv-imsic-platform.c
@@ -96,9 +96,8 @@ static int imsic_irq_set_affinity(struct irq_data *d, const struct cpumask *mask
 				  bool force)
 {
 	struct imsic_vector *old_vec, *new_vec;
-	struct irq_data *pd = d->parent_data;
 
-	old_vec = irq_data_get_irq_chip_data(pd);
+	old_vec = irq_data_get_irq_chip_data(d);
 	if (WARN_ON(!old_vec))
 		return -ENOENT;
 
@@ -116,13 +115,13 @@ static int imsic_irq_set_affinity(struct irq_data *d, const struct cpumask *mask
 		return -ENOSPC;
 
 	/* Point device to the new vector */
-	imsic_msi_update_msg(d, new_vec);
+	imsic_msi_update_msg(irq_get_irq_data(d->irq), new_vec);
 
 	/* Update irq descriptors with the new vector */
-	pd->chip_data = new_vec;
+	d->chip_data = new_vec;
 
-	/* Update effective affinity of parent irq data */
-	irq_data_update_effective_affinity(pd, cpumask_of(new_vec->cpu));
+	/* Update effective affinity */
+	irq_data_update_effective_affinity(d, cpumask_of(new_vec->cpu));
 
 	/* Move state of the old vector to the new vector */
 	imsic_vector_move(old_vec, new_vec);
@@ -135,6 +134,9 @@ static struct irq_chip imsic_irq_base_chip = {
 	.name			= "IMSIC",
 	.irq_mask		= imsic_irq_mask,
 	.irq_unmask		= imsic_irq_unmask,
+#ifdef CONFIG_SMP
+	.irq_set_affinity	= imsic_irq_set_affinity,
+#endif
 	.irq_retrigger		= imsic_irq_retrigger,
 	.irq_compose_msi_msg	= imsic_irq_compose_msg,
 	.flags			= IRQCHIP_SKIP_SET_WAKE |
@@ -245,7 +247,7 @@ static bool imsic_init_dev_msi_info(struct device *dev,
 		if (WARN_ON_ONCE(domain != real_parent))
 			return false;
 #ifdef CONFIG_SMP
-		info->chip->irq_set_affinity = imsic_irq_set_affinity;
+		info->chip->irq_set_affinity = irq_chip_set_affinity_parent;
 #endif
 		break;
 	default:
diff --git a/drivers/irqchip/irq-riscv-imsic-state.c b/drivers/irqchip/irq-riscv-imsic-state.c
index b97e6cd89ed7..06ff0e17c0c3 100644
--- a/drivers/irqchip/irq-riscv-imsic-state.c
+++ b/drivers/irqchip/irq-riscv-imsic-state.c
@@ -124,10 +124,11 @@ void __imsic_eix_update(unsigned long base_id, unsigned long num_id, bool pend,
 	}
 }
 
-static void __imsic_local_sync(struct imsic_local_priv *lpriv)
+static bool __imsic_local_sync(struct imsic_local_priv *lpriv)
 {
 	struct imsic_local_config *mlocal;
 	struct imsic_vector *vec, *mvec;
+	bool ret = true;
 	int i;
 
 	lockdep_assert_held(&lpriv->lock);
@@ -143,35 +144,75 @@ static void __imsic_local_sync(struct imsic_local_priv *lpriv)
 			__imsic_id_clear_enable(i);
 
 		/*
-		 * If the ID was being moved to a new ID on some other CPU
-		 * then we can get a MSI during the movement so check the
-		 * ID pending bit and re-trigger the new ID on other CPU
-		 * using MMIO write.
+		 * Clear the previous vector pointer of the new vector only
+		 * after the movement is complete on the old CPU.
 		 */
-		mvec = READ_ONCE(vec->move);
-		WRITE_ONCE(vec->move, NULL);
-		if (mvec && mvec != vec) {
+		mvec = READ_ONCE(vec->move_prev);
+		if (mvec) {
+			/*
+			 * If the old vector has not been updated then
+			 * try again in the next sync-up call.
+			 */
+			if (READ_ONCE(mvec->move_next)) {
+				ret = false;
+				continue;
+			}
+
+			WRITE_ONCE(vec->move_prev, NULL);
+		}
+
+		/*
+		 * If a vector was being moved to a new vector on some other
+		 * CPU then we can get a MSI during the movement so check the
+		 * ID pending bit and re-trigger the new ID on other CPU using
+		 * MMIO write.
+		 */
+		mvec = READ_ONCE(vec->move_next);
+		if (mvec) {
 			if (__imsic_id_read_clear_pending(i)) {
 				mlocal = per_cpu_ptr(imsic->global.local, mvec->cpu);
 				writel_relaxed(mvec->local_id, mlocal->msi_va);
 			}
 
+			WRITE_ONCE(vec->move_next, NULL);
 			imsic_vector_free(&lpriv->vectors[i]);
 		}
 
 skip:
 		bitmap_clear(lpriv->dirty_bitmap, i, 1);
 	}
+
+	return ret;
 }
 
-void imsic_local_sync_all(void)
+#ifdef CONFIG_SMP
+static void __imsic_local_timer_start(struct imsic_local_priv *lpriv, unsigned int cpu)
+{
+	lockdep_assert_held(&lpriv->lock);
+
+	if (!timer_pending(&lpriv->timer)) {
+		lpriv->timer.expires = jiffies + 1;
+		add_timer_on(&lpriv->timer, cpu);
+	}
+}
+#else
+static inline void __imsic_local_timer_start(struct imsic_local_priv *lpriv, unsigned int cpu)
+{
+}
+#endif
+
+void imsic_local_sync_all(bool force_all)
 {
 	struct imsic_local_priv *lpriv = this_cpu_ptr(imsic->lpriv);
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&lpriv->lock, flags);
-	bitmap_fill(lpriv->dirty_bitmap, imsic->global.nr_ids + 1);
-	__imsic_local_sync(lpriv);
+
+	if (force_all)
+		bitmap_fill(lpriv->dirty_bitmap, imsic->global.nr_ids + 1);
+	if (!__imsic_local_sync(lpriv))
+		__imsic_local_timer_start(lpriv, smp_processor_id());
+
 	raw_spin_unlock_irqrestore(&lpriv->lock, flags);
 }
 
@@ -190,12 +231,7 @@ void imsic_local_delivery(bool enable)
 #ifdef CONFIG_SMP
 static void imsic_local_timer_callback(struct timer_list *timer)
 {
-	struct imsic_local_priv *lpriv = this_cpu_ptr(imsic->lpriv);
-	unsigned long flags;
-
-	raw_spin_lock_irqsave(&lpriv->lock, flags);
-	__imsic_local_sync(lpriv);
-	raw_spin_unlock_irqrestore(&lpriv->lock, flags);
+	imsic_local_sync_all(false);
 }
 
 static void __imsic_remote_sync(struct imsic_local_priv *lpriv, unsigned int cpu)
@@ -216,14 +252,11 @@ static void __imsic_remote_sync(struct imsic_local_priv *lpriv, unsigned int cpu
 	 */
 	if (cpu_online(cpu)) {
 		if (cpu == smp_processor_id()) {
-			__imsic_local_sync(lpriv);
-			return;
+			if (__imsic_local_sync(lpriv))
+				return;
 		}
 
-		if (!timer_pending(&lpriv->timer)) {
-			lpriv->timer.expires = jiffies + 1;
-			add_timer_on(&lpriv->timer, cpu);
-		}
+		__imsic_local_timer_start(lpriv, cpu);
 	}
 }
 #else
@@ -278,8 +311,9 @@ void imsic_vector_unmask(struct imsic_vector *vec)
 	raw_spin_unlock(&lpriv->lock);
 }
 
-static bool imsic_vector_move_update(struct imsic_local_priv *lpriv, struct imsic_vector *vec,
-				     bool new_enable, struct imsic_vector *new_move)
+static bool imsic_vector_move_update(struct imsic_local_priv *lpriv,
+				     struct imsic_vector *vec, bool is_old_vec,
+				     bool new_enable, struct imsic_vector *move_vec)
 {
 	unsigned long flags;
 	bool enabled;
@@ -289,7 +323,10 @@ static bool imsic_vector_move_update(struct imsic_local_priv *lpriv, struct imsi
 	/* Update enable and move details */
 	enabled = READ_ONCE(vec->enable);
 	WRITE_ONCE(vec->enable, new_enable);
-	WRITE_ONCE(vec->move, new_move);
+	if (is_old_vec)
+		WRITE_ONCE(vec->move_next, move_vec);
+	else
+		WRITE_ONCE(vec->move_prev, move_vec);
 
 	/* Mark the vector as dirty and synchronize */
 	bitmap_set(lpriv->dirty_bitmap, vec->local_id, 1);
@@ -322,8 +359,8 @@ void imsic_vector_move(struct imsic_vector *old_vec, struct imsic_vector *new_ve
 	 * interrupt on the old vector while device was being moved
 	 * to the new vector.
 	 */
-	enabled = imsic_vector_move_update(old_lpriv, old_vec, false, new_vec);
-	imsic_vector_move_update(new_lpriv, new_vec, enabled, new_vec);
+	enabled = imsic_vector_move_update(old_lpriv, old_vec, true, false, new_vec);
+	imsic_vector_move_update(new_lpriv, new_vec, false, enabled, old_vec);
 }
 
 #ifdef CONFIG_GENERIC_IRQ_DEBUGFS
@@ -386,7 +423,8 @@ struct imsic_vector *imsic_vector_alloc(unsigned int hwirq, const struct cpumask
 	vec = &lpriv->vectors[local_id];
 	vec->hwirq = hwirq;
 	vec->enable = false;
-	vec->move = NULL;
+	vec->move_next = NULL;
+	vec->move_prev = NULL;
 
 	return vec;
 }
diff --git a/drivers/irqchip/irq-riscv-imsic-state.h b/drivers/irqchip/irq-riscv-imsic-state.h
index 391e44280827..f02842b84ed5 100644
--- a/drivers/irqchip/irq-riscv-imsic-state.h
+++ b/drivers/irqchip/irq-riscv-imsic-state.h
@@ -23,7 +23,8 @@ struct imsic_vector {
 	unsigned int				hwirq;
 	/* Details accessed using local lock held */
 	bool					enable;
-	struct imsic_vector			*move;
+	struct imsic_vector			*move_next;
+	struct imsic_vector			*move_prev;
 };
 
 struct imsic_local_priv {
@@ -74,7 +75,7 @@ static inline void __imsic_id_clear_enable(unsigned long id)
 	__imsic_eix_update(id, 1, false, false);
 }
 
-void imsic_local_sync_all(void);
+void imsic_local_sync_all(bool force_all);
 void imsic_local_delivery(bool enable);
 
 void imsic_vector_mask(struct imsic_vector *vec);
@@ -87,7 +88,7 @@ static inline bool imsic_vector_isenabled(struct imsic_vector *vec)
 
 static inline struct imsic_vector *imsic_vector_get_move(struct imsic_vector *vec)
 {
-	return READ_ONCE(vec->move);
+	return READ_ONCE(vec->move_prev);
 }
 
 void imsic_vector_move(struct imsic_vector *old_vec, struct imsic_vector *new_vec);
diff --git a/drivers/irqchip/irq-sunxi-nmi.c b/drivers/irqchip/irq-sunxi-nmi.c
index bb92fd85e975..0b4312152024 100644
--- a/drivers/irqchip/irq-sunxi-nmi.c
+++ b/drivers/irqchip/irq-sunxi-nmi.c
@@ -186,7 +186,8 @@ static int __init sunxi_sc_nmi_irq_init(struct device_node *node,
 	gc->chip_types[0].chip.irq_unmask	= irq_gc_mask_set_bit;
 	gc->chip_types[0].chip.irq_eoi		= irq_gc_ack_set_bit;
 	gc->chip_types[0].chip.irq_set_type	= sunxi_sc_nmi_set_type;
-	gc->chip_types[0].chip.flags		= IRQCHIP_EOI_THREADED | IRQCHIP_EOI_IF_HANDLED;
+	gc->chip_types[0].chip.flags		= IRQCHIP_EOI_THREADED | IRQCHIP_EOI_IF_HANDLED |
+						  IRQCHIP_SKIP_SET_WAKE;
 	gc->chip_types[0].regs.ack		= reg_offs->pend;
 	gc->chip_types[0].regs.mask		= reg_offs->enable;
 	gc->chip_types[0].regs.type		= reg_offs->ctrl;
diff --git a/drivers/leds/flash/leds-qcom-flash.c b/drivers/leds/flash/leds-qcom-flash.c
index 41ce034f700e..07a83bb2dfdf 100644
--- a/drivers/leds/flash/leds-qcom-flash.c
+++ b/drivers/leds/flash/leds-qcom-flash.c
@@ -117,7 +117,7 @@ enum {
 	REG_MAX_COUNT,
 };
 
-static struct reg_field mvflash_3ch_regs[REG_MAX_COUNT] = {
+static const struct reg_field mvflash_3ch_regs[REG_MAX_COUNT] = {
 	REG_FIELD(0x08, 0, 7),			/* status1	*/
 	REG_FIELD(0x09, 0, 7),                  /* status2	*/
 	REG_FIELD(0x0a, 0, 7),                  /* status3	*/
@@ -132,7 +132,7 @@ static struct reg_field mvflash_3ch_regs[REG_MAX_COUNT] = {
 	REG_FIELD(0x58, 0, 2),			/* therm_thrsh3 */
 };
 
-static struct reg_field mvflash_4ch_regs[REG_MAX_COUNT] = {
+static const struct reg_field mvflash_4ch_regs[REG_MAX_COUNT] = {
 	REG_FIELD(0x06, 0, 7),			/* status1	*/
 	REG_FIELD(0x07, 0, 6),			/* status2	*/
 	REG_FIELD(0x09, 0, 7),			/* status3	*/
@@ -855,11 +855,17 @@ static int qcom_flash_led_probe(struct platform_device *pdev)
 	if (val == FLASH_SUBTYPE_3CH_PM8150_VAL || val == FLASH_SUBTYPE_3CH_PMI8998_VAL) {
 		flash_data->hw_type = QCOM_MVFLASH_3CH;
 		flash_data->max_channels = 3;
-		regs = mvflash_3ch_regs;
+		regs = devm_kmemdup(dev, mvflash_3ch_regs, sizeof(mvflash_3ch_regs),
+				    GFP_KERNEL);
+		if (!regs)
+			return -ENOMEM;
 	} else if (val == FLASH_SUBTYPE_4CH_VAL) {
 		flash_data->hw_type = QCOM_MVFLASH_4CH;
 		flash_data->max_channels = 4;
-		regs = mvflash_4ch_regs;
+		regs = devm_kmemdup(dev, mvflash_4ch_regs, sizeof(mvflash_4ch_regs),
+				    GFP_KERNEL);
+		if (!regs)
+			return -ENOMEM;
 
 		rc = regmap_read(regmap, reg_base + FLASH_REVISION_REG, &val);
 		if (rc < 0) {
@@ -881,6 +887,7 @@ static int qcom_flash_led_probe(struct platform_device *pdev)
 		dev_err(dev, "Failed to allocate regmap field, rc=%d\n", rc);
 		return rc;
 	}
+	devm_kfree(dev, regs); /* devm_regmap_field_bulk_alloc() makes copies */
 
 	platform_set_drvdata(pdev, flash_data);
 	mutex_init(&flash_data->lock);
diff --git a/drivers/leds/led-class-multicolor.c b/drivers/leds/led-class-multicolor.c
index 30c1ecb5f361..c707be97049b 100644
--- a/drivers/leds/led-class-multicolor.c
+++ b/drivers/leds/led-class-multicolor.c
@@ -61,7 +61,8 @@ static ssize_t multi_intensity_store(struct device *dev,
 	for (i = 0; i < mcled_cdev->num_colors; i++)
 		mcled_cdev->subled_info[i].intensity = intensity_value[i];
 
-	led_set_brightness(led_cdev, led_cdev->brightness);
+	if (!test_bit(LED_BLINK_SW, &led_cdev->work_flags))
+		led_set_brightness(led_cdev, led_cdev->brightness);
 	ret = size;
 err_out:
 	mutex_unlock(&led_cdev->led_access);
diff --git a/drivers/leds/led-core.c b/drivers/leds/led-core.c
index 001c290bc07b..cda0995b1679 100644
--- a/drivers/leds/led-core.c
+++ b/drivers/leds/led-core.c
@@ -159,8 +159,19 @@ static void set_brightness_delayed(struct work_struct *ws)
 	 * before this work item runs once. To make sure this works properly
 	 * handle LED_SET_BRIGHTNESS_OFF first.
 	 */
-	if (test_and_clear_bit(LED_SET_BRIGHTNESS_OFF, &led_cdev->work_flags))
+	if (test_and_clear_bit(LED_SET_BRIGHTNESS_OFF, &led_cdev->work_flags)) {
 		set_brightness_delayed_set_brightness(led_cdev, LED_OFF);
+		/*
+		 * The consecutives led_set_brightness(LED_OFF),
+		 * led_set_brightness(LED_FULL) could have been executed out of
+		 * order (LED_FULL first), if the work_flags has been set
+		 * between LED_SET_BRIGHTNESS_OFF and LED_SET_BRIGHTNESS of this
+		 * work. To avoid ending with the LED turned off, turn the LED
+		 * on again.
+		 */
+		if (led_cdev->delayed_set_value != LED_OFF)
+			set_bit(LED_SET_BRIGHTNESS, &led_cdev->work_flags);
+	}
 
 	if (test_and_clear_bit(LED_SET_BRIGHTNESS, &led_cdev->work_flags))
 		set_brightness_delayed_set_brightness(led_cdev, led_cdev->delayed_set_value);
@@ -331,10 +342,13 @@ void led_set_brightness_nopm(struct led_classdev *led_cdev, unsigned int value)
 	 * change is done immediately afterwards (before the work runs),
 	 * it uses a separate work_flag.
 	 */
-	if (value) {
-		led_cdev->delayed_set_value = value;
+	led_cdev->delayed_set_value = value;
+	/* Ensure delayed_set_value is seen before work_flags modification */
+	smp_mb__before_atomic();
+
+	if (value)
 		set_bit(LED_SET_BRIGHTNESS, &led_cdev->work_flags);
-	} else {
+	else {
 		clear_bit(LED_SET_BRIGHTNESS, &led_cdev->work_flags);
 		clear_bit(LED_SET_BLINK, &led_cdev->work_flags);
 		set_bit(LED_SET_BRIGHTNESS_OFF, &led_cdev->work_flags);
diff --git a/drivers/leds/leds-cht-wcove.c b/drivers/leds/leds-cht-wcove.c
index b4998402b8c6..711ac4bd6058 100644
--- a/drivers/leds/leds-cht-wcove.c
+++ b/drivers/leds/leds-cht-wcove.c
@@ -394,7 +394,7 @@ static int cht_wc_leds_probe(struct platform_device *pdev)
 		led->cdev.pattern_clear = cht_wc_leds_pattern_clear;
 		led->cdev.max_brightness = 255;
 
-		ret = led_classdev_register(&pdev->dev, &led->cdev);
+		ret = devm_led_classdev_register(&pdev->dev, &led->cdev);
 		if (ret < 0)
 			return ret;
 	}
@@ -406,10 +406,6 @@ static int cht_wc_leds_probe(struct platform_device *pdev)
 static void cht_wc_leds_remove(struct platform_device *pdev)
 {
 	struct cht_wc_leds *leds = platform_get_drvdata(pdev);
-	int i;
-
-	for (i = 0; i < CHT_WC_LED_COUNT; i++)
-		led_classdev_unregister(&leds->leds[i].cdev);
 
 	/* Restore LED1 regs if hw-control was active else leave LED1 off */
 	if (!(leds->led1_initial_regs.ctrl & CHT_WC_LED1_SWCTL))
diff --git a/drivers/leds/leds-lp50xx.c b/drivers/leds/leds-lp50xx.c
index 175d4b06659b..e9eb0ad6751d 100644
--- a/drivers/leds/leds-lp50xx.c
+++ b/drivers/leds/leds-lp50xx.c
@@ -481,6 +481,7 @@ static int lp50xx_probe_dt(struct lp50xx *priv)
 		}
 
 		fwnode_for_each_child_node(child, led_node) {
+			int multi_index;
 			ret = fwnode_property_read_u32(led_node, "color",
 						       &color_id);
 			if (ret) {
@@ -488,8 +489,16 @@ static int lp50xx_probe_dt(struct lp50xx *priv)
 				dev_err(priv->dev, "Cannot read color\n");
 				goto child_out;
 			}
+			ret = fwnode_property_read_u32(led_node, "reg", &multi_index);
+			if (ret != 0) {
+				dev_err(priv->dev, "reg must be set\n");
+				return -EINVAL;
+			} else if (multi_index >= LP50XX_LEDS_PER_MODULE) {
+				dev_err(priv->dev, "reg %i out of range\n", multi_index);
+				return -EINVAL;
+			}
 
-			mc_led_info[num_colors].color_index = color_id;
+			mc_led_info[multi_index].color_index = color_id;
 			num_colors++;
 		}
 
diff --git a/drivers/leds/leds-lp8860.c b/drivers/leds/leds-lp8860.c
index 7a136fd81720..06196d851ade 100644
--- a/drivers/leds/leds-lp8860.c
+++ b/drivers/leds/leds-lp8860.c
@@ -265,7 +265,7 @@ static int lp8860_init(struct lp8860_led *led)
 		goto out;
 	}
 
-	reg_count = ARRAY_SIZE(lp8860_eeprom_disp_regs) / sizeof(lp8860_eeprom_disp_regs[0]);
+	reg_count = ARRAY_SIZE(lp8860_eeprom_disp_regs);
 	for (i = 0; i < reg_count; i++) {
 		ret = regmap_write(led->eeprom_regmap,
 				lp8860_eeprom_disp_regs[i].reg,
diff --git a/drivers/leds/leds-netxbig.c b/drivers/leds/leds-netxbig.c
index af5a908b8d9e..e95287416ef8 100644
--- a/drivers/leds/leds-netxbig.c
+++ b/drivers/leds/leds-netxbig.c
@@ -439,6 +439,7 @@ static int netxbig_leds_get_of_pdata(struct device *dev,
 	}
 	gpio_ext_pdev = of_find_device_by_node(gpio_ext_np);
 	if (!gpio_ext_pdev) {
+		of_node_put(gpio_ext_np);
 		dev_err(dev, "Failed to find platform device for gpio-ext\n");
 		return -ENODEV;
 	}
diff --git a/drivers/leds/rgb/leds-pwm-multicolor.c b/drivers/leds/rgb/leds-pwm-multicolor.c
index e1a81e0109e8..c0aa34b1d0e2 100644
--- a/drivers/leds/rgb/leds-pwm-multicolor.c
+++ b/drivers/leds/rgb/leds-pwm-multicolor.c
@@ -135,8 +135,11 @@ static int led_pwm_mc_probe(struct platform_device *pdev)
 
 	/* init the multicolor's LED class device */
 	cdev = &priv->mc_cdev.led_cdev;
-	fwnode_property_read_u32(mcnode, "max-brightness",
+	ret = fwnode_property_read_u32(mcnode, "max-brightness",
 				 &cdev->max_brightness);
+	if (ret)
+		goto release_mcnode;
+
 	cdev->flags = LED_CORE_SUSPENDRESUME;
 	cdev->brightness_set_blocking = led_pwm_mc_set;
 
diff --git a/drivers/leds/rgb/leds-qcom-lpg.c b/drivers/leds/rgb/leds-qcom-lpg.c
index f3c9ef2bfa57..5d8e27e2e7ae 100644
--- a/drivers/leds/rgb/leds-qcom-lpg.c
+++ b/drivers/leds/rgb/leds-qcom-lpg.c
@@ -461,7 +461,7 @@ static int lpg_calc_freq(struct lpg_channel *chan, uint64_t period)
 		max_res = LPG_RESOLUTION_9BIT;
 	}
 
-	min_period = div64_u64((u64)NSEC_PER_SEC * (1 << pwm_resolution_arr[0]),
+	min_period = div64_u64((u64)NSEC_PER_SEC * ((1 << pwm_resolution_arr[0]) - 1),
 			       clk_rate_arr[clk_len - 1]);
 	if (period <= min_period)
 		return -EINVAL;
@@ -482,7 +482,7 @@ static int lpg_calc_freq(struct lpg_channel *chan, uint64_t period)
 	 */
 
 	for (i = 0; i < pwm_resolution_count; i++) {
-		resolution = 1 << pwm_resolution_arr[i];
+		resolution = (1 << pwm_resolution_arr[i]) - 1;
 		for (clk_sel = 1; clk_sel < clk_len; clk_sel++) {
 			u64 numerator = period * clk_rate_arr[clk_sel];
 
@@ -529,7 +529,7 @@ static void lpg_calc_duty(struct lpg_channel *chan, uint64_t duty)
 	unsigned int clk_rate;
 
 	if (chan->subtype == LPG_SUBTYPE_HI_RES_PWM) {
-		max = LPG_RESOLUTION_15BIT - 1;
+		max = BIT(lpg_pwm_resolution_hi_res[chan->pwm_resolution_sel]) - 1;
 		clk_rate = lpg_clk_rates_hi_res[chan->clk_sel];
 	} else {
 		max = LPG_RESOLUTION_9BIT - 1;
@@ -1291,7 +1291,7 @@ static int lpg_pwm_get_state(struct pwm_chip *chip, struct pwm_device *pwm,
 		if (ret)
 			return ret;
 
-		state->period = DIV_ROUND_UP_ULL((u64)NSEC_PER_SEC * (1 << resolution) *
+		state->period = DIV_ROUND_UP_ULL((u64)NSEC_PER_SEC * ((1 << resolution) - 1) *
 						 pre_div * (1 << m), refclk);
 		state->duty_cycle = DIV_ROUND_UP_ULL((u64)NSEC_PER_SEC * pwm_value * pre_div * (1 << m), refclk);
 	} else {
diff --git a/drivers/mailbox/imx-mailbox.c b/drivers/mailbox/imx-mailbox.c
index f815dab3be50..0657bd3d8f97 100644
--- a/drivers/mailbox/imx-mailbox.c
+++ b/drivers/mailbox/imx-mailbox.c
@@ -226,7 +226,7 @@ static int imx_mu_generic_tx(struct imx_mu_priv *priv,
 {
 	u32 *arg = data;
 	u32 val;
-	int ret;
+	int ret, count;
 
 	switch (cp->type) {
 	case IMX_MU_TYPE_TX:
@@ -240,11 +240,20 @@ static int imx_mu_generic_tx(struct imx_mu_priv *priv,
 	case IMX_MU_TYPE_TXDB_V2:
 		imx_mu_write(priv, IMX_MU_xCR_GIRn(priv->dcfg->type, cp->idx),
 			     priv->dcfg->xCR[IMX_MU_GCR]);
-		ret = readl_poll_timeout(priv->base + priv->dcfg->xCR[IMX_MU_GCR], val,
-					 !(val & IMX_MU_xCR_GIRn(priv->dcfg->type, cp->idx)),
-					 0, 1000);
-		if (ret)
-			dev_warn_ratelimited(priv->dev, "channel type: %d failure\n", cp->type);
+		ret = -ETIMEDOUT;
+		count = 0;
+		while (ret && (count < 10)) {
+			ret =
+			readl_poll_timeout(priv->base + priv->dcfg->xCR[IMX_MU_GCR], val,
+					   !(val & IMX_MU_xCR_GIRn(priv->dcfg->type, cp->idx)),
+					   0, 10000);
+
+			if (ret) {
+				dev_warn_ratelimited(priv->dev,
+						     "channel type: %d timeout, %d times, retry\n",
+						     cp->type, ++count);
+			}
+		}
 		break;
 	default:
 		dev_warn_ratelimited(priv->dev, "Send data on wrong channel type: %d\n", cp->type);
diff --git a/drivers/mailbox/mailbox.c b/drivers/mailbox/mailbox.c
index d3d26a2c9895..92c2fb618c8e 100644
--- a/drivers/mailbox/mailbox.c
+++ b/drivers/mailbox/mailbox.c
@@ -415,11 +415,12 @@ struct mbox_chan *mbox_request_channel(struct mbox_client *cl, int index)
 
 	mutex_lock(&con_mutex);
 
-	if (of_parse_phandle_with_args(dev->of_node, "mboxes",
-				       "#mbox-cells", index, &spec)) {
+	ret = of_parse_phandle_with_args(dev->of_node, "mboxes", "#mbox-cells",
+					 index, &spec);
+	if (ret) {
 		dev_dbg(dev, "%s: can't parse \"mboxes\" property\n", __func__);
 		mutex_unlock(&con_mutex);
-		return ERR_PTR(-ENODEV);
+		return ERR_PTR(ret);
 	}
 
 	chan = ERR_PTR(-EPROBE_DEFER);
@@ -489,8 +490,8 @@ void mbox_free_channel(struct mbox_chan *chan)
 	if (chan->txdone_method == TXDONE_BY_ACK)
 		chan->txdone_method = TXDONE_BY_POLL;
 
-	module_put(chan->mbox->dev->driver->owner);
 	spin_unlock_irqrestore(&chan->lock, flags);
+	module_put(chan->mbox->dev->driver->owner);
 }
 EXPORT_SYMBOL_GPL(mbox_free_channel);
 
diff --git a/drivers/mailbox/mtk-cmdq-mailbox.c b/drivers/mailbox/mtk-cmdq-mailbox.c
index 9c43ed9bdd37..d24f71819c3d 100644
--- a/drivers/mailbox/mtk-cmdq-mailbox.c
+++ b/drivers/mailbox/mtk-cmdq-mailbox.c
@@ -92,18 +92,6 @@ struct gce_plat {
 	u32 gce_num;
 };
 
-static void cmdq_sw_ddr_enable(struct cmdq *cmdq, bool enable)
-{
-	WARN_ON(clk_bulk_enable(cmdq->pdata->gce_num, cmdq->clocks));
-
-	if (enable)
-		writel(GCE_DDR_EN | GCE_CTRL_BY_SW, cmdq->base + GCE_GCTL_VALUE);
-	else
-		writel(GCE_CTRL_BY_SW, cmdq->base + GCE_GCTL_VALUE);
-
-	clk_bulk_disable(cmdq->pdata->gce_num, cmdq->clocks);
-}
-
 u8 cmdq_get_shift_pa(struct mbox_chan *chan)
 {
 	struct cmdq *cmdq = container_of(chan->mbox, struct cmdq, mbox);
@@ -112,6 +100,19 @@ u8 cmdq_get_shift_pa(struct mbox_chan *chan)
 }
 EXPORT_SYMBOL(cmdq_get_shift_pa);
 
+static void cmdq_gctl_value_toggle(struct cmdq *cmdq, bool ddr_enable)
+{
+	u32 val = cmdq->pdata->control_by_sw ? GCE_CTRL_BY_SW : 0;
+
+	if (!cmdq->pdata->control_by_sw && !cmdq->pdata->sw_ddr_en)
+		return;
+
+	if (cmdq->pdata->sw_ddr_en && ddr_enable)
+		val |= GCE_DDR_EN;
+
+	writel(val, cmdq->base + GCE_GCTL_VALUE);
+}
+
 static int cmdq_thread_suspend(struct cmdq *cmdq, struct cmdq_thread *thread)
 {
 	u32 status;
@@ -140,16 +141,10 @@ static void cmdq_thread_resume(struct cmdq_thread *thread)
 static void cmdq_init(struct cmdq *cmdq)
 {
 	int i;
-	u32 gctl_regval = 0;
 
 	WARN_ON(clk_bulk_enable(cmdq->pdata->gce_num, cmdq->clocks));
-	if (cmdq->pdata->control_by_sw)
-		gctl_regval = GCE_CTRL_BY_SW;
-	if (cmdq->pdata->sw_ddr_en)
-		gctl_regval |= GCE_DDR_EN;
 
-	if (gctl_regval)
-		writel(gctl_regval, cmdq->base + GCE_GCTL_VALUE);
+	cmdq_gctl_value_toggle(cmdq, true);
 
 	writel(CMDQ_THR_ACTIVE_SLOT_CYCLES, cmdq->base + CMDQ_THR_SLOT_CYCLES);
 	for (i = 0; i <= CMDQ_MAX_EVENT; i++)
@@ -315,14 +310,21 @@ static irqreturn_t cmdq_irq_handler(int irq, void *dev)
 static int cmdq_runtime_resume(struct device *dev)
 {
 	struct cmdq *cmdq = dev_get_drvdata(dev);
+	int ret;
 
-	return clk_bulk_enable(cmdq->pdata->gce_num, cmdq->clocks);
+	ret = clk_bulk_enable(cmdq->pdata->gce_num, cmdq->clocks);
+	if (ret)
+		return ret;
+
+	cmdq_gctl_value_toggle(cmdq, true);
+	return 0;
 }
 
 static int cmdq_runtime_suspend(struct device *dev)
 {
 	struct cmdq *cmdq = dev_get_drvdata(dev);
 
+	cmdq_gctl_value_toggle(cmdq, false);
 	clk_bulk_disable(cmdq->pdata->gce_num, cmdq->clocks);
 	return 0;
 }
@@ -347,9 +349,6 @@ static int cmdq_suspend(struct device *dev)
 	if (task_running)
 		dev_warn(dev, "exist running task(s) in suspend\n");
 
-	if (cmdq->pdata->sw_ddr_en)
-		cmdq_sw_ddr_enable(cmdq, false);
-
 	return pm_runtime_force_suspend(dev);
 }
 
@@ -360,9 +359,6 @@ static int cmdq_resume(struct device *dev)
 	WARN_ON(pm_runtime_force_resume(dev));
 	cmdq->suspended = false;
 
-	if (cmdq->pdata->sw_ddr_en)
-		cmdq_sw_ddr_enable(cmdq, true);
-
 	return 0;
 }
 
@@ -370,9 +366,6 @@ static void cmdq_remove(struct platform_device *pdev)
 {
 	struct cmdq *cmdq = platform_get_drvdata(pdev);
 
-	if (cmdq->pdata->sw_ddr_en)
-		cmdq_sw_ddr_enable(cmdq, false);
-
 	if (!IS_ENABLED(CONFIG_PM))
 		cmdq_runtime_suspend(&pdev->dev);
 
diff --git a/drivers/mailbox/pcc.c b/drivers/mailbox/pcc.c
index 82102a4c5d68..49254d99a8ad 100644
--- a/drivers/mailbox/pcc.c
+++ b/drivers/mailbox/pcc.c
@@ -313,6 +313,10 @@ static irqreturn_t pcc_mbox_irq(int irq, void *p)
 	int ret;
 
 	pchan = chan->con_priv;
+
+	if (pcc_chan_reg_read_modify_write(&pchan->plat_irq_ack))
+		return IRQ_NONE;
+
 	if (pchan->type == ACPI_PCCT_TYPE_EXT_PCC_MASTER_SUBSPACE &&
 	    !pchan->chan_in_use)
 		return IRQ_NONE;
@@ -330,13 +334,16 @@ static irqreturn_t pcc_mbox_irq(int irq, void *p)
 		return IRQ_NONE;
 	}
 
-	if (pcc_chan_reg_read_modify_write(&pchan->plat_irq_ack))
-		return IRQ_NONE;
-
+	/*
+	 * Clear this flag after updating interrupt ack register and just
+	 * before mbox_chan_received_data() which might call pcc_send_data()
+	 * where the flag is set again to start new transfer. This is
+	 * required to avoid any possible race in updatation of this flag.
+	 */
+	pchan->chan_in_use = false;
 	mbox_chan_received_data(chan, NULL);
 
 	check_and_ack(pchan, chan);
-	pchan->chan_in_use = false;
 
 	return IRQ_HANDLED;
 }
@@ -412,8 +419,12 @@ int pcc_mbox_ioremap(struct mbox_chan *chan)
 		return -1;
 	pchan_info = chan->con_priv;
 	pcc_mbox_chan = &pchan_info->chan;
-	pcc_mbox_chan->shmem = ioremap(pcc_mbox_chan->shmem_base_addr,
-				       pcc_mbox_chan->shmem_size);
+
+	pcc_mbox_chan->shmem = acpi_os_ioremap(pcc_mbox_chan->shmem_base_addr,
+					       pcc_mbox_chan->shmem_size);
+	if (!pcc_mbox_chan->shmem)
+		return -ENXIO;
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(pcc_mbox_ioremap);
diff --git a/drivers/mailbox/tegra-hsp.c b/drivers/mailbox/tegra-hsp.c
index 19ef56cbcfd3..76f54f8b6b6c 100644
--- a/drivers/mailbox/tegra-hsp.c
+++ b/drivers/mailbox/tegra-hsp.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Copyright (c) 2016-2023, NVIDIA CORPORATION.  All rights reserved.
+ * Copyright (c) 2016-2025, NVIDIA CORPORATION.  All rights reserved.
  */
 
 #include <linux/delay.h>
@@ -28,12 +28,6 @@
 #define HSP_INT_FULL_MASK	0xff
 
 #define HSP_INT_DIMENSIONING	0x380
-#define HSP_nSM_SHIFT		0
-#define HSP_nSS_SHIFT		4
-#define HSP_nAS_SHIFT		8
-#define HSP_nDB_SHIFT		12
-#define HSP_nSI_SHIFT		16
-#define HSP_nINT_MASK		0xf
 
 #define HSP_DB_TRIGGER	0x0
 #define HSP_DB_ENABLE	0x4
@@ -97,6 +91,20 @@ struct tegra_hsp_soc {
 	bool has_per_mb_ie;
 	bool has_128_bit_mb;
 	unsigned int reg_stride;
+
+	/* Shifts for dimensioning register. */
+	unsigned int si_shift;
+	unsigned int db_shift;
+	unsigned int as_shift;
+	unsigned int ss_shift;
+	unsigned int sm_shift;
+
+	/* Masks for dimensioning register. */
+	unsigned int si_mask;
+	unsigned int db_mask;
+	unsigned int as_mask;
+	unsigned int ss_mask;
+	unsigned int sm_mask;
 };
 
 struct tegra_hsp {
@@ -388,7 +396,6 @@ static void tegra_hsp_sm_recv32(struct tegra_hsp_channel *channel)
 	value = tegra_hsp_channel_readl(channel, HSP_SM_SHRD_MBOX);
 	value &= ~HSP_SM_SHRD_MBOX_FULL;
 	msg = (void *)(unsigned long)value;
-	mbox_chan_received_data(channel->chan, msg);
 
 	/*
 	 * Need to clear all bits here since some producers, such as TCU, depend
@@ -398,6 +405,8 @@ static void tegra_hsp_sm_recv32(struct tegra_hsp_channel *channel)
 	 * explicitly, so we have to make sure we cover all possible cases.
 	 */
 	tegra_hsp_channel_writel(channel, 0x0, HSP_SM_SHRD_MBOX);
+
+	mbox_chan_received_data(channel->chan, msg);
 }
 
 static const struct tegra_hsp_sm_ops tegra_hsp_sm_32bit_ops = {
@@ -433,7 +442,6 @@ static void tegra_hsp_sm_recv128(struct tegra_hsp_channel *channel)
 	value[3] = tegra_hsp_channel_readl(channel, HSP_SHRD_MBOX_TYPE1_DATA3);
 
 	msg = (void *)(unsigned long)value;
-	mbox_chan_received_data(channel->chan, msg);
 
 	/*
 	 * Clear data registers and tag.
@@ -443,6 +451,8 @@ static void tegra_hsp_sm_recv128(struct tegra_hsp_channel *channel)
 	tegra_hsp_channel_writel(channel, 0x0, HSP_SHRD_MBOX_TYPE1_DATA2);
 	tegra_hsp_channel_writel(channel, 0x0, HSP_SHRD_MBOX_TYPE1_DATA3);
 	tegra_hsp_channel_writel(channel, 0x0, HSP_SHRD_MBOX_TYPE1_TAG);
+
+	mbox_chan_received_data(channel->chan, msg);
 }
 
 static const struct tegra_hsp_sm_ops tegra_hsp_sm_128bit_ops = {
@@ -745,11 +755,11 @@ static int tegra_hsp_probe(struct platform_device *pdev)
 		return PTR_ERR(hsp->regs);
 
 	value = tegra_hsp_readl(hsp, HSP_INT_DIMENSIONING);
-	hsp->num_sm = (value >> HSP_nSM_SHIFT) & HSP_nINT_MASK;
-	hsp->num_ss = (value >> HSP_nSS_SHIFT) & HSP_nINT_MASK;
-	hsp->num_as = (value >> HSP_nAS_SHIFT) & HSP_nINT_MASK;
-	hsp->num_db = (value >> HSP_nDB_SHIFT) & HSP_nINT_MASK;
-	hsp->num_si = (value >> HSP_nSI_SHIFT) & HSP_nINT_MASK;
+	hsp->num_sm = (value >> hsp->soc->sm_shift) & hsp->soc->sm_mask;
+	hsp->num_ss = (value >> hsp->soc->ss_shift) & hsp->soc->ss_mask;
+	hsp->num_as = (value >> hsp->soc->as_shift) & hsp->soc->as_mask;
+	hsp->num_db = (value >> hsp->soc->db_shift) & hsp->soc->db_mask;
+	hsp->num_si = (value >> hsp->soc->si_shift) & hsp->soc->si_mask;
 
 	err = platform_get_irq_byname_optional(pdev, "doorbell");
 	if (err >= 0)
@@ -913,6 +923,16 @@ static const struct tegra_hsp_soc tegra186_hsp_soc = {
 	.has_per_mb_ie = false,
 	.has_128_bit_mb = false,
 	.reg_stride = 0x100,
+	.si_shift = 16,
+	.db_shift = 12,
+	.as_shift = 8,
+	.ss_shift = 4,
+	.sm_shift = 0,
+	.si_mask = 0xf,
+	.db_mask = 0xf,
+	.as_mask = 0xf,
+	.ss_mask = 0xf,
+	.sm_mask = 0xf,
 };
 
 static const struct tegra_hsp_soc tegra194_hsp_soc = {
@@ -920,6 +940,16 @@ static const struct tegra_hsp_soc tegra194_hsp_soc = {
 	.has_per_mb_ie = true,
 	.has_128_bit_mb = false,
 	.reg_stride = 0x100,
+	.si_shift = 16,
+	.db_shift = 12,
+	.as_shift = 8,
+	.ss_shift = 4,
+	.sm_shift = 0,
+	.si_mask = 0xf,
+	.db_mask = 0xf,
+	.as_mask = 0xf,
+	.ss_mask = 0xf,
+	.sm_mask = 0xf,
 };
 
 static const struct tegra_hsp_soc tegra234_hsp_soc = {
@@ -927,6 +957,16 @@ static const struct tegra_hsp_soc tegra234_hsp_soc = {
 	.has_per_mb_ie = false,
 	.has_128_bit_mb = true,
 	.reg_stride = 0x100,
+	.si_shift = 16,
+	.db_shift = 12,
+	.as_shift = 8,
+	.ss_shift = 4,
+	.sm_shift = 0,
+	.si_mask = 0xf,
+	.db_mask = 0xf,
+	.as_mask = 0xf,
+	.ss_mask = 0xf,
+	.sm_mask = 0xf,
 };
 
 static const struct tegra_hsp_soc tegra264_hsp_soc = {
@@ -934,6 +974,16 @@ static const struct tegra_hsp_soc tegra264_hsp_soc = {
 	.has_per_mb_ie = false,
 	.has_128_bit_mb = true,
 	.reg_stride = 0x1000,
+	.si_shift = 17,
+	.db_shift = 12,
+	.as_shift = 8,
+	.ss_shift = 4,
+	.sm_shift = 0,
+	.si_mask = 0x1f,
+	.db_mask = 0x1f,
+	.as_mask = 0xf,
+	.ss_mask = 0xf,
+	.sm_mask = 0xf,
 };
 
 static const struct of_device_id tegra_hsp_match[] = {
diff --git a/drivers/mailbox/zynqmp-ipi-mailbox.c b/drivers/mailbox/zynqmp-ipi-mailbox.c
index 521d08b9ab47..d59fcb74b347 100644
--- a/drivers/mailbox/zynqmp-ipi-mailbox.c
+++ b/drivers/mailbox/zynqmp-ipi-mailbox.c
@@ -905,7 +905,7 @@ static int zynqmp_ipi_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct device_node *nc, *np = pdev->dev.of_node;
-	struct zynqmp_ipi_pdata __percpu *pdata;
+	struct zynqmp_ipi_pdata *pdata;
 	struct of_phandle_args out_irq;
 	struct zynqmp_ipi_mbox *mbox;
 	int num_mboxes, ret = -EINVAL;
diff --git a/drivers/mcb/mcb-parse.c b/drivers/mcb/mcb-parse.c
index a5f8ab9a0910..7acff8e02eb4 100644
--- a/drivers/mcb/mcb-parse.c
+++ b/drivers/mcb/mcb-parse.c
@@ -96,7 +96,7 @@ static int chameleon_parse_gdd(struct mcb_bus *bus,
 
 	ret = mcb_device_register(bus, mdev);
 	if (ret < 0)
-		goto err;
+		return ret;
 
 	return 0;
 
diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig
index 1e9db8e4acdf..0b1870a09e1f 100644
--- a/drivers/md/Kconfig
+++ b/drivers/md/Kconfig
@@ -61,6 +61,19 @@ config MD_BITMAP_FILE
 	  various kernel APIs and can only work with files on a file system not
 	  actually sitting on the MD device.
 
+config MD_LINEAR
+	tristate "Linear (append) mode"
+	depends on BLK_DEV_MD
+	help
+	  If you say Y here, then your multiple devices driver will be able to
+	  use the so-called linear mode, i.e. it will combine the hard disk
+	  partitions by simply appending one to the other.
+
+	  To compile this as a module, choose M here: the module
+	  will be called linear.
+
+	  If unsure, say Y.
+
 config MD_RAID0
 	tristate "RAID-0 (striping) mode"
 	depends on BLK_DEV_MD
diff --git a/drivers/md/Makefile b/drivers/md/Makefile
index 476a214e4bdc..87bdfc9fe14c 100644
--- a/drivers/md/Makefile
+++ b/drivers/md/Makefile
@@ -29,12 +29,14 @@ dm-zoned-y	+= dm-zoned-target.o dm-zoned-metadata.o dm-zoned-reclaim.o
 
 md-mod-y	+= md.o md-bitmap.o
 raid456-y	+= raid5.o raid5-cache.o raid5-ppl.o
+linear-y       += md-linear.o
 
 # Note: link order is important.  All raid personalities
 # and must come before md.o, as they each initialise
 # themselves, and md.o may use the personalities when it
 # auto-initialised.
 
+obj-$(CONFIG_MD_LINEAR)		+= linear.o
 obj-$(CONFIG_MD_RAID0)		+= raid0.o
 obj-$(CONFIG_MD_RAID1)		+= raid1.o
 obj-$(CONFIG_MD_RAID10)		+= raid10.o
diff --git a/drivers/md/bcache/alloc.c b/drivers/md/bcache/alloc.c
index da50f6661bae..48ce750bf70a 100644
--- a/drivers/md/bcache/alloc.c
+++ b/drivers/md/bcache/alloc.c
@@ -164,68 +164,40 @@ static void bch_invalidate_one_bucket(struct cache *ca, struct bucket *b)
  * prio is worth 1/8th of what INITIAL_PRIO is worth.
  */
 
-static inline unsigned int new_bucket_prio(struct cache *ca, struct bucket *b)
-{
-	unsigned int min_prio = (INITIAL_PRIO - ca->set->min_prio) / 8;
-
-	return (b->prio - ca->set->min_prio + min_prio) * GC_SECTORS_USED(b);
-}
-
-static inline bool new_bucket_max_cmp(const void *l, const void *r, void *args)
-{
-	struct bucket **lhs = (struct bucket **)l;
-	struct bucket **rhs = (struct bucket **)r;
-	struct cache *ca = args;
-
-	return new_bucket_prio(ca, *lhs) > new_bucket_prio(ca, *rhs);
-}
-
-static inline bool new_bucket_min_cmp(const void *l, const void *r, void *args)
-{
-	struct bucket **lhs = (struct bucket **)l;
-	struct bucket **rhs = (struct bucket **)r;
-	struct cache *ca = args;
-
-	return new_bucket_prio(ca, *lhs) < new_bucket_prio(ca, *rhs);
-}
-
-static inline void new_bucket_swap(void *l, void *r, void __always_unused *args)
-{
-	struct bucket **lhs = l, **rhs = r;
+#define bucket_prio(b)							\
+({									\
+	unsigned int min_prio = (INITIAL_PRIO - ca->set->min_prio) / 8;	\
+									\
+	(b->prio - ca->set->min_prio + min_prio) * GC_SECTORS_USED(b);	\
+})
 
-	swap(*lhs, *rhs);
-}
+#define bucket_max_cmp(l, r)	(bucket_prio(l) < bucket_prio(r))
+#define bucket_min_cmp(l, r)	(bucket_prio(l) > bucket_prio(r))
 
 static void invalidate_buckets_lru(struct cache *ca)
 {
 	struct bucket *b;
-	const struct min_heap_callbacks bucket_max_cmp_callback = {
-		.less = new_bucket_max_cmp,
-		.swp = new_bucket_swap,
-	};
-	const struct min_heap_callbacks bucket_min_cmp_callback = {
-		.less = new_bucket_min_cmp,
-		.swp = new_bucket_swap,
-	};
+	ssize_t i;
 
-	ca->heap.nr = 0;
+	ca->heap.used = 0;
 
 	for_each_bucket(b, ca) {
 		if (!bch_can_invalidate_bucket(ca, b))
 			continue;
 
-		if (!min_heap_full(&ca->heap))
-			min_heap_push(&ca->heap, &b, &bucket_max_cmp_callback, ca);
-		else if (!new_bucket_max_cmp(&b, min_heap_peek(&ca->heap), ca)) {
+		if (!heap_full(&ca->heap))
+			heap_add(&ca->heap, b, bucket_max_cmp);
+		else if (bucket_max_cmp(b, heap_peek(&ca->heap))) {
 			ca->heap.data[0] = b;
-			min_heap_sift_down(&ca->heap, 0, &bucket_max_cmp_callback, ca);
+			heap_sift(&ca->heap, 0, bucket_max_cmp);
 		}
 	}
 
-	min_heapify_all(&ca->heap, &bucket_min_cmp_callback, ca);
+	for (i = ca->heap.used / 2 - 1; i >= 0; --i)
+		heap_sift(&ca->heap, i, bucket_min_cmp);
 
 	while (!fifo_full(&ca->free_inc)) {
-		if (!ca->heap.nr) {
+		if (!heap_pop(&ca->heap, b, bucket_min_cmp)) {
 			/*
 			 * We don't want to be calling invalidate_buckets()
 			 * multiple times when it can't do anything
@@ -234,8 +206,6 @@ static void invalidate_buckets_lru(struct cache *ca)
 			wake_up_gc(ca->set);
 			return;
 		}
-		b = min_heap_peek(&ca->heap)[0];
-		min_heap_pop(&ca->heap, &bucket_min_cmp_callback, ca);
 
 		bch_invalidate_one_bucket(ca, b);
 	}
diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index 785b0d9008fa..1d33e40d26ea 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -458,7 +458,7 @@ struct cache {
 	/* Allocation stuff: */
 	struct bucket		*buckets;
 
-	DEFINE_MIN_HEAP(struct bucket *, cache_heap) heap;
+	DECLARE_HEAP(struct bucket *, heap);
 
 	/*
 	 * If nonzero, we know we aren't going to find any buckets to invalidate
diff --git a/drivers/md/bcache/bset.c b/drivers/md/bcache/bset.c
index bd97d8626887..463eb13bd0b2 100644
--- a/drivers/md/bcache/bset.c
+++ b/drivers/md/bcache/bset.c
@@ -54,11 +54,9 @@ void bch_dump_bucket(struct btree_keys *b)
 int __bch_count_data(struct btree_keys *b)
 {
 	unsigned int ret = 0;
-	struct btree_iter iter;
+	struct btree_iter_stack iter;
 	struct bkey *k;
 
-	min_heap_init(&iter.heap, NULL, MAX_BSETS);
-
 	if (b->ops->is_extents)
 		for_each_key(b, k, &iter)
 			ret += KEY_SIZE(k);
@@ -69,11 +67,9 @@ void __bch_check_keys(struct btree_keys *b, const char *fmt, ...)
 {
 	va_list args;
 	struct bkey *k, *p = NULL;
-	struct btree_iter iter;
+	struct btree_iter_stack iter;
 	const char *err;
 
-	min_heap_init(&iter.heap, NULL, MAX_BSETS);
-
 	for_each_key(b, k, &iter) {
 		if (b->ops->is_extents) {
 			err = "Keys out of order";
@@ -114,9 +110,9 @@ bug:
 
 static void bch_btree_iter_next_check(struct btree_iter *iter)
 {
-	struct bkey *k = iter->heap.data->k, *next = bkey_next(k);
+	struct bkey *k = iter->data->k, *next = bkey_next(k);
 
-	if (next < iter->heap.data->end &&
+	if (next < iter->data->end &&
 	    bkey_cmp(k, iter->b->ops->is_extents ?
 		     &START_KEY(next) : next) > 0) {
 		bch_dump_bucket(iter->b);
@@ -883,14 +879,12 @@ unsigned int bch_btree_insert_key(struct btree_keys *b, struct bkey *k,
 	unsigned int status = BTREE_INSERT_STATUS_NO_INSERT;
 	struct bset *i = bset_tree_last(b)->data;
 	struct bkey *m, *prev = NULL;
-	struct btree_iter iter;
+	struct btree_iter_stack iter;
 	struct bkey preceding_key_on_stack = ZERO_KEY;
 	struct bkey *preceding_key_p = &preceding_key_on_stack;
 
 	BUG_ON(b->ops->is_extents && !KEY_SIZE(k));
 
-	min_heap_init(&iter.heap, NULL, MAX_BSETS);
-
 	/*
 	 * If k has preceding key, preceding_key_p will be set to address
 	 *  of k's preceding key; otherwise preceding_key_p will be set
@@ -901,9 +895,9 @@ unsigned int bch_btree_insert_key(struct btree_keys *b, struct bkey *k,
 	else
 		preceding_key(k, &preceding_key_p);
 
-	m = bch_btree_iter_init(b, &iter, preceding_key_p);
+	m = bch_btree_iter_stack_init(b, &iter, preceding_key_p);
 
-	if (b->ops->insert_fixup(b, k, &iter, replace_key))
+	if (b->ops->insert_fixup(b, k, &iter.iter, replace_key))
 		return status;
 
 	status = BTREE_INSERT_STATUS_INSERT;
@@ -1083,102 +1077,79 @@ struct bkey *__bch_bset_search(struct btree_keys *b, struct bset_tree *t,
 
 /* Btree iterator */
 
-typedef bool (new_btree_iter_cmp_fn)(const void *, const void *, void *);
-
-static inline bool new_btree_iter_cmp(const void *l, const void *r, void __always_unused *args)
-{
-	const struct btree_iter_set *_l = l;
-	const struct btree_iter_set *_r = r;
-
-	return bkey_cmp(_l->k, _r->k) <= 0;
-}
+typedef bool (btree_iter_cmp_fn)(struct btree_iter_set,
+				 struct btree_iter_set);
 
-static inline void new_btree_iter_swap(void *iter1, void *iter2, void __always_unused *args)
+static inline bool btree_iter_cmp(struct btree_iter_set l,
+				  struct btree_iter_set r)
 {
-	struct btree_iter_set *_iter1 = iter1;
-	struct btree_iter_set *_iter2 = iter2;
-
-	swap(*_iter1, *_iter2);
+	return bkey_cmp(l.k, r.k) > 0;
 }
 
 static inline bool btree_iter_end(struct btree_iter *iter)
 {
-	return !iter->heap.nr;
+	return !iter->used;
 }
 
 void bch_btree_iter_push(struct btree_iter *iter, struct bkey *k,
 			 struct bkey *end)
 {
-	const struct min_heap_callbacks callbacks = {
-		.less = new_btree_iter_cmp,
-		.swp = new_btree_iter_swap,
-	};
-
 	if (k != end)
-		BUG_ON(!min_heap_push(&iter->heap,
-				 &((struct btree_iter_set) { k, end }),
-				 &callbacks,
-				 NULL));
+		BUG_ON(!heap_add(iter,
+				 ((struct btree_iter_set) { k, end }),
+				 btree_iter_cmp));
 }
 
-static struct bkey *__bch_btree_iter_init(struct btree_keys *b,
-					  struct btree_iter *iter,
-					  struct bkey *search,
-					  struct bset_tree *start)
+static struct bkey *__bch_btree_iter_stack_init(struct btree_keys *b,
+						struct btree_iter_stack *iter,
+						struct bkey *search,
+						struct bset_tree *start)
 {
 	struct bkey *ret = NULL;
 
-	iter->heap.size = ARRAY_SIZE(iter->heap.preallocated);
-	iter->heap.nr = 0;
+	iter->iter.size = ARRAY_SIZE(iter->stack_data);
+	iter->iter.used = 0;
 
 #ifdef CONFIG_BCACHE_DEBUG
-	iter->b = b;
+	iter->iter.b = b;
 #endif
 
 	for (; start <= bset_tree_last(b); start++) {
 		ret = bch_bset_search(b, start, search);
-		bch_btree_iter_push(iter, ret, bset_bkey_last(start->data));
+		bch_btree_iter_push(&iter->iter, ret, bset_bkey_last(start->data));
 	}
 
 	return ret;
 }
 
-struct bkey *bch_btree_iter_init(struct btree_keys *b,
-				 struct btree_iter *iter,
+struct bkey *bch_btree_iter_stack_init(struct btree_keys *b,
+				 struct btree_iter_stack *iter,
 				 struct bkey *search)
 {
-	return __bch_btree_iter_init(b, iter, search, b->set);
+	return __bch_btree_iter_stack_init(b, iter, search, b->set);
 }
 
 static inline struct bkey *__bch_btree_iter_next(struct btree_iter *iter,
-						 new_btree_iter_cmp_fn *cmp)
+						 btree_iter_cmp_fn *cmp)
 {
 	struct btree_iter_set b __maybe_unused;
 	struct bkey *ret = NULL;
-	const struct min_heap_callbacks callbacks = {
-		.less = cmp,
-		.swp = new_btree_iter_swap,
-	};
 
 	if (!btree_iter_end(iter)) {
 		bch_btree_iter_next_check(iter);
 
-		ret = iter->heap.data->k;
-		iter->heap.data->k = bkey_next(iter->heap.data->k);
+		ret = iter->data->k;
+		iter->data->k = bkey_next(iter->data->k);
 
-		if (iter->heap.data->k > iter->heap.data->end) {
+		if (iter->data->k > iter->data->end) {
 			WARN_ONCE(1, "bset was corrupt!\n");
-			iter->heap.data->k = iter->heap.data->end;
+			iter->data->k = iter->data->end;
 		}
 
-		if (iter->heap.data->k == iter->heap.data->end) {
-			if (iter->heap.nr) {
-				b = min_heap_peek(&iter->heap)[0];
-				min_heap_pop(&iter->heap, &callbacks, NULL);
-			}
-		}
+		if (iter->data->k == iter->data->end)
+			heap_pop(iter, b, cmp);
 		else
-			min_heap_sift_down(&iter->heap, 0, &callbacks, NULL);
+			heap_sift(iter, 0, cmp);
 	}
 
 	return ret;
@@ -1186,7 +1157,7 @@ static inline struct bkey *__bch_btree_iter_next(struct btree_iter *iter,
 
 struct bkey *bch_btree_iter_next(struct btree_iter *iter)
 {
-	return __bch_btree_iter_next(iter, new_btree_iter_cmp);
+	return __bch_btree_iter_next(iter, btree_iter_cmp);
 
 }
 
@@ -1224,18 +1195,16 @@ static void btree_mergesort(struct btree_keys *b, struct bset *out,
 			    struct btree_iter *iter,
 			    bool fixup, bool remove_stale)
 {
+	int i;
 	struct bkey *k, *last = NULL;
 	BKEY_PADDED(k) tmp;
 	bool (*bad)(struct btree_keys *, const struct bkey *) = remove_stale
 		? bch_ptr_bad
 		: bch_ptr_invalid;
-	const struct min_heap_callbacks callbacks = {
-		.less = b->ops->sort_cmp,
-		.swp = new_btree_iter_swap,
-	};
 
 	/* Heapify the iterator, using our comparison function */
-	min_heapify_all(&iter->heap, &callbacks, NULL);
+	for (i = iter->used / 2 - 1; i >= 0; --i)
+		heap_sift(iter, i, b->ops->sort_cmp);
 
 	while (!btree_iter_end(iter)) {
 		if (b->ops->sort_fixup && fixup)
@@ -1324,11 +1293,10 @@ void bch_btree_sort_partial(struct btree_keys *b, unsigned int start,
 			    struct bset_sort_state *state)
 {
 	size_t order = b->page_order, keys = 0;
-	struct btree_iter iter;
+	struct btree_iter_stack iter;
 	int oldsize = bch_count_data(b);
 
-	min_heap_init(&iter.heap, NULL, MAX_BSETS);
-	__bch_btree_iter_init(b, &iter, NULL, &b->set[start]);
+	__bch_btree_iter_stack_init(b, &iter, NULL, &b->set[start]);
 
 	if (start) {
 		unsigned int i;
@@ -1339,7 +1307,7 @@ void bch_btree_sort_partial(struct btree_keys *b, unsigned int start,
 		order = get_order(__set_bytes(b->set->data, keys));
 	}
 
-	__btree_sort(b, &iter, start, order, false, state);
+	__btree_sort(b, &iter.iter, start, order, false, state);
 
 	EBUG_ON(oldsize >= 0 && bch_count_data(b) != oldsize);
 }
@@ -1355,13 +1323,11 @@ void bch_btree_sort_into(struct btree_keys *b, struct btree_keys *new,
 			 struct bset_sort_state *state)
 {
 	uint64_t start_time = local_clock();
-	struct btree_iter iter;
-
-	min_heap_init(&iter.heap, NULL, MAX_BSETS);
+	struct btree_iter_stack iter;
 
-	bch_btree_iter_init(b, &iter, NULL);
+	bch_btree_iter_stack_init(b, &iter, NULL);
 
-	btree_mergesort(b, new->set->data, &iter, false, true);
+	btree_mergesort(b, new->set->data, &iter.iter, false, true);
 
 	bch_time_stats_update(&state->time, start_time);
 
diff --git a/drivers/md/bcache/bset.h b/drivers/md/bcache/bset.h
index f79441acd4c1..011f6062c4c0 100644
--- a/drivers/md/bcache/bset.h
+++ b/drivers/md/bcache/bset.h
@@ -187,9 +187,8 @@ struct bset_tree {
 };
 
 struct btree_keys_ops {
-	bool		(*sort_cmp)(const void *l,
-				    const void *r,
-					void *args);
+	bool		(*sort_cmp)(struct btree_iter_set l,
+				    struct btree_iter_set r);
 	struct bkey	*(*sort_fixup)(struct btree_iter *iter,
 				       struct bkey *tmp);
 	bool		(*insert_fixup)(struct btree_keys *b,
@@ -313,17 +312,23 @@ enum {
 	BTREE_INSERT_STATUS_FRONT_MERGE,
 };
 
-struct btree_iter_set {
-	struct bkey *k, *end;
-};
-
 /* Btree key iteration */
 
 struct btree_iter {
+	size_t size, used;
 #ifdef CONFIG_BCACHE_DEBUG
 	struct btree_keys *b;
 #endif
-	MIN_HEAP_PREALLOCATED(struct btree_iter_set, btree_iter_heap, MAX_BSETS) heap;
+	struct btree_iter_set {
+		struct bkey *k, *end;
+	} data[];
+};
+
+/* Fixed-size btree_iter that can be allocated on the stack */
+
+struct btree_iter_stack {
+	struct btree_iter iter;
+	struct btree_iter_set stack_data[MAX_BSETS];
 };
 
 typedef bool (*ptr_filter_fn)(struct btree_keys *b, const struct bkey *k);
@@ -335,9 +340,9 @@ struct bkey *bch_btree_iter_next_filter(struct btree_iter *iter,
 
 void bch_btree_iter_push(struct btree_iter *iter, struct bkey *k,
 			 struct bkey *end);
-struct bkey *bch_btree_iter_init(struct btree_keys *b,
-				 struct btree_iter *iter,
-				 struct bkey *search);
+struct bkey *bch_btree_iter_stack_init(struct btree_keys *b,
+				       struct btree_iter_stack *iter,
+				       struct bkey *search);
 
 struct bkey *__bch_bset_search(struct btree_keys *b, struct bset_tree *t,
 			       const struct bkey *search);
@@ -352,13 +357,14 @@ static inline struct bkey *bch_bset_search(struct btree_keys *b,
 	return search ? __bch_bset_search(b, t, search) : t->data->start;
 }
 
-#define for_each_key_filter(b, k, iter, filter)				\
-	for (bch_btree_iter_init((b), (iter), NULL);			\
-	     ((k) = bch_btree_iter_next_filter((iter), (b), filter));)
+#define for_each_key_filter(b, k, stack_iter, filter)                      \
+	for (bch_btree_iter_stack_init((b), (stack_iter), NULL);           \
+	     ((k) = bch_btree_iter_next_filter(&((stack_iter)->iter), (b), \
+					       filter));)
 
-#define for_each_key(b, k, iter)					\
-	for (bch_btree_iter_init((b), (iter), NULL);			\
-	     ((k) = bch_btree_iter_next(iter));)
+#define for_each_key(b, k, stack_iter)                           \
+	for (bch_btree_iter_stack_init((b), (stack_iter), NULL); \
+	     ((k) = bch_btree_iter_next(&((stack_iter)->iter)));)
 
 /* Sorting */
 
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index ed40d8600656..4e6ccf2c8a0b 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -149,19 +149,19 @@ void bch_btree_node_read_done(struct btree *b)
 {
 	const char *err = "bad btree header";
 	struct bset *i = btree_bset_first(b);
-	struct btree_iter iter;
+	struct btree_iter *iter;
 
 	/*
 	 * c->fill_iter can allocate an iterator with more memory space
 	 * than static MAX_BSETS.
 	 * See the comment arount cache_set->fill_iter.
 	 */
-	iter.heap.data = mempool_alloc(&b->c->fill_iter, GFP_NOIO);
-	iter.heap.size = b->c->cache->sb.bucket_size / b->c->cache->sb.block_size;
-	iter.heap.nr = 0;
+	iter = mempool_alloc(&b->c->fill_iter, GFP_NOIO);
+	iter->size = b->c->cache->sb.bucket_size / b->c->cache->sb.block_size;
+	iter->used = 0;
 
 #ifdef CONFIG_BCACHE_DEBUG
-	iter.b = &b->keys;
+	iter->b = &b->keys;
 #endif
 
 	if (!i->seq)
@@ -199,7 +199,7 @@ void bch_btree_node_read_done(struct btree *b)
 		if (i != b->keys.set[0].data && !i->keys)
 			goto err;
 
-		bch_btree_iter_push(&iter, i->start, bset_bkey_last(i));
+		bch_btree_iter_push(iter, i->start, bset_bkey_last(i));
 
 		b->written += set_blocks(i, block_bytes(b->c->cache));
 	}
@@ -211,7 +211,7 @@ void bch_btree_node_read_done(struct btree *b)
 		if (i->seq == b->keys.set[0].data->seq)
 			goto err;
 
-	bch_btree_sort_and_fix_extents(&b->keys, &iter, &b->c->sort);
+	bch_btree_sort_and_fix_extents(&b->keys, iter, &b->c->sort);
 
 	i = b->keys.set[0].data;
 	err = "short btree key";
@@ -223,7 +223,7 @@ void bch_btree_node_read_done(struct btree *b)
 		bch_bset_init_next(&b->keys, write_block(b),
 				   bset_magic(&b->c->cache->sb));
 out:
-	mempool_free(iter.heap.data, &b->c->fill_iter);
+	mempool_free(iter, &b->c->fill_iter);
 	return;
 err:
 	set_btree_node_io_error(b);
@@ -1309,11 +1309,9 @@ static bool btree_gc_mark_node(struct btree *b, struct gc_stat *gc)
 	uint8_t stale = 0;
 	unsigned int keys = 0, good_keys = 0;
 	struct bkey *k;
-	struct btree_iter iter;
+	struct btree_iter_stack iter;
 	struct bset_tree *t;
 
-	min_heap_init(&iter.heap, NULL, MAX_BSETS);
-
 	gc->nodes++;
 
 	for_each_key_filter(&b->keys, k, &iter, bch_ptr_invalid) {
@@ -1572,11 +1570,9 @@ static int btree_gc_rewrite_node(struct btree *b, struct btree_op *op,
 static unsigned int btree_gc_count_keys(struct btree *b)
 {
 	struct bkey *k;
-	struct btree_iter iter;
+	struct btree_iter_stack iter;
 	unsigned int ret = 0;
 
-	min_heap_init(&iter.heap, NULL, MAX_BSETS);
-
 	for_each_key_filter(&b->keys, k, &iter, bch_ptr_bad)
 		ret += bkey_u64s(k);
 
@@ -1615,18 +1611,18 @@ static int btree_gc_recurse(struct btree *b, struct btree_op *op,
 	int ret = 0;
 	bool should_rewrite;
 	struct bkey *k;
-	struct btree_iter iter;
+	struct btree_iter_stack iter;
 	struct gc_merge_info r[GC_MERGE_NODES];
 	struct gc_merge_info *i, *last = r + ARRAY_SIZE(r) - 1;
 
-	min_heap_init(&iter.heap, NULL, MAX_BSETS);
-	bch_btree_iter_init(&b->keys, &iter, &b->c->gc_done);
+	bch_btree_iter_stack_init(&b->keys, &iter, &b->c->gc_done);
 
 	for (i = r; i < r + ARRAY_SIZE(r); i++)
 		i->b = ERR_PTR(-EINTR);
 
 	while (1) {
-		k = bch_btree_iter_next_filter(&iter, &b->keys, bch_ptr_bad);
+		k = bch_btree_iter_next_filter(&iter.iter, &b->keys,
+					       bch_ptr_bad);
 		if (k) {
 			r->b = bch_btree_node_get(b->c, op, k, b->level - 1,
 						  true, b);
@@ -1921,9 +1917,7 @@ static int bch_btree_check_recurse(struct btree *b, struct btree_op *op)
 {
 	int ret = 0;
 	struct bkey *k, *p = NULL;
-	struct btree_iter iter;
-
-	min_heap_init(&iter.heap, NULL, MAX_BSETS);
+	struct btree_iter_stack iter;
 
 	for_each_key_filter(&b->keys, k, &iter, bch_ptr_invalid)
 		bch_initial_mark_key(b->c, b->level, k);
@@ -1931,10 +1925,10 @@ static int bch_btree_check_recurse(struct btree *b, struct btree_op *op)
 	bch_initial_mark_key(b->c, b->level + 1, &b->key);
 
 	if (b->level) {
-		bch_btree_iter_init(&b->keys, &iter, NULL);
+		bch_btree_iter_stack_init(&b->keys, &iter, NULL);
 
 		do {
-			k = bch_btree_iter_next_filter(&iter, &b->keys,
+			k = bch_btree_iter_next_filter(&iter.iter, &b->keys,
 						       bch_ptr_bad);
 			if (k) {
 				btree_node_prefetch(b, k);
@@ -1962,7 +1956,7 @@ static int bch_btree_check_thread(void *arg)
 	struct btree_check_info *info = arg;
 	struct btree_check_state *check_state = info->state;
 	struct cache_set *c = check_state->c;
-	struct btree_iter iter;
+	struct btree_iter_stack iter;
 	struct bkey *k, *p;
 	int cur_idx, prev_idx, skip_nr;
 
@@ -1970,11 +1964,9 @@ static int bch_btree_check_thread(void *arg)
 	cur_idx = prev_idx = 0;
 	ret = 0;
 
-	min_heap_init(&iter.heap, NULL, MAX_BSETS);
-
 	/* root node keys are checked before thread created */
-	bch_btree_iter_init(&c->root->keys, &iter, NULL);
-	k = bch_btree_iter_next_filter(&iter, &c->root->keys, bch_ptr_bad);
+	bch_btree_iter_stack_init(&c->root->keys, &iter, NULL);
+	k = bch_btree_iter_next_filter(&iter.iter, &c->root->keys, bch_ptr_bad);
 	BUG_ON(!k);
 
 	p = k;
@@ -1992,7 +1984,7 @@ static int bch_btree_check_thread(void *arg)
 		skip_nr = cur_idx - prev_idx;
 
 		while (skip_nr) {
-			k = bch_btree_iter_next_filter(&iter,
+			k = bch_btree_iter_next_filter(&iter.iter,
 						       &c->root->keys,
 						       bch_ptr_bad);
 			if (k)
@@ -2065,11 +2057,9 @@ int bch_btree_check(struct cache_set *c)
 	int ret = 0;
 	int i;
 	struct bkey *k = NULL;
-	struct btree_iter iter;
+	struct btree_iter_stack iter;
 	struct btree_check_state check_state;
 
-	min_heap_init(&iter.heap, NULL, MAX_BSETS);
-
 	/* check and mark root node keys */
 	for_each_key_filter(&c->root->keys, k, &iter, bch_ptr_invalid)
 		bch_initial_mark_key(c, c->root->level, k);
@@ -2563,12 +2553,11 @@ static int bch_btree_map_nodes_recurse(struct btree *b, struct btree_op *op,
 
 	if (b->level) {
 		struct bkey *k;
-		struct btree_iter iter;
+		struct btree_iter_stack iter;
 
-		min_heap_init(&iter.heap, NULL, MAX_BSETS);
-		bch_btree_iter_init(&b->keys, &iter, from);
+		bch_btree_iter_stack_init(&b->keys, &iter, from);
 
-		while ((k = bch_btree_iter_next_filter(&iter, &b->keys,
+		while ((k = bch_btree_iter_next_filter(&iter.iter, &b->keys,
 						       bch_ptr_bad))) {
 			ret = bcache_btree(map_nodes_recurse, k, b,
 				    op, from, fn, flags);
@@ -2597,12 +2586,12 @@ int bch_btree_map_keys_recurse(struct btree *b, struct btree_op *op,
 {
 	int ret = MAP_CONTINUE;
 	struct bkey *k;
-	struct btree_iter iter;
+	struct btree_iter_stack iter;
 
-	min_heap_init(&iter.heap, NULL, MAX_BSETS);
-	bch_btree_iter_init(&b->keys, &iter, from);
+	bch_btree_iter_stack_init(&b->keys, &iter, from);
 
-	while ((k = bch_btree_iter_next_filter(&iter, &b->keys, bch_ptr_bad))) {
+	while ((k = bch_btree_iter_next_filter(&iter.iter, &b->keys,
+					       bch_ptr_bad))) {
 		ret = !b->level
 			? fn(op, b, k)
 			: bcache_btree(map_keys_recurse, k,
diff --git a/drivers/md/bcache/extents.c b/drivers/md/bcache/extents.c
index a7221e5dbe81..d626ffcbecb9 100644
--- a/drivers/md/bcache/extents.c
+++ b/drivers/md/bcache/extents.c
@@ -33,16 +33,15 @@ static void sort_key_next(struct btree_iter *iter,
 	i->k = bkey_next(i->k);
 
 	if (i->k == i->end)
-		*i = iter->heap.data[--iter->heap.nr];
+		*i = iter->data[--iter->used];
 }
 
-static bool new_bch_key_sort_cmp(const void *l, const void *r, void *args)
+static bool bch_key_sort_cmp(struct btree_iter_set l,
+			     struct btree_iter_set r)
 {
-	struct btree_iter_set *_l = (struct btree_iter_set *)l;
-	struct btree_iter_set *_r = (struct btree_iter_set *)r;
-	int64_t c = bkey_cmp(_l->k, _r->k);
+	int64_t c = bkey_cmp(l.k, r.k);
 
-	return !(c ? c > 0 : _l->k < _r->k);
+	return c ? c > 0 : l.k < r.k;
 }
 
 static bool __ptr_invalid(struct cache_set *c, const struct bkey *k)
@@ -239,7 +238,7 @@ static bool bch_btree_ptr_insert_fixup(struct btree_keys *bk,
 }
 
 const struct btree_keys_ops bch_btree_keys_ops = {
-	.sort_cmp	= new_bch_key_sort_cmp,
+	.sort_cmp	= bch_key_sort_cmp,
 	.insert_fixup	= bch_btree_ptr_insert_fixup,
 	.key_invalid	= bch_btree_ptr_invalid,
 	.key_bad	= bch_btree_ptr_bad,
@@ -256,36 +255,22 @@ const struct btree_keys_ops bch_btree_keys_ops = {
  * Necessary for btree_sort_fixup() - if there are multiple keys that compare
  * equal in different sets, we have to process them newest to oldest.
  */
-
-static bool new_bch_extent_sort_cmp(const void *l, const void *r, void __always_unused *args)
-{
-	struct btree_iter_set *_l = (struct btree_iter_set *)l;
-	struct btree_iter_set *_r = (struct btree_iter_set *)r;
-	int64_t c = bkey_cmp(&START_KEY(_l->k), &START_KEY(_r->k));
-
-	return !(c ? c > 0 : _l->k < _r->k);
-}
-
-static inline void new_btree_iter_swap(void *iter1, void *iter2, void __always_unused *args)
+static bool bch_extent_sort_cmp(struct btree_iter_set l,
+				struct btree_iter_set r)
 {
-	struct btree_iter_set *_iter1 = iter1;
-	struct btree_iter_set *_iter2 = iter2;
+	int64_t c = bkey_cmp(&START_KEY(l.k), &START_KEY(r.k));
 
-	swap(*_iter1, *_iter2);
+	return c ? c > 0 : l.k < r.k;
 }
 
 static struct bkey *bch_extent_sort_fixup(struct btree_iter *iter,
 					  struct bkey *tmp)
 {
-	const struct min_heap_callbacks callbacks = {
-		.less = new_bch_extent_sort_cmp,
-		.swp = new_btree_iter_swap,
-	};
-	while (iter->heap.nr > 1) {
-		struct btree_iter_set *top = iter->heap.data, *i = top + 1;
-
-		if (iter->heap.nr > 2 &&
-		    !new_bch_extent_sort_cmp(&i[0], &i[1], NULL))
+	while (iter->used > 1) {
+		struct btree_iter_set *top = iter->data, *i = top + 1;
+
+		if (iter->used > 2 &&
+		    bch_extent_sort_cmp(i[0], i[1]))
 			i++;
 
 		if (bkey_cmp(top->k, &START_KEY(i->k)) <= 0)
@@ -293,7 +278,7 @@ static struct bkey *bch_extent_sort_fixup(struct btree_iter *iter,
 
 		if (!KEY_SIZE(i->k)) {
 			sort_key_next(iter, i);
-			min_heap_sift_down(&iter->heap, i - top, &callbacks, NULL);
+			heap_sift(iter, i - top, bch_extent_sort_cmp);
 			continue;
 		}
 
@@ -303,7 +288,7 @@ static struct bkey *bch_extent_sort_fixup(struct btree_iter *iter,
 			else
 				bch_cut_front(top->k, i->k);
 
-			min_heap_sift_down(&iter->heap, i - top, &callbacks, NULL);
+			heap_sift(iter, i - top, bch_extent_sort_cmp);
 		} else {
 			/* can't happen because of comparison func */
 			BUG_ON(!bkey_cmp(&START_KEY(top->k), &START_KEY(i->k)));
@@ -313,7 +298,7 @@ static struct bkey *bch_extent_sort_fixup(struct btree_iter *iter,
 
 				bch_cut_back(&START_KEY(i->k), tmp);
 				bch_cut_front(i->k, top->k);
-				min_heap_sift_down(&iter->heap, 0, &callbacks, NULL);
+				heap_sift(iter, 0, bch_extent_sort_cmp);
 
 				return tmp;
 			} else {
@@ -633,7 +618,7 @@ static bool bch_extent_merge(struct btree_keys *bk,
 }
 
 const struct btree_keys_ops bch_extent_keys_ops = {
-	.sort_cmp	= new_bch_extent_sort_cmp,
+	.sort_cmp	= bch_extent_sort_cmp,
 	.sort_fixup	= bch_extent_sort_fixup,
 	.insert_fixup	= bch_extent_insert_fixup,
 	.key_invalid	= bch_extent_invalid,
diff --git a/drivers/md/bcache/movinggc.c b/drivers/md/bcache/movinggc.c
index 7f482729c56d..ebd500bdf0b2 100644
--- a/drivers/md/bcache/movinggc.c
+++ b/drivers/md/bcache/movinggc.c
@@ -182,27 +182,16 @@ err:		if (!IS_ERR_OR_NULL(w->private))
 	closure_sync(&cl);
 }
 
-static bool new_bucket_cmp(const void *l, const void *r, void __always_unused *args)
+static bool bucket_cmp(struct bucket *l, struct bucket *r)
 {
-	struct bucket **_l = (struct bucket **)l;
-	struct bucket **_r = (struct bucket **)r;
-
-	return GC_SECTORS_USED(*_l) >= GC_SECTORS_USED(*_r);
-}
-
-static void new_bucket_swap(void *l, void *r, void __always_unused *args)
-{
-	struct bucket **_l = l;
-	struct bucket **_r = r;
-
-	swap(*_l, *_r);
+	return GC_SECTORS_USED(l) < GC_SECTORS_USED(r);
 }
 
 static unsigned int bucket_heap_top(struct cache *ca)
 {
 	struct bucket *b;
 
-	return (b = min_heap_peek(&ca->heap)[0]) ? GC_SECTORS_USED(b) : 0;
+	return (b = heap_peek(&ca->heap)) ? GC_SECTORS_USED(b) : 0;
 }
 
 void bch_moving_gc(struct cache_set *c)
@@ -210,10 +199,6 @@ void bch_moving_gc(struct cache_set *c)
 	struct cache *ca = c->cache;
 	struct bucket *b;
 	unsigned long sectors_to_move, reserve_sectors;
-	const struct min_heap_callbacks callbacks = {
-		.less = new_bucket_cmp,
-		.swp = new_bucket_swap,
-	};
 
 	if (!c->copy_gc_enabled)
 		return;
@@ -224,7 +209,7 @@ void bch_moving_gc(struct cache_set *c)
 	reserve_sectors = ca->sb.bucket_size *
 			     fifo_used(&ca->free[RESERVE_MOVINGGC]);
 
-	ca->heap.nr = 0;
+	ca->heap.used = 0;
 
 	for_each_bucket(b, ca) {
 		if (GC_MARK(b) == GC_MARK_METADATA ||
@@ -233,31 +218,25 @@ void bch_moving_gc(struct cache_set *c)
 		    atomic_read(&b->pin))
 			continue;
 
-		if (!min_heap_full(&ca->heap)) {
+		if (!heap_full(&ca->heap)) {
 			sectors_to_move += GC_SECTORS_USED(b);
-			min_heap_push(&ca->heap, &b, &callbacks, NULL);
-		} else if (!new_bucket_cmp(&b, min_heap_peek(&ca->heap), ca)) {
+			heap_add(&ca->heap, b, bucket_cmp);
+		} else if (bucket_cmp(b, heap_peek(&ca->heap))) {
 			sectors_to_move -= bucket_heap_top(ca);
 			sectors_to_move += GC_SECTORS_USED(b);
 
 			ca->heap.data[0] = b;
-			min_heap_sift_down(&ca->heap, 0, &callbacks, NULL);
+			heap_sift(&ca->heap, 0, bucket_cmp);
 		}
 	}
 
 	while (sectors_to_move > reserve_sectors) {
-		if (ca->heap.nr) {
-			b = min_heap_peek(&ca->heap)[0];
-			min_heap_pop(&ca->heap, &callbacks, NULL);
-		}
+		heap_pop(&ca->heap, b, bucket_cmp);
 		sectors_to_move -= GC_SECTORS_USED(b);
 	}
 
-	while (ca->heap.nr) {
-		b = min_heap_peek(&ca->heap)[0];
-		min_heap_pop(&ca->heap, &callbacks, NULL);
+	while (heap_pop(&ca->heap, b, bucket_cmp))
 		SET_GC_MOVE(b, 1);
-	}
 
 	mutex_unlock(&c->bucket_lock);
 
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index e42f1400cea9..1084b3f0dfe7 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -1733,7 +1733,12 @@ static CLOSURE_CALLBACK(cache_set_flush)
 			mutex_unlock(&b->write_lock);
 		}
 
-	if (ca->alloc_thread)
+	/*
+	 * If the register_cache_set() call to bch_cache_set_alloc() failed,
+	 * ca has not been assigned a value and return error.
+	 * So we need check ca is not NULL during bch_cache_set_unregister().
+	 */
+	if (ca && ca->alloc_thread)
 		kthread_stop(ca->alloc_thread);
 
 	if (c->journal.cur) {
@@ -1907,7 +1912,8 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb)
 	INIT_LIST_HEAD(&c->btree_cache_freed);
 	INIT_LIST_HEAD(&c->data_buckets);
 
-	iter_size = ((meta_bucket_pages(sb) * PAGE_SECTORS) / sb->block_size) *
+	iter_size = sizeof(struct btree_iter) +
+		    ((meta_bucket_pages(sb) * PAGE_SECTORS) / sb->block_size) *
 			    sizeof(struct btree_iter_set);
 
 	c->devices = kcalloc(c->nr_uuids, sizeof(void *), GFP_KERNEL);
diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c
index e8f696cb58c0..826b14cae4e5 100644
--- a/drivers/md/bcache/sysfs.c
+++ b/drivers/md/bcache/sysfs.c
@@ -660,9 +660,7 @@ static unsigned int bch_root_usage(struct cache_set *c)
 	unsigned int bytes = 0;
 	struct bkey *k;
 	struct btree *b;
-	struct btree_iter iter;
-
-	min_heap_init(&iter.heap, NULL, MAX_BSETS);
+	struct btree_iter_stack iter;
 
 	goto lock_root;
 
diff --git a/drivers/md/bcache/util.h b/drivers/md/bcache/util.h
index 539454d8e2d0..f61ab1bada6c 100644
--- a/drivers/md/bcache/util.h
+++ b/drivers/md/bcache/util.h
@@ -9,7 +9,6 @@
 #include <linux/kernel.h>
 #include <linux/sched/clock.h>
 #include <linux/llist.h>
-#include <linux/min_heap.h>
 #include <linux/ratelimit.h>
 #include <linux/vmalloc.h>
 #include <linux/workqueue.h>
@@ -31,10 +30,16 @@ struct closure;
 
 #endif
 
+#define DECLARE_HEAP(type, name)					\
+	struct {							\
+		size_t size, used;					\
+		type *data;						\
+	} name
+
 #define init_heap(heap, _size, gfp)					\
 ({									\
 	size_t _bytes;							\
-	(heap)->nr = 0;						\
+	(heap)->used = 0;						\
 	(heap)->size = (_size);						\
 	_bytes = (heap)->size * sizeof(*(heap)->data);			\
 	(heap)->data = kvmalloc(_bytes, (gfp) & GFP_KERNEL);		\
@@ -47,6 +52,64 @@ do {									\
 	(heap)->data = NULL;						\
 } while (0)
 
+#define heap_swap(h, i, j)	swap((h)->data[i], (h)->data[j])
+
+#define heap_sift(h, i, cmp)						\
+do {									\
+	size_t _r, _j = i;						\
+									\
+	for (; _j * 2 + 1 < (h)->used; _j = _r) {			\
+		_r = _j * 2 + 1;					\
+		if (_r + 1 < (h)->used &&				\
+		    cmp((h)->data[_r], (h)->data[_r + 1]))		\
+			_r++;						\
+									\
+		if (cmp((h)->data[_r], (h)->data[_j]))			\
+			break;						\
+		heap_swap(h, _r, _j);					\
+	}								\
+} while (0)
+
+#define heap_sift_down(h, i, cmp)					\
+do {									\
+	while (i) {							\
+		size_t p = (i - 1) / 2;					\
+		if (cmp((h)->data[i], (h)->data[p]))			\
+			break;						\
+		heap_swap(h, i, p);					\
+		i = p;							\
+	}								\
+} while (0)
+
+#define heap_add(h, d, cmp)						\
+({									\
+	bool _r = !heap_full(h);					\
+	if (_r) {							\
+		size_t _i = (h)->used++;				\
+		(h)->data[_i] = d;					\
+									\
+		heap_sift_down(h, _i, cmp);				\
+		heap_sift(h, _i, cmp);					\
+	}								\
+	_r;								\
+})
+
+#define heap_pop(h, d, cmp)						\
+({									\
+	bool _r = (h)->used;						\
+	if (_r) {							\
+		(d) = (h)->data[0];					\
+		(h)->used--;						\
+		heap_swap(h, 0, (h)->used);				\
+		heap_sift(h, 0, cmp);					\
+	}								\
+	_r;								\
+})
+
+#define heap_peek(h)	((h)->used ? (h)->data[0] : NULL)
+
+#define heap_full(h)	((h)->used == (h)->size)
+
 #define DECLARE_FIFO(type, name)					\
 	struct {							\
 		size_t front, back, size, mask;				\
diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c
index c1d28e365910..792e070ccf38 100644
--- a/drivers/md/bcache/writeback.c
+++ b/drivers/md/bcache/writeback.c
@@ -908,16 +908,15 @@ static int bch_dirty_init_thread(void *arg)
 	struct dirty_init_thrd_info *info = arg;
 	struct bch_dirty_init_state *state = info->state;
 	struct cache_set *c = state->c;
-	struct btree_iter iter;
+	struct btree_iter_stack iter;
 	struct bkey *k, *p;
 	int cur_idx, prev_idx, skip_nr;
 
 	k = p = NULL;
 	prev_idx = 0;
 
-	min_heap_init(&iter.heap, NULL, MAX_BSETS);
-	bch_btree_iter_init(&c->root->keys, &iter, NULL);
-	k = bch_btree_iter_next_filter(&iter, &c->root->keys, bch_ptr_bad);
+	bch_btree_iter_stack_init(&c->root->keys, &iter, NULL);
+	k = bch_btree_iter_next_filter(&iter.iter, &c->root->keys, bch_ptr_bad);
 	BUG_ON(!k);
 
 	p = k;
@@ -931,7 +930,7 @@ static int bch_dirty_init_thread(void *arg)
 		skip_nr = cur_idx - prev_idx;
 
 		while (skip_nr) {
-			k = bch_btree_iter_next_filter(&iter,
+			k = bch_btree_iter_next_filter(&iter.iter,
 						       &c->root->keys,
 						       bch_ptr_bad);
 			if (k)
@@ -980,13 +979,11 @@ void bch_sectors_dirty_init(struct bcache_device *d)
 	int i;
 	struct btree *b = NULL;
 	struct bkey *k = NULL;
-	struct btree_iter iter;
+	struct btree_iter_stack iter;
 	struct sectors_dirty_init op;
 	struct cache_set *c = d->c;
 	struct bch_dirty_init_state state;
 
-	min_heap_init(&iter.heap, NULL, MAX_BSETS);
-
 retry_lock:
 	b = c->root;
 	rw_lock(0, b, b->level);
diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index 23e0b71b991e..aaa21fe295f2 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -68,6 +68,8 @@
 #define LIST_DIRTY	1
 #define LIST_SIZE	2
 
+#define SCAN_RESCHED_CYCLE	16
+
 /*--------------------------------------------------------------*/
 
 /*
@@ -2414,7 +2416,12 @@ static void __scan(struct dm_bufio_client *c)
 
 			atomic_long_dec(&c->need_shrink);
 			freed++;
-			cond_resched();
+
+			if (unlikely(freed % SCAN_RESCHED_CYCLE == 0)) {
+				dm_bufio_unlock(c);
+				cond_resched();
+				dm_bufio_lock(c);
+			}
 		}
 	}
 }
@@ -2734,7 +2741,11 @@ static unsigned long __evict_many(struct dm_bufio_client *c,
 		__make_buffer_clean(b);
 		__free_buffer_wake(b);
 
-		cond_resched();
+		if (need_resched()) {
+			dm_bufio_unlock(c);
+			cond_resched();
+			dm_bufio_lock(c);
+		}
 	}
 
 	return count;
diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c
index 849eb6333e98..6aa4095dc587 100644
--- a/drivers/md/dm-cache-target.c
+++ b/drivers/md/dm-cache-target.c
@@ -2899,6 +2899,27 @@ static dm_cblock_t get_cache_dev_size(struct cache *cache)
 	return to_cblock(size);
 }
 
+static bool can_resume(struct cache *cache)
+{
+	/*
+	 * Disallow retrying the resume operation for devices that failed the
+	 * first resume attempt, as the failure leaves the policy object partially
+	 * initialized. Retrying could trigger BUG_ON when loading cache mappings
+	 * into the incomplete policy object.
+	 */
+	if (cache->sized && !cache->loaded_mappings) {
+		if (get_cache_mode(cache) != CM_WRITE)
+			DMERR("%s: unable to resume a failed-loaded cache, please check metadata.",
+			      cache_device_name(cache));
+		else
+			DMERR("%s: unable to resume cache due to missing proper cache table reload",
+			      cache_device_name(cache));
+		return false;
+	}
+
+	return true;
+}
+
 static bool can_resize(struct cache *cache, dm_cblock_t new_size)
 {
 	if (from_cblock(new_size) > from_cblock(cache->cache_size)) {
@@ -2947,6 +2968,9 @@ static int cache_preresume(struct dm_target *ti)
 	struct cache *cache = ti->private;
 	dm_cblock_t csize = get_cache_dev_size(cache);
 
+	if (!can_resume(cache))
+		return -EINVAL;
+
 	/*
 	 * Check to see if the cache has resized.
 	 */
diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h
index 3637761f3585..f3a3f2ef6322 100644
--- a/drivers/md/dm-core.h
+++ b/drivers/md/dm-core.h
@@ -141,6 +141,7 @@ struct mapped_device {
 #ifdef CONFIG_BLK_DEV_ZONED
 	unsigned int nr_zones;
 	void *zone_revalidate_map;
+	struct task_struct *revalidate_map_task;
 #endif
 
 #ifdef CONFIG_IMA
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 1ae2c71bb383..78c975d7cd5f 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -59,6 +59,7 @@ struct convert_context {
 	struct bio *bio_out;
 	struct bvec_iter iter_out;
 	atomic_t cc_pending;
+	unsigned int tag_offset;
 	u64 cc_sector;
 	union {
 		struct skcipher_request *req;
@@ -1256,6 +1257,7 @@ static void crypt_convert_init(struct crypt_config *cc,
 	if (bio_out)
 		ctx->iter_out = bio_out->bi_iter;
 	ctx->cc_sector = sector + cc->iv_offset;
+	ctx->tag_offset = 0;
 	init_completion(&ctx->restart);
 }
 
@@ -1588,7 +1590,6 @@ static void crypt_free_req(struct crypt_config *cc, void *req, struct bio *base_
 static blk_status_t crypt_convert(struct crypt_config *cc,
 			 struct convert_context *ctx, bool atomic, bool reset_pending)
 {
-	unsigned int tag_offset = 0;
 	unsigned int sector_step = cc->sector_size >> SECTOR_SHIFT;
 	int r;
 
@@ -1611,9 +1612,9 @@ static blk_status_t crypt_convert(struct crypt_config *cc,
 		atomic_inc(&ctx->cc_pending);
 
 		if (crypt_integrity_aead(cc))
-			r = crypt_convert_block_aead(cc, ctx, ctx->r.req_aead, tag_offset);
+			r = crypt_convert_block_aead(cc, ctx, ctx->r.req_aead, ctx->tag_offset);
 		else
-			r = crypt_convert_block_skcipher(cc, ctx, ctx->r.req, tag_offset);
+			r = crypt_convert_block_skcipher(cc, ctx, ctx->r.req, ctx->tag_offset);
 
 		switch (r) {
 		/*
@@ -1633,8 +1634,8 @@ static blk_status_t crypt_convert(struct crypt_config *cc,
 					 * exit and continue processing in a workqueue
 					 */
 					ctx->r.req = NULL;
+					ctx->tag_offset++;
 					ctx->cc_sector += sector_step;
-					tag_offset++;
 					return BLK_STS_DEV_RESOURCE;
 				}
 			} else {
@@ -1648,8 +1649,8 @@ static blk_status_t crypt_convert(struct crypt_config *cc,
 		 */
 		case -EINPROGRESS:
 			ctx->r.req = NULL;
+			ctx->tag_offset++;
 			ctx->cc_sector += sector_step;
-			tag_offset++;
 			continue;
 		/*
 		 * The request was already processed (synchronously).
@@ -1657,7 +1658,7 @@ static blk_status_t crypt_convert(struct crypt_config *cc,
 		case 0:
 			atomic_dec(&ctx->cc_pending);
 			ctx->cc_sector += sector_step;
-			tag_offset++;
+			ctx->tag_offset++;
 			if (!atomic)
 				cond_resched();
 			continue;
@@ -2092,7 +2093,6 @@ static void kcryptd_crypt_write_continue(struct work_struct *work)
 	struct crypt_config *cc = io->cc;
 	struct convert_context *ctx = &io->ctx;
 	int crypt_finished;
-	sector_t sector = io->sector;
 	blk_status_t r;
 
 	wait_for_completion(&ctx->restart);
@@ -2109,10 +2109,8 @@ static void kcryptd_crypt_write_continue(struct work_struct *work)
 	}
 
 	/* Encryption was already finished, submit io now */
-	if (crypt_finished) {
+	if (crypt_finished)
 		kcryptd_crypt_write_io_submit(io, 0);
-		io->sector = sector;
-	}
 
 	crypt_dec_pending(io);
 }
@@ -2123,14 +2121,13 @@ static void kcryptd_crypt_write_convert(struct dm_crypt_io *io)
 	struct convert_context *ctx = &io->ctx;
 	struct bio *clone;
 	int crypt_finished;
-	sector_t sector = io->sector;
 	blk_status_t r;
 
 	/*
 	 * Prevent io from disappearing until this function completes.
 	 */
 	crypt_inc_pending(io);
-	crypt_convert_init(cc, ctx, NULL, io->base_bio, sector);
+	crypt_convert_init(cc, ctx, NULL, io->base_bio, io->sector);
 
 	clone = crypt_alloc_buffer(io, io->base_bio->bi_iter.bi_size);
 	if (unlikely(!clone)) {
@@ -2147,8 +2144,6 @@ static void kcryptd_crypt_write_convert(struct dm_crypt_io *io)
 		io->ctx.iter_in = clone->bi_iter;
 	}
 
-	sector += bio_sectors(clone);
-
 	crypt_inc_pending(io);
 	r = crypt_convert(cc, ctx,
 			  test_bit(DM_CRYPT_NO_WRITE_WORKQUEUE, &cc->flags), true);
@@ -2172,10 +2167,8 @@ static void kcryptd_crypt_write_convert(struct dm_crypt_io *io)
 	}
 
 	/* Encryption was already finished, submit io now */
-	if (crypt_finished) {
+	if (crypt_finished)
 		kcryptd_crypt_write_io_submit(io, 0);
-		io->sector = sector;
-	}
 
 dec:
 	crypt_dec_pending(io);
diff --git a/drivers/md/dm-ebs-target.c b/drivers/md/dm-ebs-target.c
index 18ae45dcbfb2..b19b0142a690 100644
--- a/drivers/md/dm-ebs-target.c
+++ b/drivers/md/dm-ebs-target.c
@@ -390,6 +390,12 @@ static int ebs_map(struct dm_target *ti, struct bio *bio)
 	return DM_MAPIO_REMAPPED;
 }
 
+static void ebs_postsuspend(struct dm_target *ti)
+{
+	struct ebs_c *ec = ti->private;
+	dm_bufio_client_reset(ec->bufio);
+}
+
 static void ebs_status(struct dm_target *ti, status_type_t type,
 		       unsigned int status_flags, char *result, unsigned int maxlen)
 {
@@ -447,6 +453,7 @@ static struct target_type ebs_target = {
 	.ctr		 = ebs_ctr,
 	.dtr		 = ebs_dtr,
 	.map		 = ebs_map,
+	.postsuspend	 = ebs_postsuspend,
 	.status		 = ebs_status,
 	.io_hints	 = ebs_io_hints,
 	.prepare_ioctl	 = ebs_prepare_ioctl,
diff --git a/drivers/md/dm-flakey.c b/drivers/md/dm-flakey.c
index 731467d4ed10..347881f323d5 100644
--- a/drivers/md/dm-flakey.c
+++ b/drivers/md/dm-flakey.c
@@ -47,14 +47,15 @@ enum feature_flag_bits {
 };
 
 struct per_bio_data {
-	bool bio_submitted;
+	bool bio_can_corrupt;
+	struct bvec_iter saved_iter;
 };
 
 static int parse_features(struct dm_arg_set *as, struct flakey_c *fc,
 			  struct dm_target *ti)
 {
-	int r;
-	unsigned int argc;
+	int r = 0;
+	unsigned int argc = 0;
 	const char *arg_name;
 
 	static const struct dm_arg _args[] = {
@@ -65,14 +66,13 @@ static int parse_features(struct dm_arg_set *as, struct flakey_c *fc,
 		{0, PROBABILITY_BASE, "Invalid random corrupt argument"},
 	};
 
-	/* No feature arguments supplied. */
-	if (!as->argc)
-		return 0;
-
-	r = dm_read_arg_group(_args, as, &argc, &ti->error);
-	if (r)
+	if (as->argc && (r = dm_read_arg_group(_args, as, &argc, &ti->error)))
 		return r;
 
+	/* No feature arguments supplied. */
+	if (!argc)
+		goto error_all_io;
+
 	while (argc) {
 		arg_name = dm_shift_arg(as);
 		argc--;
@@ -217,6 +217,7 @@ static int parse_features(struct dm_arg_set *as, struct flakey_c *fc,
 	if (!fc->corrupt_bio_byte && !test_bit(ERROR_READS, &fc->flags) &&
 	    !test_bit(DROP_WRITES, &fc->flags) && !test_bit(ERROR_WRITES, &fc->flags) &&
 	    !fc->random_read_corrupt && !fc->random_write_corrupt) {
+error_all_io:
 		set_bit(ERROR_WRITES, &fc->flags);
 		set_bit(ERROR_READS, &fc->flags);
 	}
@@ -339,7 +340,8 @@ static void flakey_map_bio(struct dm_target *ti, struct bio *bio)
 }
 
 static void corrupt_bio_common(struct bio *bio, unsigned int corrupt_bio_byte,
-			       unsigned char corrupt_bio_value)
+			       unsigned char corrupt_bio_value,
+			       struct bvec_iter start)
 {
 	struct bvec_iter iter;
 	struct bio_vec bvec;
@@ -348,7 +350,7 @@ static void corrupt_bio_common(struct bio *bio, unsigned int corrupt_bio_byte,
 	 * Overwrite the Nth byte of the bio's data, on whichever page
 	 * it falls.
 	 */
-	bio_for_each_segment(bvec, bio, iter) {
+	__bio_for_each_segment(bvec, bio, iter, start) {
 		if (bio_iter_len(bio, iter) > corrupt_bio_byte) {
 			unsigned char *segment = bvec_kmap_local(&bvec);
 			segment[corrupt_bio_byte] = corrupt_bio_value;
@@ -357,36 +359,31 @@ static void corrupt_bio_common(struct bio *bio, unsigned int corrupt_bio_byte,
 				"(rw=%c bi_opf=%u bi_sector=%llu size=%u)\n",
 				bio, corrupt_bio_value, corrupt_bio_byte,
 				(bio_data_dir(bio) == WRITE) ? 'w' : 'r', bio->bi_opf,
-				(unsigned long long)bio->bi_iter.bi_sector,
-				bio->bi_iter.bi_size);
+				(unsigned long long)start.bi_sector,
+				start.bi_size);
 			break;
 		}
 		corrupt_bio_byte -= bio_iter_len(bio, iter);
 	}
 }
 
-static void corrupt_bio_data(struct bio *bio, struct flakey_c *fc)
+static void corrupt_bio_data(struct bio *bio, struct flakey_c *fc,
+			     struct bvec_iter start)
 {
 	unsigned int corrupt_bio_byte = fc->corrupt_bio_byte - 1;
 
-	if (!bio_has_data(bio))
-		return;
-
-	corrupt_bio_common(bio, corrupt_bio_byte, fc->corrupt_bio_value);
+	corrupt_bio_common(bio, corrupt_bio_byte, fc->corrupt_bio_value, start);
 }
 
-static void corrupt_bio_random(struct bio *bio)
+static void corrupt_bio_random(struct bio *bio, struct bvec_iter start)
 {
 	unsigned int corrupt_byte;
 	unsigned char corrupt_value;
 
-	if (!bio_has_data(bio))
-		return;
-
-	corrupt_byte = get_random_u32() % bio->bi_iter.bi_size;
+	corrupt_byte = get_random_u32() % start.bi_size;
 	corrupt_value = get_random_u8();
 
-	corrupt_bio_common(bio, corrupt_byte, corrupt_value);
+	corrupt_bio_common(bio, corrupt_byte, corrupt_value, start);
 }
 
 static void clone_free(struct bio *clone)
@@ -426,7 +423,7 @@ static struct bio *clone_bio(struct dm_target *ti, struct flakey_c *fc, struct b
 	if (!clone)
 		return NULL;
 
-	bio_init(clone, fc->dev->bdev, bio->bi_inline_vecs, nr_iovecs, bio->bi_opf);
+	bio_init(clone, fc->dev->bdev, clone->bi_inline_vecs, nr_iovecs, bio->bi_opf);
 
 	clone->bi_iter.bi_sector = flakey_map_sector(ti, bio->bi_iter.bi_sector);
 	clone->bi_private = bio;
@@ -481,7 +478,7 @@ static int flakey_map(struct dm_target *ti, struct bio *bio)
 	unsigned int elapsed;
 	struct per_bio_data *pb = dm_per_bio_data(bio, sizeof(struct per_bio_data));
 
-	pb->bio_submitted = false;
+	pb->bio_can_corrupt = false;
 
 	if (op_is_zone_mgmt(bio_op(bio)))
 		goto map_bio;
@@ -490,10 +487,11 @@ static int flakey_map(struct dm_target *ti, struct bio *bio)
 	elapsed = (jiffies - fc->start_time) / HZ;
 	if (elapsed % (fc->up_interval + fc->down_interval) >= fc->up_interval) {
 		bool corrupt_fixed, corrupt_random;
-		/*
-		 * Flag this bio as submitted while down.
-		 */
-		pb->bio_submitted = true;
+
+		if (bio_has_data(bio)) {
+			pb->bio_can_corrupt = true;
+			pb->saved_iter = bio->bi_iter;
+		}
 
 		/*
 		 * Error reads if neither corrupt_bio_byte or drop_writes or error_writes are set.
@@ -516,6 +514,8 @@ static int flakey_map(struct dm_target *ti, struct bio *bio)
 			return DM_MAPIO_SUBMITTED;
 		}
 
+		if (!pb->bio_can_corrupt)
+			goto map_bio;
 		/*
 		 * Corrupt matching writes.
 		 */
@@ -535,9 +535,11 @@ static int flakey_map(struct dm_target *ti, struct bio *bio)
 			struct bio *clone = clone_bio(ti, fc, bio);
 			if (clone) {
 				if (corrupt_fixed)
-					corrupt_bio_data(clone, fc);
+					corrupt_bio_data(clone, fc,
+							 clone->bi_iter);
 				if (corrupt_random)
-					corrupt_bio_random(clone);
+					corrupt_bio_random(clone,
+							   clone->bi_iter);
 				submit_bio(clone);
 				return DM_MAPIO_SUBMITTED;
 			}
@@ -559,21 +561,21 @@ static int flakey_end_io(struct dm_target *ti, struct bio *bio,
 	if (op_is_zone_mgmt(bio_op(bio)))
 		return DM_ENDIO_DONE;
 
-	if (!*error && pb->bio_submitted && (bio_data_dir(bio) == READ)) {
+	if (!*error && pb->bio_can_corrupt && (bio_data_dir(bio) == READ)) {
 		if (fc->corrupt_bio_byte) {
 			if ((fc->corrupt_bio_rw == READ) &&
 			    all_corrupt_bio_flags_match(bio, fc)) {
 				/*
 				 * Corrupt successful matching READs while in down state.
 				 */
-				corrupt_bio_data(bio, fc);
+				corrupt_bio_data(bio, fc, pb->saved_iter);
 			}
 		}
 		if (fc->random_read_corrupt) {
 			u64 rnd = get_random_u64();
 			u32 rem = do_div(rnd, PROBABILITY_BASE);
 			if (rem < fc->random_read_corrupt)
-				corrupt_bio_random(bio);
+				corrupt_bio_random(bio, pb->saved_iter);
 		}
 		if (test_bit(ERROR_READS, &fc->flags)) {
 			/*
diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c
index ee9f7cecd78e..450e1a7e7bac 100644
--- a/drivers/md/dm-integrity.c
+++ b/drivers/md/dm-integrity.c
@@ -21,6 +21,7 @@
 #include <linux/reboot.h>
 #include <crypto/hash.h>
 #include <crypto/skcipher.h>
+#include <crypto/utils.h>
 #include <linux/async_tx.h>
 #include <linux/dm-bufio.h>
 
@@ -516,7 +517,7 @@ static int sb_mac(struct dm_integrity_c *ic, bool wr)
 			dm_integrity_io_error(ic, "crypto_shash_digest", r);
 			return r;
 		}
-		if (memcmp(mac, actual_mac, mac_size)) {
+		if (crypto_memneq(mac, actual_mac, mac_size)) {
 			dm_integrity_io_error(ic, "superblock mac", -EILSEQ);
 			dm_audit_log_target(DM_MSG_PREFIX, "mac-superblock", ic->ti, 0);
 			return -EILSEQ;
@@ -859,7 +860,7 @@ static void rw_section_mac(struct dm_integrity_c *ic, unsigned int section, bool
 		if (likely(wr))
 			memcpy(&js->mac, result + (j * JOURNAL_MAC_PER_SECTOR), JOURNAL_MAC_PER_SECTOR);
 		else {
-			if (memcmp(&js->mac, result + (j * JOURNAL_MAC_PER_SECTOR), JOURNAL_MAC_PER_SECTOR)) {
+			if (crypto_memneq(&js->mac, result + (j * JOURNAL_MAC_PER_SECTOR), JOURNAL_MAC_PER_SECTOR)) {
 				dm_integrity_io_error(ic, "journal mac", -EILSEQ);
 				dm_audit_log_target(DM_MSG_PREFIX, "mac-journal", ic->ti, 0);
 			}
@@ -1401,10 +1402,9 @@ static bool find_newer_committed_node(struct dm_integrity_c *ic, struct journal_
 static int dm_integrity_rw_tag(struct dm_integrity_c *ic, unsigned char *tag, sector_t *metadata_block,
 			       unsigned int *metadata_offset, unsigned int total_size, int op)
 {
-#define MAY_BE_FILLER		1
-#define MAY_BE_HASH		2
 	unsigned int hash_offset = 0;
-	unsigned int may_be = MAY_BE_HASH | (ic->discard ? MAY_BE_FILLER : 0);
+	unsigned char mismatch_hash = 0;
+	unsigned char mismatch_filler = !ic->discard;
 
 	do {
 		unsigned char *data, *dp;
@@ -1425,7 +1425,7 @@ static int dm_integrity_rw_tag(struct dm_integrity_c *ic, unsigned char *tag, se
 		if (op == TAG_READ) {
 			memcpy(tag, dp, to_copy);
 		} else if (op == TAG_WRITE) {
-			if (memcmp(dp, tag, to_copy)) {
+			if (crypto_memneq(dp, tag, to_copy)) {
 				memcpy(dp, tag, to_copy);
 				dm_bufio_mark_partial_buffer_dirty(b, *metadata_offset, *metadata_offset + to_copy);
 			}
@@ -1433,29 +1433,30 @@ static int dm_integrity_rw_tag(struct dm_integrity_c *ic, unsigned char *tag, se
 			/* e.g.: op == TAG_CMP */
 
 			if (likely(is_power_of_2(ic->tag_size))) {
-				if (unlikely(memcmp(dp, tag, to_copy)))
-					if (unlikely(!ic->discard) ||
-					    unlikely(memchr_inv(dp, DISCARD_FILLER, to_copy) != NULL)) {
-						goto thorough_test;
-				}
+				if (unlikely(crypto_memneq(dp, tag, to_copy)))
+					goto thorough_test;
 			} else {
 				unsigned int i, ts;
 thorough_test:
 				ts = total_size;
 
 				for (i = 0; i < to_copy; i++, ts--) {
-					if (unlikely(dp[i] != tag[i]))
-						may_be &= ~MAY_BE_HASH;
-					if (likely(dp[i] != DISCARD_FILLER))
-						may_be &= ~MAY_BE_FILLER;
+					/*
+					 * Warning: the control flow must not be
+					 * dependent on match/mismatch of
+					 * individual bytes.
+					 */
+					mismatch_hash |= dp[i] ^ tag[i];
+					mismatch_filler |= dp[i] ^ DISCARD_FILLER;
 					hash_offset++;
 					if (unlikely(hash_offset == ic->tag_size)) {
-						if (unlikely(!may_be)) {
+						if (unlikely(mismatch_hash) && unlikely(mismatch_filler)) {
 							dm_bufio_release(b);
 							return ts;
 						}
 						hash_offset = 0;
-						may_be = MAY_BE_HASH | (ic->discard ? MAY_BE_FILLER : 0);
+						mismatch_hash = 0;
+						mismatch_filler = !ic->discard;
 					}
 				}
 			}
@@ -1476,8 +1477,6 @@ thorough_test:
 	} while (unlikely(total_size));
 
 	return 0;
-#undef MAY_BE_FILLER
-#undef MAY_BE_HASH
 }
 
 struct flush_request {
@@ -2076,7 +2075,7 @@ retry_kmap:
 					char checksums_onstack[MAX_T(size_t, HASH_MAX_DIGESTSIZE, MAX_TAG_SIZE)];
 
 					integrity_sector_checksum(ic, logical_sector, mem + bv.bv_offset, checksums_onstack);
-					if (unlikely(memcmp(checksums_onstack, journal_entry_tag(ic, je), ic->tag_size))) {
+					if (unlikely(crypto_memneq(checksums_onstack, journal_entry_tag(ic, je), ic->tag_size))) {
 						DMERR_LIMIT("Checksum failed when reading from journal, at sector 0x%llx",
 							    logical_sector);
 						dm_audit_log_bio(DM_MSG_PREFIX, "journal-checksum",
@@ -2595,7 +2594,7 @@ static void dm_integrity_inline_recheck(struct work_struct *w)
 		bio_put(outgoing_bio);
 
 		integrity_sector_checksum(ic, dio->bio_details.bi_iter.bi_sector, outgoing_data, digest);
-		if (unlikely(memcmp(digest, dio->integrity_payload, min(crypto_shash_digestsize(ic->internal_hash), ic->tag_size)))) {
+		if (unlikely(crypto_memneq(digest, dio->integrity_payload, min(crypto_shash_digestsize(ic->internal_hash), ic->tag_size)))) {
 			DMERR_LIMIT("%pg: Checksum failed at sector 0x%llx",
 				ic->dev->bdev, dio->bio_details.bi_iter.bi_sector);
 			atomic64_inc(&ic->number_of_mismatches);
@@ -2634,7 +2633,7 @@ static int dm_integrity_end_io(struct dm_target *ti, struct bio *bio, blk_status
 				char *mem = bvec_kmap_local(&bv);
 				//memset(mem, 0xff, ic->sectors_per_block << SECTOR_SHIFT);
 				integrity_sector_checksum(ic, dio->bio_details.bi_iter.bi_sector, mem, digest);
-				if (unlikely(memcmp(digest, dio->integrity_payload + pos,
+				if (unlikely(crypto_memneq(digest, dio->integrity_payload + pos,
 						min(crypto_shash_digestsize(ic->internal_hash), ic->tag_size)))) {
 					kunmap_local(mem);
 					dm_integrity_free_payload(dio);
@@ -2911,7 +2910,7 @@ static void do_journal_write(struct dm_integrity_c *ic, unsigned int write_start
 
 					integrity_sector_checksum(ic, sec + ((l - j) << ic->sb->log2_sectors_per_block),
 								  (char *)access_journal_data(ic, i, l), test_tag);
-					if (unlikely(memcmp(test_tag, journal_entry_tag(ic, je2), ic->tag_size))) {
+					if (unlikely(crypto_memneq(test_tag, journal_entry_tag(ic, je2), ic->tag_size))) {
 						dm_integrity_io_error(ic, "tag mismatch when replaying journal", -EILSEQ);
 						dm_audit_log_target(DM_MSG_PREFIX, "integrity-replay-journal", ic->ti, 0);
 					}
@@ -3790,10 +3789,6 @@ static void dm_integrity_status(struct dm_target *ti, status_type_t type,
 		break;
 
 	case STATUSTYPE_TABLE: {
-		__u64 watermark_percentage = (__u64)(ic->journal_entries - ic->free_sectors_threshold) * 100;
-
-		watermark_percentage += ic->journal_entries / 2;
-		do_div(watermark_percentage, ic->journal_entries);
 		arg_count = 3;
 		arg_count += !!ic->meta_dev;
 		arg_count += ic->sectors_per_block != 1;
@@ -3826,6 +3821,10 @@ static void dm_integrity_status(struct dm_target *ti, status_type_t type,
 		DMEMIT(" interleave_sectors:%u", 1U << ic->sb->log2_interleave_sectors);
 		DMEMIT(" buffer_sectors:%u", 1U << ic->log2_buffer_sectors);
 		if (ic->mode == 'J') {
+			__u64 watermark_percentage = (__u64)(ic->journal_entries - ic->free_sectors_threshold) * 100;
+
+			watermark_percentage += ic->journal_entries / 2;
+			do_div(watermark_percentage, ic->journal_entries);
 			DMEMIT(" journal_watermark:%u", (unsigned int)watermark_percentage);
 			DMEMIT(" commit_time:%u", ic->autocommit_msec);
 		}
@@ -5081,16 +5080,19 @@ try_smaller_buffer:
 
 		ic->recalc_bitmap = dm_integrity_alloc_page_list(n_bitmap_pages);
 		if (!ic->recalc_bitmap) {
+			ti->error = "Could not allocate memory for bitmap";
 			r = -ENOMEM;
 			goto bad;
 		}
 		ic->may_write_bitmap = dm_integrity_alloc_page_list(n_bitmap_pages);
 		if (!ic->may_write_bitmap) {
+			ti->error = "Could not allocate memory for bitmap";
 			r = -ENOMEM;
 			goto bad;
 		}
 		ic->bbs = kvmalloc_array(ic->n_bitmap_blocks, sizeof(struct bitmap_block_status), GFP_KERNEL);
 		if (!ic->bbs) {
+			ti->error = "Could not allocate memory for bitmap";
 			r = -ENOMEM;
 			goto bad;
 		}
@@ -5171,7 +5173,7 @@ static void dm_integrity_dtr(struct dm_target *ti)
 	BUG_ON(!RB_EMPTY_ROOT(&ic->in_progress));
 	BUG_ON(!list_empty(&ic->wait_list));
 
-	if (ic->mode == 'B')
+	if (ic->mode == 'B' && ic->bitmap_flush_work.work.func)
 		cancel_delayed_work_sync(&ic->bitmap_flush_work);
 	if (ic->metadata_wq)
 		destroy_workqueue(ic->metadata_wq);
diff --git a/drivers/md/dm-ps-historical-service-time.c b/drivers/md/dm-ps-historical-service-time.c
index b49e10d76d03..2c8626a83de4 100644
--- a/drivers/md/dm-ps-historical-service-time.c
+++ b/drivers/md/dm-ps-historical-service-time.c
@@ -541,8 +541,10 @@ static int __init dm_hst_init(void)
 {
 	int r = dm_register_path_selector(&hst_ps);
 
-	if (r < 0)
+	if (r < 0) {
 		DMERR("register failed %d", r);
+		return r;
+	}
 
 	DMINFO("version " HST_VERSION " loaded");
 
diff --git a/drivers/md/dm-ps-queue-length.c b/drivers/md/dm-ps-queue-length.c
index e305f05ad1e5..eb543e6431e0 100644
--- a/drivers/md/dm-ps-queue-length.c
+++ b/drivers/md/dm-ps-queue-length.c
@@ -260,8 +260,10 @@ static int __init dm_ql_init(void)
 {
 	int r = dm_register_path_selector(&ql_ps);
 
-	if (r < 0)
+	if (r < 0) {
 		DMERR("register failed %d", r);
+		return r;
+	}
 
 	DMINFO("version " QL_VERSION " loaded");
 
diff --git a/drivers/md/dm-ps-round-robin.c b/drivers/md/dm-ps-round-robin.c
index d1745b123dc1..66a15ac0c22c 100644
--- a/drivers/md/dm-ps-round-robin.c
+++ b/drivers/md/dm-ps-round-robin.c
@@ -220,8 +220,10 @@ static int __init dm_rr_init(void)
 {
 	int r = dm_register_path_selector(&rr_ps);
 
-	if (r < 0)
+	if (r < 0) {
 		DMERR("register failed %d", r);
+		return r;
+	}
 
 	DMINFO("version " RR_VERSION " loaded");
 
diff --git a/drivers/md/dm-ps-service-time.c b/drivers/md/dm-ps-service-time.c
index 969d31c40272..f8c43aecdb27 100644
--- a/drivers/md/dm-ps-service-time.c
+++ b/drivers/md/dm-ps-service-time.c
@@ -341,8 +341,10 @@ static int __init dm_st_init(void)
 {
 	int r = dm_register_path_selector(&st_ps);
 
-	if (r < 0)
+	if (r < 0) {
 		DMERR("register failed %d", r);
+		return r;
+	}
 
 	DMINFO("version " ST_VERSION " loaded");
 
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 1e0d3b9b75d6..163a5bbd485f 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -2410,7 +2410,7 @@ static int super_init_validation(struct raid_set *rs, struct md_rdev *rdev)
 	 */
 	sb_retrieve_failed_devices(sb, failed_devices);
 	rdev_for_each(r, mddev) {
-		if (test_bit(Journal, &rdev->flags) ||
+		if (test_bit(Journal, &r->flags) ||
 		    !r->sb_page)
 			continue;
 		sb2 = page_address(r->sb_page);
diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c
index 9511dae5b556..94b6c43dfa5c 100644
--- a/drivers/md/dm-raid1.c
+++ b/drivers/md/dm-raid1.c
@@ -133,10 +133,9 @@ static void queue_bio(struct mirror_set *ms, struct bio *bio, int rw)
 	spin_lock_irqsave(&ms->lock, flags);
 	should_wake = !(bl->head);
 	bio_list_add(bl, bio);
-	spin_unlock_irqrestore(&ms->lock, flags);
-
 	if (should_wake)
 		wakeup_mirrord(ms);
+	spin_unlock_irqrestore(&ms->lock, flags);
 }
 
 static void dispatch_bios(void *context, struct bio_list *bio_list)
@@ -646,9 +645,9 @@ static void write_callback(unsigned long error, void *context)
 	if (!ms->failures.head)
 		should_wake = 1;
 	bio_list_add(&ms->failures, bio);
-	spin_unlock_irqrestore(&ms->lock, flags);
 	if (should_wake)
 		wakeup_mirrord(ms);
+	spin_unlock_irqrestore(&ms->lock, flags);
 }
 
 static void do_write(struct mirror_set *ms, struct bio *bio)
diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c
index 4112071de0be..c68dc1653cfd 100644
--- a/drivers/md/dm-stripe.c
+++ b/drivers/md/dm-stripe.c
@@ -459,6 +459,7 @@ static void stripe_io_hints(struct dm_target *ti,
 	struct stripe_c *sc = ti->private;
 	unsigned int chunk_size = sc->chunk_size << SECTOR_SHIFT;
 
+	limits->chunk_sectors = sc->chunk_size;
 	limits->io_min = chunk_size;
 	limits->io_opt = chunk_size * sc->stripes;
 }
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index dbd39b9722b9..20b8f560a2da 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -431,6 +431,7 @@ static int dm_set_device_limits(struct dm_target *ti, struct dm_dev *dev,
 		return 0;
 	}
 
+	mutex_lock(&q->limits_lock);
 	if (blk_stack_limits(limits, &q->limits,
 			get_start_sect(bdev) + start) < 0)
 		DMWARN("%s: adding target device %pg caused an alignment inconsistency: "
@@ -448,6 +449,7 @@ static int dm_set_device_limits(struct dm_target *ti, struct dm_dev *dev,
 	 */
 	if (!dm_target_has_integrity(ti->type))
 		queue_limits_stack_integrity_bdev(limits, bdev);
+	mutex_unlock(&q->limits_lock);
 	return 0;
 }
 
@@ -523,8 +525,9 @@ static char **realloc_argv(unsigned int *size, char **old_argv)
 		gfp = GFP_NOIO;
 	}
 	argv = kmalloc_array(new_size, sizeof(*argv), gfp);
-	if (argv && old_argv) {
-		memcpy(argv, old_argv, *size * sizeof(*argv));
+	if (argv) {
+		if (old_argv)
+			memcpy(argv, old_argv, *size * sizeof(*argv));
 		*size = new_size;
 	}
 
@@ -697,6 +700,10 @@ int dm_table_add_target(struct dm_table *t, const char *type,
 		DMERR("%s: zero-length target", dm_device_name(t->md));
 		return -EINVAL;
 	}
+	if (start + len < start || start + len > LLONG_MAX >> SECTOR_SHIFT) {
+		DMERR("%s: too large device", dm_device_name(t->md));
+		return -EINVAL;
+	}
 
 	ti->type = dm_get_target_type(type);
 	if (!ti->type) {
@@ -887,17 +894,17 @@ static bool dm_table_supports_dax(struct dm_table *t,
 	return true;
 }
 
-static int device_is_rq_stackable(struct dm_target *ti, struct dm_dev *dev,
-				  sector_t start, sector_t len, void *data)
+static int device_is_not_rq_stackable(struct dm_target *ti, struct dm_dev *dev,
+				      sector_t start, sector_t len, void *data)
 {
 	struct block_device *bdev = dev->bdev;
 	struct request_queue *q = bdev_get_queue(bdev);
 
 	/* request-based cannot stack on partitions! */
 	if (bdev_is_partition(bdev))
-		return false;
+		return true;
 
-	return queue_is_mq(q);
+	return !queue_is_mq(q);
 }
 
 static int dm_table_determine_type(struct dm_table *t)
@@ -993,7 +1000,7 @@ verify_rq_based:
 
 	/* Non-request-stackable devices can't be used for request-based dm */
 	if (!ti->type->iterate_devices ||
-	    !ti->type->iterate_devices(ti, device_is_rq_stackable, NULL)) {
+	    ti->type->iterate_devices(ti, device_is_not_rq_stackable, NULL)) {
 		DMERR("table load rejected: including non-request-stackable devices");
 		return -EINVAL;
 	}
@@ -1182,7 +1189,7 @@ static int dm_keyslot_evict(struct blk_crypto_profile *profile,
 
 	t = dm_get_live_table(md, &srcu_idx);
 	if (!t)
-		return 0;
+		goto put_live_table;
 
 	for (unsigned int i = 0; i < t->num_targets; i++) {
 		struct dm_target *ti = dm_table_get_target(t, i);
@@ -1193,6 +1200,7 @@ static int dm_keyslot_evict(struct blk_crypto_profile *profile,
 					  (void *)key);
 	}
 
+put_live_table:
 	dm_put_live_table(md, srcu_idx);
 	return 0;
 }
@@ -1728,8 +1736,12 @@ static int device_not_write_zeroes_capable(struct dm_target *ti, struct dm_dev *
 					   sector_t start, sector_t len, void *data)
 {
 	struct request_queue *q = bdev_get_queue(dev->bdev);
+	int b;
 
-	return !q->limits.max_write_zeroes_sectors;
+	mutex_lock(&q->limits_lock);
+	b = !q->limits.max_write_zeroes_sectors;
+	mutex_unlock(&q->limits_lock);
+	return b;
 }
 
 static bool dm_table_supports_write_zeroes(struct dm_table *t)
diff --git a/drivers/md/dm-vdo/dedupe.c b/drivers/md/dm-vdo/dedupe.c
index 80628ae93fba..5a74b3a85ec4 100644
--- a/drivers/md/dm-vdo/dedupe.c
+++ b/drivers/md/dm-vdo/dedupe.c
@@ -2178,6 +2178,7 @@ static int initialize_index(struct vdo *vdo, struct hash_zones *zones)
 
 	vdo_set_dedupe_index_timeout_interval(vdo_dedupe_index_timeout_interval);
 	vdo_set_dedupe_index_min_timer_interval(vdo_dedupe_index_min_timer_interval);
+	spin_lock_init(&zones->lock);
 
 	/*
 	 * Since we will save up the timeouts that would have been reported but were ratelimited,
diff --git a/drivers/md/dm-vdo/indexer/index-layout.c b/drivers/md/dm-vdo/indexer/index-layout.c
index 627adc24af3b..053b7845d1f3 100644
--- a/drivers/md/dm-vdo/indexer/index-layout.c
+++ b/drivers/md/dm-vdo/indexer/index-layout.c
@@ -54,7 +54,6 @@
  * Each save also has a unique nonce.
  */
 
-#define MAGIC_SIZE 32
 #define NONCE_INFO_SIZE 32
 #define MAX_SAVES 2
 
@@ -98,9 +97,11 @@ enum region_type {
 #define SUPER_VERSION_CURRENT 3
 #define SUPER_VERSION_MAXIMUM 7
 
-static const u8 LAYOUT_MAGIC[MAGIC_SIZE] = "*ALBIREO*SINGLE*FILE*LAYOUT*001*";
+static const u8 LAYOUT_MAGIC[] = "*ALBIREO*SINGLE*FILE*LAYOUT*001*";
 static const u64 REGION_MAGIC = 0x416c6252676e3031; /* 'AlbRgn01' */
 
+#define MAGIC_SIZE (sizeof(LAYOUT_MAGIC) - 1)
+
 struct region_header {
 	u64 magic;
 	u64 region_blocks;
diff --git a/drivers/md/dm-vdo/indexer/volume.c b/drivers/md/dm-vdo/indexer/volume.c
index 655453bb276b..425b3a74f4db 100644
--- a/drivers/md/dm-vdo/indexer/volume.c
+++ b/drivers/md/dm-vdo/indexer/volume.c
@@ -754,10 +754,11 @@ static int get_volume_page_protected(struct volume *volume, struct uds_request *
 				     u32 physical_page, struct cached_page **page_ptr)
 {
 	struct cached_page *page;
+	unsigned int zone_number = request->zone_number;
 
 	get_page_from_cache(&volume->page_cache, physical_page, &page);
 	if (page != NULL) {
-		if (request->zone_number == 0) {
+		if (zone_number == 0) {
 			/* Only one zone is allowed to update the LRU. */
 			make_page_most_recent(&volume->page_cache, page);
 		}
@@ -767,7 +768,7 @@ static int get_volume_page_protected(struct volume *volume, struct uds_request *
 	}
 
 	/* Prepare to enqueue a read for the page. */
-	end_pending_search(&volume->page_cache, request->zone_number);
+	end_pending_search(&volume->page_cache, zone_number);
 	mutex_lock(&volume->read_threads_mutex);
 
 	/*
@@ -787,8 +788,7 @@ static int get_volume_page_protected(struct volume *volume, struct uds_request *
 		 * the order does not matter for correctness as it does below.
 		 */
 		mutex_unlock(&volume->read_threads_mutex);
-		begin_pending_search(&volume->page_cache, physical_page,
-				     request->zone_number);
+		begin_pending_search(&volume->page_cache, physical_page, zone_number);
 		return UDS_QUEUED;
 	}
 
@@ -797,7 +797,7 @@ static int get_volume_page_protected(struct volume *volume, struct uds_request *
 	 * "search pending" state in careful order so no other thread can mess with the data before
 	 * the caller gets to look at it.
 	 */
-	begin_pending_search(&volume->page_cache, physical_page, request->zone_number);
+	begin_pending_search(&volume->page_cache, physical_page, zone_number);
 	mutex_unlock(&volume->read_threads_mutex);
 	*page_ptr = page;
 	return UDS_SUCCESS;
@@ -849,6 +849,7 @@ static int search_cached_index_page(struct volume *volume, struct uds_request *r
 {
 	int result;
 	struct cached_page *page = NULL;
+	unsigned int zone_number = request->zone_number;
 	u32 physical_page = map_to_physical_page(volume->geometry, chapter,
 						 index_page_number);
 
@@ -858,18 +859,18 @@ static int search_cached_index_page(struct volume *volume, struct uds_request *r
 	 * invalidation by the reader thread, before the reader thread has noticed that the
 	 * invalidate_counter has been incremented.
 	 */
-	begin_pending_search(&volume->page_cache, physical_page, request->zone_number);
+	begin_pending_search(&volume->page_cache, physical_page, zone_number);
 
 	result = get_volume_page_protected(volume, request, physical_page, &page);
 	if (result != UDS_SUCCESS) {
-		end_pending_search(&volume->page_cache, request->zone_number);
+		end_pending_search(&volume->page_cache, zone_number);
 		return result;
 	}
 
 	result = uds_search_chapter_index_page(&page->index_page, volume->geometry,
 					       &request->record_name,
 					       record_page_number);
-	end_pending_search(&volume->page_cache, request->zone_number);
+	end_pending_search(&volume->page_cache, zone_number);
 	return result;
 }
 
@@ -882,6 +883,7 @@ int uds_search_cached_record_page(struct volume *volume, struct uds_request *req
 {
 	struct cached_page *record_page;
 	struct index_geometry *geometry = volume->geometry;
+	unsigned int zone_number = request->zone_number;
 	int result;
 	u32 physical_page, page_number;
 
@@ -905,11 +907,11 @@ int uds_search_cached_record_page(struct volume *volume, struct uds_request *req
 	 * invalidation by the reader thread, before the reader thread has noticed that the
 	 * invalidate_counter has been incremented.
 	 */
-	begin_pending_search(&volume->page_cache, physical_page, request->zone_number);
+	begin_pending_search(&volume->page_cache, physical_page, zone_number);
 
 	result = get_volume_page_protected(volume, request, physical_page, &record_page);
 	if (result != UDS_SUCCESS) {
-		end_pending_search(&volume->page_cache, request->zone_number);
+		end_pending_search(&volume->page_cache, zone_number);
 		return result;
 	}
 
@@ -917,7 +919,7 @@ int uds_search_cached_record_page(struct volume *volume, struct uds_request *req
 			       &request->record_name, geometry, &request->old_metadata))
 		*found = true;
 
-	end_pending_search(&volume->page_cache, request->zone_number);
+	end_pending_search(&volume->page_cache, zone_number);
 	return UDS_SUCCESS;
 }
 
diff --git a/drivers/md/dm-vdo/vdo.c b/drivers/md/dm-vdo/vdo.c
index fff847767755..b897f88250d2 100644
--- a/drivers/md/dm-vdo/vdo.c
+++ b/drivers/md/dm-vdo/vdo.c
@@ -31,9 +31,7 @@
 
 #include <linux/completion.h>
 #include <linux/device-mapper.h>
-#include <linux/kernel.h>
 #include <linux/lz4.h>
-#include <linux/module.h>
 #include <linux/mutex.h>
 #include <linux/spinlock.h>
 #include <linux/types.h>
@@ -142,12 +140,6 @@ static void finish_vdo_request_queue(void *ptr)
 	vdo_unregister_allocating_thread();
 }
 
-#ifdef MODULE
-#define MODULE_NAME THIS_MODULE->name
-#else
-#define MODULE_NAME "dm-vdo"
-#endif  /* MODULE */
-
 static const struct vdo_work_queue_type default_queue_type = {
 	.start = start_vdo_request_queue,
 	.finish = finish_vdo_request_queue,
@@ -559,8 +551,7 @@ int vdo_make(unsigned int instance, struct device_config *config, char **reason,
 	*vdo_ptr = vdo;
 
 	snprintf(vdo->thread_name_prefix, sizeof(vdo->thread_name_prefix),
-		 "%s%u", MODULE_NAME, instance);
-	BUG_ON(vdo->thread_name_prefix[0] == '\0');
+		 "vdo%u", instance);
 	result = vdo_allocate(vdo->thread_config.thread_count,
 			      struct vdo_thread, __func__, &vdo->threads);
 	if (result != VDO_SUCCESS) {
diff --git a/drivers/md/dm-verity-fec.c b/drivers/md/dm-verity-fec.c
index 6bd9848518d4..559b8179ac50 100644
--- a/drivers/md/dm-verity-fec.c
+++ b/drivers/md/dm-verity-fec.c
@@ -604,6 +604,10 @@ int verity_fec_parse_opt_args(struct dm_arg_set *as, struct dm_verity *v,
 	(*argc)--;
 
 	if (!strcasecmp(arg_name, DM_VERITY_OPT_FEC_DEV)) {
+		if (v->fec->dev) {
+			ti->error = "FEC device already specified";
+			return -EINVAL;
+		}
 		r = dm_get_device(ti, arg_value, BLK_OPEN_READ, &v->fec->dev);
 		if (r) {
 			ti->error = "FEC device lookup failed";
diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c
index c142ec5458b7..ce0462e751a6 100644
--- a/drivers/md/dm-verity-target.c
+++ b/drivers/md/dm-verity-target.c
@@ -796,6 +796,13 @@ static int verity_map(struct dm_target *ti, struct bio *bio)
 	return DM_MAPIO_SUBMITTED;
 }
 
+static void verity_postsuspend(struct dm_target *ti)
+{
+	struct dm_verity *v = ti->private;
+	flush_workqueue(v->verify_wq);
+	dm_bufio_client_reset(v->bufio);
+}
+
 /*
  * Status: V (valid) or C (corruption found)
  */
@@ -1073,6 +1080,9 @@ static int verity_alloc_most_once(struct dm_verity *v)
 {
 	struct dm_target *ti = v->ti;
 
+	if (v->validated_blocks)
+		return 0;
+
 	/* the bitset can only handle INT_MAX blocks */
 	if (v->data_blocks > INT_MAX) {
 		ti->error = "device too large to use check_at_most_once";
@@ -1096,6 +1106,9 @@ static int verity_alloc_zero_digest(struct dm_verity *v)
 	struct dm_verity_io *io;
 	u8 *zero_data;
 
+	if (v->zero_digest)
+		return 0;
+
 	v->zero_digest = kmalloc(v->digest_size, GFP_KERNEL);
 
 	if (!v->zero_digest)
@@ -1530,7 +1543,7 @@ static int verity_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 			goto bad;
 	}
 
-	/* Root hash signature is  a optional parameter*/
+	/* Root hash signature is an optional parameter */
 	r = verity_verify_root_hash(root_hash_digest_to_validate,
 				    strlen(root_hash_digest_to_validate),
 				    verify_args.sig,
@@ -1766,6 +1779,7 @@ static struct target_type verity_target = {
 	.ctr		= verity_ctr,
 	.dtr		= verity_dtr,
 	.map		= verity_map,
+	.postsuspend	= verity_postsuspend,
 	.status		= verity_status,
 	.prepare_ioctl	= verity_prepare_ioctl,
 	.iterate_devices = verity_iterate_devices,
diff --git a/drivers/md/dm-verity-verify-sig.c b/drivers/md/dm-verity-verify-sig.c
index a9e2c6c0a33c..d5261a0e4232 100644
--- a/drivers/md/dm-verity-verify-sig.c
+++ b/drivers/md/dm-verity-verify-sig.c
@@ -71,9 +71,14 @@ int verity_verify_sig_parse_opt_args(struct dm_arg_set *as,
 				     const char *arg_name)
 {
 	struct dm_target *ti = v->ti;
-	int ret = 0;
+	int ret;
 	const char *sig_key = NULL;
 
+	if (v->signature_key_desc) {
+		ti->error = DM_VERITY_VERIFY_ERR("root_hash_sig_key_desc already specified");
+		return -EINVAL;
+	}
+
 	if (!*argc) {
 		ti->error = DM_VERITY_VERIFY_ERR("Signature key not specified");
 		return -EINVAL;
@@ -83,14 +88,18 @@ int verity_verify_sig_parse_opt_args(struct dm_arg_set *as,
 	(*argc)--;
 
 	ret = verity_verify_get_sig_from_key(sig_key, sig_opts);
-	if (ret < 0)
+	if (ret < 0) {
 		ti->error = DM_VERITY_VERIFY_ERR("Invalid key specified");
+		return ret;
+	}
 
 	v->signature_key_desc = kstrdup(sig_key, GFP_KERNEL);
-	if (!v->signature_key_desc)
+	if (!v->signature_key_desc) {
+		ti->error = DM_VERITY_VERIFY_ERR("Could not allocate memory for signature key");
 		return -ENOMEM;
+	}
 
-	return ret;
+	return 0;
 }
 
 /*
diff --git a/drivers/md/dm-zone.c b/drivers/md/dm-zone.c
index c0d41c36e06e..04cc36a9d5ca 100644
--- a/drivers/md/dm-zone.c
+++ b/drivers/md/dm-zone.c
@@ -56,24 +56,31 @@ int dm_blk_report_zones(struct gendisk *disk, sector_t sector,
 {
 	struct mapped_device *md = disk->private_data;
 	struct dm_table *map;
-	int srcu_idx, ret;
+	struct dm_table *zone_revalidate_map = md->zone_revalidate_map;
+	int srcu_idx, ret = -EIO;
+	bool put_table = false;
 
-	if (!md->zone_revalidate_map) {
-		/* Regular user context */
+	if (!zone_revalidate_map || md->revalidate_map_task != current) {
+		/*
+		 * Regular user context or
+		 * Zone revalidation during __bind() is in progress, but this
+		 * call is from a different process
+		 */
 		if (dm_suspended_md(md))
 			return -EAGAIN;
 
 		map = dm_get_live_table(md, &srcu_idx);
-		if (!map)
-			return -EIO;
+		put_table = true;
 	} else {
 		/* Zone revalidation during __bind() */
-		map = md->zone_revalidate_map;
+		map = zone_revalidate_map;
 	}
 
-	ret = dm_blk_do_report_zones(md, map, sector, nr_zones, cb, data);
+	if (map)
+		ret = dm_blk_do_report_zones(md, map, sector, nr_zones, cb,
+					     data);
 
-	if (!md->zone_revalidate_map)
+	if (put_table)
 		dm_put_live_table(md, srcu_idx);
 
 	return ret;
@@ -175,7 +182,9 @@ int dm_revalidate_zones(struct dm_table *t, struct request_queue *q)
 	 * our table for dm_blk_report_zones() to use directly.
 	 */
 	md->zone_revalidate_map = t;
+	md->revalidate_map_task = current;
 	ret = blk_revalidate_disk_zones(disk);
+	md->revalidate_map_task = NULL;
 	md->zone_revalidate_map = NULL;
 
 	if (ret) {
diff --git a/drivers/md/dm-zoned-target.c b/drivers/md/dm-zoned-target.c
index 6141fc25d842..c38bd6e4c273 100644
--- a/drivers/md/dm-zoned-target.c
+++ b/drivers/md/dm-zoned-target.c
@@ -1061,7 +1061,7 @@ static int dmz_iterate_devices(struct dm_target *ti,
 	struct dmz_target *dmz = ti->private;
 	unsigned int zone_nr_sectors = dmz_zone_nr_sectors(dmz->metadata);
 	sector_t capacity;
-	int i, r;
+	int i, r = 0;
 
 	for (i = 0; i < dmz->nr_ddevs; i++) {
 		capacity = dmz->dev[i].capacity & ~(zone_nr_sectors - 1);
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 19230404d8c2..c5dcd632404c 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1541,14 +1541,18 @@ static void __send_empty_flush(struct clone_info *ci)
 {
 	struct dm_table *t = ci->map;
 	struct bio flush_bio;
+	blk_opf_t opf = REQ_OP_WRITE | REQ_PREFLUSH | REQ_SYNC;
+
+	if ((ci->io->orig_bio->bi_opf & (REQ_IDLE | REQ_SYNC)) ==
+	    (REQ_IDLE | REQ_SYNC))
+		opf |= REQ_IDLE;
 
 	/*
 	 * Use an on-stack bio for this, it's safe since we don't
 	 * need to reference it after submit. It's just used as
 	 * the basis for the clone(s).
 	 */
-	bio_init(&flush_bio, ci->io->md->disk->part0, NULL, 0,
-		 REQ_OP_WRITE | REQ_PREFLUSH | REQ_SYNC);
+	bio_init(&flush_bio, ci->io->md->disk->part0, NULL, 0, opf);
 
 	ci->bio = &flush_bio;
 	ci->sector_count = 0;
@@ -1784,19 +1788,35 @@ static void init_clone_info(struct clone_info *ci, struct dm_io *io,
 }
 
 #ifdef CONFIG_BLK_DEV_ZONED
-static inline bool dm_zone_bio_needs_split(struct mapped_device *md,
-					   struct bio *bio)
+static inline bool dm_zone_bio_needs_split(struct bio *bio)
 {
 	/*
-	 * For mapped device that need zone append emulation, we must
-	 * split any large BIO that straddles zone boundaries.
+	 * Special case the zone operations that cannot or should not be split.
 	 */
-	return dm_emulate_zone_append(md) && bio_straddles_zones(bio) &&
-		!bio_flagged(bio, BIO_ZONE_WRITE_PLUGGING);
+	switch (bio_op(bio)) {
+	case REQ_OP_ZONE_APPEND:
+	case REQ_OP_ZONE_FINISH:
+	case REQ_OP_ZONE_RESET:
+	case REQ_OP_ZONE_RESET_ALL:
+		return false;
+	default:
+		break;
+	}
+
+	/*
+	 * When mapped devices use the block layer zone write plugging, we must
+	 * split any large BIO to the mapped device limits to not submit BIOs
+	 * that span zone boundaries and to avoid potential deadlocks with
+	 * queue freeze operations.
+	 */
+	return bio_needs_zone_write_plugging(bio) || bio_straddles_zones(bio);
 }
+
 static inline bool dm_zone_plug_bio(struct mapped_device *md, struct bio *bio)
 {
-	return dm_emulate_zone_append(md) && blk_zone_plug_bio(bio, 0);
+	if (!bio_needs_zone_write_plugging(bio))
+		return false;
+	return blk_zone_plug_bio(bio, 0);
 }
 
 static blk_status_t __send_zone_reset_all_emulated(struct clone_info *ci,
@@ -1912,8 +1932,7 @@ static blk_status_t __send_zone_reset_all(struct clone_info *ci)
 }
 
 #else
-static inline bool dm_zone_bio_needs_split(struct mapped_device *md,
-					   struct bio *bio)
+static inline bool dm_zone_bio_needs_split(struct bio *bio)
 {
 	return false;
 }
@@ -1940,9 +1959,7 @@ static void dm_split_and_process_bio(struct mapped_device *md,
 
 	is_abnormal = is_abnormal_io(bio);
 	if (static_branch_unlikely(&zoned_enabled)) {
-		/* Special case REQ_OP_ZONE_RESET_ALL as it cannot be split. */
-		need_split = (bio_op(bio) != REQ_OP_ZONE_RESET_ALL) &&
-			(is_abnormal || dm_zone_bio_needs_split(md, bio));
+		need_split = is_abnormal || dm_zone_bio_needs_split(bio);
 	} else {
 		need_split = is_abnormal;
 	}
@@ -2406,21 +2423,29 @@ static struct dm_table *__bind(struct mapped_device *md, struct dm_table *t,
 			       struct queue_limits *limits)
 {
 	struct dm_table *old_map;
-	sector_t size;
+	sector_t size, old_size;
 	int ret;
 
 	lockdep_assert_held(&md->suspend_lock);
 
 	size = dm_table_get_size(t);
 
+	old_size = dm_get_size(md);
+	set_capacity(md->disk, size);
+
+	ret = dm_table_set_restrictions(t, md->queue, limits);
+	if (ret) {
+		set_capacity(md->disk, old_size);
+		old_map = ERR_PTR(ret);
+		goto out;
+	}
+
 	/*
 	 * Wipe any geometry if the size of the table changed.
 	 */
-	if (size != dm_get_size(md))
+	if (size != old_size)
 		memset(&md->geometry, 0, sizeof(md->geometry));
 
-	set_capacity(md->disk, size);
-
 	dm_table_event_callback(t, event_callback, md);
 
 	if (dm_table_request_based(t)) {
@@ -2438,10 +2463,10 @@ static struct dm_table *__bind(struct mapped_device *md, struct dm_table *t,
 		 * requests in the queue may refer to bio from the old bioset,
 		 * so you must walk through the queue to unprep.
 		 */
-		if (!md->mempools) {
+		if (!md->mempools)
 			md->mempools = t->mempools;
-			t->mempools = NULL;
-		}
+		else
+			dm_free_md_mempools(t->mempools);
 	} else {
 		/*
 		 * The md may already have mempools that need changing.
@@ -2450,14 +2475,8 @@ static struct dm_table *__bind(struct mapped_device *md, struct dm_table *t,
 		 */
 		dm_free_md_mempools(md->mempools);
 		md->mempools = t->mempools;
-		t->mempools = NULL;
-	}
-
-	ret = dm_table_set_restrictions(t, md->queue, limits);
-	if (ret) {
-		old_map = ERR_PTR(ret);
-		goto out;
 	}
+	t->mempools = NULL;
 
 	old_map = rcu_dereference_protected(md->map, lockdep_is_held(&md->suspend_lock));
 	rcu_assign_pointer(md->map, (void *)t);
diff --git a/drivers/md/md-autodetect.c b/drivers/md/md-autodetect.c
index b2a00f213c2c..4b80165afd23 100644
--- a/drivers/md/md-autodetect.c
+++ b/drivers/md/md-autodetect.c
@@ -49,6 +49,7 @@ static int md_setup_ents __initdata;
  *             instead of just one.  -- KTK
  * 18May2000: Added support for persistent-superblock arrays:
  *             md=n,0,factor,fault,device-list   uses RAID0 for device n
+ *             md=n,-1,factor,fault,device-list  uses LINEAR for device n
  *             md=n,device-list      reads a RAID superblock from the devices
  *             elements in device-list are read by name_to_kdev_t so can be
  *             a hex number or something like /dev/hda1 /dev/sdb
@@ -87,7 +88,7 @@ static int __init md_setup(char *str)
 		md_setup_ents++;
 	switch (get_option(&str, &level)) {	/* RAID level */
 	case 2: /* could be 0 or -1.. */
-		if (level == 0) {
+		if (level == 0 || level == LEVEL_LINEAR) {
 			if (get_option(&str, &factor) != 2 ||	/* Chunk Size */
 					get_option(&str, &fault) != 2) {
 				printk(KERN_WARNING "md: Too few arguments supplied to md=.\n");
@@ -95,7 +96,10 @@ static int __init md_setup(char *str)
 			}
 			md_setup_args[ent].level = level;
 			md_setup_args[ent].chunk = 1 << (factor+12);
-			pername = "raid0";
+			if (level ==  LEVEL_LINEAR)
+				pername = "linear";
+			else
+				pername = "raid0";
 			break;
 		}
 		fallthrough;
diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c
index c3a42dd66ce5..0da1d0723f88 100644
--- a/drivers/md/md-bitmap.c
+++ b/drivers/md/md-bitmap.c
@@ -787,7 +787,7 @@ static int md_bitmap_new_disk_sb(struct bitmap *bitmap)
 	 * is a good choice?  We choose COUNTER_MAX / 2 arbitrarily.
 	 */
 	write_behind = bitmap->mddev->bitmap_info.max_write_behind;
-	if (write_behind > COUNTER_MAX)
+	if (write_behind > COUNTER_MAX / 2)
 		write_behind = COUNTER_MAX / 2;
 	sb->write_behind = cpu_to_le32(write_behind);
 	bitmap->mddev->bitmap_info.max_write_behind = write_behind;
@@ -1671,24 +1671,13 @@ __acquires(bitmap->lock)
 }
 
 static int bitmap_startwrite(struct mddev *mddev, sector_t offset,
-			     unsigned long sectors, bool behind)
+			     unsigned long sectors)
 {
 	struct bitmap *bitmap = mddev->bitmap;
 
 	if (!bitmap)
 		return 0;
 
-	if (behind) {
-		int bw;
-		atomic_inc(&bitmap->behind_writes);
-		bw = atomic_read(&bitmap->behind_writes);
-		if (bw > bitmap->behind_writes_used)
-			bitmap->behind_writes_used = bw;
-
-		pr_debug("inc write-behind count %d/%lu\n",
-			 bw, bitmap->mddev->bitmap_info.max_write_behind);
-	}
-
 	while (sectors) {
 		sector_t blocks;
 		bitmap_counter_t *bmc;
@@ -1737,21 +1726,13 @@ static int bitmap_startwrite(struct mddev *mddev, sector_t offset,
 }
 
 static void bitmap_endwrite(struct mddev *mddev, sector_t offset,
-			    unsigned long sectors, bool success, bool behind)
+			    unsigned long sectors)
 {
 	struct bitmap *bitmap = mddev->bitmap;
 
 	if (!bitmap)
 		return;
 
-	if (behind) {
-		if (atomic_dec_and_test(&bitmap->behind_writes))
-			wake_up(&bitmap->behind_wait);
-		pr_debug("dec write-behind count %d/%lu\n",
-			 atomic_read(&bitmap->behind_writes),
-			 bitmap->mddev->bitmap_info.max_write_behind);
-	}
-
 	while (sectors) {
 		sector_t blocks;
 		unsigned long flags;
@@ -1764,15 +1745,16 @@ static void bitmap_endwrite(struct mddev *mddev, sector_t offset,
 			return;
 		}
 
-		if (success && !bitmap->mddev->degraded &&
-		    bitmap->events_cleared < bitmap->mddev->events) {
-			bitmap->events_cleared = bitmap->mddev->events;
-			bitmap->need_sync = 1;
-			sysfs_notify_dirent_safe(bitmap->sysfs_can_clear);
-		}
-
-		if (!success && !NEEDED(*bmc))
+		if (!bitmap->mddev->degraded) {
+			if (bitmap->events_cleared < bitmap->mddev->events) {
+				bitmap->events_cleared = bitmap->mddev->events;
+				bitmap->need_sync = 1;
+				sysfs_notify_dirent_safe(
+						bitmap->sysfs_can_clear);
+			}
+		} else if (!NEEDED(*bmc)) {
 			*bmc |= NEEDED_MASK;
+		}
 
 		if (COUNTER(*bmc) == COUNTER_MAX)
 			wake_up(&bitmap->overflow_wait);
@@ -2062,6 +2044,37 @@ static void md_bitmap_free(void *data)
 	kfree(bitmap);
 }
 
+static void bitmap_start_behind_write(struct mddev *mddev)
+{
+	struct bitmap *bitmap = mddev->bitmap;
+	int bw;
+
+	if (!bitmap)
+		return;
+
+	atomic_inc(&bitmap->behind_writes);
+	bw = atomic_read(&bitmap->behind_writes);
+	if (bw > bitmap->behind_writes_used)
+		bitmap->behind_writes_used = bw;
+
+	pr_debug("inc write-behind count %d/%lu\n",
+		 bw, bitmap->mddev->bitmap_info.max_write_behind);
+}
+
+static void bitmap_end_behind_write(struct mddev *mddev)
+{
+	struct bitmap *bitmap = mddev->bitmap;
+
+	if (!bitmap)
+		return;
+
+	if (atomic_dec_and_test(&bitmap->behind_writes))
+		wake_up(&bitmap->behind_wait);
+	pr_debug("dec write-behind count %d/%lu\n",
+		 atomic_read(&bitmap->behind_writes),
+		 bitmap->mddev->bitmap_info.max_write_behind);
+}
+
 static void bitmap_wait_behind_writes(struct mddev *mddev)
 {
 	struct bitmap *bitmap = mddev->bitmap;
@@ -2342,7 +2355,8 @@ static int bitmap_get_stats(void *data, struct md_bitmap_stats *stats)
 
 	if (!bitmap)
 		return -ENOENT;
-
+	if (!bitmap->storage.sb_page)
+		return -EINVAL;
 	sb = kmap_local_page(bitmap->storage.sb_page);
 	stats->sync_size = le64_to_cpu(sb->sync_size);
 	kunmap_local(sb);
@@ -2981,6 +2995,9 @@ static struct bitmap_operations bitmap_ops = {
 	.dirty_bits		= bitmap_dirty_bits,
 	.unplug			= bitmap_unplug,
 	.daemon_work		= bitmap_daemon_work,
+
+	.start_behind_write	= bitmap_start_behind_write,
+	.end_behind_write	= bitmap_end_behind_write,
 	.wait_behind_writes	= bitmap_wait_behind_writes,
 
 	.startwrite		= bitmap_startwrite,
diff --git a/drivers/md/md-bitmap.h b/drivers/md/md-bitmap.h
index 662e6fc141a7..31c93019c76b 100644
--- a/drivers/md/md-bitmap.h
+++ b/drivers/md/md-bitmap.h
@@ -84,12 +84,15 @@ struct bitmap_operations {
 			   unsigned long e);
 	void (*unplug)(struct mddev *mddev, bool sync);
 	void (*daemon_work)(struct mddev *mddev);
+
+	void (*start_behind_write)(struct mddev *mddev);
+	void (*end_behind_write)(struct mddev *mddev);
 	void (*wait_behind_writes)(struct mddev *mddev);
 
 	int (*startwrite)(struct mddev *mddev, sector_t offset,
-			  unsigned long sectors, bool behind);
+			  unsigned long sectors);
 	void (*endwrite)(struct mddev *mddev, sector_t offset,
-			 unsigned long sectors, bool success, bool behind);
+			 unsigned long sectors);
 	bool (*start_sync)(struct mddev *mddev, sector_t offset,
 			   sector_t *blocks, bool degraded);
 	void (*end_sync)(struct mddev *mddev, sector_t offset, sector_t *blocks);
diff --git a/drivers/md/md-linear.c b/drivers/md/md-linear.c
new file mode 100644
index 000000000000..369aed044b40
--- /dev/null
+++ b/drivers/md/md-linear.c
@@ -0,0 +1,352 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * linear.c : Multiple Devices driver for Linux Copyright (C) 1994-96 Marc
+ * ZYNGIER <zyngier@ufr-info-p7.ibp.fr> or <maz@gloups.fdn.fr>
+ */
+
+#include <linux/blkdev.h>
+#include <linux/raid/md_u.h>
+#include <linux/seq_file.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <trace/events/block.h>
+#include "md.h"
+
+struct dev_info {
+	struct md_rdev	*rdev;
+	sector_t	end_sector;
+};
+
+struct linear_conf {
+	struct rcu_head         rcu;
+	sector_t                array_sectors;
+	/* a copy of mddev->raid_disks */
+	int                     raid_disks;
+	struct dev_info         disks[] __counted_by(raid_disks);
+};
+
+/*
+ * find which device holds a particular offset
+ */
+static inline struct dev_info *which_dev(struct mddev *mddev, sector_t sector)
+{
+	int lo, mid, hi;
+	struct linear_conf *conf;
+
+	lo = 0;
+	hi = mddev->raid_disks - 1;
+	conf = mddev->private;
+
+	/*
+	 * Binary Search
+	 */
+
+	while (hi > lo) {
+
+		mid = (hi + lo) / 2;
+		if (sector < conf->disks[mid].end_sector)
+			hi = mid;
+		else
+			lo = mid + 1;
+	}
+
+	return conf->disks + lo;
+}
+
+static sector_t linear_size(struct mddev *mddev, sector_t sectors, int raid_disks)
+{
+	struct linear_conf *conf;
+	sector_t array_sectors;
+
+	conf = mddev->private;
+	WARN_ONCE(sectors || raid_disks,
+		  "%s does not support generic reshape\n", __func__);
+	array_sectors = conf->array_sectors;
+
+	return array_sectors;
+}
+
+static int linear_set_limits(struct mddev *mddev)
+{
+	struct queue_limits lim;
+	int err;
+
+	md_init_stacking_limits(&lim);
+	lim.max_hw_sectors = mddev->chunk_sectors;
+	lim.max_write_zeroes_sectors = mddev->chunk_sectors;
+	lim.io_min = mddev->chunk_sectors << 9;
+	err = mddev_stack_rdev_limits(mddev, &lim, MDDEV_STACK_INTEGRITY);
+	if (err)
+		return err;
+
+	return queue_limits_set(mddev->gendisk->queue, &lim);
+}
+
+static struct linear_conf *linear_conf(struct mddev *mddev, int raid_disks)
+{
+	struct linear_conf *conf;
+	struct md_rdev *rdev;
+	int ret = -EINVAL;
+	int cnt;
+	int i;
+
+	conf = kzalloc(struct_size(conf, disks, raid_disks), GFP_KERNEL);
+	if (!conf)
+		return ERR_PTR(-ENOMEM);
+
+	/*
+	 * conf->raid_disks is copy of mddev->raid_disks. The reason to
+	 * keep a copy of mddev->raid_disks in struct linear_conf is,
+	 * mddev->raid_disks may not be consistent with pointers number of
+	 * conf->disks[] when it is updated in linear_add() and used to
+	 * iterate old conf->disks[] earray in linear_congested().
+	 * Here conf->raid_disks is always consitent with number of
+	 * pointers in conf->disks[] array, and mddev->private is updated
+	 * with rcu_assign_pointer() in linear_addr(), such race can be
+	 * avoided.
+	 */
+	conf->raid_disks = raid_disks;
+
+	cnt = 0;
+	conf->array_sectors = 0;
+
+	rdev_for_each(rdev, mddev) {
+		int j = rdev->raid_disk;
+		struct dev_info *disk = conf->disks + j;
+		sector_t sectors;
+
+		if (j < 0 || j >= raid_disks || disk->rdev) {
+			pr_warn("md/linear:%s: disk numbering problem. Aborting!\n",
+				mdname(mddev));
+			goto out;
+		}
+
+		disk->rdev = rdev;
+		if (mddev->chunk_sectors) {
+			sectors = rdev->sectors;
+			sector_div(sectors, mddev->chunk_sectors);
+			rdev->sectors = sectors * mddev->chunk_sectors;
+		}
+
+		conf->array_sectors += rdev->sectors;
+		cnt++;
+	}
+	if (cnt != raid_disks) {
+		pr_warn("md/linear:%s: not enough drives present. Aborting!\n",
+			mdname(mddev));
+		goto out;
+	}
+
+	/*
+	 * Here we calculate the device offsets.
+	 */
+	conf->disks[0].end_sector = conf->disks[0].rdev->sectors;
+
+	for (i = 1; i < raid_disks; i++)
+		conf->disks[i].end_sector =
+			conf->disks[i-1].end_sector +
+			conf->disks[i].rdev->sectors;
+
+	if (!mddev_is_dm(mddev)) {
+		ret = linear_set_limits(mddev);
+		if (ret)
+			goto out;
+	}
+
+	return conf;
+
+out:
+	kfree(conf);
+	return ERR_PTR(ret);
+}
+
+static int linear_run(struct mddev *mddev)
+{
+	struct linear_conf *conf;
+	int ret;
+
+	if (md_check_no_bitmap(mddev))
+		return -EINVAL;
+
+	conf = linear_conf(mddev, mddev->raid_disks);
+	if (IS_ERR(conf))
+		return PTR_ERR(conf);
+
+	mddev->private = conf;
+	md_set_array_sectors(mddev, linear_size(mddev, 0, 0));
+
+	ret =  md_integrity_register(mddev);
+	if (ret) {
+		kfree(conf);
+		mddev->private = NULL;
+	}
+	return ret;
+}
+
+static int linear_add(struct mddev *mddev, struct md_rdev *rdev)
+{
+	/* Adding a drive to a linear array allows the array to grow.
+	 * It is permitted if the new drive has a matching superblock
+	 * already on it, with raid_disk equal to raid_disks.
+	 * It is achieved by creating a new linear_private_data structure
+	 * and swapping it in in-place of the current one.
+	 * The current one is never freed until the array is stopped.
+	 * This avoids races.
+	 */
+	struct linear_conf *newconf, *oldconf;
+
+	if (rdev->saved_raid_disk != mddev->raid_disks)
+		return -EINVAL;
+
+	rdev->raid_disk = rdev->saved_raid_disk;
+	rdev->saved_raid_disk = -1;
+
+	newconf = linear_conf(mddev, mddev->raid_disks + 1);
+	if (IS_ERR(newconf))
+		return PTR_ERR(newconf);
+
+	/* newconf->raid_disks already keeps a copy of * the increased
+	 * value of mddev->raid_disks, WARN_ONCE() is just used to make
+	 * sure of this. It is possible that oldconf is still referenced
+	 * in linear_congested(), therefore kfree_rcu() is used to free
+	 * oldconf until no one uses it anymore.
+	 */
+	oldconf = rcu_dereference_protected(mddev->private,
+			lockdep_is_held(&mddev->reconfig_mutex));
+	mddev->raid_disks++;
+	WARN_ONCE(mddev->raid_disks != newconf->raid_disks,
+		"copied raid_disks doesn't match mddev->raid_disks");
+	rcu_assign_pointer(mddev->private, newconf);
+	md_set_array_sectors(mddev, linear_size(mddev, 0, 0));
+	set_capacity_and_notify(mddev->gendisk, mddev->array_sectors);
+	kfree_rcu(oldconf, rcu);
+	return 0;
+}
+
+static void linear_free(struct mddev *mddev, void *priv)
+{
+	struct linear_conf *conf = priv;
+
+	kfree(conf);
+}
+
+static bool linear_make_request(struct mddev *mddev, struct bio *bio)
+{
+	struct dev_info *tmp_dev;
+	sector_t start_sector, end_sector, data_offset;
+	sector_t bio_sector = bio->bi_iter.bi_sector;
+
+	if (unlikely(bio->bi_opf & REQ_PREFLUSH)
+	    && md_flush_request(mddev, bio))
+		return true;
+
+	tmp_dev = which_dev(mddev, bio_sector);
+	start_sector = tmp_dev->end_sector - tmp_dev->rdev->sectors;
+	end_sector = tmp_dev->end_sector;
+	data_offset = tmp_dev->rdev->data_offset;
+
+	if (unlikely(bio_sector >= end_sector ||
+		     bio_sector < start_sector))
+		goto out_of_bounds;
+
+	if (unlikely(is_rdev_broken(tmp_dev->rdev))) {
+		md_error(mddev, tmp_dev->rdev);
+		bio_io_error(bio);
+		return true;
+	}
+
+	if (unlikely(bio_end_sector(bio) > end_sector)) {
+		/* This bio crosses a device boundary, so we have to split it */
+		struct bio *split = bio_split(bio, end_sector - bio_sector,
+					      GFP_NOIO, &mddev->bio_set);
+
+		if (IS_ERR(split)) {
+			bio->bi_status = errno_to_blk_status(PTR_ERR(split));
+			bio_endio(bio);
+			return true;
+		}
+
+		bio_chain(split, bio);
+		submit_bio_noacct(bio);
+		bio = split;
+	}
+
+	md_account_bio(mddev, &bio);
+	bio_set_dev(bio, tmp_dev->rdev->bdev);
+	bio->bi_iter.bi_sector = bio->bi_iter.bi_sector -
+		start_sector + data_offset;
+
+	if (unlikely((bio_op(bio) == REQ_OP_DISCARD) &&
+		     !bdev_max_discard_sectors(bio->bi_bdev))) {
+		/* Just ignore it */
+		bio_endio(bio);
+	} else {
+		if (mddev->gendisk)
+			trace_block_bio_remap(bio, disk_devt(mddev->gendisk),
+					      bio_sector);
+		mddev_check_write_zeroes(mddev, bio);
+		submit_bio_noacct(bio);
+	}
+	return true;
+
+out_of_bounds:
+	pr_err("md/linear:%s: make_request: Sector %llu out of bounds on dev %pg: %llu sectors, offset %llu\n",
+	       mdname(mddev),
+	       (unsigned long long)bio->bi_iter.bi_sector,
+	       tmp_dev->rdev->bdev,
+	       (unsigned long long)tmp_dev->rdev->sectors,
+	       (unsigned long long)start_sector);
+	bio_io_error(bio);
+	return true;
+}
+
+static void linear_status(struct seq_file *seq, struct mddev *mddev)
+{
+	seq_printf(seq, " %dk rounding", mddev->chunk_sectors / 2);
+}
+
+static void linear_error(struct mddev *mddev, struct md_rdev *rdev)
+{
+	if (!test_and_set_bit(MD_BROKEN, &mddev->flags)) {
+		char *md_name = mdname(mddev);
+
+		pr_crit("md/linear%s: Disk failure on %pg detected, failing array.\n",
+			md_name, rdev->bdev);
+	}
+}
+
+static void linear_quiesce(struct mddev *mddev, int state)
+{
+}
+
+static struct md_personality linear_personality = {
+	.name		= "linear",
+	.level		= LEVEL_LINEAR,
+	.owner		= THIS_MODULE,
+	.make_request	= linear_make_request,
+	.run		= linear_run,
+	.free		= linear_free,
+	.status		= linear_status,
+	.hot_add_disk	= linear_add,
+	.size		= linear_size,
+	.quiesce	= linear_quiesce,
+	.error_handler	= linear_error,
+};
+
+static int __init linear_init(void)
+{
+	return register_md_personality(&linear_personality);
+}
+
+static void linear_exit(void)
+{
+	unregister_md_personality(&linear_personality);
+}
+
+module_init(linear_init);
+module_exit(linear_exit);
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Linear device concatenation personality for MD (deprecated)");
+MODULE_ALIAS("md-personality-1"); /* LINEAR - deprecated*/
+MODULE_ALIAS("md-linear");
+MODULE_ALIAS("md-level--1");
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 67108c397c5a..4b3291723670 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -629,6 +629,12 @@ static void __mddev_put(struct mddev *mddev)
 	queue_work(md_misc_wq, &mddev->del_work);
 }
 
+static void mddev_put_locked(struct mddev *mddev)
+{
+	if (atomic_dec_and_test(&mddev->active))
+		__mddev_put(mddev);
+}
+
 void mddev_put(struct mddev *mddev)
 {
 	if (!atomic_dec_and_lock(&mddev->active, &all_mddevs_lock))
@@ -8124,7 +8130,7 @@ void md_error(struct mddev *mddev, struct md_rdev *rdev)
 		return;
 	mddev->pers->error_handler(mddev, rdev);
 
-	if (mddev->pers->level == 0)
+	if (mddev->pers->level == 0 || mddev->pers->level == LEVEL_LINEAR)
 		return;
 
 	if (mddev->degraded && !test_bit(MD_BROKEN, &mddev->flags))
@@ -8376,6 +8382,10 @@ static int md_seq_show(struct seq_file *seq, void *v)
 		return 0;
 
 	spin_unlock(&all_mddevs_lock);
+
+	/* prevent bitmap to be freed after checking */
+	mutex_lock(&mddev->bitmap_info.mutex);
+
 	spin_lock(&mddev->lock);
 	if (mddev->pers || mddev->raid_disks || !list_empty(&mddev->disks)) {
 		seq_printf(seq, "%s : ", mdname(mddev));
@@ -8451,14 +8461,13 @@ static int md_seq_show(struct seq_file *seq, void *v)
 		seq_printf(seq, "\n");
 	}
 	spin_unlock(&mddev->lock);
+	mutex_unlock(&mddev->bitmap_info.mutex);
 	spin_lock(&all_mddevs_lock);
 
 	if (mddev == list_last_entry(&all_mddevs, struct mddev, all_mddevs))
 		status_unused(seq);
 
-	if (atomic_dec_and_test(&mddev->active))
-		__mddev_put(mddev);
-
+	mddev_put_locked(mddev);
 	return 0;
 }
 
@@ -8745,12 +8754,32 @@ void md_submit_discard_bio(struct mddev *mddev, struct md_rdev *rdev,
 }
 EXPORT_SYMBOL_GPL(md_submit_discard_bio);
 
+static void md_bitmap_start(struct mddev *mddev,
+			    struct md_io_clone *md_io_clone)
+{
+	if (mddev->pers->bitmap_sector)
+		mddev->pers->bitmap_sector(mddev, &md_io_clone->offset,
+					   &md_io_clone->sectors);
+
+	mddev->bitmap_ops->startwrite(mddev, md_io_clone->offset,
+				      md_io_clone->sectors);
+}
+
+static void md_bitmap_end(struct mddev *mddev, struct md_io_clone *md_io_clone)
+{
+	mddev->bitmap_ops->endwrite(mddev, md_io_clone->offset,
+				    md_io_clone->sectors);
+}
+
 static void md_end_clone_io(struct bio *bio)
 {
 	struct md_io_clone *md_io_clone = bio->bi_private;
 	struct bio *orig_bio = md_io_clone->orig_bio;
 	struct mddev *mddev = md_io_clone->mddev;
 
+	if (bio_data_dir(orig_bio) == WRITE && mddev->bitmap)
+		md_bitmap_end(mddev, md_io_clone);
+
 	if (bio->bi_status && !orig_bio->bi_status)
 		orig_bio->bi_status = bio->bi_status;
 
@@ -8775,6 +8804,12 @@ static void md_clone_bio(struct mddev *mddev, struct bio **bio)
 	if (blk_queue_io_stat(bdev->bd_disk->queue))
 		md_io_clone->start_time = bio_start_io_acct(*bio);
 
+	if (bio_data_dir(*bio) == WRITE && mddev->bitmap) {
+		md_io_clone->offset = (*bio)->bi_iter.bi_sector;
+		md_io_clone->sectors = bio_sectors(*bio);
+		md_bitmap_start(mddev, md_io_clone);
+	}
+
 	clone->bi_end_io = md_end_clone_io;
 	clone->bi_private = md_io_clone;
 	*bio = clone;
@@ -8793,6 +8828,9 @@ void md_free_cloned_bio(struct bio *bio)
 	struct bio *orig_bio = md_io_clone->orig_bio;
 	struct mddev *mddev = md_io_clone->mddev;
 
+	if (bio_data_dir(orig_bio) == WRITE && mddev->bitmap)
+		md_bitmap_end(mddev, md_io_clone);
+
 	if (bio->bi_status && !orig_bio->bi_status)
 		orig_bio->bi_status = bio->bi_status;
 
@@ -9664,8 +9702,8 @@ void md_check_recovery(struct mddev *mddev)
 			 * remove disk.
 			 */
 			rdev_for_each_safe(rdev, tmp, mddev) {
-				if (test_and_clear_bit(ClusterRemove, &rdev->flags) &&
-						rdev->raid_disk < 0)
+				if (rdev->raid_disk < 0 &&
+				    test_and_clear_bit(ClusterRemove, &rdev->flags))
 					md_kick_rdev_from_array(rdev);
 			}
 		}
@@ -9852,11 +9890,11 @@ EXPORT_SYMBOL_GPL(rdev_clear_badblocks);
 static int md_notify_reboot(struct notifier_block *this,
 			    unsigned long code, void *x)
 {
-	struct mddev *mddev, *n;
+	struct mddev *mddev;
 	int need_delay = 0;
 
 	spin_lock(&all_mddevs_lock);
-	list_for_each_entry_safe(mddev, n, &all_mddevs, all_mddevs) {
+	list_for_each_entry(mddev, &all_mddevs, all_mddevs) {
 		if (!mddev_get(mddev))
 			continue;
 		spin_unlock(&all_mddevs_lock);
@@ -9868,8 +9906,8 @@ static int md_notify_reboot(struct notifier_block *this,
 			mddev_unlock(mddev);
 		}
 		need_delay = 1;
-		mddev_put(mddev);
 		spin_lock(&all_mddevs_lock);
+		mddev_put_locked(mddev);
 	}
 	spin_unlock(&all_mddevs_lock);
 
@@ -9962,8 +10000,11 @@ static void check_sb_changes(struct mddev *mddev, struct md_rdev *rdev)
 
 	/* Check for change of roles in the active devices */
 	rdev_for_each_safe(rdev2, tmp, mddev) {
-		if (test_bit(Faulty, &rdev2->flags))
+		if (test_bit(Faulty, &rdev2->flags)) {
+			if (test_bit(ClusterRemove, &rdev2->flags))
+				set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 			continue;
+		}
 
 		/* Check if the roles changed */
 		role = le16_to_cpu(sb->dev_roles[rdev2->desc_nr]);
@@ -10202,7 +10243,7 @@ void md_autostart_arrays(int part)
 
 static __exit void md_exit(void)
 {
-	struct mddev *mddev, *n;
+	struct mddev *mddev;
 	int delay = 1;
 
 	unregister_blkdev(MD_MAJOR,"md");
@@ -10223,7 +10264,7 @@ static __exit void md_exit(void)
 	remove_proc_entry("mdstat", NULL);
 
 	spin_lock(&all_mddevs_lock);
-	list_for_each_entry_safe(mddev, n, &all_mddevs, all_mddevs) {
+	list_for_each_entry(mddev, &all_mddevs, all_mddevs) {
 		if (!mddev_get(mddev))
 			continue;
 		spin_unlock(&all_mddevs_lock);
@@ -10235,8 +10276,8 @@ static __exit void md_exit(void)
 		 * the mddev for destruction by a workqueue, and the
 		 * destroy_workqueue() below will wait for that to complete.
 		 */
-		mddev_put(mddev);
 		spin_lock(&all_mddevs_lock);
+		mddev_put_locked(mddev);
 	}
 	spin_unlock(&all_mddevs_lock);
 
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 5d2e6bd58e4d..8826dce9717d 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -746,6 +746,9 @@ struct md_personality
 	void *(*takeover) (struct mddev *mddev);
 	/* Changes the consistency policy of an active array. */
 	int (*change_consistency_policy)(struct mddev *mddev, const char *buf);
+	/* convert io ranges from array to bitmap */
+	void (*bitmap_sector)(struct mddev *mddev, sector_t *offset,
+			      unsigned long *sectors);
 };
 
 struct md_sysfs_entry {
@@ -828,6 +831,8 @@ struct md_io_clone {
 	struct mddev	*mddev;
 	struct bio	*orig_bio;
 	unsigned long	start_time;
+	sector_t	offset;
+	unsigned long	sectors;
 	struct bio	bio_clone;
 };
 
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index 32d587524778..31bea72bcb01 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -385,10 +385,8 @@ static int raid0_set_limits(struct mddev *mddev)
 	lim.io_min = mddev->chunk_sectors << 9;
 	lim.io_opt = lim.io_min * mddev->raid_disks;
 	err = mddev_stack_rdev_limits(mddev, &lim, MDDEV_STACK_INTEGRITY);
-	if (err) {
-		queue_limits_cancel_update(mddev->gendisk->queue);
+	if (err)
 		return err;
-	}
 	return queue_limits_set(mddev->gendisk->queue, &lim);
 }
 
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 6c9d24203f39..fe1599db69c8 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -420,10 +420,8 @@ static void close_write(struct r1bio *r1_bio)
 		r1_bio->behind_master_bio = NULL;
 	}
 
-	/* clear the bitmap if all writes complete successfully */
-	mddev->bitmap_ops->endwrite(mddev, r1_bio->sector, r1_bio->sectors,
-				    !test_bit(R1BIO_Degraded, &r1_bio->state),
-				    test_bit(R1BIO_BehindIO, &r1_bio->state));
+	if (test_bit(R1BIO_BehindIO, &r1_bio->state))
+		mddev->bitmap_ops->end_behind_write(mddev);
 	md_write_end(mddev);
 }
 
@@ -480,8 +478,6 @@ static void raid1_end_write_request(struct bio *bio)
 		if (!test_bit(Faulty, &rdev->flags))
 			set_bit(R1BIO_WriteError, &r1_bio->state);
 		else {
-			/* Fail the request */
-			set_bit(R1BIO_Degraded, &r1_bio->state);
 			/* Finished with this branch */
 			r1_bio->bios[mirror] = NULL;
 			to_put = bio;
@@ -1492,11 +1488,8 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 			break;
 		}
 		r1_bio->bios[i] = NULL;
-		if (!rdev || test_bit(Faulty, &rdev->flags)) {
-			if (i < conf->raid_disks)
-				set_bit(R1BIO_Degraded, &r1_bio->state);
+		if (!rdev || test_bit(Faulty, &rdev->flags))
 			continue;
-		}
 
 		atomic_inc(&rdev->nr_pending);
 		if (test_bit(WriteErrorSeen, &rdev->flags)) {
@@ -1522,16 +1515,6 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 					 */
 					max_sectors = bad_sectors;
 				rdev_dec_pending(rdev, mddev);
-				/* We don't set R1BIO_Degraded as that
-				 * only applies if the disk is
-				 * missing, so it might be re-added,
-				 * and we want to know to recover this
-				 * chunk.
-				 * In this case the device is here,
-				 * and the fact that this chunk is not
-				 * in-sync is recorded in the bad
-				 * block log
-				 */
 				continue;
 			}
 			if (is_bad) {
@@ -1611,9 +1594,8 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 			    stats.behind_writes < max_write_behind)
 				alloc_behind_master_bio(r1_bio, bio);
 
-			mddev->bitmap_ops->startwrite(
-				mddev, r1_bio->sector, r1_bio->sectors,
-				test_bit(R1BIO_BehindIO, &r1_bio->state));
+			if (test_bit(R1BIO_BehindIO, &r1_bio->state))
+				mddev->bitmap_ops->start_behind_write(mddev);
 			first_clone = 0;
 		}
 
@@ -2174,14 +2156,9 @@ static int fix_sync_read_error(struct r1bio *r1_bio)
 				if (!rdev_set_badblocks(rdev, sect, s, 0))
 					abort = 1;
 			}
-			if (abort) {
-				conf->recovery_disabled =
-					mddev->recovery_disabled;
-				set_bit(MD_RECOVERY_INTR, &mddev->recovery);
-				md_done_sync(mddev, r1_bio->sectors, 0);
-				put_buf(r1_bio);
+			if (abort)
 				return 0;
-			}
+
 			/* Try next page */
 			sectors -= s;
 			sect += s;
@@ -2320,10 +2297,21 @@ static void sync_request_write(struct mddev *mddev, struct r1bio *r1_bio)
 	int disks = conf->raid_disks * 2;
 	struct bio *wbio;
 
-	if (!test_bit(R1BIO_Uptodate, &r1_bio->state))
-		/* ouch - failed to read all of that. */
-		if (!fix_sync_read_error(r1_bio))
+	if (!test_bit(R1BIO_Uptodate, &r1_bio->state)) {
+		/*
+		 * ouch - failed to read all of that.
+		 * No need to fix read error for check/repair
+		 * because all member disks are read.
+		 */
+		if (test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery) ||
+		    !fix_sync_read_error(r1_bio)) {
+			conf->recovery_disabled = mddev->recovery_disabled;
+			set_bit(MD_RECOVERY_INTR, &mddev->recovery);
+			md_done_sync(mddev, r1_bio->sectors, 0);
+			put_buf(r1_bio);
 			return;
+		}
+	}
 
 	if (test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery))
 		process_checks(r1_bio);
@@ -2567,12 +2555,10 @@ static void handle_write_finished(struct r1conf *conf, struct r1bio *r1_bio)
 			 * errors.
 			 */
 			fail = true;
-			if (!narrow_write_error(r1_bio, m)) {
+			if (!narrow_write_error(r1_bio, m))
 				md_error(conf->mddev,
 					 conf->mirrors[m].rdev);
 				/* an I/O failed, we can't clear the bitmap */
-				set_bit(R1BIO_Degraded, &r1_bio->state);
-			}
 			rdev_dec_pending(conf->mirrors[m].rdev,
 					 conf->mddev);
 		}
@@ -2663,8 +2649,6 @@ static void raid1d(struct md_thread *thread)
 			list_del(&r1_bio->retry_list);
 			idx = sector_to_idx(r1_bio->sector);
 			atomic_dec(&conf->nr_queued[idx]);
-			if (mddev->degraded)
-				set_bit(R1BIO_Degraded, &r1_bio->state);
 			if (test_bit(R1BIO_WriteError, &r1_bio->state))
 				close_write(r1_bio);
 			raid_end_bio_io(r1_bio);
@@ -3193,10 +3177,8 @@ static int raid1_set_limits(struct mddev *mddev)
 	md_init_stacking_limits(&lim);
 	lim.max_write_zeroes_sectors = 0;
 	err = mddev_stack_rdev_limits(mddev, &lim, MDDEV_STACK_INTEGRITY);
-	if (err) {
-		queue_limits_cancel_update(mddev->gendisk->queue);
+	if (err)
 		return err;
-	}
 	return queue_limits_set(mddev->gendisk->queue, &lim);
 }
 
@@ -3398,6 +3380,7 @@ static int raid1_reshape(struct mddev *mddev)
 	/* ok, everything is stopped */
 	oldpool = conf->r1bio_pool;
 	conf->r1bio_pool = newpool;
+	init_waitqueue_head(&conf->r1bio_pool.wait);
 
 	for (d = d2 = 0; d < conf->raid_disks; d++) {
 		struct md_rdev *rdev = conf->mirrors[d].rdev;
diff --git a/drivers/md/raid1.h b/drivers/md/raid1.h
index 5300cbaa58a4..33f318fcc268 100644
--- a/drivers/md/raid1.h
+++ b/drivers/md/raid1.h
@@ -188,7 +188,6 @@ struct r1bio {
 enum r1bio_state {
 	R1BIO_Uptodate,
 	R1BIO_IsSync,
-	R1BIO_Degraded,
 	R1BIO_BehindIO,
 /* Set ReadError on bios that experience a readerror so that
  * raid1d knows what to do with them.
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 862b1fb71d86..7515a98001ca 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -428,10 +428,6 @@ static void close_write(struct r10bio *r10_bio)
 {
 	struct mddev *mddev = r10_bio->mddev;
 
-	/* clear the bitmap if all writes complete successfully */
-	mddev->bitmap_ops->endwrite(mddev, r10_bio->sector, r10_bio->sectors,
-				    !test_bit(R10BIO_Degraded, &r10_bio->state),
-				    false);
 	md_write_end(mddev);
 }
 
@@ -501,7 +497,6 @@ static void raid10_end_write_request(struct bio *bio)
 				set_bit(R10BIO_WriteError, &r10_bio->state);
 			else {
 				/* Fail the request */
-				set_bit(R10BIO_Degraded, &r10_bio->state);
 				r10_bio->devs[slot].bio = NULL;
 				to_put = bio;
 				dec_rdev = 1;
@@ -1186,8 +1181,11 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio,
 		}
 	}
 
-	if (!regular_request_wait(mddev, conf, bio, r10_bio->sectors))
+	if (!regular_request_wait(mddev, conf, bio, r10_bio->sectors)) {
+		raid_end_bio_io(r10_bio);
 		return;
+	}
+
 	rdev = read_balance(conf, r10_bio, &max_sectors);
 	if (!rdev) {
 		if (err_rdev) {
@@ -1373,8 +1371,11 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio,
 	}
 
 	sectors = r10_bio->sectors;
-	if (!regular_request_wait(mddev, conf, bio, sectors))
+	if (!regular_request_wait(mddev, conf, bio, sectors)) {
+		raid_end_bio_io(r10_bio);
 		return;
+	}
+
 	if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) &&
 	    (mddev->reshape_backwards
 	     ? (bio->bi_iter.bi_sector < conf->reshape_safe &&
@@ -1430,10 +1431,8 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio,
 		r10_bio->devs[i].bio = NULL;
 		r10_bio->devs[i].repl_bio = NULL;
 
-		if (!rdev && !rrdev) {
-			set_bit(R10BIO_Degraded, &r10_bio->state);
+		if (!rdev && !rrdev)
 			continue;
-		}
 		if (rdev && test_bit(WriteErrorSeen, &rdev->flags)) {
 			sector_t first_bad;
 			sector_t dev_sector = r10_bio->devs[i].addr;
@@ -1450,14 +1449,6 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio,
 					 * to other devices yet
 					 */
 					max_sectors = bad_sectors;
-				/* We don't set R10BIO_Degraded as that
-				 * only applies if the disk is missing,
-				 * so it might be re-added, and we want to
-				 * know to recover this chunk.
-				 * In this case the device is here, and the
-				 * fact that this chunk is not in-sync is
-				 * recorded in the bad block log.
-				 */
 				continue;
 			}
 			if (is_bad) {
@@ -1493,8 +1484,6 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio,
 	md_account_bio(mddev, &bio);
 	r10_bio->master_bio = bio;
 	atomic_set(&r10_bio->remaining, 1);
-	mddev->bitmap_ops->startwrite(mddev, r10_bio->sector, r10_bio->sectors,
-				      false);
 
 	for (i = 0; i < conf->copies; i++) {
 		if (r10_bio->devs[i].bio)
@@ -1704,6 +1693,7 @@ retry_discard:
 	 * The discard bio returns only first r10bio finishes
 	 */
 	if (first_copy) {
+		md_account_bio(mddev, &bio);
 		r10_bio->master_bio = bio;
 		set_bit(R10BIO_Discard, &r10_bio->state);
 		first_copy = false;
@@ -2910,11 +2900,8 @@ static void handle_write_completed(struct r10conf *conf, struct r10bio *r10_bio)
 				rdev_dec_pending(rdev, conf->mddev);
 			} else if (bio != NULL && bio->bi_status) {
 				fail = true;
-				if (!narrow_write_error(r10_bio, m)) {
+				if (!narrow_write_error(r10_bio, m))
 					md_error(conf->mddev, rdev);
-					set_bit(R10BIO_Degraded,
-						&r10_bio->state);
-				}
 				rdev_dec_pending(rdev, conf->mddev);
 			}
 			bio = r10_bio->devs[m].repl_bio;
@@ -2973,8 +2960,6 @@ static void raid10d(struct md_thread *thread)
 			r10_bio = list_first_entry(&tmp, struct r10bio,
 						   retry_list);
 			list_del(&r10_bio->retry_list);
-			if (mddev->degraded)
-				set_bit(R10BIO_Degraded, &r10_bio->state);
 
 			if (test_bit(R10BIO_WriteError,
 				     &r10_bio->state))
@@ -3983,12 +3968,11 @@ static int raid10_set_queue_limits(struct mddev *mddev)
 	md_init_stacking_limits(&lim);
 	lim.max_write_zeroes_sectors = 0;
 	lim.io_min = mddev->chunk_sectors << 9;
+	lim.chunk_sectors = mddev->chunk_sectors;
 	lim.io_opt = lim.io_min * raid10_nr_stripes(conf);
 	err = mddev_stack_rdev_limits(mddev, &lim, MDDEV_STACK_INTEGRITY);
-	if (err) {
-		queue_limits_cancel_update(mddev->gendisk->queue);
+	if (err)
 		return err;
-	}
 	return queue_limits_set(mddev->gendisk->queue, &lim);
 }
 
diff --git a/drivers/md/raid10.h b/drivers/md/raid10.h
index 2e75e88d0802..3f16ad6904a9 100644
--- a/drivers/md/raid10.h
+++ b/drivers/md/raid10.h
@@ -161,7 +161,6 @@ enum r10bio_state {
 	R10BIO_IsSync,
 	R10BIO_IsRecover,
 	R10BIO_IsReshape,
-	R10BIO_Degraded,
 /* Set ReadError on bios that experience a read error
  * so that raid10d knows what to do with them.
  */
diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c
index b4f7b79fd187..011246e16a99 100644
--- a/drivers/md/raid5-cache.c
+++ b/drivers/md/raid5-cache.c
@@ -313,10 +313,6 @@ void r5c_handle_cached_data_endio(struct r5conf *conf,
 		if (sh->dev[i].written) {
 			set_bit(R5_UPTODATE, &sh->dev[i].flags);
 			r5c_return_dev_pending_writes(conf, &sh->dev[i]);
-			conf->mddev->bitmap_ops->endwrite(conf->mddev,
-					sh->sector, RAID5_STRIPE_SECTORS(conf),
-					!test_bit(STRIPE_DEGRADED, &sh->state),
-					false);
 		}
 	}
 }
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 2fa1f270fb1d..39e7596e78c0 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -906,8 +906,7 @@ static bool stripe_can_batch(struct stripe_head *sh)
 	if (raid5_has_log(conf) || raid5_has_ppl(conf))
 		return false;
 	return test_bit(STRIPE_BATCH_READY, &sh->state) &&
-		!test_bit(STRIPE_BITMAP_PENDING, &sh->state) &&
-		is_full_stripe_write(sh);
+	       is_full_stripe_write(sh);
 }
 
 /* we only do back search */
@@ -1345,8 +1344,6 @@ again:
 				submit_bio_noacct(rbi);
 		}
 		if (!rdev && !rrdev) {
-			if (op_is_write(op))
-				set_bit(STRIPE_DEGRADED, &sh->state);
 			pr_debug("skip op %d on disc %d for sector %llu\n",
 				bi->bi_opf, i, (unsigned long long)sh->sector);
 			clear_bit(R5_LOCKED, &sh->dev[i].flags);
@@ -2884,7 +2881,6 @@ static void raid5_end_write_request(struct bio *bi)
 			set_bit(R5_MadeGoodRepl, &sh->dev[i].flags);
 	} else {
 		if (bi->bi_status) {
-			set_bit(STRIPE_DEGRADED, &sh->state);
 			set_bit(WriteErrorSeen, &rdev->flags);
 			set_bit(R5_WriteError, &sh->dev[i].flags);
 			if (!test_and_set_bit(WantReplacement, &rdev->flags))
@@ -3548,29 +3544,9 @@ static void __add_stripe_bio(struct stripe_head *sh, struct bio *bi,
 		 (*bip)->bi_iter.bi_sector, sh->sector, dd_idx,
 		 sh->dev[dd_idx].sector);
 
-	if (conf->mddev->bitmap && firstwrite) {
-		/* Cannot hold spinlock over bitmap_startwrite,
-		 * but must ensure this isn't added to a batch until
-		 * we have added to the bitmap and set bm_seq.
-		 * So set STRIPE_BITMAP_PENDING to prevent
-		 * batching.
-		 * If multiple __add_stripe_bio() calls race here they
-		 * much all set STRIPE_BITMAP_PENDING.  So only the first one
-		 * to complete "bitmap_startwrite" gets to set
-		 * STRIPE_BIT_DELAY.  This is important as once a stripe
-		 * is added to a batch, STRIPE_BIT_DELAY cannot be changed
-		 * any more.
-		 */
-		set_bit(STRIPE_BITMAP_PENDING, &sh->state);
-		spin_unlock_irq(&sh->stripe_lock);
-		conf->mddev->bitmap_ops->startwrite(conf->mddev, sh->sector,
-					RAID5_STRIPE_SECTORS(conf), false);
-		spin_lock_irq(&sh->stripe_lock);
-		clear_bit(STRIPE_BITMAP_PENDING, &sh->state);
-		if (!sh->batch_head) {
-			sh->bm_seq = conf->seq_flush+1;
-			set_bit(STRIPE_BIT_DELAY, &sh->state);
-		}
+	if (conf->mddev->bitmap && firstwrite && !sh->batch_head) {
+		sh->bm_seq = conf->seq_flush+1;
+		set_bit(STRIPE_BIT_DELAY, &sh->state);
 	}
 }
 
@@ -3621,7 +3597,6 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
 	BUG_ON(sh->batch_head);
 	for (i = disks; i--; ) {
 		struct bio *bi;
-		int bitmap_end = 0;
 
 		if (test_bit(R5_ReadError, &sh->dev[i].flags)) {
 			struct md_rdev *rdev = conf->disks[i].rdev;
@@ -3646,8 +3621,6 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
 		sh->dev[i].towrite = NULL;
 		sh->overwrite_disks = 0;
 		spin_unlock_irq(&sh->stripe_lock);
-		if (bi)
-			bitmap_end = 1;
 
 		log_stripe_write_finished(sh);
 
@@ -3662,11 +3635,6 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
 			bio_io_error(bi);
 			bi = nextbi;
 		}
-		if (bitmap_end)
-			conf->mddev->bitmap_ops->endwrite(conf->mddev,
-					sh->sector, RAID5_STRIPE_SECTORS(conf),
-					false, false);
-		bitmap_end = 0;
 		/* and fail all 'written' */
 		bi = sh->dev[i].written;
 		sh->dev[i].written = NULL;
@@ -3675,7 +3643,6 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
 			sh->dev[i].page = sh->dev[i].orig_page;
 		}
 
-		if (bi) bitmap_end = 1;
 		while (bi && bi->bi_iter.bi_sector <
 		       sh->dev[i].sector + RAID5_STRIPE_SECTORS(conf)) {
 			struct bio *bi2 = r5_next_bio(conf, bi, sh->dev[i].sector);
@@ -3709,10 +3676,6 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
 				bi = nextbi;
 			}
 		}
-		if (bitmap_end)
-			conf->mddev->bitmap_ops->endwrite(conf->mddev,
-					sh->sector, RAID5_STRIPE_SECTORS(conf),
-					false, false);
 		/* If we were in the middle of a write the parity block might
 		 * still be locked - so just clear all R5_LOCKED flags
 		 */
@@ -4061,10 +4024,7 @@ returnbi:
 					bio_endio(wbi);
 					wbi = wbi2;
 				}
-				conf->mddev->bitmap_ops->endwrite(conf->mddev,
-					sh->sector, RAID5_STRIPE_SECTORS(conf),
-					!test_bit(STRIPE_DEGRADED, &sh->state),
-					false);
+
 				if (head_sh->batch_head) {
 					sh = list_first_entry(&sh->batch_list,
 							      struct stripe_head,
@@ -4341,7 +4301,6 @@ static void handle_parity_checks5(struct r5conf *conf, struct stripe_head *sh,
 		s->locked++;
 		set_bit(R5_Wantwrite, &dev->flags);
 
-		clear_bit(STRIPE_DEGRADED, &sh->state);
 		set_bit(STRIPE_INSYNC, &sh->state);
 		break;
 	case check_state_run:
@@ -4498,7 +4457,6 @@ static void handle_parity_checks6(struct r5conf *conf, struct stripe_head *sh,
 			clear_bit(R5_Wantwrite, &dev->flags);
 			s->locked--;
 		}
-		clear_bit(STRIPE_DEGRADED, &sh->state);
 
 		set_bit(STRIPE_INSYNC, &sh->state);
 		break;
@@ -4892,8 +4850,7 @@ static void break_stripe_batch_list(struct stripe_head *head_sh,
 					  (1 << STRIPE_COMPUTE_RUN)  |
 					  (1 << STRIPE_DISCARD) |
 					  (1 << STRIPE_BATCH_READY) |
-					  (1 << STRIPE_BATCH_ERR) |
-					  (1 << STRIPE_BITMAP_PENDING)),
+					  (1 << STRIPE_BATCH_ERR)),
 			"stripe state: %lx\n", sh->state);
 		WARN_ONCE(head_sh->state & ((1 << STRIPE_DISCARD) |
 					      (1 << STRIPE_REPLACED)),
@@ -4901,7 +4858,6 @@ static void break_stripe_batch_list(struct stripe_head *head_sh,
 
 		set_mask_bits(&sh->state, ~(STRIPE_EXPAND_SYNC_FLAGS |
 					    (1 << STRIPE_PREREAD_ACTIVE) |
-					    (1 << STRIPE_DEGRADED) |
 					    (1 << STRIPE_ON_UNPLUG_LIST)),
 			      head_sh->state & (1 << STRIPE_INSYNC));
 
@@ -5785,10 +5741,6 @@ static void make_discard_request(struct mddev *mddev, struct bio *bi)
 		}
 		spin_unlock_irq(&sh->stripe_lock);
 		if (conf->mddev->bitmap) {
-			for (d = 0; d < conf->raid_disks - conf->max_degraded;
-			     d++)
-				mddev->bitmap_ops->startwrite(mddev, sh->sector,
-					RAID5_STRIPE_SECTORS(conf), false);
 			sh->bm_seq = conf->seq_flush + 1;
 			set_bit(STRIPE_BIT_DELAY, &sh->state);
 		}
@@ -5929,6 +5881,54 @@ static enum reshape_loc get_reshape_loc(struct mddev *mddev,
 	return LOC_BEHIND_RESHAPE;
 }
 
+static void raid5_bitmap_sector(struct mddev *mddev, sector_t *offset,
+				unsigned long *sectors)
+{
+	struct r5conf *conf = mddev->private;
+	sector_t start = *offset;
+	sector_t end = start + *sectors;
+	sector_t prev_start = start;
+	sector_t prev_end = end;
+	int sectors_per_chunk;
+	enum reshape_loc loc;
+	int dd_idx;
+
+	sectors_per_chunk = conf->chunk_sectors *
+		(conf->raid_disks - conf->max_degraded);
+	start = round_down(start, sectors_per_chunk);
+	end = round_up(end, sectors_per_chunk);
+
+	start = raid5_compute_sector(conf, start, 0, &dd_idx, NULL);
+	end = raid5_compute_sector(conf, end, 0, &dd_idx, NULL);
+
+	/*
+	 * For LOC_INSIDE_RESHAPE, this IO will wait for reshape to make
+	 * progress, hence it's the same as LOC_BEHIND_RESHAPE.
+	 */
+	loc = get_reshape_loc(mddev, conf, prev_start);
+	if (likely(loc != LOC_AHEAD_OF_RESHAPE)) {
+		*offset = start;
+		*sectors = end - start;
+		return;
+	}
+
+	sectors_per_chunk = conf->prev_chunk_sectors *
+		(conf->previous_raid_disks - conf->max_degraded);
+	prev_start = round_down(prev_start, sectors_per_chunk);
+	prev_end = round_down(prev_end, sectors_per_chunk);
+
+	prev_start = raid5_compute_sector(conf, prev_start, 1, &dd_idx, NULL);
+	prev_end = raid5_compute_sector(conf, prev_end, 1, &dd_idx, NULL);
+
+	/*
+	 * for LOC_AHEAD_OF_RESHAPE, reshape can make progress before this IO
+	 * is handled in make_stripe_request(), we can't know this here hence
+	 * we set bits for both.
+	 */
+	*offset = min(start, prev_start);
+	*sectors = max(end, prev_end) - *offset;
+}
+
 static enum stripe_result make_stripe_request(struct mddev *mddev,
 		struct r5conf *conf, struct stripe_request_ctx *ctx,
 		sector_t logical_sector, struct bio *bi)
@@ -8977,6 +8977,7 @@ static struct md_personality raid6_personality =
 	.takeover	= raid6_takeover,
 	.change_consistency_policy = raid5_change_consistency_policy,
 	.prepare_suspend = raid5_prepare_suspend,
+	.bitmap_sector	= raid5_bitmap_sector,
 };
 static struct md_personality raid5_personality =
 {
@@ -9002,6 +9003,7 @@ static struct md_personality raid5_personality =
 	.takeover	= raid5_takeover,
 	.change_consistency_policy = raid5_change_consistency_policy,
 	.prepare_suspend = raid5_prepare_suspend,
+	.bitmap_sector	= raid5_bitmap_sector,
 };
 
 static struct md_personality raid4_personality =
@@ -9028,6 +9030,7 @@ static struct md_personality raid4_personality =
 	.takeover	= raid4_takeover,
 	.change_consistency_policy = raid5_change_consistency_policy,
 	.prepare_suspend = raid5_prepare_suspend,
+	.bitmap_sector	= raid5_bitmap_sector,
 };
 
 static int __init raid5_init(void)
diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h
index 896ecfc4afa6..2e42c1641049 100644
--- a/drivers/md/raid5.h
+++ b/drivers/md/raid5.h
@@ -358,7 +358,6 @@ enum {
 	STRIPE_REPLACED,
 	STRIPE_PREREAD_ACTIVE,
 	STRIPE_DELAYED,
-	STRIPE_DEGRADED,
 	STRIPE_BIT_DELAY,
 	STRIPE_EXPANDING,
 	STRIPE_EXPAND_SOURCE,
@@ -372,9 +371,6 @@ enum {
 	STRIPE_ON_RELEASE_LIST,
 	STRIPE_BATCH_READY,
 	STRIPE_BATCH_ERR,
-	STRIPE_BITMAP_PENDING,	/* Being added to bitmap, don't add
-				 * to batch yet.
-				 */
 	STRIPE_LOG_TRAPPED,	/* trapped into log (see raid5-cache.c)
 				 * this bit is used in two scenarios:
 				 *
diff --git a/drivers/media/common/siano/smsdvb-main.c b/drivers/media/common/siano/smsdvb-main.c
index 44d8fe8b220e..9b1a650ed055 100644
--- a/drivers/media/common/siano/smsdvb-main.c
+++ b/drivers/media/common/siano/smsdvb-main.c
@@ -1243,6 +1243,8 @@ static int __init smsdvb_module_init(void)
 	smsdvb_debugfs_register();
 
 	rc = smscore_register_hotplug(smsdvb_hotplug);
+	if (rc)
+		smsdvb_debugfs_unregister();
 
 	pr_debug("\n");
 
diff --git a/drivers/media/common/videobuf2/videobuf2-dma-sg.c b/drivers/media/common/videobuf2/videobuf2-dma-sg.c
index 6975a71d740f..a5aa6a2a028c 100644
--- a/drivers/media/common/videobuf2/videobuf2-dma-sg.c
+++ b/drivers/media/common/videobuf2/videobuf2-dma-sg.c
@@ -469,7 +469,7 @@ vb2_dma_sg_dmabuf_ops_begin_cpu_access(struct dma_buf *dbuf,
 	struct vb2_dma_sg_buf *buf = dbuf->priv;
 	struct sg_table *sgt = buf->dma_sgt;
 
-	dma_sync_sg_for_cpu(buf->dev, sgt->sgl, sgt->nents, buf->dma_dir);
+	dma_sync_sgtable_for_cpu(buf->dev, sgt, buf->dma_dir);
 	return 0;
 }
 
@@ -480,7 +480,7 @@ vb2_dma_sg_dmabuf_ops_end_cpu_access(struct dma_buf *dbuf,
 	struct vb2_dma_sg_buf *buf = dbuf->priv;
 	struct sg_table *sgt = buf->dma_sgt;
 
-	dma_sync_sg_for_device(buf->dev, sgt->sgl, sgt->nents, buf->dma_dir);
+	dma_sync_sgtable_for_device(buf->dev, sgt, buf->dma_dir);
 	return 0;
 }
 
diff --git a/drivers/media/dvb-frontends/cxd2841er.c b/drivers/media/dvb-frontends/cxd2841er.c
index d925ca24183b..415f1f91cc30 100644
--- a/drivers/media/dvb-frontends/cxd2841er.c
+++ b/drivers/media/dvb-frontends/cxd2841er.c
@@ -311,12 +311,8 @@ static int cxd2841er_set_reg_bits(struct cxd2841er_priv *priv,
 
 static u32 cxd2841er_calc_iffreq_xtal(enum cxd2841er_xtal xtal, u32 ifhz)
 {
-	u64 tmp;
-
-	tmp = (u64) ifhz * 16777216;
-	do_div(tmp, ((xtal == SONY_XTAL_24000) ? 48000000 : 41000000));
-
-	return (u32) tmp;
+	return div_u64(ifhz * 16777216ull,
+		       (xtal == SONY_XTAL_24000) ? 48000000 : 41000000);
 }
 
 static u32 cxd2841er_calc_iffreq(u32 ifhz)
diff --git a/drivers/media/dvb-frontends/dib7000p.c b/drivers/media/dvb-frontends/dib7000p.c
index c5582d4fa5be..40c5b1dc7d91 100644
--- a/drivers/media/dvb-frontends/dib7000p.c
+++ b/drivers/media/dvb-frontends/dib7000p.c
@@ -2193,6 +2193,8 @@ static int w7090p_tuner_write_serpar(struct i2c_adapter *i2c_adap, struct i2c_ms
 	struct dib7000p_state *state = i2c_get_adapdata(i2c_adap);
 	u8 n_overflow = 1;
 	u16 i = 1000;
+	if (msg[0].len < 3)
+		return -EOPNOTSUPP;
 	u16 serpar_num = msg[0].buf[0];
 
 	while (n_overflow == 1 && i) {
@@ -2212,6 +2214,8 @@ static int w7090p_tuner_read_serpar(struct i2c_adapter *i2c_adap, struct i2c_msg
 	struct dib7000p_state *state = i2c_get_adapdata(i2c_adap);
 	u8 n_overflow = 1, n_empty = 1;
 	u16 i = 1000;
+	if (msg[0].len < 1 || msg[1].len < 2)
+		return -EOPNOTSUPP;
 	u16 serpar_num = msg[0].buf[0];
 	u16 read_word;
 
@@ -2256,8 +2260,12 @@ static int dib7090p_rw_on_apb(struct i2c_adapter *i2c_adap,
 	u16 word;
 
 	if (num == 1) {		/* write */
+		if (msg[0].len < 3)
+			return -EOPNOTSUPP;
 		dib7000p_write_word(state, apb_address, ((msg[0].buf[1] << 8) | (msg[0].buf[2])));
 	} else {
+		if (msg[1].len < 2)
+			return -EOPNOTSUPP;
 		word = dib7000p_read_word(state, apb_address);
 		msg[1].buf[0] = (word >> 8) & 0xff;
 		msg[1].buf[1] = (word) & 0xff;
diff --git a/drivers/media/dvb-frontends/dib8000.c b/drivers/media/dvb-frontends/dib8000.c
index 2f5165918163..cfe59c3255f7 100644
--- a/drivers/media/dvb-frontends/dib8000.c
+++ b/drivers/media/dvb-frontends/dib8000.c
@@ -2701,8 +2701,11 @@ static void dib8000_set_dds(struct dib8000_state *state, s32 offset_khz)
 	u8 ratio;
 
 	if (state->revision == 0x8090) {
+		u32 internal = dib8000_read32(state, 23) / 1000;
+
 		ratio = 4;
-		unit_khz_dds_val = (1<<26) / (dib8000_read32(state, 23) / 1000);
+
+		unit_khz_dds_val = (1<<26) / (internal ?: 1);
 		if (offset_khz < 0)
 			dds = (1 << 26) - (abs_offset_khz * unit_khz_dds_val);
 		else
diff --git a/drivers/media/i2c/Kconfig b/drivers/media/i2c/Kconfig
index 8ba096b8ebca..85ecb2aeefdb 100644
--- a/drivers/media/i2c/Kconfig
+++ b/drivers/media/i2c/Kconfig
@@ -140,6 +140,7 @@ config VIDEO_IMX214
 	tristate "Sony IMX214 sensor support"
 	depends on GPIOLIB
 	select REGMAP_I2C
+	select V4L2_CCI_I2C
 	help
 	  This is a Video4Linux2 sensor driver for the Sony
 	  IMX214 camera.
diff --git a/drivers/media/i2c/adv7180.c b/drivers/media/i2c/adv7180.c
index 819ff9f7c90f..2a20a4fad796 100644
--- a/drivers/media/i2c/adv7180.c
+++ b/drivers/media/i2c/adv7180.c
@@ -195,6 +195,7 @@ struct adv7180_state;
 #define ADV7180_FLAG_V2			BIT(1)
 #define ADV7180_FLAG_MIPI_CSI2		BIT(2)
 #define ADV7180_FLAG_I2P		BIT(3)
+#define ADV7180_FLAG_TEST_PATTERN	BIT(4)
 
 struct adv7180_chip_info {
 	unsigned int flags;
@@ -682,11 +683,15 @@ static int adv7180_init_controls(struct adv7180_state *state)
 			  ADV7180_HUE_MAX, 1, ADV7180_HUE_DEF);
 	v4l2_ctrl_new_custom(&state->ctrl_hdl, &adv7180_ctrl_fast_switch, NULL);
 
-	v4l2_ctrl_new_std_menu_items(&state->ctrl_hdl, &adv7180_ctrl_ops,
-				      V4L2_CID_TEST_PATTERN,
-				      ARRAY_SIZE(test_pattern_menu) - 1,
-				      0, ARRAY_SIZE(test_pattern_menu) - 1,
-				      test_pattern_menu);
+	if (state->chip_info->flags & ADV7180_FLAG_TEST_PATTERN) {
+		v4l2_ctrl_new_std_menu_items(&state->ctrl_hdl,
+					     &adv7180_ctrl_ops,
+					     V4L2_CID_TEST_PATTERN,
+					     ARRAY_SIZE(test_pattern_menu) - 1,
+					     0,
+					     ARRAY_SIZE(test_pattern_menu) - 1,
+					     test_pattern_menu);
+	}
 
 	state->sd.ctrl_handler = &state->ctrl_hdl;
 	if (state->ctrl_hdl.error) {
@@ -1221,7 +1226,7 @@ static const struct adv7180_chip_info adv7182_info = {
 };
 
 static const struct adv7180_chip_info adv7280_info = {
-	.flags = ADV7180_FLAG_V2 | ADV7180_FLAG_I2P,
+	.flags = ADV7180_FLAG_V2 | ADV7180_FLAG_I2P | ADV7180_FLAG_TEST_PATTERN,
 	.valid_input_mask = BIT(ADV7182_INPUT_CVBS_AIN1) |
 		BIT(ADV7182_INPUT_CVBS_AIN2) |
 		BIT(ADV7182_INPUT_CVBS_AIN3) |
@@ -1235,7 +1240,8 @@ static const struct adv7180_chip_info adv7280_info = {
 };
 
 static const struct adv7180_chip_info adv7280_m_info = {
-	.flags = ADV7180_FLAG_V2 | ADV7180_FLAG_MIPI_CSI2 | ADV7180_FLAG_I2P,
+	.flags = ADV7180_FLAG_V2 | ADV7180_FLAG_MIPI_CSI2 | ADV7180_FLAG_I2P |
+		ADV7180_FLAG_TEST_PATTERN,
 	.valid_input_mask = BIT(ADV7182_INPUT_CVBS_AIN1) |
 		BIT(ADV7182_INPUT_CVBS_AIN2) |
 		BIT(ADV7182_INPUT_CVBS_AIN3) |
@@ -1256,7 +1262,8 @@ static const struct adv7180_chip_info adv7280_m_info = {
 };
 
 static const struct adv7180_chip_info adv7281_info = {
-	.flags = ADV7180_FLAG_V2 | ADV7180_FLAG_MIPI_CSI2,
+	.flags = ADV7180_FLAG_V2 | ADV7180_FLAG_MIPI_CSI2 |
+		ADV7180_FLAG_TEST_PATTERN,
 	.valid_input_mask = BIT(ADV7182_INPUT_CVBS_AIN1) |
 		BIT(ADV7182_INPUT_CVBS_AIN2) |
 		BIT(ADV7182_INPUT_CVBS_AIN7) |
@@ -1271,7 +1278,8 @@ static const struct adv7180_chip_info adv7281_info = {
 };
 
 static const struct adv7180_chip_info adv7281_m_info = {
-	.flags = ADV7180_FLAG_V2 | ADV7180_FLAG_MIPI_CSI2,
+	.flags = ADV7180_FLAG_V2 | ADV7180_FLAG_MIPI_CSI2 |
+		ADV7180_FLAG_TEST_PATTERN,
 	.valid_input_mask = BIT(ADV7182_INPUT_CVBS_AIN1) |
 		BIT(ADV7182_INPUT_CVBS_AIN2) |
 		BIT(ADV7182_INPUT_CVBS_AIN3) |
@@ -1291,7 +1299,8 @@ static const struct adv7180_chip_info adv7281_m_info = {
 };
 
 static const struct adv7180_chip_info adv7281_ma_info = {
-	.flags = ADV7180_FLAG_V2 | ADV7180_FLAG_MIPI_CSI2,
+	.flags = ADV7180_FLAG_V2 | ADV7180_FLAG_MIPI_CSI2 |
+		ADV7180_FLAG_TEST_PATTERN,
 	.valid_input_mask = BIT(ADV7182_INPUT_CVBS_AIN1) |
 		BIT(ADV7182_INPUT_CVBS_AIN2) |
 		BIT(ADV7182_INPUT_CVBS_AIN3) |
@@ -1316,7 +1325,7 @@ static const struct adv7180_chip_info adv7281_ma_info = {
 };
 
 static const struct adv7180_chip_info adv7282_info = {
-	.flags = ADV7180_FLAG_V2 | ADV7180_FLAG_I2P,
+	.flags = ADV7180_FLAG_V2 | ADV7180_FLAG_I2P | ADV7180_FLAG_TEST_PATTERN,
 	.valid_input_mask = BIT(ADV7182_INPUT_CVBS_AIN1) |
 		BIT(ADV7182_INPUT_CVBS_AIN2) |
 		BIT(ADV7182_INPUT_CVBS_AIN7) |
@@ -1331,7 +1340,8 @@ static const struct adv7180_chip_info adv7282_info = {
 };
 
 static const struct adv7180_chip_info adv7282_m_info = {
-	.flags = ADV7180_FLAG_V2 | ADV7180_FLAG_MIPI_CSI2 | ADV7180_FLAG_I2P,
+	.flags = ADV7180_FLAG_V2 | ADV7180_FLAG_MIPI_CSI2 | ADV7180_FLAG_I2P |
+		ADV7180_FLAG_TEST_PATTERN,
 	.valid_input_mask = BIT(ADV7182_INPUT_CVBS_AIN1) |
 		BIT(ADV7182_INPUT_CVBS_AIN2) |
 		BIT(ADV7182_INPUT_CVBS_AIN3) |
diff --git a/drivers/media/i2c/adv748x/adv748x.h b/drivers/media/i2c/adv748x/adv748x.h
index 9bc0121d0eff..2c1db5968af8 100644
--- a/drivers/media/i2c/adv748x/adv748x.h
+++ b/drivers/media/i2c/adv748x/adv748x.h
@@ -320,7 +320,7 @@ struct adv748x_state {
 
 /* Free run pattern select */
 #define ADV748X_SDP_FRP			0x14
-#define ADV748X_SDP_FRP_MASK		GENMASK(3, 1)
+#define ADV748X_SDP_FRP_MASK		GENMASK(2, 0)
 
 /* Saturation */
 #define ADV748X_SDP_SD_SAT_U		0xe3	/* user_map_rw_reg_e3 */
diff --git a/drivers/media/i2c/ccs-pll.c b/drivers/media/i2c/ccs-pll.c
index cf8858cb13d4..611c9823be85 100644
--- a/drivers/media/i2c/ccs-pll.c
+++ b/drivers/media/i2c/ccs-pll.c
@@ -312,6 +312,11 @@ __ccs_pll_calculate_vt_tree(struct device *dev,
 	dev_dbg(dev, "more_mul2: %u\n", more_mul);
 
 	pll_fr->pll_multiplier = mul * more_mul;
+	if (pll_fr->pll_multiplier > lim_fr->max_pll_multiplier) {
+		dev_dbg(dev, "pll multiplier %u too high\n",
+			pll_fr->pll_multiplier);
+		return -EINVAL;
+	}
 
 	if (pll_fr->pll_multiplier * pll_fr->pll_ip_clk_freq_hz >
 	    lim_fr->max_pll_op_clk_freq_hz)
@@ -397,6 +402,8 @@ static int ccs_pll_calculate_vt_tree(struct device *dev,
 	min_pre_pll_clk_div = max_t(u16, min_pre_pll_clk_div,
 				    pll->ext_clk_freq_hz /
 				    lim_fr->max_pll_ip_clk_freq_hz);
+	if (!(pll->flags & CCS_PLL_FLAG_EXT_IP_PLL_DIVIDER))
+		min_pre_pll_clk_div = clk_div_even(min_pre_pll_clk_div);
 
 	dev_dbg(dev, "vt min/max_pre_pll_clk_div: %u,%u\n",
 		min_pre_pll_clk_div, max_pre_pll_clk_div);
@@ -792,7 +799,7 @@ int ccs_pll_calculate(struct device *dev, const struct ccs_pll_limits *lim,
 		op_lim_fr->min_pre_pll_clk_div, op_lim_fr->max_pre_pll_clk_div);
 	max_op_pre_pll_clk_div =
 		min_t(u16, op_lim_fr->max_pre_pll_clk_div,
-		      clk_div_even(pll->ext_clk_freq_hz /
+		      DIV_ROUND_UP(pll->ext_clk_freq_hz,
 				   op_lim_fr->min_pll_ip_clk_freq_hz));
 	min_op_pre_pll_clk_div =
 		max_t(u16, op_lim_fr->min_pre_pll_clk_div,
@@ -815,6 +822,8 @@ int ccs_pll_calculate(struct device *dev, const struct ccs_pll_limits *lim,
 			      one_or_more(
 				      DIV_ROUND_UP(op_lim_fr->max_pll_op_clk_freq_hz,
 						   pll->ext_clk_freq_hz))));
+	if (!(pll->flags & CCS_PLL_FLAG_EXT_IP_PLL_DIVIDER))
+		min_op_pre_pll_clk_div = clk_div_even(min_op_pre_pll_clk_div);
 	dev_dbg(dev, "pll_op check: min / max op_pre_pll_clk_div: %u / %u\n",
 		min_op_pre_pll_clk_div, max_op_pre_pll_clk_div);
 
diff --git a/drivers/media/i2c/ccs/ccs-core.c b/drivers/media/i2c/ccs/ccs-core.c
index e1ae0f9fad43..4b7d8039b1c9 100644
--- a/drivers/media/i2c/ccs/ccs-core.c
+++ b/drivers/media/i2c/ccs/ccs-core.c
@@ -3562,19 +3562,20 @@ static int ccs_probe(struct i2c_client *client)
 out_disable_runtime_pm:
 	pm_runtime_put_noidle(&client->dev);
 	pm_runtime_disable(&client->dev);
+	pm_runtime_set_suspended(&client->dev);
 
 out_cleanup:
 	ccs_cleanup(sensor);
 
+out_free_ccs_limits:
+	kfree(sensor->ccs_limits);
+
 out_release_mdata:
 	kvfree(sensor->mdata.backing);
 
 out_release_sdata:
 	kvfree(sensor->sdata.backing);
 
-out_free_ccs_limits:
-	kfree(sensor->ccs_limits);
-
 out_power_off:
 	ccs_power_off(&client->dev);
 	mutex_destroy(&sensor->mutex);
@@ -3591,9 +3592,10 @@ static void ccs_remove(struct i2c_client *client)
 	v4l2_async_unregister_subdev(subdev);
 
 	pm_runtime_disable(&client->dev);
-	if (!pm_runtime_status_suspended(&client->dev))
+	if (!pm_runtime_status_suspended(&client->dev)) {
 		ccs_power_off(&client->dev);
-	pm_runtime_set_suspended(&client->dev);
+		pm_runtime_set_suspended(&client->dev);
+	}
 
 	for (i = 0; i < sensor->ssds_used; i++)
 		v4l2_device_unregister_subdev(&sensor->ssds[i].sd);
diff --git a/drivers/media/i2c/ccs/ccs-data.c b/drivers/media/i2c/ccs/ccs-data.c
index 08400edf77ce..2591dba51e17 100644
--- a/drivers/media/i2c/ccs/ccs-data.c
+++ b/drivers/media/i2c/ccs/ccs-data.c
@@ -10,6 +10,7 @@
 #include <linux/limits.h>
 #include <linux/mm.h>
 #include <linux/slab.h>
+#include <linux/string.h>
 
 #include "ccs-data-defs.h"
 
@@ -97,7 +98,7 @@ ccs_data_parse_length_specifier(const struct __ccs_data_length_specifier *__len,
 		plen = ((size_t)
 			(__len3->length[0] &
 			 ((1 << CCS_DATA_LENGTH_SPECIFIER_SIZE_SHIFT) - 1))
-			<< 16) + (__len3->length[0] << 8) + __len3->length[1];
+			<< 16) + (__len3->length[1] << 8) + __len3->length[2];
 		break;
 	}
 	default:
@@ -948,15 +949,15 @@ int ccs_data_parse(struct ccs_data_container *ccsdata, const void *data,
 
 	rval = __ccs_data_parse(&bin, ccsdata, data, len, dev, verbose);
 	if (rval)
-		return rval;
+		goto out_cleanup;
 
 	rval = bin_backing_alloc(&bin);
 	if (rval)
-		return rval;
+		goto out_cleanup;
 
 	rval = __ccs_data_parse(&bin, ccsdata, data, len, dev, false);
 	if (rval)
-		goto out_free;
+		goto out_cleanup;
 
 	if (verbose && ccsdata->version)
 		print_ccs_data_version(dev, ccsdata->version);
@@ -965,15 +966,16 @@ int ccs_data_parse(struct ccs_data_container *ccsdata, const void *data,
 		rval = -EPROTO;
 		dev_dbg(dev, "parsing mismatch; base %p; now %p; end %p\n",
 			bin.base, bin.now, bin.end);
-		goto out_free;
+		goto out_cleanup;
 	}
 
 	ccsdata->backing = bin.base;
 
 	return 0;
 
-out_free:
+out_cleanup:
 	kvfree(bin.base);
+	memset(ccsdata, 0, sizeof(*ccsdata));
 
 	return rval;
 }
diff --git a/drivers/media/i2c/ds90ub913.c b/drivers/media/i2c/ds90ub913.c
index 8eed4a200fd8..5d754372230e 100644
--- a/drivers/media/i2c/ds90ub913.c
+++ b/drivers/media/i2c/ds90ub913.c
@@ -8,6 +8,7 @@
  * Copyright (c) 2023 Tomi Valkeinen <tomi.valkeinen@ideasonboard.com>
  */
 
+#include <linux/bitfield.h>
 #include <linux/clk-provider.h>
 #include <linux/clk.h>
 #include <linux/delay.h>
@@ -146,6 +147,19 @@ static int ub913_write(const struct ub913_data *priv, u8 reg, u8 val)
 	return ret;
 }
 
+static int ub913_update_bits(const struct ub913_data *priv, u8 reg, u8 mask,
+			     u8 val)
+{
+	int ret;
+
+	ret = regmap_update_bits(priv->regmap, reg, mask, val);
+	if (ret < 0)
+		dev_err(&priv->client->dev,
+			"Cannot update register 0x%02x %d!\n", reg, ret);
+
+	return ret;
+}
+
 /*
  * GPIO chip
  */
@@ -436,10 +450,10 @@ static int ub913_set_fmt(struct v4l2_subdev *sd,
 	if (!fmt)
 		return -EINVAL;
 
-	format->format.code = finfo->outcode;
-
 	*fmt = format->format;
 
+	fmt->code = finfo->outcode;
+
 	return 0;
 }
 
@@ -733,10 +747,13 @@ static int ub913_hw_init(struct ub913_data *priv)
 	if (ret)
 		return dev_err_probe(dev, ret, "i2c master init failed\n");
 
-	ub913_read(priv, UB913_REG_GENERAL_CFG, &v);
-	v &= ~UB913_REG_GENERAL_CFG_PCLK_RISING;
-	v |= priv->pclk_polarity_rising ? UB913_REG_GENERAL_CFG_PCLK_RISING : 0;
-	ub913_write(priv, UB913_REG_GENERAL_CFG, v);
+	ret = ub913_update_bits(priv, UB913_REG_GENERAL_CFG,
+				UB913_REG_GENERAL_CFG_PCLK_RISING,
+				FIELD_PREP(UB913_REG_GENERAL_CFG_PCLK_RISING,
+					   priv->pclk_polarity_rising));
+
+	if (ret)
+		return ret;
 
 	return 0;
 }
@@ -793,7 +810,6 @@ static void ub913_subdev_uninit(struct ub913_data *priv)
 	v4l2_async_unregister_subdev(&priv->sd);
 	ub913_v4l2_nf_unregister(priv);
 	v4l2_subdev_cleanup(&priv->sd);
-	fwnode_handle_put(priv->sd.fwnode);
 	media_entity_cleanup(&priv->sd.entity);
 }
 
diff --git a/drivers/media/i2c/ds90ub953.c b/drivers/media/i2c/ds90ub953.c
index 16f88db14981..f0bad3e64f23 100644
--- a/drivers/media/i2c/ds90ub953.c
+++ b/drivers/media/i2c/ds90ub953.c
@@ -398,8 +398,13 @@ static int ub953_gpiochip_probe(struct ub953_data *priv)
 	int ret;
 
 	/* Set all GPIOs to local input mode */
-	ub953_write(priv, UB953_REG_LOCAL_GPIO_DATA, 0);
-	ub953_write(priv, UB953_REG_GPIO_INPUT_CTRL, 0xf);
+	ret = ub953_write(priv, UB953_REG_LOCAL_GPIO_DATA, 0);
+	if (ret)
+		return ret;
+
+	ret = ub953_write(priv, UB953_REG_GPIO_INPUT_CTRL, 0xf);
+	if (ret)
+		return ret;
 
 	gc->label = dev_name(dev);
 	gc->parent = dev;
@@ -961,10 +966,11 @@ static void ub953_calc_clkout_params(struct ub953_data *priv,
 	clkout_data->rate = clkout_rate;
 }
 
-static void ub953_write_clkout_regs(struct ub953_data *priv,
-				    const struct ub953_clkout_data *clkout_data)
+static int ub953_write_clkout_regs(struct ub953_data *priv,
+				   const struct ub953_clkout_data *clkout_data)
 {
 	u8 clkout_ctrl0, clkout_ctrl1;
+	int ret;
 
 	if (priv->hw_data->is_ub971)
 		clkout_ctrl0 = clkout_data->m;
@@ -974,8 +980,15 @@ static void ub953_write_clkout_regs(struct ub953_data *priv,
 
 	clkout_ctrl1 = clkout_data->n;
 
-	ub953_write(priv, UB953_REG_CLKOUT_CTRL0, clkout_ctrl0);
-	ub953_write(priv, UB953_REG_CLKOUT_CTRL1, clkout_ctrl1);
+	ret = ub953_write(priv, UB953_REG_CLKOUT_CTRL0, clkout_ctrl0);
+	if (ret)
+		return ret;
+
+	ret = ub953_write(priv, UB953_REG_CLKOUT_CTRL1, clkout_ctrl1);
+	if (ret)
+		return ret;
+
+	return 0;
 }
 
 static unsigned long ub953_clkout_recalc_rate(struct clk_hw *hw,
@@ -1055,9 +1068,7 @@ static int ub953_clkout_set_rate(struct clk_hw *hw, unsigned long rate,
 	dev_dbg(&priv->client->dev, "%s %lu (requested %lu)\n", __func__,
 		clkout_data.rate, rate);
 
-	ub953_write_clkout_regs(priv, &clkout_data);
-
-	return 0;
+	return ub953_write_clkout_regs(priv, &clkout_data);
 }
 
 static const struct clk_ops ub953_clkout_ops = {
@@ -1082,7 +1093,9 @@ static int ub953_register_clkout(struct ub953_data *priv)
 
 	/* Initialize clkout to 25MHz by default */
 	ub953_calc_clkout_params(priv, UB953_DEFAULT_CLKOUT_RATE, &clkout_data);
-	ub953_write_clkout_regs(priv, &clkout_data);
+	ret = ub953_write_clkout_regs(priv, &clkout_data);
+	if (ret)
+		return ret;
 
 	priv->clkout_clk_hw.init = &init;
 
@@ -1229,10 +1242,15 @@ static int ub953_hw_init(struct ub953_data *priv)
 	if (ret)
 		return dev_err_probe(dev, ret, "i2c init failed\n");
 
-	ub953_write(priv, UB953_REG_GENERAL_CFG,
-		    (priv->non_continous_clk ? 0 : UB953_REG_GENERAL_CFG_CONT_CLK) |
-		    ((priv->num_data_lanes - 1) << UB953_REG_GENERAL_CFG_CSI_LANE_SEL_SHIFT) |
-		    UB953_REG_GENERAL_CFG_CRC_TX_GEN_ENABLE);
+	v = 0;
+	v |= priv->non_continous_clk ? 0 : UB953_REG_GENERAL_CFG_CONT_CLK;
+	v |= (priv->num_data_lanes - 1) <<
+		UB953_REG_GENERAL_CFG_CSI_LANE_SEL_SHIFT;
+	v |= UB953_REG_GENERAL_CFG_CRC_TX_GEN_ENABLE;
+
+	ret = ub953_write(priv, UB953_REG_GENERAL_CFG, v);
+	if (ret)
+		return ret;
 
 	return 0;
 }
@@ -1291,7 +1309,6 @@ static void ub953_subdev_uninit(struct ub953_data *priv)
 	v4l2_async_unregister_subdev(&priv->sd);
 	ub953_v4l2_notifier_unregister(priv);
 	v4l2_subdev_cleanup(&priv->sd);
-	fwnode_handle_put(priv->sd.fwnode);
 	media_entity_cleanup(&priv->sd.entity);
 }
 
diff --git a/drivers/media/i2c/ds90ub960.c b/drivers/media/i2c/ds90ub960.c
index 58424d8f72af..432457a761b1 100644
--- a/drivers/media/i2c/ds90ub960.c
+++ b/drivers/media/i2c/ds90ub960.c
@@ -352,6 +352,8 @@
 
 #define UB960_SR_I2C_RX_ID(n)			(0xf8 + (n)) /* < UB960_FPD_RX_NPORTS */
 
+#define UB9702_SR_REFCLK_FREQ			0x3d
+
 /* Indirect register blocks */
 #define UB960_IND_TARGET_PAT_GEN		0x00
 #define UB960_IND_TARGET_RX_ANA(n)		(0x01 + (n))
@@ -1575,16 +1577,24 @@ static int ub960_rxport_wait_locks(struct ub960_data *priv,
 
 		ub960_rxport_read16(priv, nport, UB960_RR_RX_FREQ_HIGH, &v);
 
-		ret = ub960_rxport_get_strobe_pos(priv, nport, &strobe_pos);
-		if (ret)
-			return ret;
+		if (priv->hw_data->is_ub9702) {
+			dev_dbg(dev, "\trx%u: locked, freq %llu Hz\n",
+				nport, (v * 1000000ULL) >> 8);
+		} else {
+			ret = ub960_rxport_get_strobe_pos(priv, nport,
+							  &strobe_pos);
+			if (ret)
+				return ret;
 
-		ret = ub960_rxport_get_eq_level(priv, nport, &eq_level);
-		if (ret)
-			return ret;
+			ret = ub960_rxport_get_eq_level(priv, nport, &eq_level);
+			if (ret)
+				return ret;
 
-		dev_dbg(dev, "\trx%u: locked, SP: %d, EQ: %u, freq %llu Hz\n",
-			nport, strobe_pos, eq_level, (v * 1000000ULL) >> 8);
+			dev_dbg(dev,
+				"\trx%u: locked, SP: %d, EQ: %u, freq %llu Hz\n",
+				nport, strobe_pos, eq_level,
+				(v * 1000000ULL) >> 8);
+		}
 	}
 
 	return 0;
@@ -2523,7 +2533,7 @@ static int ub960_configure_ports_for_streaming(struct ub960_data *priv,
 				for (i = 0; i < 8; i++)
 					ub960_rxport_write(priv, nport,
 							   UB960_RR_VC_ID_MAP(i),
-							   nport);
+							   (nport << 4) | nport);
 			}
 
 			break;
@@ -2940,6 +2950,54 @@ static const struct v4l2_subdev_pad_ops ub960_pad_ops = {
 	.set_fmt = ub960_set_fmt,
 };
 
+static void ub960_log_status_ub960_sp_eq(struct ub960_data *priv,
+					 unsigned int nport)
+{
+	struct device *dev = &priv->client->dev;
+	u8 eq_level;
+	s8 strobe_pos;
+	u8 v = 0;
+
+	/* Strobe */
+
+	ub960_read(priv, UB960_XR_AEQ_CTL1, &v);
+
+	dev_info(dev, "\t%s strobe\n",
+		 (v & UB960_XR_AEQ_CTL1_AEQ_SFILTER_EN) ? "Adaptive" :
+							  "Manual");
+
+	if (v & UB960_XR_AEQ_CTL1_AEQ_SFILTER_EN) {
+		ub960_read(priv, UB960_XR_SFILTER_CFG, &v);
+
+		dev_info(dev, "\tStrobe range [%d, %d]\n",
+			 ((v >> UB960_XR_SFILTER_CFG_SFILTER_MIN_SHIFT) & 0xf) - 7,
+			 ((v >> UB960_XR_SFILTER_CFG_SFILTER_MAX_SHIFT) & 0xf) - 7);
+	}
+
+	ub960_rxport_get_strobe_pos(priv, nport, &strobe_pos);
+
+	dev_info(dev, "\tStrobe pos %d\n", strobe_pos);
+
+	/* EQ */
+
+	ub960_rxport_read(priv, nport, UB960_RR_AEQ_BYPASS, &v);
+
+	dev_info(dev, "\t%s EQ\n",
+		 (v & UB960_RR_AEQ_BYPASS_ENABLE) ? "Manual" :
+						    "Adaptive");
+
+	if (!(v & UB960_RR_AEQ_BYPASS_ENABLE)) {
+		ub960_rxport_read(priv, nport, UB960_RR_AEQ_MIN_MAX, &v);
+
+		dev_info(dev, "\tEQ range [%u, %u]\n",
+			 (v >> UB960_RR_AEQ_MIN_MAX_AEQ_FLOOR_SHIFT) & 0xf,
+			 (v >> UB960_RR_AEQ_MIN_MAX_AEQ_MAX_SHIFT) & 0xf);
+	}
+
+	if (ub960_rxport_get_eq_level(priv, nport, &eq_level) == 0)
+		dev_info(dev, "\tEQ level %u\n", eq_level);
+}
+
 static int ub960_log_status(struct v4l2_subdev *sd)
 {
 	struct ub960_data *priv = sd_to_ub960(sd);
@@ -2987,8 +3045,6 @@ static int ub960_log_status(struct v4l2_subdev *sd)
 
 	for (nport = 0; nport < priv->hw_data->num_rxports; nport++) {
 		struct ub960_rxport *rxport = priv->rxports[nport];
-		u8 eq_level;
-		s8 strobe_pos;
 		unsigned int i;
 
 		dev_info(dev, "RX %u\n", nport);
@@ -3024,44 +3080,8 @@ static int ub960_log_status(struct v4l2_subdev *sd)
 		ub960_rxport_read(priv, nport, UB960_RR_CSI_ERR_COUNTER, &v);
 		dev_info(dev, "\tcsi_err_counter %u\n", v);
 
-		/* Strobe */
-
-		ub960_read(priv, UB960_XR_AEQ_CTL1, &v);
-
-		dev_info(dev, "\t%s strobe\n",
-			 (v & UB960_XR_AEQ_CTL1_AEQ_SFILTER_EN) ? "Adaptive" :
-								  "Manual");
-
-		if (v & UB960_XR_AEQ_CTL1_AEQ_SFILTER_EN) {
-			ub960_read(priv, UB960_XR_SFILTER_CFG, &v);
-
-			dev_info(dev, "\tStrobe range [%d, %d]\n",
-				 ((v >> UB960_XR_SFILTER_CFG_SFILTER_MIN_SHIFT) & 0xf) - 7,
-				 ((v >> UB960_XR_SFILTER_CFG_SFILTER_MAX_SHIFT) & 0xf) - 7);
-		}
-
-		ub960_rxport_get_strobe_pos(priv, nport, &strobe_pos);
-
-		dev_info(dev, "\tStrobe pos %d\n", strobe_pos);
-
-		/* EQ */
-
-		ub960_rxport_read(priv, nport, UB960_RR_AEQ_BYPASS, &v);
-
-		dev_info(dev, "\t%s EQ\n",
-			 (v & UB960_RR_AEQ_BYPASS_ENABLE) ? "Manual" :
-							    "Adaptive");
-
-		if (!(v & UB960_RR_AEQ_BYPASS_ENABLE)) {
-			ub960_rxport_read(priv, nport, UB960_RR_AEQ_MIN_MAX, &v);
-
-			dev_info(dev, "\tEQ range [%u, %u]\n",
-				 (v >> UB960_RR_AEQ_MIN_MAX_AEQ_FLOOR_SHIFT) & 0xf,
-				 (v >> UB960_RR_AEQ_MIN_MAX_AEQ_MAX_SHIFT) & 0xf);
-		}
-
-		if (ub960_rxport_get_eq_level(priv, nport, &eq_level) == 0)
-			dev_info(dev, "\tEQ level %u\n", eq_level);
+		if (!priv->hw_data->is_ub9702)
+			ub960_log_status_ub960_sp_eq(priv, nport);
 
 		/* GPIOs */
 		for (i = 0; i < UB960_NUM_BC_GPIOS; i++) {
@@ -3837,7 +3857,10 @@ static int ub960_enable_core_hw(struct ub960_data *priv)
 	if (ret)
 		goto err_pd_gpio;
 
-	ret = ub960_read(priv, UB960_XR_REFCLK_FREQ, &refclk_freq);
+	if (priv->hw_data->is_ub9702)
+		ret = ub960_read(priv, UB9702_SR_REFCLK_FREQ, &refclk_freq);
+	else
+		ret = ub960_read(priv, UB960_XR_REFCLK_FREQ, &refclk_freq);
 	if (ret)
 		goto err_pd_gpio;
 
diff --git a/drivers/media/i2c/hi556.c b/drivers/media/i2c/hi556.c
index f31f9886c924..3c84cf07275f 100644
--- a/drivers/media/i2c/hi556.c
+++ b/drivers/media/i2c/hi556.c
@@ -1230,12 +1230,13 @@ static int hi556_check_hwcfg(struct device *dev)
 	ret = fwnode_property_read_u32(fwnode, "clock-frequency", &mclk);
 	if (ret) {
 		dev_err(dev, "can't get clock frequency");
-		return ret;
+		goto check_hwcfg_error;
 	}
 
 	if (mclk != HI556_MCLK) {
 		dev_err(dev, "external clock %d is not supported", mclk);
-		return -EINVAL;
+		ret = -EINVAL;
+		goto check_hwcfg_error;
 	}
 
 	if (bus_cfg.bus.mipi_csi2.num_data_lanes != 2) {
@@ -1320,7 +1321,12 @@ static int hi556_resume(struct device *dev)
 		return ret;
 	}
 
-	gpiod_set_value_cansleep(hi556->reset_gpio, 0);
+	if (hi556->reset_gpio) {
+		/* Assert reset for at least 2ms on back to back off-on */
+		usleep_range(2000, 2200);
+		gpiod_set_value_cansleep(hi556->reset_gpio, 0);
+	}
+
 	usleep_range(5000, 5500);
 	return 0;
 }
diff --git a/drivers/media/i2c/imx214.c b/drivers/media/i2c/imx214.c
index 4962cfe7c83d..ea5e294327e7 100644
--- a/drivers/media/i2c/imx214.c
+++ b/drivers/media/i2c/imx214.c
@@ -15,26 +15,152 @@
 #include <linux/regmap.h>
 #include <linux/regulator/consumer.h>
 #include <media/media-entity.h>
+#include <media/v4l2-cci.h>
 #include <media/v4l2-ctrls.h>
 #include <media/v4l2-fwnode.h>
 #include <media/v4l2-subdev.h>
 
-#define IMX214_REG_MODE_SELECT		0x0100
+#define IMX214_REG_MODE_SELECT		CCI_REG8(0x0100)
 #define IMX214_MODE_STANDBY		0x00
 #define IMX214_MODE_STREAMING		0x01
 
+#define IMX214_REG_FAST_STANDBY_CTRL	CCI_REG8(0x0106)
+
 #define IMX214_DEFAULT_CLK_FREQ	24000000
-#define IMX214_DEFAULT_LINK_FREQ 480000000
+#define IMX214_DEFAULT_LINK_FREQ	600000000
+/* Keep wrong link frequency for backward compatibility */
+#define IMX214_DEFAULT_LINK_FREQ_LEGACY	480000000
 #define IMX214_DEFAULT_PIXEL_RATE ((IMX214_DEFAULT_LINK_FREQ * 8LL) / 10)
 #define IMX214_FPS 30
 #define IMX214_MBUS_CODE MEDIA_BUS_FMT_SRGGB10_1X10
 
+/* V-TIMING internal */
+#define IMX214_REG_FRM_LENGTH_LINES	CCI_REG16(0x0340)
+
 /* Exposure control */
-#define IMX214_REG_EXPOSURE		0x0202
+#define IMX214_REG_EXPOSURE		CCI_REG16(0x0202)
 #define IMX214_EXPOSURE_MIN		0
 #define IMX214_EXPOSURE_MAX		3184
 #define IMX214_EXPOSURE_STEP		1
 #define IMX214_EXPOSURE_DEFAULT		3184
+#define IMX214_REG_EXPOSURE_RATIO	CCI_REG8(0x0222)
+#define IMX214_REG_SHORT_EXPOSURE	CCI_REG16(0x0224)
+
+/* Analog gain control */
+#define IMX214_REG_ANALOG_GAIN		CCI_REG16(0x0204)
+#define IMX214_REG_SHORT_ANALOG_GAIN	CCI_REG16(0x0216)
+
+/* Digital gain control */
+#define IMX214_REG_DIG_GAIN_GREENR	CCI_REG16(0x020e)
+#define IMX214_REG_DIG_GAIN_RED		CCI_REG16(0x0210)
+#define IMX214_REG_DIG_GAIN_BLUE	CCI_REG16(0x0212)
+#define IMX214_REG_DIG_GAIN_GREENB	CCI_REG16(0x0214)
+
+#define IMX214_REG_ORIENTATION		CCI_REG8(0x0101)
+
+#define IMX214_REG_MASK_CORR_FRAMES	CCI_REG8(0x0105)
+#define IMX214_CORR_FRAMES_TRANSMIT	0
+#define IMX214_CORR_FRAMES_MASK		1
+
+#define IMX214_REG_CSI_DATA_FORMAT	CCI_REG16(0x0112)
+#define IMX214_CSI_DATA_FORMAT_RAW8	0x0808
+#define IMX214_CSI_DATA_FORMAT_RAW10	0x0A0A
+#define IMX214_CSI_DATA_FORMAT_COMP6	0x0A06
+#define IMX214_CSI_DATA_FORMAT_COMP8	0x0A08
+
+#define IMX214_REG_CSI_LANE_MODE	CCI_REG8(0x0114)
+#define IMX214_CSI_2_LANE_MODE		1
+#define IMX214_CSI_4_LANE_MODE		3
+
+#define IMX214_REG_EXCK_FREQ		CCI_REG16(0x0136)
+#define IMX214_EXCK_FREQ(n)		((n) * 256)	/* n expressed in MHz */
+
+#define IMX214_REG_TEMP_SENSOR_CONTROL	CCI_REG8(0x0138)
+
+#define IMX214_REG_HDR_MODE		CCI_REG8(0x0220)
+#define IMX214_HDR_MODE_OFF		0
+#define IMX214_HDR_MODE_ON		1
+
+#define IMX214_REG_HDR_RES_REDUCTION	CCI_REG8(0x0221)
+#define IMX214_HDR_RES_REDU_THROUGH	0x11
+#define IMX214_HDR_RES_REDU_2_BINNING	0x22
+
+/* PLL settings */
+#define IMX214_REG_VTPXCK_DIV		CCI_REG8(0x0301)
+#define IMX214_REG_VTSYCK_DIV		CCI_REG8(0x0303)
+#define IMX214_REG_PREPLLCK_VT_DIV	CCI_REG8(0x0305)
+#define IMX214_REG_PLL_VT_MPY		CCI_REG16(0x0306)
+#define IMX214_REG_OPPXCK_DIV		CCI_REG8(0x0309)
+#define IMX214_REG_OPSYCK_DIV		CCI_REG8(0x030b)
+#define IMX214_REG_PLL_MULT_DRIV	CCI_REG8(0x0310)
+#define IMX214_PLL_SINGLE		0
+#define IMX214_PLL_DUAL			1
+
+#define IMX214_REG_LINE_LENGTH_PCK	CCI_REG16(0x0342)
+#define IMX214_REG_X_ADD_STA		CCI_REG16(0x0344)
+#define IMX214_REG_Y_ADD_STA		CCI_REG16(0x0346)
+#define IMX214_REG_X_ADD_END		CCI_REG16(0x0348)
+#define IMX214_REG_Y_ADD_END		CCI_REG16(0x034a)
+#define IMX214_REG_X_OUTPUT_SIZE	CCI_REG16(0x034c)
+#define IMX214_REG_Y_OUTPUT_SIZE	CCI_REG16(0x034e)
+#define IMX214_REG_X_EVEN_INC		CCI_REG8(0x0381)
+#define IMX214_REG_X_ODD_INC		CCI_REG8(0x0383)
+#define IMX214_REG_Y_EVEN_INC		CCI_REG8(0x0385)
+#define IMX214_REG_Y_ODD_INC		CCI_REG8(0x0387)
+
+#define IMX214_REG_SCALE_MODE		CCI_REG8(0x0401)
+#define IMX214_SCALE_NONE		0
+#define IMX214_SCALE_HORIZONTAL		1
+#define IMX214_SCALE_FULL		2
+#define IMX214_REG_SCALE_M		CCI_REG16(0x0404)
+
+#define IMX214_REG_DIG_CROP_X_OFFSET	CCI_REG16(0x0408)
+#define IMX214_REG_DIG_CROP_Y_OFFSET	CCI_REG16(0x040a)
+#define IMX214_REG_DIG_CROP_WIDTH	CCI_REG16(0x040c)
+#define IMX214_REG_DIG_CROP_HEIGHT	CCI_REG16(0x040e)
+
+#define IMX214_REG_REQ_LINK_BIT_RATE	CCI_REG32(0x0820)
+#define IMX214_LINK_BIT_RATE_MBPS(n)	((n) << 16)
+
+/* Binning mode */
+#define IMX214_REG_BINNING_MODE		CCI_REG8(0x0900)
+#define IMX214_BINNING_NONE		0
+#define IMX214_BINNING_ENABLE		1
+#define IMX214_REG_BINNING_TYPE		CCI_REG8(0x0901)
+#define IMX214_REG_BINNING_WEIGHTING	CCI_REG8(0x0902)
+#define IMX214_BINNING_AVERAGE		0x00
+#define IMX214_BINNING_SUMMED		0x01
+#define IMX214_BINNING_BAYER		0x02
+
+#define IMX214_REG_SING_DEF_CORR_EN	CCI_REG8(0x0b06)
+#define IMX214_SING_DEF_CORR_OFF	0
+#define IMX214_SING_DEF_CORR_ON		1
+
+/* AWB control */
+#define IMX214_REG_ABS_GAIN_GREENR	CCI_REG16(0x0b8e)
+#define IMX214_REG_ABS_GAIN_RED		CCI_REG16(0x0b90)
+#define IMX214_REG_ABS_GAIN_BLUE	CCI_REG16(0x0b92)
+#define IMX214_REG_ABS_GAIN_GREENB	CCI_REG16(0x0b94)
+
+#define IMX214_REG_RMSC_NR_MODE		CCI_REG8(0x3001)
+#define IMX214_REG_STATS_OUT_EN		CCI_REG8(0x3013)
+#define IMX214_STATS_OUT_OFF		0
+#define IMX214_STATS_OUT_ON		1
+
+/* Chroma noise reduction */
+#define IMX214_REG_NML_NR_EN		CCI_REG8(0x30a2)
+#define IMX214_NML_NR_OFF		0
+#define IMX214_NML_NR_ON		1
+
+#define IMX214_REG_EBD_SIZE_V		CCI_REG8(0x5041)
+#define IMX214_EBD_NO			0
+#define IMX214_EBD_4_LINE		4
+
+#define IMX214_REG_RG_STATS_LMT		CCI_REG16(0x6d12)
+#define IMX214_RG_STATS_LMT_10_BIT	0x03FF
+#define IMX214_RG_STATS_LMT_14_BIT	0x3FFF
+
+#define IMX214_REG_ATR_FAST_MOVE	CCI_REG8(0x9300)
 
 /* IMX214 native and active pixel array size */
 #define IMX214_NATIVE_WIDTH		4224U
@@ -59,8 +185,6 @@ struct imx214 {
 
 	struct v4l2_subdev sd;
 	struct media_pad pad;
-	struct v4l2_mbus_framefmt fmt;
-	struct v4l2_rect crop;
 
 	struct v4l2_ctrl_handler ctrls;
 	struct v4l2_ctrl *pixel_rate;
@@ -71,353 +195,266 @@ struct imx214 {
 	struct regulator_bulk_data	supplies[IMX214_NUM_SUPPLIES];
 
 	struct gpio_desc *enable_gpio;
-
-	/*
-	 * Serialize control access, get/set format, get selection
-	 * and start streaming.
-	 */
-	struct mutex mutex;
-};
-
-struct reg_8 {
-	u16 addr;
-	u8 val;
-};
-
-enum {
-	IMX214_TABLE_WAIT_MS = 0,
-	IMX214_TABLE_END,
-	IMX214_MAX_RETRIES,
-	IMX214_WAIT_MS
 };
 
 /*From imx214_mode_tbls.h*/
-static const struct reg_8 mode_4096x2304[] = {
-	{0x0114, 0x03},
-	{0x0220, 0x00},
-	{0x0221, 0x11},
-	{0x0222, 0x01},
-	{0x0340, 0x0C},
-	{0x0341, 0x7A},
-	{0x0342, 0x13},
-	{0x0343, 0x90},
-	{0x0344, 0x00},
-	{0x0345, 0x38},
-	{0x0346, 0x01},
-	{0x0347, 0x98},
-	{0x0348, 0x10},
-	{0x0349, 0x37},
-	{0x034A, 0x0A},
-	{0x034B, 0x97},
-	{0x0381, 0x01},
-	{0x0383, 0x01},
-	{0x0385, 0x01},
-	{0x0387, 0x01},
-	{0x0900, 0x00},
-	{0x0901, 0x00},
-	{0x0902, 0x00},
-	{0x3000, 0x35},
-	{0x3054, 0x01},
-	{0x305C, 0x11},
-
-	{0x0112, 0x0A},
-	{0x0113, 0x0A},
-	{0x034C, 0x10},
-	{0x034D, 0x00},
-	{0x034E, 0x09},
-	{0x034F, 0x00},
-	{0x0401, 0x00},
-	{0x0404, 0x00},
-	{0x0405, 0x10},
-	{0x0408, 0x00},
-	{0x0409, 0x00},
-	{0x040A, 0x00},
-	{0x040B, 0x00},
-	{0x040C, 0x10},
-	{0x040D, 0x00},
-	{0x040E, 0x09},
-	{0x040F, 0x00},
-
-	{0x0301, 0x05},
-	{0x0303, 0x02},
-	{0x0305, 0x03},
-	{0x0306, 0x00},
-	{0x0307, 0x96},
-	{0x0309, 0x0A},
-	{0x030B, 0x01},
-	{0x0310, 0x00},
-
-	{0x0820, 0x12},
-	{0x0821, 0xC0},
-	{0x0822, 0x00},
-	{0x0823, 0x00},
-
-	{0x3A03, 0x09},
-	{0x3A04, 0x50},
-	{0x3A05, 0x01},
-
-	{0x0B06, 0x01},
-	{0x30A2, 0x00},
-
-	{0x30B4, 0x00},
-
-	{0x3A02, 0xFF},
-
-	{0x3011, 0x00},
-	{0x3013, 0x01},
-
-	{0x0202, 0x0C},
-	{0x0203, 0x70},
-	{0x0224, 0x01},
-	{0x0225, 0xF4},
-
-	{0x0204, 0x00},
-	{0x0205, 0x00},
-	{0x020E, 0x01},
-	{0x020F, 0x00},
-	{0x0210, 0x01},
-	{0x0211, 0x00},
-	{0x0212, 0x01},
-	{0x0213, 0x00},
-	{0x0214, 0x01},
-	{0x0215, 0x00},
-	{0x0216, 0x00},
-	{0x0217, 0x00},
-
-	{0x4170, 0x00},
-	{0x4171, 0x10},
-	{0x4176, 0x00},
-	{0x4177, 0x3C},
-	{0xAE20, 0x04},
-	{0xAE21, 0x5C},
-
-	{IMX214_TABLE_WAIT_MS, 10},
-	{0x0138, 0x01},
-	{IMX214_TABLE_END, 0x00}
+static const struct cci_reg_sequence mode_4096x2304[] = {
+	{ IMX214_REG_HDR_MODE, IMX214_HDR_MODE_OFF },
+	{ IMX214_REG_HDR_RES_REDUCTION, IMX214_HDR_RES_REDU_THROUGH },
+	{ IMX214_REG_EXPOSURE_RATIO, 1 },
+	{ IMX214_REG_FRM_LENGTH_LINES, 3194 },
+	{ IMX214_REG_LINE_LENGTH_PCK, 5008 },
+	{ IMX214_REG_X_ADD_STA, 56 },
+	{ IMX214_REG_Y_ADD_STA, 408 },
+	{ IMX214_REG_X_ADD_END, 4151 },
+	{ IMX214_REG_Y_ADD_END, 2711 },
+	{ IMX214_REG_X_EVEN_INC, 1 },
+	{ IMX214_REG_X_ODD_INC, 1 },
+	{ IMX214_REG_Y_EVEN_INC, 1 },
+	{ IMX214_REG_Y_ODD_INC, 1 },
+	{ IMX214_REG_BINNING_MODE, IMX214_BINNING_NONE },
+	{ IMX214_REG_BINNING_TYPE, 0 },
+	{ IMX214_REG_BINNING_WEIGHTING, IMX214_BINNING_AVERAGE },
+	{ CCI_REG8(0x3000), 0x35 },
+	{ CCI_REG8(0x3054), 0x01 },
+	{ CCI_REG8(0x305C), 0x11 },
+
+	{ IMX214_REG_CSI_DATA_FORMAT, IMX214_CSI_DATA_FORMAT_RAW10 },
+	{ IMX214_REG_X_OUTPUT_SIZE, 4096 },
+	{ IMX214_REG_Y_OUTPUT_SIZE, 2304 },
+	{ IMX214_REG_SCALE_MODE, IMX214_SCALE_NONE },
+	{ IMX214_REG_SCALE_M, 2 },
+	{ IMX214_REG_DIG_CROP_X_OFFSET, 0 },
+	{ IMX214_REG_DIG_CROP_Y_OFFSET, 0 },
+	{ IMX214_REG_DIG_CROP_WIDTH, 4096 },
+	{ IMX214_REG_DIG_CROP_HEIGHT, 2304 },
+
+	{ IMX214_REG_VTPXCK_DIV, 5 },
+	{ IMX214_REG_VTSYCK_DIV, 2 },
+	{ IMX214_REG_PREPLLCK_VT_DIV, 3 },
+	{ IMX214_REG_PLL_VT_MPY, 150 },
+	{ IMX214_REG_OPPXCK_DIV, 10 },
+	{ IMX214_REG_OPSYCK_DIV, 1 },
+	{ IMX214_REG_PLL_MULT_DRIV, IMX214_PLL_SINGLE },
+
+	{ IMX214_REG_REQ_LINK_BIT_RATE, IMX214_LINK_BIT_RATE_MBPS(4800) },
+
+	{ CCI_REG8(0x3A03), 0x09 },
+	{ CCI_REG8(0x3A04), 0x50 },
+	{ CCI_REG8(0x3A05), 0x01 },
+
+	{ IMX214_REG_SING_DEF_CORR_EN, IMX214_SING_DEF_CORR_ON },
+	{ IMX214_REG_NML_NR_EN, IMX214_NML_NR_OFF },
+
+	{ CCI_REG8(0x30B4), 0x00 },
+
+	{ CCI_REG8(0x3A02), 0xFF },
+
+	{ CCI_REG8(0x3011), 0x00 },
+	{ IMX214_REG_STATS_OUT_EN, IMX214_STATS_OUT_ON },
+
+	{ IMX214_REG_EXPOSURE, IMX214_EXPOSURE_DEFAULT },
+	{ IMX214_REG_SHORT_EXPOSURE, 500 },
+
+	{ IMX214_REG_ANALOG_GAIN, 0 },
+	{ IMX214_REG_DIG_GAIN_GREENR, 256 },
+	{ IMX214_REG_DIG_GAIN_RED, 256 },
+	{ IMX214_REG_DIG_GAIN_BLUE, 256 },
+	{ IMX214_REG_DIG_GAIN_GREENB, 256 },
+	{ IMX214_REG_SHORT_ANALOG_GAIN, 0 },
+
+	{ CCI_REG8(0x4170), 0x00 },
+	{ CCI_REG8(0x4171), 0x10 },
+	{ CCI_REG8(0x4176), 0x00 },
+	{ CCI_REG8(0x4177), 0x3C },
+	{ CCI_REG8(0xAE20), 0x04 },
+	{ CCI_REG8(0xAE21), 0x5C },
 };
 
-static const struct reg_8 mode_1920x1080[] = {
-	{0x0114, 0x03},
-	{0x0220, 0x00},
-	{0x0221, 0x11},
-	{0x0222, 0x01},
-	{0x0340, 0x0C},
-	{0x0341, 0x7A},
-	{0x0342, 0x13},
-	{0x0343, 0x90},
-	{0x0344, 0x04},
-	{0x0345, 0x78},
-	{0x0346, 0x03},
-	{0x0347, 0xFC},
-	{0x0348, 0x0B},
-	{0x0349, 0xF7},
-	{0x034A, 0x08},
-	{0x034B, 0x33},
-	{0x0381, 0x01},
-	{0x0383, 0x01},
-	{0x0385, 0x01},
-	{0x0387, 0x01},
-	{0x0900, 0x00},
-	{0x0901, 0x00},
-	{0x0902, 0x00},
-	{0x3000, 0x35},
-	{0x3054, 0x01},
-	{0x305C, 0x11},
-
-	{0x0112, 0x0A},
-	{0x0113, 0x0A},
-	{0x034C, 0x07},
-	{0x034D, 0x80},
-	{0x034E, 0x04},
-	{0x034F, 0x38},
-	{0x0401, 0x00},
-	{0x0404, 0x00},
-	{0x0405, 0x10},
-	{0x0408, 0x00},
-	{0x0409, 0x00},
-	{0x040A, 0x00},
-	{0x040B, 0x00},
-	{0x040C, 0x07},
-	{0x040D, 0x80},
-	{0x040E, 0x04},
-	{0x040F, 0x38},
-
-	{0x0301, 0x05},
-	{0x0303, 0x02},
-	{0x0305, 0x03},
-	{0x0306, 0x00},
-	{0x0307, 0x96},
-	{0x0309, 0x0A},
-	{0x030B, 0x01},
-	{0x0310, 0x00},
-
-	{0x0820, 0x12},
-	{0x0821, 0xC0},
-	{0x0822, 0x00},
-	{0x0823, 0x00},
-
-	{0x3A03, 0x04},
-	{0x3A04, 0xF8},
-	{0x3A05, 0x02},
-
-	{0x0B06, 0x01},
-	{0x30A2, 0x00},
-
-	{0x30B4, 0x00},
-
-	{0x3A02, 0xFF},
-
-	{0x3011, 0x00},
-	{0x3013, 0x01},
-
-	{0x0202, 0x0C},
-	{0x0203, 0x70},
-	{0x0224, 0x01},
-	{0x0225, 0xF4},
-
-	{0x0204, 0x00},
-	{0x0205, 0x00},
-	{0x020E, 0x01},
-	{0x020F, 0x00},
-	{0x0210, 0x01},
-	{0x0211, 0x00},
-	{0x0212, 0x01},
-	{0x0213, 0x00},
-	{0x0214, 0x01},
-	{0x0215, 0x00},
-	{0x0216, 0x00},
-	{0x0217, 0x00},
-
-	{0x4170, 0x00},
-	{0x4171, 0x10},
-	{0x4176, 0x00},
-	{0x4177, 0x3C},
-	{0xAE20, 0x04},
-	{0xAE21, 0x5C},
-
-	{IMX214_TABLE_WAIT_MS, 10},
-	{0x0138, 0x01},
-	{IMX214_TABLE_END, 0x00}
+static const struct cci_reg_sequence mode_1920x1080[] = {
+	{ IMX214_REG_HDR_MODE, IMX214_HDR_MODE_OFF },
+	{ IMX214_REG_HDR_RES_REDUCTION, IMX214_HDR_RES_REDU_THROUGH },
+	{ IMX214_REG_EXPOSURE_RATIO, 1 },
+	{ IMX214_REG_FRM_LENGTH_LINES, 3194 },
+	{ IMX214_REG_LINE_LENGTH_PCK, 5008 },
+	{ IMX214_REG_X_ADD_STA, 1144 },
+	{ IMX214_REG_Y_ADD_STA, 1020 },
+	{ IMX214_REG_X_ADD_END, 3063 },
+	{ IMX214_REG_Y_ADD_END, 2099 },
+	{ IMX214_REG_X_EVEN_INC, 1 },
+	{ IMX214_REG_X_ODD_INC, 1 },
+	{ IMX214_REG_Y_EVEN_INC, 1 },
+	{ IMX214_REG_Y_ODD_INC, 1 },
+	{ IMX214_REG_BINNING_MODE, IMX214_BINNING_NONE },
+	{ IMX214_REG_BINNING_TYPE, 0 },
+	{ IMX214_REG_BINNING_WEIGHTING, IMX214_BINNING_AVERAGE },
+	{ CCI_REG8(0x3000), 0x35 },
+	{ CCI_REG8(0x3054), 0x01 },
+	{ CCI_REG8(0x305C), 0x11 },
+
+	{ IMX214_REG_CSI_DATA_FORMAT, IMX214_CSI_DATA_FORMAT_RAW10 },
+	{ IMX214_REG_X_OUTPUT_SIZE, 1920 },
+	{ IMX214_REG_Y_OUTPUT_SIZE, 1080 },
+	{ IMX214_REG_SCALE_MODE, IMX214_SCALE_NONE },
+	{ IMX214_REG_SCALE_M, 2 },
+	{ IMX214_REG_DIG_CROP_X_OFFSET, 0 },
+	{ IMX214_REG_DIG_CROP_Y_OFFSET, 0 },
+	{ IMX214_REG_DIG_CROP_WIDTH, 1920 },
+	{ IMX214_REG_DIG_CROP_HEIGHT, 1080 },
+
+	{ IMX214_REG_VTPXCK_DIV, 5 },
+	{ IMX214_REG_VTSYCK_DIV, 2 },
+	{ IMX214_REG_PREPLLCK_VT_DIV, 3 },
+	{ IMX214_REG_PLL_VT_MPY, 150 },
+	{ IMX214_REG_OPPXCK_DIV, 10 },
+	{ IMX214_REG_OPSYCK_DIV, 1 },
+	{ IMX214_REG_PLL_MULT_DRIV, IMX214_PLL_SINGLE },
+
+	{ IMX214_REG_REQ_LINK_BIT_RATE, IMX214_LINK_BIT_RATE_MBPS(4800) },
+
+	{ CCI_REG8(0x3A03), 0x04 },
+	{ CCI_REG8(0x3A04), 0xF8 },
+	{ CCI_REG8(0x3A05), 0x02 },
+
+	{ IMX214_REG_SING_DEF_CORR_EN, IMX214_SING_DEF_CORR_ON },
+	{ IMX214_REG_NML_NR_EN, IMX214_NML_NR_OFF },
+
+	{ CCI_REG8(0x30B4), 0x00 },
+
+	{ CCI_REG8(0x3A02), 0xFF },
+
+	{ CCI_REG8(0x3011), 0x00 },
+	{ IMX214_REG_STATS_OUT_EN, IMX214_STATS_OUT_ON },
+
+	{ IMX214_REG_EXPOSURE, IMX214_EXPOSURE_DEFAULT },
+	{ IMX214_REG_SHORT_EXPOSURE, 500 },
+
+	{ IMX214_REG_ANALOG_GAIN, 0 },
+	{ IMX214_REG_DIG_GAIN_GREENR, 256 },
+	{ IMX214_REG_DIG_GAIN_RED, 256 },
+	{ IMX214_REG_DIG_GAIN_BLUE, 256 },
+	{ IMX214_REG_DIG_GAIN_GREENB, 256 },
+	{ IMX214_REG_SHORT_ANALOG_GAIN, 0 },
+
+	{ CCI_REG8(0x4170), 0x00 },
+	{ CCI_REG8(0x4171), 0x10 },
+	{ CCI_REG8(0x4176), 0x00 },
+	{ CCI_REG8(0x4177), 0x3C },
+	{ CCI_REG8(0xAE20), 0x04 },
+	{ CCI_REG8(0xAE21), 0x5C },
 };
 
-static const struct reg_8 mode_table_common[] = {
+static const struct cci_reg_sequence mode_table_common[] = {
 	/* software reset */
 
 	/* software standby settings */
-	{0x0100, 0x00},
+	{ IMX214_REG_MODE_SELECT, IMX214_MODE_STANDBY },
 
 	/* ATR setting */
-	{0x9300, 0x02},
+	{ IMX214_REG_ATR_FAST_MOVE, 2 },
 
 	/* external clock setting */
-	{0x0136, 0x18},
-	{0x0137, 0x00},
+	{ IMX214_REG_EXCK_FREQ, IMX214_EXCK_FREQ(IMX214_DEFAULT_CLK_FREQ / 1000000) },
 
 	/* global setting */
 	/* basic config */
-	{0x0101, 0x00},
-	{0x0105, 0x01},
-	{0x0106, 0x01},
-	{0x4550, 0x02},
-	{0x4601, 0x00},
-	{0x4642, 0x05},
-	{0x6227, 0x11},
-	{0x6276, 0x00},
-	{0x900E, 0x06},
-	{0xA802, 0x90},
-	{0xA803, 0x11},
-	{0xA804, 0x62},
-	{0xA805, 0x77},
-	{0xA806, 0xAE},
-	{0xA807, 0x34},
-	{0xA808, 0xAE},
-	{0xA809, 0x35},
-	{0xA80A, 0x62},
-	{0xA80B, 0x83},
-	{0xAE33, 0x00},
+	{ IMX214_REG_ORIENTATION, 0 },
+	{ IMX214_REG_MASK_CORR_FRAMES, IMX214_CORR_FRAMES_MASK },
+	{ IMX214_REG_FAST_STANDBY_CTRL, 1 },
+	{ CCI_REG8(0x4550), 0x02 },
+	{ CCI_REG8(0x4601), 0x00 },
+	{ CCI_REG8(0x4642), 0x05 },
+	{ CCI_REG8(0x6227), 0x11 },
+	{ CCI_REG8(0x6276), 0x00 },
+	{ CCI_REG8(0x900E), 0x06 },
+	{ CCI_REG8(0xA802), 0x90 },
+	{ CCI_REG8(0xA803), 0x11 },
+	{ CCI_REG8(0xA804), 0x62 },
+	{ CCI_REG8(0xA805), 0x77 },
+	{ CCI_REG8(0xA806), 0xAE },
+	{ CCI_REG8(0xA807), 0x34 },
+	{ CCI_REG8(0xA808), 0xAE },
+	{ CCI_REG8(0xA809), 0x35 },
+	{ CCI_REG8(0xA80A), 0x62 },
+	{ CCI_REG8(0xA80B), 0x83 },
+	{ CCI_REG8(0xAE33), 0x00 },
 
 	/* analog setting */
-	{0x4174, 0x00},
-	{0x4175, 0x11},
-	{0x4612, 0x29},
-	{0x461B, 0x12},
-	{0x461F, 0x06},
-	{0x4635, 0x07},
-	{0x4637, 0x30},
-	{0x463F, 0x18},
-	{0x4641, 0x0D},
-	{0x465B, 0x12},
-	{0x465F, 0x11},
-	{0x4663, 0x11},
-	{0x4667, 0x0F},
-	{0x466F, 0x0F},
-	{0x470E, 0x09},
-	{0x4909, 0xAB},
-	{0x490B, 0x95},
-	{0x4915, 0x5D},
-	{0x4A5F, 0xFF},
-	{0x4A61, 0xFF},
-	{0x4A73, 0x62},
-	{0x4A85, 0x00},
-	{0x4A87, 0xFF},
+	{ CCI_REG8(0x4174), 0x00 },
+	{ CCI_REG8(0x4175), 0x11 },
+	{ CCI_REG8(0x4612), 0x29 },
+	{ CCI_REG8(0x461B), 0x12 },
+	{ CCI_REG8(0x461F), 0x06 },
+	{ CCI_REG8(0x4635), 0x07 },
+	{ CCI_REG8(0x4637), 0x30 },
+	{ CCI_REG8(0x463F), 0x18 },
+	{ CCI_REG8(0x4641), 0x0D },
+	{ CCI_REG8(0x465B), 0x12 },
+	{ CCI_REG8(0x465F), 0x11 },
+	{ CCI_REG8(0x4663), 0x11 },
+	{ CCI_REG8(0x4667), 0x0F },
+	{ CCI_REG8(0x466F), 0x0F },
+	{ CCI_REG8(0x470E), 0x09 },
+	{ CCI_REG8(0x4909), 0xAB },
+	{ CCI_REG8(0x490B), 0x95 },
+	{ CCI_REG8(0x4915), 0x5D },
+	{ CCI_REG8(0x4A5F), 0xFF },
+	{ CCI_REG8(0x4A61), 0xFF },
+	{ CCI_REG8(0x4A73), 0x62 },
+	{ CCI_REG8(0x4A85), 0x00 },
+	{ CCI_REG8(0x4A87), 0xFF },
 
 	/* embedded data */
-	{0x5041, 0x04},
-	{0x583C, 0x04},
-	{0x620E, 0x04},
-	{0x6EB2, 0x01},
-	{0x6EB3, 0x00},
-	{0x9300, 0x02},
+	{ IMX214_REG_EBD_SIZE_V, IMX214_EBD_4_LINE },
+	{ CCI_REG8(0x583C), 0x04 },
+	{ CCI_REG8(0x620E), 0x04 },
+	{ CCI_REG8(0x6EB2), 0x01 },
+	{ CCI_REG8(0x6EB3), 0x00 },
+	{ IMX214_REG_ATR_FAST_MOVE, 2 },
 
 	/* imagequality */
 	/* HDR setting */
-	{0x3001, 0x07},
-	{0x6D12, 0x3F},
-	{0x6D13, 0xFF},
-	{0x9344, 0x03},
-	{0x9706, 0x10},
-	{0x9707, 0x03},
-	{0x9708, 0x03},
-	{0x9E04, 0x01},
-	{0x9E05, 0x00},
-	{0x9E0C, 0x01},
-	{0x9E0D, 0x02},
-	{0x9E24, 0x00},
-	{0x9E25, 0x8C},
-	{0x9E26, 0x00},
-	{0x9E27, 0x94},
-	{0x9E28, 0x00},
-	{0x9E29, 0x96},
+	{ IMX214_REG_RMSC_NR_MODE, 0x07 },
+	{ IMX214_REG_RG_STATS_LMT, IMX214_RG_STATS_LMT_14_BIT },
+	{ CCI_REG8(0x9344), 0x03 },
+	{ CCI_REG8(0x9706), 0x10 },
+	{ CCI_REG8(0x9707), 0x03 },
+	{ CCI_REG8(0x9708), 0x03 },
+	{ CCI_REG8(0x9E04), 0x01 },
+	{ CCI_REG8(0x9E05), 0x00 },
+	{ CCI_REG8(0x9E0C), 0x01 },
+	{ CCI_REG8(0x9E0D), 0x02 },
+	{ CCI_REG8(0x9E24), 0x00 },
+	{ CCI_REG8(0x9E25), 0x8C },
+	{ CCI_REG8(0x9E26), 0x00 },
+	{ CCI_REG8(0x9E27), 0x94 },
+	{ CCI_REG8(0x9E28), 0x00 },
+	{ CCI_REG8(0x9E29), 0x96 },
 
 	/* CNR parameter setting */
-	{0x69DB, 0x01},
+	{ CCI_REG8(0x69DB), 0x01 },
 
 	/* Moire reduction */
-	{0x6957, 0x01},
+	{ CCI_REG8(0x6957), 0x01 },
 
 	/* image enhancement */
-	{0x6987, 0x17},
-	{0x698A, 0x03},
-	{0x698B, 0x03},
+	{ CCI_REG8(0x6987), 0x17 },
+	{ CCI_REG8(0x698A), 0x03 },
+	{ CCI_REG8(0x698B), 0x03 },
 
 	/* white balanace */
-	{0x0B8E, 0x01},
-	{0x0B8F, 0x00},
-	{0x0B90, 0x01},
-	{0x0B91, 0x00},
-	{0x0B92, 0x01},
-	{0x0B93, 0x00},
-	{0x0B94, 0x01},
-	{0x0B95, 0x00},
+	{ IMX214_REG_ABS_GAIN_GREENR, 0x0100 },
+	{ IMX214_REG_ABS_GAIN_RED, 0x0100 },
+	{ IMX214_REG_ABS_GAIN_BLUE, 0x0100 },
+	{ IMX214_REG_ABS_GAIN_GREENB, 0x0100 },
 
 	/* ATR setting */
-	{0x6E50, 0x00},
-	{0x6E51, 0x32},
-	{0x9340, 0x00},
-	{0x9341, 0x3C},
-	{0x9342, 0x03},
-	{0x9343, 0xFF},
-	{IMX214_TABLE_END, 0x00}
+	{ CCI_REG8(0x6E50), 0x00 },
+	{ CCI_REG8(0x6E51), 0x32 },
+	{ CCI_REG8(0x9340), 0x00 },
+	{ CCI_REG8(0x9341), 0x3C },
+	{ CCI_REG8(0x9342), 0x03 },
+	{ CCI_REG8(0x9343), 0xFF },
 };
 
 /*
@@ -427,16 +464,19 @@ static const struct reg_8 mode_table_common[] = {
 static const struct imx214_mode {
 	u32 width;
 	u32 height;
-	const struct reg_8 *reg_table;
+	unsigned int num_of_regs;
+	const struct cci_reg_sequence *reg_table;
 } imx214_modes[] = {
 	{
 		.width = 4096,
 		.height = 2304,
+		.num_of_regs = ARRAY_SIZE(mode_4096x2304),
 		.reg_table = mode_4096x2304,
 	},
 	{
 		.width = 1920,
 		.height = 1080,
+		.num_of_regs = ARRAY_SIZE(mode_1920x1080),
 		.reg_table = mode_1920x1080,
 	},
 };
@@ -490,6 +530,22 @@ static int __maybe_unused imx214_power_off(struct device *dev)
 	return 0;
 }
 
+static void imx214_update_pad_format(struct imx214 *imx214,
+				     const struct imx214_mode *mode,
+				     struct v4l2_mbus_framefmt *fmt, u32 code)
+{
+	fmt->code = IMX214_MBUS_CODE;
+	fmt->width = mode->width;
+	fmt->height = mode->height;
+	fmt->field = V4L2_FIELD_NONE;
+	fmt->colorspace = V4L2_COLORSPACE_SRGB;
+	fmt->ycbcr_enc = V4L2_MAP_YCBCR_ENC_DEFAULT(fmt->colorspace);
+	fmt->quantization = V4L2_MAP_QUANTIZATION_DEFAULT(true,
+							  fmt->colorspace,
+							  fmt->ycbcr_enc);
+	fmt->xfer_func = V4L2_MAP_XFER_FUNC_DEFAULT(fmt->colorspace);
+}
+
 static int imx214_enum_mbus_code(struct v4l2_subdev *sd,
 				 struct v4l2_subdev_state *sd_state,
 				 struct v4l2_subdev_mbus_code_enum *code)
@@ -549,52 +605,6 @@ static const struct v4l2_subdev_core_ops imx214_core_ops = {
 #endif
 };
 
-static struct v4l2_mbus_framefmt *
-__imx214_get_pad_format(struct imx214 *imx214,
-			struct v4l2_subdev_state *sd_state,
-			unsigned int pad,
-			enum v4l2_subdev_format_whence which)
-{
-	switch (which) {
-	case V4L2_SUBDEV_FORMAT_TRY:
-		return v4l2_subdev_state_get_format(sd_state, pad);
-	case V4L2_SUBDEV_FORMAT_ACTIVE:
-		return &imx214->fmt;
-	default:
-		return NULL;
-	}
-}
-
-static int imx214_get_format(struct v4l2_subdev *sd,
-			     struct v4l2_subdev_state *sd_state,
-			     struct v4l2_subdev_format *format)
-{
-	struct imx214 *imx214 = to_imx214(sd);
-
-	mutex_lock(&imx214->mutex);
-	format->format = *__imx214_get_pad_format(imx214, sd_state,
-						  format->pad,
-						  format->which);
-	mutex_unlock(&imx214->mutex);
-
-	return 0;
-}
-
-static struct v4l2_rect *
-__imx214_get_pad_crop(struct imx214 *imx214,
-		      struct v4l2_subdev_state *sd_state,
-		      unsigned int pad, enum v4l2_subdev_format_whence which)
-{
-	switch (which) {
-	case V4L2_SUBDEV_FORMAT_TRY:
-		return v4l2_subdev_state_get_crop(sd_state, pad);
-	case V4L2_SUBDEV_FORMAT_ACTIVE:
-		return &imx214->crop;
-	default:
-		return NULL;
-	}
-}
-
 static int imx214_set_format(struct v4l2_subdev *sd,
 			     struct v4l2_subdev_state *sd_state,
 			     struct v4l2_subdev_format *format)
@@ -604,34 +614,20 @@ static int imx214_set_format(struct v4l2_subdev *sd,
 	struct v4l2_rect *__crop;
 	const struct imx214_mode *mode;
 
-	mutex_lock(&imx214->mutex);
-
-	__crop = __imx214_get_pad_crop(imx214, sd_state, format->pad,
-				       format->which);
-
 	mode = v4l2_find_nearest_size(imx214_modes,
 				      ARRAY_SIZE(imx214_modes), width, height,
 				      format->format.width,
 				      format->format.height);
 
-	__crop->width = mode->width;
-	__crop->height = mode->height;
-
-	__format = __imx214_get_pad_format(imx214, sd_state, format->pad,
-					   format->which);
-	__format->width = __crop->width;
-	__format->height = __crop->height;
-	__format->code = IMX214_MBUS_CODE;
-	__format->field = V4L2_FIELD_NONE;
-	__format->colorspace = V4L2_COLORSPACE_SRGB;
-	__format->ycbcr_enc = V4L2_MAP_YCBCR_ENC_DEFAULT(__format->colorspace);
-	__format->quantization = V4L2_MAP_QUANTIZATION_DEFAULT(true,
-				__format->colorspace, __format->ycbcr_enc);
-	__format->xfer_func = V4L2_MAP_XFER_FUNC_DEFAULT(__format->colorspace);
+	imx214_update_pad_format(imx214, mode, &format->format,
+				 format->format.code);
+	__format = v4l2_subdev_state_get_format(sd_state, 0);
 
-	format->format = *__format;
+	*__format = format->format;
 
-	mutex_unlock(&imx214->mutex);
+	__crop = v4l2_subdev_state_get_crop(sd_state, 0);
+	__crop->width = mode->width;
+	__crop->height = mode->height;
 
 	return 0;
 }
@@ -640,14 +636,9 @@ static int imx214_get_selection(struct v4l2_subdev *sd,
 				struct v4l2_subdev_state *sd_state,
 				struct v4l2_subdev_selection *sel)
 {
-	struct imx214 *imx214 = to_imx214(sd);
-
 	switch (sel->target) {
 	case V4L2_SEL_TGT_CROP:
-		mutex_lock(&imx214->mutex);
-		sel->r = *__imx214_get_pad_crop(imx214, sd_state, sel->pad,
-						sel->which);
-		mutex_unlock(&imx214->mutex);
+		sel->r = *v4l2_subdev_state_get_crop(sd_state, 0);
 		return 0;
 
 	case V4L2_SEL_TGT_NATIVE_SIZE:
@@ -687,7 +678,6 @@ static int imx214_set_ctrl(struct v4l2_ctrl *ctrl)
 {
 	struct imx214 *imx214 = container_of(ctrl->handler,
 					     struct imx214, ctrls);
-	u8 vals[2];
 	int ret;
 
 	/*
@@ -699,12 +689,7 @@ static int imx214_set_ctrl(struct v4l2_ctrl *ctrl)
 
 	switch (ctrl->id) {
 	case V4L2_CID_EXPOSURE:
-		vals[1] = ctrl->val;
-		vals[0] = ctrl->val >> 8;
-		ret = regmap_bulk_write(imx214->regmap, IMX214_REG_EXPOSURE, vals, 2);
-		if (ret < 0)
-			dev_err(imx214->dev, "Error %d\n", ret);
-		ret = 0;
+		cci_write(imx214->regmap, IMX214_REG_EXPOSURE, ctrl->val, &ret);
 		break;
 
 	default:
@@ -790,76 +775,52 @@ static int imx214_ctrls_init(struct imx214 *imx214)
 	return 0;
 };
 
-#define MAX_CMD 4
-static int imx214_write_table(struct imx214 *imx214,
-			      const struct reg_8 table[])
-{
-	u8 vals[MAX_CMD];
-	int i;
-	int ret;
-
-	for (; table->addr != IMX214_TABLE_END ; table++) {
-		if (table->addr == IMX214_TABLE_WAIT_MS) {
-			usleep_range(table->val * 1000,
-				     table->val * 1000 + 500);
-			continue;
-		}
-
-		for (i = 0; i < MAX_CMD; i++) {
-			if (table[i].addr != (table[0].addr + i))
-				break;
-			vals[i] = table[i].val;
-		}
-
-		ret = regmap_bulk_write(imx214->regmap, table->addr, vals, i);
-
-		if (ret) {
-			dev_err(imx214->dev, "write_table error: %d\n", ret);
-			return ret;
-		}
-
-		table += i - 1;
-	}
-
-	return 0;
-}
-
 static int imx214_start_streaming(struct imx214 *imx214)
 {
+	const struct v4l2_mbus_framefmt *fmt;
+	struct v4l2_subdev_state *state;
 	const struct imx214_mode *mode;
 	int ret;
 
-	mutex_lock(&imx214->mutex);
-	ret = imx214_write_table(imx214, mode_table_common);
+	ret = cci_multi_reg_write(imx214->regmap, mode_table_common,
+				  ARRAY_SIZE(mode_table_common), NULL);
 	if (ret < 0) {
 		dev_err(imx214->dev, "could not sent common table %d\n", ret);
-		goto error;
+		return ret;
 	}
 
-	mode = v4l2_find_nearest_size(imx214_modes,
-				ARRAY_SIZE(imx214_modes), width, height,
-				imx214->fmt.width, imx214->fmt.height);
-	ret = imx214_write_table(imx214, mode->reg_table);
+	ret = cci_write(imx214->regmap, IMX214_REG_CSI_LANE_MODE,
+			IMX214_CSI_4_LANE_MODE, NULL);
+	if (ret) {
+		dev_err(imx214->dev, "failed to configure lanes\n");
+		return ret;
+	}
+
+	state = v4l2_subdev_get_locked_active_state(&imx214->sd);
+	fmt = v4l2_subdev_state_get_format(state, 0);
+	mode = v4l2_find_nearest_size(imx214_modes, ARRAY_SIZE(imx214_modes),
+				      width, height, fmt->width, fmt->height);
+	ret = cci_multi_reg_write(imx214->regmap, mode->reg_table,
+				  mode->num_of_regs, NULL);
 	if (ret < 0) {
 		dev_err(imx214->dev, "could not sent mode table %d\n", ret);
-		goto error;
+		return ret;
 	}
+
+	usleep_range(10000, 10500);
+
+	cci_write(imx214->regmap, IMX214_REG_TEMP_SENSOR_CONTROL, 0x01, NULL);
+
 	ret = __v4l2_ctrl_handler_setup(&imx214->ctrls);
 	if (ret < 0) {
 		dev_err(imx214->dev, "could not sync v4l2 controls\n");
-		goto error;
+		return ret;
 	}
-	ret = regmap_write(imx214->regmap, IMX214_REG_MODE_SELECT, IMX214_MODE_STREAMING);
-	if (ret < 0) {
+	ret = cci_write(imx214->regmap, IMX214_REG_MODE_SELECT,
+			IMX214_MODE_STREAMING, NULL);
+	if (ret < 0)
 		dev_err(imx214->dev, "could not sent start table %d\n", ret);
-		goto error;
-	}
-
-	mutex_unlock(&imx214->mutex);
-	return 0;
 
-error:
-	mutex_unlock(&imx214->mutex);
 	return ret;
 }
 
@@ -867,7 +828,8 @@ static int imx214_stop_streaming(struct imx214 *imx214)
 {
 	int ret;
 
-	ret = regmap_write(imx214->regmap, IMX214_REG_MODE_SELECT, IMX214_MODE_STANDBY);
+	ret = cci_write(imx214->regmap, IMX214_REG_MODE_SELECT,
+			IMX214_MODE_STANDBY, NULL);
 	if (ret < 0)
 		dev_err(imx214->dev, "could not sent stop table %d\n",	ret);
 
@@ -877,14 +839,17 @@ static int imx214_stop_streaming(struct imx214 *imx214)
 static int imx214_s_stream(struct v4l2_subdev *subdev, int enable)
 {
 	struct imx214 *imx214 = to_imx214(subdev);
-	int ret;
+	struct v4l2_subdev_state *state;
+	int ret = 0;
 
 	if (enable) {
 		ret = pm_runtime_resume_and_get(imx214->dev);
 		if (ret < 0)
 			return ret;
 
+		state = v4l2_subdev_lock_and_get_active_state(subdev);
 		ret = imx214_start_streaming(imx214);
+		v4l2_subdev_unlock_state(state);
 		if (ret < 0)
 			goto err_rpm_put;
 	} else {
@@ -948,7 +913,7 @@ static const struct v4l2_subdev_pad_ops imx214_subdev_pad_ops = {
 	.enum_mbus_code = imx214_enum_mbus_code,
 	.enum_frame_size = imx214_enum_frame_size,
 	.enum_frame_interval = imx214_enum_frame_interval,
-	.get_fmt = imx214_get_format,
+	.get_fmt = v4l2_subdev_get_fmt,
 	.set_fmt = imx214_set_format,
 	.get_selection = imx214_get_selection,
 	.get_frame_interval = imx214_get_frame_interval,
@@ -965,12 +930,6 @@ static const struct v4l2_subdev_internal_ops imx214_internal_ops = {
 	.init_state = imx214_entity_init_state,
 };
 
-static const struct regmap_config sensor_regmap_config = {
-	.reg_bits = 16,
-	.val_bits = 8,
-	.cache_type = REGCACHE_MAPLE,
-};
-
 static int imx214_get_regulators(struct device *dev, struct imx214 *imx214)
 {
 	unsigned int i;
@@ -992,28 +951,42 @@ static int imx214_parse_fwnode(struct device *dev)
 	int ret;
 
 	endpoint = fwnode_graph_get_next_endpoint(dev_fwnode(dev), NULL);
-	if (!endpoint) {
-		dev_err(dev, "endpoint node not found\n");
-		return -EINVAL;
-	}
+	if (!endpoint)
+		return dev_err_probe(dev, -EINVAL, "endpoint node not found\n");
 
 	ret = v4l2_fwnode_endpoint_alloc_parse(endpoint, &bus_cfg);
 	if (ret) {
-		dev_err(dev, "parsing endpoint node failed\n");
+		dev_err_probe(dev, ret, "parsing endpoint node failed\n");
 		goto done;
 	}
 
-	for (i = 0; i < bus_cfg.nr_of_link_frequencies; i++)
+	/* Check the number of MIPI CSI2 data lanes */
+	if (bus_cfg.bus.mipi_csi2.num_data_lanes != 4) {
+		ret = dev_err_probe(dev, -EINVAL,
+				    "only 4 data lanes are currently supported\n");
+		goto done;
+	}
+
+	if (bus_cfg.nr_of_link_frequencies != 1)
+		dev_warn(dev, "Only one link-frequency supported, please review your DT. Continuing anyway\n");
+
+	for (i = 0; i < bus_cfg.nr_of_link_frequencies; i++) {
 		if (bus_cfg.link_frequencies[i] == IMX214_DEFAULT_LINK_FREQ)
 			break;
-
-	if (i == bus_cfg.nr_of_link_frequencies) {
-		dev_err(dev, "link-frequencies %d not supported, Please review your DT\n",
-			IMX214_DEFAULT_LINK_FREQ);
-		ret = -EINVAL;
-		goto done;
+		if (bus_cfg.link_frequencies[i] ==
+		    IMX214_DEFAULT_LINK_FREQ_LEGACY) {
+			dev_warn(dev,
+				 "link-frequencies %d not supported, please review your DT. Continuing anyway\n",
+				 IMX214_DEFAULT_LINK_FREQ);
+			break;
+		}
 	}
 
+	if (i == bus_cfg.nr_of_link_frequencies)
+		ret = dev_err_probe(dev, -EINVAL,
+				    "link-frequencies %d not supported, please review your DT\n",
+				    IMX214_DEFAULT_LINK_FREQ);
+
 done:
 	v4l2_fwnode_endpoint_free(&bus_cfg);
 	fwnode_handle_put(endpoint);
@@ -1037,34 +1010,28 @@ static int imx214_probe(struct i2c_client *client)
 	imx214->dev = dev;
 
 	imx214->xclk = devm_clk_get(dev, NULL);
-	if (IS_ERR(imx214->xclk)) {
-		dev_err(dev, "could not get xclk");
-		return PTR_ERR(imx214->xclk);
-	}
+	if (IS_ERR(imx214->xclk))
+		return dev_err_probe(dev, PTR_ERR(imx214->xclk),
+				     "failed to get xclk\n");
 
 	ret = clk_set_rate(imx214->xclk, IMX214_DEFAULT_CLK_FREQ);
-	if (ret) {
-		dev_err(dev, "could not set xclk frequency\n");
-		return ret;
-	}
+	if (ret)
+		return dev_err_probe(dev, ret,
+				     "failed to set xclk frequency\n");
 
 	ret = imx214_get_regulators(dev, imx214);
-	if (ret < 0) {
-		dev_err(dev, "cannot get regulators\n");
-		return ret;
-	}
+	if (ret < 0)
+		return dev_err_probe(dev, ret, "failed to get regulators\n");
 
 	imx214->enable_gpio = devm_gpiod_get(dev, "enable", GPIOD_OUT_LOW);
-	if (IS_ERR(imx214->enable_gpio)) {
-		dev_err(dev, "cannot get enable gpio\n");
-		return PTR_ERR(imx214->enable_gpio);
-	}
+	if (IS_ERR(imx214->enable_gpio))
+		return dev_err_probe(dev, PTR_ERR(imx214->enable_gpio),
+				     "failed to get enable gpio\n");
 
-	imx214->regmap = devm_regmap_init_i2c(client, &sensor_regmap_config);
-	if (IS_ERR(imx214->regmap)) {
-		dev_err(dev, "regmap init failed\n");
-		return PTR_ERR(imx214->regmap);
-	}
+	imx214->regmap = devm_cci_regmap_init_i2c(client, 16);
+	if (IS_ERR(imx214->regmap))
+		return dev_err_probe(dev, PTR_ERR(imx214->regmap),
+				     "failed to initialize CCI\n");
 
 	v4l2_i2c_subdev_init(&imx214->sd, client, &imx214_subdev_ops);
 	imx214->sd.internal_ops = &imx214_internal_ops;
@@ -1075,17 +1042,10 @@ static int imx214_probe(struct i2c_client *client)
 	 */
 	imx214_power_on(imx214->dev);
 
-	pm_runtime_set_active(imx214->dev);
-	pm_runtime_enable(imx214->dev);
-	pm_runtime_idle(imx214->dev);
-
 	ret = imx214_ctrls_init(imx214);
 	if (ret < 0)
 		goto error_power_off;
 
-	mutex_init(&imx214->mutex);
-	imx214->ctrls.lock = &imx214->mutex;
-
 	imx214->sd.flags |= V4L2_SUBDEV_FL_HAS_DEVNODE;
 	imx214->pad.flags = MEDIA_PAD_FL_SOURCE;
 	imx214->sd.dev = &client->dev;
@@ -1093,28 +1053,44 @@ static int imx214_probe(struct i2c_client *client)
 
 	ret = media_entity_pads_init(&imx214->sd.entity, 1, &imx214->pad);
 	if (ret < 0) {
-		dev_err(dev, "could not register media entity\n");
+		dev_err_probe(dev, ret, "failed to init entity pads\n");
 		goto free_ctrl;
 	}
 
-	imx214_entity_init_state(&imx214->sd, NULL);
+	imx214->sd.state_lock = imx214->ctrls.lock;
+	ret = v4l2_subdev_init_finalize(&imx214->sd);
+	if (ret < 0) {
+		dev_err_probe(dev, ret, "subdev init error\n");
+		goto free_entity;
+	}
+
+	pm_runtime_set_active(imx214->dev);
+	pm_runtime_enable(imx214->dev);
 
 	ret = v4l2_async_register_subdev_sensor(&imx214->sd);
 	if (ret < 0) {
-		dev_err(dev, "could not register v4l2 device\n");
-		goto free_entity;
+		dev_err_probe(dev, ret,
+			      "failed to register sensor sub-device\n");
+		goto error_subdev_cleanup;
 	}
 
+	pm_runtime_idle(imx214->dev);
+
 	return 0;
 
+error_subdev_cleanup:
+	pm_runtime_disable(imx214->dev);
+	pm_runtime_set_suspended(&client->dev);
+	v4l2_subdev_cleanup(&imx214->sd);
+
 free_entity:
 	media_entity_cleanup(&imx214->sd.entity);
+
 free_ctrl:
-	mutex_destroy(&imx214->mutex);
 	v4l2_ctrl_handler_free(&imx214->ctrls);
+
 error_power_off:
-	pm_runtime_disable(imx214->dev);
-	regulator_bulk_disable(IMX214_NUM_SUPPLIES, imx214->supplies);
+	imx214_power_off(imx214->dev);
 
 	return ret;
 }
@@ -1125,13 +1101,14 @@ static void imx214_remove(struct i2c_client *client)
 	struct imx214 *imx214 = to_imx214(sd);
 
 	v4l2_async_unregister_subdev(&imx214->sd);
+	v4l2_subdev_cleanup(sd);
 	media_entity_cleanup(&imx214->sd.entity);
 	v4l2_ctrl_handler_free(&imx214->ctrls);
-
 	pm_runtime_disable(&client->dev);
-	pm_runtime_set_suspended(&client->dev);
-
-	mutex_destroy(&imx214->mutex);
+	if (!pm_runtime_status_suspended(&client->dev)) {
+		imx214_power_off(imx214->dev);
+		pm_runtime_set_suspended(&client->dev);
+	}
 }
 
 static const struct of_device_id imx214_of_match[] = {
diff --git a/drivers/media/i2c/imx219.c b/drivers/media/i2c/imx219.c
index e78a80b2bb2e..eaa1496c71bb 100644
--- a/drivers/media/i2c/imx219.c
+++ b/drivers/media/i2c/imx219.c
@@ -74,7 +74,7 @@
 #define IMX219_REG_VTS			CCI_REG16(0x0160)
 #define IMX219_VTS_MAX			0xffff
 
-#define IMX219_VBLANK_MIN		4
+#define IMX219_VBLANK_MIN		32
 
 /* HBLANK control - read only */
 #define IMX219_PPL_DEFAULT		3448
@@ -134,10 +134,11 @@
 
 /* Pixel rate is fixed for all the modes */
 #define IMX219_PIXEL_RATE		182400000
-#define IMX219_PIXEL_RATE_4LANE		280800000
+#define IMX219_PIXEL_RATE_4LANE		281600000
 
 #define IMX219_DEFAULT_LINK_FREQ	456000000
-#define IMX219_DEFAULT_LINK_FREQ_4LANE	363000000
+#define IMX219_DEFAULT_LINK_FREQ_4LANE_UNSUPPORTED	363000000
+#define IMX219_DEFAULT_LINK_FREQ_4LANE	364000000
 
 /* IMX219 native and active pixel array size. */
 #define IMX219_NATIVE_WIDTH		3296U
@@ -169,15 +170,6 @@ static const struct cci_reg_sequence imx219_common_regs[] = {
 	{ CCI_REG8(0x30eb), 0x05 },
 	{ CCI_REG8(0x30eb), 0x09 },
 
-	/* PLL Clock Table */
-	{ IMX219_REG_VTPXCK_DIV, 5 },
-	{ IMX219_REG_VTSYCK_DIV, 1 },
-	{ IMX219_REG_PREPLLCK_VT_DIV, 3 },	/* 0x03 = AUTO set */
-	{ IMX219_REG_PREPLLCK_OP_DIV, 3 },	/* 0x03 = AUTO set */
-	{ IMX219_REG_PLL_VT_MPY, 57 },
-	{ IMX219_REG_OPSYCK_DIV, 1 },
-	{ IMX219_REG_PLL_OP_MPY, 114 },
-
 	/* Undocumented registers */
 	{ CCI_REG8(0x455e), 0x00 },
 	{ CCI_REG8(0x471e), 0x4b },
@@ -202,12 +194,45 @@ static const struct cci_reg_sequence imx219_common_regs[] = {
 	{ IMX219_REG_EXCK_FREQ, IMX219_EXCK_FREQ(IMX219_XCLK_FREQ / 1000000) },
 };
 
+static const struct cci_reg_sequence imx219_2lane_regs[] = {
+	/* PLL Clock Table */
+	{ IMX219_REG_VTPXCK_DIV, 5 },
+	{ IMX219_REG_VTSYCK_DIV, 1 },
+	{ IMX219_REG_PREPLLCK_VT_DIV, 3 },	/* 0x03 = AUTO set */
+	{ IMX219_REG_PREPLLCK_OP_DIV, 3 },	/* 0x03 = AUTO set */
+	{ IMX219_REG_PLL_VT_MPY, 57 },
+	{ IMX219_REG_OPSYCK_DIV, 1 },
+	{ IMX219_REG_PLL_OP_MPY, 114 },
+
+	/* 2-Lane CSI Mode */
+	{ IMX219_REG_CSI_LANE_MODE, IMX219_CSI_2_LANE_MODE },
+};
+
+static const struct cci_reg_sequence imx219_4lane_regs[] = {
+	/* PLL Clock Table */
+	{ IMX219_REG_VTPXCK_DIV, 5 },
+	{ IMX219_REG_VTSYCK_DIV, 1 },
+	{ IMX219_REG_PREPLLCK_VT_DIV, 3 },	/* 0x03 = AUTO set */
+	{ IMX219_REG_PREPLLCK_OP_DIV, 3 },	/* 0x03 = AUTO set */
+	{ IMX219_REG_PLL_VT_MPY, 88 },
+	{ IMX219_REG_OPSYCK_DIV, 1 },
+	{ IMX219_REG_PLL_OP_MPY, 91 },
+
+	/* 4-Lane CSI Mode */
+	{ IMX219_REG_CSI_LANE_MODE, IMX219_CSI_4_LANE_MODE },
+};
+
 static const s64 imx219_link_freq_menu[] = {
 	IMX219_DEFAULT_LINK_FREQ,
 };
 
 static const s64 imx219_link_freq_4lane_menu[] = {
 	IMX219_DEFAULT_LINK_FREQ_4LANE,
+	/*
+	 * This will never be advertised to userspace, but will be used for
+	 * v4l2_link_freq_to_bitmap
+	 */
+	IMX219_DEFAULT_LINK_FREQ_4LANE_UNSUPPORTED,
 };
 
 static const char * const imx219_test_pattern_menu[] = {
@@ -663,9 +688,11 @@ static int imx219_set_framefmt(struct imx219 *imx219,
 
 static int imx219_configure_lanes(struct imx219 *imx219)
 {
-	return cci_write(imx219->regmap, IMX219_REG_CSI_LANE_MODE,
-			 imx219->lanes == 2 ? IMX219_CSI_2_LANE_MODE :
-			 IMX219_CSI_4_LANE_MODE, NULL);
+	/* Write the appropriate PLL settings for the number of MIPI lanes */
+	return cci_multi_reg_write(imx219->regmap,
+				  imx219->lanes == 2 ? imx219_2lane_regs : imx219_4lane_regs,
+				  imx219->lanes == 2 ? ARRAY_SIZE(imx219_2lane_regs) :
+				  ARRAY_SIZE(imx219_4lane_regs), NULL);
 };
 
 static int imx219_start_streaming(struct imx219 *imx219,
@@ -1042,6 +1069,7 @@ static int imx219_check_hwcfg(struct device *dev, struct imx219 *imx219)
 	struct v4l2_fwnode_endpoint ep_cfg = {
 		.bus_type = V4L2_MBUS_CSI2_DPHY
 	};
+	unsigned long link_freq_bitmap;
 	int ret = -EINVAL;
 
 	endpoint = fwnode_graph_get_next_endpoint(dev_fwnode(dev), NULL);
@@ -1063,23 +1091,40 @@ static int imx219_check_hwcfg(struct device *dev, struct imx219 *imx219)
 	imx219->lanes = ep_cfg.bus.mipi_csi2.num_data_lanes;
 
 	/* Check the link frequency set in device tree */
-	if (!ep_cfg.nr_of_link_frequencies) {
-		dev_err_probe(dev, -EINVAL,
-			      "link-frequency property not found in DT\n");
-		goto error_out;
+	switch (imx219->lanes) {
+	case 2:
+		ret = v4l2_link_freq_to_bitmap(dev,
+					       ep_cfg.link_frequencies,
+					       ep_cfg.nr_of_link_frequencies,
+					       imx219_link_freq_menu,
+					       ARRAY_SIZE(imx219_link_freq_menu),
+					       &link_freq_bitmap);
+		break;
+	case 4:
+		ret = v4l2_link_freq_to_bitmap(dev,
+					       ep_cfg.link_frequencies,
+					       ep_cfg.nr_of_link_frequencies,
+					       imx219_link_freq_4lane_menu,
+					       ARRAY_SIZE(imx219_link_freq_4lane_menu),
+					       &link_freq_bitmap);
+
+		if (!ret && (link_freq_bitmap & BIT(1))) {
+			dev_warn(dev, "Link frequency of %d not supported, but has been incorrectly advertised previously\n",
+				 IMX219_DEFAULT_LINK_FREQ_4LANE_UNSUPPORTED);
+			dev_warn(dev, "Using link frequency of %d\n",
+				 IMX219_DEFAULT_LINK_FREQ_4LANE);
+			link_freq_bitmap |= BIT(0);
+		}
+		break;
 	}
 
-	if (ep_cfg.nr_of_link_frequencies != 1 ||
-	   (ep_cfg.link_frequencies[0] != ((imx219->lanes == 2) ?
-	    IMX219_DEFAULT_LINK_FREQ : IMX219_DEFAULT_LINK_FREQ_4LANE))) {
+	if (ret || !(link_freq_bitmap & BIT(0))) {
+		ret = -EINVAL;
 		dev_err_probe(dev, -EINVAL,
 			      "Link frequency not supported: %lld\n",
 			      ep_cfg.link_frequencies[0]);
-		goto error_out;
 	}
 
-	ret = 0;
-
 error_out:
 	v4l2_fwnode_endpoint_free(&ep_cfg);
 	fwnode_handle_put(endpoint);
@@ -1186,6 +1231,9 @@ static int imx219_probe(struct i2c_client *client)
 		goto error_media_entity;
 	}
 
+	pm_runtime_set_active(dev);
+	pm_runtime_enable(dev);
+
 	ret = v4l2_async_register_subdev_sensor(&imx219->sd);
 	if (ret < 0) {
 		dev_err_probe(dev, ret,
@@ -1193,15 +1241,14 @@ static int imx219_probe(struct i2c_client *client)
 		goto error_subdev_cleanup;
 	}
 
-	/* Enable runtime PM and turn off the device */
-	pm_runtime_set_active(dev);
-	pm_runtime_enable(dev);
 	pm_runtime_idle(dev);
 
 	return 0;
 
 error_subdev_cleanup:
 	v4l2_subdev_cleanup(&imx219->sd);
+	pm_runtime_disable(dev);
+	pm_runtime_set_suspended(dev);
 
 error_media_entity:
 	media_entity_cleanup(&imx219->sd.entity);
@@ -1226,9 +1273,10 @@ static void imx219_remove(struct i2c_client *client)
 	imx219_free_controls(imx219);
 
 	pm_runtime_disable(&client->dev);
-	if (!pm_runtime_status_suspended(&client->dev))
+	if (!pm_runtime_status_suspended(&client->dev)) {
 		imx219_power_off(&client->dev);
-	pm_runtime_set_suspended(&client->dev);
+		pm_runtime_set_suspended(&client->dev);
+	}
 }
 
 static const struct of_device_id imx219_dt_ids[] = {
diff --git a/drivers/media/i2c/imx290.c b/drivers/media/i2c/imx290.c
index 458905dfb3e1..a87a265cd839 100644
--- a/drivers/media/i2c/imx290.c
+++ b/drivers/media/i2c/imx290.c
@@ -269,7 +269,6 @@ static const struct cci_reg_sequence imx290_global_init_settings[] = {
 	{ IMX290_WINWV, 1097 },
 	{ IMX290_XSOUTSEL, IMX290_XSOUTSEL_XVSOUTSEL_VSYNC |
 			   IMX290_XSOUTSEL_XHSOUTSEL_HSYNC },
-	{ CCI_REG8(0x3011), 0x02 },
 	{ CCI_REG8(0x3012), 0x64 },
 	{ CCI_REG8(0x3013), 0x00 },
 };
@@ -277,6 +276,7 @@ static const struct cci_reg_sequence imx290_global_init_settings[] = {
 static const struct cci_reg_sequence imx290_global_init_settings_290[] = {
 	{ CCI_REG8(0x300f), 0x00 },
 	{ CCI_REG8(0x3010), 0x21 },
+	{ CCI_REG8(0x3011), 0x00 },
 	{ CCI_REG8(0x3016), 0x09 },
 	{ CCI_REG8(0x3070), 0x02 },
 	{ CCI_REG8(0x3071), 0x11 },
@@ -330,6 +330,7 @@ static const struct cci_reg_sequence xclk_regs[][IMX290_NUM_CLK_REGS] = {
 };
 
 static const struct cci_reg_sequence imx290_global_init_settings_327[] = {
+	{ CCI_REG8(0x3011), 0x02 },
 	{ CCI_REG8(0x309e), 0x4A },
 	{ CCI_REG8(0x309f), 0x4A },
 	{ CCI_REG8(0x313b), 0x61 },
diff --git a/drivers/media/i2c/imx296.c b/drivers/media/i2c/imx296.c
index 83149fa729c4..f3bec16b527c 100644
--- a/drivers/media/i2c/imx296.c
+++ b/drivers/media/i2c/imx296.c
@@ -954,6 +954,8 @@ static int imx296_identify_model(struct imx296 *sensor)
 		return ret;
 	}
 
+	usleep_range(2000, 5000);
+
 	ret = imx296_read(sensor, IMX296_SENSOR_INFO);
 	if (ret < 0) {
 		dev_err(sensor->dev, "failed to read sensor information (%d)\n",
diff --git a/drivers/media/i2c/imx319.c b/drivers/media/i2c/imx319.c
index dd1b4ff983dc..701840f4a5cc 100644
--- a/drivers/media/i2c/imx319.c
+++ b/drivers/media/i2c/imx319.c
@@ -2442,17 +2442,19 @@ static int imx319_probe(struct i2c_client *client)
 	if (full_power)
 		pm_runtime_set_active(&client->dev);
 	pm_runtime_enable(&client->dev);
-	pm_runtime_idle(&client->dev);
 
 	ret = v4l2_async_register_subdev_sensor(&imx319->sd);
 	if (ret < 0)
 		goto error_media_entity_pm;
 
+	pm_runtime_idle(&client->dev);
+
 	return 0;
 
 error_media_entity_pm:
 	pm_runtime_disable(&client->dev);
-	pm_runtime_set_suspended(&client->dev);
+	if (full_power)
+		pm_runtime_set_suspended(&client->dev);
 	media_entity_cleanup(&imx319->sd.entity);
 
 error_handler_free:
@@ -2474,7 +2476,8 @@ static void imx319_remove(struct i2c_client *client)
 	v4l2_ctrl_handler_free(sd->ctrl_handler);
 
 	pm_runtime_disable(&client->dev);
-	pm_runtime_set_suspended(&client->dev);
+	if (!pm_runtime_status_suspended(&client->dev))
+		pm_runtime_set_suspended(&client->dev);
 
 	mutex_destroy(&imx319->mutex);
 }
diff --git a/drivers/media/i2c/imx335.c b/drivers/media/i2c/imx335.c
index fcfd1d851bd4..9b4db4cd4929 100644
--- a/drivers/media/i2c/imx335.c
+++ b/drivers/media/i2c/imx335.c
@@ -31,7 +31,7 @@
 #define IMX335_REG_CPWAIT_TIME		CCI_REG8(0x300d)
 #define IMX335_REG_WINMODE		CCI_REG8(0x3018)
 #define IMX335_REG_HTRIMMING_START	CCI_REG16_LE(0x302c)
-#define IMX335_REG_HNUM			CCI_REG8(0x302e)
+#define IMX335_REG_HNUM			CCI_REG16_LE(0x302e)
 
 /* Lines per frame */
 #define IMX335_REG_VMAX			CCI_REG24_LE(0x3030)
@@ -559,12 +559,14 @@ static int imx335_set_ctrl(struct v4l2_ctrl *ctrl)
 			imx335->vblank,
 			imx335->vblank + imx335->cur_mode->height);
 
-		return __v4l2_ctrl_modify_range(imx335->exp_ctrl,
-						IMX335_EXPOSURE_MIN,
-						imx335->vblank +
-						imx335->cur_mode->height -
-						IMX335_EXPOSURE_OFFSET,
-						1, IMX335_EXPOSURE_DEFAULT);
+		ret = __v4l2_ctrl_modify_range(imx335->exp_ctrl,
+					       IMX335_EXPOSURE_MIN,
+					       imx335->vblank +
+					       imx335->cur_mode->height -
+					       IMX335_EXPOSURE_OFFSET,
+					       1, IMX335_EXPOSURE_DEFAULT);
+		if (ret)
+			return ret;
 	}
 
 	/*
@@ -575,6 +577,13 @@ static int imx335_set_ctrl(struct v4l2_ctrl *ctrl)
 		return 0;
 
 	switch (ctrl->id) {
+	case V4L2_CID_VBLANK:
+		exposure = imx335->exp_ctrl->val;
+		analog_gain = imx335->again_ctrl->val;
+
+		ret = imx335_update_exp_gain(imx335, exposure, analog_gain);
+
+		break;
 	case V4L2_CID_EXPOSURE:
 		exposure = ctrl->val;
 		analog_gain = imx335->again_ctrl->val;
@@ -651,7 +660,8 @@ static int imx335_enum_frame_size(struct v4l2_subdev *sd,
 	struct imx335 *imx335 = to_imx335(sd);
 	u32 code;
 
-	if (fsize->index > ARRAY_SIZE(imx335_mbus_codes))
+	/* Only a single supported_mode available. */
+	if (fsize->index > 0)
 		return -EINVAL;
 
 	code = imx335_get_format_code(imx335, fsize->code);
diff --git a/drivers/media/i2c/imx412.c b/drivers/media/i2c/imx412.c
index 0bfe3046fcc8..c74097a59c42 100644
--- a/drivers/media/i2c/imx412.c
+++ b/drivers/media/i2c/imx412.c
@@ -547,7 +547,7 @@ static int imx412_update_exp_gain(struct imx412 *imx412, u32 exposure, u32 gain)
 
 	lpfr = imx412->vblank + imx412->cur_mode->height;
 
-	dev_dbg(imx412->dev, "Set exp %u, analog gain %u, lpfr %u",
+	dev_dbg(imx412->dev, "Set exp %u, analog gain %u, lpfr %u\n",
 		exposure, gain, lpfr);
 
 	ret = imx412_write_reg(imx412, IMX412_REG_HOLD, 1, 1);
@@ -594,7 +594,7 @@ static int imx412_set_ctrl(struct v4l2_ctrl *ctrl)
 	case V4L2_CID_VBLANK:
 		imx412->vblank = imx412->vblank_ctrl->val;
 
-		dev_dbg(imx412->dev, "Received vblank %u, new lpfr %u",
+		dev_dbg(imx412->dev, "Received vblank %u, new lpfr %u\n",
 			imx412->vblank,
 			imx412->vblank + imx412->cur_mode->height);
 
@@ -613,7 +613,7 @@ static int imx412_set_ctrl(struct v4l2_ctrl *ctrl)
 		exposure = ctrl->val;
 		analog_gain = imx412->again_ctrl->val;
 
-		dev_dbg(imx412->dev, "Received exp %u, analog gain %u",
+		dev_dbg(imx412->dev, "Received exp %u, analog gain %u\n",
 			exposure, analog_gain);
 
 		ret = imx412_update_exp_gain(imx412, exposure, analog_gain);
@@ -622,7 +622,7 @@ static int imx412_set_ctrl(struct v4l2_ctrl *ctrl)
 
 		break;
 	default:
-		dev_err(imx412->dev, "Invalid control %d", ctrl->id);
+		dev_err(imx412->dev, "Invalid control %d\n", ctrl->id);
 		ret = -EINVAL;
 	}
 
@@ -803,14 +803,14 @@ static int imx412_start_streaming(struct imx412 *imx412)
 	ret = imx412_write_regs(imx412, reg_list->regs,
 				reg_list->num_of_regs);
 	if (ret) {
-		dev_err(imx412->dev, "fail to write initial registers");
+		dev_err(imx412->dev, "fail to write initial registers\n");
 		return ret;
 	}
 
 	/* Setup handler will write actual exposure and gain */
 	ret =  __v4l2_ctrl_handler_setup(imx412->sd.ctrl_handler);
 	if (ret) {
-		dev_err(imx412->dev, "fail to setup handler");
+		dev_err(imx412->dev, "fail to setup handler\n");
 		return ret;
 	}
 
@@ -821,7 +821,7 @@ static int imx412_start_streaming(struct imx412 *imx412)
 	ret = imx412_write_reg(imx412, IMX412_REG_MODE_SELECT,
 			       1, IMX412_MODE_STREAMING);
 	if (ret) {
-		dev_err(imx412->dev, "fail to start streaming");
+		dev_err(imx412->dev, "fail to start streaming\n");
 		return ret;
 	}
 
@@ -895,7 +895,7 @@ static int imx412_detect(struct imx412 *imx412)
 		return ret;
 
 	if (val != IMX412_ID) {
-		dev_err(imx412->dev, "chip id mismatch: %x!=%x",
+		dev_err(imx412->dev, "chip id mismatch: %x!=%x\n",
 			IMX412_ID, val);
 		return -ENXIO;
 	}
@@ -927,7 +927,7 @@ static int imx412_parse_hw_config(struct imx412 *imx412)
 	imx412->reset_gpio = devm_gpiod_get_optional(imx412->dev, "reset",
 						     GPIOD_OUT_LOW);
 	if (IS_ERR(imx412->reset_gpio)) {
-		dev_err(imx412->dev, "failed to get reset gpio %ld",
+		dev_err(imx412->dev, "failed to get reset gpio %ld\n",
 			PTR_ERR(imx412->reset_gpio));
 		return PTR_ERR(imx412->reset_gpio);
 	}
@@ -935,13 +935,13 @@ static int imx412_parse_hw_config(struct imx412 *imx412)
 	/* Get sensor input clock */
 	imx412->inclk = devm_clk_get(imx412->dev, NULL);
 	if (IS_ERR(imx412->inclk)) {
-		dev_err(imx412->dev, "could not get inclk");
+		dev_err(imx412->dev, "could not get inclk\n");
 		return PTR_ERR(imx412->inclk);
 	}
 
 	rate = clk_get_rate(imx412->inclk);
 	if (rate != IMX412_INCLK_RATE) {
-		dev_err(imx412->dev, "inclk frequency mismatch");
+		dev_err(imx412->dev, "inclk frequency mismatch\n");
 		return -EINVAL;
 	}
 
@@ -966,14 +966,14 @@ static int imx412_parse_hw_config(struct imx412 *imx412)
 
 	if (bus_cfg.bus.mipi_csi2.num_data_lanes != IMX412_NUM_DATA_LANES) {
 		dev_err(imx412->dev,
-			"number of CSI2 data lanes %d is not supported",
+			"number of CSI2 data lanes %d is not supported\n",
 			bus_cfg.bus.mipi_csi2.num_data_lanes);
 		ret = -EINVAL;
 		goto done_endpoint_free;
 	}
 
 	if (!bus_cfg.nr_of_link_frequencies) {
-		dev_err(imx412->dev, "no link frequencies defined");
+		dev_err(imx412->dev, "no link frequencies defined\n");
 		ret = -EINVAL;
 		goto done_endpoint_free;
 	}
@@ -1034,7 +1034,7 @@ static int imx412_power_on(struct device *dev)
 
 	ret = clk_prepare_enable(imx412->inclk);
 	if (ret) {
-		dev_err(imx412->dev, "fail to enable inclk");
+		dev_err(imx412->dev, "fail to enable inclk\n");
 		goto error_reset;
 	}
 
@@ -1145,7 +1145,7 @@ static int imx412_init_controls(struct imx412 *imx412)
 		imx412->hblank_ctrl->flags |= V4L2_CTRL_FLAG_READ_ONLY;
 
 	if (ctrl_hdlr->error) {
-		dev_err(imx412->dev, "control init failed: %d",
+		dev_err(imx412->dev, "control init failed: %d\n",
 			ctrl_hdlr->error);
 		v4l2_ctrl_handler_free(ctrl_hdlr);
 		return ctrl_hdlr->error;
@@ -1183,7 +1183,7 @@ static int imx412_probe(struct i2c_client *client)
 
 	ret = imx412_parse_hw_config(imx412);
 	if (ret) {
-		dev_err(imx412->dev, "HW configuration is not supported");
+		dev_err(imx412->dev, "HW configuration is not supported\n");
 		return ret;
 	}
 
@@ -1191,14 +1191,14 @@ static int imx412_probe(struct i2c_client *client)
 
 	ret = imx412_power_on(imx412->dev);
 	if (ret) {
-		dev_err(imx412->dev, "failed to power-on the sensor");
+		dev_err(imx412->dev, "failed to power-on the sensor\n");
 		goto error_mutex_destroy;
 	}
 
 	/* Check module identity */
 	ret = imx412_detect(imx412);
 	if (ret) {
-		dev_err(imx412->dev, "failed to find sensor: %d", ret);
+		dev_err(imx412->dev, "failed to find sensor: %d\n", ret);
 		goto error_power_off;
 	}
 
@@ -1208,7 +1208,7 @@ static int imx412_probe(struct i2c_client *client)
 
 	ret = imx412_init_controls(imx412);
 	if (ret) {
-		dev_err(imx412->dev, "failed to init controls: %d", ret);
+		dev_err(imx412->dev, "failed to init controls: %d\n", ret);
 		goto error_power_off;
 	}
 
@@ -1222,14 +1222,14 @@ static int imx412_probe(struct i2c_client *client)
 	imx412->pad.flags = MEDIA_PAD_FL_SOURCE;
 	ret = media_entity_pads_init(&imx412->sd.entity, 1, &imx412->pad);
 	if (ret) {
-		dev_err(imx412->dev, "failed to init entity pads: %d", ret);
+		dev_err(imx412->dev, "failed to init entity pads: %d\n", ret);
 		goto error_handler_free;
 	}
 
 	ret = v4l2_async_register_subdev_sensor(&imx412->sd);
 	if (ret < 0) {
 		dev_err(imx412->dev,
-			"failed to register async subdev: %d", ret);
+			"failed to register async subdev: %d\n", ret);
 		goto error_media_entity;
 	}
 
diff --git a/drivers/media/i2c/ov08x40.c b/drivers/media/i2c/ov08x40.c
index 67b86dabc67e..1fe8e9b584f8 100644
--- a/drivers/media/i2c/ov08x40.c
+++ b/drivers/media/i2c/ov08x40.c
@@ -1869,6 +1869,32 @@ static int ov08x40_stop_streaming(struct ov08x40 *ov08x)
 				 OV08X40_REG_VALUE_08BIT, OV08X40_MODE_STANDBY);
 }
 
+/* Verify chip ID */
+static int ov08x40_identify_module(struct ov08x40 *ov08x)
+{
+	struct i2c_client *client = v4l2_get_subdevdata(&ov08x->sd);
+	int ret;
+	u32 val;
+
+	if (ov08x->identified)
+		return 0;
+
+	ret = ov08x40_read_reg(ov08x, OV08X40_REG_CHIP_ID,
+			       OV08X40_REG_VALUE_24BIT, &val);
+	if (ret)
+		return ret;
+
+	if (val != OV08X40_CHIP_ID) {
+		dev_err(&client->dev, "chip id mismatch: %x!=%x\n",
+			OV08X40_CHIP_ID, val);
+		return -ENXIO;
+	}
+
+	ov08x->identified = true;
+
+	return 0;
+}
+
 static int ov08x40_set_stream(struct v4l2_subdev *sd, int enable)
 {
 	struct ov08x40 *ov08x = to_ov08x40(sd);
@@ -1882,6 +1908,10 @@ static int ov08x40_set_stream(struct v4l2_subdev *sd, int enable)
 		if (ret < 0)
 			goto err_unlock;
 
+		ret = ov08x40_identify_module(ov08x);
+		if (ret)
+			goto err_rpm_put;
+
 		/*
 		 * Apply default & customized values
 		 * and then start streaming.
@@ -1906,32 +1936,6 @@ err_unlock:
 	return ret;
 }
 
-/* Verify chip ID */
-static int ov08x40_identify_module(struct ov08x40 *ov08x)
-{
-	struct i2c_client *client = v4l2_get_subdevdata(&ov08x->sd);
-	int ret;
-	u32 val;
-
-	if (ov08x->identified)
-		return 0;
-
-	ret = ov08x40_read_reg(ov08x, OV08X40_REG_CHIP_ID,
-			       OV08X40_REG_VALUE_24BIT, &val);
-	if (ret)
-		return ret;
-
-	if (val != OV08X40_CHIP_ID) {
-		dev_err(&client->dev, "chip id mismatch: %x!=%x\n",
-			OV08X40_CHIP_ID, val);
-		return -ENXIO;
-	}
-
-	ov08x->identified = true;
-
-	return 0;
-}
-
 static const struct v4l2_subdev_video_ops ov08x40_video_ops = {
 	.s_stream = ov08x40_set_stream,
 };
diff --git a/drivers/media/i2c/ov2740.c b/drivers/media/i2c/ov2740.c
index bd0b2f0f0d45..3a0835fa5766 100644
--- a/drivers/media/i2c/ov2740.c
+++ b/drivers/media/i2c/ov2740.c
@@ -1404,12 +1404,12 @@ static int ov2740_probe(struct i2c_client *client)
 	return 0;
 
 probe_error_v4l2_subdev_cleanup:
+	pm_runtime_disable(&client->dev);
+	pm_runtime_set_suspended(&client->dev);
 	v4l2_subdev_cleanup(&ov2740->sd);
 
 probe_error_media_entity_cleanup:
 	media_entity_cleanup(&ov2740->sd.entity);
-	pm_runtime_disable(&client->dev);
-	pm_runtime_set_suspended(&client->dev);
 
 probe_error_v4l2_ctrl_handler_free:
 	v4l2_ctrl_handler_free(ov2740->sd.ctrl_handler);
diff --git a/drivers/media/i2c/ov5640.c b/drivers/media/i2c/ov5640.c
index c1d3fce4a7d3..8566bc2edde9 100644
--- a/drivers/media/i2c/ov5640.c
+++ b/drivers/media/i2c/ov5640.c
@@ -1982,6 +1982,7 @@ static int ov5640_get_light_freq(struct ov5640_dev *sensor)
 			light_freq = 50;
 		} else {
 			/* 60Hz */
+			light_freq = 60;
 		}
 	}
 
diff --git a/drivers/media/i2c/ov5675.c b/drivers/media/i2c/ov5675.c
index 2833b14ee139..c0ab3c0ed88e 100644
--- a/drivers/media/i2c/ov5675.c
+++ b/drivers/media/i2c/ov5675.c
@@ -1295,11 +1295,8 @@ static int ov5675_probe(struct i2c_client *client)
 		return -ENOMEM;
 
 	ret = ov5675_get_hwcfg(ov5675, &client->dev);
-	if (ret) {
-		dev_err(&client->dev, "failed to get HW configuration: %d",
-			ret);
+	if (ret)
 		return ret;
-	}
 
 	v4l2_i2c_subdev_init(&ov5675->sd, client, &ov5675_subdev_ops);
 
diff --git a/drivers/media/i2c/ov7251.c b/drivers/media/i2c/ov7251.c
index 30f61e04ecaf..3226888d77e9 100644
--- a/drivers/media/i2c/ov7251.c
+++ b/drivers/media/i2c/ov7251.c
@@ -922,6 +922,8 @@ static int ov7251_set_power_on(struct device *dev)
 		return ret;
 	}
 
+	usleep_range(1000, 1100);
+
 	gpiod_set_value_cansleep(ov7251->enable_gpio, 1);
 
 	/* wait at least 65536 external clock cycles */
@@ -1696,7 +1698,7 @@ static int ov7251_probe(struct i2c_client *client)
 		return PTR_ERR(ov7251->analog_regulator);
 	}
 
-	ov7251->enable_gpio = devm_gpiod_get(dev, "enable", GPIOD_OUT_HIGH);
+	ov7251->enable_gpio = devm_gpiod_get(dev, "enable", GPIOD_OUT_LOW);
 	if (IS_ERR(ov7251->enable_gpio)) {
 		dev_err(dev, "cannot get enable gpio\n");
 		return PTR_ERR(ov7251->enable_gpio);
diff --git a/drivers/media/i2c/ov8856.c b/drivers/media/i2c/ov8856.c
index 3b94338f55ed..23d524de7d60 100644
--- a/drivers/media/i2c/ov8856.c
+++ b/drivers/media/i2c/ov8856.c
@@ -2276,8 +2276,8 @@ static int ov8856_get_hwcfg(struct ov8856 *ov8856, struct device *dev)
 	if (!is_acpi_node(fwnode)) {
 		ov8856->xvclk = devm_clk_get(dev, "xvclk");
 		if (IS_ERR(ov8856->xvclk)) {
-			dev_err(dev, "could not get xvclk clock (%pe)\n",
-				ov8856->xvclk);
+			dev_err_probe(dev, PTR_ERR(ov8856->xvclk),
+				      "could not get xvclk clock\n");
 			return PTR_ERR(ov8856->xvclk);
 		}
 
@@ -2382,11 +2382,8 @@ static int ov8856_probe(struct i2c_client *client)
 		return -ENOMEM;
 
 	ret = ov8856_get_hwcfg(ov8856, &client->dev);
-	if (ret) {
-		dev_err(&client->dev, "failed to get HW configuration: %d",
-			ret);
+	if (ret)
 		return ret;
-	}
 
 	v4l2_i2c_subdev_init(&ov8856->sd, client, &ov8856_subdev_ops);
 
diff --git a/drivers/media/i2c/ov9282.c b/drivers/media/i2c/ov9282.c
index 9f52af6f047f..87e5d7ce5a47 100644
--- a/drivers/media/i2c/ov9282.c
+++ b/drivers/media/i2c/ov9282.c
@@ -40,7 +40,7 @@
 /* Exposure control */
 #define OV9282_REG_EXPOSURE	0x3500
 #define OV9282_EXPOSURE_MIN	1
-#define OV9282_EXPOSURE_OFFSET	12
+#define OV9282_EXPOSURE_OFFSET	25
 #define OV9282_EXPOSURE_STEP	1
 #define OV9282_EXPOSURE_DEFAULT	0x0282
 
diff --git a/drivers/media/i2c/tc358743.c b/drivers/media/i2c/tc358743.c
index 344a670e732f..d1306f39fa13 100644
--- a/drivers/media/i2c/tc358743.c
+++ b/drivers/media/i2c/tc358743.c
@@ -110,7 +110,7 @@ static inline struct tc358743_state *to_state(struct v4l2_subdev *sd)
 
 /* --------------- I2C --------------- */
 
-static void i2c_rd(struct v4l2_subdev *sd, u16 reg, u8 *values, u32 n)
+static int i2c_rd(struct v4l2_subdev *sd, u16 reg, u8 *values, u32 n)
 {
 	struct tc358743_state *state = to_state(sd);
 	struct i2c_client *client = state->i2c_client;
@@ -136,6 +136,7 @@ static void i2c_rd(struct v4l2_subdev *sd, u16 reg, u8 *values, u32 n)
 		v4l2_err(sd, "%s: reading register 0x%x from 0x%x failed: %d\n",
 				__func__, reg, client->addr, err);
 	}
+	return err != ARRAY_SIZE(msgs);
 }
 
 static void i2c_wr(struct v4l2_subdev *sd, u16 reg, u8 *values, u32 n)
@@ -192,15 +193,24 @@ static void i2c_wr(struct v4l2_subdev *sd, u16 reg, u8 *values, u32 n)
 	}
 }
 
-static noinline u32 i2c_rdreg(struct v4l2_subdev *sd, u16 reg, u32 n)
+static noinline u32 i2c_rdreg_err(struct v4l2_subdev *sd, u16 reg, u32 n,
+				  int *err)
 {
+	int error;
 	__le32 val = 0;
 
-	i2c_rd(sd, reg, (u8 __force *)&val, n);
+	error = i2c_rd(sd, reg, (u8 __force *)&val, n);
+	if (err)
+		*err = error;
 
 	return le32_to_cpu(val);
 }
 
+static inline u32 i2c_rdreg(struct v4l2_subdev *sd, u16 reg, u32 n)
+{
+	return i2c_rdreg_err(sd, reg, n, NULL);
+}
+
 static noinline void i2c_wrreg(struct v4l2_subdev *sd, u16 reg, u32 val, u32 n)
 {
 	__le32 raw = cpu_to_le32(val);
@@ -229,6 +239,13 @@ static u16 i2c_rd16(struct v4l2_subdev *sd, u16 reg)
 	return i2c_rdreg(sd, reg, 2);
 }
 
+static int i2c_rd16_err(struct v4l2_subdev *sd, u16 reg, u16 *value)
+{
+	int err;
+	*value = i2c_rdreg_err(sd, reg, 2, &err);
+	return err;
+}
+
 static void i2c_wr16(struct v4l2_subdev *sd, u16 reg, u16 val)
 {
 	i2c_wrreg(sd, reg, val, 2);
@@ -1660,12 +1677,23 @@ static int tc358743_enum_mbus_code(struct v4l2_subdev *sd,
 	return 0;
 }
 
+static u32 tc358743_g_colorspace(u32 code)
+{
+	switch (code) {
+	case MEDIA_BUS_FMT_RGB888_1X24:
+		return V4L2_COLORSPACE_SRGB;
+	case MEDIA_BUS_FMT_UYVY8_1X16:
+		return V4L2_COLORSPACE_SMPTE170M;
+	default:
+		return 0;
+	}
+}
+
 static int tc358743_get_fmt(struct v4l2_subdev *sd,
 		struct v4l2_subdev_state *sd_state,
 		struct v4l2_subdev_format *format)
 {
 	struct tc358743_state *state = to_state(sd);
-	u8 vi_rep = i2c_rd8(sd, VI_REP);
 
 	if (format->pad != 0)
 		return -EINVAL;
@@ -1675,23 +1703,7 @@ static int tc358743_get_fmt(struct v4l2_subdev *sd,
 	format->format.height = state->timings.bt.height;
 	format->format.field = V4L2_FIELD_NONE;
 
-	switch (vi_rep & MASK_VOUT_COLOR_SEL) {
-	case MASK_VOUT_COLOR_RGB_FULL:
-	case MASK_VOUT_COLOR_RGB_LIMITED:
-		format->format.colorspace = V4L2_COLORSPACE_SRGB;
-		break;
-	case MASK_VOUT_COLOR_601_YCBCR_LIMITED:
-	case MASK_VOUT_COLOR_601_YCBCR_FULL:
-		format->format.colorspace = V4L2_COLORSPACE_SMPTE170M;
-		break;
-	case MASK_VOUT_COLOR_709_YCBCR_FULL:
-	case MASK_VOUT_COLOR_709_YCBCR_LIMITED:
-		format->format.colorspace = V4L2_COLORSPACE_REC709;
-		break;
-	default:
-		format->format.colorspace = 0;
-		break;
-	}
+	format->format.colorspace = tc358743_g_colorspace(format->format.code);
 
 	return 0;
 }
@@ -1705,19 +1717,14 @@ static int tc358743_set_fmt(struct v4l2_subdev *sd,
 	u32 code = format->format.code; /* is overwritten by get_fmt */
 	int ret = tc358743_get_fmt(sd, sd_state, format);
 
-	format->format.code = code;
+	if (code == MEDIA_BUS_FMT_RGB888_1X24 ||
+	    code == MEDIA_BUS_FMT_UYVY8_1X16)
+		format->format.code = code;
+	format->format.colorspace = tc358743_g_colorspace(format->format.code);
 
 	if (ret)
 		return ret;
 
-	switch (code) {
-	case MEDIA_BUS_FMT_RGB888_1X24:
-	case MEDIA_BUS_FMT_UYVY8_1X16:
-		break;
-	default:
-		return -EINVAL;
-	}
-
 	if (format->which == V4L2_SUBDEV_FORMAT_TRY)
 		return 0;
 
@@ -1941,8 +1948,19 @@ static int tc358743_probe_of(struct tc358743_state *state)
 	state->pdata.refclk_hz = clk_get_rate(refclk);
 	state->pdata.ddc5v_delay = DDC5V_DELAY_100_MS;
 	state->pdata.enable_hdcp = false;
-	/* A FIFO level of 16 should be enough for 2-lane 720p60 at 594 MHz. */
-	state->pdata.fifo_level = 16;
+	/*
+	 * Ideally the FIFO trigger level should be set based on the input and
+	 * output data rates, but the calculations required are buried in
+	 * Toshiba's register settings spreadsheet.
+	 * A value of 16 works with a 594Mbps data rate for 720p60 (using 2
+	 * lanes) and 1080p60 (using 4 lanes), but fails when the data rate
+	 * is increased, or a lower pixel clock is used that result in CSI
+	 * reading out faster than the data is arriving.
+	 *
+	 * A value of 374 works with both those modes at 594Mbps, and with most
+	 * modes on 972Mbps.
+	 */
+	state->pdata.fifo_level = 374;
 	/*
 	 * The PLL input clock is obtained by dividing refclk by pll_prd.
 	 * It must be between 6 MHz and 40 MHz, lower frequency is better.
@@ -2030,6 +2048,7 @@ static int tc358743_probe(struct i2c_client *client)
 	struct tc358743_platform_data *pdata = client->dev.platform_data;
 	struct v4l2_subdev *sd;
 	u16 irq_mask = MASK_HDMI_MSK | MASK_CSI_MSK;
+	u16 chipid;
 	int err;
 
 	if (!i2c_check_functionality(client->adapter, I2C_FUNC_SMBUS_BYTE_DATA))
@@ -2061,7 +2080,8 @@ static int tc358743_probe(struct i2c_client *client)
 	sd->flags |= V4L2_SUBDEV_FL_HAS_DEVNODE | V4L2_SUBDEV_FL_HAS_EVENTS;
 
 	/* i2c access */
-	if ((i2c_rd16(sd, CHIPID) & MASK_CHIPID) != 0) {
+	if (i2c_rd16_err(sd, CHIPID, &chipid) ||
+	    (chipid & MASK_CHIPID) != 0) {
 		v4l2_info(sd, "not a TC358743 on address 0x%x\n",
 			  client->addr << 1);
 		return -ENODEV;
diff --git a/drivers/media/i2c/tc358746.c b/drivers/media/i2c/tc358746.c
index 389582420ba7..048a1a381b33 100644
--- a/drivers/media/i2c/tc358746.c
+++ b/drivers/media/i2c/tc358746.c
@@ -460,24 +460,20 @@ out:
 	return err;
 }
 
-/* Use MHz as base so the div needs no u64 */
-static u32 tc358746_cfg_to_cnt(unsigned int cfg_val,
-			       unsigned int clk_mhz,
-			       unsigned int time_base)
+static u32 tc358746_cfg_to_cnt(unsigned long cfg_val, unsigned long clk_hz,
+			       unsigned long long time_base)
 {
-	return DIV_ROUND_UP(cfg_val * clk_mhz, time_base);
+	return div64_u64((u64)cfg_val * clk_hz + time_base - 1, time_base);
 }
 
-static u32 tc358746_ps_to_cnt(unsigned int cfg_val,
-			      unsigned int clk_mhz)
+static u32 tc358746_ps_to_cnt(unsigned long cfg_val, unsigned long clk_hz)
 {
-	return tc358746_cfg_to_cnt(cfg_val, clk_mhz, USEC_PER_SEC);
+	return tc358746_cfg_to_cnt(cfg_val, clk_hz, PSEC_PER_SEC);
 }
 
-static u32 tc358746_us_to_cnt(unsigned int cfg_val,
-			      unsigned int clk_mhz)
+static u32 tc358746_us_to_cnt(unsigned long cfg_val, unsigned long clk_hz)
 {
-	return tc358746_cfg_to_cnt(cfg_val, clk_mhz, 1);
+	return tc358746_cfg_to_cnt(cfg_val, clk_hz, USEC_PER_SEC);
 }
 
 static int tc358746_apply_dphy_config(struct tc358746 *tc358746)
@@ -492,7 +488,6 @@ static int tc358746_apply_dphy_config(struct tc358746 *tc358746)
 
 	/* The hs_byte_clk is also called SYSCLK in the excel sheet */
 	hs_byte_clk = cfg->hs_clk_rate / 8;
-	hs_byte_clk /= HZ_PER_MHZ;
 	hf_clk = hs_byte_clk / 2;
 
 	val = tc358746_us_to_cnt(cfg->init, hf_clk) - 1;
diff --git a/drivers/media/pci/intel/ipu-bridge.c b/drivers/media/pci/intel/ipu-bridge.c
index a0e9a71580b5..4e921c751629 100644
--- a/drivers/media/pci/intel/ipu-bridge.c
+++ b/drivers/media/pci/intel/ipu-bridge.c
@@ -59,6 +59,8 @@ static const struct ipu_sensor_config ipu_supported_sensors[] = {
 	IPU_SENSOR_CONFIG("INT33BE", 1, 419200000),
 	/* Omnivision OV2740 */
 	IPU_SENSOR_CONFIG("INT3474", 1, 180000000),
+	/* Omnivision OV5670 */
+	IPU_SENSOR_CONFIG("INT3479", 1, 422400000),
 	/* Omnivision OV8865 */
 	IPU_SENSOR_CONFIG("INT347A", 1, 360000000),
 	/* Omnivision OV7251 */
diff --git a/drivers/media/pci/intel/ipu6/ipu6-dma.c b/drivers/media/pci/intel/ipu6/ipu6-dma.c
index b71f66bd8c1f..92d513608395 100644
--- a/drivers/media/pci/intel/ipu6/ipu6-dma.c
+++ b/drivers/media/pci/intel/ipu6/ipu6-dma.c
@@ -172,7 +172,7 @@ void *ipu6_dma_alloc(struct ipu6_bus_device *sys, size_t size,
 	count = PHYS_PFN(size);
 
 	iova = alloc_iova(&mmu->dmap->iovad, count,
-			  PHYS_PFN(dma_get_mask(dev)), 0);
+			  PHYS_PFN(mmu->dmap->mmu_info->aperture_end), 0);
 	if (!iova)
 		goto out_kfree;
 
@@ -398,7 +398,7 @@ int ipu6_dma_map_sg(struct ipu6_bus_device *sys, struct scatterlist *sglist,
 		nents, npages);
 
 	iova = alloc_iova(&mmu->dmap->iovad, npages,
-			  PHYS_PFN(dma_get_mask(dev)), 0);
+			  PHYS_PFN(mmu->dmap->mmu_info->aperture_end), 0);
 	if (!iova)
 		return 0;
 
diff --git a/drivers/media/pci/intel/ipu6/ipu6-isys-video.c b/drivers/media/pci/intel/ipu6/ipu6-isys-video.c
index b37561352ead..48388c0c851c 100644
--- a/drivers/media/pci/intel/ipu6/ipu6-isys-video.c
+++ b/drivers/media/pci/intel/ipu6/ipu6-isys-video.c
@@ -1296,6 +1296,7 @@ int ipu6_isys_video_init(struct ipu6_isys_video *av)
 	av->vdev.release = video_device_release_empty;
 	av->vdev.fops = &isys_fops;
 	av->vdev.v4l2_dev = &av->isys->v4l2_dev;
+	av->vdev.dev_parent = &av->isys->adev->isp->pdev->dev;
 	if (!av->vdev.ioctl_ops)
 		av->vdev.ioctl_ops = &ipu6_v4l2_ioctl_ops;
 	av->vdev.queue = &av->aq.vbq;
diff --git a/drivers/media/pci/intel/ipu6/ipu6-isys.c b/drivers/media/pci/intel/ipu6/ipu6-isys.c
index c85e056cb904..17bc8cabcbdb 100644
--- a/drivers/media/pci/intel/ipu6/ipu6-isys.c
+++ b/drivers/media/pci/intel/ipu6/ipu6-isys.c
@@ -1133,6 +1133,7 @@ static int isys_probe(struct auxiliary_device *auxdev,
 free_fw_msg_bufs:
 	free_fw_msg_bufs(isys);
 out_remove_pkg_dir_shared_buffer:
+	cpu_latency_qos_remove_request(&isys->pm_qos);
 	if (!isp->secure_mode)
 		ipu6_cpd_free_pkg_dir(adev);
 remove_shared_buffer:
diff --git a/drivers/media/pci/intel/ipu6/ipu6.c b/drivers/media/pci/intel/ipu6/ipu6.c
index 91718eabd74e..1c5c38a30e62 100644
--- a/drivers/media/pci/intel/ipu6/ipu6.c
+++ b/drivers/media/pci/intel/ipu6/ipu6.c
@@ -463,11 +463,6 @@ static int ipu6_pci_config_setup(struct pci_dev *dev, u8 hw_ver)
 {
 	int ret;
 
-	/* disable IPU6 PCI ATS on mtl ES2 */
-	if (is_ipu6ep_mtl(hw_ver) && boot_cpu_data.x86_stepping == 0x2 &&
-	    pci_ats_supported(dev))
-		pci_disable_ats(dev);
-
 	/* No PCI msi capability for IPU6EP */
 	if (is_ipu6ep(hw_ver) || is_ipu6ep_mtl(hw_ver)) {
 		/* likely do nothing as msi not enabled by default */
diff --git a/drivers/media/pci/mgb4/mgb4_cmt.c b/drivers/media/pci/mgb4/mgb4_cmt.c
index a25b68403bc6..c22ef51436ed 100644
--- a/drivers/media/pci/mgb4/mgb4_cmt.c
+++ b/drivers/media/pci/mgb4/mgb4_cmt.c
@@ -135,8 +135,8 @@ static const u16 cmt_vals_out[][15] = {
 };
 
 static const u16 cmt_vals_in[][13] = {
-	{0x1082, 0x0000, 0x5104, 0x0000, 0x11C7, 0x0000, 0x1041, 0x02BC, 0x7C01, 0xFFE9, 0x9900, 0x9908, 0x8100},
 	{0x1104, 0x0000, 0x9208, 0x0000, 0x138E, 0x0000, 0x1041, 0x015E, 0x7C01, 0xFFE9, 0x0100, 0x0908, 0x1000},
+	{0x1082, 0x0000, 0x5104, 0x0000, 0x11C7, 0x0000, 0x1041, 0x02BC, 0x7C01, 0xFFE9, 0x9900, 0x9908, 0x8100},
 };
 
 static const u32 cmt_addrs_out[][15] = {
@@ -206,10 +206,11 @@ u32 mgb4_cmt_set_vout_freq(struct mgb4_vout_dev *voutdev, unsigned int freq)
 
 	mgb4_write_reg(video, regs->config, 0x1 | (config & ~0x3));
 
+	mgb4_mask_reg(video, regs->config, 0x100, 0x100);
+
 	for (i = 0; i < ARRAY_SIZE(cmt_addrs_out[0]); i++)
 		mgb4_write_reg(&voutdev->mgbdev->cmt, addr[i], reg_set[i]);
 
-	mgb4_mask_reg(video, regs->config, 0x100, 0x100);
 	mgb4_mask_reg(video, regs->config, 0x100, 0x0);
 
 	mgb4_write_reg(video, regs->config, config & ~0x1);
@@ -236,10 +237,11 @@ void mgb4_cmt_set_vin_freq_range(struct mgb4_vin_dev *vindev,
 
 	mgb4_write_reg(video, regs->config, 0x1 | (config & ~0x3));
 
+	mgb4_mask_reg(video, regs->config, 0x1000, 0x1000);
+
 	for (i = 0; i < ARRAY_SIZE(cmt_addrs_in[0]); i++)
 		mgb4_write_reg(&vindev->mgbdev->cmt, addr[i], reg_set[i]);
 
-	mgb4_mask_reg(video, regs->config, 0x1000, 0x1000);
 	mgb4_mask_reg(video, regs->config, 0x1000, 0x0);
 
 	mgb4_write_reg(video, regs->config, config & ~0x1);
diff --git a/drivers/media/platform/allegro-dvt/allegro-core.c b/drivers/media/platform/allegro-dvt/allegro-core.c
index 88c36eb6174a..9ca4e2f94647 100644
--- a/drivers/media/platform/allegro-dvt/allegro-core.c
+++ b/drivers/media/platform/allegro-dvt/allegro-core.c
@@ -3914,6 +3914,7 @@ static int allegro_probe(struct platform_device *pdev)
 	if (ret < 0) {
 		v4l2_err(&dev->v4l2_dev,
 			 "failed to request firmware: %d\n", ret);
+		v4l2_device_unregister(&dev->v4l2_dev);
 		return ret;
 	}
 
diff --git a/drivers/media/platform/broadcom/bcm2835-unicam.c b/drivers/media/platform/broadcom/bcm2835-unicam.c
index a1d93c14553d..9f81e1582a30 100644
--- a/drivers/media/platform/broadcom/bcm2835-unicam.c
+++ b/drivers/media/platform/broadcom/bcm2835-unicam.c
@@ -816,11 +816,6 @@ static irqreturn_t unicam_isr(int irq, void *dev)
 		}
 	}
 
-	if (unicam_reg_read(unicam, UNICAM_ICTL) & UNICAM_FCM) {
-		/* Switch out of trigger mode if selected */
-		unicam_reg_write_field(unicam, UNICAM_ICTL, 1, UNICAM_TFC);
-		unicam_reg_write_field(unicam, UNICAM_ICTL, 0, UNICAM_FCM);
-	}
 	return IRQ_HANDLED;
 }
 
@@ -984,8 +979,7 @@ static void unicam_start_rx(struct unicam_device *unicam,
 
 	unicam_reg_write_field(unicam, UNICAM_ANA, 0, UNICAM_DDL);
 
-	/* Always start in trigger frame capture mode (UNICAM_FCM set) */
-	val = UNICAM_FSIE | UNICAM_FEIE | UNICAM_FCM | UNICAM_IBOB;
+	val = UNICAM_FSIE | UNICAM_FEIE | UNICAM_IBOB;
 	line_int_freq = max(fmt->height >> 2, 128);
 	unicam_set_field(&val, line_int_freq, UNICAM_LCIE_MASK);
 	unicam_reg_write(unicam, UNICAM_ICTL, val);
diff --git a/drivers/media/platform/chips-media/wave5/wave5-hw.c b/drivers/media/platform/chips-media/wave5/wave5-hw.c
index c89aafabc742..710311d85113 100644
--- a/drivers/media/platform/chips-media/wave5/wave5-hw.c
+++ b/drivers/media/platform/chips-media/wave5/wave5-hw.c
@@ -576,7 +576,7 @@ int wave5_vpu_build_up_dec_param(struct vpu_instance *inst,
 		vpu_write_reg(inst->dev, W5_CMD_NUM_CQ_DEPTH_M1,
 			      WAVE521_COMMAND_QUEUE_DEPTH - 1);
 	}
-
+	vpu_write_reg(inst->dev, W5_CMD_ERR_CONCEAL, 0);
 	ret = send_firmware_command(inst, W5_CREATE_INSTANCE, true, NULL, NULL);
 	if (ret) {
 		wave5_vdi_free_dma_memory(vpu_dev, &p_dec_info->vb_work);
diff --git a/drivers/media/platform/chips-media/wave5/wave5-vpu-dec.c b/drivers/media/platform/chips-media/wave5/wave5-vpu-dec.c
index 0c5c9a8de91f..e238447c88bb 100644
--- a/drivers/media/platform/chips-media/wave5/wave5-vpu-dec.c
+++ b/drivers/media/platform/chips-media/wave5/wave5-vpu-dec.c
@@ -1424,10 +1424,24 @@ static int wave5_vpu_dec_start_streaming(struct vb2_queue *q, unsigned int count
 		if (ret)
 			goto free_bitstream_vbuf;
 	} else if (q->type == V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE) {
+		struct dec_initial_info *initial_info =
+			&inst->codec_info->dec_info.initial_info;
+
 		if (inst->state == VPU_INST_STATE_STOP)
 			ret = switch_state(inst, VPU_INST_STATE_INIT_SEQ);
 		if (ret)
 			goto return_buffers;
+
+		if (inst->state == VPU_INST_STATE_INIT_SEQ &&
+		    inst->dev->product_code == WAVE521C_CODE) {
+			if (initial_info->luma_bitdepth != 8) {
+				dev_info(inst->dev->dev, "%s: no support for %d bit depth",
+					 __func__, initial_info->luma_bitdepth);
+				ret = -EINVAL;
+				goto return_buffers;
+			}
+		}
+
 	}
 
 	return ret;
@@ -1446,6 +1460,16 @@ static int streamoff_output(struct vb2_queue *q)
 	struct vb2_v4l2_buffer *buf;
 	int ret;
 	dma_addr_t new_rd_ptr;
+	struct dec_output_info dec_info;
+	unsigned int i;
+
+	for (i = 0; i < v4l2_m2m_num_dst_bufs_ready(m2m_ctx); i++) {
+		ret = wave5_vpu_dec_set_disp_flag(inst, i);
+		if (ret)
+			dev_dbg(inst->dev->dev,
+				"%s: Setting display flag of buf index: %u, fail: %d\n",
+				__func__, i, ret);
+	}
 
 	while ((buf = v4l2_m2m_src_buf_remove(m2m_ctx))) {
 		dev_dbg(inst->dev->dev, "%s: (Multiplanar) buf type %4u | index %4u\n",
@@ -1453,6 +1477,11 @@ static int streamoff_output(struct vb2_queue *q)
 		v4l2_m2m_buf_done(buf, VB2_BUF_STATE_ERROR);
 	}
 
+	while (wave5_vpu_dec_get_output_info(inst, &dec_info) == 0) {
+		if (dec_info.index_frame_display >= 0)
+			wave5_vpu_dec_set_disp_flag(inst, dec_info.index_frame_display);
+	}
+
 	ret = wave5_vpu_flush_instance(inst);
 	if (ret)
 		return ret;
@@ -1535,7 +1564,7 @@ static void wave5_vpu_dec_stop_streaming(struct vb2_queue *q)
 			break;
 
 		if (wave5_vpu_dec_get_output_info(inst, &dec_output_info))
-			dev_dbg(inst->dev->dev, "Getting decoding results from fw, fail\n");
+			dev_dbg(inst->dev->dev, "there is no output info\n");
 	}
 
 	v4l2_m2m_update_stop_streaming_state(m2m_ctx, q);
diff --git a/drivers/media/platform/chips-media/wave5/wave5-vpu.c b/drivers/media/platform/chips-media/wave5/wave5-vpu.c
index 7273254ecb03..b13c5cd46d7e 100644
--- a/drivers/media/platform/chips-media/wave5/wave5-vpu.c
+++ b/drivers/media/platform/chips-media/wave5/wave5-vpu.c
@@ -54,12 +54,12 @@ static void wave5_vpu_handle_irq(void *dev_id)
 	struct vpu_device *dev = dev_id;
 
 	irq_reason = wave5_vdi_read_register(dev, W5_VPU_VINT_REASON);
+	seq_done = wave5_vdi_read_register(dev, W5_RET_SEQ_DONE_INSTANCE_INFO);
+	cmd_done = wave5_vdi_read_register(dev, W5_RET_QUEUE_CMD_DONE_INST);
 	wave5_vdi_write_register(dev, W5_VPU_VINT_REASON_CLR, irq_reason);
 	wave5_vdi_write_register(dev, W5_VPU_VINT_CLEAR, 0x1);
 
 	list_for_each_entry(inst, &dev->instances, list) {
-		seq_done = wave5_vdi_read_register(dev, W5_RET_SEQ_DONE_INSTANCE_INFO);
-		cmd_done = wave5_vdi_read_register(dev, W5_RET_QUEUE_CMD_DONE_INST);
 
 		if (irq_reason & BIT(INT_WAVE5_INIT_SEQ) ||
 		    irq_reason & BIT(INT_WAVE5_ENC_SET_PARAM)) {
diff --git a/drivers/media/platform/chips-media/wave5/wave5-vpuapi.c b/drivers/media/platform/chips-media/wave5/wave5-vpuapi.c
index 1a3efb638dde..65fdabcd9d29 100644
--- a/drivers/media/platform/chips-media/wave5/wave5-vpuapi.c
+++ b/drivers/media/platform/chips-media/wave5/wave5-vpuapi.c
@@ -73,6 +73,16 @@ int wave5_vpu_flush_instance(struct vpu_instance *inst)
 				 inst->type == VPU_INST_TYPE_DEC ? "DECODER" : "ENCODER", inst->id);
 			mutex_unlock(&inst->dev->hw_lock);
 			return -ETIMEDOUT;
+		} else if (ret == -EBUSY) {
+			struct dec_output_info dec_info;
+
+			mutex_unlock(&inst->dev->hw_lock);
+			wave5_vpu_dec_get_output_info(inst, &dec_info);
+			ret = mutex_lock_interruptible(&inst->dev->hw_lock);
+			if (ret)
+				return ret;
+			if (dec_info.index_frame_display > 0)
+				wave5_vpu_dec_set_disp_flag(inst, dec_info.index_frame_display);
 		}
 	} while (ret != 0);
 	mutex_unlock(&inst->dev->hw_lock);
diff --git a/drivers/media/platform/imagination/e5010-jpeg-enc.c b/drivers/media/platform/imagination/e5010-jpeg-enc.c
index 187f2d8abfbb..cb1f7de1b632 100644
--- a/drivers/media/platform/imagination/e5010-jpeg-enc.c
+++ b/drivers/media/platform/imagination/e5010-jpeg-enc.c
@@ -1057,8 +1057,11 @@ static int e5010_probe(struct platform_device *pdev)
 	e5010->vdev->lock = &e5010->mutex;
 
 	ret = v4l2_device_register(dev, &e5010->v4l2_dev);
-	if (ret)
-		return dev_err_probe(dev, ret, "failed to register v4l2 device\n");
+	if (ret) {
+		dev_err_probe(dev, ret, "failed to register v4l2 device\n");
+		goto fail_after_video_device_alloc;
+	}
+
 
 	e5010->m2m_dev = v4l2_m2m_init(&e5010_m2m_ops);
 	if (IS_ERR(e5010->m2m_dev)) {
@@ -1118,6 +1121,8 @@ fail_after_video_register_device:
 	v4l2_m2m_release(e5010->m2m_dev);
 fail_after_v4l2_register:
 	v4l2_device_unregister(&e5010->v4l2_dev);
+fail_after_video_device_alloc:
+	video_device_release(e5010->vdev);
 	return ret;
 }
 
diff --git a/drivers/media/platform/marvell/mcam-core.c b/drivers/media/platform/marvell/mcam-core.c
index c81593c969e0..a62c3a484cb3 100644
--- a/drivers/media/platform/marvell/mcam-core.c
+++ b/drivers/media/platform/marvell/mcam-core.c
@@ -935,7 +935,12 @@ static int mclk_enable(struct clk_hw *hw)
 	ret = pm_runtime_resume_and_get(cam->dev);
 	if (ret < 0)
 		return ret;
-	clk_enable(cam->clk[0]);
+	ret = clk_enable(cam->clk[0]);
+	if (ret) {
+		pm_runtime_put(cam->dev);
+		return ret;
+	}
+
 	mcam_reg_write(cam, REG_CLKCTRL, (mclk_src << 29) | mclk_div);
 	mcam_ctlr_power_up(cam);
 
diff --git a/drivers/media/platform/marvell/mmp-driver.c b/drivers/media/platform/marvell/mmp-driver.c
index ff9d151121d5..4fa171d469ca 100644
--- a/drivers/media/platform/marvell/mmp-driver.c
+++ b/drivers/media/platform/marvell/mmp-driver.c
@@ -232,12 +232,22 @@ static int mmpcam_probe(struct platform_device *pdev)
 	mcam_init_clk(mcam);
 
 	/*
+	 * Register with V4L.
+	 */
+
+	ret = v4l2_device_register(mcam->dev, &mcam->v4l2_dev);
+	if (ret)
+		return ret;
+
+	/*
 	 * Create a match of the sensor against its OF node.
 	 */
 	ep = fwnode_graph_get_next_endpoint(of_fwnode_handle(pdev->dev.of_node),
 					    NULL);
-	if (!ep)
-		return -ENODEV;
+	if (!ep) {
+		ret = -ENODEV;
+		goto out_v4l2_device_unregister;
+	}
 
 	v4l2_async_nf_init(&mcam->notifier, &mcam->v4l2_dev);
 
@@ -246,7 +256,7 @@ static int mmpcam_probe(struct platform_device *pdev)
 	fwnode_handle_put(ep);
 	if (IS_ERR(asd)) {
 		ret = PTR_ERR(asd);
-		goto out;
+		goto out_v4l2_device_unregister;
 	}
 
 	/*
@@ -254,7 +264,7 @@ static int mmpcam_probe(struct platform_device *pdev)
 	 */
 	ret = mccic_register(mcam);
 	if (ret)
-		goto out;
+		goto out_v4l2_device_unregister;
 
 	/*
 	 * Add OF clock provider.
@@ -283,6 +293,8 @@ static int mmpcam_probe(struct platform_device *pdev)
 	return 0;
 out:
 	mccic_shutdown(mcam);
+out_v4l2_device_unregister:
+	v4l2_device_unregister(&mcam->v4l2_dev);
 
 	return ret;
 }
@@ -293,6 +305,7 @@ static void mmpcam_remove(struct platform_device *pdev)
 	struct mcam_camera *mcam = &cam->mcam;
 
 	mccic_shutdown(mcam);
+	v4l2_device_unregister(&mcam->v4l2_dev);
 	pm_runtime_force_suspend(mcam->dev);
 }
 
diff --git a/drivers/media/platform/mediatek/vcodec/common/mtk_vcodec_fw_scp.c b/drivers/media/platform/mediatek/vcodec/common/mtk_vcodec_fw_scp.c
index ff23b225db70..1b0bc47355c0 100644
--- a/drivers/media/platform/mediatek/vcodec/common/mtk_vcodec_fw_scp.c
+++ b/drivers/media/platform/mediatek/vcodec/common/mtk_vcodec_fw_scp.c
@@ -79,8 +79,11 @@ struct mtk_vcodec_fw *mtk_vcodec_fw_scp_init(void *priv, enum mtk_vcodec_fw_use
 	}
 
 	fw = devm_kzalloc(&plat_dev->dev, sizeof(*fw), GFP_KERNEL);
-	if (!fw)
+	if (!fw) {
+		scp_put(scp);
 		return ERR_PTR(-ENOMEM);
+	}
+
 	fw->type = SCP;
 	fw->ops = &mtk_vcodec_rproc_msg;
 	fw->scp = scp;
diff --git a/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_hevc_req_multi_if.c b/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_hevc_req_multi_if.c
index aa721cc43647..2725db882e5b 100644
--- a/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_hevc_req_multi_if.c
+++ b/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_hevc_req_multi_if.c
@@ -821,7 +821,7 @@ static int vdec_hevc_slice_setup_core_buffer(struct vdec_hevc_slice_inst *inst,
 	inst->vsi_core->fb.y.dma_addr = y_fb_dma;
 	inst->vsi_core->fb.y.size = ctx->picinfo.fb_sz[0];
 	inst->vsi_core->fb.c.dma_addr = c_fb_dma;
-	inst->vsi_core->fb.y.size = ctx->picinfo.fb_sz[1];
+	inst->vsi_core->fb.c.size = ctx->picinfo.fb_sz[1];
 
 	inst->vsi_core->dec.vdec_fb_va = (unsigned long)fb;
 
diff --git a/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_vp9_req_lat_if.c b/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_vp9_req_lat_if.c
index eea709d93820..47c302745c1d 100644
--- a/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_vp9_req_lat_if.c
+++ b/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_vp9_req_lat_if.c
@@ -1188,7 +1188,8 @@ err:
 	return ret;
 }
 
-static
+/* clang stack usage explodes if this is inlined */
+static noinline_for_stack
 void vdec_vp9_slice_map_counts_eob_coef(unsigned int i, unsigned int j, unsigned int k,
 					struct vdec_vp9_slice_frame_counts *counts,
 					struct v4l2_vp9_frame_symbol_counts *counts_helper)
diff --git a/drivers/media/platform/mediatek/vcodec/encoder/venc/venc_h264_if.c b/drivers/media/platform/mediatek/vcodec/encoder/venc/venc_h264_if.c
index f8145998fcaf..8522f71fc901 100644
--- a/drivers/media/platform/mediatek/vcodec/encoder/venc/venc_h264_if.c
+++ b/drivers/media/platform/mediatek/vcodec/encoder/venc/venc_h264_if.c
@@ -594,7 +594,11 @@ static int h264_enc_init(struct mtk_vcodec_enc_ctx *ctx)
 
 	inst->ctx = ctx;
 	inst->vpu_inst.ctx = ctx;
-	inst->vpu_inst.id = is_ext ? SCP_IPI_VENC_H264 : IPI_VENC_H264;
+	if (is_ext)
+		inst->vpu_inst.id = SCP_IPI_VENC_H264;
+	else
+		inst->vpu_inst.id = IPI_VENC_H264;
+
 	inst->hw_base = mtk_vcodec_get_reg_addr(inst->ctx->dev->reg_base, VENC_SYS);
 
 	ret = vpu_enc_init(&inst->vpu_inst);
diff --git a/drivers/media/platform/nuvoton/npcm-video.c b/drivers/media/platform/nuvoton/npcm-video.c
index 60fbb9140035..e0dee768a3be 100644
--- a/drivers/media/platform/nuvoton/npcm-video.c
+++ b/drivers/media/platform/nuvoton/npcm-video.c
@@ -1650,8 +1650,8 @@ rel_ctrl_handler:
 
 static int npcm_video_ece_init(struct npcm_video *video)
 {
+	struct device_node *ece_node __free(device_node) = NULL;
 	struct device *dev = video->dev;
-	struct device_node *ece_node;
 	struct platform_device *ece_pdev;
 	void __iomem *regs;
 
@@ -1667,11 +1667,11 @@ static int npcm_video_ece_init(struct npcm_video *video)
 		dev_info(dev, "Support HEXTILE pixel format\n");
 
 		ece_pdev = of_find_device_by_node(ece_node);
-		if (IS_ERR(ece_pdev)) {
+		if (!ece_pdev) {
 			dev_err(dev, "Failed to find ECE device\n");
-			return PTR_ERR(ece_pdev);
+			return -ENODEV;
 		}
-		of_node_put(ece_node);
+		struct device *ece_dev __free(put_device) = &ece_pdev->dev;
 
 		regs = devm_platform_ioremap_resource(ece_pdev, 0);
 		if (IS_ERR(regs)) {
@@ -1686,7 +1686,7 @@ static int npcm_video_ece_init(struct npcm_video *video)
 			return PTR_ERR(video->ece.regmap);
 		}
 
-		video->ece.reset = devm_reset_control_get(&ece_pdev->dev, NULL);
+		video->ece.reset = devm_reset_control_get(ece_dev, NULL);
 		if (IS_ERR(video->ece.reset)) {
 			dev_err(dev, "Failed to get ECE reset control in DTS\n");
 			return PTR_ERR(video->ece.reset);
diff --git a/drivers/media/platform/nxp/imx-jpeg/mxc-jpeg.c b/drivers/media/platform/nxp/imx-jpeg/mxc-jpeg.c
index 1bf85c1cf964..73be1013edd0 100644
--- a/drivers/media/platform/nxp/imx-jpeg/mxc-jpeg.c
+++ b/drivers/media/platform/nxp/imx-jpeg/mxc-jpeg.c
@@ -752,6 +752,32 @@ static int mxc_get_free_slot(struct mxc_jpeg_slot_data *slot_data)
 	return -1;
 }
 
+static void mxc_jpeg_free_slot_data(struct mxc_jpeg_dev *jpeg)
+{
+	/* free descriptor for decoding/encoding phase */
+	dma_free_coherent(jpeg->dev, sizeof(struct mxc_jpeg_desc),
+			  jpeg->slot_data.desc,
+			  jpeg->slot_data.desc_handle);
+	jpeg->slot_data.desc = NULL;
+	jpeg->slot_data.desc_handle = 0;
+
+	/* free descriptor for encoder configuration phase / decoder DHT */
+	dma_free_coherent(jpeg->dev, sizeof(struct mxc_jpeg_desc),
+			  jpeg->slot_data.cfg_desc,
+			  jpeg->slot_data.cfg_desc_handle);
+	jpeg->slot_data.cfg_desc_handle = 0;
+	jpeg->slot_data.cfg_desc = NULL;
+
+	/* free configuration stream */
+	dma_free_coherent(jpeg->dev, MXC_JPEG_MAX_CFG_STREAM,
+			  jpeg->slot_data.cfg_stream_vaddr,
+			  jpeg->slot_data.cfg_stream_handle);
+	jpeg->slot_data.cfg_stream_vaddr = NULL;
+	jpeg->slot_data.cfg_stream_handle = 0;
+
+	jpeg->slot_data.used = false;
+}
+
 static bool mxc_jpeg_alloc_slot_data(struct mxc_jpeg_dev *jpeg)
 {
 	struct mxc_jpeg_desc *desc;
@@ -794,30 +820,11 @@ skip_alloc:
 	return true;
 err:
 	dev_err(jpeg->dev, "Could not allocate descriptors for slot %d", jpeg->slot_data.slot);
+	mxc_jpeg_free_slot_data(jpeg);
 
 	return false;
 }
 
-static void mxc_jpeg_free_slot_data(struct mxc_jpeg_dev *jpeg)
-{
-	/* free descriptor for decoding/encoding phase */
-	dma_free_coherent(jpeg->dev, sizeof(struct mxc_jpeg_desc),
-			  jpeg->slot_data.desc,
-			  jpeg->slot_data.desc_handle);
-
-	/* free descriptor for encoder configuration phase / decoder DHT */
-	dma_free_coherent(jpeg->dev, sizeof(struct mxc_jpeg_desc),
-			  jpeg->slot_data.cfg_desc,
-			  jpeg->slot_data.cfg_desc_handle);
-
-	/* free configuration stream */
-	dma_free_coherent(jpeg->dev, MXC_JPEG_MAX_CFG_STREAM,
-			  jpeg->slot_data.cfg_stream_vaddr,
-			  jpeg->slot_data.cfg_stream_handle);
-
-	jpeg->slot_data.used = false;
-}
-
 static void mxc_jpeg_check_and_set_last_buffer(struct mxc_jpeg_ctx *ctx,
 					       struct vb2_v4l2_buffer *src_buf,
 					       struct vb2_v4l2_buffer *dst_buf)
@@ -1918,9 +1925,19 @@ static void mxc_jpeg_buf_queue(struct vb2_buffer *vb)
 	jpeg_src_buf = vb2_to_mxc_buf(vb);
 	jpeg_src_buf->jpeg_parse_error = false;
 	ret = mxc_jpeg_parse(ctx, vb);
-	if (ret)
+	if (ret) {
 		jpeg_src_buf->jpeg_parse_error = true;
 
+		/*
+		 * if the capture queue is not setup, the device_run() won't be scheduled,
+		 * need to drop the error buffer, so that the decoding can continue
+		 */
+		if (!vb2_is_streaming(v4l2_m2m_get_dst_vq(ctx->fh.m2m_ctx))) {
+			v4l2_m2m_buf_done(vbuf, VB2_BUF_STATE_ERROR);
+			return;
+		}
+	}
+
 end:
 	v4l2_m2m_buf_queue(ctx->fh.m2m_ctx, vbuf);
 }
@@ -2679,11 +2696,12 @@ static void mxc_jpeg_detach_pm_domains(struct mxc_jpeg_dev *jpeg)
 	int i;
 
 	for (i = 0; i < jpeg->num_domains; i++) {
-		if (jpeg->pd_dev[i] && !pm_runtime_suspended(jpeg->pd_dev[i]))
+		if (!IS_ERR_OR_NULL(jpeg->pd_dev[i]) &&
+		    !pm_runtime_suspended(jpeg->pd_dev[i]))
 			pm_runtime_force_suspend(jpeg->pd_dev[i]);
-		if (jpeg->pd_link[i] && !IS_ERR(jpeg->pd_link[i]))
+		if (!IS_ERR_OR_NULL(jpeg->pd_link[i]))
 			device_link_del(jpeg->pd_link[i]);
-		if (jpeg->pd_dev[i] && !IS_ERR(jpeg->pd_dev[i]))
+		if (!IS_ERR_OR_NULL(jpeg->pd_dev[i]))
 			dev_pm_domain_detach(jpeg->pd_dev[i], true);
 		jpeg->pd_dev[i] = NULL;
 		jpeg->pd_link[i] = NULL;
diff --git a/drivers/media/platform/nxp/imx8-isi/imx8-isi-m2m.c b/drivers/media/platform/nxp/imx8-isi/imx8-isi-m2m.c
index 9745d6219a16..cd6c52e9d158 100644
--- a/drivers/media/platform/nxp/imx8-isi/imx8-isi-m2m.c
+++ b/drivers/media/platform/nxp/imx8-isi/imx8-isi-m2m.c
@@ -43,6 +43,7 @@ struct mxc_isi_m2m_ctx_queue_data {
 	struct v4l2_pix_format_mplane format;
 	const struct mxc_isi_format_info *info;
 	u32 sequence;
+	bool streaming;
 };
 
 struct mxc_isi_m2m_ctx {
@@ -486,15 +487,18 @@ static int mxc_isi_m2m_streamon(struct file *file, void *fh,
 				enum v4l2_buf_type type)
 {
 	struct mxc_isi_m2m_ctx *ctx = to_isi_m2m_ctx(fh);
+	struct mxc_isi_m2m_ctx_queue_data *q = mxc_isi_m2m_ctx_qdata(ctx, type);
 	const struct v4l2_pix_format_mplane *out_pix = &ctx->queues.out.format;
 	const struct v4l2_pix_format_mplane *cap_pix = &ctx->queues.cap.format;
 	const struct mxc_isi_format_info *cap_info = ctx->queues.cap.info;
 	const struct mxc_isi_format_info *out_info = ctx->queues.out.info;
 	struct mxc_isi_m2m *m2m = ctx->m2m;
 	bool bypass;
-
 	int ret;
 
+	if (q->streaming)
+		return 0;
+
 	mutex_lock(&m2m->lock);
 
 	if (m2m->usage_count == INT_MAX) {
@@ -547,6 +551,8 @@ static int mxc_isi_m2m_streamon(struct file *file, void *fh,
 		goto unchain;
 	}
 
+	q->streaming = true;
+
 	return 0;
 
 unchain:
@@ -569,10 +575,14 @@ static int mxc_isi_m2m_streamoff(struct file *file, void *fh,
 				 enum v4l2_buf_type type)
 {
 	struct mxc_isi_m2m_ctx *ctx = to_isi_m2m_ctx(fh);
+	struct mxc_isi_m2m_ctx_queue_data *q = mxc_isi_m2m_ctx_qdata(ctx, type);
 	struct mxc_isi_m2m *m2m = ctx->m2m;
 
 	v4l2_m2m_ioctl_streamoff(file, fh, type);
 
+	if (!q->streaming)
+		return 0;
+
 	mutex_lock(&m2m->lock);
 
 	/*
@@ -598,6 +608,8 @@ static int mxc_isi_m2m_streamoff(struct file *file, void *fh,
 
 	mutex_unlock(&m2m->lock);
 
+	q->streaming = false;
+
 	return 0;
 }
 
diff --git a/drivers/media/platform/nxp/imx8-isi/imx8-isi-video.c b/drivers/media/platform/nxp/imx8-isi/imx8-isi-video.c
index 4091f1c0e78b..a71eb30323c8 100644
--- a/drivers/media/platform/nxp/imx8-isi/imx8-isi-video.c
+++ b/drivers/media/platform/nxp/imx8-isi/imx8-isi-video.c
@@ -861,6 +861,7 @@ int mxc_isi_video_buffer_prepare(struct mxc_isi_dev *isi, struct vb2_buffer *vb2
 				 const struct mxc_isi_format_info *info,
 				 const struct v4l2_pix_format_mplane *pix)
 {
+	struct vb2_v4l2_buffer *v4l2_buf = to_vb2_v4l2_buffer(vb2);
 	unsigned int i;
 
 	for (i = 0; i < info->mem_planes; i++) {
@@ -875,6 +876,8 @@ int mxc_isi_video_buffer_prepare(struct mxc_isi_dev *isi, struct vb2_buffer *vb2
 		vb2_set_plane_payload(vb2, i, size);
 	}
 
+	v4l2_buf->field = pix->field;
+
 	return 0;
 }
 
diff --git a/drivers/media/platform/qcom/camss/camss-csid.c b/drivers/media/platform/qcom/camss/camss-csid.c
index 858db5d4ca75..e51f2ed3f031 100644
--- a/drivers/media/platform/qcom/camss/camss-csid.c
+++ b/drivers/media/platform/qcom/camss/camss-csid.c
@@ -683,11 +683,13 @@ static int csid_set_stream(struct v4l2_subdev *sd, int enable)
 	int ret;
 
 	if (enable) {
-		ret = v4l2_ctrl_handler_setup(&csid->ctrls);
-		if (ret < 0) {
-			dev_err(csid->camss->dev,
-				"could not sync v4l2 controls: %d\n", ret);
-			return ret;
+		if (csid->testgen.nmodes != CSID_PAYLOAD_MODE_DISABLED) {
+			ret = v4l2_ctrl_handler_setup(&csid->ctrls);
+			if (ret < 0) {
+				dev_err(csid->camss->dev,
+					"could not sync v4l2 controls: %d\n", ret);
+				return ret;
+			}
 		}
 
 		if (!csid->testgen.enabled &&
@@ -761,7 +763,8 @@ static void csid_try_format(struct csid_device *csid,
 		break;
 
 	case MSM_CSID_PAD_SRC:
-		if (csid->testgen_mode->cur.val == 0) {
+		if (csid->testgen.nmodes == CSID_PAYLOAD_MODE_DISABLED ||
+		    csid->testgen_mode->cur.val == 0) {
 			/* Test generator is disabled, */
 			/* keep pad formats in sync */
 			u32 code = fmt->code;
@@ -811,7 +814,8 @@ static int csid_enum_mbus_code(struct v4l2_subdev *sd,
 
 		code->code = csid->res->formats->formats[code->index].code;
 	} else {
-		if (csid->testgen_mode->cur.val == 0) {
+		if (csid->testgen.nmodes == CSID_PAYLOAD_MODE_DISABLED ||
+		    csid->testgen_mode->cur.val == 0) {
 			struct v4l2_mbus_framefmt *sink_fmt;
 
 			sink_fmt = __csid_get_format(csid, sd_state,
@@ -1190,7 +1194,8 @@ static int csid_link_setup(struct media_entity *entity,
 
 		/* If test generator is enabled */
 		/* do not allow a link from CSIPHY to CSID */
-		if (csid->testgen_mode->cur.val != 0)
+		if (csid->testgen.nmodes != CSID_PAYLOAD_MODE_DISABLED &&
+		    csid->testgen_mode->cur.val != 0)
 			return -EBUSY;
 
 		sd = media_entity_to_v4l2_subdev(remote->entity);
@@ -1283,24 +1288,27 @@ int msm_csid_register_entity(struct csid_device *csid,
 		 MSM_CSID_NAME, csid->id);
 	v4l2_set_subdevdata(sd, csid);
 
-	ret = v4l2_ctrl_handler_init(&csid->ctrls, 1);
-	if (ret < 0) {
-		dev_err(dev, "Failed to init ctrl handler: %d\n", ret);
-		return ret;
-	}
+	if (csid->testgen.nmodes != CSID_PAYLOAD_MODE_DISABLED) {
+		ret = v4l2_ctrl_handler_init(&csid->ctrls, 1);
+		if (ret < 0) {
+			dev_err(dev, "Failed to init ctrl handler: %d\n", ret);
+			return ret;
+		}
 
-	csid->testgen_mode = v4l2_ctrl_new_std_menu_items(&csid->ctrls,
-				&csid_ctrl_ops, V4L2_CID_TEST_PATTERN,
-				csid->testgen.nmodes, 0, 0,
-				csid->testgen.modes);
+		csid->testgen_mode =
+			v4l2_ctrl_new_std_menu_items(&csid->ctrls,
+						     &csid_ctrl_ops, V4L2_CID_TEST_PATTERN,
+						     csid->testgen.nmodes, 0, 0,
+						     csid->testgen.modes);
 
-	if (csid->ctrls.error) {
-		dev_err(dev, "Failed to init ctrl: %d\n", csid->ctrls.error);
-		ret = csid->ctrls.error;
-		goto free_ctrl;
-	}
+		if (csid->ctrls.error) {
+			dev_err(dev, "Failed to init ctrl: %d\n", csid->ctrls.error);
+			ret = csid->ctrls.error;
+			goto free_ctrl;
+		}
 
-	csid->subdev.ctrl_handler = &csid->ctrls;
+		csid->subdev.ctrl_handler = &csid->ctrls;
+	}
 
 	ret = csid_init_formats(sd, NULL);
 	if (ret < 0) {
@@ -1331,7 +1339,8 @@ int msm_csid_register_entity(struct csid_device *csid,
 media_cleanup:
 	media_entity_cleanup(&sd->entity);
 free_ctrl:
-	v4l2_ctrl_handler_free(&csid->ctrls);
+	if (csid->testgen.nmodes != CSID_PAYLOAD_MODE_DISABLED)
+		v4l2_ctrl_handler_free(&csid->ctrls);
 
 	return ret;
 }
@@ -1344,7 +1353,8 @@ void msm_csid_unregister_entity(struct csid_device *csid)
 {
 	v4l2_device_unregister_subdev(&csid->subdev);
 	media_entity_cleanup(&csid->subdev.entity);
-	v4l2_ctrl_handler_free(&csid->ctrls);
+	if (csid->testgen.nmodes != CSID_PAYLOAD_MODE_DISABLED)
+		v4l2_ctrl_handler_free(&csid->ctrls);
 }
 
 inline bool csid_is_lite(struct csid_device *csid)
diff --git a/drivers/media/platform/qcom/camss/camss-vfe.c b/drivers/media/platform/qcom/camss/camss-vfe.c
index 83c5a36d071f..8f6b0eccefb4 100644
--- a/drivers/media/platform/qcom/camss/camss-vfe.c
+++ b/drivers/media/platform/qcom/camss/camss-vfe.c
@@ -398,6 +398,10 @@ static u32 vfe_src_pad_code(struct vfe_line *line, u32 sink_code,
 			return sink_code;
 		}
 		break;
+	default:
+		WARN(1, "Unsupported HW version: %x\n",
+		     vfe->camss->res->version);
+		break;
 	}
 	return 0;
 }
diff --git a/drivers/media/platform/qcom/venus/core.c b/drivers/media/platform/qcom/venus/core.c
index cabcf710c046..4d10e94eefe9 100644
--- a/drivers/media/platform/qcom/venus/core.c
+++ b/drivers/media/platform/qcom/venus/core.c
@@ -354,7 +354,7 @@ static int venus_probe(struct platform_device *pdev)
 
 	ret = v4l2_device_register(dev, &core->v4l2_dev);
 	if (ret)
-		goto err_core_deinit;
+		goto err_hfi_destroy;
 
 	platform_set_drvdata(pdev, core);
 
@@ -386,24 +386,24 @@ static int venus_probe(struct platform_device *pdev)
 
 	ret = venus_enumerate_codecs(core, VIDC_SESSION_TYPE_DEC);
 	if (ret)
-		goto err_venus_shutdown;
+		goto err_core_deinit;
 
 	ret = venus_enumerate_codecs(core, VIDC_SESSION_TYPE_ENC);
 	if (ret)
-		goto err_venus_shutdown;
+		goto err_core_deinit;
 
 	ret = pm_runtime_put_sync(dev);
 	if (ret) {
 		pm_runtime_get_noresume(dev);
-		goto err_dev_unregister;
+		goto err_core_deinit;
 	}
 
 	venus_dbgfs_init(core);
 
 	return 0;
 
-err_dev_unregister:
-	v4l2_device_unregister(&core->v4l2_dev);
+err_core_deinit:
+	hfi_core_deinit(core, false);
 err_venus_shutdown:
 	venus_shutdown(core);
 err_firmware_deinit:
@@ -414,9 +414,9 @@ err_runtime_disable:
 	pm_runtime_put_noidle(dev);
 	pm_runtime_disable(dev);
 	pm_runtime_set_suspended(dev);
+	v4l2_device_unregister(&core->v4l2_dev);
+err_hfi_destroy:
 	hfi_destroy(core);
-err_core_deinit:
-	hfi_core_deinit(core, false);
 err_core_put:
 	if (core->pm_ops->core_put)
 		core->pm_ops->core_put(core);
diff --git a/drivers/media/platform/qcom/venus/hfi_msgs.c b/drivers/media/platform/qcom/venus/hfi_msgs.c
index 0a041b4db9ef..cf0d97cbc463 100644
--- a/drivers/media/platform/qcom/venus/hfi_msgs.c
+++ b/drivers/media/platform/qcom/venus/hfi_msgs.c
@@ -33,8 +33,9 @@ static void event_seq_changed(struct venus_core *core, struct venus_inst *inst,
 	struct hfi_buffer_requirements *bufreq;
 	struct hfi_extradata_input_crop *crop;
 	struct hfi_dpb_counts *dpb_count;
+	u32 ptype, rem_bytes;
+	u32 size_read = 0;
 	u8 *data_ptr;
-	u32 ptype;
 
 	inst->error = HFI_ERR_NONE;
 
@@ -44,86 +45,118 @@ static void event_seq_changed(struct venus_core *core, struct venus_inst *inst,
 		break;
 	default:
 		inst->error = HFI_ERR_SESSION_INVALID_PARAMETER;
-		goto done;
+		inst->ops->event_notify(inst, EVT_SYS_EVENT_CHANGE, &event);
+		return;
 	}
 
 	event.event_type = pkt->event_data1;
 
 	num_properties_changed = pkt->event_data2;
-	if (!num_properties_changed) {
-		inst->error = HFI_ERR_SESSION_INSUFFICIENT_RESOURCES;
-		goto done;
-	}
+	if (!num_properties_changed)
+		goto error;
 
 	data_ptr = (u8 *)&pkt->ext_event_data[0];
+	rem_bytes = pkt->shdr.hdr.size - sizeof(*pkt);
+
 	do {
+		if (rem_bytes < sizeof(u32))
+			goto error;
 		ptype = *((u32 *)data_ptr);
+
+		data_ptr += sizeof(u32);
+		rem_bytes -= sizeof(u32);
+
 		switch (ptype) {
 		case HFI_PROPERTY_PARAM_FRAME_SIZE:
-			data_ptr += sizeof(u32);
+			if (rem_bytes < sizeof(struct hfi_framesize))
+				goto error;
+
 			frame_sz = (struct hfi_framesize *)data_ptr;
 			event.width = frame_sz->width;
 			event.height = frame_sz->height;
-			data_ptr += sizeof(*frame_sz);
+			size_read = sizeof(struct hfi_framesize);
 			break;
 		case HFI_PROPERTY_PARAM_PROFILE_LEVEL_CURRENT:
-			data_ptr += sizeof(u32);
+			if (rem_bytes < sizeof(struct hfi_profile_level))
+				goto error;
+
 			profile_level = (struct hfi_profile_level *)data_ptr;
 			event.profile = profile_level->profile;
 			event.level = profile_level->level;
-			data_ptr += sizeof(*profile_level);
+			size_read = sizeof(struct hfi_profile_level);
 			break;
 		case HFI_PROPERTY_PARAM_VDEC_PIXEL_BITDEPTH:
-			data_ptr += sizeof(u32);
+			if (rem_bytes < sizeof(struct hfi_bit_depth))
+				goto error;
+
 			pixel_depth = (struct hfi_bit_depth *)data_ptr;
 			event.bit_depth = pixel_depth->bit_depth;
-			data_ptr += sizeof(*pixel_depth);
+			size_read = sizeof(struct hfi_bit_depth);
 			break;
 		case HFI_PROPERTY_PARAM_VDEC_PIC_STRUCT:
-			data_ptr += sizeof(u32);
+			if (rem_bytes < sizeof(struct hfi_pic_struct))
+				goto error;
+
 			pic_struct = (struct hfi_pic_struct *)data_ptr;
 			event.pic_struct = pic_struct->progressive_only;
-			data_ptr += sizeof(*pic_struct);
+			size_read = sizeof(struct hfi_pic_struct);
 			break;
 		case HFI_PROPERTY_PARAM_VDEC_COLOUR_SPACE:
-			data_ptr += sizeof(u32);
+			if (rem_bytes < sizeof(struct hfi_colour_space))
+				goto error;
+
 			colour_info = (struct hfi_colour_space *)data_ptr;
 			event.colour_space = colour_info->colour_space;
-			data_ptr += sizeof(*colour_info);
+			size_read = sizeof(struct hfi_colour_space);
 			break;
 		case HFI_PROPERTY_CONFIG_VDEC_ENTROPY:
-			data_ptr += sizeof(u32);
+			if (rem_bytes < sizeof(u32))
+				goto error;
+
 			event.entropy_mode = *(u32 *)data_ptr;
-			data_ptr += sizeof(u32);
+			size_read = sizeof(u32);
 			break;
 		case HFI_PROPERTY_CONFIG_BUFFER_REQUIREMENTS:
-			data_ptr += sizeof(u32);
+			if (rem_bytes < sizeof(struct hfi_buffer_requirements))
+				goto error;
+
 			bufreq = (struct hfi_buffer_requirements *)data_ptr;
 			event.buf_count = hfi_bufreq_get_count_min(bufreq, ver);
-			data_ptr += sizeof(*bufreq);
+			size_read = sizeof(struct hfi_buffer_requirements);
 			break;
 		case HFI_INDEX_EXTRADATA_INPUT_CROP:
-			data_ptr += sizeof(u32);
+			if (rem_bytes < sizeof(struct hfi_extradata_input_crop))
+				goto error;
+
 			crop = (struct hfi_extradata_input_crop *)data_ptr;
 			event.input_crop.left = crop->left;
 			event.input_crop.top = crop->top;
 			event.input_crop.width = crop->width;
 			event.input_crop.height = crop->height;
-			data_ptr += sizeof(*crop);
+			size_read = sizeof(struct hfi_extradata_input_crop);
 			break;
 		case HFI_PROPERTY_PARAM_VDEC_DPB_COUNTS:
-			data_ptr += sizeof(u32);
+			if (rem_bytes < sizeof(struct hfi_dpb_counts))
+				goto error;
+
 			dpb_count = (struct hfi_dpb_counts *)data_ptr;
 			event.buf_count = dpb_count->fw_min_cnt;
-			data_ptr += sizeof(*dpb_count);
+			size_read = sizeof(struct hfi_dpb_counts);
 			break;
 		default:
+			size_read = 0;
 			break;
 		}
+		data_ptr += size_read;
+		rem_bytes -= size_read;
 		num_properties_changed--;
 	} while (num_properties_changed > 0);
 
-done:
+	inst->ops->event_notify(inst, EVT_SYS_EVENT_CHANGE, &event);
+	return;
+
+error:
+	inst->error = HFI_ERR_SESSION_INSUFFICIENT_RESOURCES;
 	inst->ops->event_notify(inst, EVT_SYS_EVENT_CHANGE, &event);
 }
 
diff --git a/drivers/media/platform/qcom/venus/hfi_parser.c b/drivers/media/platform/qcom/venus/hfi_parser.c
index 3df241dc3a11..1b3db2caa99f 100644
--- a/drivers/media/platform/qcom/venus/hfi_parser.c
+++ b/drivers/media/platform/qcom/venus/hfi_parser.c
@@ -19,6 +19,8 @@ static void init_codecs(struct venus_core *core)
 	struct hfi_plat_caps *caps = core->caps, *cap;
 	unsigned long bit;
 
+	core->codecs_count = 0;
+
 	if (hweight_long(core->dec_codecs) + hweight_long(core->enc_codecs) > MAX_CODEC_NUM)
 		return;
 
@@ -62,7 +64,7 @@ fill_buf_mode(struct hfi_plat_caps *cap, const void *data, unsigned int num)
 		cap->cap_bufs_mode_dynamic = true;
 }
 
-static void
+static int
 parse_alloc_mode(struct venus_core *core, u32 codecs, u32 domain, void *data)
 {
 	struct hfi_buffer_alloc_mode_supported *mode = data;
@@ -70,7 +72,7 @@ parse_alloc_mode(struct venus_core *core, u32 codecs, u32 domain, void *data)
 	u32 *type;
 
 	if (num_entries > MAX_ALLOC_MODE_ENTRIES)
-		return;
+		return -EINVAL;
 
 	type = mode->data;
 
@@ -82,6 +84,8 @@ parse_alloc_mode(struct venus_core *core, u32 codecs, u32 domain, void *data)
 
 		type++;
 	}
+
+	return sizeof(*mode);
 }
 
 static void fill_profile_level(struct hfi_plat_caps *cap, const void *data,
@@ -96,7 +100,7 @@ static void fill_profile_level(struct hfi_plat_caps *cap, const void *data,
 	cap->num_pl += num;
 }
 
-static void
+static int
 parse_profile_level(struct venus_core *core, u32 codecs, u32 domain, void *data)
 {
 	struct hfi_profile_level_supported *pl = data;
@@ -104,12 +108,14 @@ parse_profile_level(struct venus_core *core, u32 codecs, u32 domain, void *data)
 	struct hfi_profile_level pl_arr[HFI_MAX_PROFILE_COUNT] = {};
 
 	if (pl->profile_count > HFI_MAX_PROFILE_COUNT)
-		return;
+		return -EINVAL;
 
 	memcpy(pl_arr, proflevel, pl->profile_count * sizeof(*proflevel));
 
 	for_each_codec(core->caps, ARRAY_SIZE(core->caps), codecs, domain,
 		       fill_profile_level, pl_arr, pl->profile_count);
+
+	return pl->profile_count * sizeof(*proflevel) + sizeof(u32);
 }
 
 static void
@@ -124,7 +130,7 @@ fill_caps(struct hfi_plat_caps *cap, const void *data, unsigned int num)
 	cap->num_caps += num;
 }
 
-static void
+static int
 parse_caps(struct venus_core *core, u32 codecs, u32 domain, void *data)
 {
 	struct hfi_capabilities *caps = data;
@@ -133,12 +139,14 @@ parse_caps(struct venus_core *core, u32 codecs, u32 domain, void *data)
 	struct hfi_capability caps_arr[MAX_CAP_ENTRIES] = {};
 
 	if (num_caps > MAX_CAP_ENTRIES)
-		return;
+		return -EINVAL;
 
 	memcpy(caps_arr, cap, num_caps * sizeof(*cap));
 
 	for_each_codec(core->caps, ARRAY_SIZE(core->caps), codecs, domain,
 		       fill_caps, caps_arr, num_caps);
+
+	return sizeof(*caps);
 }
 
 static void fill_raw_fmts(struct hfi_plat_caps *cap, const void *fmts,
@@ -153,7 +161,7 @@ static void fill_raw_fmts(struct hfi_plat_caps *cap, const void *fmts,
 	cap->num_fmts += num_fmts;
 }
 
-static void
+static int
 parse_raw_formats(struct venus_core *core, u32 codecs, u32 domain, void *data)
 {
 	struct hfi_uncompressed_format_supported *fmt = data;
@@ -162,7 +170,8 @@ parse_raw_formats(struct venus_core *core, u32 codecs, u32 domain, void *data)
 	struct raw_formats rawfmts[MAX_FMT_ENTRIES] = {};
 	u32 entries = fmt->format_entries;
 	unsigned int i = 0;
-	u32 num_planes;
+	u32 num_planes = 0;
+	u32 size;
 
 	while (entries) {
 		num_planes = pinfo->num_planes;
@@ -172,7 +181,7 @@ parse_raw_formats(struct venus_core *core, u32 codecs, u32 domain, void *data)
 		i++;
 
 		if (i >= MAX_FMT_ENTRIES)
-			return;
+			return -EINVAL;
 
 		if (pinfo->num_planes > MAX_PLANES)
 			break;
@@ -184,9 +193,13 @@ parse_raw_formats(struct venus_core *core, u32 codecs, u32 domain, void *data)
 
 	for_each_codec(core->caps, ARRAY_SIZE(core->caps), codecs, domain,
 		       fill_raw_fmts, rawfmts, i);
+	size = fmt->format_entries * (sizeof(*constr) * num_planes + 2 * sizeof(u32))
+		+ 2 * sizeof(u32);
+
+	return size;
 }
 
-static void parse_codecs(struct venus_core *core, void *data)
+static int parse_codecs(struct venus_core *core, void *data)
 {
 	struct hfi_codec_supported *codecs = data;
 
@@ -198,21 +211,27 @@ static void parse_codecs(struct venus_core *core, void *data)
 		core->dec_codecs &= ~HFI_VIDEO_CODEC_SPARK;
 		core->enc_codecs &= ~HFI_VIDEO_CODEC_HEVC;
 	}
+
+	return sizeof(*codecs);
 }
 
-static void parse_max_sessions(struct venus_core *core, const void *data)
+static int parse_max_sessions(struct venus_core *core, const void *data)
 {
 	const struct hfi_max_sessions_supported *sessions = data;
 
 	core->max_sessions_supported = sessions->max_sessions;
+
+	return sizeof(*sessions);
 }
 
-static void parse_codecs_mask(u32 *codecs, u32 *domain, void *data)
+static int parse_codecs_mask(u32 *codecs, u32 *domain, void *data)
 {
 	struct hfi_codec_mask_supported *mask = data;
 
 	*codecs = mask->codecs;
 	*domain = mask->video_domains;
+
+	return sizeof(*mask);
 }
 
 static void parser_init(struct venus_inst *inst, u32 *codecs, u32 *domain)
@@ -281,8 +300,9 @@ static int hfi_platform_parser(struct venus_core *core, struct venus_inst *inst)
 u32 hfi_parser(struct venus_core *core, struct venus_inst *inst, void *buf,
 	       u32 size)
 {
-	unsigned int words_count = size >> 2;
-	u32 *word = buf, *data, codecs = 0, domain = 0;
+	u32 *words = buf, *payload, codecs = 0, domain = 0;
+	u32 *frame_size = buf + size;
+	u32 rem_bytes = size;
 	int ret;
 
 	ret = hfi_platform_parser(core, inst);
@@ -299,38 +319,66 @@ u32 hfi_parser(struct venus_core *core, struct venus_inst *inst, void *buf,
 		memset(core->caps, 0, sizeof(core->caps));
 	}
 
-	while (words_count) {
-		data = word + 1;
+	while (words < frame_size) {
+		payload = words + 1;
 
-		switch (*word) {
+		switch (*words) {
 		case HFI_PROPERTY_PARAM_CODEC_SUPPORTED:
-			parse_codecs(core, data);
+			if (rem_bytes <= sizeof(struct hfi_codec_supported))
+				return HFI_ERR_SYS_INSUFFICIENT_RESOURCES;
+
+			ret = parse_codecs(core, payload);
+			if (ret < 0)
+				return HFI_ERR_SYS_INSUFFICIENT_RESOURCES;
+
 			init_codecs(core);
 			break;
 		case HFI_PROPERTY_PARAM_MAX_SESSIONS_SUPPORTED:
-			parse_max_sessions(core, data);
+			if (rem_bytes <= sizeof(struct hfi_max_sessions_supported))
+				return HFI_ERR_SYS_INSUFFICIENT_RESOURCES;
+
+			ret = parse_max_sessions(core, payload);
 			break;
 		case HFI_PROPERTY_PARAM_CODEC_MASK_SUPPORTED:
-			parse_codecs_mask(&codecs, &domain, data);
+			if (rem_bytes <= sizeof(struct hfi_codec_mask_supported))
+				return HFI_ERR_SYS_INSUFFICIENT_RESOURCES;
+
+			ret = parse_codecs_mask(&codecs, &domain, payload);
 			break;
 		case HFI_PROPERTY_PARAM_UNCOMPRESSED_FORMAT_SUPPORTED:
-			parse_raw_formats(core, codecs, domain, data);
+			if (rem_bytes <= sizeof(struct hfi_uncompressed_format_supported))
+				return HFI_ERR_SYS_INSUFFICIENT_RESOURCES;
+
+			ret = parse_raw_formats(core, codecs, domain, payload);
 			break;
 		case HFI_PROPERTY_PARAM_CAPABILITY_SUPPORTED:
-			parse_caps(core, codecs, domain, data);
+			if (rem_bytes <= sizeof(struct hfi_capabilities))
+				return HFI_ERR_SYS_INSUFFICIENT_RESOURCES;
+
+			ret = parse_caps(core, codecs, domain, payload);
 			break;
 		case HFI_PROPERTY_PARAM_PROFILE_LEVEL_SUPPORTED:
-			parse_profile_level(core, codecs, domain, data);
+			if (rem_bytes <= sizeof(struct hfi_profile_level_supported))
+				return HFI_ERR_SYS_INSUFFICIENT_RESOURCES;
+
+			ret = parse_profile_level(core, codecs, domain, payload);
 			break;
 		case HFI_PROPERTY_PARAM_BUFFER_ALLOC_MODE_SUPPORTED:
-			parse_alloc_mode(core, codecs, domain, data);
+			if (rem_bytes <= sizeof(struct hfi_buffer_alloc_mode_supported))
+				return HFI_ERR_SYS_INSUFFICIENT_RESOURCES;
+
+			ret = parse_alloc_mode(core, codecs, domain, payload);
 			break;
 		default:
+			ret = sizeof(u32);
 			break;
 		}
 
-		word++;
-		words_count--;
+		if (ret < 0)
+			return HFI_ERR_SYS_INSUFFICIENT_RESOURCES;
+
+		words += ret / sizeof(u32);
+		rem_bytes -= ret;
 	}
 
 	if (!core->max_sessions_supported)
diff --git a/drivers/media/platform/qcom/venus/hfi_venus.c b/drivers/media/platform/qcom/venus/hfi_venus.c
index f9437b6412b9..ab93757fff4b 100644
--- a/drivers/media/platform/qcom/venus/hfi_venus.c
+++ b/drivers/media/platform/qcom/venus/hfi_venus.c
@@ -187,6 +187,9 @@ static int venus_write_queue(struct venus_hfi_device *hdev,
 	/* ensure rd/wr indices's are read from memory */
 	rmb();
 
+	if (qsize > IFACEQ_QUEUE_SIZE / 4)
+		return -EINVAL;
+
 	if (wr_idx >= rd_idx)
 		empty_space = qsize - (wr_idx - rd_idx);
 	else
@@ -255,6 +258,9 @@ static int venus_read_queue(struct venus_hfi_device *hdev,
 	wr_idx = qhdr->write_idx;
 	qsize = qhdr->q_size;
 
+	if (qsize > IFACEQ_QUEUE_SIZE / 4)
+		return -EINVAL;
+
 	/* make sure data is valid before using it */
 	rmb();
 
@@ -1035,18 +1041,26 @@ static void venus_sfr_print(struct venus_hfi_device *hdev)
 {
 	struct device *dev = hdev->core->dev;
 	struct hfi_sfr *sfr = hdev->sfr.kva;
+	u32 size;
 	void *p;
 
 	if (!sfr)
 		return;
 
-	p = memchr(sfr->data, '\0', sfr->buf_size);
+	size = sfr->buf_size;
+	if (!size)
+		return;
+
+	if (size > ALIGNED_SFR_SIZE)
+		size = ALIGNED_SFR_SIZE;
+
+	p = memchr(sfr->data, '\0', size);
 	/*
 	 * SFR isn't guaranteed to be NULL terminated since SYS_ERROR indicates
 	 * that Venus is in the process of crashing.
 	 */
 	if (!p)
-		sfr->data[sfr->buf_size - 1] = '\0';
+		sfr->data[size - 1] = '\0';
 
 	dev_err_ratelimited(dev, "SFR message from FW: %s\n", sfr->data);
 }
diff --git a/drivers/media/platform/rockchip/rga/rga-hw.c b/drivers/media/platform/rockchip/rga/rga-hw.c
index 11c3d7234757..b2ef3beec525 100644
--- a/drivers/media/platform/rockchip/rga/rga-hw.c
+++ b/drivers/media/platform/rockchip/rga/rga-hw.c
@@ -376,7 +376,7 @@ static void rga_cmd_set_dst_info(struct rga_ctx *ctx,
 	 * Configure the dest framebuffer base address with pixel offset.
 	 */
 	offsets = rga_get_addr_offset(&ctx->out, offset, dst_x, dst_y, dst_w, dst_h);
-	dst_offset = rga_lookup_draw_pos(&offsets, mir_mode, rot_mode);
+	dst_offset = rga_lookup_draw_pos(&offsets, rot_mode, mir_mode);
 
 	dest[(RGA_DST_Y_RGB_BASE_ADDR - RGA_MODE_BASE_REG) >> 2] =
 		dst_offset->y_off;
diff --git a/drivers/media/platform/samsung/exynos4-is/mipi-csis.c b/drivers/media/platform/samsung/exynos4-is/mipi-csis.c
index 4b9b20ba3504..38c5f22b850b 100644
--- a/drivers/media/platform/samsung/exynos4-is/mipi-csis.c
+++ b/drivers/media/platform/samsung/exynos4-is/mipi-csis.c
@@ -940,13 +940,19 @@ static int s5pcsis_pm_resume(struct device *dev, bool runtime)
 					       state->supplies);
 			goto unlock;
 		}
-		clk_enable(state->clock[CSIS_CLK_GATE]);
+		ret = clk_enable(state->clock[CSIS_CLK_GATE]);
+		if (ret) {
+			phy_power_off(state->phy);
+			regulator_bulk_disable(CSIS_NUM_SUPPLIES,
+					       state->supplies);
+			goto unlock;
+		}
 	}
 	if (state->flags & ST_STREAMING)
 		s5pcsis_start_stream(state);
 
 	state->flags &= ~ST_SUSPENDED;
- unlock:
+unlock:
 	mutex_unlock(&state->lock);
 	return ret ? -EAGAIN : 0;
 }
diff --git a/drivers/media/platform/samsung/s3c-camif/camif-core.c b/drivers/media/platform/samsung/s3c-camif/camif-core.c
index e4529f666e20..8c597dd01713 100644
--- a/drivers/media/platform/samsung/s3c-camif/camif-core.c
+++ b/drivers/media/platform/samsung/s3c-camif/camif-core.c
@@ -527,10 +527,19 @@ static void s3c_camif_remove(struct platform_device *pdev)
 static int s3c_camif_runtime_resume(struct device *dev)
 {
 	struct camif_dev *camif = dev_get_drvdata(dev);
+	int ret;
+
+	ret = clk_enable(camif->clock[CLK_GATE]);
+	if (ret)
+		return ret;
 
-	clk_enable(camif->clock[CLK_GATE]);
 	/* null op on s3c244x */
-	clk_enable(camif->clock[CLK_CAM]);
+	ret = clk_enable(camif->clock[CLK_CAM]);
+	if (ret) {
+		clk_disable(camif->clock[CLK_GATE]);
+		return ret;
+	}
+
 	return 0;
 }
 
diff --git a/drivers/media/platform/samsung/s5p-mfc/s5p_mfc_opr_v6.c b/drivers/media/platform/samsung/s5p-mfc/s5p_mfc_opr_v6.c
index 73f7af674c01..0c636090d723 100644
--- a/drivers/media/platform/samsung/s5p-mfc/s5p_mfc_opr_v6.c
+++ b/drivers/media/platform/samsung/s5p-mfc/s5p_mfc_opr_v6.c
@@ -549,8 +549,9 @@ static void s5p_mfc_enc_calc_src_size_v6(struct s5p_mfc_ctx *ctx)
 		case V4L2_PIX_FMT_NV21M:
 			ctx->stride[0] = ALIGN(ctx->img_width, S5P_FIMV_NV12M_HALIGN_V6);
 			ctx->stride[1] = ALIGN(ctx->img_width, S5P_FIMV_NV12M_HALIGN_V6);
-			ctx->luma_size = ctx->stride[0] * ALIGN(ctx->img_height, 16);
-			ctx->chroma_size =  ctx->stride[0] * ALIGN(ctx->img_height / 2, 16);
+			ctx->luma_size = ALIGN(ctx->stride[0] * ALIGN(ctx->img_height, 16), 256);
+			ctx->chroma_size = ALIGN(ctx->stride[0] * ALIGN(ctx->img_height / 2, 16),
+					256);
 			break;
 		case V4L2_PIX_FMT_YUV420M:
 		case V4L2_PIX_FMT_YVU420M:
diff --git a/drivers/media/platform/st/sti/c8sectpfe/c8sectpfe-core.c b/drivers/media/platform/st/sti/c8sectpfe/c8sectpfe-core.c
index 67d3d6e50d2e..ed3a107965cc 100644
--- a/drivers/media/platform/st/sti/c8sectpfe/c8sectpfe-core.c
+++ b/drivers/media/platform/st/sti/c8sectpfe/c8sectpfe-core.c
@@ -797,13 +797,12 @@ static int c8sectpfe_probe(struct platform_device *pdev)
 		}
 		tsin->i2c_adapter =
 			of_find_i2c_adapter_by_node(i2c_bus);
+		of_node_put(i2c_bus);
 		if (!tsin->i2c_adapter) {
 			dev_err(&pdev->dev, "No i2c adapter found\n");
-			of_node_put(i2c_bus);
 			ret = -ENODEV;
 			goto err_node_put;
 		}
-		of_node_put(i2c_bus);
 
 		/* Acquire reset GPIO and activate it */
 		tsin->rst_gpio = devm_fwnode_gpiod_get(dev,
diff --git a/drivers/media/platform/st/stm32/dma2d/dma2d.c b/drivers/media/platform/st/stm32/dma2d/dma2d.c
index 92f1edee58f8..3c64e9126025 100644
--- a/drivers/media/platform/st/stm32/dma2d/dma2d.c
+++ b/drivers/media/platform/st/stm32/dma2d/dma2d.c
@@ -492,7 +492,8 @@ static void device_run(void *prv)
 	dst->sequence = frm_cap->sequence++;
 	v4l2_m2m_buf_copy_metadata(src, dst, true);
 
-	clk_enable(dev->gate);
+	if (clk_enable(dev->gate))
+		goto end;
 
 	dma2d_config_fg(dev, frm_out,
 			vb2_dma_contig_plane_dma_addr(&src->vb2_buf, 0));
diff --git a/drivers/media/platform/st/stm32/stm32-dcmipp/dcmipp-bytecap.c b/drivers/media/platform/st/stm32/stm32-dcmipp/dcmipp-bytecap.c
index 9f768f011fa2..0f6918f4db38 100644
--- a/drivers/media/platform/st/stm32/stm32-dcmipp/dcmipp-bytecap.c
+++ b/drivers/media/platform/st/stm32/stm32-dcmipp/dcmipp-bytecap.c
@@ -893,7 +893,7 @@ struct dcmipp_ent_device *dcmipp_bytecap_ent_init(struct device *dev,
 	q->dev = dev;
 
 	/* DCMIPP requires 16 bytes aligned buffers */
-	ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32) & ~0x0f);
+	ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32));
 	if (ret) {
 		dev_err(dev, "Failed to set DMA mask\n");
 		goto err_mutex_destroy;
diff --git a/drivers/media/platform/ti/davinci/vpif.c b/drivers/media/platform/ti/davinci/vpif.c
index f4e1fa76bf37..353e8ad15879 100644
--- a/drivers/media/platform/ti/davinci/vpif.c
+++ b/drivers/media/platform/ti/davinci/vpif.c
@@ -504,7 +504,7 @@ static int vpif_probe(struct platform_device *pdev)
 	pdev_display = kzalloc(sizeof(*pdev_display), GFP_KERNEL);
 	if (!pdev_display) {
 		ret = -ENOMEM;
-		goto err_put_pdev_capture;
+		goto err_del_pdev_capture;
 	}
 
 	pdev_display->name = "vpif_display";
@@ -527,6 +527,8 @@ static int vpif_probe(struct platform_device *pdev)
 
 err_put_pdev_display:
 	platform_device_put(pdev_display);
+err_del_pdev_capture:
+	platform_device_del(pdev_capture);
 err_put_pdev_capture:
 	platform_device_put(pdev_capture);
 err_put_rpm:
diff --git a/drivers/media/platform/ti/j721e-csi2rx/j721e-csi2rx.c b/drivers/media/platform/ti/j721e-csi2rx/j721e-csi2rx.c
index 22442fce7607..3853245fcf6e 100644
--- a/drivers/media/platform/ti/j721e-csi2rx/j721e-csi2rx.c
+++ b/drivers/media/platform/ti/j721e-csi2rx/j721e-csi2rx.c
@@ -619,6 +619,7 @@ static void ti_csi2rx_dma_callback(void *param)
 
 		if (ti_csi2rx_start_dma(csi, buf)) {
 			dev_err(csi->dev, "Failed to queue the next buffer for DMA\n");
+			list_del(&buf->list);
 			vb2_buffer_done(&buf->vb.vb2_buf, VB2_BUF_STATE_ERROR);
 		} else {
 			list_move_tail(&buf->list, &dma->submitted);
diff --git a/drivers/media/platform/ti/omap3isp/isp.c b/drivers/media/platform/ti/omap3isp/isp.c
index 91101ba88ef0..b2210841a320 100644
--- a/drivers/media/platform/ti/omap3isp/isp.c
+++ b/drivers/media/platform/ti/omap3isp/isp.c
@@ -1961,6 +1961,13 @@ static int isp_attach_iommu(struct isp_device *isp)
 	struct dma_iommu_mapping *mapping;
 	int ret;
 
+	/* We always want to replace any default mapping from the arch code */
+	mapping = to_dma_iommu_mapping(isp->dev);
+	if (mapping) {
+		arm_iommu_detach_device(isp->dev);
+		arm_iommu_release_mapping(mapping);
+	}
+
 	/*
 	 * Create the ARM mapping, used by the ARM DMA mapping core to allocate
 	 * VAs. This will allocate a corresponding IOMMU domain.
diff --git a/drivers/media/platform/ti/omap3isp/ispccdc.c b/drivers/media/platform/ti/omap3isp/ispccdc.c
index dd375c4e180d..7d0c723dcd11 100644
--- a/drivers/media/platform/ti/omap3isp/ispccdc.c
+++ b/drivers/media/platform/ti/omap3isp/ispccdc.c
@@ -446,8 +446,8 @@ static int ccdc_lsc_config(struct isp_ccdc_device *ccdc,
 		if (ret < 0)
 			goto done;
 
-		dma_sync_sg_for_cpu(isp->dev, req->table.sgt.sgl,
-				    req->table.sgt.nents, DMA_TO_DEVICE);
+		dma_sync_sgtable_for_cpu(isp->dev, &req->table.sgt,
+					 DMA_TO_DEVICE);
 
 		if (copy_from_user(req->table.addr, config->lsc,
 				   req->config.size)) {
@@ -455,8 +455,8 @@ static int ccdc_lsc_config(struct isp_ccdc_device *ccdc,
 			goto done;
 		}
 
-		dma_sync_sg_for_device(isp->dev, req->table.sgt.sgl,
-				       req->table.sgt.nents, DMA_TO_DEVICE);
+		dma_sync_sgtable_for_device(isp->dev, &req->table.sgt,
+					    DMA_TO_DEVICE);
 	}
 
 	spin_lock_irqsave(&ccdc->lsc.req_lock, flags);
diff --git a/drivers/media/platform/ti/omap3isp/ispstat.c b/drivers/media/platform/ti/omap3isp/ispstat.c
index 359a846205b0..d3da68408ecb 100644
--- a/drivers/media/platform/ti/omap3isp/ispstat.c
+++ b/drivers/media/platform/ti/omap3isp/ispstat.c
@@ -161,8 +161,7 @@ static void isp_stat_buf_sync_for_device(struct ispstat *stat,
 	if (ISP_STAT_USES_DMAENGINE(stat))
 		return;
 
-	dma_sync_sg_for_device(stat->isp->dev, buf->sgt.sgl,
-			       buf->sgt.nents, DMA_FROM_DEVICE);
+	dma_sync_sgtable_for_device(stat->isp->dev, &buf->sgt, DMA_FROM_DEVICE);
 }
 
 static void isp_stat_buf_sync_for_cpu(struct ispstat *stat,
@@ -171,8 +170,7 @@ static void isp_stat_buf_sync_for_cpu(struct ispstat *stat,
 	if (ISP_STAT_USES_DMAENGINE(stat))
 		return;
 
-	dma_sync_sg_for_cpu(stat->isp->dev, buf->sgt.sgl,
-			    buf->sgt.nents, DMA_FROM_DEVICE);
+	dma_sync_sgtable_for_cpu(stat->isp->dev, &buf->sgt, DMA_FROM_DEVICE);
 }
 
 static void isp_stat_buf_clear(struct ispstat *stat)
diff --git a/drivers/media/platform/verisilicon/hantro_g2_hevc_dec.c b/drivers/media/platform/verisilicon/hantro_g2_hevc_dec.c
index 85a44143b378..0e212198dd65 100644
--- a/drivers/media/platform/verisilicon/hantro_g2_hevc_dec.c
+++ b/drivers/media/platform/verisilicon/hantro_g2_hevc_dec.c
@@ -518,6 +518,7 @@ static void set_buffers(struct hantro_ctx *ctx)
 	hantro_reg_write(vpu, &g2_stream_len, src_len);
 	hantro_reg_write(vpu, &g2_strm_buffer_len, src_buf_len);
 	hantro_reg_write(vpu, &g2_strm_start_offset, 0);
+	hantro_reg_write(vpu, &g2_start_bit, 0);
 	hantro_reg_write(vpu, &g2_write_mvs_e, 1);
 
 	hantro_write_addr(vpu, G2_TILE_SIZES_ADDR, ctx->hevc_dec.tile_sizes.dma);
diff --git a/drivers/media/platform/verisilicon/hantro_postproc.c b/drivers/media/platform/verisilicon/hantro_postproc.c
index 232c93eea7ee..18cad5ac92d8 100644
--- a/drivers/media/platform/verisilicon/hantro_postproc.c
+++ b/drivers/media/platform/verisilicon/hantro_postproc.c
@@ -260,8 +260,10 @@ int hantro_postproc_init(struct hantro_ctx *ctx)
 
 	for (i = 0; i < num_buffers; i++) {
 		ret = hantro_postproc_alloc(ctx, i);
-		if (ret)
+		if (ret) {
+			hantro_postproc_free(ctx);
 			return ret;
+		}
 	}
 
 	return 0;
diff --git a/drivers/media/rc/iguanair.c b/drivers/media/rc/iguanair.c
index 276bf3c8a8cb..8af94246e591 100644
--- a/drivers/media/rc/iguanair.c
+++ b/drivers/media/rc/iguanair.c
@@ -194,8 +194,10 @@ static int iguanair_send(struct iguanair *ir, unsigned size)
 	if (rc)
 		return rc;
 
-	if (wait_for_completion_timeout(&ir->completion, TIMEOUT) == 0)
+	if (wait_for_completion_timeout(&ir->completion, TIMEOUT) == 0) {
+		usb_kill_urb(ir->urb_out);
 		return -ETIMEDOUT;
+	}
 
 	return rc;
 }
diff --git a/drivers/media/rc/streamzap.c b/drivers/media/rc/streamzap.c
index 9b209e687f25..d3b48a0dd1f4 100644
--- a/drivers/media/rc/streamzap.c
+++ b/drivers/media/rc/streamzap.c
@@ -138,39 +138,10 @@ static void sz_push_half_space(struct streamzap_ir *sz,
 	sz_push_full_space(sz, value & SZ_SPACE_MASK);
 }
 
-/*
- * streamzap_callback - usb IRQ handler callback
- *
- * This procedure is invoked on reception of data from
- * the usb remote.
- */
-static void streamzap_callback(struct urb *urb)
+static void sz_process_ir_data(struct streamzap_ir *sz, int len)
 {
-	struct streamzap_ir *sz;
 	unsigned int i;
-	int len;
 
-	if (!urb)
-		return;
-
-	sz = urb->context;
-	len = urb->actual_length;
-
-	switch (urb->status) {
-	case -ECONNRESET:
-	case -ENOENT:
-	case -ESHUTDOWN:
-		/*
-		 * this urb is terminated, clean up.
-		 * sz might already be invalid at this point
-		 */
-		dev_err(sz->dev, "urb terminated, status: %d\n", urb->status);
-		return;
-	default:
-		break;
-	}
-
-	dev_dbg(sz->dev, "%s: received urb, len %d\n", __func__, len);
 	for (i = 0; i < len; i++) {
 		dev_dbg(sz->dev, "sz->buf_in[%d]: %x\n",
 			i, (unsigned char)sz->buf_in[i]);
@@ -219,6 +190,43 @@ static void streamzap_callback(struct urb *urb)
 	}
 
 	ir_raw_event_handle(sz->rdev);
+}
+
+/*
+ * streamzap_callback - usb IRQ handler callback
+ *
+ * This procedure is invoked on reception of data from
+ * the usb remote.
+ */
+static void streamzap_callback(struct urb *urb)
+{
+	struct streamzap_ir *sz;
+	int len;
+
+	if (!urb)
+		return;
+
+	sz = urb->context;
+	len = urb->actual_length;
+
+	switch (urb->status) {
+	case 0:
+		dev_dbg(sz->dev, "%s: received urb, len %d\n", __func__, len);
+		sz_process_ir_data(sz, len);
+		break;
+	case -ECONNRESET:
+	case -ENOENT:
+	case -ESHUTDOWN:
+		/*
+		 * this urb is terminated, clean up.
+		 * sz might already be invalid at this point
+		 */
+		dev_err(sz->dev, "urb terminated, status: %d\n", urb->status);
+		return;
+	default:
+		break;
+	}
+
 	usb_submit_urb(urb, GFP_ATOMIC);
 }
 
@@ -385,8 +393,8 @@ static void streamzap_disconnect(struct usb_interface *interface)
 	if (!sz)
 		return;
 
-	rc_unregister_device(sz->rdev);
 	usb_kill_urb(sz->urb_in);
+	rc_unregister_device(sz->rdev);
 	usb_free_urb(sz->urb_in);
 	usb_free_coherent(usbdev, sz->buf_in_len, sz->buf_in, sz->dma_in);
 
diff --git a/drivers/media/test-drivers/vidtv/vidtv_bridge.c b/drivers/media/test-drivers/vidtv/vidtv_bridge.c
index 613949df897d..6d964e392d31 100644
--- a/drivers/media/test-drivers/vidtv/vidtv_bridge.c
+++ b/drivers/media/test-drivers/vidtv/vidtv_bridge.c
@@ -191,10 +191,11 @@ static int vidtv_start_streaming(struct vidtv_dvb *dvb)
 
 	mux_args.mux_buf_sz  = mux_buf_sz;
 
-	dvb->streaming = true;
 	dvb->mux = vidtv_mux_init(dvb->fe[0], dev, &mux_args);
 	if (!dvb->mux)
 		return -ENOMEM;
+
+	dvb->streaming = true;
 	vidtv_mux_start_thread(dvb->mux);
 
 	dev_dbg_ratelimited(dev, "Started streaming\n");
@@ -205,6 +206,11 @@ static int vidtv_stop_streaming(struct vidtv_dvb *dvb)
 {
 	struct device *dev = &dvb->pdev->dev;
 
+	if (!dvb->streaming) {
+		dev_warn_ratelimited(dev, "No streaming. Skipping.\n");
+		return 0;
+	}
+
 	dvb->streaming = false;
 	vidtv_mux_stop_thread(dvb->mux);
 	vidtv_mux_destroy(dvb->mux);
diff --git a/drivers/media/test-drivers/vidtv/vidtv_channel.c b/drivers/media/test-drivers/vidtv/vidtv_channel.c
index 7838e6272712..f3023e91b3eb 100644
--- a/drivers/media/test-drivers/vidtv/vidtv_channel.c
+++ b/drivers/media/test-drivers/vidtv/vidtv_channel.c
@@ -497,7 +497,7 @@ free_sdt:
 	vidtv_psi_sdt_table_destroy(m->si.sdt);
 free_pat:
 	vidtv_psi_pat_table_destroy(m->si.pat);
-	return 0;
+	return -EINVAL;
 }
 
 void vidtv_channel_si_destroy(struct vidtv_mux *m)
diff --git a/drivers/media/test-drivers/vim2m.c b/drivers/media/test-drivers/vim2m.c
index 3e3b424b4860..8ca6459286ba 100644
--- a/drivers/media/test-drivers/vim2m.c
+++ b/drivers/media/test-drivers/vim2m.c
@@ -1316,9 +1316,6 @@ static int vim2m_probe(struct platform_device *pdev)
 	vfd->v4l2_dev = &dev->v4l2_dev;
 
 	video_set_drvdata(vfd, dev);
-	v4l2_info(&dev->v4l2_dev,
-		  "Device registered as /dev/video%d\n", vfd->num);
-
 	platform_set_drvdata(pdev, dev);
 
 	dev->m2m_dev = v4l2_m2m_init(&m2m_ops);
@@ -1345,6 +1342,9 @@ static int vim2m_probe(struct platform_device *pdev)
 		goto error_m2m;
 	}
 
+	v4l2_info(&dev->v4l2_dev,
+		  "Device registered as /dev/video%d\n", vfd->num);
+
 #ifdef CONFIG_MEDIA_CONTROLLER
 	ret = v4l2_m2m_register_media_controller(dev->m2m_dev, vfd,
 						 MEDIA_ENT_F_PROC_VIDEO_SCALER);
diff --git a/drivers/media/test-drivers/vimc/vimc-streamer.c b/drivers/media/test-drivers/vimc/vimc-streamer.c
index 807551a5143b..15d863f97cbf 100644
--- a/drivers/media/test-drivers/vimc/vimc-streamer.c
+++ b/drivers/media/test-drivers/vimc/vimc-streamer.c
@@ -59,6 +59,12 @@ static void vimc_streamer_pipeline_terminate(struct vimc_stream *stream)
 			continue;
 
 		sd = media_entity_to_v4l2_subdev(ved->ent);
+		/*
+		 * Do not call .s_stream() to stop an already
+		 * stopped/unstarted subdev.
+		 */
+		if (!v4l2_subdev_is_streaming(sd))
+			continue;
 		v4l2_subdev_call(sd, video, s_stream, 0);
 	}
 }
diff --git a/drivers/media/test-drivers/visl/visl-core.c b/drivers/media/test-drivers/visl/visl-core.c
index c46464bcaf2e..93239391f2cf 100644
--- a/drivers/media/test-drivers/visl/visl-core.c
+++ b/drivers/media/test-drivers/visl/visl-core.c
@@ -161,9 +161,15 @@ static const struct visl_ctrl_desc visl_h264_ctrl_descs[] = {
 	},
 	{
 		.cfg.id = V4L2_CID_STATELESS_H264_DECODE_MODE,
+		.cfg.min = V4L2_STATELESS_H264_DECODE_MODE_SLICE_BASED,
+		.cfg.max = V4L2_STATELESS_H264_DECODE_MODE_FRAME_BASED,
+		.cfg.def = V4L2_STATELESS_H264_DECODE_MODE_SLICE_BASED,
 	},
 	{
 		.cfg.id = V4L2_CID_STATELESS_H264_START_CODE,
+		.cfg.min = V4L2_STATELESS_H264_START_CODE_NONE,
+		.cfg.max = V4L2_STATELESS_H264_START_CODE_ANNEX_B,
+		.cfg.def = V4L2_STATELESS_H264_START_CODE_NONE,
 	},
 	{
 		.cfg.id = V4L2_CID_STATELESS_H264_SLICE_PARAMS,
@@ -198,9 +204,15 @@ static const struct visl_ctrl_desc visl_hevc_ctrl_descs[] = {
 	},
 	{
 		.cfg.id = V4L2_CID_STATELESS_HEVC_DECODE_MODE,
+		.cfg.min = V4L2_STATELESS_HEVC_DECODE_MODE_SLICE_BASED,
+		.cfg.max = V4L2_STATELESS_HEVC_DECODE_MODE_FRAME_BASED,
+		.cfg.def = V4L2_STATELESS_HEVC_DECODE_MODE_SLICE_BASED,
 	},
 	{
 		.cfg.id = V4L2_CID_STATELESS_HEVC_START_CODE,
+		.cfg.min = V4L2_STATELESS_HEVC_START_CODE_NONE,
+		.cfg.max = V4L2_STATELESS_HEVC_START_CODE_ANNEX_B,
+		.cfg.def = V4L2_STATELESS_HEVC_START_CODE_NONE,
 	},
 	{
 		.cfg.id = V4L2_CID_STATELESS_HEVC_ENTRY_POINT_OFFSETS,
diff --git a/drivers/media/test-drivers/vivid/vivid-kthread-cap.c b/drivers/media/test-drivers/vivid/vivid-kthread-cap.c
index 669bd96da4c7..273e8ed8c2a9 100644
--- a/drivers/media/test-drivers/vivid/vivid-kthread-cap.c
+++ b/drivers/media/test-drivers/vivid/vivid-kthread-cap.c
@@ -789,9 +789,14 @@ static int vivid_thread_vid_cap(void *data)
 			next_jiffies_since_start = jiffies_since_start;
 
 		wait_jiffies = next_jiffies_since_start - jiffies_since_start;
-		while (time_is_after_jiffies(cur_jiffies + wait_jiffies) &&
-		       !kthread_should_stop())
-			schedule();
+		if (!time_is_after_jiffies(cur_jiffies + wait_jiffies))
+			continue;
+
+		wait_queue_head_t wait;
+
+		init_waitqueue_head(&wait);
+		wait_event_interruptible_timeout(wait, kthread_should_stop(),
+					cur_jiffies + wait_jiffies - jiffies);
 	}
 	dprintk(dev, 1, "Video Capture Thread End\n");
 	return 0;
diff --git a/drivers/media/test-drivers/vivid/vivid-kthread-out.c b/drivers/media/test-drivers/vivid/vivid-kthread-out.c
index fac6208b51da..015a7b166a1e 100644
--- a/drivers/media/test-drivers/vivid/vivid-kthread-out.c
+++ b/drivers/media/test-drivers/vivid/vivid-kthread-out.c
@@ -235,9 +235,14 @@ static int vivid_thread_vid_out(void *data)
 			next_jiffies_since_start = jiffies_since_start;
 
 		wait_jiffies = next_jiffies_since_start - jiffies_since_start;
-		while (time_is_after_jiffies(cur_jiffies + wait_jiffies) &&
-		       !kthread_should_stop())
-			schedule();
+		if (!time_is_after_jiffies(cur_jiffies + wait_jiffies))
+			continue;
+
+		wait_queue_head_t wait;
+
+		init_waitqueue_head(&wait);
+		wait_event_interruptible_timeout(wait, kthread_should_stop(),
+					cur_jiffies + wait_jiffies - jiffies);
 	}
 	dprintk(dev, 1, "Video Output Thread End\n");
 	return 0;
diff --git a/drivers/media/test-drivers/vivid/vivid-kthread-touch.c b/drivers/media/test-drivers/vivid/vivid-kthread-touch.c
index fa711ee36a3f..c862689786b6 100644
--- a/drivers/media/test-drivers/vivid/vivid-kthread-touch.c
+++ b/drivers/media/test-drivers/vivid/vivid-kthread-touch.c
@@ -135,9 +135,14 @@ static int vivid_thread_touch_cap(void *data)
 			next_jiffies_since_start = jiffies_since_start;
 
 		wait_jiffies = next_jiffies_since_start - jiffies_since_start;
-		while (time_is_after_jiffies(cur_jiffies + wait_jiffies) &&
-		       !kthread_should_stop())
-			schedule();
+		if (!time_is_after_jiffies(cur_jiffies + wait_jiffies))
+			continue;
+
+		wait_queue_head_t wait;
+
+		init_waitqueue_head(&wait);
+		wait_event_interruptible_timeout(wait, kthread_should_stop(),
+					cur_jiffies + wait_jiffies - jiffies);
 	}
 	dprintk(dev, 1, "Touch Capture Thread End\n");
 	return 0;
diff --git a/drivers/media/test-drivers/vivid/vivid-sdr-cap.c b/drivers/media/test-drivers/vivid/vivid-sdr-cap.c
index 38cda33dffb2..97cfc58b7057 100644
--- a/drivers/media/test-drivers/vivid/vivid-sdr-cap.c
+++ b/drivers/media/test-drivers/vivid/vivid-sdr-cap.c
@@ -206,9 +206,14 @@ static int vivid_thread_sdr_cap(void *data)
 			next_jiffies_since_start = jiffies_since_start;
 
 		wait_jiffies = next_jiffies_since_start - jiffies_since_start;
-		while (time_is_after_jiffies(cur_jiffies + wait_jiffies) &&
-		       !kthread_should_stop())
-			schedule();
+		if (!time_is_after_jiffies(cur_jiffies + wait_jiffies))
+			continue;
+
+		wait_queue_head_t wait;
+
+		init_waitqueue_head(&wait);
+		wait_event_interruptible_timeout(wait, kthread_should_stop(),
+					cur_jiffies + wait_jiffies - jiffies);
 	}
 	dprintk(dev, 1, "SDR Capture Thread End\n");
 	return 0;
diff --git a/drivers/media/test-drivers/vivid/vivid-vid-cap.c b/drivers/media/test-drivers/vivid/vivid-vid-cap.c
index f25e01115364..0d5919e00075 100644
--- a/drivers/media/test-drivers/vivid/vivid-vid-cap.c
+++ b/drivers/media/test-drivers/vivid/vivid-vid-cap.c
@@ -947,8 +947,8 @@ int vivid_vid_cap_s_selection(struct file *file, void *fh, struct v4l2_selection
 			if (dev->has_compose_cap) {
 				v4l2_rect_set_min_size(compose, &min_rect);
 				v4l2_rect_set_max_size(compose, &max_rect);
-				v4l2_rect_map_inside(compose, &fmt);
 			}
+			v4l2_rect_map_inside(compose, &fmt);
 			dev->fmt_cap_rect = fmt;
 			tpg_s_buf_height(&dev->tpg, fmt.height);
 		} else if (dev->has_compose_cap) {
diff --git a/drivers/media/usb/cx231xx/cx231xx-417.c b/drivers/media/usb/cx231xx/cx231xx-417.c
index abb967c8bd35..6cb130eb32d5 100644
--- a/drivers/media/usb/cx231xx/cx231xx-417.c
+++ b/drivers/media/usb/cx231xx/cx231xx-417.c
@@ -1722,6 +1722,8 @@ static void cx231xx_video_dev_init(
 	vfd->lock = &dev->lock;
 	vfd->release = video_device_release_empty;
 	vfd->ctrl_handler = &dev->mpeg_ctrl_handler.hdl;
+	vfd->device_caps = V4L2_CAP_READWRITE | V4L2_CAP_STREAMING |
+			   V4L2_CAP_VIDEO_CAPTURE;
 	video_set_drvdata(vfd, dev);
 	if (dev->tuner_type == TUNER_ABSENT) {
 		v4l2_disable_ioctl(vfd, VIDIOC_G_FREQUENCY);
diff --git a/drivers/media/usb/dvb-usb-v2/af9035.c b/drivers/media/usb/dvb-usb-v2/af9035.c
index 0d2c42819d39..218f712f56b1 100644
--- a/drivers/media/usb/dvb-usb-v2/af9035.c
+++ b/drivers/media/usb/dvb-usb-v2/af9035.c
@@ -322,13 +322,16 @@ static int af9035_i2c_master_xfer(struct i2c_adapter *adap,
 			ret = -EOPNOTSUPP;
 		} else if ((msg[0].addr == state->af9033_i2c_addr[0]) ||
 			   (msg[0].addr == state->af9033_i2c_addr[1])) {
+			/* demod access via firmware interface */
+			u32 reg;
+
 			if (msg[0].len < 3 || msg[1].len < 1) {
 				ret = -EOPNOTSUPP;
 				goto unlock;
 			}
-			/* demod access via firmware interface */
-			u32 reg = msg[0].buf[0] << 16 | msg[0].buf[1] << 8 |
-					msg[0].buf[2];
+
+			reg = msg[0].buf[0] << 16 | msg[0].buf[1] << 8 |
+				msg[0].buf[2];
 
 			if (msg[0].addr == state->af9033_i2c_addr[1])
 				reg |= 0x100000;
@@ -385,13 +388,16 @@ static int af9035_i2c_master_xfer(struct i2c_adapter *adap,
 			ret = -EOPNOTSUPP;
 		} else if ((msg[0].addr == state->af9033_i2c_addr[0]) ||
 			   (msg[0].addr == state->af9033_i2c_addr[1])) {
+			/* demod access via firmware interface */
+			u32 reg;
+
 			if (msg[0].len < 3) {
 				ret = -EOPNOTSUPP;
 				goto unlock;
 			}
-			/* demod access via firmware interface */
-			u32 reg = msg[0].buf[0] << 16 | msg[0].buf[1] << 8 |
-					msg[0].buf[2];
+
+			reg = msg[0].buf[0] << 16 | msg[0].buf[1] << 8 |
+				msg[0].buf[2];
 
 			if (msg[0].addr == state->af9033_i2c_addr[1])
 				reg |= 0x100000;
diff --git a/drivers/media/usb/dvb-usb-v2/lmedm04.c b/drivers/media/usb/dvb-usb-v2/lmedm04.c
index 8a34e6c0d6a6..f0537b741d13 100644
--- a/drivers/media/usb/dvb-usb-v2/lmedm04.c
+++ b/drivers/media/usb/dvb-usb-v2/lmedm04.c
@@ -373,6 +373,7 @@ static int lme2510_int_read(struct dvb_usb_adapter *adap)
 	struct dvb_usb_device *d = adap_to_d(adap);
 	struct lme2510_state *lme_int = adap_to_priv(adap);
 	struct usb_host_endpoint *ep;
+	int ret;
 
 	lme_int->lme_urb = usb_alloc_urb(0, GFP_KERNEL);
 
@@ -390,11 +391,20 @@ static int lme2510_int_read(struct dvb_usb_adapter *adap)
 
 	/* Quirk of pipe reporting PIPE_BULK but behaves as interrupt */
 	ep = usb_pipe_endpoint(d->udev, lme_int->lme_urb->pipe);
+	if (!ep) {
+		usb_free_urb(lme_int->lme_urb);
+		return -ENODEV;
+	}
 
 	if (usb_endpoint_type(&ep->desc) == USB_ENDPOINT_XFER_BULK)
 		lme_int->lme_urb->pipe = usb_rcvbulkpipe(d->udev, 0xa);
 
-	usb_submit_urb(lme_int->lme_urb, GFP_KERNEL);
+	ret = usb_submit_urb(lme_int->lme_urb, GFP_KERNEL);
+	if (ret) {
+		usb_free_urb(lme_int->lme_urb);
+		return ret;
+	}
+
 	info("INT Interrupt Service Started");
 
 	return 0;
diff --git a/drivers/media/usb/dvb-usb/cxusb.c b/drivers/media/usb/dvb-usb/cxusb.c
index 1d98d3465e28..ce52c936cb93 100644
--- a/drivers/media/usb/dvb-usb/cxusb.c
+++ b/drivers/media/usb/dvb-usb/cxusb.c
@@ -119,9 +119,8 @@ static void cxusb_gpio_tuner(struct dvb_usb_device *d, int onoff)
 
 	o[0] = GPIO_TUNER;
 	o[1] = onoff;
-	cxusb_ctrl_msg(d, CMD_GPIO_WRITE, o, 2, &i, 1);
 
-	if (i != 0x01)
+	if (!cxusb_ctrl_msg(d, CMD_GPIO_WRITE, o, 2, &i, 1) && i != 0x01)
 		dev_info(&d->udev->dev, "gpio_write failed.\n");
 
 	st->gpio_write_state[GPIO_TUNER] = onoff;
diff --git a/drivers/media/usb/gspca/stv06xx/stv06xx_hdcs.c b/drivers/media/usb/gspca/stv06xx/stv06xx_hdcs.c
index 5a47dcbf1c8e..303b055fefea 100644
--- a/drivers/media/usb/gspca/stv06xx/stv06xx_hdcs.c
+++ b/drivers/media/usb/gspca/stv06xx/stv06xx_hdcs.c
@@ -520,12 +520,13 @@ static int hdcs_init(struct sd *sd)
 static int hdcs_dump(struct sd *sd)
 {
 	u16 reg, val;
+	int err = 0;
 
 	pr_info("Dumping sensor registers:\n");
 
-	for (reg = HDCS_IDENT; reg <= HDCS_ROWEXPH; reg++) {
-		stv06xx_read_sensor(sd, reg, &val);
+	for (reg = HDCS_IDENT; reg <= HDCS_ROWEXPH && !err; reg++) {
+		err = stv06xx_read_sensor(sd, reg, &val);
 		pr_info("reg 0x%02x = 0x%02x\n", reg, val);
 	}
-	return 0;
+	return (err < 0) ? err : 0;
 }
diff --git a/drivers/media/usb/hdpvr/hdpvr-i2c.c b/drivers/media/usb/hdpvr/hdpvr-i2c.c
index 070559b01b01..54956a8ff15e 100644
--- a/drivers/media/usb/hdpvr/hdpvr-i2c.c
+++ b/drivers/media/usb/hdpvr/hdpvr-i2c.c
@@ -165,10 +165,16 @@ static const struct i2c_algorithm hdpvr_algo = {
 	.functionality = hdpvr_functionality,
 };
 
+/* prevent invalid 0-length usb_control_msg */
+static const struct i2c_adapter_quirks hdpvr_quirks = {
+	.flags = I2C_AQ_NO_ZERO_LEN_READ,
+};
+
 static const struct i2c_adapter hdpvr_i2c_adapter_template = {
 	.name   = "Hauppauge HD PVR I2C",
 	.owner  = THIS_MODULE,
 	.algo   = &hdpvr_algo,
+	.quirks = &hdpvr_quirks,
 };
 
 static int hdpvr_activate_ir(struct hdpvr_device *dev)
diff --git a/drivers/media/usb/uvc/uvc_ctrl.c b/drivers/media/usb/uvc/uvc_ctrl.c
index 4fe26e82e3d1..957d620ad671 100644
--- a/drivers/media/usb/uvc/uvc_ctrl.c
+++ b/drivers/media/usb/uvc/uvc_ctrl.c
@@ -862,6 +862,25 @@ static inline void uvc_clear_bit(u8 *data, int bit)
 	data[bit >> 3] &= ~(1 << (bit & 7));
 }
 
+static s32 uvc_menu_to_v4l2_menu(struct uvc_control_mapping *mapping, s32 val)
+{
+	unsigned int i;
+
+	for (i = 0; BIT(i) <= mapping->menu_mask; ++i) {
+		u32 menu_value;
+
+		if (!test_bit(i, &mapping->menu_mask))
+			continue;
+
+		menu_value = uvc_mapping_get_menu_value(mapping, i);
+
+		if (menu_value == val)
+			return i;
+	}
+
+	return val;
+}
+
 /*
  * Extract the bit string specified by mapping->offset and mapping->size
  * from the little-endian data stored at 'data' and return the result as
@@ -896,6 +915,16 @@ static s32 uvc_get_le_value(struct uvc_control_mapping *mapping,
 	if (mapping->data_type == UVC_CTRL_DATA_TYPE_SIGNED)
 		value |= -(value & (1 << (mapping->size - 1)));
 
+	/* If it is a menu, convert from uvc to v4l2. */
+	if (mapping->v4l2_type != V4L2_CTRL_TYPE_MENU)
+		return value;
+
+	switch (query) {
+	case UVC_GET_CUR:
+	case UVC_GET_DEF:
+		return uvc_menu_to_v4l2_menu(mapping, value);
+	}
+
 	return value;
 }
 
@@ -1060,32 +1089,6 @@ static int uvc_ctrl_populate_cache(struct uvc_video_chain *chain,
 	return 0;
 }
 
-static s32 __uvc_ctrl_get_value(struct uvc_control_mapping *mapping,
-				const u8 *data)
-{
-	s32 value = mapping->get(mapping, UVC_GET_CUR, data);
-
-	if (mapping->v4l2_type == V4L2_CTRL_TYPE_MENU) {
-		unsigned int i;
-
-		for (i = 0; BIT(i) <= mapping->menu_mask; ++i) {
-			u32 menu_value;
-
-			if (!test_bit(i, &mapping->menu_mask))
-				continue;
-
-			menu_value = uvc_mapping_get_menu_value(mapping, i);
-
-			if (menu_value == value) {
-				value = i;
-				break;
-			}
-		}
-	}
-
-	return value;
-}
-
 static int __uvc_ctrl_load_cur(struct uvc_video_chain *chain,
 			       struct uvc_control *ctrl)
 {
@@ -1136,8 +1139,8 @@ static int __uvc_ctrl_get(struct uvc_video_chain *chain,
 	if (ret < 0)
 		return ret;
 
-	*value = __uvc_ctrl_get_value(mapping,
-				uvc_ctrl_data(ctrl, UVC_CTRL_DATA_CURRENT));
+	*value = mapping->get(mapping, UVC_GET_CUR,
+			      uvc_ctrl_data(ctrl, UVC_CTRL_DATA_CURRENT));
 
 	return 0;
 }
@@ -1287,7 +1290,6 @@ static int __uvc_query_v4l2_ctrl(struct uvc_video_chain *chain,
 {
 	struct uvc_control_mapping *master_map = NULL;
 	struct uvc_control *master_ctrl = NULL;
-	unsigned int i;
 
 	memset(v4l2_ctrl, 0, sizeof(*v4l2_ctrl));
 	v4l2_ctrl->id = mapping->id;
@@ -1330,21 +1332,6 @@ static int __uvc_query_v4l2_ctrl(struct uvc_video_chain *chain,
 		v4l2_ctrl->minimum = ffs(mapping->menu_mask) - 1;
 		v4l2_ctrl->maximum = fls(mapping->menu_mask) - 1;
 		v4l2_ctrl->step = 1;
-
-		for (i = 0; BIT(i) <= mapping->menu_mask; ++i) {
-			u32 menu_value;
-
-			if (!test_bit(i, &mapping->menu_mask))
-				continue;
-
-			menu_value = uvc_mapping_get_menu_value(mapping, i);
-
-			if (menu_value == v4l2_ctrl->default_value) {
-				v4l2_ctrl->default_value = i;
-				break;
-			}
-		}
-
 		return 0;
 
 	case V4L2_CTRL_TYPE_BOOLEAN:
@@ -1579,6 +1566,40 @@ static void uvc_ctrl_send_slave_event(struct uvc_video_chain *chain,
 	uvc_ctrl_send_event(chain, handle, ctrl, mapping, val, changes);
 }
 
+static void uvc_ctrl_set_handle(struct uvc_fh *handle, struct uvc_control *ctrl,
+				struct uvc_fh *new_handle)
+{
+	lockdep_assert_held(&handle->chain->ctrl_mutex);
+
+	if (new_handle) {
+		if (ctrl->handle)
+			dev_warn_ratelimited(&handle->stream->dev->udev->dev,
+					     "UVC non compliance: Setting an async control with a pending operation.");
+
+		if (new_handle == ctrl->handle)
+			return;
+
+		if (ctrl->handle) {
+			WARN_ON(!ctrl->handle->pending_async_ctrls);
+			if (ctrl->handle->pending_async_ctrls)
+				ctrl->handle->pending_async_ctrls--;
+		}
+
+		ctrl->handle = new_handle;
+		handle->pending_async_ctrls++;
+		return;
+	}
+
+	/* Cannot clear the handle for a control not owned by us.*/
+	if (WARN_ON(ctrl->handle != handle))
+		return;
+
+	ctrl->handle = NULL;
+	if (WARN_ON(!handle->pending_async_ctrls))
+		return;
+	handle->pending_async_ctrls--;
+}
+
 void uvc_ctrl_status_event(struct uvc_video_chain *chain,
 			   struct uvc_control *ctrl, const u8 *data)
 {
@@ -1589,10 +1610,11 @@ void uvc_ctrl_status_event(struct uvc_video_chain *chain,
 	mutex_lock(&chain->ctrl_mutex);
 
 	handle = ctrl->handle;
-	ctrl->handle = NULL;
+	if (handle)
+		uvc_ctrl_set_handle(handle, ctrl, NULL);
 
 	list_for_each_entry(mapping, &ctrl->info.mappings, list) {
-		s32 value = __uvc_ctrl_get_value(mapping, data);
+		s32 value = mapping->get(mapping, UVC_GET_CUR, data);
 
 		/*
 		 * handle may be NULL here if the device sends auto-update
@@ -1640,10 +1662,8 @@ bool uvc_ctrl_status_event_async(struct urb *urb, struct uvc_video_chain *chain,
 	struct uvc_device *dev = chain->dev;
 	struct uvc_ctrl_work *w = &dev->async_ctrl;
 
-	if (list_empty(&ctrl->info.mappings)) {
-		ctrl->handle = NULL;
+	if (list_empty(&ctrl->info.mappings))
 		return false;
-	}
 
 	w->data = data;
 	w->urb = urb;
@@ -1669,16 +1689,21 @@ static bool uvc_ctrl_xctrls_has_control(const struct v4l2_ext_control *xctrls,
 }
 
 static void uvc_ctrl_send_events(struct uvc_fh *handle,
-	const struct v4l2_ext_control *xctrls, unsigned int xctrls_count)
+				 struct uvc_entity *entity,
+				 const struct v4l2_ext_control *xctrls,
+				 unsigned int xctrls_count)
 {
 	struct uvc_control_mapping *mapping;
 	struct uvc_control *ctrl;
-	u32 changes = V4L2_EVENT_CTRL_CH_VALUE;
 	unsigned int i;
 	unsigned int j;
 
 	for (i = 0; i < xctrls_count; ++i) {
+		u32 changes = V4L2_EVENT_CTRL_CH_VALUE;
+
 		ctrl = uvc_find_control(handle->chain, xctrls[i].id, &mapping);
+		if (ctrl->entity != entity)
+			continue;
 
 		if (ctrl->info.flags & UVC_CTRL_FLAG_ASYNCHRONOUS)
 			/* Notification will be sent from an Interrupt event. */
@@ -1810,12 +1835,20 @@ int uvc_ctrl_begin(struct uvc_video_chain *chain)
 	return mutex_lock_interruptible(&chain->ctrl_mutex) ? -ERESTARTSYS : 0;
 }
 
+/*
+ * Returns the number of uvc controls that have been correctly set, or a
+ * negative number if there has been an error.
+ */
 static int uvc_ctrl_commit_entity(struct uvc_device *dev,
-	struct uvc_entity *entity, int rollback, struct uvc_control **err_ctrl)
+				  struct uvc_fh *handle,
+				  struct uvc_entity *entity,
+				  int rollback,
+				  struct uvc_control **err_ctrl)
 {
+	unsigned int processed_ctrls = 0;
 	struct uvc_control *ctrl;
 	unsigned int i;
-	int ret;
+	int ret = 0;
 
 	if (entity == NULL)
 		return 0;
@@ -1844,8 +1877,9 @@ static int uvc_ctrl_commit_entity(struct uvc_device *dev,
 				dev->intfnum, ctrl->info.selector,
 				uvc_ctrl_data(ctrl, UVC_CTRL_DATA_CURRENT),
 				ctrl->info.size);
-		else
-			ret = 0;
+
+		if (!ret)
+			processed_ctrls++;
 
 		if (rollback || ret < 0)
 			memcpy(uvc_ctrl_data(ctrl, UVC_CTRL_DATA_CURRENT),
@@ -1854,14 +1888,25 @@ static int uvc_ctrl_commit_entity(struct uvc_device *dev,
 
 		ctrl->dirty = 0;
 
-		if (ret < 0) {
+		if (ret < 0 && !rollback) {
 			if (err_ctrl)
 				*err_ctrl = ctrl;
-			return ret;
+			/*
+			 * If we fail to set a control, we need to rollback
+			 * the next ones.
+			 */
+			rollback = 1;
 		}
+
+		if (!rollback && handle && !ret &&
+		    ctrl->info.flags & UVC_CTRL_FLAG_ASYNCHRONOUS)
+			uvc_ctrl_set_handle(handle, ctrl, handle);
 	}
 
-	return 0;
+	if (ret)
+		return ret;
+
+	return processed_ctrls;
 }
 
 static int uvc_ctrl_find_ctrl_idx(struct uvc_entity *entity,
@@ -1891,26 +1936,35 @@ int __uvc_ctrl_commit(struct uvc_fh *handle, int rollback,
 	struct uvc_video_chain *chain = handle->chain;
 	struct uvc_control *err_ctrl;
 	struct uvc_entity *entity;
-	int ret = 0;
+	int ret_out = 0;
+	int ret;
 
 	/* Find the control. */
 	list_for_each_entry(entity, &chain->entities, chain) {
-		ret = uvc_ctrl_commit_entity(chain->dev, entity, rollback,
-					     &err_ctrl);
+		ret = uvc_ctrl_commit_entity(chain->dev, handle, entity,
+					     rollback, &err_ctrl);
 		if (ret < 0) {
 			if (ctrls)
 				ctrls->error_idx =
 					uvc_ctrl_find_ctrl_idx(entity, ctrls,
 							       err_ctrl);
-			goto done;
+			/*
+			 * When we fail to commit an entity, we need to
+			 * restore the UVC_CTRL_DATA_BACKUP for all the
+			 * controls in the other entities, otherwise our cache
+			 * and the hardware will be out of sync.
+			 */
+			rollback = 1;
+
+			ret_out = ret;
+		} else if (ret > 0 && !rollback) {
+			uvc_ctrl_send_events(handle, entity,
+					     ctrls->controls, ctrls->count);
 		}
 	}
 
-	if (!rollback)
-		uvc_ctrl_send_events(handle, ctrls->controls, ctrls->count);
-done:
 	mutex_unlock(&chain->ctrl_mutex);
-	return ret;
+	return ret_out;
 }
 
 int uvc_ctrl_get(struct uvc_video_chain *chain,
@@ -2046,9 +2100,6 @@ int uvc_ctrl_set(struct uvc_fh *handle,
 	mapping->set(mapping, value,
 		uvc_ctrl_data(ctrl, UVC_CTRL_DATA_CURRENT));
 
-	if (ctrl->info.flags & UVC_CTRL_FLAG_ASYNCHRONOUS)
-		ctrl->handle = handle;
-
 	ctrl->dirty = 1;
 	ctrl->modified = 1;
 	return 0;
@@ -2377,7 +2428,7 @@ int uvc_ctrl_restore_values(struct uvc_device *dev)
 			ctrl->dirty = 1;
 		}
 
-		ret = uvc_ctrl_commit_entity(dev, entity, 0, NULL);
+		ret = uvc_ctrl_commit_entity(dev, NULL, entity, 0, NULL);
 		if (ret < 0)
 			return ret;
 	}
@@ -2770,6 +2821,26 @@ int uvc_ctrl_init_device(struct uvc_device *dev)
 	return 0;
 }
 
+void uvc_ctrl_cleanup_fh(struct uvc_fh *handle)
+{
+	struct uvc_entity *entity;
+
+	guard(mutex)(&handle->chain->ctrl_mutex);
+
+	if (!handle->pending_async_ctrls)
+		return;
+
+	list_for_each_entry(entity, &handle->chain->dev->entities, list) {
+		for (unsigned int i = 0; i < entity->ncontrols; ++i) {
+			if (entity->controls[i].handle != handle)
+				continue;
+			uvc_ctrl_set_handle(handle, &entity->controls[i], NULL);
+		}
+	}
+
+	WARN_ON(handle->pending_async_ctrls);
+}
+
 /*
  * Cleanup device controls.
  */
diff --git a/drivers/media/usb/uvc/uvc_driver.c b/drivers/media/usb/uvc/uvc_driver.c
index 9f38a9b23c01..fde5cc70bf79 100644
--- a/drivers/media/usb/uvc/uvc_driver.c
+++ b/drivers/media/usb/uvc/uvc_driver.c
@@ -235,6 +235,9 @@ static int uvc_parse_format(struct uvc_device *dev,
 	unsigned int i, n;
 	u8 ftype;
 
+	if (buflen < 4)
+		return -EINVAL;
+
 	format->type = buffer[2];
 	format->index = buffer[3];
 	format->frames = frames;
@@ -775,27 +778,14 @@ static const u8 uvc_media_transport_input_guid[16] =
 	UVC_GUID_UVC_MEDIA_TRANSPORT_INPUT;
 static const u8 uvc_processing_guid[16] = UVC_GUID_UVC_PROCESSING;
 
-static struct uvc_entity *uvc_alloc_new_entity(struct uvc_device *dev, u16 type,
-					       u16 id, unsigned int num_pads,
-					       unsigned int extra_size)
+static struct uvc_entity *uvc_alloc_entity(u16 type, u16 id,
+		unsigned int num_pads, unsigned int extra_size)
 {
 	struct uvc_entity *entity;
 	unsigned int num_inputs;
 	unsigned int size;
 	unsigned int i;
 
-	/* Per UVC 1.1+ spec 3.7.2, the ID should be non-zero. */
-	if (id == 0) {
-		dev_err(&dev->udev->dev, "Found Unit with invalid ID 0.\n");
-		return ERR_PTR(-EINVAL);
-	}
-
-	/* Per UVC 1.1+ spec 3.7.2, the ID is unique. */
-	if (uvc_entity_by_id(dev, id)) {
-		dev_err(&dev->udev->dev, "Found multiple Units with ID %u\n", id);
-		return ERR_PTR(-EINVAL);
-	}
-
 	extra_size = roundup(extra_size, sizeof(*entity->pads));
 	if (num_pads)
 		num_inputs = type & UVC_TERM_OUTPUT ? num_pads : num_pads - 1;
@@ -805,7 +795,7 @@ static struct uvc_entity *uvc_alloc_new_entity(struct uvc_device *dev, u16 type,
 	     + num_inputs;
 	entity = kzalloc(size, GFP_KERNEL);
 	if (entity == NULL)
-		return ERR_PTR(-ENOMEM);
+		return NULL;
 
 	entity->id = id;
 	entity->type = type;
@@ -917,10 +907,10 @@ static int uvc_parse_vendor_control(struct uvc_device *dev,
 			break;
 		}
 
-		unit = uvc_alloc_new_entity(dev, UVC_VC_EXTENSION_UNIT,
-					    buffer[3], p + 1, 2 * n);
-		if (IS_ERR(unit))
-			return PTR_ERR(unit);
+		unit = uvc_alloc_entity(UVC_VC_EXTENSION_UNIT, buffer[3],
+					p + 1, 2*n);
+		if (unit == NULL)
+			return -ENOMEM;
 
 		memcpy(unit->guid, &buffer[4], 16);
 		unit->extension.bNumControls = buffer[20];
@@ -1029,10 +1019,10 @@ static int uvc_parse_standard_control(struct uvc_device *dev,
 			return -EINVAL;
 		}
 
-		term = uvc_alloc_new_entity(dev, type | UVC_TERM_INPUT,
-					    buffer[3], 1, n + p);
-		if (IS_ERR(term))
-			return PTR_ERR(term);
+		term = uvc_alloc_entity(type | UVC_TERM_INPUT, buffer[3],
+					1, n + p);
+		if (term == NULL)
+			return -ENOMEM;
 
 		if (UVC_ENTITY_TYPE(term) == UVC_ITT_CAMERA) {
 			term->camera.bControlSize = n;
@@ -1088,10 +1078,10 @@ static int uvc_parse_standard_control(struct uvc_device *dev,
 			return 0;
 		}
 
-		term = uvc_alloc_new_entity(dev, type | UVC_TERM_OUTPUT,
-					    buffer[3], 1, 0);
-		if (IS_ERR(term))
-			return PTR_ERR(term);
+		term = uvc_alloc_entity(type | UVC_TERM_OUTPUT, buffer[3],
+					1, 0);
+		if (term == NULL)
+			return -ENOMEM;
 
 		memcpy(term->baSourceID, &buffer[7], 1);
 
@@ -1110,10 +1100,9 @@ static int uvc_parse_standard_control(struct uvc_device *dev,
 			return -EINVAL;
 		}
 
-		unit = uvc_alloc_new_entity(dev, buffer[2], buffer[3],
-					    p + 1, 0);
-		if (IS_ERR(unit))
-			return PTR_ERR(unit);
+		unit = uvc_alloc_entity(buffer[2], buffer[3], p + 1, 0);
+		if (unit == NULL)
+			return -ENOMEM;
 
 		memcpy(unit->baSourceID, &buffer[5], p);
 
@@ -1133,9 +1122,9 @@ static int uvc_parse_standard_control(struct uvc_device *dev,
 			return -EINVAL;
 		}
 
-		unit = uvc_alloc_new_entity(dev, buffer[2], buffer[3], 2, n);
-		if (IS_ERR(unit))
-			return PTR_ERR(unit);
+		unit = uvc_alloc_entity(buffer[2], buffer[3], 2, n);
+		if (unit == NULL)
+			return -ENOMEM;
 
 		memcpy(unit->baSourceID, &buffer[4], 1);
 		unit->processing.wMaxMultiplier =
@@ -1162,10 +1151,9 @@ static int uvc_parse_standard_control(struct uvc_device *dev,
 			return -EINVAL;
 		}
 
-		unit = uvc_alloc_new_entity(dev, buffer[2], buffer[3],
-					    p + 1, n);
-		if (IS_ERR(unit))
-			return PTR_ERR(unit);
+		unit = uvc_alloc_entity(buffer[2], buffer[3], p + 1, n);
+		if (unit == NULL)
+			return -ENOMEM;
 
 		memcpy(unit->guid, &buffer[4], 16);
 		unit->extension.bNumControls = buffer[20];
@@ -1295,20 +1283,19 @@ static int uvc_gpio_parse(struct uvc_device *dev)
 	struct gpio_desc *gpio_privacy;
 	int irq;
 
-	gpio_privacy = devm_gpiod_get_optional(&dev->udev->dev, "privacy",
+	gpio_privacy = devm_gpiod_get_optional(&dev->intf->dev, "privacy",
 					       GPIOD_IN);
 	if (IS_ERR_OR_NULL(gpio_privacy))
 		return PTR_ERR_OR_ZERO(gpio_privacy);
 
 	irq = gpiod_to_irq(gpio_privacy);
 	if (irq < 0)
-		return dev_err_probe(&dev->udev->dev, irq,
+		return dev_err_probe(&dev->intf->dev, irq,
 				     "No IRQ for privacy GPIO\n");
 
-	unit = uvc_alloc_new_entity(dev, UVC_EXT_GPIO_UNIT,
-				    UVC_EXT_GPIO_UNIT_ID, 0, 1);
-	if (IS_ERR(unit))
-		return PTR_ERR(unit);
+	unit = uvc_alloc_entity(UVC_EXT_GPIO_UNIT, UVC_EXT_GPIO_UNIT_ID, 0, 1);
+	if (!unit)
+		return -ENOMEM;
 
 	unit->gpio.gpio_privacy = gpio_privacy;
 	unit->gpio.irq = irq;
@@ -1329,15 +1316,27 @@ static int uvc_gpio_parse(struct uvc_device *dev)
 static int uvc_gpio_init_irq(struct uvc_device *dev)
 {
 	struct uvc_entity *unit = dev->gpio_unit;
+	int ret;
 
 	if (!unit || unit->gpio.irq < 0)
 		return 0;
 
-	return devm_request_threaded_irq(&dev->udev->dev, unit->gpio.irq, NULL,
-					 uvc_gpio_irq,
-					 IRQF_ONESHOT | IRQF_TRIGGER_FALLING |
-					 IRQF_TRIGGER_RISING,
-					 "uvc_privacy_gpio", dev);
+	ret = request_threaded_irq(unit->gpio.irq, NULL, uvc_gpio_irq,
+				   IRQF_ONESHOT | IRQF_TRIGGER_FALLING |
+				   IRQF_TRIGGER_RISING,
+				   "uvc_privacy_gpio", dev);
+
+	unit->gpio.initialized = !ret;
+
+	return ret;
+}
+
+static void uvc_gpio_deinit(struct uvc_device *dev)
+{
+	if (!dev->gpio_unit || !dev->gpio_unit->gpio.initialized)
+		return;
+
+	free_irq(dev->gpio_unit->gpio.irq, dev);
 }
 
 /* ------------------------------------------------------------------------
@@ -1934,6 +1933,8 @@ static void uvc_unregister_video(struct uvc_device *dev)
 {
 	struct uvc_streaming *stream;
 
+	uvc_gpio_deinit(dev);
+
 	list_for_each_entry(stream, &dev->streams, list) {
 		/* Nothing to do here, continue. */
 		if (!video_is_registered(&stream->vdev))
@@ -2219,13 +2220,16 @@ static int uvc_probe(struct usb_interface *intf,
 #endif
 
 	/* Parse the Video Class control descriptor. */
-	if (uvc_parse_control(dev) < 0) {
+	ret = uvc_parse_control(dev);
+	if (ret < 0) {
+		ret = -ENODEV;
 		uvc_dbg(dev, PROBE, "Unable to parse UVC descriptors\n");
 		goto error;
 	}
 
 	/* Parse the associated GPIOs. */
-	if (uvc_gpio_parse(dev) < 0) {
+	ret = uvc_gpio_parse(dev);
+	if (ret < 0) {
 		uvc_dbg(dev, PROBE, "Unable to parse UVC GPIOs\n");
 		goto error;
 	}
@@ -2251,24 +2255,32 @@ static int uvc_probe(struct usb_interface *intf,
 	}
 
 	/* Register the V4L2 device. */
-	if (v4l2_device_register(&intf->dev, &dev->vdev) < 0)
+	ret = v4l2_device_register(&intf->dev, &dev->vdev);
+	if (ret < 0)
 		goto error;
 
 	/* Scan the device for video chains. */
-	if (uvc_scan_device(dev) < 0)
+	if (uvc_scan_device(dev) < 0) {
+		ret = -ENODEV;
 		goto error;
+	}
 
 	/* Initialize controls. */
-	if (uvc_ctrl_init_device(dev) < 0)
+	if (uvc_ctrl_init_device(dev) < 0) {
+		ret = -ENODEV;
 		goto error;
+	}
 
 	/* Register video device nodes. */
-	if (uvc_register_chains(dev) < 0)
+	if (uvc_register_chains(dev) < 0) {
+		ret = -ENODEV;
 		goto error;
+	}
 
 #ifdef CONFIG_MEDIA_CONTROLLER
 	/* Register the media device node */
-	if (media_device_register(&dev->mdev) < 0)
+	ret = media_device_register(&dev->mdev);
+	if (ret < 0)
 		goto error;
 #endif
 	/* Save our data pointer in the interface data. */
@@ -2302,7 +2314,7 @@ static int uvc_probe(struct usb_interface *intf,
 error:
 	uvc_unregister_video(dev);
 	kref_put(&dev->ref, uvc_delete);
-	return -ENODEV;
+	return ret;
 }
 
 static void uvc_disconnect(struct usb_interface *intf)
@@ -2478,6 +2490,15 @@ static const struct uvc_device_info uvc_quirk_force_y8 = {
  * Sort these by vendor/product ID.
  */
 static const struct usb_device_id uvc_ids[] = {
+	/* HP Webcam HD 2300 */
+	{ .match_flags		= USB_DEVICE_ID_MATCH_DEVICE
+				| USB_DEVICE_ID_MATCH_INT_INFO,
+	  .idVendor		= 0x03f0,
+	  .idProduct		= 0xe207,
+	  .bInterfaceClass	= USB_CLASS_VIDEO,
+	  .bInterfaceSubClass	= 1,
+	  .bInterfaceProtocol	= 0,
+	  .driver_info		= (kernel_ulong_t)&uvc_quirk_stream_no_fid },
 	/* Quanta ACER HD User Facing */
 	{ .match_flags		= USB_DEVICE_ID_MATCH_DEVICE
 				| USB_DEVICE_ID_MATCH_INT_INFO,
@@ -2811,6 +2832,15 @@ static const struct usb_device_id uvc_ids[] = {
 	  .bInterfaceSubClass	= 1,
 	  .bInterfaceProtocol	= 0,
 	  .driver_info		= (kernel_ulong_t)&uvc_quirk_probe_minmax },
+	/* Sonix Technology Co. Ltd. - 292A IPC AR0330 */
+	{ .match_flags		= USB_DEVICE_ID_MATCH_DEVICE
+				| USB_DEVICE_ID_MATCH_INT_INFO,
+	  .idVendor		= 0x0c45,
+	  .idProduct		= 0x6366,
+	  .bInterfaceClass	= USB_CLASS_VIDEO,
+	  .bInterfaceSubClass	= 1,
+	  .bInterfaceProtocol	= 0,
+	  .driver_info		= UVC_INFO_QUIRK(UVC_QUIRK_MJPEG_NO_EOF) },
 	/* MT6227 */
 	{ .match_flags		= USB_DEVICE_ID_MATCH_DEVICE
 				| USB_DEVICE_ID_MATCH_INT_INFO,
@@ -2839,6 +2869,15 @@ static const struct usb_device_id uvc_ids[] = {
 	  .bInterfaceSubClass	= 1,
 	  .bInterfaceProtocol	= 0,
 	  .driver_info		= (kernel_ulong_t)&uvc_quirk_probe_minmax },
+	/* Kurokesu C1 PRO */
+	{ .match_flags		= USB_DEVICE_ID_MATCH_DEVICE
+				| USB_DEVICE_ID_MATCH_INT_INFO,
+	  .idVendor		= 0x16d0,
+	  .idProduct		= 0x0ed1,
+	  .bInterfaceClass	= USB_CLASS_VIDEO,
+	  .bInterfaceSubClass	= 1,
+	  .bInterfaceProtocol	= 0,
+	  .driver_info		= UVC_INFO_QUIRK(UVC_QUIRK_MJPEG_NO_EOF) },
 	/* Syntek (HP Spartan) */
 	{ .match_flags		= USB_DEVICE_ID_MATCH_DEVICE
 				| USB_DEVICE_ID_MATCH_INT_INFO,
@@ -3023,6 +3062,15 @@ static const struct usb_device_id uvc_ids[] = {
 	  .bInterfaceProtocol	= 0,
 	  .driver_info		= UVC_INFO_QUIRK(UVC_QUIRK_PROBE_MINMAX
 					| UVC_QUIRK_IGNORE_SELECTOR_UNIT) },
+	/* Actions Microelectronics Co. Display capture-UVC05 */
+	{ .match_flags		= USB_DEVICE_ID_MATCH_DEVICE
+				| USB_DEVICE_ID_MATCH_INT_INFO,
+	  .idVendor		= 0x1de1,
+	  .idProduct		= 0xf105,
+	  .bInterfaceClass	= USB_CLASS_VIDEO,
+	  .bInterfaceSubClass	= 1,
+	  .bInterfaceProtocol	= 0,
+	  .driver_info		= UVC_INFO_QUIRK(UVC_QUIRK_DISABLE_AUTOSUSPEND) },
 	/* NXP Semiconductors IR VIDEO */
 	{ .match_flags		= USB_DEVICE_ID_MATCH_DEVICE
 				| USB_DEVICE_ID_MATCH_INT_INFO,
diff --git a/drivers/media/usb/uvc/uvc_queue.c b/drivers/media/usb/uvc/uvc_queue.c
index 16fa17bbd15e..83ed7821fa2a 100644
--- a/drivers/media/usb/uvc/uvc_queue.c
+++ b/drivers/media/usb/uvc/uvc_queue.c
@@ -483,7 +483,8 @@ static void uvc_queue_buffer_complete(struct kref *ref)
 
 	buf->state = buf->error ? UVC_BUF_STATE_ERROR : UVC_BUF_STATE_DONE;
 	vb2_set_plane_payload(&buf->buf.vb2_buf, 0, buf->bytesused);
-	vb2_buffer_done(&buf->buf.vb2_buf, VB2_BUF_STATE_DONE);
+	vb2_buffer_done(&buf->buf.vb2_buf, buf->error ? VB2_BUF_STATE_ERROR :
+							VB2_BUF_STATE_DONE);
 }
 
 /*
diff --git a/drivers/media/usb/uvc/uvc_status.c b/drivers/media/usb/uvc/uvc_status.c
index a78a88c710e2..b5f6682ff383 100644
--- a/drivers/media/usb/uvc/uvc_status.c
+++ b/drivers/media/usb/uvc/uvc_status.c
@@ -269,6 +269,7 @@ int uvc_status_init(struct uvc_device *dev)
 	dev->int_urb = usb_alloc_urb(0, GFP_KERNEL);
 	if (!dev->int_urb) {
 		kfree(dev->status);
+		dev->status = NULL;
 		return -ENOMEM;
 	}
 
diff --git a/drivers/media/usb/uvc/uvc_v4l2.c b/drivers/media/usb/uvc/uvc_v4l2.c
index f4988f03640a..cb7d9fb589fc 100644
--- a/drivers/media/usb/uvc/uvc_v4l2.c
+++ b/drivers/media/usb/uvc/uvc_v4l2.c
@@ -106,6 +106,12 @@ static int uvc_ioctl_xu_ctrl_map(struct uvc_video_chain *chain,
 	struct uvc_control_mapping *map;
 	int ret;
 
+	if (xmap->data_type > UVC_CTRL_DATA_TYPE_BITMASK) {
+		uvc_dbg(chain->dev, CONTROL,
+			"Unsupported UVC data type %u\n", xmap->data_type);
+		return -EINVAL;
+	}
+
 	map = kzalloc(sizeof(*map), GFP_KERNEL);
 	if (map == NULL)
 		return -ENOMEM;
@@ -659,6 +665,8 @@ static int uvc_v4l2_release(struct file *file)
 
 	uvc_dbg(stream->dev, CALLS, "%s\n", __func__);
 
+	uvc_ctrl_cleanup_fh(handle);
+
 	/* Only free resources if this is a privileged handle. */
 	if (uvc_has_privileges(handle))
 		uvc_queue_release(&stream->queue);
diff --git a/drivers/media/usb/uvc/uvc_video.c b/drivers/media/usb/uvc/uvc_video.c
index e00f38dd07d9..57e6f9af536f 100644
--- a/drivers/media/usb/uvc/uvc_video.c
+++ b/drivers/media/usb/uvc/uvc_video.c
@@ -20,6 +20,7 @@
 #include <linux/atomic.h>
 #include <linux/unaligned.h>
 
+#include <media/jpeg.h>
 #include <media/v4l2-common.h>
 
 #include "uvcvideo.h"
@@ -79,6 +80,27 @@ int uvc_query_ctrl(struct uvc_device *dev, u8 query, u8 unit,
 	if (likely(ret == size))
 		return 0;
 
+	/*
+	 * Some devices return shorter USB control packets than expected if the
+	 * returned value can fit in less bytes. Zero all the bytes that the
+	 * device has not written.
+	 *
+	 * This quirk is applied to all controls, regardless of their data type.
+	 * Most controls are little-endian integers, in which case the missing
+	 * bytes become 0 MSBs. For other data types, a different heuristic
+	 * could be implemented if a device is found needing it.
+	 *
+	 * We exclude UVC_GET_INFO from the quirk. UVC_GET_LEN does not need
+	 * to be excluded because its size is always 1.
+	 */
+	if (ret > 0 && query != UVC_GET_INFO) {
+		memset(data + ret, 0, size - ret);
+		dev_warn_once(&dev->udev->dev,
+			      "UVC non compliance: %s control %u on unit %u returned %d bytes when we expected %u.\n",
+			      uvc_query_name(query), cs, unit, ret, size);
+		return 0;
+	}
+
 	if (ret != -EPIPE) {
 		dev_err(&dev->udev->dev,
 			"Failed to query (%s) UVC control %u on unit %u: %d (exp. %u).\n",
@@ -236,6 +258,15 @@ static void uvc_fixup_video_ctrl(struct uvc_streaming *stream,
 
 		ctrl->dwMaxPayloadTransferSize = bandwidth;
 	}
+
+	if (stream->intf->num_altsetting > 1 &&
+	    ctrl->dwMaxPayloadTransferSize > stream->maxpsize) {
+		dev_warn_ratelimited(&stream->intf->dev,
+				     "UVC non compliance: the max payload transmission size (%u) exceeds the size of the ep max packet (%u). Using the max size.\n",
+				     ctrl->dwMaxPayloadTransferSize,
+				     stream->maxpsize);
+		ctrl->dwMaxPayloadTransferSize = stream->maxpsize;
+	}
 }
 
 static size_t uvc_video_ctrl_size(struct uvc_streaming *stream)
@@ -1116,6 +1147,7 @@ static void uvc_video_stats_stop(struct uvc_streaming *stream)
 static int uvc_video_decode_start(struct uvc_streaming *stream,
 		struct uvc_buffer *buf, const u8 *data, int len)
 {
+	u8 header_len;
 	u8 fid;
 
 	/*
@@ -1129,6 +1161,7 @@ static int uvc_video_decode_start(struct uvc_streaming *stream,
 		return -EINVAL;
 	}
 
+	header_len = data[0];
 	fid = data[1] & UVC_STREAM_FID;
 
 	/*
@@ -1210,9 +1243,31 @@ static int uvc_video_decode_start(struct uvc_streaming *stream,
 		return -EAGAIN;
 	}
 
+	/*
+	 * Some cameras, when running two parallel streams (one MJPEG alongside
+	 * another non-MJPEG stream), are known to lose the EOF packet for a frame.
+	 * We can detect the end of a frame by checking for a new SOI marker, as
+	 * the SOI always lies on the packet boundary between two frames for
+	 * these devices.
+	 */
+	if (stream->dev->quirks & UVC_QUIRK_MJPEG_NO_EOF &&
+	    (stream->cur_format->fcc == V4L2_PIX_FMT_MJPEG ||
+	    stream->cur_format->fcc == V4L2_PIX_FMT_JPEG)) {
+		const u8 *packet = data + header_len;
+
+		if (len >= header_len + 2 &&
+		    packet[0] == 0xff && packet[1] == JPEG_MARKER_SOI &&
+		    buf->bytesused != 0) {
+			buf->state = UVC_BUF_STATE_READY;
+			buf->error = 1;
+			stream->last_fid ^= UVC_STREAM_FID;
+			return -EAGAIN;
+		}
+	}
+
 	stream->last_fid = fid;
 
-	return data[0];
+	return header_len;
 }
 
 static inline enum dma_data_direction uvc_stream_dir(
@@ -1382,12 +1437,6 @@ static void uvc_video_decode_meta(struct uvc_streaming *stream,
 	if (!meta_buf || length == 2)
 		return;
 
-	if (meta_buf->length - meta_buf->bytesused <
-	    length + sizeof(meta->ns) + sizeof(meta->sof)) {
-		meta_buf->error = 1;
-		return;
-	}
-
 	has_pts = mem[1] & UVC_STREAM_PTS;
 	has_scr = mem[1] & UVC_STREAM_SCR;
 
@@ -1408,6 +1457,12 @@ static void uvc_video_decode_meta(struct uvc_streaming *stream,
 				  !memcmp(scr, stream->clock.last_scr, 6)))
 		return;
 
+	if (meta_buf->length - meta_buf->bytesused <
+	    length + sizeof(meta->ns) + sizeof(meta->sof)) {
+		meta_buf->error = 1;
+		return;
+	}
+
 	meta = (struct uvc_meta_buf *)((u8 *)meta_buf->mem + meta_buf->bytesused);
 	local_irq_save(flags);
 	time = uvc_video_get_time();
diff --git a/drivers/media/usb/uvc/uvcvideo.h b/drivers/media/usb/uvc/uvcvideo.h
index b7d24a853ce4..74ac2106f08e 100644
--- a/drivers/media/usb/uvc/uvcvideo.h
+++ b/drivers/media/usb/uvc/uvcvideo.h
@@ -76,6 +76,7 @@
 #define UVC_QUIRK_NO_RESET_RESUME	0x00004000
 #define UVC_QUIRK_DISABLE_AUTOSUSPEND	0x00008000
 #define UVC_QUIRK_INVALID_DEVICE_SOF	0x00010000
+#define UVC_QUIRK_MJPEG_NO_EOF		0x00020000
 
 /* Format flags */
 #define UVC_FMT_FLAG_COMPRESSED		0x00000001
@@ -234,6 +235,7 @@ struct uvc_entity {
 			u8  *bmControls;
 			struct gpio_desc *gpio_privacy;
 			int irq;
+			bool initialized;
 		} gpio;
 	};
 
@@ -337,7 +339,11 @@ struct uvc_video_chain {
 	struct uvc_entity *processing;		/* Processing unit */
 	struct uvc_entity *selector;		/* Selector unit */
 
-	struct mutex ctrl_mutex;		/* Protects ctrl.info */
+	struct mutex ctrl_mutex;		/*
+						 * Protects ctrl.info,
+						 * ctrl.handle and
+						 * uvc_fh.pending_async_ctrls
+						 */
 
 	struct v4l2_prio_state prio;		/* V4L2 priority state */
 	u32 caps;				/* V4L2 chain-wide caps */
@@ -612,6 +618,7 @@ struct uvc_fh {
 	struct uvc_video_chain *chain;
 	struct uvc_streaming *stream;
 	enum uvc_handle_state state;
+	unsigned int pending_async_ctrls;
 };
 
 struct uvc_driver {
@@ -795,6 +802,8 @@ int uvc_ctrl_is_accessible(struct uvc_video_chain *chain, u32 v4l2_id,
 int uvc_xu_ctrl_query(struct uvc_video_chain *chain,
 		      struct uvc_xu_control_query *xqry);
 
+void uvc_ctrl_cleanup_fh(struct uvc_fh *handle);
+
 /* Utility functions */
 struct usb_host_endpoint *uvc_find_endpoint(struct usb_host_interface *alts,
 					    u8 epaddr);
diff --git a/drivers/media/v4l2-core/v4l2-common.c b/drivers/media/v4l2-core/v4l2-common.c
index 0a2f4f0d0a07..ad0b9d5fbee7 100644
--- a/drivers/media/v4l2-core/v4l2-common.c
+++ b/drivers/media/v4l2-core/v4l2-common.c
@@ -312,6 +312,12 @@ const struct v4l2_format_info *v4l2_format_info(u32 format)
 		{ .format = V4L2_PIX_FMT_NV61M,   .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 2, .comp_planes = 2, .bpp = { 1, 2, 0, 0 }, .bpp_div = { 1, 1, 1, 1 }, .hdiv = 2, .vdiv = 1 },
 		{ .format = V4L2_PIX_FMT_P012M,   .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 2, .comp_planes = 2, .bpp = { 2, 4, 0, 0 }, .bpp_div = { 1, 1, 1, 1 }, .hdiv = 2, .vdiv = 2 },
 
+		/* Tiled YUV formats, non contiguous variant */
+		{ .format = V4L2_PIX_FMT_NV12MT,        .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 2, .comp_planes = 2, .bpp = { 1, 2, 0, 0 }, .bpp_div = { 1, 1, 1, 1 }, .hdiv = 2, .vdiv = 2,
+		  .block_w = { 64, 32, 0, 0 },	.block_h = { 32, 16, 0, 0 }},
+		{ .format = V4L2_PIX_FMT_NV12MT_16X16,  .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 2, .comp_planes = 2, .bpp = { 1, 2, 0, 0 }, .bpp_div = { 1, 1, 1, 1 }, .hdiv = 2, .vdiv = 2,
+		  .block_w = { 16,  8, 0, 0 },	.block_h = { 16,  8, 0, 0 }},
+
 		/* Bayer RGB formats */
 		{ .format = V4L2_PIX_FMT_SBGGR8,	.pixel_enc = V4L2_PIXEL_ENC_BAYER, .mem_planes = 1, .comp_planes = 1, .bpp = { 1, 0, 0, 0 }, .bpp_div = { 1, 1, 1, 1 }, .hdiv = 1, .vdiv = 1 },
 		{ .format = V4L2_PIX_FMT_SGBRG8,	.pixel_enc = V4L2_PIXEL_ENC_BAYER, .mem_planes = 1, .comp_planes = 1, .bpp = { 1, 0, 0, 0 }, .bpp_div = { 1, 1, 1, 1 }, .hdiv = 1, .vdiv = 1 },
@@ -494,10 +500,10 @@ s64 v4l2_get_link_freq(struct v4l2_ctrl_handler *handler, unsigned int mul,
 
 		freq = div_u64(v4l2_ctrl_g_ctrl_int64(ctrl) * mul, div);
 
-		pr_warn("%s: Link frequency estimated using pixel rate: result might be inaccurate\n",
-			__func__);
-		pr_warn("%s: Consider implementing support for V4L2_CID_LINK_FREQ in the transmitter driver\n",
-			__func__);
+		pr_warn_once("%s: Link frequency estimated using pixel rate: result might be inaccurate\n",
+			     __func__);
+		pr_warn_once("%s: Consider implementing support for V4L2_CID_LINK_FREQ in the transmitter driver\n",
+			     __func__);
 	}
 
 	return freq > 0 ? freq : -EINVAL;
diff --git a/drivers/media/v4l2-core/v4l2-ctrls-core.c b/drivers/media/v4l2-core/v4l2-ctrls-core.c
index eeab6a5eb7ba..675642af8601 100644
--- a/drivers/media/v4l2-core/v4l2-ctrls-core.c
+++ b/drivers/media/v4l2-core/v4l2-ctrls-core.c
@@ -897,12 +897,12 @@ static int std_validate_compound(const struct v4l2_ctrl *ctrl, u32 idx,
 
 			p_h264_sps->flags &=
 				~V4L2_H264_SPS_FLAG_QPPRIME_Y_ZERO_TRANSFORM_BYPASS;
-
-			if (p_h264_sps->chroma_format_idc < 3)
-				p_h264_sps->flags &=
-					~V4L2_H264_SPS_FLAG_SEPARATE_COLOUR_PLANE;
 		}
 
+		if (p_h264_sps->chroma_format_idc < 3)
+			p_h264_sps->flags &=
+				~V4L2_H264_SPS_FLAG_SEPARATE_COLOUR_PLANE;
+
 		if (p_h264_sps->flags & V4L2_H264_SPS_FLAG_FRAME_MBS_ONLY)
 			p_h264_sps->flags &=
 				~V4L2_H264_SPS_FLAG_MB_ADAPTIVE_FRAME_FIELD;
diff --git a/drivers/media/v4l2-core/v4l2-dev.c b/drivers/media/v4l2-core/v4l2-dev.c
index 3d7711cc42bc..56f3ab966d60 100644
--- a/drivers/media/v4l2-core/v4l2-dev.c
+++ b/drivers/media/v4l2-core/v4l2-dev.c
@@ -1052,25 +1052,25 @@ int __video_register_device(struct video_device *vdev,
 	vdev->dev.class = &video_class;
 	vdev->dev.devt = MKDEV(VIDEO_MAJOR, vdev->minor);
 	vdev->dev.parent = vdev->dev_parent;
+	vdev->dev.release = v4l2_device_release;
 	dev_set_name(&vdev->dev, "%s%d", name_base, vdev->num);
+
+	/* Increase v4l2_device refcount */
+	v4l2_device_get(vdev->v4l2_dev);
+
 	mutex_lock(&videodev_lock);
 	ret = device_register(&vdev->dev);
 	if (ret < 0) {
 		mutex_unlock(&videodev_lock);
 		pr_err("%s: device_register failed\n", __func__);
-		goto cleanup;
+		put_device(&vdev->dev);
+		return ret;
 	}
-	/* Register the release callback that will be called when the last
-	   reference to the device goes away. */
-	vdev->dev.release = v4l2_device_release;
 
 	if (nr != -1 && nr != vdev->num && warn_if_nr_in_use)
 		pr_warn("%s: requested %s%d, got %s\n", __func__,
 			name_base, nr, video_device_node_name(vdev));
 
-	/* Increase v4l2_device refcount */
-	v4l2_device_get(vdev->v4l2_dev);
-
 	/* Part 5: Register the entity. */
 	ret = video_register_media_controller(vdev);
 
diff --git a/drivers/media/v4l2-core/v4l2-dv-timings.c b/drivers/media/v4l2-core/v4l2-dv-timings.c
index 2cf5dcee0ce8..4d05873892c1 100644
--- a/drivers/media/v4l2-core/v4l2-dv-timings.c
+++ b/drivers/media/v4l2-core/v4l2-dv-timings.c
@@ -764,7 +764,7 @@ bool v4l2_detect_gtf(unsigned int frame_height,
 		u64 num;
 		u32 den;
 
-		num = ((image_width * GTF_D_C_PRIME * (u64)hfreq) -
+		num = (((u64)image_width * GTF_D_C_PRIME * hfreq) -
 		      ((u64)image_width * GTF_D_M_PRIME * 1000));
 		den = (hfreq * (100 - GTF_D_C_PRIME) + GTF_D_M_PRIME * 1000) *
 		      (2 * GTF_CELL_GRAN);
@@ -774,7 +774,7 @@ bool v4l2_detect_gtf(unsigned int frame_height,
 		u64 num;
 		u32 den;
 
-		num = ((image_width * GTF_S_C_PRIME * (u64)hfreq) -
+		num = (((u64)image_width * GTF_S_C_PRIME * hfreq) -
 		      ((u64)image_width * GTF_S_M_PRIME * 1000));
 		den = (hfreq * (100 - GTF_S_C_PRIME) + GTF_S_M_PRIME * 1000) *
 		      (2 * GTF_CELL_GRAN);
diff --git a/drivers/media/v4l2-core/v4l2-mc.c b/drivers/media/v4l2-core/v4l2-mc.c
index 4bb91359e3a9..937d358697e1 100644
--- a/drivers/media/v4l2-core/v4l2-mc.c
+++ b/drivers/media/v4l2-core/v4l2-mc.c
@@ -329,7 +329,7 @@ int v4l2_create_fwnode_links_to_pad(struct v4l2_subdev *src_sd,
 	if (!(sink->flags & MEDIA_PAD_FL_SINK))
 		return -EINVAL;
 
-	fwnode_graph_for_each_endpoint(dev_fwnode(src_sd->dev), endpoint) {
+	fwnode_graph_for_each_endpoint(src_sd->fwnode, endpoint) {
 		struct fwnode_handle *remote_ep;
 		int src_idx, sink_idx, ret;
 		struct media_pad *src;
diff --git a/drivers/media/v4l2-core/v4l2-subdev.c b/drivers/media/v4l2-core/v4l2-subdev.c
index 3a4ba08810d2..1193852bad59 100644
--- a/drivers/media/v4l2-core/v4l2-subdev.c
+++ b/drivers/media/v4l2-core/v4l2-subdev.c
@@ -439,6 +439,8 @@ static int call_enum_dv_timings(struct v4l2_subdev *sd,
 static int call_get_mbus_config(struct v4l2_subdev *sd, unsigned int pad,
 				struct v4l2_mbus_config *config)
 {
+	memset(config, 0, sizeof(*config));
+
 	return check_pad(sd, pad) ? :
 	       sd->ops->pad->get_mbus_config(sd, pad, config);
 }
diff --git a/drivers/memory/omap-gpmc.c b/drivers/memory/omap-gpmc.c
index c8a0d82f9c27..719225c09a4d 100644
--- a/drivers/memory/omap-gpmc.c
+++ b/drivers/memory/omap-gpmc.c
@@ -2245,26 +2245,6 @@ static int gpmc_probe_generic_child(struct platform_device *pdev,
 		goto err;
 	}
 
-	if (of_node_name_eq(child, "nand")) {
-		/* Warn about older DT blobs with no compatible property */
-		if (!of_property_read_bool(child, "compatible")) {
-			dev_warn(&pdev->dev,
-				 "Incompatible NAND node: missing compatible");
-			ret = -EINVAL;
-			goto err;
-		}
-	}
-
-	if (of_node_name_eq(child, "onenand")) {
-		/* Warn about older DT blobs with no compatible property */
-		if (!of_property_read_bool(child, "compatible")) {
-			dev_warn(&pdev->dev,
-				 "Incompatible OneNAND node: missing compatible");
-			ret = -EINVAL;
-			goto err;
-		}
-	}
-
 	if (of_match_node(omap_nand_ids, child)) {
 		/* NAND specific setup */
 		val = 8;
diff --git a/drivers/memory/tegra/tegra20-emc.c b/drivers/memory/tegra/tegra20-emc.c
index 7193f848d17e..9b7d30a21a5b 100644
--- a/drivers/memory/tegra/tegra20-emc.c
+++ b/drivers/memory/tegra/tegra20-emc.c
@@ -474,14 +474,15 @@ tegra_emc_find_node_by_ram_code(struct tegra_emc *emc)
 
 	ram_code = tegra_read_ram_code();
 
-	for (np = of_find_node_by_name(dev->of_node, "emc-tables"); np;
-	     np = of_find_node_by_name(np, "emc-tables")) {
+	for_each_child_of_node(dev->of_node, np) {
+		if (!of_node_name_eq(np, "emc-tables"))
+			continue;
 		err = of_property_read_u32(np, "nvidia,ram-code", &value);
 		if (err || value != ram_code) {
 			struct device_node *lpddr2_np;
 			bool cfg_mismatches = false;
 
-			lpddr2_np = of_find_node_by_name(np, "lpddr2");
+			lpddr2_np = of_get_child_by_name(np, "lpddr2");
 			if (lpddr2_np) {
 				const struct lpddr2_info *info;
 
@@ -518,7 +519,6 @@ tegra_emc_find_node_by_ram_code(struct tegra_emc *emc)
 			}
 
 			if (cfg_mismatches) {
-				of_node_put(np);
 				continue;
 			}
 		}
diff --git a/drivers/memstick/core/memstick.c b/drivers/memstick/core/memstick.c
index 9a3a784054cc..e6801ad14318 100644
--- a/drivers/memstick/core/memstick.c
+++ b/drivers/memstick/core/memstick.c
@@ -322,7 +322,7 @@ EXPORT_SYMBOL(memstick_init_req);
 static int h_memstick_read_dev_id(struct memstick_dev *card,
 				  struct memstick_request **mrq)
 {
-	struct ms_id_register id_reg;
+	struct ms_id_register id_reg = {};
 
 	if (!(*mrq)) {
 		memstick_init_req(&card->current_mrq, MS_TPC_READ_REG, &id_reg,
diff --git a/drivers/memstick/host/rtsx_usb_ms.c b/drivers/memstick/host/rtsx_usb_ms.c
index ffdd8de9ec5d..d99f8922d4ad 100644
--- a/drivers/memstick/host/rtsx_usb_ms.c
+++ b/drivers/memstick/host/rtsx_usb_ms.c
@@ -813,6 +813,7 @@ static void rtsx_usb_ms_drv_remove(struct platform_device *pdev)
 
 	host->eject = true;
 	cancel_work_sync(&host->handle_req);
+	cancel_delayed_work_sync(&host->poll_card);
 
 	mutex_lock(&host->host_mutex);
 	if (host->req) {
diff --git a/drivers/mfd/axp20x.c b/drivers/mfd/axp20x.c
index 4051551757f2..cbf1029d0333 100644
--- a/drivers/mfd/axp20x.c
+++ b/drivers/mfd/axp20x.c
@@ -214,6 +214,7 @@ static const struct regmap_range axp717_writeable_ranges[] = {
 	regmap_reg_range(AXP717_VSYS_V_POWEROFF, AXP717_VSYS_V_POWEROFF),
 	regmap_reg_range(AXP717_IRQ0_EN, AXP717_IRQ4_EN),
 	regmap_reg_range(AXP717_IRQ0_STATE, AXP717_IRQ4_STATE),
+	regmap_reg_range(AXP717_TS_PIN_CFG, AXP717_TS_PIN_CFG),
 	regmap_reg_range(AXP717_ICC_CHG_SET, AXP717_CV_CHG_SET),
 	regmap_reg_range(AXP717_DCDC_OUTPUT_CONTROL, AXP717_CPUSLDO_CONTROL),
 	regmap_reg_range(AXP717_ADC_CH_EN_CONTROL, AXP717_ADC_CH_EN_CONTROL),
@@ -1033,7 +1034,8 @@ static const struct mfd_cell axp152_cells[] = {
 };
 
 static struct mfd_cell axp313a_cells[] = {
-	MFD_CELL_NAME("axp20x-regulator"),
+	/* AXP323 is sometimes paired with AXP717 as sub-PMIC */
+	MFD_CELL_BASIC("axp20x-regulator", NULL, NULL, 0, 1),
 	MFD_CELL_RES("axp313a-pek", axp313a_pek_resources),
 };
 
diff --git a/drivers/mfd/cros_ec_dev.c b/drivers/mfd/cros_ec_dev.c
index f3dc812b359f..78c48dc624e8 100644
--- a/drivers/mfd/cros_ec_dev.c
+++ b/drivers/mfd/cros_ec_dev.c
@@ -87,7 +87,6 @@ static const struct mfd_cell cros_ec_sensorhub_cells[] = {
 };
 
 static const struct mfd_cell cros_usbpd_charger_cells[] = {
-	{ .name = "cros-charge-control", },
 	{ .name = "cros-usbpd-charger", },
 	{ .name = "cros-usbpd-logger", },
 };
@@ -108,6 +107,10 @@ static const struct mfd_cell cros_ec_keyboard_leds_cells[] = {
 	{ .name = "cros-keyboard-leds", },
 };
 
+static const struct mfd_cell cros_ec_charge_control_cells[] = {
+	{ .name = "cros-charge-control", },
+};
+
 static const struct cros_feature_to_cells cros_subdevices[] = {
 	{
 		.id		= EC_FEATURE_CEC,
@@ -144,6 +147,11 @@ static const struct cros_feature_to_cells cros_subdevices[] = {
 		.mfd_cells	= cros_ec_keyboard_leds_cells,
 		.num_cells	= ARRAY_SIZE(cros_ec_keyboard_leds_cells),
 	},
+	{
+		.id		= EC_FEATURE_CHARGER,
+		.mfd_cells	= cros_ec_charge_control_cells,
+		.num_cells	= ARRAY_SIZE(cros_ec_charge_control_cells),
+	},
 };
 
 static const struct mfd_cell cros_ec_platform_cells[] = {
diff --git a/drivers/mfd/ene-kb3930.c b/drivers/mfd/ene-kb3930.c
index fa0ad2f14a39..9460a67acb0b 100644
--- a/drivers/mfd/ene-kb3930.c
+++ b/drivers/mfd/ene-kb3930.c
@@ -162,7 +162,7 @@ static int kb3930_probe(struct i2c_client *client)
 			devm_gpiod_get_array_optional(dev, "off", GPIOD_IN);
 		if (IS_ERR(ddata->off_gpios))
 			return PTR_ERR(ddata->off_gpios);
-		if (ddata->off_gpios->ndescs < 2) {
+		if (ddata->off_gpios && ddata->off_gpios->ndescs < 2) {
 			dev_err(dev, "invalid off-gpios property\n");
 			return -EINVAL;
 		}
diff --git a/drivers/mfd/exynos-lpass.c b/drivers/mfd/exynos-lpass.c
index e58990c85ed8..8b5fed476039 100644
--- a/drivers/mfd/exynos-lpass.c
+++ b/drivers/mfd/exynos-lpass.c
@@ -104,11 +104,22 @@ static const struct regmap_config exynos_lpass_reg_conf = {
 	.fast_io	= true,
 };
 
+static void exynos_lpass_disable_lpass(void *data)
+{
+	struct platform_device *pdev = data;
+	struct exynos_lpass *lpass = platform_get_drvdata(pdev);
+
+	pm_runtime_disable(&pdev->dev);
+	if (!pm_runtime_status_suspended(&pdev->dev))
+		exynos_lpass_disable(lpass);
+}
+
 static int exynos_lpass_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct exynos_lpass *lpass;
 	void __iomem *base_top;
+	int ret;
 
 	lpass = devm_kzalloc(dev, sizeof(*lpass), GFP_KERNEL);
 	if (!lpass)
@@ -122,8 +133,8 @@ static int exynos_lpass_probe(struct platform_device *pdev)
 	if (IS_ERR(lpass->sfr0_clk))
 		return PTR_ERR(lpass->sfr0_clk);
 
-	lpass->top = regmap_init_mmio(dev, base_top,
-					&exynos_lpass_reg_conf);
+	lpass->top = devm_regmap_init_mmio(dev, base_top,
+					   &exynos_lpass_reg_conf);
 	if (IS_ERR(lpass->top)) {
 		dev_err(dev, "LPASS top regmap initialization failed\n");
 		return PTR_ERR(lpass->top);
@@ -134,18 +145,11 @@ static int exynos_lpass_probe(struct platform_device *pdev)
 	pm_runtime_enable(dev);
 	exynos_lpass_enable(lpass);
 
-	return devm_of_platform_populate(dev);
-}
-
-static void exynos_lpass_remove(struct platform_device *pdev)
-{
-	struct exynos_lpass *lpass = platform_get_drvdata(pdev);
+	ret = devm_add_action_or_reset(dev, exynos_lpass_disable_lpass, pdev);
+	if (ret)
+		return ret;
 
-	exynos_lpass_disable(lpass);
-	pm_runtime_disable(&pdev->dev);
-	if (!pm_runtime_status_suspended(&pdev->dev))
-		exynos_lpass_disable(lpass);
-	regmap_exit(lpass->top);
+	return devm_of_platform_populate(dev);
 }
 
 static int __maybe_unused exynos_lpass_suspend(struct device *dev)
@@ -185,7 +189,6 @@ static struct platform_driver exynos_lpass_driver = {
 		.of_match_table	= exynos_lpass_of_match,
 	},
 	.probe	= exynos_lpass_probe,
-	.remove_new = exynos_lpass_remove,
 };
 module_platform_driver(exynos_lpass_driver);
 
diff --git a/drivers/mfd/lpc_ich.c b/drivers/mfd/lpc_ich.c
index f14901660147..4b7d0cb9340f 100644
--- a/drivers/mfd/lpc_ich.c
+++ b/drivers/mfd/lpc_ich.c
@@ -834,8 +834,9 @@ static const struct pci_device_id lpc_ich_ids[] = {
 	{ PCI_VDEVICE(INTEL, 0x2917), LPC_ICH9ME},
 	{ PCI_VDEVICE(INTEL, 0x2918), LPC_ICH9},
 	{ PCI_VDEVICE(INTEL, 0x2919), LPC_ICH9M},
-	{ PCI_VDEVICE(INTEL, 0x3197), LPC_GLK},
 	{ PCI_VDEVICE(INTEL, 0x2b9c), LPC_COUGARMOUNTAIN},
+	{ PCI_VDEVICE(INTEL, 0x3197), LPC_GLK},
+	{ PCI_VDEVICE(INTEL, 0x31e8), LPC_GLK},
 	{ PCI_VDEVICE(INTEL, 0x3a14), LPC_ICH10DO},
 	{ PCI_VDEVICE(INTEL, 0x3a16), LPC_ICH10R},
 	{ PCI_VDEVICE(INTEL, 0x3a18), LPC_ICH10},
diff --git a/drivers/mfd/max14577.c b/drivers/mfd/max14577.c
index 6fce79ec2dc6..7e7e8af9af22 100644
--- a/drivers/mfd/max14577.c
+++ b/drivers/mfd/max14577.c
@@ -456,6 +456,7 @@ static void max14577_i2c_remove(struct i2c_client *i2c)
 {
 	struct max14577 *max14577 = i2c_get_clientdata(i2c);
 
+	device_init_wakeup(max14577->dev, false);
 	mfd_remove_devices(max14577->dev);
 	regmap_del_irq_chip(max14577->irq, max14577->irq_data);
 	if (max14577->dev_type == MAXIM_DEVICE_TYPE_MAX77836)
diff --git a/drivers/mfd/sm501.c b/drivers/mfd/sm501.c
index b3592982a83b..5b6dc1cb9bfc 100644
--- a/drivers/mfd/sm501.c
+++ b/drivers/mfd/sm501.c
@@ -920,7 +920,7 @@ static void sm501_gpio_set(struct gpio_chip *chip, unsigned offset, int value)
 {
 	struct sm501_gpio_chip *smchip = gpiochip_get_data(chip);
 	struct sm501_gpio *smgpio = smchip->ourgpio;
-	unsigned long bit = 1 << offset;
+	unsigned long bit = BIT(offset);
 	void __iomem *regs = smchip->regbase;
 	unsigned long save;
 	unsigned long val;
@@ -946,7 +946,7 @@ static int sm501_gpio_input(struct gpio_chip *chip, unsigned offset)
 	struct sm501_gpio_chip *smchip = gpiochip_get_data(chip);
 	struct sm501_gpio *smgpio = smchip->ourgpio;
 	void __iomem *regs = smchip->regbase;
-	unsigned long bit = 1 << offset;
+	unsigned long bit = BIT(offset);
 	unsigned long save;
 	unsigned long ddr;
 
@@ -971,7 +971,7 @@ static int sm501_gpio_output(struct gpio_chip *chip,
 {
 	struct sm501_gpio_chip *smchip = gpiochip_get_data(chip);
 	struct sm501_gpio *smgpio = smchip->ourgpio;
-	unsigned long bit = 1 << offset;
+	unsigned long bit = BIT(offset);
 	void __iomem *regs = smchip->regbase;
 	unsigned long save;
 	unsigned long val;
diff --git a/drivers/mfd/stmpe-spi.c b/drivers/mfd/stmpe-spi.c
index 792236f56399..b9cc85ea2c40 100644
--- a/drivers/mfd/stmpe-spi.c
+++ b/drivers/mfd/stmpe-spi.c
@@ -129,7 +129,7 @@ static const struct spi_device_id stmpe_spi_id[] = {
 	{ "stmpe2403", STMPE2403 },
 	{ }
 };
-MODULE_DEVICE_TABLE(spi, stmpe_id);
+MODULE_DEVICE_TABLE(spi, stmpe_spi_id);
 
 static struct spi_driver stmpe_spi_driver = {
 	.driver = {
diff --git a/drivers/mfd/syscon.c b/drivers/mfd/syscon.c
index 2ce15f60eb10..729e79e1be49 100644
--- a/drivers/mfd/syscon.c
+++ b/drivers/mfd/syscon.c
@@ -15,6 +15,7 @@
 #include <linux/io.h>
 #include <linux/init.h>
 #include <linux/list.h>
+#include <linux/mutex.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_platform.h>
@@ -27,7 +28,7 @@
 
 static struct platform_driver syscon_driver;
 
-static DEFINE_SPINLOCK(syscon_list_slock);
+static DEFINE_MUTEX(syscon_list_lock);
 static LIST_HEAD(syscon_list);
 
 struct syscon {
@@ -54,6 +55,8 @@ static struct syscon *of_syscon_register(struct device_node *np, bool check_res)
 	struct resource res;
 	struct reset_control *reset;
 
+	WARN_ON(!mutex_is_locked(&syscon_list_lock));
+
 	struct syscon *syscon __free(kfree) = kzalloc(sizeof(*syscon), GFP_KERNEL);
 	if (!syscon)
 		return ERR_PTR(-ENOMEM);
@@ -144,9 +147,7 @@ static struct syscon *of_syscon_register(struct device_node *np, bool check_res)
 	syscon->regmap = regmap;
 	syscon->np = np;
 
-	spin_lock(&syscon_list_slock);
 	list_add_tail(&syscon->list, &syscon_list);
-	spin_unlock(&syscon_list_slock);
 
 	return_ptr(syscon);
 
@@ -167,7 +168,7 @@ static struct regmap *device_node_get_regmap(struct device_node *np,
 {
 	struct syscon *entry, *syscon = NULL;
 
-	spin_lock(&syscon_list_slock);
+	mutex_lock(&syscon_list_lock);
 
 	list_for_each_entry(entry, &syscon_list, list)
 		if (entry->np == np) {
@@ -175,11 +176,11 @@ static struct regmap *device_node_get_regmap(struct device_node *np,
 			break;
 		}
 
-	spin_unlock(&syscon_list_slock);
-
 	if (!syscon)
 		syscon = of_syscon_register(np, check_res);
 
+	mutex_unlock(&syscon_list_lock);
+
 	if (IS_ERR(syscon))
 		return ERR_CAST(syscon);
 
@@ -210,7 +211,7 @@ int of_syscon_register_regmap(struct device_node *np, struct regmap *regmap)
 		return -ENOMEM;
 
 	/* check if syscon entry already exists */
-	spin_lock(&syscon_list_slock);
+	mutex_lock(&syscon_list_lock);
 
 	list_for_each_entry(entry, &syscon_list, list)
 		if (entry->np == np) {
@@ -223,12 +224,12 @@ int of_syscon_register_regmap(struct device_node *np, struct regmap *regmap)
 
 	/* register the regmap in syscon list */
 	list_add_tail(&syscon->list, &syscon_list);
-	spin_unlock(&syscon_list_slock);
+	mutex_unlock(&syscon_list_lock);
 
 	return 0;
 
 err_unlock:
-	spin_unlock(&syscon_list_slock);
+	mutex_unlock(&syscon_list_lock);
 	kfree(syscon);
 	return ret;
 }
diff --git a/drivers/mfd/tps65219.c b/drivers/mfd/tps65219.c
index 57ff5cb294a6..d3b77abec786 100644
--- a/drivers/mfd/tps65219.c
+++ b/drivers/mfd/tps65219.c
@@ -228,7 +228,6 @@ static const struct regmap_irq_chip tps65219_irq_chip = {
 static int tps65219_probe(struct i2c_client *client)
 {
 	struct tps65219 *tps;
-	unsigned int chipid;
 	bool pwr_button;
 	int ret;
 
@@ -253,12 +252,6 @@ static int tps65219_probe(struct i2c_client *client)
 	if (ret)
 		return ret;
 
-	ret = regmap_read(tps->regmap, TPS65219_REG_TI_DEV_ID, &chipid);
-	if (ret) {
-		dev_err(tps->dev, "Failed to read device ID: %d\n", ret);
-		return ret;
-	}
-
 	ret = devm_mfd_add_devices(tps->dev, PLATFORM_DEVID_AUTO,
 				   tps65219_cells, ARRAY_SIZE(tps65219_cells),
 				   NULL, 0, regmap_irq_get_domain(tps->irq_data));
diff --git a/drivers/misc/cardreader/rtsx_usb.c b/drivers/misc/cardreader/rtsx_usb.c
index f150d8769f19..f546b050cb49 100644
--- a/drivers/misc/cardreader/rtsx_usb.c
+++ b/drivers/misc/cardreader/rtsx_usb.c
@@ -698,6 +698,12 @@ static void rtsx_usb_disconnect(struct usb_interface *intf)
 }
 
 #ifdef CONFIG_PM
+static int rtsx_usb_resume_child(struct device *dev, void *data)
+{
+	pm_request_resume(dev);
+	return 0;
+}
+
 static int rtsx_usb_suspend(struct usb_interface *intf, pm_message_t message)
 {
 	struct rtsx_ucr *ucr =
@@ -713,8 +719,10 @@ static int rtsx_usb_suspend(struct usb_interface *intf, pm_message_t message)
 			mutex_unlock(&ucr->dev_mutex);
 
 			/* Defer the autosuspend if card exists */
-			if (val & (SD_CD | MS_CD))
+			if (val & (SD_CD | MS_CD)) {
+				device_for_each_child(&intf->dev, NULL, rtsx_usb_resume_child);
 				return -EAGAIN;
+			}
 		} else {
 			/* There is an ongoing operation*/
 			return -EAGAIN;
@@ -724,12 +732,6 @@ static int rtsx_usb_suspend(struct usb_interface *intf, pm_message_t message)
 	return 0;
 }
 
-static int rtsx_usb_resume_child(struct device *dev, void *data)
-{
-	pm_request_resume(dev);
-	return 0;
-}
-
 static int rtsx_usb_resume(struct usb_interface *intf)
 {
 	device_for_each_child(&intf->dev, NULL, rtsx_usb_resume_child);
diff --git a/drivers/misc/eeprom/digsy_mtc_eeprom.c b/drivers/misc/eeprom/digsy_mtc_eeprom.c
index 88888485e6f8..ee58f7ce5bfa 100644
--- a/drivers/misc/eeprom/digsy_mtc_eeprom.c
+++ b/drivers/misc/eeprom/digsy_mtc_eeprom.c
@@ -50,7 +50,7 @@ static struct platform_device digsy_mtc_eeprom = {
 };
 
 static struct gpiod_lookup_table eeprom_spi_gpiod_table = {
-	.dev_id         = "spi_gpio",
+	.dev_id         = "spi_gpio.1",
 	.table          = {
 		GPIO_LOOKUP("gpio@b00", GPIO_EEPROM_CLK,
 			    "sck", GPIO_ACTIVE_HIGH),
diff --git a/drivers/misc/eeprom/ee1004.c b/drivers/misc/eeprom/ee1004.c
index 89224d4af4a2..e13f9fdd9d7b 100644
--- a/drivers/misc/eeprom/ee1004.c
+++ b/drivers/misc/eeprom/ee1004.c
@@ -304,6 +304,10 @@ static int ee1004_probe(struct i2c_client *client)
 				     I2C_FUNC_SMBUS_BYTE | I2C_FUNC_SMBUS_READ_BYTE_DATA))
 		return -EPFNOSUPPORT;
 
+	err = i2c_smbus_read_byte(client);
+	if (err < 0)
+		return -ENODEV;
+
 	mutex_lock(&ee1004_bus_lock);
 
 	err = ee1004_init_bus_data(client);
diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c
index 74181b8c386b..e567a36275af 100644
--- a/drivers/misc/fastrpc.c
+++ b/drivers/misc/fastrpc.c
@@ -992,7 +992,7 @@ static int fastrpc_get_args(u32 kernel, struct fastrpc_invoke_ctx *ctx)
 			mmap_read_lock(current->mm);
 			vma = find_vma(current->mm, ctx->args[i].ptr);
 			if (vma)
-				pages[i].addr += ctx->args[i].ptr -
+				pages[i].addr += (ctx->args[i].ptr & PAGE_MASK) -
 						 vma->vm_start;
 			mmap_read_unlock(current->mm);
 
@@ -1019,8 +1019,8 @@ static int fastrpc_get_args(u32 kernel, struct fastrpc_invoke_ctx *ctx)
 					(pkt_size - rlen);
 			pages[i].addr = pages[i].addr &	PAGE_MASK;
 
-			pg_start = (args & PAGE_MASK) >> PAGE_SHIFT;
-			pg_end = ((args + len - 1) & PAGE_MASK) >> PAGE_SHIFT;
+			pg_start = (rpra[i].buf.pv & PAGE_MASK) >> PAGE_SHIFT;
+			pg_end = ((rpra[i].buf.pv + len - 1) & PAGE_MASK) >> PAGE_SHIFT;
 			pages[i].size = (pg_end - pg_start + 1) * PAGE_SIZE;
 			args = args + mlen;
 			rlen -= mlen;
@@ -2344,7 +2344,7 @@ static int fastrpc_rpmsg_probe(struct rpmsg_device *rpdev)
 
 		err = fastrpc_device_register(rdev, data, false, domains[domain_id]);
 		if (err)
-			goto fdev_error;
+			goto populate_error;
 		break;
 	default:
 		err = -EINVAL;
diff --git a/drivers/misc/lkdtm/perms.c b/drivers/misc/lkdtm/perms.c
index 5b861dbff27e..6c24426104ba 100644
--- a/drivers/misc/lkdtm/perms.c
+++ b/drivers/misc/lkdtm/perms.c
@@ -29,6 +29,13 @@ static const unsigned long rodata = 0xAA55AA55;
 static unsigned long ro_after_init __ro_after_init = 0x55AA5500;
 
 /*
+ * This is a pointer to do_nothing() which is initialized at runtime rather
+ * than build time to avoid objtool IBT validation warnings caused by an
+ * inlined unrolled memcpy() in execute_location().
+ */
+static void __ro_after_init *do_nothing_ptr;
+
+/*
  * This just returns to the caller. It is designed to be copied into
  * non-executable memory regions.
  */
@@ -65,13 +72,12 @@ static noinline __nocfi void execute_location(void *dst, bool write)
 {
 	void (*func)(void);
 	func_desc_t fdesc;
-	void *do_nothing_text = dereference_function_descriptor(do_nothing);
 
-	pr_info("attempting ok execution at %px\n", do_nothing_text);
+	pr_info("attempting ok execution at %px\n", do_nothing_ptr);
 	do_nothing();
 
 	if (write == CODE_WRITE) {
-		memcpy(dst, do_nothing_text, EXEC_SIZE);
+		memcpy(dst, do_nothing_ptr, EXEC_SIZE);
 		flush_icache_range((unsigned long)dst,
 				   (unsigned long)dst + EXEC_SIZE);
 	}
@@ -267,6 +273,8 @@ static void lkdtm_ACCESS_NULL(void)
 
 void __init lkdtm_perms_init(void)
 {
+	do_nothing_ptr = dereference_function_descriptor(do_nothing);
+
 	/* Make sure we can write to __ro_after_init values during __init */
 	ro_after_init |= 0xAA;
 }
diff --git a/drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gpio.c b/drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gpio.c
index 3c1359d8d4e6..55b892f982e9 100644
--- a/drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gpio.c
+++ b/drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gpio.c
@@ -37,6 +37,7 @@
 struct pci1xxxx_gpio {
 	struct auxiliary_device *aux_dev;
 	void __iomem *reg_base;
+	raw_spinlock_t wa_lock;
 	struct gpio_chip gpio;
 	spinlock_t lock;
 	int irq_base;
@@ -164,7 +165,7 @@ static void pci1xxxx_gpio_irq_ack(struct irq_data *data)
 	unsigned long flags;
 
 	spin_lock_irqsave(&priv->lock, flags);
-	pci1xxx_assign_bit(priv->reg_base, INTR_STAT_OFFSET(gpio), (gpio % 32), true);
+	writel(BIT(gpio % 32), priv->reg_base + INTR_STAT_OFFSET(gpio));
 	spin_unlock_irqrestore(&priv->lock, flags);
 }
 
@@ -254,6 +255,7 @@ static irqreturn_t pci1xxxx_gpio_irq_handler(int irq, void *dev_id)
 	struct pci1xxxx_gpio *priv = dev_id;
 	struct gpio_chip *gc =  &priv->gpio;
 	unsigned long int_status = 0;
+	unsigned long wa_flags;
 	unsigned long flags;
 	u8 pincount;
 	int bit;
@@ -277,7 +279,9 @@ static irqreturn_t pci1xxxx_gpio_irq_handler(int irq, void *dev_id)
 			writel(BIT(bit), priv->reg_base + INTR_STATUS_OFFSET(gpiobank));
 			spin_unlock_irqrestore(&priv->lock, flags);
 			irq = irq_find_mapping(gc->irq.domain, (bit + (gpiobank * 32)));
-			handle_nested_irq(irq);
+			raw_spin_lock_irqsave(&priv->wa_lock, wa_flags);
+			generic_handle_irq(irq);
+			raw_spin_unlock_irqrestore(&priv->wa_lock, wa_flags);
 		}
 	}
 	spin_lock_irqsave(&priv->lock, flags);
diff --git a/drivers/misc/mei/bus.c b/drivers/misc/mei/bus.c
index 5576146ab13b..04f9a4b79d85 100644
--- a/drivers/misc/mei/bus.c
+++ b/drivers/misc/mei/bus.c
@@ -1353,10 +1353,16 @@ static void mei_dev_bus_put(struct mei_device *bus)
 static void mei_cl_bus_dev_release(struct device *dev)
 {
 	struct mei_cl_device *cldev = to_mei_cl_device(dev);
+	struct mei_device *mdev = cldev->cl->dev;
+	struct mei_cl *cl;
 
 	mei_cl_flush_queues(cldev->cl, NULL);
 	mei_me_cl_put(cldev->me_cl);
 	mei_dev_bus_put(cldev->bus);
+
+	list_for_each_entry(cl, &mdev->file_list, link)
+		WARN_ON(cl == cldev->cl);
+
 	kfree(cldev->cl);
 	kfree(cldev);
 }
diff --git a/drivers/misc/mei/hw-me-regs.h b/drivers/misc/mei/hw-me-regs.h
index c3a6657dcd4a..bc40b940ae21 100644
--- a/drivers/misc/mei/hw-me-regs.h
+++ b/drivers/misc/mei/hw-me-regs.h
@@ -117,6 +117,9 @@
 
 #define MEI_DEV_ID_LNL_M      0xA870  /* Lunar Lake Point M */
 
+#define MEI_DEV_ID_PTL_H      0xE370  /* Panther Lake H */
+#define MEI_DEV_ID_PTL_P      0xE470  /* Panther Lake P */
+
 /*
  * MEI HW Section
  */
diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c
index 6589635f8ba3..3f9c60b579ae 100644
--- a/drivers/misc/mei/pci-me.c
+++ b/drivers/misc/mei/pci-me.c
@@ -124,6 +124,9 @@ static const struct pci_device_id mei_me_pci_tbl[] = {
 
 	{MEI_PCI_DEVICE(MEI_DEV_ID_LNL_M, MEI_ME_PCH15_CFG)},
 
+	{MEI_PCI_DEVICE(MEI_DEV_ID_PTL_H, MEI_ME_PCH15_CFG)},
+	{MEI_PCI_DEVICE(MEI_DEV_ID_PTL_P, MEI_ME_PCH15_CFG)},
+
 	/* required last entry */
 	{0, }
 };
diff --git a/drivers/misc/mei/platform-vsc.c b/drivers/misc/mei/platform-vsc.c
index 20a11b299bcd..ab80bd3271b2 100644
--- a/drivers/misc/mei/platform-vsc.c
+++ b/drivers/misc/mei/platform-vsc.c
@@ -379,6 +379,8 @@ err_stop:
 err_cancel:
 	mei_cancel_work(mei_dev);
 
+	vsc_tp_register_event_cb(tp, NULL, NULL);
+
 	mei_disable_interrupts(mei_dev);
 
 	return ret;
@@ -387,11 +389,14 @@ err_cancel:
 static void mei_vsc_remove(struct platform_device *pdev)
 {
 	struct mei_device *mei_dev = platform_get_drvdata(pdev);
+	struct mei_vsc_hw *hw = mei_dev_to_vsc_hw(mei_dev);
 
 	pm_runtime_disable(mei_dev->dev);
 
 	mei_stop(mei_dev);
 
+	vsc_tp_register_event_cb(hw->tp, NULL, NULL);
+
 	mei_disable_interrupts(mei_dev);
 
 	mei_deregister(mei_dev);
diff --git a/drivers/misc/mei/vsc-tp.c b/drivers/misc/mei/vsc-tp.c
index 1618cca9a731..27c921c752e9 100644
--- a/drivers/misc/mei/vsc-tp.c
+++ b/drivers/misc/mei/vsc-tp.c
@@ -36,20 +36,24 @@
 #define VSC_TP_XFER_TIMEOUT_BYTES		700
 #define VSC_TP_PACKET_PADDING_SIZE		1
 #define VSC_TP_PACKET_SIZE(pkt) \
-	(sizeof(struct vsc_tp_packet) + le16_to_cpu((pkt)->len) + VSC_TP_CRC_SIZE)
+	(sizeof(struct vsc_tp_packet_hdr) + le16_to_cpu((pkt)->hdr.len) + VSC_TP_CRC_SIZE)
 #define VSC_TP_MAX_PACKET_SIZE \
-	(sizeof(struct vsc_tp_packet) + VSC_TP_MAX_MSG_SIZE + VSC_TP_CRC_SIZE)
+	(sizeof(struct vsc_tp_packet_hdr) + VSC_TP_MAX_MSG_SIZE + VSC_TP_CRC_SIZE)
 #define VSC_TP_MAX_XFER_SIZE \
 	(VSC_TP_MAX_PACKET_SIZE + VSC_TP_XFER_TIMEOUT_BYTES)
 #define VSC_TP_NEXT_XFER_LEN(len, offset) \
-	(len + sizeof(struct vsc_tp_packet) + VSC_TP_CRC_SIZE - offset + VSC_TP_PACKET_PADDING_SIZE)
+	(len + sizeof(struct vsc_tp_packet_hdr) + VSC_TP_CRC_SIZE - offset + VSC_TP_PACKET_PADDING_SIZE)
 
-struct vsc_tp_packet {
+struct vsc_tp_packet_hdr {
 	__u8 sync;
 	__u8 cmd;
 	__le16 len;
 	__le32 seq;
-	__u8 buf[] __counted_by(len);
+};
+
+struct vsc_tp_packet {
+	struct vsc_tp_packet_hdr hdr;
+	__u8 buf[VSC_TP_MAX_XFER_SIZE - sizeof(struct vsc_tp_packet_hdr)];
 };
 
 struct vsc_tp {
@@ -67,17 +71,16 @@ struct vsc_tp {
 	u32 seq;
 
 	/* command buffer */
-	void *tx_buf;
-	void *rx_buf;
+	struct vsc_tp_packet *tx_buf;
+	struct vsc_tp_packet *rx_buf;
 
 	atomic_t assert_cnt;
 	wait_queue_head_t xfer_wait;
 
 	vsc_tp_event_cb_t event_notify;
 	void *event_notify_context;
-
-	/* used to protect command download */
-	struct mutex mutex;
+	struct mutex event_notify_mutex;	/* protects event_notify + context */
+	struct mutex mutex;			/* protects command download */
 };
 
 /* GPIO resources */
@@ -109,6 +112,8 @@ static irqreturn_t vsc_tp_thread_isr(int irq, void *data)
 {
 	struct vsc_tp *tp = data;
 
+	guard(mutex)(&tp->event_notify_mutex);
+
 	if (tp->event_notify)
 		tp->event_notify(tp->event_notify_context);
 
@@ -158,12 +163,12 @@ static int vsc_tp_dev_xfer(struct vsc_tp *tp, void *obuf, void *ibuf, size_t len
 static int vsc_tp_xfer_helper(struct vsc_tp *tp, struct vsc_tp_packet *pkt,
 			      void *ibuf, u16 ilen)
 {
-	int ret, offset = 0, cpy_len, src_len, dst_len = sizeof(struct vsc_tp_packet);
+	int ret, offset = 0, cpy_len, src_len, dst_len = sizeof(struct vsc_tp_packet_hdr);
 	int next_xfer_len = VSC_TP_PACKET_SIZE(pkt) + VSC_TP_XFER_TIMEOUT_BYTES;
-	u8 *src, *crc_src, *rx_buf = tp->rx_buf;
+	u8 *src, *crc_src, *rx_buf = (u8 *)tp->rx_buf;
 	int count_down = VSC_TP_MAX_XFER_COUNT;
 	u32 recv_crc = 0, crc = ~0;
-	struct vsc_tp_packet ack;
+	struct vsc_tp_packet_hdr ack;
 	u8 *dst = (u8 *)&ack;
 	bool synced = false;
 
@@ -280,10 +285,10 @@ int vsc_tp_xfer(struct vsc_tp *tp, u8 cmd, const void *obuf, size_t olen,
 
 	guard(mutex)(&tp->mutex);
 
-	pkt->sync = VSC_TP_PACKET_SYNC;
-	pkt->cmd = cmd;
-	pkt->len = cpu_to_le16(olen);
-	pkt->seq = cpu_to_le32(++tp->seq);
+	pkt->hdr.sync = VSC_TP_PACKET_SYNC;
+	pkt->hdr.cmd = cmd;
+	pkt->hdr.len = cpu_to_le16(olen);
+	pkt->hdr.seq = cpu_to_le32(++tp->seq);
 	memcpy(pkt->buf, obuf, olen);
 
 	crc = ~crc32(~0, (u8 *)pkt, sizeof(pkt) + olen);
@@ -320,7 +325,7 @@ int vsc_tp_rom_xfer(struct vsc_tp *tp, const void *obuf, void *ibuf, size_t len)
 	guard(mutex)(&tp->mutex);
 
 	/* rom xfer is big endian */
-	cpu_to_be32_array(tp->tx_buf, obuf, words);
+	cpu_to_be32_array((__be32 *)tp->tx_buf, obuf, words);
 
 	ret = read_poll_timeout(gpiod_get_value_cansleep, ret,
 				!ret, VSC_TP_ROM_XFER_POLL_DELAY_US,
@@ -336,7 +341,7 @@ int vsc_tp_rom_xfer(struct vsc_tp *tp, const void *obuf, void *ibuf, size_t len)
 		return ret;
 
 	if (ibuf)
-		be32_to_cpu_array(ibuf, tp->rx_buf, words);
+		be32_to_cpu_array(ibuf, (__be32 *)tp->rx_buf, words);
 
 	return ret;
 }
@@ -397,6 +402,8 @@ EXPORT_SYMBOL_NS_GPL(vsc_tp_need_read, VSC_TP);
 int vsc_tp_register_event_cb(struct vsc_tp *tp, vsc_tp_event_cb_t event_cb,
 			    void *context)
 {
+	guard(mutex)(&tp->event_notify_mutex);
+
 	tp->event_notify = event_cb;
 	tp->event_notify_context = context;
 
@@ -492,11 +499,11 @@ static int vsc_tp_probe(struct spi_device *spi)
 	if (!tp)
 		return -ENOMEM;
 
-	tp->tx_buf = devm_kzalloc(dev, VSC_TP_MAX_XFER_SIZE, GFP_KERNEL);
+	tp->tx_buf = devm_kzalloc(dev, sizeof(*tp->tx_buf), GFP_KERNEL);
 	if (!tp->tx_buf)
 		return -ENOMEM;
 
-	tp->rx_buf = devm_kzalloc(dev, VSC_TP_MAX_XFER_SIZE, GFP_KERNEL);
+	tp->rx_buf = devm_kzalloc(dev, sizeof(*tp->rx_buf), GFP_KERNEL);
 	if (!tp->rx_buf)
 		return -ENOMEM;
 
@@ -504,7 +511,7 @@ static int vsc_tp_probe(struct spi_device *spi)
 	if (ret)
 		return ret;
 
-	tp->wakeuphost = devm_gpiod_get(dev, "wakeuphost", GPIOD_IN);
+	tp->wakeuphost = devm_gpiod_get(dev, "wakeuphostint", GPIOD_IN);
 	if (IS_ERR(tp->wakeuphost))
 		return PTR_ERR(tp->wakeuphost);
 
@@ -528,6 +535,7 @@ static int vsc_tp_probe(struct spi_device *spi)
 		return ret;
 
 	mutex_init(&tp->mutex);
+	mutex_init(&tp->event_notify_mutex);
 
 	/* only one child acpi device */
 	ret = acpi_dev_for_each_child(ACPI_COMPANION(dev),
@@ -550,10 +558,11 @@ static int vsc_tp_probe(struct spi_device *spi)
 	return 0;
 
 err_destroy_lock:
-	mutex_destroy(&tp->mutex);
-
 	free_irq(spi->irq, tp);
 
+	mutex_destroy(&tp->event_notify_mutex);
+	mutex_destroy(&tp->mutex);
+
 	return ret;
 }
 
@@ -563,9 +572,10 @@ static void vsc_tp_remove(struct spi_device *spi)
 
 	platform_device_unregister(tp->pdev);
 
-	mutex_destroy(&tp->mutex);
-
 	free_irq(spi->irq, tp);
+
+	mutex_destroy(&tp->event_notify_mutex);
+	mutex_destroy(&tp->mutex);
 }
 
 static void vsc_tp_shutdown(struct spi_device *spi)
diff --git a/drivers/misc/pci_endpoint_test.c b/drivers/misc/pci_endpoint_test.c
index 3aaaf47fa4ee..f05256b7c208 100644
--- a/drivers/misc/pci_endpoint_test.c
+++ b/drivers/misc/pci_endpoint_test.c
@@ -85,7 +85,6 @@
 #define PCI_DEVICE_ID_RENESAS_R8A774E1		0x0025
 #define PCI_DEVICE_ID_RENESAS_R8A779F0		0x0031
 
-#define PCI_VENDOR_ID_ROCKCHIP			0x1d87
 #define PCI_DEVICE_ID_ROCKCHIP_RK3588		0x3588
 
 static DEFINE_IDA(pci_endpoint_test_ida);
@@ -235,7 +234,7 @@ static bool pci_endpoint_test_request_irq(struct pci_endpoint_test *test)
 	return true;
 
 fail:
-	switch (irq_type) {
+	switch (test->irq_type) {
 	case IRQ_TYPE_INTX:
 		dev_err(dev, "Failed to request IRQ %d for Legacy\n",
 			pci_irq_vector(pdev, i));
@@ -252,6 +251,9 @@ fail:
 		break;
 	}
 
+	test->num_irqs = i;
+	pci_endpoint_test_release_irq(test);
+
 	return false;
 }
 
@@ -285,11 +287,13 @@ static bool pci_endpoint_test_bar(struct pci_endpoint_test *test,
 	void *read_buf __free(kfree) = NULL;
 	struct pci_dev *pdev = test->pdev;
 
+	bar_size = pci_resource_len(pdev, barno);
+	if (!bar_size)
+		return -ENODATA;
+
 	if (!test->bar[barno])
 		return false;
 
-	bar_size = pci_resource_len(pdev, barno);
-
 	if (barno == test->test_reg_bar)
 		bar_size = 0x4;
 
@@ -739,6 +743,7 @@ static bool pci_endpoint_test_set_irq(struct pci_endpoint_test *test,
 	if (!pci_endpoint_test_request_irq(test))
 		goto err;
 
+	irq_type = test->irq_type;
 	return true;
 
 err:
diff --git a/drivers/misc/tps6594-pfsm.c b/drivers/misc/tps6594-pfsm.c
index 9bcca1856bfe..db3d6a21a212 100644
--- a/drivers/misc/tps6594-pfsm.c
+++ b/drivers/misc/tps6594-pfsm.c
@@ -281,6 +281,9 @@ static int tps6594_pfsm_probe(struct platform_device *pdev)
 	pfsm->miscdev.minor = MISC_DYNAMIC_MINOR;
 	pfsm->miscdev.name = devm_kasprintf(dev, GFP_KERNEL, "pfsm-%ld-0x%02x",
 					    tps->chip_id, tps->reg);
+	if (!pfsm->miscdev.name)
+		return -ENOMEM;
+
 	pfsm->miscdev.fops = &tps6594_pfsm_fops;
 	pfsm->miscdev.parent = dev->parent;
 	pfsm->chip_id = tps->chip_id;
diff --git a/drivers/misc/vmw_vmci/vmci_host.c b/drivers/misc/vmw_vmci/vmci_host.c
index abe79f6fd2a7..b64944367ac5 100644
--- a/drivers/misc/vmw_vmci/vmci_host.c
+++ b/drivers/misc/vmw_vmci/vmci_host.c
@@ -227,6 +227,7 @@ static int drv_cp_harray_to_user(void __user *user_buf_uva,
 static int vmci_host_setup_notify(struct vmci_ctx *context,
 				  unsigned long uva)
 {
+	struct page *page;
 	int retval;
 
 	if (context->notify_page) {
@@ -243,13 +244,11 @@ static int vmci_host_setup_notify(struct vmci_ctx *context,
 	/*
 	 * Lock physical page backing a given user VA.
 	 */
-	retval = get_user_pages_fast(uva, 1, FOLL_WRITE, &context->notify_page);
-	if (retval != 1) {
-		context->notify_page = NULL;
+	retval = get_user_pages_fast(uva, 1, FOLL_WRITE, &page);
+	if (retval != 1)
 		return VMCI_ERROR_GENERIC;
-	}
-	if (context->notify_page == NULL)
-		return VMCI_ERROR_UNAVAILABLE;
+
+	context->notify_page = page;
 
 	/*
 	 * Map the locked page and set up notify pointer.
diff --git a/drivers/mmc/core/card.h b/drivers/mmc/core/card.h
index 3205feb1e8ff..9cbdd240c3a7 100644
--- a/drivers/mmc/core/card.h
+++ b/drivers/mmc/core/card.h
@@ -89,6 +89,7 @@ struct mmc_fixup {
 #define CID_MANFID_MICRON       0x13
 #define CID_MANFID_SAMSUNG      0x15
 #define CID_MANFID_APACER       0x27
+#define CID_MANFID_SWISSBIT     0x5D
 #define CID_MANFID_KINGSTON     0x70
 #define CID_MANFID_HYNIX	0x90
 #define CID_MANFID_KINGSTON_SD	0x9F
@@ -294,4 +295,9 @@ static inline int mmc_card_broken_sd_poweroff_notify(const struct mmc_card *c)
 	return c->quirks & MMC_QUIRK_BROKEN_SD_POWEROFF_NOTIFY;
 }
 
+static inline int mmc_card_no_uhs_ddr50_tuning(const struct mmc_card *c)
+{
+	return c->quirks & MMC_QUIRK_NO_UHS_DDR50_TUNING;
+}
+
 #endif
diff --git a/drivers/mmc/core/quirks.h b/drivers/mmc/core/quirks.h
index 89b512905be1..c417ed34c057 100644
--- a/drivers/mmc/core/quirks.h
+++ b/drivers/mmc/core/quirks.h
@@ -34,6 +34,22 @@ static const struct mmc_fixup __maybe_unused mmc_sd_fixups[] = {
 		   MMC_QUIRK_BROKEN_SD_CACHE | MMC_QUIRK_BROKEN_SD_POWEROFF_NOTIFY,
 		   EXT_CSD_REV_ANY),
 
+	/*
+	 * Swissbit series S46-u cards throw I/O errors during tuning requests
+	 * after the initial tuning request expectedly times out. This has
+	 * only been observed on cards manufactured on 01/2019 that are using
+	 * Bay Trail host controllers.
+	 */
+	_FIXUP_EXT("0016G", CID_MANFID_SWISSBIT, 0x5342, 2019, 1,
+		   0, -1ull, SDIO_ANY_ID, SDIO_ANY_ID, add_quirk_sd,
+		   MMC_QUIRK_NO_UHS_DDR50_TUNING, EXT_CSD_REV_ANY),
+
+	/*
+	 * Some SD cards reports discard support while they don't
+	 */
+	MMC_FIXUP(CID_NAME_ANY, CID_MANFID_SANDISK_SD, 0x5344, add_quirk_sd,
+		  MMC_QUIRK_BROKEN_SD_DISCARD),
+
 	END_FIXUP
 };
 
@@ -137,12 +153,6 @@ static const struct mmc_fixup __maybe_unused mmc_blk_fixups[] = {
 	MMC_FIXUP("M62704", CID_MANFID_KINGSTON, 0x0100, add_quirk_mmc,
 		  MMC_QUIRK_TRIM_BROKEN),
 
-	/*
-	 * Some SD cards reports discard support while they don't
-	 */
-	MMC_FIXUP(CID_NAME_ANY, CID_MANFID_SANDISK_SD, 0x5344, add_quirk_sd,
-		  MMC_QUIRK_BROKEN_SD_DISCARD),
-
 	END_FIXUP
 };
 
diff --git a/drivers/mmc/core/sd.c b/drivers/mmc/core/sd.c
index 63915541c0e4..916ae9996e9d 100644
--- a/drivers/mmc/core/sd.c
+++ b/drivers/mmc/core/sd.c
@@ -614,6 +614,29 @@ static int sd_set_current_limit(struct mmc_card *card, u8 *status)
 }
 
 /*
+ * Determine if the card should tune or not.
+ */
+static bool mmc_sd_use_tuning(struct mmc_card *card)
+{
+	/*
+	 * SPI mode doesn't define CMD19 and tuning is only valid for SDR50 and
+	 * SDR104 mode SD-cards. Note that tuning is mandatory for SDR104.
+	 */
+	if (mmc_host_is_spi(card->host))
+		return false;
+
+	switch (card->host->ios.timing) {
+	case MMC_TIMING_UHS_SDR50:
+	case MMC_TIMING_UHS_SDR104:
+		return true;
+	case MMC_TIMING_UHS_DDR50:
+		return !mmc_card_no_uhs_ddr50_tuning(card);
+	}
+
+	return false;
+}
+
+/*
  * UHS-I specific initialization procedure
  */
 static int mmc_sd_init_uhs_card(struct mmc_card *card)
@@ -656,14 +679,7 @@ static int mmc_sd_init_uhs_card(struct mmc_card *card)
 	if (err)
 		goto out;
 
-	/*
-	 * SPI mode doesn't define CMD19 and tuning is only valid for SDR50 and
-	 * SDR104 mode SD-cards. Note that tuning is mandatory for SDR104.
-	 */
-	if (!mmc_host_is_spi(card->host) &&
-		(card->host->ios.timing == MMC_TIMING_UHS_SDR50 ||
-		 card->host->ios.timing == MMC_TIMING_UHS_DDR50 ||
-		 card->host->ios.timing == MMC_TIMING_UHS_SDR104)) {
+	if (mmc_sd_use_tuning(card)) {
 		err = mmc_execute_tuning(card);
 
 		/*
diff --git a/drivers/mmc/core/sdio.c b/drivers/mmc/core/sdio.c
index 9566837c9848..4b19b8a16b09 100644
--- a/drivers/mmc/core/sdio.c
+++ b/drivers/mmc/core/sdio.c
@@ -458,6 +458,8 @@ static unsigned mmc_sdio_get_max_clock(struct mmc_card *card)
 	if (mmc_card_sd_combo(card))
 		max_dtr = min(max_dtr, mmc_sd_get_max_clock(card));
 
+	max_dtr = min_not_zero(max_dtr, card->quirk_max_rate);
+
 	return max_dtr;
 }
 
diff --git a/drivers/mmc/host/atmel-mci.c b/drivers/mmc/host/atmel-mci.c
index cdbd2edf4b2e..8c0853dca8b9 100644
--- a/drivers/mmc/host/atmel-mci.c
+++ b/drivers/mmc/host/atmel-mci.c
@@ -2499,8 +2499,10 @@ static int atmci_probe(struct platform_device *pdev)
 	/* Get MCI capabilities and set operations according to it */
 	atmci_get_cap(host);
 	ret = atmci_configure_dma(host);
-	if (ret == -EPROBE_DEFER)
+	if (ret == -EPROBE_DEFER) {
+		clk_disable_unprepare(host->mck);
 		goto err_dma_probe_defer;
+	}
 	if (ret == 0) {
 		host->prepare_data = &atmci_prepare_data_dma;
 		host->submit_data = &atmci_submit_data_dma;
diff --git a/drivers/mmc/host/bcm2835.c b/drivers/mmc/host/bcm2835.c
index 35d8fdea668b..f923447ed2ce 100644
--- a/drivers/mmc/host/bcm2835.c
+++ b/drivers/mmc/host/bcm2835.c
@@ -502,7 +502,8 @@ void bcm2835_prepare_dma(struct bcm2835_host *host, struct mmc_data *data)
 				       DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 
 	if (!desc) {
-		dma_unmap_sg(dma_chan->device->dev, data->sg, sg_len, dir_data);
+		dma_unmap_sg(dma_chan->device->dev, data->sg, data->sg_len,
+			     dir_data);
 		return;
 	}
 
diff --git a/drivers/mmc/host/dw_mmc-exynos.c b/drivers/mmc/host/dw_mmc-exynos.c
index 6dc057718d2c..89682f10e69f 100644
--- a/drivers/mmc/host/dw_mmc-exynos.c
+++ b/drivers/mmc/host/dw_mmc-exynos.c
@@ -27,6 +27,8 @@ enum dw_mci_exynos_type {
 	DW_MCI_TYPE_EXYNOS5420_SMU,
 	DW_MCI_TYPE_EXYNOS7,
 	DW_MCI_TYPE_EXYNOS7_SMU,
+	DW_MCI_TYPE_EXYNOS7870,
+	DW_MCI_TYPE_EXYNOS7870_SMU,
 	DW_MCI_TYPE_ARTPEC8,
 };
 
@@ -70,6 +72,12 @@ static struct dw_mci_exynos_compatible {
 		.compatible	= "samsung,exynos7-dw-mshc-smu",
 		.ctrl_type	= DW_MCI_TYPE_EXYNOS7_SMU,
 	}, {
+		.compatible	= "samsung,exynos7870-dw-mshc",
+		.ctrl_type	= DW_MCI_TYPE_EXYNOS7870,
+	}, {
+		.compatible	= "samsung,exynos7870-dw-mshc-smu",
+		.ctrl_type	= DW_MCI_TYPE_EXYNOS7870_SMU,
+	}, {
 		.compatible	= "axis,artpec8-dw-mshc",
 		.ctrl_type	= DW_MCI_TYPE_ARTPEC8,
 	},
@@ -85,6 +93,8 @@ static inline u8 dw_mci_exynos_get_ciu_div(struct dw_mci *host)
 		return EXYNOS4210_FIXED_CIU_CLK_DIV;
 	else if (priv->ctrl_type == DW_MCI_TYPE_EXYNOS7 ||
 			priv->ctrl_type == DW_MCI_TYPE_EXYNOS7_SMU ||
+			priv->ctrl_type == DW_MCI_TYPE_EXYNOS7870 ||
+			priv->ctrl_type == DW_MCI_TYPE_EXYNOS7870_SMU ||
 			priv->ctrl_type == DW_MCI_TYPE_ARTPEC8)
 		return SDMMC_CLKSEL_GET_DIV(mci_readl(host, CLKSEL64)) + 1;
 	else
@@ -100,7 +110,8 @@ static void dw_mci_exynos_config_smu(struct dw_mci *host)
 	 * set for non-ecryption mode at this time.
 	 */
 	if (priv->ctrl_type == DW_MCI_TYPE_EXYNOS5420_SMU ||
-		priv->ctrl_type == DW_MCI_TYPE_EXYNOS7_SMU) {
+		priv->ctrl_type == DW_MCI_TYPE_EXYNOS7_SMU ||
+		priv->ctrl_type == DW_MCI_TYPE_EXYNOS7870_SMU) {
 		mci_writel(host, MPSBEGIN0, 0);
 		mci_writel(host, MPSEND0, SDMMC_ENDING_SEC_NR_MAX);
 		mci_writel(host, MPSCTRL0, SDMMC_MPSCTRL_SECURE_WRITE_BIT |
@@ -126,6 +137,12 @@ static int dw_mci_exynos_priv_init(struct dw_mci *host)
 				DQS_CTRL_GET_RD_DELAY(priv->saved_strobe_ctrl);
 	}
 
+	if (priv->ctrl_type == DW_MCI_TYPE_EXYNOS7870 ||
+		priv->ctrl_type == DW_MCI_TYPE_EXYNOS7870_SMU) {
+		/* Quirk needed for certain Exynos SoCs */
+		host->quirks |= DW_MMC_QUIRK_FIFO64_32;
+	}
+
 	if (priv->ctrl_type == DW_MCI_TYPE_ARTPEC8) {
 		/* Quirk needed for the ARTPEC-8 SoC */
 		host->quirks |= DW_MMC_QUIRK_EXTENDED_TMOUT;
@@ -143,6 +160,8 @@ static void dw_mci_exynos_set_clksel_timing(struct dw_mci *host, u32 timing)
 
 	if (priv->ctrl_type == DW_MCI_TYPE_EXYNOS7 ||
 		priv->ctrl_type == DW_MCI_TYPE_EXYNOS7_SMU ||
+		priv->ctrl_type == DW_MCI_TYPE_EXYNOS7870 ||
+		priv->ctrl_type == DW_MCI_TYPE_EXYNOS7870_SMU ||
 		priv->ctrl_type == DW_MCI_TYPE_ARTPEC8)
 		clksel = mci_readl(host, CLKSEL64);
 	else
@@ -152,6 +171,8 @@ static void dw_mci_exynos_set_clksel_timing(struct dw_mci *host, u32 timing)
 
 	if (priv->ctrl_type == DW_MCI_TYPE_EXYNOS7 ||
 		priv->ctrl_type == DW_MCI_TYPE_EXYNOS7_SMU ||
+		priv->ctrl_type == DW_MCI_TYPE_EXYNOS7870 ||
+		priv->ctrl_type == DW_MCI_TYPE_EXYNOS7870_SMU ||
 		priv->ctrl_type == DW_MCI_TYPE_ARTPEC8)
 		mci_writel(host, CLKSEL64, clksel);
 	else
@@ -222,6 +243,8 @@ static int dw_mci_exynos_resume_noirq(struct device *dev)
 
 	if (priv->ctrl_type == DW_MCI_TYPE_EXYNOS7 ||
 		priv->ctrl_type == DW_MCI_TYPE_EXYNOS7_SMU ||
+		priv->ctrl_type == DW_MCI_TYPE_EXYNOS7870 ||
+		priv->ctrl_type == DW_MCI_TYPE_EXYNOS7870_SMU ||
 		priv->ctrl_type == DW_MCI_TYPE_ARTPEC8)
 		clksel = mci_readl(host, CLKSEL64);
 	else
@@ -230,6 +253,8 @@ static int dw_mci_exynos_resume_noirq(struct device *dev)
 	if (clksel & SDMMC_CLKSEL_WAKEUP_INT) {
 		if (priv->ctrl_type == DW_MCI_TYPE_EXYNOS7 ||
 			priv->ctrl_type == DW_MCI_TYPE_EXYNOS7_SMU ||
+			priv->ctrl_type == DW_MCI_TYPE_EXYNOS7870 ||
+			priv->ctrl_type == DW_MCI_TYPE_EXYNOS7870_SMU ||
 			priv->ctrl_type == DW_MCI_TYPE_ARTPEC8)
 			mci_writel(host, CLKSEL64, clksel);
 		else
@@ -409,6 +434,8 @@ static inline u8 dw_mci_exynos_get_clksmpl(struct dw_mci *host)
 
 	if (priv->ctrl_type == DW_MCI_TYPE_EXYNOS7 ||
 		priv->ctrl_type == DW_MCI_TYPE_EXYNOS7_SMU ||
+		priv->ctrl_type == DW_MCI_TYPE_EXYNOS7870 ||
+		priv->ctrl_type == DW_MCI_TYPE_EXYNOS7870_SMU ||
 		priv->ctrl_type == DW_MCI_TYPE_ARTPEC8)
 		return SDMMC_CLKSEL_CCLK_SAMPLE(mci_readl(host, CLKSEL64));
 	else
@@ -422,6 +449,8 @@ static inline void dw_mci_exynos_set_clksmpl(struct dw_mci *host, u8 sample)
 
 	if (priv->ctrl_type == DW_MCI_TYPE_EXYNOS7 ||
 		priv->ctrl_type == DW_MCI_TYPE_EXYNOS7_SMU ||
+		priv->ctrl_type == DW_MCI_TYPE_EXYNOS7870 ||
+		priv->ctrl_type == DW_MCI_TYPE_EXYNOS7870_SMU ||
 		priv->ctrl_type == DW_MCI_TYPE_ARTPEC8)
 		clksel = mci_readl(host, CLKSEL64);
 	else
@@ -429,6 +458,8 @@ static inline void dw_mci_exynos_set_clksmpl(struct dw_mci *host, u8 sample)
 	clksel = SDMMC_CLKSEL_UP_SAMPLE(clksel, sample);
 	if (priv->ctrl_type == DW_MCI_TYPE_EXYNOS7 ||
 		priv->ctrl_type == DW_MCI_TYPE_EXYNOS7_SMU ||
+		priv->ctrl_type == DW_MCI_TYPE_EXYNOS7870 ||
+		priv->ctrl_type == DW_MCI_TYPE_EXYNOS7870_SMU ||
 		priv->ctrl_type == DW_MCI_TYPE_ARTPEC8)
 		mci_writel(host, CLKSEL64, clksel);
 	else
@@ -443,6 +474,8 @@ static inline u8 dw_mci_exynos_move_next_clksmpl(struct dw_mci *host)
 
 	if (priv->ctrl_type == DW_MCI_TYPE_EXYNOS7 ||
 		priv->ctrl_type == DW_MCI_TYPE_EXYNOS7_SMU ||
+		priv->ctrl_type == DW_MCI_TYPE_EXYNOS7870 ||
+		priv->ctrl_type == DW_MCI_TYPE_EXYNOS7870_SMU ||
 		priv->ctrl_type == DW_MCI_TYPE_ARTPEC8)
 		clksel = mci_readl(host, CLKSEL64);
 	else
@@ -453,6 +486,8 @@ static inline u8 dw_mci_exynos_move_next_clksmpl(struct dw_mci *host)
 
 	if (priv->ctrl_type == DW_MCI_TYPE_EXYNOS7 ||
 		priv->ctrl_type == DW_MCI_TYPE_EXYNOS7_SMU ||
+		priv->ctrl_type == DW_MCI_TYPE_EXYNOS7870 ||
+		priv->ctrl_type == DW_MCI_TYPE_EXYNOS7870_SMU ||
 		priv->ctrl_type == DW_MCI_TYPE_ARTPEC8)
 		mci_writel(host, CLKSEL64, clksel);
 	else
@@ -632,6 +667,10 @@ static const struct of_device_id dw_mci_exynos_match[] = {
 			.data = &exynos_drv_data, },
 	{ .compatible = "samsung,exynos7-dw-mshc-smu",
 			.data = &exynos_drv_data, },
+	{ .compatible = "samsung,exynos7870-dw-mshc",
+			.data = &exynos_drv_data, },
+	{ .compatible = "samsung,exynos7870-dw-mshc-smu",
+			.data = &exynos_drv_data, },
 	{ .compatible = "axis,artpec8-dw-mshc",
 			.data = &artpec_drv_data, },
 	{},
diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c
index e9f6e4e62290..55158540c28c 100644
--- a/drivers/mmc/host/dw_mmc.c
+++ b/drivers/mmc/host/dw_mmc.c
@@ -2579,6 +2579,91 @@ static void dw_mci_pull_data64(struct dw_mci *host, void *buf, int cnt)
 	}
 }
 
+static void dw_mci_push_data64_32(struct dw_mci *host, void *buf, int cnt)
+{
+	struct mmc_data *data = host->data;
+	int init_cnt = cnt;
+
+	/* try and push anything in the part_buf */
+	if (unlikely(host->part_buf_count)) {
+		int len = dw_mci_push_part_bytes(host, buf, cnt);
+
+		buf += len;
+		cnt -= len;
+
+		if (host->part_buf_count == 8) {
+			mci_fifo_l_writeq(host->fifo_reg, host->part_buf);
+			host->part_buf_count = 0;
+		}
+	}
+#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+	if (unlikely((unsigned long)buf & 0x7)) {
+		while (cnt >= 8) {
+			u64 aligned_buf[16];
+			int len = min(cnt & -8, (int)sizeof(aligned_buf));
+			int items = len >> 3;
+			int i;
+			/* memcpy from input buffer into aligned buffer */
+			memcpy(aligned_buf, buf, len);
+			buf += len;
+			cnt -= len;
+			/* push data from aligned buffer into fifo */
+			for (i = 0; i < items; ++i)
+				mci_fifo_l_writeq(host->fifo_reg, aligned_buf[i]);
+		}
+	} else
+#endif
+	{
+		u64 *pdata = buf;
+
+		for (; cnt >= 8; cnt -= 8)
+			mci_fifo_l_writeq(host->fifo_reg, *pdata++);
+		buf = pdata;
+	}
+	/* put anything remaining in the part_buf */
+	if (cnt) {
+		dw_mci_set_part_bytes(host, buf, cnt);
+		/* Push data if we have reached the expected data length */
+		if ((data->bytes_xfered + init_cnt) ==
+		    (data->blksz * data->blocks))
+			mci_fifo_l_writeq(host->fifo_reg, host->part_buf);
+	}
+}
+
+static void dw_mci_pull_data64_32(struct dw_mci *host, void *buf, int cnt)
+{
+#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+	if (unlikely((unsigned long)buf & 0x7)) {
+		while (cnt >= 8) {
+			/* pull data from fifo into aligned buffer */
+			u64 aligned_buf[16];
+			int len = min(cnt & -8, (int)sizeof(aligned_buf));
+			int items = len >> 3;
+			int i;
+
+			for (i = 0; i < items; ++i)
+				aligned_buf[i] = mci_fifo_l_readq(host->fifo_reg);
+
+			/* memcpy from aligned buffer into output buffer */
+			memcpy(buf, aligned_buf, len);
+			buf += len;
+			cnt -= len;
+		}
+	} else
+#endif
+	{
+		u64 *pdata = buf;
+
+		for (; cnt >= 8; cnt -= 8)
+			*pdata++ = mci_fifo_l_readq(host->fifo_reg);
+		buf = pdata;
+	}
+	if (cnt) {
+		host->part_buf = mci_fifo_l_readq(host->fifo_reg);
+		dw_mci_pull_final_bytes(host, buf, cnt);
+	}
+}
+
 static void dw_mci_pull_data(struct dw_mci *host, void *buf, int cnt)
 {
 	int len;
@@ -3379,8 +3464,13 @@ int dw_mci_probe(struct dw_mci *host)
 		width = 16;
 		host->data_shift = 1;
 	} else if (i == 2) {
-		host->push_data = dw_mci_push_data64;
-		host->pull_data = dw_mci_pull_data64;
+		if ((host->quirks & DW_MMC_QUIRK_FIFO64_32)) {
+			host->push_data = dw_mci_push_data64_32;
+			host->pull_data = dw_mci_pull_data64_32;
+		} else {
+			host->push_data = dw_mci_push_data64;
+			host->pull_data = dw_mci_pull_data64;
+		}
 		width = 64;
 		host->data_shift = 3;
 	} else {
diff --git a/drivers/mmc/host/dw_mmc.h b/drivers/mmc/host/dw_mmc.h
index 6447b916990d..5463392dc811 100644
--- a/drivers/mmc/host/dw_mmc.h
+++ b/drivers/mmc/host/dw_mmc.h
@@ -281,6 +281,8 @@ struct dw_mci_board {
 
 /* Support for longer data read timeout */
 #define DW_MMC_QUIRK_EXTENDED_TMOUT            BIT(0)
+/* Force 32-bit access to the FIFO */
+#define DW_MMC_QUIRK_FIFO64_32                 BIT(1)
 
 #define DW_MMC_240A		0x240a
 #define DW_MMC_280A		0x280a
@@ -472,6 +474,31 @@ struct dw_mci_board {
 #define mci_fifo_writel(__value, __reg)	__raw_writel(__reg, __value)
 #define mci_fifo_writeq(__value, __reg)	__raw_writeq(__reg, __value)
 
+/*
+ * Some dw_mmc devices have 64-bit FIFOs, but expect them to be
+ * accessed using two 32-bit accesses. If such controller is used
+ * with a 64-bit kernel, this has to be done explicitly.
+ */
+static inline u64 mci_fifo_l_readq(void __iomem *addr)
+{
+	u64 ans;
+	u32 proxy[2];
+
+	proxy[0] = mci_fifo_readl(addr);
+	proxy[1] = mci_fifo_readl(addr + 4);
+	memcpy(&ans, proxy, 8);
+	return ans;
+}
+
+static inline void mci_fifo_l_writeq(void __iomem *addr, u64 value)
+{
+	u32 proxy[2];
+
+	memcpy(proxy, &value, 8);
+	mci_fifo_writel(addr, proxy[0]);
+	mci_fifo_writel(addr + 4, proxy[1]);
+}
+
 /* Register access macros */
 #define mci_readl(dev, reg)			\
 	readl_relaxed((dev)->regs + SDMMC_##reg)
diff --git a/drivers/mmc/host/mtk-sd.c b/drivers/mmc/host/mtk-sd.c
index 6e62415de2e5..be9954f5bc0a 100644
--- a/drivers/mmc/host/mtk-sd.c
+++ b/drivers/mmc/host/mtk-sd.c
@@ -263,6 +263,7 @@
 #define MSDC_PAD_TUNE_CMD2_SEL	  BIT(21)   /* RW */
 
 #define PAD_DS_TUNE_DLY_SEL       BIT(0)	  /* RW */
+#define PAD_DS_TUNE_DLY2_SEL      BIT(1)	  /* RW */
 #define PAD_DS_TUNE_DLY1	  GENMASK(6, 2)   /* RW */
 #define PAD_DS_TUNE_DLY2	  GENMASK(11, 7)  /* RW */
 #define PAD_DS_TUNE_DLY3	  GENMASK(16, 12) /* RW */
@@ -308,6 +309,7 @@
 
 /* EMMC50_PAD_DS_TUNE mask */
 #define PAD_DS_DLY_SEL		BIT(16)	/* RW */
+#define PAD_DS_DLY2_SEL		BIT(15)	/* RW */
 #define PAD_DS_DLY1		GENMASK(14, 10)	/* RW */
 #define PAD_DS_DLY3		GENMASK(4, 0)	/* RW */
 
@@ -774,12 +776,18 @@ static inline void msdc_dma_setup(struct msdc_host *host, struct msdc_dma *dma,
 static void msdc_prepare_data(struct msdc_host *host, struct mmc_data *data)
 {
 	if (!(data->host_cookie & MSDC_PREPARE_FLAG)) {
-		data->host_cookie |= MSDC_PREPARE_FLAG;
 		data->sg_count = dma_map_sg(host->dev, data->sg, data->sg_len,
 					    mmc_get_dma_dir(data));
+		if (data->sg_count)
+			data->host_cookie |= MSDC_PREPARE_FLAG;
 	}
 }
 
+static bool msdc_data_prepared(struct mmc_data *data)
+{
+	return data->host_cookie & MSDC_PREPARE_FLAG;
+}
+
 static void msdc_unprepare_data(struct msdc_host *host, struct mmc_data *data)
 {
 	if (data->host_cookie & MSDC_ASYNC_FLAG)
@@ -1343,8 +1351,19 @@ static void msdc_ops_request(struct mmc_host *mmc, struct mmc_request *mrq)
 	WARN_ON(host->mrq);
 	host->mrq = mrq;
 
-	if (mrq->data)
+	if (mrq->data) {
 		msdc_prepare_data(host, mrq->data);
+		if (!msdc_data_prepared(mrq->data)) {
+			host->mrq = NULL;
+			/*
+			 * Failed to prepare DMA area, fail fast before
+			 * starting any commands.
+			 */
+			mrq->cmd->error = -ENOSPC;
+			mmc_request_done(mmc_from_priv(host), mrq);
+			return;
+		}
+	}
 
 	/* if SBC is required, we have HW option and SW option.
 	 * if HW option is enabled, and SBC does not have "special" flags,
@@ -2361,13 +2380,23 @@ tune_done:
 static int msdc_prepare_hs400_tuning(struct mmc_host *mmc, struct mmc_ios *ios)
 {
 	struct msdc_host *host = mmc_priv(mmc);
+
 	host->hs400_mode = true;
 
-	if (host->top_base)
-		writel(host->hs400_ds_delay,
-		       host->top_base + EMMC50_PAD_DS_TUNE);
-	else
-		writel(host->hs400_ds_delay, host->base + PAD_DS_TUNE);
+	if (host->top_base) {
+		if (host->hs400_ds_dly3)
+			sdr_set_field(host->top_base + EMMC50_PAD_DS_TUNE,
+				      PAD_DS_DLY3, host->hs400_ds_dly3);
+		if (host->hs400_ds_delay)
+			writel(host->hs400_ds_delay,
+			       host->top_base + EMMC50_PAD_DS_TUNE);
+	} else {
+		if (host->hs400_ds_dly3)
+			sdr_set_field(host->base + PAD_DS_TUNE,
+				      PAD_DS_TUNE_DLY3, host->hs400_ds_dly3);
+		if (host->hs400_ds_delay)
+			writel(host->hs400_ds_delay, host->base + PAD_DS_TUNE);
+	}
 	/* hs400 mode must set it to 0 */
 	sdr_clr_bits(host->base + MSDC_PATCH_BIT2, MSDC_PATCH_BIT2_CFGCRCSTS);
 	/* to improve read performance, set outstanding to 2 */
@@ -2387,14 +2416,11 @@ static int msdc_execute_hs400_tuning(struct mmc_host *mmc, struct mmc_card *card
 	if (host->top_base) {
 		sdr_set_bits(host->top_base + EMMC50_PAD_DS_TUNE,
 			     PAD_DS_DLY_SEL);
-		if (host->hs400_ds_dly3)
-			sdr_set_field(host->top_base + EMMC50_PAD_DS_TUNE,
-				      PAD_DS_DLY3, host->hs400_ds_dly3);
+		sdr_clr_bits(host->top_base + EMMC50_PAD_DS_TUNE,
+			     PAD_DS_DLY2_SEL);
 	} else {
 		sdr_set_bits(host->base + PAD_DS_TUNE, PAD_DS_TUNE_DLY_SEL);
-		if (host->hs400_ds_dly3)
-			sdr_set_field(host->base + PAD_DS_TUNE,
-				      PAD_DS_TUNE_DLY3, host->hs400_ds_dly3);
+		sdr_clr_bits(host->base + PAD_DS_TUNE, PAD_DS_TUNE_DLY2_SEL);
 	}
 
 	host->hs400_tuning = true;
diff --git a/drivers/mmc/host/omap.c b/drivers/mmc/host/omap.c
index 335350a4e99a..ee0940d96feb 100644
--- a/drivers/mmc/host/omap.c
+++ b/drivers/mmc/host/omap.c
@@ -1272,19 +1272,25 @@ static int mmc_omap_new_slot(struct mmc_omap_host *host, int id)
 	/* Check for some optional GPIO controls */
 	slot->vsd = devm_gpiod_get_index_optional(host->dev, "vsd",
 						  id, GPIOD_OUT_LOW);
-	if (IS_ERR(slot->vsd))
-		return dev_err_probe(host->dev, PTR_ERR(slot->vsd),
+	if (IS_ERR(slot->vsd)) {
+		r = dev_err_probe(host->dev, PTR_ERR(slot->vsd),
 				     "error looking up VSD GPIO\n");
+		goto err_free_host;
+	}
 	slot->vio = devm_gpiod_get_index_optional(host->dev, "vio",
 						  id, GPIOD_OUT_LOW);
-	if (IS_ERR(slot->vio))
-		return dev_err_probe(host->dev, PTR_ERR(slot->vio),
+	if (IS_ERR(slot->vio)) {
+		r = dev_err_probe(host->dev, PTR_ERR(slot->vio),
 				     "error looking up VIO GPIO\n");
+		goto err_free_host;
+	}
 	slot->cover = devm_gpiod_get_index_optional(host->dev, "cover",
 						    id, GPIOD_IN);
-	if (IS_ERR(slot->cover))
-		return dev_err_probe(host->dev, PTR_ERR(slot->cover),
+	if (IS_ERR(slot->cover)) {
+		r = dev_err_probe(host->dev, PTR_ERR(slot->cover),
 				     "error looking up cover switch GPIO\n");
+		goto err_free_host;
+	}
 
 	host->slots[id] = slot;
 
@@ -1344,6 +1350,7 @@ err_remove_slot_name:
 		device_remove_file(&mmc->class_dev, &dev_attr_slot_name);
 err_remove_host:
 	mmc_remove_host(mmc);
+err_free_host:
 	mmc_free_host(mmc);
 	return r;
 }
diff --git a/drivers/mmc/host/renesas_sdhi_core.c b/drivers/mmc/host/renesas_sdhi_core.c
index f73b84bae0c4..6ebb3d1eeb4d 100644
--- a/drivers/mmc/host/renesas_sdhi_core.c
+++ b/drivers/mmc/host/renesas_sdhi_core.c
@@ -1112,26 +1112,26 @@ int renesas_sdhi_probe(struct platform_device *pdev,
 	num_irqs = platform_irq_count(pdev);
 	if (num_irqs < 0) {
 		ret = num_irqs;
-		goto eirq;
+		goto edisclk;
 	}
 
 	/* There must be at least one IRQ source */
 	if (!num_irqs) {
 		ret = -ENXIO;
-		goto eirq;
+		goto edisclk;
 	}
 
 	for (i = 0; i < num_irqs; i++) {
 		irq = platform_get_irq(pdev, i);
 		if (irq < 0) {
 			ret = irq;
-			goto eirq;
+			goto edisclk;
 		}
 
 		ret = devm_request_irq(&pdev->dev, irq, tmio_mmc_irq, 0,
 				       dev_name(&pdev->dev), host);
 		if (ret)
-			goto eirq;
+			goto edisclk;
 	}
 
 	ret = tmio_mmc_host_probe(host);
@@ -1143,8 +1143,6 @@ int renesas_sdhi_probe(struct platform_device *pdev,
 
 	return ret;
 
-eirq:
-	tmio_mmc_host_remove(host);
 edisclk:
 	renesas_sdhi_clk_disable(host);
 efree:
diff --git a/drivers/mmc/host/rtsx_usb_sdmmc.c b/drivers/mmc/host/rtsx_usb_sdmmc.c
index 4e86f0a705b6..2bf51fe11a09 100644
--- a/drivers/mmc/host/rtsx_usb_sdmmc.c
+++ b/drivers/mmc/host/rtsx_usb_sdmmc.c
@@ -1032,9 +1032,7 @@ static int sd_set_power_mode(struct rtsx_usb_sdmmc *host,
 		err = sd_power_on(host);
 	}
 
-	if (!err)
-		host->power_mode = power_mode;
-
+	host->power_mode = power_mode;
 	return err;
 }
 
diff --git a/drivers/mmc/host/sdhci-brcmstb.c b/drivers/mmc/host/sdhci-brcmstb.c
index 031a4b514d16..9d9ddc2f6f70 100644
--- a/drivers/mmc/host/sdhci-brcmstb.c
+++ b/drivers/mmc/host/sdhci-brcmstb.c
@@ -503,8 +503,15 @@ static int sdhci_brcmstb_suspend(struct device *dev)
 	struct sdhci_host *host = dev_get_drvdata(dev);
 	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
 	struct sdhci_brcmstb_priv *priv = sdhci_pltfm_priv(pltfm_host);
+	int ret;
 
 	clk_disable_unprepare(priv->base_clk);
+	if (host->mmc->caps2 & MMC_CAP2_CQE) {
+		ret = cqhci_suspend(host->mmc);
+		if (ret)
+			return ret;
+	}
+
 	return sdhci_pltfm_suspend(dev);
 }
 
@@ -529,6 +536,9 @@ static int sdhci_brcmstb_resume(struct device *dev)
 			ret = clk_set_rate(priv->base_clk, priv->base_freq_hz);
 	}
 
+	if (host->mmc->caps2 & MMC_CAP2_CQE)
+		ret = cqhci_resume(host->mmc);
+
 	return ret;
 }
 #endif
diff --git a/drivers/mmc/host/sdhci-esdhc-imx.c b/drivers/mmc/host/sdhci-esdhc-imx.c
index ef3a44f2dff1..d84aa20f0358 100644
--- a/drivers/mmc/host/sdhci-esdhc-imx.c
+++ b/drivers/mmc/host/sdhci-esdhc-imx.c
@@ -303,6 +303,7 @@ static struct esdhc_soc_data usdhc_s32g2_data = {
 			| ESDHC_FLAG_HAVE_CAP1 | ESDHC_FLAG_HS200
 			| ESDHC_FLAG_HS400 | ESDHC_FLAG_HS400_ES
 			| ESDHC_FLAG_SKIP_ERR004536 | ESDHC_FLAG_SKIP_CD_WAKE,
+	.quirks = SDHCI_QUIRK_NO_LED,
 };
 
 static struct esdhc_soc_data usdhc_imx7ulp_data = {
diff --git a/drivers/mmc/host/sdhci-msm.c b/drivers/mmc/host/sdhci-msm.c
index 8716004fcf6c..c2144a3efb30 100644
--- a/drivers/mmc/host/sdhci-msm.c
+++ b/drivers/mmc/host/sdhci-msm.c
@@ -134,9 +134,18 @@
 /* Timeout value to avoid infinite waiting for pwr_irq */
 #define MSM_PWR_IRQ_TIMEOUT_MS 5000
 
+/* Max load for eMMC Vdd supply */
+#define MMC_VMMC_MAX_LOAD_UA	570000
+
 /* Max load for eMMC Vdd-io supply */
 #define MMC_VQMMC_MAX_LOAD_UA	325000
 
+/* Max load for SD Vdd supply */
+#define SD_VMMC_MAX_LOAD_UA	800000
+
+/* Max load for SD Vdd-io supply */
+#define SD_VQMMC_MAX_LOAD_UA	22000
+
 #define msm_host_readl(msm_host, host, offset) \
 	msm_host->var_ops->msm_readl_relaxed(host, offset)
 
@@ -1403,11 +1412,48 @@ static int sdhci_msm_set_pincfg(struct sdhci_msm_host *msm_host, bool level)
 	return ret;
 }
 
-static int sdhci_msm_set_vmmc(struct mmc_host *mmc)
+static void msm_config_vmmc_regulator(struct mmc_host *mmc, bool hpm)
+{
+	int load;
+
+	if (!hpm)
+		load = 0;
+	else if (!mmc->card)
+		load = max(MMC_VMMC_MAX_LOAD_UA, SD_VMMC_MAX_LOAD_UA);
+	else if (mmc_card_mmc(mmc->card))
+		load = MMC_VMMC_MAX_LOAD_UA;
+	else if (mmc_card_sd(mmc->card))
+		load = SD_VMMC_MAX_LOAD_UA;
+	else
+		return;
+
+	regulator_set_load(mmc->supply.vmmc, load);
+}
+
+static void msm_config_vqmmc_regulator(struct mmc_host *mmc, bool hpm)
+{
+	int load;
+
+	if (!hpm)
+		load = 0;
+	else if (!mmc->card)
+		load = max(MMC_VQMMC_MAX_LOAD_UA, SD_VQMMC_MAX_LOAD_UA);
+	else if (mmc_card_sd(mmc->card))
+		load = SD_VQMMC_MAX_LOAD_UA;
+	else
+		return;
+
+	regulator_set_load(mmc->supply.vqmmc, load);
+}
+
+static int sdhci_msm_set_vmmc(struct sdhci_msm_host *msm_host,
+			      struct mmc_host *mmc, bool hpm)
 {
 	if (IS_ERR(mmc->supply.vmmc))
 		return 0;
 
+	msm_config_vmmc_regulator(mmc, hpm);
+
 	return mmc_regulator_set_ocr(mmc, mmc->supply.vmmc, mmc->ios.vdd);
 }
 
@@ -1420,6 +1466,8 @@ static int msm_toggle_vqmmc(struct sdhci_msm_host *msm_host,
 	if (msm_host->vqmmc_enabled == level)
 		return 0;
 
+	msm_config_vqmmc_regulator(mmc, level);
+
 	if (level) {
 		/* Set the IO voltage regulator to default voltage level */
 		if (msm_host->caps_0 & CORE_3_0V_SUPPORT)
@@ -1516,6 +1564,7 @@ static void sdhci_msm_check_power_status(struct sdhci_host *host, u32 req_type)
 {
 	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
 	struct sdhci_msm_host *msm_host = sdhci_pltfm_priv(pltfm_host);
+	struct mmc_host *mmc = host->mmc;
 	bool done = false;
 	u32 val = SWITCHABLE_SIGNALING_VOLTAGE;
 	const struct sdhci_msm_offset *msm_offset =
@@ -1573,6 +1622,12 @@ static void sdhci_msm_check_power_status(struct sdhci_host *host, u32 req_type)
 				 "%s: pwr_irq for req: (%d) timed out\n",
 				 mmc_hostname(host->mmc), req_type);
 	}
+
+	if ((req_type & REQ_BUS_ON) && mmc->card && !mmc->ops->get_cd(mmc)) {
+		sdhci_writeb(host, 0, SDHCI_POWER_CONTROL);
+		host->pwr = 0;
+	}
+
 	pr_debug("%s: %s: request %d done\n", mmc_hostname(host->mmc),
 			__func__, req_type);
 }
@@ -1631,6 +1686,13 @@ static void sdhci_msm_handle_pwr_irq(struct sdhci_host *host, int irq)
 		udelay(10);
 	}
 
+	if ((irq_status & CORE_PWRCTL_BUS_ON) && mmc->card &&
+	    !mmc->ops->get_cd(mmc)) {
+		msm_host_writel(msm_host, CORE_PWRCTL_BUS_FAIL, host,
+				msm_offset->core_pwrctl_ctl);
+		return;
+	}
+
 	/* Handle BUS ON/OFF*/
 	if (irq_status & CORE_PWRCTL_BUS_ON) {
 		pwr_state = REQ_BUS_ON;
@@ -1642,7 +1704,8 @@ static void sdhci_msm_handle_pwr_irq(struct sdhci_host *host, int irq)
 	}
 
 	if (pwr_state) {
-		ret = sdhci_msm_set_vmmc(mmc);
+		ret = sdhci_msm_set_vmmc(msm_host, mmc,
+					 pwr_state & REQ_BUS_ON);
 		if (!ret)
 			ret = sdhci_msm_set_vqmmc(msm_host, mmc,
 					pwr_state & REQ_BUS_ON);
@@ -1817,7 +1880,7 @@ static int sdhci_msm_ice_init(struct sdhci_msm_host *msm_host,
 	if (!(cqhci_readl(cq_host, CQHCI_CAP) & CQHCI_CAP_CS))
 		return 0;
 
-	ice = of_qcom_ice_get(dev);
+	ice = devm_of_qcom_ice_get(dev);
 	if (ice == ERR_PTR(-EOPNOTSUPP)) {
 		dev_warn(dev, "Disabling inline encryption support\n");
 		ice = NULL;
diff --git a/drivers/mmc/host/sdhci-of-dwcmshc.c b/drivers/mmc/host/sdhci-of-dwcmshc.c
index 8fd80dac11bf..bf29aad082a1 100644
--- a/drivers/mmc/host/sdhci-of-dwcmshc.c
+++ b/drivers/mmc/host/sdhci-of-dwcmshc.c
@@ -17,6 +17,7 @@
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/platform_device.h>
+#include <linux/pm_domain.h>
 #include <linux/pm_runtime.h>
 #include <linux/reset.h>
 #include <linux/sizes.h>
@@ -787,6 +788,29 @@ static void dwcmshc_rk35xx_postinit(struct sdhci_host *host, struct dwcmshc_priv
 	}
 }
 
+static void dwcmshc_rk3576_postinit(struct sdhci_host *host, struct dwcmshc_priv *dwc_priv)
+{
+	struct device *dev = mmc_dev(host->mmc);
+	int ret;
+
+	/*
+	 * This works around the design of the RK3576's power domains, which
+	 * makes the PD_NVM power domain, which the sdhci controller on the
+	 * RK3576 is in, never come back the same way once it's run-time
+	 * suspended once. This can happen during early kernel boot if no driver
+	 * is using either PD_NVM or its child power domain PD_SDGMAC for a
+	 * short moment, leading to it being turned off to save power. By
+	 * keeping it on, sdhci suspending won't lead to PD_NVM becoming a
+	 * candidate for getting turned off.
+	 */
+	ret = dev_pm_genpd_rpm_always_on(dev, true);
+	if (ret && ret != -EOPNOTSUPP)
+		dev_warn(dev, "failed to set PD rpm always on, SoC may hang later: %pe\n",
+			 ERR_PTR(ret));
+
+	dwcmshc_rk35xx_postinit(host, dwc_priv);
+}
+
 static int th1520_execute_tuning(struct sdhci_host *host, u32 opcode)
 {
 	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
@@ -1218,6 +1242,18 @@ static const struct dwcmshc_pltfm_data sdhci_dwcmshc_rk35xx_pdata = {
 	.postinit = dwcmshc_rk35xx_postinit,
 };
 
+static const struct dwcmshc_pltfm_data sdhci_dwcmshc_rk3576_pdata = {
+	.pdata = {
+		.ops = &sdhci_dwcmshc_rk35xx_ops,
+		.quirks = SDHCI_QUIRK_CAP_CLOCK_BASE_BROKEN |
+			  SDHCI_QUIRK_BROKEN_TIMEOUT_VAL,
+		.quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN |
+			   SDHCI_QUIRK2_CLOCK_DIV_ZERO_BROKEN,
+	},
+	.init = dwcmshc_rk35xx_init,
+	.postinit = dwcmshc_rk3576_postinit,
+};
+
 static const struct dwcmshc_pltfm_data sdhci_dwcmshc_th1520_pdata = {
 	.pdata = {
 		.ops = &sdhci_dwcmshc_th1520_ops,
@@ -1317,6 +1353,10 @@ static const struct of_device_id sdhci_dwcmshc_dt_ids[] = {
 		.data = &sdhci_dwcmshc_rk35xx_pdata,
 	},
 	{
+		.compatible = "rockchip,rk3576-dwcmshc",
+		.data = &sdhci_dwcmshc_rk3576_pdata,
+	},
+	{
 		.compatible = "rockchip,rk3568-dwcmshc",
 		.data = &sdhci_dwcmshc_rk35xx_pdata,
 	},
diff --git a/drivers/mmc/host/sdhci-omap.c b/drivers/mmc/host/sdhci-omap.c
index 5841a9afeb9f..ea4a801c9ace 100644
--- a/drivers/mmc/host/sdhci-omap.c
+++ b/drivers/mmc/host/sdhci-omap.c
@@ -1339,8 +1339,8 @@ static int sdhci_omap_probe(struct platform_device *pdev)
 	/* R1B responses is required to properly manage HW busy detection. */
 	mmc->caps |= MMC_CAP_NEED_RSP_BUSY;
 
-	/* Allow card power off and runtime PM for eMMC/SD card devices */
-	mmc->caps |= MMC_CAP_POWER_OFF_CARD | MMC_CAP_AGGRESSIVE_PM;
+	/*  Enable SDIO card power off. */
+	mmc->caps |= MMC_CAP_POWER_OFF_CARD;
 
 	ret = sdhci_setup_host(host);
 	if (ret)
diff --git a/drivers/mmc/host/sdhci-pci-core.c b/drivers/mmc/host/sdhci-pci-core.c
index 2e2e15e2d8fb..76ea0e892d4e 100644
--- a/drivers/mmc/host/sdhci-pci-core.c
+++ b/drivers/mmc/host/sdhci-pci-core.c
@@ -609,8 +609,12 @@ static void sdhci_intel_set_power(struct sdhci_host *host, unsigned char mode,
 
 	sdhci_set_power(host, mode, vdd);
 
-	if (mode == MMC_POWER_OFF)
+	if (mode == MMC_POWER_OFF) {
+		if (slot->chip->pdev->device == PCI_DEVICE_ID_INTEL_APL_SD ||
+		    slot->chip->pdev->device == PCI_DEVICE_ID_INTEL_BYT_SD)
+			usleep_range(15000, 17500);
 		return;
+	}
 
 	/*
 	 * Bus power might not enable after D3 -> D0 transition due to the
@@ -908,7 +912,8 @@ static bool glk_broken_cqhci(struct sdhci_pci_slot *slot)
 {
 	return slot->chip->pdev->device == PCI_DEVICE_ID_INTEL_GLK_EMMC &&
 	       (dmi_match(DMI_BIOS_VENDOR, "LENOVO") ||
-		dmi_match(DMI_SYS_VENDOR, "IRBIS"));
+		dmi_match(DMI_SYS_VENDOR, "IRBIS") ||
+		dmi_match(DMI_SYS_VENDOR, "Positivo Tecnologia SA"));
 }
 
 static bool jsl_broken_hs400es(struct sdhci_pci_slot *slot)
diff --git a/drivers/mmc/host/sdhci-pxav3.c b/drivers/mmc/host/sdhci-pxav3.c
index 3af43ac05825..376fd927ae73 100644
--- a/drivers/mmc/host/sdhci-pxav3.c
+++ b/drivers/mmc/host/sdhci-pxav3.c
@@ -399,6 +399,7 @@ static int sdhci_pxav3_probe(struct platform_device *pdev)
 	if (!IS_ERR(pxa->clk_core))
 		clk_prepare_enable(pxa->clk_core);
 
+	host->mmc->caps |= MMC_CAP_NEED_RSP_BUSY;
 	/* enable 1/8V DDR capable */
 	host->mmc->caps |= MMC_CAP_1_8V_DDR;
 
diff --git a/drivers/mmc/host/sdhci.h b/drivers/mmc/host/sdhci.h
index f531b617f28d..da1b0a46b1d9 100644
--- a/drivers/mmc/host/sdhci.h
+++ b/drivers/mmc/host/sdhci.h
@@ -825,4 +825,20 @@ void sdhci_switch_external_dma(struct sdhci_host *host, bool en);
 void sdhci_set_data_timeout_irq(struct sdhci_host *host, bool enable);
 void __sdhci_set_timeout(struct sdhci_host *host, struct mmc_command *cmd);
 
+#if defined(CONFIG_DYNAMIC_DEBUG) || \
+	(defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE))
+#define SDHCI_DBG_ANYWAY 0
+#elif defined(DEBUG)
+#define SDHCI_DBG_ANYWAY 1
+#else
+#define SDHCI_DBG_ANYWAY 0
+#endif
+
+#define sdhci_dbg_dumpregs(host, fmt)					\
+do {									\
+	DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, fmt);			\
+	if (DYNAMIC_DEBUG_BRANCH(descriptor) ||	SDHCI_DBG_ANYWAY)	\
+		sdhci_dumpregs(host);					\
+} while (0)
+
 #endif /* __SDHCI_HW_H */
diff --git a/drivers/mmc/host/sdhci_am654.c b/drivers/mmc/host/sdhci_am654.c
index 0aa3c40ea6ed..8e0eb0acf442 100644
--- a/drivers/mmc/host/sdhci_am654.c
+++ b/drivers/mmc/host/sdhci_am654.c
@@ -588,7 +588,8 @@ static const struct sdhci_ops sdhci_am654_ops = {
 static const struct sdhci_pltfm_data sdhci_am654_pdata = {
 	.ops = &sdhci_am654_ops,
 	.quirks = SDHCI_QUIRK_MULTIBLOCK_READ_ACMD12,
-	.quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN,
+	.quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN |
+		   SDHCI_QUIRK2_DISABLE_HW_TIMEOUT,
 };
 
 static const struct sdhci_am654_driver_data sdhci_am654_sr1_drvdata = {
@@ -618,7 +619,8 @@ static const struct sdhci_ops sdhci_j721e_8bit_ops = {
 static const struct sdhci_pltfm_data sdhci_j721e_8bit_pdata = {
 	.ops = &sdhci_j721e_8bit_ops,
 	.quirks = SDHCI_QUIRK_MULTIBLOCK_READ_ACMD12,
-	.quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN,
+	.quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN |
+		   SDHCI_QUIRK2_DISABLE_HW_TIMEOUT,
 };
 
 static const struct sdhci_am654_driver_data sdhci_j721e_8bit_drvdata = {
@@ -642,7 +644,8 @@ static const struct sdhci_ops sdhci_j721e_4bit_ops = {
 static const struct sdhci_pltfm_data sdhci_j721e_4bit_pdata = {
 	.ops = &sdhci_j721e_4bit_ops,
 	.quirks = SDHCI_QUIRK_MULTIBLOCK_READ_ACMD12,
-	.quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN,
+	.quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN |
+		   SDHCI_QUIRK2_DISABLE_HW_TIMEOUT,
 };
 
 static const struct sdhci_am654_driver_data sdhci_j721e_4bit_drvdata = {
diff --git a/drivers/mtd/ftl.c b/drivers/mtd/ftl.c
index 8c22064ead38..f2bd1984609c 100644
--- a/drivers/mtd/ftl.c
+++ b/drivers/mtd/ftl.c
@@ -344,7 +344,7 @@ static int erase_xfer(partition_t *part,
             return -ENOMEM;
 
     erase->addr = xfer->Offset;
-    erase->len = 1 << part->header.EraseUnitSize;
+    erase->len = 1ULL << part->header.EraseUnitSize;
 
     ret = mtd_erase(part->mbd.mtd, erase);
     if (!ret) {
diff --git a/drivers/mtd/hyperbus/hbmc-am654.c b/drivers/mtd/hyperbus/hbmc-am654.c
index dbe3eb361cca..4b6cbee23fe8 100644
--- a/drivers/mtd/hyperbus/hbmc-am654.c
+++ b/drivers/mtd/hyperbus/hbmc-am654.c
@@ -174,26 +174,30 @@ static int am654_hbmc_probe(struct platform_device *pdev)
 	priv->hbdev.np = of_get_next_child(np, NULL);
 	ret = of_address_to_resource(priv->hbdev.np, 0, &res);
 	if (ret)
-		return ret;
+		goto put_node;
 
 	if (of_property_read_bool(dev->of_node, "mux-controls")) {
 		struct mux_control *control = devm_mux_control_get(dev, NULL);
 
-		if (IS_ERR(control))
-			return PTR_ERR(control);
+		if (IS_ERR(control)) {
+			ret = PTR_ERR(control);
+			goto put_node;
+		}
 
 		ret = mux_control_select(control, 1);
 		if (ret) {
 			dev_err(dev, "Failed to select HBMC mux\n");
-			return ret;
+			goto put_node;
 		}
 		priv->mux_ctrl = control;
 	}
 
 	priv->hbdev.map.size = resource_size(&res);
 	priv->hbdev.map.virt = devm_ioremap_resource(dev, &res);
-	if (IS_ERR(priv->hbdev.map.virt))
-		return PTR_ERR(priv->hbdev.map.virt);
+	if (IS_ERR(priv->hbdev.map.virt)) {
+		ret = PTR_ERR(priv->hbdev.map.virt);
+		goto disable_mux;
+	}
 
 	priv->ctlr.dev = dev;
 	priv->ctlr.ops = &am654_hbmc_ops;
@@ -226,6 +230,8 @@ release_dma:
 disable_mux:
 	if (priv->mux_ctrl)
 		mux_control_deselect(priv->mux_ctrl);
+put_node:
+	of_node_put(priv->hbdev.np);
 	return ret;
 }
 
@@ -241,6 +247,7 @@ static void am654_hbmc_remove(struct platform_device *pdev)
 
 	if (dev_priv->rx_chan)
 		dma_release_channel(dev_priv->rx_chan);
+	of_node_put(priv->hbdev.np);
 }
 
 static const struct of_device_id am654_hbmc_dt_ids[] = {
diff --git a/drivers/mtd/inftlcore.c b/drivers/mtd/inftlcore.c
index 9739387cff8c..58c6e1743f5c 100644
--- a/drivers/mtd/inftlcore.c
+++ b/drivers/mtd/inftlcore.c
@@ -482,10 +482,11 @@ static inline u16 INFTL_findwriteunit(struct INFTLrecord *inftl, unsigned block)
 		silly = MAX_LOOPS;
 
 		while (thisEUN <= inftl->lastEUN) {
-			inftl_read_oob(mtd, (thisEUN * inftl->EraseSize) +
-				       blockofs, 8, &retlen, (char *)&bci);
-
-			status = bci.Status | bci.Status1;
+			if (inftl_read_oob(mtd, (thisEUN * inftl->EraseSize) +
+				       blockofs, 8, &retlen, (char *)&bci) < 0)
+				status = SECTOR_IGNORE;
+			else
+				status = bci.Status | bci.Status1;
 			pr_debug("INFTL: status of block %d in EUN %d is %x\n",
 					block , writeEUN, status);
 
diff --git a/drivers/mtd/mtdpstore.c b/drivers/mtd/mtdpstore.c
index 7ac8ac901306..9cf3872e37ae 100644
--- a/drivers/mtd/mtdpstore.c
+++ b/drivers/mtd/mtdpstore.c
@@ -417,11 +417,14 @@ static void mtdpstore_notify_add(struct mtd_info *mtd)
 	}
 
 	longcnt = BITS_TO_LONGS(div_u64(mtd->size, info->kmsg_size));
-	cxt->rmmap = kcalloc(longcnt, sizeof(long), GFP_KERNEL);
-	cxt->usedmap = kcalloc(longcnt, sizeof(long), GFP_KERNEL);
+	cxt->rmmap = devm_kcalloc(&mtd->dev, longcnt, sizeof(long), GFP_KERNEL);
+	cxt->usedmap = devm_kcalloc(&mtd->dev, longcnt, sizeof(long), GFP_KERNEL);
 
 	longcnt = BITS_TO_LONGS(div_u64(mtd->size, mtd->erasesize));
-	cxt->badmap = kcalloc(longcnt, sizeof(long), GFP_KERNEL);
+	cxt->badmap = devm_kcalloc(&mtd->dev, longcnt, sizeof(long), GFP_KERNEL);
+
+	if (!cxt->rmmap || !cxt->usedmap || !cxt->badmap)
+		return;
 
 	/* just support dmesg right now */
 	cxt->dev.flags = PSTORE_FLAGS_DMESG;
@@ -527,9 +530,6 @@ static void mtdpstore_notify_remove(struct mtd_info *mtd)
 	mtdpstore_flush_removed(cxt);
 
 	unregister_pstore_device(&cxt->dev);
-	kfree(cxt->badmap);
-	kfree(cxt->usedmap);
-	kfree(cxt->rmmap);
 	cxt->mtd = NULL;
 	cxt->index = -1;
 }
diff --git a/drivers/mtd/nand/ecc-mxic.c b/drivers/mtd/nand/ecc-mxic.c
index 47e10945b8d2..63cb206269dd 100644
--- a/drivers/mtd/nand/ecc-mxic.c
+++ b/drivers/mtd/nand/ecc-mxic.c
@@ -614,7 +614,7 @@ static int mxic_ecc_finish_io_req_external(struct nand_device *nand,
 {
 	struct mxic_ecc_engine *mxic = nand_to_mxic(nand);
 	struct mxic_ecc_ctx *ctx = nand_to_ecc_ctx(nand);
-	int nents, step, ret;
+	int nents, step, ret = 0;
 
 	if (req->mode == MTD_OPS_RAW)
 		return 0;
diff --git a/drivers/mtd/nand/onenand/onenand_base.c b/drivers/mtd/nand/onenand/onenand_base.c
index f66385faf631..0dc2ea4fc857 100644
--- a/drivers/mtd/nand/onenand/onenand_base.c
+++ b/drivers/mtd/nand/onenand/onenand_base.c
@@ -2923,6 +2923,7 @@ static int do_otp_read(struct mtd_info *mtd, loff_t from, size_t len,
 	ret = ONENAND_IS_4KB_PAGE(this) ?
 		onenand_mlc_read_ops_nolock(mtd, from, &ops) :
 		onenand_read_ops_nolock(mtd, from, &ops);
+	*retlen = ops.retlen;
 
 	/* Exit OTP access mode */
 	this->command(mtd, ONENAND_CMD_RESET, 0, 0);
diff --git a/drivers/mtd/nand/raw/atmel/nand-controller.c b/drivers/mtd/nand/raw/atmel/nand-controller.c
index f9ccfd02e804..6f8eb7fa4c59 100644
--- a/drivers/mtd/nand/raw/atmel/nand-controller.c
+++ b/drivers/mtd/nand/raw/atmel/nand-controller.c
@@ -373,7 +373,7 @@ static int atmel_nand_dma_transfer(struct atmel_nand_controller *nc,
 	dma_cookie_t cookie;
 
 	buf_dma = dma_map_single(nc->dev, buf, len, dir);
-	if (dma_mapping_error(nc->dev, dev_dma)) {
+	if (dma_mapping_error(nc->dev, buf_dma)) {
 		dev_err(nc->dev,
 			"Failed to prepare a buffer for DMA access\n");
 		goto err;
diff --git a/drivers/mtd/nand/raw/atmel/pmecc.c b/drivers/mtd/nand/raw/atmel/pmecc.c
index 3c7dee1be21d..0b402823b619 100644
--- a/drivers/mtd/nand/raw/atmel/pmecc.c
+++ b/drivers/mtd/nand/raw/atmel/pmecc.c
@@ -143,6 +143,7 @@ struct atmel_pmecc_caps {
 	int nstrengths;
 	int el_offset;
 	bool correct_erased_chunks;
+	bool clk_ctrl;
 };
 
 struct atmel_pmecc {
@@ -843,6 +844,10 @@ static struct atmel_pmecc *atmel_pmecc_create(struct platform_device *pdev,
 	if (IS_ERR(pmecc->regs.errloc))
 		return ERR_CAST(pmecc->regs.errloc);
 
+	/* pmecc data setup time */
+	if (caps->clk_ctrl)
+		writel(PMECC_CLK_133MHZ, pmecc->regs.base + ATMEL_PMECC_CLK);
+
 	/* Disable all interrupts before registering the PMECC handler. */
 	writel(0xffffffff, pmecc->regs.base + ATMEL_PMECC_IDR);
 	atmel_pmecc_reset(pmecc);
@@ -896,6 +901,7 @@ static struct atmel_pmecc_caps at91sam9g45_caps = {
 	.strengths = atmel_pmecc_strengths,
 	.nstrengths = 5,
 	.el_offset = 0x8c,
+	.clk_ctrl = true,
 };
 
 static struct atmel_pmecc_caps sama5d4_caps = {
diff --git a/drivers/mtd/nand/raw/brcmnand/brcmnand.c b/drivers/mtd/nand/raw/brcmnand/brcmnand.c
index 1b2ec0fec60c..2eb44c1428fb 100644
--- a/drivers/mtd/nand/raw/brcmnand/brcmnand.c
+++ b/drivers/mtd/nand/raw/brcmnand/brcmnand.c
@@ -2342,6 +2342,11 @@ static int brcmnand_write(struct mtd_info *mtd, struct nand_chip *chip,
 		brcmnand_send_cmd(host, CMD_PROGRAM_PAGE);
 		status = brcmnand_waitfunc(chip);
 
+		if (status < 0) {
+			ret = status;
+			goto out;
+		}
+
 		if (status & NAND_STATUS_FAIL) {
 			dev_info(ctrl->dev, "program failed at %llx\n",
 				(unsigned long long)addr);
@@ -3003,7 +3008,7 @@ static int brcmnand_resume(struct device *dev)
 		brcmnand_save_restore_cs_config(host, 1);
 
 		/* Reset the chip, required by some chips after power-up */
-		nand_reset_op(chip);
+		nand_reset(chip, 0);
 	}
 
 	return 0;
diff --git a/drivers/mtd/nand/raw/cadence-nand-controller.c b/drivers/mtd/nand/raw/cadence-nand-controller.c
index 3bc89b356963..fca54e21a164 100644
--- a/drivers/mtd/nand/raw/cadence-nand-controller.c
+++ b/drivers/mtd/nand/raw/cadence-nand-controller.c
@@ -471,6 +471,8 @@ struct cdns_nand_ctrl {
 	struct {
 		void __iomem *virt;
 		dma_addr_t dma;
+		dma_addr_t iova_dma;
+		u32 size;
 	} io;
 
 	int irq;
@@ -1835,11 +1837,11 @@ static int cadence_nand_slave_dma_transfer(struct cdns_nand_ctrl *cdns_ctrl,
 	}
 
 	if (dir == DMA_FROM_DEVICE) {
-		src_dma = cdns_ctrl->io.dma;
+		src_dma = cdns_ctrl->io.iova_dma;
 		dst_dma = buf_dma;
 	} else {
 		src_dma = buf_dma;
-		dst_dma = cdns_ctrl->io.dma;
+		dst_dma = cdns_ctrl->io.iova_dma;
 	}
 
 	tx = dmaengine_prep_dma_memcpy(cdns_ctrl->dmac, dst_dma, src_dma, len,
@@ -1861,12 +1863,12 @@ static int cadence_nand_slave_dma_transfer(struct cdns_nand_ctrl *cdns_ctrl,
 	dma_async_issue_pending(cdns_ctrl->dmac);
 	wait_for_completion(&finished);
 
-	dma_unmap_single(cdns_ctrl->dev, buf_dma, len, dir);
+	dma_unmap_single(dma_dev->dev, buf_dma, len, dir);
 
 	return 0;
 
 err_unmap:
-	dma_unmap_single(cdns_ctrl->dev, buf_dma, len, dir);
+	dma_unmap_single(dma_dev->dev, buf_dma, len, dir);
 
 err:
 	dev_dbg(cdns_ctrl->dev, "Fall back to CPU I/O\n");
@@ -2869,6 +2871,7 @@ cadence_nand_irq_cleanup(int irqnum, struct cdns_nand_ctrl *cdns_ctrl)
 static int cadence_nand_init(struct cdns_nand_ctrl *cdns_ctrl)
 {
 	dma_cap_mask_t mask;
+	struct dma_device *dma_dev = cdns_ctrl->dmac->device;
 	int ret;
 
 	cdns_ctrl->cdma_desc = dma_alloc_coherent(cdns_ctrl->dev,
@@ -2904,15 +2907,24 @@ static int cadence_nand_init(struct cdns_nand_ctrl *cdns_ctrl)
 	dma_cap_set(DMA_MEMCPY, mask);
 
 	if (cdns_ctrl->caps1->has_dma) {
-		cdns_ctrl->dmac = dma_request_channel(mask, NULL, NULL);
-		if (!cdns_ctrl->dmac) {
-			dev_err(cdns_ctrl->dev,
-				"Unable to get a DMA channel\n");
-			ret = -EBUSY;
+		cdns_ctrl->dmac = dma_request_chan_by_mask(&mask);
+		if (IS_ERR(cdns_ctrl->dmac)) {
+			ret = dev_err_probe(cdns_ctrl->dev, PTR_ERR(cdns_ctrl->dmac),
+					    "%d: Failed to get a DMA channel\n", ret);
 			goto disable_irq;
 		}
 	}
 
+	cdns_ctrl->io.iova_dma = dma_map_resource(dma_dev->dev, cdns_ctrl->io.dma,
+						  cdns_ctrl->io.size,
+						  DMA_BIDIRECTIONAL, 0);
+
+	ret = dma_mapping_error(dma_dev->dev, cdns_ctrl->io.iova_dma);
+	if (ret) {
+		dev_err(cdns_ctrl->dev, "Failed to map I/O resource to DMA\n");
+		goto dma_release_chnl;
+	}
+
 	nand_controller_init(&cdns_ctrl->controller);
 	INIT_LIST_HEAD(&cdns_ctrl->chips);
 
@@ -2923,18 +2935,22 @@ static int cadence_nand_init(struct cdns_nand_ctrl *cdns_ctrl)
 	if (ret) {
 		dev_err(cdns_ctrl->dev, "Failed to register MTD: %d\n",
 			ret);
-		goto dma_release_chnl;
+		goto unmap_dma_resource;
 	}
 
 	kfree(cdns_ctrl->buf);
 	cdns_ctrl->buf = kzalloc(cdns_ctrl->buf_size, GFP_KERNEL);
 	if (!cdns_ctrl->buf) {
 		ret = -ENOMEM;
-		goto dma_release_chnl;
+		goto unmap_dma_resource;
 	}
 
 	return 0;
 
+unmap_dma_resource:
+	dma_unmap_resource(dma_dev->dev, cdns_ctrl->io.iova_dma,
+			   cdns_ctrl->io.size, DMA_BIDIRECTIONAL, 0);
+
 dma_release_chnl:
 	if (cdns_ctrl->dmac)
 		dma_release_channel(cdns_ctrl->dmac);
@@ -2956,6 +2972,8 @@ free_buf_desc:
 static void cadence_nand_remove(struct cdns_nand_ctrl *cdns_ctrl)
 {
 	cadence_nand_chips_cleanup(cdns_ctrl);
+	dma_unmap_resource(cdns_ctrl->dmac->device->dev, cdns_ctrl->io.iova_dma,
+			   cdns_ctrl->io.size, DMA_BIDIRECTIONAL, 0);
 	cadence_nand_irq_cleanup(cdns_ctrl->irq, cdns_ctrl);
 	kfree(cdns_ctrl->buf);
 	dma_free_coherent(cdns_ctrl->dev, sizeof(struct cadence_nand_cdma_desc),
@@ -3020,7 +3038,9 @@ static int cadence_nand_dt_probe(struct platform_device *ofdev)
 	cdns_ctrl->io.virt = devm_platform_get_and_ioremap_resource(ofdev, 1, &res);
 	if (IS_ERR(cdns_ctrl->io.virt))
 		return PTR_ERR(cdns_ctrl->io.virt);
+
 	cdns_ctrl->io.dma = res->start;
+	cdns_ctrl->io.size = resource_size(res);
 
 	dt->clk = devm_clk_get(cdns_ctrl->dev, "nf_clk");
 	if (IS_ERR(dt->clk))
diff --git a/drivers/mtd/nand/raw/qcom_nandc.c b/drivers/mtd/nand/raw/qcom_nandc.c
index b8cff9240b28..275d34119acd 100644
--- a/drivers/mtd/nand/raw/qcom_nandc.c
+++ b/drivers/mtd/nand/raw/qcom_nandc.c
@@ -2858,7 +2858,12 @@ static int qcom_param_page_type_exec(struct nand_chip *chip,  const struct nand_
 	const struct nand_op_instr *instr = NULL;
 	unsigned int op_id = 0;
 	unsigned int len = 0;
-	int ret;
+	int ret, reg_base;
+
+	reg_base = NAND_READ_LOCATION_0;
+
+	if (nandc->props->qpic_v2)
+		reg_base = NAND_READ_LOCATION_LAST_CW_0;
 
 	ret = qcom_parse_instructions(chip, subop, &q_op);
 	if (ret)
@@ -2910,14 +2915,17 @@ static int qcom_param_page_type_exec(struct nand_chip *chip,  const struct nand_
 	op_id = q_op.data_instr_idx;
 	len = nand_subop_get_data_len(subop, op_id);
 
-	nandc_set_read_loc(chip, 0, 0, 0, len, 1);
+	if (nandc->props->qpic_v2)
+		nandc_set_read_loc_last(chip, reg_base, 0, len, 1);
+	else
+		nandc_set_read_loc_first(chip, reg_base, 0, len, 1);
 
 	if (!nandc->props->qpic_v2) {
 		write_reg_dma(nandc, NAND_DEV_CMD_VLD, 1, 0);
 		write_reg_dma(nandc, NAND_DEV_CMD1, 1, NAND_BAM_NEXT_SGL);
 	}
 
-	nandc->buf_count = len;
+	nandc->buf_count = 512;
 	memset(nandc->data_buffer, 0xff, nandc->buf_count);
 
 	config_nand_single_cw_page_read(chip, false, 0);
diff --git a/drivers/mtd/nand/raw/r852.c b/drivers/mtd/nand/raw/r852.c
index ed0cf732d20e..36cfe03cd4ac 100644
--- a/drivers/mtd/nand/raw/r852.c
+++ b/drivers/mtd/nand/raw/r852.c
@@ -387,6 +387,9 @@ static int r852_wait(struct nand_chip *chip)
 static int r852_ready(struct nand_chip *chip)
 {
 	struct r852_device *dev = r852_get_dev(nand_to_mtd(chip));
+	if (dev->card_unstable)
+		return 0;
+
 	return !(r852_read_reg(dev, R852_CARD_STA) & R852_CARD_STA_BUSY);
 }
 
diff --git a/drivers/mtd/nand/raw/rockchip-nand-controller.c b/drivers/mtd/nand/raw/rockchip-nand-controller.c
index 51c9cf9013dc..1b65b3aa6aa2 100644
--- a/drivers/mtd/nand/raw/rockchip-nand-controller.c
+++ b/drivers/mtd/nand/raw/rockchip-nand-controller.c
@@ -656,9 +656,16 @@ static int rk_nfc_write_page_hwecc(struct nand_chip *chip, const u8 *buf,
 
 	dma_data = dma_map_single(nfc->dev, (void *)nfc->page_buf,
 				  mtd->writesize, DMA_TO_DEVICE);
+	if (dma_mapping_error(nfc->dev, dma_data))
+		return -ENOMEM;
+
 	dma_oob = dma_map_single(nfc->dev, nfc->oob_buf,
 				 ecc->steps * oob_step,
 				 DMA_TO_DEVICE);
+	if (dma_mapping_error(nfc->dev, dma_oob)) {
+		dma_unmap_single(nfc->dev, dma_data, mtd->writesize, DMA_TO_DEVICE);
+		return -ENOMEM;
+	}
 
 	reinit_completion(&nfc->done);
 	writel(INT_DMA, nfc->regs + nfc->cfg->int_en_off);
@@ -772,9 +779,17 @@ static int rk_nfc_read_page_hwecc(struct nand_chip *chip, u8 *buf, int oob_on,
 	dma_data = dma_map_single(nfc->dev, nfc->page_buf,
 				  mtd->writesize,
 				  DMA_FROM_DEVICE);
+	if (dma_mapping_error(nfc->dev, dma_data))
+		return -ENOMEM;
+
 	dma_oob = dma_map_single(nfc->dev, nfc->oob_buf,
 				 ecc->steps * oob_step,
 				 DMA_FROM_DEVICE);
+	if (dma_mapping_error(nfc->dev, dma_oob)) {
+		dma_unmap_single(nfc->dev, dma_data, mtd->writesize,
+				 DMA_FROM_DEVICE);
+		return -ENOMEM;
+	}
 
 	/*
 	 * The first blocks (4, 8 or 16 depending on the device)
diff --git a/drivers/mtd/nand/raw/sunxi_nand.c b/drivers/mtd/nand/raw/sunxi_nand.c
index c28634e20abf..ac887754b98e 100644
--- a/drivers/mtd/nand/raw/sunxi_nand.c
+++ b/drivers/mtd/nand/raw/sunxi_nand.c
@@ -817,6 +817,7 @@ static int sunxi_nfc_hw_ecc_read_chunk(struct nand_chip *nand,
 	if (ret)
 		return ret;
 
+	sunxi_nfc_randomizer_config(nand, page, false);
 	sunxi_nfc_randomizer_enable(nand);
 	writel(NFC_DATA_TRANS | NFC_DATA_SWAP_METHOD | NFC_ECC_OP,
 	       nfc->regs + NFC_REG_CMD);
@@ -1049,6 +1050,7 @@ static int sunxi_nfc_hw_ecc_write_chunk(struct nand_chip *nand,
 	if (ret)
 		return ret;
 
+	sunxi_nfc_randomizer_config(nand, page, false);
 	sunxi_nfc_randomizer_enable(nand);
 	sunxi_nfc_hw_ecc_set_prot_oob_bytes(nand, oob, 0, bbm, page);
 
diff --git a/drivers/mtd/nand/spi/core.c b/drivers/mtd/nand/spi/core.c
index 4d76f9f71a0e..241f6a4df16c 100644
--- a/drivers/mtd/nand/spi/core.c
+++ b/drivers/mtd/nand/spi/core.c
@@ -1496,6 +1496,7 @@ static void spinand_cleanup(struct spinand_device *spinand)
 {
 	struct nand_device *nand = spinand_to_nand(spinand);
 
+	nanddev_ecc_engine_cleanup(nand);
 	nanddev_cleanup(nand);
 	spinand_manufacturer_cleanup(spinand);
 	kfree(spinand->databuf);
diff --git a/drivers/mtd/spi-nor/spansion.c b/drivers/mtd/spi-nor/spansion.c
index 5a88a6096ca8..fcd081b75784 100644
--- a/drivers/mtd/spi-nor/spansion.c
+++ b/drivers/mtd/spi-nor/spansion.c
@@ -17,6 +17,7 @@
 
 #define SPINOR_OP_CLSR		0x30	/* Clear status register 1 */
 #define SPINOR_OP_CLPEF		0x82	/* Clear program/erase failure flags */
+#define SPINOR_OP_CYPRESS_EX4B	0xB8	/* Exit 4-byte address mode */
 #define SPINOR_OP_CYPRESS_DIE_ERASE		0x61	/* Chip (die) erase */
 #define SPINOR_OP_RD_ANY_REG			0x65	/* Read any register */
 #define SPINOR_OP_WR_ANY_REG			0x71	/* Write any register */
@@ -58,6 +59,13 @@
 		   SPI_MEM_OP_DUMMY(ndummy, 0),				\
 		   SPI_MEM_OP_DATA_IN(1, buf, 0))
 
+#define CYPRESS_NOR_EN4B_EX4B_OP(enable)				\
+	SPI_MEM_OP(SPI_MEM_OP_CMD(enable ? SPINOR_OP_EN4B :		\
+					   SPINOR_OP_CYPRESS_EX4B, 0),	\
+		   SPI_MEM_OP_NO_ADDR,					\
+		   SPI_MEM_OP_NO_DUMMY,					\
+		   SPI_MEM_OP_NO_DATA)
+
 #define SPANSION_OP(opcode)						\
 	SPI_MEM_OP(SPI_MEM_OP_CMD(opcode, 0),				\
 		   SPI_MEM_OP_NO_ADDR,					\
@@ -356,6 +364,20 @@ static int cypress_nor_quad_enable_volatile(struct spi_nor *nor)
 	return 0;
 }
 
+static int cypress_nor_set_4byte_addr_mode(struct spi_nor *nor, bool enable)
+{
+	int ret;
+	struct spi_mem_op op = CYPRESS_NOR_EN4B_EX4B_OP(enable);
+
+	spi_nor_spimem_setup_op(nor, &op, nor->reg_proto);
+
+	ret = spi_mem_exec_op(nor->spimem, &op);
+	if (ret)
+		dev_dbg(nor->dev, "error %d setting 4-byte mode\n", ret);
+
+	return ret;
+}
+
 /**
  * cypress_nor_determine_addr_mode_by_sr1() - Determine current address mode
  *                                            (3 or 4-byte) by querying status
@@ -526,6 +548,9 @@ s25fs256t_post_bfpt_fixup(struct spi_nor *nor,
 	struct spi_mem_op op;
 	int ret;
 
+	/* Assign 4-byte address mode method that is not determined in BFPT */
+	nor->params->set_4byte_addr_mode = cypress_nor_set_4byte_addr_mode;
+
 	ret = cypress_nor_set_addr_mode_nbytes(nor);
 	if (ret)
 		return ret;
@@ -591,6 +616,9 @@ s25hx_t_post_bfpt_fixup(struct spi_nor *nor,
 {
 	int ret;
 
+	/* Assign 4-byte address mode method that is not determined in BFPT */
+	nor->params->set_4byte_addr_mode = cypress_nor_set_4byte_addr_mode;
+
 	ret = cypress_nor_set_addr_mode_nbytes(nor);
 	if (ret)
 		return ret;
@@ -718,6 +746,9 @@ static int s28hx_t_post_bfpt_fixup(struct spi_nor *nor,
 				   const struct sfdp_parameter_header *bfpt_header,
 				   const struct sfdp_bfpt *bfpt)
 {
+	/* Assign 4-byte address mode method that is not determined in BFPT */
+	nor->params->set_4byte_addr_mode = cypress_nor_set_4byte_addr_mode;
+
 	return cypress_nor_set_addr_mode_nbytes(nor);
 }
 
diff --git a/drivers/mtd/spi-nor/sst.c b/drivers/mtd/spi-nor/sst.c
index b5ad7118c49a..175211fe6a5e 100644
--- a/drivers/mtd/spi-nor/sst.c
+++ b/drivers/mtd/spi-nor/sst.c
@@ -174,7 +174,7 @@ static int sst_nor_write_data(struct spi_nor *nor, loff_t to, size_t len,
 	int ret;
 
 	nor->program_opcode = op;
-	ret = spi_nor_write_data(nor, to, 1, buf);
+	ret = spi_nor_write_data(nor, to, len, buf);
 	if (ret < 0)
 		return ret;
 	WARN(ret != len, "While writing %zu byte written %i bytes\n", len, ret);
diff --git a/drivers/mtd/ubi/build.c b/drivers/mtd/ubi/build.c
index 30be4ed68fad..ef6a22f372f9 100644
--- a/drivers/mtd/ubi/build.c
+++ b/drivers/mtd/ubi/build.c
@@ -1537,7 +1537,7 @@ static int ubi_mtd_param_parse(const char *val, const struct kernel_param *kp)
 	if (token) {
 		int err = kstrtoint(token, 10, &p->ubi_num);
 
-		if (err) {
+		if (err || p->ubi_num < UBI_DEV_NUM_AUTO) {
 			pr_err("UBI error: bad value for ubi_num parameter: %s\n",
 			       token);
 			return -EINVAL;
diff --git a/drivers/net/arcnet/com20020-pci.c b/drivers/net/arcnet/com20020-pci.c
index c5e571ec94c9..0472bcdff130 100644
--- a/drivers/net/arcnet/com20020-pci.c
+++ b/drivers/net/arcnet/com20020-pci.c
@@ -251,18 +251,33 @@ static int com20020pci_probe(struct pci_dev *pdev,
 			card->tx_led.default_trigger = devm_kasprintf(&pdev->dev,
 							GFP_KERNEL, "arc%d-%d-tx",
 							dev->dev_id, i);
+			if (!card->tx_led.default_trigger) {
+				ret = -ENOMEM;
+				goto err_free_arcdev;
+			}
 			card->tx_led.name = devm_kasprintf(&pdev->dev, GFP_KERNEL,
 							"pci:green:tx:%d-%d",
 							dev->dev_id, i);
-
+			if (!card->tx_led.name) {
+				ret = -ENOMEM;
+				goto err_free_arcdev;
+			}
 			card->tx_led.dev = &dev->dev;
 			card->recon_led.brightness_set = led_recon_set;
 			card->recon_led.default_trigger = devm_kasprintf(&pdev->dev,
 							GFP_KERNEL, "arc%d-%d-recon",
 							dev->dev_id, i);
+			if (!card->recon_led.default_trigger) {
+				ret = -ENOMEM;
+				goto err_free_arcdev;
+			}
 			card->recon_led.name = devm_kasprintf(&pdev->dev, GFP_KERNEL,
 							"pci:red:recon:%d-%d",
 							dev->dev_id, i);
+			if (!card->recon_led.name) {
+				ret = -ENOMEM;
+				goto err_free_arcdev;
+			}
 			card->recon_led.dev = &dev->dev;
 
 			ret = devm_led_classdev_register(&pdev->dev, &card->tx_led);
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 4d73abae503d..52ff0f9e04e0 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -497,9 +497,9 @@ static int bond_ipsec_add_sa(struct xfrm_state *xs,
 		goto out;
 	}
 
-	xs->xso.real_dev = real_dev;
 	err = real_dev->xfrmdev_ops->xdo_dev_state_add(xs, extack);
 	if (!err) {
+		xs->xso.real_dev = real_dev;
 		ipsec->xs = xs;
 		INIT_LIST_HEAD(&ipsec->list);
 		mutex_lock(&bond->ipsec_lock);
@@ -541,11 +541,11 @@ static void bond_ipsec_add_sa_all(struct bonding *bond)
 		if (ipsec->xs->xso.real_dev == real_dev)
 			continue;
 
-		ipsec->xs->xso.real_dev = real_dev;
 		if (real_dev->xfrmdev_ops->xdo_dev_state_add(ipsec->xs, NULL)) {
 			slave_warn(bond_dev, real_dev, "%s: failed to add SA\n", __func__);
-			ipsec->xs->xso.real_dev = NULL;
+			continue;
 		}
+		ipsec->xs->xso.real_dev = real_dev;
 	}
 out:
 	mutex_unlock(&bond->ipsec_lock);
@@ -627,6 +627,7 @@ static void bond_ipsec_del_sa_all(struct bonding *bond)
 				   "%s: no slave xdo_dev_state_delete\n",
 				   __func__);
 		} else {
+			ipsec->xs->xso.real_dev = NULL;
 			real_dev->xfrmdev_ops->xdo_dev_state_delete(ipsec->xs);
 			if (real_dev->xfrmdev_ops->xdo_dev_state_free)
 				real_dev->xfrmdev_ops->xdo_dev_state_free(ipsec->xs);
@@ -661,6 +662,7 @@ static void bond_ipsec_free_sa(struct xfrm_state *xs)
 
 	WARN_ON(xs->xso.real_dev != real_dev);
 
+	xs->xso.real_dev = NULL;
 	if (real_dev && real_dev->xfrmdev_ops &&
 	    real_dev->xfrmdev_ops->xdo_dev_state_free)
 		real_dev->xfrmdev_ops->xdo_dev_state_free(xs);
@@ -2113,15 +2115,26 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
 		 * set the master's mac address to that of the first slave
 		 */
 		memcpy(ss.__data, bond_dev->dev_addr, bond_dev->addr_len);
-		ss.ss_family = slave_dev->type;
-		res = dev_set_mac_address(slave_dev, (struct sockaddr *)&ss,
-					  extack);
-		if (res) {
-			slave_err(bond_dev, slave_dev, "Error %d calling set_mac_address\n", res);
-			goto err_restore_mtu;
-		}
+	} else if (bond->params.fail_over_mac == BOND_FOM_FOLLOW &&
+		   BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP &&
+		   memcmp(slave_dev->dev_addr, bond_dev->dev_addr, bond_dev->addr_len) == 0) {
+		/* Set slave to random address to avoid duplicate mac
+		 * address in later fail over.
+		 */
+		eth_random_addr(ss.__data);
+	} else {
+		goto skip_mac_set;
 	}
 
+	ss.ss_family = slave_dev->type;
+	res = dev_set_mac_address(slave_dev, (struct sockaddr *)&ss, extack);
+	if (res) {
+		slave_err(bond_dev, slave_dev, "Error %d calling set_mac_address\n", res);
+		goto err_restore_mtu;
+	}
+
+skip_mac_set:
+
 	/* set no_addrconf flag before open to prevent IPv6 addrconf */
 	slave_dev->priv_flags |= IFF_NO_ADDRCONF;
 
@@ -2542,7 +2555,7 @@ static int __bond_release_one(struct net_device *bond_dev,
 
 	RCU_INIT_POINTER(bond->current_arp_slave, NULL);
 
-	if (!all && (!bond->params.fail_over_mac ||
+	if (!all && (bond->params.fail_over_mac != BOND_FOM_ACTIVE ||
 		     BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP)) {
 		if (ether_addr_equal_64bits(bond_dev->dev_addr, slave->perm_hwaddr) &&
 		    bond_has_slaves(bond))
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index 327b6ecdc77e..d1b095af253b 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -1242,10 +1242,28 @@ static bool slave_can_set_ns_maddr(const struct bonding *bond, struct slave *sla
 	       slave->dev->flags & IFF_MULTICAST;
 }
 
+/**
+ * slave_set_ns_maddrs - add/del all NS mac addresses for slave
+ * @bond: bond device
+ * @slave: slave device
+ * @add: add or remove all the NS mac addresses
+ *
+ * This function tries to add or delete all the NS mac addresses on the slave
+ *
+ * Note, the IPv6 NS target address is the unicast address in Neighbor
+ * Solicitation (NS) message. The dest address of NS message should be
+ * solicited-node multicast address of the target. The dest mac of NS message
+ * is converted from the solicited-node multicast address.
+ *
+ * This function is called when
+ *   * arp_validate changes
+ *   * enslaving, releasing new slaves
+ */
 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];
+	struct in6_addr mcaddr;
 	int i;
 
 	if (!slave_can_set_ns_maddr(bond, slave))
@@ -1255,7 +1273,8 @@ static void slave_set_ns_maddrs(struct bonding *bond, struct slave *slave, bool
 		if (ipv6_addr_any(&targets[i]))
 			break;
 
-		if (!ndisc_mc_map(&targets[i], slot_maddr, slave->dev, 0)) {
+		addrconf_addr_solict_mult(&targets[i], &mcaddr);
+		if (!ndisc_mc_map(&mcaddr, slot_maddr, slave->dev, 0)) {
 			if (add)
 				dev_mc_add(slave->dev, slot_maddr);
 			else
@@ -1278,23 +1297,43 @@ void bond_slave_ns_maddrs_del(struct bonding *bond, struct slave *slave)
 	slave_set_ns_maddrs(bond, slave, false);
 }
 
+/**
+ * slave_set_ns_maddr - set new NS mac address for slave
+ * @bond: bond device
+ * @slave: slave device
+ * @target: the new IPv6 target
+ * @slot: the old IPv6 target in the slot
+ *
+ * This function tries to replace the old mac address to new one on the slave.
+ *
+ * Note, the target/slot IPv6 address is the unicast address in Neighbor
+ * Solicitation (NS) message. The dest address of NS message should be
+ * solicited-node multicast address of the target. The dest mac of NS message
+ * is converted from the solicited-node multicast address.
+ *
+ * This function is called when
+ *   * An IPv6 NS target is added or removed.
+ */
 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];
+	char mac_addr[MAX_ADDR_LEN];
+	struct in6_addr mcast_addr;
 
 	if (!bond->params.arp_validate || !slave_can_set_ns_maddr(bond, slave))
 		return;
 
-	/* remove the previous maddr from slave */
+	/* remove the previous mac addr from slave */
+	addrconf_addr_solict_mult(slot, &mcast_addr);
 	if (!ipv6_addr_any(slot) &&
-	    !ndisc_mc_map(slot, slot_maddr, slave->dev, 0))
-		dev_mc_del(slave->dev, slot_maddr);
+	    !ndisc_mc_map(&mcast_addr, mac_addr, slave->dev, 0))
+		dev_mc_del(slave->dev, mac_addr);
 
-	/* add new maddr on slave if target is set */
+	/* add new mac addr on slave if target is set */
+	addrconf_addr_solict_mult(target, &mcast_addr);
 	if (!ipv6_addr_any(target) &&
-	    !ndisc_mc_map(target, target_maddr, slave->dev, 0))
-		dev_mc_add(slave->dev, target_maddr);
+	    !ndisc_mc_map(&mcast_addr, mac_addr, slave->dev, 0))
+		dev_mc_add(slave->dev, mac_addr);
 }
 
 static void _bond_options_ns_ip6_target_set(struct bonding *bond, int slot,
diff --git a/drivers/net/caif/caif_virtio.c b/drivers/net/caif/caif_virtio.c
index 7fea00c7ca8a..c60386bf2d1a 100644
--- a/drivers/net/caif/caif_virtio.c
+++ b/drivers/net/caif/caif_virtio.c
@@ -745,7 +745,7 @@ err:
 
 	if (cfv->vr_rx)
 		vdev->vringh_config->del_vrhs(cfv->vdev);
-	if (cfv->vdev)
+	if (cfv->vq_tx)
 		vdev->config->del_vqs(cfv->vdev);
 	free_netdev(netdev);
 	return err;
diff --git a/drivers/net/can/c_can/c_can_platform.c b/drivers/net/can/c_can/c_can_platform.c
index 6cba9717a6d8..bb6071a758f3 100644
--- a/drivers/net/can/c_can/c_can_platform.c
+++ b/drivers/net/can/c_can/c_can_platform.c
@@ -324,7 +324,7 @@ static int c_can_plat_probe(struct platform_device *pdev)
 		/* Check if we need custom RAMINIT via syscon. Mostly for TI
 		 * platforms. Only supported with DT boot.
 		 */
-		if (np && of_property_read_bool(np, "syscon-raminit")) {
+		if (np && of_property_present(np, "syscon-raminit")) {
 			u32 id;
 			struct c_can_raminit *raminit = &priv->raminit_sys;
 
@@ -385,15 +385,16 @@ static int c_can_plat_probe(struct platform_device *pdev)
 	if (ret) {
 		dev_err(&pdev->dev, "registering %s failed (err=%d)\n",
 			KBUILD_MODNAME, ret);
-		goto exit_free_device;
+		goto exit_pm_runtime;
 	}
 
 	dev_info(&pdev->dev, "%s device registered (regs=%p, irq=%d)\n",
 		 KBUILD_MODNAME, priv->base, dev->irq);
 	return 0;
 
-exit_free_device:
+exit_pm_runtime:
 	pm_runtime_disable(priv->device);
+exit_free_device:
 	free_c_can_dev(dev);
 exit:
 	dev_err(&pdev->dev, "probe failed\n");
diff --git a/drivers/net/can/ctucanfd/ctucanfd_base.c b/drivers/net/can/ctucanfd/ctucanfd_base.c
index 64c349fd4600..f65c1a1e05cc 100644
--- a/drivers/net/can/ctucanfd/ctucanfd_base.c
+++ b/drivers/net/can/ctucanfd/ctucanfd_base.c
@@ -867,10 +867,12 @@ static void ctucan_err_interrupt(struct net_device *ndev, u32 isr)
 			}
 			break;
 		case CAN_STATE_ERROR_ACTIVE:
-			cf->can_id |= CAN_ERR_CNT;
-			cf->data[1] = CAN_ERR_CRTL_ACTIVE;
-			cf->data[6] = bec.txerr;
-			cf->data[7] = bec.rxerr;
+			if (skb) {
+				cf->can_id |= CAN_ERR_CNT;
+				cf->data[1] = CAN_ERR_CRTL_ACTIVE;
+				cf->data[6] = bec.txerr;
+				cf->data[7] = bec.rxerr;
+			}
 			break;
 		default:
 			netdev_warn(ndev, "unhandled error state (%d:%s)!\n",
diff --git a/drivers/net/can/dev/dev.c b/drivers/net/can/dev/dev.c
index 681643ab3780..63e4a495b137 100644
--- a/drivers/net/can/dev/dev.c
+++ b/drivers/net/can/dev/dev.c
@@ -147,13 +147,16 @@ void can_change_state(struct net_device *dev, struct can_frame *cf,
 EXPORT_SYMBOL_GPL(can_change_state);
 
 /* CAN device restart for bus-off recovery */
-static void can_restart(struct net_device *dev)
+static int can_restart(struct net_device *dev)
 {
 	struct can_priv *priv = netdev_priv(dev);
 	struct sk_buff *skb;
 	struct can_frame *cf;
 	int err;
 
+	if (!priv->do_set_mode)
+		return -EOPNOTSUPP;
+
 	if (netif_carrier_ok(dev))
 		netdev_err(dev, "Attempt to restart for bus-off recovery, but carrier is OK?\n");
 
@@ -175,10 +178,14 @@ static void can_restart(struct net_device *dev)
 	if (err) {
 		netdev_err(dev, "Restart failed, error %pe\n", ERR_PTR(err));
 		netif_carrier_off(dev);
+
+		return err;
 	} else {
 		netdev_dbg(dev, "Restarted\n");
 		priv->can_stats.restarts++;
 	}
+
+	return 0;
 }
 
 static void can_restart_work(struct work_struct *work)
@@ -203,9 +210,8 @@ int can_restart_now(struct net_device *dev)
 		return -EBUSY;
 
 	cancel_delayed_work_sync(&priv->restart_work);
-	can_restart(dev);
 
-	return 0;
+	return can_restart(dev);
 }
 
 /* CAN bus-off
diff --git a/drivers/net/can/dev/netlink.c b/drivers/net/can/dev/netlink.c
index 01aacdcda260..abe8dc051d94 100644
--- a/drivers/net/can/dev/netlink.c
+++ b/drivers/net/can/dev/netlink.c
@@ -285,6 +285,12 @@ static int can_changelink(struct net_device *dev, struct nlattr *tb[],
 	}
 
 	if (data[IFLA_CAN_RESTART_MS]) {
+		if (!priv->do_set_mode) {
+			NL_SET_ERR_MSG(extack,
+				       "Device doesn't support restart from Bus Off");
+			return -EOPNOTSUPP;
+		}
+
 		/* Do not allow changing restart delay while running */
 		if (dev->flags & IFF_UP)
 			return -EBUSY;
@@ -292,6 +298,12 @@ static int can_changelink(struct net_device *dev, struct nlattr *tb[],
 	}
 
 	if (data[IFLA_CAN_RESTART]) {
+		if (!priv->do_set_mode) {
+			NL_SET_ERR_MSG(extack,
+				       "Device doesn't support restart from Bus Off");
+			return -EOPNOTSUPP;
+		}
+
 		/* Do not allow a restart while not running */
 		if (!(dev->flags & IFF_UP))
 			return -EINVAL;
diff --git a/drivers/net/can/flexcan/flexcan-core.c b/drivers/net/can/flexcan/flexcan-core.c
index ac1a860986df..fca290afb532 100644
--- a/drivers/net/can/flexcan/flexcan-core.c
+++ b/drivers/net/can/flexcan/flexcan-core.c
@@ -386,6 +386,16 @@ static const struct flexcan_devtype_data fsl_lx2160a_r1_devtype_data = {
 		FLEXCAN_QUIRK_SUPPORT_RX_MAILBOX_RTR,
 };
 
+static const struct flexcan_devtype_data nxp_s32g2_devtype_data = {
+	.quirks = FLEXCAN_QUIRK_DISABLE_RXFG | FLEXCAN_QUIRK_ENABLE_EACEN_RRS |
+		FLEXCAN_QUIRK_DISABLE_MECR | FLEXCAN_QUIRK_BROKEN_PERR_STATE |
+		FLEXCAN_QUIRK_USE_RX_MAILBOX | FLEXCAN_QUIRK_SUPPORT_FD |
+		FLEXCAN_QUIRK_SUPPORT_ECC | FLEXCAN_QUIRK_NR_IRQ_3 |
+		FLEXCAN_QUIRK_SUPPORT_RX_MAILBOX |
+		FLEXCAN_QUIRK_SUPPORT_RX_MAILBOX_RTR |
+		FLEXCAN_QUIRK_SECONDARY_MB_IRQ,
+};
+
 static const struct can_bittiming_const flexcan_bittiming_const = {
 	.name = DRV_NAME,
 	.tseg1_min = 4,
@@ -1762,14 +1772,25 @@ static int flexcan_open(struct net_device *dev)
 			goto out_free_irq_boff;
 	}
 
+	if (priv->devtype_data.quirks & FLEXCAN_QUIRK_SECONDARY_MB_IRQ) {
+		err = request_irq(priv->irq_secondary_mb,
+				  flexcan_irq, IRQF_SHARED, dev->name, dev);
+		if (err)
+			goto out_free_irq_err;
+	}
+
 	flexcan_chip_interrupts_enable(dev);
 
 	netif_start_queue(dev);
 
 	return 0;
 
+ out_free_irq_err:
+	if (priv->devtype_data.quirks & FLEXCAN_QUIRK_NR_IRQ_3)
+		free_irq(priv->irq_err, dev);
  out_free_irq_boff:
-	free_irq(priv->irq_boff, dev);
+	if (priv->devtype_data.quirks & FLEXCAN_QUIRK_NR_IRQ_3)
+		free_irq(priv->irq_boff, dev);
  out_free_irq:
 	free_irq(dev->irq, dev);
  out_can_rx_offload_disable:
@@ -1794,6 +1815,9 @@ static int flexcan_close(struct net_device *dev)
 	netif_stop_queue(dev);
 	flexcan_chip_interrupts_disable(dev);
 
+	if (priv->devtype_data.quirks & FLEXCAN_QUIRK_SECONDARY_MB_IRQ)
+		free_irq(priv->irq_secondary_mb, dev);
+
 	if (priv->devtype_data.quirks & FLEXCAN_QUIRK_NR_IRQ_3) {
 		free_irq(priv->irq_err, dev);
 		free_irq(priv->irq_boff, dev);
@@ -2041,6 +2065,7 @@ static const struct of_device_id flexcan_of_match[] = {
 	{ .compatible = "fsl,vf610-flexcan", .data = &fsl_vf610_devtype_data, },
 	{ .compatible = "fsl,ls1021ar2-flexcan", .data = &fsl_ls1021a_r2_devtype_data, },
 	{ .compatible = "fsl,lx2160ar1-flexcan", .data = &fsl_lx2160a_r1_devtype_data, },
+	{ .compatible = "nxp,s32g2-flexcan", .data = &nxp_s32g2_devtype_data, },
 	{ /* sentinel */ },
 };
 MODULE_DEVICE_TABLE(of, flexcan_of_match);
@@ -2187,6 +2212,14 @@ static int flexcan_probe(struct platform_device *pdev)
 		}
 	}
 
+	if (priv->devtype_data.quirks & FLEXCAN_QUIRK_SECONDARY_MB_IRQ) {
+		priv->irq_secondary_mb = platform_get_irq_byname(pdev, "mb-1");
+		if (priv->irq_secondary_mb < 0) {
+			err = priv->irq_secondary_mb;
+			goto failed_platform_get_irq;
+		}
+	}
+
 	if (priv->devtype_data.quirks & FLEXCAN_QUIRK_SUPPORT_FD) {
 		priv->can.ctrlmode_supported |= CAN_CTRLMODE_FD |
 			CAN_CTRLMODE_FD_NON_ISO;
@@ -2260,14 +2293,19 @@ static int __maybe_unused flexcan_suspend(struct device *device)
 
 			flexcan_chip_interrupts_disable(dev);
 
+			err = flexcan_transceiver_disable(priv);
+			if (err)
+				return err;
+
 			err = pinctrl_pm_select_sleep_state(device);
 			if (err)
 				return err;
 		}
 		netif_stop_queue(dev);
 		netif_device_detach(dev);
+
+		priv->can.state = CAN_STATE_SLEEPING;
 	}
-	priv->can.state = CAN_STATE_SLEEPING;
 
 	return 0;
 }
@@ -2278,7 +2316,6 @@ static int __maybe_unused flexcan_resume(struct device *device)
 	struct flexcan_priv *priv = netdev_priv(dev);
 	int err;
 
-	priv->can.state = CAN_STATE_ERROR_ACTIVE;
 	if (netif_running(dev)) {
 		netif_device_attach(dev);
 		netif_start_queue(dev);
@@ -2292,12 +2329,20 @@ static int __maybe_unused flexcan_resume(struct device *device)
 			if (err)
 				return err;
 
-			err = flexcan_chip_start(dev);
+			err = flexcan_transceiver_enable(priv);
 			if (err)
 				return err;
 
+			err = flexcan_chip_start(dev);
+			if (err) {
+				flexcan_transceiver_disable(priv);
+				return err;
+			}
+
 			flexcan_chip_interrupts_enable(dev);
 		}
+
+		priv->can.state = CAN_STATE_ERROR_ACTIVE;
 	}
 
 	return 0;
diff --git a/drivers/net/can/flexcan/flexcan.h b/drivers/net/can/flexcan/flexcan.h
index 4933d8c7439e..2cf886618c96 100644
--- a/drivers/net/can/flexcan/flexcan.h
+++ b/drivers/net/can/flexcan/flexcan.h
@@ -70,6 +70,10 @@
 #define FLEXCAN_QUIRK_SUPPORT_RX_FIFO BIT(16)
 /* Setup stop mode with ATF SCMI protocol to support wakeup */
 #define FLEXCAN_QUIRK_SETUP_STOP_MODE_SCMI BIT(17)
+/* Device has two separate interrupt lines for two mailbox ranges, which
+ * both need to have an interrupt handler registered.
+ */
+#define FLEXCAN_QUIRK_SECONDARY_MB_IRQ	BIT(18)
 
 struct flexcan_devtype_data {
 	u32 quirks;		/* quirks needed for different IP cores */
@@ -107,6 +111,7 @@ struct flexcan_priv {
 
 	int irq_boff;
 	int irq_err;
+	int irq_secondary_mb;
 
 	/* IPC handle when setup stop mode by System Controller firmware(scfw) */
 	struct imx_sc_ipc *sc_ipc_handle;
diff --git a/drivers/net/can/kvaser_pciefd.c b/drivers/net/can/kvaser_pciefd.c
index fee012b57f33..2bef6da4befa 100644
--- a/drivers/net/can/kvaser_pciefd.c
+++ b/drivers/net/can/kvaser_pciefd.c
@@ -16,6 +16,7 @@
 #include <linux/netdevice.h>
 #include <linux/pci.h>
 #include <linux/timer.h>
+#include <net/netdev_queues.h>
 
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Kvaser AB <support@kvaser.com>");
@@ -410,10 +411,13 @@ struct kvaser_pciefd_can {
 	void __iomem *reg_base;
 	struct can_berr_counter bec;
 	u8 cmd_seq;
+	u8 tx_max_count;
+	u8 tx_idx;
+	u8 ack_idx;
 	int err_rep_cnt;
-	int echo_idx;
+	unsigned int completed_tx_pkts;
+	unsigned int completed_tx_bytes;
 	spinlock_t lock; /* Locks sensitive registers (e.g. MODE) */
-	spinlock_t echo_lock; /* Locks the message echo buffer */
 	struct timer_list bec_poll_timer;
 	struct completion start_comp, flush_comp;
 };
@@ -714,6 +718,9 @@ static int kvaser_pciefd_open(struct net_device *netdev)
 	int ret;
 	struct kvaser_pciefd_can *can = netdev_priv(netdev);
 
+	can->tx_idx = 0;
+	can->ack_idx = 0;
+
 	ret = open_candev(netdev);
 	if (ret)
 		return ret;
@@ -745,21 +752,26 @@ static int kvaser_pciefd_stop(struct net_device *netdev)
 		del_timer(&can->bec_poll_timer);
 	}
 	can->can.state = CAN_STATE_STOPPED;
+	netdev_reset_queue(netdev);
 	close_candev(netdev);
 
 	return ret;
 }
 
+static unsigned int kvaser_pciefd_tx_avail(const struct kvaser_pciefd_can *can)
+{
+	return can->tx_max_count - (READ_ONCE(can->tx_idx) - READ_ONCE(can->ack_idx));
+}
+
 static int kvaser_pciefd_prepare_tx_packet(struct kvaser_pciefd_tx_packet *p,
-					   struct kvaser_pciefd_can *can,
+					   struct can_priv *can, u8 seq,
 					   struct sk_buff *skb)
 {
 	struct canfd_frame *cf = (struct canfd_frame *)skb->data;
 	int packet_size;
-	int seq = can->echo_idx;
 
 	memset(p, 0, sizeof(*p));
-	if (can->can.ctrlmode & CAN_CTRLMODE_ONE_SHOT)
+	if (can->ctrlmode & CAN_CTRLMODE_ONE_SHOT)
 		p->header[1] |= KVASER_PCIEFD_TPACKET_SMS;
 
 	if (cf->can_id & CAN_RTR_FLAG)
@@ -782,7 +794,7 @@ static int kvaser_pciefd_prepare_tx_packet(struct kvaser_pciefd_tx_packet *p,
 	} else {
 		p->header[1] |=
 			FIELD_PREP(KVASER_PCIEFD_RPACKET_DLC_MASK,
-				   can_get_cc_dlc((struct can_frame *)cf, can->can.ctrlmode));
+				   can_get_cc_dlc((struct can_frame *)cf, can->ctrlmode));
 	}
 
 	p->header[1] |= FIELD_PREP(KVASER_PCIEFD_PACKET_SEQ_MASK, seq);
@@ -797,22 +809,24 @@ static netdev_tx_t kvaser_pciefd_start_xmit(struct sk_buff *skb,
 					    struct net_device *netdev)
 {
 	struct kvaser_pciefd_can *can = netdev_priv(netdev);
-	unsigned long irq_flags;
 	struct kvaser_pciefd_tx_packet packet;
+	unsigned int seq = can->tx_idx & (can->can.echo_skb_max - 1);
+	unsigned int frame_len;
 	int nr_words;
-	u8 count;
 
 	if (can_dev_dropped_skb(netdev, skb))
 		return NETDEV_TX_OK;
+	if (!netif_subqueue_maybe_stop(netdev, 0, kvaser_pciefd_tx_avail(can), 1, 1))
+		return NETDEV_TX_BUSY;
 
-	nr_words = kvaser_pciefd_prepare_tx_packet(&packet, can, skb);
+	nr_words = kvaser_pciefd_prepare_tx_packet(&packet, &can->can, seq, skb);
 
-	spin_lock_irqsave(&can->echo_lock, irq_flags);
 	/* Prepare and save echo skb in internal slot */
-	can_put_echo_skb(skb, netdev, can->echo_idx, 0);
-
-	/* Move echo index to the next slot */
-	can->echo_idx = (can->echo_idx + 1) % can->can.echo_skb_max;
+	WRITE_ONCE(can->can.echo_skb[seq], NULL);
+	frame_len = can_skb_get_frame_len(skb);
+	can_put_echo_skb(skb, netdev, seq, frame_len);
+	netdev_sent_queue(netdev, frame_len);
+	WRITE_ONCE(can->tx_idx, can->tx_idx + 1);
 
 	/* Write header to fifo */
 	iowrite32(packet.header[0],
@@ -836,14 +850,7 @@ static netdev_tx_t kvaser_pciefd_start_xmit(struct sk_buff *skb,
 			     KVASER_PCIEFD_KCAN_FIFO_LAST_REG);
 	}
 
-	count = FIELD_GET(KVASER_PCIEFD_KCAN_TX_NR_PACKETS_CURRENT_MASK,
-			  ioread32(can->reg_base + KVASER_PCIEFD_KCAN_TX_NR_PACKETS_REG));
-	/* No room for a new message, stop the queue until at least one
-	 * successful transmit
-	 */
-	if (count >= can->can.echo_skb_max || can->can.echo_skb[can->echo_idx])
-		netif_stop_queue(netdev);
-	spin_unlock_irqrestore(&can->echo_lock, irq_flags);
+	netif_subqueue_maybe_stop(netdev, 0, kvaser_pciefd_tx_avail(can), 1, 1);
 
 	return NETDEV_TX_OK;
 }
@@ -959,7 +966,7 @@ static int kvaser_pciefd_setup_can_ctrls(struct kvaser_pciefd *pcie)
 		u32 status, tx_nr_packets_max;
 
 		netdev = alloc_candev(sizeof(struct kvaser_pciefd_can),
-				      KVASER_PCIEFD_CAN_TX_MAX_COUNT);
+				      roundup_pow_of_two(KVASER_PCIEFD_CAN_TX_MAX_COUNT));
 		if (!netdev)
 			return -ENOMEM;
 
@@ -970,8 +977,11 @@ static int kvaser_pciefd_setup_can_ctrls(struct kvaser_pciefd *pcie)
 		can->kv_pcie = pcie;
 		can->cmd_seq = 0;
 		can->err_rep_cnt = 0;
+		can->completed_tx_pkts = 0;
+		can->completed_tx_bytes = 0;
 		can->bec.txerr = 0;
 		can->bec.rxerr = 0;
+		can->can.dev->dev_port = i;
 
 		init_completion(&can->start_comp);
 		init_completion(&can->flush_comp);
@@ -983,11 +993,9 @@ static int kvaser_pciefd_setup_can_ctrls(struct kvaser_pciefd *pcie)
 		tx_nr_packets_max =
 			FIELD_GET(KVASER_PCIEFD_KCAN_TX_NR_PACKETS_MAX_MASK,
 				  ioread32(can->reg_base + KVASER_PCIEFD_KCAN_TX_NR_PACKETS_REG));
+		can->tx_max_count = min(KVASER_PCIEFD_CAN_TX_MAX_COUNT, tx_nr_packets_max - 1);
 
 		can->can.clock.freq = pcie->freq;
-		can->can.echo_skb_max = min(KVASER_PCIEFD_CAN_TX_MAX_COUNT, tx_nr_packets_max - 1);
-		can->echo_idx = 0;
-		spin_lock_init(&can->echo_lock);
 		spin_lock_init(&can->lock);
 
 		can->can.bittiming_const = &kvaser_pciefd_bittiming_const;
@@ -1200,7 +1208,7 @@ static int kvaser_pciefd_handle_data_packet(struct kvaser_pciefd *pcie,
 		skb = alloc_canfd_skb(priv->dev, &cf);
 		if (!skb) {
 			priv->dev->stats.rx_dropped++;
-			return -ENOMEM;
+			return 0;
 		}
 
 		cf->len = can_fd_dlc2len(dlc);
@@ -1212,7 +1220,7 @@ static int kvaser_pciefd_handle_data_packet(struct kvaser_pciefd *pcie,
 		skb = alloc_can_skb(priv->dev, (struct can_frame **)&cf);
 		if (!skb) {
 			priv->dev->stats.rx_dropped++;
-			return -ENOMEM;
+			return 0;
 		}
 		can_frame_set_cc_len((struct can_frame *)cf, dlc, priv->ctrlmode);
 	}
@@ -1230,7 +1238,9 @@ static int kvaser_pciefd_handle_data_packet(struct kvaser_pciefd *pcie,
 	priv->dev->stats.rx_packets++;
 	kvaser_pciefd_set_skb_timestamp(pcie, skb, p->timestamp);
 
-	return netif_rx(skb);
+	netif_rx(skb);
+
+	return 0;
 }
 
 static void kvaser_pciefd_change_state(struct kvaser_pciefd_can *can,
@@ -1507,19 +1517,21 @@ static int kvaser_pciefd_handle_ack_packet(struct kvaser_pciefd *pcie,
 		netdev_dbg(can->can.dev, "Packet was flushed\n");
 	} else {
 		int echo_idx = FIELD_GET(KVASER_PCIEFD_PACKET_SEQ_MASK, p->header[0]);
-		int len;
-		u8 count;
+		unsigned int len, frame_len = 0;
 		struct sk_buff *skb;
 
+		if (echo_idx != (can->ack_idx & (can->can.echo_skb_max - 1)))
+			return 0;
 		skb = can->can.echo_skb[echo_idx];
-		if (skb)
-			kvaser_pciefd_set_skb_timestamp(pcie, skb, p->timestamp);
-		len = can_get_echo_skb(can->can.dev, echo_idx, NULL);
-		count = FIELD_GET(KVASER_PCIEFD_KCAN_TX_NR_PACKETS_CURRENT_MASK,
-				  ioread32(can->reg_base + KVASER_PCIEFD_KCAN_TX_NR_PACKETS_REG));
+		if (!skb)
+			return 0;
+		kvaser_pciefd_set_skb_timestamp(pcie, skb, p->timestamp);
+		len = can_get_echo_skb(can->can.dev, echo_idx, &frame_len);
 
-		if (count < can->can.echo_skb_max && netif_queue_stopped(can->can.dev))
-			netif_wake_queue(can->can.dev);
+		/* Pairs with barrier in kvaser_pciefd_start_xmit() */
+		smp_store_release(&can->ack_idx, can->ack_idx + 1);
+		can->completed_tx_pkts++;
+		can->completed_tx_bytes += frame_len;
 
 		if (!one_shot_fail) {
 			can->can.dev->stats.tx_bytes += len;
@@ -1635,32 +1647,51 @@ static int kvaser_pciefd_read_buffer(struct kvaser_pciefd *pcie, int dma_buf)
 {
 	int pos = 0;
 	int res = 0;
+	unsigned int i;
 
 	do {
 		res = kvaser_pciefd_read_packet(pcie, &pos, dma_buf);
 	} while (!res && pos > 0 && pos < KVASER_PCIEFD_DMA_SIZE);
 
+	/* Report ACKs in this buffer to BQL en masse for correct periods */
+	for (i = 0; i < pcie->nr_channels; ++i) {
+		struct kvaser_pciefd_can *can = pcie->can[i];
+
+		if (!can->completed_tx_pkts)
+			continue;
+		netif_subqueue_completed_wake(can->can.dev, 0,
+					      can->completed_tx_pkts,
+					      can->completed_tx_bytes,
+					      kvaser_pciefd_tx_avail(can), 1);
+		can->completed_tx_pkts = 0;
+		can->completed_tx_bytes = 0;
+	}
+
 	return res;
 }
 
-static u32 kvaser_pciefd_receive_irq(struct kvaser_pciefd *pcie)
+static void kvaser_pciefd_receive_irq(struct kvaser_pciefd *pcie)
 {
+	void __iomem *srb_cmd_reg = KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_CMD_REG;
 	u32 irq = ioread32(KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_IRQ_REG);
 
-	if (irq & KVASER_PCIEFD_SRB_IRQ_DPD0)
+	iowrite32(irq, KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_IRQ_REG);
+
+	if (irq & KVASER_PCIEFD_SRB_IRQ_DPD0) {
 		kvaser_pciefd_read_buffer(pcie, 0);
+		iowrite32(KVASER_PCIEFD_SRB_CMD_RDB0, srb_cmd_reg); /* Rearm buffer */
+	}
 
-	if (irq & KVASER_PCIEFD_SRB_IRQ_DPD1)
+	if (irq & KVASER_PCIEFD_SRB_IRQ_DPD1) {
 		kvaser_pciefd_read_buffer(pcie, 1);
+		iowrite32(KVASER_PCIEFD_SRB_CMD_RDB1, srb_cmd_reg); /* Rearm buffer */
+	}
 
 	if (unlikely(irq & KVASER_PCIEFD_SRB_IRQ_DOF0 ||
 		     irq & KVASER_PCIEFD_SRB_IRQ_DOF1 ||
 		     irq & KVASER_PCIEFD_SRB_IRQ_DUF0 ||
 		     irq & KVASER_PCIEFD_SRB_IRQ_DUF1))
 		dev_err(&pcie->pci->dev, "DMA IRQ error 0x%08X\n", irq);
-
-	iowrite32(irq, KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_IRQ_REG);
-	return irq;
 }
 
 static void kvaser_pciefd_transmit_irq(struct kvaser_pciefd_can *can)
@@ -1688,29 +1719,22 @@ static irqreturn_t kvaser_pciefd_irq_handler(int irq, void *dev)
 	struct kvaser_pciefd *pcie = (struct kvaser_pciefd *)dev;
 	const struct kvaser_pciefd_irq_mask *irq_mask = pcie->driver_data->irq_mask;
 	u32 pci_irq = ioread32(KVASER_PCIEFD_PCI_IRQ_ADDR(pcie));
-	u32 srb_irq = 0;
-	u32 srb_release = 0;
 	int i;
 
 	if (!(pci_irq & irq_mask->all))
 		return IRQ_NONE;
 
+	iowrite32(0, KVASER_PCIEFD_PCI_IEN_ADDR(pcie));
+
 	if (pci_irq & irq_mask->kcan_rx0)
-		srb_irq = kvaser_pciefd_receive_irq(pcie);
+		kvaser_pciefd_receive_irq(pcie);
 
 	for (i = 0; i < pcie->nr_channels; i++) {
 		if (pci_irq & irq_mask->kcan_tx[i])
 			kvaser_pciefd_transmit_irq(pcie->can[i]);
 	}
 
-	if (srb_irq & KVASER_PCIEFD_SRB_IRQ_DPD0)
-		srb_release |= KVASER_PCIEFD_SRB_CMD_RDB0;
-
-	if (srb_irq & KVASER_PCIEFD_SRB_IRQ_DPD1)
-		srb_release |= KVASER_PCIEFD_SRB_CMD_RDB1;
-
-	if (srb_release)
-		iowrite32(srb_release, KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_CMD_REG);
+	iowrite32(irq_mask->all, KVASER_PCIEFD_PCI_IEN_ADDR(pcie));
 
 	return IRQ_HANDLED;
 }
@@ -1730,13 +1754,22 @@ static void kvaser_pciefd_teardown_can_ctrls(struct kvaser_pciefd *pcie)
 	}
 }
 
+static void kvaser_pciefd_disable_irq_srcs(struct kvaser_pciefd *pcie)
+{
+	unsigned int i;
+
+	/* Masking PCI_IRQ is insufficient as running ISR will unmask it */
+	iowrite32(0, KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_IEN_REG);
+	for (i = 0; i < pcie->nr_channels; ++i)
+		iowrite32(0, pcie->can[i]->reg_base + KVASER_PCIEFD_KCAN_IEN_REG);
+}
+
 static int kvaser_pciefd_probe(struct pci_dev *pdev,
 			       const struct pci_device_id *id)
 {
 	int ret;
 	struct kvaser_pciefd *pcie;
 	const struct kvaser_pciefd_irq_mask *irq_mask;
-	void __iomem *irq_en_base;
 
 	pcie = devm_kzalloc(&pdev->dev, sizeof(*pcie), GFP_KERNEL);
 	if (!pcie)
@@ -1802,8 +1835,7 @@ static int kvaser_pciefd_probe(struct pci_dev *pdev,
 		  KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_IEN_REG);
 
 	/* Enable PCI interrupts */
-	irq_en_base = KVASER_PCIEFD_PCI_IEN_ADDR(pcie);
-	iowrite32(irq_mask->all, irq_en_base);
+	iowrite32(irq_mask->all, KVASER_PCIEFD_PCI_IEN_ADDR(pcie));
 	/* Ready the DMA buffers */
 	iowrite32(KVASER_PCIEFD_SRB_CMD_RDB0,
 		  KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_CMD_REG);
@@ -1817,8 +1849,7 @@ static int kvaser_pciefd_probe(struct pci_dev *pdev,
 	return 0;
 
 err_free_irq:
-	/* Disable PCI interrupts */
-	iowrite32(0, irq_en_base);
+	kvaser_pciefd_disable_irq_srcs(pcie);
 	free_irq(pcie->pci->irq, pcie);
 
 err_pci_free_irq_vectors:
@@ -1841,35 +1872,26 @@ err_disable_pci:
 	return ret;
 }
 
-static void kvaser_pciefd_remove_all_ctrls(struct kvaser_pciefd *pcie)
-{
-	int i;
-
-	for (i = 0; i < pcie->nr_channels; i++) {
-		struct kvaser_pciefd_can *can = pcie->can[i];
-
-		if (can) {
-			iowrite32(0, can->reg_base + KVASER_PCIEFD_KCAN_IEN_REG);
-			unregister_candev(can->can.dev);
-			del_timer(&can->bec_poll_timer);
-			kvaser_pciefd_pwm_stop(can);
-			free_candev(can->can.dev);
-		}
-	}
-}
-
 static void kvaser_pciefd_remove(struct pci_dev *pdev)
 {
 	struct kvaser_pciefd *pcie = pci_get_drvdata(pdev);
+	unsigned int i;
 
-	kvaser_pciefd_remove_all_ctrls(pcie);
+	for (i = 0; i < pcie->nr_channels; ++i) {
+		struct kvaser_pciefd_can *can = pcie->can[i];
 
-	/* Disable interrupts */
-	iowrite32(0, KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_CTRL_REG);
-	iowrite32(0, KVASER_PCIEFD_PCI_IEN_ADDR(pcie));
+		unregister_candev(can->can.dev);
+		del_timer(&can->bec_poll_timer);
+		kvaser_pciefd_pwm_stop(can);
+	}
 
+	kvaser_pciefd_disable_irq_srcs(pcie);
 	free_irq(pcie->pci->irq, pcie);
 	pci_free_irq_vectors(pcie->pci);
+
+	for (i = 0; i < pcie->nr_channels; ++i)
+		free_candev(pcie->can[i]->can.dev);
+
 	pci_iounmap(pdev, pcie->reg_base);
 	pci_release_regions(pdev);
 	pci_disable_device(pdev);
diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c
index 97cd8bbf2e32..dbcf17fb3ef2 100644
--- a/drivers/net/can/m_can/m_can.c
+++ b/drivers/net/can/m_can/m_can.c
@@ -665,7 +665,7 @@ static int m_can_handle_lost_msg(struct net_device *dev)
 	struct can_frame *frame;
 	u32 timestamp = 0;
 
-	netdev_err(dev, "msg lost in rxf0\n");
+	netdev_dbg(dev, "msg lost in rxf0\n");
 
 	stats->rx_errors++;
 	stats->rx_over_errors++;
@@ -2372,6 +2372,7 @@ struct m_can_classdev *m_can_class_allocate_dev(struct device *dev,
 	SET_NETDEV_DEV(net_dev, dev);
 
 	m_can_of_parse_mram(class_dev, mram_config_vals);
+	spin_lock_init(&class_dev->tx_handling_spinlock);
 out:
 	return class_dev;
 }
@@ -2456,9 +2457,9 @@ EXPORT_SYMBOL_GPL(m_can_class_register);
 
 void m_can_class_unregister(struct m_can_classdev *cdev)
 {
+	unregister_candev(cdev->net);
 	if (cdev->is_peripheral)
 		can_rx_offload_del(&cdev->offload);
-	unregister_candev(cdev->net);
 }
 EXPORT_SYMBOL_GPL(m_can_class_unregister);
 
diff --git a/drivers/net/can/m_can/tcan4x5x-core.c b/drivers/net/can/m_can/tcan4x5x-core.c
index 2f73bf3abad8..e8995738cf99 100644
--- a/drivers/net/can/m_can/tcan4x5x-core.c
+++ b/drivers/net/can/m_can/tcan4x5x-core.c
@@ -92,6 +92,8 @@
 #define TCAN4X5X_MODE_STANDBY BIT(6)
 #define TCAN4X5X_MODE_NORMAL BIT(7)
 
+#define TCAN4X5X_NWKRQ_VOLTAGE_VIO BIT(19)
+
 #define TCAN4X5X_DISABLE_WAKE_MSK	(BIT(31) | BIT(30))
 #define TCAN4X5X_DISABLE_INH_MSK	BIT(9)
 
@@ -267,6 +269,13 @@ static int tcan4x5x_init(struct m_can_classdev *cdev)
 	if (ret)
 		return ret;
 
+	if (tcan4x5x->nwkrq_voltage_vio) {
+		ret = regmap_set_bits(tcan4x5x->regmap, TCAN4X5X_CONFIG,
+				      TCAN4X5X_NWKRQ_VOLTAGE_VIO);
+		if (ret)
+			return ret;
+	}
+
 	return ret;
 }
 
@@ -318,21 +327,27 @@ static const struct tcan4x5x_version_info
 	return &tcan4x5x_versions[TCAN4X5X];
 }
 
-static int tcan4x5x_get_gpios(struct m_can_classdev *cdev,
-			      const struct tcan4x5x_version_info *version_info)
+static void tcan4x5x_get_dt_data(struct m_can_classdev *cdev)
+{
+	struct tcan4x5x_priv *tcan4x5x = cdev_to_priv(cdev);
+
+	tcan4x5x->nwkrq_voltage_vio =
+		of_property_read_bool(cdev->dev->of_node, "ti,nwkrq-voltage-vio");
+}
+
+static int tcan4x5x_get_gpios(struct m_can_classdev *cdev)
 {
 	struct tcan4x5x_priv *tcan4x5x = cdev_to_priv(cdev);
 	int ret;
 
-	if (version_info->has_wake_pin) {
-		tcan4x5x->device_wake_gpio = devm_gpiod_get(cdev->dev, "device-wake",
-							    GPIOD_OUT_HIGH);
-		if (IS_ERR(tcan4x5x->device_wake_gpio)) {
-			if (PTR_ERR(tcan4x5x->device_wake_gpio) == -EPROBE_DEFER)
-				return -EPROBE_DEFER;
+	tcan4x5x->device_wake_gpio = devm_gpiod_get_optional(cdev->dev,
+							     "device-wake",
+							     GPIOD_OUT_HIGH);
+	if (IS_ERR(tcan4x5x->device_wake_gpio)) {
+		if (PTR_ERR(tcan4x5x->device_wake_gpio) == -EPROBE_DEFER)
+			return -EPROBE_DEFER;
 
-			tcan4x5x_disable_wake(cdev);
-		}
+		tcan4x5x->device_wake_gpio = NULL;
 	}
 
 	tcan4x5x->reset_gpio = devm_gpiod_get_optional(cdev->dev, "reset",
@@ -344,14 +359,31 @@ static int tcan4x5x_get_gpios(struct m_can_classdev *cdev,
 	if (ret)
 		return ret;
 
-	if (version_info->has_state_pin) {
-		tcan4x5x->device_state_gpio = devm_gpiod_get_optional(cdev->dev,
-								      "device-state",
-								      GPIOD_IN);
-		if (IS_ERR(tcan4x5x->device_state_gpio)) {
-			tcan4x5x->device_state_gpio = NULL;
-			tcan4x5x_disable_state(cdev);
-		}
+	tcan4x5x->device_state_gpio = devm_gpiod_get_optional(cdev->dev,
+							      "device-state",
+							      GPIOD_IN);
+	if (IS_ERR(tcan4x5x->device_state_gpio))
+		tcan4x5x->device_state_gpio = NULL;
+
+	return 0;
+}
+
+static int tcan4x5x_check_gpios(struct m_can_classdev *cdev,
+				const struct tcan4x5x_version_info *version_info)
+{
+	struct tcan4x5x_priv *tcan4x5x = cdev_to_priv(cdev);
+	int ret;
+
+	if (version_info->has_wake_pin && !tcan4x5x->device_wake_gpio) {
+		ret = tcan4x5x_disable_wake(cdev);
+		if (ret)
+			return ret;
+	}
+
+	if (version_info->has_state_pin && !tcan4x5x->device_state_gpio) {
+		ret = tcan4x5x_disable_state(cdev);
+		if (ret)
+			return ret;
 	}
 
 	return 0;
@@ -385,10 +417,11 @@ static int tcan4x5x_can_probe(struct spi_device *spi)
 	priv = cdev_to_priv(mcan_class);
 
 	priv->power = devm_regulator_get_optional(&spi->dev, "vsup");
-	if (PTR_ERR(priv->power) == -EPROBE_DEFER) {
-		ret = -EPROBE_DEFER;
-		goto out_m_can_class_free_dev;
-	} else {
+	if (IS_ERR(priv->power)) {
+		if (PTR_ERR(priv->power) == -EPROBE_DEFER) {
+			ret = -EPROBE_DEFER;
+			goto out_m_can_class_free_dev;
+		}
 		priv->power = NULL;
 	}
 
@@ -441,18 +474,26 @@ static int tcan4x5x_can_probe(struct spi_device *spi)
 		goto out_m_can_class_free_dev;
 	}
 
+	ret = tcan4x5x_get_gpios(mcan_class);
+	if (ret) {
+		dev_err(&spi->dev, "Getting gpios failed %pe\n", ERR_PTR(ret));
+		goto out_power;
+	}
+
 	version_info = tcan4x5x_find_version(priv);
 	if (IS_ERR(version_info)) {
 		ret = PTR_ERR(version_info);
 		goto out_power;
 	}
 
-	ret = tcan4x5x_get_gpios(mcan_class, version_info);
+	ret = tcan4x5x_check_gpios(mcan_class, version_info);
 	if (ret) {
-		dev_err(&spi->dev, "Getting gpios failed %pe\n", ERR_PTR(ret));
+		dev_err(&spi->dev, "Checking gpios failed %pe\n", ERR_PTR(ret));
 		goto out_power;
 	}
 
+	tcan4x5x_get_dt_data(mcan_class);
+
 	tcan4x5x_check_wake(priv);
 
 	ret = tcan4x5x_write_tcan_reg(mcan_class, TCAN4X5X_INT_EN, 0);
diff --git a/drivers/net/can/m_can/tcan4x5x.h b/drivers/net/can/m_can/tcan4x5x.h
index e62c030d3e1e..203399d5e8cc 100644
--- a/drivers/net/can/m_can/tcan4x5x.h
+++ b/drivers/net/can/m_can/tcan4x5x.h
@@ -42,6 +42,8 @@ struct tcan4x5x_priv {
 
 	struct tcan4x5x_map_buf map_buf_rx;
 	struct tcan4x5x_map_buf map_buf_tx;
+
+	bool nwkrq_voltage_vio;
 };
 
 static inline void
diff --git a/drivers/net/can/rcar/rcar_canfd.c b/drivers/net/can/rcar/rcar_canfd.c
index df1a5d0b37b2..aa3df0d05b85 100644
--- a/drivers/net/can/rcar/rcar_canfd.c
+++ b/drivers/net/can/rcar/rcar_canfd.c
@@ -787,22 +787,14 @@ static void rcar_canfd_configure_controller(struct rcar_canfd_global *gpriv)
 }
 
 static void rcar_canfd_configure_afl_rules(struct rcar_canfd_global *gpriv,
-					   u32 ch)
+					   u32 ch, u32 rule_entry)
 {
-	u32 cfg;
-	int offset, start, page, num_rules = RCANFD_CHANNEL_NUMRULES;
+	int offset, page, num_rules = RCANFD_CHANNEL_NUMRULES;
+	u32 rule_entry_index = rule_entry % 16;
 	u32 ridx = ch + RCANFD_RFFIFO_IDX;
 
-	if (ch == 0) {
-		start = 0; /* Channel 0 always starts from 0th rule */
-	} else {
-		/* Get number of Channel 0 rules and adjust */
-		cfg = rcar_canfd_read(gpriv->base, RCANFD_GAFLCFG(ch));
-		start = RCANFD_GAFLCFG_GETRNC(gpriv, 0, cfg);
-	}
-
 	/* Enable write access to entry */
-	page = RCANFD_GAFL_PAGENUM(start);
+	page = RCANFD_GAFL_PAGENUM(rule_entry);
 	rcar_canfd_set_bit(gpriv->base, RCANFD_GAFLECTR,
 			   (RCANFD_GAFLECTR_AFLPN(gpriv, page) |
 			    RCANFD_GAFLECTR_AFLDAE));
@@ -818,13 +810,13 @@ static void rcar_canfd_configure_afl_rules(struct rcar_canfd_global *gpriv,
 		offset = RCANFD_C_GAFL_OFFSET;
 
 	/* Accept all IDs */
-	rcar_canfd_write(gpriv->base, RCANFD_GAFLID(offset, start), 0);
+	rcar_canfd_write(gpriv->base, RCANFD_GAFLID(offset, rule_entry_index), 0);
 	/* IDE or RTR is not considered for matching */
-	rcar_canfd_write(gpriv->base, RCANFD_GAFLM(offset, start), 0);
+	rcar_canfd_write(gpriv->base, RCANFD_GAFLM(offset, rule_entry_index), 0);
 	/* Any data length accepted */
-	rcar_canfd_write(gpriv->base, RCANFD_GAFLP0(offset, start), 0);
+	rcar_canfd_write(gpriv->base, RCANFD_GAFLP0(offset, rule_entry_index), 0);
 	/* Place the msg in corresponding Rx FIFO entry */
-	rcar_canfd_set_bit(gpriv->base, RCANFD_GAFLP1(offset, start),
+	rcar_canfd_set_bit(gpriv->base, RCANFD_GAFLP1(offset, rule_entry_index),
 			   RCANFD_GAFLP1_GAFLFDP(ridx));
 
 	/* Disable write access to page */
@@ -1851,6 +1843,7 @@ static int rcar_canfd_probe(struct platform_device *pdev)
 	unsigned long channels_mask = 0;
 	int err, ch_irq, g_irq;
 	int g_err_irq, g_recc_irq;
+	u32 rule_entry = 0;
 	bool fdmode = true;			/* CAN FD only mode - default */
 	char name[9] = "channelX";
 	int i;
@@ -2023,7 +2016,8 @@ static int rcar_canfd_probe(struct platform_device *pdev)
 		rcar_canfd_configure_tx(gpriv, ch);
 
 		/* Configure receive rules */
-		rcar_canfd_configure_afl_rules(gpriv, ch);
+		rcar_canfd_configure_afl_rules(gpriv, ch, rule_entry);
+		rule_entry += RCANFD_CHANNEL_NUMRULES;
 	}
 
 	/* Configure common interrupts */
diff --git a/drivers/net/can/rockchip/rockchip_canfd-core.c b/drivers/net/can/rockchip/rockchip_canfd-core.c
index df18c85fc078..07510b6f9073 100644
--- a/drivers/net/can/rockchip/rockchip_canfd-core.c
+++ b/drivers/net/can/rockchip/rockchip_canfd-core.c
@@ -622,7 +622,7 @@ rkcanfd_handle_rx_fifo_overflow_int(struct rkcanfd_priv *priv)
 	netdev_dbg(priv->ndev, "RX-FIFO overflow\n");
 
 	skb = rkcanfd_alloc_can_err_skb(priv, &cf, &timestamp);
-	if (skb)
+	if (!skb)
 		return 0;
 
 	rkcanfd_get_berr_counter_corrected(priv, &bec);
@@ -907,15 +907,16 @@ static int rkcanfd_probe(struct platform_device *pdev)
 	priv->can.data_bittiming_const = &rkcanfd_data_bittiming_const;
 	priv->can.ctrlmode_supported = CAN_CTRLMODE_LOOPBACK |
 		CAN_CTRLMODE_BERR_REPORTING;
-	if (!(priv->devtype_data.quirks & RKCANFD_QUIRK_CANFD_BROKEN))
-		priv->can.ctrlmode_supported |= CAN_CTRLMODE_FD;
 	priv->can.do_set_mode = rkcanfd_set_mode;
 	priv->can.do_get_berr_counter = rkcanfd_get_berr_counter;
 	priv->ndev = ndev;
 
 	match = device_get_match_data(&pdev->dev);
-	if (match)
+	if (match) {
 		priv->devtype_data = *(struct rkcanfd_devtype_data *)match;
+		if (!(priv->devtype_data.quirks & RKCANFD_QUIRK_CANFD_BROKEN))
+			priv->can.ctrlmode_supported |= CAN_CTRLMODE_FD;
+	}
 
 	err = can_rx_offload_add_manual(ndev, &priv->offload,
 					RKCANFD_NAPI_WEIGHT);
@@ -941,8 +942,8 @@ static void rkcanfd_remove(struct platform_device *pdev)
 	struct rkcanfd_priv *priv = platform_get_drvdata(pdev);
 	struct net_device *ndev = priv->ndev;
 
-	can_rx_offload_del(&priv->offload);
 	rkcanfd_unregister(priv);
+	can_rx_offload_del(&priv->offload);
 	free_candev(ndev);
 }
 
diff --git a/drivers/net/can/slcan/slcan-core.c b/drivers/net/can/slcan/slcan-core.c
index 24c6622d36bd..58ff2ec1d975 100644
--- a/drivers/net/can/slcan/slcan-core.c
+++ b/drivers/net/can/slcan/slcan-core.c
@@ -71,12 +71,21 @@ MODULE_AUTHOR("Dario Binacchi <dario.binacchi@amarulasolutions.com>");
 #define SLCAN_CMD_LEN 1
 #define SLCAN_SFF_ID_LEN 3
 #define SLCAN_EFF_ID_LEN 8
+#define SLCAN_DATA_LENGTH_LEN 1
+#define SLCAN_ERROR_LEN 1
 #define SLCAN_STATE_LEN 1
 #define SLCAN_STATE_BE_RXCNT_LEN 3
 #define SLCAN_STATE_BE_TXCNT_LEN 3
-#define SLCAN_STATE_FRAME_LEN       (1 + SLCAN_CMD_LEN + \
-				     SLCAN_STATE_BE_RXCNT_LEN + \
-				     SLCAN_STATE_BE_TXCNT_LEN)
+#define SLCAN_STATE_MSG_LEN     (SLCAN_CMD_LEN +		\
+                                 SLCAN_STATE_LEN +		\
+                                 SLCAN_STATE_BE_RXCNT_LEN +	\
+                                 SLCAN_STATE_BE_TXCNT_LEN)
+#define SLCAN_ERROR_MSG_LEN_MIN (SLCAN_CMD_LEN +	\
+                                 SLCAN_ERROR_LEN +	\
+                                 SLCAN_DATA_LENGTH_LEN)
+#define SLCAN_FRAME_MSG_LEN_MIN (SLCAN_CMD_LEN +	\
+                                 SLCAN_SFF_ID_LEN +	\
+                                 SLCAN_DATA_LENGTH_LEN)
 struct slcan {
 	struct can_priv         can;
 
@@ -176,6 +185,9 @@ static void slcan_bump_frame(struct slcan *sl)
 	u32 tmpid;
 	char *cmd = sl->rbuff;
 
+	if (sl->rcount < SLCAN_FRAME_MSG_LEN_MIN)
+		return;
+
 	skb = alloc_can_skb(sl->dev, &cf);
 	if (unlikely(!skb)) {
 		sl->dev->stats.rx_dropped++;
@@ -281,7 +293,7 @@ static void slcan_bump_state(struct slcan *sl)
 		return;
 	}
 
-	if (state == sl->can.state || sl->rcount < SLCAN_STATE_FRAME_LEN)
+	if (state == sl->can.state || sl->rcount != SLCAN_STATE_MSG_LEN)
 		return;
 
 	cmd += SLCAN_STATE_BE_RXCNT_LEN + SLCAN_CMD_LEN + 1;
@@ -328,6 +340,9 @@ static void slcan_bump_err(struct slcan *sl)
 	bool rx_errors = false, tx_errors = false, rx_over_errors = false;
 	int i, len;
 
+	if (sl->rcount < SLCAN_ERROR_MSG_LEN_MIN)
+		return;
+
 	/* get len from sanitized ASCII value */
 	len = cmd[1];
 	if (len >= '0' && len < '9')
@@ -456,8 +471,7 @@ static void slcan_bump(struct slcan *sl)
 static void slcan_unesc(struct slcan *sl, unsigned char s)
 {
 	if ((s == '\r') || (s == '\a')) { /* CR or BEL ends the pdu */
-		if (!test_and_clear_bit(SLF_ERROR, &sl->flags) &&
-		    sl->rcount > 4)
+		if (!test_and_clear_bit(SLF_ERROR, &sl->flags))
 			slcan_bump(sl);
 
 		sl->rcount = 0;
diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
index 3bc56517fe7a..c30b04f8fc0d 100644
--- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
+++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
@@ -75,6 +75,24 @@ static const struct can_bittiming_const mcp251xfd_data_bittiming_const = {
 	.brp_inc = 1,
 };
 
+/* The datasheet of the mcp2518fd (DS20006027B) specifies a range of
+ * [-64,63] for TDCO, indicating a relative TDCO.
+ *
+ * Manual tests have shown, that using a relative TDCO configuration
+ * results in bus off, while an absolute configuration works.
+ *
+ * For TDCO use the max value (63) from the data sheet, but 0 as the
+ * minimum.
+ */
+static const struct can_tdc_const mcp251xfd_tdc_const = {
+	.tdcv_min = 0,
+	.tdcv_max = 63,
+	.tdco_min = 0,
+	.tdco_max = 63,
+	.tdcf_min = 0,
+	.tdcf_max = 0,
+};
+
 static const char *__mcp251xfd_get_model_str(enum mcp251xfd_model model)
 {
 	switch (model) {
@@ -510,8 +528,7 @@ static int mcp251xfd_set_bittiming(const struct mcp251xfd_priv *priv)
 {
 	const struct can_bittiming *bt = &priv->can.bittiming;
 	const struct can_bittiming *dbt = &priv->can.data_bittiming;
-	u32 val = 0;
-	s8 tdco;
+	u32 tdcmod, val = 0;
 	int err;
 
 	/* CAN Control Register
@@ -575,11 +592,16 @@ static int mcp251xfd_set_bittiming(const struct mcp251xfd_priv *priv)
 		return err;
 
 	/* Transmitter Delay Compensation */
-	tdco = clamp_t(int, dbt->brp * (dbt->prop_seg + dbt->phase_seg1),
-		       -64, 63);
-	val = FIELD_PREP(MCP251XFD_REG_TDC_TDCMOD_MASK,
-			 MCP251XFD_REG_TDC_TDCMOD_AUTO) |
-		FIELD_PREP(MCP251XFD_REG_TDC_TDCO_MASK, tdco);
+	if (priv->can.ctrlmode & CAN_CTRLMODE_TDC_AUTO)
+		tdcmod = MCP251XFD_REG_TDC_TDCMOD_AUTO;
+	else if (priv->can.ctrlmode & CAN_CTRLMODE_TDC_MANUAL)
+		tdcmod = MCP251XFD_REG_TDC_TDCMOD_MANUAL;
+	else
+		tdcmod = MCP251XFD_REG_TDC_TDCMOD_DISABLED;
+
+	val = FIELD_PREP(MCP251XFD_REG_TDC_TDCMOD_MASK, tdcmod) |
+		FIELD_PREP(MCP251XFD_REG_TDC_TDCV_MASK, priv->can.tdc.tdcv) |
+		FIELD_PREP(MCP251XFD_REG_TDC_TDCO_MASK, priv->can.tdc.tdco);
 
 	return regmap_write(priv->map_reg, MCP251XFD_REG_TDC, val);
 }
@@ -2083,10 +2105,12 @@ static int mcp251xfd_probe(struct spi_device *spi)
 	priv->can.do_get_berr_counter = mcp251xfd_get_berr_counter;
 	priv->can.bittiming_const = &mcp251xfd_bittiming_const;
 	priv->can.data_bittiming_const = &mcp251xfd_data_bittiming_const;
+	priv->can.tdc_const = &mcp251xfd_tdc_const;
 	priv->can.ctrlmode_supported = CAN_CTRLMODE_LOOPBACK |
 		CAN_CTRLMODE_LISTENONLY | CAN_CTRLMODE_BERR_REPORTING |
 		CAN_CTRLMODE_FD | CAN_CTRLMODE_FD_NON_ISO |
-		CAN_CTRLMODE_CC_LEN8_DLC;
+		CAN_CTRLMODE_CC_LEN8_DLC | CAN_CTRLMODE_TDC_AUTO |
+		CAN_CTRLMODE_TDC_MANUAL;
 	set_bit(MCP251XFD_FLAGS_DOWN, priv->flags);
 	priv->ndev = ndev;
 	priv->spi = spi;
@@ -2174,8 +2198,8 @@ static void mcp251xfd_remove(struct spi_device *spi)
 	struct mcp251xfd_priv *priv = spi_get_drvdata(spi);
 	struct net_device *ndev = priv->ndev;
 
-	can_rx_offload_del(&priv->offload);
 	mcp251xfd_unregister(priv);
+	can_rx_offload_del(&priv->offload);
 	spi->max_speed_hz = priv->spi_max_speed_hz_orig;
 	free_candev(ndev);
 }
diff --git a/drivers/net/can/ti_hecc.c b/drivers/net/can/ti_hecc.c
index 644e8b8eb91e..e6d6661a908a 100644
--- a/drivers/net/can/ti_hecc.c
+++ b/drivers/net/can/ti_hecc.c
@@ -383,7 +383,7 @@ static void ti_hecc_start(struct net_device *ndev)
 	 * overflows instead of the hardware silently dropping the
 	 * messages.
 	 */
-	mbx_mask = ~BIT(HECC_RX_LAST_MBOX);
+	mbx_mask = ~BIT_U32(HECC_RX_LAST_MBOX);
 	hecc_write(priv, HECC_CANOPC, mbx_mask);
 
 	/* Enable interrupts */
diff --git a/drivers/net/can/usb/etas_es58x/es58x_devlink.c b/drivers/net/can/usb/etas_es58x/es58x_devlink.c
index eee20839d96f..0d155eb1b9e9 100644
--- a/drivers/net/can/usb/etas_es58x/es58x_devlink.c
+++ b/drivers/net/can/usb/etas_es58x/es58x_devlink.c
@@ -248,7 +248,11 @@ static int es58x_devlink_info_get(struct devlink *devlink,
 			return ret;
 	}
 
-	return devlink_info_serial_number_put(req, es58x_dev->udev->serial);
+	if (es58x_dev->udev->serial)
+		ret = devlink_info_serial_number_put(req,
+						     es58x_dev->udev->serial);
+
+	return ret;
 }
 
 const struct devlink_ops es58x_dl_ops = {
diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c
index 7d12776ab63e..8bd7e800af8f 100644
--- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c
@@ -851,6 +851,7 @@ static int kvaser_usb_init_one(struct kvaser_usb *dev, int channel)
 	netdev->ethtool_ops = &kvaser_usb_ethtool_ops;
 	SET_NETDEV_DEV(netdev, &dev->intf->dev);
 	netdev->dev_id = channel;
+	netdev->dev_port = channel;
 
 	dev->nets[channel] = priv;
 
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c
index 4d85b29a17b7..ebefc274b50a 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c
@@ -49,7 +49,7 @@ struct __packed pcan_ufd_fw_info {
 	__le32	ser_no;		/* S/N */
 	__le32	flags;		/* special functions */
 
-	/* extended data when type == PCAN_USBFD_TYPE_EXT */
+	/* extended data when type >= PCAN_USBFD_TYPE_EXT */
 	u8	cmd_out_ep;	/* ep for cmd */
 	u8	cmd_in_ep;	/* ep for replies */
 	u8	data_out_ep[2];	/* ep for CANx TX */
@@ -982,10 +982,11 @@ static int pcan_usb_fd_init(struct peak_usb_device *dev)
 			dev->can.ctrlmode |= CAN_CTRLMODE_FD_NON_ISO;
 		}
 
-		/* if vendor rsp is of type 2, then it contains EP numbers to
-		 * use for cmds pipes. If not, then default EP should be used.
+		/* if vendor rsp type is greater than or equal to 2, then it
+		 * contains EP numbers to use for cmds pipes. If not, then
+		 * default EP should be used.
 		 */
-		if (fw_info->type != cpu_to_le16(PCAN_USBFD_TYPE_EXT)) {
+		if (le16_to_cpu(fw_info->type) < PCAN_USBFD_TYPE_EXT) {
 			fw_info->cmd_out_ep = PCAN_USBPRO_EP_CMDOUT;
 			fw_info->cmd_in_ep = PCAN_USBPRO_EP_CMDIN;
 		}
@@ -1018,11 +1019,11 @@ static int pcan_usb_fd_init(struct peak_usb_device *dev)
 	dev->can_channel_id =
 		le32_to_cpu(pdev->usb_if->fw_info.dev_id[dev->ctrl_idx]);
 
-	/* if vendor rsp is of type 2, then it contains EP numbers to
-	 * use for data pipes. If not, then statically defined EP are used
-	 * (see peak_usb_create_dev()).
+	/* if vendor rsp type is greater than or equal to 2, then it contains EP
+	 * numbers to use for data pipes. If not, then statically defined EP are
+	 * used (see peak_usb_create_dev()).
 	 */
-	if (fw_info->type == cpu_to_le16(PCAN_USBFD_TYPE_EXT)) {
+	if (le16_to_cpu(fw_info->type) >= PCAN_USBFD_TYPE_EXT) {
 		dev->ep_msg_in = fw_info->data_in_ep;
 		dev->ep_msg_out = fw_info->data_out_ep[dev->ctrl_idx];
 	}
diff --git a/drivers/net/can/usb/ucan.c b/drivers/net/can/usb/ucan.c
index 39a63b7313a4..07406daf7c88 100644
--- a/drivers/net/can/usb/ucan.c
+++ b/drivers/net/can/usb/ucan.c
@@ -186,7 +186,7 @@ union ucan_ctl_payload {
 	 */
 	struct ucan_ctl_cmd_get_protocol_version cmd_get_protocol_version;
 
-	u8 raw[128];
+	u8 fw_str[128];
 } __packed;
 
 enum {
@@ -424,18 +424,20 @@ static int ucan_ctrl_command_out(struct ucan_priv *up,
 			       UCAN_USB_CTL_PIPE_TIMEOUT);
 }
 
-static int ucan_device_request_in(struct ucan_priv *up,
-				  u8 cmd, u16 subcmd, u16 datalen)
+static void ucan_get_fw_str(struct ucan_priv *up, char *fw_str, size_t size)
 {
-	return usb_control_msg(up->udev,
-			       usb_rcvctrlpipe(up->udev, 0),
-			       cmd,
-			       USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE,
-			       subcmd,
-			       0,
-			       up->ctl_msg_buffer,
-			       datalen,
-			       UCAN_USB_CTL_PIPE_TIMEOUT);
+	int ret;
+
+	ret = usb_control_msg(up->udev, usb_rcvctrlpipe(up->udev, 0),
+			      UCAN_DEVICE_GET_FW_STRING,
+			      USB_DIR_IN | USB_TYPE_VENDOR |
+			      USB_RECIP_DEVICE,
+			      0, 0, fw_str, size - 1,
+			      UCAN_USB_CTL_PIPE_TIMEOUT);
+	if (ret > 0)
+		fw_str[ret] = '\0';
+	else
+		strscpy(fw_str, "unknown", size);
 }
 
 /* Parse the device information structure reported by the device and
@@ -1314,7 +1316,6 @@ static int ucan_probe(struct usb_interface *intf,
 	u8 in_ep_addr;
 	u8 out_ep_addr;
 	union ucan_ctl_payload *ctl_msg_buffer;
-	char firmware_str[sizeof(union ucan_ctl_payload) + 1];
 
 	udev = interface_to_usbdev(intf);
 
@@ -1527,17 +1528,6 @@ static int ucan_probe(struct usb_interface *intf,
 	 */
 	ucan_parse_device_info(up, &ctl_msg_buffer->cmd_get_device_info);
 
-	/* just print some device information - if available */
-	ret = ucan_device_request_in(up, UCAN_DEVICE_GET_FW_STRING, 0,
-				     sizeof(union ucan_ctl_payload));
-	if (ret > 0) {
-		/* copy string while ensuring zero termination */
-		strscpy(firmware_str, up->ctl_msg_buffer->raw,
-			sizeof(union ucan_ctl_payload) + 1);
-	} else {
-		strcpy(firmware_str, "unknown");
-	}
-
 	/* device is compatible, reset it */
 	ret = ucan_ctrl_command_out(up, UCAN_COMMAND_RESET, 0, 0);
 	if (ret < 0)
@@ -1555,7 +1545,10 @@ static int ucan_probe(struct usb_interface *intf,
 
 	/* initialisation complete, log device info */
 	netdev_info(up->netdev, "registered device\n");
-	netdev_info(up->netdev, "firmware string: %s\n", firmware_str);
+	ucan_get_fw_str(up, up->ctl_msg_buffer->fw_str,
+			sizeof(up->ctl_msg_buffer->fw_str));
+	netdev_info(up->netdev, "firmware string: %s\n",
+		    up->ctl_msg_buffer->fw_str);
 
 	/* success */
 	return 0;
diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c
index c39cb119e760..844cf2b8f727 100644
--- a/drivers/net/dsa/b53/b53_common.c
+++ b/drivers/net/dsa/b53/b53_common.c
@@ -326,6 +326,26 @@ static void b53_get_vlan_entry(struct b53_device *dev, u16 vid,
 	}
 }
 
+static void b53_set_eap_mode(struct b53_device *dev, int port, int mode)
+{
+	u64 eap_conf;
+
+	if (is5325(dev) || is5365(dev) || dev->chip_id == BCM5389_DEVICE_ID)
+		return;
+
+	b53_read64(dev, B53_EAP_PAGE, B53_PORT_EAP_CONF(port), &eap_conf);
+
+	if (is63xx(dev)) {
+		eap_conf &= ~EAP_MODE_MASK_63XX;
+		eap_conf |= (u64)mode << EAP_MODE_SHIFT_63XX;
+	} else {
+		eap_conf &= ~EAP_MODE_MASK;
+		eap_conf |= (u64)mode << EAP_MODE_SHIFT;
+	}
+
+	b53_write64(dev, B53_EAP_PAGE, B53_PORT_EAP_CONF(port), eap_conf);
+}
+
 static void b53_set_forwarding(struct b53_device *dev, int enable)
 {
 	u8 mgmt;
@@ -339,18 +359,23 @@ static void b53_set_forwarding(struct b53_device *dev, int enable)
 
 	b53_write8(dev, B53_CTRL_PAGE, B53_SWITCH_MODE, mgmt);
 
-	/* Include IMP port in dumb forwarding mode
-	 */
-	b53_read8(dev, B53_CTRL_PAGE, B53_SWITCH_CTRL, &mgmt);
-	mgmt |= B53_MII_DUMB_FWDG_EN;
-	b53_write8(dev, B53_CTRL_PAGE, B53_SWITCH_CTRL, mgmt);
+	if (!is5325(dev)) {
+		/* Include IMP port in dumb forwarding mode */
+		b53_read8(dev, B53_CTRL_PAGE, B53_SWITCH_CTRL, &mgmt);
+		mgmt |= B53_MII_DUMB_FWDG_EN;
+		b53_write8(dev, B53_CTRL_PAGE, B53_SWITCH_CTRL, mgmt);
 
-	/* Look at B53_UC_FWD_EN and B53_MC_FWD_EN to decide whether
-	 * frames should be flooded or not.
-	 */
-	b53_read8(dev, B53_CTRL_PAGE, B53_IP_MULTICAST_CTRL, &mgmt);
-	mgmt |= B53_UC_FWD_EN | B53_MC_FWD_EN | B53_IPMC_FWD_EN;
-	b53_write8(dev, B53_CTRL_PAGE, B53_IP_MULTICAST_CTRL, mgmt);
+		/* Look at B53_UC_FWD_EN and B53_MC_FWD_EN to decide whether
+		 * frames should be flooded or not.
+		 */
+		b53_read8(dev, B53_CTRL_PAGE, B53_IP_MULTICAST_CTRL, &mgmt);
+		mgmt |= B53_UC_FWD_EN | B53_MC_FWD_EN | B53_IPMC_FWD_EN;
+		b53_write8(dev, B53_CTRL_PAGE, B53_IP_MULTICAST_CTRL, mgmt);
+	} else {
+		b53_read8(dev, B53_CTRL_PAGE, B53_IP_MULTICAST_CTRL, &mgmt);
+		mgmt |= B53_IP_MCAST_25;
+		b53_write8(dev, B53_CTRL_PAGE, B53_IP_MULTICAST_CTRL, mgmt);
+	}
 }
 
 static void b53_enable_vlan(struct b53_device *dev, int port, bool enable,
@@ -373,15 +398,17 @@ static void b53_enable_vlan(struct b53_device *dev, int port, bool enable,
 		b53_read8(dev, B53_VLAN_PAGE, B53_VLAN_CTRL5, &vc5);
 	}
 
+	vc1 &= ~VC1_RX_MCST_FWD_EN;
+
 	if (enable) {
 		vc0 |= VC0_VLAN_EN | VC0_VID_CHK_EN | VC0_VID_HASH_VID;
-		vc1 |= VC1_RX_MCST_UNTAG_EN | VC1_RX_MCST_FWD_EN;
+		vc1 |= VC1_RX_MCST_UNTAG_EN;
 		vc4 &= ~VC4_ING_VID_CHECK_MASK;
 		if (enable_filtering) {
 			vc4 |= VC4_ING_VID_VIO_DROP << VC4_ING_VID_CHECK_S;
 			vc5 |= VC5_DROP_VTABLE_MISS;
 		} else {
-			vc4 |= VC4_ING_VID_VIO_FWD << VC4_ING_VID_CHECK_S;
+			vc4 |= VC4_NO_ING_VID_CHK << VC4_ING_VID_CHECK_S;
 			vc5 &= ~VC5_DROP_VTABLE_MISS;
 		}
 
@@ -393,7 +420,7 @@ static void b53_enable_vlan(struct b53_device *dev, int port, bool enable,
 
 	} else {
 		vc0 &= ~(VC0_VLAN_EN | VC0_VID_CHK_EN | VC0_VID_HASH_VID);
-		vc1 &= ~(VC1_RX_MCST_UNTAG_EN | VC1_RX_MCST_FWD_EN);
+		vc1 &= ~VC1_RX_MCST_UNTAG_EN;
 		vc4 &= ~VC4_ING_VID_CHECK_MASK;
 		vc5 &= ~VC5_DROP_VTABLE_MISS;
 
@@ -505,6 +532,10 @@ void b53_imp_vlan_setup(struct dsa_switch *ds, int cpu_port)
 	unsigned int i;
 	u16 pvlan;
 
+	/* BCM5325 CPU port is at 8 */
+	if ((is5325(dev) || is5365(dev)) && cpu_port == B53_CPU_PORT_25)
+		cpu_port = B53_CPU_PORT;
+
 	/* Enable the IMP port to be in the same VLAN as the other ports
 	 * on a per-port basis such that we only have Port i and IMP in
 	 * the same VLAN.
@@ -555,6 +586,9 @@ static void b53_port_set_learning(struct b53_device *dev, int port,
 {
 	u16 reg;
 
+	if (is5325(dev))
+		return;
+
 	b53_read16(dev, B53_CTRL_PAGE, B53_DIS_LEARNING, &reg);
 	if (learning)
 		reg &= ~BIT(port);
@@ -576,6 +610,38 @@ static void b53_eee_enable_set(struct dsa_switch *ds, int port, bool enable)
 	b53_write16(dev, B53_EEE_PAGE, B53_EEE_EN_CTRL, reg);
 }
 
+int b53_setup_port(struct dsa_switch *ds, int port)
+{
+	struct b53_device *dev = ds->priv;
+
+	b53_port_set_ucast_flood(dev, port, true);
+	b53_port_set_mcast_flood(dev, port, true);
+	b53_port_set_learning(dev, port, false);
+
+	/* Force all traffic to go to the CPU port to prevent the ASIC from
+	 * trying to forward to bridged ports on matching FDB entries, then
+	 * dropping frames because it isn't allowed to forward there.
+	 */
+	if (dsa_is_user_port(ds, port))
+		b53_set_eap_mode(dev, port, EAP_MODE_SIMPLIFIED);
+
+	if (is5325(dev) &&
+	    in_range(port, 1, 4)) {
+		u8 reg;
+
+		b53_read8(dev, B53_CTRL_PAGE, B53_PD_MODE_CTRL_25, &reg);
+		reg &= ~PD_MODE_POWER_DOWN_PORT(0);
+		if (dsa_is_unused_port(ds, port))
+			reg |= PD_MODE_POWER_DOWN_PORT(port);
+		else
+			reg &= ~PD_MODE_POWER_DOWN_PORT(port);
+		b53_write8(dev, B53_CTRL_PAGE, B53_PD_MODE_CTRL_25, reg);
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(b53_setup_port);
+
 int b53_enable_port(struct dsa_switch *ds, int port, struct phy_device *phy)
 {
 	struct b53_device *dev = ds->priv;
@@ -588,10 +654,6 @@ int b53_enable_port(struct dsa_switch *ds, int port, struct phy_device *phy)
 
 	cpu_port = dsa_to_port(ds, port)->cpu_dp->index;
 
-	b53_port_set_ucast_flood(dev, port, true);
-	b53_port_set_mcast_flood(dev, port, true);
-	b53_port_set_learning(dev, port, false);
-
 	if (dev->ops->irq_enable)
 		ret = dev->ops->irq_enable(dev, port);
 	if (ret)
@@ -722,10 +784,6 @@ static void b53_enable_cpu_port(struct b53_device *dev, int port)
 	b53_write8(dev, B53_CTRL_PAGE, B53_PORT_CTRL(port), port_ctrl);
 
 	b53_brcm_hdr_setup(dev->ds, port);
-
-	b53_port_set_ucast_flood(dev, port, true);
-	b53_port_set_mcast_flood(dev, port, true);
-	b53_port_set_learning(dev, port, false);
 }
 
 static void b53_enable_mib(struct b53_device *dev)
@@ -737,6 +795,15 @@ static void b53_enable_mib(struct b53_device *dev)
 	b53_write8(dev, B53_MGMT_PAGE, B53_GLOBAL_CONFIG, gc);
 }
 
+static void b53_enable_stp(struct b53_device *dev)
+{
+	u8 gc;
+
+	b53_read8(dev, B53_MGMT_PAGE, B53_GLOBAL_CONFIG, &gc);
+	gc |= GC_RX_BPDU_EN;
+	b53_write8(dev, B53_MGMT_PAGE, B53_GLOBAL_CONFIG, gc);
+}
+
 static u16 b53_default_pvid(struct b53_device *dev)
 {
 	if (is5325(dev) || is5365(dev))
@@ -752,6 +819,22 @@ static bool b53_vlan_port_needs_forced_tagged(struct dsa_switch *ds, int port)
 	return dev->tag_protocol == DSA_TAG_PROTO_NONE && dsa_is_cpu_port(ds, port);
 }
 
+static bool b53_vlan_port_may_join_untagged(struct dsa_switch *ds, int port)
+{
+	struct b53_device *dev = ds->priv;
+	struct dsa_port *dp;
+
+	if (!dev->vlan_filtering)
+		return true;
+
+	dp = dsa_to_port(ds, port);
+
+	if (dsa_port_is_cpu(dp))
+		return true;
+
+	return dp->bridge == NULL;
+}
+
 int b53_configure_vlan(struct dsa_switch *ds)
 {
 	struct b53_device *dev = ds->priv;
@@ -770,7 +853,7 @@ int b53_configure_vlan(struct dsa_switch *ds)
 		b53_do_vlan_op(dev, VTA_CMD_CLEAR);
 	}
 
-	b53_enable_vlan(dev, -1, dev->vlan_enabled, ds->vlan_filtering);
+	b53_enable_vlan(dev, -1, dev->vlan_enabled, dev->vlan_filtering);
 
 	/* Create an untagged VLAN entry for the default PVID in case
 	 * CONFIG_VLAN_8021Q is disabled and there are no calls to
@@ -778,26 +861,39 @@ int b53_configure_vlan(struct dsa_switch *ds)
 	 * entry. Do this only when the tagging protocol is not
 	 * DSA_TAG_PROTO_NONE
 	 */
+	v = &dev->vlans[def_vid];
 	b53_for_each_port(dev, i) {
-		v = &dev->vlans[def_vid];
-		v->members |= BIT(i);
+		if (!b53_vlan_port_may_join_untagged(ds, i))
+			continue;
+
+		vl.members |= BIT(i);
 		if (!b53_vlan_port_needs_forced_tagged(ds, i))
-			v->untag = v->members;
-		b53_write16(dev, B53_VLAN_PAGE,
-			    B53_VLAN_PORT_DEF_TAG(i), def_vid);
+			vl.untag = vl.members;
+		b53_write16(dev, B53_VLAN_PAGE, B53_VLAN_PORT_DEF_TAG(i),
+			    def_vid);
 	}
+	b53_set_vlan_entry(dev, def_vid, &vl);
 
-	/* Upon initial call we have not set-up any VLANs, but upon
-	 * system resume, we need to restore all VLAN entries.
-	 */
-	for (vid = def_vid; vid < dev->num_vlans; vid++) {
-		v = &dev->vlans[vid];
+	if (dev->vlan_filtering) {
+		/* Upon initial call we have not set-up any VLANs, but upon
+		 * system resume, we need to restore all VLAN entries.
+		 */
+		for (vid = def_vid + 1; vid < dev->num_vlans; vid++) {
+			v = &dev->vlans[vid];
 
-		if (!v->members)
-			continue;
+			if (!v->members)
+				continue;
 
-		b53_set_vlan_entry(dev, vid, v);
-		b53_fast_age_vlan(dev, vid);
+			b53_set_vlan_entry(dev, vid, v);
+			b53_fast_age_vlan(dev, vid);
+		}
+
+		b53_for_each_port(dev, i) {
+			if (!dsa_is_cpu_port(ds, i))
+				b53_write16(dev, B53_VLAN_PAGE,
+					    B53_VLAN_PORT_DEF_TAG(i),
+					    dev->ports[i].pvid);
+		}
 	}
 
 	return 0;
@@ -876,6 +972,7 @@ static int b53_switch_reset(struct b53_device *dev)
 	}
 
 	b53_enable_mib(dev);
+	b53_enable_stp(dev);
 
 	return b53_flush_arl(dev, FAST_AGE_STATIC);
 }
@@ -1116,7 +1213,9 @@ EXPORT_SYMBOL(b53_setup_devlink_resources);
 static int b53_setup(struct dsa_switch *ds)
 {
 	struct b53_device *dev = ds->priv;
+	struct b53_vlan *vl;
 	unsigned int port;
+	u16 pvid;
 	int ret;
 
 	/* Request bridge PVID untagged when DSA_TAG_PROTO_NONE is set
@@ -1124,12 +1223,26 @@ static int b53_setup(struct dsa_switch *ds)
 	 */
 	ds->untag_bridge_pvid = dev->tag_protocol == DSA_TAG_PROTO_NONE;
 
+	/* The switch does not tell us the original VLAN for untagged
+	 * packets, so keep the CPU port always tagged.
+	 */
+	ds->untag_vlan_aware_bridge_pvid = true;
+
 	ret = b53_reset_switch(dev);
 	if (ret) {
 		dev_err(ds->dev, "failed to reset switch\n");
 		return ret;
 	}
 
+	/* setup default vlan for filtering mode */
+	pvid = b53_default_pvid(dev);
+	vl = &dev->vlans[pvid];
+	b53_for_each_port(dev, port) {
+		vl->members |= BIT(port);
+		if (!b53_vlan_port_needs_forced_tagged(ds, port))
+			vl->untag |= BIT(port);
+	}
+
 	b53_reset_mib(dev);
 
 	ret = b53_apply_config(dev);
@@ -1164,6 +1277,8 @@ static void b53_force_link(struct b53_device *dev, int port, int link)
 	if (port == dev->imp_port) {
 		off = B53_PORT_OVERRIDE_CTRL;
 		val = PORT_OVERRIDE_EN;
+	} else if (is5325(dev)) {
+		return;
 	} else {
 		off = B53_GMII_PORT_OVERRIDE_CTRL(port);
 		val = GMII_PO_EN;
@@ -1188,6 +1303,8 @@ static void b53_force_port_config(struct b53_device *dev, int port,
 	if (port == dev->imp_port) {
 		off = B53_PORT_OVERRIDE_CTRL;
 		val = PORT_OVERRIDE_EN;
+	} else if (is5325(dev)) {
+		return;
 	} else {
 		off = B53_GMII_PORT_OVERRIDE_CTRL(port);
 		val = GMII_PO_EN;
@@ -1218,10 +1335,19 @@ static void b53_force_port_config(struct b53_device *dev, int port,
 		return;
 	}
 
-	if (rx_pause)
-		reg |= PORT_OVERRIDE_RX_FLOW;
-	if (tx_pause)
-		reg |= PORT_OVERRIDE_TX_FLOW;
+	if (rx_pause) {
+		if (is5325(dev))
+			reg |= PORT_OVERRIDE_LP_FLOW_25;
+		else
+			reg |= PORT_OVERRIDE_RX_FLOW;
+	}
+
+	if (tx_pause) {
+		if (is5325(dev))
+			reg |= PORT_OVERRIDE_LP_FLOW_25;
+		else
+			reg |= PORT_OVERRIDE_TX_FLOW;
+	}
 
 	b53_write8(dev, B53_CTRL_PAGE, off, reg);
 }
@@ -1238,24 +1364,7 @@ static void b53_adjust_63xx_rgmii(struct dsa_switch *ds, int port,
 		off = B53_RGMII_CTRL_P(port);
 
 	b53_read8(dev, B53_CTRL_PAGE, off, &rgmii_ctrl);
-
-	switch (interface) {
-	case PHY_INTERFACE_MODE_RGMII_ID:
-		rgmii_ctrl |= (RGMII_CTRL_DLL_RXC | RGMII_CTRL_DLL_TXC);
-		break;
-	case PHY_INTERFACE_MODE_RGMII_RXID:
-		rgmii_ctrl &= ~(RGMII_CTRL_DLL_TXC);
-		rgmii_ctrl |= RGMII_CTRL_DLL_RXC;
-		break;
-	case PHY_INTERFACE_MODE_RGMII_TXID:
-		rgmii_ctrl &= ~(RGMII_CTRL_DLL_RXC);
-		rgmii_ctrl |= RGMII_CTRL_DLL_TXC;
-		break;
-	case PHY_INTERFACE_MODE_RGMII:
-	default:
-		rgmii_ctrl &= ~(RGMII_CTRL_DLL_RXC | RGMII_CTRL_DLL_TXC);
-		break;
-	}
+	rgmii_ctrl &= ~(RGMII_CTRL_DLL_RXC | RGMII_CTRL_DLL_TXC);
 
 	if (port != dev->imp_port) {
 		if (is63268(dev))
@@ -1285,8 +1394,7 @@ static void b53_adjust_531x5_rgmii(struct dsa_switch *ds, int port,
 	 * tx_clk aligned timing (restoring to reset defaults)
 	 */
 	b53_read8(dev, B53_CTRL_PAGE, off, &rgmii_ctrl);
-	rgmii_ctrl &= ~(RGMII_CTRL_DLL_RXC | RGMII_CTRL_DLL_TXC |
-			RGMII_CTRL_TIMING_SEL);
+	rgmii_ctrl &= ~(RGMII_CTRL_DLL_RXC | RGMII_CTRL_DLL_TXC);
 
 	/* PHY_INTERFACE_MODE_RGMII_TXID means TX internal delay, make
 	 * sure that we enable the port TX clock internal delay to
@@ -1306,7 +1414,10 @@ static void b53_adjust_531x5_rgmii(struct dsa_switch *ds, int port,
 		rgmii_ctrl |= RGMII_CTRL_DLL_TXC;
 	if (interface == PHY_INTERFACE_MODE_RGMII)
 		rgmii_ctrl |= RGMII_CTRL_DLL_TXC | RGMII_CTRL_DLL_RXC;
-	rgmii_ctrl |= RGMII_CTRL_TIMING_SEL;
+
+	if (dev->chip_id != BCM53115_DEVICE_ID)
+		rgmii_ctrl |= RGMII_CTRL_TIMING_SEL;
+
 	b53_write8(dev, B53_CTRL_PAGE, off, rgmii_ctrl);
 
 	dev_info(ds->dev, "Configured port %d for %s\n", port,
@@ -1370,6 +1481,10 @@ static void b53_phylink_get_caps(struct dsa_switch *ds, int port,
 	__set_bit(PHY_INTERFACE_MODE_MII, config->supported_interfaces);
 	__set_bit(PHY_INTERFACE_MODE_REVMII, config->supported_interfaces);
 
+	/* BCM63xx RGMII ports support RGMII */
+	if (is63xx(dev) && in_range(port, B53_63XX_RGMII0, 4))
+		phy_interface_set_rgmii(config->supported_interfaces);
+
 	config->mac_capabilities = MAC_ASYM_PAUSE | MAC_SYM_PAUSE |
 		MAC_10 | MAC_100;
 
@@ -1483,7 +1598,10 @@ int b53_vlan_filtering(struct dsa_switch *ds, int port, bool vlan_filtering,
 {
 	struct b53_device *dev = ds->priv;
 
-	b53_enable_vlan(dev, port, dev->vlan_enabled, vlan_filtering);
+	if (dev->vlan_filtering != vlan_filtering) {
+		dev->vlan_filtering = vlan_filtering;
+		b53_apply_config(dev);
+	}
 
 	return 0;
 }
@@ -1508,7 +1626,7 @@ static int b53_vlan_prepare(struct dsa_switch *ds, int port,
 	if (vlan->vid >= dev->num_vlans)
 		return -ERANGE;
 
-	b53_enable_vlan(dev, port, true, ds->vlan_filtering);
+	b53_enable_vlan(dev, port, true, dev->vlan_filtering);
 
 	return 0;
 }
@@ -1521,18 +1639,29 @@ int b53_vlan_add(struct dsa_switch *ds, int port,
 	bool untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED;
 	bool pvid = vlan->flags & BRIDGE_VLAN_INFO_PVID;
 	struct b53_vlan *vl;
+	u16 old_pvid, new_pvid;
 	int err;
 
 	err = b53_vlan_prepare(ds, port, vlan);
 	if (err)
 		return err;
 
-	vl = &dev->vlans[vlan->vid];
+	if (vlan->vid == 0)
+		return 0;
+
+	old_pvid = dev->ports[port].pvid;
+	if (pvid)
+		new_pvid = vlan->vid;
+	else if (!pvid && vlan->vid == old_pvid)
+		new_pvid = b53_default_pvid(dev);
+	else
+		new_pvid = old_pvid;
+	dev->ports[port].pvid = new_pvid;
 
-	b53_get_vlan_entry(dev, vlan->vid, vl);
+	vl = &dev->vlans[vlan->vid];
 
-	if (vlan->vid == 0 && vlan->vid == b53_default_pvid(dev))
-		untagged = true;
+	if (dsa_is_cpu_port(ds, port))
+		untagged = false;
 
 	vl->members |= BIT(port);
 	if (untagged && !b53_vlan_port_needs_forced_tagged(ds, port))
@@ -1540,13 +1669,16 @@ int b53_vlan_add(struct dsa_switch *ds, int port,
 	else
 		vl->untag &= ~BIT(port);
 
+	if (!dev->vlan_filtering)
+		return 0;
+
 	b53_set_vlan_entry(dev, vlan->vid, vl);
 	b53_fast_age_vlan(dev, vlan->vid);
 
-	if (pvid && !dsa_is_cpu_port(ds, port)) {
+	if (!dsa_is_cpu_port(ds, port) && new_pvid != old_pvid) {
 		b53_write16(dev, B53_VLAN_PAGE, B53_VLAN_PORT_DEF_TAG(port),
-			    vlan->vid);
-		b53_fast_age_vlan(dev, vlan->vid);
+			    new_pvid);
+		b53_fast_age_vlan(dev, old_pvid);
 	}
 
 	return 0;
@@ -1561,20 +1693,25 @@ int b53_vlan_del(struct dsa_switch *ds, int port,
 	struct b53_vlan *vl;
 	u16 pvid;
 
-	b53_read16(dev, B53_VLAN_PAGE, B53_VLAN_PORT_DEF_TAG(port), &pvid);
+	if (vlan->vid == 0)
+		return 0;
+
+	pvid = dev->ports[port].pvid;
 
 	vl = &dev->vlans[vlan->vid];
 
-	b53_get_vlan_entry(dev, vlan->vid, vl);
-
 	vl->members &= ~BIT(port);
 
 	if (pvid == vlan->vid)
 		pvid = b53_default_pvid(dev);
+	dev->ports[port].pvid = pvid;
 
 	if (untagged && !b53_vlan_port_needs_forced_tagged(ds, port))
 		vl->untag &= ~(BIT(port));
 
+	if (!dev->vlan_filtering)
+		return 0;
+
 	b53_set_vlan_entry(dev, vlan->vid, vl);
 	b53_fast_age_vlan(dev, vlan->vid);
 
@@ -1907,8 +2044,9 @@ int b53_br_join(struct dsa_switch *ds, int port, struct dsa_bridge bridge,
 		bool *tx_fwd_offload, struct netlink_ext_ack *extack)
 {
 	struct b53_device *dev = ds->priv;
+	struct b53_vlan *vl;
 	s8 cpu_port = dsa_to_port(ds, port)->cpu_dp->index;
-	u16 pvlan, reg;
+	u16 pvlan, reg, pvid;
 	unsigned int i;
 
 	/* On 7278, port 7 which connects to the ASP should only receive
@@ -1917,15 +2055,26 @@ int b53_br_join(struct dsa_switch *ds, int port, struct dsa_bridge bridge,
 	if (dev->chip_id == BCM7278_DEVICE_ID && port == 7)
 		return -EINVAL;
 
-	/* Make this port leave the all VLANs join since we will have proper
-	 * VLAN entries from now on
-	 */
-	if (is58xx(dev)) {
-		b53_read16(dev, B53_VLAN_PAGE, B53_JOIN_ALL_VLAN_EN, &reg);
-		reg &= ~BIT(port);
-		if ((reg & BIT(cpu_port)) == BIT(cpu_port))
-			reg &= ~BIT(cpu_port);
-		b53_write16(dev, B53_VLAN_PAGE, B53_JOIN_ALL_VLAN_EN, reg);
+	pvid = b53_default_pvid(dev);
+	vl = &dev->vlans[pvid];
+
+	if (dev->vlan_filtering) {
+		/* Make this port leave the all VLANs join since we will have
+		 * proper VLAN entries from now on
+		 */
+		if (is58xx(dev)) {
+			b53_read16(dev, B53_VLAN_PAGE, B53_JOIN_ALL_VLAN_EN,
+				   &reg);
+			reg &= ~BIT(port);
+			if ((reg & BIT(cpu_port)) == BIT(cpu_port))
+				reg &= ~BIT(cpu_port);
+			b53_write16(dev, B53_VLAN_PAGE, B53_JOIN_ALL_VLAN_EN,
+				    reg);
+		}
+
+		b53_get_vlan_entry(dev, pvid, vl);
+		vl->members &= ~BIT(port);
+		b53_set_vlan_entry(dev, pvid, vl);
 	}
 
 	b53_read16(dev, B53_PVLAN_PAGE, B53_PVLAN_PORT_MASK(port), &pvlan);
@@ -1945,6 +2094,9 @@ int b53_br_join(struct dsa_switch *ds, int port, struct dsa_bridge bridge,
 		pvlan |= BIT(i);
 	}
 
+	/* Disable redirection of unknown SA to the CPU port */
+	b53_set_eap_mode(dev, port, EAP_MODE_BASIC);
+
 	/* Configure the local port VLAN control membership to include
 	 * remote ports and update the local port bitmask
 	 */
@@ -1958,7 +2110,7 @@ EXPORT_SYMBOL(b53_br_join);
 void b53_br_leave(struct dsa_switch *ds, int port, struct dsa_bridge bridge)
 {
 	struct b53_device *dev = ds->priv;
-	struct b53_vlan *vl = &dev->vlans[0];
+	struct b53_vlan *vl;
 	s8 cpu_port = dsa_to_port(ds, port)->cpu_dp->index;
 	unsigned int i;
 	u16 pvlan, reg, pvid;
@@ -1980,22 +2132,27 @@ void b53_br_leave(struct dsa_switch *ds, int port, struct dsa_bridge bridge)
 			pvlan &= ~BIT(i);
 	}
 
+	/* Enable redirection of unknown SA to the CPU port */
+	b53_set_eap_mode(dev, port, EAP_MODE_SIMPLIFIED);
+
 	b53_write16(dev, B53_PVLAN_PAGE, B53_PVLAN_PORT_MASK(port), pvlan);
 	dev->ports[port].vlan_ctl_mask = pvlan;
 
 	pvid = b53_default_pvid(dev);
+	vl = &dev->vlans[pvid];
+
+	if (dev->vlan_filtering) {
+		/* Make this port join all VLANs without VLAN entries */
+		if (is58xx(dev)) {
+			b53_read16(dev, B53_VLAN_PAGE, B53_JOIN_ALL_VLAN_EN, &reg);
+			reg |= BIT(port);
+			if (!(reg & BIT(cpu_port)))
+				reg |= BIT(cpu_port);
+			b53_write16(dev, B53_VLAN_PAGE, B53_JOIN_ALL_VLAN_EN, reg);
+		}
 
-	/* Make this port join all VLANs without VLAN entries */
-	if (is58xx(dev)) {
-		b53_read16(dev, B53_VLAN_PAGE, B53_JOIN_ALL_VLAN_EN, &reg);
-		reg |= BIT(port);
-		if (!(reg & BIT(cpu_port)))
-			reg |= BIT(cpu_port);
-		b53_write16(dev, B53_VLAN_PAGE, B53_JOIN_ALL_VLAN_EN, reg);
-	} else {
 		b53_get_vlan_entry(dev, pvid, vl);
-		vl->members |= BIT(port) | BIT(cpu_port);
-		vl->untag |= BIT(port) | BIT(cpu_port);
+		vl->members |= BIT(port);
 		b53_set_vlan_entry(dev, pvid, vl);
 	}
 }
@@ -2048,7 +2205,13 @@ int b53_br_flags_pre(struct dsa_switch *ds, int port,
 		     struct switchdev_brport_flags flags,
 		     struct netlink_ext_ack *extack)
 {
-	if (flags.mask & ~(BR_FLOOD | BR_MCAST_FLOOD | BR_LEARNING))
+	struct b53_device *dev = ds->priv;
+	unsigned long mask = (BR_FLOOD | BR_MCAST_FLOOD);
+
+	if (!is5325(dev))
+		mask |= BR_LEARNING;
+
+	if (flags.mask & ~mask)
 		return -EINVAL;
 
 	return 0;
@@ -2297,6 +2460,7 @@ static const struct dsa_switch_ops b53_switch_ops = {
 	.phy_read		= b53_phy_read16,
 	.phy_write		= b53_phy_write16,
 	.phylink_get_caps	= b53_phylink_get_caps,
+	.port_setup		= b53_setup_port,
 	.port_enable		= b53_enable_port,
 	.port_disable		= b53_disable_port,
 	.get_mac_eee		= b53_get_mac_eee,
@@ -2741,6 +2905,7 @@ struct b53_device *b53_switch_alloc(struct device *base,
 	ds->ops = &b53_switch_ops;
 	ds->phylink_mac_ops = &b53_phylink_mac_ops;
 	dev->vlan_enabled = true;
+	dev->vlan_filtering = false;
 	/* Let DSA handle the case were multiple bridges span the same switch
 	 * device and different VLAN awareness settings are requested, which
 	 * would be breaking filtering semantics for any of the other bridge
diff --git a/drivers/net/dsa/b53/b53_priv.h b/drivers/net/dsa/b53/b53_priv.h
index 05141176daf5..4f8c97098d2a 100644
--- a/drivers/net/dsa/b53/b53_priv.h
+++ b/drivers/net/dsa/b53/b53_priv.h
@@ -95,6 +95,7 @@ struct b53_pcs {
 
 struct b53_port {
 	u16		vlan_ctl_mask;
+	u16		pvid;
 	struct ethtool_keee eee;
 };
 
@@ -146,6 +147,7 @@ struct b53_device {
 	unsigned int num_vlans;
 	struct b53_vlan *vlans;
 	bool vlan_enabled;
+	bool vlan_filtering;
 	unsigned int num_ports;
 	struct b53_port *ports;
 
@@ -380,6 +382,7 @@ enum dsa_tag_protocol b53_get_tag_protocol(struct dsa_switch *ds, int port,
 					   enum dsa_tag_protocol mprot);
 void b53_mirror_del(struct dsa_switch *ds, int port,
 		    struct dsa_mall_mirror_tc_entry *mirror);
+int b53_setup_port(struct dsa_switch *ds, int port);
 int b53_enable_port(struct dsa_switch *ds, int port, struct phy_device *phy);
 void b53_disable_port(struct dsa_switch *ds, int port);
 void b53_brcm_hdr_setup(struct dsa_switch *ds, int port);
diff --git a/drivers/net/dsa/b53/b53_regs.h b/drivers/net/dsa/b53/b53_regs.h
index bfbcb66bef66..5741231e0841 100644
--- a/drivers/net/dsa/b53/b53_regs.h
+++ b/drivers/net/dsa/b53/b53_regs.h
@@ -50,6 +50,9 @@
 /* Jumbo Frame Registers */
 #define B53_JUMBO_PAGE			0x40
 
+/* EAP Registers */
+#define B53_EAP_PAGE			0x42
+
 /* EEE Control Registers Page */
 #define B53_EEE_PAGE			0x92
 
@@ -92,17 +95,22 @@
 #define   PORT_OVERRIDE_SPEED_10M	(0 << PORT_OVERRIDE_SPEED_S)
 #define   PORT_OVERRIDE_SPEED_100M	(1 << PORT_OVERRIDE_SPEED_S)
 #define   PORT_OVERRIDE_SPEED_1000M	(2 << PORT_OVERRIDE_SPEED_S)
+#define   PORT_OVERRIDE_LP_FLOW_25	BIT(3) /* BCM5325 only */
 #define   PORT_OVERRIDE_RV_MII_25	BIT(4) /* BCM5325 only */
 #define   PORT_OVERRIDE_RX_FLOW		BIT(4)
 #define   PORT_OVERRIDE_TX_FLOW		BIT(5)
 #define   PORT_OVERRIDE_SPEED_2000M	BIT(6) /* BCM5301X only, requires setting 1000M */
 #define   PORT_OVERRIDE_EN		BIT(7) /* Use the register contents */
 
-/* Power-down mode control */
+/* Power-down mode control (8 bit) */
 #define B53_PD_MODE_CTRL_25		0x0f
+#define  PD_MODE_PORT_MASK		0x1f
+/* Bit 0 also powers down the switch. */
+#define  PD_MODE_POWER_DOWN_PORT(i)	BIT(i)
 
 /* IP Multicast control (8 bit) */
 #define B53_IP_MULTICAST_CTRL		0x21
+#define  B53_IP_MCAST_25		BIT(0)
 #define  B53_IPMC_FWD_EN		BIT(1)
 #define  B53_UC_FWD_EN			BIT(6)
 #define  B53_MC_FWD_EN			BIT(7)
@@ -481,6 +489,17 @@
 #define   JMS_MAX_SIZE			9724
 
 /*************************************************************************
+ * EAP Page Registers
+ *************************************************************************/
+#define B53_PORT_EAP_CONF(i)		(0x20 + 8 * (i))
+#define  EAP_MODE_SHIFT			51
+#define  EAP_MODE_SHIFT_63XX		50
+#define  EAP_MODE_MASK			(0x3ull << EAP_MODE_SHIFT)
+#define  EAP_MODE_MASK_63XX		(0x3ull << EAP_MODE_SHIFT_63XX)
+#define  EAP_MODE_BASIC			0
+#define  EAP_MODE_SIMPLIFIED		3
+
+/*************************************************************************
  * EEE Configuration Page Registers
  *************************************************************************/
 
diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index 0e663ec0c12a..c4771a07878e 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -1230,6 +1230,7 @@ static const struct dsa_switch_ops bcm_sf2_ops = {
 	.resume			= bcm_sf2_sw_resume,
 	.get_wol		= bcm_sf2_sw_get_wol,
 	.set_wol		= bcm_sf2_sw_set_wol,
+	.port_setup		= b53_setup_port,
 	.port_enable		= bcm_sf2_port_setup,
 	.port_disable		= bcm_sf2_port_disable,
 	.get_mac_eee		= b53_get_mac_eee,
diff --git a/drivers/net/dsa/microchip/ksz8.c b/drivers/net/dsa/microchip/ksz8.c
index da7110d67558..6c7454a43bce 100644
--- a/drivers/net/dsa/microchip/ksz8.c
+++ b/drivers/net/dsa/microchip/ksz8.c
@@ -371,6 +371,9 @@ static void ksz8863_r_mib_pkt(struct ksz_device *dev, int port, u16 addr,
 	addr -= dev->info->reg_mib_cnt;
 	ctrl_addr = addr ? KSZ8863_MIB_PACKET_DROPPED_TX_0 :
 			   KSZ8863_MIB_PACKET_DROPPED_RX_0;
+	if (ksz_is_8895_family(dev) &&
+	    ctrl_addr == KSZ8863_MIB_PACKET_DROPPED_RX_0)
+		ctrl_addr = KSZ8895_MIB_PACKET_DROPPED_RX_0;
 	ctrl_addr += port;
 	ctrl_addr |= IND_ACC_TABLE(TABLE_MIB | TABLE_READ);
 
diff --git a/drivers/net/dsa/microchip/ksz8_reg.h b/drivers/net/dsa/microchip/ksz8_reg.h
index 329688603a58..da80e659c648 100644
--- a/drivers/net/dsa/microchip/ksz8_reg.h
+++ b/drivers/net/dsa/microchip/ksz8_reg.h
@@ -784,7 +784,9 @@
 #define KSZ8795_MIB_TOTAL_TX_1		0x105
 
 #define KSZ8863_MIB_PACKET_DROPPED_TX_0 0x100
-#define KSZ8863_MIB_PACKET_DROPPED_RX_0 0x105
+#define KSZ8863_MIB_PACKET_DROPPED_RX_0 0x103
+
+#define KSZ8895_MIB_PACKET_DROPPED_RX_0 0x105
 
 #define MIB_PACKET_DROPPED		0x0000FFFF
 
diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c
index d84ee1b419a6..93bf085a61d3 100644
--- a/drivers/net/dsa/mt7530.c
+++ b/drivers/net/dsa/mt7530.c
@@ -2540,6 +2540,9 @@ mt7531_setup_common(struct dsa_switch *ds)
 	struct mt7530_priv *priv = ds->priv;
 	int ret, i;
 
+	ds->assisted_learning_on_cpu_port = true;
+	ds->mtu_enforcement_ingress = true;
+
 	mt753x_trap_frames(priv);
 
 	/* Enable and reset MIB counters */
@@ -2590,7 +2593,8 @@ mt7531_setup_common(struct dsa_switch *ds)
 	if (ret < 0)
 		return ret;
 
-	return 0;
+	/* Setup VLAN ID 0 for VLAN-unaware bridges */
+	return mt7530_setup_vlan0(priv);
 }
 
 static int
@@ -2686,14 +2690,6 @@ mt7531_setup(struct dsa_switch *ds)
 	if (ret)
 		return ret;
 
-	/* Setup VLAN ID 0 for VLAN-unaware bridges */
-	ret = mt7530_setup_vlan0(priv);
-	if (ret)
-		return ret;
-
-	ds->assisted_learning_on_cpu_port = true;
-	ds->mtu_enforcement_ingress = true;
-
 	return 0;
 }
 
diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 284270a4ade1..211c219dd52d 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -1878,6 +1878,8 @@ static int mv88e6xxx_vtu_get(struct mv88e6xxx_chip *chip, u16 vid,
 	if (!chip->info->ops->vtu_getnext)
 		return -EOPNOTSUPP;
 
+	memset(entry, 0, sizeof(*entry));
+
 	entry->vid = vid ? vid - 1 : mv88e6xxx_max_vid(chip);
 	entry->valid = false;
 
@@ -2013,7 +2015,16 @@ static int mv88e6xxx_mst_put(struct mv88e6xxx_chip *chip, u8 sid)
 	struct mv88e6xxx_mst *mst, *tmp;
 	int err;
 
-	if (!sid)
+	/* If the SID is zero, it is for a VLAN mapped to the default MSTI,
+	 * and mv88e6xxx_stu_setup() made sure it is always present, and thus,
+	 * should not be removed here.
+	 *
+	 * If the chip lacks STU support, numerically the "sid" variable will
+	 * happen to also be zero, but we don't want to rely on that fact, so
+	 * we explicitly test that first. In that case, there is also nothing
+	 * to do here.
+	 */
+	if (!mv88e6xxx_has_stu(chip) || !sid)
 		return 0;
 
 	list_for_each_entry_safe(mst, tmp, &chip->msts, node) {
@@ -2261,13 +2272,11 @@ mv88e6xxx_port_vlan_prepare(struct dsa_switch *ds, int port,
 	return err;
 }
 
-static int mv88e6xxx_port_db_load_purge(struct mv88e6xxx_chip *chip, int port,
-					const unsigned char *addr, u16 vid,
-					u8 state)
+static int mv88e6xxx_port_db_get(struct mv88e6xxx_chip *chip,
+				 const unsigned char *addr, u16 vid,
+				 u16 *fid, struct mv88e6xxx_atu_entry *entry)
 {
-	struct mv88e6xxx_atu_entry entry;
 	struct mv88e6xxx_vtu_entry vlan;
-	u16 fid;
 	int err;
 
 	/* Ports have two private address databases: one for when the port is
@@ -2278,7 +2287,7 @@ static int mv88e6xxx_port_db_load_purge(struct mv88e6xxx_chip *chip, int port,
 	 * VLAN ID into the port's database used for VLAN-unaware bridging.
 	 */
 	if (vid == 0) {
-		fid = MV88E6XXX_FID_BRIDGED;
+		*fid = MV88E6XXX_FID_BRIDGED;
 	} else {
 		err = mv88e6xxx_vtu_get(chip, vid, &vlan);
 		if (err)
@@ -2288,14 +2297,39 @@ static int mv88e6xxx_port_db_load_purge(struct mv88e6xxx_chip *chip, int port,
 		if (!vlan.valid)
 			return -EOPNOTSUPP;
 
-		fid = vlan.fid;
+		*fid = vlan.fid;
 	}
 
-	entry.state = 0;
-	ether_addr_copy(entry.mac, addr);
-	eth_addr_dec(entry.mac);
+	entry->state = 0;
+	ether_addr_copy(entry->mac, addr);
+	eth_addr_dec(entry->mac);
+
+	return mv88e6xxx_g1_atu_getnext(chip, *fid, entry);
+}
+
+static bool mv88e6xxx_port_db_find(struct mv88e6xxx_chip *chip,
+				   const unsigned char *addr, u16 vid)
+{
+	struct mv88e6xxx_atu_entry entry;
+	u16 fid;
+	int err;
+
+	err = mv88e6xxx_port_db_get(chip, addr, vid, &fid, &entry);
+	if (err)
+		return false;
+
+	return entry.state && ether_addr_equal(entry.mac, addr);
+}
+
+static int mv88e6xxx_port_db_load_purge(struct mv88e6xxx_chip *chip, int port,
+					const unsigned char *addr, u16 vid,
+					u8 state)
+{
+	struct mv88e6xxx_atu_entry entry;
+	u16 fid;
+	int err;
 
-	err = mv88e6xxx_g1_atu_getnext(chip, fid, &entry);
+	err = mv88e6xxx_port_db_get(chip, addr, vid, &fid, &entry);
 	if (err)
 		return err;
 
@@ -2893,6 +2927,13 @@ static int mv88e6xxx_port_fdb_add(struct dsa_switch *ds, int port,
 	mv88e6xxx_reg_lock(chip);
 	err = mv88e6xxx_port_db_load_purge(chip, port, addr, vid,
 					   MV88E6XXX_G1_ATU_DATA_STATE_UC_STATIC);
+	if (err)
+		goto out;
+
+	if (!mv88e6xxx_port_db_find(chip, addr, vid))
+		err = -ENOSPC;
+
+out:
 	mv88e6xxx_reg_unlock(chip);
 
 	return err;
@@ -3661,6 +3702,21 @@ static int mv88e6xxx_stats_setup(struct mv88e6xxx_chip *chip)
 	return mv88e6xxx_g1_stats_clear(chip);
 }
 
+static int mv88e6320_setup_errata(struct mv88e6xxx_chip *chip)
+{
+	u16 dummy;
+	int err;
+
+	/* Workaround for erratum
+	 *   3.3 RGMII timing may be out of spec when transmit delay is enabled
+	 */
+	err = mv88e6xxx_port_hidden_write(chip, 0, 0xf, 0x7, 0xe000);
+	if (err)
+		return err;
+
+	return mv88e6xxx_port_hidden_read(chip, 0, 0xf, 0x7, &dummy);
+}
+
 /* Check if the errata has already been applied. */
 static bool mv88e6390_setup_errata_applied(struct mv88e6xxx_chip *chip)
 {
@@ -5114,6 +5170,7 @@ static const struct mv88e6xxx_ops mv88e6290_ops = {
 
 static const struct mv88e6xxx_ops mv88e6320_ops = {
 	/* MV88E6XXX_FAMILY_6320 */
+	.setup_errata = mv88e6320_setup_errata,
 	.ieee_pri_map = mv88e6085_g1_ieee_pri_map,
 	.ip_pri_map = mv88e6085_g1_ip_pri_map,
 	.irl_init_all = mv88e6352_g2_irl_init_all,
@@ -5129,6 +5186,7 @@ static const struct mv88e6xxx_ops mv88e6320_ops = {
 	.port_set_rgmii_delay = mv88e6320_port_set_rgmii_delay,
 	.port_set_speed_duplex = mv88e6185_port_set_speed_duplex,
 	.port_tag_remap = mv88e6095_port_tag_remap,
+	.port_set_policy = mv88e6352_port_set_policy,
 	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
 	.port_set_ucast_flood = mv88e6352_port_set_ucast_flood,
 	.port_set_mcast_flood = mv88e6352_port_set_mcast_flood,
@@ -5153,8 +5211,10 @@ static const struct mv88e6xxx_ops mv88e6320_ops = {
 	.hardware_reset_pre = mv88e6xxx_g2_eeprom_wait,
 	.hardware_reset_post = mv88e6xxx_g2_eeprom_wait,
 	.reset = mv88e6352_g1_reset,
-	.vtu_getnext = mv88e6185_g1_vtu_getnext,
-	.vtu_loadpurge = mv88e6185_g1_vtu_loadpurge,
+	.vtu_getnext = mv88e6352_g1_vtu_getnext,
+	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
+	.stu_getnext = mv88e6352_g1_stu_getnext,
+	.stu_loadpurge = mv88e6352_g1_stu_loadpurge,
 	.gpio_ops = &mv88e6352_gpio_ops,
 	.avb_ops = &mv88e6352_avb_ops,
 	.ptp_ops = &mv88e6352_ptp_ops,
@@ -5163,6 +5223,7 @@ static const struct mv88e6xxx_ops mv88e6320_ops = {
 
 static const struct mv88e6xxx_ops mv88e6321_ops = {
 	/* MV88E6XXX_FAMILY_6320 */
+	.setup_errata = mv88e6320_setup_errata,
 	.ieee_pri_map = mv88e6085_g1_ieee_pri_map,
 	.ip_pri_map = mv88e6085_g1_ip_pri_map,
 	.irl_init_all = mv88e6352_g2_irl_init_all,
@@ -5178,6 +5239,7 @@ static const struct mv88e6xxx_ops mv88e6321_ops = {
 	.port_set_rgmii_delay = mv88e6320_port_set_rgmii_delay,
 	.port_set_speed_duplex = mv88e6185_port_set_speed_duplex,
 	.port_tag_remap = mv88e6095_port_tag_remap,
+	.port_set_policy = mv88e6352_port_set_policy,
 	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
 	.port_set_ucast_flood = mv88e6352_port_set_ucast_flood,
 	.port_set_mcast_flood = mv88e6352_port_set_mcast_flood,
@@ -5201,8 +5263,10 @@ static const struct mv88e6xxx_ops mv88e6321_ops = {
 	.hardware_reset_pre = mv88e6xxx_g2_eeprom_wait,
 	.hardware_reset_post = mv88e6xxx_g2_eeprom_wait,
 	.reset = mv88e6352_g1_reset,
-	.vtu_getnext = mv88e6185_g1_vtu_getnext,
-	.vtu_loadpurge = mv88e6185_g1_vtu_loadpurge,
+	.vtu_getnext = mv88e6352_g1_vtu_getnext,
+	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
+	.stu_getnext = mv88e6352_g1_stu_getnext,
+	.stu_loadpurge = mv88e6352_g1_stu_loadpurge,
 	.gpio_ops = &mv88e6352_gpio_ops,
 	.avb_ops = &mv88e6352_avb_ops,
 	.ptp_ops = &mv88e6352_ptp_ops,
@@ -5794,7 +5858,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.global1_addr = 0x1b,
 		.global2_addr = 0x1c,
 		.age_time_coeff = 3750,
-		.atu_move_port_mask = 0x1f,
+		.atu_move_port_mask = 0xf,
 		.g1_irqs = 9,
 		.g2_irqs = 10,
 		.pvt = true,
@@ -6198,6 +6262,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.num_internal_phys = 5,
 		.num_gpio = 15,
 		.max_vid = 4095,
+		.max_sid = 63,
 		.port_base_addr = 0x10,
 		.phy_base_addr = 0x0,
 		.global1_addr = 0x1b,
@@ -6223,6 +6288,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.num_internal_phys = 5,
 		.num_gpio = 15,
 		.max_vid = 4095,
+		.max_sid = 63,
 		.port_base_addr = 0x10,
 		.phy_base_addr = 0x0,
 		.global1_addr = 0x1b,
@@ -6231,6 +6297,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.g1_irqs = 8,
 		.g2_irqs = 10,
 		.atu_move_port_mask = 0xf,
+		.pvt = true,
 		.multi_chip = true,
 		.edsa_support = MV88E6XXX_EDSA_SUPPORTED,
 		.ptp_support = true,
@@ -6253,7 +6320,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.global1_addr = 0x1b,
 		.global2_addr = 0x1c,
 		.age_time_coeff = 3750,
-		.atu_move_port_mask = 0x1f,
+		.atu_move_port_mask = 0xf,
 		.g1_irqs = 9,
 		.g2_irqs = 10,
 		.pvt = true,
@@ -6593,6 +6660,13 @@ static int mv88e6xxx_port_mdb_add(struct dsa_switch *ds, int port,
 	mv88e6xxx_reg_lock(chip);
 	err = mv88e6xxx_port_db_load_purge(chip, port, mdb->addr, mdb->vid,
 					   MV88E6XXX_G1_ATU_DATA_STATE_MC_STATIC);
+	if (err)
+		goto out;
+
+	if (!mv88e6xxx_port_db_find(chip, mdb->addr, mdb->vid))
+		err = -ENOSPC;
+
+out:
 	mv88e6xxx_reg_unlock(chip);
 
 	return err;
@@ -7264,13 +7338,13 @@ static int mv88e6xxx_probe(struct mdio_device *mdiodev)
 	err = mv88e6xxx_switch_reset(chip);
 	mv88e6xxx_reg_unlock(chip);
 	if (err)
-		goto out;
+		goto out_phy;
 
 	if (np) {
 		chip->irq = of_irq_get(np, 0);
 		if (chip->irq == -EPROBE_DEFER) {
 			err = chip->irq;
-			goto out;
+			goto out_phy;
 		}
 	}
 
@@ -7289,7 +7363,7 @@ static int mv88e6xxx_probe(struct mdio_device *mdiodev)
 	mv88e6xxx_reg_unlock(chip);
 
 	if (err)
-		goto out;
+		goto out_phy;
 
 	if (chip->info->g2_irqs > 0) {
 		err = mv88e6xxx_g2_irq_setup(chip);
@@ -7323,6 +7397,8 @@ out_g1_irq:
 		mv88e6xxx_g1_irq_free(chip);
 	else
 		mv88e6xxx_irq_poll_free(chip);
+out_phy:
+	mv88e6xxx_phy_destroy(chip);
 out:
 	if (pdata)
 		dev_put(pdata->netdev);
@@ -7345,7 +7421,6 @@ static void mv88e6xxx_remove(struct mdio_device *mdiodev)
 		mv88e6xxx_ptp_free(chip);
 	}
 
-	mv88e6xxx_phy_destroy(chip);
 	mv88e6xxx_unregister_switch(chip);
 
 	mv88e6xxx_g1_vtu_prob_irq_free(chip);
@@ -7358,6 +7433,8 @@ static void mv88e6xxx_remove(struct mdio_device *mdiodev)
 		mv88e6xxx_g1_irq_free(chip);
 	else
 		mv88e6xxx_irq_poll_free(chip);
+
+	mv88e6xxx_phy_destroy(chip);
 }
 
 static void mv88e6xxx_shutdown(struct mdio_device *mdiodev)
diff --git a/drivers/net/dsa/mv88e6xxx/devlink.c b/drivers/net/dsa/mv88e6xxx/devlink.c
index a08dab75e0c0..f57fde02077d 100644
--- a/drivers/net/dsa/mv88e6xxx/devlink.c
+++ b/drivers/net/dsa/mv88e6xxx/devlink.c
@@ -743,7 +743,8 @@ void mv88e6xxx_teardown_devlink_regions_global(struct dsa_switch *ds)
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(mv88e6xxx_regions); i++)
-		dsa_devlink_region_destroy(chip->regions[i]);
+		if (chip->regions[i])
+			dsa_devlink_region_destroy(chip->regions[i]);
 }
 
 void mv88e6xxx_teardown_devlink_regions_port(struct dsa_switch *ds, int port)
diff --git a/drivers/net/dsa/mv88e6xxx/phy.c b/drivers/net/dsa/mv88e6xxx/phy.c
index 8bb88b3d900d..ee9e5d7e5277 100644
--- a/drivers/net/dsa/mv88e6xxx/phy.c
+++ b/drivers/net/dsa/mv88e6xxx/phy.c
@@ -229,7 +229,10 @@ static void mv88e6xxx_phy_ppu_state_init(struct mv88e6xxx_chip *chip)
 
 static void mv88e6xxx_phy_ppu_state_destroy(struct mv88e6xxx_chip *chip)
 {
+	mutex_lock(&chip->ppu_mutex);
 	del_timer_sync(&chip->ppu_timer);
+	cancel_work_sync(&chip->ppu_work);
+	mutex_unlock(&chip->ppu_mutex);
 }
 
 int mv88e6185_phy_ppu_read(struct mv88e6xxx_chip *chip, struct mii_bus *bus,
diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c
index 940f1b71226d..7b35d24c38d7 100644
--- a/drivers/net/dsa/ocelot/felix_vsc9959.c
+++ b/drivers/net/dsa/ocelot/felix_vsc9959.c
@@ -1543,7 +1543,7 @@ static void vsc9959_tas_clock_adjust(struct ocelot *ocelot)
 	struct tc_taprio_qopt_offload *taprio;
 	struct ocelot_port *ocelot_port;
 	struct timespec64 base_ts;
-	int port;
+	int i, port;
 	u32 val;
 
 	mutex_lock(&ocelot->fwd_domain_lock);
@@ -1575,6 +1575,9 @@ static void vsc9959_tas_clock_adjust(struct ocelot *ocelot)
 			   QSYS_PARAM_CFG_REG_3_BASE_TIME_SEC_MSB_M,
 			   QSYS_PARAM_CFG_REG_3);
 
+		for (i = 0; i < taprio->num_entries; i++)
+			vsc9959_tas_gcl_set(ocelot, i, &taprio->entries[i]);
+
 		ocelot_rmw(ocelot, QSYS_TAS_PARAM_CFG_CTRL_CONFIG_CHANGE,
 			   QSYS_TAS_PARAM_CFG_CTRL_CONFIG_CHANGE,
 			   QSYS_TAS_PARAM_CFG_CTRL);
diff --git a/drivers/net/dsa/realtek/Kconfig b/drivers/net/dsa/realtek/Kconfig
index 6989972eebc3..d6eb6713e5f6 100644
--- a/drivers/net/dsa/realtek/Kconfig
+++ b/drivers/net/dsa/realtek/Kconfig
@@ -43,4 +43,10 @@ config NET_DSA_REALTEK_RTL8366RB
 	help
 	  Select to enable support for Realtek RTL8366RB.
 
+config NET_DSA_REALTEK_RTL8366RB_LEDS
+	bool
+	depends on (LEDS_CLASS=y || LEDS_CLASS=NET_DSA_REALTEK_RTL8366RB)
+	depends on NET_DSA_REALTEK_RTL8366RB
+	default NET_DSA_REALTEK_RTL8366RB
+
 endif
diff --git a/drivers/net/dsa/realtek/Makefile b/drivers/net/dsa/realtek/Makefile
index 35491dc20d6d..17367bcba496 100644
--- a/drivers/net/dsa/realtek/Makefile
+++ b/drivers/net/dsa/realtek/Makefile
@@ -12,4 +12,7 @@ endif
 
 obj-$(CONFIG_NET_DSA_REALTEK_RTL8366RB) += rtl8366.o
 rtl8366-objs 				:= rtl8366-core.o rtl8366rb.o
+ifdef CONFIG_NET_DSA_REALTEK_RTL8366RB_LEDS
+rtl8366-objs 				+= rtl8366rb-leds.o
+endif
 obj-$(CONFIG_NET_DSA_REALTEK_RTL8365MB) += rtl8365mb.o
diff --git a/drivers/net/dsa/realtek/rtl8366rb-leds.c b/drivers/net/dsa/realtek/rtl8366rb-leds.c
new file mode 100644
index 000000000000..99c890681ae6
--- /dev/null
+++ b/drivers/net/dsa/realtek/rtl8366rb-leds.c
@@ -0,0 +1,177 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bitops.h>
+#include <linux/regmap.h>
+#include <net/dsa.h>
+#include "rtl83xx.h"
+#include "rtl8366rb.h"
+
+static inline u32 rtl8366rb_led_group_port_mask(u8 led_group, u8 port)
+{
+	switch (led_group) {
+	case 0:
+		return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port));
+	case 1:
+		return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port));
+	case 2:
+		return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port));
+	case 3:
+		return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port));
+	default:
+		return 0;
+	}
+}
+
+static int rb8366rb_get_port_led(struct rtl8366rb_led *led)
+{
+	struct realtek_priv *priv = led->priv;
+	u8 led_group = led->led_group;
+	u8 port_num = led->port_num;
+	int ret;
+	u32 val;
+
+	ret = regmap_read(priv->map, RTL8366RB_LED_X_X_CTRL_REG(led_group),
+			  &val);
+	if (ret) {
+		dev_err(priv->dev, "error reading LED on port %d group %d\n",
+			led_group, port_num);
+		return ret;
+	}
+
+	return !!(val & rtl8366rb_led_group_port_mask(led_group, port_num));
+}
+
+static int rb8366rb_set_port_led(struct rtl8366rb_led *led, bool enable)
+{
+	struct realtek_priv *priv = led->priv;
+	u8 led_group = led->led_group;
+	u8 port_num = led->port_num;
+	int ret;
+
+	ret = regmap_update_bits(priv->map,
+				 RTL8366RB_LED_X_X_CTRL_REG(led_group),
+				 rtl8366rb_led_group_port_mask(led_group,
+							       port_num),
+				 enable ? 0xffff : 0);
+	if (ret) {
+		dev_err(priv->dev, "error updating LED on port %d group %d\n",
+			led_group, port_num);
+		return ret;
+	}
+
+	/* Change the LED group to manual controlled LEDs if required */
+	ret = rb8366rb_set_ledgroup_mode(priv, led_group,
+					 RTL8366RB_LEDGROUP_FORCE);
+
+	if (ret) {
+		dev_err(priv->dev, "error updating LED GROUP group %d\n",
+			led_group);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int
+rtl8366rb_cled_brightness_set_blocking(struct led_classdev *ldev,
+				       enum led_brightness brightness)
+{
+	struct rtl8366rb_led *led = container_of(ldev, struct rtl8366rb_led,
+						 cdev);
+
+	return rb8366rb_set_port_led(led, brightness == LED_ON);
+}
+
+static int rtl8366rb_setup_led(struct realtek_priv *priv, struct dsa_port *dp,
+			       struct fwnode_handle *led_fwnode)
+{
+	struct rtl8366rb *rb = priv->chip_data;
+	struct led_init_data init_data = { };
+	enum led_default_state state;
+	struct rtl8366rb_led *led;
+	u32 led_group;
+	int ret;
+
+	ret = fwnode_property_read_u32(led_fwnode, "reg", &led_group);
+	if (ret)
+		return ret;
+
+	if (led_group >= RTL8366RB_NUM_LEDGROUPS) {
+		dev_warn(priv->dev, "Invalid LED reg %d defined for port %d",
+			 led_group, dp->index);
+		return -EINVAL;
+	}
+
+	led = &rb->leds[dp->index][led_group];
+	led->port_num = dp->index;
+	led->led_group = led_group;
+	led->priv = priv;
+
+	state = led_init_default_state_get(led_fwnode);
+	switch (state) {
+	case LEDS_DEFSTATE_ON:
+		led->cdev.brightness = 1;
+		rb8366rb_set_port_led(led, 1);
+		break;
+	case LEDS_DEFSTATE_KEEP:
+		led->cdev.brightness =
+			rb8366rb_get_port_led(led);
+		break;
+	case LEDS_DEFSTATE_OFF:
+	default:
+		led->cdev.brightness = 0;
+		rb8366rb_set_port_led(led, 0);
+	}
+
+	led->cdev.max_brightness = 1;
+	led->cdev.brightness_set_blocking =
+		rtl8366rb_cled_brightness_set_blocking;
+	init_data.fwnode = led_fwnode;
+	init_data.devname_mandatory = true;
+
+	init_data.devicename = kasprintf(GFP_KERNEL, "Realtek-%d:0%d:%d",
+					 dp->ds->index, dp->index, led_group);
+	if (!init_data.devicename)
+		return -ENOMEM;
+
+	ret = devm_led_classdev_register_ext(priv->dev, &led->cdev, &init_data);
+	if (ret) {
+		dev_warn(priv->dev, "Failed to init LED %d for port %d",
+			 led_group, dp->index);
+		return ret;
+	}
+
+	return 0;
+}
+
+int rtl8366rb_setup_leds(struct realtek_priv *priv)
+{
+	struct dsa_switch *ds = &priv->ds;
+	struct device_node *leds_np;
+	struct dsa_port *dp;
+	int ret = 0;
+
+	dsa_switch_for_each_port(dp, ds) {
+		if (!dp->dn)
+			continue;
+
+		leds_np = of_get_child_by_name(dp->dn, "leds");
+		if (!leds_np) {
+			dev_dbg(priv->dev, "No leds defined for port %d",
+				dp->index);
+			continue;
+		}
+
+		for_each_child_of_node_scoped(leds_np, led_np) {
+			ret = rtl8366rb_setup_led(priv, dp,
+						  of_fwnode_handle(led_np));
+			if (ret)
+				break;
+		}
+
+		of_node_put(leds_np);
+		if (ret)
+			return ret;
+	}
+	return 0;
+}
diff --git a/drivers/net/dsa/realtek/rtl8366rb.c b/drivers/net/dsa/realtek/rtl8366rb.c
index c7a8cd060587..ae3d49fc22b8 100644
--- a/drivers/net/dsa/realtek/rtl8366rb.c
+++ b/drivers/net/dsa/realtek/rtl8366rb.c
@@ -26,11 +26,7 @@
 #include "realtek-smi.h"
 #include "realtek-mdio.h"
 #include "rtl83xx.h"
-
-#define RTL8366RB_PORT_NUM_CPU		5
-#define RTL8366RB_NUM_PORTS		6
-#define RTL8366RB_PHY_NO_MAX		4
-#define RTL8366RB_PHY_ADDR_MAX		31
+#include "rtl8366rb.h"
 
 /* Switch Global Configuration register */
 #define RTL8366RB_SGCR				0x0000
@@ -175,39 +171,6 @@
  */
 #define RTL8366RB_VLAN_INGRESS_CTRL2_REG	0x037f
 
-/* LED control registers */
-/* The LED blink rate is global; it is used by all triggers in all groups. */
-#define RTL8366RB_LED_BLINKRATE_REG		0x0430
-#define RTL8366RB_LED_BLINKRATE_MASK		0x0007
-#define RTL8366RB_LED_BLINKRATE_28MS		0x0000
-#define RTL8366RB_LED_BLINKRATE_56MS		0x0001
-#define RTL8366RB_LED_BLINKRATE_84MS		0x0002
-#define RTL8366RB_LED_BLINKRATE_111MS		0x0003
-#define RTL8366RB_LED_BLINKRATE_222MS		0x0004
-#define RTL8366RB_LED_BLINKRATE_446MS		0x0005
-
-/* LED trigger event for each group */
-#define RTL8366RB_LED_CTRL_REG			0x0431
-#define RTL8366RB_LED_CTRL_OFFSET(led_group)	\
-	(4 * (led_group))
-#define RTL8366RB_LED_CTRL_MASK(led_group)	\
-	(0xf << RTL8366RB_LED_CTRL_OFFSET(led_group))
-
-/* The RTL8366RB_LED_X_X registers are used to manually set the LED state only
- * when the corresponding LED group in RTL8366RB_LED_CTRL_REG is
- * RTL8366RB_LEDGROUP_FORCE. Otherwise, it is ignored.
- */
-#define RTL8366RB_LED_0_1_CTRL_REG		0x0432
-#define RTL8366RB_LED_2_3_CTRL_REG		0x0433
-#define RTL8366RB_LED_X_X_CTRL_REG(led_group)	\
-	((led_group) <= 1 ? \
-		RTL8366RB_LED_0_1_CTRL_REG : \
-		RTL8366RB_LED_2_3_CTRL_REG)
-#define RTL8366RB_LED_0_X_CTRL_MASK		GENMASK(5, 0)
-#define RTL8366RB_LED_X_1_CTRL_MASK		GENMASK(11, 6)
-#define RTL8366RB_LED_2_X_CTRL_MASK		GENMASK(5, 0)
-#define RTL8366RB_LED_X_3_CTRL_MASK		GENMASK(11, 6)
-
 #define RTL8366RB_MIB_COUNT			33
 #define RTL8366RB_GLOBAL_MIB_COUNT		1
 #define RTL8366RB_MIB_COUNTER_PORT_OFFSET	0x0050
@@ -243,7 +206,6 @@
 #define RTL8366RB_PORT_STATUS_AN_MASK		0x0080
 
 #define RTL8366RB_NUM_VLANS		16
-#define RTL8366RB_NUM_LEDGROUPS		4
 #define RTL8366RB_NUM_VIDS		4096
 #define RTL8366RB_PRIORITYMAX		7
 #define RTL8366RB_NUM_FIDS		8
@@ -350,46 +312,6 @@
 #define RTL8366RB_GREEN_FEATURE_TX	BIT(0)
 #define RTL8366RB_GREEN_FEATURE_RX	BIT(2)
 
-enum rtl8366_ledgroup_mode {
-	RTL8366RB_LEDGROUP_OFF			= 0x0,
-	RTL8366RB_LEDGROUP_DUP_COL		= 0x1,
-	RTL8366RB_LEDGROUP_LINK_ACT		= 0x2,
-	RTL8366RB_LEDGROUP_SPD1000		= 0x3,
-	RTL8366RB_LEDGROUP_SPD100		= 0x4,
-	RTL8366RB_LEDGROUP_SPD10		= 0x5,
-	RTL8366RB_LEDGROUP_SPD1000_ACT		= 0x6,
-	RTL8366RB_LEDGROUP_SPD100_ACT		= 0x7,
-	RTL8366RB_LEDGROUP_SPD10_ACT		= 0x8,
-	RTL8366RB_LEDGROUP_SPD100_10_ACT	= 0x9,
-	RTL8366RB_LEDGROUP_FIBER		= 0xa,
-	RTL8366RB_LEDGROUP_AN_FAULT		= 0xb,
-	RTL8366RB_LEDGROUP_LINK_RX		= 0xc,
-	RTL8366RB_LEDGROUP_LINK_TX		= 0xd,
-	RTL8366RB_LEDGROUP_MASTER		= 0xe,
-	RTL8366RB_LEDGROUP_FORCE		= 0xf,
-
-	__RTL8366RB_LEDGROUP_MODE_MAX
-};
-
-struct rtl8366rb_led {
-	u8 port_num;
-	u8 led_group;
-	struct realtek_priv *priv;
-	struct led_classdev cdev;
-};
-
-/**
- * struct rtl8366rb - RTL8366RB-specific data
- * @max_mtu: per-port max MTU setting
- * @pvid_enabled: if PVID is set for respective port
- * @leds: per-port and per-ledgroup led info
- */
-struct rtl8366rb {
-	unsigned int max_mtu[RTL8366RB_NUM_PORTS];
-	bool pvid_enabled[RTL8366RB_NUM_PORTS];
-	struct rtl8366rb_led leds[RTL8366RB_NUM_PORTS][RTL8366RB_NUM_LEDGROUPS];
-};
-
 static struct rtl8366_mib_counter rtl8366rb_mib_counters[] = {
 	{ 0,  0, 4, "IfInOctets"				},
 	{ 0,  4, 4, "EtherStatsOctets"				},
@@ -830,9 +752,10 @@ static int rtl8366rb_jam_table(const struct rtl8366rb_jam_tbl_entry *jam_table,
 	return 0;
 }
 
-static int rb8366rb_set_ledgroup_mode(struct realtek_priv *priv,
-				      u8 led_group,
-				      enum rtl8366_ledgroup_mode mode)
+/* This code is used also with LEDs disabled */
+int rb8366rb_set_ledgroup_mode(struct realtek_priv *priv,
+			       u8 led_group,
+			       enum rtl8366_ledgroup_mode mode)
 {
 	int ret;
 	u32 val;
@@ -849,144 +772,7 @@ static int rb8366rb_set_ledgroup_mode(struct realtek_priv *priv,
 	return 0;
 }
 
-static inline u32 rtl8366rb_led_group_port_mask(u8 led_group, u8 port)
-{
-	switch (led_group) {
-	case 0:
-		return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port));
-	case 1:
-		return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port));
-	case 2:
-		return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port));
-	case 3:
-		return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port));
-	default:
-		return 0;
-	}
-}
-
-static int rb8366rb_get_port_led(struct rtl8366rb_led *led)
-{
-	struct realtek_priv *priv = led->priv;
-	u8 led_group = led->led_group;
-	u8 port_num = led->port_num;
-	int ret;
-	u32 val;
-
-	ret = regmap_read(priv->map, RTL8366RB_LED_X_X_CTRL_REG(led_group),
-			  &val);
-	if (ret) {
-		dev_err(priv->dev, "error reading LED on port %d group %d\n",
-			led_group, port_num);
-		return ret;
-	}
-
-	return !!(val & rtl8366rb_led_group_port_mask(led_group, port_num));
-}
-
-static int rb8366rb_set_port_led(struct rtl8366rb_led *led, bool enable)
-{
-	struct realtek_priv *priv = led->priv;
-	u8 led_group = led->led_group;
-	u8 port_num = led->port_num;
-	int ret;
-
-	ret = regmap_update_bits(priv->map,
-				 RTL8366RB_LED_X_X_CTRL_REG(led_group),
-				 rtl8366rb_led_group_port_mask(led_group,
-							       port_num),
-				 enable ? 0xffff : 0);
-	if (ret) {
-		dev_err(priv->dev, "error updating LED on port %d group %d\n",
-			led_group, port_num);
-		return ret;
-	}
-
-	/* Change the LED group to manual controlled LEDs if required */
-	ret = rb8366rb_set_ledgroup_mode(priv, led_group,
-					 RTL8366RB_LEDGROUP_FORCE);
-
-	if (ret) {
-		dev_err(priv->dev, "error updating LED GROUP group %d\n",
-			led_group);
-		return ret;
-	}
-
-	return 0;
-}
-
-static int
-rtl8366rb_cled_brightness_set_blocking(struct led_classdev *ldev,
-				       enum led_brightness brightness)
-{
-	struct rtl8366rb_led *led = container_of(ldev, struct rtl8366rb_led,
-						 cdev);
-
-	return rb8366rb_set_port_led(led, brightness == LED_ON);
-}
-
-static int rtl8366rb_setup_led(struct realtek_priv *priv, struct dsa_port *dp,
-			       struct fwnode_handle *led_fwnode)
-{
-	struct rtl8366rb *rb = priv->chip_data;
-	struct led_init_data init_data = { };
-	enum led_default_state state;
-	struct rtl8366rb_led *led;
-	u32 led_group;
-	int ret;
-
-	ret = fwnode_property_read_u32(led_fwnode, "reg", &led_group);
-	if (ret)
-		return ret;
-
-	if (led_group >= RTL8366RB_NUM_LEDGROUPS) {
-		dev_warn(priv->dev, "Invalid LED reg %d defined for port %d",
-			 led_group, dp->index);
-		return -EINVAL;
-	}
-
-	led = &rb->leds[dp->index][led_group];
-	led->port_num = dp->index;
-	led->led_group = led_group;
-	led->priv = priv;
-
-	state = led_init_default_state_get(led_fwnode);
-	switch (state) {
-	case LEDS_DEFSTATE_ON:
-		led->cdev.brightness = 1;
-		rb8366rb_set_port_led(led, 1);
-		break;
-	case LEDS_DEFSTATE_KEEP:
-		led->cdev.brightness =
-			rb8366rb_get_port_led(led);
-		break;
-	case LEDS_DEFSTATE_OFF:
-	default:
-		led->cdev.brightness = 0;
-		rb8366rb_set_port_led(led, 0);
-	}
-
-	led->cdev.max_brightness = 1;
-	led->cdev.brightness_set_blocking =
-		rtl8366rb_cled_brightness_set_blocking;
-	init_data.fwnode = led_fwnode;
-	init_data.devname_mandatory = true;
-
-	init_data.devicename = kasprintf(GFP_KERNEL, "Realtek-%d:0%d:%d",
-					 dp->ds->index, dp->index, led_group);
-	if (!init_data.devicename)
-		return -ENOMEM;
-
-	ret = devm_led_classdev_register_ext(priv->dev, &led->cdev, &init_data);
-	if (ret) {
-		dev_warn(priv->dev, "Failed to init LED %d for port %d",
-			 led_group, dp->index);
-		return ret;
-	}
-
-	return 0;
-}
-
+/* This code is used also with LEDs disabled */
 static int rtl8366rb_setup_all_leds_off(struct realtek_priv *priv)
 {
 	int ret = 0;
@@ -1007,38 +793,6 @@ static int rtl8366rb_setup_all_leds_off(struct realtek_priv *priv)
 	return ret;
 }
 
-static int rtl8366rb_setup_leds(struct realtek_priv *priv)
-{
-	struct dsa_switch *ds = &priv->ds;
-	struct device_node *leds_np;
-	struct dsa_port *dp;
-	int ret = 0;
-
-	dsa_switch_for_each_port(dp, ds) {
-		if (!dp->dn)
-			continue;
-
-		leds_np = of_get_child_by_name(dp->dn, "leds");
-		if (!leds_np) {
-			dev_dbg(priv->dev, "No leds defined for port %d",
-				dp->index);
-			continue;
-		}
-
-		for_each_child_of_node_scoped(leds_np, led_np) {
-			ret = rtl8366rb_setup_led(priv, dp,
-						  of_fwnode_handle(led_np));
-			if (ret)
-				break;
-		}
-
-		of_node_put(leds_np);
-		if (ret)
-			return ret;
-	}
-	return 0;
-}
-
 static int rtl8366rb_setup(struct dsa_switch *ds)
 {
 	struct realtek_priv *priv = ds->priv;
diff --git a/drivers/net/dsa/realtek/rtl8366rb.h b/drivers/net/dsa/realtek/rtl8366rb.h
new file mode 100644
index 000000000000..685ff3275faa
--- /dev/null
+++ b/drivers/net/dsa/realtek/rtl8366rb.h
@@ -0,0 +1,107 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+
+#ifndef _RTL8366RB_H
+#define _RTL8366RB_H
+
+#include "realtek.h"
+
+#define RTL8366RB_PORT_NUM_CPU		5
+#define RTL8366RB_NUM_PORTS		6
+#define RTL8366RB_PHY_NO_MAX		4
+#define RTL8366RB_NUM_LEDGROUPS		4
+#define RTL8366RB_PHY_ADDR_MAX		31
+
+/* LED control registers */
+/* The LED blink rate is global; it is used by all triggers in all groups. */
+#define RTL8366RB_LED_BLINKRATE_REG		0x0430
+#define RTL8366RB_LED_BLINKRATE_MASK		0x0007
+#define RTL8366RB_LED_BLINKRATE_28MS		0x0000
+#define RTL8366RB_LED_BLINKRATE_56MS		0x0001
+#define RTL8366RB_LED_BLINKRATE_84MS		0x0002
+#define RTL8366RB_LED_BLINKRATE_111MS		0x0003
+#define RTL8366RB_LED_BLINKRATE_222MS		0x0004
+#define RTL8366RB_LED_BLINKRATE_446MS		0x0005
+
+/* LED trigger event for each group */
+#define RTL8366RB_LED_CTRL_REG			0x0431
+#define RTL8366RB_LED_CTRL_OFFSET(led_group)	\
+	(4 * (led_group))
+#define RTL8366RB_LED_CTRL_MASK(led_group)	\
+	(0xf << RTL8366RB_LED_CTRL_OFFSET(led_group))
+
+/* The RTL8366RB_LED_X_X registers are used to manually set the LED state only
+ * when the corresponding LED group in RTL8366RB_LED_CTRL_REG is
+ * RTL8366RB_LEDGROUP_FORCE. Otherwise, it is ignored.
+ */
+#define RTL8366RB_LED_0_1_CTRL_REG		0x0432
+#define RTL8366RB_LED_2_3_CTRL_REG		0x0433
+#define RTL8366RB_LED_X_X_CTRL_REG(led_group)	\
+	((led_group) <= 1 ? \
+		RTL8366RB_LED_0_1_CTRL_REG : \
+		RTL8366RB_LED_2_3_CTRL_REG)
+#define RTL8366RB_LED_0_X_CTRL_MASK		GENMASK(5, 0)
+#define RTL8366RB_LED_X_1_CTRL_MASK		GENMASK(11, 6)
+#define RTL8366RB_LED_2_X_CTRL_MASK		GENMASK(5, 0)
+#define RTL8366RB_LED_X_3_CTRL_MASK		GENMASK(11, 6)
+
+enum rtl8366_ledgroup_mode {
+	RTL8366RB_LEDGROUP_OFF			= 0x0,
+	RTL8366RB_LEDGROUP_DUP_COL		= 0x1,
+	RTL8366RB_LEDGROUP_LINK_ACT		= 0x2,
+	RTL8366RB_LEDGROUP_SPD1000		= 0x3,
+	RTL8366RB_LEDGROUP_SPD100		= 0x4,
+	RTL8366RB_LEDGROUP_SPD10		= 0x5,
+	RTL8366RB_LEDGROUP_SPD1000_ACT		= 0x6,
+	RTL8366RB_LEDGROUP_SPD100_ACT		= 0x7,
+	RTL8366RB_LEDGROUP_SPD10_ACT		= 0x8,
+	RTL8366RB_LEDGROUP_SPD100_10_ACT	= 0x9,
+	RTL8366RB_LEDGROUP_FIBER		= 0xa,
+	RTL8366RB_LEDGROUP_AN_FAULT		= 0xb,
+	RTL8366RB_LEDGROUP_LINK_RX		= 0xc,
+	RTL8366RB_LEDGROUP_LINK_TX		= 0xd,
+	RTL8366RB_LEDGROUP_MASTER		= 0xe,
+	RTL8366RB_LEDGROUP_FORCE		= 0xf,
+
+	__RTL8366RB_LEDGROUP_MODE_MAX
+};
+
+#if IS_ENABLED(CONFIG_NET_DSA_REALTEK_RTL8366RB_LEDS)
+
+struct rtl8366rb_led {
+	u8 port_num;
+	u8 led_group;
+	struct realtek_priv *priv;
+	struct led_classdev cdev;
+};
+
+int rtl8366rb_setup_leds(struct realtek_priv *priv);
+
+#else
+
+static inline int rtl8366rb_setup_leds(struct realtek_priv *priv)
+{
+	return 0;
+}
+
+#endif /* IS_ENABLED(CONFIG_LEDS_CLASS) */
+
+/**
+ * struct rtl8366rb - RTL8366RB-specific data
+ * @max_mtu: per-port max MTU setting
+ * @pvid_enabled: if PVID is set for respective port
+ * @leds: per-port and per-ledgroup led info
+ */
+struct rtl8366rb {
+	unsigned int max_mtu[RTL8366RB_NUM_PORTS];
+	bool pvid_enabled[RTL8366RB_NUM_PORTS];
+#if IS_ENABLED(CONFIG_NET_DSA_REALTEK_RTL8366RB_LEDS)
+	struct rtl8366rb_led leds[RTL8366RB_NUM_PORTS][RTL8366RB_NUM_LEDGROUPS];
+#endif
+};
+
+/* This code is used also with LEDs disabled */
+int rb8366rb_set_ledgroup_mode(struct realtek_priv *priv,
+			       u8 led_group,
+			       enum rtl8366_ledgroup_mode mode);
+
+#endif /* _RTL8366RB_H */
diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c
index d0563ef59acf..fbac2a647b20 100644
--- a/drivers/net/dsa/sja1105/sja1105_main.c
+++ b/drivers/net/dsa/sja1105/sja1105_main.c
@@ -2083,6 +2083,7 @@ static void sja1105_bridge_stp_state_set(struct dsa_switch *ds, int port,
 	switch (state) {
 	case BR_STATE_DISABLED:
 	case BR_STATE_BLOCKING:
+	case BR_STATE_LISTENING:
 		/* From UM10944 description of DRPDTAG (why put this there?):
 		 * "Management traffic flows to the port regardless of the state
 		 * of the INGRESS flag". So BPDUs are still be allowed to pass.
@@ -2092,11 +2093,6 @@ static void sja1105_bridge_stp_state_set(struct dsa_switch *ds, int port,
 		mac[port].egress    = false;
 		mac[port].dyn_learn = false;
 		break;
-	case BR_STATE_LISTENING:
-		mac[port].ingress   = true;
-		mac[port].egress    = false;
-		mac[port].dyn_learn = false;
-		break;
 	case BR_STATE_LEARNING:
 		mac[port].ingress   = true;
 		mac[port].egress    = false;
diff --git a/drivers/net/ethernet/agere/et131x.c b/drivers/net/ethernet/agere/et131x.c
index b325e0cef120..c956151adee5 100644
--- a/drivers/net/ethernet/agere/et131x.c
+++ b/drivers/net/ethernet/agere/et131x.c
@@ -2459,6 +2459,10 @@ static int nic_send_packet(struct et131x_adapter *adapter, struct tcb *tcb)
 							  skb->data,
 							  skb_headlen(skb),
 							  DMA_TO_DEVICE);
+				if (dma_mapping_error(&adapter->pdev->dev,
+						      dma_addr))
+					return -ENOMEM;
+
 				desc[frag].addr_lo = lower_32_bits(dma_addr);
 				desc[frag].addr_hi = upper_32_bits(dma_addr);
 				frag++;
@@ -2468,6 +2472,10 @@ static int nic_send_packet(struct et131x_adapter *adapter, struct tcb *tcb)
 							  skb->data,
 							  skb_headlen(skb) / 2,
 							  DMA_TO_DEVICE);
+				if (dma_mapping_error(&adapter->pdev->dev,
+						      dma_addr))
+					return -ENOMEM;
+
 				desc[frag].addr_lo = lower_32_bits(dma_addr);
 				desc[frag].addr_hi = upper_32_bits(dma_addr);
 				frag++;
@@ -2478,6 +2486,10 @@ static int nic_send_packet(struct et131x_adapter *adapter, struct tcb *tcb)
 							  skb_headlen(skb) / 2,
 							  skb_headlen(skb) / 2,
 							  DMA_TO_DEVICE);
+				if (dma_mapping_error(&adapter->pdev->dev,
+						      dma_addr))
+					goto unmap_first_out;
+
 				desc[frag].addr_lo = lower_32_bits(dma_addr);
 				desc[frag].addr_hi = upper_32_bits(dma_addr);
 				frag++;
@@ -2489,6 +2501,9 @@ static int nic_send_packet(struct et131x_adapter *adapter, struct tcb *tcb)
 						    0,
 						    desc[frag].len_vlan,
 						    DMA_TO_DEVICE);
+			if (dma_mapping_error(&adapter->pdev->dev, dma_addr))
+				goto unmap_out;
+
 			desc[frag].addr_lo = lower_32_bits(dma_addr);
 			desc[frag].addr_hi = upper_32_bits(dma_addr);
 			frag++;
@@ -2578,6 +2593,27 @@ static int nic_send_packet(struct et131x_adapter *adapter, struct tcb *tcb)
 		       &adapter->regs->global.watchdog_timer);
 	}
 	return 0;
+
+unmap_out:
+	// Unmap the body of the packet with map_page
+	while (--i) {
+		frag--;
+		dma_addr = desc[frag].addr_lo;
+		dma_addr |= (u64)desc[frag].addr_hi << 32;
+		dma_unmap_page(&adapter->pdev->dev, dma_addr,
+			       desc[frag].len_vlan, DMA_TO_DEVICE);
+	}
+
+unmap_first_out:
+	// Unmap the header with map_single
+	while (frag--) {
+		dma_addr = desc[frag].addr_lo;
+		dma_addr |= (u64)desc[frag].addr_hi << 32;
+		dma_unmap_single(&adapter->pdev->dev, dma_addr,
+				 desc[frag].len_vlan, DMA_TO_DEVICE);
+	}
+
+	return -ENOMEM;
 }
 
 static int send_packet(struct sk_buff *skb, struct et131x_adapter *adapter)
diff --git a/drivers/net/ethernet/amd/pds_core/adminq.c b/drivers/net/ethernet/amd/pds_core/adminq.c
index c83a0a80d533..506f682d15c1 100644
--- a/drivers/net/ethernet/amd/pds_core/adminq.c
+++ b/drivers/net/ethernet/amd/pds_core/adminq.c
@@ -5,11 +5,6 @@
 
 #include "core.h"
 
-struct pdsc_wait_context {
-	struct pdsc_qcq *qcq;
-	struct completion wait_completion;
-};
-
 static int pdsc_process_notifyq(struct pdsc_qcq *qcq)
 {
 	union pds_core_notifyq_comp *comp;
@@ -109,10 +104,10 @@ void pdsc_process_adminq(struct pdsc_qcq *qcq)
 		q_info = &q->info[q->tail_idx];
 		q->tail_idx = (q->tail_idx + 1) & (q->num_descs - 1);
 
-		/* Copy out the completion data */
-		memcpy(q_info->dest, comp, sizeof(*comp));
-
-		complete_all(&q_info->wc->wait_completion);
+		if (!completion_done(&q_info->completion)) {
+			memcpy(q_info->dest, comp, sizeof(*comp));
+			complete(&q_info->completion);
+		}
 
 		if (cq->tail_idx == cq->num_descs - 1)
 			cq->done_color = !cq->done_color;
@@ -162,8 +157,7 @@ irqreturn_t pdsc_adminq_isr(int irq, void *data)
 static int __pdsc_adminq_post(struct pdsc *pdsc,
 			      struct pdsc_qcq *qcq,
 			      union pds_core_adminq_cmd *cmd,
-			      union pds_core_adminq_comp *comp,
-			      struct pdsc_wait_context *wc)
+			      union pds_core_adminq_comp *comp)
 {
 	struct pdsc_queue *q = &qcq->q;
 	struct pdsc_q_info *q_info;
@@ -205,9 +199,9 @@ static int __pdsc_adminq_post(struct pdsc *pdsc,
 	/* Post the request */
 	index = q->head_idx;
 	q_info = &q->info[index];
-	q_info->wc = wc;
 	q_info->dest = comp;
 	memcpy(q_info->desc, cmd, sizeof(*cmd));
+	reinit_completion(&q_info->completion);
 
 	dev_dbg(pdsc->dev, "head_idx %d tail_idx %d\n",
 		q->head_idx, q->tail_idx);
@@ -231,16 +225,13 @@ int pdsc_adminq_post(struct pdsc *pdsc,
 		     union pds_core_adminq_comp *comp,
 		     bool fast_poll)
 {
-	struct pdsc_wait_context wc = {
-		.wait_completion =
-			COMPLETION_INITIALIZER_ONSTACK(wc.wait_completion),
-	};
 	unsigned long poll_interval = 1;
 	unsigned long poll_jiffies;
 	unsigned long time_limit;
 	unsigned long time_start;
 	unsigned long time_done;
 	unsigned long remaining;
+	struct completion *wc;
 	int err = 0;
 	int index;
 
@@ -250,20 +241,19 @@ int pdsc_adminq_post(struct pdsc *pdsc,
 		return -ENXIO;
 	}
 
-	wc.qcq = &pdsc->adminqcq;
-	index = __pdsc_adminq_post(pdsc, &pdsc->adminqcq, cmd, comp, &wc);
+	index = __pdsc_adminq_post(pdsc, &pdsc->adminqcq, cmd, comp);
 	if (index < 0) {
 		err = index;
 		goto err_out;
 	}
 
+	wc = &pdsc->adminqcq.q.info[index].completion;
 	time_start = jiffies;
 	time_limit = time_start + HZ * pdsc->devcmd_timeout;
 	do {
 		/* Timeslice the actual wait to catch IO errors etc early */
 		poll_jiffies = msecs_to_jiffies(poll_interval);
-		remaining = wait_for_completion_timeout(&wc.wait_completion,
-							poll_jiffies);
+		remaining = wait_for_completion_timeout(wc, poll_jiffies);
 		if (remaining)
 			break;
 
@@ -292,9 +282,11 @@ int pdsc_adminq_post(struct pdsc *pdsc,
 	dev_dbg(pdsc->dev, "%s: elapsed %d msecs\n",
 		__func__, jiffies_to_msecs(time_done - time_start));
 
-	/* Check the results */
-	if (time_after_eq(time_done, time_limit))
+	/* Check the results and clear an un-completed timeout */
+	if (time_after_eq(time_done, time_limit) && !completion_done(wc)) {
 		err = -ETIMEDOUT;
+		complete(wc);
+	}
 
 	dev_dbg(pdsc->dev, "read admin queue completion idx %d:\n", index);
 	dynamic_hex_dump("comp ", DUMP_PREFIX_OFFSET, 16, 1,
diff --git a/drivers/net/ethernet/amd/pds_core/auxbus.c b/drivers/net/ethernet/amd/pds_core/auxbus.c
index 2babea110991..889a18962270 100644
--- a/drivers/net/ethernet/amd/pds_core/auxbus.c
+++ b/drivers/net/ethernet/amd/pds_core/auxbus.c
@@ -107,9 +107,6 @@ int pds_client_adminq_cmd(struct pds_auxiliary_dev *padev,
 	dev_dbg(pf->dev, "%s: %s opcode %d\n",
 		__func__, dev_name(&padev->aux_dev.dev), req->opcode);
 
-	if (pf->state)
-		return -ENXIO;
-
 	/* Wrap the client's request */
 	cmd.client_request.opcode = PDS_AQ_CMD_CLIENT_CMD;
 	cmd.client_request.client_id = cpu_to_le16(padev->client_id);
@@ -175,34 +172,31 @@ static struct pds_auxiliary_dev *pdsc_auxbus_dev_register(struct pdsc *cf,
 	return padev;
 }
 
-int pdsc_auxbus_dev_del(struct pdsc *cf, struct pdsc *pf)
+void pdsc_auxbus_dev_del(struct pdsc *cf, struct pdsc *pf,
+			 struct pds_auxiliary_dev **pd_ptr)
 {
 	struct pds_auxiliary_dev *padev;
-	int err = 0;
 
-	if (!cf)
-		return -ENODEV;
+	if (!*pd_ptr)
+		return;
 
 	mutex_lock(&pf->config_lock);
 
-	padev = pf->vfs[cf->vf_id].padev;
-	if (padev) {
-		pds_client_unregister(pf, padev->client_id);
-		auxiliary_device_delete(&padev->aux_dev);
-		auxiliary_device_uninit(&padev->aux_dev);
-		padev->client_id = 0;
-	}
-	pf->vfs[cf->vf_id].padev = NULL;
+	padev = *pd_ptr;
+	pds_client_unregister(pf, padev->client_id);
+	auxiliary_device_delete(&padev->aux_dev);
+	auxiliary_device_uninit(&padev->aux_dev);
+	*pd_ptr = NULL;
 
 	mutex_unlock(&pf->config_lock);
-	return err;
 }
 
-int pdsc_auxbus_dev_add(struct pdsc *cf, struct pdsc *pf)
+int pdsc_auxbus_dev_add(struct pdsc *cf, struct pdsc *pf,
+			enum pds_core_vif_types vt,
+			struct pds_auxiliary_dev **pd_ptr)
 {
 	struct pds_auxiliary_dev *padev;
 	char devname[PDS_DEVNAME_LEN];
-	enum pds_core_vif_types vt;
 	unsigned long mask;
 	u16 vt_support;
 	int client_id;
@@ -211,6 +205,9 @@ int pdsc_auxbus_dev_add(struct pdsc *cf, struct pdsc *pf)
 	if (!cf)
 		return -ENODEV;
 
+	if (vt >= PDS_DEV_TYPE_MAX)
+		return -EINVAL;
+
 	mutex_lock(&pf->config_lock);
 
 	mask = BIT_ULL(PDSC_S_FW_DEAD) |
@@ -222,17 +219,10 @@ int pdsc_auxbus_dev_add(struct pdsc *cf, struct pdsc *pf)
 		goto out_unlock;
 	}
 
-	/* We only support vDPA so far, so it is the only one to
-	 * be verified that it is available in the Core device and
-	 * enabled in the devlink param.  In the future this might
-	 * become a loop for several VIF types.
-	 */
-
 	/* Verify that the type is supported and enabled.  It is not
 	 * an error if there is no auxbus device support for this
 	 * VF, it just means something else needs to happen with it.
 	 */
-	vt = PDS_DEV_TYPE_VDPA;
 	vt_support = !!le16_to_cpu(pf->dev_ident.vif_types[vt]);
 	if (!(vt_support &&
 	      pf->viftype_status[vt].supported &&
@@ -258,7 +248,7 @@ int pdsc_auxbus_dev_add(struct pdsc *cf, struct pdsc *pf)
 		err = PTR_ERR(padev);
 		goto out_unlock;
 	}
-	pf->vfs[cf->vf_id].padev = padev;
+	*pd_ptr = padev;
 
 out_unlock:
 	mutex_unlock(&pf->config_lock);
diff --git a/drivers/net/ethernet/amd/pds_core/core.c b/drivers/net/ethernet/amd/pds_core/core.c
index 536635e57727..3c60d4cf9d0e 100644
--- a/drivers/net/ethernet/amd/pds_core/core.c
+++ b/drivers/net/ethernet/amd/pds_core/core.c
@@ -167,8 +167,10 @@ static void pdsc_q_map(struct pdsc_queue *q, void *base, dma_addr_t base_pa)
 	q->base = base;
 	q->base_pa = base_pa;
 
-	for (i = 0, cur = q->info; i < q->num_descs; i++, cur++)
+	for (i = 0, cur = q->info; i < q->num_descs; i++, cur++) {
 		cur->desc = base + (i * q->desc_size);
+		init_completion(&cur->completion);
+	}
 }
 
 static void pdsc_cq_map(struct pdsc_cq *cq, void *base, dma_addr_t base_pa)
@@ -325,10 +327,7 @@ static int pdsc_core_init(struct pdsc *pdsc)
 	size_t sz;
 	int err;
 
-	/* Scale the descriptor ring length based on number of CPUs and VFs */
-	numdescs = max_t(int, PDSC_ADMINQ_MIN_LENGTH, num_online_cpus());
-	numdescs += 2 * pci_sriov_get_totalvfs(pdsc->pdev);
-	numdescs = roundup_pow_of_two(numdescs);
+	numdescs = PDSC_ADMINQ_MAX_LENGTH;
 	err = pdsc_qcq_alloc(pdsc, PDS_CORE_QTYPE_ADMINQ, 0, "adminq",
 			     PDS_CORE_QCQ_F_CORE | PDS_CORE_QCQ_F_INTR,
 			     numdescs,
diff --git a/drivers/net/ethernet/amd/pds_core/core.h b/drivers/net/ethernet/amd/pds_core/core.h
index 14522d6d5f86..becd3104473c 100644
--- a/drivers/net/ethernet/amd/pds_core/core.h
+++ b/drivers/net/ethernet/amd/pds_core/core.h
@@ -16,7 +16,7 @@
 
 #define PDSC_WATCHDOG_SECS	5
 #define PDSC_QUEUE_NAME_MAX_SZ  16
-#define PDSC_ADMINQ_MIN_LENGTH	16	/* must be a power of two */
+#define PDSC_ADMINQ_MAX_LENGTH	16	/* must be a power of two */
 #define PDSC_NOTIFYQ_LENGTH	64	/* must be a power of two */
 #define PDSC_TEARDOWN_RECOVERY	false
 #define PDSC_TEARDOWN_REMOVING	true
@@ -96,7 +96,7 @@ struct pdsc_q_info {
 	unsigned int bytes;
 	unsigned int nbufs;
 	struct pdsc_buf_info bufs[PDS_CORE_MAX_FRAGS];
-	struct pdsc_wait_context *wc;
+	struct completion completion;
 	void *dest;
 };
 
@@ -303,8 +303,11 @@ void pdsc_health_thread(struct work_struct *work);
 int pdsc_register_notify(struct notifier_block *nb);
 void pdsc_unregister_notify(struct notifier_block *nb);
 void pdsc_notify(unsigned long event, void *data);
-int pdsc_auxbus_dev_add(struct pdsc *cf, struct pdsc *pf);
-int pdsc_auxbus_dev_del(struct pdsc *cf, struct pdsc *pf);
+int pdsc_auxbus_dev_add(struct pdsc *cf, struct pdsc *pf,
+			enum pds_core_vif_types vt,
+			struct pds_auxiliary_dev **pd_ptr);
+void pdsc_auxbus_dev_del(struct pdsc *cf, struct pdsc *pf,
+			 struct pds_auxiliary_dev **pd_ptr);
 
 void pdsc_process_adminq(struct pdsc_qcq *qcq);
 void pdsc_work_thread(struct work_struct *work);
diff --git a/drivers/net/ethernet/amd/pds_core/debugfs.c b/drivers/net/ethernet/amd/pds_core/debugfs.c
index ac37a4e738ae..04c5e3abd8d7 100644
--- a/drivers/net/ethernet/amd/pds_core/debugfs.c
+++ b/drivers/net/ethernet/amd/pds_core/debugfs.c
@@ -154,8 +154,9 @@ void pdsc_debugfs_add_qcq(struct pdsc *pdsc, struct pdsc_qcq *qcq)
 		debugfs_create_u32("index", 0400, intr_dentry, &intr->index);
 		debugfs_create_u32("vector", 0400, intr_dentry, &intr->vector);
 
-		intr_ctrl_regset = kzalloc(sizeof(*intr_ctrl_regset),
-					   GFP_KERNEL);
+		intr_ctrl_regset = devm_kzalloc(pdsc->dev,
+						sizeof(*intr_ctrl_regset),
+						GFP_KERNEL);
 		if (!intr_ctrl_regset)
 			return;
 		intr_ctrl_regset->regs = intr_ctrl_regs;
diff --git a/drivers/net/ethernet/amd/pds_core/devlink.c b/drivers/net/ethernet/amd/pds_core/devlink.c
index 44971e71991f..d8dc39da4161 100644
--- a/drivers/net/ethernet/amd/pds_core/devlink.c
+++ b/drivers/net/ethernet/amd/pds_core/devlink.c
@@ -56,8 +56,11 @@ int pdsc_dl_enable_set(struct devlink *dl, u32 id,
 	for (vf_id = 0; vf_id < pdsc->num_vfs; vf_id++) {
 		struct pdsc *vf = pdsc->vfs[vf_id].vf;
 
-		err = ctx->val.vbool ? pdsc_auxbus_dev_add(vf, pdsc) :
-				       pdsc_auxbus_dev_del(vf, pdsc);
+		if (ctx->val.vbool)
+			err = pdsc_auxbus_dev_add(vf, pdsc, vt_entry->vif_id,
+						  &pdsc->vfs[vf_id].padev);
+		else
+			pdsc_auxbus_dev_del(vf, pdsc, &pdsc->vfs[vf_id].padev);
 	}
 
 	return err;
@@ -102,7 +105,7 @@ int pdsc_dl_info_get(struct devlink *dl, struct devlink_info_req *req,
 		.fw_control.opcode = PDS_CORE_CMD_FW_CONTROL,
 		.fw_control.oper = PDS_CORE_FW_GET_LIST,
 	};
-	struct pds_core_fw_list_info fw_list;
+	struct pds_core_fw_list_info fw_list = {};
 	struct pdsc *pdsc = devlink_priv(dl);
 	union pds_core_dev_comp comp;
 	char buf[32];
@@ -115,8 +118,6 @@ int pdsc_dl_info_get(struct devlink *dl, struct devlink_info_req *req,
 	if (!err)
 		memcpy_fromio(&fw_list, pdsc->cmd_regs->data, sizeof(fw_list));
 	mutex_unlock(&pdsc->devcmd_lock);
-	if (err && err != -EIO)
-		return err;
 
 	listlen = min(fw_list.num_fw_slots, ARRAY_SIZE(fw_list.fw_names));
 	for (i = 0; i < listlen; i++) {
diff --git a/drivers/net/ethernet/amd/pds_core/main.c b/drivers/net/ethernet/amd/pds_core/main.c
index 660268ff9562..a3a68889137b 100644
--- a/drivers/net/ethernet/amd/pds_core/main.c
+++ b/drivers/net/ethernet/amd/pds_core/main.c
@@ -190,7 +190,8 @@ static int pdsc_init_vf(struct pdsc *vf)
 	devl_unlock(dl);
 
 	pf->vfs[vf->vf_id].vf = vf;
-	err = pdsc_auxbus_dev_add(vf, pf);
+	err = pdsc_auxbus_dev_add(vf, pf, PDS_DEV_TYPE_VDPA,
+				  &pf->vfs[vf->vf_id].padev);
 	if (err) {
 		devl_lock(dl);
 		devl_unregister(dl);
@@ -417,7 +418,7 @@ static void pdsc_remove(struct pci_dev *pdev)
 
 		pf = pdsc_get_pf_struct(pdsc->pdev);
 		if (!IS_ERR(pf)) {
-			pdsc_auxbus_dev_del(pdsc, pf);
+			pdsc_auxbus_dev_del(pdsc, pf, &pf->vfs[pdsc->vf_id].padev);
 			pf->vfs[pdsc->vf_id].vf = NULL;
 		}
 	} else {
@@ -482,7 +483,8 @@ static void pdsc_reset_prepare(struct pci_dev *pdev)
 
 		pf = pdsc_get_pf_struct(pdsc->pdev);
 		if (!IS_ERR(pf))
-			pdsc_auxbus_dev_del(pdsc, pf);
+			pdsc_auxbus_dev_del(pdsc, pf,
+					    &pf->vfs[pdsc->vf_id].padev);
 	}
 
 	pdsc_unmap_bars(pdsc);
@@ -527,7 +529,8 @@ static void pdsc_reset_done(struct pci_dev *pdev)
 
 		pf = pdsc_get_pf_struct(pdsc->pdev);
 		if (!IS_ERR(pf))
-			pdsc_auxbus_dev_add(pdsc, pf);
+			pdsc_auxbus_dev_add(pdsc, pf, PDS_DEV_TYPE_VDPA,
+					    &pf->vfs[pdsc->vf_id].padev);
 	}
 }
 
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-common.h b/drivers/net/ethernet/amd/xgbe/xgbe-common.h
index 3b70f6737633..aa25a8a0a106 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-common.h
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-common.h
@@ -1373,6 +1373,8 @@
 #define MDIO_VEND2_CTRL1_SS13		BIT(13)
 #endif
 
+#define XGBE_VEND2_MAC_AUTO_SW		BIT(9)
+
 /* MDIO mask values */
 #define XGBE_AN_CL73_INT_CMPLT		BIT(0)
 #define XGBE_AN_CL73_INC_LINK		BIT(1)
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-desc.c b/drivers/net/ethernet/amd/xgbe/xgbe-desc.c
index 230726d7b74f..d41b58fad37b 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-desc.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-desc.c
@@ -373,8 +373,13 @@ static int xgbe_map_rx_buffer(struct xgbe_prv_data *pdata,
 	}
 
 	/* Set up the header page info */
-	xgbe_set_buffer_data(&rdata->rx.hdr, &ring->rx_hdr_pa,
-			     XGBE_SKB_ALLOC_SIZE);
+	if (pdata->netdev->features & NETIF_F_RXCSUM) {
+		xgbe_set_buffer_data(&rdata->rx.hdr, &ring->rx_hdr_pa,
+				     XGBE_SKB_ALLOC_SIZE);
+	} else {
+		xgbe_set_buffer_data(&rdata->rx.hdr, &ring->rx_hdr_pa,
+				     pdata->rx_buf_size);
+	}
 
 	/* Set up the buffer page info */
 	xgbe_set_buffer_data(&rdata->rx.buf, &ring->rx_buf_pa,
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
index f393228d41c7..f1b0fb02b3cd 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
@@ -320,6 +320,18 @@ static void xgbe_config_sph_mode(struct xgbe_prv_data *pdata)
 	XGMAC_IOWRITE_BITS(pdata, MAC_RCR, HDSMS, XGBE_SPH_HDSMS_SIZE);
 }
 
+static void xgbe_disable_sph_mode(struct xgbe_prv_data *pdata)
+{
+	unsigned int i;
+
+	for (i = 0; i < pdata->channel_count; i++) {
+		if (!pdata->channel[i]->rx_ring)
+			break;
+
+		XGMAC_DMA_IOWRITE_BITS(pdata->channel[i], DMA_CH_CR, SPH, 0);
+	}
+}
+
 static int xgbe_write_rss_reg(struct xgbe_prv_data *pdata, unsigned int type,
 			      unsigned int index, unsigned int val)
 {
@@ -3545,8 +3557,12 @@ static int xgbe_init(struct xgbe_prv_data *pdata)
 	xgbe_config_tx_coalesce(pdata);
 	xgbe_config_rx_buffer_size(pdata);
 	xgbe_config_tso_mode(pdata);
-	xgbe_config_sph_mode(pdata);
-	xgbe_config_rss(pdata);
+
+	if (pdata->netdev->features & NETIF_F_RXCSUM) {
+		xgbe_config_sph_mode(pdata);
+		xgbe_config_rss(pdata);
+	}
+
 	desc_if->wrapper_tx_desc_init(pdata);
 	desc_if->wrapper_rx_desc_init(pdata);
 	xgbe_enable_dma_interrupts(pdata);
@@ -3702,5 +3718,9 @@ void xgbe_init_function_ptrs_dev(struct xgbe_hw_if *hw_if)
 	hw_if->disable_vxlan = xgbe_disable_vxlan;
 	hw_if->set_vxlan_id = xgbe_set_vxlan_id;
 
+	/* For Split Header*/
+	hw_if->enable_sph = xgbe_config_sph_mode;
+	hw_if->disable_sph = xgbe_disable_sph_mode;
+
 	DBGPR("<--xgbe_init_function_ptrs\n");
 }
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
index 5475867708f4..8bc49259d71a 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
@@ -2257,10 +2257,17 @@ static int xgbe_set_features(struct net_device *netdev,
 	if (ret)
 		return ret;
 
-	if ((features & NETIF_F_RXCSUM) && !rxcsum)
+	if ((features & NETIF_F_RXCSUM) && !rxcsum) {
+		hw_if->enable_sph(pdata);
+		hw_if->enable_vxlan(pdata);
 		hw_if->enable_rx_csum(pdata);
-	else if (!(features & NETIF_F_RXCSUM) && rxcsum)
+		schedule_work(&pdata->restart_work);
+	} else if (!(features & NETIF_F_RXCSUM) && rxcsum) {
+		hw_if->disable_sph(pdata);
+		hw_if->disable_vxlan(pdata);
 		hw_if->disable_rx_csum(pdata);
+		schedule_work(&pdata->restart_work);
+	}
 
 	if ((features & NETIF_F_HW_VLAN_CTAG_RX) && !rxvlan)
 		hw_if->enable_rx_vlan_stripping(pdata);
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
index 07f4f3418d01..ed76a8df6ec6 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
@@ -375,6 +375,10 @@ static void xgbe_an37_set(struct xgbe_prv_data *pdata, bool enable,
 		reg |= MDIO_VEND2_CTRL1_AN_RESTART;
 
 	XMDIO_WRITE(pdata, MDIO_MMD_VEND2, MDIO_CTRL1, reg);
+
+	reg = XMDIO_READ(pdata, MDIO_MMD_VEND2, MDIO_PCS_DIG_CTRL);
+	reg |= XGBE_VEND2_MAC_AUTO_SW;
+	XMDIO_WRITE(pdata, MDIO_MMD_VEND2, MDIO_PCS_DIG_CTRL, reg);
 }
 
 static void xgbe_an37_restart(struct xgbe_prv_data *pdata)
@@ -1003,6 +1007,11 @@ static void xgbe_an37_init(struct xgbe_prv_data *pdata)
 
 	netif_dbg(pdata, link, pdata->netdev, "CL37 AN (%s) initialized\n",
 		  (pdata->an_mode == XGBE_AN_MODE_CL37) ? "BaseX" : "SGMII");
+
+	reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_CTRL1);
+	reg &= ~MDIO_AN_CTRL1_ENABLE;
+	XMDIO_WRITE(pdata, MDIO_MMD_AN, MDIO_CTRL1, reg);
+
 }
 
 static void xgbe_an73_init(struct xgbe_prv_data *pdata)
@@ -1404,6 +1413,10 @@ static void xgbe_phy_status(struct xgbe_prv_data *pdata)
 
 	pdata->phy.link = pdata->phy_if.phy_impl.link_status(pdata,
 							     &an_restart);
+	/* bail out if the link status register read fails */
+	if (pdata->phy.link < 0)
+		return;
+
 	if (an_restart) {
 		xgbe_phy_config_aneg(pdata);
 		goto adjust_link;
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
index 268399dfcf22..32e633d11348 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
@@ -2855,8 +2855,7 @@ static bool xgbe_phy_valid_speed(struct xgbe_prv_data *pdata, int speed)
 static int xgbe_phy_link_status(struct xgbe_prv_data *pdata, int *an_restart)
 {
 	struct xgbe_phy_data *phy_data = pdata->phy_data;
-	unsigned int reg;
-	int ret;
+	int reg, ret;
 
 	*an_restart = 0;
 
@@ -2890,11 +2889,20 @@ static int xgbe_phy_link_status(struct xgbe_prv_data *pdata, int *an_restart)
 			return 0;
 	}
 
-	/* Link status is latched low, so read once to clear
-	 * and then read again to get current state
-	 */
-	reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_STAT1);
 	reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_STAT1);
+	if (reg < 0)
+		return reg;
+
+	/* Link status is latched low so that momentary link drops
+	 * can be detected. If link was already down read again
+	 * to get the latest state.
+	 */
+
+	if (!pdata->phy.link && !(reg & MDIO_STAT1_LSTATUS)) {
+		reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_STAT1);
+		if (reg < 0)
+			return reg;
+	}
 
 	if (pdata->en_rx_adap) {
 		/* if the link is available and adaptation is done,
@@ -2913,9 +2921,7 @@ static int xgbe_phy_link_status(struct xgbe_prv_data *pdata, int *an_restart)
 			xgbe_phy_set_mode(pdata, phy_data->cur_mode);
 		}
 
-		/* check again for the link and adaptation status */
-		reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_STAT1);
-		if ((reg & MDIO_STAT1_LSTATUS) && pdata->rx_adapt_done)
+		if (pdata->rx_adapt_done)
 			return 1;
 	} else if (reg & MDIO_STAT1_LSTATUS)
 		return 1;
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h
index d85386cac8d1..7526a0906b39 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe.h
+++ b/drivers/net/ethernet/amd/xgbe/xgbe.h
@@ -292,12 +292,12 @@
 #define XGBE_LINK_TIMEOUT		5
 #define XGBE_KR_TRAINING_WAIT_ITER	50
 
-#define XGBE_SGMII_AN_LINK_STATUS	BIT(1)
+#define XGBE_SGMII_AN_LINK_DUPLEX	BIT(1)
 #define XGBE_SGMII_AN_LINK_SPEED	(BIT(2) | BIT(3))
 #define XGBE_SGMII_AN_LINK_SPEED_10	0x00
 #define XGBE_SGMII_AN_LINK_SPEED_100	0x04
 #define XGBE_SGMII_AN_LINK_SPEED_1000	0x08
-#define XGBE_SGMII_AN_LINK_DUPLEX	BIT(4)
+#define XGBE_SGMII_AN_LINK_STATUS	BIT(4)
 
 /* ECC correctable error notification window (seconds) */
 #define XGBE_ECC_LIMIT			60
@@ -865,6 +865,10 @@ struct xgbe_hw_if {
 	void (*enable_vxlan)(struct xgbe_prv_data *);
 	void (*disable_vxlan)(struct xgbe_prv_data *);
 	void (*set_vxlan_id)(struct xgbe_prv_data *);
+
+	/* For Split Header */
+	void (*enable_sph)(struct xgbe_prv_data *pdata);
+	void (*disable_sph)(struct xgbe_prv_data *pdata);
 };
 
 /* This structure represents implementation specific routines for an
diff --git a/drivers/net/ethernet/apm/xgene-v2/main.c b/drivers/net/ethernet/apm/xgene-v2/main.c
index 9e90c2381491..68335935cea7 100644
--- a/drivers/net/ethernet/apm/xgene-v2/main.c
+++ b/drivers/net/ethernet/apm/xgene-v2/main.c
@@ -9,8 +9,6 @@
 
 #include "main.h"
 
-static const struct acpi_device_id xge_acpi_match[];
-
 static int xge_get_resources(struct xge_pdata *pdata)
 {
 	struct platform_device *pdev;
@@ -731,7 +729,7 @@ MODULE_DEVICE_TABLE(acpi, xge_acpi_match);
 static struct platform_driver xge_driver = {
 	.driver = {
 		   .name = "xgene-enet-v2",
-		   .acpi_match_table = ACPI_PTR(xge_acpi_match),
+		   .acpi_match_table = xge_acpi_match,
 	},
 	.probe = xge_probe,
 	.remove_new = xge_remove,
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
index f010bda61c96..2cd0352a11f4 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
@@ -113,6 +113,8 @@ struct aq_stats_s {
 #define AQ_HW_POWER_STATE_D0   0U
 #define AQ_HW_POWER_STATE_D3   3U
 
+#define	AQ_FW_WAKE_ON_LINK_RTPM BIT(10)
+
 #define AQ_HW_FLAG_STARTED     0x00000004U
 #define AQ_HW_FLAG_STOPPING    0x00000008U
 #define AQ_HW_FLAG_RESETTING   0x00000010U
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_main.c b/drivers/net/ethernet/aquantia/atlantic/aq_main.c
index c1d1673c5749..b565189e5913 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_main.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_main.c
@@ -123,7 +123,6 @@ static netdev_tx_t aq_ndev_start_xmit(struct sk_buff *skb, struct net_device *nd
 	}
 #endif
 
-	skb_tx_timestamp(skb);
 	return aq_nic_xmit(aq_nic, skb);
 }
 
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
index fe0e3e2a8117..b0994bd05874 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
@@ -898,6 +898,8 @@ int aq_nic_xmit(struct aq_nic_s *self, struct sk_buff *skb)
 
 	frags = aq_nic_map_skb(self, skb, ring);
 
+	skb_tx_timestamp(skb);
+
 	if (likely(frags)) {
 		err = self->aq_hw_ops->hw_ring_tx_xmit(self->aq_hw,
 						       ring, frags);
@@ -1441,7 +1443,9 @@ void aq_nic_deinit(struct aq_nic_s *self, bool link_down)
 	aq_ptp_ring_free(self);
 	aq_ptp_free(self);
 
-	if (likely(self->aq_fw_ops->deinit) && link_down) {
+	/* May be invoked during hot unplug. */
+	if (pci_device_is_present(self->pdev) &&
+	    likely(self->aq_fw_ops->deinit) && link_down) {
 		mutex_lock(&self->fwreq_mutex);
 		self->aq_fw_ops->deinit(self->aq_hw);
 		mutex_unlock(&self->fwreq_mutex);
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils_fw.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils_fw.c
index 52e2070a4a2f..7370e3f76b62 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils_fw.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils_fw.c
@@ -462,6 +462,44 @@ static int aq_a2_fw_get_mac_temp(struct aq_hw_s *self, int *temp)
 	return aq_a2_fw_get_phy_temp(self, temp);
 }
 
+static int aq_a2_fw_set_wol_params(struct aq_hw_s *self, const u8 *mac, u32 wol)
+{
+	struct mac_address_aligned_s mac_address;
+	struct link_control_s link_control;
+	struct wake_on_lan_s wake_on_lan;
+
+	memcpy(mac_address.aligned.mac_address, mac, ETH_ALEN);
+	hw_atl2_shared_buffer_write(self, mac_address, mac_address);
+
+	memset(&wake_on_lan, 0, sizeof(wake_on_lan));
+
+	if (wol & WAKE_MAGIC)
+		wake_on_lan.wake_on_magic_packet = 1U;
+
+	if (wol & (WAKE_PHY | AQ_FW_WAKE_ON_LINK_RTPM))
+		wake_on_lan.wake_on_link_up = 1U;
+
+	hw_atl2_shared_buffer_write(self, sleep_proxy, wake_on_lan);
+
+	hw_atl2_shared_buffer_get(self, link_control, link_control);
+	link_control.mode = AQ_HOST_MODE_SLEEP_PROXY;
+	hw_atl2_shared_buffer_write(self, link_control, link_control);
+
+	return hw_atl2_shared_buffer_finish_ack(self);
+}
+
+static int aq_a2_fw_set_power(struct aq_hw_s *self, unsigned int power_state,
+			      const u8 *mac)
+{
+	u32 wol = self->aq_nic_cfg->wol;
+	int err = 0;
+
+	if (wol)
+		err = aq_a2_fw_set_wol_params(self, mac, wol);
+
+	return err;
+}
+
 static int aq_a2_fw_set_eee_rate(struct aq_hw_s *self, u32 speed)
 {
 	struct link_options_s link_options;
@@ -605,6 +643,7 @@ const struct aq_fw_ops aq_a2_fw_ops = {
 	.set_state          = aq_a2_fw_set_state,
 	.update_link_status = aq_a2_fw_update_link_status,
 	.update_stats       = aq_a2_fw_update_stats,
+	.set_power          = aq_a2_fw_set_power,
 	.get_mac_temp       = aq_a2_fw_get_mac_temp,
 	.get_phy_temp       = aq_a2_fw_get_phy_temp,
 	.set_eee_rate       = aq_a2_fw_set_eee_rate,
diff --git a/drivers/net/ethernet/atheros/ag71xx.c b/drivers/net/ethernet/atheros/ag71xx.c
index 9586b6894f7e..bccc7e7b2a84 100644
--- a/drivers/net/ethernet/atheros/ag71xx.c
+++ b/drivers/net/ethernet/atheros/ag71xx.c
@@ -1213,6 +1213,11 @@ static bool ag71xx_fill_rx_buf(struct ag71xx *ag, struct ag71xx_buf *buf,
 	buf->rx.rx_buf = data;
 	buf->rx.dma_addr = dma_map_single(&ag->pdev->dev, data, ag->rx_buf_size,
 					  DMA_FROM_DEVICE);
+	if (dma_mapping_error(&ag->pdev->dev, buf->rx.dma_addr)) {
+		skb_free_frag(data);
+		buf->rx.rx_buf = NULL;
+		return false;
+	}
 	desc->data = (u32)buf->rx.dma_addr + offset;
 	return true;
 }
@@ -1511,6 +1516,10 @@ static netdev_tx_t ag71xx_hard_start_xmit(struct sk_buff *skb,
 
 	dma_addr = dma_map_single(&ag->pdev->dev, skb->data, skb->len,
 				  DMA_TO_DEVICE);
+	if (dma_mapping_error(&ag->pdev->dev, dma_addr)) {
+		netif_dbg(ag, tx_err, ndev, "DMA mapping error\n");
+		goto err_drop;
+	}
 
 	i = ring->curr & ring_mask;
 	desc = ag71xx_ring_desc(ring, i);
diff --git a/drivers/net/ethernet/atheros/atlx/atl1.c b/drivers/net/ethernet/atheros/atlx/atl1.c
index 3afd3627ce48..9c5d61990904 100644
--- a/drivers/net/ethernet/atheros/atlx/atl1.c
+++ b/drivers/net/ethernet/atheros/atlx/atl1.c
@@ -1861,14 +1861,21 @@ static u16 atl1_alloc_rx_buffers(struct atl1_adapter *adapter)
 			break;
 		}
 
-		buffer_info->alloced = 1;
-		buffer_info->skb = skb;
-		buffer_info->length = (u16) adapter->rx_buffer_len;
 		page = virt_to_page(skb->data);
 		offset = offset_in_page(skb->data);
 		buffer_info->dma = dma_map_page(&pdev->dev, page, offset,
 						adapter->rx_buffer_len,
 						DMA_FROM_DEVICE);
+		if (dma_mapping_error(&pdev->dev, buffer_info->dma)) {
+			kfree_skb(skb);
+			adapter->soft_stats.rx_dropped++;
+			break;
+		}
+
+		buffer_info->alloced = 1;
+		buffer_info->skb = skb;
+		buffer_info->length = (u16)adapter->rx_buffer_len;
+
 		rfd_desc->buffer_addr = cpu_to_le64(buffer_info->dma);
 		rfd_desc->buf_len = cpu_to_le16(adapter->rx_buffer_len);
 		rfd_desc->coalese = 0;
@@ -2183,8 +2190,8 @@ static int atl1_tx_csum(struct atl1_adapter *adapter, struct sk_buff *skb,
 	return 0;
 }
 
-static void atl1_tx_map(struct atl1_adapter *adapter, struct sk_buff *skb,
-	struct tx_packet_desc *ptpd)
+static bool atl1_tx_map(struct atl1_adapter *adapter, struct sk_buff *skb,
+			struct tx_packet_desc *ptpd)
 {
 	struct atl1_tpd_ring *tpd_ring = &adapter->tpd_ring;
 	struct atl1_buffer *buffer_info;
@@ -2194,6 +2201,7 @@ static void atl1_tx_map(struct atl1_adapter *adapter, struct sk_buff *skb,
 	unsigned int nr_frags;
 	unsigned int f;
 	int retval;
+	u16 first_mapped;
 	u16 next_to_use;
 	u16 data_len;
 	u8 hdr_len;
@@ -2201,6 +2209,7 @@ static void atl1_tx_map(struct atl1_adapter *adapter, struct sk_buff *skb,
 	buf_len -= skb->data_len;
 	nr_frags = skb_shinfo(skb)->nr_frags;
 	next_to_use = atomic_read(&tpd_ring->next_to_use);
+	first_mapped = next_to_use;
 	buffer_info = &tpd_ring->buffer_info[next_to_use];
 	BUG_ON(buffer_info->skb);
 	/* put skb in last TPD */
@@ -2216,6 +2225,8 @@ static void atl1_tx_map(struct atl1_adapter *adapter, struct sk_buff *skb,
 		buffer_info->dma = dma_map_page(&adapter->pdev->dev, page,
 						offset, hdr_len,
 						DMA_TO_DEVICE);
+		if (dma_mapping_error(&adapter->pdev->dev, buffer_info->dma))
+			goto dma_err;
 
 		if (++next_to_use == tpd_ring->count)
 			next_to_use = 0;
@@ -2242,6 +2253,9 @@ static void atl1_tx_map(struct atl1_adapter *adapter, struct sk_buff *skb,
 								page, offset,
 								buffer_info->length,
 								DMA_TO_DEVICE);
+				if (dma_mapping_error(&adapter->pdev->dev,
+						      buffer_info->dma))
+					goto dma_err;
 				if (++next_to_use == tpd_ring->count)
 					next_to_use = 0;
 			}
@@ -2254,6 +2268,8 @@ static void atl1_tx_map(struct atl1_adapter *adapter, struct sk_buff *skb,
 		buffer_info->dma = dma_map_page(&adapter->pdev->dev, page,
 						offset, buf_len,
 						DMA_TO_DEVICE);
+		if (dma_mapping_error(&adapter->pdev->dev, buffer_info->dma))
+			goto dma_err;
 		if (++next_to_use == tpd_ring->count)
 			next_to_use = 0;
 	}
@@ -2277,6 +2293,9 @@ static void atl1_tx_map(struct atl1_adapter *adapter, struct sk_buff *skb,
 			buffer_info->dma = skb_frag_dma_map(&adapter->pdev->dev,
 				frag, i * ATL1_MAX_TX_BUF_LEN,
 				buffer_info->length, DMA_TO_DEVICE);
+			if (dma_mapping_error(&adapter->pdev->dev,
+					      buffer_info->dma))
+				goto dma_err;
 
 			if (++next_to_use == tpd_ring->count)
 				next_to_use = 0;
@@ -2285,6 +2304,22 @@ static void atl1_tx_map(struct atl1_adapter *adapter, struct sk_buff *skb,
 
 	/* last tpd's buffer-info */
 	buffer_info->skb = skb;
+
+	return true;
+
+ dma_err:
+	while (first_mapped != next_to_use) {
+		buffer_info = &tpd_ring->buffer_info[first_mapped];
+		dma_unmap_page(&adapter->pdev->dev,
+			       buffer_info->dma,
+			       buffer_info->length,
+			       DMA_TO_DEVICE);
+		buffer_info->dma = 0;
+
+		if (++first_mapped == tpd_ring->count)
+			first_mapped = 0;
+	}
+	return false;
 }
 
 static void atl1_tx_queue(struct atl1_adapter *adapter, u16 count,
@@ -2355,10 +2390,8 @@ static netdev_tx_t atl1_xmit_frame(struct sk_buff *skb,
 
 	len = skb_headlen(skb);
 
-	if (unlikely(skb->len <= 0)) {
-		dev_kfree_skb_any(skb);
-		return NETDEV_TX_OK;
-	}
+	if (unlikely(skb->len <= 0))
+		goto drop_packet;
 
 	nr_frags = skb_shinfo(skb)->nr_frags;
 	for (f = 0; f < nr_frags; f++) {
@@ -2371,10 +2404,9 @@ static netdev_tx_t atl1_xmit_frame(struct sk_buff *skb,
 	if (mss) {
 		if (skb->protocol == htons(ETH_P_IP)) {
 			proto_hdr_len = skb_tcp_all_headers(skb);
-			if (unlikely(proto_hdr_len > len)) {
-				dev_kfree_skb_any(skb);
-				return NETDEV_TX_OK;
-			}
+			if (unlikely(proto_hdr_len > len))
+				goto drop_packet;
+
 			/* need additional TPD ? */
 			if (proto_hdr_len != len)
 				count += (len - proto_hdr_len +
@@ -2406,23 +2438,26 @@ static netdev_tx_t atl1_xmit_frame(struct sk_buff *skb,
 	}
 
 	tso = atl1_tso(adapter, skb, ptpd);
-	if (tso < 0) {
-		dev_kfree_skb_any(skb);
-		return NETDEV_TX_OK;
-	}
+	if (tso < 0)
+		goto drop_packet;
 
 	if (!tso) {
 		ret_val = atl1_tx_csum(adapter, skb, ptpd);
-		if (ret_val < 0) {
-			dev_kfree_skb_any(skb);
-			return NETDEV_TX_OK;
-		}
+		if (ret_val < 0)
+			goto drop_packet;
 	}
 
-	atl1_tx_map(adapter, skb, ptpd);
+	if (!atl1_tx_map(adapter, skb, ptpd))
+		goto drop_packet;
+
 	atl1_tx_queue(adapter, count, ptpd);
 	atl1_update_mailbox(adapter);
 	return NETDEV_TX_OK;
+
+drop_packet:
+	adapter->soft_stats.tx_errors++;
+	dev_kfree_skb_any(skb);
+	return NETDEV_TX_OK;
 }
 
 static int atl1_rings_clean(struct napi_struct *napi, int budget)
diff --git a/drivers/net/ethernet/broadcom/bgmac.h b/drivers/net/ethernet/broadcom/bgmac.h
index d73ef262991d..6fee9a41839c 100644
--- a/drivers/net/ethernet/broadcom/bgmac.h
+++ b/drivers/net/ethernet/broadcom/bgmac.h
@@ -328,8 +328,7 @@
 #define BGMAC_RX_FRAME_OFFSET			30		/* There are 2 unused bytes between header and real data */
 #define BGMAC_RX_BUF_OFFSET			(NET_SKB_PAD + NET_IP_ALIGN - \
 						 BGMAC_RX_FRAME_OFFSET)
-/* Jumbo frame size with FCS */
-#define BGMAC_RX_MAX_FRAME_SIZE			9724
+#define BGMAC_RX_MAX_FRAME_SIZE			1536
 #define BGMAC_RX_BUF_SIZE			(BGMAC_RX_FRAME_OFFSET + BGMAC_RX_MAX_FRAME_SIZE)
 #define BGMAC_RX_ALLOC_SIZE			(SKB_DATA_ALIGN(BGMAC_RX_BUF_SIZE + BGMAC_RX_BUF_OFFSET) + \
 						 SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 603e9c968c44..f4bafc71a739 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -758,7 +758,7 @@ tx_free:
 	dev_kfree_skb_any(skb);
 tx_kick_pending:
 	if (BNXT_TX_PTP_IS_SET(lflags)) {
-		txr->tx_buf_ring[txr->tx_prod].is_ts_pkt = 0;
+		txr->tx_buf_ring[RING_TX(bp, txr->tx_prod)].is_ts_pkt = 0;
 		atomic64_inc(&bp->ptp_cfg->stats.ts_err);
 		if (!(bp->fw_cap & BNXT_FW_CAP_TX_TS_CMP))
 			/* set SKB to err so PTP worker will clean up */
@@ -766,7 +766,7 @@ tx_kick_pending:
 	}
 	if (txr->kick_pending)
 		bnxt_txr_db_kick(bp, txr, txr->tx_prod);
-	txr->tx_buf_ring[txr->tx_prod].skb = NULL;
+	txr->tx_buf_ring[RING_TX(bp, txr->tx_prod)].skb = NULL;
 	dev_core_stats_tx_dropped_inc(dev);
 	return NETDEV_TX_OK;
 }
@@ -864,6 +864,11 @@ static void bnxt_tx_int(struct bnxt *bp, struct bnxt_napi *bnapi, int budget)
 		bnapi->events &= ~BNXT_TX_CMP_EVENT;
 }
 
+static bool bnxt_separate_head_pool(void)
+{
+	return PAGE_SIZE > BNXT_RX_PAGE_SIZE;
+}
+
 static struct page *__bnxt_alloc_rx_page(struct bnxt *bp, dma_addr_t *mapping,
 					 struct bnxt_rx_ring_info *rxr,
 					 unsigned int *offset,
@@ -886,27 +891,19 @@ static struct page *__bnxt_alloc_rx_page(struct bnxt *bp, dma_addr_t *mapping,
 }
 
 static inline u8 *__bnxt_alloc_rx_frag(struct bnxt *bp, dma_addr_t *mapping,
+				       struct bnxt_rx_ring_info *rxr,
 				       gfp_t gfp)
 {
-	u8 *data;
-	struct pci_dev *pdev = bp->pdev;
+	unsigned int offset;
+	struct page *page;
 
-	if (gfp == GFP_ATOMIC)
-		data = napi_alloc_frag(bp->rx_buf_size);
-	else
-		data = netdev_alloc_frag(bp->rx_buf_size);
-	if (!data)
+	page = page_pool_alloc_frag(rxr->head_pool, &offset,
+				    bp->rx_buf_size, gfp);
+	if (!page)
 		return NULL;
 
-	*mapping = dma_map_single_attrs(&pdev->dev, data + bp->rx_dma_offset,
-					bp->rx_buf_use_size, bp->rx_dir,
-					DMA_ATTR_WEAK_ORDERING);
-
-	if (dma_mapping_error(&pdev->dev, *mapping)) {
-		skb_free_frag(data);
-		data = NULL;
-	}
-	return data;
+	*mapping = page_pool_get_dma_addr(page) + bp->rx_dma_offset + offset;
+	return page_address(page) + offset;
 }
 
 int bnxt_alloc_rx_data(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
@@ -928,7 +925,7 @@ int bnxt_alloc_rx_data(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
 		rx_buf->data = page;
 		rx_buf->data_ptr = page_address(page) + offset + bp->rx_offset;
 	} else {
-		u8 *data = __bnxt_alloc_rx_frag(bp, &mapping, gfp);
+		u8 *data = __bnxt_alloc_rx_frag(bp, &mapping, rxr, gfp);
 
 		if (!data)
 			return -ENOMEM;
@@ -1179,13 +1176,14 @@ static struct sk_buff *bnxt_rx_skb(struct bnxt *bp,
 	}
 
 	skb = napi_build_skb(data, bp->rx_buf_size);
-	dma_unmap_single_attrs(&bp->pdev->dev, dma_addr, bp->rx_buf_use_size,
-			       bp->rx_dir, DMA_ATTR_WEAK_ORDERING);
+	dma_sync_single_for_cpu(&bp->pdev->dev, dma_addr, bp->rx_buf_use_size,
+				bp->rx_dir);
 	if (!skb) {
-		skb_free_frag(data);
+		page_pool_free_va(rxr->head_pool, data, true);
 		return NULL;
 	}
 
+	skb_mark_for_recycle(skb);
 	skb_reserve(skb, bp->rx_offset);
 	skb_put(skb, offset_and_len & 0xffff);
 	return skb;
@@ -1840,7 +1838,8 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp,
 		u8 *new_data;
 		dma_addr_t new_mapping;
 
-		new_data = __bnxt_alloc_rx_frag(bp, &new_mapping, GFP_ATOMIC);
+		new_data = __bnxt_alloc_rx_frag(bp, &new_mapping, rxr,
+						GFP_ATOMIC);
 		if (!new_data) {
 			bnxt_abort_tpa(cpr, idx, agg_bufs);
 			cpr->sw_stats->rx.rx_oom_discards += 1;
@@ -1852,16 +1851,16 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp,
 		tpa_info->mapping = new_mapping;
 
 		skb = napi_build_skb(data, bp->rx_buf_size);
-		dma_unmap_single_attrs(&bp->pdev->dev, mapping,
-				       bp->rx_buf_use_size, bp->rx_dir,
-				       DMA_ATTR_WEAK_ORDERING);
+		dma_sync_single_for_cpu(&bp->pdev->dev, mapping,
+					bp->rx_buf_use_size, bp->rx_dir);
 
 		if (!skb) {
-			skb_free_frag(data);
+			page_pool_free_va(rxr->head_pool, data, true);
 			bnxt_abort_tpa(cpr, idx, agg_bufs);
 			cpr->sw_stats->rx.rx_oom_discards += 1;
 			return NULL;
 		}
+		skb_mark_for_recycle(skb);
 		skb_reserve(skb, bp->rx_offset);
 		skb_put(skb, len);
 	}
@@ -1987,6 +1986,7 @@ static struct sk_buff *bnxt_rx_vlan(struct sk_buff *skb, u8 cmp_type,
 	}
 	return skb;
 vlan_err:
+	skb_mark_for_recycle(skb);
 	dev_kfree_skb(skb);
 	return NULL;
 }
@@ -2025,6 +2025,7 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 	struct rx_cmp_ext *rxcmp1;
 	u32 tmp_raw_cons = *raw_cons;
 	u16 cons, prod, cp_cons = RING_CMP(tmp_raw_cons);
+	struct skb_shared_info *sinfo;
 	struct bnxt_sw_rx_bd *rx_buf;
 	unsigned int len;
 	u8 *data_ptr, agg_bufs, cmp_type;
@@ -2151,6 +2152,7 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 							     false);
 			if (!frag_len)
 				goto oom_next_rx;
+
 		}
 		xdp_active = true;
 	}
@@ -2160,6 +2162,12 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 			rc = 1;
 			goto next_rx;
 		}
+		if (xdp_buff_has_frags(&xdp)) {
+			sinfo = xdp_get_shared_info_from_buff(&xdp);
+			agg_bufs = sinfo->nr_frags;
+		} else {
+			agg_bufs = 0;
+		}
 	}
 
 	if (len <= bp->rx_copy_thresh) {
@@ -2197,7 +2205,8 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 			if (!skb)
 				goto oom_next_rx;
 		} else {
-			skb = bnxt_xdp_build_skb(bp, skb, agg_bufs, rxr->page_pool, &xdp, rxcmp1);
+			skb = bnxt_xdp_build_skb(bp, skb, agg_bufs,
+						 rxr->page_pool, &xdp);
 			if (!skb) {
 				/* we should be able to free the old skb here */
 				bnxt_xdp_buff_frags_free(rxr, &xdp);
@@ -2862,6 +2871,7 @@ static int __bnxt_poll_work(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 {
 	struct bnxt_napi *bnapi = cpr->bnapi;
 	u32 raw_cons = cpr->cp_raw_cons;
+	bool flush_xdp = false;
 	u32 cons;
 	int rx_pkts = 0;
 	u8 event = 0;
@@ -2915,6 +2925,8 @@ static int __bnxt_poll_work(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 			else
 				rc = bnxt_force_rx_discard(bp, cpr, &raw_cons,
 							   &event);
+			if (event & BNXT_REDIRECT_EVENT)
+				flush_xdp = true;
 			if (likely(rc >= 0))
 				rx_pkts += rc;
 			/* Increment rx_pkts when rc is -ENOMEM to count towards
@@ -2939,7 +2951,7 @@ static int __bnxt_poll_work(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 		}
 	}
 
-	if (event & BNXT_REDIRECT_EVENT) {
+	if (flush_xdp) {
 		xdp_do_flush();
 		event &= ~BNXT_REDIRECT_EVENT;
 	}
@@ -3312,32 +3324,29 @@ static void bnxt_free_tx_skbs(struct bnxt *bp)
 		}
 		netdev_tx_reset_queue(netdev_get_tx_queue(bp->dev, i));
 	}
+
+	if (bp->ptp_cfg && !(bp->fw_cap & BNXT_FW_CAP_TX_TS_CMP))
+		bnxt_ptp_free_txts_skbs(bp->ptp_cfg);
 }
 
 static void bnxt_free_one_rx_ring(struct bnxt *bp, struct bnxt_rx_ring_info *rxr)
 {
-	struct pci_dev *pdev = bp->pdev;
 	int i, max_idx;
 
 	max_idx = bp->rx_nr_pages * RX_DESC_CNT;
 
 	for (i = 0; i < max_idx; i++) {
 		struct bnxt_sw_rx_bd *rx_buf = &rxr->rx_buf_ring[i];
-		dma_addr_t mapping = rx_buf->mapping;
 		void *data = rx_buf->data;
 
 		if (!data)
 			continue;
 
 		rx_buf->data = NULL;
-		if (BNXT_RX_PAGE_MODE(bp)) {
+		if (BNXT_RX_PAGE_MODE(bp))
 			page_pool_recycle_direct(rxr->page_pool, data);
-		} else {
-			dma_unmap_single_attrs(&pdev->dev, mapping,
-					       bp->rx_buf_use_size, bp->rx_dir,
-					       DMA_ATTR_WEAK_ORDERING);
-			skb_free_frag(data);
-		}
+		else
+			page_pool_free_va(rxr->head_pool, data, true);
 	}
 }
 
@@ -3361,16 +3370,11 @@ static void bnxt_free_one_rx_agg_ring(struct bnxt *bp, struct bnxt_rx_ring_info
 	}
 }
 
-static void bnxt_free_one_rx_ring_skbs(struct bnxt *bp, int ring_nr)
+static void bnxt_free_one_tpa_info_data(struct bnxt *bp,
+					struct bnxt_rx_ring_info *rxr)
 {
-	struct bnxt_rx_ring_info *rxr = &bp->rx_ring[ring_nr];
-	struct pci_dev *pdev = bp->pdev;
-	struct bnxt_tpa_idx_map *map;
 	int i;
 
-	if (!rxr->rx_tpa)
-		goto skip_rx_tpa_free;
-
 	for (i = 0; i < bp->max_tpa; i++) {
 		struct bnxt_tpa_info *tpa_info = &rxr->rx_tpa[i];
 		u8 *data = tpa_info->data;
@@ -3378,14 +3382,20 @@ static void bnxt_free_one_rx_ring_skbs(struct bnxt *bp, int ring_nr)
 		if (!data)
 			continue;
 
-		dma_unmap_single_attrs(&pdev->dev, tpa_info->mapping,
-				       bp->rx_buf_use_size, bp->rx_dir,
-				       DMA_ATTR_WEAK_ORDERING);
-
 		tpa_info->data = NULL;
-
-		skb_free_frag(data);
+		page_pool_free_va(rxr->head_pool, data, false);
 	}
+}
+
+static void bnxt_free_one_rx_ring_skbs(struct bnxt *bp,
+				       struct bnxt_rx_ring_info *rxr)
+{
+	struct bnxt_tpa_idx_map *map;
+
+	if (!rxr->rx_tpa)
+		goto skip_rx_tpa_free;
+
+	bnxt_free_one_tpa_info_data(bp, rxr);
 
 skip_rx_tpa_free:
 	if (!rxr->rx_buf_ring)
@@ -3413,7 +3423,7 @@ static void bnxt_free_rx_skbs(struct bnxt *bp)
 		return;
 
 	for (i = 0; i < bp->rx_nr_rings; i++)
-		bnxt_free_one_rx_ring_skbs(bp, i);
+		bnxt_free_one_rx_ring_skbs(bp, &bp->rx_ring[i]);
 }
 
 static void bnxt_free_skbs(struct bnxt *bp)
@@ -3525,29 +3535,64 @@ static int bnxt_alloc_ring(struct bnxt *bp, struct bnxt_ring_mem_info *rmem)
 	return 0;
 }
 
+static void bnxt_free_one_tpa_info(struct bnxt *bp,
+				   struct bnxt_rx_ring_info *rxr)
+{
+	int i;
+
+	kfree(rxr->rx_tpa_idx_map);
+	rxr->rx_tpa_idx_map = NULL;
+	if (rxr->rx_tpa) {
+		for (i = 0; i < bp->max_tpa; i++) {
+			kfree(rxr->rx_tpa[i].agg_arr);
+			rxr->rx_tpa[i].agg_arr = NULL;
+		}
+	}
+	kfree(rxr->rx_tpa);
+	rxr->rx_tpa = NULL;
+}
+
 static void bnxt_free_tpa_info(struct bnxt *bp)
 {
-	int i, j;
+	int i;
 
 	for (i = 0; i < bp->rx_nr_rings; i++) {
 		struct bnxt_rx_ring_info *rxr = &bp->rx_ring[i];
 
-		kfree(rxr->rx_tpa_idx_map);
-		rxr->rx_tpa_idx_map = NULL;
-		if (rxr->rx_tpa) {
-			for (j = 0; j < bp->max_tpa; j++) {
-				kfree(rxr->rx_tpa[j].agg_arr);
-				rxr->rx_tpa[j].agg_arr = NULL;
-			}
-		}
-		kfree(rxr->rx_tpa);
-		rxr->rx_tpa = NULL;
+		bnxt_free_one_tpa_info(bp, rxr);
+	}
+}
+
+static int bnxt_alloc_one_tpa_info(struct bnxt *bp,
+				   struct bnxt_rx_ring_info *rxr)
+{
+	struct rx_agg_cmp *agg;
+	int i;
+
+	rxr->rx_tpa = kcalloc(bp->max_tpa, sizeof(struct bnxt_tpa_info),
+			      GFP_KERNEL);
+	if (!rxr->rx_tpa)
+		return -ENOMEM;
+
+	if (!(bp->flags & BNXT_FLAG_CHIP_P5_PLUS))
+		return 0;
+	for (i = 0; i < bp->max_tpa; i++) {
+		agg = kcalloc(MAX_SKB_FRAGS, sizeof(*agg), GFP_KERNEL);
+		if (!agg)
+			return -ENOMEM;
+		rxr->rx_tpa[i].agg_arr = agg;
 	}
+	rxr->rx_tpa_idx_map = kzalloc(sizeof(*rxr->rx_tpa_idx_map),
+				      GFP_KERNEL);
+	if (!rxr->rx_tpa_idx_map)
+		return -ENOMEM;
+
+	return 0;
 }
 
 static int bnxt_alloc_tpa_info(struct bnxt *bp)
 {
-	int i, j;
+	int i, rc;
 
 	bp->max_tpa = MAX_TPA;
 	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
@@ -3558,25 +3603,10 @@ static int bnxt_alloc_tpa_info(struct bnxt *bp)
 
 	for (i = 0; i < bp->rx_nr_rings; i++) {
 		struct bnxt_rx_ring_info *rxr = &bp->rx_ring[i];
-		struct rx_agg_cmp *agg;
 
-		rxr->rx_tpa = kcalloc(bp->max_tpa, sizeof(struct bnxt_tpa_info),
-				      GFP_KERNEL);
-		if (!rxr->rx_tpa)
-			return -ENOMEM;
-
-		if (!(bp->flags & BNXT_FLAG_CHIP_P5_PLUS))
-			continue;
-		for (j = 0; j < bp->max_tpa; j++) {
-			agg = kcalloc(MAX_SKB_FRAGS, sizeof(*agg), GFP_KERNEL);
-			if (!agg)
-				return -ENOMEM;
-			rxr->rx_tpa[j].agg_arr = agg;
-		}
-		rxr->rx_tpa_idx_map = kzalloc(sizeof(*rxr->rx_tpa_idx_map),
-					      GFP_KERNEL);
-		if (!rxr->rx_tpa_idx_map)
-			return -ENOMEM;
+		rc = bnxt_alloc_one_tpa_info(bp, rxr);
+		if (rc)
+			return rc;
 	}
 	return 0;
 }
@@ -3600,7 +3630,9 @@ static void bnxt_free_rx_rings(struct bnxt *bp)
 			xdp_rxq_info_unreg(&rxr->xdp_rxq);
 
 		page_pool_destroy(rxr->page_pool);
-		rxr->page_pool = NULL;
+		if (bnxt_separate_head_pool())
+			page_pool_destroy(rxr->head_pool);
+		rxr->page_pool = rxr->head_pool = NULL;
 
 		kfree(rxr->rx_agg_bmap);
 		rxr->rx_agg_bmap = NULL;
@@ -3618,6 +3650,7 @@ static int bnxt_alloc_rx_page_pool(struct bnxt *bp,
 				   int numa_node)
 {
 	struct page_pool_params pp = { 0 };
+	struct page_pool *pool;
 
 	pp.pool_size = bp->rx_agg_ring_size;
 	if (BNXT_RX_PAGE_MODE(bp))
@@ -3630,14 +3663,25 @@ static int bnxt_alloc_rx_page_pool(struct bnxt *bp,
 	pp.max_len = PAGE_SIZE;
 	pp.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV;
 
-	rxr->page_pool = page_pool_create(&pp);
-	if (IS_ERR(rxr->page_pool)) {
-		int err = PTR_ERR(rxr->page_pool);
+	pool = page_pool_create(&pp);
+	if (IS_ERR(pool))
+		return PTR_ERR(pool);
+	rxr->page_pool = pool;
 
-		rxr->page_pool = NULL;
-		return err;
+	if (bnxt_separate_head_pool()) {
+		pp.pool_size = max(bp->rx_ring_size, 1024);
+		pool = page_pool_create(&pp);
+		if (IS_ERR(pool))
+			goto err_destroy_pp;
 	}
+	rxr->head_pool = pool;
+
 	return 0;
+
+err_destroy_pp:
+	page_pool_destroy(rxr->page_pool);
+	rxr->page_pool = NULL;
+	return PTR_ERR(pool);
 }
 
 static int bnxt_alloc_rx_rings(struct bnxt *bp)
@@ -4171,10 +4215,31 @@ static void bnxt_alloc_one_rx_ring_page(struct bnxt *bp,
 	rxr->rx_agg_prod = prod;
 }
 
+static int bnxt_alloc_one_tpa_info_data(struct bnxt *bp,
+					struct bnxt_rx_ring_info *rxr)
+{
+	dma_addr_t mapping;
+	u8 *data;
+	int i;
+
+	for (i = 0; i < bp->max_tpa; i++) {
+		data = __bnxt_alloc_rx_frag(bp, &mapping, rxr,
+					    GFP_KERNEL);
+		if (!data)
+			return -ENOMEM;
+
+		rxr->rx_tpa[i].data = data;
+		rxr->rx_tpa[i].data_ptr = data + bp->rx_offset;
+		rxr->rx_tpa[i].mapping = mapping;
+	}
+
+	return 0;
+}
+
 static int bnxt_alloc_one_rx_ring(struct bnxt *bp, int ring_nr)
 {
 	struct bnxt_rx_ring_info *rxr = &bp->rx_ring[ring_nr];
-	int i;
+	int rc;
 
 	bnxt_alloc_one_rx_ring_skb(bp, rxr, ring_nr);
 
@@ -4184,18 +4249,9 @@ static int bnxt_alloc_one_rx_ring(struct bnxt *bp, int ring_nr)
 	bnxt_alloc_one_rx_ring_page(bp, rxr, ring_nr);
 
 	if (rxr->rx_tpa) {
-		dma_addr_t mapping;
-		u8 *data;
-
-		for (i = 0; i < bp->max_tpa; i++) {
-			data = __bnxt_alloc_rx_frag(bp, &mapping, GFP_KERNEL);
-			if (!data)
-				return -ENOMEM;
-
-			rxr->rx_tpa[i].data = data;
-			rxr->rx_tpa[i].data_ptr = data + bp->rx_offset;
-			rxr->rx_tpa[i].mapping = mapping;
-		}
+		rc = bnxt_alloc_one_tpa_info_data(bp, rxr);
+		if (rc)
+			return rc;
 	}
 	return 0;
 }
@@ -10337,6 +10393,72 @@ void bnxt_del_one_rss_ctx(struct bnxt *bp, struct bnxt_rss_ctx *rss_ctx,
 	bp->num_rss_ctx--;
 }
 
+static bool bnxt_vnic_has_rx_ring(struct bnxt *bp, struct bnxt_vnic_info *vnic,
+				  int rxr_id)
+{
+	u16 tbl_size = bnxt_get_rxfh_indir_size(bp->dev);
+	int i, vnic_rx;
+
+	/* Ntuple VNIC always has all the rx rings. Any change of ring id
+	 * must be updated because a future filter may use it.
+	 */
+	if (vnic->flags & BNXT_VNIC_NTUPLE_FLAG)
+		return true;
+
+	for (i = 0; i < tbl_size; i++) {
+		if (vnic->flags & BNXT_VNIC_RSSCTX_FLAG)
+			vnic_rx = ethtool_rxfh_context_indir(vnic->rss_ctx)[i];
+		else
+			vnic_rx = bp->rss_indir_tbl[i];
+
+		if (rxr_id == vnic_rx)
+			return true;
+	}
+
+	return false;
+}
+
+static int bnxt_set_vnic_mru_p5(struct bnxt *bp, struct bnxt_vnic_info *vnic,
+				u16 mru, int rxr_id)
+{
+	int rc;
+
+	if (!bnxt_vnic_has_rx_ring(bp, vnic, rxr_id))
+		return 0;
+
+	if (mru) {
+		rc = bnxt_hwrm_vnic_set_rss_p5(bp, vnic, true);
+		if (rc) {
+			netdev_err(bp->dev, "hwrm vnic %d set rss failure rc: %d\n",
+				   vnic->vnic_id, rc);
+			return rc;
+		}
+	}
+	vnic->mru = mru;
+	bnxt_hwrm_vnic_update(bp, vnic,
+			      VNIC_UPDATE_REQ_ENABLES_MRU_VALID);
+
+	return 0;
+}
+
+static int bnxt_set_rss_ctx_vnic_mru(struct bnxt *bp, u16 mru, int rxr_id)
+{
+	struct ethtool_rxfh_context *ctx;
+	unsigned long context;
+	int rc;
+
+	xa_for_each(&bp->dev->ethtool->rss_ctx, context, ctx) {
+		struct bnxt_rss_ctx *rss_ctx = ethtool_rxfh_context_priv(ctx);
+		struct bnxt_vnic_info *vnic = &rss_ctx->vnic;
+
+		rc = bnxt_set_vnic_mru_p5(bp, vnic, mru, rxr_id);
+		if (rc)
+			return rc;
+	}
+
+	return 0;
+}
+
 static void bnxt_hwrm_realloc_rss_ctx_vnic(struct bnxt *bp)
 {
 	bool set_tpa = !!(bp->flags & BNXT_FLAG_TPA);
@@ -10939,11 +11061,9 @@ static void bnxt_free_irq(struct bnxt *bp)
 
 static int bnxt_request_irq(struct bnxt *bp)
 {
+	struct cpu_rmap *rmap = NULL;
 	int i, j, rc = 0;
 	unsigned long flags = 0;
-#ifdef CONFIG_RFS_ACCEL
-	struct cpu_rmap *rmap;
-#endif
 
 	rc = bnxt_setup_int_mode(bp);
 	if (rc) {
@@ -10958,15 +11078,15 @@ static int bnxt_request_irq(struct bnxt *bp)
 		int map_idx = bnxt_cp_num_to_irq_num(bp, i);
 		struct bnxt_irq *irq = &bp->irq_tbl[map_idx];
 
-#ifdef CONFIG_RFS_ACCEL
-		if (rmap && bp->bnapi[i]->rx_ring) {
+		if (IS_ENABLED(CONFIG_RFS_ACCEL) &&
+		    rmap && bp->bnapi[i]->rx_ring) {
 			rc = irq_cpu_rmap_add(rmap, irq->vector);
 			if (rc)
 				netdev_warn(bp->dev, "failed adding irq rmap for ring %d\n",
 					    j);
 			j++;
 		}
-#endif
+
 		rc = request_irq(irq->vector, irq->handler, flags, irq->name,
 				 bp->bnapi[i]);
 		if (rc)
@@ -11027,6 +11147,9 @@ static void bnxt_init_napi(struct bnxt *bp)
 		poll_fn = bnxt_poll_p5;
 	else if (BNXT_CHIP_TYPE_NITRO_A0(bp))
 		cp_nr_rings--;
+
+	set_bit(BNXT_STATE_NAPI_DISABLED, &bp->state);
+
 	for (i = 0; i < cp_nr_rings; i++) {
 		bnapi = bp->bnapi[i];
 		netif_napi_add(bp->dev, &bnapi->napi, poll_fn);
@@ -11727,6 +11850,7 @@ static int bnxt_hwrm_if_change(struct bnxt *bp, bool up)
 	struct hwrm_func_drv_if_change_input *req;
 	bool fw_reset = !bp->irq_tbl;
 	bool resc_reinit = false;
+	bool caps_change = false;
 	int rc, retry = 0;
 	u32 flags = 0;
 
@@ -11782,8 +11906,11 @@ static int bnxt_hwrm_if_change(struct bnxt *bp, bool up)
 		set_bit(BNXT_STATE_ABORT_ERR, &bp->state);
 		return -ENODEV;
 	}
-	if (resc_reinit || fw_reset) {
-		if (fw_reset) {
+	if (flags & FUNC_DRV_IF_CHANGE_RESP_FLAGS_CAPS_CHANGE)
+		caps_change = true;
+
+	if (resc_reinit || fw_reset || caps_change) {
+		if (fw_reset || caps_change) {
 			set_bit(BNXT_STATE_FW_RESET_DET, &bp->state);
 			if (!test_bit(BNXT_STATE_IN_FW_RESET, &bp->state))
 				bnxt_ulp_irq_stop(bp);
@@ -11795,13 +11922,8 @@ static int bnxt_hwrm_if_change(struct bnxt *bp, bool up)
 				set_bit(BNXT_STATE_ABORT_ERR, &bp->state);
 				return rc;
 			}
+			/* IRQ will be initialized later in bnxt_request_irq()*/
 			bnxt_clear_int_mode(bp);
-			rc = bnxt_init_int_mode(bp);
-			if (rc) {
-				clear_bit(BNXT_STATE_FW_RESET_DET, &bp->state);
-				netdev_err(bp->dev, "init int mode failed\n");
-				return rc;
-			}
 		}
 		rc = bnxt_cancel_reservations(bp, fw_reset);
 	}
@@ -12200,8 +12322,6 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 	/* VF-reps may need to be re-opened after the PF is re-opened */
 	if (BNXT_PF(bp))
 		bnxt_vf_reps_open(bp);
-	if (bp->ptp_cfg && !(bp->fw_cap & BNXT_FW_CAP_TX_TS_CMP))
-		WRITE_ONCE(bp->ptp_cfg->tx_avail, BNXT_MAX_TX_TS);
 	bnxt_ptp_init_rtc(bp, true);
 	bnxt_ptp_cfg_tstamp_filters(bp);
 	if (BNXT_SUPPORTS_MULTI_RSS_CTX(bp))
@@ -13452,7 +13572,7 @@ static void bnxt_rx_ring_reset(struct bnxt *bp)
 			bnxt_reset_task(bp, true);
 			break;
 		}
-		bnxt_free_one_rx_ring_skbs(bp, i);
+		bnxt_free_one_rx_ring_skbs(bp, rxr);
 		rxr->rx_prod = 0;
 		rxr->rx_agg_prod = 0;
 		rxr->rx_sw_agg_prod = 0;
@@ -15023,6 +15143,9 @@ static void bnxt_get_queue_stats_rx(struct net_device *dev, int i,
 	struct bnxt_cp_ring_info *cpr;
 	u64 *sw;
 
+	if (!bp->bnapi)
+		return;
+
 	cpr = &bp->bnapi[i]->cp_ring;
 	sw = cpr->stats.sw_stats;
 
@@ -15046,6 +15169,9 @@ static void bnxt_get_queue_stats_tx(struct net_device *dev, int i,
 	struct bnxt_napi *bnapi;
 	u64 *sw;
 
+	if (!bp->tx_ring)
+		return;
+
 	bnapi = bp->tx_ring[bp->tx_ring_map[i]].bnapi;
 	sw = bnapi->cp_ring.stats.sw_stats;
 
@@ -15100,6 +15226,9 @@ static int bnxt_queue_mem_alloc(struct net_device *dev, void *qmem, int idx)
 	struct bnxt_ring_struct *ring;
 	int rc;
 
+	if (!bp->rx_ring)
+		return -ENETDOWN;
+
 	rxr = &bp->rx_ring[idx];
 	clone = qmem;
 	memcpy(clone, rxr, sizeof(*rxr));
@@ -15141,15 +15270,25 @@ static int bnxt_queue_mem_alloc(struct net_device *dev, void *qmem, int idx)
 			goto err_free_rx_agg_ring;
 	}
 
+	if (bp->flags & BNXT_FLAG_TPA) {
+		rc = bnxt_alloc_one_tpa_info(bp, clone);
+		if (rc)
+			goto err_free_tpa_info;
+	}
+
 	bnxt_init_one_rx_ring_rxbd(bp, clone);
 	bnxt_init_one_rx_agg_ring_rxbd(bp, clone);
 
 	bnxt_alloc_one_rx_ring_skb(bp, clone, idx);
 	if (bp->flags & BNXT_FLAG_AGG_RINGS)
 		bnxt_alloc_one_rx_ring_page(bp, clone, idx);
+	if (bp->flags & BNXT_FLAG_TPA)
+		bnxt_alloc_one_tpa_info_data(bp, clone);
 
 	return 0;
 
+err_free_tpa_info:
+	bnxt_free_one_tpa_info(bp, clone);
 err_free_rx_agg_ring:
 	bnxt_free_ring(bp, &clone->rx_agg_ring_struct.ring_mem);
 err_free_rx_ring:
@@ -15157,9 +15296,11 @@ err_free_rx_ring:
 err_rxq_info_unreg:
 	xdp_rxq_info_unreg(&clone->xdp_rxq);
 err_page_pool_destroy:
-	clone->page_pool->p.napi = NULL;
 	page_pool_destroy(clone->page_pool);
+	if (bnxt_separate_head_pool())
+		page_pool_destroy(clone->head_pool);
 	clone->page_pool = NULL;
+	clone->head_pool = NULL;
 	return rc;
 }
 
@@ -15169,13 +15310,16 @@ static void bnxt_queue_mem_free(struct net_device *dev, void *qmem)
 	struct bnxt *bp = netdev_priv(dev);
 	struct bnxt_ring_struct *ring;
 
-	bnxt_free_one_rx_ring(bp, rxr);
-	bnxt_free_one_rx_agg_ring(bp, rxr);
+	bnxt_free_one_rx_ring_skbs(bp, rxr);
+	bnxt_free_one_tpa_info(bp, rxr);
 
 	xdp_rxq_info_unreg(&rxr->xdp_rxq);
 
 	page_pool_destroy(rxr->page_pool);
+	if (bnxt_separate_head_pool())
+		page_pool_destroy(rxr->head_pool);
 	rxr->page_pool = NULL;
+	rxr->head_pool = NULL;
 
 	ring = &rxr->rx_ring_struct;
 	bnxt_free_ring(bp, &ring->ring_mem);
@@ -15249,6 +15393,7 @@ static int bnxt_queue_start(struct net_device *dev, void *qmem, int idx)
 	struct bnxt_cp_ring_info *cpr;
 	struct bnxt_vnic_info *vnic;
 	int i, rc;
+	u16 mru;
 
 	rxr = &bp->rx_ring[idx];
 	clone = qmem;
@@ -15257,7 +15402,10 @@ static int bnxt_queue_start(struct net_device *dev, void *qmem, int idx)
 	rxr->rx_agg_prod = clone->rx_agg_prod;
 	rxr->rx_sw_agg_prod = clone->rx_sw_agg_prod;
 	rxr->rx_next_cons = clone->rx_next_cons;
+	rxr->rx_tpa = clone->rx_tpa;
+	rxr->rx_tpa_idx_map = clone->rx_tpa_idx_map;
 	rxr->page_pool = clone->page_pool;
+	rxr->head_pool = clone->head_pool;
 	rxr->xdp_rxq = clone->xdp_rxq;
 
 	bnxt_copy_rx_ring(bp, rxr, clone);
@@ -15276,21 +15424,15 @@ static int bnxt_queue_start(struct net_device *dev, void *qmem, int idx)
 	cpr = &rxr->bnapi->cp_ring;
 	cpr->sw_stats->rx.rx_resets++;
 
-	for (i = 0; i <= BNXT_VNIC_NTUPLE; i++) {
+	mru = bp->dev->mtu + ETH_HLEN + VLAN_HLEN;
+	for (i = 0; i < bp->nr_vnics; i++) {
 		vnic = &bp->vnic_info[i];
 
-		rc = bnxt_hwrm_vnic_set_rss_p5(bp, vnic, true);
-		if (rc) {
-			netdev_err(bp->dev, "hwrm vnic %d set rss failure rc: %d\n",
-				   vnic->vnic_id, rc);
+		rc = bnxt_set_vnic_mru_p5(bp, vnic, mru, idx);
+		if (rc)
 			return rc;
-		}
-		vnic->mru = bp->dev->mtu + ETH_HLEN + VLAN_HLEN;
-		bnxt_hwrm_vnic_update(bp, vnic,
-				      VNIC_UPDATE_REQ_ENABLES_MRU_VALID);
 	}
-
-	return 0;
+	return bnxt_set_rss_ctx_vnic_mru(bp, mru, idx);
 
 err_free_hwrm_rx_ring:
 	bnxt_hwrm_rx_ring_free(bp, rxr, false);
@@ -15304,12 +15446,12 @@ static int bnxt_queue_stop(struct net_device *dev, void *qmem, int idx)
 	struct bnxt_vnic_info *vnic;
 	int i;
 
-	for (i = 0; i <= BNXT_VNIC_NTUPLE; i++) {
+	for (i = 0; i < bp->nr_vnics; i++) {
 		vnic = &bp->vnic_info[i];
-		vnic->mru = 0;
-		bnxt_hwrm_vnic_update(bp, vnic,
-				      VNIC_UPDATE_REQ_ENABLES_MRU_VALID);
+
+		bnxt_set_vnic_mru_p5(bp, vnic, 0, idx);
 	}
+	bnxt_set_rss_ctx_vnic_mru(bp, 0, idx);
 	/* Make sure NAPI sees that the VNIC is disabled */
 	synchronize_net();
 	rxr = &bp->rx_ring[idx];
@@ -15318,6 +15460,8 @@ static int bnxt_queue_stop(struct net_device *dev, void *qmem, int idx)
 	bnxt_hwrm_rx_agg_ring_free(bp, rxr, false);
 	rxr->rx_next_cons = 0;
 	page_pool_disable_direct_recycling(rxr->page_pool);
+	if (bnxt_separate_head_pool())
+		page_pool_disable_direct_recycling(rxr->head_pool);
 
 	memcpy(qmem, rxr, sizeof(*rxr));
 	bnxt_init_rx_ring_struct(bp, qmem);
@@ -15343,8 +15487,8 @@ static void bnxt_remove_one(struct pci_dev *pdev)
 
 	bnxt_rdma_aux_device_del(bp);
 
-	bnxt_ptp_clear(bp);
 	unregister_netdev(dev);
+	bnxt_ptp_clear(bp);
 
 	bnxt_rdma_aux_device_uninit(bp);
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index bee645f58d0b..1758edcd1db4 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1108,6 +1108,7 @@ struct bnxt_rx_ring_info {
 	struct bnxt_ring_struct	rx_agg_ring_struct;
 	struct xdp_rxq_info	xdp_rxq;
 	struct page_pool	*page_pool;
+	struct page_pool	*head_pool;
 };
 
 struct bnxt_rx_sw_stats {
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.c
index 4e2b938ed1f7..d80ce437435f 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.c
@@ -66,20 +66,30 @@ static int bnxt_hwrm_dbg_dma_data(struct bnxt *bp, void *msg,
 			}
 		}
 
+		if (cmn_req->req_type ==
+				cpu_to_le16(HWRM_DBG_COREDUMP_RETRIEVE))
+			info->dest_buf_size += len;
+
 		if (info->dest_buf) {
 			if ((info->seg_start + off + len) <=
 			    BNXT_COREDUMP_BUF_LEN(info->buf_len)) {
-				memcpy(info->dest_buf + off, dma_buf, len);
+				u16 copylen = min_t(u16, len,
+						    info->dest_buf_size - off);
+
+				memcpy(info->dest_buf + off, dma_buf, copylen);
+				if (copylen < len)
+					break;
 			} else {
 				rc = -ENOBUFS;
+				if (cmn_req->req_type ==
+				    cpu_to_le16(HWRM_DBG_COREDUMP_LIST)) {
+					kfree(info->dest_buf);
+					info->dest_buf = NULL;
+				}
 				break;
 			}
 		}
 
-		if (cmn_req->req_type ==
-				cpu_to_le16(HWRM_DBG_COREDUMP_RETRIEVE))
-			info->dest_buf_size += len;
-
 		if (!(cmn_resp->flags & HWRM_DBG_CMN_FLAGS_MORE))
 			break;
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
index 0dbb880a7aa0..71e14be2507e 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
@@ -487,7 +487,9 @@ static int bnxt_ets_validate(struct bnxt *bp, struct ieee_ets *ets, u8 *tc)
 
 		if ((ets->tc_tx_bw[i] || ets->tc_tsa[i]) && i > bp->max_tc)
 			return -EINVAL;
+	}
 
+	for (i = 0; i < max_tc; i++) {
 		switch (ets->tc_tsa[i]) {
 		case IEEE_8021QAZ_TSA_STRICT:
 			break;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index b901ecb57f25..54ae90526d8f 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -2041,6 +2041,17 @@ static int bnxt_get_regs_len(struct net_device *dev)
 	return reg_len;
 }
 
+#define BNXT_PCIE_32B_ENTRY(start, end)			\
+	 { offsetof(struct pcie_ctx_hw_stats, start),	\
+	   offsetof(struct pcie_ctx_hw_stats, end) }
+
+static const struct {
+	u16 start;
+	u16 end;
+} bnxt_pcie_32b_entries[] = {
+	BNXT_PCIE_32B_ENTRY(pcie_ltssm_histogram[0], pcie_ltssm_histogram[3]),
+};
+
 static void bnxt_get_regs(struct net_device *dev, struct ethtool_regs *regs,
 			  void *_p)
 {
@@ -2072,12 +2083,27 @@ static void bnxt_get_regs(struct net_device *dev, struct ethtool_regs *regs,
 	req->pcie_stat_host_addr = cpu_to_le64(hw_pcie_stats_addr);
 	rc = hwrm_req_send(bp, req);
 	if (!rc) {
-		__le64 *src = (__le64 *)hw_pcie_stats;
-		u64 *dst = (u64 *)(_p + BNXT_PXP_REG_LEN);
-		int i;
-
-		for (i = 0; i < sizeof(*hw_pcie_stats) / sizeof(__le64); i++)
-			dst[i] = le64_to_cpu(src[i]);
+		u8 *dst = (u8 *)(_p + BNXT_PXP_REG_LEN);
+		u8 *src = (u8 *)hw_pcie_stats;
+		int i, j;
+
+		for (i = 0, j = 0; i < sizeof(*hw_pcie_stats); ) {
+			if (i >= bnxt_pcie_32b_entries[j].start &&
+			    i <= bnxt_pcie_32b_entries[j].end) {
+				u32 *dst32 = (u32 *)(dst + i);
+
+				*dst32 = le32_to_cpu(*(__le32 *)(src + i));
+				i += 4;
+				if (i > bnxt_pcie_32b_entries[j].end &&
+				    j < ARRAY_SIZE(bnxt_pcie_32b_entries) - 1)
+					j++;
+			} else {
+				u64 *dst64 = (u64 *)(dst + i);
+
+				*dst64 = le64_to_cpu(*(__le64 *)(src + i));
+				i += 8;
+			}
+		}
 	}
 	hwrm_req_drop(bp, req);
 }
@@ -4848,6 +4874,7 @@ static void bnxt_self_test(struct net_device *dev, struct ethtool_test *etest,
 	if (!bp->num_tests || !BNXT_PF(bp))
 		return;
 
+	memset(buf, 0, sizeof(u64) * bp->num_tests);
 	if (etest->flags & ETH_TEST_FL_OFFLINE &&
 	    bnxt_ulp_registered(bp->edev)) {
 		etest->flags |= ETH_TEST_FL_FAILED;
@@ -4855,7 +4882,6 @@ static void bnxt_self_test(struct net_device *dev, struct ethtool_test *etest,
 		return;
 	}
 
-	memset(buf, 0, sizeof(u64) * bp->num_tests);
 	if (!netif_running(dev)) {
 		etest->flags |= ETH_TEST_FL_FAILED;
 		return;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
index 781225d3ba8f..650034a4bb46 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
@@ -777,6 +777,27 @@ next_slot:
 	return HZ;
 }
 
+void bnxt_ptp_free_txts_skbs(struct bnxt_ptp_cfg *ptp)
+{
+	struct bnxt_ptp_tx_req *txts_req;
+	u16 cons = ptp->txts_cons;
+
+	/* make sure ptp aux worker finished with
+	 * possible BNXT_STATE_OPEN set
+	 */
+	ptp_cancel_worker_sync(ptp->ptp_clock);
+
+	ptp->tx_avail = BNXT_MAX_TX_TS;
+	while (cons != ptp->txts_prod) {
+		txts_req = &ptp->txts_req[cons];
+		if (!IS_ERR_OR_NULL(txts_req->tx_skb))
+			dev_kfree_skb_any(txts_req->tx_skb);
+		cons = NEXT_TXTS(cons);
+	}
+	ptp->txts_cons = cons;
+	ptp_schedule_worker(ptp->ptp_clock, 0);
+}
+
 int bnxt_ptp_get_txts_prod(struct bnxt_ptp_cfg *ptp, u16 *prod)
 {
 	spin_lock_bh(&ptp->ptp_tx_lock);
@@ -1095,7 +1116,6 @@ out:
 void bnxt_ptp_clear(struct bnxt *bp)
 {
 	struct bnxt_ptp_cfg *ptp = bp->ptp_cfg;
-	int i;
 
 	if (!ptp)
 		return;
@@ -1107,12 +1127,5 @@ void bnxt_ptp_clear(struct bnxt *bp)
 	kfree(ptp->ptp_info.pin_config);
 	ptp->ptp_info.pin_config = NULL;
 
-	for (i = 0; i < BNXT_MAX_TX_TS; i++) {
-		if (ptp->txts_req[i].tx_skb) {
-			dev_kfree_skb_any(ptp->txts_req[i].tx_skb);
-			ptp->txts_req[i].tx_skb = NULL;
-		}
-	}
-
 	bnxt_unmap_ptp_regs(bp);
 }
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h
index 61e89bb2d269..999b497990bc 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h
@@ -174,6 +174,7 @@ int bnxt_ptp_cfg_tstamp_filters(struct bnxt *bp);
 void bnxt_ptp_reapply_pps(struct bnxt *bp);
 int bnxt_hwtstamp_set(struct net_device *dev, struct ifreq *ifr);
 int bnxt_hwtstamp_get(struct net_device *dev, struct ifreq *ifr);
+void bnxt_ptp_free_txts_skbs(struct bnxt_ptp_cfg *ptp);
 int bnxt_ptp_get_txts_prod(struct bnxt_ptp_cfg *ptp, u16 *prod);
 void bnxt_get_tx_ts_p5(struct bnxt *bp, struct sk_buff *skb, u16 prod);
 int bnxt_get_rx_ts_p5(struct bnxt *bp, u64 *ts, u32 pkt_ts);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
index 546d9a3d7efe..1867552a8bdb 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
@@ -148,7 +148,6 @@ void bnxt_unregister_dev(struct bnxt_en_dev *edev)
 	struct net_device *dev = edev->net;
 	struct bnxt *bp = netdev_priv(dev);
 	struct bnxt_ulp *ulp;
-	int i = 0;
 
 	ulp = edev->ulp_tbl;
 	rtnl_lock();
@@ -164,10 +163,6 @@ void bnxt_unregister_dev(struct bnxt_en_dev *edev)
 	synchronize_rcu();
 	ulp->max_async_event_id = 0;
 	ulp->async_events_bmap = NULL;
-	while (atomic_read(&ulp->ref_count) != 0 && i < 10) {
-		msleep(100);
-		i++;
-	}
 	mutex_unlock(&edev->en_dev_lock);
 	rtnl_unlock();
 	return;
@@ -235,10 +230,9 @@ void bnxt_ulp_stop(struct bnxt *bp)
 		return;
 
 	mutex_lock(&edev->en_dev_lock);
-	if (!bnxt_ulp_registered(edev)) {
-		mutex_unlock(&edev->en_dev_lock);
-		return;
-	}
+	if (!bnxt_ulp_registered(edev) ||
+	    (edev->flags & BNXT_EN_FLAG_ULP_STOPPED))
+		goto ulp_stop_exit;
 
 	edev->flags |= BNXT_EN_FLAG_ULP_STOPPED;
 	if (aux_priv) {
@@ -254,6 +248,7 @@ void bnxt_ulp_stop(struct bnxt *bp)
 			adrv->suspend(adev, pm);
 		}
 	}
+ulp_stop_exit:
 	mutex_unlock(&edev->en_dev_lock);
 }
 
@@ -262,19 +257,13 @@ void bnxt_ulp_start(struct bnxt *bp, int err)
 	struct bnxt_aux_priv *aux_priv = bp->aux_priv;
 	struct bnxt_en_dev *edev = bp->edev;
 
-	if (!edev)
-		return;
-
-	edev->flags &= ~BNXT_EN_FLAG_ULP_STOPPED;
-
-	if (err)
+	if (!edev || err)
 		return;
 
 	mutex_lock(&edev->en_dev_lock);
-	if (!bnxt_ulp_registered(edev)) {
-		mutex_unlock(&edev->en_dev_lock);
-		return;
-	}
+	if (!bnxt_ulp_registered(edev) ||
+	    !(edev->flags & BNXT_EN_FLAG_ULP_STOPPED))
+		goto ulp_start_exit;
 
 	if (edev->ulp_tbl->msix_requested)
 		bnxt_fill_msix_vecs(bp, edev->msix_entries);
@@ -291,6 +280,8 @@ void bnxt_ulp_start(struct bnxt *bp, int err)
 			adrv->resume(adev);
 		}
 	}
+ulp_start_exit:
+	edev->flags &= ~BNXT_EN_FLAG_ULP_STOPPED;
 	mutex_unlock(&edev->en_dev_lock);
 }
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h
index 4f4914f5c84c..b76a231ca7da 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h
@@ -48,7 +48,6 @@ struct bnxt_ulp {
 	unsigned long	*async_events_bmap;
 	u16		max_async_event_id;
 	u16		msix_requested;
-	atomic_t	ref_count;
 };
 
 struct bnxt_en_dev {
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
index dc51dce209d5..844812bd6536 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
@@ -115,7 +115,7 @@ static void __bnxt_xmit_xdp_redirect(struct bnxt *bp,
 	tx_buf->action = XDP_REDIRECT;
 	tx_buf->xdpf = xdpf;
 	dma_unmap_addr_set(tx_buf, mapping, mapping);
-	dma_unmap_len_set(tx_buf, len, 0);
+	dma_unmap_len_set(tx_buf, len, len);
 }
 
 void bnxt_tx_int_xdp(struct bnxt *bp, struct bnxt_napi *bnapi, int budget)
@@ -456,23 +456,16 @@ int bnxt_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 
 struct sk_buff *
 bnxt_xdp_build_skb(struct bnxt *bp, struct sk_buff *skb, u8 num_frags,
-		   struct page_pool *pool, struct xdp_buff *xdp,
-		   struct rx_cmp_ext *rxcmp1)
+		   struct page_pool *pool, struct xdp_buff *xdp)
 {
 	struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
 
 	if (!skb)
 		return NULL;
-	skb_checksum_none_assert(skb);
-	if (RX_CMP_L4_CS_OK(rxcmp1)) {
-		if (bp->dev->features & NETIF_F_RXCSUM) {
-			skb->ip_summed = CHECKSUM_UNNECESSARY;
-			skb->csum_level = RX_CMP_ENCAP(rxcmp1);
-		}
-	}
+
 	xdp_update_skb_shared_info(skb, num_frags,
 				   sinfo->xdp_frags_size,
-				   BNXT_RX_PAGE_SIZE * sinfo->nr_frags,
+				   BNXT_RX_PAGE_SIZE * num_frags,
 				   xdp_buff_is_frag_pfmemalloc(xdp));
 	return skb;
 }
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h
index 0122782400b8..220285e190fc 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h
@@ -33,6 +33,5 @@ void bnxt_xdp_buff_frags_free(struct bnxt_rx_ring_info *rxr,
 			      struct xdp_buff *xdp);
 struct sk_buff *bnxt_xdp_build_skb(struct bnxt *bp, struct sk_buff *skb,
 				   u8 num_frags, struct page_pool *pool,
-				   struct xdp_buff *xdp,
-				   struct rx_cmp_ext *rxcmp1);
+				   struct xdp_buff *xdp);
 #endif
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
index 0715ea5bf13e..3b082114f2e5 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
@@ -41,9 +41,12 @@ void bcmgenet_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
 	struct device *kdev = &priv->pdev->dev;
+	u32 phy_wolopts = 0;
 
-	if (dev->phydev)
+	if (dev->phydev) {
 		phy_ethtool_get_wol(dev->phydev, wol);
+		phy_wolopts = wol->wolopts;
+	}
 
 	/* MAC is not wake-up capable, return what the PHY does */
 	if (!device_can_wakeup(kdev))
@@ -51,9 +54,14 @@ void bcmgenet_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 
 	/* Overlay MAC capabilities with that of the PHY queried before */
 	wol->supported |= WAKE_MAGIC | WAKE_MAGICSECURE | WAKE_FILTER;
-	wol->wolopts = priv->wolopts;
-	memset(wol->sopass, 0, sizeof(wol->sopass));
+	wol->wolopts |= priv->wolopts;
 
+	/* Return the PHY configured magic password */
+	if (phy_wolopts & WAKE_MAGICSECURE)
+		return;
+
+	/* Otherwise the MAC one */
+	memset(wol->sopass, 0, sizeof(wol->sopass));
 	if (wol->wolopts & WAKE_MAGICSECURE)
 		memcpy(wol->sopass, priv->sopass, sizeof(priv->sopass));
 }
@@ -70,7 +78,7 @@ int bcmgenet_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 	/* Try Wake-on-LAN from the PHY first */
 	if (dev->phydev) {
 		ret = phy_ethtool_set_wol(dev->phydev, wol);
-		if (ret != -EOPNOTSUPP)
+		if (ret != -EOPNOTSUPP && wol->wolopts)
 			return ret;
 	}
 
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index d178138981a9..717e110d23c9 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -55,6 +55,7 @@
 #include <linux/hwmon.h>
 #include <linux/hwmon-sysfs.h>
 #include <linux/crc32poly.h>
+#include <linux/dmi.h>
 
 #include <net/checksum.h>
 #include <net/gso.h>
@@ -18154,6 +18155,50 @@ unlock:
 
 static SIMPLE_DEV_PM_OPS(tg3_pm_ops, tg3_suspend, tg3_resume);
 
+/* Systems where ACPI _PTS (Prepare To Sleep) S5 will result in a fatal
+ * PCIe AER event on the tg3 device if the tg3 device is not, or cannot
+ * be, powered down.
+ */
+static const struct dmi_system_id tg3_restart_aer_quirk_table[] = {
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge R440"),
+		},
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge R540"),
+		},
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge R640"),
+		},
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge R650"),
+		},
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge R740"),
+		},
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge R750"),
+		},
+	},
+	{}
+};
+
 static void tg3_shutdown(struct pci_dev *pdev)
 {
 	struct net_device *dev = pci_get_drvdata(pdev);
@@ -18170,6 +18215,19 @@ static void tg3_shutdown(struct pci_dev *pdev)
 
 	if (system_state == SYSTEM_POWER_OFF)
 		tg3_power_down(tp);
+	else if (system_state == SYSTEM_RESTART &&
+		 dmi_first_match(tg3_restart_aer_quirk_table) &&
+		 pdev->current_state != PCI_D3cold &&
+		 pdev->current_state != PCI_UNKNOWN) {
+		/* Disable PCIe AER on the tg3 to avoid a fatal
+		 * error during this system restart.
+		 */
+		pcie_capability_clear_word(pdev, PCI_EXP_DEVCTL,
+					   PCI_EXP_DEVCTL_CERE |
+					   PCI_EXP_DEVCTL_NFERE |
+					   PCI_EXP_DEVCTL_FERE |
+					   PCI_EXP_DEVCTL_URRE);
+	}
 
 	rtnl_unlock();
 
diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h
index 5740c98d8c9f..2847278d9cd4 100644
--- a/drivers/net/ethernet/cadence/macb.h
+++ b/drivers/net/ethernet/cadence/macb.h
@@ -1279,6 +1279,8 @@ struct macb {
 	struct clk		*rx_clk;
 	struct clk		*tsu_clk;
 	struct net_device	*dev;
+	/* Protects hw_stats and ethtool_stats */
+	spinlock_t		stats_lock;
 	union {
 		struct macb_stats	macb;
 		struct gem_stats	gem;
diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 56901280ba04..3c2a7919b128 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -1016,22 +1016,15 @@ static void macb_update_stats(struct macb *bp)
 
 static int macb_halt_tx(struct macb *bp)
 {
-	unsigned long	halt_time, timeout;
-	u32		status;
+	u32 status;
 
 	macb_writel(bp, NCR, macb_readl(bp, NCR) | MACB_BIT(THALT));
 
-	timeout = jiffies + usecs_to_jiffies(MACB_HALT_TIMEOUT);
-	do {
-		halt_time = jiffies;
-		status = macb_readl(bp, TSR);
-		if (!(status & MACB_BIT(TGO)))
-			return 0;
-
-		udelay(250);
-	} while (time_before(halt_time, timeout));
-
-	return -ETIMEDOUT;
+	/* Poll TSR until TGO is cleared or timeout. */
+	return read_poll_timeout_atomic(macb_readl, status,
+					!(status & MACB_BIT(TGO)),
+					250, MACB_HALT_TIMEOUT, false,
+					bp, TSR);
 }
 
 static void macb_tx_unmap(struct macb *bp, struct macb_tx_skb *tx_skb, int budget)
@@ -1992,10 +1985,12 @@ static irqreturn_t macb_interrupt(int irq, void *dev_id)
 
 		if (status & MACB_BIT(ISR_ROVR)) {
 			/* We missed at least one packet */
+			spin_lock(&bp->stats_lock);
 			if (macb_is_gem(bp))
 				bp->hw_stats.gem.rx_overruns++;
 			else
 				bp->hw_stats.macb.rx_overruns++;
+			spin_unlock(&bp->stats_lock);
 
 			if (bp->caps & MACB_CAPS_ISR_CLEAR_ON_WRITE)
 				queue_writel(queue, ISR, MACB_BIT(ISR_ROVR));
@@ -3116,6 +3111,7 @@ static struct net_device_stats *gem_get_stats(struct macb *bp)
 	if (!netif_running(bp->dev))
 		return nstat;
 
+	spin_lock_irq(&bp->stats_lock);
 	gem_update_stats(bp);
 
 	nstat->rx_errors = (hwstat->rx_frame_check_sequence_errors +
@@ -3145,6 +3141,7 @@ static struct net_device_stats *gem_get_stats(struct macb *bp)
 	nstat->tx_aborted_errors = hwstat->tx_excessive_collisions;
 	nstat->tx_carrier_errors = hwstat->tx_carrier_sense_errors;
 	nstat->tx_fifo_errors = hwstat->tx_underrun;
+	spin_unlock_irq(&bp->stats_lock);
 
 	return nstat;
 }
@@ -3152,12 +3149,13 @@ static struct net_device_stats *gem_get_stats(struct macb *bp)
 static void gem_get_ethtool_stats(struct net_device *dev,
 				  struct ethtool_stats *stats, u64 *data)
 {
-	struct macb *bp;
+	struct macb *bp = netdev_priv(dev);
 
-	bp = netdev_priv(dev);
+	spin_lock_irq(&bp->stats_lock);
 	gem_update_stats(bp);
 	memcpy(data, &bp->ethtool_stats, sizeof(u64)
 			* (GEM_STATS_LEN + QUEUE_STATS_LEN * MACB_MAX_QUEUES));
+	spin_unlock_irq(&bp->stats_lock);
 }
 
 static int gem_get_sset_count(struct net_device *dev, int sset)
@@ -3207,6 +3205,7 @@ static struct net_device_stats *macb_get_stats(struct net_device *dev)
 		return gem_get_stats(bp);
 
 	/* read stats from hardware */
+	spin_lock_irq(&bp->stats_lock);
 	macb_update_stats(bp);
 
 	/* Convert HW stats into netdevice stats */
@@ -3240,6 +3239,7 @@ static struct net_device_stats *macb_get_stats(struct net_device *dev)
 	nstat->tx_carrier_errors = hwstat->tx_carrier_errors;
 	nstat->tx_fifo_errors = hwstat->tx_underruns;
 	/* Don't know about heartbeat or window errors... */
+	spin_unlock_irq(&bp->stats_lock);
 
 	return nstat;
 }
@@ -5110,13 +5110,18 @@ static int macb_probe(struct platform_device *pdev)
 		}
 	}
 	spin_lock_init(&bp->lock);
+	spin_lock_init(&bp->stats_lock);
 
 	/* setup capabilities */
 	macb_configure_caps(bp, macb_config);
 
 #ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
 	if (GEM_BFEXT(DAW64, gem_readl(bp, DCFG6))) {
-		dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(44));
+		err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(44));
+		if (err) {
+			dev_err(&pdev->dev, "failed to set DMA mask\n");
+			goto err_out_free_netdev;
+		}
 		bp->hw_dma_cap |= HW_DMA_CAP_64B;
 	}
 #endif
diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
index 608cc6af5af1..aa80c3702232 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
@@ -1429,9 +1429,9 @@ static acpi_status bgx_acpi_match_id(acpi_handle handle, u32 lvl,
 {
 	struct acpi_buffer string = { ACPI_ALLOCATE_BUFFER, NULL };
 	struct bgx *bgx = context;
-	char bgx_sel[5];
+	char bgx_sel[7];
 
-	snprintf(bgx_sel, 5, "BGX%d", bgx->bgx_id);
+	snprintf(bgx_sel, sizeof(bgx_sel), "BGX%d", bgx->bgx_id);
 	if (ACPI_FAILURE(acpi_get_name(handle, ACPI_SINGLE_NAME, &string))) {
 		pr_warn("Invalid link device\n");
 		return AE_OK;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
index 7f3f5afa864f..1546c3db08f0 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
@@ -2270,6 +2270,7 @@ int cxgb4_init_ethtool_filters(struct adapter *adap)
 		eth_filter->port[i].bmap = bitmap_zalloc(nentries, GFP_KERNEL);
 		if (!eth_filter->port[i].bmap) {
 			ret = -ENOMEM;
+			kvfree(eth_filter->port[i].loc_array);
 			goto free_eth_finfo;
 		}
 	}
diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c
index ffed14b63d41..a432783756d8 100644
--- a/drivers/net/ethernet/cisco/enic/enic_main.c
+++ b/drivers/net/ethernet/cisco/enic/enic_main.c
@@ -2127,10 +2127,10 @@ static int enic_change_mtu(struct net_device *netdev, int new_mtu)
 	if (enic_is_dynamic(enic) || enic_is_sriov_vf(enic))
 		return -EOPNOTSUPP;
 
-	if (netdev->mtu > enic->port_mtu)
+	if (new_mtu > enic->port_mtu)
 		netdev_warn(netdev,
 			    "interface MTU (%d) set higher than port MTU (%d)\n",
-			    netdev->mtu, enic->port_mtu);
+			    new_mtu, enic->port_mtu);
 
 	return _enic_change_mtu(netdev, new_mtu);
 }
diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c
index 73e1c71c5092..92833eefc04b 100644
--- a/drivers/net/ethernet/cortina/gemini.c
+++ b/drivers/net/ethernet/cortina/gemini.c
@@ -1143,6 +1143,7 @@ static int gmac_map_tx_bufs(struct net_device *netdev, struct sk_buff *skb,
 	struct gmac_txdesc *txd;
 	skb_frag_t *skb_frag;
 	dma_addr_t mapping;
+	bool tcp = false;
 	void *buffer;
 	u16 mss;
 	int ret;
@@ -1150,6 +1151,13 @@ static int gmac_map_tx_bufs(struct net_device *netdev, struct sk_buff *skb,
 	word1 = skb->len;
 	word3 = SOF_BIT;
 
+	/* Determine if we are doing TCP */
+	if (skb->protocol == htons(ETH_P_IP))
+		tcp = (ip_hdr(skb)->protocol == IPPROTO_TCP);
+	else
+		/* IPv6 */
+		tcp = (ipv6_hdr(skb)->nexthdr == IPPROTO_TCP);
+
 	mss = skb_shinfo(skb)->gso_size;
 	if (mss) {
 		/* This means we are dealing with TCP and skb->len is the
@@ -1162,8 +1170,26 @@ static int gmac_map_tx_bufs(struct net_device *netdev, struct sk_buff *skb,
 			   mss, skb->len);
 		word1 |= TSS_MTU_ENABLE_BIT;
 		word3 |= mss;
+	} else if (tcp) {
+		/* Even if we are not using TSO, use the hardware offloader
+		 * for transferring the TCP frame: this hardware has partial
+		 * TCP awareness (called TOE - TCP Offload Engine) and will
+		 * according to the datasheet put packets belonging to the
+		 * same TCP connection in the same queue for the TOE/TSO
+		 * engine to process. The engine will deal with chopping
+		 * up frames that exceed ETH_DATA_LEN which the
+		 * checksumming engine cannot handle (see below) into
+		 * manageable chunks. It flawlessly deals with quite big
+		 * frames and frames containing custom DSA EtherTypes.
+		 */
+		mss = netdev->mtu + skb_tcp_all_headers(skb);
+		mss = min(mss, skb->len);
+		netdev_dbg(netdev, "TOE/TSO len %04x mtu %04x mss %04x\n",
+			   skb->len, netdev->mtu, mss);
+		word1 |= TSS_MTU_ENABLE_BIT;
+		word3 |= mss;
 	} else if (skb->len >= ETH_FRAME_LEN) {
-		/* Hardware offloaded checksumming isn't working on frames
+		/* Hardware offloaded checksumming isn't working on non-TCP frames
 		 * bigger than 1514 bytes. A hypothesis about this is that the
 		 * checksum buffer is only 1518 bytes, so when the frames get
 		 * bigger they get truncated, or the last few bytes get
@@ -1180,21 +1206,16 @@ static int gmac_map_tx_bufs(struct net_device *netdev, struct sk_buff *skb,
 	}
 
 	if (skb->ip_summed == CHECKSUM_PARTIAL) {
-		int tcp = 0;
-
 		/* We do not switch off the checksumming on non TCP/UDP
 		 * frames: as is shown from tests, the checksumming engine
 		 * is smart enough to see that a frame is not actually TCP
 		 * or UDP and then just pass it through without any changes
 		 * to the frame.
 		 */
-		if (skb->protocol == htons(ETH_P_IP)) {
+		if (skb->protocol == htons(ETH_P_IP))
 			word1 |= TSS_IP_CHKSUM_BIT;
-			tcp = ip_hdr(skb)->protocol == IPPROTO_TCP;
-		} else { /* IPv6 */
+		else
 			word1 |= TSS_IPV6_ENABLE_BIT;
-			tcp = ipv6_hdr(skb)->nexthdr == IPPROTO_TCP;
-		}
 
 		word1 |= tcp ? TSS_TCP_CHKSUM_BIT : TSS_UDP_CHKSUM_BIT;
 	}
diff --git a/drivers/net/ethernet/davicom/dm9000.c b/drivers/net/ethernet/davicom/dm9000.c
index 150cc94ae9f8..25a604379b2f 100644
--- a/drivers/net/ethernet/davicom/dm9000.c
+++ b/drivers/net/ethernet/davicom/dm9000.c
@@ -1777,10 +1777,11 @@ static void dm9000_drv_remove(struct platform_device *pdev)
 
 	unregister_netdev(ndev);
 	dm9000_release_board(pdev, dm);
-	free_netdev(ndev);		/* free device structure */
 	if (dm->power_supply)
 		regulator_disable(dm->power_supply);
 
+	free_netdev(ndev);		/* free device structure */
+
 	dev_dbg(&pdev->dev, "released and freed device\n");
 }
 
diff --git a/drivers/net/ethernet/dlink/dl2k.c b/drivers/net/ethernet/dlink/dl2k.c
index d0ea92607870..787218d60c6b 100644
--- a/drivers/net/ethernet/dlink/dl2k.c
+++ b/drivers/net/ethernet/dlink/dl2k.c
@@ -146,6 +146,8 @@ rio_probe1 (struct pci_dev *pdev, const struct pci_device_id *ent)
 	np->ioaddr = ioaddr;
 	np->chip_id = chip_idx;
 	np->pdev = pdev;
+
+	spin_lock_init(&np->stats_lock);
 	spin_lock_init (&np->tx_lock);
 	spin_lock_init (&np->rx_lock);
 
@@ -352,7 +354,7 @@ parse_eeprom (struct net_device *dev)
 	eth_hw_addr_set(dev, psrom->mac_addr);
 
 	if (np->chip_id == CHIP_IP1000A) {
-		np->led_mode = psrom->led_mode;
+		np->led_mode = le16_to_cpu(psrom->led_mode);
 		return 0;
 	}
 
@@ -865,7 +867,6 @@ tx_error (struct net_device *dev, int tx_status)
 	frame_id = (tx_status & 0xffff0000);
 	printk (KERN_ERR "%s: Transmit error, TxStatus %4.4x, FrameId %d.\n",
 		dev->name, tx_status, frame_id);
-	dev->stats.tx_errors++;
 	/* Ttransmit Underrun */
 	if (tx_status & 0x10) {
 		dev->stats.tx_fifo_errors++;
@@ -902,9 +903,15 @@ tx_error (struct net_device *dev, int tx_status)
 		rio_set_led_mode(dev);
 		/* Let TxStartThresh stay default value */
 	}
+
+	spin_lock(&np->stats_lock);
 	/* Maximum Collisions */
 	if (tx_status & 0x08)
 		dev->stats.collisions++;
+
+	dev->stats.tx_errors++;
+	spin_unlock(&np->stats_lock);
+
 	/* Restart the Tx */
 	dw32(MACCtrl, dr16(MACCtrl) | TxEnable);
 }
@@ -1073,7 +1080,9 @@ get_stats (struct net_device *dev)
 	int i;
 #endif
 	unsigned int stat_reg;
+	unsigned long flags;
 
+	spin_lock_irqsave(&np->stats_lock, flags);
 	/* All statistics registers need to be acknowledged,
 	   else statistic overflow could cause problems */
 
@@ -1123,6 +1132,9 @@ get_stats (struct net_device *dev)
 	dr16(TCPCheckSumErrors);
 	dr16(UDPCheckSumErrors);
 	dr16(IPCheckSumErrors);
+
+	spin_unlock_irqrestore(&np->stats_lock, flags);
+
 	return &dev->stats;
 }
 
diff --git a/drivers/net/ethernet/dlink/dl2k.h b/drivers/net/ethernet/dlink/dl2k.h
index 195dc6cfd895..56aff2f0bdbf 100644
--- a/drivers/net/ethernet/dlink/dl2k.h
+++ b/drivers/net/ethernet/dlink/dl2k.h
@@ -335,7 +335,7 @@ typedef struct t_SROM {
 	u16 sub_system_id;	/* 0x06 */
 	u16 pci_base_1;		/* 0x08 (IP1000A only) */
 	u16 pci_base_2;		/* 0x0a (IP1000A only) */
-	u16 led_mode;		/* 0x0c (IP1000A only) */
+	__le16 led_mode;	/* 0x0c (IP1000A only) */
 	u16 reserved1[9];	/* 0x0e-0x1f */
 	u8 mac_addr[6];		/* 0x20-0x25 */
 	u8 reserved2[10];	/* 0x26-0x2f */
@@ -372,6 +372,8 @@ struct netdev_private {
 	struct pci_dev *pdev;
 	void __iomem *ioaddr;
 	void __iomem *eeprom_addr;
+	// To ensure synchronization when stats are updated.
+	spinlock_t stats_lock;
 	spinlock_t tx_lock;
 	spinlock_t rx_lock;
 	unsigned int rx_buf_sz;		/* Based on MTU+slack. */
diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h
index e48b861e4ce1..270ff9aab335 100644
--- a/drivers/net/ethernet/emulex/benet/be.h
+++ b/drivers/net/ethernet/emulex/benet/be.h
@@ -562,7 +562,7 @@ struct be_adapter {
 	struct be_dma_mem mbox_mem_alloced;
 
 	struct be_mcc_obj mcc_obj;
-	struct mutex mcc_lock;	/* For serializing mcc cmds to BE card */
+	spinlock_t mcc_lock;	/* For serializing mcc cmds to BE card */
 	spinlock_t mcc_cq_lock;
 
 	u16 cfg_num_rx_irqs;		/* configured via set-channels */
diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c
index 61adcebeef01..779f1324bb5f 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.c
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.c
@@ -575,7 +575,7 @@ int be_process_mcc(struct be_adapter *adapter)
 /* Wait till no more pending mcc requests are present */
 static int be_mcc_wait_compl(struct be_adapter *adapter)
 {
-#define mcc_timeout		12000 /* 12s timeout */
+#define mcc_timeout		120000 /* 12s timeout */
 	int i, status = 0;
 	struct be_mcc_obj *mcc_obj = &adapter->mcc_obj;
 
@@ -589,7 +589,7 @@ static int be_mcc_wait_compl(struct be_adapter *adapter)
 
 		if (atomic_read(&mcc_obj->q.used) == 0)
 			break;
-		usleep_range(500, 1000);
+		udelay(100);
 	}
 	if (i == mcc_timeout) {
 		dev_err(&adapter->pdev->dev, "FW not responding\n");
@@ -866,7 +866,7 @@ static bool use_mcc(struct be_adapter *adapter)
 static int be_cmd_lock(struct be_adapter *adapter)
 {
 	if (use_mcc(adapter)) {
-		mutex_lock(&adapter->mcc_lock);
+		spin_lock_bh(&adapter->mcc_lock);
 		return 0;
 	} else {
 		return mutex_lock_interruptible(&adapter->mbox_lock);
@@ -877,7 +877,7 @@ static int be_cmd_lock(struct be_adapter *adapter)
 static void be_cmd_unlock(struct be_adapter *adapter)
 {
 	if (use_mcc(adapter))
-		return mutex_unlock(&adapter->mcc_lock);
+		return spin_unlock_bh(&adapter->mcc_lock);
 	else
 		return mutex_unlock(&adapter->mbox_lock);
 }
@@ -1047,7 +1047,7 @@ int be_cmd_mac_addr_query(struct be_adapter *adapter, u8 *mac_addr,
 	struct be_cmd_req_mac_query *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -1076,7 +1076,7 @@ int be_cmd_mac_addr_query(struct be_adapter *adapter, u8 *mac_addr,
 	}
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -1088,7 +1088,7 @@ int be_cmd_pmac_add(struct be_adapter *adapter, const u8 *mac_addr,
 	struct be_cmd_req_pmac_add *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -1113,7 +1113,7 @@ int be_cmd_pmac_add(struct be_adapter *adapter, const u8 *mac_addr,
 	}
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 
 	if (base_status(status) == MCC_STATUS_UNAUTHORIZED_REQUEST)
 		status = -EPERM;
@@ -1131,7 +1131,7 @@ int be_cmd_pmac_del(struct be_adapter *adapter, u32 if_id, int pmac_id, u32 dom)
 	if (pmac_id == -1)
 		return 0;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -1151,7 +1151,7 @@ int be_cmd_pmac_del(struct be_adapter *adapter, u32 if_id, int pmac_id, u32 dom)
 	status = be_mcc_notify_wait(adapter);
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -1414,7 +1414,7 @@ int be_cmd_rxq_create(struct be_adapter *adapter,
 	struct be_dma_mem *q_mem = &rxq->dma_mem;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -1444,7 +1444,7 @@ int be_cmd_rxq_create(struct be_adapter *adapter,
 	}
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -1508,7 +1508,7 @@ int be_cmd_rxq_destroy(struct be_adapter *adapter, struct be_queue_info *q)
 	struct be_cmd_req_q_destroy *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -1525,7 +1525,7 @@ int be_cmd_rxq_destroy(struct be_adapter *adapter, struct be_queue_info *q)
 	q->created = false;
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -1593,7 +1593,7 @@ int be_cmd_get_stats(struct be_adapter *adapter, struct be_dma_mem *nonemb_cmd)
 	struct be_cmd_req_hdr *hdr;
 	int status = 0;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -1609,7 +1609,7 @@ int be_cmd_get_stats(struct be_adapter *adapter, struct be_dma_mem *nonemb_cmd)
 	/* version 1 of the cmd is not supported only by BE2 */
 	if (BE2_chip(adapter))
 		hdr->version = 0;
-	if (BE3_chip(adapter) || lancer_chip(adapter))
+	else if (BE3_chip(adapter) || lancer_chip(adapter))
 		hdr->version = 1;
 	else
 		hdr->version = 2;
@@ -1621,7 +1621,7 @@ int be_cmd_get_stats(struct be_adapter *adapter, struct be_dma_mem *nonemb_cmd)
 	adapter->stats_cmd_sent = true;
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -1637,7 +1637,7 @@ int lancer_cmd_get_pport_stats(struct be_adapter *adapter,
 			    CMD_SUBSYSTEM_ETH))
 		return -EPERM;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -1660,7 +1660,7 @@ int lancer_cmd_get_pport_stats(struct be_adapter *adapter,
 	adapter->stats_cmd_sent = true;
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -1697,7 +1697,7 @@ int be_cmd_link_status_query(struct be_adapter *adapter, u16 *link_speed,
 	struct be_cmd_req_link_status *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	if (link_status)
 		*link_status = LINK_DOWN;
@@ -1736,7 +1736,7 @@ int be_cmd_link_status_query(struct be_adapter *adapter, u16 *link_speed,
 	}
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -1747,7 +1747,7 @@ int be_cmd_get_die_temperature(struct be_adapter *adapter)
 	struct be_cmd_req_get_cntl_addnl_attribs *req;
 	int status = 0;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -1762,7 +1762,7 @@ int be_cmd_get_die_temperature(struct be_adapter *adapter)
 
 	status = be_mcc_notify(adapter);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -1811,7 +1811,7 @@ int be_cmd_get_fat_dump(struct be_adapter *adapter, u32 buf_len, void *buf)
 	if (!get_fat_cmd.va)
 		return -ENOMEM;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	while (total_size) {
 		buf_size = min(total_size, (u32)60 * 1024);
@@ -1849,9 +1849,9 @@ int be_cmd_get_fat_dump(struct be_adapter *adapter, u32 buf_len, void *buf)
 		log_offset += buf_size;
 	}
 err:
+	spin_unlock_bh(&adapter->mcc_lock);
 	dma_free_coherent(&adapter->pdev->dev, get_fat_cmd.size,
 			  get_fat_cmd.va, get_fat_cmd.dma);
-	mutex_unlock(&adapter->mcc_lock);
 	return status;
 }
 
@@ -1862,7 +1862,7 @@ int be_cmd_get_fw_ver(struct be_adapter *adapter)
 	struct be_cmd_req_get_fw_version *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -1885,7 +1885,7 @@ int be_cmd_get_fw_ver(struct be_adapter *adapter)
 			sizeof(adapter->fw_on_flash));
 	}
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -1899,7 +1899,7 @@ static int __be_cmd_modify_eqd(struct be_adapter *adapter,
 	struct be_cmd_req_modify_eq_delay *req;
 	int status = 0, i;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -1922,7 +1922,7 @@ static int __be_cmd_modify_eqd(struct be_adapter *adapter,
 
 	status = be_mcc_notify(adapter);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -1949,7 +1949,7 @@ int be_cmd_vlan_config(struct be_adapter *adapter, u32 if_id, u16 *vtag_array,
 	struct be_cmd_req_vlan_config *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -1971,7 +1971,7 @@ int be_cmd_vlan_config(struct be_adapter *adapter, u32 if_id, u16 *vtag_array,
 
 	status = be_mcc_notify_wait(adapter);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -1982,7 +1982,7 @@ static int __be_cmd_rx_filter(struct be_adapter *adapter, u32 flags, u32 value)
 	struct be_cmd_req_rx_filter *req = mem->va;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -2015,7 +2015,7 @@ static int __be_cmd_rx_filter(struct be_adapter *adapter, u32 flags, u32 value)
 
 	status = be_mcc_notify_wait(adapter);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -2046,7 +2046,7 @@ int be_cmd_set_flow_control(struct be_adapter *adapter, u32 tx_fc, u32 rx_fc)
 			    CMD_SUBSYSTEM_COMMON))
 		return -EPERM;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -2066,7 +2066,7 @@ int be_cmd_set_flow_control(struct be_adapter *adapter, u32 tx_fc, u32 rx_fc)
 	status = be_mcc_notify_wait(adapter);
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 
 	if (base_status(status) == MCC_STATUS_FEATURE_NOT_SUPPORTED)
 		return  -EOPNOTSUPP;
@@ -2085,7 +2085,7 @@ int be_cmd_get_flow_control(struct be_adapter *adapter, u32 *tx_fc, u32 *rx_fc)
 			    CMD_SUBSYSTEM_COMMON))
 		return -EPERM;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -2108,7 +2108,7 @@ int be_cmd_get_flow_control(struct be_adapter *adapter, u32 *tx_fc, u32 *rx_fc)
 	}
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -2189,7 +2189,7 @@ int be_cmd_rss_config(struct be_adapter *adapter, u8 *rsstable,
 	if (!(be_if_cap_flags(adapter) & BE_IF_FLAGS_RSS))
 		return 0;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -2214,7 +2214,7 @@ int be_cmd_rss_config(struct be_adapter *adapter, u8 *rsstable,
 
 	status = be_mcc_notify_wait(adapter);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -2226,7 +2226,7 @@ int be_cmd_set_beacon_state(struct be_adapter *adapter, u8 port_num,
 	struct be_cmd_req_enable_disable_beacon *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -2247,7 +2247,7 @@ int be_cmd_set_beacon_state(struct be_adapter *adapter, u8 port_num,
 	status = be_mcc_notify_wait(adapter);
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -2258,7 +2258,7 @@ int be_cmd_get_beacon_state(struct be_adapter *adapter, u8 port_num, u32 *state)
 	struct be_cmd_req_get_beacon_state *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -2282,7 +2282,7 @@ int be_cmd_get_beacon_state(struct be_adapter *adapter, u8 port_num, u32 *state)
 	}
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -2306,7 +2306,7 @@ int be_cmd_read_port_transceiver_data(struct be_adapter *adapter,
 		return -ENOMEM;
 	}
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -2328,7 +2328,7 @@ int be_cmd_read_port_transceiver_data(struct be_adapter *adapter,
 		memcpy(data, resp->page_data + off, len);
 	}
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	dma_free_coherent(&adapter->pdev->dev, cmd.size, cmd.va, cmd.dma);
 	return status;
 }
@@ -2345,7 +2345,7 @@ static int lancer_cmd_write_object(struct be_adapter *adapter,
 	void *ctxt = NULL;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 	adapter->flash_status = 0;
 
 	wrb = wrb_from_mccq(adapter);
@@ -2387,7 +2387,7 @@ static int lancer_cmd_write_object(struct be_adapter *adapter,
 	if (status)
 		goto err_unlock;
 
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 
 	if (!wait_for_completion_timeout(&adapter->et_cmd_compl,
 					 msecs_to_jiffies(60000)))
@@ -2406,7 +2406,7 @@ static int lancer_cmd_write_object(struct be_adapter *adapter,
 	return status;
 
 err_unlock:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -2460,7 +2460,7 @@ static int lancer_cmd_delete_object(struct be_adapter *adapter,
 	struct be_mcc_wrb *wrb;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -2478,7 +2478,7 @@ static int lancer_cmd_delete_object(struct be_adapter *adapter,
 
 	status = be_mcc_notify_wait(adapter);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -2491,7 +2491,7 @@ int lancer_cmd_read_object(struct be_adapter *adapter, struct be_dma_mem *cmd,
 	struct lancer_cmd_resp_read_object *resp;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -2525,7 +2525,7 @@ int lancer_cmd_read_object(struct be_adapter *adapter, struct be_dma_mem *cmd,
 	}
 
 err_unlock:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -2537,7 +2537,7 @@ static int be_cmd_write_flashrom(struct be_adapter *adapter,
 	struct be_cmd_write_flashrom *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 	adapter->flash_status = 0;
 
 	wrb = wrb_from_mccq(adapter);
@@ -2562,7 +2562,7 @@ static int be_cmd_write_flashrom(struct be_adapter *adapter,
 	if (status)
 		goto err_unlock;
 
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 
 	if (!wait_for_completion_timeout(&adapter->et_cmd_compl,
 					 msecs_to_jiffies(40000)))
@@ -2573,7 +2573,7 @@ static int be_cmd_write_flashrom(struct be_adapter *adapter,
 	return status;
 
 err_unlock:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -2584,7 +2584,7 @@ static int be_cmd_get_flash_crc(struct be_adapter *adapter, u8 *flashed_crc,
 	struct be_mcc_wrb *wrb;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -2611,7 +2611,7 @@ static int be_cmd_get_flash_crc(struct be_adapter *adapter, u8 *flashed_crc,
 		memcpy(flashed_crc, req->crc, 4);
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -3217,7 +3217,7 @@ int be_cmd_enable_magic_wol(struct be_adapter *adapter, u8 *mac,
 	struct be_cmd_req_acpi_wol_magic_config *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3234,7 +3234,7 @@ int be_cmd_enable_magic_wol(struct be_adapter *adapter, u8 *mac,
 	status = be_mcc_notify_wait(adapter);
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -3249,7 +3249,7 @@ int be_cmd_set_loopback(struct be_adapter *adapter, u8 port_num,
 			    CMD_SUBSYSTEM_LOWLEVEL))
 		return -EPERM;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3272,7 +3272,7 @@ int be_cmd_set_loopback(struct be_adapter *adapter, u8 port_num,
 	if (status)
 		goto err_unlock;
 
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 
 	if (!wait_for_completion_timeout(&adapter->et_cmd_compl,
 					 msecs_to_jiffies(SET_LB_MODE_TIMEOUT)))
@@ -3281,7 +3281,7 @@ int be_cmd_set_loopback(struct be_adapter *adapter, u8 port_num,
 	return status;
 
 err_unlock:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -3298,7 +3298,7 @@ int be_cmd_loopback_test(struct be_adapter *adapter, u32 port_num,
 			    CMD_SUBSYSTEM_LOWLEVEL))
 		return -EPERM;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3324,7 +3324,7 @@ int be_cmd_loopback_test(struct be_adapter *adapter, u32 port_num,
 	if (status)
 		goto err;
 
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 
 	wait_for_completion(&adapter->et_cmd_compl);
 	resp = embedded_payload(wrb);
@@ -3332,7 +3332,7 @@ int be_cmd_loopback_test(struct be_adapter *adapter, u32 port_num,
 
 	return status;
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -3348,7 +3348,7 @@ int be_cmd_ddr_dma_test(struct be_adapter *adapter, u64 pattern,
 			    CMD_SUBSYSTEM_LOWLEVEL))
 		return -EPERM;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3382,7 +3382,7 @@ int be_cmd_ddr_dma_test(struct be_adapter *adapter, u64 pattern,
 	}
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -3393,7 +3393,7 @@ int be_cmd_get_seeprom_data(struct be_adapter *adapter,
 	struct be_cmd_req_seeprom_read *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3409,7 +3409,7 @@ int be_cmd_get_seeprom_data(struct be_adapter *adapter,
 	status = be_mcc_notify_wait(adapter);
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -3424,7 +3424,7 @@ int be_cmd_get_phy_info(struct be_adapter *adapter)
 			    CMD_SUBSYSTEM_COMMON))
 		return -EPERM;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3469,7 +3469,7 @@ int be_cmd_get_phy_info(struct be_adapter *adapter)
 	}
 	dma_free_coherent(&adapter->pdev->dev, cmd.size, cmd.va, cmd.dma);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -3479,7 +3479,7 @@ static int be_cmd_set_qos(struct be_adapter *adapter, u32 bps, u32 domain)
 	struct be_cmd_req_set_qos *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3499,7 +3499,7 @@ static int be_cmd_set_qos(struct be_adapter *adapter, u32 bps, u32 domain)
 	status = be_mcc_notify_wait(adapter);
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -3611,7 +3611,7 @@ int be_cmd_get_fn_privileges(struct be_adapter *adapter, u32 *privilege,
 	struct be_cmd_req_get_fn_privileges *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3643,7 +3643,7 @@ int be_cmd_get_fn_privileges(struct be_adapter *adapter, u32 *privilege,
 	}
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -3655,7 +3655,7 @@ int be_cmd_set_fn_privileges(struct be_adapter *adapter, u32 privileges,
 	struct be_cmd_req_set_fn_privileges *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3675,7 +3675,7 @@ int be_cmd_set_fn_privileges(struct be_adapter *adapter, u32 privileges,
 
 	status = be_mcc_notify_wait(adapter);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -3707,7 +3707,7 @@ int be_cmd_get_mac_from_list(struct be_adapter *adapter, u8 *mac,
 		return -ENOMEM;
 	}
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3771,7 +3771,7 @@ int be_cmd_get_mac_from_list(struct be_adapter *adapter, u8 *mac,
 	}
 
 out:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	dma_free_coherent(&adapter->pdev->dev, get_mac_list_cmd.size,
 			  get_mac_list_cmd.va, get_mac_list_cmd.dma);
 	return status;
@@ -3831,7 +3831,7 @@ int be_cmd_set_mac_list(struct be_adapter *adapter, u8 *mac_array,
 	if (!cmd.va)
 		return -ENOMEM;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3852,8 +3852,8 @@ int be_cmd_set_mac_list(struct be_adapter *adapter, u8 *mac_array,
 	status = be_mcc_notify_wait(adapter);
 
 err:
+	spin_unlock_bh(&adapter->mcc_lock);
 	dma_free_coherent(&adapter->pdev->dev, cmd.size, cmd.va, cmd.dma);
-	mutex_unlock(&adapter->mcc_lock);
 	return status;
 }
 
@@ -3889,7 +3889,7 @@ int be_cmd_set_hsw_config(struct be_adapter *adapter, u16 pvid,
 			    CMD_SUBSYSTEM_COMMON))
 		return -EPERM;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3930,7 +3930,7 @@ int be_cmd_set_hsw_config(struct be_adapter *adapter, u16 pvid,
 	status = be_mcc_notify_wait(adapter);
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -3944,7 +3944,7 @@ int be_cmd_get_hsw_config(struct be_adapter *adapter, u16 *pvid,
 	int status;
 	u16 vid;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3991,7 +3991,7 @@ int be_cmd_get_hsw_config(struct be_adapter *adapter, u16 *pvid,
 	}
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -4190,7 +4190,7 @@ int be_cmd_set_ext_fat_capabilites(struct be_adapter *adapter,
 	struct be_cmd_req_set_ext_fat_caps *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -4206,7 +4206,7 @@ int be_cmd_set_ext_fat_capabilites(struct be_adapter *adapter,
 
 	status = be_mcc_notify_wait(adapter);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -4684,7 +4684,7 @@ int be_cmd_manage_iface(struct be_adapter *adapter, u32 iface, u8 op)
 	if (iface == 0xFFFFFFFF)
 		return -1;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -4701,7 +4701,7 @@ int be_cmd_manage_iface(struct be_adapter *adapter, u32 iface, u8 op)
 
 	status = be_mcc_notify_wait(adapter);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -4735,7 +4735,7 @@ int be_cmd_get_if_id(struct be_adapter *adapter, struct be_vf_cfg *vf_cfg,
 	struct be_cmd_resp_get_iface_list *resp;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -4756,7 +4756,7 @@ int be_cmd_get_if_id(struct be_adapter *adapter, struct be_vf_cfg *vf_cfg,
 	}
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -4850,7 +4850,7 @@ int be_cmd_enable_vf(struct be_adapter *adapter, u8 domain)
 	if (BEx_chip(adapter))
 		return 0;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -4868,7 +4868,7 @@ int be_cmd_enable_vf(struct be_adapter *adapter, u8 domain)
 	req->enable = 1;
 	status = be_mcc_notify_wait(adapter);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -4941,7 +4941,7 @@ __be_cmd_set_logical_link_config(struct be_adapter *adapter,
 	u32 link_config = 0;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -4969,7 +4969,7 @@ __be_cmd_set_logical_link_config(struct be_adapter *adapter,
 
 	status = be_mcc_notify_wait(adapter);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -5000,8 +5000,7 @@ int be_cmd_set_features(struct be_adapter *adapter)
 	struct be_mcc_wrb *wrb;
 	int status;
 
-	if (mutex_lock_interruptible(&adapter->mcc_lock))
-		return -1;
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -5039,7 +5038,7 @@ err:
 		dev_info(&adapter->pdev->dev,
 			 "Adapter does not support HW error recovery\n");
 
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -5053,7 +5052,7 @@ int be_roce_mcc_cmd(void *netdev_handle, void *wrb_payload,
 	struct be_cmd_resp_hdr *resp;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -5076,7 +5075,7 @@ int be_roce_mcc_cmd(void *netdev_handle, void *wrb_payload,
 	memcpy(wrb_payload, resp, sizeof(*resp) + resp->response_length);
 	be_dws_le_to_cpu(wrb_payload, sizeof(*resp) + resp->response_length);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 EXPORT_SYMBOL(be_roce_mcc_cmd);
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 875fe379eea2..490af6659429 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -1465,10 +1465,10 @@ static void be_tx_timeout(struct net_device *netdev, unsigned int txqueue)
 						 ntohs(tcphdr->source));
 					dev_info(dev, "TCP dest port %d\n",
 						 ntohs(tcphdr->dest));
-					dev_info(dev, "TCP sequence num %d\n",
-						 ntohs(tcphdr->seq));
-					dev_info(dev, "TCP ack_seq %d\n",
-						 ntohs(tcphdr->ack_seq));
+					dev_info(dev, "TCP sequence num %u\n",
+						 ntohl(tcphdr->seq));
+					dev_info(dev, "TCP ack_seq %u\n",
+						 ntohl(tcphdr->ack_seq));
 				} else if (ip_hdr(skb)->protocol ==
 					   IPPROTO_UDP) {
 					udphdr = udp_hdr(skb);
@@ -5667,8 +5667,8 @@ static int be_drv_init(struct be_adapter *adapter)
 	}
 
 	mutex_init(&adapter->mbox_lock);
-	mutex_init(&adapter->mcc_lock);
 	mutex_init(&adapter->rx_filter_lock);
+	spin_lock_init(&adapter->mcc_lock);
 	spin_lock_init(&adapter->mcc_cq_lock);
 	init_completion(&adapter->et_cmd_compl);
 
diff --git a/drivers/net/ethernet/engleder/tsnep_main.c b/drivers/net/ethernet/engleder/tsnep_main.c
index 44da335d66bd..6a6efe2b2bc5 100644
--- a/drivers/net/ethernet/engleder/tsnep_main.c
+++ b/drivers/net/ethernet/engleder/tsnep_main.c
@@ -67,6 +67,8 @@
 #define TSNEP_TX_TYPE_XDP_NDO_MAP_PAGE	(TSNEP_TX_TYPE_XDP_NDO | TSNEP_TX_TYPE_MAP_PAGE)
 #define TSNEP_TX_TYPE_XDP		(TSNEP_TX_TYPE_XDP_TX | TSNEP_TX_TYPE_XDP_NDO)
 #define TSNEP_TX_TYPE_XSK		BIT(12)
+#define TSNEP_TX_TYPE_TSTAMP		BIT(13)
+#define TSNEP_TX_TYPE_SKB_TSTAMP	(TSNEP_TX_TYPE_SKB | TSNEP_TX_TYPE_TSTAMP)
 
 #define TSNEP_XDP_TX		BIT(0)
 #define TSNEP_XDP_REDIRECT	BIT(1)
@@ -387,8 +389,7 @@ static void tsnep_tx_activate(struct tsnep_tx *tx, int index, int length,
 	if (entry->skb) {
 		entry->properties = length & TSNEP_DESC_LENGTH_MASK;
 		entry->properties |= TSNEP_DESC_INTERRUPT_FLAG;
-		if ((entry->type & TSNEP_TX_TYPE_SKB) &&
-		    (skb_shinfo(entry->skb)->tx_flags & SKBTX_IN_PROGRESS))
+		if ((entry->type & TSNEP_TX_TYPE_SKB_TSTAMP) == TSNEP_TX_TYPE_SKB_TSTAMP)
 			entry->properties |= TSNEP_DESC_EXTENDED_WRITEBACK_FLAG;
 
 		/* toggle user flag to prevent false acknowledge
@@ -480,7 +481,8 @@ static int tsnep_tx_map_frag(skb_frag_t *frag, struct tsnep_tx_entry *entry,
 	return mapped;
 }
 
-static int tsnep_tx_map(struct sk_buff *skb, struct tsnep_tx *tx, int count)
+static int tsnep_tx_map(struct sk_buff *skb, struct tsnep_tx *tx, int count,
+			bool do_tstamp)
 {
 	struct device *dmadev = tx->adapter->dmadev;
 	struct tsnep_tx_entry *entry;
@@ -506,6 +508,9 @@ static int tsnep_tx_map(struct sk_buff *skb, struct tsnep_tx *tx, int count)
 				entry->type = TSNEP_TX_TYPE_SKB_INLINE;
 				mapped = 0;
 			}
+
+			if (do_tstamp)
+				entry->type |= TSNEP_TX_TYPE_TSTAMP;
 		} else {
 			skb_frag_t *frag = &skb_shinfo(skb)->frags[i - 1];
 
@@ -559,11 +564,12 @@ static int tsnep_tx_unmap(struct tsnep_tx *tx, int index, int count)
 static netdev_tx_t tsnep_xmit_frame_ring(struct sk_buff *skb,
 					 struct tsnep_tx *tx)
 {
-	int count = 1;
 	struct tsnep_tx_entry *entry;
+	bool do_tstamp = false;
+	int count = 1;
 	int length;
-	int i;
 	int retval;
+	int i;
 
 	if (skb_shinfo(skb)->nr_frags > 0)
 		count += skb_shinfo(skb)->nr_frags;
@@ -580,7 +586,13 @@ static netdev_tx_t tsnep_xmit_frame_ring(struct sk_buff *skb,
 	entry = &tx->entry[tx->write];
 	entry->skb = skb;
 
-	retval = tsnep_tx_map(skb, tx, count);
+	if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) &&
+	    tx->adapter->hwtstamp_config.tx_type == HWTSTAMP_TX_ON) {
+		skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
+		do_tstamp = true;
+	}
+
+	retval = tsnep_tx_map(skb, tx, count, do_tstamp);
 	if (retval < 0) {
 		tsnep_tx_unmap(tx, tx->write, count);
 		dev_kfree_skb_any(entry->skb);
@@ -592,9 +604,6 @@ static netdev_tx_t tsnep_xmit_frame_ring(struct sk_buff *skb,
 	}
 	length = retval;
 
-	if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)
-		skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
-
 	for (i = 0; i < count; i++)
 		tsnep_tx_activate(tx, (tx->write + i) & TSNEP_RING_MASK, length,
 				  i == count - 1);
@@ -845,8 +854,7 @@ static bool tsnep_tx_poll(struct tsnep_tx *tx, int napi_budget)
 
 		length = tsnep_tx_unmap(tx, tx->read, count);
 
-		if ((entry->type & TSNEP_TX_TYPE_SKB) &&
-		    (skb_shinfo(entry->skb)->tx_flags & SKBTX_IN_PROGRESS) &&
+		if (((entry->type & TSNEP_TX_TYPE_SKB_TSTAMP) == TSNEP_TX_TYPE_SKB_TSTAMP) &&
 		    (__le32_to_cpu(entry->desc_wb->properties) &
 		     TSNEP_DESC_EXTENDED_WRITEBACK_FLAG)) {
 			struct skb_shared_hwtstamps hwtstamps;
diff --git a/drivers/net/ethernet/faraday/Kconfig b/drivers/net/ethernet/faraday/Kconfig
index c699bd6bcbb9..474073c7f94d 100644
--- a/drivers/net/ethernet/faraday/Kconfig
+++ b/drivers/net/ethernet/faraday/Kconfig
@@ -31,6 +31,7 @@ config FTGMAC100
 	depends on ARM || COMPILE_TEST
 	depends on !64BIT || BROKEN
 	select PHYLIB
+	select FIXED_PHY
 	select MDIO_ASPEED if MACH_ASPEED_G6
 	select CRC32
 	help
diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c
index 0b61f548fd18..d41832ff8bbf 100644
--- a/drivers/net/ethernet/faraday/ftgmac100.c
+++ b/drivers/net/ethernet/faraday/ftgmac100.c
@@ -1730,16 +1730,17 @@ err_register_mdiobus:
 static void ftgmac100_phy_disconnect(struct net_device *netdev)
 {
 	struct ftgmac100 *priv = netdev_priv(netdev);
+	struct phy_device *phydev = netdev->phydev;
 
-	if (!netdev->phydev)
+	if (!phydev)
 		return;
 
-	phy_disconnect(netdev->phydev);
+	phy_disconnect(phydev);
 	if (of_phy_is_fixed_link(priv->dev->of_node))
 		of_phy_deregister_fixed_link(priv->dev->of_node);
 
 	if (priv->use_ncsi)
-		fixed_phy_unregister(netdev->phydev);
+		fixed_phy_unregister(phydev);
 }
 
 static void ftgmac100_destroy_mdio(struct net_device *netdev)
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
index e15dd3d858df..c5c1d3cb0278 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -28,7 +28,6 @@
 #include <linux/percpu.h>
 #include <linux/dma-mapping.h>
 #include <linux/sort.h>
-#include <linux/phy_fixed.h>
 #include <linux/bpf.h>
 #include <linux/bpf_trace.h>
 #include <soc/fsl/bman.h>
@@ -3129,7 +3128,6 @@ static const struct net_device_ops dpaa_ops = {
 	.ndo_stop = dpaa_eth_stop,
 	.ndo_tx_timeout = dpaa_tx_timeout,
 	.ndo_get_stats64 = dpaa_get_stats64,
-	.ndo_change_carrier = fixed_phy_change_carrier,
 	.ndo_set_mac_address = dpaa_set_mac_address,
 	.ndo_validate_addr = eth_validate_addr,
 	.ndo_set_rx_mode = dpaa_set_rx_mode,
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c
index b0060cf96090..51ee995c6148 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c
@@ -415,8 +415,10 @@ static int dpaa_get_ts_info(struct net_device *net_dev,
 		of_node_put(ptp_node);
 	}
 
-	if (ptp_dev)
+	if (ptp_dev) {
 		ptp = platform_get_drvdata(ptp_dev);
+		put_device(&ptp_dev->dev);
+	}
 
 	if (ptp)
 		info->phc_index = ptp->phc_index;
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index 29886a8ba73f..c744e10e6403 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -3928,6 +3928,7 @@ static int dpaa2_eth_setup_rx_flow(struct dpaa2_eth_priv *priv,
 					 MEM_TYPE_PAGE_ORDER0, NULL);
 	if (err) {
 		dev_err(dev, "xdp_rxq_info_reg_mem_model failed\n");
+		xdp_rxq_info_unreg(&fq->channel->xdp_rxq);
 		return err;
 	}
 
@@ -4421,17 +4422,25 @@ static int dpaa2_eth_bind_dpni(struct dpaa2_eth_priv *priv)
 			return -EINVAL;
 		}
 		if (err)
-			return err;
+			goto out;
 	}
 
 	err = dpni_get_qdid(priv->mc_io, 0, priv->mc_token,
 			    DPNI_QUEUE_TX, &priv->tx_qdid);
 	if (err) {
 		dev_err(dev, "dpni_get_qdid() failed\n");
-		return err;
+		goto out;
 	}
 
 	return 0;
+
+out:
+	while (i--) {
+		if (priv->fq[i].type == DPAA2_RX_FQ &&
+		    xdp_rxq_info_is_reg(&priv->fq[i].channel->xdp_rxq))
+			xdp_rxq_info_unreg(&priv->fq[i].channel->xdp_rxq);
+	}
+	return err;
 }
 
 /* Allocate rings for storing incoming frame descriptors */
@@ -4646,12 +4655,19 @@ static int dpaa2_eth_connect_mac(struct dpaa2_eth_priv *priv)
 		return PTR_ERR(dpmac_dev);
 	}
 
-	if (IS_ERR(dpmac_dev) || dpmac_dev->dev.type != &fsl_mc_bus_dpmac_type)
+	if (IS_ERR(dpmac_dev))
 		return 0;
 
+	if (dpmac_dev->dev.type != &fsl_mc_bus_dpmac_type) {
+		err = 0;
+		goto out_put_device;
+	}
+
 	mac = kzalloc(sizeof(struct dpaa2_mac), GFP_KERNEL);
-	if (!mac)
-		return -ENOMEM;
+	if (!mac) {
+		err = -ENOMEM;
+		goto out_put_device;
+	}
 
 	mac->mc_dev = dpmac_dev;
 	mac->mc_io = priv->mc_io;
@@ -4685,6 +4701,8 @@ err_close_mac:
 	dpaa2_mac_close(mac);
 err_free_mac:
 	kfree(mac);
+out_put_device:
+	put_device(&dpmac_dev->dev);
 	return err;
 }
 
@@ -4814,6 +4832,17 @@ static void dpaa2_eth_del_ch_napi(struct dpaa2_eth_priv *priv)
 	}
 }
 
+static void dpaa2_eth_free_rx_xdp_rxq(struct dpaa2_eth_priv *priv)
+{
+	int i;
+
+	for (i = 0; i < priv->num_fqs; i++) {
+		if (priv->fq[i].type == DPAA2_RX_FQ &&
+		    xdp_rxq_info_is_reg(&priv->fq[i].channel->xdp_rxq))
+			xdp_rxq_info_unreg(&priv->fq[i].channel->xdp_rxq);
+	}
+}
+
 static int dpaa2_eth_probe(struct fsl_mc_device *dpni_dev)
 {
 	struct device *dev;
@@ -5017,6 +5046,7 @@ err_alloc_percpu_extras:
 	free_percpu(priv->percpu_stats);
 err_alloc_percpu_stats:
 	dpaa2_eth_del_ch_napi(priv);
+	dpaa2_eth_free_rx_xdp_rxq(priv);
 err_bind:
 	dpaa2_eth_free_dpbps(priv);
 err_dpbp_setup:
@@ -5069,6 +5099,7 @@ static void dpaa2_eth_remove(struct fsl_mc_device *ls_dev)
 	free_percpu(priv->percpu_extras);
 
 	dpaa2_eth_del_ch_napi(priv);
+	dpaa2_eth_free_rx_xdp_rxq(priv);
 	dpaa2_eth_free_dpbps(priv);
 	dpaa2_eth_free_dpio(priv);
 	dpaa2_eth_free_dpni(priv);
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c
index a293b08f36d4..cbd3859ea475 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c
@@ -1447,12 +1447,19 @@ static int dpaa2_switch_port_connect_mac(struct ethsw_port_priv *port_priv)
 	if (PTR_ERR(dpmac_dev) == -EPROBE_DEFER)
 		return PTR_ERR(dpmac_dev);
 
-	if (IS_ERR(dpmac_dev) || dpmac_dev->dev.type != &fsl_mc_bus_dpmac_type)
+	if (IS_ERR(dpmac_dev))
 		return 0;
 
+	if (dpmac_dev->dev.type != &fsl_mc_bus_dpmac_type) {
+		err = 0;
+		goto out_put_device;
+	}
+
 	mac = kzalloc(sizeof(*mac), GFP_KERNEL);
-	if (!mac)
-		return -ENOMEM;
+	if (!mac) {
+		err = -ENOMEM;
+		goto out_put_device;
+	}
 
 	mac->mc_dev = dpmac_dev;
 	mac->mc_io = port_priv->ethsw_data->mc_io;
@@ -1482,6 +1489,8 @@ err_close_mac:
 	dpaa2_mac_close(mac);
 err_free_mac:
 	kfree(mac);
+out_put_device:
+	put_device(&dpmac_dev->dev);
 	return err;
 }
 
diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c
index 16a7908c79f7..d8272b7a55fc 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc.c
@@ -145,6 +145,24 @@ static int enetc_ptp_parse(struct sk_buff *skb, u8 *udp,
 	return 0;
 }
 
+/**
+ * enetc_unwind_tx_frame() - Unwind the DMA mappings of a multi-buffer Tx frame
+ * @tx_ring: Pointer to the Tx ring on which the buffer descriptors are located
+ * @count: Number of Tx buffer descriptors which need to be unmapped
+ * @i: Index of the last successfully mapped Tx buffer descriptor
+ */
+static void enetc_unwind_tx_frame(struct enetc_bdr *tx_ring, int count, int i)
+{
+	while (count--) {
+		struct enetc_tx_swbd *tx_swbd = &tx_ring->tx_swbd[i];
+
+		enetc_free_tx_frame(tx_ring, tx_swbd);
+		if (i == 0)
+			i = tx_ring->bd_count;
+		i--;
+	}
+}
+
 static int enetc_map_tx_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb)
 {
 	bool do_vlan, do_onestep_tstamp = false, do_twostep_tstamp = false;
@@ -235,9 +253,11 @@ static int enetc_map_tx_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb)
 		}
 
 		if (do_onestep_tstamp) {
-			u32 lo, hi, val;
-			u64 sec, nsec;
+			__be32 new_sec_l, new_nsec;
+			u32 lo, hi, nsec, val;
+			__be16 new_sec_h;
 			u8 *data;
+			u64 sec;
 
 			lo = enetc_rd_hot(hw, ENETC_SICTR0);
 			hi = enetc_rd_hot(hw, ENETC_SICTR1);
@@ -251,13 +271,38 @@ static int enetc_map_tx_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb)
 			/* Update originTimestamp field of Sync packet
 			 * - 48 bits seconds field
 			 * - 32 bits nanseconds field
+			 *
+			 * In addition, the UDP checksum needs to be updated
+			 * by software after updating originTimestamp field,
+			 * otherwise the hardware will calculate the wrong
+			 * checksum when updating the correction field and
+			 * update it to the packet.
 			 */
 			data = skb_mac_header(skb);
-			*(__be16 *)(data + offset2) =
-				htons((sec >> 32) & 0xffff);
-			*(__be32 *)(data + offset2 + 2) =
-				htonl(sec & 0xffffffff);
-			*(__be32 *)(data + offset2 + 6) = htonl(nsec);
+			new_sec_h = htons((sec >> 32) & 0xffff);
+			new_sec_l = htonl(sec & 0xffffffff);
+			new_nsec = htonl(nsec);
+			if (udp) {
+				struct udphdr *uh = udp_hdr(skb);
+				__be32 old_sec_l, old_nsec;
+				__be16 old_sec_h;
+
+				old_sec_h = *(__be16 *)(data + offset2);
+				inet_proto_csum_replace2(&uh->check, skb, old_sec_h,
+							 new_sec_h, false);
+
+				old_sec_l = *(__be32 *)(data + offset2 + 2);
+				inet_proto_csum_replace4(&uh->check, skb, old_sec_l,
+							 new_sec_l, false);
+
+				old_nsec = *(__be32 *)(data + offset2 + 6);
+				inet_proto_csum_replace4(&uh->check, skb, old_nsec,
+							 new_nsec, false);
+			}
+
+			*(__be16 *)(data + offset2) = new_sec_h;
+			*(__be32 *)(data + offset2 + 2) = new_sec_l;
+			*(__be32 *)(data + offset2 + 6) = new_nsec;
 
 			/* Configure single-step register */
 			val = ENETC_PM0_SINGLE_STEP_EN;
@@ -328,25 +373,20 @@ static int enetc_map_tx_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb)
 dma_err:
 	dev_err(tx_ring->dev, "DMA map error");
 
-	do {
-		tx_swbd = &tx_ring->tx_swbd[i];
-		enetc_free_tx_frame(tx_ring, tx_swbd);
-		if (i == 0)
-			i = tx_ring->bd_count;
-		i--;
-	} while (count--);
+	enetc_unwind_tx_frame(tx_ring, count, i);
 
 	return 0;
 }
 
-static void enetc_map_tx_tso_hdr(struct enetc_bdr *tx_ring, struct sk_buff *skb,
-				 struct enetc_tx_swbd *tx_swbd,
-				 union enetc_tx_bd *txbd, int *i, int hdr_len,
-				 int data_len)
+static int enetc_map_tx_tso_hdr(struct enetc_bdr *tx_ring, struct sk_buff *skb,
+				struct enetc_tx_swbd *tx_swbd,
+				union enetc_tx_bd *txbd, int *i, int hdr_len,
+				int data_len)
 {
 	union enetc_tx_bd txbd_tmp;
 	u8 flags = 0, e_flags = 0;
 	dma_addr_t addr;
+	int count = 1;
 
 	enetc_clear_tx_bd(&txbd_tmp);
 	addr = tx_ring->tso_headers_dma + *i * TSO_HEADER_SIZE;
@@ -389,7 +429,10 @@ static void enetc_map_tx_tso_hdr(struct enetc_bdr *tx_ring, struct sk_buff *skb,
 		/* Write the BD */
 		txbd_tmp.ext.e_flags = e_flags;
 		*txbd = txbd_tmp;
+		count++;
 	}
+
+	return count;
 }
 
 static int enetc_map_tx_tso_data(struct enetc_bdr *tx_ring, struct sk_buff *skb,
@@ -521,9 +564,9 @@ static int enetc_map_tx_tso_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb
 
 		/* compute the csum over the L4 header */
 		csum = enetc_tso_hdr_csum(&tso, skb, hdr, hdr_len, &pos);
-		enetc_map_tx_tso_hdr(tx_ring, skb, tx_swbd, txbd, &i, hdr_len, data_len);
+		count += enetc_map_tx_tso_hdr(tx_ring, skb, tx_swbd, txbd,
+					      &i, hdr_len, data_len);
 		bd_data_num = 0;
-		count++;
 
 		while (data_len > 0) {
 			int size;
@@ -547,8 +590,13 @@ static int enetc_map_tx_tso_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb
 			err = enetc_map_tx_tso_data(tx_ring, skb, tx_swbd, txbd,
 						    tso.data, size,
 						    size == data_len);
-			if (err)
+			if (err) {
+				if (i == 0)
+					i = tx_ring->bd_count;
+				i--;
+
 				goto err_map_data;
+			}
 
 			data_len -= size;
 			count++;
@@ -577,13 +625,7 @@ err_map_data:
 	dev_err(tx_ring->dev, "DMA map error");
 
 err_chained_bd:
-	do {
-		tx_swbd = &tx_ring->tx_swbd[i];
-		enetc_free_tx_frame(tx_ring, tx_swbd);
-		if (i == 0)
-			i = tx_ring->bd_count;
-		i--;
-	} while (count--);
+	enetc_unwind_tx_frame(tx_ring, count, i);
 
 	return 0;
 }
@@ -1530,6 +1572,16 @@ static void enetc_xdp_drop(struct enetc_bdr *rx_ring, int rx_ring_first,
 	}
 }
 
+static void enetc_bulk_flip_buff(struct enetc_bdr *rx_ring, int rx_ring_first,
+				 int rx_ring_last)
+{
+	while (rx_ring_first != rx_ring_last) {
+		enetc_flip_rx_buff(rx_ring,
+				   &rx_ring->rx_swbd[rx_ring_first]);
+		enetc_bdr_idx_inc(rx_ring, &rx_ring_first);
+	}
+}
+
 static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring,
 				   struct napi_struct *napi, int work_limit,
 				   struct bpf_prog *prog)
@@ -1623,7 +1675,7 @@ static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring,
 				enetc_xdp_drop(rx_ring, orig_i, i);
 				tx_ring->stats.xdp_tx_drops++;
 			} else {
-				tx_ring->stats.xdp_tx += xdp_tx_bd_cnt;
+				tx_ring->stats.xdp_tx++;
 				rx_ring->xdp.xdp_tx_in_flight += xdp_tx_bd_cnt;
 				xdp_tx_frm_cnt++;
 				/* The XDP_TX enqueue was successful, so we
@@ -1645,11 +1697,7 @@ static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring,
 				enetc_xdp_drop(rx_ring, orig_i, i);
 				rx_ring->stats.xdp_redirect_failures++;
 			} else {
-				while (orig_i != i) {
-					enetc_flip_rx_buff(rx_ring,
-							   &rx_ring->rx_swbd[orig_i]);
-					enetc_bdr_idx_inc(rx_ring, &orig_i);
-				}
+				enetc_bulk_flip_buff(rx_ring, orig_i, i);
 				xdp_redirect_frm_cnt++;
 				rx_ring->stats.xdp_redirect++;
 			}
@@ -2929,6 +2977,9 @@ static int enetc_hwtstamp_set(struct net_device *ndev, struct ifreq *ifr)
 		new_offloads |= ENETC_F_TX_TSTAMP;
 		break;
 	case HWTSTAMP_TX_ONESTEP_SYNC:
+		if (!enetc_si_is_pf(priv->si))
+			return -EOPNOTSUPP;
+
 		new_offloads &= ~ENETC_F_TX_TSTAMP_MASK;
 		new_offloads |= ENETC_F_TX_ONESTEP_SYNC_TSTAMP;
 		break;
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c
index 2563eb8ac7b6..6a24324703bf 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c
@@ -843,6 +843,7 @@ static int enetc_set_coalesce(struct net_device *ndev,
 static int enetc_get_ts_info(struct net_device *ndev,
 			     struct kernel_ethtool_ts_info *info)
 {
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
 	int *phc_idx;
 
 	phc_idx = symbol_get(enetc_phc_index);
@@ -863,8 +864,10 @@ static int enetc_get_ts_info(struct net_device *ndev,
 				SOF_TIMESTAMPING_TX_SOFTWARE;
 
 	info->tx_types = (1 << HWTSTAMP_TX_OFF) |
-			 (1 << HWTSTAMP_TX_ON) |
-			 (1 << HWTSTAMP_TX_ONESTEP_SYNC);
+			 (1 << HWTSTAMP_TX_ON);
+
+	if (enetc_si_is_pf(priv->si))
+		info->tx_types |= (1 << HWTSTAMP_TX_ONESTEP_SYNC);
 
 	info->rx_filters = (1 << HWTSTAMP_FILTER_NONE) |
 			   (1 << HWTSTAMP_FILTER_ALL);
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_hw.h b/drivers/net/ethernet/freescale/enetc/enetc_hw.h
index 1619943fb263..4e8881b479e4 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_hw.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc_hw.h
@@ -485,7 +485,7 @@ static inline u64 _enetc_rd_reg64(void __iomem *reg)
 		tmp = ioread32(reg + 4);
 	} while (high != tmp);
 
-	return le64_to_cpu((__le64)high << 32 | low);
+	return (u64)high << 32 | low;
 }
 #endif
 
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
index c95a7c083b0f..f376bf3110a5 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
@@ -1182,19 +1182,29 @@ static int enetc_pf_register_with_ierb(struct pci_dev *pdev)
 {
 	struct platform_device *ierb_pdev;
 	struct device_node *ierb_node;
+	int ret;
 
 	ierb_node = of_find_compatible_node(NULL, NULL,
 					    "fsl,ls1028a-enetc-ierb");
-	if (!ierb_node || !of_device_is_available(ierb_node))
+	if (!ierb_node)
 		return -ENODEV;
 
+	if (!of_device_is_available(ierb_node)) {
+		of_node_put(ierb_node);
+		return -ENODEV;
+	}
+
 	ierb_pdev = of_find_device_by_node(ierb_node);
 	of_node_put(ierb_node);
 
 	if (!ierb_pdev)
 		return -EPROBE_DEFER;
 
-	return enetc_ierb_register_pf(ierb_pdev, pdev);
+	ret = enetc_ierb_register_pf(ierb_pdev, pdev);
+
+	put_device(&ierb_pdev->dev);
+
+	return ret;
 }
 
 static struct enetc_si *enetc_psi_create(struct pci_dev *pdev)
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 49d1748e0c04..a1cc338cf20f 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -714,7 +714,12 @@ static int fec_enet_txq_submit_skb(struct fec_enet_priv_tx_q *txq,
 	txq->bd.cur = bdp;
 
 	/* Trigger transmission start */
-	writel(0, txq->bd.reg_desc_active);
+	if (!(fep->quirks & FEC_QUIRK_ERR007885) ||
+	    !readl(txq->bd.reg_desc_active) ||
+	    !readl(txq->bd.reg_desc_active) ||
+	    !readl(txq->bd.reg_desc_active) ||
+	    !readl(txq->bd.reg_desc_active))
+		writel(0, txq->bd.reg_desc_active);
 
 	return 0;
 }
@@ -840,6 +845,8 @@ static int fec_enet_txq_submit_tso(struct fec_enet_priv_tx_q *txq,
 	struct fec_enet_private *fep = netdev_priv(ndev);
 	int hdr_len, total_len, data_left;
 	struct bufdesc *bdp = txq->bd.cur;
+	struct bufdesc *tmp_bdp;
+	struct bufdesc_ex *ebdp;
 	struct tso_t tso;
 	unsigned int index = 0;
 	int ret;
@@ -913,7 +920,34 @@ static int fec_enet_txq_submit_tso(struct fec_enet_priv_tx_q *txq,
 	return 0;
 
 err_release:
-	/* TODO: Release all used data descriptors for TSO */
+	/* Release all used data descriptors for TSO */
+	tmp_bdp = txq->bd.cur;
+
+	while (tmp_bdp != bdp) {
+		/* Unmap data buffers */
+		if (tmp_bdp->cbd_bufaddr &&
+		    !IS_TSO_HEADER(txq, fec32_to_cpu(tmp_bdp->cbd_bufaddr)))
+			dma_unmap_single(&fep->pdev->dev,
+					 fec32_to_cpu(tmp_bdp->cbd_bufaddr),
+					 fec16_to_cpu(tmp_bdp->cbd_datlen),
+					 DMA_TO_DEVICE);
+
+		/* Clear standard buffer descriptor fields */
+		tmp_bdp->cbd_sc = 0;
+		tmp_bdp->cbd_datlen = 0;
+		tmp_bdp->cbd_bufaddr = 0;
+
+		/* Handle extended descriptor if enabled */
+		if (fep->bufdesc_ex) {
+			ebdp = (struct bufdesc_ex *)tmp_bdp;
+			ebdp->cbd_esc = 0;
+		}
+
+		tmp_bdp = fec_enet_get_nextdesc(tmp_bdp, &txq->bd);
+	}
+
+	dev_kfree_skb_any(skb);
+
 	return ret;
 }
 
@@ -1064,6 +1098,29 @@ static void fec_enet_enable_ring(struct net_device *ndev)
 	}
 }
 
+/* Whack a reset.  We should wait for this.
+ * For i.MX6SX SOC, enet use AXI bus, we use disable MAC
+ * instead of reset MAC itself.
+ */
+static void fec_ctrl_reset(struct fec_enet_private *fep, bool allow_wol)
+{
+	u32 val;
+
+	if (!allow_wol || !(fep->wol_flag & FEC_WOL_FLAG_SLEEP_ON)) {
+		if (fep->quirks & FEC_QUIRK_HAS_MULTI_QUEUES ||
+		    ((fep->quirks & FEC_QUIRK_NO_HARD_RESET) && fep->link)) {
+			writel(0, fep->hwp + FEC_ECNTRL);
+		} else {
+			writel(FEC_ECR_RESET, fep->hwp + FEC_ECNTRL);
+			udelay(10);
+		}
+	} else {
+		val = readl(fep->hwp + FEC_ECNTRL);
+		val |= (FEC_ECR_MAGICEN | FEC_ECR_SLEEP);
+		writel(val, fep->hwp + FEC_ECNTRL);
+	}
+}
+
 /*
  * This function is called to start or restart the FEC during a link
  * change, transmit timeout, or to reconfigure the FEC.  The network
@@ -1080,17 +1137,7 @@ fec_restart(struct net_device *ndev)
 	if (fep->bufdesc_ex)
 		fec_ptp_save_state(fep);
 
-	/* Whack a reset.  We should wait for this.
-	 * For i.MX6SX SOC, enet use AXI bus, we use disable MAC
-	 * instead of reset MAC itself.
-	 */
-	if (fep->quirks & FEC_QUIRK_HAS_MULTI_QUEUES ||
-	    ((fep->quirks & FEC_QUIRK_NO_HARD_RESET) && fep->link)) {
-		writel(0, fep->hwp + FEC_ECNTRL);
-	} else {
-		writel(1, fep->hwp + FEC_ECNTRL);
-		udelay(10);
-	}
+	fec_ctrl_reset(fep, false);
 
 	/*
 	 * enet-mac reset will reset mac address registers too,
@@ -1344,22 +1391,7 @@ fec_stop(struct net_device *ndev)
 	if (fep->bufdesc_ex)
 		fec_ptp_save_state(fep);
 
-	/* Whack a reset.  We should wait for this.
-	 * For i.MX6SX SOC, enet use AXI bus, we use disable MAC
-	 * instead of reset MAC itself.
-	 */
-	if (!(fep->wol_flag & FEC_WOL_FLAG_SLEEP_ON)) {
-		if (fep->quirks & FEC_QUIRK_HAS_MULTI_QUEUES) {
-			writel(0, fep->hwp + FEC_ECNTRL);
-		} else {
-			writel(FEC_ECR_RESET, fep->hwp + FEC_ECNTRL);
-			udelay(10);
-		}
-	} else {
-		val = readl(fep->hwp + FEC_ECNTRL);
-		val |= (FEC_ECR_MAGICEN | FEC_ECR_SLEEP);
-		writel(val, fep->hwp + FEC_ECNTRL);
-	}
+	fec_ctrl_reset(fep, true);
 	writel(fep->phy_speed, fep->hwp + FEC_MII_SPEED);
 	writel(FEC_DEFAULT_IMASK, fep->hwp + FEC_IMASK);
 
@@ -3090,27 +3122,25 @@ static int fec_enet_us_to_itr_clock(struct net_device *ndev, int us)
 static void fec_enet_itr_coal_set(struct net_device *ndev)
 {
 	struct fec_enet_private *fep = netdev_priv(ndev);
-	int rx_itr, tx_itr;
-
-	/* Must be greater than zero to avoid unpredictable behavior */
-	if (!fep->rx_time_itr || !fep->rx_pkts_itr ||
-	    !fep->tx_time_itr || !fep->tx_pkts_itr)
-		return;
+	u32 rx_itr = 0, tx_itr = 0;
+	int rx_ictt, tx_ictt;
 
-	/* Select enet system clock as Interrupt Coalescing
-	 * timer Clock Source
-	 */
-	rx_itr = FEC_ITR_CLK_SEL;
-	tx_itr = FEC_ITR_CLK_SEL;
+	rx_ictt = fec_enet_us_to_itr_clock(ndev, fep->rx_time_itr);
+	tx_ictt = fec_enet_us_to_itr_clock(ndev, fep->tx_time_itr);
 
-	/* set ICFT and ICTT */
-	rx_itr |= FEC_ITR_ICFT(fep->rx_pkts_itr);
-	rx_itr |= FEC_ITR_ICTT(fec_enet_us_to_itr_clock(ndev, fep->rx_time_itr));
-	tx_itr |= FEC_ITR_ICFT(fep->tx_pkts_itr);
-	tx_itr |= FEC_ITR_ICTT(fec_enet_us_to_itr_clock(ndev, fep->tx_time_itr));
+	if (rx_ictt > 0 && fep->rx_pkts_itr > 1) {
+		/* Enable with enet system clock as Interrupt Coalescing timer Clock Source */
+		rx_itr = FEC_ITR_EN | FEC_ITR_CLK_SEL;
+		rx_itr |= FEC_ITR_ICFT(fep->rx_pkts_itr);
+		rx_itr |= FEC_ITR_ICTT(rx_ictt);
+	}
 
-	rx_itr |= FEC_ITR_EN;
-	tx_itr |= FEC_ITR_EN;
+	if (tx_ictt > 0 && fep->tx_pkts_itr > 1) {
+		/* Enable with enet system clock as Interrupt Coalescing timer Clock Source */
+		tx_itr = FEC_ITR_EN | FEC_ITR_CLK_SEL;
+		tx_itr |= FEC_ITR_ICFT(fep->tx_pkts_itr);
+		tx_itr |= FEC_ITR_ICTT(tx_ictt);
+	}
 
 	writel(tx_itr, fep->hwp + FEC_TXIC0);
 	writel(rx_itr, fep->hwp + FEC_RXIC0);
diff --git a/drivers/net/ethernet/freescale/gianfar_ethtool.c b/drivers/net/ethernet/freescale/gianfar_ethtool.c
index a99b95c4bcfb..ec13a587fe41 100644
--- a/drivers/net/ethernet/freescale/gianfar_ethtool.c
+++ b/drivers/net/ethernet/freescale/gianfar_ethtool.c
@@ -1464,8 +1464,10 @@ static int gfar_get_ts_info(struct net_device *dev,
 	if (ptp_node) {
 		ptp_dev = of_find_device_by_node(ptp_node);
 		of_node_put(ptp_node);
-		if (ptp_dev)
+		if (ptp_dev) {
 			ptp = platform_get_drvdata(ptp_dev);
+			put_device(&ptp_dev->dev);
+		}
 	}
 
 	if (ptp)
diff --git a/drivers/net/ethernet/google/gve/gve.h b/drivers/net/ethernet/google/gve/gve.h
index 95471cfcff42..8ddd366d9fde 100644
--- a/drivers/net/ethernet/google/gve/gve.h
+++ b/drivers/net/ethernet/google/gve/gve.h
@@ -1110,6 +1110,16 @@ static inline u32 gve_xdp_tx_start_queue_id(struct gve_priv *priv)
 	return gve_xdp_tx_queue_id(priv, 0);
 }
 
+static inline bool gve_supports_xdp_xmit(struct gve_priv *priv)
+{
+	switch (priv->queue_format) {
+	case GVE_GQI_QPL_FORMAT:
+		return true;
+	default:
+		return false;
+	}
+}
+
 /* gqi napi handler defined in gve_main.c */
 int gve_napi_poll(struct napi_struct *napi, int budget);
 
diff --git a/drivers/net/ethernet/google/gve/gve_adminq.c b/drivers/net/ethernet/google/gve/gve_adminq.c
index 060e0e674938..36acbcd8f62a 100644
--- a/drivers/net/ethernet/google/gve/gve_adminq.c
+++ b/drivers/net/ethernet/google/gve/gve_adminq.c
@@ -564,6 +564,7 @@ static int gve_adminq_issue_cmd(struct gve_priv *priv,
 		break;
 	default:
 		dev_err(&priv->pdev->dev, "unknown AQ command opcode %d\n", opcode);
+		return -EINVAL;
 	}
 
 	return 0;
diff --git a/drivers/net/ethernet/google/gve/gve_ethtool.c b/drivers/net/ethernet/google/gve/gve_ethtool.c
index bdfc6e77b2af..1f5db1096d4a 100644
--- a/drivers/net/ethernet/google/gve/gve_ethtool.c
+++ b/drivers/net/ethernet/google/gve/gve_ethtool.c
@@ -392,7 +392,9 @@ gve_get_ethtool_stats(struct net_device *netdev,
 				 */
 				data[i++] = 0;
 				data[i++] = 0;
-				data[i++] = tx->dqo_tx.tail - tx->dqo_tx.head;
+				data[i++] =
+					(tx->dqo_tx.tail - tx->dqo_tx.head) &
+					tx->mask;
 			}
 			do {
 				start =
diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c
index f985a3cf2b11..8ea3c7493663 100644
--- a/drivers/net/ethernet/google/gve/gve_main.c
+++ b/drivers/net/ethernet/google/gve/gve_main.c
@@ -1895,6 +1895,8 @@ static void gve_turndown(struct gve_priv *priv)
 	/* Stop tx queues */
 	netif_tx_disable(priv->dev);
 
+	xdp_features_clear_redirect_target(priv->dev);
+
 	gve_clear_napi_enabled(priv);
 	gve_clear_report_stats(priv);
 
@@ -1955,6 +1957,9 @@ static void gve_turnup(struct gve_priv *priv)
 		napi_schedule(&block->napi);
 	}
 
+	if (priv->num_xdp_queues && gve_supports_xdp_xmit(priv))
+		xdp_features_set_redirect_target(priv->dev, false);
+
 	gve_set_napi_enabled(priv);
 }
 
@@ -1967,49 +1972,56 @@ static void gve_turnup_and_check_status(struct gve_priv *priv)
 	gve_handle_link_status(priv, GVE_DEVICE_STATUS_LINK_STATUS_MASK & status);
 }
 
-static void gve_tx_timeout(struct net_device *dev, unsigned int txqueue)
+static struct gve_notify_block *gve_get_tx_notify_block(struct gve_priv *priv,
+							unsigned int txqueue)
 {
-	struct gve_notify_block *block;
-	struct gve_tx_ring *tx = NULL;
-	struct gve_priv *priv;
-	u32 last_nic_done;
-	u32 current_time;
 	u32 ntfy_idx;
 
-	netdev_info(dev, "Timeout on tx queue, %d", txqueue);
-	priv = netdev_priv(dev);
 	if (txqueue > priv->tx_cfg.num_queues)
-		goto reset;
+		return NULL;
 
 	ntfy_idx = gve_tx_idx_to_ntfy(priv, txqueue);
 	if (ntfy_idx >= priv->num_ntfy_blks)
-		goto reset;
+		return NULL;
+
+	return &priv->ntfy_blocks[ntfy_idx];
+}
 
-	block = &priv->ntfy_blocks[ntfy_idx];
-	tx = block->tx;
+static bool gve_tx_timeout_try_q_kick(struct gve_priv *priv,
+				      unsigned int txqueue)
+{
+	struct gve_notify_block *block;
+	u32 current_time;
+
+	block = gve_get_tx_notify_block(priv, txqueue);
+
+	if (!block)
+		return false;
 
 	current_time = jiffies_to_msecs(jiffies);
-	if (tx->last_kick_msec + MIN_TX_TIMEOUT_GAP > current_time)
-		goto reset;
+	if (block->tx->last_kick_msec + MIN_TX_TIMEOUT_GAP > current_time)
+		return false;
 
-	/* Check to see if there are missed completions, which will allow us to
-	 * kick the queue.
-	 */
-	last_nic_done = gve_tx_load_event_counter(priv, tx);
-	if (last_nic_done - tx->done) {
-		netdev_info(dev, "Kicking queue %d", txqueue);
-		iowrite32be(GVE_IRQ_MASK, gve_irq_doorbell(priv, block));
-		napi_schedule(&block->napi);
-		tx->last_kick_msec = current_time;
-		goto out;
-	} // Else reset.
+	netdev_info(priv->dev, "Kicking queue %d", txqueue);
+	napi_schedule(&block->napi);
+	block->tx->last_kick_msec = current_time;
+	return true;
+}
 
-reset:
-	gve_schedule_reset(priv);
+static void gve_tx_timeout(struct net_device *dev, unsigned int txqueue)
+{
+	struct gve_notify_block *block;
+	struct gve_priv *priv;
 
-out:
-	if (tx)
-		tx->queue_timeout++;
+	netdev_info(dev, "Timeout on tx queue, %d", txqueue);
+	priv = netdev_priv(dev);
+
+	if (!gve_tx_timeout_try_q_kick(priv, txqueue))
+		gve_schedule_reset(priv);
+
+	block = gve_get_tx_notify_block(priv, txqueue);
+	if (block)
+		block->tx->queue_timeout++;
 	priv->tx_timeo_cnt++;
 }
 
@@ -2202,7 +2214,7 @@ void gve_handle_report_stats(struct gve_priv *priv)
 			};
 			stats[stats_idx++] = (struct stats) {
 				.stat_name = cpu_to_be32(RX_BUFFERS_POSTED),
-				.value = cpu_to_be64(priv->rx[0].fill_cnt),
+				.value = cpu_to_be64(priv->rx[idx].fill_cnt),
 				.queue_id = cpu_to_be32(idx),
 			};
 		}
@@ -2229,7 +2241,6 @@ static void gve_set_netdev_xdp_features(struct gve_priv *priv)
 	if (priv->queue_format == GVE_GQI_QPL_FORMAT) {
 		xdp_features = NETDEV_XDP_ACT_BASIC;
 		xdp_features |= NETDEV_XDP_ACT_REDIRECT;
-		xdp_features |= NETDEV_XDP_ACT_NDO_XMIT;
 		xdp_features |= NETDEV_XDP_ACT_XSK_ZEROCOPY;
 	} else {
 		xdp_features = 0;
diff --git a/drivers/net/ethernet/google/gve/gve_tx_dqo.c b/drivers/net/ethernet/google/gve/gve_tx_dqo.c
index f879426cb552..26053cc85d1c 100644
--- a/drivers/net/ethernet/google/gve/gve_tx_dqo.c
+++ b/drivers/net/ethernet/google/gve/gve_tx_dqo.c
@@ -770,6 +770,9 @@ static int gve_tx_add_skb_dqo(struct gve_tx_ring *tx,
 	s16 completion_tag;
 
 	pkt = gve_alloc_pending_packet(tx);
+	if (!pkt)
+		return -ENOMEM;
+
 	pkt->skb = skb;
 	completion_tag = pkt - tx->dqo.pending_packets;
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.c b/drivers/net/ethernet/hisilicon/hns3/hnae3.c
index 9a63fbc69408..b25fb400f476 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.c
@@ -40,6 +40,21 @@ EXPORT_SYMBOL(hnae3_unregister_ae_algo_prepare);
  */
 static DEFINE_MUTEX(hnae3_common_lock);
 
+/* ensure the drivers being unloaded one by one */
+static DEFINE_MUTEX(hnae3_unload_lock);
+
+void hnae3_acquire_unload_lock(void)
+{
+	mutex_lock(&hnae3_unload_lock);
+}
+EXPORT_SYMBOL(hnae3_acquire_unload_lock);
+
+void hnae3_release_unload_lock(void)
+{
+	mutex_unlock(&hnae3_unload_lock);
+}
+EXPORT_SYMBOL(hnae3_release_unload_lock);
+
 static bool hnae3_client_match(enum hnae3_client_type client_type)
 {
 	if (client_type == HNAE3_CLIENT_KNIC ||
diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index d873523e84f2..388c70331a55 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -963,4 +963,6 @@ int hnae3_register_client(struct hnae3_client *client);
 void hnae3_set_client_init_flag(struct hnae3_client *client,
 				struct hnae3_ae_dev *ae_dev,
 				unsigned int inited);
+void hnae3_acquire_unload_lock(void);
+void hnae3_release_unload_lock(void);
 #endif
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
index 9bbece25552b..3d70c97a0bed 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
@@ -60,7 +60,7 @@ static struct hns3_dbg_cmd_info hns3_dbg_cmd[] = {
 		.name = "tm_qset",
 		.cmd = HNAE3_DBG_CMD_TM_QSET,
 		.dentry = HNS3_DBG_DENTRY_TM,
-		.buf_len = HNS3_DBG_READ_LEN,
+		.buf_len = HNS3_DBG_READ_LEN_1MB,
 		.init = hns3_dbg_common_file_init,
 	},
 	{
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 73825b6bd485..94432e237640 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -11,6 +11,7 @@
 #include <linux/irq.h>
 #include <linux/ip.h>
 #include <linux/ipv6.h>
+#include <linux/iommu.h>
 #include <linux/module.h>
 #include <linux/pci.h>
 #include <linux/skbuff.h>
@@ -473,20 +474,14 @@ static void hns3_mask_vector_irq(struct hns3_enet_tqp_vector *tqp_vector,
 	writel(mask_en, tqp_vector->mask_addr);
 }
 
-static void hns3_vector_enable(struct hns3_enet_tqp_vector *tqp_vector)
+static void hns3_irq_enable(struct hns3_enet_tqp_vector *tqp_vector)
 {
 	napi_enable(&tqp_vector->napi);
 	enable_irq(tqp_vector->vector_irq);
-
-	/* enable vector */
-	hns3_mask_vector_irq(tqp_vector, 1);
 }
 
-static void hns3_vector_disable(struct hns3_enet_tqp_vector *tqp_vector)
+static void hns3_irq_disable(struct hns3_enet_tqp_vector *tqp_vector)
 {
-	/* disable vector */
-	hns3_mask_vector_irq(tqp_vector, 0);
-
 	disable_irq(tqp_vector->vector_irq);
 	napi_disable(&tqp_vector->napi);
 	cancel_work_sync(&tqp_vector->rx_group.dim.work);
@@ -707,11 +702,42 @@ static int hns3_set_rx_cpu_rmap(struct net_device *netdev)
 	return 0;
 }
 
+static void hns3_enable_irqs_and_tqps(struct net_device *netdev)
+{
+	struct hns3_nic_priv *priv = netdev_priv(netdev);
+	struct hnae3_handle *h = priv->ae_handle;
+	u16 i;
+
+	for (i = 0; i < priv->vector_num; i++)
+		hns3_irq_enable(&priv->tqp_vector[i]);
+
+	for (i = 0; i < priv->vector_num; i++)
+		hns3_mask_vector_irq(&priv->tqp_vector[i], 1);
+
+	for (i = 0; i < h->kinfo.num_tqps; i++)
+		hns3_tqp_enable(h->kinfo.tqp[i]);
+}
+
+static void hns3_disable_irqs_and_tqps(struct net_device *netdev)
+{
+	struct hns3_nic_priv *priv = netdev_priv(netdev);
+	struct hnae3_handle *h = priv->ae_handle;
+	u16 i;
+
+	for (i = 0; i < h->kinfo.num_tqps; i++)
+		hns3_tqp_disable(h->kinfo.tqp[i]);
+
+	for (i = 0; i < priv->vector_num; i++)
+		hns3_mask_vector_irq(&priv->tqp_vector[i], 0);
+
+	for (i = 0; i < priv->vector_num; i++)
+		hns3_irq_disable(&priv->tqp_vector[i]);
+}
+
 static int hns3_nic_net_up(struct net_device *netdev)
 {
 	struct hns3_nic_priv *priv = netdev_priv(netdev);
 	struct hnae3_handle *h = priv->ae_handle;
-	int i, j;
 	int ret;
 
 	ret = hns3_nic_reset_all_ring(h);
@@ -720,23 +746,13 @@ static int hns3_nic_net_up(struct net_device *netdev)
 
 	clear_bit(HNS3_NIC_STATE_DOWN, &priv->state);
 
-	/* enable the vectors */
-	for (i = 0; i < priv->vector_num; i++)
-		hns3_vector_enable(&priv->tqp_vector[i]);
-
-	/* enable rcb */
-	for (j = 0; j < h->kinfo.num_tqps; j++)
-		hns3_tqp_enable(h->kinfo.tqp[j]);
+	hns3_enable_irqs_and_tqps(netdev);
 
 	/* start the ae_dev */
 	ret = h->ae_algo->ops->start ? h->ae_algo->ops->start(h) : 0;
 	if (ret) {
 		set_bit(HNS3_NIC_STATE_DOWN, &priv->state);
-		while (j--)
-			hns3_tqp_disable(h->kinfo.tqp[j]);
-
-		for (j = i - 1; j >= 0; j--)
-			hns3_vector_disable(&priv->tqp_vector[j]);
+		hns3_disable_irqs_and_tqps(netdev);
 	}
 
 	return ret;
@@ -823,17 +839,9 @@ static void hns3_reset_tx_queue(struct hnae3_handle *h)
 static void hns3_nic_net_down(struct net_device *netdev)
 {
 	struct hns3_nic_priv *priv = netdev_priv(netdev);
-	struct hnae3_handle *h = hns3_get_handle(netdev);
 	const struct hnae3_ae_ops *ops;
-	int i;
-
-	/* disable vectors */
-	for (i = 0; i < priv->vector_num; i++)
-		hns3_vector_disable(&priv->tqp_vector[i]);
 
-	/* disable rcb */
-	for (i = 0; i < h->kinfo.num_tqps; i++)
-		hns3_tqp_disable(h->kinfo.tqp[i]);
+	hns3_disable_irqs_and_tqps(netdev);
 
 	/* stop ae_dev */
 	ops = priv->ae_handle->ae_algo->ops;
@@ -1032,6 +1040,8 @@ static bool hns3_can_use_tx_sgl(struct hns3_enet_ring *ring,
 static void hns3_init_tx_spare_buffer(struct hns3_enet_ring *ring)
 {
 	u32 alloc_size = ring->tqp->handle->kinfo.tx_spare_buf_size;
+	struct net_device *netdev = ring_to_netdev(ring);
+	struct hns3_nic_priv *priv = netdev_priv(netdev);
 	struct hns3_tx_spare *tx_spare;
 	struct page *page;
 	dma_addr_t dma;
@@ -1073,6 +1083,7 @@ static void hns3_init_tx_spare_buffer(struct hns3_enet_ring *ring)
 	tx_spare->buf = page_address(page);
 	tx_spare->len = PAGE_SIZE << order;
 	ring->tx_spare = tx_spare;
+	ring->tx_copybreak = priv->tx_copybreak;
 	return;
 
 dma_mapping_error:
@@ -4867,6 +4878,30 @@ static void hns3_nic_dealloc_vector_data(struct hns3_nic_priv *priv)
 	devm_kfree(&pdev->dev, priv->tqp_vector);
 }
 
+static void hns3_update_tx_spare_buf_config(struct hns3_nic_priv *priv)
+{
+#define HNS3_MIN_SPARE_BUF_SIZE (2 * 1024 * 1024)
+#define HNS3_MAX_PACKET_SIZE (64 * 1024)
+
+	struct iommu_domain *domain = iommu_get_domain_for_dev(priv->dev);
+	struct hnae3_ae_dev *ae_dev = hns3_get_ae_dev(priv->ae_handle);
+	struct hnae3_handle *handle = priv->ae_handle;
+
+	if (ae_dev->dev_version < HNAE3_DEVICE_VERSION_V3)
+		return;
+
+	if (!(domain && iommu_is_dma_domain(domain)))
+		return;
+
+	priv->min_tx_copybreak = HNS3_MAX_PACKET_SIZE;
+	priv->min_tx_spare_buf_size = HNS3_MIN_SPARE_BUF_SIZE;
+
+	if (priv->tx_copybreak < priv->min_tx_copybreak)
+		priv->tx_copybreak = priv->min_tx_copybreak;
+	if (handle->kinfo.tx_spare_buf_size < priv->min_tx_spare_buf_size)
+		handle->kinfo.tx_spare_buf_size = priv->min_tx_spare_buf_size;
+}
+
 static void hns3_ring_get_cfg(struct hnae3_queue *q, struct hns3_nic_priv *priv,
 			      unsigned int ring_type)
 {
@@ -5100,6 +5135,7 @@ int hns3_init_all_ring(struct hns3_nic_priv *priv)
 	int i, j;
 	int ret;
 
+	hns3_update_tx_spare_buf_config(priv);
 	for (i = 0; i < ring_num; i++) {
 		ret = hns3_alloc_ring_memory(&priv->ring[i]);
 		if (ret) {
@@ -5304,6 +5340,8 @@ static int hns3_client_init(struct hnae3_handle *handle)
 	priv->ae_handle = handle;
 	priv->tx_timeout_count = 0;
 	priv->max_non_tso_bd_num = ae_dev->dev_specs.max_non_tso_bd_num;
+	priv->min_tx_copybreak = 0;
+	priv->min_tx_spare_buf_size = 0;
 	set_bit(HNS3_NIC_STATE_DOWN, &priv->state);
 
 	handle->msg_enable = netif_msg_init(debug, DEFAULT_MSG_LEVEL);
@@ -5864,8 +5902,6 @@ int hns3_set_channels(struct net_device *netdev,
 void hns3_external_lb_prepare(struct net_device *ndev, bool if_running)
 {
 	struct hns3_nic_priv *priv = netdev_priv(ndev);
-	struct hnae3_handle *h = priv->ae_handle;
-	int i;
 
 	if (!if_running)
 		return;
@@ -5876,11 +5912,7 @@ void hns3_external_lb_prepare(struct net_device *ndev, bool if_running)
 	netif_carrier_off(ndev);
 	netif_tx_disable(ndev);
 
-	for (i = 0; i < priv->vector_num; i++)
-		hns3_vector_disable(&priv->tqp_vector[i]);
-
-	for (i = 0; i < h->kinfo.num_tqps; i++)
-		hns3_tqp_disable(h->kinfo.tqp[i]);
+	hns3_disable_irqs_and_tqps(ndev);
 
 	/* delay ring buffer clearing to hns3_reset_notify_uninit_enet
 	 * during reset process, because driver may not be able
@@ -5896,7 +5928,6 @@ void hns3_external_lb_restore(struct net_device *ndev, bool if_running)
 {
 	struct hns3_nic_priv *priv = netdev_priv(ndev);
 	struct hnae3_handle *h = priv->ae_handle;
-	int i;
 
 	if (!if_running)
 		return;
@@ -5912,11 +5943,7 @@ void hns3_external_lb_restore(struct net_device *ndev, bool if_running)
 
 	clear_bit(HNS3_NIC_STATE_DOWN, &priv->state);
 
-	for (i = 0; i < priv->vector_num; i++)
-		hns3_vector_enable(&priv->tqp_vector[i]);
-
-	for (i = 0; i < h->kinfo.num_tqps; i++)
-		hns3_tqp_enable(h->kinfo.tqp[i]);
+	hns3_enable_irqs_and_tqps(ndev);
 
 	netif_tx_wake_all_queues(ndev);
 
@@ -6002,9 +6029,11 @@ module_init(hns3_init_module);
  */
 static void __exit hns3_exit_module(void)
 {
+	hnae3_acquire_unload_lock();
 	pci_unregister_driver(&hns3_driver);
 	hnae3_unregister_client(&client);
 	hns3_dbg_unregister_debugfs();
+	hnae3_release_unload_lock();
 }
 module_exit(hns3_exit_module);
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
index d36c4ed16d8d..caf7a4df8585 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
@@ -596,6 +596,8 @@ struct hns3_nic_priv {
 	struct hns3_enet_coalesce rx_coal;
 	u32 tx_copybreak;
 	u32 rx_copybreak;
+	u32 min_tx_copybreak;
+	u32 min_tx_spare_buf_size;
 };
 
 union l3_hdr_info {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 9a67fe0554a5..407ad0b985b4 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -9586,33 +9586,36 @@ static bool hclge_need_enable_vport_vlan_filter(struct hclge_vport *vport)
 	return false;
 }
 
-int hclge_enable_vport_vlan_filter(struct hclge_vport *vport, bool request_en)
+static int __hclge_enable_vport_vlan_filter(struct hclge_vport *vport,
+					    bool request_en)
 {
-	struct hclge_dev *hdev = vport->back;
 	bool need_en;
 	int ret;
 
-	mutex_lock(&hdev->vport_lock);
-
-	vport->req_vlan_fltr_en = request_en;
-
 	need_en = hclge_need_enable_vport_vlan_filter(vport);
-	if (need_en == vport->cur_vlan_fltr_en) {
-		mutex_unlock(&hdev->vport_lock);
+	if (need_en == vport->cur_vlan_fltr_en)
 		return 0;
-	}
 
 	ret = hclge_set_vport_vlan_filter(vport, need_en);
-	if (ret) {
-		mutex_unlock(&hdev->vport_lock);
+	if (ret)
 		return ret;
-	}
 
 	vport->cur_vlan_fltr_en = need_en;
 
+	return 0;
+}
+
+int hclge_enable_vport_vlan_filter(struct hclge_vport *vport, bool request_en)
+{
+	struct hclge_dev *hdev = vport->back;
+	int ret;
+
+	mutex_lock(&hdev->vport_lock);
+	vport->req_vlan_fltr_en = request_en;
+	ret = __hclge_enable_vport_vlan_filter(vport, request_en);
 	mutex_unlock(&hdev->vport_lock);
 
-	return 0;
+	return ret;
 }
 
 static int hclge_enable_vlan_filter(struct hnae3_handle *handle, bool enable)
@@ -10633,16 +10636,19 @@ static void hclge_sync_vlan_fltr_state(struct hclge_dev *hdev)
 					&vport->state))
 			continue;
 
-		ret = hclge_enable_vport_vlan_filter(vport,
-						     vport->req_vlan_fltr_en);
+		mutex_lock(&hdev->vport_lock);
+		ret = __hclge_enable_vport_vlan_filter(vport,
+						       vport->req_vlan_fltr_en);
 		if (ret) {
 			dev_err(&hdev->pdev->dev,
 				"failed to sync vlan filter state for vport%u, ret = %d\n",
 				vport->vport_id, ret);
 			set_bit(HCLGE_VPORT_STATE_VLAN_FLTR_CHANGE,
 				&vport->state);
+			mutex_unlock(&hdev->vport_lock);
 			return;
 		}
+		mutex_unlock(&hdev->vport_lock);
 	}
 }
 
@@ -12929,9 +12935,11 @@ static int __init hclge_init(void)
 
 static void __exit hclge_exit(void)
 {
+	hnae3_acquire_unload_lock();
 	hnae3_unregister_ae_algo_prepare(&ae_algo);
 	hnae3_unregister_ae_algo(&ae_algo);
 	destroy_workqueue(hclge_wq);
+	hnae3_release_unload_lock();
 }
 module_init(hclge_init);
 module_exit(hclge_exit);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c
index bab16c2191b2..16ef5a584af3 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c
@@ -439,6 +439,13 @@ static int hclge_ptp_create_clock(struct hclge_dev *hdev)
 	ptp->info.settime64 = hclge_ptp_settime;
 
 	ptp->info.n_alarm = 0;
+
+	spin_lock_init(&ptp->lock);
+	ptp->io_base = hdev->hw.hw.io_base + HCLGE_PTP_REG_OFFSET;
+	ptp->ts_cfg.rx_filter = HWTSTAMP_FILTER_NONE;
+	ptp->ts_cfg.tx_type = HWTSTAMP_TX_OFF;
+	hdev->ptp = ptp;
+
 	ptp->clock = ptp_clock_register(&ptp->info, &hdev->pdev->dev);
 	if (IS_ERR(ptp->clock)) {
 		dev_err(&hdev->pdev->dev,
@@ -450,12 +457,6 @@ static int hclge_ptp_create_clock(struct hclge_dev *hdev)
 		return -ENODEV;
 	}
 
-	spin_lock_init(&ptp->lock);
-	ptp->io_base = hdev->hw.hw.io_base + HCLGE_PTP_REG_OFFSET;
-	ptp->ts_cfg.rx_filter = HWTSTAMP_FILTER_NONE;
-	ptp->ts_cfg.tx_type = HWTSTAMP_TX_OFF;
-	hdev->ptp = ptp;
-
 	return 0;
 }
 
@@ -483,7 +484,7 @@ int hclge_ptp_init(struct hclge_dev *hdev)
 
 		ret = hclge_ptp_get_cycle(hdev);
 		if (ret)
-			return ret;
+			goto out;
 	}
 
 	ret = hclge_ptp_int_en(hdev, true);
@@ -495,14 +496,14 @@ int hclge_ptp_init(struct hclge_dev *hdev)
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
 			"failed to init freq, ret = %d\n", ret);
-		goto out;
+		goto out_clear_int;
 	}
 
 	ret = hclge_ptp_set_ts_mode(hdev, &hdev->ptp->ts_cfg);
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
 			"failed to init ts mode, ret = %d\n", ret);
-		goto out;
+		goto out_clear_int;
 	}
 
 	ktime_get_real_ts64(&ts);
@@ -510,7 +511,7 @@ int hclge_ptp_init(struct hclge_dev *hdev)
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
 			"failed to init ts time, ret = %d\n", ret);
-		goto out;
+		goto out_clear_int;
 	}
 
 	set_bit(HCLGE_STATE_PTP_EN, &hdev->state);
@@ -518,6 +519,9 @@ int hclge_ptp_init(struct hclge_dev *hdev)
 
 	return 0;
 
+out_clear_int:
+	clear_bit(HCLGE_PTP_FLAG_EN, &hdev->ptp->flags);
+	hclge_ptp_int_en(hdev, false);
 out:
 	hclge_ptp_destroy_clock(hdev);
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index d47bd8d6145f..e8573358309c 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -1294,9 +1294,8 @@ static void hclgevf_sync_vlan_filter(struct hclgevf_dev *hdev)
 	rtnl_unlock();
 }
 
-static int hclgevf_en_hw_strip_rxvtag(struct hnae3_handle *handle, bool enable)
+static int hclgevf_en_hw_strip_rxvtag_cmd(struct hclgevf_dev *hdev, bool enable)
 {
-	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
 	struct hclge_vf_to_pf_msg send_msg;
 
 	hclgevf_build_send_msg(&send_msg, HCLGE_MBX_SET_VLAN,
@@ -1305,6 +1304,19 @@ static int hclgevf_en_hw_strip_rxvtag(struct hnae3_handle *handle, bool enable)
 	return hclgevf_send_mbx_msg(hdev, &send_msg, false, NULL, 0);
 }
 
+static int hclgevf_en_hw_strip_rxvtag(struct hnae3_handle *handle, bool enable)
+{
+	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
+	int ret;
+
+	ret = hclgevf_en_hw_strip_rxvtag_cmd(hdev, enable);
+	if (ret)
+		return ret;
+
+	hdev->rxvtag_strip_en = enable;
+	return 0;
+}
+
 static int hclgevf_reset_tqp(struct hnae3_handle *handle)
 {
 #define HCLGEVF_RESET_ALL_QUEUE_DONE	1U
@@ -2206,12 +2218,13 @@ static int hclgevf_rss_init_hw(struct hclgevf_dev *hdev)
 					  tc_valid, tc_size);
 }
 
-static int hclgevf_init_vlan_config(struct hclgevf_dev *hdev)
+static int hclgevf_init_vlan_config(struct hclgevf_dev *hdev,
+				    bool rxvtag_strip_en)
 {
 	struct hnae3_handle *nic = &hdev->nic;
 	int ret;
 
-	ret = hclgevf_en_hw_strip_rxvtag(nic, true);
+	ret = hclgevf_en_hw_strip_rxvtag(nic, rxvtag_strip_en);
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
 			"failed to enable rx vlan offload, ret = %d\n", ret);
@@ -2881,7 +2894,7 @@ static int hclgevf_reset_hdev(struct hclgevf_dev *hdev)
 	if (ret)
 		return ret;
 
-	ret = hclgevf_init_vlan_config(hdev);
+	ret = hclgevf_init_vlan_config(hdev, hdev->rxvtag_strip_en);
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
 			"failed(%d) to initialize VLAN config\n", ret);
@@ -2996,7 +3009,7 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev)
 		goto err_config;
 	}
 
-	ret = hclgevf_init_vlan_config(hdev);
+	ret = hclgevf_init_vlan_config(hdev, true);
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
 			"failed(%d) to initialize VLAN config\n", ret);
@@ -3083,11 +3096,7 @@ static void hclgevf_uninit_ae_dev(struct hnae3_ae_dev *ae_dev)
 
 static u32 hclgevf_get_max_channels(struct hclgevf_dev *hdev)
 {
-	struct hnae3_handle *nic = &hdev->nic;
-	struct hnae3_knic_private_info *kinfo = &nic->kinfo;
-
-	return min_t(u32, hdev->rss_size_max,
-		     hdev->num_tqps / kinfo->tc_info.num_tc);
+	return min(hdev->rss_size_max, hdev->num_tqps);
 }
 
 /**
@@ -3412,8 +3421,10 @@ static int __init hclgevf_init(void)
 
 static void __exit hclgevf_exit(void)
 {
+	hnae3_acquire_unload_lock();
 	hnae3_unregister_ae_algo(&ae_algovf);
 	destroy_workqueue(hclgevf_wq);
+	hnae3_release_unload_lock();
 }
 module_init(hclgevf_init);
 module_exit(hclgevf_exit);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
index cccef3228461..0208425ab594 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
@@ -253,6 +253,7 @@ struct hclgevf_dev {
 	int *vector_irq;
 
 	bool gro_en;
+	bool rxvtag_strip_en;
 
 	unsigned long vlan_del_fail_bmap[BITS_TO_LONGS(VLAN_N_VID)];
 
diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c
index b619a3ec245b..04192190beba 100644
--- a/drivers/net/ethernet/ibm/ibmveth.c
+++ b/drivers/net/ethernet/ibm/ibmveth.c
@@ -1802,18 +1802,22 @@ static ssize_t veth_pool_store(struct kobject *kobj, struct attribute *attr,
 	long value = simple_strtol(buf, NULL, 10);
 	long rc;
 
+	rtnl_lock();
+
 	if (attr == &veth_active_attr) {
 		if (value && !pool->active) {
 			if (netif_running(netdev)) {
 				if (ibmveth_alloc_buffer_pool(pool)) {
 					netdev_err(netdev,
 						   "unable to alloc pool\n");
-					return -ENOMEM;
+					rc = -ENOMEM;
+					goto unlock_err;
 				}
 				pool->active = 1;
 				ibmveth_close(netdev);
-				if ((rc = ibmveth_open(netdev)))
-					return rc;
+				rc = ibmveth_open(netdev);
+				if (rc)
+					goto unlock_err;
 			} else {
 				pool->active = 1;
 			}
@@ -1833,48 +1837,59 @@ static ssize_t veth_pool_store(struct kobject *kobj, struct attribute *attr,
 
 			if (i == IBMVETH_NUM_BUFF_POOLS) {
 				netdev_err(netdev, "no active pool >= MTU\n");
-				return -EPERM;
+				rc = -EPERM;
+				goto unlock_err;
 			}
 
 			if (netif_running(netdev)) {
 				ibmveth_close(netdev);
 				pool->active = 0;
-				if ((rc = ibmveth_open(netdev)))
-					return rc;
+				rc = ibmveth_open(netdev);
+				if (rc)
+					goto unlock_err;
 			}
 			pool->active = 0;
 		}
 	} else if (attr == &veth_num_attr) {
 		if (value <= 0 || value > IBMVETH_MAX_POOL_COUNT) {
-			return -EINVAL;
+			rc = -EINVAL;
+			goto unlock_err;
 		} else {
 			if (netif_running(netdev)) {
 				ibmveth_close(netdev);
 				pool->size = value;
-				if ((rc = ibmveth_open(netdev)))
-					return rc;
+				rc = ibmveth_open(netdev);
+				if (rc)
+					goto unlock_err;
 			} else {
 				pool->size = value;
 			}
 		}
 	} else if (attr == &veth_size_attr) {
 		if (value <= IBMVETH_BUFF_OH || value > IBMVETH_MAX_BUF_SIZE) {
-			return -EINVAL;
+			rc = -EINVAL;
+			goto unlock_err;
 		} else {
 			if (netif_running(netdev)) {
 				ibmveth_close(netdev);
 				pool->buff_size = value;
-				if ((rc = ibmveth_open(netdev)))
-					return rc;
+				rc = ibmveth_open(netdev);
+				if (rc)
+					goto unlock_err;
 			} else {
 				pool->buff_size = value;
 			}
 		}
 	}
+	rtnl_unlock();
 
 	/* kick the interrupt handler to allocate/deallocate pools */
 	ibmveth_interrupt(netdev->irq, netdev);
 	return count;
+
+unlock_err:
+	rtnl_unlock();
+	return rc;
 }
 
 
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 97425c06e1ed..61db00b2b33e 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -2310,7 +2310,7 @@ static void ibmvnic_tx_scrq_clean_buffer(struct ibmvnic_adapter *adapter,
 		tx_buff = &tx_pool->tx_buff[index];
 		adapter->netdev->stats.tx_packets--;
 		adapter->netdev->stats.tx_bytes -= tx_buff->skb->len;
-		adapter->tx_stats_buffers[queue_num].packets--;
+		adapter->tx_stats_buffers[queue_num].batched_packets--;
 		adapter->tx_stats_buffers[queue_num].bytes -=
 						tx_buff->skb->len;
 		dev_kfree_skb_any(tx_buff->skb);
@@ -2402,11 +2402,13 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
 	unsigned int tx_map_failed = 0;
 	union sub_crq indir_arr[16];
 	unsigned int tx_dropped = 0;
-	unsigned int tx_packets = 0;
+	unsigned int tx_dpackets = 0;
+	unsigned int tx_bpackets = 0;
 	unsigned int tx_bytes = 0;
 	dma_addr_t data_dma_addr;
 	struct netdev_queue *txq;
 	unsigned long lpar_rc;
+	unsigned int skblen;
 	union sub_crq tx_crq;
 	unsigned int offset;
 	bool use_scrq_send_direct = false;
@@ -2521,6 +2523,7 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
 	tx_buff->skb = skb;
 	tx_buff->index = bufidx;
 	tx_buff->pool_index = queue_num;
+	skblen = skb->len;
 
 	memset(&tx_crq, 0, sizeof(tx_crq));
 	tx_crq.v1.first = IBMVNIC_CRQ_CMD;
@@ -2575,6 +2578,7 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
 		if (lpar_rc != H_SUCCESS)
 			goto tx_err;
 
+		tx_dpackets++;
 		goto early_exit;
 	}
 
@@ -2603,6 +2607,8 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
 			goto tx_err;
 	}
 
+	tx_bpackets++;
+
 early_exit:
 	if (atomic_add_return(num_entries, &tx_scrq->used)
 					>= adapter->req_tx_entries_per_subcrq) {
@@ -2610,8 +2616,7 @@ early_exit:
 		netif_stop_subqueue(netdev, queue_num);
 	}
 
-	tx_packets++;
-	tx_bytes += skb->len;
+	tx_bytes += skblen;
 	txq_trans_cond_update(txq);
 	ret = NETDEV_TX_OK;
 	goto out;
@@ -2640,10 +2645,11 @@ out:
 	rcu_read_unlock();
 	netdev->stats.tx_dropped += tx_dropped;
 	netdev->stats.tx_bytes += tx_bytes;
-	netdev->stats.tx_packets += tx_packets;
+	netdev->stats.tx_packets += tx_bpackets + tx_dpackets;
 	adapter->tx_send_failed += tx_send_failed;
 	adapter->tx_map_failed += tx_map_failed;
-	adapter->tx_stats_buffers[queue_num].packets += tx_packets;
+	adapter->tx_stats_buffers[queue_num].batched_packets += tx_bpackets;
+	adapter->tx_stats_buffers[queue_num].direct_packets += tx_dpackets;
 	adapter->tx_stats_buffers[queue_num].bytes += tx_bytes;
 	adapter->tx_stats_buffers[queue_num].dropped_packets += tx_dropped;
 
@@ -3808,7 +3814,10 @@ static void ibmvnic_get_strings(struct net_device *dev, u32 stringset, u8 *data)
 		memcpy(data, ibmvnic_stats[i].name, ETH_GSTRING_LEN);
 
 	for (i = 0; i < adapter->req_tx_queues; i++) {
-		snprintf(data, ETH_GSTRING_LEN, "tx%d_packets", i);
+		snprintf(data, ETH_GSTRING_LEN, "tx%d_batched_packets", i);
+		data += ETH_GSTRING_LEN;
+
+		snprintf(data, ETH_GSTRING_LEN, "tx%d_direct_packets", i);
 		data += ETH_GSTRING_LEN;
 
 		snprintf(data, ETH_GSTRING_LEN, "tx%d_bytes", i);
@@ -3873,7 +3882,9 @@ static void ibmvnic_get_ethtool_stats(struct net_device *dev,
 				      (adapter, ibmvnic_stats[i].offset));
 
 	for (j = 0; j < adapter->req_tx_queues; j++) {
-		data[i] = adapter->tx_stats_buffers[j].packets;
+		data[i] = adapter->tx_stats_buffers[j].batched_packets;
+		i++;
+		data[i] = adapter->tx_stats_buffers[j].direct_packets;
 		i++;
 		data[i] = adapter->tx_stats_buffers[j].bytes;
 		i++;
diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h
index 94ac36b1408b..246ddce753f9 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.h
+++ b/drivers/net/ethernet/ibm/ibmvnic.h
@@ -211,20 +211,25 @@ struct ibmvnic_statistics {
 	u8 reserved[72];
 } __packed __aligned(8);
 
-#define NUM_TX_STATS 3
 struct ibmvnic_tx_queue_stats {
-	u64 packets;
+	u64 batched_packets;
+	u64 direct_packets;
 	u64 bytes;
 	u64 dropped_packets;
 };
 
-#define NUM_RX_STATS 3
+#define NUM_TX_STATS \
+	(sizeof(struct ibmvnic_tx_queue_stats) / sizeof(u64))
+
 struct ibmvnic_rx_queue_stats {
 	u64 packets;
 	u64 bytes;
 	u64 interrupts;
 };
 
+#define NUM_RX_STATS \
+	(sizeof(struct ibmvnic_rx_queue_stats) / sizeof(u64))
+
 struct ibmvnic_acl_buffer {
 	__be32 len;
 	__be32 version;
diff --git a/drivers/net/ethernet/intel/e1000e/defines.h b/drivers/net/ethernet/intel/e1000e/defines.h
index 5e2cfa73f889..ba331899d186 100644
--- a/drivers/net/ethernet/intel/e1000e/defines.h
+++ b/drivers/net/ethernet/intel/e1000e/defines.h
@@ -638,6 +638,9 @@
 /* For checksumming, the sum of all words in the NVM should equal 0xBABA. */
 #define NVM_SUM                    0xBABA
 
+/* Uninitialized ("empty") checksum word value */
+#define NVM_CHECKSUM_UNINITIALIZED 0xFFFF
+
 /* PBA (printed board assembly) number words */
 #define NVM_PBA_OFFSET_0           8
 #define NVM_PBA_OFFSET_1           9
@@ -803,4 +806,7 @@
 /* SerDes Control */
 #define E1000_GEN_POLL_TIMEOUT          640
 
+#define E1000_FEXTNVM12_PHYPD_CTRL_MASK	0x00C00000
+#define E1000_FEXTNVM12_PHYPD_CTRL_P1	0x00800000
+
 #endif /* _E1000_DEFINES_H_ */
diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c
index 2f9655cf5dd9..df4e7d781cb1 100644
--- a/drivers/net/ethernet/intel/e1000e/ich8lan.c
+++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c
@@ -286,6 +286,45 @@ static void e1000_toggle_lanphypc_pch_lpt(struct e1000_hw *hw)
 }
 
 /**
+ * e1000_reconfigure_k1_exit_timeout - reconfigure K1 exit timeout to
+ * align to MTP and later platform requirements.
+ * @hw: pointer to the HW structure
+ *
+ * Context: PHY semaphore must be held by caller.
+ * Return: 0 on success, negative on failure
+ */
+static s32 e1000_reconfigure_k1_exit_timeout(struct e1000_hw *hw)
+{
+	u16 phy_timeout;
+	u32 fextnvm12;
+	s32 ret_val;
+
+	if (hw->mac.type < e1000_pch_mtp)
+		return 0;
+
+	/* Change Kumeran K1 power down state from P0s to P1 */
+	fextnvm12 = er32(FEXTNVM12);
+	fextnvm12 &= ~E1000_FEXTNVM12_PHYPD_CTRL_MASK;
+	fextnvm12 |= E1000_FEXTNVM12_PHYPD_CTRL_P1;
+	ew32(FEXTNVM12, fextnvm12);
+
+	/* Wait for the interface the settle */
+	usleep_range(1000, 1100);
+
+	/* Change K1 exit timeout */
+	ret_val = e1e_rphy_locked(hw, I217_PHY_TIMEOUTS_REG,
+				  &phy_timeout);
+	if (ret_val)
+		return ret_val;
+
+	phy_timeout &= ~I217_PHY_TIMEOUTS_K1_EXIT_TO_MASK;
+	phy_timeout |= 0xF00;
+
+	return e1e_wphy_locked(hw, I217_PHY_TIMEOUTS_REG,
+				  phy_timeout);
+}
+
+/**
  *  e1000_init_phy_workarounds_pchlan - PHY initialization workarounds
  *  @hw: pointer to the HW structure
  *
@@ -327,15 +366,22 @@ static s32 e1000_init_phy_workarounds_pchlan(struct e1000_hw *hw)
 	 * LANPHYPC Value bit to force the interconnect to PCIe mode.
 	 */
 	switch (hw->mac.type) {
+	case e1000_pch_mtp:
+	case e1000_pch_lnp:
+	case e1000_pch_ptp:
+	case e1000_pch_nvp:
+		/* At this point the PHY might be inaccessible so don't
+		 * propagate the failure
+		 */
+		if (e1000_reconfigure_k1_exit_timeout(hw))
+			e_dbg("Failed to reconfigure K1 exit timeout\n");
+
+		fallthrough;
 	case e1000_pch_lpt:
 	case e1000_pch_spt:
 	case e1000_pch_cnp:
 	case e1000_pch_tgp:
 	case e1000_pch_adp:
-	case e1000_pch_mtp:
-	case e1000_pch_lnp:
-	case e1000_pch_ptp:
-	case e1000_pch_nvp:
 		if (e1000_phy_is_accessible_pchlan(hw))
 			break;
 
@@ -419,8 +465,20 @@ static s32 e1000_init_phy_workarounds_pchlan(struct e1000_hw *hw)
 		 *  the PHY is in.
 		 */
 		ret_val = hw->phy.ops.check_reset_block(hw);
-		if (ret_val)
+		if (ret_val) {
 			e_err("ME blocked access to PHY after reset\n");
+			goto out;
+		}
+
+		if (hw->mac.type >= e1000_pch_mtp) {
+			ret_val = hw->phy.ops.acquire(hw);
+			if (ret_val) {
+				e_err("Failed to reconfigure K1 exit timeout\n");
+				goto out;
+			}
+			ret_val = e1000_reconfigure_k1_exit_timeout(hw);
+			hw->phy.ops.release(hw);
+		}
 	}
 
 out:
@@ -4216,6 +4274,8 @@ static s32 e1000_validate_nvm_checksum_ich8lan(struct e1000_hw *hw)
 			ret_val = e1000e_update_nvm_checksum(hw);
 			if (ret_val)
 				return ret_val;
+		} else if (hw->mac.type == e1000_pch_tgp) {
+			return 0;
 		}
 	}
 
@@ -4888,6 +4948,18 @@ static s32 e1000_init_hw_ich8lan(struct e1000_hw *hw)
 	u16 i;
 
 	e1000_initialize_hw_bits_ich8lan(hw);
+	if (hw->mac.type >= e1000_pch_mtp) {
+		ret_val = hw->phy.ops.acquire(hw);
+		if (ret_val)
+			return ret_val;
+
+		ret_val = e1000_reconfigure_k1_exit_timeout(hw);
+		hw->phy.ops.release(hw);
+		if (ret_val) {
+			e_dbg("Error failed to reconfigure K1 exit timeout\n");
+			return ret_val;
+		}
+	}
 
 	/* Initialize identification LED */
 	ret_val = mac->ops.id_led_init(hw);
diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.h b/drivers/net/ethernet/intel/e1000e/ich8lan.h
index 2504b11c3169..5feb589a9b5f 100644
--- a/drivers/net/ethernet/intel/e1000e/ich8lan.h
+++ b/drivers/net/ethernet/intel/e1000e/ich8lan.h
@@ -219,6 +219,10 @@
 #define I217_PLL_CLOCK_GATE_REG	PHY_REG(772, 28)
 #define I217_PLL_CLOCK_GATE_MASK	0x07FF
 
+/* PHY Timeouts */
+#define I217_PHY_TIMEOUTS_REG                   PHY_REG(770, 21)
+#define I217_PHY_TIMEOUTS_K1_EXIT_TO_MASK       0x0FC0
+
 #define SW_FLAG_TIMEOUT		1000	/* SW Semaphore flag timeout in ms */
 
 /* Inband Control */
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 07e903346358..5fe54e9b71e2 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -3540,9 +3540,6 @@ s32 e1000e_get_base_timinca(struct e1000_adapter *adapter, u32 *timinca)
 	case e1000_pch_cnp:
 	case e1000_pch_tgp:
 	case e1000_pch_adp:
-	case e1000_pch_mtp:
-	case e1000_pch_lnp:
-	case e1000_pch_ptp:
 	case e1000_pch_nvp:
 		if (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI) {
 			/* Stable 24MHz frequency */
@@ -3558,6 +3555,17 @@ s32 e1000e_get_base_timinca(struct e1000_adapter *adapter, u32 *timinca)
 			adapter->cc.shift = shift;
 		}
 		break;
+	case e1000_pch_mtp:
+	case e1000_pch_lnp:
+	case e1000_pch_ptp:
+		/* System firmware can misreport this value, so set it to a
+		 * stable 38400KHz frequency.
+		 */
+		incperiod = INCPERIOD_38400KHZ;
+		incvalue = INCVALUE_38400KHZ;
+		shift = INCVALUE_SHIFT_38400KHZ;
+		adapter->cc.shift = shift;
+		break;
 	case e1000_82574:
 	case e1000_82583:
 		/* Stable 25MHz frequency */
diff --git a/drivers/net/ethernet/intel/e1000e/nvm.c b/drivers/net/ethernet/intel/e1000e/nvm.c
index e609f4df86f4..16369e6d245a 100644
--- a/drivers/net/ethernet/intel/e1000e/nvm.c
+++ b/drivers/net/ethernet/intel/e1000e/nvm.c
@@ -558,6 +558,12 @@ s32 e1000e_validate_nvm_checksum_generic(struct e1000_hw *hw)
 		checksum += nvm_data;
 	}
 
+	if (hw->mac.type == e1000_pch_tgp &&
+	    nvm_data == NVM_CHECKSUM_UNINITIALIZED) {
+		e_dbg("Uninitialized NVM Checksum on TGP platform - ignoring\n");
+		return 0;
+	}
+
 	if (checksum != (u16)NVM_SUM) {
 		e_dbg("NVM Checksum Invalid\n");
 		return -E1000_ERR_NVM;
diff --git a/drivers/net/ethernet/intel/e1000e/ptp.c b/drivers/net/ethernet/intel/e1000e/ptp.c
index 89d57dd911dc..ea3c3eb2ef20 100644
--- a/drivers/net/ethernet/intel/e1000e/ptp.c
+++ b/drivers/net/ethernet/intel/e1000e/ptp.c
@@ -295,15 +295,17 @@ void e1000e_ptp_init(struct e1000_adapter *adapter)
 	case e1000_pch_cnp:
 	case e1000_pch_tgp:
 	case e1000_pch_adp:
-	case e1000_pch_mtp:
-	case e1000_pch_lnp:
-	case e1000_pch_ptp:
 	case e1000_pch_nvp:
 		if (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI)
 			adapter->ptp_clock_info.max_adj = MAX_PPB_24MHZ;
 		else
 			adapter->ptp_clock_info.max_adj = MAX_PPB_38400KHZ;
 		break;
+	case e1000_pch_mtp:
+	case e1000_pch_lnp:
+	case e1000_pch_ptp:
+		adapter->ptp_clock_info.max_adj = MAX_PPB_38400KHZ;
+		break;
 	case e1000_82574:
 	case e1000_82583:
 		adapter->ptp_clock_info.max_adj = MAX_PPB_25MHZ;
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k.h b/drivers/net/ethernet/intel/fm10k/fm10k.h
index 6119a4108838..65a2816142d9 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k.h
+++ b/drivers/net/ethernet/intel/fm10k/fm10k.h
@@ -189,13 +189,14 @@ struct fm10k_q_vector {
 	struct fm10k_ring_container rx, tx;
 
 	struct napi_struct napi;
+	struct rcu_head rcu;	/* to avoid race with update stats on free */
+
 	cpumask_t affinity_mask;
 	char name[IFNAMSIZ + 9];
 
 #ifdef CONFIG_DEBUG_FS
 	struct dentry *dbg_q_vector;
 #endif /* CONFIG_DEBUG_FS */
-	struct rcu_head rcu;	/* to avoid race with update stats on free */
 
 	/* for dynamic allocation of rings associated with this q_vector */
 	struct fm10k_ring ring[] ____cacheline_internodealigned_in_smp;
diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index d4255c2706fa..b22bb0ae9b9d 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -943,6 +943,7 @@ struct i40e_q_vector {
 	u16 reg_idx;		/* register index of the interrupt */
 
 	struct napi_struct napi;
+	struct rcu_head rcu;	/* to avoid race with update stats on free */
 
 	struct i40e_ring_container rx;
 	struct i40e_ring_container tx;
@@ -953,7 +954,6 @@ struct i40e_q_vector {
 	cpumask_t affinity_mask;
 	struct irq_affinity_notify affinity_notify;
 
-	struct rcu_head rcu;	/* to avoid race with update stats on free */
 	char name[I40E_INT_NAME_STR_LEN];
 	bool arm_wb_state;
 	bool in_busy_poll;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c
index e8031f1a9b4f..2f5a85014867 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_common.c
@@ -817,10 +817,11 @@ int i40e_pf_reset(struct i40e_hw *hw)
 void i40e_clear_hw(struct i40e_hw *hw)
 {
 	u32 num_queues, base_queue;
-	u32 num_pf_int;
-	u32 num_vf_int;
+	s32 num_pf_int;
+	s32 num_vf_int;
 	u32 num_vfs;
-	u32 i, j;
+	s32 i;
+	u32 j;
 	u32 val;
 	u32 eol = 0x7ff;
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index dfa785e39458..97f32a0c68d0 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -1546,8 +1546,8 @@ static void i40e_cleanup_reset_vf(struct i40e_vf *vf)
  * @vf: pointer to the VF structure
  * @flr: VFLR was issued or not
  *
- * Returns true if the VF is in reset, resets successfully, or resets
- * are disabled and false otherwise.
+ * Return: True if reset was performed successfully or if resets are disabled.
+ * False if reset is already in progress.
  **/
 bool i40e_reset_vf(struct i40e_vf *vf, bool flr)
 {
@@ -1566,7 +1566,7 @@ bool i40e_reset_vf(struct i40e_vf *vf, bool flr)
 
 	/* If VF is being reset already we don't need to continue. */
 	if (test_and_set_bit(I40E_VF_STATE_RESETTING, &vf->vf_states))
-		return true;
+		return false;
 
 	i40e_trigger_vf_reset(vf, flr);
 
@@ -3137,10 +3137,10 @@ static int i40e_vc_del_mac_addr_msg(struct i40e_vf *vf, u8 *msg)
 		const u8 *addr = al->list[i].addr;
 
 		/* Allow to delete VF primary MAC only if it was not set
-		 * administratively by PF or if VF is trusted.
+		 * administratively by PF.
 		 */
 		if (ether_addr_equal(addr, vf->default_lan_addr.addr)) {
-			if (i40e_can_vf_change_mac(vf))
+			if (!vf->pf_set_mac)
 				was_unimac_deleted = true;
 			else
 				continue;
@@ -4328,7 +4328,10 @@ int i40e_vc_process_vflr_event(struct i40e_pf *pf)
 		reg = rd32(hw, I40E_GLGEN_VFLRSTAT(reg_idx));
 		if (reg & BIT(bit_idx))
 			/* i40e_reset_vf will clear the bit in GLGEN_VFLRSTAT */
-			i40e_reset_vf(vf, true);
+			if (!i40e_reset_vf(vf, true)) {
+				/* At least one VF did not finish resetting, retry next time */
+				set_bit(__I40E_VFLR_EVENT_PENDING, pf->state);
+			}
 	}
 
 	return 0;
@@ -5003,7 +5006,7 @@ int i40e_get_vf_stats(struct net_device *netdev, int vf_id,
 	vf_stats->broadcast  = stats->rx_broadcast;
 	vf_stats->multicast  = stats->rx_multicast;
 	vf_stats->rx_dropped = stats->rx_discards + stats->rx_discards_other;
-	vf_stats->tx_dropped = stats->tx_discards;
+	vf_stats->tx_dropped = stats->tx_errors;
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index f782402cd789..5516795cc250 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -773,6 +773,11 @@ iavf_vlan_filter *iavf_add_vlan(struct iavf_adapter *adapter,
 		f->state = IAVF_VLAN_ADD;
 		adapter->num_vlan_filters++;
 		iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_ADD_VLAN_FILTER);
+	} else if (f->state == IAVF_VLAN_REMOVE) {
+		/* IAVF_VLAN_REMOVE means that VLAN wasn't yet removed.
+		 * We can safely only change the state here.
+		 */
+		f->state = IAVF_VLAN_ACTIVE;
 	}
 
 clearout:
@@ -793,8 +798,18 @@ static void iavf_del_vlan(struct iavf_adapter *adapter, struct iavf_vlan vlan)
 
 	f = iavf_find_vlan(adapter, vlan);
 	if (f) {
-		f->state = IAVF_VLAN_REMOVE;
-		iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_DEL_VLAN_FILTER);
+		/* IAVF_ADD_VLAN means that VLAN wasn't even added yet.
+		 * Remove it from the list.
+		 */
+		if (f->state == IAVF_VLAN_ADD) {
+			list_del(&f->list);
+			kfree(f);
+			adapter->num_vlan_filters--;
+		} else {
+			f->state = IAVF_VLAN_REMOVE;
+			iavf_schedule_aq_request(adapter,
+						 IAVF_FLAG_AQ_DEL_VLAN_FILTER);
+		}
 	}
 
 	spin_unlock_bh(&adapter->mac_vlan_list_lock);
diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink.c b/drivers/net/ethernet/intel/ice/devlink/devlink.c
index 415445cefdb2..b1efd287b330 100644
--- a/drivers/net/ethernet/intel/ice/devlink/devlink.c
+++ b/drivers/net/ethernet/intel/ice/devlink/devlink.c
@@ -977,6 +977,9 @@ static int ice_devlink_rate_node_new(struct devlink_rate *rate_node, void **priv
 
 	/* preallocate memory for ice_sched_node */
 	node = devm_kzalloc(ice_hw_to_dev(pi->hw), sizeof(*node), GFP_KERNEL);
+	if (!node)
+		return -ENOMEM;
+
 	*priv = node;
 
 	return 0;
diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index 558cda577191..2960709f6b62 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -207,6 +207,7 @@ enum ice_feature {
 	ICE_F_GNSS,
 	ICE_F_ROCE_LAG,
 	ICE_F_SRIOV_LAG,
+	ICE_F_MBX_LIMIT,
 	ICE_F_MAX
 };
 
diff --git a/drivers/net/ethernet/intel/ice/ice_adapter.c b/drivers/net/ethernet/intel/ice/ice_adapter.c
index f3e195974a8e..66e070095d1b 100644
--- a/drivers/net/ethernet/intel/ice/ice_adapter.c
+++ b/drivers/net/ethernet/intel/ice/ice_adapter.c
@@ -1,7 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 // SPDX-FileCopyrightText: Copyright Red Hat
 
-#include <linux/bitfield.h>
 #include <linux/cleanup.h>
 #include <linux/mutex.h>
 #include <linux/pci.h>
@@ -9,27 +8,21 @@
 #include <linux/spinlock.h>
 #include <linux/xarray.h>
 #include "ice_adapter.h"
+#include "ice.h"
 
 static DEFINE_XARRAY(ice_adapters);
 static DEFINE_MUTEX(ice_adapters_mutex);
 
-/* PCI bus number is 8 bits. Slot is 5 bits. Domain can have the rest. */
-#define INDEX_FIELD_DOMAIN GENMASK(BITS_PER_LONG - 1, 13)
-#define INDEX_FIELD_BUS    GENMASK(12, 5)
-#define INDEX_FIELD_SLOT   GENMASK(4, 0)
-
-static unsigned long ice_adapter_index(const struct pci_dev *pdev)
+static unsigned long ice_adapter_index(u64 dsn)
 {
-	unsigned int domain = pci_domain_nr(pdev->bus);
-
-	WARN_ON(domain > FIELD_MAX(INDEX_FIELD_DOMAIN));
-
-	return FIELD_PREP(INDEX_FIELD_DOMAIN, domain) |
-	       FIELD_PREP(INDEX_FIELD_BUS,    pdev->bus->number) |
-	       FIELD_PREP(INDEX_FIELD_SLOT,   PCI_SLOT(pdev->devfn));
+#if BITS_PER_LONG == 64
+	return dsn;
+#else
+	return (u32)dsn ^ (u32)(dsn >> 32);
+#endif
 }
 
-static struct ice_adapter *ice_adapter_new(void)
+static struct ice_adapter *ice_adapter_new(u64 dsn)
 {
 	struct ice_adapter *adapter;
 
@@ -37,6 +30,7 @@ static struct ice_adapter *ice_adapter_new(void)
 	if (!adapter)
 		return NULL;
 
+	adapter->device_serial_number = dsn;
 	spin_lock_init(&adapter->ptp_gltsyn_time_lock);
 	refcount_set(&adapter->refcount, 1);
 
@@ -67,23 +61,26 @@ static void ice_adapter_free(struct ice_adapter *adapter)
  * Return:  Pointer to ice_adapter on success.
  *          ERR_PTR() on error. -ENOMEM is the only possible error.
  */
-struct ice_adapter *ice_adapter_get(const struct pci_dev *pdev)
+struct ice_adapter *ice_adapter_get(struct pci_dev *pdev)
 {
-	unsigned long index = ice_adapter_index(pdev);
+	u64 dsn = pci_get_dsn(pdev);
 	struct ice_adapter *adapter;
+	unsigned long index;
 	int err;
 
+	index = ice_adapter_index(dsn);
 	scoped_guard(mutex, &ice_adapters_mutex) {
 		err = xa_insert(&ice_adapters, index, NULL, GFP_KERNEL);
 		if (err == -EBUSY) {
 			adapter = xa_load(&ice_adapters, index);
 			refcount_inc(&adapter->refcount);
+			WARN_ON_ONCE(adapter->device_serial_number != dsn);
 			return adapter;
 		}
 		if (err)
 			return ERR_PTR(err);
 
-		adapter = ice_adapter_new();
+		adapter = ice_adapter_new(dsn);
 		if (!adapter)
 			return ERR_PTR(-ENOMEM);
 		xa_store(&ice_adapters, index, adapter, GFP_KERNEL);
@@ -100,11 +97,13 @@ struct ice_adapter *ice_adapter_get(const struct pci_dev *pdev)
  *
  * Context: Process, may sleep.
  */
-void ice_adapter_put(const struct pci_dev *pdev)
+void ice_adapter_put(struct pci_dev *pdev)
 {
-	unsigned long index = ice_adapter_index(pdev);
+	u64 dsn = pci_get_dsn(pdev);
 	struct ice_adapter *adapter;
+	unsigned long index;
 
+	index = ice_adapter_index(dsn);
 	scoped_guard(mutex, &ice_adapters_mutex) {
 		adapter = xa_load(&ice_adapters, index);
 		if (WARN_ON(!adapter))
diff --git a/drivers/net/ethernet/intel/ice/ice_adapter.h b/drivers/net/ethernet/intel/ice/ice_adapter.h
index e233225848b3..ac15c0d2bc1a 100644
--- a/drivers/net/ethernet/intel/ice/ice_adapter.h
+++ b/drivers/net/ethernet/intel/ice/ice_adapter.h
@@ -32,6 +32,7 @@ struct ice_port_list {
  * @refcount: Reference count. struct ice_pf objects hold the references.
  * @ctrl_pf: Control PF of the adapter
  * @ports: Ports list
+ * @device_serial_number: DSN cached for collision detection on 32bit systems
  */
 struct ice_adapter {
 	refcount_t refcount;
@@ -40,9 +41,10 @@ struct ice_adapter {
 
 	struct ice_pf *ctrl_pf;
 	struct ice_port_list ports;
+	u64 device_serial_number;
 };
 
-struct ice_adapter *ice_adapter_get(const struct pci_dev *pdev);
-void ice_adapter_put(const struct pci_dev *pdev);
+struct ice_adapter *ice_adapter_get(struct pci_dev *pdev);
+void ice_adapter_put(struct pci_dev *pdev);
 
 #endif /* _ICE_ADAPTER_H */
diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
index 80f3dfd27124..66ae0352c6bc 100644
--- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
@@ -1491,7 +1491,23 @@ struct ice_aqc_dnl_equa_param {
 #define ICE_AQC_RX_EQU_POST1 (0x12 << ICE_AQC_RX_EQU_SHIFT)
 #define ICE_AQC_RX_EQU_BFLF (0x13 << ICE_AQC_RX_EQU_SHIFT)
 #define ICE_AQC_RX_EQU_BFHF (0x14 << ICE_AQC_RX_EQU_SHIFT)
-#define ICE_AQC_RX_EQU_DRATE (0x15 << ICE_AQC_RX_EQU_SHIFT)
+#define ICE_AQC_RX_EQU_CTLE_GAINHF (0x20 << ICE_AQC_RX_EQU_SHIFT)
+#define ICE_AQC_RX_EQU_CTLE_GAINLF (0x21 << ICE_AQC_RX_EQU_SHIFT)
+#define ICE_AQC_RX_EQU_CTLE_GAINDC (0x22 << ICE_AQC_RX_EQU_SHIFT)
+#define ICE_AQC_RX_EQU_CTLE_BW (0x23 << ICE_AQC_RX_EQU_SHIFT)
+#define ICE_AQC_RX_EQU_DFE_GAIN (0x30 << ICE_AQC_RX_EQU_SHIFT)
+#define ICE_AQC_RX_EQU_DFE_GAIN2 (0x31 << ICE_AQC_RX_EQU_SHIFT)
+#define ICE_AQC_RX_EQU_DFE_2 (0x32 << ICE_AQC_RX_EQU_SHIFT)
+#define ICE_AQC_RX_EQU_DFE_3 (0x33 << ICE_AQC_RX_EQU_SHIFT)
+#define ICE_AQC_RX_EQU_DFE_4 (0x34 << ICE_AQC_RX_EQU_SHIFT)
+#define ICE_AQC_RX_EQU_DFE_5 (0x35 << ICE_AQC_RX_EQU_SHIFT)
+#define ICE_AQC_RX_EQU_DFE_6 (0x36 << ICE_AQC_RX_EQU_SHIFT)
+#define ICE_AQC_RX_EQU_DFE_7 (0x37 << ICE_AQC_RX_EQU_SHIFT)
+#define ICE_AQC_RX_EQU_DFE_8 (0x38 << ICE_AQC_RX_EQU_SHIFT)
+#define ICE_AQC_RX_EQU_DFE_9 (0x39 << ICE_AQC_RX_EQU_SHIFT)
+#define ICE_AQC_RX_EQU_DFE_10 (0x3A << ICE_AQC_RX_EQU_SHIFT)
+#define ICE_AQC_RX_EQU_DFE_11 (0x3B << ICE_AQC_RX_EQU_SHIFT)
+#define ICE_AQC_RX_EQU_DFE_12 (0x3C << ICE_AQC_RX_EQU_SHIFT)
 #define ICE_AQC_TX_EQU_PRE1 0x0
 #define ICE_AQC_TX_EQU_PRE3 0x3
 #define ICE_AQC_TX_EQU_ATTEN 0x4
diff --git a/drivers/net/ethernet/intel/ice/ice_arfs.c b/drivers/net/ethernet/intel/ice/ice_arfs.c
index 7cee365cc7d1..0bb4fb56fbe6 100644
--- a/drivers/net/ethernet/intel/ice/ice_arfs.c
+++ b/drivers/net/ethernet/intel/ice/ice_arfs.c
@@ -378,6 +378,50 @@ ice_arfs_is_perfect_flow_set(struct ice_hw *hw, __be16 l3_proto, u8 l4_proto)
 }
 
 /**
+ * ice_arfs_cmp - Check if aRFS filter matches this flow.
+ * @fltr_info: filter info of the saved ARFS entry.
+ * @fk: flow dissector keys.
+ * @n_proto:  One of htons(ETH_P_IP) or htons(ETH_P_IPV6).
+ * @ip_proto: One of IPPROTO_TCP or IPPROTO_UDP.
+ *
+ * Since this function assumes limited values for n_proto and ip_proto, it
+ * is meant to be called only from ice_rx_flow_steer().
+ *
+ * Return:
+ * * true	- fltr_info refers to the same flow as fk.
+ * * false	- fltr_info and fk refer to different flows.
+ */
+static bool
+ice_arfs_cmp(const struct ice_fdir_fltr *fltr_info, const struct flow_keys *fk,
+	     __be16 n_proto, u8 ip_proto)
+{
+	/* Determine if the filter is for IPv4 or IPv6 based on flow_type,
+	 * which is one of ICE_FLTR_PTYPE_NONF_IPV{4,6}_{TCP,UDP}.
+	 */
+	bool is_v4 = fltr_info->flow_type == ICE_FLTR_PTYPE_NONF_IPV4_TCP ||
+		     fltr_info->flow_type == ICE_FLTR_PTYPE_NONF_IPV4_UDP;
+
+	/* Following checks are arranged in the quickest and most discriminative
+	 * fields first for early failure.
+	 */
+	if (is_v4)
+		return n_proto == htons(ETH_P_IP) &&
+			fltr_info->ip.v4.src_port == fk->ports.src &&
+			fltr_info->ip.v4.dst_port == fk->ports.dst &&
+			fltr_info->ip.v4.src_ip == fk->addrs.v4addrs.src &&
+			fltr_info->ip.v4.dst_ip == fk->addrs.v4addrs.dst &&
+			fltr_info->ip.v4.proto == ip_proto;
+
+	return fltr_info->ip.v6.src_port == fk->ports.src &&
+		fltr_info->ip.v6.dst_port == fk->ports.dst &&
+		fltr_info->ip.v6.proto == ip_proto &&
+		!memcmp(&fltr_info->ip.v6.src_ip, &fk->addrs.v6addrs.src,
+			sizeof(struct in6_addr)) &&
+		!memcmp(&fltr_info->ip.v6.dst_ip, &fk->addrs.v6addrs.dst,
+			sizeof(struct in6_addr));
+}
+
+/**
  * ice_rx_flow_steer - steer the Rx flow to where application is being run
  * @netdev: ptr to the netdev being adjusted
  * @skb: buffer with required header information
@@ -448,6 +492,10 @@ ice_rx_flow_steer(struct net_device *netdev, const struct sk_buff *skb,
 			continue;
 
 		fltr_info = &arfs_entry->fltr_info;
+
+		if (!ice_arfs_cmp(fltr_info, &fk, n_proto, ip_proto))
+			continue;
+
 		ret = fltr_info->fltr_id;
 
 		if (fltr_info->q_index == rxq_idx ||
@@ -511,7 +559,7 @@ void ice_init_arfs(struct ice_vsi *vsi)
 	struct hlist_head *arfs_fltr_list;
 	unsigned int i;
 
-	if (!vsi || vsi->type != ICE_VSI_PF)
+	if (!vsi || vsi->type != ICE_VSI_PF || ice_is_arfs_active(vsi))
 		return;
 
 	arfs_fltr_list = kcalloc(ICE_MAX_ARFS_LIST, sizeof(*arfs_fltr_list),
diff --git a/drivers/net/ethernet/intel/ice/ice_ddp.c b/drivers/net/ethernet/intel/ice/ice_ddp.c
index 272fd823a825..e4c8cd12a41d 100644
--- a/drivers/net/ethernet/intel/ice/ice_ddp.c
+++ b/drivers/net/ethernet/intel/ice/ice_ddp.c
@@ -2277,6 +2277,8 @@ enum ice_ddp_state ice_copy_and_init_pkg(struct ice_hw *hw, const u8 *buf,
 		return ICE_DDP_PKG_ERR;
 
 	buf_copy = devm_kmemdup(ice_hw_to_dev(hw), buf, len, GFP_KERNEL);
+	if (!buf_copy)
+		return ICE_DDP_PKG_ERR;
 
 	state = ice_init_pkg(hw, buf_copy, len);
 	if (!ice_is_init_pkg_successful(state)) {
diff --git a/drivers/net/ethernet/intel/ice/ice_debugfs.c b/drivers/net/ethernet/intel/ice/ice_debugfs.c
index 9fc0fd95a13d..cb71eca6a85b 100644
--- a/drivers/net/ethernet/intel/ice/ice_debugfs.c
+++ b/drivers/net/ethernet/intel/ice/ice_debugfs.c
@@ -606,7 +606,7 @@ void ice_debugfs_fwlog_init(struct ice_pf *pf)
 
 	pf->ice_debugfs_pf_fwlog = debugfs_create_dir("fwlog",
 						      pf->ice_debugfs_pf);
-	if (IS_ERR(pf->ice_debugfs_pf))
+	if (IS_ERR(pf->ice_debugfs_pf_fwlog))
 		goto err_create_module_files;
 
 	fw_modules_dir = debugfs_create_dir("modules",
diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.c b/drivers/net/ethernet/intel/ice/ice_eswitch.c
index fb527434b58b..5b9a7ee278f1 100644
--- a/drivers/net/ethernet/intel/ice/ice_eswitch.c
+++ b/drivers/net/ethernet/intel/ice/ice_eswitch.c
@@ -38,8 +38,7 @@ static int ice_eswitch_setup_env(struct ice_pf *pf)
 	if (ice_vsi_add_vlan_zero(uplink_vsi))
 		goto err_vlan_zero;
 
-	if (ice_cfg_dflt_vsi(uplink_vsi->port_info, uplink_vsi->idx, true,
-			     ICE_FLTR_RX))
+	if (ice_set_dflt_vsi(uplink_vsi))
 		goto err_def_rx;
 
 	if (ice_cfg_dflt_vsi(uplink_vsi->port_info, uplink_vsi->idx, true,
@@ -50,9 +49,6 @@ static int ice_eswitch_setup_env(struct ice_pf *pf)
 	if (vlan_ops->dis_rx_filtering(uplink_vsi))
 		goto err_vlan_filtering;
 
-	if (ice_vsi_update_security(uplink_vsi, ice_vsi_ctx_set_allow_override))
-		goto err_override_uplink;
-
 	if (ice_vsi_update_local_lb(uplink_vsi, true))
 		goto err_override_local_lb;
 
@@ -64,8 +60,6 @@ static int ice_eswitch_setup_env(struct ice_pf *pf)
 err_up:
 	ice_vsi_update_local_lb(uplink_vsi, false);
 err_override_local_lb:
-	ice_vsi_update_security(uplink_vsi, ice_vsi_ctx_clear_allow_override);
-err_override_uplink:
 	vlan_ops->ena_rx_filtering(uplink_vsi);
 err_vlan_filtering:
 	ice_cfg_dflt_vsi(uplink_vsi->port_info, uplink_vsi->idx, false,
@@ -276,7 +270,6 @@ static void ice_eswitch_release_env(struct ice_pf *pf)
 	vlan_ops = ice_get_compat_vsi_vlan_ops(uplink_vsi);
 
 	ice_vsi_update_local_lb(uplink_vsi, false);
-	ice_vsi_update_security(uplink_vsi, ice_vsi_ctx_clear_allow_override);
 	vlan_ops->ena_rx_filtering(uplink_vsi);
 	ice_cfg_dflt_vsi(uplink_vsi->port_info, uplink_vsi->idx, false,
 			 ICE_FLTR_TX);
@@ -509,10 +502,14 @@ err_create_repr:
  */
 int ice_eswitch_attach_vf(struct ice_pf *pf, struct ice_vf *vf)
 {
-	struct ice_repr *repr = ice_repr_create_vf(vf);
 	struct devlink *devlink = priv_to_devlink(pf);
+	struct ice_repr *repr;
 	int err;
 
+	if (!ice_is_eswitch_mode_switchdev(pf))
+		return 0;
+
+	repr = ice_repr_create_vf(vf);
 	if (IS_ERR(repr))
 		return PTR_ERR(repr);
 
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
index d5cc934d1359..2a2acbeb5722 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -693,75 +693,52 @@ static int ice_get_port_topology(struct ice_hw *hw, u8 lport,
 static int ice_get_tx_rx_equa(struct ice_hw *hw, u8 serdes_num,
 			      struct ice_serdes_equalization_to_ethtool *ptr)
 {
+	static const int tx = ICE_AQC_OP_CODE_TX_EQU;
+	static const int rx = ICE_AQC_OP_CODE_RX_EQU;
+	struct {
+		int data_in;
+		int opcode;
+		int *out;
+	} aq_params[] = {
+		{ ICE_AQC_TX_EQU_PRE1, tx, &ptr->tx_equ_pre1 },
+		{ ICE_AQC_TX_EQU_PRE3, tx, &ptr->tx_equ_pre3 },
+		{ ICE_AQC_TX_EQU_ATTEN, tx, &ptr->tx_equ_atten },
+		{ ICE_AQC_TX_EQU_POST1, tx, &ptr->tx_equ_post1 },
+		{ ICE_AQC_TX_EQU_PRE2, tx, &ptr->tx_equ_pre2 },
+		{ ICE_AQC_RX_EQU_PRE2, rx, &ptr->rx_equ_pre2 },
+		{ ICE_AQC_RX_EQU_PRE1, rx, &ptr->rx_equ_pre1 },
+		{ ICE_AQC_RX_EQU_POST1, rx, &ptr->rx_equ_post1 },
+		{ ICE_AQC_RX_EQU_BFLF, rx, &ptr->rx_equ_bflf },
+		{ ICE_AQC_RX_EQU_BFHF, rx, &ptr->rx_equ_bfhf },
+		{ ICE_AQC_RX_EQU_CTLE_GAINHF, rx, &ptr->rx_equ_ctle_gainhf },
+		{ ICE_AQC_RX_EQU_CTLE_GAINLF, rx, &ptr->rx_equ_ctle_gainlf },
+		{ ICE_AQC_RX_EQU_CTLE_GAINDC, rx, &ptr->rx_equ_ctle_gaindc },
+		{ ICE_AQC_RX_EQU_CTLE_BW, rx, &ptr->rx_equ_ctle_bw },
+		{ ICE_AQC_RX_EQU_DFE_GAIN, rx, &ptr->rx_equ_dfe_gain },
+		{ ICE_AQC_RX_EQU_DFE_GAIN2, rx, &ptr->rx_equ_dfe_gain_2 },
+		{ ICE_AQC_RX_EQU_DFE_2, rx, &ptr->rx_equ_dfe_2 },
+		{ ICE_AQC_RX_EQU_DFE_3, rx, &ptr->rx_equ_dfe_3 },
+		{ ICE_AQC_RX_EQU_DFE_4, rx, &ptr->rx_equ_dfe_4 },
+		{ ICE_AQC_RX_EQU_DFE_5, rx, &ptr->rx_equ_dfe_5 },
+		{ ICE_AQC_RX_EQU_DFE_6, rx, &ptr->rx_equ_dfe_6 },
+		{ ICE_AQC_RX_EQU_DFE_7, rx, &ptr->rx_equ_dfe_7 },
+		{ ICE_AQC_RX_EQU_DFE_8, rx, &ptr->rx_equ_dfe_8 },
+		{ ICE_AQC_RX_EQU_DFE_9, rx, &ptr->rx_equ_dfe_9 },
+		{ ICE_AQC_RX_EQU_DFE_10, rx, &ptr->rx_equ_dfe_10 },
+		{ ICE_AQC_RX_EQU_DFE_11, rx, &ptr->rx_equ_dfe_11 },
+		{ ICE_AQC_RX_EQU_DFE_12, rx, &ptr->rx_equ_dfe_12 },
+	};
 	int err;
 
-	err = ice_aq_get_phy_equalization(hw, ICE_AQC_TX_EQU_PRE1,
-					  ICE_AQC_OP_CODE_TX_EQU, serdes_num,
-					  &ptr->tx_equalization_pre1);
-	if (err)
-		return err;
-
-	err = ice_aq_get_phy_equalization(hw, ICE_AQC_TX_EQU_PRE3,
-					  ICE_AQC_OP_CODE_TX_EQU, serdes_num,
-					  &ptr->tx_equalization_pre3);
-	if (err)
-		return err;
-
-	err = ice_aq_get_phy_equalization(hw, ICE_AQC_TX_EQU_ATTEN,
-					  ICE_AQC_OP_CODE_TX_EQU, serdes_num,
-					  &ptr->tx_equalization_atten);
-	if (err)
-		return err;
-
-	err = ice_aq_get_phy_equalization(hw, ICE_AQC_TX_EQU_POST1,
-					  ICE_AQC_OP_CODE_TX_EQU, serdes_num,
-					  &ptr->tx_equalization_post1);
-	if (err)
-		return err;
-
-	err = ice_aq_get_phy_equalization(hw, ICE_AQC_TX_EQU_PRE2,
-					  ICE_AQC_OP_CODE_TX_EQU, serdes_num,
-					  &ptr->tx_equalization_pre2);
-	if (err)
-		return err;
-
-	err = ice_aq_get_phy_equalization(hw, ICE_AQC_RX_EQU_PRE2,
-					  ICE_AQC_OP_CODE_RX_EQU, serdes_num,
-					  &ptr->rx_equalization_pre2);
-	if (err)
-		return err;
-
-	err = ice_aq_get_phy_equalization(hw, ICE_AQC_RX_EQU_PRE1,
-					  ICE_AQC_OP_CODE_RX_EQU, serdes_num,
-					  &ptr->rx_equalization_pre1);
-	if (err)
-		return err;
-
-	err = ice_aq_get_phy_equalization(hw, ICE_AQC_RX_EQU_POST1,
-					  ICE_AQC_OP_CODE_RX_EQU, serdes_num,
-					  &ptr->rx_equalization_post1);
-	if (err)
-		return err;
-
-	err = ice_aq_get_phy_equalization(hw, ICE_AQC_RX_EQU_BFLF,
-					  ICE_AQC_OP_CODE_RX_EQU, serdes_num,
-					  &ptr->rx_equalization_bflf);
-	if (err)
-		return err;
-
-	err = ice_aq_get_phy_equalization(hw, ICE_AQC_RX_EQU_BFHF,
-					  ICE_AQC_OP_CODE_RX_EQU, serdes_num,
-					  &ptr->rx_equalization_bfhf);
-	if (err)
-		return err;
-
-	err = ice_aq_get_phy_equalization(hw, ICE_AQC_RX_EQU_DRATE,
-					  ICE_AQC_OP_CODE_RX_EQU, serdes_num,
-					  &ptr->rx_equalization_drate);
-	if (err)
-		return err;
+	for (int i = 0; i < ARRAY_SIZE(aq_params); i++) {
+		err = ice_aq_get_phy_equalization(hw, aq_params[i].data_in,
+						  aq_params[i].opcode,
+						  serdes_num, aq_params[i].out);
+		if (err)
+			break;
+	}
 
-	return 0;
+	return err;
 }
 
 /**
@@ -3840,8 +3817,7 @@ static u32 ice_get_combined_cnt(struct ice_vsi *vsi)
 	ice_for_each_q_vector(vsi, q_idx) {
 		struct ice_q_vector *q_vector = vsi->q_vectors[q_idx];
 
-		if (q_vector->rx.rx_ring && q_vector->tx.tx_ring)
-			combined++;
+		combined += min(q_vector->num_ring_tx, q_vector->num_ring_rx);
 	}
 
 	return combined;
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.h b/drivers/net/ethernet/intel/ice/ice_ethtool.h
index 9acccae38625..23b2cfbc9684 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.h
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.h
@@ -10,17 +10,33 @@ struct ice_phy_type_to_ethtool {
 };
 
 struct ice_serdes_equalization_to_ethtool {
-	int rx_equalization_pre2;
-	int rx_equalization_pre1;
-	int rx_equalization_post1;
-	int rx_equalization_bflf;
-	int rx_equalization_bfhf;
-	int rx_equalization_drate;
-	int tx_equalization_pre1;
-	int tx_equalization_pre3;
-	int tx_equalization_atten;
-	int tx_equalization_post1;
-	int tx_equalization_pre2;
+	int rx_equ_pre2;
+	int rx_equ_pre1;
+	int rx_equ_post1;
+	int rx_equ_bflf;
+	int rx_equ_bfhf;
+	int rx_equ_ctle_gainhf;
+	int rx_equ_ctle_gainlf;
+	int rx_equ_ctle_gaindc;
+	int rx_equ_ctle_bw;
+	int rx_equ_dfe_gain;
+	int rx_equ_dfe_gain_2;
+	int rx_equ_dfe_2;
+	int rx_equ_dfe_3;
+	int rx_equ_dfe_4;
+	int rx_equ_dfe_5;
+	int rx_equ_dfe_6;
+	int rx_equ_dfe_7;
+	int rx_equ_dfe_8;
+	int rx_equ_dfe_9;
+	int rx_equ_dfe_10;
+	int rx_equ_dfe_11;
+	int rx_equ_dfe_12;
+	int tx_equ_pre1;
+	int tx_equ_pre3;
+	int tx_equ_atten;
+	int tx_equ_post1;
+	int tx_equ_pre2;
 };
 
 struct ice_regdump_to_ethtool {
diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
index 91cbae1eec89..8d31bfe28cc8 100644
--- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
+++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
@@ -539,5 +539,8 @@
 #define E830_PRTMAC_CL01_QNT_THR_CL0_M		GENMASK(15, 0)
 #define VFINT_DYN_CTLN(_i)			(0x00003800 + ((_i) * 4))
 #define VFINT_DYN_CTLN_CLEARPBA_M		BIT(1)
+#define E830_MBX_PF_IN_FLIGHT_VF_MSGS_THRESH	0x00234000
+#define E830_MBX_VF_DEC_TRIG(_VF)		(0x00233800 + (_VF) * 4)
+#define E830_MBX_VF_IN_FLIGHT_MSGS_AT_PF_CNT(_VF)	(0x00233000 + (_VF) * 4)
 
 #endif /* _ICE_HW_AUTOGEN_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_irq.c b/drivers/net/ethernet/intel/ice/ice_irq.c
index ad82ff7d1995..09f9c7ba5279 100644
--- a/drivers/net/ethernet/intel/ice/ice_irq.c
+++ b/drivers/net/ethernet/intel/ice/ice_irq.c
@@ -45,7 +45,7 @@ static void ice_free_irq_res(struct ice_pf *pf, u16 index)
 /**
  * ice_get_irq_res - get an interrupt resource
  * @pf: board private structure
- * @dyn_only: force entry to be dynamically allocated
+ * @dyn_allowed: allow entry to be dynamically allocated
  *
  * Allocate new irq entry in the free slot of the tracker. Since xarray
  * is used, always allocate new entry at the lowest possible index. Set
@@ -53,11 +53,12 @@ static void ice_free_irq_res(struct ice_pf *pf, u16 index)
  *
  * Returns allocated irq entry or NULL on failure.
  */
-static struct ice_irq_entry *ice_get_irq_res(struct ice_pf *pf, bool dyn_only)
+static struct ice_irq_entry *ice_get_irq_res(struct ice_pf *pf,
+					     bool dyn_allowed)
 {
-	struct xa_limit limit = { .max = pf->irq_tracker.num_entries,
+	struct xa_limit limit = { .max = pf->irq_tracker.num_entries - 1,
 				  .min = 0 };
-	unsigned int num_static = pf->irq_tracker.num_static;
+	unsigned int num_static = pf->irq_tracker.num_static - 1;
 	struct ice_irq_entry *entry;
 	unsigned int index;
 	int ret;
@@ -66,9 +67,9 @@ static struct ice_irq_entry *ice_get_irq_res(struct ice_pf *pf, bool dyn_only)
 	if (!entry)
 		return NULL;
 
-	/* skip preallocated entries if the caller says so */
-	if (dyn_only)
-		limit.min = num_static;
+	/* only already allocated if the caller says so */
+	if (!dyn_allowed)
+		limit.max = num_static;
 
 	ret = xa_alloc(&pf->irq_tracker.entries, &index, entry, limit,
 		       GFP_KERNEL);
@@ -78,7 +79,7 @@ static struct ice_irq_entry *ice_get_irq_res(struct ice_pf *pf, bool dyn_only)
 		entry = NULL;
 	} else {
 		entry->index = index;
-		entry->dynamic = index >= num_static;
+		entry->dynamic = index > num_static;
 	}
 
 	return entry;
@@ -272,7 +273,7 @@ int ice_init_interrupt_scheme(struct ice_pf *pf)
 /**
  * ice_alloc_irq - Allocate new interrupt vector
  * @pf: board private structure
- * @dyn_only: force dynamic allocation of the interrupt
+ * @dyn_allowed: allow dynamic allocation of the interrupt
  *
  * Allocate new interrupt vector for a given owner id.
  * return struct msi_map with interrupt details and track
@@ -285,20 +286,20 @@ int ice_init_interrupt_scheme(struct ice_pf *pf)
  * interrupt will be allocated with pci_msix_alloc_irq_at.
  *
  * Some callers may only support dynamically allocated interrupts.
- * This is indicated with dyn_only flag.
+ * This is indicated with dyn_allowed flag.
  *
  * On failure, return map with negative .index. The caller
  * is expected to check returned map index.
  *
  */
-struct msi_map ice_alloc_irq(struct ice_pf *pf, bool dyn_only)
+struct msi_map ice_alloc_irq(struct ice_pf *pf, bool dyn_allowed)
 {
 	int sriov_base_vector = pf->sriov_base_vector;
 	struct msi_map map = { .index = -ENOENT };
 	struct device *dev = ice_pf_to_dev(pf);
 	struct ice_irq_entry *entry;
 
-	entry = ice_get_irq_res(pf, dyn_only);
+	entry = ice_get_irq_res(pf, dyn_allowed);
 	if (!entry)
 		return map;
 
diff --git a/drivers/net/ethernet/intel/ice/ice_lag.c b/drivers/net/ethernet/intel/ice/ice_lag.c
index 1ccb572ce285..d132eb477551 100644
--- a/drivers/net/ethernet/intel/ice/ice_lag.c
+++ b/drivers/net/ethernet/intel/ice/ice_lag.c
@@ -1001,6 +1001,28 @@ static void ice_lag_link(struct ice_lag *lag)
 }
 
 /**
+ * ice_lag_config_eswitch - configure eswitch to work with LAG
+ * @lag: lag info struct
+ * @netdev: active network interface device struct
+ *
+ * Updates all port representors in eswitch to use @netdev for Tx.
+ *
+ * Configures the netdev to keep dst metadata (also used in representor Tx).
+ * This is required for an uplink without switchdev mode configured.
+ */
+static void ice_lag_config_eswitch(struct ice_lag *lag,
+				   struct net_device *netdev)
+{
+	struct ice_repr *repr;
+	unsigned long id;
+
+	xa_for_each(&lag->pf->eswitch.reprs, id, repr)
+		repr->dst->u.port_info.lower_dev = netdev;
+
+	netif_keep_dst(netdev);
+}
+
+/**
  * ice_lag_unlink - handle unlink event
  * @lag: LAG info struct
  */
@@ -1021,6 +1043,9 @@ static void ice_lag_unlink(struct ice_lag *lag)
 			ice_lag_move_vf_nodes(lag, act_port, pri_port);
 		lag->primary = false;
 		lag->active_port = ICE_LAG_INVALID_PORT;
+
+		/* Config primary's eswitch back to normal operation. */
+		ice_lag_config_eswitch(lag, lag->netdev);
 	} else {
 		struct ice_lag *primary_lag;
 
@@ -1296,12 +1321,18 @@ static void ice_lag_changeupper_event(struct ice_lag *lag, void *ptr)
 		 */
 		if (!primary_lag) {
 			lag->primary = true;
+			if (!ice_is_switchdev_running(lag->pf))
+				return;
+
 			/* Configure primary's SWID to be shared */
 			ice_lag_primary_swid(lag, true);
 			primary_lag = lag;
 		} else {
 			u16 swid;
 
+			if (!ice_is_switchdev_running(primary_lag->pf))
+				return;
+
 			swid = primary_lag->pf->hw.port_info->sw_id;
 			ice_lag_set_swid(swid, lag, true);
 			ice_lag_add_prune_list(primary_lag, lag->pf);
@@ -1419,6 +1450,7 @@ static void ice_lag_monitor_active(struct ice_lag *lag, void *ptr)
 				ice_lag_move_vf_nodes(lag, prim_port,
 						      event_port);
 			lag->active_port = event_port;
+			ice_lag_config_eswitch(lag, event_netdev);
 			return;
 		}
 
@@ -1428,6 +1460,7 @@ static void ice_lag_monitor_active(struct ice_lag *lag, void *ptr)
 		/* new active port */
 		ice_lag_move_vf_nodes(lag, lag->active_port, event_port);
 		lag->active_port = event_port;
+		ice_lag_config_eswitch(lag, event_netdev);
 	} else {
 		/* port not set as currently active (e.g. new active port
 		 * has already claimed the nodes and filters
@@ -2193,7 +2226,8 @@ bool ice_lag_is_switchdev_running(struct ice_pf *pf)
 	struct ice_lag *lag = pf->lag;
 	struct net_device *tmp_nd;
 
-	if (!ice_is_feature_supported(pf, ICE_F_SRIOV_LAG) || !lag)
+	if (!ice_is_feature_supported(pf, ICE_F_SRIOV_LAG) ||
+	    !lag || !lag->upper_netdev)
 		return false;
 
 	rcu_read_lock();
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 06e712cdc3d9..8961eebe67aa 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -567,6 +567,8 @@ ice_vsi_alloc_def(struct ice_vsi *vsi, struct ice_channel *ch)
 			return -ENOMEM;
 	}
 
+	vsi->irq_dyn_alloc = pci_msix_can_alloc_dyn(vsi->back->pdev);
+
 	switch (vsi->type) {
 	case ICE_VSI_PF:
 	case ICE_VSI_SF:
@@ -3880,6 +3882,9 @@ void ice_init_feature_support(struct ice_pf *pf)
 	default:
 		break;
 	}
+
+	if (pf->hw.mac_type == ICE_MAC_E830)
+		ice_set_feature_support(pf, ICE_F_MBX_LIMIT);
 }
 
 /**
@@ -3926,24 +3931,6 @@ void ice_vsi_ctx_clear_antispoof(struct ice_vsi_ctx *ctx)
 }
 
 /**
- * ice_vsi_ctx_set_allow_override - allow destination override on VSI
- * @ctx: pointer to VSI ctx structure
- */
-void ice_vsi_ctx_set_allow_override(struct ice_vsi_ctx *ctx)
-{
-	ctx->info.sec_flags |= ICE_AQ_VSI_SEC_FLAG_ALLOW_DEST_OVRD;
-}
-
-/**
- * ice_vsi_ctx_clear_allow_override - turn off destination override on VSI
- * @ctx: pointer to VSI ctx structure
- */
-void ice_vsi_ctx_clear_allow_override(struct ice_vsi_ctx *ctx)
-{
-	ctx->info.sec_flags &= ~ICE_AQ_VSI_SEC_FLAG_ALLOW_DEST_OVRD;
-}
-
-/**
  * ice_vsi_update_local_lb - update sw block in VSI with local loopback bit
  * @vsi: pointer to VSI structure
  * @set: set or unset the bit
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h
index 1a6cfc8693ce..2b27998fd1be 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_lib.h
@@ -106,10 +106,6 @@ ice_vsi_update_security(struct ice_vsi *vsi, void (*fill)(struct ice_vsi_ctx *))
 void ice_vsi_ctx_set_antispoof(struct ice_vsi_ctx *ctx);
 
 void ice_vsi_ctx_clear_antispoof(struct ice_vsi_ctx *ctx);
-
-void ice_vsi_ctx_set_allow_override(struct ice_vsi_ctx *ctx);
-
-void ice_vsi_ctx_clear_allow_override(struct ice_vsi_ctx *ctx);
 int ice_vsi_update_local_lb(struct ice_vsi *vsi, bool set);
 int ice_vsi_add_vlan_zero(struct ice_vsi *vsi);
 int ice_vsi_del_vlan_zero(struct ice_vsi *vsi);
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 45eefe22fb5b..d1abd21cfc64 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -1546,12 +1546,20 @@ static int __ice_clean_ctrlq(struct ice_pf *pf, enum ice_ctl_q q_type)
 			ice_vf_lan_overflow_event(pf, &event);
 			break;
 		case ice_mbx_opc_send_msg_to_pf:
-			data.num_msg_proc = i;
-			data.num_pending_arq = pending;
-			data.max_num_msgs_mbx = hw->mailboxq.num_rq_entries;
-			data.async_watermark_val = ICE_MBX_OVERFLOW_WATERMARK;
+			if (ice_is_feature_supported(pf, ICE_F_MBX_LIMIT)) {
+				ice_vc_process_vf_msg(pf, &event, NULL);
+				ice_mbx_vf_dec_trig_e830(hw, &event);
+			} else {
+				u16 val = hw->mailboxq.num_rq_entries;
+
+				data.max_num_msgs_mbx = val;
+				val = ICE_MBX_OVERFLOW_WATERMARK;
+				data.async_watermark_val = val;
+				data.num_msg_proc = i;
+				data.num_pending_arq = pending;
 
-			ice_vc_process_vf_msg(pf, &event, &data);
+				ice_vc_process_vf_msg(pf, &event, &data);
+			}
 			break;
 		case ice_aqc_opc_fw_logs_event:
 			ice_get_fwlog_data(pf, &event);
@@ -2754,6 +2762,27 @@ void ice_map_xdp_rings(struct ice_vsi *vsi)
 }
 
 /**
+ * ice_unmap_xdp_rings - Unmap XDP rings from interrupt vectors
+ * @vsi: the VSI with XDP rings being unmapped
+ */
+static void ice_unmap_xdp_rings(struct ice_vsi *vsi)
+{
+	int v_idx;
+
+	ice_for_each_q_vector(vsi, v_idx) {
+		struct ice_q_vector *q_vector = vsi->q_vectors[v_idx];
+		struct ice_tx_ring *ring;
+
+		ice_for_each_tx_ring(ring, q_vector->tx)
+			if (!ring->tx_buf || !ice_ring_is_xdp(ring))
+				break;
+
+		/* restore the value of last node prior to XDP setup */
+		q_vector->tx.tx_ring = ring;
+	}
+}
+
+/**
  * ice_prepare_xdp_rings - Allocate, configure and setup Tx rings for XDP
  * @vsi: VSI to bring up Tx rings used by XDP
  * @prog: bpf program that will be assigned to VSI
@@ -2816,7 +2845,7 @@ int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog,
 	if (status) {
 		dev_err(dev, "Failed VSI LAN queue config for XDP, error: %d\n",
 			status);
-		goto clear_xdp_rings;
+		goto unmap_xdp_rings;
 	}
 
 	/* assign the prog only when it's not already present on VSI;
@@ -2832,6 +2861,8 @@ int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog,
 		ice_vsi_assign_bpf_prog(vsi, prog);
 
 	return 0;
+unmap_xdp_rings:
+	ice_unmap_xdp_rings(vsi);
 clear_xdp_rings:
 	ice_for_each_xdp_txq(vsi, i)
 		if (vsi->xdp_rings[i]) {
@@ -2848,6 +2879,8 @@ err_map_xdp:
 	mutex_unlock(&pf->avail_q_mutex);
 
 	devm_kfree(dev, vsi->xdp_rings);
+	vsi->xdp_rings = NULL;
+
 	return -ENOMEM;
 }
 
@@ -2863,7 +2896,7 @@ int ice_destroy_xdp_rings(struct ice_vsi *vsi, enum ice_xdp_cfg cfg_type)
 {
 	u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 };
 	struct ice_pf *pf = vsi->back;
-	int i, v_idx;
+	int i;
 
 	/* q_vectors are freed in reset path so there's no point in detaching
 	 * rings
@@ -2871,17 +2904,7 @@ int ice_destroy_xdp_rings(struct ice_vsi *vsi, enum ice_xdp_cfg cfg_type)
 	if (cfg_type == ICE_XDP_CFG_PART)
 		goto free_qmap;
 
-	ice_for_each_q_vector(vsi, v_idx) {
-		struct ice_q_vector *q_vector = vsi->q_vectors[v_idx];
-		struct ice_tx_ring *ring;
-
-		ice_for_each_tx_ring(ring, q_vector->tx)
-			if (!ring->tx_buf || !ice_ring_is_xdp(ring))
-				break;
-
-		/* restore the value of last node prior to XDP setup */
-		q_vector->tx.tx_ring = ring;
-	}
+	ice_unmap_xdp_rings(vsi);
 
 free_qmap:
 	mutex_lock(&pf->avail_q_mutex);
@@ -3026,11 +3049,14 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog,
 		xdp_ring_err = ice_vsi_determine_xdp_res(vsi);
 		if (xdp_ring_err) {
 			NL_SET_ERR_MSG_MOD(extack, "Not enough Tx resources for XDP");
+			goto resume_if;
 		} else {
 			xdp_ring_err = ice_prepare_xdp_rings(vsi, prog,
 							     ICE_XDP_CFG_FULL);
-			if (xdp_ring_err)
+			if (xdp_ring_err) {
 				NL_SET_ERR_MSG_MOD(extack, "Setting up XDP Tx resources failed");
+				goto resume_if;
+			}
 		}
 		xdp_features_set_redirect_target(vsi->netdev, true);
 		/* reallocate Rx queues that are used for zero-copy */
@@ -3048,6 +3074,7 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog,
 			NL_SET_ERR_MSG_MOD(extack, "Freeing XDP Rx resources failed");
 	}
 
+resume_if:
 	if (if_running)
 		ret = ice_up(vsi);
 
@@ -4082,7 +4109,11 @@ static int ice_init_pf(struct ice_pf *pf)
 
 	mutex_init(&pf->vfs.table_lock);
 	hash_init(pf->vfs.table);
-	ice_mbx_init_snapshot(&pf->hw);
+	if (ice_is_feature_supported(pf, ICE_F_MBX_LIMIT))
+		wr32(&pf->hw, E830_MBX_PF_IN_FLIGHT_VF_MSGS_THRESH,
+		     ICE_MBX_OVERFLOW_WATERMARK);
+	else
+		ice_mbx_init_snapshot(&pf->hw);
 
 	xa_init(&pf->dyn_ports);
 	xa_init(&pf->sf_nums);
@@ -5163,11 +5194,12 @@ int ice_load(struct ice_pf *pf)
 
 	ice_napi_add(vsi);
 
+	ice_init_features(pf);
+
 	err = ice_init_rdma(pf);
 	if (err)
 		goto err_init_rdma;
 
-	ice_init_features(pf);
 	ice_service_task_restart(pf);
 
 	clear_bit(ICE_DOWN, pf->state);
@@ -5175,6 +5207,7 @@ int ice_load(struct ice_pf *pf)
 	return 0;
 
 err_init_rdma:
+	ice_deinit_features(pf);
 	ice_tc_indir_block_unregister(vsi);
 err_tc_indir_block_register:
 	ice_unregister_netdev(vsi);
@@ -5198,8 +5231,8 @@ void ice_unload(struct ice_pf *pf)
 
 	devl_assert_locked(priv_to_devlink(pf));
 
-	ice_deinit_features(pf);
 	ice_deinit_rdma(pf);
+	ice_deinit_features(pf);
 	ice_tc_indir_block_unregister(vsi);
 	ice_unregister_netdev(vsi);
 	ice_devlink_destroy_pf_port(pf);
diff --git a/drivers/net/ethernet/intel/ice/ice_parser.h b/drivers/net/ethernet/intel/ice/ice_parser.h
index 6509d807627c..4f56d53d56b9 100644
--- a/drivers/net/ethernet/intel/ice/ice_parser.h
+++ b/drivers/net/ethernet/intel/ice/ice_parser.h
@@ -257,7 +257,6 @@ ice_pg_nm_cam_match(struct ice_pg_nm_cam_item *table, int size,
 /*** ICE_SID_RXPARSER_BOOST_TCAM and ICE_SID_LBL_RXPARSER_TMEM sections ***/
 #define ICE_BST_TCAM_TABLE_SIZE		256
 #define ICE_BST_TCAM_KEY_SIZE		20
-#define ICE_BST_KEY_TCAM_SIZE		19
 
 /* Boost TCAM item */
 struct ice_bst_tcam_item {
@@ -401,7 +400,6 @@ u16 ice_xlt_kb_flag_get(struct ice_xlt_kb *kb, u64 pkt_flag);
 #define ICE_PARSER_GPR_NUM	128
 #define ICE_PARSER_FLG_NUM	64
 #define ICE_PARSER_ERR_NUM	16
-#define ICE_BST_KEY_SIZE	10
 #define ICE_MARKER_ID_SIZE	9
 #define ICE_MARKER_MAX_SIZE	\
 		(ICE_MARKER_ID_SIZE * BITS_PER_BYTE - 1)
@@ -431,13 +429,13 @@ struct ice_parser_rt {
 	u8 pkt_buf[ICE_PARSER_MAX_PKT_LEN + ICE_PARSER_PKT_REV];
 	u16 pkt_len;
 	u16 po;
-	u8 bst_key[ICE_BST_KEY_SIZE];
+	u8 bst_key[ICE_BST_TCAM_KEY_SIZE];
 	struct ice_pg_cam_key pg_key;
+	u8 pg_prio;
 	struct ice_alu *alu0;
 	struct ice_alu *alu1;
 	struct ice_alu *alu2;
 	struct ice_pg_cam_action *action;
-	u8 pg_prio;
 	struct ice_gpr_pu pu;
 	u8 markers[ICE_MARKER_ID_SIZE];
 	bool protocols[ICE_PO_PAIR_SIZE];
diff --git a/drivers/net/ethernet/intel/ice/ice_parser_rt.c b/drivers/net/ethernet/intel/ice/ice_parser_rt.c
index dedf5e854e4b..3995d662e050 100644
--- a/drivers/net/ethernet/intel/ice/ice_parser_rt.c
+++ b/drivers/net/ethernet/intel/ice/ice_parser_rt.c
@@ -125,22 +125,20 @@ static void ice_bst_key_init(struct ice_parser_rt *rt,
 	else
 		key[idd] = imem->b_kb.prio;
 
-	idd = ICE_BST_KEY_TCAM_SIZE - 1;
+	idd = ICE_BST_TCAM_KEY_SIZE - 2;
 	for (i = idd; i >= 0; i--) {
 		int j;
 
 		j = ho + idd - i;
 		if (j < ICE_PARSER_MAX_PKT_LEN)
-			key[i] = rt->pkt_buf[ho + idd - i];
+			key[i] = rt->pkt_buf[j];
 		else
 			key[i] = 0;
 	}
 
-	ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Generated Boost TCAM Key:\n");
-	ice_debug(rt->psr->hw, ICE_DBG_PARSER, "%02X %02X %02X %02X %02X %02X %02X %02X %02X %02X\n",
-		  key[0], key[1], key[2], key[3], key[4],
-		  key[5], key[6], key[7], key[8], key[9]);
-	ice_debug(rt->psr->hw, ICE_DBG_PARSER, "\n");
+	ice_debug_array_w_prefix(rt->psr->hw, ICE_DBG_PARSER,
+				 KBUILD_MODNAME ": Generated Boost TCAM Key",
+				 key, ICE_BST_TCAM_KEY_SIZE);
 }
 
 static u16 ice_bit_rev_u16(u16 v, int len)
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c
index 7c6f81beaee4..369c968a0117 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp.c
@@ -2226,6 +2226,7 @@ ice_ptp_get_syncdevicetime(ktime_t *device,
 			hh_ts = ((u64)hh_ts_hi << 32) | hh_ts_lo;
 			system->cycles = hh_ts;
 			system->cs_id = CSID_X86_ART;
+			system->use_nsecs = true;
 			/* Read Device source clock time */
 			hh_ts_lo = rd32(hw, GLTSYN_HHTIME_L(tmr_idx));
 			hh_ts_hi = rd32(hw, GLTSYN_HHTIME_H(tmr_idx));
diff --git a/drivers/net/ethernet/intel/ice/ice_sched.c b/drivers/net/ethernet/intel/ice/ice_sched.c
index 6ca13c5dcb14..d9d09296d1d4 100644
--- a/drivers/net/ethernet/intel/ice/ice_sched.c
+++ b/drivers/net/ethernet/intel/ice/ice_sched.c
@@ -85,6 +85,27 @@ ice_sched_find_node_by_teid(struct ice_sched_node *start_node, u32 teid)
 }
 
 /**
+ * ice_sched_find_next_vsi_node - find the next node for a given VSI
+ * @vsi_node: VSI support node to start search with
+ *
+ * Return: Next VSI support node, or NULL.
+ *
+ * The function returns a pointer to the next node from the VSI layer
+ * assigned to the given VSI, or NULL if there is no such a node.
+ */
+static struct ice_sched_node *
+ice_sched_find_next_vsi_node(struct ice_sched_node *vsi_node)
+{
+	unsigned int vsi_handle = vsi_node->vsi_handle;
+
+	while ((vsi_node = vsi_node->sibling) != NULL)
+		if (vsi_node->vsi_handle == vsi_handle)
+			break;
+
+	return vsi_node;
+}
+
+/**
  * ice_aqc_send_sched_elem_cmd - send scheduling elements cmd
  * @hw: pointer to the HW struct
  * @cmd_opc: cmd opcode
@@ -1084,8 +1105,10 @@ ice_sched_add_nodes_to_layer(struct ice_port_info *pi,
 		if (parent->num_children < max_child_nodes) {
 			new_num_nodes = max_child_nodes - parent->num_children;
 		} else {
-			/* This parent is full, try the next sibling */
-			parent = parent->sibling;
+			/* This parent is full,
+			 * try the next available sibling.
+			 */
+			parent = ice_sched_find_next_vsi_node(parent);
 			/* Don't modify the first node TEID memory if the
 			 * first node was added already in the above call.
 			 * Instead send some temp memory for all other
@@ -1528,12 +1551,23 @@ ice_sched_get_free_qparent(struct ice_port_info *pi, u16 vsi_handle, u8 tc,
 	/* get the first queue group node from VSI sub-tree */
 	qgrp_node = ice_sched_get_first_node(pi, vsi_node, qgrp_layer);
 	while (qgrp_node) {
+		struct ice_sched_node *next_vsi_node;
+
 		/* make sure the qgroup node is part of the VSI subtree */
 		if (ice_sched_find_node_in_subtree(pi->hw, vsi_node, qgrp_node))
 			if (qgrp_node->num_children < max_children &&
 			    qgrp_node->owner == owner)
 				break;
 		qgrp_node = qgrp_node->sibling;
+		if (qgrp_node)
+			continue;
+
+		next_vsi_node = ice_sched_find_next_vsi_node(vsi_node);
+		if (!next_vsi_node)
+			break;
+
+		vsi_node = next_vsi_node;
+		qgrp_node = ice_sched_get_first_node(pi, vsi_node, qgrp_layer);
 	}
 
 	/* Select the best queue group */
@@ -1604,16 +1638,16 @@ ice_sched_get_agg_node(struct ice_port_info *pi, struct ice_sched_node *tc_node,
 /**
  * ice_sched_calc_vsi_child_nodes - calculate number of VSI child nodes
  * @hw: pointer to the HW struct
- * @num_qs: number of queues
+ * @num_new_qs: number of new queues that will be added to the tree
  * @num_nodes: num nodes array
  *
  * This function calculates the number of VSI child nodes based on the
  * number of queues.
  */
 static void
-ice_sched_calc_vsi_child_nodes(struct ice_hw *hw, u16 num_qs, u16 *num_nodes)
+ice_sched_calc_vsi_child_nodes(struct ice_hw *hw, u16 num_new_qs, u16 *num_nodes)
 {
-	u16 num = num_qs;
+	u16 num = num_new_qs;
 	u8 i, qgl, vsil;
 
 	qgl = ice_sched_get_qgrp_layer(hw);
@@ -1779,7 +1813,11 @@ ice_sched_add_vsi_support_nodes(struct ice_port_info *pi, u16 vsi_handle,
 		if (!parent)
 			return -EIO;
 
-		if (i == vsil)
+		/* Do not modify the VSI handle for already existing VSI nodes,
+		 * (if no new VSI node was added to the tree).
+		 * Assign the VSI handle only to newly added VSI nodes.
+		 */
+		if (i == vsil && num_added)
 			parent->vsi_handle = vsi_handle;
 	}
 
@@ -1813,6 +1851,41 @@ ice_sched_add_vsi_to_topo(struct ice_port_info *pi, u16 vsi_handle, u8 tc)
 }
 
 /**
+ * ice_sched_recalc_vsi_support_nodes - recalculate VSI support nodes count
+ * @hw: pointer to the HW struct
+ * @vsi_node: pointer to the leftmost VSI node that needs to be extended
+ * @new_numqs: new number of queues that has to be handled by the VSI
+ * @new_num_nodes: pointer to nodes count table to modify the VSI layer entry
+ *
+ * This function recalculates the number of supported nodes that need to
+ * be added after adding more Tx queues for a given VSI.
+ * The number of new VSI support nodes that shall be added will be saved
+ * to the @new_num_nodes table for the VSI layer.
+ */
+static void
+ice_sched_recalc_vsi_support_nodes(struct ice_hw *hw,
+				   struct ice_sched_node *vsi_node,
+				   unsigned int new_numqs, u16 *new_num_nodes)
+{
+	u32 vsi_nodes_cnt = 1;
+	u32 max_queue_cnt = 1;
+	u32 qgl, vsil;
+
+	qgl = ice_sched_get_qgrp_layer(hw);
+	vsil = ice_sched_get_vsi_layer(hw);
+
+	for (u32 i = vsil; i <= qgl; i++)
+		max_queue_cnt *= hw->max_children[i];
+
+	while ((vsi_node = ice_sched_find_next_vsi_node(vsi_node)) != NULL)
+		vsi_nodes_cnt++;
+
+	if (new_numqs > (max_queue_cnt * vsi_nodes_cnt))
+		new_num_nodes[vsil] = DIV_ROUND_UP(new_numqs, max_queue_cnt) -
+				      vsi_nodes_cnt;
+}
+
+/**
  * ice_sched_update_vsi_child_nodes - update VSI child nodes
  * @pi: port information structure
  * @vsi_handle: software VSI handle
@@ -1863,15 +1936,25 @@ ice_sched_update_vsi_child_nodes(struct ice_port_info *pi, u16 vsi_handle,
 			return status;
 	}
 
-	if (new_numqs)
-		ice_sched_calc_vsi_child_nodes(hw, new_numqs, new_num_nodes);
-	/* Keep the max number of queue configuration all the time. Update the
-	 * tree only if number of queues > previous number of queues. This may
+	ice_sched_recalc_vsi_support_nodes(hw, vsi_node,
+					   new_numqs, new_num_nodes);
+	ice_sched_calc_vsi_child_nodes(hw, new_numqs - prev_numqs,
+				       new_num_nodes);
+
+	/* Never decrease the number of queues in the tree. Update the tree
+	 * only if number of queues > previous number of queues. This may
 	 * leave some extra nodes in the tree if number of queues < previous
 	 * number but that wouldn't harm anything. Removing those extra nodes
 	 * may complicate the code if those nodes are part of SRL or
 	 * individually rate limited.
+	 * Also, add the required VSI support nodes if the existing ones cannot
+	 * handle the requested new number of queues.
 	 */
+	status = ice_sched_add_vsi_support_nodes(pi, vsi_handle, tc_node,
+						 new_num_nodes);
+	if (status)
+		return status;
+
 	status = ice_sched_add_vsi_child_nodes(pi, vsi_handle, tc_node,
 					       new_num_nodes, owner);
 	if (status)
@@ -2013,6 +2096,58 @@ static bool ice_sched_is_leaf_node_present(struct ice_sched_node *node)
 }
 
 /**
+ * ice_sched_rm_vsi_subtree - remove all nodes assigned to a given VSI
+ * @pi: port information structure
+ * @vsi_node: pointer to the leftmost node of the VSI to be removed
+ * @owner: LAN or RDMA
+ * @tc: TC number
+ *
+ * Return: Zero in case of success, or -EBUSY if the VSI has leaf nodes in TC.
+ *
+ * This function removes all the VSI support nodes associated with a given VSI
+ * and its LAN or RDMA children nodes from the scheduler tree.
+ */
+static int
+ice_sched_rm_vsi_subtree(struct ice_port_info *pi,
+			 struct ice_sched_node *vsi_node, u8 owner, u8 tc)
+{
+	u16 vsi_handle = vsi_node->vsi_handle;
+	bool all_vsi_nodes_removed = true;
+	int j = 0;
+
+	while (vsi_node) {
+		struct ice_sched_node *next_vsi_node;
+
+		if (ice_sched_is_leaf_node_present(vsi_node)) {
+			ice_debug(pi->hw, ICE_DBG_SCHED, "VSI has leaf nodes in TC %d\n", tc);
+			return -EBUSY;
+		}
+		while (j < vsi_node->num_children) {
+			if (vsi_node->children[j]->owner == owner)
+				ice_free_sched_node(pi, vsi_node->children[j]);
+			else
+				j++;
+		}
+
+		next_vsi_node = ice_sched_find_next_vsi_node(vsi_node);
+
+		/* remove the VSI if it has no children */
+		if (!vsi_node->num_children)
+			ice_free_sched_node(pi, vsi_node);
+		else
+			all_vsi_nodes_removed = false;
+
+		vsi_node = next_vsi_node;
+	}
+
+	/* clean up aggregator related VSI info if any */
+	if (all_vsi_nodes_removed)
+		ice_sched_rm_agg_vsi_info(pi, vsi_handle);
+
+	return 0;
+}
+
+/**
  * ice_sched_rm_vsi_cfg - remove the VSI and its children nodes
  * @pi: port information structure
  * @vsi_handle: software VSI handle
@@ -2038,7 +2173,6 @@ ice_sched_rm_vsi_cfg(struct ice_port_info *pi, u16 vsi_handle, u8 owner)
 
 	ice_for_each_traffic_class(i) {
 		struct ice_sched_node *vsi_node, *tc_node;
-		u8 j = 0;
 
 		tc_node = ice_sched_get_tc_node(pi, i);
 		if (!tc_node)
@@ -2048,31 +2182,12 @@ ice_sched_rm_vsi_cfg(struct ice_port_info *pi, u16 vsi_handle, u8 owner)
 		if (!vsi_node)
 			continue;
 
-		if (ice_sched_is_leaf_node_present(vsi_node)) {
-			ice_debug(pi->hw, ICE_DBG_SCHED, "VSI has leaf nodes in TC %d\n", i);
-			status = -EBUSY;
+		status = ice_sched_rm_vsi_subtree(pi, vsi_node, owner, i);
+		if (status)
 			goto exit_sched_rm_vsi_cfg;
-		}
-		while (j < vsi_node->num_children) {
-			if (vsi_node->children[j]->owner == owner) {
-				ice_free_sched_node(pi, vsi_node->children[j]);
 
-				/* reset the counter again since the num
-				 * children will be updated after node removal
-				 */
-				j = 0;
-			} else {
-				j++;
-			}
-		}
-		/* remove the VSI if it has no children */
-		if (!vsi_node->num_children) {
-			ice_free_sched_node(pi, vsi_node);
-			vsi_ctx->sched.vsi_node[i] = NULL;
+		vsi_ctx->sched.vsi_node[i] = NULL;
 
-			/* clean up aggregator related VSI info if any */
-			ice_sched_rm_agg_vsi_info(pi, vsi_handle);
-		}
 		if (owner == ICE_SCHED_NODE_OWNER_LAN)
 			vsi_ctx->sched.max_lanq[i] = 0;
 		else
diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c
index 91cb393f616f..8aabf7749aa5 100644
--- a/drivers/net/ethernet/intel/ice/ice_sriov.c
+++ b/drivers/net/ethernet/intel/ice/ice_sriov.c
@@ -36,6 +36,7 @@ static void ice_free_vf_entries(struct ice_pf *pf)
 
 	hash_for_each_safe(vfs->table, bkt, tmp, vf, entry) {
 		hash_del_rcu(&vf->entry);
+		ice_deinitialize_vf_entry(vf);
 		ice_put_vf(vf);
 	}
 }
@@ -193,9 +194,6 @@ void ice_free_vfs(struct ice_pf *pf)
 			wr32(hw, GLGEN_VFLRSTAT(reg_idx), BIT(bit_idx));
 		}
 
-		/* clear malicious info since the VF is getting released */
-		list_del(&vf->mbx_info.list_entry);
-
 		mutex_unlock(&vf->cfg_lock);
 	}
 
diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c
index 0e740342e294..c5430363e708 100644
--- a/drivers/net/ethernet/intel/ice/ice_switch.c
+++ b/drivers/net/ethernet/intel/ice/ice_switch.c
@@ -3146,7 +3146,7 @@ ice_add_update_vsi_list(struct ice_hw *hw,
 		u16 vsi_handle_arr[2];
 
 		/* A rule already exists with the new VSI being added */
-		if (cur_fltr->fwd_id.hw_vsi_id == new_fltr->fwd_id.hw_vsi_id)
+		if (cur_fltr->vsi_handle == new_fltr->vsi_handle)
 			return -EEXIST;
 
 		vsi_handle_arr[0] = cur_fltr->vsi_handle;
@@ -5977,7 +5977,7 @@ ice_adv_add_update_vsi_list(struct ice_hw *hw,
 
 		/* A rule already exists with the new VSI being added */
 		if (test_bit(vsi_handle, m_entry->vsi_list_info->vsi_map))
-			return 0;
+			return -EEXIST;
 
 		/* Update the previously created VSI list set with
 		 * the new VSI ID passed in
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 8208055d6e7f..f522dd42093a 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -527,15 +527,14 @@ err:
  * @xdp: xdp_buff used as input to the XDP program
  * @xdp_prog: XDP program to run
  * @xdp_ring: ring to be used for XDP_TX action
- * @rx_buf: Rx buffer to store the XDP action
  * @eop_desc: Last descriptor in packet to read metadata from
  *
  * Returns any of ICE_XDP_{PASS, CONSUMED, TX, REDIR}
  */
-static void
+static u32
 ice_run_xdp(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
 	    struct bpf_prog *xdp_prog, struct ice_tx_ring *xdp_ring,
-	    struct ice_rx_buf *rx_buf, union ice_32b_rx_flex_desc *eop_desc)
+	    union ice_32b_rx_flex_desc *eop_desc)
 {
 	unsigned int ret = ICE_XDP_PASS;
 	u32 act;
@@ -574,7 +573,7 @@ out_failure:
 		ret = ICE_XDP_CONSUMED;
 	}
 exit:
-	ice_set_rx_bufs_act(xdp, rx_ring, ret);
+	return ret;
 }
 
 /**
@@ -860,10 +859,8 @@ ice_add_xdp_frag(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
 		xdp_buff_set_frags_flag(xdp);
 	}
 
-	if (unlikely(sinfo->nr_frags == MAX_SKB_FRAGS)) {
-		ice_set_rx_bufs_act(xdp, rx_ring, ICE_XDP_CONSUMED);
+	if (unlikely(sinfo->nr_frags == MAX_SKB_FRAGS))
 		return -ENOMEM;
-	}
 
 	__skb_fill_page_desc_noacc(sinfo, sinfo->nr_frags++, rx_buf->page,
 				   rx_buf->page_offset, size);
@@ -924,7 +921,6 @@ ice_get_rx_buf(struct ice_rx_ring *rx_ring, const unsigned int size,
 	struct ice_rx_buf *rx_buf;
 
 	rx_buf = &rx_ring->rx_buf[ntc];
-	rx_buf->pgcnt = page_count(rx_buf->page);
 	prefetchw(rx_buf->page);
 
 	if (!size)
@@ -941,6 +937,31 @@ ice_get_rx_buf(struct ice_rx_ring *rx_ring, const unsigned int size,
 }
 
 /**
+ * ice_get_pgcnts - grab page_count() for gathered fragments
+ * @rx_ring: Rx descriptor ring to store the page counts on
+ *
+ * This function is intended to be called right before running XDP
+ * program so that the page recycling mechanism will be able to take
+ * a correct decision regarding underlying pages; this is done in such
+ * way as XDP program can change the refcount of page
+ */
+static void ice_get_pgcnts(struct ice_rx_ring *rx_ring)
+{
+	u32 nr_frags = rx_ring->nr_frags + 1;
+	u32 idx = rx_ring->first_desc;
+	struct ice_rx_buf *rx_buf;
+	u32 cnt = rx_ring->count;
+
+	for (int i = 0; i < nr_frags; i++) {
+		rx_buf = &rx_ring->rx_buf[idx];
+		rx_buf->pgcnt = page_count(rx_buf->page);
+
+		if (++idx == cnt)
+			idx = 0;
+	}
+}
+
+/**
  * ice_build_skb - Build skb around an existing buffer
  * @rx_ring: Rx descriptor ring to transact packets on
  * @xdp: xdp_buff pointing to the data
@@ -1051,12 +1072,12 @@ ice_construct_skb(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp)
 				rx_buf->page_offset + headlen, size,
 				xdp->frame_sz);
 	} else {
-		/* buffer is unused, change the act that should be taken later
-		 * on; data was copied onto skb's linear part so there's no
+		/* buffer is unused, restore biased page count in Rx buffer;
+		 * data was copied onto skb's linear part so there's no
 		 * need for adjusting page offset and we can reuse this buffer
 		 * as-is
 		 */
-		rx_buf->act = ICE_SKB_CONSUMED;
+		rx_buf->pagecnt_bias++;
 	}
 
 	if (unlikely(xdp_buff_has_frags(xdp))) {
@@ -1104,6 +1125,65 @@ ice_put_rx_buf(struct ice_rx_ring *rx_ring, struct ice_rx_buf *rx_buf)
 }
 
 /**
+ * ice_put_rx_mbuf - ice_put_rx_buf() caller, for all frame frags
+ * @rx_ring: Rx ring with all the auxiliary data
+ * @xdp: XDP buffer carrying linear + frags part
+ * @xdp_xmit: XDP_TX/XDP_REDIRECT verdict storage
+ * @ntc: a current next_to_clean value to be stored at rx_ring
+ * @verdict: return code from XDP program execution
+ *
+ * Walk through gathered fragments and satisfy internal page
+ * recycle mechanism; we take here an action related to verdict
+ * returned by XDP program;
+ */
+static void ice_put_rx_mbuf(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
+			    u32 *xdp_xmit, u32 ntc, u32 verdict)
+{
+	u32 nr_frags = rx_ring->nr_frags + 1;
+	u32 idx = rx_ring->first_desc;
+	u32 cnt = rx_ring->count;
+	u32 post_xdp_frags = 1;
+	struct ice_rx_buf *buf;
+	int i;
+
+	if (unlikely(xdp_buff_has_frags(xdp)))
+		post_xdp_frags += xdp_get_shared_info_from_buff(xdp)->nr_frags;
+
+	for (i = 0; i < post_xdp_frags; i++) {
+		buf = &rx_ring->rx_buf[idx];
+
+		if (verdict & (ICE_XDP_TX | ICE_XDP_REDIR)) {
+			ice_rx_buf_adjust_pg_offset(buf, xdp->frame_sz);
+			*xdp_xmit |= verdict;
+		} else if (verdict & ICE_XDP_CONSUMED) {
+			buf->pagecnt_bias++;
+		} else if (verdict == ICE_XDP_PASS) {
+			ice_rx_buf_adjust_pg_offset(buf, xdp->frame_sz);
+		}
+
+		ice_put_rx_buf(rx_ring, buf);
+
+		if (++idx == cnt)
+			idx = 0;
+	}
+	/* handle buffers that represented frags released by XDP prog;
+	 * for these we keep pagecnt_bias as-is; refcount from struct page
+	 * has been decremented within XDP prog and we do not have to increase
+	 * the biased refcnt
+	 */
+	for (; i < nr_frags; i++) {
+		buf = &rx_ring->rx_buf[idx];
+		ice_put_rx_buf(rx_ring, buf);
+		if (++idx == cnt)
+			idx = 0;
+	}
+
+	xdp->data = NULL;
+	rx_ring->first_desc = ntc;
+	rx_ring->nr_frags = 0;
+}
+
+/**
  * ice_clean_rx_irq - Clean completed descriptors from Rx ring - bounce buf
  * @rx_ring: Rx descriptor ring to transact packets on
  * @budget: Total limit on number of packets to process
@@ -1120,15 +1200,13 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
 	unsigned int total_rx_bytes = 0, total_rx_pkts = 0;
 	unsigned int offset = rx_ring->rx_offset;
 	struct xdp_buff *xdp = &rx_ring->xdp;
-	u32 cached_ntc = rx_ring->first_desc;
 	struct ice_tx_ring *xdp_ring = NULL;
 	struct bpf_prog *xdp_prog = NULL;
 	u32 ntc = rx_ring->next_to_clean;
+	u32 cached_ntu, xdp_verdict;
 	u32 cnt = rx_ring->count;
 	u32 xdp_xmit = 0;
-	u32 cached_ntu;
 	bool failure;
-	u32 first;
 
 	xdp_prog = READ_ONCE(rx_ring->xdp_prog);
 	if (xdp_prog) {
@@ -1190,6 +1268,7 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
 			xdp_prepare_buff(xdp, hard_start, offset, size, !!offset);
 			xdp_buff_clear_frags_flag(xdp);
 		} else if (ice_add_xdp_frag(rx_ring, xdp, rx_buf, size)) {
+			ice_put_rx_mbuf(rx_ring, xdp, NULL, ntc, ICE_XDP_CONSUMED);
 			break;
 		}
 		if (++ntc == cnt)
@@ -1199,15 +1278,15 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
 		if (ice_is_non_eop(rx_ring, rx_desc))
 			continue;
 
-		ice_run_xdp(rx_ring, xdp, xdp_prog, xdp_ring, rx_buf, rx_desc);
-		if (rx_buf->act == ICE_XDP_PASS)
+		ice_get_pgcnts(rx_ring);
+		xdp_verdict = ice_run_xdp(rx_ring, xdp, xdp_prog, xdp_ring, rx_desc);
+		if (xdp_verdict == ICE_XDP_PASS)
 			goto construct_skb;
 		total_rx_bytes += xdp_get_buff_len(xdp);
 		total_rx_pkts++;
 
-		xdp->data = NULL;
-		rx_ring->first_desc = ntc;
-		rx_ring->nr_frags = 0;
+		ice_put_rx_mbuf(rx_ring, xdp, &xdp_xmit, ntc, xdp_verdict);
+
 		continue;
 construct_skb:
 		if (likely(ice_ring_uses_build_skb(rx_ring)))
@@ -1217,18 +1296,12 @@ construct_skb:
 		/* exit if we failed to retrieve a buffer */
 		if (!skb) {
 			rx_ring->ring_stats->rx_stats.alloc_page_failed++;
-			rx_buf->act = ICE_XDP_CONSUMED;
-			if (unlikely(xdp_buff_has_frags(xdp)))
-				ice_set_rx_bufs_act(xdp, rx_ring,
-						    ICE_XDP_CONSUMED);
-			xdp->data = NULL;
-			rx_ring->first_desc = ntc;
-			rx_ring->nr_frags = 0;
-			break;
+			xdp_verdict = ICE_XDP_CONSUMED;
 		}
-		xdp->data = NULL;
-		rx_ring->first_desc = ntc;
-		rx_ring->nr_frags = 0;
+		ice_put_rx_mbuf(rx_ring, xdp, &xdp_xmit, ntc, xdp_verdict);
+
+		if (!skb)
+			break;
 
 		stat_err_bits = BIT(ICE_RX_FLEX_DESC_STATUS0_RXE_S);
 		if (unlikely(ice_test_staterr(rx_desc->wb.status_error0,
@@ -1257,23 +1330,6 @@ construct_skb:
 		total_rx_pkts++;
 	}
 
-	first = rx_ring->first_desc;
-	while (cached_ntc != first) {
-		struct ice_rx_buf *buf = &rx_ring->rx_buf[cached_ntc];
-
-		if (buf->act & (ICE_XDP_TX | ICE_XDP_REDIR)) {
-			ice_rx_buf_adjust_pg_offset(buf, xdp->frame_sz);
-			xdp_xmit |= buf->act;
-		} else if (buf->act & ICE_XDP_CONSUMED) {
-			buf->pagecnt_bias++;
-		} else if (buf->act == ICE_XDP_PASS) {
-			ice_rx_buf_adjust_pg_offset(buf, xdp->frame_sz);
-		}
-
-		ice_put_rx_buf(rx_ring, buf);
-		if (++cached_ntc >= cnt)
-			cached_ntc = 0;
-	}
 	rx_ring->next_to_clean = ntc;
 	/* return up to cleaned_count buffers to hardware */
 	failure = ice_alloc_rx_bufs(rx_ring, ICE_RX_DESC_UNUSED(rx_ring));
@@ -2368,7 +2424,9 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_tx_ring *tx_ring)
 					ICE_TXD_CTX_QW1_CMD_S);
 
 	ice_tstamp(tx_ring, skb, first, &offload);
-	if (ice_is_switchdev_running(vsi->back) && vsi->type != ICE_VSI_SF)
+	if ((ice_is_switchdev_running(vsi->back) ||
+	     ice_lag_is_switchdev_running(vsi->back)) &&
+	    vsi->type != ICE_VSI_SF)
 		ice_eswitch_set_target_vsi(skb, &offload);
 
 	if (offload.cd_qw1 & ICE_TX_DESC_DTYPE_CTX) {
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h
index feba314a3fe4..7130992d4177 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.h
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.h
@@ -201,7 +201,6 @@ struct ice_rx_buf {
 	struct page *page;
 	unsigned int page_offset;
 	unsigned int pgcnt;
-	unsigned int act;
 	unsigned int pagecnt_bias;
 };
 
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h
index afcead4baef4..f6c2b16ab456 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h
@@ -6,49 +6,6 @@
 #include "ice.h"
 
 /**
- * ice_set_rx_bufs_act - propagate Rx buffer action to frags
- * @xdp: XDP buffer representing frame (linear and frags part)
- * @rx_ring: Rx ring struct
- * act: action to store onto Rx buffers related to XDP buffer parts
- *
- * Set action that should be taken before putting Rx buffer from first frag
- * to the last.
- */
-static inline void
-ice_set_rx_bufs_act(struct xdp_buff *xdp, const struct ice_rx_ring *rx_ring,
-		    const unsigned int act)
-{
-	u32 sinfo_frags = xdp_get_shared_info_from_buff(xdp)->nr_frags;
-	u32 nr_frags = rx_ring->nr_frags + 1;
-	u32 idx = rx_ring->first_desc;
-	u32 cnt = rx_ring->count;
-	struct ice_rx_buf *buf;
-
-	for (int i = 0; i < nr_frags; i++) {
-		buf = &rx_ring->rx_buf[idx];
-		buf->act = act;
-
-		if (++idx == cnt)
-			idx = 0;
-	}
-
-	/* adjust pagecnt_bias on frags freed by XDP prog */
-	if (sinfo_frags < rx_ring->nr_frags && act == ICE_XDP_CONSUMED) {
-		u32 delta = rx_ring->nr_frags - sinfo_frags;
-
-		while (delta) {
-			if (idx == 0)
-				idx = cnt - 1;
-			else
-				idx--;
-			buf = &rx_ring->rx_buf[idx];
-			buf->pagecnt_bias--;
-			delta--;
-		}
-	}
-}
-
-/**
  * ice_test_staterr - tests bits in Rx descriptor status and error fields
  * @status_err_n: Rx descriptor status_error0 or status_error1 bits
  * @stat_err_bits: value to mask
diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.c b/drivers/net/ethernet/intel/ice/ice_vf_lib.c
index 8c434689e3f7..815ad0bfe832 100644
--- a/drivers/net/ethernet/intel/ice/ice_vf_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.c
@@ -717,6 +717,23 @@ ice_vf_clear_vsi_promisc(struct ice_vf *vf, struct ice_vsi *vsi, u8 promisc_m)
 }
 
 /**
+ * ice_reset_vf_mbx_cnt - reset VF mailbox message count
+ * @vf: pointer to the VF structure
+ *
+ * This function clears the VF mailbox message count, and should be called on
+ * VF reset.
+ */
+static void ice_reset_vf_mbx_cnt(struct ice_vf *vf)
+{
+	struct ice_pf *pf = vf->pf;
+
+	if (ice_is_feature_supported(pf, ICE_F_MBX_LIMIT))
+		ice_mbx_vf_clear_cnt_e830(&pf->hw, vf->vf_id);
+	else
+		ice_mbx_clear_malvf(&vf->mbx_info);
+}
+
+/**
  * ice_reset_all_vfs - reset all allocated VFs in one go
  * @pf: pointer to the PF structure
  *
@@ -742,7 +759,7 @@ void ice_reset_all_vfs(struct ice_pf *pf)
 
 	/* clear all malicious info if the VFs are getting reset */
 	ice_for_each_vf(pf, bkt, vf)
-		ice_mbx_clear_malvf(&vf->mbx_info);
+		ice_reset_vf_mbx_cnt(vf);
 
 	/* If VFs have been disabled, there is no need to reset */
 	if (test_and_set_bit(ICE_VF_DIS, pf->state)) {
@@ -958,7 +975,7 @@ int ice_reset_vf(struct ice_vf *vf, u32 flags)
 	ice_eswitch_update_repr(&vf->repr_id, vsi);
 
 	/* if the VF has been reset allow it to come up again */
-	ice_mbx_clear_malvf(&vf->mbx_info);
+	ice_reset_vf_mbx_cnt(vf);
 
 out_unlock:
 	if (lag && lag->bonded && lag->primary &&
@@ -1011,11 +1028,22 @@ void ice_initialize_vf_entry(struct ice_vf *vf)
 	ice_vf_fdir_init(vf);
 
 	/* Initialize mailbox info for this VF */
-	ice_mbx_init_vf_info(&pf->hw, &vf->mbx_info);
+	if (ice_is_feature_supported(pf, ICE_F_MBX_LIMIT))
+		ice_mbx_vf_clear_cnt_e830(&pf->hw, vf->vf_id);
+	else
+		ice_mbx_init_vf_info(&pf->hw, &vf->mbx_info);
 
 	mutex_init(&vf->cfg_lock);
 }
 
+void ice_deinitialize_vf_entry(struct ice_vf *vf)
+{
+	struct ice_pf *pf = vf->pf;
+
+	if (!ice_is_feature_supported(pf, ICE_F_MBX_LIMIT))
+		list_del(&vf->mbx_info.list_entry);
+}
+
 /**
  * ice_dis_vf_qs - Disable the VF queues
  * @vf: pointer to the VF structure
diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h b/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h
index 0c7e77c0a09f..5392b0404986 100644
--- a/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h
+++ b/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h
@@ -24,6 +24,7 @@
 #endif
 
 void ice_initialize_vf_entry(struct ice_vf *vf);
+void ice_deinitialize_vf_entry(struct ice_vf *vf);
 void ice_dis_vf_qs(struct ice_vf *vf);
 int ice_check_vf_init(struct ice_vf *vf);
 enum virtchnl_status_code ice_err_to_virt_err(int err);
diff --git a/drivers/net/ethernet/intel/ice/ice_vf_mbx.c b/drivers/net/ethernet/intel/ice/ice_vf_mbx.c
index 40cb4ba0789c..75c8113e58ee 100644
--- a/drivers/net/ethernet/intel/ice/ice_vf_mbx.c
+++ b/drivers/net/ethernet/intel/ice/ice_vf_mbx.c
@@ -211,6 +211,38 @@ ice_mbx_detect_malvf(struct ice_hw *hw, struct ice_mbx_vf_info *vf_info,
 }
 
 /**
+ * ice_mbx_vf_dec_trig_e830 - Decrements the VF mailbox queue counter
+ * @hw: pointer to the HW struct
+ * @event: pointer to the control queue receive event
+ *
+ * This function triggers to decrement the counter
+ * MBX_VF_IN_FLIGHT_MSGS_AT_PF_CNT when the driver replenishes
+ * the buffers at the PF mailbox queue.
+ */
+void ice_mbx_vf_dec_trig_e830(const struct ice_hw *hw,
+			      const struct ice_rq_event_info *event)
+{
+	u16 vfid = le16_to_cpu(event->desc.retval);
+
+	wr32(hw, E830_MBX_VF_DEC_TRIG(vfid), 1);
+}
+
+/**
+ * ice_mbx_vf_clear_cnt_e830 - Clear the VF mailbox queue count
+ * @hw: pointer to the HW struct
+ * @vf_id: VF ID in the PF space
+ *
+ * This function clears the counter MBX_VF_IN_FLIGHT_MSGS_AT_PF_CNT, and should
+ * be called when a VF is created and on VF reset.
+ */
+void ice_mbx_vf_clear_cnt_e830(const struct ice_hw *hw, u16 vf_id)
+{
+	u32 reg = rd32(hw, E830_MBX_VF_IN_FLIGHT_MSGS_AT_PF_CNT(vf_id));
+
+	wr32(hw, E830_MBX_VF_DEC_TRIG(vf_id), reg);
+}
+
+/**
  * ice_mbx_vf_state_handler - Handle states of the overflow algorithm
  * @hw: pointer to the HW struct
  * @mbx_data: pointer to structure containing mailbox data
diff --git a/drivers/net/ethernet/intel/ice/ice_vf_mbx.h b/drivers/net/ethernet/intel/ice/ice_vf_mbx.h
index 44bc030d17e0..684de89e5c5e 100644
--- a/drivers/net/ethernet/intel/ice/ice_vf_mbx.h
+++ b/drivers/net/ethernet/intel/ice/ice_vf_mbx.h
@@ -19,6 +19,9 @@ ice_aq_send_msg_to_vf(struct ice_hw *hw, u16 vfid, u32 v_opcode, u32 v_retval,
 		      u8 *msg, u16 msglen, struct ice_sq_cd *cd);
 
 u32 ice_conv_link_speed_to_virtchnl(bool adv_link_support, u16 link_speed);
+void ice_mbx_vf_dec_trig_e830(const struct ice_hw *hw,
+			      const struct ice_rq_event_info *event);
+void ice_mbx_vf_clear_cnt_e830(const struct ice_hw *hw, u16 vf_id);
 int
 ice_mbx_vf_state_handler(struct ice_hw *hw, struct ice_mbx_data *mbx_data,
 			 struct ice_mbx_vf_info *vf_info, bool *report_malvf);
@@ -47,5 +50,11 @@ static inline void ice_mbx_init_snapshot(struct ice_hw *hw)
 {
 }
 
+static inline void
+ice_mbx_vf_dec_trig_e830(const struct ice_hw *hw,
+			 const struct ice_rq_event_info *event)
+{
+}
+
 #endif /* CONFIG_PCI_IOV */
 #endif /* _ICE_VF_MBX_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
index b6ec01f6fa73..87ffd25b268a 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
@@ -3877,7 +3877,6 @@ static int ice_vc_repr_add_mac(struct ice_vf *vf, u8 *msg)
 		}
 
 		ice_vfhw_mac_add(vf, &al->list[i]);
-		vf->num_mac++;
 		break;
 	}
 
@@ -4008,8 +4007,10 @@ ice_is_malicious_vf(struct ice_vf *vf, struct ice_mbx_data *mbxdata)
  * @event: pointer to the AQ event
  * @mbxdata: information used to detect VF attempting mailbox overflow
  *
- * called from the common asq/arq handler to
- * process request from VF
+ * Called from the common asq/arq handler to process request from VF. When this
+ * flow is used for devices with hardware VF to PF message queue overflow
+ * support (ICE_F_MBX_LIMIT) mbxdata is set to NULL and ice_is_malicious_vf
+ * check is skipped.
  */
 void ice_vc_process_vf_msg(struct ice_pf *pf, struct ice_rq_event_info *event,
 			   struct ice_mbx_data *mbxdata)
@@ -4035,7 +4036,7 @@ void ice_vc_process_vf_msg(struct ice_pf *pf, struct ice_rq_event_info *event,
 	mutex_lock(&vf->cfg_lock);
 
 	/* Check if the VF is trying to overflow the mailbox */
-	if (ice_is_malicious_vf(vf, mbxdata))
+	if (mbxdata && ice_is_malicious_vf(vf, mbxdata))
 		goto finish;
 
 	/* Check if VF is disabled. */
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c
index 14e3f0f89c78..ef755cee64ca 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c
@@ -2091,6 +2091,11 @@ int ice_vc_add_fdir_fltr(struct ice_vf *vf, u8 *msg)
 	pf = vf->pf;
 	dev = ice_pf_to_dev(pf);
 	vf_vsi = ice_get_vf_vsi(vf);
+	if (!vf_vsi) {
+		dev_err(dev, "Can not get FDIR vf_vsi for VF %u\n", vf->vf_id);
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto err_exit;
+	}
 
 #define ICE_VF_MAX_FDIR_FILTERS	128
 	if (!ice_fdir_num_avail_fltr(&pf->hw, vf_vsi) ||
diff --git a/drivers/net/ethernet/intel/idpf/idpf.h b/drivers/net/ethernet/intel/idpf/idpf.h
index 66544faab710..a2b346d91879 100644
--- a/drivers/net/ethernet/intel/idpf/idpf.h
+++ b/drivers/net/ethernet/intel/idpf/idpf.h
@@ -143,6 +143,7 @@ enum idpf_vport_state {
  * @vport_id: Vport identifier
  * @link_speed_mbps: Link speed in mbps
  * @vport_idx: Relative vport index
+ * @max_tx_hdr_size: Max header length hardware can support
  * @state: See enum idpf_vport_state
  * @netstats: Packet and byte stats
  * @stats_lock: Lock to protect stats update
@@ -153,6 +154,7 @@ struct idpf_netdev_priv {
 	u32 vport_id;
 	u32 link_speed_mbps;
 	u16 vport_idx;
+	u16 max_tx_hdr_size;
 	enum idpf_vport_state state;
 	struct rtnl_link_stats64 netstats;
 	spinlock_t stats_lock;
@@ -368,9 +370,27 @@ struct idpf_rss_data {
 };
 
 /**
+ * struct idpf_q_coalesce - User defined coalescing configuration values for
+ *			   a single queue.
+ * @tx_intr_mode: Dynamic TX ITR or not
+ * @rx_intr_mode: Dynamic RX ITR or not
+ * @tx_coalesce_usecs: TX interrupt throttling rate
+ * @rx_coalesce_usecs: RX interrupt throttling rate
+ *
+ * Used to restore user coalescing configuration after a reset.
+ */
+struct idpf_q_coalesce {
+	u32 tx_intr_mode;
+	u32 rx_intr_mode;
+	u32 tx_coalesce_usecs;
+	u32 rx_coalesce_usecs;
+};
+
+/**
  * struct idpf_vport_user_config_data - User defined configuration values for
  *					each vport.
  * @rss_data: See struct idpf_rss_data
+ * @q_coalesce: Array of per queue coalescing data
  * @num_req_tx_qs: Number of user requested TX queues through ethtool
  * @num_req_rx_qs: Number of user requested RX queues through ethtool
  * @num_req_txq_desc: Number of user requested TX queue descriptors through
@@ -384,6 +404,7 @@ struct idpf_rss_data {
  */
 struct idpf_vport_user_config_data {
 	struct idpf_rss_data rss_data;
+	struct idpf_q_coalesce *q_coalesce;
 	u16 num_req_tx_qs;
 	u16 num_req_rx_qs;
 	u32 num_req_txq_desc;
@@ -629,13 +650,13 @@ bool idpf_is_capability_ena(struct idpf_adapter *adapter, bool all,
 	VIRTCHNL2_CAP_RX_HSPLIT_AT_L4V4	|\
 	VIRTCHNL2_CAP_RX_HSPLIT_AT_L4V6)
 
-#define IDPF_CAP_RX_CSUM_L4V4 (\
-	VIRTCHNL2_CAP_RX_CSUM_L4_IPV4_TCP	|\
-	VIRTCHNL2_CAP_RX_CSUM_L4_IPV4_UDP)
+#define IDPF_CAP_TX_CSUM_L4V4 (\
+	VIRTCHNL2_CAP_TX_CSUM_L4_IPV4_TCP	|\
+	VIRTCHNL2_CAP_TX_CSUM_L4_IPV4_UDP)
 
-#define IDPF_CAP_RX_CSUM_L4V6 (\
-	VIRTCHNL2_CAP_RX_CSUM_L4_IPV6_TCP	|\
-	VIRTCHNL2_CAP_RX_CSUM_L4_IPV6_UDP)
+#define IDPF_CAP_TX_CSUM_L4V6 (\
+	VIRTCHNL2_CAP_TX_CSUM_L4_IPV6_TCP	|\
+	VIRTCHNL2_CAP_TX_CSUM_L4_IPV6_UDP)
 
 #define IDPF_CAP_RX_CSUM (\
 	VIRTCHNL2_CAP_RX_CSUM_L3_IPV4		|\
@@ -644,11 +665,9 @@ bool idpf_is_capability_ena(struct idpf_adapter *adapter, bool all,
 	VIRTCHNL2_CAP_RX_CSUM_L4_IPV6_TCP	|\
 	VIRTCHNL2_CAP_RX_CSUM_L4_IPV6_UDP)
 
-#define IDPF_CAP_SCTP_CSUM (\
+#define IDPF_CAP_TX_SCTP_CSUM (\
 	VIRTCHNL2_CAP_TX_CSUM_L4_IPV4_SCTP	|\
-	VIRTCHNL2_CAP_TX_CSUM_L4_IPV6_SCTP	|\
-	VIRTCHNL2_CAP_RX_CSUM_L4_IPV4_SCTP	|\
-	VIRTCHNL2_CAP_RX_CSUM_L4_IPV6_SCTP)
+	VIRTCHNL2_CAP_TX_CSUM_L4_IPV6_SCTP)
 
 #define IDPF_CAP_TUNNEL_TX_CSUM (\
 	VIRTCHNL2_CAP_TX_CSUM_L3_SINGLE_TUNNEL	|\
diff --git a/drivers/net/ethernet/intel/idpf/idpf_controlq.c b/drivers/net/ethernet/intel/idpf/idpf_controlq.c
index 4849590a5591..48b8e184f3db 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_controlq.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_controlq.c
@@ -96,7 +96,7 @@ static void idpf_ctlq_init_rxq_bufs(struct idpf_ctlq_info *cq)
  */
 static void idpf_ctlq_shutdown(struct idpf_hw *hw, struct idpf_ctlq_info *cq)
 {
-	mutex_lock(&cq->cq_lock);
+	spin_lock(&cq->cq_lock);
 
 	/* free ring buffers and the ring itself */
 	idpf_ctlq_dealloc_ring_res(hw, cq);
@@ -104,8 +104,7 @@ static void idpf_ctlq_shutdown(struct idpf_hw *hw, struct idpf_ctlq_info *cq)
 	/* Set ring_size to 0 to indicate uninitialized queue */
 	cq->ring_size = 0;
 
-	mutex_unlock(&cq->cq_lock);
-	mutex_destroy(&cq->cq_lock);
+	spin_unlock(&cq->cq_lock);
 }
 
 /**
@@ -173,7 +172,7 @@ int idpf_ctlq_add(struct idpf_hw *hw,
 
 	idpf_ctlq_init_regs(hw, cq, is_rxq);
 
-	mutex_init(&cq->cq_lock);
+	spin_lock_init(&cq->cq_lock);
 
 	list_add(&cq->cq_list, &hw->cq_list_head);
 
@@ -272,7 +271,7 @@ int idpf_ctlq_send(struct idpf_hw *hw, struct idpf_ctlq_info *cq,
 	int err = 0;
 	int i;
 
-	mutex_lock(&cq->cq_lock);
+	spin_lock(&cq->cq_lock);
 
 	/* Ensure there are enough descriptors to send all messages */
 	num_desc_avail = IDPF_CTLQ_DESC_UNUSED(cq);
@@ -332,7 +331,7 @@ int idpf_ctlq_send(struct idpf_hw *hw, struct idpf_ctlq_info *cq,
 	wr32(hw, cq->reg.tail, cq->next_to_use);
 
 err_unlock:
-	mutex_unlock(&cq->cq_lock);
+	spin_unlock(&cq->cq_lock);
 
 	return err;
 }
@@ -364,7 +363,7 @@ int idpf_ctlq_clean_sq(struct idpf_ctlq_info *cq, u16 *clean_count,
 	if (*clean_count > cq->ring_size)
 		return -EBADR;
 
-	mutex_lock(&cq->cq_lock);
+	spin_lock(&cq->cq_lock);
 
 	ntc = cq->next_to_clean;
 
@@ -376,6 +375,9 @@ int idpf_ctlq_clean_sq(struct idpf_ctlq_info *cq, u16 *clean_count,
 		if (!(le16_to_cpu(desc->flags) & IDPF_CTLQ_FLAG_DD))
 			break;
 
+		/* Ensure no other fields are read until DD flag is checked */
+		dma_rmb();
+
 		/* strip off FW internal code */
 		desc_err = le16_to_cpu(desc->ret_val) & 0xff;
 
@@ -394,7 +396,7 @@ int idpf_ctlq_clean_sq(struct idpf_ctlq_info *cq, u16 *clean_count,
 
 	cq->next_to_clean = ntc;
 
-	mutex_unlock(&cq->cq_lock);
+	spin_unlock(&cq->cq_lock);
 
 	/* Return number of descriptors actually cleaned */
 	*clean_count = i;
@@ -432,7 +434,7 @@ int idpf_ctlq_post_rx_buffs(struct idpf_hw *hw, struct idpf_ctlq_info *cq,
 	if (*buff_count > 0)
 		buffs_avail = true;
 
-	mutex_lock(&cq->cq_lock);
+	spin_lock(&cq->cq_lock);
 
 	if (tbp >= cq->ring_size)
 		tbp = 0;
@@ -521,7 +523,7 @@ post_buffs_out:
 		wr32(hw, cq->reg.tail, cq->next_to_post);
 	}
 
-	mutex_unlock(&cq->cq_lock);
+	spin_unlock(&cq->cq_lock);
 
 	/* return the number of buffers that were not posted */
 	*buff_count = *buff_count - i;
@@ -549,7 +551,7 @@ int idpf_ctlq_recv(struct idpf_ctlq_info *cq, u16 *num_q_msg,
 	u16 i;
 
 	/* take the lock before we start messing with the ring */
-	mutex_lock(&cq->cq_lock);
+	spin_lock(&cq->cq_lock);
 
 	ntc = cq->next_to_clean;
 
@@ -563,6 +565,9 @@ int idpf_ctlq_recv(struct idpf_ctlq_info *cq, u16 *num_q_msg,
 		if (!(flags & IDPF_CTLQ_FLAG_DD))
 			break;
 
+		/* Ensure no other fields are read until DD flag is checked */
+		dma_rmb();
+
 		q_msg[i].vmvf_type = (flags &
 				      (IDPF_CTLQ_FLAG_FTYPE_VM |
 				       IDPF_CTLQ_FLAG_FTYPE_PF)) >>
@@ -608,7 +613,7 @@ int idpf_ctlq_recv(struct idpf_ctlq_info *cq, u16 *num_q_msg,
 
 	cq->next_to_clean = ntc;
 
-	mutex_unlock(&cq->cq_lock);
+	spin_unlock(&cq->cq_lock);
 
 	*num_q_msg = i;
 	if (*num_q_msg == 0)
diff --git a/drivers/net/ethernet/intel/idpf/idpf_controlq_api.h b/drivers/net/ethernet/intel/idpf/idpf_controlq_api.h
index e8e046ef2f0d..5890d8adca4a 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_controlq_api.h
+++ b/drivers/net/ethernet/intel/idpf/idpf_controlq_api.h
@@ -99,7 +99,7 @@ struct idpf_ctlq_info {
 
 	enum idpf_ctlq_type cq_type;
 	int q_id;
-	struct mutex cq_lock;		/* control queue lock */
+	spinlock_t cq_lock;		/* control queue lock */
 	/* used for interrupt processing */
 	u16 next_to_use;
 	u16 next_to_clean;
diff --git a/drivers/net/ethernet/intel/idpf/idpf_ethtool.c b/drivers/net/ethernet/intel/idpf/idpf_ethtool.c
index 59b1a1a09996..f0f0ced0d95f 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_ethtool.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_ethtool.c
@@ -46,7 +46,7 @@ static u32 idpf_get_rxfh_key_size(struct net_device *netdev)
 	struct idpf_vport_user_config_data *user_config;
 
 	if (!idpf_is_cap_ena_all(np->adapter, IDPF_RSS_CAPS, IDPF_CAP_RSS))
-		return -EOPNOTSUPP;
+		return 0;
 
 	user_config = &np->adapter->vport_config[np->vport_idx]->user_config;
 
@@ -65,7 +65,7 @@ static u32 idpf_get_rxfh_indir_size(struct net_device *netdev)
 	struct idpf_vport_user_config_data *user_config;
 
 	if (!idpf_is_cap_ena_all(np->adapter, IDPF_RSS_CAPS, IDPF_CAP_RSS))
-		return -EOPNOTSUPP;
+		return 0;
 
 	user_config = &np->adapter->vport_config[np->vport_idx]->user_config;
 
@@ -1089,12 +1089,14 @@ static int idpf_get_per_q_coalesce(struct net_device *netdev, u32 q_num,
 /**
  * __idpf_set_q_coalesce - set ITR values for specific queue
  * @ec: ethtool structure from user to update ITR settings
+ * @q_coal: per queue coalesce settings
  * @qv: queue vector for which itr values has to be set
  * @is_rxq: is queue type rx
  *
  * Returns 0 on success, negative otherwise.
  */
 static int __idpf_set_q_coalesce(const struct ethtool_coalesce *ec,
+				 struct idpf_q_coalesce *q_coal,
 				 struct idpf_q_vector *qv, bool is_rxq)
 {
 	u32 use_adaptive_coalesce, coalesce_usecs;
@@ -1138,20 +1140,25 @@ static int __idpf_set_q_coalesce(const struct ethtool_coalesce *ec,
 
 	if (is_rxq) {
 		qv->rx_itr_value = coalesce_usecs;
+		q_coal->rx_coalesce_usecs = coalesce_usecs;
 		if (use_adaptive_coalesce) {
 			qv->rx_intr_mode = IDPF_ITR_DYNAMIC;
+			q_coal->rx_intr_mode = IDPF_ITR_DYNAMIC;
 		} else {
 			qv->rx_intr_mode = !IDPF_ITR_DYNAMIC;
-			idpf_vport_intr_write_itr(qv, qv->rx_itr_value,
-						  false);
+			q_coal->rx_intr_mode = !IDPF_ITR_DYNAMIC;
+			idpf_vport_intr_write_itr(qv, coalesce_usecs, false);
 		}
 	} else {
 		qv->tx_itr_value = coalesce_usecs;
+		q_coal->tx_coalesce_usecs = coalesce_usecs;
 		if (use_adaptive_coalesce) {
 			qv->tx_intr_mode = IDPF_ITR_DYNAMIC;
+			q_coal->tx_intr_mode = IDPF_ITR_DYNAMIC;
 		} else {
 			qv->tx_intr_mode = !IDPF_ITR_DYNAMIC;
-			idpf_vport_intr_write_itr(qv, qv->tx_itr_value, true);
+			q_coal->tx_intr_mode = !IDPF_ITR_DYNAMIC;
+			idpf_vport_intr_write_itr(qv, coalesce_usecs, true);
 		}
 	}
 
@@ -1164,6 +1171,7 @@ static int __idpf_set_q_coalesce(const struct ethtool_coalesce *ec,
 /**
  * idpf_set_q_coalesce - set ITR values for specific queue
  * @vport: vport associated to the queue that need updating
+ * @q_coal: per queue coalesce settings
  * @ec: coalesce settings to program the device with
  * @q_num: update ITR/INTRL (coalesce) settings for this queue number/index
  * @is_rxq: is queue type rx
@@ -1171,6 +1179,7 @@ static int __idpf_set_q_coalesce(const struct ethtool_coalesce *ec,
  * Return 0 on success, and negative on failure
  */
 static int idpf_set_q_coalesce(const struct idpf_vport *vport,
+			       struct idpf_q_coalesce *q_coal,
 			       const struct ethtool_coalesce *ec,
 			       int q_num, bool is_rxq)
 {
@@ -1179,7 +1188,7 @@ static int idpf_set_q_coalesce(const struct idpf_vport *vport,
 	qv = is_rxq ? idpf_find_rxq_vec(vport, q_num) :
 		      idpf_find_txq_vec(vport, q_num);
 
-	if (qv && __idpf_set_q_coalesce(ec, qv, is_rxq))
+	if (qv && __idpf_set_q_coalesce(ec, q_coal, qv, is_rxq))
 		return -EINVAL;
 
 	return 0;
@@ -1200,9 +1209,13 @@ static int idpf_set_coalesce(struct net_device *netdev,
 			     struct netlink_ext_ack *extack)
 {
 	struct idpf_netdev_priv *np = netdev_priv(netdev);
+	struct idpf_vport_user_config_data *user_config;
+	struct idpf_q_coalesce *q_coal;
 	struct idpf_vport *vport;
 	int i, err = 0;
 
+	user_config = &np->adapter->vport_config[np->vport_idx]->user_config;
+
 	idpf_vport_ctrl_lock(netdev);
 	vport = idpf_netdev_to_vport(netdev);
 
@@ -1210,13 +1223,15 @@ static int idpf_set_coalesce(struct net_device *netdev,
 		goto unlock_mutex;
 
 	for (i = 0; i < vport->num_txq; i++) {
-		err = idpf_set_q_coalesce(vport, ec, i, false);
+		q_coal = &user_config->q_coalesce[i];
+		err = idpf_set_q_coalesce(vport, q_coal, ec, i, false);
 		if (err)
 			goto unlock_mutex;
 	}
 
 	for (i = 0; i < vport->num_rxq; i++) {
-		err = idpf_set_q_coalesce(vport, ec, i, true);
+		q_coal = &user_config->q_coalesce[i];
+		err = idpf_set_q_coalesce(vport, q_coal, ec, i, true);
 		if (err)
 			goto unlock_mutex;
 	}
@@ -1238,20 +1253,25 @@ unlock_mutex:
 static int idpf_set_per_q_coalesce(struct net_device *netdev, u32 q_num,
 				   struct ethtool_coalesce *ec)
 {
+	struct idpf_netdev_priv *np = netdev_priv(netdev);
+	struct idpf_vport_user_config_data *user_config;
+	struct idpf_q_coalesce *q_coal;
 	struct idpf_vport *vport;
 	int err;
 
 	idpf_vport_ctrl_lock(netdev);
 	vport = idpf_netdev_to_vport(netdev);
+	user_config = &np->adapter->vport_config[np->vport_idx]->user_config;
+	q_coal = &user_config->q_coalesce[q_num];
 
-	err = idpf_set_q_coalesce(vport, ec, q_num, false);
+	err = idpf_set_q_coalesce(vport, q_coal, ec, q_num, false);
 	if (err) {
 		idpf_vport_ctrl_unlock(netdev);
 
 		return err;
 	}
 
-	err = idpf_set_q_coalesce(vport, ec, q_num, true);
+	err = idpf_set_q_coalesce(vport, q_coal, ec, q_num, true);
 
 	idpf_vport_ctrl_unlock(netdev);
 
diff --git a/drivers/net/ethernet/intel/idpf/idpf_lib.c b/drivers/net/ethernet/intel/idpf/idpf_lib.c
index b4fbb99bfad2..1468a0f0df2b 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_lib.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_lib.c
@@ -703,8 +703,10 @@ static int idpf_cfg_netdev(struct idpf_vport *vport)
 {
 	struct idpf_adapter *adapter = vport->adapter;
 	struct idpf_vport_config *vport_config;
+	netdev_features_t other_offloads = 0;
+	netdev_features_t csum_offloads = 0;
+	netdev_features_t tso_offloads = 0;
 	netdev_features_t dflt_features;
-	netdev_features_t offloads = 0;
 	struct idpf_netdev_priv *np;
 	struct net_device *netdev;
 	u16 idx = vport->idx;
@@ -721,6 +723,7 @@ static int idpf_cfg_netdev(struct idpf_vport *vport)
 		np->vport = vport;
 		np->vport_idx = vport->idx;
 		np->vport_id = vport->vport_id;
+		np->max_tx_hdr_size = idpf_get_max_tx_hdr_size(adapter);
 		vport->netdev = netdev;
 
 		return idpf_init_mac_addr(vport, netdev);
@@ -738,6 +741,7 @@ static int idpf_cfg_netdev(struct idpf_vport *vport)
 	np->adapter = adapter;
 	np->vport_idx = vport->idx;
 	np->vport_id = vport->vport_id;
+	np->max_tx_hdr_size = idpf_get_max_tx_hdr_size(adapter);
 
 	spin_lock_init(&np->stats_lock);
 
@@ -766,53 +770,32 @@ static int idpf_cfg_netdev(struct idpf_vport *vport)
 
 	if (idpf_is_cap_ena_all(adapter, IDPF_RSS_CAPS, IDPF_CAP_RSS))
 		dflt_features |= NETIF_F_RXHASH;
-	if (idpf_is_cap_ena_all(adapter, IDPF_CSUM_CAPS, IDPF_CAP_RX_CSUM_L4V4))
-		dflt_features |= NETIF_F_IP_CSUM;
-	if (idpf_is_cap_ena_all(adapter, IDPF_CSUM_CAPS, IDPF_CAP_RX_CSUM_L4V6))
-		dflt_features |= NETIF_F_IPV6_CSUM;
+	if (idpf_is_cap_ena_all(adapter, IDPF_CSUM_CAPS, IDPF_CAP_TX_CSUM_L4V4))
+		csum_offloads |= NETIF_F_IP_CSUM;
+	if (idpf_is_cap_ena_all(adapter, IDPF_CSUM_CAPS, IDPF_CAP_TX_CSUM_L4V6))
+		csum_offloads |= NETIF_F_IPV6_CSUM;
 	if (idpf_is_cap_ena(adapter, IDPF_CSUM_CAPS, IDPF_CAP_RX_CSUM))
-		dflt_features |= NETIF_F_RXCSUM;
-	if (idpf_is_cap_ena_all(adapter, IDPF_CSUM_CAPS, IDPF_CAP_SCTP_CSUM))
-		dflt_features |= NETIF_F_SCTP_CRC;
+		csum_offloads |= NETIF_F_RXCSUM;
+	if (idpf_is_cap_ena_all(adapter, IDPF_CSUM_CAPS, IDPF_CAP_TX_SCTP_CSUM))
+		csum_offloads |= NETIF_F_SCTP_CRC;
 
 	if (idpf_is_cap_ena(adapter, IDPF_SEG_CAPS, VIRTCHNL2_CAP_SEG_IPV4_TCP))
-		dflt_features |= NETIF_F_TSO;
+		tso_offloads |= NETIF_F_TSO;
 	if (idpf_is_cap_ena(adapter, IDPF_SEG_CAPS, VIRTCHNL2_CAP_SEG_IPV6_TCP))
-		dflt_features |= NETIF_F_TSO6;
+		tso_offloads |= NETIF_F_TSO6;
 	if (idpf_is_cap_ena_all(adapter, IDPF_SEG_CAPS,
 				VIRTCHNL2_CAP_SEG_IPV4_UDP |
 				VIRTCHNL2_CAP_SEG_IPV6_UDP))
-		dflt_features |= NETIF_F_GSO_UDP_L4;
+		tso_offloads |= NETIF_F_GSO_UDP_L4;
 	if (idpf_is_cap_ena_all(adapter, IDPF_RSC_CAPS, IDPF_CAP_RSC))
-		offloads |= NETIF_F_GRO_HW;
-	/* advertise to stack only if offloads for encapsulated packets is
-	 * supported
-	 */
-	if (idpf_is_cap_ena(vport->adapter, IDPF_SEG_CAPS,
-			    VIRTCHNL2_CAP_SEG_TX_SINGLE_TUNNEL)) {
-		offloads |= NETIF_F_GSO_UDP_TUNNEL	|
-			    NETIF_F_GSO_GRE		|
-			    NETIF_F_GSO_GRE_CSUM	|
-			    NETIF_F_GSO_PARTIAL		|
-			    NETIF_F_GSO_UDP_TUNNEL_CSUM	|
-			    NETIF_F_GSO_IPXIP4		|
-			    NETIF_F_GSO_IPXIP6		|
-			    0;
-
-		if (!idpf_is_cap_ena_all(vport->adapter, IDPF_CSUM_CAPS,
-					 IDPF_CAP_TUNNEL_TX_CSUM))
-			netdev->gso_partial_features |=
-				NETIF_F_GSO_UDP_TUNNEL_CSUM;
-
-		netdev->gso_partial_features |= NETIF_F_GSO_GRE_CSUM;
-		offloads |= NETIF_F_TSO_MANGLEID;
-	}
+		other_offloads |= NETIF_F_GRO_HW;
 	if (idpf_is_cap_ena(adapter, IDPF_OTHER_CAPS, VIRTCHNL2_CAP_LOOPBACK))
-		offloads |= NETIF_F_LOOPBACK;
+		other_offloads |= NETIF_F_LOOPBACK;
 
-	netdev->features |= dflt_features;
-	netdev->hw_features |= dflt_features | offloads;
-	netdev->hw_enc_features |= dflt_features | offloads;
+	netdev->features |= dflt_features | csum_offloads | tso_offloads;
+	netdev->hw_features |=  netdev->features | other_offloads;
+	netdev->vlan_features |= netdev->features | other_offloads;
+	netdev->hw_enc_features |= dflt_features | other_offloads;
 	idpf_set_ethtool_ops(netdev);
 	SET_NETDEV_DEV(netdev, &adapter->pdev->dev);
 
@@ -1106,8 +1089,10 @@ static struct idpf_vport *idpf_vport_alloc(struct idpf_adapter *adapter,
 	if (!vport)
 		return vport;
 
+	num_max_q = max(max_q->max_txq, max_q->max_rxq);
 	if (!adapter->vport_config[idx]) {
 		struct idpf_vport_config *vport_config;
+		struct idpf_q_coalesce *q_coal;
 
 		vport_config = kzalloc(sizeof(*vport_config), GFP_KERNEL);
 		if (!vport_config) {
@@ -1116,6 +1101,21 @@ static struct idpf_vport *idpf_vport_alloc(struct idpf_adapter *adapter,
 			return NULL;
 		}
 
+		q_coal = kcalloc(num_max_q, sizeof(*q_coal), GFP_KERNEL);
+		if (!q_coal) {
+			kfree(vport_config);
+			kfree(vport);
+
+			return NULL;
+		}
+		for (int i = 0; i < num_max_q; i++) {
+			q_coal[i].tx_intr_mode = IDPF_ITR_DYNAMIC;
+			q_coal[i].tx_coalesce_usecs = IDPF_ITR_TX_DEF;
+			q_coal[i].rx_intr_mode = IDPF_ITR_DYNAMIC;
+			q_coal[i].rx_coalesce_usecs = IDPF_ITR_RX_DEF;
+		}
+		vport_config->user_config.q_coalesce = q_coal;
+
 		adapter->vport_config[idx] = vport_config;
 	}
 
@@ -1125,13 +1125,10 @@ static struct idpf_vport *idpf_vport_alloc(struct idpf_adapter *adapter,
 	vport->default_vport = adapter->num_alloc_vports <
 			       idpf_get_default_vports(adapter);
 
-	num_max_q = max(max_q->max_txq, max_q->max_rxq);
 	vport->q_vector_idxs = kcalloc(num_max_q, sizeof(u16), GFP_KERNEL);
-	if (!vport->q_vector_idxs) {
-		kfree(vport);
+	if (!vport->q_vector_idxs)
+		goto free_vport;
 
-		return NULL;
-	}
 	idpf_vport_init(vport, max_q);
 
 	/* This alloc is done separate from the LUT because it's not strictly
@@ -1141,11 +1138,9 @@ static struct idpf_vport *idpf_vport_alloc(struct idpf_adapter *adapter,
 	 */
 	rss_data = &adapter->vport_config[idx]->user_config.rss_data;
 	rss_data->rss_key = kzalloc(rss_data->rss_key_size, GFP_KERNEL);
-	if (!rss_data->rss_key) {
-		kfree(vport);
+	if (!rss_data->rss_key)
+		goto free_vector_idxs;
 
-		return NULL;
-	}
 	/* Initialize default rss key */
 	netdev_rss_key_fill((void *)rss_data->rss_key, rss_data->rss_key_size);
 
@@ -1158,6 +1153,13 @@ static struct idpf_vport *idpf_vport_alloc(struct idpf_adapter *adapter,
 	adapter->next_vport = idpf_get_free_slot(adapter);
 
 	return vport;
+
+free_vector_idxs:
+	kfree(vport->q_vector_idxs);
+free_vport:
+	kfree(vport);
+
+	return NULL;
 }
 
 /**
@@ -1816,11 +1818,19 @@ void idpf_vc_event_task(struct work_struct *work)
 	if (test_bit(IDPF_REMOVE_IN_PROG, adapter->flags))
 		return;
 
-	if (test_bit(IDPF_HR_FUNC_RESET, adapter->flags) ||
-	    test_bit(IDPF_HR_DRV_LOAD, adapter->flags)) {
-		set_bit(IDPF_HR_RESET_IN_PROG, adapter->flags);
-		idpf_init_hard_reset(adapter);
-	}
+	if (test_bit(IDPF_HR_FUNC_RESET, adapter->flags))
+		goto func_reset;
+
+	if (test_bit(IDPF_HR_DRV_LOAD, adapter->flags))
+		goto drv_load;
+
+	return;
+
+func_reset:
+	idpf_vc_xn_shutdown(adapter->vcxn_mngr);
+drv_load:
+	set_bit(IDPF_HR_RESET_IN_PROG, adapter->flags);
+	idpf_init_hard_reset(adapter);
 }
 
 /**
@@ -2159,8 +2169,13 @@ static int idpf_open(struct net_device *netdev)
 	idpf_vport_ctrl_lock(netdev);
 	vport = idpf_netdev_to_vport(netdev);
 
+	err = idpf_set_real_num_queues(vport);
+	if (err)
+		goto unlock;
+
 	err = idpf_vport_open(vport);
 
+unlock:
 	idpf_vport_ctrl_unlock(netdev);
 
 	return err;
@@ -2200,8 +2215,8 @@ static netdev_features_t idpf_features_check(struct sk_buff *skb,
 					     struct net_device *netdev,
 					     netdev_features_t features)
 {
-	struct idpf_vport *vport = idpf_netdev_to_vport(netdev);
-	struct idpf_adapter *adapter = vport->adapter;
+	struct idpf_netdev_priv *np = netdev_priv(netdev);
+	u16 max_tx_hdr_size = np->max_tx_hdr_size;
 	size_t len;
 
 	/* No point in doing any of this if neither checksum nor GSO are
@@ -2224,7 +2239,7 @@ static netdev_features_t idpf_features_check(struct sk_buff *skb,
 		goto unsupported;
 
 	len = skb_network_header_len(skb);
-	if (unlikely(len > idpf_get_max_tx_hdr_size(adapter)))
+	if (unlikely(len > max_tx_hdr_size))
 		goto unsupported;
 
 	if (!skb->encapsulation)
@@ -2237,7 +2252,7 @@ static netdev_features_t idpf_features_check(struct sk_buff *skb,
 
 	/* IPLEN can support at most 127 dwords */
 	len = skb_inner_network_header_len(skb);
-	if (unlikely(len > idpf_get_max_tx_hdr_size(adapter)))
+	if (unlikely(len > max_tx_hdr_size))
 		goto unsupported;
 
 	/* No need to validate L4LEN as TCP is the only protocol with a
@@ -2316,8 +2331,12 @@ void *idpf_alloc_dma_mem(struct idpf_hw *hw, struct idpf_dma_mem *mem, u64 size)
 	struct idpf_adapter *adapter = hw->back;
 	size_t sz = ALIGN(size, 4096);
 
-	mem->va = dma_alloc_coherent(&adapter->pdev->dev, sz,
-				     &mem->pa, GFP_KERNEL);
+	/* The control queue resources are freed under a spinlock, contiguous
+	 * pages will avoid IOMMU remapping and the use vmap (and vunmap in
+	 * dma_free_*() path.
+	 */
+	mem->va = dma_alloc_attrs(&adapter->pdev->dev, sz, &mem->pa,
+				  GFP_KERNEL, DMA_ATTR_FORCE_CONTIGUOUS);
 	mem->size = sz;
 
 	return mem->va;
@@ -2332,8 +2351,8 @@ void idpf_free_dma_mem(struct idpf_hw *hw, struct idpf_dma_mem *mem)
 {
 	struct idpf_adapter *adapter = hw->back;
 
-	dma_free_coherent(&adapter->pdev->dev, mem->size,
-			  mem->va, mem->pa);
+	dma_free_attrs(&adapter->pdev->dev, mem->size,
+		       mem->va, mem->pa, DMA_ATTR_FORCE_CONTIGUOUS);
 	mem->size = 0;
 	mem->va = NULL;
 	mem->pa = 0;
diff --git a/drivers/net/ethernet/intel/idpf/idpf_main.c b/drivers/net/ethernet/intel/idpf/idpf_main.c
index db476b3314c8..4c48a1a6aab0 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_main.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_main.c
@@ -62,6 +62,7 @@ destroy_wqs:
 	destroy_workqueue(adapter->vc_event_wq);
 
 	for (i = 0; i < adapter->max_vports; i++) {
+		kfree(adapter->vport_config[i]->user_config.q_coalesce);
 		kfree(adapter->vport_config[i]);
 		adapter->vport_config[i] = NULL;
 	}
@@ -87,7 +88,12 @@ destroy_wqs:
  */
 static void idpf_shutdown(struct pci_dev *pdev)
 {
-	idpf_remove(pdev);
+	struct idpf_adapter *adapter = pci_get_drvdata(pdev);
+
+	cancel_delayed_work_sync(&adapter->serv_task);
+	cancel_delayed_work_sync(&adapter->vc_event_task);
+	idpf_vc_core_deinit(adapter);
+	idpf_deinit_dflt_mbx(adapter);
 
 	if (system_state == SYSTEM_POWER_OFF)
 		pci_set_power_state(pdev, PCI_D3hot);
@@ -174,7 +180,8 @@ static int idpf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	pci_set_master(pdev);
 	pci_set_drvdata(pdev, adapter);
 
-	adapter->init_wq = alloc_workqueue("%s-%s-init", 0, 0,
+	adapter->init_wq = alloc_workqueue("%s-%s-init",
+					   WQ_UNBOUND | WQ_MEM_RECLAIM, 0,
 					   dev_driver_string(dev),
 					   dev_name(dev));
 	if (!adapter->init_wq) {
@@ -183,7 +190,8 @@ static int idpf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_free;
 	}
 
-	adapter->serv_wq = alloc_workqueue("%s-%s-service", 0, 0,
+	adapter->serv_wq = alloc_workqueue("%s-%s-service",
+					   WQ_UNBOUND | WQ_MEM_RECLAIM, 0,
 					   dev_driver_string(dev),
 					   dev_name(dev));
 	if (!adapter->serv_wq) {
@@ -192,7 +200,8 @@ static int idpf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_serv_wq_alloc;
 	}
 
-	adapter->mbx_wq = alloc_workqueue("%s-%s-mbx", 0, 0,
+	adapter->mbx_wq = alloc_workqueue("%s-%s-mbx",
+					  WQ_UNBOUND | WQ_MEM_RECLAIM, 0,
 					  dev_driver_string(dev),
 					  dev_name(dev));
 	if (!adapter->mbx_wq) {
@@ -201,7 +210,8 @@ static int idpf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_mbx_wq_alloc;
 	}
 
-	adapter->stats_wq = alloc_workqueue("%s-%s-stats", 0, 0,
+	adapter->stats_wq = alloc_workqueue("%s-%s-stats",
+					    WQ_UNBOUND | WQ_MEM_RECLAIM, 0,
 					    dev_driver_string(dev),
 					    dev_name(dev));
 	if (!adapter->stats_wq) {
@@ -210,7 +220,8 @@ static int idpf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_stats_wq_alloc;
 	}
 
-	adapter->vc_event_wq = alloc_workqueue("%s-%s-vc_event", 0, 0,
+	adapter->vc_event_wq = alloc_workqueue("%s-%s-vc_event",
+					       WQ_UNBOUND | WQ_MEM_RECLAIM, 0,
 					       dev_driver_string(dev),
 					       dev_name(dev));
 	if (!adapter->vc_event_wq) {
diff --git a/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c
index dfd7cf1d9aa0..a986dd572555 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c
@@ -362,17 +362,18 @@ netdev_tx_t idpf_tx_singleq_frame(struct sk_buff *skb,
 {
 	struct idpf_tx_offload_params offload = { };
 	struct idpf_tx_buf *first;
+	int csum, tso, needed;
 	unsigned int count;
 	__be16 protocol;
-	int csum, tso;
 
 	count = idpf_tx_desc_count_required(tx_q, skb);
 	if (unlikely(!count))
 		return idpf_tx_drop_skb(tx_q, skb);
 
-	if (idpf_tx_maybe_stop_common(tx_q,
-				      count + IDPF_TX_DESCS_PER_CACHE_LINE +
-				      IDPF_TX_DESCS_FOR_CTX)) {
+	needed = count + IDPF_TX_DESCS_PER_CACHE_LINE + IDPF_TX_DESCS_FOR_CTX;
+	if (!netif_subqueue_maybe_stop(tx_q->netdev, tx_q->idx,
+				       IDPF_DESC_UNUSED(tx_q),
+				       needed, needed)) {
 		idpf_tx_buf_hw_update(tx_q, tx_q->next_to_use, false);
 
 		u64_stats_update_begin(&tx_q->stats_sync);
diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
index 60d15b3e6e2f..4086a6ef352e 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
@@ -2132,6 +2132,19 @@ void idpf_tx_splitq_build_flow_desc(union idpf_tx_flex_desc *desc,
 	desc->flow.qw1.compl_tag = cpu_to_le16(params->compl_tag);
 }
 
+/* Global conditions to tell whether the txq (and related resources)
+ * has room to allow the use of "size" descriptors.
+ */
+static int idpf_txq_has_room(struct idpf_tx_queue *tx_q, u32 size)
+{
+	if (IDPF_DESC_UNUSED(tx_q) < size ||
+	    IDPF_TX_COMPLQ_PENDING(tx_q->txq_grp) >
+		IDPF_TX_COMPLQ_OVERFLOW_THRESH(tx_q->txq_grp->complq) ||
+	    IDPF_TX_BUF_RSV_LOW(tx_q))
+		return 0;
+	return 1;
+}
+
 /**
  * idpf_tx_maybe_stop_splitq - 1st level check for Tx splitq stop conditions
  * @tx_q: the queue to be checked
@@ -2142,29 +2155,11 @@ void idpf_tx_splitq_build_flow_desc(union idpf_tx_flex_desc *desc,
 static int idpf_tx_maybe_stop_splitq(struct idpf_tx_queue *tx_q,
 				     unsigned int descs_needed)
 {
-	if (idpf_tx_maybe_stop_common(tx_q, descs_needed))
-		goto out;
-
-	/* If there are too many outstanding completions expected on the
-	 * completion queue, stop the TX queue to give the device some time to
-	 * catch up
-	 */
-	if (unlikely(IDPF_TX_COMPLQ_PENDING(tx_q->txq_grp) >
-		     IDPF_TX_COMPLQ_OVERFLOW_THRESH(tx_q->txq_grp->complq)))
-		goto splitq_stop;
-
-	/* Also check for available book keeping buffers; if we are low, stop
-	 * the queue to wait for more completions
-	 */
-	if (unlikely(IDPF_TX_BUF_RSV_LOW(tx_q)))
-		goto splitq_stop;
-
-	return 0;
-
-splitq_stop:
-	netif_stop_subqueue(tx_q->netdev, tx_q->idx);
+	if (netif_subqueue_maybe_stop(tx_q->netdev, tx_q->idx,
+				      idpf_txq_has_room(tx_q, descs_needed),
+				      1, 1))
+		return 0;
 
-out:
 	u64_stats_update_begin(&tx_q->stats_sync);
 	u64_stats_inc(&tx_q->q_stats.q_busy);
 	u64_stats_update_end(&tx_q->stats_sync);
@@ -2190,12 +2185,6 @@ void idpf_tx_buf_hw_update(struct idpf_tx_queue *tx_q, u32 val,
 	nq = netdev_get_tx_queue(tx_q->netdev, tx_q->idx);
 	tx_q->next_to_use = val;
 
-	if (idpf_tx_maybe_stop_common(tx_q, IDPF_TX_DESC_NEEDED)) {
-		u64_stats_update_begin(&tx_q->stats_sync);
-		u64_stats_inc(&tx_q->q_stats.q_busy);
-		u64_stats_update_end(&tx_q->stats_sync);
-	}
-
 	/* Force memory writes to complete before letting h/w
 	 * know there are new descriptors to fetch.  (Only
 	 * applicable for weak-ordered memory model archs,
@@ -3008,14 +2997,11 @@ static int idpf_rx_rsc(struct idpf_rx_queue *rxq, struct sk_buff *skb,
 		return -EINVAL;
 
 	rsc_segments = DIV_ROUND_UP(skb->data_len, rsc_seg_len);
-	if (unlikely(rsc_segments == 1))
-		return 0;
 
 	NAPI_GRO_CB(skb)->count = rsc_segments;
 	skb_shinfo(skb)->gso_size = rsc_seg_len;
 
 	skb_reset_network_header(skb);
-	len = skb->len - skb_transport_offset(skb);
 
 	if (ipv4) {
 		struct iphdr *ipv4h = ip_hdr(skb);
@@ -3024,6 +3010,7 @@ static int idpf_rx_rsc(struct idpf_rx_queue *rxq, struct sk_buff *skb,
 
 		/* Reset and set transport header offset in skb */
 		skb_set_transport_header(skb, sizeof(struct iphdr));
+		len = skb->len - skb_transport_offset(skb);
 
 		/* Compute the TCP pseudo header checksum*/
 		tcp_hdr(skb)->check =
@@ -3033,6 +3020,7 @@ static int idpf_rx_rsc(struct idpf_rx_queue *rxq, struct sk_buff *skb,
 
 		skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6;
 		skb_set_transport_header(skb, sizeof(struct ipv6hdr));
+		len = skb->len - skb_transport_offset(skb);
 		tcp_hdr(skb)->check =
 			~tcp_v6_check(len, &ipv6h->saddr, &ipv6h->daddr, 0);
 	}
@@ -3072,6 +3060,7 @@ idpf_rx_process_skb_fields(struct idpf_rx_queue *rxq, struct sk_buff *skb,
 	idpf_rx_hash(rxq, skb, rx_desc, decoded);
 
 	skb->protocol = eth_type_trans(skb, rxq->netdev);
+	skb_record_rx_queue(skb, rxq->idx);
 
 	if (le16_get_bits(rx_desc->hdrlen_flags,
 			  VIRTCHNL2_RX_FLEX_DESC_ADV_RSC_M))
@@ -3080,8 +3069,6 @@ idpf_rx_process_skb_fields(struct idpf_rx_queue *rxq, struct sk_buff *skb,
 	csum_bits = idpf_rx_splitq_extract_csum_bits(rx_desc);
 	idpf_rx_csum(rxq, skb, csum_bits, decoded);
 
-	skb_record_rx_queue(skb, rxq->idx);
-
 	return 0;
 }
 
@@ -4024,6 +4011,14 @@ static int idpf_vport_splitq_napi_poll(struct napi_struct *napi, int budget)
 		return budget;
 	}
 
+	/* Switch to poll mode in the tear-down path after sending disable
+	 * queues virtchnl message, as the interrupts will be disabled after
+	 * that.
+	 */
+	if (unlikely(q_vector->num_txq && idpf_queue_has(POLL_MODE,
+							 q_vector->tx[0])))
+		return budget;
+
 	work_done = min_t(int, work_done, budget - 1);
 
 	/* Exit the polling mode, but don't re-enable interrupts if stack might
@@ -4034,15 +4029,7 @@ static int idpf_vport_splitq_napi_poll(struct napi_struct *napi, int budget)
 	else
 		idpf_vport_intr_set_wb_on_itr(q_vector);
 
-	/* Switch to poll mode in the tear-down path after sending disable
-	 * queues virtchnl message, as the interrupts will be disabled after
-	 * that
-	 */
-	if (unlikely(q_vector->num_txq && idpf_queue_has(POLL_MODE,
-							 q_vector->tx[0])))
-		return budget;
-	else
-		return work_done;
+	return work_done;
 }
 
 /**
@@ -4203,9 +4190,13 @@ static void idpf_vport_intr_napi_add_all(struct idpf_vport *vport)
 int idpf_vport_intr_alloc(struct idpf_vport *vport)
 {
 	u16 txqs_per_vector, rxqs_per_vector, bufqs_per_vector;
+	struct idpf_vport_user_config_data *user_config;
 	struct idpf_q_vector *q_vector;
+	struct idpf_q_coalesce *q_coal;
 	u32 complqs_per_vector, v_idx;
+	u16 idx = vport->idx;
 
+	user_config = &vport->adapter->vport_config[idx]->user_config;
 	vport->q_vectors = kcalloc(vport->num_q_vectors,
 				   sizeof(struct idpf_q_vector), GFP_KERNEL);
 	if (!vport->q_vectors)
@@ -4223,14 +4214,15 @@ int idpf_vport_intr_alloc(struct idpf_vport *vport)
 
 	for (v_idx = 0; v_idx < vport->num_q_vectors; v_idx++) {
 		q_vector = &vport->q_vectors[v_idx];
+		q_coal = &user_config->q_coalesce[v_idx];
 		q_vector->vport = vport;
 
-		q_vector->tx_itr_value = IDPF_ITR_TX_DEF;
-		q_vector->tx_intr_mode = IDPF_ITR_DYNAMIC;
+		q_vector->tx_itr_value = q_coal->tx_coalesce_usecs;
+		q_vector->tx_intr_mode = q_coal->tx_intr_mode;
 		q_vector->tx_itr_idx = VIRTCHNL2_ITR_IDX_1;
 
-		q_vector->rx_itr_value = IDPF_ITR_RX_DEF;
-		q_vector->rx_intr_mode = IDPF_ITR_DYNAMIC;
+		q_vector->rx_itr_value = q_coal->rx_coalesce_usecs;
+		q_vector->rx_intr_mode = q_coal->rx_intr_mode;
 		q_vector->rx_itr_idx = VIRTCHNL2_ITR_IDX_0;
 
 		if (!zalloc_cpumask_var(&q_vector->affinity_mask, GFP_KERNEL))
diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.h b/drivers/net/ethernet/intel/idpf/idpf_txrx.h
index f0537826f840..ffeeaede6cf8 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.h
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.h
@@ -438,7 +438,8 @@ struct idpf_q_vector {
 	__cacheline_group_end_aligned(cold);
 };
 libeth_cacheline_set_assert(struct idpf_q_vector, 112,
-			    424 + 2 * sizeof(struct dim),
+			    24 + sizeof(struct napi_struct) +
+			    2 * sizeof(struct dim),
 			    8 + sizeof(cpumask_var_t));
 
 struct idpf_rx_queue_stats {
@@ -1051,12 +1052,4 @@ bool idpf_rx_singleq_buf_hw_alloc_all(struct idpf_rx_queue *rxq,
 				      u16 cleaned_count);
 int idpf_tso(struct sk_buff *skb, struct idpf_tx_offload_params *off);
 
-static inline bool idpf_tx_maybe_stop_common(struct idpf_tx_queue *tx_q,
-					     u32 needed)
-{
-	return !netif_subqueue_maybe_stop(tx_q->netdev, tx_q->idx,
-					  IDPF_DESC_UNUSED(tx_q),
-					  needed, needed);
-}
-
 #endif /* !_IDPF_TXRX_H_ */
diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
index d46c95f91b0d..151beea20d34 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
@@ -376,7 +376,7 @@ static void idpf_vc_xn_init(struct idpf_vc_xn_manager *vcxn_mngr)
  * All waiting threads will be woken-up and their transaction aborted. Further
  * operations on that object will fail.
  */
-static void idpf_vc_xn_shutdown(struct idpf_vc_xn_manager *vcxn_mngr)
+void idpf_vc_xn_shutdown(struct idpf_vc_xn_manager *vcxn_mngr)
 {
 	int i;
 
@@ -612,14 +612,15 @@ idpf_vc_xn_forward_reply(struct idpf_adapter *adapter,
 		return -EINVAL;
 	}
 	xn = &adapter->vcxn_mngr->ring[xn_idx];
+	idpf_vc_xn_lock(xn);
 	salt = FIELD_GET(IDPF_VC_XN_SALT_M, msg_info);
 	if (xn->salt != salt) {
 		dev_err_ratelimited(&adapter->pdev->dev, "Transaction salt does not match (%02x != %02x)\n",
 				    xn->salt, salt);
+		idpf_vc_xn_unlock(xn);
 		return -EINVAL;
 	}
 
-	idpf_vc_xn_lock(xn);
 	switch (xn->state) {
 	case IDPF_VC_XN_WAITING:
 		/* success */
@@ -3077,12 +3078,21 @@ init_failed:
  */
 void idpf_vc_core_deinit(struct idpf_adapter *adapter)
 {
+	bool remove_in_prog;
+
 	if (!test_bit(IDPF_VC_CORE_INIT, adapter->flags))
 		return;
 
+	/* Avoid transaction timeouts when called during reset */
+	remove_in_prog = test_bit(IDPF_REMOVE_IN_PROG, adapter->flags);
+	if (!remove_in_prog)
+		idpf_vc_xn_shutdown(adapter->vcxn_mngr);
+
 	idpf_deinit_task(adapter);
 	idpf_intr_rel(adapter);
-	idpf_vc_xn_shutdown(adapter->vcxn_mngr);
+
+	if (remove_in_prog)
+		idpf_vc_xn_shutdown(adapter->vcxn_mngr);
 
 	cancel_delayed_work_sync(&adapter->serv_task);
 	cancel_delayed_work_sync(&adapter->mbx_task);
diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.h b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.h
index 83da5d8da56b..23271cf0a216 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.h
+++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.h
@@ -66,5 +66,6 @@ int idpf_send_get_stats_msg(struct idpf_vport *vport);
 int idpf_send_set_sriov_vfs_msg(struct idpf_adapter *adapter, u16 num_vfs);
 int idpf_send_get_set_rss_key_msg(struct idpf_vport *vport, bool get);
 int idpf_send_get_set_rss_lut_msg(struct idpf_vport *vport, bool get);
+void idpf_vc_xn_shutdown(struct idpf_vc_xn_manager *vcxn_mngr);
 
 #endif /* _IDPF_VIRTCHNL_H_ */
diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h
index eac0f966e0e4..323db1e2be38 100644
--- a/drivers/net/ethernet/intel/igc/igc.h
+++ b/drivers/net/ethernet/intel/igc/igc.h
@@ -319,6 +319,7 @@ struct igc_adapter {
 	struct timespec64 prev_ptp_time; /* Pre-reset PTP clock */
 	ktime_t ptp_reset_start; /* Reset time in clock mono */
 	struct system_time_snapshot snapshot;
+	struct mutex ptm_lock; /* Only allow one PTM transaction at a time */
 
 	char fw_version[32];
 
diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h
index 8e449904aa7d..d19325b0e6e0 100644
--- a/drivers/net/ethernet/intel/igc/igc_defines.h
+++ b/drivers/net/ethernet/intel/igc/igc_defines.h
@@ -574,7 +574,10 @@
 #define IGC_PTM_CTRL_SHRT_CYC(usec)	(((usec) & 0x3f) << 2)
 #define IGC_PTM_CTRL_PTM_TO(usec)	(((usec) & 0xff) << 8)
 
-#define IGC_PTM_SHORT_CYC_DEFAULT	1   /* Default short cycle interval */
+/* A short cycle time of 1us theoretically should work, but appears to be too
+ * short in practice.
+ */
+#define IGC_PTM_SHORT_CYC_DEFAULT	4   /* Default short cycle interval */
 #define IGC_PTM_CYC_TIME_DEFAULT	5   /* Default PTM cycle time */
 #define IGC_PTM_TIMEOUT_DEFAULT		255 /* Default timeout for PTM errors */
 
@@ -593,6 +596,7 @@
 #define IGC_PTM_STAT_T4M1_OVFL		BIT(3) /* T4 minus T1 overflow */
 #define IGC_PTM_STAT_ADJUST_1ST		BIT(4) /* 1588 timer adjusted during 1st PTM cycle */
 #define IGC_PTM_STAT_ADJUST_CYC		BIT(5) /* 1588 timer adjusted during non-1st PTM cycle */
+#define IGC_PTM_STAT_ALL		GENMASK(5, 0) /* Used to clear all status */
 
 /* PCIe PTM Cycle Control */
 #define IGC_PTM_CYCLE_CTRL_CYC_TIME(msec)	((msec) & 0x3ff) /* PTM Cycle Time (msec) */
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 6e70bca15db1..2a0c5a343e47 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -1096,6 +1096,7 @@ static int igc_init_empty_frame(struct igc_ring *ring,
 		return -ENOMEM;
 	}
 
+	buffer->type = IGC_TX_BUFFER_TYPE_SKB;
 	buffer->skb = skb;
 	buffer->protocol = 0;
 	buffer->bytecount = skb->len;
@@ -2707,8 +2708,9 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget)
 }
 
 static struct sk_buff *igc_construct_skb_zc(struct igc_ring *ring,
-					    struct xdp_buff *xdp)
+					    struct igc_xdp_buff *ctx)
 {
+	struct xdp_buff *xdp = &ctx->xdp;
 	unsigned int totalsize = xdp->data_end - xdp->data_meta;
 	unsigned int metasize = xdp->data - xdp->data_meta;
 	struct sk_buff *skb;
@@ -2727,27 +2729,28 @@ static struct sk_buff *igc_construct_skb_zc(struct igc_ring *ring,
 		__skb_pull(skb, metasize);
 	}
 
+	if (ctx->rx_ts) {
+		skb_shinfo(skb)->tx_flags |= SKBTX_HW_TSTAMP_NETDEV;
+		skb_hwtstamps(skb)->netdev_data = ctx->rx_ts;
+	}
+
 	return skb;
 }
 
 static void igc_dispatch_skb_zc(struct igc_q_vector *q_vector,
 				union igc_adv_rx_desc *desc,
-				struct xdp_buff *xdp,
-				ktime_t timestamp)
+				struct igc_xdp_buff *ctx)
 {
 	struct igc_ring *ring = q_vector->rx.ring;
 	struct sk_buff *skb;
 
-	skb = igc_construct_skb_zc(ring, xdp);
+	skb = igc_construct_skb_zc(ring, ctx);
 	if (!skb) {
 		ring->rx_stats.alloc_failed++;
 		set_bit(IGC_RING_FLAG_RX_ALLOC_FAILED, &ring->flags);
 		return;
 	}
 
-	if (timestamp)
-		skb_hwtstamps(skb)->hwtstamp = timestamp;
-
 	if (igc_cleanup_headers(ring, desc, skb))
 		return;
 
@@ -2783,7 +2786,6 @@ static int igc_clean_rx_irq_zc(struct igc_q_vector *q_vector, const int budget)
 		union igc_adv_rx_desc *desc;
 		struct igc_rx_buffer *bi;
 		struct igc_xdp_buff *ctx;
-		ktime_t timestamp = 0;
 		unsigned int size;
 		int res;
 
@@ -2813,6 +2815,8 @@ static int igc_clean_rx_irq_zc(struct igc_q_vector *q_vector, const int budget)
 			 */
 			bi->xdp->data_meta += IGC_TS_HDR_LEN;
 			size -= IGC_TS_HDR_LEN;
+		} else {
+			ctx->rx_ts = NULL;
 		}
 
 		bi->xdp->data_end = bi->xdp->data + size;
@@ -2821,7 +2825,7 @@ static int igc_clean_rx_irq_zc(struct igc_q_vector *q_vector, const int budget)
 		res = __igc_xdp_run_prog(adapter, prog, bi->xdp);
 		switch (res) {
 		case IGC_XDP_PASS:
-			igc_dispatch_skb_zc(q_vector, desc, bi->xdp, timestamp);
+			igc_dispatch_skb_zc(q_vector, desc, ctx);
 			fallthrough;
 		case IGC_XDP_CONSUMED:
 			xsk_buff_free(bi->xdp);
@@ -6983,6 +6987,10 @@ static int igc_probe(struct pci_dev *pdev,
 	adapter->port_num = hw->bus.func;
 	adapter->msg_enable = netif_msg_init(debug, DEFAULT_MSG_ENABLE);
 
+	/* Disable ASPM L1.2 on I226 devices to avoid packet loss */
+	if (igc_is_device_id_i226(hw))
+		pci_disable_link_state(pdev, PCIE_LINK_STATE_L1_2);
+
 	err = pci_save_state(pdev);
 	if (err)
 		goto err_ioremap;
@@ -7169,6 +7177,7 @@ static int igc_probe(struct pci_dev *pdev,
 
 err_register:
 	igc_release_hw_control(adapter);
+	igc_ptp_stop(adapter);
 err_eeprom:
 	if (!igc_check_reset_block(hw))
 		igc_reset_phy(hw);
@@ -7363,6 +7372,9 @@ static int igc_resume(struct device *dev)
 	pci_enable_wake(pdev, PCI_D3hot, 0);
 	pci_enable_wake(pdev, PCI_D3cold, 0);
 
+	if (igc_is_device_id_i226(hw))
+		pci_disable_link_state(pdev, PCIE_LINK_STATE_L1_2);
+
 	if (igc_init_interrupt_scheme(adapter, true)) {
 		netdev_err(netdev, "Unable to allocate memory for queues\n");
 		return -ENOMEM;
@@ -7475,6 +7487,9 @@ static pci_ers_result_t igc_io_slot_reset(struct pci_dev *pdev)
 		pci_enable_wake(pdev, PCI_D3hot, 0);
 		pci_enable_wake(pdev, PCI_D3cold, 0);
 
+		if (igc_is_device_id_i226(hw))
+			pci_disable_link_state_locked(pdev, PCIE_LINK_STATE_L1_2);
+
 		/* In case of PCI error, adapter loses its HW address
 		 * so we should re-assign it here.
 		 */
diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c
index 946edbad4302..efc7b30e4211 100644
--- a/drivers/net/ethernet/intel/igc/igc_ptp.c
+++ b/drivers/net/ethernet/intel/igc/igc_ptp.c
@@ -974,45 +974,62 @@ static void igc_ptm_log_error(struct igc_adapter *adapter, u32 ptm_stat)
 	}
 }
 
+/* The PTM lock: adapter->ptm_lock must be held when calling igc_ptm_trigger() */
+static void igc_ptm_trigger(struct igc_hw *hw)
+{
+	u32 ctrl;
+
+	/* To "manually" start the PTM cycle we need to set the
+	 * trigger (TRIG) bit
+	 */
+	ctrl = rd32(IGC_PTM_CTRL);
+	ctrl |= IGC_PTM_CTRL_TRIG;
+	wr32(IGC_PTM_CTRL, ctrl);
+	/* Perform flush after write to CTRL register otherwise
+	 * transaction may not start
+	 */
+	wrfl();
+}
+
+/* The PTM lock: adapter->ptm_lock must be held when calling igc_ptm_reset() */
+static void igc_ptm_reset(struct igc_hw *hw)
+{
+	u32 ctrl;
+
+	ctrl = rd32(IGC_PTM_CTRL);
+	ctrl &= ~IGC_PTM_CTRL_TRIG;
+	wr32(IGC_PTM_CTRL, ctrl);
+	/* Write to clear all status */
+	wr32(IGC_PTM_STAT, IGC_PTM_STAT_ALL);
+}
+
 static int igc_phc_get_syncdevicetime(ktime_t *device,
 				      struct system_counterval_t *system,
 				      void *ctx)
 {
-	u32 stat, t2_curr_h, t2_curr_l, ctrl;
 	struct igc_adapter *adapter = ctx;
 	struct igc_hw *hw = &adapter->hw;
+	u32 stat, t2_curr_h, t2_curr_l;
 	int err, count = 100;
 	ktime_t t1, t2_curr;
 
-	/* Get a snapshot of system clocks to use as historic value. */
-	ktime_get_snapshot(&adapter->snapshot);
-
+	/* Doing this in a loop because in the event of a
+	 * badly timed (ha!) system clock adjustment, we may
+	 * get PTM errors from the PCI root, but these errors
+	 * are transitory. Repeating the process returns valid
+	 * data eventually.
+	 */
 	do {
-		/* Doing this in a loop because in the event of a
-		 * badly timed (ha!) system clock adjustment, we may
-		 * get PTM errors from the PCI root, but these errors
-		 * are transitory. Repeating the process returns valid
-		 * data eventually.
-		 */
+		/* Get a snapshot of system clocks to use as historic value. */
+		ktime_get_snapshot(&adapter->snapshot);
 
-		/* To "manually" start the PTM cycle we need to clear and
-		 * then set again the TRIG bit.
-		 */
-		ctrl = rd32(IGC_PTM_CTRL);
-		ctrl &= ~IGC_PTM_CTRL_TRIG;
-		wr32(IGC_PTM_CTRL, ctrl);
-		ctrl |= IGC_PTM_CTRL_TRIG;
-		wr32(IGC_PTM_CTRL, ctrl);
-
-		/* The cycle only starts "for real" when software notifies
-		 * that it has read the registers, this is done by setting
-		 * VALID bit.
-		 */
-		wr32(IGC_PTM_STAT, IGC_PTM_STAT_VALID);
+		igc_ptm_trigger(hw);
 
 		err = readx_poll_timeout(rd32, IGC_PTM_STAT, stat,
 					 stat, IGC_PTM_STAT_SLEEP,
 					 IGC_PTM_STAT_TIMEOUT);
+		igc_ptm_reset(hw);
+
 		if (err < 0) {
 			netdev_err(adapter->netdev, "Timeout reading IGC_PTM_STAT register\n");
 			return err;
@@ -1021,15 +1038,7 @@ static int igc_phc_get_syncdevicetime(ktime_t *device,
 		if ((stat & IGC_PTM_STAT_VALID) == IGC_PTM_STAT_VALID)
 			break;
 
-		if (stat & ~IGC_PTM_STAT_VALID) {
-			/* An error occurred, log it. */
-			igc_ptm_log_error(adapter, stat);
-			/* The STAT register is write-1-to-clear (W1C),
-			 * so write the previous error status to clear it.
-			 */
-			wr32(IGC_PTM_STAT, stat);
-			continue;
-		}
+		igc_ptm_log_error(adapter, stat);
 	} while (--count);
 
 	if (!count) {
@@ -1061,9 +1070,16 @@ static int igc_ptp_getcrosststamp(struct ptp_clock_info *ptp,
 {
 	struct igc_adapter *adapter = container_of(ptp, struct igc_adapter,
 						   ptp_caps);
+	int ret;
+
+	/* This blocks until any in progress PTM transactions complete */
+	mutex_lock(&adapter->ptm_lock);
+
+	ret = get_device_system_crosststamp(igc_phc_get_syncdevicetime,
+					    adapter, &adapter->snapshot, cts);
+	mutex_unlock(&adapter->ptm_lock);
 
-	return get_device_system_crosststamp(igc_phc_get_syncdevicetime,
-					     adapter, &adapter->snapshot, cts);
+	return ret;
 }
 
 static int igc_ptp_getcyclesx64(struct ptp_clock_info *ptp,
@@ -1162,6 +1178,7 @@ void igc_ptp_init(struct igc_adapter *adapter)
 	spin_lock_init(&adapter->ptp_tx_lock);
 	spin_lock_init(&adapter->free_timer_lock);
 	spin_lock_init(&adapter->tmreg_lock);
+	mutex_init(&adapter->ptm_lock);
 
 	adapter->tstamp_config.rx_filter = HWTSTAMP_FILTER_NONE;
 	adapter->tstamp_config.tx_type = HWTSTAMP_TX_OFF;
@@ -1174,6 +1191,7 @@ void igc_ptp_init(struct igc_adapter *adapter)
 	if (IS_ERR(adapter->ptp_clock)) {
 		adapter->ptp_clock = NULL;
 		netdev_err(netdev, "ptp_clock_register failed\n");
+		mutex_destroy(&adapter->ptm_lock);
 	} else if (adapter->ptp_clock) {
 		netdev_info(netdev, "PHC added\n");
 		adapter->ptp_flags |= IGC_PTP_ENABLED;
@@ -1203,10 +1221,12 @@ static void igc_ptm_stop(struct igc_adapter *adapter)
 	struct igc_hw *hw = &adapter->hw;
 	u32 ctrl;
 
+	mutex_lock(&adapter->ptm_lock);
 	ctrl = rd32(IGC_PTM_CTRL);
 	ctrl &= ~IGC_PTM_CTRL_EN;
 
 	wr32(IGC_PTM_CTRL, ctrl);
+	mutex_unlock(&adapter->ptm_lock);
 }
 
 /**
@@ -1237,13 +1257,18 @@ void igc_ptp_suspend(struct igc_adapter *adapter)
  **/
 void igc_ptp_stop(struct igc_adapter *adapter)
 {
+	if (!(adapter->ptp_flags & IGC_PTP_ENABLED))
+		return;
+
 	igc_ptp_suspend(adapter);
 
+	adapter->ptp_flags &= ~IGC_PTP_ENABLED;
 	if (adapter->ptp_clock) {
 		ptp_clock_unregister(adapter->ptp_clock);
 		netdev_info(adapter->netdev, "PHC removed\n");
 		adapter->ptp_flags &= ~IGC_PTP_ENABLED;
 	}
+	mutex_destroy(&adapter->ptm_lock);
 }
 
 /**
@@ -1255,13 +1280,18 @@ void igc_ptp_stop(struct igc_adapter *adapter)
 void igc_ptp_reset(struct igc_adapter *adapter)
 {
 	struct igc_hw *hw = &adapter->hw;
-	u32 cycle_ctrl, ctrl;
+	u32 cycle_ctrl, ctrl, stat;
 	unsigned long flags;
 	u32 timadj;
 
+	if (!(adapter->ptp_flags & IGC_PTP_ENABLED))
+		return;
+
 	/* reset the tstamp_config */
 	igc_ptp_set_timestamp_mode(adapter, &adapter->tstamp_config);
 
+	mutex_lock(&adapter->ptm_lock);
+
 	spin_lock_irqsave(&adapter->tmreg_lock, flags);
 
 	switch (adapter->hw.mac.type) {
@@ -1290,14 +1320,19 @@ void igc_ptp_reset(struct igc_adapter *adapter)
 		ctrl = IGC_PTM_CTRL_EN |
 			IGC_PTM_CTRL_START_NOW |
 			IGC_PTM_CTRL_SHRT_CYC(IGC_PTM_SHORT_CYC_DEFAULT) |
-			IGC_PTM_CTRL_PTM_TO(IGC_PTM_TIMEOUT_DEFAULT) |
-			IGC_PTM_CTRL_TRIG;
+			IGC_PTM_CTRL_PTM_TO(IGC_PTM_TIMEOUT_DEFAULT);
 
 		wr32(IGC_PTM_CTRL, ctrl);
 
 		/* Force the first cycle to run. */
-		wr32(IGC_PTM_STAT, IGC_PTM_STAT_VALID);
+		igc_ptm_trigger(hw);
 
+		if (readx_poll_timeout_atomic(rd32, IGC_PTM_STAT, stat,
+					      stat, IGC_PTM_STAT_SLEEP,
+					      IGC_PTM_STAT_TIMEOUT))
+			netdev_err(adapter->netdev, "Timeout reading IGC_PTM_STAT register\n");
+
+		igc_ptm_reset(hw);
 		break;
 	default:
 		/* No work to do. */
@@ -1314,5 +1349,7 @@ void igc_ptp_reset(struct igc_adapter *adapter)
 out:
 	spin_unlock_irqrestore(&adapter->tmreg_lock, flags);
 
+	mutex_unlock(&adapter->ptm_lock);
+
 	wrfl();
 }
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
index 559b443c409f..c1f29296c1d5 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
@@ -503,9 +503,10 @@ struct ixgbe_q_vector {
 	struct ixgbe_ring_container rx, tx;
 
 	struct napi_struct napi;
+	struct rcu_head rcu;	/* to avoid race with update stats on free */
+
 	cpumask_t affinity_mask;
 	int numa_node;
-	struct rcu_head rcu;	/* to avoid race with update stats on free */
 	char name[IFNAMSIZ + 9];
 
 	/* for dynamic allocation of rings associated with this q_vector */
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c
index 07eaa3c3f4d3..530e4319a2e8 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c
@@ -167,7 +167,7 @@ int ixgbe_write_i2c_combined_generic_int(struct ixgbe_hw *hw, u8 addr,
 					 u16 reg, u16 val, bool lock)
 {
 	u32 swfw_mask = hw->phy.phy_semaphore_mask;
-	int max_retry = 1;
+	int max_retry = 3;
 	int retry = 0;
 	u8 reg_high;
 	u8 csum;
@@ -2284,7 +2284,7 @@ static int ixgbe_write_i2c_byte_generic_int(struct ixgbe_hw *hw, u8 byte_offset,
 					    u8 dev_addr, u8 data, bool lock)
 {
 	u32 swfw_mask = hw->phy.phy_semaphore_mask;
-	u32 max_retry = 1;
+	u32 max_retry = 3;
 	u32 retry = 0;
 	int status;
 
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
index 9e02e4367bec..9bd3d76b5fe2 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
@@ -1108,6 +1108,9 @@ struct mvpp2 {
 
 	/* Spinlocks for CM3 shared memory configuration */
 	spinlock_t mss_spinlock;
+
+	/* Spinlock for shared PRS parser memory and shadow table */
+	spinlock_t prs_spinlock;
 };
 
 struct mvpp2_pcpu_stats {
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
index 1641791a2d5b..8ed83fb98862 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
@@ -324,7 +324,7 @@ static const struct mvpp2_cls_flow cls_flows[MVPP2_N_PRS_FLOWS] = {
 		       MVPP2_PRS_RI_VLAN_MASK),
 	/* Non IP flow, with vlan tag */
 	MVPP2_DEF_FLOW(MVPP22_FLOW_ETHERNET, MVPP2_FL_NON_IP_TAG,
-		       MVPP22_CLS_HEK_OPT_VLAN,
+		       MVPP22_CLS_HEK_TAGGED,
 		       0, 0),
 };
 
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index 3880dcc0418b..66b5a80c9c28 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -7640,8 +7640,9 @@ static int mvpp2_probe(struct platform_device *pdev)
 	if (mvpp2_read(priv, MVPP2_VER_ID_REG) == MVPP2_VER_PP23)
 		priv->hw_version = MVPP23;
 
-	/* Init mss lock */
+	/* Init locks for shared packet processor resources */
 	spin_lock_init(&priv->mss_spinlock);
+	spin_lock_init(&priv->prs_spinlock);
 
 	/* Initialize network controller */
 	err = mvpp2_init(pdev, priv);
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c
index 9af22f497a40..93e978bdf303 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c
@@ -23,6 +23,8 @@ static int mvpp2_prs_hw_write(struct mvpp2 *priv, struct mvpp2_prs_entry *pe)
 {
 	int i;
 
+	lockdep_assert_held(&priv->prs_spinlock);
+
 	if (pe->index > MVPP2_PRS_TCAM_SRAM_SIZE - 1)
 		return -EINVAL;
 
@@ -43,11 +45,13 @@ static int mvpp2_prs_hw_write(struct mvpp2 *priv, struct mvpp2_prs_entry *pe)
 }
 
 /* Initialize tcam entry from hw */
-int mvpp2_prs_init_from_hw(struct mvpp2 *priv, struct mvpp2_prs_entry *pe,
-			   int tid)
+static int __mvpp2_prs_init_from_hw(struct mvpp2 *priv,
+				    struct mvpp2_prs_entry *pe, int tid)
 {
 	int i;
 
+	lockdep_assert_held(&priv->prs_spinlock);
+
 	if (tid > MVPP2_PRS_TCAM_SRAM_SIZE - 1)
 		return -EINVAL;
 
@@ -73,6 +77,18 @@ int mvpp2_prs_init_from_hw(struct mvpp2 *priv, struct mvpp2_prs_entry *pe,
 	return 0;
 }
 
+int mvpp2_prs_init_from_hw(struct mvpp2 *priv, struct mvpp2_prs_entry *pe,
+			   int tid)
+{
+	int err;
+
+	spin_lock_bh(&priv->prs_spinlock);
+	err = __mvpp2_prs_init_from_hw(priv, pe, tid);
+	spin_unlock_bh(&priv->prs_spinlock);
+
+	return err;
+}
+
 /* Invalidate tcam hw entry */
 static void mvpp2_prs_hw_inv(struct mvpp2 *priv, int index)
 {
@@ -374,7 +390,7 @@ static int mvpp2_prs_flow_find(struct mvpp2 *priv, int flow)
 		    priv->prs_shadow[tid].lu != MVPP2_PRS_LU_FLOWS)
 			continue;
 
-		mvpp2_prs_init_from_hw(priv, &pe, tid);
+		__mvpp2_prs_init_from_hw(priv, &pe, tid);
 		bits = mvpp2_prs_sram_ai_get(&pe);
 
 		/* Sram store classification lookup ID in AI bits [5:0] */
@@ -441,7 +457,7 @@ static void mvpp2_prs_mac_drop_all_set(struct mvpp2 *priv, int port, bool add)
 
 	if (priv->prs_shadow[MVPP2_PE_DROP_ALL].valid) {
 		/* Entry exist - update port only */
-		mvpp2_prs_init_from_hw(priv, &pe, MVPP2_PE_DROP_ALL);
+		__mvpp2_prs_init_from_hw(priv, &pe, MVPP2_PE_DROP_ALL);
 	} else {
 		/* Entry doesn't exist - create new */
 		memset(&pe, 0, sizeof(pe));
@@ -469,14 +485,17 @@ static void mvpp2_prs_mac_drop_all_set(struct mvpp2 *priv, int port, bool add)
 }
 
 /* Set port to unicast or multicast promiscuous mode */
-void mvpp2_prs_mac_promisc_set(struct mvpp2 *priv, int port,
-			       enum mvpp2_prs_l2_cast l2_cast, bool add)
+static void __mvpp2_prs_mac_promisc_set(struct mvpp2 *priv, int port,
+					enum mvpp2_prs_l2_cast l2_cast,
+					bool add)
 {
 	struct mvpp2_prs_entry pe;
 	unsigned char cast_match;
 	unsigned int ri;
 	int tid;
 
+	lockdep_assert_held(&priv->prs_spinlock);
+
 	if (l2_cast == MVPP2_PRS_L2_UNI_CAST) {
 		cast_match = MVPP2_PRS_UCAST_VAL;
 		tid = MVPP2_PE_MAC_UC_PROMISCUOUS;
@@ -489,7 +508,7 @@ void mvpp2_prs_mac_promisc_set(struct mvpp2 *priv, int port,
 
 	/* promiscuous mode - Accept unknown unicast or multicast packets */
 	if (priv->prs_shadow[tid].valid) {
-		mvpp2_prs_init_from_hw(priv, &pe, tid);
+		__mvpp2_prs_init_from_hw(priv, &pe, tid);
 	} else {
 		memset(&pe, 0, sizeof(pe));
 		mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_MAC);
@@ -522,6 +541,14 @@ void mvpp2_prs_mac_promisc_set(struct mvpp2 *priv, int port,
 	mvpp2_prs_hw_write(priv, &pe);
 }
 
+void mvpp2_prs_mac_promisc_set(struct mvpp2 *priv, int port,
+			       enum mvpp2_prs_l2_cast l2_cast, bool add)
+{
+	spin_lock_bh(&priv->prs_spinlock);
+	__mvpp2_prs_mac_promisc_set(priv, port, l2_cast, add);
+	spin_unlock_bh(&priv->prs_spinlock);
+}
+
 /* Set entry for dsa packets */
 static void mvpp2_prs_dsa_tag_set(struct mvpp2 *priv, int port, bool add,
 				  bool tagged, bool extend)
@@ -539,7 +566,7 @@ static void mvpp2_prs_dsa_tag_set(struct mvpp2 *priv, int port, bool add,
 
 	if (priv->prs_shadow[tid].valid) {
 		/* Entry exist - update port only */
-		mvpp2_prs_init_from_hw(priv, &pe, tid);
+		__mvpp2_prs_init_from_hw(priv, &pe, tid);
 	} else {
 		/* Entry doesn't exist - create new */
 		memset(&pe, 0, sizeof(pe));
@@ -610,7 +637,7 @@ static void mvpp2_prs_dsa_tag_ethertype_set(struct mvpp2 *priv, int port,
 
 	if (priv->prs_shadow[tid].valid) {
 		/* Entry exist - update port only */
-		mvpp2_prs_init_from_hw(priv, &pe, tid);
+		__mvpp2_prs_init_from_hw(priv, &pe, tid);
 	} else {
 		/* Entry doesn't exist - create new */
 		memset(&pe, 0, sizeof(pe));
@@ -673,7 +700,7 @@ static int mvpp2_prs_vlan_find(struct mvpp2 *priv, unsigned short tpid, int ai)
 		    priv->prs_shadow[tid].lu != MVPP2_PRS_LU_VLAN)
 			continue;
 
-		mvpp2_prs_init_from_hw(priv, &pe, tid);
+		__mvpp2_prs_init_from_hw(priv, &pe, tid);
 		match = mvpp2_prs_tcam_data_cmp(&pe, 0, tpid);
 		if (!match)
 			continue;
@@ -726,7 +753,7 @@ static int mvpp2_prs_vlan_add(struct mvpp2 *priv, unsigned short tpid, int ai,
 			    priv->prs_shadow[tid_aux].lu != MVPP2_PRS_LU_VLAN)
 				continue;
 
-			mvpp2_prs_init_from_hw(priv, &pe, tid_aux);
+			__mvpp2_prs_init_from_hw(priv, &pe, tid_aux);
 			ri_bits = mvpp2_prs_sram_ri_get(&pe);
 			if ((ri_bits & MVPP2_PRS_RI_VLAN_MASK) ==
 			    MVPP2_PRS_RI_VLAN_DOUBLE)
@@ -760,7 +787,7 @@ static int mvpp2_prs_vlan_add(struct mvpp2 *priv, unsigned short tpid, int ai,
 
 		mvpp2_prs_shadow_set(priv, pe.index, MVPP2_PRS_LU_VLAN);
 	} else {
-		mvpp2_prs_init_from_hw(priv, &pe, tid);
+		__mvpp2_prs_init_from_hw(priv, &pe, tid);
 	}
 	/* Update ports' mask */
 	mvpp2_prs_tcam_port_map_set(&pe, port_map);
@@ -800,7 +827,7 @@ static int mvpp2_prs_double_vlan_find(struct mvpp2 *priv, unsigned short tpid1,
 		    priv->prs_shadow[tid].lu != MVPP2_PRS_LU_VLAN)
 			continue;
 
-		mvpp2_prs_init_from_hw(priv, &pe, tid);
+		__mvpp2_prs_init_from_hw(priv, &pe, tid);
 
 		match = mvpp2_prs_tcam_data_cmp(&pe, 0, tpid1) &&
 			mvpp2_prs_tcam_data_cmp(&pe, 4, tpid2);
@@ -849,7 +876,7 @@ static int mvpp2_prs_double_vlan_add(struct mvpp2 *priv, unsigned short tpid1,
 			    priv->prs_shadow[tid_aux].lu != MVPP2_PRS_LU_VLAN)
 				continue;
 
-			mvpp2_prs_init_from_hw(priv, &pe, tid_aux);
+			__mvpp2_prs_init_from_hw(priv, &pe, tid_aux);
 			ri_bits = mvpp2_prs_sram_ri_get(&pe);
 			ri_bits &= MVPP2_PRS_RI_VLAN_MASK;
 			if (ri_bits == MVPP2_PRS_RI_VLAN_SINGLE ||
@@ -880,7 +907,7 @@ static int mvpp2_prs_double_vlan_add(struct mvpp2 *priv, unsigned short tpid1,
 
 		mvpp2_prs_shadow_set(priv, pe.index, MVPP2_PRS_LU_VLAN);
 	} else {
-		mvpp2_prs_init_from_hw(priv, &pe, tid);
+		__mvpp2_prs_init_from_hw(priv, &pe, tid);
 	}
 
 	/* Update ports' mask */
@@ -1213,8 +1240,8 @@ static void mvpp2_prs_mac_init(struct mvpp2 *priv)
 	/* Create dummy entries for drop all and promiscuous modes */
 	mvpp2_prs_drop_fc(priv);
 	mvpp2_prs_mac_drop_all_set(priv, 0, false);
-	mvpp2_prs_mac_promisc_set(priv, 0, MVPP2_PRS_L2_UNI_CAST, false);
-	mvpp2_prs_mac_promisc_set(priv, 0, MVPP2_PRS_L2_MULTI_CAST, false);
+	__mvpp2_prs_mac_promisc_set(priv, 0, MVPP2_PRS_L2_UNI_CAST, false);
+	__mvpp2_prs_mac_promisc_set(priv, 0, MVPP2_PRS_L2_MULTI_CAST, false);
 }
 
 /* Set default entries for various types of dsa packets */
@@ -1533,12 +1560,6 @@ static int mvpp2_prs_vlan_init(struct platform_device *pdev, struct mvpp2 *priv)
 	struct mvpp2_prs_entry pe;
 	int err;
 
-	priv->prs_double_vlans = devm_kcalloc(&pdev->dev, sizeof(bool),
-					      MVPP2_PRS_DBL_VLANS_MAX,
-					      GFP_KERNEL);
-	if (!priv->prs_double_vlans)
-		return -ENOMEM;
-
 	/* Double VLAN: 0x88A8, 0x8100 */
 	err = mvpp2_prs_double_vlan_add(priv, ETH_P_8021AD, ETH_P_8021Q,
 					MVPP2_PRS_PORT_MASK);
@@ -1941,7 +1962,7 @@ static int mvpp2_prs_vid_range_find(struct mvpp2_port *port, u16 vid, u16 mask)
 		    port->priv->prs_shadow[tid].lu != MVPP2_PRS_LU_VID)
 			continue;
 
-		mvpp2_prs_init_from_hw(port->priv, &pe, tid);
+		__mvpp2_prs_init_from_hw(port->priv, &pe, tid);
 
 		mvpp2_prs_tcam_data_byte_get(&pe, 2, &byte[0], &enable[0]);
 		mvpp2_prs_tcam_data_byte_get(&pe, 3, &byte[1], &enable[1]);
@@ -1970,6 +1991,8 @@ int mvpp2_prs_vid_entry_add(struct mvpp2_port *port, u16 vid)
 
 	memset(&pe, 0, sizeof(pe));
 
+	spin_lock_bh(&priv->prs_spinlock);
+
 	/* Scan TCAM and see if entry with this <vid,port> already exist */
 	tid = mvpp2_prs_vid_range_find(port, vid, mask);
 
@@ -1988,8 +2011,10 @@ int mvpp2_prs_vid_entry_add(struct mvpp2_port *port, u16 vid)
 						MVPP2_PRS_VLAN_FILT_MAX_ENTRY);
 
 		/* There isn't room for a new VID filter */
-		if (tid < 0)
+		if (tid < 0) {
+			spin_unlock_bh(&priv->prs_spinlock);
 			return tid;
+		}
 
 		mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_VID);
 		pe.index = tid;
@@ -1997,7 +2022,7 @@ int mvpp2_prs_vid_entry_add(struct mvpp2_port *port, u16 vid)
 		/* Mask all ports */
 		mvpp2_prs_tcam_port_map_set(&pe, 0);
 	} else {
-		mvpp2_prs_init_from_hw(priv, &pe, tid);
+		__mvpp2_prs_init_from_hw(priv, &pe, tid);
 	}
 
 	/* Enable the current port */
@@ -2019,6 +2044,7 @@ int mvpp2_prs_vid_entry_add(struct mvpp2_port *port, u16 vid)
 	mvpp2_prs_shadow_set(priv, pe.index, MVPP2_PRS_LU_VID);
 	mvpp2_prs_hw_write(priv, &pe);
 
+	spin_unlock_bh(&priv->prs_spinlock);
 	return 0;
 }
 
@@ -2028,15 +2054,16 @@ void mvpp2_prs_vid_entry_remove(struct mvpp2_port *port, u16 vid)
 	struct mvpp2 *priv = port->priv;
 	int tid;
 
-	/* Scan TCAM and see if entry with this <vid,port> already exist */
-	tid = mvpp2_prs_vid_range_find(port, vid, 0xfff);
+	spin_lock_bh(&priv->prs_spinlock);
 
-	/* No such entry */
-	if (tid < 0)
-		return;
+	/* Invalidate TCAM entry with this <vid,port>, if it exists */
+	tid = mvpp2_prs_vid_range_find(port, vid, 0xfff);
+	if (tid >= 0) {
+		mvpp2_prs_hw_inv(priv, tid);
+		priv->prs_shadow[tid].valid = false;
+	}
 
-	mvpp2_prs_hw_inv(priv, tid);
-	priv->prs_shadow[tid].valid = false;
+	spin_unlock_bh(&priv->prs_spinlock);
 }
 
 /* Remove all existing VID filters on this port */
@@ -2045,6 +2072,8 @@ void mvpp2_prs_vid_remove_all(struct mvpp2_port *port)
 	struct mvpp2 *priv = port->priv;
 	int tid;
 
+	spin_lock_bh(&priv->prs_spinlock);
+
 	for (tid = MVPP2_PRS_VID_PORT_FIRST(port->id);
 	     tid <= MVPP2_PRS_VID_PORT_LAST(port->id); tid++) {
 		if (priv->prs_shadow[tid].valid) {
@@ -2052,6 +2081,8 @@ void mvpp2_prs_vid_remove_all(struct mvpp2_port *port)
 			priv->prs_shadow[tid].valid = false;
 		}
 	}
+
+	spin_unlock_bh(&priv->prs_spinlock);
 }
 
 /* Remove VID filering entry for this port */
@@ -2060,10 +2091,14 @@ void mvpp2_prs_vid_disable_filtering(struct mvpp2_port *port)
 	unsigned int tid = MVPP2_PRS_VID_PORT_DFLT(port->id);
 	struct mvpp2 *priv = port->priv;
 
+	spin_lock_bh(&priv->prs_spinlock);
+
 	/* Invalidate the guard entry */
 	mvpp2_prs_hw_inv(priv, tid);
 
 	priv->prs_shadow[tid].valid = false;
+
+	spin_unlock_bh(&priv->prs_spinlock);
 }
 
 /* Add guard entry that drops packets when no VID is matched on this port */
@@ -2079,6 +2114,8 @@ void mvpp2_prs_vid_enable_filtering(struct mvpp2_port *port)
 
 	memset(&pe, 0, sizeof(pe));
 
+	spin_lock_bh(&priv->prs_spinlock);
+
 	pe.index = tid;
 
 	reg_val = mvpp2_read(priv, MVPP2_MH_REG(port->id));
@@ -2111,6 +2148,8 @@ void mvpp2_prs_vid_enable_filtering(struct mvpp2_port *port)
 	/* Update shadow table */
 	mvpp2_prs_shadow_set(priv, pe.index, MVPP2_PRS_LU_VID);
 	mvpp2_prs_hw_write(priv, &pe);
+
+	spin_unlock_bh(&priv->prs_spinlock);
 }
 
 /* Parser default initialization */
@@ -2118,6 +2157,20 @@ int mvpp2_prs_default_init(struct platform_device *pdev, struct mvpp2 *priv)
 {
 	int err, index, i;
 
+	priv->prs_shadow = devm_kcalloc(&pdev->dev, MVPP2_PRS_TCAM_SRAM_SIZE,
+					sizeof(*priv->prs_shadow),
+					GFP_KERNEL);
+	if (!priv->prs_shadow)
+		return -ENOMEM;
+
+	priv->prs_double_vlans = devm_kcalloc(&pdev->dev, sizeof(bool),
+					      MVPP2_PRS_DBL_VLANS_MAX,
+					      GFP_KERNEL);
+	if (!priv->prs_double_vlans)
+		return -ENOMEM;
+
+	spin_lock_bh(&priv->prs_spinlock);
+
 	/* Enable tcam table */
 	mvpp2_write(priv, MVPP2_PRS_TCAM_CTRL_REG, MVPP2_PRS_TCAM_EN_MASK);
 
@@ -2136,12 +2189,6 @@ int mvpp2_prs_default_init(struct platform_device *pdev, struct mvpp2 *priv)
 	for (index = 0; index < MVPP2_PRS_TCAM_SRAM_SIZE; index++)
 		mvpp2_prs_hw_inv(priv, index);
 
-	priv->prs_shadow = devm_kcalloc(&pdev->dev, MVPP2_PRS_TCAM_SRAM_SIZE,
-					sizeof(*priv->prs_shadow),
-					GFP_KERNEL);
-	if (!priv->prs_shadow)
-		return -ENOMEM;
-
 	/* Always start from lookup = 0 */
 	for (index = 0; index < MVPP2_MAX_PORTS; index++)
 		mvpp2_prs_hw_port_init(priv, index, MVPP2_PRS_LU_MH,
@@ -2158,26 +2205,13 @@ int mvpp2_prs_default_init(struct platform_device *pdev, struct mvpp2 *priv)
 	mvpp2_prs_vid_init(priv);
 
 	err = mvpp2_prs_etype_init(priv);
-	if (err)
-		return err;
-
-	err = mvpp2_prs_vlan_init(pdev, priv);
-	if (err)
-		return err;
-
-	err = mvpp2_prs_pppoe_init(priv);
-	if (err)
-		return err;
-
-	err = mvpp2_prs_ip6_init(priv);
-	if (err)
-		return err;
-
-	err = mvpp2_prs_ip4_init(priv);
-	if (err)
-		return err;
+	err = err ? : mvpp2_prs_vlan_init(pdev, priv);
+	err = err ? : mvpp2_prs_pppoe_init(priv);
+	err = err ? : mvpp2_prs_ip6_init(priv);
+	err = err ? : mvpp2_prs_ip4_init(priv);
 
-	return 0;
+	spin_unlock_bh(&priv->prs_spinlock);
+	return err;
 }
 
 /* Compare MAC DA with tcam entry data */
@@ -2217,7 +2251,7 @@ mvpp2_prs_mac_da_range_find(struct mvpp2 *priv, int pmap, const u8 *da,
 		    (priv->prs_shadow[tid].udf != udf_type))
 			continue;
 
-		mvpp2_prs_init_from_hw(priv, &pe, tid);
+		__mvpp2_prs_init_from_hw(priv, &pe, tid);
 		entry_pmap = mvpp2_prs_tcam_port_map_get(&pe);
 
 		if (mvpp2_prs_mac_range_equals(&pe, da, mask) &&
@@ -2229,7 +2263,8 @@ mvpp2_prs_mac_da_range_find(struct mvpp2 *priv, int pmap, const u8 *da,
 }
 
 /* Update parser's mac da entry */
-int mvpp2_prs_mac_da_accept(struct mvpp2_port *port, const u8 *da, bool add)
+static int __mvpp2_prs_mac_da_accept(struct mvpp2_port *port,
+				     const u8 *da, bool add)
 {
 	unsigned char mask[ETH_ALEN] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
 	struct mvpp2 *priv = port->priv;
@@ -2261,7 +2296,7 @@ int mvpp2_prs_mac_da_accept(struct mvpp2_port *port, const u8 *da, bool add)
 		/* Mask all ports */
 		mvpp2_prs_tcam_port_map_set(&pe, 0);
 	} else {
-		mvpp2_prs_init_from_hw(priv, &pe, tid);
+		__mvpp2_prs_init_from_hw(priv, &pe, tid);
 	}
 
 	mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_MAC);
@@ -2317,6 +2352,17 @@ int mvpp2_prs_mac_da_accept(struct mvpp2_port *port, const u8 *da, bool add)
 	return 0;
 }
 
+int mvpp2_prs_mac_da_accept(struct mvpp2_port *port, const u8 *da, bool add)
+{
+	int err;
+
+	spin_lock_bh(&port->priv->prs_spinlock);
+	err = __mvpp2_prs_mac_da_accept(port, da, add);
+	spin_unlock_bh(&port->priv->prs_spinlock);
+
+	return err;
+}
+
 int mvpp2_prs_update_mac_da(struct net_device *dev, const u8 *da)
 {
 	struct mvpp2_port *port = netdev_priv(dev);
@@ -2345,6 +2391,8 @@ void mvpp2_prs_mac_del_all(struct mvpp2_port *port)
 	unsigned long pmap;
 	int index, tid;
 
+	spin_lock_bh(&priv->prs_spinlock);
+
 	for (tid = MVPP2_PE_MAC_RANGE_START;
 	     tid <= MVPP2_PE_MAC_RANGE_END; tid++) {
 		unsigned char da[ETH_ALEN], da_mask[ETH_ALEN];
@@ -2354,7 +2402,7 @@ void mvpp2_prs_mac_del_all(struct mvpp2_port *port)
 		    (priv->prs_shadow[tid].udf != MVPP2_PRS_UDF_MAC_DEF))
 			continue;
 
-		mvpp2_prs_init_from_hw(priv, &pe, tid);
+		__mvpp2_prs_init_from_hw(priv, &pe, tid);
 
 		pmap = mvpp2_prs_tcam_port_map_get(&pe);
 
@@ -2375,14 +2423,17 @@ void mvpp2_prs_mac_del_all(struct mvpp2_port *port)
 			continue;
 
 		/* Remove entry from TCAM */
-		mvpp2_prs_mac_da_accept(port, da, false);
+		__mvpp2_prs_mac_da_accept(port, da, false);
 	}
+
+	spin_unlock_bh(&priv->prs_spinlock);
 }
 
 int mvpp2_prs_tag_mode_set(struct mvpp2 *priv, int port, int type)
 {
 	switch (type) {
 	case MVPP2_TAG_TYPE_EDSA:
+		spin_lock_bh(&priv->prs_spinlock);
 		/* Add port to EDSA entries */
 		mvpp2_prs_dsa_tag_set(priv, port, true,
 				      MVPP2_PRS_TAGGED, MVPP2_PRS_EDSA);
@@ -2393,9 +2444,11 @@ int mvpp2_prs_tag_mode_set(struct mvpp2 *priv, int port, int type)
 				      MVPP2_PRS_TAGGED, MVPP2_PRS_DSA);
 		mvpp2_prs_dsa_tag_set(priv, port, false,
 				      MVPP2_PRS_UNTAGGED, MVPP2_PRS_DSA);
+		spin_unlock_bh(&priv->prs_spinlock);
 		break;
 
 	case MVPP2_TAG_TYPE_DSA:
+		spin_lock_bh(&priv->prs_spinlock);
 		/* Add port to DSA entries */
 		mvpp2_prs_dsa_tag_set(priv, port, true,
 				      MVPP2_PRS_TAGGED, MVPP2_PRS_DSA);
@@ -2406,10 +2459,12 @@ int mvpp2_prs_tag_mode_set(struct mvpp2 *priv, int port, int type)
 				      MVPP2_PRS_TAGGED, MVPP2_PRS_EDSA);
 		mvpp2_prs_dsa_tag_set(priv, port, false,
 				      MVPP2_PRS_UNTAGGED, MVPP2_PRS_EDSA);
+		spin_unlock_bh(&priv->prs_spinlock);
 		break;
 
 	case MVPP2_TAG_TYPE_MH:
 	case MVPP2_TAG_TYPE_NONE:
+		spin_lock_bh(&priv->prs_spinlock);
 		/* Remove port form EDSA and DSA entries */
 		mvpp2_prs_dsa_tag_set(priv, port, false,
 				      MVPP2_PRS_TAGGED, MVPP2_PRS_DSA);
@@ -2419,6 +2474,7 @@ int mvpp2_prs_tag_mode_set(struct mvpp2 *priv, int port, int type)
 				      MVPP2_PRS_TAGGED, MVPP2_PRS_EDSA);
 		mvpp2_prs_dsa_tag_set(priv, port, false,
 				      MVPP2_PRS_UNTAGGED, MVPP2_PRS_EDSA);
+		spin_unlock_bh(&priv->prs_spinlock);
 		break;
 
 	default:
@@ -2437,11 +2493,15 @@ int mvpp2_prs_add_flow(struct mvpp2 *priv, int flow, u32 ri, u32 ri_mask)
 
 	memset(&pe, 0, sizeof(pe));
 
+	spin_lock_bh(&priv->prs_spinlock);
+
 	tid = mvpp2_prs_tcam_first_free(priv,
 					MVPP2_PE_LAST_FREE_TID,
 					MVPP2_PE_FIRST_FREE_TID);
-	if (tid < 0)
+	if (tid < 0) {
+		spin_unlock_bh(&priv->prs_spinlock);
 		return tid;
+	}
 
 	pe.index = tid;
 
@@ -2461,6 +2521,7 @@ int mvpp2_prs_add_flow(struct mvpp2 *priv, int flow, u32 ri, u32 ri_mask)
 	mvpp2_prs_tcam_port_map_set(&pe, MVPP2_PRS_PORT_MASK);
 	mvpp2_prs_hw_write(priv, &pe);
 
+	spin_unlock_bh(&priv->prs_spinlock);
 	return 0;
 }
 
@@ -2472,6 +2533,8 @@ int mvpp2_prs_def_flow(struct mvpp2_port *port)
 
 	memset(&pe, 0, sizeof(pe));
 
+	spin_lock_bh(&port->priv->prs_spinlock);
+
 	tid = mvpp2_prs_flow_find(port->priv, port->id);
 
 	/* Such entry not exist */
@@ -2480,8 +2543,10 @@ int mvpp2_prs_def_flow(struct mvpp2_port *port)
 		tid = mvpp2_prs_tcam_first_free(port->priv,
 						MVPP2_PE_LAST_FREE_TID,
 					       MVPP2_PE_FIRST_FREE_TID);
-		if (tid < 0)
+		if (tid < 0) {
+			spin_unlock_bh(&port->priv->prs_spinlock);
 			return tid;
+		}
 
 		pe.index = tid;
 
@@ -2492,13 +2557,14 @@ int mvpp2_prs_def_flow(struct mvpp2_port *port)
 		/* Update shadow table */
 		mvpp2_prs_shadow_set(port->priv, pe.index, MVPP2_PRS_LU_FLOWS);
 	} else {
-		mvpp2_prs_init_from_hw(port->priv, &pe, tid);
+		__mvpp2_prs_init_from_hw(port->priv, &pe, tid);
 	}
 
 	mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_FLOWS);
 	mvpp2_prs_tcam_port_map_set(&pe, (1 << port->id));
 	mvpp2_prs_hw_write(port->priv, &pe);
 
+	spin_unlock_bh(&port->priv->prs_spinlock);
 	return 0;
 }
 
@@ -2509,11 +2575,14 @@ int mvpp2_prs_hits(struct mvpp2 *priv, int index)
 	if (index > MVPP2_PRS_TCAM_SRAM_SIZE)
 		return -EINVAL;
 
+	spin_lock_bh(&priv->prs_spinlock);
+
 	mvpp2_write(priv, MVPP2_PRS_TCAM_HIT_IDX_REG, index);
 
 	val = mvpp2_read(priv, MVPP2_PRS_TCAM_HIT_CNT_REG);
 
 	val &= MVPP2_PRS_TCAM_HIT_CNT_MASK;
 
+	spin_unlock_bh(&priv->prs_spinlock);
 	return val;
 }
diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_ethtool.c b/drivers/net/ethernet/marvell/octeon_ep/octep_ethtool.c
index 7d0124b283da..d7a3465e6a72 100644
--- a/drivers/net/ethernet/marvell/octeon_ep/octep_ethtool.c
+++ b/drivers/net/ethernet/marvell/octeon_ep/octep_ethtool.c
@@ -157,17 +157,14 @@ octep_get_ethtool_stats(struct net_device *netdev,
 				    iface_rx_stats,
 				    iface_tx_stats);
 
-	for (q = 0; q < oct->num_oqs; q++) {
-		struct octep_iq *iq = oct->iq[q];
-		struct octep_oq *oq = oct->oq[q];
-
-		tx_packets += iq->stats.instr_completed;
-		tx_bytes += iq->stats.bytes_sent;
-		tx_busy_errors += iq->stats.tx_busy;
-
-		rx_packets += oq->stats.packets;
-		rx_bytes += oq->stats.bytes;
-		rx_alloc_errors += oq->stats.alloc_failures;
+	for (q = 0; q < OCTEP_MAX_QUEUES; q++) {
+		tx_packets += oct->stats_iq[q].instr_completed;
+		tx_bytes += oct->stats_iq[q].bytes_sent;
+		tx_busy_errors += oct->stats_iq[q].tx_busy;
+
+		rx_packets += oct->stats_oq[q].packets;
+		rx_bytes += oct->stats_oq[q].bytes;
+		rx_alloc_errors += oct->stats_oq[q].alloc_failures;
 	}
 	i = 0;
 	data[i++] = rx_packets;
@@ -205,22 +202,18 @@ octep_get_ethtool_stats(struct net_device *netdev,
 	data[i++] = iface_rx_stats->err_pkts;
 
 	/* Per Tx Queue stats */
-	for (q = 0; q < oct->num_iqs; q++) {
-		struct octep_iq *iq = oct->iq[q];
-
-		data[i++] = iq->stats.instr_posted;
-		data[i++] = iq->stats.instr_completed;
-		data[i++] = iq->stats.bytes_sent;
-		data[i++] = iq->stats.tx_busy;
+	for (q = 0; q < OCTEP_MAX_QUEUES; q++) {
+		data[i++] = oct->stats_iq[q].instr_posted;
+		data[i++] = oct->stats_iq[q].instr_completed;
+		data[i++] = oct->stats_iq[q].bytes_sent;
+		data[i++] = oct->stats_iq[q].tx_busy;
 	}
 
 	/* Per Rx Queue stats */
-	for (q = 0; q < oct->num_oqs; q++) {
-		struct octep_oq *oq = oct->oq[q];
-
-		data[i++] = oq->stats.packets;
-		data[i++] = oq->stats.bytes;
-		data[i++] = oq->stats.alloc_failures;
+	for (q = 0; q < OCTEP_MAX_QUEUES; q++) {
+		data[i++] = oct->stats_oq[q].packets;
+		data[i++] = oct->stats_oq[q].bytes;
+		data[i++] = oct->stats_oq[q].alloc_failures;
 	}
 }
 
diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c
index 549436efc204..1b2f5cae0644 100644
--- a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c
+++ b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c
@@ -822,7 +822,7 @@ static inline int octep_iq_full_check(struct octep_iq *iq)
 	if (unlikely(IQ_INSTR_SPACE(iq) >
 		     OCTEP_WAKE_QUEUE_THRESHOLD)) {
 		netif_start_subqueue(iq->netdev, iq->q_no);
-		iq->stats.restart_cnt++;
+		iq->stats->restart_cnt++;
 		return 0;
 	}
 
@@ -960,7 +960,7 @@ static netdev_tx_t octep_start_xmit(struct sk_buff *skb,
 	wmb();
 	/* Ring Doorbell to notify the NIC of new packets */
 	writel(iq->fill_cnt, iq->doorbell_reg);
-	iq->stats.instr_posted += iq->fill_cnt;
+	iq->stats->instr_posted += iq->fill_cnt;
 	iq->fill_cnt = 0;
 	return NETDEV_TX_OK;
 
@@ -991,37 +991,24 @@ dma_map_err:
 static void octep_get_stats64(struct net_device *netdev,
 			      struct rtnl_link_stats64 *stats)
 {
-	u64 tx_packets, tx_bytes, rx_packets, rx_bytes;
 	struct octep_device *oct = netdev_priv(netdev);
+	u64 tx_packets, tx_bytes, rx_packets, rx_bytes;
 	int q;
 
-	if (netif_running(netdev))
-		octep_ctrl_net_get_if_stats(oct,
-					    OCTEP_CTRL_NET_INVALID_VFID,
-					    &oct->iface_rx_stats,
-					    &oct->iface_tx_stats);
-
 	tx_packets = 0;
 	tx_bytes = 0;
 	rx_packets = 0;
 	rx_bytes = 0;
-	for (q = 0; q < oct->num_oqs; q++) {
-		struct octep_iq *iq = oct->iq[q];
-		struct octep_oq *oq = oct->oq[q];
-
-		tx_packets += iq->stats.instr_completed;
-		tx_bytes += iq->stats.bytes_sent;
-		rx_packets += oq->stats.packets;
-		rx_bytes += oq->stats.bytes;
+	for (q = 0; q < OCTEP_MAX_QUEUES; q++) {
+		tx_packets += oct->stats_iq[q].instr_completed;
+		tx_bytes += oct->stats_iq[q].bytes_sent;
+		rx_packets += oct->stats_oq[q].packets;
+		rx_bytes += oct->stats_oq[q].bytes;
 	}
 	stats->tx_packets = tx_packets;
 	stats->tx_bytes = tx_bytes;
 	stats->rx_packets = rx_packets;
 	stats->rx_bytes = rx_bytes;
-	stats->multicast = oct->iface_rx_stats.mcast_pkts;
-	stats->rx_errors = oct->iface_rx_stats.err_pkts;
-	stats->collisions = oct->iface_tx_stats.xscol;
-	stats->tx_fifo_errors = oct->iface_tx_stats.undflw;
 }
 
 /**
@@ -1197,7 +1184,7 @@ static void octep_hb_timeout_task(struct work_struct *work)
 		miss_cnt);
 	rtnl_lock();
 	if (netif_running(oct->netdev))
-		octep_stop(oct->netdev);
+		dev_close(oct->netdev);
 	rtnl_unlock();
 }
 
diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_main.h b/drivers/net/ethernet/marvell/octeon_ep/octep_main.h
index fee59e0e0138..936b786f4281 100644
--- a/drivers/net/ethernet/marvell/octeon_ep/octep_main.h
+++ b/drivers/net/ethernet/marvell/octeon_ep/octep_main.h
@@ -257,11 +257,17 @@ struct octep_device {
 	/* Pointers to Octeon Tx queues */
 	struct octep_iq *iq[OCTEP_MAX_IQ];
 
+	/* Per iq stats */
+	struct octep_iq_stats stats_iq[OCTEP_MAX_IQ];
+
 	/* Rx queues (OQ: Output Queue) */
 	u16 num_oqs;
 	/* Pointers to Octeon Rx queues */
 	struct octep_oq *oq[OCTEP_MAX_OQ];
 
+	/* Per oq stats */
+	struct octep_oq_stats stats_oq[OCTEP_MAX_OQ];
+
 	/* Hardware port number of the PCIe interface */
 	u16 pcie_port;
 
diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_rx.c b/drivers/net/ethernet/marvell/octeon_ep/octep_rx.c
index 8af75cb37c3e..82b6b19e76b4 100644
--- a/drivers/net/ethernet/marvell/octeon_ep/octep_rx.c
+++ b/drivers/net/ethernet/marvell/octeon_ep/octep_rx.c
@@ -87,7 +87,7 @@ static int octep_oq_refill(struct octep_device *oct, struct octep_oq *oq)
 		page = dev_alloc_page();
 		if (unlikely(!page)) {
 			dev_err(oq->dev, "refill: rx buffer alloc failed\n");
-			oq->stats.alloc_failures++;
+			oq->stats->alloc_failures++;
 			break;
 		}
 
@@ -98,7 +98,7 @@ static int octep_oq_refill(struct octep_device *oct, struct octep_oq *oq)
 				"OQ-%d buffer refill: DMA mapping error!\n",
 				oq->q_no);
 			put_page(page);
-			oq->stats.alloc_failures++;
+			oq->stats->alloc_failures++;
 			break;
 		}
 		oq->buff_info[refill_idx].page = page;
@@ -134,6 +134,7 @@ static int octep_setup_oq(struct octep_device *oct, int q_no)
 	oq->netdev = oct->netdev;
 	oq->dev = &oct->pdev->dev;
 	oq->q_no = q_no;
+	oq->stats = &oct->stats_oq[q_no];
 	oq->max_count = CFG_GET_OQ_NUM_DESC(oct->conf);
 	oq->ring_size_mask = oq->max_count - 1;
 	oq->buffer_size = CFG_GET_OQ_BUF_SIZE(oct->conf);
@@ -443,7 +444,7 @@ static int __octep_oq_process_rx(struct octep_device *oct,
 		if (!skb) {
 			octep_oq_drop_rx(oq, buff_info,
 					 &read_idx, &desc_used);
-			oq->stats.alloc_failures++;
+			oq->stats->alloc_failures++;
 			continue;
 		}
 		skb_reserve(skb, data_offset);
@@ -494,8 +495,8 @@ static int __octep_oq_process_rx(struct octep_device *oct,
 
 	oq->host_read_idx = read_idx;
 	oq->refill_count += desc_used;
-	oq->stats.packets += pkt;
-	oq->stats.bytes += rx_bytes;
+	oq->stats->packets += pkt;
+	oq->stats->bytes += rx_bytes;
 
 	return pkt;
 }
diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_rx.h b/drivers/net/ethernet/marvell/octeon_ep/octep_rx.h
index 3b08e2d560dc..b4696c93d0e6 100644
--- a/drivers/net/ethernet/marvell/octeon_ep/octep_rx.h
+++ b/drivers/net/ethernet/marvell/octeon_ep/octep_rx.h
@@ -186,8 +186,8 @@ struct octep_oq {
 	 */
 	u8 __iomem *pkts_sent_reg;
 
-	/* Statistics for this OQ. */
-	struct octep_oq_stats stats;
+	/* Pointer to statistics for this OQ. */
+	struct octep_oq_stats *stats;
 
 	/* Packets pending to be processed */
 	u32 pkts_pending;
diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_tx.c b/drivers/net/ethernet/marvell/octeon_ep/octep_tx.c
index 06851b78aa28..08ee90013fef 100644
--- a/drivers/net/ethernet/marvell/octeon_ep/octep_tx.c
+++ b/drivers/net/ethernet/marvell/octeon_ep/octep_tx.c
@@ -81,9 +81,9 @@ int octep_iq_process_completions(struct octep_iq *iq, u16 budget)
 	}
 
 	iq->pkts_processed += compl_pkts;
-	iq->stats.instr_completed += compl_pkts;
-	iq->stats.bytes_sent += compl_bytes;
-	iq->stats.sgentry_sent += compl_sg;
+	iq->stats->instr_completed += compl_pkts;
+	iq->stats->bytes_sent += compl_bytes;
+	iq->stats->sgentry_sent += compl_sg;
 	iq->flush_index = fi;
 
 	netdev_tx_completed_queue(iq->netdev_q, compl_pkts, compl_bytes);
@@ -187,6 +187,7 @@ static int octep_setup_iq(struct octep_device *oct, int q_no)
 	iq->netdev = oct->netdev;
 	iq->dev = &oct->pdev->dev;
 	iq->q_no = q_no;
+	iq->stats = &oct->stats_iq[q_no];
 	iq->max_count = CFG_GET_IQ_NUM_DESC(oct->conf);
 	iq->ring_size_mask = iq->max_count - 1;
 	iq->fill_threshold = CFG_GET_IQ_DB_MIN(oct->conf);
diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_tx.h b/drivers/net/ethernet/marvell/octeon_ep/octep_tx.h
index 875a2c34091f..58fb39dda977 100644
--- a/drivers/net/ethernet/marvell/octeon_ep/octep_tx.h
+++ b/drivers/net/ethernet/marvell/octeon_ep/octep_tx.h
@@ -170,8 +170,8 @@ struct octep_iq {
 	 */
 	u16 flush_index;
 
-	/* Statistics for this input queue. */
-	struct octep_iq_stats stats;
+	/* Pointer to statistics for this input queue. */
+	struct octep_iq_stats *stats;
 
 	/* Pointer to the Virtual Base addr of the input ring. */
 	struct octep_tx_desc_hw *desc_ring;
diff --git a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_ethtool.c b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_ethtool.c
index a1979b45e355..12ddb77141cc 100644
--- a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_ethtool.c
+++ b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_ethtool.c
@@ -121,12 +121,9 @@ static void octep_vf_get_ethtool_stats(struct net_device *netdev,
 	iface_tx_stats = &oct->iface_tx_stats;
 	iface_rx_stats = &oct->iface_rx_stats;
 
-	for (q = 0; q < oct->num_oqs; q++) {
-		struct octep_vf_iq *iq = oct->iq[q];
-		struct octep_vf_oq *oq = oct->oq[q];
-
-		tx_busy_errors += iq->stats.tx_busy;
-		rx_alloc_errors += oq->stats.alloc_failures;
+	for (q = 0; q < OCTEP_VF_MAX_QUEUES; q++) {
+		tx_busy_errors += oct->stats_iq[q].tx_busy;
+		rx_alloc_errors += oct->stats_oq[q].alloc_failures;
 	}
 	i = 0;
 	data[i++] = rx_alloc_errors;
@@ -141,22 +138,18 @@ static void octep_vf_get_ethtool_stats(struct net_device *netdev,
 	data[i++] = iface_rx_stats->dropped_octets_fifo_full;
 
 	/* Per Tx Queue stats */
-	for (q = 0; q < oct->num_iqs; q++) {
-		struct octep_vf_iq *iq = oct->iq[q];
-
-		data[i++] = iq->stats.instr_posted;
-		data[i++] = iq->stats.instr_completed;
-		data[i++] = iq->stats.bytes_sent;
-		data[i++] = iq->stats.tx_busy;
+	for (q = 0; q < OCTEP_VF_MAX_QUEUES; q++) {
+		data[i++] = oct->stats_iq[q].instr_posted;
+		data[i++] = oct->stats_iq[q].instr_completed;
+		data[i++] = oct->stats_iq[q].bytes_sent;
+		data[i++] = oct->stats_iq[q].tx_busy;
 	}
 
 	/* Per Rx Queue stats */
 	for (q = 0; q < oct->num_oqs; q++) {
-		struct octep_vf_oq *oq = oct->oq[q];
-
-		data[i++] = oq->stats.packets;
-		data[i++] = oq->stats.bytes;
-		data[i++] = oq->stats.alloc_failures;
+		data[i++] = oct->stats_oq[q].packets;
+		data[i++] = oct->stats_oq[q].bytes;
+		data[i++] = oct->stats_oq[q].alloc_failures;
 	}
 }
 
diff --git a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c
index 7e6771c9cdbb..ccb69bc5c952 100644
--- a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c
+++ b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c
@@ -574,7 +574,7 @@ static int octep_vf_iq_full_check(struct octep_vf_iq *iq)
 		  * caused queues to get re-enabled after
 		  * being stopped
 		  */
-		iq->stats.restart_cnt++;
+		iq->stats->restart_cnt++;
 		fallthrough;
 	case 1: /* Queue left enabled, since IQ is not yet full*/
 		return 0;
@@ -731,7 +731,7 @@ ring_dbell:
 	/* Flush the hw descriptors before writing to doorbell */
 	smp_wmb();
 	writel(iq->fill_cnt, iq->doorbell_reg);
-	iq->stats.instr_posted += iq->fill_cnt;
+	iq->stats->instr_posted += iq->fill_cnt;
 	iq->fill_cnt = 0;
 	return NETDEV_TX_OK;
 }
@@ -786,27 +786,16 @@ static void octep_vf_get_stats64(struct net_device *netdev,
 	tx_bytes = 0;
 	rx_packets = 0;
 	rx_bytes = 0;
-	for (q = 0; q < oct->num_oqs; q++) {
-		struct octep_vf_iq *iq = oct->iq[q];
-		struct octep_vf_oq *oq = oct->oq[q];
-
-		tx_packets += iq->stats.instr_completed;
-		tx_bytes += iq->stats.bytes_sent;
-		rx_packets += oq->stats.packets;
-		rx_bytes += oq->stats.bytes;
+	for (q = 0; q < OCTEP_VF_MAX_QUEUES; q++) {
+		tx_packets += oct->stats_iq[q].instr_completed;
+		tx_bytes += oct->stats_iq[q].bytes_sent;
+		rx_packets += oct->stats_oq[q].packets;
+		rx_bytes += oct->stats_oq[q].bytes;
 	}
 	stats->tx_packets = tx_packets;
 	stats->tx_bytes = tx_bytes;
 	stats->rx_packets = rx_packets;
 	stats->rx_bytes = rx_bytes;
-	if (!octep_vf_get_if_stats(oct)) {
-		stats->multicast = oct->iface_rx_stats.mcast_pkts;
-		stats->rx_errors = oct->iface_rx_stats.err_pkts;
-		stats->rx_dropped = oct->iface_rx_stats.dropped_pkts_fifo_full +
-				    oct->iface_rx_stats.err_pkts;
-		stats->rx_missed_errors = oct->iface_rx_stats.dropped_pkts_fifo_full;
-		stats->tx_dropped = oct->iface_tx_stats.dropped;
-	}
 }
 
 /**
@@ -846,7 +835,9 @@ static void octep_vf_tx_timeout(struct net_device *netdev, unsigned int txqueue)
 	struct octep_vf_device *oct = netdev_priv(netdev);
 
 	netdev_hold(netdev, NULL, GFP_ATOMIC);
-	schedule_work(&oct->tx_timeout_task);
+	if (!schedule_work(&oct->tx_timeout_task))
+		netdev_put(netdev, NULL);
+
 }
 
 static int octep_vf_set_mac(struct net_device *netdev, void *p)
diff --git a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.h b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.h
index 5769f62545cd..1a352f41f823 100644
--- a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.h
+++ b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.h
@@ -246,11 +246,17 @@ struct octep_vf_device {
 	/* Pointers to Octeon Tx queues */
 	struct octep_vf_iq *iq[OCTEP_VF_MAX_IQ];
 
+	/* Per iq stats */
+	struct octep_vf_iq_stats stats_iq[OCTEP_VF_MAX_IQ];
+
 	/* Rx queues (OQ: Output Queue) */
 	u16 num_oqs;
 	/* Pointers to Octeon Rx queues */
 	struct octep_vf_oq *oq[OCTEP_VF_MAX_OQ];
 
+	/* Per oq stats */
+	struct octep_vf_oq_stats stats_oq[OCTEP_VF_MAX_OQ];
+
 	/* Hardware port number of the PCIe interface */
 	u16 pcie_port;
 
diff --git a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_rx.c b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_rx.c
index 82821bc28634..d70c8be3cfc4 100644
--- a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_rx.c
+++ b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_rx.c
@@ -87,7 +87,7 @@ static int octep_vf_oq_refill(struct octep_vf_device *oct, struct octep_vf_oq *o
 		page = dev_alloc_page();
 		if (unlikely(!page)) {
 			dev_err(oq->dev, "refill: rx buffer alloc failed\n");
-			oq->stats.alloc_failures++;
+			oq->stats->alloc_failures++;
 			break;
 		}
 
@@ -98,7 +98,7 @@ static int octep_vf_oq_refill(struct octep_vf_device *oct, struct octep_vf_oq *o
 				"OQ-%d buffer refill: DMA mapping error!\n",
 				oq->q_no);
 			put_page(page);
-			oq->stats.alloc_failures++;
+			oq->stats->alloc_failures++;
 			break;
 		}
 		oq->buff_info[refill_idx].page = page;
@@ -134,6 +134,7 @@ static int octep_vf_setup_oq(struct octep_vf_device *oct, int q_no)
 	oq->netdev = oct->netdev;
 	oq->dev = &oct->pdev->dev;
 	oq->q_no = q_no;
+	oq->stats = &oct->stats_oq[q_no];
 	oq->max_count = CFG_GET_OQ_NUM_DESC(oct->conf);
 	oq->ring_size_mask = oq->max_count - 1;
 	oq->buffer_size = CFG_GET_OQ_BUF_SIZE(oct->conf);
@@ -458,8 +459,8 @@ static int __octep_vf_oq_process_rx(struct octep_vf_device *oct,
 
 	oq->host_read_idx = read_idx;
 	oq->refill_count += desc_used;
-	oq->stats.packets += pkt;
-	oq->stats.bytes += rx_bytes;
+	oq->stats->packets += pkt;
+	oq->stats->bytes += rx_bytes;
 
 	return pkt;
 }
diff --git a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_rx.h b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_rx.h
index fe46838b5200..9e296b7d7e34 100644
--- a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_rx.h
+++ b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_rx.h
@@ -187,7 +187,7 @@ struct octep_vf_oq {
 	u8 __iomem *pkts_sent_reg;
 
 	/* Statistics for this OQ. */
-	struct octep_vf_oq_stats stats;
+	struct octep_vf_oq_stats *stats;
 
 	/* Packets pending to be processed */
 	u32 pkts_pending;
diff --git a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_tx.c b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_tx.c
index 47a5c054fdb6..8180e5ce3d7e 100644
--- a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_tx.c
+++ b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_tx.c
@@ -82,9 +82,9 @@ int octep_vf_iq_process_completions(struct octep_vf_iq *iq, u16 budget)
 	}
 
 	iq->pkts_processed += compl_pkts;
-	iq->stats.instr_completed += compl_pkts;
-	iq->stats.bytes_sent += compl_bytes;
-	iq->stats.sgentry_sent += compl_sg;
+	iq->stats->instr_completed += compl_pkts;
+	iq->stats->bytes_sent += compl_bytes;
+	iq->stats->sgentry_sent += compl_sg;
 	iq->flush_index = fi;
 
 	netif_subqueue_completed_wake(iq->netdev, iq->q_no, compl_pkts,
@@ -186,6 +186,7 @@ static int octep_vf_setup_iq(struct octep_vf_device *oct, int q_no)
 	iq->netdev = oct->netdev;
 	iq->dev = &oct->pdev->dev;
 	iq->q_no = q_no;
+	iq->stats = &oct->stats_iq[q_no];
 	iq->max_count = CFG_GET_IQ_NUM_DESC(oct->conf);
 	iq->ring_size_mask = iq->max_count - 1;
 	iq->fill_threshold = CFG_GET_IQ_DB_MIN(oct->conf);
diff --git a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_tx.h b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_tx.h
index f338b975103c..1cede90e3a5f 100644
--- a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_tx.h
+++ b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_tx.h
@@ -129,7 +129,7 @@ struct octep_vf_iq {
 	u16 flush_index;
 
 	/* Statistics for this input queue. */
-	struct octep_vf_iq_stats stats;
+	struct octep_vf_iq_stats *stats;
 
 	/* Pointer to the Virtual Base addr of the input ring. */
 	struct octep_vf_tx_desc_hw *desc_ring;
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
index 8216f843a7cd..971993586fb4 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
@@ -66,8 +66,18 @@ static int cgx_fwi_link_change(struct cgx *cgx, int lmac_id, bool en);
 /* Supported devices */
 static const struct pci_device_id cgx_id_table[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_OCTEONTX2_CGX) },
-	{ PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_CN10K_RPM) },
-	{ PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_CN10KB_RPM) },
+	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_CN10K_RPM,
+	  PCI_ANY_ID, PCI_SUBSYS_DEVID_CN10K_A) },
+	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_CN10K_RPM,
+	  PCI_ANY_ID, PCI_SUBSYS_DEVID_CNF10K_A) },
+	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_CN10K_RPM,
+	  PCI_ANY_ID, PCI_SUBSYS_DEVID_CNF10K_B) },
+	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_CN10KB_RPM,
+	  PCI_ANY_ID, PCI_SUBSYS_DEVID_CN10K_B) },
+	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_CN10KB_RPM,
+	  PCI_ANY_ID, PCI_SUBSYS_DEVID_CN20KA) },
+	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_CN10KB_RPM,
+	  PCI_ANY_ID, PCI_SUBSYS_DEVID_CNF20KA) },
 	{ 0, }  /* end of table */
 };
 
@@ -707,6 +717,11 @@ int cgx_get_rx_stats(void *cgxd, int lmac_id, int idx, u64 *rx_stat)
 
 	if (!is_lmac_valid(cgx, lmac_id))
 		return -ENODEV;
+
+	/* pass lmac as 0 for CGX_CMR_RX_STAT9-12 */
+	if (idx >= CGX_RX_STAT_GLOBAL_INDEX)
+		lmac_id = 0;
+
 	*rx_stat =  cgx_read(cgx, lmac_id, CGXX_CMRX_RX_STAT0 + (idx * 8));
 	return 0;
 }
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
index cd0d7b7774f1..6575c422635b 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
@@ -2634,7 +2634,7 @@ static irqreturn_t rvu_mbox_intr_handler(int irq, void *rvu_irq)
 		rvupf_write64(rvu, RVU_PF_VFPF_MBOX_INTX(1), intr);
 
 		rvu_queue_work(&rvu->afvf_wq_info, 64, vfs, intr);
-		vfs -= 64;
+		vfs = 64;
 	}
 
 	intr = rvupf_read64(rvu, RVU_PF_VFPF_MBOX_INTX(0));
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index 8555edbb1c8f..f94bf04788e9 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -30,6 +30,8 @@
 #define PCI_SUBSYS_DEVID_CNF10K_A	       0xBA00
 #define PCI_SUBSYS_DEVID_CNF10K_B              0xBC00
 #define PCI_SUBSYS_DEVID_CN10K_B               0xBD00
+#define PCI_SUBSYS_DEVID_CN20KA                0xC220
+#define PCI_SUBSYS_DEVID_CNF20KA               0xC320
 
 /* PCI BAR nos */
 #define	PCI_AF_REG_BAR_NUM			0
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c
index 7fa98aeb3663..4a3370a40dd8 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c
@@ -13,19 +13,26 @@
 /* RVU LMTST */
 #define LMT_TBL_OP_READ		0
 #define LMT_TBL_OP_WRITE	1
-#define LMT_MAP_TABLE_SIZE	(128 * 1024)
 #define LMT_MAPTBL_ENTRY_SIZE	16
+#define LMT_MAX_VFS		256
+
+#define LMT_MAP_ENTRY_ENA      BIT_ULL(20)
+#define LMT_MAP_ENTRY_LINES    GENMASK_ULL(18, 16)
 
 /* Function to perform operations (read/write) on lmtst map table */
 static int lmtst_map_table_ops(struct rvu *rvu, u32 index, u64 *val,
 			       int lmt_tbl_op)
 {
 	void __iomem *lmt_map_base;
-	u64 tbl_base;
+	u64 tbl_base, cfg;
+	int pfs, vfs;
 
 	tbl_base = rvu_read64(rvu, BLKADDR_APR, APR_AF_LMT_MAP_BASE);
+	cfg  = rvu_read64(rvu, BLKADDR_APR, APR_AF_LMT_CFG);
+	vfs = 1 << (cfg & 0xF);
+	pfs = 1 << ((cfg >> 4) & 0x7);
 
-	lmt_map_base = ioremap_wc(tbl_base, LMT_MAP_TABLE_SIZE);
+	lmt_map_base = ioremap_wc(tbl_base, pfs * vfs * LMT_MAPTBL_ENTRY_SIZE);
 	if (!lmt_map_base) {
 		dev_err(rvu->dev, "Failed to setup lmt map table mapping!!\n");
 		return -ENOMEM;
@@ -35,6 +42,13 @@ static int lmtst_map_table_ops(struct rvu *rvu, u32 index, u64 *val,
 		*val = readq(lmt_map_base + index);
 	} else {
 		writeq((*val), (lmt_map_base + index));
+
+		cfg = FIELD_PREP(LMT_MAP_ENTRY_ENA, 0x1);
+		/* 2048 LMTLINES */
+		cfg |= FIELD_PREP(LMT_MAP_ENTRY_LINES, 0x6);
+
+		writeq(cfg, (lmt_map_base + (index + 8)));
+
 		/* Flushing the AP interceptor cache to make APR_LMT_MAP_ENTRY_S
 		 * changes effective. Write 1 for flush and read is being used as a
 		 * barrier and sets up a data dependency. Write to 0 after a write
@@ -52,7 +66,7 @@ static int lmtst_map_table_ops(struct rvu *rvu, u32 index, u64 *val,
 #define LMT_MAP_TBL_W1_OFF  8
 static u32 rvu_get_lmtst_tbl_index(struct rvu *rvu, u16 pcifunc)
 {
-	return ((rvu_get_pf(pcifunc) * rvu->hw->total_vfs) +
+	return ((rvu_get_pf(pcifunc) * LMT_MAX_VFS) +
 		(pcifunc & RVU_PFVF_FUNC_MASK)) * LMT_MAPTBL_ENTRY_SIZE;
 }
 
@@ -69,7 +83,7 @@ static int rvu_get_lmtaddr(struct rvu *rvu, u16 pcifunc,
 
 	mutex_lock(&rvu->rsrc_lock);
 	rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_SMMU_ADDR_REQ, iova);
-	pf = rvu_get_pf(pcifunc) & 0x1F;
+	pf = rvu_get_pf(pcifunc) & RVU_PFVF_PF_MASK;
 	val = BIT_ULL(63) | BIT_ULL(14) | BIT_ULL(13) | pf << 8 |
 	      ((pcifunc & RVU_PFVF_FUNC_MASK) & 0xFF);
 	rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_SMMU_TXN_REQ, val);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
index 87ba77e5026a..e24accfecb3f 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
@@ -580,6 +580,7 @@ static ssize_t rvu_dbg_lmtst_map_table_display(struct file *filp,
 	u64 lmt_addr, val, tbl_base;
 	int pf, vf, num_vfs, hw_vfs;
 	void __iomem *lmt_map_base;
+	int apr_pfs, apr_vfs;
 	int buf_size = 10240;
 	size_t off = 0;
 	int index = 0;
@@ -595,8 +596,12 @@ static ssize_t rvu_dbg_lmtst_map_table_display(struct file *filp,
 		return -ENOMEM;
 
 	tbl_base = rvu_read64(rvu, BLKADDR_APR, APR_AF_LMT_MAP_BASE);
+	val  = rvu_read64(rvu, BLKADDR_APR, APR_AF_LMT_CFG);
+	apr_vfs = 1 << (val & 0xF);
+	apr_pfs = 1 << ((val >> 4) & 0x7);
 
-	lmt_map_base = ioremap_wc(tbl_base, 128 * 1024);
+	lmt_map_base = ioremap_wc(tbl_base, apr_pfs * apr_vfs *
+				  LMT_MAPTBL_ENTRY_SIZE);
 	if (!lmt_map_base) {
 		dev_err(rvu->dev, "Failed to setup lmt map table mapping!!\n");
 		kfree(buf);
@@ -618,7 +623,7 @@ static ssize_t rvu_dbg_lmtst_map_table_display(struct file *filp,
 		off += scnprintf(&buf[off], buf_size - 1 - off, "PF%d  \t\t\t",
 				    pf);
 
-		index = pf * rvu->hw->total_vfs * LMT_MAPTBL_ENTRY_SIZE;
+		index = pf * apr_vfs * LMT_MAPTBL_ENTRY_SIZE;
 		off += scnprintf(&buf[off], buf_size - 1 - off, " 0x%llx\t\t",
 				 (tbl_base + index));
 		lmt_addr = readq(lmt_map_base + index);
@@ -631,7 +636,7 @@ static ssize_t rvu_dbg_lmtst_map_table_display(struct file *filp,
 		/* Reading num of VFs per PF */
 		rvu_get_pf_numvfs(rvu, pf, &num_vfs, &hw_vfs);
 		for (vf = 0; vf < num_vfs; vf++) {
-			index = (pf * rvu->hw->total_vfs * 16) +
+			index = (pf * apr_vfs * LMT_MAPTBL_ENTRY_SIZE) +
 				((vf + 1)  * LMT_MAPTBL_ENTRY_SIZE);
 			off += scnprintf(&buf[off], buf_size - 1 - off,
 					    "PF%d:VF%d  \t\t", pf, vf);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c
index 7498ab429963..06f778baaeef 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c
@@ -207,7 +207,7 @@ static void rvu_nix_unregister_interrupts(struct rvu *rvu)
 		rvu->irq_allocated[offs + NIX_AF_INT_VEC_RVU] = false;
 	}
 
-	for (i = NIX_AF_INT_VEC_AF_ERR; i < NIX_AF_INT_VEC_CNT; i++)
+	for (i = NIX_AF_INT_VEC_GEN; i < NIX_AF_INT_VEC_CNT; i++)
 		if (rvu->irq_allocated[offs + i]) {
 			free_irq(pci_irq_vector(rvu->pdev, offs + i), rvu_dl);
 			rvu->irq_allocated[offs + i] = false;
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c
index 7417087b6db5..a2807a1e4f4a 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c
@@ -352,9 +352,12 @@ int cn10k_free_matchall_ipolicer(struct otx2_nic *pfvf)
 	mutex_lock(&pfvf->mbox.lock);
 
 	/* Remove RQ's policer mapping */
-	for (qidx = 0; qidx < hw->rx_queues; qidx++)
-		cn10k_map_unmap_rq_policer(pfvf, qidx,
-					   hw->matchall_ipolicer, false);
+	for (qidx = 0; qidx < hw->rx_queues; qidx++) {
+		rc = cn10k_map_unmap_rq_policer(pfvf, qidx, hw->matchall_ipolicer, false);
+		if (rc)
+			dev_warn(pfvf->dev, "Failed to unmap RQ %d's policer (error %d).",
+				 qidx, rc);
+	}
 
 	rc = cn10k_free_leaf_profile(pfvf, hw->matchall_ipolicer);
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c
index 6cc7a78968fc..74953f67a2bf 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c
@@ -533,7 +533,8 @@ static int cn10k_mcs_write_tx_secy(struct otx2_nic *pfvf,
 	if (sw_tx_sc->encrypt)
 		sectag_tci |= (MCS_TCI_E | MCS_TCI_C);
 
-	policy = FIELD_PREP(MCS_TX_SECY_PLCY_MTU, secy->netdev->mtu);
+	policy = FIELD_PREP(MCS_TX_SECY_PLCY_MTU,
+			    pfvf->netdev->mtu + OTX2_ETH_HLEN);
 	/* Write SecTag excluding AN bits(1..0) */
 	policy |= FIELD_PREP(MCS_TX_SECY_PLCY_ST_TCI, sectag_tci >> 2);
 	policy |= FIELD_PREP(MCS_TX_SECY_PLCY_ST_OFFSET, tag_offset);
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
index 7510a918d942..f75afcf5f5ae 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
@@ -988,6 +988,7 @@ static int otx2_cq_init(struct otx2_nic *pfvf, u16 qidx)
 	int err, pool_id, non_xdp_queues;
 	struct nix_aq_enq_req *aq;
 	struct otx2_cq_queue *cq;
+	struct otx2_pool *pool;
 
 	cq = &qset->cq[qidx];
 	cq->cq_idx = qidx;
@@ -996,8 +997,13 @@ static int otx2_cq_init(struct otx2_nic *pfvf, u16 qidx)
 		cq->cq_type = CQ_RX;
 		cq->cint_idx = qidx;
 		cq->cqe_cnt = qset->rqe_cnt;
-		if (pfvf->xdp_prog)
+		if (pfvf->xdp_prog) {
+			pool = &qset->pool[qidx];
 			xdp_rxq_info_reg(&cq->xdp_rxq, pfvf->netdev, qidx, 0);
+			xdp_rxq_info_reg_mem_model(&cq->xdp_rxq,
+						   MEM_TYPE_PAGE_POOL,
+						   pool->page_pool);
+		}
 	} else if (qidx < non_xdp_queues) {
 		cq->cq_type = CQ_TX;
 		cq->cint_idx = qidx - pfvf->hw.rx_queues;
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
index f27a3456ae64..5b45fd78d282 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
@@ -364,6 +364,7 @@ struct otx2_flow_config {
 	struct list_head	flow_list_tc;
 	u8			ucast_flt_cnt;
 	bool			ntuple;
+	u16			ntuple_cnt;
 };
 
 struct dev_hw_ops {
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c
index 53f14aa944bd..aaea19345750 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c
@@ -41,6 +41,7 @@ static int otx2_dl_mcam_count_set(struct devlink *devlink, u32 id,
 	if (!pfvf->flow_cfg)
 		return 0;
 
+	pfvf->flow_cfg->ntuple_cnt = ctx->val.vu16;
 	otx2_alloc_mcam_entries(pfvf, ctx->val.vu16);
 
 	return 0;
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c
index 58720a161ee2..2750326bfcf8 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c
@@ -252,7 +252,7 @@ int otx2_mcam_entry_init(struct otx2_nic *pfvf)
 	mutex_unlock(&pfvf->mbox.lock);
 
 	/* Allocate entries for Ntuple filters */
-	count = otx2_alloc_mcam_entries(pfvf, OTX2_DEFAULT_FLOWCOUNT);
+	count = otx2_alloc_mcam_entries(pfvf, flow_cfg->ntuple_cnt);
 	if (count <= 0) {
 		otx2_clear_ntuple_flow_info(pfvf, flow_cfg);
 		return 0;
@@ -312,6 +312,7 @@ int otx2_mcam_flow_init(struct otx2_nic *pf)
 	INIT_LIST_HEAD(&pf->flow_cfg->flow_list_tc);
 
 	pf->flow_cfg->ucast_flt_cnt = OTX2_DEFAULT_UNICAST_FLOWS;
+	pf->flow_cfg->ntuple_cnt = OTX2_DEFAULT_FLOWCOUNT;
 
 	/* Allocate bare minimum number of MCAM entries needed for
 	 * unicast and ntuple filters.
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/qos.c b/drivers/net/ethernet/marvell/octeontx2/nic/qos.c
index 0f844c14485a..5765bac119f0 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/qos.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/qos.c
@@ -165,6 +165,11 @@ static void __otx2_qos_txschq_cfg(struct otx2_nic *pfvf,
 
 		otx2_config_sched_shaping(pfvf, node, cfg, &num_regs);
 	} else if (level == NIX_TXSCH_LVL_TL2) {
+		/* configure parent txschq */
+		cfg->reg[num_regs] = NIX_AF_TL2X_PARENT(node->schq);
+		cfg->regval[num_regs] = (u64)hw->tx_link << 16;
+		num_regs++;
+
 		/* configure link cfg */
 		if (level == pfvf->qos.link_cfg_lvl) {
 			cfg->reg[num_regs] = NIX_AF_TL3_TL2X_LINKX_CFG(node->schq, hw->tx_link);
@@ -1633,6 +1638,7 @@ static int otx2_qos_leaf_del_last(struct otx2_nic *pfvf, u16 classid, bool force
 	if (!node->is_static)
 		dwrr_del_node = true;
 
+	WRITE_ONCE(node->qid, OTX2_QOS_QID_INNER);
 	/* destroy the leaf node */
 	otx2_qos_disable_sq(pfvf, qid);
 	otx2_qos_destroy_node(pfvf, node);
@@ -1677,9 +1683,6 @@ static int otx2_qos_leaf_del_last(struct otx2_nic *pfvf, u16 classid, bool force
 	}
 	kfree(new_cfg);
 
-	/* update tx_real_queues */
-	otx2_qos_update_tx_netdev_queues(pfvf);
-
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/qos_sq.c b/drivers/net/ethernet/marvell/octeontx2/nic/qos_sq.c
index 9d887bfc3108..ac9345644068 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/qos_sq.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/qos_sq.c
@@ -256,6 +256,26 @@ out:
 	return err;
 }
 
+static int otx2_qos_nix_npa_ndc_sync(struct otx2_nic *pfvf)
+{
+	struct ndc_sync_op *req;
+	int rc;
+
+	mutex_lock(&pfvf->mbox.lock);
+
+	req = otx2_mbox_alloc_msg_ndc_sync_op(&pfvf->mbox);
+	if (!req) {
+		mutex_unlock(&pfvf->mbox.lock);
+		return -ENOMEM;
+	}
+
+	req->nix_lf_tx_sync = true;
+	req->npa_lf_sync = true;
+	rc = otx2_sync_mbox_msg(&pfvf->mbox);
+	mutex_unlock(&pfvf->mbox.lock);
+	return rc;
+}
+
 void otx2_qos_disable_sq(struct otx2_nic *pfvf, int qidx)
 {
 	struct otx2_qset *qset = &pfvf->qset;
@@ -285,6 +305,8 @@ void otx2_qos_disable_sq(struct otx2_nic *pfvf, int qidx)
 
 	otx2_qos_sqb_flush(pfvf, sq_idx);
 	otx2_smq_flush(pfvf, otx2_get_smq_idx(pfvf, sq_idx));
+	/* NIX/NPA NDC sync */
+	otx2_qos_nix_npa_ndc_sync(pfvf);
 	otx2_cleanup_tx_cqes(pfvf, cq);
 
 	mutex_lock(&pfvf->mbox.lock);
diff --git a/drivers/net/ethernet/mediatek/airoha_eth.c b/drivers/net/ethernet/mediatek/airoha_eth.c
index 2c26eb185283..20cf7ba9d750 100644
--- a/drivers/net/ethernet/mediatek/airoha_eth.c
+++ b/drivers/net/ethernet/mediatek/airoha_eth.c
@@ -258,11 +258,11 @@
 #define REG_GDM3_FWD_CFG		GDM3_BASE
 #define GDM3_PAD_EN_MASK		BIT(28)
 
-#define REG_GDM4_FWD_CFG		(GDM4_BASE + 0x100)
+#define REG_GDM4_FWD_CFG		GDM4_BASE
 #define GDM4_PAD_EN_MASK		BIT(28)
 #define GDM4_SPORT_OFFSET0_MASK		GENMASK(11, 8)
 
-#define REG_GDM4_SRC_PORT_SET		(GDM4_BASE + 0x33c)
+#define REG_GDM4_SRC_PORT_SET		(GDM4_BASE + 0x23c)
 #define GDM4_SPORT_OFF2_MASK		GENMASK(19, 16)
 #define GDM4_SPORT_OFF1_MASK		GENMASK(15, 12)
 #define GDM4_SPORT_OFF0_MASK		GENMASK(11, 8)
@@ -2123,17 +2123,14 @@ static void airoha_hw_cleanup(struct airoha_qdma *qdma)
 		if (!qdma->q_rx[i].ndesc)
 			continue;
 
-		napi_disable(&qdma->q_rx[i].napi);
 		netif_napi_del(&qdma->q_rx[i].napi);
 		airoha_qdma_cleanup_rx_queue(&qdma->q_rx[i]);
 		if (qdma->q_rx[i].page_pool)
 			page_pool_destroy(qdma->q_rx[i].page_pool);
 	}
 
-	for (i = 0; i < ARRAY_SIZE(qdma->q_tx_irq); i++) {
-		napi_disable(&qdma->q_tx_irq[i].napi);
+	for (i = 0; i < ARRAY_SIZE(qdma->q_tx_irq); i++)
 		netif_napi_del(&qdma->q_tx_irq[i].napi);
-	}
 
 	for (i = 0; i < ARRAY_SIZE(qdma->q_tx); i++) {
 		if (!qdma->q_tx[i].ndesc)
@@ -2158,6 +2155,21 @@ static void airoha_qdma_start_napi(struct airoha_qdma *qdma)
 	}
 }
 
+static void airoha_qdma_stop_napi(struct airoha_qdma *qdma)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(qdma->q_tx_irq); i++)
+		napi_disable(&qdma->q_tx_irq[i].napi);
+
+	for (i = 0; i < ARRAY_SIZE(qdma->q_rx); i++) {
+		if (!qdma->q_rx[i].ndesc)
+			continue;
+
+		napi_disable(&qdma->q_rx[i].napi);
+	}
+}
+
 static void airoha_update_hw_stats(struct airoha_gdm_port *port)
 {
 	struct airoha_eth *eth = port->qdma->eth;
@@ -2713,7 +2725,7 @@ static int airoha_probe(struct platform_device *pdev)
 
 	err = airoha_hw_init(pdev, eth);
 	if (err)
-		goto error;
+		goto error_hw_cleanup;
 
 	for (i = 0; i < ARRAY_SIZE(eth->qdma); i++)
 		airoha_qdma_start_napi(&eth->qdma[i]);
@@ -2728,13 +2740,16 @@ static int airoha_probe(struct platform_device *pdev)
 		err = airoha_alloc_gdm_port(eth, np);
 		if (err) {
 			of_node_put(np);
-			goto error;
+			goto error_napi_stop;
 		}
 	}
 
 	return 0;
 
-error:
+error_napi_stop:
+	for (i = 0; i < ARRAY_SIZE(eth->qdma); i++)
+		airoha_qdma_stop_napi(&eth->qdma[i]);
+error_hw_cleanup:
 	for (i = 0; i < ARRAY_SIZE(eth->qdma); i++)
 		airoha_hw_cleanup(&eth->qdma[i]);
 
@@ -2755,8 +2770,10 @@ static void airoha_remove(struct platform_device *pdev)
 	struct airoha_eth *eth = platform_get_drvdata(pdev);
 	int i;
 
-	for (i = 0; i < ARRAY_SIZE(eth->qdma); i++)
+	for (i = 0; i < ARRAY_SIZE(eth->qdma); i++) {
+		airoha_qdma_stop_napi(&eth->qdma[i]);
 		airoha_hw_cleanup(&eth->qdma[i]);
+	}
 
 	for (i = 0; i < ARRAY_SIZE(eth->ports); i++) {
 		struct airoha_gdm_port *port = eth->ports[i];
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index ed7313c10a05..272f178906d6 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -269,12 +269,8 @@ static const char * const mtk_clks_source_name[] = {
 	"ethwarp_wocpu2",
 	"ethwarp_wocpu1",
 	"ethwarp_wocpu0",
-	"top_usxgmii0_sel",
-	"top_usxgmii1_sel",
 	"top_sgm0_sel",
 	"top_sgm1_sel",
-	"top_xfi_phy0_xtal_sel",
-	"top_xfi_phy1_xtal_sel",
 	"top_eth_gmii_sel",
 	"top_eth_refck_50m_sel",
 	"top_eth_sys_200m_sel",
@@ -734,7 +730,7 @@ static void mtk_set_queue_speed(struct mtk_eth *eth, unsigned int idx,
 		case SPEED_100:
 			val |= MTK_QTX_SCH_MAX_RATE_EN |
 			       FIELD_PREP(MTK_QTX_SCH_MAX_RATE_MAN, 103) |
-			       FIELD_PREP(MTK_QTX_SCH_MAX_RATE_EXP, 3);
+			       FIELD_PREP(MTK_QTX_SCH_MAX_RATE_EXP, 3) |
 			       FIELD_PREP(MTK_QTX_SCH_MAX_RATE_WEIGHT, 1);
 			break;
 		case SPEED_1000:
@@ -757,13 +753,13 @@ static void mtk_set_queue_speed(struct mtk_eth *eth, unsigned int idx,
 		case SPEED_100:
 			val |= MTK_QTX_SCH_MAX_RATE_EN |
 			       FIELD_PREP(MTK_QTX_SCH_MAX_RATE_MAN, 1) |
-			       FIELD_PREP(MTK_QTX_SCH_MAX_RATE_EXP, 5);
+			       FIELD_PREP(MTK_QTX_SCH_MAX_RATE_EXP, 5) |
 			       FIELD_PREP(MTK_QTX_SCH_MAX_RATE_WEIGHT, 1);
 			break;
 		case SPEED_1000:
 			val |= MTK_QTX_SCH_MAX_RATE_EN |
-			       FIELD_PREP(MTK_QTX_SCH_MAX_RATE_MAN, 10) |
-			       FIELD_PREP(MTK_QTX_SCH_MAX_RATE_EXP, 5) |
+			       FIELD_PREP(MTK_QTX_SCH_MAX_RATE_MAN, 1) |
+			       FIELD_PREP(MTK_QTX_SCH_MAX_RATE_EXP, 6) |
 			       FIELD_PREP(MTK_QTX_SCH_MAX_RATE_WEIGHT, 10);
 			break;
 		default:
@@ -823,9 +819,25 @@ static const struct phylink_mac_ops mtk_phylink_ops = {
 	.mac_link_up = mtk_mac_link_up,
 };
 
+static void mtk_mdio_config(struct mtk_eth *eth)
+{
+	u32 val;
+
+	/* Configure MDC Divider */
+	val = FIELD_PREP(PPSC_MDC_CFG, eth->mdc_divider);
+
+	/* Configure MDC Turbo Mode */
+	if (mtk_is_netsys_v3_or_greater(eth))
+		mtk_m32(eth, 0, MISC_MDC_TURBO, MTK_MAC_MISC_V3);
+	else
+		val |= PPSC_MDC_TURBO;
+
+	mtk_m32(eth, PPSC_MDC_CFG, val, MTK_PPSC);
+}
+
 static int mtk_mdio_init(struct mtk_eth *eth)
 {
-	unsigned int max_clk = 2500000, divider;
+	unsigned int max_clk = 2500000;
 	struct device_node *mii_np;
 	int ret;
 	u32 val;
@@ -865,20 +877,9 @@ static int mtk_mdio_init(struct mtk_eth *eth)
 		}
 		max_clk = val;
 	}
-	divider = min_t(unsigned int, DIV_ROUND_UP(MDC_MAX_FREQ, max_clk), 63);
-
-	/* Configure MDC Turbo Mode */
-	if (mtk_is_netsys_v3_or_greater(eth))
-		mtk_m32(eth, 0, MISC_MDC_TURBO, MTK_MAC_MISC_V3);
-
-	/* Configure MDC Divider */
-	val = FIELD_PREP(PPSC_MDC_CFG, divider);
-	if (!mtk_is_netsys_v3_or_greater(eth))
-		val |= PPSC_MDC_TURBO;
-	mtk_m32(eth, PPSC_MDC_CFG, val, MTK_PPSC);
-
-	dev_dbg(eth->dev, "MDC is running on %d Hz\n", MDC_MAX_FREQ / divider);
-
+	eth->mdc_divider = min_t(unsigned int, DIV_ROUND_UP(MDC_MAX_FREQ, max_clk), 63);
+	mtk_mdio_config(eth);
+	dev_dbg(eth->dev, "MDC is running on %d Hz\n", MDC_MAX_FREQ / eth->mdc_divider);
 	ret = of_mdiobus_register(eth->mii_bus, mii_np);
 
 err_put_node:
@@ -2201,14 +2202,18 @@ skip_rx:
 		ring->data[idx] = new_data;
 		rxd->rxd1 = (unsigned int)dma_addr;
 release_desc:
+		if (MTK_HAS_CAPS(eth->soc->caps, MTK_36BIT_DMA)) {
+			if (unlikely(dma_addr == DMA_MAPPING_ERROR))
+				addr64 = FIELD_GET(RX_DMA_ADDR64_MASK,
+						   rxd->rxd2);
+			else
+				addr64 = RX_DMA_PREP_ADDR64(dma_addr);
+		}
+
 		if (MTK_HAS_CAPS(eth->soc->caps, MTK_SOC_MT7628))
 			rxd->rxd2 = RX_DMA_LSO;
 		else
-			rxd->rxd2 = RX_DMA_PREP_PLEN0(ring->buf_size);
-
-		if (MTK_HAS_CAPS(eth->soc->caps, MTK_36BIT_DMA) &&
-		    likely(dma_addr != DMA_MAPPING_ERROR))
-			rxd->rxd2 |= RX_DMA_PREP_ADDR64(dma_addr);
+			rxd->rxd2 = RX_DMA_PREP_PLEN0(ring->buf_size) | addr64;
 
 		ring->calc_idx = idx;
 		done++;
@@ -3135,11 +3140,19 @@ static int mtk_dma_init(struct mtk_eth *eth)
 static void mtk_dma_free(struct mtk_eth *eth)
 {
 	const struct mtk_soc_data *soc = eth->soc;
-	int i;
+	int i, j, txqs = 1;
+
+	if (MTK_HAS_CAPS(eth->soc->caps, MTK_QDMA))
+		txqs = MTK_QDMA_NUM_QUEUES;
+
+	for (i = 0; i < MTK_MAX_DEVS; i++) {
+		if (!eth->netdev[i])
+			continue;
+
+		for (j = 0; j < txqs; j++)
+			netdev_tx_reset_subqueue(eth->netdev[i], j);
+	}
 
-	for (i = 0; i < MTK_MAX_DEVS; i++)
-		if (eth->netdev[i])
-			netdev_reset_queue(eth->netdev[i]);
 	if (!MTK_HAS_CAPS(soc->caps, MTK_SRAM) && eth->scratch_ring) {
 		dma_free_coherent(eth->dma_dev,
 				  MTK_QDMA_RING_SIZE * soc->tx.desc_size,
@@ -3269,7 +3282,7 @@ static int mtk_start_dma(struct mtk_eth *eth)
 		if (mtk_is_netsys_v2_or_greater(eth))
 			val |= MTK_MUTLI_CNT | MTK_RESV_BUF |
 			       MTK_WCOMP_EN | MTK_DMAD_WR_WDONE |
-			       MTK_CHK_DDONE_EN | MTK_LEAKY_BUCKET_EN;
+			       MTK_CHK_DDONE_EN;
 		else
 			val |= MTK_RX_BT_32DWORDS;
 		mtk_w32(eth, val, reg_map->qdma.glo_cfg);
@@ -3414,9 +3427,6 @@ static int mtk_open(struct net_device *dev)
 			}
 			mtk_gdm_config(eth, target_mac->id, gdm_config);
 		}
-		/* Reset and enable PSE */
-		mtk_w32(eth, RST_GL_PSE, MTK_RST_GL);
-		mtk_w32(eth, 0, MTK_RST_GL);
 
 		napi_enable(&eth->tx_napi);
 		napi_enable(&eth->rx_napi);
@@ -3928,6 +3938,10 @@ static int mtk_hw_init(struct mtk_eth *eth, bool reset)
 	else
 		mtk_hw_reset(eth);
 
+	/* No MT7628/88 support yet */
+	if (reset && !MTK_HAS_CAPS(eth->soc->caps, MTK_SOC_MT7628))
+		mtk_mdio_config(eth);
+
 	if (mtk_is_netsys_v3_or_greater(eth)) {
 		/* Set FE to PDMAv2 if necessary */
 		val = mtk_r32(eth, MTK_FE_GLO_MISC);
@@ -3988,11 +4002,27 @@ static int mtk_hw_init(struct mtk_eth *eth, bool reset)
 	mtk_w32(eth, 0x21021000, MTK_FE_INT_GRP);
 
 	if (mtk_is_netsys_v3_or_greater(eth)) {
-		/* PSE should not drop port1, port8 and port9 packets */
-		mtk_w32(eth, 0x00000302, PSE_DROP_CFG);
+		/* PSE dummy page mechanism */
+		mtk_w32(eth, PSE_DUMMY_WORK_GDM(1) | PSE_DUMMY_WORK_GDM(2) |
+			PSE_DUMMY_WORK_GDM(3) | DUMMY_PAGE_THR, PSE_DUMY_REQ);
+
+		/* PSE free buffer drop threshold */
+		mtk_w32(eth, 0x00600009, PSE_IQ_REV(8));
+
+		/* PSE should not drop port8, port9 and port13 packets from
+		 * WDMA Tx
+		 */
+		mtk_w32(eth, 0x00002300, PSE_DROP_CFG);
+
+		/* PSE should drop packets to port8, port9 and port13 on WDMA Rx
+		 * ring full
+		 */
+		mtk_w32(eth, 0x00002300, PSE_PPE_DROP(0));
+		mtk_w32(eth, 0x00002300, PSE_PPE_DROP(1));
+		mtk_w32(eth, 0x00002300, PSE_PPE_DROP(2));
 
 		/* GDM and CDM Threshold */
-		mtk_w32(eth, 0x00000707, MTK_CDMW0_THRES);
+		mtk_w32(eth, 0x08000707, MTK_CDMW0_THRES);
 		mtk_w32(eth, 0x00000077, MTK_CDMW1_THRES);
 
 		/* Disable GDM1 RX CRC stripping */
@@ -4009,7 +4039,7 @@ static int mtk_hw_init(struct mtk_eth *eth, bool reset)
 		mtk_w32(eth, 0x00000300, PSE_DROP_CFG);
 
 		/* PSE should drop packets to port 8/9 on WDMA Rx ring full */
-		mtk_w32(eth, 0x00000300, PSE_PPE0_DROP);
+		mtk_w32(eth, 0x00000300, PSE_PPE_DROP(0));
 
 		/* PSE Free Queue Flow Control  */
 		mtk_w32(eth, 0x01fa01f4, PSE_FQFC_CFG2);
@@ -4655,7 +4685,7 @@ static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np)
 	}
 
 	if (mtk_is_netsys_v3_or_greater(mac->hw) &&
-	    MTK_HAS_CAPS(mac->hw->soc->caps, MTK_ESW_BIT) &&
+	    MTK_HAS_CAPS(mac->hw->soc->caps, MTK_ESW) &&
 	    id == MTK_GMAC1_ID) {
 		mac->phylink_config.mac_capabilities = MAC_ASYM_PAUSE |
 						       MAC_SYM_PAUSE |
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
index 0d5225f1d3ee..0570623e569d 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
@@ -151,7 +151,15 @@
 #define PSE_FQFC_CFG1		0x100
 #define PSE_FQFC_CFG2		0x104
 #define PSE_DROP_CFG		0x108
-#define PSE_PPE0_DROP		0x110
+#define PSE_PPE_DROP(x)		(0x110 + ((x) * 0x4))
+
+/* PSE Last FreeQ Page Request Control */
+#define PSE_DUMY_REQ		0x10C
+/* PSE_DUMY_REQ is not a typo but actually called like that also in
+ * MediaTek's datasheet
+ */
+#define PSE_DUMMY_WORK_GDM(x)	BIT(16 + (x))
+#define DUMMY_PAGE_THR		0x1
 
 /* PSE Input Queue Reservation Register*/
 #define PSE_IQ_REV(x)		(0x140 + (((x) - 1) << 2))
@@ -1260,6 +1268,7 @@ struct mtk_eth {
 	struct clk			*clks[MTK_CLK_MAX];
 
 	struct mii_bus			*mii_bus;
+	unsigned int			mdc_divider;
 	struct work_struct		pending_work;
 	unsigned long			state;
 
diff --git a/drivers/net/ethernet/mediatek/mtk_ppe_offload.c b/drivers/net/ethernet/mediatek/mtk_ppe_offload.c
index f20bb390df3a..c855fb799ce1 100644
--- a/drivers/net/ethernet/mediatek/mtk_ppe_offload.c
+++ b/drivers/net/ethernet/mediatek/mtk_ppe_offload.c
@@ -34,8 +34,10 @@ struct mtk_flow_data {
 	u16 vlan_in;
 
 	struct {
-		u16 id;
-		__be16 proto;
+		struct {
+			u16 id;
+			__be16 proto;
+		} vlans[2];
 		u8 num;
 	} vlan;
 	struct {
@@ -349,18 +351,19 @@ mtk_flow_offload_replace(struct mtk_eth *eth, struct flow_cls_offload *f,
 		case FLOW_ACTION_CSUM:
 			break;
 		case FLOW_ACTION_VLAN_PUSH:
-			if (data.vlan.num == 1 ||
+			if (data.vlan.num + data.pppoe.num == 2 ||
 			    act->vlan.proto != htons(ETH_P_8021Q))
 				return -EOPNOTSUPP;
 
-			data.vlan.id = act->vlan.vid;
-			data.vlan.proto = act->vlan.proto;
+			data.vlan.vlans[data.vlan.num].id = act->vlan.vid;
+			data.vlan.vlans[data.vlan.num].proto = act->vlan.proto;
 			data.vlan.num++;
 			break;
 		case FLOW_ACTION_VLAN_POP:
 			break;
 		case FLOW_ACTION_PPPOE_PUSH:
-			if (data.pppoe.num == 1)
+			if (data.pppoe.num == 1 ||
+			    data.vlan.num == 2)
 				return -EOPNOTSUPP;
 
 			data.pppoe.sid = act->pppoe.sid;
@@ -450,12 +453,9 @@ mtk_flow_offload_replace(struct mtk_eth *eth, struct flow_cls_offload *f,
 	if (offload_type == MTK_PPE_PKT_TYPE_BRIDGE)
 		foe.bridge.vlan = data.vlan_in;
 
-	if (data.vlan.num == 1) {
-		if (data.vlan.proto != htons(ETH_P_8021Q))
-			return -EOPNOTSUPP;
+	for (i = 0; i < data.vlan.num; i++)
+		mtk_foe_entry_set_vlan(eth, &foe, data.vlan.vlans[i].id);
 
-		mtk_foe_entry_set_vlan(eth, &foe, data.vlan.id);
-	}
 	if (data.pppoe.num == 1)
 		mtk_foe_entry_set_pppoe(eth, &foe, data.pppoe.sid);
 
diff --git a/drivers/net/ethernet/mediatek/mtk_star_emac.c b/drivers/net/ethernet/mediatek/mtk_star_emac.c
index 25989c79c92e..5eb7a97e7eb1 100644
--- a/drivers/net/ethernet/mediatek/mtk_star_emac.c
+++ b/drivers/net/ethernet/mediatek/mtk_star_emac.c
@@ -1163,6 +1163,7 @@ static int mtk_star_tx_poll(struct napi_struct *napi, int budget)
 	struct net_device *ndev = priv->ndev;
 	unsigned int head = ring->head;
 	unsigned int entry = ring->tail;
+	unsigned long flags;
 
 	while (entry != head && count < (MTK_STAR_RING_NUM_DESCS - 1)) {
 		ret = mtk_star_tx_complete_one(priv);
@@ -1182,9 +1183,9 @@ static int mtk_star_tx_poll(struct napi_struct *napi, int budget)
 		netif_wake_queue(ndev);
 
 	if (napi_complete(napi)) {
-		spin_lock(&priv->lock);
+		spin_lock_irqsave(&priv->lock, flags);
 		mtk_star_enable_dma_irq(priv, false, true);
-		spin_unlock(&priv->lock);
+		spin_unlock_irqrestore(&priv->lock, flags);
 	}
 
 	return 0;
@@ -1341,16 +1342,16 @@ push_new_skb:
 static int mtk_star_rx_poll(struct napi_struct *napi, int budget)
 {
 	struct mtk_star_priv *priv;
+	unsigned long flags;
 	int work_done = 0;
 
 	priv = container_of(napi, struct mtk_star_priv, rx_napi);
 
 	work_done = mtk_star_rx(priv, budget);
-	if (work_done < budget) {
-		napi_complete_done(napi, work_done);
-		spin_lock(&priv->lock);
+	if (work_done < budget && napi_complete_done(napi, work_done)) {
+		spin_lock_irqsave(&priv->lock, flags);
 		mtk_star_enable_dma_irq(priv, true, false);
-		spin_unlock(&priv->lock);
+		spin_unlock_irqrestore(&priv->lock, flags);
 	}
 
 	return work_done;
@@ -1467,6 +1468,8 @@ static __maybe_unused int mtk_star_suspend(struct device *dev)
 	if (netif_running(ndev))
 		mtk_star_disable(ndev);
 
+	netif_device_detach(ndev);
+
 	clk_bulk_disable_unprepare(MTK_STAR_NCLKS, priv->clks);
 
 	return 0;
@@ -1491,6 +1494,8 @@ static __maybe_unused int mtk_star_resume(struct device *dev)
 			clk_bulk_disable_unprepare(MTK_STAR_NCLKS, priv->clks);
 	}
 
+	netif_device_attach(ndev);
+
 	return ret;
 }
 
diff --git a/drivers/net/ethernet/mediatek/mtk_wed.c b/drivers/net/ethernet/mediatek/mtk_wed.c
index e212a4ba9275..499ca7000125 100644
--- a/drivers/net/ethernet/mediatek/mtk_wed.c
+++ b/drivers/net/ethernet/mediatek/mtk_wed.c
@@ -2794,7 +2794,6 @@ void mtk_wed_add_hw(struct device_node *np, struct mtk_eth *eth,
 	if (!pdev)
 		goto err_of_node_put;
 
-	get_device(&pdev->dev);
 	irq = platform_get_irq(pdev, 0);
 	if (irq < 0)
 		goto err_put_device;
diff --git a/drivers/net/ethernet/mellanox/mlx4/alloc.c b/drivers/net/ethernet/mellanox/mlx4/alloc.c
index b330020dc0d6..f2bded847e61 100644
--- a/drivers/net/ethernet/mellanox/mlx4/alloc.c
+++ b/drivers/net/ethernet/mellanox/mlx4/alloc.c
@@ -682,9 +682,9 @@ static struct mlx4_db_pgdir *mlx4_alloc_db_pgdir(struct device *dma_device)
 }
 
 static int mlx4_alloc_db_from_pgdir(struct mlx4_db_pgdir *pgdir,
-				    struct mlx4_db *db, int order)
+				    struct mlx4_db *db, unsigned int order)
 {
-	int o;
+	unsigned int o;
 	int i;
 
 	for (o = order; o <= 1; ++o) {
@@ -712,7 +712,7 @@ found:
 	return 0;
 }
 
-int mlx4_db_alloc(struct mlx4_dev *dev, struct mlx4_db *db, int order)
+int mlx4_db_alloc(struct mlx4_dev *dev, struct mlx4_db *db, unsigned int order)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	struct mlx4_db_pgdir *pgdir;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_clock.c b/drivers/net/ethernet/mellanox/mlx4/en_clock.c
index cd754cd76bde..d73a2044dc26 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_clock.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_clock.c
@@ -249,7 +249,7 @@ static const struct ptp_clock_info mlx4_en_ptp_clock_info = {
 static u32 freq_to_shift(u16 freq)
 {
 	u32 freq_khz = freq * 1000;
-	u64 max_val_cycles = freq_khz * 1000 * MLX4_EN_WRAP_AROUND_SEC;
+	u64 max_val_cycles = freq_khz * 1000ULL * MLX4_EN_WRAP_AROUND_SEC;
 	u64 max_val_cycles_rounded = 1ULL << fls64(max_val_cycles - 1);
 	/* calculate max possible multiplier in order to fit in 64bit */
 	u64 max_mul = div64_u64(ULLONG_MAX, max_val_cycles_rounded);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index cd17a3f4faf8..a68cd3f0304c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -1897,6 +1897,7 @@ static int mlx4_en_get_ts_info(struct net_device *dev,
 	if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_TS) {
 		info->so_timestamping |=
 			SOF_TIMESTAMPING_TX_HARDWARE |
+			SOF_TIMESTAMPING_TX_SOFTWARE |
 			SOF_TIMESTAMPING_RX_HARDWARE |
 			SOF_TIMESTAMPING_RAW_HARDWARE;
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 1ddb11cb25f9..6e077d202827 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -450,6 +450,8 @@ int mlx4_en_process_tx_cq(struct net_device *dev,
 
 	if (unlikely(!priv->port_up))
 		return 0;
+	if (unlikely(!napi_budget) && cq->type == TX_XDP)
+		return 0;
 
 	netdev_txq_bql_complete_prefetchw(ring->tx_queue);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index e733b81e18a2..5bb4940da59d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -1925,8 +1925,8 @@ static int cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out,
 
 	err = mlx5_cmd_invoke(dev, inb, outb, out, out_size, callback, context,
 			      pages_queue, token, force_polling);
-	if (callback)
-		return err;
+	if (callback && !err)
+		return 0;
 
 	if (err > 0) /* Failed in FW, command didn't execute */
 		err = deliv_status_to_err(err);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
index 98d4306929f3..a2cf3e79693d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
@@ -46,6 +46,9 @@ mlx5_devlink_info_get(struct devlink *devlink, struct devlink_info_req *req,
 	u32 running_fw, stored_fw;
 	int err;
 
+	if (!mlx5_core_is_pf(dev))
+		return 0;
+
 	err = devlink_info_version_fixed_put(req, "fw.psid", dev->board_id);
 	if (err)
 		return err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 57b7298a0e79..e048a667e075 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -94,8 +94,6 @@ struct page_pool;
 #define MLX5_MPWRQ_DEF_LOG_STRIDE_SZ(mdev) \
 	MLX5_MPWRQ_LOG_STRIDE_SZ(mdev, order_base_2(MLX5E_RX_MAX_HEAD))
 
-#define MLX5_MPWRQ_MAX_LOG_WQE_SZ 18
-
 /* Keep in sync with mlx5e_mpwrq_log_wqe_sz.
  * These are theoretical maximums, which can be further restricted by
  * capabilities. These values are used for static resource allocations and
@@ -385,7 +383,6 @@ enum {
 	MLX5E_SQ_STATE_VLAN_NEED_L2_INLINE,
 	MLX5E_SQ_STATE_PENDING_XSK_TX,
 	MLX5E_SQ_STATE_PENDING_TLS_RX_RESYNC,
-	MLX5E_SQ_STATE_XDP_MULTIBUF,
 	MLX5E_NUM_SQ_STATES, /* Must be kept last */
 };
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
index 1e8b7d330701..b5aac0e1a68e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
@@ -18,7 +18,8 @@ enum {
 
 enum {
 	MLX5E_TC_PRIO = 0,
-	MLX5E_NIC_PRIO
+	MLX5E_PROMISC_PRIO,
+	MLX5E_NIC_PRIO,
 };
 
 struct mlx5e_flow_table {
@@ -68,9 +69,13 @@ struct mlx5e_l2_table {
 				 MLX5_HASH_FIELD_SEL_DST_IP   |\
 				 MLX5_HASH_FIELD_SEL_IPSEC_SPI)
 
-/* NIC prio FTS */
+/* NIC promisc FT level */
 enum {
 	MLX5E_PROMISC_FT_LEVEL,
+};
+
+/* NIC prio FTS */
+enum {
 	MLX5E_VLAN_FT_LEVEL,
 	MLX5E_L2_FT_LEVEL,
 	MLX5E_TTC_FT_LEVEL,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
index 64b62ed17b07..58ec5e44aa7a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
@@ -10,6 +10,9 @@
 #include <net/page_pool/types.h>
 #include <net/xdp_sock_drv.h>
 
+#define MLX5_MPWRQ_MAX_LOG_WQE_SZ 18
+#define MLX5_REP_MPWRQ_MAX_LOG_WQE_SZ 17
+
 static u8 mlx5e_mpwrq_min_page_shift(struct mlx5_core_dev *mdev)
 {
 	u8 min_page_shift = MLX5_CAP_GEN_2(mdev, log_min_mkey_entity_size);
@@ -103,18 +106,22 @@ u8 mlx5e_mpwrq_log_wqe_sz(struct mlx5_core_dev *mdev, u8 page_shift,
 			  enum mlx5e_mpwrq_umr_mode umr_mode)
 {
 	u8 umr_entry_size = mlx5e_mpwrq_umr_entry_size(umr_mode);
-	u8 max_pages_per_wqe, max_log_mpwqe_size;
+	u8 max_pages_per_wqe, max_log_wqe_size_calc;
+	u8 max_log_wqe_size_cap;
 	u16 max_wqe_size;
 
 	/* Keep in sync with MLX5_MPWRQ_MAX_PAGES_PER_WQE. */
 	max_wqe_size = mlx5e_get_max_sq_aligned_wqebbs(mdev) * MLX5_SEND_WQE_BB;
 	max_pages_per_wqe = ALIGN_DOWN(max_wqe_size - sizeof(struct mlx5e_umr_wqe),
 				       MLX5_UMR_FLEX_ALIGNMENT) / umr_entry_size;
-	max_log_mpwqe_size = ilog2(max_pages_per_wqe) + page_shift;
+	max_log_wqe_size_calc = ilog2(max_pages_per_wqe) + page_shift;
+
+	WARN_ON_ONCE(max_log_wqe_size_calc < MLX5E_ORDER2_MAX_PACKET_MTU);
 
-	WARN_ON_ONCE(max_log_mpwqe_size < MLX5E_ORDER2_MAX_PACKET_MTU);
+	max_log_wqe_size_cap = mlx5_core_is_ecpf(mdev) ?
+			   MLX5_REP_MPWRQ_MAX_LOG_WQE_SZ : MLX5_MPWRQ_MAX_LOG_WQE_SZ;
 
-	return min_t(u8, max_log_mpwqe_size, MLX5_MPWRQ_MAX_LOG_WQE_SZ);
+	return min_t(u8, max_log_wqe_size_calc, max_log_wqe_size_cap);
 }
 
 u8 mlx5e_mpwrq_pages_per_wqe(struct mlx5_core_dev *mdev, u8 page_shift,
@@ -423,7 +430,7 @@ u8 mlx5e_shampo_get_log_pkt_per_rsrv(struct mlx5_core_dev *mdev,
 				     struct mlx5e_params *params)
 {
 	u32 resrv_size = BIT(mlx5e_shampo_get_log_rsrv_size(mdev, params)) *
-			 PAGE_SIZE;
+			 MLX5E_SHAMPO_WQ_BASE_RESRV_SIZE;
 
 	return order_base_2(DIV_ROUND_UP(resrv_size, params->sw_mtu));
 }
@@ -827,7 +834,8 @@ static u32 mlx5e_shampo_get_log_cq_size(struct mlx5_core_dev *mdev,
 					struct mlx5e_params *params,
 					struct mlx5e_xsk_param *xsk)
 {
-	int rsrv_size = BIT(mlx5e_shampo_get_log_rsrv_size(mdev, params)) * PAGE_SIZE;
+	int rsrv_size = BIT(mlx5e_shampo_get_log_rsrv_size(mdev, params)) *
+		MLX5E_SHAMPO_WQ_BASE_RESRV_SIZE;
 	u16 num_strides = BIT(mlx5e_mpwqe_get_log_num_strides(mdev, params, xsk));
 	int pkt_per_rsrv = BIT(mlx5e_shampo_get_log_pkt_per_rsrv(mdev, params));
 	u8 log_stride_sz = mlx5e_mpwqe_get_log_stride_size(mdev, params, xsk);
@@ -1036,7 +1044,8 @@ u32 mlx5e_shampo_hd_per_wqe(struct mlx5_core_dev *mdev,
 			    struct mlx5e_params *params,
 			    struct mlx5e_rq_param *rq_param)
 {
-	int resv_size = BIT(mlx5e_shampo_get_log_rsrv_size(mdev, params)) * PAGE_SIZE;
+	int resv_size = BIT(mlx5e_shampo_get_log_rsrv_size(mdev, params)) *
+		MLX5E_SHAMPO_WQ_BASE_RESRV_SIZE;
 	u16 num_strides = BIT(mlx5e_mpwqe_get_log_num_strides(mdev, params, NULL));
 	int pkt_per_resv = BIT(mlx5e_shampo_get_log_pkt_per_rsrv(mdev, params));
 	u8 log_stride_sz = mlx5e_mpwqe_get_log_stride_size(mdev, params, NULL);
@@ -1240,7 +1249,6 @@ void mlx5e_build_xdpsq_param(struct mlx5_core_dev *mdev,
 	mlx5e_build_sq_param_common(mdev, param);
 	MLX5_SET(wq, wq, log_wq_sz, params->log_sq_size);
 	param->is_mpw = MLX5E_GET_PFLAG(params, MLX5E_PFLAG_XDP_TX_MPWQE);
-	param->is_xdp_mb = !mlx5e_rx_is_linear_skb(mdev, params, xsk);
 	mlx5e_build_tx_cq_param(mdev, params, &param->cqp);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h
index 3f8986f9d862..bd5877acc5b1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h
@@ -33,7 +33,6 @@ struct mlx5e_sq_param {
 	struct mlx5_wq_param       wq;
 	bool                       is_mpw;
 	bool                       is_tls;
-	bool                       is_xdp_mb;
 	u16                        stop_room;
 };
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c
index 8e25f4ef5ccc..5ae787656a7c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c
@@ -331,6 +331,9 @@ static int port_set_buffer(struct mlx5e_priv *priv,
 	if (err)
 		goto out;
 
+	/* RO bits should be set to 0 on write */
+	MLX5_SET(pbmc_reg, in, port_buffer_size, 0);
+
 	err = mlx5e_port_set_pbmc(mdev, in);
 out:
 	kfree(in);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c
index f0744a45db92..4e461cb03b83 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c
@@ -374,7 +374,7 @@ void mlx5e_reactivate_qos_sq(struct mlx5e_priv *priv, u16 qid, struct netdev_que
 void mlx5e_reset_qdisc(struct net_device *dev, u16 qid)
 {
 	struct netdev_queue *dev_queue = netdev_get_tx_queue(dev, qid);
-	struct Qdisc *qdisc = dev_queue->qdisc_sleeping;
+	struct Qdisc *qdisc = rtnl_dereference(dev_queue->qdisc_sleeping);
 
 	if (!qdisc)
 		return;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c
index 5d128c5b4529..0f5d7ea8956f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c
@@ -48,15 +48,10 @@ mlx5_esw_bridge_lag_rep_get(struct net_device *dev, struct mlx5_eswitch *esw)
 	struct list_head *iter;
 
 	netdev_for_each_lower_dev(dev, lower, iter) {
-		struct mlx5_core_dev *mdev;
-		struct mlx5e_priv *priv;
-
 		if (!mlx5e_eswitch_rep(lower))
 			continue;
 
-		priv = netdev_priv(lower);
-		mdev = priv->mdev;
-		if (mlx5_lag_is_shared_fdb(mdev) && mlx5_esw_bridge_dev_same_esw(lower, esw))
+		if (mlx5_esw_bridge_dev_same_esw(lower, esw))
 			return lower;
 	}
 
@@ -125,7 +120,7 @@ static bool mlx5_esw_bridge_is_local(struct net_device *dev, struct net_device *
 	priv = netdev_priv(rep);
 	mdev = priv->mdev;
 	if (netif_is_lag_master(dev))
-		return mlx5_lag_is_shared_fdb(mdev) && mlx5_lag_is_master(mdev);
+		return mlx5_lag_is_master(mdev);
 	return true;
 }
 
@@ -455,6 +450,9 @@ static int mlx5_esw_bridge_switchdev_event(struct notifier_block *nb,
 	if (!rep)
 		return NOTIFY_DONE;
 
+	if (netif_is_lag_master(dev) && !mlx5_lag_is_shared_fdb(esw->dev))
+		return NOTIFY_DONE;
+
 	switch (event) {
 	case SWITCHDEV_FDB_ADD_TO_BRIDGE:
 		fdb_info = container_of(info,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
index 09433b91be17..dbd9482359e1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
@@ -16,7 +16,6 @@ static const char * const sq_sw_state_type_name[] = {
 	[MLX5E_SQ_STATE_VLAN_NEED_L2_INLINE] = "vlan_need_l2_inline",
 	[MLX5E_SQ_STATE_PENDING_XSK_TX] = "pending_xsk_tx",
 	[MLX5E_SQ_STATE_PENDING_TLS_RX_RESYNC] = "pending_tls_rx_resync",
-	[MLX5E_SQ_STATE_XDP_MULTIBUF] = "xdp_multibuf",
 };
 
 static int mlx5e_wait_for_sq_flush(struct mlx5e_txqsq *sq)
@@ -177,6 +176,7 @@ static int mlx5e_tx_reporter_ptpsq_unhealthy_recover(void *ctx)
 
 	priv = ptpsq->txqsq.priv;
 
+	rtnl_lock();
 	mutex_lock(&priv->state_lock);
 	chs = &priv->channels;
 	netdev = priv->netdev;
@@ -184,22 +184,19 @@ static int mlx5e_tx_reporter_ptpsq_unhealthy_recover(void *ctx)
 	carrier_ok = netif_carrier_ok(netdev);
 	netif_carrier_off(netdev);
 
-	rtnl_lock();
 	mlx5e_deactivate_priv_channels(priv);
-	rtnl_unlock();
 
 	mlx5e_ptp_close(chs->ptp);
 	err = mlx5e_ptp_open(priv, &chs->params, chs->c[0]->lag_port, &chs->ptp);
 
-	rtnl_lock();
 	mlx5e_activate_priv_channels(priv);
-	rtnl_unlock();
 
 	/* return carrier back if needed */
 	if (carrier_ok)
 		netif_carrier_on(netdev);
 
 	mutex_unlock(&priv->state_lock);
+	rtnl_unlock();
 
 	return err;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c
index e4e487c8431b..b9cf79e27124 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c
@@ -165,9 +165,6 @@ static int mlx5e_tc_tun_parse_vxlan(struct mlx5e_priv *priv,
 	struct flow_match_enc_keyid enc_keyid;
 	void *misc_c, *misc_v;
 
-	misc_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters);
-	misc_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters);
-
 	if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_KEYID))
 		return 0;
 
@@ -182,6 +179,30 @@ static int mlx5e_tc_tun_parse_vxlan(struct mlx5e_priv *priv,
 		err = mlx5e_tc_tun_parse_vxlan_gbp_option(priv, spec, f);
 		if (err)
 			return err;
+
+		/* We can't mix custom tunnel headers with symbolic ones and we
+		 * don't have a symbolic field name for GBP, so we use custom
+		 * tunnel headers in this case. We need hardware support to
+		 * match on custom tunnel headers, but we already know it's
+		 * supported because the previous call successfully checked for
+		 * that.
+		 */
+		misc_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+				      misc_parameters_5);
+		misc_v = MLX5_ADDR_OF(fte_match_param, spec->match_value,
+				      misc_parameters_5);
+
+		/* Shift by 8 to account for the reserved bits in the vxlan
+		 * header after the VNI.
+		 */
+		MLX5_SET(fte_match_set_misc5, misc_c, tunnel_header_1,
+			 be32_to_cpu(enc_keyid.mask->keyid) << 8);
+		MLX5_SET(fte_match_set_misc5, misc_v, tunnel_header_1,
+			 be32_to_cpu(enc_keyid.key->keyid) << 8);
+
+		spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS_5;
+
+		return 0;
 	}
 
 	/* match on VNI is required */
@@ -195,6 +216,11 @@ static int mlx5e_tc_tun_parse_vxlan(struct mlx5e_priv *priv,
 		return -EOPNOTSUPP;
 	}
 
+	misc_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+			      misc_parameters);
+	misc_v = MLX5_ADDR_OF(fte_match_param, spec->match_value,
+			      misc_parameters);
+
 	MLX5_SET(fte_match_set_misc, misc_c, vxlan_vni,
 		 be32_to_cpu(enc_keyid.mask->keyid));
 	MLX5_SET(fte_match_set_misc, misc_v, vxlan_vni,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index 4610621a340e..14192da4b8ed 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -546,6 +546,7 @@ mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd,
 	bool inline_ok;
 	bool linear;
 	u16 pi;
+	int i;
 
 	struct mlx5e_xdpsq_stats *stats = sq->stats;
 
@@ -612,41 +613,33 @@ mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd,
 
 	cseg->opmod_idx_opcode = cpu_to_be32((sq->pc << 8) | MLX5_OPCODE_SEND);
 
-	if (test_bit(MLX5E_SQ_STATE_XDP_MULTIBUF, &sq->state)) {
-		int i;
-
-		memset(&cseg->trailer, 0, sizeof(cseg->trailer));
-		memset(eseg, 0, sizeof(*eseg) - sizeof(eseg->trailer));
-
-		eseg->inline_hdr.sz = cpu_to_be16(inline_hdr_sz);
+	memset(&cseg->trailer, 0, sizeof(cseg->trailer));
+	memset(eseg, 0, sizeof(*eseg) - sizeof(eseg->trailer));
 
-		for (i = 0; i < num_frags; i++) {
-			skb_frag_t *frag = &xdptxdf->sinfo->frags[i];
-			dma_addr_t addr;
+	eseg->inline_hdr.sz = cpu_to_be16(inline_hdr_sz);
 
-			addr = xdptxdf->dma_arr ? xdptxdf->dma_arr[i] :
-				page_pool_get_dma_addr(skb_frag_page(frag)) +
-				skb_frag_off(frag);
+	for (i = 0; i < num_frags; i++) {
+		skb_frag_t *frag = &xdptxdf->sinfo->frags[i];
+		dma_addr_t addr;
 
-			dseg->addr = cpu_to_be64(addr);
-			dseg->byte_count = cpu_to_be32(skb_frag_size(frag));
-			dseg->lkey = sq->mkey_be;
-			dseg++;
-		}
+		addr = xdptxdf->dma_arr ? xdptxdf->dma_arr[i] :
+			page_pool_get_dma_addr(skb_frag_page(frag)) +
+			skb_frag_off(frag);
 
-		cseg->qpn_ds = cpu_to_be32((sq->sqn << 8) | ds_cnt);
+		dseg->addr = cpu_to_be64(addr);
+		dseg->byte_count = cpu_to_be32(skb_frag_size(frag));
+		dseg->lkey = sq->mkey_be;
+		dseg++;
+	}
 
-		sq->db.wqe_info[pi] = (struct mlx5e_xdp_wqe_info) {
-			.num_wqebbs = num_wqebbs,
-			.num_pkts = 1,
-		};
+	cseg->qpn_ds = cpu_to_be32((sq->sqn << 8) | ds_cnt);
 
-		sq->pc += num_wqebbs;
-	} else {
-		cseg->fm_ce_se = 0;
+	sq->db.wqe_info[pi] = (struct mlx5e_xdp_wqe_info) {
+		.num_wqebbs = num_wqebbs,
+		.num_pkts = 1,
+	};
 
-		sq->pc++;
-	}
+	sq->pc += num_wqebbs;
 
 	xsk_tx_metadata_request(meta, &mlx5e_xsk_tx_metadata_ops, eseg);
 
@@ -713,8 +706,8 @@ static void mlx5e_free_xdpsq_desc(struct mlx5e_xdpsq *sq,
 				xdpi = mlx5e_xdpi_fifo_pop(xdpi_fifo);
 				page = xdpi.page.page;
 
-				/* No need to check ((page->pp_magic & ~0x3UL) == PP_SIGNATURE)
-				 * as we know this is a page_pool page.
+				/* No need to check page_pool_page_is_pp() as we
+				 * know this is a page_pool page.
 				 */
 				page_pool_recycle_direct(page->pp, page);
 			} while (++n < num);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
index 1baf8933a07c..39dcbf863421 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
@@ -266,8 +266,7 @@ static void mlx5e_ipsec_init_macs(struct mlx5e_ipsec_sa_entry *sa_entry,
 				  struct mlx5_accel_esp_xfrm_attrs *attrs)
 {
 	struct mlx5_core_dev *mdev = mlx5e_ipsec_sa2dev(sa_entry);
-	struct xfrm_state *x = sa_entry->x;
-	struct net_device *netdev;
+	struct net_device *netdev = sa_entry->dev;
 	struct neighbour *n;
 	u8 addr[ETH_ALEN];
 	const void *pkey;
@@ -277,8 +276,6 @@ static void mlx5e_ipsec_init_macs(struct mlx5e_ipsec_sa_entry *sa_entry,
 	    attrs->type != XFRM_DEV_OFFLOAD_PACKET)
 		return;
 
-	netdev = x->xso.real_dev;
-
 	mlx5_query_mac_address(mdev, addr);
 	switch (attrs->dir) {
 	case XFRM_DEV_OFFLOAD_IN:
@@ -707,6 +704,7 @@ static int mlx5e_xfrm_add_state(struct xfrm_state *x,
 		return -ENOMEM;
 
 	sa_entry->x = x;
+	sa_entry->dev = netdev;
 	sa_entry->ipsec = ipsec;
 	/* Check if this SA is originated from acquire flow temporary SA */
 	if (x->xso.flags & XFRM_DEV_OFFLOAD_FLAG_ACQ)
@@ -849,8 +847,6 @@ static int mlx5e_ipsec_netevent_event(struct notifier_block *nb,
 	struct mlx5e_ipsec_sa_entry *sa_entry;
 	struct mlx5e_ipsec *ipsec;
 	struct neighbour *n = ptr;
-	struct net_device *netdev;
-	struct xfrm_state *x;
 	unsigned long idx;
 
 	if (event != NETEVENT_NEIGH_UPDATE || !(n->nud_state & NUD_VALID))
@@ -870,11 +866,9 @@ static int mlx5e_ipsec_netevent_event(struct notifier_block *nb,
 				continue;
 		}
 
-		x = sa_entry->x;
-		netdev = x->xso.real_dev;
 		data = sa_entry->work->data;
 
-		neigh_ha_snapshot(data->addr, n, netdev);
+		neigh_ha_snapshot(data->addr, n, sa_entry->dev);
 		queue_work(ipsec->wq, &sa_entry->work->work);
 	}
 
@@ -1005,8 +999,8 @@ static void mlx5e_xfrm_update_stats(struct xfrm_state *x)
 	size_t headers;
 
 	lockdep_assert(lockdep_is_held(&x->lock) ||
-		       lockdep_is_held(&dev_net(x->xso.real_dev)->xfrm.xfrm_cfg_mutex) ||
-		       lockdep_is_held(&dev_net(x->xso.real_dev)->xfrm.xfrm_state_lock));
+		       lockdep_is_held(&net->xfrm.xfrm_cfg_mutex) ||
+		       lockdep_is_held(&net->xfrm.xfrm_state_lock));
 
 	if (x->xso.flags & XFRM_DEV_OFFLOAD_FLAG_ACQ)
 		return;
@@ -1141,7 +1135,7 @@ mlx5e_ipsec_build_accel_pol_attrs(struct mlx5e_ipsec_pol_entry *pol_entry,
 static int mlx5e_xfrm_add_policy(struct xfrm_policy *x,
 				 struct netlink_ext_ack *extack)
 {
-	struct net_device *netdev = x->xdo.real_dev;
+	struct net_device *netdev = x->xdo.dev;
 	struct mlx5e_ipsec_pol_entry *pol_entry;
 	struct mlx5e_priv *priv;
 	int err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
index 7d943e93cf6d..9aff779c77c8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
@@ -260,6 +260,7 @@ struct mlx5e_ipsec_limits {
 struct mlx5e_ipsec_sa_entry {
 	struct mlx5e_ipsec_esn_state esn_state;
 	struct xfrm_state *x;
+	struct net_device *dev;
 	struct mlx5e_ipsec *ipsec;
 	struct mlx5_accel_esp_xfrm_attrs attrs;
 	void (*set_iv_op)(struct sk_buff *skb, struct xfrm_state *x,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
index 57861d34d46f..59b9653f573c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
@@ -165,6 +165,25 @@ static void ipsec_rx_status_pass_destroy(struct mlx5e_ipsec *ipsec,
 #endif
 }
 
+static void ipsec_rx_rule_add_match_obj(struct mlx5e_ipsec_sa_entry *sa_entry,
+					struct mlx5e_ipsec_rx *rx,
+					struct mlx5_flow_spec *spec)
+{
+	struct mlx5e_ipsec *ipsec = sa_entry->ipsec;
+
+	if (rx == ipsec->rx_esw) {
+		mlx5_esw_ipsec_rx_rule_add_match_obj(sa_entry, spec);
+	} else {
+		MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
+				 misc_parameters_2.metadata_reg_c_2);
+		MLX5_SET(fte_match_param, spec->match_value,
+			 misc_parameters_2.metadata_reg_c_2,
+			 sa_entry->ipsec_obj_id | BIT(31));
+
+		spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS_2;
+	}
+}
+
 static int rx_add_rule_drop_auth_trailer(struct mlx5e_ipsec_sa_entry *sa_entry,
 					 struct mlx5e_ipsec_rx *rx)
 {
@@ -200,11 +219,8 @@ static int rx_add_rule_drop_auth_trailer(struct mlx5e_ipsec_sa_entry *sa_entry,
 
 	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, misc_parameters_2.ipsec_syndrome);
 	MLX5_SET(fte_match_param, spec->match_value, misc_parameters_2.ipsec_syndrome, 1);
-	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, misc_parameters_2.metadata_reg_c_2);
-	MLX5_SET(fte_match_param, spec->match_value,
-		 misc_parameters_2.metadata_reg_c_2,
-		 sa_entry->ipsec_obj_id | BIT(31));
 	spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2;
+	ipsec_rx_rule_add_match_obj(sa_entry, rx, spec);
 	rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1);
 	if (IS_ERR(rule)) {
 		err = PTR_ERR(rule);
@@ -281,10 +297,8 @@ static int rx_add_rule_drop_replay(struct mlx5e_ipsec_sa_entry *sa_entry, struct
 
 	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, misc_parameters_2.metadata_reg_c_4);
 	MLX5_SET(fte_match_param, spec->match_value, misc_parameters_2.metadata_reg_c_4, 1);
-	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, misc_parameters_2.metadata_reg_c_2);
-	MLX5_SET(fte_match_param, spec->match_value,  misc_parameters_2.metadata_reg_c_2,
-		 sa_entry->ipsec_obj_id | BIT(31));
 	spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2;
+	ipsec_rx_rule_add_match_obj(sa_entry, rx, spec);
 	rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1);
 	if (IS_ERR(rule)) {
 		err = PTR_ERR(rule);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
index 727fa7c18523..6056106edcc6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
@@ -327,6 +327,10 @@ void mlx5e_ipsec_offload_handle_rx_skb(struct net_device *netdev,
 	if (unlikely(!sa_entry)) {
 		rcu_read_unlock();
 		atomic64_inc(&ipsec->sw_stats.ipsec_rx_drop_sadb_miss);
+		/* Clear secpath to prevent invalid dereference
+		 * in downstream XFRM policy checks.
+		 */
+		secpath_reset(skb);
 		return;
 	}
 	xfrm_state_hold(sa_entry->x);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dim.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dim.c
index 298bb74ec5e9..d1d629697e28 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_dim.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dim.c
@@ -113,7 +113,7 @@ int mlx5e_dim_rx_change(struct mlx5e_rq *rq, bool enable)
 		__set_bit(MLX5E_RQ_STATE_DIM, &rq->state);
 	} else {
 		__clear_bit(MLX5E_RQ_STATE_DIM, &rq->state);
-
+		synchronize_net();
 		mlx5e_dim_disable(rq->dim);
 		rq->dim = NULL;
 	}
@@ -140,7 +140,7 @@ int mlx5e_dim_tx_change(struct mlx5e_txqsq *sq, bool enable)
 		__set_bit(MLX5E_SQ_STATE_DIM, &sq->state);
 	} else {
 		__clear_bit(MLX5E_SQ_STATE_DIM, &sq->state);
-
+		synchronize_net();
 		mlx5e_dim_disable(sq->dim);
 		sq->dim = NULL;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
index 05058710d2c7..537e732085b2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
@@ -776,7 +776,7 @@ static int mlx5e_create_promisc_table(struct mlx5e_flow_steering *fs)
 	ft_attr.max_fte = MLX5E_PROMISC_TABLE_SIZE;
 	ft_attr.autogroup.max_num_groups = 1;
 	ft_attr.level = MLX5E_PROMISC_FT_LEVEL;
-	ft_attr.prio = MLX5E_NIC_PRIO;
+	ft_attr.prio = MLX5E_PROMISC_PRIO;
 
 	ft->t = mlx5_create_auto_grouped_flow_table(fs->ns, &ft_attr);
 	if (IS_ERR(ft->t)) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 62b8a7c1c6b5..4a2f58a9d706 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -2030,41 +2030,12 @@ int mlx5e_open_xdpsq(struct mlx5e_channel *c, struct mlx5e_params *params,
 	csp.min_inline_mode = sq->min_inline_mode;
 	set_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
 
-	if (param->is_xdp_mb)
-		set_bit(MLX5E_SQ_STATE_XDP_MULTIBUF, &sq->state);
-
 	err = mlx5e_create_sq_rdy(c->mdev, param, &csp, 0, &sq->sqn);
 	if (err)
 		goto err_free_xdpsq;
 
 	mlx5e_set_xmit_fp(sq, param->is_mpw);
 
-	if (!param->is_mpw && !test_bit(MLX5E_SQ_STATE_XDP_MULTIBUF, &sq->state)) {
-		unsigned int ds_cnt = MLX5E_TX_WQE_EMPTY_DS_COUNT + 1;
-		unsigned int inline_hdr_sz = 0;
-		int i;
-
-		if (sq->min_inline_mode != MLX5_INLINE_MODE_NONE) {
-			inline_hdr_sz = MLX5E_XDP_MIN_INLINE;
-			ds_cnt++;
-		}
-
-		/* Pre initialize fixed WQE fields */
-		for (i = 0; i < mlx5_wq_cyc_get_size(&sq->wq); i++) {
-			struct mlx5e_tx_wqe      *wqe  = mlx5_wq_cyc_get_wqe(&sq->wq, i);
-			struct mlx5_wqe_ctrl_seg *cseg = &wqe->ctrl;
-			struct mlx5_wqe_eth_seg  *eseg = &wqe->eth;
-
-			sq->db.wqe_info[i] = (struct mlx5e_xdp_wqe_info) {
-				.num_wqebbs = 1,
-				.num_pkts   = 1,
-			};
-
-			cseg->qpn_ds = cpu_to_be32((sq->sqn << 8) | ds_cnt);
-			eseg->inline_hdr.sz = cpu_to_be16(inline_hdr_sz);
-		}
-	}
-
 	return 0;
 
 err_free_xdpsq:
@@ -3788,8 +3759,11 @@ static int mlx5e_setup_tc_mqprio(struct mlx5e_priv *priv,
 	/* MQPRIO is another toplevel qdisc that can't be attached
 	 * simultaneously with the offloaded HTB.
 	 */
-	if (WARN_ON(mlx5e_selq_is_htb_enabled(&priv->selq)))
-		return -EINVAL;
+	if (mlx5e_selq_is_htb_enabled(&priv->selq)) {
+		NL_SET_ERR_MSG_MOD(mqprio->extack,
+				   "MQPRIO cannot be configured when HTB offload is enabled.");
+		return -EOPNOTSUPP;
+	}
 
 	switch (mqprio->mode) {
 	case TC_MQPRIO_MODE_DCB:
@@ -4344,6 +4318,10 @@ static netdev_features_t mlx5e_fix_uplink_rep_features(struct net_device *netdev
 	if (netdev->features & NETIF_F_HW_VLAN_CTAG_FILTER)
 		netdev_warn(netdev, "Disabling HW_VLAN CTAG FILTERING, not supported in switchdev mode\n");
 
+	features &= ~NETIF_F_HW_MACSEC;
+	if (netdev->features & NETIF_F_HW_MACSEC)
+		netdev_warn(netdev, "Disabling HW MACsec offload, not supported in switchdev mode\n");
+
 	return features;
 }
 
@@ -5099,11 +5077,9 @@ static int mlx5e_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	struct mlx5_core_dev *mdev = priv->mdev;
 	u8 mode, setting;
-	int err;
 
-	err = mlx5_eswitch_get_vepa(mdev->priv.eswitch, &setting);
-	if (err)
-		return err;
+	if (mlx5_eswitch_get_vepa(mdev->priv.eswitch, &setting))
+		return -EOPNOTSUPP;
 	mode = setting ? BRIDGE_MODE_VEPA : BRIDGE_MODE_VEB;
 	return ndo_dflt_bridge_getlink(skb, pid, seq, dev,
 				       mode,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 0657d1076535..18ec392d1740 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -65,6 +65,7 @@
 #define MLX5E_REP_PARAMS_DEF_LOG_SQ_SIZE \
 	max(0x7, MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE)
 #define MLX5E_REP_PARAMS_DEF_NUM_CHANNELS 1
+#define MLX5E_REP_PARAMS_DEF_LOG_RQ_SIZE 0x8
 
 static const char mlx5e_rep_driver_name[] = "mlx5e_rep";
 
@@ -854,6 +855,8 @@ static void mlx5e_build_rep_params(struct net_device *netdev)
 
 	/* RQ */
 	mlx5e_build_rq_params(mdev, params);
+	if (!mlx5e_is_uplink_rep(priv) && mlx5_core_is_ecpf(mdev))
+		params->log_rq_mtu_frames = MLX5E_REP_PARAMS_DEF_LOG_RQ_SIZE;
 
 	/* If netdev is already registered (e.g. move from nic profile to uplink,
 	 * RTNL lock must be held before triggering netdev notifiers.
@@ -885,6 +888,8 @@ static void mlx5e_build_rep_netdev(struct net_device *netdev,
 	netdev->ethtool_ops = &mlx5e_rep_ethtool_ops;
 
 	netdev->watchdog_timeo    = 15 * HZ;
+	if (mlx5_core_is_ecpf(mdev))
+		netdev->tx_queue_len = 1 << MLX5E_REP_PARAMS_DEF_LOG_SQ_SIZE;
 
 #if IS_ENABLED(CONFIG_MLX5_CLS_ACT)
 	netdev->hw_features    |= NETIF_F_HW_TC;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 8e24ba96c779..673043d9ed11 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -1156,8 +1156,9 @@ static void mlx5e_lro_update_tcp_hdr(struct mlx5_cqe64 *cqe, struct tcphdr *tcp)
 	}
 }
 
-static void mlx5e_lro_update_hdr(struct sk_buff *skb, struct mlx5_cqe64 *cqe,
-				 u32 cqe_bcnt)
+static unsigned int mlx5e_lro_update_hdr(struct sk_buff *skb,
+					 struct mlx5_cqe64 *cqe,
+					 u32 cqe_bcnt)
 {
 	struct ethhdr	*eth = (struct ethhdr *)(skb->data);
 	struct tcphdr	*tcp;
@@ -1207,6 +1208,8 @@ static void mlx5e_lro_update_hdr(struct sk_buff *skb, struct mlx5_cqe64 *cqe,
 		tcp->check = tcp_v6_check(payload_len, &ipv6->saddr,
 					  &ipv6->daddr, check);
 	}
+
+	return (unsigned int)((unsigned char *)tcp + tcp->doff * 4 - skb->data);
 }
 
 static void *mlx5e_shampo_get_packet_hd(struct mlx5e_rq *rq, u16 header_index)
@@ -1563,8 +1566,10 @@ static inline void mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe,
 		mlx5e_macsec_offload_handle_rx_skb(netdev, skb, cqe);
 
 	if (lro_num_seg > 1) {
-		mlx5e_lro_update_hdr(skb, cqe, cqe_bcnt);
-		skb_shinfo(skb)->gso_size = DIV_ROUND_UP(cqe_bcnt, lro_num_seg);
+		unsigned int hdrlen = mlx5e_lro_update_hdr(skb, cqe, cqe_bcnt);
+
+		skb_shinfo(skb)->gso_size = DIV_ROUND_UP(cqe_bcnt - hdrlen, lro_num_seg);
+		skb_shinfo(skb)->gso_segs = lro_num_seg;
 		/* Subtract one since we already counted this as one
 		 * "regular" packet in mlx5e_complete_rx_cqe()
 		 */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
index 1d60465cc2ca..2f7a543feca6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
@@ -166,6 +166,9 @@ mlx5e_test_loopback_validate(struct sk_buff *skb,
 	struct udphdr *udph;
 	struct iphdr *iph;
 
+	if (skb_linearize(skb))
+		goto out;
+
 	/* We are only going to peek, no need to clone the SKB */
 	if (MLX5E_TEST_PKT_SIZE - ETH_HLEN > skb_headlen(skb))
 		goto out;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 6b3b1afe8312..4d766eea32a3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1750,9 +1750,6 @@ extra_split_attr_dests_needed(struct mlx5e_tc_flow *flow, struct mlx5_flow_attr
 	    !list_is_first(&attr->list, &flow->attrs))
 		return 0;
 
-	if (flow_flag_test(flow, SLOW))
-		return 0;
-
 	esw_attr = attr->esw_attr;
 	if (!esw_attr->split_count ||
 	    esw_attr->split_count == esw_attr->out_count - 1)
@@ -1766,7 +1763,7 @@ extra_split_attr_dests_needed(struct mlx5e_tc_flow *flow, struct mlx5_flow_attr
 	for (i = esw_attr->split_count; i < esw_attr->out_count; i++) {
 		/* external dest with encap is considered as internal by firmware */
 		if (esw_attr->dests[i].vport == MLX5_VPORT_UPLINK &&
-		    !(esw_attr->dests[i].flags & MLX5_ESW_DEST_ENCAP_VALID))
+		    !(esw_attr->dests[i].flags & MLX5_ESW_DEST_ENCAP))
 			ext_dest = true;
 		else
 			int_dest = true;
@@ -2031,9 +2028,8 @@ err_out:
 	return err;
 }
 
-static bool mlx5_flow_has_geneve_opt(struct mlx5e_tc_flow *flow)
+static bool mlx5_flow_has_geneve_opt(struct mlx5_flow_spec *spec)
 {
-	struct mlx5_flow_spec *spec = &flow->attr->parse_attr->spec;
 	void *headers_v = MLX5_ADDR_OF(fte_match_param,
 				       spec->match_value,
 				       misc_parameters_3);
@@ -2072,7 +2068,7 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv,
 	}
 	complete_all(&flow->del_hw_done);
 
-	if (mlx5_flow_has_geneve_opt(flow))
+	if (mlx5_flow_has_geneve_opt(&attr->parse_attr->spec))
 		mlx5_geneve_tlv_option_del(priv->mdev->geneve);
 
 	if (flow->decap_route)
@@ -2577,12 +2573,13 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv,
 
 		err = mlx5e_tc_tun_parse(filter_dev, priv, tmp_spec, f, match_level);
 		if (err) {
-			kvfree(tmp_spec);
 			NL_SET_ERR_MSG_MOD(extack, "Failed to parse tunnel attributes");
 			netdev_warn(priv->netdev, "Failed to parse tunnel attributes");
-			return err;
+		} else {
+			err = mlx5e_tc_set_attr_rx_tun(flow, tmp_spec);
 		}
-		err = mlx5e_tc_set_attr_rx_tun(flow, tmp_spec);
+		if (mlx5_flow_has_geneve_opt(tmp_spec))
+			mlx5_geneve_tlv_option_del(priv->mdev->geneve);
 		kvfree(tmp_spec);
 		if (err)
 			return err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 68cb86b37e56..4241cf07a030 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -887,8 +887,8 @@ static void comp_irq_release_sf(struct mlx5_core_dev *dev, u16 vecidx)
 
 static int comp_irq_request_sf(struct mlx5_core_dev *dev, u16 vecidx)
 {
+	struct mlx5_irq_pool *pool = mlx5_irq_table_get_comp_irq_pool(dev);
 	struct mlx5_eq_table *table = dev->priv.eq_table;
-	struct mlx5_irq_pool *pool = mlx5_irq_pool_get(dev);
 	struct irq_affinity_desc af_desc = {};
 	struct mlx5_irq *irq;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c
index ed977ae75fab..4bba2884c1c0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c
@@ -85,6 +85,19 @@ err_header_alloc:
 	return err;
 }
 
+void mlx5_esw_ipsec_rx_rule_add_match_obj(struct mlx5e_ipsec_sa_entry *sa_entry,
+					  struct mlx5_flow_spec *spec)
+{
+	MLX5_SET(fte_match_param, spec->match_criteria,
+		 misc_parameters_2.metadata_reg_c_1,
+		 ESW_IPSEC_RX_MAPPED_ID_MATCH_MASK);
+	MLX5_SET(fte_match_param, spec->match_value,
+		 misc_parameters_2.metadata_reg_c_1,
+		 sa_entry->rx_mapped_id << ESW_ZONE_ID_BITS);
+
+	spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS_2;
+}
+
 void mlx5_esw_ipsec_rx_id_mapping_remove(struct mlx5e_ipsec_sa_entry *sa_entry)
 {
 	struct mlx5e_ipsec *ipsec = sa_entry->ipsec;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h
index ac9c65b89166..514c15258b1d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h
@@ -20,6 +20,8 @@ int mlx5_esw_ipsec_rx_ipsec_obj_id_search(struct mlx5e_priv *priv, u32 id,
 void mlx5_esw_ipsec_tx_create_attr_set(struct mlx5e_ipsec *ipsec,
 				       struct mlx5e_ipsec_tx_create_attr *attr);
 void mlx5_esw_ipsec_restore_dest_uplink(struct mlx5_core_dev *mdev);
+void mlx5_esw_ipsec_rx_rule_add_match_obj(struct mlx5e_ipsec_sa_entry *sa_entry,
+					  struct mlx5_flow_spec *spec);
 #else
 static inline void mlx5_esw_ipsec_rx_create_attr_set(struct mlx5e_ipsec *ipsec,
 						     struct mlx5e_ipsec_rx_create_attr *attr) {}
@@ -48,5 +50,8 @@ static inline void mlx5_esw_ipsec_tx_create_attr_set(struct mlx5e_ipsec *ipsec,
 						     struct mlx5e_ipsec_tx_create_attr *attr) {}
 
 static inline void mlx5_esw_ipsec_restore_dest_uplink(struct mlx5_core_dev *mdev) {}
+static inline void
+mlx5_esw_ipsec_rx_rule_add_match_obj(struct mlx5e_ipsec_sa_entry *sa_entry,
+				     struct mlx5_flow_spec *spec) {}
 #endif /* CONFIG_MLX5_ESWITCH */
 #endif /* __MLX5_ESW_IPSEC_FS_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c
index 8587cd572da5..bdb825aa8726 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c
@@ -96,7 +96,7 @@ static int esw_create_legacy_fdb_table(struct mlx5_eswitch *esw)
 	if (!flow_group_in)
 		return -ENOMEM;
 
-	ft_attr.max_fte = POOL_NEXT_SIZE;
+	ft_attr.max_fte = MLX5_FS_MAX_POOL_SIZE;
 	ft_attr.prio = LEGACY_FDB_PRIO;
 	fdb = mlx5_create_flow_table(root_ns, &ft_attr);
 	if (IS_ERR(fdb)) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 7aef30dbd82d..6544546a1153 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1295,12 +1295,15 @@ mlx5_eswitch_enable_pf_vf_vports(struct mlx5_eswitch *esw,
 		ret = mlx5_eswitch_load_pf_vf_vport(esw, MLX5_VPORT_ECPF, enabled_events);
 		if (ret)
 			goto ecpf_err;
-		if (mlx5_core_ec_sriov_enabled(esw->dev)) {
-			ret = mlx5_eswitch_load_ec_vf_vports(esw, esw->esw_funcs.num_ec_vfs,
-							     enabled_events);
-			if (ret)
-				goto ec_vf_err;
-		}
+	}
+
+	/* Enable ECVF vports */
+	if (mlx5_core_ec_sriov_enabled(esw->dev)) {
+		ret = mlx5_eswitch_load_ec_vf_vports(esw,
+						     esw->esw_funcs.num_ec_vfs,
+						     enabled_events);
+		if (ret)
+			goto ec_vf_err;
 	}
 
 	/* Enable VF vports */
@@ -1331,9 +1334,11 @@ void mlx5_eswitch_disable_pf_vf_vports(struct mlx5_eswitch *esw)
 {
 	mlx5_eswitch_unload_vf_vports(esw, esw->esw_funcs.num_vfs);
 
+	if (mlx5_core_ec_sriov_enabled(esw->dev))
+		mlx5_eswitch_unload_ec_vf_vports(esw,
+						 esw->esw_funcs.num_ec_vfs);
+
 	if (mlx5_ecpf_vport_exists(esw->dev)) {
-		if (mlx5_core_ec_sriov_enabled(esw->dev))
-			mlx5_eswitch_unload_ec_vf_vports(esw, esw->esw_funcs.num_vfs);
 		mlx5_eswitch_unload_pf_vf_vport(esw, MLX5_VPORT_ECPF);
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 3950b1d4b3d8..558962423521 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -1181,19 +1181,19 @@ static void esw_set_peer_miss_rule_source_port(struct mlx5_eswitch *esw,
 static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw,
 				       struct mlx5_core_dev *peer_dev)
 {
+	struct mlx5_eswitch *peer_esw = peer_dev->priv.eswitch;
 	struct mlx5_flow_destination dest = {};
 	struct mlx5_flow_act flow_act = {0};
 	struct mlx5_flow_handle **flows;
-	/* total vports is the same for both e-switches */
-	int nvports = esw->total_vports;
 	struct mlx5_flow_handle *flow;
+	struct mlx5_vport *peer_vport;
 	struct mlx5_flow_spec *spec;
-	struct mlx5_vport *vport;
 	int err, pfindex;
 	unsigned long i;
 	void *misc;
 
-	if (!MLX5_VPORT_MANAGER(esw->dev) && !mlx5_core_is_ecpf_esw_manager(esw->dev))
+	if (!MLX5_VPORT_MANAGER(peer_dev) &&
+	    !mlx5_core_is_ecpf_esw_manager(peer_dev))
 		return 0;
 
 	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
@@ -1202,7 +1202,7 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw,
 
 	peer_miss_rules_setup(esw, peer_dev, spec, &dest);
 
-	flows = kvcalloc(nvports, sizeof(*flows), GFP_KERNEL);
+	flows = kvcalloc(peer_esw->total_vports, sizeof(*flows), GFP_KERNEL);
 	if (!flows) {
 		err = -ENOMEM;
 		goto alloc_flows_err;
@@ -1212,10 +1212,10 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw,
 	misc = MLX5_ADDR_OF(fte_match_param, spec->match_value,
 			    misc_parameters);
 
-	if (mlx5_core_is_ecpf_esw_manager(esw->dev)) {
-		vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_PF);
-		esw_set_peer_miss_rule_source_port(esw, peer_dev->priv.eswitch,
-						   spec, MLX5_VPORT_PF);
+	if (mlx5_core_is_ecpf_esw_manager(peer_dev)) {
+		peer_vport = mlx5_eswitch_get_vport(peer_esw, MLX5_VPORT_PF);
+		esw_set_peer_miss_rule_source_port(esw, peer_esw, spec,
+						   MLX5_VPORT_PF);
 
 		flow = mlx5_add_flow_rules(mlx5_eswitch_get_slow_fdb(esw),
 					   spec, &flow_act, &dest, 1);
@@ -1223,11 +1223,11 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw,
 			err = PTR_ERR(flow);
 			goto add_pf_flow_err;
 		}
-		flows[vport->index] = flow;
+		flows[peer_vport->index] = flow;
 	}
 
-	if (mlx5_ecpf_vport_exists(esw->dev)) {
-		vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_ECPF);
+	if (mlx5_ecpf_vport_exists(peer_dev)) {
+		peer_vport = mlx5_eswitch_get_vport(peer_esw, MLX5_VPORT_ECPF);
 		MLX5_SET(fte_match_set_misc, misc, source_port, MLX5_VPORT_ECPF);
 		flow = mlx5_add_flow_rules(mlx5_eswitch_get_slow_fdb(esw),
 					   spec, &flow_act, &dest, 1);
@@ -1235,13 +1235,14 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw,
 			err = PTR_ERR(flow);
 			goto add_ecpf_flow_err;
 		}
-		flows[vport->index] = flow;
+		flows[peer_vport->index] = flow;
 	}
 
-	mlx5_esw_for_each_vf_vport(esw, i, vport, mlx5_core_max_vfs(esw->dev)) {
+	mlx5_esw_for_each_vf_vport(peer_esw, i, peer_vport,
+				   mlx5_core_max_vfs(peer_dev)) {
 		esw_set_peer_miss_rule_source_port(esw,
-						   peer_dev->priv.eswitch,
-						   spec, vport->vport);
+						   peer_esw,
+						   spec, peer_vport->vport);
 
 		flow = mlx5_add_flow_rules(mlx5_eswitch_get_slow_fdb(esw),
 					   spec, &flow_act, &dest, 1);
@@ -1249,22 +1250,22 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw,
 			err = PTR_ERR(flow);
 			goto add_vf_flow_err;
 		}
-		flows[vport->index] = flow;
+		flows[peer_vport->index] = flow;
 	}
 
-	if (mlx5_core_ec_sriov_enabled(esw->dev)) {
-		mlx5_esw_for_each_ec_vf_vport(esw, i, vport, mlx5_core_max_ec_vfs(esw->dev)) {
-			if (i >= mlx5_core_max_ec_vfs(peer_dev))
-				break;
-			esw_set_peer_miss_rule_source_port(esw, peer_dev->priv.eswitch,
-							   spec, vport->vport);
+	if (mlx5_core_ec_sriov_enabled(peer_dev)) {
+		mlx5_esw_for_each_ec_vf_vport(peer_esw, i, peer_vport,
+					      mlx5_core_max_ec_vfs(peer_dev)) {
+			esw_set_peer_miss_rule_source_port(esw, peer_esw,
+							   spec,
+							   peer_vport->vport);
 			flow = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb,
 						   spec, &flow_act, &dest, 1);
 			if (IS_ERR(flow)) {
 				err = PTR_ERR(flow);
 				goto add_ec_vf_flow_err;
 			}
-			flows[vport->index] = flow;
+			flows[peer_vport->index] = flow;
 		}
 	}
 
@@ -1281,25 +1282,27 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw,
 	return 0;
 
 add_ec_vf_flow_err:
-	mlx5_esw_for_each_ec_vf_vport(esw, i, vport, mlx5_core_max_ec_vfs(esw->dev)) {
-		if (!flows[vport->index])
+	mlx5_esw_for_each_ec_vf_vport(peer_esw, i, peer_vport,
+				      mlx5_core_max_ec_vfs(peer_dev)) {
+		if (!flows[peer_vport->index])
 			continue;
-		mlx5_del_flow_rules(flows[vport->index]);
+		mlx5_del_flow_rules(flows[peer_vport->index]);
 	}
 add_vf_flow_err:
-	mlx5_esw_for_each_vf_vport(esw, i, vport, mlx5_core_max_vfs(esw->dev)) {
-		if (!flows[vport->index])
+	mlx5_esw_for_each_vf_vport(peer_esw, i, peer_vport,
+				   mlx5_core_max_vfs(peer_dev)) {
+		if (!flows[peer_vport->index])
 			continue;
-		mlx5_del_flow_rules(flows[vport->index]);
+		mlx5_del_flow_rules(flows[peer_vport->index]);
 	}
-	if (mlx5_ecpf_vport_exists(esw->dev)) {
-		vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_ECPF);
-		mlx5_del_flow_rules(flows[vport->index]);
+	if (mlx5_ecpf_vport_exists(peer_dev)) {
+		peer_vport = mlx5_eswitch_get_vport(peer_esw, MLX5_VPORT_ECPF);
+		mlx5_del_flow_rules(flows[peer_vport->index]);
 	}
 add_ecpf_flow_err:
-	if (mlx5_core_is_ecpf_esw_manager(esw->dev)) {
-		vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_PF);
-		mlx5_del_flow_rules(flows[vport->index]);
+	if (mlx5_core_is_ecpf_esw_manager(peer_dev)) {
+		peer_vport = mlx5_eswitch_get_vport(peer_esw, MLX5_VPORT_PF);
+		mlx5_del_flow_rules(flows[peer_vport->index]);
 	}
 add_pf_flow_err:
 	esw_warn(esw->dev, "FDB: Failed to add peer miss flow rule err %d\n", err);
@@ -1312,37 +1315,34 @@ alloc_flows_err:
 static void esw_del_fdb_peer_miss_rules(struct mlx5_eswitch *esw,
 					struct mlx5_core_dev *peer_dev)
 {
+	struct mlx5_eswitch *peer_esw = peer_dev->priv.eswitch;
 	u16 peer_index = mlx5_get_dev_index(peer_dev);
 	struct mlx5_flow_handle **flows;
-	struct mlx5_vport *vport;
+	struct mlx5_vport *peer_vport;
 	unsigned long i;
 
 	flows = esw->fdb_table.offloads.peer_miss_rules[peer_index];
 	if (!flows)
 		return;
 
-	if (mlx5_core_ec_sriov_enabled(esw->dev)) {
-		mlx5_esw_for_each_ec_vf_vport(esw, i, vport, mlx5_core_max_ec_vfs(esw->dev)) {
-			/* The flow for a particular vport could be NULL if the other ECPF
-			 * has fewer or no VFs enabled
-			 */
-			if (!flows[vport->index])
-				continue;
-			mlx5_del_flow_rules(flows[vport->index]);
-		}
+	if (mlx5_core_ec_sriov_enabled(peer_dev)) {
+		mlx5_esw_for_each_ec_vf_vport(peer_esw, i, peer_vport,
+					      mlx5_core_max_ec_vfs(peer_dev))
+			mlx5_del_flow_rules(flows[peer_vport->index]);
 	}
 
-	mlx5_esw_for_each_vf_vport(esw, i, vport, mlx5_core_max_vfs(esw->dev))
-		mlx5_del_flow_rules(flows[vport->index]);
+	mlx5_esw_for_each_vf_vport(peer_esw, i, peer_vport,
+				   mlx5_core_max_vfs(peer_dev))
+		mlx5_del_flow_rules(flows[peer_vport->index]);
 
-	if (mlx5_ecpf_vport_exists(esw->dev)) {
-		vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_ECPF);
-		mlx5_del_flow_rules(flows[vport->index]);
+	if (mlx5_ecpf_vport_exists(peer_dev)) {
+		peer_vport = mlx5_eswitch_get_vport(peer_esw, MLX5_VPORT_ECPF);
+		mlx5_del_flow_rules(flows[peer_vport->index]);
 	}
 
-	if (mlx5_core_is_ecpf_esw_manager(esw->dev)) {
-		vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_PF);
-		mlx5_del_flow_rules(flows[vport->index]);
+	if (mlx5_core_is_ecpf_esw_manager(peer_dev)) {
+		peer_vport = mlx5_eswitch_get_vport(peer_esw, MLX5_VPORT_PF);
+		mlx5_del_flow_rules(flows[peer_vport->index]);
 	}
 
 	kvfree(flows);
@@ -3514,7 +3514,9 @@ int esw_offloads_enable(struct mlx5_eswitch *esw)
 	int err;
 
 	mutex_init(&esw->offloads.termtbl_mutex);
-	mlx5_rdma_enable_roce(esw->dev);
+	err = mlx5_rdma_enable_roce(esw->dev);
+	if (err)
+		goto err_roce;
 
 	err = mlx5_esw_host_number_init(esw);
 	if (err)
@@ -3575,6 +3577,7 @@ err_vport_metadata:
 	esw_offloads_metadata_uninit(esw);
 err_metadata:
 	mlx5_rdma_disable_roce(esw->dev);
+err_roce:
 	mutex_destroy(&esw->offloads.termtbl_mutex);
 	return err;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/events.c b/drivers/net/ethernet/mellanox/mlx5/core/events.c
index d91ea53eb394..fc6e56305cbb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/events.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/events.c
@@ -163,11 +163,16 @@ static int temp_warn(struct notifier_block *nb, unsigned long type, void *data)
 	u64 value_msb;
 
 	value_lsb = be64_to_cpu(eqe->data.temp_warning.sensor_warning_lsb);
+	/* bit 1-63 are not supported for NICs,
+	 * hence read only bit 0 (asic) from lsb.
+	 */
+	value_lsb &= 0x1;
 	value_msb = be64_to_cpu(eqe->data.temp_warning.sensor_warning_msb);
 
-	mlx5_core_warn(events->dev,
-		       "High temperature on sensors with bit set %llx %llx",
-		       value_msb, value_lsb);
+	if (net_ratelimit())
+		mlx5_core_warn(events->dev,
+			       "High temperature on sensors with bit set %llx %llx",
+			       value_msb, value_lsb);
 
 	return NOTIFY_OK;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 0ce999706d41..7ef0a4af89e4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -113,13 +113,16 @@
 #define ETHTOOL_PRIO_NUM_LEVELS 1
 #define ETHTOOL_NUM_PRIOS 11
 #define ETHTOOL_MIN_LEVEL (KERNEL_MIN_LEVEL + ETHTOOL_NUM_PRIOS)
-/* Promiscuous, Vlan, mac, ttc, inner ttc, {UDP/ANY/aRFS/accel/{esp, esp_err}}, IPsec policy,
+/* Vlan, mac, ttc, inner ttc, {UDP/ANY/aRFS/accel/{esp, esp_err}}, IPsec policy,
  * {IPsec RoCE MPV,Alias table},IPsec RoCE policy
  */
-#define KERNEL_NIC_PRIO_NUM_LEVELS 11
+#define KERNEL_NIC_PRIO_NUM_LEVELS 10
 #define KERNEL_NIC_NUM_PRIOS 1
-/* One more level for tc */
-#define KERNEL_MIN_LEVEL (KERNEL_NIC_PRIO_NUM_LEVELS + 1)
+/* One more level for tc, and one more for promisc */
+#define KERNEL_MIN_LEVEL (KERNEL_NIC_PRIO_NUM_LEVELS + 2)
+
+#define KERNEL_NIC_PROMISC_NUM_PRIOS 1
+#define KERNEL_NIC_PROMISC_NUM_LEVELS 1
 
 #define KERNEL_NIC_TC_NUM_PRIOS  1
 #define KERNEL_NIC_TC_NUM_LEVELS 3
@@ -187,6 +190,8 @@ static struct init_tree_node {
 			   ADD_NS(MLX5_FLOW_TABLE_MISS_ACTION_DEF,
 				  ADD_MULTIPLE_PRIO(KERNEL_NIC_TC_NUM_PRIOS,
 						    KERNEL_NIC_TC_NUM_LEVELS),
+				  ADD_MULTIPLE_PRIO(KERNEL_NIC_PROMISC_NUM_PRIOS,
+						    KERNEL_NIC_PROMISC_NUM_LEVELS),
 				  ADD_MULTIPLE_PRIO(KERNEL_NIC_NUM_PRIOS,
 						    KERNEL_NIC_PRIO_NUM_LEVELS))),
 		  ADD_PRIO(0, BY_PASS_MIN_LEVEL, 0, FS_CHAINING_CAPS,
@@ -2200,6 +2205,7 @@ try_add_to_existing_fg(struct mlx5_flow_table *ft,
 	struct mlx5_flow_handle *rule;
 	struct match_list *iter;
 	bool take_write = false;
+	bool try_again = false;
 	struct fs_fte *fte;
 	u64  version = 0;
 	int err;
@@ -2264,6 +2270,7 @@ skip_search:
 		nested_down_write_ref_node(&g->node, FS_LOCK_PARENT);
 
 		if (!g->node.active) {
+			try_again = true;
 			up_write_ref_node(&g->node, false);
 			continue;
 		}
@@ -2285,7 +2292,8 @@ skip_search:
 			tree_put_node(&fte->node, false);
 		return rule;
 	}
-	rule = ERR_PTR(-ENOENT);
+	err = try_again ? -EAGAIN : -ENOENT;
+	rule = ERR_PTR(err);
 out:
 	kmem_cache_free(steering->ftes_cache, fte);
 	return rule;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.c
index c14590acc772..f6abfd00d7e6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.c
@@ -50,10 +50,12 @@ mlx5_ft_pool_get_avail_sz(struct mlx5_core_dev *dev, enum fs_flow_table_type tab
 	int i, found_i = -1;
 
 	for (i = ARRAY_SIZE(FT_POOLS) - 1; i >= 0; i--) {
-		if (dev->priv.ft_pool->ft_left[i] && FT_POOLS[i] >= desired_size &&
+		if (dev->priv.ft_pool->ft_left[i] &&
+		    (FT_POOLS[i] >= desired_size ||
+		     desired_size == MLX5_FS_MAX_POOL_SIZE) &&
 		    FT_POOLS[i] <= max_ft_size) {
 			found_i = i;
-			if (desired_size != POOL_NEXT_SIZE)
+			if (desired_size != MLX5_FS_MAX_POOL_SIZE)
 				break;
 		}
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.h
index 25f4274b372b..173e312db720 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.h
@@ -7,8 +7,6 @@
 #include <linux/mlx5/driver.h>
 #include "fs_core.h"
 
-#define POOL_NEXT_SIZE 0
-
 int mlx5_ft_pool_init(struct mlx5_core_dev *dev);
 void mlx5_ft_pool_destroy(struct mlx5_core_dev *dev);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index a6329ca2d9bf..52c8035547be 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -799,6 +799,7 @@ static void poll_health(struct timer_list *t)
 	health->prev = count;
 	if (health->miss_counter == MAX_MISSES) {
 		mlx5_core_err(dev, "device's health compromised - reached miss count\n");
+		health->synd = ioread8(&h->synd);
 		print_health_info(dev);
 		queue_work(health->wq, &health->report_work);
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c b/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c
index 1477db7f5307..2691d88cdee1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c
@@ -175,7 +175,7 @@ unlock:
 
 void mlx5_irq_affinity_irq_release(struct mlx5_core_dev *dev, struct mlx5_irq *irq)
 {
-	struct mlx5_irq_pool *pool = mlx5_irq_pool_get(dev);
+	struct mlx5_irq_pool *pool = mlx5_irq_get_pool(irq);
 	int cpu;
 
 	cpu = cpumask_first(mlx5_irq_get_affinity_mask(irq));
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
index 7f68468c2e75..4b3da7ebd631 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
@@ -859,7 +859,7 @@ void mlx5_disable_lag(struct mlx5_lag *ldev)
 				mlx5_eswitch_reload_ib_reps(ldev->pf[i].dev->priv.eswitch);
 }
 
-static bool mlx5_shared_fdb_supported(struct mlx5_lag *ldev)
+bool mlx5_lag_shared_fdb_supported(struct mlx5_lag *ldev)
 {
 	struct mlx5_core_dev *dev;
 	int i;
@@ -937,7 +937,7 @@ static void mlx5_do_bond(struct mlx5_lag *ldev)
 	}
 
 	if (do_bond && !__mlx5_lag_is_active(ldev)) {
-		bool shared_fdb = mlx5_shared_fdb_supported(ldev);
+		bool shared_fdb = mlx5_lag_shared_fdb_supported(ldev);
 
 		roce_lag = mlx5_lag_is_roce_lag(ldev);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h
index 50fcb1eee574..48a5f3e7b91a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h
@@ -92,6 +92,7 @@ mlx5_lag_is_ready(struct mlx5_lag *ldev)
 	return test_bit(MLX5_LAG_FLAG_NDEVS_READY, &ldev->state_flags);
 }
 
+bool mlx5_lag_shared_fdb_supported(struct mlx5_lag *ldev);
 bool mlx5_lag_check_prereq(struct mlx5_lag *ldev);
 void mlx5_modify_lag(struct mlx5_lag *ldev,
 		     struct lag_tracker *tracker);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c
index 571ea26edd0c..2381a0eec190 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c
@@ -81,7 +81,8 @@ static int enable_mpesw(struct mlx5_lag *ldev)
 	if (mlx5_eswitch_mode(dev0) != MLX5_ESWITCH_OFFLOADS ||
 	    !MLX5_CAP_PORT_SELECTION(dev0, port_select_flow_table) ||
 	    !MLX5_CAP_GEN(dev0, create_lag_when_not_master_up) ||
-	    !mlx5_lag_check_prereq(ldev))
+	    !mlx5_lag_check_prereq(ldev) ||
+	    !mlx5_lag_shared_fdb_supported(ldev))
 		return -EOPNOTSUPP;
 
 	err = mlx5_mpesw_metadata_set(ldev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
index b306ae79bf97..863196ad0ddc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
@@ -322,17 +322,16 @@ static void mlx5_pps_out(struct work_struct *work)
 	}
 }
 
-static void mlx5_timestamp_overflow(struct work_struct *work)
+static long mlx5_timestamp_overflow(struct ptp_clock_info *ptp_info)
 {
-	struct delayed_work *dwork = to_delayed_work(work);
 	struct mlx5_core_dev *mdev;
 	struct mlx5_timer *timer;
 	struct mlx5_clock *clock;
 	unsigned long flags;
 
-	timer = container_of(dwork, struct mlx5_timer, overflow_work);
-	clock = container_of(timer, struct mlx5_clock, timer);
+	clock = container_of(ptp_info, struct mlx5_clock, ptp_info);
 	mdev = container_of(clock, struct mlx5_core_dev, clock);
+	timer = &clock->timer;
 
 	if (mdev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR)
 		goto out;
@@ -343,7 +342,7 @@ static void mlx5_timestamp_overflow(struct work_struct *work)
 	write_sequnlock_irqrestore(&clock->lock, flags);
 
 out:
-	schedule_delayed_work(&timer->overflow_work, timer->overflow_period);
+	return timer->overflow_period;
 }
 
 static int mlx5_ptp_settime_real_time(struct mlx5_core_dev *mdev,
@@ -521,6 +520,7 @@ static int mlx5_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm)
 	timer->cycles.mult = mult;
 	mlx5_update_clock_info_page(mdev);
 	write_sequnlock_irqrestore(&clock->lock, flags);
+	ptp_schedule_worker(clock->ptp, timer->overflow_period);
 
 	return 0;
 }
@@ -856,6 +856,7 @@ static const struct ptp_clock_info mlx5_ptp_clock_info = {
 	.settime64	= mlx5_ptp_settime,
 	.enable		= NULL,
 	.verify		= NULL,
+	.do_aux_work	= mlx5_timestamp_overflow,
 };
 
 static int mlx5_query_mtpps_pin_mode(struct mlx5_core_dev *mdev, u8 pin,
@@ -1056,12 +1057,11 @@ static void mlx5_init_overflow_period(struct mlx5_clock *clock)
 	do_div(ns, NSEC_PER_SEC / HZ);
 	timer->overflow_period = ns;
 
-	INIT_DELAYED_WORK(&timer->overflow_work, mlx5_timestamp_overflow);
-	if (timer->overflow_period)
-		schedule_delayed_work(&timer->overflow_work, 0);
-	else
+	if (!timer->overflow_period) {
+		timer->overflow_period = HZ;
 		mlx5_core_warn(mdev,
-			       "invalid overflow period, overflow_work is not scheduled\n");
+			       "invalid overflow period, overflow_work is scheduled once per second\n");
+	}
 
 	if (clock_info)
 		clock_info->overflow_period = timer->overflow_period;
@@ -1176,6 +1176,9 @@ void mlx5_init_clock(struct mlx5_core_dev *mdev)
 
 	MLX5_NB_INIT(&clock->pps_nb, mlx5_pps_event, PPS_EVENT);
 	mlx5_eq_notifier_register(mdev, &clock->pps_nb);
+
+	if (clock->ptp)
+		ptp_schedule_worker(clock->ptp, 0);
 }
 
 void mlx5_cleanup_clock(struct mlx5_core_dev *mdev)
@@ -1192,7 +1195,6 @@ void mlx5_cleanup_clock(struct mlx5_core_dev *mdev)
 	}
 
 	cancel_work_sync(&clock->pps_info.out_work);
-	cancel_delayed_work_sync(&clock->timer.overflow_work);
 
 	if (mdev->clock_info) {
 		free_page((unsigned long)mdev->clock_info);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/dm.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/dm.c
index 7c5516b0a844..8115071c34a4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/dm.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/dm.c
@@ -30,7 +30,7 @@ struct mlx5_dm *mlx5_dm_create(struct mlx5_core_dev *dev)
 
 	dm = kzalloc(sizeof(*dm), GFP_KERNEL);
 	if (!dm)
-		return ERR_PTR(-ENOMEM);
+		return NULL;
 
 	spin_lock_init(&dm->lock);
 
@@ -96,7 +96,7 @@ err_modify_hdr:
 err_steering:
 	kfree(dm);
 
-	return ERR_PTR(-ENOMEM);
+	return NULL;
 }
 
 void mlx5_dm_cleanup(struct mlx5_core_dev *dev)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c
index a80ecb672f33..d313cb7f0ed8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c
@@ -161,7 +161,8 @@ mlx5_chains_create_table(struct mlx5_fs_chains *chains,
 		ft_attr.flags |= (MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT |
 				  MLX5_FLOW_TABLE_TUNNEL_EN_DECAP);
 
-	sz = (chain == mlx5_chains_get_nf_ft_chain(chains)) ? FT_TBL_SZ : POOL_NEXT_SIZE;
+	sz = (chain == mlx5_chains_get_nf_ft_chain(chains)) ?
+		FT_TBL_SZ : MLX5_FS_MAX_POOL_SIZE;
 	ft_attr.max_fte = sz;
 
 	/* We use chains_default_ft(chains) as the table's next_ft till
@@ -196,6 +197,11 @@ mlx5_chains_create_table(struct mlx5_fs_chains *chains,
 		ns = mlx5_get_flow_namespace(chains->dev, chains->ns);
 	}
 
+	if (!ns) {
+		mlx5_core_warn(chains->dev, "Failed to get flow namespace\n");
+		return ERR_PTR(-EOPNOTSUPP);
+	}
+
 	ft_attr.autogroup.num_reserved_entries = 2;
 	ft_attr.autogroup.max_num_groups = chains->group_num;
 	ft = mlx5_create_auto_grouped_flow_table(ns, &ft_attr);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c
index 9f13cea16446..43b2216bc0a2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c
@@ -618,10 +618,6 @@ struct mlx5_ttc_table *mlx5_create_inner_ttc_table(struct mlx5_core_dev *dev,
 	bool use_l4_type;
 	int err;
 
-	ttc = kvzalloc(sizeof(*ttc), GFP_KERNEL);
-	if (!ttc)
-		return ERR_PTR(-ENOMEM);
-
 	switch (params->ns_type) {
 	case MLX5_FLOW_NAMESPACE_PORT_SEL:
 		use_l4_type = MLX5_CAP_GEN_2(dev, pcc_ifa2) &&
@@ -635,7 +631,16 @@ struct mlx5_ttc_table *mlx5_create_inner_ttc_table(struct mlx5_core_dev *dev,
 		return ERR_PTR(-EINVAL);
 	}
 
+	ttc = kvzalloc(sizeof(*ttc), GFP_KERNEL);
+	if (!ttc)
+		return ERR_PTR(-ENOMEM);
+
 	ns = mlx5_get_flow_namespace(dev, params->ns_type);
+	if (!ns) {
+		kvfree(ttc);
+		return ERR_PTR(-EOPNOTSUPP);
+	}
+
 	groups = use_l4_type ? &inner_ttc_groups[TTC_GROUPS_USE_L4_TYPE] :
 			       &inner_ttc_groups[TTC_GROUPS_DEFAULT];
 
@@ -691,10 +696,6 @@ struct mlx5_ttc_table *mlx5_create_ttc_table(struct mlx5_core_dev *dev,
 	bool use_l4_type;
 	int err;
 
-	ttc = kvzalloc(sizeof(*ttc), GFP_KERNEL);
-	if (!ttc)
-		return ERR_PTR(-ENOMEM);
-
 	switch (params->ns_type) {
 	case MLX5_FLOW_NAMESPACE_PORT_SEL:
 		use_l4_type = MLX5_CAP_GEN_2(dev, pcc_ifa2) &&
@@ -708,7 +709,16 @@ struct mlx5_ttc_table *mlx5_create_ttc_table(struct mlx5_core_dev *dev,
 		return ERR_PTR(-EINVAL);
 	}
 
+	ttc = kvzalloc(sizeof(*ttc), GFP_KERNEL);
+	if (!ttc)
+		return ERR_PTR(-ENOMEM);
+
 	ns = mlx5_get_flow_namespace(dev, params->ns_type);
+	if (!ns) {
+		kvfree(ttc);
+		return ERR_PTR(-EOPNOTSUPP);
+	}
+
 	groups = use_l4_type ? &ttc_groups[TTC_GROUPS_USE_L4_TYPE] :
 			       &ttc_groups[TTC_GROUPS_DEFAULT];
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 220a9ac75c8b..11d8739b9497 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1092,9 +1092,6 @@ static int mlx5_init_once(struct mlx5_core_dev *dev)
 	}
 
 	dev->dm = mlx5_dm_create(dev);
-	if (IS_ERR(dev->dm))
-		mlx5_core_warn(dev, "Failed to init device memory %ld\n", PTR_ERR(dev->dm));
-
 	dev->tracer = mlx5_fw_tracer_create(dev);
 	dev->hv_vhca = mlx5_hv_vhca_create(dev);
 	dev->rsc_dump = mlx5_rsc_dump_create(dev);
@@ -2241,6 +2238,7 @@ static const struct pci_device_id mlx5_core_pci_table[] = {
 	{ PCI_VDEVICE(MELLANOX, 0x1021) },			/* ConnectX-7 */
 	{ PCI_VDEVICE(MELLANOX, 0x1023) },			/* ConnectX-8 */
 	{ PCI_VDEVICE(MELLANOX, 0x1025) },			/* ConnectX-9 */
+	{ PCI_VDEVICE(MELLANOX, 0x1027) },			/* ConnectX-10 */
 	{ PCI_VDEVICE(MELLANOX, 0xa2d2) },			/* BlueField integrated ConnectX-5 network controller */
 	{ PCI_VDEVICE(MELLANOX, 0xa2d3), MLX5_PCI_DEV_IS_VF},	/* BlueField integrated ConnectX-5 network controller VF */
 	{ PCI_VDEVICE(MELLANOX, 0xa2d6) },			/* BlueField-2 integrated ConnectX-6 Dx network controller */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h
index 0881e961d8b1..586688da9940 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h
@@ -10,12 +10,15 @@
 
 struct mlx5_irq;
 struct cpu_rmap;
+struct mlx5_irq_pool;
 
 int mlx5_irq_table_init(struct mlx5_core_dev *dev);
 void mlx5_irq_table_cleanup(struct mlx5_core_dev *dev);
 int mlx5_irq_table_create(struct mlx5_core_dev *dev);
 void mlx5_irq_table_destroy(struct mlx5_core_dev *dev);
 void mlx5_irq_table_free_irqs(struct mlx5_core_dev *dev);
+struct mlx5_irq_pool *
+mlx5_irq_table_get_comp_irq_pool(struct mlx5_core_dev *dev);
 int mlx5_irq_table_get_num_comp(struct mlx5_irq_table *table);
 int mlx5_irq_table_get_sfs_vec(struct mlx5_irq_table *table);
 struct mlx5_irq_table *mlx5_irq_table_get(struct mlx5_core_dev *dev);
@@ -38,7 +41,6 @@ struct cpumask *mlx5_irq_get_affinity_mask(struct mlx5_irq *irq);
 int mlx5_irq_get_index(struct mlx5_irq *irq);
 int mlx5_irq_get_irq(const struct mlx5_irq *irq);
 
-struct mlx5_irq_pool;
 #ifdef CONFIG_MLX5_SF
 struct mlx5_irq *mlx5_irq_affinity_irq_request_auto(struct mlx5_core_dev *dev,
 						    struct cpumask *used_cpus, u16 vecidx);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
index 972e8e9df585..9bc9bd83c232 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
@@ -291,7 +291,7 @@ static void free_4k(struct mlx5_core_dev *dev, u64 addr, u32 function)
 static int alloc_system_page(struct mlx5_core_dev *dev, u32 function)
 {
 	struct device *device = mlx5_core_dma_dev(dev);
-	int nid = dev_to_node(device);
+	int nid = dev->priv.numa_node;
 	struct page *page;
 	u64 zero_addr = 1;
 	u64 addr;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
index 7db9cab9bedf..2c5f850c31f6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
@@ -378,6 +378,11 @@ int mlx5_irq_get_index(struct mlx5_irq *irq)
 	return irq->map.index;
 }
 
+struct mlx5_irq_pool *mlx5_irq_get_pool(struct mlx5_irq *irq)
+{
+	return irq->pool;
+}
+
 /* irq_pool API */
 
 /* requesting an irq from a given pool according to given index */
@@ -405,18 +410,20 @@ static struct mlx5_irq_pool *sf_ctrl_irq_pool_get(struct mlx5_irq_table *irq_tab
 	return irq_table->sf_ctrl_pool;
 }
 
-static struct mlx5_irq_pool *sf_irq_pool_get(struct mlx5_irq_table *irq_table)
+static struct mlx5_irq_pool *
+sf_comp_irq_pool_get(struct mlx5_irq_table *irq_table)
 {
 	return irq_table->sf_comp_pool;
 }
 
-struct mlx5_irq_pool *mlx5_irq_pool_get(struct mlx5_core_dev *dev)
+struct mlx5_irq_pool *
+mlx5_irq_table_get_comp_irq_pool(struct mlx5_core_dev *dev)
 {
 	struct mlx5_irq_table *irq_table = mlx5_irq_table_get(dev);
 	struct mlx5_irq_pool *pool = NULL;
 
 	if (mlx5_core_is_sf(dev))
-		pool = sf_irq_pool_get(irq_table);
+		pool = sf_comp_irq_pool_get(irq_table);
 
 	/* In some configs, there won't be a pool of SFs IRQs. Hence, returning
 	 * the PF IRQs pool in case the SF pool doesn't exist.
@@ -572,7 +579,7 @@ irq_pool_alloc(struct mlx5_core_dev *dev, int start, int size, char *name,
 	pool->min_threshold = min_threshold * MLX5_EQ_REFS_PER_IRQ;
 	pool->max_threshold = max_threshold * MLX5_EQ_REFS_PER_IRQ;
 	mlx5_core_dbg(dev, "pool->name = %s, pool->size = %d, pool->start = %d",
-		      name, size, start);
+		      name ? name : "mlx5_pcif_pool", size, start);
 	return pool;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.h b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.h
index c4d377f8df30..cc064425fe16 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.h
@@ -28,7 +28,6 @@ struct mlx5_irq_pool {
 	struct mlx5_core_dev *dev;
 };
 
-struct mlx5_irq_pool *mlx5_irq_pool_get(struct mlx5_core_dev *dev);
 static inline bool mlx5_irq_pool_is_sf_pool(struct mlx5_irq_pool *pool)
 {
 	return !strncmp("mlx5_sf", pool->name, strlen("mlx5_sf"));
@@ -40,5 +39,6 @@ struct mlx5_irq *mlx5_irq_alloc(struct mlx5_irq_pool *pool, int i,
 int mlx5_irq_get_locked(struct mlx5_irq *irq);
 int mlx5_irq_read_locked(struct mlx5_irq *irq);
 int mlx5_irq_put(struct mlx5_irq *irq);
+struct mlx5_irq_pool *mlx5_irq_get_pool(struct mlx5_irq *irq);
 
 #endif /* __PCI_IRQ_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/rdma.c b/drivers/net/ethernet/mellanox/mlx5/core/rdma.c
index a42f6cd99b74..5c552b71e371 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/rdma.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/rdma.c
@@ -118,8 +118,8 @@ static void mlx5_rdma_make_default_gid(struct mlx5_core_dev *dev, union ib_gid *
 
 static int mlx5_rdma_add_roce_addr(struct mlx5_core_dev *dev)
 {
+	u8 mac[ETH_ALEN] = {};
 	union ib_gid gid;
-	u8 mac[ETH_ALEN];
 
 	mlx5_rdma_make_default_gid(dev, &gid);
 	return mlx5_core_roce_gid_set(dev, 0,
@@ -140,17 +140,17 @@ void mlx5_rdma_disable_roce(struct mlx5_core_dev *dev)
 	mlx5_nic_vport_disable_roce(dev);
 }
 
-void mlx5_rdma_enable_roce(struct mlx5_core_dev *dev)
+int mlx5_rdma_enable_roce(struct mlx5_core_dev *dev)
 {
 	int err;
 
 	if (!MLX5_CAP_GEN(dev, roce))
-		return;
+		return 0;
 
 	err = mlx5_nic_vport_enable_roce(dev);
 	if (err) {
 		mlx5_core_err(dev, "Failed to enable RoCE: %d\n", err);
-		return;
+		return err;
 	}
 
 	err = mlx5_rdma_add_roce_addr(dev);
@@ -165,10 +165,11 @@ void mlx5_rdma_enable_roce(struct mlx5_core_dev *dev)
 		goto del_roce_addr;
 	}
 
-	return;
+	return err;
 
 del_roce_addr:
 	mlx5_rdma_del_roce_addr(dev);
 disable_roce:
 	mlx5_nic_vport_disable_roce(dev);
+	return err;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/rdma.h b/drivers/net/ethernet/mellanox/mlx5/core/rdma.h
index 750cff2a71a4..3d9e76c3d42f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/rdma.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/rdma.h
@@ -8,12 +8,12 @@
 
 #ifdef CONFIG_MLX5_ESWITCH
 
-void mlx5_rdma_enable_roce(struct mlx5_core_dev *dev);
+int mlx5_rdma_enable_roce(struct mlx5_core_dev *dev);
 void mlx5_rdma_disable_roce(struct mlx5_core_dev *dev);
 
 #else /* CONFIG_MLX5_ESWITCH */
 
-static inline void mlx5_rdma_enable_roce(struct mlx5_core_dev *dev) {}
+static inline int mlx5_rdma_enable_roce(struct mlx5_core_dev *dev) { return 0; }
 static inline void mlx5_rdma_disable_roce(struct mlx5_core_dev *dev) {}
 
 #endif /* CONFIG_MLX5_ESWITCH */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_bwc.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_bwc.h
index 4fe8c32d8fbe..681fb73f00bb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_bwc.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_bwc.h
@@ -16,8 +16,8 @@ struct mlx5hws_bwc_matcher {
 	struct mlx5hws_matcher *matcher;
 	struct mlx5hws_match_template *mt;
 	struct mlx5hws_action_template *at[MLX5HWS_BWC_MATCHER_ATTACH_AT_NUM];
+	u32 priority;
 	u8 num_of_at;
-	u16 priority;
 	u8 size_log;
 	u32 num_of_rules; /* atomically accessed */
 	struct list_head *rules;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_definer.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_definer.c
index 3f4c58bada37..fc9ba534d5d9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_definer.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_definer.c
@@ -70,7 +70,7 @@
 			u32 second_dw_mask = (mask) & ((1 << _bit_off) - 1); \
 			_HWS_SET32(p, (v) >> _bit_off, byte_off, 0, (mask) >> _bit_off); \
 			_HWS_SET32(p, (v) & second_dw_mask, (byte_off) + DW_SIZE, \
-				    (bit_off) % BITS_IN_DW, second_dw_mask); \
+				    (bit_off + BITS_IN_DW) % BITS_IN_DW, second_dw_mask); \
 		} else { \
 			_HWS_SET32(p, v, byte_off, (bit_off), (mask)); \
 		} \
@@ -508,7 +508,7 @@ static int
 hws_definer_conv_outer(struct mlx5hws_definer_conv_data *cd,
 		       u32 *match_param)
 {
-	bool is_s_ipv6, is_d_ipv6, smac_set, dmac_set;
+	bool is_ipv6, smac_set, dmac_set, ip_addr_set, ip_ver_set;
 	struct mlx5hws_definer_fc *fc = cd->fc;
 	struct mlx5hws_definer_fc *curr_fc;
 	u32 *s_ipv6, *d_ipv6;
@@ -520,6 +520,20 @@ hws_definer_conv_outer(struct mlx5hws_definer_conv_data *cd,
 		return -EINVAL;
 	}
 
+	ip_addr_set = HWS_IS_FLD_SET_SZ(match_param,
+					outer_headers.src_ipv4_src_ipv6,
+					0x80) ||
+		      HWS_IS_FLD_SET_SZ(match_param,
+					outer_headers.dst_ipv4_dst_ipv6, 0x80);
+	ip_ver_set = HWS_IS_FLD_SET(match_param, outer_headers.ip_version) ||
+		     HWS_IS_FLD_SET(match_param, outer_headers.ethertype);
+
+	if (ip_addr_set && !ip_ver_set) {
+		mlx5hws_err(cd->ctx,
+			    "Unsupported match on IP address without version or ethertype\n");
+		return -EINVAL;
+	}
+
 	/* L2 Check ethertype */
 	HWS_SET_HDR(fc, match_param, ETH_TYPE_O,
 		    outer_headers.ethertype,
@@ -558,6 +572,9 @@ hws_definer_conv_outer(struct mlx5hws_definer_conv_data *cd,
 	HWS_SET_HDR(fc, match_param, IP_PROTOCOL_O,
 		    outer_headers.ip_protocol,
 		    eth_l3_outer.protocol_next_header);
+	HWS_SET_HDR(fc, match_param, IP_VERSION_O,
+		    outer_headers.ip_version,
+		    eth_l3_outer.ip_version);
 	HWS_SET_HDR(fc, match_param, IP_TTL_O,
 		    outer_headers.ttl_hoplimit,
 		    eth_l3_outer.time_to_live_hop_limit);
@@ -569,10 +586,16 @@ hws_definer_conv_outer(struct mlx5hws_definer_conv_data *cd,
 			      outer_headers.dst_ipv4_dst_ipv6.ipv6_layout);
 
 	/* Assume IPv6 is used if ipv6 bits are set */
-	is_s_ipv6 = s_ipv6[0] || s_ipv6[1] || s_ipv6[2];
-	is_d_ipv6 = d_ipv6[0] || d_ipv6[1] || d_ipv6[2];
+	is_ipv6 = s_ipv6[0] || s_ipv6[1] || s_ipv6[2] ||
+		  d_ipv6[0] || d_ipv6[1] || d_ipv6[2];
 
-	if (is_s_ipv6) {
+	/* IHL is an IPv4-specific field. */
+	if (is_ipv6 && HWS_IS_FLD_SET(match_param, outer_headers.ipv4_ihl)) {
+		mlx5hws_err(cd->ctx, "Unsupported match on IPv6 address and IPv4 IHL\n");
+		return -EINVAL;
+	}
+
+	if (is_ipv6) {
 		/* Handle IPv6 source address */
 		HWS_SET_HDR(fc, match_param, IPV6_SRC_127_96_O,
 			    outer_headers.src_ipv4_src_ipv6.ipv6_simple_layout.ipv6_127_96,
@@ -586,13 +609,6 @@ hws_definer_conv_outer(struct mlx5hws_definer_conv_data *cd,
 		HWS_SET_HDR(fc, match_param, IPV6_SRC_31_0_O,
 			    outer_headers.src_ipv4_src_ipv6.ipv6_simple_layout.ipv6_31_0,
 			    ipv6_src_outer.ipv6_address_31_0);
-	} else {
-		/* Handle IPv4 source address */
-		HWS_SET_HDR(fc, match_param, IPV4_SRC_O,
-			    outer_headers.src_ipv4_src_ipv6.ipv6_simple_layout.ipv6_31_0,
-			    ipv4_src_dest_outer.source_address);
-	}
-	if (is_d_ipv6) {
 		/* Handle IPv6 destination address */
 		HWS_SET_HDR(fc, match_param, IPV6_DST_127_96_O,
 			    outer_headers.dst_ipv4_dst_ipv6.ipv6_simple_layout.ipv6_127_96,
@@ -607,6 +623,10 @@ hws_definer_conv_outer(struct mlx5hws_definer_conv_data *cd,
 			    outer_headers.dst_ipv4_dst_ipv6.ipv6_simple_layout.ipv6_31_0,
 			    ipv6_dst_outer.ipv6_address_31_0);
 	} else {
+		/* Handle IPv4 source address */
+		HWS_SET_HDR(fc, match_param, IPV4_SRC_O,
+			    outer_headers.src_ipv4_src_ipv6.ipv6_simple_layout.ipv6_31_0,
+			    ipv4_src_dest_outer.source_address);
 		/* Handle IPv4 destination address */
 		HWS_SET_HDR(fc, match_param, IPV4_DST_O,
 			    outer_headers.dst_ipv4_dst_ipv6.ipv6_simple_layout.ipv6_31_0,
@@ -664,7 +684,7 @@ static int
 hws_definer_conv_inner(struct mlx5hws_definer_conv_data *cd,
 		       u32 *match_param)
 {
-	bool is_s_ipv6, is_d_ipv6, smac_set, dmac_set;
+	bool is_ipv6, smac_set, dmac_set, ip_addr_set, ip_ver_set;
 	struct mlx5hws_definer_fc *fc = cd->fc;
 	struct mlx5hws_definer_fc *curr_fc;
 	u32 *s_ipv6, *d_ipv6;
@@ -676,6 +696,20 @@ hws_definer_conv_inner(struct mlx5hws_definer_conv_data *cd,
 		return -EINVAL;
 	}
 
+	ip_addr_set = HWS_IS_FLD_SET_SZ(match_param,
+					inner_headers.src_ipv4_src_ipv6,
+					0x80) ||
+		      HWS_IS_FLD_SET_SZ(match_param,
+					inner_headers.dst_ipv4_dst_ipv6, 0x80);
+	ip_ver_set = HWS_IS_FLD_SET(match_param, inner_headers.ip_version) ||
+		     HWS_IS_FLD_SET(match_param, inner_headers.ethertype);
+
+	if (ip_addr_set && !ip_ver_set) {
+		mlx5hws_err(cd->ctx,
+			    "Unsupported match on IP address without version or ethertype\n");
+		return -EINVAL;
+	}
+
 	/* L2 Check ethertype */
 	HWS_SET_HDR(fc, match_param, ETH_TYPE_I,
 		    inner_headers.ethertype,
@@ -727,10 +761,16 @@ hws_definer_conv_inner(struct mlx5hws_definer_conv_data *cd,
 			      inner_headers.dst_ipv4_dst_ipv6.ipv6_layout);
 
 	/* Assume IPv6 is used if ipv6 bits are set */
-	is_s_ipv6 = s_ipv6[0] || s_ipv6[1] || s_ipv6[2];
-	is_d_ipv6 = d_ipv6[0] || d_ipv6[1] || d_ipv6[2];
+	is_ipv6 = s_ipv6[0] || s_ipv6[1] || s_ipv6[2] ||
+		  d_ipv6[0] || d_ipv6[1] || d_ipv6[2];
 
-	if (is_s_ipv6) {
+	/* IHL is an IPv4-specific field. */
+	if (is_ipv6 && HWS_IS_FLD_SET(match_param, inner_headers.ipv4_ihl)) {
+		mlx5hws_err(cd->ctx, "Unsupported match on IPv6 address and IPv4 IHL\n");
+		return -EINVAL;
+	}
+
+	if (is_ipv6) {
 		/* Handle IPv6 source address */
 		HWS_SET_HDR(fc, match_param, IPV6_SRC_127_96_I,
 			    inner_headers.src_ipv4_src_ipv6.ipv6_simple_layout.ipv6_127_96,
@@ -744,13 +784,6 @@ hws_definer_conv_inner(struct mlx5hws_definer_conv_data *cd,
 		HWS_SET_HDR(fc, match_param, IPV6_SRC_31_0_I,
 			    inner_headers.src_ipv4_src_ipv6.ipv6_simple_layout.ipv6_31_0,
 			    ipv6_src_inner.ipv6_address_31_0);
-	} else {
-		/* Handle IPv4 source address */
-		HWS_SET_HDR(fc, match_param, IPV4_SRC_I,
-			    inner_headers.src_ipv4_src_ipv6.ipv6_simple_layout.ipv6_31_0,
-			    ipv4_src_dest_inner.source_address);
-	}
-	if (is_d_ipv6) {
 		/* Handle IPv6 destination address */
 		HWS_SET_HDR(fc, match_param, IPV6_DST_127_96_I,
 			    inner_headers.dst_ipv4_dst_ipv6.ipv6_simple_layout.ipv6_127_96,
@@ -765,6 +798,10 @@ hws_definer_conv_inner(struct mlx5hws_definer_conv_data *cd,
 			    inner_headers.dst_ipv4_dst_ipv6.ipv6_simple_layout.ipv6_31_0,
 			    ipv6_dst_inner.ipv6_address_31_0);
 	} else {
+		/* Handle IPv4 source address */
+		HWS_SET_HDR(fc, match_param, IPV4_SRC_I,
+			    inner_headers.src_ipv4_src_ipv6.ipv6_simple_layout.ipv6_31_0,
+			    ipv4_src_dest_inner.source_address);
 		/* Handle IPv4 destination address */
 		HWS_SET_HDR(fc, match_param, IPV4_DST_I,
 			    inner_headers.dst_ipv4_dst_ipv6.ipv6_simple_layout.ipv6_31_0,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
index 0d5f750faa45..b04024d0ae67 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
@@ -465,19 +465,22 @@ int mlx5_query_nic_vport_node_guid(struct mlx5_core_dev *mdev, u64 *node_guid)
 {
 	u32 *out;
 	int outlen = MLX5_ST_SZ_BYTES(query_nic_vport_context_out);
+	int err;
 
 	out = kvzalloc(outlen, GFP_KERNEL);
 	if (!out)
 		return -ENOMEM;
 
-	mlx5_query_nic_vport_context(mdev, 0, out);
+	err = mlx5_query_nic_vport_context(mdev, 0, out);
+	if (err)
+		goto out;
 
 	*node_guid = MLX5_GET64(query_nic_vport_context_out, out,
 				nic_vport_context.node_guid);
-
+out:
 	kvfree(out);
 
-	return 0;
+	return err;
 }
 EXPORT_SYMBOL_GPL(mlx5_query_nic_vport_node_guid);
 
@@ -519,19 +522,22 @@ int mlx5_query_nic_vport_qkey_viol_cntr(struct mlx5_core_dev *mdev,
 {
 	u32 *out;
 	int outlen = MLX5_ST_SZ_BYTES(query_nic_vport_context_out);
+	int err;
 
 	out = kvzalloc(outlen, GFP_KERNEL);
 	if (!out)
 		return -ENOMEM;
 
-	mlx5_query_nic_vport_context(mdev, 0, out);
+	err = mlx5_query_nic_vport_context(mdev, 0, out);
+	if (err)
+		goto out;
 
 	*qkey_viol_cntr = MLX5_GET(query_nic_vport_context_out, out,
 				   nic_vport_context.qkey_violation_counter);
-
+out:
 	kvfree(out);
 
-	return 0;
+	return err;
 }
 EXPORT_SYMBOL_GPL(mlx5_query_nic_vport_qkey_viol_cntr);
 
diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c
index 385a56ac7348..c82254a8ae66 100644
--- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c
+++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c
@@ -447,8 +447,10 @@ static int mlxbf_gige_probe(struct platform_device *pdev)
 	priv->llu_plu_irq = platform_get_irq(pdev, MLXBF_GIGE_LLU_PLU_INTR_IDX);
 
 	phy_irq = acpi_dev_gpio_irq_get_by(ACPI_COMPANION(&pdev->dev), "phy", 0);
-	if (phy_irq < 0) {
-		dev_err(&pdev->dev, "Error getting PHY irq. Use polling instead");
+	if (phy_irq == -EPROBE_DEFER) {
+		err = -EPROBE_DEFER;
+		goto out;
+	} else if (phy_irq < 0) {
 		phy_irq = PHY_POLL;
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c
index 46245e0b2462..43c84900369a 100644
--- a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c
+++ b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c
@@ -14,7 +14,6 @@
 #define MLXFW_FSM_STATE_WAIT_TIMEOUT_MS 30000
 #define MLXFW_FSM_STATE_WAIT_ROUNDS \
 	(MLXFW_FSM_STATE_WAIT_TIMEOUT_MS / MLXFW_FSM_STATE_WAIT_CYCLE_MS)
-#define MLXFW_FSM_MAX_COMPONENT_SIZE (10 * (1 << 20))
 
 static const int mlxfw_fsm_state_errno[] = {
 	[MLXFW_FSM_STATE_ERR_ERROR] = -EIO,
@@ -229,7 +228,6 @@ static int mlxfw_flash_component(struct mlxfw_dev *mlxfw_dev,
 		return err;
 	}
 
-	comp_max_size = min_t(u32, comp_max_size, MLXFW_FSM_MAX_COMPONENT_SIZE);
 	if (comp->data_size > comp_max_size) {
 		MLXFW_ERR_MSG(mlxfw_dev, extack,
 			      "Component size is bigger than limit", -EINVAL);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c
index 2bed8c86b7cf..3f64cdbabfa3 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c
@@ -768,7 +768,9 @@ static void __mlxsw_sp_port_get_stats(struct net_device *dev,
 	err = mlxsw_sp_get_hw_stats_by_group(&hw_stats, &len, grp);
 	if (err)
 		return;
-	mlxsw_sp_port_get_stats_raw(dev, grp, prio, ppcnt_pl);
+	err = mlxsw_sp_port_get_stats_raw(dev, grp, prio, ppcnt_pl);
+	if (err)
+		return;
 	for (i = 0; i < len; i++) {
 		data[data_index + i] = hw_stats[i].getter(ppcnt_pl);
 		if (!hw_stats[i].cells_bytes)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c
index 69cd689dbc83..5afe6b155ef0 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c
@@ -1003,10 +1003,10 @@ static void mlxsw_sp_mr_route_stats_update(struct mlxsw_sp *mlxsw_sp,
 	mr->mr_ops->route_stats(mlxsw_sp, mr_route->route_priv, &packets,
 				&bytes);
 
-	if (mr_route->mfc->mfc_un.res.pkt != packets)
-		mr_route->mfc->mfc_un.res.lastuse = jiffies;
-	mr_route->mfc->mfc_un.res.pkt = packets;
-	mr_route->mfc->mfc_un.res.bytes = bytes;
+	if (atomic_long_read(&mr_route->mfc->mfc_un.res.pkt) != packets)
+		WRITE_ONCE(mr_route->mfc->mfc_un.res.lastuse, jiffies);
+	atomic_long_set(&mr_route->mfc->mfc_un.res.pkt, packets);
+	atomic_long_set(&mr_route->mfc->mfc_un.res.bytes, bytes);
 }
 
 static void mlxsw_sp_mr_stats_update(struct work_struct *work)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 7d6d859cef3f..511cd92e0e3e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -3014,6 +3014,9 @@ static int mlxsw_sp_neigh_rif_made_sync(struct mlxsw_sp *mlxsw_sp,
 		.rif = rif,
 	};
 
+	if (!mlxsw_sp_dev_lower_is_port(mlxsw_sp_rif_dev(rif)))
+		return 0;
+
 	neigh_for_each(&arp_tbl, mlxsw_sp_neigh_rif_made_sync_each, &rms);
 	if (rms.err)
 		goto err_arp;
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_csr.h b/drivers/net/ethernet/meta/fbnic/fbnic_csr.h
index 21db509acbc1..e91b4432fddd 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_csr.h
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_csr.h
@@ -700,8 +700,10 @@ enum {
 /* PUL User Registers */
 #define FBNIC_CSR_START_PUL_USER	0x31000	/* CSR section delimiter */
 #define FBNIC_PUL_OB_TLP_HDR_AW_CFG	0x3103d		/* 0xc40f4 */
+#define FBNIC_PUL_OB_TLP_HDR_AW_CFG_FLUSH	CSR_BIT(19)
 #define FBNIC_PUL_OB_TLP_HDR_AW_CFG_BME		CSR_BIT(18)
 #define FBNIC_PUL_OB_TLP_HDR_AR_CFG	0x3103e		/* 0xc40f8 */
+#define FBNIC_PUL_OB_TLP_HDR_AR_CFG_FLUSH	CSR_BIT(19)
 #define FBNIC_PUL_OB_TLP_HDR_AR_CFG_BME		CSR_BIT(18)
 #define FBNIC_CSR_END_PUL_USER	0x31080	/* CSR section delimiter */
 
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_fw.c b/drivers/net/ethernet/meta/fbnic/fbnic_fw.c
index 8f7a2a19ddf8..d6cf97ecf327 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_fw.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_fw.c
@@ -17,11 +17,29 @@ static void __fbnic_mbx_wr_desc(struct fbnic_dev *fbd, int mbx_idx,
 {
 	u32 desc_offset = FBNIC_IPC_MBX(mbx_idx, desc_idx);
 
+	/* Write the upper 32b and then the lower 32b. Doing this the
+	 * FW can then read lower, upper, lower to verify that the state
+	 * of the descriptor wasn't changed mid-transaction.
+	 */
 	fw_wr32(fbd, desc_offset + 1, upper_32_bits(desc));
 	fw_wrfl(fbd);
 	fw_wr32(fbd, desc_offset, lower_32_bits(desc));
 }
 
+static void __fbnic_mbx_invalidate_desc(struct fbnic_dev *fbd, int mbx_idx,
+					int desc_idx, u32 desc)
+{
+	u32 desc_offset = FBNIC_IPC_MBX(mbx_idx, desc_idx);
+
+	/* For initialization we write the lower 32b of the descriptor first.
+	 * This way we can set the state to mark it invalid before we clear the
+	 * upper 32b.
+	 */
+	fw_wr32(fbd, desc_offset, desc);
+	fw_wrfl(fbd);
+	fw_wr32(fbd, desc_offset + 1, 0);
+}
+
 static u64 __fbnic_mbx_rd_desc(struct fbnic_dev *fbd, int mbx_idx, int desc_idx)
 {
 	u32 desc_offset = FBNIC_IPC_MBX(mbx_idx, desc_idx);
@@ -33,29 +51,41 @@ static u64 __fbnic_mbx_rd_desc(struct fbnic_dev *fbd, int mbx_idx, int desc_idx)
 	return desc;
 }
 
-static void fbnic_mbx_init_desc_ring(struct fbnic_dev *fbd, int mbx_idx)
+static void fbnic_mbx_reset_desc_ring(struct fbnic_dev *fbd, int mbx_idx)
 {
 	int desc_idx;
 
+	/* Disable DMA transactions from the device,
+	 * and flush any transactions triggered during cleaning
+	 */
+	switch (mbx_idx) {
+	case FBNIC_IPC_MBX_RX_IDX:
+		wr32(fbd, FBNIC_PUL_OB_TLP_HDR_AW_CFG,
+		     FBNIC_PUL_OB_TLP_HDR_AW_CFG_FLUSH);
+		break;
+	case FBNIC_IPC_MBX_TX_IDX:
+		wr32(fbd, FBNIC_PUL_OB_TLP_HDR_AR_CFG,
+		     FBNIC_PUL_OB_TLP_HDR_AR_CFG_FLUSH);
+		break;
+	}
+
+	wrfl(fbd);
+
 	/* Initialize first descriptor to all 0s. Doing this gives us a
 	 * solid stop for the firmware to hit when it is done looping
 	 * through the ring.
 	 */
-	__fbnic_mbx_wr_desc(fbd, mbx_idx, 0, 0);
-
-	fw_wrfl(fbd);
+	__fbnic_mbx_invalidate_desc(fbd, mbx_idx, 0, 0);
 
 	/* We then fill the rest of the ring starting at the end and moving
 	 * back toward descriptor 0 with skip descriptors that have no
 	 * length nor address, and tell the firmware that they can skip
 	 * them and just move past them to the one we initialized to 0.
 	 */
-	for (desc_idx = FBNIC_IPC_MBX_DESC_LEN; --desc_idx;) {
-		__fbnic_mbx_wr_desc(fbd, mbx_idx, desc_idx,
-				    FBNIC_IPC_MBX_DESC_FW_CMPL |
-				    FBNIC_IPC_MBX_DESC_HOST_CMPL);
-		fw_wrfl(fbd);
-	}
+	for (desc_idx = FBNIC_IPC_MBX_DESC_LEN; --desc_idx;)
+		__fbnic_mbx_invalidate_desc(fbd, mbx_idx, desc_idx,
+					    FBNIC_IPC_MBX_DESC_FW_CMPL |
+					    FBNIC_IPC_MBX_DESC_HOST_CMPL);
 }
 
 void fbnic_mbx_init(struct fbnic_dev *fbd)
@@ -76,7 +106,7 @@ void fbnic_mbx_init(struct fbnic_dev *fbd)
 	wr32(fbd, FBNIC_INTR_CLEAR(0), 1u << FBNIC_FW_MSIX_ENTRY);
 
 	for (i = 0; i < FBNIC_IPC_MBX_INDICES; i++)
-		fbnic_mbx_init_desc_ring(fbd, i);
+		fbnic_mbx_reset_desc_ring(fbd, i);
 }
 
 static int fbnic_mbx_map_msg(struct fbnic_dev *fbd, int mbx_idx,
@@ -97,11 +127,8 @@ static int fbnic_mbx_map_msg(struct fbnic_dev *fbd, int mbx_idx,
 		return -EBUSY;
 
 	addr = dma_map_single(fbd->dev, msg, PAGE_SIZE, direction);
-	if (dma_mapping_error(fbd->dev, addr)) {
-		free_page((unsigned long)msg);
-
+	if (dma_mapping_error(fbd->dev, addr))
 		return -ENOSPC;
-	}
 
 	mbx->buf_info[tail].msg = msg;
 	mbx->buf_info[tail].addr = addr;
@@ -141,7 +168,7 @@ static void fbnic_mbx_clean_desc_ring(struct fbnic_dev *fbd, int mbx_idx)
 {
 	int i;
 
-	fbnic_mbx_init_desc_ring(fbd, mbx_idx);
+	fbnic_mbx_reset_desc_ring(fbd, mbx_idx);
 
 	for (i = FBNIC_IPC_MBX_DESC_LEN; i--;)
 		fbnic_mbx_unmap_and_free_msg(fbd, mbx_idx, i);
@@ -265,67 +292,41 @@ static int fbnic_fw_xmit_simple_msg(struct fbnic_dev *fbd, u32 msg_type)
 	return err;
 }
 
-/**
- * fbnic_fw_xmit_cap_msg - Allocate and populate a FW capabilities message
- * @fbd: FBNIC device structure
- *
- * Return: NULL on failure to allocate, error pointer on error, or pointer
- * to new TLV test message.
- *
- * Sends a single TLV header indicating the host wants the firmware to
- * confirm the capabilities and version.
- **/
-static int fbnic_fw_xmit_cap_msg(struct fbnic_dev *fbd)
-{
-	int err = fbnic_fw_xmit_simple_msg(fbd, FBNIC_TLV_MSG_ID_HOST_CAP_REQ);
-
-	/* Return 0 if we are not calling this on ASIC */
-	return (err == -EOPNOTSUPP) ? 0 : err;
-}
-
-static void fbnic_mbx_postinit_desc_ring(struct fbnic_dev *fbd, int mbx_idx)
+static void fbnic_mbx_init_desc_ring(struct fbnic_dev *fbd, int mbx_idx)
 {
 	struct fbnic_fw_mbx *mbx = &fbd->mbx[mbx_idx];
 
-	/* This is a one time init, so just exit if it is completed */
-	if (mbx->ready)
-		return;
-
 	mbx->ready = true;
 
 	switch (mbx_idx) {
 	case FBNIC_IPC_MBX_RX_IDX:
+		/* Enable DMA writes from the device */
+		wr32(fbd, FBNIC_PUL_OB_TLP_HDR_AW_CFG,
+		     FBNIC_PUL_OB_TLP_HDR_AW_CFG_BME);
+
 		/* Make sure we have a page for the FW to write to */
 		fbnic_mbx_alloc_rx_msgs(fbd);
 		break;
 	case FBNIC_IPC_MBX_TX_IDX:
-		/* Force version to 1 if we successfully requested an update
-		 * from the firmware. This should be overwritten once we get
-		 * the actual version from the firmware in the capabilities
-		 * request message.
-		 */
-		if (!fbnic_fw_xmit_cap_msg(fbd) &&
-		    !fbd->fw_cap.running.mgmt.version)
-			fbd->fw_cap.running.mgmt.version = 1;
+		/* Enable DMA reads from the device */
+		wr32(fbd, FBNIC_PUL_OB_TLP_HDR_AR_CFG,
+		     FBNIC_PUL_OB_TLP_HDR_AR_CFG_BME);
 		break;
 	}
 }
 
-static void fbnic_mbx_postinit(struct fbnic_dev *fbd)
+static bool fbnic_mbx_event(struct fbnic_dev *fbd)
 {
-	int i;
-
-	/* We only need to do this on the first interrupt following init.
+	/* We only need to do this on the first interrupt following reset.
 	 * this primes the mailbox so that we will have cleared all the
 	 * skip descriptors.
 	 */
 	if (!(rd32(fbd, FBNIC_INTR_STATUS(0)) & (1u << FBNIC_FW_MSIX_ENTRY)))
-		return;
+		return false;
 
 	wr32(fbd, FBNIC_INTR_CLEAR(0), 1u << FBNIC_FW_MSIX_ENTRY);
 
-	for (i = 0; i < FBNIC_IPC_MBX_INDICES; i++)
-		fbnic_mbx_postinit_desc_ring(fbd, i);
+	return true;
 }
 
 /**
@@ -726,7 +727,7 @@ next_page:
 
 void fbnic_mbx_poll(struct fbnic_dev *fbd)
 {
-	fbnic_mbx_postinit(fbd);
+	fbnic_mbx_event(fbd);
 
 	fbnic_mbx_process_tx_msgs(fbd);
 	fbnic_mbx_process_rx_msgs(fbd);
@@ -734,60 +735,80 @@ void fbnic_mbx_poll(struct fbnic_dev *fbd)
 
 int fbnic_mbx_poll_tx_ready(struct fbnic_dev *fbd)
 {
-	struct fbnic_fw_mbx *tx_mbx;
-	int attempts = 50;
+	unsigned long timeout = jiffies + 10 * HZ + 1;
+	int err, i;
 
-	/* Immediate fail if BAR4 isn't there */
-	if (!fbnic_fw_present(fbd))
-		return -ENODEV;
+	do {
+		if (!time_is_after_jiffies(timeout))
+			return -ETIMEDOUT;
 
-	tx_mbx = &fbd->mbx[FBNIC_IPC_MBX_TX_IDX];
-	while (!tx_mbx->ready && --attempts) {
 		/* Force the firmware to trigger an interrupt response to
 		 * avoid the mailbox getting stuck closed if the interrupt
 		 * is reset.
 		 */
-		fbnic_mbx_init_desc_ring(fbd, FBNIC_IPC_MBX_TX_IDX);
+		fbnic_mbx_reset_desc_ring(fbd, FBNIC_IPC_MBX_TX_IDX);
 
-		msleep(200);
+		/* Immediate fail if BAR4 went away */
+		if (!fbnic_fw_present(fbd))
+			return -ENODEV;
 
-		fbnic_mbx_poll(fbd);
-	}
+		msleep(20);
+	} while (!fbnic_mbx_event(fbd));
+
+	/* FW has shown signs of life. Enable DMA and start Tx/Rx */
+	for (i = 0; i < FBNIC_IPC_MBX_INDICES; i++)
+		fbnic_mbx_init_desc_ring(fbd, i);
+
+	/* Request an update from the firmware. This should overwrite
+	 * mgmt.version once we get the actual version from the firmware
+	 * in the capabilities request message.
+	 */
+	err = fbnic_fw_xmit_simple_msg(fbd, FBNIC_TLV_MSG_ID_HOST_CAP_REQ);
+	if (err)
+		goto clean_mbx;
+
+	/* Use "1" to indicate we entered the state waiting for a response */
+	fbd->fw_cap.running.mgmt.version = 1;
 
-	return attempts ? 0 : -ETIMEDOUT;
+	return 0;
+clean_mbx:
+	/* Cleanup Rx buffers and disable mailbox */
+	fbnic_mbx_clean(fbd);
+	return err;
 }
 
 void fbnic_mbx_flush_tx(struct fbnic_dev *fbd)
 {
+	unsigned long timeout = jiffies + 10 * HZ + 1;
 	struct fbnic_fw_mbx *tx_mbx;
-	int attempts = 50;
-	u8 count = 0;
-
-	/* Nothing to do if there is no mailbox */
-	if (!fbnic_fw_present(fbd))
-		return;
+	u8 tail;
 
 	/* Record current Rx stats */
 	tx_mbx = &fbd->mbx[FBNIC_IPC_MBX_TX_IDX];
 
-	/* Nothing to do if mailbox never got to ready */
-	if (!tx_mbx->ready)
-		return;
+	spin_lock_irq(&fbd->fw_tx_lock);
+
+	/* Clear ready to prevent any further attempts to transmit */
+	tx_mbx->ready = false;
+
+	/* Read tail to determine the last tail state for the ring */
+	tail = tx_mbx->tail;
+
+	spin_unlock_irq(&fbd->fw_tx_lock);
 
 	/* Give firmware time to process packet,
-	 * we will wait up to 10 seconds which is 50 waits of 200ms.
+	 * we will wait up to 10 seconds which is 500 waits of 20ms.
 	 */
 	do {
 		u8 head = tx_mbx->head;
 
-		if (head == tx_mbx->tail)
+		/* Tx ring is empty once head == tail */
+		if (head == tail)
 			break;
 
-		msleep(200);
+		msleep(20);
 		fbnic_mbx_process_tx_msgs(fbd);
-
-		count += (tx_mbx->head - head) % FBNIC_IPC_MBX_DESC_LEN;
-	} while (count < FBNIC_IPC_MBX_DESC_LEN && --attempts);
+	} while (time_is_after_jiffies(timeout));
 }
 
 void fbnic_get_fw_ver_commit_str(struct fbnic_dev *fbd, char *fw_version,
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_mac.c b/drivers/net/ethernet/meta/fbnic/fbnic_mac.c
index 7b654d0a6dac..06fa65e4f35b 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_mac.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_mac.c
@@ -79,12 +79,6 @@ static void fbnic_mac_init_axi(struct fbnic_dev *fbd)
 	fbnic_init_readrq(fbd, FBNIC_QM_RNI_RBP_CTL, cls, readrq);
 	fbnic_init_mps(fbd, FBNIC_QM_RNI_RDE_CTL, cls, mps);
 	fbnic_init_mps(fbd, FBNIC_QM_RNI_RCM_CTL, cls, mps);
-
-	/* Enable XALI AR/AW outbound */
-	wr32(fbd, FBNIC_PUL_OB_TLP_HDR_AW_CFG,
-	     FBNIC_PUL_OB_TLP_HDR_AW_CFG_BME);
-	wr32(fbd, FBNIC_PUL_OB_TLP_HDR_AR_CFG,
-	     FBNIC_PUL_OB_TLP_HDR_AR_CFG_BME);
 }
 
 static void fbnic_mac_init_qm(struct fbnic_dev *fbd)
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c
index a400616a24d4..79e94632533c 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c
@@ -544,6 +544,8 @@ struct net_device *fbnic_netdev_alloc(struct fbnic_dev *fbd)
 	fbnic_rss_key_fill(fbn->rss_key);
 	fbnic_rss_init_en_mask(fbn);
 
+	netdev->priv_flags |= IFF_UNICAST_FLT;
+
 	netdev->features |=
 		NETIF_F_RXHASH |
 		NETIF_F_SG |
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c
index 6a6d7e22f1a7..fc52db8e36f2 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c
@@ -389,8 +389,8 @@ static void fbnic_page_pool_init(struct fbnic_ring *ring, unsigned int idx,
 {
 	struct fbnic_rx_buf *rx_buf = &ring->rx_buf[idx];
 
-	page_pool_fragment_page(page, PAGECNT_BIAS_MAX);
-	rx_buf->pagecnt_bias = PAGECNT_BIAS_MAX;
+	page_pool_fragment_page(page, FBNIC_PAGECNT_BIAS_MAX);
+	rx_buf->pagecnt_bias = FBNIC_PAGECNT_BIAS_MAX;
 	rx_buf->page = page;
 }
 
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h
index 2f91f68d11d5..05cde71db9df 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h
@@ -59,10 +59,8 @@ struct fbnic_queue_stats {
 	struct u64_stats_sync syncp;
 };
 
-/* Pagecnt bias is long max to reserve the last bit to catch overflow
- * cases where if we overcharge the bias it will flip over to be negative.
- */
-#define PAGECNT_BIAS_MAX	LONG_MAX
+#define FBNIC_PAGECNT_BIAS_MAX	PAGE_SIZE
+
 struct fbnic_rx_buf {
 	struct page *page;
 	long pagecnt_bias;
diff --git a/drivers/net/ethernet/microchip/lan743x_ethtool.c b/drivers/net/ethernet/microchip/lan743x_ethtool.c
index 1a1cbd034eda..2acd9c3531de 100644
--- a/drivers/net/ethernet/microchip/lan743x_ethtool.c
+++ b/drivers/net/ethernet/microchip/lan743x_ethtool.c
@@ -18,6 +18,8 @@
 #define EEPROM_MAC_OFFSET		    (0x01)
 #define MAX_EEPROM_SIZE			    (512)
 #define MAX_OTP_SIZE			    (1024)
+#define MAX_HS_OTP_SIZE			    (8 * 1024)
+#define MAX_HS_EEPROM_SIZE		    (64 * 1024)
 #define OTP_INDICATOR_1			    (0xF3)
 #define OTP_INDICATOR_2			    (0xF7)
 
@@ -272,6 +274,9 @@ static int lan743x_hs_otp_read(struct lan743x_adapter *adapter, u32 offset,
 	int ret;
 	int i;
 
+	if (offset + length > MAX_HS_OTP_SIZE)
+		return -EINVAL;
+
 	ret = lan743x_hs_syslock_acquire(adapter, LOCK_TIMEOUT_MAX_CNT);
 	if (ret < 0)
 		return ret;
@@ -320,6 +325,9 @@ static int lan743x_hs_otp_write(struct lan743x_adapter *adapter, u32 offset,
 	int ret;
 	int i;
 
+	if (offset + length > MAX_HS_OTP_SIZE)
+		return -EINVAL;
+
 	ret = lan743x_hs_syslock_acquire(adapter, LOCK_TIMEOUT_MAX_CNT);
 	if (ret < 0)
 		return ret;
@@ -497,6 +505,9 @@ static int lan743x_hs_eeprom_read(struct lan743x_adapter *adapter,
 	u32 val;
 	int i;
 
+	if (offset + length > MAX_HS_EEPROM_SIZE)
+		return -EINVAL;
+
 	retval = lan743x_hs_syslock_acquire(adapter, LOCK_TIMEOUT_MAX_CNT);
 	if (retval < 0)
 		return retval;
@@ -539,6 +550,9 @@ static int lan743x_hs_eeprom_write(struct lan743x_adapter *adapter,
 	u32 val;
 	int i;
 
+	if (offset + length > MAX_HS_EEPROM_SIZE)
+		return -EINVAL;
+
 	retval = lan743x_hs_syslock_acquire(adapter, LOCK_TIMEOUT_MAX_CNT);
 	if (retval < 0)
 		return retval;
@@ -604,9 +618,9 @@ static int lan743x_ethtool_get_eeprom_len(struct net_device *netdev)
 	struct lan743x_adapter *adapter = netdev_priv(netdev);
 
 	if (adapter->flags & LAN743X_ADAPTER_FLAG_OTP)
-		return MAX_OTP_SIZE;
+		return adapter->is_pci11x1x ? MAX_HS_OTP_SIZE : MAX_OTP_SIZE;
 
-	return MAX_EEPROM_SIZE;
+	return adapter->is_pci11x1x ? MAX_HS_EEPROM_SIZE : MAX_EEPROM_SIZE;
 }
 
 static int lan743x_ethtool_get_eeprom(struct net_device *netdev,
diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c
index 4dc5adcda6a3..9836fbbea0cc 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.c
+++ b/drivers/net/ethernet/microchip/lan743x_main.c
@@ -1330,7 +1330,7 @@ static int lan743x_mac_set_mtu(struct lan743x_adapter *adapter, int new_mtu)
 }
 
 /* PHY */
-static int lan743x_phy_reset(struct lan743x_adapter *adapter)
+static int lan743x_hw_reset_phy(struct lan743x_adapter *adapter)
 {
 	u32 data;
 
@@ -1346,11 +1346,6 @@ static int lan743x_phy_reset(struct lan743x_adapter *adapter)
 				  50000, 1000000);
 }
 
-static int lan743x_phy_init(struct lan743x_adapter *adapter)
-{
-	return lan743x_phy_reset(adapter);
-}
-
 static void lan743x_phy_interface_select(struct lan743x_adapter *adapter)
 {
 	u32 id_rev;
@@ -1815,6 +1810,7 @@ static void lan743x_tx_frame_add_lso(struct lan743x_tx *tx,
 	if (nr_frags <= 0) {
 		tx->frame_data0 |= TX_DESC_DATA0_LS_;
 		tx->frame_data0 |= TX_DESC_DATA0_IOC_;
+		tx->frame_last = tx->frame_first;
 	}
 	tx_descriptor = &tx->ring_cpu_ptr[tx->frame_tail];
 	tx_descriptor->data0 = cpu_to_le32(tx->frame_data0);
@@ -1884,6 +1880,7 @@ static int lan743x_tx_frame_add_fragment(struct lan743x_tx *tx,
 		tx->frame_first = 0;
 		tx->frame_data0 = 0;
 		tx->frame_tail = 0;
+		tx->frame_last = 0;
 		return -ENOMEM;
 	}
 
@@ -1924,16 +1921,18 @@ static void lan743x_tx_frame_end(struct lan743x_tx *tx,
 	    TX_DESC_DATA0_DTYPE_DATA_) {
 		tx->frame_data0 |= TX_DESC_DATA0_LS_;
 		tx->frame_data0 |= TX_DESC_DATA0_IOC_;
+		tx->frame_last = tx->frame_tail;
 	}
 
-	tx_descriptor = &tx->ring_cpu_ptr[tx->frame_tail];
-	buffer_info = &tx->buffer_info[tx->frame_tail];
+	tx_descriptor = &tx->ring_cpu_ptr[tx->frame_last];
+	buffer_info = &tx->buffer_info[tx->frame_last];
 	buffer_info->skb = skb;
 	if (time_stamp)
 		buffer_info->flags |= TX_BUFFER_INFO_FLAG_TIMESTAMP_REQUESTED;
 	if (ignore_sync)
 		buffer_info->flags |= TX_BUFFER_INFO_FLAG_IGNORE_SYNC;
 
+	tx_descriptor = &tx->ring_cpu_ptr[tx->frame_tail];
 	tx_descriptor->data0 = cpu_to_le32(tx->frame_data0);
 	tx->frame_tail = lan743x_tx_next_index(tx, tx->frame_tail);
 	tx->last_tail = tx->frame_tail;
@@ -3462,6 +3461,7 @@ static int lan743x_hardware_init(struct lan743x_adapter *adapter,
 				 struct pci_dev *pdev)
 {
 	struct lan743x_tx *tx;
+	u32 sgmii_ctl;
 	int index;
 	int ret;
 
@@ -3474,6 +3474,15 @@ static int lan743x_hardware_init(struct lan743x_adapter *adapter,
 		spin_lock_init(&adapter->eth_syslock_spinlock);
 		mutex_init(&adapter->sgmii_rw_lock);
 		pci11x1x_set_rfe_rd_fifo_threshold(adapter);
+		sgmii_ctl = lan743x_csr_read(adapter, SGMII_CTL);
+		if (adapter->is_sgmii_en) {
+			sgmii_ctl |= SGMII_CTL_SGMII_ENABLE_;
+			sgmii_ctl &= ~SGMII_CTL_SGMII_POWER_DN_;
+		} else {
+			sgmii_ctl &= ~SGMII_CTL_SGMII_ENABLE_;
+			sgmii_ctl |= SGMII_CTL_SGMII_POWER_DN_;
+		}
+		lan743x_csr_write(adapter, SGMII_CTL, sgmii_ctl);
 	} else {
 		adapter->max_tx_channels = LAN743X_MAX_TX_CHANNELS;
 		adapter->used_tx_channels = LAN743X_USED_TX_CHANNELS;
@@ -3491,10 +3500,6 @@ static int lan743x_hardware_init(struct lan743x_adapter *adapter,
 	if (ret)
 		return ret;
 
-	ret = lan743x_phy_init(adapter);
-	if (ret)
-		return ret;
-
 	ret = lan743x_ptp_init(adapter);
 	if (ret)
 		return ret;
@@ -3522,7 +3527,6 @@ static int lan743x_hardware_init(struct lan743x_adapter *adapter,
 
 static int lan743x_mdiobus_init(struct lan743x_adapter *adapter)
 {
-	u32 sgmii_ctl;
 	int ret;
 
 	adapter->mdiobus = devm_mdiobus_alloc(&adapter->pdev->dev);
@@ -3534,10 +3538,6 @@ static int lan743x_mdiobus_init(struct lan743x_adapter *adapter)
 	adapter->mdiobus->priv = (void *)adapter;
 	if (adapter->is_pci11x1x) {
 		if (adapter->is_sgmii_en) {
-			sgmii_ctl = lan743x_csr_read(adapter, SGMII_CTL);
-			sgmii_ctl |= SGMII_CTL_SGMII_ENABLE_;
-			sgmii_ctl &= ~SGMII_CTL_SGMII_POWER_DN_;
-			lan743x_csr_write(adapter, SGMII_CTL, sgmii_ctl);
 			netif_dbg(adapter, drv, adapter->netdev,
 				  "SGMII operation\n");
 			adapter->mdiobus->read = lan743x_mdiobus_read_c22;
@@ -3548,10 +3548,6 @@ static int lan743x_mdiobus_init(struct lan743x_adapter *adapter)
 			netif_dbg(adapter, drv, adapter->netdev,
 				  "lan743x-mdiobus-c45\n");
 		} else {
-			sgmii_ctl = lan743x_csr_read(adapter, SGMII_CTL);
-			sgmii_ctl &= ~SGMII_CTL_SGMII_ENABLE_;
-			sgmii_ctl |= SGMII_CTL_SGMII_POWER_DN_;
-			lan743x_csr_write(adapter, SGMII_CTL, sgmii_ctl);
 			netif_dbg(adapter, drv, adapter->netdev,
 				  "RGMII operation\n");
 			// Only C22 support when RGMII I/F
@@ -3637,6 +3633,10 @@ static int lan743x_pcidev_probe(struct pci_dev *pdev,
 	if (ret)
 		goto cleanup_pci;
 
+	ret = lan743x_hw_reset_phy(adapter);
+	if (ret)
+		goto cleanup_pci;
+
 	ret = lan743x_hardware_init(adapter, pdev);
 	if (ret)
 		goto cleanup_pci;
diff --git a/drivers/net/ethernet/microchip/lan743x_main.h b/drivers/net/ethernet/microchip/lan743x_main.h
index 8ef897c114d3..2f0cab0c85e1 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.h
+++ b/drivers/net/ethernet/microchip/lan743x_main.h
@@ -980,6 +980,7 @@ struct lan743x_tx {
 	u32		frame_first;
 	u32		frame_data0;
 	u32		frame_tail;
+	u32		frame_last;
 
 	struct lan743x_tx_buffer_info *buffer_info;
 
diff --git a/drivers/net/ethernet/microchip/lan743x_ptp.h b/drivers/net/ethernet/microchip/lan743x_ptp.h
index 0d29914cd460..225e8232474d 100644
--- a/drivers/net/ethernet/microchip/lan743x_ptp.h
+++ b/drivers/net/ethernet/microchip/lan743x_ptp.h
@@ -18,9 +18,9 @@
  */
 #define LAN743X_PTP_N_EVENT_CHAN	2
 #define LAN743X_PTP_N_PEROUT		LAN743X_PTP_N_EVENT_CHAN
-#define LAN743X_PTP_N_EXTTS		4
-#define LAN743X_PTP_N_PPS		0
 #define PCI11X1X_PTP_IO_MAX_CHANNELS	8
+#define LAN743X_PTP_N_EXTTS		PCI11X1X_PTP_IO_MAX_CHANNELS
+#define LAN743X_PTP_N_PPS		0
 #define PTP_CMD_CTL_TIMEOUT_CNT		50
 
 struct lan743x_adapter;
diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c
index 534d4716d5f7..b34e015eedf9 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c
@@ -353,6 +353,11 @@ static void lan966x_ifh_set_rew_op(void *ifh, u64 rew_op)
 	lan966x_ifh_set(ifh, rew_op, IFH_POS_REW_CMD, IFH_WID_REW_CMD);
 }
 
+static void lan966x_ifh_set_oam_type(void *ifh, u64 oam_type)
+{
+	lan966x_ifh_set(ifh, oam_type, IFH_POS_PDU_TYPE, IFH_WID_PDU_TYPE);
+}
+
 static void lan966x_ifh_set_timestamp(void *ifh, u64 timestamp)
 {
 	lan966x_ifh_set(ifh, timestamp, IFH_POS_TIMESTAMP, IFH_WID_TIMESTAMP);
@@ -380,6 +385,7 @@ static netdev_tx_t lan966x_port_xmit(struct sk_buff *skb,
 			return err;
 
 		lan966x_ifh_set_rew_op(ifh, LAN966X_SKB_CB(skb)->rew_op);
+		lan966x_ifh_set_oam_type(ifh, LAN966X_SKB_CB(skb)->pdu_type);
 		lan966x_ifh_set_timestamp(ifh, LAN966X_SKB_CB(skb)->ts_id);
 	}
 
@@ -874,6 +880,7 @@ static int lan966x_probe_port(struct lan966x *lan966x, u32 p,
 	lan966x_vlan_port_set_vlan_aware(port, 0);
 	lan966x_vlan_port_set_vid(port, HOST_PVID, false, false);
 	lan966x_vlan_port_apply(port);
+	lan966x_vlan_port_rew_host(port);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.h b/drivers/net/ethernet/microchip/lan966x/lan966x_main.h
index 25cb2f61986f..8aa39497818f 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.h
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.h
@@ -75,6 +75,10 @@
 #define IFH_REW_OP_ONE_STEP_PTP		0x3
 #define IFH_REW_OP_TWO_STEP_PTP		0x4
 
+#define IFH_PDU_TYPE_NONE		0
+#define IFH_PDU_TYPE_IPV4		7
+#define IFH_PDU_TYPE_IPV6		8
+
 #define FDMA_RX_DCB_MAX_DBS		1
 #define FDMA_TX_DCB_MAX_DBS		1
 
@@ -254,6 +258,7 @@ struct lan966x_phc {
 
 struct lan966x_skb_cb {
 	u8 rew_op;
+	u8 pdu_type;
 	u16 ts_id;
 	unsigned long jiffies;
 };
@@ -492,6 +497,7 @@ void lan966x_vlan_port_apply(struct lan966x_port *port);
 bool lan966x_vlan_cpu_member_cpu_vlan_mask(struct lan966x *lan966x, u16 vid);
 void lan966x_vlan_port_set_vlan_aware(struct lan966x_port *port,
 				      bool vlan_aware);
+void lan966x_vlan_port_rew_host(struct lan966x_port *port);
 int lan966x_vlan_port_set_vid(struct lan966x_port *port,
 			      u16 vid,
 			      bool pvid,
diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c b/drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c
index 63905bb5a63a..87e5e81d40dc 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c
@@ -322,34 +322,55 @@ void lan966x_ptp_hwtstamp_get(struct lan966x_port *port,
 	*cfg = phc->hwtstamp_config;
 }
 
-static int lan966x_ptp_classify(struct lan966x_port *port, struct sk_buff *skb)
+static void lan966x_ptp_classify(struct lan966x_port *port, struct sk_buff *skb,
+				 u8 *rew_op, u8 *pdu_type)
 {
 	struct ptp_header *header;
 	u8 msgtype;
 	int type;
 
-	if (port->ptp_tx_cmd == IFH_REW_OP_NOOP)
-		return IFH_REW_OP_NOOP;
+	if (port->ptp_tx_cmd == IFH_REW_OP_NOOP) {
+		*rew_op = IFH_REW_OP_NOOP;
+		*pdu_type = IFH_PDU_TYPE_NONE;
+		return;
+	}
 
 	type = ptp_classify_raw(skb);
-	if (type == PTP_CLASS_NONE)
-		return IFH_REW_OP_NOOP;
+	if (type == PTP_CLASS_NONE) {
+		*rew_op = IFH_REW_OP_NOOP;
+		*pdu_type = IFH_PDU_TYPE_NONE;
+		return;
+	}
 
 	header = ptp_parse_header(skb, type);
-	if (!header)
-		return IFH_REW_OP_NOOP;
+	if (!header) {
+		*rew_op = IFH_REW_OP_NOOP;
+		*pdu_type = IFH_PDU_TYPE_NONE;
+		return;
+	}
 
-	if (port->ptp_tx_cmd == IFH_REW_OP_TWO_STEP_PTP)
-		return IFH_REW_OP_TWO_STEP_PTP;
+	if (type & PTP_CLASS_L2)
+		*pdu_type = IFH_PDU_TYPE_NONE;
+	if (type & PTP_CLASS_IPV4)
+		*pdu_type = IFH_PDU_TYPE_IPV4;
+	if (type & PTP_CLASS_IPV6)
+		*pdu_type = IFH_PDU_TYPE_IPV6;
+
+	if (port->ptp_tx_cmd == IFH_REW_OP_TWO_STEP_PTP) {
+		*rew_op = IFH_REW_OP_TWO_STEP_PTP;
+		return;
+	}
 
 	/* If it is sync and run 1 step then set the correct operation,
 	 * otherwise run as 2 step
 	 */
 	msgtype = ptp_get_msgtype(header, type);
-	if ((msgtype & 0xf) == 0)
-		return IFH_REW_OP_ONE_STEP_PTP;
+	if ((msgtype & 0xf) == 0) {
+		*rew_op = IFH_REW_OP_ONE_STEP_PTP;
+		return;
+	}
 
-	return IFH_REW_OP_TWO_STEP_PTP;
+	*rew_op = IFH_REW_OP_TWO_STEP_PTP;
 }
 
 static void lan966x_ptp_txtstamp_old_release(struct lan966x_port *port)
@@ -374,10 +395,12 @@ int lan966x_ptp_txtstamp_request(struct lan966x_port *port,
 {
 	struct lan966x *lan966x = port->lan966x;
 	unsigned long flags;
+	u8 pdu_type;
 	u8 rew_op;
 
-	rew_op = lan966x_ptp_classify(port, skb);
+	lan966x_ptp_classify(port, skb, &rew_op, &pdu_type);
 	LAN966X_SKB_CB(skb)->rew_op = rew_op;
+	LAN966X_SKB_CB(skb)->pdu_type = pdu_type;
 
 	if (rew_op != IFH_REW_OP_TWO_STEP_PTP)
 		return 0;
diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_switchdev.c b/drivers/net/ethernet/microchip/lan966x/lan966x_switchdev.c
index 1c88120eb291..bcb4db76b75c 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_switchdev.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_switchdev.c
@@ -297,6 +297,7 @@ static void lan966x_port_bridge_leave(struct lan966x_port *port,
 	lan966x_vlan_port_set_vlan_aware(port, false);
 	lan966x_vlan_port_set_vid(port, HOST_PVID, false, false);
 	lan966x_vlan_port_apply(port);
+	lan966x_vlan_port_rew_host(port);
 }
 
 int lan966x_port_changeupper(struct net_device *dev,
diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_vlan.c b/drivers/net/ethernet/microchip/lan966x/lan966x_vlan.c
index fa34a739c748..7da22520724c 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_vlan.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_vlan.c
@@ -149,6 +149,27 @@ void lan966x_vlan_port_set_vlan_aware(struct lan966x_port *port,
 	port->vlan_aware = vlan_aware;
 }
 
+/* When the interface is in host mode, the interface should not be vlan aware
+ * but it should insert all the tags that it gets from the network stack.
+ * The tags are not in the data of the frame but actually in the skb and the ifh
+ * is configured already to get this tag. So what we need to do is to update the
+ * rewriter to insert the vlan tag for all frames which have a vlan tag
+ * different than 0.
+ */
+void lan966x_vlan_port_rew_host(struct lan966x_port *port)
+{
+	struct lan966x *lan966x = port->lan966x;
+	u32 val;
+
+	/* Tag all frames except when VID=0*/
+	val = REW_TAG_CFG_TAG_CFG_SET(2);
+
+	/* Update only some bits in the register */
+	lan_rmw(val,
+		REW_TAG_CFG_TAG_CFG,
+		lan966x, REW_TAG_CFG(port->chip_port));
+}
+
 void lan966x_vlan_port_apply(struct lan966x_port *port)
 {
 	struct lan966x *lan966x = port->lan966x;
diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c
index 0c2ba2fa88c4..876de6db63c4 100644
--- a/drivers/net/ethernet/microsoft/mana/gdma_main.c
+++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c
@@ -28,6 +28,9 @@ static void mana_gd_init_pf_regs(struct pci_dev *pdev)
 	gc->db_page_base = gc->bar0_va +
 				mana_gd_r64(gc, GDMA_PF_REG_DB_PAGE_OFF);
 
+	gc->phys_db_page_base = gc->bar0_pa +
+				mana_gd_r64(gc, GDMA_PF_REG_DB_PAGE_OFF);
+
 	sriov_base_off = mana_gd_r64(gc, GDMA_SRIOV_REG_CFG_BASE_OFF);
 
 	sriov_base_va = gc->bar0_va + sriov_base_off;
@@ -131,9 +134,10 @@ static int mana_gd_detect_devices(struct pci_dev *pdev)
 	struct gdma_list_devices_resp resp = {};
 	struct gdma_general_req req = {};
 	struct gdma_dev_id dev;
-	u32 i, max_num_devs;
+	int found_dev = 0;
 	u16 dev_type;
 	int err;
+	u32 i;
 
 	mana_gd_init_req_hdr(&req.hdr, GDMA_LIST_DEVICES, sizeof(req),
 			     sizeof(resp));
@@ -145,12 +149,17 @@ static int mana_gd_detect_devices(struct pci_dev *pdev)
 		return err ? err : -EPROTO;
 	}
 
-	max_num_devs = min_t(u32, MAX_NUM_GDMA_DEVICES, resp.num_of_devs);
-
-	for (i = 0; i < max_num_devs; i++) {
+	for (i = 0; i < GDMA_DEV_LIST_SIZE &&
+	     found_dev < resp.num_of_devs; i++) {
 		dev = resp.devs[i];
 		dev_type = dev.type;
 
+		/* Skip empty devices */
+		if (dev.as_uint32 == 0)
+			continue;
+
+		found_dev++;
+
 		/* HWC is already detected in mana_hwc_create_channel(). */
 		if (dev_type == GDMA_DEVICE_HWC)
 			continue;
@@ -1038,7 +1047,7 @@ static u32 mana_gd_write_client_oob(const struct gdma_wqe_request *wqe_req,
 	header->inline_oob_size_div4 = client_oob_size / sizeof(u32);
 
 	if (oob_in_sgl) {
-		WARN_ON_ONCE(!pad_data || wqe_req->num_sge < 2);
+		WARN_ON_ONCE(wqe_req->num_sge < 2);
 
 		header->client_oob_in_sgl = 1;
 
diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index b2d206dec70c..12c22261dd3a 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -636,30 +636,16 @@ int mana_pre_alloc_rxbufs(struct mana_port_context *mpc, int new_mtu, int num_qu
 	mpc->rxbpre_total = 0;
 
 	for (i = 0; i < num_rxb; i++) {
-		if (mpc->rxbpre_alloc_size > PAGE_SIZE) {
-			va = netdev_alloc_frag(mpc->rxbpre_alloc_size);
-			if (!va)
-				goto error;
-
-			page = virt_to_head_page(va);
-			/* Check if the frag falls back to single page */
-			if (compound_order(page) <
-			    get_order(mpc->rxbpre_alloc_size)) {
-				put_page(page);
-				goto error;
-			}
-		} else {
-			page = dev_alloc_page();
-			if (!page)
-				goto error;
+		page = dev_alloc_pages(get_order(mpc->rxbpre_alloc_size));
+		if (!page)
+			goto error;
 
-			va = page_to_virt(page);
-		}
+		va = page_to_virt(page);
 
 		da = dma_map_single(dev, va + mpc->rxbpre_headroom,
 				    mpc->rxbpre_datasize, DMA_FROM_DEVICE);
 		if (dma_mapping_error(dev, da)) {
-			put_page(virt_to_head_page(va));
+			put_page(page);
 			goto error;
 		}
 
@@ -1618,7 +1604,7 @@ drop:
 }
 
 static void *mana_get_rxfrag(struct mana_rxq *rxq, struct device *dev,
-			     dma_addr_t *da, bool *from_pool, bool is_napi)
+			     dma_addr_t *da, bool *from_pool)
 {
 	struct page *page;
 	void *va;
@@ -1629,21 +1615,6 @@ static void *mana_get_rxfrag(struct mana_rxq *rxq, struct device *dev,
 	if (rxq->xdp_save_va) {
 		va = rxq->xdp_save_va;
 		rxq->xdp_save_va = NULL;
-	} else if (rxq->alloc_size > PAGE_SIZE) {
-		if (is_napi)
-			va = napi_alloc_frag(rxq->alloc_size);
-		else
-			va = netdev_alloc_frag(rxq->alloc_size);
-
-		if (!va)
-			return NULL;
-
-		page = virt_to_head_page(va);
-		/* Check if the frag falls back to single page */
-		if (compound_order(page) < get_order(rxq->alloc_size)) {
-			put_page(page);
-			return NULL;
-		}
 	} else {
 		page = page_pool_dev_alloc_pages(rxq->page_pool);
 		if (!page)
@@ -1676,7 +1647,7 @@ static void mana_refill_rx_oob(struct device *dev, struct mana_rxq *rxq,
 	dma_addr_t da;
 	void *va;
 
-	va = mana_get_rxfrag(rxq, dev, &da, &from_pool, true);
+	va = mana_get_rxfrag(rxq, dev, &da, &from_pool);
 	if (!va)
 		return;
 
@@ -2083,7 +2054,7 @@ static int mana_fill_rx_oob(struct mana_recv_buf_oob *rx_oob, u32 mem_key,
 	if (mpc->rxbufs_pre)
 		va = mana_get_rxbuf_pre(rxq, &da);
 	else
-		va = mana_get_rxfrag(rxq, dev, &da, &from_pool, false);
+		va = mana_get_rxfrag(rxq, dev, &da, &from_pool);
 
 	if (!va)
 		return -ENOMEM;
@@ -2169,6 +2140,7 @@ static int mana_create_page_pool(struct mana_rxq *rxq, struct gdma_context *gc)
 	pprm.nid = gc->numa_node;
 	pprm.napi = &rxq->rx_cq.napi;
 	pprm.netdev = rxq->ndev;
+	pprm.order = get_order(rxq->alloc_size);
 
 	rxq->page_pool = page_pool_create(&pprm);
 
diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index ef93df520887..08bee56aea35 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -830,6 +830,7 @@ EXPORT_SYMBOL(ocelot_vlan_prepare);
 int ocelot_vlan_add(struct ocelot *ocelot, int port, u16 vid, bool pvid,
 		    bool untagged)
 {
+	struct ocelot_port *ocelot_port = ocelot->ports[port];
 	int err;
 
 	/* Ignore VID 0 added to our RX filter by the 8021q module, since
@@ -849,6 +850,11 @@ int ocelot_vlan_add(struct ocelot *ocelot, int port, u16 vid, bool pvid,
 					   ocelot_bridge_vlan_find(ocelot, vid));
 		if (err)
 			return err;
+	} else if (ocelot_port->pvid_vlan &&
+		   ocelot_bridge_vlan_find(ocelot, vid) == ocelot_port->pvid_vlan) {
+		err = ocelot_port_set_pvid(ocelot, port, NULL);
+		if (err)
+			return err;
 	}
 
 	/* Untagged egress vlan clasification */
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c b/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c
index 2ec62c8d86e1..59486fe2ad18 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c
@@ -20,6 +20,8 @@ nfp_bpf_cmsg_alloc(struct nfp_app_bpf *bpf, unsigned int size)
 	struct sk_buff *skb;
 
 	skb = nfp_app_ctrl_msg_alloc(bpf->app, size, GFP_KERNEL);
+	if (!skb)
+		return NULL;
 	skb_put(skb, size);
 
 	return skb;
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
index 3d3f936779f7..d6bea7152805 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
@@ -3526,10 +3526,6 @@ void ionic_lif_free(struct ionic_lif *lif)
 	lif->info = NULL;
 	lif->info_pa = 0;
 
-	/* unmap doorbell page */
-	ionic_bus_unmap_dbpage(lif->ionic, lif->kern_dbpage);
-	lif->kern_dbpage = NULL;
-
 	mutex_destroy(&lif->config_lock);
 	mutex_destroy(&lif->queue_lock);
 
@@ -3555,6 +3551,9 @@ void ionic_lif_deinit(struct ionic_lif *lif)
 	ionic_lif_qcq_deinit(lif, lif->notifyqcq);
 	ionic_lif_qcq_deinit(lif, lif->adminqcq);
 
+	ionic_bus_unmap_dbpage(lif->ionic, lif->kern_dbpage);
+	lif->kern_dbpage = NULL;
+
 	ionic_lif_reset(lif);
 }
 
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_main.c b/drivers/net/ethernet/pensando/ionic/ionic_main.c
index 0f817c3f92d8..533df5993048 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_main.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_main.c
@@ -515,9 +515,9 @@ static int __ionic_dev_cmd_wait(struct ionic *ionic, unsigned long max_seconds,
 	unsigned long start_time;
 	unsigned long max_wait;
 	unsigned long duration;
-	int done = 0;
 	bool fw_up;
 	int opcode;
+	bool done;
 	int err;
 
 	/* Wait for dev cmd to complete, retrying if we get EAGAIN,
@@ -525,6 +525,7 @@ static int __ionic_dev_cmd_wait(struct ionic *ionic, unsigned long max_seconds,
 	 */
 	max_wait = jiffies + (max_seconds * HZ);
 try_again:
+	done = false;
 	opcode = idev->opcode;
 	start_time = jiffies;
 	for (fw_up = ionic_is_fw_running(idev);
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
index 0eeda7e502db..0f5758c273c2 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
@@ -321,7 +321,7 @@ static int ionic_xdp_post_frame(struct ionic_queue *q, struct xdp_frame *frame,
 					   len, DMA_TO_DEVICE);
 	} else /* XDP_REDIRECT */ {
 		dma_addr = ionic_tx_map_single(q, frame->data, len);
-		if (!dma_addr)
+		if (dma_addr == DMA_MAPPING_ERROR)
 			return -EIO;
 	}
 
@@ -357,7 +357,7 @@ static int ionic_xdp_post_frame(struct ionic_queue *q, struct xdp_frame *frame,
 			} else {
 				dma_addr = ionic_tx_map_frag(q, frag, 0,
 							     skb_frag_size(frag));
-				if (dma_mapping_error(q->dev, dma_addr)) {
+				if (dma_addr == DMA_MAPPING_ERROR) {
 					ionic_tx_desc_unmap_bufs(q, desc_info);
 					return -EIO;
 				}
@@ -1083,7 +1083,7 @@ static dma_addr_t ionic_tx_map_single(struct ionic_queue *q,
 		net_warn_ratelimited("%s: DMA single map failed on %s!\n",
 				     dev_name(dev), q->name);
 		q_to_tx_stats(q)->dma_map_err++;
-		return 0;
+		return DMA_MAPPING_ERROR;
 	}
 	return dma_addr;
 }
@@ -1100,7 +1100,7 @@ static dma_addr_t ionic_tx_map_frag(struct ionic_queue *q,
 		net_warn_ratelimited("%s: DMA frag map failed on %s!\n",
 				     dev_name(dev), q->name);
 		q_to_tx_stats(q)->dma_map_err++;
-		return 0;
+		return DMA_MAPPING_ERROR;
 	}
 	return dma_addr;
 }
@@ -1116,7 +1116,7 @@ static int ionic_tx_map_skb(struct ionic_queue *q, struct sk_buff *skb,
 	int frag_idx;
 
 	dma_addr = ionic_tx_map_single(q, skb->data, skb_headlen(skb));
-	if (!dma_addr)
+	if (dma_addr == DMA_MAPPING_ERROR)
 		return -EIO;
 	buf_info->dma_addr = dma_addr;
 	buf_info->len = skb_headlen(skb);
@@ -1126,7 +1126,7 @@ static int ionic_tx_map_skb(struct ionic_queue *q, struct sk_buff *skb,
 	nfrags = skb_shinfo(skb)->nr_frags;
 	for (frag_idx = 0; frag_idx < nfrags; frag_idx++, frag++) {
 		dma_addr = ionic_tx_map_frag(q, frag, 0, skb_frag_size(frag));
-		if (!dma_addr)
+		if (dma_addr == DMA_MAPPING_ERROR)
 			goto dma_fail;
 		buf_info->dma_addr = dma_addr;
 		buf_info->len = skb_frag_size(frag);
diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index 99df00c30b8c..b5d744d2586f 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -203,7 +203,7 @@ static struct pci_driver qede_pci_driver = {
 };
 
 static struct qed_eth_cb_ops qede_ll_ops = {
-	{
+	.common = {
 #ifdef CONFIG_RFS_ACCEL
 		.arfs_filter_op = qede_arfs_filter_op,
 #endif
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c
index f9dd50152b1e..d57b976b9040 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c
@@ -454,8 +454,10 @@ static int qlcnic_sriov_set_guest_vlan_mode(struct qlcnic_adapter *adapter,
 
 	num_vlans = sriov->num_allowed_vlans;
 	sriov->allowed_vlans = kcalloc(num_vlans, sizeof(u16), GFP_KERNEL);
-	if (!sriov->allowed_vlans)
+	if (!sriov->allowed_vlans) {
+		qlcnic_sriov_free_vlans(adapter);
 		return -ENOMEM;
+	}
 
 	vlans = (u16 *)&cmd->rsp.arg[3];
 	for (i = 0; i < num_vlans; i++)
@@ -1482,8 +1484,11 @@ static int qlcnic_sriov_channel_cfg_cmd(struct qlcnic_adapter *adapter, u8 cmd_o
 	}
 
 	cmd_op = (cmd.rsp.arg[0] & 0xff);
-	if (cmd.rsp.arg[0] >> 25 == 2)
-		return 2;
+	if (cmd.rsp.arg[0] >> 25 == 2) {
+		ret = 2;
+		goto out;
+	}
+
 	if (cmd_op == QLCNIC_BC_CMD_CHANNEL_INIT)
 		set_bit(QLC_BC_VF_STATE, &vf->state);
 	else
@@ -2167,8 +2172,10 @@ int qlcnic_sriov_alloc_vlans(struct qlcnic_adapter *adapter)
 		vf = &sriov->vf_info[i];
 		vf->sriov_vlans = kcalloc(sriov->num_allowed_vlans,
 					  sizeof(*vf->sriov_vlans), GFP_KERNEL);
-		if (!vf->sriov_vlans)
+		if (!vf->sriov_vlans) {
+			qlcnic_sriov_free_vlans(adapter);
 			return -ENOMEM;
+		}
 	}
 
 	return 0;
diff --git a/drivers/net/ethernet/realtek/r8169.h b/drivers/net/ethernet/realtek/r8169.h
index e2db944e6fa8..be4c9622618d 100644
--- a/drivers/net/ethernet/realtek/r8169.h
+++ b/drivers/net/ethernet/realtek/r8169.h
@@ -68,6 +68,7 @@ enum mac_version {
 	/* support for RTL_GIGA_MAC_VER_60 has been removed */
 	RTL_GIGA_MAC_VER_61,
 	RTL_GIGA_MAC_VER_63,
+	RTL_GIGA_MAC_VER_64,
 	RTL_GIGA_MAC_VER_65,
 	RTL_GIGA_MAC_VER_66,
 	RTL_GIGA_MAC_NONE
diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 5ed2818bac25..7b82779e4cd5 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -55,6 +55,7 @@
 #define FIRMWARE_8107E_2	"rtl_nic/rtl8107e-2.fw"
 #define FIRMWARE_8125A_3	"rtl_nic/rtl8125a-3.fw"
 #define FIRMWARE_8125B_2	"rtl_nic/rtl8125b-2.fw"
+#define FIRMWARE_8125D_1	"rtl_nic/rtl8125d-1.fw"
 #define FIRMWARE_8126A_2	"rtl_nic/rtl8126a-2.fw"
 #define FIRMWARE_8126A_3	"rtl_nic/rtl8126a-3.fw"
 
@@ -138,6 +139,7 @@ static const struct {
 	[RTL_GIGA_MAC_VER_61] = {"RTL8125A",		FIRMWARE_8125A_3},
 	/* reserve 62 for CFG_METHOD_4 in the vendor driver */
 	[RTL_GIGA_MAC_VER_63] = {"RTL8125B",		FIRMWARE_8125B_2},
+	[RTL_GIGA_MAC_VER_64] = {"RTL8125D",		FIRMWARE_8125D_1},
 	[RTL_GIGA_MAC_VER_65] = {"RTL8126A",		FIRMWARE_8126A_2},
 	[RTL_GIGA_MAC_VER_66] = {"RTL8126A",		FIRMWARE_8126A_3},
 };
@@ -707,6 +709,7 @@ MODULE_FIRMWARE(FIRMWARE_8168FP_3);
 MODULE_FIRMWARE(FIRMWARE_8107E_2);
 MODULE_FIRMWARE(FIRMWARE_8125A_3);
 MODULE_FIRMWARE(FIRMWARE_8125B_2);
+MODULE_FIRMWARE(FIRMWARE_8125D_1);
 MODULE_FIRMWARE(FIRMWARE_8126A_2);
 MODULE_FIRMWARE(FIRMWARE_8126A_3);
 
@@ -2098,10 +2101,7 @@ static void rtl_set_eee_txidle_timer(struct rtl8169_private *tp)
 		tp->tx_lpi_timer = timer_val;
 		r8168_mac_ocp_write(tp, 0xe048, timer_val);
 		break;
-	case RTL_GIGA_MAC_VER_61:
-	case RTL_GIGA_MAC_VER_63:
-	case RTL_GIGA_MAC_VER_65:
-	case RTL_GIGA_MAC_VER_66:
+	case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_66:
 		tp->tx_lpi_timer = timer_val;
 		RTL_W16(tp, EEE_TXIDLE_TIMER_8125, timer_val);
 		break;
@@ -2233,6 +2233,9 @@ static enum mac_version rtl8169_get_mac_version(u16 xid, bool gmii)
 		{ 0x7cf, 0x64a,	RTL_GIGA_MAC_VER_66 },
 		{ 0x7cf, 0x649,	RTL_GIGA_MAC_VER_65 },
 
+		/* 8125D family. */
+		{ 0x7cf, 0x688,	RTL_GIGA_MAC_VER_64 },
+
 		/* 8125B family. */
 		{ 0x7cf, 0x641,	RTL_GIGA_MAC_VER_63 },
 
@@ -2500,9 +2503,7 @@ static void rtl_init_rxcfg(struct rtl8169_private *tp)
 	case RTL_GIGA_MAC_VER_61:
 		RTL_W32(tp, RxConfig, RX_FETCH_DFLT_8125 | RX_DMA_BURST);
 		break;
-	case RTL_GIGA_MAC_VER_63:
-	case RTL_GIGA_MAC_VER_65:
-	case RTL_GIGA_MAC_VER_66:
+	case RTL_GIGA_MAC_VER_63 ... RTL_GIGA_MAC_VER_66:
 		RTL_W32(tp, RxConfig, RX_FETCH_DFLT_8125 | RX_DMA_BURST |
 			RX_PAUSE_SLOT_ON);
 		break;
@@ -2850,6 +2851,32 @@ static u32 rtl_csi_read(struct rtl8169_private *tp, int addr)
 		RTL_R32(tp, CSIDR) : ~0;
 }
 
+static void rtl_disable_zrxdc_timeout(struct rtl8169_private *tp)
+{
+	struct pci_dev *pdev = tp->pci_dev;
+	u32 csi;
+	int rc;
+	u8 val;
+
+#define RTL_GEN3_RELATED_OFF	0x0890
+#define RTL_GEN3_ZRXDC_NONCOMPL	0x1
+	if (pdev->cfg_size > RTL_GEN3_RELATED_OFF) {
+		rc = pci_read_config_byte(pdev, RTL_GEN3_RELATED_OFF, &val);
+		if (rc == PCIBIOS_SUCCESSFUL) {
+			val &= ~RTL_GEN3_ZRXDC_NONCOMPL;
+			rc = pci_write_config_byte(pdev, RTL_GEN3_RELATED_OFF,
+						   val);
+			if (rc == PCIBIOS_SUCCESSFUL)
+				return;
+		}
+	}
+
+	netdev_notice_once(tp->dev,
+		"No native access to PCI extended config space, falling back to CSI\n");
+	csi = rtl_csi_read(tp, RTL_GEN3_RELATED_OFF);
+	rtl_csi_write(tp, RTL_GEN3_RELATED_OFF, csi & ~RTL_GEN3_ZRXDC_NONCOMPL);
+}
+
 static void rtl_set_aspm_entry_latency(struct rtl8169_private *tp, u8 val)
 {
 	struct pci_dev *pdev = tp->pci_dev;
@@ -3814,8 +3841,15 @@ static void rtl_hw_start_8125b(struct rtl8169_private *tp)
 	rtl_hw_start_8125_common(tp);
 }
 
+static void rtl_hw_start_8125d(struct rtl8169_private *tp)
+{
+	rtl_set_def_aspm_entry_latency(tp);
+	rtl_hw_start_8125_common(tp);
+}
+
 static void rtl_hw_start_8126a(struct rtl8169_private *tp)
 {
+	rtl_disable_zrxdc_timeout(tp);
 	rtl_set_def_aspm_entry_latency(tp);
 	rtl_hw_start_8125_common(tp);
 }
@@ -3862,6 +3896,7 @@ static void rtl_hw_config(struct rtl8169_private *tp)
 		[RTL_GIGA_MAC_VER_53] = rtl_hw_start_8117,
 		[RTL_GIGA_MAC_VER_61] = rtl_hw_start_8125a_2,
 		[RTL_GIGA_MAC_VER_63] = rtl_hw_start_8125b,
+		[RTL_GIGA_MAC_VER_64] = rtl_hw_start_8125d,
 		[RTL_GIGA_MAC_VER_65] = rtl_hw_start_8126a,
 		[RTL_GIGA_MAC_VER_66] = rtl_hw_start_8126a,
 	};
@@ -3879,6 +3914,7 @@ static void rtl_hw_start_8125(struct rtl8169_private *tp)
 	/* disable interrupt coalescing */
 	switch (tp->mac_version) {
 	case RTL_GIGA_MAC_VER_61:
+	case RTL_GIGA_MAC_VER_64:
 		for (i = 0xa00; i < 0xb00; i += 4)
 			RTL_W32(tp, i, 0);
 		break;
@@ -5231,6 +5267,7 @@ static int r8169_mdio_register(struct rtl8169_private *tp)
 	new_bus->priv = tp;
 	new_bus->parent = &pdev->dev;
 	new_bus->irq[0] = PHY_MAC_INTERRUPT;
+	new_bus->phy_mask = GENMASK(31, 1);
 	snprintf(new_bus->id, MII_BUS_ID_SIZE, "r8169-%x-%x",
 		 pci_domain_nr(pdev->bus), pci_dev_id(pdev));
 
diff --git a/drivers/net/ethernet/realtek/r8169_phy_config.c b/drivers/net/ethernet/realtek/r8169_phy_config.c
index cf29b1208482..d09b2a41cd06 100644
--- a/drivers/net/ethernet/realtek/r8169_phy_config.c
+++ b/drivers/net/ethernet/realtek/r8169_phy_config.c
@@ -1104,6 +1104,15 @@ static void rtl8125b_hw_phy_config(struct rtl8169_private *tp,
 	rtl8125b_config_eee_phy(phydev);
 }
 
+static void rtl8125d_hw_phy_config(struct rtl8169_private *tp,
+				   struct phy_device *phydev)
+{
+	r8169_apply_firmware(tp);
+	rtl8125_legacy_force_mode(phydev);
+	rtl8168g_disable_aldps(phydev);
+	rtl8125b_config_eee_phy(phydev);
+}
+
 static void rtl8126a_hw_phy_config(struct rtl8169_private *tp,
 				   struct phy_device *phydev)
 {
@@ -1160,6 +1169,7 @@ void r8169_hw_phy_config(struct rtl8169_private *tp, struct phy_device *phydev,
 		[RTL_GIGA_MAC_VER_53] = rtl8117_hw_phy_config,
 		[RTL_GIGA_MAC_VER_61] = rtl8125a_2_hw_phy_config,
 		[RTL_GIGA_MAC_VER_63] = rtl8125b_hw_phy_config,
+		[RTL_GIGA_MAC_VER_64] = rtl8125d_hw_phy_config,
 		[RTL_GIGA_MAC_VER_65] = rtl8126a_hw_phy_config,
 		[RTL_GIGA_MAC_VER_66] = rtl8126a_hw_phy_config,
 	};
diff --git a/drivers/net/ethernet/realtek/rtase/rtase_main.c b/drivers/net/ethernet/realtek/rtase/rtase_main.c
index 14ffd45e9a25..3a588aaa89c5 100644
--- a/drivers/net/ethernet/realtek/rtase/rtase_main.c
+++ b/drivers/net/ethernet/realtek/rtase/rtase_main.c
@@ -1501,7 +1501,10 @@ static void rtase_wait_for_quiescence(const struct net_device *dev)
 static void rtase_sw_reset(struct net_device *dev)
 {
 	struct rtase_private *tp = netdev_priv(dev);
+	struct rtase_ring *ring, *tmp;
+	struct rtase_int_vector *ivec;
 	int ret;
+	u32 i;
 
 	netif_stop_queue(dev);
 	netif_carrier_off(dev);
@@ -1512,6 +1515,13 @@ static void rtase_sw_reset(struct net_device *dev)
 	rtase_tx_clear(tp);
 	rtase_rx_clear(tp);
 
+	for (i = 0; i < tp->int_nums; i++) {
+		ivec = &tp->int_vector[i];
+		list_for_each_entry_safe(ring, tmp, &ivec->ring_list,
+					 ring_entry)
+			list_del(&ring->ring_entry);
+	}
+
 	ret = rtase_init_ring(dev);
 	if (ret) {
 		netdev_err(dev, "unable to init ring\n");
@@ -1914,8 +1924,8 @@ static u16 rtase_calc_time_mitigation(u32 time_us)
 
 	time_us = min_t(int, time_us, RTASE_MITI_MAX_TIME);
 
-	msb = fls(time_us);
-	if (msb >= RTASE_MITI_COUNT_BIT_NUM) {
+	if (time_us > RTASE_MITI_TIME_COUNT_MASK) {
+		msb = fls(time_us);
 		time_unit = msb - RTASE_MITI_COUNT_BIT_NUM;
 		time_count = time_us >> (msb - RTASE_MITI_COUNT_BIT_NUM);
 	} else {
diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index 6f6b0566c65b..cc4f0d16c763 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -3208,10 +3208,15 @@ static int ravb_suspend(struct device *dev)
 
 	netif_device_detach(ndev);
 
-	if (priv->wol_enabled)
-		return ravb_wol_setup(ndev);
+	rtnl_lock();
+	if (priv->wol_enabled) {
+		ret = ravb_wol_setup(ndev);
+		rtnl_unlock();
+		return ret;
+	}
 
 	ret = ravb_close(ndev);
+	rtnl_unlock();
 	if (ret)
 		return ret;
 
@@ -3236,19 +3241,20 @@ static int ravb_resume(struct device *dev)
 	if (!netif_running(ndev))
 		return 0;
 
+	rtnl_lock();
 	/* If WoL is enabled restore the interface. */
-	if (priv->wol_enabled) {
+	if (priv->wol_enabled)
 		ret = ravb_wol_restore(ndev);
-		if (ret)
-			return ret;
-	} else {
+	else
 		ret = pm_runtime_force_resume(dev);
-		if (ret)
-			return ret;
+	if (ret) {
+		rtnl_unlock();
+		return ret;
 	}
 
 	/* Reopening the interface will restore the device to the working state. */
 	ret = ravb_open(ndev);
+	rtnl_unlock();
 	if (ret < 0)
 		goto out_rpm_put;
 
diff --git a/drivers/net/ethernet/renesas/rtsn.c b/drivers/net/ethernet/renesas/rtsn.c
index 6b3f7fca8d15..05c4b6c8c9c3 100644
--- a/drivers/net/ethernet/renesas/rtsn.c
+++ b/drivers/net/ethernet/renesas/rtsn.c
@@ -1259,7 +1259,12 @@ static int rtsn_probe(struct platform_device *pdev)
 	priv = netdev_priv(ndev);
 	priv->pdev = pdev;
 	priv->ndev = ndev;
+
 	priv->ptp_priv = rcar_gen4_ptp_alloc(pdev);
+	if (!priv->ptp_priv) {
+		ret = -ENOMEM;
+		goto error_free;
+	}
 
 	spin_lock_init(&priv->lock);
 	platform_set_drvdata(pdev, priv);
diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index 7a25903e35c3..bc12c0c7347f 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -3494,10 +3494,12 @@ static int sh_eth_suspend(struct device *dev)
 
 	netif_device_detach(ndev);
 
+	rtnl_lock();
 	if (mdp->wol_enabled)
 		ret = sh_eth_wol_setup(ndev);
 	else
 		ret = sh_eth_close(ndev);
+	rtnl_unlock();
 
 	return ret;
 }
@@ -3511,10 +3513,12 @@ static int sh_eth_resume(struct device *dev)
 	if (!netif_running(ndev))
 		return 0;
 
+	rtnl_lock();
 	if (mdp->wol_enabled)
 		ret = sh_eth_wol_restore(ndev);
 	else
 		ret = sh_eth_open(ndev);
+	rtnl_unlock();
 
 	if (ret < 0)
 		return ret;
diff --git a/drivers/net/ethernet/sfc/ef100_ethtool.c b/drivers/net/ethernet/sfc/ef100_ethtool.c
index 5c2551369812..6c3b74000d3b 100644
--- a/drivers/net/ethernet/sfc/ef100_ethtool.c
+++ b/drivers/net/ethernet/sfc/ef100_ethtool.c
@@ -59,6 +59,7 @@ const struct ethtool_ops ef100_ethtool_ops = {
 	.get_rxfh_indir_size	= efx_ethtool_get_rxfh_indir_size,
 	.get_rxfh_key_size	= efx_ethtool_get_rxfh_key_size,
 	.rxfh_per_ctx_key	= true,
+	.cap_rss_rxnfc_adds	= true,
 	.rxfh_priv_size		= sizeof(struct efx_rss_context_priv),
 	.get_rxfh		= efx_ethtool_get_rxfh,
 	.set_rxfh		= efx_ethtool_set_rxfh,
diff --git a/drivers/net/ethernet/sfc/ethtool.c b/drivers/net/ethernet/sfc/ethtool.c
index bb1930818beb..83d715544f7f 100644
--- a/drivers/net/ethernet/sfc/ethtool.c
+++ b/drivers/net/ethernet/sfc/ethtool.c
@@ -263,6 +263,7 @@ const struct ethtool_ops efx_ethtool_ops = {
 	.get_rxfh_indir_size	= efx_ethtool_get_rxfh_indir_size,
 	.get_rxfh_key_size	= efx_ethtool_get_rxfh_key_size,
 	.rxfh_per_ctx_key	= true,
+	.cap_rss_rxnfc_adds	= true,
 	.rxfh_priv_size		= sizeof(struct efx_rss_context_priv),
 	.get_rxfh		= efx_ethtool_get_rxfh,
 	.set_rxfh		= efx_ethtool_set_rxfh,
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
index 83ad7c7935e3..23d9ece46d9c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
@@ -379,6 +379,12 @@ static int intel_crosststamp(ktime_t *device,
 		return -ETIMEDOUT;
 	}
 
+	*system = (struct system_counterval_t) {
+		.cycles = 0,
+		.cs_id = CSID_X86_ART,
+		.use_nsecs = false,
+	};
+
 	num_snapshot = (readl(ioaddr + GMAC_TIMESTAMP_STATUS) &
 			GMAC_TIMESTAMP_ATSNS_MASK) >>
 			GMAC_TIMESTAMP_ATSNS_SHIFT;
@@ -394,7 +400,7 @@ static int intel_crosststamp(ktime_t *device,
 	}
 
 	system->cycles *= intel_priv->crossts_adj;
-	system->cs_id = CSID_X86_ART;
+
 	priv->plat->flags &= ~STMMAC_FLAG_INT_SNAPSHOT_EN;
 
 	return 0;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
index bfe6e2d631bd..702ea5a00b56 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
@@ -11,6 +11,8 @@
 #include "dwmac_dma.h"
 #include "dwmac1000.h"
 
+#define DRIVER_NAME "dwmac-loongson-pci"
+
 /* Normal Loongson Tx Summary */
 #define DMA_INTR_ENA_NIE_TX_LOONGSON	0x00040000
 /* Normal Loongson Rx Summary */
@@ -516,6 +518,19 @@ static int loongson_dwmac_acpi_config(struct pci_dev *pdev,
 	return 0;
 }
 
+/* Loongson's DWMAC device may take nearly two seconds to complete DMA reset */
+static int loongson_dwmac_fix_reset(void *priv, void __iomem *ioaddr)
+{
+	u32 value = readl(ioaddr + DMA_BUS_MODE);
+
+	value |= DMA_BUS_MODE_SFT_RESET;
+	writel(value, ioaddr + DMA_BUS_MODE);
+
+	return readl_poll_timeout(ioaddr + DMA_BUS_MODE, value,
+				  !(value & DMA_BUS_MODE_SFT_RESET),
+				  10000, 2000000);
+}
+
 static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
 	struct plat_stmmacenet_data *plat;
@@ -555,7 +570,7 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id
 	for (i = 0; i < PCI_STD_NUM_BARS; i++) {
 		if (pci_resource_len(pdev, i) == 0)
 			continue;
-		ret = pcim_iomap_regions(pdev, BIT(0), pci_name(pdev));
+		ret = pcim_iomap_regions(pdev, BIT(0), DRIVER_NAME);
 		if (ret)
 			goto err_disable_device;
 		break;
@@ -566,6 +581,7 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id
 
 	plat->bsp_priv = ld;
 	plat->setup = loongson_dwmac_setup;
+	plat->fix_soc_reset = loongson_dwmac_fix_reset;
 	ld->dev = &pdev->dev;
 	ld->loongson_id = readl(res.addr + GMAC_VERSION) & 0xff;
 
@@ -574,6 +590,9 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id
 	if (ret)
 		goto err_disable_device;
 
+	plat->tx_fifo_size = SZ_16K * plat->tx_queues_to_use;
+	plat->rx_fifo_size = SZ_16K * plat->rx_queues_to_use;
+
 	if (dev_of_node(&pdev->dev))
 		ret = loongson_dwmac_dt_config(pdev, plat, &res);
 	else
@@ -673,7 +692,7 @@ static const struct pci_device_id loongson_dwmac_id_table[] = {
 MODULE_DEVICE_TABLE(pci, loongson_dwmac_id_table);
 
 static struct pci_driver loongson_dwmac_driver = {
-	.name = "dwmac-loongson-pci",
+	.name = DRIVER_NAME,
 	.id_table = loongson_dwmac_id_table,
 	.probe = loongson_dwmac_probe,
 	.remove = loongson_dwmac_remove,
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
index 50073bdade46..8f90eae93774 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
@@ -33,6 +33,7 @@ struct rk_gmac_ops {
 	void (*set_clock_selection)(struct rk_priv_data *bsp_priv, bool input,
 				    bool enable);
 	void (*integrated_phy_powerup)(struct rk_priv_data *bsp_priv);
+	bool php_grf_required;
 	bool regs_valid;
 	u32 regs[];
 };
@@ -1263,6 +1264,7 @@ static const struct rk_gmac_ops rk3576_ops = {
 	.set_rgmii_speed = rk3576_set_gmac_speed,
 	.set_rmii_speed = rk3576_set_gmac_speed,
 	.set_clock_selection = rk3576_set_clock_selection,
+	.php_grf_required = true,
 	.regs_valid = true,
 	.regs = {
 		0x2a220000, /* gmac0 */
@@ -1410,6 +1412,7 @@ static const struct rk_gmac_ops rk3588_ops = {
 	.set_rgmii_speed = rk3588_set_gmac_speed,
 	.set_rmii_speed = rk3588_set_gmac_speed,
 	.set_clock_selection = rk3588_set_clock_selection,
+	.php_grf_required = true,
 	.regs_valid = true,
 	.regs = {
 		0xfe1b0000, /* gmac0 */
@@ -1830,8 +1833,22 @@ static struct rk_priv_data *rk_gmac_setup(struct platform_device *pdev,
 
 	bsp_priv->grf = syscon_regmap_lookup_by_phandle(dev->of_node,
 							"rockchip,grf");
-	bsp_priv->php_grf = syscon_regmap_lookup_by_phandle(dev->of_node,
-							    "rockchip,php-grf");
+	if (IS_ERR(bsp_priv->grf)) {
+		dev_err_probe(dev, PTR_ERR(bsp_priv->grf),
+			      "failed to lookup rockchip,grf\n");
+		return ERR_CAST(bsp_priv->grf);
+	}
+
+	if (ops->php_grf_required) {
+		bsp_priv->php_grf =
+			syscon_regmap_lookup_by_phandle(dev->of_node,
+							"rockchip,php-grf");
+		if (IS_ERR(bsp_priv->php_grf)) {
+			dev_err_probe(dev, PTR_ERR(bsp_priv->php_grf),
+				      "failed to lookup rockchip,php-grf\n");
+			return ERR_CAST(bsp_priv->php_grf);
+		}
+	}
 
 	if (plat->phy_node) {
 		bsp_priv->integrated_phy = of_property_read_bool(plat->phy_node,
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
index 4a0ae92b3055..ce8367b63823 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
@@ -964,7 +964,7 @@ static int sun8i_dwmac_set_syscon(struct device *dev,
 		/* of_mdio_parse_addr returns a valid (0 ~ 31) PHY
 		 * address. No need to mask it again.
 		 */
-		reg |= 1 << H3_EPHY_ADDR_SHIFT;
+		reg |= ret << H3_EPHY_ADDR_SHIFT;
 	} else {
 		/* For SoCs without internal PHY the PHY selection bit should be
 		 * set to 0 (external PHY).
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
index 7840bc403788..5dcc95bc0ad2 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
@@ -364,19 +364,17 @@ static int dwxgmac2_dma_interrupt(struct stmmac_priv *priv,
 	}
 
 	/* TX/RX NORMAL interrupts */
-	if (likely(intr_status & XGMAC_NIS)) {
-		if (likely(intr_status & XGMAC_RI)) {
-			u64_stats_update_begin(&stats->syncp);
-			u64_stats_inc(&stats->rx_normal_irq_n[chan]);
-			u64_stats_update_end(&stats->syncp);
-			ret |= handle_rx;
-		}
-		if (likely(intr_status & (XGMAC_TI | XGMAC_TBU))) {
-			u64_stats_update_begin(&stats->syncp);
-			u64_stats_inc(&stats->tx_normal_irq_n[chan]);
-			u64_stats_update_end(&stats->syncp);
-			ret |= handle_tx;
-		}
+	if (likely(intr_status & XGMAC_RI)) {
+		u64_stats_update_begin(&stats->syncp);
+		u64_stats_inc(&stats->rx_normal_irq_n[chan]);
+		u64_stats_update_end(&stats->syncp);
+		ret |= handle_rx;
+	}
+	if (likely(intr_status & (XGMAC_TI | XGMAC_TBU))) {
+		u64_stats_update_begin(&stats->syncp);
+		u64_stats_inc(&stats->tx_normal_irq_n[chan]);
+		u64_stats_update_end(&stats->syncp);
+		ret |= handle_tx;
 	}
 
 	/* Clear interrupts */
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_est.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_est.c
index c9693f77e1f6..ac6f2e3a3fcd 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_est.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_est.c
@@ -32,6 +32,11 @@ static int est_configure(struct stmmac_priv *priv, struct stmmac_est *cfg,
 	int i, ret = 0;
 	u32 ctrl;
 
+	if (!ptp_rate) {
+		netdev_warn(priv->dev, "Invalid PTP rate");
+		return -EINVAL;
+	}
+
 	ret |= est_write(est_addr, EST_BTR_LOW, cfg->btr[0], false);
 	ret |= est_write(est_addr, EST_BTR_HIGH, cfg->btr[1], false);
 	ret |= est_write(est_addr, EST_TER, cfg->ter, false);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index cf7b59b8cc64..058cd9e9fd71 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -835,6 +835,11 @@ int stmmac_init_tstamp_counter(struct stmmac_priv *priv, u32 systime_flags)
 	if (!(priv->dma_cap.time_stamp || priv->dma_cap.atime_stamp))
 		return -EOPNOTSUPP;
 
+	if (!priv->plat->clk_ptp_rate) {
+		netdev_err(priv->dev, "Invalid PTP clock rate");
+		return -EINVAL;
+	}
+
 	stmmac_config_hw_tstamping(priv, priv->ptpaddr, systime_flags);
 	priv->systime_flags = systime_flags;
 
@@ -2495,7 +2500,7 @@ static bool stmmac_xdp_xmit_zc(struct stmmac_priv *priv, u32 queue, u32 budget)
 
 	budget = min(budget, stmmac_tx_avail(priv, queue));
 
-	while (budget-- > 0) {
+	for (; budget > 0; budget--) {
 		struct stmmac_metadata_request meta_req;
 		struct xsk_tx_metadata *meta = NULL;
 		dma_addr_t dma_addr;
@@ -3598,7 +3603,6 @@ static int stmmac_request_irq_multi_msi(struct net_device *dev)
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
 	enum request_irq_err irq_err;
-	cpumask_t cpu_mask;
 	int irq_idx = 0;
 	char *int_name;
 	int ret;
@@ -3727,9 +3731,8 @@ static int stmmac_request_irq_multi_msi(struct net_device *dev)
 			irq_idx = i;
 			goto irq_error;
 		}
-		cpumask_clear(&cpu_mask);
-		cpumask_set_cpu(i % num_online_cpus(), &cpu_mask);
-		irq_set_affinity_hint(priv->rx_irq[i], &cpu_mask);
+		irq_set_affinity_hint(priv->rx_irq[i],
+				      cpumask_of(i % num_online_cpus()));
 	}
 
 	/* Request Tx MSI irq */
@@ -3752,9 +3755,8 @@ static int stmmac_request_irq_multi_msi(struct net_device *dev)
 			irq_idx = i;
 			goto irq_error;
 		}
-		cpumask_clear(&cpu_mask);
-		cpumask_set_cpu(i % num_online_cpus(), &cpu_mask);
-		irq_set_affinity_hint(priv->tx_irq[i], &cpu_mask);
+		irq_set_affinity_hint(priv->tx_irq[i],
+				      cpumask_of(i % num_online_cpus()));
 	}
 
 	return 0;
@@ -4419,8 +4421,6 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (priv->sarc_type)
 		stmmac_set_desc_sarc(priv, first, priv->sarc_type);
 
-	skb_tx_timestamp(skb);
-
 	if (unlikely((skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) &&
 		     priv->hwts_tx_en)) {
 		/* declare that device is doing timestamping */
@@ -4455,6 +4455,7 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
 	}
 
 	netdev_tx_sent_queue(netdev_get_tx_queue(dev, queue), skb->len);
+	skb_tx_timestamp(skb);
 
 	stmmac_flush_tx_descriptors(priv, queue);
 	stmmac_tx_timer_arm(priv, queue);
@@ -4698,8 +4699,6 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (priv->sarc_type)
 		stmmac_set_desc_sarc(priv, first, priv->sarc_type);
 
-	skb_tx_timestamp(skb);
-
 	/* Ready to fill the first descriptor and set the OWN bit w/o any
 	 * problems because all the descriptors are actually ready to be
 	 * passed to the DMA engine.
@@ -4746,7 +4745,7 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 	netdev_tx_sent_queue(netdev_get_tx_queue(dev, queue), skb->len);
 
 	stmmac_enable_dma_transmission(priv, priv->ioaddr, queue);
-
+	skb_tx_timestamp(skb);
 	stmmac_flush_tx_descriptors(priv, queue);
 	stmmac_tx_timer_arm(priv, queue);
 
@@ -7236,6 +7235,36 @@ static int stmmac_hw_init(struct stmmac_priv *priv)
 	if (priv->dma_cap.tsoen)
 		dev_info(priv->device, "TSO supported\n");
 
+	if (priv->dma_cap.number_rx_queues &&
+	    priv->plat->rx_queues_to_use > priv->dma_cap.number_rx_queues) {
+		dev_warn(priv->device,
+			 "Number of Rx queues (%u) exceeds dma capability\n",
+			 priv->plat->rx_queues_to_use);
+		priv->plat->rx_queues_to_use = priv->dma_cap.number_rx_queues;
+	}
+	if (priv->dma_cap.number_tx_queues &&
+	    priv->plat->tx_queues_to_use > priv->dma_cap.number_tx_queues) {
+		dev_warn(priv->device,
+			 "Number of Tx queues (%u) exceeds dma capability\n",
+			 priv->plat->tx_queues_to_use);
+		priv->plat->tx_queues_to_use = priv->dma_cap.number_tx_queues;
+	}
+
+	if (priv->dma_cap.rx_fifo_size &&
+	    priv->plat->rx_fifo_size > priv->dma_cap.rx_fifo_size) {
+		dev_warn(priv->device,
+			 "Rx FIFO size (%u) exceeds dma capability\n",
+			 priv->plat->rx_fifo_size);
+		priv->plat->rx_fifo_size = priv->dma_cap.rx_fifo_size;
+	}
+	if (priv->dma_cap.tx_fifo_size &&
+	    priv->plat->tx_fifo_size > priv->dma_cap.tx_fifo_size) {
+		dev_warn(priv->device,
+			 "Tx FIFO size (%u) exceeds dma capability\n",
+			 priv->plat->tx_fifo_size);
+		priv->plat->tx_fifo_size = priv->dma_cap.tx_fifo_size;
+	}
+
 	priv->hw->vlan_fail_q_en =
 		(priv->plat->flags & STMMAC_FLAG_VLAN_FAIL_Q_EN);
 	priv->hw->vlan_fail_q = priv->plat->vlan_fail_q;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index aaf008bdbbcd..8fd868b671a2 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -419,6 +419,7 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac)
 	struct device_node *np = pdev->dev.of_node;
 	struct plat_stmmacenet_data *plat;
 	struct stmmac_dma_cfg *dma_cfg;
+	static int bus_id = -ENODEV;
 	int phy_mode;
 	void *ret;
 	int rc;
@@ -454,8 +455,14 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac)
 	of_property_read_u32(np, "max-speed", &plat->max_speed);
 
 	plat->bus_id = of_alias_get_id(np, "ethernet");
-	if (plat->bus_id < 0)
-		plat->bus_id = 0;
+	if (plat->bus_id < 0) {
+		if (bus_id < 0)
+			bus_id = of_alias_get_highest_id("ethernet");
+		/* No ethernet alias found, init at -1 so first bus_id is 0 */
+		if (bus_id < 0)
+			bus_id = -1;
+		plat->bus_id = ++bus_id;
+	}
 
 	/* Default to phy auto-detection */
 	plat->phy_addr = -1;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c
index a6b1de9a251d..5c85040a1b93 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c
@@ -303,7 +303,7 @@ void stmmac_ptp_register(struct stmmac_priv *priv)
 
 	/* Calculate the clock domain crossing (CDC) error if necessary */
 	priv->plat->cdc_error_adj = 0;
-	if (priv->plat->has_gmac4 && priv->plat->clk_ptp_rate)
+	if (priv->plat->has_gmac4)
 		priv->plat->cdc_error_adj = (2 * NSEC_PER_SEC) / priv->plat->clk_ptp_rate;
 
 	stmmac_ptp_clock_ops.n_per_out = priv->dma_cap.pps_out_num;
diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c
index 41a27ae58ced..1e4cf89bd79a 100644
--- a/drivers/net/ethernet/sun/niu.c
+++ b/drivers/net/ethernet/sun/niu.c
@@ -3336,7 +3336,7 @@ static int niu_rbr_add_page(struct niu *np, struct rx_ring_info *rp,
 
 	addr = np->ops->map_page(np->device, page, 0,
 				 PAGE_SIZE, DMA_FROM_DEVICE);
-	if (!addr) {
+	if (np->ops->mapping_error(np->device, addr)) {
 		__free_page(page);
 		return -ENOMEM;
 	}
@@ -6672,6 +6672,8 @@ static netdev_tx_t niu_start_xmit(struct sk_buff *skb,
 	len = skb_headlen(skb);
 	mapping = np->ops->map_single(np->device, skb->data,
 				      len, DMA_TO_DEVICE);
+	if (np->ops->mapping_error(np->device, mapping))
+		goto out_drop;
 
 	prod = rp->prod;
 
@@ -6713,6 +6715,8 @@ static netdev_tx_t niu_start_xmit(struct sk_buff *skb,
 		mapping = np->ops->map_page(np->device, skb_frag_page(frag),
 					    skb_frag_off(frag), len,
 					    DMA_TO_DEVICE);
+		if (np->ops->mapping_error(np->device, mapping))
+			goto out_unmap;
 
 		rp->tx_buffs[prod].skb = NULL;
 		rp->tx_buffs[prod].mapping = mapping;
@@ -6737,6 +6741,19 @@ static netdev_tx_t niu_start_xmit(struct sk_buff *skb,
 out:
 	return NETDEV_TX_OK;
 
+out_unmap:
+	while (i--) {
+		const skb_frag_t *frag;
+
+		prod = PREVIOUS_TX(rp, prod);
+		frag = &skb_shinfo(skb)->frags[i];
+		np->ops->unmap_page(np->device, rp->tx_buffs[prod].mapping,
+				    skb_frag_size(frag), DMA_TO_DEVICE);
+	}
+
+	np->ops->unmap_single(np->device, rp->tx_buffs[rp->prod].mapping,
+			      skb_headlen(skb), DMA_TO_DEVICE);
+
 out_drop:
 	rp->tx_errors++;
 	kfree_skb(skb);
@@ -9058,6 +9075,8 @@ static void niu_try_msix(struct niu *np, u8 *ldg_num_map)
 		msi_vec[i].entry = i;
 	}
 
+	pdev->dev_flags |= PCI_DEV_FLAGS_MSIX_TOUCH_ENTRY_DATA_FIRST;
+
 	num_irqs = pci_enable_msix_range(pdev, msi_vec, 1, num_irqs);
 	if (num_irqs < 0) {
 		np->flags &= ~NIU_FLAGS_MSIX;
@@ -9636,6 +9655,11 @@ static void niu_pci_unmap_single(struct device *dev, u64 dma_address,
 	dma_unmap_single(dev, dma_address, size, direction);
 }
 
+static int niu_pci_mapping_error(struct device *dev, u64 addr)
+{
+	return dma_mapping_error(dev, addr);
+}
+
 static const struct niu_ops niu_pci_ops = {
 	.alloc_coherent	= niu_pci_alloc_coherent,
 	.free_coherent	= niu_pci_free_coherent,
@@ -9643,6 +9667,7 @@ static const struct niu_ops niu_pci_ops = {
 	.unmap_page	= niu_pci_unmap_page,
 	.map_single	= niu_pci_map_single,
 	.unmap_single	= niu_pci_unmap_single,
+	.mapping_error	= niu_pci_mapping_error,
 };
 
 static void niu_driver_version(void)
@@ -10009,6 +10034,11 @@ static void niu_phys_unmap_single(struct device *dev, u64 dma_address,
 	/* Nothing to do.  */
 }
 
+static int niu_phys_mapping_error(struct device *dev, u64 dma_address)
+{
+	return false;
+}
+
 static const struct niu_ops niu_phys_ops = {
 	.alloc_coherent	= niu_phys_alloc_coherent,
 	.free_coherent	= niu_phys_free_coherent,
@@ -10016,6 +10046,7 @@ static const struct niu_ops niu_phys_ops = {
 	.unmap_page	= niu_phys_unmap_page,
 	.map_single	= niu_phys_map_single,
 	.unmap_single	= niu_phys_unmap_single,
+	.mapping_error	= niu_phys_mapping_error,
 };
 
 static int niu_of_probe(struct platform_device *op)
diff --git a/drivers/net/ethernet/sun/niu.h b/drivers/net/ethernet/sun/niu.h
index 04c215f91fc0..0b169c08b0f2 100644
--- a/drivers/net/ethernet/sun/niu.h
+++ b/drivers/net/ethernet/sun/niu.h
@@ -2879,6 +2879,9 @@ struct tx_ring_info {
 #define NEXT_TX(tp, index) \
 	(((index) + 1) < (tp)->pending ? ((index) + 1) : 0)
 
+#define PREVIOUS_TX(tp, index) \
+	(((index) - 1) >= 0 ? ((index) - 1) : (((tp)->pending) - 1))
+
 static inline u32 niu_tx_avail(struct tx_ring_info *tp)
 {
 	return (tp->pending -
@@ -3140,6 +3143,7 @@ struct niu_ops {
 			  enum dma_data_direction direction);
 	void (*unmap_single)(struct device *dev, u64 dma_address,
 			     size_t size, enum dma_data_direction direction);
+	int (*mapping_error)(struct device *dev, u64 dma_address);
 };
 
 struct niu_link_config {
diff --git a/drivers/net/ethernet/tehuti/tn40.c b/drivers/net/ethernet/tehuti/tn40.c
index 259bdac24cf2..558b791a97ed 100644
--- a/drivers/net/ethernet/tehuti/tn40.c
+++ b/drivers/net/ethernet/tehuti/tn40.c
@@ -1778,7 +1778,7 @@ static int tn40_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	ret = tn40_phy_register(priv);
 	if (ret) {
 		dev_err(&pdev->dev, "failed to set up PHY.\n");
-		goto err_free_irq;
+		goto err_cleanup_swnodes;
 	}
 
 	ret = tn40_priv_init(priv);
@@ -1795,6 +1795,8 @@ static int tn40_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	return 0;
 err_unregister_phydev:
 	tn40_phy_unregister(priv);
+err_cleanup_swnodes:
+	tn40_swnodes_cleanup(priv);
 err_free_irq:
 	pci_free_irq_vectors(pdev);
 err_unset_drvdata:
@@ -1816,6 +1818,7 @@ static void tn40_remove(struct pci_dev *pdev)
 	unregister_netdev(ndev);
 
 	tn40_phy_unregister(priv);
+	tn40_swnodes_cleanup(priv);
 	pci_free_irq_vectors(priv->pdev);
 	pci_set_drvdata(pdev, NULL);
 	iounmap(priv->regs);
@@ -1832,6 +1835,10 @@ static const struct pci_device_id tn40_id_table[] = {
 			 PCI_VENDOR_ID_ASUSTEK, 0x8709) },
 	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_TEHUTI, 0x4022,
 			 PCI_VENDOR_ID_EDIMAX, 0x8103) },
+	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_TEHUTI, PCI_DEVICE_ID_TEHUTI_TN9510,
+			 PCI_VENDOR_ID_TEHUTI, 0x3015) },
+	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_TEHUTI, PCI_DEVICE_ID_TEHUTI_TN9510,
+			 PCI_VENDOR_ID_EDIMAX, 0x8102) },
 	{ }
 };
 
diff --git a/drivers/net/ethernet/tehuti/tn40.h b/drivers/net/ethernet/tehuti/tn40.h
index 490781fe5120..25da8686d469 100644
--- a/drivers/net/ethernet/tehuti/tn40.h
+++ b/drivers/net/ethernet/tehuti/tn40.h
@@ -4,10 +4,13 @@
 #ifndef _TN40_H_
 #define _TN40_H_
 
+#include <linux/property.h>
 #include "tn40_regs.h"
 
 #define TN40_DRV_NAME "tn40xx"
 
+#define PCI_DEVICE_ID_TEHUTI_TN9510	0x4025
+
 #define TN40_MDIO_SPEED_1MHZ (1)
 #define TN40_MDIO_SPEED_6MHZ (6)
 
@@ -102,10 +105,39 @@ struct tn40_txdb {
 	int size; /* Number of elements in the db */
 };
 
+#define NODE_PROP(_NAME, _PROP)	(		\
+	(const struct software_node) {		\
+		.name = _NAME,			\
+		.properties = _PROP,		\
+	})
+
+#define NODE_PAR_PROP(_NAME, _PAR, _PROP)	(	\
+	(const struct software_node) {		\
+		.name = _NAME,			\
+		.parent = _PAR,			\
+		.properties = _PROP,		\
+	})
+
+enum tn40_swnodes {
+	SWNODE_MDIO,
+	SWNODE_PHY,
+	SWNODE_MAX
+};
+
+struct tn40_nodes {
+	char phy_name[32];
+	char mdio_name[32];
+	struct property_entry phy_props[3];
+	struct software_node swnodes[SWNODE_MAX];
+	const struct software_node *group[SWNODE_MAX + 1];
+};
+
 struct tn40_priv {
 	struct net_device *ndev;
 	struct pci_dev *pdev;
 
+	struct tn40_nodes nodes;
+
 	struct napi_struct napi;
 	/* RX FIFOs: 1 for data (full) descs, and 2 for free descs */
 	struct tn40_rxd_fifo rxd_fifo0;
@@ -225,6 +257,7 @@ static inline void tn40_write_reg(struct tn40_priv *priv, u32 reg, u32 val)
 
 int tn40_set_link_speed(struct tn40_priv *priv, u32 speed);
 
+void tn40_swnodes_cleanup(struct tn40_priv *priv);
 int tn40_mdiobus_init(struct tn40_priv *priv);
 
 int tn40_phy_register(struct tn40_priv *priv);
diff --git a/drivers/net/ethernet/tehuti/tn40_mdio.c b/drivers/net/ethernet/tehuti/tn40_mdio.c
index af18615d64a8..5bb0cbc87d06 100644
--- a/drivers/net/ethernet/tehuti/tn40_mdio.c
+++ b/drivers/net/ethernet/tehuti/tn40_mdio.c
@@ -14,6 +14,8 @@
 	 (FIELD_PREP(TN40_MDIO_PRTAD_MASK, (port))))
 #define TN40_MDIO_CMD_READ BIT(15)
 
+#define AQR105_FIRMWARE "tehuti/aqr105-tn40xx.cld"
+
 static void tn40_mdio_set_speed(struct tn40_priv *priv, u32 speed)
 {
 	void __iomem *regs = priv->regs;
@@ -111,6 +113,56 @@ static int tn40_mdio_write_c45(struct mii_bus *mii_bus, int addr, int devnum,
 	return  tn40_mdio_write(mii_bus->priv, addr, devnum, regnum, val);
 }
 
+/* registers an mdio node and an aqr105 PHY at address 1
+ * tn40_mdio-%id {
+ *	ethernet-phy@1 {
+ *		compatible = "ethernet-phy-id03a1.b4a3";
+ *		reg = <1>;
+ *		firmware-name = AQR105_FIRMWARE;
+ *	};
+ * };
+ */
+static int tn40_swnodes_register(struct tn40_priv *priv)
+{
+	struct tn40_nodes *nodes = &priv->nodes;
+	struct pci_dev *pdev = priv->pdev;
+	struct software_node *swnodes;
+	u32 id;
+
+	id = pci_dev_id(pdev);
+
+	snprintf(nodes->phy_name, sizeof(nodes->phy_name), "ethernet-phy@1");
+	snprintf(nodes->mdio_name, sizeof(nodes->mdio_name), "tn40_mdio-%x",
+		 id);
+
+	swnodes = nodes->swnodes;
+
+	swnodes[SWNODE_MDIO] = NODE_PROP(nodes->mdio_name, NULL);
+
+	nodes->phy_props[0] = PROPERTY_ENTRY_STRING("compatible",
+						    "ethernet-phy-id03a1.b4a3");
+	nodes->phy_props[1] = PROPERTY_ENTRY_U32("reg", 1);
+	nodes->phy_props[2] = PROPERTY_ENTRY_STRING("firmware-name",
+						    AQR105_FIRMWARE);
+	swnodes[SWNODE_PHY] = NODE_PAR_PROP(nodes->phy_name,
+					    &swnodes[SWNODE_MDIO],
+					    nodes->phy_props);
+
+	nodes->group[SWNODE_PHY] = &swnodes[SWNODE_PHY];
+	nodes->group[SWNODE_MDIO] = &swnodes[SWNODE_MDIO];
+	return software_node_register_node_group(nodes->group);
+}
+
+void tn40_swnodes_cleanup(struct tn40_priv *priv)
+{
+	/* cleanup of swnodes is only needed for AQR105-based cards */
+	if (priv->pdev->device == PCI_DEVICE_ID_TEHUTI_TN9510) {
+		fwnode_handle_put(dev_fwnode(&priv->mdio->dev));
+		device_remove_software_node(&priv->mdio->dev);
+		software_node_unregister_node_group(priv->nodes.group);
+	}
+}
+
 int tn40_mdiobus_init(struct tn40_priv *priv)
 {
 	struct pci_dev *pdev = priv->pdev;
@@ -129,14 +181,40 @@ int tn40_mdiobus_init(struct tn40_priv *priv)
 
 	bus->read_c45 = tn40_mdio_read_c45;
 	bus->write_c45 = tn40_mdio_write_c45;
+	priv->mdio = bus;
+
+	/* provide swnodes for AQR105-based cards only */
+	if (pdev->device == PCI_DEVICE_ID_TEHUTI_TN9510) {
+		ret = tn40_swnodes_register(priv);
+		if (ret) {
+			pr_err("swnodes failed\n");
+			return ret;
+		}
+
+		ret = device_add_software_node(&bus->dev,
+					       priv->nodes.group[SWNODE_MDIO]);
+		if (ret) {
+			dev_err(&pdev->dev,
+				"device_add_software_node failed: %d\n", ret);
+			goto err_swnodes_unregister;
+		}
+	}
 
 	ret = devm_mdiobus_register(&pdev->dev, bus);
 	if (ret) {
 		dev_err(&pdev->dev, "failed to register mdiobus %d %u %u\n",
 			ret, bus->state, MDIOBUS_UNREGISTERED);
-		return ret;
+		goto err_swnodes_cleanup;
 	}
 	tn40_mdio_set_speed(priv, TN40_MDIO_SPEED_6MHZ);
-	priv->mdio = bus;
 	return 0;
+
+err_swnodes_unregister:
+	software_node_unregister_node_group(priv->nodes.group);
+	return ret;
+err_swnodes_cleanup:
+	tn40_swnodes_cleanup(priv);
+	return ret;
 }
+
+MODULE_FIRMWARE(AQR105_FIRMWARE);
diff --git a/drivers/net/ethernet/ti/Kconfig b/drivers/net/ethernet/ti/Kconfig
index 0d5a862cd78a..3a13d60a947a 100644
--- a/drivers/net/ethernet/ti/Kconfig
+++ b/drivers/net/ethernet/ti/Kconfig
@@ -99,6 +99,7 @@ config TI_K3_AM65_CPSW_NUSS
 	select NET_DEVLINK
 	select TI_DAVINCI_MDIO
 	select PHYLINK
+	select PAGE_POOL
 	select TI_K3_CPPI_DESC_POOL
 	imply PHY_TI_GMII_SEL
 	depends on TI_K3_AM65_CPTS || !TI_K3_AM65_CPTS
diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
index dfca13b82bdc..6b5cff087686 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c
+++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
@@ -585,31 +585,38 @@ static void am65_cpsw_nuss_xmit_free(struct am65_cpsw_tx_chn *tx_chn,
 static void am65_cpsw_nuss_tx_cleanup(void *data, dma_addr_t desc_dma)
 {
 	struct am65_cpsw_tx_chn *tx_chn = data;
+	enum am65_cpsw_tx_buf_type buf_type;
 	struct cppi5_host_desc_t *desc_tx;
+	struct xdp_frame *xdpf;
 	struct sk_buff *skb;
 	void **swdata;
 
 	desc_tx = k3_cppi_desc_pool_dma2virt(tx_chn->desc_pool, desc_dma);
 	swdata = cppi5_hdesc_get_swdata(desc_tx);
-	skb = *(swdata);
-	am65_cpsw_nuss_xmit_free(tx_chn, desc_tx);
+	buf_type = am65_cpsw_nuss_buf_type(tx_chn, desc_dma);
+	if (buf_type == AM65_CPSW_TX_BUF_TYPE_SKB) {
+		skb = *(swdata);
+		dev_kfree_skb_any(skb);
+	} else {
+		xdpf = *(swdata);
+		xdp_return_frame(xdpf);
+	}
 
-	dev_kfree_skb_any(skb);
+	am65_cpsw_nuss_xmit_free(tx_chn, desc_tx);
 }
 
 static struct sk_buff *am65_cpsw_build_skb(void *page_addr,
 					   struct net_device *ndev,
-					   unsigned int len)
+					   unsigned int len,
+					   unsigned int headroom)
 {
 	struct sk_buff *skb;
 
-	len += AM65_CPSW_HEADROOM;
-
 	skb = build_skb(page_addr, len);
 	if (unlikely(!skb))
 		return NULL;
 
-	skb_reserve(skb, AM65_CPSW_HEADROOM);
+	skb_reserve(skb, headroom);
 	skb->dev = ndev;
 
 	return skb;
@@ -1191,16 +1198,8 @@ static int am65_cpsw_nuss_rx_packets(struct am65_cpsw_rx_flow *flow,
 	dev_dbg(dev, "%s rx csum_info:%#x\n", __func__, csum_info);
 
 	dma_unmap_single(rx_chn->dma_dev, buf_dma, buf_dma_len, DMA_FROM_DEVICE);
-
 	k3_cppi_desc_pool_free(rx_chn->desc_pool, desc_rx);
 
-	skb = am65_cpsw_build_skb(page_addr, ndev,
-				  AM65_CPSW_MAX_PACKET_SIZE);
-	if (unlikely(!skb)) {
-		new_page = page;
-		goto requeue;
-	}
-
 	if (port->xdp_prog) {
 		xdp_init_buff(&xdp, PAGE_SIZE, &port->xdp_rxq[flow->id]);
 		xdp_prepare_buff(&xdp, page_addr, AM65_CPSW_HEADROOM,
@@ -1210,9 +1209,16 @@ static int am65_cpsw_nuss_rx_packets(struct am65_cpsw_rx_flow *flow,
 		if (*xdp_state != AM65_CPSW_XDP_PASS)
 			goto allocate;
 
-		/* Compute additional headroom to be reserved */
-		headroom = (xdp.data - xdp.data_hard_start) - skb_headroom(skb);
-		skb_reserve(skb, headroom);
+		headroom = xdp.data - xdp.data_hard_start;
+	} else {
+		headroom = AM65_CPSW_HEADROOM;
+	}
+
+	skb = am65_cpsw_build_skb(page_addr, ndev,
+				  PAGE_SIZE, headroom);
+	if (unlikely(!skb)) {
+		new_page = page;
+		goto requeue;
 	}
 
 	ndev_priv = netdev_priv(ndev);
@@ -2201,13 +2207,11 @@ static void am65_cpsw_nuss_remove_tx_chns(struct am65_cpsw_common *common)
 	struct device *dev = common->dev;
 	int i;
 
-	devm_remove_action(dev, am65_cpsw_nuss_free_tx_chns, common);
-
 	common->tx_ch_rate_msk = 0;
 	for (i = 0; i < common->tx_ch_num; i++) {
 		struct am65_cpsw_tx_chn *tx_chn = &common->tx_chns[i];
 
-		if (tx_chn->irq)
+		if (tx_chn->irq > 0)
 			devm_free_irq(dev, tx_chn->irq, tx_chn);
 
 		netif_napi_del(&tx_chn->napi_tx);
@@ -2219,16 +2223,18 @@ static void am65_cpsw_nuss_remove_tx_chns(struct am65_cpsw_common *common)
 static int am65_cpsw_nuss_ndev_add_tx_napi(struct am65_cpsw_common *common)
 {
 	struct device *dev = common->dev;
+	struct am65_cpsw_tx_chn *tx_chn;
 	int i, ret = 0;
 
 	for (i = 0; i < common->tx_ch_num; i++) {
-		struct am65_cpsw_tx_chn *tx_chn = &common->tx_chns[i];
+		tx_chn = &common->tx_chns[i];
 
-		netif_napi_add_tx(common->dma_ndev, &tx_chn->napi_tx,
-				  am65_cpsw_nuss_tx_poll);
 		hrtimer_init(&tx_chn->tx_hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED);
 		tx_chn->tx_hrtimer.function = &am65_cpsw_nuss_tx_timer_callback;
 
+		netif_napi_add_tx(common->dma_ndev, &tx_chn->napi_tx,
+				  am65_cpsw_nuss_tx_poll);
+
 		ret = devm_request_irq(dev, tx_chn->irq,
 				       am65_cpsw_nuss_tx_irq,
 				       IRQF_TRIGGER_HIGH,
@@ -2240,7 +2246,16 @@ static int am65_cpsw_nuss_ndev_add_tx_napi(struct am65_cpsw_common *common)
 		}
 	}
 
+	return 0;
+
 err:
+	netif_napi_del(&tx_chn->napi_tx);
+	for (--i; i >= 0; i--) {
+		tx_chn = &common->tx_chns[i];
+		devm_free_irq(dev, tx_chn->irq, tx_chn);
+		netif_napi_del(&tx_chn->napi_tx);
+	}
+
 	return ret;
 }
 
@@ -2321,12 +2336,10 @@ static int am65_cpsw_nuss_init_tx_chns(struct am65_cpsw_common *common)
 		goto err;
 	}
 
+	return 0;
+
 err:
-	i = devm_add_action(dev, am65_cpsw_nuss_free_tx_chns, common);
-	if (i) {
-		dev_err(dev, "Failed to add free_tx_chns action %d\n", i);
-		return i;
-	}
+	am65_cpsw_nuss_free_tx_chns(common);
 
 	return ret;
 }
@@ -2354,7 +2367,6 @@ static void am65_cpsw_nuss_remove_rx_chns(struct am65_cpsw_common *common)
 
 	rx_chn = &common->rx_chns;
 	flows = rx_chn->flows;
-	devm_remove_action(dev, am65_cpsw_nuss_free_rx_chns, common);
 
 	for (i = 0; i < common->rx_ch_num_flows; i++) {
 		if (!(flows[i].irq < 0))
@@ -2453,7 +2465,7 @@ static int am65_cpsw_nuss_init_rx_chns(struct am65_cpsw_common *common)
 						i, &rx_flow_cfg);
 		if (ret) {
 			dev_err(dev, "Failed to init rx flow%d %d\n", i, ret);
-			goto err;
+			goto err_flow;
 		}
 		if (!i)
 			fdqring_id =
@@ -2465,18 +2477,19 @@ static int am65_cpsw_nuss_init_rx_chns(struct am65_cpsw_common *common)
 			dev_err(dev, "Failed to get rx dma irq %d\n",
 				flow->irq);
 			ret = flow->irq;
-			goto err;
+			goto err_flow;
 		}
 
 		snprintf(flow->name,
 			 sizeof(flow->name), "%s-rx%d",
 			 dev_name(dev), i);
-		netif_napi_add(common->dma_ndev, &flow->napi_rx,
-			       am65_cpsw_nuss_rx_poll);
 		hrtimer_init(&flow->rx_hrtimer, CLOCK_MONOTONIC,
 			     HRTIMER_MODE_REL_PINNED);
 		flow->rx_hrtimer.function = &am65_cpsw_nuss_rx_timer_callback;
 
+		netif_napi_add(common->dma_ndev, &flow->napi_rx,
+			       am65_cpsw_nuss_rx_poll);
+
 		ret = devm_request_irq(dev, flow->irq,
 				       am65_cpsw_nuss_rx_irq,
 				       IRQF_TRIGGER_HIGH,
@@ -2485,20 +2498,28 @@ static int am65_cpsw_nuss_init_rx_chns(struct am65_cpsw_common *common)
 			dev_err(dev, "failure requesting rx %d irq %u, %d\n",
 				i, flow->irq, ret);
 			flow->irq = -EINVAL;
-			goto err;
+			goto err_request_irq;
 		}
 	}
 
 	/* setup classifier to route priorities to flows */
 	cpsw_ale_classifier_setup_default(common->ale, common->rx_ch_num_flows);
 
-err:
-	i = devm_add_action(dev, am65_cpsw_nuss_free_rx_chns, common);
-	if (i) {
-		dev_err(dev, "Failed to add free_rx_chns action %d\n", i);
-		return i;
+	return 0;
+
+err_request_irq:
+	netif_napi_del(&flow->napi_rx);
+
+err_flow:
+	for (--i; i >= 0; i--) {
+		flow = &rx_chn->flows[i];
+		devm_free_irq(dev, flow->irq, flow);
+		netif_napi_del(&flow->napi_rx);
 	}
 
+err:
+	am65_cpsw_nuss_free_rx_chns(common);
+
 	return ret;
 }
 
@@ -2657,7 +2678,7 @@ static int am65_cpsw_nuss_init_slave_ports(struct am65_cpsw_common *common)
 				of_property_read_bool(port_np, "ti,mac-only");
 
 		/* get phy/link info */
-		port->slave.port_np = port_np;
+		port->slave.port_np = of_node_get(port_np);
 		ret = of_get_phy_mode(port_np, &port->slave.phy_if);
 		if (ret) {
 			dev_err(dev, "%pOF read phy-mode err %d\n",
@@ -2670,13 +2691,15 @@ static int am65_cpsw_nuss_init_slave_ports(struct am65_cpsw_common *common)
 			goto of_node_put;
 
 		ret = of_get_mac_address(port_np, port->slave.mac_addr);
-		if (ret) {
+		if (ret == -EPROBE_DEFER) {
+			goto of_node_put;
+		} else if (ret) {
 			am65_cpsw_am654_get_efuse_macid(port_np,
 							port->port_id,
 							port->slave.mac_addr);
 			if (!is_valid_ether_addr(port->slave.mac_addr)) {
 				eth_random_addr(port->slave.mac_addr);
-				dev_err(dev, "Use random MAC address\n");
+				dev_info(dev, "Use random MAC address\n");
 			}
 		}
 
@@ -2718,6 +2741,17 @@ static void am65_cpsw_nuss_phylink_cleanup(struct am65_cpsw_common *common)
 	}
 }
 
+static void am65_cpsw_remove_dt(struct am65_cpsw_common *common)
+{
+	struct am65_cpsw_port *port;
+	int i;
+
+	for (i = 0; i < common->port_num; i++) {
+		port = &common->ports[i];
+		of_node_put(port->slave.port_np);
+	}
+}
+
 static int
 am65_cpsw_nuss_init_port_ndev(struct am65_cpsw_common *common, u32 port_idx)
 {
@@ -3324,7 +3358,7 @@ static int am65_cpsw_nuss_register_ndevs(struct am65_cpsw_common *common)
 		return ret;
 	ret = am65_cpsw_nuss_init_rx_chns(common);
 	if (ret)
-		return ret;
+		goto err_remove_tx;
 
 	/* The DMA Channels are not guaranteed to be in a clean state.
 	 * Reset and disable them to ensure that they are back to the
@@ -3345,7 +3379,7 @@ static int am65_cpsw_nuss_register_ndevs(struct am65_cpsw_common *common)
 
 	ret = am65_cpsw_nuss_register_devlink(common);
 	if (ret)
-		return ret;
+		goto err_remove_rx;
 
 	for (i = 0; i < common->port_num; i++) {
 		port = &common->ports[i];
@@ -3376,6 +3410,10 @@ static int am65_cpsw_nuss_register_ndevs(struct am65_cpsw_common *common)
 err_cleanup_ndev:
 	am65_cpsw_nuss_cleanup_ndev(common);
 	am65_cpsw_unregister_devlink(common);
+err_remove_rx:
+	am65_cpsw_nuss_remove_rx_chns(common);
+err_remove_tx:
+	am65_cpsw_nuss_remove_tx_chns(common);
 
 	return ret;
 }
@@ -3395,6 +3433,8 @@ int am65_cpsw_nuss_update_tx_rx_chns(struct am65_cpsw_common *common,
 		return ret;
 
 	ret = am65_cpsw_nuss_init_rx_chns(common);
+	if (ret)
+		am65_cpsw_nuss_remove_tx_chns(common);
 
 	return ret;
 }
@@ -3546,6 +3586,16 @@ static int am65_cpsw_nuss_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	am65_cpsw_nuss_get_ver(common);
+
+	ret = am65_cpsw_nuss_init_host_p(common);
+	if (ret)
+		goto err_pm_clear;
+
+	ret = am65_cpsw_nuss_init_slave_ports(common);
+	if (ret)
+		goto err_pm_clear;
+
 	node = of_get_child_by_name(dev->of_node, "mdio");
 	if (!node) {
 		dev_warn(dev, "MDIO node not found\n");
@@ -3562,16 +3612,6 @@ static int am65_cpsw_nuss_probe(struct platform_device *pdev)
 	}
 	of_node_put(node);
 
-	am65_cpsw_nuss_get_ver(common);
-
-	ret = am65_cpsw_nuss_init_host_p(common);
-	if (ret)
-		goto err_of_clear;
-
-	ret = am65_cpsw_nuss_init_slave_ports(common);
-	if (ret)
-		goto err_of_clear;
-
 	/* init common data */
 	ale_params.dev = dev;
 	ale_params.ale_ageout = AM65_CPSW_ALE_AGEOUT_DEFAULT;
@@ -3618,6 +3658,7 @@ err_ndevs_clear:
 	am65_cpsw_nuss_cleanup_ndev(common);
 	am65_cpsw_nuss_phylink_cleanup(common);
 	am65_cpts_release(common->cpts);
+	am65_cpsw_remove_dt(common);
 err_of_clear:
 	if (common->mdio_dev)
 		of_platform_device_destroy(common->mdio_dev, NULL);
@@ -3652,9 +3693,12 @@ static void am65_cpsw_nuss_remove(struct platform_device *pdev)
 	 */
 	am65_cpsw_nuss_cleanup_ndev(common);
 	am65_cpsw_unregister_devlink(common);
+	am65_cpsw_nuss_remove_rx_chns(common);
+	am65_cpsw_nuss_remove_tx_chns(common);
 	am65_cpsw_nuss_phylink_cleanup(common);
 	am65_cpts_release(common->cpts);
 	am65_cpsw_disable_serdes_phy(common);
+	am65_cpsw_remove_dt(common);
 
 	if (common->mdio_dev)
 		of_platform_device_destroy(common->mdio_dev, NULL);
@@ -3713,8 +3757,10 @@ static int am65_cpsw_nuss_resume(struct device *dev)
 	if (ret)
 		return ret;
 	ret = am65_cpsw_nuss_init_rx_chns(common);
-	if (ret)
+	if (ret) {
+		am65_cpsw_nuss_remove_tx_chns(common);
 		return ret;
+	}
 
 	/* If RX IRQ was disabled before suspend, keep it disabled */
 	for (i = 0; i < common->rx_ch_num_flows; i++) {
diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c
index 557cc71b9dd2..0eee1a0527b5 100644
--- a/drivers/net/ethernet/ti/cpsw_new.c
+++ b/drivers/net/ethernet/ti/cpsw_new.c
@@ -1417,6 +1417,7 @@ static int cpsw_create_ports(struct cpsw_common *cpsw)
 		ndev->netdev_ops = &cpsw_netdev_ops;
 		ndev->ethtool_ops = &cpsw_ethtool_ops;
 		SET_NETDEV_DEV(ndev, dev);
+		ndev->dev.of_node = slave_data->slave_node;
 
 		if (!napi_ndev) {
 			/* CPSW Host port CPDMA interface is shared between
diff --git a/drivers/net/ethernet/ti/icssg/icss_iep.c b/drivers/net/ethernet/ti/icssg/icss_iep.c
index 768578c0d958..d8c9fe1d98c4 100644
--- a/drivers/net/ethernet/ti/icssg/icss_iep.c
+++ b/drivers/net/ethernet/ti/icssg/icss_iep.c
@@ -406,66 +406,79 @@ static void icss_iep_update_to_next_boundary(struct icss_iep *iep, u64 start_ns)
 static int icss_iep_perout_enable_hw(struct icss_iep *iep,
 				     struct ptp_perout_request *req, int on)
 {
+	struct timespec64 ts;
+	u64 ns_start;
+	u64 ns_width;
 	int ret;
 	u64 cmp;
 
+	if (!on) {
+		/* Disable CMP 1 */
+		regmap_update_bits(iep->map, ICSS_IEP_CMP_CFG_REG,
+				   IEP_CMP_CFG_CMP_EN(1), 0);
+
+		/* clear CMP regs */
+		regmap_write(iep->map, ICSS_IEP_CMP1_REG0, 0);
+		if (iep->plat_data->flags & ICSS_IEP_64BIT_COUNTER_SUPPORT)
+			regmap_write(iep->map, ICSS_IEP_CMP1_REG1, 0);
+
+		/* Disable sync */
+		regmap_write(iep->map, ICSS_IEP_SYNC_CTRL_REG, 0);
+
+		return 0;
+	}
+
+	/* Calculate width of the signal for PPS/PEROUT handling */
+	ts.tv_sec = req->on.sec;
+	ts.tv_nsec = req->on.nsec;
+	ns_width = timespec64_to_ns(&ts);
+
+	if (req->flags & PTP_PEROUT_PHASE) {
+		ts.tv_sec = req->phase.sec;
+		ts.tv_nsec = req->phase.nsec;
+		ns_start = timespec64_to_ns(&ts);
+	} else {
+		ns_start = 0;
+	}
+
 	if (iep->ops && iep->ops->perout_enable) {
 		ret = iep->ops->perout_enable(iep->clockops_data, req, on, &cmp);
 		if (ret)
 			return ret;
 
-		if (on) {
-			/* Configure CMP */
-			regmap_write(iep->map, ICSS_IEP_CMP1_REG0, lower_32_bits(cmp));
-			if (iep->plat_data->flags & ICSS_IEP_64BIT_COUNTER_SUPPORT)
-				regmap_write(iep->map, ICSS_IEP_CMP1_REG1, upper_32_bits(cmp));
-			/* Configure SYNC, 1ms pulse width */
-			regmap_write(iep->map, ICSS_IEP_SYNC_PWIDTH_REG, 1000000);
-			regmap_write(iep->map, ICSS_IEP_SYNC0_PERIOD_REG, 0);
-			regmap_write(iep->map, ICSS_IEP_SYNC_START_REG, 0);
-			regmap_write(iep->map, ICSS_IEP_SYNC_CTRL_REG, 0); /* one-shot mode */
-			/* Enable CMP 1 */
-			regmap_update_bits(iep->map, ICSS_IEP_CMP_CFG_REG,
-					   IEP_CMP_CFG_CMP_EN(1), IEP_CMP_CFG_CMP_EN(1));
-		} else {
-			/* Disable CMP 1 */
-			regmap_update_bits(iep->map, ICSS_IEP_CMP_CFG_REG,
-					   IEP_CMP_CFG_CMP_EN(1), 0);
-
-			/* clear regs */
-			regmap_write(iep->map, ICSS_IEP_CMP1_REG0, 0);
-			if (iep->plat_data->flags & ICSS_IEP_64BIT_COUNTER_SUPPORT)
-				regmap_write(iep->map, ICSS_IEP_CMP1_REG1, 0);
-		}
+		/* Configure CMP */
+		regmap_write(iep->map, ICSS_IEP_CMP1_REG0, lower_32_bits(cmp));
+		if (iep->plat_data->flags & ICSS_IEP_64BIT_COUNTER_SUPPORT)
+			regmap_write(iep->map, ICSS_IEP_CMP1_REG1, upper_32_bits(cmp));
+		/* Configure SYNC, based on req on width */
+		regmap_write(iep->map, ICSS_IEP_SYNC_PWIDTH_REG,
+			     div_u64(ns_width, iep->def_inc));
+		regmap_write(iep->map, ICSS_IEP_SYNC0_PERIOD_REG, 0);
+		regmap_write(iep->map, ICSS_IEP_SYNC_START_REG,
+			     div_u64(ns_start, iep->def_inc));
+		regmap_write(iep->map, ICSS_IEP_SYNC_CTRL_REG, 0); /* one-shot mode */
+		/* Enable CMP 1 */
+		regmap_update_bits(iep->map, ICSS_IEP_CMP_CFG_REG,
+				   IEP_CMP_CFG_CMP_EN(1), IEP_CMP_CFG_CMP_EN(1));
 	} else {
-		if (on) {
-			u64 start_ns;
-
-			iep->period = ((u64)req->period.sec * NSEC_PER_SEC) +
-				      req->period.nsec;
-			start_ns = ((u64)req->period.sec * NSEC_PER_SEC)
-				   + req->period.nsec;
-			icss_iep_update_to_next_boundary(iep, start_ns);
-
-			/* Enable Sync in single shot mode  */
-			regmap_write(iep->map, ICSS_IEP_SYNC_CTRL_REG,
-				     IEP_SYNC_CTRL_SYNC_N_EN(0) | IEP_SYNC_CTRL_SYNC_EN);
-			/* Enable CMP 1 */
-			regmap_update_bits(iep->map, ICSS_IEP_CMP_CFG_REG,
-					   IEP_CMP_CFG_CMP_EN(1), IEP_CMP_CFG_CMP_EN(1));
-		} else {
-			/* Disable CMP 1 */
-			regmap_update_bits(iep->map, ICSS_IEP_CMP_CFG_REG,
-					   IEP_CMP_CFG_CMP_EN(1), 0);
-
-			/* clear CMP regs */
-			regmap_write(iep->map, ICSS_IEP_CMP1_REG0, 0);
-			if (iep->plat_data->flags & ICSS_IEP_64BIT_COUNTER_SUPPORT)
-				regmap_write(iep->map, ICSS_IEP_CMP1_REG1, 0);
-
-			/* Disable sync */
-			regmap_write(iep->map, ICSS_IEP_SYNC_CTRL_REG, 0);
-		}
+		u64 start_ns;
+
+		iep->period = ((u64)req->period.sec * NSEC_PER_SEC) +
+				req->period.nsec;
+		start_ns = ((u64)req->period.sec * NSEC_PER_SEC)
+				+ req->period.nsec;
+		icss_iep_update_to_next_boundary(iep, start_ns);
+
+		regmap_write(iep->map, ICSS_IEP_SYNC_PWIDTH_REG,
+			     div_u64(ns_width, iep->def_inc));
+		regmap_write(iep->map, ICSS_IEP_SYNC_START_REG,
+			     div_u64(ns_start, iep->def_inc));
+		/* Enable Sync in single shot mode  */
+		regmap_write(iep->map, ICSS_IEP_SYNC_CTRL_REG,
+			     IEP_SYNC_CTRL_SYNC_N_EN(0) | IEP_SYNC_CTRL_SYNC_EN);
+		/* Enable CMP 1 */
+		regmap_update_bits(iep->map, ICSS_IEP_CMP_CFG_REG,
+				   IEP_CMP_CFG_CMP_EN(1), IEP_CMP_CFG_CMP_EN(1));
 	}
 
 	return 0;
@@ -476,6 +489,21 @@ static int icss_iep_perout_enable(struct icss_iep *iep,
 {
 	int ret = 0;
 
+	if (!on)
+		goto disable;
+
+	/* Reject requests with unsupported flags */
+	if (req->flags & ~(PTP_PEROUT_DUTY_CYCLE |
+			  PTP_PEROUT_PHASE))
+		return -EOPNOTSUPP;
+
+	/* Set default "on" time (1ms) for the signal if not passed by the app */
+	if (!(req->flags & PTP_PEROUT_DUTY_CYCLE)) {
+		req->on.sec = 0;
+		req->on.nsec = NSEC_PER_MSEC;
+	}
+
+disable:
 	mutex_lock(&iep->ptp_clk_mutex);
 
 	if (iep->pps_enabled) {
@@ -568,10 +596,13 @@ static int icss_iep_pps_enable(struct icss_iep *iep, int on)
 	if (on) {
 		ns = icss_iep_gettime(iep, NULL);
 		ts = ns_to_timespec64(ns);
+		rq.perout.flags = 0;
 		rq.perout.period.sec = 1;
 		rq.perout.period.nsec = 0;
 		rq.perout.start.sec = ts.tv_sec + 2;
 		rq.perout.start.nsec = 0;
+		rq.perout.on.sec = 0;
+		rq.perout.on.nsec = NSEC_PER_MSEC;
 		ret = icss_iep_perout_enable_hw(iep, &rq.perout, on);
 	} else {
 		ret = icss_iep_perout_enable_hw(iep, &rq.perout, on);
@@ -590,7 +621,8 @@ exit:
 
 static int icss_iep_extts_enable(struct icss_iep *iep, u32 index, int on)
 {
-	u32 val, cap, ret = 0;
+	u32 val, cap;
+	int ret = 0;
 
 	mutex_lock(&iep->ptp_clk_mutex);
 
@@ -654,11 +686,17 @@ struct icss_iep *icss_iep_get_idx(struct device_node *np, int idx)
 	struct platform_device *pdev;
 	struct device_node *iep_np;
 	struct icss_iep *iep;
+	int ret;
 
 	iep_np = of_parse_phandle(np, "ti,iep", idx);
-	if (!iep_np || !of_device_is_available(iep_np))
+	if (!iep_np)
 		return ERR_PTR(-ENODEV);
 
+	if (!of_device_is_available(iep_np)) {
+		of_node_put(iep_np);
+		return ERR_PTR(-ENODEV);
+	}
+
 	pdev = of_find_device_by_node(iep_np);
 	of_node_put(iep_np);
 
@@ -667,21 +705,28 @@ struct icss_iep *icss_iep_get_idx(struct device_node *np, int idx)
 		return ERR_PTR(-EPROBE_DEFER);
 
 	iep = platform_get_drvdata(pdev);
-	if (!iep)
-		return ERR_PTR(-EPROBE_DEFER);
+	if (!iep) {
+		ret = -EPROBE_DEFER;
+		goto err_put_pdev;
+	}
 
 	device_lock(iep->dev);
 	if (iep->client_np) {
 		device_unlock(iep->dev);
 		dev_err(iep->dev, "IEP is already acquired by %s",
 			iep->client_np->name);
-		return ERR_PTR(-EBUSY);
+		ret = -EBUSY;
+		goto err_put_pdev;
 	}
 	iep->client_np = np;
 	device_unlock(iep->dev);
-	get_device(iep->dev);
 
 	return iep;
+
+err_put_pdev:
+	put_device(&pdev->dev);
+
+	return ERR_PTR(ret);
 }
 EXPORT_SYMBOL_GPL(icss_iep_get_idx);
 
diff --git a/drivers/net/ethernet/ti/icssg/icssg_config.c b/drivers/net/ethernet/ti/icssg/icssg_config.c
index ddfd1c02a885..da53eb04b0a4 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_config.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_config.c
@@ -288,8 +288,12 @@ static int prueth_fw_offload_buffer_setup(struct prueth_emac *emac)
 	int i;
 
 	addr = lower_32_bits(prueth->msmcram.pa);
-	if (slice)
-		addr += PRUETH_NUM_BUF_POOLS * PRUETH_EMAC_BUF_POOL_SIZE;
+	if (slice) {
+		if (prueth->pdata.banked_ms_ram)
+			addr += MSMC_RAM_BANK_SIZE;
+		else
+			addr += PRUETH_SW_TOTAL_BUF_SIZE_PER_SLICE;
+	}
 
 	if (addr % SZ_64K) {
 		dev_warn(prueth->dev, "buffer pool needs to be 64KB aligned\n");
@@ -297,43 +301,66 @@ static int prueth_fw_offload_buffer_setup(struct prueth_emac *emac)
 	}
 
 	bpool_cfg = emac->dram.va + BUFFER_POOL_0_ADDR_OFFSET;
-	/* workaround for f/w bug. bpool 0 needs to be initialized */
-	for (i = 0; i <  PRUETH_NUM_BUF_POOLS; i++) {
+
+	/* Configure buffer pools for forwarding buffers
+	 * - used by firmware to store packets to be forwarded to other port
+	 * - 8 total pools per slice
+	 */
+	for (i = 0; i <  PRUETH_NUM_FWD_BUF_POOLS_PER_SLICE; i++) {
 		writel(addr, &bpool_cfg[i].addr);
-		writel(PRUETH_EMAC_BUF_POOL_SIZE, &bpool_cfg[i].len);
-		addr += PRUETH_EMAC_BUF_POOL_SIZE;
+		writel(PRUETH_SW_FWD_BUF_POOL_SIZE, &bpool_cfg[i].len);
+		addr += PRUETH_SW_FWD_BUF_POOL_SIZE;
 	}
 
-	if (!slice)
-		addr += PRUETH_NUM_BUF_POOLS * PRUETH_EMAC_BUF_POOL_SIZE;
-	else
-		addr += PRUETH_SW_NUM_BUF_POOLS_HOST * PRUETH_SW_BUF_POOL_SIZE_HOST;
-
-	for (i = PRUETH_NUM_BUF_POOLS;
-	     i < 2 * PRUETH_SW_NUM_BUF_POOLS_HOST + PRUETH_NUM_BUF_POOLS;
-	     i++) {
-		/* The driver only uses first 4 queues per PRU so only initialize them */
-		if (i % PRUETH_SW_NUM_BUF_POOLS_HOST < PRUETH_SW_NUM_BUF_POOLS_PER_PRU) {
-			writel(addr, &bpool_cfg[i].addr);
-			writel(PRUETH_SW_BUF_POOL_SIZE_HOST, &bpool_cfg[i].len);
-			addr += PRUETH_SW_BUF_POOL_SIZE_HOST;
+	/* Configure buffer pools for Local Injection buffers
+	 *  - used by firmware to store packets received from host core
+	 *  - 16 total pools per slice
+	 */
+	for (i = 0; i < PRUETH_NUM_LI_BUF_POOLS_PER_SLICE; i++) {
+		int cfg_idx = i + PRUETH_NUM_FWD_BUF_POOLS_PER_SLICE;
+
+		/* The driver only uses first 4 queues per PRU,
+		 * so only initialize buffer for them
+		 */
+		if ((i % PRUETH_NUM_LI_BUF_POOLS_PER_PORT_PER_SLICE)
+			 < PRUETH_SW_USED_LI_BUF_POOLS_PER_PORT_PER_SLICE) {
+			writel(addr, &bpool_cfg[cfg_idx].addr);
+			writel(PRUETH_SW_LI_BUF_POOL_SIZE,
+			       &bpool_cfg[cfg_idx].len);
+			addr += PRUETH_SW_LI_BUF_POOL_SIZE;
 		} else {
-			writel(0, &bpool_cfg[i].addr);
-			writel(0, &bpool_cfg[i].len);
+			writel(0, &bpool_cfg[cfg_idx].addr);
+			writel(0, &bpool_cfg[cfg_idx].len);
 		}
 	}
 
-	if (!slice)
-		addr += PRUETH_SW_NUM_BUF_POOLS_HOST * PRUETH_SW_BUF_POOL_SIZE_HOST;
-	else
-		addr += PRUETH_EMAC_RX_CTX_BUF_SIZE;
+	/* Express RX buffer queue
+	 *  - used by firmware to store express packets to be transmitted
+	 *    to the host core
+	 */
+	rxq_ctx = emac->dram.va + HOST_RX_Q_EXP_CONTEXT_OFFSET;
+	for (i = 0; i < 3; i++)
+		writel(addr, &rxq_ctx->start[i]);
+
+	addr += PRUETH_SW_HOST_EXP_BUF_POOL_SIZE;
+	writel(addr, &rxq_ctx->end);
 
+	/* Pre-emptible RX buffer queue
+	 *  - used by firmware to store preemptible packets to be transmitted
+	 *    to the host core
+	 */
 	rxq_ctx = emac->dram.va + HOST_RX_Q_PRE_CONTEXT_OFFSET;
 	for (i = 0; i < 3; i++)
 		writel(addr, &rxq_ctx->start[i]);
 
-	addr += PRUETH_EMAC_RX_CTX_BUF_SIZE;
-	writel(addr - SZ_2K, &rxq_ctx->end);
+	addr += PRUETH_SW_HOST_PRE_BUF_POOL_SIZE;
+	writel(addr, &rxq_ctx->end);
+
+	/* Set pointer for default dropped packet write
+	 *  - used by firmware to temporarily store packet to be dropped
+	 */
+	rxq_ctx = emac->dram.va + DEFAULT_MSMC_Q_OFFSET;
+	writel(addr, &rxq_ctx->start[0]);
 
 	return 0;
 }
@@ -347,13 +374,13 @@ static int prueth_emac_buffer_setup(struct prueth_emac *emac)
 	u32 addr;
 	int i;
 
-	/* Layout to have 64KB aligned buffer pool
-	 * |BPOOL0|BPOOL1|RX_CTX0|RX_CTX1|
-	 */
-
 	addr = lower_32_bits(prueth->msmcram.pa);
-	if (slice)
-		addr += PRUETH_NUM_BUF_POOLS * PRUETH_EMAC_BUF_POOL_SIZE;
+	if (slice) {
+		if (prueth->pdata.banked_ms_ram)
+			addr += MSMC_RAM_BANK_SIZE;
+		else
+			addr += PRUETH_EMAC_TOTAL_BUF_SIZE_PER_SLICE;
+	}
 
 	if (addr % SZ_64K) {
 		dev_warn(prueth->dev, "buffer pool needs to be 64KB aligned\n");
@@ -361,39 +388,66 @@ static int prueth_emac_buffer_setup(struct prueth_emac *emac)
 	}
 
 	bpool_cfg = emac->dram.va + BUFFER_POOL_0_ADDR_OFFSET;
-	/* workaround for f/w bug. bpool 0 needs to be initilalized */
-	writel(addr, &bpool_cfg[0].addr);
-	writel(0, &bpool_cfg[0].len);
 
-	for (i = PRUETH_EMAC_BUF_POOL_START;
-	     i < PRUETH_EMAC_BUF_POOL_START + PRUETH_NUM_BUF_POOLS;
-	     i++) {
-		writel(addr, &bpool_cfg[i].addr);
-		writel(PRUETH_EMAC_BUF_POOL_SIZE, &bpool_cfg[i].len);
-		addr += PRUETH_EMAC_BUF_POOL_SIZE;
+	/* Configure buffer pools for forwarding buffers
+	 *  - in mac mode - no forwarding so initialize all pools to 0
+	 *  - 8 total pools per slice
+	 */
+	for (i = 0; i <  PRUETH_NUM_FWD_BUF_POOLS_PER_SLICE; i++) {
+		writel(0, &bpool_cfg[i].addr);
+		writel(0, &bpool_cfg[i].len);
 	}
 
-	if (!slice)
-		addr += PRUETH_NUM_BUF_POOLS * PRUETH_EMAC_BUF_POOL_SIZE;
-	else
-		addr += PRUETH_EMAC_RX_CTX_BUF_SIZE * 2;
+	/* Configure buffer pools for Local Injection buffers
+	 *  - used by firmware to store packets received from host core
+	 *  - 16 total pools per slice
+	 */
+	bpool_cfg = emac->dram.va + BUFFER_POOL_0_ADDR_OFFSET;
+	for (i = 0; i < PRUETH_NUM_LI_BUF_POOLS_PER_SLICE; i++) {
+		int cfg_idx = i + PRUETH_NUM_FWD_BUF_POOLS_PER_SLICE;
+
+		/* In EMAC mode, only first 4 buffers are used,
+		 * as 1 slice needs to handle only 1 port
+		 */
+		if (i < PRUETH_EMAC_USED_LI_BUF_POOLS_PER_PORT_PER_SLICE) {
+			writel(addr, &bpool_cfg[cfg_idx].addr);
+			writel(PRUETH_EMAC_LI_BUF_POOL_SIZE,
+			       &bpool_cfg[cfg_idx].len);
+			addr += PRUETH_EMAC_LI_BUF_POOL_SIZE;
+		} else {
+			writel(0, &bpool_cfg[cfg_idx].addr);
+			writel(0, &bpool_cfg[cfg_idx].len);
+		}
+	}
 
-	/* Pre-emptible RX buffer queue */
-	rxq_ctx = emac->dram.va + HOST_RX_Q_PRE_CONTEXT_OFFSET;
+	/* Express RX buffer queue
+	 *  - used by firmware to store express packets to be transmitted
+	 *    to host core
+	 */
+	rxq_ctx = emac->dram.va + HOST_RX_Q_EXP_CONTEXT_OFFSET;
 	for (i = 0; i < 3; i++)
 		writel(addr, &rxq_ctx->start[i]);
 
-	addr += PRUETH_EMAC_RX_CTX_BUF_SIZE;
+	addr += PRUETH_EMAC_HOST_EXP_BUF_POOL_SIZE;
 	writel(addr, &rxq_ctx->end);
 
-	/* Express RX buffer queue */
-	rxq_ctx = emac->dram.va + HOST_RX_Q_EXP_CONTEXT_OFFSET;
+	/* Pre-emptible RX buffer queue
+	 *  - used by firmware to store preemptible packets to be transmitted
+	 *    to host core
+	 */
+	rxq_ctx = emac->dram.va + HOST_RX_Q_PRE_CONTEXT_OFFSET;
 	for (i = 0; i < 3; i++)
 		writel(addr, &rxq_ctx->start[i]);
 
-	addr += PRUETH_EMAC_RX_CTX_BUF_SIZE;
+	addr += PRUETH_EMAC_HOST_PRE_BUF_POOL_SIZE;
 	writel(addr, &rxq_ctx->end);
 
+	/* Set pointer for default dropped packet write
+	 *  - used by firmware to temporarily store packet to be dropped
+	 */
+	rxq_ctx = emac->dram.va + DEFAULT_MSMC_Q_OFFSET;
+	writel(addr, &rxq_ctx->start[0]);
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/ti/icssg/icssg_config.h b/drivers/net/ethernet/ti/icssg/icssg_config.h
index c884e9fa099e..60d69744ffae 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_config.h
+++ b/drivers/net/ethernet/ti/icssg/icssg_config.h
@@ -26,21 +26,71 @@ struct icssg_flow_cfg {
 #define PRUETH_MAX_RX_FLOWS	1	/* excluding default flow */
 #define PRUETH_RX_FLOW_DATA	0
 
-#define PRUETH_EMAC_BUF_POOL_SIZE	SZ_8K
-#define PRUETH_EMAC_POOLS_PER_SLICE	24
-#define PRUETH_EMAC_BUF_POOL_START	8
-#define PRUETH_NUM_BUF_POOLS	8
-#define PRUETH_EMAC_RX_CTX_BUF_SIZE	SZ_16K	/* per slice */
-#define MSMC_RAM_SIZE	\
-	(2 * (PRUETH_EMAC_BUF_POOL_SIZE * PRUETH_NUM_BUF_POOLS + \
-	 PRUETH_EMAC_RX_CTX_BUF_SIZE * 2))
-
-#define PRUETH_SW_BUF_POOL_SIZE_HOST	SZ_4K
-#define PRUETH_SW_NUM_BUF_POOLS_HOST	8
-#define PRUETH_SW_NUM_BUF_POOLS_PER_PRU 4
-#define MSMC_RAM_SIZE_SWITCH_MODE \
-	(MSMC_RAM_SIZE + \
-	(2 * PRUETH_SW_BUF_POOL_SIZE_HOST * PRUETH_SW_NUM_BUF_POOLS_HOST))
+/* Defines for forwarding path buffer pools:
+ *   - used by firmware to store packets to be forwarded to other port
+ *   - 8 total pools per slice
+ *   - only used in switch mode (as no forwarding in mac mode)
+ */
+#define PRUETH_NUM_FWD_BUF_POOLS_PER_SLICE			8
+#define PRUETH_SW_FWD_BUF_POOL_SIZE				(SZ_8K)
+
+/* Defines for local injection path buffer pools:
+ *   - used by firmware to store packets received from host core
+ *   - 16 total pools per slice
+ *   - 8 pools per port per slice and each slice handles both ports
+ *   - only 4 out of 8 pools used per port (as only 4 real QoS levels in ICSSG)
+ *   - switch mode: 8 total pools used
+ *   - mac mode:    4 total pools used
+ */
+#define PRUETH_NUM_LI_BUF_POOLS_PER_SLICE			16
+#define PRUETH_NUM_LI_BUF_POOLS_PER_PORT_PER_SLICE		8
+#define PRUETH_SW_LI_BUF_POOL_SIZE				SZ_4K
+#define PRUETH_SW_USED_LI_BUF_POOLS_PER_SLICE			8
+#define PRUETH_SW_USED_LI_BUF_POOLS_PER_PORT_PER_SLICE		4
+#define PRUETH_EMAC_LI_BUF_POOL_SIZE				SZ_8K
+#define PRUETH_EMAC_USED_LI_BUF_POOLS_PER_SLICE			4
+#define PRUETH_EMAC_USED_LI_BUF_POOLS_PER_PORT_PER_SLICE	4
+
+/* Defines for host egress path - express and preemptible buffers
+ *   - used by firmware to store express and preemptible packets
+ *     to be transmitted to host core
+ *   - used by both mac/switch modes
+ */
+#define PRUETH_SW_HOST_EXP_BUF_POOL_SIZE	SZ_16K
+#define PRUETH_SW_HOST_PRE_BUF_POOL_SIZE	(SZ_16K - SZ_2K)
+#define PRUETH_EMAC_HOST_EXP_BUF_POOL_SIZE	PRUETH_SW_HOST_EXP_BUF_POOL_SIZE
+#define PRUETH_EMAC_HOST_PRE_BUF_POOL_SIZE	PRUETH_SW_HOST_PRE_BUF_POOL_SIZE
+
+/* Buffer used by firmware to temporarily store packet to be dropped */
+#define PRUETH_SW_DROP_PKT_BUF_SIZE		SZ_2K
+#define PRUETH_EMAC_DROP_PKT_BUF_SIZE		PRUETH_SW_DROP_PKT_BUF_SIZE
+
+/* Total switch mode memory usage for buffers per slice */
+#define PRUETH_SW_TOTAL_BUF_SIZE_PER_SLICE \
+	(PRUETH_SW_FWD_BUF_POOL_SIZE * PRUETH_NUM_FWD_BUF_POOLS_PER_SLICE + \
+	 PRUETH_SW_LI_BUF_POOL_SIZE * PRUETH_SW_USED_LI_BUF_POOLS_PER_SLICE + \
+	 PRUETH_SW_HOST_EXP_BUF_POOL_SIZE + \
+	 PRUETH_SW_HOST_PRE_BUF_POOL_SIZE + \
+	 PRUETH_SW_DROP_PKT_BUF_SIZE)
+
+/* Total switch mode memory usage for all buffers */
+#define PRUETH_SW_TOTAL_BUF_SIZE \
+	(2 * PRUETH_SW_TOTAL_BUF_SIZE_PER_SLICE)
+
+/* Total mac mode memory usage for buffers per slice */
+#define PRUETH_EMAC_TOTAL_BUF_SIZE_PER_SLICE \
+	(PRUETH_EMAC_LI_BUF_POOL_SIZE * \
+	 PRUETH_EMAC_USED_LI_BUF_POOLS_PER_SLICE + \
+	 PRUETH_EMAC_HOST_EXP_BUF_POOL_SIZE + \
+	 PRUETH_EMAC_HOST_PRE_BUF_POOL_SIZE + \
+	 PRUETH_EMAC_DROP_PKT_BUF_SIZE)
+
+/* Total mac mode memory usage for all buffers */
+#define PRUETH_EMAC_TOTAL_BUF_SIZE \
+	(2 * PRUETH_EMAC_TOTAL_BUF_SIZE_PER_SLICE)
+
+/* Size of 1 bank of MSMC/OC_SRAM memory */
+#define MSMC_RAM_BANK_SIZE			SZ_256K
 
 #define PRUETH_SWITCH_FDB_MASK ((SIZE_OF_FDB / NUMBER_OF_FDB_BUCKET_ENTRIES) - 1)
 
diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
index cb11635a8d12..ddbc4624ae88 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
@@ -50,6 +50,8 @@
 /* CTRLMMR_ICSSG_RGMII_CTRL register bits */
 #define ICSSG_CTRL_RGMII_ID_MODE                BIT(24)
 
+static void emac_adjust_link(struct net_device *ndev);
+
 static int emac_get_tx_ts(struct prueth_emac *emac,
 			  struct emac_tx_ts_response *rsp)
 {
@@ -266,6 +268,10 @@ static int prueth_emac_common_start(struct prueth *prueth)
 		ret = icssg_config(prueth, emac, slice);
 		if (ret)
 			goto disable_class;
+
+		mutex_lock(&emac->ndev->phydev->lock);
+		emac_adjust_link(emac->ndev);
+		mutex_unlock(&emac->ndev->phydev->lock);
 	}
 
 	ret = prueth_emac_start(prueth);
@@ -1510,10 +1516,15 @@ static int prueth_probe(struct platform_device *pdev)
 		goto put_mem;
 	}
 
-	msmc_ram_size = MSMC_RAM_SIZE;
 	prueth->is_switchmode_supported = prueth->pdata.switch_mode;
-	if (prueth->is_switchmode_supported)
-		msmc_ram_size = MSMC_RAM_SIZE_SWITCH_MODE;
+	if (prueth->pdata.banked_ms_ram) {
+		/* Reserve 2 MSMC RAM banks for buffers to avoid arbitration */
+		msmc_ram_size = (2 * MSMC_RAM_BANK_SIZE);
+	} else {
+		msmc_ram_size = PRUETH_EMAC_TOTAL_BUF_SIZE;
+		if (prueth->is_switchmode_supported)
+			msmc_ram_size = PRUETH_SW_TOTAL_BUF_SIZE;
+	}
 
 	/* NOTE: FW bug needs buffer base to be 64KB aligned */
 	prueth->msmcram.va =
@@ -1555,6 +1566,7 @@ static int prueth_probe(struct platform_device *pdev)
 	}
 
 	spin_lock_init(&prueth->vtbl_lock);
+	spin_lock_init(&prueth->stats_lock);
 	/* setup netdev interfaces */
 	if (eth0_node) {
 		ret = prueth_netdev_init(prueth, eth0_node);
@@ -1669,7 +1681,8 @@ put_iep0:
 
 free_pool:
 	gen_pool_free(prueth->sram_pool,
-		      (unsigned long)prueth->msmcram.va, msmc_ram_size);
+		      (unsigned long)prueth->msmcram.va,
+		      prueth->msmcram.size);
 
 put_mem:
 	pruss_release_mem_region(prueth->pruss, &prueth->shram);
@@ -1721,8 +1734,8 @@ static void prueth_remove(struct platform_device *pdev)
 	icss_iep_put(prueth->iep0);
 
 	gen_pool_free(prueth->sram_pool,
-		      (unsigned long)prueth->msmcram.va,
-		      MSMC_RAM_SIZE);
+		(unsigned long)prueth->msmcram.va,
+		prueth->msmcram.size);
 
 	pruss_release_mem_region(prueth->pruss, &prueth->shram);
 
@@ -1739,12 +1752,14 @@ static const struct prueth_pdata am654_icssg_pdata = {
 	.fdqring_mode = K3_RINGACC_RING_MODE_MESSAGE,
 	.quirk_10m_link_issue = 1,
 	.switch_mode = 1,
+	.banked_ms_ram = 0,
 };
 
 static const struct prueth_pdata am64x_icssg_pdata = {
 	.fdqring_mode = K3_RINGACC_RING_MODE_RING,
 	.quirk_10m_link_issue = 1,
 	.switch_mode = 1,
+	.banked_ms_ram = 1,
 };
 
 static const struct of_device_id prueth_dt_match[] = {
diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.h b/drivers/net/ethernet/ti/icssg/icssg_prueth.h
index 5473315ea204..693c8731c094 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.h
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.h
@@ -207,11 +207,13 @@ struct prueth_emac {
  * @fdqring_mode: Free desc queue mode
  * @quirk_10m_link_issue: 10M link detect errata
  * @switch_mode: switch firmware support
+ * @banked_ms_ram: banked memory support
  */
 struct prueth_pdata {
 	enum k3_ring_mode fdqring_mode;
 	u32	quirk_10m_link_issue:1;
 	u32	switch_mode:1;
+	u32	banked_ms_ram:1;
 };
 
 struct icssg_firmwares {
@@ -297,6 +299,8 @@ struct prueth {
 	int default_vlan;
 	/** @vtbl_lock: Lock for vtbl in shared memory */
 	spinlock_t vtbl_lock;
+	/** @stats_lock: Lock for reading icssg stats */
+	spinlock_t stats_lock;
 };
 
 struct emac_tx_ts_response {
diff --git a/drivers/net/ethernet/ti/icssg/icssg_stats.c b/drivers/net/ethernet/ti/icssg/icssg_stats.c
index 8800bd3a8d07..172ae38381b4 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_stats.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_stats.c
@@ -26,7 +26,17 @@ void emac_update_hardware_stats(struct prueth_emac *emac)
 	u32 val, reg;
 	int i;
 
+	spin_lock(&prueth->stats_lock);
+
 	for (i = 0; i < ARRAY_SIZE(icssg_all_miig_stats); i++) {
+		/* In MII mode TX lines are swapped inside ICSSG, so read Tx stats
+		 * from slice1 for port0 and slice0 for port1 to get accurate Tx
+		 * stats for a given port
+		 */
+		if (emac->phy_if == PHY_INTERFACE_MODE_MII &&
+		    icssg_all_miig_stats[i].offset >= ICSSG_TX_PACKET_OFFSET &&
+		    icssg_all_miig_stats[i].offset <= ICSSG_TX_BYTE_OFFSET)
+			base = stats_base[slice ^ 1];
 		regmap_read(prueth->miig_rt,
 			    base + icssg_all_miig_stats[i].offset,
 			    &val);
@@ -51,6 +61,8 @@ void emac_update_hardware_stats(struct prueth_emac *emac)
 			emac->pa_stats[i] += val;
 		}
 	}
+
+	spin_unlock(&prueth->stats_lock);
 }
 
 void icssg_stats_work_handler(struct work_struct *work)
diff --git a/drivers/net/ethernet/ti/icssg/icssg_switch_map.h b/drivers/net/ethernet/ti/icssg/icssg_switch_map.h
index 424a7e945ea8..12541a12ebd6 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_switch_map.h
+++ b/drivers/net/ethernet/ti/icssg/icssg_switch_map.h
@@ -180,6 +180,9 @@
 /* Used to notify the FW of the current link speed */
 #define PORT_LINK_SPEED_OFFSET                             0x00A8
 
+/* 2k memory pointer reserved for default writes by PRU0*/
+#define DEFAULT_MSMC_Q_OFFSET                              0x00AC
+
 /* TAS gate mask for windows list0 */
 #define TAS_GATE_MASK_LIST0                                0x0100
 
diff --git a/drivers/net/ethernet/vertexcom/mse102x.c b/drivers/net/ethernet/vertexcom/mse102x.c
index 89dc4c401a8d..545177e84c0e 100644
--- a/drivers/net/ethernet/vertexcom/mse102x.c
+++ b/drivers/net/ethernet/vertexcom/mse102x.c
@@ -6,6 +6,7 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <linux/if_vlan.h>
 #include <linux/interrupt.h>
 #include <linux/module.h>
 #include <linux/kernel.h>
@@ -33,7 +34,7 @@
 #define CMD_CTR		(0x2 << CMD_SHIFT)
 
 #define CMD_MASK	GENMASK(15, CMD_SHIFT)
-#define LEN_MASK	GENMASK(CMD_SHIFT - 1, 0)
+#define LEN_MASK	GENMASK(CMD_SHIFT - 2, 0)
 
 #define DET_CMD_LEN	4
 #define DET_SOF_LEN	2
@@ -262,7 +263,7 @@ static int mse102x_tx_frame_spi(struct mse102x_net *mse, struct sk_buff *txp,
 }
 
 static int mse102x_rx_frame_spi(struct mse102x_net *mse, u8 *buff,
-				unsigned int frame_len)
+				unsigned int frame_len, bool drop)
 {
 	struct mse102x_net_spi *mses = to_mse102x_spi(mse);
 	struct spi_transfer *xfer = &mses->spi_xfer;
@@ -280,6 +281,9 @@ static int mse102x_rx_frame_spi(struct mse102x_net *mse, u8 *buff,
 		netdev_err(mse->ndev, "%s: spi_sync() failed: %d\n",
 			   __func__, ret);
 		mse->stats.xfer_err++;
+	} else if (drop) {
+		netdev_dbg(mse->ndev, "%s: Drop frame\n", __func__);
+		ret = -EINVAL;
 	} else if (*sof != cpu_to_be16(DET_SOF)) {
 		netdev_dbg(mse->ndev, "%s: SPI start of frame is invalid (0x%04x)\n",
 			   __func__, *sof);
@@ -302,11 +306,12 @@ static void mse102x_dump_packet(const char *msg, int len, const char *data)
 		       data, len, true);
 }
 
-static void mse102x_rx_pkt_spi(struct mse102x_net *mse)
+static irqreturn_t mse102x_rx_pkt_spi(struct mse102x_net *mse)
 {
 	struct sk_buff *skb;
 	unsigned int rxalign;
 	unsigned int rxlen;
+	bool drop = false;
 	__be16 rx = 0;
 	u16 cmd_resp;
 	u8 *rxpkt;
@@ -322,14 +327,15 @@ static void mse102x_rx_pkt_spi(struct mse102x_net *mse)
 		mse102x_tx_cmd_spi(mse, CMD_CTR);
 		ret = mse102x_rx_cmd_spi(mse, (u8 *)&rx);
 		if (ret)
-			return;
+			return IRQ_NONE;
 
 		cmd_resp = be16_to_cpu(rx);
 		if ((cmd_resp & CMD_MASK) != CMD_RTS) {
 			net_dbg_ratelimited("%s: Unexpected response (0x%04x)\n",
 					    __func__, cmd_resp);
 			mse->stats.invalid_rts++;
-			return;
+			drop = true;
+			goto drop;
 		}
 
 		net_dbg_ratelimited("%s: Unexpected response to first CMD\n",
@@ -337,26 +343,34 @@ static void mse102x_rx_pkt_spi(struct mse102x_net *mse)
 	}
 
 	rxlen = cmd_resp & LEN_MASK;
-	if (!rxlen) {
-		net_dbg_ratelimited("%s: No frame length defined\n", __func__);
+	if (rxlen < ETH_ZLEN || rxlen > VLAN_ETH_FRAME_LEN) {
+		net_dbg_ratelimited("%s: Invalid frame length: %d\n", __func__,
+				    rxlen);
 		mse->stats.invalid_len++;
-		return;
+		drop = true;
 	}
 
+	/* In case of a invalid CMD_RTS, the frame must be consumed anyway.
+	 * So assume the maximum possible frame length.
+	 */
+drop:
+	if (drop)
+		rxlen = VLAN_ETH_FRAME_LEN;
+
 	rxalign = ALIGN(rxlen + DET_SOF_LEN + DET_DFT_LEN, 4);
 	skb = netdev_alloc_skb_ip_align(mse->ndev, rxalign);
 	if (!skb)
-		return;
+		return IRQ_NONE;
 
 	/* 2 bytes Start of frame (before ethernet header)
 	 * 2 bytes Data frame tail (after ethernet frame)
 	 * They are copied, but ignored.
 	 */
 	rxpkt = skb_put(skb, rxlen) - DET_SOF_LEN;
-	if (mse102x_rx_frame_spi(mse, rxpkt, rxlen)) {
+	if (mse102x_rx_frame_spi(mse, rxpkt, rxlen, drop)) {
 		mse->ndev->stats.rx_errors++;
 		dev_kfree_skb(skb);
-		return;
+		return IRQ_HANDLED;
 	}
 
 	if (netif_msg_pktdata(mse))
@@ -367,6 +381,8 @@ static void mse102x_rx_pkt_spi(struct mse102x_net *mse)
 
 	mse->ndev->stats.rx_packets++;
 	mse->ndev->stats.rx_bytes += rxlen;
+
+	return IRQ_HANDLED;
 }
 
 static int mse102x_tx_pkt_spi(struct mse102x_net *mse, struct sk_buff *txb,
@@ -498,17 +514,19 @@ static irqreturn_t mse102x_irq(int irq, void *_mse)
 {
 	struct mse102x_net *mse = _mse;
 	struct mse102x_net_spi *mses = to_mse102x_spi(mse);
+	irqreturn_t ret;
 
 	mutex_lock(&mses->lock);
-	mse102x_rx_pkt_spi(mse);
+	ret = mse102x_rx_pkt_spi(mse);
 	mutex_unlock(&mses->lock);
 
-	return IRQ_HANDLED;
+	return ret;
 }
 
 static int mse102x_net_open(struct net_device *ndev)
 {
 	struct mse102x_net *mse = netdev_priv(ndev);
+	struct mse102x_net_spi *mses = to_mse102x_spi(mse);
 	int ret;
 
 	ret = request_threaded_irq(ndev->irq, NULL, mse102x_irq, IRQF_ONESHOT,
@@ -524,6 +542,13 @@ static int mse102x_net_open(struct net_device *ndev)
 
 	netif_carrier_on(ndev);
 
+	/* The SPI interrupt can stuck in case of pending packet(s).
+	 * So poll for possible packet(s) to re-arm the interrupt.
+	 */
+	mutex_lock(&mses->lock);
+	mse102x_rx_pkt_spi(mse);
+	mutex_unlock(&mses->lock);
+
 	netif_dbg(mse, ifup, ndev, "network device up\n");
 
 	return 0;
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_hw.c b/drivers/net/ethernet/wangxun/libwx/wx_hw.c
index deaf670c160e..e79220cb725b 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_hw.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_hw.c
@@ -1531,7 +1531,6 @@ static void wx_configure_rx_ring(struct wx *wx,
 				 struct wx_ring *ring)
 {
 	u16 reg_idx = ring->reg_idx;
-	union wx_rx_desc *rx_desc;
 	u64 rdba = ring->dma;
 	u32 rxdctl;
 
@@ -1561,9 +1560,9 @@ static void wx_configure_rx_ring(struct wx *wx,
 	memset(ring->rx_buffer_info, 0,
 	       sizeof(struct wx_rx_buffer) * ring->count);
 
-	/* initialize Rx descriptor 0 */
-	rx_desc = WX_RX_DESC(ring, 0);
-	rx_desc->wb.upper.length = 0;
+	/* reset ntu and ntc to place SW in sync with hardware */
+	ring->next_to_clean = 0;
+	ring->next_to_use = 0;
 
 	/* enable receive descriptor ring */
 	wr32m(wx, WX_PX_RR_CFG(reg_idx),
@@ -2356,6 +2355,8 @@ void wx_update_stats(struct wx *wx)
 		hwstats->fdirmiss += rd32(wx, WX_RDB_FDIR_MISS);
 	}
 
+	/* qmprc is not cleared on read, manual reset it */
+	hwstats->qmprc = 0;
 	for (i = 0; i < wx->mac.max_rx_queues; i++)
 		hwstats->qmprc += rd32(wx, WX_PX_MPRC(i));
 }
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_lib.c b/drivers/net/ethernet/wangxun/libwx/wx_lib.c
index 2b3d6586f44a..4c203f4afd68 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_lib.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_lib.c
@@ -172,10 +172,6 @@ static void wx_dma_sync_frag(struct wx_ring *rx_ring,
 				      skb_frag_off(frag),
 				      skb_frag_size(frag),
 				      DMA_FROM_DEVICE);
-
-	/* If the page was released, just unmap it. */
-	if (unlikely(WX_CB(skb)->page_released))
-		page_pool_put_full_page(rx_ring->page_pool, rx_buffer->page, false);
 }
 
 static struct wx_rx_buffer *wx_get_rx_buffer(struct wx_ring *rx_ring,
@@ -225,10 +221,6 @@ static void wx_put_rx_buffer(struct wx_ring *rx_ring,
 			     struct sk_buff *skb,
 			     int rx_buffer_pgcnt)
 {
-	if (!IS_ERR(skb) && WX_CB(skb)->dma == rx_buffer->dma)
-		/* the page has been released from the ring */
-		WX_CB(skb)->page_released = true;
-
 	/* clear contents of rx_buffer */
 	rx_buffer->page = NULL;
 	rx_buffer->skb = NULL;
@@ -309,10 +301,11 @@ static bool wx_alloc_mapped_page(struct wx_ring *rx_ring,
 		return true;
 
 	page = page_pool_dev_alloc_pages(rx_ring->page_pool);
-	WARN_ON(!page);
+	if (unlikely(!page))
+		return false;
 	dma = page_pool_get_dma_addr(page);
 
-	bi->page_dma = dma;
+	bi->dma = dma;
 	bi->page = page;
 	bi->page_offset = 0;
 
@@ -349,7 +342,7 @@ void wx_alloc_rx_buffers(struct wx_ring *rx_ring, u16 cleaned_count)
 						 DMA_FROM_DEVICE);
 
 		rx_desc->read.pkt_addr =
-			cpu_to_le64(bi->page_dma + bi->page_offset);
+			cpu_to_le64(bi->dma + bi->page_offset);
 
 		rx_desc++;
 		bi++;
@@ -362,6 +355,8 @@ void wx_alloc_rx_buffers(struct wx_ring *rx_ring, u16 cleaned_count)
 
 		/* clear the status bits for the next_to_use descriptor */
 		rx_desc->wb.upper.status_error = 0;
+		/* clear the length for the next_to_use descriptor */
+		rx_desc->wb.upper.length = 0;
 
 		cleaned_count--;
 	} while (cleaned_count);
@@ -1335,6 +1330,7 @@ static void wx_tx_csum(struct wx_ring *tx_ring, struct wx_tx_buffer *first,
 	u8 tun_prot = 0;
 
 	if (skb->ip_summed != CHECKSUM_PARTIAL) {
+csum_failed:
 		if (!(first->tx_flags & WX_TX_FLAGS_HW_VLAN) &&
 		    !(first->tx_flags & WX_TX_FLAGS_CC))
 			return;
@@ -1428,7 +1424,8 @@ static void wx_tx_csum(struct wx_ring *tx_ring, struct wx_tx_buffer *first,
 					WX_TXD_L4LEN_SHIFT;
 			break;
 		default:
-			break;
+			skb_checksum_help(skb);
+			goto csum_failed;
 		}
 
 		/* update TX checksum flag */
@@ -1582,6 +1579,7 @@ static void wx_set_rss_queues(struct wx *wx)
 
 	clear_bit(WX_FLAG_FDIR_HASH, wx->flags);
 
+	wx->ring_feature[RING_F_FDIR].indices = 1;
 	/* Use Flow Director in addition to RSS to ensure the best
 	 * distribution of flows across cores, even when an FDIR flow
 	 * isn't matched.
@@ -1620,7 +1618,7 @@ static void wx_set_num_queues(struct wx *wx)
  */
 static int wx_acquire_msix_vectors(struct wx *wx)
 {
-	struct irq_affinity affd = { .pre_vectors = 1 };
+	struct irq_affinity affd = { .post_vectors = 1 };
 	int nvecs, i;
 
 	/* We start by asking for one vector per queue pair */
@@ -1657,16 +1655,17 @@ static int wx_acquire_msix_vectors(struct wx *wx)
 		return nvecs;
 	}
 
-	wx->msix_entry->entry = 0;
-	wx->msix_entry->vector = pci_irq_vector(wx->pdev, 0);
 	nvecs -= 1;
 	for (i = 0; i < nvecs; i++) {
 		wx->msix_q_entries[i].entry = i;
-		wx->msix_q_entries[i].vector = pci_irq_vector(wx->pdev, i + 1);
+		wx->msix_q_entries[i].vector = pci_irq_vector(wx->pdev, i);
 	}
 
 	wx->num_q_vectors = nvecs;
 
+	wx->msix_entry->entry = nvecs;
+	wx->msix_entry->vector = pci_irq_vector(wx->pdev, nvecs);
+
 	return 0;
 }
 
@@ -2116,7 +2115,6 @@ static void wx_set_ivar(struct wx *wx, s8 direction,
 		wr32(wx, WX_PX_MISC_IVAR, ivar);
 	} else {
 		/* tx or rx causes */
-		msix_vector += 1; /* offset for queue vectors */
 		msix_vector |= WX_PX_IVAR_ALLOC_VAL;
 		index = ((16 * (queue & 1)) + (8 * direction));
 		ivar = rd32(wx, WX_PX_IVAR(queue >> 1));
@@ -2147,7 +2145,7 @@ void wx_write_eitr(struct wx_q_vector *q_vector)
 
 	itr_reg |= WX_PX_ITR_CNT_WDIS;
 
-	wr32(wx, WX_PX_ITR(v_idx + 1), itr_reg);
+	wr32(wx, WX_PX_ITR(v_idx), itr_reg);
 }
 
 /**
@@ -2193,9 +2191,9 @@ void wx_configure_vectors(struct wx *wx)
 		wx_write_eitr(q_vector);
 	}
 
-	wx_set_ivar(wx, -1, 0, 0);
+	wx_set_ivar(wx, -1, 0, v_idx);
 	if (pdev->msix_enabled)
-		wr32(wx, WX_PX_ITR(0), 1950);
+		wr32(wx, WX_PX_ITR(v_idx), 1950);
 }
 EXPORT_SYMBOL(wx_configure_vectors);
 
@@ -2215,9 +2213,6 @@ static void wx_clean_rx_ring(struct wx_ring *rx_ring)
 		if (rx_buffer->skb) {
 			struct sk_buff *skb = rx_buffer->skb;
 
-			if (WX_CB(skb)->page_released)
-				page_pool_put_full_page(rx_ring->page_pool, rx_buffer->page, false);
-
 			dev_kfree_skb(skb);
 		}
 
@@ -2241,6 +2236,9 @@ static void wx_clean_rx_ring(struct wx_ring *rx_ring)
 		}
 	}
 
+	/* Zero out the descriptor ring */
+	memset(rx_ring->desc, 0, rx_ring->size);
+
 	rx_ring->next_to_alloc = 0;
 	rx_ring->next_to_clean = 0;
 	rx_ring->next_to_use = 0;
@@ -2424,7 +2422,7 @@ static int wx_alloc_page_pool(struct wx_ring *rx_ring)
 	struct page_pool_params pp_params = {
 		.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV,
 		.order = 0,
-		.pool_size = rx_ring->size,
+		.pool_size = rx_ring->count,
 		.nid = dev_to_node(rx_ring->dev),
 		.dev = rx_ring->dev,
 		.dma_dir = DMA_FROM_DEVICE,
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_type.h b/drivers/net/ethernet/wangxun/libwx/wx_type.h
index b54bffda027b..950cacaf095a 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_type.h
+++ b/drivers/net/ethernet/wangxun/libwx/wx_type.h
@@ -787,7 +787,6 @@ enum wx_reset_type {
 struct wx_cb {
 	dma_addr_t dma;
 	u16     append_cnt;      /* number of skb's appended */
-	bool    page_released;
 	bool    dma_released;
 };
 
@@ -875,7 +874,6 @@ struct wx_tx_buffer {
 struct wx_rx_buffer {
 	struct sk_buff *skb;
 	dma_addr_t dma;
-	dma_addr_t page_dma;
 	struct page *page;
 	unsigned int page_offset;
 };
@@ -1136,7 +1134,7 @@ struct wx {
 };
 
 #define WX_INTR_ALL (~0ULL)
-#define WX_INTR_Q(i) BIT((i) + 1)
+#define WX_INTR_Q(i) BIT((i))
 
 /* register operations */
 #define wr32(a, reg, value)	writel((value), ((a)->hw_addr + (reg)))
diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c b/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c
index 53aeae2f884b..d2fb77f1d876 100644
--- a/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c
+++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c
@@ -154,7 +154,7 @@ static void ngbe_irq_enable(struct wx *wx, bool queues)
 	if (queues)
 		wx_intr_enable(wx, NGBE_INTR_ALL);
 	else
-		wx_intr_enable(wx, NGBE_INTR_MISC);
+		wx_intr_enable(wx, NGBE_INTR_MISC(wx));
 }
 
 /**
@@ -607,7 +607,7 @@ static int ngbe_probe(struct pci_dev *pdev,
 	/* setup the private structure */
 	err = ngbe_sw_init(wx);
 	if (err)
-		goto err_free_mac_table;
+		goto err_pci_release_regions;
 
 	/* check if flash load is done after hw power up */
 	err = wx_check_flash_load(wx, NGBE_SPI_ILDR_STATUS_PERST);
@@ -701,6 +701,7 @@ err_register:
 err_clear_interrupt_scheme:
 	wx_clear_interrupt_scheme(wx);
 err_free_mac_table:
+	kfree(wx->rss_key);
 	kfree(wx->mac_table);
 err_pci_release_regions:
 	pci_release_selected_regions(pdev,
diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_type.h b/drivers/net/ethernet/wangxun/ngbe/ngbe_type.h
index f48ed7fc1805..f4dc4acbedae 100644
--- a/drivers/net/ethernet/wangxun/ngbe/ngbe_type.h
+++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_type.h
@@ -80,7 +80,7 @@
 				NGBE_PX_MISC_IEN_GPIO)
 
 #define NGBE_INTR_ALL				0x1FF
-#define NGBE_INTR_MISC				BIT(0)
+#define NGBE_INTR_MISC(A)			BIT((A)->num_q_vectors)
 
 #define NGBE_PHY_CONFIG(reg_offset)		(0x14000 + ((reg_offset) * 4))
 #define NGBE_CFG_LAN_SPEED			0x14440
diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_irq.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_irq.c
index 0ee73a265545..76d33c042eee 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_irq.c
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_irq.c
@@ -21,7 +21,7 @@ void txgbe_irq_enable(struct wx *wx, bool queues)
 	wr32(wx, WX_PX_MISC_IEN, TXGBE_PX_MISC_IEN_MASK);
 
 	/* unmask interrupt */
-	wx_intr_enable(wx, TXGBE_INTR_MISC);
+	wx_intr_enable(wx, TXGBE_INTR_MISC(wx));
 	if (queues)
 		wx_intr_enable(wx, TXGBE_INTR_QALL(wx));
 }
@@ -68,7 +68,6 @@ free_queue_irqs:
 		free_irq(wx->msix_q_entries[vector].vector,
 			 wx->q_vector[vector]);
 	}
-	wx_reset_interrupt_capability(wx);
 	return err;
 }
 
@@ -148,7 +147,7 @@ static irqreturn_t txgbe_misc_irq_thread_fn(int irq, void *data)
 		nhandled++;
 	}
 
-	wx_intr_enable(wx, TXGBE_INTR_MISC);
+	wx_intr_enable(wx, TXGBE_INTR_MISC(wx));
 	return (nhandled > 0 ? IRQ_HANDLED : IRQ_NONE);
 }
 
@@ -169,6 +168,7 @@ void txgbe_free_misc_irq(struct txgbe *txgbe)
 	free_irq(txgbe->link_irq, txgbe);
 	free_irq(txgbe->misc.irq, txgbe);
 	txgbe_del_irq_domain(txgbe);
+	txgbe->wx->misc_irq_domain = false;
 }
 
 int txgbe_setup_misc_irq(struct txgbe *txgbe)
diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c
index f77450268036..9ede260b85dc 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c
@@ -308,10 +308,14 @@ static int txgbe_open(struct net_device *netdev)
 
 	wx_configure(wx);
 
-	err = txgbe_request_queue_irqs(wx);
+	err = txgbe_setup_misc_irq(wx->priv);
 	if (err)
 		goto err_free_resources;
 
+	err = txgbe_request_queue_irqs(wx);
+	if (err)
+		goto err_free_misc_irq;
+
 	/* Notify the stack of the actual queue counts. */
 	err = netif_set_real_num_tx_queues(netdev, wx->num_tx_queues);
 	if (err)
@@ -327,6 +331,9 @@ static int txgbe_open(struct net_device *netdev)
 
 err_free_irq:
 	wx_free_irq(wx);
+err_free_misc_irq:
+	txgbe_free_misc_irq(wx->priv);
+	wx_reset_interrupt_capability(wx);
 err_free_resources:
 	wx_free_resources(wx);
 err_reset:
@@ -365,6 +372,7 @@ static int txgbe_close(struct net_device *netdev)
 
 	txgbe_down(wx);
 	wx_free_irq(wx);
+	txgbe_free_misc_irq(wx->priv);
 	wx_free_resources(wx);
 	txgbe_fdir_filter_exit(wx);
 	wx_control_hw(wx, false);
@@ -410,7 +418,6 @@ static void txgbe_shutdown(struct pci_dev *pdev)
 int txgbe_setup_tc(struct net_device *dev, u8 tc)
 {
 	struct wx *wx = netdev_priv(dev);
-	struct txgbe *txgbe = wx->priv;
 
 	/* Hardware has to reinitialize queues and interrupts to
 	 * match packet buffer alignment. Unfortunately, the
@@ -421,7 +428,6 @@ int txgbe_setup_tc(struct net_device *dev, u8 tc)
 	else
 		txgbe_reset(wx);
 
-	txgbe_free_misc_irq(txgbe);
 	wx_clear_interrupt_scheme(wx);
 
 	if (tc)
@@ -430,7 +436,6 @@ int txgbe_setup_tc(struct net_device *dev, u8 tc)
 		netdev_reset_tc(dev);
 
 	wx_init_interrupt_scheme(wx);
-	txgbe_setup_misc_irq(txgbe);
 
 	if (netif_running(dev))
 		txgbe_open(dev);
@@ -559,7 +564,7 @@ static int txgbe_probe(struct pci_dev *pdev,
 	/* setup the private structure */
 	err = txgbe_sw_init(wx);
 	if (err)
-		goto err_free_mac_table;
+		goto err_pci_release_regions;
 
 	/* check if flash load is done after hw power up */
 	err = wx_check_flash_load(wx, TXGBE_SPI_ILDR_STATUS_PERST);
@@ -677,13 +682,9 @@ static int txgbe_probe(struct pci_dev *pdev,
 
 	txgbe_init_fdir(txgbe);
 
-	err = txgbe_setup_misc_irq(txgbe);
-	if (err)
-		goto err_release_hw;
-
 	err = txgbe_init_phy(txgbe);
 	if (err)
-		goto err_free_misc_irq;
+		goto err_release_hw;
 
 	err = register_netdev(netdev);
 	if (err)
@@ -711,12 +712,11 @@ static int txgbe_probe(struct pci_dev *pdev,
 
 err_remove_phy:
 	txgbe_remove_phy(txgbe);
-err_free_misc_irq:
-	txgbe_free_misc_irq(txgbe);
 err_release_hw:
 	wx_clear_interrupt_scheme(wx);
 	wx_control_hw(wx, false);
 err_free_mac_table:
+	kfree(wx->rss_key);
 	kfree(wx->mac_table);
 err_pci_release_regions:
 	pci_release_selected_regions(pdev,
@@ -745,7 +745,6 @@ static void txgbe_remove(struct pci_dev *pdev)
 	unregister_netdev(netdev);
 
 	txgbe_remove_phy(txgbe);
-	txgbe_free_misc_irq(txgbe);
 	wx_free_isb_resources(wx);
 
 	pci_release_selected_regions(pdev,
diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h b/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h
index 8ea413a7abe9..5fe415f3f2ca 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h
@@ -264,8 +264,8 @@ struct txgbe_fdir_filter {
 #define TXGBE_DEFAULT_RX_WORK           128
 #endif
 
-#define TXGBE_INTR_MISC       BIT(0)
-#define TXGBE_INTR_QALL(A)    GENMASK((A)->num_q_vectors, 1)
+#define TXGBE_INTR_MISC(A)    BIT((A)->num_q_vectors)
+#define TXGBE_INTR_QALL(A)    (TXGBE_INTR_MISC(A) - 1)
 
 #define TXGBE_MAX_EITR        GENMASK(11, 3)
 
diff --git a/drivers/net/ethernet/xilinx/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c
index 1072e2210aed..6b93418224e7 100644
--- a/drivers/net/ethernet/xilinx/ll_temac_main.c
+++ b/drivers/net/ethernet/xilinx/ll_temac_main.c
@@ -1309,7 +1309,7 @@ ll_temac_ethtools_set_ringparam(struct net_device *ndev,
 	if (ering->rx_pending > RX_BD_NUM_MAX ||
 	    ering->rx_mini_pending ||
 	    ering->rx_jumbo_pending ||
-	    ering->rx_pending > TX_BD_NUM_MAX)
+	    ering->tx_pending > TX_BD_NUM_MAX)
 		return -EINVAL;
 
 	if (netif_running(ndev))
diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
index de10a2d08c42..2d47b35443af 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
@@ -843,7 +843,7 @@ static void axienet_dma_tx_cb(void *data, const struct dmaengine_result *result)
 	dev_consume_skb_any(skbuf_dma->skb);
 	netif_txq_completed_wake(txq, 1, len,
 				 CIRC_SPACE(lp->tx_ring_head, lp->tx_ring_tail, TX_BD_NUM_MAX),
-				 2 * MAX_SKB_FRAGS);
+				 2);
 }
 
 /**
@@ -877,7 +877,7 @@ axienet_start_xmit_dmaengine(struct sk_buff *skb, struct net_device *ndev)
 
 	dma_dev = lp->tx_chan->device;
 	sg_len = skb_shinfo(skb)->nr_frags + 1;
-	if (CIRC_SPACE(lp->tx_ring_head, lp->tx_ring_tail, TX_BD_NUM_MAX) <= sg_len) {
+	if (CIRC_SPACE(lp->tx_ring_head, lp->tx_ring_tail, TX_BD_NUM_MAX) <= 1) {
 		netif_stop_queue(ndev);
 		if (net_ratelimit())
 			netdev_warn(ndev, "TX ring unexpectedly full\n");
@@ -927,7 +927,7 @@ axienet_start_xmit_dmaengine(struct sk_buff *skb, struct net_device *ndev)
 	txq = skb_get_tx_queue(lp->ndev, skb);
 	netdev_tx_sent_queue(txq, skb->len);
 	netif_txq_maybe_stop(txq, CIRC_SPACE(lp->tx_ring_head, lp->tx_ring_tail, TX_BD_NUM_MAX),
-			     MAX_SKB_FRAGS + 1, 2 * MAX_SKB_FRAGS);
+			     1, 2);
 
 	dmaengine_submit(dma_tx_desc);
 	dma_async_issue_pending(lp->tx_chan);
@@ -2888,6 +2888,7 @@ static int axienet_probe(struct platform_device *pdev)
 
 	lp->phylink_config.dev = &ndev->dev;
 	lp->phylink_config.type = PHYLINK_NETDEV;
+	lp->phylink_config.mac_managed_pm = true;
 	lp->phylink_config.mac_capabilities = MAC_SYM_PAUSE | MAC_ASYM_PAUSE |
 		MAC_10FD | MAC_100FD | MAC_1000FD;
 
diff --git a/drivers/net/ethernet/xilinx/xilinx_emaclite.c b/drivers/net/ethernet/xilinx/xilinx_emaclite.c
index 940452d0a4d2..258096543b08 100644
--- a/drivers/net/ethernet/xilinx/xilinx_emaclite.c
+++ b/drivers/net/ethernet/xilinx/xilinx_emaclite.c
@@ -285,7 +285,7 @@ static void xemaclite_aligned_read(u32 *src_ptr, u8 *dest_ptr,
 
 		/* Read the remaining data */
 		for (; length > 0; length--)
-			*to_u8_ptr = *from_u8_ptr;
+			*to_u8_ptr++ = *from_u8_ptr++;
 	}
 }
 
diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index ba15a0a4ce62..963fb9261f01 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -1902,21 +1902,9 @@ static void geneve_destroy_tunnels(struct net *net, struct list_head *head)
 {
 	struct geneve_net *gn = net_generic(net, geneve_net_id);
 	struct geneve_dev *geneve, *next;
-	struct net_device *dev, *aux;
 
-	/* gather any geneve devices that were moved into this ns */
-	for_each_netdev_safe(net, dev, aux)
-		if (dev->rtnl_link_ops == &geneve_link_ops)
-			unregister_netdevice_queue(dev, head);
-
-	/* now gather any other geneve devices that were created in this ns */
-	list_for_each_entry_safe(geneve, next, &gn->geneve_list, next) {
-		/* If geneve->dev is in the same netns, it was already added
-		 * to the list by the previous loop.
-		 */
-		if (!net_eq(dev_net(geneve->dev), net))
-			unregister_netdevice_queue(geneve->dev, head);
-	}
+	list_for_each_entry_safe(geneve, next, &gn->geneve_list, next)
+		geneve_dellink(geneve->dev, head);
 }
 
 static void __net_exit geneve_exit_batch_rtnl(struct list_head *net_list,
diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index 47406ce99016..33b78b4007fe 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -2487,11 +2487,6 @@ static void __net_exit gtp_net_exit_batch_rtnl(struct list_head *net_list,
 	list_for_each_entry(net, net_list, exit_list) {
 		struct gtp_net *gn = net_generic(net, gtp_net_id);
 		struct gtp_dev *gtp, *gtp_next;
-		struct net_device *dev;
-
-		for_each_netdev(net, dev)
-			if (dev->rtnl_link_ops == &gtp_link_ops)
-				gtp_dellink(dev, dev_to_kill);
 
 		list_for_each_entry_safe(gtp, gtp_next, &gn->gtp_dev_list, list)
 			gtp_dellink(gtp->dev, dev_to_kill);
diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index e690b95b1bbb..0733493cfa6f 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -158,7 +158,6 @@ struct hv_netvsc_packet {
 	u8 cp_partial; /* partial copy into send buffer */
 
 	u8 rmsg_size; /* RNDIS header and PPI size */
-	u8 rmsg_pgcnt; /* page count of RNDIS header and PPI */
 	u8 page_buf_cnt;
 
 	u16 q_idx;
@@ -893,6 +892,18 @@ struct nvsp_message {
 				 sizeof(struct nvsp_message))
 #define NETVSC_MIN_IN_MSG_SIZE sizeof(struct vmpacket_descriptor)
 
+/* Maximum # of contiguous data ranges that can make up a trasmitted packet.
+ * Typically it's the max SKB fragments plus 2 for the rndis packet and the
+ * linear portion of the SKB. But if MAX_SKB_FRAGS is large, the value may
+ * need to be limited to MAX_PAGE_BUFFER_COUNT, which is the max # of entries
+ * in a GPA direct packet sent to netvsp over VMBus.
+ */
+#if MAX_SKB_FRAGS + 2 < MAX_PAGE_BUFFER_COUNT
+#define MAX_DATA_RANGES (MAX_SKB_FRAGS + 2)
+#else
+#define MAX_DATA_RANGES MAX_PAGE_BUFFER_COUNT
+#endif
+
 /* Estimated requestor size:
  * out_ring_size/min_out_msg_size + in_ring_size/min_in_msg_size
  */
@@ -1050,6 +1061,7 @@ struct net_device_context {
 	struct net_device __rcu *vf_netdev;
 	struct netvsc_vf_pcpu_stats __percpu *vf_stats;
 	struct delayed_work vf_takeover;
+	struct delayed_work vfns_work;
 
 	/* 1: allocated, serial number is valid. 0: not allocated */
 	u32 vf_alloc;
@@ -1064,6 +1076,8 @@ struct net_device_context {
 	struct netvsc_device_info *saved_netvsc_dev_info;
 };
 
+void netvsc_vfns_work(struct work_struct *w);
+
 /* Azure hosts don't support non-TCP port numbers in hashing for fragmented
  * packets. We can use ethtool to change UDP hash level when necessary.
  */
diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index 2b6ec979a62f..807465dd4c8e 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -947,8 +947,7 @@ static void netvsc_copy_to_send_buf(struct netvsc_device *net_device,
 		     + pend_size;
 	int i;
 	u32 padding = 0;
-	u32 page_count = packet->cp_partial ? packet->rmsg_pgcnt :
-		packet->page_buf_cnt;
+	u32 page_count = packet->cp_partial ? 1 : packet->page_buf_cnt;
 	u32 remain;
 
 	/* Add padding */
@@ -1049,6 +1048,42 @@ static int netvsc_dma_map(struct hv_device *hv_dev,
 	return 0;
 }
 
+/* Build an "array" of mpb entries describing the data to be transferred
+ * over VMBus. After the desc header fields, each "array" entry is variable
+ * size, and each entry starts after the end of the previous entry. The
+ * "offset" and "len" fields for each entry imply the size of the entry.
+ *
+ * The pfns are in HV_HYP_PAGE_SIZE, because all communication with Hyper-V
+ * uses that granularity, even if the system page size of the guest is larger.
+ * Each entry in the input "pb" array must describe a contiguous range of
+ * guest physical memory so that the pfns are sequential if the range crosses
+ * a page boundary. The offset field must be < HV_HYP_PAGE_SIZE.
+ */
+static inline void netvsc_build_mpb_array(struct hv_page_buffer *pb,
+				u32 page_buffer_count,
+				struct vmbus_packet_mpb_array *desc,
+				u32 *desc_size)
+{
+	struct hv_mpb_array *mpb_entry = &desc->range;
+	int i, j;
+
+	for (i = 0; i < page_buffer_count; i++) {
+		u32 offset = pb[i].offset;
+		u32 len = pb[i].len;
+
+		mpb_entry->offset = offset;
+		mpb_entry->len = len;
+
+		for (j = 0; j < HVPFN_UP(offset + len); j++)
+			mpb_entry->pfn_array[j] = pb[i].pfn + j;
+
+		mpb_entry = (struct hv_mpb_array *)&mpb_entry->pfn_array[j];
+	}
+
+	desc->rangecount = page_buffer_count;
+	*desc_size = (char *)mpb_entry - (char *)desc;
+}
+
 static inline int netvsc_send_pkt(
 	struct hv_device *device,
 	struct hv_netvsc_packet *packet,
@@ -1091,8 +1126,11 @@ static inline int netvsc_send_pkt(
 
 	packet->dma_range = NULL;
 	if (packet->page_buf_cnt) {
+		struct vmbus_channel_packet_page_buffer desc;
+		u32 desc_size;
+
 		if (packet->cp_partial)
-			pb += packet->rmsg_pgcnt;
+			pb++;
 
 		ret = netvsc_dma_map(ndev_ctx->device_ctx, packet, pb);
 		if (ret) {
@@ -1100,11 +1138,12 @@ static inline int netvsc_send_pkt(
 			goto exit;
 		}
 
-		ret = vmbus_sendpacket_pagebuffer(out_channel,
-						  pb, packet->page_buf_cnt,
-						  &nvmsg, sizeof(nvmsg),
-						  req_id);
-
+		netvsc_build_mpb_array(pb, packet->page_buf_cnt,
+				(struct vmbus_packet_mpb_array *)&desc,
+				 &desc_size);
+		ret = vmbus_sendpacket_mpb_desc(out_channel,
+				(struct vmbus_packet_mpb_array *)&desc,
+				desc_size, &nvmsg, sizeof(nvmsg), req_id);
 		if (ret)
 			netvsc_dma_unmap(ndev_ctx->device_ctx, packet);
 	} else {
@@ -1253,7 +1292,7 @@ int netvsc_send(struct net_device *ndev,
 		packet->send_buf_index = section_index;
 
 		if (packet->cp_partial) {
-			packet->page_buf_cnt -= packet->rmsg_pgcnt;
+			packet->page_buf_cnt--;
 			packet->total_data_buflen = msd_len + packet->rmsg_size;
 		} else {
 			packet->page_buf_cnt = 0;
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 23180f7b67b6..d6fe8b5184a9 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -325,43 +325,10 @@ static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb,
 	return txq;
 }
 
-static u32 fill_pg_buf(unsigned long hvpfn, u32 offset, u32 len,
-		       struct hv_page_buffer *pb)
-{
-	int j = 0;
-
-	hvpfn += offset >> HV_HYP_PAGE_SHIFT;
-	offset = offset & ~HV_HYP_PAGE_MASK;
-
-	while (len > 0) {
-		unsigned long bytes;
-
-		bytes = HV_HYP_PAGE_SIZE - offset;
-		if (bytes > len)
-			bytes = len;
-		pb[j].pfn = hvpfn;
-		pb[j].offset = offset;
-		pb[j].len = bytes;
-
-		offset += bytes;
-		len -= bytes;
-
-		if (offset == HV_HYP_PAGE_SIZE && len) {
-			hvpfn++;
-			offset = 0;
-			j++;
-		}
-	}
-
-	return j + 1;
-}
-
 static u32 init_page_array(void *hdr, u32 len, struct sk_buff *skb,
 			   struct hv_netvsc_packet *packet,
 			   struct hv_page_buffer *pb)
 {
-	u32 slots_used = 0;
-	char *data = skb->data;
 	int frags = skb_shinfo(skb)->nr_frags;
 	int i;
 
@@ -370,28 +337,27 @@ static u32 init_page_array(void *hdr, u32 len, struct sk_buff *skb,
 	 * 2. skb linear data
 	 * 3. skb fragment data
 	 */
-	slots_used += fill_pg_buf(virt_to_hvpfn(hdr),
-				  offset_in_hvpage(hdr),
-				  len,
-				  &pb[slots_used]);
 
+	pb[0].offset = offset_in_hvpage(hdr);
+	pb[0].len = len;
+	pb[0].pfn = virt_to_hvpfn(hdr);
 	packet->rmsg_size = len;
-	packet->rmsg_pgcnt = slots_used;
 
-	slots_used += fill_pg_buf(virt_to_hvpfn(data),
-				  offset_in_hvpage(data),
-				  skb_headlen(skb),
-				  &pb[slots_used]);
+	pb[1].offset = offset_in_hvpage(skb->data);
+	pb[1].len = skb_headlen(skb);
+	pb[1].pfn = virt_to_hvpfn(skb->data);
 
 	for (i = 0; i < frags; i++) {
 		skb_frag_t *frag = skb_shinfo(skb)->frags + i;
+		struct hv_page_buffer *cur_pb = &pb[i + 2];
+		u64 pfn = page_to_hvpfn(skb_frag_page(frag));
+		u32 offset = skb_frag_off(frag);
 
-		slots_used += fill_pg_buf(page_to_hvpfn(skb_frag_page(frag)),
-					  skb_frag_off(frag),
-					  skb_frag_size(frag),
-					  &pb[slots_used]);
+		cur_pb->offset = offset_in_hvpage(offset);
+		cur_pb->len = skb_frag_size(frag);
+		cur_pb->pfn = pfn + (offset >> HV_HYP_PAGE_SHIFT);
 	}
-	return slots_used;
+	return frags + 2;
 }
 
 static int count_skb_frag_slots(struct sk_buff *skb)
@@ -482,7 +448,7 @@ static int netvsc_xmit(struct sk_buff *skb, struct net_device *net, bool xdp_tx)
 	struct net_device *vf_netdev;
 	u32 rndis_msg_size;
 	u32 hash;
-	struct hv_page_buffer pb[MAX_PAGE_BUFFER_COUNT];
+	struct hv_page_buffer pb[MAX_DATA_RANGES];
 
 	/* If VF is present and up then redirect packets to it.
 	 * Skip the VF if it is marked down or has no carrier.
@@ -2350,8 +2316,11 @@ static int netvsc_prepare_bonding(struct net_device *vf_netdev)
 	if (!ndev)
 		return NOTIFY_DONE;
 
-	/* set slave flag before open to prevent IPv6 addrconf */
+	/* Set slave flag and no addrconf flag before open
+	 * to prevent IPv6 addrconf.
+	 */
 	vf_netdev->flags |= IFF_SLAVE;
+	vf_netdev->priv_flags |= IFF_NO_ADDRCONF;
 	return NOTIFY_DONE;
 }
 
@@ -2547,6 +2516,7 @@ static int netvsc_probe(struct hv_device *dev,
 	spin_lock_init(&net_device_ctx->lock);
 	INIT_LIST_HEAD(&net_device_ctx->reconfig_events);
 	INIT_DELAYED_WORK(&net_device_ctx->vf_takeover, netvsc_vf_setup);
+	INIT_DELAYED_WORK(&net_device_ctx->vfns_work, netvsc_vfns_work);
 
 	net_device_ctx->vf_stats
 		= netdev_alloc_pcpu_stats(struct netvsc_vf_pcpu_stats);
@@ -2689,6 +2659,8 @@ static void netvsc_remove(struct hv_device *dev)
 	cancel_delayed_work_sync(&ndev_ctx->dwork);
 
 	rtnl_lock();
+	cancel_delayed_work_sync(&ndev_ctx->vfns_work);
+
 	nvdev = rtnl_dereference(ndev_ctx->nvdev);
 	if (nvdev) {
 		cancel_work_sync(&nvdev->subchan_work);
@@ -2730,6 +2702,7 @@ static int netvsc_suspend(struct hv_device *dev)
 	cancel_delayed_work_sync(&ndev_ctx->dwork);
 
 	rtnl_lock();
+	cancel_delayed_work_sync(&ndev_ctx->vfns_work);
 
 	nvdev = rtnl_dereference(ndev_ctx->nvdev);
 	if (nvdev == NULL) {
@@ -2823,6 +2796,27 @@ static void netvsc_event_set_vf_ns(struct net_device *ndev)
 	}
 }
 
+void netvsc_vfns_work(struct work_struct *w)
+{
+	struct net_device_context *ndev_ctx =
+		container_of(w, struct net_device_context, vfns_work.work);
+	struct net_device *ndev;
+
+	if (!rtnl_trylock()) {
+		schedule_delayed_work(&ndev_ctx->vfns_work, 1);
+		return;
+	}
+
+	ndev = hv_get_drvdata(ndev_ctx->device_ctx);
+	if (!ndev)
+		goto out;
+
+	netvsc_event_set_vf_ns(ndev);
+
+out:
+	rtnl_unlock();
+}
+
 /*
  * On Hyper-V, every VF interface is matched with a corresponding
  * synthetic interface. The synthetic interface is presented first
@@ -2833,10 +2827,12 @@ static int netvsc_netdev_event(struct notifier_block *this,
 			       unsigned long event, void *ptr)
 {
 	struct net_device *event_dev = netdev_notifier_info_to_dev(ptr);
+	struct net_device_context *ndev_ctx;
 	int ret = 0;
 
 	if (event_dev->netdev_ops == &device_ops && event == NETDEV_REGISTER) {
-		netvsc_event_set_vf_ns(event_dev);
+		ndev_ctx = netdev_priv(event_dev);
+		schedule_delayed_work(&ndev_ctx->vfns_work, 0);
 		return NOTIFY_DONE;
 	}
 
diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c
index ecc2128ca9b7..e457f809fe31 100644
--- a/drivers/net/hyperv/rndis_filter.c
+++ b/drivers/net/hyperv/rndis_filter.c
@@ -225,8 +225,7 @@ static int rndis_filter_send_request(struct rndis_device *dev,
 				  struct rndis_request *req)
 {
 	struct hv_netvsc_packet *packet;
-	struct hv_page_buffer page_buf[2];
-	struct hv_page_buffer *pb = page_buf;
+	struct hv_page_buffer pb;
 	int ret;
 
 	/* Setup the packet to send it */
@@ -235,27 +234,14 @@ static int rndis_filter_send_request(struct rndis_device *dev,
 	packet->total_data_buflen = req->request_msg.msg_len;
 	packet->page_buf_cnt = 1;
 
-	pb[0].pfn = virt_to_phys(&req->request_msg) >>
-					HV_HYP_PAGE_SHIFT;
-	pb[0].len = req->request_msg.msg_len;
-	pb[0].offset = offset_in_hvpage(&req->request_msg);
-
-	/* Add one page_buf when request_msg crossing page boundary */
-	if (pb[0].offset + pb[0].len > HV_HYP_PAGE_SIZE) {
-		packet->page_buf_cnt++;
-		pb[0].len = HV_HYP_PAGE_SIZE -
-			pb[0].offset;
-		pb[1].pfn = virt_to_phys((void *)&req->request_msg
-			+ pb[0].len) >> HV_HYP_PAGE_SHIFT;
-		pb[1].offset = 0;
-		pb[1].len = req->request_msg.msg_len -
-			pb[0].len;
-	}
+	pb.pfn = virt_to_phys(&req->request_msg) >> HV_HYP_PAGE_SHIFT;
+	pb.len = req->request_msg.msg_len;
+	pb.offset = offset_in_hvpage(&req->request_msg);
 
 	trace_rndis_send(dev->ndev, 0, &req->request_msg);
 
 	rcu_read_lock_bh();
-	ret = netvsc_send(dev->ndev, packet, NULL, pb, NULL, false);
+	ret = netvsc_send(dev->ndev, packet, NULL, &pb, NULL, false);
 	rcu_read_unlock_bh();
 
 	return ret;
diff --git a/drivers/net/ieee802154/ca8210.c b/drivers/net/ieee802154/ca8210.c
index 753215ebc67c..a036910f6082 100644
--- a/drivers/net/ieee802154/ca8210.c
+++ b/drivers/net/ieee802154/ca8210.c
@@ -1446,8 +1446,7 @@ static u8 mcps_data_request(
 	command.pdata.data_req.src_addr_mode = src_addr_mode;
 	command.pdata.data_req.dst.mode = dst_address_mode;
 	if (dst_address_mode != MAC_MODE_NO_ADDR) {
-		command.pdata.data_req.dst.pan_id[0] = LS_BYTE(dst_pan_id);
-		command.pdata.data_req.dst.pan_id[1] = MS_BYTE(dst_pan_id);
+		put_unaligned_le16(dst_pan_id, command.pdata.data_req.dst.pan_id);
 		if (dst_address_mode == MAC_MODE_SHORT_ADDR) {
 			command.pdata.data_req.dst.address[0] = LS_BYTE(
 				dst_addr->short_address
@@ -1795,12 +1794,12 @@ static int ca8210_skb_rx(
 	}
 	hdr.source.mode = data_ind[0];
 	dev_dbg(&priv->spi->dev, "srcAddrMode: %#03x\n", hdr.source.mode);
-	hdr.source.pan_id = *(u16 *)&data_ind[1];
+	hdr.source.pan_id = cpu_to_le16(get_unaligned_le16(&data_ind[1]));
 	dev_dbg(&priv->spi->dev, "srcPanId: %#06x\n", hdr.source.pan_id);
 	memcpy(&hdr.source.extended_addr, &data_ind[3], 8);
 	hdr.dest.mode = data_ind[11];
 	dev_dbg(&priv->spi->dev, "dstAddrMode: %#03x\n", hdr.dest.mode);
-	hdr.dest.pan_id = *(u16 *)&data_ind[12];
+	hdr.dest.pan_id = cpu_to_le16(get_unaligned_le16(&data_ind[12]));
 	dev_dbg(&priv->spi->dev, "dstPanId: %#06x\n", hdr.dest.pan_id);
 	memcpy(&hdr.dest.extended_addr, &data_ind[14], 8);
 
@@ -1927,7 +1926,7 @@ static int ca8210_skb_tx(
 	status =  mcps_data_request(
 		header.source.mode,
 		header.dest.mode,
-		header.dest.pan_id,
+		le16_to_cpu(header.dest.pan_id),
 		(union macaddr *)&header.dest.extended_addr,
 		skb->len - mac_len,
 		&skb->data[mac_len],
diff --git a/drivers/net/ipa/data/ipa_data-v4.7.c b/drivers/net/ipa/data/ipa_data-v4.7.c
index c8c23d9be961..41f212209993 100644
--- a/drivers/net/ipa/data/ipa_data-v4.7.c
+++ b/drivers/net/ipa/data/ipa_data-v4.7.c
@@ -28,20 +28,18 @@ enum ipa_resource_type {
 enum ipa_rsrc_group_id {
 	/* Source resource group identifiers */
 	IPA_RSRC_GROUP_SRC_UL_DL			= 0,
-	IPA_RSRC_GROUP_SRC_UC_RX_Q,
 	IPA_RSRC_GROUP_SRC_COUNT,	/* Last in set; not a source group */
 
 	/* Destination resource group identifiers */
-	IPA_RSRC_GROUP_DST_UL_DL_DPL			= 0,
-	IPA_RSRC_GROUP_DST_UNUSED_1,
+	IPA_RSRC_GROUP_DST_UL_DL			= 0,
 	IPA_RSRC_GROUP_DST_COUNT,	/* Last; not a destination group */
 };
 
 /* QSB configuration data for an SoC having IPA v4.7 */
 static const struct ipa_qsb_data ipa_qsb_data[] = {
 	[IPA_QSB_MASTER_DDR] = {
-		.max_writes		= 8,
-		.max_reads		= 0,	/* no limit (hardware max) */
+		.max_writes		= 12,
+		.max_reads		= 13,
 		.max_reads_beats	= 120,
 	},
 };
@@ -81,7 +79,7 @@ static const struct ipa_gsi_endpoint_data ipa_gsi_endpoint_data[] = {
 		},
 		.endpoint = {
 			.config = {
-				.resource_group	= IPA_RSRC_GROUP_DST_UL_DL_DPL,
+				.resource_group	= IPA_RSRC_GROUP_DST_UL_DL,
 				.aggregation	= true,
 				.status_enable	= true,
 				.rx = {
@@ -106,6 +104,7 @@ static const struct ipa_gsi_endpoint_data ipa_gsi_endpoint_data[] = {
 			.filter_support	= true,
 			.config = {
 				.resource_group	= IPA_RSRC_GROUP_SRC_UL_DL,
+				.checksum       = true,
 				.qmap		= true,
 				.status_enable	= true,
 				.tx = {
@@ -128,7 +127,8 @@ static const struct ipa_gsi_endpoint_data ipa_gsi_endpoint_data[] = {
 		},
 		.endpoint = {
 			.config = {
-				.resource_group	= IPA_RSRC_GROUP_DST_UL_DL_DPL,
+				.resource_group	= IPA_RSRC_GROUP_DST_UL_DL,
+				.checksum       = true,
 				.qmap		= true,
 				.aggregation	= true,
 				.rx = {
@@ -197,12 +197,12 @@ static const struct ipa_resource ipa_resource_src[] = {
 /* Destination resource configuration data for an SoC having IPA v4.7 */
 static const struct ipa_resource ipa_resource_dst[] = {
 	[IPA_RESOURCE_TYPE_DST_DATA_SECTORS] = {
-		.limits[IPA_RSRC_GROUP_DST_UL_DL_DPL] = {
+		.limits[IPA_RSRC_GROUP_DST_UL_DL] = {
 			.min = 7,	.max = 7,
 		},
 	},
 	[IPA_RESOURCE_TYPE_DST_DPS_DMARS] = {
-		.limits[IPA_RSRC_GROUP_DST_UL_DL_DPL] = {
+		.limits[IPA_RSRC_GROUP_DST_UL_DL] = {
 			.min = 2,	.max = 2,
 		},
 	},
diff --git a/drivers/net/ipa/ipa_sysfs.c b/drivers/net/ipa/ipa_sysfs.c
index a59bd215494c..a53e9e6f6cdf 100644
--- a/drivers/net/ipa/ipa_sysfs.c
+++ b/drivers/net/ipa/ipa_sysfs.c
@@ -37,8 +37,12 @@ static const char *ipa_version_string(struct ipa *ipa)
 		return "4.11";
 	case IPA_VERSION_5_0:
 		return "5.0";
+	case IPA_VERSION_5_1:
+		return "5.1";
+	case IPA_VERSION_5_5:
+		return "5.5";
 	default:
-		return "0.0";	/* Won't happen (checked at probe time) */
+		return "0.0";	/* Should not happen */
 	}
 }
 
diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c
index b1afcb8740de..ca62188a317a 100644
--- a/drivers/net/ipvlan/ipvlan_core.c
+++ b/drivers/net/ipvlan/ipvlan_core.c
@@ -3,6 +3,7 @@
  */
 
 #include <net/inet_dscp.h>
+#include <net/ip.h>
 
 #include "ipvlan.h"
 
@@ -415,20 +416,25 @@ struct ipvl_addr *ipvlan_addr_lookup(struct ipvl_port *port, void *lyr3h,
 
 static noinline_for_stack int ipvlan_process_v4_outbound(struct sk_buff *skb)
 {
-	const struct iphdr *ip4h = ip_hdr(skb);
 	struct net_device *dev = skb->dev;
 	struct net *net = dev_net(dev);
-	struct rtable *rt;
 	int err, ret = NET_XMIT_DROP;
+	const struct iphdr *ip4h;
+	struct rtable *rt;
 	struct flowi4 fl4 = {
 		.flowi4_oif = dev->ifindex,
-		.flowi4_tos = ip4h->tos & INET_DSCP_MASK,
 		.flowi4_flags = FLOWI_FLAG_ANYSRC,
 		.flowi4_mark = skb->mark,
-		.daddr = ip4h->daddr,
-		.saddr = ip4h->saddr,
 	};
 
+	if (!pskb_network_may_pull(skb, sizeof(struct iphdr)))
+		goto err;
+
+	ip4h = ip_hdr(skb);
+	fl4.daddr = ip4h->daddr;
+	fl4.saddr = ip4h->saddr;
+	fl4.flowi4_tos = inet_dscp_to_dsfield(ip4h_dscp(ip4h));
+
 	rt = ip_route_output_flow(net, &fl4, NULL);
 	if (IS_ERR(rt))
 		goto err;
@@ -487,6 +493,12 @@ static int ipvlan_process_v6_outbound(struct sk_buff *skb)
 	struct net_device *dev = skb->dev;
 	int err, ret = NET_XMIT_DROP;
 
+	if (!pskb_network_may_pull(skb, sizeof(struct ipv6hdr))) {
+		DEV_STATS_INC(dev, tx_errors);
+		kfree_skb(skb);
+		return ret;
+	}
+
 	err = ipvlan_route_v6_outbound(dev, skb);
 	if (unlikely(err)) {
 		DEV_STATS_INC(dev, tx_errors);
diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c
index 1993b90b1a5f..491e56b3263f 100644
--- a/drivers/net/loopback.c
+++ b/drivers/net/loopback.c
@@ -244,8 +244,22 @@ static netdev_tx_t blackhole_netdev_xmit(struct sk_buff *skb,
 	return NETDEV_TX_OK;
 }
 
+static int blackhole_neigh_output(struct neighbour *n, struct sk_buff *skb)
+{
+	kfree_skb(skb);
+	return 0;
+}
+
+static int blackhole_neigh_construct(struct net_device *dev,
+				     struct neighbour *n)
+{
+	n->output = blackhole_neigh_output;
+	return 0;
+}
+
 static const struct net_device_ops blackhole_netdev_ops = {
 	.ndo_start_xmit = blackhole_netdev_xmit,
+	.ndo_neigh_construct = blackhole_neigh_construct,
 };
 
 /* This is a dst-dummy device used specifically for invalidated
diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index ee2159282573..090a56a5e456 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -246,15 +246,39 @@ static sci_t make_sci(const u8 *addr, __be16 port)
 	return sci;
 }
 
-static sci_t macsec_frame_sci(struct macsec_eth_header *hdr, bool sci_present)
+static sci_t macsec_active_sci(struct macsec_secy *secy)
 {
-	sci_t sci;
+	struct macsec_rx_sc *rx_sc = rcu_dereference_bh(secy->rx_sc);
+
+	/* Case single RX SC */
+	if (rx_sc && !rcu_dereference_bh(rx_sc->next))
+		return (rx_sc->active) ? rx_sc->sci : 0;
+	/* Case no RX SC or multiple */
+	else
+		return 0;
+}
+
+static sci_t macsec_frame_sci(struct macsec_eth_header *hdr, bool sci_present,
+			      struct macsec_rxh_data *rxd)
+{
+	struct macsec_dev *macsec;
+	sci_t sci = 0;
 
-	if (sci_present)
+	/* SC = 1 */
+	if (sci_present) {
 		memcpy(&sci, hdr->secure_channel_id,
 		       sizeof(hdr->secure_channel_id));
-	else
+	/* SC = 0; ES = 0 */
+	} else if ((!(hdr->tci_an & (MACSEC_TCI_ES | MACSEC_TCI_SC))) &&
+		   (list_is_singular(&rxd->secys))) {
+		/* Only one SECY should exist on this scenario */
+		macsec = list_first_or_null_rcu(&rxd->secys, struct macsec_dev,
+						secys);
+		if (macsec)
+			return macsec_active_sci(&macsec->secy);
+	} else {
 		sci = make_sci(hdr->eth.h_source, MACSEC_PORT_ES);
+	}
 
 	return sci;
 }
@@ -1108,7 +1132,7 @@ static rx_handler_result_t macsec_handle_frame(struct sk_buff **pskb)
 	struct macsec_rxh_data *rxd;
 	struct macsec_dev *macsec;
 	unsigned int len;
-	sci_t sci;
+	sci_t sci = 0;
 	u32 hdr_pn;
 	bool cbit;
 	struct pcpu_rx_sc_stats *rxsc_stats;
@@ -1155,11 +1179,14 @@ static rx_handler_result_t macsec_handle_frame(struct sk_buff **pskb)
 
 	macsec_skb_cb(skb)->has_sci = !!(hdr->tci_an & MACSEC_TCI_SC);
 	macsec_skb_cb(skb)->assoc_num = hdr->tci_an & MACSEC_AN_MASK;
-	sci = macsec_frame_sci(hdr, macsec_skb_cb(skb)->has_sci);
 
 	rcu_read_lock();
 	rxd = macsec_data_rcu(skb->dev);
 
+	sci = macsec_frame_sci(hdr, macsec_skb_cb(skb)->has_sci, rxd);
+	if (!sci)
+		goto drop_nosc;
+
 	list_for_each_entry_rcu(macsec, &rxd->secys, secys) {
 		struct macsec_rx_sc *sc = find_rx_sc(&macsec->secy, sci);
 
@@ -1282,6 +1309,7 @@ drop:
 	macsec_rxsa_put(rx_sa);
 drop_nosa:
 	macsec_rxsc_put(rx_sc);
+drop_nosc:
 	rcu_read_unlock();
 drop_direct:
 	kfree_skb(skb);
diff --git a/drivers/net/mctp/mctp-i2c.c b/drivers/net/mctp/mctp-i2c.c
index e70fb6687994..503a9174321c 100644
--- a/drivers/net/mctp/mctp-i2c.c
+++ b/drivers/net/mctp/mctp-i2c.c
@@ -538,7 +538,7 @@ static void mctp_i2c_xmit(struct mctp_i2c_dev *midev, struct sk_buff *skb)
 		rc = __i2c_transfer(midev->adapter, &msg, 1);
 
 		/* on tx errors, the flow can no longer be considered valid */
-		if (rc)
+		if (rc < 0)
 			mctp_i2c_invalidate_tx_flow(midev, skb);
 
 		break;
@@ -584,6 +584,7 @@ static int mctp_i2c_header_create(struct sk_buff *skb, struct net_device *dev,
 	struct mctp_i2c_hdr *hdr;
 	struct mctp_hdr *mhdr;
 	u8 lldst, llsrc;
+	int rc;
 
 	if (len > MCTP_I2C_MAXMTU)
 		return -EMSGSIZE;
@@ -594,6 +595,10 @@ static int mctp_i2c_header_create(struct sk_buff *skb, struct net_device *dev,
 	lldst = *((u8 *)daddr);
 	llsrc = *((u8 *)saddr);
 
+	rc = skb_cow_head(skb, sizeof(struct mctp_i2c_hdr));
+	if (rc)
+		return rc;
+
 	skb_push(skb, sizeof(struct mctp_i2c_hdr));
 	skb_reset_mac_header(skb);
 	hdr = (void *)skb_mac_header(skb);
diff --git a/drivers/net/mctp/mctp-i3c.c b/drivers/net/mctp/mctp-i3c.c
index ee9d562f0817..47513ebbc680 100644
--- a/drivers/net/mctp/mctp-i3c.c
+++ b/drivers/net/mctp/mctp-i3c.c
@@ -506,6 +506,14 @@ static int mctp_i3c_header_create(struct sk_buff *skb, struct net_device *dev,
 	   const void *saddr, unsigned int len)
 {
 	struct mctp_i3c_internal_hdr *ihdr;
+	int rc;
+
+	if (!daddr || !saddr)
+		return -EINVAL;
+
+	rc = skb_cow_head(skb, sizeof(struct mctp_i3c_internal_hdr));
+	if (rc)
+		return rc;
 
 	skb_push(skb, sizeof(struct mctp_i3c_internal_hdr));
 	skb_reset_mac_header(skb);
diff --git a/drivers/net/mdio/mdio-bcm-unimac.c b/drivers/net/mdio/mdio-bcm-unimac.c
index b7bc70586ee0..369540b43ada 100644
--- a/drivers/net/mdio/mdio-bcm-unimac.c
+++ b/drivers/net/mdio/mdio-bcm-unimac.c
@@ -209,10 +209,9 @@ static int unimac_mdio_clk_set(struct unimac_mdio_priv *priv)
 	if (ret)
 		return ret;
 
-	if (!priv->clk)
+	rate = clk_get_rate(priv->clk);
+	if (!rate)
 		rate = 250000000;
-	else
-		rate = clk_get_rate(priv->clk);
 
 	div = (rate / (2 * priv->clk_freq)) - 1;
 	if (div & ~MDIO_CLK_DIV_MASK) {
diff --git a/drivers/net/mdio/mdio-mux-meson-gxl.c b/drivers/net/mdio/mdio-mux-meson-gxl.c
index 89554021b5cc..f9f02d313649 100644
--- a/drivers/net/mdio/mdio-mux-meson-gxl.c
+++ b/drivers/net/mdio/mdio-mux-meson-gxl.c
@@ -17,6 +17,7 @@
 #define  REG2_LEDACT		GENMASK(23, 22)
 #define  REG2_LEDLINK		GENMASK(25, 24)
 #define  REG2_DIV4SEL		BIT(27)
+#define  REG2_REVERSED		BIT(28)
 #define  REG2_ADCBYPASS		BIT(30)
 #define  REG2_CLKINSEL		BIT(31)
 #define ETH_REG3		0x4
@@ -65,7 +66,7 @@ static void gxl_enable_internal_mdio(struct gxl_mdio_mux *priv)
 	 * The only constraint is that it must match the one in
 	 * drivers/net/phy/meson-gxl.c to properly match the PHY.
 	 */
-	writel(FIELD_PREP(REG2_PHYID, EPHY_GXL_ID),
+	writel(REG2_REVERSED | FIELD_PREP(REG2_PHYID, EPHY_GXL_ID),
 	       priv->regs + ETH_REG2);
 
 	/* Enable the internal phy */
diff --git a/drivers/net/netdevsim/ipsec.c b/drivers/net/netdevsim/ipsec.c
index 3612b0633bd1..88187dd4eb2d 100644
--- a/drivers/net/netdevsim/ipsec.c
+++ b/drivers/net/netdevsim/ipsec.c
@@ -39,10 +39,14 @@ static ssize_t nsim_dbg_netdev_ops_read(struct file *filp,
 		if (!sap->used)
 			continue;
 
-		p += scnprintf(p, bufsize - (p - buf),
-			       "sa[%i] %cx ipaddr=0x%08x %08x %08x %08x\n",
-			       i, (sap->rx ? 'r' : 't'), sap->ipaddr[0],
-			       sap->ipaddr[1], sap->ipaddr[2], sap->ipaddr[3]);
+		if (sap->xs->props.family == AF_INET6)
+			p += scnprintf(p, bufsize - (p - buf),
+				       "sa[%i] %cx ipaddr=%pI6c\n",
+				       i, (sap->rx ? 'r' : 't'), &sap->ipaddr);
+		else
+			p += scnprintf(p, bufsize - (p - buf),
+				       "sa[%i] %cx ipaddr=%pI4\n",
+				       i, (sap->rx ? 'r' : 't'), &sap->ipaddr[3]);
 		p += scnprintf(p, bufsize - (p - buf),
 			       "sa[%i]    spi=0x%08x proto=0x%x salt=0x%08x crypt=%d\n",
 			       i, be32_to_cpu(sap->xs->id.spi),
diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c
index 1b29d1d794a2..ee2a7b2f6268 100644
--- a/drivers/net/netdevsim/netdev.c
+++ b/drivers/net/netdevsim/netdev.c
@@ -25,6 +25,7 @@
 #include <net/pkt_cls.h>
 #include <net/rtnetlink.h>
 #include <net/udp_tunnel.h>
+#include <net/busy_poll.h>
 
 #include "netdevsim.h"
 
@@ -341,6 +342,7 @@ static int nsim_rcv(struct nsim_rq *rq, int budget)
 			break;
 
 		skb = skb_dequeue(&rq->skb_queue);
+		skb_mark_napi_id(skb, &rq->napi);
 		netif_receive_skb(skb);
 	}
 
@@ -353,7 +355,8 @@ static int nsim_poll(struct napi_struct *napi, int budget)
 	int done;
 
 	done = nsim_rcv(rq, budget);
-	napi_complete(napi);
+	if (done < budget)
+		napi_complete_done(napi, done);
 
 	return done;
 }
diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h
index bf02efa10956..84181dcb9883 100644
--- a/drivers/net/netdevsim/netdevsim.h
+++ b/drivers/net/netdevsim/netdevsim.h
@@ -129,6 +129,7 @@ struct netdevsim {
 		u32 sleep;
 		u32 __ports[2][NSIM_UDP_TUNNEL_N_PORTS];
 		u32 (*ports)[NSIM_UDP_TUNNEL_N_PORTS];
+		struct dentry *ddir;
 		struct debugfs_u32_array dfs_ports[2];
 	} udp_ports;
 
diff --git a/drivers/net/netdevsim/udp_tunnels.c b/drivers/net/netdevsim/udp_tunnels.c
index 02dc3123eb6c..640b4983a9a0 100644
--- a/drivers/net/netdevsim/udp_tunnels.c
+++ b/drivers/net/netdevsim/udp_tunnels.c
@@ -112,9 +112,11 @@ nsim_udp_tunnels_info_reset_write(struct file *file, const char __user *data,
 	struct net_device *dev = file->private_data;
 	struct netdevsim *ns = netdev_priv(dev);
 
-	memset(ns->udp_ports.ports, 0, sizeof(ns->udp_ports.__ports));
 	rtnl_lock();
-	udp_tunnel_nic_reset_ntf(dev);
+	if (dev->reg_state == NETREG_REGISTERED) {
+		memset(ns->udp_ports.ports, 0, sizeof(ns->udp_ports.__ports));
+		udp_tunnel_nic_reset_ntf(dev);
+	}
 	rtnl_unlock();
 
 	return count;
@@ -144,23 +146,23 @@ int nsim_udp_tunnels_info_create(struct nsim_dev *nsim_dev,
 	else
 		ns->udp_ports.ports = nsim_dev->udp_ports.__ports;
 
-	debugfs_create_u32("udp_ports_inject_error", 0600,
-			   ns->nsim_dev_port->ddir,
+	ns->udp_ports.ddir = debugfs_create_dir("udp_ports",
+						ns->nsim_dev_port->ddir);
+
+	debugfs_create_u32("inject_error", 0600, ns->udp_ports.ddir,
 			   &ns->udp_ports.inject_error);
 
 	ns->udp_ports.dfs_ports[0].array = ns->udp_ports.ports[0];
 	ns->udp_ports.dfs_ports[0].n_elements = NSIM_UDP_TUNNEL_N_PORTS;
-	debugfs_create_u32_array("udp_ports_table0", 0400,
-				 ns->nsim_dev_port->ddir,
+	debugfs_create_u32_array("table0", 0400, ns->udp_ports.ddir,
 				 &ns->udp_ports.dfs_ports[0]);
 
 	ns->udp_ports.dfs_ports[1].array = ns->udp_ports.ports[1];
 	ns->udp_ports.dfs_ports[1].n_elements = NSIM_UDP_TUNNEL_N_PORTS;
-	debugfs_create_u32_array("udp_ports_table1", 0400,
-				 ns->nsim_dev_port->ddir,
+	debugfs_create_u32_array("table1", 0400, ns->udp_ports.ddir,
 				 &ns->udp_ports.dfs_ports[1]);
 
-	debugfs_create_file("udp_ports_reset", 0200, ns->nsim_dev_port->ddir,
+	debugfs_create_file("reset", 0200, ns->udp_ports.ddir,
 			    dev, &nsim_udp_tunnels_info_reset_fops);
 
 	/* Note: it's not normal to allocate the info struct like this!
@@ -196,6 +198,9 @@ int nsim_udp_tunnels_info_create(struct nsim_dev *nsim_dev,
 
 void nsim_udp_tunnels_info_destroy(struct net_device *dev)
 {
+	struct netdevsim *ns = netdev_priv(dev);
+
+	debugfs_remove_recursive(ns->udp_ports.ddir);
 	kfree(dev->udp_tunnel_nic_info);
 	dev->udp_tunnel_nic_info = NULL;
 }
diff --git a/drivers/net/pcs/pcs-xpcs-plat.c b/drivers/net/pcs/pcs-xpcs-plat.c
index 629315f1e57c..9dcaf7a66113 100644
--- a/drivers/net/pcs/pcs-xpcs-plat.c
+++ b/drivers/net/pcs/pcs-xpcs-plat.c
@@ -66,7 +66,7 @@ static int xpcs_mmio_read_reg_indirect(struct dw_xpcs_plat *pxpcs,
 	switch (pxpcs->reg_width) {
 	case 4:
 		writel(page, pxpcs->reg_base + (DW_VR_CSR_VIEWPORT << 2));
-		ret = readl(pxpcs->reg_base + (ofs << 2));
+		ret = readl(pxpcs->reg_base + (ofs << 2)) & 0xffff;
 		break;
 	default:
 		writew(page, pxpcs->reg_base + (DW_VR_CSR_VIEWPORT << 1));
@@ -124,7 +124,7 @@ static int xpcs_mmio_read_reg_direct(struct dw_xpcs_plat *pxpcs,
 
 	switch (pxpcs->reg_width) {
 	case 4:
-		ret = readl(pxpcs->reg_base + (csr << 2));
+		ret = readl(pxpcs->reg_base + (csr << 2)) & 0xffff;
 		break;
 	default:
 		ret = readw(pxpcs->reg_base + (csr << 1));
diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c
index ddded162c44c..9260c822e467 100644
--- a/drivers/net/phy/broadcom.c
+++ b/drivers/net/phy/broadcom.c
@@ -655,7 +655,7 @@ static int bcm5481x_read_abilities(struct phy_device *phydev)
 {
 	struct device_node *np = phydev->mdio.dev.of_node;
 	struct bcm54xx_phy_priv *priv = phydev->priv;
-	int i, val, err;
+	int i, val, err, aneg;
 
 	for (i = 0; i < ARRAY_SIZE(bcm54811_linkmodes); i++)
 		linkmode_clear_bit(bcm54811_linkmodes[i], phydev->supported);
@@ -676,9 +676,19 @@ static int bcm5481x_read_abilities(struct phy_device *phydev)
 		if (val < 0)
 			return val;
 
+		/* BCM54811 is not capable of LDS but the corresponding bit
+		 * in LRESR is set to 1 and marked "Ignore" in the datasheet.
+		 * So we must read the bcm54811 as unable to auto-negotiate
+		 * in BroadR-Reach mode.
+		 */
+		if (BRCM_PHY_MODEL(phydev) == PHY_ID_BCM54811)
+			aneg = 0;
+		else
+			aneg = val & LRESR_LDSABILITY;
+
 		linkmode_mod_bit(ETHTOOL_LINK_MODE_Autoneg_BIT,
 				 phydev->supported,
-				 val & LRESR_LDSABILITY);
+				 aneg);
 		linkmode_mod_bit(ETHTOOL_LINK_MODE_100baseT1_Full_BIT,
 				 phydev->supported,
 				 val & LRESR_100_1PAIR);
@@ -735,8 +745,15 @@ static int bcm54811_config_aneg(struct phy_device *phydev)
 
 	/* Aneg firstly. */
 	if (priv->brr_mode) {
-		/* BCM54811 is only capable of autonegotiation in IEEE mode */
-		phydev->autoneg = 0;
+		/* BCM54811 is only capable of autonegotiation in IEEE mode.
+		 * In BroadR-Reach mode, disable the Long Distance Signaling,
+		 * the BRR mode autoneg as supported in other Broadcom PHYs.
+		 * This bit is marked as "Reserved" and "Default 1, must be
+		 *  written to 0 after every device reset" in the datasheet.
+		 */
+		ret = phy_modify(phydev, MII_BCM54XX_LRECR, LRECR_LDSEN, 0);
+		if (ret < 0)
+			return ret;
 		ret = bcm_config_lre_aneg(phydev, false);
 	} else {
 		ret = genphy_config_aneg(phydev);
@@ -859,7 +876,7 @@ static int brcm_fet_config_init(struct phy_device *phydev)
 		return reg;
 
 	/* Unmask events we are interested in and mask interrupts globally. */
-	if (phydev->phy_id == PHY_ID_BCM5221)
+	if (phydev->drv->phy_id == PHY_ID_BCM5221)
 		reg = MII_BRCM_FET_IR_ENABLE |
 		      MII_BRCM_FET_IR_MASK;
 	else
@@ -888,7 +905,7 @@ static int brcm_fet_config_init(struct phy_device *phydev)
 		return err;
 	}
 
-	if (phydev->phy_id != PHY_ID_BCM5221) {
+	if (phydev->drv->phy_id != PHY_ID_BCM5221) {
 		/* Set the LED mode */
 		reg = __phy_read(phydev, MII_BRCM_FET_SHDW_AUXMODE4);
 		if (reg < 0) {
@@ -1009,7 +1026,7 @@ static int brcm_fet_suspend(struct phy_device *phydev)
 		return err;
 	}
 
-	if (phydev->phy_id == PHY_ID_BCM5221)
+	if (phydev->drv->phy_id == PHY_ID_BCM5221)
 		/* Force Low Power Mode with clock enabled */
 		reg = BCM5221_SHDW_AM4_EN_CLK_LPM | BCM5221_SHDW_AM4_FORCE_LPM;
 	else
diff --git a/drivers/net/phy/marvell-88q2xxx.c b/drivers/net/phy/marvell-88q2xxx.c
index c812f16eaa3a..b3a5a0af19da 100644
--- a/drivers/net/phy/marvell-88q2xxx.c
+++ b/drivers/net/phy/marvell-88q2xxx.c
@@ -95,6 +95,10 @@
 
 #define MDIO_MMD_PCS_MV_TDR_OFF_CUTOFF			65246
 
+struct mv88q2xxx_priv {
+	bool enable_temp;
+};
+
 struct mmd_val {
 	int devad;
 	u32 regnum;
@@ -669,17 +673,12 @@ static const struct hwmon_chip_info mv88q2xxx_hwmon_chip_info = {
 
 static int mv88q2xxx_hwmon_probe(struct phy_device *phydev)
 {
+	struct mv88q2xxx_priv *priv = phydev->priv;
 	struct device *dev = &phydev->mdio.dev;
 	struct device *hwmon;
 	char *hwmon_name;
-	int ret;
-
-	/* Enable temperature sense */
-	ret = phy_modify_mmd(phydev, MDIO_MMD_PCS, MDIO_MMD_PCS_MV_TEMP_SENSOR2,
-			     MDIO_MMD_PCS_MV_TEMP_SENSOR2_DIS_MASK, 0);
-	if (ret < 0)
-		return ret;
 
+	priv->enable_temp = true;
 	hwmon_name = devm_hwmon_sanitize_name(dev, dev_name(dev));
 	if (IS_ERR(hwmon_name))
 		return PTR_ERR(hwmon_name);
@@ -702,6 +701,14 @@ static int mv88q2xxx_hwmon_probe(struct phy_device *phydev)
 
 static int mv88q2xxx_probe(struct phy_device *phydev)
 {
+	struct mv88q2xxx_priv *priv;
+
+	priv = devm_kzalloc(&phydev->mdio.dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	phydev->priv = priv;
+
 	return mv88q2xxx_hwmon_probe(phydev);
 }
 
@@ -792,6 +799,18 @@ static int mv88q222x_revb1_revb2_config_init(struct phy_device *phydev)
 
 static int mv88q222x_config_init(struct phy_device *phydev)
 {
+	struct mv88q2xxx_priv *priv = phydev->priv;
+	int ret;
+
+	/* Enable temperature sense */
+	if (priv->enable_temp) {
+		ret = phy_modify_mmd(phydev, MDIO_MMD_PCS,
+				     MDIO_MMD_PCS_MV_TEMP_SENSOR2,
+				     MDIO_MMD_PCS_MV_TEMP_SENSOR2_DIS_MASK, 0);
+		if (ret < 0)
+			return ret;
+	}
+
 	if (phydev->c45_ids.device_ids[MDIO_MMD_PMAPMD] == PHY_ID_88Q2220_REVB0)
 		return mv88q222x_revb0_config_init(phydev);
 	else
diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c
index 7e2f10182c0c..591e8fd33d8e 100644
--- a/drivers/net/phy/mdio_bus.c
+++ b/drivers/net/phy/mdio_bus.c
@@ -889,6 +889,9 @@ int __mdiobus_read(struct mii_bus *bus, int addr, u32 regnum)
 
 	lockdep_assert_held_once(&bus->mdio_lock);
 
+	if (addr >= PHY_MAX_ADDR)
+		return -ENXIO;
+
 	if (bus->read)
 		retval = bus->read(bus, addr, regnum);
 	else
@@ -918,6 +921,9 @@ int __mdiobus_write(struct mii_bus *bus, int addr, u32 regnum, u16 val)
 
 	lockdep_assert_held_once(&bus->mdio_lock);
 
+	if (addr >= PHY_MAX_ADDR)
+		return -ENXIO;
+
 	if (bus->write)
 		err = bus->write(bus, addr, regnum, val);
 	else
@@ -979,6 +985,9 @@ int __mdiobus_c45_read(struct mii_bus *bus, int addr, int devad, u32 regnum)
 
 	lockdep_assert_held_once(&bus->mdio_lock);
 
+	if (addr >= PHY_MAX_ADDR)
+		return -ENXIO;
+
 	if (bus->read_c45)
 		retval = bus->read_c45(bus, addr, devad, regnum);
 	else
@@ -1010,6 +1019,9 @@ int __mdiobus_c45_write(struct mii_bus *bus, int addr, int devad, u32 regnum,
 
 	lockdep_assert_held_once(&bus->mdio_lock);
 
+	if (addr >= PHY_MAX_ADDR)
+		return -ENXIO;
+
 	if (bus->write_c45)
 		err = bus->write_c45(bus, addr, devad, regnum, val);
 	else
diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index 64926240b007..92e9eb4146d9 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -470,6 +470,8 @@ static const struct kszphy_type ksz8051_type = {
 
 static const struct kszphy_type ksz8081_type = {
 	.led_mode_reg		= MII_KSZPHY_CTRL_2,
+	.cable_diag_reg		= KSZ8081_LMD,
+	.pair_mask		= KSZPHY_WIRE_PAIR_MASK,
 	.has_broadcast_disable	= true,
 	.has_nand_tree_disable	= true,
 	.has_rmii_ref_clk_sel	= true,
@@ -5392,6 +5394,14 @@ static int lan8841_suspend(struct phy_device *phydev)
 	return kszphy_generic_suspend(phydev);
 }
 
+static int ksz9131_resume(struct phy_device *phydev)
+{
+	if (phydev->suspended && phy_interface_is_rgmii(phydev))
+		ksz9131_config_rgmii_delay(phydev);
+
+	return kszphy_resume(phydev);
+}
+
 static struct phy_driver ksphy_driver[] = {
 {
 	.phy_id		= PHY_ID_KS8737,
@@ -5637,7 +5647,7 @@ static struct phy_driver ksphy_driver[] = {
 	.get_strings	= kszphy_get_strings,
 	.get_stats	= kszphy_get_stats,
 	.suspend	= kszphy_suspend,
-	.resume		= kszphy_resume,
+	.resume		= ksz9131_resume,
 	.cable_test_start	= ksz9x31_cable_test_start,
 	.cable_test_get_status	= ksz9x31_cable_test_get_status,
 	.get_features	= ksz9477_get_features,
diff --git a/drivers/net/phy/microchip.c b/drivers/net/phy/microchip.c
index 691969a4910f..ffca1cec4ec9 100644
--- a/drivers/net/phy/microchip.c
+++ b/drivers/net/phy/microchip.c
@@ -37,47 +37,6 @@ static int lan88xx_write_page(struct phy_device *phydev, int page)
 	return __phy_write(phydev, LAN88XX_EXT_PAGE_ACCESS, page);
 }
 
-static int lan88xx_phy_config_intr(struct phy_device *phydev)
-{
-	int rc;
-
-	if (phydev->interrupts == PHY_INTERRUPT_ENABLED) {
-		/* unmask all source and clear them before enable */
-		rc = phy_write(phydev, LAN88XX_INT_MASK, 0x7FFF);
-		rc = phy_read(phydev, LAN88XX_INT_STS);
-		rc = phy_write(phydev, LAN88XX_INT_MASK,
-			       LAN88XX_INT_MASK_MDINTPIN_EN_ |
-			       LAN88XX_INT_MASK_LINK_CHANGE_);
-	} else {
-		rc = phy_write(phydev, LAN88XX_INT_MASK, 0);
-		if (rc)
-			return rc;
-
-		/* Ack interrupts after they have been disabled */
-		rc = phy_read(phydev, LAN88XX_INT_STS);
-	}
-
-	return rc < 0 ? rc : 0;
-}
-
-static irqreturn_t lan88xx_handle_interrupt(struct phy_device *phydev)
-{
-	int irq_status;
-
-	irq_status = phy_read(phydev, LAN88XX_INT_STS);
-	if (irq_status < 0) {
-		phy_error(phydev);
-		return IRQ_NONE;
-	}
-
-	if (!(irq_status & LAN88XX_INT_STS_LINK_CHANGE_))
-		return IRQ_NONE;
-
-	phy_trigger_machine(phydev);
-
-	return IRQ_HANDLED;
-}
-
 static int lan88xx_suspend(struct phy_device *phydev)
 {
 	struct lan88xx_priv *priv = phydev->priv;
@@ -373,7 +332,7 @@ static void lan88xx_link_change_notify(struct phy_device *phydev)
 	 * As workaround, set to 10 before setting to 100
 	 * at forced 100 F/H mode.
 	 */
-	if (!phydev->autoneg && phydev->speed == 100) {
+	if (phydev->state == PHY_NOLINK && !phydev->autoneg && phydev->speed == 100) {
 		/* disable phy interrupt */
 		temp = phy_read(phydev, LAN88XX_INT_MASK);
 		temp &= ~LAN88XX_INT_MASK_MDINTPIN_EN_;
@@ -527,9 +486,11 @@ static struct phy_driver microchip_phy_driver[] = {
 	.config_init	= lan88xx_config_init,
 	.config_aneg	= lan88xx_config_aneg,
 	.link_change_notify = lan88xx_link_change_notify,
+	.soft_reset	= genphy_soft_reset,
 
-	.config_intr	= lan88xx_phy_config_intr,
-	.handle_interrupt = lan88xx_handle_interrupt,
+	/* Interrupt handling is broken, do not define related
+	 * functions to force polling.
+	 */
 
 	.suspend	= lan88xx_suspend,
 	.resume		= genphy_resume,
diff --git a/drivers/net/phy/mscc/mscc_ptp.c b/drivers/net/phy/mscc/mscc_ptp.c
index 738a8822fcf0..bce6cc5b04ee 100644
--- a/drivers/net/phy/mscc/mscc_ptp.c
+++ b/drivers/net/phy/mscc/mscc_ptp.c
@@ -897,6 +897,7 @@ static int vsc85xx_eth1_conf(struct phy_device *phydev, enum ts_blk blk,
 				     get_unaligned_be32(ptp_multicast));
 	} else {
 		val |= ANA_ETH1_FLOW_ADDR_MATCH2_ANY_MULTICAST;
+		val |= ANA_ETH1_FLOW_ADDR_MATCH2_ANY_UNICAST;
 		vsc85xx_ts_write_csr(phydev, blk,
 				     MSCC_ANA_ETH1_FLOW_ADDR_MATCH2(0), val);
 		vsc85xx_ts_write_csr(phydev, blk,
@@ -943,7 +944,9 @@ static int vsc85xx_ip1_conf(struct phy_device *phydev, enum ts_blk blk,
 	/* UDP checksum offset in IPv4 packet
 	 * according to: https://tools.ietf.org/html/rfc768
 	 */
-	val |= IP1_NXT_PROT_UDP_CHKSUM_OFF(26) | IP1_NXT_PROT_UDP_CHKSUM_CLEAR;
+	val |= IP1_NXT_PROT_UDP_CHKSUM_OFF(26);
+	if (enable)
+		val |= IP1_NXT_PROT_UDP_CHKSUM_CLEAR;
 	vsc85xx_ts_write_csr(phydev, blk, MSCC_ANA_IP1_NXT_PROT_UDP_CHKSUM,
 			     val);
 
@@ -1163,18 +1166,24 @@ static void vsc85xx_txtstamp(struct mii_timestamper *mii_ts,
 		container_of(mii_ts, struct vsc8531_private, mii_ts);
 
 	if (!vsc8531->ptp->configured)
-		return;
+		goto out;
 
-	if (vsc8531->ptp->tx_type == HWTSTAMP_TX_OFF) {
-		kfree_skb(skb);
-		return;
-	}
+	if (vsc8531->ptp->tx_type == HWTSTAMP_TX_OFF)
+		goto out;
+
+	if (vsc8531->ptp->tx_type == HWTSTAMP_TX_ONESTEP_SYNC)
+		if (ptp_msg_is_sync(skb, type))
+			goto out;
 
 	skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
 
 	mutex_lock(&vsc8531->ts_lock);
 	__skb_queue_tail(&vsc8531->ptp->tx_queue, skb);
 	mutex_unlock(&vsc8531->ts_lock);
+	return;
+
+out:
+	kfree_skb(skb);
 }
 
 static bool vsc85xx_rxtstamp(struct mii_timestamper *mii_ts,
diff --git a/drivers/net/phy/mscc/mscc_ptp.h b/drivers/net/phy/mscc/mscc_ptp.h
index da3465360e90..ae9ad925bfa8 100644
--- a/drivers/net/phy/mscc/mscc_ptp.h
+++ b/drivers/net/phy/mscc/mscc_ptp.h
@@ -98,6 +98,7 @@
 #define MSCC_ANA_ETH1_FLOW_ADDR_MATCH2(x) (MSCC_ANA_ETH1_FLOW_ENA(x) + 3)
 #define ANA_ETH1_FLOW_ADDR_MATCH2_MASK_MASK	GENMASK(22, 20)
 #define ANA_ETH1_FLOW_ADDR_MATCH2_ANY_MULTICAST	0x400000
+#define ANA_ETH1_FLOW_ADDR_MATCH2_ANY_UNICAST	0x200000
 #define ANA_ETH1_FLOW_ADDR_MATCH2_FULL_ADDR	0x100000
 #define ANA_ETH1_FLOW_ADDR_MATCH2_SRC_DEST_MASK	GENMASK(17, 16)
 #define ANA_ETH1_FLOW_ADDR_MATCH2_SRC_DEST	0x020000
diff --git a/drivers/net/phy/nxp-c45-tja11xx.c b/drivers/net/phy/nxp-c45-tja11xx.c
index 5af5ade4fc64..99a5eee77bec 100644
--- a/drivers/net/phy/nxp-c45-tja11xx.c
+++ b/drivers/net/phy/nxp-c45-tja11xx.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /* NXP C45 PHY driver
- * Copyright 2021-2023 NXP
+ * Copyright 2021-2025 NXP
  * Author: Radu Pirea <radu-nicolae.pirea@oss.nxp.com>
  */
 
@@ -18,9 +18,16 @@
 
 #include "nxp-c45-tja11xx.h"
 
+#define PHY_ID_MASK			GENMASK(31, 4)
+/* Same id: TJA1103, TJA1104 */
 #define PHY_ID_TJA_1103			0x001BB010
 #define PHY_ID_TJA_1120			0x001BB031
 
+#define VEND1_DEVICE_ID3		0x0004
+#define TJA1120_DEV_ID3_SILICON_VERSION	GENMASK(15, 12)
+#define TJA1120_DEV_ID3_SAMPLE_TYPE	GENMASK(11, 8)
+#define DEVICE_ID3_SAMPLE_TYPE_R	0x9
+
 #define VEND1_DEVICE_CONTROL		0x0040
 #define DEVICE_CONTROL_RESET		BIT(15)
 #define DEVICE_CONTROL_CONFIG_GLOBAL_EN	BIT(14)
@@ -108,6 +115,9 @@
 #define MII_BASIC_CONFIG_RMII		0x5
 #define MII_BASIC_CONFIG_MII		0x4
 
+#define VEND1_SGMII_BASIC_CONTROL	0xB000
+#define SGMII_LPM			BIT(11)
+
 #define VEND1_SYMBOL_ERROR_CNT_XTD	0x8351
 #define EXTENDED_CNT_EN			BIT(15)
 #define VEND1_MONITOR_STATUS		0xAC80
@@ -1296,6 +1306,8 @@ static int nxp_c45_soft_reset(struct phy_device *phydev)
 	if (ret)
 		return ret;
 
+	usleep_range(2000, 2050);
+
 	return phy_read_mmd_poll_timeout(phydev, MDIO_MMD_VEND1,
 					 VEND1_DEVICE_CONTROL, ret,
 					 !(ret & DEVICE_CONTROL_RESET), 20000,
@@ -1581,6 +1593,63 @@ static int nxp_c45_set_phy_mode(struct phy_device *phydev)
 	return 0;
 }
 
+/* Errata: ES_TJA1120 and ES_TJA1121 Rev. 1.0 — 28 November 2024 Section 3.1 & 3.2 */
+static void nxp_c45_tja1120_errata(struct phy_device *phydev)
+{
+	bool macsec_ability, sgmii_ability;
+	int silicon_version, sample_type;
+	int phy_abilities;
+	int ret = 0;
+
+	ret = phy_read_mmd(phydev, MDIO_MMD_VEND1, VEND1_DEVICE_ID3);
+	if (ret < 0)
+		return;
+
+	sample_type = FIELD_GET(TJA1120_DEV_ID3_SAMPLE_TYPE, ret);
+	if (sample_type != DEVICE_ID3_SAMPLE_TYPE_R)
+		return;
+
+	silicon_version = FIELD_GET(TJA1120_DEV_ID3_SILICON_VERSION, ret);
+
+	phy_abilities = phy_read_mmd(phydev, MDIO_MMD_VEND1,
+				     VEND1_PORT_ABILITIES);
+	macsec_ability = !!(phy_abilities & MACSEC_ABILITY);
+	sgmii_ability = !!(phy_abilities & SGMII_ABILITY);
+	if ((!macsec_ability && silicon_version == 2) ||
+	    (macsec_ability && silicon_version == 1)) {
+		/* TJA1120/TJA1121 PHY configuration errata workaround.
+		 * Apply PHY writes sequence before link up.
+		 */
+		if (!macsec_ability) {
+			phy_write_mmd(phydev, MDIO_MMD_VEND1, 0x01F8, 0x4b95);
+			phy_write_mmd(phydev, MDIO_MMD_VEND1, 0x01F9, 0xf3cd);
+		} else {
+			phy_write_mmd(phydev, MDIO_MMD_VEND1, 0x01F8, 0x89c7);
+			phy_write_mmd(phydev, MDIO_MMD_VEND1, 0x01F9, 0x0893);
+		}
+
+		phy_write_mmd(phydev, MDIO_MMD_VEND1, 0x0476, 0x58a0);
+
+		phy_write_mmd(phydev, MDIO_MMD_PMAPMD, 0x8921, 0xa3a);
+		phy_write_mmd(phydev, MDIO_MMD_PMAPMD, 0x89F1, 0x16c1);
+
+		phy_write_mmd(phydev, MDIO_MMD_VEND1, 0x01F8, 0x0);
+		phy_write_mmd(phydev, MDIO_MMD_VEND1, 0x01F9, 0x0);
+
+		if (sgmii_ability) {
+			/* TJA1120B/TJA1121B SGMII PCS restart errata workaround.
+			 * Put SGMII PCS into power down mode and back up.
+			 */
+			phy_set_bits_mmd(phydev, MDIO_MMD_VEND1,
+					 VEND1_SGMII_BASIC_CONTROL,
+					 SGMII_LPM);
+			phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1,
+					   VEND1_SGMII_BASIC_CONTROL,
+					   SGMII_LPM);
+		}
+	}
+}
+
 static int nxp_c45_config_init(struct phy_device *phydev)
 {
 	int ret;
@@ -1597,6 +1666,9 @@ static int nxp_c45_config_init(struct phy_device *phydev)
 	phy_write_mmd(phydev, MDIO_MMD_VEND1, 0x01F8, 1);
 	phy_write_mmd(phydev, MDIO_MMD_VEND1, 0x01F9, 2);
 
+	if (phy_id_compare(phydev->phy_id, PHY_ID_TJA_1120, GENMASK(31, 4)))
+		nxp_c45_tja1120_errata(phydev);
+
 	phy_set_bits_mmd(phydev, MDIO_MMD_VEND1, VEND1_PHY_CONFIG,
 			 PHY_CONFIG_AUTO);
 
@@ -1860,6 +1932,30 @@ static void tja1120_nmi_handler(struct phy_device *phydev,
 	}
 }
 
+static int nxp_c45_macsec_ability(struct phy_device *phydev)
+{
+	bool macsec_ability;
+	int phy_abilities;
+
+	phy_abilities = phy_read_mmd(phydev, MDIO_MMD_VEND1,
+				     VEND1_PORT_ABILITIES);
+	macsec_ability = !!(phy_abilities & MACSEC_ABILITY);
+
+	return macsec_ability;
+}
+
+static int tja1103_match_phy_device(struct phy_device *phydev)
+{
+	return phy_id_compare(phydev->phy_id, PHY_ID_TJA_1103, PHY_ID_MASK) &&
+	       !nxp_c45_macsec_ability(phydev);
+}
+
+static int tja1104_match_phy_device(struct phy_device *phydev)
+{
+	return phy_id_compare(phydev->phy_id, PHY_ID_TJA_1103, PHY_ID_MASK) &&
+	       nxp_c45_macsec_ability(phydev);
+}
+
 static const struct nxp_c45_regmap tja1120_regmap = {
 	.vend1_ptp_clk_period	= 0x1020,
 	.vend1_event_msg_filt	= 0x9010,
@@ -1930,7 +2026,6 @@ static const struct nxp_c45_phy_data tja1120_phy_data = {
 
 static struct phy_driver nxp_c45_driver[] = {
 	{
-		PHY_ID_MATCH_MODEL(PHY_ID_TJA_1103),
 		.name			= "NXP C45 TJA1103",
 		.get_features		= nxp_c45_get_features,
 		.driver_data		= &tja1103_phy_data,
@@ -1952,6 +2047,31 @@ static struct phy_driver nxp_c45_driver[] = {
 		.get_sqi		= nxp_c45_get_sqi,
 		.get_sqi_max		= nxp_c45_get_sqi_max,
 		.remove			= nxp_c45_remove,
+		.match_phy_device	= tja1103_match_phy_device,
+	},
+	{
+		.name			= "NXP C45 TJA1104",
+		.get_features		= nxp_c45_get_features,
+		.driver_data		= &tja1103_phy_data,
+		.probe			= nxp_c45_probe,
+		.soft_reset		= nxp_c45_soft_reset,
+		.config_aneg		= genphy_c45_config_aneg,
+		.config_init		= nxp_c45_config_init,
+		.config_intr		= tja1103_config_intr,
+		.handle_interrupt	= nxp_c45_handle_interrupt,
+		.read_status		= genphy_c45_read_status,
+		.suspend		= genphy_c45_pma_suspend,
+		.resume			= genphy_c45_pma_resume,
+		.get_sset_count		= nxp_c45_get_sset_count,
+		.get_strings		= nxp_c45_get_strings,
+		.get_stats		= nxp_c45_get_stats,
+		.cable_test_start	= nxp_c45_cable_test_start,
+		.cable_test_get_status	= nxp_c45_cable_test_get_status,
+		.set_loopback		= genphy_c45_loopback,
+		.get_sqi		= nxp_c45_get_sqi,
+		.get_sqi_max		= nxp_c45_get_sqi_max,
+		.remove			= nxp_c45_remove,
+		.match_phy_device	= tja1104_match_phy_device,
 	},
 	{
 		PHY_ID_MATCH_MODEL(PHY_ID_TJA_1120),
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 4f3e742907cb..c9cfdc33fc5f 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -616,6 +616,49 @@ int phy_ethtool_get_stats(struct phy_device *phydev,
 EXPORT_SYMBOL(phy_ethtool_get_stats);
 
 /**
+ * __phy_ethtool_get_phy_stats - Retrieve standardized PHY statistics
+ * @phydev: Pointer to the PHY device
+ * @phy_stats: Pointer to ethtool_eth_phy_stats structure
+ * @phydev_stats: Pointer to ethtool_phy_stats structure
+ *
+ * Fetches PHY statistics using a kernel-defined interface for consistent
+ * diagnostics. Unlike phy_ethtool_get_stats(), which allows custom stats,
+ * this function enforces a standardized format for better interoperability.
+ */
+void __phy_ethtool_get_phy_stats(struct phy_device *phydev,
+				 struct ethtool_eth_phy_stats *phy_stats,
+				 struct ethtool_phy_stats *phydev_stats)
+{
+	if (!phydev->drv || !phydev->drv->get_phy_stats)
+		return;
+
+	mutex_lock(&phydev->lock);
+	phydev->drv->get_phy_stats(phydev, phy_stats, phydev_stats);
+	mutex_unlock(&phydev->lock);
+}
+
+/**
+ * __phy_ethtool_get_link_ext_stats - Retrieve extended link statistics for a PHY
+ * @phydev: Pointer to the PHY device
+ * @link_stats: Pointer to the structure to store extended link statistics
+ *
+ * Populates the ethtool_link_ext_stats structure with link down event counts
+ * and additional driver-specific link statistics, if available.
+ */
+void __phy_ethtool_get_link_ext_stats(struct phy_device *phydev,
+				      struct ethtool_link_ext_stats *link_stats)
+{
+	link_stats->link_down_events = READ_ONCE(phydev->link_down_events);
+
+	if (!phydev->drv || !phydev->drv->get_link_stats)
+		return;
+
+	mutex_lock(&phydev->lock);
+	phydev->drv->get_link_stats(phydev, link_stats);
+	mutex_unlock(&phydev->lock);
+}
+
+/**
  * phy_ethtool_get_plca_cfg - Get PLCA RS configuration
  * @phydev: the phy_device struct
  * @plca_cfg: where to store the retrieved configuration
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 499797646580..834624a61060 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -289,6 +289,46 @@ static bool phy_drv_wol_enabled(struct phy_device *phydev)
 	return wol.wolopts != 0;
 }
 
+static void phy_link_change(struct phy_device *phydev, bool up)
+{
+	struct net_device *netdev = phydev->attached_dev;
+
+	if (up)
+		netif_carrier_on(netdev);
+	else
+		netif_carrier_off(netdev);
+	phydev->adjust_link(netdev);
+	if (phydev->mii_ts && phydev->mii_ts->link_state)
+		phydev->mii_ts->link_state(phydev->mii_ts, phydev);
+}
+
+/**
+ * phy_uses_state_machine - test whether consumer driver uses PAL state machine
+ * @phydev: the target PHY device structure
+ *
+ * Ultimately, this aims to indirectly determine whether the PHY is attached
+ * to a consumer which uses the state machine by calling phy_start() and
+ * phy_stop().
+ *
+ * When the PHY driver consumer uses phylib, it must have previously called
+ * phy_connect_direct() or one of its derivatives, so that phy_prepare_link()
+ * has set up a hook for monitoring state changes.
+ *
+ * When the PHY driver is used by the MAC driver consumer through phylink (the
+ * only other provider of a phy_link_change() method), using the PHY state
+ * machine is not optional.
+ *
+ * Return: true if consumer calls phy_start() and phy_stop(), false otherwise.
+ */
+static bool phy_uses_state_machine(struct phy_device *phydev)
+{
+	if (phydev->phy_link_change == phy_link_change)
+		return phydev->attached_dev && phydev->adjust_link;
+
+	/* phydev->phy_link_change is implicitly phylink_phy_change() */
+	return true;
+}
+
 static bool mdio_bus_phy_may_suspend(struct phy_device *phydev)
 {
 	struct device_driver *drv = phydev->mdio.dev.driver;
@@ -355,7 +395,7 @@ static __maybe_unused int mdio_bus_phy_suspend(struct device *dev)
 	 * may call phy routines that try to grab the same lock, and that may
 	 * lead to a deadlock.
 	 */
-	if (phydev->attached_dev && phydev->adjust_link)
+	if (phy_uses_state_machine(phydev))
 		phy_stop_machine(phydev);
 
 	if (!mdio_bus_phy_may_suspend(phydev))
@@ -409,7 +449,7 @@ no_resume:
 		}
 	}
 
-	if (phydev->attached_dev && phydev->adjust_link)
+	if (phy_uses_state_machine(phydev))
 		phy_start_machine(phydev);
 
 	return 0;
@@ -1101,19 +1141,6 @@ struct phy_device *phy_find_first(struct mii_bus *bus)
 }
 EXPORT_SYMBOL(phy_find_first);
 
-static void phy_link_change(struct phy_device *phydev, bool up)
-{
-	struct net_device *netdev = phydev->attached_dev;
-
-	if (up)
-		netif_carrier_on(netdev);
-	else
-		netif_carrier_off(netdev);
-	phydev->adjust_link(netdev);
-	if (phydev->mii_ts && phydev->mii_ts->link_state)
-		phydev->mii_ts->link_state(phydev->mii_ts, phydev);
-}
-
 /**
  * phy_prepare_link - prepares the PHY layer to monitor link status
  * @phydev: target phy_device struct
@@ -1983,8 +2010,10 @@ void phy_detach(struct phy_device *phydev)
 	struct module *ndev_owner = NULL;
 	struct mii_bus *bus;
 
-	if (phydev->devlink)
+	if (phydev->devlink) {
 		device_link_del(phydev->devlink);
+		phydev->devlink = NULL;
+	}
 
 	if (phydev->sysfs_links) {
 		if (dev)
@@ -3634,7 +3663,8 @@ static int phy_probe(struct device *dev)
 	/* Get the LEDs from the device tree, and instantiate standard
 	 * LEDs for them.
 	 */
-	if (IS_ENABLED(CONFIG_PHYLIB_LEDS))
+	if (IS_ENABLED(CONFIG_PHYLIB_LEDS) && !phy_driver_is_genphy(phydev) &&
+	    !phy_driver_is_genphy_10g(phydev))
 		err = of_phy_leds(phydev);
 
 out:
@@ -3651,7 +3681,8 @@ static int phy_remove(struct device *dev)
 
 	cancel_delayed_work_sync(&phydev->state_queue);
 
-	if (IS_ENABLED(CONFIG_PHYLIB_LEDS))
+	if (IS_ENABLED(CONFIG_PHYLIB_LEDS) && !phy_driver_is_genphy(phydev) &&
+	    !phy_driver_is_genphy_10g(phydev))
 		phy_leds_unregister(phydev);
 
 	phydev->state = PHY_DOWN;
@@ -3776,6 +3807,8 @@ static const struct ethtool_phy_ops phy_ethtool_phy_ops = {
 static const struct phylib_stubs __phylib_stubs = {
 	.hwtstamp_get = __phy_hwtstamp_get,
 	.hwtstamp_set = __phy_hwtstamp_set,
+	.get_phy_stats = __phy_ethtool_get_phy_stats,
+	.get_link_ext_stats = __phy_ethtool_get_link_ext_stats,
 };
 
 static void phylib_register_stubs(void)
diff --git a/drivers/net/phy/phy_led_triggers.c b/drivers/net/phy/phy_led_triggers.c
index f550576eb9da..6f9d8da76c4d 100644
--- a/drivers/net/phy/phy_led_triggers.c
+++ b/drivers/net/phy/phy_led_triggers.c
@@ -91,9 +91,8 @@ int phy_led_triggers_register(struct phy_device *phy)
 	if (!phy->phy_num_led_triggers)
 		return 0;
 
-	phy->led_link_trigger = devm_kzalloc(&phy->mdio.dev,
-					     sizeof(*phy->led_link_trigger),
-					     GFP_KERNEL);
+	phy->led_link_trigger = kzalloc(sizeof(*phy->led_link_trigger),
+					GFP_KERNEL);
 	if (!phy->led_link_trigger) {
 		err = -ENOMEM;
 		goto out_clear;
@@ -103,10 +102,9 @@ int phy_led_triggers_register(struct phy_device *phy)
 	if (err)
 		goto out_free_link;
 
-	phy->phy_led_triggers = devm_kcalloc(&phy->mdio.dev,
-					    phy->phy_num_led_triggers,
-					    sizeof(struct phy_led_trigger),
-					    GFP_KERNEL);
+	phy->phy_led_triggers = kcalloc(phy->phy_num_led_triggers,
+					sizeof(struct phy_led_trigger),
+					GFP_KERNEL);
 	if (!phy->phy_led_triggers) {
 		err = -ENOMEM;
 		goto out_unreg_link;
@@ -127,11 +125,11 @@ int phy_led_triggers_register(struct phy_device *phy)
 out_unreg:
 	while (i--)
 		phy_led_trigger_unregister(&phy->phy_led_triggers[i]);
-	devm_kfree(&phy->mdio.dev, phy->phy_led_triggers);
+	kfree(phy->phy_led_triggers);
 out_unreg_link:
 	phy_led_trigger_unregister(phy->led_link_trigger);
 out_free_link:
-	devm_kfree(&phy->mdio.dev, phy->led_link_trigger);
+	kfree(phy->led_link_trigger);
 	phy->led_link_trigger = NULL;
 out_clear:
 	phy->phy_num_led_triggers = 0;
@@ -145,8 +143,13 @@ void phy_led_triggers_unregister(struct phy_device *phy)
 
 	for (i = 0; i < phy->phy_num_led_triggers; i++)
 		phy_led_trigger_unregister(&phy->phy_led_triggers[i]);
+	kfree(phy->phy_led_triggers);
+	phy->phy_led_triggers = NULL;
 
-	if (phy->led_link_trigger)
+	if (phy->led_link_trigger) {
 		phy_led_trigger_unregister(phy->led_link_trigger);
+		kfree(phy->led_link_trigger);
+		phy->led_link_trigger = NULL;
+	}
 }
 EXPORT_SYMBOL_GPL(phy_led_triggers_unregister);
diff --git a/drivers/net/phy/phy_link_topology.c b/drivers/net/phy/phy_link_topology.c
index 4a5d73002a1a..0e9e987f37dd 100644
--- a/drivers/net/phy/phy_link_topology.c
+++ b/drivers/net/phy/phy_link_topology.c
@@ -73,7 +73,7 @@ int phy_link_topo_add_phy(struct net_device *dev,
 				      xa_limit_32b, &topo->next_phy_index,
 				      GFP_KERNEL);
 
-	if (ret)
+	if (ret < 0)
 		goto err;
 
 	return 0;
diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index 3e9957b6aa14..b78dfcbec936 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -1811,7 +1811,7 @@ bool phylink_expects_phy(struct phylink *pl)
 {
 	if (pl->cfg_link_an_mode == MLO_AN_FIXED ||
 	    (pl->cfg_link_an_mode == MLO_AN_INBAND &&
-	     phy_interface_mode_is_8023z(pl->link_config.interface)))
+	     phy_interface_mode_is_8023z(pl->link_interface)))
 		return false;
 	return true;
 }
diff --git a/drivers/net/phy/qcom/at803x.c b/drivers/net/phy/qcom/at803x.c
index 105602581a03..ac909ad8a87b 100644
--- a/drivers/net/phy/qcom/at803x.c
+++ b/drivers/net/phy/qcom/at803x.c
@@ -26,9 +26,6 @@
 
 #define AT803X_LED_CONTROL			0x18
 
-#define AT803X_PHY_MMD3_WOL_CTRL		0x8012
-#define AT803X_WOL_EN				BIT(5)
-
 #define AT803X_REG_CHIP_CONFIG			0x1f
 #define AT803X_BT_BX_REG_SEL			0x8000
 
@@ -866,30 +863,6 @@ static int at8031_config_init(struct phy_device *phydev)
 	return at803x_config_init(phydev);
 }
 
-static int at8031_set_wol(struct phy_device *phydev,
-			  struct ethtool_wolinfo *wol)
-{
-	int ret;
-
-	/* First setup MAC address and enable WOL interrupt */
-	ret = at803x_set_wol(phydev, wol);
-	if (ret)
-		return ret;
-
-	if (wol->wolopts & WAKE_MAGIC)
-		/* Enable WOL function for 1588 */
-		ret = phy_modify_mmd(phydev, MDIO_MMD_PCS,
-				     AT803X_PHY_MMD3_WOL_CTRL,
-				     0, AT803X_WOL_EN);
-	else
-		/* Disable WoL function for 1588 */
-		ret = phy_modify_mmd(phydev, MDIO_MMD_PCS,
-				     AT803X_PHY_MMD3_WOL_CTRL,
-				     AT803X_WOL_EN, 0);
-
-	return ret;
-}
-
 static int at8031_config_intr(struct phy_device *phydev)
 {
 	struct at803x_priv *priv = phydev->priv;
diff --git a/drivers/net/phy/qcom/qca807x.c b/drivers/net/phy/qcom/qca807x.c
index bd8a51ec0ecd..ec336c3e338d 100644
--- a/drivers/net/phy/qcom/qca807x.c
+++ b/drivers/net/phy/qcom/qca807x.c
@@ -774,7 +774,7 @@ static int qca807x_config_init(struct phy_device *phydev)
 	control_dac &= ~QCA807X_CONTROL_DAC_MASK;
 	if (!priv->dac_full_amplitude)
 		control_dac |= QCA807X_CONTROL_DAC_DSP_AMPLITUDE;
-	if (!priv->dac_full_amplitude)
+	if (!priv->dac_full_bias_current)
 		control_dac |= QCA807X_CONTROL_DAC_DSP_BIAS_CURRENT;
 	if (!priv->dac_disable_bias_current_tweak)
 		control_dac |= QCA807X_CONTROL_DAC_BIAS_CURRENT_TWEAK;
diff --git a/drivers/net/phy/qcom/qca808x.c b/drivers/net/phy/qcom/qca808x.c
index 5048304ccc9e..c3aad0e6b700 100644
--- a/drivers/net/phy/qcom/qca808x.c
+++ b/drivers/net/phy/qcom/qca808x.c
@@ -633,7 +633,7 @@ static struct phy_driver qca808x_driver[] = {
 	.handle_interrupt	= at803x_handle_interrupt,
 	.get_tunable		= at803x_get_tunable,
 	.set_tunable		= at803x_set_tunable,
-	.set_wol		= at803x_set_wol,
+	.set_wol		= at8031_set_wol,
 	.get_wol		= at803x_get_wol,
 	.get_features		= qca808x_get_features,
 	.config_aneg		= qca808x_config_aneg,
diff --git a/drivers/net/phy/qcom/qcom-phy-lib.c b/drivers/net/phy/qcom/qcom-phy-lib.c
index d28815ef56bb..af7d0d8e81be 100644
--- a/drivers/net/phy/qcom/qcom-phy-lib.c
+++ b/drivers/net/phy/qcom/qcom-phy-lib.c
@@ -115,6 +115,31 @@ int at803x_set_wol(struct phy_device *phydev,
 }
 EXPORT_SYMBOL_GPL(at803x_set_wol);
 
+int at8031_set_wol(struct phy_device *phydev,
+		   struct ethtool_wolinfo *wol)
+{
+	int ret;
+
+	/* First setup MAC address and enable WOL interrupt */
+	ret = at803x_set_wol(phydev, wol);
+	if (ret)
+		return ret;
+
+	if (wol->wolopts & WAKE_MAGIC)
+		/* Enable WOL function for 1588 */
+		ret = phy_modify_mmd(phydev, MDIO_MMD_PCS,
+				     AT803X_PHY_MMD3_WOL_CTRL,
+				     0, AT803X_WOL_EN);
+	else
+		/* Disable WoL function for 1588 */
+		ret = phy_modify_mmd(phydev, MDIO_MMD_PCS,
+				     AT803X_PHY_MMD3_WOL_CTRL,
+				     AT803X_WOL_EN, 0);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(at8031_set_wol);
+
 void at803x_get_wol(struct phy_device *phydev,
 		    struct ethtool_wolinfo *wol)
 {
diff --git a/drivers/net/phy/qcom/qcom.h b/drivers/net/phy/qcom/qcom.h
index 4bb541728846..7f7151c8baca 100644
--- a/drivers/net/phy/qcom/qcom.h
+++ b/drivers/net/phy/qcom/qcom.h
@@ -172,6 +172,9 @@
 #define AT803X_LOC_MAC_ADDR_16_31_OFFSET	0x804B
 #define AT803X_LOC_MAC_ADDR_32_47_OFFSET	0x804A
 
+#define AT803X_PHY_MMD3_WOL_CTRL		0x8012
+#define AT803X_WOL_EN				BIT(5)
+
 #define AT803X_DEBUG_ADDR			0x1D
 #define AT803X_DEBUG_DATA			0x1E
 
@@ -215,6 +218,8 @@ int at803x_debug_reg_mask(struct phy_device *phydev, u16 reg,
 int at803x_debug_reg_write(struct phy_device *phydev, u16 reg, u16 data);
 int at803x_set_wol(struct phy_device *phydev,
 		   struct ethtool_wolinfo *wol);
+int at8031_set_wol(struct phy_device *phydev,
+		   struct ethtool_wolinfo *wol);
 void at803x_get_wol(struct phy_device *phydev,
 		    struct ethtool_wolinfo *wol);
 int at803x_ack_interrupt(struct phy_device *phydev);
diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c
index 166f6a728373..8ce5705af69c 100644
--- a/drivers/net/phy/realtek.c
+++ b/drivers/net/phy/realtek.c
@@ -92,6 +92,7 @@
 
 #define RTL_GENERIC_PHYID			0x001cc800
 #define RTL_8211FVD_PHYID			0x001cc878
+#define RTL_8221B				0x001cc840
 #define RTL_8221B_VB_CG				0x001cc849
 #define RTL_8221B_VN_CG				0x001cc84a
 #define RTL_8251B				0x001cc862
@@ -1040,6 +1041,23 @@ static bool rtlgen_supports_2_5gbps(struct phy_device *phydev)
 	return val >= 0 && val & MDIO_PMA_SPEED_2_5G;
 }
 
+/* On internal PHY's MMD reads over C22 always return 0.
+ * Check a MMD register which is known to be non-zero.
+ */
+static bool rtlgen_supports_mmd(struct phy_device *phydev)
+{
+	int val;
+
+	phy_lock_mdio_bus(phydev);
+	__phy_write(phydev, MII_MMD_CTRL, MDIO_MMD_PCS);
+	__phy_write(phydev, MII_MMD_DATA, MDIO_PCS_EEE_ABLE);
+	__phy_write(phydev, MII_MMD_CTRL, MDIO_MMD_PCS | MII_MMD_CTRL_NOINCR);
+	val = __phy_read(phydev, MII_MMD_DATA);
+	phy_unlock_mdio_bus(phydev);
+
+	return val > 0;
+}
+
 static int rtlgen_match_phy_device(struct phy_device *phydev)
 {
 	return phydev->phy_id == RTL_GENERIC_PHYID &&
@@ -1049,7 +1067,8 @@ static int rtlgen_match_phy_device(struct phy_device *phydev)
 static int rtl8226_match_phy_device(struct phy_device *phydev)
 {
 	return phydev->phy_id == RTL_GENERIC_PHYID &&
-	       rtlgen_supports_2_5gbps(phydev);
+	       rtlgen_supports_2_5gbps(phydev) &&
+	       rtlgen_supports_mmd(phydev);
 }
 
 static int rtlgen_is_c45_match(struct phy_device *phydev, unsigned int id,
@@ -1061,6 +1080,11 @@ static int rtlgen_is_c45_match(struct phy_device *phydev, unsigned int id,
 		return !is_c45 && (id == phydev->phy_id);
 }
 
+static int rtl8221b_match_phy_device(struct phy_device *phydev)
+{
+	return phydev->phy_id == RTL_8221B && rtlgen_supports_mmd(phydev);
+}
+
 static int rtl8221b_vb_cg_c22_match_phy_device(struct phy_device *phydev)
 {
 	return rtlgen_is_c45_match(phydev, RTL_8221B_VB_CG, false);
@@ -1081,9 +1105,22 @@ static int rtl8221b_vn_cg_c45_match_phy_device(struct phy_device *phydev)
 	return rtlgen_is_c45_match(phydev, RTL_8221B_VN_CG, true);
 }
 
-static int rtl8251b_c22_match_phy_device(struct phy_device *phydev)
+static int rtl_internal_nbaset_match_phy_device(struct phy_device *phydev)
 {
-	return rtlgen_is_c45_match(phydev, RTL_8251B, false);
+	if (phydev->is_c45)
+		return false;
+
+	switch (phydev->phy_id) {
+	case RTL_GENERIC_PHYID:
+	case RTL_8221B:
+	case RTL_8251B:
+	case 0x001cc841:
+		break;
+	default:
+		return false;
+	}
+
+	return rtlgen_supports_2_5gbps(phydev) && !rtlgen_supports_mmd(phydev);
 }
 
 static int rtl8251b_c45_match_phy_device(struct phy_device *phydev)
@@ -1345,10 +1382,8 @@ static struct phy_driver realtek_drvs[] = {
 		.resume		= rtlgen_resume,
 		.read_page	= rtl821x_read_page,
 		.write_page	= rtl821x_write_page,
-		.read_mmd	= rtl822x_read_mmd,
-		.write_mmd	= rtl822x_write_mmd,
 	}, {
-		PHY_ID_MATCH_EXACT(0x001cc840),
+		.match_phy_device = rtl8221b_match_phy_device,
 		.name		= "RTL8226B_RTL8221B 2.5Gbps PHY",
 		.get_features	= rtl822x_get_features,
 		.config_aneg	= rtl822x_config_aneg,
@@ -1359,8 +1394,6 @@ static struct phy_driver realtek_drvs[] = {
 		.resume		= rtlgen_resume,
 		.read_page	= rtl821x_read_page,
 		.write_page	= rtl821x_write_page,
-		.read_mmd	= rtl822x_read_mmd,
-		.write_mmd	= rtl822x_write_mmd,
 	}, {
 		PHY_ID_MATCH_EXACT(0x001cc838),
 		.name           = "RTL8226-CG 2.5Gbps PHY",
@@ -1438,8 +1471,9 @@ static struct phy_driver realtek_drvs[] = {
 		.read_page      = rtl821x_read_page,
 		.write_page     = rtl821x_write_page,
 	}, {
-		.match_phy_device = rtl8251b_c22_match_phy_device,
-		.name           = "RTL8126A-internal 5Gbps PHY",
+		.match_phy_device = rtl_internal_nbaset_match_phy_device,
+		.name           = "Realtek Internal NBASE-T PHY",
+		.flags		= PHY_IS_INTERNAL,
 		.get_features   = rtl822x_get_features,
 		.config_aneg    = rtl822x_config_aneg,
 		.read_status    = rtl822x_read_status,
diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c
index dcec92625cf6..7b33993f7001 100644
--- a/drivers/net/phy/sfp.c
+++ b/drivers/net/phy/sfp.c
@@ -385,7 +385,7 @@ static void sfp_fixup_rollball(struct sfp *sfp)
 	sfp->phy_t_retry = msecs_to_jiffies(1000);
 }
 
-static void sfp_fixup_fs_2_5gt(struct sfp *sfp)
+static void sfp_fixup_rollball_wait4s(struct sfp *sfp)
 {
 	sfp_fixup_rollball(sfp);
 
@@ -399,7 +399,7 @@ static void sfp_fixup_fs_2_5gt(struct sfp *sfp)
 static void sfp_fixup_fs_10gt(struct sfp *sfp)
 {
 	sfp_fixup_10gbaset_30m(sfp);
-	sfp_fixup_fs_2_5gt(sfp);
+	sfp_fixup_rollball_wait4s(sfp);
 }
 
 static void sfp_fixup_halny_gsfp(struct sfp *sfp)
@@ -479,9 +479,10 @@ static const struct sfp_quirk sfp_quirks[] = {
 	// PHY.
 	SFP_QUIRK_F("FS", "SFP-10G-T", sfp_fixup_fs_10gt),
 
-	// Fiberstore SFP-2.5G-T uses Rollball protocol to talk to the PHY and
-	// needs 4 sec wait before probing the PHY.
-	SFP_QUIRK_F("FS", "SFP-2.5G-T", sfp_fixup_fs_2_5gt),
+	// Fiberstore SFP-2.5G-T and SFP-10GM-T uses Rollball protocol to talk
+	// to the PHY and needs 4 sec wait before probing the PHY.
+	SFP_QUIRK_F("FS", "SFP-2.5G-T", sfp_fixup_rollball_wait4s),
+	SFP_QUIRK_F("FS", "SFP-10GM-T", sfp_fixup_rollball_wait4s),
 
 	// Fiberstore GPON-ONU-34-20BI can operate at 2500base-X, but report 1.2GBd
 	// NRZ in their EEPROM
@@ -515,6 +516,8 @@ static const struct sfp_quirk sfp_quirks[] = {
 
 	SFP_QUIRK_F("OEM", "SFP-10G-T", sfp_fixup_rollball_cc),
 	SFP_QUIRK_M("OEM", "SFP-2.5G-T", sfp_quirk_oem_2_5g),
+	SFP_QUIRK_M("OEM", "SFP-2.5G-BX10-D", sfp_quirk_2500basex),
+	SFP_QUIRK_M("OEM", "SFP-2.5G-BX10-U", sfp_quirk_2500basex),
 	SFP_QUIRK_F("OEM", "RTSFP-10", sfp_fixup_rollball_cc),
 	SFP_QUIRK_F("OEM", "RTSFP-10G", sfp_fixup_rollball_cc),
 	SFP_QUIRK_F("Turris", "RTSFP-2.5G", sfp_fixup_rollball),
diff --git a/drivers/net/phy/smsc.c b/drivers/net/phy/smsc.c
index 150aea7c9c36..de66b621eb99 100644
--- a/drivers/net/phy/smsc.c
+++ b/drivers/net/phy/smsc.c
@@ -155,10 +155,29 @@ static int smsc_phy_reset(struct phy_device *phydev)
 
 static int lan87xx_config_aneg(struct phy_device *phydev)
 {
-	int rc;
+	u8 mdix_ctrl;
 	int val;
+	int rc;
 
-	switch (phydev->mdix_ctrl) {
+	/* When auto-negotiation is disabled (forced mode), the PHY's
+	 * Auto-MDIX will continue toggling the TX/RX pairs.
+	 *
+	 * To establish a stable link, we must select a fixed MDI mode.
+	 * If the user has not specified a fixed MDI mode (i.e., mdix_ctrl is
+	 * 'auto'), we default to ETH_TP_MDI. This choice of a ETH_TP_MDI mode
+	 * mirrors the behavior the hardware would exhibit if the AUTOMDIX_EN
+	 * strap were configured for a fixed MDI connection.
+	 */
+	if (phydev->autoneg == AUTONEG_DISABLE) {
+		if (phydev->mdix_ctrl == ETH_TP_MDI_AUTO)
+			mdix_ctrl = ETH_TP_MDI;
+		else
+			mdix_ctrl = phydev->mdix_ctrl;
+	} else {
+		mdix_ctrl = phydev->mdix_ctrl;
+	}
+
+	switch (mdix_ctrl) {
 	case ETH_TP_MDI:
 		val = SPECIAL_CTRL_STS_OVRRD_AMDIX_;
 		break;
@@ -167,7 +186,8 @@ static int lan87xx_config_aneg(struct phy_device *phydev)
 			SPECIAL_CTRL_STS_AMDIX_STATE_;
 		break;
 	case ETH_TP_MDI_AUTO:
-		val = SPECIAL_CTRL_STS_AMDIX_ENABLE_;
+		val = SPECIAL_CTRL_STS_OVRRD_AMDIX_ |
+			SPECIAL_CTRL_STS_AMDIX_ENABLE_;
 		break;
 	default:
 		return genphy_config_aneg(phydev);
@@ -183,7 +203,7 @@ static int lan87xx_config_aneg(struct phy_device *phydev)
 	rc |= val;
 	phy_write(phydev, SPECIAL_CTRL_STS, rc);
 
-	phydev->mdix = phydev->mdix_ctrl;
+	phydev->mdix = mdix_ctrl;
 	return genphy_config_aneg(phydev);
 }
 
@@ -261,6 +281,33 @@ int lan87xx_read_status(struct phy_device *phydev)
 }
 EXPORT_SYMBOL_GPL(lan87xx_read_status);
 
+static int lan87xx_phy_config_init(struct phy_device *phydev)
+{
+	int rc;
+
+	/* The LAN87xx PHY's initial MDI-X mode is determined by the AUTOMDIX_EN
+	 * hardware strap, but the driver cannot read the strap's status. This
+	 * creates an unpredictable initial state.
+	 *
+	 * To ensure consistent and reliable behavior across all boards,
+	 * override the strap configuration on initialization and force the PHY
+	 * into a known state with Auto-MDIX enabled, which is the expected
+	 * default for modern hardware.
+	 */
+	rc = phy_modify(phydev, SPECIAL_CTRL_STS,
+			SPECIAL_CTRL_STS_OVRRD_AMDIX_ |
+			SPECIAL_CTRL_STS_AMDIX_ENABLE_ |
+			SPECIAL_CTRL_STS_AMDIX_STATE_,
+			SPECIAL_CTRL_STS_OVRRD_AMDIX_ |
+			SPECIAL_CTRL_STS_AMDIX_ENABLE_);
+	if (rc < 0)
+		return rc;
+
+	phydev->mdix_ctrl = ETH_TP_MDI_AUTO;
+
+	return smsc_phy_config_init(phydev);
+}
+
 static int lan874x_phy_config_init(struct phy_device *phydev)
 {
 	u16 val;
@@ -694,7 +741,7 @@ static struct phy_driver smsc_phy_driver[] = {
 
 	/* basic functions */
 	.read_status	= lan87xx_read_status,
-	.config_init	= smsc_phy_config_init,
+	.config_init	= lan87xx_phy_config_init,
 	.soft_reset	= smsc_phy_reset,
 	.config_aneg	= lan87xx_config_aneg,
 
@@ -737,6 +784,7 @@ static struct phy_driver smsc_phy_driver[] = {
 
 	/* PHY_BASIC_FEATURES */
 
+	.flags		= PHY_RST_AFTER_CLK_EN,
 	.probe		= smsc_phy_probe,
 
 	/* basic functions */
diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index 4583e15ad03a..1420c4efa48e 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -72,6 +72,17 @@
 #define PPP_PROTO_LEN	2
 #define PPP_LCP_HDRLEN	4
 
+/* The filter instructions generated by libpcap are constructed
+ * assuming a four-byte PPP header on each packet, where the last
+ * 2 bytes are the protocol field defined in the RFC and the first
+ * byte of the first 2 bytes indicates the direction.
+ * The second byte is currently unused, but we still need to initialize
+ * it to prevent crafted BPF programs from reading them which would
+ * cause reading of uninitialized data.
+ */
+#define PPP_FILTER_OUTBOUND_TAG 0x0100
+#define PPP_FILTER_INBOUND_TAG  0x0000
+
 /*
  * An instance of /dev/ppp can be associated with either a ppp
  * interface unit or a ppp channel.  In both cases, file->private_data
@@ -1762,10 +1773,10 @@ ppp_send_frame(struct ppp *ppp, struct sk_buff *skb)
 
 	if (proto < 0x8000) {
 #ifdef CONFIG_PPP_FILTER
-		/* check if we should pass this packet */
-		/* the filter instructions are constructed assuming
-		   a four-byte PPP header on each packet */
-		*(u8 *)skb_push(skb, 2) = 1;
+		/* check if the packet passes the pass and active filters.
+		 * See comment for PPP_FILTER_OUTBOUND_TAG above.
+		 */
+		*(__be16 *)skb_push(skb, 2) = htons(PPP_FILTER_OUTBOUND_TAG);
 		if (ppp->pass_filter &&
 		    bpf_prog_run(ppp->pass_filter, skb) == 0) {
 			if (ppp->debug & 1)
@@ -2482,14 +2493,13 @@ ppp_receive_nonmp_frame(struct ppp *ppp, struct sk_buff *skb)
 		/* network protocol frame - give it to the kernel */
 
 #ifdef CONFIG_PPP_FILTER
-		/* check if the packet passes the pass and active filters */
-		/* the filter instructions are constructed assuming
-		   a four-byte PPP header on each packet */
 		if (ppp->pass_filter || ppp->active_filter) {
 			if (skb_unclone(skb, GFP_ATOMIC))
 				goto err;
-
-			*(u8 *)skb_push(skb, 2) = 0;
+			/* Check if the packet passes the pass and active filters.
+			 * See comment for PPP_FILTER_INBOUND_TAG above.
+			 */
+			*(__be16 *)skb_push(skb, 2) = htons(PPP_FILTER_INBOUND_TAG);
 			if (ppp->pass_filter &&
 			    bpf_prog_run(ppp->pass_filter, skb) == 0) {
 				if (ppp->debug & 1)
diff --git a/drivers/net/ppp/ppp_synctty.c b/drivers/net/ppp/ppp_synctty.c
index 644e99fc3623..9c4932198931 100644
--- a/drivers/net/ppp/ppp_synctty.c
+++ b/drivers/net/ppp/ppp_synctty.c
@@ -506,6 +506,11 @@ ppp_sync_txmunge(struct syncppp *ap, struct sk_buff *skb)
 	unsigned char *data;
 	int islcp;
 
+	/* Ensure we can safely access protocol field and LCP code */
+	if (!pskb_may_pull(skb, 3)) {
+		kfree_skb(skb);
+		return NULL;
+	}
 	data  = skb->data;
 	proto = get_unaligned_be16(data);
 
diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c
index 689687bd2574..cec3bb22471b 100644
--- a/drivers/net/ppp/pptp.c
+++ b/drivers/net/ppp/pptp.c
@@ -159,19 +159,17 @@ static int pptp_xmit(struct ppp_channel *chan, struct sk_buff *skb)
 	int len;
 	unsigned char *data;
 	__u32 seq_recv;
-
-
 	struct rtable *rt;
 	struct net_device *tdev;
 	struct iphdr  *iph;
 	int    max_headroom;
 
 	if (sk_pppox(po)->sk_state & PPPOX_DEAD)
-		goto tx_error;
+		goto tx_drop;
 
 	rt = pptp_route_output(po, &fl4);
 	if (IS_ERR(rt))
-		goto tx_error;
+		goto tx_drop;
 
 	tdev = rt->dst.dev;
 
@@ -179,16 +177,20 @@ static int pptp_xmit(struct ppp_channel *chan, struct sk_buff *skb)
 
 	if (skb_headroom(skb) < max_headroom || skb_cloned(skb) || skb_shared(skb)) {
 		struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom);
-		if (!new_skb) {
-			ip_rt_put(rt);
+
+		if (!new_skb)
 			goto tx_error;
-		}
+
 		if (skb->sk)
 			skb_set_owner_w(new_skb, skb->sk);
 		consume_skb(skb);
 		skb = new_skb;
 	}
 
+	/* Ensure we can safely access protocol field and LCP code */
+	if (!pskb_may_pull(skb, 3))
+		goto tx_error;
+
 	data = skb->data;
 	islcp = ((data[0] << 8) + data[1]) == PPP_LCP && 1 <= data[2] && data[2] <= 7;
 
@@ -262,6 +264,8 @@ static int pptp_xmit(struct ppp_channel *chan, struct sk_buff *skb)
 	return 1;
 
 tx_error:
+	ip_rt_put(rt);
+tx_drop:
 	kfree_skb(skb);
 	return 1;
 }
diff --git a/drivers/net/pse-pd/pd692x0.c b/drivers/net/pse-pd/pd692x0.c
index 0af7db80b2f8..7cfc36cadb57 100644
--- a/drivers/net/pse-pd/pd692x0.c
+++ b/drivers/net/pse-pd/pd692x0.c
@@ -999,13 +999,12 @@ static int pd692x0_pi_get_voltage(struct pse_controller_dev *pcdev, int id)
 	return (buf.sub[0] << 8 | buf.sub[1]) * 100000;
 }
 
-static int pd692x0_pi_get_current_limit(struct pse_controller_dev *pcdev,
-					int id)
+static int pd692x0_pi_get_pw_limit(struct pse_controller_dev *pcdev,
+				   int id)
 {
 	struct pd692x0_priv *priv = to_pd692x0_priv(pcdev);
 	struct pd692x0_msg msg, buf = {0};
-	int mW, uV, uA, ret;
-	s64 tmp_64;
+	int ret;
 
 	msg = pd692x0_msg_template_list[PD692X0_MSG_GET_PORT_PARAM];
 	msg.sub[2] = id;
@@ -1013,48 +1012,24 @@ static int pd692x0_pi_get_current_limit(struct pse_controller_dev *pcdev,
 	if (ret < 0)
 		return ret;
 
-	ret = pd692x0_pi_get_pw_from_table(buf.data[2], buf.data[3]);
-	if (ret < 0)
-		return ret;
-	mW = ret;
-
-	ret = pd692x0_pi_get_voltage(pcdev, id);
-	if (ret < 0)
-		return ret;
-	uV = ret;
-
-	tmp_64 = mW;
-	tmp_64 *= 1000000000ull;
-	/* uA = mW * 1000000000 / uV */
-	uA = DIV_ROUND_CLOSEST_ULL(tmp_64, uV);
-	return uA;
+	return pd692x0_pi_get_pw_from_table(buf.data[0], buf.data[1]);
 }
 
-static int pd692x0_pi_set_current_limit(struct pse_controller_dev *pcdev,
-					int id, int max_uA)
+static int pd692x0_pi_set_pw_limit(struct pse_controller_dev *pcdev,
+				   int id, int max_mW)
 {
 	struct pd692x0_priv *priv = to_pd692x0_priv(pcdev);
 	struct device *dev = &priv->client->dev;
 	struct pd692x0_msg msg, buf = {0};
-	int uV, ret, mW;
-	s64 tmp_64;
+	int ret;
 
 	ret = pd692x0_fw_unavailable(priv);
 	if (ret)
 		return ret;
 
-	ret = pd692x0_pi_get_voltage(pcdev, id);
-	if (ret < 0)
-		return ret;
-	uV = ret;
-
 	msg = pd692x0_msg_template_list[PD692X0_MSG_SET_PORT_PARAM];
 	msg.sub[2] = id;
-	tmp_64 = uV;
-	tmp_64 *= max_uA;
-	/* mW = uV * uA / 1000000000 */
-	mW = DIV_ROUND_CLOSEST_ULL(tmp_64, 1000000000);
-	ret = pd692x0_pi_set_pw_from_table(dev, &msg, mW);
+	ret = pd692x0_pi_set_pw_from_table(dev, &msg, max_mW);
 	if (ret)
 		return ret;
 
@@ -1068,8 +1043,8 @@ static const struct pse_controller_ops pd692x0_ops = {
 	.pi_disable = pd692x0_pi_disable,
 	.pi_is_enabled = pd692x0_pi_is_enabled,
 	.pi_get_voltage = pd692x0_pi_get_voltage,
-	.pi_get_current_limit = pd692x0_pi_get_current_limit,
-	.pi_set_current_limit = pd692x0_pi_set_current_limit,
+	.pi_get_pw_limit = pd692x0_pi_get_pw_limit,
+	.pi_set_pw_limit = pd692x0_pi_set_pw_limit,
 };
 
 #define PD692X0_FW_LINE_MAX_SZ 0xff
diff --git a/drivers/net/pse-pd/pse_core.c b/drivers/net/pse-pd/pse_core.c
index 2906ce173f66..bb509d973e91 100644
--- a/drivers/net/pse-pd/pse_core.c
+++ b/drivers/net/pse-pd/pse_core.c
@@ -291,32 +291,24 @@ static int pse_pi_get_voltage(struct regulator_dev *rdev)
 	return ret;
 }
 
-static int _pse_ethtool_get_status(struct pse_controller_dev *pcdev,
-				   int id,
-				   struct netlink_ext_ack *extack,
-				   struct pse_control_status *status);
-
 static int pse_pi_get_current_limit(struct regulator_dev *rdev)
 {
 	struct pse_controller_dev *pcdev = rdev_get_drvdata(rdev);
 	const struct pse_controller_ops *ops;
-	struct netlink_ext_ack extack = {};
-	struct pse_control_status st = {};
-	int id, uV, ret;
+	int id, uV, mW, ret;
 	s64 tmp_64;
 
 	ops = pcdev->ops;
 	id = rdev_get_id(rdev);
+	if (!ops->pi_get_pw_limit || !ops->pi_get_voltage)
+		return -EOPNOTSUPP;
+
 	mutex_lock(&pcdev->lock);
-	if (ops->pi_get_current_limit) {
-		ret = ops->pi_get_current_limit(pcdev, id);
+	ret = ops->pi_get_pw_limit(pcdev, id);
+	if (ret < 0)
 		goto out;
-	}
+	mW = ret;
 
-	/* If pi_get_current_limit() callback not populated get voltage
-	 * from pi_get_voltage() and power limit from ethtool_get_status()
-	 *  to calculate current limit.
-	 */
 	ret = _pse_pi_get_voltage(rdev);
 	if (!ret) {
 		dev_err(pcdev->dev, "Voltage null\n");
@@ -327,16 +319,7 @@ static int pse_pi_get_current_limit(struct regulator_dev *rdev)
 		goto out;
 	uV = ret;
 
-	ret = _pse_ethtool_get_status(pcdev, id, &extack, &st);
-	if (ret)
-		goto out;
-
-	if (!st.c33_avail_pw_limit) {
-		ret = -ENODATA;
-		goto out;
-	}
-
-	tmp_64 = st.c33_avail_pw_limit;
+	tmp_64 = mW;
 	tmp_64 *= 1000000000ull;
 	/* uA = mW * 1000000000 / uV */
 	ret = DIV_ROUND_CLOSEST_ULL(tmp_64, uV);
@@ -351,15 +334,33 @@ static int pse_pi_set_current_limit(struct regulator_dev *rdev, int min_uA,
 {
 	struct pse_controller_dev *pcdev = rdev_get_drvdata(rdev);
 	const struct pse_controller_ops *ops;
-	int id, ret;
+	int id, mW, ret;
+	s64 tmp_64;
 
 	ops = pcdev->ops;
-	if (!ops->pi_set_current_limit)
+	if (!ops->pi_set_pw_limit || !ops->pi_get_voltage)
 		return -EOPNOTSUPP;
 
+	if (max_uA > MAX_PI_CURRENT)
+		return -ERANGE;
+
 	id = rdev_get_id(rdev);
 	mutex_lock(&pcdev->lock);
-	ret = ops->pi_set_current_limit(pcdev, id, max_uA);
+	ret = _pse_pi_get_voltage(rdev);
+	if (!ret) {
+		dev_err(pcdev->dev, "Voltage null\n");
+		ret = -ERANGE;
+		goto out;
+	}
+	if (ret < 0)
+		goto out;
+
+	tmp_64 = ret;
+	tmp_64 *= max_uA;
+	/* mW = uA * uV / 1000000000 */
+	mW = DIV_ROUND_CLOSEST_ULL(tmp_64, 1000000000);
+	ret = ops->pi_set_pw_limit(pcdev, id, mW);
+out:
 	mutex_unlock(&pcdev->lock);
 
 	return ret;
@@ -403,11 +404,9 @@ devm_pse_pi_regulator_register(struct pse_controller_dev *pcdev,
 
 	rinit_data->constraints.valid_ops_mask = REGULATOR_CHANGE_STATUS;
 
-	if (pcdev->ops->pi_set_current_limit) {
+	if (pcdev->ops->pi_set_pw_limit)
 		rinit_data->constraints.valid_ops_mask |=
 			REGULATOR_CHANGE_CURRENT;
-		rinit_data->constraints.max_uA = MAX_PI_CURRENT;
-	}
 
 	rinit_data->supply_regulator = "vpwr";
 
@@ -736,23 +735,6 @@ out:
 }
 EXPORT_SYMBOL_GPL(of_pse_control_get);
 
-static int _pse_ethtool_get_status(struct pse_controller_dev *pcdev,
-				   int id,
-				   struct netlink_ext_ack *extack,
-				   struct pse_control_status *status)
-{
-	const struct pse_controller_ops *ops;
-
-	ops = pcdev->ops;
-	if (!ops->ethtool_get_status) {
-		NL_SET_ERR_MSG(extack,
-			       "PSE driver does not support status report");
-		return -EOPNOTSUPP;
-	}
-
-	return ops->ethtool_get_status(pcdev, id, extack, status);
-}
-
 /**
  * pse_ethtool_get_status - get status of PSE control
  * @psec: PSE control pointer
@@ -765,11 +747,21 @@ int pse_ethtool_get_status(struct pse_control *psec,
 			   struct netlink_ext_ack *extack,
 			   struct pse_control_status *status)
 {
+	const struct pse_controller_ops *ops;
+	struct pse_controller_dev *pcdev;
 	int err;
 
-	mutex_lock(&psec->pcdev->lock);
-	err = _pse_ethtool_get_status(psec->pcdev, psec->id, extack, status);
-	mutex_unlock(&psec->pcdev->lock);
+	pcdev = psec->pcdev;
+	ops = pcdev->ops;
+	if (!ops->ethtool_get_status) {
+		NL_SET_ERR_MSG(extack,
+			       "PSE driver does not support status report");
+		return -EOPNOTSUPP;
+	}
+
+	mutex_lock(&pcdev->lock);
+	err = ops->ethtool_get_status(pcdev, psec->id, extack, status);
+	mutex_unlock(&pcdev->lock);
 
 	return err;
 }
diff --git a/drivers/net/tap.c b/drivers/net/tap.c
index 5aa41d5f7765..5ca6ecf0ce5f 100644
--- a/drivers/net/tap.c
+++ b/drivers/net/tap.c
@@ -1329,9 +1329,9 @@ int tap_queue_resize(struct tap_dev *tap)
 	list_for_each_entry(q, &tap->queue_list, next)
 		rings[i++] = &q->ring;
 
-	ret = ptr_ring_resize_multiple(rings, n,
-				       dev->tx_queue_len, GFP_KERNEL,
-				       __skb_array_destroy_skb);
+	ret = ptr_ring_resize_multiple_bh(rings, n,
+					  dev->tx_queue_len, GFP_KERNEL,
+					  __skb_array_destroy_skb);
 
 	kfree(rings);
 	return ret;
diff --git a/drivers/net/team/team_core.c b/drivers/net/team/team_core.c
index 1c85dda83825..6cfafaac1b4f 100644
--- a/drivers/net/team/team_core.c
+++ b/drivers/net/team/team_core.c
@@ -1175,6 +1175,13 @@ static int team_port_add(struct team *team, struct net_device *port_dev,
 		return -EBUSY;
 	}
 
+	if (netdev_has_upper_dev(port_dev, dev)) {
+		NL_SET_ERR_MSG(extack, "Device is already a lower device of the team interface");
+		netdev_err(dev, "Device %s is already a lower device of the team interface\n",
+			   portname);
+		return -EBUSY;
+	}
+
 	if (port_dev->features & NETIF_F_VLAN_CHALLENGED &&
 	    vlan_uses_dev(dev)) {
 		NL_SET_ERR_MSG(extack, "Device is VLAN challenged and team device has VLAN set up");
@@ -2633,7 +2640,9 @@ int team_nl_options_set_doit(struct sk_buff *skb, struct genl_info *info)
 				ctx.data.u32_val = nla_get_u32(attr_data);
 				break;
 			case TEAM_OPTION_TYPE_STRING:
-				if (nla_len(attr_data) > TEAM_STRING_MAX_LEN) {
+				if (nla_len(attr_data) > TEAM_STRING_MAX_LEN ||
+				    !memchr(nla_data(attr_data), '\0',
+					    nla_len(attr_data))) {
 					err = -EINVAL;
 					goto team_put;
 				}
diff --git a/drivers/net/thunderbolt/main.c b/drivers/net/thunderbolt/main.c
index 0a53ec293d04..dcaa62377808 100644
--- a/drivers/net/thunderbolt/main.c
+++ b/drivers/net/thunderbolt/main.c
@@ -396,9 +396,9 @@ static void tbnet_tear_down(struct tbnet *net, bool send_logout)
 
 		ret = tb_xdomain_disable_paths(net->xd,
 					       net->local_transmit_path,
-					       net->rx_ring.ring->hop,
+					       net->tx_ring.ring->hop,
 					       net->remote_transmit_path,
-					       net->tx_ring.ring->hop);
+					       net->rx_ring.ring->hop);
 		if (ret)
 			netdev_warn(net->dev, "failed to disable DMA paths\n");
 
@@ -662,9 +662,9 @@ static void tbnet_connected_work(struct work_struct *work)
 		goto err_free_rx_buffers;
 
 	ret = tb_xdomain_enable_paths(net->xd, net->local_transmit_path,
-				      net->rx_ring.ring->hop,
+				      net->tx_ring.ring->hop,
 				      net->remote_transmit_path,
-				      net->tx_ring.ring->hop);
+				      net->rx_ring.ring->hop);
 	if (ret) {
 		netdev_err(net->dev, "failed to enable DMA paths\n");
 		goto err_free_tx_buffers;
@@ -924,8 +924,12 @@ static int tbnet_open(struct net_device *dev)
 
 	netif_carrier_off(dev);
 
-	ring = tb_ring_alloc_tx(xd->tb->nhi, -1, TBNET_RING_SIZE,
-				RING_FLAG_FRAME);
+	flags = RING_FLAG_FRAME;
+	/* Only enable full E2E if the other end supports it too */
+	if (tbnet_e2e && net->svc->prtcstns & TBNET_E2E)
+		flags |= RING_FLAG_E2E;
+
+	ring = tb_ring_alloc_tx(xd->tb->nhi, -1, TBNET_RING_SIZE, flags);
 	if (!ring) {
 		netdev_err(dev, "failed to allocate Tx ring\n");
 		return -ENOMEM;
@@ -944,11 +948,6 @@ static int tbnet_open(struct net_device *dev)
 	sof_mask = BIT(TBIP_PDF_FRAME_START);
 	eof_mask = BIT(TBIP_PDF_FRAME_END);
 
-	flags = RING_FLAG_FRAME;
-	/* Only enable full E2E if the other end supports it too */
-	if (tbnet_e2e && net->svc->prtcstns & TBNET_E2E)
-		flags |= RING_FLAG_E2E;
-
 	ring = tb_ring_alloc_rx(xd->tb->nhi, -1, TBNET_RING_SIZE, flags,
 				net->tx_ring.ring->hop, sof_mask,
 				eof_mask, tbnet_start_poll, net);
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 03fe9e3ee7af..fae1a0ab36bd 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -580,7 +580,7 @@ static inline bool tun_not_capable(struct tun_struct *tun)
 	struct net *net = dev_net(tun->dev);
 
 	return ((uid_valid(tun->owner) && !uid_eq(cred->euid, tun->owner)) ||
-		  (gid_valid(tun->group) && !in_egroup_p(tun->group))) &&
+		(gid_valid(tun->group) && !in_egroup_p(tun->group))) &&
 		!ns_capable(net->user_ns, CAP_NET_ADMIN);
 }
 
@@ -3697,9 +3697,9 @@ static int tun_queue_resize(struct tun_struct *tun)
 	list_for_each_entry(tfile, &tun->disabled, next)
 		rings[i++] = &tfile->tx_ring;
 
-	ret = ptr_ring_resize_multiple(rings, n,
-				       dev->tx_queue_len, GFP_KERNEL,
-				       tun_ptr_free);
+	ret = ptr_ring_resize_multiple_bh(rings, n,
+					  dev->tx_queue_len, GFP_KERNEL,
+					  tun_ptr_free);
 
 	kfree(rings);
 	return ret;
diff --git a/drivers/net/usb/aqc111.c b/drivers/net/usb/aqc111.c
index ff5be2cbf17b..9201ee10a13f 100644
--- a/drivers/net/usb/aqc111.c
+++ b/drivers/net/usb/aqc111.c
@@ -30,11 +30,14 @@ static int aqc111_read_cmd_nopm(struct usbnet *dev, u8 cmd, u16 value,
 	ret = usbnet_read_cmd_nopm(dev, cmd, USB_DIR_IN | USB_TYPE_VENDOR |
 				   USB_RECIP_DEVICE, value, index, data, size);
 
-	if (unlikely(ret < 0))
+	if (unlikely(ret < size)) {
 		netdev_warn(dev->net,
 			    "Failed to read(0x%x) reg index 0x%04x: %d\n",
 			    cmd, index, ret);
 
+		ret = ret < 0 ? ret : -ENODATA;
+	}
+
 	return ret;
 }
 
@@ -46,11 +49,14 @@ static int aqc111_read_cmd(struct usbnet *dev, u8 cmd, u16 value,
 	ret = usbnet_read_cmd(dev, cmd, USB_DIR_IN | USB_TYPE_VENDOR |
 			      USB_RECIP_DEVICE, value, index, data, size);
 
-	if (unlikely(ret < 0))
+	if (unlikely(ret < size)) {
 		netdev_warn(dev->net,
 			    "Failed to read(0x%x) reg index 0x%04x: %d\n",
 			    cmd, index, ret);
 
+		ret = ret < 0 ? ret : -ENODATA;
+	}
+
 	return ret;
 }
 
diff --git a/drivers/net/usb/asix.h b/drivers/net/usb/asix.h
index 74162190bccc..8531b804021a 100644
--- a/drivers/net/usb/asix.h
+++ b/drivers/net/usb/asix.h
@@ -224,7 +224,6 @@ int asix_write_rx_ctl(struct usbnet *dev, u16 mode, int in_pm);
 
 u16 asix_read_medium_status(struct usbnet *dev, int in_pm);
 int asix_write_medium_mode(struct usbnet *dev, u16 mode, int in_pm);
-void asix_adjust_link(struct net_device *netdev);
 
 int asix_write_gpio(struct usbnet *dev, u16 value, int sleep, int in_pm);
 
diff --git a/drivers/net/usb/asix_common.c b/drivers/net/usb/asix_common.c
index 72ffc89b477a..7fd763917ae2 100644
--- a/drivers/net/usb/asix_common.c
+++ b/drivers/net/usb/asix_common.c
@@ -414,28 +414,6 @@ int asix_write_medium_mode(struct usbnet *dev, u16 mode, int in_pm)
 	return ret;
 }
 
-/* set MAC link settings according to information from phylib */
-void asix_adjust_link(struct net_device *netdev)
-{
-	struct phy_device *phydev = netdev->phydev;
-	struct usbnet *dev = netdev_priv(netdev);
-	u16 mode = 0;
-
-	if (phydev->link) {
-		mode = AX88772_MEDIUM_DEFAULT;
-
-		if (phydev->duplex == DUPLEX_HALF)
-			mode &= ~AX_MEDIUM_FD;
-
-		if (phydev->speed != SPEED_100)
-			mode &= ~AX_MEDIUM_PS;
-	}
-
-	asix_write_medium_mode(dev, mode, 0);
-	phy_print_status(phydev);
-	usbnet_link_change(dev, phydev->link, 0);
-}
-
 int asix_write_gpio(struct usbnet *dev, u16 value, int sleep, int in_pm)
 {
 	int ret;
diff --git a/drivers/net/usb/asix_devices.c b/drivers/net/usb/asix_devices.c
index 57d6e5abc30e..d9f5942ccc44 100644
--- a/drivers/net/usb/asix_devices.c
+++ b/drivers/net/usb/asix_devices.c
@@ -676,6 +676,7 @@ static int ax88772_init_mdio(struct usbnet *dev)
 	priv->mdio->read = &asix_mdio_bus_read;
 	priv->mdio->write = &asix_mdio_bus_write;
 	priv->mdio->name = "Asix MDIO Bus";
+	priv->mdio->phy_mask = ~(BIT(priv->phy_addr) | BIT(AX_EMBD_PHY_ADDR));
 	/* mii bus name is usb-<usb bus number>-<usb device number> */
 	snprintf(priv->mdio->id, MII_BUS_ID_SIZE, "usb-%03d:%03d",
 		 dev->udev->bus->busnum, dev->udev->devnum);
@@ -752,7 +753,6 @@ static void ax88772_mac_link_down(struct phylink_config *config,
 	struct usbnet *dev = netdev_priv(to_net_dev(config->dev));
 
 	asix_write_medium_mode(dev, 0, 0);
-	usbnet_link_change(dev, false, false);
 }
 
 static void ax88772_mac_link_up(struct phylink_config *config,
@@ -783,7 +783,6 @@ static void ax88772_mac_link_up(struct phylink_config *config,
 		m |= AX_MEDIUM_RFC;
 
 	asix_write_medium_mode(dev, m, 0);
-	usbnet_link_change(dev, true, false);
 }
 
 static const struct phylink_mac_ops ax88772_phylink_mac_ops = {
@@ -1350,10 +1349,9 @@ static const struct driver_info ax88772_info = {
 	.description = "ASIX AX88772 USB 2.0 Ethernet",
 	.bind = ax88772_bind,
 	.unbind = ax88772_unbind,
-	.status = asix_status,
 	.reset = ax88772_reset,
 	.stop = ax88772_stop,
-	.flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_LINK_INTR | FLAG_MULTI_PACKET,
+	.flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_MULTI_PACKET,
 	.rx_fixup = asix_rx_fixup_common,
 	.tx_fixup = asix_tx_fixup,
 };
@@ -1362,11 +1360,9 @@ static const struct driver_info ax88772b_info = {
 	.description = "ASIX AX88772B USB 2.0 Ethernet",
 	.bind = ax88772_bind,
 	.unbind = ax88772_unbind,
-	.status = asix_status,
 	.reset = ax88772_reset,
 	.stop = ax88772_stop,
-	.flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_LINK_INTR |
-	         FLAG_MULTI_PACKET,
+	.flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_MULTI_PACKET,
 	.rx_fixup = asix_rx_fixup_common,
 	.tx_fixup = asix_tx_fixup,
 	.data = FLAG_EEPROM_MAC,
@@ -1376,11 +1372,9 @@ static const struct driver_info lxausb_t1l_info = {
 	.description = "Linux Automation GmbH USB 10Base-T1L",
 	.bind = ax88772_bind,
 	.unbind = ax88772_unbind,
-	.status = asix_status,
 	.reset = ax88772_reset,
 	.stop = ax88772_stop,
-	.flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_LINK_INTR |
-		 FLAG_MULTI_PACKET,
+	.flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_MULTI_PACKET,
 	.rx_fixup = asix_rx_fixup_common,
 	.tx_fixup = asix_tx_fixup,
 	.data = FLAG_EEPROM_MAC,
@@ -1412,15 +1406,26 @@ static const struct driver_info hg20f9_info = {
 	.description = "HG20F9 USB 2.0 Ethernet",
 	.bind = ax88772_bind,
 	.unbind = ax88772_unbind,
-	.status = asix_status,
 	.reset = ax88772_reset,
-	.flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_LINK_INTR |
-	         FLAG_MULTI_PACKET,
+	.flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_MULTI_PACKET,
 	.rx_fixup = asix_rx_fixup_common,
 	.tx_fixup = asix_tx_fixup,
 	.data = FLAG_EEPROM_MAC,
 };
 
+static const struct driver_info lyconsys_fibergecko100_info = {
+	.description = "LyconSys FiberGecko 100 USB 2.0 to SFP Adapter",
+	.bind = ax88178_bind,
+	.status = asix_status,
+	.link_reset = ax88178_link_reset,
+	.reset = ax88178_link_reset,
+	.flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_LINK_INTR |
+		 FLAG_MULTI_PACKET,
+	.rx_fixup = asix_rx_fixup_common,
+	.tx_fixup = asix_tx_fixup,
+	.data = 0x20061201,
+};
+
 static const struct usb_device_id	products [] = {
 {
 	// Linksys USB200M
@@ -1578,6 +1583,10 @@ static const struct usb_device_id	products [] = {
 	// Linux Automation GmbH USB 10Base-T1L
 	USB_DEVICE(0x33f7, 0x0004),
 	.driver_info = (unsigned long) &lxausb_t1l_info,
+}, {
+	/* LyconSys FiberGecko 100 */
+	USB_DEVICE(0x1d2a, 0x0801),
+	.driver_info = (unsigned long) &lyconsys_fibergecko100_info,
 },
 	{ },		// END
 };
diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c
index a6469235d904..a032c1ded406 100644
--- a/drivers/net/usb/cdc_ether.c
+++ b/drivers/net/usb/cdc_ether.c
@@ -783,6 +783,13 @@ static const struct usb_device_id	products[] = {
 	.driver_info = 0,
 },
 
+/* Lenovo ThinkPad Hybrid USB-C with USB-A Dock (40af0135eu, based on Realtek RTL8153) */
+{
+	USB_DEVICE_AND_INTERFACE_INFO(LENOVO_VENDOR_ID, 0xa359, USB_CLASS_COMM,
+			USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
+	.driver_info = 0,
+},
+
 /* Aquantia AQtion USB to 5GbE Controller (based on AQC111U) */
 {
 	USB_DEVICE_AND_INTERFACE_INFO(AQUANTIA_VENDOR_ID, 0xc101,
diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index d5c47a2a62dc..4abfdfcf0e28 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -893,6 +893,10 @@ int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_
 		}
 	}
 
+	if (ctx->func_desc)
+		ctx->filtering_supported = !!(ctx->func_desc->bmNetworkCapabilities
+			& USB_CDC_NCM_NCAP_ETH_FILTER);
+
 	iface_no = ctx->data->cur_altsetting->desc.bInterfaceNumber;
 
 	/* Device-specific flags */
@@ -1899,6 +1903,14 @@ static void cdc_ncm_status(struct usbnet *dev, struct urb *urb)
 	}
 }
 
+static void cdc_ncm_update_filter(struct usbnet *dev)
+{
+	struct cdc_ncm_ctx *ctx = (struct cdc_ncm_ctx *)dev->data[0];
+
+	if (ctx->filtering_supported)
+		usbnet_cdc_update_filter(dev);
+}
+
 static const struct driver_info cdc_ncm_info = {
 	.description = "CDC NCM (NO ZLP)",
 	.flags = FLAG_POINTTOPOINT | FLAG_NO_SETINT | FLAG_MULTI_PACKET
@@ -1909,7 +1921,7 @@ static const struct driver_info cdc_ncm_info = {
 	.status = cdc_ncm_status,
 	.rx_fixup = cdc_ncm_rx_fixup,
 	.tx_fixup = cdc_ncm_tx_fixup,
-	.set_rx_mode = usbnet_cdc_update_filter,
+	.set_rx_mode = cdc_ncm_update_filter,
 };
 
 /* Same as cdc_ncm_info, but with FLAG_SEND_ZLP  */
@@ -1923,7 +1935,7 @@ static const struct driver_info cdc_ncm_zlp_info = {
 	.status = cdc_ncm_status,
 	.rx_fixup = cdc_ncm_rx_fixup,
 	.tx_fixup = cdc_ncm_tx_fixup,
-	.set_rx_mode = usbnet_cdc_update_filter,
+	.set_rx_mode = cdc_ncm_update_filter,
 };
 
 /* Same as cdc_ncm_info, but with FLAG_SEND_ZLP */
@@ -1965,7 +1977,7 @@ static const struct driver_info wwan_info = {
 	.status = cdc_ncm_status,
 	.rx_fixup = cdc_ncm_rx_fixup,
 	.tx_fixup = cdc_ncm_tx_fixup,
-	.set_rx_mode = usbnet_cdc_update_filter,
+	.set_rx_mode = cdc_ncm_update_filter,
 };
 
 /* Same as wwan_info, but with FLAG_NOARP  */
@@ -1979,7 +1991,7 @@ static const struct driver_info wwan_noarp_info = {
 	.status = cdc_ncm_status,
 	.rx_fixup = cdc_ncm_rx_fixup,
 	.tx_fixup = cdc_ncm_tx_fixup,
-	.set_rx_mode = usbnet_cdc_update_filter,
+	.set_rx_mode = cdc_ncm_update_filter,
 };
 
 static const struct usb_device_id cdc_devs[] = {
diff --git a/drivers/net/usb/ch9200.c b/drivers/net/usb/ch9200.c
index f69d9b902da0..a206ffa76f1b 100644
--- a/drivers/net/usb/ch9200.c
+++ b/drivers/net/usb/ch9200.c
@@ -178,6 +178,7 @@ static int ch9200_mdio_read(struct net_device *netdev, int phy_id, int loc)
 {
 	struct usbnet *dev = netdev_priv(netdev);
 	unsigned char buff[2];
+	int ret;
 
 	netdev_dbg(netdev, "%s phy_id:%02x loc:%02x\n",
 		   __func__, phy_id, loc);
@@ -185,8 +186,10 @@ static int ch9200_mdio_read(struct net_device *netdev, int phy_id, int loc)
 	if (phy_id != 0)
 		return -ENODEV;
 
-	control_read(dev, REQUEST_READ, 0, loc * 2, buff, 0x02,
-		     CONTROL_TIMEOUT_MS);
+	ret = control_read(dev, REQUEST_READ, 0, loc * 2, buff, 0x02,
+			   CONTROL_TIMEOUT_MS);
+	if (ret < 0)
+		return ret;
 
 	return (buff[0] | buff[1] << 8);
 }
diff --git a/drivers/net/usb/gl620a.c b/drivers/net/usb/gl620a.c
index 46af78caf457..0bfa37c14059 100644
--- a/drivers/net/usb/gl620a.c
+++ b/drivers/net/usb/gl620a.c
@@ -179,9 +179,7 @@ static int genelink_bind(struct usbnet *dev, struct usb_interface *intf)
 {
 	dev->hard_mtu = GL_RCV_BUF_SIZE;
 	dev->net->hard_header_len += 4;
-	dev->in = usb_rcvbulkpipe(dev->udev, dev->driver_info->in);
-	dev->out = usb_sndbulkpipe(dev->udev, dev->driver_info->out);
-	return 0;
+	return usbnet_get_endpoints(dev, intf);
 }
 
 static const struct driver_info	genelink_info = {
diff --git a/drivers/net/usb/ipheth.c b/drivers/net/usb/ipheth.c
index 46afb95ffabe..a19789b57190 100644
--- a/drivers/net/usb/ipheth.c
+++ b/drivers/net/usb/ipheth.c
@@ -61,7 +61,18 @@
 #define IPHETH_USBINTF_PROTO    1
 
 #define IPHETH_IP_ALIGN		2	/* padding at front of URB */
-#define IPHETH_NCM_HEADER_SIZE  (12 + 96) /* NCMH + NCM0 */
+/* On iOS devices, NCM headers in RX have a fixed size regardless of DPE count:
+ * - NTH16 (NCMH): 12 bytes, as per CDC NCM 1.0 spec
+ * - NDP16 (NCM0): 96 bytes, of which
+ *    - NDP16 fixed header: 8 bytes
+ *    - maximum of 22 DPEs (21 datagrams + trailer), 4 bytes each
+ */
+#define IPHETH_NDP16_MAX_DPE	22
+#define IPHETH_NDP16_HEADER_SIZE (sizeof(struct usb_cdc_ncm_ndp16) + \
+				  IPHETH_NDP16_MAX_DPE * \
+				  sizeof(struct usb_cdc_ncm_dpe16))
+#define IPHETH_NCM_HEADER_SIZE	(sizeof(struct usb_cdc_ncm_nth16) + \
+				 IPHETH_NDP16_HEADER_SIZE)
 #define IPHETH_TX_BUF_SIZE      ETH_FRAME_LEN
 #define IPHETH_RX_BUF_SIZE_LEGACY (IPHETH_IP_ALIGN + ETH_FRAME_LEN)
 #define IPHETH_RX_BUF_SIZE_NCM	65536
@@ -207,15 +218,23 @@ static int ipheth_rcvbulk_callback_legacy(struct urb *urb)
 	return ipheth_consume_skb(buf, len, dev);
 }
 
+/* In "NCM mode", the iOS device encapsulates RX (phone->computer) traffic
+ * in NCM Transfer Blocks (similarly to CDC NCM). However, unlike reverse
+ * tethering (handled by the `cdc_ncm` driver), regular tethering is not
+ * compliant with the CDC NCM spec, as the device is missing the necessary
+ * descriptors, and TX (computer->phone) traffic is not encapsulated
+ * at all. Thus `ipheth` implements a very limited subset of the spec with
+ * the sole purpose of parsing RX URBs.
+ */
 static int ipheth_rcvbulk_callback_ncm(struct urb *urb)
 {
 	struct usb_cdc_ncm_nth16 *ncmh;
 	struct usb_cdc_ncm_ndp16 *ncm0;
 	struct usb_cdc_ncm_dpe16 *dpe;
 	struct ipheth_device *dev;
+	u16 dg_idx, dg_len;
 	int retval = -EINVAL;
 	char *buf;
-	int len;
 
 	dev = urb->context;
 
@@ -226,40 +245,42 @@ static int ipheth_rcvbulk_callback_ncm(struct urb *urb)
 
 	ncmh = urb->transfer_buffer;
 	if (ncmh->dwSignature != cpu_to_le32(USB_CDC_NCM_NTH16_SIGN) ||
-	    le16_to_cpu(ncmh->wNdpIndex) >= urb->actual_length) {
-		dev->net->stats.rx_errors++;
-		return retval;
-	}
+	    /* On iOS, NDP16 directly follows NTH16 */
+	    ncmh->wNdpIndex != cpu_to_le16(sizeof(struct usb_cdc_ncm_nth16)))
+		goto rx_error;
 
-	ncm0 = urb->transfer_buffer + le16_to_cpu(ncmh->wNdpIndex);
-	if (ncm0->dwSignature != cpu_to_le32(USB_CDC_NCM_NDP16_NOCRC_SIGN) ||
-	    le16_to_cpu(ncmh->wHeaderLength) + le16_to_cpu(ncm0->wLength) >=
-	    urb->actual_length) {
-		dev->net->stats.rx_errors++;
-		return retval;
-	}
+	ncm0 = urb->transfer_buffer + sizeof(struct usb_cdc_ncm_nth16);
+	if (ncm0->dwSignature != cpu_to_le32(USB_CDC_NCM_NDP16_NOCRC_SIGN))
+		goto rx_error;
 
 	dpe = ncm0->dpe16;
-	while (le16_to_cpu(dpe->wDatagramIndex) != 0 &&
-	       le16_to_cpu(dpe->wDatagramLength) != 0) {
-		if (le16_to_cpu(dpe->wDatagramIndex) >= urb->actual_length ||
-		    le16_to_cpu(dpe->wDatagramIndex) +
-		    le16_to_cpu(dpe->wDatagramLength) > urb->actual_length) {
+	for (int dpe_i = 0; dpe_i < IPHETH_NDP16_MAX_DPE; ++dpe_i, ++dpe) {
+		dg_idx = le16_to_cpu(dpe->wDatagramIndex);
+		dg_len = le16_to_cpu(dpe->wDatagramLength);
+
+		/* Null DPE must be present after last datagram pointer entry
+		 * (3.3.1 USB CDC NCM spec v1.0)
+		 */
+		if (dg_idx == 0 && dg_len == 0)
+			return 0;
+
+		if (dg_idx < IPHETH_NCM_HEADER_SIZE ||
+		    dg_idx >= urb->actual_length ||
+		    dg_len > urb->actual_length - dg_idx) {
 			dev->net->stats.rx_length_errors++;
 			return retval;
 		}
 
-		buf = urb->transfer_buffer + le16_to_cpu(dpe->wDatagramIndex);
-		len = le16_to_cpu(dpe->wDatagramLength);
+		buf = urb->transfer_buffer + dg_idx;
 
-		retval = ipheth_consume_skb(buf, len, dev);
+		retval = ipheth_consume_skb(buf, dg_len, dev);
 		if (retval != 0)
 			return retval;
-
-		dpe++;
 	}
 
-	return 0;
+rx_error:
+	dev->net->stats.rx_errors++;
+	return retval;
 }
 
 static void ipheth_rcvbulk_callback(struct urb *urb)
diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index 531b1b6a37d1..2f8637224b69 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -4229,8 +4229,6 @@ static void lan78xx_disconnect(struct usb_interface *intf)
 	if (!dev)
 		return;
 
-	netif_napi_del(&dev->napi);
-
 	udev = interface_to_usbdev(intf);
 	net = dev->net;
 
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 9fe7f704a2f7..7e0608f56835 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1365,9 +1365,11 @@ static const struct usb_device_id products[] = {
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x10a0, 0)}, /* Telit FN920C04 */
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x10a4, 0)}, /* Telit FN920C04 */
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x10a9, 0)}, /* Telit FN920C04 */
+	{QMI_QUIRK_SET_DTR(0x1bc7, 0x10b0, 0)}, /* Telit FE990B */
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x10c0, 0)}, /* Telit FE910C04 */
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x10c4, 0)}, /* Telit FE910C04 */
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x10c8, 0)}, /* Telit FE910C04 */
+	{QMI_QUIRK_SET_DTR(0x1bc7, 0x10d0, 0)}, /* Telit FN990B */
 	{QMI_FIXED_INTF(0x1bc7, 0x1100, 3)},	/* Telit ME910 */
 	{QMI_FIXED_INTF(0x1bc7, 0x1101, 3)},	/* Telit ME910 dual modem */
 	{QMI_FIXED_INTF(0x1bc7, 0x1200, 5)},	/* Telit LE920 */
@@ -1424,6 +1426,7 @@ static const struct usb_device_id products[] = {
 	{QMI_QUIRK_SET_DTR(0x22de, 0x9051, 2)}, /* Hucom Wireless HM-211S/K */
 	{QMI_FIXED_INTF(0x22de, 0x9061, 3)},	/* WeTelecom WPD-600N */
 	{QMI_QUIRK_SET_DTR(0x1e0e, 0x9001, 5)},	/* SIMCom 7100E, 7230E, 7600E ++ */
+	{QMI_QUIRK_SET_DTR(0x1e0e, 0x9071, 3)},	/* SIMCom 8230C ++ */
 	{QMI_QUIRK_SET_DTR(0x2c7c, 0x0121, 4)},	/* Quectel EC21 Mini PCIe */
 	{QMI_QUIRK_SET_DTR(0x2c7c, 0x0191, 4)},	/* Quectel EG91 */
 	{QMI_QUIRK_SET_DTR(0x2c7c, 0x0195, 4)},	/* Quectel EG95 */
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 468c73974046..2cab046749a9 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -785,6 +785,7 @@ enum rtl8152_flags {
 #define DEVICE_ID_THINKPAD_USB_C_DONGLE			0x720c
 #define DEVICE_ID_THINKPAD_USB_C_DOCK_GEN2		0xa387
 #define DEVICE_ID_THINKPAD_USB_C_DOCK_GEN3		0x3062
+#define DEVICE_ID_THINKPAD_HYBRID_USB_C_DOCK		0xa359
 
 struct tally_counter {
 	__le64	tx_packets;
@@ -9787,6 +9788,7 @@ static bool rtl8152_supports_lenovo_macpassthru(struct usb_device *udev)
 		case DEVICE_ID_THINKPAD_USB_C_DOCK_GEN2:
 		case DEVICE_ID_THINKPAD_USB_C_DOCK_GEN3:
 		case DEVICE_ID_THINKPAD_USB_C_DONGLE:
+		case DEVICE_ID_THINKPAD_HYBRID_USB_C_DOCK:
 			return 1;
 		}
 	} else if (vendor_id == VENDOR_ID_REALTEK && parent_vendor_id == VENDOR_ID_LENOVO) {
@@ -10064,6 +10066,8 @@ static const struct usb_device_id rtl8152_table[] = {
 	{ USB_DEVICE(VENDOR_ID_MICROSOFT, 0x0927) },
 	{ USB_DEVICE(VENDOR_ID_MICROSOFT, 0x0c5e) },
 	{ USB_DEVICE(VENDOR_ID_SAMSUNG, 0xa101) },
+
+	/* Lenovo */
 	{ USB_DEVICE(VENDOR_ID_LENOVO,  0x304f) },
 	{ USB_DEVICE(VENDOR_ID_LENOVO,  0x3054) },
 	{ USB_DEVICE(VENDOR_ID_LENOVO,  0x3062) },
@@ -10074,11 +10078,14 @@ static const struct usb_device_id rtl8152_table[] = {
 	{ USB_DEVICE(VENDOR_ID_LENOVO,  0x720c) },
 	{ USB_DEVICE(VENDOR_ID_LENOVO,  0x7214) },
 	{ USB_DEVICE(VENDOR_ID_LENOVO,  0x721e) },
+	{ USB_DEVICE(VENDOR_ID_LENOVO,  0xa359) },
 	{ USB_DEVICE(VENDOR_ID_LENOVO,  0xa387) },
+
 	{ USB_DEVICE(VENDOR_ID_LINKSYS, 0x0041) },
 	{ USB_DEVICE(VENDOR_ID_NVIDIA,  0x09ff) },
 	{ USB_DEVICE(VENDOR_ID_TPLINK,  0x0601) },
 	{ USB_DEVICE(VENDOR_ID_DLINK,   0xb301) },
+	{ USB_DEVICE(VENDOR_ID_DELL,    0xb097) },
 	{ USB_DEVICE(VENDOR_ID_ASUS,    0x1976) },
 	{}
 };
diff --git a/drivers/net/usb/r8153_ecm.c b/drivers/net/usb/r8153_ecm.c
index 20b2df8d74ae..8d860dacdf49 100644
--- a/drivers/net/usb/r8153_ecm.c
+++ b/drivers/net/usb/r8153_ecm.c
@@ -135,6 +135,12 @@ static const struct usb_device_id products[] = {
 				      USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
 	.driver_info = (unsigned long)&r8153_info,
 },
+/* Lenovo ThinkPad Hybrid USB-C with USB-A Dock (40af0135eu, based on Realtek RTL8153) */
+{
+	USB_DEVICE_AND_INTERFACE_INFO(VENDOR_ID_LENOVO, 0xa359, USB_CLASS_COMM,
+				      USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
+	.driver_info = (unsigned long)&r8153_info,
+},
 
 	{ },		/* END */
 };
diff --git a/drivers/net/usb/rtl8150.c b/drivers/net/usb/rtl8150.c
index 01a3b2417a54..ddff6f19ff98 100644
--- a/drivers/net/usb/rtl8150.c
+++ b/drivers/net/usb/rtl8150.c
@@ -71,6 +71,14 @@
 #define MSR_SPEED		(1<<3)
 #define MSR_LINK		(1<<2)
 
+/* USB endpoints */
+enum rtl8150_usb_ep {
+	RTL8150_USB_EP_CONTROL = 0,
+	RTL8150_USB_EP_BULK_IN = 1,
+	RTL8150_USB_EP_BULK_OUT = 2,
+	RTL8150_USB_EP_INT_IN = 3,
+};
+
 /* Interrupt pipe data */
 #define INT_TSR			0x00
 #define INT_RSR			0x01
@@ -867,6 +875,13 @@ static int rtl8150_probe(struct usb_interface *intf,
 	struct usb_device *udev = interface_to_usbdev(intf);
 	rtl8150_t *dev;
 	struct net_device *netdev;
+	static const u8 bulk_ep_addr[] = {
+		RTL8150_USB_EP_BULK_IN | USB_DIR_IN,
+		RTL8150_USB_EP_BULK_OUT | USB_DIR_OUT,
+		0};
+	static const u8 int_ep_addr[] = {
+		RTL8150_USB_EP_INT_IN | USB_DIR_IN,
+		0};
 
 	netdev = alloc_etherdev(sizeof(rtl8150_t));
 	if (!netdev)
@@ -880,6 +895,13 @@ static int rtl8150_probe(struct usb_interface *intf,
 		return -ENOMEM;
 	}
 
+	/* Verify that all required endpoints are present */
+	if (!usb_check_bulk_endpoints(intf, bulk_ep_addr) ||
+	    !usb_check_int_endpoints(intf, int_ep_addr)) {
+		dev_err(&intf->dev, "couldn't find required endpoints\n");
+		goto out;
+	}
+
 	tasklet_setup(&dev->tl, rx_fixup);
 	spin_lock_init(&dev->rx_pool_lock);
 
diff --git a/drivers/net/usb/sierra_net.c b/drivers/net/usb/sierra_net.c
index 3d239b8d1a1b..52e9fd8116f9 100644
--- a/drivers/net/usb/sierra_net.c
+++ b/drivers/net/usb/sierra_net.c
@@ -689,6 +689,10 @@ static int sierra_net_bind(struct usbnet *dev, struct usb_interface *intf)
 			status);
 		return -ENODEV;
 	}
+	if (!dev->status) {
+		dev_err(&dev->udev->dev, "No status endpoint found");
+		return -ENODEV;
+	}
 	/* Initialize sierra private data */
 	priv = kzalloc(sizeof *priv, GFP_KERNEL);
 	if (!priv)
diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index 44179f4e807f..ccf45ca2feb5 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -178,6 +178,17 @@ int usbnet_get_ethernet_addr(struct usbnet *dev, int iMACAddress)
 }
 EXPORT_SYMBOL_GPL(usbnet_get_ethernet_addr);
 
+static bool usbnet_needs_usb_name_format(struct usbnet *dev, struct net_device *net)
+{
+	/* Point to point devices which don't have a real MAC address
+	 * (or report a fake local one) have historically used the usb%d
+	 * naming. Preserve this..
+	 */
+	return (dev->driver_info->flags & FLAG_POINTTOPOINT) != 0 &&
+		(is_zero_ether_addr(net->dev_addr) ||
+		 is_local_ether_addr(net->dev_addr));
+}
+
 static void intr_complete (struct urb *urb)
 {
 	struct usbnet	*dev = urb->context;
@@ -519,7 +530,8 @@ static int rx_submit (struct usbnet *dev, struct urb *urb, gfp_t flags)
 	    netif_device_present (dev->net) &&
 	    test_bit(EVENT_DEV_OPEN, &dev->flags) &&
 	    !test_bit (EVENT_RX_HALT, &dev->flags) &&
-	    !test_bit (EVENT_DEV_ASLEEP, &dev->flags)) {
+	    !test_bit (EVENT_DEV_ASLEEP, &dev->flags) &&
+	    !usbnet_going_away(dev)) {
 		switch (retval = usb_submit_urb (urb, GFP_ATOMIC)) {
 		case -EPIPE:
 			usbnet_defer_kevent (dev, EVENT_RX_HALT);
@@ -540,8 +552,7 @@ static int rx_submit (struct usbnet *dev, struct urb *urb, gfp_t flags)
 			tasklet_schedule (&dev->bh);
 			break;
 		case 0:
-			if (!usbnet_going_away(dev))
-				__usbnet_queue_skb(&dev->rxq, skb, rx_start);
+			__usbnet_queue_skb(&dev->rxq, skb, rx_start);
 		}
 	} else {
 		netif_dbg(dev, ifdown, dev->net, "rx: stopped\n");
@@ -1102,6 +1113,9 @@ static void __handle_link_change(struct usbnet *dev)
 	if (!test_bit(EVENT_DEV_OPEN, &dev->flags))
 		return;
 
+	if (test_and_clear_bit(EVENT_LINK_CARRIER_ON, &dev->flags))
+		netif_carrier_on(dev->net);
+
 	if (!netif_carrier_ok(dev->net)) {
 		/* kill URBs for reading packets to save bus bandwidth */
 		unlink_urbs(dev, &dev->rxq);
@@ -1762,13 +1776,11 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod)
 		if (status < 0)
 			goto out1;
 
-		// heuristic:  "usb%d" for links we know are two-host,
-		// else "eth%d" when there's reasonable doubt.  userspace
-		// can rename the link if it knows better.
+		/* heuristic: rename to "eth%d" if we are not sure this link
+		 * is two-host (these links keep "usb%d")
+		 */
 		if ((dev->driver_info->flags & FLAG_ETHER) != 0 &&
-		    ((dev->driver_info->flags & FLAG_POINTTOPOINT) == 0 ||
-		     /* somebody touched it*/
-		     !is_zero_ether_addr(net->dev_addr)))
+		    !usbnet_needs_usb_name_format(dev, net))
 			strscpy(net->name, "eth%d", sizeof(net->name));
 		/* WLAN devices should always be named "wlan%d" */
 		if ((dev->driver_info->flags & FLAG_WLAN) != 0)
@@ -2000,10 +2012,12 @@ EXPORT_SYMBOL(usbnet_manage_power);
 void usbnet_link_change(struct usbnet *dev, bool link, bool need_reset)
 {
 	/* update link after link is reseted */
-	if (link && !need_reset)
-		netif_carrier_on(dev->net);
-	else
+	if (link && !need_reset) {
+		set_bit(EVENT_LINK_CARRIER_ON, &dev->flags);
+	} else {
+		clear_bit(EVENT_LINK_CARRIER_ON, &dev->flags);
 		netif_carrier_off(dev->net);
+	}
 
 	if (need_reset && link)
 		usbnet_defer_kevent(dev, EVENT_LINK_RESET);
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 60027b439021..fb3908798458 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -298,6 +298,10 @@ struct send_queue {
 
 	/* Record whether sq is in reset state. */
 	bool reset;
+
+	struct xsk_buff_pool *xsk_pool;
+
+	dma_addr_t xsk_hdr_dma_addr;
 };
 
 /* Internal representation of a receive virtqueue */
@@ -501,6 +505,8 @@ struct virtio_net_common_hdr {
 	};
 };
 
+static struct virtio_net_common_hdr xsk_hdr;
+
 static void virtnet_sq_free_unused_buf(struct virtqueue *vq, void *buf);
 static void virtnet_sq_free_unused_buf_done(struct virtqueue *vq);
 static int virtnet_xdp_handler(struct bpf_prog *xdp_prog, struct xdp_buff *xdp,
@@ -759,6 +765,26 @@ static unsigned int mergeable_ctx_to_truesize(void *mrg_ctx)
 	return (unsigned long)mrg_ctx & ((1 << MRG_CTX_HEADER_SHIFT) - 1);
 }
 
+static int check_mergeable_len(struct net_device *dev, void *mrg_ctx,
+			       unsigned int len)
+{
+	unsigned int headroom, tailroom, room, truesize;
+
+	truesize = mergeable_ctx_to_truesize(mrg_ctx);
+	headroom = mergeable_ctx_to_headroom(mrg_ctx);
+	tailroom = headroom ? sizeof(struct skb_shared_info) : 0;
+	room = SKB_DATA_ALIGN(headroom + tailroom);
+
+	if (len > truesize - room) {
+		pr_debug("%s: rx error: len %u exceeds truesize %lu\n",
+			 dev->name, len, (unsigned long)(truesize - room));
+		DEV_STATS_INC(dev, rx_length_errors);
+		return -1;
+	}
+
+	return 0;
+}
+
 static struct sk_buff *virtnet_build_skb(void *buf, unsigned int buflen,
 					 unsigned int headroom,
 					 unsigned int len)
@@ -1092,15 +1118,29 @@ static void sg_fill_dma(struct scatterlist *sg, dma_addr_t addr, u32 len)
 	sg->length = len;
 }
 
+/* Note that @len is the length of received data without virtio header */
 static struct xdp_buff *buf_to_xdp(struct virtnet_info *vi,
-				   struct receive_queue *rq, void *buf, u32 len)
+				   struct receive_queue *rq, void *buf,
+				   u32 len, bool first_buf)
 {
 	struct xdp_buff *xdp;
 	u32 bufsize;
 
 	xdp = (struct xdp_buff *)buf;
 
-	bufsize = xsk_pool_get_rx_frame_size(rq->xsk_pool) + vi->hdr_len;
+	/* In virtnet_add_recvbuf_xsk, we use part of XDP_PACKET_HEADROOM for
+	 * virtio header and ask the vhost to fill data from
+	 *         hard_start + XDP_PACKET_HEADROOM - vi->hdr_len
+	 * The first buffer has virtio header so the remaining region for frame
+	 * data is
+	 *         xsk_pool_get_rx_frame_size()
+	 * While other buffers than the first one do not have virtio header, so
+	 * the maximum frame data's length can be
+	 *         xsk_pool_get_rx_frame_size() + vi->hdr_len
+	 */
+	bufsize = xsk_pool_get_rx_frame_size(rq->xsk_pool);
+	if (!first_buf)
+		bufsize += vi->hdr_len;
 
 	if (unlikely(len > bufsize)) {
 		pr_debug("%s: rx error: len %u exceeds truesize %u\n",
@@ -1225,7 +1265,7 @@ static int xsk_append_merge_buffer(struct virtnet_info *vi,
 
 		u64_stats_add(&stats->bytes, len);
 
-		xdp = buf_to_xdp(vi, rq, buf, len);
+		xdp = buf_to_xdp(vi, rq, buf, len, false);
 		if (!xdp)
 			goto err;
 
@@ -1323,7 +1363,7 @@ static void virtnet_receive_xsk_buf(struct virtnet_info *vi, struct receive_queu
 
 	u64_stats_add(&stats->bytes, len);
 
-	xdp = buf_to_xdp(vi, rq, buf, len);
+	xdp = buf_to_xdp(vi, rq, buf, len, true);
 	if (!xdp)
 		return;
 
@@ -1643,7 +1683,8 @@ static unsigned int virtnet_get_headroom(struct virtnet_info *vi)
  * across multiple buffers (num_buf > 1), and we make sure buffers
  * have enough headroom.
  */
-static struct page *xdp_linearize_page(struct receive_queue *rq,
+static struct page *xdp_linearize_page(struct net_device *dev,
+				       struct receive_queue *rq,
 				       int *num_buf,
 				       struct page *p,
 				       int offset,
@@ -1663,18 +1704,27 @@ static struct page *xdp_linearize_page(struct receive_queue *rq,
 	memcpy(page_address(page) + page_off, page_address(p) + offset, *len);
 	page_off += *len;
 
+	/* Only mergeable mode can go inside this while loop. In small mode,
+	 * *num_buf == 1, so it cannot go inside.
+	 */
 	while (--*num_buf) {
 		unsigned int buflen;
 		void *buf;
+		void *ctx;
 		int off;
 
-		buf = virtnet_rq_get_buf(rq, &buflen, NULL);
+		buf = virtnet_rq_get_buf(rq, &buflen, &ctx);
 		if (unlikely(!buf))
 			goto err_buf;
 
 		p = virt_to_head_page(buf);
 		off = buf - page_address(p);
 
+		if (check_mergeable_len(dev, ctx, buflen)) {
+			put_page(p);
+			goto err_buf;
+		}
+
 		/* guard against a misconfigured or uncooperative backend that
 		 * is sending packet larger than the MTU.
 		 */
@@ -1763,7 +1813,7 @@ static struct sk_buff *receive_small_xdp(struct net_device *dev,
 		headroom = vi->hdr_len + header_offset;
 		buflen = SKB_DATA_ALIGN(GOOD_PACKET_LEN + headroom) +
 			SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
-		xdp_page = xdp_linearize_page(rq, &num_buf, page,
+		xdp_page = xdp_linearize_page(dev, rq, &num_buf, page,
 					      offset, header_offset,
 					      &tlen);
 		if (!xdp_page)
@@ -2098,7 +2148,7 @@ static void *mergeable_xdp_get_buf(struct virtnet_info *vi,
 	 */
 	if (!xdp_prog->aux->xdp_has_frags) {
 		/* linearize data for XDP */
-		xdp_page = xdp_linearize_page(rq, num_buf,
+		xdp_page = xdp_linearize_page(vi->dev, rq, num_buf,
 					      *page, offset,
 					      XDP_PACKET_HEADROOM,
 					      len);
@@ -3225,6 +3275,12 @@ static int virtnet_tx_resize(struct virtnet_info *vi, struct send_queue *sq,
 {
 	int qindex, err;
 
+	if (ring_num <= MAX_SKB_FRAGS + 2) {
+		netdev_err(vi->dev, "tx size (%d) cannot be smaller than %d\n",
+			   ring_num, MAX_SKB_FRAGS + 2);
+		return -EINVAL;
+	}
+
 	qindex = sq - vi->sq;
 
 	virtnet_tx_pause(vi, sq);
@@ -5421,6 +5477,10 @@ static void virtnet_get_base_stats(struct net_device *dev,
 
 	if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_TX_SPEED)
 		tx->hw_drop_ratelimits = 0;
+
+	netdev_stat_queue_sum(dev,
+			      dev->real_num_rx_queues, vi->max_queue_pairs, rx,
+			      dev->real_num_tx_queues, vi->max_queue_pairs, tx);
 }
 
 static const struct netdev_stat_ops virtnet_stat_ops = {
@@ -5537,7 +5597,7 @@ static int virtnet_rq_bind_xsk_pool(struct virtnet_info *vi, struct receive_queu
 
 	virtnet_rx_pause(vi, rq);
 
-	err = virtqueue_reset(rq->vq, virtnet_rq_unmap_free_buf);
+	err = virtqueue_reset(rq->vq, virtnet_rq_unmap_free_buf, NULL);
 	if (err) {
 		netdev_err(vi->dev, "reset rx fail: rx queue index: %d err: %d\n", qindex, err);
 
@@ -5556,6 +5616,30 @@ unreg:
 	return err;
 }
 
+static int virtnet_sq_bind_xsk_pool(struct virtnet_info *vi,
+				    struct send_queue *sq,
+				    struct xsk_buff_pool *pool)
+{
+	int err, qindex;
+
+	qindex = sq - vi->sq;
+
+	virtnet_tx_pause(vi, sq);
+
+	err = virtqueue_reset(sq->vq, virtnet_sq_free_unused_buf,
+			      virtnet_sq_free_unused_buf_done);
+	if (err) {
+		netdev_err(vi->dev, "reset tx fail: tx queue index: %d err: %d\n", qindex, err);
+		pool = NULL;
+	}
+
+	sq->xsk_pool = pool;
+
+	virtnet_tx_resume(vi, sq);
+
+	return err;
+}
+
 static int virtnet_xsk_pool_enable(struct net_device *dev,
 				   struct xsk_buff_pool *pool,
 				   u16 qid)
@@ -5564,6 +5648,7 @@ static int virtnet_xsk_pool_enable(struct net_device *dev,
 	struct receive_queue *rq;
 	struct device *dma_dev;
 	struct send_queue *sq;
+	dma_addr_t hdr_dma;
 	int err, size;
 
 	if (vi->hdr_len > xsk_pool_get_headroom(pool))
@@ -5601,6 +5686,13 @@ static int virtnet_xsk_pool_enable(struct net_device *dev,
 	if (!rq->xsk_buffs)
 		return -ENOMEM;
 
+	hdr_dma = virtqueue_dma_map_single_attrs(sq->vq, &xsk_hdr, vi->hdr_len,
+						 DMA_TO_DEVICE, 0);
+	if (virtqueue_dma_mapping_error(sq->vq, hdr_dma)) {
+		err = -ENOMEM;
+		goto err_free_buffs;
+	}
+
 	err = xsk_pool_dma_map(pool, dma_dev, 0);
 	if (err)
 		goto err_xsk_map;
@@ -5609,11 +5701,26 @@ static int virtnet_xsk_pool_enable(struct net_device *dev,
 	if (err)
 		goto err_rq;
 
+	err = virtnet_sq_bind_xsk_pool(vi, sq, pool);
+	if (err)
+		goto err_sq;
+
+	/* Now, we do not support tx offload(such as tx csum), so all the tx
+	 * virtnet hdr is zero. So all the tx packets can share a single hdr.
+	 */
+	sq->xsk_hdr_dma_addr = hdr_dma;
+
 	return 0;
 
+err_sq:
+	virtnet_rq_bind_xsk_pool(vi, rq, NULL);
 err_rq:
 	xsk_pool_dma_unmap(pool, 0);
 err_xsk_map:
+	virtqueue_dma_unmap_single_attrs(rq->vq, hdr_dma, vi->hdr_len,
+					 DMA_TO_DEVICE, 0);
+err_free_buffs:
+	kvfree(rq->xsk_buffs);
 	return err;
 }
 
@@ -5622,19 +5729,24 @@ static int virtnet_xsk_pool_disable(struct net_device *dev, u16 qid)
 	struct virtnet_info *vi = netdev_priv(dev);
 	struct xsk_buff_pool *pool;
 	struct receive_queue *rq;
+	struct send_queue *sq;
 	int err;
 
 	if (qid >= vi->curr_queue_pairs)
 		return -EINVAL;
 
+	sq = &vi->sq[qid];
 	rq = &vi->rq[qid];
 
 	pool = rq->xsk_pool;
 
 	err = virtnet_rq_bind_xsk_pool(vi, rq, NULL);
+	err |= virtnet_sq_bind_xsk_pool(vi, sq, NULL);
 
 	xsk_pool_dma_unmap(pool, 0);
 
+	virtqueue_dma_unmap_single_attrs(sq->vq, sq->xsk_hdr_dma_addr,
+					 vi->hdr_len, DMA_TO_DEVICE, 0);
 	kvfree(rq->xsk_buffs);
 
 	return err;
@@ -6696,7 +6808,7 @@ static int virtnet_probe(struct virtio_device *vdev)
 	   otherwise get link status from config. */
 	netif_carrier_off(dev);
 	if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_STATUS)) {
-		virtnet_config_changed_work(&vi->config_work);
+		virtio_config_changed(vi->vdev);
 	} else {
 		vi->status = VIRTIO_NET_S_LINK_UP;
 		virtnet_update_settings(vi);
diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c
index b70654c7ad34..c48c2de6f961 100644
--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -1560,6 +1560,30 @@ vmxnet3_get_hdr_len(struct vmxnet3_adapter *adapter, struct sk_buff *skb,
 	return (hlen + (hdr.tcp->doff << 2));
 }
 
+static void
+vmxnet3_lro_tunnel(struct sk_buff *skb, __be16 ip_proto)
+{
+	struct udphdr *uh = NULL;
+
+	if (ip_proto == htons(ETH_P_IP)) {
+		struct iphdr *iph = (struct iphdr *)skb->data;
+
+		if (iph->protocol == IPPROTO_UDP)
+			uh = (struct udphdr *)(iph + 1);
+	} else {
+		struct ipv6hdr *iph = (struct ipv6hdr *)skb->data;
+
+		if (iph->nexthdr == IPPROTO_UDP)
+			uh = (struct udphdr *)(iph + 1);
+	}
+	if (uh) {
+		if (uh->check)
+			skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL_CSUM;
+		else
+			skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL;
+	}
+}
+
 static int
 vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq,
 		       struct vmxnet3_adapter *adapter, int quota)
@@ -1873,6 +1897,8 @@ sop_done:
 			if (segCnt != 0 && mss != 0) {
 				skb_shinfo(skb)->gso_type = rcd->v4 ?
 					SKB_GSO_TCPV4 : SKB_GSO_TCPV6;
+				if (encap_lro)
+					vmxnet3_lro_tunnel(skb, skb->protocol);
 				skb_shinfo(skb)->gso_size = mss;
 				skb_shinfo(skb)->gso_segs = segCnt;
 			} else if ((segCnt != 0 || skb->len > mtu) && !encap_lro) {
@@ -3599,8 +3625,6 @@ vmxnet3_change_mtu(struct net_device *netdev, int new_mtu)
 	struct vmxnet3_adapter *adapter = netdev_priv(netdev);
 	int err = 0;
 
-	WRITE_ONCE(netdev->mtu, new_mtu);
-
 	/*
 	 * Reset_work may be in the middle of resetting the device, wait for its
 	 * completion.
@@ -3614,6 +3638,7 @@ vmxnet3_change_mtu(struct net_device *netdev, int new_mtu)
 
 		/* we need to re-create the rx queue based on the new mtu */
 		vmxnet3_rq_destroy_all(adapter);
+		WRITE_ONCE(netdev->mtu, new_mtu);
 		vmxnet3_adjust_rx_ring_size(adapter);
 		err = vmxnet3_rq_create_all(adapter);
 		if (err) {
@@ -3630,6 +3655,8 @@ vmxnet3_change_mtu(struct net_device *netdev, int new_mtu)
 				   "Closing it\n", err);
 			goto out;
 		}
+	} else {
+		WRITE_ONCE(netdev->mtu, new_mtu);
 	}
 
 out:
diff --git a/drivers/net/vmxnet3/vmxnet3_xdp.c b/drivers/net/vmxnet3/vmxnet3_xdp.c
index 1341374a4588..5f470499e600 100644
--- a/drivers/net/vmxnet3/vmxnet3_xdp.c
+++ b/drivers/net/vmxnet3/vmxnet3_xdp.c
@@ -28,7 +28,7 @@ vmxnet3_xdp_get_tq(struct vmxnet3_adapter *adapter)
 	if (likely(cpu < tq_number))
 		tq = &adapter->tx_queue[cpu];
 	else
-		tq = &adapter->tx_queue[reciprocal_scale(cpu, tq_number)];
+		tq = &adapter->tx_queue[cpu % tq_number];
 
 	return tq;
 }
@@ -124,6 +124,7 @@ vmxnet3_xdp_xmit_frame(struct vmxnet3_adapter *adapter,
 	u32 buf_size;
 	u32 dw2;
 
+	spin_lock_irq(&tq->tx_lock);
 	dw2 = (tq->tx_ring.gen ^ 0x1) << VMXNET3_TXD_GEN_SHIFT;
 	dw2 |= xdpf->len;
 	ctx.sop_txd = tq->tx_ring.base + tq->tx_ring.next2fill;
@@ -134,6 +135,7 @@ vmxnet3_xdp_xmit_frame(struct vmxnet3_adapter *adapter,
 
 	if (vmxnet3_cmd_ring_desc_avail(&tq->tx_ring) == 0) {
 		tq->stats.tx_ring_full++;
+		spin_unlock_irq(&tq->tx_lock);
 		return -ENOSPC;
 	}
 
@@ -142,8 +144,10 @@ vmxnet3_xdp_xmit_frame(struct vmxnet3_adapter *adapter,
 		tbi->dma_addr = dma_map_single(&adapter->pdev->dev,
 					       xdpf->data, buf_size,
 					       DMA_TO_DEVICE);
-		if (dma_mapping_error(&adapter->pdev->dev, tbi->dma_addr))
+		if (dma_mapping_error(&adapter->pdev->dev, tbi->dma_addr)) {
+			spin_unlock_irq(&tq->tx_lock);
 			return -EFAULT;
+		}
 		tbi->map_type |= VMXNET3_MAP_SINGLE;
 	} else { /* XDP buffer from page pool */
 		page = virt_to_page(xdpf->data);
@@ -182,6 +186,7 @@ vmxnet3_xdp_xmit_frame(struct vmxnet3_adapter *adapter,
 	dma_wmb();
 	gdesc->dword[2] = cpu_to_le32(le32_to_cpu(gdesc->dword[2]) ^
 						  VMXNET3_TXD_GEN);
+	spin_unlock_irq(&tq->tx_lock);
 
 	/* No need to handle the case when tx_num_deferred doesn't reach
 	 * threshold. Backend driver at hypervisor side will poll and reset
@@ -225,6 +230,7 @@ vmxnet3_xdp_xmit(struct net_device *dev,
 {
 	struct vmxnet3_adapter *adapter = netdev_priv(dev);
 	struct vmxnet3_tx_queue *tq;
+	struct netdev_queue *nq;
 	int i;
 
 	if (unlikely(test_bit(VMXNET3_STATE_BIT_QUIESCED, &adapter->state)))
@@ -236,6 +242,9 @@ vmxnet3_xdp_xmit(struct net_device *dev,
 	if (tq->stopped)
 		return -ENETDOWN;
 
+	nq = netdev_get_tx_queue(adapter->netdev, tq->qid);
+
+	__netif_tx_lock(nq, smp_processor_id());
 	for (i = 0; i < n; i++) {
 		if (vmxnet3_xdp_xmit_frame(adapter, frames[i], tq, true)) {
 			tq->stats.xdp_xmit_err++;
@@ -243,6 +252,7 @@ vmxnet3_xdp_xmit(struct net_device *dev,
 		}
 	}
 	tq->stats.xdp_xmit += i;
+	__netif_tx_unlock(nq);
 
 	return i;
 }
@@ -387,7 +397,7 @@ vmxnet3_process_xdp(struct vmxnet3_adapter *adapter,
 
 	xdp_init_buff(&xdp, PAGE_SIZE, &rq->xdp_rxq);
 	xdp_prepare_buff(&xdp, page_address(page), rq->page_pool->p.offset,
-			 rbi->len, false);
+			 rcd->len, false);
 	xdp_buff_clear_frags_flag(&xdp);
 
 	xdp_prog = rcu_dereference(rq->adapter->xdp_bpf_prog);
diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 4087f72f0d2b..89dde220058a 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -1324,6 +1324,8 @@ static void vrf_ip6_input_dst(struct sk_buff *skb, struct net_device *vrf_dev,
 	struct net *net = dev_net(vrf_dev);
 	struct rt6_info *rt6;
 
+	skb_dst_drop(skb);
+
 	rt6 = vrf_ip6_route_lookup(net, vrf_dev, &fl6, ifindex, skb,
 				   RT6_LOOKUP_F_HAS_SADDR | RT6_LOOKUP_F_IFACE);
 	if (unlikely(!rt6))
diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c
index 6e9a3795846a..1a7077093800 100644
--- a/drivers/net/vxlan/vxlan_core.c
+++ b/drivers/net/vxlan/vxlan_core.c
@@ -227,9 +227,9 @@ static int vxlan_fdb_info(struct sk_buff *skb, struct vxlan_dev *vxlan,
 			be32_to_cpu(fdb->vni)))
 		goto nla_put_failure;
 
-	ci.ndm_used	 = jiffies_to_clock_t(now - fdb->used);
+	ci.ndm_used	 = jiffies_to_clock_t(now - READ_ONCE(fdb->used));
 	ci.ndm_confirmed = 0;
-	ci.ndm_updated	 = jiffies_to_clock_t(now - fdb->updated);
+	ci.ndm_updated	 = jiffies_to_clock_t(now - READ_ONCE(fdb->updated));
 	ci.ndm_refcnt	 = 0;
 
 	if (nla_put(skb, NDA_CACHEINFO, sizeof(ci), &ci))
@@ -434,8 +434,8 @@ static struct vxlan_fdb *vxlan_find_mac(struct vxlan_dev *vxlan,
 	struct vxlan_fdb *f;
 
 	f = __vxlan_find_mac(vxlan, mac, vni);
-	if (f && f->used != jiffies)
-		f->used = jiffies;
+	if (f && READ_ONCE(f->used) != jiffies)
+		WRITE_ONCE(f->used, jiffies);
 
 	return f;
 }
@@ -605,10 +605,10 @@ static int vxlan_fdb_append(struct vxlan_fdb *f,
 	if (rd == NULL)
 		return -ENOMEM;
 
-	if (dst_cache_init(&rd->dst_cache, GFP_ATOMIC)) {
-		kfree(rd);
-		return -ENOMEM;
-	}
+	/* The driver can work correctly without a dst cache, so do not treat
+	 * dst cache initialization errors as fatal.
+	 */
+	dst_cache_init(&rd->dst_cache, GFP_ATOMIC | __GFP_NOWARN);
 
 	rd->remote_ip = *ip;
 	rd->remote_port = port;
@@ -1009,12 +1009,12 @@ static int vxlan_fdb_update_existing(struct vxlan_dev *vxlan,
 	    !(f->flags & NTF_VXLAN_ADDED_BY_USER)) {
 		if (f->state != state) {
 			f->state = state;
-			f->updated = jiffies;
+			WRITE_ONCE(f->updated, jiffies);
 			notify = 1;
 		}
 		if (f->flags != fdb_flags) {
 			f->flags = fdb_flags;
-			f->updated = jiffies;
+			WRITE_ONCE(f->updated, jiffies);
 			notify = 1;
 		}
 	}
@@ -1048,7 +1048,7 @@ static int vxlan_fdb_update_existing(struct vxlan_dev *vxlan,
 	}
 
 	if (ndm_flags & NTF_USE)
-		f->used = jiffies;
+		WRITE_ONCE(f->used, jiffies);
 
 	if (notify) {
 		if (rd == NULL)
@@ -1477,7 +1477,7 @@ static bool vxlan_snoop(struct net_device *dev,
 				    src_mac, &rdst->remote_ip.sa, &src_ip->sa);
 
 		rdst->remote_ip = *src_ip;
-		f->updated = jiffies;
+		WRITE_ONCE(f->updated, jiffies);
 		vxlan_fdb_notify(vxlan, f, rdst, RTM_NEWNEIGH, true, NULL);
 	} else {
 		u32 hash_index = fdb_head_index(vxlan, src_mac, vni);
@@ -2825,7 +2825,7 @@ static void vxlan_cleanup(struct timer_list *t)
 			if (f->flags & NTF_EXT_LEARNED)
 				continue;
 
-			timeout = f->used + vxlan->cfg.age_interval * HZ;
+			timeout = READ_ONCE(f->used) + vxlan->cfg.age_interval * HZ;
 			if (time_before_eq(timeout, jiffies)) {
 				netdev_dbg(vxlan->dev,
 					   "garbage collect %pM\n",
@@ -2871,8 +2871,11 @@ static int vxlan_init(struct net_device *dev)
 	struct vxlan_dev *vxlan = netdev_priv(dev);
 	int err;
 
-	if (vxlan->cfg.flags & VXLAN_F_VNIFILTER)
-		vxlan_vnigroup_init(vxlan);
+	if (vxlan->cfg.flags & VXLAN_F_VNIFILTER) {
+		err = vxlan_vnigroup_init(vxlan);
+		if (err)
+			return err;
+	}
 
 	err = gro_cells_init(&vxlan->gro_cells, dev);
 	if (err)
@@ -4337,6 +4340,7 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[],
 			    struct netlink_ext_ack *extack)
 {
 	struct vxlan_dev *vxlan = netdev_priv(dev);
+	bool rem_ip_changed, change_igmp;
 	struct net_device *lowerdev;
 	struct vxlan_config conf;
 	struct vxlan_rdst *dst;
@@ -4360,8 +4364,13 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[],
 	if (err)
 		return err;
 
+	rem_ip_changed = !vxlan_addr_equal(&conf.remote_ip, &dst->remote_ip);
+	change_igmp = vxlan->dev->flags & IFF_UP &&
+		      (rem_ip_changed ||
+		       dst->remote_ifindex != conf.remote_ifindex);
+
 	/* handle default dst entry */
-	if (!vxlan_addr_equal(&conf.remote_ip, &dst->remote_ip)) {
+	if (rem_ip_changed) {
 		u32 hash_index = fdb_head_index(vxlan, all_zeros_mac, conf.vni);
 
 		spin_lock_bh(&vxlan->hash_lock[hash_index]);
@@ -4405,6 +4414,9 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[],
 		}
 	}
 
+	if (change_igmp && vxlan_addr_multicast(&dst->remote_ip))
+		err = vxlan_multicast_leave(vxlan);
+
 	if (conf.age_interval != vxlan->cfg.age_interval)
 		mod_timer(&vxlan->age_timer, jiffies);
 
@@ -4412,7 +4424,12 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[],
 	if (lowerdev && lowerdev != dst->remote_dev)
 		dst->remote_dev = lowerdev;
 	vxlan_config_apply(dev, &conf, lowerdev, vxlan->net, true);
-	return 0;
+
+	if (!err && change_igmp &&
+	    vxlan_addr_multicast(&dst->remote_ip))
+		err = vxlan_multicast_join(vxlan);
+
+	return err;
 }
 
 static void vxlan_dellink(struct net_device *dev, struct list_head *head)
diff --git a/drivers/net/vxlan/vxlan_vnifilter.c b/drivers/net/vxlan/vxlan_vnifilter.c
index d2023e7131bd..06d19e90eadb 100644
--- a/drivers/net/vxlan/vxlan_vnifilter.c
+++ b/drivers/net/vxlan/vxlan_vnifilter.c
@@ -411,6 +411,11 @@ static int vxlan_vnifilter_dump(struct sk_buff *skb, struct netlink_callback *cb
 	struct tunnel_msg *tmsg;
 	struct net_device *dev;
 
+	if (cb->nlh->nlmsg_len < nlmsg_msg_size(sizeof(struct tunnel_msg))) {
+		NL_SET_ERR_MSG(cb->extack, "Invalid msg length");
+		return -EINVAL;
+	}
+
 	tmsg = nlmsg_data(cb->nlh);
 
 	if (tmsg->flags & ~TUNNEL_MSG_VALID_USER_FLAGS) {
@@ -622,7 +627,11 @@ static void vxlan_vni_delete_group(struct vxlan_dev *vxlan,
 	 * default dst remote_ip previously added for this vni
 	 */
 	if (!vxlan_addr_any(&vninode->remote_ip) ||
-	    !vxlan_addr_any(&dst->remote_ip))
+	    !vxlan_addr_any(&dst->remote_ip)) {
+		u32 hash_index = fdb_head_index(vxlan, all_zeros_mac,
+						vninode->vni);
+
+		spin_lock_bh(&vxlan->hash_lock[hash_index]);
 		__vxlan_fdb_delete(vxlan, all_zeros_mac,
 				   (vxlan_addr_any(&vninode->remote_ip) ?
 				   dst->remote_ip : vninode->remote_ip),
@@ -630,6 +639,8 @@ static void vxlan_vni_delete_group(struct vxlan_dev *vxlan,
 				   vninode->vni, vninode->vni,
 				   dst->remote_ifindex,
 				   true);
+		spin_unlock_bh(&vxlan->hash_lock[hash_index]);
+	}
 
 	if (vxlan->dev->flags & IFF_UP) {
 		if (vxlan_addr_multicast(&vninode->remote_ip) &&
diff --git a/drivers/net/wireguard/device.c b/drivers/net/wireguard/device.c
index 45e9b908dbfb..acb9ce7a626a 100644
--- a/drivers/net/wireguard/device.c
+++ b/drivers/net/wireguard/device.c
@@ -364,6 +364,7 @@ static int wg_newlink(struct net *src_net, struct net_device *dev,
 	if (ret < 0)
 		goto err_free_handshake_queue;
 
+	dev_set_threaded(dev, true);
 	ret = register_netdevice(dev);
 	if (ret < 0)
 		goto err_uninit_ratelimiter;
diff --git a/drivers/net/wireless/ath/ath10k/core.c b/drivers/net/wireless/ath/ath10k/core.c
index b3294287bce1..7b6812909ab3 100644
--- a/drivers/net/wireless/ath/ath10k/core.c
+++ b/drivers/net/wireless/ath/ath10k/core.c
@@ -2484,12 +2484,50 @@ static int ath10k_init_hw_params(struct ath10k *ar)
 	return 0;
 }
 
+static bool ath10k_core_needs_recovery(struct ath10k *ar)
+{
+	long time_left;
+
+	/* Sometimes the recovery will fail and then the next all recovery fail,
+	 * so avoid infinite recovery.
+	 */
+	if (atomic_read(&ar->fail_cont_count) >= ATH10K_RECOVERY_MAX_FAIL_COUNT) {
+		ath10k_err(ar, "consecutive fail %d times, will shutdown driver!",
+			   atomic_read(&ar->fail_cont_count));
+		ar->state = ATH10K_STATE_WEDGED;
+		return false;
+	}
+
+	ath10k_dbg(ar, ATH10K_DBG_BOOT, "total recovery count: %d", ++ar->recovery_count);
+
+	if (atomic_read(&ar->pending_recovery)) {
+		/* Sometimes it happened another recovery work before the previous one
+		 * completed, then the second recovery work will destroy the previous
+		 * one, thus below is to avoid that.
+		 */
+		time_left = wait_for_completion_timeout(&ar->driver_recovery,
+							ATH10K_RECOVERY_TIMEOUT_HZ);
+		if (time_left) {
+			ath10k_warn(ar, "previous recovery succeeded, skip this!\n");
+			return false;
+		}
+
+		/* Record the continuous recovery fail count when recovery failed. */
+		atomic_inc(&ar->fail_cont_count);
+
+		/* Avoid having multiple recoveries at the same time. */
+		return false;
+	}
+
+	atomic_inc(&ar->pending_recovery);
+
+	return true;
+}
+
 void ath10k_core_start_recovery(struct ath10k *ar)
 {
-	if (test_and_set_bit(ATH10K_FLAG_RESTARTING, &ar->dev_flags)) {
-		ath10k_warn(ar, "already restarting\n");
+	if (!ath10k_core_needs_recovery(ar))
 		return;
-	}
 
 	queue_work(ar->workqueue, &ar->restart_work);
 }
@@ -2525,6 +2563,8 @@ static void ath10k_core_restart(struct work_struct *work)
 	struct ath10k *ar = container_of(work, struct ath10k, restart_work);
 	int ret;
 
+	reinit_completion(&ar->driver_recovery);
+
 	set_bit(ATH10K_FLAG_CRASH_FLUSH, &ar->dev_flags);
 
 	/* Place a barrier to make sure the compiler doesn't reorder
@@ -2589,8 +2629,6 @@ static void ath10k_core_restart(struct work_struct *work)
 	if (ret)
 		ath10k_warn(ar, "failed to send firmware crash dump via devcoredump: %d",
 			    ret);
-
-	complete(&ar->driver_recovery);
 }
 
 static void ath10k_core_set_coverage_class_work(struct work_struct *work)
diff --git a/drivers/net/wireless/ath/ath10k/core.h b/drivers/net/wireless/ath/ath10k/core.h
index 446dca74f06a..85e16c945b5c 100644
--- a/drivers/net/wireless/ath/ath10k/core.h
+++ b/drivers/net/wireless/ath/ath10k/core.h
@@ -4,6 +4,7 @@
  * Copyright (c) 2011-2017 Qualcomm Atheros, Inc.
  * Copyright (c) 2018-2019, The Linux Foundation. All rights reserved.
  * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries.
  */
 
 #ifndef _CORE_H_
@@ -87,6 +88,8 @@
 				  IEEE80211_IFACE_SKIP_SDATA_NOT_IN_DRIVER)
 #define ATH10K_ITER_RESUME_FLAGS (IEEE80211_IFACE_ITER_RESUME_ALL |\
 				  IEEE80211_IFACE_SKIP_SDATA_NOT_IN_DRIVER)
+#define ATH10K_RECOVERY_TIMEOUT_HZ			(5 * HZ)
+#define ATH10K_RECOVERY_MAX_FAIL_COUNT			4
 
 struct ath10k;
 
@@ -865,9 +868,6 @@ enum ath10k_dev_flags {
 	/* Per Station statistics service */
 	ATH10K_FLAG_PEER_STATS,
 
-	/* Indicates that ath10k device is during recovery process and not complete */
-	ATH10K_FLAG_RESTARTING,
-
 	/* protected by conf_mutex */
 	ATH10K_FLAG_NAPI_ENABLED,
 };
@@ -1211,6 +1211,11 @@ struct ath10k {
 	struct work_struct bundle_tx_work;
 	struct work_struct tx_complete_work;
 
+	atomic_t pending_recovery;
+	unsigned int recovery_count;
+	/* continuous recovery fail count */
+	atomic_t fail_cont_count;
+
 	/* cycle count is reported twice for each visited channel during scan.
 	 * access protected by data_lock
 	 */
diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c
index 6b467696bc98..6493731333ab 100644
--- a/drivers/net/wireless/ath/ath10k/mac.c
+++ b/drivers/net/wireless/ath/ath10k/mac.c
@@ -8125,7 +8125,12 @@ static void ath10k_reconfig_complete(struct ieee80211_hw *hw,
 		ath10k_info(ar, "device successfully recovered\n");
 		ar->state = ATH10K_STATE_ON;
 		ieee80211_wake_queues(ar->hw);
-		clear_bit(ATH10K_FLAG_RESTARTING, &ar->dev_flags);
+
+		/* Clear recovery state. */
+		complete(&ar->driver_recovery);
+		atomic_set(&ar->fail_cont_count, 0);
+		atomic_set(&ar->pending_recovery, 0);
+
 		if (ar->hw_params.hw_restart_disconnect) {
 			list_for_each_entry(arvif, &ar->arvifs, list) {
 				if (arvif->is_up && arvif->vdev_type == WMI_VDEV_TYPE_STA)
diff --git a/drivers/net/wireless/ath/ath10k/snoc.c b/drivers/net/wireless/ath/ath10k/snoc.c
index 0fe47d51013c..59f7ccb33fde 100644
--- a/drivers/net/wireless/ath/ath10k/snoc.c
+++ b/drivers/net/wireless/ath/ath10k/snoc.c
@@ -937,7 +937,9 @@ static int ath10k_snoc_hif_start(struct ath10k *ar)
 
 	dev_set_threaded(ar->napi_dev, true);
 	ath10k_core_napi_enable(ar);
-	ath10k_snoc_irq_enable(ar);
+	/* IRQs are left enabled when we restart due to a firmware crash */
+	if (!test_bit(ATH10K_SNOC_FLAG_RECOVERY, &ar_snoc->flags))
+		ath10k_snoc_irq_enable(ar);
 	ath10k_snoc_rx_post(ar);
 
 	clear_bit(ATH10K_SNOC_FLAG_RECOVERY, &ar_snoc->flags);
diff --git a/drivers/net/wireless/ath/ath10k/wmi.c b/drivers/net/wireless/ath/ath10k/wmi.c
index 5e061f7525a6..09066e6aca40 100644
--- a/drivers/net/wireless/ath/ath10k/wmi.c
+++ b/drivers/net/wireless/ath/ath10k/wmi.c
@@ -4,6 +4,7 @@
  * Copyright (c) 2011-2017 Qualcomm Atheros, Inc.
  * Copyright (c) 2018-2019, The Linux Foundation. All rights reserved.
  * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries.
  */
 
 #include <linux/skbuff.h>
@@ -1941,6 +1942,11 @@ int ath10k_wmi_cmd_send(struct ath10k *ar, struct sk_buff *skb, u32 cmd_id)
 	}
 
 	wait_event_timeout(ar->wmi.tx_credits_wq, ({
+		if (ar->state == ATH10K_STATE_WEDGED) {
+			ret = -ESHUTDOWN;
+			ath10k_dbg(ar, ATH10K_DBG_WMI,
+				   "drop wmi command %d, hardware is wedged\n", cmd_id);
+		}
 		/* try to send pending beacons first. they take priority */
 		ath10k_wmi_tx_beacons_nowait(ar);
 
diff --git a/drivers/net/wireless/ath/ath11k/ahb.c b/drivers/net/wireless/ath/ath11k/ahb.c
index 97b12f51ef28..9389dc5f4a3d 100644
--- a/drivers/net/wireless/ath/ath11k/ahb.c
+++ b/drivers/net/wireless/ath/ath11k/ahb.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
- * Copyright (c) 2022-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2022-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include <linux/module.h>
@@ -1290,6 +1290,7 @@ static void ath11k_ahb_remove(struct platform_device *pdev)
 	ath11k_core_deinit(ab);
 
 qmi_fail:
+	ath11k_fw_destroy(ab);
 	ath11k_ahb_free_resources(ab);
 }
 
@@ -1309,6 +1310,7 @@ static void ath11k_ahb_shutdown(struct platform_device *pdev)
 	ath11k_core_deinit(ab);
 
 free_resources:
+	ath11k_fw_destroy(ab);
 	ath11k_ahb_free_resources(ab);
 }
 
diff --git a/drivers/net/wireless/ath/ath11k/ce.c b/drivers/net/wireless/ath/ath11k/ce.c
index e66e86bdec20..9d8efec46508 100644
--- a/drivers/net/wireless/ath/ath11k/ce.c
+++ b/drivers/net/wireless/ath/ath11k/ce.c
@@ -393,11 +393,10 @@ static int ath11k_ce_completed_recv_next(struct ath11k_ce_pipe *pipe,
 		goto err;
 	}
 
+	/* Make sure descriptor is read after the head pointer. */
+	dma_rmb();
+
 	*nbytes = ath11k_hal_ce_dst_status_get_length(desc);
-	if (*nbytes == 0) {
-		ret = -EIO;
-		goto err;
-	}
 
 	*skb = pipe->dest_ring->skb[sw_index];
 	pipe->dest_ring->skb[sw_index] = NULL;
@@ -430,8 +429,8 @@ static void ath11k_ce_recv_process_cb(struct ath11k_ce_pipe *pipe)
 		dma_unmap_single(ab->dev, ATH11K_SKB_RXCB(skb)->paddr,
 				 max_nbytes, DMA_FROM_DEVICE);
 
-		if (unlikely(max_nbytes < nbytes)) {
-			ath11k_warn(ab, "rxed more than expected (nbytes %d, max %d)",
+		if (unlikely(max_nbytes < nbytes || nbytes == 0)) {
+			ath11k_warn(ab, "unexpected rx length (nbytes %d, max %d)",
 				    nbytes, max_nbytes);
 			dev_kfree_skb_any(skb);
 			continue;
diff --git a/drivers/net/wireless/ath/ath11k/core.c b/drivers/net/wireless/ath/ath11k/core.c
index ccf4ad35fdc3..2ec1771262fd 100644
--- a/drivers/net/wireless/ath/ath11k/core.c
+++ b/drivers/net/wireless/ath/ath11k/core.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include <linux/module.h>
@@ -811,6 +811,52 @@ static const struct ath11k_hw_params ath11k_hw_params[] = {
 	},
 };
 
+static const struct dmi_system_id ath11k_pm_quirk_table[] = {
+	{
+		.driver_data = (void *)ATH11K_PM_WOW,
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "21J4"),
+		},
+	},
+	{
+		.driver_data = (void *)ATH11K_PM_WOW,
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "21K4"),
+		},
+	},
+	{
+		.driver_data = (void *)ATH11K_PM_WOW,
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "21K6"),
+		},
+	},
+	{
+		.driver_data = (void *)ATH11K_PM_WOW,
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "21K8"),
+		},
+	},
+	{
+		.driver_data = (void *)ATH11K_PM_WOW,
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "21KA"),
+		},
+	},
+	{
+		.driver_data = (void *)ATH11K_PM_WOW,
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "21F9"),
+		},
+	},
+	{}
+};
+
 static inline struct ath11k_pdev *ath11k_core_get_single_pdev(struct ath11k_base *ab)
 {
 	WARN_ON(!ab->hw_params.single_pdev_only);
@@ -855,6 +901,7 @@ void ath11k_fw_stats_init(struct ath11k *ar)
 	INIT_LIST_HEAD(&ar->fw_stats.bcn);
 
 	init_completion(&ar->fw_stats_complete);
+	init_completion(&ar->fw_stats_done);
 }
 
 void ath11k_fw_stats_free(struct ath11k_fw_stats *stats)
@@ -1811,6 +1858,20 @@ int ath11k_core_qmi_firmware_ready(struct ath11k_base *ab)
 {
 	int ret;
 
+	switch (ath11k_crypto_mode) {
+	case ATH11K_CRYPT_MODE_SW:
+		set_bit(ATH11K_FLAG_HW_CRYPTO_DISABLED, &ab->dev_flags);
+		set_bit(ATH11K_FLAG_RAW_MODE, &ab->dev_flags);
+		break;
+	case ATH11K_CRYPT_MODE_HW:
+		clear_bit(ATH11K_FLAG_HW_CRYPTO_DISABLED, &ab->dev_flags);
+		clear_bit(ATH11K_FLAG_RAW_MODE, &ab->dev_flags);
+		break;
+	default:
+		ath11k_info(ab, "invalid crypto_mode: %d\n", ath11k_crypto_mode);
+		return -EINVAL;
+	}
+
 	ret = ath11k_core_start_firmware(ab, ab->fw_mode);
 	if (ret) {
 		ath11k_err(ab, "failed to start firmware: %d\n", ret);
@@ -1829,20 +1890,6 @@ int ath11k_core_qmi_firmware_ready(struct ath11k_base *ab)
 		goto err_firmware_stop;
 	}
 
-	switch (ath11k_crypto_mode) {
-	case ATH11K_CRYPT_MODE_SW:
-		set_bit(ATH11K_FLAG_HW_CRYPTO_DISABLED, &ab->dev_flags);
-		set_bit(ATH11K_FLAG_RAW_MODE, &ab->dev_flags);
-		break;
-	case ATH11K_CRYPT_MODE_HW:
-		clear_bit(ATH11K_FLAG_HW_CRYPTO_DISABLED, &ab->dev_flags);
-		clear_bit(ATH11K_FLAG_RAW_MODE, &ab->dev_flags);
-		break;
-	default:
-		ath11k_info(ab, "invalid crypto_mode: %d\n", ath11k_crypto_mode);
-		return -EINVAL;
-	}
-
 	if (ath11k_frame_mode == ATH11K_HW_TXRX_RAW)
 		set_bit(ATH11K_FLAG_RAW_MODE, &ab->dev_flags);
 
@@ -1915,6 +1962,7 @@ err_hal_srng_deinit:
 void ath11k_core_halt(struct ath11k *ar)
 {
 	struct ath11k_base *ab = ar->ab;
+	struct list_head *pos, *n;
 
 	lockdep_assert_held(&ar->conf_mutex);
 
@@ -1929,7 +1977,12 @@ void ath11k_core_halt(struct ath11k *ar)
 
 	rcu_assign_pointer(ab->pdevs_active[ar->pdev_idx], NULL);
 	synchronize_rcu();
-	INIT_LIST_HEAD(&ar->arvifs);
+
+	spin_lock_bh(&ar->data_lock);
+	list_for_each_safe(pos, n, &ar->arvifs)
+		list_del_init(pos);
+	spin_unlock_bh(&ar->data_lock);
+
 	idr_init(&ar->txmgmt_idr);
 }
 
@@ -2190,8 +2243,17 @@ EXPORT_SYMBOL(ath11k_core_pre_init);
 
 int ath11k_core_init(struct ath11k_base *ab)
 {
+	const struct dmi_system_id *dmi_id;
 	int ret;
 
+	dmi_id = dmi_first_match(ath11k_pm_quirk_table);
+	if (dmi_id)
+		ab->pm_policy = (kernel_ulong_t)dmi_id->driver_data;
+	else
+		ab->pm_policy = ATH11K_PM_DEFAULT;
+
+	ath11k_dbg(ab, ATH11K_DBG_BOOT, "pm policy %u\n", ab->pm_policy);
+
 	ret = ath11k_core_soc_create(ab);
 	if (ret) {
 		ath11k_err(ab, "failed to create soc core: %d\n", ret);
@@ -2214,7 +2276,6 @@ void ath11k_core_deinit(struct ath11k_base *ab)
 	ath11k_hif_power_down(ab);
 	ath11k_mac_destroy(ab);
 	ath11k_core_soc_destroy(ab);
-	ath11k_fw_destroy(ab);
 }
 EXPORT_SYMBOL(ath11k_core_deinit);
 
diff --git a/drivers/net/wireless/ath/ath11k/core.h b/drivers/net/wireless/ath/ath11k/core.h
index 09c37e19a168..09fdb7be0e19 100644
--- a/drivers/net/wireless/ath/ath11k/core.h
+++ b/drivers/net/wireless/ath/ath11k/core.h
@@ -599,6 +599,8 @@ struct ath11k_fw_stats {
 	struct list_head pdevs;
 	struct list_head vdevs;
 	struct list_head bcn;
+	u32 num_vdev_recvd;
+	u32 num_bcn_recvd;
 };
 
 struct ath11k_dbg_htt_stats {
@@ -780,7 +782,7 @@ struct ath11k {
 	u8 alpha2[REG_ALPHA2_LEN + 1];
 	struct ath11k_fw_stats fw_stats;
 	struct completion fw_stats_complete;
-	bool fw_stats_done;
+	struct completion fw_stats_done;
 
 	/* protected by conf_mutex */
 	bool ps_state_enable;
@@ -889,6 +891,11 @@ struct ath11k_msi_config {
 	u16 hw_rev;
 };
 
+enum ath11k_pm_policy {
+	ATH11K_PM_DEFAULT,
+	ATH11K_PM_WOW,
+};
+
 /* Master structure to hold the hw data which may be used in core module */
 struct ath11k_base {
 	enum ath11k_hw_rev hw_rev;
@@ -1051,6 +1058,8 @@ struct ath11k_base {
 	} testmode;
 #endif
 
+	enum ath11k_pm_policy pm_policy;
+
 	/* must be last */
 	u8 drv_priv[] __aligned(sizeof(void *));
 };
diff --git a/drivers/net/wireless/ath/ath11k/debugfs.c b/drivers/net/wireless/ath/ath11k/debugfs.c
index 57281a135dd7..5d46f8e4c231 100644
--- a/drivers/net/wireless/ath/ath11k/debugfs.c
+++ b/drivers/net/wireless/ath/ath11k/debugfs.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2020 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include <linux/vmalloc.h>
@@ -93,57 +93,14 @@ void ath11k_debugfs_add_dbring_entry(struct ath11k *ar,
 	spin_unlock_bh(&dbr_data->lock);
 }
 
-static void ath11k_debugfs_fw_stats_reset(struct ath11k *ar)
-{
-	spin_lock_bh(&ar->data_lock);
-	ar->fw_stats_done = false;
-	ath11k_fw_stats_pdevs_free(&ar->fw_stats.pdevs);
-	ath11k_fw_stats_vdevs_free(&ar->fw_stats.vdevs);
-	spin_unlock_bh(&ar->data_lock);
-}
-
 void ath11k_debugfs_fw_stats_process(struct ath11k *ar, struct ath11k_fw_stats *stats)
 {
 	struct ath11k_base *ab = ar->ab;
-	struct ath11k_pdev *pdev;
-	bool is_end;
-	static unsigned int num_vdev, num_bcn;
-	size_t total_vdevs_started = 0;
-	int i;
-
-	/* WMI_REQUEST_PDEV_STAT request has been already processed */
-
-	if (stats->stats_id == WMI_REQUEST_RSSI_PER_CHAIN_STAT) {
-		ar->fw_stats_done = true;
-		return;
-	}
-
-	if (stats->stats_id == WMI_REQUEST_VDEV_STAT) {
-		if (list_empty(&stats->vdevs)) {
-			ath11k_warn(ab, "empty vdev stats");
-			return;
-		}
-		/* FW sends all the active VDEV stats irrespective of PDEV,
-		 * hence limit until the count of all VDEVs started
-		 */
-		for (i = 0; i < ab->num_radios; i++) {
-			pdev = rcu_dereference(ab->pdevs_active[i]);
-			if (pdev && pdev->ar)
-				total_vdevs_started += ar->num_started_vdevs;
-		}
-
-		is_end = ((++num_vdev) == total_vdevs_started);
-
-		list_splice_tail_init(&stats->vdevs,
-				      &ar->fw_stats.vdevs);
-
-		if (is_end) {
-			ar->fw_stats_done = true;
-			num_vdev = 0;
-		}
-		return;
-	}
+	bool is_end = true;
 
+	/* WMI_REQUEST_PDEV_STAT, WMI_REQUEST_RSSI_PER_CHAIN_STAT and
+	 * WMI_REQUEST_VDEV_STAT requests have been already processed.
+	 */
 	if (stats->stats_id == WMI_REQUEST_BCN_STAT) {
 		if (list_empty(&stats->bcn)) {
 			ath11k_warn(ab, "empty bcn stats");
@@ -152,97 +109,18 @@ void ath11k_debugfs_fw_stats_process(struct ath11k *ar, struct ath11k_fw_stats *
 		/* Mark end until we reached the count of all started VDEVs
 		 * within the PDEV
 		 */
-		is_end = ((++num_bcn) == ar->num_started_vdevs);
+		if (ar->num_started_vdevs)
+			is_end = ((++ar->fw_stats.num_bcn_recvd) ==
+				  ar->num_started_vdevs);
 
 		list_splice_tail_init(&stats->bcn,
 				      &ar->fw_stats.bcn);
 
-		if (is_end) {
-			ar->fw_stats_done = true;
-			num_bcn = 0;
-		}
+		if (is_end)
+			complete(&ar->fw_stats_done);
 	}
 }
 
-static int ath11k_debugfs_fw_stats_request(struct ath11k *ar,
-					   struct stats_request_params *req_param)
-{
-	struct ath11k_base *ab = ar->ab;
-	unsigned long timeout, time_left;
-	int ret;
-
-	lockdep_assert_held(&ar->conf_mutex);
-
-	/* FW stats can get split when exceeding the stats data buffer limit.
-	 * In that case, since there is no end marking for the back-to-back
-	 * received 'update stats' event, we keep a 3 seconds timeout in case,
-	 * fw_stats_done is not marked yet
-	 */
-	timeout = jiffies + msecs_to_jiffies(3 * 1000);
-
-	ath11k_debugfs_fw_stats_reset(ar);
-
-	reinit_completion(&ar->fw_stats_complete);
-
-	ret = ath11k_wmi_send_stats_request_cmd(ar, req_param);
-
-	if (ret) {
-		ath11k_warn(ab, "could not request fw stats (%d)\n",
-			    ret);
-		return ret;
-	}
-
-	time_left = wait_for_completion_timeout(&ar->fw_stats_complete, 1 * HZ);
-
-	if (!time_left)
-		return -ETIMEDOUT;
-
-	for (;;) {
-		if (time_after(jiffies, timeout))
-			break;
-
-		spin_lock_bh(&ar->data_lock);
-		if (ar->fw_stats_done) {
-			spin_unlock_bh(&ar->data_lock);
-			break;
-		}
-		spin_unlock_bh(&ar->data_lock);
-	}
-	return 0;
-}
-
-int ath11k_debugfs_get_fw_stats(struct ath11k *ar, u32 pdev_id,
-				u32 vdev_id, u32 stats_id)
-{
-	struct ath11k_base *ab = ar->ab;
-	struct stats_request_params req_param;
-	int ret;
-
-	mutex_lock(&ar->conf_mutex);
-
-	if (ar->state != ATH11K_STATE_ON) {
-		ret = -ENETDOWN;
-		goto err_unlock;
-	}
-
-	req_param.pdev_id = pdev_id;
-	req_param.vdev_id = vdev_id;
-	req_param.stats_id = stats_id;
-
-	ret = ath11k_debugfs_fw_stats_request(ar, &req_param);
-	if (ret)
-		ath11k_warn(ab, "failed to request fw stats: %d\n", ret);
-
-	ath11k_dbg(ab, ATH11K_DBG_WMI,
-		   "debug get fw stat pdev id %d vdev id %d stats id 0x%x\n",
-		   pdev_id, vdev_id, stats_id);
-
-err_unlock:
-	mutex_unlock(&ar->conf_mutex);
-
-	return ret;
-}
-
 static int ath11k_open_pdev_stats(struct inode *inode, struct file *file)
 {
 	struct ath11k *ar = inode->i_private;
@@ -268,7 +146,7 @@ static int ath11k_open_pdev_stats(struct inode *inode, struct file *file)
 	req_param.vdev_id = 0;
 	req_param.stats_id = WMI_REQUEST_PDEV_STAT;
 
-	ret = ath11k_debugfs_fw_stats_request(ar, &req_param);
+	ret = ath11k_mac_fw_stats_request(ar, &req_param);
 	if (ret) {
 		ath11k_warn(ab, "failed to request fw pdev stats: %d\n", ret);
 		goto err_free;
@@ -339,7 +217,7 @@ static int ath11k_open_vdev_stats(struct inode *inode, struct file *file)
 	req_param.vdev_id = 0;
 	req_param.stats_id = WMI_REQUEST_VDEV_STAT;
 
-	ret = ath11k_debugfs_fw_stats_request(ar, &req_param);
+	ret = ath11k_mac_fw_stats_request(ar, &req_param);
 	if (ret) {
 		ath11k_warn(ar->ab, "failed to request fw vdev stats: %d\n", ret);
 		goto err_free;
@@ -415,7 +293,7 @@ static int ath11k_open_bcn_stats(struct inode *inode, struct file *file)
 			continue;
 
 		req_param.vdev_id = arvif->vdev_id;
-		ret = ath11k_debugfs_fw_stats_request(ar, &req_param);
+		ret = ath11k_mac_fw_stats_request(ar, &req_param);
 		if (ret) {
 			ath11k_warn(ar->ab, "failed to request fw bcn stats: %d\n", ret);
 			goto err_free;
diff --git a/drivers/net/wireless/ath/ath11k/debugfs.h b/drivers/net/wireless/ath/ath11k/debugfs.h
index a39e458637b0..ed7fec177588 100644
--- a/drivers/net/wireless/ath/ath11k/debugfs.h
+++ b/drivers/net/wireless/ath/ath11k/debugfs.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2022, 2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef _ATH11K_DEBUGFS_H_
@@ -273,8 +273,6 @@ void ath11k_debugfs_unregister(struct ath11k *ar);
 void ath11k_debugfs_fw_stats_process(struct ath11k *ar, struct ath11k_fw_stats *stats);
 
 void ath11k_debugfs_fw_stats_init(struct ath11k *ar);
-int ath11k_debugfs_get_fw_stats(struct ath11k *ar, u32 pdev_id,
-				u32 vdev_id, u32 stats_id);
 
 static inline bool ath11k_debugfs_is_pktlog_lite_mode_enabled(struct ath11k *ar)
 {
@@ -381,12 +379,6 @@ static inline int ath11k_debugfs_rx_filter(struct ath11k *ar)
 	return 0;
 }
 
-static inline int ath11k_debugfs_get_fw_stats(struct ath11k *ar,
-					      u32 pdev_id, u32 vdev_id, u32 stats_id)
-{
-	return 0;
-}
-
 static inline void
 ath11k_debugfs_add_dbring_entry(struct ath11k *ar,
 				enum wmi_direct_buffer_module id,
diff --git a/drivers/net/wireless/ath/ath11k/dp.c b/drivers/net/wireless/ath/ath11k/dp.c
index fbf666d0ecf1..f124b7329e1a 100644
--- a/drivers/net/wireless/ath/ath11k/dp.c
+++ b/drivers/net/wireless/ath/ath11k/dp.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include <crypto/hash.h>
@@ -104,14 +104,12 @@ void ath11k_dp_srng_cleanup(struct ath11k_base *ab, struct dp_srng *ring)
 	if (!ring->vaddr_unaligned)
 		return;
 
-	if (ring->cached) {
-		dma_unmap_single(ab->dev, ring->paddr_unaligned, ring->size,
-				 DMA_FROM_DEVICE);
-		kfree(ring->vaddr_unaligned);
-	} else {
+	if (ring->cached)
+		dma_free_noncoherent(ab->dev, ring->size, ring->vaddr_unaligned,
+				     ring->paddr_unaligned, DMA_FROM_DEVICE);
+	else
 		dma_free_coherent(ab->dev, ring->size, ring->vaddr_unaligned,
 				  ring->paddr_unaligned);
-	}
 
 	ring->vaddr_unaligned = NULL;
 }
@@ -249,25 +247,14 @@ int ath11k_dp_srng_setup(struct ath11k_base *ab, struct dp_srng *ring,
 		default:
 			cached = false;
 		}
-
-		if (cached) {
-			ring->vaddr_unaligned = kzalloc(ring->size, GFP_KERNEL);
-			if (!ring->vaddr_unaligned)
-				return -ENOMEM;
-
-			ring->paddr_unaligned = dma_map_single(ab->dev,
-							       ring->vaddr_unaligned,
-							       ring->size,
-							       DMA_FROM_DEVICE);
-			if (dma_mapping_error(ab->dev, ring->paddr_unaligned)) {
-				kfree(ring->vaddr_unaligned);
-				ring->vaddr_unaligned = NULL;
-				return -ENOMEM;
-			}
-		}
 	}
 
-	if (!cached)
+	if (cached)
+		ring->vaddr_unaligned = dma_alloc_noncoherent(ab->dev, ring->size,
+							      &ring->paddr_unaligned,
+							      DMA_FROM_DEVICE,
+							      GFP_KERNEL);
+	else
 		ring->vaddr_unaligned = dma_alloc_coherent(ab->dev, ring->size,
 							   &ring->paddr_unaligned,
 							   GFP_KERNEL);
diff --git a/drivers/net/wireless/ath/ath11k/dp.h b/drivers/net/wireless/ath/ath11k/dp.h
index 65d2bc0687c8..eaf902c25e19 100644
--- a/drivers/net/wireless/ath/ath11k/dp.h
+++ b/drivers/net/wireless/ath/ath11k/dp.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2023, 2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef ATH11K_DP_H
@@ -20,7 +20,6 @@ struct ath11k_ext_irq_grp;
 
 struct dp_rx_tid {
 	u8 tid;
-	u32 *vaddr;
 	dma_addr_t paddr;
 	u32 size;
 	u32 ba_win_sz;
@@ -37,6 +36,9 @@ struct dp_rx_tid {
 	/* Timer info related to fragments */
 	struct timer_list frag_timer;
 	struct ath11k_base *ab;
+	u32 *vaddr_unaligned;
+	dma_addr_t paddr_unaligned;
+	u32 unaligned_size;
 };
 
 #define DP_REO_DESC_FREE_THRESHOLD  64
diff --git a/drivers/net/wireless/ath/ath11k/dp_rx.c b/drivers/net/wireless/ath/ath11k/dp_rx.c
index 40088e62572e..007d86959042 100644
--- a/drivers/net/wireless/ath/ath11k/dp_rx.c
+++ b/drivers/net/wireless/ath/ath11k/dp_rx.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include <linux/ieee80211.h>
@@ -675,11 +675,11 @@ void ath11k_dp_reo_cmd_list_cleanup(struct ath11k_base *ab)
 	list_for_each_entry_safe(cmd, tmp, &dp->reo_cmd_list, list) {
 		list_del(&cmd->list);
 		rx_tid = &cmd->data;
-		if (rx_tid->vaddr) {
-			dma_unmap_single(ab->dev, rx_tid->paddr,
-					 rx_tid->size, DMA_BIDIRECTIONAL);
-			kfree(rx_tid->vaddr);
-			rx_tid->vaddr = NULL;
+		if (rx_tid->vaddr_unaligned) {
+			dma_free_noncoherent(ab->dev, rx_tid->unaligned_size,
+					     rx_tid->vaddr_unaligned,
+					     rx_tid->paddr_unaligned, DMA_BIDIRECTIONAL);
+			rx_tid->vaddr_unaligned = NULL;
 		}
 		kfree(cmd);
 	}
@@ -689,11 +689,11 @@ void ath11k_dp_reo_cmd_list_cleanup(struct ath11k_base *ab)
 		list_del(&cmd_cache->list);
 		dp->reo_cmd_cache_flush_count--;
 		rx_tid = &cmd_cache->data;
-		if (rx_tid->vaddr) {
-			dma_unmap_single(ab->dev, rx_tid->paddr,
-					 rx_tid->size, DMA_BIDIRECTIONAL);
-			kfree(rx_tid->vaddr);
-			rx_tid->vaddr = NULL;
+		if (rx_tid->vaddr_unaligned) {
+			dma_free_noncoherent(ab->dev, rx_tid->unaligned_size,
+					     rx_tid->vaddr_unaligned,
+					     rx_tid->paddr_unaligned, DMA_BIDIRECTIONAL);
+			rx_tid->vaddr_unaligned = NULL;
 		}
 		kfree(cmd_cache);
 	}
@@ -708,11 +708,11 @@ static void ath11k_dp_reo_cmd_free(struct ath11k_dp *dp, void *ctx,
 	if (status != HAL_REO_CMD_SUCCESS)
 		ath11k_warn(dp->ab, "failed to flush rx tid hw desc, tid %d status %d\n",
 			    rx_tid->tid, status);
-	if (rx_tid->vaddr) {
-		dma_unmap_single(dp->ab->dev, rx_tid->paddr, rx_tid->size,
-				 DMA_BIDIRECTIONAL);
-		kfree(rx_tid->vaddr);
-		rx_tid->vaddr = NULL;
+	if (rx_tid->vaddr_unaligned) {
+		dma_free_noncoherent(dp->ab->dev, rx_tid->unaligned_size,
+				     rx_tid->vaddr_unaligned,
+				     rx_tid->paddr_unaligned, DMA_BIDIRECTIONAL);
+		rx_tid->vaddr_unaligned = NULL;
 	}
 }
 
@@ -749,10 +749,10 @@ static void ath11k_dp_reo_cache_flush(struct ath11k_base *ab,
 	if (ret) {
 		ath11k_err(ab, "failed to send HAL_REO_CMD_FLUSH_CACHE cmd, tid %d (%d)\n",
 			   rx_tid->tid, ret);
-		dma_unmap_single(ab->dev, rx_tid->paddr, rx_tid->size,
-				 DMA_BIDIRECTIONAL);
-		kfree(rx_tid->vaddr);
-		rx_tid->vaddr = NULL;
+		dma_free_noncoherent(ab->dev, rx_tid->unaligned_size,
+				     rx_tid->vaddr_unaligned,
+				     rx_tid->paddr_unaligned, DMA_BIDIRECTIONAL);
+		rx_tid->vaddr_unaligned = NULL;
 	}
 }
 
@@ -802,10 +802,10 @@ static void ath11k_dp_rx_tid_del_func(struct ath11k_dp *dp, void *ctx,
 
 	return;
 free_desc:
-	dma_unmap_single(ab->dev, rx_tid->paddr, rx_tid->size,
-			 DMA_BIDIRECTIONAL);
-	kfree(rx_tid->vaddr);
-	rx_tid->vaddr = NULL;
+	dma_free_noncoherent(ab->dev, rx_tid->unaligned_size,
+			     rx_tid->vaddr_unaligned,
+			     rx_tid->paddr_unaligned, DMA_BIDIRECTIONAL);
+	rx_tid->vaddr_unaligned = NULL;
 }
 
 void ath11k_peer_rx_tid_delete(struct ath11k *ar,
@@ -831,14 +831,16 @@ void ath11k_peer_rx_tid_delete(struct ath11k *ar,
 		if (ret != -ESHUTDOWN)
 			ath11k_err(ar->ab, "failed to send HAL_REO_CMD_UPDATE_RX_QUEUE cmd, tid %d (%d)\n",
 				   tid, ret);
-		dma_unmap_single(ar->ab->dev, rx_tid->paddr, rx_tid->size,
-				 DMA_BIDIRECTIONAL);
-		kfree(rx_tid->vaddr);
-		rx_tid->vaddr = NULL;
+		dma_free_noncoherent(ar->ab->dev, rx_tid->unaligned_size,
+				     rx_tid->vaddr_unaligned,
+				     rx_tid->paddr_unaligned, DMA_BIDIRECTIONAL);
+		rx_tid->vaddr_unaligned = NULL;
 	}
 
 	rx_tid->paddr = 0;
+	rx_tid->paddr_unaligned = 0;
 	rx_tid->size = 0;
+	rx_tid->unaligned_size = 0;
 }
 
 static int ath11k_dp_rx_link_desc_return(struct ath11k_base *ab,
@@ -982,10 +984,9 @@ static void ath11k_dp_rx_tid_mem_free(struct ath11k_base *ab,
 	if (!rx_tid->active)
 		goto unlock_exit;
 
-	dma_unmap_single(ab->dev, rx_tid->paddr, rx_tid->size,
-			 DMA_BIDIRECTIONAL);
-	kfree(rx_tid->vaddr);
-	rx_tid->vaddr = NULL;
+	dma_free_noncoherent(ab->dev, rx_tid->unaligned_size, rx_tid->vaddr_unaligned,
+			     rx_tid->paddr_unaligned, DMA_BIDIRECTIONAL);
+	rx_tid->vaddr_unaligned = NULL;
 
 	rx_tid->active = false;
 
@@ -1000,9 +1001,8 @@ int ath11k_peer_rx_tid_setup(struct ath11k *ar, const u8 *peer_mac, int vdev_id,
 	struct ath11k_base *ab = ar->ab;
 	struct ath11k_peer *peer;
 	struct dp_rx_tid *rx_tid;
-	u32 hw_desc_sz;
-	u32 *addr_aligned;
-	void *vaddr;
+	u32 hw_desc_sz, *vaddr;
+	void *vaddr_unaligned;
 	dma_addr_t paddr;
 	int ret;
 
@@ -1050,37 +1050,34 @@ int ath11k_peer_rx_tid_setup(struct ath11k *ar, const u8 *peer_mac, int vdev_id,
 	else
 		hw_desc_sz = ath11k_hal_reo_qdesc_size(DP_BA_WIN_SZ_MAX, tid);
 
-	vaddr = kzalloc(hw_desc_sz + HAL_LINK_DESC_ALIGN - 1, GFP_ATOMIC);
-	if (!vaddr) {
+	rx_tid->unaligned_size = hw_desc_sz + HAL_LINK_DESC_ALIGN - 1;
+	vaddr_unaligned = dma_alloc_noncoherent(ab->dev, rx_tid->unaligned_size, &paddr,
+						DMA_BIDIRECTIONAL, GFP_ATOMIC);
+	if (!vaddr_unaligned) {
 		spin_unlock_bh(&ab->base_lock);
 		return -ENOMEM;
 	}
 
-	addr_aligned = PTR_ALIGN(vaddr, HAL_LINK_DESC_ALIGN);
-
-	ath11k_hal_reo_qdesc_setup(addr_aligned, tid, ba_win_sz,
-				   ssn, pn_type);
-
-	paddr = dma_map_single(ab->dev, addr_aligned, hw_desc_sz,
-			       DMA_BIDIRECTIONAL);
-
-	ret = dma_mapping_error(ab->dev, paddr);
-	if (ret) {
-		spin_unlock_bh(&ab->base_lock);
-		ath11k_warn(ab, "failed to setup dma map for peer %pM rx tid %d: %d\n",
-			    peer_mac, tid, ret);
-		goto err_mem_free;
-	}
-
-	rx_tid->vaddr = vaddr;
-	rx_tid->paddr = paddr;
+	rx_tid->vaddr_unaligned = vaddr_unaligned;
+	vaddr = PTR_ALIGN(vaddr_unaligned, HAL_LINK_DESC_ALIGN);
+	rx_tid->paddr_unaligned = paddr;
+	rx_tid->paddr = rx_tid->paddr_unaligned + ((unsigned long)vaddr -
+			(unsigned long)rx_tid->vaddr_unaligned);
+	ath11k_hal_reo_qdesc_setup(vaddr, tid, ba_win_sz, ssn, pn_type);
 	rx_tid->size = hw_desc_sz;
 	rx_tid->active = true;
 
+	/* After dma_alloc_noncoherent, vaddr is being modified for reo qdesc setup.
+	 * Since these changes are not reflected in the device, driver now needs to
+	 * explicitly call dma_sync_single_for_device.
+	 */
+	dma_sync_single_for_device(ab->dev, rx_tid->paddr,
+				   rx_tid->size,
+				   DMA_TO_DEVICE);
 	spin_unlock_bh(&ab->base_lock);
 
-	ret = ath11k_wmi_peer_rx_reorder_queue_setup(ar, vdev_id, peer_mac,
-						     paddr, tid, 1, ba_win_sz);
+	ret = ath11k_wmi_peer_rx_reorder_queue_setup(ar, vdev_id, peer_mac, rx_tid->paddr,
+						     tid, 1, ba_win_sz);
 	if (ret) {
 		ath11k_warn(ar->ab, "failed to setup rx reorder queue for peer %pM tid %d: %d\n",
 			    peer_mac, tid, ret);
@@ -1088,12 +1085,6 @@ int ath11k_peer_rx_tid_setup(struct ath11k *ar, const u8 *peer_mac, int vdev_id,
 	}
 
 	return ret;
-
-err_mem_free:
-	kfree(rx_tid->vaddr);
-	rx_tid->vaddr = NULL;
-
-	return ret;
 }
 
 int ath11k_dp_rx_ampdu_start(struct ath11k *ar,
@@ -2646,7 +2637,7 @@ int ath11k_dp_process_rx(struct ath11k_base *ab, int ring_id,
 	struct ath11k *ar;
 	struct hal_reo_dest_ring *desc;
 	enum hal_reo_dest_ring_push_reason push_reason;
-	u32 cookie;
+	u32 cookie, info0, rx_msdu_info0, rx_mpdu_info0;
 	int i;
 
 	for (i = 0; i < MAX_RADIOS; i++)
@@ -2659,11 +2650,14 @@ int ath11k_dp_process_rx(struct ath11k_base *ab, int ring_id,
 try_again:
 	ath11k_hal_srng_access_begin(ab, srng);
 
+	/* Make sure descriptor is read after the head pointer. */
+	dma_rmb();
+
 	while (likely(desc =
 	      (struct hal_reo_dest_ring *)ath11k_hal_srng_dst_get_next_entry(ab,
 									     srng))) {
 		cookie = FIELD_GET(BUFFER_ADDR_INFO1_SW_COOKIE,
-				   desc->buf_addr_info.info1);
+				   READ_ONCE(desc->buf_addr_info.info1));
 		buf_id = FIELD_GET(DP_RXDMA_BUF_COOKIE_BUF_ID,
 				   cookie);
 		mac_id = FIELD_GET(DP_RXDMA_BUF_COOKIE_PDEV_ID, cookie);
@@ -2692,8 +2686,9 @@ try_again:
 
 		num_buffs_reaped[mac_id]++;
 
+		info0 = READ_ONCE(desc->info0);
 		push_reason = FIELD_GET(HAL_REO_DEST_RING_INFO0_PUSH_REASON,
-					desc->info0);
+					info0);
 		if (unlikely(push_reason !=
 			     HAL_REO_DEST_RING_PUSH_REASON_ROUTING_INSTRUCTION)) {
 			dev_kfree_skb_any(msdu);
@@ -2701,18 +2696,21 @@ try_again:
 			continue;
 		}
 
-		rxcb->is_first_msdu = !!(desc->rx_msdu_info.info0 &
+		rx_msdu_info0 = READ_ONCE(desc->rx_msdu_info.info0);
+		rx_mpdu_info0 = READ_ONCE(desc->rx_mpdu_info.info0);
+
+		rxcb->is_first_msdu = !!(rx_msdu_info0 &
 					 RX_MSDU_DESC_INFO0_FIRST_MSDU_IN_MPDU);
-		rxcb->is_last_msdu = !!(desc->rx_msdu_info.info0 &
+		rxcb->is_last_msdu = !!(rx_msdu_info0 &
 					RX_MSDU_DESC_INFO0_LAST_MSDU_IN_MPDU);
-		rxcb->is_continuation = !!(desc->rx_msdu_info.info0 &
+		rxcb->is_continuation = !!(rx_msdu_info0 &
 					   RX_MSDU_DESC_INFO0_MSDU_CONTINUATION);
 		rxcb->peer_id = FIELD_GET(RX_MPDU_DESC_META_DATA_PEER_ID,
-					  desc->rx_mpdu_info.meta_data);
+					  READ_ONCE(desc->rx_mpdu_info.meta_data));
 		rxcb->seq_no = FIELD_GET(RX_MPDU_DESC_INFO0_SEQ_NUM,
-					 desc->rx_mpdu_info.info0);
+					 rx_mpdu_info0);
 		rxcb->tid = FIELD_GET(HAL_REO_DEST_RING_INFO0_RX_QUEUE_NUM,
-				      desc->info0);
+				      info0);
 
 		rxcb->mac_id = mac_id;
 		__skb_queue_tail(&msdu_list[mac_id], msdu);
@@ -3872,6 +3870,7 @@ int ath11k_dp_process_rx_err(struct ath11k_base *ab, struct napi_struct *napi,
 		ath11k_hal_rx_msdu_link_info_get(link_desc_va, &num_msdus, msdu_cookies,
 						 &rbm);
 		if (rbm != HAL_RX_BUF_RBM_WBM_IDLE_DESC_LIST &&
+		    rbm != HAL_RX_BUF_RBM_SW1_BM &&
 		    rbm != HAL_RX_BUF_RBM_SW3_BM) {
 			ab->soc_stats.invalid_rbm++;
 			ath11k_warn(ab, "invalid return buffer manager %d\n", rbm);
diff --git a/drivers/net/wireless/ath/ath11k/fw.c b/drivers/net/wireless/ath/ath11k/fw.c
index 4e36292a79db..cbbd8e57119f 100644
--- a/drivers/net/wireless/ath/ath11k/fw.c
+++ b/drivers/net/wireless/ath/ath11k/fw.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
- * Copyright (c) 2022-2023, Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2022-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include "core.h"
@@ -166,3 +166,4 @@ void ath11k_fw_destroy(struct ath11k_base *ab)
 {
 	release_firmware(ab->fw.fw);
 }
+EXPORT_SYMBOL(ath11k_fw_destroy);
diff --git a/drivers/net/wireless/ath/ath11k/hal.c b/drivers/net/wireless/ath/ath11k/hal.c
index f02599bd1c36..f38decae77a9 100644
--- a/drivers/net/wireless/ath/ath11k/hal.c
+++ b/drivers/net/wireless/ath/ath11k/hal.c
@@ -599,7 +599,7 @@ u32 ath11k_hal_ce_dst_status_get_length(void *buf)
 	struct hal_ce_srng_dst_status_desc *desc = buf;
 	u32 len;
 
-	len = FIELD_GET(HAL_CE_DST_STATUS_DESC_FLAGS_LEN, desc->flags);
+	len = FIELD_GET(HAL_CE_DST_STATUS_DESC_FLAGS_LEN, READ_ONCE(desc->flags));
 	desc->flags &= ~HAL_CE_DST_STATUS_DESC_FLAGS_LEN;
 
 	return len;
@@ -829,7 +829,7 @@ void ath11k_hal_srng_access_begin(struct ath11k_base *ab, struct hal_srng *srng)
 		srng->u.src_ring.cached_tp =
 			*(volatile u32 *)srng->u.src_ring.tp_addr;
 	} else {
-		srng->u.dst_ring.cached_hp = *srng->u.dst_ring.hp_addr;
+		srng->u.dst_ring.cached_hp = READ_ONCE(*srng->u.dst_ring.hp_addr);
 
 		/* Try to prefetch the next descriptor in the ring */
 		if (srng->flags & HAL_SRNG_FLAGS_CACHED)
@@ -1346,6 +1346,10 @@ EXPORT_SYMBOL(ath11k_hal_srng_init);
 void ath11k_hal_srng_deinit(struct ath11k_base *ab)
 {
 	struct ath11k_hal *hal = &ab->hal;
+	int i;
+
+	for (i = 0; i < HAL_SRNG_RING_ID_MAX; i++)
+		ab->hal.srng_list[i].initialized = 0;
 
 	ath11k_hal_unregister_srng_key(ab);
 	ath11k_hal_free_cont_rdp(ab);
diff --git a/drivers/net/wireless/ath/ath11k/hal_rx.c b/drivers/net/wireless/ath/ath11k/hal_rx.c
index 8f7dd43dc1bd..753bd93f0212 100644
--- a/drivers/net/wireless/ath/ath11k/hal_rx.c
+++ b/drivers/net/wireless/ath/ath11k/hal_rx.c
@@ -372,7 +372,8 @@ int ath11k_hal_wbm_desc_parse_err(struct ath11k_base *ab, void *desc,
 
 	ret_buf_mgr = FIELD_GET(BUFFER_ADDR_INFO1_RET_BUF_MGR,
 				wbm_desc->buf_addr_info.info1);
-	if (ret_buf_mgr != HAL_RX_BUF_RBM_SW3_BM) {
+	if (ret_buf_mgr != HAL_RX_BUF_RBM_SW1_BM &&
+	    ret_buf_mgr != HAL_RX_BUF_RBM_SW3_BM) {
 		ab->soc_stats.invalid_rbm++;
 		return -EINVAL;
 	}
diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c
index f8068d2e848c..ddf4ec6b244b 100644
--- a/drivers/net/wireless/ath/ath11k/mac.c
+++ b/drivers/net/wireless/ath/ath11k/mac.c
@@ -8681,9 +8681,9 @@ ath11k_mac_op_set_bitrate_mask(struct ieee80211_hw *hw,
 				    arvif->vdev_id, ret);
 			return ret;
 		}
-		ieee80211_iterate_stations_atomic(ar->hw,
-						  ath11k_mac_disable_peer_fixed_rate,
-						  arvif);
+		ieee80211_iterate_stations_mtx(ar->hw,
+					       ath11k_mac_disable_peer_fixed_rate,
+					       arvif);
 	} else if (ath11k_mac_bitrate_mask_get_single_nss(ar, arvif, band, mask,
 							  &single_nss)) {
 		rate = WMI_FIXED_RATE_NONE;
@@ -8750,9 +8750,9 @@ ath11k_mac_op_set_bitrate_mask(struct ieee80211_hw *hw,
 		}
 
 		mutex_lock(&ar->conf_mutex);
-		ieee80211_iterate_stations_atomic(ar->hw,
-						  ath11k_mac_disable_peer_fixed_rate,
-						  arvif);
+		ieee80211_iterate_stations_mtx(ar->hw,
+					       ath11k_mac_disable_peer_fixed_rate,
+					       arvif);
 
 		arvif->bitrate_mask = *mask;
 		ieee80211_iterate_stations_atomic(ar->hw,
@@ -8938,6 +8938,86 @@ static void ath11k_mac_put_chain_rssi(struct station_info *sinfo,
 	}
 }
 
+static void ath11k_mac_fw_stats_reset(struct ath11k *ar)
+{
+	spin_lock_bh(&ar->data_lock);
+	ath11k_fw_stats_pdevs_free(&ar->fw_stats.pdevs);
+	ath11k_fw_stats_vdevs_free(&ar->fw_stats.vdevs);
+	ar->fw_stats.num_vdev_recvd = 0;
+	ar->fw_stats.num_bcn_recvd = 0;
+	spin_unlock_bh(&ar->data_lock);
+}
+
+int ath11k_mac_fw_stats_request(struct ath11k *ar,
+				struct stats_request_params *req_param)
+{
+	struct ath11k_base *ab = ar->ab;
+	unsigned long time_left;
+	int ret;
+
+	lockdep_assert_held(&ar->conf_mutex);
+
+	ath11k_mac_fw_stats_reset(ar);
+
+	reinit_completion(&ar->fw_stats_complete);
+	reinit_completion(&ar->fw_stats_done);
+
+	ret = ath11k_wmi_send_stats_request_cmd(ar, req_param);
+
+	if (ret) {
+		ath11k_warn(ab, "could not request fw stats (%d)\n",
+			    ret);
+		return ret;
+	}
+
+	time_left = wait_for_completion_timeout(&ar->fw_stats_complete, 1 * HZ);
+	if (!time_left)
+		return -ETIMEDOUT;
+
+	/* FW stats can get split when exceeding the stats data buffer limit.
+	 * In that case, since there is no end marking for the back-to-back
+	 * received 'update stats' event, we keep a 3 seconds timeout in case,
+	 * fw_stats_done is not marked yet
+	 */
+	time_left = wait_for_completion_timeout(&ar->fw_stats_done, 3 * HZ);
+	if (!time_left)
+		return -ETIMEDOUT;
+
+	return 0;
+}
+
+static int ath11k_mac_get_fw_stats(struct ath11k *ar, u32 pdev_id,
+				   u32 vdev_id, u32 stats_id)
+{
+	struct ath11k_base *ab = ar->ab;
+	struct stats_request_params req_param;
+	int ret;
+
+	mutex_lock(&ar->conf_mutex);
+
+	if (ar->state != ATH11K_STATE_ON) {
+		ret = -ENETDOWN;
+		goto err_unlock;
+	}
+
+	req_param.pdev_id = pdev_id;
+	req_param.vdev_id = vdev_id;
+	req_param.stats_id = stats_id;
+
+	ret = ath11k_mac_fw_stats_request(ar, &req_param);
+	if (ret)
+		ath11k_warn(ab, "failed to request fw stats: %d\n", ret);
+
+	ath11k_dbg(ab, ATH11K_DBG_WMI,
+		   "debug get fw stat pdev id %d vdev id %d stats id 0x%x\n",
+		   pdev_id, vdev_id, stats_id);
+
+err_unlock:
+	mutex_unlock(&ar->conf_mutex);
+
+	return ret;
+}
+
 static void ath11k_mac_op_sta_statistics(struct ieee80211_hw *hw,
 					 struct ieee80211_vif *vif,
 					 struct ieee80211_sta *sta,
@@ -8975,8 +9055,8 @@ static void ath11k_mac_op_sta_statistics(struct ieee80211_hw *hw,
 	if (!(sinfo->filled & BIT_ULL(NL80211_STA_INFO_CHAIN_SIGNAL)) &&
 	    arsta->arvif->vdev_type == WMI_VDEV_TYPE_STA &&
 	    ar->ab->hw_params.supports_rssi_stats &&
-	    !ath11k_debugfs_get_fw_stats(ar, ar->pdev->pdev_id, 0,
-					 WMI_REQUEST_RSSI_PER_CHAIN_STAT)) {
+	    !ath11k_mac_get_fw_stats(ar, ar->pdev->pdev_id, 0,
+				     WMI_REQUEST_RSSI_PER_CHAIN_STAT)) {
 		ath11k_mac_put_chain_rssi(sinfo, arsta, "fw stats", true);
 	}
 
@@ -8984,8 +9064,8 @@ static void ath11k_mac_op_sta_statistics(struct ieee80211_hw *hw,
 	if (!signal &&
 	    arsta->arvif->vdev_type == WMI_VDEV_TYPE_STA &&
 	    ar->ab->hw_params.supports_rssi_stats &&
-	    !(ath11k_debugfs_get_fw_stats(ar, ar->pdev->pdev_id, 0,
-					WMI_REQUEST_VDEV_STAT)))
+	    !(ath11k_mac_get_fw_stats(ar, ar->pdev->pdev_id, 0,
+				      WMI_REQUEST_VDEV_STAT)))
 		signal = arsta->rssi_beacon;
 
 	ath11k_dbg(ar->ab, ATH11K_DBG_MAC,
@@ -9331,11 +9411,13 @@ static int ath11k_fw_stats_request(struct ath11k *ar,
 	lockdep_assert_held(&ar->conf_mutex);
 
 	spin_lock_bh(&ar->data_lock);
-	ar->fw_stats_done = false;
 	ath11k_fw_stats_pdevs_free(&ar->fw_stats.pdevs);
+	ar->fw_stats.num_vdev_recvd = 0;
+	ar->fw_stats.num_bcn_recvd = 0;
 	spin_unlock_bh(&ar->data_lock);
 
 	reinit_completion(&ar->fw_stats_complete);
+	reinit_completion(&ar->fw_stats_done);
 
 	ret = ath11k_wmi_send_stats_request_cmd(ar, req_param);
 	if (ret) {
diff --git a/drivers/net/wireless/ath/ath11k/mac.h b/drivers/net/wireless/ath/ath11k/mac.h
index f5800fbecff8..5e61eea1bb03 100644
--- a/drivers/net/wireless/ath/ath11k/mac.h
+++ b/drivers/net/wireless/ath/ath11k/mac.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2023, 2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef ATH11K_MAC_H
@@ -179,4 +179,6 @@ int ath11k_mac_vif_set_keepalive(struct ath11k_vif *arvif,
 void ath11k_mac_fill_reg_tpc_info(struct ath11k *ar,
 				  struct ieee80211_vif *vif,
 				  struct ieee80211_chanctx_conf *ctx);
+int ath11k_mac_fw_stats_request(struct ath11k *ar,
+				struct stats_request_params *req_param);
 #endif
diff --git a/drivers/net/wireless/ath/ath11k/pci.c b/drivers/net/wireless/ath/ath11k/pci.c
index be9d2c69cc41..6ebfa5d02e2e 100644
--- a/drivers/net/wireless/ath/ath11k/pci.c
+++ b/drivers/net/wireless/ath/ath11k/pci.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2019-2020 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include <linux/module.h>
@@ -981,6 +981,7 @@ static void ath11k_pci_remove(struct pci_dev *pdev)
 	ath11k_core_deinit(ab);
 
 qmi_fail:
+	ath11k_fw_destroy(ab);
 	ath11k_mhi_unregister(ab_pci);
 
 	ath11k_pcic_free_irq(ab);
diff --git a/drivers/net/wireless/ath/ath11k/qmi.c b/drivers/net/wireless/ath/ath11k/qmi.c
index 7a22483b35cd..a5555c959dec 100644
--- a/drivers/net/wireless/ath/ath11k/qmi.c
+++ b/drivers/net/wireless/ath/ath11k/qmi.c
@@ -1989,6 +1989,15 @@ static int ath11k_qmi_alloc_target_mem_chunk(struct ath11k_base *ab)
 			    chunk->prev_size == chunk->size)
 				continue;
 
+			if (ab->qmi.mem_seg_count <= ATH11K_QMI_FW_MEM_REQ_SEGMENT_CNT) {
+				ath11k_dbg(ab, ATH11K_DBG_QMI,
+					   "size/type mismatch (current %d %u) (prev %d %u), try later with small size\n",
+					    chunk->size, chunk->type,
+					    chunk->prev_size, chunk->prev_type);
+				ab->qmi.target_mem_delayed = true;
+				return 0;
+			}
+
 			/* cannot reuse the existing chunk */
 			dma_free_coherent(ab->dev, chunk->prev_size,
 					  chunk->vaddr, chunk->paddr);
diff --git a/drivers/net/wireless/ath/ath11k/wmi.c b/drivers/net/wireless/ath/ath11k/wmi.c
index 87abfa547529..5f7edf622de7 100644
--- a/drivers/net/wireless/ath/ath11k/wmi.c
+++ b/drivers/net/wireless/ath/ath11k/wmi.c
@@ -8157,6 +8157,11 @@ static void ath11k_peer_assoc_conf_event(struct ath11k_base *ab, struct sk_buff
 static void ath11k_update_stats_event(struct ath11k_base *ab, struct sk_buff *skb)
 {
 	struct ath11k_fw_stats stats = {};
+	size_t total_vdevs_started = 0;
+	struct ath11k_pdev *pdev;
+	bool is_end = true;
+	int i;
+
 	struct ath11k *ar;
 	int ret;
 
@@ -8183,18 +8188,50 @@ static void ath11k_update_stats_event(struct ath11k_base *ab, struct sk_buff *sk
 
 	spin_lock_bh(&ar->data_lock);
 
-	/* WMI_REQUEST_PDEV_STAT can be requested via .get_txpower mac ops or via
+	/* WMI_REQUEST_PDEV_STAT, WMI_REQUEST_VDEV_STAT and
+	 * WMI_REQUEST_RSSI_PER_CHAIN_STAT can be requested via mac ops or via
 	 * debugfs fw stats. Therefore, processing it separately.
 	 */
 	if (stats.stats_id == WMI_REQUEST_PDEV_STAT) {
 		list_splice_tail_init(&stats.pdevs, &ar->fw_stats.pdevs);
-		ar->fw_stats_done = true;
+		complete(&ar->fw_stats_done);
+		goto complete;
+	}
+
+	if (stats.stats_id == WMI_REQUEST_RSSI_PER_CHAIN_STAT) {
+		complete(&ar->fw_stats_done);
+		goto complete;
+	}
+
+	if (stats.stats_id == WMI_REQUEST_VDEV_STAT) {
+		if (list_empty(&stats.vdevs)) {
+			ath11k_warn(ab, "empty vdev stats");
+			goto complete;
+		}
+		/* FW sends all the active VDEV stats irrespective of PDEV,
+		 * hence limit until the count of all VDEVs started
+		 */
+		for (i = 0; i < ab->num_radios; i++) {
+			pdev = rcu_dereference(ab->pdevs_active[i]);
+			if (pdev && pdev->ar)
+				total_vdevs_started += ar->num_started_vdevs;
+		}
+
+		if (total_vdevs_started)
+			is_end = ((++ar->fw_stats.num_vdev_recvd) ==
+				  total_vdevs_started);
+
+		list_splice_tail_init(&stats.vdevs,
+				      &ar->fw_stats.vdevs);
+
+		if (is_end)
+			complete(&ar->fw_stats_done);
+
 		goto complete;
 	}
 
-	/* WMI_REQUEST_VDEV_STAT, WMI_REQUEST_BCN_STAT and WMI_REQUEST_RSSI_PER_CHAIN_STAT
-	 * are currently requested only via debugfs fw stats. Hence, processing these
-	 * in debugfs context
+	/* WMI_REQUEST_BCN_STAT is currently requested only via debugfs fw stats.
+	 * Hence, processing it in debugfs context
 	 */
 	ath11k_debugfs_fw_stats_process(ar, &stats);
 
diff --git a/drivers/net/wireless/ath/ath12k/ce.c b/drivers/net/wireless/ath/ath12k/ce.c
index be0d669d31fc..740586fe49d1 100644
--- a/drivers/net/wireless/ath/ath12k/ce.c
+++ b/drivers/net/wireless/ath/ath12k/ce.c
@@ -343,11 +343,10 @@ static int ath12k_ce_completed_recv_next(struct ath12k_ce_pipe *pipe,
 		goto err;
 	}
 
+	/* Make sure descriptor is read after the head pointer. */
+	dma_rmb();
+
 	*nbytes = ath12k_hal_ce_dst_status_get_length(desc);
-	if (*nbytes == 0) {
-		ret = -EIO;
-		goto err;
-	}
 
 	*skb = pipe->dest_ring->skb[sw_index];
 	pipe->dest_ring->skb[sw_index] = NULL;
@@ -380,8 +379,8 @@ static void ath12k_ce_recv_process_cb(struct ath12k_ce_pipe *pipe)
 		dma_unmap_single(ab->dev, ATH12K_SKB_RXCB(skb)->paddr,
 				 max_nbytes, DMA_FROM_DEVICE);
 
-		if (unlikely(max_nbytes < nbytes)) {
-			ath12k_warn(ab, "rxed more than expected (nbytes %d, max %d)",
+		if (unlikely(max_nbytes < nbytes || nbytes == 0)) {
+			ath12k_warn(ab, "unexpected rx length (nbytes %d, max %d)",
 				    nbytes, max_nbytes);
 			dev_kfree_skb_any(skb);
 			continue;
diff --git a/drivers/net/wireless/ath/ath12k/ce.h b/drivers/net/wireless/ath/ath12k/ce.h
index 857bc5f9e946..f9547a3945e4 100644
--- a/drivers/net/wireless/ath/ath12k/ce.h
+++ b/drivers/net/wireless/ath/ath12k/ce.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2022, 2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2022, 2024-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef ATH12K_CE_H
@@ -39,8 +39,8 @@
 #define PIPEDIR_INOUT_H2H	4 /* bidirectional, host to host */
 
 /* CE address/mask */
-#define CE_HOST_IE_ADDRESS	0x00A1803C
-#define CE_HOST_IE_2_ADDRESS	0x00A18040
+#define CE_HOST_IE_ADDRESS	0x75804C
+#define CE_HOST_IE_2_ADDRESS	0x758050
 #define CE_HOST_IE_3_ADDRESS	CE_HOST_IE_ADDRESS
 
 #define CE_HOST_IE_3_SHIFT	0xC
diff --git a/drivers/net/wireless/ath/ath12k/core.c b/drivers/net/wireless/ath/ath12k/core.c
index 51252e8bc1ae..c3c76e268062 100644
--- a/drivers/net/wireless/ath/ath12k/core.c
+++ b/drivers/net/wireless/ath/ath12k/core.c
@@ -161,7 +161,7 @@ EXPORT_SYMBOL(ath12k_core_resume);
 
 static int __ath12k_core_create_board_name(struct ath12k_base *ab, char *name,
 					   size_t name_len, bool with_variant,
-					   bool bus_type_mode)
+					   bool bus_type_mode, bool with_default)
 {
 	/* strlen(',variant=') + strlen(ab->qmi.target.bdf_ext) */
 	char variant[9 + ATH12K_QMI_BDF_EXT_STR_LENGTH] = { 0 };
@@ -192,7 +192,9 @@ static int __ath12k_core_create_board_name(struct ath12k_base *ab, char *name,
 			  "bus=%s,qmi-chip-id=%d,qmi-board-id=%d%s",
 			  ath12k_bus_str(ab->hif.bus),
 			  ab->qmi.target.chip_id,
-			  ab->qmi.target.board_id, variant);
+			  with_default ?
+			  ATH12K_BOARD_ID_DEFAULT : ab->qmi.target.board_id,
+			  variant);
 		break;
 	}
 
@@ -204,19 +206,19 @@ static int __ath12k_core_create_board_name(struct ath12k_base *ab, char *name,
 static int ath12k_core_create_board_name(struct ath12k_base *ab, char *name,
 					 size_t name_len)
 {
-	return __ath12k_core_create_board_name(ab, name, name_len, true, false);
+	return __ath12k_core_create_board_name(ab, name, name_len, true, false, false);
 }
 
 static int ath12k_core_create_fallback_board_name(struct ath12k_base *ab, char *name,
 						  size_t name_len)
 {
-	return __ath12k_core_create_board_name(ab, name, name_len, false, false);
+	return __ath12k_core_create_board_name(ab, name, name_len, false, false, true);
 }
 
 static int ath12k_core_create_bus_type_board_name(struct ath12k_base *ab, char *name,
 						  size_t name_len)
 {
-	return __ath12k_core_create_board_name(ab, name, name_len, false, true);
+	return __ath12k_core_create_board_name(ab, name, name_len, false, true, true);
 }
 
 const struct firmware *ath12k_core_firmware_request(struct ath12k_base *ab,
@@ -1002,6 +1004,7 @@ static void ath12k_rfkill_work(struct work_struct *work)
 
 void ath12k_core_halt(struct ath12k *ar)
 {
+	struct list_head *pos, *n;
 	struct ath12k_base *ab = ar->ab;
 
 	lockdep_assert_held(&ar->conf_mutex);
@@ -1017,7 +1020,12 @@ void ath12k_core_halt(struct ath12k *ar)
 
 	rcu_assign_pointer(ab->pdevs_active[ar->pdev_idx], NULL);
 	synchronize_rcu();
-	INIT_LIST_HEAD(&ar->arvifs);
+
+	spin_lock_bh(&ar->data_lock);
+	list_for_each_safe(pos, n, &ar->arvifs)
+		list_del_init(pos);
+	spin_unlock_bh(&ar->data_lock);
+
 	idr_init(&ar->txmgmt_idr);
 }
 
diff --git a/drivers/net/wireless/ath/ath12k/core.h b/drivers/net/wireless/ath/ath12k/core.h
index 7f2e9a9b4097..3faf3430effb 100644
--- a/drivers/net/wireless/ath/ath12k/core.h
+++ b/drivers/net/wireless/ath/ath12k/core.h
@@ -148,6 +148,7 @@ struct ath12k_ext_irq_grp {
 	u32 num_irq;
 	u32 grp_id;
 	u64 timestamp;
+	bool napi_enabled;
 	struct napi_struct napi;
 	struct net_device *napi_ndev;
 };
diff --git a/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.c b/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.c
index f1b7e74aefe4..6f2e7ecc66af 100644
--- a/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.c
+++ b/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.c
@@ -1646,6 +1646,9 @@ static ssize_t ath12k_write_htt_stats_type(struct file *file,
 	const int size = 32;
 	int num_args;
 
+	if (count > size)
+		return -EINVAL;
+
 	char *buf __free(kfree) = kzalloc(size, GFP_KERNEL);
 	if (!buf)
 		return -ENOMEM;
diff --git a/drivers/net/wireless/ath/ath12k/dp.c b/drivers/net/wireless/ath/ath12k/dp.c
index 217eb57663f0..3244f7c3ca4f 100644
--- a/drivers/net/wireless/ath/ath12k/dp.c
+++ b/drivers/net/wireless/ath/ath12k/dp.c
@@ -79,6 +79,7 @@ int ath12k_dp_peer_setup(struct ath12k *ar, int vdev_id, const u8 *addr)
 	ret = ath12k_dp_rx_peer_frag_setup(ar, addr, vdev_id);
 	if (ret) {
 		ath12k_warn(ab, "failed to setup rx defrag context\n");
+		tid--;
 		goto peer_clean;
 	}
 
@@ -96,7 +97,7 @@ peer_clean:
 		return -ENOENT;
 	}
 
-	for (; tid >= 0; tid--)
+	for (tid--; tid >= 0; tid--)
 		ath12k_dp_rx_peer_tid_delete(ar, peer, tid);
 
 	spin_unlock_bh(&ab->base_lock);
diff --git a/drivers/net/wireless/ath/ath12k/dp_mon.c b/drivers/net/wireless/ath/ath12k/dp_mon.c
index 5c6749bc4039..7bfd323cdf24 100644
--- a/drivers/net/wireless/ath/ath12k/dp_mon.c
+++ b/drivers/net/wireless/ath/ath12k/dp_mon.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2019-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include "dp_mon.h"
@@ -666,6 +666,11 @@ ath12k_dp_mon_rx_parse_status_tlv(struct ath12k_base *ab,
 		if (userid < HAL_MAX_UL_MU_USERS) {
 			struct hal_rx_user_status *rxuser_stats =
 				&ppdu_info->userstats[userid];
+
+			if (ppdu_info->num_mpdu_fcs_ok > 1 ||
+			    ppdu_info->num_mpdu_fcs_err > 1)
+				ppdu_info->userstats[userid].ampdu_present = true;
+
 			ppdu_info->num_users += 1;
 
 			ath12k_dp_mon_rx_handle_ofdma_info(tlv_data, rxuser_stats);
@@ -783,8 +788,8 @@ ath12k_dp_mon_rx_parse_status_tlv(struct ath12k_base *ab,
 		if (userid < HAL_MAX_UL_MU_USERS) {
 			info[0] = __le32_to_cpu(mpdu_start->info0);
 			ppdu_info->userid = userid;
-			ppdu_info->ampdu_id[userid] =
-				u32_get_bits(info[0], HAL_RX_MPDU_START_INFO1_PEERID);
+			ppdu_info->userstats[userid].ampdu_id =
+				u32_get_bits(info[0], HAL_RX_MPDU_START_INFO0_PPDU_ID);
 		}
 
 		mon_mpdu = kzalloc(sizeof(*mon_mpdu), GFP_ATOMIC);
@@ -1020,15 +1025,14 @@ static void ath12k_dp_mon_update_radiotap(struct ath12k *ar,
 {
 	struct ieee80211_supported_band *sband;
 	u8 *ptr = NULL;
-	u16 ampdu_id = ppduinfo->ampdu_id[ppduinfo->userid];
 
 	rxs->flag |= RX_FLAG_MACTIME_START;
 	rxs->signal = ppduinfo->rssi_comb + ATH12K_DEFAULT_NOISE_FLOOR;
 	rxs->nss = ppduinfo->nss + 1;
 
-	if (ampdu_id) {
+	if (ppduinfo->userstats[ppduinfo->userid].ampdu_present) {
 		rxs->flag |= RX_FLAG_AMPDU_DETAILS;
-		rxs->ampdu_reference = ampdu_id;
+		rxs->ampdu_reference = ppduinfo->userstats[ppduinfo->userid].ampdu_id;
 	}
 
 	if (ppduinfo->he_mu_flags) {
@@ -1076,6 +1080,8 @@ static void ath12k_dp_mon_rx_deliver_msdu(struct ath12k *ar, struct napi_struct
 	bool is_mcbc = rxcb->is_mcbc;
 	bool is_eapol_tkip = rxcb->is_eapol;
 
+	status->link_valid = 0;
+
 	if ((status->encoding == RX_ENC_HE) && !(status->flag & RX_FLAG_RADIOTAP_HE) &&
 	    !(status->flag & RX_FLAG_SKIP_MONITOR)) {
 		he = skb_push(msdu, sizeof(known));
@@ -2118,7 +2124,7 @@ int ath12k_dp_mon_srng_process(struct ath12k *ar, int mac_id, int *budget,
 		dest_idx = 0;
 move_next:
 		ath12k_dp_mon_buf_replenish(ab, buf_ring, 1);
-		ath12k_hal_srng_src_get_next_entry(ab, srng);
+		ath12k_hal_srng_dst_get_next_entry(ab, srng);
 		num_buffs_reaped++;
 	}
 
diff --git a/drivers/net/wireless/ath/ath12k/dp_rx.c b/drivers/net/wireless/ath/ath12k/dp_rx.c
index 91e3393f7b5f..eebdcc16e8fc 100644
--- a/drivers/net/wireless/ath/ath12k/dp_rx.c
+++ b/drivers/net/wireless/ath/ath12k/dp_rx.c
@@ -228,12 +228,6 @@ static void ath12k_dp_rx_desc_get_crypto_header(struct ath12k_base *ab,
 	ab->hal_rx_ops->rx_desc_get_crypto_header(desc, crypto_hdr, enctype);
 }
 
-static u16 ath12k_dp_rxdesc_get_mpdu_frame_ctrl(struct ath12k_base *ab,
-						struct hal_rx_desc *desc)
-{
-	return ab->hal_rx_ops->rx_desc_get_mpdu_frame_ctl(desc);
-}
-
 static inline u8 ath12k_dp_rx_get_msdu_src_link(struct ath12k_base *ab,
 						struct hal_rx_desc *desc)
 {
@@ -1768,6 +1762,7 @@ static int ath12k_dp_rx_msdu_coalesce(struct ath12k *ar,
 	struct hal_rx_desc *ldesc;
 	int space_extra, rem_len, buf_len;
 	u32 hal_rx_desc_sz = ar->ab->hal.hal_desc_sz;
+	bool is_continuation;
 
 	/* As the msdu is spread across multiple rx buffers,
 	 * find the offset to the start of msdu for computing
@@ -1816,7 +1811,8 @@ static int ath12k_dp_rx_msdu_coalesce(struct ath12k *ar,
 	rem_len = msdu_len - buf_first_len;
 	while ((skb = __skb_dequeue(msdu_list)) != NULL && rem_len > 0) {
 		rxcb = ATH12K_SKB_RXCB(skb);
-		if (rxcb->is_continuation)
+		is_continuation = rxcb->is_continuation;
+		if (is_continuation)
 			buf_len = DP_RX_BUFFER_SIZE - hal_rx_desc_sz;
 		else
 			buf_len = rem_len;
@@ -1834,7 +1830,7 @@ static int ath12k_dp_rx_msdu_coalesce(struct ath12k *ar,
 		dev_kfree_skb_any(skb);
 
 		rem_len -= buf_len;
-		if (!rxcb->is_continuation)
+		if (!is_continuation)
 			break;
 	}
 
@@ -1872,8 +1868,7 @@ static void ath12k_dp_rx_h_csum_offload(struct ath12k *ar, struct sk_buff *msdu)
 			  CHECKSUM_NONE : CHECKSUM_UNNECESSARY;
 }
 
-static int ath12k_dp_rx_crypto_mic_len(struct ath12k *ar,
-				       enum hal_encrypt_type enctype)
+int ath12k_dp_rx_crypto_mic_len(struct ath12k *ar, enum hal_encrypt_type enctype)
 {
 	switch (enctype) {
 	case HAL_ENCRYPT_TYPE_OPEN:
@@ -2067,10 +2062,13 @@ static void ath12k_get_dot11_hdr_from_rx_desc(struct ath12k *ar,
 	struct hal_rx_desc *rx_desc = rxcb->rx_desc;
 	struct ath12k_base *ab = ar->ab;
 	size_t hdr_len, crypto_len;
-	struct ieee80211_hdr *hdr;
-	u16 qos_ctl;
-	__le16 fc;
-	u8 *crypto_hdr;
+	struct ieee80211_hdr hdr;
+	__le16 qos_ctl;
+	u8 *crypto_hdr, mesh_ctrl;
+
+	ath12k_dp_rx_desc_get_dot11_hdr(ab, rx_desc, &hdr);
+	hdr_len = ieee80211_hdrlen(hdr.frame_control);
+	mesh_ctrl = ath12k_dp_rx_h_mesh_ctl_present(ab, rx_desc);
 
 	if (!(status->flag & RX_FLAG_IV_STRIPPED)) {
 		crypto_len = ath12k_dp_rx_crypto_param_len(ar, enctype);
@@ -2078,27 +2076,21 @@ static void ath12k_get_dot11_hdr_from_rx_desc(struct ath12k *ar,
 		ath12k_dp_rx_desc_get_crypto_header(ab, rx_desc, crypto_hdr, enctype);
 	}
 
-	fc = cpu_to_le16(ath12k_dp_rxdesc_get_mpdu_frame_ctrl(ab, rx_desc));
-	hdr_len = ieee80211_hdrlen(fc);
 	skb_push(msdu, hdr_len);
-	hdr = (struct ieee80211_hdr *)msdu->data;
-	hdr->frame_control = fc;
-
-	/* Get wifi header from rx_desc */
-	ath12k_dp_rx_desc_get_dot11_hdr(ab, rx_desc, hdr);
+	memcpy(msdu->data, &hdr, min(hdr_len, sizeof(hdr)));
 
 	if (rxcb->is_mcbc)
 		status->flag &= ~RX_FLAG_PN_VALIDATED;
 
 	/* Add QOS header */
-	if (ieee80211_is_data_qos(hdr->frame_control)) {
-		qos_ctl = rxcb->tid;
-		if (ath12k_dp_rx_h_mesh_ctl_present(ab, rx_desc))
-			qos_ctl |= IEEE80211_QOS_CTL_MESH_CONTROL_PRESENT;
+	if (ieee80211_is_data_qos(hdr.frame_control)) {
+		struct ieee80211_hdr *qos_ptr = (struct ieee80211_hdr *)msdu->data;
+
+		qos_ctl = cpu_to_le16(rxcb->tid & IEEE80211_QOS_CTL_TID_MASK);
+		if (mesh_ctrl)
+			qos_ctl |= cpu_to_le16(IEEE80211_QOS_CTL_MESH_CONTROL_PRESENT);
 
-		/* TODO: Add other QoS ctl fields when required */
-		memcpy(msdu->data + (hdr_len - IEEE80211_QOS_CTL_LEN),
-		       &qos_ctl, IEEE80211_QOS_CTL_LEN);
+		memcpy(ieee80211_get_qos_ctl(qos_ptr), &qos_ctl, IEEE80211_QOS_CTL_LEN);
 	}
 }
 
@@ -2470,6 +2462,29 @@ static void ath12k_dp_rx_deliver_msdu(struct ath12k *ar, struct napi_struct *nap
 	ieee80211_rx_napi(ath12k_ar_to_hw(ar), pubsta, msdu, napi);
 }
 
+static bool ath12k_dp_rx_check_nwifi_hdr_len_valid(struct ath12k_base *ab,
+						   struct hal_rx_desc *rx_desc,
+						   struct sk_buff *msdu)
+{
+	struct ieee80211_hdr *hdr;
+	u8 decap_type;
+	u32 hdr_len;
+
+	decap_type = ath12k_dp_rx_h_decap_type(ab, rx_desc);
+	if (decap_type != DP_RX_DECAP_TYPE_NATIVE_WIFI)
+		return true;
+
+	hdr = (struct ieee80211_hdr *)msdu->data;
+	hdr_len = ieee80211_hdrlen(hdr->frame_control);
+
+	if ((likely(hdr_len <= DP_MAX_NWIFI_HDR_LEN)))
+		return true;
+
+	ab->soc_stats.invalid_rbm++;
+	WARN_ON_ONCE(1);
+	return false;
+}
+
 static int ath12k_dp_rx_process_msdu(struct ath12k *ar,
 				     struct sk_buff *msdu,
 				     struct sk_buff_head *msdu_list,
@@ -2528,6 +2543,11 @@ static int ath12k_dp_rx_process_msdu(struct ath12k *ar,
 		}
 	}
 
+	if (unlikely(!ath12k_dp_rx_check_nwifi_hdr_len_valid(ab, rx_desc, msdu))) {
+		ret = -EINVAL;
+		goto free_out;
+	}
+
 	ath12k_dp_rx_h_ppdu(ar, rx_desc, rx_status);
 	ath12k_dp_rx_h_mpdu(ar, msdu, rx_desc, rx_status);
 
@@ -2880,6 +2900,9 @@ mic_fail:
 		    RX_FLAG_IV_STRIPPED | RX_FLAG_DECRYPTED;
 	skb_pull(msdu, hal_rx_desc_sz);
 
+	if (unlikely(!ath12k_dp_rx_check_nwifi_hdr_len_valid(ab, rx_desc, msdu)))
+		return -EINVAL;
+
 	ath12k_dp_rx_h_ppdu(ar, rx_desc, rxs);
 	ath12k_dp_rx_h_undecap(ar, msdu, rx_desc,
 			       HAL_ENCRYPT_TYPE_TKIP_MIC, rxs, true);
@@ -3600,6 +3623,9 @@ static int ath12k_dp_rx_h_null_q_desc(struct ath12k *ar, struct sk_buff *msdu,
 		skb_put(msdu, hal_rx_desc_sz + l3pad_bytes + msdu_len);
 		skb_pull(msdu, hal_rx_desc_sz + l3pad_bytes);
 	}
+	if (unlikely(!ath12k_dp_rx_check_nwifi_hdr_len_valid(ab, desc, msdu)))
+		return -EINVAL;
+
 	ath12k_dp_rx_h_ppdu(ar, desc, status);
 
 	ath12k_dp_rx_h_mpdu(ar, msdu, desc, status);
@@ -3644,7 +3670,7 @@ static bool ath12k_dp_rx_h_reo_err(struct ath12k *ar, struct sk_buff *msdu,
 	return drop;
 }
 
-static void ath12k_dp_rx_h_tkip_mic_err(struct ath12k *ar, struct sk_buff *msdu,
+static bool ath12k_dp_rx_h_tkip_mic_err(struct ath12k *ar, struct sk_buff *msdu,
 					struct ieee80211_rx_status *status)
 {
 	struct ath12k_base *ab = ar->ab;
@@ -3659,9 +3685,21 @@ static void ath12k_dp_rx_h_tkip_mic_err(struct ath12k *ar, struct sk_buff *msdu,
 
 	l3pad_bytes = ath12k_dp_rx_h_l3pad(ab, desc);
 	msdu_len = ath12k_dp_rx_h_msdu_len(ab, desc);
+
+	if ((hal_rx_desc_sz + l3pad_bytes + msdu_len) > DP_RX_BUFFER_SIZE) {
+		ath12k_dbg(ab, ATH12K_DBG_DATA,
+			   "invalid msdu len in tkip mic err %u\n", msdu_len);
+		ath12k_dbg_dump(ab, ATH12K_DBG_DATA, NULL, "", desc,
+				sizeof(*desc));
+		return true;
+	}
+
 	skb_put(msdu, hal_rx_desc_sz + l3pad_bytes + msdu_len);
 	skb_pull(msdu, hal_rx_desc_sz + l3pad_bytes);
 
+	if (unlikely(!ath12k_dp_rx_check_nwifi_hdr_len_valid(ab, desc, msdu)))
+		return true;
+
 	ath12k_dp_rx_h_ppdu(ar, desc, status);
 
 	status->flag |= (RX_FLAG_MMIC_STRIPPED | RX_FLAG_MMIC_ERROR |
@@ -3669,6 +3707,7 @@ static void ath12k_dp_rx_h_tkip_mic_err(struct ath12k *ar, struct sk_buff *msdu,
 
 	ath12k_dp_rx_h_undecap(ar, msdu, desc,
 			       HAL_ENCRYPT_TYPE_TKIP_MIC, status, false);
+	return false;
 }
 
 static bool ath12k_dp_rx_h_rxdma_err(struct ath12k *ar,  struct sk_buff *msdu,
@@ -3687,7 +3726,7 @@ static bool ath12k_dp_rx_h_rxdma_err(struct ath12k *ar,  struct sk_buff *msdu,
 	case HAL_REO_ENTR_RING_RXDMA_ECODE_TKIP_MIC_ERR:
 		err_bitmap = ath12k_dp_rx_h_mpdu_err(ab, rx_desc);
 		if (err_bitmap & HAL_RX_MPDU_ERR_TKIP_MIC) {
-			ath12k_dp_rx_h_tkip_mic_err(ar, msdu, status);
+			drop = ath12k_dp_rx_h_tkip_mic_err(ar, msdu, status);
 			break;
 		}
 		fallthrough;
diff --git a/drivers/net/wireless/ath/ath12k/dp_rx.h b/drivers/net/wireless/ath/ath12k/dp_rx.h
index eb1f92559179..4232091d9e32 100644
--- a/drivers/net/wireless/ath/ath12k/dp_rx.h
+++ b/drivers/net/wireless/ath/ath12k/dp_rx.h
@@ -143,4 +143,7 @@ int ath12k_dp_htt_tlv_iter(struct ath12k_base *ab, const void *ptr, size_t len,
 			   int (*iter)(struct ath12k_base *ar, u16 tag, u16 len,
 				       const void *ptr, void *data),
 			   void *data);
+
+int ath12k_dp_rx_crypto_mic_len(struct ath12k *ar, enum hal_encrypt_type enctype);
+
 #endif /* ATH12K_DP_RX_H */
diff --git a/drivers/net/wireless/ath/ath12k/dp_tx.c b/drivers/net/wireless/ath/ath12k/dp_tx.c
index 44406e0b4a34..21e07b5cee57 100644
--- a/drivers/net/wireless/ath/ath12k/dp_tx.c
+++ b/drivers/net/wireless/ath/ath12k/dp_tx.c
@@ -117,7 +117,7 @@ static void ath12k_hal_tx_cmd_ext_desc_setup(struct ath12k_base *ab,
 			       le32_encode_bits(ti->data_len,
 						HAL_TX_MSDU_EXT_INFO1_BUF_LEN);
 
-	tcl_ext_cmd->info1 = le32_encode_bits(1, HAL_TX_MSDU_EXT_INFO1_EXTN_OVERRIDE) |
+	tcl_ext_cmd->info1 |= le32_encode_bits(1, HAL_TX_MSDU_EXT_INFO1_EXTN_OVERRIDE) |
 				le32_encode_bits(ti->encap_type,
 						 HAL_TX_MSDU_EXT_INFO1_ENCAP_TYPE) |
 				le32_encode_bits(ti->encrypt_type,
@@ -227,7 +227,7 @@ int ath12k_dp_tx(struct ath12k *ar, struct ath12k_vif *arvif,
 	struct ath12k_skb_cb *skb_cb = ATH12K_SKB_CB(skb);
 	struct hal_tcl_data_cmd *hal_tcl_desc;
 	struct hal_tx_msdu_ext_desc *msg;
-	struct sk_buff *skb_ext_desc;
+	struct sk_buff *skb_ext_desc = NULL;
 	struct hal_srng *tcl_ring;
 	struct ieee80211_hdr *hdr = (void *)skb->data;
 	struct dp_tx_ring *tx_ring;
@@ -397,17 +397,15 @@ map:
 			if (ret < 0) {
 				ath12k_dbg(ab, ATH12K_DBG_DP_TX,
 					   "Failed to add HTT meta data, dropping packet\n");
-				goto fail_unmap_dma;
+				goto fail_free_ext_skb;
 			}
 		}
 
 		ti.paddr = dma_map_single(ab->dev, skb_ext_desc->data,
 					  skb_ext_desc->len, DMA_TO_DEVICE);
 		ret = dma_mapping_error(ab->dev, ti.paddr);
-		if (ret) {
-			kfree_skb(skb_ext_desc);
-			goto fail_unmap_dma;
-		}
+		if (ret)
+			goto fail_free_ext_skb;
 
 		ti.data_len = skb_ext_desc->len;
 		ti.type = HAL_TCL_DESC_TYPE_EXT_DESC;
@@ -443,7 +441,7 @@ map:
 			ring_selector++;
 		}
 
-		goto fail_unmap_dma;
+		goto fail_unmap_dma_ext;
 	}
 
 	ath12k_hal_tx_cmd_desc_setup(ab, hal_tcl_desc, &ti);
@@ -459,13 +457,16 @@ map:
 
 	return 0;
 
-fail_unmap_dma:
-	dma_unmap_single(ab->dev, ti.paddr, ti.data_len, DMA_TO_DEVICE);
-
+fail_unmap_dma_ext:
 	if (skb_cb->paddr_ext_desc)
 		dma_unmap_single(ab->dev, skb_cb->paddr_ext_desc,
 				 sizeof(struct hal_tx_msdu_ext_desc),
 				 DMA_TO_DEVICE);
+fail_free_ext_skb:
+	kfree_skb(skb_ext_desc);
+
+fail_unmap_dma:
+	dma_unmap_single(ab->dev, ti.paddr, ti.data_len, DMA_TO_DEVICE);
 
 fail_remove_tx_buf:
 	ath12k_dp_tx_release_txbuf(dp, tx_desc, pool_id);
@@ -557,15 +558,16 @@ ath12k_dp_tx_process_htt_tx_complete(struct ath12k_base *ab,
 
 	switch (wbm_status) {
 	case HAL_WBM_REL_HTT_TX_COMP_STATUS_OK:
-	case HAL_WBM_REL_HTT_TX_COMP_STATUS_DROP:
-	case HAL_WBM_REL_HTT_TX_COMP_STATUS_TTL:
 		ts.acked = (wbm_status == HAL_WBM_REL_HTT_TX_COMP_STATUS_OK);
 		ts.ack_rssi = le32_get_bits(status_desc->info2,
 					    HTT_TX_WBM_COMP_INFO2_ACK_RSSI);
 		ath12k_dp_tx_htt_tx_complete_buf(ab, msdu, tx_ring, &ts);
 		break;
+	case HAL_WBM_REL_HTT_TX_COMP_STATUS_DROP:
+	case HAL_WBM_REL_HTT_TX_COMP_STATUS_TTL:
 	case HAL_WBM_REL_HTT_TX_COMP_STATUS_REINJ:
 	case HAL_WBM_REL_HTT_TX_COMP_STATUS_INSPECT:
+	case HAL_WBM_REL_HTT_TX_COMP_STATUS_VDEVID_MISMATCH:
 		ath12k_dp_tx_free_txbuf(ab, msdu, mac_id, tx_ring);
 		break;
 	case HAL_WBM_REL_HTT_TX_COMP_STATUS_MEC_NOTIFY:
diff --git a/drivers/net/wireless/ath/ath12k/hal.c b/drivers/net/wireless/ath/ath12k/hal.c
index ca04bfae8bdc..3afb11c7bf18 100644
--- a/drivers/net/wireless/ath/ath12k/hal.c
+++ b/drivers/net/wireless/ath/ath12k/hal.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 #include <linux/dma-mapping.h>
 #include "hal_tx.h"
@@ -449,8 +449,8 @@ static u8 *ath12k_hw_qcn9274_rx_desc_mpdu_start_addr2(struct hal_rx_desc *desc)
 
 static bool ath12k_hw_qcn9274_rx_desc_is_da_mcbc(struct hal_rx_desc *desc)
 {
-	return __le32_to_cpu(desc->u.qcn9274.mpdu_start.info6) &
-	       RX_MPDU_START_INFO6_MCAST_BCAST;
+	return __le16_to_cpu(desc->u.qcn9274.msdu_end.info5) &
+	       RX_MSDU_END_INFO5_DA_IS_MCBC;
 }
 
 static void ath12k_hw_qcn9274_rx_desc_get_dot11_hdr(struct hal_rx_desc *desc,
@@ -511,11 +511,6 @@ static void ath12k_hw_qcn9274_rx_desc_get_crypto_hdr(struct hal_rx_desc *desc,
 	crypto_hdr[7] = HAL_RX_MPDU_INFO_PN_GET_BYTE2(desc->u.qcn9274.mpdu_start.pn[1]);
 }
 
-static u16 ath12k_hw_qcn9274_rx_desc_get_mpdu_frame_ctl(struct hal_rx_desc *desc)
-{
-	return __le16_to_cpu(desc->u.qcn9274.mpdu_start.frame_ctrl);
-}
-
 static int ath12k_hal_srng_create_config_qcn9274(struct ath12k_base *ab)
 {
 	struct ath12k_hal *hal = &ab->hal;
@@ -552,9 +547,9 @@ static int ath12k_hal_srng_create_config_qcn9274(struct ath12k_base *ab)
 	s->reg_start[1] = HAL_SEQ_WCSS_UMAC_REO_REG + HAL_REO_STATUS_HP;
 
 	s = &hal->srng_config[HAL_TCL_DATA];
-	s->reg_start[0] = HAL_SEQ_WCSS_UMAC_TCL_REG + HAL_TCL1_RING_BASE_LSB;
+	s->reg_start[0] = HAL_SEQ_WCSS_UMAC_TCL_REG + HAL_TCL1_RING_BASE_LSB(ab);
 	s->reg_start[1] = HAL_SEQ_WCSS_UMAC_TCL_REG + HAL_TCL1_RING_HP;
-	s->reg_size[0] = HAL_TCL2_RING_BASE_LSB - HAL_TCL1_RING_BASE_LSB;
+	s->reg_size[0] = HAL_TCL2_RING_BASE_LSB(ab) - HAL_TCL1_RING_BASE_LSB(ab);
 	s->reg_size[1] = HAL_TCL2_RING_HP - HAL_TCL1_RING_HP;
 
 	s = &hal->srng_config[HAL_TCL_CMD];
@@ -566,29 +561,29 @@ static int ath12k_hal_srng_create_config_qcn9274(struct ath12k_base *ab)
 	s->reg_start[1] = HAL_SEQ_WCSS_UMAC_TCL_REG + HAL_TCL_STATUS_RING_HP;
 
 	s = &hal->srng_config[HAL_CE_SRC];
-	s->reg_start[0] = HAL_SEQ_WCSS_UMAC_CE0_SRC_REG + HAL_CE_DST_RING_BASE_LSB;
-	s->reg_start[1] = HAL_SEQ_WCSS_UMAC_CE0_SRC_REG + HAL_CE_DST_RING_HP;
-	s->reg_size[0] = HAL_SEQ_WCSS_UMAC_CE1_SRC_REG -
-		HAL_SEQ_WCSS_UMAC_CE0_SRC_REG;
-	s->reg_size[1] = HAL_SEQ_WCSS_UMAC_CE1_SRC_REG -
-		HAL_SEQ_WCSS_UMAC_CE0_SRC_REG;
+	s->reg_start[0] = HAL_SEQ_WCSS_UMAC_CE0_SRC_REG(ab) + HAL_CE_DST_RING_BASE_LSB;
+	s->reg_start[1] = HAL_SEQ_WCSS_UMAC_CE0_SRC_REG(ab) + HAL_CE_DST_RING_HP;
+	s->reg_size[0] = HAL_SEQ_WCSS_UMAC_CE1_SRC_REG(ab) -
+		HAL_SEQ_WCSS_UMAC_CE0_SRC_REG(ab);
+	s->reg_size[1] = HAL_SEQ_WCSS_UMAC_CE1_SRC_REG(ab) -
+		HAL_SEQ_WCSS_UMAC_CE0_SRC_REG(ab);
 
 	s = &hal->srng_config[HAL_CE_DST];
-	s->reg_start[0] = HAL_SEQ_WCSS_UMAC_CE0_DST_REG + HAL_CE_DST_RING_BASE_LSB;
-	s->reg_start[1] = HAL_SEQ_WCSS_UMAC_CE0_DST_REG + HAL_CE_DST_RING_HP;
-	s->reg_size[0] = HAL_SEQ_WCSS_UMAC_CE1_DST_REG -
-		HAL_SEQ_WCSS_UMAC_CE0_DST_REG;
-	s->reg_size[1] = HAL_SEQ_WCSS_UMAC_CE1_DST_REG -
-		HAL_SEQ_WCSS_UMAC_CE0_DST_REG;
+	s->reg_start[0] = HAL_SEQ_WCSS_UMAC_CE0_DST_REG(ab) + HAL_CE_DST_RING_BASE_LSB;
+	s->reg_start[1] = HAL_SEQ_WCSS_UMAC_CE0_DST_REG(ab) + HAL_CE_DST_RING_HP;
+	s->reg_size[0] = HAL_SEQ_WCSS_UMAC_CE1_DST_REG(ab) -
+		HAL_SEQ_WCSS_UMAC_CE0_DST_REG(ab);
+	s->reg_size[1] = HAL_SEQ_WCSS_UMAC_CE1_DST_REG(ab) -
+		HAL_SEQ_WCSS_UMAC_CE0_DST_REG(ab);
 
 	s = &hal->srng_config[HAL_CE_DST_STATUS];
-	s->reg_start[0] = HAL_SEQ_WCSS_UMAC_CE0_DST_REG +
+	s->reg_start[0] = HAL_SEQ_WCSS_UMAC_CE0_DST_REG(ab) +
 		HAL_CE_DST_STATUS_RING_BASE_LSB;
-	s->reg_start[1] = HAL_SEQ_WCSS_UMAC_CE0_DST_REG + HAL_CE_DST_STATUS_RING_HP;
-	s->reg_size[0] = HAL_SEQ_WCSS_UMAC_CE1_DST_REG -
-		HAL_SEQ_WCSS_UMAC_CE0_DST_REG;
-	s->reg_size[1] = HAL_SEQ_WCSS_UMAC_CE1_DST_REG -
-		HAL_SEQ_WCSS_UMAC_CE0_DST_REG;
+	s->reg_start[1] = HAL_SEQ_WCSS_UMAC_CE0_DST_REG(ab) + HAL_CE_DST_STATUS_RING_HP;
+	s->reg_size[0] = HAL_SEQ_WCSS_UMAC_CE1_DST_REG(ab) -
+		HAL_SEQ_WCSS_UMAC_CE0_DST_REG(ab);
+	s->reg_size[1] = HAL_SEQ_WCSS_UMAC_CE1_DST_REG(ab) -
+		HAL_SEQ_WCSS_UMAC_CE0_DST_REG(ab);
 
 	s = &hal->srng_config[HAL_WBM_IDLE_LINK];
 	s->reg_start[0] = HAL_SEQ_WCSS_UMAC_WBM_REG + HAL_WBM_IDLE_LINK_RING_BASE_LSB(ab);
@@ -736,7 +731,6 @@ const struct hal_rx_ops hal_rx_qcn9274_ops = {
 	.rx_desc_is_da_mcbc = ath12k_hw_qcn9274_rx_desc_is_da_mcbc,
 	.rx_desc_get_dot11_hdr = ath12k_hw_qcn9274_rx_desc_get_dot11_hdr,
 	.rx_desc_get_crypto_header = ath12k_hw_qcn9274_rx_desc_get_crypto_hdr,
-	.rx_desc_get_mpdu_frame_ctl = ath12k_hw_qcn9274_rx_desc_get_mpdu_frame_ctl,
 	.dp_rx_h_msdu_done = ath12k_hw_qcn9274_dp_rx_h_msdu_done,
 	.dp_rx_h_l4_cksum_fail = ath12k_hw_qcn9274_dp_rx_h_l4_cksum_fail,
 	.dp_rx_h_ip_cksum_fail = ath12k_hw_qcn9274_dp_rx_h_ip_cksum_fail,
@@ -908,8 +902,8 @@ static u8 *ath12k_hw_qcn9274_compact_rx_desc_mpdu_start_addr2(struct hal_rx_desc
 
 static bool ath12k_hw_qcn9274_compact_rx_desc_is_da_mcbc(struct hal_rx_desc *desc)
 {
-	return __le32_to_cpu(desc->u.qcn9274_compact.mpdu_start.info6) &
-	       RX_MPDU_START_INFO6_MCAST_BCAST;
+	return __le16_to_cpu(desc->u.qcn9274_compact.msdu_end.info5) &
+	       RX_MSDU_END_INFO5_DA_IS_MCBC;
 }
 
 static void ath12k_hw_qcn9274_compact_rx_desc_get_dot11_hdr(struct hal_rx_desc *desc,
@@ -975,11 +969,6 @@ ath12k_hw_qcn9274_compact_rx_desc_get_crypto_hdr(struct hal_rx_desc *desc,
 		HAL_RX_MPDU_INFO_PN_GET_BYTE2(desc->u.qcn9274_compact.mpdu_start.pn[1]);
 }
 
-static u16 ath12k_hw_qcn9274_compact_rx_desc_get_mpdu_frame_ctl(struct hal_rx_desc *desc)
-{
-	return __le16_to_cpu(desc->u.qcn9274_compact.mpdu_start.frame_ctrl);
-}
-
 static bool ath12k_hw_qcn9274_compact_dp_rx_h_msdu_done(struct hal_rx_desc *desc)
 {
 	return !!le32_get_bits(desc->u.qcn9274_compact.msdu_end.info14,
@@ -1080,8 +1069,6 @@ const struct hal_rx_ops hal_rx_qcn9274_compact_ops = {
 	.rx_desc_is_da_mcbc = ath12k_hw_qcn9274_compact_rx_desc_is_da_mcbc,
 	.rx_desc_get_dot11_hdr = ath12k_hw_qcn9274_compact_rx_desc_get_dot11_hdr,
 	.rx_desc_get_crypto_header = ath12k_hw_qcn9274_compact_rx_desc_get_crypto_hdr,
-	.rx_desc_get_mpdu_frame_ctl =
-		ath12k_hw_qcn9274_compact_rx_desc_get_mpdu_frame_ctl,
 	.dp_rx_h_msdu_done = ath12k_hw_qcn9274_compact_dp_rx_h_msdu_done,
 	.dp_rx_h_l4_cksum_fail = ath12k_hw_qcn9274_compact_dp_rx_h_l4_cksum_fail,
 	.dp_rx_h_ip_cksum_fail = ath12k_hw_qcn9274_compact_dp_rx_h_ip_cksum_fail,
@@ -1330,11 +1317,6 @@ static void ath12k_hw_wcn7850_rx_desc_get_crypto_hdr(struct hal_rx_desc *desc,
 	crypto_hdr[7] = HAL_RX_MPDU_INFO_PN_GET_BYTE2(desc->u.wcn7850.mpdu_start.pn[1]);
 }
 
-static u16 ath12k_hw_wcn7850_rx_desc_get_mpdu_frame_ctl(struct hal_rx_desc *desc)
-{
-	return __le16_to_cpu(desc->u.wcn7850.mpdu_start.frame_ctrl);
-}
-
 static int ath12k_hal_srng_create_config_wcn7850(struct ath12k_base *ab)
 {
 	struct ath12k_hal *hal = &ab->hal;
@@ -1371,9 +1353,9 @@ static int ath12k_hal_srng_create_config_wcn7850(struct ath12k_base *ab)
 
 	s = &hal->srng_config[HAL_TCL_DATA];
 	s->max_rings = 5;
-	s->reg_start[0] = HAL_SEQ_WCSS_UMAC_TCL_REG + HAL_TCL1_RING_BASE_LSB;
+	s->reg_start[0] = HAL_SEQ_WCSS_UMAC_TCL_REG + HAL_TCL1_RING_BASE_LSB(ab);
 	s->reg_start[1] = HAL_SEQ_WCSS_UMAC_TCL_REG + HAL_TCL1_RING_HP;
-	s->reg_size[0] = HAL_TCL2_RING_BASE_LSB - HAL_TCL1_RING_BASE_LSB;
+	s->reg_size[0] = HAL_TCL2_RING_BASE_LSB(ab) - HAL_TCL1_RING_BASE_LSB(ab);
 	s->reg_size[1] = HAL_TCL2_RING_HP - HAL_TCL1_RING_HP;
 
 	s = &hal->srng_config[HAL_TCL_CMD];
@@ -1386,31 +1368,31 @@ static int ath12k_hal_srng_create_config_wcn7850(struct ath12k_base *ab)
 
 	s = &hal->srng_config[HAL_CE_SRC];
 	s->max_rings = 12;
-	s->reg_start[0] = HAL_SEQ_WCSS_UMAC_CE0_SRC_REG + HAL_CE_DST_RING_BASE_LSB;
-	s->reg_start[1] = HAL_SEQ_WCSS_UMAC_CE0_SRC_REG + HAL_CE_DST_RING_HP;
-	s->reg_size[0] = HAL_SEQ_WCSS_UMAC_CE1_SRC_REG -
-		HAL_SEQ_WCSS_UMAC_CE0_SRC_REG;
-	s->reg_size[1] = HAL_SEQ_WCSS_UMAC_CE1_SRC_REG -
-		HAL_SEQ_WCSS_UMAC_CE0_SRC_REG;
+	s->reg_start[0] = HAL_SEQ_WCSS_UMAC_CE0_SRC_REG(ab) + HAL_CE_DST_RING_BASE_LSB;
+	s->reg_start[1] = HAL_SEQ_WCSS_UMAC_CE0_SRC_REG(ab) + HAL_CE_DST_RING_HP;
+	s->reg_size[0] = HAL_SEQ_WCSS_UMAC_CE1_SRC_REG(ab) -
+		HAL_SEQ_WCSS_UMAC_CE0_SRC_REG(ab);
+	s->reg_size[1] = HAL_SEQ_WCSS_UMAC_CE1_SRC_REG(ab) -
+		HAL_SEQ_WCSS_UMAC_CE0_SRC_REG(ab);
 
 	s = &hal->srng_config[HAL_CE_DST];
 	s->max_rings = 12;
-	s->reg_start[0] = HAL_SEQ_WCSS_UMAC_CE0_DST_REG + HAL_CE_DST_RING_BASE_LSB;
-	s->reg_start[1] = HAL_SEQ_WCSS_UMAC_CE0_DST_REG + HAL_CE_DST_RING_HP;
-	s->reg_size[0] = HAL_SEQ_WCSS_UMAC_CE1_DST_REG -
-		HAL_SEQ_WCSS_UMAC_CE0_DST_REG;
-	s->reg_size[1] = HAL_SEQ_WCSS_UMAC_CE1_DST_REG -
-		HAL_SEQ_WCSS_UMAC_CE0_DST_REG;
+	s->reg_start[0] = HAL_SEQ_WCSS_UMAC_CE0_DST_REG(ab) + HAL_CE_DST_RING_BASE_LSB;
+	s->reg_start[1] = HAL_SEQ_WCSS_UMAC_CE0_DST_REG(ab) + HAL_CE_DST_RING_HP;
+	s->reg_size[0] = HAL_SEQ_WCSS_UMAC_CE1_DST_REG(ab) -
+		HAL_SEQ_WCSS_UMAC_CE0_DST_REG(ab);
+	s->reg_size[1] = HAL_SEQ_WCSS_UMAC_CE1_DST_REG(ab) -
+		HAL_SEQ_WCSS_UMAC_CE0_DST_REG(ab);
 
 	s = &hal->srng_config[HAL_CE_DST_STATUS];
 	s->max_rings = 12;
-	s->reg_start[0] = HAL_SEQ_WCSS_UMAC_CE0_DST_REG +
+	s->reg_start[0] = HAL_SEQ_WCSS_UMAC_CE0_DST_REG(ab) +
 		HAL_CE_DST_STATUS_RING_BASE_LSB;
-	s->reg_start[1] = HAL_SEQ_WCSS_UMAC_CE0_DST_REG + HAL_CE_DST_STATUS_RING_HP;
-	s->reg_size[0] = HAL_SEQ_WCSS_UMAC_CE1_DST_REG -
-		HAL_SEQ_WCSS_UMAC_CE0_DST_REG;
-	s->reg_size[1] = HAL_SEQ_WCSS_UMAC_CE1_DST_REG -
-		HAL_SEQ_WCSS_UMAC_CE0_DST_REG;
+	s->reg_start[1] = HAL_SEQ_WCSS_UMAC_CE0_DST_REG(ab) + HAL_CE_DST_STATUS_RING_HP;
+	s->reg_size[0] = HAL_SEQ_WCSS_UMAC_CE1_DST_REG(ab) -
+		HAL_SEQ_WCSS_UMAC_CE0_DST_REG(ab);
+	s->reg_size[1] = HAL_SEQ_WCSS_UMAC_CE1_DST_REG(ab) -
+		HAL_SEQ_WCSS_UMAC_CE0_DST_REG(ab);
 
 	s = &hal->srng_config[HAL_WBM_IDLE_LINK];
 	s->reg_start[0] = HAL_SEQ_WCSS_UMAC_WBM_REG + HAL_WBM_IDLE_LINK_RING_BASE_LSB(ab);
@@ -1555,7 +1537,6 @@ const struct hal_rx_ops hal_rx_wcn7850_ops = {
 	.rx_desc_is_da_mcbc = ath12k_hw_wcn7850_rx_desc_is_da_mcbc,
 	.rx_desc_get_dot11_hdr = ath12k_hw_wcn7850_rx_desc_get_dot11_hdr,
 	.rx_desc_get_crypto_header = ath12k_hw_wcn7850_rx_desc_get_crypto_hdr,
-	.rx_desc_get_mpdu_frame_ctl = ath12k_hw_wcn7850_rx_desc_get_mpdu_frame_ctl,
 	.dp_rx_h_msdu_done = ath12k_hw_wcn7850_dp_rx_h_msdu_done,
 	.dp_rx_h_l4_cksum_fail = ath12k_hw_wcn7850_dp_rx_h_l4_cksum_fail,
 	.dp_rx_h_ip_cksum_fail = ath12k_hw_wcn7850_dp_rx_h_ip_cksum_fail,
@@ -1756,7 +1737,7 @@ static void ath12k_hal_srng_src_hw_init(struct ath12k_base *ab,
 			      HAL_TCL1_RING_BASE_MSB_RING_BASE_ADDR_MSB) |
 	      u32_encode_bits((srng->entry_size * srng->num_entries),
 			      HAL_TCL1_RING_BASE_MSB_RING_SIZE);
-	ath12k_hif_write32(ab, reg_base + HAL_TCL1_RING_BASE_MSB_OFFSET, val);
+	ath12k_hif_write32(ab, reg_base + HAL_TCL1_RING_BASE_MSB_OFFSET(ab), val);
 
 	val = u32_encode_bits(srng->entry_size, HAL_REO1_RING_ID_ENTRY_SIZE);
 	ath12k_hif_write32(ab, reg_base + HAL_TCL1_RING_ID_OFFSET(ab), val);
@@ -1962,7 +1943,7 @@ u32 ath12k_hal_ce_dst_status_get_length(struct hal_ce_srng_dst_status_desc *desc
 {
 	u32 len;
 
-	len = le32_get_bits(desc->flags, HAL_CE_DST_STATUS_DESC_FLAGS_LEN);
+	len = le32_get_bits(READ_ONCE(desc->flags), HAL_CE_DST_STATUS_DESC_FLAGS_LEN);
 	desc->flags &= ~cpu_to_le32(HAL_CE_DST_STATUS_DESC_FLAGS_LEN);
 
 	return len;
@@ -2132,7 +2113,7 @@ void ath12k_hal_srng_access_begin(struct ath12k_base *ab, struct hal_srng *srng)
 		srng->u.src_ring.cached_tp =
 			*(volatile u32 *)srng->u.src_ring.tp_addr;
 	else
-		srng->u.dst_ring.cached_hp = *srng->u.dst_ring.hp_addr;
+		srng->u.dst_ring.cached_hp = READ_ONCE(*srng->u.dst_ring.hp_addr);
 }
 
 /* Update cached ring head/tail pointers to HW. ath12k_hal_srng_access_begin()
diff --git a/drivers/net/wireless/ath/ath12k/hal.h b/drivers/net/wireless/ath/ath12k/hal.h
index 8a78bb9a10bc..fb7ec6fce07d 100644
--- a/drivers/net/wireless/ath/ath12k/hal.h
+++ b/drivers/net/wireless/ath/ath12k/hal.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef ATH12K_HAL_H
@@ -44,10 +44,14 @@ struct ath12k_base;
 #define HAL_SEQ_WCSS_UMAC_OFFSET		0x00a00000
 #define HAL_SEQ_WCSS_UMAC_REO_REG		0x00a38000
 #define HAL_SEQ_WCSS_UMAC_TCL_REG		0x00a44000
-#define HAL_SEQ_WCSS_UMAC_CE0_SRC_REG		0x01b80000
-#define HAL_SEQ_WCSS_UMAC_CE0_DST_REG		0x01b81000
-#define HAL_SEQ_WCSS_UMAC_CE1_SRC_REG		0x01b82000
-#define HAL_SEQ_WCSS_UMAC_CE1_DST_REG		0x01b83000
+#define HAL_SEQ_WCSS_UMAC_CE0_SRC_REG(ab) \
+	((ab)->hw_params->regs->hal_umac_ce0_src_reg_base)
+#define HAL_SEQ_WCSS_UMAC_CE0_DST_REG(ab) \
+	((ab)->hw_params->regs->hal_umac_ce0_dest_reg_base)
+#define HAL_SEQ_WCSS_UMAC_CE1_SRC_REG(ab) \
+	((ab)->hw_params->regs->hal_umac_ce1_src_reg_base)
+#define HAL_SEQ_WCSS_UMAC_CE1_DST_REG(ab) \
+	((ab)->hw_params->regs->hal_umac_ce1_dest_reg_base)
 #define HAL_SEQ_WCSS_UMAC_WBM_REG		0x00a34000
 
 #define HAL_CE_WFSS_CE_REG_BASE			0x01b80000
@@ -57,8 +61,10 @@ struct ath12k_base;
 /* SW2TCL(x) R0 ring configuration address */
 #define HAL_TCL1_RING_CMN_CTRL_REG		0x00000020
 #define HAL_TCL1_RING_DSCP_TID_MAP		0x00000240
-#define HAL_TCL1_RING_BASE_LSB			0x00000900
-#define HAL_TCL1_RING_BASE_MSB			0x00000904
+#define HAL_TCL1_RING_BASE_LSB(ab) \
+	((ab)->hw_params->regs->hal_tcl1_ring_base_lsb)
+#define HAL_TCL1_RING_BASE_MSB(ab) \
+	((ab)->hw_params->regs->hal_tcl1_ring_base_msb)
 #define HAL_TCL1_RING_ID(ab)			((ab)->hw_params->regs->hal_tcl1_ring_id)
 #define HAL_TCL1_RING_MISC(ab) \
 	((ab)->hw_params->regs->hal_tcl1_ring_misc)
@@ -76,30 +82,31 @@ struct ath12k_base;
 	((ab)->hw_params->regs->hal_tcl1_ring_msi1_base_msb)
 #define HAL_TCL1_RING_MSI1_DATA(ab) \
 	((ab)->hw_params->regs->hal_tcl1_ring_msi1_data)
-#define HAL_TCL2_RING_BASE_LSB			0x00000978
+#define HAL_TCL2_RING_BASE_LSB(ab) \
+	((ab)->hw_params->regs->hal_tcl2_ring_base_lsb)
 #define HAL_TCL_RING_BASE_LSB(ab) \
 	((ab)->hw_params->regs->hal_tcl_ring_base_lsb)
 
-#define HAL_TCL1_RING_MSI1_BASE_LSB_OFFSET(ab)				\
-	(HAL_TCL1_RING_MSI1_BASE_LSB(ab) - HAL_TCL1_RING_BASE_LSB)
-#define HAL_TCL1_RING_MSI1_BASE_MSB_OFFSET(ab)				\
-	(HAL_TCL1_RING_MSI1_BASE_MSB(ab) - HAL_TCL1_RING_BASE_LSB)
-#define HAL_TCL1_RING_MSI1_DATA_OFFSET(ab)				\
-	(HAL_TCL1_RING_MSI1_DATA(ab) - HAL_TCL1_RING_BASE_LSB)
-#define HAL_TCL1_RING_BASE_MSB_OFFSET				\
-	(HAL_TCL1_RING_BASE_MSB - HAL_TCL1_RING_BASE_LSB)
-#define HAL_TCL1_RING_ID_OFFSET(ab)				\
-	(HAL_TCL1_RING_ID(ab) - HAL_TCL1_RING_BASE_LSB)
-#define HAL_TCL1_RING_CONSR_INT_SETUP_IX0_OFFSET(ab)			\
-	(HAL_TCL1_RING_CONSUMER_INT_SETUP_IX0(ab) - HAL_TCL1_RING_BASE_LSB)
-#define HAL_TCL1_RING_CONSR_INT_SETUP_IX1_OFFSET(ab) \
-		(HAL_TCL1_RING_CONSUMER_INT_SETUP_IX1(ab) - HAL_TCL1_RING_BASE_LSB)
-#define HAL_TCL1_RING_TP_ADDR_LSB_OFFSET(ab) \
-		(HAL_TCL1_RING_TP_ADDR_LSB(ab) - HAL_TCL1_RING_BASE_LSB)
-#define HAL_TCL1_RING_TP_ADDR_MSB_OFFSET(ab) \
-		(HAL_TCL1_RING_TP_ADDR_MSB(ab) - HAL_TCL1_RING_BASE_LSB)
-#define HAL_TCL1_RING_MISC_OFFSET(ab) \
-		(HAL_TCL1_RING_MISC(ab) - HAL_TCL1_RING_BASE_LSB)
+#define HAL_TCL1_RING_MSI1_BASE_LSB_OFFSET(ab) ({ typeof(ab) _ab = (ab); \
+	(HAL_TCL1_RING_MSI1_BASE_LSB(_ab) - HAL_TCL1_RING_BASE_LSB(_ab)); })
+#define HAL_TCL1_RING_MSI1_BASE_MSB_OFFSET(ab)	({ typeof(ab) _ab = (ab); \
+	(HAL_TCL1_RING_MSI1_BASE_MSB(_ab) - HAL_TCL1_RING_BASE_LSB(_ab)); })
+#define HAL_TCL1_RING_MSI1_DATA_OFFSET(ab) ({ typeof(ab) _ab = (ab); \
+	(HAL_TCL1_RING_MSI1_DATA(_ab) - HAL_TCL1_RING_BASE_LSB(_ab)); })
+#define HAL_TCL1_RING_BASE_MSB_OFFSET(ab) ({ typeof(ab) _ab = (ab); \
+	(HAL_TCL1_RING_BASE_MSB(_ab) - HAL_TCL1_RING_BASE_LSB(_ab)); })
+#define HAL_TCL1_RING_ID_OFFSET(ab) ({ typeof(ab) _ab = (ab); \
+	(HAL_TCL1_RING_ID(_ab) - HAL_TCL1_RING_BASE_LSB(_ab)); })
+#define HAL_TCL1_RING_CONSR_INT_SETUP_IX0_OFFSET(ab) ({ typeof(ab) _ab = (ab); \
+	(HAL_TCL1_RING_CONSUMER_INT_SETUP_IX0(_ab) - HAL_TCL1_RING_BASE_LSB(_ab)); })
+#define HAL_TCL1_RING_CONSR_INT_SETUP_IX1_OFFSET(ab) ({ typeof(ab) _ab = (ab); \
+	(HAL_TCL1_RING_CONSUMER_INT_SETUP_IX1(_ab) - HAL_TCL1_RING_BASE_LSB(_ab)); })
+#define HAL_TCL1_RING_TP_ADDR_LSB_OFFSET(ab) ({ typeof(ab) _ab = (ab); \
+	(HAL_TCL1_RING_TP_ADDR_LSB(_ab) - HAL_TCL1_RING_BASE_LSB(_ab)); })
+#define HAL_TCL1_RING_TP_ADDR_MSB_OFFSET(ab) ({ typeof(ab) _ab = (ab); \
+	(HAL_TCL1_RING_TP_ADDR_MSB(_ab) - HAL_TCL1_RING_BASE_LSB(_ab)); })
+#define HAL_TCL1_RING_MISC_OFFSET(ab) ({ typeof(ab) _ab = (ab); \
+	(HAL_TCL1_RING_MISC(_ab) - HAL_TCL1_RING_BASE_LSB(_ab)); })
 
 /* SW2TCL(x) R2 ring pointers (head/tail) address */
 #define HAL_TCL1_RING_HP			0x00002000
@@ -1068,7 +1075,6 @@ struct hal_rx_ops {
 	bool (*rx_desc_is_da_mcbc)(struct hal_rx_desc *desc);
 	void (*rx_desc_get_dot11_hdr)(struct hal_rx_desc *desc,
 				      struct ieee80211_hdr *hdr);
-	u16 (*rx_desc_get_mpdu_frame_ctl)(struct hal_rx_desc *desc);
 	void (*rx_desc_get_crypto_header)(struct hal_rx_desc *desc,
 					  u8 *crypto_hdr,
 					  enum hal_encrypt_type enctype);
diff --git a/drivers/net/wireless/ath/ath12k/hal_desc.h b/drivers/net/wireless/ath/ath12k/hal_desc.h
index 739f73370015..8cbe28950d0c 100644
--- a/drivers/net/wireless/ath/ath12k/hal_desc.h
+++ b/drivers/net/wireless/ath/ath12k/hal_desc.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2022, 2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2022, 2024-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 #include "core.h"
 
@@ -705,7 +705,7 @@ enum hal_rx_msdu_desc_reo_dest_ind {
 #define RX_MSDU_DESC_INFO0_DECAP_FORMAT		GENMASK(30, 29)
 
 #define HAL_RX_MSDU_PKT_LENGTH_GET(val)		\
-	(u32_get_bits((val), RX_MSDU_DESC_INFO0_MSDU_LENGTH))
+	(le32_get_bits((val), RX_MSDU_DESC_INFO0_MSDU_LENGTH))
 
 struct rx_msdu_desc {
 	__le32 info0;
@@ -1296,6 +1296,7 @@ enum hal_wbm_htt_tx_comp_status {
 	HAL_WBM_REL_HTT_TX_COMP_STATUS_REINJ,
 	HAL_WBM_REL_HTT_TX_COMP_STATUS_INSPECT,
 	HAL_WBM_REL_HTT_TX_COMP_STATUS_MEC_NOTIFY,
+	HAL_WBM_REL_HTT_TX_COMP_STATUS_VDEVID_MISMATCH,
 	HAL_WBM_REL_HTT_TX_COMP_STATUS_MAX,
 };
 
@@ -2966,7 +2967,7 @@ struct hal_mon_buf_ring {
 
 #define HAL_MON_DEST_COOKIE_BUF_ID      GENMASK(17, 0)
 
-#define HAL_MON_DEST_INFO0_END_OFFSET		GENMASK(15, 0)
+#define HAL_MON_DEST_INFO0_END_OFFSET		GENMASK(11, 0)
 #define HAL_MON_DEST_INFO0_FLUSH_DETECTED	BIT(16)
 #define HAL_MON_DEST_INFO0_END_OF_PPDU		BIT(17)
 #define HAL_MON_DEST_INFO0_INITIATOR		BIT(18)
diff --git a/drivers/net/wireless/ath/ath12k/hal_rx.h b/drivers/net/wireless/ath/ath12k/hal_rx.h
index 095216eabc01..8c37cbc01b1c 100644
--- a/drivers/net/wireless/ath/ath12k/hal_rx.h
+++ b/drivers/net/wireless/ath/ath12k/hal_rx.h
@@ -143,6 +143,8 @@ struct hal_rx_user_status {
 	u32 mpdu_fcs_ok_bitmap[HAL_RX_NUM_WORDS_PER_PPDU_BITMAP];
 	u32 mpdu_ok_byte_count;
 	u32 mpdu_err_byte_count;
+	bool ampdu_present;
+	u16 ampdu_id;
 };
 
 #define HAL_MAX_UL_MU_USERS	37
@@ -226,7 +228,6 @@ struct hal_rx_mon_ppdu_info {
 	u8 addr4[ETH_ALEN];
 	struct hal_rx_user_status userstats[HAL_MAX_UL_MU_USERS];
 	u8 userid;
-	u16 ampdu_id[HAL_MAX_UL_MU_USERS];
 	bool first_msdu_in_mpdu;
 	bool is_ampdu;
 	u8 medium_prot_type;
diff --git a/drivers/net/wireless/ath/ath12k/hw.c b/drivers/net/wireless/ath/ath12k/hw.c
index ec1bda95e555..057ef2d282b2 100644
--- a/drivers/net/wireless/ath/ath12k/hw.c
+++ b/drivers/net/wireless/ath/ath12k/hw.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include <linux/types.h>
@@ -615,6 +615,9 @@ static const struct ath12k_hw_regs qcn9274_v1_regs = {
 	.hal_tcl1_ring_msi1_base_msb = 0x0000094c,
 	.hal_tcl1_ring_msi1_data = 0x00000950,
 	.hal_tcl_ring_base_lsb = 0x00000b58,
+	.hal_tcl1_ring_base_lsb = 0x00000900,
+	.hal_tcl1_ring_base_msb = 0x00000904,
+	.hal_tcl2_ring_base_lsb = 0x00000978,
 
 	/* TCL STATUS ring address */
 	.hal_tcl_status_ring_base_lsb = 0x00000d38,
@@ -677,6 +680,14 @@ static const struct ath12k_hw_regs qcn9274_v1_regs = {
 
 	/* REO status ring address */
 	.hal_reo_status_ring_base = 0x00000a84,
+
+	/* CE base address */
+	.hal_umac_ce0_src_reg_base = 0x01b80000,
+	.hal_umac_ce0_dest_reg_base = 0x01b81000,
+	.hal_umac_ce1_src_reg_base = 0x01b82000,
+	.hal_umac_ce1_dest_reg_base = 0x01b83000,
+
+	.gcc_gcc_pcie_hot_rst = 0x1e38338,
 };
 
 static const struct ath12k_hw_regs qcn9274_v2_regs = {
@@ -691,6 +702,9 @@ static const struct ath12k_hw_regs qcn9274_v2_regs = {
 	.hal_tcl1_ring_msi1_base_msb = 0x0000094c,
 	.hal_tcl1_ring_msi1_data = 0x00000950,
 	.hal_tcl_ring_base_lsb = 0x00000b58,
+	.hal_tcl1_ring_base_lsb = 0x00000900,
+	.hal_tcl1_ring_base_msb = 0x00000904,
+	.hal_tcl2_ring_base_lsb = 0x00000978,
 
 	/* TCL STATUS ring address */
 	.hal_tcl_status_ring_base_lsb = 0x00000d38,
@@ -757,6 +771,14 @@ static const struct ath12k_hw_regs qcn9274_v2_regs = {
 
 	/* REO status ring address */
 	.hal_reo_status_ring_base = 0x00000aa0,
+
+	/* CE base address */
+	.hal_umac_ce0_src_reg_base = 0x01b80000,
+	.hal_umac_ce0_dest_reg_base = 0x01b81000,
+	.hal_umac_ce1_src_reg_base = 0x01b82000,
+	.hal_umac_ce1_dest_reg_base = 0x01b83000,
+
+	.gcc_gcc_pcie_hot_rst = 0x1e38338,
 };
 
 static const struct ath12k_hw_regs wcn7850_regs = {
@@ -771,6 +793,9 @@ static const struct ath12k_hw_regs wcn7850_regs = {
 	.hal_tcl1_ring_msi1_base_msb = 0x0000094c,
 	.hal_tcl1_ring_msi1_data = 0x00000950,
 	.hal_tcl_ring_base_lsb = 0x00000b58,
+	.hal_tcl1_ring_base_lsb = 0x00000900,
+	.hal_tcl1_ring_base_msb = 0x00000904,
+	.hal_tcl2_ring_base_lsb = 0x00000978,
 
 	/* TCL STATUS ring address */
 	.hal_tcl_status_ring_base_lsb = 0x00000d38,
@@ -833,6 +858,14 @@ static const struct ath12k_hw_regs wcn7850_regs = {
 
 	/* REO status ring address */
 	.hal_reo_status_ring_base = 0x00000a84,
+
+	/* CE base address */
+	.hal_umac_ce0_src_reg_base = 0x01b80000,
+	.hal_umac_ce0_dest_reg_base = 0x01b81000,
+	.hal_umac_ce1_src_reg_base = 0x01b82000,
+	.hal_umac_ce1_dest_reg_base = 0x01b83000,
+
+	.gcc_gcc_pcie_hot_rst = 0x1e40304,
 };
 
 static const struct ath12k_hw_hal_params ath12k_hw_hal_params_qcn9274 = {
@@ -1051,7 +1084,7 @@ static const struct ath12k_hw_params ath12k_hw_params[] = {
 		.download_calib = true,
 		.supports_suspend = false,
 		.tcl_ring_retry = true,
-		.reoq_lut_support = false,
+		.reoq_lut_support = true,
 		.supports_shadow_regs = false,
 
 		.num_tcl_banks = 48,
diff --git a/drivers/net/wireless/ath/ath12k/hw.h b/drivers/net/wireless/ath/ath12k/hw.h
index 8d52182e28ae..862b11325a90 100644
--- a/drivers/net/wireless/ath/ath12k/hw.h
+++ b/drivers/net/wireless/ath/ath12k/hw.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef ATH12K_HW_H
@@ -293,6 +293,9 @@ struct ath12k_hw_regs {
 	u32 hal_tcl1_ring_msi1_base_msb;
 	u32 hal_tcl1_ring_msi1_data;
 	u32 hal_tcl_ring_base_lsb;
+	u32 hal_tcl1_ring_base_lsb;
+	u32 hal_tcl1_ring_base_msb;
+	u32 hal_tcl2_ring_base_lsb;
 
 	u32 hal_tcl_status_ring_base_lsb;
 
@@ -316,6 +319,11 @@ struct ath12k_hw_regs {
 	u32 pcie_qserdes_sysclk_en_sel;
 	u32 pcie_pcs_osc_dtct_config_base;
 
+	u32 hal_umac_ce0_src_reg_base;
+	u32 hal_umac_ce0_dest_reg_base;
+	u32 hal_umac_ce1_src_reg_base;
+	u32 hal_umac_ce1_dest_reg_base;
+
 	u32 hal_ppe_rel_ring_base;
 
 	u32 hal_reo2_ring_base;
@@ -347,6 +355,8 @@ struct ath12k_hw_regs {
 	u32 hal_reo_cmd_ring_base;
 
 	u32 hal_reo_status_ring_base;
+
+	u32 gcc_gcc_pcie_hot_rst;
 };
 
 static inline const char *ath12k_bd_ie_type_str(enum ath12k_bd_ie_type type)
diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index 8946141aa0dc..4b3fbec397ac 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -3864,8 +3864,8 @@ static int ath12k_install_key(struct ath12k_vif *arvif,
 
 	switch (key->cipher) {
 	case WLAN_CIPHER_SUITE_CCMP:
+	case WLAN_CIPHER_SUITE_CCMP_256:
 		arg.key_cipher = WMI_CIPHER_AES_CCM;
-		/* TODO: Re-check if flag is valid */
 		key->flags |= IEEE80211_KEY_FLAG_GENERATE_IV_MGMT;
 		break;
 	case WLAN_CIPHER_SUITE_TKIP:
@@ -3873,12 +3873,10 @@ static int ath12k_install_key(struct ath12k_vif *arvif,
 		arg.key_txmic_len = 8;
 		arg.key_rxmic_len = 8;
 		break;
-	case WLAN_CIPHER_SUITE_CCMP_256:
-		arg.key_cipher = WMI_CIPHER_AES_CCM;
-		break;
 	case WLAN_CIPHER_SUITE_GCMP:
 	case WLAN_CIPHER_SUITE_GCMP_256:
 		arg.key_cipher = WMI_CIPHER_AES_GCM;
+		key->flags |= IEEE80211_KEY_FLAG_GENERATE_IV_MGMT;
 		break;
 	default:
 		ath12k_warn(ar->ab, "cipher %d is not supported\n", key->cipher);
@@ -5725,6 +5723,8 @@ static int ath12k_mac_mgmt_tx_wmi(struct ath12k *ar, struct ath12k_vif *arvif,
 	struct ath12k_base *ab = ar->ab;
 	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
 	struct ieee80211_tx_info *info;
+	enum hal_encrypt_type enctype;
+	unsigned int mic_len;
 	dma_addr_t paddr;
 	int buf_id;
 	int ret;
@@ -5738,12 +5738,16 @@ static int ath12k_mac_mgmt_tx_wmi(struct ath12k *ar, struct ath12k_vif *arvif,
 		return -ENOSPC;
 
 	info = IEEE80211_SKB_CB(skb);
-	if (!(info->flags & IEEE80211_TX_CTL_HW_80211_ENCAP)) {
+	if ((ATH12K_SKB_CB(skb)->flags & ATH12K_SKB_CIPHER_SET) &&
+	    !(info->flags & IEEE80211_TX_CTL_HW_80211_ENCAP)) {
 		if ((ieee80211_is_action(hdr->frame_control) ||
 		     ieee80211_is_deauth(hdr->frame_control) ||
 		     ieee80211_is_disassoc(hdr->frame_control)) &&
 		     ieee80211_has_protected(hdr->frame_control)) {
-			skb_put(skb, IEEE80211_CCMP_MIC_LEN);
+			enctype =
+			    ath12k_dp_tx_get_encrypt_type(ATH12K_SKB_CB(skb)->cipher);
+			mic_len = ath12k_dp_rx_crypto_mic_len(ar, enctype);
+			skb_put(skb, mic_len);
 		}
 	}
 
@@ -7220,9 +7224,9 @@ ath12k_mac_vdev_start_restart(struct ath12k_vif *arvif,
 							chandef->chan->band,
 							arvif->vif->type);
 	arg.min_power = 0;
-	arg.max_power = chandef->chan->max_power * 2;
-	arg.max_reg_power = chandef->chan->max_reg_power * 2;
-	arg.max_antenna_gain = chandef->chan->max_antenna_gain * 2;
+	arg.max_power = chandef->chan->max_power;
+	arg.max_reg_power = chandef->chan->max_reg_power;
+	arg.max_antenna_gain = chandef->chan->max_antenna_gain;
 
 	arg.pref_tx_streams = ar->num_tx_chains;
 	arg.pref_rx_streams = ar->num_rx_chains;
@@ -9214,6 +9218,7 @@ static int ath12k_mac_hw_register(struct ath12k_hw *ah)
 
 	wiphy->mbssid_max_interfaces = mbssid_max_interfaces;
 	wiphy->ema_max_profile_periodicity = TARGET_EMA_MAX_PROFILE_PERIOD;
+	ieee80211_hw_set(hw, SUPPORTS_MULTI_BSSID);
 
 	if (is_6ghz) {
 		wiphy_ext_feature_set(wiphy,
diff --git a/drivers/net/wireless/ath/ath12k/pci.c b/drivers/net/wireless/ath/ath12k/pci.c
index bd269aa1740b..0ac92a606cea 100644
--- a/drivers/net/wireless/ath/ath12k/pci.c
+++ b/drivers/net/wireless/ath/ath12k/pci.c
@@ -290,10 +290,10 @@ static void ath12k_pci_enable_ltssm(struct ath12k_base *ab)
 
 	ath12k_dbg(ab, ATH12K_DBG_PCI, "pci ltssm 0x%x\n", val);
 
-	val = ath12k_pci_read32(ab, GCC_GCC_PCIE_HOT_RST);
+	val = ath12k_pci_read32(ab, GCC_GCC_PCIE_HOT_RST(ab));
 	val |= GCC_GCC_PCIE_HOT_RST_VAL;
-	ath12k_pci_write32(ab, GCC_GCC_PCIE_HOT_RST, val);
-	val = ath12k_pci_read32(ab, GCC_GCC_PCIE_HOT_RST);
+	ath12k_pci_write32(ab, GCC_GCC_PCIE_HOT_RST(ab), val);
+	val = ath12k_pci_read32(ab, GCC_GCC_PCIE_HOT_RST(ab));
 
 	ath12k_dbg(ab, ATH12K_DBG_PCI, "pci pcie_hot_rst 0x%x\n", val);
 
@@ -481,8 +481,11 @@ static void __ath12k_pci_ext_irq_disable(struct ath12k_base *ab)
 
 		ath12k_pci_ext_grp_disable(irq_grp);
 
-		napi_synchronize(&irq_grp->napi);
-		napi_disable(&irq_grp->napi);
+		if (irq_grp->napi_enabled) {
+			napi_synchronize(&irq_grp->napi);
+			napi_disable(&irq_grp->napi);
+			irq_grp->napi_enabled = false;
+		}
 	}
 }
 
@@ -1112,7 +1115,11 @@ void ath12k_pci_ext_irq_enable(struct ath12k_base *ab)
 	for (i = 0; i < ATH12K_EXT_IRQ_GRP_NUM_MAX; i++) {
 		struct ath12k_ext_irq_grp *irq_grp = &ab->ext_irq_grp[i];
 
-		napi_enable(&irq_grp->napi);
+		if (!irq_grp->napi_enabled) {
+			napi_enable(&irq_grp->napi);
+			irq_grp->napi_enabled = true;
+		}
+
 		ath12k_pci_ext_grp_enable(irq_grp);
 	}
 
@@ -1294,6 +1301,9 @@ void ath12k_pci_power_down(struct ath12k_base *ab, bool is_suspend)
 {
 	struct ath12k_pci *ab_pci = ath12k_pci_priv(ab);
 
+	if (!test_bit(ATH12K_PCI_FLAG_INIT_DONE, &ab_pci->flags))
+		return;
+
 	/* restore aspm in case firmware bootup fails */
 	ath12k_pci_aspm_restore(ab_pci);
 
@@ -1496,6 +1506,8 @@ static int ath12k_pci_probe(struct pci_dev *pdev,
 	return 0;
 
 err_free_irq:
+	/* __free_irq() expects the caller to have cleared the affinity hint */
+	ath12k_pci_set_irq_affinity_hint(ab_pci, NULL);
 	ath12k_pci_free_irq(ab);
 
 err_ce_free:
@@ -1507,12 +1519,12 @@ err_hal_srng_deinit:
 err_mhi_unregister:
 	ath12k_mhi_unregister(ab_pci);
 
-err_pci_msi_free:
-	ath12k_pci_msi_free(ab_pci);
-
 err_irq_affinity_cleanup:
 	ath12k_pci_set_irq_affinity_hint(ab_pci, NULL);
 
+err_pci_msi_free:
+	ath12k_pci_msi_free(ab_pci);
+
 err_pci_free_region:
 	ath12k_pci_free_region(ab_pci);
 
@@ -1541,6 +1553,7 @@ static void ath12k_pci_remove(struct pci_dev *pdev)
 	ath12k_core_deinit(ab);
 
 qmi_fail:
+	ath12k_fw_unmap(ab);
 	ath12k_mhi_unregister(ab_pci);
 
 	ath12k_pci_free_irq(ab);
diff --git a/drivers/net/wireless/ath/ath12k/pci.h b/drivers/net/wireless/ath/ath12k/pci.h
index 31584a7ad80e..9321674eef8b 100644
--- a/drivers/net/wireless/ath/ath12k/pci.h
+++ b/drivers/net/wireless/ath/ath12k/pci.h
@@ -28,7 +28,9 @@
 #define PCIE_PCIE_PARF_LTSSM			0x1e081b0
 #define PARM_LTSSM_VALUE			0x111
 
-#define GCC_GCC_PCIE_HOT_RST			0x1e38338
+#define GCC_GCC_PCIE_HOT_RST(ab) \
+	((ab)->hw_params->regs->gcc_gcc_pcie_hot_rst)
+
 #define GCC_GCC_PCIE_HOT_RST_VAL		0x10
 
 #define PCIE_PCIE_INT_ALL_CLEAR			0x1e08228
diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c
index 2cd3ff9b0164..5c5fc2b7642f 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.c
+++ b/drivers/net/wireless/ath/ath12k/wmi.c
@@ -980,14 +980,24 @@ int ath12k_wmi_vdev_down(struct ath12k *ar, u8 vdev_id)
 static void ath12k_wmi_put_wmi_channel(struct ath12k_wmi_channel_params *chan,
 				       struct wmi_vdev_start_req_arg *arg)
 {
+	u32 center_freq1 = arg->band_center_freq1;
+
 	memset(chan, 0, sizeof(*chan));
 
 	chan->mhz = cpu_to_le32(arg->freq);
-	chan->band_center_freq1 = cpu_to_le32(arg->band_center_freq1);
-	if (arg->mode == MODE_11AC_VHT80_80)
+	chan->band_center_freq1 = cpu_to_le32(center_freq1);
+	if (arg->mode == MODE_11BE_EHT160) {
+		if (arg->freq > center_freq1)
+			chan->band_center_freq1 = cpu_to_le32(center_freq1 + 40);
+		else
+			chan->band_center_freq1 = cpu_to_le32(center_freq1 - 40);
+
+		chan->band_center_freq2 = cpu_to_le32(center_freq1);
+	} else if (arg->mode == MODE_11BE_EHT80_80) {
 		chan->band_center_freq2 = cpu_to_le32(arg->band_center_freq2);
-	else
+	} else {
 		chan->band_center_freq2 = 0;
+	}
 
 	chan->info |= le32_encode_bits(arg->mode, WMI_CHAN_INFO_MODE);
 	if (arg->passive)
@@ -2157,7 +2167,7 @@ int ath12k_wmi_send_peer_assoc_cmd(struct ath12k *ar,
 
 	for (i = 0; i < arg->peer_eht_mcs_count; i++) {
 		eht_mcs = ptr;
-		eht_mcs->tlv_header = ath12k_wmi_tlv_cmd_hdr(WMI_TAG_HE_RATE_SET,
+		eht_mcs->tlv_header = ath12k_wmi_tlv_cmd_hdr(WMI_TAG_EHT_RATE_SET,
 							     sizeof(*eht_mcs));
 
 		eht_mcs->rx_mcs_set = cpu_to_le32(arg->peer_eht_rx_mcs_set[i]);
@@ -2206,8 +2216,8 @@ void ath12k_wmi_start_scan_init(struct ath12k *ar,
 	arg->dwell_time_active = 50;
 	arg->dwell_time_active_2g = 0;
 	arg->dwell_time_passive = 150;
-	arg->dwell_time_active_6g = 40;
-	arg->dwell_time_passive_6g = 30;
+	arg->dwell_time_active_6g = 70;
+	arg->dwell_time_passive_6g = 70;
 	arg->min_rest_time = 50;
 	arg->max_rest_time = 500;
 	arg->repeat_probe_time = 0;
@@ -4372,6 +4382,7 @@ static int ath12k_service_ready_ext_event(struct ath12k_base *ab,
 	return 0;
 
 err:
+	kfree(svc_rdy_ext.mac_phy_caps);
 	ath12k_wmi_free_dbring_caps(ab);
 	return ret;
 }
@@ -4681,6 +4692,22 @@ static struct ath12k_reg_rule
 	return reg_rule_ptr;
 }
 
+static u8 ath12k_wmi_ignore_num_extra_rules(struct ath12k_wmi_reg_rule_ext_params *rule,
+					    u32 num_reg_rules)
+{
+	u8 num_invalid_5ghz_rules = 0;
+	u32 count, start_freq;
+
+	for (count = 0; count < num_reg_rules; count++) {
+		start_freq = le32_get_bits(rule[count].freq_info, REG_RULE_START_FREQ);
+
+		if (start_freq >= ATH12K_MIN_6G_FREQ)
+			num_invalid_5ghz_rules++;
+	}
+
+	return num_invalid_5ghz_rules;
+}
+
 static int ath12k_pull_reg_chan_list_ext_update_ev(struct ath12k_base *ab,
 						   struct sk_buff *skb,
 						   struct ath12k_reg_info *reg_info)
@@ -4691,6 +4718,7 @@ static int ath12k_pull_reg_chan_list_ext_update_ev(struct ath12k_base *ab,
 	u32 num_2g_reg_rules, num_5g_reg_rules;
 	u32 num_6g_reg_rules_ap[WMI_REG_CURRENT_MAX_AP_TYPE];
 	u32 num_6g_reg_rules_cl[WMI_REG_CURRENT_MAX_AP_TYPE][WMI_REG_MAX_CLIENT_TYPE];
+	u8 num_invalid_5ghz_ext_rules;
 	u32 total_reg_rules = 0;
 	int ret, i, j;
 
@@ -4784,20 +4812,6 @@ static int ath12k_pull_reg_chan_list_ext_update_ev(struct ath12k_base *ab,
 
 	memcpy(reg_info->alpha2, &ev->alpha2, REG_ALPHA2_LEN);
 
-	/* FIXME: Currently FW includes 6G reg rule also in 5G rule
-	 * list for country US.
-	 * Having same 6G reg rule in 5G and 6G rules list causes
-	 * intersect check to be true, and same rules will be shown
-	 * multiple times in iw cmd. So added hack below to avoid
-	 * parsing 6G rule from 5G reg rule list, and this can be
-	 * removed later, after FW updates to remove 6G reg rule
-	 * from 5G rules list.
-	 */
-	if (memcmp(reg_info->alpha2, "US", 2) == 0) {
-		reg_info->num_5g_reg_rules = REG_US_5G_NUM_REG_RULES;
-		num_5g_reg_rules = reg_info->num_5g_reg_rules;
-	}
-
 	reg_info->dfs_region = le32_to_cpu(ev->dfs_region);
 	reg_info->phybitmap = le32_to_cpu(ev->phybitmap);
 	reg_info->num_phy = le32_to_cpu(ev->num_phy);
@@ -4900,8 +4914,29 @@ static int ath12k_pull_reg_chan_list_ext_update_ev(struct ath12k_base *ab,
 		}
 	}
 
+	ext_wmi_reg_rule += num_2g_reg_rules;
+
+	/* Firmware might include 6 GHz reg rule in 5 GHz rule list
+	 * for few countries along with separate 6 GHz rule.
+	 * Having same 6 GHz reg rule in 5 GHz and 6 GHz rules list
+	 * causes intersect check to be true, and same rules will be
+	 * shown multiple times in iw cmd.
+	 * Hence, avoid parsing 6 GHz rule from 5 GHz reg rule list
+	 */
+	num_invalid_5ghz_ext_rules = ath12k_wmi_ignore_num_extra_rules(ext_wmi_reg_rule,
+								       num_5g_reg_rules);
+
+	if (num_invalid_5ghz_ext_rules) {
+		ath12k_dbg(ab, ATH12K_DBG_WMI,
+			   "CC: %s 5 GHz reg rules number %d from fw, %d number of invalid 5 GHz rules",
+			   reg_info->alpha2, reg_info->num_5g_reg_rules,
+			   num_invalid_5ghz_ext_rules);
+
+		num_5g_reg_rules = num_5g_reg_rules - num_invalid_5ghz_ext_rules;
+		reg_info->num_5g_reg_rules = num_5g_reg_rules;
+	}
+
 	if (num_5g_reg_rules) {
-		ext_wmi_reg_rule += num_2g_reg_rules;
 		reg_info->reg_rules_5g_ptr =
 			create_ext_reg_rules_from_wmi(num_5g_reg_rules,
 						      ext_wmi_reg_rule);
@@ -4913,7 +4948,12 @@ static int ath12k_pull_reg_chan_list_ext_update_ev(struct ath12k_base *ab,
 		}
 	}
 
-	ext_wmi_reg_rule += num_5g_reg_rules;
+	/* We have adjusted the number of 5 GHz reg rules above. But still those
+	 * many rules needs to be adjusted in ext_wmi_reg_rule.
+	 *
+	 * NOTE: num_invalid_5ghz_ext_rules will be 0 for rest other cases.
+	 */
+	ext_wmi_reg_rule += (num_5g_reg_rules + num_invalid_5ghz_ext_rules);
 
 	for (i = 0; i < WMI_REG_CURRENT_MAX_AP_TYPE; i++) {
 		reg_info->reg_rules_6g_ap_ptr[i] =
@@ -5189,6 +5229,11 @@ static int wmi_process_mgmt_tx_comp(struct ath12k *ar, u32 desc_id,
 	dma_unmap_single(ar->ab->dev, skb_cb->paddr, msdu->len, DMA_TO_DEVICE);
 
 	info = IEEE80211_SKB_CB(msdu);
+	memset(&info->status, 0, sizeof(info->status));
+
+	/* skip tx rate update from ieee80211_status*/
+	info->status.rates[0].idx = -1;
+
 	if ((!(info->flags & IEEE80211_TX_CTL_NO_ACK)) && !status)
 		info->flags |= IEEE80211_TX_STAT_ACK;
 
@@ -5754,7 +5799,7 @@ static int ath12k_reg_chan_list_event(struct ath12k_base *ab, struct sk_buff *sk
 		goto fallback;
 	}
 
-	spin_lock(&ab->base_lock);
+	spin_lock_bh(&ab->base_lock);
 	if (test_bit(ATH12K_FLAG_REGISTERED, &ab->dev_flags)) {
 		/* Once mac is registered, ar is valid and all CC events from
 		 * fw is considered to be received due to user requests
@@ -5778,7 +5823,7 @@ static int ath12k_reg_chan_list_event(struct ath12k_base *ab, struct sk_buff *sk
 		ab->default_regd[pdev_idx] = regd;
 	}
 	ab->dfs_region = reg_info->dfs_region;
-	spin_unlock(&ab->base_lock);
+	spin_unlock_bh(&ab->base_lock);
 
 	goto mem_free;
 
@@ -6549,7 +6594,7 @@ static int ath12k_wmi_tlv_services_parser(struct ath12k_base *ab,
 					  void *data)
 {
 	const struct wmi_service_available_event *ev;
-	u32 *wmi_ext2_service_bitmap;
+	__le32 *wmi_ext2_service_bitmap;
 	int i, j;
 	u16 expected_len;
 
@@ -6581,12 +6626,12 @@ static int ath12k_wmi_tlv_services_parser(struct ath12k_base *ab,
 			   ev->wmi_service_segment_bitmap[3]);
 		break;
 	case WMI_TAG_ARRAY_UINT32:
-		wmi_ext2_service_bitmap = (u32 *)ptr;
+		wmi_ext2_service_bitmap = (__le32 *)ptr;
 		for (i = 0, j = WMI_MAX_EXT_SERVICE;
 		     i < WMI_SERVICE_SEGMENT_BM_SIZE32 && j < WMI_MAX_EXT2_SERVICE;
 		     i++) {
 			do {
-				if (wmi_ext2_service_bitmap[i] &
+				if (__le32_to_cpu(wmi_ext2_service_bitmap[i]) &
 				    BIT(j % WMI_AVAIL_SERVICE_BITS_IN_SIZE32))
 					set_bit(j, ab->wmi_ab.svc_map);
 			} while (++j % WMI_AVAIL_SERVICE_BITS_IN_SIZE32);
@@ -6594,8 +6639,10 @@ static int ath12k_wmi_tlv_services_parser(struct ath12k_base *ab,
 
 		ath12k_dbg(ab, ATH12K_DBG_WMI,
 			   "wmi_ext2_service_bitmap 0x%04x 0x%04x 0x%04x 0x%04x",
-			   wmi_ext2_service_bitmap[0], wmi_ext2_service_bitmap[1],
-			   wmi_ext2_service_bitmap[2], wmi_ext2_service_bitmap[3]);
+			   __le32_to_cpu(wmi_ext2_service_bitmap[0]),
+			   __le32_to_cpu(wmi_ext2_service_bitmap[1]),
+			   __le32_to_cpu(wmi_ext2_service_bitmap[2]),
+			   __le32_to_cpu(wmi_ext2_service_bitmap[3]));
 		break;
 	}
 	return 0;
diff --git a/drivers/net/wireless/ath/ath12k/wmi.h b/drivers/net/wireless/ath/ath12k/wmi.h
index 6a913f9b8315..b495cdea7111 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.h
+++ b/drivers/net/wireless/ath/ath12k/wmi.h
@@ -3943,7 +3943,6 @@ struct ath12k_wmi_eht_rate_set_params {
 #define MAX_REG_RULES 10
 #define REG_ALPHA2_LEN 2
 #define MAX_6G_REG_RULES 5
-#define REG_US_5G_NUM_REG_RULES 4
 
 enum wmi_start_event_param {
 	WMI_VDEV_START_RESP_EVENT = 0,
diff --git a/drivers/net/wireless/ath/ath6kl/bmi.c b/drivers/net/wireless/ath/ath6kl/bmi.c
index af98e871199d..5a9e93fd1ef4 100644
--- a/drivers/net/wireless/ath/ath6kl/bmi.c
+++ b/drivers/net/wireless/ath/ath6kl/bmi.c
@@ -87,7 +87,9 @@ int ath6kl_bmi_get_target_info(struct ath6kl *ar,
 		 * We need to do some backwards compatibility to make this work.
 		 */
 		if (le32_to_cpu(targ_info->byte_count) != sizeof(*targ_info)) {
-			WARN_ON(1);
+			ath6kl_err("mismatched byte count %d vs. expected %zd\n",
+				   le32_to_cpu(targ_info->byte_count),
+				   sizeof(*targ_info));
 			return -EINVAL;
 		}
 
diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_beacon.c b/drivers/net/wireless/ath/ath9k/htc_drv_beacon.c
index 547634f82183..81fa7cbad892 100644
--- a/drivers/net/wireless/ath/ath9k/htc_drv_beacon.c
+++ b/drivers/net/wireless/ath/ath9k/htc_drv_beacon.c
@@ -290,6 +290,9 @@ void ath9k_htc_swba(struct ath9k_htc_priv *priv,
 	struct ath_common *common = ath9k_hw_common(priv->ah);
 	int slot;
 
+	if (!priv->cur_beacon_conf.enable_beacon)
+		return;
+
 	if (swba->beacon_pending != 0) {
 		priv->beacon.bmisscnt++;
 		if (priv->beacon.bmisscnt > BSTUCK_THRESHOLD) {
diff --git a/drivers/net/wireless/ath/ath9k/init.c b/drivers/net/wireless/ath/ath9k/init.c
index 7fad7e75af6a..619bebd389bd 100644
--- a/drivers/net/wireless/ath/ath9k/init.c
+++ b/drivers/net/wireless/ath/ath9k/init.c
@@ -691,7 +691,9 @@ static int ath9k_of_init(struct ath_softc *sc)
 		ah->ah_flags |= AH_NO_EEP_SWAP;
 	}
 
-	of_get_mac_address(np, common->macaddr);
+	ret = of_get_mac_address(np, common->macaddr);
+	if (ret == -EPROBE_DEFER)
+		return ret;
 
 	return 0;
 }
diff --git a/drivers/net/wireless/ath/carl9170/usb.c b/drivers/net/wireless/ath/carl9170/usb.c
index a3e03580cd9f..564ca6a61985 100644
--- a/drivers/net/wireless/ath/carl9170/usb.c
+++ b/drivers/net/wireless/ath/carl9170/usb.c
@@ -438,14 +438,21 @@ static void carl9170_usb_rx_complete(struct urb *urb)
 
 		if (atomic_read(&ar->rx_anch_urbs) == 0) {
 			/*
-			 * The system is too slow to cope with
-			 * the enormous workload. We have simply
-			 * run out of active rx urbs and this
-			 * unfortunately leads to an unpredictable
-			 * device.
+			 * At this point, either the system is too slow to
+			 * cope with the enormous workload (so we have simply
+			 * run out of active rx urbs and this unfortunately
+			 * leads to an unpredictable device), or the device
+			 * is not fully functional after an unsuccessful
+			 * firmware loading attempts (so it doesn't pass
+			 * ieee80211_register_hw() and there is no internal
+			 * workqueue at all).
 			 */
 
-			ieee80211_queue_work(ar->hw, &ar->ping_work);
+			if (ar->registered)
+				ieee80211_queue_work(ar->hw, &ar->ping_work);
+			else
+				pr_warn_once("device %s is not registered\n",
+					     dev_name(&ar->udev->dev));
 		}
 	} else {
 		/*
diff --git a/drivers/net/wireless/ath/wcn36xx/main.c b/drivers/net/wireless/ath/wcn36xx/main.c
index 408776562a7e..cd36cab6db75 100644
--- a/drivers/net/wireless/ath/wcn36xx/main.c
+++ b/drivers/net/wireless/ath/wcn36xx/main.c
@@ -1590,7 +1590,10 @@ static int wcn36xx_probe(struct platform_device *pdev)
 	}
 
 	n_channels = wcn_band_2ghz.n_channels + wcn_band_5ghz.n_channels;
-	wcn->chan_survey = devm_kmalloc(wcn->dev, n_channels, GFP_KERNEL);
+	wcn->chan_survey = devm_kcalloc(wcn->dev,
+					n_channels,
+					sizeof(struct wcn36xx_chan_survey),
+					GFP_KERNEL);
 	if (!wcn->chan_survey) {
 		ret = -ENOMEM;
 		goto out_wq;
diff --git a/drivers/net/wireless/atmel/at76c50x-usb.c b/drivers/net/wireless/atmel/at76c50x-usb.c
index 504e05ea30f2..97ea7ab0f491 100644
--- a/drivers/net/wireless/atmel/at76c50x-usb.c
+++ b/drivers/net/wireless/atmel/at76c50x-usb.c
@@ -2552,7 +2552,7 @@ static void at76_disconnect(struct usb_interface *interface)
 
 	wiphy_info(priv->hw->wiphy, "disconnecting\n");
 	at76_delete_device(priv);
-	usb_put_dev(priv->udev);
+	usb_put_dev(interface_to_usbdev(interface));
 	dev_info(&interface->dev, "disconnected\n");
 }
 
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c
index 8a1e33764244..cfdd92564060 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c
@@ -1167,6 +1167,7 @@ static int brcmf_ops_sdio_suspend(struct device *dev)
 	struct brcmf_bus *bus_if;
 	struct brcmf_sdio_dev *sdiodev;
 	mmc_pm_flag_t sdio_flags;
+	bool cap_power_off;
 	int ret = 0;
 
 	func = container_of(dev, struct sdio_func, dev);
@@ -1174,19 +1175,23 @@ static int brcmf_ops_sdio_suspend(struct device *dev)
 	if (func->num != 1)
 		return 0;
 
+	cap_power_off = !!(func->card->host->caps & MMC_CAP_POWER_OFF_CARD);
 
 	bus_if = dev_get_drvdata(dev);
 	sdiodev = bus_if->bus_priv.sdio;
 
-	if (sdiodev->wowl_enabled) {
+	if (sdiodev->wowl_enabled || !cap_power_off) {
 		brcmf_sdiod_freezer_on(sdiodev);
 		brcmf_sdio_wd_timer(sdiodev->bus, 0);
 
 		sdio_flags = MMC_PM_KEEP_POWER;
-		if (sdiodev->settings->bus.sdio.oob_irq_supported)
-			enable_irq_wake(sdiodev->settings->bus.sdio.oob_irq_nr);
-		else
-			sdio_flags |= MMC_PM_WAKE_SDIO_IRQ;
+
+		if (sdiodev->wowl_enabled) {
+			if (sdiodev->settings->bus.sdio.oob_irq_supported)
+				enable_irq_wake(sdiodev->settings->bus.sdio.oob_irq_nr);
+			else
+				sdio_flags |= MMC_PM_WAKE_SDIO_IRQ;
+		}
 
 		if (sdio_set_host_pm_flags(sdiodev->func1, sdio_flags))
 			brcmf_err("Failed to set pm_flags %x\n", sdio_flags);
@@ -1208,18 +1213,19 @@ static int brcmf_ops_sdio_resume(struct device *dev)
 	struct brcmf_sdio_dev *sdiodev = bus_if->bus_priv.sdio;
 	struct sdio_func *func = container_of(dev, struct sdio_func, dev);
 	int ret = 0;
+	bool cap_power_off = !!(func->card->host->caps & MMC_CAP_POWER_OFF_CARD);
 
 	brcmf_dbg(SDIO, "Enter: F%d\n", func->num);
 	if (func->num != 2)
 		return 0;
 
-	if (!sdiodev->wowl_enabled) {
+	if (!sdiodev->wowl_enabled && cap_power_off) {
 		/* bus was powered off and device removed, probe again */
 		ret = brcmf_sdiod_probe(sdiodev);
 		if (ret)
 			brcmf_err("Failed to probe device on resume\n");
 	} else {
-		if (sdiodev->settings->bus.sdio.oob_irq_supported)
+		if (sdiodev->wowl_enabled && sdiodev->settings->bus.sdio.oob_irq_supported)
 			disable_irq_wake(sdiodev->settings->bus.sdio.oob_irq_nr);
 
 		brcmf_sdiod_freezer_off(sdiodev);
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
index 349aa3439502..708a4e2ad839 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
@@ -1541,10 +1541,6 @@ brcmf_cfg80211_scan(struct wiphy *wiphy, struct cfg80211_scan_request *request)
 		return -EAGAIN;
 	}
 
-	/* If scan req comes for p2p0, send it over primary I/F */
-	if (vif == cfg->p2p.bss_idx[P2PAPI_BSSCFG_DEVICE].vif)
-		vif = cfg->p2p.bss_idx[P2PAPI_BSSCFG_PRIMARY].vif;
-
 	brcmf_dbg(SCAN, "START ESCAN\n");
 
 	cfg->scan_request = request;
@@ -1560,6 +1556,10 @@ brcmf_cfg80211_scan(struct wiphy *wiphy, struct cfg80211_scan_request *request)
 	if (err)
 		goto scan_out;
 
+	/* If scan req comes for p2p0, send it over primary I/F */
+	if (vif == cfg->p2p.bss_idx[P2PAPI_BSSCFG_DEVICE].vif)
+		vif = cfg->p2p.bss_idx[P2PAPI_BSSCFG_PRIMARY].vif;
+
 	err = brcmf_do_escan(vif->ifp, request);
 	if (err)
 		goto scan_out;
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c
index da72fd2d541f..20ab9b1eea28 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c
@@ -540,6 +540,11 @@ void brcmf_txfinalize(struct brcmf_if *ifp, struct sk_buff *txp, bool success)
 	struct ethhdr *eh;
 	u16 type;
 
+	if (!ifp) {
+		brcmu_pkt_buf_free_skb(txp);
+		return;
+	}
+
 	eh = (struct ethhdr *)(txp->data);
 	type = ntohs(eh->h_proto);
 
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil.h
index 31e080e4da66..ab3d6cfcb02b 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil.h
@@ -6,6 +6,8 @@
 #ifndef _fwil_h_
 #define _fwil_h_
 
+#include "debug.h"
+
 /*******************************************************************************
  * Dongle command codes that are interpreted by firmware
  ******************************************************************************/
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/of.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/of.c
index af930e34c21f..22c064848124 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/of.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/of.c
@@ -97,13 +97,13 @@ void brcmf_of_probe(struct device *dev, enum brcmf_bus_type bus_type,
 	/* Set board-type to the first string of the machine compatible prop */
 	root = of_find_node_by_path("/");
 	if (root && err) {
-		char *board_type;
+		char *board_type = NULL;
 		const char *tmp;
 
-		of_property_read_string_index(root, "compatible", 0, &tmp);
-
 		/* get rid of '/' in the compatible string to be able to find the FW */
-		board_type = devm_kstrdup(dev, tmp, GFP_KERNEL);
+		if (!of_property_read_string_index(root, "compatible", 0, &tmp))
+			board_type = devm_kstrdup(dev, tmp, GFP_KERNEL);
+
 		if (!board_type) {
 			of_node_put(root);
 			return;
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c
index 8afbf529c745..0364b81f6e91 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c
@@ -896,14 +896,16 @@ brcmf_usb_dl_writeimage(struct brcmf_usbdev_info *devinfo, u8 *fw, int fwlen)
 	}
 
 	/* 1) Prepare USB boot loader for runtime image */
-	brcmf_usb_dl_cmd(devinfo, DL_START, &state, sizeof(state));
+	err = brcmf_usb_dl_cmd(devinfo, DL_START, &state, sizeof(state));
+	if (err)
+		goto fail;
 
 	rdlstate = le32_to_cpu(state.state);
 	rdlbytes = le32_to_cpu(state.bytes);
 
 	/* 2) Check we are in the Waiting state */
 	if (rdlstate != DL_WAITING) {
-		brcmf_err("Failed to DL_START\n");
+		brcmf_err("Invalid DL state: %u\n", rdlstate);
 		err = -EINVAL;
 		goto fail;
 	}
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_n.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_n.c
index d69879e1bd87..d362c4337616 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_n.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_n.c
@@ -23423,6 +23423,9 @@ wlc_phy_iqcal_gainparams_nphy(struct brcms_phy *pi, u16 core_no,
 				break;
 		}
 
+		if (WARN_ON(k == NPHY_IQCAL_NUMGAINS))
+			return;
+
 		params->txgm = tbl_iqcal_gainparams_nphy[band_idx][k][1];
 		params->pga = tbl_iqcal_gainparams_nphy[band_idx][k][2];
 		params->pad = tbl_iqcal_gainparams_nphy[band_idx][k][3];
diff --git a/drivers/net/wireless/intel/iwlegacy/4965-mac.c b/drivers/net/wireless/intel/iwlegacy/4965-mac.c
index 05c4af41bdb9..a94cf27ffe4b 100644
--- a/drivers/net/wireless/intel/iwlegacy/4965-mac.c
+++ b/drivers/net/wireless/intel/iwlegacy/4965-mac.c
@@ -1575,8 +1575,11 @@ il4965_tx_cmd_build_rate(struct il_priv *il,
 	    || rate_idx > RATE_COUNT_LEGACY)
 		rate_idx = rate_lowest_index(&il->bands[info->band], sta);
 	/* For 5 GHZ band, remap mac80211 rate indices into driver indices */
-	if (info->band == NL80211_BAND_5GHZ)
+	if (info->band == NL80211_BAND_5GHZ) {
 		rate_idx += IL_FIRST_OFDM_RATE;
+		if (rate_idx > IL_LAST_OFDM_RATE)
+			rate_idx = IL_LAST_OFDM_RATE;
+	}
 	/* Get PLCP rate for tx_cmd->rate_n_flags */
 	rate_plcp = il_rates[rate_idx].plcp;
 	/* Zero out flags for this packet */
diff --git a/drivers/net/wireless/intel/iwlwifi/Makefile b/drivers/net/wireless/intel/iwlwifi/Makefile
index 64c123314245..a3052684b341 100644
--- a/drivers/net/wireless/intel/iwlwifi/Makefile
+++ b/drivers/net/wireless/intel/iwlwifi/Makefile
@@ -11,7 +11,7 @@ iwlwifi-objs		+= pcie/ctxt-info.o pcie/ctxt-info-gen3.o
 iwlwifi-objs		+= pcie/trans-gen2.o pcie/tx-gen2.o
 iwlwifi-$(CONFIG_IWLDVM) += cfg/1000.o cfg/2000.o cfg/5000.o cfg/6000.o
 iwlwifi-$(CONFIG_IWLMVM) += cfg/7000.o cfg/8000.o cfg/9000.o cfg/22000.o
-iwlwifi-$(CONFIG_IWLMVM) += cfg/ax210.o cfg/bz.o cfg/sc.o
+iwlwifi-$(CONFIG_IWLMVM) += cfg/ax210.o cfg/bz.o cfg/sc.o cfg/dr.o
 iwlwifi-objs		+= iwl-dbg-tlv.o
 iwlwifi-objs		+= iwl-trans.o
 
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/22000.c b/drivers/net/wireless/intel/iwlwifi/cfg/22000.c
index 2e2fcb3807ef..10d647fbc971 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/22000.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/22000.c
@@ -44,6 +44,8 @@
 	IWL_QU_C_HR_B_FW_PRE "-" __stringify(api) ".ucode"
 #define IWL_QU_B_JF_B_MODULE_FIRMWARE(api) \
 	IWL_QU_B_JF_B_FW_PRE "-" __stringify(api) ".ucode"
+#define IWL_QU_C_JF_B_MODULE_FIRMWARE(api) \
+	IWL_QU_C_JF_B_FW_PRE "-" __stringify(api) ".ucode"
 #define IWL_CC_A_MODULE_FIRMWARE(api)			\
 	IWL_CC_A_FW_PRE "-" __stringify(api) ".ucode"
 
@@ -423,6 +425,7 @@ const struct iwl_cfg iwl_cfg_quz_a0_hr_b0 = {
 MODULE_FIRMWARE(IWL_QU_B_HR_B_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
 MODULE_FIRMWARE(IWL_QU_C_HR_B_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
 MODULE_FIRMWARE(IWL_QU_B_JF_B_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
+MODULE_FIRMWARE(IWL_QU_C_JF_B_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
 MODULE_FIRMWARE(IWL_QUZ_A_HR_B_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
 MODULE_FIRMWARE(IWL_QUZ_A_JF_B_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
 MODULE_FIRMWARE(IWL_CC_A_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/dr.c b/drivers/net/wireless/intel/iwlwifi/cfg/dr.c
new file mode 100644
index 000000000000..d3542af0f625
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/dr.c
@@ -0,0 +1,165 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/*
+ * Copyright (C) 2024 Intel Corporation
+ */
+#include <linux/module.h>
+#include <linux/stringify.h>
+#include "iwl-config.h"
+#include "iwl-prph.h"
+#include "fw/api/txq.h"
+
+/* Highest firmware API version supported */
+#define IWL_DR_UCODE_API_MAX	96
+
+/* Lowest firmware API version supported */
+#define IWL_DR_UCODE_API_MIN	96
+
+/* NVM versions */
+#define IWL_DR_NVM_VERSION		0x0a1d
+
+/* Memory offsets and lengths */
+#define IWL_DR_DCCM_OFFSET		0x800000 /* LMAC1 */
+#define IWL_DR_DCCM_LEN			0x10000 /* LMAC1 */
+#define IWL_DR_DCCM2_OFFSET		0x880000
+#define IWL_DR_DCCM2_LEN		0x8000
+#define IWL_DR_SMEM_OFFSET		0x400000
+#define IWL_DR_SMEM_LEN			0xD0000
+
+#define IWL_DR_A_PE_A_FW_PRE		"iwlwifi-dr-a0-pe-a0"
+#define IWL_BR_A_PET_A_FW_PRE		"iwlwifi-br-a0-petc-a0"
+#define IWL_BR_A_PE_A_FW_PRE		"iwlwifi-br-a0-pe-a0"
+
+#define IWL_DR_A_PE_A_FW_MODULE_FIRMWARE(api) \
+	IWL_DR_A_PE_A_FW_PRE "-" __stringify(api) ".ucode"
+#define IWL_BR_A_PET_A_FW_MODULE_FIRMWARE(api) \
+	IWL_BR_A_PET_A_FW_PRE "-" __stringify(api) ".ucode"
+#define IWL_BR_A_PE_A_FW_MODULE_FIRMWARE(api) \
+	IWL_BR_A_PE_A_FW_PRE "-" __stringify(api) ".ucode"
+
+static const struct iwl_base_params iwl_dr_base_params = {
+	.eeprom_size = OTP_LOW_IMAGE_SIZE_32K,
+	.num_of_queues = 512,
+	.max_tfd_queue_size = 65536,
+	.shadow_ram_support = true,
+	.led_compensation = 57,
+	.wd_timeout = IWL_LONG_WD_TIMEOUT,
+	.max_event_log_size = 512,
+	.shadow_reg_enable = true,
+	.pcie_l1_allowed = true,
+};
+
+#define IWL_DEVICE_DR_COMMON						\
+	.ucode_api_max = IWL_DR_UCODE_API_MAX,			\
+	.ucode_api_min = IWL_DR_UCODE_API_MIN,			\
+	.led_mode = IWL_LED_RF_STATE,					\
+	.nvm_hw_section_num = 10,					\
+	.non_shared_ant = ANT_B,					\
+	.dccm_offset = IWL_DR_DCCM_OFFSET,				\
+	.dccm_len = IWL_DR_DCCM_LEN,					\
+	.dccm2_offset = IWL_DR_DCCM2_OFFSET,				\
+	.dccm2_len = IWL_DR_DCCM2_LEN,				\
+	.smem_offset = IWL_DR_SMEM_OFFSET,				\
+	.smem_len = IWL_DR_SMEM_LEN,					\
+	.apmg_not_supported = true,					\
+	.trans.mq_rx_supported = true,					\
+	.vht_mu_mimo_supported = true,					\
+	.mac_addr_from_csr = 0x30,					\
+	.nvm_ver = IWL_DR_NVM_VERSION,				\
+	.trans.rf_id = true,						\
+	.trans.gen2 = true,						\
+	.nvm_type = IWL_NVM_EXT,					\
+	.dbgc_supported = true,						\
+	.min_umac_error_event_table = 0xD0000,				\
+	.d3_debug_data_base_addr = 0x401000,				\
+	.d3_debug_data_length = 60 * 1024,				\
+	.mon_smem_regs = {						\
+		.write_ptr = {						\
+			.addr = LDBG_M2S_BUF_WPTR,			\
+			.mask = LDBG_M2S_BUF_WPTR_VAL_MSK,		\
+	},								\
+		.cycle_cnt = {						\
+			.addr = LDBG_M2S_BUF_WRAP_CNT,			\
+			.mask = LDBG_M2S_BUF_WRAP_CNT_VAL_MSK,		\
+		},							\
+	},								\
+	.trans.umac_prph_offset = 0x300000,				\
+	.trans.device_family = IWL_DEVICE_FAMILY_DR,			\
+	.trans.base_params = &iwl_dr_base_params,			\
+	.min_txq_size = 128,						\
+	.gp2_reg_addr = 0xd02c68,					\
+	.min_ba_txq_size = IWL_DEFAULT_QUEUE_SIZE_EHT,			\
+	.mon_dram_regs = {						\
+		.write_ptr = {						\
+			.addr = DBGC_CUR_DBGBUF_STATUS,			\
+			.mask = DBGC_CUR_DBGBUF_STATUS_OFFSET_MSK,	\
+		},							\
+		.cycle_cnt = {						\
+			.addr = DBGC_DBGBUF_WRAP_AROUND,		\
+			.mask = 0xffffffff,				\
+		},							\
+		.cur_frag = {						\
+			.addr = DBGC_CUR_DBGBUF_STATUS,			\
+			.mask = DBGC_CUR_DBGBUF_STATUS_IDX_MSK,		\
+		},							\
+	},								\
+	.mon_dbgi_regs = {						\
+		.write_ptr = {						\
+			.addr = DBGI_SRAM_FIFO_POINTERS,		\
+			.mask = DBGI_SRAM_FIFO_POINTERS_WR_PTR_MSK,	\
+		},							\
+	}
+
+#define IWL_DEVICE_DR							\
+	IWL_DEVICE_DR_COMMON,						\
+	.uhb_supported = true,						\
+	.features = IWL_TX_CSUM_NETIF_FLAGS | NETIF_F_RXCSUM,		\
+	.num_rbds = IWL_NUM_RBDS_DR_EHT,				\
+	.ht_params = &iwl_22000_ht_params
+
+/*
+ * This size was picked according to 8 MSDUs inside 512 A-MSDUs in an
+ * A-MPDU, with additional overhead to account for processing time.
+ */
+#define IWL_NUM_RBDS_DR_EHT		(512 * 16)
+
+const struct iwl_cfg_trans_params iwl_dr_trans_cfg = {
+	.device_family = IWL_DEVICE_FAMILY_DR,
+	.base_params = &iwl_dr_base_params,
+	.mq_rx_supported = true,
+	.rf_id = true,
+	.gen2 = true,
+	.integrated = true,
+	.umac_prph_offset = 0x300000,
+	.xtal_latency = 12000,
+	.low_latency_xtal = true,
+	.ltr_delay = IWL_CFG_TRANS_LTR_DELAY_2500US,
+};
+
+const char iwl_dr_name[] = "Intel(R) TBD Dr device";
+
+const struct iwl_cfg iwl_cfg_dr = {
+	.fw_name_mac = "dr",
+	IWL_DEVICE_DR,
+};
+
+const struct iwl_cfg_trans_params iwl_br_trans_cfg = {
+	.device_family = IWL_DEVICE_FAMILY_DR,
+	.base_params = &iwl_dr_base_params,
+	.mq_rx_supported = true,
+	.rf_id = true,
+	.gen2 = true,
+	.umac_prph_offset = 0x300000,
+	.xtal_latency = 12000,
+	.low_latency_xtal = true,
+};
+
+const char iwl_br_name[] = "Intel(R) TBD Br device";
+
+const struct iwl_cfg iwl_cfg_br = {
+	.fw_name_mac = "br",
+	IWL_DEVICE_DR,
+};
+
+MODULE_FIRMWARE(IWL_DR_A_PE_A_FW_MODULE_FIRMWARE(IWL_DR_UCODE_API_MAX));
+MODULE_FIRMWARE(IWL_BR_A_PET_A_FW_MODULE_FIRMWARE(IWL_DR_UCODE_API_MAX));
+MODULE_FIRMWARE(IWL_BR_A_PE_A_FW_MODULE_FIRMWARE(IWL_DR_UCODE_API_MAX));
diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/main.c b/drivers/net/wireless/intel/iwlwifi/dvm/main.c
index e0b14be25b02..b8713ebd7190 100644
--- a/drivers/net/wireless/intel/iwlwifi/dvm/main.c
+++ b/drivers/net/wireless/intel/iwlwifi/dvm/main.c
@@ -1048,9 +1048,11 @@ static void iwl_bg_restart(struct work_struct *data)
  *
  *****************************************************************************/
 
-static void iwl_setup_deferred_work(struct iwl_priv *priv)
+static int iwl_setup_deferred_work(struct iwl_priv *priv)
 {
 	priv->workqueue = alloc_ordered_workqueue(DRV_NAME, 0);
+	if (!priv->workqueue)
+		return -ENOMEM;
 
 	INIT_WORK(&priv->restart, iwl_bg_restart);
 	INIT_WORK(&priv->beacon_update, iwl_bg_beacon_update);
@@ -1067,6 +1069,8 @@ static void iwl_setup_deferred_work(struct iwl_priv *priv)
 	timer_setup(&priv->statistics_periodic, iwl_bg_statistics_periodic, 0);
 
 	timer_setup(&priv->ucode_trace, iwl_bg_ucode_trace, 0);
+
+	return 0;
 }
 
 void iwl_cancel_deferred_work(struct iwl_priv *priv)
@@ -1454,7 +1458,9 @@ static struct iwl_op_mode *iwl_op_mode_dvm_start(struct iwl_trans *trans,
 	/********************
 	 * 6. Setup services
 	 ********************/
-	iwl_setup_deferred_work(priv);
+	if (iwl_setup_deferred_work(priv))
+		goto out_uninit_drv;
+
 	iwl_setup_rx_handlers(priv);
 
 	iwl_power_initialize(priv);
@@ -1492,6 +1498,7 @@ out_destroy_workqueue:
 	iwl_cancel_deferred_work(priv);
 	destroy_workqueue(priv->workqueue);
 	priv->workqueue = NULL;
+out_uninit_drv:
 	iwl_uninit_drv(priv);
 out_free_eeprom_blob:
 	kfree(priv->eeprom_blob);
diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/rs.c b/drivers/net/wireless/intel/iwlwifi/dvm/rs.c
index 8879e668ef0d..ed964103281e 100644
--- a/drivers/net/wireless/intel/iwlwifi/dvm/rs.c
+++ b/drivers/net/wireless/intel/iwlwifi/dvm/rs.c
@@ -2899,7 +2899,7 @@ static void rs_fill_link_cmd(struct iwl_priv *priv,
 		/* Repeat initial/next rate.
 		 * For legacy IWL_NUMBER_TRY == 1, this loop will not execute.
 		 * For HT IWL_HT_NUMBER_TRY == 3, this executes twice. */
-		while (repeat_rate > 0 && (index < LINK_QUAL_MAX_RETRY_NUM)) {
+		while (repeat_rate > 0 && index < (LINK_QUAL_MAX_RETRY_NUM - 1)) {
 			if (is_legacy(tbl_type.lq_type)) {
 				if (ant_toggle_cnt < NUM_TRY_BEFORE_ANT_TOGGLE)
 					ant_toggle_cnt++;
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
index 0bc32291815e..a26c5573d209 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
@@ -108,7 +108,7 @@ static int iwl_acpi_get_dsm_integer(struct device *dev, int rev, int func,
 				    size_t expected_size)
 {
 	union acpi_object *obj;
-	int ret = 0;
+	int ret;
 
 	obj = iwl_acpi_get_dsm_object(dev, rev, func, NULL, guid);
 	if (IS_ERR(obj)) {
@@ -123,8 +123,10 @@ static int iwl_acpi_get_dsm_integer(struct device *dev, int rev, int func,
 	} else if (obj->type == ACPI_TYPE_BUFFER) {
 		__le64 le_value = 0;
 
-		if (WARN_ON_ONCE(expected_size > sizeof(le_value)))
-			return -EINVAL;
+		if (WARN_ON_ONCE(expected_size > sizeof(le_value))) {
+			ret = -EINVAL;
+			goto out;
+		}
 
 		/* if the buffer size doesn't match the expected size */
 		if (obj->buffer.length != expected_size)
@@ -145,8 +147,9 @@ static int iwl_acpi_get_dsm_integer(struct device *dev, int rev, int func,
 	}
 
 	IWL_DEBUG_DEV_RADIO(dev,
-			    "ACPI: DSM method evaluated: func=%d, ret=%d\n",
-			    func, ret);
+			    "ACPI: DSM method evaluated: func=%d, value=%lld\n",
+			    func, *value);
+	ret = 0;
 out:
 	ACPI_FREE(obj);
 	return ret;
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
index fb2ea38e89ac..385755af8237 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2005-2014, 2018-2024 Intel Corporation
+ * Copyright (C) 2005-2014, 2018-2025 Intel Corporation
  * Copyright (C) 2013-2015 Intel Mobile Communications GmbH
  * Copyright (C) 2015-2017 Intel Deutschland GmbH
  */
@@ -558,41 +558,71 @@ static void iwl_dump_prph(struct iwl_fw_runtime *fwrt,
 }
 
 /*
- * alloc_sgtable - allocates scallerlist table in the given size,
- * fills it with pages and returns it
+ * alloc_sgtable - allocates (chained) scatterlist in the given size,
+ *	fills it with pages and returns it
  * @size: the size (in bytes) of the table
-*/
-static struct scatterlist *alloc_sgtable(int size)
+ */
+static struct scatterlist *alloc_sgtable(ssize_t size)
 {
-	int alloc_size, nents, i;
-	struct page *new_page;
-	struct scatterlist *iter;
-	struct scatterlist *table;
+	struct scatterlist *result = NULL, *prev;
+	int nents, i, n_prev;
 
 	nents = DIV_ROUND_UP(size, PAGE_SIZE);
-	table = kcalloc(nents, sizeof(*table), GFP_KERNEL);
-	if (!table)
-		return NULL;
-	sg_init_table(table, nents);
-	iter = table;
-	for_each_sg(table, iter, sg_nents(table), i) {
-		new_page = alloc_page(GFP_KERNEL);
-		if (!new_page) {
-			/* release all previous allocated pages in the table */
-			iter = table;
-			for_each_sg(table, iter, sg_nents(table), i) {
-				new_page = sg_page(iter);
-				if (new_page)
-					__free_page(new_page);
-			}
-			kfree(table);
+
+#define N_ENTRIES_PER_PAGE (PAGE_SIZE / sizeof(*result))
+	/*
+	 * We need an additional entry for table chaining,
+	 * this ensures the loop can finish i.e. we can
+	 * fit at least two entries per page (obviously,
+	 * many more really fit.)
+	 */
+	BUILD_BUG_ON(N_ENTRIES_PER_PAGE < 2);
+
+	while (nents > 0) {
+		struct scatterlist *new, *iter;
+		int n_fill, n_alloc;
+
+		if (nents <= N_ENTRIES_PER_PAGE) {
+			/* last needed table */
+			n_fill = nents;
+			n_alloc = nents;
+			nents = 0;
+		} else {
+			/* fill a page with entries */
+			n_alloc = N_ENTRIES_PER_PAGE;
+			/* reserve one for chaining */
+			n_fill = n_alloc - 1;
+			nents -= n_fill;
+		}
+
+		new = kcalloc(n_alloc, sizeof(*new), GFP_KERNEL);
+		if (!new) {
+			if (result)
+				_devcd_free_sgtable(result);
 			return NULL;
 		}
-		alloc_size = min_t(int, size, PAGE_SIZE);
-		size -= PAGE_SIZE;
-		sg_set_page(iter, new_page, alloc_size, 0);
+		sg_init_table(new, n_alloc);
+
+		if (!result)
+			result = new;
+		else
+			sg_chain(prev, n_prev, new);
+		prev = new;
+		n_prev = n_alloc;
+
+		for_each_sg(new, iter, n_fill, i) {
+			struct page *new_page = alloc_page(GFP_KERNEL);
+
+			if (!new_page) {
+				_devcd_free_sgtable(result);
+				return NULL;
+			}
+
+			sg_set_page(iter, new_page, PAGE_SIZE, 0);
+		}
 	}
-	return table;
+
+	return result;
 }
 
 static void iwl_fw_get_prph_len(struct iwl_fw_runtime *fwrt,
@@ -2661,7 +2691,7 @@ static u32 iwl_dump_ini_trigger(struct iwl_fw_runtime *fwrt,
 	}
 	/* collect DRAM_IMR region in the last */
 	if (imr_reg_data.reg_tlv)
-		size += iwl_dump_ini_mem(fwrt, list, &reg_data,
+		size += iwl_dump_ini_mem(fwrt, list, &imr_reg_data,
 					 &iwl_dump_ini_region_ops[IWL_FW_INI_REGION_DRAM_IMR]);
 
 	if (size) {
@@ -2925,6 +2955,7 @@ int iwl_fw_dbg_collect(struct iwl_fw_runtime *fwrt,
 	struct iwl_fw_dump_desc *desc;
 	unsigned int delay = 0;
 	bool monitor_only = false;
+	int ret;
 
 	if (trigger) {
 		u16 occurrences = le16_to_cpu(trigger->occurrences) - 1;
@@ -2955,7 +2986,11 @@ int iwl_fw_dbg_collect(struct iwl_fw_runtime *fwrt,
 	desc->trig_desc.type = cpu_to_le32(trig);
 	memcpy(desc->trig_desc.data, str, len);
 
-	return iwl_fw_dbg_collect_desc(fwrt, desc, monitor_only, delay);
+	ret = iwl_fw_dbg_collect_desc(fwrt, desc, monitor_only, delay);
+	if (ret)
+		kfree(desc);
+
+	return ret;
 }
 IWL_EXPORT_SYMBOL(iwl_fw_dbg_collect);
 
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/uefi.c b/drivers/net/wireless/intel/iwlwifi/fw/uefi.c
index 091fb6fd7c78..86d6286a1537 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/uefi.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/uefi.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright(c) 2021-2024 Intel Corporation
+ * Copyright(c) 2021-2025 Intel Corporation
  */
 
 #include "iwl-drv.h"
@@ -13,9 +13,12 @@
 #include <linux/efi.h>
 #include "fw/runtime.h"
 
-#define IWL_EFI_VAR_GUID EFI_GUID(0x92daaf2f, 0xc02b, 0x455b,	\
-				  0xb2, 0xec, 0xf5, 0xa3,	\
-				  0x59, 0x4f, 0x4a, 0xea)
+#define IWL_EFI_WIFI_GUID	EFI_GUID(0x92daaf2f, 0xc02b, 0x455b,	\
+					 0xb2, 0xec, 0xf5, 0xa3,	\
+					 0x59, 0x4f, 0x4a, 0xea)
+#define IWL_EFI_WIFI_BT_GUID	EFI_GUID(0xe65d8884, 0xd4af, 0x4b20,	\
+					 0x8d, 0x03, 0x77, 0x2e,	\
+					 0xcc, 0x3d, 0xa5, 0x31)
 
 struct iwl_uefi_pnvm_mem_desc {
 	__le32 addr;
@@ -61,7 +64,7 @@ void *iwl_uefi_get_pnvm(struct iwl_trans *trans, size_t *len)
 
 	*len = 0;
 
-	data = iwl_uefi_get_variable(IWL_UEFI_OEM_PNVM_NAME, &IWL_EFI_VAR_GUID,
+	data = iwl_uefi_get_variable(IWL_UEFI_OEM_PNVM_NAME, &IWL_EFI_WIFI_GUID,
 				     &package_size);
 	if (IS_ERR(data)) {
 		IWL_DEBUG_FW(trans,
@@ -76,18 +79,18 @@ void *iwl_uefi_get_pnvm(struct iwl_trans *trans, size_t *len)
 	return data;
 }
 
-static
-void *iwl_uefi_get_verified_variable(struct iwl_trans *trans,
-				     efi_char16_t *uefi_var_name,
-				     char *var_name,
-				     unsigned int expected_size,
-				     unsigned long *size)
+static void *
+iwl_uefi_get_verified_variable_guid(struct iwl_trans *trans,
+				    efi_guid_t *guid,
+				    efi_char16_t *uefi_var_name,
+				    char *var_name,
+				    unsigned int expected_size,
+				    unsigned long *size)
 {
 	void *var;
 	unsigned long var_size;
 
-	var = iwl_uefi_get_variable(uefi_var_name, &IWL_EFI_VAR_GUID,
-				    &var_size);
+	var = iwl_uefi_get_variable(uefi_var_name, guid, &var_size);
 
 	if (IS_ERR(var)) {
 		IWL_DEBUG_RADIO(trans,
@@ -112,6 +115,18 @@ void *iwl_uefi_get_verified_variable(struct iwl_trans *trans,
 	return var;
 }
 
+static void *
+iwl_uefi_get_verified_variable(struct iwl_trans *trans,
+			       efi_char16_t *uefi_var_name,
+			       char *var_name,
+			       unsigned int expected_size,
+			       unsigned long *size)
+{
+	return iwl_uefi_get_verified_variable_guid(trans, &IWL_EFI_WIFI_GUID,
+						   uefi_var_name, var_name,
+						   expected_size, size);
+}
+
 int iwl_uefi_handle_tlv_mem_desc(struct iwl_trans *trans, const u8 *data,
 				 u32 tlv_len, struct iwl_pnvm_image *pnvm_data)
 {
@@ -311,8 +326,9 @@ void iwl_uefi_get_step_table(struct iwl_trans *trans)
 	if (trans->trans_cfg->device_family < IWL_DEVICE_FAMILY_AX210)
 		return;
 
-	data = iwl_uefi_get_verified_variable(trans, IWL_UEFI_STEP_NAME,
-					      "STEP", sizeof(*data), NULL);
+	data = iwl_uefi_get_verified_variable_guid(trans, &IWL_EFI_WIFI_BT_GUID,
+						   IWL_UEFI_STEP_NAME,
+						   "STEP", sizeof(*data), NULL);
 	if (IS_ERR(data))
 		return;
 
@@ -657,8 +673,10 @@ int iwl_uefi_get_eckv(struct iwl_fw_runtime *fwrt, u32 *extl_clk)
 	struct uefi_cnv_var_eckv *data;
 	int ret = 0;
 
-	data = iwl_uefi_get_verified_variable(fwrt->trans, IWL_UEFI_ECKV_NAME,
-					      "ECKV", sizeof(*data), NULL);
+	data = iwl_uefi_get_verified_variable_guid(fwrt->trans,
+						   &IWL_EFI_WIFI_BT_GUID,
+						   IWL_UEFI_ECKV_NAME,
+						   "ECKV", sizeof(*data), NULL);
 	if (IS_ERR(data))
 		return -EINVAL;
 
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/uefi.h b/drivers/net/wireless/intel/iwlwifi/fw/uefi.h
index e525d449e656..c931f5cedb0b 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/uefi.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/uefi.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
- * Copyright(c) 2021-2024 Intel Corporation
+ * Copyright(c) 2021-2025 Intel Corporation
  */
 #ifndef __iwl_fw_uefi__
 #define __iwl_fw_uefi__
@@ -19,7 +19,7 @@
 #define IWL_UEFI_WTAS_NAME		L"UefiCnvWlanWTAS"
 #define IWL_UEFI_SPLC_NAME		L"UefiCnvWlanSPLC"
 #define IWL_UEFI_WRDD_NAME		L"UefiCnvWlanWRDD"
-#define IWL_UEFI_ECKV_NAME		L"UefiCnvWlanECKV"
+#define IWL_UEFI_ECKV_NAME		L"UefiCnvCommonECKV"
 #define IWL_UEFI_DSM_NAME		L"UefiCnvWlanGeneralCfg"
 #define IWL_UEFI_WBEM_NAME		L"UefiCnvWlanWBEM"
 #define IWL_UEFI_PUNCTURING_NAME	L"UefiCnvWlanPuncturing"
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-config.h b/drivers/net/wireless/intel/iwlwifi/iwl-config.h
index 17721bb47e25..89744dbedb4a 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-config.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-config.h
@@ -38,6 +38,7 @@ enum iwl_device_family {
 	IWL_DEVICE_FAMILY_AX210,
 	IWL_DEVICE_FAMILY_BZ,
 	IWL_DEVICE_FAMILY_SC,
+	IWL_DEVICE_FAMILY_DR,
 };
 
 /*
@@ -424,6 +425,8 @@ struct iwl_cfg {
 #define IWL_CFG_MAC_TYPE_SC2		0x49
 #define IWL_CFG_MAC_TYPE_SC2F		0x4A
 #define IWL_CFG_MAC_TYPE_BZ_W		0x4B
+#define IWL_CFG_MAC_TYPE_BR		0x4C
+#define IWL_CFG_MAC_TYPE_DR		0x4D
 
 #define IWL_CFG_RF_TYPE_TH		0x105
 #define IWL_CFG_RF_TYPE_TH1		0x108
@@ -434,6 +437,7 @@ struct iwl_cfg {
 #define IWL_CFG_RF_TYPE_GF		0x10D
 #define IWL_CFG_RF_TYPE_FM		0x112
 #define IWL_CFG_RF_TYPE_WH		0x113
+#define IWL_CFG_RF_TYPE_PE		0x114
 
 #define IWL_CFG_RF_ID_TH		0x1
 #define IWL_CFG_RF_ID_TH1		0x1
@@ -506,6 +510,8 @@ extern const struct iwl_cfg_trans_params iwl_ma_trans_cfg;
 extern const struct iwl_cfg_trans_params iwl_bz_trans_cfg;
 extern const struct iwl_cfg_trans_params iwl_gl_trans_cfg;
 extern const struct iwl_cfg_trans_params iwl_sc_trans_cfg;
+extern const struct iwl_cfg_trans_params iwl_dr_trans_cfg;
+extern const struct iwl_cfg_trans_params iwl_br_trans_cfg;
 extern const char iwl9162_name[];
 extern const char iwl9260_name[];
 extern const char iwl9260_1_name[];
@@ -551,6 +557,8 @@ extern const char iwl_mtp_name[];
 extern const char iwl_sc_name[];
 extern const char iwl_sc2_name[];
 extern const char iwl_sc2f_name[];
+extern const char iwl_dr_name[];
+extern const char iwl_br_name[];
 #if IS_ENABLED(CONFIG_IWLDVM)
 extern const struct iwl_cfg iwl5300_agn_cfg;
 extern const struct iwl_cfg iwl5100_agn_cfg;
@@ -658,6 +666,8 @@ extern const struct iwl_cfg iwl_cfg_gl;
 extern const struct iwl_cfg iwl_cfg_sc;
 extern const struct iwl_cfg iwl_cfg_sc2;
 extern const struct iwl_cfg iwl_cfg_sc2f;
+extern const struct iwl_cfg iwl_cfg_dr;
+extern const struct iwl_cfg iwl_cfg_br;
 #endif /* CONFIG_IWLMVM */
 
 #endif /* __IWL_CONFIG_H__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-csr.h b/drivers/net/wireless/intel/iwlwifi/iwl-csr.h
index 98563757ce2c..405bba199fe7 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-csr.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-csr.h
@@ -148,6 +148,7 @@
  * during a error FW error.
  */
 #define CSR_FUNC_SCRATCH_INIT_VALUE		(0x01010101)
+#define CSR_FUNC_SCRATCH_POWER_OFF_MASK		0xFFFF
 
 /* Bits for CSR_HW_IF_CONFIG_REG */
 #define CSR_HW_IF_CONFIG_REG_MSK_MAC_STEP_DASH	(0x0000000F)
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c
index 08d990ba8a79..ce787326aa69 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2018-2024 Intel Corporation
+ * Copyright (C) 2018-2025 Intel Corporation
  */
 #include <linux/firmware.h>
 #include "iwl-drv.h"
@@ -1372,15 +1372,15 @@ void _iwl_dbg_tlv_time_point(struct iwl_fw_runtime *fwrt,
 	switch (tp_id) {
 	case IWL_FW_INI_TIME_POINT_EARLY:
 		iwl_dbg_tlv_init_cfg(fwrt);
-		iwl_dbg_tlv_apply_config(fwrt, conf_list);
 		iwl_dbg_tlv_update_drams(fwrt);
 		iwl_dbg_tlv_tp_trigger(fwrt, sync, trig_list, tp_data, NULL);
+		iwl_dbg_tlv_apply_config(fwrt, conf_list);
 		break;
 	case IWL_FW_INI_TIME_POINT_AFTER_ALIVE:
 		iwl_dbg_tlv_apply_buffers(fwrt);
 		iwl_dbg_tlv_send_hcmds(fwrt, hcmd_list);
-		iwl_dbg_tlv_apply_config(fwrt, conf_list);
 		iwl_dbg_tlv_tp_trigger(fwrt, sync, trig_list, tp_data, NULL);
+		iwl_dbg_tlv_apply_config(fwrt, conf_list);
 		break;
 	case IWL_FW_INI_TIME_POINT_PERIODIC:
 		iwl_dbg_tlv_set_periodic_trigs(fwrt);
@@ -1390,14 +1390,14 @@ void _iwl_dbg_tlv_time_point(struct iwl_fw_runtime *fwrt,
 	case IWL_FW_INI_TIME_POINT_MISSED_BEACONS:
 	case IWL_FW_INI_TIME_POINT_FW_DHC_NOTIFICATION:
 		iwl_dbg_tlv_send_hcmds(fwrt, hcmd_list);
-		iwl_dbg_tlv_apply_config(fwrt, conf_list);
 		iwl_dbg_tlv_tp_trigger(fwrt, sync, trig_list, tp_data,
 				       iwl_dbg_tlv_check_fw_pkt);
+		iwl_dbg_tlv_apply_config(fwrt, conf_list);
 		break;
 	default:
 		iwl_dbg_tlv_send_hcmds(fwrt, hcmd_list);
-		iwl_dbg_tlv_apply_config(fwrt, conf_list);
 		iwl_dbg_tlv_tp_trigger(fwrt, sync, trig_list, tp_data, NULL);
+		iwl_dbg_tlv_apply_config(fwrt, conf_list);
 		break;
 	}
 }
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
index c620911a1193..754e01688900 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
@@ -1197,7 +1197,7 @@ static int iwl_parse_tlv_firmware(struct iwl_drv *drv,
 
 			if (tlv_len != sizeof(*fseq_ver))
 				goto invalid_tlv_len;
-			IWL_INFO(drv, "TLV_FW_FSEQ_VERSION: %s\n",
+			IWL_INFO(drv, "TLV_FW_FSEQ_VERSION: %.32s\n",
 				 fseq_ver->version);
 			}
 			break;
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-trans.c b/drivers/net/wireless/intel/iwlwifi/iwl-trans.c
index 3c9d91496c82..510e04b721da 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-trans.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-trans.c
@@ -2,7 +2,7 @@
 /*
  * Copyright (C) 2015 Intel Mobile Communications GmbH
  * Copyright (C) 2016-2017 Intel Deutschland GmbH
- * Copyright (C) 2019-2021, 2023-2024 Intel Corporation
+ * Copyright (C) 2019-2021, 2023-2025 Intel Corporation
  */
 #include <linux/kernel.h>
 #include <linux/bsearch.h>
@@ -347,7 +347,6 @@ void __releases(nic_access)
 iwl_trans_release_nic_access(struct iwl_trans *trans)
 {
 	iwl_trans_pcie_release_nic_access(trans);
-	__release(nic_access);
 }
 IWL_EXPORT_SYMBOL(iwl_trans_release_nic_access);
 
@@ -420,6 +419,9 @@ IWL_EXPORT_SYMBOL(iwl_trans_tx);
 void iwl_trans_reclaim(struct iwl_trans *trans, int queue, int ssn,
 		       struct sk_buff_head *skbs, bool is_flush)
 {
+	if (unlikely(test_bit(STATUS_FW_ERROR, &trans->status)))
+		return;
+
 	if (WARN_ONCE(trans->state != IWL_TRANS_FW_ALIVE,
 		      "bad state = %d\n", trans->state))
 		return;
@@ -452,6 +454,9 @@ IWL_EXPORT_SYMBOL(iwl_trans_txq_enable_cfg);
 
 int iwl_trans_wait_txq_empty(struct iwl_trans *trans, int queue)
 {
+	if (unlikely(test_bit(STATUS_FW_ERROR, &trans->status)))
+		return -EIO;
+
 	if (WARN_ONCE(trans->state != IWL_TRANS_FW_ALIVE,
 		      "bad state = %d\n", trans->state))
 		return -EIO;
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/coex.c b/drivers/net/wireless/intel/iwlwifi/mvm/coex.c
index b607961970e9..9b8624304fa3 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/coex.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/coex.c
@@ -530,18 +530,15 @@ static void iwl_mvm_bt_coex_notif_iterator(void *_data, u8 *mac,
 					   struct ieee80211_vif *vif)
 {
 	struct iwl_mvm *mvm = _data;
+	struct ieee80211_bss_conf *link_conf;
+	unsigned int link_id;
 
 	lockdep_assert_held(&mvm->mutex);
 
 	if (vif->type != NL80211_IFTYPE_STATION)
 		return;
 
-	for (int link_id = 0;
-	     link_id < IEEE80211_MLD_MAX_NUM_LINKS;
-	     link_id++) {
-		struct ieee80211_bss_conf *link_conf =
-			rcu_dereference_check(vif->link_conf[link_id],
-					      lockdep_is_held(&mvm->mutex));
+	for_each_vif_active_link(vif, link_conf, link_id) {
 		struct ieee80211_chanctx_conf *chanctx_conf =
 			rcu_dereference_check(link_conf->chanctx_conf,
 					      lockdep_is_held(&mvm->mutex));
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
index 6a4300c01d41..7e258dcdf501 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
@@ -2375,6 +2375,7 @@ static void iwl_mvm_convert_gtk_v2(struct iwl_wowlan_status_data *status,
 
 	status->gtk[0].len = data->key_len;
 	status->gtk[0].flags = data->key_flags;
+	status->gtk[0].id = status->gtk[0].flags & IWL_WOWLAN_GTK_IDX_MASK;
 
 	memcpy(status->gtk[0].key, data->key, sizeof(data->key));
 
@@ -2686,6 +2687,7 @@ iwl_mvm_send_wowlan_get_status(struct iwl_mvm *mvm, u8 sta_id)
 		 * currently used key.
 		 */
 		status->gtk[0].flags = v6->gtk.key_index | BIT(7);
+		status->gtk[0].id = v6->gtk.key_index;
 	} else if (notif_ver == 7) {
 		struct iwl_wowlan_status_v7 *v7 = (void *)cmd.resp_pkt->data;
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
index 91ca830a7b60..f4276fdee6be 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
@@ -1518,6 +1518,13 @@ static ssize_t iwl_dbgfs_fw_dbg_clear_write(struct iwl_mvm *mvm,
 	if (mvm->trans->trans_cfg->device_family < IWL_DEVICE_FAMILY_9000)
 		return -EOPNOTSUPP;
 
+	/*
+	 * If the firmware is not running, silently succeed since there is
+	 * no data to clear.
+	 */
+	if (!iwl_mvm_firmware_running(mvm))
+		return count;
+
 	mutex_lock(&mvm->mutex);
 	iwl_fw_dbg_clear_monitor_buf(&mvm->fwrt);
 	mutex_unlock(&mvm->mutex);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c b/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c
index 55245f913286..2ed7a0d77ef8 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c
@@ -773,7 +773,11 @@ iwl_mvm_ftm_set_secured_ranging(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 
 			target.bssid = bssid;
 			target.cipher = cipher;
+			target.tk = NULL;
 			ieee80211_iter_keys(mvm->hw, vif, iter, &target);
+
+			if (!WARN_ON(!target.tk))
+				memcpy(tk, target.tk, TK_11AZ_LEN);
 		} else {
 			memcpy(tk, entry->tk, sizeof(entry->tk));
 		}
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
index f30b0fc8eca9..2b9a684cf61d 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2012-2014, 2018-2024 Intel Corporation
+ * Copyright (C) 2012-2014, 2018-2025 Intel Corporation
  * Copyright (C) 2013-2015 Intel Mobile Communications GmbH
  * Copyright (C) 2016-2017 Intel Deutschland GmbH
  */
@@ -422,6 +422,8 @@ static int iwl_mvm_load_ucode_wait_alive(struct iwl_mvm *mvm,
 	/* if reached this point, Alive notification was received */
 	iwl_mei_alive_notif(true);
 
+	iwl_trans_fw_alive(mvm->trans, alive_data.scd_base_addr);
+
 	ret = iwl_pnvm_load(mvm->trans, &mvm->notif_wait,
 			    &mvm->fw->ucode_capa);
 	if (ret) {
@@ -430,8 +432,6 @@ static int iwl_mvm_load_ucode_wait_alive(struct iwl_mvm *mvm,
 		return ret;
 	}
 
-	iwl_trans_fw_alive(mvm->trans, alive_data.scd_base_addr);
-
 	/*
 	 * Note: all the queues are enabled as part of the interface
 	 * initialization, but in firmware restart scenarios they
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
index e96ddaeeeeff..d013de30e7ed 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2012-2014, 2018-2024 Intel Corporation
+ * Copyright (C) 2012-2014, 2018-2025 Intel Corporation
  * Copyright (C) 2013-2014 Intel Mobile Communications GmbH
  * Copyright (C) 2015-2017 Intel Deutschland GmbH
  */
@@ -962,7 +962,7 @@ u16 iwl_mvm_mac_ctxt_get_beacon_flags(const struct iwl_fw *fw, u8 rate_idx)
 	u16 flags = iwl_mvm_mac80211_idx_to_hwrate(fw, rate_idx);
 	bool is_new_rate = iwl_fw_lookup_cmd_ver(fw, BEACON_TEMPLATE_CMD, 0) > 10;
 
-	if (rate_idx <= IWL_FIRST_CCK_RATE)
+	if (rate_idx <= IWL_LAST_CCK_RATE)
 		flags |= is_new_rate ? IWL_MAC_BEACON_CCK
 			  : IWL_MAC_BEACON_CCK_V1;
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index d37d83d24635..3fd257f770ba 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -4096,6 +4096,20 @@ iwl_mvm_sta_state_authorized_to_assoc(struct iwl_mvm *mvm,
 	return 0;
 }
 
+void iwl_mvm_smps_workaround(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
+			     bool update)
+{
+	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
+
+	if (!iwl_mvm_has_rlc_offload(mvm))
+		return;
+
+	mvmvif->ps_disabled = !vif->cfg.ps;
+
+	if (update)
+		iwl_mvm_power_update_mac(mvm);
+}
+
 /* Common part for MLD and non-MLD modes */
 int iwl_mvm_mac_sta_state_common(struct ieee80211_hw *hw,
 				 struct ieee80211_vif *vif,
@@ -4188,6 +4202,7 @@ int iwl_mvm_mac_sta_state_common(struct ieee80211_hw *hw,
 		   new_state == IEEE80211_STA_AUTHORIZED) {
 		ret = iwl_mvm_sta_state_assoc_to_authorized(mvm, vif, sta,
 							    callbacks);
+		iwl_mvm_smps_workaround(mvm, vif, true);
 	} else if (old_state == IEEE80211_STA_AUTHORIZED &&
 		   new_state == IEEE80211_STA_ASSOC) {
 		ret = iwl_mvm_sta_state_authorized_to_assoc(mvm, vif, sta,
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c
index e252f0dcea20..04da02bdd953 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2022-2024 Intel Corporation
+ * Copyright (C) 2022-2025 Intel Corporation
  */
 #include "mvm.h"
 
@@ -961,6 +961,7 @@ static void iwl_mvm_mld_vif_cfg_changed_station(struct iwl_mvm *mvm,
 	}
 
 	if (changes & BSS_CHANGED_PS) {
+		iwl_mvm_smps_workaround(mvm, vif, false);
 		ret = iwl_mvm_power_update_mac(mvm);
 		if (ret)
 			IWL_ERR(mvm, "failed to update power mode\n");
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
index ef07cff203b0..7d86d273092a 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
@@ -3042,4 +3042,7 @@ iwl_mvm_send_ap_tx_power_constraint_cmd(struct iwl_mvm *mvm,
 					struct ieee80211_vif *vif,
 					struct ieee80211_bss_conf *bss_conf,
 					bool is_ap);
+
+void iwl_mvm_smps_workaround(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
+			     bool update);
 #endif /* __IWL_MVM_H__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
index 4dd4a9d5c71f..a7dbc0a5ea84 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
@@ -61,8 +61,10 @@ static int __init iwl_mvm_init(void)
 	}
 
 	ret = iwl_opmode_register("iwlmvm", &iwl_mvm_ops);
-	if (ret)
+	if (ret) {
 		pr_err("Unable to register MVM op_mode: %d\n", ret);
+		iwl_mvm_rate_control_unregister();
+	}
 
 	return ret;
 }
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c
index a8c4e354e2ce..5f8f24580444 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c
@@ -2,6 +2,7 @@
 /******************************************************************************
  *
  * Copyright(c) 2005 - 2014, 2018 - 2023 Intel Corporation. All rights reserved.
+ * Copyright(c) 2025 Intel Corporation
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
  * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
  *****************************************************************************/
@@ -2709,6 +2710,7 @@ static void rs_drv_get_rate(void *mvm_r, struct ieee80211_sta *sta,
 							  optimal_rate);
 		iwl_mvm_hwrate_to_tx_rate_v1(last_ucode_rate, info->band,
 					     &txrc->reported_rate);
+		txrc->reported_rate.count = 1;
 	}
 	spin_unlock_bh(&lq_sta->pers.lock);
 }
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
index 65f8933c34b4..64bd5d10765d 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
@@ -854,10 +854,15 @@ static bool iwl_mvm_reorder(struct iwl_mvm *mvm,
 	 * already ahead and it will be dropped.
 	 * If the last sub-frame is not on this queue - we will get frame
 	 * release notification with up to date NSSN.
+	 * If this is the first frame that is stored in the buffer, the head_sn
+	 * may be outdated. Update it based on the last NSSN to make sure it
+	 * will be released when the frame release notification arrives.
 	 */
 	if (!amsdu || last_subframe)
 		iwl_mvm_release_frames(mvm, sta, napi, baid_data,
 				       buffer, nssn);
+	else if (buffer->num_stored == 1)
+		buffer->head_sn = nssn;
 
 	spin_unlock_bh(&buffer->lock);
 	return true;
@@ -995,7 +1000,7 @@ iwl_mvm_decode_he_phy_ru_alloc(struct iwl_mvm_rx_phy_data *phy_data,
 	 */
 	u8 ru = le32_get_bits(phy_data->d1, IWL_RX_PHY_DATA1_HE_RU_ALLOC_MASK);
 	u32 rate_n_flags = phy_data->rate_n_flags;
-	u32 he_type = rate_n_flags & RATE_MCS_HE_TYPE_MSK_V1;
+	u32 he_type = rate_n_flags & RATE_MCS_HE_TYPE_MSK;
 	u8 offs = 0;
 
 	rx_status->bw = RATE_INFO_BW_HE_RU;
@@ -1050,13 +1055,13 @@ iwl_mvm_decode_he_phy_ru_alloc(struct iwl_mvm_rx_phy_data *phy_data,
 
 	if (he_mu)
 		he_mu->flags2 |=
-			le16_encode_bits(FIELD_GET(RATE_MCS_CHAN_WIDTH_MSK_V1,
+			le16_encode_bits(FIELD_GET(RATE_MCS_CHAN_WIDTH_MSK,
 						   rate_n_flags),
 					 IEEE80211_RADIOTAP_HE_MU_FLAGS2_BW_FROM_SIG_A_BW);
-	else if (he_type == RATE_MCS_HE_TYPE_TRIG_V1)
+	else if (he_type == RATE_MCS_HE_TYPE_TRIG)
 		he->data6 |=
 			cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA6_TB_PPDU_BW_KNOWN) |
-			le16_encode_bits(FIELD_GET(RATE_MCS_CHAN_WIDTH_MSK_V1,
+			le16_encode_bits(FIELD_GET(RATE_MCS_CHAN_WIDTH_MSK,
 						   rate_n_flags),
 					 IEEE80211_RADIOTAP_HE_DATA6_TB_PPDU_BW);
 }
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
index ddcbd80a49fb..853b95709a79 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
@@ -835,7 +835,7 @@ static inline bool iwl_mvm_scan_fits(struct iwl_mvm *mvm, int n_ssids,
 				     int n_channels)
 {
 	return ((n_ssids <= PROBE_OPTION_MAX) &&
-		(n_channels <= mvm->fw->ucode_capa.n_scan_channels) &
+		(n_channels <= mvm->fw->ucode_capa.n_scan_channels) &&
 		(ies->common_ie_len +
 		 ies->len[NL80211_BAND_2GHZ] + ies->len[NL80211_BAND_5GHZ] +
 		 ies->len[NL80211_BAND_6GHZ] <=
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c
index 72fa7ac86516..17b8ccc27569 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c
@@ -1030,6 +1030,8 @@ void iwl_mvm_rx_session_protect_notif(struct iwl_mvm *mvm,
 		/* End TE, notify mac80211 */
 		mvmvif->time_event_data.id = SESSION_PROTECT_CONF_MAX_ID;
 		mvmvif->time_event_data.link_id = -1;
+		/* set the bit so the ROC cleanup will actually clean up */
+		set_bit(IWL_MVM_STATUS_ROC_P2P_RUNNING, &mvm->status);
 		iwl_mvm_roc_finished(mvm);
 		ieee80211_remain_on_channel_expired(mvm->hw);
 	} else if (le32_to_cpu(notif->start)) {
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
index ca026b5256ce..5f4942f6cc68 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
@@ -1880,7 +1880,9 @@ static void iwl_mvm_rx_tx_cmd_single(struct iwl_mvm *mvm,
 				IWL_DEBUG_TX_REPLY(mvm,
 						   "Next reclaimed packet:%d\n",
 						   next_reclaimed);
-				iwl_mvm_count_mpdu(mvmsta, sta_id, 1, true, 0);
+				if (tid < IWL_MAX_TID_COUNT)
+					iwl_mvm_count_mpdu(mvmsta, sta_id, 1,
+							   true, 0);
 			} else {
 				IWL_DEBUG_TX_REPLY(mvm,
 						   "NDP - don't update next_reclaimed\n");
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
index 8fb2aa282242..68989d183e82 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
@@ -540,6 +540,9 @@ VISIBLE_IF_IWLWIFI_KUNIT const struct pci_device_id iwl_hw_card_ids[] = {
 	{IWL_PCI_DEVICE(0xE340, PCI_ANY_ID, iwl_sc_trans_cfg)},
 	{IWL_PCI_DEVICE(0xD340, PCI_ANY_ID, iwl_sc_trans_cfg)},
 	{IWL_PCI_DEVICE(0x6E70, PCI_ANY_ID, iwl_sc_trans_cfg)},
+
+/* Dr devices */
+	{IWL_PCI_DEVICE(0x272F, PCI_ANY_ID, iwl_dr_trans_cfg)},
 #endif /* CONFIG_IWLMVM */
 
 	{0}
@@ -584,6 +587,8 @@ VISIBLE_IF_IWLWIFI_KUNIT const struct iwl_dev_info iwl_dev_info_table[] = {
 	IWL_DEV_INFO(0x7A70, 0x1692, iwlax411_2ax_cfg_so_gf4_a0, iwl_ax411_killer_1690i_name),
 	IWL_DEV_INFO(0x7AF0, 0x1691, iwlax411_2ax_cfg_so_gf4_a0, iwl_ax411_killer_1690s_name),
 	IWL_DEV_INFO(0x7AF0, 0x1692, iwlax411_2ax_cfg_so_gf4_a0, iwl_ax411_killer_1690i_name),
+	IWL_DEV_INFO(0x7F70, 0x1691, iwlax411_2ax_cfg_so_gf4_a0, iwl_ax411_killer_1690s_name),
+	IWL_DEV_INFO(0x7F70, 0x1692, iwlax411_2ax_cfg_so_gf4_a0, iwl_ax411_killer_1690i_name),
 
 	IWL_DEV_INFO(0x271C, 0x0214, iwl9260_2ac_cfg, iwl9260_1_name),
 	IWL_DEV_INFO(0x7E40, 0x1691, iwl_cfg_ma, iwl_ax411_killer_1690s_name),
@@ -1182,6 +1187,19 @@ VISIBLE_IF_IWLWIFI_KUNIT const struct iwl_dev_info iwl_dev_info_table[] = {
 		      IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
 		      iwl_cfg_sc2f, iwl_sc2f_name),
+/* Dr */
+	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
+		      IWL_CFG_MAC_TYPE_DR, IWL_CFG_ANY,
+		      IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+		      IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+		      iwl_cfg_dr, iwl_dr_name),
+
+/* Br */
+	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
+		      IWL_CFG_MAC_TYPE_BR, IWL_CFG_ANY,
+		      IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+		      IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+		      iwl_cfg_br, iwl_br_name),
 #endif /* CONFIG_IWLMVM */
 };
 EXPORT_SYMBOL_IF_IWLWIFI_KUNIT(iwl_dev_info_table);
@@ -1635,11 +1653,27 @@ static int _iwl_pci_resume(struct device *device, bool restore)
 	 * Scratch value was altered, this means the device was powered off, we
 	 * need to reset it completely.
 	 * Note: MAC (bits 0:7) will be cleared upon suspend even with wowlan,
-	 * so assume that any bits there mean that the device is usable.
+	 * but not bits [15:8]. So if we have bits set in lower word, assume
+	 * the device is alive.
+	 * For older devices, just try silently to grab the NIC.
 	 */
-	if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_BZ &&
-	    !iwl_read32(trans, CSR_FUNC_SCRATCH))
-		device_was_powered_off = true;
+	if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_BZ) {
+		if (!(iwl_read32(trans, CSR_FUNC_SCRATCH) &
+		      CSR_FUNC_SCRATCH_POWER_OFF_MASK))
+			device_was_powered_off = true;
+	} else {
+		/*
+		 * bh are re-enabled by iwl_trans_pcie_release_nic_access,
+		 * so re-enable them if _iwl_trans_pcie_grab_nic_access fails.
+		 */
+		local_bh_disable();
+		if (_iwl_trans_pcie_grab_nic_access(trans, true)) {
+			iwl_trans_pcie_release_nic_access(trans);
+		} else {
+			device_was_powered_off = true;
+			local_bh_enable();
+		}
+	}
 
 	if (restore || device_was_powered_off) {
 		trans->state = IWL_TRANS_NO_FW;
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
index 27a7e0b5b3d5..6019114a5d1a 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
- * Copyright (C) 2003-2015, 2018-2024 Intel Corporation
+ * Copyright (C) 2003-2015, 2018-2025 Intel Corporation
  * Copyright (C) 2013-2015 Intel Mobile Communications GmbH
  * Copyright (C) 2016-2017 Intel Deutschland GmbH
  */
@@ -558,10 +558,10 @@ void iwl_trans_pcie_free(struct iwl_trans *trans);
 void iwl_trans_pcie_free_pnvm_dram_regions(struct iwl_dram_regions *dram_regions,
 					   struct device *dev);
 
-bool __iwl_trans_pcie_grab_nic_access(struct iwl_trans *trans);
-#define _iwl_trans_pcie_grab_nic_access(trans)			\
+bool __iwl_trans_pcie_grab_nic_access(struct iwl_trans *trans, bool silent);
+#define _iwl_trans_pcie_grab_nic_access(trans, silent)		\
 	__cond_lock(nic_access_nobh,				\
-		    likely(__iwl_trans_pcie_grab_nic_access(trans)))
+		    likely(__iwl_trans_pcie_grab_nic_access(trans, silent)))
 
 /*****************************************************
 * RX
@@ -643,7 +643,8 @@ dma_addr_t iwl_pcie_get_sgt_tb_phys(struct sg_table *sgt, unsigned int offset,
 				    unsigned int len);
 struct sg_table *iwl_pcie_prep_tso(struct iwl_trans *trans, struct sk_buff *skb,
 				   struct iwl_cmd_meta *cmd_meta,
-				   u8 **hdr, unsigned int hdr_room);
+				   u8 **hdr, unsigned int hdr_room,
+				   unsigned int offset);
 
 void iwl_pcie_free_tso_pages(struct iwl_trans *trans, struct sk_buff *skb,
 			     struct iwl_cmd_meta *cmd_meta);
@@ -1101,7 +1102,8 @@ void iwl_trans_pcie_set_bits_mask(struct iwl_trans *trans, u32 reg,
 int iwl_trans_pcie_read_config32(struct iwl_trans *trans, u32 ofs,
 				 u32 *val);
 bool iwl_trans_pcie_grab_nic_access(struct iwl_trans *trans);
-void iwl_trans_pcie_release_nic_access(struct iwl_trans *trans);
+void __releases(nic_access_nobh)
+iwl_trans_pcie_release_nic_access(struct iwl_trans *trans);
 
 /* transport gen 1 exported functions */
 void iwl_trans_pcie_fw_alive(struct iwl_trans *trans, u32 scd_addr);
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
index d19b3bd0866b..462ebe088b3c 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
@@ -2191,7 +2191,7 @@ EXPORT_SYMBOL(iwl_trans_pcie_remove);
  * This version doesn't disable BHs but rather assumes they're
  * already disabled.
  */
-bool __iwl_trans_pcie_grab_nic_access(struct iwl_trans *trans)
+bool __iwl_trans_pcie_grab_nic_access(struct iwl_trans *trans, bool silent)
 {
 	int ret;
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
@@ -2243,6 +2243,11 @@ bool __iwl_trans_pcie_grab_nic_access(struct iwl_trans *trans)
 	if (unlikely(ret < 0)) {
 		u32 cntrl = iwl_read32(trans, CSR_GP_CNTRL);
 
+		if (silent) {
+			spin_unlock(&trans_pcie->reg_lock);
+			return false;
+		}
+
 		WARN_ONCE(1,
 			  "Timeout waiting for hardware access (CSR_GP_CNTRL 0x%08x)\n",
 			  cntrl);
@@ -2273,7 +2278,7 @@ bool iwl_trans_pcie_grab_nic_access(struct iwl_trans *trans)
 	bool ret;
 
 	local_bh_disable();
-	ret = __iwl_trans_pcie_grab_nic_access(trans);
+	ret = __iwl_trans_pcie_grab_nic_access(trans, false);
 	if (ret) {
 		/* keep BHs disabled until iwl_trans_pcie_release_nic_access */
 		return ret;
@@ -2282,7 +2287,8 @@ bool iwl_trans_pcie_grab_nic_access(struct iwl_trans *trans)
 	return false;
 }
 
-void iwl_trans_pcie_release_nic_access(struct iwl_trans *trans)
+void __releases(nic_access_nobh)
+iwl_trans_pcie_release_nic_access(struct iwl_trans *trans)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 
@@ -2309,6 +2315,7 @@ void iwl_trans_pcie_release_nic_access(struct iwl_trans *trans)
 	 * scheduled on different CPUs (after we drop reg_lock).
 	 */
 out:
+	__release(nic_access_nobh);
 	spin_unlock_bh(&trans_pcie->reg_lock);
 }
 
@@ -2719,6 +2726,8 @@ static ssize_t iwl_dbgfs_rx_queue_read(struct file *file,
 	for (i = 0; i < trans->num_rx_queues && pos < bufsz; i++) {
 		struct iwl_rxq *rxq = &trans_pcie->rxq[i];
 
+		spin_lock_bh(&rxq->lock);
+
 		pos += scnprintf(buf + pos, bufsz - pos, "queue#: %2d\n",
 				 i);
 		pos += scnprintf(buf + pos, bufsz - pos, "\tread: %u\n",
@@ -2739,6 +2748,7 @@ static ssize_t iwl_dbgfs_rx_queue_read(struct file *file,
 			pos += scnprintf(buf + pos, bufsz - pos,
 					 "\tclosed_rb_num: Not Allocated\n");
 		}
+		spin_unlock_bh(&rxq->lock);
 	}
 	ret = simple_read_from_buffer(user_buf, count, ppos, buf, pos);
 	kfree(buf);
@@ -3403,8 +3413,11 @@ iwl_trans_pcie_dump_data(struct iwl_trans *trans, u32 dump_mask,
 		/* Dump RBs is supported only for pre-9000 devices (1 queue) */
 		struct iwl_rxq *rxq = &trans_pcie->rxq[0];
 		/* RBs */
+		spin_lock_bh(&rxq->lock);
 		num_rbs = iwl_get_closed_rb_stts(trans, rxq);
 		num_rbs = (num_rbs - rxq->read) & RX_QUEUE_MASK;
+		spin_unlock_bh(&rxq->lock);
+
 		len += num_rbs * (sizeof(*data) +
 				  sizeof(struct iwl_fw_error_dump_rb) +
 				  (PAGE_SIZE << trans_pcie->rx_page_order));
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
index b1846abb99b7..477a05cd1288 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
  * Copyright (C) 2017 Intel Deutschland GmbH
- * Copyright (C) 2018-2020, 2023-2024 Intel Corporation
+ * Copyright (C) 2018-2020, 2023-2025 Intel Corporation
  */
 #include <net/tso.h>
 #include <linux/tcp.h>
@@ -188,7 +188,8 @@ static int iwl_txq_gen2_build_amsdu(struct iwl_trans *trans,
 		(3 + snap_ip_tcp_hdrlen + sizeof(struct ethhdr));
 
 	/* Our device supports 9 segments at most, it will fit in 1 page */
-	sgt = iwl_pcie_prep_tso(trans, skb, out_meta, &start_hdr, hdr_room);
+	sgt = iwl_pcie_prep_tso(trans, skb, out_meta, &start_hdr, hdr_room,
+				snap_ip_tcp_hdrlen + hdr_len);
 	if (!sgt)
 		return -ENOMEM;
 
@@ -347,6 +348,7 @@ iwl_tfh_tfd *iwl_txq_gen2_build_tx_amsdu(struct iwl_trans *trans,
 	return tfd;
 
 out_err:
+	iwl_pcie_free_tso_pages(trans, skb, out_meta);
 	iwl_txq_gen2_tfd_unmap(trans, out_meta, tfd);
 	return NULL;
 }
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
index 9fe050f0ddc1..f0213a6b8cf5 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2003-2014, 2018-2021, 2023-2024 Intel Corporation
+ * Copyright (C) 2003-2014, 2018-2021, 2023-2025 Intel Corporation
  * Copyright (C) 2013-2015 Intel Mobile Communications GmbH
  * Copyright (C) 2016-2017 Intel Deutschland GmbH
  */
@@ -1021,7 +1021,7 @@ static int iwl_pcie_set_cmd_in_flight(struct iwl_trans *trans,
 	 * returned. This needs to be done only on NICs that have
 	 * apmg_wake_up_wa set (see above.)
 	 */
-	if (!_iwl_trans_pcie_grab_nic_access(trans))
+	if (!_iwl_trans_pcie_grab_nic_access(trans, false))
 		return -EIO;
 
 	/*
@@ -1853,6 +1853,7 @@ dma_addr_t iwl_pcie_get_sgt_tb_phys(struct sg_table *sgt, unsigned int offset,
  * @cmd_meta: command meta to store the scatter list information for unmapping
  * @hdr: output argument for TSO headers
  * @hdr_room: requested length for TSO headers
+ * @offset: offset into the data from which mapping should start
  *
  * Allocate space for a scatter gather list and TSO headers and map the SKB
  * using the scatter gather list. The SKB is unmapped again when the page is
@@ -1862,9 +1863,12 @@ dma_addr_t iwl_pcie_get_sgt_tb_phys(struct sg_table *sgt, unsigned int offset,
  */
 struct sg_table *iwl_pcie_prep_tso(struct iwl_trans *trans, struct sk_buff *skb,
 				   struct iwl_cmd_meta *cmd_meta,
-				   u8 **hdr, unsigned int hdr_room)
+				   u8 **hdr, unsigned int hdr_room,
+				   unsigned int offset)
 {
 	struct sg_table *sgt;
+	unsigned int n_segments = skb_shinfo(skb)->nr_frags + 1;
+	int orig_nents;
 
 	if (WARN_ON_ONCE(skb_has_frag_list(skb)))
 		return NULL;
@@ -1872,8 +1876,7 @@ struct sg_table *iwl_pcie_prep_tso(struct iwl_trans *trans, struct sk_buff *skb,
 	*hdr = iwl_pcie_get_page_hdr(trans,
 				     hdr_room + __alignof__(struct sg_table) +
 				     sizeof(struct sg_table) +
-				     (skb_shinfo(skb)->nr_frags + 1) *
-				     sizeof(struct scatterlist),
+				     n_segments * sizeof(struct scatterlist),
 				     skb);
 	if (!*hdr)
 		return NULL;
@@ -1881,14 +1884,15 @@ struct sg_table *iwl_pcie_prep_tso(struct iwl_trans *trans, struct sk_buff *skb,
 	sgt = (void *)PTR_ALIGN(*hdr + hdr_room, __alignof__(struct sg_table));
 	sgt->sgl = (void *)(sgt + 1);
 
-	sg_init_table(sgt->sgl, skb_shinfo(skb)->nr_frags + 1);
+	sg_init_table(sgt->sgl, n_segments);
 
 	/* Only map the data, not the header (it is copied to the TSO page) */
-	sgt->orig_nents = skb_to_sgvec(skb, sgt->sgl, skb_headlen(skb),
-				       skb->data_len);
-	if (WARN_ON_ONCE(sgt->orig_nents <= 0))
+	orig_nents = skb_to_sgvec(skb, sgt->sgl, offset, skb->len - offset);
+	if (WARN_ON_ONCE(orig_nents <= 0))
 		return NULL;
 
+	sgt->orig_nents = orig_nents;
+
 	/* And map the entire SKB */
 	if (dma_map_sgtable(trans->dev, sgt, DMA_TO_DEVICE, 0) < 0)
 		return NULL;
@@ -1937,7 +1941,8 @@ static int iwl_fill_data_tbs_amsdu(struct iwl_trans *trans, struct sk_buff *skb,
 		(3 + snap_ip_tcp_hdrlen + sizeof(struct ethhdr)) + iv_len;
 
 	/* Our device supports 9 segments at most, it will fit in 1 page */
-	sgt = iwl_pcie_prep_tso(trans, skb, out_meta, &start_hdr, hdr_room);
+	sgt = iwl_pcie_prep_tso(trans, skb, out_meta, &start_hdr, hdr_room,
+				snap_ip_tcp_hdrlen + hdr_len + iv_len);
 	if (!sgt)
 		return -ENOMEM;
 
diff --git a/drivers/net/wireless/intersil/p54/fwio.c b/drivers/net/wireless/intersil/p54/fwio.c
index 772084a9bd8d..3baf8ab01e22 100644
--- a/drivers/net/wireless/intersil/p54/fwio.c
+++ b/drivers/net/wireless/intersil/p54/fwio.c
@@ -231,6 +231,7 @@ int p54_download_eeprom(struct p54_common *priv, void *buf,
 
 	mutex_lock(&priv->eeprom_mutex);
 	priv->eeprom = buf;
+	priv->eeprom_slice_size = len;
 	eeprom_hdr = skb_put(skb, eeprom_hdr_size + len);
 
 	if (priv->fw_var < 0x509) {
@@ -253,6 +254,7 @@ int p54_download_eeprom(struct p54_common *priv, void *buf,
 		ret = -EBUSY;
 	}
 	priv->eeprom = NULL;
+	priv->eeprom_slice_size = 0;
 	mutex_unlock(&priv->eeprom_mutex);
 	return ret;
 }
diff --git a/drivers/net/wireless/intersil/p54/p54.h b/drivers/net/wireless/intersil/p54/p54.h
index 522656de4159..aeb5e40cc5ef 100644
--- a/drivers/net/wireless/intersil/p54/p54.h
+++ b/drivers/net/wireless/intersil/p54/p54.h
@@ -258,6 +258,7 @@ struct p54_common {
 
 	/* eeprom handling */
 	void *eeprom;
+	size_t eeprom_slice_size;
 	struct completion eeprom_comp;
 	struct mutex eeprom_mutex;
 };
diff --git a/drivers/net/wireless/intersil/p54/txrx.c b/drivers/net/wireless/intersil/p54/txrx.c
index 8414aa208655..2deb1bb54f24 100644
--- a/drivers/net/wireless/intersil/p54/txrx.c
+++ b/drivers/net/wireless/intersil/p54/txrx.c
@@ -496,14 +496,19 @@ static void p54_rx_eeprom_readback(struct p54_common *priv,
 		return ;
 
 	if (priv->fw_var >= 0x509) {
-		memcpy(priv->eeprom, eeprom->v2.data,
-		       le16_to_cpu(eeprom->v2.len));
+		if (le16_to_cpu(eeprom->v2.len) != priv->eeprom_slice_size)
+			return;
+
+		memcpy(priv->eeprom, eeprom->v2.data, priv->eeprom_slice_size);
 	} else {
-		memcpy(priv->eeprom, eeprom->v1.data,
-		       le16_to_cpu(eeprom->v1.len));
+		if (le16_to_cpu(eeprom->v1.len) != priv->eeprom_slice_size)
+			return;
+
+		memcpy(priv->eeprom, eeprom->v1.data, priv->eeprom_slice_size);
 	}
 
 	priv->eeprom = NULL;
+	priv->eeprom_slice_size = 0;
 	tmp = p54_find_and_unlink_skb(priv, hdr->req_id);
 	dev_kfree_skb_any(tmp);
 	complete(&priv->eeprom_comp);
diff --git a/drivers/net/wireless/marvell/mwifiex/util.c b/drivers/net/wireless/marvell/mwifiex/util.c
index 1f1f6280a0f2..86e20edb593b 100644
--- a/drivers/net/wireless/marvell/mwifiex/util.c
+++ b/drivers/net/wireless/marvell/mwifiex/util.c
@@ -477,7 +477,9 @@ mwifiex_process_mgmt_packet(struct mwifiex_private *priv,
 				    "auth: receive authentication from %pM\n",
 				    ieee_hdr->addr3);
 		} else {
-			if (!priv->wdev.connected)
+			if (!priv->wdev.connected ||
+			    !ether_addr_equal(ieee_hdr->addr3,
+					      priv->curr_bss_params.bss_descriptor.mac_address))
 				return 0;
 
 			if (ieee80211_is_deauth(ieee_hdr->frame_control)) {
diff --git a/drivers/net/wireless/marvell/mwl8k.c b/drivers/net/wireless/marvell/mwl8k.c
index bab9ef37a1ab..8bcb1d0dd618 100644
--- a/drivers/net/wireless/marvell/mwl8k.c
+++ b/drivers/net/wireless/marvell/mwl8k.c
@@ -1227,6 +1227,10 @@ static int rxq_refill(struct ieee80211_hw *hw, int index, int limit)
 
 		addr = dma_map_single(&priv->pdev->dev, skb->data,
 				      MWL8K_RX_MAXSZ, DMA_FROM_DEVICE);
+		if (dma_mapping_error(&priv->pdev->dev, addr)) {
+			kfree_skb(skb);
+			break;
+		}
 
 		rxq->rxd_count++;
 		rx = rxq->tail++;
diff --git a/drivers/net/wireless/mediatek/mt76/dma.c b/drivers/net/wireless/mediatek/mt76/dma.c
index 5f46d6daeaa7..8940f8bb7bb5 100644
--- a/drivers/net/wireless/mediatek/mt76/dma.c
+++ b/drivers/net/wireless/mediatek/mt76/dma.c
@@ -999,6 +999,7 @@ void mt76_dma_cleanup(struct mt76_dev *dev)
 	int i;
 
 	mt76_worker_disable(&dev->tx_worker);
+	napi_disable(&dev->tx_napi);
 	netif_napi_del(&dev->tx_napi);
 
 	for (i = 0; i < ARRAY_SIZE(dev->phys); i++) {
diff --git a/drivers/net/wireless/mediatek/mt76/eeprom.c b/drivers/net/wireless/mediatek/mt76/eeprom.c
index 0bc66cc19acd..443517d06c9f 100644
--- a/drivers/net/wireless/mediatek/mt76/eeprom.c
+++ b/drivers/net/wireless/mediatek/mt76/eeprom.c
@@ -95,6 +95,10 @@ int mt76_get_of_data_from_mtd(struct mt76_dev *dev, void *eep, int offset, int l
 
 #ifdef CONFIG_NL80211_TESTMODE
 	dev->test_mtd.name = devm_kstrdup(dev->dev, part, GFP_KERNEL);
+	if (!dev->test_mtd.name) {
+		ret = -ENOMEM;
+		goto out_put_node;
+	}
 	dev->test_mtd.offset = offset;
 #endif
 
diff --git a/drivers/net/wireless/mediatek/mt76/mac80211.c b/drivers/net/wireless/mediatek/mt76/mac80211.c
index 9d5561f44134..0ca83f1a3e3e 100644
--- a/drivers/net/wireless/mediatek/mt76/mac80211.c
+++ b/drivers/net/wireless/mediatek/mt76/mac80211.c
@@ -958,11 +958,11 @@ int mt76_set_channel(struct mt76_phy *phy, struct cfg80211_chan_def *chandef,
 
 	if (chandef->chan != phy->main_chan)
 		memset(phy->chan_state, 0, sizeof(*phy->chan_state));
-	mt76_worker_enable(&dev->tx_worker);
 
 	ret = dev->drv->set_channel(phy);
 
 	clear_bit(MT76_RESET, &phy->state);
+	mt76_worker_enable(&dev->tx_worker);
 	mt76_worker_schedule(&dev->tx_worker);
 
 	mutex_unlock(&dev->mutex);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h
index 0b75a45ad2e8..a6ac8e5512eb 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76.h
@@ -489,6 +489,7 @@ struct mt76_hw_cap {
 #define MT_DRV_RX_DMA_HDR		BIT(3)
 #define MT_DRV_HW_MGMT_TXQ		BIT(4)
 #define MT_DRV_AMSDU_OFFLOAD		BIT(5)
+#define MT_DRV_IGNORE_TXS_FAILED	BIT(6)
 
 struct mt76_driver_ops {
 	u32 drv_flags;
@@ -755,6 +756,7 @@ struct mt76_testmode_data {
 
 struct mt76_vif {
 	u8 idx;
+	u8 link_idx;
 	u8 omac_idx;
 	u8 band_idx;
 	u8 wmm_idx;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c
index 96e34277fece..1cc8fc8fefe7 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c
@@ -1113,7 +1113,7 @@ mt7615_mcu_uni_add_dev(struct mt7615_phy *phy, struct ieee80211_vif *vif,
 {
 	struct mt7615_vif *mvif = (struct mt7615_vif *)vif->drv_priv;
 
-	return mt76_connac_mcu_uni_add_dev(phy->mt76, &vif->bss_conf,
+	return mt76_connac_mcu_uni_add_dev(phy->mt76, &vif->bss_conf, &mvif->mt76,
 					   &mvif->sta.wcid, enable);
 }
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac3_mac.h b/drivers/net/wireless/mediatek/mt76/mt76_connac3_mac.h
index db0c29e65185..487ad716f872 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76_connac3_mac.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76_connac3_mac.h
@@ -314,6 +314,9 @@ enum tx_frag_idx {
 #define MT_TXFREE_INFO_COUNT		GENMASK(27, 24)
 #define MT_TXFREE_INFO_STAT		GENMASK(29, 28)
 
+#define MT_TXS_HDR_SIZE			4 /* Unit: DW */
+#define MT_TXS_SIZE			12 /* Unit: DW */
+
 #define MT_TXS0_BW			GENMASK(31, 29)
 #define MT_TXS0_TID			GENMASK(28, 26)
 #define MT_TXS0_AMPDU			BIT(25)
diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c
index 864246f94088..a6324f6ead78 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c
@@ -1137,10 +1137,10 @@ EXPORT_SYMBOL_GPL(mt76_connac_mcu_wtbl_ba_tlv);
 
 int mt76_connac_mcu_uni_add_dev(struct mt76_phy *phy,
 				struct ieee80211_bss_conf *bss_conf,
+				struct mt76_vif *mvif,
 				struct mt76_wcid *wcid,
 				bool enable)
 {
-	struct mt76_vif *mvif = (struct mt76_vif *)bss_conf->vif->drv_priv;
 	struct mt76_dev *dev = phy->dev;
 	struct {
 		struct {
@@ -1164,7 +1164,7 @@ int mt76_connac_mcu_uni_add_dev(struct mt76_phy *phy,
 			.tag = cpu_to_le16(DEV_INFO_ACTIVE),
 			.len = cpu_to_le16(sizeof(struct req_tlv)),
 			.active = enable,
-			.link_idx = mvif->idx,
+			.link_idx = mvif->link_idx,
 		},
 	};
 	struct {
@@ -1187,7 +1187,7 @@ int mt76_connac_mcu_uni_add_dev(struct mt76_phy *phy,
 			.bmc_tx_wlan_idx = cpu_to_le16(wcid->idx),
 			.sta_idx = cpu_to_le16(wcid->idx),
 			.conn_state = 1,
-			.link_idx = mvif->idx,
+			.link_idx = mvif->link_idx,
 		},
 	};
 	int err, idx, cmd, len;
@@ -1696,8 +1696,8 @@ int mt76_connac_mcu_hw_scan(struct mt76_phy *phy, struct ieee80211_vif *vif,
 		if (!sreq->ssids[i].ssid_len)
 			continue;
 
-		req->ssids[i].ssid_len = cpu_to_le32(sreq->ssids[i].ssid_len);
-		memcpy(req->ssids[i].ssid, sreq->ssids[i].ssid,
+		req->ssids[n_ssids].ssid_len = cpu_to_le32(sreq->ssids[i].ssid_len);
+		memcpy(req->ssids[n_ssids].ssid, sreq->ssids[i].ssid,
 		       sreq->ssids[i].ssid_len);
 		n_ssids++;
 	}
diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h
index 1b0e80dfc346..57a8340fa700 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h
@@ -1938,6 +1938,7 @@ void mt76_connac_mcu_sta_ba_tlv(struct sk_buff *skb,
 				bool enable, bool tx);
 int mt76_connac_mcu_uni_add_dev(struct mt76_phy *phy,
 				struct ieee80211_bss_conf *bss_conf,
+				struct mt76_vif *mvif,
 				struct mt76_wcid *wcid,
 				bool enable);
 int mt76_connac_mcu_sta_ba(struct mt76_dev *dev, struct mt76_vif *mvif,
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c b/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
index 1eb955f3ca13..911e162a4598 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
@@ -156,7 +156,8 @@ mt76x0e_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	static const struct mt76_driver_ops drv_ops = {
 		.txwi_size = sizeof(struct mt76x02_txwi),
 		.drv_flags = MT_DRV_TX_ALIGNED4_SKBS |
-			     MT_DRV_SW_RX_AIRTIME,
+			     MT_DRV_SW_RX_AIRTIME |
+			     MT_DRV_IGNORE_TXS_FAILED,
 		.survey_flags = SURVEY_INFO_TIME_TX,
 		.update_survey = mt76x02_update_channel,
 		.set_channel = mt76x0_set_channel,
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c b/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
index b031c500b741..90e5666c0857 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
@@ -214,7 +214,8 @@ static int mt76x0u_probe(struct usb_interface *usb_intf,
 			 const struct usb_device_id *id)
 {
 	static const struct mt76_driver_ops drv_ops = {
-		.drv_flags = MT_DRV_SW_RX_AIRTIME,
+		.drv_flags = MT_DRV_SW_RX_AIRTIME |
+			     MT_DRV_IGNORE_TXS_FAILED,
 		.survey_flags = SURVEY_INFO_TIME_TX,
 		.update_survey = mt76x02_update_channel,
 		.set_channel = mt76x0_set_channel,
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c
index 67c9d1caa0bd..55f076231bdc 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c
@@ -22,7 +22,8 @@ mt76x2e_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	static const struct mt76_driver_ops drv_ops = {
 		.txwi_size = sizeof(struct mt76x02_txwi),
 		.drv_flags = MT_DRV_TX_ALIGNED4_SKBS |
-			     MT_DRV_SW_RX_AIRTIME,
+			     MT_DRV_SW_RX_AIRTIME |
+			     MT_DRV_IGNORE_TXS_FAILED,
 		.survey_flags = SURVEY_INFO_TIME_TX,
 		.update_survey = mt76x02_update_channel,
 		.set_channel = mt76x2e_set_channel,
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c b/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c
index e832ad53e239..96cecc576a98 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c
@@ -17,11 +17,14 @@ static const struct usb_device_id mt76x2u_device_table[] = {
 	{ USB_DEVICE(0x057c, 0x8503) },	/* Avm FRITZ!WLAN AC860 */
 	{ USB_DEVICE(0x7392, 0xb711) },	/* Edimax EW 7722 UAC */
 	{ USB_DEVICE(0x0e8d, 0x7632) },	/* HC-M7662BU1 */
+	{ USB_DEVICE(0x0471, 0x2126) }, /* LiteOn WN4516R module, nonstandard USB connector */
+	{ USB_DEVICE(0x0471, 0x7600) }, /* LiteOn WN4519R module, nonstandard USB connector */
 	{ USB_DEVICE(0x2c4e, 0x0103) },	/* Mercury UD13 */
 	{ USB_DEVICE(0x0846, 0x9014) },	/* Netgear WNDA3100v3 */
 	{ USB_DEVICE(0x0846, 0x9053) },	/* Netgear A6210 */
 	{ USB_DEVICE(0x045e, 0x02e6) },	/* XBox One Wireless Adapter */
 	{ USB_DEVICE(0x045e, 0x02fe) },	/* XBox One Wireless Adapter */
+	{ USB_DEVICE(0x2357, 0x0137) },	/* TP-Link TL-WDN6200 */
 	{ },
 };
 
@@ -29,7 +32,8 @@ static int mt76x2u_probe(struct usb_interface *intf,
 			 const struct usb_device_id *id)
 {
 	static const struct mt76_driver_ops drv_ops = {
-		.drv_flags = MT_DRV_SW_RX_AIRTIME,
+		.drv_flags = MT_DRV_SW_RX_AIRTIME |
+			     MT_DRV_IGNORE_TXS_FAILED,
 		.survey_flags = SURVEY_INFO_TIME_TX,
 		.update_survey = mt76x02_update_channel,
 		.set_channel = mt76x2u_set_channel,
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/usb_init.c b/drivers/net/wireless/mediatek/mt76/mt76x2/usb_init.c
index 33a14365ec9b..3b5562811511 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/usb_init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/usb_init.c
@@ -191,6 +191,7 @@ int mt76x2u_register_device(struct mt76x02_dev *dev)
 {
 	struct ieee80211_hw *hw = mt76_hw(dev);
 	struct mt76_usb *usb = &dev->mt76.usb;
+	bool vht;
 	int err;
 
 	INIT_DELAYED_WORK(&dev->cal_work, mt76x2u_phy_calibrate);
@@ -217,7 +218,17 @@ int mt76x2u_register_device(struct mt76x02_dev *dev)
 
 	/* check hw sg support in order to enable AMSDU */
 	hw->max_tx_fragments = dev->mt76.usb.sg_en ? MT_TX_SG_MAX_SIZE : 1;
-	err = mt76_register_device(&dev->mt76, true, mt76x02_rates,
+	switch (dev->mt76.rev) {
+	case 0x76320044:
+		/* these ASIC revisions do not support VHT */
+		vht = false;
+		break;
+	default:
+		vht = true;
+		break;
+	}
+
+	err = mt76_register_device(&dev->mt76, vht, mt76x02_rates,
 				   ARRAY_SIZE(mt76x02_rates));
 	if (err)
 		goto fail;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/eeprom.c b/drivers/net/wireless/mediatek/mt76/mt7915/eeprom.c
index bfdbc15abaa9..928e0b07a9bf 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/eeprom.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/eeprom.c
@@ -2,9 +2,14 @@
 /* Copyright (C) 2020 MediaTek Inc. */
 
 #include <linux/firmware.h>
+#include <linux/moduleparam.h>
 #include "mt7915.h"
 #include "eeprom.h"
 
+static bool enable_6ghz;
+module_param(enable_6ghz, bool, 0644);
+MODULE_PARM_DESC(enable_6ghz, "Enable 6 GHz instead of 5 GHz on hardware that supports both");
+
 static int mt7915_eeprom_load_precal(struct mt7915_dev *dev)
 {
 	struct mt76_dev *mdev = &dev->mt76;
@@ -170,8 +175,20 @@ static void mt7915_eeprom_parse_band_config(struct mt7915_phy *phy)
 			phy->mt76->cap.has_6ghz = true;
 			return;
 		case MT_EE_V2_BAND_SEL_5GHZ_6GHZ:
-			phy->mt76->cap.has_5ghz = true;
-			phy->mt76->cap.has_6ghz = true;
+			if (enable_6ghz) {
+				phy->mt76->cap.has_6ghz = true;
+				u8p_replace_bits(&eeprom[MT_EE_WIFI_CONF + band],
+						 MT_EE_V2_BAND_SEL_6GHZ,
+						 MT_EE_WIFI_CONF0_BAND_SEL);
+			} else {
+				phy->mt76->cap.has_5ghz = true;
+				u8p_replace_bits(&eeprom[MT_EE_WIFI_CONF + band],
+						 MT_EE_V2_BAND_SEL_5GHZ,
+						 MT_EE_WIFI_CONF0_BAND_SEL);
+			}
+			/* force to buffer mode */
+			dev->flash_mode = true;
+
 			return;
 		default:
 			phy->mt76->cap.has_2ghz = true;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/init.c b/drivers/net/wireless/mediatek/mt76/mt7915/init.c
index 6bef96e3d2a3..bc983ab10b0c 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/init.c
@@ -82,7 +82,7 @@ static ssize_t mt7915_thermal_temp_store(struct device *dev,
 		return ret;
 
 	mutex_lock(&phy->dev->mt76.mutex);
-	val = clamp_val(DIV_ROUND_CLOSEST(val, 1000), 60, 130);
+	val = DIV_ROUND_CLOSEST(clamp_val(val, 60 * 1000, 130 * 1000), 1000);
 
 	if ((i - 1 == MT7915_CRIT_TEMP_IDX &&
 	     val > phy->throttle_temp[MT7915_MAX_TEMP_IDX]) ||
@@ -1239,14 +1239,14 @@ int mt7915_register_device(struct mt7915_dev *dev)
 	if (ret)
 		goto unreg_dev;
 
-	ieee80211_queue_work(mt76_hw(dev), &dev->init_work);
-
 	if (phy2) {
 		ret = mt7915_register_ext_phy(dev, phy2);
 		if (ret)
 			goto unreg_thermal;
 	}
 
+	ieee80211_queue_work(mt76_hw(dev), &dev->init_work);
+
 	dev->recovery.hw_init_done = true;
 
 	ret = mt7915_init_debugfs(&dev->phy);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
index cf77ce0c8759..799e8d2cc7e6 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
@@ -1388,6 +1388,8 @@ mt7915_mac_restart(struct mt7915_dev *dev)
 	if (dev_is_pci(mdev->dev)) {
 		mt76_wr(dev, MT_PCIE_MAC_INT_ENABLE, 0xff);
 		if (dev->hif2) {
+			mt76_wr(dev, MT_PCIE_RECOG_ID,
+				dev->hif2->index | MT_PCIE_RECOG_ID_SEM);
 			if (is_mt7915(mdev))
 				mt76_wr(dev, MT_PCIE1_MAC_INT_ENABLE, 0xff);
 			else
@@ -1442,9 +1444,11 @@ static void
 mt7915_mac_full_reset(struct mt7915_dev *dev)
 {
 	struct mt76_phy *ext_phy;
+	struct mt7915_phy *phy2;
 	int i;
 
 	ext_phy = dev->mt76.phys[MT_BAND1];
+	phy2 = ext_phy ? ext_phy->priv : NULL;
 
 	dev->recovery.hw_full_reset = true;
 
@@ -1474,6 +1478,9 @@ mt7915_mac_full_reset(struct mt7915_dev *dev)
 
 	memset(dev->mt76.wcid_mask, 0, sizeof(dev->mt76.wcid_mask));
 	dev->mt76.vif_mask = 0;
+	dev->phy.omac_mask = 0;
+	if (phy2)
+		phy2->omac_mask = 0;
 
 	i = mt76_wcid_alloc(dev->mt76.wcid_mask, MT7915_WTBL_STA);
 	dev->mt76.global_wcid.idx = i;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/main.c b/drivers/net/wireless/mediatek/mt76/mt7915/main.c
index d75e8dea1fbd..8c0d63cebf3e 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/main.c
@@ -246,8 +246,10 @@ static int mt7915_add_interface(struct ieee80211_hw *hw,
 	phy->omac_mask |= BIT_ULL(mvif->mt76.omac_idx);
 
 	idx = mt76_wcid_alloc(dev->mt76.wcid_mask, mt7915_wtbl_size(dev));
-	if (idx < 0)
-		return -ENOSPC;
+	if (idx < 0) {
+		ret = -ENOSPC;
+		goto out;
+	}
 
 	INIT_LIST_HEAD(&mvif->sta.rc_list);
 	INIT_LIST_HEAD(&mvif->sta.wcid.poll_list);
@@ -619,8 +621,9 @@ static void mt7915_bss_info_changed(struct ieee80211_hw *hw,
 	if (changed & BSS_CHANGED_ASSOC)
 		set_bss_info = vif->cfg.assoc;
 	if (changed & BSS_CHANGED_BEACON_ENABLED &&
+	    info->enable_beacon &&
 	    vif->type != NL80211_IFTYPE_AP)
-		set_bss_info = set_sta = info->enable_beacon;
+		set_bss_info = set_sta = 1;
 
 	if (set_bss_info == 1)
 		mt7915_mcu_add_bss_info(phy, vif, true);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
index 87d0dd040001..3398c25cb03c 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
@@ -2071,16 +2071,21 @@ static int mt7915_load_firmware(struct mt7915_dev *dev)
 {
 	int ret;
 
-	/* make sure fw is download state */
-	if (mt7915_firmware_state(dev, false)) {
-		/* restart firmware once */
-		mt76_connac_mcu_restart(&dev->mt76);
-		ret = mt7915_firmware_state(dev, false);
-		if (ret) {
-			dev_err(dev->mt76.dev,
-				"Firmware is not ready for download\n");
-			return ret;
-		}
+	/* Release Semaphore if taken by previous failed attempt */
+	ret = mt76_connac_mcu_patch_sem_ctrl(&dev->mt76, false);
+	if (ret != PATCH_REL_SEM_SUCCESS) {
+		dev_err(dev->mt76.dev, "Could not release semaphore\n");
+		/* Continue anyways */
+	}
+
+	/* Always restart MCU firmware */
+	mt76_connac_mcu_restart(&dev->mt76);
+
+	/* Check if MCU is ready */
+	ret = mt7915_firmware_state(dev, false);
+	if (ret) {
+		dev_err(dev->mt76.dev, "Firmware did not enter download state\n");
+		return ret;
 	}
 
 	ret = mt76_connac2_load_patch(&dev->mt76, fw_name_var(dev, ROM_PATCH));
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c b/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c
index 44e112b8b5b3..a6245c3ccef4 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c
@@ -484,7 +484,7 @@ static u32 __mt7915_reg_addr(struct mt7915_dev *dev, u32 addr)
 			continue;
 
 		ofs = addr - dev->reg.map[i].phys;
-		if (ofs > dev->reg.map[i].size)
+		if (ofs >= dev->reg.map[i].size)
 			continue;
 
 		return dev->reg.map[i].maps + ofs;
@@ -649,6 +649,9 @@ int mt7915_mmio_wed_init(struct mt7915_dev *dev, void *pdev_ptr,
 		wed->wlan.base = devm_ioremap(dev->mt76.dev,
 					      pci_resource_start(pci_dev, 0),
 					      pci_resource_len(pci_dev, 0));
+		if (!wed->wlan.base)
+			return -ENOMEM;
+
 		wed->wlan.phy_base = pci_resource_start(pci_dev, 0);
 		wed->wlan.wpdma_int = pci_resource_start(pci_dev, 0) +
 				      MT_INT_WED_SOURCE_CSR;
@@ -676,6 +679,9 @@ int mt7915_mmio_wed_init(struct mt7915_dev *dev, void *pdev_ptr,
 		wed->wlan.bus_type = MTK_WED_BUS_AXI;
 		wed->wlan.base = devm_ioremap(dev->mt76.dev, res->start,
 					      resource_size(res));
+		if (!wed->wlan.base)
+			return -ENOMEM;
+
 		wed->wlan.phy_base = res->start;
 		wed->wlan.wpdma_int = res->start + MT_INT_SOURCE_CSR;
 		wed->wlan.wpdma_mask = res->start + MT_INT_MASK_CSR;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h b/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h
index ac0b1f0eb27c..5fe872ef2e93 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h
@@ -191,6 +191,7 @@ struct mt7915_hif {
 	struct device *dev;
 	void __iomem *regs;
 	int irq;
+	u32 index;
 };
 
 struct mt7915_phy {
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/pci.c b/drivers/net/wireless/mediatek/mt76/mt7915/pci.c
index 39132894e8ea..07b0a5766eab 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/pci.c
@@ -42,6 +42,7 @@ static struct mt7915_hif *mt7915_pci_get_hif2(u32 idx)
 			continue;
 
 		get_device(hif->dev);
+		hif->index = idx;
 		goto out;
 	}
 	hif = NULL;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
index 047106b65d2b..bd1455698ebe 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
@@ -647,6 +647,7 @@ mt7921_vif_connect_iter(void *priv, u8 *mac,
 		ieee80211_disconnect(vif, true);
 
 	mt76_connac_mcu_uni_add_dev(&dev->mphy, &vif->bss_conf,
+				    &mvif->bss_conf.mt76,
 				    &mvif->sta.deflink.wcid, true);
 	mt7921_mcu_set_tx(dev, vif);
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/main.c b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
index a7f5bfbc02ed..5b832f1aa00d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
@@ -83,6 +83,11 @@ mt7921_init_he_caps(struct mt792x_phy *phy, enum nl80211_band band,
 			he_cap_elem->phy_cap_info[9] |=
 				IEEE80211_HE_PHY_CAP9_TX_1024_QAM_LESS_THAN_242_TONE_RU |
 				IEEE80211_HE_PHY_CAP9_RX_1024_QAM_LESS_THAN_242_TONE_RU;
+
+			if (is_mt7922(phy->mt76->dev)) {
+				he_cap_elem->phy_cap_info[0] |=
+					IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G;
+			}
 			break;
 		case NL80211_IFTYPE_STATION:
 			he_cap_elem->mac_cap_info[1] |=
@@ -308,6 +313,7 @@ mt7921_add_interface(struct ieee80211_hw *hw, struct ieee80211_vif *vif)
 	mvif->bss_conf.mt76.wmm_idx = mvif->bss_conf.mt76.idx % MT76_CONNAC_MAX_WMM_SETS;
 
 	ret = mt76_connac_mcu_uni_add_dev(&dev->mphy, &vif->bss_conf,
+					  &mvif->bss_conf.mt76,
 					  &mvif->sta.deflink.wcid, true);
 	if (ret)
 		goto out;
@@ -531,7 +537,13 @@ static int mt7921_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 	} else {
 		if (idx == *wcid_keyidx)
 			*wcid_keyidx = -1;
-		goto out;
+
+		/* For security issue we don't trigger the key deletion when
+		 * reassociating. But we should trigger the deletion process
+		 * to avoid using incorrect cipher after disconnection,
+		 */
+		if (vif->type != NL80211_IFTYPE_STATION || vif->cfg.assoc)
+			goto out;
 	}
 
 	mt76_wcid_key_setup(&dev->mt76, wcid, key);
@@ -798,6 +810,7 @@ int mt7921_mac_sta_add(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 	msta->deflink.wcid.phy_idx = mvif->bss_conf.mt76.band_idx;
 	msta->deflink.wcid.tx_info |= MT_WCID_TX_INFO_SET;
 	msta->deflink.last_txs = jiffies;
+	msta->deflink.sta = msta;
 
 	ret = mt76_connac_pm_wake(&dev->mphy, &dev->pm);
 	if (ret)
@@ -1160,6 +1173,9 @@ static void mt7921_sta_set_decap_offload(struct ieee80211_hw *hw,
 	struct mt792x_sta *msta = (struct mt792x_sta *)sta->drv_priv;
 	struct mt792x_dev *dev = mt792x_hw_dev(hw);
 
+	if (!msta->deflink.wcid.sta)
+		return;
+
 	mt792x_mutex_acquire(dev);
 
 	if (enabled)
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/usb.c b/drivers/net/wireless/mediatek/mt76/mt7921/usb.c
index 8aa4f0203208..e3459295ad88 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/usb.c
@@ -21,6 +21,9 @@ static const struct usb_device_id mt7921u_device_table[] = {
 	/* Netgear, Inc. [A8000,AXE3000] */
 	{ USB_DEVICE_AND_INTERFACE_INFO(0x0846, 0x9060, 0xff, 0xff, 0xff),
 		.driver_info = (kernel_ulong_t)MT7921_FIRMWARE_WM },
+	/* TP-Link TXE50UH */
+	{ USB_DEVICE_AND_INTERFACE_INFO(0x35bc, 0x0107, 0xff, 0xff, 0xff),
+		.driver_info = (kernel_ulong_t)MT7921_FIRMWARE_WM },
 	{ },
 };
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/init.c b/drivers/net/wireless/mediatek/mt76/mt7925/init.c
index 039949b344b9..02899320da5c 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/init.c
@@ -52,6 +52,8 @@ static int mt7925_thermal_init(struct mt792x_phy *phy)
 
 	name = devm_kasprintf(&wiphy->dev, GFP_KERNEL, "mt7925_%s",
 			      wiphy_name(wiphy));
+	if (!name)
+		return -ENOMEM;
 
 	hwmon = devm_hwmon_device_register_with_groups(&wiphy->dev, name, phy,
 						       mt7925_hwmon_groups);
@@ -204,6 +206,12 @@ static void mt7925_init_work(struct work_struct *work)
 		return;
 	}
 
+	ret = mt7925_mcu_set_thermal_protect(dev);
+	if (ret) {
+		dev_err(dev->mt76.dev, "thermal protection enable failed\n");
+		return;
+	}
+
 	/* we support chip reset now */
 	dev->hw_init_done = true;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mac.c b/drivers/net/wireless/mediatek/mt76/mt7925/mac.c
index 634c42bbf23f..a095fb31e391 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/mac.c
@@ -49,7 +49,7 @@ static void mt7925_mac_sta_poll(struct mt792x_dev *dev)
 			break;
 		mlink = list_first_entry(&sta_poll_list,
 					 struct mt792x_link_sta, wcid.poll_list);
-		msta = container_of(mlink, struct mt792x_sta, deflink);
+		msta = mlink->sta;
 		spin_lock_bh(&dev->mt76.sta_poll_lock);
 		list_del_init(&mlink->wcid.poll_list);
 		spin_unlock_bh(&dev->mt76.sta_poll_lock);
@@ -1271,6 +1271,7 @@ mt7925_vif_connect_iter(void *priv, u8 *mac,
 	struct mt792x_dev *dev = mvif->phy->dev;
 	struct ieee80211_hw *hw = mt76_hw(dev);
 	struct ieee80211_bss_conf *bss_conf;
+	struct mt792x_bss_conf *mconf;
 	int i;
 
 	if (vif->type == NL80211_IFTYPE_STATION)
@@ -1278,8 +1279,9 @@ mt7925_vif_connect_iter(void *priv, u8 *mac,
 
 	for_each_set_bit(i, &valid, IEEE80211_MLD_MAX_NUM_LINKS) {
 		bss_conf = mt792x_vif_to_bss_conf(vif, i);
+		mconf = mt792x_vif_to_link(mvif, i);
 
-		mt76_connac_mcu_uni_add_dev(&dev->mphy, bss_conf,
+		mt76_connac_mcu_uni_add_dev(&dev->mphy, bss_conf, &mconf->mt76,
 					    &mvif->sta.deflink.wcid, true);
 		mt7925_mcu_set_tx(dev, bss_conf);
 	}
diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/main.c b/drivers/net/wireless/mediatek/mt76/mt7925/main.c
index 791c8b00e112..a635b223dab1 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/main.c
@@ -256,7 +256,7 @@ int mt7925_init_mlo_caps(struct mt792x_phy *phy)
 
 	ext_capab[0].eml_capabilities = phy->eml_cap;
 	ext_capab[0].mld_capa_and_ops =
-		u16_encode_bits(1, IEEE80211_MLD_CAP_OP_MAX_SIMUL_LINKS);
+		u16_encode_bits(0, IEEE80211_MLD_CAP_OP_MAX_SIMUL_LINKS);
 
 	wiphy->flags |= WIPHY_FLAG_SUPPORTS_MLO;
 	wiphy->iftype_ext_capab = ext_capab;
@@ -356,27 +356,29 @@ static int mt7925_mac_link_bss_add(struct mt792x_dev *dev,
 	struct mt76_txq *mtxq;
 	int idx, ret = 0;
 
-	mconf->mt76.idx = __ffs64(~dev->mt76.vif_mask);
-	if (mconf->mt76.idx >= MT792x_MAX_INTERFACES) {
-		ret = -ENOSPC;
-		goto out;
+	if (vif->type == NL80211_IFTYPE_P2P_DEVICE) {
+		mconf->mt76.idx = MT792x_MAX_INTERFACES;
+	} else {
+		mconf->mt76.idx = __ffs64(~dev->mt76.vif_mask);
+
+		if (mconf->mt76.idx >= MT792x_MAX_INTERFACES) {
+			ret = -ENOSPC;
+			goto out;
+		}
 	}
 
 	mconf->mt76.omac_idx = ieee80211_vif_is_mld(vif) ?
 			       0 : mconf->mt76.idx;
 	mconf->mt76.band_idx = 0xff;
-	mconf->mt76.wmm_idx = mconf->mt76.idx % MT76_CONNAC_MAX_WMM_SETS;
+	mconf->mt76.wmm_idx = ieee80211_vif_is_mld(vif) ?
+			      0 : mconf->mt76.idx % MT76_CONNAC_MAX_WMM_SETS;
+	mconf->mt76.link_idx = hweight16(mvif->valid_links);
 
 	if (mvif->phy->mt76->chandef.chan->band != NL80211_BAND_2GHZ)
 		mconf->mt76.basic_rates_idx = MT792x_BASIC_RATES_TBL + 4;
 	else
 		mconf->mt76.basic_rates_idx = MT792x_BASIC_RATES_TBL;
 
-	ret = mt76_connac_mcu_uni_add_dev(&dev->mphy, link_conf,
-					  &mlink->wcid, true);
-	if (ret)
-		goto out;
-
 	dev->mt76.vif_mask |= BIT_ULL(mconf->mt76.idx);
 	mvif->phy->omac_mask |= BIT_ULL(mconf->mt76.omac_idx);
 
@@ -384,7 +386,7 @@ static int mt7925_mac_link_bss_add(struct mt792x_dev *dev,
 
 	INIT_LIST_HEAD(&mlink->wcid.poll_list);
 	mlink->wcid.idx = idx;
-	mlink->wcid.phy_idx = mconf->mt76.band_idx;
+	mlink->wcid.phy_idx = 0;
 	mlink->wcid.hw_key_idx = -1;
 	mlink->wcid.tx_info |= MT_WCID_TX_INFO_SET;
 	mt76_wcid_init(&mlink->wcid);
@@ -395,6 +397,12 @@ static int mt7925_mac_link_bss_add(struct mt792x_dev *dev,
 	ewma_rssi_init(&mconf->rssi);
 
 	rcu_assign_pointer(dev->mt76.wcid[idx], &mlink->wcid);
+
+	ret = mt76_connac_mcu_uni_add_dev(&dev->mphy, link_conf, &mconf->mt76,
+					  &mlink->wcid, true);
+	if (ret)
+		goto out;
+
 	if (vif->txq) {
 		mtxq = (struct mt76_txq *)vif->txq->drv_priv;
 		mtxq->wcid = idx;
@@ -837,6 +845,7 @@ static int mt7925_mac_link_sta_add(struct mt76_dev *mdev,
 	u8 link_id = link_sta->link_id;
 	struct mt792x_link_sta *mlink;
 	struct mt792x_sta *msta;
+	struct mt76_wcid *wcid;
 	int ret, idx;
 
 	msta = (struct mt792x_sta *)link_sta->sta->drv_priv;
@@ -850,11 +859,20 @@ static int mt7925_mac_link_sta_add(struct mt76_dev *mdev,
 	INIT_LIST_HEAD(&mlink->wcid.poll_list);
 	mlink->wcid.sta = 1;
 	mlink->wcid.idx = idx;
-	mlink->wcid.phy_idx = mconf->mt76.band_idx;
+	mlink->wcid.phy_idx = 0;
 	mlink->wcid.tx_info |= MT_WCID_TX_INFO_SET;
 	mlink->last_txs = jiffies;
 	mlink->wcid.link_id = link_sta->link_id;
 	mlink->wcid.link_valid = !!link_sta->sta->valid_links;
+	mlink->sta = msta;
+
+	wcid = &mlink->wcid;
+	ewma_signal_init(&wcid->rssi);
+	rcu_assign_pointer(dev->mt76.wcid[wcid->idx], wcid);
+	mt76_wcid_init(wcid);
+	ewma_avg_signal_init(&mlink->avg_ack_signal);
+	memset(mlink->airtime_ac, 0,
+	       sizeof(msta->deflink.airtime_ac));
 
 	ret = mt76_connac_pm_wake(&dev->mphy, &dev->pm);
 	if (ret)
@@ -866,9 +884,14 @@ static int mt7925_mac_link_sta_add(struct mt76_dev *mdev,
 	link_conf = mt792x_vif_to_bss_conf(vif, link_id);
 
 	/* should update bss info before STA add */
-	if (vif->type == NL80211_IFTYPE_STATION && !link_sta->sta->tdls)
-		mt7925_mcu_add_bss_info(&dev->phy, mconf->mt76.ctx,
-					link_conf, link_sta, false);
+	if (vif->type == NL80211_IFTYPE_STATION && !link_sta->sta->tdls) {
+		if (ieee80211_vif_is_mld(vif))
+			mt7925_mcu_add_bss_info(&dev->phy, mconf->mt76.ctx,
+						link_conf, link_sta, link_sta != mlink->pri_link);
+		else
+			mt7925_mcu_add_bss_info(&dev->phy, mconf->mt76.ctx,
+						link_conf, link_sta, false);
+	}
 
 	if (ieee80211_vif_is_mld(vif) &&
 	    link_sta == mlink->pri_link) {
@@ -904,7 +927,6 @@ mt7925_mac_sta_add_links(struct mt792x_dev *dev, struct ieee80211_vif *vif,
 			 struct ieee80211_sta *sta, unsigned long new_links)
 {
 	struct mt792x_sta *msta = (struct mt792x_sta *)sta->drv_priv;
-	struct mt76_wcid *wcid;
 	unsigned int link_id;
 	int err = 0;
 
@@ -921,14 +943,6 @@ mt7925_mac_sta_add_links(struct mt792x_dev *dev, struct ieee80211_vif *vif,
 				err = -ENOMEM;
 				break;
 			}
-
-			wcid = &mlink->wcid;
-			ewma_signal_init(&wcid->rssi);
-			rcu_assign_pointer(dev->mt76.wcid[wcid->idx], wcid);
-			mt76_wcid_init(wcid);
-			ewma_avg_signal_init(&mlink->avg_ack_signal);
-			memset(mlink->airtime_ac, 0,
-			       sizeof(msta->deflink.airtime_ac));
 		}
 
 		msta->valid_links |= BIT(link_id);
@@ -1141,8 +1155,12 @@ static void mt7925_mac_link_sta_remove(struct mt76_dev *mdev,
 		struct mt792x_bss_conf *mconf;
 
 		mconf = mt792x_link_conf_to_mconf(link_conf);
-		mt7925_mcu_add_bss_info(&dev->phy, mconf->mt76.ctx, link_conf,
-					link_sta, false);
+
+		if (ieee80211_vif_is_mld(vif))
+			mt792x_mac_link_bss_remove(dev, mconf, mlink);
+		else
+			mt7925_mcu_add_bss_info(&dev->phy, mconf->mt76.ctx, link_conf,
+						link_sta, false);
 	}
 
 	spin_lock_bh(&mdev->sta_poll_lock);
@@ -1162,6 +1180,31 @@ mt7925_mac_sta_remove_links(struct mt792x_dev *dev, struct ieee80211_vif *vif,
 	struct mt76_wcid *wcid;
 	unsigned int link_id;
 
+	/* clean up bss before starec */
+	for_each_set_bit(link_id, &old_links, IEEE80211_MLD_MAX_NUM_LINKS) {
+		struct ieee80211_link_sta *link_sta;
+		struct ieee80211_bss_conf *link_conf;
+		struct mt792x_bss_conf *mconf;
+		struct mt792x_link_sta *mlink;
+
+		link_sta = mt792x_sta_to_link_sta(vif, sta, link_id);
+		if (!link_sta)
+			continue;
+
+		mlink = mt792x_sta_to_link(msta, link_id);
+		if (!mlink)
+			continue;
+
+		link_conf = mt792x_vif_to_bss_conf(vif, link_id);
+		if (!link_conf)
+			continue;
+
+		mconf = mt792x_link_conf_to_mconf(link_conf);
+
+		mt7925_mcu_add_bss_info(&dev->phy, mconf->mt76.ctx, link_conf,
+					link_sta, false);
+	}
+
 	for_each_set_bit(link_id, &old_links, IEEE80211_MLD_MAX_NUM_LINKS) {
 		struct ieee80211_link_sta *link_sta;
 		struct mt792x_link_sta *mlink;
@@ -1206,6 +1249,9 @@ void mt7925_mac_sta_remove(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 
 	mt7925_mac_sta_remove_links(dev, vif, sta, rem);
 
+	if (ieee80211_vif_is_mld(vif))
+		mt7925_mcu_del_dev(mdev, vif);
+
 	if (vif->type == NL80211_IFTYPE_STATION) {
 		struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
 
@@ -1519,6 +1565,9 @@ static void mt7925_sta_set_decap_offload(struct ieee80211_hw *hw,
 	unsigned long valid = mvif->valid_links;
 	u8 i;
 
+	if (!msta->vif)
+		return;
+
 	mt792x_mutex_acquire(dev);
 
 	valid = ieee80211_vif_is_mld(vif) ? mvif->valid_links : BIT(0);
@@ -1533,6 +1582,9 @@ static void mt7925_sta_set_decap_offload(struct ieee80211_hw *hw,
 		else
 			clear_bit(MT_WCID_FLAG_HDR_TRANS, &mlink->wcid.flags);
 
+		if (!mlink->wcid.sta)
+			continue;
+
 		mt7925_mcu_wtbl_update_hdr_trans(dev, vif, sta, i);
 	}
 
@@ -1895,6 +1947,13 @@ static void mt7925_link_info_changed(struct ieee80211_hw *hw,
 	if (changed & (BSS_CHANGED_QOS | BSS_CHANGED_BEACON_ENABLED))
 		mt7925_mcu_set_tx(dev, info);
 
+	if (changed & BSS_CHANGED_BSSID) {
+		if (ieee80211_vif_is_mld(vif) &&
+		    hweight16(mvif->valid_links) == 2)
+			/* Indicate the secondary setup done */
+			mt7925_mcu_uni_bss_bcnft(dev, info, true);
+	}
+
 	mt792x_mutex_release(dev);
 }
 
@@ -1946,6 +2005,8 @@ mt7925_change_vif_links(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 					     GFP_KERNEL);
 			mlink = devm_kzalloc(dev->mt76.dev, sizeof(*mlink),
 					     GFP_KERNEL);
+			if (!mconf || !mlink)
+				return -ENOMEM;
 		}
 
 		mconfs[link_id] = mconf;
@@ -1974,6 +2035,8 @@ mt7925_change_vif_links(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 			goto free;
 
 		if (mconf != &mvif->bss_conf) {
+			mt7925_mcu_set_bss_pm(dev, link_conf, true);
+
 			err = mt7925_set_mlo_roc(phy, &mvif->bss_conf,
 						 vif->active_links);
 			if (err < 0)
@@ -2071,18 +2134,16 @@ static void mt7925_unassign_vif_chanctx(struct ieee80211_hw *hw,
 	struct mt792x_chanctx *mctx = (struct mt792x_chanctx *)ctx->drv_priv;
 	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
 	struct mt792x_dev *dev = mt792x_hw_dev(hw);
-	struct ieee80211_bss_conf *pri_link_conf;
 	struct mt792x_bss_conf *mconf;
 
 	mutex_lock(&dev->mt76.mutex);
 
 	if (ieee80211_vif_is_mld(vif)) {
 		mconf = mt792x_vif_to_link(mvif, link_conf->link_id);
-		pri_link_conf = mt792x_vif_to_bss_conf(vif, mvif->deflink_id);
 
 		if (vif->type == NL80211_IFTYPE_STATION &&
 		    mconf == &mvif->bss_conf)
-			mt7925_mcu_add_bss_info(&dev->phy, NULL, pri_link_conf,
+			mt7925_mcu_add_bss_info(&dev->phy, NULL, link_conf,
 						NULL, false);
 	} else {
 		mconf = &mvif->bss_conf;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
index 748ea6adbc6b..e42b4f0abbe7 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
@@ -123,10 +123,8 @@ EXPORT_SYMBOL_GPL(mt7925_mcu_regval);
 int mt7925_mcu_update_arp_filter(struct mt76_dev *dev,
 				 struct ieee80211_bss_conf *link_conf)
 {
-	struct ieee80211_vif *mvif = container_of((void *)link_conf->vif,
-						  struct ieee80211_vif,
-						  drv_priv);
 	struct mt792x_bss_conf *mconf = mt792x_link_conf_to_mconf(link_conf);
+	struct ieee80211_vif *mvif = link_conf->vif;
 	struct sk_buff *skb;
 	int i, len = min_t(int, mvif->cfg.arp_addr_cnt,
 			   IEEE80211_BSS_ARP_ADDR_LIST_LEN);
@@ -586,6 +584,54 @@ int mt7925_mcu_uni_rx_ba(struct mt792x_dev *dev,
 				 enable, false);
 }
 
+static int mt7925_mcu_read_eeprom(struct mt792x_dev *dev, u32 offset, u8 *val)
+{
+	struct {
+		u8 rsv[4];
+
+		__le16 tag;
+		__le16 len;
+
+		__le32 addr;
+		__le32 valid;
+		u8 data[MT7925_EEPROM_BLOCK_SIZE];
+	} __packed req = {
+		.tag = cpu_to_le16(1),
+		.len = cpu_to_le16(sizeof(req) - 4),
+		.addr = cpu_to_le32(round_down(offset,
+				    MT7925_EEPROM_BLOCK_SIZE)),
+	};
+	struct evt {
+		u8 rsv[4];
+
+		__le16 tag;
+		__le16 len;
+
+		__le32 ver;
+		__le32 addr;
+		__le32 valid;
+		__le32 size;
+		__le32 magic_num;
+		__le32 type;
+		__le32 rsv1[4];
+		u8 data[32];
+	} __packed *res;
+	struct sk_buff *skb;
+	int ret;
+
+	ret = mt76_mcu_send_and_get_msg(&dev->mt76, MCU_WM_UNI_CMD_QUERY(EFUSE_CTRL),
+					&req, sizeof(req), true, &skb);
+	if (ret)
+		return ret;
+
+	res = (struct evt *)skb->data;
+	*val = res->data[offset % MT7925_EEPROM_BLOCK_SIZE];
+
+	dev_kfree_skb(skb);
+
+	return 0;
+}
+
 static int mt7925_load_clc(struct mt792x_dev *dev, const char *fw_name)
 {
 	const struct mt76_connac2_fw_trailer *hdr;
@@ -594,13 +640,20 @@ static int mt7925_load_clc(struct mt792x_dev *dev, const char *fw_name)
 	struct mt76_dev *mdev = &dev->mt76;
 	struct mt792x_phy *phy = &dev->phy;
 	const struct firmware *fw;
+	u8 *clc_base = NULL, hw_encap = 0;
 	int ret, i, len, offset = 0;
-	u8 *clc_base = NULL;
 
 	if (mt7925_disable_clc ||
 	    mt76_is_usb(&dev->mt76))
 		return 0;
 
+	if (mt76_is_mmio(&dev->mt76)) {
+		ret = mt7925_mcu_read_eeprom(dev, MT_EE_HW_TYPE, &hw_encap);
+		if (ret)
+			return ret;
+		hw_encap = u8_get_bits(hw_encap, MT_EE_HW_TYPE_ENCAP);
+	}
+
 	ret = request_firmware(&fw, fw_name, mdev->dev);
 	if (ret)
 		return ret;
@@ -638,13 +691,17 @@ static int mt7925_load_clc(struct mt792x_dev *dev, const char *fw_name)
 	for (offset = 0; offset < len; offset += le32_to_cpu(clc->len)) {
 		clc = (const struct mt7925_clc *)(clc_base + offset);
 
-		if (clc->idx > ARRAY_SIZE(phy->clc))
+		if (clc->idx >= ARRAY_SIZE(phy->clc))
 			break;
 
 		/* do not init buf again if chip reset triggered */
 		if (phy->clc[clc->idx])
 			continue;
 
+		/* header content sanity */
+		if (u8_get_bits(clc->type, MT_EE_HW_TYPE_ENCAP) != hw_encap)
+			continue;
+
 		phy->clc[clc->idx] = devm_kmemdup(mdev->dev, clc,
 						  le32_to_cpu(clc->len),
 						  GFP_KERNEL);
@@ -680,7 +737,7 @@ int mt7925_mcu_fw_log_2_host(struct mt792x_dev *dev, u8 ctrl)
 	int ret;
 
 	ret = mt76_mcu_send_and_get_msg(&dev->mt76, MCU_UNI_CMD(WSYS_CONFIG),
-					&req, sizeof(req), false, NULL);
+					&req, sizeof(req), true, NULL);
 	return ret;
 }
 
@@ -823,7 +880,7 @@ mt7925_mcu_get_nic_capability(struct mt792x_dev *dev)
 			mt7925_mcu_parse_phy_cap(dev, tlv->data);
 			break;
 		case MT_NIC_CAP_CHIP_CAP:
-			memcpy(&dev->phy.chip_cap, (void *)skb->data, sizeof(u64));
+			dev->phy.chip_cap = le64_to_cpu(*(__le64 *)tlv->data);
 			break;
 		case MT_NIC_CAP_EML_CAP:
 			mt7925_mcu_parse_eml_cap(dev, tlv->data);
@@ -872,6 +929,23 @@ int mt7925_mcu_set_deep_sleep(struct mt792x_dev *dev, bool enable)
 }
 EXPORT_SYMBOL_GPL(mt7925_mcu_set_deep_sleep);
 
+int mt7925_mcu_set_thermal_protect(struct mt792x_dev *dev)
+{
+	char cmd[64];
+	int ret = 0;
+
+	snprintf(cmd, sizeof(cmd), "ThermalProtGband %d %d %d %d %d %d %d %d %d %d",
+		 0, 100, 90, 80, 30, 1, 1, 115, 105, 5);
+	ret = mt7925_mcu_chip_config(dev, cmd);
+
+	snprintf(cmd, sizeof(cmd), "ThermalProtAband %d %d %d %d %d %d %d %d %d %d",
+		 1, 100, 90, 80, 30, 1, 1, 115, 105, 5);
+	ret |= mt7925_mcu_chip_config(dev, cmd);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(mt7925_mcu_set_thermal_protect);
+
 int mt7925_run_firmware(struct mt792x_dev *dev)
 {
 	int err;
@@ -1153,7 +1227,12 @@ int mt7925_mcu_set_mlo_roc(struct mt792x_bss_conf *mconf, u16 sel_links,
 			u8 rsv[4];
 		} __packed hdr;
 		struct roc_acquire_tlv roc[2];
-	} __packed req;
+	} __packed req = {
+			.roc[0].tag = cpu_to_le16(UNI_ROC_NUM),
+			.roc[0].len = cpu_to_le16(sizeof(struct roc_acquire_tlv)),
+			.roc[1].tag = cpu_to_le16(UNI_ROC_NUM),
+			.roc[1].len = cpu_to_le16(sizeof(struct roc_acquire_tlv))
+	};
 
 	if (!mconf || hweight16(vif->valid_links) < 2 ||
 	    hweight16(sel_links) != 2)
@@ -1200,6 +1279,8 @@ int mt7925_mcu_set_mlo_roc(struct mt792x_bss_conf *mconf, u16 sel_links,
 		req.roc[i].bw_from_ap = CMD_CBW_20MHZ;
 		req.roc[i].center_chan = center_ch;
 		req.roc[i].center_chan_from_ap = center_ch;
+		req.roc[i].center_chan2 = 0;
+		req.roc[i].center_chan2_from_ap = 0;
 
 		/* STR : 0xfe indicates BAND_ALL with enabling DBDC
 		 * EMLSR : 0xff indicates (BAND_AUTO) without DBDC
@@ -1215,7 +1296,7 @@ int mt7925_mcu_set_mlo_roc(struct mt792x_bss_conf *mconf, u16 sel_links,
 	}
 
 	return mt76_mcu_send_msg(&mvif->phy->dev->mt76, MCU_UNI_CMD(ROC),
-				 &req, sizeof(req), false);
+				 &req, sizeof(req), true);
 }
 
 int mt7925_mcu_set_roc(struct mt792x_phy *phy, struct mt792x_bss_conf *mconf,
@@ -1264,7 +1345,7 @@ int mt7925_mcu_set_roc(struct mt792x_phy *phy, struct mt792x_bss_conf *mconf,
 	}
 
 	return mt76_mcu_send_msg(&dev->mt76, MCU_UNI_CMD(ROC),
-				 &req, sizeof(req), false);
+				 &req, sizeof(req), true);
 }
 
 int mt7925_mcu_abort_roc(struct mt792x_phy *phy, struct mt792x_bss_conf *mconf,
@@ -1294,7 +1375,7 @@ int mt7925_mcu_abort_roc(struct mt792x_phy *phy, struct mt792x_bss_conf *mconf,
 	};
 
 	return mt76_mcu_send_msg(&dev->mt76, MCU_UNI_CMD(ROC),
-				 &req, sizeof(req), false);
+				 &req, sizeof(req), true);
 }
 
 int mt7925_mcu_set_eeprom(struct mt792x_dev *dev)
@@ -1315,7 +1396,7 @@ int mt7925_mcu_set_eeprom(struct mt792x_dev *dev)
 	};
 
 	return mt76_mcu_send_and_get_msg(&dev->mt76, MCU_UNI_CMD(EFUSE_CTRL),
-					 &req, sizeof(req), false, NULL);
+					 &req, sizeof(req), true, NULL);
 }
 EXPORT_SYMBOL_GPL(mt7925_mcu_set_eeprom);
 
@@ -1357,7 +1438,7 @@ int mt7925_mcu_uni_bss_ps(struct mt792x_dev *dev,
 				 &ps_req, sizeof(ps_req), true);
 }
 
-static int
+int
 mt7925_mcu_uni_bss_bcnft(struct mt792x_dev *dev,
 			 struct ieee80211_bss_conf *link_conf, bool enable)
 {
@@ -1447,12 +1528,12 @@ mt7925_mcu_set_bss_pm(struct mt792x_dev *dev,
 	int err;
 
 	err = mt76_mcu_send_msg(&dev->mt76, MCU_UNI_CMD(BSS_INFO_UPDATE),
-				&req1, sizeof(req1), false);
+				&req1, sizeof(req1), true);
 	if (err < 0 || !enable)
 		return err;
 
 	return mt76_mcu_send_msg(&dev->mt76, MCU_UNI_CMD(BSS_INFO_UPDATE),
-				 &req, sizeof(req), false);
+				 &req, sizeof(req), true);
 }
 
 static void
@@ -1898,7 +1979,11 @@ int mt7925_mcu_sta_update(struct mt792x_dev *dev,
 		mlink = mt792x_sta_to_link(msta, link_sta->link_id);
 	}
 	info.wcid = link_sta ? &mlink->wcid : &mvif->sta.deflink.wcid;
-	info.newly = link_sta ? state != MT76_STA_INFO_STATE_ASSOC : true;
+
+	if (link_sta)
+		info.newly = state != MT76_STA_INFO_STATE_ASSOC;
+	else
+		info.newly = state == MT76_STA_INFO_STATE_ASSOC ? false : true;
 
 	if (ieee80211_vif_is_mld(vif))
 		err = mt7925_mcu_mlo_sta_cmd(&dev->mphy, &info);
@@ -1914,32 +1999,21 @@ int mt7925_mcu_set_beacon_filter(struct mt792x_dev *dev,
 {
 #define MT7925_FIF_BIT_CLR		BIT(1)
 #define MT7925_FIF_BIT_SET		BIT(0)
-	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
-	unsigned long valid = ieee80211_vif_is_mld(vif) ?
-				      mvif->valid_links : BIT(0);
-	struct ieee80211_bss_conf *bss_conf;
 	int err = 0;
-	int i;
 
 	if (enable) {
-		for_each_set_bit(i, &valid, IEEE80211_MLD_MAX_NUM_LINKS) {
-			bss_conf = mt792x_vif_to_bss_conf(vif, i);
-			err = mt7925_mcu_uni_bss_bcnft(dev, bss_conf, true);
-			if (err < 0)
-				return err;
-		}
+		err = mt7925_mcu_uni_bss_bcnft(dev, &vif->bss_conf, true);
+		if (err < 0)
+			return err;
 
 		return mt7925_mcu_set_rxfilter(dev, 0,
 					       MT7925_FIF_BIT_SET,
 					       MT_WF_RFCR_DROP_OTHER_BEACON);
 	}
 
-	for_each_set_bit(i, &valid, IEEE80211_MLD_MAX_NUM_LINKS) {
-		bss_conf = mt792x_vif_to_bss_conf(vif, i);
-		err = mt7925_mcu_set_bss_pm(dev, bss_conf, false);
-		if (err)
-			return err;
-	}
+	err = mt7925_mcu_set_bss_pm(dev, &vif->bss_conf, false);
+	if (err < 0)
+		return err;
 
 	return mt7925_mcu_set_rxfilter(dev, 0,
 				       MT7925_FIF_BIT_CLR,
@@ -1976,8 +2050,6 @@ int mt7925_get_txpwr_info(struct mt792x_dev *dev, u8 band_idx, struct mt7925_txp
 int mt7925_mcu_set_sniffer(struct mt792x_dev *dev, struct ieee80211_vif *vif,
 			   bool enable)
 {
-	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
-
 	struct {
 		struct {
 			u8 band_idx;
@@ -1991,7 +2063,7 @@ int mt7925_mcu_set_sniffer(struct mt792x_dev *dev, struct ieee80211_vif *vif,
 		} __packed enable;
 	} __packed req = {
 		.hdr = {
-			.band_idx = mvif->bss_conf.mt76.band_idx,
+			.band_idx = 0,
 		},
 		.enable = {
 			.tag = cpu_to_le16(UNI_SNIFFER_ENABLE),
@@ -2000,8 +2072,6 @@ int mt7925_mcu_set_sniffer(struct mt792x_dev *dev, struct ieee80211_vif *vif,
 		},
 	};
 
-	mt76_mcu_send_msg(&dev->mt76, MCU_UNI_CMD(SNIFFER), &req, sizeof(req), true);
-
 	return mt76_mcu_send_msg(&dev->mt76, MCU_UNI_CMD(SNIFFER), &req, sizeof(req),
 				 true);
 }
@@ -2050,7 +2120,7 @@ int mt7925_mcu_config_sniffer(struct mt792x_vif *vif,
 		} __packed tlv;
 	} __packed req = {
 		.hdr = {
-			.band_idx = vif->bss_conf.mt76.band_idx,
+			.band_idx = 0,
 		},
 		.tlv = {
 			.tag = cpu_to_le16(UNI_SNIFFER_CONFIG),
@@ -2179,11 +2249,27 @@ void mt7925_mcu_bss_rlm_tlv(struct sk_buff *skb, struct mt76_phy *phy,
 	req = (struct bss_rlm_tlv *)tlv;
 	req->control_channel = chandef->chan->hw_value;
 	req->center_chan = ieee80211_frequency_to_channel(freq1);
-	req->center_chan2 = ieee80211_frequency_to_channel(freq2);
+	req->center_chan2 = 0;
 	req->tx_streams = hweight8(phy->antenna_mask);
 	req->ht_op_info = 4; /* set HT 40M allowed */
 	req->rx_streams = hweight8(phy->antenna_mask);
-	req->band = band;
+	req->center_chan2 = 0;
+	req->sco = 0;
+	req->band = 1;
+
+	switch (band) {
+	case NL80211_BAND_2GHZ:
+		req->band = 1;
+		break;
+	case NL80211_BAND_5GHZ:
+		req->band = 2;
+		break;
+	case NL80211_BAND_6GHZ:
+		req->band = 3;
+		break;
+	default:
+		break;
+	}
 
 	switch (chandef->width) {
 	case NL80211_CHAN_WIDTH_40:
@@ -2194,6 +2280,7 @@ void mt7925_mcu_bss_rlm_tlv(struct sk_buff *skb, struct mt76_phy *phy,
 		break;
 	case NL80211_CHAN_WIDTH_80P80:
 		req->bw = CMD_CBW_8080MHZ;
+		req->center_chan2 = ieee80211_frequency_to_channel(freq2);
 		break;
 	case NL80211_CHAN_WIDTH_160:
 		req->bw = CMD_CBW_160MHZ;
@@ -2463,6 +2550,7 @@ static void
 mt7925_mcu_bss_mld_tlv(struct sk_buff *skb,
 		       struct ieee80211_bss_conf *link_conf)
 {
+	struct ieee80211_vif *vif = link_conf->vif;
 	struct mt792x_bss_conf *mconf = mt792x_link_conf_to_mconf(link_conf);
 	struct mt792x_vif *mvif = (struct mt792x_vif *)link_conf->vif->drv_priv;
 	struct bss_mld_tlv *mld;
@@ -2483,7 +2571,7 @@ mt7925_mcu_bss_mld_tlv(struct sk_buff *skb,
 	mld->eml_enable = !!(link_conf->vif->cfg.eml_cap &
 			     IEEE80211_EML_CAP_EMLSR_SUPP);
 
-	memcpy(mld->mac_addr, link_conf->addr, ETH_ALEN);
+	memcpy(mld->mac_addr, vif->addr, ETH_ALEN);
 }
 
 static void
@@ -2574,6 +2662,62 @@ int mt7925_mcu_set_timing(struct mt792x_phy *phy,
 				     MCU_UNI_CMD(BSS_INFO_UPDATE), true);
 }
 
+void mt7925_mcu_del_dev(struct mt76_dev *mdev,
+			struct ieee80211_vif *vif)
+{
+	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
+	struct {
+		struct {
+			u8 omac_idx;
+			u8 band_idx;
+			__le16 pad;
+		} __packed hdr;
+		struct req_tlv {
+			__le16 tag;
+			__le16 len;
+			u8 active;
+			u8 link_idx; /* hw link idx */
+			u8 omac_addr[ETH_ALEN];
+		} __packed tlv;
+	} dev_req = {
+		.tlv = {
+			.tag = cpu_to_le16(DEV_INFO_ACTIVE),
+			.len = cpu_to_le16(sizeof(struct req_tlv)),
+			.active = true,
+		},
+	};
+	struct {
+		struct {
+			u8 bss_idx;
+			u8 pad[3];
+		} __packed hdr;
+		struct mt76_connac_bss_basic_tlv basic;
+	} basic_req = {
+		.basic = {
+			.tag = cpu_to_le16(UNI_BSS_INFO_BASIC),
+			.len = cpu_to_le16(sizeof(struct mt76_connac_bss_basic_tlv)),
+			.active = true,
+			.conn_state = 1,
+		},
+	};
+
+	dev_req.hdr.omac_idx = mvif->bss_conf.mt76.omac_idx;
+	dev_req.hdr.band_idx = mvif->bss_conf.mt76.band_idx;
+
+	basic_req.hdr.bss_idx = mvif->bss_conf.mt76.idx;
+	basic_req.basic.omac_idx = mvif->bss_conf.mt76.omac_idx;
+	basic_req.basic.band_idx = mvif->bss_conf.mt76.band_idx;
+	basic_req.basic.link_idx = mvif->bss_conf.mt76.link_idx;
+
+	mt76_mcu_send_msg(mdev, MCU_UNI_CMD(BSS_INFO_UPDATE),
+			  &basic_req, sizeof(basic_req), true);
+
+	/* recovery omac address for the legacy interface */
+	memcpy(dev_req.tlv.omac_addr, vif->addr, ETH_ALEN);
+	mt76_mcu_send_msg(mdev, MCU_UNI_CMD(DEV_INFO_UPDATE),
+			  &dev_req, sizeof(dev_req), true);
+}
+
 int mt7925_mcu_add_bss_info(struct mt792x_phy *phy,
 			    struct ieee80211_chanctx_conf *ctx,
 			    struct ieee80211_bss_conf *link_conf,
@@ -2614,7 +2758,7 @@ int mt7925_mcu_add_bss_info(struct mt792x_phy *phy,
 				     MCU_UNI_CMD(BSS_INFO_UPDATE), true);
 }
 
-int mt7925_mcu_set_dbdc(struct mt76_phy *phy)
+int mt7925_mcu_set_dbdc(struct mt76_phy *phy, bool enable)
 {
 	struct mt76_dev *mdev = phy->dev;
 
@@ -2634,11 +2778,11 @@ int mt7925_mcu_set_dbdc(struct mt76_phy *phy)
 	tlv = mt76_connac_mcu_add_tlv(skb, UNI_MBMC_SETTING, sizeof(*conf));
 	conf = (struct mbmc_conf_tlv *)tlv;
 
-	conf->mbmc_en = 1;
+	conf->mbmc_en = enable;
 	conf->band = 0; /* unused */
 
 	err = mt76_mcu_skb_send_msg(mdev, skb, MCU_UNI_CMD(SET_DBDC_PARMS),
-				    false);
+				    true);
 
 	return err;
 }
@@ -2666,6 +2810,9 @@ int mt7925_mcu_hw_scan(struct mt76_phy *phy, struct ieee80211_vif *vif,
 	struct tlv *tlv;
 	int max_len;
 
+	if (test_bit(MT76_HW_SCANNING, &phy->state))
+		return -EBUSY;
+
 	max_len = sizeof(*hdr) + sizeof(*req) + sizeof(*ssid) +
 				sizeof(*bssid) + sizeof(*chan_info) +
 				sizeof(*misc) + sizeof(*ie);
@@ -2700,8 +2847,8 @@ int mt7925_mcu_hw_scan(struct mt76_phy *phy, struct ieee80211_vif *vif,
 		if (!sreq->ssids[i].ssid_len)
 			continue;
 
-		ssid->ssids[i].ssid_len = cpu_to_le32(sreq->ssids[i].ssid_len);
-		memcpy(ssid->ssids[i].ssid, sreq->ssids[i].ssid,
+		ssid->ssids[n_ssids].ssid_len = cpu_to_le32(sreq->ssids[i].ssid_len);
+		memcpy(ssid->ssids[n_ssids].ssid, sreq->ssids[i].ssid,
 		       sreq->ssids[i].ssid_len);
 		n_ssids++;
 	}
@@ -2753,7 +2900,7 @@ int mt7925_mcu_hw_scan(struct mt76_phy *phy, struct ieee80211_vif *vif,
 	}
 
 	err = mt76_mcu_skb_send_msg(mdev, skb, MCU_UNI_CMD(SCAN_REQ),
-				    false);
+				    true);
 	if (err < 0)
 		clear_bit(MT76_HW_SCANNING, &phy->state);
 
@@ -2859,7 +3006,7 @@ int mt7925_mcu_sched_scan_req(struct mt76_phy *phy,
 	}
 
 	return mt76_mcu_skb_send_msg(mdev, skb, MCU_UNI_CMD(SCAN_REQ),
-				     false);
+				     true);
 }
 EXPORT_SYMBOL_GPL(mt7925_mcu_sched_scan_req);
 
@@ -2895,7 +3042,7 @@ mt7925_mcu_sched_scan_enable(struct mt76_phy *phy,
 		clear_bit(MT76_HW_SCHED_SCANNING, &phy->state);
 
 	return mt76_mcu_skb_send_msg(mdev, skb, MCU_UNI_CMD(SCAN_REQ),
-				     false);
+				     true);
 }
 
 int mt7925_mcu_cancel_hw_scan(struct mt76_phy *phy,
@@ -2934,7 +3081,7 @@ int mt7925_mcu_cancel_hw_scan(struct mt76_phy *phy,
 	}
 
 	return mt76_mcu_send_msg(phy->dev, MCU_UNI_CMD(SCAN_REQ),
-				 &req, sizeof(req), false);
+				 &req, sizeof(req), true);
 }
 EXPORT_SYMBOL_GPL(mt7925_mcu_cancel_hw_scan);
 
@@ -3039,7 +3186,7 @@ int mt7925_mcu_set_channel_domain(struct mt76_phy *phy)
 	memcpy(__skb_push(skb, sizeof(req)), &req, sizeof(req));
 
 	return mt76_mcu_skb_send_msg(dev, skb, MCU_UNI_CMD(SET_DOMAIN_INFO),
-				     false);
+				     true);
 }
 EXPORT_SYMBOL_GPL(mt7925_mcu_set_channel_domain);
 
@@ -3071,16 +3218,16 @@ __mt7925_mcu_set_clc(struct mt792x_dev *dev, u8 *alpha2,
 
 		.idx = idx,
 		.env = env_cap,
-		.acpi_conf = mt792x_acpi_get_flags(&dev->phy),
 	};
 	int ret, valid_cnt = 0;
-	u8 i, *pos;
+	u8 *pos, *last_pos;
 
 	if (!clc)
 		return 0;
 
 	pos = clc->data + sizeof(*seg) * clc->nr_seg;
-	for (i = 0; i < clc->nr_country; i++) {
+	last_pos = clc->data + le32_to_cpu(*(__le32 *)(clc->data + 4));
+	while (pos < last_pos) {
 		struct mt7925_clc_rule *rule = (struct mt7925_clc_rule *)pos;
 
 		pos += sizeof(*rule);
@@ -3182,6 +3329,10 @@ int mt7925_mcu_fill_message(struct mt76_dev *mdev, struct sk_buff *skb,
 		else
 			uni_txd->option = MCU_CMD_UNI_EXT_ACK;
 
+		if (cmd == MCU_UNI_CMD(HIF_CTRL) ||
+		    cmd == MCU_UNI_CMD(CHIP_CONFIG))
+			uni_txd->option &= ~MCU_CMD_ACK;
+
 		goto exit;
 	}
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.h b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.h
index ac53bdc99332..ee89d5778adf 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.h
@@ -566,8 +566,8 @@ struct mt7925_wow_pattern_tlv {
 	u8 offset;
 	u8 mask[MT76_CONNAC_WOW_MASK_MAX_LEN];
 	u8 pattern[MT76_CONNAC_WOW_PATTEN_MAX_LEN];
-	u8 rsv[7];
-} __packed;
+	u8 rsv[4];
+};
 
 struct roc_acquire_tlv {
 	__le16 tag;
@@ -616,7 +616,7 @@ mt7925_mcu_get_cipher(int cipher)
 	}
 }
 
-int mt7925_mcu_set_dbdc(struct mt76_phy *phy);
+int mt7925_mcu_set_dbdc(struct mt76_phy *phy, bool enable);
 int mt7925_mcu_hw_scan(struct mt76_phy *phy, struct ieee80211_vif *vif,
 		       struct ieee80211_scan_request *scan_req);
 int mt7925_mcu_cancel_hw_scan(struct mt76_phy *phy,
@@ -627,6 +627,8 @@ int mt7925_mcu_sched_scan_req(struct mt76_phy *phy,
 int mt7925_mcu_sched_scan_enable(struct mt76_phy *phy,
 				 struct ieee80211_vif *vif,
 				 bool enable);
+void mt7925_mcu_del_dev(struct mt76_dev *mdev,
+			struct ieee80211_vif *vif);
 int mt7925_mcu_add_bss_info(struct mt792x_phy *phy,
 			    struct ieee80211_chanctx_conf *ctx,
 			    struct ieee80211_bss_conf *link_conf,
@@ -635,6 +637,7 @@ int mt7925_mcu_add_bss_info(struct mt792x_phy *phy,
 int mt7925_mcu_set_timing(struct mt792x_phy *phy,
 			  struct ieee80211_bss_conf *link_conf);
 int mt7925_mcu_set_deep_sleep(struct mt792x_dev *dev, bool enable);
+int mt7925_mcu_set_thermal_protect(struct mt792x_dev *dev);
 int mt7925_mcu_set_channel_domain(struct mt76_phy *phy);
 int mt7925_mcu_set_radio_en(struct mt792x_phy *phy, bool enable);
 int mt7925_mcu_set_chctx(struct mt76_phy *phy, struct mt76_vif *mvif,
@@ -643,4 +646,7 @@ int mt7925_mcu_set_chctx(struct mt76_phy *phy, struct mt76_vif *mvif,
 int mt7925_mcu_set_rate_txpower(struct mt76_phy *phy);
 int mt7925_mcu_update_arp_filter(struct mt76_dev *dev,
 				 struct ieee80211_bss_conf *link_conf);
+int
+mt7925_mcu_uni_bss_bcnft(struct mt792x_dev *dev,
+			 struct ieee80211_bss_conf *link_conf, bool enable);
 #endif
diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mt7925.h b/drivers/net/wireless/mediatek/mt76/mt7925/mt7925.h
index f5c02e5f5066..c83b8a210498 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/mt7925.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/mt7925.h
@@ -147,9 +147,12 @@ enum mt7925_eeprom_field {
 	MT_EE_CHIP_ID =		0x000,
 	MT_EE_VERSION =		0x002,
 	MT_EE_MAC_ADDR =	0x004,
+	MT_EE_HW_TYPE =		0xa71,
 	__MT_EE_MAX =		0x9ff
 };
 
+#define MT_EE_HW_TYPE_ENCAP     GENMASK(1, 0)
+
 enum {
 	TXPWR_USER,
 	TXPWR_EEPROM,
diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/pci.c b/drivers/net/wireless/mediatek/mt76/mt7925/pci.c
index 9aec675450f2..5e428f19f972 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/pci.c
@@ -482,9 +482,6 @@ static int mt7925_pci_suspend(struct device *device)
 
 	/* disable interrupt */
 	mt76_wr(dev, dev->irq_map->host_irq_enable, 0);
-	mt76_wr(dev, MT_WFDMA0_HOST_INT_DIS,
-		dev->irq_map->tx.all_complete_mask |
-		MT_INT_RX_DONE_ALL | MT_INT_MCU_CMD);
 
 	mt76_wr(dev, MT_PCIE_MAC_INT_ENABLE, 0x0);
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/regs.h b/drivers/net/wireless/mediatek/mt76/mt7925/regs.h
index 985794a40c1a..341987e47f67 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/regs.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/regs.h
@@ -28,7 +28,7 @@
 #define MT_MDP_TO_HIF			0
 #define MT_MDP_TO_WM			1
 
-#define MT_WFDMA0_HOST_INT_ENA		MT_WFDMA0(0x228)
+#define MT_WFDMA0_HOST_INT_ENA		MT_WFDMA0(0x204)
 #define MT_WFDMA0_HOST_INT_DIS		MT_WFDMA0(0x22c)
 #define HOST_RX_DONE_INT_ENA4		BIT(12)
 #define HOST_RX_DONE_INT_ENA5		BIT(13)
@@ -58,7 +58,7 @@
 
 #define MT_INT_TX_DONE_MCU		(MT_INT_TX_DONE_MCU_WM |	\
 					 MT_INT_TX_DONE_FWDL)
-#define MT_INT_TX_DONE_ALL		(MT_INT_TX_DONE_MCU_WM |	\
+#define MT_INT_TX_DONE_ALL		(MT_INT_TX_DONE_MCU |	\
 					 MT_INT_TX_DONE_BAND0 |	\
 					GENMASK(18, 4))
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt792x.h b/drivers/net/wireless/mediatek/mt76/mt792x.h
index ab12616ec2b8..2b8b9b2977f7 100644
--- a/drivers/net/wireless/mediatek/mt76/mt792x.h
+++ b/drivers/net/wireless/mediatek/mt76/mt792x.h
@@ -241,6 +241,7 @@ static inline struct mt792x_bss_conf *
 mt792x_vif_to_link(struct mt792x_vif *mvif, u8 link_id)
 {
 	struct ieee80211_vif *vif;
+	struct mt792x_bss_conf *bss_conf;
 
 	vif = container_of((void *)mvif, struct ieee80211_vif, drv_priv);
 
@@ -248,8 +249,10 @@ mt792x_vif_to_link(struct mt792x_vif *mvif, u8 link_id)
 	    link_id >= IEEE80211_LINK_UNSPECIFIED)
 		return &mvif->bss_conf;
 
-	return rcu_dereference_protected(mvif->link_conf[link_id],
-		lockdep_is_held(&mvif->phy->dev->mt76.mutex));
+	bss_conf = rcu_dereference_protected(mvif->link_conf[link_id],
+					     lockdep_is_held(&mvif->phy->dev->mt76.mutex));
+
+	return bss_conf ? bss_conf : &mvif->bss_conf;
 }
 
 static inline struct mt792x_link_sta *
diff --git a/drivers/net/wireless/mediatek/mt76/mt792x_core.c b/drivers/net/wireless/mediatek/mt76/mt792x_core.c
index 78fe37c2e07b..b87eed4d168d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt792x_core.c
+++ b/drivers/net/wireless/mediatek/mt76/mt792x_core.c
@@ -147,7 +147,8 @@ void mt792x_mac_link_bss_remove(struct mt792x_dev *dev,
 	link_conf = mt792x_vif_to_bss_conf(vif, mconf->link_id);
 
 	mt76_connac_free_pending_tx_skbs(&dev->pm, &mlink->wcid);
-	mt76_connac_mcu_uni_add_dev(&dev->mphy, link_conf, &mlink->wcid, false);
+	mt76_connac_mcu_uni_add_dev(&dev->mphy, link_conf, &mconf->mt76,
+				    &mlink->wcid, false);
 
 	rcu_assign_pointer(dev->mt76.wcid[idx], NULL);
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt792x_mac.c b/drivers/net/wireless/mediatek/mt76/mt792x_mac.c
index 106273935b26..05978d9c7b91 100644
--- a/drivers/net/wireless/mediatek/mt76/mt792x_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt792x_mac.c
@@ -153,7 +153,7 @@ struct mt76_wcid *mt792x_rx_get_wcid(struct mt792x_dev *dev, u16 idx,
 		return NULL;
 
 	link = container_of(wcid, struct mt792x_link_sta, wcid);
-	sta = container_of(link, struct mt792x_sta, deflink);
+	sta = link->sta;
 	if (!sta->vif)
 		return NULL;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/dma.c b/drivers/net/wireless/mediatek/mt76/mt7996/dma.c
index 69a7d9b2e38b..4b68d2fc5e09 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/dma.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/dma.c
@@ -493,7 +493,7 @@ int mt7996_dma_init(struct mt7996_dev *dev)
 	ret = mt76_queue_alloc(dev, &dev->mt76.q_rx[MT_RXQ_MCU],
 			       MT_RXQ_ID(MT_RXQ_MCU),
 			       MT7996_RX_MCU_RING_SIZE,
-			       MT_RX_BUF_SIZE,
+			       MT7996_RX_MCU_BUF_SIZE,
 			       MT_RXQ_RING_BASE(MT_RXQ_MCU));
 	if (ret)
 		return ret;
@@ -502,7 +502,7 @@ int mt7996_dma_init(struct mt7996_dev *dev)
 	ret = mt76_queue_alloc(dev, &dev->mt76.q_rx[MT_RXQ_MCU_WA],
 			       MT_RXQ_ID(MT_RXQ_MCU_WA),
 			       MT7996_RX_MCU_RING_SIZE_WA,
-			       MT_RX_BUF_SIZE,
+			       MT7996_RX_MCU_BUF_SIZE,
 			       MT_RXQ_RING_BASE(MT_RXQ_MCU_WA));
 	if (ret)
 		return ret;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/init.c b/drivers/net/wireless/mediatek/mt76/mt7996/init.c
index 5e96973226bb..c55038554114 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/init.c
@@ -16,9 +16,6 @@
 
 static const struct ieee80211_iface_limit if_limits[] = {
 	{
-		.max = 1,
-		.types = BIT(NL80211_IFTYPE_ADHOC)
-	}, {
 		.max = 16,
 		.types = BIT(NL80211_IFTYPE_AP)
 #ifdef CONFIG_MAC80211_MESH
@@ -85,7 +82,7 @@ static ssize_t mt7996_thermal_temp_store(struct device *dev,
 		return ret;
 
 	mutex_lock(&phy->dev->mt76.mutex);
-	val = clamp_val(DIV_ROUND_CLOSEST(val, 1000), 40, 130);
+	val = DIV_ROUND_CLOSEST(clamp_val(val, 40 * 1000, 130 * 1000), 1000);
 
 	/* add a safety margin ~10 */
 	if ((i - 1 == MT7996_CRIT_TEMP_IDX &&
@@ -1080,6 +1077,9 @@ mt7996_init_he_caps(struct mt7996_phy *phy, enum nl80211_band band,
 	he_cap_elem->phy_cap_info[2] = IEEE80211_HE_PHY_CAP2_STBC_TX_UNDER_80MHZ |
 				       IEEE80211_HE_PHY_CAP2_STBC_RX_UNDER_80MHZ;
 
+	he_cap_elem->phy_cap_info[7] =
+			IEEE80211_HE_PHY_CAP7_HE_SU_MU_PPDU_4XLTF_AND_08_US_GI;
+
 	switch (iftype) {
 	case NL80211_IFTYPE_AP:
 		he_cap_elem->mac_cap_info[0] |= IEEE80211_HE_MAC_CAP0_TWT_RES;
@@ -1119,8 +1119,7 @@ mt7996_init_he_caps(struct mt7996_phy *phy, enum nl80211_band band,
 			IEEE80211_HE_PHY_CAP6_PARTIAL_BW_EXT_RANGE |
 			IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT;
 		he_cap_elem->phy_cap_info[7] |=
-			IEEE80211_HE_PHY_CAP7_POWER_BOOST_FACTOR_SUPP |
-			IEEE80211_HE_PHY_CAP7_HE_SU_MU_PPDU_4XLTF_AND_08_US_GI;
+			IEEE80211_HE_PHY_CAP7_POWER_BOOST_FACTOR_SUPP;
 		he_cap_elem->phy_cap_info[8] |=
 			IEEE80211_HE_PHY_CAP8_20MHZ_IN_40MHZ_HE_PPDU_IN_2G |
 			IEEE80211_HE_PHY_CAP8_20MHZ_IN_160MHZ_HE_PPDU |
@@ -1190,7 +1189,12 @@ mt7996_init_eht_caps(struct mt7996_phy *phy, enum nl80211_band band,
 
 	eht_cap_elem->mac_cap_info[0] =
 		IEEE80211_EHT_MAC_CAP0_EPCS_PRIO_ACCESS |
-		IEEE80211_EHT_MAC_CAP0_OM_CONTROL;
+		IEEE80211_EHT_MAC_CAP0_OM_CONTROL |
+		u8_encode_bits(IEEE80211_EHT_MAC_CAP0_MAX_MPDU_LEN_11454,
+			       IEEE80211_EHT_MAC_CAP0_MAX_MPDU_LEN_MASK);
+
+	eht_cap_elem->mac_cap_info[1] |=
+		IEEE80211_EHT_MAC_CAP1_MAX_AMPDU_LEN_MASK;
 
 	eht_cap_elem->phy_cap_info[0] =
 		IEEE80211_EHT_PHY_CAP0_NDP_4_EHT_LFT_32_GI |
@@ -1233,21 +1237,20 @@ mt7996_init_eht_caps(struct mt7996_phy *phy, enum nl80211_band band,
 		IEEE80211_EHT_PHY_CAP3_CODEBOOK_7_5_MU_FDBK;
 
 	eht_cap_elem->phy_cap_info[4] =
+		IEEE80211_EHT_PHY_CAP4_EHT_MU_PPDU_4_EHT_LTF_08_GI |
 		u8_encode_bits(min_t(int, sts - 1, 2),
 			       IEEE80211_EHT_PHY_CAP4_MAX_NC_MASK);
 
 	eht_cap_elem->phy_cap_info[5] =
 		u8_encode_bits(IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_16US,
 			       IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_MASK) |
-		u8_encode_bits(u8_get_bits(0x11, GENMASK(1, 0)),
+		u8_encode_bits(u8_get_bits(1, GENMASK(1, 0)),
 			       IEEE80211_EHT_PHY_CAP5_MAX_NUM_SUPP_EHT_LTF_MASK);
 
 	val = width == NL80211_CHAN_WIDTH_320 ? 0xf :
 	      width == NL80211_CHAN_WIDTH_160 ? 0x7 :
 	      width == NL80211_CHAN_WIDTH_80 ? 0x3 : 0x1;
 	eht_cap_elem->phy_cap_info[6] =
-		u8_encode_bits(u8_get_bits(0x11, GENMASK(4, 2)),
-			       IEEE80211_EHT_PHY_CAP6_MAX_NUM_SUPP_EHT_LTF_MASK) |
 		u8_encode_bits(val, IEEE80211_EHT_PHY_CAP6_MCS15_SUPP_MASK);
 
 	val = u8_encode_bits(nss, IEEE80211_EHT_MCS_NSS_RX) |
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
index 0d21414e2c88..0990a3d481f2 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
@@ -623,6 +623,14 @@ mt7996_mac_fill_rx(struct mt7996_dev *dev, enum mt76_rxq_id q,
 		status->last_amsdu = amsdu_info == MT_RXD4_LAST_AMSDU_FRAME;
 	}
 
+	/* IEEE 802.11 fragmentation can only be applied to unicast frames.
+	 * Hence, drop fragments with multicast/broadcast RA.
+	 * This check fixes vulnerabilities, like CVE-2020-26145.
+	 */
+	if ((ieee80211_has_morefrags(fc) || seq_ctrl & IEEE80211_SCTL_FRAG) &&
+	    FIELD_GET(MT_RXD3_NORMAL_ADDR_TYPE, rxd3) != MT_RXD3_NORMAL_U2M)
+		return -EINVAL;
+
 	hdr_gap = (u8 *)rxd - skb->data + 2 * remove_pad;
 	if (hdr_trans && ieee80211_has_morefrags(fc)) {
 		if (mt7996_reverse_frag0_hdr_trans(skb, hdr_gap))
@@ -819,6 +827,7 @@ void mt7996_mac_write_txwi(struct mt7996_dev *dev, __le32 *txwi,
 			   struct ieee80211_key_conf *key, int pid,
 			   enum mt76_txq_id qid, u32 changed)
 {
+	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
 	struct ieee80211_vif *vif = info->control.vif;
 	u8 band_idx = (info->hw_queue & MT_TX_HW_QUEUE_PHY) >> 2;
@@ -886,8 +895,9 @@ void mt7996_mac_write_txwi(struct mt7996_dev *dev, __le32 *txwi,
 	val = MT_TXD6_DIS_MAT | MT_TXD6_DAS;
 	if (is_mt7996(&dev->mt76))
 		val |= FIELD_PREP(MT_TXD6_MSDU_CNT, 1);
-	else
+	else if (is_8023 || !ieee80211_is_mgmt(hdr->frame_control))
 		val |= FIELD_PREP(MT_TXD6_MSDU_CNT_V2, 1);
+
 	txwi[6] = cpu_to_le32(val);
 	txwi[7] = 0;
 
@@ -897,7 +907,6 @@ void mt7996_mac_write_txwi(struct mt7996_dev *dev, __le32 *txwi,
 		mt7996_mac_write_txwi_80211(dev, txwi, skb, key);
 
 	if (txwi[1] & cpu_to_le32(MT_TXD1_FIXED_RATE)) {
-		struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
 		bool mcast = ieee80211_is_data(hdr->frame_control) &&
 			     is_multicast_ether_addr(hdr->addr1);
 		u8 idx = MT7996_BASIC_RATES_TBL;
@@ -1398,7 +1407,7 @@ bool mt7996_rx_check(struct mt76_dev *mdev, void *data, int len)
 		mt7996_mac_tx_free(dev, data, len);
 		return false;
 	case PKT_TYPE_TXS:
-		for (rxd += 4; rxd + 8 <= end; rxd += 8)
+		for (rxd += MT_TXS_HDR_SIZE; rxd + MT_TXS_SIZE <= end; rxd += MT_TXS_SIZE)
 			mt7996_mac_add_txs(dev, rxd);
 		return false;
 	case PKT_TYPE_RX_FW_MONITOR:
@@ -1441,7 +1450,7 @@ void mt7996_queue_rx_skb(struct mt76_dev *mdev, enum mt76_rxq_id q,
 		mt7996_mcu_rx_event(dev, skb);
 		break;
 	case PKT_TYPE_TXS:
-		for (rxd += 4; rxd + 8 <= end; rxd += 8)
+		for (rxd += MT_TXS_HDR_SIZE; rxd + MT_TXS_SIZE <= end; rxd += MT_TXS_SIZE)
 			mt7996_mac_add_txs(dev, rxd);
 		dev_kfree_skb(skb);
 		break;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
index 39f071ece35e..4d11083b86c0 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
@@ -496,8 +496,7 @@ static void mt7996_configure_filter(struct ieee80211_hw *hw,
 
 	MT76_FILTER(CONTROL, MT_WF_RFCR_DROP_CTS |
 			     MT_WF_RFCR_DROP_RTS |
-			     MT_WF_RFCR_DROP_CTL_RSV |
-			     MT_WF_RFCR_DROP_NDPA);
+			     MT_WF_RFCR_DROP_CTL_RSV);
 
 	*total_flags = flags;
 	mt76_wr(dev, MT_WF_RFCR(phy->mt76->band_idx), phy->rxfilter);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
index 6c445a9dbc03..265958f7b787 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
@@ -2070,7 +2070,7 @@ mt7996_mcu_sta_rate_ctrl_tlv(struct sk_buff *skb, struct mt7996_dev *dev,
 			cap |= STA_CAP_VHT_TX_STBC;
 		if (sta->deflink.vht_cap.cap & IEEE80211_VHT_CAP_RXSTBC_1)
 			cap |= STA_CAP_VHT_RX_STBC;
-		if (vif->bss_conf.vht_ldpc &&
+		if ((vif->type != NL80211_IFTYPE_AP || vif->bss_conf.vht_ldpc) &&
 		    (sta->deflink.vht_cap.cap & IEEE80211_VHT_CAP_RXLDPC))
 			cap |= STA_CAP_VHT_LDPC;
 
@@ -3666,6 +3666,13 @@ int mt7996_mcu_get_chip_config(struct mt7996_dev *dev, u32 *cap)
 
 int mt7996_mcu_get_chan_mib_info(struct mt7996_phy *phy, bool chan_switch)
 {
+	enum {
+		IDX_TX_TIME,
+		IDX_RX_TIME,
+		IDX_OBSS_AIRTIME,
+		IDX_NON_WIFI_TIME,
+		IDX_NUM
+	};
 	struct {
 		struct {
 			u8 band;
@@ -3675,16 +3682,15 @@ int mt7996_mcu_get_chan_mib_info(struct mt7996_phy *phy, bool chan_switch)
 			__le16 tag;
 			__le16 len;
 			__le32 offs;
-		} data[4];
+		} data[IDX_NUM];
 	} __packed req = {
 		.hdr.band = phy->mt76->band_idx,
 	};
-	/* strict order */
 	static const u32 offs[] = {
-		UNI_MIB_TX_TIME,
-		UNI_MIB_RX_TIME,
-		UNI_MIB_OBSS_AIRTIME,
-		UNI_MIB_NON_WIFI_TIME,
+		[IDX_TX_TIME] = UNI_MIB_TX_TIME,
+		[IDX_RX_TIME] = UNI_MIB_RX_TIME,
+		[IDX_OBSS_AIRTIME] = UNI_MIB_OBSS_AIRTIME,
+		[IDX_NON_WIFI_TIME] = UNI_MIB_NON_WIFI_TIME,
 	};
 	struct mt76_channel_state *state = phy->mt76->chan_state;
 	struct mt76_channel_state *state_ts = &phy->state_ts;
@@ -3693,7 +3699,7 @@ int mt7996_mcu_get_chan_mib_info(struct mt7996_phy *phy, bool chan_switch)
 	struct sk_buff *skb;
 	int i, ret;
 
-	for (i = 0; i < 4; i++) {
+	for (i = 0; i < IDX_NUM; i++) {
 		req.data[i].tag = cpu_to_le16(UNI_CMD_MIB_DATA);
 		req.data[i].len = cpu_to_le16(sizeof(req.data[i]));
 		req.data[i].offs = cpu_to_le32(offs[i]);
@@ -3712,17 +3718,24 @@ int mt7996_mcu_get_chan_mib_info(struct mt7996_phy *phy, bool chan_switch)
 		goto out;
 
 #define __res_u64(s) le64_to_cpu(res[s].data)
-	state->cc_tx += __res_u64(1) - state_ts->cc_tx;
-	state->cc_bss_rx += __res_u64(2) - state_ts->cc_bss_rx;
-	state->cc_rx += __res_u64(2) + __res_u64(3) - state_ts->cc_rx;
-	state->cc_busy += __res_u64(0) + __res_u64(1) + __res_u64(2) + __res_u64(3) -
+	state->cc_tx += __res_u64(IDX_TX_TIME) - state_ts->cc_tx;
+	state->cc_bss_rx += __res_u64(IDX_RX_TIME) - state_ts->cc_bss_rx;
+	state->cc_rx += __res_u64(IDX_RX_TIME) +
+			__res_u64(IDX_OBSS_AIRTIME) -
+			state_ts->cc_rx;
+	state->cc_busy += __res_u64(IDX_TX_TIME) +
+			  __res_u64(IDX_RX_TIME) +
+			  __res_u64(IDX_OBSS_AIRTIME) +
+			  __res_u64(IDX_NON_WIFI_TIME) -
 			  state_ts->cc_busy;
-
 out:
-	state_ts->cc_tx = __res_u64(1);
-	state_ts->cc_bss_rx = __res_u64(2);
-	state_ts->cc_rx = __res_u64(2) + __res_u64(3);
-	state_ts->cc_busy = __res_u64(0) + __res_u64(1) + __res_u64(2) + __res_u64(3);
+	state_ts->cc_tx = __res_u64(IDX_TX_TIME);
+	state_ts->cc_bss_rx = __res_u64(IDX_RX_TIME);
+	state_ts->cc_rx = __res_u64(IDX_RX_TIME) + __res_u64(IDX_OBSS_AIRTIME);
+	state_ts->cc_busy = __res_u64(IDX_TX_TIME) +
+			    __res_u64(IDX_RX_TIME) +
+			    __res_u64(IDX_OBSS_AIRTIME) +
+			    __res_u64(IDX_NON_WIFI_TIME);
 #undef __res_u64
 
 	dev_kfree_skb(skb);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.h b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.h
index 43468bcaffc6..a75e1c9435bb 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.h
@@ -908,7 +908,8 @@ enum {
 	UNI_CMD_SER_SET_RECOVER_L3_TX_DISABLE,
 	UNI_CMD_SER_SET_RECOVER_L3_BF,
 	UNI_CMD_SER_SET_RECOVER_L4_MDP,
-	UNI_CMD_SER_SET_RECOVER_FULL,
+	UNI_CMD_SER_SET_RECOVER_FROM_ETH,
+	UNI_CMD_SER_SET_RECOVER_FULL = 8,
 	UNI_CMD_SER_SET_SYSTEM_ASSERT,
 	/* action */
 	UNI_CMD_SER_ENABLE = 1,
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mmio.c b/drivers/net/wireless/mediatek/mt76/mt7996/mmio.c
index 40e45fb2b626..bffee73b780c 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mmio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mmio.c
@@ -177,7 +177,7 @@ static u32 __mt7996_reg_addr(struct mt7996_dev *dev, u32 addr)
 			continue;
 
 		ofs = addr - dev->reg.map[i].phys;
-		if (ofs > dev->reg.map[i].size)
+		if (ofs >= dev->reg.map[i].size)
 			continue;
 
 		return dev->reg.map[i].mapped + ofs;
@@ -281,7 +281,7 @@ static int mt7996_mmio_wed_reset(struct mtk_wed_device *wed)
 	if (test_and_set_bit(MT76_STATE_WED_RESET, &mphy->state))
 		return -EBUSY;
 
-	ret = mt7996_mcu_set_ser(dev, UNI_CMD_SER_TRIGGER, UNI_CMD_SER_SET_RECOVER_L1,
+	ret = mt7996_mcu_set_ser(dev, UNI_CMD_SER_TRIGGER, UNI_CMD_SER_SET_RECOVER_FROM_ETH,
 				 mphy->band_idx);
 	if (ret)
 		goto out;
@@ -323,6 +323,9 @@ int mt7996_mmio_wed_init(struct mt7996_dev *dev, void *pdev_ptr,
 	wed->wlan.base = devm_ioremap(dev->mt76.dev,
 				      pci_resource_start(pci_dev, 0),
 				      pci_resource_len(pci_dev, 0));
+	if (!wed->wlan.base)
+		return -ENOMEM;
+
 	wed->wlan.phy_base = pci_resource_start(pci_dev, 0);
 
 	if (hif2) {
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
index ab8c9070630b..425fd030bee0 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
@@ -28,6 +28,9 @@
 #define MT7996_RX_RING_SIZE		1536
 #define MT7996_RX_MCU_RING_SIZE		512
 #define MT7996_RX_MCU_RING_SIZE_WA	1024
+/* scatter-gather of mcu event is not supported in connac3 */
+#define MT7996_RX_MCU_BUF_SIZE		(2048 + \
+					 SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
 
 #define MT7996_FIRMWARE_WA		"mediatek/mt7996/mt7996_wa.bin"
 #define MT7996_FIRMWARE_WM		"mediatek/mt7996/mt7996_wm.bin"
diff --git a/drivers/net/wireless/mediatek/mt76/tx.c b/drivers/net/wireless/mediatek/mt76/tx.c
index ce193e625666..065a1e453745 100644
--- a/drivers/net/wireless/mediatek/mt76/tx.c
+++ b/drivers/net/wireless/mediatek/mt76/tx.c
@@ -100,7 +100,8 @@ __mt76_tx_status_skb_done(struct mt76_dev *dev, struct sk_buff *skb, u8 flags,
 		return;
 
 	/* Tx status can be unreliable. if it fails, mark the frame as ACKed */
-	if (flags & MT_TX_CB_TXS_FAILED) {
+	if (flags & MT_TX_CB_TXS_FAILED &&
+	    (dev->drv->drv_flags & MT_DRV_IGNORE_TXS_FAILED)) {
 		info->status.rates[0].count = 0;
 		info->status.rates[0].idx = -1;
 		info->flags |= IEEE80211_TX_STAT_ACK;
diff --git a/drivers/net/wireless/mediatek/mt76/usb.c b/drivers/net/wireless/mediatek/mt76/usb.c
index 58ff06823389..f9e67b8c3b3c 100644
--- a/drivers/net/wireless/mediatek/mt76/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/usb.c
@@ -33,9 +33,9 @@ int __mt76u_vendor_request(struct mt76_dev *dev, u8 req, u8 req_type,
 
 		ret = usb_control_msg(udev, pipe, req, req_type, val,
 				      offset, buf, len, MT_VEND_REQ_TOUT_MS);
-		if (ret == -ENODEV)
+		if (ret == -ENODEV || ret == -EPROTO)
 			set_bit(MT76_REMOVED, &dev->phy.state);
-		if (ret >= 0 || ret == -ENODEV)
+		if (ret >= 0 || ret == -ENODEV || ret == -EPROTO)
 			return ret;
 		usleep_range(5000, 10000);
 	}
diff --git a/drivers/net/wireless/purelifi/plfxlc/mac.c b/drivers/net/wireless/purelifi/plfxlc/mac.c
index eae93efa6150..a7f5d287e369 100644
--- a/drivers/net/wireless/purelifi/plfxlc/mac.c
+++ b/drivers/net/wireless/purelifi/plfxlc/mac.c
@@ -99,12 +99,6 @@ int plfxlc_mac_init_hw(struct ieee80211_hw *hw)
 	return r;
 }
 
-void plfxlc_mac_release(struct plfxlc_mac *mac)
-{
-	plfxlc_chip_release(&mac->chip);
-	lockdep_assert_held(&mac->lock);
-}
-
 int plfxlc_op_start(struct ieee80211_hw *hw)
 {
 	plfxlc_hw_mac(hw)->chip.usb.initialized = 1;
@@ -756,3 +750,9 @@ struct ieee80211_hw *plfxlc_mac_alloc_hw(struct usb_interface *intf)
 	SET_IEEE80211_DEV(hw, &intf->dev);
 	return hw;
 }
+
+void plfxlc_mac_release_hw(struct ieee80211_hw *hw)
+{
+	plfxlc_chip_release(&plfxlc_hw_mac(hw)->chip);
+	ieee80211_free_hw(hw);
+}
diff --git a/drivers/net/wireless/purelifi/plfxlc/mac.h b/drivers/net/wireless/purelifi/plfxlc/mac.h
index 9384acddcf26..56da502999c1 100644
--- a/drivers/net/wireless/purelifi/plfxlc/mac.h
+++ b/drivers/net/wireless/purelifi/plfxlc/mac.h
@@ -168,7 +168,7 @@ static inline u8 *plfxlc_mac_get_perm_addr(struct plfxlc_mac *mac)
 }
 
 struct ieee80211_hw *plfxlc_mac_alloc_hw(struct usb_interface *intf);
-void plfxlc_mac_release(struct plfxlc_mac *mac);
+void plfxlc_mac_release_hw(struct ieee80211_hw *hw);
 
 int plfxlc_mac_preinit_hw(struct ieee80211_hw *hw, const u8 *hw_address);
 int plfxlc_mac_init_hw(struct ieee80211_hw *hw);
diff --git a/drivers/net/wireless/purelifi/plfxlc/usb.c b/drivers/net/wireless/purelifi/plfxlc/usb.c
index 56d1139ba8bc..966a9e211963 100644
--- a/drivers/net/wireless/purelifi/plfxlc/usb.c
+++ b/drivers/net/wireless/purelifi/plfxlc/usb.c
@@ -503,8 +503,10 @@ int plfxlc_usb_wreq_async(struct plfxlc_usb *usb, const u8 *buffer,
 			  (void *)buffer, buffer_len, complete_fn, context);
 
 	r = usb_submit_urb(urb, GFP_ATOMIC);
-	if (r)
+	if (r) {
+		usb_free_urb(urb);
 		dev_err(&udev->dev, "Async write submit failed (%d)\n", r);
+	}
 
 	return r;
 }
@@ -602,7 +604,7 @@ static int probe(struct usb_interface *intf,
 	r = plfxlc_upload_mac_and_serial(intf, hw_address, serial_number);
 	if (r) {
 		dev_err(&intf->dev, "MAC and Serial upload failed (%d)\n", r);
-		goto error;
+		goto error_free_hw;
 	}
 
 	chip->unit_type = STA;
@@ -611,13 +613,13 @@ static int probe(struct usb_interface *intf,
 	r = plfxlc_mac_preinit_hw(hw, hw_address);
 	if (r) {
 		dev_err(&intf->dev, "Init mac failed (%d)\n", r);
-		goto error;
+		goto error_free_hw;
 	}
 
 	r = ieee80211_register_hw(hw);
 	if (r) {
 		dev_err(&intf->dev, "Register device failed (%d)\n", r);
-		goto error;
+		goto error_free_hw;
 	}
 
 	if ((le16_to_cpu(interface_to_usbdev(intf)->descriptor.idVendor) ==
@@ -630,7 +632,7 @@ static int probe(struct usb_interface *intf,
 	}
 	if (r != 0) {
 		dev_err(&intf->dev, "FPGA download failed (%d)\n", r);
-		goto error;
+		goto error_unreg_hw;
 	}
 
 	tx->mac_fifo_full = 0;
@@ -640,21 +642,21 @@ static int probe(struct usb_interface *intf,
 	r = plfxlc_usb_init_hw(usb);
 	if (r < 0) {
 		dev_err(&intf->dev, "usb_init_hw failed (%d)\n", r);
-		goto error;
+		goto error_unreg_hw;
 	}
 
 	msleep(PLF_MSLEEP_TIME);
 	r = plfxlc_chip_switch_radio(chip, PLFXLC_RADIO_ON);
 	if (r < 0) {
 		dev_dbg(&intf->dev, "chip_switch_radio_on failed (%d)\n", r);
-		goto error;
+		goto error_unreg_hw;
 	}
 
 	msleep(PLF_MSLEEP_TIME);
 	r = plfxlc_chip_set_rate(chip, 8);
 	if (r < 0) {
 		dev_dbg(&intf->dev, "chip_set_rate failed (%d)\n", r);
-		goto error;
+		goto error_unreg_hw;
 	}
 
 	msleep(PLF_MSLEEP_TIME);
@@ -662,7 +664,7 @@ static int probe(struct usb_interface *intf,
 			    hw_address, ETH_ALEN, USB_REQ_MAC_WR);
 	if (r < 0) {
 		dev_dbg(&intf->dev, "MAC_WR failure (%d)\n", r);
-		goto error;
+		goto error_unreg_hw;
 	}
 
 	plfxlc_chip_enable_rxtx(chip);
@@ -689,12 +691,12 @@ static int probe(struct usb_interface *intf,
 	plfxlc_mac_init_hw(hw);
 	usb->initialized = true;
 	return 0;
+
+error_unreg_hw:
+	ieee80211_unregister_hw(hw);
+error_free_hw:
+	plfxlc_mac_release_hw(hw);
 error:
-	if (hw) {
-		plfxlc_mac_release(plfxlc_hw_mac(hw));
-		ieee80211_unregister_hw(hw);
-		ieee80211_free_hw(hw);
-	}
 	dev_err(&intf->dev, "pureLifi:Device error");
 	return r;
 }
@@ -728,8 +730,7 @@ static void disconnect(struct usb_interface *intf)
 	 */
 	usb_reset_device(interface_to_usbdev(intf));
 
-	plfxlc_mac_release(mac);
-	ieee80211_free_hw(hw);
+	plfxlc_mac_release_hw(hw);
 }
 
 static void plfxlc_usb_resume(struct plfxlc_usb *usb)
diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00soc.c b/drivers/net/wireless/ralink/rt2x00/rt2x00soc.c
index eface610178d..f7f3a2340c39 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2x00soc.c
+++ b/drivers/net/wireless/ralink/rt2x00/rt2x00soc.c
@@ -108,7 +108,7 @@ exit_free_device:
 }
 EXPORT_SYMBOL_GPL(rt2x00soc_probe);
 
-int rt2x00soc_remove(struct platform_device *pdev)
+void rt2x00soc_remove(struct platform_device *pdev)
 {
 	struct ieee80211_hw *hw = platform_get_drvdata(pdev);
 	struct rt2x00_dev *rt2x00dev = hw->priv;
@@ -119,8 +119,6 @@ int rt2x00soc_remove(struct platform_device *pdev)
 	rt2x00lib_remove_dev(rt2x00dev);
 	rt2x00soc_free_reg(rt2x00dev);
 	ieee80211_free_hw(hw);
-
-	return 0;
 }
 EXPORT_SYMBOL_GPL(rt2x00soc_remove);
 
diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00soc.h b/drivers/net/wireless/ralink/rt2x00/rt2x00soc.h
index 021fd06b3627..d6226b8a10e0 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2x00soc.h
+++ b/drivers/net/wireless/ralink/rt2x00/rt2x00soc.h
@@ -17,7 +17,7 @@
  * SoC driver handlers.
  */
 int rt2x00soc_probe(struct platform_device *pdev, const struct rt2x00_ops *ops);
-int rt2x00soc_remove(struct platform_device *pdev);
+void rt2x00soc_remove(struct platform_device *pdev);
 #ifdef CONFIG_PM
 int rt2x00soc_suspend(struct platform_device *pdev, pm_message_t state);
 int rt2x00soc_resume(struct platform_device *pdev);
diff --git a/drivers/net/wireless/realtek/rtl818x/rtl8187/dev.c b/drivers/net/wireless/realtek/rtl818x/rtl8187/dev.c
index 220ac5bdf279..8a57d6c72335 100644
--- a/drivers/net/wireless/realtek/rtl818x/rtl8187/dev.c
+++ b/drivers/net/wireless/realtek/rtl818x/rtl8187/dev.c
@@ -1041,10 +1041,11 @@ static void rtl8187_stop(struct ieee80211_hw *dev, bool suspend)
 	rtl818x_iowrite8(priv, &priv->map->CONFIG4, reg | RTL818X_CONFIG4_VCOOFF);
 	rtl818x_iowrite8(priv, &priv->map->EEPROM_CMD, RTL818X_EEPROM_CMD_NORMAL);
 
+	usb_kill_anchored_urbs(&priv->anchored);
+
 	while ((skb = skb_dequeue(&priv->b_tx_status.queue)))
 		dev_kfree_skb_any(skb);
 
-	usb_kill_anchored_urbs(&priv->anchored);
 	mutex_unlock(&priv->conf_mutex);
 
 	if (!priv->is_rtl8187b)
diff --git a/drivers/net/wireless/realtek/rtl8xxxu/core.c b/drivers/net/wireless/realtek/rtl8xxxu/core.c
index f95898f68d68..c6f69d87c38d 100644
--- a/drivers/net/wireless/realtek/rtl8xxxu/core.c
+++ b/drivers/net/wireless/realtek/rtl8xxxu/core.c
@@ -860,9 +860,10 @@ rtl8xxxu_writeN(struct rtl8xxxu_priv *priv, u16 addr, u8 *buf, u16 len)
 	return len;
 
 write_error:
-	dev_info(&udev->dev,
-		 "%s: Failed to write block at addr: %04x size: %04x\n",
-		 __func__, addr, blocksize);
+	if (rtl8xxxu_debug & RTL8XXXU_DEBUG_REG_WRITE)
+		dev_info(&udev->dev,
+			 "%s: Failed to write block at addr: %04x size: %04x\n",
+			 __func__, addr, blocksize);
 	return -EAGAIN;
 }
 
@@ -4064,8 +4065,14 @@ static int rtl8xxxu_init_device(struct ieee80211_hw *hw)
 	 */
 	rtl8xxxu_write16(priv, REG_TRXFF_BNDY + 2, fops->trxff_boundary);
 
-	ret = rtl8xxxu_download_firmware(priv);
-	dev_dbg(dev, "%s: download_firmware %i\n", __func__, ret);
+	for (int retry = 5; retry >= 0 ; retry--) {
+		ret = rtl8xxxu_download_firmware(priv);
+		dev_dbg(dev, "%s: download_firmware %i\n", __func__, ret);
+		if (ret != -EAGAIN)
+			break;
+		if (retry)
+			dev_dbg(dev, "%s: retry firmware download\n", __func__);
+	}
 	if (ret)
 		goto exit;
 	ret = rtl8xxxu_start_firmware(priv);
@@ -6610,7 +6617,7 @@ static int rtl8xxxu_submit_rx_urb(struct rtl8xxxu_priv *priv,
 		skb_size = fops->rx_agg_buf_size;
 		skb_size += (rx_desc_sz + sizeof(struct rtl8723au_phy_stats));
 	} else {
-		skb_size = IEEE80211_MAX_FRAME_LEN;
+		skb_size = IEEE80211_MAX_FRAME_LEN + rx_desc_sz;
 	}
 
 	skb = __netdev_alloc_skb(NULL, skb_size, GFP_KERNEL);
@@ -8147,6 +8154,8 @@ static const struct usb_device_id dev_table[] = {
 	.driver_info = (unsigned long)&rtl8192cu_fops},
 {USB_DEVICE_AND_INTERFACE_INFO(USB_VENDOR_ID_REALTEK, 0x817e, 0xff, 0xff, 0xff),
 	.driver_info = (unsigned long)&rtl8192cu_fops},
+{USB_DEVICE_AND_INTERFACE_INFO(USB_VENDOR_ID_REALTEK, 0x8186, 0xff, 0xff, 0xff),
+	.driver_info = (unsigned long)&rtl8192cu_fops},
 {USB_DEVICE_AND_INTERFACE_INFO(USB_VENDOR_ID_REALTEK, 0x818a, 0xff, 0xff, 0xff),
 	.driver_info = (unsigned long)&rtl8192cu_fops},
 {USB_DEVICE_AND_INTERFACE_INFO(USB_VENDOR_ID_REALTEK, 0x317f, 0xff, 0xff, 0xff),
@@ -8157,12 +8166,18 @@ static const struct usb_device_id dev_table[] = {
 	.driver_info = (unsigned long)&rtl8192cu_fops},
 {USB_DEVICE_AND_INTERFACE_INFO(0x050d, 0x1102, 0xff, 0xff, 0xff),
 	.driver_info = (unsigned long)&rtl8192cu_fops},
+{USB_DEVICE_AND_INTERFACE_INFO(0x050d, 0x11f2, 0xff, 0xff, 0xff),
+	.driver_info = (unsigned long)&rtl8192cu_fops},
 {USB_DEVICE_AND_INTERFACE_INFO(0x06f8, 0xe033, 0xff, 0xff, 0xff),
 	.driver_info = (unsigned long)&rtl8192cu_fops},
+{USB_DEVICE_AND_INTERFACE_INFO(0x07b8, 0x8188, 0xff, 0xff, 0xff),
+	.driver_info = (unsigned long)&rtl8192cu_fops},
 {USB_DEVICE_AND_INTERFACE_INFO(0x07b8, 0x8189, 0xff, 0xff, 0xff),
 	.driver_info = (unsigned long)&rtl8192cu_fops},
 {USB_DEVICE_AND_INTERFACE_INFO(0x0846, 0x9041, 0xff, 0xff, 0xff),
 	.driver_info = (unsigned long)&rtl8192cu_fops},
+{USB_DEVICE_AND_INTERFACE_INFO(0x0846, 0x9043, 0xff, 0xff, 0xff),
+	.driver_info = (unsigned long)&rtl8192cu_fops},
 {USB_DEVICE_AND_INTERFACE_INFO(0x0b05, 0x17ba, 0xff, 0xff, 0xff),
 	.driver_info = (unsigned long)&rtl8192cu_fops},
 {USB_DEVICE_AND_INTERFACE_INFO(USB_VENDOR_ID_REALTEK, 0x1e1e, 0xff, 0xff, 0xff),
@@ -8179,6 +8194,10 @@ static const struct usb_device_id dev_table[] = {
 	.driver_info = (unsigned long)&rtl8192cu_fops},
 {USB_DEVICE_AND_INTERFACE_INFO(0x13d3, 0x3357, 0xff, 0xff, 0xff),
 	.driver_info = (unsigned long)&rtl8192cu_fops},
+{USB_DEVICE_AND_INTERFACE_INFO(0x13d3, 0x3358, 0xff, 0xff, 0xff),
+	.driver_info = (unsigned long)&rtl8192cu_fops},
+{USB_DEVICE_AND_INTERFACE_INFO(0x13d3, 0x3359, 0xff, 0xff, 0xff),
+	.driver_info = (unsigned long)&rtl8192cu_fops},
 {USB_DEVICE_AND_INTERFACE_INFO(0x2001, 0x330b, 0xff, 0xff, 0xff),
 	.driver_info = (unsigned long)&rtl8192cu_fops},
 {USB_DEVICE_AND_INTERFACE_INFO(0x2019, 0x4902, 0xff, 0xff, 0xff),
@@ -8193,6 +8212,8 @@ static const struct usb_device_id dev_table[] = {
 	.driver_info = (unsigned long)&rtl8192cu_fops},
 {USB_DEVICE_AND_INTERFACE_INFO(0x4856, 0x0091, 0xff, 0xff, 0xff),
 	.driver_info = (unsigned long)&rtl8192cu_fops},
+{USB_DEVICE_AND_INTERFACE_INFO(0x9846, 0x9041, 0xff, 0xff, 0xff),
+	.driver_info = (unsigned long)&rtl8192cu_fops},
 {USB_DEVICE_AND_INTERFACE_INFO(0xcdab, 0x8010, 0xff, 0xff, 0xff),
 	.driver_info = (unsigned long)&rtl8192cu_fops},
 {USB_DEVICE_AND_INTERFACE_INFO(0x04f2, 0xaff7, 0xff, 0xff, 0xff),
@@ -8218,6 +8239,8 @@ static const struct usb_device_id dev_table[] = {
 	.driver_info = (unsigned long)&rtl8192cu_fops},
 {USB_DEVICE_AND_INTERFACE_INFO(0x0586, 0x341f, 0xff, 0xff, 0xff),
 	.driver_info = (unsigned long)&rtl8192cu_fops},
+{USB_DEVICE_AND_INTERFACE_INFO(0x06f8, 0xe033, 0xff, 0xff, 0xff),
+	.driver_info = (unsigned long)&rtl8192cu_fops},
 {USB_DEVICE_AND_INTERFACE_INFO(0x06f8, 0xe035, 0xff, 0xff, 0xff),
 	.driver_info = (unsigned long)&rtl8192cu_fops},
 {USB_DEVICE_AND_INTERFACE_INFO(0x0b05, 0x17ab, 0xff, 0xff, 0xff),
@@ -8226,6 +8249,8 @@ static const struct usb_device_id dev_table[] = {
 	.driver_info = (unsigned long)&rtl8192cu_fops},
 {USB_DEVICE_AND_INTERFACE_INFO(0x0df6, 0x0070, 0xff, 0xff, 0xff),
 	.driver_info = (unsigned long)&rtl8192cu_fops},
+{USB_DEVICE_AND_INTERFACE_INFO(0x0df6, 0x0077, 0xff, 0xff, 0xff),
+	.driver_info = (unsigned long)&rtl8192cu_fops},
 {USB_DEVICE_AND_INTERFACE_INFO(0x0789, 0x016d, 0xff, 0xff, 0xff),
 	.driver_info = (unsigned long)&rtl8192cu_fops},
 {USB_DEVICE_AND_INTERFACE_INFO(0x07aa, 0x0056, 0xff, 0xff, 0xff),
@@ -8248,6 +8273,8 @@ static const struct usb_device_id dev_table[] = {
 	.driver_info = (unsigned long)&rtl8192cu_fops},
 {USB_DEVICE_AND_INTERFACE_INFO(0x2001, 0x330a, 0xff, 0xff, 0xff),
 	.driver_info = (unsigned long)&rtl8192cu_fops},
+{USB_DEVICE_AND_INTERFACE_INFO(0x2001, 0x330d, 0xff, 0xff, 0xff),
+	.driver_info = (unsigned long)&rtl8192cu_fops},
 {USB_DEVICE_AND_INTERFACE_INFO(0x2019, 0xab2b, 0xff, 0xff, 0xff),
 	.driver_info = (unsigned long)&rtl8192cu_fops},
 {USB_DEVICE_AND_INTERFACE_INFO(0x20f4, 0x624d, 0xff, 0xff, 0xff),
diff --git a/drivers/net/wireless/realtek/rtlwifi/base.c b/drivers/net/wireless/realtek/rtlwifi/base.c
index aab4605de9c4..ff61867d142f 100644
--- a/drivers/net/wireless/realtek/rtlwifi/base.c
+++ b/drivers/net/wireless/realtek/rtlwifi/base.c
@@ -575,9 +575,15 @@ static void rtl_free_entries_from_ack_queue(struct ieee80211_hw *hw,
 
 void rtl_deinit_core(struct ieee80211_hw *hw)
 {
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+
 	rtl_c2hcmd_launcher(hw, 0);
 	rtl_free_entries_from_scan_list(hw);
 	rtl_free_entries_from_ack_queue(hw, false);
+	if (rtlpriv->works.rtl_wq) {
+		destroy_workqueue(rtlpriv->works.rtl_wq);
+		rtlpriv->works.rtl_wq = NULL;
+	}
 }
 EXPORT_SYMBOL_GPL(rtl_deinit_core);
 
@@ -2696,9 +2702,6 @@ MODULE_AUTHOR("Larry Finger	<Larry.FInger@lwfinger.net>");
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Realtek 802.11n PCI wireless core");
 
-struct rtl_global_var rtl_global_var = {};
-EXPORT_SYMBOL_GPL(rtl_global_var);
-
 static int __init rtl_core_module_init(void)
 {
 	BUILD_BUG_ON(TX_PWR_BY_RATE_NUM_RATE < TX_PWR_BY_RATE_NUM_SECTION);
@@ -2712,10 +2715,6 @@ static int __init rtl_core_module_init(void)
 	/* add debugfs */
 	rtl_debugfs_add_topdir();
 
-	/* init some global vars */
-	INIT_LIST_HEAD(&rtl_global_var.glb_priv_list);
-	spin_lock_init(&rtl_global_var.glb_list_lock);
-
 	return 0;
 }
 
diff --git a/drivers/net/wireless/realtek/rtlwifi/base.h b/drivers/net/wireless/realtek/rtlwifi/base.h
index f081a9a90563..f3a6a43a42ec 100644
--- a/drivers/net/wireless/realtek/rtlwifi/base.h
+++ b/drivers/net/wireless/realtek/rtlwifi/base.h
@@ -124,7 +124,6 @@ int rtl_send_smps_action(struct ieee80211_hw *hw,
 u8 *rtl_find_ie(u8 *data, unsigned int len, u8 ie);
 void rtl_recognize_peer(struct ieee80211_hw *hw, u8 *data, unsigned int len);
 u8 rtl_tid_to_ac(u8 tid);
-extern struct rtl_global_var rtl_global_var;
 void rtl_phy_scan_operation_backup(struct ieee80211_hw *hw, u8 operation);
 
 #endif
diff --git a/drivers/net/wireless/realtek/rtlwifi/pci.c b/drivers/net/wireless/realtek/rtlwifi/pci.c
index 11709b6c83f1..d080469264cf 100644
--- a/drivers/net/wireless/realtek/rtlwifi/pci.c
+++ b/drivers/net/wireless/realtek/rtlwifi/pci.c
@@ -155,6 +155,16 @@ static void _rtl_pci_update_default_setting(struct ieee80211_hw *hw)
 	    ((u8)init_aspm) == (PCI_EXP_LNKCTL_ASPM_L0S |
 				PCI_EXP_LNKCTL_ASPM_L1 | PCI_EXP_LNKCTL_CCC))
 		ppsc->support_aspm = false;
+
+	/* RTL8723BE found on some ASUSTek laptops, such as F441U and
+	 * X555UQ with subsystem ID 11ad:1723 are known to output large
+	 * amounts of PCIe AER errors during and after boot up, causing
+	 * heavy lags, poor network throughput, and occasional lock-ups.
+	 */
+	if (rtlpriv->rtlhal.hw_type == HARDWARE_TYPE_RTL8723BE &&
+	    (rtlpci->pdev->subsystem_vendor == 0x11ad &&
+	     rtlpci->pdev->subsystem_device == 0x1723))
+		ppsc->support_aspm = false;
 }
 
 static bool _rtl_pci_platform_switch_device_pci_aspm(
@@ -295,46 +305,6 @@ static bool rtl_pci_get_amd_l1_patch(struct ieee80211_hw *hw)
 	return status;
 }
 
-static bool rtl_pci_check_buddy_priv(struct ieee80211_hw *hw,
-				     struct rtl_priv **buddy_priv)
-{
-	struct rtl_priv *rtlpriv = rtl_priv(hw);
-	struct rtl_pci_priv *pcipriv = rtl_pcipriv(hw);
-	struct rtl_priv *tpriv = NULL, *iter;
-	struct rtl_pci_priv *tpcipriv = NULL;
-
-	if (!list_empty(&rtlpriv->glb_var->glb_priv_list)) {
-		list_for_each_entry(iter, &rtlpriv->glb_var->glb_priv_list,
-				    list) {
-			tpcipriv = (struct rtl_pci_priv *)iter->priv;
-			rtl_dbg(rtlpriv, COMP_INIT, DBG_LOUD,
-				"pcipriv->ndis_adapter.funcnumber %x\n",
-				pcipriv->ndis_adapter.funcnumber);
-			rtl_dbg(rtlpriv, COMP_INIT, DBG_LOUD,
-				"tpcipriv->ndis_adapter.funcnumber %x\n",
-				tpcipriv->ndis_adapter.funcnumber);
-
-			if (pcipriv->ndis_adapter.busnumber ==
-			    tpcipriv->ndis_adapter.busnumber &&
-			    pcipriv->ndis_adapter.devnumber ==
-			    tpcipriv->ndis_adapter.devnumber &&
-			    pcipriv->ndis_adapter.funcnumber !=
-			    tpcipriv->ndis_adapter.funcnumber) {
-				tpriv = iter;
-				break;
-			}
-		}
-	}
-
-	rtl_dbg(rtlpriv, COMP_INIT, DBG_LOUD,
-		"find_buddy_priv %d\n", tpriv != NULL);
-
-	if (tpriv)
-		*buddy_priv = tpriv;
-
-	return tpriv != NULL;
-}
-
 static void rtl_pci_parse_configuration(struct pci_dev *pdev,
 					struct ieee80211_hw *hw)
 {
@@ -602,8 +572,11 @@ remap:
 		dma_map_single(&rtlpci->pdev->dev, skb_tail_pointer(skb),
 			       rtlpci->rxbuffersize, DMA_FROM_DEVICE);
 	bufferaddress = *((dma_addr_t *)skb->cb);
-	if (dma_mapping_error(&rtlpci->pdev->dev, bufferaddress))
+	if (dma_mapping_error(&rtlpci->pdev->dev, bufferaddress)) {
+		if (!new_skb)
+			kfree_skb(skb);
 		return 0;
+	}
 	rtlpci->rx_ring[rxring_idx].rx_buf[desc_idx] = skb;
 	if (rtlpriv->use_new_trx_flow) {
 		/* skb->cb may be 64 bit address */
@@ -832,13 +805,19 @@ new_trx_end:
 		skb = new_skb;
 no_new:
 		if (rtlpriv->use_new_trx_flow) {
-			_rtl_pci_init_one_rxdesc(hw, skb, (u8 *)buffer_desc,
-						 rxring_idx,
-						 rtlpci->rx_ring[rxring_idx].idx);
+			if (!_rtl_pci_init_one_rxdesc(hw, skb, (u8 *)buffer_desc,
+						      rxring_idx,
+						      rtlpci->rx_ring[rxring_idx].idx)) {
+				if (new_skb)
+					dev_kfree_skb_any(skb);
+			}
 		} else {
-			_rtl_pci_init_one_rxdesc(hw, skb, (u8 *)pdesc,
-						 rxring_idx,
-						 rtlpci->rx_ring[rxring_idx].idx);
+			if (!_rtl_pci_init_one_rxdesc(hw, skb, (u8 *)pdesc,
+						      rxring_idx,
+						      rtlpci->rx_ring[rxring_idx].idx)) {
+				if (new_skb)
+					dev_kfree_skb_any(skb);
+			}
 			if (rtlpci->rx_ring[rxring_idx].idx ==
 			    rtlpci->rxringcount - 1)
 				rtlpriv->cfg->ops->set_desc(hw, (u8 *)pdesc,
@@ -1696,8 +1675,6 @@ static void rtl_pci_deinit(struct ieee80211_hw *hw)
 	synchronize_irq(rtlpci->pdev->irq);
 	tasklet_kill(&rtlpriv->works.irq_tasklet);
 	cancel_work_sync(&rtlpriv->works.lps_change_work);
-
-	destroy_workqueue(rtlpriv->works.rtl_wq);
 }
 
 static int rtl_pci_init(struct ieee80211_hw *hw, struct pci_dev *pdev)
@@ -2011,7 +1988,6 @@ static bool _rtl_pci_find_adapter(struct pci_dev *pdev,
 		pcipriv->ndis_adapter.amd_l1_patch);
 
 	rtl_pci_parse_configuration(pdev, hw);
-	list_add_tail(&rtlpriv->list, &rtlpriv->glb_var->glb_priv_list);
 
 	return true;
 }
@@ -2158,7 +2134,6 @@ int rtl_pci_probe(struct pci_dev *pdev,
 	rtlpriv->rtlhal.interface = INTF_PCI;
 	rtlpriv->cfg = (struct rtl_hal_cfg *)(id->driver_data);
 	rtlpriv->intf_ops = &rtl_pci_ops;
-	rtlpriv->glb_var = &rtl_global_var;
 	rtl_efuse_ops_init(hw);
 
 	/* MEM map */
@@ -2209,7 +2184,7 @@ int rtl_pci_probe(struct pci_dev *pdev,
 	if (rtlpriv->cfg->ops->init_sw_vars(hw)) {
 		pr_err("Can't init_sw_vars\n");
 		err = -ENODEV;
-		goto fail3;
+		goto fail2;
 	}
 	rtl_init_sw_leds(hw);
 
@@ -2227,14 +2202,14 @@ int rtl_pci_probe(struct pci_dev *pdev,
 	err = rtl_pci_init(hw, pdev);
 	if (err) {
 		pr_err("Failed to init PCI\n");
-		goto fail3;
+		goto fail4;
 	}
 
 	err = ieee80211_register_hw(hw);
 	if (err) {
 		pr_err("Can't register mac80211 hw.\n");
 		err = -ENODEV;
-		goto fail3;
+		goto fail5;
 	}
 	rtlpriv->mac80211.mac80211_registered = 1;
 
@@ -2257,16 +2232,19 @@ int rtl_pci_probe(struct pci_dev *pdev,
 	set_bit(RTL_STATUS_INTERFACE_START, &rtlpriv->status);
 	return 0;
 
-fail3:
-	pci_set_drvdata(pdev, NULL);
+fail5:
+	rtl_pci_deinit(hw);
+fail4:
 	rtl_deinit_core(hw);
+fail3:
+	wait_for_completion(&rtlpriv->firmware_loading_complete);
+	rtlpriv->cfg->ops->deinit_sw_vars(hw);
 
 fail2:
 	if (rtlpriv->io.pci_mem_start != 0)
 		pci_iounmap(pdev, (void __iomem *)rtlpriv->io.pci_mem_start);
 
 	pci_release_regions(pdev);
-	complete(&rtlpriv->firmware_loading_complete);
 
 fail1:
 	if (hw)
@@ -2317,7 +2295,6 @@ void rtl_pci_disconnect(struct pci_dev *pdev)
 	if (rtlpci->using_msi)
 		pci_disable_msi(rtlpci->pdev);
 
-	list_del(&rtlpriv->list);
 	if (rtlpriv->io.pci_mem_start != 0) {
 		pci_iounmap(pdev, (void __iomem *)rtlpriv->io.pci_mem_start);
 		pci_release_regions(pdev);
@@ -2376,7 +2353,6 @@ EXPORT_SYMBOL(rtl_pci_resume);
 const struct rtl_intf_ops rtl_pci_ops = {
 	.adapter_start = rtl_pci_start,
 	.adapter_stop = rtl_pci_stop,
-	.check_buddy_priv = rtl_pci_check_buddy_priv,
 	.adapter_tx = rtl_pci_tx,
 	.flush = rtl_pci_flush,
 	.reset_trx_ring = rtl_pci_reset_trx_ring,
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192se/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192se/sw.c
index bbf8ff63dced..e63c67b1861b 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192se/sw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192se/sw.c
@@ -64,22 +64,23 @@ static void rtl92se_fw_cb(const struct firmware *firmware, void *context)
 
 	rtl_dbg(rtlpriv, COMP_ERR, DBG_LOUD,
 		"Firmware callback routine entered!\n");
-	complete(&rtlpriv->firmware_loading_complete);
 	if (!firmware) {
 		pr_err("Firmware %s not available\n", fw_name);
 		rtlpriv->max_fw_size = 0;
-		return;
+		goto exit;
 	}
 	if (firmware->size > rtlpriv->max_fw_size) {
 		pr_err("Firmware is too big!\n");
 		rtlpriv->max_fw_size = 0;
 		release_firmware(firmware);
-		return;
+		goto exit;
 	}
 	pfirmware = (struct rt_firmware *)rtlpriv->rtlhal.pfirmware;
 	memcpy(pfirmware->sz_fw_tmpbuffer, firmware->data, firmware->size);
 	pfirmware->sz_fw_tmpbufferlen = firmware->size;
 	release_firmware(firmware);
+exit:
+	complete(&rtlpriv->firmware_loading_complete);
 }
 
 static int rtl92s_init_sw_vars(struct ieee80211_hw *hw)
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/fw.h b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/fw.h
index c269942b3f4a..af8d17b9e012 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/fw.h
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/fw.h
@@ -197,9 +197,9 @@ enum rtl8821a_h2c_cmd {
 
 /* _MEDIA_STATUS_RPT_PARM_CMD1 */
 #define SET_H2CCMD_MSRRPT_PARM_OPMODE(__cmd, __value)	\
-	u8p_replace_bits(__cmd + 1, __value, BIT(0))
+	u8p_replace_bits(__cmd, __value, BIT(0))
 #define SET_H2CCMD_MSRRPT_PARM_MACID_IND(__cmd, __value)	\
-	u8p_replace_bits(__cmd + 1, __value, BIT(1))
+	u8p_replace_bits(__cmd, __value, BIT(1))
 
 /* AP_OFFLOAD */
 #define SET_H2CCMD_AP_OFFLOAD_ON(__cmd, __value)	\
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/phy.c b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/phy.c
index 1be51ea3f3c8..9eddbada8af1 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/phy.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/phy.c
@@ -2033,8 +2033,10 @@ static bool _rtl8821ae_phy_config_bb_with_pgheaderfile(struct ieee80211_hw *hw,
 			if (!_rtl8821ae_check_condition(hw, v1)) {
 				i += 2; /* skip the pair of expression*/
 				v2 = array[i+1];
-				while (v2 != 0xDEAD)
+				while (v2 != 0xDEAD) {
 					i += 3;
+					v2 = array[i + 1];
+				}
 			}
 		}
 	}
diff --git a/drivers/net/wireless/realtek/rtlwifi/usb.c b/drivers/net/wireless/realtek/rtlwifi/usb.c
index d37a017b2b81..f5718e570011 100644
--- a/drivers/net/wireless/realtek/rtlwifi/usb.c
+++ b/drivers/net/wireless/realtek/rtlwifi/usb.c
@@ -629,11 +629,6 @@ static void _rtl_usb_cleanup_rx(struct ieee80211_hw *hw)
 	tasklet_kill(&rtlusb->rx_work_tasklet);
 	cancel_work_sync(&rtlpriv->works.lps_change_work);
 
-	if (rtlpriv->works.rtl_wq) {
-		destroy_workqueue(rtlpriv->works.rtl_wq);
-		rtlpriv->works.rtl_wq = NULL;
-	}
-
 	skb_queue_purge(&rtlusb->rx_queue);
 
 	while ((urb = usb_get_from_anchor(&rtlusb->rx_cleanup_urbs))) {
@@ -1028,19 +1023,22 @@ int rtl_usb_probe(struct usb_interface *intf,
 	err = ieee80211_register_hw(hw);
 	if (err) {
 		pr_err("Can't register mac80211 hw.\n");
-		goto error_out;
+		goto error_init_vars;
 	}
 	rtlpriv->mac80211.mac80211_registered = 1;
 
 	set_bit(RTL_STATUS_INTERFACE_START, &rtlpriv->status);
 	return 0;
 
+error_init_vars:
+	wait_for_completion(&rtlpriv->firmware_loading_complete);
+	rtlpriv->cfg->ops->deinit_sw_vars(hw);
 error_out:
+	rtl_usb_deinit(hw);
 	rtl_deinit_core(hw);
 error_out2:
 	_rtl_usb_io_handler_release(hw);
 	usb_put_dev(udev);
-	complete(&rtlpriv->firmware_loading_complete);
 	kfree(rtlpriv->usb_data);
 	ieee80211_free_hw(hw);
 	return -ENODEV;
diff --git a/drivers/net/wireless/realtek/rtlwifi/wifi.h b/drivers/net/wireless/realtek/rtlwifi/wifi.h
index ae6e351bc83c..f1830ddcdd8c 100644
--- a/drivers/net/wireless/realtek/rtlwifi/wifi.h
+++ b/drivers/net/wireless/realtek/rtlwifi/wifi.h
@@ -2270,8 +2270,6 @@ struct rtl_intf_ops {
 	/*com */
 	int (*adapter_start)(struct ieee80211_hw *hw);
 	void (*adapter_stop)(struct ieee80211_hw *hw);
-	bool (*check_buddy_priv)(struct ieee80211_hw *hw,
-				 struct rtl_priv **buddy_priv);
 
 	int (*adapter_tx)(struct ieee80211_hw *hw,
 			  struct ieee80211_sta *sta,
@@ -2514,14 +2512,6 @@ struct dig_t {
 	u32 rssi_max;
 };
 
-struct rtl_global_var {
-	/* from this list we can get
-	 * other adapter's rtl_priv
-	 */
-	struct list_head glb_priv_list;
-	spinlock_t glb_list_lock;
-};
-
 #define IN_4WAY_TIMEOUT_TIME	(30 * MSEC_PER_SEC)	/* 30 seconds */
 
 struct rtl_btc_info {
@@ -2667,9 +2657,7 @@ struct rtl_scan_list {
 struct rtl_priv {
 	struct ieee80211_hw *hw;
 	struct completion firmware_loading_complete;
-	struct list_head list;
 	struct rtl_priv *buddy_priv;
-	struct rtl_global_var *glb_var;
 	struct rtl_dmsp_ctl dmsp_ctl;
 	struct rtl_locks locks;
 	struct rtl_works works;
diff --git a/drivers/net/wireless/realtek/rtw88/coex.c b/drivers/net/wireless/realtek/rtw88/coex.c
index a99776af56c2..c476e65c4d71 100644
--- a/drivers/net/wireless/realtek/rtw88/coex.c
+++ b/drivers/net/wireless/realtek/rtw88/coex.c
@@ -309,7 +309,7 @@ static void rtw_coex_tdma_timer_base(struct rtw_dev *rtwdev, u8 type)
 {
 	struct rtw_coex *coex = &rtwdev->coex;
 	struct rtw_coex_stat *coex_stat = &coex->stat;
-	u8 para[2] = {0};
+	u8 para[6] = {};
 	u8 times;
 	u16 tbtt_interval = coex_stat->wl_beacon_interval;
 
diff --git a/drivers/net/wireless/realtek/rtw88/hci.h b/drivers/net/wireless/realtek/rtw88/hci.h
index 96aeda26014e..d4bee9c3ecfe 100644
--- a/drivers/net/wireless/realtek/rtw88/hci.h
+++ b/drivers/net/wireless/realtek/rtw88/hci.h
@@ -19,6 +19,8 @@ struct rtw_hci_ops {
 	void (*link_ps)(struct rtw_dev *rtwdev, bool enter);
 	void (*interface_cfg)(struct rtw_dev *rtwdev);
 	void (*dynamic_rx_agg)(struct rtw_dev *rtwdev, bool enable);
+	void (*write_firmware_page)(struct rtw_dev *rtwdev, u32 page,
+				    const u8 *data, u32 size);
 
 	int (*write_data_rsvd_page)(struct rtw_dev *rtwdev, u8 *buf, u32 size);
 	int (*write_data_h2c)(struct rtw_dev *rtwdev, u8 *buf, u32 size);
@@ -79,6 +81,12 @@ static inline void rtw_hci_dynamic_rx_agg(struct rtw_dev *rtwdev, bool enable)
 		rtwdev->hci.ops->dynamic_rx_agg(rtwdev, enable);
 }
 
+static inline void rtw_hci_write_firmware_page(struct rtw_dev *rtwdev, u32 page,
+					       const u8 *data, u32 size)
+{
+	rtwdev->hci.ops->write_firmware_page(rtwdev, page, data, size);
+}
+
 static inline int
 rtw_hci_write_data_rsvd_page(struct rtw_dev *rtwdev, u8 *buf, u32 size)
 {
diff --git a/drivers/net/wireless/realtek/rtw88/mac.c b/drivers/net/wireless/realtek/rtw88/mac.c
index 564f5988ee82..efb1da198e74 100644
--- a/drivers/net/wireless/realtek/rtw88/mac.c
+++ b/drivers/net/wireless/realtek/rtw88/mac.c
@@ -783,7 +783,8 @@ static int __rtw_download_firmware(struct rtw_dev *rtwdev,
 	if (!check_firmware_size(data, size))
 		return -EINVAL;
 
-	if (!ltecoex_read_reg(rtwdev, 0x38, &ltecoex_bckp))
+	if (rtwdev->chip->ltecoex_addr &&
+	    !ltecoex_read_reg(rtwdev, 0x38, &ltecoex_bckp))
 		return -EBUSY;
 
 	wlan_cpu_enable(rtwdev, false);
@@ -801,7 +802,8 @@ static int __rtw_download_firmware(struct rtw_dev *rtwdev,
 
 	wlan_cpu_enable(rtwdev, true);
 
-	if (!ltecoex_reg_write(rtwdev, 0x38, ltecoex_bckp)) {
+	if (rtwdev->chip->ltecoex_addr &&
+	    !ltecoex_reg_write(rtwdev, 0x38, ltecoex_bckp)) {
 		ret = -EBUSY;
 		goto dlfw_fail;
 	}
@@ -852,8 +854,8 @@ fwdl_ready:
 	}
 }
 
-static void
-write_firmware_page(struct rtw_dev *rtwdev, u32 page, const u8 *data, u32 size)
+void rtw_write_firmware_page(struct rtw_dev *rtwdev, u32 page,
+			     const u8 *data, u32 size)
 {
 	u32 val32;
 	u32 block_nr;
@@ -883,6 +885,7 @@ write_firmware_page(struct rtw_dev *rtwdev, u32 page, const u8 *data, u32 size)
 		rtw_write32(rtwdev, write_addr, le32_to_cpu(remain_data));
 	}
 }
+EXPORT_SYMBOL(rtw_write_firmware_page);
 
 static int
 download_firmware_legacy(struct rtw_dev *rtwdev, const u8 *data, u32 size)
@@ -900,11 +903,13 @@ download_firmware_legacy(struct rtw_dev *rtwdev, const u8 *data, u32 size)
 	rtw_write8_set(rtwdev, REG_MCUFW_CTRL, BIT_FWDL_CHK_RPT);
 
 	for (page = 0; page < total_page; page++) {
-		write_firmware_page(rtwdev, page, data, DLFW_PAGE_SIZE_LEGACY);
+		rtw_hci_write_firmware_page(rtwdev, page, data,
+					    DLFW_PAGE_SIZE_LEGACY);
 		data += DLFW_PAGE_SIZE_LEGACY;
 	}
 	if (last_page_size)
-		write_firmware_page(rtwdev, page, data, last_page_size);
+		rtw_hci_write_firmware_page(rtwdev, page, data,
+					    last_page_size);
 
 	if (!check_hw_ready(rtwdev, REG_MCUFW_CTRL, BIT_FWDL_CHK_RPT, 1)) {
 		rtw_err(rtwdev, "failed to check download firmware report\n");
diff --git a/drivers/net/wireless/realtek/rtw88/mac.h b/drivers/net/wireless/realtek/rtw88/mac.h
index 58c3dccc14bb..737c6d5d8da7 100644
--- a/drivers/net/wireless/realtek/rtw88/mac.h
+++ b/drivers/net/wireless/realtek/rtw88/mac.h
@@ -32,6 +32,8 @@ void rtw_set_channel_mac(struct rtw_dev *rtwdev, u8 channel, u8 bw,
 			 u8 primary_ch_idx);
 int rtw_mac_power_on(struct rtw_dev *rtwdev);
 void rtw_mac_power_off(struct rtw_dev *rtwdev);
+void rtw_write_firmware_page(struct rtw_dev *rtwdev, u32 page,
+			     const u8 *data, u32 size);
 int rtw_download_firmware(struct rtw_dev *rtwdev, struct rtw_fw_state *fw);
 int rtw_mac_init(struct rtw_dev *rtwdev);
 void rtw_mac_flush_queues(struct rtw_dev *rtwdev, u32 queues, bool drop);
diff --git a/drivers/net/wireless/realtek/rtw88/main.c b/drivers/net/wireless/realtek/rtw88/main.c
index bbdef38c7e34..01c8b748b20b 100644
--- a/drivers/net/wireless/realtek/rtw88/main.c
+++ b/drivers/net/wireless/realtek/rtw88/main.c
@@ -329,7 +329,7 @@ int rtw_sta_add(struct rtw_dev *rtwdev, struct ieee80211_sta *sta,
 	struct rtw_vif *rtwvif = (struct rtw_vif *)vif->drv_priv;
 	int i;
 
-	if (vif->type == NL80211_IFTYPE_STATION) {
+	if (vif->type == NL80211_IFTYPE_STATION && !sta->tdls) {
 		si->mac_id = rtwvif->mac_id;
 	} else {
 		si->mac_id = rtw_acquire_macid(rtwdev);
@@ -366,7 +366,7 @@ void rtw_sta_remove(struct rtw_dev *rtwdev, struct ieee80211_sta *sta,
 
 	cancel_work_sync(&si->rc_work);
 
-	if (vif->type != NL80211_IFTYPE_STATION)
+	if (vif->type != NL80211_IFTYPE_STATION || sta->tdls)
 		rtw_release_macid(rtwdev, si->mac_id);
 	if (fw_exist)
 		rtw_fw_media_status_report(rtwdev, si->mac_id, false);
@@ -1543,6 +1543,7 @@ static void rtw_init_ht_cap(struct rtw_dev *rtwdev,
 {
 	const struct rtw_chip_info *chip = rtwdev->chip;
 	struct rtw_efuse *efuse = &rtwdev->efuse;
+	int i;
 
 	ht_cap->ht_supported = true;
 	ht_cap->cap = 0;
@@ -1562,25 +1563,20 @@ static void rtw_init_ht_cap(struct rtw_dev *rtwdev,
 	ht_cap->ampdu_factor = IEEE80211_HT_MAX_AMPDU_64K;
 	ht_cap->ampdu_density = chip->ampdu_density;
 	ht_cap->mcs.tx_params = IEEE80211_HT_MCS_TX_DEFINED;
-	if (efuse->hw_cap.nss > 1) {
-		ht_cap->mcs.rx_mask[0] = 0xFF;
-		ht_cap->mcs.rx_mask[1] = 0xFF;
-		ht_cap->mcs.rx_mask[4] = 0x01;
-		ht_cap->mcs.rx_highest = cpu_to_le16(300);
-	} else {
-		ht_cap->mcs.rx_mask[0] = 0xFF;
-		ht_cap->mcs.rx_mask[1] = 0x00;
-		ht_cap->mcs.rx_mask[4] = 0x01;
-		ht_cap->mcs.rx_highest = cpu_to_le16(150);
-	}
+
+	for (i = 0; i < efuse->hw_cap.nss; i++)
+		ht_cap->mcs.rx_mask[i] = 0xFF;
+	ht_cap->mcs.rx_mask[4] = 0x01;
+	ht_cap->mcs.rx_highest = cpu_to_le16(150 * efuse->hw_cap.nss);
 }
 
 static void rtw_init_vht_cap(struct rtw_dev *rtwdev,
 			     struct ieee80211_sta_vht_cap *vht_cap)
 {
 	struct rtw_efuse *efuse = &rtwdev->efuse;
-	u16 mcs_map;
+	u16 mcs_map = 0;
 	__le16 highest;
+	int i;
 
 	if (efuse->hw_cap.ptcl != EFUSE_HW_CAP_IGNORE &&
 	    efuse->hw_cap.ptcl != EFUSE_HW_CAP_PTCL_VHT)
@@ -1603,21 +1599,15 @@ static void rtw_init_vht_cap(struct rtw_dev *rtwdev,
 	if (rtw_chip_has_rx_ldpc(rtwdev))
 		vht_cap->cap |= IEEE80211_VHT_CAP_RXLDPC;
 
-	mcs_map = IEEE80211_VHT_MCS_SUPPORT_0_9 << 0 |
-		  IEEE80211_VHT_MCS_NOT_SUPPORTED << 4 |
-		  IEEE80211_VHT_MCS_NOT_SUPPORTED << 6 |
-		  IEEE80211_VHT_MCS_NOT_SUPPORTED << 8 |
-		  IEEE80211_VHT_MCS_NOT_SUPPORTED << 10 |
-		  IEEE80211_VHT_MCS_NOT_SUPPORTED << 12 |
-		  IEEE80211_VHT_MCS_NOT_SUPPORTED << 14;
-	if (efuse->hw_cap.nss > 1) {
-		highest = cpu_to_le16(780);
-		mcs_map |= IEEE80211_VHT_MCS_SUPPORT_0_9 << 2;
-	} else {
-		highest = cpu_to_le16(390);
-		mcs_map |= IEEE80211_VHT_MCS_NOT_SUPPORTED << 2;
+	for (i = 0; i < 8; i++) {
+		if (i < efuse->hw_cap.nss)
+			mcs_map |= IEEE80211_VHT_MCS_SUPPORT_0_9 << (i * 2);
+		else
+			mcs_map |= IEEE80211_VHT_MCS_NOT_SUPPORTED << (i * 2);
 	}
 
+	highest = cpu_to_le16(390 * efuse->hw_cap.nss);
+
 	vht_cap->vht_mcs.rx_mcs_map = cpu_to_le16(mcs_map);
 	vht_cap->vht_mcs.tx_mcs_map = cpu_to_le16(mcs_map);
 	vht_cap->vht_mcs.rx_highest = highest;
diff --git a/drivers/net/wireless/realtek/rtw88/main.h b/drivers/net/wireless/realtek/rtw88/main.h
index 945117afe143..c808bb271e9d 100644
--- a/drivers/net/wireless/realtek/rtw88/main.h
+++ b/drivers/net/wireless/realtek/rtw88/main.h
@@ -508,12 +508,12 @@ struct rtw_5g_txpwr_idx {
 	struct rtw_5g_vht_ns_pwr_idx_diff vht_2s_diff;
 	struct rtw_5g_vht_ns_pwr_idx_diff vht_3s_diff;
 	struct rtw_5g_vht_ns_pwr_idx_diff vht_4s_diff;
-};
+} __packed;
 
 struct rtw_txpwr_idx {
 	struct rtw_2g_txpwr_idx pwr_idx_2g;
 	struct rtw_5g_txpwr_idx pwr_idx_5g;
-};
+} __packed;
 
 struct rtw_channel_params {
 	u8 center_chan;
diff --git a/drivers/net/wireless/realtek/rtw88/pci.c b/drivers/net/wireless/realtek/rtw88/pci.c
index 0b9b8807af2c..fab9bb9257dd 100644
--- a/drivers/net/wireless/realtek/rtw88/pci.c
+++ b/drivers/net/wireless/realtek/rtw88/pci.c
@@ -12,6 +12,7 @@
 #include "fw.h"
 #include "ps.h"
 #include "debug.h"
+#include "mac.h"
 
 static bool rtw_disable_msi;
 static bool rtw_pci_disable_aspm;
@@ -1602,6 +1603,7 @@ static struct rtw_hci_ops rtw_pci_ops = {
 	.link_ps = rtw_pci_link_ps,
 	.interface_cfg = rtw_pci_interface_cfg,
 	.dynamic_rx_agg = NULL,
+	.write_firmware_page = rtw_write_firmware_page,
 
 	.read8 = rtw_pci_read8,
 	.read16 = rtw_pci_read16,
diff --git a/drivers/net/wireless/realtek/rtw88/reg.h b/drivers/net/wireless/realtek/rtw88/reg.h
index 4d9b8668e8b0..2708ee2f12a4 100644
--- a/drivers/net/wireless/realtek/rtw88/reg.h
+++ b/drivers/net/wireless/realtek/rtw88/reg.h
@@ -109,6 +109,7 @@
 #define BIT_SHIFT_ROM_PGE	16
 #define BIT_FW_INIT_RDY		BIT(15)
 #define BIT_FW_DW_RDY		BIT(14)
+#define BIT_CPU_CLK_SEL		(BIT(12) | BIT(13))
 #define BIT_RPWM_TOGGLE		BIT(7)
 #define BIT_RAM_DL_SEL		BIT(7)	/* legacy only */
 #define BIT_DMEM_CHKSUM_OK	BIT(6)
@@ -126,7 +127,7 @@
 				 BIT_CHECK_SUM_OK)
 #define FW_READY_LEGACY		(BIT_MCUFWDL_RDY | BIT_FWDL_CHK_RPT |	       \
 				 BIT_WINTINI_RDY | BIT_RAM_DL_SEL)
-#define FW_READY_MASK		0xffff
+#define FW_READY_MASK		(0xffff & ~BIT_CPU_CLK_SEL)
 
 #define REG_MCU_TST_CFG		0x84
 #define VAL_FW_TRIGGER		0x1
diff --git a/drivers/net/wireless/realtek/rtw88/rtw8703b.c b/drivers/net/wireless/realtek/rtw88/rtw8703b.c
index 222608de33cd..a977aad9c650 100644
--- a/drivers/net/wireless/realtek/rtw88/rtw8703b.c
+++ b/drivers/net/wireless/realtek/rtw88/rtw8703b.c
@@ -911,7 +911,7 @@ static void rtw8703b_set_channel_bb(struct rtw_dev *rtwdev, u8 channel, u8 bw,
 		rtw_write32_mask(rtwdev, REG_FPGA0_RFMOD, BIT_MASK_RFMOD, 0x0);
 		rtw_write32_mask(rtwdev, REG_FPGA1_RFMOD, BIT_MASK_RFMOD, 0x0);
 		rtw_write32_mask(rtwdev, REG_OFDM0_TX_PSD_NOISE,
-				 GENMASK(31, 20), 0x0);
+				 GENMASK(31, 30), 0x0);
 		rtw_write32(rtwdev, REG_BBRX_DFIR, 0x4A880000);
 		rtw_write32(rtwdev, REG_OFDM0_A_TX_AFE, 0x19F60000);
 		break;
@@ -1257,9 +1257,9 @@ static u8 rtw8703b_iqk_rx_path(struct rtw_dev *rtwdev,
 	rtw_write32(rtwdev, REG_RXIQK_TONE_A_11N, 0x38008c1c);
 	rtw_write32(rtwdev, REG_TX_IQK_TONE_B, 0x38008c1c);
 	rtw_write32(rtwdev, REG_RX_IQK_TONE_B, 0x38008c1c);
-	rtw_write32(rtwdev, REG_TXIQK_PI_A_11N, 0x8216000f);
+	rtw_write32(rtwdev, REG_TXIQK_PI_A_11N, 0x8214030f);
 	rtw_write32(rtwdev, REG_RXIQK_PI_A_11N, 0x28110000);
-	rtw_write32(rtwdev, REG_TXIQK_PI_B, 0x28110000);
+	rtw_write32(rtwdev, REG_TXIQK_PI_B, 0x82110000);
 	rtw_write32(rtwdev, REG_RXIQK_PI_B, 0x28110000);
 
 	/* LOK setting */
@@ -1431,7 +1431,7 @@ void rtw8703b_iqk_fill_a_matrix(struct rtw_dev *rtwdev, const s32 result[])
 		return;
 
 	tmp_rx_iqi |= FIELD_PREP(BIT_MASK_RXIQ_S1_X, result[IQK_S1_RX_X]);
-	tmp_rx_iqi |= FIELD_PREP(BIT_MASK_RXIQ_S1_Y1, result[IQK_S1_RX_X]);
+	tmp_rx_iqi |= FIELD_PREP(BIT_MASK_RXIQ_S1_Y1, result[IQK_S1_RX_Y]);
 	rtw_write32(rtwdev, REG_A_RXIQI, tmp_rx_iqi);
 	rtw_write32_mask(rtwdev, REG_RXIQK_MATRIX_LSB_11N, BIT_MASK_RXIQ_S1_Y2,
 			 BIT_SET_RXIQ_S1_Y2(result[IQK_S1_RX_Y]));
diff --git a/drivers/net/wireless/realtek/rtw88/rtw8723x.h b/drivers/net/wireless/realtek/rtw88/rtw8723x.h
index e93bfce994bf..a99af527c92c 100644
--- a/drivers/net/wireless/realtek/rtw88/rtw8723x.h
+++ b/drivers/net/wireless/realtek/rtw88/rtw8723x.h
@@ -47,7 +47,7 @@ struct rtw8723xe_efuse {
 	u8 device_id[2];
 	u8 sub_vendor_id[2];
 	u8 sub_device_id[2];
-};
+} __packed;
 
 struct rtw8723xu_efuse {
 	u8 res4[48];                    /* 0xd0 */
@@ -56,12 +56,12 @@ struct rtw8723xu_efuse {
 	u8 usb_option;                  /* 0x104 */
 	u8 res5[2];			/* 0x105 */
 	u8 mac_addr[ETH_ALEN];          /* 0x107 */
-};
+} __packed;
 
 struct rtw8723xs_efuse {
 	u8 res4[0x4a];			/* 0xd0 */
 	u8 mac_addr[ETH_ALEN];		/* 0x11a */
-};
+} __packed;
 
 struct rtw8723x_efuse {
 	__le16 rtl_id;
@@ -96,7 +96,7 @@ struct rtw8723x_efuse {
 		struct rtw8723xu_efuse u;
 		struct rtw8723xs_efuse s;
 	};
-};
+} __packed;
 
 #define RTW8723X_IQK_ADDA_REG_NUM	16
 #define RTW8723X_IQK_MAC8_REG_NUM	3
diff --git a/drivers/net/wireless/realtek/rtw88/rtw8821c.h b/drivers/net/wireless/realtek/rtw88/rtw8821c.h
index 91ed921407bb..10172f4d74bf 100644
--- a/drivers/net/wireless/realtek/rtw88/rtw8821c.h
+++ b/drivers/net/wireless/realtek/rtw88/rtw8821c.h
@@ -27,7 +27,7 @@ struct rtw8821cu_efuse {
 	u8 res11[0xcf];
 	u8 package_type;		/* 0x1fb */
 	u8 res12[0x4];
-};
+} __packed;
 
 struct rtw8821ce_efuse {
 	u8 mac_addr[ETH_ALEN];		/* 0xd0 */
@@ -47,7 +47,8 @@ struct rtw8821ce_efuse {
 	u8 ltr_en:1;
 	u8 res1:2;
 	u8 obff:2;
-	u8 res2:3;
+	u8 res2_1:1;
+	u8 res2_2:2;
 	u8 obff_cap:2;
 	u8 res3:4;
 	u8 res4[3];
@@ -63,7 +64,7 @@ struct rtw8821ce_efuse {
 	u8 res6:1;
 	u8 port_t_power_on_value:5;
 	u8 res7;
-};
+} __packed;
 
 struct rtw8821cs_efuse {
 	u8 res4[0x4a];			/* 0xd0 */
@@ -101,7 +102,7 @@ struct rtw8821c_efuse {
 		struct rtw8821cu_efuse u;
 		struct rtw8821cs_efuse s;
 	};
-};
+} __packed;
 
 static inline void
 _rtw_write32s_mask(struct rtw_dev *rtwdev, u32 addr, u32 mask, u32 data)
diff --git a/drivers/net/wireless/realtek/rtw88/rtw8822b.c b/drivers/net/wireless/realtek/rtw88/rtw8822b.c
index 6edb17aea90e..4a6c0a9266a0 100644
--- a/drivers/net/wireless/realtek/rtw88/rtw8822b.c
+++ b/drivers/net/wireless/realtek/rtw88/rtw8822b.c
@@ -976,11 +976,11 @@ static void rtw8822b_query_rx_desc(struct rtw_dev *rtwdev, u8 *rx_desc,
 }
 
 static void
-rtw8822b_set_tx_power_index_by_rate(struct rtw_dev *rtwdev, u8 path, u8 rs)
+rtw8822b_set_tx_power_index_by_rate(struct rtw_dev *rtwdev, u8 path,
+				    u8 rs, u32 *phy_pwr_idx)
 {
 	struct rtw_hal *hal = &rtwdev->hal;
 	static const u32 offset_txagc[2] = {0x1d00, 0x1d80};
-	static u32 phy_pwr_idx;
 	u8 rate, rate_idx, pwr_index, shift;
 	int j;
 
@@ -988,12 +988,12 @@ rtw8822b_set_tx_power_index_by_rate(struct rtw_dev *rtwdev, u8 path, u8 rs)
 		rate = rtw_rate_section[rs][j];
 		pwr_index = hal->tx_pwr_tbl[path][rate];
 		shift = rate & 0x3;
-		phy_pwr_idx |= ((u32)pwr_index << (shift * 8));
+		*phy_pwr_idx |= ((u32)pwr_index << (shift * 8));
 		if (shift == 0x3) {
 			rate_idx = rate & 0xfc;
 			rtw_write32(rtwdev, offset_txagc[path] + rate_idx,
-				    phy_pwr_idx);
-			phy_pwr_idx = 0;
+				    *phy_pwr_idx);
+			*phy_pwr_idx = 0;
 		}
 	}
 }
@@ -1001,11 +1001,13 @@ rtw8822b_set_tx_power_index_by_rate(struct rtw_dev *rtwdev, u8 path, u8 rs)
 static void rtw8822b_set_tx_power_index(struct rtw_dev *rtwdev)
 {
 	struct rtw_hal *hal = &rtwdev->hal;
+	u32 phy_pwr_idx = 0;
 	int rs, path;
 
 	for (path = 0; path < hal->rf_path_num; path++) {
 		for (rs = 0; rs < RTW_RATE_SECTION_MAX; rs++)
-			rtw8822b_set_tx_power_index_by_rate(rtwdev, path, rs);
+			rtw8822b_set_tx_power_index_by_rate(rtwdev, path, rs,
+							    &phy_pwr_idx);
 	}
 }
 
diff --git a/drivers/net/wireless/realtek/rtw88/rtw8822b.h b/drivers/net/wireless/realtek/rtw88/rtw8822b.h
index cf85e63966a1..e815bc97c218 100644
--- a/drivers/net/wireless/realtek/rtw88/rtw8822b.h
+++ b/drivers/net/wireless/realtek/rtw88/rtw8822b.h
@@ -27,7 +27,7 @@ struct rtw8822bu_efuse {
 	u8 res11[0xcf];
 	u8 package_type;		/* 0x1fb */
 	u8 res12[0x4];
-};
+} __packed;
 
 struct rtw8822be_efuse {
 	u8 mac_addr[ETH_ALEN];		/* 0xd0 */
@@ -47,7 +47,8 @@ struct rtw8822be_efuse {
 	u8 ltr_en:1;
 	u8 res1:2;
 	u8 obff:2;
-	u8 res2:3;
+	u8 res2_1:1;
+	u8 res2_2:2;
 	u8 obff_cap:2;
 	u8 res3:4;
 	u8 res4[3];
@@ -63,7 +64,7 @@ struct rtw8822be_efuse {
 	u8 res6:1;
 	u8 port_t_power_on_value:5;
 	u8 res7;
-};
+} __packed;
 
 struct rtw8822bs_efuse {
 	u8 res4[0x4a];			/* 0xd0 */
@@ -103,7 +104,7 @@ struct rtw8822b_efuse {
 		struct rtw8822bu_efuse u;
 		struct rtw8822bs_efuse s;
 	};
-};
+} __packed;
 
 static inline void
 _rtw_write32s_mask(struct rtw_dev *rtwdev, u32 addr, u32 mask, u32 data)
diff --git a/drivers/net/wireless/realtek/rtw88/rtw8822c.c b/drivers/net/wireless/realtek/rtw88/rtw8822c.c
index 1dbe1cdbc3fd..3157cd834233 100644
--- a/drivers/net/wireless/realtek/rtw88/rtw8822c.c
+++ b/drivers/net/wireless/realtek/rtw88/rtw8822c.c
@@ -3993,7 +3993,8 @@ static void rtw8822c_dpk_cal_coef1(struct rtw_dev *rtwdev)
 	rtw_write32(rtwdev, REG_NCTL0, 0x00001148);
 	rtw_write32(rtwdev, REG_NCTL0, 0x00001149);
 
-	check_hw_ready(rtwdev, 0x2d9c, MASKBYTE0, 0x55);
+	if (!check_hw_ready(rtwdev, 0x2d9c, MASKBYTE0, 0x55))
+		rtw_warn(rtwdev, "DPK stuck, performance may be suboptimal");
 
 	rtw_write8(rtwdev, 0x1b10, 0x0);
 	rtw_write32_mask(rtwdev, REG_NCTL0, BIT_SUBPAGE, 0x0000000c);
diff --git a/drivers/net/wireless/realtek/rtw88/rtw8822c.h b/drivers/net/wireless/realtek/rtw88/rtw8822c.h
index e2b383d633cd..fc62b67a15f2 100644
--- a/drivers/net/wireless/realtek/rtw88/rtw8822c.h
+++ b/drivers/net/wireless/realtek/rtw88/rtw8822c.h
@@ -14,7 +14,7 @@ struct rtw8822cu_efuse {
 	u8 res1[3];
 	u8 mac_addr[ETH_ALEN];		/* 0x157 */
 	u8 res2[0x3d];
-};
+} __packed;
 
 struct rtw8822cs_efuse {
 	u8 res0[0x4a];			/* 0x120 */
@@ -39,7 +39,8 @@ struct rtw8822ce_efuse {
 	u8 ltr_en:1;
 	u8 res1:2;
 	u8 obff:2;
-	u8 res2:3;
+	u8 res2_1:1;
+	u8 res2_2:2;
 	u8 obff_cap:2;
 	u8 res3:4;
 	u8 class_code[3];
@@ -55,7 +56,7 @@ struct rtw8822ce_efuse {
 	u8 res6:1;
 	u8 port_t_power_on_value:5;
 	u8 res7;
-};
+} __packed;
 
 struct rtw8822c_efuse {
 	__le16 rtl_id;
@@ -102,7 +103,7 @@ struct rtw8822c_efuse {
 		struct rtw8822cu_efuse u;
 		struct rtw8822cs_efuse s;
 	};
-};
+} __packed;
 
 enum rtw8822c_dpk_agc_phase {
 	RTW_DPK_GAIN_CHECK,
diff --git a/drivers/net/wireless/realtek/rtw88/sdio.c b/drivers/net/wireless/realtek/rtw88/sdio.c
index b67e551fcee3..787fa09fd063 100644
--- a/drivers/net/wireless/realtek/rtw88/sdio.c
+++ b/drivers/net/wireless/realtek/rtw88/sdio.c
@@ -10,6 +10,7 @@
 #include <linux/mmc/host.h>
 #include <linux/mmc/sdio_func.h>
 #include "main.h"
+#include "mac.h"
 #include "debug.h"
 #include "fw.h"
 #include "ps.h"
@@ -718,10 +719,7 @@ static u8 rtw_sdio_get_tx_qsel(struct rtw_dev *rtwdev, struct sk_buff *skb,
 	case RTW_TX_QUEUE_H2C:
 		return TX_DESC_QSEL_H2C;
 	case RTW_TX_QUEUE_MGMT:
-		if (rtw_chip_wcpu_11n(rtwdev))
-			return TX_DESC_QSEL_HIGH;
-		else
-			return TX_DESC_QSEL_MGMT;
+		return TX_DESC_QSEL_MGMT;
 	case RTW_TX_QUEUE_HI0:
 		return TX_DESC_QSEL_HIGH;
 	default:
@@ -1158,6 +1156,7 @@ static struct rtw_hci_ops rtw_sdio_ops = {
 	.link_ps = rtw_sdio_link_ps,
 	.interface_cfg = rtw_sdio_interface_cfg,
 	.dynamic_rx_agg = NULL,
+	.write_firmware_page = rtw_write_firmware_page,
 
 	.read8 = rtw_sdio_read8,
 	.read16 = rtw_sdio_read16,
@@ -1193,6 +1192,8 @@ static void rtw_sdio_indicate_tx_status(struct rtw_dev *rtwdev,
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
 	struct ieee80211_hw *hw = rtwdev->hw;
 
+	skb_pull(skb, rtwdev->chip->tx_pkt_desc_sz);
+
 	/* enqueue to wait for tx report */
 	if (info->flags & IEEE80211_TX_CTL_REQ_TX_STATUS) {
 		rtw_tx_report_enqueue(rtwdev, skb, tx_data->sn);
@@ -1226,10 +1227,7 @@ static void rtw_sdio_process_tx_queue(struct rtw_dev *rtwdev,
 		return;
 	}
 
-	if (queue <= RTW_TX_QUEUE_VO)
-		rtw_sdio_indicate_tx_status(rtwdev, skb);
-	else
-		dev_kfree_skb_any(skb);
+	rtw_sdio_indicate_tx_status(rtwdev, skb);
 }
 
 static void rtw_sdio_tx_handler(struct work_struct *work)
diff --git a/drivers/net/wireless/realtek/rtw88/usb.c b/drivers/net/wireless/realtek/rtw88/usb.c
index 07695294767a..a446be45f26e 100644
--- a/drivers/net/wireless/realtek/rtw88/usb.c
+++ b/drivers/net/wireless/realtek/rtw88/usb.c
@@ -138,7 +138,7 @@ static void rtw_usb_write(struct rtw_dev *rtwdev, u32 addr, u32 val, int len)
 
 	ret = usb_control_msg(udev, usb_sndctrlpipe(udev, 0),
 			      RTW_USB_CMD_REQ, RTW_USB_CMD_WRITE,
-			      addr, 0, data, len, 30000);
+			      addr, 0, data, len, 500);
 	if (ret < 0 && ret != -ENODEV && count++ < 4)
 		rtw_err(rtwdev, "write register 0x%x failed with %d\n",
 			addr, ret);
@@ -164,6 +164,60 @@ static void rtw_usb_write32(struct rtw_dev *rtwdev, u32 addr, u32 val)
 	rtw_usb_write(rtwdev, addr, val, 4);
 }
 
+static void rtw_usb_write_firmware_page(struct rtw_dev *rtwdev, u32 page,
+					const u8 *data, u32 size)
+{
+	struct rtw_usb *rtwusb = rtw_get_usb_priv(rtwdev);
+	struct usb_device *udev = rtwusb->udev;
+	u32 addr = FW_START_ADDR_LEGACY;
+	u8 *data_dup, *buf;
+	u32 n, block_size;
+	int ret;
+
+	switch (rtwdev->chip->id) {
+	case RTW_CHIP_TYPE_8723D:
+		block_size = 254;
+		break;
+	default:
+		block_size = 196;
+		break;
+	}
+
+	data_dup = kmemdup(data, size, GFP_KERNEL);
+	if (!data_dup)
+		return;
+
+	buf = data_dup;
+
+	rtw_write32_mask(rtwdev, REG_MCUFW_CTRL, BIT_ROM_PGE, page);
+
+	while (size > 0) {
+		if (size >= block_size)
+			n = block_size;
+		else if (size >= 8)
+			n = 8;
+		else
+			n = 1;
+
+		ret = usb_control_msg(udev, usb_sndctrlpipe(udev, 0),
+				      RTW_USB_CMD_REQ, RTW_USB_CMD_WRITE,
+				      addr, 0, buf, n, 500);
+		if (ret != n) {
+			if (ret != -ENODEV)
+				rtw_err(rtwdev,
+					"write 0x%x len %d failed: %d\n",
+					addr, n, ret);
+			break;
+		}
+
+		addr += n;
+		buf += n;
+		size -= n;
+	}
+
+	kfree(data_dup);
+}
+
 static int dma_mapping_to_ep(enum rtw_dma_mapping dma_mapping)
 {
 	switch (dma_mapping) {
@@ -815,6 +869,7 @@ static struct rtw_hci_ops rtw_usb_ops = {
 	.link_ps = rtw_usb_link_ps,
 	.interface_cfg = rtw_usb_interface_cfg,
 	.dynamic_rx_agg = rtw_usb_dynamic_rx_agg,
+	.write_firmware_page = rtw_usb_write_firmware_page,
 
 	.write8  = rtw_usb_write8,
 	.write16 = rtw_usb_write16,
diff --git a/drivers/net/wireless/realtek/rtw88/util.c b/drivers/net/wireless/realtek/rtw88/util.c
index e222d3c01a77..66819f694405 100644
--- a/drivers/net/wireless/realtek/rtw88/util.c
+++ b/drivers/net/wireless/realtek/rtw88/util.c
@@ -101,7 +101,8 @@ void rtw_desc_to_mcsrate(u16 rate, u8 *mcs, u8 *nss)
 		*nss = 4;
 		*mcs = rate - DESC_RATEVHT4SS_MCS0;
 	} else if (rate >= DESC_RATEMCS0 &&
-		   rate <= DESC_RATEMCS15) {
+		   rate <= DESC_RATEMCS31) {
+		*nss = 0;
 		*mcs = rate - DESC_RATEMCS0;
 	}
 }
diff --git a/drivers/net/wireless/realtek/rtw89/cam.c b/drivers/net/wireless/realtek/rtw89/cam.c
index 8d140b94cb44..0c8ea5e629e6 100644
--- a/drivers/net/wireless/realtek/rtw89/cam.c
+++ b/drivers/net/wireless/realtek/rtw89/cam.c
@@ -6,6 +6,7 @@
 #include "debug.h"
 #include "fw.h"
 #include "mac.h"
+#include "ps.h"
 
 static struct sk_buff *
 rtw89_cam_get_sec_key_cmd(struct rtw89_dev *rtwdev,
@@ -447,9 +448,11 @@ int rtw89_cam_sec_key_add(struct rtw89_dev *rtwdev,
 
 	switch (key->cipher) {
 	case WLAN_CIPHER_SUITE_WEP40:
+		rtw89_leave_ips_by_hwflags(rtwdev);
 		hw_key_type = RTW89_SEC_KEY_TYPE_WEP40;
 		break;
 	case WLAN_CIPHER_SUITE_WEP104:
+		rtw89_leave_ips_by_hwflags(rtwdev);
 		hw_key_type = RTW89_SEC_KEY_TYPE_WEP104;
 		break;
 	case WLAN_CIPHER_SUITE_CCMP:
diff --git a/drivers/net/wireless/realtek/rtw89/chan.c b/drivers/net/wireless/realtek/rtw89/chan.c
index ba6332da8019..559aa60e3df0 100644
--- a/drivers/net/wireless/realtek/rtw89/chan.c
+++ b/drivers/net/wireless/realtek/rtw89/chan.c
@@ -10,6 +10,10 @@
 #include "ps.h"
 #include "util.h"
 
+static void rtw89_swap_chanctx(struct rtw89_dev *rtwdev,
+			       enum rtw89_chanctx_idx idx1,
+			       enum rtw89_chanctx_idx idx2);
+
 static enum rtw89_subband rtw89_get_subband_type(enum rtw89_band band,
 						 u8 center_chan)
 {
@@ -226,11 +230,15 @@ static void rtw89_config_default_chandef(struct rtw89_dev *rtwdev)
 void rtw89_entity_init(struct rtw89_dev *rtwdev)
 {
 	struct rtw89_hal *hal = &rtwdev->hal;
+	struct rtw89_entity_mgnt *mgnt = &hal->entity_mgnt;
 
 	hal->entity_pause = false;
 	bitmap_zero(hal->entity_map, NUM_OF_RTW89_CHANCTX);
 	bitmap_zero(hal->changes, NUM_OF_RTW89_CHANCTX_CHANGES);
 	atomic_set(&hal->roc_chanctx_idx, RTW89_CHANCTX_IDLE);
+
+	INIT_LIST_HEAD(&mgnt->active_list);
+
 	rtw89_config_default_chandef(rtwdev);
 }
 
@@ -272,6 +280,143 @@ static void rtw89_entity_calculate_weight(struct rtw89_dev *rtwdev,
 	}
 }
 
+static void rtw89_normalize_link_chanctx(struct rtw89_dev *rtwdev,
+					 struct rtw89_vif_link *rtwvif_link)
+{
+	struct rtw89_vif *rtwvif = rtwvif_link->rtwvif;
+	struct rtw89_vif_link *cur;
+
+	if (unlikely(!rtwvif_link->chanctx_assigned))
+		return;
+
+	cur = rtw89_vif_get_link_inst(rtwvif, 0);
+	if (!cur || !cur->chanctx_assigned)
+		return;
+
+	if (cur == rtwvif_link)
+		return;
+
+	rtw89_swap_chanctx(rtwdev, rtwvif_link->chanctx_idx, cur->chanctx_idx);
+}
+
+const struct rtw89_chan *__rtw89_mgnt_chan_get(struct rtw89_dev *rtwdev,
+					       const char *caller_message,
+					       u8 link_index)
+{
+	struct rtw89_hal *hal = &rtwdev->hal;
+	struct rtw89_entity_mgnt *mgnt = &hal->entity_mgnt;
+	enum rtw89_chanctx_idx chanctx_idx;
+	enum rtw89_chanctx_idx roc_idx;
+	enum rtw89_entity_mode mode;
+	u8 role_index;
+
+	lockdep_assert_held(&rtwdev->mutex);
+
+	if (unlikely(link_index >= __RTW89_MLD_MAX_LINK_NUM)) {
+		WARN(1, "link index %u is invalid (max link inst num: %d)\n",
+		     link_index, __RTW89_MLD_MAX_LINK_NUM);
+		goto dflt;
+	}
+
+	mode = rtw89_get_entity_mode(rtwdev);
+	switch (mode) {
+	case RTW89_ENTITY_MODE_SCC_OR_SMLD:
+	case RTW89_ENTITY_MODE_MCC:
+		role_index = 0;
+		break;
+	case RTW89_ENTITY_MODE_MCC_PREPARE:
+		role_index = 1;
+		break;
+	default:
+		WARN(1, "Invalid ent mode: %d\n", mode);
+		goto dflt;
+	}
+
+	chanctx_idx = mgnt->chanctx_tbl[role_index][link_index];
+	if (chanctx_idx == RTW89_CHANCTX_IDLE)
+		goto dflt;
+
+	roc_idx = atomic_read(&hal->roc_chanctx_idx);
+	if (roc_idx != RTW89_CHANCTX_IDLE) {
+		/* ROC is ongoing (given ROC runs on RTW89_ROC_BY_LINK_INDEX).
+		 * If @link_index is the same as RTW89_ROC_BY_LINK_INDEX, get
+		 * the ongoing ROC chanctx.
+		 */
+		if (link_index == RTW89_ROC_BY_LINK_INDEX)
+			chanctx_idx = roc_idx;
+	}
+
+	return rtw89_chan_get(rtwdev, chanctx_idx);
+
+dflt:
+	rtw89_debug(rtwdev, RTW89_DBG_CHAN,
+		    "%s (%s): prefetch NULL on link index %u\n",
+		    __func__, caller_message ?: "", link_index);
+
+	return rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
+}
+EXPORT_SYMBOL(__rtw89_mgnt_chan_get);
+
+static void rtw89_entity_recalc_mgnt_roles(struct rtw89_dev *rtwdev)
+{
+	struct rtw89_hal *hal = &rtwdev->hal;
+	struct rtw89_entity_mgnt *mgnt = &hal->entity_mgnt;
+	struct rtw89_vif_link *link;
+	struct rtw89_vif *role;
+	u8 pos = 0;
+	int i, j;
+
+	lockdep_assert_held(&rtwdev->mutex);
+
+	for (i = 0; i < RTW89_MAX_INTERFACE_NUM; i++)
+		mgnt->active_roles[i] = NULL;
+
+	for (i = 0; i < RTW89_MAX_INTERFACE_NUM; i++) {
+		for (j = 0; j < __RTW89_MLD_MAX_LINK_NUM; j++)
+			mgnt->chanctx_tbl[i][j] = RTW89_CHANCTX_IDLE;
+	}
+
+	/* To be consistent with legacy behavior, expect the first active role
+	 * which uses RTW89_CHANCTX_0 to put at position 0, and make its first
+	 * link instance take RTW89_CHANCTX_0. (normalizing)
+	 */
+	list_for_each_entry(role, &mgnt->active_list, mgnt_entry) {
+		for (i = 0; i < role->links_inst_valid_num; i++) {
+			link = rtw89_vif_get_link_inst(role, i);
+			if (!link || !link->chanctx_assigned)
+				continue;
+
+			if (link->chanctx_idx == RTW89_CHANCTX_0) {
+				rtw89_normalize_link_chanctx(rtwdev, link);
+
+				list_del(&role->mgnt_entry);
+				list_add(&role->mgnt_entry, &mgnt->active_list);
+				goto fill;
+			}
+		}
+	}
+
+fill:
+	list_for_each_entry(role, &mgnt->active_list, mgnt_entry) {
+		if (unlikely(pos >= RTW89_MAX_INTERFACE_NUM)) {
+			rtw89_warn(rtwdev,
+				   "%s: active roles are over max iface num\n",
+				   __func__);
+			break;
+		}
+
+		for (i = 0; i < role->links_inst_valid_num; i++) {
+			link = rtw89_vif_get_link_inst(role, i);
+			if (!link || !link->chanctx_assigned)
+				continue;
+
+			mgnt->chanctx_tbl[pos][i] = link->chanctx_idx;
+		}
+
+		mgnt->active_roles[pos++] = role;
+	}
+}
+
 enum rtw89_entity_mode rtw89_entity_recalc(struct rtw89_dev *rtwdev)
 {
 	DECLARE_BITMAP(recalc_map, NUM_OF_RTW89_CHANCTX) = {};
@@ -298,9 +443,14 @@ enum rtw89_entity_mode rtw89_entity_recalc(struct rtw89_dev *rtwdev)
 		set_bit(RTW89_CHANCTX_0, recalc_map);
 		fallthrough;
 	case 1:
-		mode = RTW89_ENTITY_MODE_SCC;
+		mode = RTW89_ENTITY_MODE_SCC_OR_SMLD;
 		break;
 	case 2 ... NUM_OF_RTW89_CHANCTX:
+		if (w.active_roles == 1) {
+			mode = RTW89_ENTITY_MODE_SCC_OR_SMLD;
+			break;
+		}
+
 		if (w.active_roles != NUM_OF_RTW89_MCC_ROLES) {
 			rtw89_debug(rtwdev, RTW89_DBG_CHAN,
 				    "unhandled ent: %d chanctxs %d roles\n",
@@ -327,6 +477,8 @@ enum rtw89_entity_mode rtw89_entity_recalc(struct rtw89_dev *rtwdev)
 		rtw89_assign_entity_chan(rtwdev, idx, &chan);
 	}
 
+	rtw89_entity_recalc_mgnt_roles(rtwdev);
+
 	if (hal->entity_pause)
 		return rtw89_get_entity_mode(rtwdev);
 
@@ -650,7 +802,7 @@ fill:
 
 	mcc_role->limit.max_toa = max_toa_us / 1024;
 	mcc_role->limit.max_tob = max_tob_us / 1024;
-	mcc_role->limit.max_dur = max_dur_us / 1024;
+	mcc_role->limit.max_dur = mcc_role->limit.max_toa + mcc_role->limit.max_tob;
 	mcc_role->limit.enable = true;
 
 	rtw89_debug(rtwdev, RTW89_DBG_CHAN,
@@ -716,6 +868,7 @@ struct rtw89_mcc_fill_role_selector {
 };
 
 static_assert((u8)NUM_OF_RTW89_CHANCTX >= NUM_OF_RTW89_MCC_ROLES);
+static_assert(RTW89_MAX_INTERFACE_NUM >= NUM_OF_RTW89_MCC_ROLES);
 
 static int rtw89_mcc_fill_role_iterator(struct rtw89_dev *rtwdev,
 					struct rtw89_mcc_role *mcc_role,
@@ -745,14 +898,18 @@ static int rtw89_mcc_fill_role_iterator(struct rtw89_dev *rtwdev,
 
 static int rtw89_mcc_fill_all_roles(struct rtw89_dev *rtwdev)
 {
+	struct rtw89_hal *hal = &rtwdev->hal;
+	struct rtw89_entity_mgnt *mgnt = &hal->entity_mgnt;
 	struct rtw89_mcc_fill_role_selector sel = {};
 	struct rtw89_vif_link *rtwvif_link;
 	struct rtw89_vif *rtwvif;
 	int ret;
+	int i;
 
-	rtw89_for_each_rtwvif(rtwdev, rtwvif) {
-		if (!rtw89_vif_is_active_role(rtwvif))
-			continue;
+	for (i = 0; i < NUM_OF_RTW89_MCC_ROLES; i++) {
+		rtwvif = mgnt->active_roles[i];
+		if (!rtwvif)
+			break;
 
 		rtwvif_link = rtw89_vif_get_link_inst(rtwvif, 0);
 		if (unlikely(!rtwvif_link)) {
@@ -760,14 +917,7 @@ static int rtw89_mcc_fill_all_roles(struct rtw89_dev *rtwdev)
 			continue;
 		}
 
-		if (sel.bind_vif[rtwvif_link->chanctx_idx]) {
-			rtw89_warn(rtwdev,
-				   "MCC skip extra vif <macid %d> on chanctx[%d]\n",
-				   rtwvif_link->mac_id, rtwvif_link->chanctx_idx);
-			continue;
-		}
-
-		sel.bind_vif[rtwvif_link->chanctx_idx] = rtwvif_link;
+		sel.bind_vif[i] = rtwvif_link;
 	}
 
 	ret = rtw89_iterate_mcc_roles(rtwdev, rtw89_mcc_fill_role_iterator, &sel);
@@ -2381,7 +2531,25 @@ void rtw89_chanctx_pause(struct rtw89_dev *rtwdev,
 	hal->entity_pause = true;
 }
 
-void rtw89_chanctx_proceed(struct rtw89_dev *rtwdev)
+static void rtw89_chanctx_proceed_cb(struct rtw89_dev *rtwdev,
+				     const struct rtw89_chanctx_cb_parm *parm)
+{
+	int ret;
+
+	if (!parm || !parm->cb)
+		return;
+
+	ret = parm->cb(rtwdev, parm->data);
+	if (ret)
+		rtw89_warn(rtwdev, "%s (%s): cb failed: %d\n", __func__,
+			   parm->caller ?: "unknown", ret);
+}
+
+/* pass @cb_parm if there is a @cb_parm->cb which needs to invoke right after
+ * call rtw89_set_channel() and right before proceed entity according to mode.
+ */
+void rtw89_chanctx_proceed(struct rtw89_dev *rtwdev,
+			   const struct rtw89_chanctx_cb_parm *cb_parm)
 {
 	struct rtw89_hal *hal = &rtwdev->hal;
 	enum rtw89_entity_mode mode;
@@ -2389,14 +2557,18 @@ void rtw89_chanctx_proceed(struct rtw89_dev *rtwdev)
 
 	lockdep_assert_held(&rtwdev->mutex);
 
-	if (!hal->entity_pause)
+	if (unlikely(!hal->entity_pause)) {
+		rtw89_chanctx_proceed_cb(rtwdev, cb_parm);
 		return;
+	}
 
 	rtw89_debug(rtwdev, RTW89_DBG_CHAN, "chanctx proceed\n");
 
 	hal->entity_pause = false;
 	rtw89_set_channel(rtwdev);
 
+	rtw89_chanctx_proceed_cb(rtwdev, cb_parm);
+
 	mode = rtw89_get_entity_mode(rtwdev);
 	switch (mode) {
 	case RTW89_ENTITY_MODE_MCC:
@@ -2501,12 +2673,21 @@ int rtw89_chanctx_ops_assign_vif(struct rtw89_dev *rtwdev,
 				 struct ieee80211_chanctx_conf *ctx)
 {
 	struct rtw89_chanctx_cfg *cfg = (struct rtw89_chanctx_cfg *)ctx->drv_priv;
+	struct rtw89_vif *rtwvif = rtwvif_link->rtwvif;
+	struct rtw89_hal *hal = &rtwdev->hal;
+	struct rtw89_entity_mgnt *mgnt = &hal->entity_mgnt;
 	struct rtw89_entity_weight w = {};
 
 	rtwvif_link->chanctx_idx = cfg->idx;
 	rtwvif_link->chanctx_assigned = true;
 	cfg->ref_count++;
 
+	if (rtwdev->scanning)
+		rtw89_hw_scan_abort(rtwdev, rtwdev->scan_info.scanning_vif);
+
+	if (list_empty(&rtwvif->mgnt_entry))
+		list_add_tail(&rtwvif->mgnt_entry, &mgnt->active_list);
+
 	if (cfg->idx == RTW89_CHANCTX_0)
 		goto out;
 
@@ -2526,6 +2707,7 @@ void rtw89_chanctx_ops_unassign_vif(struct rtw89_dev *rtwdev,
 				    struct ieee80211_chanctx_conf *ctx)
 {
 	struct rtw89_chanctx_cfg *cfg = (struct rtw89_chanctx_cfg *)ctx->drv_priv;
+	struct rtw89_vif *rtwvif = rtwvif_link->rtwvif;
 	struct rtw89_hal *hal = &rtwdev->hal;
 	enum rtw89_chanctx_idx roll;
 	enum rtw89_entity_mode cur;
@@ -2536,6 +2718,12 @@ void rtw89_chanctx_ops_unassign_vif(struct rtw89_dev *rtwdev,
 	rtwvif_link->chanctx_assigned = false;
 	cfg->ref_count--;
 
+	if (rtwdev->scanning)
+		rtw89_hw_scan_abort(rtwdev, rtwdev->scan_info.scanning_vif);
+
+	if (!rtw89_vif_is_active_role(rtwvif))
+		list_del_init(&rtwvif->mgnt_entry);
+
 	if (cfg->ref_count != 0)
 		goto out;
 
diff --git a/drivers/net/wireless/realtek/rtw89/chan.h b/drivers/net/wireless/realtek/rtw89/chan.h
index 4ed777ea5064..092a6f676894 100644
--- a/drivers/net/wireless/realtek/rtw89/chan.h
+++ b/drivers/net/wireless/realtek/rtw89/chan.h
@@ -38,23 +38,32 @@ enum rtw89_chanctx_pause_reasons {
 	RTW89_CHANCTX_PAUSE_REASON_ROC,
 };
 
+struct rtw89_chanctx_cb_parm {
+	int (*cb)(struct rtw89_dev *rtwdev, void *data);
+	void *data;
+	const char *caller;
+};
+
 struct rtw89_entity_weight {
 	unsigned int active_chanctxs;
 	unsigned int active_roles;
 };
 
-static inline bool rtw89_get_entity_state(struct rtw89_dev *rtwdev)
+static inline bool rtw89_get_entity_state(struct rtw89_dev *rtwdev,
+					  enum rtw89_phy_idx phy_idx)
 {
 	struct rtw89_hal *hal = &rtwdev->hal;
 
-	return READ_ONCE(hal->entity_active);
+	return READ_ONCE(hal->entity_active[phy_idx]);
 }
 
-static inline void rtw89_set_entity_state(struct rtw89_dev *rtwdev, bool active)
+static inline void rtw89_set_entity_state(struct rtw89_dev *rtwdev,
+					  enum rtw89_phy_idx phy_idx,
+					  bool active)
 {
 	struct rtw89_hal *hal = &rtwdev->hal;
 
-	WRITE_ONCE(hal->entity_active, active);
+	WRITE_ONCE(hal->entity_active[phy_idx], active);
 }
 
 static inline
@@ -97,7 +106,16 @@ void rtw89_queue_chanctx_change(struct rtw89_dev *rtwdev,
 void rtw89_chanctx_track(struct rtw89_dev *rtwdev);
 void rtw89_chanctx_pause(struct rtw89_dev *rtwdev,
 			 enum rtw89_chanctx_pause_reasons rsn);
-void rtw89_chanctx_proceed(struct rtw89_dev *rtwdev);
+void rtw89_chanctx_proceed(struct rtw89_dev *rtwdev,
+			   const struct rtw89_chanctx_cb_parm *cb_parm);
+
+const struct rtw89_chan *__rtw89_mgnt_chan_get(struct rtw89_dev *rtwdev,
+					       const char *caller_message,
+					       u8 link_index);
+
+#define rtw89_mgnt_chan_get(rtwdev, link_index) \
+	__rtw89_mgnt_chan_get(rtwdev, __func__, link_index)
+
 int rtw89_chanctx_ops_add(struct rtw89_dev *rtwdev,
 			  struct ieee80211_chanctx_conf *ctx);
 void rtw89_chanctx_ops_remove(struct rtw89_dev *rtwdev,
diff --git a/drivers/net/wireless/realtek/rtw89/coex.c b/drivers/net/wireless/realtek/rtw89/coex.c
index 8d54d71fcf53..6cdbf02f405a 100644
--- a/drivers/net/wireless/realtek/rtw89/coex.c
+++ b/drivers/net/wireless/realtek/rtw89/coex.c
@@ -89,10 +89,10 @@ static const struct rtw89_btc_fbtc_slot s_def[] = {
 	[CXST_B4]	= __DEF_FBTC_SLOT(50,  0xe5555555, SLOT_MIX),
 	[CXST_LK]	= __DEF_FBTC_SLOT(20,  0xea5a5a5a, SLOT_ISO),
 	[CXST_BLK]	= __DEF_FBTC_SLOT(500, 0x55555555, SLOT_MIX),
-	[CXST_E2G]	= __DEF_FBTC_SLOT(0,   0xea5a5a5a, SLOT_MIX),
-	[CXST_E5G]	= __DEF_FBTC_SLOT(0,   0xffffffff, SLOT_ISO),
+	[CXST_E2G]	= __DEF_FBTC_SLOT(5,   0xea5a5a5a, SLOT_MIX),
+	[CXST_E5G]	= __DEF_FBTC_SLOT(5,   0xffffffff, SLOT_ISO),
 	[CXST_EBT]	= __DEF_FBTC_SLOT(5,   0xe5555555, SLOT_MIX),
-	[CXST_ENULL]	= __DEF_FBTC_SLOT(0,   0xaaaaaaaa, SLOT_ISO),
+	[CXST_ENULL]	= __DEF_FBTC_SLOT(5,   0xaaaaaaaa, SLOT_ISO),
 	[CXST_WLK]	= __DEF_FBTC_SLOT(250, 0xea5a5a5a, SLOT_MIX),
 	[CXST_W1FDD]	= __DEF_FBTC_SLOT(50,  0xffffffff, SLOT_ISO),
 	[CXST_B1FDD]	= __DEF_FBTC_SLOT(50,  0xffffdfff, SLOT_ISO),
@@ -5356,7 +5356,8 @@ static void _action_wl_scan(struct rtw89_dev *rtwdev)
 	struct rtw89_btc_wl_info *wl = &btc->cx.wl;
 	struct rtw89_btc_wl_dbcc_info *wl_dinfo = &wl->dbcc_info;
 
-	if (RTW89_CHK_FW_FEATURE(SCAN_OFFLOAD, &rtwdev->fw)) {
+	if (btc->cx.state_map != BTC_WLINKING &&
+	    RTW89_CHK_FW_FEATURE(SCAN_OFFLOAD, &rtwdev->fw)) {
 		_action_wl_25g_mcc(rtwdev);
 		rtw89_debug(rtwdev, RTW89_DBG_BTC, "[BTC], Scan offload!\n");
 	} else if (rtwdev->dbcc_en) {
@@ -7178,6 +7179,8 @@ void rtw89_btc_ntfy_scan_finish(struct rtw89_dev *rtwdev, u8 phy_idx)
 		_fw_set_drv_info(rtwdev, CXDRVINFO_DBCC);
 	}
 
+	btc->dm.tdma_instant_excute = 1;
+
 	_run_coex(rtwdev, BTC_RSN_NTFY_SCAN_FINISH);
 }
 
@@ -7630,7 +7633,8 @@ void rtw89_btc_ntfy_role_info(struct rtw89_dev *rtwdev,
 	else
 		wl->status.map.connecting = 0;
 
-	if (state == BTC_ROLE_MSTS_STA_DIS_CONN)
+	if (state == BTC_ROLE_MSTS_STA_DIS_CONN ||
+	    state == BTC_ROLE_MSTS_STA_CONN_END)
 		wl->status.map._4way = false;
 
 	_run_coex(rtwdev, BTC_RSN_NTFY_ROLE_INFO);
diff --git a/drivers/net/wireless/realtek/rtw89/core.c b/drivers/net/wireless/realtek/rtw89/core.c
index 5b8e65f6de6a..c336c66ac8e3 100644
--- a/drivers/net/wireless/realtek/rtw89/core.c
+++ b/drivers/net/wireless/realtek/rtw89/core.c
@@ -192,13 +192,13 @@ static const struct ieee80211_iface_combination rtw89_iface_combs[] = {
 	{
 		.limits = rtw89_iface_limits,
 		.n_limits = ARRAY_SIZE(rtw89_iface_limits),
-		.max_interfaces = 2,
+		.max_interfaces = RTW89_MAX_INTERFACE_NUM,
 		.num_different_channels = 1,
 	},
 	{
 		.limits = rtw89_iface_limits_mcc,
 		.n_limits = ARRAY_SIZE(rtw89_iface_limits_mcc),
-		.max_interfaces = 2,
+		.max_interfaces = RTW89_MAX_INTERFACE_NUM,
 		.num_different_channels = 2,
 	},
 };
@@ -341,83 +341,47 @@ void rtw89_get_channel_params(const struct cfg80211_chan_def *chandef,
 	rtw89_chan_create(chan, center_chan, channel->hw_value, band, bandwidth);
 }
 
-void rtw89_core_set_chip_txpwr(struct rtw89_dev *rtwdev)
+static void __rtw89_core_set_chip_txpwr(struct rtw89_dev *rtwdev,
+					const struct rtw89_chan *chan,
+					enum rtw89_phy_idx phy_idx)
 {
-	struct rtw89_hal *hal = &rtwdev->hal;
 	const struct rtw89_chip_info *chip = rtwdev->chip;
-	const struct rtw89_chan *chan;
-	enum rtw89_chanctx_idx chanctx_idx;
-	enum rtw89_chanctx_idx roc_idx;
-	enum rtw89_phy_idx phy_idx;
-	enum rtw89_entity_mode mode;
 	bool entity_active;
 
-	entity_active = rtw89_get_entity_state(rtwdev);
+	entity_active = rtw89_get_entity_state(rtwdev, phy_idx);
 	if (!entity_active)
 		return;
 
-	mode = rtw89_get_entity_mode(rtwdev);
-	switch (mode) {
-	case RTW89_ENTITY_MODE_SCC:
-	case RTW89_ENTITY_MODE_MCC:
-		chanctx_idx = RTW89_CHANCTX_0;
-		break;
-	case RTW89_ENTITY_MODE_MCC_PREPARE:
-		chanctx_idx = RTW89_CHANCTX_1;
-		break;
-	default:
-		WARN(1, "Invalid ent mode: %d\n", mode);
-		return;
-	}
+	chip->ops->set_txpwr(rtwdev, chan, phy_idx);
+}
 
-	roc_idx = atomic_read(&hal->roc_chanctx_idx);
-	if (roc_idx != RTW89_CHANCTX_IDLE)
-		chanctx_idx = roc_idx;
+void rtw89_core_set_chip_txpwr(struct rtw89_dev *rtwdev)
+{
+	const struct rtw89_chan *chan;
 
-	phy_idx = RTW89_PHY_0;
-	chan = rtw89_chan_get(rtwdev, chanctx_idx);
-	chip->ops->set_txpwr(rtwdev, chan, phy_idx);
+	chan = rtw89_mgnt_chan_get(rtwdev, 0);
+	__rtw89_core_set_chip_txpwr(rtwdev, chan, RTW89_PHY_0);
+
+	if (!rtwdev->support_mlo)
+		return;
+
+	chan = rtw89_mgnt_chan_get(rtwdev, 1);
+	__rtw89_core_set_chip_txpwr(rtwdev, chan, RTW89_PHY_1);
 }
 
-int rtw89_set_channel(struct rtw89_dev *rtwdev)
+static void __rtw89_set_channel(struct rtw89_dev *rtwdev,
+				const struct rtw89_chan *chan,
+				enum rtw89_mac_idx mac_idx,
+				enum rtw89_phy_idx phy_idx)
 {
-	struct rtw89_hal *hal = &rtwdev->hal;
 	const struct rtw89_chip_info *chip = rtwdev->chip;
 	const struct rtw89_chan_rcd *chan_rcd;
-	const struct rtw89_chan *chan;
-	enum rtw89_chanctx_idx chanctx_idx;
-	enum rtw89_chanctx_idx roc_idx;
-	enum rtw89_mac_idx mac_idx;
-	enum rtw89_phy_idx phy_idx;
 	struct rtw89_channel_help_params bak;
-	enum rtw89_entity_mode mode;
 	bool entity_active;
 
-	entity_active = rtw89_get_entity_state(rtwdev);
+	entity_active = rtw89_get_entity_state(rtwdev, phy_idx);
 
-	mode = rtw89_entity_recalc(rtwdev);
-	switch (mode) {
-	case RTW89_ENTITY_MODE_SCC:
-	case RTW89_ENTITY_MODE_MCC:
-		chanctx_idx = RTW89_CHANCTX_0;
-		break;
-	case RTW89_ENTITY_MODE_MCC_PREPARE:
-		chanctx_idx = RTW89_CHANCTX_1;
-		break;
-	default:
-		WARN(1, "Invalid ent mode: %d\n", mode);
-		return -EINVAL;
-	}
-
-	roc_idx = atomic_read(&hal->roc_chanctx_idx);
-	if (roc_idx != RTW89_CHANCTX_IDLE)
-		chanctx_idx = roc_idx;
-
-	mac_idx = RTW89_MAC_0;
-	phy_idx = RTW89_PHY_0;
-
-	chan = rtw89_chan_get(rtwdev, chanctx_idx);
-	chan_rcd = rtw89_chan_rcd_get(rtwdev, chanctx_idx);
+	chan_rcd = rtw89_chan_rcd_get_by_chan(chan);
 
 	rtw89_chip_set_channel_prepare(rtwdev, &bak, chan, mac_idx, phy_idx);
 
@@ -432,7 +396,29 @@ int rtw89_set_channel(struct rtw89_dev *rtwdev)
 		rtw89_chip_rfk_band_changed(rtwdev, phy_idx, chan);
 	}
 
-	rtw89_set_entity_state(rtwdev, true);
+	rtw89_set_entity_state(rtwdev, phy_idx, true);
+}
+
+int rtw89_set_channel(struct rtw89_dev *rtwdev)
+{
+	const struct rtw89_chan *chan;
+	enum rtw89_entity_mode mode;
+
+	mode = rtw89_entity_recalc(rtwdev);
+	if (mode < 0 || mode >= NUM_OF_RTW89_ENTITY_MODE) {
+		WARN(1, "Invalid ent mode: %d\n", mode);
+		return -EINVAL;
+	}
+
+	chan = rtw89_mgnt_chan_get(rtwdev, 0);
+	__rtw89_set_channel(rtwdev, chan, RTW89_MAC_0, RTW89_PHY_0);
+
+	if (!rtwdev->support_mlo)
+		return 0;
+
+	chan = rtw89_mgnt_chan_get(rtwdev, 1);
+	__rtw89_set_channel(rtwdev, chan, RTW89_MAC_1, RTW89_PHY_1);
+
 	return 0;
 }
 
@@ -2028,6 +2014,11 @@ static void rtw89_core_cancel_6ghz_probe_tx(struct rtw89_dev *rtwdev,
 	if (rx_status->band != NL80211_BAND_6GHZ)
 		return;
 
+	if (unlikely(!(rtwdev->chip->support_bands & BIT(NL80211_BAND_6GHZ)))) {
+		rtw89_debug(rtwdev, RTW89_DBG_UNEXP, "invalid rx on unsupported 6 GHz\n");
+		return;
+	}
+
 	ssid_ie = cfg80211_find_ie(WLAN_EID_SSID, ies, skb->len);
 
 	list_for_each_entry(info, &pkt_list[NL80211_BAND_6GHZ], list) {
@@ -3157,9 +3148,10 @@ void rtw89_roc_start(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif)
 	rtw89_leave_ips_by_hwflags(rtwdev);
 	rtw89_leave_lps(rtwdev);
 
-	rtwvif_link = rtw89_vif_get_link_inst(rtwvif, 0);
+	rtwvif_link = rtw89_vif_get_link_inst(rtwvif, RTW89_ROC_BY_LINK_INDEX);
 	if (unlikely(!rtwvif_link)) {
-		rtw89_err(rtwdev, "roc start: find no link on HW-0\n");
+		rtw89_err(rtwdev, "roc start: find no link on HW-%u\n",
+			  RTW89_ROC_BY_LINK_INDEX);
 		return;
 	}
 
@@ -3211,9 +3203,10 @@ void rtw89_roc_end(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif)
 	rtw89_leave_ips_by_hwflags(rtwdev);
 	rtw89_leave_lps(rtwdev);
 
-	rtwvif_link = rtw89_vif_get_link_inst(rtwvif, 0);
+	rtwvif_link = rtw89_vif_get_link_inst(rtwvif, RTW89_ROC_BY_LINK_INDEX);
 	if (unlikely(!rtwvif_link)) {
-		rtw89_err(rtwdev, "roc end: find no link on HW-0\n");
+		rtw89_err(rtwdev, "roc end: find no link on HW-%u\n",
+			  RTW89_ROC_BY_LINK_INDEX);
 		return;
 	}
 
@@ -3224,7 +3217,7 @@ void rtw89_roc_end(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif)
 
 	roc->state = RTW89_ROC_IDLE;
 	rtw89_config_roc_chandef(rtwdev, rtwvif_link->chanctx_idx, NULL);
-	rtw89_chanctx_proceed(rtwdev);
+	rtw89_chanctx_proceed(rtwdev, NULL);
 	ret = rtw89_core_send_nullfunc(rtwdev, rtwvif_link, true, false);
 	if (ret)
 		rtw89_debug(rtwdev, RTW89_DBG_TXRX,
@@ -4874,8 +4867,6 @@ static int rtw89_chip_efuse_info_setup(struct rtw89_dev *rtwdev)
 
 	rtw89_hci_mac_pre_deinit(rtwdev);
 
-	rtw89_mac_pwr_off(rtwdev);
-
 	return 0;
 }
 
@@ -4956,36 +4947,45 @@ int rtw89_chip_info_setup(struct rtw89_dev *rtwdev)
 
 	rtw89_read_chip_ver(rtwdev);
 
+	ret = rtw89_mac_pwr_on(rtwdev);
+	if (ret) {
+		rtw89_err(rtwdev, "failed to power on\n");
+		return ret;
+	}
+
 	ret = rtw89_wait_firmware_completion(rtwdev);
 	if (ret) {
 		rtw89_err(rtwdev, "failed to wait firmware completion\n");
-		return ret;
+		goto out;
 	}
 
 	ret = rtw89_fw_recognize(rtwdev);
 	if (ret) {
 		rtw89_err(rtwdev, "failed to recognize firmware\n");
-		return ret;
+		goto out;
 	}
 
 	ret = rtw89_chip_efuse_info_setup(rtwdev);
 	if (ret)
-		return ret;
+		goto out;
 
 	ret = rtw89_fw_recognize_elements(rtwdev);
 	if (ret) {
 		rtw89_err(rtwdev, "failed to recognize firmware elements\n");
-		return ret;
+		goto out;
 	}
 
 	ret = rtw89_chip_board_info_setup(rtwdev);
 	if (ret)
-		return ret;
+		goto out;
 
 	rtw89_core_setup_rfe_parms(rtwdev);
 	rtwdev->ps_mode = rtw89_update_ps_mode(rtwdev);
 
-	return 0;
+out:
+	rtw89_mac_pwr_off(rtwdev);
+
+	return ret;
 }
 EXPORT_SYMBOL(rtw89_chip_info_setup);
 
diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index de33320b1354..4f64ea392e6c 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -17,6 +17,7 @@ struct rtw89_dev;
 struct rtw89_pci_info;
 struct rtw89_mac_gen_def;
 struct rtw89_phy_gen_def;
+struct rtw89_fw_blacklist;
 struct rtw89_efuse_block_cfg;
 struct rtw89_h2c_rf_tssi;
 struct rtw89_fw_txpwr_track_cfg;
@@ -3424,6 +3425,8 @@ enum rtw89_roc_state {
 	RTW89_ROC_MGMT,
 };
 
+#define RTW89_ROC_BY_LINK_INDEX 0
+
 struct rtw89_roc {
 	struct ieee80211_channel chan;
 	struct delayed_work roc_work;
@@ -4230,6 +4233,7 @@ struct rtw89_chip_info {
 	bool try_ce_fw;
 	u8 bbmcu_nr;
 	u32 needed_fw_elms;
+	const struct rtw89_fw_blacklist *fw_blacklist;
 	u32 fifo_size;
 	bool small_fifo_size;
 	u32 dle_scc_rsvd_size;
@@ -4619,7 +4623,7 @@ enum rtw89_chanctx_changes {
 };
 
 enum rtw89_entity_mode {
-	RTW89_ENTITY_MODE_SCC,
+	RTW89_ENTITY_MODE_SCC_OR_SMLD,
 	RTW89_ENTITY_MODE_MCC_PREPARE,
 	RTW89_ENTITY_MODE_MCC,
 
@@ -4628,6 +4632,16 @@ enum rtw89_entity_mode {
 	RTW89_ENTITY_MODE_UNHANDLED = -ESRCH,
 };
 
+#define RTW89_MAX_INTERFACE_NUM 2
+
+/* only valid when running with chanctx_ops */
+struct rtw89_entity_mgnt {
+	struct list_head active_list;
+	struct rtw89_vif *active_roles[RTW89_MAX_INTERFACE_NUM];
+	enum rtw89_chanctx_idx chanctx_tbl[RTW89_MAX_INTERFACE_NUM]
+					  [__RTW89_MLD_MAX_LINK_NUM];
+};
+
 struct rtw89_chanctx {
 	struct cfg80211_chan_def chandef;
 	struct rtw89_chan chan;
@@ -4668,9 +4682,10 @@ struct rtw89_hal {
 	struct rtw89_chanctx chanctx[NUM_OF_RTW89_CHANCTX];
 	struct cfg80211_chan_def roc_chandef;
 
-	bool entity_active;
+	bool entity_active[RTW89_PHY_MAX];
 	bool entity_pause;
 	enum rtw89_entity_mode entity_mode;
+	struct rtw89_entity_mgnt entity_mgnt;
 
 	struct rtw89_edcca_bak edcca_bak;
 	u32 disabled_dm_bitmap; /* bitmap of enum rtw89_dm_type */
@@ -5607,6 +5622,7 @@ struct rtw89_dev {
 struct rtw89_vif {
 	struct rtw89_dev *rtwdev;
 	struct list_head list;
+	struct list_head mgnt_entry;
 
 	u8 mac_addr[ETH_ALEN];
 	__be32 ip_addr;
@@ -6362,6 +6378,15 @@ const struct rtw89_chan_rcd *rtw89_chan_rcd_get(struct rtw89_dev *rtwdev,
 }
 
 static inline
+const struct rtw89_chan_rcd *rtw89_chan_rcd_get_by_chan(const struct rtw89_chan *chan)
+{
+	const struct rtw89_chanctx *chanctx =
+		container_of_const(chan, struct rtw89_chanctx, chan);
+
+	return &chanctx->rcd;
+}
+
+static inline
 const struct rtw89_chan *rtw89_scan_chan_get(struct rtw89_dev *rtwdev)
 {
 	struct rtw89_vif_link *rtwvif_link = rtwdev->scan_info.scanning_vif;
diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c
index e6bceef691e9..10a3a66a9981 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.c
+++ b/drivers/net/wireless/realtek/rtw89/fw.c
@@ -38,6 +38,16 @@ struct rtw89_arp_rsp {
 
 static const u8 mss_signature[] = {0x4D, 0x53, 0x53, 0x4B, 0x50, 0x4F, 0x4F, 0x4C};
 
+const struct rtw89_fw_blacklist rtw89_fw_blacklist_default = {
+	.ver = 0x00,
+	.list = {0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0,
+		 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0,
+		 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0,
+		 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0,
+	},
+};
+EXPORT_SYMBOL(rtw89_fw_blacklist_default);
+
 union rtw89_fw_element_arg {
 	size_t offset;
 	enum rtw89_rf_path rf_path;
@@ -285,7 +295,7 @@ static int __parse_formatted_mssc(struct rtw89_dev *rtwdev,
 	if (!sec->secure_boot)
 		goto out;
 
-	sb_sel_ver = le32_to_cpu(section_content->sb_sel_ver.v);
+	sb_sel_ver = get_unaligned_le32(&section_content->sb_sel_ver.v);
 	if (sb_sel_ver && sb_sel_ver != sec->sb_sel_mgn)
 		goto ignore;
 
@@ -315,6 +325,46 @@ ignore:
 	return 0;
 }
 
+static int __check_secure_blacklist(struct rtw89_dev *rtwdev,
+				    struct rtw89_fw_bin_info *info,
+				    struct rtw89_fw_hdr_section_info *section_info,
+				    const void *content)
+{
+	const struct rtw89_fw_blacklist *chip_blacklist = rtwdev->chip->fw_blacklist;
+	const union rtw89_fw_section_mssc_content *section_content = content;
+	struct rtw89_fw_secure *sec = &rtwdev->fw.sec;
+	u8 byte_idx;
+	u8 bit_mask;
+
+	if (!sec->secure_boot)
+		return 0;
+
+	if (!info->secure_section_exist || section_info->ignore)
+		return 0;
+
+	if (!chip_blacklist) {
+		rtw89_err(rtwdev, "chip no blacklist for secure firmware\n");
+		return -ENOENT;
+	}
+
+	byte_idx = section_content->blacklist.bit_in_chip_list >> 3;
+	bit_mask = BIT(section_content->blacklist.bit_in_chip_list & 0x7);
+
+	if (section_content->blacklist.ver > chip_blacklist->ver) {
+		rtw89_err(rtwdev, "chip blacklist out of date (%u, %u)\n",
+			  section_content->blacklist.ver, chip_blacklist->ver);
+		return -EINVAL;
+	}
+
+	if (chip_blacklist->list[byte_idx] & bit_mask) {
+		rtw89_err(rtwdev, "firmware %u in chip blacklist\n",
+			  section_content->blacklist.ver);
+		return -EPERM;
+	}
+
+	return 0;
+}
+
 static int __parse_security_section(struct rtw89_dev *rtwdev,
 				    struct rtw89_fw_bin_info *info,
 				    struct rtw89_fw_hdr_section_info *section_info,
@@ -340,7 +390,7 @@ static int __parse_security_section(struct rtw89_dev *rtwdev,
 		info->secure_section_exist = true;
 	}
 
-	return 0;
+	return __check_secure_blacklist(rtwdev, info, section_info, content);
 }
 
 static int rtw89_fw_hdr_parser_v1(struct rtw89_dev *rtwdev, const u8 *fw, u32 len,
@@ -451,6 +501,30 @@ static int rtw89_fw_hdr_parser(struct rtw89_dev *rtwdev,
 	}
 }
 
+static int rtw89_mfw_validate_hdr(struct rtw89_dev *rtwdev,
+				  const struct firmware *firmware,
+				  const struct rtw89_mfw_hdr *mfw_hdr)
+{
+	const void *mfw = firmware->data;
+	u32 mfw_len = firmware->size;
+	u8 fw_nr = mfw_hdr->fw_nr;
+	const void *ptr;
+
+	if (fw_nr == 0) {
+		rtw89_err(rtwdev, "mfw header has no fw entry\n");
+		return -ENOENT;
+	}
+
+	ptr = &mfw_hdr->info[fw_nr];
+
+	if (ptr > mfw + mfw_len) {
+		rtw89_err(rtwdev, "mfw header out of address\n");
+		return -EFAULT;
+	}
+
+	return 0;
+}
+
 static
 int rtw89_mfw_recognize(struct rtw89_dev *rtwdev, enum rtw89_fw_type type,
 			struct rtw89_fw_suit *fw_suit, bool nowarn)
@@ -461,6 +535,7 @@ int rtw89_mfw_recognize(struct rtw89_dev *rtwdev, enum rtw89_fw_type type,
 	u32 mfw_len = firmware->size;
 	const struct rtw89_mfw_hdr *mfw_hdr = (const struct rtw89_mfw_hdr *)mfw;
 	const struct rtw89_mfw_info *mfw_info = NULL, *tmp;
+	int ret;
 	int i;
 
 	if (mfw_hdr->sig != RTW89_MFW_SIG) {
@@ -473,6 +548,10 @@ int rtw89_mfw_recognize(struct rtw89_dev *rtwdev, enum rtw89_fw_type type,
 		return 0;
 	}
 
+	ret = rtw89_mfw_validate_hdr(rtwdev, firmware, mfw_hdr);
+	if (ret)
+		return ret;
+
 	for (i = 0; i < mfw_hdr->fw_nr; i++) {
 		tmp = &mfw_hdr->info[i];
 		if (tmp->type != type)
@@ -502,6 +581,12 @@ int rtw89_mfw_recognize(struct rtw89_dev *rtwdev, enum rtw89_fw_type type,
 found:
 	fw_suit->data = mfw + le32_to_cpu(mfw_info->shift);
 	fw_suit->size = le32_to_cpu(mfw_info->size);
+
+	if (fw_suit->data + fw_suit->size > mfw + mfw_len) {
+		rtw89_err(rtwdev, "fw_suit %d out of address\n", type);
+		return -EFAULT;
+	}
+
 	return 0;
 }
 
@@ -513,12 +598,17 @@ static u32 rtw89_mfw_get_size(struct rtw89_dev *rtwdev)
 		(const struct rtw89_mfw_hdr *)firmware->data;
 	const struct rtw89_mfw_info *mfw_info;
 	u32 size;
+	int ret;
 
 	if (mfw_hdr->sig != RTW89_MFW_SIG) {
 		rtw89_warn(rtwdev, "not mfw format\n");
 		return 0;
 	}
 
+	ret = rtw89_mfw_validate_hdr(rtwdev, firmware, mfw_hdr);
+	if (ret)
+		return ret;
+
 	mfw_info = &mfw_hdr->info[mfw_hdr->fw_nr - 1];
 	size = le32_to_cpu(mfw_info->shift) + le32_to_cpu(mfw_info->size);
 
@@ -1234,7 +1324,6 @@ static int __rtw89_fw_download_hdr(struct rtw89_dev *rtwdev,
 	ret = rtw89_h2c_tx(rtwdev, skb, false);
 	if (ret) {
 		rtw89_err(rtwdev, "failed to send h2c\n");
-		ret = -1;
 		goto fail;
 	}
 
@@ -1311,7 +1400,6 @@ static int __rtw89_fw_download_main(struct rtw89_dev *rtwdev,
 		ret = rtw89_h2c_tx(rtwdev, skb, true);
 		if (ret) {
 			rtw89_err(rtwdev, "failed to send h2c\n");
-			ret = -1;
 			goto fail;
 		}
 
@@ -3080,9 +3168,10 @@ int rtw89_fw_h2c_assoc_cmac_tbl_g7(struct rtw89_dev *rtwdev,
 			      CCTLINFO_G7_W5_NOMINAL_PKT_PADDING3 |
 			      CCTLINFO_G7_W5_NOMINAL_PKT_PADDING4);
 
-	h2c->w6 = le32_encode_bits(vif->type == NL80211_IFTYPE_STATION ? 1 : 0,
+	h2c->w6 = le32_encode_bits(vif->cfg.aid, CCTLINFO_G7_W6_AID12_PAID) |
+		  le32_encode_bits(vif->type == NL80211_IFTYPE_STATION ? 1 : 0,
 				   CCTLINFO_G7_W6_ULDL);
-	h2c->m6 = cpu_to_le32(CCTLINFO_G7_W6_ULDL);
+	h2c->m6 = cpu_to_le32(CCTLINFO_G7_W6_AID12_PAID | CCTLINFO_G7_W6_ULDL);
 
 	if (rtwsta_link) {
 		h2c->w8 = le32_encode_bits(link_sta->he_cap.has_he,
@@ -4927,7 +5016,7 @@ int rtw89_fw_h2c_scan_list_offload_be(struct rtw89_dev *rtwdev, int ch_num,
 	return 0;
 }
 
-#define RTW89_SCAN_DELAY_TSF_UNIT 104800
+#define RTW89_SCAN_DELAY_TSF_UNIT 1000000
 int rtw89_fw_h2c_scan_offload_ax(struct rtw89_dev *rtwdev,
 				 struct rtw89_scan_option *option,
 				 struct rtw89_vif_link *rtwvif_link,
@@ -5845,13 +5934,18 @@ static int rtw89_fw_read_c2h_reg(struct rtw89_dev *rtwdev,
 	const struct rtw89_chip_info *chip = rtwdev->chip;
 	struct rtw89_fw_info *fw_info = &rtwdev->fw;
 	const u32 *c2h_reg = chip->c2h_regs;
-	u32 ret;
+	u32 ret, timeout;
 	u8 i, val;
 
 	info->id = RTW89_FWCMD_C2HREG_FUNC_NULL;
 
+	if (rtwdev->hci.type == RTW89_HCI_TYPE_USB)
+		timeout = RTW89_C2H_TIMEOUT_USB;
+	else
+		timeout = RTW89_C2H_TIMEOUT;
+
 	ret = read_poll_timeout_atomic(rtw89_read8, val, val, 1,
-				       RTW89_C2H_TIMEOUT, false, rtwdev,
+				       timeout, false, rtwdev,
 				       chip->c2h_ctrl_reg);
 	if (ret) {
 		rtw89_warn(rtwdev, "c2h reg timeout\n");
@@ -6637,21 +6731,24 @@ void rtw89_hw_scan_start(struct rtw89_dev *rtwdev,
 	rtw89_chanctx_pause(rtwdev, RTW89_CHANCTX_PAUSE_REASON_HW_SCAN);
 }
 
-void rtw89_hw_scan_complete(struct rtw89_dev *rtwdev,
-			    struct rtw89_vif_link *rtwvif_link,
-			    bool aborted)
+struct rtw89_hw_scan_complete_cb_data {
+	struct rtw89_vif_link *rtwvif_link;
+	bool aborted;
+};
+
+static int rtw89_hw_scan_complete_cb(struct rtw89_dev *rtwdev, void *data)
 {
 	const struct rtw89_mac_gen_def *mac = rtwdev->chip->mac_def;
 	struct rtw89_hw_scan_info *scan_info = &rtwdev->scan_info;
+	struct rtw89_hw_scan_complete_cb_data *cb_data = data;
+	struct rtw89_vif_link *rtwvif_link = cb_data->rtwvif_link;
 	struct cfg80211_scan_info info = {
-		.aborted = aborted,
+		.aborted = cb_data->aborted,
 	};
 	struct rtw89_vif *rtwvif;
 
 	if (!rtwvif_link)
-		return;
-
-	rtw89_chanctx_proceed(rtwdev);
+		return -EINVAL;
 
 	rtwvif = rtwvif_link->rtwvif;
 
@@ -6672,6 +6769,29 @@ void rtw89_hw_scan_complete(struct rtw89_dev *rtwdev,
 	scan_info->last_chan_idx = 0;
 	scan_info->scanning_vif = NULL;
 	scan_info->abort = false;
+
+	return 0;
+}
+
+void rtw89_hw_scan_complete(struct rtw89_dev *rtwdev,
+			    struct rtw89_vif_link *rtwvif_link,
+			    bool aborted)
+{
+	struct rtw89_hw_scan_complete_cb_data cb_data = {
+		.rtwvif_link = rtwvif_link,
+		.aborted = aborted,
+	};
+	const struct rtw89_chanctx_cb_parm cb_parm = {
+		.cb = rtw89_hw_scan_complete_cb,
+		.data = &cb_data,
+		.caller = __func__,
+	};
+
+	/* The things here needs to be done after setting channel (for coex)
+	 * and before proceeding entity mode (for MCC). So, pass a callback
+	 * of them for the right sequence rather than doing them directly.
+	 */
+	rtw89_chanctx_proceed(rtwdev, &cb_parm);
 }
 
 void rtw89_hw_scan_abort(struct rtw89_dev *rtwdev,
diff --git a/drivers/net/wireless/realtek/rtw89/fw.h b/drivers/net/wireless/realtek/rtw89/fw.h
index ccbbc43f33fe..2981d6eeb678 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.h
+++ b/drivers/net/wireless/realtek/rtw89/fw.h
@@ -97,6 +97,8 @@ struct rtw89_h2creg_sch_tx_en {
 #define RTW89_C2HREG_HDR_LEN 2
 #define RTW89_H2CREG_HDR_LEN 2
 #define RTW89_C2H_TIMEOUT 1000000
+#define RTW89_C2H_TIMEOUT_USB 4000
+
 struct rtw89_mac_c2h_info {
 	u8 id;
 	u8 content_len;
@@ -640,6 +642,11 @@ struct rtw89_fw_mss_pool_hdr {
 
 union rtw89_fw_section_mssc_content {
 	struct {
+		u8 pad[0x20];
+		u8 bit_in_chip_list;
+		u8 ver;
+	} __packed blacklist;
+	struct {
 		u8 pad[58];
 		__le32 v;
 	} __packed sb_sel_ver;
@@ -649,6 +656,13 @@ union rtw89_fw_section_mssc_content {
 	} __packed key_sign_len;
 } __packed;
 
+struct rtw89_fw_blacklist {
+	u8 ver;
+	u8 list[32];
+};
+
+extern const struct rtw89_fw_blacklist rtw89_fw_blacklist_default;
+
 static inline void SET_CTRL_INFO_MACID(void *table, u32 val)
 {
 	le32p_replace_bits((__le32 *)(table) + 0, val, GENMASK(6, 0));
diff --git a/drivers/net/wireless/realtek/rtw89/mac.c b/drivers/net/wireless/realtek/rtw89/mac.c
index 4e15d539e3d1..8b7ca63af7ed 100644
--- a/drivers/net/wireless/realtek/rtw89/mac.c
+++ b/drivers/net/wireless/realtek/rtw89/mac.c
@@ -1441,6 +1441,23 @@ void rtw89_mac_notify_wake(struct rtw89_dev *rtwdev)
 	rtw89_mac_send_rpwm(rtwdev, state, true);
 }
 
+static void rtw89_mac_power_switch_boot_mode(struct rtw89_dev *rtwdev)
+{
+	u32 boot_mode;
+
+	if (rtwdev->hci.type != RTW89_HCI_TYPE_USB)
+		return;
+
+	boot_mode = rtw89_read32_mask(rtwdev, R_AX_GPIO_MUXCFG, B_AX_BOOT_MODE);
+	if (!boot_mode)
+		return;
+
+	rtw89_write32_clr(rtwdev, R_AX_SYS_PW_CTRL, B_AX_APFN_ONMAC);
+	rtw89_write32_clr(rtwdev, R_AX_SYS_STATUS1, B_AX_AUTO_WLPON);
+	rtw89_write32_clr(rtwdev, R_AX_GPIO_MUXCFG, B_AX_BOOT_MODE);
+	rtw89_write32_clr(rtwdev, R_AX_RSV_CTRL, B_AX_R_DIS_PRST);
+}
+
 static int rtw89_mac_power_switch(struct rtw89_dev *rtwdev, bool on)
 {
 #define PWR_ACT 1
@@ -1450,6 +1467,8 @@ static int rtw89_mac_power_switch(struct rtw89_dev *rtwdev, bool on)
 	int ret;
 	u8 val;
 
+	rtw89_mac_power_switch_boot_mode(rtwdev);
+
 	if (on) {
 		cfg_seq = chip->pwr_on_seq;
 		cfg_func = chip->ops->pwr_on_func;
@@ -1483,13 +1502,29 @@ static int rtw89_mac_power_switch(struct rtw89_dev *rtwdev, bool on)
 		clear_bit(RTW89_FLAG_CMAC1_FUNC, rtwdev->flags);
 		clear_bit(RTW89_FLAG_FW_RDY, rtwdev->flags);
 		rtw89_write8(rtwdev, R_AX_SCOREBOARD + 3, MAC_AX_NOTIFY_PWR_MAJOR);
-		rtw89_set_entity_state(rtwdev, false);
+		rtw89_set_entity_state(rtwdev, RTW89_PHY_0, false);
+		rtw89_set_entity_state(rtwdev, RTW89_PHY_1, false);
 	}
 
 	return 0;
 #undef PWR_ACT
 }
 
+int rtw89_mac_pwr_on(struct rtw89_dev *rtwdev)
+{
+	int ret;
+
+	ret = rtw89_mac_power_switch(rtwdev, true);
+	if (ret) {
+		rtw89_mac_power_switch(rtwdev, false);
+		ret = rtw89_mac_power_switch(rtwdev, true);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
 void rtw89_mac_pwr_off(struct rtw89_dev *rtwdev)
 {
 	rtw89_mac_power_switch(rtwdev, false);
@@ -3917,14 +3952,6 @@ int rtw89_mac_partial_init(struct rtw89_dev *rtwdev, bool include_bb)
 {
 	int ret;
 
-	ret = rtw89_mac_power_switch(rtwdev, true);
-	if (ret) {
-		rtw89_mac_power_switch(rtwdev, false);
-		ret = rtw89_mac_power_switch(rtwdev, true);
-		if (ret)
-			return ret;
-	}
-
 	rtw89_mac_ctrl_hci_dma_trx(rtwdev, true);
 
 	if (include_bb) {
@@ -3957,6 +3984,10 @@ int rtw89_mac_init(struct rtw89_dev *rtwdev)
 	bool include_bb = !!chip->bbmcu_nr;
 	int ret;
 
+	ret = rtw89_mac_pwr_on(rtwdev);
+	if (ret)
+		return ret;
+
 	ret = rtw89_mac_partial_init(rtwdev, include_bb);
 	if (ret)
 		goto fail;
@@ -3988,7 +4019,7 @@ int rtw89_mac_init(struct rtw89_dev *rtwdev)
 
 	return ret;
 fail:
-	rtw89_mac_power_switch(rtwdev, false);
+	rtw89_mac_pwr_off(rtwdev);
 
 	return ret;
 }
@@ -4744,6 +4775,32 @@ void rtw89_mac_set_he_obss_narrow_bw_ru(struct rtw89_dev *rtwdev,
 		rtw89_write32_set(rtwdev, reg, mac->narrow_bw_ru_dis.mask);
 }
 
+void rtw89_mac_set_he_tb(struct rtw89_dev *rtwdev,
+			 struct rtw89_vif_link *rtwvif_link)
+{
+	struct ieee80211_bss_conf *bss_conf;
+	bool set;
+	u32 reg;
+
+	if (rtwdev->chip->chip_gen != RTW89_CHIP_BE)
+		return;
+
+	rcu_read_lock();
+
+	bss_conf = rtw89_vif_rcu_dereference_link(rtwvif_link, true);
+	set = bss_conf->he_support && !bss_conf->eht_support;
+
+	rcu_read_unlock();
+
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_BE_CLIENT_OM_CTRL,
+				   rtwvif_link->mac_idx);
+
+	if (set)
+		rtw89_write32_set(rtwdev, reg, B_BE_TRIG_DIS_EHTTB);
+	else
+		rtw89_write32_clr(rtwdev, reg, B_BE_TRIG_DIS_EHTTB);
+}
+
 void rtw89_mac_stop_ap(struct rtw89_dev *rtwdev, struct rtw89_vif_link *rtwvif_link)
 {
 	rtw89_mac_port_cfg_func_sw(rtwdev, rtwvif_link);
@@ -5475,11 +5532,11 @@ void rtw89_mac_c2h_handle(struct rtw89_dev *rtwdev, struct sk_buff *skb,
 	case RTW89_MAC_C2H_CLASS_FWDBG:
 		return;
 	default:
-		rtw89_info(rtwdev, "c2h class %d not support\n", class);
+		rtw89_info(rtwdev, "MAC c2h class %d not support\n", class);
 		return;
 	}
 	if (!handler) {
-		rtw89_info(rtwdev, "c2h class %d func %d not support\n", class,
+		rtw89_info(rtwdev, "MAC c2h class %d func %d not support\n", class,
 			   func);
 		return;
 	}
diff --git a/drivers/net/wireless/realtek/rtw89/mac.h b/drivers/net/wireless/realtek/rtw89/mac.h
index 0c269961a573..7974849f41e2 100644
--- a/drivers/net/wireless/realtek/rtw89/mac.h
+++ b/drivers/net/wireless/realtek/rtw89/mac.h
@@ -1120,6 +1120,7 @@ rtw89_write32_port_set(struct rtw89_dev *rtwdev, struct rtw89_vif_link *rtwvif_l
 	rtw89_write32_set(rtwdev, reg, bit);
 }
 
+int rtw89_mac_pwr_on(struct rtw89_dev *rtwdev);
 void rtw89_mac_pwr_off(struct rtw89_dev *rtwdev);
 int rtw89_mac_partial_init(struct rtw89_dev *rtwdev, bool include_bb);
 int rtw89_mac_init(struct rtw89_dev *rtwdev);
@@ -1160,6 +1161,8 @@ void rtw89_mac_port_cfg_rx_sync(struct rtw89_dev *rtwdev,
 				struct rtw89_vif_link *rtwvif_link, bool en);
 void rtw89_mac_set_he_obss_narrow_bw_ru(struct rtw89_dev *rtwdev,
 					struct rtw89_vif_link *rtwvif_link);
+void rtw89_mac_set_he_tb(struct rtw89_dev *rtwdev,
+			 struct rtw89_vif_link *rtwvif_link);
 void rtw89_mac_stop_ap(struct rtw89_dev *rtwdev, struct rtw89_vif_link *rtwvif_link);
 void rtw89_mac_enable_beacon_for_ap_vifs(struct rtw89_dev *rtwdev, bool en);
 int rtw89_mac_remove_vif(struct rtw89_dev *rtwdev, struct rtw89_vif_link *vif);
diff --git a/drivers/net/wireless/realtek/rtw89/mac80211.c b/drivers/net/wireless/realtek/rtw89/mac80211.c
index 13fb3cac2701..3a1a2b243adf 100644
--- a/drivers/net/wireless/realtek/rtw89/mac80211.c
+++ b/drivers/net/wireless/realtek/rtw89/mac80211.c
@@ -189,8 +189,10 @@ static int rtw89_ops_add_interface(struct ieee80211_hw *hw,
 
 	rtw89_core_txq_init(rtwdev, vif->txq);
 
-	if (!rtw89_rtwvif_in_list(rtwdev, rtwvif))
+	if (!rtw89_rtwvif_in_list(rtwdev, rtwvif)) {
 		list_add_tail(&rtwvif->list, &rtwdev->rtwvifs_list);
+		INIT_LIST_HEAD(&rtwvif->mgnt_entry);
+	}
 
 	ether_addr_copy(rtwvif->mac_addr, vif->addr);
 
@@ -667,6 +669,7 @@ static void __rtw89_ops_bss_link_assoc(struct rtw89_dev *rtwdev,
 	rtw89_chip_cfg_txpwr_ul_tb_offset(rtwdev, rtwvif_link);
 	rtw89_mac_port_update(rtwdev, rtwvif_link);
 	rtw89_mac_set_he_obss_narrow_bw_ru(rtwdev, rtwvif_link);
+	rtw89_mac_set_he_tb(rtwdev, rtwvif_link);
 }
 
 static void __rtw89_ops_bss_assoc(struct rtw89_dev *rtwdev,
@@ -1271,11 +1274,11 @@ static void rtw89_ops_cancel_hw_scan(struct ieee80211_hw *hw,
 	if (!RTW89_CHK_FW_FEATURE(SCAN_OFFLOAD, &rtwdev->fw))
 		return;
 
-	if (!rtwdev->scanning)
-		return;
-
 	mutex_lock(&rtwdev->mutex);
 
+	if (!rtwdev->scanning)
+		goto out;
+
 	rtwvif_link = rtw89_vif_get_link_inst(rtwvif, 0);
 	if (unlikely(!rtwvif_link)) {
 		rtw89_err(rtwdev, "cancel hw scan: find no link on HW-0\n");
diff --git a/drivers/net/wireless/realtek/rtw89/pci.c b/drivers/net/wireless/realtek/rtw89/pci.c
index 5aef7fa37878..e203d3b2a827 100644
--- a/drivers/net/wireless/realtek/rtw89/pci.c
+++ b/drivers/net/wireless/realtek/rtw89/pci.c
@@ -228,7 +228,7 @@ int rtw89_pci_sync_skb_for_device_and_validate_rx_info(struct rtw89_dev *rtwdev,
 						       struct sk_buff *skb)
 {
 	struct rtw89_pci_rx_info *rx_info = RTW89_PCI_RX_SKB_CB(skb);
-	int rx_tag_retry = 100;
+	int rx_tag_retry = 1000;
 	int ret;
 
 	do {
@@ -2492,7 +2492,7 @@ static int rtw89_pci_dphy_delay(struct rtw89_dev *rtwdev)
 				       PCIE_DPHY_DLY_25US, PCIE_PHY_GEN1);
 }
 
-static void rtw89_pci_power_wake(struct rtw89_dev *rtwdev, bool pwr_up)
+static void rtw89_pci_power_wake_ax(struct rtw89_dev *rtwdev, bool pwr_up)
 {
 	if (pwr_up)
 		rtw89_write32_set(rtwdev, R_AX_HCI_OPT_CTRL, BIT_WAKE_CTRL);
@@ -2799,6 +2799,8 @@ static int rtw89_pci_ops_deinit(struct rtw89_dev *rtwdev)
 {
 	const struct rtw89_pci_info *info = rtwdev->pci_info;
 
+	rtw89_pci_power_wake(rtwdev, false);
+
 	if (rtwdev->chip->chip_id == RTL8852A) {
 		/* ltr sw trigger */
 		rtw89_write32_set(rtwdev, R_AX_LTR_CTRL_0, B_AX_APP_LTR_IDLE);
@@ -2841,7 +2843,7 @@ static int rtw89_pci_ops_mac_pre_init_ax(struct rtw89_dev *rtwdev)
 		return ret;
 	}
 
-	rtw89_pci_power_wake(rtwdev, true);
+	rtw89_pci_power_wake_ax(rtwdev, true);
 	rtw89_pci_autoload_hang(rtwdev);
 	rtw89_pci_l12_vmain(rtwdev);
 	rtw89_pci_gen2_force_ib(rtwdev);
@@ -2886,6 +2888,13 @@ static int rtw89_pci_ops_mac_pre_init_ax(struct rtw89_dev *rtwdev)
 	return 0;
 }
 
+static int rtw89_pci_ops_mac_pre_deinit_ax(struct rtw89_dev *rtwdev)
+{
+	rtw89_pci_power_wake_ax(rtwdev, false);
+
+	return 0;
+}
+
 int rtw89_pci_ltr_set(struct rtw89_dev *rtwdev, bool en)
 {
 	u32 val;
@@ -4264,7 +4273,7 @@ const struct rtw89_pci_gen_def rtw89_pci_gen_ax = {
 					    B_AX_RDU_INT},
 
 	.mac_pre_init = rtw89_pci_ops_mac_pre_init_ax,
-	.mac_pre_deinit = NULL,
+	.mac_pre_deinit = rtw89_pci_ops_mac_pre_deinit_ax,
 	.mac_post_init = rtw89_pci_ops_mac_post_init_ax,
 
 	.clr_idx_all = rtw89_pci_clr_idx_all_ax,
@@ -4280,6 +4289,8 @@ const struct rtw89_pci_gen_def rtw89_pci_gen_ax = {
 	.aspm_set = rtw89_pci_aspm_set_ax,
 	.clkreq_set = rtw89_pci_clkreq_set_ax,
 	.l1ss_set = rtw89_pci_l1ss_set_ax,
+
+	.power_wake = rtw89_pci_power_wake_ax,
 };
 EXPORT_SYMBOL(rtw89_pci_gen_ax);
 
diff --git a/drivers/net/wireless/realtek/rtw89/pci.h b/drivers/net/wireless/realtek/rtw89/pci.h
index 48c3ab735db2..0ea4dcb84dd8 100644
--- a/drivers/net/wireless/realtek/rtw89/pci.h
+++ b/drivers/net/wireless/realtek/rtw89/pci.h
@@ -1276,6 +1276,8 @@ struct rtw89_pci_gen_def {
 	void (*aspm_set)(struct rtw89_dev *rtwdev, bool enable);
 	void (*clkreq_set)(struct rtw89_dev *rtwdev, bool enable);
 	void (*l1ss_set)(struct rtw89_dev *rtwdev, bool enable);
+
+	void (*power_wake)(struct rtw89_dev *rtwdev, bool pwr_up);
 };
 
 struct rtw89_pci_info {
@@ -1766,4 +1768,13 @@ static inline int rtw89_pci_poll_txdma_ch_idle(struct rtw89_dev *rtwdev)
 
 	return gen_def->poll_txdma_ch_idle(rtwdev);
 }
+
+static inline void rtw89_pci_power_wake(struct rtw89_dev *rtwdev, bool pwr_up)
+{
+	const struct rtw89_pci_info *info = rtwdev->pci_info;
+	const struct rtw89_pci_gen_def *gen_def = info->gen_def;
+
+	gen_def->power_wake(rtwdev, pwr_up);
+}
+
 #endif
diff --git a/drivers/net/wireless/realtek/rtw89/pci_be.c b/drivers/net/wireless/realtek/rtw89/pci_be.c
index 7cc328222965..2f0d9ff25ba5 100644
--- a/drivers/net/wireless/realtek/rtw89/pci_be.c
+++ b/drivers/net/wireless/realtek/rtw89/pci_be.c
@@ -614,5 +614,7 @@ const struct rtw89_pci_gen_def rtw89_pci_gen_be = {
 	.aspm_set = rtw89_pci_aspm_set_be,
 	.clkreq_set = rtw89_pci_clkreq_set_be,
 	.l1ss_set = rtw89_pci_l1ss_set_be,
+
+	.power_wake = _patch_pcie_power_wake_be,
 };
 EXPORT_SYMBOL(rtw89_pci_gen_be);
diff --git a/drivers/net/wireless/realtek/rtw89/phy.c b/drivers/net/wireless/realtek/rtw89/phy.c
index 4b47b45f897c..355c3f58ab18 100644
--- a/drivers/net/wireless/realtek/rtw89/phy.c
+++ b/drivers/net/wireless/realtek/rtw89/phy.c
@@ -3062,10 +3062,16 @@ rtw89_phy_c2h_rfk_report_state(struct rtw89_dev *rtwdev, struct sk_buff *c2h, u3
 		    (int)(len - sizeof(report->hdr)), &report->state);
 }
 
+static void
+rtw89_phy_c2h_rfk_log_tas_pwr(struct rtw89_dev *rtwdev, struct sk_buff *c2h, u32 len)
+{
+}
+
 static
 void (* const rtw89_phy_c2h_rfk_report_handler[])(struct rtw89_dev *rtwdev,
 						  struct sk_buff *c2h, u32 len) = {
 	[RTW89_PHY_C2H_RFK_REPORT_FUNC_STATE] = rtw89_phy_c2h_rfk_report_state,
+	[RTW89_PHY_C2H_RFK_LOG_TAS_PWR] = rtw89_phy_c2h_rfk_log_tas_pwr,
 };
 
 bool rtw89_phy_c2h_chk_atomic(struct rtw89_dev *rtwdev, u8 class, u8 func)
@@ -3119,11 +3125,11 @@ void rtw89_phy_c2h_handle(struct rtw89_dev *rtwdev, struct sk_buff *skb,
 			return;
 		fallthrough;
 	default:
-		rtw89_info(rtwdev, "c2h class %d not support\n", class);
+		rtw89_info(rtwdev, "PHY c2h class %d not support\n", class);
 		return;
 	}
 	if (!handler) {
-		rtw89_info(rtwdev, "c2h class %d func %d not support\n", class,
+		rtw89_info(rtwdev, "PHY c2h class %d func %d not support\n", class,
 			   func);
 		return;
 	}
@@ -3892,7 +3898,6 @@ static void rtw89_phy_cfo_set_crystal_cap(struct rtw89_dev *rtwdev,
 
 	if (!force && cfo->crystal_cap == crystal_cap)
 		return;
-	crystal_cap = clamp_t(u8, crystal_cap, 0, 127);
 	if (chip->chip_id == RTL8852A || chip->chip_id == RTL8851B) {
 		rtw89_phy_cfo_set_xcap_reg(rtwdev, true, crystal_cap);
 		rtw89_phy_cfo_set_xcap_reg(rtwdev, false, crystal_cap);
@@ -4015,7 +4020,7 @@ static void rtw89_phy_cfo_crystal_cap_adjust(struct rtw89_dev *rtwdev,
 					     s32 curr_cfo)
 {
 	struct rtw89_cfo_tracking_info *cfo = &rtwdev->cfo_tracking;
-	s8 crystal_cap = cfo->crystal_cap;
+	int crystal_cap = cfo->crystal_cap;
 	s32 cfo_abs = abs(curr_cfo);
 	int sign;
 
@@ -4036,15 +4041,17 @@ static void rtw89_phy_cfo_crystal_cap_adjust(struct rtw89_dev *rtwdev,
 	}
 	sign = curr_cfo > 0 ? 1 : -1;
 	if (cfo_abs > CFO_TRK_STOP_TH_4)
-		crystal_cap += 7 * sign;
+		crystal_cap += 3 * sign;
 	else if (cfo_abs > CFO_TRK_STOP_TH_3)
-		crystal_cap += 5 * sign;
-	else if (cfo_abs > CFO_TRK_STOP_TH_2)
 		crystal_cap += 3 * sign;
+	else if (cfo_abs > CFO_TRK_STOP_TH_2)
+		crystal_cap += 1 * sign;
 	else if (cfo_abs > CFO_TRK_STOP_TH_1)
 		crystal_cap += 1 * sign;
 	else
 		return;
+
+	crystal_cap = clamp(crystal_cap, 0, 127);
 	rtw89_phy_cfo_set_crystal_cap(rtwdev, (u8)crystal_cap, false);
 	rtw89_debug(rtwdev, RTW89_DBG_CFO,
 		    "X_cap{Curr,Default}={0x%x,0x%x}\n",
diff --git a/drivers/net/wireless/realtek/rtw89/phy.h b/drivers/net/wireless/realtek/rtw89/phy.h
index 7e335c02ee6f..961a4bacb02a 100644
--- a/drivers/net/wireless/realtek/rtw89/phy.h
+++ b/drivers/net/wireless/realtek/rtw89/phy.h
@@ -57,7 +57,7 @@
 #define CFO_TRK_STOP_TH_4 (30 << 2)
 #define CFO_TRK_STOP_TH_3 (20 << 2)
 #define CFO_TRK_STOP_TH_2 (10 << 2)
-#define CFO_TRK_STOP_TH_1 (00 << 2)
+#define CFO_TRK_STOP_TH_1 (03 << 2)
 #define CFO_TRK_STOP_TH (2 << 2)
 #define CFO_SW_COMP_FINE_TUNE (2 << 2)
 #define CFO_PERIOD_CNT 15
@@ -151,6 +151,7 @@ enum rtw89_phy_c2h_rfk_log_func {
 
 enum rtw89_phy_c2h_rfk_report_func {
 	RTW89_PHY_C2H_RFK_REPORT_FUNC_STATE = 0,
+	RTW89_PHY_C2H_RFK_LOG_TAS_PWR = 6,
 };
 
 enum rtw89_phy_c2h_dm_func {
diff --git a/drivers/net/wireless/realtek/rtw89/reg.h b/drivers/net/wireless/realtek/rtw89/reg.h
index 69678eab2309..7ec516979fe2 100644
--- a/drivers/net/wireless/realtek/rtw89/reg.h
+++ b/drivers/net/wireless/realtek/rtw89/reg.h
@@ -182,6 +182,7 @@
 
 #define R_AX_SYS_STATUS1 0x00F4
 #define B_AX_SEL_0XC0_MASK GENMASK(17, 16)
+#define B_AX_AUTO_WLPON BIT(10)
 #define B_AX_PAD_HCI_SEL_V2_MASK GENMASK(5, 3)
 #define MAC_AX_HCI_SEL_SDIO_UART 0
 #define MAC_AX_HCI_SEL_MULTI_USB 1
@@ -7093,6 +7094,10 @@
 #define B_BE_MACLBK_RDY_NUM_MASK GENMASK(7, 3)
 #define B_BE_MACLBK_EN BIT(0)
 
+#define R_BE_CLIENT_OM_CTRL 0x11040
+#define R_BE_CLIENT_OM_CTRL_C1 0x15040
+#define B_BE_TRIG_DIS_EHTTB BIT(24)
+
 #define R_BE_WMAC_NAV_CTL 0x11080
 #define R_BE_WMAC_NAV_CTL_C1 0x15080
 #define B_BE_WMAC_NAV_UPPER_EN BIT(26)
diff --git a/drivers/net/wireless/realtek/rtw89/regd.c b/drivers/net/wireless/realtek/rtw89/regd.c
index bb064a086970..e8df68818da0 100644
--- a/drivers/net/wireless/realtek/rtw89/regd.c
+++ b/drivers/net/wireless/realtek/rtw89/regd.c
@@ -695,6 +695,7 @@ void rtw89_regd_notifier(struct wiphy *wiphy, struct regulatory_request *request
 	struct ieee80211_hw *hw = wiphy_to_ieee80211_hw(wiphy);
 	struct rtw89_dev *rtwdev = hw->priv;
 
+	wiphy_lock(wiphy);
 	mutex_lock(&rtwdev->mutex);
 	rtw89_leave_ps_mode(rtwdev);
 
@@ -712,6 +713,7 @@ void rtw89_regd_notifier(struct wiphy *wiphy, struct regulatory_request *request
 
 exit:
 	mutex_unlock(&rtwdev->mutex);
+	wiphy_unlock(wiphy);
 }
 
 /* Maximum Transmit Power field (@raw) can be EIRP or PSD.
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8851b.c b/drivers/net/wireless/realtek/rtw89/rtw8851b.c
index f9766bf30e71..0d2a1e712b34 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8851b.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8851b.c
@@ -2443,6 +2443,7 @@ const struct rtw89_chip_info rtw8851b_chip_info = {
 	.try_ce_fw		= true,
 	.bbmcu_nr		= 0,
 	.needed_fw_elms		= 0,
+	.fw_blacklist		= NULL,
 	.fifo_size		= 196608,
 	.small_fifo_size	= true,
 	.dle_scc_rsvd_size	= 98304,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852a.c b/drivers/net/wireless/realtek/rtw89/rtw8852a.c
index 42d369d2e916..5f08207936c6 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852a.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852a.c
@@ -2159,6 +2159,7 @@ const struct rtw89_chip_info rtw8852a_chip_info = {
 	.try_ce_fw		= false,
 	.bbmcu_nr		= 0,
 	.needed_fw_elms		= 0,
+	.fw_blacklist		= NULL,
 	.fifo_size		= 458752,
 	.small_fifo_size	= false,
 	.dle_scc_rsvd_size	= 0,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852b.c b/drivers/net/wireless/realtek/rtw89/rtw8852b.c
index 364aa21cbd44..0e03d97ba1cf 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852b.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852b.c
@@ -797,6 +797,7 @@ const struct rtw89_chip_info rtw8852b_chip_info = {
 	.try_ce_fw		= true,
 	.bbmcu_nr		= 0,
 	.needed_fw_elms		= 0,
+	.fw_blacklist		= &rtw89_fw_blacklist_default,
 	.fifo_size		= 196608,
 	.small_fifo_size	= true,
 	.dle_scc_rsvd_size	= 98304,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852bt.c b/drivers/net/wireless/realtek/rtw89/rtw8852bt.c
index dab7e71ec6a1..1dd3e51bab9f 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852bt.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852bt.c
@@ -731,6 +731,7 @@ const struct rtw89_chip_info rtw8852bt_chip_info = {
 	.try_ce_fw		= true,
 	.bbmcu_nr		= 0,
 	.needed_fw_elms		= RTW89_AX_GEN_DEF_NEEDED_FW_ELEMENTS_NO_6GHZ,
+	.fw_blacklist		= &rtw89_fw_blacklist_default,
 	.fifo_size		= 458752,
 	.small_fifo_size	= true,
 	.dle_scc_rsvd_size	= 98304,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852c.c b/drivers/net/wireless/realtek/rtw89/rtw8852c.c
index dbe77abb2c48..5e2592cf1a9f 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852c.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852c.c
@@ -2936,6 +2936,7 @@ const struct rtw89_chip_info rtw8852c_chip_info = {
 	.try_ce_fw		= false,
 	.bbmcu_nr		= 0,
 	.needed_fw_elms		= 0,
+	.fw_blacklist		= &rtw89_fw_blacklist_default,
 	.fifo_size		= 458752,
 	.small_fifo_size	= false,
 	.dle_scc_rsvd_size	= 0,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8922a.c b/drivers/net/wireless/realtek/rtw89/rtw8922a.c
index ef7747adbcc2..64a41f24b2ad 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8922a.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8922a.c
@@ -2632,6 +2632,7 @@ const struct rtw89_chip_info rtw8922a_chip_info = {
 	.try_ce_fw		= false,
 	.bbmcu_nr		= 1,
 	.needed_fw_elms		= RTW89_BE_GEN_DEF_NEEDED_FW_ELEMENTS,
+	.fw_blacklist		= &rtw89_fw_blacklist_default,
 	.fifo_size		= 589824,
 	.small_fifo_size	= false,
 	.dle_scc_rsvd_size	= 0,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8922a_rfk.c b/drivers/net/wireless/realtek/rtw89/rtw8922a_rfk.c
index 28907df7407d..c958d6ab24d3 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8922a_rfk.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8922a_rfk.c
@@ -77,11 +77,6 @@ void rtw8922a_ctl_band_ch_bw(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 					     RR_CFGCH_BAND0 | RR_CFGCH_CH);
 			rf_reg[path][i] |= u32_encode_bits(central_ch, RR_CFGCH_CH);
 
-			if (band == RTW89_BAND_2G)
-				rtw89_write_rf(rtwdev, path, RR_SMD, RR_VCO2, 0x0);
-			else
-				rtw89_write_rf(rtwdev, path, RR_SMD, RR_VCO2, 0x1);
-
 			switch (band) {
 			case RTW89_BAND_2G:
 			default:
diff --git a/drivers/net/wireless/realtek/rtw89/ser.c b/drivers/net/wireless/realtek/rtw89/ser.c
index 7b203bb7f151..02c2ac12f197 100644
--- a/drivers/net/wireless/realtek/rtw89/ser.c
+++ b/drivers/net/wireless/realtek/rtw89/ser.c
@@ -156,9 +156,11 @@ static void ser_state_run(struct rtw89_ser *ser, u8 evt)
 	rtw89_debug(rtwdev, RTW89_DBG_SER, "ser: %s receive %s\n",
 		    ser_st_name(ser), ser_ev_name(ser, evt));
 
+	wiphy_lock(rtwdev->hw->wiphy);
 	mutex_lock(&rtwdev->mutex);
 	rtw89_leave_lps(rtwdev);
 	mutex_unlock(&rtwdev->mutex);
+	wiphy_unlock(rtwdev->hw->wiphy);
 
 	ser->st_tbl[ser->state].st_func(ser, evt);
 }
@@ -707,9 +709,11 @@ static void ser_l2_reset_st_hdl(struct rtw89_ser *ser, u8 evt)
 
 	switch (evt) {
 	case SER_EV_STATE_IN:
+		wiphy_lock(rtwdev->hw->wiphy);
 		mutex_lock(&rtwdev->mutex);
 		ser_l2_reset_st_pre_hdl(ser);
 		mutex_unlock(&rtwdev->mutex);
+		wiphy_unlock(rtwdev->hw->wiphy);
 
 		ieee80211_restart_hw(rtwdev->hw);
 		ser_set_alarm(ser, SER_RECFG_TIMEOUT, SER_EV_L2_RECFG_TIMEOUT);
diff --git a/drivers/net/wireless/realtek/rtw89/wow.c b/drivers/net/wireless/realtek/rtw89/wow.c
index 3e81fd974ec1..fdb715dc175c 100644
--- a/drivers/net/wireless/realtek/rtw89/wow.c
+++ b/drivers/net/wireless/realtek/rtw89/wow.c
@@ -1415,6 +1415,8 @@ static void rtw89_fw_release_pno_pkt_list(struct rtw89_dev *rtwdev,
 static int rtw89_pno_scan_update_probe_req(struct rtw89_dev *rtwdev,
 					   struct rtw89_vif_link *rtwvif_link)
 {
+	static const u8 basic_rate_ie[] = {WLAN_EID_SUPP_RATES, 0x08,
+		 0x0c, 0x12, 0x18, 0x24, 0x30, 0x48, 0x60, 0x6c};
 	struct rtw89_wow_param *rtw_wow = &rtwdev->wow;
 	struct cfg80211_sched_scan_request *nd_config = rtw_wow->nd_config;
 	u8 num = nd_config->n_match_sets, i;
@@ -1426,10 +1428,11 @@ static int rtw89_pno_scan_update_probe_req(struct rtw89_dev *rtwdev,
 		skb = ieee80211_probereq_get(rtwdev->hw, rtwvif_link->mac_addr,
 					     nd_config->match_sets[i].ssid.ssid,
 					     nd_config->match_sets[i].ssid.ssid_len,
-					     nd_config->ie_len);
+					     nd_config->ie_len + sizeof(basic_rate_ie));
 		if (!skb)
 			return -ENOMEM;
 
+		skb_put_data(skb, basic_rate_ie, sizeof(basic_rate_ie));
 		skb_put_data(skb, nd_config->ie, nd_config->ie_len);
 
 		info = kzalloc(sizeof(*info), GFP_KERNEL);
diff --git a/drivers/net/wireless/ti/wl1251/tx.c b/drivers/net/wireless/ti/wl1251/tx.c
index 474b603c121c..adb4840b0489 100644
--- a/drivers/net/wireless/ti/wl1251/tx.c
+++ b/drivers/net/wireless/ti/wl1251/tx.c
@@ -342,8 +342,10 @@ void wl1251_tx_work(struct work_struct *work)
 	while ((skb = skb_dequeue(&wl->tx_queue))) {
 		if (!woken_up) {
 			ret = wl1251_ps_elp_wakeup(wl);
-			if (ret < 0)
+			if (ret < 0) {
+				skb_queue_head(&wl->tx_queue, skb);
 				goto out;
+			}
 			woken_up = true;
 		}
 
diff --git a/drivers/net/wireless/ti/wlcore/main.c b/drivers/net/wireless/ti/wlcore/main.c
index 0c77b8524160..42805ed7ca12 100644
--- a/drivers/net/wireless/ti/wlcore/main.c
+++ b/drivers/net/wireless/ti/wlcore/main.c
@@ -2612,24 +2612,24 @@ static int wl1271_op_add_interface(struct ieee80211_hw *hw,
 	if (test_bit(WL1271_FLAG_RECOVERY_IN_PROGRESS, &wl->flags) ||
 	    test_bit(WLVIF_FLAG_INITIALIZED, &wlvif->flags)) {
 		ret = -EBUSY;
-		goto out;
+		goto out_unlock;
 	}
 
 
 	ret = wl12xx_init_vif_data(wl, vif);
 	if (ret < 0)
-		goto out;
+		goto out_unlock;
 
 	wlvif->wl = wl;
 	role_type = wl12xx_get_role_type(wl, wlvif);
 	if (role_type == WL12XX_INVALID_ROLE_TYPE) {
 		ret = -EINVAL;
-		goto out;
+		goto out_unlock;
 	}
 
 	ret = wlcore_allocate_hw_queue_base(wl, wlvif);
 	if (ret < 0)
-		goto out;
+		goto out_unlock;
 
 	/*
 	 * TODO: after the nvs issue will be solved, move this block
@@ -2644,7 +2644,7 @@ static int wl1271_op_add_interface(struct ieee80211_hw *hw,
 
 		ret = wl12xx_init_fw(wl);
 		if (ret < 0)
-			goto out;
+			goto out_unlock;
 	}
 
 	/*
diff --git a/drivers/net/wireless/virtual/mac80211_hwsim.c b/drivers/net/wireless/virtual/mac80211_hwsim.c
index 3f424f14de4e..6fcc21f596ea 100644
--- a/drivers/net/wireless/virtual/mac80211_hwsim.c
+++ b/drivers/net/wireless/virtual/mac80211_hwsim.c
@@ -4,7 +4,7 @@
  * Copyright (c) 2008, Jouni Malinen <j@w1.fi>
  * Copyright (c) 2011, Javier Lopez <jlopex@gmail.com>
  * Copyright (c) 2016 - 2017 Intel Deutschland GmbH
- * Copyright (C) 2018 - 2024 Intel Corporation
+ * Copyright (C) 2018 - 2025 Intel Corporation
  */
 
 /*
@@ -1229,6 +1229,11 @@ static void mac80211_hwsim_set_tsf(struct ieee80211_hw *hw,
 	/* MLD not supported here */
 	u32 bcn_int = data->link_data[0].beacon_int;
 	u64 delta = abs(tsf - now);
+	struct ieee80211_bss_conf *conf;
+
+	conf = link_conf_dereference_protected(vif, data->link_data[0].link_id);
+	if (conf && !conf->enable_beacon)
+		return;
 
 	/* adjust after beaconing with new timestamp at old TBTT */
 	if (tsf > now) {
@@ -1983,11 +1988,13 @@ static void mac80211_hwsim_tx(struct ieee80211_hw *hw,
 			return;
 		}
 
-		if (sta && sta->mlo) {
-			if (WARN_ON(!link_sta)) {
-				ieee80211_free_txskb(hw, skb);
-				return;
-			}
+		/* Do address translations only between shared links. It is
+		 * possible that while an non-AP MLD station and an AP MLD
+		 * station have shared links, the frame is intended to be sent
+		 * on a link which is not shared (for example when sending a
+		 * probe response).
+		 */
+		if (sta && sta->mlo && link_sta) {
 			/* address translation to link addresses on TX */
 			ether_addr_copy(hdr->addr1, link_sta->addr);
 			ether_addr_copy(hdr->addr2, bss_conf->addr);
diff --git a/drivers/net/wireless/zydas/zd1211rw/zd_mac.c b/drivers/net/wireless/zydas/zd1211rw/zd_mac.c
index f90c33d19b39..8fd7be37e209 100644
--- a/drivers/net/wireless/zydas/zd1211rw/zd_mac.c
+++ b/drivers/net/wireless/zydas/zd1211rw/zd_mac.c
@@ -583,7 +583,11 @@ void zd_mac_tx_to_dev(struct sk_buff *skb, int error)
 
 		skb_queue_tail(q, skb);
 		while (skb_queue_len(q) > ZD_MAC_MAX_ACK_WAITERS) {
-			zd_mac_tx_status(hw, skb_dequeue(q),
+			skb = skb_dequeue(q);
+			if (!skb)
+				break;
+
+			zd_mac_tx_status(hw, skb,
 					 mac->ack_pending ? mac->ack_signal : 0,
 					 NULL);
 			mac->ack_pending = 0;
diff --git a/drivers/net/wwan/iosm/iosm_ipc_pcie.c b/drivers/net/wwan/iosm/iosm_ipc_pcie.c
index 04517bd3325a..a066977af0be 100644
--- a/drivers/net/wwan/iosm/iosm_ipc_pcie.c
+++ b/drivers/net/wwan/iosm/iosm_ipc_pcie.c
@@ -6,6 +6,7 @@
 #include <linux/acpi.h>
 #include <linux/bitfield.h>
 #include <linux/module.h>
+#include <linux/suspend.h>
 #include <net/rtnetlink.h>
 
 #include "iosm_ipc_imem.h"
@@ -18,6 +19,7 @@ MODULE_LICENSE("GPL v2");
 /* WWAN GUID */
 static guid_t wwan_acpi_guid = GUID_INIT(0xbad01b75, 0x22a8, 0x4f48, 0x87, 0x92,
 				       0xbd, 0xde, 0x94, 0x67, 0x74, 0x7d);
+static bool pci_registered;
 
 static void ipc_pcie_resources_release(struct iosm_pcie *ipc_pcie)
 {
@@ -448,7 +450,6 @@ static struct pci_driver iosm_ipc_driver = {
 	},
 	.id_table = iosm_ipc_ids,
 };
-module_pci_driver(iosm_ipc_driver);
 
 int ipc_pcie_addr_map(struct iosm_pcie *ipc_pcie, unsigned char *data,
 		      size_t size, dma_addr_t *mapping, int direction)
@@ -530,3 +531,56 @@ void ipc_pcie_kfree_skb(struct iosm_pcie *ipc_pcie, struct sk_buff *skb)
 	IPC_CB(skb)->mapping = 0;
 	dev_kfree_skb(skb);
 }
+
+static int pm_notify(struct notifier_block *nb, unsigned long mode, void *_unused)
+{
+	if (mode == PM_HIBERNATION_PREPARE || mode == PM_RESTORE_PREPARE) {
+		if (pci_registered) {
+			pci_unregister_driver(&iosm_ipc_driver);
+			pci_registered = false;
+		}
+	} else if (mode == PM_POST_HIBERNATION || mode == PM_POST_RESTORE) {
+		if (!pci_registered) {
+			int ret;
+
+			ret = pci_register_driver(&iosm_ipc_driver);
+			if (ret) {
+				pr_err(KBUILD_MODNAME ": unable to re-register PCI driver: %d\n",
+				       ret);
+			} else {
+				pci_registered = true;
+			}
+		}
+	}
+
+	return 0;
+}
+
+static struct notifier_block pm_notifier = {
+	.notifier_call = pm_notify,
+};
+
+static int __init iosm_ipc_driver_init(void)
+{
+	int ret;
+
+	ret = pci_register_driver(&iosm_ipc_driver);
+	if (ret)
+		return ret;
+
+	pci_registered = true;
+
+	register_pm_notifier(&pm_notifier);
+
+	return 0;
+}
+module_init(iosm_ipc_driver_init);
+
+static void __exit iosm_ipc_driver_exit(void)
+{
+	unregister_pm_notifier(&pm_notifier);
+
+	if (pci_registered)
+		pci_unregister_driver(&iosm_ipc_driver);
+}
+module_exit(iosm_ipc_driver_exit);
diff --git a/drivers/net/wwan/mhi_wwan_mbim.c b/drivers/net/wwan/mhi_wwan_mbim.c
index d5a9360323d2..c814fbd756a1 100644
--- a/drivers/net/wwan/mhi_wwan_mbim.c
+++ b/drivers/net/wwan/mhi_wwan_mbim.c
@@ -220,7 +220,7 @@ static int mbim_rx_verify_nth16(struct mhi_mbim_context *mbim, struct sk_buff *s
 	if (mbim->rx_seq + 1 != le16_to_cpu(nth16->wSequence) &&
 	    (mbim->rx_seq || le16_to_cpu(nth16->wSequence)) &&
 	    !(mbim->rx_seq == 0xffff && !le16_to_cpu(nth16->wSequence))) {
-		net_err_ratelimited("sequence number glitch prev=%d curr=%d\n",
+		net_dbg_ratelimited("sequence number glitch prev=%d curr=%d\n",
 				    mbim->rx_seq, le16_to_cpu(nth16->wSequence));
 	}
 	mbim->rx_seq = le16_to_cpu(nth16->wSequence);
@@ -550,8 +550,8 @@ static int mhi_mbim_newlink(void *ctxt, struct net_device *ndev, u32 if_id,
 	struct mhi_mbim_link *link = wwan_netdev_drvpriv(ndev);
 	struct mhi_mbim_context *mbim = ctxt;
 
-	link->session = if_id;
 	link->mbim = mbim;
+	link->session = mhi_mbim_get_link_mux_id(link->mbim->mdev->mhi_cntrl) + if_id;
 	link->ndev = ndev;
 	u64_stats_init(&link->rx_syncp);
 	u64_stats_init(&link->tx_syncp);
@@ -607,7 +607,7 @@ static int mhi_mbim_probe(struct mhi_device *mhi_dev, const struct mhi_device_id
 {
 	struct mhi_controller *cntrl = mhi_dev->mhi_cntrl;
 	struct mhi_mbim_context *mbim;
-	int err, link_id;
+	int err;
 
 	mbim = devm_kzalloc(&mhi_dev->dev, sizeof(*mbim), GFP_KERNEL);
 	if (!mbim)
@@ -628,11 +628,8 @@ static int mhi_mbim_probe(struct mhi_device *mhi_dev, const struct mhi_device_id
 	/* Number of transfer descriptors determines size of the queue */
 	mbim->rx_queue_sz = mhi_get_free_desc_count(mhi_dev, DMA_FROM_DEVICE);
 
-	/* Get the corresponding mux_id from mhi */
-	link_id = mhi_mbim_get_link_mux_id(cntrl);
-
 	/* Register wwan link ops with MHI controller representing WWAN instance */
-	return wwan_register_ops(&cntrl->mhi_dev->dev, &mhi_mbim_wwan_ops, mbim, link_id);
+	return wwan_register_ops(&cntrl->mhi_dev->dev, &mhi_mbim_wwan_ops, mbim, 0);
 }
 
 static void mhi_mbim_remove(struct mhi_device *mhi_dev)
diff --git a/drivers/net/wwan/t7xx/t7xx_netdev.c b/drivers/net/wwan/t7xx/t7xx_netdev.c
index 91fa082e9cab..fc0a7cb181df 100644
--- a/drivers/net/wwan/t7xx/t7xx_netdev.c
+++ b/drivers/net/wwan/t7xx/t7xx_netdev.c
@@ -302,7 +302,7 @@ static int t7xx_ccmni_wwan_newlink(void *ctxt, struct net_device *dev, u32 if_id
 	ccmni->ctlb = ctlb;
 	ccmni->dev = dev;
 	atomic_set(&ccmni->usage, 0);
-	ctlb->ccmni_inst[if_id] = ccmni;
+	WRITE_ONCE(ctlb->ccmni_inst[if_id], ccmni);
 
 	ret = register_netdevice(dev);
 	if (ret)
@@ -324,6 +324,7 @@ static void t7xx_ccmni_wwan_dellink(void *ctxt, struct net_device *dev, struct l
 	if (WARN_ON(ctlb->ccmni_inst[if_id] != ccmni))
 		return;
 
+	WRITE_ONCE(ctlb->ccmni_inst[if_id], NULL);
 	unregister_netdevice(dev);
 }
 
@@ -419,7 +420,7 @@ static void t7xx_ccmni_recv_skb(struct t7xx_ccmni_ctrl *ccmni_ctlb, struct sk_bu
 
 	skb_cb = T7XX_SKB_CB(skb);
 	netif_id = skb_cb->netif_idx;
-	ccmni = ccmni_ctlb->ccmni_inst[netif_id];
+	ccmni = READ_ONCE(ccmni_ctlb->ccmni_inst[netif_id]);
 	if (!ccmni) {
 		dev_kfree_skb(skb);
 		return;
@@ -441,7 +442,7 @@ static void t7xx_ccmni_recv_skb(struct t7xx_ccmni_ctrl *ccmni_ctlb, struct sk_bu
 
 static void t7xx_ccmni_queue_tx_irq_notify(struct t7xx_ccmni_ctrl *ctlb, int qno)
 {
-	struct t7xx_ccmni *ccmni = ctlb->ccmni_inst[0];
+	struct t7xx_ccmni *ccmni = READ_ONCE(ctlb->ccmni_inst[0]);
 	struct netdev_queue *net_queue;
 
 	if (netif_running(ccmni->dev) && atomic_read(&ccmni->usage) > 0) {
@@ -453,7 +454,7 @@ static void t7xx_ccmni_queue_tx_irq_notify(struct t7xx_ccmni_ctrl *ctlb, int qno
 
 static void t7xx_ccmni_queue_tx_full_notify(struct t7xx_ccmni_ctrl *ctlb, int qno)
 {
-	struct t7xx_ccmni *ccmni = ctlb->ccmni_inst[0];
+	struct t7xx_ccmni *ccmni = READ_ONCE(ctlb->ccmni_inst[0]);
 	struct netdev_queue *net_queue;
 
 	if (atomic_read(&ccmni->usage) > 0) {
@@ -471,7 +472,7 @@ static void t7xx_ccmni_queue_state_notify(struct t7xx_pci_dev *t7xx_dev,
 	if (ctlb->md_sta != MD_STATE_READY)
 		return;
 
-	if (!ctlb->ccmni_inst[0]) {
+	if (!READ_ONCE(ctlb->ccmni_inst[0])) {
 		dev_warn(&t7xx_dev->pdev->dev, "No netdev registered yet\n");
 		return;
 	}
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index 63fe51d0e64d..2042399e890a 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -637,8 +637,6 @@ static int xennet_xdp_xmit_one(struct net_device *dev,
 	tx_stats->packets++;
 	u64_stats_update_end(&tx_stats->syncp);
 
-	xennet_tx_buf_gc(queue);
-
 	return 0;
 }
 
@@ -848,9 +846,6 @@ static netdev_tx_t xennet_start_xmit(struct sk_buff *skb, struct net_device *dev
 	tx_stats->packets++;
 	u64_stats_update_end(&tx_stats->syncp);
 
-	/* Note: It is not safe to access skb after xennet_tx_buf_gc()! */
-	xennet_tx_buf_gc(queue);
-
 	if (!netfront_tx_slot_available(queue))
 		netif_tx_stop_queue(netdev_get_tx_queue(dev, queue->id));
 
@@ -985,20 +980,27 @@ static u32 xennet_run_xdp(struct netfront_queue *queue, struct page *pdata,
 	act = bpf_prog_run_xdp(prog, xdp);
 	switch (act) {
 	case XDP_TX:
-		get_page(pdata);
 		xdpf = xdp_convert_buff_to_frame(xdp);
+		if (unlikely(!xdpf)) {
+			trace_xdp_exception(queue->info->netdev, prog, act);
+			break;
+		}
+		get_page(pdata);
 		err = xennet_xdp_xmit(queue->info->netdev, 1, &xdpf, 0);
-		if (unlikely(!err))
+		if (unlikely(err <= 0)) {
+			if (err < 0)
+				trace_xdp_exception(queue->info->netdev, prog, act);
 			xdp_return_frame_rx_napi(xdpf);
-		else if (unlikely(err < 0))
-			trace_xdp_exception(queue->info->netdev, prog, act);
+		}
 		break;
 	case XDP_REDIRECT:
 		get_page(pdata);
 		err = xdp_do_redirect(queue->info->netdev, xdp, prog);
 		*need_xdp_flush = true;
-		if (unlikely(err))
+		if (unlikely(err)) {
 			trace_xdp_exception(queue->info->netdev, prog, act);
+			xdp_return_buff(xdp);
+		}
 		break;
 	case XDP_PASS:
 	case XDP_DROP:
diff --git a/drivers/ntb/hw/amd/ntb_hw_amd.c b/drivers/ntb/hw/amd/ntb_hw_amd.c
index d687e8c2cc78..63ceed89b62e 100644
--- a/drivers/ntb/hw/amd/ntb_hw_amd.c
+++ b/drivers/ntb/hw/amd/ntb_hw_amd.c
@@ -1318,6 +1318,7 @@ static const struct pci_device_id amd_ntb_pci_tbl[] = {
 	{ PCI_VDEVICE(AMD, 0x148b), (kernel_ulong_t)&dev_data[1] },
 	{ PCI_VDEVICE(AMD, 0x14c0), (kernel_ulong_t)&dev_data[1] },
 	{ PCI_VDEVICE(AMD, 0x14c3), (kernel_ulong_t)&dev_data[1] },
+	{ PCI_VDEVICE(AMD, 0x155a), (kernel_ulong_t)&dev_data[1] },
 	{ PCI_VDEVICE(HYGON, 0x145b), (kernel_ulong_t)&dev_data[0] },
 	{ 0, }
 };
diff --git a/drivers/ntb/hw/idt/ntb_hw_idt.c b/drivers/ntb/hw/idt/ntb_hw_idt.c
index 6fc9dfe82474..419de7038570 100644
--- a/drivers/ntb/hw/idt/ntb_hw_idt.c
+++ b/drivers/ntb/hw/idt/ntb_hw_idt.c
@@ -1041,7 +1041,7 @@ static inline char *idt_get_mw_name(enum idt_mw_type mw_type)
 static struct idt_mw_cfg *idt_scan_mws(struct idt_ntb_dev *ndev, int port,
 				       unsigned char *mw_cnt)
 {
-	struct idt_mw_cfg mws[IDT_MAX_NR_MWS], *ret_mws;
+	struct idt_mw_cfg *mws;
 	const struct idt_ntb_bar *bars;
 	enum idt_mw_type mw_type;
 	unsigned char widx, bidx, en_cnt;
@@ -1049,6 +1049,11 @@ static struct idt_mw_cfg *idt_scan_mws(struct idt_ntb_dev *ndev, int port,
 	int aprt_size;
 	u32 data;
 
+	mws = devm_kcalloc(&ndev->ntb.pdev->dev, IDT_MAX_NR_MWS,
+			   sizeof(*mws), GFP_KERNEL);
+	if (!mws)
+		return ERR_PTR(-ENOMEM);
+
 	/* Retrieve the array of the BARs registers */
 	bars = portdata_tbl[port].bars;
 
@@ -1103,16 +1108,7 @@ static struct idt_mw_cfg *idt_scan_mws(struct idt_ntb_dev *ndev, int port,
 		}
 	}
 
-	/* Allocate memory for memory window descriptors */
-	ret_mws = devm_kcalloc(&ndev->ntb.pdev->dev, *mw_cnt, sizeof(*ret_mws),
-			       GFP_KERNEL);
-	if (!ret_mws)
-		return ERR_PTR(-ENOMEM);
-
-	/* Copy the info of detected memory windows */
-	memcpy(ret_mws, mws, (*mw_cnt)*sizeof(*ret_mws));
-
-	return ret_mws;
+	return mws;
 }
 
 /*
diff --git a/drivers/ntb/hw/intel/ntb_hw_gen3.c b/drivers/ntb/hw/intel/ntb_hw_gen3.c
index ffcfc3e02c35..a5aa96a31f4a 100644
--- a/drivers/ntb/hw/intel/ntb_hw_gen3.c
+++ b/drivers/ntb/hw/intel/ntb_hw_gen3.c
@@ -215,6 +215,9 @@ static int gen3_init_ntb(struct intel_ntb_dev *ndev)
 	}
 
 	ndev->db_valid_mask = BIT_ULL(ndev->db_count) - 1;
+	/* Make sure we are not using DB's used for link status */
+	if (ndev->hwerr_flags & NTB_HWERR_MSIX_VECTOR32_BAD)
+		ndev->db_valid_mask &= ~ndev->db_link_mask;
 
 	ndev->reg->db_iowrite(ndev->db_valid_mask,
 			      ndev->self_mmio +
diff --git a/drivers/ntb/hw/mscc/ntb_hw_switchtec.c b/drivers/ntb/hw/mscc/ntb_hw_switchtec.c
index ad1786be2554..f851397b65d6 100644
--- a/drivers/ntb/hw/mscc/ntb_hw_switchtec.c
+++ b/drivers/ntb/hw/mscc/ntb_hw_switchtec.c
@@ -288,7 +288,7 @@ static int switchtec_ntb_mw_set_trans(struct ntb_dev *ntb, int pidx, int widx,
 	if (size != 0 && xlate_pos < 12)
 		return -EINVAL;
 
-	if (!IS_ALIGNED(addr, BIT_ULL(xlate_pos))) {
+	if (xlate_pos >= 0 && !IS_ALIGNED(addr, BIT_ULL(xlate_pos))) {
 		/*
 		 * In certain circumstances we can get a buffer that is
 		 * not aligned to its size. (Most of the time
diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c
index a22ea4a4b202..4f775c3e218f 100644
--- a/drivers/ntb/ntb_transport.c
+++ b/drivers/ntb/ntb_transport.c
@@ -1353,7 +1353,7 @@ static int ntb_transport_probe(struct ntb_client *self, struct ntb_dev *ndev)
 	qp_count = ilog2(qp_bitmap);
 	if (nt->use_msi) {
 		qp_count -= 1;
-		nt->msi_db_mask = 1 << qp_count;
+		nt->msi_db_mask = BIT_ULL(qp_count);
 		ntb_db_clear_mask(ndev, nt->msi_db_mask);
 	}
 
diff --git a/drivers/ntb/test/ntb_perf.c b/drivers/ntb/test/ntb_perf.c
index 72bc1d017a46..dfd175f79e8f 100644
--- a/drivers/ntb/test/ntb_perf.c
+++ b/drivers/ntb/test/ntb_perf.c
@@ -839,10 +839,8 @@ static int perf_copy_chunk(struct perf_thread *pthr,
 	dma_set_unmap(tx, unmap);
 
 	ret = dma_submit_error(dmaengine_submit(tx));
-	if (ret) {
-		dmaengine_unmap_put(unmap);
+	if (ret)
 		goto err_free_resource;
-	}
 
 	dmaengine_unmap_put(unmap);
 
diff --git a/drivers/nvdimm/label.c b/drivers/nvdimm/label.c
index 082253a3a956..04f4a049599a 100644
--- a/drivers/nvdimm/label.c
+++ b/drivers/nvdimm/label.c
@@ -442,7 +442,8 @@ int nd_label_data_init(struct nvdimm_drvdata *ndd)
 	if (ndd->data)
 		return 0;
 
-	if (ndd->nsarea.status || ndd->nsarea.max_xfer == 0) {
+	if (ndd->nsarea.status || ndd->nsarea.max_xfer == 0 ||
+	    ndd->nsarea.config_size == 0) {
 		dev_dbg(ndd->dev, "failed to init config data area: (%u:%u)\n",
 			ndd->nsarea.max_xfer, ndd->nsarea.config_size);
 		return -ENXIO;
diff --git a/drivers/nvme/host/Kconfig b/drivers/nvme/host/Kconfig
index 486afe598184..09ed1f61c9a8 100644
--- a/drivers/nvme/host/Kconfig
+++ b/drivers/nvme/host/Kconfig
@@ -97,6 +97,7 @@ config NVME_TCP_TLS
 	depends on NVME_TCP
 	select NET_HANDSHAKE
 	select KEYS
+	select TLS
 	help
 	  Enables TLS encryption for NVMe TCP using the netlink handshake API.
 
diff --git a/drivers/nvme/host/apple.c b/drivers/nvme/host/apple.c
index b1387dc459a3..328f5a103628 100644
--- a/drivers/nvme/host/apple.c
+++ b/drivers/nvme/host/apple.c
@@ -599,7 +599,8 @@ static inline void apple_nvme_handle_cqe(struct apple_nvme_queue *q,
 	}
 
 	if (!nvme_try_complete_req(req, cqe->status, cqe->result) &&
-	    !blk_mq_add_to_batch(req, iob, nvme_req(req)->status,
+	    !blk_mq_add_to_batch(req, iob,
+				 nvme_req(req)->status != NVME_SC_SUCCESS,
 				 apple_nvme_complete_batch))
 		apple_nvme_complete_rq(req);
 }
@@ -649,7 +650,7 @@ static bool apple_nvme_handle_cq(struct apple_nvme_queue *q, bool force)
 
 	found = apple_nvme_poll_cq(q, &iob);
 
-	if (!rq_list_empty(iob.req_list))
+	if (!rq_list_empty(&iob.req_list))
 		apple_nvme_complete_batch(&iob);
 
 	return found;
@@ -1518,6 +1519,7 @@ static struct apple_nvme *apple_nvme_alloc(struct platform_device *pdev)
 
 	return anv;
 put_dev:
+	apple_nvme_detach_genpd(anv);
 	put_device(anv->dev);
 	return ERR_PTR(ret);
 }
@@ -1551,6 +1553,7 @@ out_uninit_ctrl:
 	nvme_uninit_ctrl(&anv->ctrl);
 out_put_ctrl:
 	nvme_put_ctrl(&anv->ctrl);
+	apple_nvme_detach_genpd(anv);
 	return ret;
 }
 
diff --git a/drivers/nvme/host/constants.c b/drivers/nvme/host/constants.c
index 2b9e6cfaf2a8..1a0058be5821 100644
--- a/drivers/nvme/host/constants.c
+++ b/drivers/nvme/host/constants.c
@@ -145,7 +145,7 @@ static const char * const nvme_statuses[] = {
 	[NVME_SC_BAD_ATTRIBUTES] = "Conflicting Attributes",
 	[NVME_SC_INVALID_PI] = "Invalid Protection Information",
 	[NVME_SC_READ_ONLY] = "Attempted Write to Read Only Range",
-	[NVME_SC_ONCS_NOT_SUPPORTED] = "ONCS Not Supported",
+	[NVME_SC_CMD_SIZE_LIM_EXCEEDED	] = "Command Size Limits Exceeded",
 	[NVME_SC_ZONE_BOUNDARY_ERROR] = "Zoned Boundary Error",
 	[NVME_SC_ZONE_FULL] = "Zone Is Full",
 	[NVME_SC_ZONE_READ_ONLY] = "Zone Is Read Only",
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 249914b90dbf..9e223574db7f 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -284,7 +284,6 @@ static blk_status_t nvme_error_status(u16 status)
 	case NVME_SC_NS_NOT_READY:
 		return BLK_STS_TARGET;
 	case NVME_SC_BAD_ATTRIBUTES:
-	case NVME_SC_ONCS_NOT_SUPPORTED:
 	case NVME_SC_INVALID_OPCODE:
 	case NVME_SC_INVALID_FIELD:
 	case NVME_SC_INVALID_NS:
@@ -376,12 +375,12 @@ static void nvme_log_err_passthru(struct request *req)
 		nr->status & NVME_SC_MASK,	/* Status Code */
 		nr->status & NVME_STATUS_MORE ? "MORE " : "",
 		nr->status & NVME_STATUS_DNR  ? "DNR "  : "",
-		nr->cmd->common.cdw10,
-		nr->cmd->common.cdw11,
-		nr->cmd->common.cdw12,
-		nr->cmd->common.cdw13,
-		nr->cmd->common.cdw14,
-		nr->cmd->common.cdw14);
+		le32_to_cpu(nr->cmd->common.cdw10),
+		le32_to_cpu(nr->cmd->common.cdw11),
+		le32_to_cpu(nr->cmd->common.cdw12),
+		le32_to_cpu(nr->cmd->common.cdw13),
+		le32_to_cpu(nr->cmd->common.cdw14),
+		le32_to_cpu(nr->cmd->common.cdw15));
 }
 
 enum nvme_disposition {
@@ -429,6 +428,12 @@ static inline void nvme_end_req_zoned(struct request *req)
 
 static inline void __nvme_end_req(struct request *req)
 {
+	if (unlikely(nvme_req(req)->status && !(req->rq_flags & RQF_QUIET))) {
+		if (blk_rq_is_passthrough(req))
+			nvme_log_err_passthru(req);
+		else
+			nvme_log_error(req);
+	}
 	nvme_end_req_zoned(req);
 	nvme_trace_bio_complete(req);
 	if (req->cmd_flags & REQ_NVME_MPATH)
@@ -439,12 +444,6 @@ void nvme_end_req(struct request *req)
 {
 	blk_status_t status = nvme_error_status(nvme_req(req)->status);
 
-	if (unlikely(nvme_req(req)->status && !(req->rq_flags & RQF_QUIET))) {
-		if (blk_rq_is_passthrough(req))
-			nvme_log_err_passthru(req);
-		else
-			nvme_log_error(req);
-	}
 	__nvme_end_req(req);
 	blk_mq_end_request(req, status);
 }
@@ -562,8 +561,6 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
 	switch (new_state) {
 	case NVME_CTRL_LIVE:
 		switch (old_state) {
-		case NVME_CTRL_NEW:
-		case NVME_CTRL_RESETTING:
 		case NVME_CTRL_CONNECTING:
 			changed = true;
 			fallthrough;
@@ -760,6 +757,10 @@ blk_status_t nvme_fail_nonready_command(struct nvme_ctrl *ctrl,
 	    !test_bit(NVME_CTRL_FAILFAST_EXPIRED, &ctrl->flags) &&
 	    !blk_noretry_request(rq) && !(rq->cmd_flags & REQ_NVME_MPATH))
 		return BLK_STS_RESOURCE;
+
+	if (!(rq->rq_flags & RQF_DONTPREP))
+		nvme_clear_nvme_request(rq);
+
 	return nvme_host_path_error(rq);
 }
 EXPORT_SYMBOL_GPL(nvme_fail_nonready_command);
@@ -1691,7 +1692,13 @@ int nvme_set_queue_count(struct nvme_ctrl *ctrl, int *count)
 
 	status = nvme_set_features(ctrl, NVME_FEAT_NUM_QUEUES, q_count, NULL, 0,
 			&result);
-	if (status < 0)
+
+	/*
+	 * It's either a kernel error or the host observed a connection
+	 * lost. In either case it's not possible communicate with the
+	 * controller and thus enter the error code path.
+	 */
+	if (status < 0 || status == NVME_SC_HOST_PATH_ERROR)
 		return status;
 
 	/*
@@ -3085,7 +3092,7 @@ int nvme_get_log(struct nvme_ctrl *ctrl, u32 nsid, u8 log_page, u8 lsp, u8 csi,
 static int nvme_get_effects_log(struct nvme_ctrl *ctrl, u8 csi,
 				struct nvme_effects_log **log)
 {
-	struct nvme_effects_log	*cel = xa_load(&ctrl->cels, csi);
+	struct nvme_effects_log *old, *cel = xa_load(&ctrl->cels, csi);
 	int ret;
 
 	if (cel)
@@ -3102,7 +3109,11 @@ static int nvme_get_effects_log(struct nvme_ctrl *ctrl, u8 csi,
 		return ret;
 	}
 
-	xa_store(&ctrl->cels, csi, cel, GFP_KERNEL);
+	old = xa_store(&ctrl->cels, csi, cel, GFP_KERNEL);
+	if (xa_is_err(old)) {
+		kfree(cel);
+		return xa_err(old);
+	}
 out:
 	*log = cel;
 	return 0;
@@ -3164,6 +3175,25 @@ free_data:
 	return ret;
 }
 
+static int nvme_init_effects_log(struct nvme_ctrl *ctrl,
+		u8 csi, struct nvme_effects_log **log)
+{
+	struct nvme_effects_log *effects, *old;
+
+	effects = kzalloc(sizeof(*effects), GFP_KERNEL);
+	if (!effects)
+		return -ENOMEM;
+
+	old = xa_store(&ctrl->cels, csi, effects, GFP_KERNEL);
+	if (xa_is_err(old)) {
+		kfree(effects);
+		return xa_err(old);
+	}
+
+	*log = effects;
+	return 0;
+}
+
 static void nvme_init_known_nvm_effects(struct nvme_ctrl *ctrl)
 {
 	struct nvme_effects_log	*log = ctrl->effects;
@@ -3210,10 +3240,9 @@ static int nvme_init_effects(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
 	}
 
 	if (!ctrl->effects) {
-		ctrl->effects = kzalloc(sizeof(*ctrl->effects), GFP_KERNEL);
-		if (!ctrl->effects)
-			return -ENOMEM;
-		xa_store(&ctrl->cels, NVME_CSI_NVM, ctrl->effects, GFP_KERNEL);
+		ret = nvme_init_effects_log(ctrl, NVME_CSI_NVM, &ctrl->effects);
+		if (ret < 0)
+			return ret;
 	}
 
 	nvme_init_known_nvm_effects(ctrl);
@@ -3829,7 +3858,7 @@ static void nvme_ns_add_to_ctrl_list(struct nvme_ns *ns)
 			return;
 		}
 	}
-	list_add(&ns->list, &ns->ctrl->namespaces);
+	list_add_rcu(&ns->list, &ns->ctrl->namespaces);
 }
 
 static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info)
@@ -4247,6 +4276,15 @@ static void nvme_scan_work(struct work_struct *work)
 			nvme_scan_ns_sequential(ctrl);
 	}
 	mutex_unlock(&ctrl->scan_lock);
+
+	/* Requeue if we have missed AENs */
+	if (test_bit(NVME_AER_NOTICE_NS_CHANGED, &ctrl->events))
+		nvme_queue_scan(ctrl);
+#ifdef CONFIG_NVME_MULTIPATH
+	else if (ctrl->ana_log_buf)
+		/* Re-read the ANA log page to not miss updates */
+		queue_work(nvme_wq, &ctrl->ana_work);
+#endif
 }
 
 /*
@@ -4438,7 +4476,8 @@ static void nvme_fw_act_work(struct work_struct *work)
 		msleep(100);
 	}
 
-	if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_LIVE))
+	if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_CONNECTING) ||
+	    !nvme_change_ctrl_state(ctrl, NVME_CTRL_LIVE))
 		return;
 
 	nvme_unquiesce_io_queues(ctrl);
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index b81af7919e94..7c13a400071e 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -786,49 +786,8 @@ nvme_fc_ctrl_connectivity_loss(struct nvme_fc_ctrl *ctrl)
 		"NVME-FC{%d}: controller connectivity lost. Awaiting "
 		"Reconnect", ctrl->cnum);
 
-	switch (nvme_ctrl_state(&ctrl->ctrl)) {
-	case NVME_CTRL_NEW:
-	case NVME_CTRL_LIVE:
-		/*
-		 * Schedule a controller reset. The reset will terminate the
-		 * association and schedule the reconnect timer.  Reconnects
-		 * will be attempted until either the ctlr_loss_tmo
-		 * (max_retries * connect_delay) expires or the remoteport's
-		 * dev_loss_tmo expires.
-		 */
-		if (nvme_reset_ctrl(&ctrl->ctrl)) {
-			dev_warn(ctrl->ctrl.device,
-				"NVME-FC{%d}: Couldn't schedule reset.\n",
-				ctrl->cnum);
-			nvme_delete_ctrl(&ctrl->ctrl);
-		}
-		break;
-
-	case NVME_CTRL_CONNECTING:
-		/*
-		 * The association has already been terminated and the
-		 * controller is attempting reconnects.  No need to do anything
-		 * futher.  Reconnects will be attempted until either the
-		 * ctlr_loss_tmo (max_retries * connect_delay) expires or the
-		 * remoteport's dev_loss_tmo expires.
-		 */
-		break;
-
-	case NVME_CTRL_RESETTING:
-		/*
-		 * Controller is already in the process of terminating the
-		 * association.  No need to do anything further. The reconnect
-		 * step will kick in naturally after the association is
-		 * terminated.
-		 */
-		break;
-
-	case NVME_CTRL_DELETING:
-	case NVME_CTRL_DELETING_NOIO:
-	default:
-		/* no action to take - let it delete */
-		break;
-	}
+	set_bit(ASSOC_FAILED, &ctrl->flags);
+	nvme_reset_ctrl(&ctrl->ctrl);
 }
 
 /**
@@ -2080,7 +2039,8 @@ done:
 		nvme_fc_complete_rq(rq);
 
 check_error:
-	if (terminate_assoc && ctrl->ctrl.state != NVME_CTRL_RESETTING)
+	if (terminate_assoc &&
+	    nvme_ctrl_state(&ctrl->ctrl) != NVME_CTRL_RESETTING)
 		queue_work(nvme_reset_wq, &ctrl->ioerr_work);
 }
 
@@ -2534,6 +2494,8 @@ __nvme_fc_abort_outstanding_ios(struct nvme_fc_ctrl *ctrl, bool start_queues)
 static void
 nvme_fc_error_recovery(struct nvme_fc_ctrl *ctrl, char *errmsg)
 {
+	enum nvme_ctrl_state state = nvme_ctrl_state(&ctrl->ctrl);
+
 	/*
 	 * if an error (io timeout, etc) while (re)connecting, the remote
 	 * port requested terminating of the association (disconnect_ls)
@@ -2541,9 +2503,8 @@ nvme_fc_error_recovery(struct nvme_fc_ctrl *ctrl, char *errmsg)
 	 * the controller.  Abort any ios on the association and let the
 	 * create_association error path resolve things.
 	 */
-	if (ctrl->ctrl.state == NVME_CTRL_CONNECTING) {
+	if (state == NVME_CTRL_CONNECTING) {
 		__nvme_fc_abort_outstanding_ios(ctrl, true);
-		set_bit(ASSOC_FAILED, &ctrl->flags);
 		dev_warn(ctrl->ctrl.device,
 			"NVME-FC{%d}: transport error during (re)connect\n",
 			ctrl->cnum);
@@ -2551,7 +2512,7 @@ nvme_fc_error_recovery(struct nvme_fc_ctrl *ctrl, char *errmsg)
 	}
 
 	/* Otherwise, only proceed if in LIVE state - e.g. on first error */
-	if (ctrl->ctrl.state != NVME_CTRL_LIVE)
+	if (state != NVME_CTRL_LIVE)
 		return;
 
 	dev_warn(ctrl->ctrl.device,
@@ -3062,7 +3023,6 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
 	struct nvmefc_ls_rcv_op *disls = NULL;
 	unsigned long flags;
 	int ret;
-	bool changed;
 
 	++ctrl->ctrl.nr_reconnects;
 
@@ -3173,12 +3133,13 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
 	if (ret)
 		goto out_term_aen_ops;
 
-	changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
+	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE)) {
+		ret = -EIO;
+		goto out_term_aen_ops;
+	}
 
 	ctrl->ctrl.nr_reconnects = 0;
-
-	if (changed)
-		nvme_start_ctrl(&ctrl->ctrl);
+	nvme_start_ctrl(&ctrl->ctrl);
 
 	return 0;	/* Success */
 
@@ -3579,8 +3540,7 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
 	list_add_tail(&ctrl->ctrl_list, &rport->ctrl_list);
 	spin_unlock_irqrestore(&rport->lock, flags);
 
-	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_RESETTING) ||
-	    !nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING)) {
+	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING)) {
 		dev_err(ctrl->ctrl.device,
 			"NVME-FC{%d}: failed to init ctrl state\n", ctrl->cnum);
 		goto fail_ctrl;
diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c
index a96976b22fa7..64ae8af01d9a 100644
--- a/drivers/nvme/host/ioctl.c
+++ b/drivers/nvme/host/ioctl.c
@@ -120,19 +120,31 @@ static int nvme_map_user_request(struct request *req, u64 ubuffer,
 	struct nvme_ns *ns = q->queuedata;
 	struct block_device *bdev = ns ? ns->disk->part0 : NULL;
 	bool supports_metadata = bdev && blk_get_integrity(bdev->bd_disk);
+	struct nvme_ctrl *ctrl = nvme_req(req)->ctrl;
 	bool has_metadata = meta_buffer && meta_len;
 	struct bio *bio = NULL;
 	int ret;
 
-	if (has_metadata && !supports_metadata)
-		return -EINVAL;
+	if (!nvme_ctrl_sgl_supported(ctrl))
+		dev_warn_once(ctrl->device, "using unchecked data buffer\n");
+	if (has_metadata) {
+		if (!supports_metadata) {
+			ret = -EINVAL;
+			goto out;
+		}
+		if (!nvme_ctrl_meta_sgl_supported(ctrl))
+			dev_warn_once(ctrl->device,
+				      "using unchecked metadata buffer\n");
+	}
 
 	if (ioucmd && (ioucmd->flags & IORING_URING_CMD_FIXED)) {
 		struct iov_iter iter;
 
 		/* fixedbufs is only for non-vectored io */
-		if (WARN_ON_ONCE(flags & NVME_IOCTL_VEC))
-			return -EINVAL;
+		if (flags & NVME_IOCTL_VEC) {
+			ret = -EINVAL;
+			goto out;
+		}
 		ret = io_uring_cmd_import_fixed(ubuffer, bufflen,
 				rq_data_dir(req), &iter, ioucmd);
 		if (ret < 0)
@@ -276,8 +288,7 @@ static bool nvme_validate_passthru_nsid(struct nvme_ctrl *ctrl,
 {
 	if (ns && nsid != ns->head->ns_id) {
 		dev_err(ctrl->device,
-			"%s: nsid (%u) in cmd does not match nsid (%u)"
-			"of namespace\n",
+			"%s: nsid (%u) in cmd does not match nsid (%u) of namespace\n",
 			current->comm, nsid, ns->head->ns_id);
 		return false;
 	}
@@ -431,21 +442,14 @@ static enum rq_end_io_ret nvme_uring_cmd_end_io(struct request *req,
 	pdu->result = le64_to_cpu(nvme_req(req)->result.u64);
 
 	/*
-	 * For iopoll, complete it directly. Note that using the uring_cmd
-	 * helper for this is safe only because we check blk_rq_is_poll().
-	 * As that returns false if we're NOT on a polled queue, then it's
-	 * safe to use the polled completion helper.
-	 *
-	 * Otherwise, move the completion to task work.
+	 * IOPOLL could potentially complete this request directly, but
+	 * if multiple rings are polling on the same queue, then it's possible
+	 * for one ring to find completions for another ring. Punting the
+	 * completion via task_work will always direct it to the right
+	 * location, rather than potentially complete requests for ringA
+	 * under iopoll invocations from ringB.
 	 */
-	if (blk_rq_is_poll(req)) {
-		if (pdu->bio)
-			blk_rq_unmap_user(pdu->bio);
-		io_uring_cmd_iopoll_done(ioucmd, pdu->result, pdu->status);
-	} else {
-		io_uring_cmd_do_in_task_lazy(ioucmd, nvme_uring_task_cb);
-	}
-
+	io_uring_cmd_do_in_task_lazy(ioucmd, nvme_uring_task_cb);
 	return RQ_END_IO_FREE;
 }
 
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index f25582e4d88b..561dd08022c0 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -427,7 +427,7 @@ static bool nvme_available_path(struct nvme_ns_head *head)
 	struct nvme_ns *ns;
 
 	if (!test_bit(NVME_NSHEAD_DISK_LIVE, &head->flags))
-		return NULL;
+		return false;
 
 	list_for_each_entry_srcu(ns, &head->list, siblings,
 				 srcu_read_lock_held(&head->srcu)) {
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 61bba5513de0..dcdce7d12e44 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -1130,6 +1130,13 @@ static inline bool nvme_ctrl_sgl_supported(struct nvme_ctrl *ctrl)
 	return ctrl->sgls & ((1 << 0) | (1 << 1));
 }
 
+static inline bool nvme_ctrl_meta_sgl_supported(struct nvme_ctrl *ctrl)
+{
+	if (ctrl->ops->flags & NVME_F_FABRICS)
+		return true;
+	return ctrl->sgls & NVME_CTRL_SGLS_MSDS;
+}
+
 #ifdef CONFIG_NVME_HOST_AUTH
 int __init nvme_init_auth(void);
 void __exit nvme_exit_auth(void);
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 76b3f7b396c8..2bddc9f60fec 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -43,6 +43,7 @@
  */
 #define NVME_MAX_KB_SZ	8192
 #define NVME_MAX_SEGS	128
+#define NVME_MAX_META_SEGS 15
 #define NVME_MAX_NR_ALLOCATIONS	5
 
 static int use_threaded_interrupts;
@@ -143,6 +144,7 @@ struct nvme_dev {
 	bool hmb;
 
 	mempool_t *iod_mempool;
+	mempool_t *iod_meta_mempool;
 
 	/* shadow doorbell buffer support: */
 	__le32 *dbbuf_dbs;
@@ -238,6 +240,8 @@ struct nvme_iod {
 	dma_addr_t first_dma;
 	dma_addr_t meta_dma;
 	struct sg_table sgt;
+	struct sg_table meta_sgt;
+	union nvme_descriptor meta_list;
 	union nvme_descriptor list[NVME_MAX_NR_ALLOCATIONS];
 };
 
@@ -386,7 +390,7 @@ static bool nvme_dbbuf_update_and_check_event(u16 value, __le32 *dbbuf_db,
  * as it only leads to a small amount of wasted memory for the lifetime of
  * the I/O.
  */
-static int nvme_pci_npages_prp(void)
+static __always_inline int nvme_pci_npages_prp(void)
 {
 	unsigned max_bytes = (NVME_MAX_KB_SZ * 1024) + NVME_CTRL_PAGE_SIZE;
 	unsigned nprps = DIV_ROUND_UP(max_bytes, NVME_CTRL_PAGE_SIZE);
@@ -505,6 +509,15 @@ static void nvme_commit_rqs(struct blk_mq_hw_ctx *hctx)
 	spin_unlock(&nvmeq->sq_lock);
 }
 
+static inline bool nvme_pci_metadata_use_sgls(struct nvme_dev *dev,
+					      struct request *req)
+{
+	if (!nvme_ctrl_meta_sgl_supported(&dev->ctrl))
+		return false;
+	return req->nr_integrity_segments > 1 ||
+		nvme_req(req)->flags & NVME_REQ_USERCMD;
+}
+
 static inline bool nvme_pci_use_sgls(struct nvme_dev *dev, struct request *req,
 				     int nseg)
 {
@@ -517,8 +530,10 @@ static inline bool nvme_pci_use_sgls(struct nvme_dev *dev, struct request *req,
 		return false;
 	if (!nvmeq->qid)
 		return false;
+	if (nvme_pci_metadata_use_sgls(dev, req))
+		return true;
 	if (!sgl_threshold || avg_seg_size < sgl_threshold)
-		return false;
+		return nvme_req(req)->flags & NVME_REQ_USERCMD;
 	return true;
 }
 
@@ -779,7 +794,8 @@ static blk_status_t nvme_map_data(struct nvme_dev *dev, struct request *req,
 		struct bio_vec bv = req_bvec(req);
 
 		if (!is_pci_p2pdma_page(bv.bv_page)) {
-			if ((bv.bv_offset & (NVME_CTRL_PAGE_SIZE - 1)) +
+			if (!nvme_pci_metadata_use_sgls(dev, req) &&
+			    (bv.bv_offset & (NVME_CTRL_PAGE_SIZE - 1)) +
 			     bv.bv_len <= NVME_CTRL_PAGE_SIZE * 2)
 				return nvme_setup_prp_simple(dev, req,
 							     &cmnd->rw, &bv);
@@ -823,11 +839,69 @@ out_free_sg:
 	return ret;
 }
 
-static blk_status_t nvme_map_metadata(struct nvme_dev *dev, struct request *req,
-		struct nvme_command *cmnd)
+static blk_status_t nvme_pci_setup_meta_sgls(struct nvme_dev *dev,
+					     struct request *req)
+{
+	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
+	struct nvme_rw_command *cmnd = &iod->cmd.rw;
+	struct nvme_sgl_desc *sg_list;
+	struct scatterlist *sgl, *sg;
+	unsigned int entries;
+	dma_addr_t sgl_dma;
+	int rc, i;
+
+	iod->meta_sgt.sgl = mempool_alloc(dev->iod_meta_mempool, GFP_ATOMIC);
+	if (!iod->meta_sgt.sgl)
+		return BLK_STS_RESOURCE;
+
+	sg_init_table(iod->meta_sgt.sgl, req->nr_integrity_segments);
+	iod->meta_sgt.orig_nents = blk_rq_map_integrity_sg(req,
+							   iod->meta_sgt.sgl);
+	if (!iod->meta_sgt.orig_nents)
+		goto out_free_sg;
+
+	rc = dma_map_sgtable(dev->dev, &iod->meta_sgt, rq_dma_dir(req),
+			     DMA_ATTR_NO_WARN);
+	if (rc)
+		goto out_free_sg;
+
+	sg_list = dma_pool_alloc(dev->prp_small_pool, GFP_ATOMIC, &sgl_dma);
+	if (!sg_list)
+		goto out_unmap_sg;
+
+	entries = iod->meta_sgt.nents;
+	iod->meta_list.sg_list = sg_list;
+	iod->meta_dma = sgl_dma;
+
+	cmnd->flags = NVME_CMD_SGL_METASEG;
+	cmnd->metadata = cpu_to_le64(sgl_dma);
+
+	sgl = iod->meta_sgt.sgl;
+	if (entries == 1) {
+		nvme_pci_sgl_set_data(sg_list, sgl);
+		return BLK_STS_OK;
+	}
+
+	sgl_dma += sizeof(*sg_list);
+	nvme_pci_sgl_set_seg(sg_list, sgl_dma, entries);
+	for_each_sg(sgl, sg, entries, i)
+		nvme_pci_sgl_set_data(&sg_list[i + 1], sg);
+
+	return BLK_STS_OK;
+
+out_unmap_sg:
+	dma_unmap_sgtable(dev->dev, &iod->meta_sgt, rq_dma_dir(req), 0);
+out_free_sg:
+	mempool_free(iod->meta_sgt.sgl, dev->iod_meta_mempool);
+	return BLK_STS_RESOURCE;
+}
+
+static blk_status_t nvme_pci_setup_meta_mptr(struct nvme_dev *dev,
+					     struct request *req)
 {
 	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
 	struct bio_vec bv = rq_integrity_vec(req);
+	struct nvme_command *cmnd = &iod->cmd;
 
 	iod->meta_dma = dma_map_bvec(dev->dev, &bv, rq_dma_dir(req), 0);
 	if (dma_mapping_error(dev->dev, iod->meta_dma))
@@ -836,6 +910,13 @@ static blk_status_t nvme_map_metadata(struct nvme_dev *dev, struct request *req,
 	return BLK_STS_OK;
 }
 
+static blk_status_t nvme_map_metadata(struct nvme_dev *dev, struct request *req)
+{
+	if (nvme_pci_metadata_use_sgls(dev, req))
+		return nvme_pci_setup_meta_sgls(dev, req);
+	return nvme_pci_setup_meta_mptr(dev, req);
+}
+
 static blk_status_t nvme_prep_rq(struct nvme_dev *dev, struct request *req)
 {
 	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
@@ -844,6 +925,7 @@ static blk_status_t nvme_prep_rq(struct nvme_dev *dev, struct request *req)
 	iod->aborted = false;
 	iod->nr_allocations = -1;
 	iod->sgt.nents = 0;
+	iod->meta_sgt.nents = 0;
 
 	ret = nvme_setup_cmd(req->q->queuedata, req);
 	if (ret)
@@ -856,7 +938,7 @@ static blk_status_t nvme_prep_rq(struct nvme_dev *dev, struct request *req)
 	}
 
 	if (blk_integrity_rq(req)) {
-		ret = nvme_map_metadata(dev, req, &iod->cmd);
+		ret = nvme_map_metadata(dev, req);
 		if (ret)
 			goto out_unmap_data;
 	}
@@ -903,7 +985,7 @@ static blk_status_t nvme_queue_rq(struct blk_mq_hw_ctx *hctx,
 	return BLK_STS_OK;
 }
 
-static void nvme_submit_cmds(struct nvme_queue *nvmeq, struct request **rqlist)
+static void nvme_submit_cmds(struct nvme_queue *nvmeq, struct rq_list *rqlist)
 {
 	struct request *req;
 
@@ -931,11 +1013,10 @@ static bool nvme_prep_rq_batch(struct nvme_queue *nvmeq, struct request *req)
 	return nvme_prep_rq(nvmeq->dev, req) == BLK_STS_OK;
 }
 
-static void nvme_queue_rqs(struct request **rqlist)
+static void nvme_queue_rqs(struct rq_list *rqlist)
 {
-	struct request *submit_list = NULL;
-	struct request *requeue_list = NULL;
-	struct request **requeue_lastp = &requeue_list;
+	struct rq_list submit_list = { };
+	struct rq_list requeue_list = { };
 	struct nvme_queue *nvmeq = NULL;
 	struct request *req;
 
@@ -945,9 +1026,9 @@ static void nvme_queue_rqs(struct request **rqlist)
 		nvmeq = req->mq_hctx->driver_data;
 
 		if (nvme_prep_rq_batch(nvmeq, req))
-			rq_list_add(&submit_list, req); /* reverse order */
+			rq_list_add_tail(&submit_list, req);
 		else
-			rq_list_add_tail(&requeue_lastp, req);
+			rq_list_add_tail(&requeue_list, req);
 	}
 
 	if (nvmeq)
@@ -955,17 +1036,31 @@ static void nvme_queue_rqs(struct request **rqlist)
 	*rqlist = requeue_list;
 }
 
+static __always_inline void nvme_unmap_metadata(struct nvme_dev *dev,
+						struct request *req)
+{
+	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
+
+	if (!iod->meta_sgt.nents) {
+		dma_unmap_page(dev->dev, iod->meta_dma,
+			       rq_integrity_vec(req).bv_len,
+			       rq_dma_dir(req));
+		return;
+	}
+
+	dma_pool_free(dev->prp_small_pool, iod->meta_list.sg_list,
+		      iod->meta_dma);
+	dma_unmap_sgtable(dev->dev, &iod->meta_sgt, rq_dma_dir(req), 0);
+	mempool_free(iod->meta_sgt.sgl, dev->iod_meta_mempool);
+}
+
 static __always_inline void nvme_pci_unmap_rq(struct request *req)
 {
 	struct nvme_queue *nvmeq = req->mq_hctx->driver_data;
 	struct nvme_dev *dev = nvmeq->dev;
 
-	if (blk_integrity_rq(req)) {
-	        struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
-
-		dma_unmap_page(dev->dev, iod->meta_dma,
-			       rq_integrity_vec(req).bv_len, rq_dma_dir(req));
-	}
+	if (blk_integrity_rq(req))
+		nvme_unmap_metadata(dev, req);
 
 	if (blk_rq_nr_phys_segments(req))
 		nvme_unmap_data(dev, req);
@@ -1035,8 +1130,9 @@ static inline void nvme_handle_cqe(struct nvme_queue *nvmeq,
 
 	trace_nvme_sq(req, cqe->sq_head, nvmeq->sq_tail);
 	if (!nvme_try_complete_req(req, cqe->status, cqe->result) &&
-	    !blk_mq_add_to_batch(req, iob, nvme_req(req)->status,
-					nvme_pci_complete_batch))
+	    !blk_mq_add_to_batch(req, iob,
+				 nvme_req(req)->status != NVME_SC_SUCCESS,
+				 nvme_pci_complete_batch))
 		nvme_pci_complete_rq(req);
 }
 
@@ -1079,7 +1175,7 @@ static irqreturn_t nvme_irq(int irq, void *data)
 	DEFINE_IO_COMP_BATCH(iob);
 
 	if (nvme_poll_cq(nvmeq, &iob)) {
-		if (!rq_list_empty(iob.req_list))
+		if (!rq_list_empty(&iob.req_list))
 			nvme_pci_complete_batch(&iob);
 		return IRQ_HANDLED;
 	}
@@ -1106,7 +1202,9 @@ static void nvme_poll_irqdisable(struct nvme_queue *nvmeq)
 	WARN_ON_ONCE(test_bit(NVMEQ_POLLED, &nvmeq->flags));
 
 	disable_irq(pci_irq_vector(pdev, nvmeq->cq_vector));
+	spin_lock(&nvmeq->cq_poll_lock);
 	nvme_poll_cq(nvmeq, NULL);
+	spin_unlock(&nvmeq->cq_poll_lock);
 	enable_irq(pci_irq_vector(pdev, nvmeq->cq_vector));
 }
 
@@ -1316,9 +1414,20 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req)
 	struct nvme_dev *dev = nvmeq->dev;
 	struct request *abort_req;
 	struct nvme_command cmd = { };
+	struct pci_dev *pdev = to_pci_dev(dev->dev);
 	u32 csts = readl(dev->bar + NVME_REG_CSTS);
 	u8 opcode;
 
+	/*
+	 * Shutdown the device immediately if we see it is disconnected. This
+	 * unblocks PCIe error handling if the nvme driver is waiting in
+	 * error_resume for a device that has been removed. We can't unbind the
+	 * driver while the driver's error callback is waiting to complete, so
+	 * we're relying on a timeout to break that deadlock if a removal
+	 * occurs while reset work is running.
+	 */
+	if (pci_dev_is_disconnected(pdev))
+		nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_DELETING);
 	if (nvme_state_terminal(&dev->ctrl))
 		goto disable;
 
@@ -1326,7 +1435,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req)
 	 * the recovery mechanism will surely fail.
 	 */
 	mb();
-	if (pci_channel_offline(to_pci_dev(dev->dev)))
+	if (pci_channel_offline(pdev))
 		return BLK_EH_RESET_TIMER;
 
 	/*
@@ -1779,8 +1888,28 @@ static int nvme_pci_configure_admin_queue(struct nvme_dev *dev)
 	 * might be pointing at!
 	 */
 	result = nvme_disable_ctrl(&dev->ctrl, false);
-	if (result < 0)
-		return result;
+	if (result < 0) {
+		struct pci_dev *pdev = to_pci_dev(dev->dev);
+
+		/*
+		 * The NVMe Controller Reset method did not get an expected
+		 * CSTS.RDY transition, so something with the device appears to
+		 * be stuck. Use the lower level and bigger hammer PCIe
+		 * Function Level Reset to attempt restoring the device to its
+		 * initial state, and try again.
+		 */
+		result = pcie_reset_flr(pdev, false);
+		if (result < 0)
+			return result;
+
+		pci_restore_state(pdev);
+		result = nvme_disable_ctrl(&dev->ctrl, false);
+		if (result < 0)
+			return result;
+
+		dev_info(dev->ctrl.device,
+			"controller reset completed after pcie flr\n");
+	}
 
 	result = nvme_alloc_queue(dev, 0, NVME_AQ_DEPTH);
 	if (result)
@@ -1888,6 +2017,18 @@ static void nvme_map_cmb(struct nvme_dev *dev)
 		return;
 
 	/*
+	 * Controllers may support a CMB size larger than their BAR, for
+	 * example, due to being behind a bridge. Reduce the CMB to the
+	 * reported size of the BAR
+	 */
+	size = min(size, bar_size - offset);
+
+	if (!IS_ALIGNED(size, memremap_compat_align()) ||
+	    !IS_ALIGNED(pci_resource_start(pdev, bar),
+			memremap_compat_align()))
+		return;
+
+	/*
 	 * Tell the controller about the host side address mapping the CMB,
 	 * and enable CMB decoding for the NVMe 1.4+ scheme:
 	 */
@@ -1897,17 +2038,10 @@ static void nvme_map_cmb(struct nvme_dev *dev)
 			     dev->bar + NVME_REG_CMBMSC);
 	}
 
-	/*
-	 * Controllers may support a CMB size larger than their BAR,
-	 * for example, due to being behind a bridge. Reduce the CMB to
-	 * the reported size of the BAR
-	 */
-	if (size > bar_size - offset)
-		size = bar_size - offset;
-
 	if (pci_p2pdma_add_resource(pdev, bar, size, offset)) {
 		dev_warn(dev->ctrl.device,
 			 "failed to register the CMB\n");
+		hi_lo_writeq(0, dev->bar + NVME_REG_CMBMSC);
 		return;
 	}
 
@@ -2719,6 +2853,7 @@ static void nvme_release_prp_pools(struct nvme_dev *dev)
 
 static int nvme_pci_alloc_iod_mempool(struct nvme_dev *dev)
 {
+	size_t meta_size = sizeof(struct scatterlist) * (NVME_MAX_META_SEGS + 1);
 	size_t alloc_size = sizeof(struct scatterlist) * NVME_MAX_SEGS;
 
 	dev->iod_mempool = mempool_create_node(1,
@@ -2727,7 +2862,18 @@ static int nvme_pci_alloc_iod_mempool(struct nvme_dev *dev)
 			dev_to_node(dev->dev));
 	if (!dev->iod_mempool)
 		return -ENOMEM;
+
+	dev->iod_meta_mempool = mempool_create_node(1,
+			mempool_kmalloc, mempool_kfree,
+			(void *)meta_size, GFP_KERNEL,
+			dev_to_node(dev->dev));
+	if (!dev->iod_meta_mempool)
+		goto free;
+
 	return 0;
+free:
+	mempool_destroy(dev->iod_mempool);
+	return -ENOMEM;
 }
 
 static void nvme_free_tagset(struct nvme_dev *dev)
@@ -2792,6 +2938,11 @@ static void nvme_reset_work(struct work_struct *work)
 	if (result)
 		goto out;
 
+	if (nvme_ctrl_meta_sgl_supported(&dev->ctrl))
+		dev->ctrl.max_integrity_segments = NVME_MAX_META_SEGS;
+	else
+		dev->ctrl.max_integrity_segments = 1;
+
 	nvme_dbbuf_dma_alloc(dev);
 
 	result = nvme_setup_host_mem(dev);
@@ -2987,7 +3138,9 @@ static unsigned long check_vendor_combination_bug(struct pci_dev *pdev)
 		 * because of high power consumption (> 2 Watt) in s2idle
 		 * sleep. Only some boards with Intel CPU are affected.
 		 */
-		if (dmi_match(DMI_BOARD_NAME, "GMxPXxx") ||
+		if (dmi_match(DMI_BOARD_NAME, "DN50Z-140HC-YD") ||
+		    dmi_match(DMI_BOARD_NAME, "GMxPXxx") ||
+		    dmi_match(DMI_BOARD_NAME, "GXxMRXx") ||
 		    dmi_match(DMI_BOARD_NAME, "PH4PG31") ||
 		    dmi_match(DMI_BOARD_NAME, "PH4PRX1_PH6PRX1") ||
 		    dmi_match(DMI_BOARD_NAME, "PH6PG01_PH6PG71"))
@@ -3059,11 +3212,6 @@ static struct nvme_dev *nvme_pci_alloc_dev(struct pci_dev *pdev,
 	dev->ctrl.max_hw_sectors = min_t(u32,
 		NVME_MAX_KB_SZ << 1, dma_opt_mapping_size(&pdev->dev) >> 9);
 	dev->ctrl.max_segments = NVME_MAX_SEGS;
-
-	/*
-	 * There is no support for SGLs for metadata (yet), so we are limited to
-	 * a single integrity segment for the separate metadata pointer.
-	 */
 	dev->ctrl.max_integrity_segments = 1;
 	return dev;
 
@@ -3126,6 +3274,11 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (result)
 		goto out_disable;
 
+	if (nvme_ctrl_meta_sgl_supported(&dev->ctrl))
+		dev->ctrl.max_integrity_segments = NVME_MAX_META_SEGS;
+	else
+		dev->ctrl.max_integrity_segments = 1;
+
 	nvme_dbbuf_dma_alloc(dev);
 
 	result = nvme_setup_host_mem(dev);
@@ -3168,6 +3321,7 @@ out_disable:
 	nvme_free_queues(dev, 0);
 out_release_iod_mempool:
 	mempool_destroy(dev->iod_mempool);
+	mempool_destroy(dev->iod_meta_mempool);
 out_release_prp_pools:
 	nvme_release_prp_pools(dev);
 out_dev_unmap:
@@ -3233,6 +3387,7 @@ static void nvme_remove(struct pci_dev *pdev)
 	nvme_dbbuf_dma_free(dev);
 	nvme_free_queues(dev, 0);
 	mempool_destroy(dev->iod_mempool);
+	mempool_destroy(dev->iod_meta_mempool);
 	nvme_release_prp_pools(dev);
 	nvme_dev_unmap(dev);
 	nvme_uninit_ctrl(&dev->ctrl);
@@ -3402,7 +3557,7 @@ static pci_ers_result_t nvme_slot_reset(struct pci_dev *pdev)
 
 	dev_info(dev->ctrl.device, "restart after slot reset\n");
 	pci_restore_state(pdev);
-	if (!nvme_try_sched_reset(&dev->ctrl))
+	if (nvme_try_sched_reset(&dev->ctrl))
 		nvme_unquiesce_io_queues(&dev->ctrl);
 	return PCI_ERS_RESULT_RECOVERED;
 }
@@ -3452,6 +3607,9 @@ static const struct pci_device_id nvme_id_table[] = {
 		.driver_data = NVME_QUIRK_BOGUS_NID, },
 	{ PCI_DEVICE(0x1217, 0x8760), /* O2 Micro 64GB Steam Deck */
 		.driver_data = NVME_QUIRK_DMAPOOL_ALIGN_512, },
+	{ PCI_DEVICE(0x126f, 0x1001),	/* Silicon Motion generic */
+		.driver_data = NVME_QUIRK_NO_DEEPEST_PS |
+				NVME_QUIRK_IGNORE_DEV_SUBNQN, },
 	{ PCI_DEVICE(0x126f, 0x2262),	/* Silicon Motion generic */
 		.driver_data = NVME_QUIRK_NO_DEEPEST_PS |
 				NVME_QUIRK_BOGUS_NID, },
@@ -3475,6 +3633,9 @@ static const struct pci_device_id nvme_id_table[] = {
 				NVME_QUIRK_IGNORE_DEV_SUBNQN, },
 	{ PCI_DEVICE(0x15b7, 0x5008),   /* Sandisk SN530 */
 		.driver_data = NVME_QUIRK_BROKEN_MSI },
+	{ PCI_DEVICE(0x15b7, 0x5009),   /* Sandisk SN550 */
+		.driver_data = NVME_QUIRK_BROKEN_MSI |
+				NVME_QUIRK_NO_DEEPEST_PS },
 	{ PCI_DEVICE(0x1987, 0x5012),	/* Phison E12 */
 		.driver_data = NVME_QUIRK_BOGUS_NID, },
 	{ PCI_DEVICE(0x1987, 0x5016),	/* Phison E16 */
@@ -3552,12 +3713,16 @@ static const struct pci_device_id nvme_id_table[] = {
 		.driver_data = NVME_QUIRK_BOGUS_NID, },
 	{ PCI_DEVICE(0x1cc1, 0x5350),   /* ADATA XPG GAMMIX S50 */
 		.driver_data = NVME_QUIRK_BOGUS_NID, },
+	{ PCI_DEVICE(0x1dbe, 0x5216),   /* Acer/INNOGRIT FA100/5216 NVMe SSD */
+		.driver_data = NVME_QUIRK_BOGUS_NID, },
 	{ PCI_DEVICE(0x1dbe, 0x5236),   /* ADATA XPG GAMMIX S70 */
 		.driver_data = NVME_QUIRK_BOGUS_NID, },
 	{ PCI_DEVICE(0x1e49, 0x0021),   /* ZHITAI TiPro5000 NVMe SSD */
 		.driver_data = NVME_QUIRK_NO_DEEPEST_PS, },
 	{ PCI_DEVICE(0x1e49, 0x0041),   /* ZHITAI TiPro7000 NVMe SSD */
 		.driver_data = NVME_QUIRK_NO_DEEPEST_PS, },
+	{ PCI_DEVICE(0x025e, 0xf1ac),   /* SOLIDIGM  P44 pro SSDPFKKW020X7  */
+		.driver_data = NVME_QUIRK_NO_DEEPEST_PS, },
 	{ PCI_DEVICE(0xc0a9, 0x540a),   /* Crucial P2 */
 		.driver_data = NVME_QUIRK_BOGUS_NID, },
 	{ PCI_DEVICE(0x1d97, 0x2263), /* Lexar NM610 */
diff --git a/drivers/nvme/host/pr.c b/drivers/nvme/host/pr.c
index dc7922f22600..80dd09aa01a3 100644
--- a/drivers/nvme/host/pr.c
+++ b/drivers/nvme/host/pr.c
@@ -82,8 +82,6 @@ static int nvme_status_to_pr_err(int status)
 		return PR_STS_SUCCESS;
 	case NVME_SC_RESERVATION_CONFLICT:
 		return PR_STS_RESERVATION_CONFLICT;
-	case NVME_SC_ONCS_NOT_SUPPORTED:
-		return -EOPNOTSUPP;
 	case NVME_SC_BAD_ATTRIBUTES:
 	case NVME_SC_INVALID_OPCODE:
 	case NVME_SC_INVALID_FIELD:
diff --git a/drivers/nvme/host/sysfs.c b/drivers/nvme/host/sysfs.c
index b68a9e5f1ea3..3a41b9ab0f13 100644
--- a/drivers/nvme/host/sysfs.c
+++ b/drivers/nvme/host/sysfs.c
@@ -792,7 +792,7 @@ static umode_t nvme_tls_attrs_are_visible(struct kobject *kobj,
 	return a->mode;
 }
 
-const struct attribute_group nvme_tls_attrs_group = {
+static const struct attribute_group nvme_tls_attrs_group = {
 	.attrs		= nvme_tls_attrs,
 	.is_visible	= nvme_tls_attrs_are_visible,
 };
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 55abfe5e1d25..83a6b18b01ad 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -54,6 +54,8 @@ MODULE_PARM_DESC(tls_handshake_timeout,
 		 "nvme TLS handshake timeout in seconds (default 10)");
 #endif
 
+static atomic_t nvme_tcp_cpu_queues[NR_CPUS];
+
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 /* lockdep can detect a circular dependency of the form
  *   sk_lock -> mmap_lock (page fault) -> fs locks -> sk_lock
@@ -127,6 +129,7 @@ enum nvme_tcp_queue_flags {
 	NVME_TCP_Q_ALLOCATED	= 0,
 	NVME_TCP_Q_LIVE		= 1,
 	NVME_TCP_Q_POLLING	= 2,
+	NVME_TCP_Q_IO_CPU_SET	= 3,
 };
 
 enum nvme_tcp_recv_state {
@@ -214,6 +217,19 @@ static inline int nvme_tcp_queue_id(struct nvme_tcp_queue *queue)
 	return queue - queue->ctrl->queues;
 }
 
+static inline bool nvme_tcp_recv_pdu_supported(enum nvme_tcp_pdu_type type)
+{
+	switch (type) {
+	case nvme_tcp_c2h_term:
+	case nvme_tcp_c2h_data:
+	case nvme_tcp_r2t:
+	case nvme_tcp_rsp:
+		return true;
+	default:
+		return false;
+	}
+}
+
 /*
  * Check if the queue is TLS encrypted
  */
@@ -437,7 +453,8 @@ nvme_tcp_fetch_request(struct nvme_tcp_queue *queue)
 			return NULL;
 	}
 
-	list_del(&req->entry);
+	list_del_init(&req->entry);
+	init_llist_node(&req->lentry);
 	return req;
 }
 
@@ -545,6 +562,8 @@ static int nvme_tcp_init_request(struct blk_mq_tag_set *set,
 	req->queue = queue;
 	nvme_req(rq)->ctrl = &ctrl->ctrl;
 	nvme_req(rq)->cmd = &pdu->cmd;
+	init_llist_node(&req->lentry);
+	INIT_LIST_HEAD(&req->entry);
 
 	return 0;
 }
@@ -749,6 +768,14 @@ static int nvme_tcp_handle_r2t(struct nvme_tcp_queue *queue,
 		return -EPROTO;
 	}
 
+	if (llist_on_list(&req->lentry) ||
+	    !list_empty(&req->entry)) {
+		dev_err(queue->ctrl->ctrl.device,
+			"req %d unexpected r2t while processing request\n",
+			rq->tag);
+		return -EPROTO;
+	}
+
 	req->pdu_len = 0;
 	req->h2cdata_left = r2t_length;
 	req->h2cdata_offset = r2t_offset;
@@ -760,6 +787,40 @@ static int nvme_tcp_handle_r2t(struct nvme_tcp_queue *queue,
 	return 0;
 }
 
+static void nvme_tcp_handle_c2h_term(struct nvme_tcp_queue *queue,
+		struct nvme_tcp_term_pdu *pdu)
+{
+	u16 fes;
+	const char *msg;
+	u32 plen = le32_to_cpu(pdu->hdr.plen);
+
+	static const char * const msg_table[] = {
+		[NVME_TCP_FES_INVALID_PDU_HDR] = "Invalid PDU Header Field",
+		[NVME_TCP_FES_PDU_SEQ_ERR] = "PDU Sequence Error",
+		[NVME_TCP_FES_HDR_DIGEST_ERR] = "Header Digest Error",
+		[NVME_TCP_FES_DATA_OUT_OF_RANGE] = "Data Transfer Out Of Range",
+		[NVME_TCP_FES_DATA_LIMIT_EXCEEDED] = "Data Transfer Limit Exceeded",
+		[NVME_TCP_FES_UNSUPPORTED_PARAM] = "Unsupported Parameter",
+	};
+
+	if (plen < NVME_TCP_MIN_C2HTERM_PLEN ||
+	    plen > NVME_TCP_MAX_C2HTERM_PLEN) {
+		dev_err(queue->ctrl->ctrl.device,
+			"Received a malformed C2HTermReq PDU (plen = %u)\n",
+			plen);
+		return;
+	}
+
+	fes = le16_to_cpu(pdu->fes);
+	if (fes && fes < ARRAY_SIZE(msg_table))
+		msg = msg_table[fes];
+	else
+		msg = "Unknown";
+
+	dev_err(queue->ctrl->ctrl.device,
+		"Received C2HTermReq (FES = %s)\n", msg);
+}
+
 static int nvme_tcp_recv_pdu(struct nvme_tcp_queue *queue, struct sk_buff *skb,
 		unsigned int *offset, size_t *len)
 {
@@ -781,6 +842,25 @@ static int nvme_tcp_recv_pdu(struct nvme_tcp_queue *queue, struct sk_buff *skb,
 		return 0;
 
 	hdr = queue->pdu;
+	if (unlikely(hdr->hlen != sizeof(struct nvme_tcp_rsp_pdu))) {
+		if (!nvme_tcp_recv_pdu_supported(hdr->type))
+			goto unsupported_pdu;
+
+		dev_err(queue->ctrl->ctrl.device,
+			"pdu type %d has unexpected header length (%d)\n",
+			hdr->type, hdr->hlen);
+		return -EPROTO;
+	}
+
+	if (unlikely(hdr->type == nvme_tcp_c2h_term)) {
+		/*
+		 * C2HTermReq never includes Header or Data digests.
+		 * Skip the checks.
+		 */
+		nvme_tcp_handle_c2h_term(queue, (void *)queue->pdu);
+		return -EINVAL;
+	}
+
 	if (queue->hdr_digest) {
 		ret = nvme_tcp_verify_hdgst(queue, queue->pdu, hdr->hlen);
 		if (unlikely(ret))
@@ -804,10 +884,13 @@ static int nvme_tcp_recv_pdu(struct nvme_tcp_queue *queue, struct sk_buff *skb,
 		nvme_tcp_init_recv_ctx(queue);
 		return nvme_tcp_handle_r2t(queue, (void *)queue->pdu);
 	default:
-		dev_err(queue->ctrl->ctrl.device,
-			"unsupported pdu type (%d)\n", hdr->type);
-		return -EINVAL;
+		goto unsupported_pdu;
 	}
+
+unsupported_pdu:
+	dev_err(queue->ctrl->ctrl.device,
+		"unsupported pdu type (%d)\n", hdr->type);
+	return -EINVAL;
 }
 
 static inline void nvme_tcp_end_request(struct request *rq, u16 status)
@@ -1277,7 +1360,7 @@ static int nvme_tcp_try_recv(struct nvme_tcp_queue *queue)
 	queue->nr_cqe = 0;
 	consumed = sock->ops->read_sock(sk, &rd_desc, nvme_tcp_recv_skb);
 	release_sock(sk);
-	return consumed;
+	return consumed == -EAGAIN ? 0 : consumed;
 }
 
 static void nvme_tcp_io_work(struct work_struct *w)
@@ -1305,6 +1388,11 @@ static void nvme_tcp_io_work(struct work_struct *w)
 		else if (unlikely(result < 0))
 			return;
 
+		/* did we get some space after spending time in recv? */
+		if (nvme_tcp_queue_has_pending(queue) &&
+		    sk_stream_is_writeable(queue->sock->sk))
+			pending = true;
+
 		if (!pending || !queue->rd_enabled)
 			return;
 
@@ -1446,8 +1534,11 @@ static int nvme_tcp_init_connection(struct nvme_tcp_queue *queue)
 		msg.msg_control = cbuf;
 		msg.msg_controllen = sizeof(cbuf);
 	}
+	msg.msg_flags = MSG_WAITALL;
 	ret = kernel_recvmsg(queue->sock, &msg, &iov, 1,
 			iov.iov_len, msg.msg_flags);
+	if (ret >= 0 && ret < sizeof(*icresp))
+		ret = -ECONNRESET;
 	if (ret < 0) {
 		pr_warn("queue %d: failed to receive icresp, error %d\n",
 			nvme_tcp_queue_id(queue), ret);
@@ -1562,23 +1653,56 @@ static bool nvme_tcp_poll_queue(struct nvme_tcp_queue *queue)
 			  ctrl->io_queues[HCTX_TYPE_POLL];
 }
 
+/*
+ * Track the number of queues assigned to each cpu using a global per-cpu
+ * counter and select the least used cpu from the mq_map. Our goal is to spread
+ * different controllers I/O threads across different cpu cores.
+ *
+ * Note that the accounting is not 100% perfect, but we don't need to be, we're
+ * simply putting our best effort to select the best candidate cpu core that we
+ * find at any given point.
+ */
 static void nvme_tcp_set_queue_io_cpu(struct nvme_tcp_queue *queue)
 {
 	struct nvme_tcp_ctrl *ctrl = queue->ctrl;
-	int qid = nvme_tcp_queue_id(queue);
-	int n = 0;
+	struct blk_mq_tag_set *set = &ctrl->tag_set;
+	int qid = nvme_tcp_queue_id(queue) - 1;
+	unsigned int *mq_map = NULL;
+	int cpu, min_queues = INT_MAX, io_cpu;
+
+	if (wq_unbound)
+		goto out;
 
 	if (nvme_tcp_default_queue(queue))
-		n = qid - 1;
+		mq_map = set->map[HCTX_TYPE_DEFAULT].mq_map;
 	else if (nvme_tcp_read_queue(queue))
-		n = qid - ctrl->io_queues[HCTX_TYPE_DEFAULT] - 1;
+		mq_map = set->map[HCTX_TYPE_READ].mq_map;
 	else if (nvme_tcp_poll_queue(queue))
-		n = qid - ctrl->io_queues[HCTX_TYPE_DEFAULT] -
-				ctrl->io_queues[HCTX_TYPE_READ] - 1;
-	if (wq_unbound)
-		queue->io_cpu = WORK_CPU_UNBOUND;
-	else
-		queue->io_cpu = cpumask_next_wrap(n - 1, cpu_online_mask, -1, false);
+		mq_map = set->map[HCTX_TYPE_POLL].mq_map;
+
+	if (WARN_ON(!mq_map))
+		goto out;
+
+	/* Search for the least used cpu from the mq_map */
+	io_cpu = WORK_CPU_UNBOUND;
+	for_each_online_cpu(cpu) {
+		int num_queues = atomic_read(&nvme_tcp_cpu_queues[cpu]);
+
+		if (mq_map[cpu] != qid)
+			continue;
+		if (num_queues < min_queues) {
+			io_cpu = cpu;
+			min_queues = num_queues;
+		}
+	}
+	if (io_cpu != WORK_CPU_UNBOUND) {
+		queue->io_cpu = io_cpu;
+		atomic_inc(&nvme_tcp_cpu_queues[io_cpu]);
+		set_bit(NVME_TCP_Q_IO_CPU_SET, &queue->flags);
+	}
+out:
+	dev_dbg(ctrl->ctrl.device, "queue %d: using cpu %d\n",
+		qid, queue->io_cpu);
 }
 
 static void nvme_tcp_tls_done(void *data, int status, key_serial_t pskid)
@@ -1653,9 +1777,14 @@ static int nvme_tcp_start_tls(struct nvme_ctrl *nctrl,
 			qid, ret);
 		tls_handshake_cancel(queue->sock->sk);
 	} else {
-		dev_dbg(nctrl->device,
-			"queue %d: TLS handshake complete, error %d\n",
-			qid, queue->tls_err);
+		if (queue->tls_err) {
+			dev_err(nctrl->device,
+				"queue %d: TLS handshake complete, error %d\n",
+				qid, queue->tls_err);
+		} else {
+			dev_dbg(nctrl->device,
+				"queue %d: TLS handshake complete\n", qid);
+		}
 		ret = queue->tls_err;
 	}
 	return ret;
@@ -1722,7 +1851,7 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, int qid,
 
 	queue->sock->sk->sk_allocation = GFP_ATOMIC;
 	queue->sock->sk->sk_use_task_frag = false;
-	nvme_tcp_set_queue_io_cpu(queue);
+	queue->io_cpu = WORK_CPU_UNBOUND;
 	queue->request = NULL;
 	queue->data_remaining = 0;
 	queue->ddgst_remaining = 0;
@@ -1836,7 +1965,7 @@ static void __nvme_tcp_stop_queue(struct nvme_tcp_queue *queue)
 	cancel_work_sync(&queue->io_work);
 }
 
-static void nvme_tcp_stop_queue(struct nvme_ctrl *nctrl, int qid)
+static void nvme_tcp_stop_queue_nowait(struct nvme_ctrl *nctrl, int qid)
 {
 	struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl);
 	struct nvme_tcp_queue *queue = &ctrl->queues[qid];
@@ -1844,6 +1973,9 @@ static void nvme_tcp_stop_queue(struct nvme_ctrl *nctrl, int qid)
 	if (!test_bit(NVME_TCP_Q_ALLOCATED, &queue->flags))
 		return;
 
+	if (test_and_clear_bit(NVME_TCP_Q_IO_CPU_SET, &queue->flags))
+		atomic_dec(&nvme_tcp_cpu_queues[queue->io_cpu]);
+
 	mutex_lock(&queue->queue_lock);
 	if (test_and_clear_bit(NVME_TCP_Q_LIVE, &queue->flags))
 		__nvme_tcp_stop_queue(queue);
@@ -1852,6 +1984,31 @@ static void nvme_tcp_stop_queue(struct nvme_ctrl *nctrl, int qid)
 	mutex_unlock(&queue->queue_lock);
 }
 
+static void nvme_tcp_wait_queue(struct nvme_ctrl *nctrl, int qid)
+{
+	struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl);
+	struct nvme_tcp_queue *queue = &ctrl->queues[qid];
+	int timeout = 100;
+
+	while (timeout > 0) {
+		if (!test_bit(NVME_TCP_Q_ALLOCATED, &queue->flags) ||
+		    !sk_wmem_alloc_get(queue->sock->sk))
+			return;
+		msleep(2);
+		timeout -= 2;
+	}
+	dev_warn(nctrl->device,
+		 "qid %d: timeout draining sock wmem allocation expired\n",
+		 qid);
+}
+
+static void nvme_tcp_stop_queue(struct nvme_ctrl *nctrl, int qid)
+{
+	nvme_tcp_stop_queue_nowait(nctrl, qid);
+	nvme_tcp_wait_queue(nctrl, qid);
+}
+
+
 static void nvme_tcp_setup_sock_ops(struct nvme_tcp_queue *queue)
 {
 	write_lock_bh(&queue->sock->sk->sk_callback_lock);
@@ -1878,9 +2035,10 @@ static int nvme_tcp_start_queue(struct nvme_ctrl *nctrl, int idx)
 	nvme_tcp_init_recv_ctx(queue);
 	nvme_tcp_setup_sock_ops(queue);
 
-	if (idx)
+	if (idx) {
+		nvme_tcp_set_queue_io_cpu(queue);
 		ret = nvmf_connect_io_queue(nctrl, idx);
-	else
+	} else
 		ret = nvmf_connect_admin_queue(nctrl);
 
 	if (!ret) {
@@ -1918,7 +2076,9 @@ static void nvme_tcp_stop_io_queues(struct nvme_ctrl *ctrl)
 	int i;
 
 	for (i = 1; i < ctrl->queue_count; i++)
-		nvme_tcp_stop_queue(ctrl, i);
+		nvme_tcp_stop_queue_nowait(ctrl, i);
+	for (i = 1; i < ctrl->queue_count; i++)
+		nvme_tcp_wait_queue(ctrl, i);
 }
 
 static int nvme_tcp_start_io_queues(struct nvme_ctrl *ctrl,
@@ -2455,6 +2615,8 @@ static void nvme_tcp_submit_async_event(struct nvme_ctrl *arg)
 	ctrl->async_req.offset = 0;
 	ctrl->async_req.curr_bio = NULL;
 	ctrl->async_req.data_len = 0;
+	init_llist_node(&ctrl->async_req.lentry);
+	INIT_LIST_HEAD(&ctrl->async_req.entry);
 
 	nvme_tcp_queue_request(&ctrl->async_req, true, true);
 }
@@ -2624,6 +2786,7 @@ static int nvme_tcp_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob)
 {
 	struct nvme_tcp_queue *queue = hctx->driver_data;
 	struct sock *sk = queue->sock->sk;
+	int ret;
 
 	if (!test_bit(NVME_TCP_Q_LIVE, &queue->flags))
 		return 0;
@@ -2631,9 +2794,9 @@ static int nvme_tcp_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob)
 	set_bit(NVME_TCP_Q_POLLING, &queue->flags);
 	if (sk_can_busy_loop(sk) && skb_queue_empty_lockless(&sk->sk_receive_queue))
 		sk_busy_loop(sk, true);
-	nvme_tcp_try_recv(queue);
+	ret = nvme_tcp_try_recv(queue);
 	clear_bit(NVME_TCP_Q_POLLING, &queue->flags);
-	return queue->nr_cqe;
+	return ret < 0 ? ret : queue->nr_cqe;
 }
 
 static int nvme_tcp_get_address(struct nvme_ctrl *ctrl, char *buf, int size)
@@ -2856,6 +3019,7 @@ static struct nvmf_transport_ops nvme_tcp_transport = {
 static int __init nvme_tcp_init_module(void)
 {
 	unsigned int wq_flags = WQ_MEM_RECLAIM | WQ_HIGHPRI | WQ_SYSFS;
+	int cpu;
 
 	BUILD_BUG_ON(sizeof(struct nvme_tcp_hdr) != 8);
 	BUILD_BUG_ON(sizeof(struct nvme_tcp_cmd_pdu) != 72);
@@ -2873,6 +3037,9 @@ static int __init nvme_tcp_init_module(void)
 	if (!nvme_tcp_wq)
 		return -ENOMEM;
 
+	for_each_possible_cpu(cpu)
+		atomic_set(&nvme_tcp_cpu_queues[cpu], 0);
+
 	nvmf_register_transport(&nvme_tcp_transport);
 	return 0;
 }
diff --git a/drivers/nvme/target/Kconfig b/drivers/nvme/target/Kconfig
index 46be031f91b4..34438cec32b9 100644
--- a/drivers/nvme/target/Kconfig
+++ b/drivers/nvme/target/Kconfig
@@ -98,6 +98,7 @@ config NVME_TARGET_TCP_TLS
 	bool "NVMe over Fabrics TCP target TLS encryption support"
 	depends on NVME_TARGET_TCP
 	select NET_HANDSHAKE
+	select TLS
 	help
 	  Enables TLS encryption for the NVMe TCP target using the netlink handshake API.
 
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index ed2424f8a396..710e74d3ec3e 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -62,14 +62,7 @@ inline u16 errno_to_nvme_status(struct nvmet_req *req, int errno)
 		return  NVME_SC_LBA_RANGE | NVME_STATUS_DNR;
 	case -EOPNOTSUPP:
 		req->error_loc = offsetof(struct nvme_common_command, opcode);
-		switch (req->cmd->common.opcode) {
-		case nvme_cmd_dsm:
-		case nvme_cmd_write_zeroes:
-			return NVME_SC_ONCS_NOT_SUPPORTED | NVME_STATUS_DNR;
-		default:
-			return NVME_SC_INVALID_OPCODE | NVME_STATUS_DNR;
-		}
-		break;
+		return NVME_SC_INVALID_OPCODE | NVME_STATUS_DNR;
 	case -ENODATA:
 		req->error_loc = offsetof(struct nvme_rw_command, nsid);
 		return NVME_SC_ACCESS_DENIED;
@@ -1721,24 +1714,24 @@ static int __init nvmet_init(void)
 	if (!nvmet_wq)
 		goto out_free_buffered_work_queue;
 
-	error = nvmet_init_discovery();
+	error = nvmet_init_debugfs();
 	if (error)
 		goto out_free_nvmet_work_queue;
 
-	error = nvmet_init_debugfs();
+	error = nvmet_init_discovery();
 	if (error)
-		goto out_exit_discovery;
+		goto out_exit_debugfs;
 
 	error = nvmet_init_configfs();
 	if (error)
-		goto out_exit_debugfs;
+		goto out_exit_discovery;
 
 	return 0;
 
-out_exit_debugfs:
-	nvmet_exit_debugfs();
 out_exit_discovery:
 	nvmet_exit_discovery();
+out_exit_debugfs:
+	nvmet_exit_debugfs();
 out_free_nvmet_work_queue:
 	destroy_workqueue(nvmet_wq);
 out_free_buffered_work_queue:
@@ -1753,8 +1746,8 @@ out_destroy_bvec_cache:
 static void __exit nvmet_exit(void)
 {
 	nvmet_exit_configfs();
-	nvmet_exit_debugfs();
 	nvmet_exit_discovery();
+	nvmet_exit_debugfs();
 	ida_destroy(&cntlid_ida);
 	destroy_workqueue(nvmet_wq);
 	destroy_workqueue(buffered_io_wq);
diff --git a/drivers/nvme/target/debugfs.c b/drivers/nvme/target/debugfs.c
index 220c7391fc19..c6571fbd35e3 100644
--- a/drivers/nvme/target/debugfs.c
+++ b/drivers/nvme/target/debugfs.c
@@ -78,7 +78,7 @@ static int nvmet_ctrl_state_show(struct seq_file *m, void *p)
 	bool sep = false;
 	int i;
 
-	for (i = 0; i < 7; i++) {
+	for (i = 0; i < ARRAY_SIZE(csts_state_names); i++) {
 		int state = BIT(i);
 
 		if (!(ctrl->csts & state))
diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c
index 3ef4beacde32..ef8c5961e10c 100644
--- a/drivers/nvme/target/fc.c
+++ b/drivers/nvme/target/fc.c
@@ -172,20 +172,6 @@ struct nvmet_fc_tgt_assoc {
 	struct work_struct		del_work;
 };
 
-
-static inline int
-nvmet_fc_iodnum(struct nvmet_fc_ls_iod *iodptr)
-{
-	return (iodptr - iodptr->tgtport->iod);
-}
-
-static inline int
-nvmet_fc_fodnum(struct nvmet_fc_fcp_iod *fodptr)
-{
-	return (fodptr - fodptr->queue->fod);
-}
-
-
 /*
  * Association and Connection IDs:
  *
@@ -1042,33 +1028,24 @@ nvmet_fc_alloc_hostport(struct nvmet_fc_tgtport *tgtport, void *hosthandle)
 	struct nvmet_fc_hostport *newhost, *match = NULL;
 	unsigned long flags;
 
+	/*
+	 * Caller holds a reference on tgtport.
+	 */
+
 	/* if LLDD not implemented, leave as NULL */
 	if (!hosthandle)
 		return NULL;
 
-	/*
-	 * take reference for what will be the newly allocated hostport if
-	 * we end up using a new allocation
-	 */
-	if (!nvmet_fc_tgtport_get(tgtport))
-		return ERR_PTR(-EINVAL);
-
 	spin_lock_irqsave(&tgtport->lock, flags);
 	match = nvmet_fc_match_hostport(tgtport, hosthandle);
 	spin_unlock_irqrestore(&tgtport->lock, flags);
 
-	if (match) {
-		/* no new allocation - release reference */
-		nvmet_fc_tgtport_put(tgtport);
+	if (match)
 		return match;
-	}
 
 	newhost = kzalloc(sizeof(*newhost), GFP_KERNEL);
-	if (!newhost) {
-		/* no new allocation - release reference */
-		nvmet_fc_tgtport_put(tgtport);
+	if (!newhost)
 		return ERR_PTR(-ENOMEM);
-	}
 
 	spin_lock_irqsave(&tgtport->lock, flags);
 	match = nvmet_fc_match_hostport(tgtport, hosthandle);
@@ -1077,6 +1054,7 @@ nvmet_fc_alloc_hostport(struct nvmet_fc_tgtport *tgtport, void *hosthandle)
 		kfree(newhost);
 		newhost = match;
 	} else {
+		nvmet_fc_tgtport_get(tgtport);
 		newhost->tgtport = tgtport;
 		newhost->hosthandle = hosthandle;
 		INIT_LIST_HEAD(&newhost->host_list);
@@ -1111,7 +1089,8 @@ static void
 nvmet_fc_schedule_delete_assoc(struct nvmet_fc_tgt_assoc *assoc)
 {
 	nvmet_fc_tgtport_get(assoc->tgtport);
-	queue_work(nvmet_wq, &assoc->del_work);
+	if (!queue_work(nvmet_wq, &assoc->del_work))
+		nvmet_fc_tgtport_put(assoc->tgtport);
 }
 
 static bool
diff --git a/drivers/nvme/target/fcloop.c b/drivers/nvme/target/fcloop.c
index e1abb27927ff..f1b5ffc00ce8 100644
--- a/drivers/nvme/target/fcloop.c
+++ b/drivers/nvme/target/fcloop.c
@@ -478,7 +478,7 @@ fcloop_t2h_xmt_ls_rsp(struct nvme_fc_local_port *localport,
 	if (targetport) {
 		tport = targetport->private;
 		spin_lock(&tport->lock);
-		list_add_tail(&tport->ls_list, &tls_req->ls_list);
+		list_add_tail(&tls_req->ls_list, &tport->ls_list);
 		spin_unlock(&tport->lock);
 		queue_work(nvmet_wq, &tport->ls_work);
 	}
@@ -623,12 +623,13 @@ fcloop_fcp_recv_work(struct work_struct *work)
 {
 	struct fcloop_fcpreq *tfcp_req =
 		container_of(work, struct fcloop_fcpreq, fcp_rcv_work);
-	struct nvmefc_fcp_req *fcpreq = tfcp_req->fcpreq;
+	struct nvmefc_fcp_req *fcpreq;
 	unsigned long flags;
 	int ret = 0;
 	bool aborted = false;
 
 	spin_lock_irqsave(&tfcp_req->reqlock, flags);
+	fcpreq = tfcp_req->fcpreq;
 	switch (tfcp_req->inistate) {
 	case INI_IO_START:
 		tfcp_req->inistate = INI_IO_ACTIVE;
@@ -643,16 +644,19 @@ fcloop_fcp_recv_work(struct work_struct *work)
 	}
 	spin_unlock_irqrestore(&tfcp_req->reqlock, flags);
 
-	if (unlikely(aborted))
-		ret = -ECANCELED;
-	else {
-		if (likely(!check_for_drop(tfcp_req)))
-			ret = nvmet_fc_rcv_fcp_req(tfcp_req->tport->targetport,
-				&tfcp_req->tgt_fcp_req,
-				fcpreq->cmdaddr, fcpreq->cmdlen);
-		else
-			pr_info("%s: dropped command ********\n", __func__);
+	if (unlikely(aborted)) {
+		/* the abort handler will call fcloop_call_host_done */
+		return;
 	}
+
+	if (unlikely(check_for_drop(tfcp_req))) {
+		pr_info("%s: dropped command ********\n", __func__);
+		return;
+	}
+
+	ret = nvmet_fc_rcv_fcp_req(tfcp_req->tport->targetport,
+				   &tfcp_req->tgt_fcp_req,
+				   fcpreq->cmdaddr, fcpreq->cmdlen);
 	if (ret)
 		fcloop_call_host_done(fcpreq, tfcp_req, ret);
 }
@@ -667,9 +671,10 @@ fcloop_fcp_abort_recv_work(struct work_struct *work)
 	unsigned long flags;
 
 	spin_lock_irqsave(&tfcp_req->reqlock, flags);
-	fcpreq = tfcp_req->fcpreq;
 	switch (tfcp_req->inistate) {
 	case INI_IO_ABORTED:
+		fcpreq = tfcp_req->fcpreq;
+		tfcp_req->fcpreq = NULL;
 		break;
 	case INI_IO_COMPLETED:
 		completed = true;
@@ -691,10 +696,6 @@ fcloop_fcp_abort_recv_work(struct work_struct *work)
 		nvmet_fc_rcv_fcp_abort(tfcp_req->tport->targetport,
 					&tfcp_req->tgt_fcp_req);
 
-	spin_lock_irqsave(&tfcp_req->reqlock, flags);
-	tfcp_req->fcpreq = NULL;
-	spin_unlock_irqrestore(&tfcp_req->reqlock, flags);
-
 	fcloop_call_host_done(fcpreq, tfcp_req, -ECANCELED);
 	/* call_host_done releases reference for abort downcall */
 }
diff --git a/drivers/nvme/target/io-cmd-bdev.c b/drivers/nvme/target/io-cmd-bdev.c
index eaf31c823cbe..73ecbc13c5b2 100644
--- a/drivers/nvme/target/io-cmd-bdev.c
+++ b/drivers/nvme/target/io-cmd-bdev.c
@@ -145,15 +145,8 @@ u16 blk_to_nvme_status(struct nvmet_req *req, blk_status_t blk_sts)
 		req->error_loc = offsetof(struct nvme_rw_command, slba);
 		break;
 	case BLK_STS_NOTSUPP:
+		status = NVME_SC_INVALID_OPCODE | NVME_STATUS_DNR;
 		req->error_loc = offsetof(struct nvme_common_command, opcode);
-		switch (req->cmd->common.opcode) {
-		case nvme_cmd_dsm:
-		case nvme_cmd_write_zeroes:
-			status = NVME_SC_ONCS_NOT_SUPPORTED | NVME_STATUS_DNR;
-			break;
-		default:
-			status = NVME_SC_INVALID_OPCODE | NVME_STATUS_DNR;
-		}
 		break;
 	case BLK_STS_MEDIUM:
 		status = NVME_SC_ACCESS_DENIED;
diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h
index 190f55e6d753..3062562c096a 100644
--- a/drivers/nvme/target/nvmet.h
+++ b/drivers/nvme/target/nvmet.h
@@ -714,6 +714,8 @@ static inline void nvmet_req_bio_put(struct nvmet_req *req, struct bio *bio)
 {
 	if (bio != &req->b.inline_bio)
 		bio_put(bio);
+	else
+		bio_uninit(bio);
 }
 
 #ifdef CONFIG_NVME_TARGET_AUTH
diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c
index 1afd93026f9b..2a4536ef6184 100644
--- a/drivers/nvme/target/rdma.c
+++ b/drivers/nvme/target/rdma.c
@@ -996,6 +996,27 @@ out_err:
 	nvmet_req_complete(&cmd->req, status);
 }
 
+static bool nvmet_rdma_recv_not_live(struct nvmet_rdma_queue *queue,
+		struct nvmet_rdma_rsp *rsp)
+{
+	unsigned long flags;
+	bool ret = true;
+
+	spin_lock_irqsave(&queue->state_lock, flags);
+	/*
+	 * recheck queue state is not live to prevent a race condition
+	 * with RDMA_CM_EVENT_ESTABLISHED handler.
+	 */
+	if (queue->state == NVMET_RDMA_Q_LIVE)
+		ret = false;
+	else if (queue->state == NVMET_RDMA_Q_CONNECTING)
+		list_add_tail(&rsp->wait_list, &queue->rsp_wait_list);
+	else
+		nvmet_rdma_put_rsp(rsp);
+	spin_unlock_irqrestore(&queue->state_lock, flags);
+	return ret;
+}
+
 static void nvmet_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc)
 {
 	struct nvmet_rdma_cmd *cmd =
@@ -1038,17 +1059,9 @@ static void nvmet_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc)
 	rsp->n_rdma = 0;
 	rsp->invalidate_rkey = 0;
 
-	if (unlikely(queue->state != NVMET_RDMA_Q_LIVE)) {
-		unsigned long flags;
-
-		spin_lock_irqsave(&queue->state_lock, flags);
-		if (queue->state == NVMET_RDMA_Q_CONNECTING)
-			list_add_tail(&rsp->wait_list, &queue->rsp_wait_list);
-		else
-			nvmet_rdma_put_rsp(rsp);
-		spin_unlock_irqrestore(&queue->state_lock, flags);
+	if (unlikely(queue->state != NVMET_RDMA_Q_LIVE) &&
+	    nvmet_rdma_recv_not_live(queue, rsp))
 		return;
-	}
 
 	nvmet_rdma_handle_command(queue, rsp);
 }
diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
index 7c51c2a8c109..6268b18d2456 100644
--- a/drivers/nvme/target/tcp.c
+++ b/drivers/nvme/target/tcp.c
@@ -571,10 +571,16 @@ static void nvmet_tcp_queue_response(struct nvmet_req *req)
 	struct nvmet_tcp_cmd *cmd =
 		container_of(req, struct nvmet_tcp_cmd, req);
 	struct nvmet_tcp_queue	*queue = cmd->queue;
+	enum nvmet_tcp_recv_state queue_state;
+	struct nvmet_tcp_cmd *queue_cmd;
 	struct nvme_sgl_desc *sgl;
 	u32 len;
 
-	if (unlikely(cmd == queue->cmd)) {
+	/* Pairs with store_release in nvmet_prepare_receive_pdu() */
+	queue_state = smp_load_acquire(&queue->rcv_state);
+	queue_cmd = READ_ONCE(queue->cmd);
+
+	if (unlikely(cmd == queue_cmd)) {
 		sgl = &cmd->req.cmd->common.dptr.sgl;
 		len = le32_to_cpu(sgl->length);
 
@@ -583,7 +589,7 @@ static void nvmet_tcp_queue_response(struct nvmet_req *req)
 		 * Avoid using helpers, this might happen before
 		 * nvmet_req_init is completed.
 		 */
-		if (queue->rcv_state == NVMET_TCP_RECV_PDU &&
+		if (queue_state == NVMET_TCP_RECV_PDU &&
 		    len && len <= cmd->req.port->inline_data_size &&
 		    nvme_is_write(cmd->req.cmd))
 			return;
@@ -847,8 +853,9 @@ static void nvmet_prepare_receive_pdu(struct nvmet_tcp_queue *queue)
 {
 	queue->offset = 0;
 	queue->left = sizeof(struct nvme_tcp_hdr);
-	queue->cmd = NULL;
-	queue->rcv_state = NVMET_TCP_RECV_PDU;
+	WRITE_ONCE(queue->cmd, NULL);
+	/* Ensure rcv_state is visible only after queue->cmd is set */
+	smp_store_release(&queue->rcv_state, NVMET_TCP_RECV_PDU);
 }
 
 static void nvmet_tcp_free_crypto(struct nvmet_tcp_queue *queue)
@@ -1553,6 +1560,9 @@ static void nvmet_tcp_restore_socket_callbacks(struct nvmet_tcp_queue *queue)
 {
 	struct socket *sock = queue->sock;
 
+	if (!queue->state_change)
+		return;
+
 	write_lock_bh(&sock->sk->sk_callback_lock);
 	sock->sk->sk_data_ready =  queue->data_ready;
 	sock->sk->sk_state_change = queue->state_change;
@@ -1931,10 +1941,10 @@ static void nvmet_tcp_alloc_queue(struct nvmet_tcp_port *port,
 		struct sock *sk = queue->sock->sk;
 
 		/* Restore the default callbacks before starting upcall */
-		read_lock_bh(&sk->sk_callback_lock);
+		write_lock_bh(&sk->sk_callback_lock);
 		sk->sk_user_data = NULL;
 		sk->sk_data_ready = port->data_ready;
-		read_unlock_bh(&sk->sk_callback_lock);
+		write_unlock_bh(&sk->sk_callback_lock);
 		if (!nvmet_tcp_try_peek_pdu(queue)) {
 			if (!nvmet_tcp_tls_handshake(queue))
 				return;
diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c
index e1a15fbc6ad0..d1869e6de384 100644
--- a/drivers/nvmem/core.c
+++ b/drivers/nvmem/core.c
@@ -581,9 +581,11 @@ static int nvmem_cell_info_to_nvmem_cell_entry_nodup(struct nvmem_device *nvmem,
 	cell->nbits = info->nbits;
 	cell->np = info->np;
 
-	if (cell->nbits)
+	if (cell->nbits) {
 		cell->bytes = DIV_ROUND_UP(cell->nbits + cell->bit_offset,
 					   BITS_PER_BYTE);
+		cell->raw_len = ALIGN(cell->bytes, nvmem->word_size);
+	}
 
 	if (!IS_ALIGNED(cell->offset, nvmem->stride)) {
 		dev_err(&nvmem->dev,
@@ -592,6 +594,18 @@ static int nvmem_cell_info_to_nvmem_cell_entry_nodup(struct nvmem_device *nvmem,
 		return -EINVAL;
 	}
 
+	if (!IS_ALIGNED(cell->raw_len, nvmem->word_size)) {
+		dev_err(&nvmem->dev,
+			"cell %s raw len %zd unaligned to nvmem word size %d\n",
+			cell->name ?: "<unknown>", cell->raw_len,
+			nvmem->word_size);
+
+		if (info->raw_len)
+			return -EINVAL;
+
+		cell->raw_len = ALIGN(cell->raw_len, nvmem->word_size);
+	}
+
 	return 0;
 }
 
@@ -824,7 +838,9 @@ static int nvmem_add_cells_from_dt(struct nvmem_device *nvmem, struct device_nod
 		if (addr && len == (2 * sizeof(u32))) {
 			info.bit_offset = be32_to_cpup(addr++);
 			info.nbits = be32_to_cpup(addr);
-			if (info.bit_offset >= BITS_PER_BYTE || info.nbits < 1) {
+			if (info.bit_offset >= BITS_PER_BYTE * info.bytes ||
+			    info.nbits < 1 ||
+			    info.bit_offset + info.nbits > BITS_PER_BYTE * info.bytes) {
 				dev_err(dev, "nvmem: invalid bits on %pOF\n", child);
 				of_node_put(child);
 				return -EINVAL;
@@ -1617,21 +1633,29 @@ EXPORT_SYMBOL_GPL(nvmem_cell_put);
 static void nvmem_shift_read_buffer_in_place(struct nvmem_cell_entry *cell, void *buf)
 {
 	u8 *p, *b;
-	int i, extra, bit_offset = cell->bit_offset;
+	int i, extra, bytes_offset;
+	int bit_offset = cell->bit_offset;
 
 	p = b = buf;
-	if (bit_offset) {
+
+	bytes_offset = bit_offset / BITS_PER_BYTE;
+	b += bytes_offset;
+	bit_offset %= BITS_PER_BYTE;
+
+	if (bit_offset % BITS_PER_BYTE) {
 		/* First shift */
-		*b++ >>= bit_offset;
+		*p = *b++ >> bit_offset;
 
 		/* setup rest of the bytes if any */
 		for (i = 1; i < cell->bytes; i++) {
 			/* Get bits from next byte and shift them towards msb */
-			*p |= *b << (BITS_PER_BYTE - bit_offset);
+			*p++ |= *b << (BITS_PER_BYTE - bit_offset);
 
-			p = b;
-			*b++ >>= bit_offset;
+			*p = *b++ >> bit_offset;
 		}
+	} else if (p != b) {
+		memmove(p, b, cell->bytes - bytes_offset);
+		p += cell->bytes - 1;
 	} else {
 		/* point to the msb */
 		p += cell->bytes - 1;
@@ -1780,6 +1804,8 @@ static int __nvmem_cell_entry_write(struct nvmem_cell_entry *cell, void *buf, si
 		return -EINVAL;
 
 	if (cell->bit_offset || cell->nbits) {
+		if (len != BITS_TO_BYTES(cell->nbits) && len != cell->bytes)
+			return -EINVAL;
 		buf = nvmem_cell_prepare_write_buffer(cell, buf, len);
 		if (IS_ERR(buf))
 			return PTR_ERR(buf);
diff --git a/drivers/nvmem/imx-ocotp-ele.c b/drivers/nvmem/imx-ocotp-ele.c
index 1ba494497698..7807ec0e2d18 100644
--- a/drivers/nvmem/imx-ocotp-ele.c
+++ b/drivers/nvmem/imx-ocotp-ele.c
@@ -12,6 +12,7 @@
 #include <linux/of.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
+#include <linux/if_ether.h>	/* ETH_ALEN */
 
 enum fuse_type {
 	FUSE_FSB = BIT(0),
@@ -71,13 +72,15 @@ static int imx_ocotp_reg_read(void *context, unsigned int offset, void *val, siz
 	u32 *buf;
 	void *p;
 	int i;
+	u8 skipbytes;
 
-	index = offset;
-	num_bytes = round_up(bytes, 4);
-	count = num_bytes >> 2;
+	if (offset + bytes > priv->data->size)
+		bytes = priv->data->size - offset;
 
-	if (count > ((priv->data->size >> 2) - index))
-		count = (priv->data->size >> 2) - index;
+	index = offset >> 2;
+	skipbytes = offset - (index << 2);
+	num_bytes = round_up(bytes + skipbytes, 4);
+	count = num_bytes >> 2;
 
 	p = kzalloc(num_bytes, GFP_KERNEL);
 	if (!p)
@@ -100,7 +103,7 @@ static int imx_ocotp_reg_read(void *context, unsigned int offset, void *val, siz
 			*buf++ = readl_relaxed(reg + (i << 2));
 	}
 
-	memcpy(val, (u8 *)p, bytes);
+	memcpy(val, ((u8 *)p) + skipbytes, bytes);
 
 	mutex_unlock(&priv->lock);
 
@@ -109,6 +112,28 @@ static int imx_ocotp_reg_read(void *context, unsigned int offset, void *val, siz
 	return 0;
 };
 
+static int imx_ocotp_cell_pp(void *context, const char *id, int index,
+			     unsigned int offset, void *data, size_t bytes)
+{
+	u8 *buf = data;
+	int i;
+
+	/* Deal with some post processing of nvmem cell data */
+	if (id && !strcmp(id, "mac-address")) {
+		bytes = min(bytes, ETH_ALEN);
+		for (i = 0; i < bytes / 2; i++)
+			swap(buf[i], buf[bytes - i - 1]);
+	}
+
+	return 0;
+}
+
+static void imx_ocotp_fixup_dt_cell_info(struct nvmem_device *nvmem,
+					 struct nvmem_cell_info *cell)
+{
+	cell->read_post_process = imx_ocotp_cell_pp;
+}
+
 static int imx_ele_ocotp_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -131,10 +156,12 @@ static int imx_ele_ocotp_probe(struct platform_device *pdev)
 	priv->config.owner = THIS_MODULE;
 	priv->config.size = priv->data->size;
 	priv->config.reg_read = priv->data->reg_read;
-	priv->config.word_size = 4;
+	priv->config.word_size = 1;
 	priv->config.stride = 1;
 	priv->config.priv = priv;
 	priv->config.read_only = true;
+	priv->config.add_legacy_fixed_of_cells = true;
+	priv->config.fixup_dt_cell_info = imx_ocotp_fixup_dt_cell_info;
 	mutex_init(&priv->lock);
 
 	nvmem = devm_nvmem_register(dev, &priv->config);
diff --git a/drivers/nvmem/imx-ocotp.c b/drivers/nvmem/imx-ocotp.c
index 79dd4fda0329..7bf7656d4f96 100644
--- a/drivers/nvmem/imx-ocotp.c
+++ b/drivers/nvmem/imx-ocotp.c
@@ -23,6 +23,7 @@
 #include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <linux/delay.h>
+#include <linux/if_ether.h>	/* ETH_ALEN */
 
 #define IMX_OCOTP_OFFSET_B0W0		0x400 /* Offset from base address of the
 					       * OTP Bank0 Word0
@@ -227,9 +228,11 @@ static int imx_ocotp_cell_pp(void *context, const char *id, int index,
 	int i;
 
 	/* Deal with some post processing of nvmem cell data */
-	if (id && !strcmp(id, "mac-address"))
+	if (id && !strcmp(id, "mac-address")) {
+		bytes = min(bytes, ETH_ALEN);
 		for (i = 0; i < bytes / 2; i++)
 			swap(buf[i], buf[bytes - i - 1]);
+	}
 
 	return 0;
 }
diff --git a/drivers/nvmem/layouts/u-boot-env.c b/drivers/nvmem/layouts/u-boot-env.c
index 731e6f4f12b2..21f6dcf905dd 100644
--- a/drivers/nvmem/layouts/u-boot-env.c
+++ b/drivers/nvmem/layouts/u-boot-env.c
@@ -92,7 +92,7 @@ int u_boot_env_parse(struct device *dev, struct nvmem_device *nvmem,
 	size_t crc32_data_offset;
 	size_t crc32_data_len;
 	size_t crc32_offset;
-	__le32 *crc32_addr;
+	uint32_t *crc32_addr;
 	size_t data_offset;
 	size_t data_len;
 	size_t dev_size;
@@ -143,8 +143,8 @@ int u_boot_env_parse(struct device *dev, struct nvmem_device *nvmem,
 		goto err_kfree;
 	}
 
-	crc32_addr = (__le32 *)(buf + crc32_offset);
-	crc32 = le32_to_cpu(*crc32_addr);
+	crc32_addr = (uint32_t *)(buf + crc32_offset);
+	crc32 = *crc32_addr;
 	crc32_data_len = dev_size - crc32_data_offset;
 	data_len = dev_size - data_offset;
 
diff --git a/drivers/nvmem/qcom-spmi-sdam.c b/drivers/nvmem/qcom-spmi-sdam.c
index 9aa8f42faa4c..4f1cca6eab71 100644
--- a/drivers/nvmem/qcom-spmi-sdam.c
+++ b/drivers/nvmem/qcom-spmi-sdam.c
@@ -144,6 +144,7 @@ static int sdam_probe(struct platform_device *pdev)
 	sdam->sdam_config.owner = THIS_MODULE;
 	sdam->sdam_config.add_legacy_fixed_of_cells = true;
 	sdam->sdam_config.stride = 1;
+	sdam->sdam_config.size = sdam->size;
 	sdam->sdam_config.word_size = 1;
 	sdam->sdam_config.reg_read = sdam_read;
 	sdam->sdam_config.reg_write = sdam_write;
diff --git a/drivers/nvmem/qfprom.c b/drivers/nvmem/qfprom.c
index 116a39e804c7..a872c640b8c5 100644
--- a/drivers/nvmem/qfprom.c
+++ b/drivers/nvmem/qfprom.c
@@ -321,19 +321,32 @@ static int qfprom_reg_read(void *context,
 			unsigned int reg, void *_val, size_t bytes)
 {
 	struct qfprom_priv *priv = context;
-	u8 *val = _val;
-	int i = 0, words = bytes;
+	u32 *val = _val;
 	void __iomem *base = priv->qfpcorrected;
+	int words = DIV_ROUND_UP(bytes, sizeof(u32));
+	int i;
 
 	if (read_raw_data && priv->qfpraw)
 		base = priv->qfpraw;
 
-	while (words--)
-		*val++ = readb(base + reg + i++);
+	for (i = 0; i < words; i++)
+		*val++ = readl(base + reg + i * sizeof(u32));
 
 	return 0;
 }
 
+/* Align reads to word boundary */
+static void qfprom_fixup_dt_cell_info(struct nvmem_device *nvmem,
+				      struct nvmem_cell_info *cell)
+{
+	unsigned int byte_offset = cell->offset % sizeof(u32);
+
+	cell->bit_offset += byte_offset * BITS_PER_BYTE;
+	cell->offset -= byte_offset;
+	if (byte_offset && !cell->nbits)
+		cell->nbits = cell->bytes * BITS_PER_BYTE;
+}
+
 static void qfprom_runtime_disable(void *data)
 {
 	pm_runtime_disable(data);
@@ -358,10 +371,11 @@ static int qfprom_probe(struct platform_device *pdev)
 	struct nvmem_config econfig = {
 		.name = "qfprom",
 		.add_legacy_fixed_of_cells = true,
-		.stride = 1,
-		.word_size = 1,
+		.stride = 4,
+		.word_size = 4,
 		.id = NVMEM_DEVID_AUTO,
 		.reg_read = qfprom_reg_read,
+		.fixup_dt_cell_info = qfprom_fixup_dt_cell_info,
 	};
 	struct device *dev = &pdev->dev;
 	struct resource *res;
diff --git a/drivers/nvmem/rockchip-otp.c b/drivers/nvmem/rockchip-otp.c
index ebc3f0b24166..d88f12c53242 100644
--- a/drivers/nvmem/rockchip-otp.c
+++ b/drivers/nvmem/rockchip-otp.c
@@ -59,7 +59,6 @@
 #define RK3588_OTPC_AUTO_EN		0x08
 #define RK3588_OTPC_INT_ST		0x84
 #define RK3588_OTPC_DOUT0		0x20
-#define RK3588_NO_SECURE_OFFSET		0x300
 #define RK3588_NBYTES			4
 #define RK3588_BURST_NUM		1
 #define RK3588_BURST_SHIFT		8
@@ -69,6 +68,7 @@
 
 struct rockchip_data {
 	int size;
+	int read_offset;
 	const char * const *clks;
 	int num_clks;
 	nvmem_reg_read_t reg_read;
@@ -196,7 +196,7 @@ static int rk3588_otp_read(void *context, unsigned int offset,
 	addr_start = round_down(offset, RK3588_NBYTES) / RK3588_NBYTES;
 	addr_end = round_up(offset + bytes, RK3588_NBYTES) / RK3588_NBYTES;
 	addr_len = addr_end - addr_start;
-	addr_start += RK3588_NO_SECURE_OFFSET;
+	addr_start += otp->data->read_offset / RK3588_NBYTES;
 
 	buf = kzalloc(array_size(addr_len, RK3588_NBYTES), GFP_KERNEL);
 	if (!buf)
@@ -274,12 +274,21 @@ static const struct rockchip_data px30_data = {
 	.reg_read = px30_otp_read,
 };
 
+static const struct rockchip_data rk3576_data = {
+	.size = 0x100,
+	.read_offset = 0x700,
+	.clks = px30_otp_clocks,
+	.num_clks = ARRAY_SIZE(px30_otp_clocks),
+	.reg_read = rk3588_otp_read,
+};
+
 static const char * const rk3588_otp_clocks[] = {
 	"otp", "apb_pclk", "phy", "arb",
 };
 
 static const struct rockchip_data rk3588_data = {
 	.size = 0x400,
+	.read_offset = 0xc00,
 	.clks = rk3588_otp_clocks,
 	.num_clks = ARRAY_SIZE(rk3588_otp_clocks),
 	.reg_read = rk3588_otp_read,
@@ -295,6 +304,10 @@ static const struct of_device_id rockchip_otp_match[] = {
 		.data = &px30_data,
 	},
 	{
+		.compatible = "rockchip,rk3576-otp",
+		.data = &rk3576_data,
+	},
+	{
 		.compatible = "rockchip,rk3588-otp",
 		.data = &rk3588_data,
 	},
diff --git a/drivers/nvmem/zynqmp_nvmem.c b/drivers/nvmem/zynqmp_nvmem.c
index 8682adaacd69..7da717d6c7fa 100644
--- a/drivers/nvmem/zynqmp_nvmem.c
+++ b/drivers/nvmem/zynqmp_nvmem.c
@@ -213,6 +213,7 @@ static int zynqmp_nvmem_probe(struct platform_device *pdev)
 	econfig.word_size = 1;
 	econfig.size = ZYNQMP_NVMEM_SIZE;
 	econfig.dev = dev;
+	econfig.priv = dev;
 	econfig.add_legacy_fixed_of_cells = true;
 	econfig.reg_read = zynqmp_nvmem_read;
 	econfig.reg_write = zynqmp_nvmem_write;
diff --git a/drivers/of/address.c b/drivers/of/address.c
index a565b8c91da5..0e708a863e4a 100644
--- a/drivers/of/address.c
+++ b/drivers/of/address.c
@@ -200,17 +200,15 @@ static u64 of_bus_pci_map(__be32 *addr, const __be32 *range, int na, int ns,
 
 static int __of_address_resource_bounds(struct resource *r, u64 start, u64 size)
 {
-	u64 end = start;
-
 	if (overflows_type(start, r->start))
 		return -EOVERFLOW;
-	if (size && check_add_overflow(end, size - 1, &end))
-		return -EOVERFLOW;
-	if (overflows_type(end, r->end))
-		return -EOVERFLOW;
 
 	r->start = start;
-	r->end = end;
+
+	if (!size)
+		r->end = wrapping_sub(typeof(r->end), r->start, 1);
+	else if (size && check_add_overflow(r->start, size - 1, &r->end))
+		return -EOVERFLOW;
 
 	return 0;
 }
diff --git a/drivers/of/base.c b/drivers/of/base.c
index 63161d0f72b4..4bb87e0cbaf1 100644
--- a/drivers/of/base.c
+++ b/drivers/of/base.c
@@ -841,10 +841,10 @@ struct device_node *of_find_node_opts_by_path(const char *path, const char **opt
 	/* The path could begin with an alias */
 	if (*path != '/') {
 		int len;
-		const char *p = separator;
+		const char *p = strchrnul(path, '/');
 
-		if (!p)
-			p = strchrnul(path, '/');
+		if (separator && separator < p)
+			p = separator;
 		len = p - path;
 
 		/* of_aliases must not be NULL */
@@ -1493,7 +1493,6 @@ int of_parse_phandle_with_args_map(const struct device_node *np,
 		 * specifier into the out_args structure, keeping the
 		 * bits specified in <list>-map-pass-thru.
 		 */
-		match_array = map - new_size;
 		for (i = 0; i < new_size; i++) {
 			__be32 val = *(map - new_size + i);
 
@@ -1502,6 +1501,7 @@ int of_parse_phandle_with_args_map(const struct device_node *np,
 				val |= cpu_to_be32(out_args->args[i]) & pass[i];
 			}
 
+			initial_match_array[i] = val;
 			out_args->args[i] = be32_to_cpu(val);
 		}
 		out_args->args_count = list_size = new_size;
diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c
index 546e76ac407c..8c80f4dc8b3f 100644
--- a/drivers/of/fdt.c
+++ b/drivers/of/fdt.c
@@ -8,7 +8,6 @@
 
 #define pr_fmt(fmt)	"OF: fdt: " fmt
 
-#include <linux/acpi.h>
 #include <linux/crash_dump.h>
 #include <linux/crc32.h>
 #include <linux/kernel.h>
@@ -512,8 +511,6 @@ void __init early_init_fdt_scan_reserved_mem(void)
 			break;
 		memblock_reserve(base, size);
 	}
-
-	fdt_init_reserved_mem();
 }
 
 /**
@@ -1214,14 +1211,10 @@ void __init unflatten_device_tree(void)
 {
 	void *fdt = initial_boot_params;
 
-	/* Don't use the bootloader provided DTB if ACPI is enabled */
-	if (!acpi_disabled)
-		fdt = NULL;
+	/* Save the statically-placed regions in the reserved_mem array */
+	fdt_scan_reserved_mem_reg_nodes();
 
-	/*
-	 * Populate an empty root node when ACPI is enabled or bootloader
-	 * doesn't provide one.
-	 */
+	/* Populate an empty root node when bootloader doesn't provide one */
 	if (!fdt) {
 		fdt = (void *) __dtb_empty_root_begin;
 		/* fdt_totalsize() will be used for copy size */
diff --git a/drivers/of/irq.c b/drivers/of/irq.c
index 1fb329c0a55b..5fbfc4d4e06e 100644
--- a/drivers/of/irq.c
+++ b/drivers/of/irq.c
@@ -16,6 +16,7 @@
 
 #define pr_fmt(fmt)	"OF: " fmt
 
+#include <linux/cleanup.h>
 #include <linux/device.h>
 #include <linux/errno.h>
 #include <linux/list.h>
@@ -38,11 +39,15 @@
 unsigned int irq_of_parse_and_map(struct device_node *dev, int index)
 {
 	struct of_phandle_args oirq;
+	unsigned int ret;
 
 	if (of_irq_parse_one(dev, index, &oirq))
 		return 0;
 
-	return irq_create_of_mapping(&oirq);
+	ret = irq_create_of_mapping(&oirq);
+	of_node_put(oirq.np);
+
+	return ret;
 }
 EXPORT_SYMBOL_GPL(irq_of_parse_and_map);
 
@@ -165,6 +170,8 @@ const __be32 *of_irq_parse_imap_parent(const __be32 *imap, int len, struct of_ph
  * the specifier for each map, and then returns the translated map.
  *
  * Return: 0 on success and a negative number on error
+ *
+ * Note: refcount of node @out_irq->np is increased by 1 on success.
  */
 int of_irq_parse_raw(const __be32 *addr, struct of_phandle_args *out_irq)
 {
@@ -310,6 +317,12 @@ int of_irq_parse_raw(const __be32 *addr, struct of_phandle_args *out_irq)
 		addrsize = (imap - match_array) - intsize;
 
 		if (ipar == newpar) {
+			/*
+			 * We got @ipar's refcount, but the refcount was
+			 * gotten again by of_irq_parse_imap_parent() via its
+			 * alias @newpar.
+			 */
+			of_node_put(ipar);
 			pr_debug("%pOF interrupt-map entry to self\n", ipar);
 			return 0;
 		}
@@ -339,10 +352,12 @@ EXPORT_SYMBOL_GPL(of_irq_parse_raw);
  * This function resolves an interrupt for a node by walking the interrupt tree,
  * finding which interrupt controller node it is attached to, and returning the
  * interrupt specifier that can be used to retrieve a Linux IRQ number.
+ *
+ * Note: refcount of node @out_irq->np is increased by 1 on success.
  */
 int of_irq_parse_one(struct device_node *device, int index, struct of_phandle_args *out_irq)
 {
-	struct device_node *p;
+	struct device_node __free(device_node) *p = NULL;
 	const __be32 *addr;
 	u32 intsize;
 	int i, res, addr_len;
@@ -367,41 +382,33 @@ int of_irq_parse_one(struct device_node *device, int index, struct of_phandle_ar
 	/* Try the new-style interrupts-extended first */
 	res = of_parse_phandle_with_args(device, "interrupts-extended",
 					"#interrupt-cells", index, out_irq);
-	if (!res)
-		return of_irq_parse_raw(addr_buf, out_irq);
-
-	/* Look for the interrupt parent. */
-	p = of_irq_find_parent(device);
-	if (p == NULL)
-		return -EINVAL;
+	if (!res) {
+		p = out_irq->np;
+	} else {
+		/* Look for the interrupt parent. */
+		p = of_irq_find_parent(device);
+		/* Get size of interrupt specifier */
+		if (!p || of_property_read_u32(p, "#interrupt-cells", &intsize))
+			return -EINVAL;
+
+		pr_debug(" parent=%pOF, intsize=%d\n", p, intsize);
+
+		/* Copy intspec into irq structure */
+		out_irq->np = p;
+		out_irq->args_count = intsize;
+		for (i = 0; i < intsize; i++) {
+			res = of_property_read_u32_index(device, "interrupts",
+							(index * intsize) + i,
+							out_irq->args + i);
+			if (res)
+				return res;
+		}
 
-	/* Get size of interrupt specifier */
-	if (of_property_read_u32(p, "#interrupt-cells", &intsize)) {
-		res = -EINVAL;
-		goto out;
+		pr_debug(" intspec=%d\n", *out_irq->args);
 	}
 
-	pr_debug(" parent=%pOF, intsize=%d\n", p, intsize);
-
-	/* Copy intspec into irq structure */
-	out_irq->np = p;
-	out_irq->args_count = intsize;
-	for (i = 0; i < intsize; i++) {
-		res = of_property_read_u32_index(device, "interrupts",
-						 (index * intsize) + i,
-						 out_irq->args + i);
-		if (res)
-			goto out;
-	}
-
-	pr_debug(" intspec=%d\n", *out_irq->args);
-
-
 	/* Check if there are any interrupt-map translations to process */
-	res = of_irq_parse_raw(addr_buf, out_irq);
- out:
-	of_node_put(p);
-	return res;
+	return of_irq_parse_raw(addr_buf, out_irq);
 }
 EXPORT_SYMBOL_GPL(of_irq_parse_one);
 
@@ -505,8 +512,10 @@ int of_irq_count(struct device_node *dev)
 	struct of_phandle_args irq;
 	int nr = 0;
 
-	while (of_irq_parse_one(dev, nr, &irq) == 0)
+	while (of_irq_parse_one(dev, nr, &irq) == 0) {
+		of_node_put(irq.np);
 		nr++;
+	}
 
 	return nr;
 }
@@ -623,6 +632,8 @@ void __init of_irq_init(const struct of_device_id *matches)
 				       __func__, desc->dev, desc->dev,
 				       desc->interrupt_parent);
 				of_node_clear_flag(desc->dev, OF_POPULATED);
+				of_node_put(desc->interrupt_parent);
+				of_node_put(desc->dev);
 				kfree(desc);
 				continue;
 			}
@@ -653,6 +664,7 @@ void __init of_irq_init(const struct of_device_id *matches)
 err:
 	list_for_each_entry_safe(desc, temp_desc, &intc_desc_list, list) {
 		list_del(&desc->list);
+		of_node_put(desc->interrupt_parent);
 		of_node_put(desc->dev);
 		kfree(desc);
 	}
diff --git a/drivers/of/of_private.h b/drivers/of/of_private.h
index c235d6c909a1..106988622525 100644
--- a/drivers/of/of_private.h
+++ b/drivers/of/of_private.h
@@ -9,6 +9,7 @@
  */
 
 #define FDT_ALIGN_SIZE 8
+#define MAX_RESERVED_REGIONS    64
 
 /**
  * struct alias_prop - Alias property in 'aliases' node
@@ -183,7 +184,7 @@ static inline struct device_node *__of_get_dma_parent(const struct device_node *
 #endif
 
 int fdt_scan_reserved_mem(void);
-void fdt_init_reserved_mem(void);
+void __init fdt_scan_reserved_mem_reg_nodes(void);
 
 bool of_fdt_device_is_available(const void *blob, unsigned long node);
 
diff --git a/drivers/of/of_reserved_mem.c b/drivers/of/of_reserved_mem.c
index 46e1c3fbc769..45445a1600a9 100644
--- a/drivers/of/of_reserved_mem.c
+++ b/drivers/of/of_reserved_mem.c
@@ -27,7 +27,6 @@
 
 #include "of_private.h"
 
-#define MAX_RESERVED_REGIONS	64
 static struct reserved_mem reserved_mem[MAX_RESERVED_REGIONS];
 static int reserved_mem_count;
 
@@ -51,11 +50,13 @@ static int __init early_init_dt_alloc_reserved_memory_arch(phys_addr_t size,
 			memblock_phys_free(base, size);
 	}
 
-	kmemleak_ignore_phys(base);
+	if (!err)
+		kmemleak_ignore_phys(base);
 
 	return err;
 }
 
+static void __init fdt_init_reserved_mem_node(struct reserved_mem *rmem);
 /*
  * fdt_reserved_mem_save_node() - save fdt node for second pass initialization
  */
@@ -74,6 +75,9 @@ static void __init fdt_reserved_mem_save_node(unsigned long node, const char *un
 	rmem->base = base;
 	rmem->size = size;
 
+	/* Call the region specific initialization function */
+	fdt_init_reserved_mem_node(rmem);
+
 	reserved_mem_count++;
 	return;
 }
@@ -106,7 +110,6 @@ static int __init __reserved_mem_reserve_reg(unsigned long node,
 	phys_addr_t base, size;
 	int len;
 	const __be32 *prop;
-	int first = 1;
 	bool nomap;
 
 	prop = of_get_flat_dt_prop(node, "reg", &len);
@@ -134,10 +137,6 @@ static int __init __reserved_mem_reserve_reg(unsigned long node,
 			       uname, &base, (unsigned long)(size / SZ_1M));
 
 		len -= t_len;
-		if (first) {
-			fdt_reserved_mem_save_node(node, uname, base, size);
-			first = 0;
-		}
 	}
 	return 0;
 }
@@ -165,12 +164,82 @@ static int __init __reserved_mem_check_root(unsigned long node)
 	return 0;
 }
 
+static void __init __rmem_check_for_overlap(void);
+
+/**
+ * fdt_scan_reserved_mem_reg_nodes() - Store info for the "reg" defined
+ * reserved memory regions.
+ *
+ * This function is used to scan through the DT and store the
+ * information for the reserved memory regions that are defined using
+ * the "reg" property. The region node number, name, base address, and
+ * size are all stored in the reserved_mem array by calling the
+ * fdt_reserved_mem_save_node() function.
+ */
+void __init fdt_scan_reserved_mem_reg_nodes(void)
+{
+	int t_len = (dt_root_addr_cells + dt_root_size_cells) * sizeof(__be32);
+	const void *fdt = initial_boot_params;
+	phys_addr_t base, size;
+	const __be32 *prop;
+	int node, child;
+	int len;
+
+	if (!fdt)
+		return;
+
+	node = fdt_path_offset(fdt, "/reserved-memory");
+	if (node < 0) {
+		pr_info("Reserved memory: No reserved-memory node in the DT\n");
+		return;
+	}
+
+	if (__reserved_mem_check_root(node)) {
+		pr_err("Reserved memory: unsupported node format, ignoring\n");
+		return;
+	}
+
+	fdt_for_each_subnode(child, fdt, node) {
+		const char *uname;
+
+		prop = of_get_flat_dt_prop(child, "reg", &len);
+		if (!prop)
+			continue;
+		if (!of_fdt_device_is_available(fdt, child))
+			continue;
+
+		uname = fdt_get_name(fdt, child, NULL);
+		if (len && len % t_len != 0) {
+			pr_err("Reserved memory: invalid reg property in '%s', skipping node.\n",
+			       uname);
+			continue;
+		}
+
+		if (len > t_len)
+			pr_warn("%s() ignores %d regions in node '%s'\n",
+				__func__, len / t_len - 1, uname);
+
+		base = dt_mem_next_cell(dt_root_addr_cells, &prop);
+		size = dt_mem_next_cell(dt_root_size_cells, &prop);
+
+		if (size)
+			fdt_reserved_mem_save_node(child, uname, base, size);
+	}
+
+	/* check for overlapping reserved regions */
+	__rmem_check_for_overlap();
+}
+
+static int __init __reserved_mem_alloc_size(unsigned long node, const char *uname);
+
 /*
  * fdt_scan_reserved_mem() - scan a single FDT node for reserved memory
  */
 int __init fdt_scan_reserved_mem(void)
 {
 	int node, child;
+	int dynamic_nodes_cnt = 0;
+	int dynamic_nodes[MAX_RESERVED_REGIONS];
 	const void *fdt = initial_boot_params;
 
 	node = fdt_path_offset(fdt, "/reserved-memory");
@@ -192,8 +261,24 @@ int __init fdt_scan_reserved_mem(void)
 		uname = fdt_get_name(fdt, child, NULL);
 
 		err = __reserved_mem_reserve_reg(child, uname);
-		if (err == -ENOENT && of_get_flat_dt_prop(child, "size", NULL))
-			fdt_reserved_mem_save_node(child, uname, 0, 0);
+		/*
+		 * Save the nodes for the dynamically-placed regions
+		 * into an array which will be used for allocation right
+		 * after all the statically-placed regions are reserved
+		 * or marked as no-map. This is done to avoid dynamically
+		 * allocating from one of the statically-placed regions.
+		 */
+		if (err == -ENOENT && of_get_flat_dt_prop(child, "size", NULL)) {
+			dynamic_nodes[dynamic_nodes_cnt] = child;
+			dynamic_nodes_cnt++;
+		}
+	}
+	for (int i = 0; i < dynamic_nodes_cnt; i++) {
+		const char *uname;
+
+		child = dynamic_nodes[i];
+		uname = fdt_get_name(fdt, child, NULL);
+		__reserved_mem_alloc_size(child, uname);
 	}
 	return 0;
 }
@@ -253,8 +338,7 @@ static int __init __reserved_mem_alloc_in_range(phys_addr_t size,
  * __reserved_mem_alloc_size() - allocate reserved memory described by
  *	'size', 'alignment'  and 'alloc-ranges' properties.
  */
-static int __init __reserved_mem_alloc_size(unsigned long node,
-	const char *uname, phys_addr_t *res_base, phys_addr_t *res_size)
+static int __init __reserved_mem_alloc_size(unsigned long node, const char *uname)
 {
 	int t_len = (dt_root_addr_cells + dt_root_size_cells) * sizeof(__be32);
 	phys_addr_t start = 0, end = 0;
@@ -334,9 +418,8 @@ static int __init __reserved_mem_alloc_size(unsigned long node,
 		return -ENOMEM;
 	}
 
-	*res_base = base;
-	*res_size = size;
-
+	/* Save region in the reserved_mem array */
+	fdt_reserved_mem_save_node(node, uname, base, size);
 	return 0;
 }
 
@@ -425,48 +508,37 @@ static void __init __rmem_check_for_overlap(void)
 }
 
 /**
- * fdt_init_reserved_mem() - allocate and init all saved reserved memory regions
+ * fdt_init_reserved_mem_node() - Initialize a reserved memory region
+ * @rmem: reserved_mem struct of the memory region to be initialized.
+ *
+ * This function is used to call the region specific initialization
+ * function for a reserved memory region.
  */
-void __init fdt_init_reserved_mem(void)
+static void __init fdt_init_reserved_mem_node(struct reserved_mem *rmem)
 {
-	int i;
-
-	/* check for overlapping reserved regions */
-	__rmem_check_for_overlap();
-
-	for (i = 0; i < reserved_mem_count; i++) {
-		struct reserved_mem *rmem = &reserved_mem[i];
-		unsigned long node = rmem->fdt_node;
-		int err = 0;
-		bool nomap;
+	unsigned long node = rmem->fdt_node;
+	int err = 0;
+	bool nomap;
 
-		nomap = of_get_flat_dt_prop(node, "no-map", NULL) != NULL;
+	nomap = of_get_flat_dt_prop(node, "no-map", NULL) != NULL;
 
-		if (rmem->size == 0)
-			err = __reserved_mem_alloc_size(node, rmem->name,
-						 &rmem->base, &rmem->size);
-		if (err == 0) {
-			err = __reserved_mem_init_node(rmem);
-			if (err != 0 && err != -ENOENT) {
-				pr_info("node %s compatible matching fail\n",
-					rmem->name);
-				if (nomap)
-					memblock_clear_nomap(rmem->base, rmem->size);
-				else
-					memblock_phys_free(rmem->base,
-							   rmem->size);
-			} else {
-				phys_addr_t end = rmem->base + rmem->size - 1;
-				bool reusable =
-					(of_get_flat_dt_prop(node, "reusable", NULL)) != NULL;
-
-				pr_info("%pa..%pa (%lu KiB) %s %s %s\n",
-					&rmem->base, &end, (unsigned long)(rmem->size / SZ_1K),
-					nomap ? "nomap" : "map",
-					reusable ? "reusable" : "non-reusable",
-					rmem->name ? rmem->name : "unknown");
-			}
-		}
+	err = __reserved_mem_init_node(rmem);
+	if (err != 0 && err != -ENOENT) {
+		pr_info("node %s compatible matching fail\n", rmem->name);
+		if (nomap)
+			memblock_clear_nomap(rmem->base, rmem->size);
+		else
+			memblock_phys_free(rmem->base, rmem->size);
+	} else {
+		phys_addr_t end = rmem->base + rmem->size - 1;
+		bool reusable =
+			(of_get_flat_dt_prop(node, "reusable", NULL)) != NULL;
+
+		pr_info("%pa..%pa (%lu KiB) %s %s %s\n",
+			&rmem->base, &end, (unsigned long)(rmem->size / SZ_1K),
+			nomap ? "nomap" : "map",
+			reusable ? "reusable" : "non-reusable",
+			rmem->name ? rmem->name : "unknown");
 	}
 }
 
diff --git a/drivers/of/property.c b/drivers/of/property.c
index 7bd8390f2fba..906a33ae717f 100644
--- a/drivers/of/property.c
+++ b/drivers/of/property.c
@@ -1317,9 +1317,9 @@ static struct device_node *parse_interrupt_map(struct device_node *np,
 	addrcells = of_bus_n_addr_cells(np);
 
 	imap = of_get_property(np, "interrupt-map", &imaplen);
-	imaplen /= sizeof(*imap);
 	if (!imap)
 		return NULL;
+	imaplen /= sizeof(*imap);
 
 	imap_end = imap + imaplen;
 
diff --git a/drivers/of/resolver.c b/drivers/of/resolver.c
index 5cf96776dd7d..7d935908b543 100644
--- a/drivers/of/resolver.c
+++ b/drivers/of/resolver.c
@@ -249,25 +249,22 @@ static int adjust_local_phandle_references(struct device_node *local_fixups,
  */
 int of_resolve_phandles(struct device_node *overlay)
 {
-	struct device_node *child, *local_fixups, *refnode;
-	struct device_node *tree_symbols, *overlay_fixups;
+	struct device_node *child, *refnode;
+	struct device_node *overlay_fixups;
+	struct device_node __free(device_node) *local_fixups = NULL;
 	struct property *prop;
 	const char *refpath;
 	phandle phandle, phandle_delta;
 	int err;
 
-	tree_symbols = NULL;
-
 	if (!overlay) {
 		pr_err("null overlay\n");
-		err = -EINVAL;
-		goto out;
+		return -EINVAL;
 	}
 
 	if (!of_node_check_flag(overlay, OF_DETACHED)) {
 		pr_err("overlay not detached\n");
-		err = -EINVAL;
-		goto out;
+		return -EINVAL;
 	}
 
 	phandle_delta = live_tree_max_phandle() + 1;
@@ -279,7 +276,7 @@ int of_resolve_phandles(struct device_node *overlay)
 
 	err = adjust_local_phandle_references(local_fixups, overlay, phandle_delta);
 	if (err)
-		goto out;
+		return err;
 
 	overlay_fixups = NULL;
 
@@ -288,16 +285,13 @@ int of_resolve_phandles(struct device_node *overlay)
 			overlay_fixups = child;
 	}
 
-	if (!overlay_fixups) {
-		err = 0;
-		goto out;
-	}
+	if (!overlay_fixups)
+		return 0;
 
-	tree_symbols = of_find_node_by_path("/__symbols__");
+	struct device_node __free(device_node) *tree_symbols = of_find_node_by_path("/__symbols__");
 	if (!tree_symbols) {
 		pr_err("no symbols in root of device tree.\n");
-		err = -EINVAL;
-		goto out;
+		return -EINVAL;
 	}
 
 	for_each_property_of_node(overlay_fixups, prop) {
@@ -311,14 +305,12 @@ int of_resolve_phandles(struct device_node *overlay)
 		if (err) {
 			pr_err("node label '%s' not found in live devicetree symbols table\n",
 			       prop->name);
-			goto out;
+			return err;
 		}
 
 		refnode = of_find_node_by_path(refpath);
-		if (!refnode) {
-			err = -ENOENT;
-			goto out;
-		}
+		if (!refnode)
+			return -ENOENT;
 
 		phandle = refnode->phandle;
 		of_node_put(refnode);
@@ -328,11 +320,8 @@ int of_resolve_phandles(struct device_node *overlay)
 			break;
 	}
 
-out:
 	if (err)
 		pr_err("overlay phandle fixup failed: %d\n", err);
-	of_node_put(tree_symbols);
-
 	return err;
 }
 EXPORT_SYMBOL_GPL(of_resolve_phandles);
diff --git a/drivers/of/unittest-data/tests-platform.dtsi b/drivers/of/unittest-data/tests-platform.dtsi
index fa39611071b3..cd310b26b50c 100644
--- a/drivers/of/unittest-data/tests-platform.dtsi
+++ b/drivers/of/unittest-data/tests-platform.dtsi
@@ -34,5 +34,18 @@
 				};
 			};
 		};
+
+		platform-tests-2 {
+			// No #address-cells or #size-cells
+			node {
+				#address-cells = <1>;
+				#size-cells = <1>;
+
+				test-device@100 {
+					compatible = "test-sub-device";
+					reg = <0x100 1>;
+				};
+			};
+		};
 	};
 };
diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c
index daf9a2dddd7e..9a72f75e5c2d 100644
--- a/drivers/of/unittest.c
+++ b/drivers/of/unittest.c
@@ -1342,6 +1342,7 @@ static void __init of_unittest_bus_3cell_ranges(void)
 static void __init of_unittest_reg(void)
 {
 	struct device_node *np;
+	struct resource res;
 	int ret;
 	u64 addr, size;
 
@@ -1358,6 +1359,19 @@ static void __init of_unittest_reg(void)
 		np, addr);
 
 	of_node_put(np);
+
+	np = of_find_node_by_path("/testcase-data/platform-tests-2/node/test-device@100");
+	if (!np) {
+		pr_err("missing testcase data\n");
+		return;
+	}
+
+	ret = of_address_to_resource(np, 0, &res);
+	unittest(ret == -EINVAL, "of_address_to_resource(%pOF) expected error on untranslatable address\n",
+		 np);
+
+	of_node_put(np);
+
 }
 
 struct of_unittest_expected_res {
@@ -1902,15 +1916,16 @@ static int __init unittest_data_add(void)
 	rc = of_resolve_phandles(unittest_data_node);
 	if (rc) {
 		pr_err("%s: Failed to resolve phandles (rc=%i)\n", __func__, rc);
-		of_overlay_mutex_unlock();
-		return -EINVAL;
+		rc = -EINVAL;
+		goto unlock;
 	}
 
 	/* attach the sub-tree to live tree */
 	if (!of_root) {
 		pr_warn("%s: no live tree to attach sub-tree\n", __func__);
 		kfree(unittest_data);
-		return -ENODEV;
+		rc = -ENODEV;
+		goto unlock;
 	}
 
 	EXPECT_BEGIN(KERN_INFO,
@@ -1929,9 +1944,10 @@ static int __init unittest_data_add(void)
 	EXPECT_END(KERN_INFO,
 		   "Duplicate name in testcase-data, renamed to \"duplicate-name#1\"");
 
+unlock:
 	of_overlay_mutex_unlock();
 
-	return 0;
+	return rc;
 }
 
 #ifdef CONFIG_OF_OVERLAY
diff --git a/drivers/opp/core.c b/drivers/opp/core.c
index 3aa18737470f..5ac209472c0c 100644
--- a/drivers/opp/core.c
+++ b/drivers/opp/core.c
@@ -101,11 +101,30 @@ struct opp_table *_find_opp_table(struct device *dev)
  * representation in the OPP table and manage the clock configuration themselves
  * in an platform specific way.
  */
-static bool assert_single_clk(struct opp_table *opp_table)
+static bool assert_single_clk(struct opp_table *opp_table,
+			      unsigned int __always_unused index)
 {
 	return !WARN_ON(opp_table->clk_count > 1);
 }
 
+/*
+ * Returns true if clock table is large enough to contain the clock index.
+ */
+static bool assert_clk_index(struct opp_table *opp_table,
+			     unsigned int index)
+{
+	return opp_table->clk_count > index;
+}
+
+/*
+ * Returns true if bandwidth table is large enough to contain the bandwidth index.
+ */
+static bool assert_bandwidth_index(struct opp_table *opp_table,
+				   unsigned int index)
+{
+	return opp_table->path_count > index;
+}
+
 /**
  * dev_pm_opp_get_voltage() - Gets the voltage corresponding to an opp
  * @opp:	opp for which voltage has to be returned for
@@ -499,12 +518,12 @@ static struct dev_pm_opp *_opp_table_find_key(struct opp_table *opp_table,
 		unsigned long (*read)(struct dev_pm_opp *opp, int index),
 		bool (*compare)(struct dev_pm_opp **opp, struct dev_pm_opp *temp_opp,
 				unsigned long opp_key, unsigned long key),
-		bool (*assert)(struct opp_table *opp_table))
+		bool (*assert)(struct opp_table *opp_table, unsigned int index))
 {
 	struct dev_pm_opp *temp_opp, *opp = ERR_PTR(-ERANGE);
 
 	/* Assert that the requirement is met */
-	if (assert && !assert(opp_table))
+	if (assert && !assert(opp_table, index))
 		return ERR_PTR(-EINVAL);
 
 	mutex_lock(&opp_table->lock);
@@ -532,7 +551,7 @@ _find_key(struct device *dev, unsigned long *key, int index, bool available,
 	  unsigned long (*read)(struct dev_pm_opp *opp, int index),
 	  bool (*compare)(struct dev_pm_opp **opp, struct dev_pm_opp *temp_opp,
 			  unsigned long opp_key, unsigned long key),
-	  bool (*assert)(struct opp_table *opp_table))
+	  bool (*assert)(struct opp_table *opp_table, unsigned int index))
 {
 	struct opp_table *opp_table;
 	struct dev_pm_opp *opp;
@@ -555,7 +574,7 @@ _find_key(struct device *dev, unsigned long *key, int index, bool available,
 static struct dev_pm_opp *_find_key_exact(struct device *dev,
 		unsigned long key, int index, bool available,
 		unsigned long (*read)(struct dev_pm_opp *opp, int index),
-		bool (*assert)(struct opp_table *opp_table))
+		bool (*assert)(struct opp_table *opp_table, unsigned int index))
 {
 	/*
 	 * The value of key will be updated here, but will be ignored as the
@@ -568,7 +587,7 @@ static struct dev_pm_opp *_find_key_exact(struct device *dev,
 static struct dev_pm_opp *_opp_table_find_key_ceil(struct opp_table *opp_table,
 		unsigned long *key, int index, bool available,
 		unsigned long (*read)(struct dev_pm_opp *opp, int index),
-		bool (*assert)(struct opp_table *opp_table))
+		bool (*assert)(struct opp_table *opp_table, unsigned int index))
 {
 	return _opp_table_find_key(opp_table, key, index, available, read,
 				   _compare_ceil, assert);
@@ -577,7 +596,7 @@ static struct dev_pm_opp *_opp_table_find_key_ceil(struct opp_table *opp_table,
 static struct dev_pm_opp *_find_key_ceil(struct device *dev, unsigned long *key,
 		int index, bool available,
 		unsigned long (*read)(struct dev_pm_opp *opp, int index),
-		bool (*assert)(struct opp_table *opp_table))
+		bool (*assert)(struct opp_table *opp_table, unsigned int index))
 {
 	return _find_key(dev, key, index, available, read, _compare_ceil,
 			 assert);
@@ -586,7 +605,7 @@ static struct dev_pm_opp *_find_key_ceil(struct device *dev, unsigned long *key,
 static struct dev_pm_opp *_find_key_floor(struct device *dev,
 		unsigned long *key, int index, bool available,
 		unsigned long (*read)(struct dev_pm_opp *opp, int index),
-		bool (*assert)(struct opp_table *opp_table))
+		bool (*assert)(struct opp_table *opp_table, unsigned int index))
 {
 	return _find_key(dev, key, index, available, read, _compare_floor,
 			 assert);
@@ -647,7 +666,8 @@ struct dev_pm_opp *
 dev_pm_opp_find_freq_exact_indexed(struct device *dev, unsigned long freq,
 				   u32 index, bool available)
 {
-	return _find_key_exact(dev, freq, index, available, _read_freq, NULL);
+	return _find_key_exact(dev, freq, index, available, _read_freq,
+			       assert_clk_index);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_find_freq_exact_indexed);
 
@@ -707,7 +727,8 @@ struct dev_pm_opp *
 dev_pm_opp_find_freq_ceil_indexed(struct device *dev, unsigned long *freq,
 				  u32 index)
 {
-	return _find_key_ceil(dev, freq, index, true, _read_freq, NULL);
+	return _find_key_ceil(dev, freq, index, true, _read_freq,
+			      assert_clk_index);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_find_freq_ceil_indexed);
 
@@ -760,7 +781,7 @@ struct dev_pm_opp *
 dev_pm_opp_find_freq_floor_indexed(struct device *dev, unsigned long *freq,
 				   u32 index)
 {
-	return _find_key_floor(dev, freq, index, true, _read_freq, NULL);
+	return _find_key_floor(dev, freq, index, true, _read_freq, assert_clk_index);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_find_freq_floor_indexed);
 
@@ -878,7 +899,8 @@ struct dev_pm_opp *dev_pm_opp_find_bw_ceil(struct device *dev, unsigned int *bw,
 	unsigned long temp = *bw;
 	struct dev_pm_opp *opp;
 
-	opp = _find_key_ceil(dev, &temp, index, true, _read_bw, NULL);
+	opp = _find_key_ceil(dev, &temp, index, true, _read_bw,
+			     assert_bandwidth_index);
 	*bw = temp;
 	return opp;
 }
@@ -909,7 +931,8 @@ struct dev_pm_opp *dev_pm_opp_find_bw_floor(struct device *dev,
 	unsigned long temp = *bw;
 	struct dev_pm_opp *opp;
 
-	opp = _find_key_floor(dev, &temp, index, true, _read_bw, NULL);
+	opp = _find_key_floor(dev, &temp, index, true, _read_bw,
+			      assert_bandwidth_index);
 	*bw = temp;
 	return opp;
 }
@@ -1702,7 +1725,7 @@ void dev_pm_opp_remove(struct device *dev, unsigned long freq)
 	if (IS_ERR(opp_table))
 		return;
 
-	if (!assert_single_clk(opp_table))
+	if (!assert_single_clk(opp_table, 0))
 		goto put_table;
 
 	mutex_lock(&opp_table->lock);
@@ -2054,7 +2077,7 @@ int _opp_add_v1(struct opp_table *opp_table, struct device *dev,
 	unsigned long tol, u_volt = data->u_volt;
 	int ret;
 
-	if (!assert_single_clk(opp_table))
+	if (!assert_single_clk(opp_table, 0))
 		return -EINVAL;
 
 	new_opp = _opp_allocate(opp_table);
@@ -2911,7 +2934,7 @@ static int _opp_set_availability(struct device *dev, unsigned long freq,
 		return r;
 	}
 
-	if (!assert_single_clk(opp_table)) {
+	if (!assert_single_clk(opp_table, 0)) {
 		r = -EINVAL;
 		goto put_table;
 	}
@@ -2987,7 +3010,7 @@ int dev_pm_opp_adjust_voltage(struct device *dev, unsigned long freq,
 		return r;
 	}
 
-	if (!assert_single_clk(opp_table)) {
+	if (!assert_single_clk(opp_table, 0)) {
 		r = -EINVAL;
 		goto put_table;
 	}
diff --git a/drivers/opp/of.c b/drivers/opp/of.c
index 55c8cfef97d4..dcab0e7ace10 100644
--- a/drivers/opp/of.c
+++ b/drivers/opp/of.c
@@ -959,7 +959,7 @@ static struct dev_pm_opp *_opp_add_static_v2(struct opp_table *opp_table,
 
 	ret = _of_opp_alloc_required_opps(opp_table, new_opp);
 	if (ret)
-		goto free_opp;
+		goto put_node;
 
 	if (!of_property_read_u32(np, "clock-latency-ns", &val))
 		new_opp->clock_latency_ns = val;
@@ -1009,6 +1009,8 @@ static struct dev_pm_opp *_opp_add_static_v2(struct opp_table *opp_table,
 
 free_required_opps:
 	_of_opp_free_required_opps(opp_table, new_opp);
+put_node:
+	of_node_put(np);
 free_opp:
 	_opp_free(new_opp);
 
diff --git a/drivers/parport/parport_serial.c b/drivers/parport/parport_serial.c
index 3644997a8342..24d4f3a3ec3d 100644
--- a/drivers/parport/parport_serial.c
+++ b/drivers/parport/parport_serial.c
@@ -266,10 +266,14 @@ static struct pci_device_id parport_serial_pci_tbl[] = {
 	{ 0x1409, 0x7168, 0x1409, 0xd079, 0, 0, timedia_9079c },
 
 	/* WCH CARDS */
-	{ 0x4348, 0x5053, PCI_ANY_ID, PCI_ANY_ID, 0, 0, wch_ch353_1s1p},
-	{ 0x4348, 0x7053, 0x4348, 0x3253, 0, 0, wch_ch353_2s1p},
-	{ 0x1c00, 0x3050, 0x1c00, 0x3050, 0, 0, wch_ch382_0s1p},
-	{ 0x1c00, 0x3250, 0x1c00, 0x3250, 0, 0, wch_ch382_2s1p},
+	{ PCI_VENDOR_ID_WCHCN, PCI_DEVICE_ID_WCHCN_CH353_1S1P,
+	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, wch_ch353_1s1p },
+	{ PCI_VENDOR_ID_WCHCN, PCI_DEVICE_ID_WCHCN_CH353_2S1P,
+	  0x4348, 0x3253, 0, 0, wch_ch353_2s1p },
+	{ PCI_VENDOR_ID_WCHIC, PCI_DEVICE_ID_WCHIC_CH382_0S1P,
+	  0x1c00, 0x3050, 0, 0, wch_ch382_0s1p },
+	{ PCI_VENDOR_ID_WCHIC, PCI_DEVICE_ID_WCHIC_CH382_2S1P,
+	  0x1c00, 0x3250, 0, 0, wch_ch382_2s1p },
 
 	/* BrainBoxes PX272/PX306 MIO card */
 	{ PCI_VENDOR_ID_INTASHIELD, 0x4100,
diff --git a/drivers/pci/Kconfig b/drivers/pci/Kconfig
index 0d94e4a967d8..7cef00d9d7ab 100644
--- a/drivers/pci/Kconfig
+++ b/drivers/pci/Kconfig
@@ -194,6 +194,12 @@ config PCI_P2PDMA
 	  P2P DMA transactions must be between devices behind the same root
 	  port.
 
+	  Enabling this option will reduce the entropy of x86 KASLR memory
+	  regions. For example - on a 46 bit system, the entropy goes down
+	  from 16 bits to 15 bits. The actual reduction in entropy depends
+	  on the physical address bits, on processor features, kernel config
+	  (5 level page table) and physical memory present on the system.
+
 	  If unsure, say N.
 
 config PCI_LABEL
diff --git a/drivers/pci/ats.c b/drivers/pci/ats.c
index 6afff1f1b143..c331b108e71d 100644
--- a/drivers/pci/ats.c
+++ b/drivers/pci/ats.c
@@ -538,4 +538,37 @@ int pci_max_pasids(struct pci_dev *pdev)
 	return (1 << FIELD_GET(PCI_PASID_CAP_WIDTH, supported));
 }
 EXPORT_SYMBOL_GPL(pci_max_pasids);
+
+/**
+ * pci_pasid_status - Check the PASID status
+ * @pdev: PCI device structure
+ *
+ * Returns a negative value when no PASID capability is present.
+ * Otherwise the value of the control register is returned.
+ * Status reported are:
+ *
+ * PCI_PASID_CTRL_ENABLE - PASID enabled
+ * PCI_PASID_CTRL_EXEC - Execute permission enabled
+ * PCI_PASID_CTRL_PRIV - Privileged mode enabled
+ */
+int pci_pasid_status(struct pci_dev *pdev)
+{
+	int pasid;
+	u16 ctrl;
+
+	if (pdev->is_virtfn)
+		pdev = pci_physfn(pdev);
+
+	pasid = pdev->pasid_cap;
+	if (!pasid)
+		return -EINVAL;
+
+	pci_read_config_word(pdev, pasid + PCI_PASID_CTRL, &ctrl);
+
+	ctrl &= PCI_PASID_CTRL_ENABLE | PCI_PASID_CTRL_EXEC |
+		PCI_PASID_CTRL_PRIV;
+
+	return ctrl;
+}
+EXPORT_SYMBOL_GPL(pci_pasid_status);
 #endif /* CONFIG_PCI_PASID */
diff --git a/drivers/pci/controller/cadence/pci-j721e.c b/drivers/pci/controller/cadence/pci-j721e.c
index e091c3e55b5c..bae829ac759e 100644
--- a/drivers/pci/controller/cadence/pci-j721e.c
+++ b/drivers/pci/controller/cadence/pci-j721e.c
@@ -355,6 +355,7 @@ static const struct j721e_pcie_data j7200_pcie_rc_data = {
 static const struct j721e_pcie_data j7200_pcie_ep_data = {
 	.mode = PCI_MODE_EP,
 	.quirk_detect_quiet_flag = true,
+	.linkdown_irq_regfield = J7200_LINK_DOWN,
 	.quirk_disable_flr = true,
 	.max_lanes = 2,
 };
@@ -376,13 +377,13 @@ static const struct j721e_pcie_data j784s4_pcie_rc_data = {
 	.mode = PCI_MODE_RC,
 	.quirk_retrain_flag = true,
 	.byte_access_allowed = false,
-	.linkdown_irq_regfield = LINK_DOWN,
+	.linkdown_irq_regfield = J7200_LINK_DOWN,
 	.max_lanes = 4,
 };
 
 static const struct j721e_pcie_data j784s4_pcie_ep_data = {
 	.mode = PCI_MODE_EP,
-	.linkdown_irq_regfield = LINK_DOWN,
+	.linkdown_irq_regfield = J7200_LINK_DOWN,
 	.max_lanes = 4,
 };
 
diff --git a/drivers/pci/controller/cadence/pcie-cadence-ep.c b/drivers/pci/controller/cadence/pcie-cadence-ep.c
index e0cc4560dfde..f700e8c49082 100644
--- a/drivers/pci/controller/cadence/pcie-cadence-ep.c
+++ b/drivers/pci/controller/cadence/pcie-cadence-ep.c
@@ -292,13 +292,14 @@ static int cdns_pcie_ep_set_msix(struct pci_epc *epc, u8 fn, u8 vfn,
 	struct cdns_pcie *pcie = &ep->pcie;
 	u32 cap = CDNS_PCIE_EP_FUNC_MSIX_CAP_OFFSET;
 	u32 val, reg;
+	u16 actual_interrupts = interrupts + 1;
 
 	fn = cdns_pcie_get_fn_from_vfn(pcie, fn, vfn);
 
 	reg = cap + PCI_MSIX_FLAGS;
 	val = cdns_pcie_ep_fn_readw(pcie, fn, reg);
 	val &= ~PCI_MSIX_FLAGS_QSIZE;
-	val |= interrupts;
+	val |= interrupts; /* 0's based value */
 	cdns_pcie_ep_fn_writew(pcie, fn, reg, val);
 
 	/* Set MSIX BAR and offset */
@@ -308,7 +309,7 @@ static int cdns_pcie_ep_set_msix(struct pci_epc *epc, u8 fn, u8 vfn,
 
 	/* Set PBA BAR and offset.  BAR must match MSIX BAR */
 	reg = cap + PCI_MSIX_PBA;
-	val = (offset + (interrupts * PCI_MSIX_ENTRY_SIZE)) | bir;
+	val = (offset + (actual_interrupts * PCI_MSIX_ENTRY_SIZE)) | bir;
 	cdns_pcie_ep_fn_writel(pcie, fn, reg, val);
 
 	return 0;
@@ -352,8 +353,7 @@ static void cdns_pcie_ep_assert_intx(struct cdns_pcie_ep *ep, u8 fn, u8 intx,
 	spin_unlock_irqrestore(&ep->lock, flags);
 
 	offset = CDNS_PCIE_NORMAL_MSG_ROUTING(MSG_ROUTING_LOCAL) |
-		 CDNS_PCIE_NORMAL_MSG_CODE(msg_code) |
-		 CDNS_PCIE_MSG_NO_DATA;
+		 CDNS_PCIE_NORMAL_MSG_CODE(msg_code);
 	writel(0, ep->irq_cpu_addr + offset);
 }
 
diff --git a/drivers/pci/controller/cadence/pcie-cadence-host.c b/drivers/pci/controller/cadence/pcie-cadence-host.c
index 8af95e9da7ce..741e10a575ec 100644
--- a/drivers/pci/controller/cadence/pcie-cadence-host.c
+++ b/drivers/pci/controller/cadence/pcie-cadence-host.c
@@ -570,14 +570,5 @@ int cdns_pcie_host_setup(struct cdns_pcie_rc *rc)
 	if (!bridge->ops)
 		bridge->ops = &cdns_pcie_host_ops;
 
-	ret = pci_host_probe(bridge);
-	if (ret < 0)
-		goto err_init;
-
-	return 0;
-
- err_init:
-	pm_runtime_put_sync(dev);
-
-	return ret;
+	return pci_host_probe(bridge);
 }
diff --git a/drivers/pci/controller/cadence/pcie-cadence.h b/drivers/pci/controller/cadence/pcie-cadence.h
index f5eeff834ec1..39ee9945c903 100644
--- a/drivers/pci/controller/cadence/pcie-cadence.h
+++ b/drivers/pci/controller/cadence/pcie-cadence.h
@@ -246,7 +246,7 @@ struct cdns_pcie_rp_ib_bar {
 #define CDNS_PCIE_NORMAL_MSG_CODE_MASK		GENMASK(15, 8)
 #define CDNS_PCIE_NORMAL_MSG_CODE(code) \
 	(((code) << 8) & CDNS_PCIE_NORMAL_MSG_CODE_MASK)
-#define CDNS_PCIE_MSG_NO_DATA			BIT(16)
+#define CDNS_PCIE_MSG_DATA			BIT(16)
 
 struct cdns_pcie;
 
diff --git a/drivers/pci/controller/dwc/pci-imx6.c b/drivers/pci/controller/dwc/pci-imx6.c
index c8d5c90aa4d4..3b24fed3177d 100644
--- a/drivers/pci/controller/dwc/pci-imx6.c
+++ b/drivers/pci/controller/dwc/pci-imx6.c
@@ -48,6 +48,8 @@
 #define IMX95_PCIE_SS_RW_REG_0			0xf0
 #define IMX95_PCIE_REF_CLKEN			BIT(23)
 #define IMX95_PCIE_PHY_CR_PARA_SEL		BIT(9)
+#define IMX95_PCIE_SS_RW_REG_1			0xf4
+#define IMX95_PCIE_SYS_AUX_PWR_DET		BIT(31)
 
 #define IMX95_PE0_GEN_CTRL_1			0x1050
 #define IMX95_PCIE_DEVICE_TYPE			GENMASK(3, 0)
@@ -206,6 +208,19 @@ static unsigned int imx_pcie_grp_offset(const struct imx_pcie *imx_pcie)
 
 static int imx95_pcie_init_phy(struct imx_pcie *imx_pcie)
 {
+	/*
+	 * ERR051624: The Controller Without Vaux Cannot Exit L23 Ready
+	 * Through Beacon or PERST# De-assertion
+	 *
+	 * When the auxiliary power is not available, the controller
+	 * cannot exit from L23 Ready with beacon or PERST# de-assertion
+	 * when main power is not removed.
+	 *
+	 * Workaround: Set SS_RW_REG_1[SYS_AUX_PWR_DET] to 1.
+	 */
+	regmap_set_bits(imx_pcie->iomuxc_gpr, IMX95_PCIE_SS_RW_REG_1,
+			IMX95_PCIE_SYS_AUX_PWR_DET);
+
 	regmap_update_bits(imx_pcie->iomuxc_gpr,
 			IMX95_PCIE_SS_RW_REG_0,
 			IMX95_PCIE_PHY_CR_PARA_SEL,
@@ -598,10 +613,9 @@ static int imx_pcie_attach_pd(struct device *dev)
 
 static int imx6sx_pcie_enable_ref_clk(struct imx_pcie *imx_pcie, bool enable)
 {
-	if (enable)
-		regmap_clear_bits(imx_pcie->iomuxc_gpr, IOMUXC_GPR12,
-				  IMX6SX_GPR12_PCIE_TEST_POWERDOWN);
-
+	regmap_update_bits(imx_pcie->iomuxc_gpr, IOMUXC_GPR12,
+			   IMX6SX_GPR12_PCIE_TEST_POWERDOWN,
+			   enable ? 0 : IMX6SX_GPR12_PCIE_TEST_POWERDOWN);
 	return 0;
 }
 
@@ -630,19 +644,20 @@ static int imx8mm_pcie_enable_ref_clk(struct imx_pcie *imx_pcie, bool enable)
 {
 	int offset = imx_pcie_grp_offset(imx_pcie);
 
-	if (enable) {
-		regmap_clear_bits(imx_pcie->iomuxc_gpr, offset, IMX8MQ_GPR_PCIE_CLK_REQ_OVERRIDE);
-		regmap_set_bits(imx_pcie->iomuxc_gpr, offset, IMX8MQ_GPR_PCIE_CLK_REQ_OVERRIDE_EN);
-	}
-
+	regmap_update_bits(imx_pcie->iomuxc_gpr, offset,
+			   IMX8MQ_GPR_PCIE_CLK_REQ_OVERRIDE,
+			   enable ? 0 : IMX8MQ_GPR_PCIE_CLK_REQ_OVERRIDE);
+	regmap_update_bits(imx_pcie->iomuxc_gpr, offset,
+			   IMX8MQ_GPR_PCIE_CLK_REQ_OVERRIDE_EN,
+			   enable ? IMX8MQ_GPR_PCIE_CLK_REQ_OVERRIDE_EN : 0);
 	return 0;
 }
 
 static int imx7d_pcie_enable_ref_clk(struct imx_pcie *imx_pcie, bool enable)
 {
-	if (!enable)
-		regmap_set_bits(imx_pcie->iomuxc_gpr, IOMUXC_GPR12,
-				IMX7D_GPR12_PCIE_PHY_REFCLK_SEL);
+	regmap_update_bits(imx_pcie->iomuxc_gpr, IOMUXC_GPR12,
+			   IMX7D_GPR12_PCIE_PHY_REFCLK_SEL,
+			   enable ? 0 : IMX7D_GPR12_PCIE_PHY_REFCLK_SEL);
 	return 0;
 }
 
@@ -775,6 +790,7 @@ static void imx_pcie_assert_core_reset(struct imx_pcie *imx_pcie)
 static int imx_pcie_deassert_core_reset(struct imx_pcie *imx_pcie)
 {
 	reset_control_deassert(imx_pcie->pciephy_reset);
+	reset_control_deassert(imx_pcie->apps_reset);
 
 	if (imx_pcie->drvdata->core_reset)
 		imx_pcie->drvdata->core_reset(imx_pcie, false);
@@ -966,7 +982,9 @@ static int imx_pcie_host_init(struct dw_pcie_rp *pp)
 			goto err_clk_disable;
 		}
 
-		ret = phy_set_mode_ext(imx_pcie->phy, PHY_MODE_PCIE, PHY_MODE_PCIE_RC);
+		ret = phy_set_mode_ext(imx_pcie->phy, PHY_MODE_PCIE,
+				       imx_pcie->drvdata->mode == DW_PCIE_EP_TYPE ?
+						PHY_MODE_PCIE_EP : PHY_MODE_PCIE_RC);
 		if (ret) {
 			dev_err(dev, "unable to set PCIe PHY mode\n");
 			goto err_phy_exit;
@@ -1391,7 +1409,6 @@ static int imx_pcie_probe(struct platform_device *pdev)
 	switch (imx_pcie->drvdata->variant) {
 	case IMX8MQ:
 	case IMX8MQ_EP:
-	case IMX7D:
 		if (dbi_base->start == IMX8MQ_PCIE2_BASE_ADDR)
 			imx_pcie->controller_id = 1;
 		break;
diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c b/drivers/pci/controller/dwc/pcie-designware-ep.c
index cc8ff4a01436..00289948f9c1 100644
--- a/drivers/pci/controller/dwc/pcie-designware-ep.c
+++ b/drivers/pci/controller/dwc/pcie-designware-ep.c
@@ -222,19 +222,30 @@ static int dw_pcie_ep_set_bar(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 	if ((flags & PCI_BASE_ADDRESS_MEM_TYPE_64) && (bar & 1))
 		return -EINVAL;
 
-	reg = PCI_BASE_ADDRESS_0 + (4 * bar);
-
-	if (!(flags & PCI_BASE_ADDRESS_SPACE))
-		type = PCIE_ATU_TYPE_MEM;
-	else
-		type = PCIE_ATU_TYPE_IO;
+	/*
+	 * Certain EPF drivers dynamically change the physical address of a BAR
+	 * (i.e. they call set_bar() twice, without ever calling clear_bar(), as
+	 * calling clear_bar() would clear the BAR's PCI address assigned by the
+	 * host).
+	 */
+	if (ep->epf_bar[bar]) {
+		/*
+		 * We can only dynamically change a BAR if the new BAR size and
+		 * BAR flags do not differ from the existing configuration.
+		 */
+		if (ep->epf_bar[bar]->barno != bar ||
+		    ep->epf_bar[bar]->size != size ||
+		    ep->epf_bar[bar]->flags != flags)
+			return -EINVAL;
 
-	ret = dw_pcie_ep_inbound_atu(ep, func_no, type, epf_bar->phys_addr, bar);
-	if (ret)
-		return ret;
+		/*
+		 * When dynamically changing a BAR, skip writing the BAR reg, as
+		 * that would clear the BAR's PCI address assigned by the host.
+		 */
+		goto config_atu;
+	}
 
-	if (ep->epf_bar[bar])
-		return 0;
+	reg = PCI_BASE_ADDRESS_0 + (4 * bar);
 
 	dw_pcie_dbi_ro_wr_en(pci);
 
@@ -246,9 +257,20 @@ static int dw_pcie_ep_set_bar(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 		dw_pcie_ep_writel_dbi(ep, func_no, reg + 4, 0);
 	}
 
-	ep->epf_bar[bar] = epf_bar;
 	dw_pcie_dbi_ro_wr_dis(pci);
 
+config_atu:
+	if (!(flags & PCI_BASE_ADDRESS_SPACE))
+		type = PCIE_ATU_TYPE_MEM;
+	else
+		type = PCIE_ATU_TYPE_IO;
+
+	ret = dw_pcie_ep_inbound_atu(ep, func_no, type, epf_bar->phys_addr, bar);
+	if (ret)
+		return ret;
+
+	ep->epf_bar[bar] = epf_bar;
+
 	return 0;
 }
 
@@ -258,7 +280,7 @@ static int dw_pcie_find_index(struct dw_pcie_ep *ep, phys_addr_t addr,
 	u32 index;
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
 
-	for (index = 0; index < pci->num_ob_windows; index++) {
+	for_each_set_bit(index, ep->ob_window_map, pci->num_ob_windows) {
 		if (ep->outbound_addr[index] != addr)
 			continue;
 		*atu_index = index;
@@ -376,6 +398,7 @@ static int dw_pcie_ep_set_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
 	struct dw_pcie_ep_func *ep_func;
 	u32 val, reg;
+	u16 actual_interrupts = interrupts + 1;
 
 	ep_func = dw_pcie_ep_get_func_from_ep(ep, func_no);
 	if (!ep_func || !ep_func->msix_cap)
@@ -386,7 +409,7 @@ static int dw_pcie_ep_set_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 	reg = ep_func->msix_cap + PCI_MSIX_FLAGS;
 	val = dw_pcie_ep_readw_dbi(ep, func_no, reg);
 	val &= ~PCI_MSIX_FLAGS_QSIZE;
-	val |= interrupts;
+	val |= interrupts; /* 0's based value */
 	dw_pcie_writew_dbi(pci, reg, val);
 
 	reg = ep_func->msix_cap + PCI_MSIX_TABLE;
@@ -394,7 +417,7 @@ static int dw_pcie_ep_set_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 	dw_pcie_ep_writel_dbi(ep, func_no, reg, val);
 
 	reg = ep_func->msix_cap + PCI_MSIX_PBA;
-	val = (offset + (interrupts * PCI_MSIX_ENTRY_SIZE)) | bir;
+	val = (offset + (actual_interrupts * PCI_MSIX_ENTRY_SIZE)) | bir;
 	dw_pcie_ep_writel_dbi(ep, func_no, reg, val);
 
 	dw_pcie_dbi_ro_wr_dis(pci);
@@ -733,6 +756,7 @@ int dw_pcie_ep_init_registers(struct dw_pcie_ep *ep)
 	if (ret)
 		return ret;
 
+	ret = -ENOMEM;
 	if (!ep->ib_window_map) {
 		ep->ib_window_map = devm_bitmap_zalloc(dev, pci->num_ib_windows,
 						       GFP_KERNEL);
diff --git a/drivers/pci/controller/dwc/pcie-designware-host.c b/drivers/pci/controller/dwc/pcie-designware-host.c
index 3e41865c7290..d428457d9c43 100644
--- a/drivers/pci/controller/dwc/pcie-designware-host.c
+++ b/drivers/pci/controller/dwc/pcie-designware-host.c
@@ -902,7 +902,7 @@ static int dw_pcie_pme_turn_off(struct dw_pcie *pci)
 	if (ret)
 		return ret;
 
-	mem = ioremap(atu.cpu_addr, pci->region_align);
+	mem = ioremap(pci->pp.msg_res->start, pci->region_align);
 	if (!mem)
 		return -ENOMEM;
 
@@ -946,6 +946,7 @@ int dw_pcie_suspend_noirq(struct dw_pcie *pci)
 		return ret;
 	}
 
+	dw_pcie_stop_link(pci);
 	if (pci->pp.ops->deinit)
 		pci->pp.ops->deinit(&pci->pp);
 
diff --git a/drivers/pci/controller/dwc/pcie-designware.c b/drivers/pci/controller/dwc/pcie-designware.c
index 6d6cbc8b5b2c..d40afe74ddd1 100644
--- a/drivers/pci/controller/dwc/pcie-designware.c
+++ b/drivers/pci/controller/dwc/pcie-designware.c
@@ -752,22 +752,19 @@ static void dw_pcie_link_set_max_link_width(struct dw_pcie *pci, u32 num_lanes)
 	/* Set link width speed control register */
 	lwsc = dw_pcie_readl_dbi(pci, PCIE_LINK_WIDTH_SPEED_CONTROL);
 	lwsc &= ~PORT_LOGIC_LINK_WIDTH_MASK;
+	lwsc |= PORT_LOGIC_LINK_WIDTH_1_LANES;
 	switch (num_lanes) {
 	case 1:
 		plc |= PORT_LINK_MODE_1_LANES;
-		lwsc |= PORT_LOGIC_LINK_WIDTH_1_LANES;
 		break;
 	case 2:
 		plc |= PORT_LINK_MODE_2_LANES;
-		lwsc |= PORT_LOGIC_LINK_WIDTH_2_LANES;
 		break;
 	case 4:
 		plc |= PORT_LINK_MODE_4_LANES;
-		lwsc |= PORT_LOGIC_LINK_WIDTH_4_LANES;
 		break;
 	case 8:
 		plc |= PORT_LINK_MODE_8_LANES;
-		lwsc |= PORT_LOGIC_LINK_WIDTH_8_LANES;
 		break;
 	default:
 		dev_err(pci->dev, "num-lanes %u: invalid value\n", num_lanes);
diff --git a/drivers/pci/controller/dwc/pcie-dw-rockchip.c b/drivers/pci/controller/dwc/pcie-dw-rockchip.c
index 1170e1107508..6b113a1212a9 100644
--- a/drivers/pci/controller/dwc/pcie-dw-rockchip.c
+++ b/drivers/pci/controller/dwc/pcie-dw-rockchip.c
@@ -44,7 +44,6 @@
 #define PCIE_LINKUP			(PCIE_SMLH_LINKUP | PCIE_RDLH_LINKUP)
 #define PCIE_RDLH_LINK_UP_CHGED		BIT(1)
 #define PCIE_LINK_REQ_RST_NOT_INT	BIT(2)
-#define PCIE_L0S_ENTRY			0x11
 #define PCIE_CLIENT_GENERAL_CONTROL	0x0
 #define PCIE_CLIENT_INTR_STATUS_LEGACY	0x8
 #define PCIE_CLIENT_INTR_MASK_LEGACY	0x1c
@@ -177,8 +176,7 @@ static int rockchip_pcie_link_up(struct dw_pcie *pci)
 	struct rockchip_pcie *rockchip = to_rockchip_pcie(pci);
 	u32 val = rockchip_pcie_get_ltssm(rockchip);
 
-	if ((val & PCIE_LINKUP) == PCIE_LINKUP &&
-	    (val & PCIE_LTSSM_STATUS_MASK) == PCIE_L0S_ENTRY)
+	if ((val & PCIE_LINKUP) == PCIE_LINKUP)
 		return 1;
 
 	return 0;
@@ -379,8 +377,8 @@ static int rockchip_pcie_phy_init(struct rockchip_pcie *rockchip)
 
 static void rockchip_pcie_phy_deinit(struct rockchip_pcie *rockchip)
 {
-	phy_exit(rockchip->phy);
 	phy_power_off(rockchip->phy);
+	phy_exit(rockchip->phy);
 }
 
 static const struct dw_pcie_ops dw_pcie_ops = {
diff --git a/drivers/pci/controller/dwc/pcie-histb.c b/drivers/pci/controller/dwc/pcie-histb.c
index 7a11c618b9d9..5538e5bf99fb 100644
--- a/drivers/pci/controller/dwc/pcie-histb.c
+++ b/drivers/pci/controller/dwc/pcie-histb.c
@@ -409,16 +409,21 @@ static int histb_pcie_probe(struct platform_device *pdev)
 	ret = histb_pcie_host_enable(pp);
 	if (ret) {
 		dev_err(dev, "failed to enable host\n");
-		return ret;
+		goto err_exit_phy;
 	}
 
 	ret = dw_pcie_host_init(pp);
 	if (ret) {
 		dev_err(dev, "failed to initialize host\n");
-		return ret;
+		goto err_exit_phy;
 	}
 
 	return 0;
+
+err_exit_phy:
+	phy_exit(hipcie->phy);
+
+	return ret;
 }
 
 static void histb_pcie_remove(struct platform_device *pdev)
@@ -427,8 +432,7 @@ static void histb_pcie_remove(struct platform_device *pdev)
 
 	histb_pcie_host_disable(hipcie);
 
-	if (hipcie->phy)
-		phy_exit(hipcie->phy);
+	phy_exit(hipcie->phy);
 }
 
 static const struct of_device_id histb_pcie_of_match[] = {
diff --git a/drivers/pci/controller/dwc/pcie-qcom.c b/drivers/pci/controller/dwc/pcie-qcom.c
index 6483e1874477..4c141e05f84e 100644
--- a/drivers/pci/controller/dwc/pcie-qcom.c
+++ b/drivers/pci/controller/dwc/pcie-qcom.c
@@ -1559,6 +1559,8 @@ static irqreturn_t qcom_pcie_global_irq_thread(int irq, void *data)
 		pci_lock_rescan_remove();
 		pci_rescan_bus(pp->bridge->bus);
 		pci_unlock_rescan_remove();
+
+		qcom_pcie_icc_opp_update(pcie);
 	} else {
 		dev_WARN_ONCE(dev, 1, "Received unknown event. INT_STATUS: 0x%08x\n",
 			      status);
diff --git a/drivers/pci/controller/dwc/pcie-rcar-gen4.c b/drivers/pci/controller/dwc/pcie-rcar-gen4.c
index 3a5511c3f7d9..5d77a0164860 100644
--- a/drivers/pci/controller/dwc/pcie-rcar-gen4.c
+++ b/drivers/pci/controller/dwc/pcie-rcar-gen4.c
@@ -403,6 +403,7 @@ static const struct pci_epc_features rcar_gen4_pcie_epc_features = {
 	.msix_capable = false,
 	.bar[BAR_1] = { .type = BAR_RESERVED, },
 	.bar[BAR_3] = { .type = BAR_RESERVED, },
+	.bar[BAR_4] = { .type = BAR_FIXED, .fixed_size = 256 },
 	.bar[BAR_5] = { .type = BAR_RESERVED, },
 	.align = SZ_1M,
 };
diff --git a/drivers/pci/controller/pcie-apple.c b/drivers/pci/controller/pcie-apple.c
index fefab2758a06..16725f9536f6 100644
--- a/drivers/pci/controller/pcie-apple.c
+++ b/drivers/pci/controller/pcie-apple.c
@@ -541,7 +541,7 @@ static int apple_pcie_setup_port(struct apple_pcie *pcie,
 	rmw_set(PORT_APPCLK_EN, port->base + PORT_APPCLK);
 
 	/* Assert PERST# before setting up the clock */
-	gpiod_set_value(reset, 1);
+	gpiod_set_value_cansleep(reset, 1);
 
 	ret = apple_pcie_setup_refclk(pcie, port);
 	if (ret < 0)
@@ -552,7 +552,7 @@ static int apple_pcie_setup_port(struct apple_pcie *pcie,
 
 	/* Deassert PERST# */
 	rmw_set(PORT_PERST_OFF, port->base + PORT_PERST);
-	gpiod_set_value(reset, 0);
+	gpiod_set_value_cansleep(reset, 0);
 
 	/* Wait for 100ms after PERST# deassertion (PCIe r5.0, 6.6.1) */
 	msleep(100);
@@ -585,6 +585,9 @@ static int apple_pcie_setup_port(struct apple_pcie *pcie,
 	list_add_tail(&port->entry, &pcie->ports);
 	init_completion(&pcie->event);
 
+	/* In the success path, we keep a reference to np around */
+	of_node_get(np);
+
 	ret = apple_pcie_port_register_irqs(port);
 	WARN_ON(ret);
 
@@ -764,7 +767,6 @@ static int apple_pcie_init(struct pci_config_window *cfg)
 {
 	struct device *dev = cfg->parent;
 	struct platform_device *platform = to_platform_device(dev);
-	struct device_node *of_port;
 	struct apple_pcie *pcie;
 	int ret;
 
@@ -787,11 +789,10 @@ static int apple_pcie_init(struct pci_config_window *cfg)
 	if (ret)
 		return ret;
 
-	for_each_child_of_node(dev->of_node, of_port) {
+	for_each_available_child_of_node_scoped(dev->of_node, of_port) {
 		ret = apple_pcie_setup_port(pcie, of_port);
 		if (ret) {
 			dev_err(pcie->dev, "Port %pOF setup fail: %d\n", of_port, ret);
-			of_node_put(of_port);
 			return ret;
 		}
 	}
diff --git a/drivers/pci/controller/pcie-brcmstb.c b/drivers/pci/controller/pcie-brcmstb.c
index 9321280f6edb..81f085cebf62 100644
--- a/drivers/pci/controller/pcie-brcmstb.c
+++ b/drivers/pci/controller/pcie-brcmstb.c
@@ -309,8 +309,8 @@ static int brcm_pcie_encode_ibar_size(u64 size)
 	if (log2_in >= 12 && log2_in <= 15)
 		/* Covers 4KB to 32KB (inclusive) */
 		return (log2_in - 12) + 0x1c;
-	else if (log2_in >= 16 && log2_in <= 35)
-		/* Covers 64KB to 32GB, (inclusive) */
+	else if (log2_in >= 16 && log2_in <= 36)
+		/* Covers 64KB to 64GB, (inclusive) */
 		return log2_in - 15;
 	/* Something is awry so disable */
 	return 0;
@@ -403,10 +403,10 @@ static int brcm_pcie_set_ssc(struct brcm_pcie *pcie)
 static void brcm_pcie_set_gen(struct brcm_pcie *pcie, int gen)
 {
 	u16 lnkctl2 = readw(pcie->base + BRCM_PCIE_CAP_REGS + PCI_EXP_LNKCTL2);
-	u32 lnkcap = readl(pcie->base + BRCM_PCIE_CAP_REGS + PCI_EXP_LNKCAP);
+	u32 lnkcap = readl(pcie->base + PCIE_RC_CFG_PRIV1_LINK_CAPABILITY);
 
 	lnkcap = (lnkcap & ~PCI_EXP_LNKCAP_SLS) | gen;
-	writel(lnkcap, pcie->base + BRCM_PCIE_CAP_REGS + PCI_EXP_LNKCAP);
+	writel(lnkcap, pcie->base + PCIE_RC_CFG_PRIV1_LINK_CAPABILITY);
 
 	lnkctl2 = (lnkctl2 & ~0xf) | gen;
 	writew(lnkctl2, pcie->base + BRCM_PCIE_CAP_REGS + PCI_EXP_LNKCTL2);
@@ -1276,6 +1276,10 @@ static int brcm_pcie_start_link(struct brcm_pcie *pcie)
 	bool ssc_good = false;
 	int ret, i;
 
+	/* Limit the generation if specified */
+	if (pcie->gen)
+		brcm_pcie_set_gen(pcie, pcie->gen);
+
 	/* Unassert the fundamental reset */
 	ret = pcie->perst_set(pcie, 0);
 	if (ret)
@@ -1302,9 +1306,6 @@ static int brcm_pcie_start_link(struct brcm_pcie *pcie)
 
 	brcm_config_clkreq(pcie);
 
-	if (pcie->gen)
-		brcm_pcie_set_gen(pcie, pcie->gen);
-
 	if (pcie->ssc) {
 		ret = brcm_pcie_set_ssc(pcie);
 		if (ret == 0)
@@ -1367,7 +1368,8 @@ static int brcm_pcie_add_bus(struct pci_bus *bus)
 
 		ret = regulator_bulk_get(dev, sr->num_supplies, sr->supplies);
 		if (ret) {
-			dev_info(dev, "No regulators for downstream device\n");
+			dev_info(dev, "Did not get regulators, err=%d\n", ret);
+			pcie->sr = NULL;
 			goto no_regulators;
 		}
 
@@ -1390,7 +1392,7 @@ static void brcm_pcie_remove_bus(struct pci_bus *bus)
 	struct subdev_regulators *sr = pcie->sr;
 	struct device *dev = &bus->dev;
 
-	if (!sr)
+	if (!sr || !bus->parent || !pci_is_root_bus(bus->parent))
 		return;
 
 	if (regulator_bulk_disable(sr->num_supplies, sr->supplies))
@@ -1784,7 +1786,7 @@ static struct pci_ops brcm7425_pcie_ops = {
 
 static int brcm_pcie_probe(struct platform_device *pdev)
 {
-	struct device_node *np = pdev->dev.of_node, *msi_np;
+	struct device_node *np = pdev->dev.of_node;
 	struct pci_host_bridge *bridge;
 	const struct pcie_cfg_data *data;
 	struct brcm_pcie *pcie;
@@ -1888,9 +1890,14 @@ static int brcm_pcie_probe(struct platform_device *pdev)
 		goto fail;
 	}
 
-	msi_np = of_parse_phandle(pcie->np, "msi-parent", 0);
-	if (pci_msi_enabled() && msi_np == pcie->np) {
-		ret = brcm_pcie_enable_msi(pcie);
+	if (pci_msi_enabled()) {
+		struct device_node *msi_np = of_parse_phandle(pcie->np, "msi-parent", 0);
+
+		if (msi_np == pcie->np)
+			ret = brcm_pcie_enable_msi(pcie);
+
+		of_node_put(msi_np);
+
 		if (ret) {
 			dev_err(pcie->dev, "probe of internal MSI failed");
 			goto fail;
@@ -1940,3 +1947,4 @@ module_platform_driver(brcm_pcie_driver);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Broadcom STB PCIe RC driver");
 MODULE_AUTHOR("Broadcom");
+MODULE_SOFTDEP("pre: irq_bcm2712_mip");
diff --git a/drivers/pci/controller/pcie-rcar-ep.c b/drivers/pci/controller/pcie-rcar-ep.c
index 047e2cef5afc..c5e0d025bc43 100644
--- a/drivers/pci/controller/pcie-rcar-ep.c
+++ b/drivers/pci/controller/pcie-rcar-ep.c
@@ -107,7 +107,7 @@ static int rcar_pcie_parse_outbound_ranges(struct rcar_pcie_endpoint *ep,
 		}
 		if (!devm_request_mem_region(&pdev->dev, res->start,
 					     resource_size(res),
-					     outbound_name)) {
+					     res->name)) {
 			dev_err(pcie->dev, "Cannot request memory region %s.\n",
 				outbound_name);
 			return -EIO;
diff --git a/drivers/pci/controller/pcie-rockchip-host.c b/drivers/pci/controller/pcie-rockchip-host.c
index cbec71114825..18e65571c145 100644
--- a/drivers/pci/controller/pcie-rockchip-host.c
+++ b/drivers/pci/controller/pcie-rockchip-host.c
@@ -367,7 +367,7 @@ static int rockchip_pcie_host_init_port(struct rockchip_pcie *rockchip)
 		}
 	}
 
-	rockchip_pcie_write(rockchip, ROCKCHIP_VENDOR_ID,
+	rockchip_pcie_write(rockchip, PCI_VENDOR_ID_ROCKCHIP,
 			    PCIE_CORE_CONFIG_VENDOR);
 	rockchip_pcie_write(rockchip,
 			    PCI_CLASS_BRIDGE_PCI_NORMAL << 8,
@@ -439,7 +439,7 @@ static irqreturn_t rockchip_pcie_subsys_irq_handler(int irq, void *arg)
 			dev_dbg(dev, "malformed TLP received from the link\n");
 
 		if (sub_reg & PCIE_CORE_INT_UCR)
-			dev_dbg(dev, "malformed TLP received from the link\n");
+			dev_dbg(dev, "Unexpected Completion received from the link\n");
 
 		if (sub_reg & PCIE_CORE_INT_FCE)
 			dev_dbg(dev, "an error was observed in the flow control advertisements from the other side\n");
diff --git a/drivers/pci/controller/pcie-rockchip.h b/drivers/pci/controller/pcie-rockchip.h
index 15ee949f2485..688f51d9bde6 100644
--- a/drivers/pci/controller/pcie-rockchip.h
+++ b/drivers/pci/controller/pcie-rockchip.h
@@ -188,7 +188,6 @@
 #define AXI_WRAPPER_NOR_MSG			0xc
 
 #define PCIE_RC_SEND_PME_OFF			0x11960
-#define ROCKCHIP_VENDOR_ID			0x1d87
 #define PCIE_LINK_IS_L2(x) \
 	(((x) & PCIE_CLIENT_DEBUG_LTSSM_MASK) == PCIE_CLIENT_DEBUG_LTSSM_L2)
 #define PCIE_LINK_UP(x) \
diff --git a/drivers/pci/controller/pcie-xilinx-cpm.c b/drivers/pci/controller/pcie-xilinx-cpm.c
index a0f5e1d67b04..1594d9e9e637 100644
--- a/drivers/pci/controller/pcie-xilinx-cpm.c
+++ b/drivers/pci/controller/pcie-xilinx-cpm.c
@@ -570,15 +570,17 @@ static int xilinx_cpm_pcie_probe(struct platform_device *pdev)
 		return err;
 
 	bus = resource_list_first_type(&bridge->windows, IORESOURCE_BUS);
-	if (!bus)
-		return -ENODEV;
+	if (!bus) {
+		err = -ENODEV;
+		goto err_free_irq_domains;
+	}
 
 	port->variant = of_device_get_match_data(dev);
 
 	err = xilinx_cpm_pcie_parse_dt(port, bus->res);
 	if (err) {
 		dev_err(dev, "Parsing DT failed\n");
-		goto err_parse_dt;
+		goto err_free_irq_domains;
 	}
 
 	xilinx_cpm_pcie_init_port(port);
@@ -602,7 +604,7 @@ err_host_bridge:
 	xilinx_cpm_free_interrupts(port);
 err_setup_irq:
 	pci_ecam_free(port->cfg);
-err_parse_dt:
+err_free_irq_domains:
 	xilinx_cpm_free_irq_domains(port);
 	return err;
 }
diff --git a/drivers/pci/controller/plda/pcie-microchip-host.c b/drivers/pci/controller/plda/pcie-microchip-host.c
index 48f60a04b740..3fdfffdf0270 100644
--- a/drivers/pci/controller/plda/pcie-microchip-host.c
+++ b/drivers/pci/controller/plda/pcie-microchip-host.c
@@ -7,27 +7,31 @@
  * Author: Daire McNamara <daire.mcnamara@microchip.com>
  */
 
+#include <linux/align.h>
+#include <linux/bits.h>
 #include <linux/bitfield.h>
 #include <linux/clk.h>
 #include <linux/irqchip/chained_irq.h>
 #include <linux/irqdomain.h>
+#include <linux/log2.h>
 #include <linux/module.h>
 #include <linux/msi.h>
 #include <linux/of_address.h>
 #include <linux/of_pci.h>
 #include <linux/pci-ecam.h>
 #include <linux/platform_device.h>
+#include <linux/wordpart.h>
 
 #include "../../pci.h"
 #include "pcie-plda.h"
 
+#define MC_MAX_NUM_INBOUND_WINDOWS		8
+#define MPFS_NC_BOUNCE_ADDR			0x80000000
+
 /* PCIe Bridge Phy and Controller Phy offsets */
 #define MC_PCIE1_BRIDGE_ADDR			0x00008000u
 #define MC_PCIE1_CTRL_ADDR			0x0000a000u
 
-#define MC_PCIE_BRIDGE_ADDR			(MC_PCIE1_BRIDGE_ADDR)
-#define MC_PCIE_CTRL_ADDR			(MC_PCIE1_CTRL_ADDR)
-
 /* PCIe Controller Phy Regs */
 #define SEC_ERROR_EVENT_CNT			0x20
 #define DED_ERROR_EVENT_CNT			0x24
@@ -128,7 +132,6 @@
 	[EVENT_LOCAL_ ## x] = { __stringify(x), s }
 
 #define PCIE_EVENT(x) \
-	.base = MC_PCIE_CTRL_ADDR, \
 	.offset = PCIE_EVENT_INT, \
 	.mask_offset = PCIE_EVENT_INT, \
 	.mask_high = 1, \
@@ -136,7 +139,6 @@
 	.enb_mask = PCIE_EVENT_INT_ENB_MASK
 
 #define SEC_EVENT(x) \
-	.base = MC_PCIE_CTRL_ADDR, \
 	.offset = SEC_ERROR_INT, \
 	.mask_offset = SEC_ERROR_INT_MASK, \
 	.mask = SEC_ERROR_INT_ ## x ## _INT, \
@@ -144,7 +146,6 @@
 	.enb_mask = 0
 
 #define DED_EVENT(x) \
-	.base = MC_PCIE_CTRL_ADDR, \
 	.offset = DED_ERROR_INT, \
 	.mask_offset = DED_ERROR_INT_MASK, \
 	.mask_high = 1, \
@@ -152,7 +153,6 @@
 	.enb_mask = 0
 
 #define LOCAL_EVENT(x) \
-	.base = MC_PCIE_BRIDGE_ADDR, \
 	.offset = ISTATUS_LOCAL, \
 	.mask_offset = IMASK_LOCAL, \
 	.mask_high = 0, \
@@ -179,7 +179,8 @@ struct event_map {
 
 struct mc_pcie {
 	struct plda_pcie_rp plda;
-	void __iomem *axi_base_addr;
+	void __iomem *bridge_base_addr;
+	void __iomem *ctrl_base_addr;
 };
 
 struct cause {
@@ -253,7 +254,6 @@ static struct event_map local_status_to_event[] = {
 };
 
 static struct {
-	u32 base;
 	u32 offset;
 	u32 mask;
 	u32 shift;
@@ -325,8 +325,7 @@ static inline u32 reg_to_event(u32 reg, struct event_map field)
 
 static u32 pcie_events(struct mc_pcie *port)
 {
-	void __iomem *ctrl_base_addr = port->axi_base_addr + MC_PCIE_CTRL_ADDR;
-	u32 reg = readl_relaxed(ctrl_base_addr + PCIE_EVENT_INT);
+	u32 reg = readl_relaxed(port->ctrl_base_addr + PCIE_EVENT_INT);
 	u32 val = 0;
 	int i;
 
@@ -338,8 +337,7 @@ static u32 pcie_events(struct mc_pcie *port)
 
 static u32 sec_errors(struct mc_pcie *port)
 {
-	void __iomem *ctrl_base_addr = port->axi_base_addr + MC_PCIE_CTRL_ADDR;
-	u32 reg = readl_relaxed(ctrl_base_addr + SEC_ERROR_INT);
+	u32 reg = readl_relaxed(port->ctrl_base_addr + SEC_ERROR_INT);
 	u32 val = 0;
 	int i;
 
@@ -351,8 +349,7 @@ static u32 sec_errors(struct mc_pcie *port)
 
 static u32 ded_errors(struct mc_pcie *port)
 {
-	void __iomem *ctrl_base_addr = port->axi_base_addr + MC_PCIE_CTRL_ADDR;
-	u32 reg = readl_relaxed(ctrl_base_addr + DED_ERROR_INT);
+	u32 reg = readl_relaxed(port->ctrl_base_addr + DED_ERROR_INT);
 	u32 val = 0;
 	int i;
 
@@ -364,8 +361,7 @@ static u32 ded_errors(struct mc_pcie *port)
 
 static u32 local_events(struct mc_pcie *port)
 {
-	void __iomem *bridge_base_addr = port->axi_base_addr + MC_PCIE_BRIDGE_ADDR;
-	u32 reg = readl_relaxed(bridge_base_addr + ISTATUS_LOCAL);
+	u32 reg = readl_relaxed(port->bridge_base_addr + ISTATUS_LOCAL);
 	u32 val = 0;
 	int i;
 
@@ -412,8 +408,12 @@ static void mc_ack_event_irq(struct irq_data *data)
 	void __iomem *addr;
 	u32 mask;
 
-	addr = mc_port->axi_base_addr + event_descs[event].base +
-		event_descs[event].offset;
+	if (event_descs[event].offset == ISTATUS_LOCAL)
+		addr = mc_port->bridge_base_addr;
+	else
+		addr = mc_port->ctrl_base_addr;
+
+	addr += event_descs[event].offset;
 	mask = event_descs[event].mask;
 	mask |= event_descs[event].enb_mask;
 
@@ -429,8 +429,12 @@ static void mc_mask_event_irq(struct irq_data *data)
 	u32 mask;
 	u32 val;
 
-	addr = mc_port->axi_base_addr + event_descs[event].base +
-		event_descs[event].mask_offset;
+	if (event_descs[event].offset == ISTATUS_LOCAL)
+		addr = mc_port->bridge_base_addr;
+	else
+		addr = mc_port->ctrl_base_addr;
+
+	addr += event_descs[event].mask_offset;
 	mask = event_descs[event].mask;
 	if (event_descs[event].enb_mask) {
 		mask <<= PCIE_EVENT_INT_ENB_SHIFT;
@@ -460,8 +464,12 @@ static void mc_unmask_event_irq(struct irq_data *data)
 	u32 mask;
 	u32 val;
 
-	addr = mc_port->axi_base_addr + event_descs[event].base +
-		event_descs[event].mask_offset;
+	if (event_descs[event].offset == ISTATUS_LOCAL)
+		addr = mc_port->bridge_base_addr;
+	else
+		addr = mc_port->ctrl_base_addr;
+
+	addr += event_descs[event].mask_offset;
 	mask = event_descs[event].mask;
 
 	if (event_descs[event].enb_mask)
@@ -554,26 +562,20 @@ static const struct plda_event mc_event = {
 
 static inline void mc_clear_secs(struct mc_pcie *port)
 {
-	void __iomem *ctrl_base_addr = port->axi_base_addr + MC_PCIE_CTRL_ADDR;
-
-	writel_relaxed(SEC_ERROR_INT_ALL_RAM_SEC_ERR_INT, ctrl_base_addr +
-		       SEC_ERROR_INT);
-	writel_relaxed(0, ctrl_base_addr + SEC_ERROR_EVENT_CNT);
+	writel_relaxed(SEC_ERROR_INT_ALL_RAM_SEC_ERR_INT,
+		       port->ctrl_base_addr + SEC_ERROR_INT);
+	writel_relaxed(0, port->ctrl_base_addr + SEC_ERROR_EVENT_CNT);
 }
 
 static inline void mc_clear_deds(struct mc_pcie *port)
 {
-	void __iomem *ctrl_base_addr = port->axi_base_addr + MC_PCIE_CTRL_ADDR;
-
-	writel_relaxed(DED_ERROR_INT_ALL_RAM_DED_ERR_INT, ctrl_base_addr +
-		       DED_ERROR_INT);
-	writel_relaxed(0, ctrl_base_addr + DED_ERROR_EVENT_CNT);
+	writel_relaxed(DED_ERROR_INT_ALL_RAM_DED_ERR_INT,
+		       port->ctrl_base_addr + DED_ERROR_INT);
+	writel_relaxed(0, port->ctrl_base_addr + DED_ERROR_EVENT_CNT);
 }
 
 static void mc_disable_interrupts(struct mc_pcie *port)
 {
-	void __iomem *bridge_base_addr = port->axi_base_addr + MC_PCIE_BRIDGE_ADDR;
-	void __iomem *ctrl_base_addr = port->axi_base_addr + MC_PCIE_CTRL_ADDR;
 	u32 val;
 
 	/* Ensure ECC bypass is enabled */
@@ -581,22 +583,22 @@ static void mc_disable_interrupts(struct mc_pcie *port)
 	      ECC_CONTROL_RX_RAM_ECC_BYPASS |
 	      ECC_CONTROL_PCIE2AXI_RAM_ECC_BYPASS |
 	      ECC_CONTROL_AXI2PCIE_RAM_ECC_BYPASS;
-	writel_relaxed(val, ctrl_base_addr + ECC_CONTROL);
+	writel_relaxed(val, port->ctrl_base_addr + ECC_CONTROL);
 
 	/* Disable SEC errors and clear any outstanding */
-	writel_relaxed(SEC_ERROR_INT_ALL_RAM_SEC_ERR_INT, ctrl_base_addr +
-		       SEC_ERROR_INT_MASK);
+	writel_relaxed(SEC_ERROR_INT_ALL_RAM_SEC_ERR_INT,
+		       port->ctrl_base_addr + SEC_ERROR_INT_MASK);
 	mc_clear_secs(port);
 
 	/* Disable DED errors and clear any outstanding */
-	writel_relaxed(DED_ERROR_INT_ALL_RAM_DED_ERR_INT, ctrl_base_addr +
-		       DED_ERROR_INT_MASK);
+	writel_relaxed(DED_ERROR_INT_ALL_RAM_DED_ERR_INT,
+		       port->ctrl_base_addr + DED_ERROR_INT_MASK);
 	mc_clear_deds(port);
 
 	/* Disable local interrupts and clear any outstanding */
-	writel_relaxed(0, bridge_base_addr + IMASK_LOCAL);
-	writel_relaxed(GENMASK(31, 0), bridge_base_addr + ISTATUS_LOCAL);
-	writel_relaxed(GENMASK(31, 0), bridge_base_addr + ISTATUS_MSI);
+	writel_relaxed(0, port->bridge_base_addr + IMASK_LOCAL);
+	writel_relaxed(GENMASK(31, 0), port->bridge_base_addr + ISTATUS_LOCAL);
+	writel_relaxed(GENMASK(31, 0), port->bridge_base_addr + ISTATUS_MSI);
 
 	/* Disable PCIe events and clear any outstanding */
 	val = PCIE_EVENT_INT_L2_EXIT_INT |
@@ -605,11 +607,96 @@ static void mc_disable_interrupts(struct mc_pcie *port)
 	      PCIE_EVENT_INT_L2_EXIT_INT_MASK |
 	      PCIE_EVENT_INT_HOTRST_EXIT_INT_MASK |
 	      PCIE_EVENT_INT_DLUP_EXIT_INT_MASK;
-	writel_relaxed(val, ctrl_base_addr + PCIE_EVENT_INT);
+	writel_relaxed(val, port->ctrl_base_addr + PCIE_EVENT_INT);
 
 	/* Disable host interrupts and clear any outstanding */
-	writel_relaxed(0, bridge_base_addr + IMASK_HOST);
-	writel_relaxed(GENMASK(31, 0), bridge_base_addr + ISTATUS_HOST);
+	writel_relaxed(0, port->bridge_base_addr + IMASK_HOST);
+	writel_relaxed(GENMASK(31, 0), port->bridge_base_addr + ISTATUS_HOST);
+}
+
+static void mc_pcie_setup_inbound_atr(struct mc_pcie *port, int window_index,
+				      u64 axi_addr, u64 pcie_addr, u64 size)
+{
+	u32 table_offset = window_index * ATR_ENTRY_SIZE;
+	void __iomem *table_addr = port->bridge_base_addr + table_offset;
+	u32 atr_sz;
+	u32 val;
+
+	atr_sz = ilog2(size) - 1;
+
+	val = ALIGN_DOWN(lower_32_bits(pcie_addr), SZ_4K);
+	val |= FIELD_PREP(ATR_SIZE_MASK, atr_sz);
+	val |= ATR_IMPL_ENABLE;
+
+	writel(val, table_addr + ATR0_PCIE_WIN0_SRCADDR_PARAM);
+
+	writel(upper_32_bits(pcie_addr), table_addr + ATR0_PCIE_WIN0_SRC_ADDR);
+
+	writel(lower_32_bits(axi_addr), table_addr + ATR0_PCIE_WIN0_TRSL_ADDR_LSB);
+	writel(upper_32_bits(axi_addr), table_addr + ATR0_PCIE_WIN0_TRSL_ADDR_UDW);
+
+	writel(TRSL_ID_AXI4_MASTER_0, table_addr + ATR0_PCIE_WIN0_TRSL_PARAM);
+}
+
+static int mc_pcie_setup_inbound_ranges(struct platform_device *pdev,
+					struct mc_pcie *port)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *dn = dev->of_node;
+	struct of_range_parser parser;
+	struct of_range range;
+	int atr_index = 0;
+
+	/*
+	 * MPFS PCIe Root Port is 32-bit only, behind a Fabric Interface
+	 * Controller FPGA logic block which contains the AXI-S interface.
+	 *
+	 * From the point of view of the PCIe Root Port, there are only two
+	 * supported Root Port configurations:
+	 *
+	 * Configuration 1: for use with fully coherent designs; supports a
+	 * window from 0x0 (CPU space) to specified PCIe space.
+	 *
+	 * Configuration 2: for use with non-coherent designs; supports two
+	 * 1 GB windows to CPU space; one mapping CPU space 0 to PCIe space
+	 * 0x80000000 and a second mapping CPU space 0x40000000 to PCIe
+	 * space 0xc0000000. This cfg needs two windows because of how the
+	 * MSI space is allocated in the AXI-S range on MPFS.
+	 *
+	 * The FIC interface outside the PCIe block *must* complete the
+	 * inbound address translation as per MCHP MPFS FPGA design
+	 * guidelines.
+	 */
+	if (device_property_read_bool(dev, "dma-noncoherent")) {
+		/*
+		 * Always need same two tables in this case.  Need two tables
+		 * due to hardware interactions between address and size.
+		 */
+		mc_pcie_setup_inbound_atr(port, 0, 0,
+					  MPFS_NC_BOUNCE_ADDR, SZ_1G);
+		mc_pcie_setup_inbound_atr(port, 1, SZ_1G,
+					  MPFS_NC_BOUNCE_ADDR + SZ_1G, SZ_1G);
+	} else {
+		/* Find any DMA ranges */
+		if (of_pci_dma_range_parser_init(&parser, dn)) {
+			/* No DMA range property - setup default */
+			mc_pcie_setup_inbound_atr(port, 0, 0, 0, SZ_4G);
+			return 0;
+		}
+
+		for_each_of_range(&parser, &range) {
+			if (atr_index >= MC_MAX_NUM_INBOUND_WINDOWS) {
+				dev_err(dev, "too many inbound ranges; %d available tables\n",
+					MC_MAX_NUM_INBOUND_WINDOWS);
+				return -EINVAL;
+			}
+			mc_pcie_setup_inbound_atr(port, atr_index, 0,
+						  range.pci_addr, range.size);
+			atr_index++;
+		}
+	}
+
+	return 0;
 }
 
 static int mc_platform_init(struct pci_config_window *cfg)
@@ -617,12 +704,10 @@ static int mc_platform_init(struct pci_config_window *cfg)
 	struct device *dev = cfg->parent;
 	struct platform_device *pdev = to_platform_device(dev);
 	struct pci_host_bridge *bridge = platform_get_drvdata(pdev);
-	void __iomem *bridge_base_addr =
-		port->axi_base_addr + MC_PCIE_BRIDGE_ADDR;
 	int ret;
 
 	/* Configure address translation table 0 for PCIe config space */
-	plda_pcie_setup_window(bridge_base_addr, 0, cfg->res.start,
+	plda_pcie_setup_window(port->bridge_base_addr, 0, cfg->res.start,
 			       cfg->res.start,
 			       resource_size(&cfg->res));
 
@@ -634,6 +719,10 @@ static int mc_platform_init(struct pci_config_window *cfg)
 	if (ret)
 		return ret;
 
+	ret = mc_pcie_setup_inbound_ranges(pdev, port);
+	if (ret)
+		return ret;
+
 	port->plda.event_ops = &mc_event_ops;
 	port->plda.event_irq_chip = &mc_event_irq_chip;
 	port->plda.events_bitmap = GENMASK(NUM_EVENTS - 1, 0);
@@ -649,7 +738,7 @@ static int mc_platform_init(struct pci_config_window *cfg)
 static int mc_host_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
-	void __iomem *bridge_base_addr;
+	void __iomem *apb_base_addr;
 	struct plda_pcie_rp *plda;
 	int ret;
 	u32 val;
@@ -661,30 +750,45 @@ static int mc_host_probe(struct platform_device *pdev)
 	plda = &port->plda;
 	plda->dev = dev;
 
-	port->axi_base_addr = devm_platform_ioremap_resource(pdev, 1);
-	if (IS_ERR(port->axi_base_addr))
-		return PTR_ERR(port->axi_base_addr);
+	port->bridge_base_addr = devm_platform_ioremap_resource_byname(pdev,
+								    "bridge");
+	port->ctrl_base_addr = devm_platform_ioremap_resource_byname(pdev,
+								    "ctrl");
+	if (!IS_ERR(port->bridge_base_addr) && !IS_ERR(port->ctrl_base_addr))
+		goto addrs_set;
+
+	/*
+	 * The original, incorrect, binding that lumped the control and
+	 * bridge addresses together still needs to be handled by the driver.
+	 */
+	apb_base_addr = devm_platform_ioremap_resource_byname(pdev, "apb");
+	if (IS_ERR(apb_base_addr))
+		return dev_err_probe(dev, PTR_ERR(apb_base_addr),
+				     "both legacy apb register and ctrl/bridge regions missing");
+
+	port->bridge_base_addr = apb_base_addr + MC_PCIE1_BRIDGE_ADDR;
+	port->ctrl_base_addr = apb_base_addr + MC_PCIE1_CTRL_ADDR;
 
+addrs_set:
 	mc_disable_interrupts(port);
 
-	bridge_base_addr = port->axi_base_addr + MC_PCIE_BRIDGE_ADDR;
-	plda->bridge_addr = bridge_base_addr;
+	plda->bridge_addr = port->bridge_base_addr;
 	plda->num_events = NUM_EVENTS;
 
 	/* Allow enabling MSI by disabling MSI-X */
-	val = readl(bridge_base_addr + PCIE_PCI_IRQ_DW0);
+	val = readl(port->bridge_base_addr + PCIE_PCI_IRQ_DW0);
 	val &= ~MSIX_CAP_MASK;
-	writel(val, bridge_base_addr + PCIE_PCI_IRQ_DW0);
+	writel(val, port->bridge_base_addr + PCIE_PCI_IRQ_DW0);
 
 	/* Pick num vectors from bitfile programmed onto FPGA fabric */
-	val = readl(bridge_base_addr + PCIE_PCI_IRQ_DW0);
+	val = readl(port->bridge_base_addr + PCIE_PCI_IRQ_DW0);
 	val &= NUM_MSI_MSGS_MASK;
 	val >>= NUM_MSI_MSGS_SHIFT;
 
 	plda->msi.num_vectors = 1 << val;
 
 	/* Pick vector address from design */
-	plda->msi.vector_phy = readl_relaxed(bridge_base_addr + IMSI_ADDR);
+	plda->msi.vector_phy = readl_relaxed(port->bridge_base_addr + IMSI_ADDR);
 
 	ret = mc_pcie_init_clks(dev);
 	if (ret) {
diff --git a/drivers/pci/controller/plda/pcie-plda-host.c b/drivers/pci/controller/plda/pcie-plda-host.c
index 8533dc618d45..4153214ca410 100644
--- a/drivers/pci/controller/plda/pcie-plda-host.c
+++ b/drivers/pci/controller/plda/pcie-plda-host.c
@@ -8,11 +8,14 @@
  * Author: Daire McNamara <daire.mcnamara@microchip.com>
  */
 
+#include <linux/align.h>
+#include <linux/bitfield.h>
 #include <linux/irqchip/chained_irq.h>
 #include <linux/irqdomain.h>
 #include <linux/msi.h>
 #include <linux/pci_regs.h>
 #include <linux/pci-ecam.h>
+#include <linux/wordpart.h>
 
 #include "pcie-plda.h"
 
@@ -502,8 +505,9 @@ void plda_pcie_setup_window(void __iomem *bridge_base_addr, u32 index,
 	writel(val, bridge_base_addr + (index * ATR_ENTRY_SIZE) +
 	       ATR0_AXI4_SLV0_TRSL_PARAM);
 
-	val = lower_32_bits(axi_addr) | (atr_sz << ATR_SIZE_SHIFT) |
-			    ATR_IMPL_ENABLE;
+	val = ALIGN_DOWN(lower_32_bits(axi_addr), SZ_4K);
+	val |= FIELD_PREP(ATR_SIZE_MASK, atr_sz);
+	val |= ATR_IMPL_ENABLE;
 	writel(val, bridge_base_addr + (index * ATR_ENTRY_SIZE) +
 	       ATR0_AXI4_SLV0_SRCADDR_PARAM);
 
@@ -518,13 +522,20 @@ void plda_pcie_setup_window(void __iomem *bridge_base_addr, u32 index,
 	val = upper_32_bits(pci_addr);
 	writel(val, bridge_base_addr + (index * ATR_ENTRY_SIZE) +
 	       ATR0_AXI4_SLV0_TRSL_ADDR_UDW);
+}
+EXPORT_SYMBOL_GPL(plda_pcie_setup_window);
+
+void plda_pcie_setup_inbound_address_translation(struct plda_pcie_rp *port)
+{
+	void __iomem *bridge_base_addr = port->bridge_addr;
+	u32 val;
 
 	val = readl(bridge_base_addr + ATR0_PCIE_WIN0_SRCADDR_PARAM);
 	val |= (ATR0_PCIE_ATR_SIZE << ATR0_PCIE_ATR_SIZE_SHIFT);
 	writel(val, bridge_base_addr + ATR0_PCIE_WIN0_SRCADDR_PARAM);
 	writel(0, bridge_base_addr + ATR0_PCIE_WIN0_SRC_ADDR);
 }
-EXPORT_SYMBOL_GPL(plda_pcie_setup_window);
+EXPORT_SYMBOL_GPL(plda_pcie_setup_inbound_address_translation);
 
 int plda_pcie_setup_iomems(struct pci_host_bridge *bridge,
 			   struct plda_pcie_rp *port)
diff --git a/drivers/pci/controller/plda/pcie-plda.h b/drivers/pci/controller/plda/pcie-plda.h
index 0e7dc0d8e5ba..61ece26065ea 100644
--- a/drivers/pci/controller/plda/pcie-plda.h
+++ b/drivers/pci/controller/plda/pcie-plda.h
@@ -89,14 +89,15 @@
 
 /* PCIe AXI slave table init defines */
 #define ATR0_AXI4_SLV0_SRCADDR_PARAM		0x800u
-#define  ATR_SIZE_SHIFT				1
-#define  ATR_IMPL_ENABLE			1
+#define  ATR_SIZE_MASK				GENMASK(6, 1)
+#define  ATR_IMPL_ENABLE			BIT(0)
 #define ATR0_AXI4_SLV0_SRC_ADDR			0x804u
 #define ATR0_AXI4_SLV0_TRSL_ADDR_LSB		0x808u
 #define ATR0_AXI4_SLV0_TRSL_ADDR_UDW		0x80cu
 #define ATR0_AXI4_SLV0_TRSL_PARAM		0x810u
 #define  PCIE_TX_RX_INTERFACE			0x00000000u
 #define  PCIE_CONFIG_INTERFACE			0x00000001u
+#define  TRSL_ID_AXI4_MASTER_0			0x00000004u
 
 #define CONFIG_SPACE_ADDR_OFFSET		0x1000u
 
@@ -204,6 +205,7 @@ int plda_init_interrupts(struct platform_device *pdev,
 void plda_pcie_setup_window(void __iomem *bridge_base_addr, u32 index,
 			    phys_addr_t axi_addr, phys_addr_t pci_addr,
 			    size_t size);
+void plda_pcie_setup_inbound_address_translation(struct plda_pcie_rp *port);
 int plda_pcie_setup_iomems(struct pci_host_bridge *bridge,
 			   struct plda_pcie_rp *port);
 int plda_pcie_host_init(struct plda_pcie_rp *port, struct pci_ops *ops,
diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c
index 9d9596947350..8df064b62a2f 100644
--- a/drivers/pci/controller/vmd.c
+++ b/drivers/pci/controller/vmd.c
@@ -17,6 +17,8 @@
 #include <linux/rculist.h>
 #include <linux/rcupdate.h>
 
+#include <xen/xen.h>
+
 #include <asm/irqdomain.h>
 
 #define VMD_CFGBAR	0
@@ -125,7 +127,7 @@ struct vmd_irq_list {
 struct vmd_dev {
 	struct pci_dev		*dev;
 
-	spinlock_t		cfg_lock;
+	raw_spinlock_t		cfg_lock;
 	void __iomem		*cfgbar;
 
 	int msix_count;
@@ -391,7 +393,7 @@ static int vmd_pci_read(struct pci_bus *bus, unsigned int devfn, int reg,
 	if (!addr)
 		return -EFAULT;
 
-	spin_lock_irqsave(&vmd->cfg_lock, flags);
+	raw_spin_lock_irqsave(&vmd->cfg_lock, flags);
 	switch (len) {
 	case 1:
 		*value = readb(addr);
@@ -406,7 +408,7 @@ static int vmd_pci_read(struct pci_bus *bus, unsigned int devfn, int reg,
 		ret = -EINVAL;
 		break;
 	}
-	spin_unlock_irqrestore(&vmd->cfg_lock, flags);
+	raw_spin_unlock_irqrestore(&vmd->cfg_lock, flags);
 	return ret;
 }
 
@@ -426,7 +428,7 @@ static int vmd_pci_write(struct pci_bus *bus, unsigned int devfn, int reg,
 	if (!addr)
 		return -EFAULT;
 
-	spin_lock_irqsave(&vmd->cfg_lock, flags);
+	raw_spin_lock_irqsave(&vmd->cfg_lock, flags);
 	switch (len) {
 	case 1:
 		writeb(value, addr);
@@ -444,7 +446,7 @@ static int vmd_pci_write(struct pci_bus *bus, unsigned int devfn, int reg,
 		ret = -EINVAL;
 		break;
 	}
-	spin_unlock_irqrestore(&vmd->cfg_lock, flags);
+	raw_spin_unlock_irqrestore(&vmd->cfg_lock, flags);
 	return ret;
 }
 
@@ -970,6 +972,24 @@ static int vmd_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	struct vmd_dev *vmd;
 	int err;
 
+	if (xen_domain()) {
+		/*
+		 * Xen doesn't have knowledge about devices in the VMD bus
+		 * because the config space of devices behind the VMD bridge is
+		 * not known to Xen, and hence Xen cannot discover or configure
+		 * them in any way.
+		 *
+		 * Bypass of MSI remapping won't work in that case as direct
+		 * write by Linux to the MSI entries won't result in functional
+		 * interrupts, as Xen is the entity that manages the host
+		 * interrupt controller and must configure interrupts.  However
+		 * multiplexing of interrupts by the VMD bridge will work under
+		 * Xen, so force the usage of that mode which must always be
+		 * supported by VMD bridges.
+		 */
+		features &= ~VMD_FEAT_CAN_BYPASS_MSI_REMAP;
+	}
+
 	if (resource_size(&dev->resource[VMD_CFGBAR]) < (1 << 20))
 		return -ENOMEM;
 
@@ -1009,7 +1029,7 @@ static int vmd_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	if (features & VMD_FEAT_OFFSET_FIRST_VECTOR)
 		vmd->first_vec = 1;
 
-	spin_lock_init(&vmd->cfg_lock);
+	raw_spin_lock_init(&vmd->cfg_lock);
 	pci_set_drvdata(dev, vmd);
 	err = vmd_enable_domain(vmd, features);
 	if (err)
diff --git a/drivers/pci/devres.c b/drivers/pci/devres.c
index b133967faef8..3f2691888c35 100644
--- a/drivers/pci/devres.c
+++ b/drivers/pci/devres.c
@@ -40,7 +40,7 @@
  * Legacy struct storing addresses to whole mapped BARs.
  */
 struct pcim_iomap_devres {
-	void __iomem *table[PCI_STD_NUM_BARS];
+	void __iomem *table[PCI_NUM_RESOURCES];
 };
 
 /* Used to restore the old INTx state on driver detach. */
@@ -411,46 +411,20 @@ static inline bool mask_contains_bar(int mask, int bar)
 	return mask & BIT(bar);
 }
 
-/*
- * This is a copy of pci_intx() used to bypass the problem of recursive
- * function calls due to the hybrid nature of pci_intx().
- */
-static void __pcim_intx(struct pci_dev *pdev, int enable)
-{
-	u16 pci_command, new;
-
-	pci_read_config_word(pdev, PCI_COMMAND, &pci_command);
-
-	if (enable)
-		new = pci_command & ~PCI_COMMAND_INTX_DISABLE;
-	else
-		new = pci_command | PCI_COMMAND_INTX_DISABLE;
-
-	if (new != pci_command)
-		pci_write_config_word(pdev, PCI_COMMAND, new);
-}
-
 static void pcim_intx_restore(struct device *dev, void *data)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct pcim_intx_devres *res = data;
 
-	__pcim_intx(pdev, res->orig_intx);
+	pci_intx(pdev, res->orig_intx);
 }
 
-static struct pcim_intx_devres *get_or_create_intx_devres(struct device *dev)
+static void save_orig_intx(struct pci_dev *pdev, struct pcim_intx_devres *res)
 {
-	struct pcim_intx_devres *res;
-
-	res = devres_find(dev, pcim_intx_restore, NULL, NULL);
-	if (res)
-		return res;
+	u16 pci_command;
 
-	res = devres_alloc(pcim_intx_restore, sizeof(*res), GFP_KERNEL);
-	if (res)
-		devres_add(dev, res);
-
-	return res;
+	pci_read_config_word(pdev, PCI_COMMAND, &pci_command);
+	res->orig_intx = !(pci_command & PCI_COMMAND_INTX_DISABLE);
 }
 
 /**
@@ -466,16 +440,28 @@ static struct pcim_intx_devres *get_or_create_intx_devres(struct device *dev)
 int pcim_intx(struct pci_dev *pdev, int enable)
 {
 	struct pcim_intx_devres *res;
+	struct device *dev = &pdev->dev;
 
-	res = get_or_create_intx_devres(&pdev->dev);
-	if (!res)
-		return -ENOMEM;
+	/*
+	 * pcim_intx() must only restore the INTx value that existed before the
+	 * driver was loaded, i.e., before it called pcim_intx() for the
+	 * first time.
+	 */
+	res = devres_find(dev, pcim_intx_restore, NULL, NULL);
+	if (!res) {
+		res = devres_alloc(pcim_intx_restore, sizeof(*res), GFP_KERNEL);
+		if (!res)
+			return -ENOMEM;
+
+		save_orig_intx(pdev, res);
+		devres_add(dev, res);
+	}
 
-	res->orig_intx = !enable;
-	__pcim_intx(pdev, enable);
+	pci_intx(pdev, enable);
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(pcim_intx);
 
 static void pcim_disable_device(void *pdev_raw)
 {
@@ -591,7 +577,7 @@ static int pcim_add_mapping_to_legacy_table(struct pci_dev *pdev,
 {
 	void __iomem **legacy_iomap_table;
 
-	if (bar >= PCI_STD_NUM_BARS)
+	if (!pci_bar_index_is_valid(bar))
 		return -EINVAL;
 
 	legacy_iomap_table = (void __iomem **)pcim_iomap_table(pdev);
@@ -636,7 +622,7 @@ static void pcim_remove_bar_from_legacy_table(struct pci_dev *pdev, int bar)
 {
 	void __iomem **legacy_iomap_table;
 
-	if (bar >= PCI_STD_NUM_BARS)
+	if (!pci_bar_index_is_valid(bar))
 		return;
 
 	legacy_iomap_table = (void __iomem **)pcim_iomap_table(pdev);
@@ -669,6 +655,9 @@ void __iomem *pcim_iomap(struct pci_dev *pdev, int bar, unsigned long maxlen)
 	void __iomem *mapping;
 	struct pcim_addr_devres *res;
 
+	if (!pci_bar_index_is_valid(bar))
+		return NULL;
+
 	res = pcim_addr_devres_alloc(pdev);
 	if (!res)
 		return NULL;
@@ -736,6 +725,9 @@ void __iomem *pcim_iomap_region(struct pci_dev *pdev, int bar,
 	int ret;
 	struct pcim_addr_devres *res;
 
+	if (!pci_bar_index_is_valid(bar))
+		return IOMEM_ERR_PTR(-EINVAL);
+
 	res = pcim_addr_devres_alloc(pdev);
 	if (!res)
 		return IOMEM_ERR_PTR(-ENOMEM);
@@ -836,6 +828,9 @@ static int _pcim_request_region(struct pci_dev *pdev, int bar, const char *name,
 	int ret;
 	struct pcim_addr_devres *res;
 
+	if (!pci_bar_index_is_valid(bar))
+		return -EINVAL;
+
 	res = pcim_addr_devres_alloc(pdev);
 	if (!res)
 		return -ENOMEM;
@@ -939,7 +934,7 @@ static void pcim_release_all_regions(struct pci_dev *pdev)
  * desired, release individual regions with pcim_release_region() or all of
  * them at once with pcim_release_all_regions().
  */
-static int pcim_request_all_regions(struct pci_dev *pdev, const char *name)
+int pcim_request_all_regions(struct pci_dev *pdev, const char *name)
 {
 	int ret;
 	int bar;
@@ -957,6 +952,7 @@ err:
 
 	return ret;
 }
+EXPORT_SYMBOL(pcim_request_all_regions);
 
 /**
  * pcim_iomap_regions_request_all - Request all BARs and iomap specified ones
@@ -1056,6 +1052,9 @@ void __iomem *pcim_iomap_range(struct pci_dev *pdev, int bar,
 	void __iomem *mapping;
 	struct pcim_addr_devres *res;
 
+	if (!pci_bar_index_is_valid(bar))
+		return IOMEM_ERR_PTR(-EINVAL);
+
 	res = pcim_addr_devres_alloc(pdev);
 	if (!res)
 		return IOMEM_ERR_PTR(-ENOMEM);
diff --git a/drivers/pci/endpoint/functions/pci-epf-mhi.c b/drivers/pci/endpoint/functions/pci-epf-mhi.c
index 54286a40bdfb..6643a88c7a0c 100644
--- a/drivers/pci/endpoint/functions/pci-epf-mhi.c
+++ b/drivers/pci/endpoint/functions/pci-epf-mhi.c
@@ -125,7 +125,7 @@ static const struct pci_epf_mhi_ep_info sm8450_info = {
 
 static struct pci_epf_header sa8775p_header = {
 	.vendorid = PCI_VENDOR_ID_QCOM,
-	.deviceid = 0x0306,               /* FIXME: Update deviceid for sa8775p EP */
+	.deviceid = 0x0116,
 	.baseclass_code = PCI_CLASS_OTHERS,
 	.interrupt_pin = PCI_INTERRUPT_INTA,
 };
diff --git a/drivers/pci/endpoint/functions/pci-epf-test.c b/drivers/pci/endpoint/functions/pci-epf-test.c
index 7c2ed6eae53a..21aa3709e257 100644
--- a/drivers/pci/endpoint/functions/pci-epf-test.c
+++ b/drivers/pci/endpoint/functions/pci-epf-test.c
@@ -251,7 +251,7 @@ static int pci_epf_test_init_dma_chan(struct pci_epf_test *epf_test)
 
 fail_back_rx:
 	dma_release_channel(epf_test->dma_chan_rx);
-	epf_test->dma_chan_tx = NULL;
+	epf_test->dma_chan_rx = NULL;
 
 fail_back_tx:
 	dma_cap_zero(mask);
@@ -361,8 +361,8 @@ static void pci_epf_test_copy(struct pci_epf_test *epf_test,
 
 	ktime_get_ts64(&start);
 	if (reg->flags & FLAG_USE_DMA) {
-		if (epf_test->dma_private) {
-			dev_err(dev, "Cannot transfer data using DMA\n");
+		if (!dma_has_cap(DMA_MEMCPY, epf_test->dma_chan_tx->device->cap_mask)) {
+			dev_err(dev, "DMA controller doesn't support MEMCPY\n");
 			ret = -EINVAL;
 			goto err_map_addr;
 		}
@@ -703,6 +703,7 @@ static int pci_epf_test_set_bar(struct pci_epf *epf)
 		if (ret) {
 			pci_epf_free_space(epf, epf_test->reg[bar], bar,
 					   PRIMARY_INTERFACE);
+			epf_test->reg[bar] = NULL;
 			dev_err(dev, "Failed to set BAR%d\n", bar);
 			if (bar == test_reg_bar)
 				return ret;
@@ -878,6 +879,7 @@ static void pci_epf_test_free_space(struct pci_epf *epf)
 
 		pci_epf_free_space(epf, epf_test->reg[bar], bar,
 				   PRIMARY_INTERFACE);
+		epf_test->reg[bar] = NULL;
 	}
 }
 
diff --git a/drivers/pci/endpoint/functions/pci-epf-vntb.c b/drivers/pci/endpoint/functions/pci-epf-vntb.c
index 874cb097b093..62d09a528e68 100644
--- a/drivers/pci/endpoint/functions/pci-epf-vntb.c
+++ b/drivers/pci/endpoint/functions/pci-epf-vntb.c
@@ -530,7 +530,7 @@ static int epf_ntb_db_bar_init(struct epf_ntb *ntb)
 	struct device *dev = &ntb->epf->dev;
 	int ret;
 	struct pci_epf_bar *epf_bar;
-	void __iomem *mw_addr;
+	void *mw_addr;
 	enum pci_barno barno;
 	size_t size = sizeof(u32) * ntb->db_count;
 
@@ -700,7 +700,7 @@ static int epf_ntb_init_epc_bar(struct epf_ntb *ntb)
 		barno = pci_epc_get_next_free_bar(epc_features, barno);
 		if (barno < 0) {
 			dev_err(dev, "Fail to get NTB function BAR\n");
-			return barno;
+			return -ENOENT;
 		}
 		ntb->epf_ntb_bar[bar] = barno;
 	}
diff --git a/drivers/pci/endpoint/pci-epc-core.c b/drivers/pci/endpoint/pci-epc-core.c
index 62f7dff43730..de665342dc16 100644
--- a/drivers/pci/endpoint/pci-epc-core.c
+++ b/drivers/pci/endpoint/pci-epc-core.c
@@ -856,7 +856,7 @@ void devm_pci_epc_destroy(struct device *dev, struct pci_epc *epc)
 {
 	int r;
 
-	r = devres_destroy(dev, devm_pci_epc_release, devm_pci_epc_match,
+	r = devres_release(dev, devm_pci_epc_release, devm_pci_epc_match,
 			   epc);
 	dev_WARN_ONCE(dev, r, "couldn't find PCI EPC resource\n");
 }
diff --git a/drivers/pci/endpoint/pci-epf-core.c b/drivers/pci/endpoint/pci-epf-core.c
index 8fa2797d4169..963d2f3aa5d4 100644
--- a/drivers/pci/endpoint/pci-epf-core.c
+++ b/drivers/pci/endpoint/pci-epf-core.c
@@ -202,6 +202,7 @@ void pci_epf_remove_vepf(struct pci_epf *epf_pf, struct pci_epf *epf_vf)
 
 	mutex_lock(&epf_pf->lock);
 	clear_bit(epf_vf->vfunc_no, &epf_pf->vfunction_num_map);
+	epf_vf->epf_pf = NULL;
 	list_del(&epf_vf->list);
 	mutex_unlock(&epf_pf->lock);
 }
@@ -235,12 +236,13 @@ void pci_epf_free_space(struct pci_epf *epf, void *addr, enum pci_barno bar,
 	}
 
 	dev = epc->dev.parent;
-	dma_free_coherent(dev, epf_bar[bar].size, addr,
+	dma_free_coherent(dev, epf_bar[bar].aligned_size, addr,
 			  epf_bar[bar].phys_addr);
 
 	epf_bar[bar].phys_addr = 0;
 	epf_bar[bar].addr = NULL;
 	epf_bar[bar].size = 0;
+	epf_bar[bar].aligned_size = 0;
 	epf_bar[bar].barno = 0;
 	epf_bar[bar].flags = 0;
 }
@@ -263,7 +265,7 @@ void *pci_epf_alloc_space(struct pci_epf *epf, size_t size, enum pci_barno bar,
 			  enum pci_epc_interface_type type)
 {
 	u64 bar_fixed_size = epc_features->bar[bar].fixed_size;
-	size_t align = epc_features->align;
+	size_t aligned_size, align = epc_features->align;
 	struct pci_epf_bar *epf_bar;
 	dma_addr_t phys_addr;
 	struct pci_epc *epc;
@@ -280,12 +282,18 @@ void *pci_epf_alloc_space(struct pci_epf *epf, size_t size, enum pci_barno bar,
 			return NULL;
 		}
 		size = bar_fixed_size;
+	} else {
+		/* BAR size must be power of two */
+		size = roundup_pow_of_two(size);
 	}
 
-	if (align)
-		size = ALIGN(size, align);
-	else
-		size = roundup_pow_of_two(size);
+	/*
+	 * Allocate enough memory to accommodate the iATU alignment
+	 * requirement.  In most cases, this will be the same as .size but
+	 * it might be different if, for example, the fixed size of a BAR
+	 * is smaller than align.
+	 */
+	aligned_size = align ? ALIGN(size, align) : size;
 
 	if (type == PRIMARY_INTERFACE) {
 		epc = epf->epc;
@@ -296,7 +304,7 @@ void *pci_epf_alloc_space(struct pci_epf *epf, size_t size, enum pci_barno bar,
 	}
 
 	dev = epc->dev.parent;
-	space = dma_alloc_coherent(dev, size, &phys_addr, GFP_KERNEL);
+	space = dma_alloc_coherent(dev, aligned_size, &phys_addr, GFP_KERNEL);
 	if (!space) {
 		dev_err(dev, "failed to allocate mem space\n");
 		return NULL;
@@ -305,6 +313,7 @@ void *pci_epf_alloc_space(struct pci_epf *epf, size_t size, enum pci_barno bar,
 	epf_bar[bar].phys_addr = phys_addr;
 	epf_bar[bar].addr = space;
 	epf_bar[bar].size = size;
+	epf_bar[bar].aligned_size = aligned_size;
 	epf_bar[bar].barno = bar;
 	if (upper_32_bits(size) || epc_features->bar[bar].only_64bit)
 		epf_bar[bar].flags |= PCI_BASE_ADDRESS_MEM_TYPE_64;
diff --git a/drivers/pci/hotplug/pciehp_core.c b/drivers/pci/hotplug/pciehp_core.c
index ff458e692fed..997841c69893 100644
--- a/drivers/pci/hotplug/pciehp_core.c
+++ b/drivers/pci/hotplug/pciehp_core.c
@@ -286,9 +286,12 @@ static int pciehp_suspend(struct pcie_device *dev)
 
 static bool pciehp_device_replaced(struct controller *ctrl)
 {
-	struct pci_dev *pdev __free(pci_dev_put);
+	struct pci_dev *pdev __free(pci_dev_put) = NULL;
 	u32 reg;
 
+	if (pci_dev_is_disconnected(ctrl->pcie->port))
+		return false;
+
 	pdev = pci_get_slot(ctrl->pcie->port->subordinate, PCI_DEVFN(0, 0));
 	if (!pdev)
 		return true;
diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c
index 736ad8baa2a5..8f3e4c7de961 100644
--- a/drivers/pci/hotplug/pciehp_hpc.c
+++ b/drivers/pci/hotplug/pciehp_hpc.c
@@ -842,7 +842,9 @@ void pcie_enable_interrupt(struct controller *ctrl)
 {
 	u16 mask;
 
-	mask = PCI_EXP_SLTCTL_HPIE | PCI_EXP_SLTCTL_DLLSCE;
+	mask = PCI_EXP_SLTCTL_DLLSCE;
+	if (!pciehp_poll_mode)
+		mask |= PCI_EXP_SLTCTL_HPIE;
 	pcie_write_cmd(ctrl, mask, mask);
 }
 
diff --git a/drivers/pci/hotplug/pnv_php.c b/drivers/pci/hotplug/pnv_php.c
index 573a41869c15..4f85e7fe29ec 100644
--- a/drivers/pci/hotplug/pnv_php.c
+++ b/drivers/pci/hotplug/pnv_php.c
@@ -3,12 +3,15 @@
  * PCI Hotplug Driver for PowerPC PowerNV platform.
  *
  * Copyright Gavin Shan, IBM Corporation 2016.
+ * Copyright (C) 2025 Raptor Engineering, LLC
+ * Copyright (C) 2025 Raptor Computing Systems, LLC
  */
 
 #include <linux/bitfield.h>
 #include <linux/libfdt.h>
 #include <linux/module.h>
 #include <linux/pci.h>
+#include <linux/delay.h>
 #include <linux/pci_hotplug.h>
 #include <linux/of_fdt.h>
 
@@ -36,8 +39,10 @@ static void pnv_php_register(struct device_node *dn);
 static void pnv_php_unregister_one(struct device_node *dn);
 static void pnv_php_unregister(struct device_node *dn);
 
+static void pnv_php_enable_irq(struct pnv_php_slot *php_slot);
+
 static void pnv_php_disable_irq(struct pnv_php_slot *php_slot,
-				bool disable_device)
+				bool disable_device, bool disable_msi)
 {
 	struct pci_dev *pdev = php_slot->pdev;
 	u16 ctrl;
@@ -53,19 +58,15 @@ static void pnv_php_disable_irq(struct pnv_php_slot *php_slot,
 		php_slot->irq = 0;
 	}
 
-	if (php_slot->wq) {
-		destroy_workqueue(php_slot->wq);
-		php_slot->wq = NULL;
-	}
-
-	if (disable_device) {
+	if (disable_device || disable_msi) {
 		if (pdev->msix_enabled)
 			pci_disable_msix(pdev);
 		else if (pdev->msi_enabled)
 			pci_disable_msi(pdev);
+	}
 
+	if (disable_device)
 		pci_disable_device(pdev);
-	}
 }
 
 static void pnv_php_free_slot(struct kref *kref)
@@ -74,7 +75,8 @@ static void pnv_php_free_slot(struct kref *kref)
 					struct pnv_php_slot, kref);
 
 	WARN_ON(!list_empty(&php_slot->children));
-	pnv_php_disable_irq(php_slot, false);
+	pnv_php_disable_irq(php_slot, false, false);
+	destroy_workqueue(php_slot->wq);
 	kfree(php_slot->name);
 	kfree(php_slot);
 }
@@ -391,6 +393,20 @@ static int pnv_php_get_power_state(struct hotplug_slot *slot, u8 *state)
 	return 0;
 }
 
+static int pcie_check_link_active(struct pci_dev *pdev)
+{
+	u16 lnk_status;
+	int ret;
+
+	ret = pcie_capability_read_word(pdev, PCI_EXP_LNKSTA, &lnk_status);
+	if (ret == PCIBIOS_DEVICE_NOT_FOUND || PCI_POSSIBLE_ERROR(lnk_status))
+		return -ENODEV;
+
+	ret = !!(lnk_status & PCI_EXP_LNKSTA_DLLLA);
+
+	return ret;
+}
+
 static int pnv_php_get_adapter_state(struct hotplug_slot *slot, u8 *state)
 {
 	struct pnv_php_slot *php_slot = to_pnv_php_slot(slot);
@@ -403,6 +419,19 @@ static int pnv_php_get_adapter_state(struct hotplug_slot *slot, u8 *state)
 	 */
 	ret = pnv_pci_get_presence_state(php_slot->id, &presence);
 	if (ret >= 0) {
+		if (pci_pcie_type(php_slot->pdev) == PCI_EXP_TYPE_DOWNSTREAM &&
+			presence == OPAL_PCI_SLOT_EMPTY) {
+			/*
+			 * Similar to pciehp_hpc, check whether the Link Active
+			 * bit is set to account for broken downstream bridges
+			 * that don't properly assert Presence Detect State, as
+			 * was observed on the Microsemi Switchtec PM8533 PFX
+			 * [11f8:8533].
+			 */
+			if (pcie_check_link_active(php_slot->pdev) > 0)
+				presence = OPAL_PCI_SLOT_PRESENT;
+		}
+
 		*state = presence;
 		ret = 0;
 	} else {
@@ -442,6 +471,61 @@ static int pnv_php_set_attention_state(struct hotplug_slot *slot, u8 state)
 	return 0;
 }
 
+static int pnv_php_activate_slot(struct pnv_php_slot *php_slot,
+				 struct hotplug_slot *slot)
+{
+	int ret, i;
+
+	/*
+	 * Issue initial slot activation command to firmware
+	 *
+	 * Firmware will power slot on, attempt to train the link, and
+	 * discover any downstream devices. If this process fails, firmware
+	 * will return an error code and an invalid device tree. Failure
+	 * can be caused for multiple reasons, including a faulty
+	 * downstream device, poor connection to the downstream device, or
+	 * a previously latched PHB fence.  On failure, issue fundamental
+	 * reset up to three times before aborting.
+	 */
+	ret = pnv_php_set_slot_power_state(slot, OPAL_PCI_SLOT_POWER_ON);
+	if (ret) {
+		SLOT_WARN(
+			php_slot,
+			"PCI slot activation failed with error code %d, possible frozen PHB",
+			ret);
+		SLOT_WARN(
+			php_slot,
+			"Attempting complete PHB reset before retrying slot activation\n");
+		for (i = 0; i < 3; i++) {
+			/*
+			 * Slot activation failed, PHB may be fenced from a
+			 * prior device failure.
+			 *
+			 * Use the OPAL fundamental reset call to both try a
+			 * device reset and clear any potentially active PHB
+			 * fence / freeze.
+			 */
+			SLOT_WARN(php_slot, "Try %d...\n", i + 1);
+			pci_set_pcie_reset_state(php_slot->pdev,
+						 pcie_warm_reset);
+			msleep(250);
+			pci_set_pcie_reset_state(php_slot->pdev,
+						 pcie_deassert_reset);
+
+			ret = pnv_php_set_slot_power_state(
+				slot, OPAL_PCI_SLOT_POWER_ON);
+			if (!ret)
+				break;
+		}
+
+		if (i >= 3)
+			SLOT_WARN(php_slot,
+				  "Failed to bring slot online, aborting!\n");
+	}
+
+	return ret;
+}
+
 static int pnv_php_enable(struct pnv_php_slot *php_slot, bool rescan)
 {
 	struct hotplug_slot *slot = &php_slot->slot;
@@ -504,7 +588,7 @@ static int pnv_php_enable(struct pnv_php_slot *php_slot, bool rescan)
 		goto scan;
 
 	/* Power is off, turn it on and then scan the slot */
-	ret = pnv_php_set_slot_power_state(slot, OPAL_PCI_SLOT_POWER_ON);
+	ret = pnv_php_activate_slot(php_slot, slot);
 	if (ret)
 		return ret;
 
@@ -561,8 +645,58 @@ static int pnv_php_reset_slot(struct hotplug_slot *slot, bool probe)
 static int pnv_php_enable_slot(struct hotplug_slot *slot)
 {
 	struct pnv_php_slot *php_slot = to_pnv_php_slot(slot);
+	u32 prop32;
+	int ret;
+
+	ret = pnv_php_enable(php_slot, true);
+	if (ret)
+		return ret;
+
+	/* (Re-)enable interrupt if the slot supports surprise hotplug */
+	ret = of_property_read_u32(php_slot->dn, "ibm,slot-surprise-pluggable",
+				   &prop32);
+	if (!ret && prop32)
+		pnv_php_enable_irq(php_slot);
+
+	return 0;
+}
+
+/*
+ * Disable any hotplug interrupts for all slots on the provided bus, as well as
+ * all downstream slots in preparation for a hot unplug.
+ */
+static int pnv_php_disable_all_irqs(struct pci_bus *bus)
+{
+	struct pci_bus *child_bus;
+	struct pci_slot *slot;
+
+	/* First go down child buses */
+	list_for_each_entry(child_bus, &bus->children, node)
+		pnv_php_disable_all_irqs(child_bus);
+
+	/* Disable IRQs for all pnv_php slots on this bus */
+	list_for_each_entry(slot, &bus->slots, list) {
+		struct pnv_php_slot *php_slot = to_pnv_php_slot(slot->hotplug);
 
-	return pnv_php_enable(php_slot, true);
+		pnv_php_disable_irq(php_slot, false, true);
+	}
+
+	return 0;
+}
+
+/*
+ * Disable any hotplug interrupts for all downstream slots on the provided
+ * bus in preparation for a hot unplug.
+ */
+static int pnv_php_disable_all_downstream_irqs(struct pci_bus *bus)
+{
+	struct pci_bus *child_bus;
+
+	/* Go down child buses, recursively deactivating their IRQs */
+	list_for_each_entry(child_bus, &bus->children, node)
+		pnv_php_disable_all_irqs(child_bus);
+
+	return 0;
 }
 
 static int pnv_php_disable_slot(struct hotplug_slot *slot)
@@ -579,6 +713,13 @@ static int pnv_php_disable_slot(struct hotplug_slot *slot)
 	    php_slot->state != PNV_PHP_STATE_REGISTERED)
 		return 0;
 
+	/*
+	 * Free all IRQ resources from all child slots before remove.
+	 * Note that we do not disable the root slot IRQ here as that
+	 * would also deactivate the slot hot (re)plug interrupt!
+	 */
+	pnv_php_disable_all_downstream_irqs(php_slot->bus);
+
 	/* Remove all devices behind the slot */
 	pci_lock_rescan_remove();
 	pci_hp_remove_devices(php_slot->bus);
@@ -647,6 +788,15 @@ static struct pnv_php_slot *pnv_php_alloc_slot(struct device_node *dn)
 		return NULL;
 	}
 
+	/* Allocate workqueue for this slot's interrupt handling */
+	php_slot->wq = alloc_workqueue("pciehp-%s", 0, 0, php_slot->name);
+	if (!php_slot->wq) {
+		SLOT_WARN(php_slot, "Cannot alloc workqueue\n");
+		kfree(php_slot->name);
+		kfree(php_slot);
+		return NULL;
+	}
+
 	if (dn->child && PCI_DN(dn->child))
 		php_slot->slot_no = PCI_SLOT(PCI_DN(dn->child)->devfn);
 	else
@@ -745,16 +895,63 @@ static int pnv_php_enable_msix(struct pnv_php_slot *php_slot)
 	return entry.vector;
 }
 
+static void
+pnv_php_detect_clear_suprise_removal_freeze(struct pnv_php_slot *php_slot)
+{
+	struct pci_dev *pdev = php_slot->pdev;
+	struct eeh_dev *edev;
+	struct eeh_pe *pe;
+	int i, rc;
+
+	/*
+	 * When a device is surprise removed from a downstream bridge slot,
+	 * the upstream bridge port can still end up frozen due to related EEH
+	 * events, which will in turn block the MSI interrupts for slot hotplug
+	 * detection.
+	 *
+	 * Detect and thaw any frozen upstream PE after slot deactivation.
+	 */
+	edev = pci_dev_to_eeh_dev(pdev);
+	pe = edev ? edev->pe : NULL;
+	rc = eeh_pe_get_state(pe);
+	if ((rc == -ENODEV) || (rc == -ENOENT)) {
+		SLOT_WARN(
+			php_slot,
+			"Upstream bridge PE state unknown, hotplug detect may fail\n");
+	} else {
+		if (pe->state & EEH_PE_ISOLATED) {
+			SLOT_WARN(
+				php_slot,
+				"Upstream bridge PE %02x frozen, thawing...\n",
+				pe->addr);
+			for (i = 0; i < 3; i++)
+				if (!eeh_unfreeze_pe(pe))
+					break;
+			if (i >= 3)
+				SLOT_WARN(
+					php_slot,
+					"Unable to thaw PE %02x, hotplug detect will fail!\n",
+					pe->addr);
+			else
+				SLOT_WARN(php_slot,
+					  "PE %02x thawed successfully\n",
+					  pe->addr);
+		}
+	}
+}
+
 static void pnv_php_event_handler(struct work_struct *work)
 {
 	struct pnv_php_event *event =
 		container_of(work, struct pnv_php_event, work);
 	struct pnv_php_slot *php_slot = event->php_slot;
 
-	if (event->added)
+	if (event->added) {
 		pnv_php_enable_slot(&php_slot->slot);
-	else
+	} else {
 		pnv_php_disable_slot(&php_slot->slot);
+		pnv_php_detect_clear_suprise_removal_freeze(php_slot);
+	}
 
 	kfree(event);
 }
@@ -843,14 +1040,6 @@ static void pnv_php_init_irq(struct pnv_php_slot *php_slot, int irq)
 	u16 sts, ctrl;
 	int ret;
 
-	/* Allocate workqueue */
-	php_slot->wq = alloc_workqueue("pciehp-%s", 0, 0, php_slot->name);
-	if (!php_slot->wq) {
-		SLOT_WARN(php_slot, "Cannot alloc workqueue\n");
-		pnv_php_disable_irq(php_slot, true);
-		return;
-	}
-
 	/* Check PDC (Presence Detection Change) is broken or not */
 	ret = of_property_read_u32(php_slot->dn, "ibm,slot-broken-pdc",
 				   &broken_pdc);
@@ -869,7 +1058,7 @@ static void pnv_php_init_irq(struct pnv_php_slot *php_slot, int irq)
 	ret = request_irq(irq, pnv_php_interrupt, IRQF_SHARED,
 			  php_slot->name, php_slot);
 	if (ret) {
-		pnv_php_disable_irq(php_slot, true);
+		pnv_php_disable_irq(php_slot, true, true);
 		SLOT_WARN(php_slot, "Error %d enabling IRQ %d\n", ret, irq);
 		return;
 	}
diff --git a/drivers/pci/hotplug/s390_pci_hpc.c b/drivers/pci/hotplug/s390_pci_hpc.c
index 055518ee354d..d9996516f49e 100644
--- a/drivers/pci/hotplug/s390_pci_hpc.c
+++ b/drivers/pci/hotplug/s390_pci_hpc.c
@@ -59,16 +59,15 @@ static int disable_slot(struct hotplug_slot *hotplug_slot)
 
 	pdev = pci_get_slot(zdev->zbus->bus, zdev->devfn);
 	if (pdev && pci_num_vf(pdev)) {
-		pci_dev_put(pdev);
 		rc = -EBUSY;
 		goto out;
 	}
 
 	rc = zpci_deconfigure_device(zdev);
 out:
-	mutex_unlock(&zdev->state_lock);
 	if (pdev)
 		pci_dev_put(pdev);
+	mutex_unlock(&zdev->state_lock);
 	return rc;
 }
 
diff --git a/drivers/pci/iomap.c b/drivers/pci/iomap.c
index 9fb7cacc15cd..fe706ed946df 100644
--- a/drivers/pci/iomap.c
+++ b/drivers/pci/iomap.c
@@ -9,6 +9,8 @@
 
 #include <linux/export.h>
 
+#include "pci.h" /* for pci_bar_index_is_valid() */
+
 /**
  * pci_iomap_range - create a virtual mapping cookie for a PCI BAR
  * @dev: PCI device that owns the BAR
@@ -33,12 +35,19 @@ void __iomem *pci_iomap_range(struct pci_dev *dev,
 			      unsigned long offset,
 			      unsigned long maxlen)
 {
-	resource_size_t start = pci_resource_start(dev, bar);
-	resource_size_t len = pci_resource_len(dev, bar);
-	unsigned long flags = pci_resource_flags(dev, bar);
+	resource_size_t start, len;
+	unsigned long flags;
+
+	if (!pci_bar_index_is_valid(bar))
+		return NULL;
+
+	start = pci_resource_start(dev, bar);
+	len = pci_resource_len(dev, bar);
+	flags = pci_resource_flags(dev, bar);
 
 	if (len <= offset || !start)
 		return NULL;
+
 	len -= offset;
 	start += offset;
 	if (maxlen && len > maxlen)
@@ -77,16 +86,20 @@ void __iomem *pci_iomap_wc_range(struct pci_dev *dev,
 				 unsigned long offset,
 				 unsigned long maxlen)
 {
-	resource_size_t start = pci_resource_start(dev, bar);
-	resource_size_t len = pci_resource_len(dev, bar);
-	unsigned long flags = pci_resource_flags(dev, bar);
+	resource_size_t start, len;
+	unsigned long flags;
 
-
-	if (flags & IORESOURCE_IO)
+	if (!pci_bar_index_is_valid(bar))
 		return NULL;
 
+	start = pci_resource_start(dev, bar);
+	len = pci_resource_len(dev, bar);
+	flags = pci_resource_flags(dev, bar);
+
 	if (len <= offset || !start)
 		return NULL;
+	if (flags & IORESOURCE_IO)
+		return NULL;
 
 	len -= offset;
 	start += offset;
diff --git a/drivers/pci/msi/msi.c b/drivers/pci/msi/msi.c
index 2f647cac4cae..8b8848788618 100644
--- a/drivers/pci/msi/msi.c
+++ b/drivers/pci/msi/msi.c
@@ -10,12 +10,12 @@
 #include <linux/err.h>
 #include <linux/export.h>
 #include <linux/irq.h>
+#include <linux/irqdomain.h>
 
 #include "../pci.h"
 #include "msi.h"
 
 int pci_msi_enable = 1;
-int pci_msi_ignore_mask;
 
 /**
  * pci_msi_supported - check whether MSI may be enabled on a device
@@ -295,8 +295,7 @@ static int msi_setup_msi_desc(struct pci_dev *dev, int nvec,
 	/* Lies, damned lies, and MSIs */
 	if (dev->dev_flags & PCI_DEV_FLAGS_HAS_MSI_MASKING)
 		control |= PCI_MSI_FLAGS_MASKBIT;
-	/* Respect XEN's mask disabling */
-	if (pci_msi_ignore_mask)
+	if (pci_msi_domain_supports(dev, MSI_FLAG_NO_MASK, DENY_LEGACY))
 		control &= ~PCI_MSI_FLAGS_MASKBIT;
 
 	desc.nvec_used			= nvec;
@@ -609,12 +608,16 @@ void msix_prepare_msi_desc(struct pci_dev *dev, struct msi_desc *desc)
 	desc->pci.msi_attrib.is_64		= 1;
 	desc->pci.msi_attrib.default_irq	= dev->irq;
 	desc->pci.mask_base			= dev->msix_base;
-	desc->pci.msi_attrib.can_mask		= !pci_msi_ignore_mask &&
-						  !desc->pci.msi_attrib.is_virtual;
 
-	if (desc->pci.msi_attrib.can_mask) {
+
+	if (!pci_msi_domain_supports(dev, MSI_FLAG_NO_MASK, DENY_LEGACY) &&
+	    !desc->pci.msi_attrib.is_virtual) {
 		void __iomem *addr = pci_msix_desc_addr(desc);
 
+		desc->pci.msi_attrib.can_mask = 1;
+		/* Workaround for SUN NIU insanity, which requires write before read */
+		if (dev->dev_flags & PCI_DEV_FLAGS_MSIX_TOUCH_ENTRY_DATA_FIRST)
+			writel(0, addr + PCI_MSIX_ENTRY_DATA);
 		desc->pci.msix_ctrl = readl(addr + PCI_MSIX_ENTRY_VECTOR_CTRL);
 	}
 }
@@ -659,9 +662,6 @@ static void msix_mask_all(void __iomem *base, int tsize)
 	u32 ctrl = PCI_MSIX_ENTRY_CTRL_MASKBIT;
 	int i;
 
-	if (pci_msi_ignore_mask)
-		return;
-
 	for (i = 0; i < tsize; i++, base += PCI_MSIX_ENTRY_SIZE)
 		writel(ctrl, base + PCI_MSIX_ENTRY_VECTOR_CTRL);
 }
@@ -744,15 +744,17 @@ static int msix_capability_init(struct pci_dev *dev, struct msix_entry *entries,
 	/* Disable INTX */
 	pci_intx_for_msi(dev, 0);
 
-	/*
-	 * Ensure that all table entries are masked to prevent
-	 * stale entries from firing in a crash kernel.
-	 *
-	 * Done late to deal with a broken Marvell NVME device
-	 * which takes the MSI-X mask bits into account even
-	 * when MSI-X is disabled, which prevents MSI delivery.
-	 */
-	msix_mask_all(dev->msix_base, tsize);
+	if (!pci_msi_domain_supports(dev, MSI_FLAG_NO_MASK, DENY_LEGACY)) {
+		/*
+		 * Ensure that all table entries are masked to prevent
+		 * stale entries from firing in a crash kernel.
+		 *
+		 * Done late to deal with a broken Marvell NVME device
+		 * which takes the MSI-X mask bits into account even
+		 * when MSI-X is disabled, which prevents MSI delivery.
+		 */
+		msix_mask_all(dev->msix_base, tsize);
+	}
 	pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_MASKALL, 0);
 
 	pcibios_free_irq(dev);
diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c
index af370628e583..99c58ee09fbb 100644
--- a/drivers/pci/pci-acpi.c
+++ b/drivers/pci/pci-acpi.c
@@ -816,13 +816,11 @@ int pci_acpi_program_hp_params(struct pci_dev *dev)
 bool pciehp_is_native(struct pci_dev *bridge)
 {
 	const struct pci_host_bridge *host;
-	u32 slot_cap;
 
 	if (!IS_ENABLED(CONFIG_HOTPLUG_PCI_PCIE))
 		return false;
 
-	pcie_capability_read_dword(bridge, PCI_EXP_SLTCAP, &slot_cap);
-	if (!(slot_cap & PCI_EXP_SLTCAP_HPC))
+	if (!bridge->is_pciehp)
 		return false;
 
 	if (pcie_ports_native)
diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index 3e5a117f5b5d..5af4a804a4f8 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -1444,7 +1444,7 @@ static ssize_t __resource_resize_store(struct device *dev, int n,
 		return -EINVAL;
 
 	device_lock(dev);
-	if (dev->driver) {
+	if (dev->driver || pci_num_vf(pdev)) {
 		ret = -EBUSY;
 		goto unlock;
 	}
@@ -1466,7 +1466,7 @@ static ssize_t __resource_resize_store(struct device *dev, int n,
 
 	pci_remove_resource_files(pdev);
 
-	for (i = 0; i < PCI_STD_NUM_BARS; i++) {
+	for (i = 0; i < PCI_BRIDGE_RESOURCES; i++) {
 		if (pci_resource_len(pdev, i) &&
 		    pci_resource_flags(pdev, i) == flags)
 			pci_release_resource(pdev, i);
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index dd3c6dcb47ae..3d1365f558d3 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -955,8 +955,10 @@ struct pci_acs {
 };
 
 static void __pci_config_acs(struct pci_dev *dev, struct pci_acs *caps,
-			     const char *p, u16 mask, u16 flags)
+			     const char *p, const u16 acs_mask, const u16 acs_flags)
 {
+	u16 flags = acs_flags;
+	u16 mask = acs_mask;
 	char *delimit;
 	int ret = 0;
 
@@ -964,7 +966,7 @@ static void __pci_config_acs(struct pci_dev *dev, struct pci_acs *caps,
 		return;
 
 	while (*p) {
-		if (!mask) {
+		if (!acs_mask) {
 			/* Check for ACS flags */
 			delimit = strstr(p, "@");
 			if (delimit) {
@@ -972,6 +974,8 @@ static void __pci_config_acs(struct pci_dev *dev, struct pci_acs *caps,
 				u32 shift = 0;
 
 				end = delimit - p - 1;
+				mask = 0;
+				flags = 0;
 
 				while (end > -1) {
 					if (*(p + end) == '0') {
@@ -1028,10 +1032,14 @@ static void __pci_config_acs(struct pci_dev *dev, struct pci_acs *caps,
 
 	pci_dbg(dev, "ACS mask  = %#06x\n", mask);
 	pci_dbg(dev, "ACS flags = %#06x\n", flags);
+	pci_dbg(dev, "ACS control = %#06x\n", caps->ctrl);
+	pci_dbg(dev, "ACS fw_ctrl = %#06x\n", caps->fw_ctrl);
 
-	/* If mask is 0 then we copy the bit from the firmware setting. */
-	caps->ctrl = (caps->ctrl & ~mask) | (caps->fw_ctrl & mask);
-	caps->ctrl |= flags;
+	/*
+	 * For mask bits that are 0, copy them from the firmware setting
+	 * and apply flags for all the mask bits that are 1.
+	 */
+	caps->ctrl = (caps->fw_ctrl & ~mask) | (flags & mask);
 
 	pci_info(dev, "Configured ACS to %#06x\n", caps->ctrl);
 }
@@ -3015,8 +3023,12 @@ static const struct dmi_system_id bridge_d3_blacklist[] = {
  * pci_bridge_d3_possible - Is it possible to put the bridge into D3
  * @bridge: Bridge to check
  *
- * This function checks if it is possible to move the bridge to D3.
- * Currently we only allow D3 for recent enough PCIe ports and Thunderbolt.
+ * Currently we only allow D3 for some PCIe ports and for Thunderbolt.
+ *
+ * Return: Whether it is possible to move the bridge to D3.
+ *
+ * The return value is guaranteed to be constant across the entire lifetime
+ * of the bridge, including its hot-removal.
  */
 bool pci_bridge_d3_possible(struct pci_dev *bridge)
 {
@@ -3060,10 +3072,10 @@ bool pci_bridge_d3_possible(struct pci_dev *bridge)
 			return false;
 
 		/*
-		 * It should be safe to put PCIe ports from 2015 or newer
-		 * to D3.
+		 * Out of caution, we only allow PCIe ports from 2015 or newer
+		 * into D3 on x86.
 		 */
-		if (dmi_get_bios_year() >= 2015)
+		if (!IS_ENABLED(CONFIG_X86) || dmi_get_bios_year() >= 2015)
 			return true;
 		break;
 	}
@@ -3914,6 +3926,9 @@ EXPORT_SYMBOL(pci_enable_atomic_ops_to_root);
  */
 void pci_release_region(struct pci_dev *pdev, int bar)
 {
+	if (!pci_bar_index_is_valid(bar))
+		return;
+
 	/*
 	 * This is done for backwards compatibility, because the old PCI devres
 	 * API had a mode in which the function became managed if it had been
@@ -3959,6 +3974,9 @@ EXPORT_SYMBOL(pci_release_region);
 static int __pci_request_region(struct pci_dev *pdev, int bar,
 				const char *res_name, int exclusive)
 {
+	if (!pci_bar_index_is_valid(bar))
+		return -EINVAL;
+
 	if (pci_is_managed(pdev)) {
 		if (exclusive == IORESOURCE_EXCLUSIVE)
 			return pcim_request_region_exclusive(pdev, bar, res_name);
@@ -4486,11 +4504,6 @@ void pci_disable_parity(struct pci_dev *dev)
  * @enable: boolean: whether to enable or disable PCI INTx
  *
  * Enables/disables PCI INTx for device @pdev
- *
- * NOTE:
- * This is a "hybrid" function: It's normally unmanaged, but becomes managed
- * when pcim_enable_device() has been called in advance. This hybrid feature is
- * DEPRECATED! If you want managed cleanup, use pcim_intx() instead.
  */
 void pci_intx(struct pci_dev *pdev, int enable)
 {
@@ -4503,15 +4516,10 @@ void pci_intx(struct pci_dev *pdev, int enable)
 	else
 		new = pci_command | PCI_COMMAND_INTX_DISABLE;
 
-	if (new != pci_command) {
-		/* Preserve the "hybrid" behavior for backwards compatibility */
-		if (pci_is_managed(pdev)) {
-			WARN_ON_ONCE(pcim_intx(pdev, enable) != 0);
-			return;
-		}
+	if (new == pci_command)
+		return;
 
-		pci_write_config_word(pdev, PCI_COMMAND, new);
-	}
+	pci_write_config_word(pdev, PCI_COMMAND, new);
 }
 EXPORT_SYMBOL_GPL(pci_intx);
 
@@ -4941,7 +4949,7 @@ int pci_bridge_wait_for_secondary_bus(struct pci_dev *dev, char *reset_type)
 		delay);
 	if (!pcie_wait_for_link_delay(dev, true, delay)) {
 		/* Did not train, no need to wait any further */
-		pci_info(dev, "Data Link Layer Link Active not set in 1000 msec\n");
+		pci_info(dev, "Data Link Layer Link Active not set in %d msec\n", delay);
 		return -ENOTTY;
 	}
 
@@ -5639,7 +5647,8 @@ static void pci_slot_unlock(struct pci_slot *slot)
 			continue;
 		if (dev->subordinate)
 			pci_bus_unlock(dev->subordinate);
-		pci_dev_unlock(dev);
+		else
+			pci_dev_unlock(dev);
 	}
 }
 
@@ -6194,38 +6203,66 @@ u32 pcie_bandwidth_available(struct pci_dev *dev, struct pci_dev **limiting_dev,
 EXPORT_SYMBOL(pcie_bandwidth_available);
 
 /**
- * pcie_get_speed_cap - query for the PCI device's link speed capability
+ * pcie_get_supported_speeds - query Supported Link Speed Vector
  * @dev: PCI device to query
  *
- * Query the PCI device speed capability.  Return the maximum link speed
- * supported by the device.
+ * Query @dev supported link speeds.
+ *
+ * Implementation Note in PCIe r6.0 sec 7.5.3.18 recommends determining
+ * supported link speeds using the Supported Link Speeds Vector in the Link
+ * Capabilities 2 Register (when available).
+ *
+ * Link Capabilities 2 was added in PCIe r3.0, sec 7.8.18.
+ *
+ * Without Link Capabilities 2, i.e., prior to PCIe r3.0, Supported Link
+ * Speeds field in Link Capabilities is used and only 2.5 GT/s and 5.0 GT/s
+ * speeds were defined.
+ *
+ * For @dev without Supported Link Speed Vector, the field is synthesized
+ * from the Max Link Speed field in the Link Capabilities Register.
+ *
+ * Return: Supported Link Speeds Vector (+ reserved 0 at LSB).
  */
-enum pci_bus_speed pcie_get_speed_cap(struct pci_dev *dev)
+u8 pcie_get_supported_speeds(struct pci_dev *dev)
 {
 	u32 lnkcap2, lnkcap;
+	u8 speeds;
 
 	/*
-	 * Link Capabilities 2 was added in PCIe r3.0, sec 7.8.18.  The
-	 * implementation note there recommends using the Supported Link
-	 * Speeds Vector in Link Capabilities 2 when supported.
-	 *
-	 * Without Link Capabilities 2, i.e., prior to PCIe r3.0, software
-	 * should use the Supported Link Speeds field in Link Capabilities,
-	 * where only 2.5 GT/s and 5.0 GT/s speeds were defined.
+	 * Speeds retain the reserved 0 at LSB before PCIe Supported Link
+	 * Speeds Vector to allow using SLS Vector bit defines directly.
 	 */
 	pcie_capability_read_dword(dev, PCI_EXP_LNKCAP2, &lnkcap2);
+	speeds = lnkcap2 & PCI_EXP_LNKCAP2_SLS;
+
+	/* Ignore speeds higher than Max Link Speed */
+	pcie_capability_read_dword(dev, PCI_EXP_LNKCAP, &lnkcap);
+	speeds &= GENMASK(lnkcap & PCI_EXP_LNKCAP_SLS, 0);
 
 	/* PCIe r3.0-compliant */
-	if (lnkcap2)
-		return PCIE_LNKCAP2_SLS2SPEED(lnkcap2);
+	if (speeds)
+		return speeds;
 
-	pcie_capability_read_dword(dev, PCI_EXP_LNKCAP, &lnkcap);
+	/* Synthesize from the Max Link Speed field */
 	if ((lnkcap & PCI_EXP_LNKCAP_SLS) == PCI_EXP_LNKCAP_SLS_5_0GB)
-		return PCIE_SPEED_5_0GT;
+		speeds = PCI_EXP_LNKCAP2_SLS_5_0GB | PCI_EXP_LNKCAP2_SLS_2_5GB;
 	else if ((lnkcap & PCI_EXP_LNKCAP_SLS) == PCI_EXP_LNKCAP_SLS_2_5GB)
-		return PCIE_SPEED_2_5GT;
+		speeds = PCI_EXP_LNKCAP2_SLS_2_5GB;
 
-	return PCI_SPEED_UNKNOWN;
+	return speeds;
+}
+
+/**
+ * pcie_get_speed_cap - query for the PCI device's link speed capability
+ * @dev: PCI device to query
+ *
+ * Query the PCI device speed capability.
+ *
+ * Return: the maximum link speed supported by the device.
+ */
+enum pci_bus_speed pcie_get_speed_cap(struct pci_dev *dev)
+{
+	return PCIE_LNKCAP2_SLS2SPEED(dev->supported_speeds);
 }
 EXPORT_SYMBOL(pcie_get_speed_cap);
 
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 1cdc2c9547a7..b65868e70951 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -165,6 +165,22 @@ static inline void pci_wakeup_event(struct pci_dev *dev)
 	pm_wakeup_event(&dev->dev, 100);
 }
 
+/**
+ * pci_bar_index_is_valid - Check whether a BAR index is within valid range
+ * @bar: BAR index
+ *
+ * Protects against overflowing &struct pci_dev.resource array.
+ *
+ * Return: true for valid index, false otherwise.
+ */
+static inline bool pci_bar_index_is_valid(int bar)
+{
+	if (bar >= 0 && bar < PCI_NUM_RESOURCES)
+		return true;
+
+	return false;
+}
+
 static inline bool pci_has_subordinate(struct pci_dev *pci_dev)
 {
 	return !!(pci_dev->subordinate);
@@ -374,6 +390,7 @@ static inline int pcie_dev_speed_mbps(enum pci_bus_speed speed)
 	return -EINVAL;
 }
 
+u8 pcie_get_supported_speeds(struct pci_dev *dev);
 const char *pci_speed_string(enum pci_bus_speed speed);
 enum pci_bus_speed pcie_get_speed_cap(struct pci_dev *dev);
 enum pcie_link_width pcie_get_width_cap(struct pci_dev *dev);
diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c
index cee2365e54b8..b8289b6c395b 100644
--- a/drivers/pci/pcie/aspm.c
+++ b/drivers/pci/pcie/aspm.c
@@ -81,24 +81,44 @@ void pci_configure_aspm_l1ss(struct pci_dev *pdev)
 
 void pci_save_aspm_l1ss_state(struct pci_dev *pdev)
 {
+	struct pci_dev *parent = pdev->bus->self;
 	struct pci_cap_saved_state *save_state;
-	u16 l1ss = pdev->l1ss;
 	u32 *cap;
 
 	/*
+	 * If this is a Downstream Port, we never restore the L1SS state
+	 * directly; we only restore it when we restore the state of the
+	 * Upstream Port below it.
+	 */
+	if (pcie_downstream_port(pdev) || !parent)
+		return;
+
+	if (!pdev->l1ss || !parent->l1ss)
+		return;
+
+	/*
 	 * Save L1 substate configuration. The ASPM L0s/L1 configuration
 	 * in PCI_EXP_LNKCTL_ASPMC is saved by pci_save_pcie_state().
 	 */
-	if (!l1ss)
+	save_state = pci_find_saved_ext_cap(pdev, PCI_EXT_CAP_ID_L1SS);
+	if (!save_state)
 		return;
 
-	save_state = pci_find_saved_ext_cap(pdev, PCI_EXT_CAP_ID_L1SS);
+	cap = &save_state->cap.data[0];
+	pci_read_config_dword(pdev, pdev->l1ss + PCI_L1SS_CTL2, cap++);
+	pci_read_config_dword(pdev, pdev->l1ss + PCI_L1SS_CTL1, cap++);
+
+	/*
+	 * Save parent's L1 substate configuration so we have it for
+	 * pci_restore_aspm_l1ss_state(pdev) to restore.
+	 */
+	save_state = pci_find_saved_ext_cap(parent, PCI_EXT_CAP_ID_L1SS);
 	if (!save_state)
 		return;
 
 	cap = &save_state->cap.data[0];
-	pci_read_config_dword(pdev, l1ss + PCI_L1SS_CTL2, cap++);
-	pci_read_config_dword(pdev, l1ss + PCI_L1SS_CTL1, cap++);
+	pci_read_config_dword(parent, parent->l1ss + PCI_L1SS_CTL2, cap++);
+	pci_read_config_dword(parent, parent->l1ss + PCI_L1SS_CTL1, cap++);
 }
 
 void pci_restore_aspm_l1ss_state(struct pci_dev *pdev)
@@ -805,6 +825,15 @@ static void pcie_aspm_cap_init(struct pcie_link_state *link, int blacklist)
 	pcie_capability_read_word(parent, PCI_EXP_LNKCTL, &parent_lnkctl);
 	pcie_capability_read_word(child, PCI_EXP_LNKCTL, &child_lnkctl);
 
+	/* Disable L0s/L1 before updating L1SS config */
+	if (FIELD_GET(PCI_EXP_LNKCTL_ASPMC, child_lnkctl) ||
+	    FIELD_GET(PCI_EXP_LNKCTL_ASPMC, parent_lnkctl)) {
+		pcie_capability_write_word(child, PCI_EXP_LNKCTL,
+					   child_lnkctl & ~PCI_EXP_LNKCTL_ASPMC);
+		pcie_capability_write_word(parent, PCI_EXP_LNKCTL,
+					   parent_lnkctl & ~PCI_EXP_LNKCTL_ASPMC);
+	}
+
 	/*
 	 * Setup L0s state
 	 *
@@ -829,6 +858,13 @@ static void pcie_aspm_cap_init(struct pcie_link_state *link, int blacklist)
 
 	aspm_l1ss_init(link);
 
+	/* Restore L0s/L1 if they were enabled */
+	if (FIELD_GET(PCI_EXP_LNKCTL_ASPMC, child_lnkctl) ||
+	    FIELD_GET(PCI_EXP_LNKCTL_ASPMC, parent_lnkctl)) {
+		pcie_capability_write_word(parent, PCI_EXP_LNKCTL, parent_lnkctl);
+		pcie_capability_write_word(child, PCI_EXP_LNKCTL, child_lnkctl);
+	}
+
 	/* Save default state */
 	link->aspm_default = link->aspm_enabled;
 
@@ -845,25 +881,28 @@ static void pcie_aspm_cap_init(struct pcie_link_state *link, int blacklist)
 	}
 }
 
-/* Configure the ASPM L1 substates */
+/* Configure the ASPM L1 substates. Caller must disable L1 first. */
 static void pcie_config_aspm_l1ss(struct pcie_link_state *link, u32 state)
 {
-	u32 val, enable_req;
+	u32 val;
 	struct pci_dev *child = link->downstream, *parent = link->pdev;
 
-	enable_req = (link->aspm_enabled ^ state) & state;
+	val = 0;
+	if (state & PCIE_LINK_STATE_L1_1)
+		val |= PCI_L1SS_CTL1_ASPM_L1_1;
+	if (state & PCIE_LINK_STATE_L1_2)
+		val |= PCI_L1SS_CTL1_ASPM_L1_2;
+	if (state & PCIE_LINK_STATE_L1_1_PCIPM)
+		val |= PCI_L1SS_CTL1_PCIPM_L1_1;
+	if (state & PCIE_LINK_STATE_L1_2_PCIPM)
+		val |= PCI_L1SS_CTL1_PCIPM_L1_2;
 
 	/*
-	 * Here are the rules specified in the PCIe spec for enabling L1SS:
-	 * - When enabling L1.x, enable bit at parent first, then at child
-	 * - When disabling L1.x, disable bit at child first, then at parent
-	 * - When enabling ASPM L1.x, need to disable L1
-	 *   (at child followed by parent).
-	 * - The ASPM/PCIPM L1.2 must be disabled while programming timing
+	 * PCIe r6.2, sec 5.5.4, rules for enabling L1 PM Substates:
+	 * - Clear L1.x enable bits at child first, then at parent
+	 * - Set L1.x enable bits at parent first, then at child
+	 * - ASPM/PCIPM L1.2 must be disabled while programming timing
 	 *   parameters
-	 *
-	 * To keep it simple, disable all L1SS bits first, and later enable
-	 * what is needed.
 	 */
 
 	/* Disable all L1 substates */
@@ -871,26 +910,6 @@ static void pcie_config_aspm_l1ss(struct pcie_link_state *link, u32 state)
 				       PCI_L1SS_CTL1_L1SS_MASK, 0);
 	pci_clear_and_set_config_dword(parent, parent->l1ss + PCI_L1SS_CTL1,
 				       PCI_L1SS_CTL1_L1SS_MASK, 0);
-	/*
-	 * If needed, disable L1, and it gets enabled later
-	 * in pcie_config_aspm_link().
-	 */
-	if (enable_req & (PCIE_LINK_STATE_L1_1 | PCIE_LINK_STATE_L1_2)) {
-		pcie_capability_clear_word(child, PCI_EXP_LNKCTL,
-					   PCI_EXP_LNKCTL_ASPM_L1);
-		pcie_capability_clear_word(parent, PCI_EXP_LNKCTL,
-					   PCI_EXP_LNKCTL_ASPM_L1);
-	}
-
-	val = 0;
-	if (state & PCIE_LINK_STATE_L1_1)
-		val |= PCI_L1SS_CTL1_ASPM_L1_1;
-	if (state & PCIE_LINK_STATE_L1_2)
-		val |= PCI_L1SS_CTL1_ASPM_L1_2;
-	if (state & PCIE_LINK_STATE_L1_1_PCIPM)
-		val |= PCI_L1SS_CTL1_PCIPM_L1_1;
-	if (state & PCIE_LINK_STATE_L1_2_PCIPM)
-		val |= PCI_L1SS_CTL1_PCIPM_L1_2;
 
 	/* Enable what we need to enable */
 	pci_clear_and_set_config_dword(parent, parent->l1ss + PCI_L1SS_CTL1,
@@ -937,21 +956,30 @@ static void pcie_config_aspm_link(struct pcie_link_state *link, u32 state)
 		dwstream |= PCI_EXP_LNKCTL_ASPM_L1;
 	}
 
+	/*
+	 * Per PCIe r6.2, sec 5.5.4, setting either or both of the enable
+	 * bits for ASPM L1 PM Substates must be done while ASPM L1 is
+	 * disabled. Disable L1 here and apply new configuration after L1SS
+	 * configuration has been completed.
+	 *
+	 * Per sec 7.5.3.7, when disabling ASPM L1, software must disable
+	 * it in the Downstream component prior to disabling it in the
+	 * Upstream component, and ASPM L1 must be enabled in the Upstream
+	 * component prior to enabling it in the Downstream component.
+	 *
+	 * Sec 7.5.3.7 also recommends programming the same ASPM Control
+	 * value for all functions of a multi-function device.
+	 */
+	list_for_each_entry(child, &linkbus->devices, bus_list)
+		pcie_config_aspm_dev(child, 0);
+	pcie_config_aspm_dev(parent, 0);
+
 	if (link->aspm_capable & PCIE_LINK_STATE_L1SS)
 		pcie_config_aspm_l1ss(link, state);
 
-	/*
-	 * Spec 2.0 suggests all functions should be configured the
-	 * same setting for ASPM. Enabling ASPM L1 should be done in
-	 * upstream component first and then downstream, and vice
-	 * versa for disabling ASPM L1. Spec doesn't mention L0S.
-	 */
-	if (state & PCIE_LINK_STATE_L1)
-		pcie_config_aspm_dev(parent, upstream);
+	pcie_config_aspm_dev(parent, upstream);
 	list_for_each_entry(child, &linkbus->devices, bus_list)
 		pcie_config_aspm_dev(child, dwstream);
-	if (!(state & PCIE_LINK_STATE_L1))
-		pcie_config_aspm_dev(parent, upstream);
 
 	link->aspm_enabled = state;
 
@@ -1242,16 +1270,16 @@ void pcie_aspm_exit_link_state(struct pci_dev *pdev)
 	parent_link = link->parent;
 
 	/*
-	 * link->downstream is a pointer to the pci_dev of function 0.  If
-	 * we remove that function, the pci_dev is about to be deallocated,
-	 * so we can't use link->downstream again.  Free the link state to
-	 * avoid this.
+	 * Free the parent link state, no later than function 0 (i.e.
+	 * link->downstream) being removed.
 	 *
-	 * If we're removing a non-0 function, it's possible we could
-	 * retain the link state, but PCIe r6.0, sec 7.5.3.7, recommends
-	 * programming the same ASPM Control value for all functions of
-	 * multi-function devices, so disable ASPM for all of them.
+	 * Do not free the link state any earlier. If function 0 is a
+	 * switch upstream port, this link state is parent_link to all
+	 * subordinate ones.
 	 */
+	if (pdev != link->downstream)
+		goto out;
+
 	pcie_config_aspm_link(link, 0);
 	list_del(&link->sibling);
 	free_link_state(link);
@@ -1262,6 +1290,7 @@ void pcie_aspm_exit_link_state(struct pci_dev *pdev)
 		pcie_config_aspm_path(parent_link);
 	}
 
+ out:
 	mutex_unlock(&aspm_lock);
 	up_read(&pci_bus_sem);
 }
diff --git a/drivers/pci/pcie/dpc.c b/drivers/pci/pcie/dpc.c
index 2b6ef7efa3c1..cdc54315d879 100644
--- a/drivers/pci/pcie/dpc.c
+++ b/drivers/pci/pcie/dpc.c
@@ -260,40 +260,48 @@ static int dpc_get_aer_uncorrect_severity(struct pci_dev *dev,
 void dpc_process_error(struct pci_dev *pdev)
 {
 	u16 cap = pdev->dpc_cap, status, source, reason, ext_reason;
-	struct aer_err_info info;
+	struct aer_err_info info = {};
 
 	pci_read_config_word(pdev, cap + PCI_EXP_DPC_STATUS, &status);
-	pci_read_config_word(pdev, cap + PCI_EXP_DPC_SOURCE_ID, &source);
-
-	pci_info(pdev, "containment event, status:%#06x source:%#06x\n",
-		 status, source);
 
 	reason = status & PCI_EXP_DPC_STATUS_TRIGGER_RSN;
-	ext_reason = status & PCI_EXP_DPC_STATUS_TRIGGER_RSN_EXT;
-	pci_warn(pdev, "%s detected\n",
-		 (reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_UNCOR) ?
-		 "unmasked uncorrectable error" :
-		 (reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_NFE) ?
-		 "ERR_NONFATAL" :
-		 (reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_FE) ?
-		 "ERR_FATAL" :
-		 (ext_reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_RP_PIO) ?
-		 "RP PIO error" :
-		 (ext_reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_SW_TRIGGER) ?
-		 "software trigger" :
-		 "reserved error");
-
-	/* show RP PIO error detail information */
-	if (pdev->dpc_rp_extensions &&
-	    reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_IN_EXT &&
-	    ext_reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_RP_PIO)
-		dpc_process_rp_pio_error(pdev);
-	else if (reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_UNCOR &&
-		 dpc_get_aer_uncorrect_severity(pdev, &info) &&
-		 aer_get_device_error_info(pdev, &info)) {
-		aer_print_error(pdev, &info);
-		pci_aer_clear_nonfatal_status(pdev);
-		pci_aer_clear_fatal_status(pdev);
+
+	switch (reason) {
+	case PCI_EXP_DPC_STATUS_TRIGGER_RSN_UNCOR:
+		pci_warn(pdev, "containment event, status:%#06x: unmasked uncorrectable error detected\n",
+			 status);
+		if (dpc_get_aer_uncorrect_severity(pdev, &info) &&
+		    aer_get_device_error_info(pdev, &info)) {
+			aer_print_error(pdev, &info);
+			pci_aer_clear_nonfatal_status(pdev);
+			pci_aer_clear_fatal_status(pdev);
+		}
+		break;
+	case PCI_EXP_DPC_STATUS_TRIGGER_RSN_NFE:
+	case PCI_EXP_DPC_STATUS_TRIGGER_RSN_FE:
+		pci_read_config_word(pdev, cap + PCI_EXP_DPC_SOURCE_ID,
+				     &source);
+		pci_warn(pdev, "containment event, status:%#06x, %s received from %04x:%02x:%02x.%d\n",
+			 status,
+			 (reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_FE) ?
+				"ERR_FATAL" : "ERR_NONFATAL",
+			 pci_domain_nr(pdev->bus), PCI_BUS_NUM(source),
+			 PCI_SLOT(source), PCI_FUNC(source));
+		break;
+	case PCI_EXP_DPC_STATUS_TRIGGER_RSN_IN_EXT:
+		ext_reason = status & PCI_EXP_DPC_STATUS_TRIGGER_RSN_EXT;
+		pci_warn(pdev, "containment event, status:%#06x: %s detected\n",
+			 status,
+			 (ext_reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_RP_PIO) ?
+			 "RP PIO error" :
+			 (ext_reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_SW_TRIGGER) ?
+			 "software trigger" :
+			 "reserved error");
+		/* show RP PIO error detail information */
+		if (ext_reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_RP_PIO &&
+		    pdev->dpc_rp_extensions)
+			dpc_process_rp_pio_error(pdev);
+		break;
 	}
 }
 
diff --git a/drivers/pci/pcie/portdrv.c b/drivers/pci/pcie/portdrv.c
index 6af5e0425872..604c055f6078 100644
--- a/drivers/pci/pcie/portdrv.c
+++ b/drivers/pci/pcie/portdrv.c
@@ -228,10 +228,12 @@ static int get_port_device_capability(struct pci_dev *dev)
 
 		/*
 		 * Disable hot-plug interrupts in case they have been enabled
-		 * by the BIOS and the hot-plug service driver is not loaded.
+		 * by the BIOS and the hot-plug service driver won't be loaded
+		 * to handle them.
 		 */
-		pcie_capability_clear_word(dev, PCI_EXP_SLTCTL,
-			  PCI_EXP_SLTCTL_CCIE | PCI_EXP_SLTCTL_HPIE);
+		if (!IS_ENABLED(CONFIG_HOTPLUG_PCI_PCIE))
+			pcie_capability_clear_word(dev, PCI_EXP_SLTCTL,
+				PCI_EXP_SLTCTL_CCIE | PCI_EXP_SLTCTL_HPIE);
 	}
 
 #ifdef CONFIG_PCIEAER
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index ebb0c1d5cae2..b358b93a0275 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -908,6 +908,7 @@ static int pci_register_host_bridge(struct pci_host_bridge *bridge)
 	resource_size_t offset, next_offset;
 	LIST_HEAD(resources);
 	struct resource *res, *next_res;
+	bool bus_registered = false;
 	char addr[64], *fmt;
 	const char *name;
 	int err;
@@ -950,10 +951,9 @@ static int pci_register_host_bridge(struct pci_host_bridge *bridge)
 	/* Temporarily move resources off the list */
 	list_splice_init(&bridge->windows, &resources);
 	err = device_add(&bridge->dev);
-	if (err) {
-		put_device(&bridge->dev);
+	if (err)
 		goto free;
-	}
+
 	bus->bridge = get_device(&bridge->dev);
 	device_enable_async_suspend(bus->bridge);
 	pci_set_bus_of_node(bus);
@@ -972,6 +972,7 @@ static int pci_register_host_bridge(struct pci_host_bridge *bridge)
 	name = dev_name(&bus->dev);
 
 	err = device_register(&bus->dev);
+	bus_registered = true;
 	if (err)
 		goto unregister;
 
@@ -1058,12 +1059,15 @@ static int pci_register_host_bridge(struct pci_host_bridge *bridge)
 unregister:
 	put_device(&bridge->dev);
 	device_del(&bridge->dev);
-
 free:
 #ifdef CONFIG_PCI_DOMAINS_GENERIC
 	pci_bus_release_domain_nr(parent, bus->domain_nr);
 #endif
-	kfree(bus);
+	if (bus_registered)
+		put_device(&bus->dev);
+	else
+		kfree(bus);
+
 	return err;
 }
 
@@ -1172,7 +1176,10 @@ static struct pci_bus *pci_alloc_child_bus(struct pci_bus *parent,
 add_dev:
 	pci_set_bus_msi_domain(child);
 	ret = device_register(&child->dev);
-	WARN_ON(ret < 0);
+	if (WARN_ON(ret < 0)) {
+		put_device(&child->dev);
+		return NULL;
+	}
 
 	pcibios_add_bus(child);
 
@@ -1328,8 +1335,6 @@ static int pci_scan_bridge_extend(struct pci_bus *bus, struct pci_dev *dev,
 	pci_write_config_word(dev, PCI_BRIDGE_CONTROL,
 			      bctl & ~PCI_BRIDGE_CTL_MASTER_ABORT);
 
-	pci_enable_rrs_sv(dev);
-
 	if ((secondary || subordinate) && !pcibios_assign_all_busses() &&
 	    !is_cardbus && !broken) {
 		unsigned int cmax, buses;
@@ -1570,6 +1575,11 @@ void set_pcie_port_type(struct pci_dev *pdev)
 	pdev->pcie_cap = pos;
 	pci_read_config_word(pdev, pos + PCI_EXP_FLAGS, &reg16);
 	pdev->pcie_flags_reg = reg16;
+
+	type = pci_pcie_type(pdev);
+	if (type == PCI_EXP_TYPE_ROOT_PORT)
+		pci_enable_rrs_sv(pdev);
+
 	pci_read_config_dword(pdev, pos + PCI_EXP_DEVCAP, &pdev->devcap);
 	pdev->pcie_mpss = FIELD_GET(PCI_EXP_DEVCAP_PAYLOAD, pdev->devcap);
 
@@ -1586,7 +1596,6 @@ void set_pcie_port_type(struct pci_dev *pdev)
 	 * correctly so detect impossible configurations here and correct
 	 * the port type accordingly.
 	 */
-	type = pci_pcie_type(pdev);
 	if (type == PCI_EXP_TYPE_DOWNSTREAM) {
 		/*
 		 * If pdev claims to be downstream port but the parent
@@ -1618,7 +1627,7 @@ void set_pcie_hotplug_bridge(struct pci_dev *pdev)
 
 	pcie_capability_read_dword(pdev, PCI_EXP_SLTCAP, &reg32);
 	if (reg32 & PCI_EXP_SLTCAP_HPC)
-		pdev->is_hotplug_bridge = 1;
+		pdev->is_hotplug_bridge = pdev->is_pciehp = 1;
 }
 
 static void set_pcie_thunderbolt(struct pci_dev *dev)
@@ -1963,6 +1972,9 @@ int pci_setup_device(struct pci_dev *dev)
 
 	set_pcie_untrusted(dev);
 
+	if (pci_is_pcie(dev))
+		dev->supported_speeds = pcie_get_supported_speeds(dev);
+
 	/* "Unknown power state" */
 	dev->current_state = PCI_UNKNOWN;
 
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index 8103bc24a54e..db609d26811b 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -4995,6 +4995,18 @@ static int pci_quirk_brcm_acs(struct pci_dev *dev, u16 acs_flags)
 		PCI_ACS_SV | PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF);
 }
 
+static int pci_quirk_loongson_acs(struct pci_dev *dev, u16 acs_flags)
+{
+	/*
+	 * Loongson PCIe Root Ports don't advertise an ACS capability, but
+	 * they do not allow peer-to-peer transactions between Root Ports.
+	 * Allow each Root Port to be in a separate IOMMU group by masking
+	 * SV/RR/CR/UF bits.
+	 */
+	return pci_acs_ctrl_enabled(acs_flags,
+		PCI_ACS_SV | PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF);
+}
+
 /*
  * Wangxun 40G/25G/10G/1G NICs have no ACS capability, but on
  * multi-function devices, the hardware isolates the functions by
@@ -5128,6 +5140,17 @@ static const struct pci_dev_acs_enabled {
 	{ PCI_VENDOR_ID_BROADCOM, 0x1762, pci_quirk_mf_endpoint_acs },
 	{ PCI_VENDOR_ID_BROADCOM, 0x1763, pci_quirk_mf_endpoint_acs },
 	{ PCI_VENDOR_ID_BROADCOM, 0xD714, pci_quirk_brcm_acs },
+	/* Loongson PCIe Root Ports */
+	{ PCI_VENDOR_ID_LOONGSON, 0x3C09, pci_quirk_loongson_acs },
+	{ PCI_VENDOR_ID_LOONGSON, 0x3C19, pci_quirk_loongson_acs },
+	{ PCI_VENDOR_ID_LOONGSON, 0x3C29, pci_quirk_loongson_acs },
+	{ PCI_VENDOR_ID_LOONGSON, 0x7A09, pci_quirk_loongson_acs },
+	{ PCI_VENDOR_ID_LOONGSON, 0x7A19, pci_quirk_loongson_acs },
+	{ PCI_VENDOR_ID_LOONGSON, 0x7A29, pci_quirk_loongson_acs },
+	{ PCI_VENDOR_ID_LOONGSON, 0x7A39, pci_quirk_loongson_acs },
+	{ PCI_VENDOR_ID_LOONGSON, 0x7A49, pci_quirk_loongson_acs },
+	{ PCI_VENDOR_ID_LOONGSON, 0x7A59, pci_quirk_loongson_acs },
+	{ PCI_VENDOR_ID_LOONGSON, 0x7A69, pci_quirk_loongson_acs },
 	/* Amazon Annapurna Labs */
 	{ PCI_VENDOR_ID_AMAZON_ANNAPURNA_LABS, 0x0031, pci_quirk_al_acs },
 	/* Zhaoxin multi-function devices */
@@ -5522,7 +5545,7 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x443, quirk_intel_qat_vf_cap);
  * AMD Matisse USB 3.0 Host Controller 0x149c
  * Intel 82579LM Gigabit Ethernet Controller 0x1502
  * Intel 82579V Gigabit Ethernet Controller 0x1503
- *
+ * Mediatek MT7922 802.11ax PCI Express Wireless Network Adapter
  */
 static void quirk_no_flr(struct pci_dev *dev)
 {
@@ -5534,6 +5557,7 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_AMD, 0x149c, quirk_no_flr);
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_AMD, 0x7901, quirk_no_flr);
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x1502, quirk_no_flr);
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x1503, quirk_no_flr);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_MEDIATEK, 0x0616, quirk_no_flr);
 
 /* FLR may cause the SolidRun SNET DPU (rev 0x1) to hang */
 static void quirk_no_flr_snet(struct pci_dev *dev)
@@ -5985,6 +6009,17 @@ SWITCHTEC_QUIRK(0x5552);  /* PAXA 52XG5 */
 SWITCHTEC_QUIRK(0x5536);  /* PAXA 36XG5 */
 SWITCHTEC_QUIRK(0x5528);  /* PAXA 28XG5 */
 
+#define SWITCHTEC_PCI100X_QUIRK(vid) \
+	DECLARE_PCI_FIXUP_CLASS_FINAL(PCI_VENDOR_ID_EFAR, vid, \
+		PCI_CLASS_BRIDGE_OTHER, 8, quirk_switchtec_ntb_dma_alias)
+SWITCHTEC_PCI100X_QUIRK(0x1001);  /* PCI1001XG4 */
+SWITCHTEC_PCI100X_QUIRK(0x1002);  /* PCI1002XG4 */
+SWITCHTEC_PCI100X_QUIRK(0x1003);  /* PCI1003XG4 */
+SWITCHTEC_PCI100X_QUIRK(0x1004);  /* PCI1004XG4 */
+SWITCHTEC_PCI100X_QUIRK(0x1005);  /* PCI1005XG4 */
+SWITCHTEC_PCI100X_QUIRK(0x1006);  /* PCI1006XG4 */
+
+
 /*
  * The PLX NTB uses devfn proxy IDs to move TLPs between NT endpoints.
  * These IDs are used to forward responses to the originator on the other
@@ -6254,6 +6289,7 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x9a2b, dpc_log_size);
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x9a2d, dpc_log_size);
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x9a2f, dpc_log_size);
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x9a31, dpc_log_size);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0xa72f, dpc_log_size);
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0xa73f, dpc_log_size);
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0xa76e, dpc_log_size);
 #endif
diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c
index 23082bc0ca37..1eceabef9e84 100644
--- a/drivers/pci/setup-bus.c
+++ b/drivers/pci/setup-bus.c
@@ -814,11 +814,9 @@ static resource_size_t calculate_iosize(resource_size_t size,
 	size = (size & 0xff) + ((size & ~0xffUL) << 2);
 #endif
 	size = size + size1;
-	if (size < old_size)
-		size = old_size;
 
-	size = ALIGN(max(size, add_size) + children_add_size, align);
-	return size;
+	size = max(size, add_size) + children_add_size;
+	return ALIGN(max(size, old_size), align);
 }
 
 static resource_size_t calculate_memsize(resource_size_t size,
@@ -1150,7 +1148,6 @@ static int pbus_size_mem(struct pci_bus *bus, unsigned long mask,
 		min_align = 1ULL << (max_order + __ffs(SZ_1M));
 		min_align = max(min_align, win_align);
 		size0 = calculate_memsize(size, min_size, 0, 0, resource_size(b_res), win_align);
-		add_align = win_align;
 		pci_info(bus->self, "bridge window %pR to %pR requires relaxed alignment rules\n",
 			 b_res, &bus->busn_res);
 	}
@@ -2105,8 +2102,7 @@ pci_root_bus_distribute_available_resources(struct pci_bus *bus,
 		 * in case of root bus.
 		 */
 		if (bridge && pci_bridge_resources_not_assigned(dev))
-			pci_bridge_distribute_available_resources(bridge,
-								  add_list);
+			pci_bridge_distribute_available_resources(dev, add_list);
 		else
 			pci_root_bus_distribute_available_resources(b, add_list);
 	}
diff --git a/drivers/pci/switch/switchtec.c b/drivers/pci/switch/switchtec.c
index c7e1089ffdaf..b14dfab04d84 100644
--- a/drivers/pci/switch/switchtec.c
+++ b/drivers/pci/switch/switchtec.c
@@ -1739,6 +1739,26 @@ static void switchtec_pci_remove(struct pci_dev *pdev)
 		.driver_data = gen, \
 	}
 
+#define SWITCHTEC_PCI100X_DEVICE(device_id, gen) \
+	{ \
+		.vendor     = PCI_VENDOR_ID_EFAR, \
+		.device     = device_id, \
+		.subvendor  = PCI_ANY_ID, \
+		.subdevice  = PCI_ANY_ID, \
+		.class      = (PCI_CLASS_MEMORY_OTHER << 8), \
+		.class_mask = 0xFFFFFFFF, \
+		.driver_data = gen, \
+	}, \
+	{ \
+		.vendor     = PCI_VENDOR_ID_EFAR, \
+		.device     = device_id, \
+		.subvendor  = PCI_ANY_ID, \
+		.subdevice  = PCI_ANY_ID, \
+		.class      = (PCI_CLASS_BRIDGE_OTHER << 8), \
+		.class_mask = 0xFFFFFFFF, \
+		.driver_data = gen, \
+	}
+
 static const struct pci_device_id switchtec_pci_tbl[] = {
 	SWITCHTEC_PCI_DEVICE(0x8531, SWITCHTEC_GEN3),  /* PFX 24xG3 */
 	SWITCHTEC_PCI_DEVICE(0x8532, SWITCHTEC_GEN3),  /* PFX 32xG3 */
@@ -1833,6 +1853,12 @@ static const struct pci_device_id switchtec_pci_tbl[] = {
 	SWITCHTEC_PCI_DEVICE(0x5552, SWITCHTEC_GEN5),  /* PAXA 52XG5 */
 	SWITCHTEC_PCI_DEVICE(0x5536, SWITCHTEC_GEN5),  /* PAXA 36XG5 */
 	SWITCHTEC_PCI_DEVICE(0x5528, SWITCHTEC_GEN5),  /* PAXA 28XG5 */
+	SWITCHTEC_PCI100X_DEVICE(0x1001, SWITCHTEC_GEN4),  /* PCI1001 16XG4 */
+	SWITCHTEC_PCI100X_DEVICE(0x1002, SWITCHTEC_GEN4),  /* PCI1002 12XG4 */
+	SWITCHTEC_PCI100X_DEVICE(0x1003, SWITCHTEC_GEN4),  /* PCI1003 16XG4 */
+	SWITCHTEC_PCI100X_DEVICE(0x1004, SWITCHTEC_GEN4),  /* PCI1004 16XG4 */
+	SWITCHTEC_PCI100X_DEVICE(0x1005, SWITCHTEC_GEN4),  /* PCI1005 16XG4 */
+	SWITCHTEC_PCI100X_DEVICE(0x1006, SWITCHTEC_GEN4),  /* PCI1006 16XG4 */
 	{0}
 };
 MODULE_DEVICE_TABLE(pci, switchtec_pci_tbl);
diff --git a/drivers/perf/amlogic/meson_ddr_pmu_core.c b/drivers/perf/amlogic/meson_ddr_pmu_core.c
index 07446d784a1a..c1e755c356a3 100644
--- a/drivers/perf/amlogic/meson_ddr_pmu_core.c
+++ b/drivers/perf/amlogic/meson_ddr_pmu_core.c
@@ -511,7 +511,7 @@ int meson_ddr_pmu_create(struct platform_device *pdev)
 
 	fmt_attr_fill(pmu->info.hw_info->fmt_attr);
 
-	pmu->cpu = smp_processor_id();
+	pmu->cpu = raw_smp_processor_id();
 
 	name = devm_kasprintf(&pdev->dev, GFP_KERNEL, DDR_PERF_DEV_NAME);
 	if (!name)
diff --git a/drivers/perf/arm-cmn.c b/drivers/perf/arm-cmn.c
index 30506c43776f..978b239ec10b 100644
--- a/drivers/perf/arm-cmn.c
+++ b/drivers/perf/arm-cmn.c
@@ -727,8 +727,8 @@ static umode_t arm_cmn_event_attr_is_visible(struct kobject *kobj,
 
 		if ((chan == 5 && cmn->rsp_vc_num < 2) ||
 		    (chan == 6 && cmn->dat_vc_num < 2) ||
-		    (chan == 7 && cmn->snp_vc_num < 2) ||
-		    (chan == 8 && cmn->req_vc_num < 2))
+		    (chan == 7 && cmn->req_vc_num < 2) ||
+		    (chan == 8 && cmn->snp_vc_num < 2))
 			return 0;
 	}
 
@@ -884,8 +884,8 @@ static umode_t arm_cmn_event_attr_is_visible(struct kobject *kobj,
 	_CMN_EVENT_XP(pub_##_name, (_event) | (4 << 5)),	\
 	_CMN_EVENT_XP(rsp2_##_name, (_event) | (5 << 5)),	\
 	_CMN_EVENT_XP(dat2_##_name, (_event) | (6 << 5)),	\
-	_CMN_EVENT_XP(snp2_##_name, (_event) | (7 << 5)),	\
-	_CMN_EVENT_XP(req2_##_name, (_event) | (8 << 5))
+	_CMN_EVENT_XP(req2_##_name, (_event) | (7 << 5)),	\
+	_CMN_EVENT_XP(snp2_##_name, (_event) | (8 << 5))
 
 #define CMN_EVENT_XP_DAT(_name, _event)				\
 	_CMN_EVENT_XP_PORT(dat_##_name, (_event) | (3 << 5)),	\
@@ -2557,6 +2557,7 @@ static int arm_cmn_probe(struct platform_device *pdev)
 
 	cmn->dev = &pdev->dev;
 	cmn->part = (unsigned long)device_get_match_data(cmn->dev);
+	cmn->cpu = cpumask_local_spread(0, dev_to_node(cmn->dev));
 	platform_set_drvdata(pdev, cmn);
 
 	if (cmn->part == PART_CMN600 && has_acpi_companion(cmn->dev)) {
@@ -2584,7 +2585,6 @@ static int arm_cmn_probe(struct platform_device *pdev)
 	if (err)
 		return err;
 
-	cmn->cpu = cpumask_local_spread(0, dev_to_node(cmn->dev));
 	cmn->pmu = (struct pmu) {
 		.module = THIS_MODULE,
 		.parent = cmn->dev,
@@ -2650,6 +2650,7 @@ static const struct acpi_device_id arm_cmn_acpi_match[] = {
 	{ "ARMHC600", PART_CMN600 },
 	{ "ARMHC650" },
 	{ "ARMHC700" },
+	{ "ARMHC003" },
 	{}
 };
 MODULE_DEVICE_TABLE(acpi, arm_cmn_acpi_match);
@@ -2660,6 +2661,7 @@ static struct platform_driver arm_cmn_driver = {
 		.name = "arm-cmn",
 		.of_match_table = of_match_ptr(arm_cmn_of_match),
 		.acpi_match_table = ACPI_PTR(arm_cmn_acpi_match),
+		.suppress_bind_attrs = true,
 	},
 	.probe = arm_cmn_probe,
 	.remove_new = arm_cmn_remove,
diff --git a/drivers/perf/arm-ni.c b/drivers/perf/arm-ni.c
index 90fcfe693439..fb09730a9aa0 100644
--- a/drivers/perf/arm-ni.c
+++ b/drivers/perf/arm-ni.c
@@ -545,6 +545,8 @@ static int arm_ni_init_cd(struct arm_ni *ni, struct arm_ni_node *node, u64 res_s
 		return err;
 
 	cd->cpu = cpumask_local_spread(0, dev_to_node(ni->dev));
+	irq_set_affinity(cd->irq, cpumask_of(cd->cpu));
+
 	cd->pmu = (struct pmu) {
 		.module = THIS_MODULE,
 		.parent = ni->dev,
@@ -576,6 +578,23 @@ static int arm_ni_init_cd(struct arm_ni *ni, struct arm_ni_node *node, u64 res_s
 	return err;
 }
 
+static void arm_ni_remove(struct platform_device *pdev)
+{
+	struct arm_ni *ni = platform_get_drvdata(pdev);
+
+	for (int i = 0; i < ni->num_cds; i++) {
+		struct arm_ni_cd *cd = ni->cds + i;
+
+		if (!cd->pmu_base)
+			continue;
+
+		writel_relaxed(0, cd->pmu_base + NI_PMCR);
+		writel_relaxed(U32_MAX, cd->pmu_base + NI_PMINTENCLR);
+		perf_pmu_unregister(&cd->pmu);
+		cpuhp_state_remove_instance_nocalls(arm_ni_hp_state, &cd->cpuhp_node);
+	}
+}
+
 static void arm_ni_probe_domain(void __iomem *base, struct arm_ni_node *node)
 {
 	u32 reg = readl_relaxed(base + NI_NODE_TYPE);
@@ -644,6 +663,7 @@ static int arm_ni_probe(struct platform_device *pdev)
 	ni->num_cds = num_cds;
 	ni->part = part;
 	ni->id = atomic_fetch_inc(&id);
+	platform_set_drvdata(pdev, ni);
 
 	for (int v = 0; v < cfg.num_components; v++) {
 		reg = readl_relaxed(cfg.base + NI_CHILD_PTR(v));
@@ -657,8 +677,11 @@ static int arm_ni_probe(struct platform_device *pdev)
 				reg = readl_relaxed(pd.base + NI_CHILD_PTR(c));
 				arm_ni_probe_domain(base + reg, &cd);
 				ret = arm_ni_init_cd(ni, &cd, res->start);
-				if (ret)
+				if (ret) {
+					ni->cds[cd.id].pmu_base = NULL;
+					arm_ni_remove(pdev);
 					return ret;
+				}
 			}
 		}
 	}
@@ -666,23 +689,6 @@ static int arm_ni_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static void arm_ni_remove(struct platform_device *pdev)
-{
-	struct arm_ni *ni = platform_get_drvdata(pdev);
-
-	for (int i = 0; i < ni->num_cds; i++) {
-		struct arm_ni_cd *cd = ni->cds + i;
-
-		if (!cd->pmu_base)
-			continue;
-
-		writel_relaxed(0, cd->pmu_base + NI_PMCR);
-		writel_relaxed(U32_MAX, cd->pmu_base + NI_PMINTENCLR);
-		perf_pmu_unregister(&cd->pmu);
-		cpuhp_state_remove_instance_nocalls(arm_ni_hp_state, &cd->cpuhp_node);
-	}
-}
-
 #ifdef CONFIG_OF
 static const struct of_device_id arm_ni_of_match[] = {
 	{ .compatible = "arm,ni-700" },
@@ -704,6 +710,7 @@ static struct platform_driver arm_ni_driver = {
 		.name = "arm-ni",
 		.of_match_table = of_match_ptr(arm_ni_of_match),
 		.acpi_match_table = ACPI_PTR(arm_ni_acpi_match),
+		.suppress_bind_attrs = true,
 	},
 	.probe = arm_ni_probe,
 	.remove = arm_ni_remove,
diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c
index 398cce3d76fc..2f33e69a8caf 100644
--- a/drivers/perf/arm_pmu.c
+++ b/drivers/perf/arm_pmu.c
@@ -342,12 +342,10 @@ armpmu_add(struct perf_event *event, int flags)
 	if (idx < 0)
 		return idx;
 
-	/*
-	 * If there is an event in the counter we are going to use then make
-	 * sure it is disabled.
-	 */
+	/* The newly-allocated counter should be empty */
+	WARN_ON_ONCE(hw_events->events[idx]);
+
 	event->hw.idx = idx;
-	armpmu->disable(event);
 	hw_events->events[idx] = event;
 
 	hwc->state = PERF_HES_STOPPED | PERF_HES_UPTODATE;
diff --git a/drivers/perf/arm_pmuv3.c b/drivers/perf/arm_pmuv3.c
index 0afe02f879b4..d9b56f0f9094 100644
--- a/drivers/perf/arm_pmuv3.c
+++ b/drivers/perf/arm_pmuv3.c
@@ -816,10 +816,10 @@ static void armv8pmu_start(struct arm_pmu *cpu_pmu)
 	else
 		armv8pmu_disable_user_access();
 
+	kvm_vcpu_pmu_resync_el0();
+
 	/* Enable all counters */
 	armv8pmu_pmcr_write(armv8pmu_pmcr_read() | ARMV8_PMU_PMCR_E);
-
-	kvm_vcpu_pmu_resync_el0();
 }
 
 static void armv8pmu_stop(struct arm_pmu *cpu_pmu)
diff --git a/drivers/perf/cxl_pmu.c b/drivers/perf/cxl_pmu.c
index 43d68b69e630..16328569fde9 100644
--- a/drivers/perf/cxl_pmu.c
+++ b/drivers/perf/cxl_pmu.c
@@ -870,7 +870,7 @@ static int cxl_pmu_probe(struct device *dev)
 		return rc;
 	irq = rc;
 
-	irq_name = devm_kasprintf(dev, GFP_KERNEL, "%s_overflow\n", dev_name);
+	irq_name = devm_kasprintf(dev, GFP_KERNEL, "%s_overflow", dev_name);
 	if (!irq_name)
 		return -ENOMEM;
 
diff --git a/drivers/perf/dwc_pcie_pmu.c b/drivers/perf/dwc_pcie_pmu.c
index 4ca50f9b6dfe..7dbda36884c8 100644
--- a/drivers/perf/dwc_pcie_pmu.c
+++ b/drivers/perf/dwc_pcie_pmu.c
@@ -567,8 +567,10 @@ static int dwc_pcie_register_dev(struct pci_dev *pdev)
 		return PTR_ERR(plat_dev);
 
 	dev_info = kzalloc(sizeof(*dev_info), GFP_KERNEL);
-	if (!dev_info)
+	if (!dev_info) {
+		platform_device_unregister(plat_dev);
 		return -ENOMEM;
+	}
 
 	/* Cache platform device to handle pci device hotplug */
 	dev_info->plat_dev = plat_dev;
@@ -724,6 +726,15 @@ static struct platform_driver dwc_pcie_pmu_driver = {
 	.driver = {.name = "dwc_pcie_pmu",},
 };
 
+static void dwc_pcie_cleanup_devices(void)
+{
+	struct dwc_pcie_dev_info *dev_info, *tmp;
+
+	list_for_each_entry_safe(dev_info, tmp, &dwc_pcie_dev_info_head, dev_node) {
+		dwc_pcie_unregister_dev(dev_info);
+	}
+}
+
 static int __init dwc_pcie_pmu_init(void)
 {
 	struct pci_dev *pdev = NULL;
@@ -736,7 +747,7 @@ static int __init dwc_pcie_pmu_init(void)
 		ret = dwc_pcie_register_dev(pdev);
 		if (ret) {
 			pci_dev_put(pdev);
-			return ret;
+			goto err_cleanup;
 		}
 	}
 
@@ -745,35 +756,35 @@ static int __init dwc_pcie_pmu_init(void)
 				      dwc_pcie_pmu_online_cpu,
 				      dwc_pcie_pmu_offline_cpu);
 	if (ret < 0)
-		return ret;
+		goto err_cleanup;
 
 	dwc_pcie_pmu_hp_state = ret;
 
 	ret = platform_driver_register(&dwc_pcie_pmu_driver);
 	if (ret)
-		goto platform_driver_register_err;
+		goto err_remove_cpuhp;
 
 	ret = bus_register_notifier(&pci_bus_type, &dwc_pcie_pmu_nb);
 	if (ret)
-		goto platform_driver_register_err;
+		goto err_unregister_driver;
 	notify = true;
 
 	return 0;
 
-platform_driver_register_err:
+err_unregister_driver:
+	platform_driver_unregister(&dwc_pcie_pmu_driver);
+err_remove_cpuhp:
 	cpuhp_remove_multi_state(dwc_pcie_pmu_hp_state);
-
+err_cleanup:
+	dwc_pcie_cleanup_devices();
 	return ret;
 }
 
 static void __exit dwc_pcie_pmu_exit(void)
 {
-	struct dwc_pcie_dev_info *dev_info, *tmp;
-
 	if (notify)
 		bus_unregister_notifier(&pci_bus_type, &dwc_pcie_pmu_nb);
-	list_for_each_entry_safe(dev_info, tmp, &dwc_pcie_dev_info_head, dev_node)
-		dwc_pcie_unregister_dev(dev_info);
+	dwc_pcie_cleanup_devices();
 	platform_driver_unregister(&dwc_pcie_pmu_driver);
 	cpuhp_remove_multi_state(dwc_pcie_pmu_hp_state);
 }
diff --git a/drivers/phy/freescale/phy-fsl-imx8m-pcie.c b/drivers/phy/freescale/phy-fsl-imx8m-pcie.c
index e98361dcdead..afd52392cd53 100644
--- a/drivers/phy/freescale/phy-fsl-imx8m-pcie.c
+++ b/drivers/phy/freescale/phy-fsl-imx8m-pcie.c
@@ -162,6 +162,16 @@ static int imx8_pcie_phy_power_on(struct phy *phy)
 	return ret;
 }
 
+static int imx8_pcie_phy_power_off(struct phy *phy)
+{
+	struct imx8_pcie_phy *imx8_phy = phy_get_drvdata(phy);
+
+	reset_control_assert(imx8_phy->reset);
+	reset_control_assert(imx8_phy->perst);
+
+	return 0;
+}
+
 static int imx8_pcie_phy_init(struct phy *phy)
 {
 	struct imx8_pcie_phy *imx8_phy = phy_get_drvdata(phy);
@@ -182,6 +192,7 @@ static const struct phy_ops imx8_pcie_phy_ops = {
 	.init		= imx8_pcie_phy_init,
 	.exit		= imx8_pcie_phy_exit,
 	.power_on	= imx8_pcie_phy_power_on,
+	.power_off	= imx8_pcie_phy_power_off,
 	.owner		= THIS_MODULE,
 };
 
diff --git a/drivers/phy/freescale/phy-fsl-imx8mq-usb.c b/drivers/phy/freescale/phy-fsl-imx8mq-usb.c
index adc6394626ce..f914f016b3d2 100644
--- a/drivers/phy/freescale/phy-fsl-imx8mq-usb.c
+++ b/drivers/phy/freescale/phy-fsl-imx8mq-usb.c
@@ -95,12 +95,12 @@ static u32 phy_tx_preemp_amp_tune_from_property(u32 microamp)
 static u32 phy_tx_vboost_level_from_property(u32 microvolt)
 {
 	switch (microvolt) {
-	case 0 ... 960:
-		return 0;
-	case 961 ... 1160:
-		return 2;
-	default:
+	case 1156:
+		return 5;
+	case 844:
 		return 3;
+	default:
+		return 4;
 	}
 }
 
diff --git a/drivers/phy/phy-core.c b/drivers/phy/phy-core.c
index 413f76e2d174..e0a6a272f571 100644
--- a/drivers/phy/phy-core.c
+++ b/drivers/phy/phy-core.c
@@ -405,13 +405,14 @@ EXPORT_SYMBOL_GPL(phy_power_off);
 
 int phy_set_mode_ext(struct phy *phy, enum phy_mode mode, int submode)
 {
-	int ret;
+	int ret = 0;
 
-	if (!phy || !phy->ops->set_mode)
+	if (!phy)
 		return 0;
 
 	mutex_lock(&phy->mutex);
-	ret = phy->ops->set_mode(phy, mode, submode);
+	if (phy->ops->set_mode)
+		ret = phy->ops->set_mode(phy, mode, submode);
 	if (!ret)
 		phy->attrs.mode = mode;
 	mutex_unlock(&phy->mutex);
diff --git a/drivers/phy/qualcomm/phy-qcom-eusb2-repeater.c b/drivers/phy/qualcomm/phy-qcom-eusb2-repeater.c
index 68cc8e24f383..163950e16dbe 100644
--- a/drivers/phy/qualcomm/phy-qcom-eusb2-repeater.c
+++ b/drivers/phy/qualcomm/phy-qcom-eusb2-repeater.c
@@ -37,32 +37,13 @@
 #define EUSB2_TUNE_EUSB_EQU		0x5A
 #define EUSB2_TUNE_EUSB_HS_COMP_CUR	0x5B
 
-enum eusb2_reg_layout {
-	TUNE_EUSB_HS_COMP_CUR,
-	TUNE_EUSB_EQU,
-	TUNE_EUSB_SLEW,
-	TUNE_USB2_HS_COMP_CUR,
-	TUNE_USB2_PREEM,
-	TUNE_USB2_EQU,
-	TUNE_USB2_SLEW,
-	TUNE_SQUELCH_U,
-	TUNE_HSDISC,
-	TUNE_RES_FSDIF,
-	TUNE_IUSB2,
-	TUNE_USB2_CROSSOVER,
-	NUM_TUNE_FIELDS,
-
-	FORCE_VAL_5 = NUM_TUNE_FIELDS,
-	FORCE_EN_5,
-
-	EN_CTL1,
-
-	RPTR_STATUS,
-	LAYOUT_SIZE,
+struct eusb2_repeater_init_tbl_reg {
+	unsigned int reg;
+	unsigned int value;
 };
 
 struct eusb2_repeater_cfg {
-	const u32 *init_tbl;
+	const struct eusb2_repeater_init_tbl_reg *init_tbl;
 	int init_tbl_num;
 	const char * const *vreg_list;
 	int num_vregs;
@@ -82,16 +63,16 @@ static const char * const pm8550b_vreg_l[] = {
 	"vdd18", "vdd3",
 };
 
-static const u32 pm8550b_init_tbl[NUM_TUNE_FIELDS] = {
-	[TUNE_IUSB2] = 0x8,
-	[TUNE_SQUELCH_U] = 0x3,
-	[TUNE_USB2_PREEM] = 0x5,
+static const struct eusb2_repeater_init_tbl_reg pm8550b_init_tbl[] = {
+	{ EUSB2_TUNE_IUSB2, 0x8 },
+	{ EUSB2_TUNE_SQUELCH_U, 0x3 },
+	{ EUSB2_TUNE_USB2_PREEM, 0x5 },
 };
 
-static const u32 smb2360_init_tbl[NUM_TUNE_FIELDS] = {
-	[TUNE_IUSB2] = 0x5,
-	[TUNE_SQUELCH_U] = 0x3,
-	[TUNE_USB2_PREEM] = 0x2,
+static const struct eusb2_repeater_init_tbl_reg smb2360_init_tbl[] = {
+	{ EUSB2_TUNE_IUSB2, 0x5 },
+	{ EUSB2_TUNE_SQUELCH_U, 0x3 },
+	{ EUSB2_TUNE_USB2_PREEM, 0x2 },
 };
 
 static const struct eusb2_repeater_cfg pm8550b_eusb2_cfg = {
@@ -129,17 +110,10 @@ static int eusb2_repeater_init(struct phy *phy)
 	struct eusb2_repeater *rptr = phy_get_drvdata(phy);
 	struct device_node *np = rptr->dev->of_node;
 	struct regmap *regmap = rptr->regmap;
-	const u32 *init_tbl = rptr->cfg->init_tbl;
-	u8 tune_usb2_preem = init_tbl[TUNE_USB2_PREEM];
-	u8 tune_hsdisc = init_tbl[TUNE_HSDISC];
-	u8 tune_iusb2 = init_tbl[TUNE_IUSB2];
 	u32 base = rptr->base;
-	u32 val;
+	u32 poll_val;
 	int ret;
-
-	of_property_read_u8(np, "qcom,tune-usb2-amplitude", &tune_iusb2);
-	of_property_read_u8(np, "qcom,tune-usb2-disc-thres", &tune_hsdisc);
-	of_property_read_u8(np, "qcom,tune-usb2-preem", &tune_usb2_preem);
+	u8 val;
 
 	ret = regulator_bulk_enable(rptr->cfg->num_vregs, rptr->vregs);
 	if (ret)
@@ -147,21 +121,24 @@ static int eusb2_repeater_init(struct phy *phy)
 
 	regmap_write(regmap, base + EUSB2_EN_CTL1, EUSB2_RPTR_EN);
 
-	regmap_write(regmap, base + EUSB2_TUNE_EUSB_HS_COMP_CUR, init_tbl[TUNE_EUSB_HS_COMP_CUR]);
-	regmap_write(regmap, base + EUSB2_TUNE_EUSB_EQU, init_tbl[TUNE_EUSB_EQU]);
-	regmap_write(regmap, base + EUSB2_TUNE_EUSB_SLEW, init_tbl[TUNE_EUSB_SLEW]);
-	regmap_write(regmap, base + EUSB2_TUNE_USB2_HS_COMP_CUR, init_tbl[TUNE_USB2_HS_COMP_CUR]);
-	regmap_write(regmap, base + EUSB2_TUNE_USB2_EQU, init_tbl[TUNE_USB2_EQU]);
-	regmap_write(regmap, base + EUSB2_TUNE_USB2_SLEW, init_tbl[TUNE_USB2_SLEW]);
-	regmap_write(regmap, base + EUSB2_TUNE_SQUELCH_U, init_tbl[TUNE_SQUELCH_U]);
-	regmap_write(regmap, base + EUSB2_TUNE_RES_FSDIF, init_tbl[TUNE_RES_FSDIF]);
-	regmap_write(regmap, base + EUSB2_TUNE_USB2_CROSSOVER, init_tbl[TUNE_USB2_CROSSOVER]);
-
-	regmap_write(regmap, base + EUSB2_TUNE_USB2_PREEM, tune_usb2_preem);
-	regmap_write(regmap, base + EUSB2_TUNE_HSDISC, tune_hsdisc);
-	regmap_write(regmap, base + EUSB2_TUNE_IUSB2, tune_iusb2);
-
-	ret = regmap_read_poll_timeout(regmap, base + EUSB2_RPTR_STATUS, val, val & RPTR_OK, 10, 5);
+	/* Write registers from init table */
+	for (int i = 0; i < rptr->cfg->init_tbl_num; i++)
+		regmap_write(regmap, base + rptr->cfg->init_tbl[i].reg,
+			     rptr->cfg->init_tbl[i].value);
+
+	/* Override registers from devicetree values */
+	if (!of_property_read_u8(np, "qcom,tune-usb2-amplitude", &val))
+		regmap_write(regmap, base + EUSB2_TUNE_USB2_PREEM, val);
+
+	if (!of_property_read_u8(np, "qcom,tune-usb2-disc-thres", &val))
+		regmap_write(regmap, base + EUSB2_TUNE_HSDISC, val);
+
+	if (!of_property_read_u8(np, "qcom,tune-usb2-preem", &val))
+		regmap_write(regmap, base + EUSB2_TUNE_IUSB2, val);
+
+	/* Wait for status OK */
+	ret = regmap_read_poll_timeout(regmap, base + EUSB2_RPTR_STATUS, poll_val,
+				       poll_val & RPTR_OK, 10, 5);
 	if (ret)
 		dev_err(rptr->dev, "initialization timed-out\n");
 
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-usb.c b/drivers/phy/qualcomm/phy-qcom-qmp-usb.c
index 8e2cd2c178d6..c12efd127a61 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp-usb.c
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-usb.c
@@ -2044,12 +2044,16 @@ static void __iomem *qmp_usb_iomap(struct device *dev, struct device_node *np,
 					int index, bool exclusive)
 {
 	struct resource res;
+	void __iomem *mem;
 
 	if (!exclusive) {
 		if (of_address_to_resource(np, index, &res))
 			return IOMEM_ERR_PTR(-EINVAL);
 
-		return devm_ioremap(dev, res.start, resource_size(&res));
+		mem = devm_ioremap(dev, res.start, resource_size(&res));
+		if (!mem)
+			return IOMEM_ERR_PTR(-ENOMEM);
+		return mem;
 	}
 
 	return devm_of_iomap(dev, np, index, NULL);
diff --git a/drivers/phy/renesas/phy-rcar-gen3-usb2.c b/drivers/phy/renesas/phy-rcar-gen3-usb2.c
index 58e123305152..b45aee8f5964 100644
--- a/drivers/phy/renesas/phy-rcar-gen3-usb2.c
+++ b/drivers/phy/renesas/phy-rcar-gen3-usb2.c
@@ -9,6 +9,7 @@
  * Copyright (C) 2014 Cogent Embedded, Inc.
  */
 
+#include <linux/cleanup.h>
 #include <linux/extcon-provider.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
@@ -107,7 +108,6 @@ struct rcar_gen3_phy {
 	struct rcar_gen3_chan *ch;
 	u32 int_enable_bits;
 	bool initialized;
-	bool otg_initialized;
 	bool powered;
 };
 
@@ -119,9 +119,8 @@ struct rcar_gen3_chan {
 	struct regulator *vbus;
 	struct reset_control *rstc;
 	struct work_struct work;
-	struct mutex lock;	/* protects rphys[...].powered */
+	spinlock_t lock;	/* protects access to hardware and driver data structure. */
 	enum usb_dr_mode dr_mode;
-	int irq;
 	u32 obint_enable_bits;
 	bool extcon_host;
 	bool is_otg_channel;
@@ -320,16 +319,15 @@ static bool rcar_gen3_is_any_rphy_initialized(struct rcar_gen3_chan *ch)
 	return false;
 }
 
-static bool rcar_gen3_needs_init_otg(struct rcar_gen3_chan *ch)
+static bool rcar_gen3_is_any_otg_rphy_initialized(struct rcar_gen3_chan *ch)
 {
-	int i;
-
-	for (i = 0; i < NUM_OF_PHYS; i++) {
-		if (ch->rphys[i].otg_initialized)
-			return false;
+	for (enum rcar_gen3_phy_index i = PHY_INDEX_BOTH_HC; i <= PHY_INDEX_EHCI;
+	     i++) {
+		if (ch->rphys[i].initialized)
+			return true;
 	}
 
-	return true;
+	return false;
 }
 
 static bool rcar_gen3_are_all_rphys_power_off(struct rcar_gen3_chan *ch)
@@ -351,7 +349,9 @@ static ssize_t role_store(struct device *dev, struct device_attribute *attr,
 	bool is_b_device;
 	enum phy_mode cur_mode, new_mode;
 
-	if (!ch->is_otg_channel || !rcar_gen3_is_any_rphy_initialized(ch))
+	guard(spinlock_irqsave)(&ch->lock);
+
+	if (!ch->is_otg_channel || !rcar_gen3_is_any_otg_rphy_initialized(ch))
 		return -EIO;
 
 	if (sysfs_streq(buf, "host"))
@@ -389,7 +389,7 @@ static ssize_t role_show(struct device *dev, struct device_attribute *attr,
 {
 	struct rcar_gen3_chan *ch = dev_get_drvdata(dev);
 
-	if (!ch->is_otg_channel || !rcar_gen3_is_any_rphy_initialized(ch))
+	if (!ch->is_otg_channel || !rcar_gen3_is_any_otg_rphy_initialized(ch))
 		return -EIO;
 
 	return sprintf(buf, "%s\n", rcar_gen3_is_host(ch) ? "host" :
@@ -402,6 +402,9 @@ static void rcar_gen3_init_otg(struct rcar_gen3_chan *ch)
 	void __iomem *usb2_base = ch->base;
 	u32 val;
 
+	if (!ch->is_otg_channel || rcar_gen3_is_any_otg_rphy_initialized(ch))
+		return;
+
 	/* Should not use functions of read-modify-write a register */
 	val = readl(usb2_base + USB2_LINECTRL1);
 	val = (val & ~USB2_LINECTRL1_DP_RPD) | USB2_LINECTRL1_DPRPD_EN |
@@ -415,7 +418,7 @@ static void rcar_gen3_init_otg(struct rcar_gen3_chan *ch)
 		val = readl(usb2_base + USB2_ADPCTRL);
 		writel(val | USB2_ADPCTRL_IDPULLUP, usb2_base + USB2_ADPCTRL);
 	}
-	msleep(20);
+	mdelay(20);
 
 	writel(0xffffffff, usb2_base + USB2_OBINTSTA);
 	writel(ch->obint_enable_bits, usb2_base + USB2_OBINTEN);
@@ -427,16 +430,27 @@ static irqreturn_t rcar_gen3_phy_usb2_irq(int irq, void *_ch)
 {
 	struct rcar_gen3_chan *ch = _ch;
 	void __iomem *usb2_base = ch->base;
-	u32 status = readl(usb2_base + USB2_OBINTSTA);
+	struct device *dev = ch->dev;
 	irqreturn_t ret = IRQ_NONE;
+	u32 status;
+
+	pm_runtime_get_noresume(dev);
+
+	if (pm_runtime_suspended(dev))
+		goto rpm_put;
 
-	if (status & ch->obint_enable_bits) {
-		dev_vdbg(ch->dev, "%s: %08x\n", __func__, status);
-		writel(ch->obint_enable_bits, usb2_base + USB2_OBINTSTA);
-		rcar_gen3_device_recognition(ch);
-		ret = IRQ_HANDLED;
+	scoped_guard(spinlock, &ch->lock) {
+		status = readl(usb2_base + USB2_OBINTSTA);
+		if (status & ch->obint_enable_bits) {
+			dev_vdbg(dev, "%s: %08x\n", __func__, status);
+			writel(ch->obint_enable_bits, usb2_base + USB2_OBINTSTA);
+			rcar_gen3_device_recognition(ch);
+			ret = IRQ_HANDLED;
+		}
 	}
 
+rpm_put:
+	pm_runtime_put_noidle(dev);
 	return ret;
 }
 
@@ -446,32 +460,23 @@ static int rcar_gen3_phy_usb2_init(struct phy *p)
 	struct rcar_gen3_chan *channel = rphy->ch;
 	void __iomem *usb2_base = channel->base;
 	u32 val;
-	int ret;
 
-	if (!rcar_gen3_is_any_rphy_initialized(channel) && channel->irq >= 0) {
-		INIT_WORK(&channel->work, rcar_gen3_phy_usb2_work);
-		ret = request_irq(channel->irq, rcar_gen3_phy_usb2_irq,
-				  IRQF_SHARED, dev_name(channel->dev), channel);
-		if (ret < 0) {
-			dev_err(channel->dev, "No irq handler (%d)\n", channel->irq);
-			return ret;
-		}
-	}
+	guard(spinlock_irqsave)(&channel->lock);
 
 	/* Initialize USB2 part */
 	val = readl(usb2_base + USB2_INT_ENABLE);
 	val |= USB2_INT_ENABLE_UCOM_INTEN | rphy->int_enable_bits;
 	writel(val, usb2_base + USB2_INT_ENABLE);
-	writel(USB2_SPD_RSM_TIMSET_INIT, usb2_base + USB2_SPD_RSM_TIMSET);
-	writel(USB2_OC_TIMSET_INIT, usb2_base + USB2_OC_TIMSET);
-
-	/* Initialize otg part */
-	if (channel->is_otg_channel) {
-		if (rcar_gen3_needs_init_otg(channel))
-			rcar_gen3_init_otg(channel);
-		rphy->otg_initialized = true;
+
+	if (!rcar_gen3_is_any_rphy_initialized(channel)) {
+		writel(USB2_SPD_RSM_TIMSET_INIT, usb2_base + USB2_SPD_RSM_TIMSET);
+		writel(USB2_OC_TIMSET_INIT, usb2_base + USB2_OC_TIMSET);
 	}
 
+	/* Initialize otg part (only if we initialize a PHY with IRQs). */
+	if (rphy->int_enable_bits)
+		rcar_gen3_init_otg(channel);
+
 	rphy->initialized = true;
 
 	return 0;
@@ -484,10 +489,9 @@ static int rcar_gen3_phy_usb2_exit(struct phy *p)
 	void __iomem *usb2_base = channel->base;
 	u32 val;
 
-	rphy->initialized = false;
+	guard(spinlock_irqsave)(&channel->lock);
 
-	if (channel->is_otg_channel)
-		rphy->otg_initialized = false;
+	rphy->initialized = false;
 
 	val = readl(usb2_base + USB2_INT_ENABLE);
 	val &= ~rphy->int_enable_bits;
@@ -495,9 +499,6 @@ static int rcar_gen3_phy_usb2_exit(struct phy *p)
 		val &= ~USB2_INT_ENABLE_UCOM_INTEN;
 	writel(val, usb2_base + USB2_INT_ENABLE);
 
-	if (channel->irq >= 0 && !rcar_gen3_is_any_rphy_initialized(channel))
-		free_irq(channel->irq, channel);
-
 	return 0;
 }
 
@@ -509,16 +510,17 @@ static int rcar_gen3_phy_usb2_power_on(struct phy *p)
 	u32 val;
 	int ret = 0;
 
-	mutex_lock(&channel->lock);
-	if (!rcar_gen3_are_all_rphys_power_off(channel))
-		goto out;
-
 	if (channel->vbus) {
 		ret = regulator_enable(channel->vbus);
 		if (ret)
-			goto out;
+			return ret;
 	}
 
+	guard(spinlock_irqsave)(&channel->lock);
+
+	if (!rcar_gen3_are_all_rphys_power_off(channel))
+		goto out;
+
 	val = readl(usb2_base + USB2_USBCTR);
 	val |= USB2_USBCTR_PLL_RST;
 	writel(val, usb2_base + USB2_USBCTR);
@@ -528,7 +530,6 @@ static int rcar_gen3_phy_usb2_power_on(struct phy *p)
 out:
 	/* The powered flag should be set for any other phys anyway */
 	rphy->powered = true;
-	mutex_unlock(&channel->lock);
 
 	return 0;
 }
@@ -539,18 +540,20 @@ static int rcar_gen3_phy_usb2_power_off(struct phy *p)
 	struct rcar_gen3_chan *channel = rphy->ch;
 	int ret = 0;
 
-	mutex_lock(&channel->lock);
-	rphy->powered = false;
+	scoped_guard(spinlock_irqsave, &channel->lock) {
+		rphy->powered = false;
 
-	if (!rcar_gen3_are_all_rphys_power_off(channel))
-		goto out;
+		if (rcar_gen3_are_all_rphys_power_off(channel)) {
+			u32 val = readl(channel->base + USB2_USBCTR);
+
+			val |= USB2_USBCTR_PLL_RST;
+			writel(val, channel->base + USB2_USBCTR);
+		}
+	}
 
 	if (channel->vbus)
 		ret = regulator_disable(channel->vbus);
 
-out:
-	mutex_unlock(&channel->lock);
-
 	return ret;
 }
 
@@ -703,7 +706,7 @@ static int rcar_gen3_phy_usb2_probe(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	struct rcar_gen3_chan *channel;
 	struct phy_provider *provider;
-	int ret = 0, i;
+	int ret = 0, i, irq;
 
 	if (!dev->of_node) {
 		dev_err(dev, "This driver needs device tree\n");
@@ -719,8 +722,6 @@ static int rcar_gen3_phy_usb2_probe(struct platform_device *pdev)
 		return PTR_ERR(channel->base);
 
 	channel->obint_enable_bits = USB2_OBINT_BITS;
-	/* get irq number here and request_irq for OTG in phy_init */
-	channel->irq = platform_get_irq_optional(pdev, 0);
 	channel->dr_mode = rcar_gen3_get_dr_mode(dev->of_node);
 	if (channel->dr_mode != USB_DR_MODE_UNKNOWN) {
 		channel->is_otg_channel = true;
@@ -763,7 +764,7 @@ static int rcar_gen3_phy_usb2_probe(struct platform_device *pdev)
 	if (phy_data->no_adp_ctrl)
 		channel->obint_enable_bits = USB2_OBINT_IDCHG_EN;
 
-	mutex_init(&channel->lock);
+	spin_lock_init(&channel->lock);
 	for (i = 0; i < NUM_OF_PHYS; i++) {
 		channel->rphys[i].phy = devm_phy_create(dev, NULL,
 							phy_data->phy_usb2_ops);
@@ -789,6 +790,20 @@ static int rcar_gen3_phy_usb2_probe(struct platform_device *pdev)
 		channel->vbus = NULL;
 	}
 
+	irq = platform_get_irq_optional(pdev, 0);
+	if (irq < 0 && irq != -ENXIO) {
+		ret = irq;
+		goto error;
+	} else if (irq > 0) {
+		INIT_WORK(&channel->work, rcar_gen3_phy_usb2_work);
+		ret = devm_request_irq(dev, irq, rcar_gen3_phy_usb2_irq,
+				       IRQF_SHARED, dev_name(dev), channel);
+		if (ret < 0) {
+			dev_err(dev, "Failed to request irq (%d)\n", irq);
+			goto error;
+		}
+	}
+
 	provider = devm_of_phy_provider_register(dev, rcar_gen3_phy_usb2_xlate);
 	if (IS_ERR(provider)) {
 		dev_err(dev, "Failed to register PHY provider\n");
diff --git a/drivers/phy/rockchip/Kconfig b/drivers/phy/rockchip/Kconfig
index 2f7a05f21dc5..dcb8e1628632 100644
--- a/drivers/phy/rockchip/Kconfig
+++ b/drivers/phy/rockchip/Kconfig
@@ -125,6 +125,7 @@ config PHY_ROCKCHIP_USBDP
 	depends on ARCH_ROCKCHIP && OF
 	depends on TYPEC
 	select GENERIC_PHY
+	select USB_COMMON
 	help
 	  Enable this to support the Rockchip USB3.0/DP combo PHY with
 	  Samsung IP block. This is required for USB3 support on RK3588.
diff --git a/drivers/phy/rockchip/phy-rockchip-naneng-combphy.c b/drivers/phy/rockchip/phy-rockchip-naneng-combphy.c
index 2eb3329ca23f..1ef6d9630f7e 100644
--- a/drivers/phy/rockchip/phy-rockchip-naneng-combphy.c
+++ b/drivers/phy/rockchip/phy-rockchip-naneng-combphy.c
@@ -309,7 +309,10 @@ static int rockchip_combphy_parse_dt(struct device *dev, struct rockchip_combphy
 
 	priv->ext_refclk = device_property_present(dev, "rockchip,ext-refclk");
 
-	priv->phy_rst = devm_reset_control_get(dev, "phy");
+	priv->phy_rst = devm_reset_control_get_exclusive(dev, "phy");
+	/* fallback to old behaviour */
+	if (PTR_ERR(priv->phy_rst) == -ENOENT)
+		priv->phy_rst = devm_reset_control_array_get_exclusive(dev);
 	if (IS_ERR(priv->phy_rst))
 		return dev_err_probe(dev, PTR_ERR(priv->phy_rst), "failed to get phy reset\n");
 
diff --git a/drivers/phy/rockchip/phy-rockchip-pcie.c b/drivers/phy/rockchip/phy-rockchip-pcie.c
index 51cc5ece0e63..a75affbb49b6 100644
--- a/drivers/phy/rockchip/phy-rockchip-pcie.c
+++ b/drivers/phy/rockchip/phy-rockchip-pcie.c
@@ -30,9 +30,8 @@
 #define PHY_CFG_ADDR_SHIFT    1
 #define PHY_CFG_DATA_MASK     0xf
 #define PHY_CFG_ADDR_MASK     0x3f
-#define PHY_CFG_RD_MASK       0x3ff
 #define PHY_CFG_WR_ENABLE     1
-#define PHY_CFG_WR_DISABLE    1
+#define PHY_CFG_WR_DISABLE    0
 #define PHY_CFG_WR_SHIFT      0
 #define PHY_CFG_WR_MASK       1
 #define PHY_CFG_PLL_LOCK      0x10
diff --git a/drivers/phy/rockchip/phy-rockchip-samsung-hdptx.c b/drivers/phy/rockchip/phy-rockchip-samsung-hdptx.c
index 69c3ec0938f7..5547f8df8e71 100644
--- a/drivers/phy/rockchip/phy-rockchip-samsung-hdptx.c
+++ b/drivers/phy/rockchip/phy-rockchip-samsung-hdptx.c
@@ -94,8 +94,8 @@
 #define LCPLL_ALONE_MODE		BIT(1)
 /* CMN_REG(0097) */
 #define DIG_CLK_SEL			BIT(1)
-#define ROPLL_REF			BIT(1)
-#define LCPLL_REF			0
+#define LCPLL_REF			BIT(1)
+#define ROPLL_REF			0
 /* CMN_REG(0099) */
 #define CMN_ROPLL_ALONE_MODE		BIT(2)
 #define ROPLL_ALONE_MODE		BIT(2)
@@ -192,6 +192,7 @@
 #define LN3_TX_SER_RATE_SEL_HBR2	BIT(3)
 #define LN3_TX_SER_RATE_SEL_HBR3	BIT(2)
 
+#define HDMI14_MAX_RATE			340000000
 #define HDMI20_MAX_RATE			600000000
 
 struct lcpll_config {
@@ -266,11 +267,22 @@ enum rk_hdptx_reset {
 	RST_MAX
 };
 
+#define MAX_HDPTX_PHY_NUM	2
+
+struct rk_hdptx_phy_cfg {
+	unsigned int num_phys;
+	unsigned int phy_ids[MAX_HDPTX_PHY_NUM];
+};
+
 struct rk_hdptx_phy {
 	struct device *dev;
 	struct regmap *regmap;
 	struct regmap *grf;
 
+	/* PHY const config */
+	const struct rk_hdptx_phy_cfg *cfgs;
+	int phy_id;
+
 	struct phy *phy;
 	struct phy_config *phy_cfg;
 	struct clk_bulk_data *clks;
@@ -317,6 +329,8 @@ static const struct ropll_config ropll_tmds_cfg[] = {
 	  1, 1, 0, 0x20, 0x0c, 1, 0x0e, 0, 0, },
 	{ 650000, 162, 162, 1, 1, 11, 1, 1, 1, 1, 1, 1, 1, 54, 0, 16, 4, 1,
 	  1, 1, 0, 0x20, 0x0c, 1, 0x0e, 0, 0, },
+	{ 502500, 84, 84, 1, 1, 7, 1, 1, 1, 1, 1, 1, 1, 11, 1, 4, 5,
+	  4, 11, 1, 0, 0x20, 0x0c, 1, 0x0e, 0, 0, },
 	{ 337500, 0x70, 0x70, 1, 1, 0xf, 1, 1, 1, 1, 1, 1, 1, 0x2, 0, 0x01, 5,
 	  1, 1, 1, 0, 0x20, 0x0c, 1, 0x0e, 0, 0, },
 	{ 400000, 100, 100, 1, 1, 11, 1, 1, 0, 1, 0, 1, 1, 0x9, 0, 0x05, 0,
@@ -767,9 +781,7 @@ static int rk_hdptx_ropll_tmds_cmn_config(struct rk_hdptx_phy *hdptx,
 {
 	const struct ropll_config *cfg = NULL;
 	struct ropll_config rc = {0};
-	int i;
-
-	hdptx->rate = rate * 100;
+	int ret, i;
 
 	for (i = 0; i < ARRAY_SIZE(ropll_tmds_cfg); i++)
 		if (rate == ropll_tmds_cfg[i].bit_rate) {
@@ -828,7 +840,11 @@ static int rk_hdptx_ropll_tmds_cmn_config(struct rk_hdptx_phy *hdptx,
 	regmap_update_bits(hdptx->regmap, CMN_REG(0086), PLL_PCG_CLK_EN,
 			   PLL_PCG_CLK_EN);
 
-	return rk_hdptx_post_enable_pll(hdptx);
+	ret = rk_hdptx_post_enable_pll(hdptx);
+	if (!ret)
+		hdptx->rate = rate * 100;
+
+	return ret;
 }
 
 static int rk_hdptx_ropll_tmds_mode_config(struct rk_hdptx_phy *hdptx,
@@ -838,7 +854,7 @@ static int rk_hdptx_ropll_tmds_mode_config(struct rk_hdptx_phy *hdptx,
 
 	regmap_write(hdptx->regmap, LNTOP_REG(0200), 0x06);
 
-	if (rate >= 3400000) {
+	if (rate > HDMI14_MAX_RATE / 100) {
 		/* For 1/40 bitrate clk */
 		rk_hdptx_multi_reg_write(hdptx, rk_hdtpx_tmds_lntop_highbr_seq);
 	} else {
@@ -1019,15 +1035,14 @@ static int rk_hdptx_phy_clk_register(struct rk_hdptx_phy *hdptx)
 	struct device *dev = hdptx->dev;
 	const char *name, *pname;
 	struct clk *refclk;
-	int ret, id;
+	int ret;
 
 	refclk = devm_clk_get(dev, "ref");
 	if (IS_ERR(refclk))
 		return dev_err_probe(dev, PTR_ERR(refclk),
 				     "Failed to get ref clock\n");
 
-	id = of_alias_get_id(dev->of_node, "hdptxphy");
-	name = id > 0 ? "clk_hdmiphy_pixel1" : "clk_hdmiphy_pixel0";
+	name = hdptx->phy_id > 0 ? "clk_hdmiphy_pixel1" : "clk_hdmiphy_pixel0";
 	pname = __clk_get_name(refclk);
 
 	hdptx->hw.init = CLK_HW_INIT(name, pname, &hdptx_phy_clk_ops,
@@ -1070,8 +1085,9 @@ static int rk_hdptx_phy_probe(struct platform_device *pdev)
 	struct phy_provider *phy_provider;
 	struct device *dev = &pdev->dev;
 	struct rk_hdptx_phy *hdptx;
+	struct resource *res;
 	void __iomem *regs;
-	int ret;
+	int ret, id;
 
 	hdptx = devm_kzalloc(dev, sizeof(*hdptx), GFP_KERNEL);
 	if (!hdptx)
@@ -1079,11 +1095,27 @@ static int rk_hdptx_phy_probe(struct platform_device *pdev)
 
 	hdptx->dev = dev;
 
-	regs = devm_platform_ioremap_resource(pdev, 0);
+	regs = devm_platform_get_and_ioremap_resource(pdev, 0, &res);
 	if (IS_ERR(regs))
 		return dev_err_probe(dev, PTR_ERR(regs),
 				     "Failed to ioremap resource\n");
 
+	hdptx->cfgs = device_get_match_data(dev);
+	if (!hdptx->cfgs)
+		return dev_err_probe(dev, -EINVAL, "missing match data\n");
+
+	/* find the phy-id from the io address */
+	hdptx->phy_id = -ENODEV;
+	for (id = 0; id < hdptx->cfgs->num_phys; id++) {
+		if (res->start == hdptx->cfgs->phy_ids[id]) {
+			hdptx->phy_id = id;
+			break;
+		}
+	}
+
+	if (hdptx->phy_id < 0)
+		return dev_err_probe(dev, -ENODEV, "no matching device found\n");
+
 	ret = devm_clk_bulk_get_all(dev, &hdptx->clks);
 	if (ret < 0)
 		return dev_err_probe(dev, ret, "Failed to get clocks\n");
@@ -1147,8 +1179,19 @@ static const struct dev_pm_ops rk_hdptx_phy_pm_ops = {
 		       rk_hdptx_phy_runtime_resume, NULL)
 };
 
+static const struct rk_hdptx_phy_cfg rk3588_hdptx_phy_cfgs = {
+	.num_phys = 2,
+	.phy_ids = {
+		0xfed60000,
+		0xfed70000,
+	},
+};
+
 static const struct of_device_id rk_hdptx_phy_of_match[] = {
-	{ .compatible = "rockchip,rk3588-hdptx-phy", },
+	{
+		.compatible = "rockchip,rk3588-hdptx-phy",
+		.data = &rk3588_hdptx_phy_cfgs
+	},
 	{}
 };
 MODULE_DEVICE_TABLE(of, rk_hdptx_phy_of_match);
diff --git a/drivers/phy/rockchip/phy-rockchip-usbdp.c b/drivers/phy/rockchip/phy-rockchip-usbdp.c
index 2c51e5c62d3e..d2021f7941e3 100644
--- a/drivers/phy/rockchip/phy-rockchip-usbdp.c
+++ b/drivers/phy/rockchip/phy-rockchip-usbdp.c
@@ -187,6 +187,8 @@ struct rk_udphy {
 	u32 dp_aux_din_sel;
 	bool dp_sink_hpd_sel;
 	bool dp_sink_hpd_cfg;
+	unsigned int link_rate;
+	unsigned int lanes;
 	u8 bw;
 	int id;
 
@@ -1045,7 +1047,6 @@ static int rk_udphy_dp_phy_init(struct phy *phy)
 	mutex_lock(&udphy->mutex);
 
 	udphy->dp_in_use = true;
-	rk_udphy_dp_hpd_event_trigger(udphy, udphy->dp_sink_hpd_cfg);
 
 	mutex_unlock(&udphy->mutex);
 
@@ -1103,15 +1104,19 @@ static int rk_udphy_dp_phy_power_off(struct phy *phy)
 	return 0;
 }
 
-static int rk_udphy_dp_phy_verify_link_rate(unsigned int link_rate)
+/*
+ * Verify link rate
+ */
+static int rk_udphy_dp_phy_verify_link_rate(struct rk_udphy *udphy,
+					    struct phy_configure_opts_dp *dp)
 {
-	switch (link_rate) {
+	switch (dp->link_rate) {
 	case 1620:
 	case 2700:
 	case 5400:
 	case 8100:
+		udphy->link_rate = dp->link_rate;
 		break;
-
 	default:
 		return -EINVAL;
 	}
@@ -1119,45 +1124,44 @@ static int rk_udphy_dp_phy_verify_link_rate(unsigned int link_rate)
 	return 0;
 }
 
-static int rk_udphy_dp_phy_verify_config(struct rk_udphy *udphy,
-					 struct phy_configure_opts_dp *dp)
+static int rk_udphy_dp_phy_verify_lanes(struct rk_udphy *udphy,
+					struct phy_configure_opts_dp *dp)
 {
-	int i, ret;
-
-	/* If changing link rate was required, verify it's supported. */
-	ret = rk_udphy_dp_phy_verify_link_rate(dp->link_rate);
-	if (ret)
-		return ret;
-
-	/* Verify lane count. */
 	switch (dp->lanes) {
 	case 1:
 	case 2:
 	case 4:
 		/* valid lane count. */
+		udphy->lanes = dp->lanes;
 		break;
 
 	default:
 		return -EINVAL;
 	}
 
-	/*
-	 * If changing voltages is required, check swing and pre-emphasis
-	 * levels, per-lane.
-	 */
-	if (dp->set_voltages) {
-		/* Lane count verified previously. */
-		for (i = 0; i < dp->lanes; i++) {
-			if (dp->voltage[i] > 3 || dp->pre[i] > 3)
-				return -EINVAL;
+	return 0;
+}
 
-			/*
-			 * Sum of voltage swing and pre-emphasis levels cannot
-			 * exceed 3.
-			 */
-			if (dp->voltage[i] + dp->pre[i] > 3)
-				return -EINVAL;
-		}
+/*
+ * If changing voltages is required, check swing and pre-emphasis
+ * levels, per-lane.
+ */
+static int rk_udphy_dp_phy_verify_voltages(struct rk_udphy *udphy,
+					   struct phy_configure_opts_dp *dp)
+{
+	int i;
+
+	/* Lane count verified previously. */
+	for (i = 0; i < udphy->lanes; i++) {
+		if (dp->voltage[i] > 3 || dp->pre[i] > 3)
+			return -EINVAL;
+
+		/*
+		 * Sum of voltage swing and pre-emphasis levels cannot
+		 * exceed 3.
+		 */
+		if (dp->voltage[i] + dp->pre[i] > 3)
+			return -EINVAL;
 	}
 
 	return 0;
@@ -1197,9 +1201,23 @@ static int rk_udphy_dp_phy_configure(struct phy *phy,
 	u32 i, val, lane;
 	int ret;
 
-	ret = rk_udphy_dp_phy_verify_config(udphy, dp);
-	if (ret)
-		return ret;
+	if (dp->set_rate) {
+		ret = rk_udphy_dp_phy_verify_link_rate(udphy, dp);
+		if (ret)
+			return ret;
+	}
+
+	if (dp->set_lanes) {
+		ret = rk_udphy_dp_phy_verify_lanes(udphy, dp);
+		if (ret)
+			return ret;
+	}
+
+	if (dp->set_voltages) {
+		ret = rk_udphy_dp_phy_verify_voltages(udphy, dp);
+		if (ret)
+			return ret;
+	}
 
 	if (dp->set_rate) {
 		regmap_update_bits(udphy->pma_regmap, CMN_DP_RSTN_OFFSET,
@@ -1244,9 +1262,9 @@ static int rk_udphy_dp_phy_configure(struct phy *phy,
 	}
 
 	if (dp->set_voltages) {
-		for (i = 0; i < dp->lanes; i++) {
+		for (i = 0; i < udphy->lanes; i++) {
 			lane = udphy->dp_lane_sel[i];
-			switch (dp->link_rate) {
+			switch (udphy->link_rate) {
 			case 1620:
 			case 2700:
 				regmap_update_bits(udphy->pma_regmap,
diff --git a/drivers/phy/samsung/phy-exynos5-usbdrd.c b/drivers/phy/samsung/phy-exynos5-usbdrd.c
index c421b495eb0f..28d02ae60cc1 100644
--- a/drivers/phy/samsung/phy-exynos5-usbdrd.c
+++ b/drivers/phy/samsung/phy-exynos5-usbdrd.c
@@ -488,9 +488,9 @@ exynos5_usbdrd_pipe3_set_refclk(struct phy_usb_instance *inst)
 	reg |=	PHYCLKRST_REFCLKSEL_EXT_REFCLK;
 
 	/* FSEL settings corresponding to reference clock */
-	reg &= ~PHYCLKRST_FSEL_PIPE_MASK |
-		PHYCLKRST_MPLL_MULTIPLIER_MASK |
-		PHYCLKRST_SSC_REFCLKSEL_MASK;
+	reg &= ~(PHYCLKRST_FSEL_PIPE_MASK |
+		 PHYCLKRST_MPLL_MULTIPLIER_MASK |
+		 PHYCLKRST_SSC_REFCLKSEL_MASK);
 	switch (phy_drd->extrefclk) {
 	case EXYNOS5_FSEL_50MHZ:
 		reg |= (PHYCLKRST_MPLL_MULTIPLIER_50M_REF |
@@ -532,9 +532,9 @@ exynos5_usbdrd_utmi_set_refclk(struct phy_usb_instance *inst)
 	reg &= ~PHYCLKRST_REFCLKSEL_MASK;
 	reg |=	PHYCLKRST_REFCLKSEL_EXT_REFCLK;
 
-	reg &= ~PHYCLKRST_FSEL_UTMI_MASK |
-		PHYCLKRST_MPLL_MULTIPLIER_MASK |
-		PHYCLKRST_SSC_REFCLKSEL_MASK;
+	reg &= ~(PHYCLKRST_FSEL_UTMI_MASK |
+		 PHYCLKRST_MPLL_MULTIPLIER_MASK |
+		 PHYCLKRST_SSC_REFCLKSEL_MASK);
 	reg |= PHYCLKRST_FSEL(phy_drd->extrefclk);
 
 	return reg;
@@ -1296,14 +1296,17 @@ static int exynos5_usbdrd_gs101_phy_exit(struct phy *phy)
 	struct exynos5_usbdrd_phy *phy_drd = to_usbdrd_phy(inst);
 	int ret;
 
+	if (inst->phy_cfg->id == EXYNOS5_DRDPHY_UTMI) {
+		ret = exynos850_usbdrd_phy_exit(phy);
+		if (ret)
+			return ret;
+	}
+
+	exynos5_usbdrd_phy_isol(inst, true);
+
 	if (inst->phy_cfg->id != EXYNOS5_DRDPHY_UTMI)
 		return 0;
 
-	ret = exynos850_usbdrd_phy_exit(phy);
-	if (ret)
-		return ret;
-
-	exynos5_usbdrd_phy_isol(inst, true);
 	return regulator_bulk_disable(phy_drd->drv_data->n_regulators,
 				      phy_drd->regulators);
 }
@@ -1510,8 +1513,11 @@ static const struct exynos5_usbdrd_phy_tuning gs101_tunes_pipe3_preinit[] = {
 	PHY_TUNING_ENTRY_PMA(0x09e0, -1, 0x00),
 	PHY_TUNING_ENTRY_PMA(0x09e4, -1, 0x36),
 	PHY_TUNING_ENTRY_PMA(0x1e7c, -1, 0x06),
-	PHY_TUNING_ENTRY_PMA(0x1e90, -1, 0x00),
-	PHY_TUNING_ENTRY_PMA(0x1e94, -1, 0x36),
+	PHY_TUNING_ENTRY_PMA(0x19e0, -1, 0x00),
+	PHY_TUNING_ENTRY_PMA(0x19e4, -1, 0x36),
+	/* fix bootloader bug */
+	PHY_TUNING_ENTRY_PMA(0x1e90, -1, 0x02),
+	PHY_TUNING_ENTRY_PMA(0x1e94, -1, 0x0b),
 	/* improve LVCC */
 	PHY_TUNING_ENTRY_PMA(0x08f0, -1, 0x30),
 	PHY_TUNING_ENTRY_PMA(0x18f0, -1, 0x30),
diff --git a/drivers/phy/starfive/phy-jh7110-usb.c b/drivers/phy/starfive/phy-jh7110-usb.c
index cb5454fbe2c8..b505d89860b4 100644
--- a/drivers/phy/starfive/phy-jh7110-usb.c
+++ b/drivers/phy/starfive/phy-jh7110-usb.c
@@ -18,6 +18,8 @@
 #include <linux/usb/of.h>
 
 #define USB_125M_CLK_RATE		125000000
+#define USB_CLK_MODE_OFF		0x0
+#define USB_CLK_MODE_RX_NORMAL_PWR	BIT(1)
 #define USB_LS_KEEPALIVE_OFF		0x4
 #define USB_LS_KEEPALIVE_ENABLE		BIT(4)
 
@@ -78,6 +80,7 @@ static int jh7110_usb2_phy_init(struct phy *_phy)
 {
 	struct jh7110_usb2_phy *phy = phy_get_drvdata(_phy);
 	int ret;
+	unsigned int val;
 
 	ret = clk_set_rate(phy->usb_125m_clk, USB_125M_CLK_RATE);
 	if (ret)
@@ -87,6 +90,10 @@ static int jh7110_usb2_phy_init(struct phy *_phy)
 	if (ret)
 		return ret;
 
+	val = readl(phy->regs + USB_CLK_MODE_OFF);
+	val |= USB_CLK_MODE_RX_NORMAL_PWR;
+	writel(val, phy->regs + USB_CLK_MODE_OFF);
+
 	return 0;
 }
 
diff --git a/drivers/phy/tegra/xusb-tegra186.c b/drivers/phy/tegra/xusb-tegra186.c
index 0f60d5d1c167..e818f6c3980e 100644
--- a/drivers/phy/tegra/xusb-tegra186.c
+++ b/drivers/phy/tegra/xusb-tegra186.c
@@ -237,6 +237,8 @@
 #define   DATA0_VAL_PD				BIT(1)
 #define   USE_XUSB_AO				BIT(4)
 
+#define TEGRA_UTMI_PAD_MAX 4
+
 #define TEGRA186_LANE(_name, _offset, _shift, _mask, _type)		\
 	{								\
 		.name = _name,						\
@@ -269,7 +271,7 @@ struct tegra186_xusb_padctl {
 
 	/* UTMI bias and tracking */
 	struct clk *usb2_trk_clk;
-	unsigned int bias_pad_enable;
+	DECLARE_BITMAP(utmi_pad_enabled, TEGRA_UTMI_PAD_MAX);
 
 	/* padctl context */
 	struct tegra186_xusb_padctl_context context;
@@ -603,12 +605,8 @@ static void tegra186_utmi_bias_pad_power_on(struct tegra_xusb_padctl *padctl)
 	u32 value;
 	int err;
 
-	mutex_lock(&padctl->lock);
-
-	if (priv->bias_pad_enable++ > 0) {
-		mutex_unlock(&padctl->lock);
+	if (!bitmap_empty(priv->utmi_pad_enabled, TEGRA_UTMI_PAD_MAX))
 		return;
-	}
 
 	err = clk_prepare_enable(priv->usb2_trk_clk);
 	if (err < 0)
@@ -650,16 +648,15 @@ static void tegra186_utmi_bias_pad_power_on(struct tegra_xusb_padctl *padctl)
 		udelay(100);
 	}
 
-	if (padctl->soc->trk_hw_mode) {
-		value = padctl_readl(padctl, XUSB_PADCTL_USB2_BIAS_PAD_CTL2);
-		value |= USB2_TRK_HW_MODE;
+	value = padctl_readl(padctl, XUSB_PADCTL_USB2_BIAS_PAD_CTL2);
+	if (padctl->soc->trk_update_on_idle)
 		value &= ~CYA_TRK_CODE_UPDATE_ON_IDLE;
-		padctl_writel(padctl, value, XUSB_PADCTL_USB2_BIAS_PAD_CTL2);
-	} else {
-		clk_disable_unprepare(priv->usb2_trk_clk);
-	}
+	if (padctl->soc->trk_hw_mode)
+		value |= USB2_TRK_HW_MODE;
+	padctl_writel(padctl, value, XUSB_PADCTL_USB2_BIAS_PAD_CTL2);
 
-	mutex_unlock(&padctl->lock);
+	if (!padctl->soc->trk_hw_mode)
+		clk_disable_unprepare(priv->usb2_trk_clk);
 }
 
 static void tegra186_utmi_bias_pad_power_off(struct tegra_xusb_padctl *padctl)
@@ -667,17 +664,8 @@ static void tegra186_utmi_bias_pad_power_off(struct tegra_xusb_padctl *padctl)
 	struct tegra186_xusb_padctl *priv = to_tegra186_xusb_padctl(padctl);
 	u32 value;
 
-	mutex_lock(&padctl->lock);
-
-	if (WARN_ON(priv->bias_pad_enable == 0)) {
-		mutex_unlock(&padctl->lock);
+	if (!bitmap_empty(priv->utmi_pad_enabled, TEGRA_UTMI_PAD_MAX))
 		return;
-	}
-
-	if (--priv->bias_pad_enable > 0) {
-		mutex_unlock(&padctl->lock);
-		return;
-	}
 
 	value = padctl_readl(padctl, XUSB_PADCTL_USB2_BIAS_PAD_CTL1);
 	value |= USB2_PD_TRK;
@@ -690,13 +678,13 @@ static void tegra186_utmi_bias_pad_power_off(struct tegra_xusb_padctl *padctl)
 		clk_disable_unprepare(priv->usb2_trk_clk);
 	}
 
-	mutex_unlock(&padctl->lock);
 }
 
 static void tegra186_utmi_pad_power_on(struct phy *phy)
 {
 	struct tegra_xusb_lane *lane = phy_get_drvdata(phy);
 	struct tegra_xusb_padctl *padctl = lane->pad->padctl;
+	struct tegra186_xusb_padctl *priv = to_tegra186_xusb_padctl(padctl);
 	struct tegra_xusb_usb2_port *port;
 	struct device *dev = padctl->dev;
 	unsigned int index = lane->index;
@@ -705,9 +693,16 @@ static void tegra186_utmi_pad_power_on(struct phy *phy)
 	if (!phy)
 		return;
 
+	mutex_lock(&padctl->lock);
+	if (test_bit(index, priv->utmi_pad_enabled)) {
+		mutex_unlock(&padctl->lock);
+		return;
+	}
+
 	port = tegra_xusb_find_usb2_port(padctl, index);
 	if (!port) {
 		dev_err(dev, "no port found for USB2 lane %u\n", index);
+		mutex_unlock(&padctl->lock);
 		return;
 	}
 
@@ -724,18 +719,28 @@ static void tegra186_utmi_pad_power_on(struct phy *phy)
 	value = padctl_readl(padctl, XUSB_PADCTL_USB2_OTG_PADX_CTL1(index));
 	value &= ~USB2_OTG_PD_DR;
 	padctl_writel(padctl, value, XUSB_PADCTL_USB2_OTG_PADX_CTL1(index));
+
+	set_bit(index, priv->utmi_pad_enabled);
+	mutex_unlock(&padctl->lock);
 }
 
 static void tegra186_utmi_pad_power_down(struct phy *phy)
 {
 	struct tegra_xusb_lane *lane = phy_get_drvdata(phy);
 	struct tegra_xusb_padctl *padctl = lane->pad->padctl;
+	struct tegra186_xusb_padctl *priv = to_tegra186_xusb_padctl(padctl);
 	unsigned int index = lane->index;
 	u32 value;
 
 	if (!phy)
 		return;
 
+	mutex_lock(&padctl->lock);
+	if (!test_bit(index, priv->utmi_pad_enabled)) {
+		mutex_unlock(&padctl->lock);
+		return;
+	}
+
 	dev_dbg(padctl->dev, "power down UTMI pad %u\n", index);
 
 	value = padctl_readl(padctl, XUSB_PADCTL_USB2_OTG_PADX_CTL0(index));
@@ -748,7 +753,11 @@ static void tegra186_utmi_pad_power_down(struct phy *phy)
 
 	udelay(2);
 
+	clear_bit(index, priv->utmi_pad_enabled);
+
 	tegra186_utmi_bias_pad_power_off(padctl);
+
+	mutex_unlock(&padctl->lock);
 }
 
 static int tegra186_xusb_padctl_vbus_override(struct tegra_xusb_padctl *padctl,
@@ -774,13 +783,15 @@ static int tegra186_xusb_padctl_vbus_override(struct tegra_xusb_padctl *padctl,
 }
 
 static int tegra186_xusb_padctl_id_override(struct tegra_xusb_padctl *padctl,
-					    bool status)
+					    struct tegra_xusb_usb2_port *port, bool status)
 {
-	u32 value;
+	u32 value, id_override;
+	int err = 0;
 
 	dev_dbg(padctl->dev, "%s id override\n", status ? "set" : "clear");
 
 	value = padctl_readl(padctl, USB2_VBUS_ID);
+	id_override = value & ID_OVERRIDE(~0);
 
 	if (status) {
 		if (value & VBUS_OVERRIDE) {
@@ -791,15 +802,35 @@ static int tegra186_xusb_padctl_id_override(struct tegra_xusb_padctl *padctl,
 			value = padctl_readl(padctl, USB2_VBUS_ID);
 		}
 
-		value &= ~ID_OVERRIDE(~0);
-		value |= ID_OVERRIDE_GROUNDED;
+		if (id_override != ID_OVERRIDE_GROUNDED) {
+			value &= ~ID_OVERRIDE(~0);
+			value |= ID_OVERRIDE_GROUNDED;
+			padctl_writel(padctl, value, USB2_VBUS_ID);
+
+			err = regulator_enable(port->supply);
+			if (err) {
+				dev_err(padctl->dev, "Failed to enable regulator: %d\n", err);
+				return err;
+			}
+		}
 	} else {
-		value &= ~ID_OVERRIDE(~0);
-		value |= ID_OVERRIDE_FLOATING;
+		if (id_override == ID_OVERRIDE_GROUNDED) {
+			/*
+			 * The regulator is disabled only when the role transitions
+			 * from USB_ROLE_HOST to USB_ROLE_NONE.
+			 */
+			err = regulator_disable(port->supply);
+			if (err) {
+				dev_err(padctl->dev, "Failed to disable regulator: %d\n", err);
+				return err;
+			}
+
+			value &= ~ID_OVERRIDE(~0);
+			value |= ID_OVERRIDE_FLOATING;
+			padctl_writel(padctl, value, USB2_VBUS_ID);
+		}
 	}
 
-	padctl_writel(padctl, value, USB2_VBUS_ID);
-
 	return 0;
 }
 
@@ -818,27 +849,20 @@ static int tegra186_utmi_phy_set_mode(struct phy *phy, enum phy_mode mode,
 
 	if (mode == PHY_MODE_USB_OTG) {
 		if (submode == USB_ROLE_HOST) {
-			tegra186_xusb_padctl_id_override(padctl, true);
-
-			err = regulator_enable(port->supply);
+			err = tegra186_xusb_padctl_id_override(padctl, port, true);
+			if (err)
+				goto out;
 		} else if (submode == USB_ROLE_DEVICE) {
 			tegra186_xusb_padctl_vbus_override(padctl, true);
 		} else if (submode == USB_ROLE_NONE) {
-			/*
-			 * When port is peripheral only or role transitions to
-			 * USB_ROLE_NONE from USB_ROLE_DEVICE, regulator is not
-			 * enabled.
-			 */
-			if (regulator_is_enabled(port->supply))
-				regulator_disable(port->supply);
-
-			tegra186_xusb_padctl_id_override(padctl, false);
+			err = tegra186_xusb_padctl_id_override(padctl, port, false);
+			if (err)
+				goto out;
 			tegra186_xusb_padctl_vbus_override(padctl, false);
 		}
 	}
-
+out:
 	mutex_unlock(&padctl->lock);
-
 	return err;
 }
 
@@ -928,6 +952,7 @@ static int tegra186_utmi_phy_init(struct phy *phy)
 	unsigned int index = lane->index;
 	struct device *dev = padctl->dev;
 	int err;
+	u32 reg;
 
 	port = tegra_xusb_find_usb2_port(padctl, index);
 	if (!port) {
@@ -935,6 +960,16 @@ static int tegra186_utmi_phy_init(struct phy *phy)
 		return -ENODEV;
 	}
 
+	if (port->mode == USB_DR_MODE_OTG ||
+	    port->mode == USB_DR_MODE_PERIPHERAL) {
+		/* reset VBUS&ID OVERRIDE */
+		reg = padctl_readl(padctl, USB2_VBUS_ID);
+		reg &= ~VBUS_OVERRIDE;
+		reg &= ~ID_OVERRIDE(~0);
+		reg |= ID_OVERRIDE_FLOATING;
+		padctl_writel(padctl, reg, USB2_VBUS_ID);
+	}
+
 	if (port->supply && port->mode == USB_DR_MODE_HOST) {
 		err = regulator_enable(port->supply);
 		if (err) {
@@ -1691,7 +1726,8 @@ const struct tegra_xusb_padctl_soc tegra234_xusb_padctl_soc = {
 	.num_supplies = ARRAY_SIZE(tegra194_xusb_padctl_supply_names),
 	.supports_gen2 = true,
 	.poll_trk_completed = true,
-	.trk_hw_mode = true,
+	.trk_hw_mode = false,
+	.trk_update_on_idle = true,
 	.supports_lp_cfg_en = true,
 };
 EXPORT_SYMBOL_GPL(tegra234_xusb_padctl_soc);
diff --git a/drivers/phy/tegra/xusb.c b/drivers/phy/tegra/xusb.c
index 342f5ccf611d..c758145e912d 100644
--- a/drivers/phy/tegra/xusb.c
+++ b/drivers/phy/tegra/xusb.c
@@ -548,16 +548,16 @@ static int tegra_xusb_port_init(struct tegra_xusb_port *port,
 
 	err = dev_set_name(&port->dev, "%s-%u", name, index);
 	if (err < 0)
-		goto unregister;
+		goto put_device;
 
 	err = device_add(&port->dev);
 	if (err < 0)
-		goto unregister;
+		goto put_device;
 
 	return 0;
 
-unregister:
-	device_unregister(&port->dev);
+put_device:
+	put_device(&port->dev);
 	return err;
 }
 
diff --git a/drivers/phy/tegra/xusb.h b/drivers/phy/tegra/xusb.h
index 6e45d194c689..d2b5f9565132 100644
--- a/drivers/phy/tegra/xusb.h
+++ b/drivers/phy/tegra/xusb.h
@@ -434,6 +434,7 @@ struct tegra_xusb_padctl_soc {
 	bool need_fake_usb3_port;
 	bool poll_trk_completed;
 	bool trk_hw_mode;
+	bool trk_update_on_idle;
 	bool supports_lp_cfg_en;
 };
 
diff --git a/drivers/phy/ti/phy-gmii-sel.c b/drivers/phy/ti/phy-gmii-sel.c
index 103b266fec77..2c2256fe5a3b 100644
--- a/drivers/phy/ti/phy-gmii-sel.c
+++ b/drivers/phy/ti/phy-gmii-sel.c
@@ -423,6 +423,12 @@ static int phy_gmii_sel_init_ports(struct phy_gmii_sel_priv *priv)
 	return 0;
 }
 
+static const struct regmap_config phy_gmii_sel_regmap_cfg = {
+	.reg_bits = 32,
+	.val_bits = 32,
+	.reg_stride = 4,
+};
+
 static int phy_gmii_sel_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -467,7 +473,14 @@ static int phy_gmii_sel_probe(struct platform_device *pdev)
 
 	priv->regmap = syscon_node_to_regmap(node->parent);
 	if (IS_ERR(priv->regmap)) {
-		priv->regmap = device_node_to_regmap(node);
+		void __iomem *base;
+
+		base = devm_platform_ioremap_resource(pdev, 0);
+		if (IS_ERR(base))
+			return dev_err_probe(dev, PTR_ERR(base),
+					     "failed to get base memory resource\n");
+
+		priv->regmap = regmap_init_mmio(dev, base, &phy_gmii_sel_regmap_cfg);
 		if (IS_ERR(priv->regmap))
 			return dev_err_probe(dev, PTR_ERR(priv->regmap),
 					     "Failed to get syscon\n");
diff --git a/drivers/pinctrl/bcm/pinctrl-bcm281xx.c b/drivers/pinctrl/bcm/pinctrl-bcm281xx.c
index 73dbf29c002f..a039b490cdb8 100644
--- a/drivers/pinctrl/bcm/pinctrl-bcm281xx.c
+++ b/drivers/pinctrl/bcm/pinctrl-bcm281xx.c
@@ -72,7 +72,7 @@ static enum bcm281xx_pin_type hdmi_pin = BCM281XX_PIN_TYPE_HDMI;
 struct bcm281xx_pin_function {
 	const char *name;
 	const char * const *groups;
-	const unsigned ngroups;
+	const unsigned int ngroups;
 };
 
 /*
@@ -84,10 +84,10 @@ struct bcm281xx_pinctrl_data {
 
 	/* List of all pins */
 	const struct pinctrl_pin_desc *pins;
-	const unsigned npins;
+	const unsigned int npins;
 
 	const struct bcm281xx_pin_function *functions;
-	const unsigned nfunctions;
+	const unsigned int nfunctions;
 
 	struct regmap *regmap;
 };
@@ -941,7 +941,7 @@ static struct bcm281xx_pinctrl_data bcm281xx_pinctrl = {
 };
 
 static inline enum bcm281xx_pin_type pin_type_get(struct pinctrl_dev *pctldev,
-						  unsigned pin)
+						  unsigned int pin)
 {
 	struct bcm281xx_pinctrl_data *pdata = pinctrl_dev_get_drvdata(pctldev);
 
@@ -974,7 +974,7 @@ static const struct regmap_config bcm281xx_pinctrl_regmap_config = {
 	.reg_bits = 32,
 	.reg_stride = 4,
 	.val_bits = 32,
-	.max_register = BCM281XX_PIN_VC_CAM3_SDA,
+	.max_register = BCM281XX_PIN_VC_CAM3_SDA * 4,
 };
 
 static int bcm281xx_pinctrl_get_groups_count(struct pinctrl_dev *pctldev)
@@ -985,7 +985,7 @@ static int bcm281xx_pinctrl_get_groups_count(struct pinctrl_dev *pctldev)
 }
 
 static const char *bcm281xx_pinctrl_get_group_name(struct pinctrl_dev *pctldev,
-						   unsigned group)
+						   unsigned int group)
 {
 	struct bcm281xx_pinctrl_data *pdata = pinctrl_dev_get_drvdata(pctldev);
 
@@ -993,9 +993,9 @@ static const char *bcm281xx_pinctrl_get_group_name(struct pinctrl_dev *pctldev,
 }
 
 static int bcm281xx_pinctrl_get_group_pins(struct pinctrl_dev *pctldev,
-					   unsigned group,
+					   unsigned int group,
 					   const unsigned **pins,
-					   unsigned *num_pins)
+					   unsigned int *num_pins)
 {
 	struct bcm281xx_pinctrl_data *pdata = pinctrl_dev_get_drvdata(pctldev);
 
@@ -1007,7 +1007,7 @@ static int bcm281xx_pinctrl_get_group_pins(struct pinctrl_dev *pctldev,
 
 static void bcm281xx_pinctrl_pin_dbg_show(struct pinctrl_dev *pctldev,
 					  struct seq_file *s,
-					  unsigned offset)
+					  unsigned int offset)
 {
 	seq_printf(s, " %s", dev_name(pctldev->dev));
 }
@@ -1029,7 +1029,7 @@ static int bcm281xx_pinctrl_get_fcns_count(struct pinctrl_dev *pctldev)
 }
 
 static const char *bcm281xx_pinctrl_get_fcn_name(struct pinctrl_dev *pctldev,
-						 unsigned function)
+						 unsigned int function)
 {
 	struct bcm281xx_pinctrl_data *pdata = pinctrl_dev_get_drvdata(pctldev);
 
@@ -1037,9 +1037,9 @@ static const char *bcm281xx_pinctrl_get_fcn_name(struct pinctrl_dev *pctldev,
 }
 
 static int bcm281xx_pinctrl_get_fcn_groups(struct pinctrl_dev *pctldev,
-					   unsigned function,
+					   unsigned int function,
 					   const char * const **groups,
-					   unsigned * const num_groups)
+					   unsigned int * const num_groups)
 {
 	struct bcm281xx_pinctrl_data *pdata = pinctrl_dev_get_drvdata(pctldev);
 
@@ -1050,8 +1050,8 @@ static int bcm281xx_pinctrl_get_fcn_groups(struct pinctrl_dev *pctldev,
 }
 
 static int bcm281xx_pinmux_set(struct pinctrl_dev *pctldev,
-			       unsigned function,
-			       unsigned group)
+			       unsigned int function,
+			       unsigned int group)
 {
 	struct bcm281xx_pinctrl_data *pdata = pinctrl_dev_get_drvdata(pctldev);
 	const struct bcm281xx_pin_function *f = &pdata->functions[function];
@@ -1082,7 +1082,7 @@ static const struct pinmux_ops bcm281xx_pinctrl_pinmux_ops = {
 };
 
 static int bcm281xx_pinctrl_pin_config_get(struct pinctrl_dev *pctldev,
-					   unsigned pin,
+					   unsigned int pin,
 					   unsigned long *config)
 {
 	return -ENOTSUPP;
@@ -1091,9 +1091,9 @@ static int bcm281xx_pinctrl_pin_config_get(struct pinctrl_dev *pctldev,
 
 /* Goes through the configs and update register val/mask */
 static int bcm281xx_std_pin_update(struct pinctrl_dev *pctldev,
-				   unsigned pin,
+				   unsigned int pin,
 				   unsigned long *configs,
-				   unsigned num_configs,
+				   unsigned int num_configs,
 				   u32 *val,
 				   u32 *mask)
 {
@@ -1207,9 +1207,9 @@ static const u16 bcm281xx_pullup_map[] = {
 
 /* Goes through the configs and update register val/mask */
 static int bcm281xx_i2c_pin_update(struct pinctrl_dev *pctldev,
-				   unsigned pin,
+				   unsigned int pin,
 				   unsigned long *configs,
-				   unsigned num_configs,
+				   unsigned int num_configs,
 				   u32 *val,
 				   u32 *mask)
 {
@@ -1277,9 +1277,9 @@ static int bcm281xx_i2c_pin_update(struct pinctrl_dev *pctldev,
 
 /* Goes through the configs and update register val/mask */
 static int bcm281xx_hdmi_pin_update(struct pinctrl_dev *pctldev,
-				    unsigned pin,
+				    unsigned int pin,
 				    unsigned long *configs,
-				    unsigned num_configs,
+				    unsigned int num_configs,
 				    u32 *val,
 				    u32 *mask)
 {
@@ -1321,9 +1321,9 @@ static int bcm281xx_hdmi_pin_update(struct pinctrl_dev *pctldev,
 }
 
 static int bcm281xx_pinctrl_pin_config_set(struct pinctrl_dev *pctldev,
-					   unsigned pin,
+					   unsigned int pin,
 					   unsigned long *configs,
-					   unsigned num_configs)
+					   unsigned int num_configs)
 {
 	struct bcm281xx_pinctrl_data *pdata = pinctrl_dev_get_drvdata(pctldev);
 	enum bcm281xx_pin_type pin_type;
diff --git a/drivers/pinctrl/berlin/berlin.c b/drivers/pinctrl/berlin/berlin.c
index c372a2a24be4..9dc2da8056b7 100644
--- a/drivers/pinctrl/berlin/berlin.c
+++ b/drivers/pinctrl/berlin/berlin.c
@@ -204,6 +204,7 @@ static int berlin_pinctrl_build_state(struct platform_device *pdev)
 	const struct berlin_desc_group *desc_group;
 	const struct berlin_desc_function *desc_function;
 	int i, max_functions = 0;
+	struct pinfunction *new_functions;
 
 	pctrl->nfunctions = 0;
 
@@ -229,12 +230,15 @@ static int berlin_pinctrl_build_state(struct platform_device *pdev)
 		}
 	}
 
-	pctrl->functions = krealloc(pctrl->functions,
+	new_functions = krealloc(pctrl->functions,
 				    pctrl->nfunctions * sizeof(*pctrl->functions),
 				    GFP_KERNEL);
-	if (!pctrl->functions)
+	if (!new_functions) {
+		kfree(pctrl->functions);
 		return -ENOMEM;
+	}
 
+	pctrl->functions = new_functions;
 	/* map functions to theirs groups */
 	for (i = 0; i < pctrl->desc->ngroups; i++) {
 		desc_group = pctrl->desc->groups + i;
diff --git a/drivers/pinctrl/devicetree.c b/drivers/pinctrl/devicetree.c
index 6a94ecd6a8de..0b7f74beb6a6 100644
--- a/drivers/pinctrl/devicetree.c
+++ b/drivers/pinctrl/devicetree.c
@@ -143,10 +143,14 @@ static int dt_to_map_one_config(struct pinctrl *p,
 		pctldev = get_pinctrl_dev_from_of_node(np_pctldev);
 		if (pctldev)
 			break;
-		/* Do not defer probing of hogs (circular loop) */
+		/*
+		 * Do not defer probing of hogs (circular loop)
+		 *
+		 * Return 1 to let the caller catch the case.
+		 */
 		if (np_pctldev == p->dev->of_node) {
 			of_node_put(np_pctldev);
-			return -ENODEV;
+			return 1;
 		}
 	}
 	of_node_put(np_pctldev);
@@ -265,6 +269,8 @@ int pinctrl_dt_to_map(struct pinctrl *p, struct pinctrl_dev *pctldev)
 			ret = dt_to_map_one_config(p, pctldev, statename,
 						   np_config);
 			of_node_put(np_config);
+			if (ret == 1)
+				continue;
 			if (ret < 0)
 				goto err;
 		}
diff --git a/drivers/pinctrl/freescale/pinctrl-imx.c b/drivers/pinctrl/freescale/pinctrl-imx.c
index d05c2c478e79..4e1fe457a608 100644
--- a/drivers/pinctrl/freescale/pinctrl-imx.c
+++ b/drivers/pinctrl/freescale/pinctrl-imx.c
@@ -37,16 +37,16 @@ static inline const struct group_desc *imx_pinctrl_find_group_by_name(
 				struct pinctrl_dev *pctldev,
 				const char *name)
 {
-	const struct group_desc *grp = NULL;
+	const struct group_desc *grp;
 	int i;
 
 	for (i = 0; i < pctldev->num_groups; i++) {
 		grp = pinctrl_generic_get_group(pctldev, i);
 		if (grp && !strcmp(grp->grp.name, name))
-			break;
+			return grp;
 	}
 
-	return grp;
+	return NULL;
 }
 
 static void imx_pin_dbg_show(struct pinctrl_dev *pctldev, struct seq_file *s,
diff --git a/drivers/pinctrl/intel/pinctrl-intel.c b/drivers/pinctrl/intel/pinctrl-intel.c
index 928607a21d36..f8abc69a39d1 100644
--- a/drivers/pinctrl/intel/pinctrl-intel.c
+++ b/drivers/pinctrl/intel/pinctrl-intel.c
@@ -1531,7 +1531,6 @@ static int intel_pinctrl_probe_pwm(struct intel_pinctrl *pctrl,
 		.clk_rate = 19200000,
 		.npwm = 1,
 		.base_unit_bits = 22,
-		.bypass = true,
 	};
 	struct pwm_chip *chip;
 
diff --git a/drivers/pinctrl/meson/pinctrl-meson.c b/drivers/pinctrl/meson/pinctrl-meson.c
index 253a0cc57e39..e5a32a0532ee 100644
--- a/drivers/pinctrl/meson/pinctrl-meson.c
+++ b/drivers/pinctrl/meson/pinctrl-meson.c
@@ -487,7 +487,7 @@ static int meson_pinconf_get(struct pinctrl_dev *pcdev, unsigned int pin,
 	case PIN_CONFIG_BIAS_PULL_DOWN:
 	case PIN_CONFIG_BIAS_PULL_UP:
 		if (meson_pinconf_get_pull(pc, pin) == param)
-			arg = 1;
+			arg = 60000;
 		else
 			return -EINVAL;
 		break;
diff --git a/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c b/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c
index 4c4ada06423d..53b6eb748659 100644
--- a/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c
+++ b/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c
@@ -358,9 +358,7 @@ static int armada_37xx_pmx_set_by_name(struct pinctrl_dev *pctldev,
 
 	val = grp->val[func];
 
-	regmap_update_bits(info->regmap, reg, mask, val);
-
-	return 0;
+	return regmap_update_bits(info->regmap, reg, mask, val);
 }
 
 static int armada_37xx_pmx_set(struct pinctrl_dev *pctldev,
@@ -402,10 +400,13 @@ static int armada_37xx_gpio_get_direction(struct gpio_chip *chip,
 	struct armada_37xx_pinctrl *info = gpiochip_get_data(chip);
 	unsigned int reg = OUTPUT_EN;
 	unsigned int val, mask;
+	int ret;
 
 	armada_37xx_update_reg(&reg, &offset);
 	mask = BIT(offset);
-	regmap_read(info->regmap, reg, &val);
+	ret = regmap_read(info->regmap, reg, &val);
+	if (ret)
+		return ret;
 
 	if (val & mask)
 		return GPIO_LINE_DIRECTION_OUT;
@@ -417,20 +418,22 @@ static int armada_37xx_gpio_direction_output(struct gpio_chip *chip,
 					     unsigned int offset, int value)
 {
 	struct armada_37xx_pinctrl *info = gpiochip_get_data(chip);
-	unsigned int reg = OUTPUT_EN;
+	unsigned int en_offset = offset;
+	unsigned int reg = OUTPUT_VAL;
 	unsigned int mask, val, ret;
 
 	armada_37xx_update_reg(&reg, &offset);
 	mask = BIT(offset);
+	val = value ? mask : 0;
 
-	ret = regmap_update_bits(info->regmap, reg, mask, mask);
-
+	ret = regmap_update_bits(info->regmap, reg, mask, val);
 	if (ret)
 		return ret;
 
-	reg = OUTPUT_VAL;
-	val = value ? mask : 0;
-	regmap_update_bits(info->regmap, reg, mask, val);
+	reg = OUTPUT_EN;
+	armada_37xx_update_reg(&reg, &en_offset);
+
+	regmap_update_bits(info->regmap, reg, mask, mask);
 
 	return 0;
 }
@@ -440,11 +443,14 @@ static int armada_37xx_gpio_get(struct gpio_chip *chip, unsigned int offset)
 	struct armada_37xx_pinctrl *info = gpiochip_get_data(chip);
 	unsigned int reg = INPUT_VAL;
 	unsigned int val, mask;
+	int ret;
 
 	armada_37xx_update_reg(&reg, &offset);
 	mask = BIT(offset);
 
-	regmap_read(info->regmap, reg, &val);
+	ret = regmap_read(info->regmap, reg, &val);
+	if (ret)
+		return ret;
 
 	return (val & mask) != 0;
 }
@@ -469,16 +475,17 @@ static int armada_37xx_pmx_gpio_set_direction(struct pinctrl_dev *pctldev,
 {
 	struct armada_37xx_pinctrl *info = pinctrl_dev_get_drvdata(pctldev);
 	struct gpio_chip *chip = range->gc;
+	int ret;
 
 	dev_dbg(info->dev, "gpio_direction for pin %u as %s-%d to %s\n",
 		offset, range->name, offset, input ? "input" : "output");
 
 	if (input)
-		armada_37xx_gpio_direction_input(chip, offset);
+		ret = armada_37xx_gpio_direction_input(chip, offset);
 	else
-		armada_37xx_gpio_direction_output(chip, offset, 0);
+		ret = armada_37xx_gpio_direction_output(chip, offset, 0);
 
-	return 0;
+	return ret;
 }
 
 static int armada_37xx_gpio_request_enable(struct pinctrl_dev *pctldev,
diff --git a/drivers/pinctrl/nomadik/pinctrl-nomadik.c b/drivers/pinctrl/nomadik/pinctrl-nomadik.c
index f4f10c60c1d2..dcc662be0800 100644
--- a/drivers/pinctrl/nomadik/pinctrl-nomadik.c
+++ b/drivers/pinctrl/nomadik/pinctrl-nomadik.c
@@ -438,9 +438,9 @@ static void nmk_prcm_altcx_set_mode(struct nmk_pinctrl *npct,
  *  - Any spurious wake up event during switch sequence to be ignored and
  *    cleared
  */
-static void nmk_gpio_glitch_slpm_init(unsigned int *slpm)
+static int nmk_gpio_glitch_slpm_init(unsigned int *slpm)
 {
-	int i;
+	int i, j, ret;
 
 	for (i = 0; i < NMK_MAX_BANKS; i++) {
 		struct nmk_gpio_chip *chip = nmk_gpio_chips[i];
@@ -449,11 +449,21 @@ static void nmk_gpio_glitch_slpm_init(unsigned int *slpm)
 		if (!chip)
 			break;
 
-		clk_enable(chip->clk);
+		ret = clk_enable(chip->clk);
+		if (ret) {
+			for (j = 0; j < i; j++) {
+				chip = nmk_gpio_chips[j];
+				clk_disable(chip->clk);
+			}
+
+			return ret;
+		}
 
 		slpm[i] = readl(chip->addr + NMK_GPIO_SLPC);
 		writel(temp, chip->addr + NMK_GPIO_SLPC);
 	}
+
+	return 0;
 }
 
 static void nmk_gpio_glitch_slpm_restore(unsigned int *slpm)
@@ -923,7 +933,9 @@ static int nmk_pmx_set(struct pinctrl_dev *pctldev, unsigned int function,
 
 			slpm[nmk_chip->bank] &= ~BIT(bit);
 		}
-		nmk_gpio_glitch_slpm_init(slpm);
+		ret = nmk_gpio_glitch_slpm_init(slpm);
+		if (ret)
+			goto out_pre_slpm_init;
 	}
 
 	for (i = 0; i < g->grp.npins; i++) {
@@ -940,7 +952,10 @@ static int nmk_pmx_set(struct pinctrl_dev *pctldev, unsigned int function,
 		dev_dbg(npct->dev, "setting pin %d to altsetting %d\n",
 			g->grp.pins[i], g->altsetting);
 
-		clk_enable(nmk_chip->clk);
+		ret = clk_enable(nmk_chip->clk);
+		if (ret)
+			goto out_glitch;
+
 		/*
 		 * If the pin is switching to altfunc, and there was an
 		 * interrupt installed on it which has been lazy disabled,
@@ -988,6 +1003,7 @@ static int nmk_gpio_request_enable(struct pinctrl_dev *pctldev,
 	struct nmk_gpio_chip *nmk_chip;
 	struct gpio_chip *chip;
 	unsigned int bit;
+	int ret;
 
 	if (!range) {
 		dev_err(npct->dev, "invalid range\n");
@@ -1004,7 +1020,9 @@ static int nmk_gpio_request_enable(struct pinctrl_dev *pctldev,
 
 	find_nmk_gpio_from_pin(pin, &bit);
 
-	clk_enable(nmk_chip->clk);
+	ret = clk_enable(nmk_chip->clk);
+	if (ret)
+		return ret;
 	/* There is no glitch when converting any pin to GPIO */
 	__nmk_gpio_set_mode(nmk_chip, bit, NMK_GPIO_ALT_GPIO);
 	clk_disable(nmk_chip->clk);
@@ -1058,6 +1076,7 @@ static int nmk_pin_config_set(struct pinctrl_dev *pctldev, unsigned int pin,
 	unsigned long cfg;
 	int pull, slpm, output, val, i;
 	bool lowemi, gpiomode, sleep;
+	int ret;
 
 	nmk_chip = find_nmk_gpio_from_pin(pin, &bit);
 	if (!nmk_chip) {
@@ -1116,7 +1135,9 @@ static int nmk_pin_config_set(struct pinctrl_dev *pctldev, unsigned int pin,
 			output ? (val ? "high" : "low") : "",
 			lowemi ? "on" : "off");
 
-		clk_enable(nmk_chip->clk);
+		ret = clk_enable(nmk_chip->clk);
+		if (ret)
+			return ret;
 		if (gpiomode)
 			/* No glitch when going to GPIO mode */
 			__nmk_gpio_set_mode(nmk_chip, bit, NMK_GPIO_ALT_GPIO);
diff --git a/drivers/pinctrl/nuvoton/pinctrl-npcm8xx.c b/drivers/pinctrl/nuvoton/pinctrl-npcm8xx.c
index 471f644c5eef..f6a1e684a386 100644
--- a/drivers/pinctrl/nuvoton/pinctrl-npcm8xx.c
+++ b/drivers/pinctrl/nuvoton/pinctrl-npcm8xx.c
@@ -1290,12 +1290,14 @@ static struct npcm8xx_func npcm8xx_funcs[] = {
 };
 
 #define NPCM8XX_PINCFG(a, b, c, d, e, f, g, h, i, j, k, l, m, n, o, p, q) \
-	[a] { .fn0 = fn_ ## b, .reg0 = NPCM8XX_GCR_ ## c, .bit0 = d, \
+	[a] = {								  \
+			.flag = q,					  \
+			.fn0 = fn_ ## b, .reg0 = NPCM8XX_GCR_ ## c, .bit0 = d, \
 			.fn1 = fn_ ## e, .reg1 = NPCM8XX_GCR_ ## f, .bit1 = g, \
 			.fn2 = fn_ ## h, .reg2 = NPCM8XX_GCR_ ## i, .bit2 = j, \
 			.fn3 = fn_ ## k, .reg3 = NPCM8XX_GCR_ ## l, .bit3 = m, \
 			.fn4 = fn_ ## n, .reg4 = NPCM8XX_GCR_ ## o, .bit4 = p, \
-			.flag = q }
+	}
 
 /* Drive strength controlled by NPCM8XX_GP_N_ODSC */
 #define DRIVE_STRENGTH_LO_SHIFT		8
@@ -2361,8 +2363,8 @@ static int npcm8xx_gpio_fw(struct npcm8xx_pinctrl *pctrl)
 			return dev_err_probe(dev, ret, "gpio-ranges fail for GPIO bank %u\n", id);
 
 		ret = fwnode_irq_get(child, 0);
-		if (!ret)
-			return dev_err_probe(dev, ret, "No IRQ for GPIO bank %u\n", id);
+		if (ret < 0)
+			return dev_err_probe(dev, ret, "Failed to retrieve IRQ for bank %u\n", id);
 
 		pctrl->gpio_bank[id].irq = ret;
 		pctrl->gpio_bank[id].irq_chip = npcmgpio_irqchip;
@@ -2374,6 +2376,9 @@ static int npcm8xx_gpio_fw(struct npcm8xx_pinctrl *pctrl)
 		pctrl->gpio_bank[id].gc.parent = dev;
 		pctrl->gpio_bank[id].gc.fwnode = child;
 		pctrl->gpio_bank[id].gc.label = devm_kasprintf(dev, GFP_KERNEL, "%pfw", child);
+		if (pctrl->gpio_bank[id].gc.label == NULL)
+			return -ENOMEM;
+
 		pctrl->gpio_bank[id].gc.dbg_show = npcmgpio_dbg_show;
 		pctrl->gpio_bank[id].direction_input = pctrl->gpio_bank[id].gc.direction_input;
 		pctrl->gpio_bank[id].gc.direction_input = npcmgpio_direction_input;
diff --git a/drivers/pinctrl/pinconf-generic.c b/drivers/pinctrl/pinconf-generic.c
index 0b13d7f17b32..42547f64453e 100644
--- a/drivers/pinctrl/pinconf-generic.c
+++ b/drivers/pinctrl/pinconf-generic.c
@@ -89,12 +89,12 @@ static void pinconf_generic_dump_one(struct pinctrl_dev *pctldev,
 		seq_puts(s, items[i].display);
 		/* Print unit if available */
 		if (items[i].has_arg) {
-			seq_printf(s, " (0x%x",
-				   pinconf_to_config_argument(config));
+			u32 val = pinconf_to_config_argument(config);
+
 			if (items[i].format)
-				seq_printf(s, " %s)", items[i].format);
+				seq_printf(s, " (%u %s)", val, items[i].format);
 			else
-				seq_puts(s, ")");
+				seq_printf(s, " (0x%x)", val);
 		}
 	}
 }
diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c
index 7f66ec73199a..debf36ce5785 100644
--- a/drivers/pinctrl/pinctrl-amd.c
+++ b/drivers/pinctrl/pinctrl-amd.c
@@ -908,12 +908,13 @@ static bool amd_gpio_should_save(struct amd_gpio *gpio_dev, unsigned int pin)
 	return false;
 }
 
-static int amd_gpio_suspend(struct device *dev)
+static int amd_gpio_suspend_hibernate_common(struct device *dev, bool is_suspend)
 {
 	struct amd_gpio *gpio_dev = dev_get_drvdata(dev);
 	struct pinctrl_desc *desc = gpio_dev->pctrl->desc;
 	unsigned long flags;
 	int i;
+	u32 wake_mask = is_suspend ? WAKE_SOURCE_SUSPEND : WAKE_SOURCE_HIBERNATE;
 
 	for (i = 0; i < desc->npins; i++) {
 		int pin = desc->pins[i].number;
@@ -925,11 +926,22 @@ static int amd_gpio_suspend(struct device *dev)
 		gpio_dev->saved_regs[i] = readl(gpio_dev->base + pin * 4) & ~PIN_IRQ_PENDING;
 
 		/* mask any interrupts not intended to be a wake source */
-		if (!(gpio_dev->saved_regs[i] & WAKE_SOURCE)) {
+		if (!(gpio_dev->saved_regs[i] & wake_mask)) {
 			writel(gpio_dev->saved_regs[i] & ~BIT(INTERRUPT_MASK_OFF),
 			       gpio_dev->base + pin * 4);
-			pm_pr_dbg("Disabling GPIO #%d interrupt for suspend.\n",
-				  pin);
+			pm_pr_dbg("Disabling GPIO #%d interrupt for %s.\n",
+				  pin, is_suspend ? "suspend" : "hibernate");
+		}
+
+		/*
+		 * debounce enabled over suspend has shown issues with a GPIO
+		 * being unable to wake the system, as we're only interested in
+		 * the actual wakeup event, clear it.
+		 */
+		if (gpio_dev->saved_regs[i] & (DB_CNTRl_MASK << DB_CNTRL_OFF)) {
+			amd_gpio_set_debounce(gpio_dev, pin, 0);
+			pm_pr_dbg("Clearing debounce for GPIO #%d during %s.\n",
+				  pin, is_suspend ? "suspend" : "hibernate");
 		}
 
 		raw_spin_unlock_irqrestore(&gpio_dev->lock, flags);
@@ -938,6 +950,16 @@ static int amd_gpio_suspend(struct device *dev)
 	return 0;
 }
 
+static int amd_gpio_suspend(struct device *dev)
+{
+	return amd_gpio_suspend_hibernate_common(dev, true);
+}
+
+static int amd_gpio_hibernate(struct device *dev)
+{
+	return amd_gpio_suspend_hibernate_common(dev, false);
+}
+
 static int amd_gpio_resume(struct device *dev)
 {
 	struct amd_gpio *gpio_dev = dev_get_drvdata(dev);
@@ -961,8 +983,12 @@ static int amd_gpio_resume(struct device *dev)
 }
 
 static const struct dev_pm_ops amd_gpio_pm_ops = {
-	SET_LATE_SYSTEM_SLEEP_PM_OPS(amd_gpio_suspend,
-				     amd_gpio_resume)
+	.suspend_late = amd_gpio_suspend,
+	.resume_early = amd_gpio_resume,
+	.freeze_late = amd_gpio_hibernate,
+	.thaw_early = amd_gpio_resume,
+	.poweroff_late = amd_gpio_hibernate,
+	.restore_early = amd_gpio_resume,
 };
 #endif
 
diff --git a/drivers/pinctrl/pinctrl-amd.h b/drivers/pinctrl/pinctrl-amd.h
index cf59089f2776..c9522c62d791 100644
--- a/drivers/pinctrl/pinctrl-amd.h
+++ b/drivers/pinctrl/pinctrl-amd.h
@@ -80,10 +80,9 @@
 #define FUNCTION_MASK		GENMASK(1, 0)
 #define FUNCTION_INVALID	GENMASK(7, 0)
 
-#define WAKE_SOURCE	(BIT(WAKE_CNTRL_OFF_S0I3) | \
-			 BIT(WAKE_CNTRL_OFF_S3)   | \
-			 BIT(WAKE_CNTRL_OFF_S4)   | \
-			 BIT(WAKECNTRL_Z_OFF))
+#define WAKE_SOURCE_SUSPEND  (BIT(WAKE_CNTRL_OFF_S0I3) | \
+			      BIT(WAKE_CNTRL_OFF_S3))
+#define WAKE_SOURCE_HIBERNATE BIT(WAKE_CNTRL_OFF_S4)
 
 struct amd_function {
 	const char *name;
diff --git a/drivers/pinctrl/pinctrl-at91.c b/drivers/pinctrl/pinctrl-at91.c
index 93ab277d9943..fbe74e4ef320 100644
--- a/drivers/pinctrl/pinctrl-at91.c
+++ b/drivers/pinctrl/pinctrl-at91.c
@@ -1819,12 +1819,16 @@ static int at91_gpio_probe(struct platform_device *pdev)
 	struct at91_gpio_chip *at91_chip = NULL;
 	struct gpio_chip *chip;
 	struct pinctrl_gpio_range *range;
+	int alias_idx;
 	int ret = 0;
 	int irq, i;
-	int alias_idx = of_alias_get_id(np, "gpio");
 	uint32_t ngpio;
 	char **names;
 
+	alias_idx = of_alias_get_id(np, "gpio");
+	if (alias_idx < 0)
+		return alias_idx;
+
 	BUG_ON(alias_idx >= ARRAY_SIZE(gpio_chips));
 	if (gpio_chips[alias_idx])
 		return dev_err_probe(dev, -EBUSY, "%d slot is occupied.\n", alias_idx);
diff --git a/drivers/pinctrl/pinctrl-cy8c95x0.c b/drivers/pinctrl/pinctrl-cy8c95x0.c
index 5096ccdd459e..7a6a1434ae7f 100644
--- a/drivers/pinctrl/pinctrl-cy8c95x0.c
+++ b/drivers/pinctrl/pinctrl-cy8c95x0.c
@@ -42,7 +42,7 @@
 #define CY8C95X0_PORTSEL	0x18
 /* Port settings, write PORTSEL first */
 #define CY8C95X0_INTMASK	0x19
-#define CY8C95X0_PWMSEL		0x1A
+#define CY8C95X0_SELPWM		0x1A
 #define CY8C95X0_INVERT		0x1B
 #define CY8C95X0_DIRECTION	0x1C
 /* Drive mode register change state on writing '1' */
@@ -330,14 +330,14 @@ static int cypress_get_pin_mask(struct cy8c95x0_pinctrl *chip, unsigned int pin)
 static bool cy8c95x0_readable_register(struct device *dev, unsigned int reg)
 {
 	/*
-	 * Only 12 registers are present per port (see Table 6 in the
-	 * datasheet).
+	 * Only 12 registers are present per port (see Table 6 in the datasheet).
 	 */
-	if (reg >= CY8C95X0_VIRTUAL && (reg % MUXED_STRIDE) < 12)
-		return true;
+	if (reg >= CY8C95X0_VIRTUAL && (reg % MUXED_STRIDE) >= 12)
+		return false;
 
 	switch (reg) {
 	case 0x24 ... 0x27:
+	case 0x31 ... 0x3f:
 		return false;
 	default:
 		return true;
@@ -346,8 +346,11 @@ static bool cy8c95x0_readable_register(struct device *dev, unsigned int reg)
 
 static bool cy8c95x0_writeable_register(struct device *dev, unsigned int reg)
 {
-	if (reg >= CY8C95X0_VIRTUAL)
-		return true;
+	/*
+	 * Only 12 registers are present per port (see Table 6 in the datasheet).
+	 */
+	if (reg >= CY8C95X0_VIRTUAL && (reg % MUXED_STRIDE) >= 12)
+		return false;
 
 	switch (reg) {
 	case CY8C95X0_INPUT_(0) ... CY8C95X0_INPUT_(7):
@@ -355,6 +358,7 @@ static bool cy8c95x0_writeable_register(struct device *dev, unsigned int reg)
 	case CY8C95X0_DEVID:
 		return false;
 	case 0x24 ... 0x27:
+	case 0x31 ... 0x3f:
 		return false;
 	default:
 		return true;
@@ -367,8 +371,8 @@ static bool cy8c95x0_volatile_register(struct device *dev, unsigned int reg)
 	case CY8C95X0_INPUT_(0) ... CY8C95X0_INPUT_(7):
 	case CY8C95X0_INTSTATUS_(0) ... CY8C95X0_INTSTATUS_(7):
 	case CY8C95X0_INTMASK:
+	case CY8C95X0_SELPWM:
 	case CY8C95X0_INVERT:
-	case CY8C95X0_PWMSEL:
 	case CY8C95X0_DIRECTION:
 	case CY8C95X0_DRV_PU:
 	case CY8C95X0_DRV_PD:
@@ -397,7 +401,7 @@ static bool cy8c95x0_muxed_register(unsigned int reg)
 {
 	switch (reg) {
 	case CY8C95X0_INTMASK:
-	case CY8C95X0_PWMSEL:
+	case CY8C95X0_SELPWM:
 	case CY8C95X0_INVERT:
 	case CY8C95X0_DIRECTION:
 	case CY8C95X0_DRV_PU:
@@ -468,7 +472,11 @@ static const struct regmap_config cy8c9520_i2c_regmap = {
 	.max_register = 0,		/* Updated at runtime */
 	.num_reg_defaults_raw = 0,	/* Updated at runtime */
 	.use_single_read = true,	/* Workaround for regcache bug */
+#if IS_ENABLED(CONFIG_DEBUG_PINCTRL)
+	.disable_locking = false,
+#else
 	.disable_locking = true,
+#endif
 };
 
 static inline int cy8c95x0_regmap_update_bits_base(struct cy8c95x0_pinctrl *chip,
@@ -799,7 +807,7 @@ static int cy8c95x0_gpio_get_pincfg(struct cy8c95x0_pinctrl *chip,
 		reg = CY8C95X0_DIRECTION;
 		break;
 	case PIN_CONFIG_MODE_PWM:
-		reg = CY8C95X0_PWMSEL;
+		reg = CY8C95X0_SELPWM;
 		break;
 	case PIN_CONFIG_OUTPUT:
 		reg = CY8C95X0_OUTPUT;
@@ -881,7 +889,7 @@ static int cy8c95x0_gpio_set_pincfg(struct cy8c95x0_pinctrl *chip,
 		reg = CY8C95X0_DRV_PP_FAST;
 		break;
 	case PIN_CONFIG_MODE_PWM:
-		reg = CY8C95X0_PWMSEL;
+		reg = CY8C95X0_SELPWM;
 		break;
 	case PIN_CONFIG_OUTPUT_ENABLE:
 		ret = cy8c95x0_pinmux_direction(chip, off, !arg);
@@ -1171,7 +1179,7 @@ static void cy8c95x0_pin_dbg_show(struct pinctrl_dev *pctldev, struct seq_file *
 	bitmap_zero(mask, MAX_LINE);
 	__set_bit(pin, mask);
 
-	if (cy8c95x0_read_regs_mask(chip, CY8C95X0_PWMSEL, pwm, mask)) {
+	if (cy8c95x0_read_regs_mask(chip, CY8C95X0_SELPWM, pwm, mask)) {
 		seq_puts(s, "not available");
 		return;
 	}
@@ -1216,7 +1224,7 @@ static int cy8c95x0_set_mode(struct cy8c95x0_pinctrl *chip, unsigned int off, bo
 	u8 port = cypress_get_port(chip, off);
 	u8 bit = cypress_get_pin_mask(chip, off);
 
-	return cy8c95x0_regmap_write_bits(chip, CY8C95X0_PWMSEL, port, bit, mode ? bit : 0);
+	return cy8c95x0_regmap_write_bits(chip, CY8C95X0_SELPWM, port, bit, mode ? bit : 0);
 }
 
 static int cy8c95x0_pinmux_mode(struct cy8c95x0_pinctrl *chip,
@@ -1365,7 +1373,7 @@ static int cy8c95x0_irq_setup(struct cy8c95x0_pinctrl *chip, int irq)
 
 	ret = devm_request_threaded_irq(chip->dev, irq,
 					NULL, cy8c95x0_irq_handler,
-					IRQF_ONESHOT | IRQF_SHARED | IRQF_TRIGGER_HIGH,
+					IRQF_ONESHOT | IRQF_SHARED,
 					dev_name(chip->dev), chip);
 	if (ret) {
 		dev_err(chip->dev, "failed to request irq %d\n", irq);
diff --git a/drivers/pinctrl/pinctrl-mcp23s08.c b/drivers/pinctrl/pinctrl-mcp23s08.c
index f384c72d9554..60fcd53830a7 100644
--- a/drivers/pinctrl/pinctrl-mcp23s08.c
+++ b/drivers/pinctrl/pinctrl-mcp23s08.c
@@ -382,6 +382,7 @@ static irqreturn_t mcp23s08_irq(int irq, void *data)
 {
 	struct mcp23s08 *mcp = data;
 	int intcap, intcon, intf, i, gpio, gpio_orig, intcap_mask, defval, gpinten;
+	bool need_unmask = false;
 	unsigned long int enabled_interrupts;
 	unsigned int child_irq;
 	bool intf_set, intcap_changed, gpio_bit_changed,
@@ -396,9 +397,6 @@ static irqreturn_t mcp23s08_irq(int irq, void *data)
 		goto unlock;
 	}
 
-	if (mcp_read(mcp, MCP_INTCAP, &intcap))
-		goto unlock;
-
 	if (mcp_read(mcp, MCP_INTCON, &intcon))
 		goto unlock;
 
@@ -408,6 +406,16 @@ static irqreturn_t mcp23s08_irq(int irq, void *data)
 	if (mcp_read(mcp, MCP_DEFVAL, &defval))
 		goto unlock;
 
+	/* Mask level interrupts to avoid their immediate reactivation after clearing */
+	if (intcon) {
+		need_unmask = true;
+		if (mcp_write(mcp, MCP_GPINTEN, gpinten & ~intcon))
+			goto unlock;
+	}
+
+	if (mcp_read(mcp, MCP_INTCAP, &intcap))
+		goto unlock;
+
 	/* This clears the interrupt(configurable on S18) */
 	if (mcp_read(mcp, MCP_GPIO, &gpio))
 		goto unlock;
@@ -470,9 +478,18 @@ static irqreturn_t mcp23s08_irq(int irq, void *data)
 		}
 	}
 
+	if (need_unmask) {
+		mutex_lock(&mcp->lock);
+		goto unlock;
+	}
+
 	return IRQ_HANDLED;
 
 unlock:
+	if (need_unmask)
+		if (mcp_write(mcp, MCP_GPINTEN, gpinten))
+			dev_err(mcp->chip.parent, "can't unmask GPINTEN\n");
+
 	mutex_unlock(&mcp->lock);
 	return IRQ_HANDLED;
 }
@@ -619,6 +636,14 @@ int mcp23s08_probe_one(struct mcp23s08 *mcp, struct device *dev,
 
 	mcp->reset_gpio = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_LOW);
 
+	/*
+	 * Reset the chip - we don't really know what state it's in, so reset
+	 * all pins to input first to prevent surprises.
+	 */
+	ret = mcp_write(mcp, MCP_IODIR, mcp->chip.ngpio == 16 ? 0xFFFF : 0xFF);
+	if (ret < 0)
+		return ret;
+
 	/* verify MCP_IOCON.SEQOP = 0, so sequential reads work,
 	 * and MCP_IOCON.HAEN = 1, so we work with all chips.
 	 */
diff --git a/drivers/pinctrl/pinmux.c b/drivers/pinctrl/pinmux.c
index 0743190da59e..2c31e7f2a27a 100644
--- a/drivers/pinctrl/pinmux.c
+++ b/drivers/pinctrl/pinmux.c
@@ -236,18 +236,7 @@ static const char *pin_free(struct pinctrl_dev *pctldev, int pin,
 			if (desc->mux_usecount)
 				return NULL;
 		}
-	}
-
-	/*
-	 * If there is no kind of request function for the pin we just assume
-	 * we got it by default and proceed.
-	 */
-	if (gpio_range && ops->gpio_disable_free)
-		ops->gpio_disable_free(pctldev, gpio_range, pin);
-	else if (ops->free)
-		ops->free(pctldev, pin);
 
-	scoped_guard(mutex, &desc->mux_lock) {
 		if (gpio_range) {
 			owner = desc->gpio_owner;
 			desc->gpio_owner = NULL;
@@ -258,6 +247,15 @@ static const char *pin_free(struct pinctrl_dev *pctldev, int pin,
 		}
 	}
 
+	/*
+	 * If there is no kind of request function for the pin we just assume
+	 * we got it by default and proceed.
+	 */
+	if (gpio_range && ops->gpio_disable_free)
+		ops->gpio_disable_free(pctldev, gpio_range, pin);
+	else if (ops->free)
+		ops->free(pctldev, pin);
+
 	module_put(pctldev->owner);
 
 	return owner;
diff --git a/drivers/pinctrl/qcom/pinctrl-msm.c b/drivers/pinctrl/qcom/pinctrl-msm.c
index aeaf0d1958f5..553232809789 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm.c
@@ -43,7 +43,6 @@
  * @pctrl:          pinctrl handle.
  * @chip:           gpiochip handle.
  * @desc:           pin controller descriptor
- * @restart_nb:     restart notifier block.
  * @irq:            parent irq for the TLMM irq_chip.
  * @intr_target_use_scm: route irq to application cpu using scm calls
  * @lock:           Spinlock to protect register resources as well
@@ -63,7 +62,6 @@ struct msm_pinctrl {
 	struct pinctrl_dev *pctrl;
 	struct gpio_chip chip;
 	struct pinctrl_desc desc;
-	struct notifier_block restart_nb;
 
 	int irq;
 
@@ -1037,6 +1035,25 @@ static bool msm_gpio_needs_dual_edge_parent_workaround(struct irq_data *d,
 	       test_bit(d->hwirq, pctrl->skip_wake_irqs);
 }
 
+static void msm_gpio_irq_init_valid_mask(struct gpio_chip *gc,
+					 unsigned long *valid_mask,
+					 unsigned int ngpios)
+{
+	struct msm_pinctrl *pctrl = gpiochip_get_data(gc);
+	const struct msm_pingroup *g;
+	int i;
+
+	bitmap_fill(valid_mask, ngpios);
+
+	for (i = 0; i < ngpios; i++) {
+		g = &pctrl->soc->groups[i];
+
+		if (g->intr_detection_width != 1 &&
+		    g->intr_detection_width != 2)
+			clear_bit(i, valid_mask);
+	}
+}
+
 static int msm_gpio_irq_set_type(struct irq_data *d, unsigned int type)
 {
 	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
@@ -1044,8 +1061,7 @@ static int msm_gpio_irq_set_type(struct irq_data *d, unsigned int type)
 	const struct msm_pingroup *g;
 	u32 intr_target_mask = GENMASK(2, 0);
 	unsigned long flags;
-	bool was_enabled;
-	u32 val;
+	u32 val, oldval;
 
 	if (msm_gpio_needs_dual_edge_parent_workaround(d, type)) {
 		set_bit(d->hwirq, pctrl->dual_edge_irqs);
@@ -1107,8 +1123,7 @@ static int msm_gpio_irq_set_type(struct irq_data *d, unsigned int type)
 	 * internal circuitry of TLMM, toggling the RAW_STATUS
 	 * could cause the INTR_STATUS to be set for EDGE interrupts.
 	 */
-	val = msm_readl_intr_cfg(pctrl, g);
-	was_enabled = val & BIT(g->intr_raw_status_bit);
+	val = oldval = msm_readl_intr_cfg(pctrl, g);
 	val |= BIT(g->intr_raw_status_bit);
 	if (g->intr_detection_width == 2) {
 		val &= ~(3 << g->intr_detection_bit);
@@ -1161,9 +1176,11 @@ static int msm_gpio_irq_set_type(struct irq_data *d, unsigned int type)
 	/*
 	 * The first time we set RAW_STATUS_EN it could trigger an interrupt.
 	 * Clear the interrupt.  This is safe because we have
-	 * IRQCHIP_SET_TYPE_MASKED.
+	 * IRQCHIP_SET_TYPE_MASKED. When changing the interrupt type, we could
+	 * also still have a non-matching interrupt latched, so clear whenever
+	 * making changes to the interrupt configuration.
 	 */
-	if (!was_enabled)
+	if (val != oldval)
 		msm_ack_intr_status(pctrl, g);
 
 	if (test_bit(d->hwirq, pctrl->dual_edge_irqs))
@@ -1440,6 +1457,7 @@ static int msm_gpio_init(struct msm_pinctrl *pctrl)
 	girq->default_type = IRQ_TYPE_NONE;
 	girq->handler = handle_bad_irq;
 	girq->parents[0] = pctrl->irq;
+	girq->init_valid_mask = msm_gpio_irq_init_valid_mask;
 
 	ret = gpiochip_add_data(&pctrl->chip, pctrl);
 	if (ret) {
@@ -1470,10 +1488,9 @@ static int msm_gpio_init(struct msm_pinctrl *pctrl)
 	return 0;
 }
 
-static int msm_ps_hold_restart(struct notifier_block *nb, unsigned long action,
-			       void *data)
+static int msm_ps_hold_restart(struct sys_off_data *data)
 {
-	struct msm_pinctrl *pctrl = container_of(nb, struct msm_pinctrl, restart_nb);
+	struct msm_pinctrl *pctrl = data->cb_data;
 
 	writel(0, pctrl->regs[0] + PS_HOLD_OFFSET);
 	mdelay(1000);
@@ -1484,7 +1501,11 @@ static struct msm_pinctrl *poweroff_pctrl;
 
 static void msm_ps_hold_poweroff(void)
 {
-	msm_ps_hold_restart(&poweroff_pctrl->restart_nb, 0, NULL);
+	struct sys_off_data data = {
+		.cb_data = poweroff_pctrl,
+	};
+
+	msm_ps_hold_restart(&data);
 }
 
 static void msm_pinctrl_setup_pm_reset(struct msm_pinctrl *pctrl)
@@ -1494,9 +1515,11 @@ static void msm_pinctrl_setup_pm_reset(struct msm_pinctrl *pctrl)
 
 	for (i = 0; i < pctrl->soc->nfunctions; i++)
 		if (!strcmp(func[i].name, "ps_hold")) {
-			pctrl->restart_nb.notifier_call = msm_ps_hold_restart;
-			pctrl->restart_nb.priority = 128;
-			if (register_restart_handler(&pctrl->restart_nb))
+			if (devm_register_sys_off_handler(pctrl->dev,
+							  SYS_OFF_MODE_RESTART,
+							  128,
+							  msm_ps_hold_restart,
+							  pctrl))
 				dev_err(pctrl->dev,
 					"failed to setup restart handler.\n");
 			poweroff_pctrl = pctrl;
@@ -1598,8 +1621,6 @@ void msm_pinctrl_remove(struct platform_device *pdev)
 	struct msm_pinctrl *pctrl = platform_get_drvdata(pdev);
 
 	gpiochip_remove(&pctrl->chip);
-
-	unregister_restart_handler(&pctrl->restart_nb);
 }
 EXPORT_SYMBOL(msm_pinctrl_remove);
 
diff --git a/drivers/pinctrl/qcom/pinctrl-qcm2290.c b/drivers/pinctrl/qcom/pinctrl-qcm2290.c
index f5c1c427b44e..61b7c22e963c 100644
--- a/drivers/pinctrl/qcom/pinctrl-qcm2290.c
+++ b/drivers/pinctrl/qcom/pinctrl-qcm2290.c
@@ -165,6 +165,10 @@ static const struct pinctrl_pin_desc qcm2290_pins[] = {
 	PINCTRL_PIN(62, "GPIO_62"),
 	PINCTRL_PIN(63, "GPIO_63"),
 	PINCTRL_PIN(64, "GPIO_64"),
+	PINCTRL_PIN(65, "GPIO_65"),
+	PINCTRL_PIN(66, "GPIO_66"),
+	PINCTRL_PIN(67, "GPIO_67"),
+	PINCTRL_PIN(68, "GPIO_68"),
 	PINCTRL_PIN(69, "GPIO_69"),
 	PINCTRL_PIN(70, "GPIO_70"),
 	PINCTRL_PIN(71, "GPIO_71"),
@@ -179,12 +183,17 @@ static const struct pinctrl_pin_desc qcm2290_pins[] = {
 	PINCTRL_PIN(80, "GPIO_80"),
 	PINCTRL_PIN(81, "GPIO_81"),
 	PINCTRL_PIN(82, "GPIO_82"),
+	PINCTRL_PIN(83, "GPIO_83"),
+	PINCTRL_PIN(84, "GPIO_84"),
+	PINCTRL_PIN(85, "GPIO_85"),
 	PINCTRL_PIN(86, "GPIO_86"),
 	PINCTRL_PIN(87, "GPIO_87"),
 	PINCTRL_PIN(88, "GPIO_88"),
 	PINCTRL_PIN(89, "GPIO_89"),
 	PINCTRL_PIN(90, "GPIO_90"),
 	PINCTRL_PIN(91, "GPIO_91"),
+	PINCTRL_PIN(92, "GPIO_92"),
+	PINCTRL_PIN(93, "GPIO_93"),
 	PINCTRL_PIN(94, "GPIO_94"),
 	PINCTRL_PIN(95, "GPIO_95"),
 	PINCTRL_PIN(96, "GPIO_96"),
diff --git a/drivers/pinctrl/renesas/pinctrl-rza2.c b/drivers/pinctrl/renesas/pinctrl-rza2.c
index af689d7c117f..8369fab61758 100644
--- a/drivers/pinctrl/renesas/pinctrl-rza2.c
+++ b/drivers/pinctrl/renesas/pinctrl-rza2.c
@@ -243,6 +243,9 @@ static int rza2_gpio_register(struct rza2_pinctrl_priv *priv)
 	int ret;
 
 	chip.label = devm_kasprintf(priv->dev, GFP_KERNEL, "%pOFn", np);
+	if (!chip.label)
+		return -ENOMEM;
+
 	chip.parent = priv->dev;
 	chip.ngpio = priv->npins;
 
@@ -253,6 +256,8 @@ static int rza2_gpio_register(struct rza2_pinctrl_priv *priv)
 		return ret;
 	}
 
+	of_node_put(of_args.np);
+
 	if ((of_args.args[0] != 0) ||
 	    (of_args.args[1] != 0) ||
 	    (of_args.args[2] != priv->npins)) {
diff --git a/drivers/pinctrl/renesas/pinctrl-rzg2l.c b/drivers/pinctrl/renesas/pinctrl-rzg2l.c
index 3a81837b5e62..bde58f5a743c 100644
--- a/drivers/pinctrl/renesas/pinctrl-rzg2l.c
+++ b/drivers/pinctrl/renesas/pinctrl-rzg2l.c
@@ -155,7 +155,7 @@
 #define PWPR_REGWE_B		BIT(5)	/* OEN Register Write Enable, known only in RZ/V2H(P) */
 
 #define PM_MASK			0x03
-#define PFC_MASK		0x07
+#define PFC_MASK		0x0f
 #define IEN_MASK		0x01
 #define IOLH_MASK		0x03
 #define SR_MASK			0x01
@@ -311,6 +311,7 @@ struct rzg2l_pinctrl_pin_settings {
  * @pmc: PMC registers cache
  * @pfc: PFC registers cache
  * @iolh: IOLH registers cache
+ * @pupd: PUPD registers cache
  * @ien: IEN registers cache
  * @sd_ch: SD_CH registers cache
  * @eth_poc: ET_POC registers cache
@@ -324,6 +325,7 @@ struct rzg2l_pinctrl_reg_cache {
 	u32	*pfc;
 	u32	*iolh[2];
 	u32	*ien[2];
+	u32	*pupd[2];
 	u8	sd_ch[2];
 	u8	eth_poc[2];
 	u8	eth_mode;
@@ -2539,6 +2541,11 @@ static int rzg2l_pinctrl_reg_cache_alloc(struct rzg2l_pinctrl *pctrl)
 		if (!cache->ien[i])
 			return -ENOMEM;
 
+		cache->pupd[i] = devm_kcalloc(pctrl->dev, nports, sizeof(*cache->pupd[i]),
+					      GFP_KERNEL);
+		if (!cache->pupd[i])
+			return -ENOMEM;
+
 		/* Allocate dedicated cache. */
 		dedicated_cache->iolh[i] = devm_kcalloc(pctrl->dev, n_dedicated_pins,
 							sizeof(*dedicated_cache->iolh[i]),
@@ -2583,6 +2590,8 @@ static int rzg2l_gpio_register(struct rzg2l_pinctrl *pctrl)
 	if (ret)
 		return dev_err_probe(pctrl->dev, ret, "Unable to parse gpio-ranges\n");
 
+	of_node_put(of_args.np);
+
 	if (of_args.args[0] != 0 || of_args.args[1] != 0 ||
 	    of_args.args[2] != pctrl->data->n_port_pins)
 		return dev_err_probe(pctrl->dev, -EINVAL,
@@ -2777,7 +2786,7 @@ static void rzg2l_pinctrl_pm_setup_regs(struct rzg2l_pinctrl *pctrl, bool suspen
 	struct rzg2l_pinctrl_reg_cache *cache = pctrl->cache;
 
 	for (u32 port = 0; port < nports; port++) {
-		bool has_iolh, has_ien;
+		bool has_iolh, has_ien, has_pupd;
 		u32 off, caps;
 		u8 pincnt;
 		u64 cfg;
@@ -2789,6 +2798,7 @@ static void rzg2l_pinctrl_pm_setup_regs(struct rzg2l_pinctrl *pctrl, bool suspen
 		caps = FIELD_GET(PIN_CFG_MASK, cfg);
 		has_iolh = !!(caps & (PIN_CFG_IOLH_A | PIN_CFG_IOLH_B | PIN_CFG_IOLH_C));
 		has_ien = !!(caps & PIN_CFG_IEN);
+		has_pupd = !!(caps & PIN_CFG_PUPD);
 
 		if (suspend)
 			RZG2L_PCTRL_REG_ACCESS32(suspend, pctrl->base + PFC(off), cache->pfc[port]);
@@ -2807,6 +2817,15 @@ static void rzg2l_pinctrl_pm_setup_regs(struct rzg2l_pinctrl *pctrl, bool suspen
 			}
 		}
 
+		if (has_pupd) {
+			RZG2L_PCTRL_REG_ACCESS32(suspend, pctrl->base + PUPD(off),
+						 cache->pupd[0][port]);
+			if (pincnt >= 4) {
+				RZG2L_PCTRL_REG_ACCESS32(suspend, pctrl->base + PUPD(off),
+							 cache->pupd[1][port]);
+			}
+		}
+
 		RZG2L_PCTRL_REG_ACCESS16(suspend, pctrl->base + PM(off), cache->pm[port]);
 		RZG2L_PCTRL_REG_ACCESS8(suspend, pctrl->base + P(off), cache->p[port]);
 
@@ -3180,6 +3199,7 @@ static struct platform_driver rzg2l_pinctrl_driver = {
 		.name = DRV_NAME,
 		.of_match_table = of_match_ptr(rzg2l_pinctrl_of_table),
 		.pm = pm_sleep_ptr(&rzg2l_pinctrl_pm_ops),
+		.suppress_bind_attrs = true,
 	},
 	.probe = rzg2l_pinctrl_probe,
 };
diff --git a/drivers/pinctrl/renesas/pinctrl-rzv2m.c b/drivers/pinctrl/renesas/pinctrl-rzv2m.c
index 4062c56619f5..8c7169db4fcc 100644
--- a/drivers/pinctrl/renesas/pinctrl-rzv2m.c
+++ b/drivers/pinctrl/renesas/pinctrl-rzv2m.c
@@ -940,6 +940,8 @@ static int rzv2m_gpio_register(struct rzv2m_pinctrl *pctrl)
 		return ret;
 	}
 
+	of_node_put(of_args.np);
+
 	if (of_args.args[0] != 0 || of_args.args[1] != 0 ||
 	    of_args.args[2] != pctrl->data->n_port_pins) {
 		dev_err(pctrl->dev, "gpio-ranges does not match selected SOC\n");
diff --git a/drivers/pinctrl/samsung/pinctrl-exynos-arm64.c b/drivers/pinctrl/samsung/pinctrl-exynos-arm64.c
index 5480e0884abe..a2ac1702d0df 100644
--- a/drivers/pinctrl/samsung/pinctrl-exynos-arm64.c
+++ b/drivers/pinctrl/samsung/pinctrl-exynos-arm64.c
@@ -809,8 +809,8 @@ static const struct samsung_pin_ctrl exynosautov920_pin_ctrl[] = {
 		.pin_banks	= exynosautov920_pin_banks0,
 		.nr_banks	= ARRAY_SIZE(exynosautov920_pin_banks0),
 		.eint_wkup_init	= exynos_eint_wkup_init,
-		.suspend	= exynos_pinctrl_suspend,
-		.resume		= exynos_pinctrl_resume,
+		.suspend	= exynosautov920_pinctrl_suspend,
+		.resume		= exynosautov920_pinctrl_resume,
 		.retention_data	= &exynosautov920_retention_data,
 	}, {
 		/* pin-controller instance 1 AUD data */
@@ -821,43 +821,43 @@ static const struct samsung_pin_ctrl exynosautov920_pin_ctrl[] = {
 		.pin_banks	= exynosautov920_pin_banks2,
 		.nr_banks	= ARRAY_SIZE(exynosautov920_pin_banks2),
 		.eint_gpio_init	= exynos_eint_gpio_init,
-		.suspend	= exynos_pinctrl_suspend,
-		.resume		= exynos_pinctrl_resume,
+		.suspend	= exynosautov920_pinctrl_suspend,
+		.resume		= exynosautov920_pinctrl_resume,
 	}, {
 		/* pin-controller instance 3 HSI1 data */
 		.pin_banks	= exynosautov920_pin_banks3,
 		.nr_banks	= ARRAY_SIZE(exynosautov920_pin_banks3),
 		.eint_gpio_init	= exynos_eint_gpio_init,
-		.suspend	= exynos_pinctrl_suspend,
-		.resume		= exynos_pinctrl_resume,
+		.suspend	= exynosautov920_pinctrl_suspend,
+		.resume		= exynosautov920_pinctrl_resume,
 	}, {
 		/* pin-controller instance 4 HSI2 data */
 		.pin_banks	= exynosautov920_pin_banks4,
 		.nr_banks	= ARRAY_SIZE(exynosautov920_pin_banks4),
 		.eint_gpio_init	= exynos_eint_gpio_init,
-		.suspend	= exynos_pinctrl_suspend,
-		.resume		= exynos_pinctrl_resume,
+		.suspend	= exynosautov920_pinctrl_suspend,
+		.resume		= exynosautov920_pinctrl_resume,
 	}, {
 		/* pin-controller instance 5 HSI2UFS data */
 		.pin_banks	= exynosautov920_pin_banks5,
 		.nr_banks	= ARRAY_SIZE(exynosautov920_pin_banks5),
 		.eint_gpio_init	= exynos_eint_gpio_init,
-		.suspend	= exynos_pinctrl_suspend,
-		.resume		= exynos_pinctrl_resume,
+		.suspend	= exynosautov920_pinctrl_suspend,
+		.resume		= exynosautov920_pinctrl_resume,
 	}, {
 		/* pin-controller instance 6 PERIC0 data */
 		.pin_banks	= exynosautov920_pin_banks6,
 		.nr_banks	= ARRAY_SIZE(exynosautov920_pin_banks6),
 		.eint_gpio_init	= exynos_eint_gpio_init,
-		.suspend	= exynos_pinctrl_suspend,
-		.resume		= exynos_pinctrl_resume,
+		.suspend	= exynosautov920_pinctrl_suspend,
+		.resume		= exynosautov920_pinctrl_resume,
 	}, {
 		/* pin-controller instance 7 PERIC1 data */
 		.pin_banks	= exynosautov920_pin_banks7,
 		.nr_banks	= ARRAY_SIZE(exynosautov920_pin_banks7),
 		.eint_gpio_init	= exynos_eint_gpio_init,
-		.suspend	= exynos_pinctrl_suspend,
-		.resume		= exynos_pinctrl_resume,
+		.suspend	= exynosautov920_pinctrl_suspend,
+		.resume		= exynosautov920_pinctrl_resume,
 	},
 };
 
@@ -939,83 +939,83 @@ const struct samsung_pinctrl_of_match_data fsd_of_data __initconst = {
 
 /* pin banks of gs101 pin-controller (ALIVE) */
 static const struct samsung_pin_bank_data gs101_pin_alive[] = {
-	EXYNOS850_PIN_BANK_EINTW(8, 0x0, "gpa0", 0x00),
-	EXYNOS850_PIN_BANK_EINTW(7, 0x20, "gpa1", 0x04),
-	EXYNOS850_PIN_BANK_EINTW(5, 0x40, "gpa2", 0x08),
-	EXYNOS850_PIN_BANK_EINTW(4, 0x60, "gpa3", 0x0c),
-	EXYNOS850_PIN_BANK_EINTW(4, 0x80, "gpa4", 0x10),
-	EXYNOS850_PIN_BANK_EINTW(7, 0xa0, "gpa5", 0x14),
-	EXYNOS850_PIN_BANK_EINTW(8, 0xc0, "gpa9", 0x18),
-	EXYNOS850_PIN_BANK_EINTW(2, 0xe0, "gpa10", 0x1c),
+	GS101_PIN_BANK_EINTW(8, 0x0, "gpa0", 0x00, 0x00),
+	GS101_PIN_BANK_EINTW(7, 0x20, "gpa1", 0x04, 0x08),
+	GS101_PIN_BANK_EINTW(5, 0x40, "gpa2", 0x08, 0x10),
+	GS101_PIN_BANK_EINTW(4, 0x60, "gpa3", 0x0c, 0x18),
+	GS101_PIN_BANK_EINTW(4, 0x80, "gpa4", 0x10, 0x1c),
+	GS101_PIN_BANK_EINTW(7, 0xa0, "gpa5", 0x14, 0x20),
+	GS101_PIN_BANK_EINTW(8, 0xc0, "gpa9", 0x18, 0x28),
+	GS101_PIN_BANK_EINTW(2, 0xe0, "gpa10", 0x1c, 0x30),
 };
 
 /* pin banks of gs101 pin-controller (FAR_ALIVE) */
 static const struct samsung_pin_bank_data gs101_pin_far_alive[] = {
-	EXYNOS850_PIN_BANK_EINTW(8, 0x0, "gpa6", 0x00),
-	EXYNOS850_PIN_BANK_EINTW(4, 0x20, "gpa7", 0x04),
-	EXYNOS850_PIN_BANK_EINTW(8, 0x40, "gpa8", 0x08),
-	EXYNOS850_PIN_BANK_EINTW(2, 0x60, "gpa11", 0x0c),
+	GS101_PIN_BANK_EINTW(8, 0x0, "gpa6", 0x00, 0x00),
+	GS101_PIN_BANK_EINTW(4, 0x20, "gpa7", 0x04, 0x08),
+	GS101_PIN_BANK_EINTW(8, 0x40, "gpa8", 0x08, 0x0c),
+	GS101_PIN_BANK_EINTW(2, 0x60, "gpa11", 0x0c, 0x14),
 };
 
 /* pin banks of gs101 pin-controller (GSACORE) */
 static const struct samsung_pin_bank_data gs101_pin_gsacore[] = {
-	EXYNOS850_PIN_BANK_EINTG(2, 0x0, "gps0", 0x00),
-	EXYNOS850_PIN_BANK_EINTG(8, 0x20, "gps1", 0x04),
-	EXYNOS850_PIN_BANK_EINTG(3, 0x40, "gps2", 0x08),
+	GS101_PIN_BANK_EINTG(2, 0x0, "gps0", 0x00, 0x00),
+	GS101_PIN_BANK_EINTG(8, 0x20, "gps1", 0x04, 0x04),
+	GS101_PIN_BANK_EINTG(3, 0x40, "gps2", 0x08, 0x0c),
 };
 
 /* pin banks of gs101 pin-controller (GSACTRL) */
 static const struct samsung_pin_bank_data gs101_pin_gsactrl[] = {
-	EXYNOS850_PIN_BANK_EINTW(6, 0x0, "gps3", 0x00),
+	GS101_PIN_BANK_EINTW(6, 0x0, "gps3", 0x00, 0x00),
 };
 
 /* pin banks of gs101 pin-controller (PERIC0) */
 static const struct samsung_pin_bank_data gs101_pin_peric0[] = {
-	EXYNOS850_PIN_BANK_EINTG(5, 0x0, "gpp0", 0x00),
-	EXYNOS850_PIN_BANK_EINTG(4, 0x20, "gpp1", 0x04),
-	EXYNOS850_PIN_BANK_EINTG(4, 0x40, "gpp2", 0x08),
-	EXYNOS850_PIN_BANK_EINTG(2, 0x60, "gpp3", 0x0c),
-	EXYNOS850_PIN_BANK_EINTG(4, 0x80, "gpp4", 0x10),
-	EXYNOS850_PIN_BANK_EINTG(2, 0xa0, "gpp5", 0x14),
-	EXYNOS850_PIN_BANK_EINTG(4, 0xc0, "gpp6", 0x18),
-	EXYNOS850_PIN_BANK_EINTG(2, 0xe0, "gpp7", 0x1c),
-	EXYNOS850_PIN_BANK_EINTG(4, 0x100, "gpp8", 0x20),
-	EXYNOS850_PIN_BANK_EINTG(2, 0x120, "gpp9", 0x24),
-	EXYNOS850_PIN_BANK_EINTG(4, 0x140, "gpp10", 0x28),
-	EXYNOS850_PIN_BANK_EINTG(2, 0x160, "gpp11", 0x2c),
-	EXYNOS850_PIN_BANK_EINTG(4, 0x180, "gpp12", 0x30),
-	EXYNOS850_PIN_BANK_EINTG(2, 0x1a0, "gpp13", 0x34),
-	EXYNOS850_PIN_BANK_EINTG(4, 0x1c0, "gpp14", 0x38),
-	EXYNOS850_PIN_BANK_EINTG(2, 0x1e0, "gpp15", 0x3c),
-	EXYNOS850_PIN_BANK_EINTG(4, 0x200, "gpp16", 0x40),
-	EXYNOS850_PIN_BANK_EINTG(2, 0x220, "gpp17", 0x44),
-	EXYNOS850_PIN_BANK_EINTG(4, 0x240, "gpp18", 0x48),
-	EXYNOS850_PIN_BANK_EINTG(4, 0x260, "gpp19", 0x4c),
+	GS101_PIN_BANK_EINTG(5, 0x0, "gpp0", 0x00, 0x00),
+	GS101_PIN_BANK_EINTG(4, 0x20, "gpp1", 0x04, 0x08),
+	GS101_PIN_BANK_EINTG(4, 0x40, "gpp2", 0x08, 0x0c),
+	GS101_PIN_BANK_EINTG(2, 0x60, "gpp3", 0x0c, 0x10),
+	GS101_PIN_BANK_EINTG(4, 0x80, "gpp4", 0x10, 0x14),
+	GS101_PIN_BANK_EINTG(2, 0xa0, "gpp5", 0x14, 0x18),
+	GS101_PIN_BANK_EINTG(4, 0xc0, "gpp6", 0x18, 0x1c),
+	GS101_PIN_BANK_EINTG(2, 0xe0, "gpp7", 0x1c, 0x20),
+	GS101_PIN_BANK_EINTG(4, 0x100, "gpp8", 0x20, 0x24),
+	GS101_PIN_BANK_EINTG(2, 0x120, "gpp9", 0x24, 0x28),
+	GS101_PIN_BANK_EINTG(4, 0x140, "gpp10", 0x28, 0x2c),
+	GS101_PIN_BANK_EINTG(2, 0x160, "gpp11", 0x2c, 0x30),
+	GS101_PIN_BANK_EINTG(4, 0x180, "gpp12", 0x30, 0x34),
+	GS101_PIN_BANK_EINTG(2, 0x1a0, "gpp13", 0x34, 0x38),
+	GS101_PIN_BANK_EINTG(4, 0x1c0, "gpp14", 0x38, 0x3c),
+	GS101_PIN_BANK_EINTG(2, 0x1e0, "gpp15", 0x3c, 0x40),
+	GS101_PIN_BANK_EINTG(4, 0x200, "gpp16", 0x40, 0x44),
+	GS101_PIN_BANK_EINTG(2, 0x220, "gpp17", 0x44, 0x48),
+	GS101_PIN_BANK_EINTG(4, 0x240, "gpp18", 0x48, 0x4c),
+	GS101_PIN_BANK_EINTG(4, 0x260, "gpp19", 0x4c, 0x50),
 };
 
 /* pin banks of gs101 pin-controller (PERIC1) */
 static const struct samsung_pin_bank_data gs101_pin_peric1[] = {
-	EXYNOS850_PIN_BANK_EINTG(8, 0x0, "gpp20", 0x00),
-	EXYNOS850_PIN_BANK_EINTG(4, 0x20, "gpp21", 0x04),
-	EXYNOS850_PIN_BANK_EINTG(2, 0x40, "gpp22", 0x08),
-	EXYNOS850_PIN_BANK_EINTG(8, 0x60, "gpp23", 0x0c),
-	EXYNOS850_PIN_BANK_EINTG(4, 0x80, "gpp24", 0x10),
-	EXYNOS850_PIN_BANK_EINTG(4, 0xa0, "gpp25", 0x14),
-	EXYNOS850_PIN_BANK_EINTG(5, 0xc0, "gpp26", 0x18),
-	EXYNOS850_PIN_BANK_EINTG(4, 0xe0, "gpp27", 0x1c),
+	GS101_PIN_BANK_EINTG(8, 0x0, "gpp20", 0x00, 0x00),
+	GS101_PIN_BANK_EINTG(4, 0x20, "gpp21", 0x04, 0x08),
+	GS101_PIN_BANK_EINTG(2, 0x40, "gpp22", 0x08, 0x0c),
+	GS101_PIN_BANK_EINTG(8, 0x60, "gpp23", 0x0c, 0x10),
+	GS101_PIN_BANK_EINTG(4, 0x80, "gpp24", 0x10, 0x18),
+	GS101_PIN_BANK_EINTG(4, 0xa0, "gpp25", 0x14, 0x1c),
+	GS101_PIN_BANK_EINTG(5, 0xc0, "gpp26", 0x18, 0x20),
+	GS101_PIN_BANK_EINTG(4, 0xe0, "gpp27", 0x1c, 0x28),
 };
 
 /* pin banks of gs101 pin-controller (HSI1) */
 static const struct samsung_pin_bank_data gs101_pin_hsi1[] = {
-	EXYNOS850_PIN_BANK_EINTG(6, 0x0, "gph0", 0x00),
-	EXYNOS850_PIN_BANK_EINTG(7, 0x20, "gph1", 0x04),
+	GS101_PIN_BANK_EINTG(6, 0x0, "gph0", 0x00, 0x00),
+	GS101_PIN_BANK_EINTG(7, 0x20, "gph1", 0x04, 0x08),
 };
 
 /* pin banks of gs101 pin-controller (HSI2) */
 static const struct samsung_pin_bank_data gs101_pin_hsi2[] = {
-	EXYNOS850_PIN_BANK_EINTG(6, 0x0, "gph2", 0x00),
-	EXYNOS850_PIN_BANK_EINTG(2, 0x20, "gph3", 0x04),
-	EXYNOS850_PIN_BANK_EINTG(6, 0x40, "gph4", 0x08),
+	GS101_PIN_BANK_EINTG(6, 0x0, "gph2", 0x00, 0x00),
+	GS101_PIN_BANK_EINTG(2, 0x20, "gph3", 0x04, 0x08),
+	GS101_PIN_BANK_EINTG(6, 0x40, "gph4", 0x08, 0x0c),
 };
 
 static const struct samsung_pin_ctrl gs101_pin_ctrl[] __initconst = {
@@ -1024,15 +1024,15 @@ static const struct samsung_pin_ctrl gs101_pin_ctrl[] __initconst = {
 		.pin_banks	= gs101_pin_alive,
 		.nr_banks	= ARRAY_SIZE(gs101_pin_alive),
 		.eint_wkup_init = exynos_eint_wkup_init,
-		.suspend	= exynos_pinctrl_suspend,
-		.resume		= exynos_pinctrl_resume,
+		.suspend	= gs101_pinctrl_suspend,
+		.resume		= gs101_pinctrl_resume,
 	}, {
 		/* pin banks of gs101 pin-controller (FAR_ALIVE) */
 		.pin_banks	= gs101_pin_far_alive,
 		.nr_banks	= ARRAY_SIZE(gs101_pin_far_alive),
 		.eint_wkup_init = exynos_eint_wkup_init,
-		.suspend	= exynos_pinctrl_suspend,
-		.resume		= exynos_pinctrl_resume,
+		.suspend	= gs101_pinctrl_suspend,
+		.resume		= gs101_pinctrl_resume,
 	}, {
 		/* pin banks of gs101 pin-controller (GSACORE) */
 		.pin_banks	= gs101_pin_gsacore,
@@ -1046,29 +1046,29 @@ static const struct samsung_pin_ctrl gs101_pin_ctrl[] __initconst = {
 		.pin_banks	= gs101_pin_peric0,
 		.nr_banks	= ARRAY_SIZE(gs101_pin_peric0),
 		.eint_gpio_init = exynos_eint_gpio_init,
-		.suspend	= exynos_pinctrl_suspend,
-		.resume		= exynos_pinctrl_resume,
+		.suspend	= gs101_pinctrl_suspend,
+		.resume		= gs101_pinctrl_resume,
 	}, {
 		/* pin banks of gs101 pin-controller (PERIC1) */
 		.pin_banks	= gs101_pin_peric1,
 		.nr_banks	= ARRAY_SIZE(gs101_pin_peric1),
 		.eint_gpio_init = exynos_eint_gpio_init,
-		.suspend	= exynos_pinctrl_suspend,
-		.resume	= exynos_pinctrl_resume,
+		.suspend	= gs101_pinctrl_suspend,
+		.resume		= gs101_pinctrl_resume,
 	}, {
 		/* pin banks of gs101 pin-controller (HSI1) */
 		.pin_banks	= gs101_pin_hsi1,
 		.nr_banks	= ARRAY_SIZE(gs101_pin_hsi1),
 		.eint_gpio_init = exynos_eint_gpio_init,
-		.suspend	= exynos_pinctrl_suspend,
-		.resume		= exynos_pinctrl_resume,
+		.suspend	= gs101_pinctrl_suspend,
+		.resume		= gs101_pinctrl_resume,
 	}, {
 		/* pin banks of gs101 pin-controller (HSI2) */
 		.pin_banks	= gs101_pin_hsi2,
 		.nr_banks	= ARRAY_SIZE(gs101_pin_hsi2),
 		.eint_gpio_init = exynos_eint_gpio_init,
-		.suspend	= exynos_pinctrl_suspend,
-		.resume		= exynos_pinctrl_resume,
+		.suspend	= gs101_pinctrl_suspend,
+		.resume		= gs101_pinctrl_resume,
 	},
 };
 
diff --git a/drivers/pinctrl/samsung/pinctrl-exynos.c b/drivers/pinctrl/samsung/pinctrl-exynos.c
index b79c211c0374..7887fd416651 100644
--- a/drivers/pinctrl/samsung/pinctrl-exynos.c
+++ b/drivers/pinctrl/samsung/pinctrl-exynos.c
@@ -636,7 +636,7 @@ static void exynos_irq_demux_eint16_31(struct irq_desc *desc)
 		if (clk_enable(b->drvdata->pclk)) {
 			dev_err(b->gpio_chip.parent,
 				"unable to enable clock for pending IRQs\n");
-			return;
+			goto out;
 		}
 	}
 
@@ -652,6 +652,7 @@ static void exynos_irq_demux_eint16_31(struct irq_desc *desc)
 	if (eintd->nr_banks)
 		clk_disable(eintd->banks[0]->drvdata->pclk);
 
+out:
 	chained_irq_exit(chip, desc);
 }
 
@@ -760,153 +761,187 @@ __init int exynos_eint_wkup_init(struct samsung_pinctrl_drv_data *d)
 	return 0;
 }
 
-static void exynos_pinctrl_suspend_bank(
-				struct samsung_pinctrl_drv_data *drvdata,
-				struct samsung_pin_bank *bank)
+static void exynos_set_wakeup(struct samsung_pin_bank *bank)
 {
-	struct exynos_eint_gpio_save *save = bank->soc_priv;
-	const void __iomem *regs = bank->eint_base;
+	struct exynos_irq_chip *irq_chip;
 
-	if (clk_enable(bank->drvdata->pclk)) {
-		dev_err(bank->gpio_chip.parent,
-			"unable to enable clock for saving state\n");
-		return;
+	if (bank->irq_chip) {
+		irq_chip = bank->irq_chip;
+		irq_chip->set_eint_wakeup_mask(bank->drvdata, irq_chip);
 	}
-
-	save->eint_con = readl(regs + EXYNOS_GPIO_ECON_OFFSET
-						+ bank->eint_offset);
-	save->eint_fltcon0 = readl(regs + EXYNOS_GPIO_EFLTCON_OFFSET
-						+ 2 * bank->eint_offset);
-	save->eint_fltcon1 = readl(regs + EXYNOS_GPIO_EFLTCON_OFFSET
-						+ 2 * bank->eint_offset + 4);
-	save->eint_mask = readl(regs + bank->irq_chip->eint_mask
-						+ bank->eint_offset);
-
-	clk_disable(bank->drvdata->pclk);
-
-	pr_debug("%s: save     con %#010x\n", bank->name, save->eint_con);
-	pr_debug("%s: save fltcon0 %#010x\n", bank->name, save->eint_fltcon0);
-	pr_debug("%s: save fltcon1 %#010x\n", bank->name, save->eint_fltcon1);
-	pr_debug("%s: save    mask %#010x\n", bank->name, save->eint_mask);
 }
 
-static void exynosauto_pinctrl_suspend_bank(struct samsung_pinctrl_drv_data *drvdata,
-					    struct samsung_pin_bank *bank)
+void exynos_pinctrl_suspend(struct samsung_pin_bank *bank)
 {
 	struct exynos_eint_gpio_save *save = bank->soc_priv;
 	const void __iomem *regs = bank->eint_base;
 
-	if (clk_enable(bank->drvdata->pclk)) {
-		dev_err(bank->gpio_chip.parent,
-			"unable to enable clock for saving state\n");
-		return;
+	if (bank->eint_type == EINT_TYPE_GPIO) {
+		save->eint_con = readl(regs + EXYNOS_GPIO_ECON_OFFSET
+				       + bank->eint_offset);
+		save->eint_fltcon0 = readl(regs + EXYNOS_GPIO_EFLTCON_OFFSET
+					   + 2 * bank->eint_offset);
+		save->eint_fltcon1 = readl(regs + EXYNOS_GPIO_EFLTCON_OFFSET
+					   + 2 * bank->eint_offset + 4);
+		save->eint_mask = readl(regs + bank->irq_chip->eint_mask
+					+ bank->eint_offset);
+
+		pr_debug("%s: save     con %#010x\n",
+			 bank->name, save->eint_con);
+		pr_debug("%s: save fltcon0 %#010x\n",
+			 bank->name, save->eint_fltcon0);
+		pr_debug("%s: save fltcon1 %#010x\n",
+			 bank->name, save->eint_fltcon1);
+		pr_debug("%s: save    mask %#010x\n",
+			 bank->name, save->eint_mask);
+	} else if (bank->eint_type == EINT_TYPE_WKUP) {
+		exynos_set_wakeup(bank);
 	}
-
-	save->eint_con = readl(regs + bank->pctl_offset + bank->eint_con_offset);
-	save->eint_mask = readl(regs + bank->pctl_offset + bank->eint_mask_offset);
-
-	clk_disable(bank->drvdata->pclk);
-
-	pr_debug("%s: save     con %#010x\n", bank->name, save->eint_con);
-	pr_debug("%s: save    mask %#010x\n", bank->name, save->eint_mask);
 }
 
-void exynos_pinctrl_suspend(struct samsung_pinctrl_drv_data *drvdata)
+void gs101_pinctrl_suspend(struct samsung_pin_bank *bank)
 {
-	struct samsung_pin_bank *bank = drvdata->pin_banks;
-	struct exynos_irq_chip *irq_chip = NULL;
-	int i;
+	struct exynos_eint_gpio_save *save = bank->soc_priv;
+	const void __iomem *regs = bank->eint_base;
 
-	for (i = 0; i < drvdata->nr_banks; ++i, ++bank) {
-		if (bank->eint_type == EINT_TYPE_GPIO) {
-			if (bank->eint_con_offset)
-				exynosauto_pinctrl_suspend_bank(drvdata, bank);
-			else
-				exynos_pinctrl_suspend_bank(drvdata, bank);
-		}
-		else if (bank->eint_type == EINT_TYPE_WKUP) {
-			if (!irq_chip) {
-				irq_chip = bank->irq_chip;
-				irq_chip->set_eint_wakeup_mask(drvdata,
-							       irq_chip);
-			}
-		}
+	if (bank->eint_type == EINT_TYPE_GPIO) {
+		save->eint_con = readl(regs + EXYNOS_GPIO_ECON_OFFSET
+				       + bank->eint_offset);
+
+		save->eint_fltcon0 = readl(regs + EXYNOS_GPIO_EFLTCON_OFFSET
+					   + bank->eint_fltcon_offset);
+
+		/* fltcon1 register only exists for pins 4-7 */
+		if (bank->nr_pins > 4)
+			save->eint_fltcon1 = readl(regs +
+						EXYNOS_GPIO_EFLTCON_OFFSET
+						+ bank->eint_fltcon_offset + 4);
+
+		save->eint_mask = readl(regs + bank->irq_chip->eint_mask
+					+ bank->eint_offset);
+
+		pr_debug("%s: save     con %#010x\n",
+			 bank->name, save->eint_con);
+		pr_debug("%s: save fltcon0 %#010x\n",
+			 bank->name, save->eint_fltcon0);
+		if (bank->nr_pins > 4)
+			pr_debug("%s: save fltcon1 %#010x\n",
+				 bank->name, save->eint_fltcon1);
+		pr_debug("%s: save    mask %#010x\n",
+			 bank->name, save->eint_mask);
+	} else if (bank->eint_type == EINT_TYPE_WKUP) {
+		exynos_set_wakeup(bank);
 	}
 }
 
-static void exynos_pinctrl_resume_bank(
-				struct samsung_pinctrl_drv_data *drvdata,
-				struct samsung_pin_bank *bank)
+void exynosautov920_pinctrl_suspend(struct samsung_pin_bank *bank)
 {
 	struct exynos_eint_gpio_save *save = bank->soc_priv;
-	void __iomem *regs = bank->eint_base;
+	const void __iomem *regs = bank->eint_base;
 
-	if (clk_enable(bank->drvdata->pclk)) {
-		dev_err(bank->gpio_chip.parent,
-			"unable to enable clock for restoring state\n");
-		return;
+	if (bank->eint_type == EINT_TYPE_GPIO) {
+		save->eint_con = readl(regs + bank->pctl_offset +
+				       bank->eint_con_offset);
+		save->eint_mask = readl(regs + bank->pctl_offset +
+					bank->eint_mask_offset);
+		pr_debug("%s: save     con %#010x\n",
+			 bank->name, save->eint_con);
+		pr_debug("%s: save    mask %#010x\n",
+			 bank->name, save->eint_mask);
+	} else if (bank->eint_type == EINT_TYPE_WKUP) {
+		exynos_set_wakeup(bank);
 	}
+}
 
-	pr_debug("%s:     con %#010x => %#010x\n", bank->name,
-			readl(regs + EXYNOS_GPIO_ECON_OFFSET
-			+ bank->eint_offset), save->eint_con);
-	pr_debug("%s: fltcon0 %#010x => %#010x\n", bank->name,
-			readl(regs + EXYNOS_GPIO_EFLTCON_OFFSET
-			+ 2 * bank->eint_offset), save->eint_fltcon0);
-	pr_debug("%s: fltcon1 %#010x => %#010x\n", bank->name,
-			readl(regs + EXYNOS_GPIO_EFLTCON_OFFSET
-			+ 2 * bank->eint_offset + 4), save->eint_fltcon1);
-	pr_debug("%s:    mask %#010x => %#010x\n", bank->name,
-			readl(regs + bank->irq_chip->eint_mask
-			+ bank->eint_offset), save->eint_mask);
-
-	writel(save->eint_con, regs + EXYNOS_GPIO_ECON_OFFSET
-						+ bank->eint_offset);
-	writel(save->eint_fltcon0, regs + EXYNOS_GPIO_EFLTCON_OFFSET
-						+ 2 * bank->eint_offset);
-	writel(save->eint_fltcon1, regs + EXYNOS_GPIO_EFLTCON_OFFSET
-						+ 2 * bank->eint_offset + 4);
-	writel(save->eint_mask, regs + bank->irq_chip->eint_mask
-						+ bank->eint_offset);
+void gs101_pinctrl_resume(struct samsung_pin_bank *bank)
+{
+	struct exynos_eint_gpio_save *save = bank->soc_priv;
 
-	clk_disable(bank->drvdata->pclk);
+	void __iomem *regs = bank->eint_base;
+	void __iomem *eint_fltcfg0 = regs + EXYNOS_GPIO_EFLTCON_OFFSET
+		     + bank->eint_fltcon_offset;
+
+	if (bank->eint_type == EINT_TYPE_GPIO) {
+		pr_debug("%s:     con %#010x => %#010x\n", bank->name,
+			 readl(regs + EXYNOS_GPIO_ECON_OFFSET
+			       + bank->eint_offset), save->eint_con);
+
+		pr_debug("%s: fltcon0 %#010x => %#010x\n", bank->name,
+			 readl(eint_fltcfg0), save->eint_fltcon0);
+
+		/* fltcon1 register only exists for pins 4-7 */
+		if (bank->nr_pins > 4)
+			pr_debug("%s: fltcon1 %#010x => %#010x\n", bank->name,
+				 readl(eint_fltcfg0 + 4), save->eint_fltcon1);
+
+		pr_debug("%s:    mask %#010x => %#010x\n", bank->name,
+			 readl(regs + bank->irq_chip->eint_mask
+			       + bank->eint_offset), save->eint_mask);
+
+		writel(save->eint_con, regs + EXYNOS_GPIO_ECON_OFFSET
+		       + bank->eint_offset);
+		writel(save->eint_fltcon0, eint_fltcfg0);
+
+		if (bank->nr_pins > 4)
+			writel(save->eint_fltcon1, eint_fltcfg0 + 4);
+		writel(save->eint_mask, regs + bank->irq_chip->eint_mask
+		       + bank->eint_offset);
+	}
 }
 
-static void exynosauto_pinctrl_resume_bank(struct samsung_pinctrl_drv_data *drvdata,
-					   struct samsung_pin_bank *bank)
+void exynos_pinctrl_resume(struct samsung_pin_bank *bank)
 {
 	struct exynos_eint_gpio_save *save = bank->soc_priv;
 	void __iomem *regs = bank->eint_base;
 
-	if (clk_enable(bank->drvdata->pclk)) {
-		dev_err(bank->gpio_chip.parent,
-			"unable to enable clock for restoring state\n");
-		return;
+	if (bank->eint_type == EINT_TYPE_GPIO) {
+		pr_debug("%s:     con %#010x => %#010x\n", bank->name,
+			 readl(regs + EXYNOS_GPIO_ECON_OFFSET
+			       + bank->eint_offset), save->eint_con);
+		pr_debug("%s: fltcon0 %#010x => %#010x\n", bank->name,
+			 readl(regs + EXYNOS_GPIO_EFLTCON_OFFSET
+			       + 2 * bank->eint_offset), save->eint_fltcon0);
+		pr_debug("%s: fltcon1 %#010x => %#010x\n", bank->name,
+			 readl(regs + EXYNOS_GPIO_EFLTCON_OFFSET
+			       + 2 * bank->eint_offset + 4),
+			 save->eint_fltcon1);
+		pr_debug("%s:    mask %#010x => %#010x\n", bank->name,
+			 readl(regs + bank->irq_chip->eint_mask
+			       + bank->eint_offset), save->eint_mask);
+
+		writel(save->eint_con, regs + EXYNOS_GPIO_ECON_OFFSET
+		       + bank->eint_offset);
+		writel(save->eint_fltcon0, regs + EXYNOS_GPIO_EFLTCON_OFFSET
+		       + 2 * bank->eint_offset);
+		writel(save->eint_fltcon1, regs + EXYNOS_GPIO_EFLTCON_OFFSET
+		       + 2 * bank->eint_offset + 4);
+		writel(save->eint_mask, regs + bank->irq_chip->eint_mask
+		       + bank->eint_offset);
 	}
-
-	pr_debug("%s:     con %#010x => %#010x\n", bank->name,
-		 readl(regs + bank->pctl_offset + bank->eint_con_offset), save->eint_con);
-	pr_debug("%s:    mask %#010x => %#010x\n", bank->name,
-		 readl(regs + bank->pctl_offset + bank->eint_mask_offset), save->eint_mask);
-
-	writel(save->eint_con, regs + bank->pctl_offset + bank->eint_con_offset);
-	writel(save->eint_mask, regs + bank->pctl_offset + bank->eint_mask_offset);
-
-	clk_disable(bank->drvdata->pclk);
 }
 
-void exynos_pinctrl_resume(struct samsung_pinctrl_drv_data *drvdata)
+void exynosautov920_pinctrl_resume(struct samsung_pin_bank *bank)
 {
-	struct samsung_pin_bank *bank = drvdata->pin_banks;
-	int i;
+	struct exynos_eint_gpio_save *save = bank->soc_priv;
+	void __iomem *regs = bank->eint_base;
 
-	for (i = 0; i < drvdata->nr_banks; ++i, ++bank)
-		if (bank->eint_type == EINT_TYPE_GPIO) {
-			if (bank->eint_con_offset)
-				exynosauto_pinctrl_resume_bank(drvdata, bank);
-			else
-				exynos_pinctrl_resume_bank(drvdata, bank);
-		}
+	if (bank->eint_type == EINT_TYPE_GPIO) {
+		/* exynosautov920 has eint_con_offset for all but one bank */
+		if (!bank->eint_con_offset)
+			exynos_pinctrl_resume(bank);
+
+		pr_debug("%s:     con %#010x => %#010x\n", bank->name,
+			 readl(regs + bank->pctl_offset + bank->eint_con_offset),
+			 save->eint_con);
+		pr_debug("%s:    mask %#010x => %#010x\n", bank->name,
+			 readl(regs + bank->pctl_offset +
+			       bank->eint_mask_offset), save->eint_mask);
+
+		writel(save->eint_con,
+		       regs + bank->pctl_offset + bank->eint_con_offset);
+		writel(save->eint_mask,
+		       regs + bank->pctl_offset + bank->eint_mask_offset);
+	}
 }
 
 static void exynos_retention_enable(struct samsung_pinctrl_drv_data *drvdata)
diff --git a/drivers/pinctrl/samsung/pinctrl-exynos.h b/drivers/pinctrl/samsung/pinctrl-exynos.h
index 305cb1d31de4..c70b8ead56b4 100644
--- a/drivers/pinctrl/samsung/pinctrl-exynos.h
+++ b/drivers/pinctrl/samsung/pinctrl-exynos.h
@@ -165,6 +165,28 @@
 		.name			= id				\
 	}
 
+#define GS101_PIN_BANK_EINTG(pins, reg, id, offs, fltcon_offs) \
+	{							\
+		.type			= &exynos850_bank_type_off,	\
+		.pctl_offset		= reg,			\
+		.nr_pins		= pins,			\
+		.eint_type		= EINT_TYPE_GPIO,	\
+		.eint_offset		= offs,			\
+		.eint_fltcon_offset	= fltcon_offs,		\
+		.name			= id			\
+	}
+
+#define GS101_PIN_BANK_EINTW(pins, reg, id, offs, fltcon_offs) \
+	{								\
+		.type			= &exynos850_bank_type_alive,	\
+		.pctl_offset		= reg,				\
+		.nr_pins		= pins,				\
+		.eint_type		= EINT_TYPE_WKUP,		\
+		.eint_offset		= offs,				\
+		.eint_fltcon_offset	= fltcon_offs,			\
+		.name			= id				\
+	}
+
 /**
  * struct exynos_weint_data: irq specific data for all the wakeup interrupts
  * generated by the external wakeup interrupt controller.
@@ -189,8 +211,12 @@ struct exynos_muxed_weint_data {
 
 int exynos_eint_gpio_init(struct samsung_pinctrl_drv_data *d);
 int exynos_eint_wkup_init(struct samsung_pinctrl_drv_data *d);
-void exynos_pinctrl_suspend(struct samsung_pinctrl_drv_data *drvdata);
-void exynos_pinctrl_resume(struct samsung_pinctrl_drv_data *drvdata);
+void exynosautov920_pinctrl_resume(struct samsung_pin_bank *bank);
+void exynosautov920_pinctrl_suspend(struct samsung_pin_bank *bank);
+void exynos_pinctrl_suspend(struct samsung_pin_bank *bank);
+void exynos_pinctrl_resume(struct samsung_pin_bank *bank);
+void gs101_pinctrl_suspend(struct samsung_pin_bank *bank);
+void gs101_pinctrl_resume(struct samsung_pin_bank *bank);
 struct samsung_retention_ctrl *
 exynos_retention_init(struct samsung_pinctrl_drv_data *drvdata,
 		      const struct samsung_retention_data *data);
diff --git a/drivers/pinctrl/samsung/pinctrl-samsung.c b/drivers/pinctrl/samsung/pinctrl-samsung.c
index 675efa5d86a9..210534586c0c 100644
--- a/drivers/pinctrl/samsung/pinctrl-samsung.c
+++ b/drivers/pinctrl/samsung/pinctrl-samsung.c
@@ -1230,6 +1230,7 @@ samsung_pinctrl_get_soc_data(struct samsung_pinctrl_drv_data *d,
 		bank->eint_con_offset = bdata->eint_con_offset;
 		bank->eint_mask_offset = bdata->eint_mask_offset;
 		bank->eint_pend_offset = bdata->eint_pend_offset;
+		bank->eint_fltcon_offset = bdata->eint_fltcon_offset;
 		bank->name = bdata->name;
 
 		raw_spin_lock_init(&bank->slock);
@@ -1272,7 +1273,7 @@ static int samsung_pinctrl_probe(struct platform_device *pdev)
 
 	ret = platform_get_irq_optional(pdev, 0);
 	if (ret < 0 && ret != -ENXIO)
-		return ret;
+		goto err_put_banks;
 	if (ret > 0)
 		drvdata->irq = ret;
 
@@ -1332,6 +1333,7 @@ err_put_banks:
 static int __maybe_unused samsung_pinctrl_suspend(struct device *dev)
 {
 	struct samsung_pinctrl_drv_data *drvdata = dev_get_drvdata(dev);
+	struct samsung_pin_bank *bank;
 	int i;
 
 	i = clk_enable(drvdata->pclk);
@@ -1342,7 +1344,7 @@ static int __maybe_unused samsung_pinctrl_suspend(struct device *dev)
 	}
 
 	for (i = 0; i < drvdata->nr_banks; i++) {
-		struct samsung_pin_bank *bank = &drvdata->pin_banks[i];
+		bank = &drvdata->pin_banks[i];
 		const void __iomem *reg = bank->pctl_base + bank->pctl_offset;
 		const u8 *offs = bank->type->reg_offset;
 		const u8 *widths = bank->type->fld_width;
@@ -1370,10 +1372,14 @@ static int __maybe_unused samsung_pinctrl_suspend(struct device *dev)
 		}
 	}
 
+	for (i = 0; i < drvdata->nr_banks; i++) {
+		bank = &drvdata->pin_banks[i];
+		if (drvdata->suspend)
+			drvdata->suspend(bank);
+	}
+
 	clk_disable(drvdata->pclk);
 
-	if (drvdata->suspend)
-		drvdata->suspend(drvdata);
 	if (drvdata->retention_ctrl && drvdata->retention_ctrl->enable)
 		drvdata->retention_ctrl->enable(drvdata);
 
@@ -1391,6 +1397,7 @@ static int __maybe_unused samsung_pinctrl_suspend(struct device *dev)
 static int __maybe_unused samsung_pinctrl_resume(struct device *dev)
 {
 	struct samsung_pinctrl_drv_data *drvdata = dev_get_drvdata(dev);
+	struct samsung_pin_bank *bank;
 	int ret;
 	int i;
 
@@ -1405,11 +1412,14 @@ static int __maybe_unused samsung_pinctrl_resume(struct device *dev)
 		return ret;
 	}
 
-	if (drvdata->resume)
-		drvdata->resume(drvdata);
+	for (i = 0; i < drvdata->nr_banks; i++) {
+		bank = &drvdata->pin_banks[i];
+		if (drvdata->resume)
+			drvdata->resume(bank);
+	}
 
 	for (i = 0; i < drvdata->nr_banks; i++) {
-		struct samsung_pin_bank *bank = &drvdata->pin_banks[i];
+		bank = &drvdata->pin_banks[i];
 		void __iomem *reg = bank->pctl_base + bank->pctl_offset;
 		const u8 *offs = bank->type->reg_offset;
 		const u8 *widths = bank->type->fld_width;
diff --git a/drivers/pinctrl/samsung/pinctrl-samsung.h b/drivers/pinctrl/samsung/pinctrl-samsung.h
index a1e7377bd890..7ffd2e193e42 100644
--- a/drivers/pinctrl/samsung/pinctrl-samsung.h
+++ b/drivers/pinctrl/samsung/pinctrl-samsung.h
@@ -144,6 +144,7 @@ struct samsung_pin_bank_type {
  * @eint_con_offset: ExynosAuto SoC-specific EINT control register offset of bank.
  * @eint_mask_offset: ExynosAuto SoC-specific EINT mask register offset of bank.
  * @eint_pend_offset: ExynosAuto SoC-specific EINT pend register offset of bank.
+ * @eint_fltcon_offset: GS101 SoC-specific EINT filter config register offset.
  * @name: name to be prefixed for each pin in this pin bank.
  */
 struct samsung_pin_bank_data {
@@ -158,6 +159,7 @@ struct samsung_pin_bank_data {
 	u32		eint_con_offset;
 	u32		eint_mask_offset;
 	u32		eint_pend_offset;
+	u32		eint_fltcon_offset;
 	const char	*name;
 };
 
@@ -175,6 +177,7 @@ struct samsung_pin_bank_data {
  * @eint_con_offset: ExynosAuto SoC-specific EINT register or interrupt offset of bank.
  * @eint_mask_offset: ExynosAuto SoC-specific EINT mask register offset of bank.
  * @eint_pend_offset: ExynosAuto SoC-specific EINT pend register offset of bank.
+ * @eint_fltcon_offset: GS101 SoC-specific EINT filter config register offset.
  * @name: name to be prefixed for each pin in this pin bank.
  * @id: id of the bank, propagated to the pin range.
  * @pin_base: starting pin number of the bank.
@@ -201,6 +204,7 @@ struct samsung_pin_bank {
 	u32		eint_con_offset;
 	u32		eint_mask_offset;
 	u32		eint_pend_offset;
+	u32		eint_fltcon_offset;
 	const char	*name;
 	u32		id;
 
@@ -281,8 +285,8 @@ struct samsung_pin_ctrl {
 	int		(*eint_gpio_init)(struct samsung_pinctrl_drv_data *);
 	int		(*eint_wkup_init)(struct samsung_pinctrl_drv_data *);
 	void		(*pud_value_init)(struct samsung_pinctrl_drv_data *drvdata);
-	void		(*suspend)(struct samsung_pinctrl_drv_data *);
-	void		(*resume)(struct samsung_pinctrl_drv_data *);
+	void		(*suspend)(struct samsung_pin_bank *bank);
+	void		(*resume)(struct samsung_pin_bank *bank);
 };
 
 /**
@@ -331,8 +335,8 @@ struct samsung_pinctrl_drv_data {
 
 	struct samsung_retention_ctrl	*retention_ctrl;
 
-	void (*suspend)(struct samsung_pinctrl_drv_data *);
-	void (*resume)(struct samsung_pinctrl_drv_data *);
+	void (*suspend)(struct samsung_pin_bank *bank);
+	void (*resume)(struct samsung_pin_bank *bank);
 };
 
 /**
diff --git a/drivers/pinctrl/sophgo/pinctrl-cv18xx.c b/drivers/pinctrl/sophgo/pinctrl-cv18xx.c
index 57f2674e75d6..84b4850771ce 100644
--- a/drivers/pinctrl/sophgo/pinctrl-cv18xx.c
+++ b/drivers/pinctrl/sophgo/pinctrl-cv18xx.c
@@ -574,10 +574,10 @@ static int cv1800_pinconf_compute_config(struct cv1800_pinctrl *pctrl,
 					 struct cv1800_pin *pin,
 					 unsigned long *configs,
 					 unsigned int num_configs,
-					 u32 *value)
+					 u32 *value, u32 *mask)
 {
 	int i;
-	u32 v = 0;
+	u32 v = 0, m = 0;
 	enum cv1800_pin_io_type type;
 	int ret;
 
@@ -596,10 +596,12 @@ static int cv1800_pinconf_compute_config(struct cv1800_pinctrl *pctrl,
 		case PIN_CONFIG_BIAS_PULL_DOWN:
 			v &= ~PIN_IO_PULLDOWN;
 			v |= FIELD_PREP(PIN_IO_PULLDOWN, arg);
+			m |= PIN_IO_PULLDOWN;
 			break;
 		case PIN_CONFIG_BIAS_PULL_UP:
 			v &= ~PIN_IO_PULLUP;
 			v |= FIELD_PREP(PIN_IO_PULLUP, arg);
+			m |= PIN_IO_PULLUP;
 			break;
 		case PIN_CONFIG_DRIVE_STRENGTH_UA:
 			ret = cv1800_pinctrl_oc2reg(pctrl, pin, arg);
@@ -607,6 +609,7 @@ static int cv1800_pinconf_compute_config(struct cv1800_pinctrl *pctrl,
 				return ret;
 			v &= ~PIN_IO_DRIVE;
 			v |= FIELD_PREP(PIN_IO_DRIVE, ret);
+			m |= PIN_IO_DRIVE;
 			break;
 		case PIN_CONFIG_INPUT_SCHMITT_UV:
 			ret = cv1800_pinctrl_schmitt2reg(pctrl, pin, arg);
@@ -614,6 +617,7 @@ static int cv1800_pinconf_compute_config(struct cv1800_pinctrl *pctrl,
 				return ret;
 			v &= ~PIN_IO_SCHMITT;
 			v |= FIELD_PREP(PIN_IO_SCHMITT, ret);
+			m |= PIN_IO_SCHMITT;
 			break;
 		case PIN_CONFIG_POWER_SOURCE:
 			/* Ignore power source as it is always fixed */
@@ -621,10 +625,12 @@ static int cv1800_pinconf_compute_config(struct cv1800_pinctrl *pctrl,
 		case PIN_CONFIG_SLEW_RATE:
 			v &= ~PIN_IO_OUT_FAST_SLEW;
 			v |= FIELD_PREP(PIN_IO_OUT_FAST_SLEW, arg);
+			m |= PIN_IO_OUT_FAST_SLEW;
 			break;
 		case PIN_CONFIG_BIAS_BUS_HOLD:
 			v &= ~PIN_IO_BUS_HOLD;
 			v |= FIELD_PREP(PIN_IO_BUS_HOLD, arg);
+			m |= PIN_IO_BUS_HOLD;
 			break;
 		default:
 			return -ENOTSUPP;
@@ -632,17 +638,19 @@ static int cv1800_pinconf_compute_config(struct cv1800_pinctrl *pctrl,
 	}
 
 	*value = v;
+	*mask = m;
 
 	return 0;
 }
 
 static int cv1800_pin_set_config(struct cv1800_pinctrl *pctrl,
 				 unsigned int pin_id,
-				 u32 value)
+				 u32 value, u32 mask)
 {
 	struct cv1800_pin *pin = cv1800_get_pin(pctrl, pin_id);
 	unsigned long flags;
 	void __iomem *addr;
+	u32 reg;
 
 	if (!pin)
 		return -EINVAL;
@@ -650,7 +658,10 @@ static int cv1800_pin_set_config(struct cv1800_pinctrl *pctrl,
 	addr = cv1800_pinctrl_get_component_addr(pctrl, &pin->conf);
 
 	raw_spin_lock_irqsave(&pctrl->lock, flags);
-	writel(value, addr);
+	reg = readl(addr);
+	reg &= ~mask;
+	reg |= value;
+	writel(reg, addr);
 	raw_spin_unlock_irqrestore(&pctrl->lock, flags);
 
 	return 0;
@@ -662,16 +673,17 @@ static int cv1800_pconf_set(struct pinctrl_dev *pctldev,
 {
 	struct cv1800_pinctrl *pctrl = pinctrl_dev_get_drvdata(pctldev);
 	struct cv1800_pin *pin = cv1800_get_pin(pctrl, pin_id);
-	u32 value;
+	u32 value, mask;
 
 	if (!pin)
 		return -ENODEV;
 
 	if (cv1800_pinconf_compute_config(pctrl, pin,
-					  configs, num_configs, &value))
+					  configs, num_configs,
+					  &value, &mask))
 		return -ENOTSUPP;
 
-	return cv1800_pin_set_config(pctrl, pin_id, value);
+	return cv1800_pin_set_config(pctrl, pin_id, value, mask);
 }
 
 static int cv1800_pconf_group_set(struct pinctrl_dev *pctldev,
@@ -682,7 +694,7 @@ static int cv1800_pconf_group_set(struct pinctrl_dev *pctldev,
 	struct cv1800_pinctrl *pctrl = pinctrl_dev_get_drvdata(pctldev);
 	const struct group_desc *group;
 	const struct cv1800_pin_mux_config *pinmuxs;
-	u32 value;
+	u32 value, mask;
 	int i;
 
 	group = pinctrl_generic_get_group(pctldev, gsel);
@@ -692,11 +704,12 @@ static int cv1800_pconf_group_set(struct pinctrl_dev *pctldev,
 	pinmuxs = group->data;
 
 	if (cv1800_pinconf_compute_config(pctrl, pinmuxs[0].pin,
-					  configs, num_configs, &value))
+					  configs, num_configs,
+					  &value, &mask))
 		return -ENOTSUPP;
 
 	for (i = 0; i < group->grp.npins; i++)
-		cv1800_pin_set_config(pctrl, group->grp.pins[i], value);
+		cv1800_pin_set_config(pctrl, group->grp.pins[i], value, mask);
 
 	return 0;
 }
diff --git a/drivers/pinctrl/stm32/pinctrl-stm32.c b/drivers/pinctrl/stm32/pinctrl-stm32.c
index 5b7fa77c1184..2659a854a514 100644
--- a/drivers/pinctrl/stm32/pinctrl-stm32.c
+++ b/drivers/pinctrl/stm32/pinctrl-stm32.c
@@ -86,7 +86,6 @@ struct stm32_pinctrl_group {
 
 struct stm32_gpio_bank {
 	void __iomem *base;
-	struct clk *clk;
 	struct reset_control *rstc;
 	spinlock_t lock;
 	struct gpio_chip gpio_chip;
@@ -108,6 +107,7 @@ struct stm32_pinctrl {
 	unsigned ngroups;
 	const char **grp_names;
 	struct stm32_gpio_bank *banks;
+	struct clk_bulk_data *clks;
 	unsigned nbanks;
 	const struct stm32_pinctrl_match_data *match_data;
 	struct irq_domain	*domain;
@@ -407,6 +407,7 @@ static struct irq_chip stm32_gpio_irq_chip = {
 	.irq_set_wake	= irq_chip_set_wake_parent,
 	.irq_request_resources = stm32_gpio_irq_request_resources,
 	.irq_release_resources = stm32_gpio_irq_release_resources,
+	.irq_set_affinity = IS_ENABLED(CONFIG_SMP) ? irq_chip_set_affinity_parent : NULL,
 };
 
 static int stm32_gpio_domain_translate(struct irq_domain *d,
@@ -1308,12 +1309,6 @@ static int stm32_gpiolib_register_bank(struct stm32_pinctrl *pctl, struct fwnode
 	if (IS_ERR(bank->base))
 		return PTR_ERR(bank->base);
 
-	err = clk_prepare_enable(bank->clk);
-	if (err) {
-		dev_err(dev, "failed to prepare_enable clk (%d)\n", err);
-		return err;
-	}
-
 	bank->gpio_chip = stm32_gpio_template;
 
 	fwnode_property_read_string(fwnode, "st,bank-name", &bank->gpio_chip.label);
@@ -1360,26 +1355,20 @@ static int stm32_gpiolib_register_bank(struct stm32_pinctrl *pctl, struct fwnode
 							   bank->fwnode, &stm32_gpio_domain_ops,
 							   bank);
 
-		if (!bank->domain) {
-			err = -ENODEV;
-			goto err_clk;
-		}
+		if (!bank->domain)
+			return -ENODEV;
 	}
 
 	names = devm_kcalloc(dev, npins, sizeof(char *), GFP_KERNEL);
-	if (!names) {
-		err = -ENOMEM;
-		goto err_clk;
-	}
+	if (!names)
+		return -ENOMEM;
 
 	for (i = 0; i < npins; i++) {
 		stm32_pin = stm32_pctrl_get_desc_pin_from_gpio(pctl, bank, i);
 		if (stm32_pin && stm32_pin->pin.name) {
 			names[i] = devm_kasprintf(dev, GFP_KERNEL, "%s", stm32_pin->pin.name);
-			if (!names[i]) {
-				err = -ENOMEM;
-				goto err_clk;
-			}
+			if (!names[i])
+				return -ENOMEM;
 		} else {
 			names[i] = NULL;
 		}
@@ -1390,15 +1379,11 @@ static int stm32_gpiolib_register_bank(struct stm32_pinctrl *pctl, struct fwnode
 	err = gpiochip_add_data(&bank->gpio_chip, bank);
 	if (err) {
 		dev_err(dev, "Failed to add gpiochip(%d)!\n", bank_nr);
-		goto err_clk;
+		return err;
 	}
 
 	dev_info(dev, "%s bank added\n", bank->gpio_chip.label);
 	return 0;
-
-err_clk:
-	clk_disable_unprepare(bank->clk);
-	return err;
 }
 
 static struct irq_domain *stm32_pctrl_get_irq_domain(struct platform_device *pdev)
@@ -1621,6 +1606,11 @@ int stm32_pctl_probe(struct platform_device *pdev)
 	if (!pctl->banks)
 		return -ENOMEM;
 
+	pctl->clks = devm_kcalloc(dev, banks, sizeof(*pctl->clks),
+				  GFP_KERNEL);
+	if (!pctl->clks)
+		return -ENOMEM;
+
 	i = 0;
 	for_each_gpiochip_node(dev, child) {
 		struct stm32_gpio_bank *bank = &pctl->banks[i];
@@ -1632,24 +1622,27 @@ int stm32_pctl_probe(struct platform_device *pdev)
 			return -EPROBE_DEFER;
 		}
 
-		bank->clk = of_clk_get_by_name(np, NULL);
-		if (IS_ERR(bank->clk)) {
+		pctl->clks[i].clk = of_clk_get_by_name(np, NULL);
+		if (IS_ERR(pctl->clks[i].clk)) {
 			fwnode_handle_put(child);
-			return dev_err_probe(dev, PTR_ERR(bank->clk),
+			return dev_err_probe(dev, PTR_ERR(pctl->clks[i].clk),
 					     "failed to get clk\n");
 		}
+		pctl->clks[i].id = "pctl";
 		i++;
 	}
 
+	ret = clk_bulk_prepare_enable(banks, pctl->clks);
+	if (ret) {
+		dev_err(dev, "failed to prepare_enable clk (%d)\n", ret);
+		return ret;
+	}
+
 	for_each_gpiochip_node(dev, child) {
 		ret = stm32_gpiolib_register_bank(pctl, child);
 		if (ret) {
 			fwnode_handle_put(child);
-
-			for (i = 0; i < pctl->nbanks; i++)
-				clk_disable_unprepare(pctl->banks[i].clk);
-
-			return ret;
+			goto err_register;
 		}
 
 		pctl->nbanks++;
@@ -1658,6 +1651,15 @@ int stm32_pctl_probe(struct platform_device *pdev)
 	dev_info(dev, "Pinctrl STM32 initialized\n");
 
 	return 0;
+err_register:
+	for (i = 0; i < pctl->nbanks; i++) {
+		struct stm32_gpio_bank *bank = &pctl->banks[i];
+
+		gpiochip_remove(&bank->gpio_chip);
+	}
+
+	clk_bulk_disable_unprepare(banks, pctl->clks);
+	return ret;
 }
 
 static int __maybe_unused stm32_pinctrl_restore_gpio_regs(
@@ -1726,10 +1728,8 @@ static int __maybe_unused stm32_pinctrl_restore_gpio_regs(
 int __maybe_unused stm32_pinctrl_suspend(struct device *dev)
 {
 	struct stm32_pinctrl *pctl = dev_get_drvdata(dev);
-	int i;
 
-	for (i = 0; i < pctl->nbanks; i++)
-		clk_disable(pctl->banks[i].clk);
+	clk_bulk_disable(pctl->nbanks, pctl->clks);
 
 	return 0;
 }
@@ -1738,10 +1738,11 @@ int __maybe_unused stm32_pinctrl_resume(struct device *dev)
 {
 	struct stm32_pinctrl *pctl = dev_get_drvdata(dev);
 	struct stm32_pinctrl_group *g = pctl->groups;
-	int i;
+	int i, ret;
 
-	for (i = 0; i < pctl->nbanks; i++)
-		clk_enable(pctl->banks[i].clk);
+	ret = clk_bulk_enable(pctl->nbanks, pctl->clks);
+	if (ret)
+		return ret;
 
 	for (i = 0; i < pctl->ngroups; i++, g++)
 		stm32_pinctrl_restore_gpio_regs(pctl, g->pin);
diff --git a/drivers/pinctrl/sunxi/pinctrl-sunxi.c b/drivers/pinctrl/sunxi/pinctrl-sunxi.c
index bde67ee31417..8fbbdcc52deb 100644
--- a/drivers/pinctrl/sunxi/pinctrl-sunxi.c
+++ b/drivers/pinctrl/sunxi/pinctrl-sunxi.c
@@ -395,6 +395,7 @@ static int sunxi_pctrl_dt_node_to_map(struct pinctrl_dev *pctldev,
 	const char *function, *pin_prop;
 	const char *group;
 	int ret, npins, nmaps, configlen = 0, i = 0;
+	struct pinctrl_map *new_map;
 
 	*map = NULL;
 	*num_maps = 0;
@@ -469,9 +470,13 @@ static int sunxi_pctrl_dt_node_to_map(struct pinctrl_dev *pctldev,
 	 * We know have the number of maps we need, we can resize our
 	 * map array
 	 */
-	*map = krealloc(*map, i * sizeof(struct pinctrl_map), GFP_KERNEL);
-	if (!*map)
-		return -ENOMEM;
+	new_map = krealloc(*map, i * sizeof(struct pinctrl_map), GFP_KERNEL);
+	if (!new_map) {
+		ret = -ENOMEM;
+		goto err_free_map;
+	}
+
+	*map = new_map;
 
 	return 0;
 
diff --git a/drivers/pinctrl/tegra/pinctrl-tegra.c b/drivers/pinctrl/tegra/pinctrl-tegra.c
index c83e5a65e680..edcc78ebce45 100644
--- a/drivers/pinctrl/tegra/pinctrl-tegra.c
+++ b/drivers/pinctrl/tegra/pinctrl-tegra.c
@@ -270,13 +270,16 @@ static int tegra_pinctrl_set_mux(struct pinctrl_dev *pctldev,
 	val = pmx_readl(pmx, g->mux_bank, g->mux_reg);
 	val &= ~(0x3 << g->mux_bit);
 	val |= i << g->mux_bit;
+	/* Set the SFIO/GPIO selection to SFIO when under pinmux control*/
+	if (pmx->soc->sfsel_in_mux)
+		val |= (1 << g->sfsel_bit);
 	pmx_writel(pmx, val, g->mux_bank, g->mux_reg);
 
 	return 0;
 }
 
-static const struct tegra_pingroup *tegra_pinctrl_get_group(struct pinctrl_dev *pctldev,
-					unsigned int offset)
+static int tegra_pinctrl_get_group_index(struct pinctrl_dev *pctldev,
+					 unsigned int offset)
 {
 	struct tegra_pmx *pmx = pinctrl_dev_get_drvdata(pctldev);
 	unsigned int group, num_pins, j;
@@ -289,12 +292,35 @@ static const struct tegra_pingroup *tegra_pinctrl_get_group(struct pinctrl_dev *
 			continue;
 		for (j = 0; j < num_pins; j++) {
 			if (offset == pins[j])
-				return &pmx->soc->groups[group];
+				return group;
 		}
 	}
 
-	dev_err(pctldev->dev, "Pingroup not found for pin %u\n", offset);
-	return NULL;
+	return -EINVAL;
+}
+
+static const struct tegra_pingroup *tegra_pinctrl_get_group(struct pinctrl_dev *pctldev,
+							    unsigned int offset,
+							    int group_index)
+{
+	struct tegra_pmx *pmx = pinctrl_dev_get_drvdata(pctldev);
+
+	if (group_index < 0 || group_index >= pmx->soc->ngroups)
+		return NULL;
+
+	return &pmx->soc->groups[group_index];
+}
+
+static struct tegra_pingroup_config *tegra_pinctrl_get_group_config(struct pinctrl_dev *pctldev,
+								    unsigned int offset,
+								    int group_index)
+{
+	struct tegra_pmx *pmx = pinctrl_dev_get_drvdata(pctldev);
+
+	if (group_index < 0)
+		return NULL;
+
+	return &pmx->pingroup_configs[group_index];
 }
 
 static int tegra_pinctrl_gpio_request_enable(struct pinctrl_dev *pctldev,
@@ -303,12 +329,15 @@ static int tegra_pinctrl_gpio_request_enable(struct pinctrl_dev *pctldev,
 {
 	struct tegra_pmx *pmx = pinctrl_dev_get_drvdata(pctldev);
 	const struct tegra_pingroup *group;
+	struct tegra_pingroup_config *config;
+	int group_index;
 	u32 value;
 
 	if (!pmx->soc->sfsel_in_mux)
 		return 0;
 
-	group = tegra_pinctrl_get_group(pctldev, offset);
+	group_index = tegra_pinctrl_get_group_index(pctldev, offset);
+	group = tegra_pinctrl_get_group(pctldev, offset, group_index);
 
 	if (!group)
 		return -EINVAL;
@@ -316,7 +345,11 @@ static int tegra_pinctrl_gpio_request_enable(struct pinctrl_dev *pctldev,
 	if (group->mux_reg < 0 || group->sfsel_bit < 0)
 		return -EINVAL;
 
+	config = tegra_pinctrl_get_group_config(pctldev, offset, group_index);
+	if (!config)
+		return -EINVAL;
 	value = pmx_readl(pmx, group->mux_bank, group->mux_reg);
+	config->is_sfsel = (value & BIT(group->sfsel_bit)) != 0;
 	value &= ~BIT(group->sfsel_bit);
 	pmx_writel(pmx, value, group->mux_bank, group->mux_reg);
 
@@ -329,12 +362,15 @@ static void tegra_pinctrl_gpio_disable_free(struct pinctrl_dev *pctldev,
 {
 	struct tegra_pmx *pmx = pinctrl_dev_get_drvdata(pctldev);
 	const struct tegra_pingroup *group;
+	struct tegra_pingroup_config *config;
+	int group_index;
 	u32 value;
 
 	if (!pmx->soc->sfsel_in_mux)
 		return;
 
-	group = tegra_pinctrl_get_group(pctldev, offset);
+	group_index = tegra_pinctrl_get_group_index(pctldev, offset);
+	group = tegra_pinctrl_get_group(pctldev, offset, group_index);
 
 	if (!group)
 		return;
@@ -342,8 +378,12 @@ static void tegra_pinctrl_gpio_disable_free(struct pinctrl_dev *pctldev,
 	if (group->mux_reg < 0 || group->sfsel_bit < 0)
 		return;
 
+	config = tegra_pinctrl_get_group_config(pctldev, offset, group_index);
+	if (!config)
+		return;
 	value = pmx_readl(pmx, group->mux_bank, group->mux_reg);
-	value |= BIT(group->sfsel_bit);
+	if (config->is_sfsel)
+		value |= BIT(group->sfsel_bit);
 	pmx_writel(pmx, value, group->mux_bank, group->mux_reg);
 }
 
@@ -788,6 +828,12 @@ int tegra_pinctrl_probe(struct platform_device *pdev,
 	pmx->dev = &pdev->dev;
 	pmx->soc = soc_data;
 
+	pmx->pingroup_configs = devm_kcalloc(&pdev->dev,
+					     pmx->soc->ngroups, sizeof(*pmx->pingroup_configs),
+					     GFP_KERNEL);
+	if (!pmx->pingroup_configs)
+		return -ENOMEM;
+
 	/*
 	 * Each mux group will appear in 4 functions' list of groups.
 	 * This over-allocates slightly, since not all groups are mux groups.
diff --git a/drivers/pinctrl/tegra/pinctrl-tegra.h b/drivers/pinctrl/tegra/pinctrl-tegra.h
index b3289bdf727d..b97136685f7a 100644
--- a/drivers/pinctrl/tegra/pinctrl-tegra.h
+++ b/drivers/pinctrl/tegra/pinctrl-tegra.h
@@ -8,6 +8,10 @@
 #ifndef __PINMUX_TEGRA_H__
 #define __PINMUX_TEGRA_H__
 
+struct tegra_pingroup_config {
+	bool is_sfsel;
+};
+
 struct tegra_pmx {
 	struct device *dev;
 	struct pinctrl_dev *pctl;
@@ -21,6 +25,8 @@ struct tegra_pmx {
 	int nbanks;
 	void __iomem **regs;
 	u32 *backup_regs;
+	/* Array of size soc->ngroups */
+	struct tegra_pingroup_config *pingroup_configs;
 };
 
 enum tegra_pinconf_param {
diff --git a/drivers/platform/chrome/cros_ec_lpc.c b/drivers/platform/chrome/cros_ec_lpc.c
index 626e2635e3da..ac198d1fd170 100644
--- a/drivers/platform/chrome/cros_ec_lpc.c
+++ b/drivers/platform/chrome/cros_ec_lpc.c
@@ -30,6 +30,7 @@
 
 #define DRV_NAME "cros_ec_lpcs"
 #define ACPI_DRV_NAME "GOOG0004"
+#define FRMW_ACPI_DRV_NAME "FRMWC004"
 
 /* True if ACPI device is present */
 static bool cros_ec_lpc_acpi_device_found;
@@ -460,7 +461,7 @@ static int cros_ec_lpc_probe(struct platform_device *pdev)
 	acpi_status status;
 	struct cros_ec_device *ec_dev;
 	struct cros_ec_lpc *ec_lpc;
-	struct lpc_driver_data *driver_data;
+	const struct lpc_driver_data *driver_data;
 	u8 buf[2] = {};
 	int irq, ret;
 	u32 quirks;
@@ -472,6 +473,9 @@ static int cros_ec_lpc_probe(struct platform_device *pdev)
 	ec_lpc->mmio_memory_base = EC_LPC_ADDR_MEMMAP;
 
 	driver_data = platform_get_drvdata(pdev);
+	if (!driver_data)
+		driver_data = acpi_device_get_match_data(dev);
+
 	if (driver_data) {
 		quirks = driver_data->quirks;
 
@@ -625,12 +629,6 @@ static void cros_ec_lpc_remove(struct platform_device *pdev)
 	cros_ec_unregister(ec_dev);
 }
 
-static const struct acpi_device_id cros_ec_lpc_acpi_device_ids[] = {
-	{ ACPI_DRV_NAME, 0 },
-	{ }
-};
-MODULE_DEVICE_TABLE(acpi, cros_ec_lpc_acpi_device_ids);
-
 static const struct lpc_driver_data framework_laptop_npcx_lpc_driver_data __initconst = {
 	.quirks = CROS_EC_LPC_QUIRK_REMAP_MEMORY,
 	.quirk_mmio_memory_base = 0xE00,
@@ -642,6 +640,13 @@ static const struct lpc_driver_data framework_laptop_mec_lpc_driver_data __initc
 	.quirk_aml_mutex_name = "ECMT",
 };
 
+static const struct acpi_device_id cros_ec_lpc_acpi_device_ids[] = {
+	{ ACPI_DRV_NAME, 0 },
+	{ FRMW_ACPI_DRV_NAME, (kernel_ulong_t)&framework_laptop_npcx_lpc_driver_data },
+	{ }
+};
+MODULE_DEVICE_TABLE(acpi, cros_ec_lpc_acpi_device_ids);
+
 static const struct dmi_system_id cros_ec_lpc_dmi_table[] __initconst = {
 	{
 		/*
@@ -795,7 +800,8 @@ static int __init cros_ec_lpc_init(void)
 	int ret;
 	const struct dmi_system_id *dmi_match;
 
-	cros_ec_lpc_acpi_device_found = !!cros_ec_lpc_get_device(ACPI_DRV_NAME);
+	cros_ec_lpc_acpi_device_found = !!cros_ec_lpc_get_device(ACPI_DRV_NAME) ||
+		!!cros_ec_lpc_get_device(FRMW_ACPI_DRV_NAME);
 
 	dmi_match = dmi_first_match(cros_ec_lpc_dmi_table);
 
diff --git a/drivers/platform/chrome/cros_ec_sensorhub.c b/drivers/platform/chrome/cros_ec_sensorhub.c
index 50cdae67fa32..9bad8f72680e 100644
--- a/drivers/platform/chrome/cros_ec_sensorhub.c
+++ b/drivers/platform/chrome/cros_ec_sensorhub.c
@@ -8,6 +8,7 @@
 
 #include <linux/init.h>
 #include <linux/device.h>
+#include <linux/delay.h>
 #include <linux/mod_devicetable.h>
 #include <linux/module.h>
 #include <linux/platform_data/cros_ec_commands.h>
@@ -18,6 +19,7 @@
 #include <linux/types.h>
 
 #define DRV_NAME		"cros-ec-sensorhub"
+#define CROS_EC_CMD_INFO_RETRIES 50
 
 static void cros_ec_sensorhub_free_sensor(void *arg)
 {
@@ -53,7 +55,7 @@ static int cros_ec_sensorhub_register(struct device *dev,
 	int sensor_type[MOTIONSENSE_TYPE_MAX] = { 0 };
 	struct cros_ec_command *msg = sensorhub->msg;
 	struct cros_ec_dev *ec = sensorhub->ec;
-	int ret, i;
+	int ret, i, retries;
 	char *name;
 
 
@@ -65,12 +67,25 @@ static int cros_ec_sensorhub_register(struct device *dev,
 		sensorhub->params->cmd = MOTIONSENSE_CMD_INFO;
 		sensorhub->params->info.sensor_num = i;
 
-		ret = cros_ec_cmd_xfer_status(ec->ec_dev, msg);
+		retries = CROS_EC_CMD_INFO_RETRIES;
+		do {
+			ret = cros_ec_cmd_xfer_status(ec->ec_dev, msg);
+			if (ret == -EBUSY) {
+				/* The EC is still busy initializing sensors. */
+				usleep_range(5000, 6000);
+				retries--;
+			}
+		} while (ret == -EBUSY && retries);
+
 		if (ret < 0) {
-			dev_warn(dev, "no info for EC sensor %d : %d/%d\n",
-				 i, ret, msg->result);
+			dev_err(dev, "no info for EC sensor %d : %d/%d\n",
+				i, ret, msg->result);
 			continue;
 		}
+		if (retries < CROS_EC_CMD_INFO_RETRIES) {
+			dev_warn(dev, "%d retries needed to bring up sensor %d\n",
+				 CROS_EC_CMD_INFO_RETRIES - retries, i);
+		}
 
 		switch (sensorhub->resp->info.type) {
 		case MOTIONSENSE_TYPE_ACCEL:
diff --git a/drivers/platform/chrome/cros_ec_typec.c b/drivers/platform/chrome/cros_ec_typec.c
index f1324466efac..ca665b901010 100644
--- a/drivers/platform/chrome/cros_ec_typec.c
+++ b/drivers/platform/chrome/cros_ec_typec.c
@@ -1226,8 +1226,8 @@ static int cros_typec_probe(struct platform_device *pdev)
 
 	typec->ec = dev_get_drvdata(pdev->dev.parent);
 	if (!typec->ec) {
-		dev_err(dev, "couldn't find parent EC device\n");
-		return -ENODEV;
+		dev_warn(dev, "couldn't find parent EC device\n");
+		return -EPROBE_DEFER;
 	}
 
 	platform_set_drvdata(pdev, typec);
diff --git a/drivers/platform/cznic/Kconfig b/drivers/platform/cznic/Kconfig
index 49c383eb6785..13e37b49d9d0 100644
--- a/drivers/platform/cznic/Kconfig
+++ b/drivers/platform/cznic/Kconfig
@@ -6,6 +6,7 @@
 
 menuconfig CZNIC_PLATFORMS
 	bool "Platform support for CZ.NIC's Turris hardware"
+	depends on ARCH_MVEBU || COMPILE_TEST
 	help
 	  Say Y here to be able to choose driver support for CZ.NIC's Turris
 	  devices. This option alone does not add any kernel code.
diff --git a/drivers/platform/loongarch/loongson-laptop.c b/drivers/platform/loongarch/loongson-laptop.c
index 99203584949d..61b18ac206c9 100644
--- a/drivers/platform/loongarch/loongson-laptop.c
+++ b/drivers/platform/loongarch/loongson-laptop.c
@@ -56,8 +56,7 @@ static struct input_dev *generic_inputdev;
 static acpi_handle hotkey_handle;
 static struct key_entry hotkey_keycode_map[GENERIC_HOTKEY_MAP_MAX];
 
-int loongson_laptop_turn_on_backlight(void);
-int loongson_laptop_turn_off_backlight(void);
+static bool bl_powered;
 static int loongson_laptop_backlight_update(struct backlight_device *bd);
 
 /* 2. ACPI Helpers and device model */
@@ -354,16 +353,42 @@ static int ec_backlight_level(u8 level)
 	return level;
 }
 
+static int ec_backlight_set_power(bool state)
+{
+	int status;
+	union acpi_object arg0 = { ACPI_TYPE_INTEGER };
+	struct acpi_object_list args = { 1, &arg0 };
+
+	arg0.integer.value = state;
+	status = acpi_evaluate_object(NULL, "\\BLSW", &args, NULL);
+	if (ACPI_FAILURE(status)) {
+		pr_info("Loongson lvds error: 0x%x\n", status);
+		return -EIO;
+	}
+
+	return 0;
+}
+
 static int loongson_laptop_backlight_update(struct backlight_device *bd)
 {
-	int lvl = ec_backlight_level(bd->props.brightness);
+	bool target_powered = !backlight_is_blank(bd);
+	int ret = 0, lvl = ec_backlight_level(bd->props.brightness);
 
 	if (lvl < 0)
 		return -EIO;
+
 	if (ec_set_brightness(lvl))
 		return -EIO;
 
-	return 0;
+	if (target_powered != bl_powered) {
+		ret = ec_backlight_set_power(target_powered);
+		if (ret < 0)
+			return ret;
+
+		bl_powered = target_powered;
+	}
+
+	return ret;
 }
 
 static int loongson_laptop_get_brightness(struct backlight_device *bd)
@@ -384,7 +409,7 @@ static const struct backlight_ops backlight_laptop_ops = {
 
 static int laptop_backlight_register(void)
 {
-	int status = 0;
+	int status = 0, ret;
 	struct backlight_properties props;
 
 	memset(&props, 0, sizeof(props));
@@ -392,44 +417,20 @@ static int laptop_backlight_register(void)
 	if (!acpi_evalf(hotkey_handle, &status, "ECLL", "d"))
 		return -EIO;
 
-	props.brightness = 1;
+	ret = ec_backlight_set_power(true);
+	if (ret)
+		return ret;
+
+	bl_powered = true;
+
 	props.max_brightness = status;
+	props.brightness = ec_get_brightness();
+	props.power = BACKLIGHT_POWER_ON;
 	props.type = BACKLIGHT_PLATFORM;
 
 	backlight_device_register("loongson_laptop",
 				NULL, NULL, &backlight_laptop_ops, &props);
 
-	return 0;
-}
-
-int loongson_laptop_turn_on_backlight(void)
-{
-	int status;
-	union acpi_object arg0 = { ACPI_TYPE_INTEGER };
-	struct acpi_object_list args = { 1, &arg0 };
-
-	arg0.integer.value = 1;
-	status = acpi_evaluate_object(NULL, "\\BLSW", &args, NULL);
-	if (ACPI_FAILURE(status)) {
-		pr_info("Loongson lvds error: 0x%x\n", status);
-		return -ENODEV;
-	}
-
-	return 0;
-}
-
-int loongson_laptop_turn_off_backlight(void)
-{
-	int status;
-	union acpi_object arg0 = { ACPI_TYPE_INTEGER };
-	struct acpi_object_list args = { 1, &arg0 };
-
-	arg0.integer.value = 0;
-	status = acpi_evaluate_object(NULL, "\\BLSW", &args, NULL);
-	if (ACPI_FAILURE(status)) {
-		pr_info("Loongson lvds error: 0x%x\n", status);
-		return -ENODEV;
-	}
 
 	return 0;
 }
@@ -611,11 +612,17 @@ static int __init generic_acpi_laptop_init(void)
 
 static void __exit generic_acpi_laptop_exit(void)
 {
+	int i;
+
 	if (generic_inputdev) {
-		if (input_device_registered)
-			input_unregister_device(generic_inputdev);
-		else
+		if (!input_device_registered) {
 			input_free_device(generic_inputdev);
+		} else {
+			input_unregister_device(generic_inputdev);
+
+			for (i = 0; i < ARRAY_SIZE(generic_sub_drivers); i++)
+				generic_subdriver_exit(&generic_sub_drivers[i]);
+		}
 	}
 }
 
diff --git a/drivers/platform/mellanox/mlxbf-pmc.c b/drivers/platform/mellanox/mlxbf-pmc.c
index 9d18dfca6a67..9a0220b4de3c 100644
--- a/drivers/platform/mellanox/mlxbf-pmc.c
+++ b/drivers/platform/mellanox/mlxbf-pmc.c
@@ -15,6 +15,7 @@
 #include <linux/hwmon.h>
 #include <linux/platform_device.h>
 #include <linux/string.h>
+#include <linux/string_helpers.h>
 #include <uapi/linux/psci.h>
 
 #define MLXBF_PMC_WRITE_REG_32 0x82000009
@@ -710,7 +711,7 @@ static const struct mlxbf_pmc_events mlxbf_pmc_llt_events[] = {
 	{101, "GDC_BANK0_HIT_DCL_PARTIAL"},
 	{102, "GDC_BANK0_EVICT_DCL"},
 	{103, "GDC_BANK0_G_RSE_PIPE_CACHE_DATA0"},
-	{103, "GDC_BANK0_G_RSE_PIPE_CACHE_DATA1"},
+	{104, "GDC_BANK0_G_RSE_PIPE_CACHE_DATA1"},
 	{105, "GDC_BANK0_ARB_STRB"},
 	{106, "GDC_BANK0_ARB_WAIT"},
 	{107, "GDC_BANK0_GGA_STRB"},
@@ -1067,7 +1068,7 @@ static int mlxbf_pmc_get_event_num(const char *blk, const char *evt)
 	return -ENODEV;
 }
 
-/* Get the event number given the name */
+/* Get the event name given the number */
 static char *mlxbf_pmc_get_event_name(const char *blk, u32 evt)
 {
 	const struct mlxbf_pmc_events *events;
@@ -1168,7 +1169,7 @@ static int mlxbf_pmc_program_l3_counter(unsigned int blk_num, u32 cnt_num, u32 e
 /* Method to handle crspace counter programming */
 static int mlxbf_pmc_program_crspace_counter(unsigned int blk_num, u32 cnt_num, u32 evt)
 {
-	void *addr;
+	void __iomem *addr;
 	u32 word;
 	int ret;
 
@@ -1192,7 +1193,7 @@ static int mlxbf_pmc_program_crspace_counter(unsigned int blk_num, u32 cnt_num,
 /* Method to clear crspace counter value */
 static int mlxbf_pmc_clear_crspace_counter(unsigned int blk_num, u32 cnt_num)
 {
-	void *addr;
+	void __iomem *addr;
 
 	addr = pmc->block[blk_num].mmio_base +
 		MLXBF_PMC_CRSPACE_PERFMON_VAL0(pmc->block[blk_num].counters) +
@@ -1405,7 +1406,7 @@ static int mlxbf_pmc_read_l3_event(unsigned int blk_num, u32 cnt_num, u64 *resul
 static int mlxbf_pmc_read_crspace_event(unsigned int blk_num, u32 cnt_num, u64 *result)
 {
 	u32 word, evt;
-	void *addr;
+	void __iomem *addr;
 	int ret;
 
 	addr = pmc->block[blk_num].mmio_base +
@@ -1625,6 +1626,7 @@ static ssize_t mlxbf_pmc_event_store(struct device *dev,
 		attr, struct mlxbf_pmc_attribute, dev_attr);
 	unsigned int blk_num, cnt_num;
 	bool is_l3 = false;
+	char *evt_name;
 	int evt_num;
 	int err;
 
@@ -1632,14 +1634,23 @@ static ssize_t mlxbf_pmc_event_store(struct device *dev,
 	cnt_num = attr_event->index;
 
 	if (isalpha(buf[0])) {
+		/* Remove the trailing newline character if present */
+		evt_name = kstrdup_and_replace(buf, '\n', '\0', GFP_KERNEL);
+		if (!evt_name)
+			return -ENOMEM;
+
 		evt_num = mlxbf_pmc_get_event_num(pmc->block_name[blk_num],
-						  buf);
+						  evt_name);
+		kfree(evt_name);
 		if (evt_num < 0)
 			return -EINVAL;
 	} else {
 		err = kstrtouint(buf, 0, &evt_num);
 		if (err < 0)
 			return err;
+
+		if (!mlxbf_pmc_get_event_name(pmc->block_name[blk_num], evt_num))
+			return -EINVAL;
 	}
 
 	if (strstr(pmc->block_name[blk_num], "l3cache"))
@@ -1720,13 +1731,14 @@ static ssize_t mlxbf_pmc_enable_store(struct device *dev,
 {
 	struct mlxbf_pmc_attribute *attr_enable = container_of(
 		attr, struct mlxbf_pmc_attribute, dev_attr);
-	unsigned int en, blk_num;
+	unsigned int blk_num;
 	u32 word;
 	int err;
+	bool en;
 
 	blk_num = attr_enable->nr;
 
-	err = kstrtouint(buf, 0, &en);
+	err = kstrtobool(buf, &en);
 	if (err < 0)
 		return err;
 
@@ -1746,14 +1758,11 @@ static ssize_t mlxbf_pmc_enable_store(struct device *dev,
 			MLXBF_PMC_CRSPACE_PERFMON_CTL(pmc->block[blk_num].counters),
 			MLXBF_PMC_WRITE_REG_32, word);
 	} else {
-		if (en && en != 1)
-			return -EINVAL;
-
 		err = mlxbf_pmc_config_l3_counters(blk_num, false, !!en);
 		if (err)
 			return err;
 
-		if (en == 1) {
+		if (en) {
 			err = mlxbf_pmc_config_l3_counters(blk_num, true, false);
 			if (err)
 				return err;
diff --git a/drivers/platform/mellanox/mlxbf-tmfifo.c b/drivers/platform/mellanox/mlxbf-tmfifo.c
index 6c834e39352d..d2c27cc0733b 100644
--- a/drivers/platform/mellanox/mlxbf-tmfifo.c
+++ b/drivers/platform/mellanox/mlxbf-tmfifo.c
@@ -281,7 +281,8 @@ static int mlxbf_tmfifo_alloc_vrings(struct mlxbf_tmfifo *fifo,
 		vring->align = SMP_CACHE_BYTES;
 		vring->index = i;
 		vring->vdev_id = tm_vdev->vdev.id.device;
-		vring->drop_desc.len = VRING_DROP_DESC_MAX_LEN;
+		vring->drop_desc.len = cpu_to_virtio32(&tm_vdev->vdev,
+						       VRING_DROP_DESC_MAX_LEN);
 		dev = &tm_vdev->vdev.dev;
 
 		size = vring_size(vring->num, vring->align);
diff --git a/drivers/platform/mellanox/mlxreg-lc.c b/drivers/platform/mellanox/mlxreg-lc.c
index 43d119e3a473..99152676dbd2 100644
--- a/drivers/platform/mellanox/mlxreg-lc.c
+++ b/drivers/platform/mellanox/mlxreg-lc.c
@@ -688,7 +688,7 @@ static int mlxreg_lc_completion_notify(void *handle, struct i2c_adapter *parent,
 	if (regval & mlxreg_lc->data->mask) {
 		mlxreg_lc->state |= MLXREG_LC_SYNCED;
 		mlxreg_lc_state_update_locked(mlxreg_lc, MLXREG_LC_SYNCED, 1);
-		if (mlxreg_lc->state & ~MLXREG_LC_POWERED) {
+		if (!(mlxreg_lc->state & MLXREG_LC_POWERED)) {
 			err = mlxreg_lc_power_on_off(mlxreg_lc, 1);
 			if (err)
 				goto mlxreg_lc_regmap_power_on_off_fail;
diff --git a/drivers/platform/mellanox/nvsw-sn2201.c b/drivers/platform/mellanox/nvsw-sn2201.c
index abe7be602f84..e708521e5274 100644
--- a/drivers/platform/mellanox/nvsw-sn2201.c
+++ b/drivers/platform/mellanox/nvsw-sn2201.c
@@ -1088,7 +1088,7 @@ static int nvsw_sn2201_i2c_completion_notify(void *handle, int id)
 	if (!nvsw_sn2201->main_mux_devs->adapter) {
 		err = -ENODEV;
 		dev_err(nvsw_sn2201->dev, "Failed to get adapter for bus %d\n",
-			nvsw_sn2201->cpld_devs->nr);
+			nvsw_sn2201->main_mux_devs->nr);
 		goto i2c_get_adapter_main_fail;
 	}
 
diff --git a/drivers/platform/x86/Makefile b/drivers/platform/x86/Makefile
index e1b142947067..4631c7bb22cd 100644
--- a/drivers/platform/x86/Makefile
+++ b/drivers/platform/x86/Makefile
@@ -58,6 +58,8 @@ obj-$(CONFIG_X86_PLATFORM_DRIVERS_HP)	+= hp/
 # Hewlett Packard Enterprise
 obj-$(CONFIG_UV_SYSFS)       += uv_sysfs.o
 
+obj-$(CONFIG_FW_ATTR_CLASS)	+= firmware_attributes_class.o
+
 # IBM Thinkpad and Lenovo
 obj-$(CONFIG_IBM_RTL)		+= ibm_rtl.o
 obj-$(CONFIG_IDEAPAD_LAPTOP)	+= ideapad-laptop.o
@@ -120,7 +122,6 @@ obj-$(CONFIG_SYSTEM76_ACPI)	+= system76_acpi.o
 obj-$(CONFIG_TOPSTAR_LAPTOP)	+= topstar-laptop.o
 
 # Platform drivers
-obj-$(CONFIG_FW_ATTR_CLASS)		+= firmware_attributes_class.o
 obj-$(CONFIG_SERIAL_MULTI_INSTANTIATE)	+= serial-multi-instantiate.o
 obj-$(CONFIG_MLX_PLATFORM)		+= mlx-platform.o
 obj-$(CONFIG_TOUCHSCREEN_DMI)		+= touchscreen_dmi.o
diff --git a/drivers/platform/x86/acer-wmi.c b/drivers/platform/x86/acer-wmi.c
index 7169b84ccdb6..c5679e4a58a7 100644
--- a/drivers/platform/x86/acer-wmi.c
+++ b/drivers/platform/x86/acer-wmi.c
@@ -95,6 +95,7 @@ enum acer_wmi_event_ids {
 	WMID_HOTKEY_EVENT = 0x1,
 	WMID_ACCEL_OR_KBD_DOCK_EVENT = 0x5,
 	WMID_GAMING_TURBO_KEY_EVENT = 0x7,
+	WMID_AC_EVENT = 0x8,
 };
 
 enum acer_wmi_predator_v4_sys_info_command {
@@ -398,6 +399,20 @@ static struct quirk_entry quirk_acer_predator_ph315_53 = {
 	.gpu_fans = 1,
 };
 
+static struct quirk_entry quirk_acer_predator_ph16_72 = {
+	.turbo = 1,
+	.cpu_fans = 1,
+	.gpu_fans = 1,
+	.predator_v4 = 1,
+};
+
+static struct quirk_entry quirk_acer_predator_pt14_51 = {
+	.turbo = 1,
+	.cpu_fans = 1,
+	.gpu_fans = 1,
+	.predator_v4 = 1,
+};
+
 static struct quirk_entry quirk_acer_predator_v4 = {
 	.predator_v4 = 1,
 };
@@ -571,6 +586,15 @@ static const struct dmi_system_id acer_quirks[] __initconst = {
 	},
 	{
 		.callback = dmi_matched,
+		.ident = "Acer Nitro AN515-58",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Nitro AN515-58"),
+		},
+		.driver_data = &quirk_acer_predator_v4,
+	},
+	{
+		.callback = dmi_matched,
 		.ident = "Acer Predator PH315-53",
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
@@ -598,6 +622,15 @@ static const struct dmi_system_id acer_quirks[] __initconst = {
 	},
 	{
 		.callback = dmi_matched,
+		.ident = "Acer Predator PH16-72",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Predator PH16-72"),
+		},
+		.driver_data = &quirk_acer_predator_ph16_72,
+	},
+	{
+		.callback = dmi_matched,
 		.ident = "Acer Predator PH18-71",
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
@@ -606,6 +639,15 @@ static const struct dmi_system_id acer_quirks[] __initconst = {
 		.driver_data = &quirk_acer_predator_v4,
 	},
 	{
+		.callback = dmi_matched,
+		.ident = "Acer Predator PT14-51",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Predator PT14-51"),
+		},
+		.driver_data = &quirk_acer_predator_pt14_51,
+	},
+	{
 		.callback = set_force_caps,
 		.ident = "Acer Aspire Switch 10E SW3-016",
 		.matches = {
@@ -2285,6 +2327,9 @@ static void acer_wmi_notify(union acpi_object *obj, void *context)
 		if (return_value.key_num == 0x5 && has_cap(ACER_CAP_PLATFORM_PROFILE))
 			acer_thermal_profile_change();
 		break;
+	case WMID_AC_EVENT:
+		/* We ignore AC events here */
+		break;
 	default:
 		pr_warn("Unknown function number - %d - %d\n",
 			return_value.function, return_value.key_num);
diff --git a/drivers/platform/x86/amd/pmc/pmc-quirks.c b/drivers/platform/x86/amd/pmc/pmc-quirks.c
index b4f49720c87f..04686ae1e976 100644
--- a/drivers/platform/x86/amd/pmc/pmc-quirks.c
+++ b/drivers/platform/x86/amd/pmc/pmc-quirks.c
@@ -189,6 +189,15 @@ static const struct dmi_system_id fwbug_list[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "82XQ"),
 		}
 	},
+	/* https://gitlab.freedesktop.org/drm/amd/-/issues/4434 */
+	{
+		.ident = "Lenovo Yoga 6 13ALC6",
+		.driver_data = &quirk_s2idle_bug,
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "82ND"),
+		}
+	},
 	/* https://gitlab.freedesktop.org/drm/amd/-/issues/2684 */
 	{
 		.ident = "HP Laptop 15s-eq2xxx",
@@ -217,6 +226,22 @@ static const struct dmi_system_id fwbug_list[] = {
 			DMI_MATCH(DMI_BIOS_VERSION, "03.05"),
 		}
 	},
+	{
+		.ident = "MECHREVO Wujie 14X (GX4HRXL)",
+		.driver_data = &quirk_spurious_8042,
+		.matches = {
+			DMI_MATCH(DMI_BOARD_NAME, "WUJIE14-GX4HRXL"),
+		}
+	},
+	/* https://bugzilla.kernel.org/show_bug.cgi?id=220116 */
+	{
+		.ident = "PCSpecialist Lafite Pro V 14M",
+		.driver_data = &quirk_spurious_8042,
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "PCSpecialist"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Lafite Pro V 14M"),
+		}
+	},
 	{}
 };
 
diff --git a/drivers/platform/x86/amd/pmc/pmc.c b/drivers/platform/x86/amd/pmc/pmc.c
index 4d3acfe849bf..357a46fdffed 100644
--- a/drivers/platform/x86/amd/pmc/pmc.c
+++ b/drivers/platform/x86/amd/pmc/pmc.c
@@ -393,6 +393,8 @@ static int amd_pmc_setup_smu_logging(struct amd_pmc_dev *dev)
 			return -ENOMEM;
 	}
 
+	memset_io(dev->smu_virt_addr, 0, sizeof(struct smu_metrics));
+
 	/* Start the logging */
 	amd_pmc_send_cmd(dev, 0, NULL, SMU_MSG_LOG_RESET, false);
 	amd_pmc_send_cmd(dev, 0, NULL, SMU_MSG_LOG_START, false);
@@ -892,10 +894,9 @@ static void amd_pmc_s2idle_check(void)
 	struct smu_metrics table;
 	int rc;
 
-	/* CZN: Ensure that future s0i3 entry attempts at least 10ms passed */
-	if (pdev->cpu_id == AMD_CPU_ID_CZN && !get_metrics_table(pdev, &table) &&
-	    table.s0i3_last_entry_status)
-		usleep_range(10000, 20000);
+	/* Avoid triggering OVP */
+	if (!get_metrics_table(pdev, &table) && table.s0i3_last_entry_status)
+		msleep(2500);
 
 	/* Dump the IdleMask before we add to the STB */
 	amd_pmc_idlemask_read(pdev, pdev->dev, NULL);
diff --git a/drivers/platform/x86/amd/pmf/auto-mode.c b/drivers/platform/x86/amd/pmf/auto-mode.c
index 02ff68be10d0..a184922bba8d 100644
--- a/drivers/platform/x86/amd/pmf/auto-mode.c
+++ b/drivers/platform/x86/amd/pmf/auto-mode.c
@@ -120,9 +120,9 @@ static void amd_pmf_set_automode(struct amd_pmf_dev *dev, int idx,
 	amd_pmf_send_cmd(dev, SET_SPPT_APU_ONLY, false, pwr_ctrl->sppt_apu_only, NULL);
 	amd_pmf_send_cmd(dev, SET_STT_MIN_LIMIT, false, pwr_ctrl->stt_min, NULL);
 	amd_pmf_send_cmd(dev, SET_STT_LIMIT_APU, false,
-			 pwr_ctrl->stt_skin_temp[STT_TEMP_APU], NULL);
+			 fixp_q88_fromint(pwr_ctrl->stt_skin_temp[STT_TEMP_APU]), NULL);
 	amd_pmf_send_cmd(dev, SET_STT_LIMIT_HS2, false,
-			 pwr_ctrl->stt_skin_temp[STT_TEMP_HS2], NULL);
+			 fixp_q88_fromint(pwr_ctrl->stt_skin_temp[STT_TEMP_HS2]), NULL);
 
 	if (is_apmf_func_supported(dev, APMF_FUNC_SET_FAN_IDX))
 		apmf_update_fan_idx(dev, config_store.mode_set[idx].fan_control.manual,
diff --git a/drivers/platform/x86/amd/pmf/cnqf.c b/drivers/platform/x86/amd/pmf/cnqf.c
index bc8899e15c91..207a0b33d8d3 100644
--- a/drivers/platform/x86/amd/pmf/cnqf.c
+++ b/drivers/platform/x86/amd/pmf/cnqf.c
@@ -81,10 +81,10 @@ static int amd_pmf_set_cnqf(struct amd_pmf_dev *dev, int src, int idx,
 	amd_pmf_send_cmd(dev, SET_SPPT, false, pc->sppt, NULL);
 	amd_pmf_send_cmd(dev, SET_SPPT_APU_ONLY, false, pc->sppt_apu_only, NULL);
 	amd_pmf_send_cmd(dev, SET_STT_MIN_LIMIT, false, pc->stt_min, NULL);
-	amd_pmf_send_cmd(dev, SET_STT_LIMIT_APU, false, pc->stt_skin_temp[STT_TEMP_APU],
-			 NULL);
-	amd_pmf_send_cmd(dev, SET_STT_LIMIT_HS2, false, pc->stt_skin_temp[STT_TEMP_HS2],
-			 NULL);
+	amd_pmf_send_cmd(dev, SET_STT_LIMIT_APU, false,
+			 fixp_q88_fromint(pc->stt_skin_temp[STT_TEMP_APU]), NULL);
+	amd_pmf_send_cmd(dev, SET_STT_LIMIT_HS2, false,
+			 fixp_q88_fromint(pc->stt_skin_temp[STT_TEMP_HS2]), NULL);
 
 	if (is_apmf_func_supported(dev, APMF_FUNC_SET_FAN_IDX))
 		apmf_update_fan_idx(dev,
diff --git a/drivers/platform/x86/amd/pmf/core.c b/drivers/platform/x86/amd/pmf/core.c
index 347bb43a5f2b..719caa2a00f0 100644
--- a/drivers/platform/x86/amd/pmf/core.c
+++ b/drivers/platform/x86/amd/pmf/core.c
@@ -176,6 +176,20 @@ static void __maybe_unused amd_pmf_dump_registers(struct amd_pmf_dev *dev)
 	dev_dbg(dev->dev, "AMD_PMF_REGISTER_MESSAGE:%x\n", value);
 }
 
+/**
+ * fixp_q88_fromint: Convert integer to Q8.8
+ * @val: input value
+ *
+ * Converts an integer into binary fixed point format where 8 bits
+ * are used for integer and 8 bits are used for the decimal.
+ *
+ * Return: unsigned integer converted to Q8.8 format
+ */
+u32 fixp_q88_fromint(u32 val)
+{
+	return val << 8;
+}
+
 int amd_pmf_send_cmd(struct amd_pmf_dev *dev, u8 message, bool get, u32 arg, u32 *data)
 {
 	int rc;
diff --git a/drivers/platform/x86/amd/pmf/pmf.h b/drivers/platform/x86/amd/pmf/pmf.h
index 8ce8816da9c1..34ba0309a33a 100644
--- a/drivers/platform/x86/amd/pmf/pmf.h
+++ b/drivers/platform/x86/amd/pmf/pmf.h
@@ -105,9 +105,12 @@ struct cookie_header {
 #define PMF_TA_IF_VERSION_MAJOR				1
 #define TA_PMF_ACTION_MAX					32
 #define TA_PMF_UNDO_MAX						8
-#define TA_OUTPUT_RESERVED_MEM				906
+#define TA_OUTPUT_RESERVED_MEM				922
 #define MAX_OPERATION_PARAMS					4
 
+#define TA_ERROR_CRYPTO_INVALID_PARAM				0x20002
+#define TA_ERROR_CRYPTO_BIN_TOO_LARGE				0x2000d
+
 #define PMF_IF_V1		1
 #define PMF_IF_V2		2
 
@@ -743,6 +746,7 @@ int apmf_install_handler(struct amd_pmf_dev *pmf_dev);
 int apmf_os_power_slider_update(struct amd_pmf_dev *dev, u8 flag);
 int amd_pmf_set_dram_addr(struct amd_pmf_dev *dev, bool alloc_buffer);
 int amd_pmf_notify_sbios_heartbeat_event_v2(struct amd_pmf_dev *dev, u8 flag);
+u32 fixp_q88_fromint(u32 val);
 
 /* SPS Layer */
 int amd_pmf_get_pprof_modes(struct amd_pmf_dev *pmf);
diff --git a/drivers/platform/x86/amd/pmf/sps.c b/drivers/platform/x86/amd/pmf/sps.c
index 92f7fb22277d..3a24209f7df0 100644
--- a/drivers/platform/x86/amd/pmf/sps.c
+++ b/drivers/platform/x86/amd/pmf/sps.c
@@ -198,9 +198,11 @@ static void amd_pmf_update_slider_v2(struct amd_pmf_dev *dev, int idx)
 	amd_pmf_send_cmd(dev, SET_STT_MIN_LIMIT, false,
 			 apts_config_store.val[idx].stt_min_limit, NULL);
 	amd_pmf_send_cmd(dev, SET_STT_LIMIT_APU, false,
-			 apts_config_store.val[idx].stt_skin_temp_limit_apu, NULL);
+			 fixp_q88_fromint(apts_config_store.val[idx].stt_skin_temp_limit_apu),
+			 NULL);
 	amd_pmf_send_cmd(dev, SET_STT_LIMIT_HS2, false,
-			 apts_config_store.val[idx].stt_skin_temp_limit_hs2, NULL);
+			 fixp_q88_fromint(apts_config_store.val[idx].stt_skin_temp_limit_hs2),
+			 NULL);
 }
 
 void amd_pmf_update_slider(struct amd_pmf_dev *dev, bool op, int idx,
@@ -217,9 +219,11 @@ void amd_pmf_update_slider(struct amd_pmf_dev *dev, bool op, int idx,
 		amd_pmf_send_cmd(dev, SET_STT_MIN_LIMIT, false,
 				 config_store.prop[src][idx].stt_min, NULL);
 		amd_pmf_send_cmd(dev, SET_STT_LIMIT_APU, false,
-				 config_store.prop[src][idx].stt_skin_temp[STT_TEMP_APU], NULL);
+				 fixp_q88_fromint(config_store.prop[src][idx].stt_skin_temp[STT_TEMP_APU]),
+				 NULL);
 		amd_pmf_send_cmd(dev, SET_STT_LIMIT_HS2, false,
-				 config_store.prop[src][idx].stt_skin_temp[STT_TEMP_HS2], NULL);
+				 fixp_q88_fromint(config_store.prop[src][idx].stt_skin_temp[STT_TEMP_HS2]),
+				 NULL);
 	} else if (op == SLIDER_OP_GET) {
 		amd_pmf_send_cmd(dev, GET_SPL, true, ARG_NONE, &table->prop[src][idx].spl);
 		amd_pmf_send_cmd(dev, GET_FPPT, true, ARG_NONE, &table->prop[src][idx].fppt);
diff --git a/drivers/platform/x86/amd/pmf/tee-if.c b/drivers/platform/x86/amd/pmf/tee-if.c
index 19c27b6e4666..a9b195ec6f33 100644
--- a/drivers/platform/x86/amd/pmf/tee-if.c
+++ b/drivers/platform/x86/amd/pmf/tee-if.c
@@ -27,8 +27,11 @@ module_param(pb_side_load, bool, 0444);
 MODULE_PARM_DESC(pb_side_load, "Sideload policy binaries debug policy failures");
 #endif
 
-static const uuid_t amd_pmf_ta_uuid = UUID_INIT(0x6fd93b77, 0x3fb8, 0x524d,
-						0xb1, 0x2d, 0xc5, 0x29, 0xb1, 0x3d, 0x85, 0x43);
+static const uuid_t amd_pmf_ta_uuid[] = { UUID_INIT(0xd9b39bf2, 0x66bd, 0x4154, 0xaf, 0xb8, 0x8a,
+						    0xcc, 0x2b, 0x2b, 0x60, 0xd6),
+					  UUID_INIT(0x6fd93b77, 0x3fb8, 0x524d, 0xb1, 0x2d, 0xc5,
+						    0x29, 0xb1, 0x3d, 0x85, 0x43),
+					};
 
 static const char *amd_pmf_uevent_as_str(unsigned int state)
 {
@@ -120,7 +123,8 @@ static void amd_pmf_apply_policies(struct amd_pmf_dev *dev, struct ta_pmf_enact_
 
 		case PMF_POLICY_STT_SKINTEMP_APU:
 			if (dev->prev_data->stt_skintemp_apu != val) {
-				amd_pmf_send_cmd(dev, SET_STT_LIMIT_APU, false, val, NULL);
+				amd_pmf_send_cmd(dev, SET_STT_LIMIT_APU, false,
+						 fixp_q88_fromint(val), NULL);
 				dev_dbg(dev->dev, "update STT_SKINTEMP_APU: %u\n", val);
 				dev->prev_data->stt_skintemp_apu = val;
 			}
@@ -128,7 +132,8 @@ static void amd_pmf_apply_policies(struct amd_pmf_dev *dev, struct ta_pmf_enact_
 
 		case PMF_POLICY_STT_SKINTEMP_HS2:
 			if (dev->prev_data->stt_skintemp_hs2 != val) {
-				amd_pmf_send_cmd(dev, SET_STT_LIMIT_HS2, false, val, NULL);
+				amd_pmf_send_cmd(dev, SET_STT_LIMIT_HS2, false,
+						 fixp_q88_fromint(val), NULL);
 				dev_dbg(dev->dev, "update STT_SKINTEMP_HS2: %u\n", val);
 				dev->prev_data->stt_skintemp_hs2 = val;
 			}
@@ -321,14 +326,19 @@ static int amd_pmf_start_policy_engine(struct amd_pmf_dev *dev)
 		 */
 		schedule_delayed_work(&dev->pb_work, msecs_to_jiffies(pb_actions_ms * 3));
 	} else {
-		dev_err(dev->dev, "ta invoke cmd init failed err: %x\n", res);
+		dev_dbg(dev->dev, "ta invoke cmd init failed err: %x\n", res);
 		dev->smart_pc_enabled = false;
-		return -EIO;
+		return res;
 	}
 
 	return 0;
 }
 
+static inline bool amd_pmf_pb_valid(struct amd_pmf_dev *dev)
+{
+	return memchr_inv(dev->policy_buf, 0xff, dev->policy_sz);
+}
+
 #ifdef CONFIG_AMD_PMF_DEBUG
 static void amd_pmf_hex_dump_pb(struct amd_pmf_dev *dev)
 {
@@ -356,12 +366,22 @@ static ssize_t amd_pmf_get_pb_data(struct file *filp, const char __user *buf,
 	dev->policy_buf = new_policy_buf;
 	dev->policy_sz = length;
 
+	if (!amd_pmf_pb_valid(dev)) {
+		ret = -EINVAL;
+		goto cleanup;
+	}
+
 	amd_pmf_hex_dump_pb(dev);
 	ret = amd_pmf_start_policy_engine(dev);
 	if (ret < 0)
-		return ret;
+		goto cleanup;
 
 	return length;
+
+cleanup:
+	kfree(dev->policy_buf);
+	dev->policy_buf = NULL;
+	return ret;
 }
 
 static const struct file_operations pb_fops = {
@@ -390,24 +410,24 @@ static int amd_pmf_amdtee_ta_match(struct tee_ioctl_version_data *ver, const voi
 	return ver->impl_id == TEE_IMPL_ID_AMDTEE;
 }
 
-static int amd_pmf_ta_open_session(struct tee_context *ctx, u32 *id)
+static int amd_pmf_ta_open_session(struct tee_context *ctx, u32 *id, const uuid_t *uuid)
 {
 	struct tee_ioctl_open_session_arg sess_arg = {};
 	int rc;
 
-	export_uuid(sess_arg.uuid, &amd_pmf_ta_uuid);
+	export_uuid(sess_arg.uuid, uuid);
 	sess_arg.clnt_login = TEE_IOCTL_LOGIN_PUBLIC;
 	sess_arg.num_params = 0;
 
 	rc = tee_client_open_session(ctx, &sess_arg, NULL);
 	if (rc < 0 || sess_arg.ret != 0) {
 		pr_err("Failed to open TEE session err:%#x, rc:%d\n", sess_arg.ret, rc);
-		return rc;
+		return rc ?: -EINVAL;
 	}
 
 	*id = sess_arg.session;
 
-	return rc;
+	return 0;
 }
 
 static int amd_pmf_register_input_device(struct amd_pmf_dev *dev)
@@ -434,7 +454,7 @@ static int amd_pmf_register_input_device(struct amd_pmf_dev *dev)
 	return 0;
 }
 
-static int amd_pmf_tee_init(struct amd_pmf_dev *dev)
+static int amd_pmf_tee_init(struct amd_pmf_dev *dev, const uuid_t *uuid)
 {
 	u32 size;
 	int ret;
@@ -442,10 +462,12 @@ static int amd_pmf_tee_init(struct amd_pmf_dev *dev)
 	dev->tee_ctx = tee_client_open_context(NULL, amd_pmf_amdtee_ta_match, NULL, NULL);
 	if (IS_ERR(dev->tee_ctx)) {
 		dev_err(dev->dev, "Failed to open TEE context\n");
-		return PTR_ERR(dev->tee_ctx);
+		ret = PTR_ERR(dev->tee_ctx);
+		dev->tee_ctx = NULL;
+		return ret;
 	}
 
-	ret = amd_pmf_ta_open_session(dev->tee_ctx, &dev->session_id);
+	ret = amd_pmf_ta_open_session(dev->tee_ctx, &dev->session_id, uuid);
 	if (ret) {
 		dev_err(dev->dev, "Failed to open TA session (%d)\n", ret);
 		ret = -EINVAL;
@@ -482,14 +504,18 @@ out_ctx:
 
 static void amd_pmf_tee_deinit(struct amd_pmf_dev *dev)
 {
+	if (!dev->tee_ctx)
+		return;
 	tee_shm_free(dev->fw_shm_pool);
 	tee_client_close_session(dev->tee_ctx, dev->session_id);
 	tee_client_close_context(dev->tee_ctx);
+	dev->tee_ctx = NULL;
 }
 
 int amd_pmf_init_smart_pc(struct amd_pmf_dev *dev)
 {
-	int ret;
+	bool status;
+	int ret, i;
 
 	ret = apmf_check_smart_pc(dev);
 	if (ret) {
@@ -502,53 +528,91 @@ int amd_pmf_init_smart_pc(struct amd_pmf_dev *dev)
 		return -ENODEV;
 	}
 
-	ret = amd_pmf_tee_init(dev);
-	if (ret)
-		return ret;
-
 	INIT_DELAYED_WORK(&dev->pb_work, amd_pmf_invoke_cmd);
 
 	ret = amd_pmf_set_dram_addr(dev, true);
 	if (ret)
-		goto error;
+		goto err_cancel_work;
 
 	dev->policy_base = devm_ioremap(dev->dev, dev->policy_addr, dev->policy_sz);
 	if (!dev->policy_base) {
 		ret = -ENOMEM;
-		goto error;
+		goto err_free_dram_buf;
 	}
 
 	dev->policy_buf = kzalloc(dev->policy_sz, GFP_KERNEL);
 	if (!dev->policy_buf) {
 		ret = -ENOMEM;
-		goto error;
+		goto err_free_dram_buf;
 	}
 
 	memcpy_fromio(dev->policy_buf, dev->policy_base, dev->policy_sz);
 
+	if (!amd_pmf_pb_valid(dev)) {
+		dev_info(dev->dev, "No Smart PC policy present\n");
+		ret = -EINVAL;
+		goto err_free_policy;
+	}
+
 	amd_pmf_hex_dump_pb(dev);
 
 	dev->prev_data = kzalloc(sizeof(*dev->prev_data), GFP_KERNEL);
 	if (!dev->prev_data) {
 		ret = -ENOMEM;
-		goto error;
+		goto err_free_policy;
 	}
 
-	ret = amd_pmf_start_policy_engine(dev);
-	if (ret)
-		goto error;
+	for (i = 0; i < ARRAY_SIZE(amd_pmf_ta_uuid); i++) {
+		ret = amd_pmf_tee_init(dev, &amd_pmf_ta_uuid[i]);
+		if (ret)
+			goto err_free_prev_data;
+
+		ret = amd_pmf_start_policy_engine(dev);
+		switch (ret) {
+		case TA_PMF_TYPE_SUCCESS:
+			status = true;
+			break;
+		case TA_ERROR_CRYPTO_INVALID_PARAM:
+		case TA_ERROR_CRYPTO_BIN_TOO_LARGE:
+			amd_pmf_tee_deinit(dev);
+			status = false;
+			break;
+		default:
+			ret = -EINVAL;
+			amd_pmf_tee_deinit(dev);
+			goto err_free_prev_data;
+		}
+
+		if (status)
+			break;
+	}
+
+	if (!status && !pb_side_load) {
+		ret = -EINVAL;
+		goto err_free_prev_data;
+	}
 
 	if (pb_side_load)
 		amd_pmf_open_pb(dev, dev->dbgfs_dir);
 
 	ret = amd_pmf_register_input_device(dev);
 	if (ret)
-		goto error;
+		goto err_pmf_remove_pb;
 
 	return 0;
 
-error:
-	amd_pmf_deinit_smart_pc(dev);
+err_pmf_remove_pb:
+	if (pb_side_load && dev->esbin)
+		amd_pmf_remove_pb(dev);
+	amd_pmf_tee_deinit(dev);
+err_free_prev_data:
+	kfree(dev->prev_data);
+err_free_policy:
+	kfree(dev->policy_buf);
+err_free_dram_buf:
+	kfree(dev->buf);
+err_cancel_work:
+	cancel_delayed_work_sync(&dev->pb_work);
 
 	return ret;
 }
diff --git a/drivers/platform/x86/asus-laptop.c b/drivers/platform/x86/asus-laptop.c
index 9d7e6b712abf..8d2e6d8be9e5 100644
--- a/drivers/platform/x86/asus-laptop.c
+++ b/drivers/platform/x86/asus-laptop.c
@@ -426,11 +426,14 @@ static int asus_pega_lucid_set(struct asus_laptop *asus, int unit, bool enable)
 
 static int pega_acc_axis(struct asus_laptop *asus, int curr, char *method)
 {
+	unsigned long long val = (unsigned long long)curr;
+	acpi_status status;
 	int i, delta;
-	unsigned long long val;
-	for (i = 0; i < PEGA_ACC_RETRIES; i++) {
-		acpi_evaluate_integer(asus->handle, method, NULL, &val);
 
+	for (i = 0; i < PEGA_ACC_RETRIES; i++) {
+		status = acpi_evaluate_integer(asus->handle, method, NULL, &val);
+		if (ACPI_FAILURE(status))
+			continue;
 		/* The output is noisy.  From reading the ASL
 		 * dissassembly, timeout errors are returned with 1's
 		 * in the high word, and the lack of locking around
diff --git a/drivers/platform/x86/asus-nb-wmi.c b/drivers/platform/x86/asus-nb-wmi.c
index a5933980ade3..90ad0045fec5 100644
--- a/drivers/platform/x86/asus-nb-wmi.c
+++ b/drivers/platform/x86/asus-nb-wmi.c
@@ -529,6 +529,15 @@ static const struct dmi_system_id asus_quirks[] = {
 		},
 		.driver_data = &quirk_asus_zenbook_duo_kbd,
 	},
+	{
+		.callback = dmi_matched,
+		.ident = "ASUS Zenbook Duo UX8406CA",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "UX8406CA"),
+		},
+		.driver_data = &quirk_asus_zenbook_duo_kbd,
+	},
 	{},
 };
 
diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c
index 1101e5b2488e..9d79c5ea8b49 100644
--- a/drivers/platform/x86/asus-wmi.c
+++ b/drivers/platform/x86/asus-wmi.c
@@ -304,6 +304,7 @@ struct asus_wmi {
 
 	u32 kbd_rgb_dev;
 	bool kbd_rgb_state_available;
+	bool oobe_state_available;
 
 	u8 throttle_thermal_policy_mode;
 	u32 throttle_thermal_policy_dev;
@@ -1826,7 +1827,7 @@ static int asus_wmi_led_init(struct asus_wmi *asus)
 			goto error;
 	}
 
-	if (asus_wmi_dev_is_present(asus, ASUS_WMI_DEVID_OOBE)) {
+	if (asus->oobe_state_available) {
 		/*
 		 * Disable OOBE state, so that e.g. the keyboard backlight
 		 * works.
@@ -4741,6 +4742,7 @@ static int asus_wmi_add(struct platform_device *pdev)
 	asus->egpu_enable_available = asus_wmi_dev_is_present(asus, ASUS_WMI_DEVID_EGPU);
 	asus->dgpu_disable_available = asus_wmi_dev_is_present(asus, ASUS_WMI_DEVID_DGPU);
 	asus->kbd_rgb_state_available = asus_wmi_dev_is_present(asus, ASUS_WMI_DEVID_TUF_RGB_STATE);
+	asus->oobe_state_available = asus_wmi_dev_is_present(asus, ASUS_WMI_DEVID_OOBE);
 	asus->ally_mcu_usb_switch = acpi_has_method(NULL, ASUS_USB0_PWR_EC0_CSEE)
 						&& dmi_check_system(asus_ally_mcu_quirk);
 
@@ -4795,7 +4797,8 @@ static int asus_wmi_add(struct platform_device *pdev)
 		goto fail_leds;
 
 	asus_wmi_get_devstate(asus, ASUS_WMI_DEVID_WLAN, &result);
-	if (result & (ASUS_WMI_DSTS_PRESENCE_BIT | ASUS_WMI_DSTS_USER_BIT))
+	if ((result & (ASUS_WMI_DSTS_PRESENCE_BIT | ASUS_WMI_DSTS_USER_BIT)) ==
+	    (ASUS_WMI_DSTS_PRESENCE_BIT | ASUS_WMI_DSTS_USER_BIT))
 		asus->driver->wlan_ctrl_by_user = 1;
 
 	if (!(asus->driver->wlan_ctrl_by_user && ashs_present())) {
@@ -4993,6 +4996,13 @@ static int asus_hotk_restore(struct device *device)
 	}
 	if (!IS_ERR_OR_NULL(asus->kbd_led.dev))
 		kbd_led_update(asus);
+	if (asus->oobe_state_available) {
+		/*
+		 * Disable OOBE state, so that e.g. the keyboard backlight
+		 * works.
+		 */
+		asus_wmi_set_devstate(ASUS_WMI_DEVID_OOBE, 1, NULL);
+	}
 
 	if (asus_wmi_has_fnlock_key(asus))
 		asus_wmi_fnlock_update(asus);
diff --git a/drivers/platform/x86/dell/dell-uart-backlight.c b/drivers/platform/x86/dell/dell-uart-backlight.c
index c45bc332af7a..e4868584cde2 100644
--- a/drivers/platform/x86/dell/dell-uart-backlight.c
+++ b/drivers/platform/x86/dell/dell-uart-backlight.c
@@ -325,7 +325,7 @@ static int dell_uart_bl_serdev_probe(struct serdev_device *serdev)
 	return PTR_ERR_OR_ZERO(dell_bl->bl);
 }
 
-struct serdev_device_driver dell_uart_bl_serdev_driver = {
+static struct serdev_device_driver dell_uart_bl_serdev_driver = {
 	.probe = dell_uart_bl_serdev_probe,
 	.driver = {
 		.name = KBUILD_MODNAME,
diff --git a/drivers/platform/x86/dell/dell-wmi-ddv.c b/drivers/platform/x86/dell/dell-wmi-ddv.c
index e75cd6e1efe6..ab5f7d3ab824 100644
--- a/drivers/platform/x86/dell/dell-wmi-ddv.c
+++ b/drivers/platform/x86/dell/dell-wmi-ddv.c
@@ -665,8 +665,10 @@ static ssize_t temp_show(struct device *dev, struct device_attribute *attr, char
 	if (ret < 0)
 		return ret;
 
-	/* Use 2731 instead of 2731.5 to avoid unnecessary rounding */
-	return sysfs_emit(buf, "%d\n", value - 2731);
+	/* Use 2732 instead of 2731.5 to avoid unnecessary rounding and to emulate
+	 * the behaviour of the OEM application which seems to round down the result.
+	 */
+	return sysfs_emit(buf, "%d\n", value - 2732);
 }
 
 static ssize_t eppid_show(struct device *dev, struct device_attribute *attr, char *buf)
diff --git a/drivers/platform/x86/dell/dell-wmi-sysman/dell-wmi-sysman.h b/drivers/platform/x86/dell/dell-wmi-sysman/dell-wmi-sysman.h
index 3ad33a094588..817ee7ba07ca 100644
--- a/drivers/platform/x86/dell/dell-wmi-sysman/dell-wmi-sysman.h
+++ b/drivers/platform/x86/dell/dell-wmi-sysman/dell-wmi-sysman.h
@@ -89,6 +89,11 @@ extern struct wmi_sysman_priv wmi_priv;
 
 enum { ENUM, INT, STR, PO };
 
+#define ENUM_MIN_ELEMENTS		8
+#define INT_MIN_ELEMENTS		9
+#define STR_MIN_ELEMENTS		8
+#define PO_MIN_ELEMENTS			4
+
 enum {
 	ATTR_NAME,
 	DISPL_NAME_LANG_CODE,
diff --git a/drivers/platform/x86/dell/dell-wmi-sysman/enum-attributes.c b/drivers/platform/x86/dell/dell-wmi-sysman/enum-attributes.c
index 8cc212c85266..fc2f58b4cbc6 100644
--- a/drivers/platform/x86/dell/dell-wmi-sysman/enum-attributes.c
+++ b/drivers/platform/x86/dell/dell-wmi-sysman/enum-attributes.c
@@ -23,9 +23,10 @@ static ssize_t current_value_show(struct kobject *kobj, struct kobj_attribute *a
 	obj = get_wmiobj_pointer(instance_id, DELL_WMI_BIOS_ENUMERATION_ATTRIBUTE_GUID);
 	if (!obj)
 		return -EIO;
-	if (obj->package.elements[CURRENT_VAL].type != ACPI_TYPE_STRING) {
+	if (obj->type != ACPI_TYPE_PACKAGE || obj->package.count < ENUM_MIN_ELEMENTS ||
+	    obj->package.elements[CURRENT_VAL].type != ACPI_TYPE_STRING) {
 		kfree(obj);
-		return -EINVAL;
+		return -EIO;
 	}
 	ret = snprintf(buf, PAGE_SIZE, "%s\n", obj->package.elements[CURRENT_VAL].string.pointer);
 	kfree(obj);
diff --git a/drivers/platform/x86/dell/dell-wmi-sysman/int-attributes.c b/drivers/platform/x86/dell/dell-wmi-sysman/int-attributes.c
index 951e75b538fa..735248064239 100644
--- a/drivers/platform/x86/dell/dell-wmi-sysman/int-attributes.c
+++ b/drivers/platform/x86/dell/dell-wmi-sysman/int-attributes.c
@@ -25,9 +25,10 @@ static ssize_t current_value_show(struct kobject *kobj, struct kobj_attribute *a
 	obj = get_wmiobj_pointer(instance_id, DELL_WMI_BIOS_INTEGER_ATTRIBUTE_GUID);
 	if (!obj)
 		return -EIO;
-	if (obj->package.elements[CURRENT_VAL].type != ACPI_TYPE_INTEGER) {
+	if (obj->type != ACPI_TYPE_PACKAGE || obj->package.count < INT_MIN_ELEMENTS ||
+	    obj->package.elements[CURRENT_VAL].type != ACPI_TYPE_INTEGER) {
 		kfree(obj);
-		return -EINVAL;
+		return -EIO;
 	}
 	ret = snprintf(buf, PAGE_SIZE, "%lld\n", obj->package.elements[CURRENT_VAL].integer.value);
 	kfree(obj);
diff --git a/drivers/platform/x86/dell/dell-wmi-sysman/passobj-attributes.c b/drivers/platform/x86/dell/dell-wmi-sysman/passobj-attributes.c
index 230e6ee96636..3167e06d416e 100644
--- a/drivers/platform/x86/dell/dell-wmi-sysman/passobj-attributes.c
+++ b/drivers/platform/x86/dell/dell-wmi-sysman/passobj-attributes.c
@@ -26,9 +26,10 @@ static ssize_t is_enabled_show(struct kobject *kobj, struct kobj_attribute *attr
 	obj = get_wmiobj_pointer(instance_id, DELL_WMI_BIOS_PASSOBJ_ATTRIBUTE_GUID);
 	if (!obj)
 		return -EIO;
-	if (obj->package.elements[IS_PASS_SET].type != ACPI_TYPE_INTEGER) {
+	if (obj->type != ACPI_TYPE_PACKAGE || obj->package.count < PO_MIN_ELEMENTS ||
+	    obj->package.elements[IS_PASS_SET].type != ACPI_TYPE_INTEGER) {
 		kfree(obj);
-		return -EINVAL;
+		return -EIO;
 	}
 	ret = snprintf(buf, PAGE_SIZE, "%lld\n", obj->package.elements[IS_PASS_SET].integer.value);
 	kfree(obj);
@@ -45,7 +46,7 @@ static ssize_t current_password_store(struct kobject *kobj,
 	int length;
 
 	length = strlen(buf);
-	if (buf[length-1] == '\n')
+	if (length && buf[length - 1] == '\n')
 		length--;
 
 	/* firmware does verifiation of min/max password length,
diff --git a/drivers/platform/x86/dell/dell-wmi-sysman/string-attributes.c b/drivers/platform/x86/dell/dell-wmi-sysman/string-attributes.c
index c392f0ecf8b5..0d2c74f8d1aa 100644
--- a/drivers/platform/x86/dell/dell-wmi-sysman/string-attributes.c
+++ b/drivers/platform/x86/dell/dell-wmi-sysman/string-attributes.c
@@ -25,9 +25,10 @@ static ssize_t current_value_show(struct kobject *kobj, struct kobj_attribute *a
 	obj = get_wmiobj_pointer(instance_id, DELL_WMI_BIOS_STRING_ATTRIBUTE_GUID);
 	if (!obj)
 		return -EIO;
-	if (obj->package.elements[CURRENT_VAL].type != ACPI_TYPE_STRING) {
+	if (obj->type != ACPI_TYPE_PACKAGE || obj->package.count < STR_MIN_ELEMENTS ||
+	    obj->package.elements[CURRENT_VAL].type != ACPI_TYPE_STRING) {
 		kfree(obj);
-		return -EINVAL;
+		return -EIO;
 	}
 	ret = snprintf(buf, PAGE_SIZE, "%s\n", obj->package.elements[CURRENT_VAL].string.pointer);
 	kfree(obj);
diff --git a/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c b/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c
index 40ddc6eb7562..f5402b714657 100644
--- a/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c
+++ b/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c
@@ -25,7 +25,6 @@ struct wmi_sysman_priv wmi_priv = {
 /* reset bios to defaults */
 static const char * const reset_types[] = {"builtinsafe", "lastknowngood", "factory", "custom"};
 static int reset_option = -1;
-static const struct class *fw_attr_class;
 
 
 /**
@@ -408,10 +407,10 @@ static int init_bios_attributes(int attr_type, const char *guid)
 		return retval;
 
 	switch (attr_type) {
-	case ENUM:	min_elements = 8;	break;
-	case INT:	min_elements = 9;	break;
-	case STR:	min_elements = 8;	break;
-	case PO:	min_elements = 4;	break;
+	case ENUM:	min_elements = ENUM_MIN_ELEMENTS;	break;
+	case INT:	min_elements = INT_MIN_ELEMENTS;	break;
+	case STR:	min_elements = STR_MIN_ELEMENTS;	break;
+	case PO:	min_elements = PO_MIN_ELEMENTS;		break;
 	default:
 		pr_err("Error: Unknown attr_type: %d\n", attr_type);
 		return -EINVAL;
@@ -541,15 +540,11 @@ static int __init sysman_init(void)
 		goto err_exit_bios_attr_pass_interface;
 	}
 
-	ret = fw_attributes_class_get(&fw_attr_class);
-	if (ret)
-		goto err_exit_bios_attr_pass_interface;
-
-	wmi_priv.class_dev = device_create(fw_attr_class, NULL, MKDEV(0, 0),
+	wmi_priv.class_dev = device_create(&firmware_attributes_class, NULL, MKDEV(0, 0),
 				  NULL, "%s", DRIVER_NAME);
 	if (IS_ERR(wmi_priv.class_dev)) {
 		ret = PTR_ERR(wmi_priv.class_dev);
-		goto err_unregister_class;
+		goto err_exit_bios_attr_pass_interface;
 	}
 
 	wmi_priv.main_dir_kset = kset_create_and_add("attributes", NULL,
@@ -602,10 +597,7 @@ err_release_attributes_data:
 	release_attributes_data();
 
 err_destroy_classdev:
-	device_destroy(fw_attr_class, MKDEV(0, 0));
-
-err_unregister_class:
-	fw_attributes_class_put();
+	device_unregister(wmi_priv.class_dev);
 
 err_exit_bios_attr_pass_interface:
 	exit_bios_attr_pass_interface();
@@ -619,8 +611,7 @@ err_exit_bios_attr_set_interface:
 static void __exit sysman_exit(void)
 {
 	release_attributes_data();
-	device_destroy(fw_attr_class, MKDEV(0, 0));
-	fw_attributes_class_put();
+	device_unregister(wmi_priv.class_dev);
 	exit_bios_attr_set_interface();
 	exit_bios_attr_pass_interface();
 }
diff --git a/drivers/platform/x86/dell/dell_rbu.c b/drivers/platform/x86/dell/dell_rbu.c
index 9f51e0fcab04..fee20866b41e 100644
--- a/drivers/platform/x86/dell/dell_rbu.c
+++ b/drivers/platform/x86/dell/dell_rbu.c
@@ -292,7 +292,7 @@ static int packet_read_list(char *data, size_t * pread_length)
 	remaining_bytes = *pread_length;
 	bytes_read = rbu_data.packet_read_count;
 
-	list_for_each_entry(newpacket, (&packet_data_head.list)->next, list) {
+	list_for_each_entry(newpacket, &packet_data_head.list, list) {
 		bytes_copied = do_packet_read(pdest, newpacket,
 			remaining_bytes, bytes_read, &temp_count);
 		remaining_bytes -= bytes_copied;
@@ -315,14 +315,14 @@ static void packet_empty_list(void)
 {
 	struct packet_data *newpacket, *tmp;
 
-	list_for_each_entry_safe(newpacket, tmp, (&packet_data_head.list)->next, list) {
+	list_for_each_entry_safe(newpacket, tmp, &packet_data_head.list, list) {
 		list_del(&newpacket->list);
 
 		/*
 		 * zero out the RBU packet memory before freeing
 		 * to make sure there are no stale RBU packets left in memory
 		 */
-		memset(newpacket->data, 0, rbu_data.packetsize);
+		memset(newpacket->data, 0, newpacket->length);
 		set_memory_wb((unsigned long)newpacket->data,
 			1 << newpacket->ordernum);
 		free_pages((unsigned long) newpacket->data,
diff --git a/drivers/platform/x86/firmware_attributes_class.c b/drivers/platform/x86/firmware_attributes_class.c
index 182a07d8ae3d..87672c49e86a 100644
--- a/drivers/platform/x86/firmware_attributes_class.c
+++ b/drivers/platform/x86/firmware_attributes_class.c
@@ -2,48 +2,35 @@
 
 /* Firmware attributes class helper module */
 
-#include <linux/mutex.h>
-#include <linux/device/class.h>
 #include <linux/module.h>
 #include "firmware_attributes_class.h"
 
-static DEFINE_MUTEX(fw_attr_lock);
-static int fw_attr_inuse;
-
-static const struct class firmware_attributes_class = {
+const struct class firmware_attributes_class = {
 	.name = "firmware-attributes",
 };
+EXPORT_SYMBOL_GPL(firmware_attributes_class);
+
+static __init int fw_attributes_class_init(void)
+{
+	return class_register(&firmware_attributes_class);
+}
+module_init(fw_attributes_class_init);
+
+static __exit void fw_attributes_class_exit(void)
+{
+	class_unregister(&firmware_attributes_class);
+}
+module_exit(fw_attributes_class_exit);
 
 int fw_attributes_class_get(const struct class **fw_attr_class)
 {
-	int err;
-
-	mutex_lock(&fw_attr_lock);
-	if (!fw_attr_inuse) { /*first time class is being used*/
-		err = class_register(&firmware_attributes_class);
-		if (err) {
-			mutex_unlock(&fw_attr_lock);
-			return err;
-		}
-	}
-	fw_attr_inuse++;
 	*fw_attr_class = &firmware_attributes_class;
-	mutex_unlock(&fw_attr_lock);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(fw_attributes_class_get);
 
 int fw_attributes_class_put(void)
 {
-	mutex_lock(&fw_attr_lock);
-	if (!fw_attr_inuse) {
-		mutex_unlock(&fw_attr_lock);
-		return -EINVAL;
-	}
-	fw_attr_inuse--;
-	if (!fw_attr_inuse) /* No more consumers */
-		class_unregister(&firmware_attributes_class);
-	mutex_unlock(&fw_attr_lock);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(fw_attributes_class_put);
diff --git a/drivers/platform/x86/firmware_attributes_class.h b/drivers/platform/x86/firmware_attributes_class.h
index 363c75f1ac1b..ef6c3764a834 100644
--- a/drivers/platform/x86/firmware_attributes_class.h
+++ b/drivers/platform/x86/firmware_attributes_class.h
@@ -5,6 +5,9 @@
 #ifndef FW_ATTR_CLASS_H
 #define FW_ATTR_CLASS_H
 
+#include <linux/device/class.h>
+
+extern const struct class firmware_attributes_class;
 int fw_attributes_class_get(const struct class **fw_attr_class);
 int fw_attributes_class_put(void);
 
diff --git a/drivers/platform/x86/fujitsu-laptop.c b/drivers/platform/x86/fujitsu-laptop.c
index ae992ac1ab4a..6d5300c54a42 100644
--- a/drivers/platform/x86/fujitsu-laptop.c
+++ b/drivers/platform/x86/fujitsu-laptop.c
@@ -17,13 +17,13 @@
 /*
  * fujitsu-laptop.c - Fujitsu laptop support, providing access to additional
  * features made available on a range of Fujitsu laptops including the
- * P2xxx/P5xxx/S6xxx/S7xxx series.
+ * P2xxx/P5xxx/S2xxx/S6xxx/S7xxx series.
  *
  * This driver implements a vendor-specific backlight control interface for
  * Fujitsu laptops and provides support for hotkeys present on certain Fujitsu
  * laptops.
  *
- * This driver has been tested on a Fujitsu Lifebook S6410, S7020 and
+ * This driver has been tested on a Fujitsu Lifebook S2110, S6410, S7020 and
  * P8010.  It should work on most P-series and S-series Lifebooks, but
  * YMMV.
  *
@@ -107,7 +107,11 @@
 #define KEY2_CODE			0x411
 #define KEY3_CODE			0x412
 #define KEY4_CODE			0x413
-#define KEY5_CODE			0x420
+#define KEY5_CODE			0x414
+#define KEY6_CODE			0x415
+#define KEY7_CODE			0x416
+#define KEY8_CODE			0x417
+#define KEY9_CODE			0x420
 
 /* Hotkey ringbuffer limits */
 #define MAX_HOTKEY_RINGBUFFER_SIZE	100
@@ -560,7 +564,7 @@ static const struct key_entry keymap_default[] = {
 	{ KE_KEY, KEY2_CODE,            { KEY_PROG2 } },
 	{ KE_KEY, KEY3_CODE,            { KEY_PROG3 } },
 	{ KE_KEY, KEY4_CODE,            { KEY_PROG4 } },
-	{ KE_KEY, KEY5_CODE,            { KEY_RFKILL } },
+	{ KE_KEY, KEY9_CODE,            { KEY_RFKILL } },
 	/* Soft keys read from status flags */
 	{ KE_KEY, FLAG_RFKILL,          { KEY_RFKILL } },
 	{ KE_KEY, FLAG_TOUCHPAD_TOGGLE, { KEY_TOUCHPAD_TOGGLE } },
@@ -584,6 +588,18 @@ static const struct key_entry keymap_p8010[] = {
 	{ KE_END, 0 }
 };
 
+static const struct key_entry keymap_s2110[] = {
+	{ KE_KEY, KEY1_CODE, { KEY_PROG1 } }, /* "A" */
+	{ KE_KEY, KEY2_CODE, { KEY_PROG2 } }, /* "B" */
+	{ KE_KEY, KEY3_CODE, { KEY_WWW } },   /* "Internet" */
+	{ KE_KEY, KEY4_CODE, { KEY_EMAIL } }, /* "E-mail" */
+	{ KE_KEY, KEY5_CODE, { KEY_STOPCD } },
+	{ KE_KEY, KEY6_CODE, { KEY_PLAYPAUSE } },
+	{ KE_KEY, KEY7_CODE, { KEY_PREVIOUSSONG } },
+	{ KE_KEY, KEY8_CODE, { KEY_NEXTSONG } },
+	{ KE_END, 0 }
+};
+
 static const struct key_entry *keymap = keymap_default;
 
 static int fujitsu_laptop_dmi_keymap_override(const struct dmi_system_id *id)
@@ -621,6 +637,15 @@ static const struct dmi_system_id fujitsu_laptop_dmi_table[] = {
 		},
 		.driver_data = (void *)keymap_p8010
 	},
+	{
+		.callback = fujitsu_laptop_dmi_keymap_override,
+		.ident = "Fujitsu LifeBook S2110",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU SIEMENS"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK S2110"),
+		},
+		.driver_data = (void *)keymap_s2110
+	},
 	{}
 };
 
diff --git a/drivers/platform/x86/hp/hp-bioscfg/bioscfg.c b/drivers/platform/x86/hp/hp-bioscfg/bioscfg.c
index 2dc50152158a..00b04adb4f19 100644
--- a/drivers/platform/x86/hp/hp-bioscfg/bioscfg.c
+++ b/drivers/platform/x86/hp/hp-bioscfg/bioscfg.c
@@ -24,8 +24,6 @@ struct bioscfg_priv bioscfg_drv = {
 	.mutex = __MUTEX_INITIALIZER(bioscfg_drv.mutex),
 };
 
-static const struct class *fw_attr_class;
-
 ssize_t display_name_language_code_show(struct kobject *kobj,
 					struct kobj_attribute *attr,
 					char *buf)
@@ -972,11 +970,7 @@ static int __init hp_init(void)
 	if (ret)
 		return ret;
 
-	ret = fw_attributes_class_get(&fw_attr_class);
-	if (ret)
-		goto err_unregister_class;
-
-	bioscfg_drv.class_dev = device_create(fw_attr_class, NULL, MKDEV(0, 0),
+	bioscfg_drv.class_dev = device_create(&firmware_attributes_class, NULL, MKDEV(0, 0),
 					      NULL, "%s", DRIVER_NAME);
 	if (IS_ERR(bioscfg_drv.class_dev)) {
 		ret = PTR_ERR(bioscfg_drv.class_dev);
@@ -1043,10 +1037,9 @@ err_release_attributes_data:
 	release_attributes_data();
 
 err_destroy_classdev:
-	device_destroy(fw_attr_class, MKDEV(0, 0));
+	device_unregister(bioscfg_drv.class_dev);
 
 err_unregister_class:
-	fw_attributes_class_put();
 	hp_exit_attr_set_interface();
 
 	return ret;
@@ -1055,9 +1048,8 @@ err_unregister_class:
 static void __exit hp_exit(void)
 {
 	release_attributes_data();
-	device_destroy(fw_attr_class, MKDEV(0, 0));
+	device_unregister(bioscfg_drv.class_dev);
 
-	fw_attributes_class_put();
 	hp_exit_attr_set_interface();
 }
 
diff --git a/drivers/platform/x86/ideapad-laptop.c b/drivers/platform/x86/ideapad-laptop.c
index c908f52ed717..c7e8bcf3d623 100644
--- a/drivers/platform/x86/ideapad-laptop.c
+++ b/drivers/platform/x86/ideapad-laptop.c
@@ -15,6 +15,7 @@
 #include <linux/bug.h>
 #include <linux/cleanup.h>
 #include <linux/debugfs.h>
+#include <linux/delay.h>
 #include <linux/device.h>
 #include <linux/dmi.h>
 #include <linux/i8042.h>
@@ -267,6 +268,20 @@ static void ideapad_shared_exit(struct ideapad_private *priv)
  */
 #define IDEAPAD_EC_TIMEOUT 200 /* in ms */
 
+/*
+ * Some models (e.g., ThinkBook since 2024) have a low tolerance for being
+ * polled too frequently. Doing so may break the state machine in the EC,
+ * resulting in a hard shutdown.
+ *
+ * It is also observed that frequent polls may disturb the ongoing operation
+ * and notably delay the availability of EC response.
+ *
+ * These values are used as the delay before the first poll and the interval
+ * between subsequent polls to solve the above issues.
+ */
+#define IDEAPAD_EC_POLL_MIN_US 150
+#define IDEAPAD_EC_POLL_MAX_US 300
+
 static int eval_int(acpi_handle handle, const char *name, unsigned long *res)
 {
 	unsigned long long result;
@@ -383,7 +398,7 @@ static int read_ec_data(acpi_handle handle, unsigned long cmd, unsigned long *da
 	end_jiffies = jiffies + msecs_to_jiffies(IDEAPAD_EC_TIMEOUT) + 1;
 
 	while (time_before(jiffies, end_jiffies)) {
-		schedule();
+		usleep_range(IDEAPAD_EC_POLL_MIN_US, IDEAPAD_EC_POLL_MAX_US);
 
 		err = eval_vpcr(handle, 1, &val);
 		if (err)
@@ -414,7 +429,7 @@ static int write_ec_cmd(acpi_handle handle, unsigned long cmd, unsigned long dat
 	end_jiffies = jiffies + msecs_to_jiffies(IDEAPAD_EC_TIMEOUT) + 1;
 
 	while (time_before(jiffies, end_jiffies)) {
-		schedule();
+		usleep_range(IDEAPAD_EC_POLL_MIN_US, IDEAPAD_EC_POLL_MAX_US);
 
 		err = eval_vpcr(handle, 1, &val);
 		if (err)
@@ -1297,6 +1312,16 @@ static const struct key_entry ideapad_keymap[] = {
 	/* Specific to some newer models */
 	{ KE_KEY,	0x3e | IDEAPAD_WMI_KEY, { KEY_MICMUTE } },
 	{ KE_KEY,	0x3f | IDEAPAD_WMI_KEY, { KEY_RFKILL } },
+	/* Star- (User Assignable Key) */
+	{ KE_KEY,	0x44 | IDEAPAD_WMI_KEY, { KEY_PROG1 } },
+	/* Eye */
+	{ KE_KEY,	0x45 | IDEAPAD_WMI_KEY, { KEY_PROG3 } },
+	/* Performance toggle also Fn+Q, handled inside ideapad_wmi_notify() */
+	{ KE_KEY,	0x3d | IDEAPAD_WMI_KEY, { KEY_PROG4 } },
+	/* shift + prtsc */
+	{ KE_KEY,   0x2d | IDEAPAD_WMI_KEY, { KEY_CUT } },
+	{ KE_KEY,   0x29 | IDEAPAD_WMI_KEY, { KEY_TOUCHPAD_TOGGLE } },
+	{ KE_KEY,   0x2a | IDEAPAD_WMI_KEY, { KEY_ROOT_MENU } },
 
 	{ KE_END },
 };
@@ -1647,7 +1672,7 @@ static int ideapad_kbd_bl_init(struct ideapad_private *priv)
 	priv->kbd_bl.led.name                    = "platform::" LED_FUNCTION_KBD_BACKLIGHT;
 	priv->kbd_bl.led.brightness_get          = ideapad_kbd_bl_led_cdev_brightness_get;
 	priv->kbd_bl.led.brightness_set_blocking = ideapad_kbd_bl_led_cdev_brightness_set;
-	priv->kbd_bl.led.flags                   = LED_BRIGHT_HW_CHANGED;
+	priv->kbd_bl.led.flags                   = LED_BRIGHT_HW_CHANGED | LED_RETAIN_AT_SHUTDOWN;
 
 	err = led_classdev_register(&priv->platform_device->dev, &priv->kbd_bl.led);
 	if (err)
@@ -1706,7 +1731,7 @@ static int ideapad_fn_lock_led_init(struct ideapad_private *priv)
 	priv->fn_lock.led.name                    = "platform::" LED_FUNCTION_FNLOCK;
 	priv->fn_lock.led.brightness_get          = ideapad_fn_lock_led_cdev_get;
 	priv->fn_lock.led.brightness_set_blocking = ideapad_fn_lock_led_cdev_set;
-	priv->fn_lock.led.flags                   = LED_BRIGHT_HW_CHANGED;
+	priv->fn_lock.led.flags                   = LED_BRIGHT_HW_CHANGED | LED_RETAIN_AT_SHUTDOWN;
 
 	err = led_classdev_register(&priv->platform_device->dev, &priv->fn_lock.led);
 	if (err)
@@ -2083,6 +2108,12 @@ static void ideapad_wmi_notify(struct wmi_device *wdev, union acpi_object *data)
 		dev_dbg(&wdev->dev, "WMI fn-key event: 0x%llx\n",
 			data->integer.value);
 
+		/* performance button triggered by 0x3d */
+		if (data->integer.value == 0x3d && priv->dytc) {
+			platform_profile_cycle();
+			break;
+		}
+
 		/* 0x02 FnLock, 0x03 Esc */
 		if (data->integer.value == 0x02 || data->integer.value == 0x03)
 			ideapad_fn_lock_led_notify(priv, data->integer.value == 0x02);
diff --git a/drivers/platform/x86/intel/hid.c b/drivers/platform/x86/intel/hid.c
index 445e7a59beb4..59392f1a0d8a 100644
--- a/drivers/platform/x86/intel/hid.c
+++ b/drivers/platform/x86/intel/hid.c
@@ -44,16 +44,17 @@ MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Alex Hung");
 
 static const struct acpi_device_id intel_hid_ids[] = {
-	{"INT33D5", 0},
-	{"INTC1051", 0},
-	{"INTC1054", 0},
-	{"INTC1070", 0},
-	{"INTC1076", 0},
-	{"INTC1077", 0},
-	{"INTC1078", 0},
-	{"INTC107B", 0},
-	{"INTC10CB", 0},
-	{"", 0},
+	{ "INT33D5" },
+	{ "INTC1051" },
+	{ "INTC1054" },
+	{ "INTC1070" },
+	{ "INTC1076" },
+	{ "INTC1077" },
+	{ "INTC1078" },
+	{ "INTC107B" },
+	{ "INTC10CB" },
+	{ "INTC10CC" },
+	{ }
 };
 MODULE_DEVICE_TABLE(acpi, intel_hid_ids);
 
@@ -132,6 +133,13 @@ static const struct dmi_system_id button_array_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "Surface Go 3"),
 		},
 	},
+	{
+		.ident = "Microsoft Surface Go 4",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Microsoft Corporation"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Surface Go 4"),
+		},
+	},
 	{ }
 };
 
diff --git a/drivers/platform/x86/intel/int3472/discrete.c b/drivers/platform/x86/intel/int3472/discrete.c
index 3de463c3d13b..9e69ac9cfb92 100644
--- a/drivers/platform/x86/intel/int3472/discrete.c
+++ b/drivers/platform/x86/intel/int3472/discrete.c
@@ -2,6 +2,7 @@
 /* Author: Dan Scally <djrscally@gmail.com> */
 
 #include <linux/acpi.h>
+#include <linux/array_size.h>
 #include <linux/bitfield.h>
 #include <linux/device.h>
 #include <linux/gpio/consumer.h>
@@ -55,7 +56,7 @@ static void skl_int3472_log_sensor_module_name(struct int3472_discrete_device *i
 
 static int skl_int3472_fill_gpiod_lookup(struct gpiod_lookup *table_entry,
 					 struct acpi_resource_gpio *agpio,
-					 const char *func, u32 polarity)
+					 const char *func, unsigned long gpio_flags)
 {
 	char *path = agpio->resource_source.string_ptr;
 	struct acpi_device *adev;
@@ -70,14 +71,14 @@ static int skl_int3472_fill_gpiod_lookup(struct gpiod_lookup *table_entry,
 	if (!adev)
 		return -ENODEV;
 
-	*table_entry = GPIO_LOOKUP(acpi_dev_name(adev), agpio->pin_table[0], func, polarity);
+	*table_entry = GPIO_LOOKUP(acpi_dev_name(adev), agpio->pin_table[0], func, gpio_flags);
 
 	return 0;
 }
 
 static int skl_int3472_map_gpio_to_sensor(struct int3472_discrete_device *int3472,
 					  struct acpi_resource_gpio *agpio,
-					  const char *func, u32 polarity)
+					  const char *func, unsigned long gpio_flags)
 {
 	int ret;
 
@@ -87,7 +88,7 @@ static int skl_int3472_map_gpio_to_sensor(struct int3472_discrete_device *int347
 	}
 
 	ret = skl_int3472_fill_gpiod_lookup(&int3472->gpios.table[int3472->n_sensor_gpios],
-					    agpio, func, polarity);
+					    agpio, func, gpio_flags);
 	if (ret)
 		return ret;
 
@@ -100,7 +101,7 @@ static int skl_int3472_map_gpio_to_sensor(struct int3472_discrete_device *int347
 static struct gpio_desc *
 skl_int3472_gpiod_get_from_temp_lookup(struct int3472_discrete_device *int3472,
 				       struct acpi_resource_gpio *agpio,
-				       const char *func, u32 polarity)
+				       const char *func, unsigned long gpio_flags)
 {
 	struct gpio_desc *desc;
 	int ret;
@@ -111,7 +112,7 @@ skl_int3472_gpiod_get_from_temp_lookup(struct int3472_discrete_device *int3472,
 		return ERR_PTR(-ENOMEM);
 
 	lookup->dev_id = dev_name(int3472->dev);
-	ret = skl_int3472_fill_gpiod_lookup(&lookup->table[0], agpio, func, polarity);
+	ret = skl_int3472_fill_gpiod_lookup(&lookup->table[0], agpio, func, gpio_flags);
 	if (ret)
 		return ERR_PTR(ret);
 
@@ -122,32 +123,76 @@ skl_int3472_gpiod_get_from_temp_lookup(struct int3472_discrete_device *int3472,
 	return desc;
 }
 
-static void int3472_get_func_and_polarity(u8 type, const char **func, u32 *polarity)
+/**
+ * struct int3472_gpio_map - Map GPIOs to whatever is expected by the
+ * sensor driver (as in DT bindings)
+ * @hid: The ACPI HID of the device without the instance number e.g. INT347E
+ * @type_from: The GPIO type from ACPI ?SDT
+ * @type_to: The assigned GPIO type, typically same as @type_from
+ * @func: The function, e.g. "enable"
+ * @polarity_low: GPIO_ACTIVE_LOW true if the @polarity_low is true,
+ * GPIO_ACTIVE_HIGH otherwise
+ */
+struct int3472_gpio_map {
+	const char *hid;
+	u8 type_from;
+	u8 type_to;
+	bool polarity_low;
+	const char *func;
+};
+
+static const struct int3472_gpio_map int3472_gpio_map[] = {
+	{ "INT347E", INT3472_GPIO_TYPE_RESET, INT3472_GPIO_TYPE_RESET, false, "enable" },
+};
+
+static void int3472_get_func_and_polarity(struct acpi_device *adev, u8 *type,
+					  const char **func, unsigned long *gpio_flags)
 {
-	switch (type) {
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(int3472_gpio_map); i++) {
+		/*
+		 * Map the firmware-provided GPIO to whatever a driver expects
+		 * (as in DT bindings). First check if the type matches with the
+		 * GPIO map, then further check that the device _HID matches.
+		 */
+		if (*type != int3472_gpio_map[i].type_from)
+			continue;
+
+		if (!acpi_dev_hid_uid_match(adev, int3472_gpio_map[i].hid, NULL))
+			continue;
+
+		*type = int3472_gpio_map[i].type_to;
+		*gpio_flags = int3472_gpio_map[i].polarity_low ?
+			      GPIO_ACTIVE_LOW : GPIO_ACTIVE_HIGH;
+		*func = int3472_gpio_map[i].func;
+		return;
+	}
+
+	switch (*type) {
 	case INT3472_GPIO_TYPE_RESET:
 		*func = "reset";
-		*polarity = GPIO_ACTIVE_LOW;
+		*gpio_flags = GPIO_ACTIVE_LOW;
 		break;
 	case INT3472_GPIO_TYPE_POWERDOWN:
 		*func = "powerdown";
-		*polarity = GPIO_ACTIVE_LOW;
+		*gpio_flags = GPIO_ACTIVE_LOW;
 		break;
 	case INT3472_GPIO_TYPE_CLK_ENABLE:
 		*func = "clk-enable";
-		*polarity = GPIO_ACTIVE_HIGH;
+		*gpio_flags = GPIO_ACTIVE_HIGH;
 		break;
 	case INT3472_GPIO_TYPE_PRIVACY_LED:
 		*func = "privacy-led";
-		*polarity = GPIO_ACTIVE_HIGH;
+		*gpio_flags = GPIO_ACTIVE_HIGH;
 		break;
 	case INT3472_GPIO_TYPE_POWER_ENABLE:
 		*func = "power-enable";
-		*polarity = GPIO_ACTIVE_HIGH;
+		*gpio_flags = GPIO_ACTIVE_HIGH;
 		break;
 	default:
 		*func = "unknown";
-		*polarity = GPIO_ACTIVE_HIGH;
+		*gpio_flags = GPIO_ACTIVE_HIGH;
 		break;
 	}
 }
@@ -194,7 +239,7 @@ static int skl_int3472_handle_gpio_resources(struct acpi_resource *ares,
 	struct gpio_desc *gpio;
 	const char *err_msg;
 	const char *func;
-	u32 polarity;
+	unsigned long gpio_flags;
 	int ret;
 
 	if (!acpi_gpio_get_io_resource(ares, &agpio))
@@ -217,7 +262,7 @@ static int skl_int3472_handle_gpio_resources(struct acpi_resource *ares,
 
 	type = FIELD_GET(INT3472_GPIO_DSM_TYPE, obj->integer.value);
 
-	int3472_get_func_and_polarity(type, &func, &polarity);
+	int3472_get_func_and_polarity(int3472->sensor, &type, &func, &gpio_flags);
 
 	pin = FIELD_GET(INT3472_GPIO_DSM_PIN, obj->integer.value);
 	if (pin != agpio->pin_table[0])
@@ -227,16 +272,16 @@ static int skl_int3472_handle_gpio_resources(struct acpi_resource *ares,
 
 	active_value = FIELD_GET(INT3472_GPIO_DSM_SENSOR_ON_VAL, obj->integer.value);
 	if (!active_value)
-		polarity ^= GPIO_ACTIVE_LOW;
+		gpio_flags ^= GPIO_ACTIVE_LOW;
 
 	dev_dbg(int3472->dev, "%s %s pin %d active-%s\n", func,
 		agpio->resource_source.string_ptr, agpio->pin_table[0],
-		str_high_low(polarity == GPIO_ACTIVE_HIGH));
+		str_high_low(gpio_flags == GPIO_ACTIVE_HIGH));
 
 	switch (type) {
 	case INT3472_GPIO_TYPE_RESET:
 	case INT3472_GPIO_TYPE_POWERDOWN:
-		ret = skl_int3472_map_gpio_to_sensor(int3472, agpio, func, polarity);
+		ret = skl_int3472_map_gpio_to_sensor(int3472, agpio, func, gpio_flags);
 		if (ret)
 			err_msg = "Failed to map GPIO pin to sensor\n";
 
@@ -244,7 +289,7 @@ static int skl_int3472_handle_gpio_resources(struct acpi_resource *ares,
 	case INT3472_GPIO_TYPE_CLK_ENABLE:
 	case INT3472_GPIO_TYPE_PRIVACY_LED:
 	case INT3472_GPIO_TYPE_POWER_ENABLE:
-		gpio = skl_int3472_gpiod_get_from_temp_lookup(int3472, agpio, func, polarity);
+		gpio = skl_int3472_gpiod_get_from_temp_lookup(int3472, agpio, func, gpio_flags);
 		if (IS_ERR(gpio)) {
 			ret = PTR_ERR(gpio);
 			err_msg = "Failed to get GPIO\n";
@@ -336,6 +381,9 @@ static int skl_int3472_discrete_probe(struct platform_device *pdev)
 	struct int3472_cldb cldb;
 	int ret;
 
+	if (!adev)
+		return -ENODEV;
+
 	ret = skl_int3472_fill_cldb(adev, &cldb);
 	if (ret) {
 		dev_err(&pdev->dev, "Couldn't fill CLDB structure\n");
diff --git a/drivers/platform/x86/intel/int3472/tps68470.c b/drivers/platform/x86/intel/int3472/tps68470.c
index 1e107fd49f82..81ac4c691963 100644
--- a/drivers/platform/x86/intel/int3472/tps68470.c
+++ b/drivers/platform/x86/intel/int3472/tps68470.c
@@ -152,6 +152,9 @@ static int skl_int3472_tps68470_probe(struct i2c_client *client)
 	int ret;
 	int i;
 
+	if (!adev)
+		return -ENODEV;
+
 	n_consumers = skl_int3472_fill_clk_pdata(&client->dev, &clk_pdata);
 	if (n_consumers < 0)
 		return n_consumers;
diff --git a/drivers/platform/x86/intel/pmc/core.c b/drivers/platform/x86/intel/pmc/core.c
index 4e9c8c96c8cc..257c03c59fd9 100644
--- a/drivers/platform/x86/intel/pmc/core.c
+++ b/drivers/platform/x86/intel/pmc/core.c
@@ -625,8 +625,8 @@ static u32 convert_ltr_scale(u32 val)
 static int pmc_core_ltr_show(struct seq_file *s, void *unused)
 {
 	struct pmc_dev *pmcdev = s->private;
-	u64 decoded_snoop_ltr, decoded_non_snoop_ltr;
-	u32 ltr_raw_data, scale, val;
+	u64 decoded_snoop_ltr, decoded_non_snoop_ltr, val;
+	u32 ltr_raw_data, scale;
 	u16 snoop_ltr, nonsnoop_ltr;
 	unsigned int i, index, ltr_index = 0;
 
diff --git a/drivers/platform/x86/intel/pmt/class.c b/drivers/platform/x86/intel/pmt/class.c
index c3ca2ac91b05..d2f0aea6ea50 100644
--- a/drivers/platform/x86/intel/pmt/class.c
+++ b/drivers/platform/x86/intel/pmt/class.c
@@ -97,7 +97,7 @@ intel_pmt_read(struct file *filp, struct kobject *kobj,
 	if (count > entry->size - off)
 		count = entry->size - off;
 
-	count = pmt_telem_read_mmio(entry->ep->pcidev, entry->cb, entry->header.guid, buf,
+	count = pmt_telem_read_mmio(entry->pcidev, entry->cb, entry->header.guid, buf,
 				    entry->base, off, count);
 
 	return count;
@@ -252,6 +252,7 @@ static int intel_pmt_populate_entry(struct intel_pmt_entry *entry,
 		return -EINVAL;
 	}
 
+	entry->pcidev = pci_dev;
 	entry->guid = header->guid;
 	entry->size = header->size;
 	entry->cb = ivdev->priv_data;
diff --git a/drivers/platform/x86/intel/pmt/class.h b/drivers/platform/x86/intel/pmt/class.h
index b2006d57779d..f6ce80c4e051 100644
--- a/drivers/platform/x86/intel/pmt/class.h
+++ b/drivers/platform/x86/intel/pmt/class.h
@@ -39,6 +39,7 @@ struct intel_pmt_header {
 
 struct intel_pmt_entry {
 	struct telem_endpoint	*ep;
+	struct pci_dev		*pcidev;
 	struct intel_pmt_header	header;
 	struct bin_attribute	pmt_bin_attr;
 	struct kobject		*kobj;
diff --git a/drivers/platform/x86/intel/speed_select_if/isst_if_common.c b/drivers/platform/x86/intel/speed_select_if/isst_if_common.c
index dbcd3087aaa4..31239a93dd71 100644
--- a/drivers/platform/x86/intel/speed_select_if/isst_if_common.c
+++ b/drivers/platform/x86/intel/speed_select_if/isst_if_common.c
@@ -84,7 +84,7 @@ static DECLARE_HASHTABLE(isst_hash, 8);
 static DEFINE_MUTEX(isst_hash_lock);
 
 static int isst_store_new_cmd(int cmd, u32 cpu, int mbox_cmd_type, u32 param,
-			      u32 data)
+			      u64 data)
 {
 	struct isst_cmd *sst_cmd;
 
diff --git a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c
index 0591053813a2..5ab45b751666 100644
--- a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c
+++ b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c
@@ -467,10 +467,13 @@ static int uncore_probe(struct auxiliary_device *auxdev, const struct auxiliary_
 
 	/* Get the package ID from the TPMI core */
 	plat_info = tpmi_get_platform_data(auxdev);
-	if (plat_info)
-		pkg = plat_info->package_id;
-	else
+	if (unlikely(!plat_info)) {
 		dev_info(&auxdev->dev, "Platform information is NULL\n");
+		ret = -ENODEV;
+		goto err_rem_common;
+	}
+
+	pkg = plat_info->package_id;
 
 	for (i = 0; i < num_resources; ++i) {
 		struct tpmi_uncore_power_domain_info *pd_info;
diff --git a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency.c b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency.c
index a450b8a6bcec..529b19833537 100644
--- a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency.c
+++ b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency.c
@@ -146,15 +146,13 @@ static int uncore_event_cpu_online(unsigned int cpu)
 {
 	struct uncore_data *data;
 	int target;
+	int ret;
 
 	/* Check if there is an online cpu in the package for uncore MSR */
 	target = cpumask_any_and(&uncore_cpu_mask, topology_die_cpumask(cpu));
 	if (target < nr_cpu_ids)
 		return 0;
 
-	/* Use this CPU on this die as a control CPU */
-	cpumask_set_cpu(cpu, &uncore_cpu_mask);
-
 	data = uncore_get_instance(cpu);
 	if (!data)
 		return 0;
@@ -163,7 +161,14 @@ static int uncore_event_cpu_online(unsigned int cpu)
 	data->die_id = topology_die_id(cpu);
 	data->domain_id = UNCORE_DOMAIN_ID_INVALID;
 
-	return uncore_freq_add_entry(data, cpu);
+	ret = uncore_freq_add_entry(data, cpu);
+	if (ret)
+		return ret;
+
+	/* Use this CPU on this die as a control CPU */
+	cpumask_set_cpu(cpu, &uncore_cpu_mask);
+
+	return 0;
 }
 
 static int uncore_event_cpu_offline(unsigned int cpu)
diff --git a/drivers/platform/x86/intel/vsec.c b/drivers/platform/x86/intel/vsec.c
index 7b5cc9993974..55dd2286f3f3 100644
--- a/drivers/platform/x86/intel/vsec.c
+++ b/drivers/platform/x86/intel/vsec.c
@@ -410,6 +410,11 @@ static const struct intel_vsec_platform_info oobmsm_info = {
 	.caps = VSEC_CAP_TELEMETRY | VSEC_CAP_SDSI | VSEC_CAP_TPMI,
 };
 
+/* DMR OOBMSM info */
+static const struct intel_vsec_platform_info dmr_oobmsm_info = {
+	.caps = VSEC_CAP_TELEMETRY | VSEC_CAP_TPMI,
+};
+
 /* TGL info */
 static const struct intel_vsec_platform_info tgl_info = {
 	.caps = VSEC_CAP_TELEMETRY,
@@ -426,6 +431,7 @@ static const struct intel_vsec_platform_info lnl_info = {
 #define PCI_DEVICE_ID_INTEL_VSEC_MTL_M		0x7d0d
 #define PCI_DEVICE_ID_INTEL_VSEC_MTL_S		0xad0d
 #define PCI_DEVICE_ID_INTEL_VSEC_OOBMSM		0x09a7
+#define PCI_DEVICE_ID_INTEL_VSEC_OOBMSM_DMR	0x09a1
 #define PCI_DEVICE_ID_INTEL_VSEC_RPL		0xa77d
 #define PCI_DEVICE_ID_INTEL_VSEC_TGL		0x9a0d
 #define PCI_DEVICE_ID_INTEL_VSEC_LNL_M		0x647d
@@ -435,6 +441,7 @@ static const struct pci_device_id intel_vsec_pci_ids[] = {
 	{ PCI_DEVICE_DATA(INTEL, VSEC_MTL_M, &mtl_info) },
 	{ PCI_DEVICE_DATA(INTEL, VSEC_MTL_S, &mtl_info) },
 	{ PCI_DEVICE_DATA(INTEL, VSEC_OOBMSM, &oobmsm_info) },
+	{ PCI_DEVICE_DATA(INTEL, VSEC_OOBMSM_DMR, &dmr_oobmsm_info) },
 	{ PCI_DEVICE_DATA(INTEL, VSEC_RPL, &tgl_info) },
 	{ PCI_DEVICE_DATA(INTEL, VSEC_TGL, &tgl_info) },
 	{ PCI_DEVICE_DATA(INTEL, VSEC_LNL_M, &lnl_info) },
diff --git a/drivers/platform/x86/lenovo-yoga-tab2-pro-1380-fastcharger.c b/drivers/platform/x86/lenovo-yoga-tab2-pro-1380-fastcharger.c
index 32d9b6009c42..21de7c3a1ee3 100644
--- a/drivers/platform/x86/lenovo-yoga-tab2-pro-1380-fastcharger.c
+++ b/drivers/platform/x86/lenovo-yoga-tab2-pro-1380-fastcharger.c
@@ -219,7 +219,7 @@ static int yt2_1380_fc_serdev_probe(struct serdev_device *serdev)
 	return 0;
 }
 
-struct serdev_device_driver yt2_1380_fc_serdev_driver = {
+static struct serdev_device_driver yt2_1380_fc_serdev_driver = {
 	.probe = yt2_1380_fc_serdev_probe,
 	.driver = {
 		.name = KBUILD_MODNAME,
diff --git a/drivers/platform/x86/msi-wmi-platform.c b/drivers/platform/x86/msi-wmi-platform.c
index 9b5c7f8c79b0..dc5e9878cb68 100644
--- a/drivers/platform/x86/msi-wmi-platform.c
+++ b/drivers/platform/x86/msi-wmi-platform.c
@@ -10,6 +10,7 @@
 #include <linux/acpi.h>
 #include <linux/bits.h>
 #include <linux/bitfield.h>
+#include <linux/cleanup.h>
 #include <linux/debugfs.h>
 #include <linux/device.h>
 #include <linux/device/driver.h>
@@ -17,6 +18,7 @@
 #include <linux/hwmon.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/mutex.h>
 #include <linux/printk.h>
 #include <linux/rwsem.h>
 #include <linux/types.h>
@@ -76,8 +78,13 @@ enum msi_wmi_platform_method {
 	MSI_PLATFORM_GET_WMI		= 0x1d,
 };
 
-struct msi_wmi_platform_debugfs_data {
+struct msi_wmi_platform_data {
 	struct wmi_device *wdev;
+	struct mutex wmi_lock;	/* Necessary when calling WMI methods */
+};
+
+struct msi_wmi_platform_debugfs_data {
+	struct msi_wmi_platform_data *data;
 	enum msi_wmi_platform_method method;
 	struct rw_semaphore buffer_lock;	/* Protects debugfs buffer */
 	size_t length;
@@ -132,8 +139,9 @@ static int msi_wmi_platform_parse_buffer(union acpi_object *obj, u8 *output, siz
 	return 0;
 }
 
-static int msi_wmi_platform_query(struct wmi_device *wdev, enum msi_wmi_platform_method method,
-				  u8 *input, size_t input_length, u8 *output, size_t output_length)
+static int msi_wmi_platform_query(struct msi_wmi_platform_data *data,
+				  enum msi_wmi_platform_method method, u8 *input,
+				  size_t input_length, u8 *output, size_t output_length)
 {
 	struct acpi_buffer out = { ACPI_ALLOCATE_BUFFER, NULL };
 	struct acpi_buffer in = {
@@ -147,9 +155,15 @@ static int msi_wmi_platform_query(struct wmi_device *wdev, enum msi_wmi_platform
 	if (!input_length || !output_length)
 		return -EINVAL;
 
-	status = wmidev_evaluate_method(wdev, 0x0, method, &in, &out);
-	if (ACPI_FAILURE(status))
-		return -EIO;
+	/*
+	 * The ACPI control method responsible for handling the WMI method calls
+	 * is not thread-safe. Because of this we have to do the locking ourself.
+	 */
+	scoped_guard(mutex, &data->wmi_lock) {
+		status = wmidev_evaluate_method(data->wdev, 0x0, method, &in, &out);
+		if (ACPI_FAILURE(status))
+			return -EIO;
+	}
 
 	obj = out.pointer;
 	if (!obj)
@@ -170,22 +184,22 @@ static umode_t msi_wmi_platform_is_visible(const void *drvdata, enum hwmon_senso
 static int msi_wmi_platform_read(struct device *dev, enum hwmon_sensor_types type, u32 attr,
 				 int channel, long *val)
 {
-	struct wmi_device *wdev = dev_get_drvdata(dev);
+	struct msi_wmi_platform_data *data = dev_get_drvdata(dev);
 	u8 input[32] = { 0 };
 	u8 output[32];
-	u16 data;
+	u16 value;
 	int ret;
 
-	ret = msi_wmi_platform_query(wdev, MSI_PLATFORM_GET_FAN, input, sizeof(input), output,
+	ret = msi_wmi_platform_query(data, MSI_PLATFORM_GET_FAN, input, sizeof(input), output,
 				     sizeof(output));
 	if (ret < 0)
 		return ret;
 
-	data = get_unaligned_be16(&output[channel * 2 + 1]);
-	if (!data)
+	value = get_unaligned_be16(&output[channel * 2 + 1]);
+	if (!value)
 		*val = 0;
 	else
-		*val = 480000 / data;
+		*val = 480000 / value;
 
 	return 0;
 }
@@ -231,7 +245,7 @@ static ssize_t msi_wmi_platform_write(struct file *fp, const char __user *input,
 		return ret;
 
 	down_write(&data->buffer_lock);
-	ret = msi_wmi_platform_query(data->wdev, data->method, payload, data->length, data->buffer,
+	ret = msi_wmi_platform_query(data->data, data->method, payload, data->length, data->buffer,
 				     data->length);
 	up_write(&data->buffer_lock);
 
@@ -277,17 +291,17 @@ static void msi_wmi_platform_debugfs_remove(void *data)
 	debugfs_remove_recursive(dir);
 }
 
-static void msi_wmi_platform_debugfs_add(struct wmi_device *wdev, struct dentry *dir,
+static void msi_wmi_platform_debugfs_add(struct msi_wmi_platform_data *drvdata, struct dentry *dir,
 					 const char *name, enum msi_wmi_platform_method method)
 {
 	struct msi_wmi_platform_debugfs_data *data;
 	struct dentry *entry;
 
-	data = devm_kzalloc(&wdev->dev, sizeof(*data), GFP_KERNEL);
+	data = devm_kzalloc(&drvdata->wdev->dev, sizeof(*data), GFP_KERNEL);
 	if (!data)
 		return;
 
-	data->wdev = wdev;
+	data->data = drvdata;
 	data->method = method;
 	init_rwsem(&data->buffer_lock);
 
@@ -298,82 +312,82 @@ static void msi_wmi_platform_debugfs_add(struct wmi_device *wdev, struct dentry
 
 	entry = debugfs_create_file(name, 0600, dir, data, &msi_wmi_platform_debugfs_fops);
 	if (IS_ERR(entry))
-		devm_kfree(&wdev->dev, data);
+		devm_kfree(&drvdata->wdev->dev, data);
 }
 
-static void msi_wmi_platform_debugfs_init(struct wmi_device *wdev)
+static void msi_wmi_platform_debugfs_init(struct msi_wmi_platform_data *data)
 {
 	struct dentry *dir;
 	char dir_name[64];
 	int ret, method;
 
-	scnprintf(dir_name, ARRAY_SIZE(dir_name), "%s-%s", DRIVER_NAME, dev_name(&wdev->dev));
+	scnprintf(dir_name, ARRAY_SIZE(dir_name), "%s-%s", DRIVER_NAME, dev_name(&data->wdev->dev));
 
 	dir = debugfs_create_dir(dir_name, NULL);
 	if (IS_ERR(dir))
 		return;
 
-	ret = devm_add_action_or_reset(&wdev->dev, msi_wmi_platform_debugfs_remove, dir);
+	ret = devm_add_action_or_reset(&data->wdev->dev, msi_wmi_platform_debugfs_remove, dir);
 	if (ret < 0)
 		return;
 
 	for (method = MSI_PLATFORM_GET_PACKAGE; method <= MSI_PLATFORM_GET_WMI; method++)
-		msi_wmi_platform_debugfs_add(wdev, dir, msi_wmi_platform_debugfs_names[method - 1],
+		msi_wmi_platform_debugfs_add(data, dir, msi_wmi_platform_debugfs_names[method - 1],
 					     method);
 }
 
-static int msi_wmi_platform_hwmon_init(struct wmi_device *wdev)
+static int msi_wmi_platform_hwmon_init(struct msi_wmi_platform_data *data)
 {
 	struct device *hdev;
 
-	hdev = devm_hwmon_device_register_with_info(&wdev->dev, "msi_wmi_platform", wdev,
+	hdev = devm_hwmon_device_register_with_info(&data->wdev->dev, "msi_wmi_platform", data,
 						    &msi_wmi_platform_chip_info, NULL);
 
 	return PTR_ERR_OR_ZERO(hdev);
 }
 
-static int msi_wmi_platform_ec_init(struct wmi_device *wdev)
+static int msi_wmi_platform_ec_init(struct msi_wmi_platform_data *data)
 {
 	u8 input[32] = { 0 };
 	u8 output[32];
 	u8 flags;
 	int ret;
 
-	ret = msi_wmi_platform_query(wdev, MSI_PLATFORM_GET_EC, input, sizeof(input), output,
+	ret = msi_wmi_platform_query(data, MSI_PLATFORM_GET_EC, input, sizeof(input), output,
 				     sizeof(output));
 	if (ret < 0)
 		return ret;
 
 	flags = output[MSI_PLATFORM_EC_FLAGS_OFFSET];
 
-	dev_dbg(&wdev->dev, "EC RAM version %lu.%lu\n",
+	dev_dbg(&data->wdev->dev, "EC RAM version %lu.%lu\n",
 		FIELD_GET(MSI_PLATFORM_EC_MAJOR_MASK, flags),
 		FIELD_GET(MSI_PLATFORM_EC_MINOR_MASK, flags));
-	dev_dbg(&wdev->dev, "EC firmware version %.28s\n",
+	dev_dbg(&data->wdev->dev, "EC firmware version %.28s\n",
 		&output[MSI_PLATFORM_EC_VERSION_OFFSET]);
 
 	if (!(flags & MSI_PLATFORM_EC_IS_TIGERLAKE)) {
 		if (!force)
 			return -ENODEV;
 
-		dev_warn(&wdev->dev, "Loading on a non-Tigerlake platform\n");
+		dev_warn(&data->wdev->dev, "Loading on a non-Tigerlake platform\n");
 	}
 
 	return 0;
 }
 
-static int msi_wmi_platform_init(struct wmi_device *wdev)
+static int msi_wmi_platform_init(struct msi_wmi_platform_data *data)
 {
 	u8 input[32] = { 0 };
 	u8 output[32];
 	int ret;
 
-	ret = msi_wmi_platform_query(wdev, MSI_PLATFORM_GET_WMI, input, sizeof(input), output,
+	ret = msi_wmi_platform_query(data, MSI_PLATFORM_GET_WMI, input, sizeof(input), output,
 				     sizeof(output));
 	if (ret < 0)
 		return ret;
 
-	dev_dbg(&wdev->dev, "WMI interface version %u.%u\n",
+	dev_dbg(&data->wdev->dev, "WMI interface version %u.%u\n",
 		output[MSI_PLATFORM_WMI_MAJOR_OFFSET],
 		output[MSI_PLATFORM_WMI_MINOR_OFFSET]);
 
@@ -381,7 +395,8 @@ static int msi_wmi_platform_init(struct wmi_device *wdev)
 		if (!force)
 			return -ENODEV;
 
-		dev_warn(&wdev->dev, "Loading despite unsupported WMI interface version (%u.%u)\n",
+		dev_warn(&data->wdev->dev,
+			 "Loading despite unsupported WMI interface version (%u.%u)\n",
 			 output[MSI_PLATFORM_WMI_MAJOR_OFFSET],
 			 output[MSI_PLATFORM_WMI_MINOR_OFFSET]);
 	}
@@ -391,19 +406,31 @@ static int msi_wmi_platform_init(struct wmi_device *wdev)
 
 static int msi_wmi_platform_probe(struct wmi_device *wdev, const void *context)
 {
+	struct msi_wmi_platform_data *data;
 	int ret;
 
-	ret = msi_wmi_platform_init(wdev);
+	data = devm_kzalloc(&wdev->dev, sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	data->wdev = wdev;
+	dev_set_drvdata(&wdev->dev, data);
+
+	ret = devm_mutex_init(&wdev->dev, &data->wmi_lock);
+	if (ret < 0)
+		return ret;
+
+	ret = msi_wmi_platform_init(data);
 	if (ret < 0)
 		return ret;
 
-	ret = msi_wmi_platform_ec_init(wdev);
+	ret = msi_wmi_platform_ec_init(data);
 	if (ret < 0)
 		return ret;
 
-	msi_wmi_platform_debugfs_init(wdev);
+	msi_wmi_platform_debugfs_init(data);
 
-	return msi_wmi_platform_hwmon_init(wdev);
+	return msi_wmi_platform_hwmon_init(data);
 }
 
 static const struct wmi_device_id msi_wmi_platform_id_table[] = {
diff --git a/drivers/platform/x86/serdev_helpers.h b/drivers/platform/x86/serdev_helpers.h
index bcf3a0c356ea..3bc7fd8e1e19 100644
--- a/drivers/platform/x86/serdev_helpers.h
+++ b/drivers/platform/x86/serdev_helpers.h
@@ -35,7 +35,7 @@ get_serdev_controller(const char *serial_ctrl_hid,
 	ctrl_adev = acpi_dev_get_first_match_dev(serial_ctrl_hid, serial_ctrl_uid, -1);
 	if (!ctrl_adev) {
 		pr_err("error could not get %s/%s serial-ctrl adev\n",
-		       serial_ctrl_hid, serial_ctrl_uid);
+		       serial_ctrl_hid, serial_ctrl_uid ?: "*");
 		return ERR_PTR(-ENODEV);
 	}
 
@@ -43,7 +43,7 @@ get_serdev_controller(const char *serial_ctrl_hid,
 	ctrl_dev = get_device(acpi_get_first_physical_node(ctrl_adev));
 	if (!ctrl_dev) {
 		pr_err("error could not get %s/%s serial-ctrl physical node\n",
-		       serial_ctrl_hid, serial_ctrl_uid);
+		       serial_ctrl_hid, serial_ctrl_uid ?: "*");
 		ctrl_dev = ERR_PTR(-ENODEV);
 		goto put_ctrl_adev;
 	}
diff --git a/drivers/platform/x86/think-lmi.c b/drivers/platform/x86/think-lmi.c
index 4cfb53206cb8..6ad2af46248b 100644
--- a/drivers/platform/x86/think-lmi.c
+++ b/drivers/platform/x86/think-lmi.c
@@ -192,7 +192,6 @@ static const char * const level_options[] = {
 	[TLMI_LEVEL_MASTER] = "master",
 };
 static struct think_lmi tlmi_priv;
-static const struct class *fw_attr_class;
 static DEFINE_MUTEX(tlmi_mutex);
 
 static inline struct tlmi_pwd_setting *to_tlmi_pwd_setting(struct kobject *kobj)
@@ -907,6 +906,7 @@ static const struct attribute_group auth_attr_group = {
 	.is_visible = auth_attr_is_visible,
 	.attrs = auth_attrs,
 };
+__ATTRIBUTE_GROUPS(auth_attr);
 
 /* ---- Attributes sysfs --------------------------------------------------------- */
 static ssize_t display_name_show(struct kobject *kobj, struct kobj_attribute *attr,
@@ -995,8 +995,8 @@ static ssize_t current_value_store(struct kobject *kobj,
 			ret = -EINVAL;
 			goto out;
 		}
-		set_str = kasprintf(GFP_KERNEL, "%s,%s,%s", setting->display_name,
-					new_setting, tlmi_priv.pwd_admin->signature);
+		set_str = kasprintf(GFP_KERNEL, "%s,%s,%s", setting->name,
+				    new_setting, tlmi_priv.pwd_admin->signature);
 		if (!set_str) {
 			ret = -ENOMEM;
 			goto out;
@@ -1026,7 +1026,7 @@ static ssize_t current_value_store(struct kobject *kobj,
 				goto out;
 		}
 
-		set_str = kasprintf(GFP_KERNEL, "%s,%s;", setting->display_name,
+		set_str = kasprintf(GFP_KERNEL, "%s,%s;", setting->name,
 				    new_setting);
 		if (!set_str) {
 			ret = -ENOMEM;
@@ -1054,11 +1054,11 @@ static ssize_t current_value_store(struct kobject *kobj,
 		}
 
 		if (auth_str)
-			set_str = kasprintf(GFP_KERNEL, "%s,%s,%s", setting->display_name,
-					new_setting, auth_str);
+			set_str = kasprintf(GFP_KERNEL, "%s,%s,%s", setting->name,
+					    new_setting, auth_str);
 		else
-			set_str = kasprintf(GFP_KERNEL, "%s,%s;", setting->display_name,
-					new_setting);
+			set_str = kasprintf(GFP_KERNEL, "%s,%s;", setting->name,
+					    new_setting);
 		if (!set_str) {
 			ret = -ENOMEM;
 			goto out;
@@ -1122,6 +1122,7 @@ static const struct attribute_group tlmi_attr_group = {
 	.is_visible = attr_is_visible,
 	.attrs = tlmi_attrs,
 };
+__ATTRIBUTE_GROUPS(tlmi_attr);
 
 static void tlmi_attr_setting_release(struct kobject *kobj)
 {
@@ -1141,11 +1142,13 @@ static void tlmi_pwd_setting_release(struct kobject *kobj)
 static const struct kobj_type tlmi_attr_setting_ktype = {
 	.release        = &tlmi_attr_setting_release,
 	.sysfs_ops	= &kobj_sysfs_ops,
+	.default_groups = tlmi_attr_groups,
 };
 
 static const struct kobj_type tlmi_pwd_setting_ktype = {
 	.release        = &tlmi_pwd_setting_release,
 	.sysfs_ops	= &kobj_sysfs_ops,
+	.default_groups = auth_attr_groups,
 };
 
 static ssize_t pending_reboot_show(struct kobject *kobj, struct kobj_attribute *attr,
@@ -1314,21 +1317,18 @@ static struct kobj_attribute debug_cmd = __ATTR_WO(debug_cmd);
 /* ---- Initialisation --------------------------------------------------------- */
 static void tlmi_release_attr(void)
 {
-	int i;
+	struct kobject *pos, *n;
 
 	/* Attribute structures */
-	for (i = 0; i < TLMI_SETTINGS_COUNT; i++) {
-		if (tlmi_priv.setting[i]) {
-			sysfs_remove_group(&tlmi_priv.setting[i]->kobj, &tlmi_attr_group);
-			kobject_put(&tlmi_priv.setting[i]->kobj);
-		}
-	}
 	sysfs_remove_file(&tlmi_priv.attribute_kset->kobj, &pending_reboot.attr);
 	sysfs_remove_file(&tlmi_priv.attribute_kset->kobj, &save_settings.attr);
 
 	if (tlmi_priv.can_debug_cmd && debug_support)
 		sysfs_remove_file(&tlmi_priv.attribute_kset->kobj, &debug_cmd.attr);
 
+	list_for_each_entry_safe(pos, n, &tlmi_priv.attribute_kset->list, entry)
+		kobject_put(pos);
+
 	kset_unregister(tlmi_priv.attribute_kset);
 
 	/* Free up any saved signatures */
@@ -1336,19 +1336,8 @@ static void tlmi_release_attr(void)
 	kfree(tlmi_priv.pwd_admin->save_signature);
 
 	/* Authentication structures */
-	sysfs_remove_group(&tlmi_priv.pwd_admin->kobj, &auth_attr_group);
-	kobject_put(&tlmi_priv.pwd_admin->kobj);
-	sysfs_remove_group(&tlmi_priv.pwd_power->kobj, &auth_attr_group);
-	kobject_put(&tlmi_priv.pwd_power->kobj);
-
-	if (tlmi_priv.opcode_support) {
-		sysfs_remove_group(&tlmi_priv.pwd_system->kobj, &auth_attr_group);
-		kobject_put(&tlmi_priv.pwd_system->kobj);
-		sysfs_remove_group(&tlmi_priv.pwd_hdd->kobj, &auth_attr_group);
-		kobject_put(&tlmi_priv.pwd_hdd->kobj);
-		sysfs_remove_group(&tlmi_priv.pwd_nvme->kobj, &auth_attr_group);
-		kobject_put(&tlmi_priv.pwd_nvme->kobj);
-	}
+	list_for_each_entry_safe(pos, n, &tlmi_priv.authentication_kset->list, entry)
+		kobject_put(pos);
 
 	kset_unregister(tlmi_priv.authentication_kset);
 }
@@ -1375,11 +1364,7 @@ static int tlmi_sysfs_init(void)
 {
 	int i, ret;
 
-	ret = fw_attributes_class_get(&fw_attr_class);
-	if (ret)
-		return ret;
-
-	tlmi_priv.class_dev = device_create(fw_attr_class, NULL, MKDEV(0, 0),
+	tlmi_priv.class_dev = device_create(&firmware_attributes_class, NULL, MKDEV(0, 0),
 			NULL, "%s", "thinklmi");
 	if (IS_ERR(tlmi_priv.class_dev)) {
 		ret = PTR_ERR(tlmi_priv.class_dev);
@@ -1393,6 +1378,14 @@ static int tlmi_sysfs_init(void)
 		goto fail_device_created;
 	}
 
+	tlmi_priv.authentication_kset = kset_create_and_add("authentication", NULL,
+							    &tlmi_priv.class_dev->kobj);
+	if (!tlmi_priv.authentication_kset) {
+		kset_unregister(tlmi_priv.attribute_kset);
+		ret = -ENOMEM;
+		goto fail_device_created;
+	}
+
 	for (i = 0; i < TLMI_SETTINGS_COUNT; i++) {
 		/* Check if index is a valid setting - skip if it isn't */
 		if (!tlmi_priv.setting[i])
@@ -1409,12 +1402,8 @@ static int tlmi_sysfs_init(void)
 
 		/* Build attribute */
 		tlmi_priv.setting[i]->kobj.kset = tlmi_priv.attribute_kset;
-		ret = kobject_add(&tlmi_priv.setting[i]->kobj, NULL,
-				  "%s", tlmi_priv.setting[i]->display_name);
-		if (ret)
-			goto fail_create_attr;
-
-		ret = sysfs_create_group(&tlmi_priv.setting[i]->kobj, &tlmi_attr_group);
+		ret = kobject_init_and_add(&tlmi_priv.setting[i]->kobj, &tlmi_attr_setting_ktype,
+					   NULL, "%s", tlmi_priv.setting[i]->display_name);
 		if (ret)
 			goto fail_create_attr;
 	}
@@ -1434,55 +1423,34 @@ static int tlmi_sysfs_init(void)
 	}
 
 	/* Create authentication entries */
-	tlmi_priv.authentication_kset = kset_create_and_add("authentication", NULL,
-								&tlmi_priv.class_dev->kobj);
-	if (!tlmi_priv.authentication_kset) {
-		ret = -ENOMEM;
-		goto fail_create_attr;
-	}
 	tlmi_priv.pwd_admin->kobj.kset = tlmi_priv.authentication_kset;
-	ret = kobject_add(&tlmi_priv.pwd_admin->kobj, NULL, "%s", "Admin");
-	if (ret)
-		goto fail_create_attr;
-
-	ret = sysfs_create_group(&tlmi_priv.pwd_admin->kobj, &auth_attr_group);
+	ret = kobject_init_and_add(&tlmi_priv.pwd_admin->kobj, &tlmi_pwd_setting_ktype,
+				   NULL, "%s", "Admin");
 	if (ret)
 		goto fail_create_attr;
 
 	tlmi_priv.pwd_power->kobj.kset = tlmi_priv.authentication_kset;
-	ret = kobject_add(&tlmi_priv.pwd_power->kobj, NULL, "%s", "Power-on");
-	if (ret)
-		goto fail_create_attr;
-
-	ret = sysfs_create_group(&tlmi_priv.pwd_power->kobj, &auth_attr_group);
+	ret = kobject_init_and_add(&tlmi_priv.pwd_power->kobj, &tlmi_pwd_setting_ktype,
+				   NULL, "%s", "Power-on");
 	if (ret)
 		goto fail_create_attr;
 
 	if (tlmi_priv.opcode_support) {
 		tlmi_priv.pwd_system->kobj.kset = tlmi_priv.authentication_kset;
-		ret = kobject_add(&tlmi_priv.pwd_system->kobj, NULL, "%s", "System");
-		if (ret)
-			goto fail_create_attr;
-
-		ret = sysfs_create_group(&tlmi_priv.pwd_system->kobj, &auth_attr_group);
+		ret = kobject_init_and_add(&tlmi_priv.pwd_system->kobj, &tlmi_pwd_setting_ktype,
+					   NULL, "%s", "System");
 		if (ret)
 			goto fail_create_attr;
 
 		tlmi_priv.pwd_hdd->kobj.kset = tlmi_priv.authentication_kset;
-		ret = kobject_add(&tlmi_priv.pwd_hdd->kobj, NULL, "%s", "HDD");
-		if (ret)
-			goto fail_create_attr;
-
-		ret = sysfs_create_group(&tlmi_priv.pwd_hdd->kobj, &auth_attr_group);
+		ret = kobject_init_and_add(&tlmi_priv.pwd_hdd->kobj, &tlmi_pwd_setting_ktype,
+					   NULL, "%s", "HDD");
 		if (ret)
 			goto fail_create_attr;
 
 		tlmi_priv.pwd_nvme->kobj.kset = tlmi_priv.authentication_kset;
-		ret = kobject_add(&tlmi_priv.pwd_nvme->kobj, NULL, "%s", "NVMe");
-		if (ret)
-			goto fail_create_attr;
-
-		ret = sysfs_create_group(&tlmi_priv.pwd_nvme->kobj, &auth_attr_group);
+		ret = kobject_init_and_add(&tlmi_priv.pwd_nvme->kobj, &tlmi_pwd_setting_ktype,
+					   NULL, "%s", "NVMe");
 		if (ret)
 			goto fail_create_attr;
 	}
@@ -1492,9 +1460,8 @@ static int tlmi_sysfs_init(void)
 fail_create_attr:
 	tlmi_release_attr();
 fail_device_created:
-	device_destroy(fw_attr_class, MKDEV(0, 0));
+	device_unregister(tlmi_priv.class_dev);
 fail_class_created:
-	fw_attributes_class_put();
 	return ret;
 }
 
@@ -1516,8 +1483,6 @@ static struct tlmi_pwd_setting *tlmi_create_auth(const char *pwd_type,
 	new_pwd->maxlen = tlmi_priv.pwdcfg.core.max_length;
 	new_pwd->index = 0;
 
-	kobject_init(&new_pwd->kobj, &tlmi_pwd_setting_ktype);
-
 	return new_pwd;
 }
 
@@ -1568,9 +1533,6 @@ static int tlmi_analyze(void)
 			continue;
 		}
 
-		/* It is not allowed to have '/' for file name. Convert it into '\'. */
-		strreplace(item, '/', '\\');
-
 		/* Remove the value part */
 		strreplace(item, ',', '\0');
 
@@ -1582,11 +1544,16 @@ static int tlmi_analyze(void)
 			goto fail_clear_attr;
 		}
 		setting->index = i;
+
+		strscpy(setting->name, item);
+		/* It is not allowed to have '/' for file name. Convert it into '\'. */
+		strreplace(item, '/', '\\');
 		strscpy(setting->display_name, item);
+
 		/* If BIOS selections supported, load those */
 		if (tlmi_priv.can_get_bios_selections) {
-			ret = tlmi_get_bios_selections(setting->display_name,
-					&setting->possible_values);
+			ret = tlmi_get_bios_selections(setting->name,
+						       &setting->possible_values);
 			if (ret || !setting->possible_values)
 				pr_info("Error retrieving possible values for %d : %s\n",
 						i, setting->display_name);
@@ -1619,7 +1586,6 @@ static int tlmi_analyze(void)
 		if (setting->possible_values)
 			strreplace(setting->possible_values, ',', ';');
 
-		kobject_init(&setting->kobj, &tlmi_attr_setting_ktype);
 		tlmi_priv.setting[i] = setting;
 		kfree(item);
 	}
@@ -1715,8 +1681,7 @@ fail_clear_attr:
 static void tlmi_remove(struct wmi_device *wdev)
 {
 	tlmi_release_attr();
-	device_destroy(fw_attr_class, MKDEV(0, 0));
-	fw_attributes_class_put();
+	device_unregister(tlmi_priv.class_dev);
 }
 
 static int tlmi_probe(struct wmi_device *wdev, const void *context)
diff --git a/drivers/platform/x86/think-lmi.h b/drivers/platform/x86/think-lmi.h
index e1975ffebeb4..7f9632a53736 100644
--- a/drivers/platform/x86/think-lmi.h
+++ b/drivers/platform/x86/think-lmi.h
@@ -84,6 +84,7 @@ struct tlmi_pwd_setting {
 struct tlmi_attr_setting {
 	struct kobject kobj;
 	int index;
+	char name[TLMI_SETTINGS_MAXLEN];
 	char display_name[TLMI_SETTINGS_MAXLEN];
 	char *possible_values;
 };
diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c
index 2cfb2ac3f465..2c67d9758e6b 100644
--- a/drivers/platform/x86/thinkpad_acpi.c
+++ b/drivers/platform/x86/thinkpad_acpi.c
@@ -232,6 +232,7 @@ enum tpacpi_hkey_event_t {
 	/* Thermal events */
 	TP_HKEY_EV_ALARM_BAT_HOT	= 0x6011, /* battery too hot */
 	TP_HKEY_EV_ALARM_BAT_XHOT	= 0x6012, /* battery critically hot */
+	TP_HKEY_EV_ALARM_BAT_LIM_CHANGE	= 0x6013, /* battery charge limit changed*/
 	TP_HKEY_EV_ALARM_SENSOR_HOT	= 0x6021, /* sensor too hot */
 	TP_HKEY_EV_ALARM_SENSOR_XHOT	= 0x6022, /* sensor critically hot */
 	TP_HKEY_EV_THM_TABLE_CHANGED	= 0x6030, /* windows; thermal table changed */
@@ -560,12 +561,12 @@ static unsigned long __init tpacpi_check_quirks(
 	return 0;
 }
 
-static inline bool __pure __init tpacpi_is_lenovo(void)
+static __always_inline bool __pure __init tpacpi_is_lenovo(void)
 {
 	return thinkpad_id.vendor == PCI_VENDOR_ID_LENOVO;
 }
 
-static inline bool __pure __init tpacpi_is_ibm(void)
+static __always_inline bool __pure __init tpacpi_is_ibm(void)
 {
 	return thinkpad_id.vendor == PCI_VENDOR_ID_IBM;
 }
@@ -3778,6 +3779,10 @@ static bool hotkey_notify_6xxx(const u32 hkey, bool *send_acpi_ev)
 		pr_alert("THERMAL EMERGENCY: battery is extremely hot!\n");
 		/* recommended action: immediate sleep/hibernate */
 		break;
+	case TP_HKEY_EV_ALARM_BAT_LIM_CHANGE:
+		pr_debug("Battery Info: battery charge threshold changed\n");
+		/* User changed charging threshold. No action needed */
+		return true;
 	case TP_HKEY_EV_ALARM_SENSOR_HOT:
 		pr_crit("THERMAL ALARM: a sensor reports something is too hot!\n");
 		/* recommended action: warn user through gui, that */
@@ -7883,6 +7888,7 @@ static struct ibm_struct volume_driver_data = {
 
 #define FAN_NS_CTRL_STATUS	BIT(2)		/* Bit which determines control is enabled or not */
 #define FAN_NS_CTRL		BIT(4)		/* Bit which determines control is by host or EC */
+#define FAN_CLOCK_TPM		(22500*60)	/* Ticks per minute for a 22.5 kHz clock */
 
 enum {					/* Fan control constants */
 	fan_status_offset = 0x2f,	/* EC register 0x2f */
@@ -7938,6 +7944,7 @@ static int fan_watchdog_maxinterval;
 
 static bool fan_with_ns_addr;
 static bool ecfw_with_fan_dec_rpm;
+static bool fan_speed_in_tpr;
 
 static struct mutex fan_mutex;
 
@@ -8140,8 +8147,11 @@ static int fan_get_speed(unsigned int *speed)
 			     !acpi_ec_read(fan_rpm_offset + 1, &hi)))
 			return -EIO;
 
-		if (likely(speed))
+		if (likely(speed)) {
 			*speed = (hi << 8) | lo;
+			if (fan_speed_in_tpr && *speed != 0)
+				*speed = FAN_CLOCK_TPM / *speed;
+		}
 		break;
 	case TPACPI_FAN_RD_TPEC_NS:
 		if (!acpi_ec_read(fan_rpm_status_ns, &lo))
@@ -8174,8 +8184,11 @@ static int fan2_get_speed(unsigned int *speed)
 		if (rc)
 			return -EIO;
 
-		if (likely(speed))
+		if (likely(speed)) {
 			*speed = (hi << 8) | lo;
+			if (fan_speed_in_tpr && *speed != 0)
+				*speed = FAN_CLOCK_TPM / *speed;
+		}
 		break;
 
 	case TPACPI_FAN_RD_TPEC_NS:
@@ -8786,6 +8799,8 @@ static const struct attribute_group fan_driver_attr_group = {
 #define TPACPI_FAN_NOFAN	0x0008		/* no fan available */
 #define TPACPI_FAN_NS		0x0010		/* For EC with non-Standard register addresses */
 #define TPACPI_FAN_DECRPM	0x0020		/* For ECFW's with RPM in register as decimal */
+#define TPACPI_FAN_TPR		0x0040		/* Fan speed is in Ticks Per Revolution */
+#define TPACPI_FAN_NOACPI	0x0080		/* Don't use ACPI methods even if detected */
 
 static const struct tpacpi_quirk fan_quirk_table[] __initconst = {
 	TPACPI_QEC_IBM('1', 'Y', TPACPI_FAN_Q1),
@@ -8815,6 +8830,10 @@ static const struct tpacpi_quirk fan_quirk_table[] __initconst = {
 	TPACPI_Q_LNV3('R', '0', 'V', TPACPI_FAN_NS),	/* 11e Gen5 KL-Y */
 	TPACPI_Q_LNV3('N', '1', 'O', TPACPI_FAN_NOFAN),	/* X1 Tablet (2nd gen) */
 	TPACPI_Q_LNV3('R', '0', 'Q', TPACPI_FAN_DECRPM),/* L480 */
+	TPACPI_Q_LNV('8', 'F', TPACPI_FAN_TPR),		/* ThinkPad x120e */
+	TPACPI_Q_LNV3('R', '0', '0', TPACPI_FAN_NOACPI),/* E560 */
+	TPACPI_Q_LNV3('R', '1', '2', TPACPI_FAN_NOACPI),/* T495 */
+	TPACPI_Q_LNV3('R', '1', '3', TPACPI_FAN_NOACPI),/* T495s */
 };
 
 static int __init fan_init(struct ibm_init_struct *iibm)
@@ -8866,6 +8885,13 @@ static int __init fan_init(struct ibm_init_struct *iibm)
 		tp_features.fan_ctrl_status_undef = 1;
 	}
 
+	if (quirks & TPACPI_FAN_NOACPI) {
+		/* E560, T495, T495s */
+		pr_info("Ignoring buggy ACPI fan access method\n");
+		fang_handle = NULL;
+		fanw_handle = NULL;
+	}
+
 	if (gfan_handle) {
 		/* 570, 600e/x, 770e, 770x */
 		fan_status_access_mode = TPACPI_FAN_RD_ACPI_GFAN;
@@ -8885,6 +8911,8 @@ static int __init fan_init(struct ibm_init_struct *iibm)
 
 			if (quirks & TPACPI_FAN_Q1)
 				fan_quirk1_setup();
+			if (quirks & TPACPI_FAN_TPR)
+				fan_speed_in_tpr = true;
 			/* Try and probe the 2nd fan */
 			tp_features.second_fan = 1; /* needed for get_speed to work */
 			res = fan2_get_speed(&speed);
@@ -9958,6 +9986,7 @@ static const struct tpacpi_quirk battery_quirk_table[] __initconst = {
 	 * Individual addressing is broken on models that expose the
 	 * primary battery as BAT1.
 	 */
+	TPACPI_Q_LNV('G', '8', true),       /* ThinkPad X131e */
 	TPACPI_Q_LNV('8', 'F', true),       /* Thinkpad X120e */
 	TPACPI_Q_LNV('J', '7', true),       /* B5400 */
 	TPACPI_Q_LNV('J', 'I', true),       /* Thinkpad 11e */
@@ -10317,6 +10346,10 @@ static struct ibm_struct proxsensor_driver_data = {
 #define DYTC_MODE_PSC_BALANCE  5  /* Default mode aka balanced */
 #define DYTC_MODE_PSC_PERFORM  7  /* High power mode aka performance */
 
+#define DYTC_MODE_PSCV9_LOWPOWER 1  /* Low power mode */
+#define DYTC_MODE_PSCV9_BALANCE  3  /* Default mode aka balanced */
+#define DYTC_MODE_PSCV9_PERFORM  4  /* High power mode aka performance */
+
 #define DYTC_ERR_MASK       0xF  /* Bits 0-3 in cmd result are the error result */
 #define DYTC_ERR_SUCCESS      1  /* CMD completed successful */
 
@@ -10337,6 +10370,10 @@ static int dytc_capabilities;
 static bool dytc_mmc_get_available;
 static int profile_force;
 
+static int platform_psc_profile_lowpower = DYTC_MODE_PSC_LOWPOWER;
+static int platform_psc_profile_balanced = DYTC_MODE_PSC_BALANCE;
+static int platform_psc_profile_performance = DYTC_MODE_PSC_PERFORM;
+
 static int convert_dytc_to_profile(int funcmode, int dytcmode,
 		enum platform_profile_option *profile)
 {
@@ -10358,19 +10395,15 @@ static int convert_dytc_to_profile(int funcmode, int dytcmode,
 		}
 		return 0;
 	case DYTC_FUNCTION_PSC:
-		switch (dytcmode) {
-		case DYTC_MODE_PSC_LOWPOWER:
+		if (dytcmode == platform_psc_profile_lowpower)
 			*profile = PLATFORM_PROFILE_LOW_POWER;
-			break;
-		case DYTC_MODE_PSC_BALANCE:
+		else if (dytcmode == platform_psc_profile_balanced)
 			*profile =  PLATFORM_PROFILE_BALANCED;
-			break;
-		case DYTC_MODE_PSC_PERFORM:
+		else if (dytcmode == platform_psc_profile_performance)
 			*profile =  PLATFORM_PROFILE_PERFORMANCE;
-			break;
-		default: /* Unknown mode */
+		else
 			return -EINVAL;
-		}
+
 		return 0;
 	case DYTC_FUNCTION_AMT:
 		/* For now return balanced. It's the closest we have to 'auto' */
@@ -10391,19 +10424,19 @@ static int convert_profile_to_dytc(enum platform_profile_option profile, int *pe
 		if (dytc_capabilities & BIT(DYTC_FC_MMC))
 			*perfmode = DYTC_MODE_MMC_LOWPOWER;
 		else if (dytc_capabilities & BIT(DYTC_FC_PSC))
-			*perfmode = DYTC_MODE_PSC_LOWPOWER;
+			*perfmode = platform_psc_profile_lowpower;
 		break;
 	case PLATFORM_PROFILE_BALANCED:
 		if (dytc_capabilities & BIT(DYTC_FC_MMC))
 			*perfmode = DYTC_MODE_MMC_BALANCE;
 		else if (dytc_capabilities & BIT(DYTC_FC_PSC))
-			*perfmode = DYTC_MODE_PSC_BALANCE;
+			*perfmode = platform_psc_profile_balanced;
 		break;
 	case PLATFORM_PROFILE_PERFORMANCE:
 		if (dytc_capabilities & BIT(DYTC_FC_MMC))
 			*perfmode = DYTC_MODE_MMC_PERFORM;
 		else if (dytc_capabilities & BIT(DYTC_FC_PSC))
-			*perfmode = DYTC_MODE_PSC_PERFORM;
+			*perfmode = platform_psc_profile_performance;
 		break;
 	default: /* Unknown profile */
 		return -EOPNOTSUPP;
@@ -10592,6 +10625,7 @@ static int tpacpi_dytc_profile_init(struct ibm_init_struct *iibm)
 	if (output & BIT(DYTC_QUERY_ENABLE_BIT))
 		dytc_version = (output >> DYTC_QUERY_REV_BIT) & 0xF;
 
+	dbg_printk(TPACPI_DBG_INIT, "DYTC version %d\n", dytc_version);
 	/* Check DYTC is enabled and supports mode setting */
 	if (dytc_version < 5)
 		return -ENODEV;
@@ -10630,6 +10664,11 @@ static int tpacpi_dytc_profile_init(struct ibm_init_struct *iibm)
 		}
 	} else if (dytc_capabilities & BIT(DYTC_FC_PSC)) { /* PSC MODE */
 		pr_debug("PSC is supported\n");
+		if (dytc_version >= 9) { /* update profiles for DYTC 9 and up */
+			platform_psc_profile_lowpower = DYTC_MODE_PSCV9_LOWPOWER;
+			platform_psc_profile_balanced = DYTC_MODE_PSCV9_BALANCE;
+			platform_psc_profile_performance = DYTC_MODE_PSCV9_PERFORM;
+		}
 	} else {
 		dbg_printk(TPACPI_DBG_INIT, "No DYTC support available\n");
 		return -ENODEV;
@@ -11438,6 +11477,8 @@ static int __must_check __init get_thinkpad_model_data(
 		tp->vendor = PCI_VENDOR_ID_IBM;
 	else if (dmi_name_in_vendors("LENOVO"))
 		tp->vendor = PCI_VENDOR_ID_LENOVO;
+	else if (dmi_name_in_vendors("NEC"))
+		tp->vendor = PCI_VENDOR_ID_LENOVO;
 	else
 		return 0;
 
diff --git a/drivers/platform/x86/x86-android-tablets/Kconfig b/drivers/platform/x86/x86-android-tablets/Kconfig
index 88d9e8f2ff24..c98dfbdfb9dd 100644
--- a/drivers/platform/x86/x86-android-tablets/Kconfig
+++ b/drivers/platform/x86/x86-android-tablets/Kconfig
@@ -8,6 +8,7 @@ config X86_ANDROID_TABLETS
 	depends on I2C && SPI && SERIAL_DEV_BUS && ACPI && EFI && GPIOLIB && PMIC_OPREGION
 	select NEW_LEDS
 	select LEDS_CLASS
+	select POWER_SUPPLY
 	help
 	  X86 tablets which ship with Android as (part of) the factory image
 	  typically have various problems with their DSDTs. The factory kernels
diff --git a/drivers/platform/x86/x86-android-tablets/lenovo.c b/drivers/platform/x86/x86-android-tablets/lenovo.c
index ae087f1471c1..a60efbaf4817 100644
--- a/drivers/platform/x86/x86-android-tablets/lenovo.c
+++ b/drivers/platform/x86/x86-android-tablets/lenovo.c
@@ -601,7 +601,7 @@ static const struct regulator_init_data lenovo_yoga_tab2_1380_bq24190_vbus_init_
 	.num_consumer_supplies = 1,
 };
 
-struct bq24190_platform_data lenovo_yoga_tab2_1380_bq24190_pdata = {
+static struct bq24190_platform_data lenovo_yoga_tab2_1380_bq24190_pdata = {
 	.regulator_init_data = &lenovo_yoga_tab2_1380_bq24190_vbus_init_data,
 };
 
@@ -726,7 +726,7 @@ static const struct platform_device_info lenovo_yoga_tab2_1380_pdevs[] __initcon
 	},
 };
 
-const char * const lenovo_yoga_tab2_1380_modules[] __initconst = {
+static const char * const lenovo_yoga_tab2_1380_modules[] __initconst = {
 	"bq24190_charger",            /* For the Vbus regulator for lc824206xa */
 	NULL
 };
diff --git a/drivers/pmdomain/amlogic/meson-secure-pwrc.c b/drivers/pmdomain/amlogic/meson-secure-pwrc.c
index 42ce41a2fe3a..ff76ea36835e 100644
--- a/drivers/pmdomain/amlogic/meson-secure-pwrc.c
+++ b/drivers/pmdomain/amlogic/meson-secure-pwrc.c
@@ -221,7 +221,7 @@ static const struct meson_secure_pwrc_domain_desc t7_pwrc_domains[] = {
 	SEC_PD(T7_VI_CLK2,	0),
 	/* ETH is for ethernet online wakeup, and should be always on */
 	SEC_PD(T7_ETH,		GENPD_FLAG_ALWAYS_ON),
-	SEC_PD(T7_ISP,		0),
+	TOP_PD(T7_ISP,		0, PWRC_T7_MIPI_ISP_ID),
 	SEC_PD(T7_MIPI_ISP,	0),
 	TOP_PD(T7_GDC,		0, PWRC_T7_NIC3_ID),
 	TOP_PD(T7_DEWARP,	0, PWRC_T7_NIC3_ID),
diff --git a/drivers/pmdomain/core.c b/drivers/pmdomain/core.c
index 88819659df83..2643525a572b 100644
--- a/drivers/pmdomain/core.c
+++ b/drivers/pmdomain/core.c
@@ -697,6 +697,37 @@ bool dev_pm_genpd_get_hwmode(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(dev_pm_genpd_get_hwmode);
 
+/**
+ * dev_pm_genpd_rpm_always_on() - Control if the PM domain can be powered off.
+ *
+ * @dev: Device for which the PM domain may need to stay on for.
+ * @on: Value to set or unset for the condition.
+ *
+ * For some usecases a consumer driver requires its device to remain power-on
+ * from the PM domain perspective during runtime. This function allows the
+ * behaviour to be dynamically controlled for a device attached to a genpd.
+ *
+ * It is assumed that the users guarantee that the genpd wouldn't be detached
+ * while this routine is getting called.
+ *
+ * Return: Returns 0 on success and negative error values on failures.
+ */
+int dev_pm_genpd_rpm_always_on(struct device *dev, bool on)
+{
+	struct generic_pm_domain *genpd;
+
+	genpd = dev_to_genpd_safe(dev);
+	if (!genpd)
+		return -ENODEV;
+
+	genpd_lock(genpd);
+	dev_gpd_data(dev)->rpm_always_on = on;
+	genpd_unlock(genpd);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(dev_pm_genpd_rpm_always_on);
+
 static int _genpd_power_on(struct generic_pm_domain *genpd, bool timed)
 {
 	unsigned int state_idx = genpd->state_idx;
@@ -868,6 +899,10 @@ static int genpd_power_off(struct generic_pm_domain *genpd, bool one_dev_on,
 		if (!pm_runtime_suspended(pdd->dev) ||
 			irq_safe_dev_in_sleep_domain(pdd->dev, genpd))
 			not_suspended++;
+
+		/* The device may need its PM domain to stay powered on. */
+		if (to_gpd_data(pdd)->rpm_always_on)
+			return -EBUSY;
 	}
 
 	if (not_suspended > 1 || (not_suspended == 1 && !one_dev_on))
@@ -2193,8 +2228,10 @@ static int genpd_alloc_data(struct generic_pm_domain *genpd)
 	return 0;
 put:
 	put_device(&genpd->dev);
-	if (genpd->free_states == genpd_free_default_power_state)
+	if (genpd->free_states == genpd_free_default_power_state) {
 		kfree(genpd->states);
+		genpd->states = NULL;
+	}
 free:
 	if (genpd_is_cpu_domain(genpd))
 		free_cpumask_var(genpd->cpus);
@@ -3043,7 +3080,7 @@ struct device *genpd_dev_pm_attach_by_id(struct device *dev,
 	/* Verify that the index is within a valid range. */
 	num_domains = of_count_phandle_with_args(dev->of_node, "power-domains",
 						 "#power-domain-cells");
-	if (index >= num_domains)
+	if (num_domains < 0 || index >= num_domains)
 		return NULL;
 
 	/* Allocate and register device on the genpd bus. */
diff --git a/drivers/pmdomain/governor.c b/drivers/pmdomain/governor.c
index d1a10eeebd16..600592f19669 100644
--- a/drivers/pmdomain/governor.c
+++ b/drivers/pmdomain/governor.c
@@ -8,6 +8,7 @@
 #include <linux/pm_domain.h>
 #include <linux/pm_qos.h>
 #include <linux/hrtimer.h>
+#include <linux/cpu.h>
 #include <linux/cpuidle.h>
 #include <linux/cpumask.h>
 #include <linux/ktime.h>
@@ -349,6 +350,8 @@ static bool cpu_power_down_ok(struct dev_pm_domain *pd)
 	struct cpuidle_device *dev;
 	ktime_t domain_wakeup, next_hrtimer;
 	ktime_t now = ktime_get();
+	struct device *cpu_dev;
+	s64 cpu_constraint, global_constraint;
 	s64 idle_duration_ns;
 	int cpu, i;
 
@@ -359,6 +362,7 @@ static bool cpu_power_down_ok(struct dev_pm_domain *pd)
 	if (!(genpd->flags & GENPD_FLAG_CPU_DOMAIN))
 		return true;
 
+	global_constraint = cpu_latency_qos_limit();
 	/*
 	 * Find the next wakeup for any of the online CPUs within the PM domain
 	 * and its subdomains. Note, we only need the genpd->cpus, as it already
@@ -372,8 +376,16 @@ static bool cpu_power_down_ok(struct dev_pm_domain *pd)
 			if (ktime_before(next_hrtimer, domain_wakeup))
 				domain_wakeup = next_hrtimer;
 		}
+
+		cpu_dev = get_cpu_device(cpu);
+		if (cpu_dev) {
+			cpu_constraint = dev_pm_qos_raw_resume_latency(cpu_dev);
+			if (cpu_constraint < global_constraint)
+				global_constraint = cpu_constraint;
+		}
 	}
 
+	global_constraint *= NSEC_PER_USEC;
 	/* The minimum idle duration is from now - until the next wakeup. */
 	idle_duration_ns = ktime_to_ns(ktime_sub(domain_wakeup, now));
 	if (idle_duration_ns <= 0)
@@ -389,8 +401,10 @@ static bool cpu_power_down_ok(struct dev_pm_domain *pd)
 	 */
 	i = genpd->state_idx;
 	do {
-		if (idle_duration_ns >= (genpd->states[i].residency_ns +
-		    genpd->states[i].power_off_latency_ns)) {
+		if ((idle_duration_ns >= (genpd->states[i].residency_ns +
+		    genpd->states[i].power_off_latency_ns)) &&
+		    (global_constraint >= (genpd->states[i].power_on_latency_ns +
+		    genpd->states[i].power_off_latency_ns))) {
 			genpd->state_idx = i;
 			return true;
 		}
diff --git a/drivers/pmdomain/imx/gpcv2.c b/drivers/pmdomain/imx/gpcv2.c
index e03c2cb39a69..0dbf1893abfa 100644
--- a/drivers/pmdomain/imx/gpcv2.c
+++ b/drivers/pmdomain/imx/gpcv2.c
@@ -1361,7 +1361,7 @@ static int imx_pgc_domain_probe(struct platform_device *pdev)
 	}
 
 	if (IS_ENABLED(CONFIG_LOCKDEP) &&
-	    of_property_read_bool(domain->dev->of_node, "power-domains"))
+	    of_property_present(domain->dev->of_node, "power-domains"))
 		lockdep_set_subclass(&domain->genpd.mlock, 1);
 
 	ret = of_genpd_add_provider_simple(domain->dev->of_node,
diff --git a/drivers/pmdomain/imx/imx8m-blk-ctrl.c b/drivers/pmdomain/imx/imx8m-blk-ctrl.c
index ca942d7929c2..8b7b175f5896 100644
--- a/drivers/pmdomain/imx/imx8m-blk-ctrl.c
+++ b/drivers/pmdomain/imx/imx8m-blk-ctrl.c
@@ -665,6 +665,11 @@ static const struct imx8m_blk_ctrl_data imx8mn_disp_blk_ctl_dev_data = {
 #define  LCDIF_1_RD_HURRY	GENMASK(15, 13)
 #define  LCDIF_0_RD_HURRY	GENMASK(12, 10)
 
+#define ISI_CACHE_CTRL		0x50
+#define  ISI_V_WR_HURRY		GENMASK(28, 26)
+#define  ISI_U_WR_HURRY		GENMASK(25, 23)
+#define  ISI_Y_WR_HURRY		GENMASK(22, 20)
+
 static int imx8mp_media_power_notifier(struct notifier_block *nb,
 				unsigned long action, void *data)
 {
@@ -694,6 +699,11 @@ static int imx8mp_media_power_notifier(struct notifier_block *nb,
 		regmap_set_bits(bc->regmap, LCDIF_ARCACHE_CTRL,
 				FIELD_PREP(LCDIF_1_RD_HURRY, 7) |
 				FIELD_PREP(LCDIF_0_RD_HURRY, 7));
+		/* Same here for ISI */
+		regmap_set_bits(bc->regmap, ISI_CACHE_CTRL,
+				FIELD_PREP(ISI_V_WR_HURRY, 7) |
+				FIELD_PREP(ISI_U_WR_HURRY, 7) |
+				FIELD_PREP(ISI_Y_WR_HURRY, 7));
 	}
 
 	return NOTIFY_OK;
diff --git a/drivers/pmdomain/renesas/rcar-gen4-sysc.c b/drivers/pmdomain/renesas/rcar-gen4-sysc.c
index 66409cff2083..e001b5c25bed 100644
--- a/drivers/pmdomain/renesas/rcar-gen4-sysc.c
+++ b/drivers/pmdomain/renesas/rcar-gen4-sysc.c
@@ -338,11 +338,6 @@ static int __init rcar_gen4_sysc_pd_init(void)
 		struct rcar_gen4_sysc_pd *pd;
 		size_t n;
 
-		if (!area->name) {
-			/* Skip NULLified area */
-			continue;
-		}
-
 		n = strlen(area->name) + 1;
 		pd = kzalloc(sizeof(*pd) + n, GFP_KERNEL);
 		if (!pd) {
diff --git a/drivers/pmdomain/renesas/rcar-sysc.c b/drivers/pmdomain/renesas/rcar-sysc.c
index b99326917330..1e2948523789 100644
--- a/drivers/pmdomain/renesas/rcar-sysc.c
+++ b/drivers/pmdomain/renesas/rcar-sysc.c
@@ -396,11 +396,6 @@ static int __init rcar_sysc_pd_init(void)
 		struct rcar_sysc_pd *pd;
 		size_t n;
 
-		if (!area->name) {
-			/* Skip NULLified area */
-			continue;
-		}
-
 		n = strlen(area->name) + 1;
 		pd = kzalloc(sizeof(*pd) + n, GFP_KERNEL);
 		if (!pd) {
diff --git a/drivers/pmdomain/ti/Kconfig b/drivers/pmdomain/ti/Kconfig
index 67c608bf7ed0..5386b362a7ab 100644
--- a/drivers/pmdomain/ti/Kconfig
+++ b/drivers/pmdomain/ti/Kconfig
@@ -10,7 +10,7 @@ if SOC_TI
 config TI_SCI_PM_DOMAINS
 	tristate "TI SCI PM Domains Driver"
 	depends on TI_SCI_PROTOCOL
-	depends on PM_GENERIC_DOMAINS
+	select PM_GENERIC_DOMAINS if PM
 	help
 	  Generic power domain implementation for TI device implementing
 	  the TI SCI protocol.
diff --git a/drivers/power/reset/at91-reset.c b/drivers/power/reset/at91-reset.c
index 16512654295f..f1e0a0857a90 100644
--- a/drivers/power/reset/at91-reset.c
+++ b/drivers/power/reset/at91-reset.c
@@ -129,12 +129,11 @@ static int at91_reset(struct notifier_block *this, unsigned long mode,
 		"	str	%4, [%0, %6]\n\t"
 		/* Disable SDRAM1 accesses */
 		"1:	tst	%1, #0\n\t"
-		"	beq	2f\n\t"
 		"	strne	%3, [%1, #" __stringify(AT91_DDRSDRC_RTR) "]\n\t"
 		/* Power down SDRAM1 */
 		"	strne	%4, [%1, %6]\n\t"
 		/* Reset CPU */
-		"2:	str	%5, [%2, #" __stringify(AT91_RSTC_CR) "]\n\t"
+		"	str	%5, [%2, #" __stringify(AT91_RSTC_CR) "]\n\t"
 
 		"	b	.\n\t"
 		:
@@ -145,7 +144,7 @@ static int at91_reset(struct notifier_block *this, unsigned long mode,
 		  "r" cpu_to_le32(AT91_DDRSDRC_LPCB_POWER_DOWN),
 		  "r" (reset->data->reset_args),
 		  "r" (reset->ramc_lpr)
-		: "r4");
+	);
 
 	return NOTIFY_DONE;
 }
diff --git a/drivers/power/supply/axp20x_battery.c b/drivers/power/supply/axp20x_battery.c
index f71cc90fea12..88fbae613e8b 100644
--- a/drivers/power/supply/axp20x_battery.c
+++ b/drivers/power/supply/axp20x_battery.c
@@ -89,6 +89,8 @@
 #define AXP717_BAT_CC_MIN_UA		0
 #define AXP717_BAT_CC_MAX_UA		3008000
 
+#define AXP717_TS_PIN_DISABLE		BIT(4)
+
 struct axp20x_batt_ps;
 
 struct axp_data {
@@ -117,6 +119,7 @@ struct axp20x_batt_ps {
 	/* Maximum constant charge current */
 	unsigned int max_ccc;
 	const struct axp_data	*data;
+	bool ts_disable;
 };
 
 static int axp20x_battery_get_max_voltage(struct axp20x_batt_ps *axp20x_batt,
@@ -466,10 +469,9 @@ static int axp717_battery_get_prop(struct power_supply *psy,
 
 	/*
 	 * If a fault is detected it must also be cleared; if the
-	 * condition persists it should reappear (This is an
-	 * assumption, it's actually not documented). A restart was
-	 * not sufficient to clear the bit in testing despite the
-	 * register listed as POR.
+	 * condition persists it should reappear. A restart was not
+	 * sufficient to clear the bit in testing despite the register
+	 * listed as POR.
 	 */
 	case POWER_SUPPLY_PROP_HEALTH:
 		ret = regmap_read(axp20x_batt->regmap, AXP717_PMU_FAULT,
@@ -480,26 +482,26 @@ static int axp717_battery_get_prop(struct power_supply *psy,
 		switch (reg & AXP717_BATT_PMU_FAULT_MASK) {
 		case AXP717_BATT_UVLO_2_5V:
 			val->intval = POWER_SUPPLY_HEALTH_DEAD;
-			regmap_update_bits(axp20x_batt->regmap,
-					   AXP717_PMU_FAULT,
-					   AXP717_BATT_UVLO_2_5V,
-					   AXP717_BATT_UVLO_2_5V);
+			regmap_write_bits(axp20x_batt->regmap,
+					  AXP717_PMU_FAULT,
+					  AXP717_BATT_UVLO_2_5V,
+					  AXP717_BATT_UVLO_2_5V);
 			return 0;
 
 		case AXP717_BATT_OVER_TEMP:
 			val->intval = POWER_SUPPLY_HEALTH_HOT;
-			regmap_update_bits(axp20x_batt->regmap,
-					   AXP717_PMU_FAULT,
-					   AXP717_BATT_OVER_TEMP,
-					   AXP717_BATT_OVER_TEMP);
+			regmap_write_bits(axp20x_batt->regmap,
+					  AXP717_PMU_FAULT,
+					  AXP717_BATT_OVER_TEMP,
+					  AXP717_BATT_OVER_TEMP);
 			return 0;
 
 		case AXP717_BATT_UNDER_TEMP:
 			val->intval = POWER_SUPPLY_HEALTH_COLD;
-			regmap_update_bits(axp20x_batt->regmap,
-					   AXP717_PMU_FAULT,
-					   AXP717_BATT_UNDER_TEMP,
-					   AXP717_BATT_UNDER_TEMP);
+			regmap_write_bits(axp20x_batt->regmap,
+					  AXP717_PMU_FAULT,
+					  AXP717_BATT_UNDER_TEMP,
+					  AXP717_BATT_UNDER_TEMP);
 			return 0;
 
 		default:
@@ -984,6 +986,24 @@ static void axp717_set_battery_info(struct platform_device *pdev,
 	int ccc = info->constant_charge_current_max_ua;
 	int val;
 
+	axp_batt->ts_disable = (device_property_read_bool(axp_batt->dev,
+							  "x-powers,no-thermistor"));
+
+	/*
+	 * Under rare conditions an incorrectly programmed efuse for
+	 * the temp sensor on the PMIC may trigger a fault condition.
+	 * Allow users to hard-code if the ts pin is not used to work
+	 * around this problem. Note that this requires the battery
+	 * be correctly defined in the device tree with a monitored
+	 * battery node.
+	 */
+	if (axp_batt->ts_disable) {
+		regmap_update_bits(axp_batt->regmap,
+				   AXP717_TS_PIN_CFG,
+				   AXP717_TS_PIN_DISABLE,
+				   AXP717_TS_PIN_DISABLE);
+	}
+
 	if (vmin > 0 && axp717_set_voltage_min_design(axp_batt, vmin))
 		dev_err(&pdev->dev,
 			"couldn't set voltage_min_design\n");
diff --git a/drivers/power/supply/bq27xxx_battery.c b/drivers/power/supply/bq27xxx_battery.c
index 51fb88aca0f9..871f03d160c5 100644
--- a/drivers/power/supply/bq27xxx_battery.c
+++ b/drivers/power/supply/bq27xxx_battery.c
@@ -1913,7 +1913,6 @@ static void bq27xxx_battery_update_unlocked(struct bq27xxx_device_info *di)
 		cache.flags = -1; /* read error */
 	if (cache.flags >= 0) {
 		cache.capacity = bq27xxx_battery_read_soc(di);
-		di->cache.flags = cache.flags;
 
 		/*
 		 * On gauges with signed current reporting the current must be
@@ -2063,7 +2062,7 @@ static int bq27xxx_battery_get_property(struct power_supply *psy,
 	mutex_unlock(&di->lock);
 
 	if (psp != POWER_SUPPLY_PROP_PRESENT && di->cache.flags < 0)
-		return -ENODEV;
+		return di->cache.flags;
 
 	switch (psp) {
 	case POWER_SUPPLY_PROP_STATUS:
diff --git a/drivers/power/supply/bq27xxx_battery_i2c.c b/drivers/power/supply/bq27xxx_battery_i2c.c
index ba0d22d90429..868e95f0887e 100644
--- a/drivers/power/supply/bq27xxx_battery_i2c.c
+++ b/drivers/power/supply/bq27xxx_battery_i2c.c
@@ -6,6 +6,7 @@
  *	Andrew F. Davis <afd@ti.com>
  */
 
+#include <linux/delay.h>
 #include <linux/i2c.h>
 #include <linux/interrupt.h>
 #include <linux/module.h>
@@ -31,6 +32,7 @@ static int bq27xxx_battery_i2c_read(struct bq27xxx_device_info *di, u8 reg,
 	struct i2c_msg msg[2];
 	u8 data[2];
 	int ret;
+	int retry = 0;
 
 	if (!client->adapter)
 		return -ENODEV;
@@ -47,7 +49,16 @@ static int bq27xxx_battery_i2c_read(struct bq27xxx_device_info *di, u8 reg,
 	else
 		msg[1].len = 2;
 
-	ret = i2c_transfer(client->adapter, msg, ARRAY_SIZE(msg));
+	do {
+		ret = i2c_transfer(client->adapter, msg, ARRAY_SIZE(msg));
+		if (ret == -EBUSY && ++retry < 3) {
+			/* sleep 10 milliseconds when busy */
+			usleep_range(10000, 11000);
+			continue;
+		}
+		break;
+	} while (1);
+
 	if (ret < 0)
 		return ret;
 
diff --git a/drivers/power/supply/collie_battery.c b/drivers/power/supply/collie_battery.c
index 68390bd1004f..3daf7befc0bf 100644
--- a/drivers/power/supply/collie_battery.c
+++ b/drivers/power/supply/collie_battery.c
@@ -440,6 +440,7 @@ err_put_gpio_full:
 
 static void collie_bat_remove(struct ucb1x00_dev *dev)
 {
+	device_init_wakeup(&ucb->dev, 0);
 	free_irq(gpiod_to_irq(collie_bat_main.gpio_full), &collie_bat_main);
 	power_supply_unregister(collie_bat_bu.psy);
 	power_supply_unregister(collie_bat_main.psy);
diff --git a/drivers/power/supply/cpcap-charger.c b/drivers/power/supply/cpcap-charger.c
index 91e7292d86bb..66dc622159a6 100644
--- a/drivers/power/supply/cpcap-charger.c
+++ b/drivers/power/supply/cpcap-charger.c
@@ -688,9 +688,8 @@ static void cpcap_usb_detect(struct work_struct *work)
 		struct power_supply *battery;
 
 		battery = power_supply_get_by_name("battery");
-		if (IS_ERR_OR_NULL(battery)) {
-			dev_err(ddata->dev, "battery power_supply not available %li\n",
-					PTR_ERR(battery));
+		if (!battery) {
+			dev_err(ddata->dev, "battery power_supply not available\n");
 			return;
 		}
 
diff --git a/drivers/power/supply/da9150-fg.c b/drivers/power/supply/da9150-fg.c
index 652c1f213af1..4f28ef1bba1a 100644
--- a/drivers/power/supply/da9150-fg.c
+++ b/drivers/power/supply/da9150-fg.c
@@ -247,9 +247,9 @@ static int da9150_fg_current_avg(struct da9150_fg *fg,
 				      DA9150_QIF_SD_GAIN_SIZE);
 	da9150_fg_read_sync_end(fg);
 
-	div = (u64) (sd_gain * shunt_val * 65536ULL);
+	div = 65536ULL * sd_gain * shunt_val;
 	do_div(div, 1000000);
-	res = (u64) (iavg * 1000000ULL);
+	res = 1000000ULL * iavg;
 	do_div(res, div);
 
 	val->intval = (int) res;
diff --git a/drivers/power/supply/max14577_charger.c b/drivers/power/supply/max14577_charger.c
index b28c04157709..90d40b35256f 100644
--- a/drivers/power/supply/max14577_charger.c
+++ b/drivers/power/supply/max14577_charger.c
@@ -501,7 +501,7 @@ static struct max14577_charger_platform_data *max14577_charger_dt_init(
 static struct max14577_charger_platform_data *max14577_charger_dt_init(
 		struct platform_device *pdev)
 {
-	return NULL;
+	return ERR_PTR(-ENODATA);
 }
 #endif /* CONFIG_OF */
 
@@ -572,7 +572,7 @@ static int max14577_charger_probe(struct platform_device *pdev)
 	chg->max14577 = max14577;
 
 	chg->pdata = max14577_charger_dt_init(pdev);
-	if (IS_ERR_OR_NULL(chg->pdata))
+	if (IS_ERR(chg->pdata))
 		return PTR_ERR(chg->pdata);
 
 	ret = max14577_charger_reg_init(chg);
diff --git a/drivers/power/supply/max17040_battery.c b/drivers/power/supply/max17040_battery.c
index 51310f6e4803..c1640bc6accd 100644
--- a/drivers/power/supply/max17040_battery.c
+++ b/drivers/power/supply/max17040_battery.c
@@ -410,8 +410,9 @@ static int max17040_get_property(struct power_supply *psy,
 		if (!chip->channel_temp)
 			return -ENODATA;
 
-		iio_read_channel_processed_scale(chip->channel_temp,
-						 &val->intval, 10);
+		iio_read_channel_processed(chip->channel_temp, &val->intval);
+		val->intval /= 100; /* Convert from milli- to deci-degree */
+
 		break;
 	default:
 		return -EINVAL;
diff --git a/drivers/power/supply/max77693_charger.c b/drivers/power/supply/max77693_charger.c
index 4caac142c428..b32d88111185 100644
--- a/drivers/power/supply/max77693_charger.c
+++ b/drivers/power/supply/max77693_charger.c
@@ -608,7 +608,7 @@ static int max77693_set_charge_input_threshold_volt(struct max77693_charger *chg
 	case 4700000:
 	case 4800000:
 	case 4900000:
-		data = (uvolt - 4700000) / 100000;
+		data = ((uvolt - 4700000) / 100000) + 1;
 		break;
 	default:
 		dev_err(chg->dev, "Wrong value for charge input voltage regulation threshold\n");
diff --git a/drivers/power/supply/qcom_battmgr.c b/drivers/power/supply/qcom_battmgr.c
index f0a64c00ddaa..c2037b58fbcd 100644
--- a/drivers/power/supply/qcom_battmgr.c
+++ b/drivers/power/supply/qcom_battmgr.c
@@ -980,6 +980,8 @@ static unsigned int qcom_battmgr_sc8280xp_parse_technology(const char *chemistry
 {
 	if (!strncmp(chemistry, "LIO", BATTMGR_CHEMISTRY_LEN))
 		return POWER_SUPPLY_TECHNOLOGY_LION;
+	if (!strncmp(chemistry, "LIP", BATTMGR_CHEMISTRY_LEN))
+		return POWER_SUPPLY_TECHNOLOGY_LIPO;
 
 	pr_err("Unknown battery technology '%s'\n", chemistry);
 	return POWER_SUPPLY_TECHNOLOGY_UNKNOWN;
diff --git a/drivers/powercap/dtpm_cpu.c b/drivers/powercap/dtpm_cpu.c
index 6b6f51b21550..99390ec1481f 100644
--- a/drivers/powercap/dtpm_cpu.c
+++ b/drivers/powercap/dtpm_cpu.c
@@ -96,6 +96,8 @@ static u64 get_pd_power_uw(struct dtpm *dtpm)
 	int i;
 
 	pd = em_cpu_get(dtpm_cpu->cpu);
+	if (!pd)
+		return 0;
 
 	pd_mask = em_span_cpus(pd);
 
diff --git a/drivers/powercap/intel_rapl_common.c b/drivers/powercap/intel_rapl_common.c
index 5e793b80fd6b..c3de52e78e01 100644
--- a/drivers/powercap/intel_rapl_common.c
+++ b/drivers/powercap/intel_rapl_common.c
@@ -340,12 +340,28 @@ static int set_domain_enable(struct powercap_zone *power_zone, bool mode)
 {
 	struct rapl_domain *rd = power_zone_to_rapl_domain(power_zone);
 	struct rapl_defaults *defaults = get_defaults(rd->rp);
+	u64 val;
 	int ret;
 
 	cpus_read_lock();
 	ret = rapl_write_pl_data(rd, POWER_LIMIT1, PL_ENABLE, mode);
-	if (!ret && defaults->set_floor_freq)
+	if (ret)
+		goto end;
+
+	ret = rapl_read_pl_data(rd, POWER_LIMIT1, PL_ENABLE, false, &val);
+	if (ret)
+		goto end;
+
+	if (mode != val) {
+		pr_debug("%s cannot be %s\n", power_zone->name,
+			 str_enabled_disabled(mode));
+		goto end;
+	}
+
+	if (defaults->set_floor_freq)
 		defaults->set_floor_freq(rd, mode);
+
+end:
 	cpus_read_unlock();
 
 	return ret;
diff --git a/drivers/powercap/powercap_sys.c b/drivers/powercap/powercap_sys.c
index 52c32dcbf7d8..4112a0097338 100644
--- a/drivers/powercap/powercap_sys.c
+++ b/drivers/powercap/powercap_sys.c
@@ -627,8 +627,7 @@ struct powercap_control_type *powercap_register_control_type(
 	dev_set_name(&control_type->dev, "%s", name);
 	result = device_register(&control_type->dev);
 	if (result) {
-		if (control_type->allocated)
-			kfree(control_type);
+		put_device(&control_type->dev);
 		return ERR_PTR(result);
 	}
 	idr_init(&control_type->idr);
diff --git a/drivers/pps/clients/pps-gpio.c b/drivers/pps/clients/pps-gpio.c
index 791fdc9326dd..1412f8af15f2 100644
--- a/drivers/pps/clients/pps-gpio.c
+++ b/drivers/pps/clients/pps-gpio.c
@@ -206,16 +206,16 @@ static int pps_gpio_probe(struct platform_device *pdev)
 	}
 
 	/* register IRQ interrupt handler */
-	ret = devm_request_irq(dev, data->irq, pps_gpio_irq_handler,
-			get_irqf_trigger_flags(data), data->info.name, data);
+	ret = request_irq(data->irq, pps_gpio_irq_handler,
+			  get_irqf_trigger_flags(data), data->info.name, data);
 	if (ret) {
 		pps_unregister_source(data->pps);
 		dev_err(dev, "failed to acquire IRQ %d\n", data->irq);
 		return -EINVAL;
 	}
 
-	dev_info(data->pps->dev, "Registered IRQ %d as PPS source\n",
-		 data->irq);
+	dev_dbg(&data->pps->dev, "Registered IRQ %d as PPS source\n",
+		data->irq);
 
 	return 0;
 }
@@ -224,6 +224,7 @@ static void pps_gpio_remove(struct platform_device *pdev)
 {
 	struct pps_gpio_device_data *data = platform_get_drvdata(pdev);
 
+	free_irq(data->irq, data);
 	pps_unregister_source(data->pps);
 	del_timer_sync(&data->echo_timer);
 	/* reset echo pin in any case */
diff --git a/drivers/pps/clients/pps-ktimer.c b/drivers/pps/clients/pps-ktimer.c
index d33106bd7a29..2f465549b843 100644
--- a/drivers/pps/clients/pps-ktimer.c
+++ b/drivers/pps/clients/pps-ktimer.c
@@ -56,7 +56,7 @@ static struct pps_source_info pps_ktimer_info = {
 
 static void __exit pps_ktimer_exit(void)
 {
-	dev_info(pps->dev, "ktimer PPS source unregistered\n");
+	dev_dbg(&pps->dev, "ktimer PPS source unregistered\n");
 
 	del_timer_sync(&ktimer);
 	pps_unregister_source(pps);
@@ -74,7 +74,7 @@ static int __init pps_ktimer_init(void)
 	timer_setup(&ktimer, pps_ktimer_event, 0);
 	mod_timer(&ktimer, jiffies + HZ);
 
-	dev_info(pps->dev, "ktimer PPS source registered\n");
+	dev_dbg(&pps->dev, "ktimer PPS source registered\n");
 
 	return 0;
 }
diff --git a/drivers/pps/clients/pps-ldisc.c b/drivers/pps/clients/pps-ldisc.c
index 443d6bae19d1..fa5660f3c4b7 100644
--- a/drivers/pps/clients/pps-ldisc.c
+++ b/drivers/pps/clients/pps-ldisc.c
@@ -32,7 +32,7 @@ static void pps_tty_dcd_change(struct tty_struct *tty, bool active)
 	pps_event(pps, &ts, active ? PPS_CAPTUREASSERT :
 			PPS_CAPTURECLEAR, NULL);
 
-	dev_dbg(pps->dev, "PPS %s at %lu\n",
+	dev_dbg(&pps->dev, "PPS %s at %lu\n",
 			active ? "assert" : "clear", jiffies);
 }
 
@@ -69,7 +69,7 @@ static int pps_tty_open(struct tty_struct *tty)
 		goto err_unregister;
 	}
 
-	dev_info(pps->dev, "source \"%s\" added\n", info.path);
+	dev_dbg(&pps->dev, "source \"%s\" added\n", info.path);
 
 	return 0;
 
@@ -89,7 +89,7 @@ static void pps_tty_close(struct tty_struct *tty)
 	if (WARN_ON(!pps))
 		return;
 
-	dev_info(pps->dev, "removed\n");
+	dev_info(&pps->dev, "removed\n");
 	pps_unregister_source(pps);
 }
 
diff --git a/drivers/pps/clients/pps_parport.c b/drivers/pps/clients/pps_parport.c
index abaffb4e1c1c..24db06750297 100644
--- a/drivers/pps/clients/pps_parport.c
+++ b/drivers/pps/clients/pps_parport.c
@@ -81,7 +81,7 @@ static void parport_irq(void *handle)
 	/* check the signal (no signal means the pulse is lost this time) */
 	if (!signal_is_set(port)) {
 		local_irq_restore(flags);
-		dev_err(dev->pps->dev, "lost the signal\n");
+		dev_err(&dev->pps->dev, "lost the signal\n");
 		goto out_assert;
 	}
 
@@ -98,7 +98,7 @@ static void parport_irq(void *handle)
 	/* timeout */
 	dev->cw_err++;
 	if (dev->cw_err >= CLEAR_WAIT_MAX_ERRORS) {
-		dev_err(dev->pps->dev, "disabled clear edge capture after %d"
+		dev_err(&dev->pps->dev, "disabled clear edge capture after %d"
 				" timeouts\n", dev->cw_err);
 		dev->cw = 0;
 		dev->cw_err = 0;
diff --git a/drivers/pps/kapi.c b/drivers/pps/kapi.c
index d9d566f70ed1..92d1b62ea239 100644
--- a/drivers/pps/kapi.c
+++ b/drivers/pps/kapi.c
@@ -41,7 +41,7 @@ static void pps_add_offset(struct pps_ktime *ts, struct pps_ktime *offset)
 static void pps_echo_client_default(struct pps_device *pps, int event,
 		void *data)
 {
-	dev_info(pps->dev, "echo %s %s\n",
+	dev_info(&pps->dev, "echo %s %s\n",
 		event & PPS_CAPTUREASSERT ? "assert" : "",
 		event & PPS_CAPTURECLEAR ? "clear" : "");
 }
@@ -112,7 +112,7 @@ struct pps_device *pps_register_source(struct pps_source_info *info,
 		goto kfree_pps;
 	}
 
-	dev_info(pps->dev, "new PPS source %s\n", info->name);
+	dev_dbg(&pps->dev, "new PPS source %s\n", info->name);
 
 	return pps;
 
@@ -166,7 +166,7 @@ void pps_event(struct pps_device *pps, struct pps_event_time *ts, int event,
 	/* check event type */
 	BUG_ON((event & (PPS_CAPTUREASSERT | PPS_CAPTURECLEAR)) == 0);
 
-	dev_dbg(pps->dev, "PPS event at %lld.%09ld\n",
+	dev_dbg(&pps->dev, "PPS event at %lld.%09ld\n",
 			(s64)ts->ts_real.tv_sec, ts->ts_real.tv_nsec);
 
 	timespec_to_pps_ktime(&ts_real, ts->ts_real);
@@ -188,7 +188,7 @@ void pps_event(struct pps_device *pps, struct pps_event_time *ts, int event,
 		/* Save the time stamp */
 		pps->assert_tu = ts_real;
 		pps->assert_sequence++;
-		dev_dbg(pps->dev, "capture assert seq #%u\n",
+		dev_dbg(&pps->dev, "capture assert seq #%u\n",
 			pps->assert_sequence);
 
 		captured = ~0;
@@ -202,7 +202,7 @@ void pps_event(struct pps_device *pps, struct pps_event_time *ts, int event,
 		/* Save the time stamp */
 		pps->clear_tu = ts_real;
 		pps->clear_sequence++;
-		dev_dbg(pps->dev, "capture clear seq #%u\n",
+		dev_dbg(&pps->dev, "capture clear seq #%u\n",
 			pps->clear_sequence);
 
 		captured = ~0;
diff --git a/drivers/pps/kc.c b/drivers/pps/kc.c
index 50dc59af45be..fbd23295afd7 100644
--- a/drivers/pps/kc.c
+++ b/drivers/pps/kc.c
@@ -43,11 +43,11 @@ int pps_kc_bind(struct pps_device *pps, struct pps_bind_args *bind_args)
 			pps_kc_hardpps_mode = 0;
 			pps_kc_hardpps_dev = NULL;
 			spin_unlock_irq(&pps_kc_hardpps_lock);
-			dev_info(pps->dev, "unbound kernel"
+			dev_info(&pps->dev, "unbound kernel"
 					" consumer\n");
 		} else {
 			spin_unlock_irq(&pps_kc_hardpps_lock);
-			dev_err(pps->dev, "selected kernel consumer"
+			dev_err(&pps->dev, "selected kernel consumer"
 					" is not bound\n");
 			return -EINVAL;
 		}
@@ -57,11 +57,11 @@ int pps_kc_bind(struct pps_device *pps, struct pps_bind_args *bind_args)
 			pps_kc_hardpps_mode = bind_args->edge;
 			pps_kc_hardpps_dev = pps;
 			spin_unlock_irq(&pps_kc_hardpps_lock);
-			dev_info(pps->dev, "bound kernel consumer: "
+			dev_info(&pps->dev, "bound kernel consumer: "
 				"edge=0x%x\n", bind_args->edge);
 		} else {
 			spin_unlock_irq(&pps_kc_hardpps_lock);
-			dev_err(pps->dev, "another kernel consumer"
+			dev_err(&pps->dev, "another kernel consumer"
 					" is already bound\n");
 			return -EINVAL;
 		}
@@ -83,7 +83,7 @@ void pps_kc_remove(struct pps_device *pps)
 		pps_kc_hardpps_mode = 0;
 		pps_kc_hardpps_dev = NULL;
 		spin_unlock_irq(&pps_kc_hardpps_lock);
-		dev_info(pps->dev, "unbound kernel consumer"
+		dev_info(&pps->dev, "unbound kernel consumer"
 				" on device removal\n");
 	} else
 		spin_unlock_irq(&pps_kc_hardpps_lock);
diff --git a/drivers/pps/pps.c b/drivers/pps/pps.c
index 25d47907db17..9463232af8d2 100644
--- a/drivers/pps/pps.c
+++ b/drivers/pps/pps.c
@@ -25,7 +25,7 @@
  * Local variables
  */
 
-static dev_t pps_devt;
+static int pps_major;
 static struct class *pps_class;
 
 static DEFINE_MUTEX(pps_idr_lock);
@@ -41,6 +41,9 @@ static __poll_t pps_cdev_poll(struct file *file, poll_table *wait)
 
 	poll_wait(file, &pps->queue, wait);
 
+	if (pps->last_fetched_ev == pps->last_ev)
+		return 0;
+
 	return EPOLLIN | EPOLLRDNORM;
 }
 
@@ -62,7 +65,7 @@ static int pps_cdev_pps_fetch(struct pps_device *pps, struct pps_fdata *fdata)
 	else {
 		unsigned long ticks;
 
-		dev_dbg(pps->dev, "timeout %lld.%09d\n",
+		dev_dbg(&pps->dev, "timeout %lld.%09d\n",
 				(long long) fdata->timeout.sec,
 				fdata->timeout.nsec);
 		ticks = fdata->timeout.sec * HZ;
@@ -80,7 +83,7 @@ static int pps_cdev_pps_fetch(struct pps_device *pps, struct pps_fdata *fdata)
 
 	/* Check for pending signals */
 	if (err == -ERESTARTSYS) {
-		dev_dbg(pps->dev, "pending signal caught\n");
+		dev_dbg(&pps->dev, "pending signal caught\n");
 		return -EINTR;
 	}
 
@@ -98,7 +101,7 @@ static long pps_cdev_ioctl(struct file *file,
 
 	switch (cmd) {
 	case PPS_GETPARAMS:
-		dev_dbg(pps->dev, "PPS_GETPARAMS\n");
+		dev_dbg(&pps->dev, "PPS_GETPARAMS\n");
 
 		spin_lock_irq(&pps->lock);
 
@@ -114,7 +117,7 @@ static long pps_cdev_ioctl(struct file *file,
 		break;
 
 	case PPS_SETPARAMS:
-		dev_dbg(pps->dev, "PPS_SETPARAMS\n");
+		dev_dbg(&pps->dev, "PPS_SETPARAMS\n");
 
 		/* Check the capabilities */
 		if (!capable(CAP_SYS_TIME))
@@ -124,14 +127,14 @@ static long pps_cdev_ioctl(struct file *file,
 		if (err)
 			return -EFAULT;
 		if (!(params.mode & (PPS_CAPTUREASSERT | PPS_CAPTURECLEAR))) {
-			dev_dbg(pps->dev, "capture mode unspecified (%x)\n",
+			dev_dbg(&pps->dev, "capture mode unspecified (%x)\n",
 								params.mode);
 			return -EINVAL;
 		}
 
 		/* Check for supported capabilities */
 		if ((params.mode & ~pps->info.mode) != 0) {
-			dev_dbg(pps->dev, "unsupported capabilities (%x)\n",
+			dev_dbg(&pps->dev, "unsupported capabilities (%x)\n",
 								params.mode);
 			return -EINVAL;
 		}
@@ -144,7 +147,7 @@ static long pps_cdev_ioctl(struct file *file,
 		/* Restore the read only parameters */
 		if ((params.mode & (PPS_TSFMT_TSPEC | PPS_TSFMT_NTPFP)) == 0) {
 			/* section 3.3 of RFC 2783 interpreted */
-			dev_dbg(pps->dev, "time format unspecified (%x)\n",
+			dev_dbg(&pps->dev, "time format unspecified (%x)\n",
 								params.mode);
 			pps->params.mode |= PPS_TSFMT_TSPEC;
 		}
@@ -165,7 +168,7 @@ static long pps_cdev_ioctl(struct file *file,
 		break;
 
 	case PPS_GETCAP:
-		dev_dbg(pps->dev, "PPS_GETCAP\n");
+		dev_dbg(&pps->dev, "PPS_GETCAP\n");
 
 		err = put_user(pps->info.mode, iuarg);
 		if (err)
@@ -176,7 +179,7 @@ static long pps_cdev_ioctl(struct file *file,
 	case PPS_FETCH: {
 		struct pps_fdata fdata;
 
-		dev_dbg(pps->dev, "PPS_FETCH\n");
+		dev_dbg(&pps->dev, "PPS_FETCH\n");
 
 		err = copy_from_user(&fdata, uarg, sizeof(struct pps_fdata));
 		if (err)
@@ -186,9 +189,11 @@ static long pps_cdev_ioctl(struct file *file,
 		if (err)
 			return err;
 
-		/* Return the fetched timestamp */
+		/* Return the fetched timestamp and save last fetched event  */
 		spin_lock_irq(&pps->lock);
 
+		pps->last_fetched_ev = pps->last_ev;
+
 		fdata.info.assert_sequence = pps->assert_sequence;
 		fdata.info.clear_sequence = pps->clear_sequence;
 		fdata.info.assert_tu = pps->assert_tu;
@@ -206,7 +211,7 @@ static long pps_cdev_ioctl(struct file *file,
 	case PPS_KC_BIND: {
 		struct pps_bind_args bind_args;
 
-		dev_dbg(pps->dev, "PPS_KC_BIND\n");
+		dev_dbg(&pps->dev, "PPS_KC_BIND\n");
 
 		/* Check the capabilities */
 		if (!capable(CAP_SYS_TIME))
@@ -218,7 +223,7 @@ static long pps_cdev_ioctl(struct file *file,
 
 		/* Check for supported capabilities */
 		if ((bind_args.edge & ~pps->info.mode) != 0) {
-			dev_err(pps->dev, "unsupported capabilities (%x)\n",
+			dev_err(&pps->dev, "unsupported capabilities (%x)\n",
 					bind_args.edge);
 			return -EINVAL;
 		}
@@ -227,7 +232,7 @@ static long pps_cdev_ioctl(struct file *file,
 		if (bind_args.tsformat != PPS_TSFMT_TSPEC ||
 				(bind_args.edge & ~PPS_CAPTUREBOTH) != 0 ||
 				bind_args.consumer != PPS_KC_HARDPPS) {
-			dev_err(pps->dev, "invalid kernel consumer bind"
+			dev_err(&pps->dev, "invalid kernel consumer bind"
 					" parameters (%x)\n", bind_args.edge);
 			return -EINVAL;
 		}
@@ -259,7 +264,7 @@ static long pps_cdev_compat_ioctl(struct file *file,
 		struct pps_fdata fdata;
 		int err;
 
-		dev_dbg(pps->dev, "PPS_FETCH\n");
+		dev_dbg(&pps->dev, "PPS_FETCH\n");
 
 		err = copy_from_user(&compat, uarg, sizeof(struct pps_fdata_compat));
 		if (err)
@@ -272,9 +277,11 @@ static long pps_cdev_compat_ioctl(struct file *file,
 		if (err)
 			return err;
 
-		/* Return the fetched timestamp */
+		/* Return the fetched timestamp and save last fetched event  */
 		spin_lock_irq(&pps->lock);
 
+		pps->last_fetched_ev = pps->last_ev;
+
 		compat.info.assert_sequence = pps->assert_sequence;
 		compat.info.clear_sequence = pps->clear_sequence;
 		compat.info.current_mode = pps->current_mode;
@@ -296,20 +303,36 @@ static long pps_cdev_compat_ioctl(struct file *file,
 #define pps_cdev_compat_ioctl	NULL
 #endif
 
+static struct pps_device *pps_idr_get(unsigned long id)
+{
+	struct pps_device *pps;
+
+	mutex_lock(&pps_idr_lock);
+	pps = idr_find(&pps_idr, id);
+	if (pps)
+		get_device(&pps->dev);
+
+	mutex_unlock(&pps_idr_lock);
+	return pps;
+}
+
 static int pps_cdev_open(struct inode *inode, struct file *file)
 {
-	struct pps_device *pps = container_of(inode->i_cdev,
-						struct pps_device, cdev);
+	struct pps_device *pps = pps_idr_get(iminor(inode));
+
+	if (!pps)
+		return -ENODEV;
+
 	file->private_data = pps;
-	kobject_get(&pps->dev->kobj);
 	return 0;
 }
 
 static int pps_cdev_release(struct inode *inode, struct file *file)
 {
-	struct pps_device *pps = container_of(inode->i_cdev,
-						struct pps_device, cdev);
-	kobject_put(&pps->dev->kobj);
+	struct pps_device *pps = file->private_data;
+
+	WARN_ON(pps->id != iminor(inode));
+	put_device(&pps->dev);
 	return 0;
 }
 
@@ -331,22 +354,13 @@ static void pps_device_destruct(struct device *dev)
 {
 	struct pps_device *pps = dev_get_drvdata(dev);
 
-	cdev_del(&pps->cdev);
-
-	/* Now we can release the ID for re-use */
 	pr_debug("deallocating pps%d\n", pps->id);
-	mutex_lock(&pps_idr_lock);
-	idr_remove(&pps_idr, pps->id);
-	mutex_unlock(&pps_idr_lock);
-
-	kfree(dev);
 	kfree(pps);
 }
 
 int pps_register_cdev(struct pps_device *pps)
 {
 	int err;
-	dev_t devt;
 
 	mutex_lock(&pps_idr_lock);
 	/*
@@ -363,40 +377,29 @@ int pps_register_cdev(struct pps_device *pps)
 		goto out_unlock;
 	}
 	pps->id = err;
-	mutex_unlock(&pps_idr_lock);
-
-	devt = MKDEV(MAJOR(pps_devt), pps->id);
 
-	cdev_init(&pps->cdev, &pps_cdev_fops);
-	pps->cdev.owner = pps->info.owner;
-
-	err = cdev_add(&pps->cdev, devt, 1);
-	if (err) {
-		pr_err("%s: failed to add char device %d:%d\n",
-				pps->info.name, MAJOR(pps_devt), pps->id);
+	pps->dev.class = pps_class;
+	pps->dev.parent = pps->info.dev;
+	pps->dev.devt = MKDEV(pps_major, pps->id);
+	dev_set_drvdata(&pps->dev, pps);
+	dev_set_name(&pps->dev, "pps%d", pps->id);
+	err = device_register(&pps->dev);
+	if (err)
 		goto free_idr;
-	}
-	pps->dev = device_create(pps_class, pps->info.dev, devt, pps,
-							"pps%d", pps->id);
-	if (IS_ERR(pps->dev)) {
-		err = PTR_ERR(pps->dev);
-		goto del_cdev;
-	}
 
 	/* Override the release function with our own */
-	pps->dev->release = pps_device_destruct;
+	pps->dev.release = pps_device_destruct;
 
-	pr_debug("source %s got cdev (%d:%d)\n", pps->info.name,
-			MAJOR(pps_devt), pps->id);
+	pr_debug("source %s got cdev (%d:%d)\n", pps->info.name, pps_major,
+		 pps->id);
 
+	get_device(&pps->dev);
+	mutex_unlock(&pps_idr_lock);
 	return 0;
 
-del_cdev:
-	cdev_del(&pps->cdev);
-
 free_idr:
-	mutex_lock(&pps_idr_lock);
 	idr_remove(&pps_idr, pps->id);
+	put_device(&pps->dev);
 out_unlock:
 	mutex_unlock(&pps_idr_lock);
 	return err;
@@ -406,7 +409,13 @@ void pps_unregister_cdev(struct pps_device *pps)
 {
 	pr_debug("unregistering pps%d\n", pps->id);
 	pps->lookup_cookie = NULL;
-	device_destroy(pps_class, pps->dev->devt);
+	device_destroy(pps_class, pps->dev.devt);
+
+	/* Now we can release the ID for re-use */
+	mutex_lock(&pps_idr_lock);
+	idr_remove(&pps_idr, pps->id);
+	put_device(&pps->dev);
+	mutex_unlock(&pps_idr_lock);
 }
 
 /*
@@ -426,6 +435,11 @@ void pps_unregister_cdev(struct pps_device *pps)
  * so that it will not be used again, even if the pps device cannot
  * be removed from the idr due to pending references holding the minor
  * number in use.
+ *
+ * Since pps_idr holds a reference to the device, the returned
+ * pps_device is guaranteed to be valid until pps_unregister_cdev() is
+ * called on it. But after calling pps_unregister_cdev(), it may be
+ * freed at any time.
  */
 struct pps_device *pps_lookup_dev(void const *cookie)
 {
@@ -448,13 +462,11 @@ EXPORT_SYMBOL(pps_lookup_dev);
 static void __exit pps_exit(void)
 {
 	class_destroy(pps_class);
-	unregister_chrdev_region(pps_devt, PPS_MAX_SOURCES);
+	__unregister_chrdev(pps_major, 0, PPS_MAX_SOURCES, "pps");
 }
 
 static int __init pps_init(void)
 {
-	int err;
-
 	pps_class = class_create("pps");
 	if (IS_ERR(pps_class)) {
 		pr_err("failed to allocate class\n");
@@ -462,8 +474,9 @@ static int __init pps_init(void)
 	}
 	pps_class->dev_groups = pps_groups;
 
-	err = alloc_chrdev_region(&pps_devt, 0, PPS_MAX_SOURCES, "pps");
-	if (err < 0) {
+	pps_major = __register_chrdev(0, 0, PPS_MAX_SOURCES, "pps",
+				      &pps_cdev_fops);
+	if (pps_major < 0) {
 		pr_err("failed to allocate char device region\n");
 		goto remove_class;
 	}
@@ -476,8 +489,7 @@ static int __init pps_init(void)
 
 remove_class:
 	class_destroy(pps_class);
-
-	return err;
+	return pps_major;
 }
 
 subsys_initcall(pps_init);
diff --git a/drivers/ptp/ptp_chardev.c b/drivers/ptp/ptp_chardev.c
index ea96a14d72d1..bf6468c56419 100644
--- a/drivers/ptp/ptp_chardev.c
+++ b/drivers/ptp/ptp_chardev.c
@@ -4,6 +4,7 @@
  *
  * Copyright (C) 2010 OMICRON electronics GmbH
  */
+#include <linux/compat.h>
 #include <linux/module.h>
 #include <linux/posix-clock.h>
 #include <linux/poll.h>
@@ -176,6 +177,9 @@ long ptp_ioctl(struct posix_clock_context *pccontext, unsigned int cmd,
 	struct timespec64 ts;
 	int enable, err = 0;
 
+	if (in_compat_syscall() && cmd != PTP_ENABLE_PPS && cmd != PTP_ENABLE_PPS2)
+		arg = (unsigned long)compat_ptr(arg);
+
 	tsevq = pccontext->private_clkdata;
 
 	switch (cmd) {
diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c
index 77a36e7bddd5..642a540861d4 100644
--- a/drivers/ptp/ptp_clock.c
+++ b/drivers/ptp/ptp_clock.c
@@ -96,7 +96,7 @@ static int ptp_clock_settime(struct posix_clock *pc, const struct timespec64 *tp
 	struct ptp_clock *ptp = container_of(pc, struct ptp_clock, clock);
 
 	if (ptp_clock_freerun(ptp)) {
-		pr_err("ptp: physical clock is free running\n");
+		pr_err_ratelimited("ptp: physical clock is free running\n");
 		return -EBUSY;
 	}
 
@@ -121,7 +121,8 @@ static int ptp_clock_adjtime(struct posix_clock *pc, struct __kernel_timex *tx)
 	struct ptp_clock_info *ops;
 	int err = -EOPNOTSUPP;
 
-	if (ptp_clock_freerun(ptp)) {
+	if (tx->modes & (ADJ_SETOFFSET | ADJ_FREQUENCY | ADJ_OFFSET) &&
+	    ptp_clock_freerun(ptp)) {
 		pr_err("ptp: physical clock is free running\n");
 		return -EBUSY;
 	}
@@ -217,6 +218,11 @@ static int ptp_getcycles64(struct ptp_clock_info *info, struct timespec64 *ts)
 		return info->gettime64(info, ts);
 }
 
+static int ptp_enable(struct ptp_clock_info *ptp, struct ptp_clock_request *request, int on)
+{
+	return -EOPNOTSUPP;
+}
+
 static void ptp_aux_kworker(struct kthread_work *work)
 {
 	struct ptp_clock *ptp = container_of(work, struct ptp_clock,
@@ -294,6 +300,9 @@ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info,
 			ptp->info->getcrosscycles = ptp->info->getcrosststamp;
 	}
 
+	if (!ptp->info->enable)
+		ptp->info->enable = ptp_enable;
+
 	if (ptp->info->do_aux_work) {
 		kthread_init_delayed_work(&ptp->aux_work, ptp_aux_kworker);
 		ptp->kworker = kthread_create_worker(0, "ptp%d", ptp->index);
diff --git a/drivers/ptp/ptp_ocp.c b/drivers/ptp/ptp_ocp.c
index 5feecaadde8e..efbd80db778d 100644
--- a/drivers/ptp/ptp_ocp.c
+++ b/drivers/ptp/ptp_ocp.c
@@ -315,6 +315,8 @@ struct ptp_ocp_serial_port {
 #define OCP_BOARD_ID_LEN		13
 #define OCP_SERIAL_LEN			6
 #define OCP_SMA_NUM			4
+#define OCP_SIGNAL_NUM			4
+#define OCP_FREQ_NUM			4
 
 enum {
 	PORT_GNSS,
@@ -342,8 +344,8 @@ struct ptp_ocp {
 	struct dcf_master_reg	__iomem *dcf_out;
 	struct dcf_slave_reg	__iomem *dcf_in;
 	struct tod_reg		__iomem *nmea_out;
-	struct frequency_reg	__iomem *freq_in[4];
-	struct ptp_ocp_ext_src	*signal_out[4];
+	struct frequency_reg	__iomem *freq_in[OCP_FREQ_NUM];
+	struct ptp_ocp_ext_src	*signal_out[OCP_SIGNAL_NUM];
 	struct ptp_ocp_ext_src	*pps;
 	struct ptp_ocp_ext_src	*ts0;
 	struct ptp_ocp_ext_src	*ts1;
@@ -378,10 +380,12 @@ struct ptp_ocp {
 	u32			utc_tai_offset;
 	u32			ts_window_adjust;
 	u64			fw_cap;
-	struct ptp_ocp_signal	signal[4];
+	struct ptp_ocp_signal	signal[OCP_SIGNAL_NUM];
 	struct ptp_ocp_sma_connector sma[OCP_SMA_NUM];
 	const struct ocp_sma_op *sma_op;
 	struct dpll_device *dpll;
+	int signals_nr;
+	int freq_in_nr;
 };
 
 #define OCP_REQ_TIMESTAMP	BIT(0)
@@ -2067,6 +2071,7 @@ ptp_ocp_signal_set(struct ptp_ocp *bp, int gen, struct ptp_ocp_signal *s)
 	if (!s->start) {
 		/* roundup() does not work on 32-bit systems */
 		s->start = DIV64_U64_ROUND_UP(start_ns, s->period);
+		s->start *= s->period;
 		s->start = ktime_add(s->start, s->phase);
 	}
 
@@ -2573,12 +2578,60 @@ static const struct ocp_sma_op ocp_fb_sma_op = {
 	.set_output	= ptp_ocp_sma_fb_set_output,
 };
 
+static int
+ptp_ocp_sma_adva_set_output(struct ptp_ocp *bp, int sma_nr, u32 val)
+{
+	u32 reg, mask, shift;
+	unsigned long flags;
+	u32 __iomem *gpio;
+
+	gpio = sma_nr > 2 ? &bp->sma_map1->gpio2 : &bp->sma_map2->gpio2;
+	shift = sma_nr & 1 ? 0 : 16;
+
+	mask = 0xffff << (16 - shift);
+
+	spin_lock_irqsave(&bp->lock, flags);
+
+	reg = ioread32(gpio);
+	reg = (reg & mask) | (val << shift);
+
+	iowrite32(reg, gpio);
+
+	spin_unlock_irqrestore(&bp->lock, flags);
+
+	return 0;
+}
+
+static int
+ptp_ocp_sma_adva_set_inputs(struct ptp_ocp *bp, int sma_nr, u32 val)
+{
+	u32 reg, mask, shift;
+	unsigned long flags;
+	u32 __iomem *gpio;
+
+	gpio = sma_nr > 2 ? &bp->sma_map2->gpio1 : &bp->sma_map1->gpio1;
+	shift = sma_nr & 1 ? 0 : 16;
+
+	mask = 0xffff << (16 - shift);
+
+	spin_lock_irqsave(&bp->lock, flags);
+
+	reg = ioread32(gpio);
+	reg = (reg & mask) | (val << shift);
+
+	iowrite32(reg, gpio);
+
+	spin_unlock_irqrestore(&bp->lock, flags);
+
+	return 0;
+}
+
 static const struct ocp_sma_op ocp_adva_sma_op = {
 	.tbl		= { ptp_ocp_adva_sma_in, ptp_ocp_adva_sma_out },
 	.init		= ptp_ocp_sma_fb_init,
 	.get		= ptp_ocp_sma_fb_get,
-	.set_inputs	= ptp_ocp_sma_fb_set_inputs,
-	.set_output	= ptp_ocp_sma_fb_set_output,
+	.set_inputs	= ptp_ocp_sma_adva_set_inputs,
+	.set_output	= ptp_ocp_sma_adva_set_output,
 };
 
 static int
@@ -2644,6 +2697,8 @@ ptp_ocp_fb_board_init(struct ptp_ocp *bp, struct ocp_resource *r)
 	bp->eeprom_map = fb_eeprom_map;
 	bp->fw_version = ioread32(&bp->image->version);
 	bp->sma_op = &ocp_fb_sma_op;
+	bp->signals_nr = 4;
+	bp->freq_in_nr = 4;
 
 	ptp_ocp_fb_set_version(bp);
 
@@ -2809,6 +2864,8 @@ ptp_ocp_art_board_init(struct ptp_ocp *bp, struct ocp_resource *r)
 	bp->fw_version = ioread32(&bp->reg->version);
 	bp->fw_tag = 2;
 	bp->sma_op = &ocp_art_sma_op;
+	bp->signals_nr = 4;
+	bp->freq_in_nr = 4;
 
 	/* Enable MAC serial port during initialisation */
 	iowrite32(1, &bp->board_config->mro50_serial_activate);
@@ -2835,6 +2892,8 @@ ptp_ocp_adva_board_init(struct ptp_ocp *bp, struct ocp_resource *r)
 	bp->flash_start = 0xA00000;
 	bp->eeprom_map = fb_eeprom_map;
 	bp->sma_op = &ocp_adva_sma_op;
+	bp->signals_nr = 2;
+	bp->freq_in_nr = 2;
 
 	version = ioread32(&bp->image->version);
 	/* if lower 16 bits are empty, this is the fw loader. */
@@ -3955,7 +4014,7 @@ _signal_summary_show(struct seq_file *s, struct ptp_ocp *bp, int nr)
 {
 	struct signal_reg __iomem *reg = bp->signal_out[nr]->mem;
 	struct ptp_ocp_signal *signal = &bp->signal[nr];
-	char label[8];
+	char label[16];
 	bool on;
 	u32 val;
 
@@ -3981,7 +4040,7 @@ static void
 _frequency_summary_show(struct seq_file *s, int nr,
 			struct frequency_reg __iomem *reg)
 {
-	char label[8];
+	char label[16];
 	bool on;
 	u32 val;
 
@@ -4125,11 +4184,11 @@ ptp_ocp_summary_show(struct seq_file *s, void *data)
 	}
 
 	if (bp->fw_cap & OCP_CAP_SIGNAL)
-		for (i = 0; i < 4; i++)
+		for (i = 0; i < bp->signals_nr; i++)
 			_signal_summary_show(s, bp, i);
 
 	if (bp->fw_cap & OCP_CAP_FREQ)
-		for (i = 0; i < 4; i++)
+		for (i = 0; i < bp->freq_in_nr; i++)
 			_frequency_summary_show(s, i, bp->freq_in[i]);
 
 	if (bp->irig_out) {
@@ -4420,7 +4479,7 @@ ptp_ocp_complete(struct ptp_ocp *bp)
 
 	pps = pps_lookup_dev(bp->ptp);
 	if (pps)
-		ptp_ocp_symlink(bp, pps->dev, "pps");
+		ptp_ocp_symlink(bp, &pps->dev, "pps");
 
 	ptp_ocp_debugfs_add_device(bp);
 
diff --git a/drivers/ptp/ptp_private.h b/drivers/ptp/ptp_private.h
index 18934e28469e..b352df4cd3f9 100644
--- a/drivers/ptp/ptp_private.h
+++ b/drivers/ptp/ptp_private.h
@@ -24,6 +24,11 @@
 #define PTP_DEFAULT_MAX_VCLOCKS 20
 #define PTP_MAX_CHANNELS 2048
 
+enum {
+	PTP_LOCK_PHYSICAL = 0,
+	PTP_LOCK_VIRTUAL,
+};
+
 struct timestamp_event_queue {
 	struct ptp_extts_event buf[PTP_MAX_TIMESTAMPS];
 	int head;
@@ -100,10 +105,20 @@ static inline bool ptp_vclock_in_use(struct ptp_clock *ptp)
 {
 	bool in_use = false;
 
+	/* Virtual clocks can't be stacked on top of virtual clocks.
+	 * Avoid acquiring the n_vclocks_mux on virtual clocks, to allow this
+	 * function to be called from code paths where the n_vclocks_mux of the
+	 * parent physical clock is already held. Functionally that's not an
+	 * issue, but lockdep would complain, because they have the same lock
+	 * class.
+	 */
+	if (ptp->is_virtual_clock)
+		return false;
+
 	if (mutex_lock_interruptible(&ptp->n_vclocks_mux))
 		return true;
 
-	if (!ptp->is_virtual_clock && ptp->n_vclocks)
+	if (ptp->n_vclocks)
 		in_use = true;
 
 	mutex_unlock(&ptp->n_vclocks_mux);
diff --git a/drivers/ptp/ptp_vclock.c b/drivers/ptp/ptp_vclock.c
index 7febfdcbde8b..8ed4b8598924 100644
--- a/drivers/ptp/ptp_vclock.c
+++ b/drivers/ptp/ptp_vclock.c
@@ -154,6 +154,11 @@ static long ptp_vclock_refresh(struct ptp_clock_info *ptp)
 	return PTP_VCLOCK_REFRESH_INTERVAL;
 }
 
+static void ptp_vclock_set_subclass(struct ptp_clock *ptp)
+{
+	lockdep_set_subclass(&ptp->clock.rwsem, PTP_LOCK_VIRTUAL);
+}
+
 static const struct ptp_clock_info ptp_vclock_info = {
 	.owner		= THIS_MODULE,
 	.name		= "ptp virtual clock",
@@ -213,6 +218,8 @@ struct ptp_vclock *ptp_vclock_register(struct ptp_clock *pclock)
 		return NULL;
 	}
 
+	ptp_vclock_set_subclass(vclock->clock);
+
 	timecounter_init(&vclock->tc, &vclock->cc, 0);
 	ptp_schedule_worker(vclock->clock, PTP_VCLOCK_REFRESH_INTERVAL);
 
diff --git a/drivers/pwm/core.c b/drivers/pwm/core.c
index 210368099a06..3697781c0179 100644
--- a/drivers/pwm/core.c
+++ b/drivers/pwm/core.c
@@ -6,7 +6,7 @@
  * Copyright (C) 2011-2012 Avionic Design GmbH
  */
 
-#define DEFAULT_SYMBOL_NAMESPACE PWM
+#define DEFAULT_SYMBOL_NAMESPACE "PWM"
 
 #include <linux/acpi.h>
 #include <linux/module.h>
@@ -148,7 +148,7 @@ static bool pwm_state_valid(const struct pwm_state *state)
 	 * and supposed to be ignored. So also ignore any strange values and
 	 * consider the state ok.
 	 */
-	if (state->enabled)
+	if (!state->enabled)
 		return true;
 
 	if (!state->period)
diff --git a/drivers/pwm/pwm-axi-pwmgen.c b/drivers/pwm/pwm-axi-pwmgen.c
index b5477659ba18..73c68f494e7f 100644
--- a/drivers/pwm/pwm-axi-pwmgen.c
+++ b/drivers/pwm/pwm-axi-pwmgen.c
@@ -174,7 +174,7 @@ static int axi_pwmgen_probe(struct platform_device *pdev)
 	struct regmap *regmap;
 	struct pwm_chip *chip;
 	struct axi_pwmgen_ddata *ddata;
-	struct clk *clk;
+	struct clk *axi_clk, *clk;
 	void __iomem *io_base;
 	int ret;
 
@@ -197,9 +197,26 @@ static int axi_pwmgen_probe(struct platform_device *pdev)
 	ddata = pwmchip_get_drvdata(chip);
 	ddata->regmap = regmap;
 
-	clk = devm_clk_get_enabled(dev, NULL);
+	/*
+	 * Using NULL here instead of "axi" for backwards compatibility. There
+	 * are some dtbs that don't give clock-names and have the "ext" clock
+	 * as the one and only clock (due to mistake in the original bindings).
+	 */
+	axi_clk = devm_clk_get_enabled(dev, NULL);
+	if (IS_ERR(axi_clk))
+		return dev_err_probe(dev, PTR_ERR(axi_clk), "failed to get axi clock\n");
+
+	clk = devm_clk_get_optional_enabled(dev, "ext");
 	if (IS_ERR(clk))
-		return dev_err_probe(dev, PTR_ERR(clk), "failed to get clock\n");
+		return dev_err_probe(dev, PTR_ERR(clk), "failed to get ext clock\n");
+
+	/*
+	 * If there is no "ext" clock, it means the HDL was compiled with
+	 * ASYNC_CLK_EN=0. In this case, the AXI clock is also used for the
+	 * PWM output clock.
+	 */
+	if (!clk)
+		clk = axi_clk;
 
 	ret = devm_clk_rate_exclusive_get(dev, clk);
 	if (ret)
diff --git a/drivers/pwm/pwm-dwc-core.c b/drivers/pwm/pwm-dwc-core.c
index c8425493b95d..6dabec93a3c6 100644
--- a/drivers/pwm/pwm-dwc-core.c
+++ b/drivers/pwm/pwm-dwc-core.c
@@ -9,7 +9,7 @@
  * Author: Raymond Tan <raymond.tan@intel.com>
  */
 
-#define DEFAULT_SYMBOL_NAMESPACE dwc_pwm
+#define DEFAULT_SYMBOL_NAMESPACE "dwc_pwm"
 
 #include <linux/bitops.h>
 #include <linux/export.h>
diff --git a/drivers/pwm/pwm-fsl-ftm.c b/drivers/pwm/pwm-fsl-ftm.c
index 2510c10ca473..c45a5fca4cbb 100644
--- a/drivers/pwm/pwm-fsl-ftm.c
+++ b/drivers/pwm/pwm-fsl-ftm.c
@@ -118,6 +118,9 @@ static unsigned int fsl_pwm_ticks_to_ns(struct fsl_pwm_chip *fpc,
 	unsigned long long exval;
 
 	rate = clk_get_rate(fpc->clk[fpc->period.clk_select]);
+	if (rate >> fpc->period.clk_ps == 0)
+		return 0;
+
 	exval = ticks;
 	exval *= 1000000000UL;
 	do_div(exval, rate >> fpc->period.clk_ps);
@@ -190,6 +193,9 @@ static unsigned int fsl_pwm_calculate_duty(struct fsl_pwm_chip *fpc,
 	unsigned int period = fpc->period.mod_period + 1;
 	unsigned int period_ns = fsl_pwm_ticks_to_ns(fpc, period);
 
+	if (!period_ns)
+		return 0;
+
 	duty = (unsigned long long)duty_ns * period;
 	do_div(duty, period_ns);
 
diff --git a/drivers/pwm/pwm-lpss.c b/drivers/pwm/pwm-lpss.c
index 867e2bc8c601..3b99feb3bb49 100644
--- a/drivers/pwm/pwm-lpss.c
+++ b/drivers/pwm/pwm-lpss.c
@@ -19,7 +19,7 @@
 #include <linux/pm_runtime.h>
 #include <linux/time.h>
 
-#define DEFAULT_SYMBOL_NAMESPACE PWM_LPSS
+#define DEFAULT_SYMBOL_NAMESPACE "PWM_LPSS"
 
 #include "pwm-lpss.h"
 
diff --git a/drivers/pwm/pwm-mediatek.c b/drivers/pwm/pwm-mediatek.c
index 01dfa0fab80a..33d3554b9197 100644
--- a/drivers/pwm/pwm-mediatek.c
+++ b/drivers/pwm/pwm-mediatek.c
@@ -121,21 +121,27 @@ static int pwm_mediatek_config(struct pwm_chip *chip, struct pwm_device *pwm,
 	struct pwm_mediatek_chip *pc = to_pwm_mediatek_chip(chip);
 	u32 clkdiv = 0, cnt_period, cnt_duty, reg_width = PWMDWIDTH,
 	    reg_thres = PWMTHRES;
+	unsigned long clk_rate;
 	u64 resolution;
 	int ret;
 
 	ret = pwm_mediatek_clk_enable(chip, pwm);
-
 	if (ret < 0)
 		return ret;
 
+	clk_rate = clk_get_rate(pc->clk_pwms[pwm->hwpwm]);
+	if (!clk_rate) {
+		ret = -EINVAL;
+		goto out;
+	}
+
 	/* Make sure we use the bus clock and not the 26MHz clock */
 	if (pc->soc->has_ck_26m_sel)
 		writel(0, pc->regs + PWM_CK_26M_SEL);
 
 	/* Using resolution in picosecond gets accuracy higher */
 	resolution = (u64)NSEC_PER_SEC * 1000;
-	do_div(resolution, clk_get_rate(pc->clk_pwms[pwm->hwpwm]));
+	do_div(resolution, clk_rate);
 
 	cnt_period = DIV_ROUND_CLOSEST_ULL((u64)period_ns * 1000, resolution);
 	while (cnt_period > 8191) {
@@ -146,9 +152,9 @@ static int pwm_mediatek_config(struct pwm_chip *chip, struct pwm_device *pwm,
 	}
 
 	if (clkdiv > PWM_CLK_DIV_MAX) {
-		pwm_mediatek_clk_disable(chip, pwm);
 		dev_err(pwmchip_parent(chip), "period of %d ns not supported\n", period_ns);
-		return -EINVAL;
+		ret = -EINVAL;
+		goto out;
 	}
 
 	if (pc->soc->pwm45_fixup && pwm->hwpwm > 2) {
@@ -165,9 +171,10 @@ static int pwm_mediatek_config(struct pwm_chip *chip, struct pwm_device *pwm,
 	pwm_mediatek_writel(pc, pwm->hwpwm, reg_width, cnt_period);
 	pwm_mediatek_writel(pc, pwm->hwpwm, reg_thres, cnt_duty);
 
+out:
 	pwm_mediatek_clk_disable(chip, pwm);
 
-	return 0;
+	return ret;
 }
 
 static int pwm_mediatek_enable(struct pwm_chip *chip, struct pwm_device *pwm)
diff --git a/drivers/pwm/pwm-microchip-core.c b/drivers/pwm/pwm-microchip-core.c
index c1f2287b8e97..12821b4bbf97 100644
--- a/drivers/pwm/pwm-microchip-core.c
+++ b/drivers/pwm/pwm-microchip-core.c
@@ -327,7 +327,7 @@ static int mchp_core_pwm_apply_locked(struct pwm_chip *chip, struct pwm_device *
 		 * mchp_core_pwm_calc_period().
 		 * The period is locked and we cannot change this, so we abort.
 		 */
-		if (hw_period_steps == MCHPCOREPWM_PERIOD_STEPS_MAX)
+		if (hw_period_steps > MCHPCOREPWM_PERIOD_STEPS_MAX)
 			return -EINVAL;
 
 		prescale = hw_prescale;
diff --git a/drivers/pwm/pwm-rcar.c b/drivers/pwm/pwm-rcar.c
index 2261789cc27d..578dbdd2d5a7 100644
--- a/drivers/pwm/pwm-rcar.c
+++ b/drivers/pwm/pwm-rcar.c
@@ -8,6 +8,7 @@
  * - The hardware cannot generate a 0% duty cycle.
  */
 
+#include <linux/bitfield.h>
 #include <linux/clk.h>
 #include <linux/err.h>
 #include <linux/io.h>
@@ -102,23 +103,24 @@ static void rcar_pwm_set_clock_control(struct rcar_pwm_chip *rp,
 	rcar_pwm_write(rp, value, RCAR_PWMCR);
 }
 
-static int rcar_pwm_set_counter(struct rcar_pwm_chip *rp, int div, int duty_ns,
-				int period_ns)
+static int rcar_pwm_set_counter(struct rcar_pwm_chip *rp, int div, u64 duty_ns,
+				u64 period_ns)
 {
-	unsigned long long one_cycle, tmp;	/* 0.01 nanoseconds */
+	unsigned long long tmp;
 	unsigned long clk_rate = clk_get_rate(rp->clk);
 	u32 cyc, ph;
 
-	one_cycle = NSEC_PER_SEC * 100ULL << div;
-	do_div(one_cycle, clk_rate);
+	/* div <= 24 == RCAR_PWM_MAX_DIVISION, so the shift doesn't overflow. */
+	tmp = mul_u64_u64_div_u64(period_ns, clk_rate, (u64)NSEC_PER_SEC << div);
+	if (tmp > FIELD_MAX(RCAR_PWMCNT_CYC0_MASK))
+		tmp = FIELD_MAX(RCAR_PWMCNT_CYC0_MASK);
 
-	tmp = period_ns * 100ULL;
-	do_div(tmp, one_cycle);
-	cyc = (tmp << RCAR_PWMCNT_CYC0_SHIFT) & RCAR_PWMCNT_CYC0_MASK;
+	cyc = FIELD_PREP(RCAR_PWMCNT_CYC0_MASK, tmp);
 
-	tmp = duty_ns * 100ULL;
-	do_div(tmp, one_cycle);
-	ph = tmp & RCAR_PWMCNT_PH0_MASK;
+	tmp = mul_u64_u64_div_u64(duty_ns, clk_rate, (u64)NSEC_PER_SEC << div);
+	if (tmp > FIELD_MAX(RCAR_PWMCNT_PH0_MASK))
+		tmp = FIELD_MAX(RCAR_PWMCNT_PH0_MASK);
+	ph = FIELD_PREP(RCAR_PWMCNT_PH0_MASK, tmp);
 
 	/* Avoid prohibited setting */
 	if (cyc == 0 || ph == 0)
diff --git a/drivers/pwm/pwm-stm32-lp.c b/drivers/pwm/pwm-stm32-lp.c
index 989731256f50..5832dce8ed9d 100644
--- a/drivers/pwm/pwm-stm32-lp.c
+++ b/drivers/pwm/pwm-stm32-lp.c
@@ -167,8 +167,12 @@ static int stm32_pwm_lp_get_state(struct pwm_chip *chip,
 	regmap_read(priv->regmap, STM32_LPTIM_CR, &val);
 	state->enabled = !!FIELD_GET(STM32_LPTIM_ENABLE, val);
 	/* Keep PWM counter clock refcount in sync with PWM initial state */
-	if (state->enabled)
-		clk_enable(priv->clk);
+	if (state->enabled) {
+		int ret = clk_enable(priv->clk);
+
+		if (ret)
+			return ret;
+	}
 
 	regmap_read(priv->regmap, STM32_LPTIM_CFGR, &val);
 	presc = FIELD_GET(STM32_LPTIM_PRESC, val);
diff --git a/drivers/pwm/pwm-stm32.c b/drivers/pwm/pwm-stm32.c
index eb24054f9729..4f231f8aae7d 100644
--- a/drivers/pwm/pwm-stm32.c
+++ b/drivers/pwm/pwm-stm32.c
@@ -688,8 +688,11 @@ static int stm32_pwm_probe(struct platform_device *pdev)
 	chip->ops = &stm32pwm_ops;
 
 	/* Initialize clock refcount to number of enabled PWM channels. */
-	for (i = 0; i < num_enabled; i++)
-		clk_enable(priv->clk);
+	for (i = 0; i < num_enabled; i++) {
+		ret = clk_enable(priv->clk);
+		if (ret)
+			return ret;
+	}
 
 	ret = devm_pwmchip_add(dev, chip);
 	if (ret < 0)
diff --git a/drivers/rapidio/devices/rio_mport_cdev.c b/drivers/rapidio/devices/rio_mport_cdev.c
index 27afbb9d544b..cbf531d0ba68 100644
--- a/drivers/rapidio/devices/rio_mport_cdev.c
+++ b/drivers/rapidio/devices/rio_mport_cdev.c
@@ -1742,7 +1742,8 @@ static int rio_mport_add_riodev(struct mport_cdev_priv *priv,
 		err = rio_add_net(net);
 		if (err) {
 			rmcd_debug(RDEV, "failed to register net, err=%d", err);
-			kfree(net);
+			put_device(&net->dev);
+			mport->net = NULL;
 			goto cleanup;
 		}
 	}
diff --git a/drivers/rapidio/rio-scan.c b/drivers/rapidio/rio-scan.c
index fdcf742b2adb..c12941f71e2c 100644
--- a/drivers/rapidio/rio-scan.c
+++ b/drivers/rapidio/rio-scan.c
@@ -871,7 +871,10 @@ static struct rio_net *rio_scan_alloc_net(struct rio_mport *mport,
 		dev_set_name(&net->dev, "rnet_%d", net->id);
 		net->dev.parent = &mport->dev;
 		net->dev.release = rio_scan_release_dev;
-		rio_add_net(net);
+		if (rio_add_net(net)) {
+			put_device(&net->dev);
+			net = NULL;
+		}
 	}
 
 	return net;
diff --git a/drivers/rapidio/rio_cm.c b/drivers/rapidio/rio_cm.c
index 9135227301c8..e548edf64eca 100644
--- a/drivers/rapidio/rio_cm.c
+++ b/drivers/rapidio/rio_cm.c
@@ -789,6 +789,9 @@ static int riocm_ch_send(u16 ch_id, void *buf, int len)
 	if (buf == NULL || ch_id == 0 || len == 0 || len > RIO_MAX_MSG_SIZE)
 		return -EINVAL;
 
+	if (len < sizeof(struct rio_ch_chan_hdr))
+		return -EINVAL;		/* insufficient data from user */
+
 	ch = riocm_get_channel(ch_id);
 	if (!ch) {
 		riocm_error("%s(%d) ch_%d not found", current->comm,
diff --git a/drivers/ras/amd/atl/internal.h b/drivers/ras/amd/atl/internal.h
index 143d04c779a8..b7c7d5ba4d9d 100644
--- a/drivers/ras/amd/atl/internal.h
+++ b/drivers/ras/amd/atl/internal.h
@@ -361,4 +361,7 @@ static inline void atl_debug_on_bad_intlv_mode(struct addr_ctx *ctx)
 	atl_debug(ctx, "Unrecognized interleave mode: %u", ctx->map.intlv_mode);
 }
 
+#define MI300_UMC_MCA_COL	GENMASK(5, 1)
+#define MI300_UMC_MCA_ROW13	BIT(23)
+
 #endif /* __AMD_ATL_INTERNAL_H__ */
diff --git a/drivers/ras/amd/atl/umc.c b/drivers/ras/amd/atl/umc.c
index dc8aa12f63c8..6e072b7667e9 100644
--- a/drivers/ras/amd/atl/umc.c
+++ b/drivers/ras/amd/atl/umc.c
@@ -229,7 +229,6 @@ int get_umc_info_mi300(void)
  * Additionally, the PC and Bank bits may be hashed. This must be accounted for before
  * reconstructing the normalized address.
  */
-#define MI300_UMC_MCA_COL	GENMASK(5, 1)
 #define MI300_UMC_MCA_BANK	GENMASK(9, 6)
 #define MI300_UMC_MCA_ROW	GENMASK(24, 10)
 #define MI300_UMC_MCA_PC	BIT(25)
@@ -320,7 +319,7 @@ static unsigned long convert_dram_to_norm_addr_mi300(unsigned long addr)
  * See amd_atl::convert_dram_to_norm_addr_mi300() for MI300 address formats.
  */
 #define MI300_NUM_COL		BIT(HWEIGHT(MI300_UMC_MCA_COL))
-static void retire_row_mi300(struct atl_err *a_err)
+static void _retire_row_mi300(struct atl_err *a_err)
 {
 	unsigned long addr;
 	struct page *p;
@@ -351,6 +350,22 @@ static void retire_row_mi300(struct atl_err *a_err)
 	}
 }
 
+/*
+ * In addition to the column bits, the row[13] bit should also be included when
+ * calculating addresses affected by a physical row.
+ *
+ * Instead of running through another loop over a single bit, just run through
+ * the column bits twice and flip the row[13] bit in-between.
+ *
+ * See MI300_UMC_MCA_ROW for the row bits in MCA_ADDR_UMC value.
+ */
+static void retire_row_mi300(struct atl_err *a_err)
+{
+	_retire_row_mi300(a_err);
+	a_err->addr ^= MI300_UMC_MCA_ROW13;
+	_retire_row_mi300(a_err);
+}
+
 void amd_retire_dram_row(struct atl_err *a_err)
 {
 	if (df_cfg.rev == DF4p5 && df_cfg.flags.heterogeneous)
diff --git a/drivers/ras/amd/fmpm.c b/drivers/ras/amd/fmpm.c
index 90de737fbc90..8877c6ff64c4 100644
--- a/drivers/ras/amd/fmpm.c
+++ b/drivers/ras/amd/fmpm.c
@@ -250,6 +250,13 @@ static bool rec_has_valid_entries(struct fru_rec *rec)
 	return true;
 }
 
+/*
+ * Row retirement is done on MI300 systems, and some bits are 'don't
+ * care' for comparing addresses with unique physical rows.  This
+ * includes all column bits and the row[13] bit.
+ */
+#define MASK_ADDR(addr)	((addr) & ~(MI300_UMC_MCA_ROW13 | MI300_UMC_MCA_COL))
+
 static bool fpds_equal(struct cper_fru_poison_desc *old, struct cper_fru_poison_desc *new)
 {
 	/*
@@ -258,7 +265,7 @@ static bool fpds_equal(struct cper_fru_poison_desc *old, struct cper_fru_poison_
 	 *
 	 * Also, order the checks from most->least likely to fail to shortcut the code.
 	 */
-	if (old->addr != new->addr)
+	if (MASK_ADDR(old->addr) != MASK_ADDR(new->addr))
 		return false;
 
 	if (old->hw_id != new->hw_id)
diff --git a/drivers/regulator/ad5398.c b/drivers/regulator/ad5398.c
index 40f7dba42b5a..404cbe32711e 100644
--- a/drivers/regulator/ad5398.c
+++ b/drivers/regulator/ad5398.c
@@ -14,6 +14,7 @@
 #include <linux/platform_device.h>
 #include <linux/regulator/driver.h>
 #include <linux/regulator/machine.h>
+#include <linux/regulator/of_regulator.h>
 
 #define AD5398_CURRENT_EN_MASK	0x8000
 
@@ -221,15 +222,20 @@ static int ad5398_probe(struct i2c_client *client)
 	const struct ad5398_current_data_format *df =
 			(struct ad5398_current_data_format *)id->driver_data;
 
-	if (!init_data)
-		return -EINVAL;
-
 	chip = devm_kzalloc(&client->dev, sizeof(*chip), GFP_KERNEL);
 	if (!chip)
 		return -ENOMEM;
 
 	config.dev = &client->dev;
+	if (client->dev.of_node)
+		init_data = of_get_regulator_init_data(&client->dev,
+						       client->dev.of_node,
+						       &ad5398_reg);
+	if (!init_data)
+		return -EINVAL;
+
 	config.init_data = init_data;
+	config.of_node = client->dev.of_node;
 	config.driver_data = chip;
 
 	chip->client = client;
diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index 1179766811f5..e7f2a8b65947 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -2024,6 +2024,10 @@ static int regulator_resolve_supply(struct regulator_dev *rdev)
 
 		if (have_full_constraints()) {
 			r = dummy_regulator_rdev;
+			if (!r) {
+				ret = -EPROBE_DEFER;
+				goto out;
+			}
 			get_device(&r->dev);
 		} else {
 			dev_err(dev, "Failed to resolve %s-supply for %s\n",
@@ -2041,6 +2045,10 @@ static int regulator_resolve_supply(struct regulator_dev *rdev)
 			goto out;
 		}
 		r = dummy_regulator_rdev;
+		if (!r) {
+			ret = -EPROBE_DEFER;
+			goto out;
+		}
 		get_device(&r->dev);
 	}
 
@@ -2166,8 +2174,10 @@ struct regulator *_regulator_get_common(struct regulator_dev *rdev, struct devic
 			 * enabled, even if it isn't hooked up, and just
 			 * provide a dummy.
 			 */
-			dev_warn(dev, "supply %s not found, using dummy regulator\n", id);
 			rdev = dummy_regulator_rdev;
+			if (!rdev)
+				return ERR_PTR(-EPROBE_DEFER);
+			dev_warn(dev, "supply %s not found, using dummy regulator\n", id);
 			get_device(&rdev->dev);
 			break;
 
@@ -4946,7 +4956,7 @@ int _regulator_bulk_get(struct device *dev, int num_consumers,
 						       consumers[i].supply, get_type);
 		if (IS_ERR(consumers[i].consumer)) {
 			ret = dev_err_probe(dev, PTR_ERR(consumers[i].consumer),
-					    "Failed to get supply '%s'",
+					    "Failed to get supply '%s'\n",
 					    consumers[i].supply);
 			consumers[i].consumer = NULL;
 			goto err;
@@ -5526,6 +5536,7 @@ static void regulator_remove_coupling(struct regulator_dev *rdev)
 				 ERR_PTR(err));
 	}
 
+	rdev->coupling_desc.n_coupled = 0;
 	kfree(rdev->coupling_desc.coupled_rdevs);
 	rdev->coupling_desc.coupled_rdevs = NULL;
 }
diff --git a/drivers/regulator/dummy.c b/drivers/regulator/dummy.c
index 5b9b9e4e762d..9f59889129ab 100644
--- a/drivers/regulator/dummy.c
+++ b/drivers/regulator/dummy.c
@@ -60,7 +60,7 @@ static struct platform_driver dummy_regulator_driver = {
 	.probe		= dummy_regulator_probe,
 	.driver		= {
 		.name		= "reg-dummy",
-		.probe_type	= PROBE_PREFER_ASYNCHRONOUS,
+		.probe_type	= PROBE_FORCE_SYNCHRONOUS,
 	},
 };
 
diff --git a/drivers/regulator/fan53555.c b/drivers/regulator/fan53555.c
index bd9447dac596..c282236959b1 100644
--- a/drivers/regulator/fan53555.c
+++ b/drivers/regulator/fan53555.c
@@ -147,6 +147,7 @@ struct fan53555_device_info {
 	unsigned int slew_mask;
 	const unsigned int *ramp_delay_table;
 	unsigned int n_ramp_values;
+	unsigned int enable_time;
 	unsigned int slew_rate;
 };
 
@@ -282,6 +283,7 @@ static int fan53526_voltages_setup_fairchild(struct fan53555_device_info *di)
 	di->slew_mask = CTL_SLEW_MASK;
 	di->ramp_delay_table = slew_rates;
 	di->n_ramp_values = ARRAY_SIZE(slew_rates);
+	di->enable_time = 250;
 	di->vsel_count = FAN53526_NVOLTAGES;
 
 	return 0;
@@ -296,10 +298,12 @@ static int fan53555_voltages_setup_fairchild(struct fan53555_device_info *di)
 		case FAN53555_CHIP_REV_00:
 			di->vsel_min = 600000;
 			di->vsel_step = 10000;
+			di->enable_time = 400;
 			break;
 		case FAN53555_CHIP_REV_13:
 			di->vsel_min = 800000;
 			di->vsel_step = 10000;
+			di->enable_time = 400;
 			break;
 		default:
 			dev_err(di->dev,
@@ -311,13 +315,19 @@ static int fan53555_voltages_setup_fairchild(struct fan53555_device_info *di)
 	case FAN53555_CHIP_ID_01:
 	case FAN53555_CHIP_ID_03:
 	case FAN53555_CHIP_ID_05:
+		di->vsel_min = 600000;
+		di->vsel_step = 10000;
+		di->enable_time = 400;
+		break;
 	case FAN53555_CHIP_ID_08:
 		di->vsel_min = 600000;
 		di->vsel_step = 10000;
+		di->enable_time = 175;
 		break;
 	case FAN53555_CHIP_ID_04:
 		di->vsel_min = 603000;
 		di->vsel_step = 12826;
+		di->enable_time = 400;
 		break;
 	default:
 		dev_err(di->dev,
@@ -350,6 +360,7 @@ static int fan53555_voltages_setup_rockchip(struct fan53555_device_info *di)
 	di->slew_mask = CTL_SLEW_MASK;
 	di->ramp_delay_table = slew_rates;
 	di->n_ramp_values = ARRAY_SIZE(slew_rates);
+	di->enable_time = 360;
 	di->vsel_count = FAN53555_NVOLTAGES;
 
 	return 0;
@@ -372,6 +383,7 @@ static int rk8602_voltages_setup_rockchip(struct fan53555_device_info *di)
 	di->slew_mask = CTL_SLEW_MASK;
 	di->ramp_delay_table = slew_rates;
 	di->n_ramp_values = ARRAY_SIZE(slew_rates);
+	di->enable_time = 360;
 	di->vsel_count = RK8602_NVOLTAGES;
 
 	return 0;
@@ -395,6 +407,7 @@ static int fan53555_voltages_setup_silergy(struct fan53555_device_info *di)
 	di->slew_mask = CTL_SLEW_MASK;
 	di->ramp_delay_table = slew_rates;
 	di->n_ramp_values = ARRAY_SIZE(slew_rates);
+	di->enable_time = 400;
 	di->vsel_count = FAN53555_NVOLTAGES;
 
 	return 0;
@@ -594,6 +607,7 @@ static int fan53555_regulator_register(struct fan53555_device_info *di,
 	rdesc->ramp_mask = di->slew_mask;
 	rdesc->ramp_delay_table = di->ramp_delay_table;
 	rdesc->n_ramp_values = di->n_ramp_values;
+	rdesc->enable_time = di->enable_time;
 	rdesc->owner = THIS_MODULE;
 
 	rdev = devm_regulator_register(di->dev, &di->desc, config);
diff --git a/drivers/regulator/gpio-regulator.c b/drivers/regulator/gpio-regulator.c
index 65927fa2ef16..1bdd494cf882 100644
--- a/drivers/regulator/gpio-regulator.c
+++ b/drivers/regulator/gpio-regulator.c
@@ -260,8 +260,10 @@ static int gpio_regulator_probe(struct platform_device *pdev)
 		return -ENOMEM;
 	}
 
-	drvdata->gpiods = devm_kzalloc(dev, sizeof(struct gpio_desc *),
-				       GFP_KERNEL);
+	drvdata->gpiods = devm_kcalloc(dev, config->ngpios,
+				       sizeof(struct gpio_desc *), GFP_KERNEL);
+	if (!drvdata->gpiods)
+		return -ENOMEM;
 
 	if (config->input_supply) {
 		drvdata->desc.supply_name = devm_kstrdup(&pdev->dev,
@@ -274,8 +276,6 @@ static int gpio_regulator_probe(struct platform_device *pdev)
 		}
 	}
 
-	if (!drvdata->gpiods)
-		return -ENOMEM;
 	for (i = 0; i < config->ngpios; i++) {
 		drvdata->gpiods[i] = devm_gpiod_get_index(dev,
 							  NULL,
diff --git a/drivers/regulator/max14577-regulator.c b/drivers/regulator/max14577-regulator.c
index 5e7171b9065a..41fd15adfd1f 100644
--- a/drivers/regulator/max14577-regulator.c
+++ b/drivers/regulator/max14577-regulator.c
@@ -40,11 +40,14 @@ static int max14577_reg_get_current_limit(struct regulator_dev *rdev)
 	struct max14577 *max14577 = rdev_get_drvdata(rdev);
 	const struct maxim_charger_current *limits =
 		&maxim_charger_currents[max14577->dev_type];
+	int ret;
 
 	if (rdev_get_id(rdev) != MAX14577_CHARGER)
 		return -EINVAL;
 
-	max14577_read_reg(rmap, MAX14577_CHG_REG_CHG_CTRL4, &reg_data);
+	ret = max14577_read_reg(rmap, MAX14577_CHG_REG_CHG_CTRL4, &reg_data);
+	if (ret < 0)
+		return ret;
 
 	if ((reg_data & CHGCTRL4_MBCICHWRCL_MASK) == 0)
 		return limits->min;
diff --git a/drivers/regulator/max20086-regulator.c b/drivers/regulator/max20086-regulator.c
index 59eb23d467ec..fcdd2d0317a5 100644
--- a/drivers/regulator/max20086-regulator.c
+++ b/drivers/regulator/max20086-regulator.c
@@ -5,6 +5,7 @@
 // Copyright (C) 2022 Laurent Pinchart <laurent.pinchart@idesonboard.com>
 // Copyright (C) 2018 Avnet, Inc.
 
+#include <linux/cleanup.h>
 #include <linux/err.h>
 #include <linux/gpio/consumer.h>
 #include <linux/i2c.h>
@@ -28,7 +29,7 @@
 #define	MAX20086_REG_ADC4		0x09
 
 /* DEVICE IDs */
-#define MAX20086_DEVICE_ID_MAX20086	0x40
+#define MAX20086_DEVICE_ID_MAX20086	0x30
 #define MAX20086_DEVICE_ID_MAX20087	0x20
 #define MAX20086_DEVICE_ID_MAX20088	0x10
 #define MAX20086_DEVICE_ID_MAX20089	0x00
@@ -132,23 +133,27 @@ static int max20086_regulators_register(struct max20086 *chip)
 
 static int max20086_parse_regulators_dt(struct max20086 *chip, bool *boot_on)
 {
-	struct of_regulator_match matches[MAX20086_MAX_REGULATORS] = { };
-	struct device_node *node;
+	struct of_regulator_match *matches;
 	unsigned int i;
 	int ret;
 
-	node = of_get_child_by_name(chip->dev->of_node, "regulators");
+	struct device_node *node __free(device_node) =
+		of_get_child_by_name(chip->dev->of_node, "regulators");
 	if (!node) {
 		dev_err(chip->dev, "regulators node not found\n");
 		return -ENODEV;
 	}
 
+	matches = devm_kcalloc(chip->dev, chip->info->num_outputs,
+			       sizeof(*matches), GFP_KERNEL);
+	if (!matches)
+		return -ENOMEM;
+
 	for (i = 0; i < chip->info->num_outputs; ++i)
 		matches[i].name = max20086_output_names[i];
 
 	ret = of_regulator_match(chip->dev, node, matches,
 				 chip->info->num_outputs);
-	of_node_put(node);
 	if (ret < 0) {
 		dev_err(chip->dev, "Failed to match regulators\n");
 		return -EINVAL;
@@ -259,7 +264,7 @@ static int max20086_i2c_probe(struct i2c_client *i2c)
 	 * shutdown.
 	 */
 	flags = boot_on ? GPIOD_OUT_HIGH : GPIOD_OUT_LOW;
-	chip->ena_gpiod = devm_gpiod_get(chip->dev, "enable", flags);
+	chip->ena_gpiod = devm_gpiod_get_optional(chip->dev, "enable", flags);
 	if (IS_ERR(chip->ena_gpiod)) {
 		ret = PTR_ERR(chip->ena_gpiod);
 		dev_err(chip->dev, "Failed to get enable GPIO: %d\n", ret);
diff --git a/drivers/regulator/of_regulator.c b/drivers/regulator/of_regulator.c
index 3f490d81abc2..deab0b95b663 100644
--- a/drivers/regulator/of_regulator.c
+++ b/drivers/regulator/of_regulator.c
@@ -446,7 +446,7 @@ int of_regulator_match(struct device *dev, struct device_node *node,
 					"failed to parse DT for regulator %pOFn\n",
 					child);
 				of_node_put(child);
-				return -EINVAL;
+				goto err_put;
 			}
 			match->of_node = of_node_get(child);
 			count++;
@@ -455,6 +455,18 @@ int of_regulator_match(struct device *dev, struct device_node *node,
 	}
 
 	return count;
+
+err_put:
+	for (i = 0; i < num_matches; i++) {
+		struct of_regulator_match *match = &matches[i];
+
+		match->init_data = NULL;
+		if (match->of_node) {
+			of_node_put(match->of_node);
+			match->of_node = NULL;
+		}
+	}
+	return -EINVAL;
 }
 EXPORT_SYMBOL_GPL(of_regulator_match);
 
diff --git a/drivers/regulator/pca9450-regulator.c b/drivers/regulator/pca9450-regulator.c
index 9714afe347dc..1ffa145319f2 100644
--- a/drivers/regulator/pca9450-regulator.c
+++ b/drivers/regulator/pca9450-regulator.c
@@ -454,7 +454,7 @@ static const struct pca9450_regulator_desc pca9450a_regulators[] = {
 			.n_linear_ranges = ARRAY_SIZE(pca9450_ldo5_volts),
 			.vsel_reg = PCA9450_REG_LDO5CTRL_H,
 			.vsel_mask = LDO5HOUT_MASK,
-			.enable_reg = PCA9450_REG_LDO5CTRL_H,
+			.enable_reg = PCA9450_REG_LDO5CTRL_L,
 			.enable_mask = LDO5H_EN_MASK,
 			.owner = THIS_MODULE,
 		},
@@ -663,7 +663,7 @@ static const struct pca9450_regulator_desc pca9450bc_regulators[] = {
 			.n_linear_ranges = ARRAY_SIZE(pca9450_ldo5_volts),
 			.vsel_reg = PCA9450_REG_LDO5CTRL_H,
 			.vsel_mask = LDO5HOUT_MASK,
-			.enable_reg = PCA9450_REG_LDO5CTRL_H,
+			.enable_reg = PCA9450_REG_LDO5CTRL_L,
 			.enable_mask = LDO5H_EN_MASK,
 			.owner = THIS_MODULE,
 		},
@@ -835,7 +835,7 @@ static const struct pca9450_regulator_desc pca9451a_regulators[] = {
 			.n_linear_ranges = ARRAY_SIZE(pca9450_ldo5_volts),
 			.vsel_reg = PCA9450_REG_LDO5CTRL_H,
 			.vsel_mask = LDO5HOUT_MASK,
-			.enable_reg = PCA9450_REG_LDO5CTRL_H,
+			.enable_reg = PCA9450_REG_LDO5CTRL_L,
 			.enable_mask = LDO5H_EN_MASK,
 			.owner = THIS_MODULE,
 		},
diff --git a/drivers/regulator/rk808-regulator.c b/drivers/regulator/rk808-regulator.c
index 37476d2558fd..72df554b6375 100644
--- a/drivers/regulator/rk808-regulator.c
+++ b/drivers/regulator/rk808-regulator.c
@@ -270,8 +270,8 @@ static const unsigned int rk817_buck1_4_ramp_table[] = {
 
 static int rk806_set_mode_dcdc(struct regulator_dev *rdev, unsigned int mode)
 {
-	int rid = rdev_get_id(rdev);
-	int ctr_bit, reg;
+	unsigned int rid = rdev_get_id(rdev);
+	unsigned int ctr_bit, reg;
 
 	reg = RK806_POWER_FPWM_EN0 + rid / 8;
 	ctr_bit = rid % 8;
diff --git a/drivers/remoteproc/imx_rproc.c b/drivers/remoteproc/imx_rproc.c
index 800015ff7ff9..cc3f5b7fe9dd 100644
--- a/drivers/remoteproc/imx_rproc.c
+++ b/drivers/remoteproc/imx_rproc.c
@@ -1029,8 +1029,8 @@ static int imx_rproc_clk_enable(struct imx_rproc *priv)
 	struct device *dev = priv->dev;
 	int ret;
 
-	/* Remote core is not under control of Linux */
-	if (dcfg->method == IMX_RPROC_NONE)
+	/* Remote core is not under control of Linux or it is managed by SCU API */
+	if (dcfg->method == IMX_RPROC_NONE || dcfg->method == IMX_RPROC_SCU_API)
 		return 0;
 
 	priv->clk = devm_clk_get(dev, NULL);
diff --git a/drivers/remoteproc/mtk_scp.c b/drivers/remoteproc/mtk_scp.c
index e744c07507ee..f98a11d4cf29 100644
--- a/drivers/remoteproc/mtk_scp.c
+++ b/drivers/remoteproc/mtk_scp.c
@@ -1326,6 +1326,11 @@ static int scp_cluster_init(struct platform_device *pdev, struct mtk_scp_of_clus
 	return ret;
 }
 
+static const struct of_device_id scp_core_match[] = {
+	{ .compatible = "mediatek,scp-core" },
+	{}
+};
+
 static int scp_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -1357,13 +1362,15 @@ static int scp_probe(struct platform_device *pdev)
 	INIT_LIST_HEAD(&scp_cluster->mtk_scp_list);
 	mutex_init(&scp_cluster->cluster_lock);
 
-	ret = devm_of_platform_populate(dev);
+	ret = of_platform_populate(dev_of_node(dev), scp_core_match, NULL, dev);
 	if (ret)
 		return dev_err_probe(dev, ret, "Failed to populate platform devices\n");
 
 	ret = scp_cluster_init(pdev, scp_cluster);
-	if (ret)
+	if (ret) {
+		of_platform_depopulate(dev);
 		return ret;
+	}
 
 	return 0;
 }
@@ -1379,6 +1386,7 @@ static void scp_remove(struct platform_device *pdev)
 		rproc_del(scp->rproc);
 		scp_free(scp);
 	}
+	of_platform_depopulate(&pdev->dev);
 	mutex_destroy(&scp_cluster->cluster_lock);
 }
 
diff --git a/drivers/remoteproc/omap_remoteproc.c b/drivers/remoteproc/omap_remoteproc.c
index 9ae2e831456d..3260dd512491 100644
--- a/drivers/remoteproc/omap_remoteproc.c
+++ b/drivers/remoteproc/omap_remoteproc.c
@@ -37,6 +37,10 @@
 
 #include <linux/platform_data/dmtimer-omap.h>
 
+#ifdef CONFIG_ARM_DMA_USE_IOMMU
+#include <asm/dma-iommu.h>
+#endif
+
 #include "omap_remoteproc.h"
 #include "remoteproc_internal.h"
 
@@ -1323,6 +1327,19 @@ static int omap_rproc_probe(struct platform_device *pdev)
 	/* All existing OMAP IPU and DSP processors have an MMU */
 	rproc->has_iommu = true;
 
+#ifdef CONFIG_ARM_DMA_USE_IOMMU
+	/*
+	 * Throw away the ARM DMA mapping that we'll never use, so it doesn't
+	 * interfere with the core rproc->domain and we get the right DMA ops.
+	 */
+	if (pdev->dev.archdata.mapping) {
+		struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(&pdev->dev);
+
+		arm_iommu_detach_device(&pdev->dev);
+		arm_iommu_release_mapping(mapping);
+	}
+#endif
+
 	ret = omap_rproc_of_get_internal_memories(pdev, rproc);
 	if (ret)
 		return ret;
diff --git a/drivers/remoteproc/qcom_q6v5_mss.c b/drivers/remoteproc/qcom_q6v5_mss.c
index 32c3531b20c7..e19081d53022 100644
--- a/drivers/remoteproc/qcom_q6v5_mss.c
+++ b/drivers/remoteproc/qcom_q6v5_mss.c
@@ -1839,6 +1839,13 @@ static int q6v5_pds_attach(struct device *dev, struct device **devs,
 	while (pd_names[num_pds])
 		num_pds++;
 
+	/* Handle single power domain */
+	if (num_pds == 1 && dev->pm_domain) {
+		devs[0] = dev;
+		pm_runtime_enable(dev);
+		return 1;
+	}
+
 	for (i = 0; i < num_pds; i++) {
 		devs[i] = dev_pm_domain_attach_by_name(dev, pd_names[i]);
 		if (IS_ERR_OR_NULL(devs[i])) {
@@ -1859,8 +1866,15 @@ unroll_attach:
 static void q6v5_pds_detach(struct q6v5 *qproc, struct device **pds,
 			    size_t pd_count)
 {
+	struct device *dev = qproc->dev;
 	int i;
 
+	/* Handle single power domain */
+	if (pd_count == 1 && dev->pm_domain) {
+		pm_runtime_disable(dev);
+		return;
+	}
+
 	for (i = 0; i < pd_count; i++)
 		dev_pm_domain_detach(pds[i], false);
 }
@@ -2469,13 +2483,13 @@ static const struct rproc_hexagon_res msm8974_mss = {
 			.supply = "pll",
 			.uA = 100000,
 		},
-		{}
-	},
-	.fallback_proxy_supply = (struct qcom_mss_reg_res[]) {
 		{
 			.supply = "mx",
 			.uV = 1050000,
 		},
+		{}
+	},
+	.fallback_proxy_supply = (struct qcom_mss_reg_res[]) {
 		{
 			.supply = "cx",
 			.uA = 100000,
@@ -2501,7 +2515,6 @@ static const struct rproc_hexagon_res msm8974_mss = {
 		NULL
 	},
 	.proxy_pd_names = (char*[]){
-		"mx",
 		"cx",
 		NULL
 	},
diff --git a/drivers/remoteproc/qcom_q6v5_pas.c b/drivers/remoteproc/qcom_q6v5_pas.c
index 1a2d08ec9de9..ea4a91f37b50 100644
--- a/drivers/remoteproc/qcom_q6v5_pas.c
+++ b/drivers/remoteproc/qcom_q6v5_pas.c
@@ -509,16 +509,16 @@ static int adsp_pds_attach(struct device *dev, struct device **devs,
 	if (!pd_names)
 		return 0;
 
+	while (pd_names[num_pds])
+		num_pds++;
+
 	/* Handle single power domain */
-	if (dev->pm_domain) {
+	if (num_pds == 1 && dev->pm_domain) {
 		devs[0] = dev;
 		pm_runtime_enable(dev);
 		return 1;
 	}
 
-	while (pd_names[num_pds])
-		num_pds++;
-
 	for (i = 0; i < num_pds; i++) {
 		devs[i] = dev_pm_domain_attach_by_name(dev, pd_names[i]);
 		if (IS_ERR_OR_NULL(devs[i])) {
@@ -543,7 +543,7 @@ static void adsp_pds_detach(struct qcom_adsp *adsp, struct device **pds,
 	int i;
 
 	/* Handle single power domain */
-	if (dev->pm_domain && pd_count) {
+	if (pd_count == 1 && dev->pm_domain) {
 		pm_runtime_disable(dev);
 		return;
 	}
@@ -1356,6 +1356,7 @@ static const struct adsp_data sc7280_wpss_resource = {
 	.crash_reason_smem = 626,
 	.firmware_name = "wpss.mdt",
 	.pas_id = 6,
+	.minidump_id = 4,
 	.auto_boot = false,
 	.proxy_pd_names = (char*[]){
 		"cx",
@@ -1418,7 +1419,7 @@ static const struct adsp_data sm8650_mpss_resource = {
 };
 
 static const struct of_device_id adsp_of_match[] = {
-	{ .compatible = "qcom,msm8226-adsp-pil", .data = &adsp_resource_init},
+	{ .compatible = "qcom,msm8226-adsp-pil", .data = &msm8996_adsp_resource},
 	{ .compatible = "qcom,msm8953-adsp-pil", .data = &msm8996_adsp_resource},
 	{ .compatible = "qcom,msm8974-adsp-pil", .data = &adsp_resource_init},
 	{ .compatible = "qcom,msm8996-adsp-pil", .data = &msm8996_adsp_resource},
diff --git a/drivers/remoteproc/qcom_wcnss.c b/drivers/remoteproc/qcom_wcnss.c
index a7bb9da27029..a2ae6adf0053 100644
--- a/drivers/remoteproc/qcom_wcnss.c
+++ b/drivers/remoteproc/qcom_wcnss.c
@@ -117,10 +117,10 @@ static const struct wcnss_data pronto_v1_data = {
 	.pmu_offset = 0x1004,
 	.spare_offset = 0x1088,
 
-	.pd_names = { "mx", "cx" },
+	.pd_names = { "cx", "mx" },
 	.vregs = (struct wcnss_vreg_info[]) {
-		{ "vddmx", 950000, 1150000, 0 },
 		{ "vddcx", .super_turbo = true},
+		{ "vddmx", 950000, 1150000, 0 },
 		{ "vddpx", 1800000, 1800000, 0 },
 	},
 	.num_pd_vregs = 2,
@@ -131,10 +131,10 @@ static const struct wcnss_data pronto_v2_data = {
 	.pmu_offset = 0x1004,
 	.spare_offset = 0x1088,
 
-	.pd_names = { "mx", "cx" },
+	.pd_names = { "cx", "mx" },
 	.vregs = (struct wcnss_vreg_info[]) {
-		{ "vddmx", 1287500, 1287500, 0 },
 		{ "vddcx", .super_turbo = true },
+		{ "vddmx", 1287500, 1287500, 0 },
 		{ "vddpx", 1800000, 1800000, 0 },
 	},
 	.num_pd_vregs = 2,
@@ -397,8 +397,17 @@ static irqreturn_t wcnss_stop_ack_interrupt(int irq, void *dev)
 static int wcnss_init_pds(struct qcom_wcnss *wcnss,
 			  const char * const pd_names[WCNSS_MAX_PDS])
 {
+	struct device *dev = wcnss->dev;
 	int i, ret;
 
+	/* Handle single power domain */
+	if (dev->pm_domain) {
+		wcnss->pds[0] = dev;
+		wcnss->num_pds = 1;
+		pm_runtime_enable(dev);
+		return 0;
+	}
+
 	for (i = 0; i < WCNSS_MAX_PDS; i++) {
 		if (!pd_names[i])
 			break;
@@ -418,8 +427,15 @@ static int wcnss_init_pds(struct qcom_wcnss *wcnss,
 
 static void wcnss_release_pds(struct qcom_wcnss *wcnss)
 {
+	struct device *dev = wcnss->dev;
 	int i;
 
+	/* Handle single power domain */
+	if (wcnss->num_pds == 1 && dev->pm_domain) {
+		pm_runtime_disable(dev);
+		return;
+	}
+
 	for (i = 0; i < wcnss->num_pds; i++)
 		dev_pm_domain_detach(wcnss->pds[i], false);
 }
@@ -437,10 +453,14 @@ static int wcnss_init_regulators(struct qcom_wcnss *wcnss,
 	 * the regulators for the power domains. For old device trees we need to
 	 * reserve extra space to manage them through the regulator interface.
 	 */
-	if (wcnss->num_pds)
-		info += num_pd_vregs;
-	else
+	if (wcnss->num_pds) {
+		info += wcnss->num_pds;
+		/* Handle single power domain case */
+		if (wcnss->num_pds < num_pd_vregs)
+			num_vregs += num_pd_vregs - wcnss->num_pds;
+	} else {
 		num_vregs += num_pd_vregs;
+	}
 
 	bulk = devm_kcalloc(wcnss->dev,
 			    num_vregs, sizeof(struct regulator_bulk_data),
diff --git a/drivers/remoteproc/qcom_wcnss_iris.c b/drivers/remoteproc/qcom_wcnss_iris.c
index dd36fd077911..1e197f773474 100644
--- a/drivers/remoteproc/qcom_wcnss_iris.c
+++ b/drivers/remoteproc/qcom_wcnss_iris.c
@@ -197,6 +197,7 @@ struct qcom_iris *qcom_iris_probe(struct device *parent, bool *use_48mhz_xo)
 
 err_device_del:
 	device_del(&iris->dev);
+	put_device(&iris->dev);
 
 	return ERR_PTR(ret);
 }
@@ -204,4 +205,5 @@ err_device_del:
 void qcom_iris_remove(struct qcom_iris *iris)
 {
 	device_del(&iris->dev);
+	put_device(&iris->dev);
 }
diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c
index f276956f2c5c..b7011eb384a5 100644
--- a/drivers/remoteproc/remoteproc_core.c
+++ b/drivers/remoteproc/remoteproc_core.c
@@ -1617,7 +1617,7 @@ static int rproc_attach(struct rproc *rproc)
 	ret = rproc_set_rsc_table(rproc);
 	if (ret) {
 		dev_err(dev, "can't load resource table: %d\n", ret);
-		goto unprepare_device;
+		goto clean_up_resources;
 	}
 
 	/* reset max_notifyid */
@@ -1634,7 +1634,7 @@ static int rproc_attach(struct rproc *rproc)
 	ret = rproc_handle_resources(rproc, rproc_loading_handlers);
 	if (ret) {
 		dev_err(dev, "Failed to process resources: %d\n", ret);
-		goto unprepare_device;
+		goto clean_up_resources;
 	}
 
 	/* Allocate carveout resources associated to rproc */
@@ -1653,9 +1653,9 @@ static int rproc_attach(struct rproc *rproc)
 
 clean_up_resources:
 	rproc_resource_cleanup(rproc);
-unprepare_device:
 	/* release HW resources if needed */
 	rproc_unprepare_device(rproc);
+	kfree(rproc->clean_table);
 disable_iommu:
 	rproc_disable_iommu(rproc);
 	return ret;
@@ -2025,6 +2025,7 @@ int rproc_shutdown(struct rproc *rproc)
 	kfree(rproc->cached_table);
 	rproc->cached_table = NULL;
 	rproc->table_ptr = NULL;
+	rproc->table_sz = 0;
 out:
 	mutex_unlock(&rproc->lock);
 	return ret;
@@ -2486,6 +2487,13 @@ struct rproc *rproc_alloc(struct device *dev, const char *name,
 	rproc->dev.driver_data = rproc;
 	idr_init(&rproc->notifyids);
 
+	/* Assign a unique device index and name */
+	rproc->index = ida_alloc(&rproc_dev_index, GFP_KERNEL);
+	if (rproc->index < 0) {
+		dev_err(dev, "ida_alloc failed: %d\n", rproc->index);
+		goto put_device;
+	}
+
 	rproc->name = kstrdup_const(name, GFP_KERNEL);
 	if (!rproc->name)
 		goto put_device;
@@ -2496,13 +2504,6 @@ struct rproc *rproc_alloc(struct device *dev, const char *name,
 	if (rproc_alloc_ops(rproc, ops))
 		goto put_device;
 
-	/* Assign a unique device index and name */
-	rproc->index = ida_alloc(&rproc_dev_index, GFP_KERNEL);
-	if (rproc->index < 0) {
-		dev_err(dev, "ida_alloc failed: %d\n", rproc->index);
-		goto put_device;
-	}
-
 	dev_set_name(&rproc->dev, "remoteproc%d", rproc->index);
 
 	atomic_set(&rproc->power, 0);
diff --git a/drivers/remoteproc/ti_k3_dsp_remoteproc.c b/drivers/remoteproc/ti_k3_dsp_remoteproc.c
index 8be3f631c192..73be3d216791 100644
--- a/drivers/remoteproc/ti_k3_dsp_remoteproc.c
+++ b/drivers/remoteproc/ti_k3_dsp_remoteproc.c
@@ -115,10 +115,6 @@ static void k3_dsp_rproc_mbox_callback(struct mbox_client *client, void *data)
 	const char *name = kproc->rproc->name;
 	u32 msg = omap_mbox_message(data);
 
-	/* Do not forward messages from a detached core */
-	if (kproc->rproc->state == RPROC_DETACHED)
-		return;
-
 	dev_dbg(dev, "mbox msg: 0x%x\n", msg);
 
 	switch (msg) {
@@ -159,10 +155,6 @@ static void k3_dsp_rproc_kick(struct rproc *rproc, int vqid)
 	mbox_msg_t msg = (mbox_msg_t)vqid;
 	int ret;
 
-	/* Do not forward messages to a detached core */
-	if (kproc->rproc->state == RPROC_DETACHED)
-		return;
-
 	/* send the index of the triggered virtqueue in the mailbox payload */
 	ret = mbox_send_message(kproc->mbox, (void *)msg);
 	if (ret < 0)
@@ -576,11 +568,9 @@ static int k3_dsp_reserved_mem_init(struct k3_dsp_rproc *kproc)
 			return -EINVAL;
 
 		rmem = of_reserved_mem_lookup(rmem_np);
-		if (!rmem) {
-			of_node_put(rmem_np);
-			return -EINVAL;
-		}
 		of_node_put(rmem_np);
+		if (!rmem)
+			return -EINVAL;
 
 		kproc->rmem[i].bus_addr = rmem->base;
 		/* 64-bit address regions currently not supported */
diff --git a/drivers/remoteproc/ti_k3_m4_remoteproc.c b/drivers/remoteproc/ti_k3_m4_remoteproc.c
index 09f0484a90e1..6cd50b16a8e8 100644
--- a/drivers/remoteproc/ti_k3_m4_remoteproc.c
+++ b/drivers/remoteproc/ti_k3_m4_remoteproc.c
@@ -228,7 +228,7 @@ static int k3_m4_rproc_unprepare(struct rproc *rproc)
 	int ret;
 
 	/* If the core is going to be detached do not assert the module reset */
-	if (rproc->state == RPROC_ATTACHED)
+	if (rproc->state == RPROC_DETACHED)
 		return 0;
 
 	ret = kproc->ti_sci->ops.dev_ops.put_device(kproc->ti_sci,
@@ -433,11 +433,9 @@ static int k3_m4_reserved_mem_init(struct k3_m4_rproc *kproc)
 			return -EINVAL;
 
 		rmem = of_reserved_mem_lookup(rmem_np);
-		if (!rmem) {
-			of_node_put(rmem_np);
-			return -EINVAL;
-		}
 		of_node_put(rmem_np);
+		if (!rmem)
+			return -EINVAL;
 
 		kproc->rmem[i].bus_addr = rmem->base;
 		/* 64-bit address regions currently not supported */
diff --git a/drivers/remoteproc/ti_k3_r5_remoteproc.c b/drivers/remoteproc/ti_k3_r5_remoteproc.c
index 747ee467da88..941bb130c85c 100644
--- a/drivers/remoteproc/ti_k3_r5_remoteproc.c
+++ b/drivers/remoteproc/ti_k3_r5_remoteproc.c
@@ -194,10 +194,6 @@ static void k3_r5_rproc_mbox_callback(struct mbox_client *client, void *data)
 	const char *name = kproc->rproc->name;
 	u32 msg = omap_mbox_message(data);
 
-	/* Do not forward message from a detached core */
-	if (kproc->rproc->state == RPROC_DETACHED)
-		return;
-
 	dev_dbg(dev, "mbox msg: 0x%x\n", msg);
 
 	switch (msg) {
@@ -233,10 +229,6 @@ static void k3_r5_rproc_kick(struct rproc *rproc, int vqid)
 	mbox_msg_t msg = (mbox_msg_t)vqid;
 	int ret;
 
-	/* Do not forward message to a detached core */
-	if (kproc->rproc->state == RPROC_DETACHED)
-		return;
-
 	/* send the index of the triggered virtqueue in the mailbox payload */
 	ret = mbox_send_message(kproc->mbox, (void *)msg);
 	if (ret < 0)
@@ -448,13 +440,36 @@ static int k3_r5_rproc_prepare(struct rproc *rproc)
 {
 	struct k3_r5_rproc *kproc = rproc->priv;
 	struct k3_r5_cluster *cluster = kproc->cluster;
-	struct k3_r5_core *core = kproc->core;
+	struct k3_r5_core *core = kproc->core, *core0, *core1;
 	struct device *dev = kproc->dev;
 	u32 ctrl = 0, cfg = 0, stat = 0;
 	u64 boot_vec = 0;
 	bool mem_init_dis;
 	int ret;
 
+	/*
+	 * R5 cores require to be powered on sequentially, core0 should be in
+	 * higher power state than core1 in a cluster. So, wait for core0 to
+	 * power up before proceeding to core1 and put timeout of 2sec. This
+	 * waiting mechanism is necessary because rproc_auto_boot_callback() for
+	 * core1 can be called before core0 due to thread execution order.
+	 *
+	 * By placing the wait mechanism here in .prepare() ops, this condition
+	 * is enforced for rproc boot requests from sysfs as well.
+	 */
+	core0 = list_first_entry(&cluster->cores, struct k3_r5_core, elem);
+	core1 = list_last_entry(&cluster->cores, struct k3_r5_core, elem);
+	if (cluster->mode == CLUSTER_MODE_SPLIT && core == core1 &&
+	    !core0->released_from_reset) {
+		ret = wait_event_interruptible_timeout(cluster->core_transition,
+						       core0->released_from_reset,
+						       msecs_to_jiffies(2000));
+		if (ret <= 0) {
+			dev_err(dev, "can not power up core1 before core0");
+			return -EPERM;
+		}
+	}
+
 	ret = ti_sci_proc_get_status(core->tsp, &boot_vec, &cfg, &ctrl, &stat);
 	if (ret < 0)
 		return ret;
@@ -471,6 +486,14 @@ static int k3_r5_rproc_prepare(struct rproc *rproc)
 	}
 
 	/*
+	 * Notify all threads in the wait queue when core0 state has changed so
+	 * that threads waiting for this condition can be executed.
+	 */
+	core->released_from_reset = true;
+	if (core == core0)
+		wake_up_interruptible(&cluster->core_transition);
+
+	/*
 	 * Newer IP revisions like on J7200 SoCs support h/w auto-initialization
 	 * of TCMs, so there is no need to perform the s/w memzero. This bit is
 	 * configurable through System Firmware, the default value does perform
@@ -515,10 +538,30 @@ static int k3_r5_rproc_unprepare(struct rproc *rproc)
 {
 	struct k3_r5_rproc *kproc = rproc->priv;
 	struct k3_r5_cluster *cluster = kproc->cluster;
-	struct k3_r5_core *core = kproc->core;
+	struct k3_r5_core *core = kproc->core, *core0, *core1;
 	struct device *dev = kproc->dev;
 	int ret;
 
+	/*
+	 * Ensure power-down of cores is sequential in split mode. Core1 must
+	 * power down before Core0 to maintain the expected state. By placing
+	 * the wait mechanism here in .unprepare() ops, this condition is
+	 * enforced for rproc stop or shutdown requests from sysfs and device
+	 * removal as well.
+	 */
+	core0 = list_first_entry(&cluster->cores, struct k3_r5_core, elem);
+	core1 = list_last_entry(&cluster->cores, struct k3_r5_core, elem);
+	if (cluster->mode == CLUSTER_MODE_SPLIT && core == core0 &&
+	    core1->released_from_reset) {
+		ret = wait_event_interruptible_timeout(cluster->core_transition,
+						       !core1->released_from_reset,
+						       msecs_to_jiffies(2000));
+		if (ret <= 0) {
+			dev_err(dev, "can not power down core0 before core1");
+			return -EPERM;
+		}
+	}
+
 	/* Re-use LockStep-mode reset logic for Single-CPU mode */
 	ret = (cluster->mode == CLUSTER_MODE_LOCKSTEP ||
 	       cluster->mode == CLUSTER_MODE_SINGLECPU) ?
@@ -526,6 +569,14 @@ static int k3_r5_rproc_unprepare(struct rproc *rproc)
 	if (ret)
 		dev_err(dev, "unable to disable cores, ret = %d\n", ret);
 
+	/*
+	 * Notify all threads in the wait queue when core1 state has changed so
+	 * that threads waiting for this condition can be executed.
+	 */
+	core->released_from_reset = false;
+	if (core == core1)
+		wake_up_interruptible(&cluster->core_transition);
+
 	return ret;
 }
 
@@ -551,7 +602,7 @@ static int k3_r5_rproc_start(struct rproc *rproc)
 	struct k3_r5_rproc *kproc = rproc->priv;
 	struct k3_r5_cluster *cluster = kproc->cluster;
 	struct device *dev = kproc->dev;
-	struct k3_r5_core *core0, *core;
+	struct k3_r5_core *core;
 	u32 boot_addr;
 	int ret;
 
@@ -573,21 +624,9 @@ static int k3_r5_rproc_start(struct rproc *rproc)
 				goto unroll_core_run;
 		}
 	} else {
-		/* do not allow core 1 to start before core 0 */
-		core0 = list_first_entry(&cluster->cores, struct k3_r5_core,
-					 elem);
-		if (core != core0 && core0->rproc->state == RPROC_OFFLINE) {
-			dev_err(dev, "%s: can not start core 1 before core 0\n",
-				__func__);
-			return -EPERM;
-		}
-
 		ret = k3_r5_core_run(core);
 		if (ret)
 			return ret;
-
-		core->released_from_reset = true;
-		wake_up_interruptible(&cluster->core_transition);
 	}
 
 	return 0;
@@ -628,8 +667,7 @@ static int k3_r5_rproc_stop(struct rproc *rproc)
 {
 	struct k3_r5_rproc *kproc = rproc->priv;
 	struct k3_r5_cluster *cluster = kproc->cluster;
-	struct device *dev = kproc->dev;
-	struct k3_r5_core *core1, *core = kproc->core;
+	struct k3_r5_core *core = kproc->core;
 	int ret;
 
 	/* halt all applicable cores */
@@ -642,16 +680,6 @@ static int k3_r5_rproc_stop(struct rproc *rproc)
 			}
 		}
 	} else {
-		/* do not allow core 0 to stop before core 1 */
-		core1 = list_last_entry(&cluster->cores, struct k3_r5_core,
-					elem);
-		if (core != core1 && core1->rproc->state != RPROC_OFFLINE) {
-			dev_err(dev, "%s: can not stop core 0 before core 1\n",
-				__func__);
-			ret = -EPERM;
-			goto out;
-		}
-
 		ret = k3_r5_core_halt(core);
 		if (ret)
 			goto out;
@@ -955,6 +983,13 @@ out:
 	return ret;
 }
 
+static void k3_r5_mem_release(void *data)
+{
+	struct device *dev = data;
+
+	of_reserved_mem_device_release(dev);
+}
+
 static int k3_r5_reserved_mem_init(struct k3_r5_rproc *kproc)
 {
 	struct device *dev = kproc->dev;
@@ -985,28 +1020,25 @@ static int k3_r5_reserved_mem_init(struct k3_r5_rproc *kproc)
 		return ret;
 	}
 
+	ret = devm_add_action_or_reset(dev, k3_r5_mem_release, dev);
+	if (ret)
+		return ret;
+
 	num_rmems--;
-	kproc->rmem = kcalloc(num_rmems, sizeof(*kproc->rmem), GFP_KERNEL);
-	if (!kproc->rmem) {
-		ret = -ENOMEM;
-		goto release_rmem;
-	}
+	kproc->rmem = devm_kcalloc(dev, num_rmems, sizeof(*kproc->rmem), GFP_KERNEL);
+	if (!kproc->rmem)
+		return -ENOMEM;
 
 	/* use remaining reserved memory regions for static carveouts */
 	for (i = 0; i < num_rmems; i++) {
 		rmem_np = of_parse_phandle(np, "memory-region", i + 1);
-		if (!rmem_np) {
-			ret = -EINVAL;
-			goto unmap_rmem;
-		}
+		if (!rmem_np)
+			return -EINVAL;
 
 		rmem = of_reserved_mem_lookup(rmem_np);
-		if (!rmem) {
-			of_node_put(rmem_np);
-			ret = -EINVAL;
-			goto unmap_rmem;
-		}
 		of_node_put(rmem_np);
+		if (!rmem)
+			return -EINVAL;
 
 		kproc->rmem[i].bus_addr = rmem->base;
 		/*
@@ -1021,12 +1053,11 @@ static int k3_r5_reserved_mem_init(struct k3_r5_rproc *kproc)
 		 */
 		kproc->rmem[i].dev_addr = (u32)rmem->base;
 		kproc->rmem[i].size = rmem->size;
-		kproc->rmem[i].cpu_addr = ioremap_wc(rmem->base, rmem->size);
+		kproc->rmem[i].cpu_addr = devm_ioremap_wc(dev, rmem->base, rmem->size);
 		if (!kproc->rmem[i].cpu_addr) {
 			dev_err(dev, "failed to map reserved memory#%d at %pa of size %pa\n",
 				i + 1, &rmem->base, &rmem->size);
-			ret = -ENOMEM;
-			goto unmap_rmem;
+			return -ENOMEM;
 		}
 
 		dev_dbg(dev, "reserved memory%d: bus addr %pa size 0x%zx va %pK da 0x%x\n",
@@ -1037,25 +1068,6 @@ static int k3_r5_reserved_mem_init(struct k3_r5_rproc *kproc)
 	kproc->num_rmems = num_rmems;
 
 	return 0;
-
-unmap_rmem:
-	for (i--; i >= 0; i--)
-		iounmap(kproc->rmem[i].cpu_addr);
-	kfree(kproc->rmem);
-release_rmem:
-	of_reserved_mem_device_release(dev);
-	return ret;
-}
-
-static void k3_r5_reserved_mem_exit(struct k3_r5_rproc *kproc)
-{
-	int i;
-
-	for (i = 0; i < kproc->num_rmems; i++)
-		iounmap(kproc->rmem[i].cpu_addr);
-	kfree(kproc->rmem);
-
-	of_reserved_mem_device_release(kproc->dev);
 }
 
 /*
@@ -1282,10 +1294,10 @@ init_rmem:
 			goto out;
 		}
 
-		ret = rproc_add(rproc);
+		ret = devm_rproc_add(dev, rproc);
 		if (ret) {
-			dev_err(dev, "rproc_add failed, ret = %d\n", ret);
-			goto err_add;
+			dev_err_probe(dev, ret, "rproc_add failed\n");
+			goto out;
 		}
 
 		/* create only one rproc in lockstep, single-cpu or
@@ -1295,26 +1307,6 @@ init_rmem:
 		    cluster->mode == CLUSTER_MODE_SINGLECPU ||
 		    cluster->mode == CLUSTER_MODE_SINGLECORE)
 			break;
-
-		/*
-		 * R5 cores require to be powered on sequentially, core0
-		 * should be in higher power state than core1 in a cluster
-		 * So, wait for current core to power up before proceeding
-		 * to next core and put timeout of 2sec for each core.
-		 *
-		 * This waiting mechanism is necessary because
-		 * rproc_auto_boot_callback() for core1 can be called before
-		 * core0 due to thread execution order.
-		 */
-		ret = wait_event_interruptible_timeout(cluster->core_transition,
-						       core->released_from_reset,
-						       msecs_to_jiffies(2000));
-		if (ret <= 0) {
-			dev_err(dev,
-				"Timed out waiting for %s core to power up!\n",
-				rproc->name);
-			goto err_powerup;
-		}
 	}
 
 	return 0;
@@ -1329,10 +1321,6 @@ err_split:
 		}
 	}
 
-err_powerup:
-	rproc_del(rproc);
-err_add:
-	k3_r5_reserved_mem_exit(kproc);
 out:
 	/* undo core0 upon any failures on core1 in split-mode */
 	if (cluster->mode == CLUSTER_MODE_SPLIT && core == core1) {
@@ -1375,10 +1363,6 @@ static void k3_r5_cluster_rproc_exit(void *data)
 		}
 
 		mbox_free_channel(kproc->mbox);
-
-		rproc_del(rproc);
-
-		k3_r5_reserved_mem_exit(kproc);
 	}
 }
 
diff --git a/drivers/remoteproc/xlnx_r5_remoteproc.c b/drivers/remoteproc/xlnx_r5_remoteproc.c
index 5aeedeaf3c41..c165422d0651 100644
--- a/drivers/remoteproc/xlnx_r5_remoteproc.c
+++ b/drivers/remoteproc/xlnx_r5_remoteproc.c
@@ -906,6 +906,8 @@ static struct zynqmp_r5_core *zynqmp_r5_add_rproc_core(struct device *cdev)
 
 	rproc_coredump_set_elf_info(r5_rproc, ELFCLASS32, EM_ARM);
 
+	r5_rproc->recovery_disabled = true;
+	r5_rproc->has_iommu = false;
 	r5_rproc->auto_boot = false;
 	r5_core = r5_rproc->priv;
 	r5_core->dev = cdev;
diff --git a/drivers/reset/Kconfig b/drivers/reset/Kconfig
index 5484a65f66b9..1cf577e3223b 100644
--- a/drivers/reset/Kconfig
+++ b/drivers/reset/Kconfig
@@ -51,8 +51,8 @@ config RESET_BERLIN
 
 config RESET_BRCMSTB
 	tristate "Broadcom STB reset controller"
-	depends on ARCH_BRCMSTB || COMPILE_TEST
-	default ARCH_BRCMSTB
+	depends on ARCH_BRCMSTB || ARCH_BCM2835 || COMPILE_TEST
+	default ARCH_BRCMSTB || ARCH_BCM2835
 	help
 	  This enables the reset controller driver for Broadcom STB SoCs using
 	  a SUN_TOP_CTRL_SW_INIT style controller.
@@ -60,11 +60,11 @@ config RESET_BRCMSTB
 config RESET_BRCMSTB_RESCAL
 	tristate "Broadcom STB RESCAL reset controller"
 	depends on HAS_IOMEM
-	depends on ARCH_BRCMSTB || COMPILE_TEST
-	default ARCH_BRCMSTB
+	depends on ARCH_BRCMSTB || ARCH_BCM2835 || COMPILE_TEST
+	default ARCH_BRCMSTB || ARCH_BCM2835
 	help
 	  This enables the RESCAL reset controller for SATA, PCIe0, or PCIe1 on
-	  BCM7216.
+	  BCM7216 or the BCM2712.
 
 config RESET_EYEQ
 	bool "Mobileye EyeQ reset controller"
diff --git a/drivers/rpmsg/qcom_smd.c b/drivers/rpmsg/qcom_smd.c
index 43f601c84b4f..79d35ab43729 100644
--- a/drivers/rpmsg/qcom_smd.c
+++ b/drivers/rpmsg/qcom_smd.c
@@ -746,7 +746,7 @@ static int __qcom_smd_send(struct qcom_smd_channel *channel, const void *data,
 	__le32 hdr[5] = { cpu_to_le32(len), };
 	int tlen = sizeof(hdr) + len;
 	unsigned long flags;
-	int ret;
+	int ret = 0;
 
 	/* Word aligned channels only accept word size aligned data */
 	if (channel->info_word && len % 4)
diff --git a/drivers/rtc/class.c b/drivers/rtc/class.c
index e31fa0ad127e..a0afdeaac270 100644
--- a/drivers/rtc/class.c
+++ b/drivers/rtc/class.c
@@ -327,7 +327,7 @@ static void rtc_device_get_offset(struct rtc_device *rtc)
 	 *
 	 * Otherwise the offset seconds should be 0.
 	 */
-	if (rtc->start_secs > rtc->range_max ||
+	if ((rtc->start_secs >= 0 && rtc->start_secs > rtc->range_max) ||
 	    rtc->start_secs + range_secs - 1 < rtc->range_min)
 		rtc->offset_secs = rtc->start_secs - rtc->range_min;
 	else if (rtc->start_secs > rtc->range_min)
diff --git a/drivers/rtc/lib.c b/drivers/rtc/lib.c
index fe361652727a..13b5b1f20465 100644
--- a/drivers/rtc/lib.c
+++ b/drivers/rtc/lib.c
@@ -46,24 +46,38 @@ EXPORT_SYMBOL(rtc_year_days);
  * rtc_time64_to_tm - converts time64_t to rtc_time.
  *
  * @time:	The number of seconds since 01-01-1970 00:00:00.
- *		(Must be positive.)
+ *		Works for values since at least 1900
  * @tm:		Pointer to the struct rtc_time.
  */
 void rtc_time64_to_tm(time64_t time, struct rtc_time *tm)
 {
-	unsigned int secs;
-	int days;
+	int days, secs;
 
 	u64 u64tmp;
 	u32 u32tmp, udays, century, day_of_century, year_of_century, year,
 		day_of_year, month, day;
 	bool is_Jan_or_Feb, is_leap_year;
 
-	/* time must be positive */
+	/*
+	 * Get days and seconds while preserving the sign to
+	 * handle negative time values (dates before 1970-01-01)
+	 */
 	days = div_s64_rem(time, 86400, &secs);
 
+	/*
+	 * We need 0 <= secs < 86400 which isn't given for negative
+	 * values of time. Fixup accordingly.
+	 */
+	if (secs < 0) {
+		days -= 1;
+		secs += 86400;
+	}
+
 	/* day of the week, 1970-01-01 was a Thursday */
 	tm->tm_wday = (days + 4) % 7;
+	/* Ensure tm_wday is always positive */
+	if (tm->tm_wday < 0)
+		tm->tm_wday += 7;
 
 	/*
 	 * The following algorithm is, basically, Proposition 6.3 of Neri
@@ -93,7 +107,7 @@ void rtc_time64_to_tm(time64_t time, struct rtc_time *tm)
 	 * thus, is slightly different from [1].
 	 */
 
-	udays		= ((u32) days) + 719468;
+	udays		= days + 719468;
 
 	u32tmp		= 4 * udays + 3;
 	century		= u32tmp / 146097;
diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c
index 5849d2970bba..095de4e0e4f3 100644
--- a/drivers/rtc/rtc-cmos.c
+++ b/drivers/rtc/rtc-cmos.c
@@ -697,8 +697,12 @@ static irqreturn_t cmos_interrupt(int irq, void *p)
 {
 	u8		irqstat;
 	u8		rtc_control;
+	unsigned long	flags;
 
-	spin_lock(&rtc_lock);
+	/* We cannot use spin_lock() here, as cmos_interrupt() is also called
+	 * in a non-irq context.
+	 */
+	spin_lock_irqsave(&rtc_lock, flags);
 
 	/* When the HPET interrupt handler calls us, the interrupt
 	 * status is passed as arg1 instead of the irq number.  But
@@ -732,7 +736,7 @@ static irqreturn_t cmos_interrupt(int irq, void *p)
 			hpet_mask_rtc_irq_bit(RTC_AIE);
 		CMOS_READ(RTC_INTR_FLAGS);
 	}
-	spin_unlock(&rtc_lock);
+	spin_unlock_irqrestore(&rtc_lock, flags);
 
 	if (is_intr(irqstat)) {
 		rtc_update_irq(p, 1, irqstat);
@@ -1300,9 +1304,7 @@ static void cmos_check_wkalrm(struct device *dev)
 	 * ACK the rtc irq here
 	 */
 	if (t_now >= cmos->alarm_expires && cmos_use_acpi_alarm()) {
-		local_irq_disable();
 		cmos_interrupt(0, (void *)cmos->rtc);
-		local_irq_enable();
 		return;
 	}
 
diff --git a/drivers/rtc/rtc-ds1307.c b/drivers/rtc/rtc-ds1307.c
index 872e0b679be4..1960d1bd851c 100644
--- a/drivers/rtc/rtc-ds1307.c
+++ b/drivers/rtc/rtc-ds1307.c
@@ -279,6 +279,13 @@ static int ds1307_get_time(struct device *dev, struct rtc_time *t)
 		if (tmp & DS1340_BIT_OSF)
 			return -EINVAL;
 		break;
+	case ds_1341:
+		ret = regmap_read(ds1307->regmap, DS1337_REG_STATUS, &tmp);
+		if (ret)
+			return ret;
+		if (tmp & DS1337_BIT_OSF)
+			return -EINVAL;
+		break;
 	case ds_1388:
 		ret = regmap_read(ds1307->regmap, DS1388_REG_FLAG, &tmp);
 		if (ret)
@@ -377,6 +384,10 @@ static int ds1307_set_time(struct device *dev, struct rtc_time *t)
 		regmap_update_bits(ds1307->regmap, DS1340_REG_FLAG,
 				   DS1340_BIT_OSF, 0);
 		break;
+	case ds_1341:
+		regmap_update_bits(ds1307->regmap, DS1337_REG_STATUS,
+				   DS1337_BIT_OSF, 0);
+		break;
 	case ds_1388:
 		regmap_update_bits(ds1307->regmap, DS1388_REG_FLAG,
 				   DS1388_BIT_OSF, 0);
@@ -1466,7 +1477,7 @@ static long ds3231_clk_sqw_round_rate(struct clk_hw *hw, unsigned long rate,
 			return ds3231_clk_sqw_rates[i];
 	}
 
-	return 0;
+	return ds3231_clk_sqw_rates[ARRAY_SIZE(ds3231_clk_sqw_rates) - 1];
 }
 
 static int ds3231_clk_sqw_set_rate(struct clk_hw *hw, unsigned long rate,
@@ -1807,18 +1818,14 @@ static int ds1307_probe(struct i2c_client *client)
 		 * For some variants, be sure alarms can trigger when we're
 		 * running on Vbackup (BBSQI/BBSQW)
 		 */
-		if (want_irq || ds1307_can_wakeup_device) {
+		if (want_irq || ds1307_can_wakeup_device)
 			regs[0] |= DS1337_BIT_INTCN | chip->bbsqi_bit;
-			regs[0] &= ~(DS1337_BIT_A2IE | DS1337_BIT_A1IE);
-		}
 
 		regmap_write(ds1307->regmap, DS1337_REG_CONTROL,
 			     regs[0]);
 
-		/* oscillator fault?  clear flag, and warn */
+		/* oscillator fault? warn */
 		if (regs[1] & DS1337_BIT_OSF) {
-			regmap_write(ds1307->regmap, DS1337_REG_STATUS,
-				     regs[1] & ~DS1337_BIT_OSF);
 			dev_warn(ds1307->dev, "SET TIME!\n");
 		}
 		break;
diff --git a/drivers/rtc/rtc-hym8563.c b/drivers/rtc/rtc-hym8563.c
index 63f11ea3589d..759dc2ad6e3b 100644
--- a/drivers/rtc/rtc-hym8563.c
+++ b/drivers/rtc/rtc-hym8563.c
@@ -294,7 +294,7 @@ static long hym8563_clkout_round_rate(struct clk_hw *hw, unsigned long rate,
 		if (clkout_rates[i] <= rate)
 			return clkout_rates[i];
 
-	return 0;
+	return clkout_rates[0];
 }
 
 static int hym8563_clkout_set_rate(struct clk_hw *hw, unsigned long rate,
diff --git a/drivers/rtc/rtc-loongson.c b/drivers/rtc/rtc-loongson.c
index e8ffc1ab90b0..c9d5b91a6544 100644
--- a/drivers/rtc/rtc-loongson.c
+++ b/drivers/rtc/rtc-loongson.c
@@ -114,6 +114,13 @@ static irqreturn_t loongson_rtc_isr(int irq, void *id)
 	struct loongson_rtc_priv *priv = (struct loongson_rtc_priv *)id;
 
 	rtc_update_irq(priv->rtcdev, 1, RTC_AF | RTC_IRQF);
+
+	/*
+	 * The TOY_MATCH0_REG should be cleared 0 here,
+	 * otherwise the interrupt cannot be cleared.
+	 */
+	regmap_write(priv->regmap, TOY_MATCH0_REG, 0);
+
 	return IRQ_HANDLED;
 }
 
@@ -122,6 +129,14 @@ static u32 loongson_rtc_handler(void *id)
 {
 	struct loongson_rtc_priv *priv = (struct loongson_rtc_priv *)id;
 
+	rtc_update_irq(priv->rtcdev, 1, RTC_AF | RTC_IRQF);
+
+	/*
+	 * The TOY_MATCH0_REG should be cleared 0 here,
+	 * otherwise the interrupt cannot be cleared.
+	 */
+	regmap_write(priv->regmap, TOY_MATCH0_REG, 0);
+
 	spin_lock(&priv->lock);
 	/* Disable RTC alarm wakeup and interrupt */
 	writel(readl(priv->pm_base + PM1_EN_REG) & ~RTC_EN,
@@ -131,11 +146,7 @@ static u32 loongson_rtc_handler(void *id)
 	writel(RTC_STS, priv->pm_base + PM1_STS_REG);
 	spin_unlock(&priv->lock);
 
-	/*
-	 * The TOY_MATCH0_REG should be cleared 0 here,
-	 * otherwise the interrupt cannot be cleared.
-	 */
-	return regmap_write(priv->regmap, TOY_MATCH0_REG, 0);
+	return ACPI_INTERRUPT_HANDLED;
 }
 
 static int loongson_rtc_set_enabled(struct device *dev)
diff --git a/drivers/rtc/rtc-nct3018y.c b/drivers/rtc/rtc-nct3018y.c
index 76c5f464b2da..cea05fca0bcc 100644
--- a/drivers/rtc/rtc-nct3018y.c
+++ b/drivers/rtc/rtc-nct3018y.c
@@ -376,7 +376,7 @@ static long nct3018y_clkout_round_rate(struct clk_hw *hw, unsigned long rate,
 		if (clkout_rates[i] <= rate)
 			return clkout_rates[i];
 
-	return 0;
+	return clkout_rates[0];
 }
 
 static int nct3018y_clkout_set_rate(struct clk_hw *hw, unsigned long rate,
diff --git a/drivers/rtc/rtc-pcf2127.c b/drivers/rtc/rtc-pcf2127.c
index 9c04c4e1a49c..fc079b9dcf71 100644
--- a/drivers/rtc/rtc-pcf2127.c
+++ b/drivers/rtc/rtc-pcf2127.c
@@ -1383,6 +1383,11 @@ static int pcf2127_i2c_probe(struct i2c_client *client)
 		variant = &pcf21xx_cfg[type];
 	}
 
+	if (variant->type == PCF2131) {
+		config.read_flag_mask = 0x0;
+		config.write_flag_mask = 0x0;
+	}
+
 	config.max_register = variant->max_register,
 
 	regmap = devm_regmap_init(&client->dev, &pcf2127_i2c_regmap,
@@ -1456,7 +1461,7 @@ static int pcf2127_spi_probe(struct spi_device *spi)
 		variant = &pcf21xx_cfg[type];
 	}
 
-	config.max_register = variant->max_register,
+	config.max_register = variant->max_register;
 
 	regmap = devm_regmap_init_spi(spi, &config);
 	if (IS_ERR(regmap)) {
diff --git a/drivers/rtc/rtc-pcf85063.c b/drivers/rtc/rtc-pcf85063.c
index fdbc07f14036..2b4921c23467 100644
--- a/drivers/rtc/rtc-pcf85063.c
+++ b/drivers/rtc/rtc-pcf85063.c
@@ -35,6 +35,7 @@
 #define PCF85063_REG_CTRL1_CAP_SEL	BIT(0)
 #define PCF85063_REG_CTRL1_STOP		BIT(5)
 #define PCF85063_REG_CTRL1_EXT_TEST	BIT(7)
+#define PCF85063_REG_CTRL1_SWR		0x58
 
 #define PCF85063_REG_CTRL2		0x01
 #define PCF85063_CTRL2_AF		BIT(6)
@@ -322,7 +323,16 @@ static const struct rtc_class_ops pcf85063_rtc_ops = {
 static int pcf85063_nvmem_read(void *priv, unsigned int offset,
 			       void *val, size_t bytes)
 {
-	return regmap_read(priv, PCF85063_REG_RAM, val);
+	unsigned int tmp;
+	int ret;
+
+	ret = regmap_read(priv, PCF85063_REG_RAM, &tmp);
+	if (ret < 0)
+		return ret;
+
+	*(u8 *)val = tmp;
+
+	return 0;
 }
 
 static int pcf85063_nvmem_write(void *priv, unsigned int offset,
@@ -400,7 +410,7 @@ static long pcf85063_clkout_round_rate(struct clk_hw *hw, unsigned long rate,
 		if (clkout_rates[i] <= rate)
 			return clkout_rates[i];
 
-	return 0;
+	return clkout_rates[0];
 }
 
 static int pcf85063_clkout_set_rate(struct clk_hw *hw, unsigned long rate,
@@ -580,7 +590,7 @@ static int pcf85063_probe(struct i2c_client *client)
 
 	i2c_set_clientdata(client, pcf85063);
 
-	err = regmap_read(pcf85063->regmap, PCF85063_REG_CTRL1, &tmp);
+	err = regmap_read(pcf85063->regmap, PCF85063_REG_SC, &tmp);
 	if (err) {
 		dev_err(&client->dev, "RTC chip is not present\n");
 		return err;
@@ -590,6 +600,22 @@ static int pcf85063_probe(struct i2c_client *client)
 	if (IS_ERR(pcf85063->rtc))
 		return PTR_ERR(pcf85063->rtc);
 
+	/*
+	 * If a Power loss is detected, SW reset the device.
+	 * From PCF85063A datasheet:
+	 * There is a low probability that some devices will have corruption
+	 * of the registers after the automatic power-on reset...
+	 */
+	if (tmp & PCF85063_REG_SC_OS) {
+		dev_warn(&client->dev,
+			 "POR issue detected, sending a SW reset\n");
+		err = regmap_write(pcf85063->regmap, PCF85063_REG_CTRL1,
+				   PCF85063_REG_CTRL1_SWR);
+		if (err < 0)
+			dev_warn(&client->dev,
+				 "SW reset failed, trying to continue\n");
+	}
+
 	err = pcf85063_load_capacitance(pcf85063, client->dev.of_node,
 					config->force_cap_7000 ? 7000 : 0);
 	if (err < 0)
diff --git a/drivers/rtc/rtc-pcf8563.c b/drivers/rtc/rtc-pcf8563.c
index 647d52f1f5c5..23b21b908915 100644
--- a/drivers/rtc/rtc-pcf8563.c
+++ b/drivers/rtc/rtc-pcf8563.c
@@ -386,7 +386,7 @@ static long pcf8563_clkout_round_rate(struct clk_hw *hw, unsigned long rate,
 		if (clkout_rates[i] <= rate)
 			return clkout_rates[i];
 
-	return 0;
+	return clkout_rates[0];
 }
 
 static int pcf8563_clkout_set_rate(struct clk_hw *hw, unsigned long rate,
diff --git a/drivers/rtc/rtc-rv3028.c b/drivers/rtc/rtc-rv3028.c
index 2f001c59c61d..86b7f821e937 100644
--- a/drivers/rtc/rtc-rv3028.c
+++ b/drivers/rtc/rtc-rv3028.c
@@ -738,7 +738,7 @@ static long rv3028_clkout_round_rate(struct clk_hw *hw, unsigned long rate,
 		if (clkout_rates[i] <= rate)
 			return clkout_rates[i];
 
-	return 0;
+	return clkout_rates[0];
 }
 
 static int rv3028_clkout_set_rate(struct clk_hw *hw, unsigned long rate,
diff --git a/drivers/rtc/rtc-rv3032.c b/drivers/rtc/rtc-rv3032.c
index 35b2e36b426a..cb01038a2e27 100644
--- a/drivers/rtc/rtc-rv3032.c
+++ b/drivers/rtc/rtc-rv3032.c
@@ -69,7 +69,7 @@
 #define RV3032_CLKOUT2_FD_MSK		GENMASK(6, 5)
 #define RV3032_CLKOUT2_OS		BIT(7)
 
-#define RV3032_CTRL1_EERD		BIT(3)
+#define RV3032_CTRL1_EERD		BIT(2)
 #define RV3032_CTRL1_WADA		BIT(5)
 
 #define RV3032_CTRL2_STOP		BIT(0)
diff --git a/drivers/rtc/rtc-sh.c b/drivers/rtc/rtc-sh.c
index 27a191fa3704..e66c9c6fd372 100644
--- a/drivers/rtc/rtc-sh.c
+++ b/drivers/rtc/rtc-sh.c
@@ -485,9 +485,15 @@ static int __init sh_rtc_probe(struct platform_device *pdev)
 		return -ENOENT;
 	}
 
-	rtc->periodic_irq = ret;
-	rtc->carry_irq = platform_get_irq(pdev, 1);
-	rtc->alarm_irq = platform_get_irq(pdev, 2);
+	if (!pdev->dev.of_node) {
+		rtc->periodic_irq = ret;
+		rtc->carry_irq = platform_get_irq(pdev, 1);
+		rtc->alarm_irq = platform_get_irq(pdev, 2);
+	} else {
+		rtc->alarm_irq = ret;
+		rtc->periodic_irq = platform_get_irq(pdev, 1);
+		rtc->carry_irq = platform_get_irq(pdev, 2);
+	}
 
 	res = platform_get_resource(pdev, IORESOURCE_IO, 0);
 	if (!res)
diff --git a/drivers/rtc/rtc-tps6594.c b/drivers/rtc/rtc-tps6594.c
index e69667634137..7c6246e3f029 100644
--- a/drivers/rtc/rtc-tps6594.c
+++ b/drivers/rtc/rtc-tps6594.c
@@ -37,7 +37,7 @@
 #define MAX_OFFSET (277774)
 
 // Number of ticks per hour
-#define TICKS_PER_HOUR (32768 * 3600)
+#define TICKS_PER_HOUR (32768 * 3600LL)
 
 // Multiplier for ppb conversions
 #define PPB_MULT NANO
diff --git a/drivers/rtc/rtc-zynqmp.c b/drivers/rtc/rtc-zynqmp.c
index 08ed171bdab4..b6f96c10196a 100644
--- a/drivers/rtc/rtc-zynqmp.c
+++ b/drivers/rtc/rtc-zynqmp.c
@@ -318,8 +318,8 @@ static int xlnx_rtc_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	/* Getting the rtc_clk info */
-	xrtcdev->rtc_clk = devm_clk_get_optional(&pdev->dev, "rtc_clk");
+	/* Getting the rtc info */
+	xrtcdev->rtc_clk = devm_clk_get_optional(&pdev->dev, "rtc");
 	if (IS_ERR(xrtcdev->rtc_clk)) {
 		if (PTR_ERR(xrtcdev->rtc_clk) != -EPROBE_DEFER)
 			dev_warn(&pdev->dev, "Device clock not found.\n");
diff --git a/drivers/s390/char/sclp.c b/drivers/s390/char/sclp.c
index fbffd451031f..45bd001206a2 100644
--- a/drivers/s390/char/sclp.c
+++ b/drivers/s390/char/sclp.c
@@ -245,7 +245,6 @@ static void sclp_request_timeout(bool force_restart);
 static void sclp_process_queue(void);
 static void __sclp_make_read_req(void);
 static int sclp_init_mask(int calculate);
-static int sclp_init(void);
 
 static void
 __sclp_queue_read_req(void)
@@ -1251,8 +1250,7 @@ static struct platform_driver sclp_pdrv = {
 
 /* Initialize SCLP driver. Return zero if driver is operational, non-zero
  * otherwise. */
-static int
-sclp_init(void)
+int sclp_init(void)
 {
 	unsigned long flags;
 	int rc = 0;
@@ -1305,13 +1303,7 @@ fail_unlock:
 
 static __init int sclp_initcall(void)
 {
-	int rc;
-
-	rc = platform_driver_register(&sclp_pdrv);
-	if (rc)
-		return rc;
-
-	return sclp_init();
+	return platform_driver_register(&sclp_pdrv);
 }
 
 arch_initcall(sclp_initcall);
diff --git a/drivers/s390/char/sclp_con.c b/drivers/s390/char/sclp_con.c
index e5d947c763ea..6a030ba38bf3 100644
--- a/drivers/s390/char/sclp_con.c
+++ b/drivers/s390/char/sclp_con.c
@@ -264,6 +264,19 @@ static struct console sclp_console =
 };
 
 /*
+ *  Release allocated pages.
+ */
+static void __init __sclp_console_free_pages(void)
+{
+	struct list_head *page, *p;
+
+	list_for_each_safe(page, p, &sclp_con_pages) {
+		list_del(page);
+		free_page((unsigned long)page);
+	}
+}
+
+/*
  * called by console_init() in drivers/char/tty_io.c at boot-time.
  */
 static int __init
@@ -282,6 +295,10 @@ sclp_console_init(void)
 	/* Allocate pages for output buffering */
 	for (i = 0; i < sclp_console_pages; i++) {
 		page = (void *) get_zeroed_page(GFP_KERNEL | GFP_DMA);
+		if (!page) {
+			__sclp_console_free_pages();
+			return -ENOMEM;
+		}
 		list_add_tail(page, &sclp_con_pages);
 	}
 	sclp_conbuf = NULL;
diff --git a/drivers/s390/char/sclp_tty.c b/drivers/s390/char/sclp_tty.c
index 892c18d2f87e..d3edacb6ee14 100644
--- a/drivers/s390/char/sclp_tty.c
+++ b/drivers/s390/char/sclp_tty.c
@@ -490,6 +490,17 @@ static const struct tty_operations sclp_ops = {
 	.flush_buffer = sclp_tty_flush_buffer,
 };
 
+/* Release allocated pages. */
+static void __init __sclp_tty_free_pages(void)
+{
+	struct list_head *page, *p;
+
+	list_for_each_safe(page, p, &sclp_tty_pages) {
+		list_del(page);
+		free_page((unsigned long)page);
+	}
+}
+
 static int __init
 sclp_tty_init(void)
 {
@@ -516,6 +527,7 @@ sclp_tty_init(void)
 	for (i = 0; i < MAX_KMEM_PAGES; i++) {
 		page = (void *) get_zeroed_page(GFP_KERNEL | GFP_DMA);
 		if (page == NULL) {
+			__sclp_tty_free_pages();
 			tty_driver_kref_put(driver);
 			return -ENOMEM;
 		}
diff --git a/drivers/s390/cio/chp.c b/drivers/s390/cio/chp.c
index a07bbecba61c..0c5bda060249 100644
--- a/drivers/s390/cio/chp.c
+++ b/drivers/s390/cio/chp.c
@@ -682,7 +682,8 @@ static int info_update(void)
 	if (time_after(jiffies, chp_info_expires)) {
 		/* Data is too old, update. */
 		rc = sclp_chp_read_info(&chp_info);
-		chp_info_expires = jiffies + CHP_INFO_UPDATE_INTERVAL ;
+		if (!rc)
+			chp_info_expires = jiffies + CHP_INFO_UPDATE_INTERVAL;
 	}
 	mutex_unlock(&info_lock);
 
diff --git a/drivers/s390/crypto/ap_bus.h b/drivers/s390/crypto/ap_bus.h
index f4622ee4d894..6111913c858c 100644
--- a/drivers/s390/crypto/ap_bus.h
+++ b/drivers/s390/crypto/ap_bus.h
@@ -180,7 +180,7 @@ struct ap_card {
 	atomic64_t total_request_count;	/* # requests ever for this AP device.*/
 };
 
-#define TAPQ_CARD_HWINFO_MASK 0xFEFF0000FFFF0F0FUL
+#define TAPQ_CARD_HWINFO_MASK 0xFFFF0000FFFF0F0FUL
 #define ASSOC_IDX_INVALID 0x10000
 
 #define to_ap_card(x) container_of((x), struct ap_card, ap_dev.device)
diff --git a/drivers/s390/crypto/pkey_api.c b/drivers/s390/crypto/pkey_api.c
index 3a39e167bdbf..d62fea0fbdfc 100644
--- a/drivers/s390/crypto/pkey_api.c
+++ b/drivers/s390/crypto/pkey_api.c
@@ -85,7 +85,7 @@ static void *_copy_apqns_from_user(void __user *uapqns, size_t nr_apqns)
 	if (!uapqns || nr_apqns == 0)
 		return NULL;
 
-	return memdup_user(uapqns, nr_apqns * sizeof(struct pkey_apqn));
+	return memdup_array_user(uapqns, nr_apqns, sizeof(struct pkey_apqn));
 }
 
 static int pkey_ioctl_genseck(struct pkey_genseck __user *ugs)
diff --git a/drivers/s390/crypto/vfio_ap_ops.c b/drivers/s390/crypto/vfio_ap_ops.c
index 9f76f2d7b66e..3bac163057d8 100644
--- a/drivers/s390/crypto/vfio_ap_ops.c
+++ b/drivers/s390/crypto/vfio_ap_ops.c
@@ -851,48 +851,66 @@ static void vfio_ap_mdev_remove(struct mdev_device *mdev)
 	vfio_put_device(&matrix_mdev->vdev);
 }
 
-#define MDEV_SHARING_ERR "Userspace may not re-assign queue %02lx.%04lx " \
-			 "already assigned to %s"
+#define MDEV_SHARING_ERR "Userspace may not assign queue %02lx.%04lx to mdev: already assigned to %s"
 
-static void vfio_ap_mdev_log_sharing_err(struct ap_matrix_mdev *matrix_mdev,
-					 unsigned long *apm,
-					 unsigned long *aqm)
+#define MDEV_IN_USE_ERR "Can not reserve queue %02lx.%04lx for host driver: in use by mdev"
+
+static void vfio_ap_mdev_log_sharing_err(struct ap_matrix_mdev *assignee,
+					 struct ap_matrix_mdev *assigned_to,
+					 unsigned long *apm, unsigned long *aqm)
 {
 	unsigned long apid, apqi;
-	const struct device *dev = mdev_dev(matrix_mdev->mdev);
-	const char *mdev_name = dev_name(dev);
 
-	for_each_set_bit_inv(apid, apm, AP_DEVICES)
+	for_each_set_bit_inv(apid, apm, AP_DEVICES) {
+		for_each_set_bit_inv(apqi, aqm, AP_DOMAINS) {
+			dev_warn(mdev_dev(assignee->mdev), MDEV_SHARING_ERR,
+				 apid, apqi, dev_name(mdev_dev(assigned_to->mdev)));
+		}
+	}
+}
+
+static void vfio_ap_mdev_log_in_use_err(struct ap_matrix_mdev *assignee,
+					unsigned long *apm, unsigned long *aqm)
+{
+	unsigned long apid, apqi;
+
+	for_each_set_bit_inv(apid, apm, AP_DEVICES) {
 		for_each_set_bit_inv(apqi, aqm, AP_DOMAINS)
-			dev_warn(dev, MDEV_SHARING_ERR, apid, apqi, mdev_name);
+			dev_warn(mdev_dev(assignee->mdev), MDEV_IN_USE_ERR, apid, apqi);
+	}
 }
 
 /**
  * vfio_ap_mdev_verify_no_sharing - verify APQNs are not shared by matrix mdevs
  *
+ * @assignee: the matrix mdev to which @mdev_apm and @mdev_aqm are being
+ *	      assigned; or, NULL if this function was called by the AP bus
+ *	      driver in_use callback to verify none of the APQNs being reserved
+ *	      for the host device driver are in use by a vfio_ap mediated device
  * @mdev_apm: mask indicating the APIDs of the APQNs to be verified
  * @mdev_aqm: mask indicating the APQIs of the APQNs to be verified
  *
- * Verifies that each APQN derived from the Cartesian product of a bitmap of
- * AP adapter IDs and AP queue indexes is not configured for any matrix
- * mediated device. AP queue sharing is not allowed.
+ * Verifies that each APQN derived from the Cartesian product of APIDs
+ * represented by the bits set in @mdev_apm and the APQIs of the bits set in
+ * @mdev_aqm is not assigned to a mediated device other than the mdev to which
+ * the APQN is being assigned (@assignee). AP queue sharing is not allowed.
  *
  * Return: 0 if the APQNs are not shared; otherwise return -EADDRINUSE.
  */
-static int vfio_ap_mdev_verify_no_sharing(unsigned long *mdev_apm,
+static int vfio_ap_mdev_verify_no_sharing(struct ap_matrix_mdev *assignee,
+					  unsigned long *mdev_apm,
 					  unsigned long *mdev_aqm)
 {
-	struct ap_matrix_mdev *matrix_mdev;
+	struct ap_matrix_mdev *assigned_to;
 	DECLARE_BITMAP(apm, AP_DEVICES);
 	DECLARE_BITMAP(aqm, AP_DOMAINS);
 
-	list_for_each_entry(matrix_mdev, &matrix_dev->mdev_list, node) {
+	list_for_each_entry(assigned_to, &matrix_dev->mdev_list, node) {
 		/*
-		 * If the input apm and aqm are fields of the matrix_mdev
-		 * object, then move on to the next matrix_mdev.
+		 * If the mdev to which the mdev_apm and mdev_aqm is being
+		 * assigned is the same as the mdev being verified
 		 */
-		if (mdev_apm == matrix_mdev->matrix.apm &&
-		    mdev_aqm == matrix_mdev->matrix.aqm)
+		if (assignee == assigned_to)
 			continue;
 
 		memset(apm, 0, sizeof(apm));
@@ -902,15 +920,16 @@ static int vfio_ap_mdev_verify_no_sharing(unsigned long *mdev_apm,
 		 * We work on full longs, as we can only exclude the leftover
 		 * bits in non-inverse order. The leftover is all zeros.
 		 */
-		if (!bitmap_and(apm, mdev_apm, matrix_mdev->matrix.apm,
-				AP_DEVICES))
+		if (!bitmap_and(apm, mdev_apm, assigned_to->matrix.apm,	AP_DEVICES))
 			continue;
 
-		if (!bitmap_and(aqm, mdev_aqm, matrix_mdev->matrix.aqm,
-				AP_DOMAINS))
+		if (!bitmap_and(aqm, mdev_aqm, assigned_to->matrix.aqm,	AP_DOMAINS))
 			continue;
 
-		vfio_ap_mdev_log_sharing_err(matrix_mdev, apm, aqm);
+		if (assignee)
+			vfio_ap_mdev_log_sharing_err(assignee, assigned_to, apm, aqm);
+		else
+			vfio_ap_mdev_log_in_use_err(assigned_to, apm, aqm);
 
 		return -EADDRINUSE;
 	}
@@ -939,7 +958,8 @@ static int vfio_ap_mdev_validate_masks(struct ap_matrix_mdev *matrix_mdev)
 					       matrix_mdev->matrix.aqm))
 		return -EADDRNOTAVAIL;
 
-	return vfio_ap_mdev_verify_no_sharing(matrix_mdev->matrix.apm,
+	return vfio_ap_mdev_verify_no_sharing(matrix_mdev,
+					      matrix_mdev->matrix.apm,
 					      matrix_mdev->matrix.aqm);
 }
 
@@ -2467,7 +2487,7 @@ int vfio_ap_mdev_resource_in_use(unsigned long *apm, unsigned long *aqm)
 
 	mutex_lock(&matrix_dev->guests_lock);
 	mutex_lock(&matrix_dev->mdevs_lock);
-	ret = vfio_ap_mdev_verify_no_sharing(apm, aqm);
+	ret = vfio_ap_mdev_verify_no_sharing(NULL, apm, aqm);
 	mutex_unlock(&matrix_dev->mdevs_lock);
 	mutex_unlock(&matrix_dev->guests_lock);
 
diff --git a/drivers/s390/net/ism_drv.c b/drivers/s390/net/ism_drv.c
index e36e3ea165d3..7cfc4f986297 100644
--- a/drivers/s390/net/ism_drv.c
+++ b/drivers/s390/net/ism_drv.c
@@ -131,6 +131,7 @@ static int ism_cmd(struct ism_dev *ism, void *cmd)
 	struct ism_req_hdr *req = cmd;
 	struct ism_resp_hdr *resp = cmd;
 
+	spin_lock(&ism->cmd_lock);
 	__ism_write_cmd(ism, req + 1, sizeof(*req), req->len - sizeof(*req));
 	__ism_write_cmd(ism, req, 0, sizeof(*req));
 
@@ -144,6 +145,7 @@ static int ism_cmd(struct ism_dev *ism, void *cmd)
 	}
 	__ism_read_cmd(ism, resp + 1, sizeof(*resp), resp->len - sizeof(*resp));
 out:
+	spin_unlock(&ism->cmd_lock);
 	return resp->ret;
 }
 
@@ -588,6 +590,15 @@ out:
 	return ret;
 }
 
+static void ism_dev_release(struct device *dev)
+{
+	struct ism_dev *ism;
+
+	ism = container_of(dev, struct ism_dev, dev);
+
+	kfree(ism);
+}
+
 static int ism_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
 	struct ism_dev *ism;
@@ -598,9 +609,11 @@ static int ism_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		return -ENOMEM;
 
 	spin_lock_init(&ism->lock);
+	spin_lock_init(&ism->cmd_lock);
 	dev_set_drvdata(&pdev->dev, ism);
 	ism->pdev = pdev;
 	ism->dev.parent = &pdev->dev;
+	ism->dev.release = ism_dev_release;
 	device_initialize(&ism->dev);
 	dev_set_name(&ism->dev, dev_name(&pdev->dev));
 	ret = device_add(&ism->dev);
@@ -637,7 +650,7 @@ err:
 	device_del(&ism->dev);
 err_dev:
 	dev_set_drvdata(&pdev->dev, NULL);
-	kfree(ism);
+	put_device(&ism->dev);
 
 	return ret;
 }
@@ -682,7 +695,7 @@ static void ism_remove(struct pci_dev *pdev)
 	pci_disable_device(pdev);
 	device_del(&ism->dev);
 	dev_set_drvdata(&pdev->dev, NULL);
-	kfree(ism);
+	put_device(&ism->dev);
 }
 
 static struct pci_driver ism_driver = {
diff --git a/drivers/s390/scsi/zfcp_sysfs.c b/drivers/s390/scsi/zfcp_sysfs.c
index cb67fa80fb12..a95da6768f66 100644
--- a/drivers/s390/scsi/zfcp_sysfs.c
+++ b/drivers/s390/scsi/zfcp_sysfs.c
@@ -450,6 +450,8 @@ static ssize_t zfcp_sysfs_unit_add_store(struct device *dev,
 	if (kstrtoull(buf, 0, (unsigned long long *) &fcp_lun))
 		return -EINVAL;
 
+	flush_work(&port->rport_work);
+
 	retval = zfcp_unit_add(port, fcp_lun);
 	if (retval)
 		return retval;
diff --git a/drivers/s390/virtio/virtio_ccw.c b/drivers/s390/virtio/virtio_ccw.c
index 21fa7ac849e5..4904b831c0a7 100644
--- a/drivers/s390/virtio/virtio_ccw.c
+++ b/drivers/s390/virtio/virtio_ccw.c
@@ -302,11 +302,17 @@ static struct airq_info *new_airq_info(int index)
 static unsigned long *get_airq_indicator(struct virtqueue *vqs[], int nvqs,
 					 u64 *first, void **airq_info)
 {
-	int i, j;
+	int i, j, queue_idx, highest_queue_idx = -1;
 	struct airq_info *info;
 	unsigned long *indicator_addr = NULL;
 	unsigned long bit, flags;
 
+	/* Array entries without an actual queue pointer must be ignored. */
+	for (i = 0; i < nvqs; i++) {
+		if (vqs[i])
+			highest_queue_idx++;
+	}
+
 	for (i = 0; i < MAX_AIRQ_AREAS && !indicator_addr; i++) {
 		mutex_lock(&airq_areas_lock);
 		if (!airq_areas[i])
@@ -316,7 +322,7 @@ static unsigned long *get_airq_indicator(struct virtqueue *vqs[], int nvqs,
 		if (!info)
 			return NULL;
 		write_lock_irqsave(&info->lock, flags);
-		bit = airq_iv_alloc(info->aiv, nvqs);
+		bit = airq_iv_alloc(info->aiv, highest_queue_idx + 1);
 		if (bit == -1UL) {
 			/* Not enough vacancies. */
 			write_unlock_irqrestore(&info->lock, flags);
@@ -325,8 +331,10 @@ static unsigned long *get_airq_indicator(struct virtqueue *vqs[], int nvqs,
 		*first = bit;
 		*airq_info = info;
 		indicator_addr = info->aiv->vector;
-		for (j = 0; j < nvqs; j++) {
-			airq_iv_set_ptr(info->aiv, bit + j,
+		for (j = 0, queue_idx = 0; j < nvqs; j++) {
+			if (!vqs[j])
+				continue;
+			airq_iv_set_ptr(info->aiv, bit + queue_idx++,
 					(unsigned long)vqs[j]);
 		}
 		write_unlock_irqrestore(&info->lock, flags);
diff --git a/drivers/scsi/aacraid/comminit.c b/drivers/scsi/aacraid/comminit.c
index 28cf18955a08..726c8531b7d3 100644
--- a/drivers/scsi/aacraid/comminit.c
+++ b/drivers/scsi/aacraid/comminit.c
@@ -481,8 +481,7 @@ void aac_define_int_mode(struct aac_dev *dev)
 	    pci_find_capability(dev->pdev, PCI_CAP_ID_MSIX)) {
 		min_msix = 2;
 		i = pci_alloc_irq_vectors(dev->pdev,
-					  min_msix, msi_count,
-					  PCI_IRQ_MSIX | PCI_IRQ_AFFINITY);
+					  min_msix, msi_count, PCI_IRQ_MSIX);
 		if (i > 0) {
 			dev->msi_enabled = 1;
 			msi_count = i;
diff --git a/drivers/scsi/bfa/bfad_im.c b/drivers/scsi/bfa/bfad_im.c
index 66fb701401de..0cc04c84b259 100644
--- a/drivers/scsi/bfa/bfad_im.c
+++ b/drivers/scsi/bfa/bfad_im.c
@@ -706,6 +706,7 @@ bfad_im_probe(struct bfad_s *bfad)
 
 	if (bfad_thread_workq(bfad) != BFA_STATUS_OK) {
 		kfree(im);
+		bfad->im = NULL;
 		return BFA_STATUS_FAILED;
 	}
 
diff --git a/drivers/scsi/elx/efct/efct_hw.c b/drivers/scsi/elx/efct/efct_hw.c
index 5a5525054d71..5b079b8b7a08 100644
--- a/drivers/scsi/elx/efct/efct_hw.c
+++ b/drivers/scsi/elx/efct/efct_hw.c
@@ -1120,7 +1120,7 @@ int
 efct_hw_parse_filter(struct efct_hw *hw, void *value)
 {
 	int rc = 0;
-	char *p = NULL;
+	char *p = NULL, *pp = NULL;
 	char *token;
 	u32 idx = 0;
 
@@ -1132,6 +1132,7 @@ efct_hw_parse_filter(struct efct_hw *hw, void *value)
 		efc_log_err(hw->os, "p is NULL\n");
 		return -ENOMEM;
 	}
+	pp = p;
 
 	idx = 0;
 	while ((token = strsep(&p, ",")) && *token) {
@@ -1144,7 +1145,7 @@ efct_hw_parse_filter(struct efct_hw *hw, void *value)
 		if (idx == ARRAY_SIZE(hw->config.filter_def))
 			break;
 	}
-	kfree(p);
+	kfree(pp);
 
 	return rc;
 }
diff --git a/drivers/scsi/elx/efct/efct_lio.c b/drivers/scsi/elx/efct/efct_lio.c
index 9ac69356b13e..bd3d489e56ae 100644
--- a/drivers/scsi/elx/efct/efct_lio.c
+++ b/drivers/scsi/elx/efct/efct_lio.c
@@ -382,7 +382,7 @@ efct_lio_sg_unmap(struct efct_io *io)
 		return;
 
 	dma_unmap_sg(&io->efct->pci->dev, cmd->t_data_sg,
-		     ocp->seg_map_cnt, cmd->data_direction);
+		     cmd->t_data_nents, cmd->data_direction);
 	ocp->seg_map_cnt = 0;
 }
 
diff --git a/drivers/scsi/fnic/fnic_main.c b/drivers/scsi/fnic/fnic_main.c
index adec0df24bc4..1cb517f731f4 100644
--- a/drivers/scsi/fnic/fnic_main.c
+++ b/drivers/scsi/fnic/fnic_main.c
@@ -16,7 +16,6 @@
 #include <linux/spinlock.h>
 #include <linux/workqueue.h>
 #include <linux/if_ether.h>
-#include <linux/blk-mq-pci.h>
 #include <scsi/fc/fc_fip.h>
 #include <scsi/scsi_host.h>
 #include <scsi/scsi_transport.h>
@@ -601,7 +600,7 @@ void fnic_mq_map_queues_cpus(struct Scsi_Host *host)
 		return;
 	}
 
-	blk_mq_pci_map_queues(qmap, l_pdev, FNIC_PCI_OFFSET);
+	blk_mq_map_hw_queues(qmap, &l_pdev->dev, FNIC_PCI_OFFSET);
 }
 
 static int fnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
diff --git a/drivers/scsi/hisi_sas/hisi_sas.h b/drivers/scsi/hisi_sas/hisi_sas.h
index d223f482488f..010479a354ee 100644
--- a/drivers/scsi/hisi_sas/hisi_sas.h
+++ b/drivers/scsi/hisi_sas/hisi_sas.h
@@ -9,7 +9,6 @@
 
 #include <linux/acpi.h>
 #include <linux/blk-mq.h>
-#include <linux/blk-mq-pci.h>
 #include <linux/clk.h>
 #include <linux/debugfs.h>
 #include <linux/dmapool.h>
diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index ffd15fa4f9e5..d9500b730690 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -912,8 +912,28 @@ static void hisi_sas_phyup_work_common(struct work_struct *work,
 		container_of(work, typeof(*phy), works[event]);
 	struct hisi_hba *hisi_hba = phy->hisi_hba;
 	struct asd_sas_phy *sas_phy = &phy->sas_phy;
+	struct asd_sas_port *sas_port = sas_phy->port;
+	struct hisi_sas_port *port = phy->port;
+	struct device *dev = hisi_hba->dev;
+	struct domain_device *port_dev;
 	int phy_no = sas_phy->id;
 
+	if (!test_bit(HISI_SAS_RESETTING_BIT, &hisi_hba->flags) &&
+	    sas_port && port && (port->id != phy->port_id)) {
+		dev_info(dev, "phy%d's hw port id changed from %d to %llu\n",
+				phy_no, port->id, phy->port_id);
+		port_dev = sas_port->port_dev;
+		if (port_dev && !dev_is_expander(port_dev->dev_type)) {
+			/*
+			 * Set the device state to gone to block
+			 * sending IO to the device.
+			 */
+			set_bit(SAS_DEV_GONE, &port_dev->state);
+			hisi_sas_notify_phy_event(phy, HISI_PHYE_LINK_RESET);
+			return;
+		}
+	}
+
 	phy->wait_phyup_cnt = 0;
 	if (phy->identify.target_port_protocols == SAS_PROTOCOL_SSP)
 		hisi_hba->hw->sl_notify_ssp(hisi_hba, phy_no);
@@ -1830,33 +1850,14 @@ static int hisi_sas_I_T_nexus_reset(struct domain_device *device)
 	}
 	hisi_sas_dereg_device(hisi_hba, device);
 
-	rc = hisi_sas_debug_I_T_nexus_reset(device);
-	if (rc == TMF_RESP_FUNC_COMPLETE && dev_is_sata(device)) {
-		struct sas_phy *local_phy;
-
+	if (dev_is_sata(device)) {
 		rc = hisi_sas_softreset_ata_disk(device);
-		switch (rc) {
-		case -ECOMM:
-			rc = -ENODEV;
-			break;
-		case TMF_RESP_FUNC_FAILED:
-		case -EMSGSIZE:
-		case -EIO:
-			local_phy = sas_get_local_phy(device);
-			rc = sas_phy_enable(local_phy, 0);
-			if (!rc) {
-				local_phy->enabled = 0;
-				dev_err(dev, "Disabled local phy of ATA disk %016llx due to softreset fail (%d)\n",
-					SAS_ADDR(device->sas_addr), rc);
-				rc = -ENODEV;
-			}
-			sas_put_local_phy(local_phy);
-			break;
-		default:
-			break;
-		}
+		if (rc == TMF_RESP_FUNC_FAILED)
+			dev_err(dev, "ata disk %016llx reset (%d)\n",
+				SAS_ADDR(device->sas_addr), rc);
 	}
 
+	rc = hisi_sas_debug_I_T_nexus_reset(device);
 	if ((rc == TMF_RESP_FUNC_COMPLETE) || (rc == -ENODEV))
 		hisi_sas_release_task(hisi_hba, device);
 
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
index 342d75f12051..89ff33daba40 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
@@ -2501,6 +2501,7 @@ static void prep_ata_v2_hw(struct hisi_hba *hisi_hba,
 	struct hisi_sas_port *port = to_hisi_sas_port(sas_port);
 	struct sas_ata_task *ata_task = &task->ata_task;
 	struct sas_tmf_task *tmf = slot->tmf;
+	int phy_id;
 	u8 *buf_cmd;
 	int has_data = 0, hdr_tag = 0;
 	u32 dw0, dw1 = 0, dw2 = 0;
@@ -2508,10 +2509,14 @@ static void prep_ata_v2_hw(struct hisi_hba *hisi_hba,
 	/* create header */
 	/* dw0 */
 	dw0 = port->id << CMD_HDR_PORT_OFF;
-	if (parent_dev && dev_is_expander(parent_dev->dev_type))
+	if (parent_dev && dev_is_expander(parent_dev->dev_type)) {
 		dw0 |= 3 << CMD_HDR_CMD_OFF;
-	else
+	} else {
+		phy_id = device->phy->identify.phy_identifier;
+		dw0 |= (1U << phy_id) << CMD_HDR_PHY_ID_OFF;
+		dw0 |= CMD_HDR_FORCE_PHY_MSK;
 		dw0 |= 4 << CMD_HDR_CMD_OFF;
+	}
 
 	if (tmf && ata_task->force_phy) {
 		dw0 |= CMD_HDR_FORCE_PHY_MSK;
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
index cd394d8c9f07..2b04556681a1 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
@@ -358,6 +358,10 @@
 #define CMD_HDR_RESP_REPORT_MSK		(0x1 << CMD_HDR_RESP_REPORT_OFF)
 #define CMD_HDR_TLR_CTRL_OFF		6
 #define CMD_HDR_TLR_CTRL_MSK		(0x3 << CMD_HDR_TLR_CTRL_OFF)
+#define CMD_HDR_PHY_ID_OFF		8
+#define CMD_HDR_PHY_ID_MSK		(0x1ff << CMD_HDR_PHY_ID_OFF)
+#define CMD_HDR_FORCE_PHY_OFF		17
+#define CMD_HDR_FORCE_PHY_MSK		(0x1U << CMD_HDR_FORCE_PHY_OFF)
 #define CMD_HDR_PORT_OFF		18
 #define CMD_HDR_PORT_MSK		(0xf << CMD_HDR_PORT_OFF)
 #define CMD_HDR_PRIORITY_OFF		27
@@ -1425,15 +1429,21 @@ static void prep_ata_v3_hw(struct hisi_hba *hisi_hba,
 	struct hisi_sas_cmd_hdr *hdr = slot->cmd_hdr;
 	struct asd_sas_port *sas_port = device->port;
 	struct hisi_sas_port *port = to_hisi_sas_port(sas_port);
+	int phy_id;
 	u8 *buf_cmd;
 	int has_data = 0, hdr_tag = 0;
 	u32 dw1 = 0, dw2 = 0;
 
 	hdr->dw0 = cpu_to_le32(port->id << CMD_HDR_PORT_OFF);
-	if (parent_dev && dev_is_expander(parent_dev->dev_type))
+	if (parent_dev && dev_is_expander(parent_dev->dev_type)) {
 		hdr->dw0 |= cpu_to_le32(3 << CMD_HDR_CMD_OFF);
-	else
+	} else {
+		phy_id = device->phy->identify.phy_identifier;
+		hdr->dw0 |= cpu_to_le32((1U << phy_id)
+				<< CMD_HDR_PHY_ID_OFF);
+		hdr->dw0 |= CMD_HDR_FORCE_PHY_MSK;
 		hdr->dw0 |= cpu_to_le32(4U << CMD_HDR_CMD_OFF);
+	}
 
 	switch (task->data_dir) {
 	case DMA_TO_DEVICE:
@@ -3323,8 +3333,8 @@ static void hisi_sas_map_queues(struct Scsi_Host *shost)
 		if (i == HCTX_TYPE_POLL)
 			blk_mq_map_queues(qmap);
 		else
-			blk_mq_pci_map_queues(qmap, hisi_hba->pci_dev,
-					      BASE_VECTORS_V3_HW);
+			blk_mq_map_hw_queues(qmap, hisi_hba->dev,
+					     BASE_VECTORS_V3_HW);
 		qoff += qmap->nr_queues;
 	}
 }
diff --git a/drivers/scsi/ibmvscsi_tgt/libsrp.c b/drivers/scsi/ibmvscsi_tgt/libsrp.c
index 8a0e28aec928..0ecad398ed3d 100644
--- a/drivers/scsi/ibmvscsi_tgt/libsrp.c
+++ b/drivers/scsi/ibmvscsi_tgt/libsrp.c
@@ -184,7 +184,8 @@ static int srp_direct_data(struct ibmvscsis_cmd *cmd, struct srp_direct_buf *md,
 	err = rdma_io(cmd, sg, nsg, md, 1, dir, len);
 
 	if (dma_map)
-		dma_unmap_sg(iue->target->dev, sg, nsg, DMA_BIDIRECTIONAL);
+		dma_unmap_sg(iue->target->dev, sg, cmd->se_cmd.t_data_nents,
+			     DMA_BIDIRECTIONAL);
 
 	return err;
 }
@@ -256,7 +257,8 @@ rdma:
 	err = rdma_io(cmd, sg, nsg, md, nmd, dir, len);
 
 	if (dma_map)
-		dma_unmap_sg(iue->target->dev, sg, nsg, DMA_BIDIRECTIONAL);
+		dma_unmap_sg(iue->target->dev, sg, cmd->se_cmd.t_data_nents,
+			     DMA_BIDIRECTIONAL);
 
 free_mem:
 	if (token && dma_map) {
diff --git a/drivers/scsi/isci/request.c b/drivers/scsi/isci/request.c
index 355a0bc0828e..bb89a2e33eb4 100644
--- a/drivers/scsi/isci/request.c
+++ b/drivers/scsi/isci/request.c
@@ -2904,7 +2904,7 @@ static void isci_request_io_request_complete(struct isci_host *ihost,
 					 task->total_xfer_len, task->data_dir);
 		else  /* unmap the sgl dma addresses */
 			dma_unmap_sg(&ihost->pdev->dev, task->scatter,
-				     request->num_sg_entries, task->data_dir);
+				     task->num_scatter, task->data_dir);
 		break;
 	case SAS_PROTOCOL_SMP: {
 		struct scatterlist *sg = &task->smp_task.smp_req;
diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c
index 2b1bf990a9dc..29af3722ea22 100644
--- a/drivers/scsi/libiscsi.c
+++ b/drivers/scsi/libiscsi.c
@@ -3184,7 +3184,8 @@ iscsi_conn_setup(struct iscsi_cls_session *cls_session, int dd_size,
 		return NULL;
 	conn = cls_conn->dd_data;
 
-	conn->dd_data = cls_conn->dd_data + sizeof(*conn);
+	if (dd_size)
+		conn->dd_data = cls_conn->dd_data + sizeof(*conn);
 	conn->session = session;
 	conn->cls_conn = cls_conn;
 	conn->c_stage = ISCSI_CONN_INITIAL_STAGE;
diff --git a/drivers/scsi/lpfc/lpfc_bsg.c b/drivers/scsi/lpfc/lpfc_bsg.c
index 85059b83ea6b..1c6b024160da 100644
--- a/drivers/scsi/lpfc/lpfc_bsg.c
+++ b/drivers/scsi/lpfc/lpfc_bsg.c
@@ -398,7 +398,11 @@ lpfc_bsg_send_mgmt_cmd(struct bsg_job *job)
 	/* in case no data is transferred */
 	bsg_reply->reply_payload_rcv_len = 0;
 
-	if (ndlp->nlp_flag & NLP_ELS_SND_MASK)
+	if (test_bit(NLP_PLOGI_SND, &ndlp->nlp_flag) ||
+	    test_bit(NLP_PRLI_SND, &ndlp->nlp_flag) ||
+	    test_bit(NLP_ADISC_SND, &ndlp->nlp_flag) ||
+	    test_bit(NLP_LOGO_SND, &ndlp->nlp_flag) ||
+	    test_bit(NLP_RNID_SND, &ndlp->nlp_flag))
 		return -ENODEV;
 
 	/* allocate our bsg tracking structure */
diff --git a/drivers/scsi/lpfc/lpfc_crtn.h b/drivers/scsi/lpfc/lpfc_crtn.h
index d4e46a08f94d..36470bd71617 100644
--- a/drivers/scsi/lpfc/lpfc_crtn.h
+++ b/drivers/scsi/lpfc/lpfc_crtn.h
@@ -571,7 +571,7 @@ int lpfc_issue_reg_vfi(struct lpfc_vport *);
 int lpfc_issue_unreg_vfi(struct lpfc_vport *);
 int lpfc_selective_reset(struct lpfc_hba *);
 int lpfc_sli4_read_config(struct lpfc_hba *);
-void lpfc_sli4_node_prep(struct lpfc_hba *);
+void lpfc_sli4_node_rpi_restore(struct lpfc_hba *phba);
 int lpfc_sli4_els_sgl_update(struct lpfc_hba *phba);
 int lpfc_sli4_nvmet_sgl_update(struct lpfc_hba *phba);
 int lpfc_io_buf_flush(struct lpfc_hba *phba, struct list_head *sglist);
diff --git a/drivers/scsi/lpfc/lpfc_ct.c b/drivers/scsi/lpfc/lpfc_ct.c
index ce3a1f42713d..30891ad17e2a 100644
--- a/drivers/scsi/lpfc/lpfc_ct.c
+++ b/drivers/scsi/lpfc/lpfc_ct.c
@@ -735,7 +735,7 @@ lpfc_prep_node_fc4type(struct lpfc_vport *vport, uint32_t Did, uint8_t fc4_type)
 
 			lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY,
 					 "0238 Process x%06x NameServer Rsp "
-					 "Data: x%x x%x x%x x%lx x%x\n", Did,
+					 "Data: x%lx x%x x%x x%lx x%x\n", Did,
 					 ndlp->nlp_flag, ndlp->nlp_fc4_type,
 					 ndlp->nlp_state, vport->fc_flag,
 					 vport->fc_rscn_id_cnt);
@@ -744,7 +744,7 @@ lpfc_prep_node_fc4type(struct lpfc_vport *vport, uint32_t Did, uint8_t fc4_type)
 			 * state of ndlp hit devloss, change state to
 			 * allow rediscovery.
 			 */
-			if (ndlp->nlp_flag & NLP_NPR_2B_DISC &&
+			if (test_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag) &&
 			    ndlp->nlp_state == NLP_STE_UNUSED_NODE) {
 				lpfc_nlp_set_state(vport, ndlp,
 						   NLP_STE_NPR_NODE);
@@ -832,12 +832,10 @@ lpfc_ns_rsp_audit_did(struct lpfc_vport *vport, uint32_t Did, uint8_t fc4_type)
 			if (ndlp->nlp_type != NLP_NVME_INITIATOR ||
 			    ndlp->nlp_state != NLP_STE_UNMAPPED_NODE)
 				continue;
-			spin_lock_irq(&ndlp->lock);
 			if (ndlp->nlp_DID == Did)
-				ndlp->nlp_flag &= ~NLP_NVMET_RECOV;
+				clear_bit(NLP_NVMET_RECOV, &ndlp->nlp_flag);
 			else
-				ndlp->nlp_flag |= NLP_NVMET_RECOV;
-			spin_unlock_irq(&ndlp->lock);
+				set_bit(NLP_NVMET_RECOV, &ndlp->nlp_flag);
 		}
 	}
 }
@@ -894,13 +892,11 @@ lpfc_ns_rsp(struct lpfc_vport *vport, struct lpfc_dmabuf *mp, uint8_t fc4_type,
 	 */
 	if (vport->phba->nvmet_support) {
 		list_for_each_entry(ndlp, &vport->fc_nodes, nlp_listp) {
-			if (!(ndlp->nlp_flag & NLP_NVMET_RECOV))
+			if (!test_bit(NLP_NVMET_RECOV, &ndlp->nlp_flag))
 				continue;
 			lpfc_disc_state_machine(vport, ndlp, NULL,
 						NLP_EVT_DEVICE_RECOVERY);
-			spin_lock_irq(&ndlp->lock);
-			ndlp->nlp_flag &= ~NLP_NVMET_RECOV;
-			spin_unlock_irq(&ndlp->lock);
+			clear_bit(NLP_NVMET_RECOV, &ndlp->nlp_flag);
 		}
 	}
 
@@ -1440,7 +1436,7 @@ lpfc_cmpl_ct_cmd_gff_id(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 	if (ndlp) {
 		lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY,
 				 "0242 Process x%x GFF "
-				 "NameServer Rsp Data: x%x x%lx x%x\n",
+				 "NameServer Rsp Data: x%lx x%lx x%x\n",
 				 did, ndlp->nlp_flag, vport->fc_flag,
 				 vport->fc_rscn_id_cnt);
 	} else {
diff --git a/drivers/scsi/lpfc/lpfc_debugfs.c b/drivers/scsi/lpfc/lpfc_debugfs.c
index a2d2b02b3418..1b601e45bc45 100644
--- a/drivers/scsi/lpfc/lpfc_debugfs.c
+++ b/drivers/scsi/lpfc/lpfc_debugfs.c
@@ -870,8 +870,8 @@ lpfc_debugfs_nodelist_data(struct lpfc_vport *vport, char *buf, int size)
 				wwn_to_u64(ndlp->nlp_nodename.u.wwn));
 		len += scnprintf(buf+len, size-len, "RPI:x%04x ",
 				 ndlp->nlp_rpi);
-		len +=  scnprintf(buf+len, size-len, "flag:x%08x ",
-			ndlp->nlp_flag);
+		len += scnprintf(buf+len, size-len, "flag:x%08lx ",
+				 ndlp->nlp_flag);
 		if (!ndlp->nlp_type)
 			len += scnprintf(buf+len, size-len, "UNKNOWN_TYPE ");
 		if (ndlp->nlp_type & NLP_FC_NODE)
@@ -6289,7 +6289,6 @@ lpfc_debugfs_initialize(struct lpfc_vport *vport)
 			}
 			phba->nvmeio_trc_on = 1;
 			phba->nvmeio_trc_output_idx = 0;
-			phba->nvmeio_trc = NULL;
 		} else {
 nvmeio_off:
 			phba->nvmeio_trc_size = 0;
diff --git a/drivers/scsi/lpfc/lpfc_disc.h b/drivers/scsi/lpfc/lpfc_disc.h
index f5ae8cc15820..af5d5bd75642 100644
--- a/drivers/scsi/lpfc/lpfc_disc.h
+++ b/drivers/scsi/lpfc/lpfc_disc.h
@@ -102,7 +102,7 @@ struct lpfc_nodelist {
 
 	spinlock_t	lock;			/* Node management lock */
 
-	uint32_t         nlp_flag;		/* entry flags */
+	unsigned long    nlp_flag;		/* entry flags */
 	uint32_t         nlp_DID;		/* FC D_ID of entry */
 	uint32_t         nlp_last_elscmd;	/* Last ELS cmd sent */
 	uint16_t         nlp_type;
@@ -182,37 +182,37 @@ struct lpfc_node_rrq {
 #define lpfc_ndlp_check_qdepth(phba, ndlp) \
 	(ndlp->cmd_qdepth < phba->sli4_hba.max_cfg_param.max_xri)
 
-/* Defines for nlp_flag (uint32) */
-#define NLP_IGNR_REG_CMPL  0x00000001 /* Rcvd rscn before we cmpl reg login */
-#define NLP_REG_LOGIN_SEND 0x00000002   /* sent reglogin to adapter */
-#define NLP_RELEASE_RPI    0x00000004   /* Release RPI to free pool */
-#define NLP_SUPPRESS_RSP   0x00000010	/* Remote NPort supports suppress rsp */
-#define NLP_PLOGI_SND      0x00000020	/* sent PLOGI request for this entry */
-#define NLP_PRLI_SND       0x00000040	/* sent PRLI request for this entry */
-#define NLP_ADISC_SND      0x00000080	/* sent ADISC request for this entry */
-#define NLP_LOGO_SND       0x00000100	/* sent LOGO request for this entry */
-#define NLP_RNID_SND       0x00000400	/* sent RNID request for this entry */
-#define NLP_ELS_SND_MASK   0x000007e0	/* sent ELS request for this entry */
-#define NLP_NVMET_RECOV    0x00001000   /* NVMET auditing node for recovery. */
-#define NLP_UNREG_INP      0x00008000	/* UNREG_RPI cmd is in progress */
-#define NLP_DROPPED        0x00010000	/* Init ref count has been dropped */
-#define NLP_DELAY_TMO      0x00020000	/* delay timeout is running for node */
-#define NLP_NPR_2B_DISC    0x00040000	/* node is included in num_disc_nodes */
-#define NLP_RCV_PLOGI      0x00080000	/* Rcv'ed PLOGI from remote system */
-#define NLP_LOGO_ACC       0x00100000	/* Process LOGO after ACC completes */
-#define NLP_TGT_NO_SCSIID  0x00200000	/* good PRLI but no binding for scsid */
-#define NLP_ISSUE_LOGO     0x00400000	/* waiting to issue a LOGO */
-#define NLP_IN_DEV_LOSS    0x00800000	/* devloss in progress */
-#define NLP_ACC_REGLOGIN   0x01000000	/* Issue Reg Login after successful
+/* nlp_flag mask bits */
+enum lpfc_nlp_flag {
+	NLP_IGNR_REG_CMPL  = 0,         /* Rcvd rscn before we cmpl reg login */
+	NLP_REG_LOGIN_SEND = 1,         /* sent reglogin to adapter */
+	NLP_SUPPRESS_RSP   = 4,         /* Remote NPort supports suppress rsp */
+	NLP_PLOGI_SND      = 5,         /* sent PLOGI request for this entry */
+	NLP_PRLI_SND       = 6,         /* sent PRLI request for this entry */
+	NLP_ADISC_SND      = 7,         /* sent ADISC request for this entry */
+	NLP_LOGO_SND       = 8,         /* sent LOGO request for this entry */
+	NLP_RNID_SND       = 10,        /* sent RNID request for this entry */
+	NLP_NVMET_RECOV    = 12,        /* NVMET auditing node for recovery. */
+	NLP_UNREG_INP      = 15,        /* UNREG_RPI cmd is in progress */
+	NLP_DROPPED        = 16,        /* Init ref count has been dropped */
+	NLP_DELAY_TMO      = 17,        /* delay timeout is running for node */
+	NLP_NPR_2B_DISC    = 18,        /* node is included in num_disc_nodes */
+	NLP_RCV_PLOGI      = 19,        /* Rcv'ed PLOGI from remote system */
+	NLP_LOGO_ACC       = 20,        /* Process LOGO after ACC completes */
+	NLP_TGT_NO_SCSIID  = 21,        /* good PRLI but no binding for scsid */
+	NLP_ISSUE_LOGO     = 22,        /* waiting to issue a LOGO */
+	NLP_IN_DEV_LOSS    = 23,        /* devloss in progress */
+	NLP_ACC_REGLOGIN   = 24,        /* Issue Reg Login after successful
 					   ACC */
-#define NLP_NPR_ADISC      0x02000000	/* Issue ADISC when dq'ed from
+	NLP_NPR_ADISC      = 25,        /* Issue ADISC when dq'ed from
 					   NPR list */
-#define NLP_RM_DFLT_RPI    0x04000000	/* need to remove leftover dflt RPI */
-#define NLP_NODEV_REMOVE   0x08000000	/* Defer removal till discovery ends */
-#define NLP_TARGET_REMOVE  0x10000000   /* Target remove in process */
-#define NLP_SC_REQ         0x20000000	/* Target requires authentication */
-#define NLP_FIRSTBURST     0x40000000	/* Target supports FirstBurst */
-#define NLP_RPI_REGISTERED 0x80000000	/* nlp_rpi is valid */
+	NLP_RM_DFLT_RPI    = 26,        /* need to remove leftover dflt RPI */
+	NLP_NODEV_REMOVE   = 27,        /* Defer removal till discovery ends */
+	NLP_TARGET_REMOVE  = 28,        /* Target remove in process */
+	NLP_SC_REQ         = 29,        /* Target requires authentication */
+	NLP_FIRSTBURST     = 30,        /* Target supports FirstBurst */
+	NLP_RPI_REGISTERED = 31         /* nlp_rpi is valid */
+};
 
 /* There are 4 different double linked lists nodelist entries can reside on.
  * The Port Login (PLOGI) list and Address Discovery (ADISC) list are used
diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c
index d737b897ddd8..b5fa5054e952 100644
--- a/drivers/scsi/lpfc/lpfc_els.c
+++ b/drivers/scsi/lpfc/lpfc_els.c
@@ -725,11 +725,9 @@ lpfc_cmpl_els_flogi_fabric(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 		list_for_each_entry_safe(np, next_np,
 					&vport->fc_nodes, nlp_listp) {
 			if ((np->nlp_state != NLP_STE_NPR_NODE) ||
-				   !(np->nlp_flag & NLP_NPR_ADISC))
+			    !test_bit(NLP_NPR_ADISC, &np->nlp_flag))
 				continue;
-			spin_lock_irq(&np->lock);
-			np->nlp_flag &= ~NLP_NPR_ADISC;
-			spin_unlock_irq(&np->lock);
+			clear_bit(NLP_NPR_ADISC, &np->nlp_flag);
 			lpfc_unreg_rpi(vport, np);
 		}
 		lpfc_cleanup_pending_mbox(vport);
@@ -864,9 +862,7 @@ lpfc_cmpl_els_flogi_nport(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 		       sizeof(struct lpfc_name));
 		/* Set state will put ndlp onto node list if not already done */
 		lpfc_nlp_set_state(vport, ndlp, NLP_STE_NPR_NODE);
-		spin_lock_irq(&ndlp->lock);
-		ndlp->nlp_flag |= NLP_NPR_2B_DISC;
-		spin_unlock_irq(&ndlp->lock);
+		set_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag);
 
 		mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
 		if (!mbox)
@@ -1018,7 +1014,7 @@ stop_rr_fcf_flogi:
 		 * registered with the SCSI transport, remove the initial
 		 * reference to trigger node release.
 		 */
-		if (!(ndlp->nlp_flag & NLP_IN_DEV_LOSS) &&
+		if (!test_bit(NLP_IN_DEV_LOSS, &ndlp->nlp_flag) &&
 		    !(ndlp->fc4_xpt_flags & SCSI_XPT_REGD))
 			lpfc_nlp_put(ndlp);
 
@@ -1548,7 +1544,7 @@ lpfc_initial_flogi(struct lpfc_vport *vport)
 		 * Otherwise, decrement node reference to trigger release.
 		 */
 		if (!(ndlp->fc4_xpt_flags & (SCSI_XPT_REGD | NVME_XPT_REGD)) &&
-		    !(ndlp->nlp_flag & NLP_IN_DEV_LOSS))
+		    !test_bit(NLP_IN_DEV_LOSS, &ndlp->nlp_flag))
 			lpfc_nlp_put(ndlp);
 		return 0;
 	}
@@ -1597,7 +1593,7 @@ lpfc_initial_fdisc(struct lpfc_vport *vport)
 		 * Otherwise, decrement node reference to trigger release.
 		 */
 		if (!(ndlp->fc4_xpt_flags & (SCSI_XPT_REGD | NVME_XPT_REGD)) &&
-		    !(ndlp->nlp_flag & NLP_IN_DEV_LOSS))
+		    !test_bit(NLP_IN_DEV_LOSS, &ndlp->nlp_flag))
 			lpfc_nlp_put(ndlp);
 		return 0;
 	}
@@ -1675,9 +1671,9 @@ lpfc_plogi_confirm_nport(struct lpfc_hba *phba, uint32_t *prsp,
 	struct lpfc_nodelist *new_ndlp;
 	struct serv_parm *sp;
 	uint8_t  name[sizeof(struct lpfc_name)];
-	uint32_t keepDID = 0, keep_nlp_flag = 0;
+	uint32_t keepDID = 0;
 	int rc;
-	uint32_t keep_new_nlp_flag = 0;
+	unsigned long keep_nlp_flag = 0, keep_new_nlp_flag = 0;
 	uint16_t keep_nlp_state;
 	u32 keep_nlp_fc4_type = 0;
 	struct lpfc_nvme_rport *keep_nrport = NULL;
@@ -1704,8 +1700,8 @@ lpfc_plogi_confirm_nport(struct lpfc_hba *phba, uint32_t *prsp,
 	}
 
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS | LOG_NODE,
-			 "3178 PLOGI confirm: ndlp x%x x%x x%x: "
-			 "new_ndlp x%x x%x x%x\n",
+			 "3178 PLOGI confirm: ndlp x%x x%lx x%x: "
+			 "new_ndlp x%x x%lx x%x\n",
 			 ndlp->nlp_DID, ndlp->nlp_flag,  ndlp->nlp_fc4_type,
 			 (new_ndlp ? new_ndlp->nlp_DID : 0),
 			 (new_ndlp ? new_ndlp->nlp_flag : 0),
@@ -1769,48 +1765,48 @@ lpfc_plogi_confirm_nport(struct lpfc_hba *phba, uint32_t *prsp,
 	new_ndlp->nlp_flag = ndlp->nlp_flag;
 
 	/* if new_ndlp had NLP_UNREG_INP set, keep it */
-	if (keep_new_nlp_flag & NLP_UNREG_INP)
-		new_ndlp->nlp_flag |= NLP_UNREG_INP;
+	if (test_bit(NLP_UNREG_INP, &keep_new_nlp_flag))
+		set_bit(NLP_UNREG_INP, &new_ndlp->nlp_flag);
 	else
-		new_ndlp->nlp_flag &= ~NLP_UNREG_INP;
+		clear_bit(NLP_UNREG_INP, &new_ndlp->nlp_flag);
 
 	/* if new_ndlp had NLP_RPI_REGISTERED set, keep it */
-	if (keep_new_nlp_flag & NLP_RPI_REGISTERED)
-		new_ndlp->nlp_flag |= NLP_RPI_REGISTERED;
+	if (test_bit(NLP_RPI_REGISTERED, &keep_new_nlp_flag))
+		set_bit(NLP_RPI_REGISTERED, &new_ndlp->nlp_flag);
 	else
-		new_ndlp->nlp_flag &= ~NLP_RPI_REGISTERED;
+		clear_bit(NLP_RPI_REGISTERED, &new_ndlp->nlp_flag);
 
 	/*
 	 * Retain the DROPPED flag. This will take care of the init
 	 * refcount when affecting the state change
 	 */
-	if (keep_new_nlp_flag & NLP_DROPPED)
-		new_ndlp->nlp_flag |= NLP_DROPPED;
+	if (test_bit(NLP_DROPPED, &keep_new_nlp_flag))
+		set_bit(NLP_DROPPED, &new_ndlp->nlp_flag);
 	else
-		new_ndlp->nlp_flag &= ~NLP_DROPPED;
+		clear_bit(NLP_DROPPED, &new_ndlp->nlp_flag);
 
 	ndlp->nlp_flag = keep_new_nlp_flag;
 
 	/* if ndlp had NLP_UNREG_INP set, keep it */
-	if (keep_nlp_flag & NLP_UNREG_INP)
-		ndlp->nlp_flag |= NLP_UNREG_INP;
+	if (test_bit(NLP_UNREG_INP, &keep_nlp_flag))
+		set_bit(NLP_UNREG_INP, &ndlp->nlp_flag);
 	else
-		ndlp->nlp_flag &= ~NLP_UNREG_INP;
+		clear_bit(NLP_UNREG_INP, &ndlp->nlp_flag);
 
 	/* if ndlp had NLP_RPI_REGISTERED set, keep it */
-	if (keep_nlp_flag & NLP_RPI_REGISTERED)
-		ndlp->nlp_flag |= NLP_RPI_REGISTERED;
+	if (test_bit(NLP_RPI_REGISTERED, &keep_nlp_flag))
+		set_bit(NLP_RPI_REGISTERED, &ndlp->nlp_flag);
 	else
-		ndlp->nlp_flag &= ~NLP_RPI_REGISTERED;
+		clear_bit(NLP_RPI_REGISTERED, &ndlp->nlp_flag);
 
 	/*
 	 * Retain the DROPPED flag. This will take care of the init
 	 * refcount when affecting the state change
 	 */
-	if (keep_nlp_flag & NLP_DROPPED)
-		ndlp->nlp_flag |= NLP_DROPPED;
+	if (test_bit(NLP_DROPPED, &keep_nlp_flag))
+		set_bit(NLP_DROPPED, &ndlp->nlp_flag);
 	else
-		ndlp->nlp_flag &= ~NLP_DROPPED;
+		clear_bit(NLP_DROPPED, &ndlp->nlp_flag);
 
 	spin_unlock_irq(&new_ndlp->lock);
 	spin_unlock_irq(&ndlp->lock);
@@ -1888,7 +1884,7 @@ lpfc_plogi_confirm_nport(struct lpfc_hba *phba, uint32_t *prsp,
 			     phba->active_rrq_pool);
 
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS | LOG_NODE,
-			 "3173 PLOGI confirm exit: new_ndlp x%x x%x x%x\n",
+			 "3173 PLOGI confirm exit: new_ndlp x%x x%lx x%x\n",
 			 new_ndlp->nlp_DID, new_ndlp->nlp_flag,
 			 new_ndlp->nlp_fc4_type);
 
@@ -2009,7 +2005,7 @@ lpfc_cmpl_els_plogi(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 	IOCB_t *irsp;
 	struct lpfc_nodelist *ndlp, *free_ndlp;
 	struct lpfc_dmabuf *prsp;
-	int disc;
+	bool disc;
 	struct serv_parm *sp = NULL;
 	u32 ulp_status, ulp_word4, did, iotag;
 	bool release_node = false;
@@ -2044,10 +2040,7 @@ lpfc_cmpl_els_plogi(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 	/* Since ndlp can be freed in the disc state machine, note if this node
 	 * is being used during discovery.
 	 */
-	spin_lock_irq(&ndlp->lock);
-	disc = (ndlp->nlp_flag & NLP_NPR_2B_DISC);
-	ndlp->nlp_flag &= ~NLP_NPR_2B_DISC;
-	spin_unlock_irq(&ndlp->lock);
+	disc = test_and_clear_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag);
 
 	/* PLOGI completes to NPort <nlp_DID> */
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS,
@@ -2060,9 +2053,7 @@ lpfc_cmpl_els_plogi(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 
 	/* Check to see if link went down during discovery */
 	if (lpfc_els_chk_latt(vport)) {
-		spin_lock_irq(&ndlp->lock);
-		ndlp->nlp_flag |= NLP_NPR_2B_DISC;
-		spin_unlock_irq(&ndlp->lock);
+		set_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag);
 		goto out;
 	}
 
@@ -2070,11 +2061,8 @@ lpfc_cmpl_els_plogi(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 		/* Check for retry */
 		if (lpfc_els_retry(phba, cmdiocb, rspiocb)) {
 			/* ELS command is being retried */
-			if (disc) {
-				spin_lock_irq(&ndlp->lock);
-				ndlp->nlp_flag |= NLP_NPR_2B_DISC;
-				spin_unlock_irq(&ndlp->lock);
-			}
+			if (disc)
+				set_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag);
 			goto out;
 		}
 		/* Warn PLOGI status Don't print the vport to vport rjts */
@@ -2097,7 +2085,8 @@ lpfc_cmpl_els_plogi(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 		 * with the reglogin process.
 		 */
 		spin_lock_irq(&ndlp->lock);
-		if ((ndlp->nlp_flag & (NLP_ACC_REGLOGIN | NLP_RCV_PLOGI)) &&
+		if ((test_bit(NLP_ACC_REGLOGIN, &ndlp->nlp_flag) ||
+		     test_bit(NLP_RCV_PLOGI, &ndlp->nlp_flag)) &&
 		    ndlp->nlp_state == NLP_STE_REG_LOGIN_ISSUE) {
 			spin_unlock_irq(&ndlp->lock);
 			goto out;
@@ -2108,8 +2097,8 @@ lpfc_cmpl_els_plogi(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 		 * start the device remove process.
 		 */
 		if (!(ndlp->fc4_xpt_flags & (SCSI_XPT_REGD | NVME_XPT_REGD))) {
-			ndlp->nlp_flag &= ~NLP_NPR_2B_DISC;
-			if (!(ndlp->nlp_flag & NLP_IN_DEV_LOSS))
+			clear_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag);
+			if (!test_bit(NLP_IN_DEV_LOSS, &ndlp->nlp_flag))
 				release_node = true;
 		}
 		spin_unlock_irq(&ndlp->lock);
@@ -2212,12 +2201,13 @@ lpfc_issue_els_plogi(struct lpfc_vport *vport, uint32_t did, uint8_t retry)
 	 * outstanding UNREG_RPI mbox command completes, unless we
 	 * are going offline. This logic does not apply for Fabric DIDs
 	 */
-	if ((ndlp->nlp_flag & (NLP_IGNR_REG_CMPL | NLP_UNREG_INP)) &&
+	if ((test_bit(NLP_IGNR_REG_CMPL, &ndlp->nlp_flag) ||
+	     test_bit(NLP_UNREG_INP, &ndlp->nlp_flag)) &&
 	    ((ndlp->nlp_DID & Fabric_DID_MASK) != Fabric_DID_MASK) &&
 	    !test_bit(FC_OFFLINE_MODE, &vport->fc_flag)) {
 		lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY,
 				 "4110 Issue PLOGI x%x deferred "
-				 "on NPort x%x rpi x%x flg x%x Data:"
+				 "on NPort x%x rpi x%x flg x%lx Data:"
 				 " x%px\n",
 				 ndlp->nlp_defer_did, ndlp->nlp_DID,
 				 ndlp->nlp_rpi, ndlp->nlp_flag, ndlp);
@@ -2335,10 +2325,10 @@ lpfc_cmpl_els_prli(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 	ulp_status = get_job_ulpstatus(phba, rspiocb);
 	ulp_word4 = get_job_word4(phba, rspiocb);
 
-	spin_lock_irq(&ndlp->lock);
-	ndlp->nlp_flag &= ~NLP_PRLI_SND;
+	clear_bit(NLP_PRLI_SND, &ndlp->nlp_flag);
 
 	/* Driver supports multiple FC4 types.  Counters matter. */
+	spin_lock_irq(&ndlp->lock);
 	vport->fc_prli_sent--;
 	ndlp->fc4_prli_sent--;
 	spin_unlock_irq(&ndlp->lock);
@@ -2379,7 +2369,7 @@ lpfc_cmpl_els_prli(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 		/* Warn PRLI status */
 		lpfc_printf_vlog(vport, mode, LOG_ELS,
 				 "2754 PRLI DID:%06X Status:x%x/x%x, "
-				 "data: x%x x%x x%x\n",
+				 "data: x%x x%x x%lx\n",
 				 ndlp->nlp_DID, ulp_status,
 				 ulp_word4, ndlp->nlp_state,
 				 ndlp->fc4_prli_sent, ndlp->nlp_flag);
@@ -2396,10 +2386,10 @@ lpfc_cmpl_els_prli(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 		if ((ndlp->nlp_state >= NLP_STE_PLOGI_ISSUE &&
 		     ndlp->nlp_state <= NLP_STE_REG_LOGIN_ISSUE) ||
 		    (ndlp->nlp_state == NLP_STE_NPR_NODE &&
-		     ndlp->nlp_flag & NLP_DELAY_TMO)) {
-			lpfc_printf_vlog(vport, KERN_WARNING, LOG_NODE,
+		     test_bit(NLP_DELAY_TMO, &ndlp->nlp_flag))) {
+			lpfc_printf_vlog(vport, KERN_ERR, LOG_NODE,
 					 "2784 PRLI cmpl: Allow Node recovery "
-					 "DID x%06x nstate x%x nflag x%x\n",
+					 "DID x%06x nstate x%x nflag x%lx\n",
 					 ndlp->nlp_DID, ndlp->nlp_state,
 					 ndlp->nlp_flag);
 			goto out;
@@ -2420,8 +2410,8 @@ lpfc_cmpl_els_prli(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 		spin_lock_irq(&ndlp->lock);
 		if (!(ndlp->fc4_xpt_flags & (SCSI_XPT_REGD | NVME_XPT_REGD)) &&
 		    !ndlp->fc4_prli_sent) {
-			ndlp->nlp_flag &= ~NLP_NPR_2B_DISC;
-			if (!(ndlp->nlp_flag & NLP_IN_DEV_LOSS))
+			clear_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag);
+			if (!test_bit(NLP_IN_DEV_LOSS, &ndlp->nlp_flag))
 				release_node = true;
 		}
 		spin_unlock_irq(&ndlp->lock);
@@ -2496,7 +2486,8 @@ lpfc_issue_els_prli(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	ndlp->nlp_type &= ~(NLP_FCP_TARGET | NLP_FCP_INITIATOR);
 	ndlp->nlp_type &= ~(NLP_NVME_TARGET | NLP_NVME_INITIATOR);
 	ndlp->nlp_fcp_info &= ~NLP_FCP_2_DEVICE;
-	ndlp->nlp_flag &= ~(NLP_FIRSTBURST | NLP_NPR_2B_DISC);
+	clear_bit(NLP_FIRSTBURST, &ndlp->nlp_flag);
+	clear_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag);
 	ndlp->nvme_fb_size = 0;
 
  send_next_prli:
@@ -2627,8 +2618,8 @@ lpfc_issue_els_prli(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	 * the ndlp is used to track outstanding PRLIs for different
 	 * FC4 types.
 	 */
+	set_bit(NLP_PRLI_SND, &ndlp->nlp_flag);
 	spin_lock_irq(&ndlp->lock);
-	ndlp->nlp_flag |= NLP_PRLI_SND;
 	vport->fc_prli_sent++;
 	ndlp->fc4_prli_sent++;
 	spin_unlock_irq(&ndlp->lock);
@@ -2789,7 +2780,7 @@ lpfc_cmpl_els_adisc(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 	struct lpfc_vport *vport = cmdiocb->vport;
 	IOCB_t *irsp;
 	struct lpfc_nodelist *ndlp;
-	int  disc;
+	bool  disc;
 	u32 ulp_status, ulp_word4, tmo, iotag;
 	bool release_node = false;
 
@@ -2818,10 +2809,8 @@ lpfc_cmpl_els_adisc(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 	/* Since ndlp can be freed in the disc state machine, note if this node
 	 * is being used during discovery.
 	 */
-	spin_lock_irq(&ndlp->lock);
-	disc = (ndlp->nlp_flag & NLP_NPR_2B_DISC);
-	ndlp->nlp_flag &= ~(NLP_ADISC_SND | NLP_NPR_2B_DISC);
-	spin_unlock_irq(&ndlp->lock);
+	disc = test_and_clear_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag);
+	clear_bit(NLP_ADISC_SND, &ndlp->nlp_flag);
 	/* ADISC completes to NPort <nlp_DID> */
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS,
 			 "0104 ADISC completes to NPort x%x "
@@ -2832,9 +2821,7 @@ lpfc_cmpl_els_adisc(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 
 	/* Check to see if link went down during discovery */
 	if (lpfc_els_chk_latt(vport)) {
-		spin_lock_irq(&ndlp->lock);
-		ndlp->nlp_flag |= NLP_NPR_2B_DISC;
-		spin_unlock_irq(&ndlp->lock);
+		set_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag);
 		goto out;
 	}
 
@@ -2843,9 +2830,7 @@ lpfc_cmpl_els_adisc(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 		if (lpfc_els_retry(phba, cmdiocb, rspiocb)) {
 			/* ELS command is being retried */
 			if (disc) {
-				spin_lock_irq(&ndlp->lock);
-				ndlp->nlp_flag |= NLP_NPR_2B_DISC;
-				spin_unlock_irq(&ndlp->lock);
+				set_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag);
 				lpfc_set_disctmo(vport);
 			}
 			goto out;
@@ -2864,8 +2849,8 @@ lpfc_cmpl_els_adisc(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 		 */
 		spin_lock_irq(&ndlp->lock);
 		if (!(ndlp->fc4_xpt_flags & (SCSI_XPT_REGD | NVME_XPT_REGD))) {
-			ndlp->nlp_flag &= ~NLP_NPR_2B_DISC;
-			if (!(ndlp->nlp_flag & NLP_IN_DEV_LOSS))
+			clear_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag);
+			if (!test_bit(NLP_IN_DEV_LOSS, &ndlp->nlp_flag))
 				release_node = true;
 		}
 		spin_unlock_irq(&ndlp->lock);
@@ -2938,9 +2923,7 @@ lpfc_issue_els_adisc(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 
 	phba->fc_stat.elsXmitADISC++;
 	elsiocb->cmd_cmpl = lpfc_cmpl_els_adisc;
-	spin_lock_irq(&ndlp->lock);
-	ndlp->nlp_flag |= NLP_ADISC_SND;
-	spin_unlock_irq(&ndlp->lock);
+	set_bit(NLP_ADISC_SND, &ndlp->nlp_flag);
 	elsiocb->ndlp = lpfc_nlp_get(ndlp);
 	if (!elsiocb->ndlp) {
 		lpfc_els_free_iocb(phba, elsiocb);
@@ -2961,9 +2944,7 @@ lpfc_issue_els_adisc(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	return 0;
 
 err:
-	spin_lock_irq(&ndlp->lock);
-	ndlp->nlp_flag &= ~NLP_ADISC_SND;
-	spin_unlock_irq(&ndlp->lock);
+	clear_bit(NLP_ADISC_SND, &ndlp->nlp_flag);
 	return 1;
 }
 
@@ -2985,7 +2966,6 @@ lpfc_cmpl_els_logo(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 	struct lpfc_nodelist *ndlp = cmdiocb->ndlp;
 	struct lpfc_vport *vport = ndlp->vport;
 	IOCB_t *irsp;
-	unsigned long flags;
 	uint32_t skip_recovery = 0;
 	int wake_up_waiter = 0;
 	u32 ulp_status;
@@ -3007,8 +2987,8 @@ lpfc_cmpl_els_logo(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 		iotag = irsp->ulpIoTag;
 	}
 
+	clear_bit(NLP_LOGO_SND, &ndlp->nlp_flag);
 	spin_lock_irq(&ndlp->lock);
-	ndlp->nlp_flag &= ~NLP_LOGO_SND;
 	if (ndlp->save_flags & NLP_WAIT_FOR_LOGO) {
 		wake_up_waiter = 1;
 		ndlp->save_flags &= ~NLP_WAIT_FOR_LOGO;
@@ -3023,7 +3003,7 @@ lpfc_cmpl_els_logo(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 	/* LOGO completes to NPort <nlp_DID> */
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS,
 			 "0105 LOGO completes to NPort x%x "
-			 "IoTag x%x refcnt %d nflags x%x xflags x%x "
+			 "IoTag x%x refcnt %d nflags x%lx xflags x%x "
 			 "Data: x%x x%x x%x x%x\n",
 			 ndlp->nlp_DID, iotag,
 			 kref_read(&ndlp->kref), ndlp->nlp_flag,
@@ -3061,12 +3041,8 @@ lpfc_cmpl_els_logo(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 	/* The driver sets this flag for an NPIV instance that doesn't want to
 	 * log into the remote port.
 	 */
-	if (ndlp->nlp_flag & NLP_TARGET_REMOVE) {
-		spin_lock_irq(&ndlp->lock);
-		if (phba->sli_rev == LPFC_SLI_REV4)
-			ndlp->nlp_flag |= NLP_RELEASE_RPI;
-		ndlp->nlp_flag &= ~NLP_NPR_2B_DISC;
-		spin_unlock_irq(&ndlp->lock);
+	if (test_bit(NLP_TARGET_REMOVE, &ndlp->nlp_flag)) {
+		clear_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag);
 		lpfc_disc_state_machine(vport, ndlp, cmdiocb,
 					NLP_EVT_DEVICE_RM);
 		goto out_rsrc_free;
@@ -3089,9 +3065,7 @@ out:
 	if (ndlp->nlp_type & (NLP_FCP_TARGET | NLP_NVME_TARGET) &&
 	    skip_recovery == 0) {
 		lpfc_cancel_retry_delay_tmo(vport, ndlp);
-		spin_lock_irqsave(&ndlp->lock, flags);
-		ndlp->nlp_flag |= NLP_NPR_2B_DISC;
-		spin_unlock_irqrestore(&ndlp->lock, flags);
+		set_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag);
 
 		lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS,
 				 "3187 LOGO completes to NPort x%x: Start "
@@ -3113,9 +3087,7 @@ out:
 	 * register with the transport.
 	 */
 	if (!(ndlp->fc4_xpt_flags & (SCSI_XPT_REGD | NVME_XPT_REGD))) {
-		spin_lock_irq(&ndlp->lock);
-		ndlp->nlp_flag &= ~NLP_NPR_2B_DISC;
-		spin_unlock_irq(&ndlp->lock);
+		clear_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag);
 		lpfc_disc_state_machine(vport, ndlp, cmdiocb,
 					NLP_EVT_DEVICE_RM);
 	}
@@ -3156,12 +3128,8 @@ lpfc_issue_els_logo(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	uint16_t cmdsize;
 	int rc;
 
-	spin_lock_irq(&ndlp->lock);
-	if (ndlp->nlp_flag & NLP_LOGO_SND) {
-		spin_unlock_irq(&ndlp->lock);
+	if (test_bit(NLP_LOGO_SND, &ndlp->nlp_flag))
 		return 0;
-	}
-	spin_unlock_irq(&ndlp->lock);
 
 	cmdsize = (2 * sizeof(uint32_t)) + sizeof(struct lpfc_name);
 	elsiocb = lpfc_prep_els_iocb(vport, 1, cmdsize, retry, ndlp,
@@ -3180,10 +3148,8 @@ lpfc_issue_els_logo(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 
 	phba->fc_stat.elsXmitLOGO++;
 	elsiocb->cmd_cmpl = lpfc_cmpl_els_logo;
-	spin_lock_irq(&ndlp->lock);
-	ndlp->nlp_flag |= NLP_LOGO_SND;
-	ndlp->nlp_flag &= ~NLP_ISSUE_LOGO;
-	spin_unlock_irq(&ndlp->lock);
+	set_bit(NLP_LOGO_SND, &ndlp->nlp_flag);
+	clear_bit(NLP_ISSUE_LOGO, &ndlp->nlp_flag);
 	elsiocb->ndlp = lpfc_nlp_get(ndlp);
 	if (!elsiocb->ndlp) {
 		lpfc_els_free_iocb(phba, elsiocb);
@@ -3208,9 +3174,7 @@ lpfc_issue_els_logo(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	return 0;
 
 err:
-	spin_lock_irq(&ndlp->lock);
-	ndlp->nlp_flag &= ~NLP_LOGO_SND;
-	spin_unlock_irq(&ndlp->lock);
+	clear_bit(NLP_LOGO_SND, &ndlp->nlp_flag);
 	return 1;
 }
 
@@ -3286,13 +3250,13 @@ lpfc_cmpl_els_cmd(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 static int
 lpfc_reg_fab_ctrl_node(struct lpfc_vport *vport, struct lpfc_nodelist *fc_ndlp)
 {
-	int rc = 0;
+	int rc;
 	struct lpfc_hba *phba = vport->phba;
 	struct lpfc_nodelist *ns_ndlp;
 	LPFC_MBOXQ_t *mbox;
 
-	if (fc_ndlp->nlp_flag & NLP_RPI_REGISTERED)
-		return rc;
+	if (test_bit(NLP_RPI_REGISTERED, &fc_ndlp->nlp_flag))
+		return 0;
 
 	ns_ndlp = lpfc_findnode_did(vport, NameServer_DID);
 	if (!ns_ndlp)
@@ -3309,7 +3273,7 @@ lpfc_reg_fab_ctrl_node(struct lpfc_vport *vport, struct lpfc_nodelist *fc_ndlp)
 	if (!mbox) {
 		lpfc_printf_vlog(vport, KERN_ERR, LOG_NODE,
 				 "0936 %s: no memory for reg_login "
-				 "Data: x%x x%x x%x x%x\n", __func__,
+				 "Data: x%x x%x x%lx x%x\n", __func__,
 				 fc_ndlp->nlp_DID, fc_ndlp->nlp_state,
 				 fc_ndlp->nlp_flag, fc_ndlp->nlp_rpi);
 		return -ENOMEM;
@@ -3321,7 +3285,7 @@ lpfc_reg_fab_ctrl_node(struct lpfc_vport *vport, struct lpfc_nodelist *fc_ndlp)
 		goto out;
 	}
 
-	fc_ndlp->nlp_flag |= NLP_REG_LOGIN_SEND;
+	set_bit(NLP_REG_LOGIN_SEND, &fc_ndlp->nlp_flag);
 	mbox->mbox_cmpl = lpfc_mbx_cmpl_fc_reg_login;
 	mbox->ctx_ndlp = lpfc_nlp_get(fc_ndlp);
 	if (!mbox->ctx_ndlp) {
@@ -3345,7 +3309,7 @@ lpfc_reg_fab_ctrl_node(struct lpfc_vport *vport, struct lpfc_nodelist *fc_ndlp)
 	lpfc_mbox_rsrc_cleanup(phba, mbox, MBOX_THD_UNLOCKED);
 	lpfc_printf_vlog(vport, KERN_ERR, LOG_NODE,
 			 "0938 %s: failed to format reg_login "
-			 "Data: x%x x%x x%x x%x\n", __func__,
+			 "Data: x%x x%x x%lx x%x\n", __func__,
 			 fc_ndlp->nlp_DID, fc_ndlp->nlp_state,
 			 fc_ndlp->nlp_flag, fc_ndlp->nlp_rpi);
 	return rc;
@@ -4384,11 +4348,8 @@ lpfc_cancel_retry_delay_tmo(struct lpfc_vport *vport, struct lpfc_nodelist *nlp)
 {
 	struct lpfc_work_evt *evtp;
 
-	if (!(nlp->nlp_flag & NLP_DELAY_TMO))
+	if (!test_and_clear_bit(NLP_DELAY_TMO, &nlp->nlp_flag))
 		return;
-	spin_lock_irq(&nlp->lock);
-	nlp->nlp_flag &= ~NLP_DELAY_TMO;
-	spin_unlock_irq(&nlp->lock);
 	del_timer_sync(&nlp->nlp_delayfunc);
 	nlp->nlp_last_elscmd = 0;
 	if (!list_empty(&nlp->els_retry_evt.evt_listp)) {
@@ -4397,10 +4358,7 @@ lpfc_cancel_retry_delay_tmo(struct lpfc_vport *vport, struct lpfc_nodelist *nlp)
 		evtp = &nlp->els_retry_evt;
 		lpfc_nlp_put((struct lpfc_nodelist *)evtp->evt_arg1);
 	}
-	if (nlp->nlp_flag & NLP_NPR_2B_DISC) {
-		spin_lock_irq(&nlp->lock);
-		nlp->nlp_flag &= ~NLP_NPR_2B_DISC;
-		spin_unlock_irq(&nlp->lock);
+	if (test_and_clear_bit(NLP_NPR_2B_DISC, &nlp->nlp_flag)) {
 		if (vport->num_disc_nodes) {
 			if (vport->port_state < LPFC_VPORT_READY) {
 				/* Check if there are more ADISCs to be sent */
@@ -4480,14 +4438,11 @@ lpfc_els_retry_delay_handler(struct lpfc_nodelist *ndlp)
 	spin_lock_irq(&ndlp->lock);
 	cmd = ndlp->nlp_last_elscmd;
 	ndlp->nlp_last_elscmd = 0;
+	spin_unlock_irq(&ndlp->lock);
 
-	if (!(ndlp->nlp_flag & NLP_DELAY_TMO)) {
-		spin_unlock_irq(&ndlp->lock);
+	if (!test_and_clear_bit(NLP_DELAY_TMO, &ndlp->nlp_flag))
 		return;
-	}
 
-	ndlp->nlp_flag &= ~NLP_DELAY_TMO;
-	spin_unlock_irq(&ndlp->lock);
 	/*
 	 * If a discovery event readded nlp_delayfunc after timer
 	 * firing and before processing the timer, cancel the
@@ -5010,9 +4965,7 @@ out_retry:
 			/* delay is specified in milliseconds */
 			mod_timer(&ndlp->nlp_delayfunc,
 				jiffies + msecs_to_jiffies(delay));
-			spin_lock_irq(&ndlp->lock);
-			ndlp->nlp_flag |= NLP_DELAY_TMO;
-			spin_unlock_irq(&ndlp->lock);
+			set_bit(NLP_DELAY_TMO, &ndlp->nlp_flag);
 
 			ndlp->nlp_prev_state = ndlp->nlp_state;
 			if ((cmd == ELS_CMD_PRLI) ||
@@ -5072,7 +5025,7 @@ out_retry:
 		lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS,
 				 "0108 No retry ELS command x%x to remote "
 				 "NPORT x%x Retried:%d Error:x%x/%x "
-				 "IoTag x%x nflags x%x\n",
+				 "IoTag x%x nflags x%lx\n",
 				 cmd, did, cmdiocb->retry, ulp_status,
 				 ulp_word4, cmdiocb->iotag,
 				 (ndlp ? ndlp->nlp_flag : 0));
@@ -5239,7 +5192,7 @@ lpfc_cmpl_els_logo_acc(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 	/* ACC to LOGO completes to NPort <nlp_DID> */
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS,
 			 "0109 ACC to LOGO completes to NPort x%x refcnt %d "
-			 "last els x%x Data: x%x x%x x%x\n",
+			 "last els x%x Data: x%lx x%x x%x\n",
 			 ndlp->nlp_DID, kref_read(&ndlp->kref),
 			 ndlp->nlp_last_elscmd, ndlp->nlp_flag, ndlp->nlp_state,
 			 ndlp->nlp_rpi);
@@ -5254,16 +5207,14 @@ lpfc_cmpl_els_logo_acc(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 		goto out;
 
 	if (ndlp->nlp_state == NLP_STE_NPR_NODE) {
-		if (ndlp->nlp_flag & NLP_RPI_REGISTERED)
+		if (test_bit(NLP_RPI_REGISTERED, &ndlp->nlp_flag))
 			lpfc_unreg_rpi(vport, ndlp);
 
 		/* If came from PRLO, then PRLO_ACC is done.
 		 * Start rediscovery now.
 		 */
 		if (ndlp->nlp_last_elscmd == ELS_CMD_PRLO) {
-			spin_lock_irq(&ndlp->lock);
-			ndlp->nlp_flag |= NLP_NPR_2B_DISC;
-			spin_unlock_irq(&ndlp->lock);
+			set_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag);
 			ndlp->nlp_prev_state = ndlp->nlp_state;
 			lpfc_nlp_set_state(vport, ndlp, NLP_STE_PLOGI_ISSUE);
 			lpfc_issue_els_plogi(vport, ndlp->nlp_DID, 0);
@@ -5300,7 +5251,7 @@ lpfc_mbx_cmpl_dflt_rpi(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 
 	if (ndlp) {
 		lpfc_printf_vlog(ndlp->vport, KERN_INFO, LOG_NODE,
-				 "0006 rpi x%x DID:%x flg:%x %d x%px "
+				 "0006 rpi x%x DID:%x flg:%lx %d x%px "
 				 "mbx_cmd x%x mbx_flag x%x x%px\n",
 				 ndlp->nlp_rpi, ndlp->nlp_DID, ndlp->nlp_flag,
 				 kref_read(&ndlp->kref), ndlp, mbx_cmd,
@@ -5311,11 +5262,9 @@ lpfc_mbx_cmpl_dflt_rpi(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 		 * first on an UNREG_LOGIN and then release the final
 		 * references.
 		 */
-		spin_lock_irq(&ndlp->lock);
-		ndlp->nlp_flag &= ~NLP_REG_LOGIN_SEND;
+		clear_bit(NLP_REG_LOGIN_SEND, &ndlp->nlp_flag);
 		if (mbx_cmd == MBX_UNREG_LOGIN)
-			ndlp->nlp_flag &= ~NLP_UNREG_INP;
-		spin_unlock_irq(&ndlp->lock);
+			clear_bit(NLP_UNREG_INP, &ndlp->nlp_flag);
 		lpfc_nlp_put(ndlp);
 		lpfc_drop_node(ndlp->vport, ndlp);
 	}
@@ -5381,23 +5330,23 @@ lpfc_cmpl_els_rsp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 	/* ELS response tag <ulpIoTag> completes */
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS,
 			 "0110 ELS response tag x%x completes "
-			 "Data: x%x x%x x%x x%x x%x x%x x%x x%x %p %p\n",
+			 "Data: x%x x%x x%x x%x x%lx x%x x%x x%x %p %p\n",
 			 iotag, ulp_status, ulp_word4, tmo,
 			 ndlp->nlp_DID, ndlp->nlp_flag, ndlp->nlp_state,
 			 ndlp->nlp_rpi, kref_read(&ndlp->kref), mbox, ndlp);
 	if (mbox) {
-		if (ulp_status == 0
-		    && (ndlp->nlp_flag & NLP_ACC_REGLOGIN)) {
+		if (ulp_status == 0 &&
+		    test_bit(NLP_ACC_REGLOGIN, &ndlp->nlp_flag)) {
 			if (!lpfc_unreg_rpi(vport, ndlp) &&
 			    !test_bit(FC_PT2PT, &vport->fc_flag)) {
-				if (ndlp->nlp_state ==  NLP_STE_PLOGI_ISSUE ||
+				if (ndlp->nlp_state == NLP_STE_PLOGI_ISSUE ||
 				    ndlp->nlp_state ==
 				     NLP_STE_REG_LOGIN_ISSUE) {
 					lpfc_printf_vlog(vport, KERN_INFO,
 							 LOG_DISCOVERY,
 							 "0314 PLOGI recov "
 							 "DID x%x "
-							 "Data: x%x x%x x%x\n",
+							 "Data: x%x x%x x%lx\n",
 							 ndlp->nlp_DID,
 							 ndlp->nlp_state,
 							 ndlp->nlp_rpi,
@@ -5414,18 +5363,17 @@ lpfc_cmpl_els_rsp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 				goto out_free_mbox;
 
 			mbox->vport = vport;
-			if (ndlp->nlp_flag & NLP_RM_DFLT_RPI) {
+			if (test_bit(NLP_RM_DFLT_RPI, &ndlp->nlp_flag)) {
 				mbox->mbox_flag |= LPFC_MBX_IMED_UNREG;
 				mbox->mbox_cmpl = lpfc_mbx_cmpl_dflt_rpi;
-			}
-			else {
+			} else {
 				mbox->mbox_cmpl = lpfc_mbx_cmpl_reg_login;
 				ndlp->nlp_prev_state = ndlp->nlp_state;
 				lpfc_nlp_set_state(vport, ndlp,
 					   NLP_STE_REG_LOGIN_ISSUE);
 			}
 
-			ndlp->nlp_flag |= NLP_REG_LOGIN_SEND;
+			set_bit(NLP_REG_LOGIN_SEND, &ndlp->nlp_flag);
 			if (lpfc_sli_issue_mbox(phba, mbox, MBX_NOWAIT)
 			    != MBX_NOT_FINISHED)
 				goto out;
@@ -5434,12 +5382,12 @@ lpfc_cmpl_els_rsp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 			 * set for this failed mailbox command.
 			 */
 			lpfc_nlp_put(ndlp);
-			ndlp->nlp_flag &= ~NLP_REG_LOGIN_SEND;
+			clear_bit(NLP_REG_LOGIN_SEND, &ndlp->nlp_flag);
 
 			/* ELS rsp: Cannot issue reg_login for <NPortid> */
 			lpfc_printf_vlog(vport, KERN_ERR, LOG_TRACE_EVENT,
 				"0138 ELS rsp: Cannot issue reg_login for x%x "
-				"Data: x%x x%x x%x\n",
+				"Data: x%lx x%x x%x\n",
 				ndlp->nlp_DID, ndlp->nlp_flag, ndlp->nlp_state,
 				ndlp->nlp_rpi);
 		}
@@ -5448,32 +5396,20 @@ out_free_mbox:
 	}
 out:
 	if (ndlp && shost) {
-		spin_lock_irq(&ndlp->lock);
 		if (mbox)
-			ndlp->nlp_flag &= ~NLP_ACC_REGLOGIN;
-		ndlp->nlp_flag &= ~NLP_RM_DFLT_RPI;
-		spin_unlock_irq(&ndlp->lock);
+			clear_bit(NLP_ACC_REGLOGIN, &ndlp->nlp_flag);
+		clear_bit(NLP_RM_DFLT_RPI, &ndlp->nlp_flag);
 	}
 
 	/* An SLI4 NPIV instance wants to drop the node at this point under
-	 * these conditions and release the RPI.
+	 * these conditions because it doesn't need the login.
 	 */
 	if (phba->sli_rev == LPFC_SLI_REV4 &&
 	    vport && vport->port_type == LPFC_NPIV_PORT &&
 	    !(ndlp->fc4_xpt_flags & SCSI_XPT_REGD)) {
-		if (ndlp->nlp_flag & NLP_RELEASE_RPI) {
-			if (ndlp->nlp_state != NLP_STE_PLOGI_ISSUE &&
-			    ndlp->nlp_state != NLP_STE_REG_LOGIN_ISSUE) {
-				lpfc_sli4_free_rpi(phba, ndlp->nlp_rpi);
-				spin_lock_irq(&ndlp->lock);
-				ndlp->nlp_rpi = LPFC_RPI_ALLOC_ERROR;
-				ndlp->nlp_flag &= ~NLP_RELEASE_RPI;
-				spin_unlock_irq(&ndlp->lock);
-			}
-			lpfc_drop_node(vport, ndlp);
-		} else if (ndlp->nlp_state != NLP_STE_PLOGI_ISSUE &&
-			   ndlp->nlp_state != NLP_STE_REG_LOGIN_ISSUE &&
-			   ndlp->nlp_state != NLP_STE_PRLI_ISSUE) {
+		if (ndlp->nlp_state != NLP_STE_PLOGI_ISSUE &&
+		    ndlp->nlp_state != NLP_STE_REG_LOGIN_ISSUE &&
+		    ndlp->nlp_state != NLP_STE_PRLI_ISSUE) {
 			/* Drop ndlp if there is no planned or outstanding
 			 * issued PRLI.
 			 *
@@ -5540,9 +5476,7 @@ lpfc_els_rsp_acc(struct lpfc_vport *vport, uint32_t flag,
 		elsiocb = lpfc_prep_els_iocb(vport, 0, cmdsize, oldiocb->retry,
 					     ndlp, ndlp->nlp_DID, ELS_CMD_ACC);
 		if (!elsiocb) {
-			spin_lock_irq(&ndlp->lock);
-			ndlp->nlp_flag &= ~NLP_LOGO_ACC;
-			spin_unlock_irq(&ndlp->lock);
+			clear_bit(NLP_LOGO_ACC, &ndlp->nlp_flag);
 			return 1;
 		}
 
@@ -5570,7 +5504,7 @@ lpfc_els_rsp_acc(struct lpfc_vport *vport, uint32_t flag,
 		pcmd += sizeof(uint32_t);
 
 		lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_RSP,
-			"Issue ACC:       did:x%x flg:x%x",
+			"Issue ACC:       did:x%x flg:x%lx",
 			ndlp->nlp_DID, ndlp->nlp_flag, 0);
 		break;
 	case ELS_CMD_FLOGI:
@@ -5649,7 +5583,7 @@ lpfc_els_rsp_acc(struct lpfc_vport *vport, uint32_t flag,
 		}
 
 		lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_RSP,
-			"Issue ACC FLOGI/PLOGI: did:x%x flg:x%x",
+			"Issue ACC FLOGI/PLOGI: did:x%x flg:x%lx",
 			ndlp->nlp_DID, ndlp->nlp_flag, 0);
 		break;
 	case ELS_CMD_PRLO:
@@ -5687,7 +5621,7 @@ lpfc_els_rsp_acc(struct lpfc_vport *vport, uint32_t flag,
 		els_pkt_ptr->un.prlo.acceptRspCode = PRLO_REQ_EXECUTED;
 
 		lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_RSP,
-			"Issue ACC PRLO:  did:x%x flg:x%x",
+			"Issue ACC PRLO:  did:x%x flg:x%lx",
 			ndlp->nlp_DID, ndlp->nlp_flag, 0);
 		break;
 	case ELS_CMD_RDF:
@@ -5732,12 +5666,10 @@ lpfc_els_rsp_acc(struct lpfc_vport *vport, uint32_t flag,
 	default:
 		return 1;
 	}
-	if (ndlp->nlp_flag & NLP_LOGO_ACC) {
-		spin_lock_irq(&ndlp->lock);
-		if (!(ndlp->nlp_flag & NLP_RPI_REGISTERED ||
-			ndlp->nlp_flag & NLP_REG_LOGIN_SEND))
-			ndlp->nlp_flag &= ~NLP_LOGO_ACC;
-		spin_unlock_irq(&ndlp->lock);
+	if (test_bit(NLP_LOGO_ACC, &ndlp->nlp_flag)) {
+		if (!test_bit(NLP_RPI_REGISTERED, &ndlp->nlp_flag) &&
+		    !test_bit(NLP_REG_LOGIN_SEND, &ndlp->nlp_flag))
+			clear_bit(NLP_LOGO_ACC, &ndlp->nlp_flag);
 		elsiocb->cmd_cmpl = lpfc_cmpl_els_logo_acc;
 	} else {
 		elsiocb->cmd_cmpl = lpfc_cmpl_els_rsp;
@@ -5760,7 +5692,7 @@ lpfc_els_rsp_acc(struct lpfc_vport *vport, uint32_t flag,
 	/* Xmit ELS ACC response tag <ulpIoTag> */
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS,
 			 "0128 Xmit ELS ACC response Status: x%x, IoTag: x%x, "
-			 "XRI: x%x, DID: x%x, nlp_flag: x%x nlp_state: x%x "
+			 "XRI: x%x, DID: x%x, nlp_flag: x%lx nlp_state: x%x "
 			 "RPI: x%x, fc_flag x%lx refcnt %d\n",
 			 rc, elsiocb->iotag, elsiocb->sli4_xritag,
 			 ndlp->nlp_DID, ndlp->nlp_flag, ndlp->nlp_state,
@@ -5835,13 +5767,13 @@ lpfc_els_rsp_reject(struct lpfc_vport *vport, uint32_t rejectError,
 	/* Xmit ELS RJT <err> response tag <ulpIoTag> */
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS,
 			 "0129 Xmit ELS RJT x%x response tag x%x "
-			 "xri x%x, did x%x, nlp_flag x%x, nlp_state x%x, "
+			 "xri x%x, did x%x, nlp_flag x%lx, nlp_state x%x, "
 			 "rpi x%x\n",
 			 rejectError, elsiocb->iotag,
 			 get_job_ulpcontext(phba, elsiocb), ndlp->nlp_DID,
 			 ndlp->nlp_flag, ndlp->nlp_state, ndlp->nlp_rpi);
 	lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_RSP,
-		"Issue LS_RJT:    did:x%x flg:x%x err:x%x",
+		"Issue LS_RJT:    did:x%x flg:x%lx err:x%x",
 		ndlp->nlp_DID, ndlp->nlp_flag, rejectError);
 
 	phba->fc_stat.elsXmitLSRJT++;
@@ -5852,18 +5784,6 @@ lpfc_els_rsp_reject(struct lpfc_vport *vport, uint32_t rejectError,
 		return 1;
 	}
 
-	/* The NPIV instance is rejecting this unsolicited ELS. Make sure the
-	 * node's assigned RPI gets released provided this node is not already
-	 * registered with the transport.
-	 */
-	if (phba->sli_rev == LPFC_SLI_REV4 &&
-	    vport->port_type == LPFC_NPIV_PORT &&
-	    !(ndlp->fc4_xpt_flags & SCSI_XPT_REGD)) {
-		spin_lock_irq(&ndlp->lock);
-		ndlp->nlp_flag |= NLP_RELEASE_RPI;
-		spin_unlock_irq(&ndlp->lock);
-	}
-
 	rc = lpfc_sli_issue_iocb(phba, LPFC_ELS_RING, elsiocb, 0);
 	if (rc == IOCB_ERROR) {
 		lpfc_els_free_iocb(phba, elsiocb);
@@ -5944,7 +5864,7 @@ lpfc_issue_els_edc_rsp(struct lpfc_vport *vport, struct lpfc_iocbq *cmdiocb,
 		lpfc_format_edc_lft_desc(phba, tlv);
 
 	lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_RSP,
-			      "Issue EDC ACC:      did:x%x flg:x%x refcnt %d",
+			      "Issue EDC ACC:      did:x%x flg:x%lx refcnt %d",
 			      ndlp->nlp_DID, ndlp->nlp_flag,
 			      kref_read(&ndlp->kref));
 	elsiocb->cmd_cmpl = lpfc_cmpl_els_rsp;
@@ -5966,7 +5886,7 @@ lpfc_issue_els_edc_rsp(struct lpfc_vport *vport, struct lpfc_iocbq *cmdiocb,
 	/* Xmit ELS ACC response tag <ulpIoTag> */
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS,
 			 "0152 Xmit EDC ACC response Status: x%x, IoTag: x%x, "
-			 "XRI: x%x, DID: x%x, nlp_flag: x%x nlp_state: x%x "
+			 "XRI: x%x, DID: x%x, nlp_flag: x%lx nlp_state: x%x "
 			 "RPI: x%x, fc_flag x%lx\n",
 			 rc, elsiocb->iotag, elsiocb->sli4_xritag,
 			 ndlp->nlp_DID, ndlp->nlp_flag, ndlp->nlp_state,
@@ -6035,7 +5955,7 @@ lpfc_els_rsp_adisc_acc(struct lpfc_vport *vport, struct lpfc_iocbq *oldiocb,
 	/* Xmit ADISC ACC response tag <ulpIoTag> */
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS,
 			 "0130 Xmit ADISC ACC response iotag x%x xri: "
-			 "x%x, did x%x, nlp_flag x%x, nlp_state x%x rpi x%x\n",
+			 "x%x, did x%x, nlp_flag x%lx, nlp_state x%x rpi x%x\n",
 			 elsiocb->iotag, ulp_context,
 			 ndlp->nlp_DID, ndlp->nlp_flag, ndlp->nlp_state,
 			 ndlp->nlp_rpi);
@@ -6051,7 +5971,7 @@ lpfc_els_rsp_adisc_acc(struct lpfc_vport *vport, struct lpfc_iocbq *oldiocb,
 	ap->DID = be32_to_cpu(vport->fc_myDID);
 
 	lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_RSP,
-		      "Issue ACC ADISC: did:x%x flg:x%x refcnt %d",
+		      "Issue ACC ADISC: did:x%x flg:x%lx refcnt %d",
 		      ndlp->nlp_DID, ndlp->nlp_flag, kref_read(&ndlp->kref));
 
 	phba->fc_stat.elsXmitACC++;
@@ -6157,7 +6077,7 @@ lpfc_els_rsp_prli_acc(struct lpfc_vport *vport, struct lpfc_iocbq *oldiocb,
 	/* Xmit PRLI ACC response tag <ulpIoTag> */
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS,
 			 "0131 Xmit PRLI ACC response tag x%x xri x%x, "
-			 "did x%x, nlp_flag x%x, nlp_state x%x, rpi x%x\n",
+			 "did x%x, nlp_flag x%lx, nlp_state x%x, rpi x%x\n",
 			 elsiocb->iotag, ulp_context,
 			 ndlp->nlp_DID, ndlp->nlp_flag, ndlp->nlp_state,
 			 ndlp->nlp_rpi);
@@ -6228,7 +6148,7 @@ lpfc_els_rsp_prli_acc(struct lpfc_vport *vport, struct lpfc_iocbq *oldiocb,
 
 		lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME_DISC,
 				 "6015 NVME issue PRLI ACC word1 x%08x "
-				 "word4 x%08x word5 x%08x flag x%x, "
+				 "word4 x%08x word5 x%08x flag x%lx, "
 				 "fcp_info x%x nlp_type x%x\n",
 				 npr_nvme->word1, npr_nvme->word4,
 				 npr_nvme->word5, ndlp->nlp_flag,
@@ -6243,7 +6163,7 @@ lpfc_els_rsp_prli_acc(struct lpfc_vport *vport, struct lpfc_iocbq *oldiocb,
 				 ndlp->nlp_DID);
 
 	lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_RSP,
-		      "Issue ACC PRLI:  did:x%x flg:x%x",
+		      "Issue ACC PRLI:  did:x%x flg:x%lx",
 		      ndlp->nlp_DID, ndlp->nlp_flag, kref_read(&ndlp->kref));
 
 	phba->fc_stat.elsXmitACC++;
@@ -6357,7 +6277,7 @@ lpfc_els_rsp_rnid_acc(struct lpfc_vport *vport, uint8_t format,
 	}
 
 	lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_RSP,
-		      "Issue ACC RNID:  did:x%x flg:x%x refcnt %d",
+		      "Issue ACC RNID:  did:x%x flg:x%lx refcnt %d",
 		      ndlp->nlp_DID, ndlp->nlp_flag, kref_read(&ndlp->kref));
 
 	phba->fc_stat.elsXmitACC++;
@@ -6414,7 +6334,7 @@ lpfc_els_clear_rrq(struct lpfc_vport *vport,
 			get_job_ulpcontext(phba, iocb));
 
 	lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_RSP,
-		"Clear RRQ:  did:x%x flg:x%x exchg:x%.08x",
+		"Clear RRQ:  did:x%x flg:x%lx exchg:x%.08x",
 		ndlp->nlp_DID, ndlp->nlp_flag, rrq->rrq_exchg);
 	if (vport->fc_myDID == be32_to_cpu(bf_get(rrq_did, rrq)))
 		xri = bf_get(rrq_oxid, rrq);
@@ -6491,7 +6411,7 @@ lpfc_els_rsp_echo_acc(struct lpfc_vport *vport, uint8_t *data,
 	memcpy(pcmd, data, cmdsize - sizeof(uint32_t));
 
 	lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_RSP,
-		      "Issue ACC ECHO:  did:x%x flg:x%x refcnt %d",
+		      "Issue ACC ECHO:  did:x%x flg:x%lx refcnt %d",
 		      ndlp->nlp_DID, ndlp->nlp_flag, kref_read(&ndlp->kref));
 
 	phba->fc_stat.elsXmitACC++;
@@ -6541,14 +6461,12 @@ lpfc_els_disc_adisc(struct lpfc_vport *vport)
 	list_for_each_entry_safe(ndlp, next_ndlp, &vport->fc_nodes, nlp_listp) {
 
 		if (ndlp->nlp_state != NLP_STE_NPR_NODE ||
-		    !(ndlp->nlp_flag & NLP_NPR_ADISC))
+		    !test_bit(NLP_NPR_ADISC, &ndlp->nlp_flag))
 			continue;
 
-		spin_lock_irq(&ndlp->lock);
-		ndlp->nlp_flag &= ~NLP_NPR_ADISC;
-		spin_unlock_irq(&ndlp->lock);
+		clear_bit(NLP_NPR_ADISC, &ndlp->nlp_flag);
 
-		if (!(ndlp->nlp_flag & NLP_NPR_2B_DISC)) {
+		if (!test_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag)) {
 			/* This node was marked for ADISC but was not picked
 			 * for discovery. This is possible if the node was
 			 * missing in gidft response.
@@ -6606,9 +6524,9 @@ lpfc_els_disc_plogi(struct lpfc_vport *vport)
 	/* go thru NPR nodes and issue any remaining ELS PLOGIs */
 	list_for_each_entry_safe(ndlp, next_ndlp, &vport->fc_nodes, nlp_listp) {
 		if (ndlp->nlp_state == NLP_STE_NPR_NODE &&
-				(ndlp->nlp_flag & NLP_NPR_2B_DISC) != 0 &&
-				(ndlp->nlp_flag & NLP_DELAY_TMO) == 0 &&
-				(ndlp->nlp_flag & NLP_NPR_ADISC) == 0) {
+		    test_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag) &&
+		    !test_bit(NLP_DELAY_TMO, &ndlp->nlp_flag) &&
+		    !test_bit(NLP_NPR_ADISC, &ndlp->nlp_flag)) {
 			ndlp->nlp_prev_state = ndlp->nlp_state;
 			lpfc_nlp_set_state(vport, ndlp, NLP_STE_PLOGI_ISSUE);
 			lpfc_issue_els_plogi(vport, ndlp->nlp_DID, 0);
@@ -7104,7 +7022,7 @@ lpfc_els_rdp_cmpl(struct lpfc_hba *phba, struct lpfc_rdp_context *rdp_context,
 
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS,
 			"2171 Xmit RDP response tag x%x xri x%x, "
-			"did x%x, nlp_flag x%x, nlp_state x%x, rpi x%x",
+			"did x%x, nlp_flag x%lx, nlp_state x%x, rpi x%x",
 			elsiocb->iotag, ulp_context,
 			ndlp->nlp_DID, ndlp->nlp_flag, ndlp->nlp_state,
 			ndlp->nlp_rpi);
@@ -8078,7 +7996,7 @@ lpfc_els_rcv_rscn(struct lpfc_vport *vport, struct lpfc_iocbq *cmdiocb,
 	 */
 	if (vport->port_state <= LPFC_NS_QRY) {
 		lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_UNSOL,
-			"RCV RSCN ignore: did:x%x/ste:x%x flg:x%x",
+			"RCV RSCN ignore: did:x%x/ste:x%x flg:x%lx",
 			ndlp->nlp_DID, vport->port_state, ndlp->nlp_flag);
 
 		lpfc_els_rsp_acc(vport, ELS_CMD_ACC, cmdiocb, ndlp, NULL);
@@ -8108,7 +8026,7 @@ lpfc_els_rcv_rscn(struct lpfc_vport *vport, struct lpfc_iocbq *cmdiocb,
 					 vport->fc_flag, payload_len,
 					 *lp, vport->fc_rscn_id_cnt);
 			lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_UNSOL,
-				"RCV RSCN vport:  did:x%x/ste:x%x flg:x%x",
+				"RCV RSCN vport:  did:x%x/ste:x%x flg:x%lx",
 				ndlp->nlp_DID, vport->port_state,
 				ndlp->nlp_flag);
 
@@ -8145,7 +8063,7 @@ lpfc_els_rcv_rscn(struct lpfc_vport *vport, struct lpfc_iocbq *cmdiocb,
 	if (test_bit(FC_RSCN_MODE, &vport->fc_flag) ||
 	    test_bit(FC_NDISC_ACTIVE, &vport->fc_flag)) {
 		lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_UNSOL,
-			"RCV RSCN defer:  did:x%x/ste:x%x flg:x%x",
+			"RCV RSCN defer:  did:x%x/ste:x%x flg:x%lx",
 			ndlp->nlp_DID, vport->port_state, ndlp->nlp_flag);
 
 		set_bit(FC_RSCN_DEFERRED, &vport->fc_flag);
@@ -8201,7 +8119,7 @@ lpfc_els_rcv_rscn(struct lpfc_vport *vport, struct lpfc_iocbq *cmdiocb,
 		return 0;
 	}
 	lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_UNSOL,
-		"RCV RSCN:        did:x%x/ste:x%x flg:x%x",
+		"RCV RSCN:        did:x%x/ste:x%x flg:x%lx",
 		ndlp->nlp_DID, vport->port_state, ndlp->nlp_flag);
 
 	set_bit(FC_RSCN_MODE, &vport->fc_flag);
@@ -8707,7 +8625,7 @@ lpfc_els_rsp_rls_acc(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 	/* Xmit ELS RLS ACC response tag <ulpIoTag> */
 	lpfc_printf_vlog(ndlp->vport, KERN_INFO, LOG_ELS,
 			 "2874 Xmit ELS RLS ACC response tag x%x xri x%x, "
-			 "did x%x, nlp_flag x%x, nlp_state x%x, rpi x%x\n",
+			 "did x%x, nlp_flag x%lx, nlp_state x%x, rpi x%x\n",
 			 elsiocb->iotag, ulp_context,
 			 ndlp->nlp_DID, ndlp->nlp_flag, ndlp->nlp_state,
 			 ndlp->nlp_rpi);
@@ -8869,7 +8787,7 @@ lpfc_els_rcv_rtv(struct lpfc_vport *vport, struct lpfc_iocbq *cmdiocb,
 	/* Xmit ELS RLS ACC response tag <ulpIoTag> */
 	lpfc_printf_vlog(ndlp->vport, KERN_INFO, LOG_ELS,
 			 "2875 Xmit ELS RTV ACC response tag x%x xri x%x, "
-			 "did x%x, nlp_flag x%x, nlp_state x%x, rpi x%x, "
+			 "did x%x, nlp_flag x%lx, nlp_state x%x, rpi x%x, "
 			 "Data: x%x x%x x%x\n",
 			 elsiocb->iotag, ulp_context,
 			 ndlp->nlp_DID, ndlp->nlp_flag, ndlp->nlp_state,
@@ -9066,7 +8984,7 @@ lpfc_els_rsp_rpl_acc(struct lpfc_vport *vport, uint16_t cmdsize,
 	/* Xmit ELS RPL ACC response tag <ulpIoTag> */
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS,
 			 "0120 Xmit ELS RPL ACC response tag x%x "
-			 "xri x%x, did x%x, nlp_flag x%x, nlp_state x%x, "
+			 "xri x%x, did x%x, nlp_flag x%lx, nlp_state x%x, "
 			 "rpi x%x\n",
 			 elsiocb->iotag, ulp_context,
 			 ndlp->nlp_DID, ndlp->nlp_flag, ndlp->nlp_state,
@@ -10411,14 +10329,11 @@ lpfc_els_unsol_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 	 * Do not process any unsolicited ELS commands
 	 * if the ndlp is in DEV_LOSS
 	 */
-	spin_lock_irq(&ndlp->lock);
-	if (ndlp->nlp_flag & NLP_IN_DEV_LOSS) {
-		spin_unlock_irq(&ndlp->lock);
+	if (test_bit(NLP_IN_DEV_LOSS, &ndlp->nlp_flag)) {
 		if (newnode)
 			lpfc_nlp_put(ndlp);
 		goto dropit;
 	}
-	spin_unlock_irq(&ndlp->lock);
 
 	elsiocb->ndlp = lpfc_nlp_get(ndlp);
 	if (!elsiocb->ndlp)
@@ -10447,7 +10362,7 @@ lpfc_els_unsol_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 	switch (cmd) {
 	case ELS_CMD_PLOGI:
 		lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_UNSOL,
-			"RCV PLOGI:       did:x%x/ste:x%x flg:x%x",
+			"RCV PLOGI:       did:x%x/ste:x%x flg:x%lx",
 			did, vport->port_state, ndlp->nlp_flag);
 
 		phba->fc_stat.elsRcvPLOGI++;
@@ -10486,9 +10401,7 @@ lpfc_els_unsol_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 			}
 		}
 
-		spin_lock_irq(&ndlp->lock);
-		ndlp->nlp_flag &= ~NLP_TARGET_REMOVE;
-		spin_unlock_irq(&ndlp->lock);
+		clear_bit(NLP_TARGET_REMOVE, &ndlp->nlp_flag);
 
 		lpfc_disc_state_machine(vport, ndlp, elsiocb,
 					NLP_EVT_RCV_PLOGI);
@@ -10496,7 +10409,7 @@ lpfc_els_unsol_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 		break;
 	case ELS_CMD_FLOGI:
 		lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_UNSOL,
-			"RCV FLOGI:       did:x%x/ste:x%x flg:x%x",
+			"RCV FLOGI:       did:x%x/ste:x%x flg:x%lx",
 			did, vport->port_state, ndlp->nlp_flag);
 
 		phba->fc_stat.elsRcvFLOGI++;
@@ -10523,7 +10436,7 @@ lpfc_els_unsol_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 		break;
 	case ELS_CMD_LOGO:
 		lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_UNSOL,
-			"RCV LOGO:        did:x%x/ste:x%x flg:x%x",
+			"RCV LOGO:        did:x%x/ste:x%x flg:x%lx",
 			did, vport->port_state, ndlp->nlp_flag);
 
 		phba->fc_stat.elsRcvLOGO++;
@@ -10540,7 +10453,7 @@ lpfc_els_unsol_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 		break;
 	case ELS_CMD_PRLO:
 		lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_UNSOL,
-			"RCV PRLO:        did:x%x/ste:x%x flg:x%x",
+			"RCV PRLO:        did:x%x/ste:x%x flg:x%lx",
 			did, vport->port_state, ndlp->nlp_flag);
 
 		phba->fc_stat.elsRcvPRLO++;
@@ -10569,7 +10482,7 @@ lpfc_els_unsol_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 		break;
 	case ELS_CMD_ADISC:
 		lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_UNSOL,
-			"RCV ADISC:       did:x%x/ste:x%x flg:x%x",
+			"RCV ADISC:       did:x%x/ste:x%x flg:x%lx",
 			did, vport->port_state, ndlp->nlp_flag);
 
 		lpfc_send_els_event(vport, ndlp, payload);
@@ -10584,7 +10497,7 @@ lpfc_els_unsol_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 		break;
 	case ELS_CMD_PDISC:
 		lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_UNSOL,
-			"RCV PDISC:       did:x%x/ste:x%x flg:x%x",
+			"RCV PDISC:       did:x%x/ste:x%x flg:x%lx",
 			did, vport->port_state, ndlp->nlp_flag);
 
 		phba->fc_stat.elsRcvPDISC++;
@@ -10598,7 +10511,7 @@ lpfc_els_unsol_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 		break;
 	case ELS_CMD_FARPR:
 		lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_UNSOL,
-			"RCV FARPR:       did:x%x/ste:x%x flg:x%x",
+			"RCV FARPR:       did:x%x/ste:x%x flg:x%lx",
 			did, vport->port_state, ndlp->nlp_flag);
 
 		phba->fc_stat.elsRcvFARPR++;
@@ -10606,7 +10519,7 @@ lpfc_els_unsol_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 		break;
 	case ELS_CMD_FARP:
 		lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_UNSOL,
-			"RCV FARP:        did:x%x/ste:x%x flg:x%x",
+			"RCV FARP:        did:x%x/ste:x%x flg:x%lx",
 			did, vport->port_state, ndlp->nlp_flag);
 
 		phba->fc_stat.elsRcvFARP++;
@@ -10614,7 +10527,7 @@ lpfc_els_unsol_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 		break;
 	case ELS_CMD_FAN:
 		lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_UNSOL,
-			"RCV FAN:         did:x%x/ste:x%x flg:x%x",
+			"RCV FAN:         did:x%x/ste:x%x flg:x%lx",
 			did, vport->port_state, ndlp->nlp_flag);
 
 		phba->fc_stat.elsRcvFAN++;
@@ -10623,7 +10536,7 @@ lpfc_els_unsol_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 	case ELS_CMD_PRLI:
 	case ELS_CMD_NVMEPRLI:
 		lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_UNSOL,
-			"RCV PRLI:        did:x%x/ste:x%x flg:x%x",
+			"RCV PRLI:        did:x%x/ste:x%x flg:x%lx",
 			did, vport->port_state, ndlp->nlp_flag);
 
 		phba->fc_stat.elsRcvPRLI++;
@@ -10637,7 +10550,7 @@ lpfc_els_unsol_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 		break;
 	case ELS_CMD_LIRR:
 		lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_UNSOL,
-			"RCV LIRR:        did:x%x/ste:x%x flg:x%x",
+			"RCV LIRR:        did:x%x/ste:x%x flg:x%lx",
 			did, vport->port_state, ndlp->nlp_flag);
 
 		phba->fc_stat.elsRcvLIRR++;
@@ -10648,7 +10561,7 @@ lpfc_els_unsol_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 		break;
 	case ELS_CMD_RLS:
 		lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_UNSOL,
-			"RCV RLS:         did:x%x/ste:x%x flg:x%x",
+			"RCV RLS:         did:x%x/ste:x%x flg:x%lx",
 			did, vport->port_state, ndlp->nlp_flag);
 
 		phba->fc_stat.elsRcvRLS++;
@@ -10659,7 +10572,7 @@ lpfc_els_unsol_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 		break;
 	case ELS_CMD_RPL:
 		lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_UNSOL,
-			"RCV RPL:         did:x%x/ste:x%x flg:x%x",
+			"RCV RPL:         did:x%x/ste:x%x flg:x%lx",
 			did, vport->port_state, ndlp->nlp_flag);
 
 		phba->fc_stat.elsRcvRPL++;
@@ -10670,7 +10583,7 @@ lpfc_els_unsol_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 		break;
 	case ELS_CMD_RNID:
 		lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_UNSOL,
-			"RCV RNID:        did:x%x/ste:x%x flg:x%x",
+			"RCV RNID:        did:x%x/ste:x%x flg:x%lx",
 			did, vport->port_state, ndlp->nlp_flag);
 
 		phba->fc_stat.elsRcvRNID++;
@@ -10681,7 +10594,7 @@ lpfc_els_unsol_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 		break;
 	case ELS_CMD_RTV:
 		lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_UNSOL,
-			"RCV RTV:        did:x%x/ste:x%x flg:x%x",
+			"RCV RTV:        did:x%x/ste:x%x flg:x%lx",
 			did, vport->port_state, ndlp->nlp_flag);
 		phba->fc_stat.elsRcvRTV++;
 		lpfc_els_rcv_rtv(vport, elsiocb, ndlp);
@@ -10691,7 +10604,7 @@ lpfc_els_unsol_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 		break;
 	case ELS_CMD_RRQ:
 		lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_UNSOL,
-			"RCV RRQ:         did:x%x/ste:x%x flg:x%x",
+			"RCV RRQ:         did:x%x/ste:x%x flg:x%lx",
 			did, vport->port_state, ndlp->nlp_flag);
 
 		phba->fc_stat.elsRcvRRQ++;
@@ -10702,7 +10615,7 @@ lpfc_els_unsol_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 		break;
 	case ELS_CMD_ECHO:
 		lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_UNSOL,
-			"RCV ECHO:        did:x%x/ste:x%x flg:x%x",
+			"RCV ECHO:        did:x%x/ste:x%x flg:x%lx",
 			did, vport->port_state, ndlp->nlp_flag);
 
 		phba->fc_stat.elsRcvECHO++;
@@ -10718,7 +10631,8 @@ lpfc_els_unsol_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 		break;
 	case ELS_CMD_FPIN:
 		lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_UNSOL,
-				      "RCV FPIN:       did:x%x/ste:x%x flg:x%x",
+				      "RCV FPIN:       did:x%x/ste:x%x "
+				      "flg:x%lx",
 				      did, vport->port_state, ndlp->nlp_flag);
 
 		lpfc_els_rcv_fpin(vport, (struct fc_els_fpin *)payload,
@@ -11226,9 +11140,7 @@ lpfc_retry_pport_discovery(struct lpfc_hba *phba)
 		return;
 
 	mod_timer(&ndlp->nlp_delayfunc, jiffies + msecs_to_jiffies(1000));
-	spin_lock_irq(&ndlp->lock);
-	ndlp->nlp_flag |= NLP_DELAY_TMO;
-	spin_unlock_irq(&ndlp->lock);
+	set_bit(NLP_DELAY_TMO, &ndlp->nlp_flag);
 	ndlp->nlp_last_elscmd = ELS_CMD_FLOGI;
 	phba->pport->port_state = LPFC_FLOGI;
 	return;
@@ -11359,11 +11271,9 @@ lpfc_cmpl_els_fdisc(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 		list_for_each_entry_safe(np, next_np,
 			&vport->fc_nodes, nlp_listp) {
 			if ((np->nlp_state != NLP_STE_NPR_NODE) ||
-			    !(np->nlp_flag & NLP_NPR_ADISC))
+			    !test_bit(NLP_NPR_ADISC, &np->nlp_flag))
 				continue;
-			spin_lock_irq(&ndlp->lock);
-			np->nlp_flag &= ~NLP_NPR_ADISC;
-			spin_unlock_irq(&ndlp->lock);
+			clear_bit(NLP_NPR_ADISC, &np->nlp_flag);
 			lpfc_unreg_rpi(vport, np);
 		}
 		lpfc_cleanup_pending_mbox(vport);
@@ -11566,7 +11476,7 @@ lpfc_cmpl_els_npiv_logo(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 	/* NPIV LOGO completes to NPort <nlp_DID> */
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS,
 			 "2928 NPIV LOGO completes to NPort x%x "
-			 "Data: x%x x%x x%x x%x x%x x%x x%x\n",
+			 "Data: x%x x%x x%x x%x x%x x%lx x%x\n",
 			 ndlp->nlp_DID, ulp_status, ulp_word4,
 			 tmo, vport->num_disc_nodes,
 			 kref_read(&ndlp->kref), ndlp->nlp_flag,
@@ -11582,8 +11492,9 @@ lpfc_cmpl_els_npiv_logo(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 		/* Wake up lpfc_vport_delete if waiting...*/
 		if (ndlp->logo_waitq)
 			wake_up(ndlp->logo_waitq);
+		clear_bit(NLP_ISSUE_LOGO, &ndlp->nlp_flag);
+		clear_bit(NLP_LOGO_SND, &ndlp->nlp_flag);
 		spin_lock_irq(&ndlp->lock);
-		ndlp->nlp_flag &= ~(NLP_ISSUE_LOGO | NLP_LOGO_SND);
 		ndlp->save_flags &= ~NLP_WAIT_FOR_LOGO;
 		spin_unlock_irq(&ndlp->lock);
 	}
@@ -11633,13 +11544,11 @@ lpfc_issue_els_npiv_logo(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 	memcpy(pcmd, &vport->fc_portname, sizeof(struct lpfc_name));
 
 	lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_CMD,
-		"Issue LOGO npiv  did:x%x flg:x%x",
+		"Issue LOGO npiv  did:x%x flg:x%lx",
 		ndlp->nlp_DID, ndlp->nlp_flag, 0);
 
 	elsiocb->cmd_cmpl = lpfc_cmpl_els_npiv_logo;
-	spin_lock_irq(&ndlp->lock);
-	ndlp->nlp_flag |= NLP_LOGO_SND;
-	spin_unlock_irq(&ndlp->lock);
+	set_bit(NLP_LOGO_SND, &ndlp->nlp_flag);
 	elsiocb->ndlp = lpfc_nlp_get(ndlp);
 	if (!elsiocb->ndlp) {
 		lpfc_els_free_iocb(phba, elsiocb);
@@ -11655,9 +11564,7 @@ lpfc_issue_els_npiv_logo(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 	return 0;
 
 err:
-	spin_lock_irq(&ndlp->lock);
-	ndlp->nlp_flag &= ~NLP_LOGO_SND;
-	spin_unlock_irq(&ndlp->lock);
+	clear_bit(NLP_LOGO_SND, &ndlp->nlp_flag);
 	return 1;
 }
 
@@ -12138,7 +12045,7 @@ lpfc_sli_abts_recover_port(struct lpfc_vport *vport,
 	lpfc_printf_log(phba, KERN_ERR, LOG_TRACE_EVENT,
 			"3094 Start rport recovery on shost id 0x%x "
 			"fc_id 0x%06x vpi 0x%x rpi 0x%x state 0x%x "
-			"flags 0x%x\n",
+			"flag 0x%lx\n",
 			shost->host_no, ndlp->nlp_DID,
 			vport->vpi, ndlp->nlp_rpi, ndlp->nlp_state,
 			ndlp->nlp_flag);
@@ -12148,8 +12055,8 @@ lpfc_sli_abts_recover_port(struct lpfc_vport *vport,
 	 */
 	spin_lock_irqsave(&ndlp->lock, flags);
 	ndlp->nlp_fcp_info &= ~NLP_FCP_2_DEVICE;
-	ndlp->nlp_flag |= NLP_ISSUE_LOGO;
 	spin_unlock_irqrestore(&ndlp->lock, flags);
+	set_bit(NLP_ISSUE_LOGO, &ndlp->nlp_flag);
 	lpfc_unreg_rpi(vport, ndlp);
 }
 
diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c
index 6e8d8a96c54f..3ba515c1fe3a 100644
--- a/drivers/scsi/lpfc/lpfc_hbadisc.c
+++ b/drivers/scsi/lpfc/lpfc_hbadisc.c
@@ -137,7 +137,7 @@ lpfc_terminate_rport_io(struct fc_rport *rport)
 	ndlp = rdata->pnode;
 	vport = ndlp->vport;
 	lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_RPORT,
-			      "rport terminate: sid:x%x did:x%x flg:x%x",
+			      "rport terminate: sid:x%x did:x%x flg:x%lx",
 			      ndlp->nlp_sid, ndlp->nlp_DID, ndlp->nlp_flag);
 
 	if (ndlp->nlp_sid != NLP_NO_SID)
@@ -155,7 +155,7 @@ lpfc_dev_loss_tmo_callbk(struct fc_rport *rport)
 	struct lpfc_hba   *phba;
 	struct lpfc_work_evt *evtp;
 	unsigned long iflags;
-	bool nvme_reg = false;
+	bool drop_initial_node_ref = false;
 
 	ndlp = ((struct lpfc_rport_data *)rport->dd_data)->pnode;
 	if (!ndlp)
@@ -165,11 +165,11 @@ lpfc_dev_loss_tmo_callbk(struct fc_rport *rport)
 	phba  = vport->phba;
 
 	lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_RPORT,
-		"rport devlosscb: sid:x%x did:x%x flg:x%x",
+		"rport devlosscb: sid:x%x did:x%x flg:x%lx",
 		ndlp->nlp_sid, ndlp->nlp_DID, ndlp->nlp_flag);
 
 	lpfc_printf_vlog(ndlp->vport, KERN_INFO, LOG_NODE,
-			 "3181 dev_loss_callbk x%06x, rport x%px flg x%x "
+			 "3181 dev_loss_callbk x%06x, rport x%px flg x%lx "
 			 "load_flag x%lx refcnt %u state %d xpt x%x\n",
 			 ndlp->nlp_DID, ndlp->rport, ndlp->nlp_flag,
 			 vport->load_flag, kref_read(&ndlp->kref),
@@ -177,13 +177,19 @@ lpfc_dev_loss_tmo_callbk(struct fc_rport *rport)
 
 	/* Don't schedule a worker thread event if the vport is going down. */
 	if (test_bit(FC_UNLOADING, &vport->load_flag) ||
-	    !test_bit(HBA_SETUP, &phba->hba_flag)) {
+	    (phba->sli_rev == LPFC_SLI_REV4 &&
+	    !test_bit(HBA_SETUP, &phba->hba_flag))) {
 
 		spin_lock_irqsave(&ndlp->lock, iflags);
 		ndlp->rport = NULL;
 
-		if (ndlp->fc4_xpt_flags & NVME_XPT_REGD)
-			nvme_reg = true;
+		/* Only 1 thread can drop the initial node reference.
+		 * If not registered for NVME and NLP_DROPPED flag is
+		 * clear, remove the initial reference.
+		 */
+		if (!(ndlp->fc4_xpt_flags & NVME_XPT_REGD))
+			if (!test_and_set_bit(NLP_DROPPED, &ndlp->nlp_flag))
+				drop_initial_node_ref = true;
 
 		/* The scsi_transport is done with the rport so lpfc cannot
 		 * call to unregister.
@@ -194,13 +200,16 @@ lpfc_dev_loss_tmo_callbk(struct fc_rport *rport)
 			/* If NLP_XPT_REGD was cleared in lpfc_nlp_unreg_node,
 			 * unregister calls were made to the scsi and nvme
 			 * transports and refcnt was already decremented. Clear
-			 * the NLP_XPT_REGD flag only if the NVME Rport is
+			 * the NLP_XPT_REGD flag only if the NVME nrport is
 			 * confirmed unregistered.
 			 */
-			if (!nvme_reg && ndlp->fc4_xpt_flags & NLP_XPT_REGD) {
-				ndlp->fc4_xpt_flags &= ~NLP_XPT_REGD;
+			if (ndlp->fc4_xpt_flags & NLP_XPT_REGD) {
+				if (!(ndlp->fc4_xpt_flags & NVME_XPT_REGD))
+					ndlp->fc4_xpt_flags &= ~NLP_XPT_REGD;
 				spin_unlock_irqrestore(&ndlp->lock, iflags);
-				lpfc_nlp_put(ndlp); /* may free ndlp */
+
+				/* Release scsi transport reference */
+				lpfc_nlp_put(ndlp);
 			} else {
 				spin_unlock_irqrestore(&ndlp->lock, iflags);
 			}
@@ -208,29 +217,24 @@ lpfc_dev_loss_tmo_callbk(struct fc_rport *rport)
 			spin_unlock_irqrestore(&ndlp->lock, iflags);
 		}
 
-		spin_lock_irqsave(&ndlp->lock, iflags);
-
-		/* Only 1 thread can drop the initial node reference.  If
-		 * another thread has set NLP_DROPPED, this thread is done.
-		 */
-		if (nvme_reg || (ndlp->nlp_flag & NLP_DROPPED)) {
-			spin_unlock_irqrestore(&ndlp->lock, iflags);
-			return;
-		}
-
-		ndlp->nlp_flag |= NLP_DROPPED;
-		spin_unlock_irqrestore(&ndlp->lock, iflags);
-		lpfc_nlp_put(ndlp);
+		if (drop_initial_node_ref)
+			lpfc_nlp_put(ndlp);
 		return;
 	}
 
 	if (ndlp->nlp_state == NLP_STE_MAPPED_NODE)
 		return;
 
-	/* check for recovered fabric node */
-	if (ndlp->nlp_state == NLP_STE_UNMAPPED_NODE &&
-	    ndlp->nlp_DID == Fabric_DID)
+	/* Ignore callback for a mismatched (stale) rport */
+	if (ndlp->rport != rport) {
+		lpfc_vlog_msg(vport, KERN_WARNING, LOG_NODE,
+			      "6788 fc rport mismatch: d_id x%06x ndlp x%px "
+			      "fc rport x%px node rport x%px state x%x "
+			      "refcnt %u\n",
+			      ndlp->nlp_DID, ndlp, rport, ndlp->rport,
+			      ndlp->nlp_state, kref_read(&ndlp->kref));
 		return;
+	}
 
 	if (rport->port_name != wwn_to_u64(ndlp->nlp_portname.u.wwn))
 		lpfc_printf_vlog(vport, KERN_ERR, LOG_TRACE_EVENT,
@@ -247,14 +251,14 @@ lpfc_dev_loss_tmo_callbk(struct fc_rport *rport)
 		return;
 	}
 
-	spin_lock_irqsave(&ndlp->lock, iflags);
-	ndlp->nlp_flag |= NLP_IN_DEV_LOSS;
+	set_bit(NLP_IN_DEV_LOSS, &ndlp->nlp_flag);
 
+	spin_lock_irqsave(&ndlp->lock, iflags);
 	/* If there is a PLOGI in progress, and we are in a
 	 * NLP_NPR_2B_DISC state, don't turn off the flag.
 	 */
 	if (ndlp->nlp_state != NLP_STE_PLOGI_ISSUE)
-		ndlp->nlp_flag &= ~NLP_NPR_2B_DISC;
+		clear_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag);
 
 	/*
 	 * The backend does not expect any more calls associated with this
@@ -283,15 +287,13 @@ lpfc_dev_loss_tmo_callbk(struct fc_rport *rport)
 	} else {
 		lpfc_printf_vlog(ndlp->vport, KERN_INFO, LOG_NODE,
 				 "3188 worker thread is stopped %s x%06x, "
-				 " rport x%px flg x%x load_flag x%lx refcnt "
+				 " rport x%px flg x%lx load_flag x%lx refcnt "
 				 "%d\n", __func__, ndlp->nlp_DID,
 				 ndlp->rport, ndlp->nlp_flag,
 				 vport->load_flag, kref_read(&ndlp->kref));
 		if (!(ndlp->fc4_xpt_flags & NVME_XPT_REGD)) {
-			spin_lock_irqsave(&ndlp->lock, iflags);
 			/* Node is in dev loss.  No further transaction. */
-			ndlp->nlp_flag &= ~NLP_IN_DEV_LOSS;
-			spin_unlock_irqrestore(&ndlp->lock, iflags);
+			clear_bit(NLP_IN_DEV_LOSS, &ndlp->nlp_flag);
 			lpfc_disc_state_machine(vport, ndlp, NULL,
 						NLP_EVT_DEVICE_RM);
 		}
@@ -424,7 +426,7 @@ lpfc_check_nlp_post_devloss(struct lpfc_vport *vport,
 		lpfc_nlp_get(ndlp);
 		lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY | LOG_NODE,
 				 "8438 Devloss timeout reversed on DID x%x "
-				 "refcnt %d ndlp %p flag x%x "
+				 "refcnt %d ndlp %p flag x%lx "
 				 "port_state = x%x\n",
 				 ndlp->nlp_DID, kref_read(&ndlp->kref), ndlp,
 				 ndlp->nlp_flag, vport->port_state);
@@ -467,7 +469,7 @@ lpfc_dev_loss_tmo_handler(struct lpfc_nodelist *ndlp)
 			      ndlp->nlp_DID, ndlp->nlp_type, ndlp->nlp_sid);
 
 	lpfc_printf_vlog(ndlp->vport, KERN_INFO, LOG_NODE,
-			 "3182 %s x%06x, nflag x%x xflags x%x refcnt %d\n",
+			 "3182 %s x%06x, nflag x%lx xflags x%x refcnt %d\n",
 			 __func__, ndlp->nlp_DID, ndlp->nlp_flag,
 			 ndlp->fc4_xpt_flags, kref_read(&ndlp->kref));
 
@@ -481,9 +483,7 @@ lpfc_dev_loss_tmo_handler(struct lpfc_nodelist *ndlp)
 				 *(name+4), *(name+5), *(name+6), *(name+7),
 				 ndlp->nlp_DID);
 
-		spin_lock_irqsave(&ndlp->lock, iflags);
-		ndlp->nlp_flag &= ~NLP_IN_DEV_LOSS;
-		spin_unlock_irqrestore(&ndlp->lock, iflags);
+		clear_bit(NLP_IN_DEV_LOSS, &ndlp->nlp_flag);
 		return fcf_inuse;
 	}
 
@@ -511,7 +511,7 @@ lpfc_dev_loss_tmo_handler(struct lpfc_nodelist *ndlp)
 			}
 			break;
 		case Fabric_Cntl_DID:
-			if (ndlp->nlp_flag & NLP_REG_LOGIN_SEND)
+			if (test_bit(NLP_REG_LOGIN_SEND, &ndlp->nlp_flag))
 				recovering = true;
 			break;
 		case FDMI_DID:
@@ -539,15 +539,13 @@ lpfc_dev_loss_tmo_handler(struct lpfc_nodelist *ndlp)
 		 * the following lpfc_nlp_put is necessary after fabric node is
 		 * recovered.
 		 */
-		spin_lock_irqsave(&ndlp->lock, iflags);
-		ndlp->nlp_flag &= ~NLP_IN_DEV_LOSS;
-		spin_unlock_irqrestore(&ndlp->lock, iflags);
+		clear_bit(NLP_IN_DEV_LOSS, &ndlp->nlp_flag);
 		if (recovering) {
 			lpfc_printf_vlog(vport, KERN_INFO,
 					 LOG_DISCOVERY | LOG_NODE,
 					 "8436 Devloss timeout marked on "
 					 "DID x%x refcnt %d ndlp %p "
-					 "flag x%x port_state = x%x\n",
+					 "flag x%lx port_state = x%x\n",
 					 ndlp->nlp_DID, kref_read(&ndlp->kref),
 					 ndlp, ndlp->nlp_flag,
 					 vport->port_state);
@@ -564,7 +562,7 @@ lpfc_dev_loss_tmo_handler(struct lpfc_nodelist *ndlp)
 					 LOG_DISCOVERY | LOG_NODE,
 					 "8437 Devloss timeout ignored on "
 					 "DID x%x refcnt %d ndlp %p "
-					 "flag x%x port_state = x%x\n",
+					 "flag x%lx port_state = x%x\n",
 					 ndlp->nlp_DID, kref_read(&ndlp->kref),
 					 ndlp, ndlp->nlp_flag,
 					 vport->port_state);
@@ -584,7 +582,7 @@ lpfc_dev_loss_tmo_handler(struct lpfc_nodelist *ndlp)
 		lpfc_printf_vlog(vport, KERN_ERR, LOG_TRACE_EVENT,
 				 "0203 Devloss timeout on "
 				 "WWPN %02x:%02x:%02x:%02x:%02x:%02x:%02x:%02x "
-				 "NPort x%06x Data: x%x x%x x%x refcnt %d\n",
+				 "NPort x%06x Data: x%lx x%x x%x refcnt %d\n",
 				 *name, *(name+1), *(name+2), *(name+3),
 				 *(name+4), *(name+5), *(name+6), *(name+7),
 				 ndlp->nlp_DID, ndlp->nlp_flag,
@@ -594,15 +592,13 @@ lpfc_dev_loss_tmo_handler(struct lpfc_nodelist *ndlp)
 		lpfc_printf_vlog(vport, KERN_INFO, LOG_TRACE_EVENT,
 				 "0204 Devloss timeout on "
 				 "WWPN %02x:%02x:%02x:%02x:%02x:%02x:%02x:%02x "
-				 "NPort x%06x Data: x%x x%x x%x\n",
+				 "NPort x%06x Data: x%lx x%x x%x\n",
 				 *name, *(name+1), *(name+2), *(name+3),
 				 *(name+4), *(name+5), *(name+6), *(name+7),
 				 ndlp->nlp_DID, ndlp->nlp_flag,
 				 ndlp->nlp_state, ndlp->nlp_rpi);
 	}
-	spin_lock_irqsave(&ndlp->lock, iflags);
-	ndlp->nlp_flag &= ~NLP_IN_DEV_LOSS;
-	spin_unlock_irqrestore(&ndlp->lock, iflags);
+	clear_bit(NLP_IN_DEV_LOSS, &ndlp->nlp_flag);
 
 	/* If we are devloss, but we are in the process of rediscovering the
 	 * ndlp, don't issue a NLP_EVT_DEVICE_RM event.
@@ -1367,7 +1363,7 @@ lpfc_linkup_cleanup_nodes(struct lpfc_vport *vport)
 			if (ndlp->nlp_DID != Fabric_DID)
 				lpfc_unreg_rpi(vport, ndlp);
 			lpfc_nlp_set_state(vport, ndlp, NLP_STE_NPR_NODE);
-		} else if (!(ndlp->nlp_flag & NLP_NPR_ADISC)) {
+		} else if (!test_bit(NLP_NPR_ADISC, &ndlp->nlp_flag)) {
 			/* Fail outstanding IO now since device is
 			 * marked for PLOGI.
 			 */
@@ -3876,14 +3872,13 @@ lpfc_mbx_cmpl_reg_login(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 	pmb->ctx_ndlp = NULL;
 
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_SLI | LOG_NODE | LOG_DISCOVERY,
-			 "0002 rpi:%x DID:%x flg:%x %d x%px\n",
+			 "0002 rpi:%x DID:%x flg:%lx %d x%px\n",
 			 ndlp->nlp_rpi, ndlp->nlp_DID, ndlp->nlp_flag,
 			 kref_read(&ndlp->kref),
 			 ndlp);
-	if (ndlp->nlp_flag & NLP_REG_LOGIN_SEND)
-		ndlp->nlp_flag &= ~NLP_REG_LOGIN_SEND;
+	clear_bit(NLP_REG_LOGIN_SEND, &ndlp->nlp_flag);
 
-	if (ndlp->nlp_flag & NLP_IGNR_REG_CMPL ||
+	if (test_bit(NLP_IGNR_REG_CMPL, &ndlp->nlp_flag) ||
 	    ndlp->nlp_state != NLP_STE_REG_LOGIN_ISSUE) {
 		/* We rcvd a rscn after issuing this
 		 * mbox reg login, we may have cycled
@@ -3893,16 +3888,14 @@ lpfc_mbx_cmpl_reg_login(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 		 * there is another reg login in
 		 * process.
 		 */
-		spin_lock_irq(&ndlp->lock);
-		ndlp->nlp_flag &= ~NLP_IGNR_REG_CMPL;
-		spin_unlock_irq(&ndlp->lock);
+		clear_bit(NLP_IGNR_REG_CMPL, &ndlp->nlp_flag);
 
 		/*
 		 * We cannot leave the RPI registered because
 		 * if we go thru discovery again for this ndlp
 		 * a subsequent REG_RPI will fail.
 		 */
-		ndlp->nlp_flag |= NLP_RPI_REGISTERED;
+		set_bit(NLP_RPI_REGISTERED, &ndlp->nlp_flag);
 		lpfc_unreg_rpi(vport, ndlp);
 	}
 
@@ -4215,7 +4208,7 @@ lpfc_mbx_cmpl_fabric_reg_login(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 
 	if (phba->sli_rev < LPFC_SLI_REV4)
 		ndlp->nlp_rpi = mb->un.varWords[0];
-	ndlp->nlp_flag |= NLP_RPI_REGISTERED;
+	set_bit(NLP_RPI_REGISTERED, &ndlp->nlp_flag);
 	ndlp->nlp_type |= NLP_FABRIC;
 	lpfc_nlp_set_state(vport, ndlp, NLP_STE_UNMAPPED_NODE);
 
@@ -4346,9 +4339,7 @@ out:
 		 * reference.
 		 */
 		if (!(ndlp->fc4_xpt_flags & (SCSI_XPT_REGD | NVME_XPT_REGD))) {
-			spin_lock_irq(&ndlp->lock);
-			ndlp->nlp_flag &= ~NLP_NPR_2B_DISC;
-			spin_unlock_irq(&ndlp->lock);
+			clear_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag);
 			lpfc_nlp_put(ndlp);
 		}
 
@@ -4369,11 +4360,11 @@ out:
 
 	if (phba->sli_rev < LPFC_SLI_REV4)
 		ndlp->nlp_rpi = mb->un.varWords[0];
-	ndlp->nlp_flag |= NLP_RPI_REGISTERED;
+	set_bit(NLP_RPI_REGISTERED, &ndlp->nlp_flag);
 	ndlp->nlp_type |= NLP_FABRIC;
 	lpfc_nlp_set_state(vport, ndlp, NLP_STE_UNMAPPED_NODE);
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_NODE | LOG_DISCOVERY,
-			 "0003 rpi:%x DID:%x flg:%x %d x%px\n",
+			 "0003 rpi:%x DID:%x flg:%lx %d x%px\n",
 			 ndlp->nlp_rpi, ndlp->nlp_DID, ndlp->nlp_flag,
 			 kref_read(&ndlp->kref),
 			 ndlp);
@@ -4465,8 +4456,8 @@ lpfc_mbx_cmpl_fc_reg_login(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 			 __func__, ndlp->nlp_DID, ndlp->nlp_rpi,
 			 ndlp->nlp_state);
 
-	ndlp->nlp_flag |= NLP_RPI_REGISTERED;
-	ndlp->nlp_flag &= ~NLP_REG_LOGIN_SEND;
+	set_bit(NLP_RPI_REGISTERED, &ndlp->nlp_flag);
+	clear_bit(NLP_REG_LOGIN_SEND, &ndlp->nlp_flag);
 	ndlp->nlp_type |= NLP_FABRIC;
 	lpfc_nlp_set_state(vport, ndlp, NLP_STE_UNMAPPED_NODE);
 
@@ -4500,7 +4491,7 @@ lpfc_register_remote_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 
 
 	lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_RPORT,
-			      "rport add:       did:x%x flg:x%x type x%x",
+			      "rport add:       did:x%x flg:x%lx type x%x",
 			      ndlp->nlp_DID, ndlp->nlp_flag, ndlp->nlp_type);
 
 	/* Don't add the remote port if unloading. */
@@ -4568,7 +4559,7 @@ lpfc_unregister_remote_port(struct lpfc_nodelist *ndlp)
 		return;
 
 	lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_RPORT,
-		"rport delete:    did:x%x flg:x%x type x%x",
+		"rport delete:    did:x%x flg:x%lx type x%x",
 		ndlp->nlp_DID, ndlp->nlp_flag, ndlp->nlp_type);
 
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_NODE,
@@ -4684,7 +4675,7 @@ lpfc_nlp_unreg_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 		lpfc_printf_vlog(vport, KERN_INFO,
 				 LOG_ELS | LOG_NODE | LOG_DISCOVERY,
 				 "0999 %s Not regd: ndlp x%px rport x%px DID "
-				 "x%x FLG x%x XPT x%x\n",
+				 "x%x FLG x%lx XPT x%x\n",
 				  __func__, ndlp, ndlp->rport, ndlp->nlp_DID,
 				  ndlp->nlp_flag, ndlp->fc4_xpt_flags);
 		return;
@@ -4700,7 +4691,7 @@ lpfc_nlp_unreg_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 	} else if (!ndlp->rport) {
 		lpfc_printf_vlog(vport, KERN_INFO,
 				 LOG_ELS | LOG_NODE | LOG_DISCOVERY,
-				 "1999 %s NDLP in devloss x%px DID x%x FLG x%x"
+				 "1999 %s NDLP in devloss x%px DID x%x FLG x%lx"
 				 " XPT x%x refcnt %u\n",
 				 __func__, ndlp, ndlp->nlp_DID, ndlp->nlp_flag,
 				 ndlp->fc4_xpt_flags,
@@ -4745,7 +4736,7 @@ lpfc_handle_adisc_state(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 		ndlp->nlp_type |= NLP_FC_NODE;
 		fallthrough;
 	case NLP_STE_MAPPED_NODE:
-		ndlp->nlp_flag &= ~NLP_NODEV_REMOVE;
+		clear_bit(NLP_NODEV_REMOVE, &ndlp->nlp_flag);
 		lpfc_nlp_reg_node(vport, ndlp);
 		break;
 
@@ -4756,7 +4747,7 @@ lpfc_handle_adisc_state(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	 * backend, attempt it now
 	 */
 	case NLP_STE_NPR_NODE:
-		ndlp->nlp_flag &= ~NLP_RCV_PLOGI;
+		clear_bit(NLP_RCV_PLOGI, &ndlp->nlp_flag);
 		fallthrough;
 	default:
 		lpfc_nlp_unreg_node(vport, ndlp);
@@ -4777,13 +4768,13 @@ lpfc_nlp_state_cleanup(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	}
 
 	if (new_state == NLP_STE_UNMAPPED_NODE) {
-		ndlp->nlp_flag &= ~NLP_NODEV_REMOVE;
+		clear_bit(NLP_NODEV_REMOVE, &ndlp->nlp_flag);
 		ndlp->nlp_type |= NLP_FC_NODE;
 	}
 	if (new_state == NLP_STE_MAPPED_NODE)
-		ndlp->nlp_flag &= ~NLP_NODEV_REMOVE;
+		clear_bit(NLP_NODEV_REMOVE, &ndlp->nlp_flag);
 	if (new_state == NLP_STE_NPR_NODE)
-		ndlp->nlp_flag &= ~NLP_RCV_PLOGI;
+		clear_bit(NLP_RCV_PLOGI, &ndlp->nlp_flag);
 
 	/* Reg/Unreg for FCP and NVME Transport interface */
 	if ((old_state == NLP_STE_MAPPED_NODE ||
@@ -4791,7 +4782,7 @@ lpfc_nlp_state_cleanup(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 		/* For nodes marked for ADISC, Handle unreg in ADISC cmpl
 		 * if linkup. In linkdown do unreg_node
 		 */
-		if (!(ndlp->nlp_flag & NLP_NPR_ADISC) ||
+		if (!test_bit(NLP_NPR_ADISC, &ndlp->nlp_flag) ||
 		    !lpfc_is_link_up(vport->phba))
 			lpfc_nlp_unreg_node(vport, ndlp);
 	}
@@ -4811,9 +4802,7 @@ lpfc_nlp_state_cleanup(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	    (!ndlp->rport ||
 	     ndlp->rport->scsi_target_id == -1 ||
 	     ndlp->rport->scsi_target_id >= LPFC_MAX_TARGET)) {
-		spin_lock_irq(&ndlp->lock);
-		ndlp->nlp_flag |= NLP_TGT_NO_SCSIID;
-		spin_unlock_irq(&ndlp->lock);
+		set_bit(NLP_TGT_NO_SCSIID, &ndlp->nlp_flag);
 		lpfc_nlp_set_state(vport, ndlp, NLP_STE_UNMAPPED_NODE);
 	}
 }
@@ -4845,7 +4834,7 @@ lpfc_nlp_set_state(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 		   int state)
 {
 	int  old_state = ndlp->nlp_state;
-	int node_dropped = ndlp->nlp_flag & NLP_DROPPED;
+	bool node_dropped = test_bit(NLP_DROPPED, &ndlp->nlp_flag);
 	char name1[16], name2[16];
 	unsigned long iflags;
 
@@ -4861,7 +4850,7 @@ lpfc_nlp_set_state(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 
 	if (node_dropped && old_state == NLP_STE_UNUSED_NODE &&
 	    state != NLP_STE_UNUSED_NODE) {
-		ndlp->nlp_flag &= ~NLP_DROPPED;
+		clear_bit(NLP_DROPPED, &ndlp->nlp_flag);
 		lpfc_nlp_get(ndlp);
 	}
 
@@ -4869,7 +4858,7 @@ lpfc_nlp_set_state(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	    state != NLP_STE_NPR_NODE)
 		lpfc_cancel_retry_delay_tmo(vport, ndlp);
 	if (old_state == NLP_STE_UNMAPPED_NODE) {
-		ndlp->nlp_flag &= ~NLP_TGT_NO_SCSIID;
+		clear_bit(NLP_TGT_NO_SCSIID, &ndlp->nlp_flag);
 		ndlp->nlp_type &= ~NLP_FC_NODE;
 	}
 
@@ -4966,14 +4955,8 @@ lpfc_drop_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 	 * reference from lpfc_nlp_init.  If set, don't drop it again and
 	 * introduce an imbalance.
 	 */
-	spin_lock_irq(&ndlp->lock);
-	if (!(ndlp->nlp_flag & NLP_DROPPED)) {
-		ndlp->nlp_flag |= NLP_DROPPED;
-		spin_unlock_irq(&ndlp->lock);
+	if (!test_and_set_bit(NLP_DROPPED, &ndlp->nlp_flag))
 		lpfc_nlp_put(ndlp);
-		return;
-	}
-	spin_unlock_irq(&ndlp->lock);
 }
 
 /*
@@ -5076,7 +5059,7 @@ lpfc_check_sli_ndlp(struct lpfc_hba *phba,
 		case CMD_GEN_REQUEST64_CR:
 			if (iocb->ndlp == ndlp)
 				return 1;
-			fallthrough;
+			break;
 		case CMD_ELS_REQUEST64_CR:
 			if (remote_id == ndlp->nlp_DID)
 				return 1;
@@ -5088,9 +5071,9 @@ lpfc_check_sli_ndlp(struct lpfc_hba *phba,
 	} else if (pring->ringno == LPFC_FCP_RING) {
 		/* Skip match check if waiting to relogin to FCP target */
 		if ((ndlp->nlp_type & NLP_FCP_TARGET) &&
-		    (ndlp->nlp_flag & NLP_DELAY_TMO)) {
+		    test_bit(NLP_DELAY_TMO, &ndlp->nlp_flag))
 			return 0;
-		}
+
 		if (ulp_context == ndlp->nlp_rpi)
 			return 1;
 	}
@@ -5160,7 +5143,7 @@ lpfc_no_rpi(struct lpfc_hba *phba, struct lpfc_nodelist *ndlp)
 	 * Everything that matches on txcmplq will be returned
 	 * by firmware with a no rpi error.
 	 */
-	if (ndlp->nlp_flag & NLP_RPI_REGISTERED) {
+	if (test_bit(NLP_RPI_REGISTERED, &ndlp->nlp_flag)) {
 		if (phba->sli_rev != LPFC_SLI_REV4)
 			lpfc_sli3_dequeue_nport_iocbs(phba, ndlp, &completions);
 		else
@@ -5194,29 +5177,19 @@ lpfc_nlp_logo_unreg(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 	lpfc_issue_els_logo(vport, ndlp, 0);
 
 	/* Check to see if there are any deferred events to process */
-	if ((ndlp->nlp_flag & NLP_UNREG_INP) &&
-	    (ndlp->nlp_defer_did != NLP_EVT_NOTHING_PENDING)) {
+	if (test_bit(NLP_UNREG_INP, &ndlp->nlp_flag) &&
+	    ndlp->nlp_defer_did != NLP_EVT_NOTHING_PENDING) {
 		lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY,
 				 "1434 UNREG cmpl deferred logo x%x "
 				 "on NPort x%x Data: x%x x%px\n",
 				 ndlp->nlp_rpi, ndlp->nlp_DID,
 				 ndlp->nlp_defer_did, ndlp);
 
-		ndlp->nlp_flag &= ~NLP_UNREG_INP;
+		clear_bit(NLP_UNREG_INP, &ndlp->nlp_flag);
 		ndlp->nlp_defer_did = NLP_EVT_NOTHING_PENDING;
 		lpfc_issue_els_plogi(vport, ndlp->nlp_DID, 0);
 	} else {
-		/* NLP_RELEASE_RPI is only set for SLI4 ports. */
-		if (ndlp->nlp_flag & NLP_RELEASE_RPI) {
-			lpfc_sli4_free_rpi(vport->phba, ndlp->nlp_rpi);
-			spin_lock_irq(&ndlp->lock);
-			ndlp->nlp_flag &= ~NLP_RELEASE_RPI;
-			ndlp->nlp_rpi = LPFC_RPI_ALLOC_ERROR;
-			spin_unlock_irq(&ndlp->lock);
-		}
-		spin_lock_irq(&ndlp->lock);
-		ndlp->nlp_flag &= ~NLP_UNREG_INP;
-		spin_unlock_irq(&ndlp->lock);
+		clear_bit(NLP_UNREG_INP, &ndlp->nlp_flag);
 	}
 
 	/* The node has an outstanding reference for the unreg. Now
@@ -5236,8 +5209,6 @@ static void
 lpfc_set_unreg_login_mbx_cmpl(struct lpfc_hba *phba, struct lpfc_vport *vport,
 	struct lpfc_nodelist *ndlp, LPFC_MBOXQ_t *mbox)
 {
-	unsigned long iflags;
-
 	/* Driver always gets a reference on the mailbox job
 	 * in support of async jobs.
 	 */
@@ -5245,9 +5216,8 @@ lpfc_set_unreg_login_mbx_cmpl(struct lpfc_hba *phba, struct lpfc_vport *vport,
 	if (!mbox->ctx_ndlp)
 		return;
 
-	if (ndlp->nlp_flag & NLP_ISSUE_LOGO) {
+	if (test_bit(NLP_ISSUE_LOGO, &ndlp->nlp_flag)) {
 		mbox->mbox_cmpl = lpfc_nlp_logo_unreg;
-
 	} else if (phba->sli_rev == LPFC_SLI_REV4 &&
 		   !test_bit(FC_UNLOADING, &vport->load_flag) &&
 		    (bf_get(lpfc_sli_intf_if_type, &phba->sli4_hba.sli_intf) >=
@@ -5255,13 +5225,6 @@ lpfc_set_unreg_login_mbx_cmpl(struct lpfc_hba *phba, struct lpfc_vport *vport,
 		    (kref_read(&ndlp->kref) > 0)) {
 		mbox->mbox_cmpl = lpfc_sli4_unreg_rpi_cmpl_clr;
 	} else {
-		if (test_bit(FC_UNLOADING, &vport->load_flag)) {
-			if (phba->sli_rev == LPFC_SLI_REV4) {
-				spin_lock_irqsave(&ndlp->lock, iflags);
-				ndlp->nlp_flag |= NLP_RELEASE_RPI;
-				spin_unlock_irqrestore(&ndlp->lock, iflags);
-			}
-		}
 		mbox->mbox_cmpl = lpfc_sli_def_mbox_cmpl;
 	}
 }
@@ -5283,13 +5246,13 @@ lpfc_unreg_rpi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 	int rc, acc_plogi = 1;
 	uint16_t rpi;
 
-	if (ndlp->nlp_flag & NLP_RPI_REGISTERED ||
-	    ndlp->nlp_flag & NLP_REG_LOGIN_SEND) {
-		if (ndlp->nlp_flag & NLP_REG_LOGIN_SEND)
+	if (test_bit(NLP_RPI_REGISTERED, &ndlp->nlp_flag) ||
+	    test_bit(NLP_REG_LOGIN_SEND, &ndlp->nlp_flag)) {
+		if (test_bit(NLP_REG_LOGIN_SEND, &ndlp->nlp_flag))
 			lpfc_printf_vlog(vport, KERN_INFO,
 					 LOG_NODE | LOG_DISCOVERY,
 					 "3366 RPI x%x needs to be "
-					 "unregistered nlp_flag x%x "
+					 "unregistered nlp_flag x%lx "
 					 "did x%x\n",
 					 ndlp->nlp_rpi, ndlp->nlp_flag,
 					 ndlp->nlp_DID);
@@ -5297,11 +5260,11 @@ lpfc_unreg_rpi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 		/* If there is already an UNREG in progress for this ndlp,
 		 * no need to queue up another one.
 		 */
-		if (ndlp->nlp_flag & NLP_UNREG_INP) {
+		if (test_bit(NLP_UNREG_INP, &ndlp->nlp_flag)) {
 			lpfc_printf_vlog(vport, KERN_INFO,
 					 LOG_NODE | LOG_DISCOVERY,
 					 "1436 unreg_rpi SKIP UNREG x%x on "
-					 "NPort x%x deferred x%x  flg x%x "
+					 "NPort x%x deferred x%x flg x%lx "
 					 "Data: x%px\n",
 					 ndlp->nlp_rpi, ndlp->nlp_DID,
 					 ndlp->nlp_defer_did,
@@ -5324,27 +5287,24 @@ lpfc_unreg_rpi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 				return 1;
 			}
 
+			/* Accept PLOGIs after unreg_rpi_cmpl. */
 			if (mbox->mbox_cmpl == lpfc_sli4_unreg_rpi_cmpl_clr)
-				/*
-				 * accept PLOGIs after unreg_rpi_cmpl
-				 */
 				acc_plogi = 0;
-			if (((ndlp->nlp_DID & Fabric_DID_MASK) !=
-			    Fabric_DID_MASK) &&
-			    (!test_bit(FC_OFFLINE_MODE, &vport->fc_flag)))
-				ndlp->nlp_flag |= NLP_UNREG_INP;
+
+			if (!test_bit(FC_OFFLINE_MODE, &vport->fc_flag))
+				set_bit(NLP_UNREG_INP, &ndlp->nlp_flag);
 
 			lpfc_printf_vlog(vport, KERN_INFO,
 					 LOG_NODE | LOG_DISCOVERY,
 					 "1433 unreg_rpi UNREG x%x on "
-					 "NPort x%x deferred flg x%x "
+					 "NPort x%x deferred flg x%lx "
 					 "Data:x%px\n",
 					 ndlp->nlp_rpi, ndlp->nlp_DID,
 					 ndlp->nlp_flag, ndlp);
 
 			rc = lpfc_sli_issue_mbox(phba, mbox, MBX_NOWAIT);
 			if (rc == MBX_NOT_FINISHED) {
-				ndlp->nlp_flag &= ~NLP_UNREG_INP;
+				clear_bit(NLP_UNREG_INP, &ndlp->nlp_flag);
 				mempool_free(mbox, phba->mbox_mem_pool);
 				acc_plogi = 1;
 				lpfc_nlp_put(ndlp);
@@ -5354,7 +5314,7 @@ lpfc_unreg_rpi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 					 LOG_NODE | LOG_DISCOVERY,
 					 "1444 Failed to allocate mempool "
 					 "unreg_rpi UNREG x%x, "
-					 "DID x%x, flag x%x, "
+					 "DID x%x, flag x%lx, "
 					 "ndlp x%px\n",
 					 ndlp->nlp_rpi, ndlp->nlp_DID,
 					 ndlp->nlp_flag, ndlp);
@@ -5364,7 +5324,7 @@ lpfc_unreg_rpi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 			 * not unloading.
 			 */
 			if (!test_bit(FC_UNLOADING, &vport->load_flag)) {
-				ndlp->nlp_flag &= ~NLP_UNREG_INP;
+				clear_bit(NLP_UNREG_INP, &ndlp->nlp_flag);
 				lpfc_issue_els_logo(vport, ndlp, 0);
 				ndlp->nlp_prev_state = ndlp->nlp_state;
 				lpfc_nlp_set_state(vport, ndlp,
@@ -5377,13 +5337,13 @@ lpfc_unreg_rpi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 out:
 		if (phba->sli_rev != LPFC_SLI_REV4)
 			ndlp->nlp_rpi = 0;
-		ndlp->nlp_flag &= ~NLP_RPI_REGISTERED;
-		ndlp->nlp_flag &= ~NLP_NPR_ADISC;
+		clear_bit(NLP_RPI_REGISTERED, &ndlp->nlp_flag);
+		clear_bit(NLP_NPR_ADISC, &ndlp->nlp_flag);
 		if (acc_plogi)
-			ndlp->nlp_flag &= ~NLP_LOGO_ACC;
+			clear_bit(NLP_LOGO_ACC, &ndlp->nlp_flag);
 		return 1;
 	}
-	ndlp->nlp_flag &= ~NLP_LOGO_ACC;
+	clear_bit(NLP_LOGO_ACC, &ndlp->nlp_flag);
 	return 0;
 }
 
@@ -5411,7 +5371,7 @@ lpfc_unreg_hba_rpis(struct lpfc_hba *phba)
 	for (i = 0; i <= phba->max_vports && vports[i] != NULL; i++) {
 		spin_lock_irqsave(&vports[i]->fc_nodes_list_lock, iflags);
 		list_for_each_entry(ndlp, &vports[i]->fc_nodes, nlp_listp) {
-			if (ndlp->nlp_flag & NLP_RPI_REGISTERED) {
+			if (test_bit(NLP_RPI_REGISTERED, &ndlp->nlp_flag)) {
 				/* The mempool_alloc might sleep */
 				spin_unlock_irqrestore(&vports[i]->fc_nodes_list_lock,
 						       iflags);
@@ -5499,7 +5459,7 @@ lpfc_cleanup_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 	/* Cleanup node for NPort <nlp_DID> */
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_NODE,
 			 "0900 Cleanup node for NPort x%x "
-			 "Data: x%x x%x x%x\n",
+			 "Data: x%lx x%x x%x\n",
 			 ndlp->nlp_DID, ndlp->nlp_flag,
 			 ndlp->nlp_state, ndlp->nlp_rpi);
 	lpfc_dequeue_node(vport, ndlp);
@@ -5544,9 +5504,7 @@ lpfc_cleanup_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 
 	lpfc_els_abort(phba, ndlp);
 
-	spin_lock_irq(&ndlp->lock);
-	ndlp->nlp_flag &= ~NLP_DELAY_TMO;
-	spin_unlock_irq(&ndlp->lock);
+	clear_bit(NLP_DELAY_TMO, &ndlp->nlp_flag);
 
 	ndlp->nlp_last_elscmd = 0;
 	del_timer_sync(&ndlp->nlp_delayfunc);
@@ -5555,10 +5513,6 @@ lpfc_cleanup_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 	list_del_init(&ndlp->dev_loss_evt.evt_listp);
 	list_del_init(&ndlp->recovery_evt.evt_listp);
 	lpfc_cleanup_vports_rrqs(vport, ndlp);
-
-	if (phba->sli_rev == LPFC_SLI_REV4)
-		ndlp->nlp_flag |= NLP_RELEASE_RPI;
-
 	return 0;
 }
 
@@ -5622,6 +5576,7 @@ static struct lpfc_nodelist *
 __lpfc_findnode_did(struct lpfc_vport *vport, uint32_t did)
 {
 	struct lpfc_nodelist *ndlp;
+	struct lpfc_nodelist *np = NULL;
 	uint32_t data1;
 
 	list_for_each_entry(ndlp, &vport->fc_nodes, nlp_listp) {
@@ -5632,18 +5587,24 @@ __lpfc_findnode_did(struct lpfc_vport *vport, uint32_t did)
 				 );
 			lpfc_printf_vlog(vport, KERN_INFO, LOG_NODE_VERBOSE,
 					 "0929 FIND node DID "
-					 "Data: x%px x%x x%x x%x x%x x%px\n",
+					 "Data: x%px x%x x%lx x%x x%x x%px\n",
 					 ndlp, ndlp->nlp_DID,
 					 ndlp->nlp_flag, data1, ndlp->nlp_rpi,
 					 ndlp->active_rrqs_xri_bitmap);
-			return ndlp;
+
+			/* Check for new or potentially stale node */
+			if (ndlp->nlp_state != NLP_STE_UNUSED_NODE)
+				return ndlp;
+			np = ndlp;
 		}
 	}
 
-	/* FIND node did <did> NOT FOUND */
-	lpfc_printf_vlog(vport, KERN_INFO, LOG_NODE,
-			 "0932 FIND node did x%x NOT FOUND.\n", did);
-	return NULL;
+	if (!np)
+		/* FIND node did <did> NOT FOUND */
+		lpfc_printf_vlog(vport, KERN_INFO, LOG_NODE,
+				 "0932 FIND node did x%x NOT FOUND.\n", did);
+
+	return np;
 }
 
 struct lpfc_nodelist *
@@ -5679,7 +5640,7 @@ lpfc_findnode_mapped(struct lpfc_vport *vport)
 					       iflags);
 			lpfc_printf_vlog(vport, KERN_INFO, LOG_NODE_VERBOSE,
 					 "2025 FIND node DID MAPPED "
-					 "Data: x%px x%x x%x x%x x%px\n",
+					 "Data: x%px x%x x%lx x%x x%px\n",
 					 ndlp, ndlp->nlp_DID,
 					 ndlp->nlp_flag, data1,
 					 ndlp->active_rrqs_xri_bitmap);
@@ -5713,13 +5674,11 @@ lpfc_setup_disc_node(struct lpfc_vport *vport, uint32_t did)
 
 		lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY,
 				 "6453 Setup New Node 2B_DISC x%x "
-				 "Data:x%x x%x x%lx\n",
+				 "Data:x%lx x%x x%lx\n",
 				 ndlp->nlp_DID, ndlp->nlp_flag,
 				 ndlp->nlp_state, vport->fc_flag);
 
-		spin_lock_irq(&ndlp->lock);
-		ndlp->nlp_flag |= NLP_NPR_2B_DISC;
-		spin_unlock_irq(&ndlp->lock);
+		set_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag);
 		return ndlp;
 	}
 
@@ -5738,7 +5697,7 @@ lpfc_setup_disc_node(struct lpfc_vport *vport, uint32_t did)
 
 			lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY,
 					 "6455 Setup RSCN Node 2B_DISC x%x "
-					 "Data:x%x x%x x%lx\n",
+					 "Data:x%lx x%x x%lx\n",
 					 ndlp->nlp_DID, ndlp->nlp_flag,
 					 ndlp->nlp_state, vport->fc_flag);
 
@@ -5756,13 +5715,11 @@ lpfc_setup_disc_node(struct lpfc_vport *vport, uint32_t did)
 							NLP_EVT_DEVICE_RECOVERY);
 			}
 
-			spin_lock_irq(&ndlp->lock);
-			ndlp->nlp_flag |= NLP_NPR_2B_DISC;
-			spin_unlock_irq(&ndlp->lock);
+			set_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag);
 		} else {
 			lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY,
 					 "6456 Skip Setup RSCN Node x%x "
-					 "Data:x%x x%x x%lx\n",
+					 "Data:x%lx x%x x%lx\n",
 					 ndlp->nlp_DID, ndlp->nlp_flag,
 					 ndlp->nlp_state, vport->fc_flag);
 			ndlp = NULL;
@@ -5770,7 +5727,7 @@ lpfc_setup_disc_node(struct lpfc_vport *vport, uint32_t did)
 	} else {
 		lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY,
 				 "6457 Setup Active Node 2B_DISC x%x "
-				 "Data:x%x x%x x%lx\n",
+				 "Data:x%lx x%x x%lx\n",
 				 ndlp->nlp_DID, ndlp->nlp_flag,
 				 ndlp->nlp_state, vport->fc_flag);
 
@@ -5781,7 +5738,7 @@ lpfc_setup_disc_node(struct lpfc_vport *vport, uint32_t did)
 		if (ndlp->nlp_state == NLP_STE_ADISC_ISSUE ||
 		    ndlp->nlp_state == NLP_STE_PLOGI_ISSUE ||
 		    (!vport->phba->nvmet_support &&
-		     ndlp->nlp_flag & NLP_RCV_PLOGI))
+		     test_bit(NLP_RCV_PLOGI, &ndlp->nlp_flag)))
 			return NULL;
 
 		if (vport->phba->nvmet_support)
@@ -5791,10 +5748,7 @@ lpfc_setup_disc_node(struct lpfc_vport *vport, uint32_t did)
 		 * allows for rediscovery
 		 */
 		lpfc_nlp_set_state(vport, ndlp, NLP_STE_NPR_NODE);
-
-		spin_lock_irq(&ndlp->lock);
-		ndlp->nlp_flag |= NLP_NPR_2B_DISC;
-		spin_unlock_irq(&ndlp->lock);
+		set_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag);
 	}
 	return ndlp;
 }
@@ -6165,7 +6119,7 @@ lpfc_disc_timeout_handler(struct lpfc_vport *vport)
 				/* Clean up the ndlp on Fabric connections */
 				lpfc_drop_node(vport, ndlp);
 
-			} else if (!(ndlp->nlp_flag & NLP_NPR_ADISC)) {
+			} else if (!test_bit(NLP_NPR_ADISC, &ndlp->nlp_flag)) {
 				/* Fail outstanding IO now since device
 				 * is marked for PLOGI.
 				 */
@@ -6378,11 +6332,11 @@ lpfc_mbx_cmpl_fdmi_reg_login(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 
 	if (phba->sli_rev < LPFC_SLI_REV4)
 		ndlp->nlp_rpi = mb->un.varWords[0];
-	ndlp->nlp_flag |= NLP_RPI_REGISTERED;
+	set_bit(NLP_RPI_REGISTERED, &ndlp->nlp_flag);
 	ndlp->nlp_type |= NLP_FABRIC;
 	lpfc_nlp_set_state(vport, ndlp, NLP_STE_UNMAPPED_NODE);
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_NODE | LOG_DISCOVERY,
-			 "0004 rpi:%x DID:%x flg:%x %d x%px\n",
+			 "0004 rpi:%x DID:%x flg:%lx %d x%px\n",
 			 ndlp->nlp_rpi, ndlp->nlp_DID, ndlp->nlp_flag,
 			 kref_read(&ndlp->kref),
 			 ndlp);
@@ -6432,7 +6386,7 @@ __lpfc_find_node(struct lpfc_vport *vport, node_filter filter, void *param)
 		if (filter(ndlp, param)) {
 			lpfc_printf_vlog(vport, KERN_INFO, LOG_NODE_VERBOSE,
 					 "3185 FIND node filter %ps DID "
-					 "ndlp x%px did x%x flg x%x st x%x "
+					 "ndlp x%px did x%x flg x%lx st x%x "
 					 "xri x%x type x%x rpi x%x\n",
 					 filter, ndlp, ndlp->nlp_DID,
 					 ndlp->nlp_flag, ndlp->nlp_state,
@@ -6567,9 +6521,10 @@ lpfc_nlp_init(struct lpfc_vport *vport, uint32_t did)
 	INIT_LIST_HEAD(&ndlp->nlp_listp);
 	if (vport->phba->sli_rev == LPFC_SLI_REV4) {
 		ndlp->nlp_rpi = rpi;
-		lpfc_printf_vlog(vport, KERN_INFO, LOG_NODE | LOG_DISCOVERY,
-				 "0007 Init New ndlp x%px, rpi:x%x DID:%x "
-				 "flg:x%x refcnt:%d\n",
+		lpfc_printf_vlog(vport, KERN_INFO,
+				 LOG_ELS | LOG_NODE | LOG_DISCOVERY,
+				 "0007 Init New ndlp x%px, rpi:x%x DID:x%x "
+				 "flg:x%lx refcnt:%d\n",
 				 ndlp, ndlp->nlp_rpi, ndlp->nlp_DID,
 				 ndlp->nlp_flag, kref_read(&ndlp->kref));
 
@@ -6601,7 +6556,7 @@ lpfc_nlp_release(struct kref *kref)
 	struct lpfc_vport *vport = ndlp->vport;
 
 	lpfc_debugfs_disc_trc(ndlp->vport, LPFC_DISC_TRC_NODE,
-		"node release:    did:x%x flg:x%x type:x%x",
+		"node release:    did:x%x flg:x%lx type:x%x",
 		ndlp->nlp_DID, ndlp->nlp_flag, ndlp->nlp_type);
 
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_NODE,
@@ -6613,19 +6568,12 @@ lpfc_nlp_release(struct kref *kref)
 	lpfc_cancel_retry_delay_tmo(vport, ndlp);
 	lpfc_cleanup_node(vport, ndlp);
 
-	/* Not all ELS transactions have registered the RPI with the port.
-	 * In these cases the rpi usage is temporary and the node is
-	 * released when the WQE is completed.  Catch this case to free the
-	 * RPI to the pool.  Because this node is in the release path, a lock
-	 * is unnecessary.  All references are gone and the node has been
-	 * dequeued.
+	/* All nodes are initialized with an RPI that needs to be released
+	 * now. All references are gone and the node has been dequeued.
 	 */
-	if (ndlp->nlp_flag & NLP_RELEASE_RPI) {
-		if (ndlp->nlp_rpi != LPFC_RPI_ALLOC_ERROR &&
-		    !(ndlp->nlp_flag & (NLP_RPI_REGISTERED | NLP_UNREG_INP))) {
-			lpfc_sli4_free_rpi(vport->phba, ndlp->nlp_rpi);
-			ndlp->nlp_rpi = LPFC_RPI_ALLOC_ERROR;
-		}
+	if (vport->phba->sli_rev == LPFC_SLI_REV4) {
+		lpfc_sli4_free_rpi(vport->phba, ndlp->nlp_rpi);
+		ndlp->nlp_rpi = LPFC_RPI_ALLOC_ERROR;
 	}
 
 	/* The node is not freed back to memory, it is released to a pool so
@@ -6654,7 +6602,7 @@ lpfc_nlp_get(struct lpfc_nodelist *ndlp)
 
 	if (ndlp) {
 		lpfc_debugfs_disc_trc(ndlp->vport, LPFC_DISC_TRC_NODE,
-			"node get:        did:x%x flg:x%x refcnt:x%x",
+			"node get:        did:x%x flg:x%lx refcnt:x%x",
 			ndlp->nlp_DID, ndlp->nlp_flag,
 			kref_read(&ndlp->kref));
 
@@ -6686,7 +6634,7 @@ lpfc_nlp_put(struct lpfc_nodelist *ndlp)
 {
 	if (ndlp) {
 		lpfc_debugfs_disc_trc(ndlp->vport, LPFC_DISC_TRC_NODE,
-				"node put:        did:x%x flg:x%x refcnt:x%x",
+				"node put:        did:x%x flg:x%lx refcnt:x%x",
 				ndlp->nlp_DID, ndlp->nlp_flag,
 				kref_read(&ndlp->kref));
 	} else {
@@ -6739,11 +6687,12 @@ lpfc_fcf_inuse(struct lpfc_hba *phba)
 				spin_unlock_irqrestore(&vports[i]->fc_nodes_list_lock,
 						       iflags);
 				goto out;
-			} else if (ndlp->nlp_flag & NLP_RPI_REGISTERED) {
+			} else if (test_bit(NLP_RPI_REGISTERED,
+					    &ndlp->nlp_flag)) {
 				ret = 1;
 				lpfc_printf_log(phba, KERN_INFO,
 						LOG_NODE | LOG_DISCOVERY,
-						"2624 RPI %x DID %x flag %x "
+						"2624 RPI %x DID %x flag %lx "
 						"still logged in\n",
 						ndlp->nlp_rpi, ndlp->nlp_DID,
 						ndlp->nlp_flag);
diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c
index a3658ef1141b..3ddcaa864f07 100644
--- a/drivers/scsi/lpfc/lpfc_init.c
+++ b/drivers/scsi/lpfc/lpfc_init.c
@@ -3092,7 +3092,8 @@ lpfc_cleanup(struct lpfc_vport *vport)
 				lpfc_printf_vlog(ndlp->vport, KERN_ERR,
 						 LOG_DISCOVERY,
 						 "0282 did:x%x ndlp:x%px "
-						 "refcnt:%d xflags x%x nflag x%x\n",
+						 "refcnt:%d xflags x%x "
+						 "nflag x%lx\n",
 						 ndlp->nlp_DID, (void *)ndlp,
 						 kref_read(&ndlp->kref),
 						 ndlp->fc4_xpt_flags,
@@ -3379,7 +3380,7 @@ lpfc_block_mgmt_io(struct lpfc_hba *phba, int mbx_action)
 }
 
 /**
- * lpfc_sli4_node_prep - Assign RPIs for active nodes.
+ * lpfc_sli4_node_rpi_restore - Recover assigned RPIs for active nodes.
  * @phba: pointer to lpfc hba data structure.
  *
  * Allocate RPIs for all active remote nodes. This is needed whenever
@@ -3387,7 +3388,7 @@ lpfc_block_mgmt_io(struct lpfc_hba *phba, int mbx_action)
  * is to fixup the temporary rpi assignments.
  **/
 void
-lpfc_sli4_node_prep(struct lpfc_hba *phba)
+lpfc_sli4_node_rpi_restore(struct lpfc_hba *phba)
 {
 	struct lpfc_nodelist  *ndlp, *next_ndlp;
 	struct lpfc_vport **vports;
@@ -3397,10 +3398,10 @@ lpfc_sli4_node_prep(struct lpfc_hba *phba)
 		return;
 
 	vports = lpfc_create_vport_work_array(phba);
-	if (vports == NULL)
+	if (!vports)
 		return;
 
-	for (i = 0; i <= phba->max_vports && vports[i] != NULL; i++) {
+	for (i = 0; i <= phba->max_vports && vports[i]; i++) {
 		if (test_bit(FC_UNLOADING, &vports[i]->load_flag))
 			continue;
 
@@ -3409,14 +3410,20 @@ lpfc_sli4_node_prep(struct lpfc_hba *phba)
 					 nlp_listp) {
 			rpi = lpfc_sli4_alloc_rpi(phba);
 			if (rpi == LPFC_RPI_ALLOC_ERROR) {
-				/* TODO print log? */
+				lpfc_printf_vlog(ndlp->vport, KERN_INFO,
+						 LOG_NODE | LOG_DISCOVERY,
+						 "0099 RPI alloc error for "
+						 "ndlp x%px DID:x%06x "
+						 "flg:x%lx\n",
+						 ndlp, ndlp->nlp_DID,
+						 ndlp->nlp_flag);
 				continue;
 			}
 			ndlp->nlp_rpi = rpi;
 			lpfc_printf_vlog(ndlp->vport, KERN_INFO,
 					 LOG_NODE | LOG_DISCOVERY,
 					 "0009 Assign RPI x%x to ndlp x%px "
-					 "DID:x%06x flg:x%x\n",
+					 "DID:x%06x flg:x%lx\n",
 					 ndlp->nlp_rpi, ndlp, ndlp->nlp_DID,
 					 ndlp->nlp_flag);
 		}
@@ -3820,35 +3827,12 @@ lpfc_offline_prep(struct lpfc_hba *phba, int mbx_action)
 						 &vports[i]->fc_nodes,
 						 nlp_listp) {
 
-				spin_lock_irq(&ndlp->lock);
-				ndlp->nlp_flag &= ~NLP_NPR_ADISC;
-				spin_unlock_irq(&ndlp->lock);
-
+				clear_bit(NLP_NPR_ADISC, &ndlp->nlp_flag);
 				if (offline || hba_pci_err) {
-					spin_lock_irq(&ndlp->lock);
-					ndlp->nlp_flag &= ~(NLP_UNREG_INP |
-							    NLP_RPI_REGISTERED);
-					spin_unlock_irq(&ndlp->lock);
-					if (phba->sli_rev == LPFC_SLI_REV4)
-						lpfc_sli_rpi_release(vports[i],
-								     ndlp);
-				} else {
-					lpfc_unreg_rpi(vports[i], ndlp);
-				}
-				/*
-				 * Whenever an SLI4 port goes offline, free the
-				 * RPI. Get a new RPI when the adapter port
-				 * comes back online.
-				 */
-				if (phba->sli_rev == LPFC_SLI_REV4) {
-					lpfc_printf_vlog(vports[i], KERN_INFO,
-						 LOG_NODE | LOG_DISCOVERY,
-						 "0011 Free RPI x%x on "
-						 "ndlp: x%px did x%x\n",
-						 ndlp->nlp_rpi, ndlp,
-						 ndlp->nlp_DID);
-					lpfc_sli4_free_rpi(phba, ndlp->nlp_rpi);
-					ndlp->nlp_rpi = LPFC_RPI_ALLOC_ERROR;
+					clear_bit(NLP_UNREG_INP,
+						  &ndlp->nlp_flag);
+					clear_bit(NLP_RPI_REGISTERED,
+						  &ndlp->nlp_flag);
 				}
 
 				if (ndlp->nlp_type & NLP_FABRIC) {
@@ -6925,9 +6909,7 @@ lpfc_sli4_async_fip_evt(struct lpfc_hba *phba,
 			 */
 			mod_timer(&ndlp->nlp_delayfunc,
 				  jiffies + msecs_to_jiffies(1000));
-			spin_lock_irq(&ndlp->lock);
-			ndlp->nlp_flag |= NLP_DELAY_TMO;
-			spin_unlock_irq(&ndlp->lock);
+			set_bit(NLP_DELAY_TMO, &ndlp->nlp_flag);
 			ndlp->nlp_last_elscmd = ELS_CMD_FDISC;
 			vport->port_state = LPFC_FDISC;
 		} else {
@@ -13190,6 +13172,7 @@ lpfc_sli4_enable_msi(struct lpfc_hba *phba)
 	eqhdl = lpfc_get_eq_hdl(0);
 	rc = pci_irq_vector(phba->pcidev, 0);
 	if (rc < 0) {
+		free_irq(phba->pcidev->irq, phba);
 		pci_free_irq_vectors(phba->pcidev);
 		lpfc_printf_log(phba, KERN_WARNING, LOG_INIT,
 				"0496 MSI pci_irq_vec failed (%d)\n", rc);
@@ -13270,6 +13253,7 @@ lpfc_sli4_enable_intr(struct lpfc_hba *phba, uint32_t cfg_mode)
 			eqhdl = lpfc_get_eq_hdl(0);
 			retval = pci_irq_vector(phba->pcidev, 0);
 			if (retval < 0) {
+				free_irq(phba->pcidev->irq, phba);
 				lpfc_printf_log(phba, KERN_WARNING, LOG_INIT,
 					"0502 INTR pci_irq_vec failed (%d)\n",
 					 retval);
diff --git a/drivers/scsi/lpfc/lpfc_nportdisc.c b/drivers/scsi/lpfc/lpfc_nportdisc.c
index 4574716c8764..4d88cfe71cae 100644
--- a/drivers/scsi/lpfc/lpfc_nportdisc.c
+++ b/drivers/scsi/lpfc/lpfc_nportdisc.c
@@ -65,7 +65,7 @@ lpfc_check_adisc(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 		 struct lpfc_name *nn, struct lpfc_name *pn)
 {
 	/* First, we MUST have a RPI registered */
-	if (!(ndlp->nlp_flag & NLP_RPI_REGISTERED))
+	if (!test_bit(NLP_RPI_REGISTERED, &ndlp->nlp_flag))
 		return 0;
 
 	/* Compare the ADISC rsp WWNN / WWPN matches our internal node
@@ -239,7 +239,7 @@ lpfc_els_abort(struct lpfc_hba *phba, struct lpfc_nodelist *ndlp)
 	/* Abort outstanding I/O on NPort <nlp_DID> */
 	lpfc_printf_vlog(ndlp->vport, KERN_INFO, LOG_DISCOVERY,
 			 "2819 Abort outstanding I/O on NPort x%x "
-			 "Data: x%x x%x x%x\n",
+			 "Data: x%lx x%x x%x\n",
 			 ndlp->nlp_DID, ndlp->nlp_flag, ndlp->nlp_state,
 			 ndlp->nlp_rpi);
 	/* Clean up all fabric IOs first.*/
@@ -340,7 +340,7 @@ lpfc_defer_plogi_acc(struct lpfc_hba *phba, LPFC_MBOXQ_t *login_mbox)
 
 	/* Now process the REG_RPI cmpl */
 	lpfc_mbx_cmpl_reg_login(phba, login_mbox);
-	ndlp->nlp_flag &= ~NLP_ACC_REGLOGIN;
+	clear_bit(NLP_ACC_REGLOGIN, &ndlp->nlp_flag);
 	kfree(save_iocb);
 }
 
@@ -404,7 +404,7 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 
 	/* PLOGI chkparm OK */
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS,
-			 "0114 PLOGI chkparm OK Data: x%x x%x x%x "
+			 "0114 PLOGI chkparm OK Data: x%x x%x x%lx "
 			 "x%x x%x x%lx\n",
 			 ndlp->nlp_DID, ndlp->nlp_state, ndlp->nlp_flag,
 			 ndlp->nlp_rpi, vport->port_state,
@@ -429,7 +429,7 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	/* if already logged in, do implicit logout */
 	switch (ndlp->nlp_state) {
 	case  NLP_STE_NPR_NODE:
-		if (!(ndlp->nlp_flag & NLP_NPR_ADISC))
+		if (!test_bit(NLP_NPR_ADISC, &ndlp->nlp_flag))
 			break;
 		fallthrough;
 	case  NLP_STE_REG_LOGIN_ISSUE:
@@ -449,7 +449,7 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 			ndlp->nlp_type &= ~(NLP_NVME_TARGET | NLP_NVME_INITIATOR);
 			ndlp->nlp_fcp_info &= ~NLP_FCP_2_DEVICE;
 			ndlp->nlp_nvme_info &= ~NLP_NVME_NSLER;
-			ndlp->nlp_flag &= ~NLP_FIRSTBURST;
+			clear_bit(NLP_FIRSTBURST, &ndlp->nlp_flag);
 
 			lpfc_els_rsp_acc(vport, ELS_CMD_PLOGI, cmdiocb,
 					 ndlp, NULL);
@@ -480,7 +480,7 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	ndlp->nlp_type &= ~(NLP_NVME_TARGET | NLP_NVME_INITIATOR);
 	ndlp->nlp_fcp_info &= ~NLP_FCP_2_DEVICE;
 	ndlp->nlp_nvme_info &= ~NLP_NVME_NSLER;
-	ndlp->nlp_flag &= ~NLP_FIRSTBURST;
+	clear_bit(NLP_FIRSTBURST, &ndlp->nlp_flag);
 
 	login_mbox = NULL;
 	link_mbox = NULL;
@@ -552,13 +552,13 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 		lpfc_can_disctmo(vport);
 	}
 
-	ndlp->nlp_flag &= ~NLP_SUPPRESS_RSP;
+	clear_bit(NLP_SUPPRESS_RSP, &ndlp->nlp_flag);
 	if ((phba->sli.sli_flag & LPFC_SLI_SUPPRESS_RSP) &&
 	    sp->cmn.valid_vendor_ver_level) {
 		vid = be32_to_cpu(sp->un.vv.vid);
 		flag = be32_to_cpu(sp->un.vv.flags);
 		if ((vid == LPFC_VV_EMLX_ID) && (flag & LPFC_VV_SUPPRESS_RSP))
-			ndlp->nlp_flag |= NLP_SUPPRESS_RSP;
+			set_bit(NLP_SUPPRESS_RSP, &ndlp->nlp_flag);
 	}
 
 	login_mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
@@ -627,10 +627,9 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 			 * this ELS request. The only way to do this is
 			 * to register, then unregister the RPI.
 			 */
-			spin_lock_irq(&ndlp->lock);
-			ndlp->nlp_flag |= (NLP_RM_DFLT_RPI | NLP_ACC_REGLOGIN |
-					   NLP_RCV_PLOGI);
-			spin_unlock_irq(&ndlp->lock);
+			set_bit(NLP_RM_DFLT_RPI, &ndlp->nlp_flag);
+			set_bit(NLP_ACC_REGLOGIN, &ndlp->nlp_flag);
+			set_bit(NLP_RCV_PLOGI, &ndlp->nlp_flag);
 		}
 
 		stat.un.b.lsRjtRsnCode = LSRJT_INVALID_CMD;
@@ -665,9 +664,8 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 
 	login_mbox->ctx_u.save_iocb = save_iocb; /* For PLOGI ACC */
 
-	spin_lock_irq(&ndlp->lock);
-	ndlp->nlp_flag |= (NLP_ACC_REGLOGIN | NLP_RCV_PLOGI);
-	spin_unlock_irq(&ndlp->lock);
+	set_bit(NLP_ACC_REGLOGIN, &ndlp->nlp_flag);
+	set_bit(NLP_RCV_PLOGI, &ndlp->nlp_flag);
 
 	/* Start the ball rolling by issuing REG_LOGIN here */
 	rc = lpfc_sli_issue_mbox(phba, login_mbox, MBX_NOWAIT);
@@ -797,7 +795,7 @@ out:
 		 */
 		if (ndlp->nlp_type & (NLP_FCP_TARGET | NLP_NVME_TARGET)) {
 			if ((ndlp->nlp_state != NLP_STE_MAPPED_NODE) &&
-			    !(ndlp->nlp_flag & NLP_NPR_ADISC))
+			    !test_bit(NLP_NPR_ADISC, &ndlp->nlp_flag))
 				lpfc_nlp_set_state(vport, ndlp,
 						   NLP_STE_MAPPED_NODE);
 		}
@@ -814,9 +812,7 @@ out:
 	/* 1 sec timeout */
 	mod_timer(&ndlp->nlp_delayfunc, jiffies + msecs_to_jiffies(1000));
 
-	spin_lock_irq(&ndlp->lock);
-	ndlp->nlp_flag |= NLP_DELAY_TMO;
-	spin_unlock_irq(&ndlp->lock);
+	set_bit(NLP_DELAY_TMO, &ndlp->nlp_flag);
 	ndlp->nlp_last_elscmd = ELS_CMD_PLOGI;
 	ndlp->nlp_prev_state = ndlp->nlp_state;
 	lpfc_nlp_set_state(vport, ndlp, NLP_STE_NPR_NODE);
@@ -835,9 +831,7 @@ lpfc_rcv_logo(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	/* Only call LOGO ACC for first LOGO, this avoids sending unnecessary
 	 * PLOGIs during LOGO storms from a device.
 	 */
-	spin_lock_irq(&ndlp->lock);
-	ndlp->nlp_flag |= NLP_LOGO_ACC;
-	spin_unlock_irq(&ndlp->lock);
+	set_bit(NLP_LOGO_ACC, &ndlp->nlp_flag);
 	if (els_cmd == ELS_CMD_PRLO)
 		lpfc_els_rsp_acc(vport, ELS_CMD_PRLO, cmdiocb, ndlp, NULL);
 	else
@@ -890,9 +884,7 @@ lpfc_rcv_logo(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 			 */
 			mod_timer(&ndlp->nlp_delayfunc,
 				  jiffies + msecs_to_jiffies(1000));
-			spin_lock_irq(&ndlp->lock);
-			ndlp->nlp_flag |= NLP_DELAY_TMO;
-			spin_unlock_irq(&ndlp->lock);
+			set_bit(NLP_DELAY_TMO, &ndlp->nlp_flag);
 			ndlp->nlp_last_elscmd = ELS_CMD_FDISC;
 			vport->port_state = LPFC_FDISC;
 		} else {
@@ -915,14 +907,12 @@ lpfc_rcv_logo(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 		     ndlp->nlp_state <= NLP_STE_PRLI_ISSUE)) {
 			mod_timer(&ndlp->nlp_delayfunc,
 				  jiffies + msecs_to_jiffies(1000 * 1));
-			spin_lock_irq(&ndlp->lock);
-			ndlp->nlp_flag |= NLP_DELAY_TMO;
-			spin_unlock_irq(&ndlp->lock);
+			set_bit(NLP_DELAY_TMO, &ndlp->nlp_flag);
 			ndlp->nlp_last_elscmd = ELS_CMD_PLOGI;
 			lpfc_printf_vlog(vport, KERN_INFO,
 					 LOG_NODE | LOG_ELS | LOG_DISCOVERY,
 					 "3204 Start nlpdelay on DID x%06x "
-					 "nflag x%x lastels x%x ref cnt %u",
+					 "nflag x%lx lastels x%x ref cnt %u",
 					 ndlp->nlp_DID, ndlp->nlp_flag,
 					 ndlp->nlp_last_elscmd,
 					 kref_read(&ndlp->kref));
@@ -935,9 +925,7 @@ out:
 	ndlp->nlp_prev_state = ndlp->nlp_state;
 	lpfc_nlp_set_state(vport, ndlp, NLP_STE_NPR_NODE);
 
-	spin_lock_irq(&ndlp->lock);
-	ndlp->nlp_flag &= ~NLP_NPR_ADISC;
-	spin_unlock_irq(&ndlp->lock);
+	clear_bit(NLP_NPR_ADISC, &ndlp->nlp_flag);
 	/* The driver has to wait until the ACC completes before it continues
 	 * processing the LOGO.  The action will resume in
 	 * lpfc_cmpl_els_logo_acc routine. Since part of processing includes an
@@ -978,7 +966,7 @@ lpfc_rcv_prli_support_check(struct lpfc_vport *vport,
 out:
 	lpfc_printf_vlog(vport, KERN_WARNING, LOG_DISCOVERY,
 			 "6115 Rcv PRLI (%x) check failed: ndlp rpi %d "
-			 "state x%x flags x%x port_type: x%x "
+			 "state x%x flags x%lx port_type: x%x "
 			 "npr->initfcn: x%x npr->tgtfcn: x%x\n",
 			 cmd, ndlp->nlp_rpi, ndlp->nlp_state,
 			 ndlp->nlp_flag, vport->port_type,
@@ -1020,7 +1008,7 @@ lpfc_rcv_prli(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 			if (npr->prliType == PRLI_NVME_TYPE)
 				ndlp->nlp_type |= NLP_NVME_TARGET;
 			if (npr->writeXferRdyDis)
-				ndlp->nlp_flag |= NLP_FIRSTBURST;
+				set_bit(NLP_FIRSTBURST, &ndlp->nlp_flag);
 		}
 		if (npr->Retry && ndlp->nlp_type &
 					(NLP_FCP_INITIATOR | NLP_FCP_TARGET))
@@ -1057,7 +1045,7 @@ lpfc_rcv_prli(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 			roles |= FC_RPORT_ROLE_FCP_TARGET;
 
 		lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_RPORT,
-			"rport rolechg:   role:x%x did:x%x flg:x%x",
+			"rport rolechg:   role:x%x did:x%x flg:x%lx",
 			roles, ndlp->nlp_DID, ndlp->nlp_flag);
 
 		if (vport->cfg_enable_fc4_type != LPFC_ENABLE_NVME)
@@ -1068,10 +1056,8 @@ lpfc_rcv_prli(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 static uint32_t
 lpfc_disc_set_adisc(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 {
-	if (!(ndlp->nlp_flag & NLP_RPI_REGISTERED)) {
-		spin_lock_irq(&ndlp->lock);
-		ndlp->nlp_flag &= ~NLP_NPR_ADISC;
-		spin_unlock_irq(&ndlp->lock);
+	if (!test_bit(NLP_RPI_REGISTERED, &ndlp->nlp_flag)) {
+		clear_bit(NLP_NPR_ADISC, &ndlp->nlp_flag);
 		return 0;
 	}
 
@@ -1081,16 +1067,12 @@ lpfc_disc_set_adisc(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 		    (test_bit(FC_RSCN_MODE, &vport->fc_flag) ||
 		    ((ndlp->nlp_fcp_info & NLP_FCP_2_DEVICE) &&
 		     (ndlp->nlp_type & NLP_FCP_TARGET)))) {
-			spin_lock_irq(&ndlp->lock);
-			ndlp->nlp_flag |= NLP_NPR_ADISC;
-			spin_unlock_irq(&ndlp->lock);
+			set_bit(NLP_NPR_ADISC, &ndlp->nlp_flag);
 			return 1;
 		}
 	}
 
-	spin_lock_irq(&ndlp->lock);
-	ndlp->nlp_flag &= ~NLP_NPR_ADISC;
-	spin_unlock_irq(&ndlp->lock);
+	clear_bit(NLP_NPR_ADISC, &ndlp->nlp_flag);
 	lpfc_unreg_rpi(vport, ndlp);
 	return 0;
 }
@@ -1115,10 +1097,10 @@ lpfc_release_rpi(struct lpfc_hba *phba, struct lpfc_vport *vport,
 	/* If there is already an UNREG in progress for this ndlp,
 	 * no need to queue up another one.
 	 */
-	if (ndlp->nlp_flag & NLP_UNREG_INP) {
+	if (test_bit(NLP_UNREG_INP, &ndlp->nlp_flag)) {
 		lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY,
 				 "1435 release_rpi SKIP UNREG x%x on "
-				 "NPort x%x deferred x%x  flg x%x "
+				 "NPort x%x deferred x%x  flg x%lx "
 				 "Data: x%px\n",
 				 ndlp->nlp_rpi, ndlp->nlp_DID,
 				 ndlp->nlp_defer_did,
@@ -1143,11 +1125,11 @@ lpfc_release_rpi(struct lpfc_hba *phba, struct lpfc_vport *vport,
 
 		if (((ndlp->nlp_DID & Fabric_DID_MASK) != Fabric_DID_MASK) &&
 		    (!test_bit(FC_OFFLINE_MODE, &vport->fc_flag)))
-			ndlp->nlp_flag |= NLP_UNREG_INP;
+			set_bit(NLP_UNREG_INP, &ndlp->nlp_flag);
 
 		lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY,
 				 "1437 release_rpi UNREG x%x "
-				 "on NPort x%x flg x%x\n",
+				 "on NPort x%x flg x%lx\n",
 				 ndlp->nlp_rpi, ndlp->nlp_DID, ndlp->nlp_flag);
 
 		rc = lpfc_sli_issue_mbox(phba, pmb, MBX_NOWAIT);
@@ -1175,7 +1157,7 @@ lpfc_disc_illegal(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	}
 	lpfc_printf_vlog(vport, KERN_ERR, LOG_TRACE_EVENT,
 			 "0271 Illegal State Transition: node x%x "
-			 "event x%x, state x%x Data: x%x x%x\n",
+			 "event x%x, state x%x Data: x%x x%lx\n",
 			 ndlp->nlp_DID, evt, ndlp->nlp_state, ndlp->nlp_rpi,
 			 ndlp->nlp_flag);
 	return ndlp->nlp_state;
@@ -1190,13 +1172,12 @@ lpfc_cmpl_plogi_illegal(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	 * working on the same NPortID, do nothing for this thread
 	 * to stop it.
 	 */
-	if (!(ndlp->nlp_flag & NLP_RCV_PLOGI)) {
+	if (!test_bit(NLP_RCV_PLOGI, &ndlp->nlp_flag))
 		lpfc_printf_vlog(vport, KERN_ERR, LOG_TRACE_EVENT,
 				 "0272 Illegal State Transition: node x%x "
-				 "event x%x, state x%x Data: x%x x%x\n",
+				 "event x%x, state x%x Data: x%x x%lx\n",
 				  ndlp->nlp_DID, evt, ndlp->nlp_state,
 				  ndlp->nlp_rpi, ndlp->nlp_flag);
-	}
 	return ndlp->nlp_state;
 }
 
@@ -1230,9 +1211,7 @@ lpfc_rcv_logo_unused_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 {
 	struct lpfc_iocbq *cmdiocb = (struct lpfc_iocbq *) arg;
 
-	spin_lock_irq(&ndlp->lock);
-	ndlp->nlp_flag |= NLP_LOGO_ACC;
-	spin_unlock_irq(&ndlp->lock);
+	set_bit(NLP_LOGO_ACC, &ndlp->nlp_flag);
 	lpfc_els_rsp_acc(vport, ELS_CMD_ACC, cmdiocb, ndlp, NULL);
 
 	return ndlp->nlp_state;
@@ -1290,11 +1269,9 @@ lpfc_rcv_plogi_plogi_issue(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 			NULL);
 	} else {
 		if (lpfc_rcv_plogi(vport, ndlp, cmdiocb) &&
-		    (ndlp->nlp_flag & NLP_NPR_2B_DISC) &&
-		    (vport->num_disc_nodes)) {
-			spin_lock_irq(&ndlp->lock);
-			ndlp->nlp_flag &= ~NLP_NPR_2B_DISC;
-			spin_unlock_irq(&ndlp->lock);
+		    test_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag) &&
+		    vport->num_disc_nodes) {
+			clear_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag);
 			/* Check if there are more PLOGIs to be sent */
 			lpfc_more_plogi(vport);
 			if (vport->num_disc_nodes == 0) {
@@ -1356,9 +1333,7 @@ lpfc_rcv_els_plogi_issue(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 
 	/* Put ndlp in npr state set plogi timer for 1 sec */
 	mod_timer(&ndlp->nlp_delayfunc, jiffies + msecs_to_jiffies(1000 * 1));
-	spin_lock_irq(&ndlp->lock);
-	ndlp->nlp_flag |= NLP_DELAY_TMO;
-	spin_unlock_irq(&ndlp->lock);
+	set_bit(NLP_DELAY_TMO, &ndlp->nlp_flag);
 	ndlp->nlp_last_elscmd = ELS_CMD_PLOGI;
 	ndlp->nlp_prev_state = NLP_STE_PLOGI_ISSUE;
 	lpfc_nlp_set_state(vport, ndlp, NLP_STE_NPR_NODE);
@@ -1389,7 +1364,7 @@ lpfc_cmpl_plogi_plogi_issue(struct lpfc_vport *vport,
 
 	ulp_status = get_job_ulpstatus(phba, rspiocb);
 
-	if (ndlp->nlp_flag & NLP_ACC_REGLOGIN) {
+	if (test_bit(NLP_ACC_REGLOGIN, &ndlp->nlp_flag)) {
 		/* Recovery from PLOGI collision logic */
 		return ndlp->nlp_state;
 	}
@@ -1418,7 +1393,7 @@ lpfc_cmpl_plogi_plogi_issue(struct lpfc_vport *vport,
 		goto out;
 	/* PLOGI chkparm OK */
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS,
-			 "0121 PLOGI chkparm OK Data: x%x x%x x%x x%x\n",
+			 "0121 PLOGI chkparm OK Data: x%x x%x x%lx x%x\n",
 			 ndlp->nlp_DID, ndlp->nlp_state,
 			 ndlp->nlp_flag, ndlp->nlp_rpi);
 	if (vport->cfg_fcp_class == 2 && (sp->cls2.classValid))
@@ -1446,14 +1421,14 @@ lpfc_cmpl_plogi_plogi_issue(struct lpfc_vport *vport,
 			ed_tov = (phba->fc_edtov + 999999) / 1000000;
 		}
 
-		ndlp->nlp_flag &= ~NLP_SUPPRESS_RSP;
+		clear_bit(NLP_SUPPRESS_RSP, &ndlp->nlp_flag);
 		if ((phba->sli.sli_flag & LPFC_SLI_SUPPRESS_RSP) &&
 		    sp->cmn.valid_vendor_ver_level) {
 			vid = be32_to_cpu(sp->un.vv.vid);
 			flag = be32_to_cpu(sp->un.vv.flags);
 			if ((vid == LPFC_VV_EMLX_ID) &&
 			    (flag & LPFC_VV_SUPPRESS_RSP))
-				ndlp->nlp_flag |= NLP_SUPPRESS_RSP;
+				set_bit(NLP_SUPPRESS_RSP, &ndlp->nlp_flag);
 		}
 
 		/*
@@ -1476,7 +1451,7 @@ lpfc_cmpl_plogi_plogi_issue(struct lpfc_vport *vport,
 						 LOG_TRACE_EVENT,
 						 "0133 PLOGI: no memory "
 						 "for config_link "
-						 "Data: x%x x%x x%x x%x\n",
+						 "Data: x%x x%x x%lx x%x\n",
 						 ndlp->nlp_DID, ndlp->nlp_state,
 						 ndlp->nlp_flag, ndlp->nlp_rpi);
 				goto out;
@@ -1500,7 +1475,7 @@ lpfc_cmpl_plogi_plogi_issue(struct lpfc_vport *vport,
 	if (!mbox) {
 		lpfc_printf_vlog(vport, KERN_ERR, LOG_TRACE_EVENT,
 				 "0018 PLOGI: no memory for reg_login "
-				 "Data: x%x x%x x%x x%x\n",
+				 "Data: x%x x%x x%lx x%x\n",
 				 ndlp->nlp_DID, ndlp->nlp_state,
 				 ndlp->nlp_flag, ndlp->nlp_rpi);
 		goto out;
@@ -1520,7 +1495,7 @@ lpfc_cmpl_plogi_plogi_issue(struct lpfc_vport *vport,
 			mbox->mbox_cmpl = lpfc_mbx_cmpl_fdmi_reg_login;
 			break;
 		default:
-			ndlp->nlp_flag |= NLP_REG_LOGIN_SEND;
+			set_bit(NLP_REG_LOGIN_SEND, &ndlp->nlp_flag);
 			mbox->mbox_cmpl = lpfc_mbx_cmpl_reg_login;
 		}
 
@@ -1535,8 +1510,7 @@ lpfc_cmpl_plogi_plogi_issue(struct lpfc_vport *vport,
 					   NLP_STE_REG_LOGIN_ISSUE);
 			return ndlp->nlp_state;
 		}
-		if (ndlp->nlp_flag & NLP_REG_LOGIN_SEND)
-			ndlp->nlp_flag &= ~NLP_REG_LOGIN_SEND;
+		clear_bit(NLP_REG_LOGIN_SEND, &ndlp->nlp_flag);
 		/* decrement node reference count to the failed mbox
 		 * command
 		 */
@@ -1544,7 +1518,7 @@ lpfc_cmpl_plogi_plogi_issue(struct lpfc_vport *vport,
 		lpfc_mbox_rsrc_cleanup(phba, mbox, MBOX_THD_UNLOCKED);
 		lpfc_printf_vlog(vport, KERN_ERR, LOG_TRACE_EVENT,
 				 "0134 PLOGI: cannot issue reg_login "
-				 "Data: x%x x%x x%x x%x\n",
+				 "Data: x%x x%x x%lx x%x\n",
 				 ndlp->nlp_DID, ndlp->nlp_state,
 				 ndlp->nlp_flag, ndlp->nlp_rpi);
 	} else {
@@ -1552,7 +1526,7 @@ lpfc_cmpl_plogi_plogi_issue(struct lpfc_vport *vport,
 
 		lpfc_printf_vlog(vport, KERN_ERR, LOG_TRACE_EVENT,
 				 "0135 PLOGI: cannot format reg_login "
-				 "Data: x%x x%x x%x x%x\n",
+				 "Data: x%x x%x x%lx x%x\n",
 				 ndlp->nlp_DID, ndlp->nlp_state,
 				 ndlp->nlp_flag, ndlp->nlp_rpi);
 	}
@@ -1605,18 +1579,15 @@ static uint32_t
 lpfc_device_rm_plogi_issue(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 			   void *arg, uint32_t evt)
 {
-	if (ndlp->nlp_flag & NLP_NPR_2B_DISC) {
-		spin_lock_irq(&ndlp->lock);
-		ndlp->nlp_flag |= NLP_NODEV_REMOVE;
-		spin_unlock_irq(&ndlp->lock);
+	if (test_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag)) {
+		set_bit(NLP_NODEV_REMOVE, &ndlp->nlp_flag);
 		return ndlp->nlp_state;
-	} else {
-		/* software abort outstanding PLOGI */
-		lpfc_els_abort(vport->phba, ndlp);
-
-		lpfc_drop_node(vport, ndlp);
-		return NLP_STE_FREED_NODE;
 	}
+	/* software abort outstanding PLOGI */
+	lpfc_els_abort(vport->phba, ndlp);
+
+	lpfc_drop_node(vport, ndlp);
+	return NLP_STE_FREED_NODE;
 }
 
 static uint32_t
@@ -1636,9 +1607,8 @@ lpfc_device_recov_plogi_issue(struct lpfc_vport *vport,
 
 	ndlp->nlp_prev_state = NLP_STE_PLOGI_ISSUE;
 	lpfc_nlp_set_state(vport, ndlp, NLP_STE_NPR_NODE);
-	spin_lock_irq(&ndlp->lock);
-	ndlp->nlp_flag &= ~(NLP_NODEV_REMOVE | NLP_NPR_2B_DISC);
-	spin_unlock_irq(&ndlp->lock);
+	clear_bit(NLP_NODEV_REMOVE, &ndlp->nlp_flag);
+	clear_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag);
 
 	return ndlp->nlp_state;
 }
@@ -1656,10 +1626,7 @@ lpfc_rcv_plogi_adisc_issue(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	cmdiocb = (struct lpfc_iocbq *) arg;
 
 	if (lpfc_rcv_plogi(vport, ndlp, cmdiocb)) {
-		if (ndlp->nlp_flag & NLP_NPR_2B_DISC) {
-			spin_lock_irq(&ndlp->lock);
-			ndlp->nlp_flag &= ~NLP_NPR_2B_DISC;
-			spin_unlock_irq(&ndlp->lock);
+		if (test_and_clear_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag)) {
 			if (vport->num_disc_nodes)
 				lpfc_more_adisc(vport);
 		}
@@ -1748,9 +1715,7 @@ lpfc_cmpl_adisc_adisc_issue(struct lpfc_vport *vport,
 		/* 1 sec timeout */
 		mod_timer(&ndlp->nlp_delayfunc,
 			  jiffies + msecs_to_jiffies(1000));
-		spin_lock_irq(&ndlp->lock);
-		ndlp->nlp_flag |= NLP_DELAY_TMO;
-		spin_unlock_irq(&ndlp->lock);
+		set_bit(NLP_DELAY_TMO, &ndlp->nlp_flag);
 		ndlp->nlp_last_elscmd = ELS_CMD_PLOGI;
 
 		ndlp->nlp_prev_state = NLP_STE_ADISC_ISSUE;
@@ -1789,18 +1754,15 @@ static uint32_t
 lpfc_device_rm_adisc_issue(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 			   void *arg, uint32_t evt)
 {
-	if (ndlp->nlp_flag & NLP_NPR_2B_DISC) {
-		spin_lock_irq(&ndlp->lock);
-		ndlp->nlp_flag |= NLP_NODEV_REMOVE;
-		spin_unlock_irq(&ndlp->lock);
+	if (test_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag)) {
+		set_bit(NLP_NODEV_REMOVE, &ndlp->nlp_flag);
 		return ndlp->nlp_state;
-	} else {
-		/* software abort outstanding ADISC */
-		lpfc_els_abort(vport->phba, ndlp);
-
-		lpfc_drop_node(vport, ndlp);
-		return NLP_STE_FREED_NODE;
 	}
+	/* software abort outstanding ADISC */
+	lpfc_els_abort(vport->phba, ndlp);
+
+	lpfc_drop_node(vport, ndlp);
+	return NLP_STE_FREED_NODE;
 }
 
 static uint32_t
@@ -1820,9 +1782,8 @@ lpfc_device_recov_adisc_issue(struct lpfc_vport *vport,
 
 	ndlp->nlp_prev_state = NLP_STE_ADISC_ISSUE;
 	lpfc_nlp_set_state(vport, ndlp, NLP_STE_NPR_NODE);
-	spin_lock_irq(&ndlp->lock);
-	ndlp->nlp_flag &= ~(NLP_NODEV_REMOVE | NLP_NPR_2B_DISC);
-	spin_unlock_irq(&ndlp->lock);
+	clear_bit(NLP_NODEV_REMOVE, &ndlp->nlp_flag);
+	clear_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag);
 	lpfc_disc_set_adisc(vport, ndlp);
 	return ndlp->nlp_state;
 }
@@ -1856,7 +1817,7 @@ lpfc_rcv_prli_reglogin_issue(struct lpfc_vport *vport,
 		 * transition to UNMAPPED provided the RPI has completed
 		 * registration.
 		 */
-		if (ndlp->nlp_flag & NLP_RPI_REGISTERED) {
+		if (test_bit(NLP_RPI_REGISTERED, &ndlp->nlp_flag)) {
 			lpfc_rcv_prli(vport, ndlp, cmdiocb);
 			lpfc_els_rsp_prli_acc(vport, cmdiocb, ndlp);
 		} else {
@@ -1895,7 +1856,7 @@ lpfc_rcv_logo_reglogin_issue(struct lpfc_vport *vport,
 	if ((mb = phba->sli.mbox_active)) {
 		if ((mb->u.mb.mbxCommand == MBX_REG_LOGIN64) &&
 		   (ndlp == mb->ctx_ndlp)) {
-			ndlp->nlp_flag &= ~NLP_REG_LOGIN_SEND;
+			clear_bit(NLP_REG_LOGIN_SEND, &ndlp->nlp_flag);
 			lpfc_nlp_put(ndlp);
 			mb->ctx_ndlp = NULL;
 			mb->mbox_cmpl = lpfc_sli_def_mbox_cmpl;
@@ -1906,7 +1867,7 @@ lpfc_rcv_logo_reglogin_issue(struct lpfc_vport *vport,
 	list_for_each_entry_safe(mb, nextmb, &phba->sli.mboxq, list) {
 		if ((mb->u.mb.mbxCommand == MBX_REG_LOGIN64) &&
 		   (ndlp == mb->ctx_ndlp)) {
-			ndlp->nlp_flag &= ~NLP_REG_LOGIN_SEND;
+			clear_bit(NLP_REG_LOGIN_SEND, &ndlp->nlp_flag);
 			lpfc_nlp_put(ndlp);
 			list_del(&mb->list);
 			phba->sli.mboxq_cnt--;
@@ -1976,9 +1937,7 @@ lpfc_cmpl_reglogin_reglogin_issue(struct lpfc_vport *vport,
 		/* Put ndlp in npr state set plogi timer for 1 sec */
 		mod_timer(&ndlp->nlp_delayfunc,
 			  jiffies + msecs_to_jiffies(1000 * 1));
-		spin_lock_irq(&ndlp->lock);
-		ndlp->nlp_flag |= NLP_DELAY_TMO;
-		spin_unlock_irq(&ndlp->lock);
+		set_bit(NLP_DELAY_TMO, &ndlp->nlp_flag);
 		ndlp->nlp_last_elscmd = ELS_CMD_PLOGI;
 
 		lpfc_issue_els_logo(vport, ndlp, 0);
@@ -1989,7 +1948,7 @@ lpfc_cmpl_reglogin_reglogin_issue(struct lpfc_vport *vport,
 	if (phba->sli_rev < LPFC_SLI_REV4)
 		ndlp->nlp_rpi = mb->un.varWords[0];
 
-	ndlp->nlp_flag |= NLP_RPI_REGISTERED;
+	set_bit(NLP_RPI_REGISTERED, &ndlp->nlp_flag);
 
 	/* Only if we are not a fabric nport do we issue PRLI */
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY,
@@ -2061,15 +2020,12 @@ lpfc_device_rm_reglogin_issue(struct lpfc_vport *vport,
 			      void *arg,
 			      uint32_t evt)
 {
-	if (ndlp->nlp_flag & NLP_NPR_2B_DISC) {
-		spin_lock_irq(&ndlp->lock);
-		ndlp->nlp_flag |= NLP_NODEV_REMOVE;
-		spin_unlock_irq(&ndlp->lock);
+	if (test_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag)) {
+		set_bit(NLP_NODEV_REMOVE, &ndlp->nlp_flag);
 		return ndlp->nlp_state;
-	} else {
-		lpfc_drop_node(vport, ndlp);
-		return NLP_STE_FREED_NODE;
 	}
+	lpfc_drop_node(vport, ndlp);
+	return NLP_STE_FREED_NODE;
 }
 
 static uint32_t
@@ -2084,17 +2040,16 @@ lpfc_device_recov_reglogin_issue(struct lpfc_vport *vport,
 
 	ndlp->nlp_prev_state = NLP_STE_REG_LOGIN_ISSUE;
 	lpfc_nlp_set_state(vport, ndlp, NLP_STE_NPR_NODE);
-	spin_lock_irq(&ndlp->lock);
 
 	/* If we are a target we won't immediately transition into PRLI,
 	 * so if REG_LOGIN already completed we don't need to ignore it.
 	 */
-	if (!(ndlp->nlp_flag & NLP_RPI_REGISTERED) ||
+	if (!test_bit(NLP_RPI_REGISTERED, &ndlp->nlp_flag) ||
 	    !vport->phba->nvmet_support)
-		ndlp->nlp_flag |= NLP_IGNR_REG_CMPL;
+		set_bit(NLP_IGNR_REG_CMPL, &ndlp->nlp_flag);
 
-	ndlp->nlp_flag &= ~(NLP_NODEV_REMOVE | NLP_NPR_2B_DISC);
-	spin_unlock_irq(&ndlp->lock);
+	clear_bit(NLP_NODEV_REMOVE, &ndlp->nlp_flag);
+	clear_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag);
 	lpfc_disc_set_adisc(vport, ndlp);
 	return ndlp->nlp_state;
 }
@@ -2228,7 +2183,8 @@ lpfc_cmpl_prli_prli_issue(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 			if (npr->targetFunc) {
 				ndlp->nlp_type |= NLP_FCP_TARGET;
 				if (npr->writeXferRdyDis)
-					ndlp->nlp_flag |= NLP_FIRSTBURST;
+					set_bit(NLP_FIRSTBURST,
+						&ndlp->nlp_flag);
 			}
 			if (npr->Retry)
 				ndlp->nlp_fcp_info |= NLP_FCP_2_DEVICE;
@@ -2272,7 +2228,7 @@ lpfc_cmpl_prli_prli_issue(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 				/* Both sides support FB. The target's first
 				 * burst size is a 512 byte encoded value.
 				 */
-				ndlp->nlp_flag |= NLP_FIRSTBURST;
+				set_bit(NLP_FIRSTBURST, &ndlp->nlp_flag);
 				ndlp->nvme_fb_size = bf_get_be32(prli_fb_sz,
 								 nvpr);
 
@@ -2287,7 +2243,7 @@ lpfc_cmpl_prli_prli_issue(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 
 		lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME_DISC,
 				 "6029 NVME PRLI Cmpl w1 x%08x "
-				 "w4 x%08x w5 x%08x flag x%x, "
+				 "w4 x%08x w5 x%08x flag x%lx, "
 				 "fcp_info x%x nlp_type x%x\n",
 				 be32_to_cpu(nvpr->word1),
 				 be32_to_cpu(nvpr->word4),
@@ -2299,9 +2255,7 @@ lpfc_cmpl_prli_prli_issue(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	    (vport->port_type == LPFC_NPIV_PORT) &&
 	     vport->cfg_restrict_login) {
 out:
-		spin_lock_irq(&ndlp->lock);
-		ndlp->nlp_flag |= NLP_TARGET_REMOVE;
-		spin_unlock_irq(&ndlp->lock);
+		set_bit(NLP_TARGET_REMOVE, &ndlp->nlp_flag);
 		lpfc_issue_els_logo(vport, ndlp, 0);
 
 		ndlp->nlp_prev_state = NLP_STE_PRLI_ISSUE;
@@ -2353,18 +2307,15 @@ static uint32_t
 lpfc_device_rm_prli_issue(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 			  void *arg, uint32_t evt)
 {
-	if (ndlp->nlp_flag & NLP_NPR_2B_DISC) {
-		spin_lock_irq(&ndlp->lock);
-		ndlp->nlp_flag |= NLP_NODEV_REMOVE;
-		spin_unlock_irq(&ndlp->lock);
+	if (test_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag)) {
+		set_bit(NLP_NODEV_REMOVE, &ndlp->nlp_flag);
 		return ndlp->nlp_state;
-	} else {
-		/* software abort outstanding PLOGI */
-		lpfc_els_abort(vport->phba, ndlp);
-
-		lpfc_drop_node(vport, ndlp);
-		return NLP_STE_FREED_NODE;
 	}
+	/* software abort outstanding PLOGI */
+	lpfc_els_abort(vport->phba, ndlp);
+
+	lpfc_drop_node(vport, ndlp);
+	return NLP_STE_FREED_NODE;
 }
 
 
@@ -2401,9 +2352,8 @@ lpfc_device_recov_prli_issue(struct lpfc_vport *vport,
 
 	ndlp->nlp_prev_state = NLP_STE_PRLI_ISSUE;
 	lpfc_nlp_set_state(vport, ndlp, NLP_STE_NPR_NODE);
-	spin_lock_irq(&ndlp->lock);
-	ndlp->nlp_flag &= ~(NLP_NODEV_REMOVE | NLP_NPR_2B_DISC);
-	spin_unlock_irq(&ndlp->lock);
+	clear_bit(NLP_NODEV_REMOVE, &ndlp->nlp_flag);
+	clear_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag);
 	lpfc_disc_set_adisc(vport, ndlp);
 	return ndlp->nlp_state;
 }
@@ -2442,9 +2392,7 @@ lpfc_rcv_logo_logo_issue(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 {
 	struct lpfc_iocbq *cmdiocb = (struct lpfc_iocbq *)arg;
 
-	spin_lock_irq(&ndlp->lock);
-	ndlp->nlp_flag |= NLP_LOGO_ACC;
-	spin_unlock_irq(&ndlp->lock);
+	set_bit(NLP_LOGO_ACC, &ndlp->nlp_flag);
 	lpfc_els_rsp_acc(vport, ELS_CMD_ACC, cmdiocb, ndlp, NULL);
 	return ndlp->nlp_state;
 }
@@ -2483,9 +2431,8 @@ lpfc_cmpl_logo_logo_issue(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 {
 	ndlp->nlp_prev_state = NLP_STE_LOGO_ISSUE;
 	lpfc_nlp_set_state(vport, ndlp, NLP_STE_NPR_NODE);
-	spin_lock_irq(&ndlp->lock);
-	ndlp->nlp_flag &= ~(NLP_NODEV_REMOVE | NLP_NPR_2B_DISC);
-	spin_unlock_irq(&ndlp->lock);
+	clear_bit(NLP_NODEV_REMOVE, &ndlp->nlp_flag);
+	clear_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag);
 	lpfc_disc_set_adisc(vport, ndlp);
 	return ndlp->nlp_state;
 }
@@ -2591,8 +2538,9 @@ lpfc_device_recov_unmap_node(struct lpfc_vport *vport,
 {
 	ndlp->nlp_prev_state = NLP_STE_UNMAPPED_NODE;
 	lpfc_nlp_set_state(vport, ndlp, NLP_STE_NPR_NODE);
+	clear_bit(NLP_NODEV_REMOVE, &ndlp->nlp_flag);
+	clear_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag);
 	spin_lock_irq(&ndlp->lock);
-	ndlp->nlp_flag &= ~(NLP_NODEV_REMOVE | NLP_NPR_2B_DISC);
 	ndlp->nlp_fc4_type &= ~(NLP_FC4_FCP | NLP_FC4_NVME);
 	spin_unlock_irq(&ndlp->lock);
 	lpfc_disc_set_adisc(vport, ndlp);
@@ -2653,9 +2601,7 @@ lpfc_rcv_prlo_mapped_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	lpfc_sli_abort_iocb(vport, ndlp->nlp_sid, 0, LPFC_CTX_TGT);
 
 	/* Send PRLO_ACC */
-	spin_lock_irq(&ndlp->lock);
-	ndlp->nlp_flag |= NLP_LOGO_ACC;
-	spin_unlock_irq(&ndlp->lock);
+	set_bit(NLP_LOGO_ACC, &ndlp->nlp_flag);
 	lpfc_els_rsp_acc(vport, ELS_CMD_PRLO, cmdiocb, ndlp, NULL);
 
 	/* Save ELS_CMD_PRLO as the last elscmd and then set to NPR.
@@ -2665,7 +2611,7 @@ lpfc_rcv_prlo_mapped_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	ndlp->nlp_prev_state = ndlp->nlp_state;
 
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_NODE | LOG_ELS | LOG_DISCOVERY,
-			 "3422 DID x%06x nflag x%x lastels x%x ref cnt %u\n",
+			 "3422 DID x%06x nflag x%lx lastels x%x ref cnt %u\n",
 			 ndlp->nlp_DID, ndlp->nlp_flag,
 			 ndlp->nlp_last_elscmd,
 			 kref_read(&ndlp->kref));
@@ -2685,8 +2631,9 @@ lpfc_device_recov_mapped_node(struct lpfc_vport *vport,
 
 	ndlp->nlp_prev_state = NLP_STE_MAPPED_NODE;
 	lpfc_nlp_set_state(vport, ndlp, NLP_STE_NPR_NODE);
+	clear_bit(NLP_NODEV_REMOVE, &ndlp->nlp_flag);
+	clear_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag);
 	spin_lock_irq(&ndlp->lock);
-	ndlp->nlp_flag &= ~(NLP_NODEV_REMOVE | NLP_NPR_2B_DISC);
 	ndlp->nlp_fc4_type &= ~(NLP_FC4_FCP | NLP_FC4_NVME);
 	spin_unlock_irq(&ndlp->lock);
 	return ndlp->nlp_state;
@@ -2699,16 +2646,16 @@ lpfc_rcv_plogi_npr_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	struct lpfc_iocbq *cmdiocb  = (struct lpfc_iocbq *) arg;
 
 	/* Ignore PLOGI if we have an outstanding LOGO */
-	if (ndlp->nlp_flag & (NLP_LOGO_SND | NLP_LOGO_ACC))
+	if (test_bit(NLP_LOGO_SND, &ndlp->nlp_flag) ||
+	    test_bit(NLP_LOGO_ACC, &ndlp->nlp_flag))
 		return ndlp->nlp_state;
 	if (lpfc_rcv_plogi(vport, ndlp, cmdiocb)) {
 		lpfc_cancel_retry_delay_tmo(vport, ndlp);
-		spin_lock_irq(&ndlp->lock);
-		ndlp->nlp_flag &= ~(NLP_NPR_ADISC | NLP_NPR_2B_DISC);
-		spin_unlock_irq(&ndlp->lock);
-	} else if (!(ndlp->nlp_flag & NLP_NPR_2B_DISC)) {
+		clear_bit(NLP_NPR_ADISC, &ndlp->nlp_flag);
+		clear_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag);
+	} else if (!test_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag)) {
 		/* send PLOGI immediately, move to PLOGI issue state */
-		if (!(ndlp->nlp_flag & NLP_DELAY_TMO)) {
+		if (!test_bit(NLP_DELAY_TMO, &ndlp->nlp_flag)) {
 			ndlp->nlp_prev_state = NLP_STE_NPR_NODE;
 			lpfc_nlp_set_state(vport, ndlp, NLP_STE_PLOGI_ISSUE);
 			lpfc_issue_els_plogi(vport, ndlp->nlp_DID, 0);
@@ -2729,14 +2676,14 @@ lpfc_rcv_prli_npr_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	stat.un.b.lsRjtRsnCodeExp = LSEXP_NOTHING_MORE;
 	lpfc_els_rsp_reject(vport, stat.un.lsRjtError, cmdiocb, ndlp, NULL);
 
-	if (!(ndlp->nlp_flag & NLP_DELAY_TMO)) {
+	if (!test_bit(NLP_DELAY_TMO, &ndlp->nlp_flag)) {
 		/*
 		 * ADISC nodes will be handled in regular discovery path after
 		 * receiving response from NS.
 		 *
 		 * For other nodes, Send PLOGI to trigger an implicit LOGO.
 		 */
-		if (!(ndlp->nlp_flag & NLP_NPR_ADISC)) {
+		if (!test_bit(NLP_NPR_ADISC, &ndlp->nlp_flag)) {
 			ndlp->nlp_prev_state = NLP_STE_NPR_NODE;
 			lpfc_nlp_set_state(vport, ndlp, NLP_STE_PLOGI_ISSUE);
 			lpfc_issue_els_plogi(vport, ndlp->nlp_DID, 0);
@@ -2767,15 +2714,15 @@ lpfc_rcv_padisc_npr_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	 * or discovery in progress for this node. Starting discovery
 	 * here will affect the counting of discovery threads.
 	 */
-	if (!(ndlp->nlp_flag & NLP_DELAY_TMO) &&
-	    !(ndlp->nlp_flag & NLP_NPR_2B_DISC)) {
+	if (!test_bit(NLP_DELAY_TMO, &ndlp->nlp_flag) &&
+	    !test_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag)) {
 		/*
 		 * ADISC nodes will be handled in regular discovery path after
 		 * receiving response from NS.
 		 *
 		 * For other nodes, Send PLOGI to trigger an implicit LOGO.
 		 */
-		if (!(ndlp->nlp_flag & NLP_NPR_ADISC)) {
+		if (!test_bit(NLP_NPR_ADISC, &ndlp->nlp_flag)) {
 			ndlp->nlp_prev_state = NLP_STE_NPR_NODE;
 			lpfc_nlp_set_state(vport, ndlp, NLP_STE_PLOGI_ISSUE);
 			lpfc_issue_els_plogi(vport, ndlp->nlp_DID, 0);
@@ -2790,24 +2737,18 @@ lpfc_rcv_prlo_npr_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 {
 	struct lpfc_iocbq *cmdiocb = (struct lpfc_iocbq *) arg;
 
-	spin_lock_irq(&ndlp->lock);
-	ndlp->nlp_flag |= NLP_LOGO_ACC;
-	spin_unlock_irq(&ndlp->lock);
+	set_bit(NLP_LOGO_ACC, &ndlp->nlp_flag);
 
 	lpfc_els_rsp_acc(vport, ELS_CMD_ACC, cmdiocb, ndlp, NULL);
 
-	if ((ndlp->nlp_flag & NLP_DELAY_TMO) == 0) {
+	if (!test_bit(NLP_DELAY_TMO, &ndlp->nlp_flag)) {
 		mod_timer(&ndlp->nlp_delayfunc,
 			  jiffies + msecs_to_jiffies(1000 * 1));
-		spin_lock_irq(&ndlp->lock);
-		ndlp->nlp_flag |= NLP_DELAY_TMO;
-		ndlp->nlp_flag &= ~NLP_NPR_ADISC;
-		spin_unlock_irq(&ndlp->lock);
+		set_bit(NLP_DELAY_TMO, &ndlp->nlp_flag);
+		clear_bit(NLP_NPR_ADISC, &ndlp->nlp_flag);
 		ndlp->nlp_last_elscmd = ELS_CMD_PLOGI;
 	} else {
-		spin_lock_irq(&ndlp->lock);
-		ndlp->nlp_flag &= ~NLP_NPR_ADISC;
-		spin_unlock_irq(&ndlp->lock);
+		clear_bit(NLP_NPR_ADISC, &ndlp->nlp_flag);
 	}
 	return ndlp->nlp_state;
 }
@@ -2844,7 +2785,7 @@ lpfc_cmpl_prli_npr_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 
 	ulp_status = get_job_ulpstatus(phba, rspiocb);
 
-	if (ulp_status && (ndlp->nlp_flag & NLP_NODEV_REMOVE)) {
+	if (ulp_status && test_bit(NLP_NODEV_REMOVE, &ndlp->nlp_flag)) {
 		lpfc_drop_node(vport, ndlp);
 		return NLP_STE_FREED_NODE;
 	}
@@ -2877,7 +2818,7 @@ lpfc_cmpl_adisc_npr_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 
 	ulp_status = get_job_ulpstatus(phba, rspiocb);
 
-	if (ulp_status && (ndlp->nlp_flag & NLP_NODEV_REMOVE)) {
+	if (ulp_status && test_bit(NLP_NODEV_REMOVE, &ndlp->nlp_flag)) {
 		lpfc_drop_node(vport, ndlp);
 		return NLP_STE_FREED_NODE;
 	}
@@ -2896,12 +2837,11 @@ lpfc_cmpl_reglogin_npr_node(struct lpfc_vport *vport,
 		/* SLI4 ports have preallocated logical rpis. */
 		if (vport->phba->sli_rev < LPFC_SLI_REV4)
 			ndlp->nlp_rpi = mb->un.varWords[0];
-		ndlp->nlp_flag |= NLP_RPI_REGISTERED;
-		if (ndlp->nlp_flag & NLP_LOGO_ACC) {
+		set_bit(NLP_RPI_REGISTERED, &ndlp->nlp_flag);
+		if (test_bit(NLP_LOGO_ACC, &ndlp->nlp_flag))
 			lpfc_unreg_rpi(vport, ndlp);
-		}
 	} else {
-		if (ndlp->nlp_flag & NLP_NODEV_REMOVE) {
+		if (test_bit(NLP_NODEV_REMOVE, &ndlp->nlp_flag)) {
 			lpfc_drop_node(vport, ndlp);
 			return NLP_STE_FREED_NODE;
 		}
@@ -2913,10 +2853,8 @@ static uint32_t
 lpfc_device_rm_npr_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 			void *arg, uint32_t evt)
 {
-	if (ndlp->nlp_flag & NLP_NPR_2B_DISC) {
-		spin_lock_irq(&ndlp->lock);
-		ndlp->nlp_flag |= NLP_NODEV_REMOVE;
-		spin_unlock_irq(&ndlp->lock);
+	if (test_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag)) {
+		set_bit(NLP_NODEV_REMOVE, &ndlp->nlp_flag);
 		return ndlp->nlp_state;
 	}
 	lpfc_drop_node(vport, ndlp);
@@ -2932,8 +2870,9 @@ lpfc_device_recov_npr_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 		return ndlp->nlp_state;
 
 	lpfc_cancel_retry_delay_tmo(vport, ndlp);
+	clear_bit(NLP_NODEV_REMOVE, &ndlp->nlp_flag);
+	clear_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag);
 	spin_lock_irq(&ndlp->lock);
-	ndlp->nlp_flag &= ~(NLP_NODEV_REMOVE | NLP_NPR_2B_DISC);
 	ndlp->nlp_fc4_type &= ~(NLP_FC4_FCP | NLP_FC4_NVME);
 	spin_unlock_irq(&ndlp->lock);
 	return ndlp->nlp_state;
@@ -3146,7 +3085,7 @@ lpfc_disc_state_machine(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	/* DSM in event <evt> on NPort <nlp_DID> in state <cur_state> */
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY,
 			 "0211 DSM in event x%x on NPort x%x in "
-			 "state %d rpi x%x Data: x%x x%x\n",
+			 "state %d rpi x%x Data: x%lx x%x\n",
 			 evt, ndlp->nlp_DID, cur_state, ndlp->nlp_rpi,
 			 ndlp->nlp_flag, data1);
 
@@ -3163,12 +3102,12 @@ lpfc_disc_state_machine(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 			((uint32_t)ndlp->nlp_type));
 		lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY,
 			 "0212 DSM out state %d on NPort x%x "
-			 "rpi x%x Data: x%x x%x\n",
+			 "rpi x%x Data: x%lx x%x\n",
 			 rc, ndlp->nlp_DID, ndlp->nlp_rpi, ndlp->nlp_flag,
 			 data1);
 
 		lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_DSM,
-			"DSM out:         ste:%d did:x%x flg:x%x",
+			"DSM out:         ste:%d did:x%x flg:x%lx",
 			rc, ndlp->nlp_DID, ndlp->nlp_flag);
 		/* Decrement the ndlp reference count held for this function */
 		lpfc_nlp_put(ndlp);
diff --git a/drivers/scsi/lpfc/lpfc_nvme.c b/drivers/scsi/lpfc/lpfc_nvme.c
index fec23c723730..e9d9884830f3 100644
--- a/drivers/scsi/lpfc/lpfc_nvme.c
+++ b/drivers/scsi/lpfc/lpfc_nvme.c
@@ -1232,7 +1232,7 @@ lpfc_nvme_prep_io_cmd(struct lpfc_vport *vport,
 
 			/* Word 5 */
 			if ((phba->cfg_nvme_enable_fb) &&
-			    (pnode->nlp_flag & NLP_FIRSTBURST)) {
+			    test_bit(NLP_FIRSTBURST, &pnode->nlp_flag)) {
 				req_len = lpfc_ncmd->nvmeCmd->payload_length;
 				if (req_len < pnode->nvme_fb_size)
 					wqe->fcp_iwrite.initial_xfer_len =
@@ -2644,14 +2644,11 @@ lpfc_nvme_unregister_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 				 * reference. Check if another thread has set
 				 * NLP_DROPPED.
 				 */
-				spin_lock_irq(&ndlp->lock);
-				if (!(ndlp->nlp_flag & NLP_DROPPED)) {
-					ndlp->nlp_flag |= NLP_DROPPED;
-					spin_unlock_irq(&ndlp->lock);
+				if (!test_and_set_bit(NLP_DROPPED,
+						      &ndlp->nlp_flag)) {
 					lpfc_nlp_put(ndlp);
 					return;
 				}
-				spin_unlock_irq(&ndlp->lock);
 			}
 		}
 	}
diff --git a/drivers/scsi/lpfc/lpfc_nvmet.c b/drivers/scsi/lpfc/lpfc_nvmet.c
index 55c3e2c2bf8f..e6c9112a8862 100644
--- a/drivers/scsi/lpfc/lpfc_nvmet.c
+++ b/drivers/scsi/lpfc/lpfc_nvmet.c
@@ -2854,7 +2854,7 @@ lpfc_nvmet_prep_fcp_wqe(struct lpfc_hba *phba,
 			/* In template ar=1 wqes=0 sup=0 irsp=0 irsplen=0 */
 
 			if (rsp->rsplen == LPFC_NVMET_SUCCESS_LEN) {
-				if (ndlp->nlp_flag & NLP_SUPPRESS_RSP)
+				if (test_bit(NLP_SUPPRESS_RSP, &ndlp->nlp_flag))
 					bf_set(wqe_sup,
 					       &wqe->fcp_tsend.wqe_com, 1);
 			} else {
diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c
index 11c974bffa72..67e089881181 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.c
+++ b/drivers/scsi/lpfc/lpfc_scsi.c
@@ -390,6 +390,10 @@ lpfc_sli4_vport_delete_fcp_xri_aborted(struct lpfc_vport *vport)
 	if (!(vport->cfg_enable_fc4_type & LPFC_ENABLE_FCP))
 		return;
 
+	/* may be called before queues established if hba_setup fails */
+	if (!phba->sli4_hba.hdwq)
+		return;
+
 	spin_lock_irqsave(&phba->hbalock, iflag);
 	for (idx = 0; idx < phba->cfg_hdw_queue; idx++) {
 		qp = &phba->sli4_hba.hdwq[idx];
@@ -4629,7 +4633,7 @@ static int lpfc_scsi_prep_cmnd_buf_s3(struct lpfc_vport *vport,
 			iocb_cmd->ulpCommand = CMD_FCP_IWRITE64_CR;
 			iocb_cmd->ulpPU = PARM_READ_CHECK;
 			if (vport->cfg_first_burst_size &&
-			    (pnode->nlp_flag & NLP_FIRSTBURST)) {
+			    test_bit(NLP_FIRSTBURST, &pnode->nlp_flag)) {
 				u32 xrdy_len;
 
 				fcpdl = scsi_bufflen(scsi_cmnd);
@@ -5829,7 +5833,7 @@ lpfc_send_taskmgmt(struct lpfc_vport *vport, struct fc_rport *rport,
 
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_FCP,
 			 "0702 Issue %s to TGT %d LUN %llu "
-			 "rpi x%x nlp_flag x%x Data: x%x x%x\n",
+			 "rpi x%x nlp_flag x%lx Data: x%x x%x\n",
 			 lpfc_taskmgmt_name(task_mgmt_cmd), tgt_id, lun_id,
 			 pnode->nlp_rpi, pnode->nlp_flag, iocbq->sli4_xritag,
 			 iocbq->cmd_flag);
@@ -6094,8 +6098,8 @@ lpfc_target_reset_handler(struct scsi_cmnd *cmnd)
 		lpfc_printf_vlog(vport, KERN_ERR, LOG_TRACE_EVENT,
 			"0722 Target Reset rport failure: rdata x%px\n", rdata);
 		if (pnode) {
+			clear_bit(NLP_NPR_ADISC, &pnode->nlp_flag);
 			spin_lock_irqsave(&pnode->lock, flags);
-			pnode->nlp_flag &= ~NLP_NPR_ADISC;
 			pnode->nlp_fcp_info &= ~NLP_FCP_2_DEVICE;
 			spin_unlock_irqrestore(&pnode->lock, flags);
 		}
@@ -6124,7 +6128,7 @@ lpfc_target_reset_handler(struct scsi_cmnd *cmnd)
 		    !pnode->logo_waitq) {
 			pnode->logo_waitq = &waitq;
 			pnode->nlp_fcp_info &= ~NLP_FCP_2_DEVICE;
-			pnode->nlp_flag |= NLP_ISSUE_LOGO;
+			set_bit(NLP_ISSUE_LOGO, &pnode->nlp_flag);
 			pnode->save_flags |= NLP_WAIT_FOR_LOGO;
 			spin_unlock_irqrestore(&pnode->lock, flags);
 			lpfc_unreg_rpi(vport, pnode);
diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index 6748fba48a07..c4acf594286e 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -2842,27 +2842,6 @@ lpfc_sli_wake_mbox_wait(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmboxq)
 	return;
 }
 
-static void
-__lpfc_sli_rpi_release(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
-{
-	unsigned long iflags;
-
-	if (ndlp->nlp_flag & NLP_RELEASE_RPI) {
-		lpfc_sli4_free_rpi(vport->phba, ndlp->nlp_rpi);
-		spin_lock_irqsave(&ndlp->lock, iflags);
-		ndlp->nlp_flag &= ~NLP_RELEASE_RPI;
-		ndlp->nlp_rpi = LPFC_RPI_ALLOC_ERROR;
-		spin_unlock_irqrestore(&ndlp->lock, iflags);
-	}
-	ndlp->nlp_flag &= ~NLP_UNREG_INP;
-}
-
-void
-lpfc_sli_rpi_release(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
-{
-	__lpfc_sli_rpi_release(vport, ndlp);
-}
-
 /**
  * lpfc_sli_def_mbox_cmpl - Default mailbox completion handler
  * @phba: Pointer to HBA context object.
@@ -2932,18 +2911,18 @@ lpfc_sli_def_mbox_cmpl(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 				vport,
 				KERN_INFO, LOG_MBOX | LOG_DISCOVERY,
 				"1438 UNREG cmpl deferred mbox x%x "
-				"on NPort x%x Data: x%x x%x x%px x%lx x%x\n",
+				"on NPort x%x Data: x%lx x%x x%px x%lx x%x\n",
 				ndlp->nlp_rpi, ndlp->nlp_DID,
 				ndlp->nlp_flag, ndlp->nlp_defer_did,
 				ndlp, vport->load_flag, kref_read(&ndlp->kref));
 
-			if ((ndlp->nlp_flag & NLP_UNREG_INP) &&
-			    (ndlp->nlp_defer_did != NLP_EVT_NOTHING_PENDING)) {
-				ndlp->nlp_flag &= ~NLP_UNREG_INP;
+			if (test_bit(NLP_UNREG_INP, &ndlp->nlp_flag) &&
+			    ndlp->nlp_defer_did != NLP_EVT_NOTHING_PENDING) {
+				clear_bit(NLP_UNREG_INP, &ndlp->nlp_flag);
 				ndlp->nlp_defer_did = NLP_EVT_NOTHING_PENDING;
 				lpfc_issue_els_plogi(vport, ndlp->nlp_DID, 0);
 			} else {
-				__lpfc_sli_rpi_release(vport, ndlp);
+				clear_bit(NLP_UNREG_INP, &ndlp->nlp_flag);
 			}
 
 			/* The unreg_login mailbox is complete and had a
@@ -2991,6 +2970,7 @@ lpfc_sli4_unreg_rpi_cmpl_clr(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 {
 	struct lpfc_vport  *vport = pmb->vport;
 	struct lpfc_nodelist *ndlp;
+	bool unreg_inp;
 
 	ndlp = pmb->ctx_ndlp;
 	if (pmb->u.mb.mbxCommand == MBX_UNREG_LOGIN) {
@@ -3003,20 +2983,26 @@ lpfc_sli4_unreg_rpi_cmpl_clr(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 					 vport, KERN_INFO,
 					 LOG_MBOX | LOG_SLI | LOG_NODE,
 					 "0010 UNREG_LOGIN vpi:x%x "
-					 "rpi:%x DID:%x defer x%x flg x%x "
+					 "rpi:%x DID:%x defer x%x flg x%lx "
 					 "x%px\n",
 					 vport->vpi, ndlp->nlp_rpi,
 					 ndlp->nlp_DID, ndlp->nlp_defer_did,
 					 ndlp->nlp_flag,
 					 ndlp);
-				ndlp->nlp_flag &= ~NLP_LOGO_ACC;
+
+				/* Cleanup the nlp_flag now that the UNREG RPI
+				 * has completed.
+				 */
+				unreg_inp = test_and_clear_bit(NLP_UNREG_INP,
+							       &ndlp->nlp_flag);
+				clear_bit(NLP_LOGO_ACC, &ndlp->nlp_flag);
 
 				/* Check to see if there are any deferred
 				 * events to process
 				 */
-				if ((ndlp->nlp_flag & NLP_UNREG_INP) &&
-				    (ndlp->nlp_defer_did !=
-				    NLP_EVT_NOTHING_PENDING)) {
+				if (unreg_inp &&
+				    ndlp->nlp_defer_did !=
+				    NLP_EVT_NOTHING_PENDING) {
 					lpfc_printf_vlog(
 						vport, KERN_INFO,
 						LOG_MBOX | LOG_SLI | LOG_NODE,
@@ -3025,14 +3011,12 @@ lpfc_sli4_unreg_rpi_cmpl_clr(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 						"NPort x%x Data: x%x x%px\n",
 						ndlp->nlp_rpi, ndlp->nlp_DID,
 						ndlp->nlp_defer_did, ndlp);
-					ndlp->nlp_flag &= ~NLP_UNREG_INP;
 					ndlp->nlp_defer_did =
 						NLP_EVT_NOTHING_PENDING;
 					lpfc_issue_els_plogi(
 						vport, ndlp->nlp_DID, 0);
-				} else {
-					__lpfc_sli_rpi_release(vport, ndlp);
 				}
+
 				lpfc_nlp_put(ndlp);
 			}
 		}
@@ -6020,9 +6004,9 @@ lpfc_sli4_get_ctl_attr(struct lpfc_hba *phba)
 	phba->sli4_hba.flash_id = bf_get(lpfc_cntl_attr_flash_id, cntl_attr);
 	phba->sli4_hba.asic_rev = bf_get(lpfc_cntl_attr_asic_rev, cntl_attr);
 
-	memset(phba->BIOSVersion, 0, sizeof(phba->BIOSVersion));
-	strlcat(phba->BIOSVersion, (char *)cntl_attr->bios_ver_str,
+	memcpy(phba->BIOSVersion, cntl_attr->bios_ver_str,
 		sizeof(phba->BIOSVersion));
+	phba->BIOSVersion[sizeof(phba->BIOSVersion) - 1] = '\0';
 
 	lpfc_printf_log(phba, KERN_INFO, LOG_SLI,
 			"3086 lnk_type:%d, lnk_numb:%d, bios_ver:%s, "
@@ -8750,6 +8734,7 @@ lpfc_sli4_hba_setup(struct lpfc_hba *phba)
 				lpfc_sli_config_mbox_opcode_get(
 					phba, mboxq),
 				rc, dd);
+
 	/*
 	 * Allocate all resources (xri,rpi,vpi,vfi) now.  Subsequent
 	 * calls depends on these resources to complete port setup.
@@ -8762,6 +8747,8 @@ lpfc_sli4_hba_setup(struct lpfc_hba *phba)
 		goto out_free_mbox;
 	}
 
+	lpfc_sli4_node_rpi_restore(phba);
+
 	lpfc_set_host_data(phba, mboxq);
 
 	rc = lpfc_sli_issue_mbox(phba, mboxq, MBX_POLL);
@@ -8949,7 +8936,6 @@ lpfc_sli4_hba_setup(struct lpfc_hba *phba)
 		rc = -ENODEV;
 		goto out_free_iocblist;
 	}
-	lpfc_sli4_node_prep(phba);
 
 	if (!test_bit(HBA_FCOE_MODE, &phba->hba_flag)) {
 		if ((phba->nvmet_support == 0) || (phba->cfg_nvmet_mrq == 1)) {
@@ -14354,9 +14340,7 @@ lpfc_sli4_sp_handle_mbox_event(struct lpfc_hba *phba, struct lpfc_mcqe *mcqe)
 			 * an unsolicited PLOGI from the same NPortId from
 			 * starting another mailbox transaction.
 			 */
-			spin_lock_irqsave(&ndlp->lock, iflags);
-			ndlp->nlp_flag |= NLP_UNREG_INP;
-			spin_unlock_irqrestore(&ndlp->lock, iflags);
+			set_bit(NLP_UNREG_INP, &ndlp->nlp_flag);
 			lpfc_unreg_login(phba, vport->vpi,
 					 pmbox->un.varWords[0], pmb);
 			pmb->mbox_cmpl = lpfc_mbx_cmpl_dflt_rpi;
@@ -19105,9 +19089,9 @@ lpfc_sli4_seq_abort_rsp(struct lpfc_vport *vport,
 	 * to free ndlp when transmit completes
 	 */
 	if (ndlp->nlp_state == NLP_STE_UNUSED_NODE &&
-	    !(ndlp->nlp_flag & NLP_DROPPED) &&
+	    !test_bit(NLP_DROPPED, &ndlp->nlp_flag) &&
 	    !(ndlp->fc4_xpt_flags & (NVME_XPT_REGD | SCSI_XPT_REGD))) {
-		ndlp->nlp_flag |= NLP_DROPPED;
+		set_bit(NLP_DROPPED, &ndlp->nlp_flag);
 		lpfc_nlp_put(ndlp);
 	}
 }
@@ -21125,11 +21109,7 @@ lpfc_cleanup_pending_mbox(struct lpfc_vport *vport)
 				/* Unregister the RPI when mailbox complete */
 				mb->mbox_flag |= LPFC_MBX_IMED_UNREG;
 				restart_loop = 1;
-				spin_unlock_irq(&phba->hbalock);
-				spin_lock(&ndlp->lock);
-				ndlp->nlp_flag &= ~NLP_IGNR_REG_CMPL;
-				spin_unlock(&ndlp->lock);
-				spin_lock_irq(&phba->hbalock);
+				clear_bit(NLP_IGNR_REG_CMPL, &ndlp->nlp_flag);
 				break;
 			}
 		}
@@ -21144,9 +21124,7 @@ lpfc_cleanup_pending_mbox(struct lpfc_vport *vport)
 			ndlp = mb->ctx_ndlp;
 			mb->ctx_ndlp = NULL;
 			if (ndlp) {
-				spin_lock(&ndlp->lock);
-				ndlp->nlp_flag &= ~NLP_IGNR_REG_CMPL;
-				spin_unlock(&ndlp->lock);
+				clear_bit(NLP_IGNR_REG_CMPL, &ndlp->nlp_flag);
 				lpfc_nlp_put(ndlp);
 			}
 		}
@@ -21155,9 +21133,7 @@ lpfc_cleanup_pending_mbox(struct lpfc_vport *vport)
 
 	/* Release the ndlp with the cleaned-up active mailbox command */
 	if (act_mbx_ndlp) {
-		spin_lock(&act_mbx_ndlp->lock);
-		act_mbx_ndlp->nlp_flag &= ~NLP_IGNR_REG_CMPL;
-		spin_unlock(&act_mbx_ndlp->lock);
+		clear_bit(NLP_IGNR_REG_CMPL, &act_mbx_ndlp->nlp_flag);
 		lpfc_nlp_put(act_mbx_ndlp);
 	}
 }
diff --git a/drivers/scsi/lpfc/lpfc_vport.c b/drivers/scsi/lpfc/lpfc_vport.c
index 7a4d4d8e2ad5..9e0e35763377 100644
--- a/drivers/scsi/lpfc/lpfc_vport.c
+++ b/drivers/scsi/lpfc/lpfc_vport.c
@@ -496,7 +496,7 @@ lpfc_send_npiv_logo(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 	    !ndlp->logo_waitq) {
 		ndlp->logo_waitq = &waitq;
 		ndlp->nlp_fcp_info &= ~NLP_FCP_2_DEVICE;
-		ndlp->nlp_flag |= NLP_ISSUE_LOGO;
+		set_bit(NLP_ISSUE_LOGO, &ndlp->nlp_flag);
 		ndlp->save_flags |= NLP_WAIT_FOR_LOGO;
 	}
 	spin_unlock_irq(&ndlp->lock);
@@ -515,8 +515,8 @@ lpfc_send_npiv_logo(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 	}
 
 	/* Error - clean up node flags. */
+	clear_bit(NLP_ISSUE_LOGO, &ndlp->nlp_flag);
 	spin_lock_irq(&ndlp->lock);
-	ndlp->nlp_flag &= ~NLP_ISSUE_LOGO;
 	ndlp->save_flags &= ~NLP_WAIT_FOR_LOGO;
 	spin_unlock_irq(&ndlp->lock);
 
@@ -708,7 +708,7 @@ lpfc_vport_delete(struct fc_vport *fc_vport)
 
 			lpfc_printf_vlog(vport, KERN_INFO, LOG_VPORT | LOG_ELS,
 					 "1829 DA_ID issue status %d. "
-					 "SFlag x%x NState x%x, NFlag x%x "
+					 "SFlag x%x NState x%x, NFlag x%lx "
 					 "Rpi x%x\n",
 					 rc, ndlp->save_flags, ndlp->nlp_state,
 					 ndlp->nlp_flag, ndlp->nlp_rpi);
diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
index 50f1dcb6d584..8a44e01ebf9b 100644
--- a/drivers/scsi/megaraid/megaraid_sas_base.c
+++ b/drivers/scsi/megaraid/megaraid_sas_base.c
@@ -37,7 +37,6 @@
 #include <linux/poll.h>
 #include <linux/vmalloc.h>
 #include <linux/irq_poll.h>
-#include <linux/blk-mq-pci.h>
 
 #include <scsi/scsi.h>
 #include <scsi/scsi_cmnd.h>
@@ -2104,6 +2103,9 @@ static int megasas_device_configure(struct scsi_device *sdev,
 	/* This sdev property may change post OCR */
 	megasas_set_dynamic_target_properties(sdev, lim, is_target_prop);
 
+	if (!MEGASAS_IS_LOGICAL(sdev))
+		sdev->no_vpd_size = 1;
+
 	mutex_unlock(&instance->reset_mutex);
 
 	return 0;
@@ -3193,7 +3195,7 @@ static void megasas_map_queues(struct Scsi_Host *shost)
 	map = &shost->tag_set.map[HCTX_TYPE_DEFAULT];
 	map->nr_queues = instance->msix_vectors - offset;
 	map->queue_offset = 0;
-	blk_mq_pci_map_queues(map, instance->pdev, offset);
+	blk_mq_map_hw_queues(map, &instance->pdev->dev, offset);
 	qoff += map->nr_queues;
 	offset += map->nr_queues;
 
@@ -3663,8 +3665,10 @@ megasas_complete_cmd(struct megasas_instance *instance, struct megasas_cmd *cmd,
 
 		case MFI_STAT_SCSI_IO_FAILED:
 		case MFI_STAT_LD_INIT_IN_PROGRESS:
-			cmd->scmd->result =
-			    (DID_ERROR << 16) | hdr->scsi_status;
+			if (hdr->scsi_status == 0xf0)
+				cmd->scmd->result = (DID_ERROR << 16) | SAM_STAT_CHECK_CONDITION;
+			else
+				cmd->scmd->result = (DID_ERROR << 16) | hdr->scsi_status;
 			break;
 
 		case MFI_STAT_SCSI_DONE_WITH_ERROR:
@@ -5906,7 +5910,11 @@ megasas_set_high_iops_queue_affinity_and_hint(struct megasas_instance *instance)
 	const struct cpumask *mask;
 
 	if (instance->perf_mode == MR_BALANCED_PERF_MODE) {
-		mask = cpumask_of_node(dev_to_node(&instance->pdev->dev));
+		int nid = dev_to_node(&instance->pdev->dev);
+
+		if (nid == NUMA_NO_NODE)
+			nid = 0;
+		mask = cpumask_of_node(nid);
 
 		for (i = 0; i < instance->low_latency_index_start; i++) {
 			irq = pci_irq_vector(instance->pdev, i);
diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.c b/drivers/scsi/megaraid/megaraid_sas_fusion.c
index 1eec23da28e2..1eea4df9e47d 100644
--- a/drivers/scsi/megaraid/megaraid_sas_fusion.c
+++ b/drivers/scsi/megaraid/megaraid_sas_fusion.c
@@ -2043,7 +2043,10 @@ map_cmd_status(struct fusion_context *fusion,
 
 	case MFI_STAT_SCSI_IO_FAILED:
 	case MFI_STAT_LD_INIT_IN_PROGRESS:
-		scmd->result = (DID_ERROR << 16) | ext_status;
+		if (ext_status == 0xf0)
+			scmd->result = (DID_ERROR << 16) | SAM_STAT_CHECK_CONDITION;
+		else
+			scmd->result = (DID_ERROR << 16) | ext_status;
 		break;
 
 	case MFI_STAT_SCSI_DONE_WITH_ERROR:
diff --git a/drivers/scsi/mpi3mr/mpi3mr.h b/drivers/scsi/mpi3mr/mpi3mr.h
index 1e715fd65a7d..ab7c5f1fc041 100644
--- a/drivers/scsi/mpi3mr/mpi3mr.h
+++ b/drivers/scsi/mpi3mr/mpi3mr.h
@@ -12,7 +12,6 @@
 
 #include <linux/blkdev.h>
 #include <linux/blk-mq.h>
-#include <linux/blk-mq-pci.h>
 #include <linux/delay.h>
 #include <linux/dmapool.h>
 #include <linux/errno.h>
@@ -81,13 +80,14 @@ extern atomic64_t event_counter;
 
 /* Admin queue management definitions */
 #define MPI3MR_ADMIN_REQ_Q_SIZE		(2 * MPI3MR_PAGE_SIZE_4K)
-#define MPI3MR_ADMIN_REPLY_Q_SIZE	(4 * MPI3MR_PAGE_SIZE_4K)
+#define MPI3MR_ADMIN_REPLY_Q_SIZE	(8 * MPI3MR_PAGE_SIZE_4K)
 #define MPI3MR_ADMIN_REQ_FRAME_SZ	128
 #define MPI3MR_ADMIN_REPLY_FRAME_SZ	16
 
 /* Operational queue management definitions */
 #define MPI3MR_OP_REQ_Q_QD		512
 #define MPI3MR_OP_REP_Q_QD		1024
+#define MPI3MR_OP_REP_Q_QD2K		2048
 #define MPI3MR_OP_REP_Q_QD4K		4096
 #define MPI3MR_OP_REQ_Q_SEG_SIZE	4096
 #define MPI3MR_OP_REP_Q_SEG_SIZE	4096
@@ -329,6 +329,7 @@ enum mpi3mr_reset_reason {
 #define MPI3MR_RESET_REASON_OSTYPE_SHIFT	28
 #define MPI3MR_RESET_REASON_IOCNUM_SHIFT	20
 
+
 /* Queue type definitions */
 enum queue_type {
 	MPI3MR_DEFAULT_QUEUE = 0,
@@ -388,6 +389,7 @@ struct mpi3mr_ioc_facts {
 	u16 max_msix_vectors;
 	u8 personality;
 	u8 dma_mask;
+	bool max_req_limit;
 	u8 protocol_flags;
 	u8 sge_mod_mask;
 	u8 sge_mod_value;
@@ -457,6 +459,8 @@ struct op_req_qinfo {
  * @enable_irq_poll: Flag to indicate polling is enabled
  * @in_use: Queue is handled by poll/ISR
  * @qtype: Type of queue (types defined in enum queue_type)
+ * @qfull_watermark: Watermark defined in reply queue to avoid
+ *                    reply queue full
  */
 struct op_reply_qinfo {
 	u16 ci;
@@ -472,6 +476,7 @@ struct op_reply_qinfo {
 	bool enable_irq_poll;
 	atomic_t in_use;
 	enum queue_type qtype;
+	u16 qfull_watermark;
 };
 
 /**
@@ -1091,6 +1096,7 @@ struct scmd_priv {
  * @ts_update_interval: Timestamp update interval
  * @reset_in_progress: Reset in progress flag
  * @unrecoverable: Controller unrecoverable flag
+ * @io_admin_reset_sync: Manage state of I/O ops during an admin reset process
  * @prev_reset_result: Result of previous reset
  * @reset_mutex: Controller reset mutex
  * @reset_waitq: Controller reset  wait queue
@@ -1154,6 +1160,8 @@ struct scmd_priv {
  * @snapdump_trigger_active: Snapdump trigger active flag
  * @pci_err_recovery: PCI error recovery in progress
  * @block_on_pci_err: Block IO during PCI error recovery
+ * @reply_qfull_count: Occurences of reply queue full avoidance kicking-in
+ * @prevent_reply_qfull: Enable reply queue prevention
  */
 struct mpi3mr_ioc {
 	struct list_head list;
@@ -1277,6 +1285,7 @@ struct mpi3mr_ioc {
 	u16 ts_update_interval;
 	u8 reset_in_progress;
 	u8 unrecoverable;
+	u8 io_admin_reset_sync;
 	int prev_reset_result;
 	struct mutex reset_mutex;
 	wait_queue_head_t reset_waitq;
@@ -1352,6 +1361,8 @@ struct mpi3mr_ioc {
 	bool fw_release_trigger_active;
 	bool pci_err_recovery;
 	bool block_on_pci_err;
+	atomic_t reply_qfull_count;
+	bool prevent_reply_qfull;
 };
 
 /**
diff --git a/drivers/scsi/mpi3mr/mpi3mr_app.c b/drivers/scsi/mpi3mr/mpi3mr_app.c
index 10b8e4dc64f8..1532436f0f3a 100644
--- a/drivers/scsi/mpi3mr/mpi3mr_app.c
+++ b/drivers/scsi/mpi3mr/mpi3mr_app.c
@@ -2951,6 +2951,7 @@ void mpi3mr_bsg_init(struct mpi3mr_ioc *mrioc)
 		.max_hw_sectors		= MPI3MR_MAX_APP_XFER_SECTORS,
 		.max_segments		= MPI3MR_MAX_APP_XFER_SEGMENTS,
 	};
+	struct request_queue *q;
 
 	device_initialize(bsg_dev);
 
@@ -2966,14 +2967,17 @@ void mpi3mr_bsg_init(struct mpi3mr_ioc *mrioc)
 		return;
 	}
 
-	mrioc->bsg_queue = bsg_setup_queue(bsg_dev, dev_name(bsg_dev), &lim,
+	q = bsg_setup_queue(bsg_dev, dev_name(bsg_dev), &lim,
 			mpi3mr_bsg_request, NULL, 0);
-	if (IS_ERR(mrioc->bsg_queue)) {
+	if (IS_ERR(q)) {
 		ioc_err(mrioc, "%s: bsg registration failed\n",
 		    dev_name(bsg_dev));
 		device_del(bsg_dev);
 		put_device(bsg_dev);
+		return;
 	}
+
+	mrioc->bsg_queue = q;
 }
 
 /**
@@ -3057,6 +3061,29 @@ reply_queue_count_show(struct device *dev, struct device_attribute *attr,
 static DEVICE_ATTR_RO(reply_queue_count);
 
 /**
+ * reply_qfull_count_show - Show reply qfull count
+ * @dev: class device
+ * @attr: Device attributes
+ * @buf: Buffer to copy
+ *
+ * Retrieves the current value of the reply_qfull_count from the mrioc structure and
+ * formats it as a string for display.
+ *
+ * Return: sysfs_emit() return
+ */
+static ssize_t
+reply_qfull_count_show(struct device *dev, struct device_attribute *attr,
+			char *buf)
+{
+	struct Scsi_Host *shost = class_to_shost(dev);
+	struct mpi3mr_ioc *mrioc = shost_priv(shost);
+
+	return sysfs_emit(buf, "%u\n", atomic_read(&mrioc->reply_qfull_count));
+}
+
+static DEVICE_ATTR_RO(reply_qfull_count);
+
+/**
  * logging_level_show - Show controller debug level
  * @dev: class device
  * @attr: Device attributes
@@ -3148,6 +3175,7 @@ static struct attribute *mpi3mr_host_attrs[] = {
 	&dev_attr_fw_queue_depth.attr,
 	&dev_attr_op_req_q_count.attr,
 	&dev_attr_reply_queue_count.attr,
+	&dev_attr_reply_qfull_count.attr,
 	&dev_attr_logging_level.attr,
 	&dev_attr_adp_state.attr,
 	NULL,
diff --git a/drivers/scsi/mpi3mr/mpi3mr_fw.c b/drivers/scsi/mpi3mr/mpi3mr_fw.c
index 5ed31fe57474..604f37e5c0c3 100644
--- a/drivers/scsi/mpi3mr/mpi3mr_fw.c
+++ b/drivers/scsi/mpi3mr/mpi3mr_fw.c
@@ -17,7 +17,7 @@ static void mpi3mr_process_factsdata(struct mpi3mr_ioc *mrioc,
 	struct mpi3_ioc_facts_data *facts_data);
 static void mpi3mr_pel_wait_complete(struct mpi3mr_ioc *mrioc,
 	struct mpi3mr_drv_cmd *drv_cmd);
-
+static int mpi3mr_check_op_admin_proc(struct mpi3mr_ioc *mrioc);
 static int poll_queues;
 module_param(poll_queues, int, 0444);
 MODULE_PARM_DESC(poll_queues, "Number of queues for io_uring poll mode. (Range 1 - 126)");
@@ -174,6 +174,9 @@ static void mpi3mr_print_event_data(struct mpi3mr_ioc *mrioc,
 	char *desc = NULL;
 	u16 event;
 
+	if (!(mrioc->logging_level & MPI3_DEBUG_EVENT))
+		return;
+
 	event = event_reply->event;
 
 	switch (event) {
@@ -459,7 +462,7 @@ int mpi3mr_process_admin_reply_q(struct mpi3mr_ioc *mrioc)
 	}
 
 	do {
-		if (mrioc->unrecoverable)
+		if (mrioc->unrecoverable || mrioc->io_admin_reset_sync)
 			break;
 
 		mrioc->admin_req_ci = le16_to_cpu(reply_desc->request_queue_ci);
@@ -554,7 +557,7 @@ int mpi3mr_process_op_reply_q(struct mpi3mr_ioc *mrioc,
 	}
 
 	do {
-		if (mrioc->unrecoverable)
+		if (mrioc->unrecoverable || mrioc->io_admin_reset_sync)
 			break;
 
 		req_q_idx = le16_to_cpu(reply_desc->request_queue_id) - 1;
@@ -563,7 +566,7 @@ int mpi3mr_process_op_reply_q(struct mpi3mr_ioc *mrioc,
 		WRITE_ONCE(op_req_q->ci, le16_to_cpu(reply_desc->request_queue_ci));
 		mpi3mr_process_op_reply_desc(mrioc, reply_desc, &reply_dma,
 		    reply_qidx);
-		atomic_dec(&op_reply_q->pend_ios);
+
 		if (reply_dma)
 			mpi3mr_repost_reply_buf(mrioc, reply_dma);
 		num_op_reply++;
@@ -2104,15 +2107,22 @@ static int mpi3mr_create_op_reply_q(struct mpi3mr_ioc *mrioc, u16 qidx)
 	}
 
 	reply_qid = qidx + 1;
-	op_reply_q->num_replies = MPI3MR_OP_REP_Q_QD;
-	if ((mrioc->pdev->device == MPI3_MFGPAGE_DEVID_SAS4116) &&
-		!mrioc->pdev->revision)
-		op_reply_q->num_replies = MPI3MR_OP_REP_Q_QD4K;
+
+	if (mrioc->pdev->device == MPI3_MFGPAGE_DEVID_SAS4116) {
+		if (mrioc->pdev->revision)
+			op_reply_q->num_replies = MPI3MR_OP_REP_Q_QD;
+		else
+			op_reply_q->num_replies = MPI3MR_OP_REP_Q_QD4K;
+	} else
+		op_reply_q->num_replies = MPI3MR_OP_REP_Q_QD2K;
+
 	op_reply_q->ci = 0;
 	op_reply_q->ephase = 1;
 	atomic_set(&op_reply_q->pend_ios, 0);
 	atomic_set(&op_reply_q->in_use, 0);
 	op_reply_q->enable_irq_poll = false;
+	op_reply_q->qfull_watermark =
+		op_reply_q->num_replies - (MPI3MR_THRESHOLD_REPLY_COUNT * 2);
 
 	if (!op_reply_q->q_segments) {
 		retval = mpi3mr_alloc_op_reply_q_segments(mrioc, qidx);
@@ -2416,8 +2426,10 @@ int mpi3mr_op_request_post(struct mpi3mr_ioc *mrioc,
 	void *segment_base_addr;
 	u16 req_sz = mrioc->facts.op_req_sz;
 	struct segments *segments = op_req_q->q_segments;
+	struct op_reply_qinfo *op_reply_q = NULL;
 
 	reply_qidx = op_req_q->reply_qid - 1;
+	op_reply_q = mrioc->op_reply_qinfo + reply_qidx;
 
 	if (mrioc->unrecoverable)
 		return -EFAULT;
@@ -2448,6 +2460,15 @@ int mpi3mr_op_request_post(struct mpi3mr_ioc *mrioc,
 		goto out;
 	}
 
+	/* Reply queue is nearing to get full, push back IOs to SML */
+	if ((mrioc->prevent_reply_qfull == true) &&
+		(atomic_read(&op_reply_q->pend_ios) >
+	     (op_reply_q->qfull_watermark))) {
+		atomic_inc(&mrioc->reply_qfull_count);
+		retval = -EAGAIN;
+		goto out;
+	}
+
 	segment_base_addr = segments[pi / op_req_q->segment_qd].segment;
 	req_entry = (u8 *)segment_base_addr +
 	    ((pi % op_req_q->segment_qd) * req_sz);
@@ -2726,7 +2747,10 @@ static void mpi3mr_watchdog_work(struct work_struct *work)
 		return;
 	}
 
-	if (mrioc->ts_update_counter++ >= mrioc->ts_update_interval) {
+	if (!(mrioc->facts.ioc_capabilities &
+		MPI3_IOCFACTS_CAPABILITY_NON_SUPERVISOR_IOC) &&
+		(mrioc->ts_update_counter++ >= mrioc->ts_update_interval)) {
+
 		mrioc->ts_update_counter = 0;
 		mpi3mr_sync_timestamp(mrioc);
 	}
@@ -3091,6 +3115,9 @@ static void mpi3mr_process_factsdata(struct mpi3mr_ioc *mrioc,
 	mrioc->facts.dma_mask = (facts_flags &
 	    MPI3_IOCFACTS_FLAGS_DMA_ADDRESS_WIDTH_MASK) >>
 	    MPI3_IOCFACTS_FLAGS_DMA_ADDRESS_WIDTH_SHIFT;
+	mrioc->facts.dma_mask = (facts_flags &
+	    MPI3_IOCFACTS_FLAGS_DMA_ADDRESS_WIDTH_MASK) >>
+	    MPI3_IOCFACTS_FLAGS_DMA_ADDRESS_WIDTH_SHIFT;
 	mrioc->facts.protocol_flags = facts_data->protocol_flags;
 	mrioc->facts.mpi_version = le32_to_cpu(facts_data->mpi_version.word);
 	mrioc->facts.max_reqs = le16_to_cpu(facts_data->max_outstanding_requests);
@@ -4214,6 +4241,9 @@ retry_init:
 		mrioc->shost->transportt = mpi3mr_transport_template;
 	}
 
+	if (mrioc->facts.max_req_limit)
+		mrioc->prevent_reply_qfull = true;
+
 	mrioc->reply_sz = mrioc->facts.reply_sz;
 
 	retval = mpi3mr_check_reset_dma_mask(mrioc);
@@ -4370,6 +4400,7 @@ retry_init:
 		goto out_failed_noretry;
 	}
 
+	mrioc->io_admin_reset_sync = 0;
 	if (is_resume || mrioc->block_on_pci_err) {
 		dprint_reset(mrioc, "setting up single ISR\n");
 		retval = mpi3mr_setup_isr(mrioc, 1);
@@ -5229,6 +5260,55 @@ cleanup_drv_cmd:
 }
 
 /**
+ * mpi3mr_check_op_admin_proc -
+ * @mrioc: Adapter instance reference
+ *
+ * Check if any of the operation reply queues
+ * or the admin reply queue are currently in use.
+ * If any queue is in use, this function waits for
+ * a maximum of 10 seconds for them to become available.
+ *
+ * Return: 0 on success, non-zero on failure.
+ */
+static int mpi3mr_check_op_admin_proc(struct mpi3mr_ioc *mrioc)
+{
+
+	u16 timeout = 10 * 10;
+	u16 elapsed_time = 0;
+	bool op_admin_in_use = false;
+
+	do {
+		op_admin_in_use = false;
+
+		/* Check admin_reply queue first to exit early */
+		if (atomic_read(&mrioc->admin_reply_q_in_use) == 1)
+			op_admin_in_use = true;
+		else {
+			/* Check op_reply queues */
+			int i;
+
+			for (i = 0; i < mrioc->num_queues; i++) {
+				if (atomic_read(&mrioc->op_reply_qinfo[i].in_use) == 1) {
+					op_admin_in_use = true;
+					break;
+				}
+			}
+		}
+
+		if (!op_admin_in_use)
+			break;
+
+		msleep(100);
+
+	} while (++elapsed_time < timeout);
+
+	if (op_admin_in_use)
+		return 1;
+
+	return 0;
+}
+
+/**
  * mpi3mr_soft_reset_handler - Reset the controller
  * @mrioc: Adapter instance reference
  * @reset_reason: Reset reason code
@@ -5308,6 +5388,7 @@ int mpi3mr_soft_reset_handler(struct mpi3mr_ioc *mrioc,
 	mpi3mr_wait_for_host_io(mrioc, MPI3MR_RESET_HOST_IOWAIT_TIMEOUT);
 
 	mpi3mr_ioc_disable_intr(mrioc);
+	mrioc->io_admin_reset_sync = 1;
 
 	if (snapdump) {
 		mpi3mr_set_diagsave(mrioc);
@@ -5335,6 +5416,16 @@ int mpi3mr_soft_reset_handler(struct mpi3mr_ioc *mrioc,
 		ioc_err(mrioc, "Failed to issue soft reset to the ioc\n");
 		goto out;
 	}
+
+	retval = mpi3mr_check_op_admin_proc(mrioc);
+	if (retval) {
+		ioc_err(mrioc, "Soft reset failed due to an Admin or I/O queue polling\n"
+				"thread still processing replies even after a 10 second\n"
+				"timeout. Marking the controller as unrecoverable!\n");
+
+		goto out;
+	}
+
 	if (mrioc->num_io_throttle_group !=
 	    mrioc->facts.max_io_throttle_group) {
 		ioc_err(mrioc,
diff --git a/drivers/scsi/mpi3mr/mpi3mr_os.c b/drivers/scsi/mpi3mr/mpi3mr_os.c
index 1bef88130d0c..990646e1e18d 100644
--- a/drivers/scsi/mpi3mr/mpi3mr_os.c
+++ b/drivers/scsi/mpi3mr/mpi3mr_os.c
@@ -49,6 +49,13 @@ static void mpi3mr_send_event_ack(struct mpi3mr_ioc *mrioc, u8 event,
 
 #define MPI3_EVENT_WAIT_FOR_DEVICES_TO_REFRESH	(0xFFFE)
 
+/*
+ * SAS Log info code for a NCQ collateral abort after an NCQ error:
+ * IOC_LOGINFO_PREFIX_PL | PL_LOGINFO_CODE_SATA_NCQ_FAIL_ALL_CMDS_AFTR_ERR
+ * See: drivers/message/fusion/lsi/mpi_log_sas.h
+ */
+#define IOC_LOGINFO_SATA_NCQ_FAIL_AFTER_ERR	0x31080000
+
 /**
  * mpi3mr_host_tag_for_scmd - Get host tag for a scmd
  * @mrioc: Adapter instance reference
@@ -3397,7 +3404,18 @@ void mpi3mr_process_op_reply_desc(struct mpi3mr_ioc *mrioc,
 		scmd->result = DID_NO_CONNECT << 16;
 		break;
 	case MPI3_IOCSTATUS_SCSI_IOC_TERMINATED:
-		scmd->result = DID_SOFT_ERROR << 16;
+		if (ioc_loginfo == IOC_LOGINFO_SATA_NCQ_FAIL_AFTER_ERR) {
+			/*
+			 * This is a ATA NCQ command aborted due to another NCQ
+			 * command failure. We must retry this command
+			 * immediately but without incrementing its retry
+			 * counter.
+			 */
+			WARN_ON_ONCE(xfer_count != 0);
+			scmd->result = DID_IMM_RETRY << 16;
+		} else {
+			scmd->result = DID_SOFT_ERROR << 16;
+		}
 		break;
 	case MPI3_IOCSTATUS_SCSI_TASK_TERMINATED:
 	case MPI3_IOCSTATUS_SCSI_EXT_TERMINATED:
@@ -4042,7 +4060,7 @@ static void mpi3mr_map_queues(struct Scsi_Host *shost)
 		 */
 		map->queue_offset = qoff;
 		if (i != HCTX_TYPE_POLL)
-			blk_mq_pci_map_queues(map, mrioc->pdev, offset);
+			blk_mq_map_hw_queues(map, &mrioc->pdev->dev, offset);
 		else
 			blk_mq_map_queues(map);
 
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c
index 16ac2267c71e..c1d8f2c91a5e 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.c
@@ -5629,8 +5629,7 @@ _base_static_config_pages(struct MPT3SAS_ADAPTER *ioc)
 	if (!ioc->is_gen35_ioc && ioc->manu_pg11.EEDPTagMode == 0) {
 		pr_err("%s: overriding NVDATA EEDPTagMode setting\n",
 		    ioc->name);
-		ioc->manu_pg11.EEDPTagMode &= ~0x3;
-		ioc->manu_pg11.EEDPTagMode |= 0x1;
+		ioc->manu_pg11.EEDPTagMode = 0x1;
 		mpt3sas_config_set_manufacturing_pg11(ioc, &mpi_reply,
 		    &ioc->manu_pg11);
 	}
diff --git a/drivers/scsi/mpt3sas/mpt3sas_ctl.c b/drivers/scsi/mpt3sas/mpt3sas_ctl.c
index 87784c96249a..47faa27bc355 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_ctl.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_ctl.c
@@ -679,6 +679,7 @@ _ctl_do_mpt_command(struct MPT3SAS_ADAPTER *ioc, struct mpt3_ioctl_command karg,
 	size_t data_in_sz = 0;
 	long ret;
 	u16 device_handle = MPT3SAS_INVALID_DEVICE_HANDLE;
+	int tm_ret;
 
 	issue_reset = 0;
 
@@ -1120,18 +1121,25 @@ _ctl_do_mpt_command(struct MPT3SAS_ADAPTER *ioc, struct mpt3_ioctl_command karg,
 			if (pcie_device && (!ioc->tm_custom_handling) &&
 			    (!(mpt3sas_scsih_is_pcie_scsi_device(
 			    pcie_device->device_info))))
-				mpt3sas_scsih_issue_locked_tm(ioc,
+				tm_ret = mpt3sas_scsih_issue_locked_tm(ioc,
 				  le16_to_cpu(mpi_request->FunctionDependent1),
 				  0, 0, 0,
 				  MPI2_SCSITASKMGMT_TASKTYPE_TARGET_RESET, 0,
 				  0, pcie_device->reset_timeout,
 			MPI26_SCSITASKMGMT_MSGFLAGS_PROTOCOL_LVL_RST_PCIE);
 			else
-				mpt3sas_scsih_issue_locked_tm(ioc,
+				tm_ret = mpt3sas_scsih_issue_locked_tm(ioc,
 				  le16_to_cpu(mpi_request->FunctionDependent1),
 				  0, 0, 0,
 				  MPI2_SCSITASKMGMT_TASKTYPE_TARGET_RESET, 0,
 				  0, 30, MPI2_SCSITASKMGMT_MSGFLAGS_LINK_RESET);
+
+			if (tm_ret != SUCCESS) {
+				ioc_info(ioc,
+					 "target reset failed, issue hard reset: handle (0x%04x)\n",
+					 le16_to_cpu(mpi_request->FunctionDependent1));
+				mpt3sas_base_hard_reset_handler(ioc, FORCE_BIG_HAMMER);
+			}
 		} else
 			mpt3sas_base_hard_reset_handler(ioc, FORCE_BIG_HAMMER);
 	}
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index f2a55aa5fe65..9719da76461c 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -53,7 +53,6 @@
 #include <linux/pci.h>
 #include <linux/interrupt.h>
 #include <linux/raid_class.h>
-#include <linux/blk-mq-pci.h>
 #include <linux/unaligned.h>
 
 #include "mpt3sas_base.h"
@@ -196,6 +195,14 @@ struct sense_info {
 #define MPT3SAS_PORT_ENABLE_COMPLETE (0xFFFD)
 #define MPT3SAS_ABRT_TASK_SET (0xFFFE)
 #define MPT3SAS_REMOVE_UNRESPONDING_DEVICES (0xFFFF)
+
+/*
+ * SAS Log info code for a NCQ collateral abort after an NCQ error:
+ * IOC_LOGINFO_PREFIX_PL | PL_LOGINFO_CODE_SATA_NCQ_FAIL_ALL_CMDS_AFTR_ERR
+ * See: drivers/message/fusion/lsi/mpi_log_sas.h
+ */
+#define IOC_LOGINFO_SATA_NCQ_FAIL_AFTER_ERR	0x31080000
+
 /**
  * struct fw_event_work - firmware event struct
  * @list: link list framework
@@ -5815,6 +5822,17 @@ _scsih_io_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index, u32 reply)
 			scmd->result = DID_TRANSPORT_DISRUPTED << 16;
 			goto out;
 		}
+		if (log_info == IOC_LOGINFO_SATA_NCQ_FAIL_AFTER_ERR) {
+			/*
+			 * This is a ATA NCQ command aborted due to another NCQ
+			 * command failure. We must retry this command
+			 * immediately but without incrementing its retry
+			 * counter.
+			 */
+			WARN_ON_ONCE(xfer_cnt != 0);
+			scmd->result = DID_IMM_RETRY << 16;
+			break;
+		}
 		if (log_info == 0x31110630) {
 			if (scmd->retries > 2) {
 				scmd->result = DID_NO_CONNECT << 16;
@@ -10791,8 +10809,7 @@ _mpt3sas_fw_work(struct MPT3SAS_ADAPTER *ioc, struct fw_event_work *fw_event)
 		break;
 	case MPI2_EVENT_PCIE_TOPOLOGY_CHANGE_LIST:
 		_scsih_pcie_topology_change_event(ioc, fw_event);
-		ioc->current_event = NULL;
-		return;
+		break;
 	}
 out:
 	fw_event_work_put(fw_event);
@@ -11890,7 +11907,7 @@ static void scsih_map_queues(struct Scsi_Host *shost)
 		 */
 		map->queue_offset = qoff;
 		if (i != HCTX_TYPE_POLL)
-			blk_mq_pci_map_queues(map, ioc->pdev, offset);
+			blk_mq_map_hw_queues(map, &ioc->pdev->dev, offset);
 		else
 			blk_mq_map_queues(map);
 
diff --git a/drivers/scsi/mvsas/mv_sas.c b/drivers/scsi/mvsas/mv_sas.c
index 1444b1f1c4c8..d6897432cf0f 100644
--- a/drivers/scsi/mvsas/mv_sas.c
+++ b/drivers/scsi/mvsas/mv_sas.c
@@ -828,7 +828,7 @@ err_out:
 	dev_printk(KERN_ERR, mvi->dev, "mvsas prep failed[%d]!\n", rc);
 	if (!sas_protocol_ata(task->task_proto))
 		if (n_elem)
-			dma_unmap_sg(mvi->dev, task->scatter, n_elem,
+			dma_unmap_sg(mvi->dev, task->scatter, task->num_scatter,
 				     task->data_dir);
 prep_out:
 	return rc;
@@ -874,7 +874,7 @@ static void mvs_slot_task_free(struct mvs_info *mvi, struct sas_task *task,
 	if (!sas_protocol_ata(task->task_proto))
 		if (slot->n_elem)
 			dma_unmap_sg(mvi->dev, task->scatter,
-				     slot->n_elem, task->data_dir);
+				     task->num_scatter, task->data_dir);
 
 	switch (task->task_proto) {
 	case SAS_PROTOCOL_SMP:
diff --git a/drivers/scsi/pm8001/pm8001_init.c b/drivers/scsi/pm8001/pm8001_init.c
index 33e1eba62ca1..b53b1ae5b74c 100644
--- a/drivers/scsi/pm8001/pm8001_init.c
+++ b/drivers/scsi/pm8001/pm8001_init.c
@@ -101,7 +101,7 @@ static void pm8001_map_queues(struct Scsi_Host *shost)
 	struct blk_mq_queue_map *qmap = &shost->tag_set.map[HCTX_TYPE_DEFAULT];
 
 	if (pm8001_ha->number_of_intr > 1) {
-		blk_mq_pci_map_queues(qmap, pm8001_ha->pdev, 1);
+		blk_mq_map_hw_queues(qmap, &pm8001_ha->pdev->dev, 1);
 		return;
 	}
 
diff --git a/drivers/scsi/pm8001/pm8001_sas.c b/drivers/scsi/pm8001/pm8001_sas.c
index ee2da8e49d4c..a9d6dac41334 100644
--- a/drivers/scsi/pm8001/pm8001_sas.c
+++ b/drivers/scsi/pm8001/pm8001_sas.c
@@ -719,6 +719,7 @@ static void pm8001_dev_gone_notify(struct domain_device *dev)
 			spin_lock_irqsave(&pm8001_ha->lock, flags);
 		}
 		PM8001_CHIP_DISP->dereg_dev_req(pm8001_ha, device_id);
+		pm8001_ha->phy[pm8001_dev->attached_phy].phy_attached = 0;
 		pm8001_free_dev(pm8001_dev);
 	} else {
 		pm8001_dbg(pm8001_ha, DISC, "Found dev has gone.\n");
diff --git a/drivers/scsi/pm8001/pm8001_sas.h b/drivers/scsi/pm8001/pm8001_sas.h
index ced6721380a8..c46470e0cf63 100644
--- a/drivers/scsi/pm8001/pm8001_sas.h
+++ b/drivers/scsi/pm8001/pm8001_sas.h
@@ -56,7 +56,6 @@
 #include <scsi/sas_ata.h>
 #include <linux/atomic.h>
 #include <linux/blk-mq.h>
-#include <linux/blk-mq-pci.h>
 #include "pm8001_defs.h"
 
 #define DRV_NAME		"pm80xx"
diff --git a/drivers/scsi/qedf/qedf_main.c b/drivers/scsi/qedf/qedf_main.c
index e979ec1478c1..e895bd25098f 100644
--- a/drivers/scsi/qedf/qedf_main.c
+++ b/drivers/scsi/qedf/qedf_main.c
@@ -699,7 +699,7 @@ static u32 qedf_get_login_failures(void *cookie)
 }
 
 static struct qed_fcoe_cb_ops qedf_cb_ops = {
-	{
+	.common = {
 		.link_update = qedf_link_update,
 		.bw_update = qedf_bw_update,
 		.schedule_recovery_handler = qedf_schedule_recovery_handler,
diff --git a/drivers/scsi/qla1280.c b/drivers/scsi/qla1280.c
index 8958547ac111..fed07b146070 100644
--- a/drivers/scsi/qla1280.c
+++ b/drivers/scsi/qla1280.c
@@ -2867,7 +2867,7 @@ qla1280_64bit_start_scsi(struct scsi_qla_host *ha, struct srb * sp)
 			dprintk(3, "S/G Segment phys_addr=%x %x, len=0x%x\n",
 				cpu_to_le32(upper_32_bits(dma_handle)),
 				cpu_to_le32(lower_32_bits(dma_handle)),
-				cpu_to_le32(sg_dma_len(sg_next(s))));
+				cpu_to_le32(sg_dma_len(s)));
 			remseg--;
 		}
 		dprintk(5, "qla1280_64bit_start_scsi: Scatter/gather "
diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index 15066c112817..cb95b7b12051 100644
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -4098,6 +4098,8 @@ struct qla_hw_data {
 		uint32_t	npiv_supported		:1;
 		uint32_t	pci_channel_io_perm_failure	:1;
 		uint32_t	fce_enabled		:1;
+		uint32_t	user_enabled_fce	:1;
+		uint32_t	fce_dump_buf_alloced	:1;
 		uint32_t	fac_supported		:1;
 
 		uint32_t	chip_reset_done		:1;
diff --git a/drivers/scsi/qla2xxx/qla_dfs.c b/drivers/scsi/qla2xxx/qla_dfs.c
index a1545dad0c0c..08273520c777 100644
--- a/drivers/scsi/qla2xxx/qla_dfs.c
+++ b/drivers/scsi/qla2xxx/qla_dfs.c
@@ -409,26 +409,31 @@ qla2x00_dfs_fce_show(struct seq_file *s, void *unused)
 
 	mutex_lock(&ha->fce_mutex);
 
-	seq_puts(s, "FCE Trace Buffer\n");
-	seq_printf(s, "In Pointer = %llx\n\n", (unsigned long long)ha->fce_wr);
-	seq_printf(s, "Base = %llx\n\n", (unsigned long long) ha->fce_dma);
-	seq_puts(s, "FCE Enable Registers\n");
-	seq_printf(s, "%08x %08x %08x %08x %08x %08x\n",
-	    ha->fce_mb[0], ha->fce_mb[2], ha->fce_mb[3], ha->fce_mb[4],
-	    ha->fce_mb[5], ha->fce_mb[6]);
-
-	fce = (uint32_t *) ha->fce;
-	fce_start = (unsigned long long) ha->fce_dma;
-	for (cnt = 0; cnt < fce_calc_size(ha->fce_bufs) / 4; cnt++) {
-		if (cnt % 8 == 0)
-			seq_printf(s, "\n%llx: ",
-			    (unsigned long long)((cnt * 4) + fce_start));
-		else
-			seq_putc(s, ' ');
-		seq_printf(s, "%08x", *fce++);
-	}
+	if (ha->flags.user_enabled_fce) {
+		seq_puts(s, "FCE Trace Buffer\n");
+		seq_printf(s, "In Pointer = %llx\n\n", (unsigned long long)ha->fce_wr);
+		seq_printf(s, "Base = %llx\n\n", (unsigned long long)ha->fce_dma);
+		seq_puts(s, "FCE Enable Registers\n");
+		seq_printf(s, "%08x %08x %08x %08x %08x %08x\n",
+			   ha->fce_mb[0], ha->fce_mb[2], ha->fce_mb[3], ha->fce_mb[4],
+			   ha->fce_mb[5], ha->fce_mb[6]);
+
+		fce = (uint32_t *)ha->fce;
+		fce_start = (unsigned long long)ha->fce_dma;
+		for (cnt = 0; cnt < fce_calc_size(ha->fce_bufs) / 4; cnt++) {
+			if (cnt % 8 == 0)
+				seq_printf(s, "\n%llx: ",
+					   (unsigned long long)((cnt * 4) + fce_start));
+			else
+				seq_putc(s, ' ');
+			seq_printf(s, "%08x", *fce++);
+		}
 
-	seq_puts(s, "\nEnd\n");
+		seq_puts(s, "\nEnd\n");
+	} else {
+		seq_puts(s, "FCE Trace is currently not enabled\n");
+		seq_puts(s, "\techo [ 1 | 0 ] > fce\n");
+	}
 
 	mutex_unlock(&ha->fce_mutex);
 
@@ -467,7 +472,7 @@ qla2x00_dfs_fce_release(struct inode *inode, struct file *file)
 	struct qla_hw_data *ha = vha->hw;
 	int rval;
 
-	if (ha->flags.fce_enabled)
+	if (ha->flags.fce_enabled || !ha->fce)
 		goto out;
 
 	mutex_lock(&ha->fce_mutex);
@@ -488,11 +493,88 @@ out:
 	return single_release(inode, file);
 }
 
+static ssize_t
+qla2x00_dfs_fce_write(struct file *file, const char __user *buffer,
+		      size_t count, loff_t *pos)
+{
+	struct seq_file *s = file->private_data;
+	struct scsi_qla_host *vha = s->private;
+	struct qla_hw_data *ha = vha->hw;
+	char *buf;
+	int rc = 0;
+	unsigned long enable;
+
+	if (!IS_QLA25XX(ha) && !IS_QLA81XX(ha) && !IS_QLA83XX(ha) &&
+	    !IS_QLA27XX(ha) && !IS_QLA28XX(ha)) {
+		ql_dbg(ql_dbg_user, vha, 0xd034,
+		       "this adapter does not support FCE.");
+		return -EINVAL;
+	}
+
+	buf = memdup_user_nul(buffer, count);
+	if (IS_ERR(buf)) {
+		ql_dbg(ql_dbg_user, vha, 0xd037,
+		    "fail to copy user buffer.");
+		return PTR_ERR(buf);
+	}
+
+	enable = kstrtoul(buf, 0, 0);
+	rc = count;
+
+	mutex_lock(&ha->fce_mutex);
+
+	if (enable) {
+		if (ha->flags.user_enabled_fce) {
+			mutex_unlock(&ha->fce_mutex);
+			goto out_free;
+		}
+		ha->flags.user_enabled_fce = 1;
+		if (!ha->fce) {
+			rc = qla2x00_alloc_fce_trace(vha);
+			if (rc) {
+				ha->flags.user_enabled_fce = 0;
+				mutex_unlock(&ha->fce_mutex);
+				goto out_free;
+			}
+
+			/* adjust fw dump buffer to take into account of this feature */
+			if (!ha->flags.fce_dump_buf_alloced)
+				qla2x00_alloc_fw_dump(vha);
+		}
+
+		if (!ha->flags.fce_enabled)
+			qla_enable_fce_trace(vha);
+
+		ql_dbg(ql_dbg_user, vha, 0xd045, "User enabled FCE .\n");
+	} else {
+		if (!ha->flags.user_enabled_fce) {
+			mutex_unlock(&ha->fce_mutex);
+			goto out_free;
+		}
+		ha->flags.user_enabled_fce = 0;
+		if (ha->flags.fce_enabled) {
+			qla2x00_disable_fce_trace(vha, NULL, NULL);
+			ha->flags.fce_enabled = 0;
+		}
+
+		qla2x00_free_fce_trace(ha);
+		/* no need to re-adjust fw dump buffer */
+
+		ql_dbg(ql_dbg_user, vha, 0xd04f, "User disabled FCE .\n");
+	}
+
+	mutex_unlock(&ha->fce_mutex);
+out_free:
+	kfree(buf);
+	return rc;
+}
+
 static const struct file_operations dfs_fce_ops = {
 	.open		= qla2x00_dfs_fce_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
 	.release	= qla2x00_dfs_fce_release,
+	.write		= qla2x00_dfs_fce_write,
 };
 
 static int
@@ -626,8 +708,6 @@ qla2x00_dfs_setup(scsi_qla_host_t *vha)
 	if (!IS_QLA25XX(ha) && !IS_QLA81XX(ha) && !IS_QLA83XX(ha) &&
 	    !IS_QLA27XX(ha) && !IS_QLA28XX(ha))
 		goto out;
-	if (!ha->fce)
-		goto out;
 
 	if (qla2x00_dfs_root)
 		goto create_dir;
diff --git a/drivers/scsi/qla2xxx/qla_gbl.h b/drivers/scsi/qla2xxx/qla_gbl.h
index cededfda9d0e..e556f57c91af 100644
--- a/drivers/scsi/qla2xxx/qla_gbl.h
+++ b/drivers/scsi/qla2xxx/qla_gbl.h
@@ -11,6 +11,9 @@
 /*
  * Global Function Prototypes in qla_init.c source file.
  */
+int  qla2x00_alloc_fce_trace(scsi_qla_host_t *);
+void qla2x00_free_fce_trace(struct qla_hw_data *ha);
+void qla_enable_fce_trace(scsi_qla_host_t *);
 extern int qla2x00_initialize_adapter(scsi_qla_host_t *);
 extern int qla24xx_post_prli_work(struct scsi_qla_host *vha, fc_port_t *fcport);
 
diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index 31fc6a0eca3e..79cdfec2bca3 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -2681,7 +2681,7 @@ exit:
 	return rval;
 }
 
-static void qla_enable_fce_trace(scsi_qla_host_t *vha)
+void qla_enable_fce_trace(scsi_qla_host_t *vha)
 {
 	int rval;
 	struct qla_hw_data *ha = vha->hw;
@@ -3717,25 +3717,24 @@ qla24xx_chip_diag(scsi_qla_host_t *vha)
 	return rval;
 }
 
-static void
-qla2x00_alloc_fce_trace(scsi_qla_host_t *vha)
+int qla2x00_alloc_fce_trace(scsi_qla_host_t *vha)
 {
 	dma_addr_t tc_dma;
 	void *tc;
 	struct qla_hw_data *ha = vha->hw;
 
 	if (!IS_FWI2_CAPABLE(ha))
-		return;
+		return -EINVAL;
 
 	if (!IS_QLA25XX(ha) && !IS_QLA81XX(ha) && !IS_QLA83XX(ha) &&
 	    !IS_QLA27XX(ha) && !IS_QLA28XX(ha))
-		return;
+		return -EINVAL;
 
 	if (ha->fce) {
 		ql_dbg(ql_dbg_init, vha, 0x00bd,
 		       "%s: FCE Mem is already allocated.\n",
 		       __func__);
-		return;
+		return -EIO;
 	}
 
 	/* Allocate memory for Fibre Channel Event Buffer. */
@@ -3745,7 +3744,7 @@ qla2x00_alloc_fce_trace(scsi_qla_host_t *vha)
 		ql_log(ql_log_warn, vha, 0x00be,
 		       "Unable to allocate (%d KB) for FCE.\n",
 		       FCE_SIZE / 1024);
-		return;
+		return -ENOMEM;
 	}
 
 	ql_dbg(ql_dbg_init, vha, 0x00c0,
@@ -3754,6 +3753,16 @@ qla2x00_alloc_fce_trace(scsi_qla_host_t *vha)
 	ha->fce_dma = tc_dma;
 	ha->fce = tc;
 	ha->fce_bufs = FCE_NUM_BUFFERS;
+	return 0;
+}
+
+void qla2x00_free_fce_trace(struct qla_hw_data *ha)
+{
+	if (!ha->fce)
+		return;
+	dma_free_coherent(&ha->pdev->dev, FCE_SIZE, ha->fce, ha->fce_dma);
+	ha->fce = NULL;
+	ha->fce_dma = 0;
 }
 
 static void
@@ -3844,9 +3853,10 @@ qla2x00_alloc_fw_dump(scsi_qla_host_t *vha)
 		if (ha->tgt.atio_ring)
 			mq_size += ha->tgt.atio_q_length * sizeof(request_t);
 
-		qla2x00_alloc_fce_trace(vha);
-		if (ha->fce)
+		if (ha->fce) {
 			fce_size = sizeof(struct qla2xxx_fce_chain) + FCE_SIZE;
+			ha->flags.fce_dump_buf_alloced = 1;
+		}
 		qla2x00_alloc_eft_trace(vha);
 		if (ha->eft)
 			eft_size = EFT_SIZE;
diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c
index 0cd6f3e14882..13b6cb1b93ac 100644
--- a/drivers/scsi/qla2xxx/qla_mbx.c
+++ b/drivers/scsi/qla2xxx/qla_mbx.c
@@ -2147,7 +2147,7 @@ qla24xx_get_port_database(scsi_qla_host_t *vha, u16 nport_handle,
 
 	pdb_dma = dma_map_single(&vha->hw->pdev->dev, pdb,
 	    sizeof(*pdb), DMA_FROM_DEVICE);
-	if (!pdb_dma) {
+	if (dma_mapping_error(&vha->hw->pdev->dev, pdb_dma)) {
 		ql_log(ql_log_warn, vha, 0x1116, "Failed to map dma buffer.\n");
 		return QLA_MEMORY_ALLOC_FAILED;
 	}
diff --git a/drivers/scsi/qla2xxx/qla_nvme.c b/drivers/scsi/qla2xxx/qla_nvme.c
index 8f4cc136a9c9..8ee2e337c9e1 100644
--- a/drivers/scsi/qla2xxx/qla_nvme.c
+++ b/drivers/scsi/qla2xxx/qla_nvme.c
@@ -8,7 +8,6 @@
 #include <linux/delay.h>
 #include <linux/nvme.h>
 #include <linux/nvme-fc.h>
-#include <linux/blk-mq-pci.h>
 #include <linux/blk-mq.h>
 
 static struct nvme_fc_port_template qla_nvme_fc_transport;
@@ -841,7 +840,7 @@ static void qla_nvme_map_queues(struct nvme_fc_local_port *lport,
 {
 	struct scsi_qla_host *vha = lport->private;
 
-	blk_mq_pci_map_queues(map, vha->hw->pdev, vha->irq_offset);
+	blk_mq_map_hw_queues(map, &vha->hw->pdev->dev, vha->irq_offset);
 }
 
 static void qla_nvme_localport_delete(struct nvme_fc_local_port *lport)
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 7ab717ed7232..31535beaaa16 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -13,7 +13,6 @@
 #include <linux/mutex.h>
 #include <linux/kobject.h>
 #include <linux/slab.h>
-#include <linux/blk-mq-pci.h>
 #include <linux/refcount.h>
 #include <linux/crash_dump.h>
 #include <linux/trace_events.h>
@@ -8071,7 +8070,8 @@ static void qla2xxx_map_queues(struct Scsi_Host *shost)
 	if (USER_CTRL_IRQ(vha->hw) || !vha->hw->mqiobase)
 		blk_mq_map_queues(qmap);
 	else
-		blk_mq_pci_map_queues(qmap, vha->hw->pdev, vha->irq_offset);
+		blk_mq_map_hw_queues(qmap, &vha->hw->pdev->dev,
+				       vha->irq_offset);
 }
 
 struct scsi_host_template qla2xxx_driver_template = {
diff --git a/drivers/scsi/qla4xxx/ql4_os.c b/drivers/scsi/qla4xxx/ql4_os.c
index d91f54a6e752..97e9ca5a2a02 100644
--- a/drivers/scsi/qla4xxx/ql4_os.c
+++ b/drivers/scsi/qla4xxx/ql4_os.c
@@ -3420,6 +3420,8 @@ static int qla4xxx_alloc_pdu(struct iscsi_task *task, uint8_t opcode)
 		task_data->data_dma = dma_map_single(&ha->pdev->dev, task->data,
 						     task->data_count,
 						     DMA_TO_DEVICE);
+		if (dma_mapping_error(&ha->pdev->dev, task_data->data_dma))
+			return -ENOMEM;
 	}
 
 	DEBUG2(ql4_printk(KERN_INFO, ha, "%s: MaxRecvLen %u, iscsi hrd %d\n",
diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c
index a77e0499b738..9d2db5bc8ee7 100644
--- a/drivers/scsi/scsi.c
+++ b/drivers/scsi/scsi.c
@@ -695,26 +695,23 @@ void scsi_cdl_check(struct scsi_device *sdev)
  */
 int scsi_cdl_enable(struct scsi_device *sdev, bool enable)
 {
-	struct scsi_mode_data data;
-	struct scsi_sense_hdr sshdr;
-	struct scsi_vpd *vpd;
-	bool is_ata = false;
 	char buf[64];
+	bool is_ata;
 	int ret;
 
 	if (!sdev->cdl_supported)
 		return -EOPNOTSUPP;
 
 	rcu_read_lock();
-	vpd = rcu_dereference(sdev->vpd_pg89);
-	if (vpd)
-		is_ata = true;
+	is_ata = rcu_dereference(sdev->vpd_pg89);
 	rcu_read_unlock();
 
 	/*
 	 * For ATA devices, CDL needs to be enabled with a SET FEATURES command.
 	 */
 	if (is_ata) {
+		struct scsi_mode_data data;
+		struct scsi_sense_hdr sshdr;
 		char *buf_data;
 		int len;
 
@@ -723,16 +720,30 @@ int scsi_cdl_enable(struct scsi_device *sdev, bool enable)
 		if (ret)
 			return -EINVAL;
 
-		/* Enable CDL using the ATA feature page */
+		/* Enable or disable CDL using the ATA feature page */
 		len = min_t(size_t, sizeof(buf),
 			    data.length - data.header_length -
 			    data.block_descriptor_length);
 		buf_data = buf + data.header_length +
 			data.block_descriptor_length;
-		if (enable)
-			buf_data[4] = 0x02;
-		else
-			buf_data[4] = 0;
+
+		/*
+		 * If we want to enable CDL and CDL is already enabled on the
+		 * device, do nothing. This avoids needlessly resetting the CDL
+		 * statistics on the device as that is implied by the CDL enable
+		 * action. Similar to this, there is no need to do anything if
+		 * we want to disable CDL and CDL is already disabled.
+		 */
+		if (enable) {
+			if ((buf_data[4] & 0x03) == 0x02)
+				goto out;
+			buf_data[4] &= ~0x03;
+			buf_data[4] |= 0x02;
+		} else {
+			if ((buf_data[4] & 0x03) == 0x00)
+				goto out;
+			buf_data[4] &= ~0x03;
+		}
 
 		ret = scsi_mode_select(sdev, 1, 0, buf_data, len, 5 * HZ, 3,
 				       &data, &sshdr);
@@ -744,6 +755,7 @@ int scsi_cdl_enable(struct scsi_device *sdev, bool enable)
 		}
 	}
 
+out:
 	sdev->cdl_enable = enable;
 
 	return 0;
diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c
index 680ba180a672..89a2aaccdcfc 100644
--- a/drivers/scsi/scsi_debug.c
+++ b/drivers/scsi/scsi_debug.c
@@ -173,6 +173,10 @@ static const char *sdebug_version_date = "20210520";
 #define DEF_ZBC_MAX_OPEN_ZONES	8
 #define DEF_ZBC_NR_CONV_ZONES	1
 
+/* Default parameters for tape drives */
+#define TAPE_DEF_DENSITY  0x0
+#define TAPE_DEF_BLKSIZE  0
+
 #define SDEBUG_LUN_0_VAL 0
 
 /* bit mask values for sdebug_opts */
@@ -363,6 +367,10 @@ struct sdebug_dev_info {
 	ktime_t create_ts;	/* time since bootup that this device was created */
 	struct sdeb_zone_state *zstate;
 
+	/* For tapes */
+	unsigned int tape_blksize;
+	unsigned int tape_density;
+
 	struct dentry *debugfs_entry;
 	struct spinlock list_lock;
 	struct list_head inject_err_list;
@@ -773,7 +781,7 @@ static const struct opcode_info_t opcode_info_arr[SDEB_I_LAST_ELEM_P1 + 1] = {
 /* 20 */
 	{0, 0x1e, 0, 0, NULL, NULL, /* ALLOW REMOVAL */
 	    {6,  0, 0, 0, 0x3, 0xc7, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0} },
-	{0, 0x1, 0, 0, resp_start_stop, NULL, /* REWIND ?? */
+	{0, 0x1, 0, 0, NULL, NULL, /* REWIND ?? */
 	    {6,  0x1, 0, 0, 0, 0xc7, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0} },
 	{0, 0, 0, F_INV_OP | FF_RESPOND, NULL, NULL, /* ATA_PT */
 	    {0,  0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0} },
@@ -2742,7 +2750,7 @@ static int resp_mode_sense(struct scsi_cmnd *scp,
 	unsigned char *ap;
 	unsigned char *arr __free(kfree);
 	unsigned char *cmd = scp->cmnd;
-	bool dbd, llbaa, msense_6, is_disk, is_zbc;
+	bool dbd, llbaa, msense_6, is_disk, is_zbc, is_tape;
 
 	arr = kzalloc(SDEBUG_MAX_MSENSE_SZ, GFP_ATOMIC);
 	if (!arr)
@@ -2755,7 +2763,8 @@ static int resp_mode_sense(struct scsi_cmnd *scp,
 	llbaa = msense_6 ? false : !!(cmd[1] & 0x10);
 	is_disk = (sdebug_ptype == TYPE_DISK);
 	is_zbc = devip->zoned;
-	if ((is_disk || is_zbc) && !dbd)
+	is_tape = (sdebug_ptype == TYPE_TAPE);
+	if ((is_disk || is_zbc || is_tape) && !dbd)
 		bd_len = llbaa ? 16 : 8;
 	else
 		bd_len = 0;
@@ -2793,15 +2802,25 @@ static int resp_mode_sense(struct scsi_cmnd *scp,
 			put_unaligned_be32(0xffffffff, ap + 0);
 		else
 			put_unaligned_be32(sdebug_capacity, ap + 0);
-		put_unaligned_be16(sdebug_sector_size, ap + 6);
+		if (is_tape) {
+			ap[0] = devip->tape_density;
+			put_unaligned_be16(devip->tape_blksize, ap + 6);
+		} else
+			put_unaligned_be16(sdebug_sector_size, ap + 6);
 		offset += bd_len;
 		ap = arr + offset;
 	} else if (16 == bd_len) {
+		if (is_tape) {
+			mk_sense_invalid_fld(scp, SDEB_IN_DATA, 1, 4);
+			return check_condition_result;
+		}
 		put_unaligned_be64((u64)sdebug_capacity, ap + 0);
 		put_unaligned_be32(sdebug_sector_size, ap + 12);
 		offset += bd_len;
 		ap = arr + offset;
 	}
+	if (cmd[2] == 0)
+		goto only_bd; /* Only block descriptor requested */
 
 	/*
 	 * N.B. If len>0 before resp_*_pg() call, then form of that call should be:
@@ -2902,6 +2921,7 @@ static int resp_mode_sense(struct scsi_cmnd *scp,
 	default:
 		goto bad_pcode;
 	}
+only_bd:
 	if (msense_6)
 		arr[0] = offset - 1;
 	else
@@ -2945,8 +2965,27 @@ static int resp_mode_select(struct scsi_cmnd *scp,
 			    __func__, param_len, res);
 	md_len = mselect6 ? (arr[0] + 1) : (get_unaligned_be16(arr + 0) + 2);
 	bd_len = mselect6 ? arr[3] : get_unaligned_be16(arr + 6);
-	off = bd_len + (mselect6 ? 4 : 8);
-	if (md_len > 2 || off >= res) {
+	off = (mselect6 ? 4 : 8);
+	if (sdebug_ptype == TYPE_TAPE) {
+		int blksize;
+
+		if (bd_len != 8) {
+			mk_sense_invalid_fld(scp, SDEB_IN_DATA,
+					mselect6 ? 3 : 6, -1);
+			return check_condition_result;
+		}
+		blksize = get_unaligned_be16(arr + off + 6);
+		if ((blksize % 4) != 0) {
+			mk_sense_invalid_fld(scp, SDEB_IN_DATA, off + 6, -1);
+			return check_condition_result;
+		}
+		devip->tape_density = arr[off];
+		devip->tape_blksize = blksize;
+	}
+	off += bd_len;
+	if (off >= res)
+		return 0; /* No page written, just descriptors */
+	if (md_len > 2) {
 		mk_sense_invalid_fld(scp, SDEB_IN_DATA, 0, -1);
 		return check_condition_result;
 	}
@@ -5835,6 +5874,10 @@ static struct sdebug_dev_info *sdebug_device_create(
 		} else {
 			devip->zoned = false;
 		}
+		if (sdebug_ptype == TYPE_TAPE) {
+			devip->tape_density = TAPE_DEF_DENSITY;
+			devip->tape_blksize = TAPE_DEF_BLKSIZE;
+		}
 		devip->create_ts = ktime_get_boottime();
 		atomic_set(&devip->stopped, (sdeb_tur_ms_to_ready > 0 ? 2 : 0));
 		spin_lock_init(&devip->list_lock);
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index adee6f60c966..ce4b428b63f8 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -865,13 +865,18 @@ static void scsi_io_completion_action(struct scsi_cmnd *cmd, int result)
 				case 0x1a: /* start stop unit in progress */
 				case 0x1b: /* sanitize in progress */
 				case 0x1d: /* configuration in progress */
-				case 0x24: /* depopulation in progress */
-				case 0x25: /* depopulation restore in progress */
 					action = ACTION_DELAYED_RETRY;
 					break;
 				case 0x0a: /* ALUA state transition */
 					action = ACTION_DELAYED_REPREP;
 					break;
+				/*
+				 * Depopulation might take many hours,
+				 * thus it is not worthwhile to retry.
+				 */
+				case 0x24: /* depopulation in progress */
+				case 0x25: /* depopulation restore in progress */
+					fallthrough;
 				default:
 					action = ACTION_FAIL;
 					break;
@@ -1232,8 +1237,12 @@ EXPORT_SYMBOL_GPL(scsi_alloc_request);
  */
 static void scsi_cleanup_rq(struct request *rq)
 {
+	struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(rq);
+
+	cmd->flags = 0;
+
 	if (rq->rq_flags & RQF_DONTPREP) {
-		scsi_mq_uninit_cmd(blk_mq_rq_to_pdu(rq));
+		scsi_mq_uninit_cmd(cmd);
 		rq->rq_flags &= ~RQF_DONTPREP;
 	}
 }
@@ -1648,13 +1657,6 @@ static blk_status_t scsi_prepare_cmd(struct request *req)
 	if (in_flight)
 		__set_bit(SCMD_STATE_INFLIGHT, &cmd->state);
 
-	/*
-	 * Only clear the driver-private command data if the LLD does not supply
-	 * a function to initialize that data.
-	 */
-	if (!shost->hostt->init_cmd_priv)
-		memset(cmd + 1, 0, shost->hostt->cmd_size);
-
 	cmd->prot_op = SCSI_PROT_NORMAL;
 	if (blk_rq_bytes(req))
 		cmd->sc_data_direction = rq_dma_dir(req);
@@ -1821,6 +1823,13 @@ static blk_status_t scsi_queue_rq(struct blk_mq_hw_ctx *hctx,
 	if (!scsi_host_queue_ready(q, shost, sdev, cmd))
 		goto out_dec_target_busy;
 
+	/*
+	 * Only clear the driver-private command data if the LLD does not supply
+	 * a function to initialize that data.
+	 */
+	if (shost->hostt->cmd_size && !shost->hostt->init_cmd_priv)
+		memset(cmd + 1, 0, shost->hostt->cmd_size);
+
 	if (!(req->rq_flags & RQF_DONTPREP)) {
 		ret = scsi_prepare_cmd(req);
 		if (ret != BLK_STS_OK)
diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c
index 042329b74c6e..36e0b3105460 100644
--- a/drivers/scsi/scsi_scan.c
+++ b/drivers/scsi/scsi_scan.c
@@ -245,7 +245,7 @@ static int scsi_realloc_sdev_budget_map(struct scsi_device *sdev,
 	}
 	ret = sbitmap_init_node(&sdev->budget_map,
 				scsi_device_max_queue_depth(sdev),
-				new_shift, GFP_KERNEL,
+				new_shift, GFP_NOIO,
 				sdev->request_queue->node, false, true);
 	if (!ret)
 		sbitmap_resize(&sdev->budget_map, depth);
@@ -1881,7 +1881,7 @@ int scsi_scan_host_selected(struct Scsi_Host *shost, unsigned int channel,
 
 	return 0;
 }
-
+EXPORT_SYMBOL(scsi_scan_host_selected);
 static void scsi_sysfs_add_devices(struct Scsi_Host *shost)
 {
 	struct scsi_device *sdev;
diff --git a/drivers/scsi/scsi_sysctl.c b/drivers/scsi/scsi_sysctl.c
index 093774d77534..daa160459c9b 100644
--- a/drivers/scsi/scsi_sysctl.c
+++ b/drivers/scsi/scsi_sysctl.c
@@ -17,7 +17,9 @@ static struct ctl_table scsi_table[] = {
 	  .data		= &scsi_logging_level,
 	  .maxlen	= sizeof(scsi_logging_level),
 	  .mode		= 0644,
-	  .proc_handler	= proc_dointvec },
+	  .proc_handler	= proc_dointvec_minmax,
+	  .extra1	= SYSCTL_ZERO,
+	  .extra2	= SYSCTL_INT_MAX },
 };
 
 static struct ctl_table_header *scsi_table_header;
diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c
index fde7de3b1e55..7528bb7c06bb 100644
--- a/drivers/scsi/scsi_transport_iscsi.c
+++ b/drivers/scsi/scsi_transport_iscsi.c
@@ -2170,6 +2170,8 @@ static int iscsi_iter_destroy_conn_fn(struct device *dev, void *data)
 		return 0;
 
 	iscsi_remove_conn(iscsi_dev_to_conn(dev));
+	iscsi_put_conn(iscsi_dev_to_conn(dev));
+
 	return 0;
 }
 
@@ -3209,11 +3211,14 @@ iscsi_set_host_param(struct iscsi_transport *transport,
 	}
 
 	/* see similar check in iscsi_if_set_param() */
-	if (strlen(data) > ev->u.set_host_param.len)
-		return -EINVAL;
+	if (strlen(data) > ev->u.set_host_param.len) {
+		err = -EINVAL;
+		goto out;
+	}
 
 	err = transport->set_host_param(shost, ev->u.set_host_param.param,
 					data, ev->u.set_host_param.len);
+out:
 	scsi_host_put(shost);
 	return err;
 }
@@ -3523,7 +3528,7 @@ static int iscsi_new_flashnode(struct iscsi_transport *transport,
 		pr_err("%s could not find host no %u\n",
 		       __func__, ev->u.new_flashnode.host_no);
 		err = -ENODEV;
-		goto put_host;
+		goto exit_new_fnode;
 	}
 
 	index = transport->new_flashnode(shost, data, len);
@@ -3533,7 +3538,6 @@ static int iscsi_new_flashnode(struct iscsi_transport *transport,
 	else
 		err = -EIO;
 
-put_host:
 	scsi_host_put(shost);
 
 exit_new_fnode:
@@ -3558,7 +3562,7 @@ static int iscsi_del_flashnode(struct iscsi_transport *transport,
 		pr_err("%s could not find host no %u\n",
 		       __func__, ev->u.del_flashnode.host_no);
 		err = -ENODEV;
-		goto put_host;
+		goto exit_del_fnode;
 	}
 
 	idx = ev->u.del_flashnode.flashnode_idx;
@@ -3600,7 +3604,7 @@ static int iscsi_login_flashnode(struct iscsi_transport *transport,
 		pr_err("%s could not find host no %u\n",
 		       __func__, ev->u.login_flashnode.host_no);
 		err = -ENODEV;
-		goto put_host;
+		goto exit_login_fnode;
 	}
 
 	idx = ev->u.login_flashnode.flashnode_idx;
@@ -3652,7 +3656,7 @@ static int iscsi_logout_flashnode(struct iscsi_transport *transport,
 		pr_err("%s could not find host no %u\n",
 		       __func__, ev->u.logout_flashnode.host_no);
 		err = -ENODEV;
-		goto put_host;
+		goto exit_logout_fnode;
 	}
 
 	idx = ev->u.logout_flashnode.flashnode_idx;
@@ -3702,7 +3706,7 @@ static int iscsi_logout_flashnode_sid(struct iscsi_transport *transport,
 		pr_err("%s could not find host no %u\n",
 		       __func__, ev->u.logout_flashnode.host_no);
 		err = -ENODEV;
-		goto put_host;
+		goto exit_logout_sid;
 	}
 
 	session = iscsi_session_lookup(ev->u.logout_flashnode_sid.sid);
@@ -4104,7 +4108,7 @@ iscsi_if_rx(struct sk_buff *skb)
 		}
 		do {
 			/*
-			 * special case for GET_STATS:
+			 * special case for GET_STATS, GET_CHAP and GET_HOST_STATS:
 			 * on success - sending reply and stats from
 			 * inside of if_recv_msg(),
 			 * on error - fall through.
@@ -4113,6 +4117,8 @@ iscsi_if_rx(struct sk_buff *skb)
 				break;
 			if (ev->type == ISCSI_UEVENT_GET_CHAP && !err)
 				break;
+			if (ev->type == ISCSI_UEVENT_GET_HOST_STATS && !err)
+				break;
 			err = iscsi_if_send_reply(portid, nlh->nlmsg_type,
 						  ev, sizeof(*ev));
 			if (err == -EAGAIN && --retries < 0) {
diff --git a/drivers/scsi/scsi_transport_sas.c b/drivers/scsi/scsi_transport_sas.c
index 4e33f1661e4c..d322802c7790 100644
--- a/drivers/scsi/scsi_transport_sas.c
+++ b/drivers/scsi/scsi_transport_sas.c
@@ -40,6 +40,8 @@
 #include <scsi/scsi_transport_sas.h>
 
 #include "scsi_sas_internal.h"
+#include "scsi_priv.h"
+
 struct sas_host_attrs {
 	struct list_head rphy_list;
 	struct mutex lock;
@@ -1681,32 +1683,66 @@ int scsi_is_sas_rphy(const struct device *dev)
 }
 EXPORT_SYMBOL(scsi_is_sas_rphy);
 
-
-/*
- * SCSI scan helper
- */
-
-static int sas_user_scan(struct Scsi_Host *shost, uint channel,
-		uint id, u64 lun)
+static void scan_channel_zero(struct Scsi_Host *shost, uint id, u64 lun)
 {
 	struct sas_host_attrs *sas_host = to_sas_host_attrs(shost);
 	struct sas_rphy *rphy;
 
-	mutex_lock(&sas_host->lock);
 	list_for_each_entry(rphy, &sas_host->rphy_list, list) {
 		if (rphy->identify.device_type != SAS_END_DEVICE ||
 		    rphy->scsi_target_id == -1)
 			continue;
 
-		if ((channel == SCAN_WILD_CARD || channel == 0) &&
-		    (id == SCAN_WILD_CARD || id == rphy->scsi_target_id)) {
+		if (id == SCAN_WILD_CARD || id == rphy->scsi_target_id) {
 			scsi_scan_target(&rphy->dev, 0, rphy->scsi_target_id,
 					 lun, SCSI_SCAN_MANUAL);
 		}
 	}
-	mutex_unlock(&sas_host->lock);
+}
 
-	return 0;
+/*
+ * SCSI scan helper
+ */
+
+static int sas_user_scan(struct Scsi_Host *shost, uint channel,
+		uint id, u64 lun)
+{
+	struct sas_host_attrs *sas_host = to_sas_host_attrs(shost);
+	int res = 0;
+	int i;
+
+	switch (channel) {
+	case 0:
+		mutex_lock(&sas_host->lock);
+		scan_channel_zero(shost, id, lun);
+		mutex_unlock(&sas_host->lock);
+		break;
+
+	case SCAN_WILD_CARD:
+		mutex_lock(&sas_host->lock);
+		scan_channel_zero(shost, id, lun);
+		mutex_unlock(&sas_host->lock);
+
+		for (i = 1; i <= shost->max_channel; i++) {
+			res = scsi_scan_host_selected(shost, i, id, lun,
+						      SCSI_SCAN_MANUAL);
+			if (res)
+				goto exit_scan;
+		}
+		break;
+
+	default:
+		if (channel < shost->max_channel) {
+			res = scsi_scan_host_selected(shost, channel, id, lun,
+						      SCSI_SCAN_MANUAL);
+		} else {
+			res = -EINVAL;
+		}
+		break;
+	}
+
+exit_scan:
+	return res;
 }
 
 
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index ca4bc0ac76ad..e1b06f803a94 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -1190,8 +1190,8 @@ static u8 sd_group_number(struct scsi_cmnd *cmd)
 	if (!sdkp->rscs)
 		return 0;
 
-	return min3((u32)rq->write_hint, (u32)sdkp->permanent_stream_count,
-		    0x3fu);
+	return min3((u32)rq->bio->bi_write_hint,
+		    (u32)sdkp->permanent_stream_count, 0x3fu);
 }
 
 static blk_status_t sd_setup_rw32_cmnd(struct scsi_cmnd *cmd, bool write,
@@ -1389,7 +1389,7 @@ static blk_status_t sd_setup_read_write_cmnd(struct scsi_cmnd *cmd)
 		ret = sd_setup_rw16_cmnd(cmd, write, lba, nr_blocks,
 					 protect | fua, dld);
 	} else if ((nr_blocks > 0xff) || (lba > 0x1fffff) ||
-		   sdp->use_10_for_rw || protect || rq->write_hint) {
+		   sdp->use_10_for_rw || protect || rq->bio->bi_write_hint) {
 		ret = sd_setup_rw10_cmnd(cmd, write, lba, nr_blocks,
 					 protect | fua);
 	} else {
@@ -3388,7 +3388,7 @@ static void sd_read_block_limits_ext(struct scsi_disk *sdkp)
 
 	rcu_read_lock();
 	vpd = rcu_dereference(sdkp->device->vpd_pgb7);
-	if (vpd && vpd->len >= 2)
+	if (vpd && vpd->len >= 6)
 		sdkp->rscs = vpd->data[5] & 1;
 	rcu_read_unlock();
 }
@@ -4179,7 +4179,9 @@ static void sd_shutdown(struct device *dev)
 	if ((system_state != SYSTEM_RESTART &&
 	     sdkp->device->manage_system_start_stop) ||
 	    (system_state == SYSTEM_POWER_OFF &&
-	     sdkp->device->manage_shutdown)) {
+	     sdkp->device->manage_shutdown) ||
+	    (system_state == SYSTEM_RUNNING &&
+	     sdkp->device->manage_runtime_start_stop)) {
 		sd_printk(KERN_NOTICE, sdkp, "Stopping disk\n");
 		sd_start_stop_device(sdkp, 0);
 	}
diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c
index 6ab27f4f4878..b8d42098f0b6 100644
--- a/drivers/scsi/sd_zbc.c
+++ b/drivers/scsi/sd_zbc.c
@@ -169,6 +169,7 @@ static void *sd_zbc_alloc_report_buffer(struct scsi_disk *sdkp,
 					unsigned int nr_zones, size_t *buflen)
 {
 	struct request_queue *q = sdkp->disk->queue;
+	unsigned int max_segments;
 	size_t bufsize;
 	void *buf;
 
@@ -180,12 +181,15 @@ static void *sd_zbc_alloc_report_buffer(struct scsi_disk *sdkp,
 	 * Furthermore, since the report zone command cannot be split, make
 	 * sure that the allocated buffer can always be mapped by limiting the
 	 * number of pages allocated to the HBA max segments limit.
+	 * Since max segments can be larger than the max inline bio vectors,
+	 * further limit the allocated buffer to BIO_MAX_INLINE_VECS.
 	 */
 	nr_zones = min(nr_zones, sdkp->zone_info.nr_zones);
 	bufsize = roundup((nr_zones + 1) * 64, SECTOR_SIZE);
 	bufsize = min_t(size_t, bufsize,
 			queue_max_hw_sectors(q) << SECTOR_SHIFT);
-	bufsize = min_t(size_t, bufsize, queue_max_segments(q) << PAGE_SHIFT);
+	max_segments = min(BIO_MAX_INLINE_VECS, queue_max_segments(q));
+	bufsize = min_t(size_t, bufsize, max_segments << PAGE_SHIFT);
 
 	while (bufsize >= SECTOR_SIZE) {
 		buf = kvzalloc(bufsize, GFP_KERNEL | __GFP_NORETRY);
diff --git a/drivers/scsi/smartpqi/smartpqi_init.c b/drivers/scsi/smartpqi/smartpqi_init.c
index 870f37b70546..c5a21e369e16 100644
--- a/drivers/scsi/smartpqi/smartpqi_init.c
+++ b/drivers/scsi/smartpqi/smartpqi_init.c
@@ -19,7 +19,7 @@
 #include <linux/bcd.h>
 #include <linux/reboot.h>
 #include <linux/cciss_ioctl.h>
-#include <linux/blk-mq-pci.h>
+#include <linux/crash_dump.h>
 #include <scsi/scsi_host.h>
 #include <scsi/scsi_cmnd.h>
 #include <scsi/scsi_device.h>
@@ -5247,7 +5247,7 @@ static void pqi_calculate_io_resources(struct pqi_ctrl_info *ctrl_info)
 	ctrl_info->error_buffer_length =
 		ctrl_info->max_io_slots * PQI_ERROR_BUFFER_ELEMENT_LENGTH;
 
-	if (reset_devices)
+	if (is_kdump_kernel())
 		max_transfer_size = min(ctrl_info->max_transfer_size,
 			PQI_MAX_TRANSFER_SIZE_KDUMP);
 	else
@@ -5276,7 +5276,7 @@ static void pqi_calculate_queue_resources(struct pqi_ctrl_info *ctrl_info)
 	u16 num_elements_per_iq;
 	u16 num_elements_per_oq;
 
-	if (reset_devices) {
+	if (is_kdump_kernel()) {
 		num_queue_groups = 1;
 	} else {
 		int num_cpus;
@@ -5990,7 +5990,7 @@ static bool pqi_is_parity_write_stream(struct pqi_ctrl_info *ctrl_info,
 			pqi_stream_data->next_lba = rmd.first_block +
 				rmd.block_cnt;
 			pqi_stream_data->last_accessed = jiffies;
-			per_cpu_ptr(device->raid_io_stats, smp_processor_id())->write_stream_cnt++;
+				per_cpu_ptr(device->raid_io_stats, raw_smp_processor_id())->write_stream_cnt++;
 			return true;
 		}
 
@@ -6069,7 +6069,7 @@ static int pqi_scsi_queue_command(struct Scsi_Host *shost, struct scsi_cmnd *scm
 			rc = pqi_raid_bypass_submit_scsi_cmd(ctrl_info, device, scmd, queue_group);
 			if (rc == 0 || rc == SCSI_MLQUEUE_HOST_BUSY) {
 				raid_bypassed = true;
-				per_cpu_ptr(device->raid_io_stats, smp_processor_id())->raid_bypass_cnt++;
+				per_cpu_ptr(device->raid_io_stats, raw_smp_processor_id())->raid_bypass_cnt++;
 			}
 		}
 		if (!raid_bypassed)
@@ -6547,10 +6547,10 @@ static void pqi_map_queues(struct Scsi_Host *shost)
 	struct pqi_ctrl_info *ctrl_info = shost_to_hba(shost);
 
 	if (!ctrl_info->disable_managed_interrupts)
-		return blk_mq_pci_map_queues(&shost->tag_set.map[HCTX_TYPE_DEFAULT],
-			      ctrl_info->pci_dev, 0);
+		blk_mq_map_hw_queues(&shost->tag_set.map[HCTX_TYPE_DEFAULT],
+				       &ctrl_info->pci_dev->dev, 0);
 	else
-		return blk_mq_map_queues(&shost->tag_set.map[HCTX_TYPE_DEFAULT]);
+		blk_mq_map_queues(&shost->tag_set.map[HCTX_TYPE_DEFAULT]);
 }
 
 static inline bool pqi_is_tape_changer_device(struct pqi_scsi_dev *device)
@@ -8288,12 +8288,12 @@ static int pqi_ctrl_init(struct pqi_ctrl_info *ctrl_info)
 	u32 product_id;
 
 	if (reset_devices) {
-		if (pqi_is_fw_triage_supported(ctrl_info)) {
+		if (is_kdump_kernel() && pqi_is_fw_triage_supported(ctrl_info)) {
 			rc = sis_wait_for_fw_triage_completion(ctrl_info);
 			if (rc)
 				return rc;
 		}
-		if (sis_is_ctrl_logging_supported(ctrl_info)) {
+		if (is_kdump_kernel() && sis_is_ctrl_logging_supported(ctrl_info)) {
 			sis_notify_kdump(ctrl_info);
 			rc = sis_wait_for_ctrl_logging_completion(ctrl_info);
 			if (rc)
@@ -8344,7 +8344,7 @@ static int pqi_ctrl_init(struct pqi_ctrl_info *ctrl_info)
 	ctrl_info->product_id = (u8)product_id;
 	ctrl_info->product_revision = (u8)(product_id >> 8);
 
-	if (reset_devices) {
+	if (is_kdump_kernel()) {
 		if (ctrl_info->max_outstanding_requests >
 			PQI_MAX_OUTSTANDING_REQUESTS_KDUMP)
 				ctrl_info->max_outstanding_requests =
@@ -8480,7 +8480,7 @@ static int pqi_ctrl_init(struct pqi_ctrl_info *ctrl_info)
 	if (rc)
 		return rc;
 
-	if (ctrl_info->ctrl_logging_supported && !reset_devices) {
+	if (ctrl_info->ctrl_logging_supported && !is_kdump_kernel()) {
 		pqi_host_setup_buffer(ctrl_info, &ctrl_info->ctrl_log_memory, PQI_CTRL_LOG_TOTAL_SIZE, PQI_CTRL_LOG_MIN_SIZE);
 		pqi_host_memory_update(ctrl_info, &ctrl_info->ctrl_log_memory, PQI_VENDOR_GENERAL_CTRL_LOG_MEMORY_UPDATE);
 	}
@@ -9710,6 +9710,10 @@ static const struct pci_device_id pqi_pci_id_table[] = {
 	},
 	{
 		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+				0x1bd4, 0x00a3)
+	},
+	{
+		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
 			       0x1ff9, 0x00a1)
 	},
 	{
@@ -10046,6 +10050,30 @@ static const struct pci_device_id pqi_pci_id_table[] = {
 	},
 	{
 		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+			       0x207d, 0x4044)
+	},
+	{
+		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+			       0x207d, 0x4054)
+	},
+	{
+		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+			       0x207d, 0x4084)
+	},
+	{
+		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+			       0x207d, 0x4094)
+	},
+	{
+		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+			       0x207d, 0x4140)
+	},
+	{
+		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+			       0x207d, 0x4240)
+	},
+	{
+		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
 			       PCI_VENDOR_ID_ADVANTECH, 0x8312)
 	},
 	{
@@ -10262,6 +10290,14 @@ static const struct pci_device_id pqi_pci_id_table[] = {
 	},
 	{
 		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+			       0x1018, 0x8238)
+	},
+	{
+		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+			       0x1f3f, 0x0610)
+	},
+	{
+		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
 			       PCI_VENDOR_ID_LENOVO, 0x0220)
 	},
 	{
@@ -10270,10 +10306,30 @@ static const struct pci_device_id pqi_pci_id_table[] = {
 	},
 	{
 		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+			       PCI_VENDOR_ID_LENOVO, 0x0222)
+	},
+	{
+		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+			       PCI_VENDOR_ID_LENOVO, 0x0223)
+	},
+	{
+		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+			       PCI_VENDOR_ID_LENOVO, 0x0224)
+	},
+	{
+		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+			       PCI_VENDOR_ID_LENOVO, 0x0225)
+	},
+	{
+		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
 			       PCI_VENDOR_ID_LENOVO, 0x0520)
 	},
 	{
 		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+			       PCI_VENDOR_ID_LENOVO, 0x0521)
+	},
+	{
+		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
 			       PCI_VENDOR_ID_LENOVO, 0x0522)
 	},
 	{
@@ -10294,6 +10350,26 @@ static const struct pci_device_id pqi_pci_id_table[] = {
 	},
 	{
 		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+			       PCI_VENDOR_ID_LENOVO, 0x0624)
+	},
+	{
+		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+			       PCI_VENDOR_ID_LENOVO, 0x0625)
+	},
+	{
+		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+			       PCI_VENDOR_ID_LENOVO, 0x0626)
+	},
+	{
+		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+			       PCI_VENDOR_ID_LENOVO, 0x0627)
+	},
+	{
+		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+			       PCI_VENDOR_ID_LENOVO, 0x0628)
+	},
+	{
+		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
 				0x1014, 0x0718)
 	},
 	{
@@ -10322,6 +10398,10 @@ static const struct pci_device_id pqi_pci_id_table[] = {
 	},
 	{
 		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+				0x1ded, 0x3301)
+	},
+	{
+		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
 			       0x1ff9, 0x0045)
 	},
 	{
@@ -10470,6 +10550,10 @@ static const struct pci_device_id pqi_pci_id_table[] = {
 	},
 	{
 		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+				0x1f51, 0x100b)
+	},
+	{
+		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
 			       0x1f51, 0x100e)
 	},
 	{
diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c
index c9038284bc89..3e982c166baf 100644
--- a/drivers/scsi/st.c
+++ b/drivers/scsi/st.c
@@ -952,7 +952,6 @@ static void reset_state(struct scsi_tape *STp)
 		STp->partition = find_partition(STp);
 		if (STp->partition < 0)
 			STp->partition = 0;
-		STp->new_partition = STp->partition;
 	}
 }
 
@@ -1027,6 +1026,11 @@ static int test_ready(struct scsi_tape *STp, int do_wait)
 			retval = new_session ? CHKRES_NEW_SESSION : CHKRES_READY;
 		break;
 	}
+	if (STp->first_tur) {
+		/* Don't set pos_unknown right after device recognition */
+		STp->pos_unknown = 0;
+		STp->first_tur = 0;
+	}
 
 	if (SRpnt != NULL)
 		st_release_request(SRpnt);
@@ -2889,7 +2893,6 @@ static int st_int_ioctl(struct scsi_tape *STp, unsigned int cmd_in, unsigned lon
 			timeout = STp->long_timeout * 8;
 
 		DEBC_printk(STp, "Erasing tape.\n");
-		fileno = blkno = at_sm = 0;
 		break;
 	case MTSETBLK:		/* Set block length */
 	case MTSETDENSITY:	/* Set tape density */
@@ -2922,14 +2925,17 @@ static int st_int_ioctl(struct scsi_tape *STp, unsigned int cmd_in, unsigned lon
 		if (cmd_in == MTSETDENSITY) {
 			(STp->buffer)->b_data[4] = arg;
 			STp->density_changed = 1;	/* At least we tried ;-) */
+			STp->changed_density = arg;
 		} else if (cmd_in == SET_DENS_AND_BLK)
 			(STp->buffer)->b_data[4] = arg >> 24;
 		else
 			(STp->buffer)->b_data[4] = STp->density;
 		if (cmd_in == MTSETBLK || cmd_in == SET_DENS_AND_BLK) {
 			ltmp = arg & MT_ST_BLKSIZE_MASK;
-			if (cmd_in == MTSETBLK)
+			if (cmd_in == MTSETBLK) {
 				STp->blksize_changed = 1; /* At least we tried ;-) */
+				STp->changed_blksize = arg;
+			}
 		} else
 			ltmp = STp->block_size;
 		(STp->buffer)->b_data[9] = (ltmp >> 16);
@@ -3076,7 +3082,9 @@ static int st_int_ioctl(struct scsi_tape *STp, unsigned int cmd_in, unsigned lon
 			   cmd_in == MTSETDRVBUFFER ||
 			   cmd_in == SET_DENS_AND_BLK) {
 			if (cmdstatp->sense_hdr.sense_key == ILLEGAL_REQUEST &&
-			    !(STp->use_pf & PF_TESTED)) {
+				cmdstatp->sense_hdr.asc == 0x24 &&
+				(STp->device)->scsi_level <= SCSI_2 &&
+				!(STp->use_pf & PF_TESTED)) {
 				/* Try the other possible state of Page Format if not
 				   already tried */
 				STp->use_pf = (STp->use_pf ^ USE_PF) | PF_TESTED;
@@ -3628,9 +3636,25 @@ static long st_ioctl(struct file *file, unsigned int cmd_in, unsigned long arg)
 				retval = (-EIO);
 				goto out;
 			}
-			reset_state(STp);
+			reset_state(STp); /* Clears pos_unknown */
 			/* remove this when the midlevel properly clears was_reset */
 			STp->device->was_reset = 0;
+
+			/* Fix the device settings after reset, ignore errors */
+			if (mtc.mt_op == MTREW || mtc.mt_op == MTSEEK ||
+				mtc.mt_op == MTEOM) {
+				if (STp->can_partitions) {
+					/* STp->new_partition contains the
+					 *  latest partition set
+					 */
+					STp->partition = 0;
+					switch_partition(STp);
+				}
+				if (STp->density_changed)
+					st_int_ioctl(STp, MTSETDENSITY, STp->changed_density);
+				if (STp->blksize_changed)
+					st_int_ioctl(STp, MTSETBLK, STp->changed_blksize);
+			}
 		}
 
 		if (mtc.mt_op != MTNOP && mtc.mt_op != MTSETBLK &&
@@ -4114,7 +4138,7 @@ static void validate_options(void)
  */
 static int __init st_setup(char *str)
 {
-	int i, len, ints[5];
+	int i, len, ints[ARRAY_SIZE(parms) + 1];
 	char *stp;
 
 	stp = get_options(str, ARRAY_SIZE(ints), ints);
@@ -4325,6 +4349,7 @@ static int st_probe(struct device *dev)
 	blk_queue_rq_timeout(tpnt->device->request_queue, ST_TIMEOUT);
 	tpnt->long_timeout = ST_LONG_TIMEOUT;
 	tpnt->try_dio = try_direct_io;
+	tpnt->first_tur = 1;
 
 	for (i = 0; i < ST_NBR_MODES; i++) {
 		STm = &(tpnt->modes[i]);
diff --git a/drivers/scsi/st.h b/drivers/scsi/st.h
index 7a68eaba7e81..6d31b894ee84 100644
--- a/drivers/scsi/st.h
+++ b/drivers/scsi/st.h
@@ -165,12 +165,15 @@ struct scsi_tape {
 	unsigned char compression_changed;
 	unsigned char drv_buffer;
 	unsigned char density;
+	unsigned char changed_density;
 	unsigned char door_locked;
 	unsigned char autorew_dev;   /* auto-rewind device */
 	unsigned char rew_at_close;  /* rewind necessary at close */
 	unsigned char inited;
 	unsigned char cleaning_req;  /* cleaning requested? */
+	unsigned char first_tur;     /* first TEST UNIT READY */
 	int block_size;
+	int changed_blksize;
 	int min_block;
 	int max_block;
 	int recover_count;     /* From tape opening */
diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c
index d0b55c1fa908..954a1cc50ba7 100644
--- a/drivers/scsi/storvsc_drv.c
+++ b/drivers/scsi/storvsc_drv.c
@@ -171,6 +171,12 @@ do {								\
 		dev_warn(&(dev)->device, fmt, ##__VA_ARGS__);	\
 } while (0)
 
+#define storvsc_log_ratelimited(dev, level, fmt, ...)				\
+do {										\
+	if (do_logging(level))							\
+		dev_warn_ratelimited(&(dev)->device, fmt, ##__VA_ARGS__);	\
+} while (0)
+
 struct vmscsi_request {
 	u16 length;
 	u8 srb_status;
@@ -356,7 +362,7 @@ MODULE_PARM_DESC(ring_avail_percent_lowater,
 /*
  * Timeout in seconds for all devices managed by this driver.
  */
-static int storvsc_timeout = 180;
+static const int storvsc_timeout = 180;
 
 #if IS_ENABLED(CONFIG_SCSI_FC_ATTRS)
 static struct scsi_transport_template *fc_transport_template;
@@ -762,7 +768,7 @@ static void  handle_multichannel_storage(struct hv_device *device, int max_chns)
 		return;
 	}
 
-	t = wait_for_completion_timeout(&request->wait_event, 10*HZ);
+	t = wait_for_completion_timeout(&request->wait_event, storvsc_timeout * HZ);
 	if (t == 0) {
 		dev_err(dev, "Failed to create sub-channel: timed out\n");
 		return;
@@ -827,7 +833,7 @@ static int storvsc_execute_vstor_op(struct hv_device *device,
 	if (ret != 0)
 		return ret;
 
-	t = wait_for_completion_timeout(&request->wait_event, 5*HZ);
+	t = wait_for_completion_timeout(&request->wait_event, storvsc_timeout * HZ);
 	if (t == 0)
 		return -ETIMEDOUT;
 
@@ -1177,7 +1183,7 @@ static void storvsc_on_io_completion(struct storvsc_device *stor_device,
 		int loglevel = (stor_pkt->vm_srb.cdb[0] == TEST_UNIT_READY) ?
 			STORVSC_LOGGING_WARN : STORVSC_LOGGING_ERROR;
 
-		storvsc_log(device, loglevel,
+		storvsc_log_ratelimited(device, loglevel,
 			"tag#%d cmd 0x%x status: scsi 0x%x srb 0x%x hv 0x%x\n",
 			scsi_cmd_to_rq(request->cmd)->tag,
 			stor_pkt->vm_srb.cdb[0],
@@ -1345,6 +1351,8 @@ static int storvsc_connect_to_vsp(struct hv_device *device, u32 ring_size,
 		return ret;
 
 	ret = storvsc_channel_init(device, is_fc);
+	if (ret)
+		vmbus_close(device->channel);
 
 	return ret;
 }
@@ -1662,7 +1670,7 @@ static int storvsc_host_reset_handler(struct scsi_cmnd *scmnd)
 	if (ret != 0)
 		return FAILED;
 
-	t = wait_for_completion_timeout(&request->wait_event, 5*HZ);
+	t = wait_for_completion_timeout(&request->wait_event, storvsc_timeout * HZ);
 	if (t == 0)
 		return TIMEOUT_ERROR;
 
@@ -1794,6 +1802,7 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd)
 
 	length = scsi_bufflen(scmnd);
 	payload = (struct vmbus_packet_mpb_array *)&cmd_request->mpb;
+	payload->range.len = 0;
 	payload_sz = 0;
 
 	if (scsi_sg_count(scmnd)) {
@@ -1812,6 +1821,7 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd)
 				return SCSI_MLQUEUE_DEVICE_BUSY;
 		}
 
+		payload->rangecount = 1;
 		payload->range.len = length;
 		payload->range.offset = offset_in_hvpg;
 
diff --git a/drivers/slimbus/messaging.c b/drivers/slimbus/messaging.c
index 242570a5e565..455c1fd1490f 100644
--- a/drivers/slimbus/messaging.c
+++ b/drivers/slimbus/messaging.c
@@ -148,8 +148,9 @@ int slim_do_transfer(struct slim_controller *ctrl, struct slim_msg_txn *txn)
 	}
 
 	ret = ctrl->xfer_msg(ctrl, txn);
-
-	if (!ret && need_tid && !txn->msg->comp) {
+	if (ret == -ETIMEDOUT) {
+		slim_free_txn_tid(ctrl, txn);
+	} else if (!ret && need_tid && !txn->msg->comp) {
 		unsigned long ms = txn->rl + HZ;
 
 		time_left = wait_for_completion_timeout(txn->comp,
diff --git a/drivers/soc/apple/rtkit-internal.h b/drivers/soc/apple/rtkit-internal.h
index 27c9fa745fd5..b8d5244678f0 100644
--- a/drivers/soc/apple/rtkit-internal.h
+++ b/drivers/soc/apple/rtkit-internal.h
@@ -44,6 +44,7 @@ struct apple_rtkit {
 
 	struct apple_rtkit_shmem ioreport_buffer;
 	struct apple_rtkit_shmem crashlog_buffer;
+	struct apple_rtkit_shmem oslog_buffer;
 
 	struct apple_rtkit_shmem syslog_buffer;
 	char *syslog_msg_buffer;
diff --git a/drivers/soc/apple/rtkit.c b/drivers/soc/apple/rtkit.c
index e6d940292c9f..45ccbe2cbcd6 100644
--- a/drivers/soc/apple/rtkit.c
+++ b/drivers/soc/apple/rtkit.c
@@ -66,8 +66,9 @@ enum {
 #define APPLE_RTKIT_SYSLOG_MSG_SIZE  GENMASK_ULL(31, 24)
 
 #define APPLE_RTKIT_OSLOG_TYPE GENMASK_ULL(63, 56)
-#define APPLE_RTKIT_OSLOG_INIT	1
-#define APPLE_RTKIT_OSLOG_ACK	3
+#define APPLE_RTKIT_OSLOG_BUFFER_REQUEST 1
+#define APPLE_RTKIT_OSLOG_SIZE GENMASK_ULL(55, 36)
+#define APPLE_RTKIT_OSLOG_IOVA GENMASK_ULL(35, 0)
 
 #define APPLE_RTKIT_MIN_SUPPORTED_VERSION 11
 #define APPLE_RTKIT_MAX_SUPPORTED_VERSION 12
@@ -251,15 +252,21 @@ static int apple_rtkit_common_rx_get_buffer(struct apple_rtkit *rtk,
 					    struct apple_rtkit_shmem *buffer,
 					    u8 ep, u64 msg)
 {
-	size_t n_4kpages = FIELD_GET(APPLE_RTKIT_BUFFER_REQUEST_SIZE, msg);
 	u64 reply;
 	int err;
 
+	/* The different size vs. IOVA shifts look odd but are indeed correct this way */
+	if (ep == APPLE_RTKIT_EP_OSLOG) {
+		buffer->size = FIELD_GET(APPLE_RTKIT_OSLOG_SIZE, msg);
+		buffer->iova = FIELD_GET(APPLE_RTKIT_OSLOG_IOVA, msg) << 12;
+	} else {
+		buffer->size = FIELD_GET(APPLE_RTKIT_BUFFER_REQUEST_SIZE, msg) << 12;
+		buffer->iova = FIELD_GET(APPLE_RTKIT_BUFFER_REQUEST_IOVA, msg);
+	}
+
 	buffer->buffer = NULL;
 	buffer->iomem = NULL;
 	buffer->is_mapped = false;
-	buffer->iova = FIELD_GET(APPLE_RTKIT_BUFFER_REQUEST_IOVA, msg);
-	buffer->size = n_4kpages << 12;
 
 	dev_dbg(rtk->dev, "RTKit: buffer request for 0x%zx bytes at %pad\n",
 		buffer->size, &buffer->iova);
@@ -284,11 +291,21 @@ static int apple_rtkit_common_rx_get_buffer(struct apple_rtkit *rtk,
 	}
 
 	if (!buffer->is_mapped) {
-		reply = FIELD_PREP(APPLE_RTKIT_SYSLOG_TYPE,
-				   APPLE_RTKIT_BUFFER_REQUEST);
-		reply |= FIELD_PREP(APPLE_RTKIT_BUFFER_REQUEST_SIZE, n_4kpages);
-		reply |= FIELD_PREP(APPLE_RTKIT_BUFFER_REQUEST_IOVA,
-				    buffer->iova);
+		/* oslog uses different fields and needs a shifted IOVA instead of size */
+		if (ep == APPLE_RTKIT_EP_OSLOG) {
+			reply = FIELD_PREP(APPLE_RTKIT_OSLOG_TYPE,
+					   APPLE_RTKIT_OSLOG_BUFFER_REQUEST);
+			reply |= FIELD_PREP(APPLE_RTKIT_OSLOG_SIZE, buffer->size);
+			reply |= FIELD_PREP(APPLE_RTKIT_OSLOG_IOVA,
+					    buffer->iova >> 12);
+		} else {
+			reply = FIELD_PREP(APPLE_RTKIT_SYSLOG_TYPE,
+					   APPLE_RTKIT_BUFFER_REQUEST);
+			reply |= FIELD_PREP(APPLE_RTKIT_BUFFER_REQUEST_SIZE,
+					    buffer->size >> 12);
+			reply |= FIELD_PREP(APPLE_RTKIT_BUFFER_REQUEST_IOVA,
+					    buffer->iova);
+		}
 		apple_rtkit_send_message(rtk, ep, reply, NULL, false);
 	}
 
@@ -482,25 +499,18 @@ static void apple_rtkit_syslog_rx(struct apple_rtkit *rtk, u64 msg)
 	}
 }
 
-static void apple_rtkit_oslog_rx_init(struct apple_rtkit *rtk, u64 msg)
-{
-	u64 ack;
-
-	dev_dbg(rtk->dev, "RTKit: oslog init: msg: 0x%llx\n", msg);
-	ack = FIELD_PREP(APPLE_RTKIT_OSLOG_TYPE, APPLE_RTKIT_OSLOG_ACK);
-	apple_rtkit_send_message(rtk, APPLE_RTKIT_EP_OSLOG, ack, NULL, false);
-}
-
 static void apple_rtkit_oslog_rx(struct apple_rtkit *rtk, u64 msg)
 {
 	u8 type = FIELD_GET(APPLE_RTKIT_OSLOG_TYPE, msg);
 
 	switch (type) {
-	case APPLE_RTKIT_OSLOG_INIT:
-		apple_rtkit_oslog_rx_init(rtk, msg);
+	case APPLE_RTKIT_OSLOG_BUFFER_REQUEST:
+		apple_rtkit_common_rx_get_buffer(rtk, &rtk->oslog_buffer,
+						 APPLE_RTKIT_EP_OSLOG, msg);
 		break;
 	default:
-		dev_warn(rtk->dev, "RTKit: Unknown oslog message: %llx\n", msg);
+		dev_warn(rtk->dev, "RTKit: Unknown oslog message: %llx\n",
+			 msg);
 	}
 }
 
@@ -667,7 +677,7 @@ struct apple_rtkit *apple_rtkit_init(struct device *dev, void *cookie,
 	rtk->mbox->rx = apple_rtkit_rx;
 	rtk->mbox->cookie = rtk;
 
-	rtk->wq = alloc_ordered_workqueue("rtkit-%s", WQ_MEM_RECLAIM,
+	rtk->wq = alloc_ordered_workqueue("rtkit-%s", WQ_HIGHPRI | WQ_MEM_RECLAIM,
 					  dev_name(rtk->dev));
 	if (!rtk->wq) {
 		ret = -ENOMEM;
@@ -710,6 +720,7 @@ int apple_rtkit_reinit(struct apple_rtkit *rtk)
 
 	apple_rtkit_free_buffer(rtk, &rtk->ioreport_buffer);
 	apple_rtkit_free_buffer(rtk, &rtk->crashlog_buffer);
+	apple_rtkit_free_buffer(rtk, &rtk->oslog_buffer);
 	apple_rtkit_free_buffer(rtk, &rtk->syslog_buffer);
 
 	kfree(rtk->syslog_msg_buffer);
@@ -890,6 +901,7 @@ void apple_rtkit_free(struct apple_rtkit *rtk)
 
 	apple_rtkit_free_buffer(rtk, &rtk->ioreport_buffer);
 	apple_rtkit_free_buffer(rtk, &rtk->crashlog_buffer);
+	apple_rtkit_free_buffer(rtk, &rtk->oslog_buffer);
 	apple_rtkit_free_buffer(rtk, &rtk->syslog_buffer);
 
 	kfree(rtk->syslog_msg_buffer);
diff --git a/drivers/soc/aspeed/aspeed-lpc-snoop.c b/drivers/soc/aspeed/aspeed-lpc-snoop.c
index 888b5840c015..54db2abc2e2a 100644
--- a/drivers/soc/aspeed/aspeed-lpc-snoop.c
+++ b/drivers/soc/aspeed/aspeed-lpc-snoop.c
@@ -58,6 +58,7 @@ struct aspeed_lpc_snoop_model_data {
 };
 
 struct aspeed_lpc_snoop_channel {
+	bool enabled;
 	struct kfifo		fifo;
 	wait_queue_head_t	wq;
 	struct miscdevice	miscdev;
@@ -166,7 +167,7 @@ static int aspeed_lpc_snoop_config_irq(struct aspeed_lpc_snoop *lpc_snoop,
 	int rc;
 
 	lpc_snoop->irq = platform_get_irq(pdev, 0);
-	if (!lpc_snoop->irq)
+	if (lpc_snoop->irq < 0)
 		return -ENODEV;
 
 	rc = devm_request_irq(dev, lpc_snoop->irq,
@@ -190,6 +191,9 @@ static int aspeed_lpc_enable_snoop(struct aspeed_lpc_snoop *lpc_snoop,
 	const struct aspeed_lpc_snoop_model_data *model_data =
 		of_device_get_match_data(dev);
 
+	if (WARN_ON(lpc_snoop->chan[channel].enabled))
+		return -EBUSY;
+
 	init_waitqueue_head(&lpc_snoop->chan[channel].wq);
 	/* Create FIFO datastructure */
 	rc = kfifo_alloc(&lpc_snoop->chan[channel].fifo,
@@ -200,11 +204,15 @@ static int aspeed_lpc_enable_snoop(struct aspeed_lpc_snoop *lpc_snoop,
 	lpc_snoop->chan[channel].miscdev.minor = MISC_DYNAMIC_MINOR;
 	lpc_snoop->chan[channel].miscdev.name =
 		devm_kasprintf(dev, GFP_KERNEL, "%s%d", DEVICE_NAME, channel);
+	if (!lpc_snoop->chan[channel].miscdev.name) {
+		rc = -ENOMEM;
+		goto err_free_fifo;
+	}
 	lpc_snoop->chan[channel].miscdev.fops = &snoop_fops;
 	lpc_snoop->chan[channel].miscdev.parent = dev;
 	rc = misc_register(&lpc_snoop->chan[channel].miscdev);
 	if (rc)
-		return rc;
+		goto err_free_fifo;
 
 	/* Enable LPC snoop channel at requested port */
 	switch (channel) {
@@ -221,7 +229,8 @@ static int aspeed_lpc_enable_snoop(struct aspeed_lpc_snoop *lpc_snoop,
 		hicrb_en = HICRB_ENSNP1D;
 		break;
 	default:
-		return -EINVAL;
+		rc = -EINVAL;
+		goto err_misc_deregister;
 	}
 
 	regmap_update_bits(lpc_snoop->regmap, HICR5, hicr5_en, hicr5_en);
@@ -231,12 +240,23 @@ static int aspeed_lpc_enable_snoop(struct aspeed_lpc_snoop *lpc_snoop,
 		regmap_update_bits(lpc_snoop->regmap, HICRB,
 				hicrb_en, hicrb_en);
 
+	lpc_snoop->chan[channel].enabled = true;
+
+	return 0;
+
+err_misc_deregister:
+	misc_deregister(&lpc_snoop->chan[channel].miscdev);
+err_free_fifo:
+	kfifo_free(&lpc_snoop->chan[channel].fifo);
 	return rc;
 }
 
 static void aspeed_lpc_disable_snoop(struct aspeed_lpc_snoop *lpc_snoop,
 				     int channel)
 {
+	if (!lpc_snoop->chan[channel].enabled)
+		return;
+
 	switch (channel) {
 	case 0:
 		regmap_update_bits(lpc_snoop->regmap, HICR5,
@@ -252,8 +272,10 @@ static void aspeed_lpc_disable_snoop(struct aspeed_lpc_snoop *lpc_snoop,
 		return;
 	}
 
-	kfifo_free(&lpc_snoop->chan[channel].fifo);
+	lpc_snoop->chan[channel].enabled = false;
+	/* Consider improving safety wrt concurrent reader(s) */
 	misc_deregister(&lpc_snoop->chan[channel].miscdev);
+	kfifo_free(&lpc_snoop->chan[channel].fifo);
 }
 
 static int aspeed_lpc_snoop_probe(struct platform_device *pdev)
diff --git a/drivers/soc/atmel/soc.c b/drivers/soc/atmel/soc.c
index 2a42b28931c9..298b542dd1c0 100644
--- a/drivers/soc/atmel/soc.c
+++ b/drivers/soc/atmel/soc.c
@@ -399,7 +399,7 @@ static const struct of_device_id at91_soc_allowed_list[] __initconst = {
 
 static int __init atmel_soc_device_init(void)
 {
-	struct device_node *np = of_find_node_by_path("/");
+	struct device_node *np __free(device_node) = of_find_node_by_path("/");
 
 	if (!of_match_node(at91_soc_allowed_list, np))
 		return 0;
diff --git a/drivers/soc/imx/soc-imx8m.c b/drivers/soc/imx/soc-imx8m.c
index 5ea8887828c0..3ed8161d7d28 100644
--- a/drivers/soc/imx/soc-imx8m.c
+++ b/drivers/soc/imx/soc-imx8m.c
@@ -30,11 +30,9 @@
 
 struct imx8_soc_data {
 	char *name;
-	int (*soc_revision)(u32 *socrev);
+	int (*soc_revision)(u32 *socrev, u64 *socuid);
 };
 
-static u64 soc_uid;
-
 #ifdef CONFIG_HAVE_ARM_SMCCC
 static u32 imx8mq_soc_revision_from_atf(void)
 {
@@ -51,24 +49,22 @@ static u32 imx8mq_soc_revision_from_atf(void)
 static inline u32 imx8mq_soc_revision_from_atf(void) { return 0; };
 #endif
 
-static int imx8mq_soc_revision(u32 *socrev)
+static int imx8mq_soc_revision(u32 *socrev, u64 *socuid)
 {
-	struct device_node *np;
+	struct device_node *np __free(device_node) =
+		of_find_compatible_node(NULL, NULL, "fsl,imx8mq-ocotp");
 	void __iomem *ocotp_base;
 	u32 magic;
 	u32 rev;
 	struct clk *clk;
 	int ret;
 
-	np = of_find_compatible_node(NULL, NULL, "fsl,imx8mq-ocotp");
 	if (!np)
 		return -EINVAL;
 
 	ocotp_base = of_iomap(np, 0);
-	if (!ocotp_base) {
-		ret = -EINVAL;
-		goto err_iomap;
-	}
+	if (!ocotp_base)
+		return -EINVAL;
 
 	clk = of_clk_get_by_name(np, NULL);
 	if (IS_ERR(clk)) {
@@ -89,44 +85,39 @@ static int imx8mq_soc_revision(u32 *socrev)
 			rev = REV_B1;
 	}
 
-	soc_uid = readl_relaxed(ocotp_base + OCOTP_UID_HIGH);
-	soc_uid <<= 32;
-	soc_uid |= readl_relaxed(ocotp_base + OCOTP_UID_LOW);
+	*socuid = readl_relaxed(ocotp_base + OCOTP_UID_HIGH);
+	*socuid <<= 32;
+	*socuid |= readl_relaxed(ocotp_base + OCOTP_UID_LOW);
 
 	*socrev = rev;
 
 	clk_disable_unprepare(clk);
 	clk_put(clk);
 	iounmap(ocotp_base);
-	of_node_put(np);
 
 	return 0;
 
 err_clk:
 	iounmap(ocotp_base);
-err_iomap:
-	of_node_put(np);
 	return ret;
 }
 
-static int imx8mm_soc_uid(void)
+static int imx8mm_soc_uid(u64 *socuid)
 {
+	struct device_node *np __free(device_node) =
+		of_find_compatible_node(NULL, NULL, "fsl,imx8mm-ocotp");
 	void __iomem *ocotp_base;
-	struct device_node *np;
 	struct clk *clk;
 	int ret = 0;
 	u32 offset = of_machine_is_compatible("fsl,imx8mp") ?
 		     IMX8MP_OCOTP_UID_OFFSET : 0;
 
-	np = of_find_compatible_node(NULL, NULL, "fsl,imx8mm-ocotp");
 	if (!np)
 		return -EINVAL;
 
 	ocotp_base = of_iomap(np, 0);
-	if (!ocotp_base) {
-		ret = -EINVAL;
-		goto err_iomap;
-	}
+	if (!ocotp_base)
+		return -EINVAL;
 
 	clk = of_clk_get_by_name(np, NULL);
 	if (IS_ERR(clk)) {
@@ -136,47 +127,36 @@ static int imx8mm_soc_uid(void)
 
 	clk_prepare_enable(clk);
 
-	soc_uid = readl_relaxed(ocotp_base + OCOTP_UID_HIGH + offset);
-	soc_uid <<= 32;
-	soc_uid |= readl_relaxed(ocotp_base + OCOTP_UID_LOW + offset);
+	*socuid = readl_relaxed(ocotp_base + OCOTP_UID_HIGH + offset);
+	*socuid <<= 32;
+	*socuid |= readl_relaxed(ocotp_base + OCOTP_UID_LOW + offset);
 
 	clk_disable_unprepare(clk);
 	clk_put(clk);
 
 err_clk:
 	iounmap(ocotp_base);
-err_iomap:
-	of_node_put(np);
-
 	return ret;
 }
 
-static int imx8mm_soc_revision(u32 *socrev)
+static int imx8mm_soc_revision(u32 *socrev, u64 *socuid)
 {
-	struct device_node *np;
+	struct device_node *np __free(device_node) =
+		of_find_compatible_node(NULL, NULL, "fsl,imx8mm-anatop");
 	void __iomem *anatop_base;
-	int ret;
 
-	np = of_find_compatible_node(NULL, NULL, "fsl,imx8mm-anatop");
 	if (!np)
 		return -EINVAL;
 
 	anatop_base = of_iomap(np, 0);
-	if (!anatop_base) {
-		ret = -EINVAL;
-		goto err_iomap;
-	}
+	if (!anatop_base)
+		return -EINVAL;
 
 	*socrev = readl_relaxed(anatop_base + ANADIG_DIGPROG_IMX8MM);
 
 	iounmap(anatop_base);
-	of_node_put(np);
 
-	return imx8mm_soc_uid();
-
-err_iomap:
-	of_node_put(np);
-	return ret;
+	return imx8mm_soc_uid(socuid);
 }
 
 static const struct imx8_soc_data imx8mq_soc_data = {
@@ -207,21 +187,34 @@ static __maybe_unused const struct of_device_id imx8_soc_match[] = {
 	{ }
 };
 
-#define imx8_revision(soc_rev) \
-	soc_rev ? \
-	kasprintf(GFP_KERNEL, "%d.%d", (soc_rev >> 4) & 0xf,  soc_rev & 0xf) : \
+#define imx8_revision(dev, soc_rev) \
+	(soc_rev) ? \
+	devm_kasprintf((dev), GFP_KERNEL, "%d.%d", ((soc_rev) >> 4) & 0xf, (soc_rev) & 0xf) : \
 	"unknown"
 
+static void imx8m_unregister_soc(void *data)
+{
+	soc_device_unregister(data);
+}
+
+static void imx8m_unregister_cpufreq(void *data)
+{
+	platform_device_unregister(data);
+}
+
 static int imx8m_soc_probe(struct platform_device *pdev)
 {
 	struct soc_device_attribute *soc_dev_attr;
-	struct soc_device *soc_dev;
+	struct platform_device *cpufreq_dev;
+	const struct imx8_soc_data *data;
+	struct device *dev = &pdev->dev;
 	const struct of_device_id *id;
+	struct soc_device *soc_dev;
 	u32 soc_rev = 0;
-	const struct imx8_soc_data *data;
+	u64 soc_uid = 0;
 	int ret;
 
-	soc_dev_attr = kzalloc(sizeof(*soc_dev_attr), GFP_KERNEL);
+	soc_dev_attr = devm_kzalloc(dev, sizeof(*soc_dev_attr), GFP_KERNEL);
 	if (!soc_dev_attr)
 		return -ENOMEM;
 
@@ -229,58 +222,52 @@ static int imx8m_soc_probe(struct platform_device *pdev)
 
 	ret = of_property_read_string(of_root, "model", &soc_dev_attr->machine);
 	if (ret)
-		goto free_soc;
+		return ret;
 
 	id = of_match_node(imx8_soc_match, of_root);
-	if (!id) {
-		ret = -ENODEV;
-		goto free_soc;
-	}
+	if (!id)
+		return -ENODEV;
 
 	data = id->data;
 	if (data) {
 		soc_dev_attr->soc_id = data->name;
 		if (data->soc_revision) {
-			ret = data->soc_revision(&soc_rev);
+			ret = data->soc_revision(&soc_rev, &soc_uid);
 			if (ret)
-				goto free_soc;
+				return ret;
 		}
 	}
 
-	soc_dev_attr->revision = imx8_revision(soc_rev);
-	if (!soc_dev_attr->revision) {
-		ret = -ENOMEM;
-		goto free_soc;
-	}
+	soc_dev_attr->revision = imx8_revision(dev, soc_rev);
+	if (!soc_dev_attr->revision)
+		return -ENOMEM;
 
-	soc_dev_attr->serial_number = kasprintf(GFP_KERNEL, "%016llX", soc_uid);
-	if (!soc_dev_attr->serial_number) {
-		ret = -ENOMEM;
-		goto free_rev;
-	}
+	soc_dev_attr->serial_number = devm_kasprintf(dev, GFP_KERNEL, "%016llX", soc_uid);
+	if (!soc_dev_attr->serial_number)
+		return -ENOMEM;
 
 	soc_dev = soc_device_register(soc_dev_attr);
-	if (IS_ERR(soc_dev)) {
-		ret = PTR_ERR(soc_dev);
-		goto free_serial_number;
-	}
+	if (IS_ERR(soc_dev))
+		return PTR_ERR(soc_dev);
+
+	ret = devm_add_action(dev, imx8m_unregister_soc, soc_dev);
+	if (ret)
+		return ret;
 
 	pr_info("SoC: %s revision %s\n", soc_dev_attr->soc_id,
 		soc_dev_attr->revision);
 
-	if (IS_ENABLED(CONFIG_ARM_IMX_CPUFREQ_DT))
-		platform_device_register_simple("imx-cpufreq-dt", -1, NULL, 0);
+	if (IS_ENABLED(CONFIG_ARM_IMX_CPUFREQ_DT)) {
+		cpufreq_dev = platform_device_register_simple("imx-cpufreq-dt", -1, NULL, 0);
+		if (IS_ERR(cpufreq_dev))
+			return dev_err_probe(dev, PTR_ERR(cpufreq_dev),
+					     "Failed to register imx-cpufreq-dev device\n");
+		ret = devm_add_action(dev, imx8m_unregister_cpufreq, cpufreq_dev);
+		if (ret)
+			return ret;
+	}
 
 	return 0;
-
-free_serial_number:
-	kfree(soc_dev_attr->serial_number);
-free_rev:
-	if (strcmp(soc_dev_attr->revision, "unknown"))
-		kfree(soc_dev_attr->revision);
-free_soc:
-	kfree(soc_dev_attr);
-	return ret;
 }
 
 static struct platform_driver imx8m_soc_driver = {
diff --git a/drivers/soc/loongson/loongson2_guts.c b/drivers/soc/loongson/loongson2_guts.c
index ef352a0f5022..1fcf7ca8083e 100644
--- a/drivers/soc/loongson/loongson2_guts.c
+++ b/drivers/soc/loongson/loongson2_guts.c
@@ -114,8 +114,11 @@ static int loongson2_guts_probe(struct platform_device *pdev)
 	if (of_property_read_string(root, "model", &machine))
 		of_property_read_string_index(root, "compatible", 0, &machine);
 	of_node_put(root);
-	if (machine)
+	if (machine) {
 		soc_dev_attr.machine = devm_kstrdup(dev, machine, GFP_KERNEL);
+		if (!soc_dev_attr.machine)
+			return -ENOMEM;
+	}
 
 	svr = loongson2_guts_get_svr();
 	soc_die = loongson2_soc_die_match(svr, loongson2_soc_die);
diff --git a/drivers/soc/mediatek/mtk-devapc.c b/drivers/soc/mediatek/mtk-devapc.c
index 56cc345552a4..d83a46334adb 100644
--- a/drivers/soc/mediatek/mtk-devapc.c
+++ b/drivers/soc/mediatek/mtk-devapc.c
@@ -273,23 +273,31 @@ static int mtk_devapc_probe(struct platform_device *pdev)
 		return -EINVAL;
 
 	devapc_irq = irq_of_parse_and_map(node, 0);
-	if (!devapc_irq)
-		return -EINVAL;
+	if (!devapc_irq) {
+		ret = -EINVAL;
+		goto err;
+	}
 
 	ctx->infra_clk = devm_clk_get_enabled(&pdev->dev, "devapc-infra-clock");
-	if (IS_ERR(ctx->infra_clk))
-		return -EINVAL;
+	if (IS_ERR(ctx->infra_clk)) {
+		ret = -EINVAL;
+		goto err;
+	}
 
 	ret = devm_request_irq(&pdev->dev, devapc_irq, devapc_violation_irq,
 			       IRQF_TRIGGER_NONE, "devapc", ctx);
 	if (ret)
-		return ret;
+		goto err;
 
 	platform_set_drvdata(pdev, ctx);
 
 	start_devapc(ctx);
 
 	return 0;
+
+err:
+	iounmap(ctx->infra_base);
+	return ret;
 }
 
 static void mtk_devapc_remove(struct platform_device *pdev)
@@ -297,6 +305,7 @@ static void mtk_devapc_remove(struct platform_device *pdev)
 	struct mtk_devapc_context *ctx = platform_get_drvdata(pdev);
 
 	stop_devapc(ctx);
+	iounmap(ctx->infra_base);
 }
 
 static struct platform_driver mtk_devapc_driver = {
diff --git a/drivers/soc/mediatek/mtk-mutex.c b/drivers/soc/mediatek/mtk-mutex.c
index 5250c1d702eb..aaa965d4b050 100644
--- a/drivers/soc/mediatek/mtk-mutex.c
+++ b/drivers/soc/mediatek/mtk-mutex.c
@@ -155,6 +155,7 @@
 #define MT8188_MUTEX_MOD_DISP1_VPP_MERGE3	23
 #define MT8188_MUTEX_MOD_DISP1_VPP_MERGE4	24
 #define MT8188_MUTEX_MOD_DISP1_DISP_MIXER	30
+#define MT8188_MUTEX_MOD_DISP1_DPI1		38
 #define MT8188_MUTEX_MOD_DISP1_DP_INTF1		39
 
 #define MT8195_MUTEX_MOD_DISP_OVL0		0
@@ -289,6 +290,7 @@
 #define MT8188_MUTEX_SOF_DSI0			1
 #define MT8188_MUTEX_SOF_DP_INTF0		3
 #define MT8188_MUTEX_SOF_DP_INTF1		4
+#define MT8188_MUTEX_SOF_DPI1			5
 #define MT8195_MUTEX_SOF_DSI0			1
 #define MT8195_MUTEX_SOF_DSI1			2
 #define MT8195_MUTEX_SOF_DP_INTF0		3
@@ -301,6 +303,7 @@
 #define MT8188_MUTEX_EOF_DSI0			(MT8188_MUTEX_SOF_DSI0 << 7)
 #define MT8188_MUTEX_EOF_DP_INTF0		(MT8188_MUTEX_SOF_DP_INTF0 << 7)
 #define MT8188_MUTEX_EOF_DP_INTF1		(MT8188_MUTEX_SOF_DP_INTF1 << 7)
+#define MT8188_MUTEX_EOF_DPI1			(MT8188_MUTEX_SOF_DPI1 << 7)
 #define MT8195_MUTEX_EOF_DSI0			(MT8195_MUTEX_SOF_DSI0 << 7)
 #define MT8195_MUTEX_EOF_DSI1			(MT8195_MUTEX_SOF_DSI1 << 7)
 #define MT8195_MUTEX_EOF_DP_INTF0		(MT8195_MUTEX_SOF_DP_INTF0 << 7)
@@ -472,6 +475,7 @@ static const u8 mt8188_mutex_mod[DDP_COMPONENT_ID_MAX] = {
 	[DDP_COMPONENT_PWM0] = MT8188_MUTEX_MOD2_DISP_PWM0,
 	[DDP_COMPONENT_DP_INTF0] = MT8188_MUTEX_MOD_DISP_DP_INTF0,
 	[DDP_COMPONENT_DP_INTF1] = MT8188_MUTEX_MOD_DISP1_DP_INTF1,
+	[DDP_COMPONENT_DPI1] = MT8188_MUTEX_MOD_DISP1_DPI1,
 	[DDP_COMPONENT_ETHDR_MIXER] = MT8188_MUTEX_MOD_DISP1_DISP_MIXER,
 	[DDP_COMPONENT_MDP_RDMA0] = MT8188_MUTEX_MOD_DISP1_MDP_RDMA0,
 	[DDP_COMPONENT_MDP_RDMA1] = MT8188_MUTEX_MOD_DISP1_MDP_RDMA1,
@@ -686,6 +690,8 @@ static const u16 mt8188_mutex_sof[DDP_MUTEX_SOF_MAX] = {
 	[MUTEX_SOF_SINGLE_MODE] = MUTEX_SOF_SINGLE_MODE,
 	[MUTEX_SOF_DSI0] =
 		MT8188_MUTEX_SOF_DSI0 | MT8188_MUTEX_EOF_DSI0,
+	[MUTEX_SOF_DPI1] =
+		MT8188_MUTEX_SOF_DPI1 | MT8188_MUTEX_EOF_DPI1,
 	[MUTEX_SOF_DP_INTF0] =
 		MT8188_MUTEX_SOF_DP_INTF0 | MT8188_MUTEX_EOF_DP_INTF0,
 	[MUTEX_SOF_DP_INTF1] =
diff --git a/drivers/soc/qcom/ice.c b/drivers/soc/qcom/ice.c
index 50be7a9274a1..9d89bfc50e8b 100644
--- a/drivers/soc/qcom/ice.c
+++ b/drivers/soc/qcom/ice.c
@@ -11,6 +11,7 @@
 #include <linux/cleanup.h>
 #include <linux/clk.h>
 #include <linux/delay.h>
+#include <linux/device.h>
 #include <linux/iopoll.h>
 #include <linux/of.h>
 #include <linux/of_platform.h>
@@ -324,6 +325,53 @@ struct qcom_ice *of_qcom_ice_get(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(of_qcom_ice_get);
 
+static void qcom_ice_put(const struct qcom_ice *ice)
+{
+	struct platform_device *pdev = to_platform_device(ice->dev);
+
+	if (!platform_get_resource_byname(pdev, IORESOURCE_MEM, "ice"))
+		platform_device_put(pdev);
+}
+
+static void devm_of_qcom_ice_put(struct device *dev, void *res)
+{
+	qcom_ice_put(*(struct qcom_ice **)res);
+}
+
+/**
+ * devm_of_qcom_ice_get() - Devres managed helper to get an ICE instance from
+ * a DT node.
+ * @dev: device pointer for the consumer device.
+ *
+ * This function will provide an ICE instance either by creating one for the
+ * consumer device if its DT node provides the 'ice' reg range and the 'ice'
+ * clock (for legacy DT style). On the other hand, if consumer provides a
+ * phandle via 'qcom,ice' property to an ICE DT, the ICE instance will already
+ * be created and so this function will return that instead.
+ *
+ * Return: ICE pointer on success, NULL if there is no ICE data provided by the
+ * consumer or ERR_PTR() on error.
+ */
+struct qcom_ice *devm_of_qcom_ice_get(struct device *dev)
+{
+	struct qcom_ice *ice, **dr;
+
+	dr = devres_alloc(devm_of_qcom_ice_put, sizeof(*dr), GFP_KERNEL);
+	if (!dr)
+		return ERR_PTR(-ENOMEM);
+
+	ice = of_qcom_ice_get(dev);
+	if (!IS_ERR_OR_NULL(ice)) {
+		*dr = ice;
+		devres_add(dev, dr);
+	} else {
+		devres_free(dr);
+	}
+
+	return ice;
+}
+EXPORT_SYMBOL_GPL(devm_of_qcom_ice_get);
+
 static int qcom_ice_probe(struct platform_device *pdev)
 {
 	struct qcom_ice *engine;
diff --git a/drivers/soc/qcom/llcc-qcom.c b/drivers/soc/qcom/llcc-qcom.c
index a470285f54a8..133dc4833313 100644
--- a/drivers/soc/qcom/llcc-qcom.c
+++ b/drivers/soc/qcom/llcc-qcom.c
@@ -2511,6 +2511,7 @@ static const struct llcc_slice_config x1e80100_data[] = {
 		.fixed_size = true,
 		.bonus_ways = 0xfff,
 		.cache_mode = 0,
+		.activate_on_init = true,
 	}, {
 		.usecase_id = LLCC_CAMEXP0,
 		.slice_id = 4,
diff --git a/drivers/soc/qcom/mdt_loader.c b/drivers/soc/qcom/mdt_loader.c
index b2c0fb55d4ae..44589d10b15b 100644
--- a/drivers/soc/qcom/mdt_loader.c
+++ b/drivers/soc/qcom/mdt_loader.c
@@ -83,7 +83,7 @@ ssize_t qcom_mdt_get_size(const struct firmware *fw)
 	int i;
 
 	ehdr = (struct elf32_hdr *)fw->data;
-	phdrs = (struct elf32_phdr *)(ehdr + 1);
+	phdrs = (struct elf32_phdr *)(fw->data + ehdr->e_phoff);
 
 	for (i = 0; i < ehdr->e_phnum; i++) {
 		phdr = &phdrs[i];
@@ -135,7 +135,7 @@ void *qcom_mdt_read_metadata(const struct firmware *fw, size_t *data_len,
 	void *data;
 
 	ehdr = (struct elf32_hdr *)fw->data;
-	phdrs = (struct elf32_phdr *)(ehdr + 1);
+	phdrs = (struct elf32_phdr *)(fw->data + ehdr->e_phoff);
 
 	if (ehdr->e_phnum < 2)
 		return ERR_PTR(-EINVAL);
@@ -215,7 +215,7 @@ int qcom_mdt_pas_init(struct device *dev, const struct firmware *fw,
 	int i;
 
 	ehdr = (struct elf32_hdr *)fw->data;
-	phdrs = (struct elf32_phdr *)(ehdr + 1);
+	phdrs = (struct elf32_phdr *)(fw->data + ehdr->e_phoff);
 
 	for (i = 0; i < ehdr->e_phnum; i++) {
 		phdr = &phdrs[i];
@@ -270,7 +270,7 @@ static bool qcom_mdt_bins_are_split(const struct firmware *fw, const char *fw_na
 	int i;
 
 	ehdr = (struct elf32_hdr *)fw->data;
-	phdrs = (struct elf32_phdr *)(ehdr + 1);
+	phdrs = (struct elf32_phdr *)(fw->data + ehdr->e_phoff);
 
 	for (i = 0; i < ehdr->e_phnum; i++) {
 		/*
@@ -312,7 +312,7 @@ static int __qcom_mdt_load(struct device *dev, const struct firmware *fw,
 
 	is_split = qcom_mdt_bins_are_split(fw, fw_name);
 	ehdr = (struct elf32_hdr *)fw->data;
-	phdrs = (struct elf32_phdr *)(ehdr + 1);
+	phdrs = (struct elf32_phdr *)(fw->data + ehdr->e_phoff);
 
 	for (i = 0; i < ehdr->e_phnum; i++) {
 		phdr = &phdrs[i];
diff --git a/drivers/soc/qcom/pdr_interface.c b/drivers/soc/qcom/pdr_interface.c
index 328b6153b2be..71be378d2e43 100644
--- a/drivers/soc/qcom/pdr_interface.c
+++ b/drivers/soc/qcom/pdr_interface.c
@@ -75,7 +75,6 @@ static int pdr_locator_new_server(struct qmi_handle *qmi,
 {
 	struct pdr_handle *pdr = container_of(qmi, struct pdr_handle,
 					      locator_hdl);
-	struct pdr_service *pds;
 
 	mutex_lock(&pdr->lock);
 	/* Create a local client port for QMI communication */
@@ -87,12 +86,7 @@ static int pdr_locator_new_server(struct qmi_handle *qmi,
 	mutex_unlock(&pdr->lock);
 
 	/* Service pending lookup requests */
-	mutex_lock(&pdr->list_lock);
-	list_for_each_entry(pds, &pdr->lookups, node) {
-		if (pds->need_locator_lookup)
-			schedule_work(&pdr->locator_work);
-	}
-	mutex_unlock(&pdr->list_lock);
+	schedule_work(&pdr->locator_work);
 
 	return 0;
 }
diff --git a/drivers/soc/qcom/pmic_glink.c b/drivers/soc/qcom/pmic_glink.c
index baa4ac6704a9..5963f49f6e6e 100644
--- a/drivers/soc/qcom/pmic_glink.c
+++ b/drivers/soc/qcom/pmic_glink.c
@@ -169,7 +169,10 @@ static int pmic_glink_rpmsg_callback(struct rpmsg_device *rpdev, void *data,
 	return 0;
 }
 
-static void pmic_glink_aux_release(struct device *dev) {}
+static void pmic_glink_aux_release(struct device *dev)
+{
+	of_node_put(dev->of_node);
+}
 
 static int pmic_glink_add_aux_device(struct pmic_glink *pg,
 				     struct auxiliary_device *aux,
@@ -183,8 +186,10 @@ static int pmic_glink_add_aux_device(struct pmic_glink *pg,
 	aux->dev.release = pmic_glink_aux_release;
 	device_set_of_node_from_dev(&aux->dev, parent);
 	ret = auxiliary_device_init(aux);
-	if (ret)
+	if (ret) {
+		of_node_put(aux->dev.of_node);
 		return ret;
+	}
 
 	ret = auxiliary_device_add(aux);
 	if (ret)
diff --git a/drivers/soc/qcom/pmic_glink_altmode.c b/drivers/soc/qcom/pmic_glink_altmode.c
index 463b1c528831..db25f406878b 100644
--- a/drivers/soc/qcom/pmic_glink_altmode.c
+++ b/drivers/soc/qcom/pmic_glink_altmode.c
@@ -219,21 +219,29 @@ static void pmic_glink_altmode_worker(struct work_struct *work)
 {
 	struct pmic_glink_altmode_port *alt_port = work_to_altmode_port(work);
 	struct pmic_glink_altmode *altmode = alt_port->altmode;
+	enum drm_connector_status conn_status;
 
 	typec_switch_set(alt_port->typec_switch, alt_port->orientation);
 
-	if (alt_port->svid == USB_TYPEC_DP_SID && alt_port->mode == 0xff)
-		pmic_glink_altmode_safe(altmode, alt_port);
-	else if (alt_port->svid == USB_TYPEC_DP_SID)
-		pmic_glink_altmode_enable_dp(altmode, alt_port, alt_port->mode,
-					     alt_port->hpd_state, alt_port->hpd_irq);
-	else
-		pmic_glink_altmode_enable_usb(altmode, alt_port);
+	if (alt_port->svid == USB_TYPEC_DP_SID) {
+		if (alt_port->mode == 0xff) {
+			pmic_glink_altmode_safe(altmode, alt_port);
+		} else {
+			pmic_glink_altmode_enable_dp(altmode, alt_port,
+						     alt_port->mode,
+						     alt_port->hpd_state,
+						     alt_port->hpd_irq);
+		}
 
-	drm_aux_hpd_bridge_notify(&alt_port->bridge->dev,
-				  alt_port->hpd_state ?
-				  connector_status_connected :
-				  connector_status_disconnected);
+		if (alt_port->hpd_state)
+			conn_status = connector_status_connected;
+		else
+			conn_status = connector_status_disconnected;
+
+		drm_aux_hpd_bridge_notify(&alt_port->bridge->dev, conn_status);
+	} else {
+		pmic_glink_altmode_enable_usb(altmode, alt_port);
+	}
 
 	pmic_glink_altmode_request(altmode, ALTMODE_PAN_ACK, alt_port->index);
 }
diff --git a/drivers/soc/qcom/qmi_encdec.c b/drivers/soc/qcom/qmi_encdec.c
index bb09eff85cff..dafe0a4c202e 100644
--- a/drivers/soc/qcom/qmi_encdec.c
+++ b/drivers/soc/qcom/qmi_encdec.c
@@ -304,6 +304,8 @@ static int qmi_encode(const struct qmi_elem_info *ei_array, void *out_buf,
 	const void *buf_src;
 	int encode_tlv = 0;
 	int rc;
+	u8 val8;
+	u16 val16;
 
 	if (!ei_array)
 		return 0;
@@ -338,7 +340,6 @@ static int qmi_encode(const struct qmi_elem_info *ei_array, void *out_buf,
 			break;
 
 		case QMI_DATA_LEN:
-			memcpy(&data_len_value, buf_src, temp_ei->elem_size);
 			data_len_sz = temp_ei->elem_size == sizeof(u8) ?
 					sizeof(u8) : sizeof(u16);
 			/* Check to avoid out of range buffer access */
@@ -348,8 +349,17 @@ static int qmi_encode(const struct qmi_elem_info *ei_array, void *out_buf,
 				       __func__);
 				return -ETOOSMALL;
 			}
-			rc = qmi_encode_basic_elem(buf_dst, &data_len_value,
-						   1, data_len_sz);
+			if (data_len_sz == sizeof(u8)) {
+				val8 = *(u8 *)buf_src;
+				data_len_value = (u32)val8;
+				rc = qmi_encode_basic_elem(buf_dst, &val8,
+							   1, data_len_sz);
+			} else {
+				val16 = *(u16 *)buf_src;
+				data_len_value = (u32)le16_to_cpu(val16);
+				rc = qmi_encode_basic_elem(buf_dst, &val16,
+							   1, data_len_sz);
+			}
 			UPDATE_ENCODE_VARIABLES(temp_ei, buf_dst,
 						encoded_bytes, tlv_len,
 						encode_tlv, rc);
@@ -523,14 +533,23 @@ static int qmi_decode_string_elem(const struct qmi_elem_info *ei_array,
 	u32 string_len = 0;
 	u32 string_len_sz = 0;
 	const struct qmi_elem_info *temp_ei = ei_array;
+	u8 val8;
+	u16 val16;
 
 	if (dec_level == 1) {
 		string_len = tlv_len;
 	} else {
 		string_len_sz = temp_ei->elem_len <= U8_MAX ?
 				sizeof(u8) : sizeof(u16);
-		rc = qmi_decode_basic_elem(&string_len, buf_src,
-					   1, string_len_sz);
+		if (string_len_sz == sizeof(u8)) {
+			rc = qmi_decode_basic_elem(&val8, buf_src,
+						   1, string_len_sz);
+			string_len = (u32)val8;
+		} else {
+			rc = qmi_decode_basic_elem(&val16, buf_src,
+						   1, string_len_sz);
+			string_len = (u32)val16;
+		}
 		decoded_bytes += rc;
 	}
 
@@ -604,6 +623,9 @@ static int qmi_decode(const struct qmi_elem_info *ei_array, void *out_c_struct,
 	u32 decoded_bytes = 0;
 	const void *buf_src = in_buf;
 	int rc;
+	u8 val8;
+	u16 val16;
+	u32 val32;
 
 	while (decoded_bytes < in_buf_len) {
 		if (dec_level >= 2 && temp_ei->data_type == QMI_EOTI)
@@ -642,9 +664,17 @@ static int qmi_decode(const struct qmi_elem_info *ei_array, void *out_c_struct,
 		if (temp_ei->data_type == QMI_DATA_LEN) {
 			data_len_sz = temp_ei->elem_size == sizeof(u8) ?
 					sizeof(u8) : sizeof(u16);
-			rc = qmi_decode_basic_elem(&data_len_value, buf_src,
-						   1, data_len_sz);
-			memcpy(buf_dst, &data_len_value, sizeof(u32));
+			if (data_len_sz == sizeof(u8)) {
+				rc = qmi_decode_basic_elem(&val8, buf_src,
+							   1, data_len_sz);
+				data_len_value = (u32)val8;
+			} else {
+				rc = qmi_decode_basic_elem(&val16, buf_src,
+							   1, data_len_sz);
+				data_len_value = (u32)val16;
+			}
+			val32 = cpu_to_le32(data_len_value);
+			memcpy(buf_dst, &val32, sizeof(u32));
 			temp_ei = temp_ei + 1;
 			buf_dst = out_c_struct + temp_ei->offset;
 			tlv_len -= data_len_sz;
diff --git a/drivers/soc/qcom/rpmh-rsc.c b/drivers/soc/qcom/rpmh-rsc.c
index de86009ecd91..641f29a98cbd 100644
--- a/drivers/soc/qcom/rpmh-rsc.c
+++ b/drivers/soc/qcom/rpmh-rsc.c
@@ -1075,7 +1075,7 @@ static int rpmh_rsc_probe(struct platform_device *pdev)
 	drv->ver.minor = rsc_id & (MINOR_VER_MASK << MINOR_VER_SHIFT);
 	drv->ver.minor >>= MINOR_VER_SHIFT;
 
-	if (drv->ver.major == 3)
+	if (drv->ver.major >= 3)
 		drv->regs = rpmh_rsc_reg_offset_ver_3_0;
 	else
 		drv->regs = rpmh_rsc_reg_offset_ver_2_7;
diff --git a/drivers/soc/qcom/smem_state.c b/drivers/soc/qcom/smem_state.c
index e848cc9a3cf8..a8be3a2f3382 100644
--- a/drivers/soc/qcom/smem_state.c
+++ b/drivers/soc/qcom/smem_state.c
@@ -116,7 +116,8 @@ struct qcom_smem_state *qcom_smem_state_get(struct device *dev,
 
 	if (args.args_count != 1) {
 		dev_err(dev, "invalid #qcom,smem-state-cells\n");
-		return ERR_PTR(-EINVAL);
+		state = ERR_PTR(-EINVAL);
+		goto put;
 	}
 
 	state = of_node_to_state(args.np);
diff --git a/drivers/soc/qcom/smp2p.c b/drivers/soc/qcom/smp2p.c
index cefcbd61c628..95d8a8f728db 100644
--- a/drivers/soc/qcom/smp2p.c
+++ b/drivers/soc/qcom/smp2p.c
@@ -578,7 +578,7 @@ static int qcom_smp2p_probe(struct platform_device *pdev)
 	smp2p->mbox_client.knows_txdone = true;
 	smp2p->mbox_chan = mbox_request_channel(&smp2p->mbox_client, 0);
 	if (IS_ERR(smp2p->mbox_chan)) {
-		if (PTR_ERR(smp2p->mbox_chan) != -ENODEV)
+		if (PTR_ERR(smp2p->mbox_chan) != -ENOENT)
 			return PTR_ERR(smp2p->mbox_chan);
 
 		smp2p->mbox_chan = NULL;
diff --git a/drivers/soc/qcom/socinfo.c b/drivers/soc/qcom/socinfo.c
index ecfd3da9d5e8..c2f2a1ce4194 100644
--- a/drivers/soc/qcom/socinfo.c
+++ b/drivers/soc/qcom/socinfo.c
@@ -789,7 +789,7 @@ static int qcom_socinfo_probe(struct platform_device *pdev)
 	if (!qs->attr.soc_id || !qs->attr.revision)
 		return -ENOMEM;
 
-	if (offsetof(struct socinfo, serial_num) <= item_size) {
+	if (offsetofend(struct socinfo, serial_num) <= item_size) {
 		qs->attr.serial_number = devm_kasprintf(&pdev->dev, GFP_KERNEL,
 							"%u",
 							le32_to_cpu(info->serial_num));
diff --git a/drivers/soc/samsung/exynos-asv.c b/drivers/soc/samsung/exynos-asv.c
index 97006cc3b946..8e681f519526 100644
--- a/drivers/soc/samsung/exynos-asv.c
+++ b/drivers/soc/samsung/exynos-asv.c
@@ -9,6 +9,7 @@
  * Samsung Exynos SoC Adaptive Supply Voltage support
  */
 
+#include <linux/array_size.h>
 #include <linux/cpu.h>
 #include <linux/device.h>
 #include <linux/energy_model.h>
diff --git a/drivers/soc/samsung/exynos-chipid.c b/drivers/soc/samsung/exynos-chipid.c
index b1118d37779e..dedfe6d0fb3f 100644
--- a/drivers/soc/samsung/exynos-chipid.c
+++ b/drivers/soc/samsung/exynos-chipid.c
@@ -12,6 +12,7 @@
  * Samsung Exynos SoC Adaptive Supply Voltage and Chip ID support
  */
 
+#include <linux/array_size.h>
 #include <linux/device.h>
 #include <linux/errno.h>
 #include <linux/mfd/syscon.h>
@@ -131,6 +132,8 @@ static int exynos_chipid_probe(struct platform_device *pdev)
 
 	soc_dev_attr->revision = devm_kasprintf(&pdev->dev, GFP_KERNEL,
 						"%x", soc_info.revision);
+	if (!soc_dev_attr->revision)
+		return -ENOMEM;
 	soc_dev_attr->soc_id = product_id_to_soc_id(soc_info.product_id);
 	if (!soc_dev_attr->soc_id) {
 		pr_err("Unknown SoC\n");
diff --git a/drivers/soc/samsung/exynos-pmu.c b/drivers/soc/samsung/exynos-pmu.c
index d8c53cec7f37..c40313886a01 100644
--- a/drivers/soc/samsung/exynos-pmu.c
+++ b/drivers/soc/samsung/exynos-pmu.c
@@ -5,6 +5,7 @@
 //
 // Exynos - CPU PMU(Power Management Unit) support
 
+#include <linux/array_size.h>
 #include <linux/arm-smccc.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
@@ -126,7 +127,7 @@ static int tensor_set_bits_atomic(void *ctx, unsigned int offset, u32 val,
 		if (ret)
 			return ret;
 	}
-	return ret;
+	return 0;
 }
 
 static bool tensor_is_atomic(unsigned int reg)
diff --git a/drivers/soc/samsung/exynos-usi.c b/drivers/soc/samsung/exynos-usi.c
index 114352695ac2..5a93a68dba87 100644
--- a/drivers/soc/samsung/exynos-usi.c
+++ b/drivers/soc/samsung/exynos-usi.c
@@ -6,6 +6,7 @@
  * Samsung Exynos USI driver (Universal Serial Interface).
  */
 
+#include <linux/array_size.h>
 #include <linux/clk.h>
 #include <linux/mfd/syscon.h>
 #include <linux/module.h>
diff --git a/drivers/soc/samsung/exynos3250-pmu.c b/drivers/soc/samsung/exynos3250-pmu.c
index 30f230ed1769..4bad12a99542 100644
--- a/drivers/soc/samsung/exynos3250-pmu.c
+++ b/drivers/soc/samsung/exynos3250-pmu.c
@@ -5,6 +5,7 @@
 //
 // Exynos3250 - CPU PMU (Power Management Unit) support
 
+#include <linux/array_size.h>
 #include <linux/soc/samsung/exynos-regs-pmu.h>
 #include <linux/soc/samsung/exynos-pmu.h>
 
diff --git a/drivers/soc/samsung/exynos5250-pmu.c b/drivers/soc/samsung/exynos5250-pmu.c
index 7a2d50be6b4a..2ae5c3e1b07a 100644
--- a/drivers/soc/samsung/exynos5250-pmu.c
+++ b/drivers/soc/samsung/exynos5250-pmu.c
@@ -5,6 +5,7 @@
 //
 // Exynos5250 - CPU PMU (Power Management Unit) support
 
+#include <linux/array_size.h>
 #include <linux/soc/samsung/exynos-regs-pmu.h>
 #include <linux/soc/samsung/exynos-pmu.h>
 
diff --git a/drivers/soc/samsung/exynos5420-pmu.c b/drivers/soc/samsung/exynos5420-pmu.c
index 6fedcd78cb45..58a2209795f7 100644
--- a/drivers/soc/samsung/exynos5420-pmu.c
+++ b/drivers/soc/samsung/exynos5420-pmu.c
@@ -5,6 +5,7 @@
 //
 // Exynos5420 - CPU PMU (Power Management Unit) support
 
+#include <linux/array_size.h>
 #include <linux/pm.h>
 #include <linux/soc/samsung/exynos-regs-pmu.h>
 #include <linux/soc/samsung/exynos-pmu.h>
diff --git a/drivers/soc/tegra/cbb/tegra234-cbb.c b/drivers/soc/tegra/cbb/tegra234-cbb.c
index 5cf0e8c34164..e8cc46874c72 100644
--- a/drivers/soc/tegra/cbb/tegra234-cbb.c
+++ b/drivers/soc/tegra/cbb/tegra234-cbb.c
@@ -185,6 +185,8 @@ static void tegra234_cbb_error_clear(struct tegra_cbb *cbb)
 {
 	struct tegra234_cbb *priv = to_tegra234_cbb(cbb);
 
+	writel(0, priv->mon + FABRIC_MN_MASTER_ERR_FORCE_0);
+
 	writel(0x3f, priv->mon + FABRIC_MN_MASTER_ERR_STATUS_0);
 	dsb(sy);
 }
diff --git a/drivers/soc/tegra/fuse/fuse-tegra30.c b/drivers/soc/tegra/fuse/fuse-tegra30.c
index eb14e5ff5a0a..e24ab5f7d2bf 100644
--- a/drivers/soc/tegra/fuse/fuse-tegra30.c
+++ b/drivers/soc/tegra/fuse/fuse-tegra30.c
@@ -647,15 +647,20 @@ static const struct nvmem_cell_lookup tegra234_fuse_lookups[] = {
 };
 
 static const struct nvmem_keepout tegra234_fuse_keepouts[] = {
-	{ .start = 0x01c, .end = 0x0c8 },
-	{ .start = 0x12c, .end = 0x184 },
+	{ .start = 0x01c, .end = 0x064 },
+	{ .start = 0x084, .end = 0x0a0 },
+	{ .start = 0x0a4, .end = 0x0c8 },
+	{ .start = 0x12c, .end = 0x164 },
+	{ .start = 0x16c, .end = 0x184 },
 	{ .start = 0x190, .end = 0x198 },
 	{ .start = 0x1a0, .end = 0x204 },
-	{ .start = 0x21c, .end = 0x250 },
-	{ .start = 0x25c, .end = 0x2f0 },
+	{ .start = 0x21c, .end = 0x2f0 },
 	{ .start = 0x310, .end = 0x3d8 },
-	{ .start = 0x400, .end = 0x4f0 },
-	{ .start = 0x4f8, .end = 0x7e8 },
+	{ .start = 0x400, .end = 0x420 },
+	{ .start = 0x444, .end = 0x490 },
+	{ .start = 0x4bc, .end = 0x4f0 },
+	{ .start = 0x4f8, .end = 0x54c },
+	{ .start = 0x57c, .end = 0x7e8 },
 	{ .start = 0x8d0, .end = 0x8d8 },
 	{ .start = 0xacc, .end = 0xf00 }
 };
diff --git a/drivers/soc/ti/k3-socinfo.c b/drivers/soc/ti/k3-socinfo.c
index 4fb0f0a24828..704039eb3c07 100644
--- a/drivers/soc/ti/k3-socinfo.c
+++ b/drivers/soc/ti/k3-socinfo.c
@@ -105,6 +105,12 @@ err_unknown_variant:
 	return -ENODEV;
 }
 
+static const struct regmap_config k3_chipinfo_regmap_cfg = {
+	.reg_bits = 32,
+	.val_bits = 32,
+	.reg_stride = 4,
+};
+
 static int k3_chipinfo_probe(struct platform_device *pdev)
 {
 	struct device_node *node = pdev->dev.of_node;
@@ -112,13 +118,18 @@ static int k3_chipinfo_probe(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	struct soc_device *soc_dev;
 	struct regmap *regmap;
+	void __iomem *base;
 	u32 partno_id;
 	u32 variant;
 	u32 jtag_id;
 	u32 mfg;
 	int ret;
 
-	regmap = device_node_to_regmap(node);
+	base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	regmap = regmap_init_mmio(dev, base, &k3_chipinfo_regmap_cfg);
 	if (IS_ERR(regmap))
 		return PTR_ERR(regmap);
 
diff --git a/drivers/soundwire/amd_manager.c b/drivers/soundwire/amd_manager.c
index 0d01849c3586..a325ce52c396 100644
--- a/drivers/soundwire/amd_manager.c
+++ b/drivers/soundwire/amd_manager.c
@@ -187,7 +187,7 @@ static u64 amd_sdw_send_cmd_get_resp(struct amd_sdw_manager *amd_manager, u32 lo
 
 	if (sts & AMD_SDW_IMM_RES_VALID) {
 		dev_err(amd_manager->dev, "SDW%x manager is in bad state\n", amd_manager->instance);
-		writel(0x00, amd_manager->mmio + ACP_SW_IMM_CMD_STS);
+		writel(AMD_SDW_IMM_RES_VALID, amd_manager->mmio + ACP_SW_IMM_CMD_STS);
 	}
 	writel(upper_data, amd_manager->mmio + ACP_SW_IMM_CMD_UPPER_WORD);
 	writel(lower_data, amd_manager->mmio + ACP_SW_IMM_CMD_LOWER_QWORD);
@@ -972,6 +972,7 @@ static void amd_sdw_manager_remove(struct platform_device *pdev)
 	int ret;
 
 	pm_runtime_disable(&pdev->dev);
+	cancel_work_sync(&amd_manager->amd_sdw_work);
 	amd_disable_sdw_interrupts(amd_manager);
 	sdw_bus_master_delete(&amd_manager->bus);
 	ret = amd_disable_sdw_manager(amd_manager);
@@ -1076,10 +1077,10 @@ static int __maybe_unused amd_pm_prepare(struct device *dev)
 	 * device is not in runtime suspend state, observed that device alerts are missing
 	 * without pm_prepare on AMD platforms in clockstop mode0.
 	 */
-	if (amd_manager->power_mode_mask & AMD_SDW_CLK_STOP_MODE) {
-		ret = pm_request_resume(dev);
+	if (amd_manager->power_mode_mask) {
+		ret = pm_runtime_resume(dev);
 		if (ret < 0) {
-			dev_err(bus->dev, "pm_request_resume failed: %d\n", ret);
+			dev_err(bus->dev, "pm_runtime_resume failed: %d\n", ret);
 			return 0;
 		}
 	}
@@ -1107,9 +1108,12 @@ static int __maybe_unused amd_suspend(struct device *dev)
 	}
 
 	if (amd_manager->power_mode_mask & AMD_SDW_CLK_STOP_MODE) {
+		cancel_work_sync(&amd_manager->amd_sdw_work);
 		amd_sdw_wake_enable(amd_manager, false);
 		return amd_sdw_clock_stop(amd_manager);
 	} else if (amd_manager->power_mode_mask & AMD_SDW_POWER_OFF_MODE) {
+		cancel_work_sync(&amd_manager->amd_sdw_work);
+		amd_sdw_wake_enable(amd_manager, false);
 		/*
 		 * As per hardware programming sequence on AMD platforms,
 		 * clock stop should be invoked first before powering-off
@@ -1137,6 +1141,7 @@ static int __maybe_unused amd_suspend_runtime(struct device *dev)
 		amd_sdw_wake_enable(amd_manager, true);
 		return amd_sdw_clock_stop(amd_manager);
 	} else if (amd_manager->power_mode_mask & AMD_SDW_POWER_OFF_MODE) {
+		amd_sdw_wake_enable(amd_manager, true);
 		ret = amd_sdw_clock_stop(amd_manager);
 		if (ret)
 			return ret;
diff --git a/drivers/soundwire/bus.c b/drivers/soundwire/bus.c
index 263ca32f0c5c..6c7989e2079e 100644
--- a/drivers/soundwire/bus.c
+++ b/drivers/soundwire/bus.c
@@ -121,6 +121,10 @@ int sdw_bus_master_add(struct sdw_bus *bus, struct device *parent,
 	set_bit(SDW_GROUP13_DEV_NUM, bus->assigned);
 	set_bit(SDW_MASTER_DEV_NUM, bus->assigned);
 
+	ret = sdw_irq_create(bus, fwnode);
+	if (ret)
+		return ret;
+
 	/*
 	 * SDW is an enumerable bus, but devices can be powered off. So,
 	 * they won't be able to report as present.
@@ -137,6 +141,7 @@ int sdw_bus_master_add(struct sdw_bus *bus, struct device *parent,
 
 	if (ret < 0) {
 		dev_err(bus->dev, "Finding slaves failed:%d\n", ret);
+		sdw_irq_delete(bus);
 		return ret;
 	}
 
@@ -155,10 +160,6 @@ int sdw_bus_master_add(struct sdw_bus *bus, struct device *parent,
 	bus->params.curr_bank = SDW_BANK0;
 	bus->params.next_bank = SDW_BANK1;
 
-	ret = sdw_irq_create(bus, fwnode);
-	if (ret)
-		return ret;
-
 	return 0;
 }
 EXPORT_SYMBOL(sdw_bus_master_add);
@@ -1731,15 +1732,15 @@ static int sdw_handle_slave_alerts(struct sdw_slave *slave)
 
 		/* Update the Slave driver */
 		if (slave_notify) {
+			if (slave->prop.use_domain_irq && slave->irq)
+				handle_nested_irq(slave->irq);
+
 			mutex_lock(&slave->sdw_dev_lock);
 
 			if (slave->probed) {
 				struct device *dev = &slave->dev;
 				struct sdw_driver *drv = drv_to_sdw_driver(dev->driver);
 
-				if (slave->prop.use_domain_irq && slave->irq)
-					handle_nested_irq(slave->irq);
-
 				if (drv->ops && drv->ops->interrupt_callback) {
 					slave_intr.sdca_cascade = sdca_cascade;
 					slave_intr.control_port = clear;
diff --git a/drivers/soundwire/cadence_master.c b/drivers/soundwire/cadence_master.c
index 05652e983539..6f2b5ec5c87c 100644
--- a/drivers/soundwire/cadence_master.c
+++ b/drivers/soundwire/cadence_master.c
@@ -1341,7 +1341,7 @@ static u32 cdns_set_initial_frame_shape(int n_rows, int n_cols)
 	return val;
 }
 
-static void cdns_init_clock_ctrl(struct sdw_cdns *cdns)
+static int cdns_init_clock_ctrl(struct sdw_cdns *cdns)
 {
 	struct sdw_bus *bus = &cdns->bus;
 	struct sdw_master_prop *prop = &bus->prop;
@@ -1355,14 +1355,25 @@ static void cdns_init_clock_ctrl(struct sdw_cdns *cdns)
 		prop->default_row,
 		prop->default_col);
 
+	if (!prop->default_frame_rate || !prop->default_row) {
+		dev_err(cdns->dev, "Default frame_rate %d or row %d is invalid\n",
+			prop->default_frame_rate, prop->default_row);
+		return -EINVAL;
+	}
+
 	/* Set clock divider */
-	divider	= (prop->mclk_freq / prop->max_clk_freq) - 1;
+	divider	= (prop->mclk_freq * SDW_DOUBLE_RATE_FACTOR /
+		bus->params.curr_dr_freq) - 1;
 
 	cdns_updatel(cdns, CDNS_MCP_CLK_CTRL0,
 		     CDNS_MCP_CLK_MCLKD_MASK, divider);
 	cdns_updatel(cdns, CDNS_MCP_CLK_CTRL1,
 		     CDNS_MCP_CLK_MCLKD_MASK, divider);
 
+	/* Set frame shape base on the actual bus frequency. */
+	prop->default_col = bus->params.curr_dr_freq /
+			    prop->default_frame_rate / prop->default_row;
+
 	/*
 	 * Frame shape changes after initialization have to be done
 	 * with the bank switch mechanism
@@ -1375,6 +1386,8 @@ static void cdns_init_clock_ctrl(struct sdw_cdns *cdns)
 	ssp_interval = prop->default_frame_rate / SDW_CADENCE_GSYNC_HZ;
 	cdns_writel(cdns, CDNS_MCP_SSP_CTRL0, ssp_interval);
 	cdns_writel(cdns, CDNS_MCP_SSP_CTRL1, ssp_interval);
+
+	return 0;
 }
 
 /**
@@ -1383,9 +1396,12 @@ static void cdns_init_clock_ctrl(struct sdw_cdns *cdns)
  */
 int sdw_cdns_init(struct sdw_cdns *cdns)
 {
+	int ret;
 	u32 val;
 
-	cdns_init_clock_ctrl(cdns);
+	ret = cdns_init_clock_ctrl(cdns);
+	if (ret)
+		return ret;
 
 	sdw_cdns_check_self_clearing_bits(cdns, __func__, false, 0);
 
diff --git a/drivers/soundwire/slave.c b/drivers/soundwire/slave.c
index f1a4df6cfebd..2bcb733de4de 100644
--- a/drivers/soundwire/slave.c
+++ b/drivers/soundwire/slave.c
@@ -12,6 +12,7 @@ static void sdw_slave_release(struct device *dev)
 {
 	struct sdw_slave *slave = dev_to_sdw_dev(dev);
 
+	of_node_put(slave->dev.of_node);
 	mutex_destroy(&slave->sdw_dev_lock);
 	kfree(slave);
 }
diff --git a/drivers/soundwire/stream.c b/drivers/soundwire/stream.c
index 7aa4900dcf31..6c1e3aed8162 100644
--- a/drivers/soundwire/stream.c
+++ b/drivers/soundwire/stream.c
@@ -1414,7 +1414,7 @@ static int _sdw_prepare_stream(struct sdw_stream_runtime *stream,
 		if (ret < 0) {
 			dev_err(bus->dev, "Prepare port(s) failed ret = %d\n",
 				ret);
-			return ret;
+			goto restore_params;
 		}
 	}
 
diff --git a/drivers/spi/atmel-quadspi.c b/drivers/spi/atmel-quadspi.c
index caecb2ad2a15..02d83e2956cd 100644
--- a/drivers/spi/atmel-quadspi.c
+++ b/drivers/spi/atmel-quadspi.c
@@ -138,11 +138,15 @@
 #define QSPI_WPSR_WPVSRC_MASK           GENMASK(15, 8)
 #define QSPI_WPSR_WPVSRC(src)           (((src) << 8) & QSPI_WPSR_WPVSRC)
 
+#define ATMEL_QSPI_TIMEOUT		1000	/* ms */
+
 struct atmel_qspi_caps {
 	bool has_qspick;
 	bool has_ricr;
 };
 
+struct atmel_qspi_ops;
+
 struct atmel_qspi {
 	void __iomem		*regs;
 	void __iomem		*mem;
@@ -150,13 +154,22 @@ struct atmel_qspi {
 	struct clk		*qspick;
 	struct platform_device	*pdev;
 	const struct atmel_qspi_caps *caps;
+	const struct atmel_qspi_ops *ops;
 	resource_size_t		mmap_size;
 	u32			pending;
+	u32			irq_mask;
 	u32			mr;
 	u32			scr;
 	struct completion	cmd_completion;
 };
 
+struct atmel_qspi_ops {
+	int (*set_cfg)(struct atmel_qspi *aq, const struct spi_mem_op *op,
+		       u32 *offset);
+	int (*transfer)(struct spi_mem *mem, const struct spi_mem_op *op,
+			u32 offset);
+};
+
 struct atmel_qspi_mode {
 	u8 cmd_buswidth;
 	u8 addr_buswidth;
@@ -404,10 +417,67 @@ static int atmel_qspi_set_cfg(struct atmel_qspi *aq,
 	return 0;
 }
 
+static int atmel_qspi_wait_for_completion(struct atmel_qspi *aq, u32 irq_mask)
+{
+	int err = 0;
+	u32 sr;
+
+	/* Poll INSTRuction End status */
+	sr = atmel_qspi_read(aq, QSPI_SR);
+	if ((sr & irq_mask) == irq_mask)
+		return 0;
+
+	/* Wait for INSTRuction End interrupt */
+	reinit_completion(&aq->cmd_completion);
+	aq->pending = sr & irq_mask;
+	aq->irq_mask = irq_mask;
+	atmel_qspi_write(irq_mask, aq, QSPI_IER);
+	if (!wait_for_completion_timeout(&aq->cmd_completion,
+					 msecs_to_jiffies(ATMEL_QSPI_TIMEOUT)))
+		err = -ETIMEDOUT;
+	atmel_qspi_write(irq_mask, aq, QSPI_IDR);
+
+	return err;
+}
+
+static int atmel_qspi_transfer(struct spi_mem *mem,
+			       const struct spi_mem_op *op, u32 offset)
+{
+	struct atmel_qspi *aq = spi_controller_get_devdata(mem->spi->controller);
+
+	/* Skip to the final steps if there is no data */
+	if (!op->data.nbytes)
+		return atmel_qspi_wait_for_completion(aq,
+						      QSPI_SR_CMD_COMPLETED);
+
+	/* Dummy read of QSPI_IFR to synchronize APB and AHB accesses */
+	(void)atmel_qspi_read(aq, QSPI_IFR);
+
+	/* Send/Receive data */
+	if (op->data.dir == SPI_MEM_DATA_IN) {
+		memcpy_fromio(op->data.buf.in, aq->mem + offset,
+			      op->data.nbytes);
+
+		/* Synchronize AHB and APB accesses again */
+		rmb();
+	} else {
+		memcpy_toio(aq->mem + offset, op->data.buf.out,
+			    op->data.nbytes);
+
+		/* Synchronize AHB and APB accesses again */
+		wmb();
+	}
+
+	/* Release the chip-select */
+	atmel_qspi_write(QSPI_CR_LASTXFER, aq, QSPI_CR);
+
+	return atmel_qspi_wait_for_completion(aq, QSPI_SR_CMD_COMPLETED);
+}
+
 static int atmel_qspi_exec_op(struct spi_mem *mem, const struct spi_mem_op *op)
 {
 	struct atmel_qspi *aq = spi_controller_get_devdata(mem->spi->controller);
-	u32 sr, offset;
+	u32 offset;
 	int err;
 
 	/*
@@ -416,46 +486,20 @@ static int atmel_qspi_exec_op(struct spi_mem *mem, const struct spi_mem_op *op)
 	 * when the flash memories overrun the controller's memory space.
 	 */
 	if (op->addr.val + op->data.nbytes > aq->mmap_size)
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
+
+	if (op->addr.nbytes > 4)
+		return -EOPNOTSUPP;
 
 	err = pm_runtime_resume_and_get(&aq->pdev->dev);
 	if (err < 0)
 		return err;
 
-	err = atmel_qspi_set_cfg(aq, op, &offset);
+	err = aq->ops->set_cfg(aq, op, &offset);
 	if (err)
 		goto pm_runtime_put;
 
-	/* Skip to the final steps if there is no data */
-	if (op->data.nbytes) {
-		/* Dummy read of QSPI_IFR to synchronize APB and AHB accesses */
-		(void)atmel_qspi_read(aq, QSPI_IFR);
-
-		/* Send/Receive data */
-		if (op->data.dir == SPI_MEM_DATA_IN)
-			memcpy_fromio(op->data.buf.in, aq->mem + offset,
-				      op->data.nbytes);
-		else
-			memcpy_toio(aq->mem + offset, op->data.buf.out,
-				    op->data.nbytes);
-
-		/* Release the chip-select */
-		atmel_qspi_write(QSPI_CR_LASTXFER, aq, QSPI_CR);
-	}
-
-	/* Poll INSTRuction End status */
-	sr = atmel_qspi_read(aq, QSPI_SR);
-	if ((sr & QSPI_SR_CMD_COMPLETED) == QSPI_SR_CMD_COMPLETED)
-		goto pm_runtime_put;
-
-	/* Wait for INSTRuction End interrupt */
-	reinit_completion(&aq->cmd_completion);
-	aq->pending = sr & QSPI_SR_CMD_COMPLETED;
-	atmel_qspi_write(QSPI_SR_CMD_COMPLETED, aq, QSPI_IER);
-	if (!wait_for_completion_timeout(&aq->cmd_completion,
-					 msecs_to_jiffies(1000)))
-		err = -ETIMEDOUT;
-	atmel_qspi_write(QSPI_SR_CMD_COMPLETED, aq, QSPI_IDR);
+	err = aq->ops->transfer(mem, op, offset);
 
 pm_runtime_put:
 	pm_runtime_mark_last_busy(&aq->pdev->dev);
@@ -571,12 +615,17 @@ static irqreturn_t atmel_qspi_interrupt(int irq, void *dev_id)
 		return IRQ_NONE;
 
 	aq->pending |= pending;
-	if ((aq->pending & QSPI_SR_CMD_COMPLETED) == QSPI_SR_CMD_COMPLETED)
+	if ((aq->pending & aq->irq_mask) == aq->irq_mask)
 		complete(&aq->cmd_completion);
 
 	return IRQ_HANDLED;
 }
 
+static const struct atmel_qspi_ops atmel_qspi_ops = {
+	.set_cfg = atmel_qspi_set_cfg,
+	.transfer = atmel_qspi_transfer,
+};
+
 static int atmel_qspi_probe(struct platform_device *pdev)
 {
 	struct spi_controller *ctrl;
@@ -601,6 +650,7 @@ static int atmel_qspi_probe(struct platform_device *pdev)
 
 	init_completion(&aq->cmd_completion);
 	aq->pdev = pdev;
+	aq->ops = &atmel_qspi_ops;
 
 	/* Map the registers */
 	aq->regs = devm_platform_ioremap_resource_byname(pdev, "qspi_base");
diff --git a/drivers/spi/spi-bcm2835.c b/drivers/spi/spi-bcm2835.c
index e1b9b1235787..5926e004d9a6 100644
--- a/drivers/spi/spi-bcm2835.c
+++ b/drivers/spi/spi-bcm2835.c
@@ -1162,7 +1162,8 @@ static void bcm2835_spi_cleanup(struct spi_device *spi)
 				 sizeof(u32),
 				 DMA_TO_DEVICE);
 
-	gpiod_put(bs->cs_gpio);
+	if (!IS_ERR(bs->cs_gpio))
+		gpiod_put(bs->cs_gpio);
 	spi_set_csgpiod(spi, 0, NULL);
 
 	kfree(target);
@@ -1225,7 +1226,12 @@ static int bcm2835_spi_setup(struct spi_device *spi)
 	struct bcm2835_spi *bs = spi_controller_get_devdata(ctlr);
 	struct bcm2835_spidev *target = spi_get_ctldata(spi);
 	struct gpiod_lookup_table *lookup __free(kfree) = NULL;
-	int ret;
+	const char *pinctrl_compats[] = {
+		"brcm,bcm2835-gpio",
+		"brcm,bcm2711-gpio",
+		"brcm,bcm7211-gpio",
+	};
+	int ret, i;
 	u32 cs;
 
 	if (!target) {
@@ -1290,6 +1296,14 @@ static int bcm2835_spi_setup(struct spi_device *spi)
 		goto err_cleanup;
 	}
 
+	for (i = 0; i < ARRAY_SIZE(pinctrl_compats); i++) {
+		if (of_find_compatible_node(NULL, NULL, pinctrl_compats[i]))
+			break;
+	}
+
+	if (i == ARRAY_SIZE(pinctrl_compats))
+		return 0;
+
 	/*
 	 * TODO: The code below is a slightly better alternative to the utter
 	 * abuse of the GPIO API that I found here before. It creates a
diff --git a/drivers/spi/spi-bcm63xx-hsspi.c b/drivers/spi/spi-bcm63xx-hsspi.c
index 1ca857c2a4aa..8df12efeea21 100644
--- a/drivers/spi/spi-bcm63xx-hsspi.c
+++ b/drivers/spi/spi-bcm63xx-hsspi.c
@@ -745,7 +745,7 @@ static int bcm63xx_hsspi_probe(struct platform_device *pdev)
 	if (IS_ERR(clk))
 		return PTR_ERR(clk);
 
-	reset = devm_reset_control_get_optional_exclusive(dev, NULL);
+	reset = devm_reset_control_get_optional_shared(dev, NULL);
 	if (IS_ERR(reset))
 		return PTR_ERR(reset);
 
diff --git a/drivers/spi/spi-bcm63xx.c b/drivers/spi/spi-bcm63xx.c
index ef3a7226db12..a95badb7b711 100644
--- a/drivers/spi/spi-bcm63xx.c
+++ b/drivers/spi/spi-bcm63xx.c
@@ -523,7 +523,7 @@ static int bcm63xx_spi_probe(struct platform_device *pdev)
 		return PTR_ERR(clk);
 	}
 
-	reset = devm_reset_control_get_optional_exclusive(dev, NULL);
+	reset = devm_reset_control_get_optional_shared(dev, NULL);
 	if (IS_ERR(reset))
 		return PTR_ERR(reset);
 
diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c
index 73b1edd0531b..56be0b6901a8 100644
--- a/drivers/spi/spi-cadence-quadspi.c
+++ b/drivers/spi/spi-cadence-quadspi.c
@@ -1634,6 +1634,12 @@ static int cqspi_request_mmap_dma(struct cqspi_st *cqspi)
 		int ret = PTR_ERR(cqspi->rx_chan);
 
 		cqspi->rx_chan = NULL;
+		if (ret == -ENODEV) {
+			/* DMA support is not mandatory */
+			dev_info(&cqspi->pdev->dev, "No Rx DMA available\n");
+			return 0;
+		}
+
 		return dev_err_probe(&cqspi->pdev->dev, ret, "No Rx DMA available\n");
 	}
 	init_completion(&cqspi->rx_dma_complete);
@@ -1923,12 +1929,7 @@ static int cqspi_probe(struct platform_device *pdev)
 			goto probe_setup_failed;
 	}
 
-	ret = devm_pm_runtime_enable(dev);
-	if (ret) {
-		if (cqspi->rx_chan)
-			dma_release_channel(cqspi->rx_chan);
-		goto probe_setup_failed;
-	}
+	pm_runtime_enable(dev);
 
 	pm_runtime_set_autosuspend_delay(dev, CQSPI_AUTOSUSPEND_TIMEOUT);
 	pm_runtime_use_autosuspend(dev);
@@ -1946,6 +1947,7 @@ static int cqspi_probe(struct platform_device *pdev)
 	return 0;
 probe_setup_failed:
 	cqspi_controller_enable(cqspi, 0);
+	pm_runtime_disable(dev);
 probe_reset_failed:
 	if (cqspi->is_jh7110)
 		cqspi_jh7110_disable_clk(pdev, cqspi);
@@ -1964,7 +1966,8 @@ static void cqspi_remove(struct platform_device *pdev)
 	if (cqspi->rx_chan)
 		dma_release_channel(cqspi->rx_chan);
 
-	clk_disable_unprepare(cqspi->clk);
+	if (pm_runtime_get_sync(&pdev->dev) >= 0)
+		clk_disable(cqspi->clk);
 
 	if (cqspi->is_jh7110)
 		cqspi_jh7110_disable_clk(pdev, cqspi);
diff --git a/drivers/spi/spi-cadence-xspi.c b/drivers/spi/spi-cadence-xspi.c
index aed98ab14334..6dcba0e0ddaa 100644
--- a/drivers/spi/spi-cadence-xspi.c
+++ b/drivers/spi/spi-cadence-xspi.c
@@ -432,7 +432,7 @@ static bool cdns_mrvl_xspi_setup_clock(struct cdns_xspi_dev *cdns_xspi,
 	u32 clk_reg;
 	bool update_clk = false;
 
-	while (i < ARRAY_SIZE(cdns_mrvl_xspi_clk_div_list)) {
+	while (i < (ARRAY_SIZE(cdns_mrvl_xspi_clk_div_list) - 1)) {
 		clk_val = MRVL_XSPI_CLOCK_DIVIDED(
 				cdns_mrvl_xspi_clk_div_list[i]);
 		if (clk_val <= requested_clk)
diff --git a/drivers/spi/spi-cs42l43.c b/drivers/spi/spi-cs42l43.c
index 5b8ed65f8094..7a02fb42a88b 100644
--- a/drivers/spi/spi-cs42l43.c
+++ b/drivers/spi/spi-cs42l43.c
@@ -265,7 +265,7 @@ static struct spi_board_info *cs42l43_create_bridge_amp(struct cs42l43_spi *priv
 	struct spi_board_info *info;
 
 	if (spkid >= 0) {
-		props = devm_kmalloc(priv->dev, sizeof(*props), GFP_KERNEL);
+		props = devm_kcalloc(priv->dev, 2, sizeof(*props), GFP_KERNEL);
 		if (!props)
 			return NULL;
 
diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c
index 3fa990fb59c7..e26363ae7489 100644
--- a/drivers/spi/spi-fsl-dspi.c
+++ b/drivers/spi/spi-fsl-dspi.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0+
 //
 // Copyright 2013 Freescale Semiconductor, Inc.
-// Copyright 2020 NXP
+// Copyright 2020-2025 NXP
 //
 // Freescale DSPI driver
 // This file contains a driver for the Freescale DSPI
@@ -62,6 +62,7 @@
 #define SPI_SR_TFIWF			BIT(18)
 #define SPI_SR_RFDF			BIT(17)
 #define SPI_SR_CMDFFF			BIT(16)
+#define SPI_SR_TXRXS			BIT(30)
 #define SPI_SR_CLEAR			(SPI_SR_TCFQF | \
 					SPI_SR_TFUF | SPI_SR_TFFF | \
 					SPI_SR_CMDTCF | SPI_SR_SPEF | \
@@ -921,9 +922,20 @@ static int dspi_transfer_one_message(struct spi_controller *ctlr,
 	struct spi_transfer *transfer;
 	bool cs = false;
 	int status = 0;
+	u32 val = 0;
+	bool cs_change = false;
 
 	message->actual_length = 0;
 
+	/* Put DSPI in running mode if halted. */
+	regmap_read(dspi->regmap, SPI_MCR, &val);
+	if (val & SPI_MCR_HALT) {
+		regmap_update_bits(dspi->regmap, SPI_MCR, SPI_MCR_HALT, 0);
+		while (regmap_read(dspi->regmap, SPI_SR, &val) >= 0 &&
+		       !(val & SPI_SR_TXRXS))
+			;
+	}
+
 	list_for_each_entry(transfer, &message->transfers, transfer_list) {
 		dspi->cur_transfer = transfer;
 		dspi->cur_msg = message;
@@ -953,6 +965,7 @@ static int dspi_transfer_one_message(struct spi_controller *ctlr,
 				dspi->tx_cmd |= SPI_PUSHR_CMD_CONT;
 		}
 
+		cs_change = transfer->cs_change;
 		dspi->tx = transfer->tx_buf;
 		dspi->rx = transfer->rx_buf;
 		dspi->len = transfer->len;
@@ -962,17 +975,28 @@ static int dspi_transfer_one_message(struct spi_controller *ctlr,
 				   SPI_MCR_CLR_TXF | SPI_MCR_CLR_RXF,
 				   SPI_MCR_CLR_TXF | SPI_MCR_CLR_RXF);
 
+		regmap_write(dspi->regmap, SPI_SR, SPI_SR_CLEAR);
+
 		spi_take_timestamp_pre(dspi->ctlr, dspi->cur_transfer,
 				       dspi->progress, !dspi->irq);
 
 		if (dspi->devtype_data->trans_mode == DSPI_DMA_MODE) {
 			status = dspi_dma_xfer(dspi);
 		} else {
+			/*
+			 * Reinitialize the completion before transferring data
+			 * to avoid the case where it might remain in the done
+			 * state due to a spurious interrupt from a previous
+			 * transfer. This could falsely signal that the current
+			 * transfer has completed.
+			 */
+			if (dspi->irq)
+				reinit_completion(&dspi->xfer_done);
+
 			dspi_fifo_write(dspi);
 
 			if (dspi->irq) {
 				wait_for_completion(&dspi->xfer_done);
-				reinit_completion(&dspi->xfer_done);
 			} else {
 				do {
 					status = dspi_poll(dspi);
@@ -988,6 +1012,15 @@ static int dspi_transfer_one_message(struct spi_controller *ctlr,
 			dspi_deassert_cs(spi, &cs);
 	}
 
+	if (status || !cs_change) {
+		/* Put DSPI in stop mode */
+		regmap_update_bits(dspi->regmap, SPI_MCR,
+				   SPI_MCR_HALT, SPI_MCR_HALT);
+		while (regmap_read(dspi->regmap, SPI_SR, &val) >= 0 &&
+		       val & SPI_SR_TXRXS)
+			;
+	}
+
 	message->status = status;
 	spi_finalize_current_message(ctlr);
 
@@ -1167,6 +1200,20 @@ static int dspi_resume(struct device *dev)
 
 static SIMPLE_DEV_PM_OPS(dspi_pm, dspi_suspend, dspi_resume);
 
+static const struct regmap_range dspi_yes_ranges[] = {
+	regmap_reg_range(SPI_MCR, SPI_MCR),
+	regmap_reg_range(SPI_TCR, SPI_CTAR(3)),
+	regmap_reg_range(SPI_SR, SPI_TXFR3),
+	regmap_reg_range(SPI_RXFR0, SPI_RXFR3),
+	regmap_reg_range(SPI_CTARE(0), SPI_CTARE(3)),
+	regmap_reg_range(SPI_SREX, SPI_SREX),
+};
+
+static const struct regmap_access_table dspi_access_table = {
+	.yes_ranges	= dspi_yes_ranges,
+	.n_yes_ranges	= ARRAY_SIZE(dspi_yes_ranges),
+};
+
 static const struct regmap_range dspi_volatile_ranges[] = {
 	regmap_reg_range(SPI_MCR, SPI_TCR),
 	regmap_reg_range(SPI_SR, SPI_SR),
@@ -1184,6 +1231,8 @@ static const struct regmap_config dspi_regmap_config = {
 	.reg_stride	= 4,
 	.max_register	= 0x88,
 	.volatile_table	= &dspi_volatile_table,
+	.rd_table	= &dspi_access_table,
+	.wr_table	= &dspi_access_table,
 };
 
 static const struct regmap_range dspi_xspi_volatile_ranges[] = {
@@ -1205,6 +1254,8 @@ static const struct regmap_config dspi_xspi_regmap_config[] = {
 		.reg_stride	= 4,
 		.max_register	= 0x13c,
 		.volatile_table	= &dspi_xspi_volatile_table,
+		.rd_table	= &dspi_access_table,
+		.wr_table	= &dspi_access_table,
 	},
 	{
 		.name		= "pushr",
@@ -1227,6 +1278,8 @@ static int dspi_init(struct fsl_dspi *dspi)
 	if (!spi_controller_is_target(dspi->ctlr))
 		mcr |= SPI_MCR_HOST;
 
+	mcr |= SPI_MCR_HALT;
+
 	regmap_write(dspi->regmap, SPI_MCR, mcr);
 	regmap_write(dspi->regmap, SPI_SR, SPI_SR_CLEAR);
 
diff --git a/drivers/spi/spi-fsl-qspi.c b/drivers/spi/spi-fsl-qspi.c
index 79bac30e79af..21e357966d2a 100644
--- a/drivers/spi/spi-fsl-qspi.c
+++ b/drivers/spi/spi-fsl-qspi.c
@@ -839,6 +839,19 @@ static const struct spi_controller_mem_ops fsl_qspi_mem_ops = {
 	.get_name = fsl_qspi_get_name,
 };
 
+static void fsl_qspi_cleanup(void *data)
+{
+	struct fsl_qspi *q = data;
+
+	/* disable the hardware */
+	qspi_writel(q, QUADSPI_MCR_MDIS_MASK, q->iobase + QUADSPI_MCR);
+	qspi_writel(q, 0x0, q->iobase + QUADSPI_RSER);
+
+	fsl_qspi_clk_disable_unprep(q);
+
+	mutex_destroy(&q->lock);
+}
+
 static int fsl_qspi_probe(struct platform_device *pdev)
 {
 	struct spi_controller *ctlr;
@@ -928,15 +941,16 @@ static int fsl_qspi_probe(struct platform_device *pdev)
 
 	ctlr->dev.of_node = np;
 
+	ret = devm_add_action_or_reset(dev, fsl_qspi_cleanup, q);
+	if (ret)
+		goto err_put_ctrl;
+
 	ret = devm_spi_register_controller(dev, ctlr);
 	if (ret)
-		goto err_destroy_mutex;
+		goto err_put_ctrl;
 
 	return 0;
 
-err_destroy_mutex:
-	mutex_destroy(&q->lock);
-
 err_disable_clk:
 	fsl_qspi_clk_disable_unprep(q);
 
@@ -947,19 +961,6 @@ err_put_ctrl:
 	return ret;
 }
 
-static void fsl_qspi_remove(struct platform_device *pdev)
-{
-	struct fsl_qspi *q = platform_get_drvdata(pdev);
-
-	/* disable the hardware */
-	qspi_writel(q, QUADSPI_MCR_MDIS_MASK, q->iobase + QUADSPI_MCR);
-	qspi_writel(q, 0x0, q->iobase + QUADSPI_RSER);
-
-	fsl_qspi_clk_disable_unprep(q);
-
-	mutex_destroy(&q->lock);
-}
-
 static int fsl_qspi_suspend(struct device *dev)
 {
 	return 0;
@@ -997,7 +998,6 @@ static struct platform_driver fsl_qspi_driver = {
 		.pm =   &fsl_qspi_pm_ops,
 	},
 	.probe          = fsl_qspi_probe,
-	.remove_new	= fsl_qspi_remove,
 };
 module_platform_driver(fsl_qspi_driver);
 
diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c
index 4c31d36f3130..810541eed213 100644
--- a/drivers/spi/spi-imx.c
+++ b/drivers/spi/spi-imx.c
@@ -1614,10 +1614,13 @@ static int spi_imx_transfer_one(struct spi_controller *controller,
 				struct spi_device *spi,
 				struct spi_transfer *transfer)
 {
+	int ret;
 	struct spi_imx_data *spi_imx = spi_controller_get_devdata(spi->controller);
 	unsigned long hz_per_byte, byte_limit;
 
-	spi_imx_setupxfer(spi, transfer);
+	ret = spi_imx_setupxfer(spi, transfer);
+	if (ret < 0)
+		return ret;
 	transfer->effective_speed_hz = spi_imx->spi_bus_clk;
 
 	/* flush rxfifo before transfer */
diff --git a/drivers/spi/spi-loopback-test.c b/drivers/spi/spi-loopback-test.c
index 31a878d9458d..7740f94847a8 100644
--- a/drivers/spi/spi-loopback-test.c
+++ b/drivers/spi/spi-loopback-test.c
@@ -420,7 +420,7 @@ MODULE_LICENSE("GPL");
 static void spi_test_print_hex_dump(char *pre, const void *ptr, size_t len)
 {
 	/* limit the hex_dump */
-	if (len < 1024) {
+	if (len <= 1024) {
 		print_hex_dump(KERN_INFO, pre,
 			       DUMP_PREFIX_OFFSET, 16, 1,
 			       ptr, len, 0);
diff --git a/drivers/spi/spi-microchip-core.c b/drivers/spi/spi-microchip-core.c
index 7c1a9a985373..92b63a7f2041 100644
--- a/drivers/spi/spi-microchip-core.c
+++ b/drivers/spi/spi-microchip-core.c
@@ -70,8 +70,7 @@
 #define INT_RX_CHANNEL_OVERFLOW		BIT(2)
 #define INT_TX_CHANNEL_UNDERRUN		BIT(3)
 
-#define INT_ENABLE_MASK (CONTROL_RX_DATA_INT | CONTROL_TX_DATA_INT | \
-			 CONTROL_RX_OVER_INT | CONTROL_TX_UNDER_INT)
+#define INT_ENABLE_MASK (CONTROL_RX_OVER_INT | CONTROL_TX_UNDER_INT)
 
 #define REG_CONTROL		(0x00)
 #define REG_FRAME_SIZE		(0x04)
@@ -133,10 +132,15 @@ static inline void mchp_corespi_disable(struct mchp_corespi *spi)
 	mchp_corespi_write(spi, REG_CONTROL, control);
 }
 
-static inline void mchp_corespi_read_fifo(struct mchp_corespi *spi)
+static inline void mchp_corespi_read_fifo(struct mchp_corespi *spi, int fifo_max)
 {
-	while (spi->rx_len >= spi->n_bytes && !(mchp_corespi_read(spi, REG_STATUS) & STATUS_RXFIFO_EMPTY)) {
-		u32 data = mchp_corespi_read(spi, REG_RX_DATA);
+	for (int i = 0; i < fifo_max; i++) {
+		u32 data;
+
+		while (mchp_corespi_read(spi, REG_STATUS) & STATUS_RXFIFO_EMPTY)
+			;
+
+		data = mchp_corespi_read(spi, REG_RX_DATA);
 
 		spi->rx_len -= spi->n_bytes;
 
@@ -211,11 +215,10 @@ static inline void mchp_corespi_set_xfer_size(struct mchp_corespi *spi, int len)
 	mchp_corespi_write(spi, REG_FRAMESUP, len);
 }
 
-static inline void mchp_corespi_write_fifo(struct mchp_corespi *spi)
+static inline void mchp_corespi_write_fifo(struct mchp_corespi *spi, int fifo_max)
 {
-	int fifo_max, i = 0;
+	int i = 0;
 
-	fifo_max = DIV_ROUND_UP(min(spi->tx_len, FIFO_DEPTH), spi->n_bytes);
 	mchp_corespi_set_xfer_size(spi, fifo_max);
 
 	while ((i < fifo_max) && !(mchp_corespi_read(spi, REG_STATUS) & STATUS_TXFIFO_FULL)) {
@@ -413,19 +416,6 @@ static irqreturn_t mchp_corespi_interrupt(int irq, void *dev_id)
 	if (intfield == 0)
 		return IRQ_NONE;
 
-	if (intfield & INT_TXDONE)
-		mchp_corespi_write(spi, REG_INT_CLEAR, INT_TXDONE);
-
-	if (intfield & INT_RXRDY) {
-		mchp_corespi_write(spi, REG_INT_CLEAR, INT_RXRDY);
-
-		if (spi->rx_len)
-			mchp_corespi_read_fifo(spi);
-	}
-
-	if (!spi->rx_len && !spi->tx_len)
-		finalise = true;
-
 	if (intfield & INT_RX_CHANNEL_OVERFLOW) {
 		mchp_corespi_write(spi, REG_INT_CLEAR, INT_RX_CHANNEL_OVERFLOW);
 		finalise = true;
@@ -512,9 +502,14 @@ static int mchp_corespi_transfer_one(struct spi_controller *host,
 
 	mchp_corespi_write(spi, REG_SLAVE_SELECT, spi->pending_slave_select);
 
-	while (spi->tx_len)
-		mchp_corespi_write_fifo(spi);
+	while (spi->tx_len) {
+		int fifo_max = DIV_ROUND_UP(min(spi->tx_len, FIFO_DEPTH), spi->n_bytes);
+
+		mchp_corespi_write_fifo(spi, fifo_max);
+		mchp_corespi_read_fifo(spi, fifo_max);
+	}
 
+	spi_finalize_current_transfer(host);
 	return 1;
 }
 
diff --git a/drivers/spi/spi-mux.c b/drivers/spi/spi-mux.c
index c02c4204442f..0eb35c4e3987 100644
--- a/drivers/spi/spi-mux.c
+++ b/drivers/spi/spi-mux.c
@@ -68,9 +68,7 @@ static int spi_mux_select(struct spi_device *spi)
 
 	priv->current_cs = spi_get_chipselect(spi, 0);
 
-	spi_setup(priv->spi);
-
-	return 0;
+	return spi_setup(priv->spi);
 }
 
 static int spi_mux_setup(struct spi_device *spi)
diff --git a/drivers/spi/spi-omap2-mcspi.c b/drivers/spi/spi-omap2-mcspi.c
index 4a2f84c4d22e..4c5f12b76de6 100644
--- a/drivers/spi/spi-omap2-mcspi.c
+++ b/drivers/spi/spi-omap2-mcspi.c
@@ -134,6 +134,7 @@ struct omap2_mcspi {
 	size_t			max_xfer_len;
 	u32			ref_clk_hz;
 	bool			use_multi_mode;
+	bool			last_msg_kept_cs;
 };
 
 struct omap2_mcspi_cs {
@@ -1269,6 +1270,10 @@ static int omap2_mcspi_prepare_message(struct spi_controller *ctlr,
 	 * multi-mode is applicable.
 	 */
 	mcspi->use_multi_mode = true;
+
+	if (mcspi->last_msg_kept_cs)
+		mcspi->use_multi_mode = false;
+
 	list_for_each_entry(tr, &msg->transfers, transfer_list) {
 		if (!tr->bits_per_word)
 			bits_per_word = msg->spi->bits_per_word;
@@ -1287,18 +1292,19 @@ static int omap2_mcspi_prepare_message(struct spi_controller *ctlr,
 			mcspi->use_multi_mode = false;
 		}
 
-		/* Check if transfer asks to change the CS status after the transfer */
-		if (!tr->cs_change)
-			mcspi->use_multi_mode = false;
-
-		/*
-		 * If at least one message is not compatible, switch back to single mode
-		 *
-		 * The bits_per_word of certain transfer can be different, but it will have no
-		 * impact on the signal itself.
-		 */
-		if (!mcspi->use_multi_mode)
-			break;
+		if (list_is_last(&tr->transfer_list, &msg->transfers)) {
+			/* Check if transfer asks to keep the CS status after the whole message */
+			if (tr->cs_change) {
+				mcspi->use_multi_mode = false;
+				mcspi->last_msg_kept_cs = true;
+			} else {
+				mcspi->last_msg_kept_cs = false;
+			}
+		} else {
+			/* Check if transfer asks to change the CS status after the transfer */
+			if (!tr->cs_change)
+				mcspi->use_multi_mode = false;
+		}
 	}
 
 	omap2_mcspi_set_mode(ctlr);
@@ -1561,10 +1567,15 @@ static int omap2_mcspi_probe(struct platform_device *pdev)
 	}
 
 	mcspi->ref_clk = devm_clk_get_optional_enabled(&pdev->dev, NULL);
-	if (IS_ERR(mcspi->ref_clk))
-		mcspi->ref_clk_hz = OMAP2_MCSPI_MAX_FREQ;
-	else
+	if (IS_ERR(mcspi->ref_clk)) {
+		status = PTR_ERR(mcspi->ref_clk);
+		dev_err_probe(&pdev->dev, status, "Failed to get ref_clk");
+		goto free_ctlr;
+	}
+	if (mcspi->ref_clk)
 		mcspi->ref_clk_hz = clk_get_rate(mcspi->ref_clk);
+	else
+		mcspi->ref_clk_hz = OMAP2_MCSPI_MAX_FREQ;
 	ctlr->max_speed_hz = mcspi->ref_clk_hz;
 	ctlr->min_speed_hz = mcspi->ref_clk_hz >> 15;
 
diff --git a/drivers/spi/spi-rockchip.c b/drivers/spi/spi-rockchip.c
index 40a64a598a74..5008489d6fac 100644
--- a/drivers/spi/spi-rockchip.c
+++ b/drivers/spi/spi-rockchip.c
@@ -547,7 +547,7 @@ static int rockchip_spi_config(struct rockchip_spi *rs,
 	cr0 |= (spi->mode & 0x3U) << CR0_SCPH_OFFSET;
 	if (spi->mode & SPI_LSB_FIRST)
 		cr0 |= CR0_FBM_LSB << CR0_FBM_OFFSET;
-	if (spi->mode & SPI_CS_HIGH)
+	if ((spi->mode & SPI_CS_HIGH) && !(spi_get_csgpiod(spi, 0)))
 		cr0 |= BIT(spi_get_chipselect(spi, 0)) << CR0_SOI_OFFSET;
 
 	if (xfer->rx_buf && xfer->tx_buf)
diff --git a/drivers/spi/spi-sh-msiof.c b/drivers/spi/spi-sh-msiof.c
index 3519656515ea..1870f8c85213 100644
--- a/drivers/spi/spi-sh-msiof.c
+++ b/drivers/spi/spi-sh-msiof.c
@@ -918,6 +918,7 @@ static int sh_msiof_transfer_one(struct spi_controller *ctlr,
 	void *rx_buf = t->rx_buf;
 	unsigned int len = t->len;
 	unsigned int bits = t->bits_per_word;
+	unsigned int max_wdlen = 256;
 	unsigned int bytes_per_word;
 	unsigned int words;
 	int n;
@@ -931,17 +932,17 @@ static int sh_msiof_transfer_one(struct spi_controller *ctlr,
 	if (!spi_controller_is_target(p->ctlr))
 		sh_msiof_spi_set_clk_regs(p, t);
 
+	if (tx_buf)
+		max_wdlen = min(max_wdlen, p->tx_fifo_size);
+	if (rx_buf)
+		max_wdlen = min(max_wdlen, p->rx_fifo_size);
+
 	while (ctlr->dma_tx && len > 15) {
 		/*
 		 *  DMA supports 32-bit words only, hence pack 8-bit and 16-bit
 		 *  words, with byte resp. word swapping.
 		 */
-		unsigned int l = 0;
-
-		if (tx_buf)
-			l = min(round_down(len, 4), p->tx_fifo_size * 4);
-		if (rx_buf)
-			l = min(round_down(len, 4), p->rx_fifo_size * 4);
+		unsigned int l = min(round_down(len, 4), max_wdlen * 4);
 
 		if (bits <= 8) {
 			copy32 = copy_bswap32;
diff --git a/drivers/spi/spi-sn-f-ospi.c b/drivers/spi/spi-sn-f-ospi.c
index a7c3b3923b4a..fd8c8eb37d01 100644
--- a/drivers/spi/spi-sn-f-ospi.c
+++ b/drivers/spi/spi-sn-f-ospi.c
@@ -116,6 +116,9 @@ struct f_ospi {
 
 static u32 f_ospi_get_dummy_cycle(const struct spi_mem_op *op)
 {
+	if (!op->dummy.nbytes)
+		return 0;
+
 	return (op->dummy.nbytes * 8) / op->dummy.buswidth;
 }
 
diff --git a/drivers/spi/spi-stm32.c b/drivers/spi/spi-stm32.c
index fc72a89fb3a7..3b1b810f33bf 100644
--- a/drivers/spi/spi-stm32.c
+++ b/drivers/spi/spi-stm32.c
@@ -2069,9 +2069,15 @@ static int stm32_spi_probe(struct platform_device *pdev)
 	struct resource *res;
 	struct reset_control *rst;
 	struct device_node *np = pdev->dev.of_node;
+	const struct stm32_spi_cfg *cfg;
 	bool device_mode;
 	int ret;
-	const struct stm32_spi_cfg *cfg = of_device_get_match_data(&pdev->dev);
+
+	cfg = of_device_get_match_data(&pdev->dev);
+	if (!cfg) {
+		dev_err(&pdev->dev, "Failed to get match data for platform\n");
+		return -ENODEV;
+	}
 
 	device_mode = of_property_read_bool(np, "spi-slave");
 	if (!cfg->has_device_mode && device_mode) {
diff --git a/drivers/spi/spi-sun4i.c b/drivers/spi/spi-sun4i.c
index 2ee6755b43f5..3019f57e6584 100644
--- a/drivers/spi/spi-sun4i.c
+++ b/drivers/spi/spi-sun4i.c
@@ -264,6 +264,9 @@ static int sun4i_spi_transfer_one(struct spi_controller *host,
 	else
 		reg |= SUN4I_CTL_DHB;
 
+	/* Now that the settings are correct, enable the interface */
+	reg |= SUN4I_CTL_ENABLE;
+
 	sun4i_spi_write(sspi, SUN4I_CTL_REG, reg);
 
 	/* Ensure that we have a parent clock fast enough */
@@ -404,7 +407,7 @@ static int sun4i_spi_runtime_resume(struct device *dev)
 	}
 
 	sun4i_spi_write(sspi, SUN4I_CTL_REG,
-			SUN4I_CTL_ENABLE | SUN4I_CTL_MASTER | SUN4I_CTL_TP);
+			SUN4I_CTL_MASTER | SUN4I_CTL_TP);
 
 	return 0;
 
diff --git a/drivers/spi/spi-tegra114.c b/drivers/spi/spi-tegra114.c
index bc7cc4088eea..11db703a0dde 100644
--- a/drivers/spi/spi-tegra114.c
+++ b/drivers/spi/spi-tegra114.c
@@ -728,9 +728,9 @@ static int tegra_spi_set_hw_cs_timing(struct spi_device *spi)
 	u32 inactive_cycles;
 	u8 cs_state;
 
-	if (setup->unit != SPI_DELAY_UNIT_SCK ||
-	    hold->unit != SPI_DELAY_UNIT_SCK ||
-	    inactive->unit != SPI_DELAY_UNIT_SCK) {
+	if ((setup->value && setup->unit != SPI_DELAY_UNIT_SCK) ||
+	    (hold->value && hold->unit != SPI_DELAY_UNIT_SCK) ||
+	    (inactive->value && inactive->unit != SPI_DELAY_UNIT_SCK)) {
 		dev_err(&spi->dev,
 			"Invalid delay unit %d, should be SPI_DELAY_UNIT_SCK\n",
 			SPI_DELAY_UNIT_SCK);
diff --git a/drivers/spi/spi-tegra210-quad.c b/drivers/spi/spi-tegra210-quad.c
index 43f11b0e9e76..92348ebc60c7 100644
--- a/drivers/spi/spi-tegra210-quad.c
+++ b/drivers/spi/spi-tegra210-quad.c
@@ -134,7 +134,7 @@
 #define QSPI_COMMAND_VALUE_SET(X)		(((x) & 0xFF) << 0)
 
 #define QSPI_CMB_SEQ_CMD_CFG			0x1a0
-#define QSPI_COMMAND_X1_X2_X4(x)		(((x) & 0x3) << 13)
+#define QSPI_COMMAND_X1_X2_X4(x)		((((x) >> 1) & 0x3) << 13)
 #define QSPI_COMMAND_X1_X2_X4_MASK		(0x03 << 13)
 #define QSPI_COMMAND_SDR_DDR			BIT(12)
 #define QSPI_COMMAND_SIZE_SET(x)		(((x) & 0xFF) << 0)
@@ -147,7 +147,7 @@
 #define QSPI_ADDRESS_VALUE_SET(X)		(((x) & 0xFFFF) << 0)
 
 #define QSPI_CMB_SEQ_ADDR_CFG			0x1ac
-#define QSPI_ADDRESS_X1_X2_X4(x)		(((x) & 0x3) << 13)
+#define QSPI_ADDRESS_X1_X2_X4(x)		((((x) >> 1) & 0x3) << 13)
 #define QSPI_ADDRESS_X1_X2_X4_MASK		(0x03 << 13)
 #define QSPI_ADDRESS_SDR_DDR			BIT(12)
 #define QSPI_ADDRESS_SIZE_SET(x)		(((x) & 0xFF) << 0)
@@ -1036,10 +1036,6 @@ static u32 tegra_qspi_addr_config(bool is_ddr, u8 bus_width, u8 len)
 {
 	u32 addr_config = 0;
 
-	/* Extract Address configuration and value */
-	is_ddr = 0; //Only SDR mode supported
-	bus_width = 0; //X1 mode
-
 	if (is_ddr)
 		addr_config |= QSPI_ADDRESS_SDR_DDR;
 	else
@@ -1079,13 +1075,13 @@ static int tegra_qspi_combined_seq_xfer(struct tegra_qspi *tqspi,
 		switch (transfer_phase) {
 		case CMD_TRANSFER:
 			/* X1 SDR mode */
-			cmd_config = tegra_qspi_cmd_config(false, 0,
+			cmd_config = tegra_qspi_cmd_config(false, xfer->tx_nbits,
 							   xfer->len);
 			cmd_value = *((const u8 *)(xfer->tx_buf));
 			break;
 		case ADDR_TRANSFER:
 			/* X1 SDR mode */
-			addr_config = tegra_qspi_addr_config(false, 0,
+			addr_config = tegra_qspi_addr_config(false, xfer->tx_nbits,
 							     xfer->len);
 			address_value = *((const u32 *)(xfer->tx_buf));
 			break;
@@ -1117,9 +1113,9 @@ static int tegra_qspi_combined_seq_xfer(struct tegra_qspi *tqspi,
 					(&tqspi->xfer_completion,
 					QSPI_DMA_TIMEOUT);
 
-			if (WARN_ON(ret == 0)) {
-				dev_err(tqspi->dev, "QSPI Transfer failed with timeout: %d\n",
-					ret);
+			if (WARN_ON_ONCE(ret == 0)) {
+				dev_err_ratelimited(tqspi->dev,
+						    "QSPI Transfer failed with timeout\n");
 				if (tqspi->is_curr_dma_xfer &&
 				    (tqspi->cur_direction & DATA_DIR_TX))
 					dmaengine_terminate_all
@@ -1163,26 +1159,22 @@ static int tegra_qspi_combined_seq_xfer(struct tegra_qspi *tqspi,
 				ret = -EIO;
 				goto exit;
 			}
-			if (!xfer->cs_change) {
-				tegra_qspi_transfer_end(spi);
-				spi_transfer_delay_exec(xfer);
-			}
 			break;
 		default:
 			ret = -EINVAL;
 			goto exit;
 		}
 		msg->actual_length += xfer->len;
+		if (!xfer->cs_change && transfer_phase == DATA_TRANSFER) {
+			tegra_qspi_transfer_end(spi);
+			spi_transfer_delay_exec(xfer);
+		}
 		transfer_phase++;
 	}
 	ret = 0;
 
 exit:
 	msg->status = ret;
-	if (ret < 0) {
-		tegra_qspi_transfer_end(spi);
-		spi_transfer_delay_exec(xfer);
-	}
 
 	return ret;
 }
diff --git a/drivers/spi/spi-zynq-qspi.c b/drivers/spi/spi-zynq-qspi.c
index b67455bda972..de4c18247432 100644
--- a/drivers/spi/spi-zynq-qspi.c
+++ b/drivers/spi/spi-zynq-qspi.c
@@ -379,12 +379,21 @@ static int zynq_qspi_setup_op(struct spi_device *spi)
 {
 	struct spi_controller *ctlr = spi->controller;
 	struct zynq_qspi *qspi = spi_controller_get_devdata(ctlr);
+	int ret;
 
 	if (ctlr->busy)
 		return -EBUSY;
 
-	clk_enable(qspi->refclk);
-	clk_enable(qspi->pclk);
+	ret = clk_enable(qspi->refclk);
+	if (ret)
+		return ret;
+
+	ret = clk_enable(qspi->pclk);
+	if (ret) {
+		clk_disable(qspi->refclk);
+		return ret;
+	}
+
 	zynq_qspi_write(qspi, ZYNQ_QSPI_ENABLE_OFFSET,
 			ZYNQ_QSPI_ENABLE_ENABLE_MASK);
 
diff --git a/drivers/spi/spi-zynqmp-gqspi.c b/drivers/spi/spi-zynqmp-gqspi.c
index b9df39e06e7c..4b091b4d4ff3 100644
--- a/drivers/spi/spi-zynqmp-gqspi.c
+++ b/drivers/spi/spi-zynqmp-gqspi.c
@@ -799,7 +799,6 @@ static void zynqmp_process_dma_irq(struct zynqmp_qspi *xqspi)
 static irqreturn_t zynqmp_qspi_irq(int irq, void *dev_id)
 {
 	struct zynqmp_qspi *xqspi = (struct zynqmp_qspi *)dev_id;
-	irqreturn_t ret = IRQ_NONE;
 	u32 status, mask, dma_status = 0;
 
 	status = zynqmp_gqspi_read(xqspi, GQSPI_ISR_OFST);
@@ -814,27 +813,24 @@ static irqreturn_t zynqmp_qspi_irq(int irq, void *dev_id)
 				   dma_status);
 	}
 
-	if (mask & GQSPI_ISR_TXNOT_FULL_MASK) {
+	if (!mask && !dma_status)
+		return IRQ_NONE;
+
+	if (mask & GQSPI_ISR_TXNOT_FULL_MASK)
 		zynqmp_qspi_filltxfifo(xqspi, GQSPI_TX_FIFO_FILL);
-		ret = IRQ_HANDLED;
-	}
 
-	if (dma_status & GQSPI_QSPIDMA_DST_I_STS_DONE_MASK) {
+	if (dma_status & GQSPI_QSPIDMA_DST_I_STS_DONE_MASK)
 		zynqmp_process_dma_irq(xqspi);
-		ret = IRQ_HANDLED;
-	} else if (!(mask & GQSPI_IER_RXEMPTY_MASK) &&
-			(mask & GQSPI_IER_GENFIFOEMPTY_MASK)) {
+	else if (!(mask & GQSPI_IER_RXEMPTY_MASK) &&
+			(mask & GQSPI_IER_GENFIFOEMPTY_MASK))
 		zynqmp_qspi_readrxfifo(xqspi, GQSPI_RX_FIFO_FILL);
-		ret = IRQ_HANDLED;
-	}
 
 	if (xqspi->bytes_to_receive == 0 && xqspi->bytes_to_transfer == 0 &&
 	    ((status & GQSPI_IRQ_MASK) == GQSPI_IRQ_MASK)) {
 		zynqmp_gqspi_write(xqspi, GQSPI_IDR_OFST, GQSPI_ISR_IDR_MASK);
 		complete(&xqspi->data_completion);
-		ret = IRQ_HANDLED;
 	}
-	return ret;
+	return IRQ_HANDLED;
 }
 
 /**
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 0f3e6e2c2474..8d6341b0d866 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -4141,10 +4141,13 @@ static int __spi_validate(struct spi_device *spi, struct spi_message *message)
 				xfer->tx_nbits != SPI_NBITS_OCTAL)
 				return -EINVAL;
 			if ((xfer->tx_nbits == SPI_NBITS_DUAL) &&
-				!(spi->mode & (SPI_TX_DUAL | SPI_TX_QUAD)))
+				!(spi->mode & (SPI_TX_DUAL | SPI_TX_QUAD | SPI_TX_OCTAL)))
 				return -EINVAL;
 			if ((xfer->tx_nbits == SPI_NBITS_QUAD) &&
-				!(spi->mode & SPI_TX_QUAD))
+				!(spi->mode & (SPI_TX_QUAD | SPI_TX_OCTAL)))
+				return -EINVAL;
+			if ((xfer->tx_nbits == SPI_NBITS_OCTAL) &&
+				!(spi->mode & SPI_TX_OCTAL))
 				return -EINVAL;
 		}
 		/* Check transfer rx_nbits */
@@ -4157,10 +4160,13 @@ static int __spi_validate(struct spi_device *spi, struct spi_message *message)
 				xfer->rx_nbits != SPI_NBITS_OCTAL)
 				return -EINVAL;
 			if ((xfer->rx_nbits == SPI_NBITS_DUAL) &&
-				!(spi->mode & (SPI_RX_DUAL | SPI_RX_QUAD)))
+				!(spi->mode & (SPI_RX_DUAL | SPI_RX_QUAD | SPI_RX_OCTAL)))
 				return -EINVAL;
 			if ((xfer->rx_nbits == SPI_NBITS_QUAD) &&
-				!(spi->mode & SPI_RX_QUAD))
+				!(spi->mode & (SPI_RX_QUAD | SPI_RX_OCTAL)))
+				return -EINVAL;
+			if ((xfer->rx_nbits == SPI_NBITS_OCTAL) &&
+				!(spi->mode & SPI_RX_OCTAL))
 				return -EINVAL;
 		}
 
diff --git a/drivers/staging/axis-fifo/axis-fifo.c b/drivers/staging/axis-fifo/axis-fifo.c
index 1bbb9a6db597..6769f066b0b4 100644
--- a/drivers/staging/axis-fifo/axis-fifo.c
+++ b/drivers/staging/axis-fifo/axis-fifo.c
@@ -393,16 +393,14 @@ static ssize_t axis_fifo_read(struct file *f, char __user *buf,
 
 	bytes_available = ioread32(fifo->base_addr + XLLF_RLR_OFFSET);
 	if (!bytes_available) {
-		dev_err(fifo->dt_device, "received a packet of length 0 - fifo core will be reset\n");
-		reset_ip_core(fifo);
+		dev_err(fifo->dt_device, "received a packet of length 0\n");
 		ret = -EIO;
 		goto end_unlock;
 	}
 
 	if (bytes_available > len) {
-		dev_err(fifo->dt_device, "user read buffer too small (available bytes=%zu user buffer bytes=%zu) - fifo core will be reset\n",
+		dev_err(fifo->dt_device, "user read buffer too small (available bytes=%zu user buffer bytes=%zu)\n",
 			bytes_available, len);
-		reset_ip_core(fifo);
 		ret = -EINVAL;
 		goto end_unlock;
 	}
@@ -411,8 +409,7 @@ static ssize_t axis_fifo_read(struct file *f, char __user *buf,
 		/* this probably can't happen unless IP
 		 * registers were previously mishandled
 		 */
-		dev_err(fifo->dt_device, "received a packet that isn't word-aligned - fifo core will be reset\n");
-		reset_ip_core(fifo);
+		dev_err(fifo->dt_device, "received a packet that isn't word-aligned\n");
 		ret = -EIO;
 		goto end_unlock;
 	}
@@ -433,7 +430,6 @@ static ssize_t axis_fifo_read(struct file *f, char __user *buf,
 
 		if (copy_to_user(buf + copied * sizeof(u32), tmp_buf,
 				 copy * sizeof(u32))) {
-			reset_ip_core(fifo);
 			ret = -EFAULT;
 			goto end_unlock;
 		}
@@ -542,7 +538,6 @@ static ssize_t axis_fifo_write(struct file *f, const char __user *buf,
 
 		if (copy_from_user(tmp_buf, buf + copied * sizeof(u32),
 				   copy * sizeof(u32))) {
-			reset_ip_core(fifo);
 			ret = -EFAULT;
 			goto end_unlock;
 		}
@@ -775,9 +770,6 @@ static int axis_fifo_parse_dt(struct axis_fifo *fifo)
 		goto end;
 	}
 
-	/* IP sets TDFV to fifo depth - 4 so we will do the same */
-	fifo->tx_fifo_depth -= 4;
-
 	ret = get_dts_property(fifo, "xlnx,use-rx-data", &fifo->has_rx_fifo);
 	if (ret) {
 		dev_err(fifo->dt_device, "missing xlnx,use-rx-data property\n");
diff --git a/drivers/staging/fbtft/fbtft-core.c b/drivers/staging/fbtft/fbtft-core.c
index 4cfa494243b9..8fab5126765d 100644
--- a/drivers/staging/fbtft/fbtft-core.c
+++ b/drivers/staging/fbtft/fbtft-core.c
@@ -694,6 +694,7 @@ struct fb_info *fbtft_framebuffer_alloc(struct fbtft_display *display,
 	return info;
 
 release_framebuf:
+	fb_deferred_io_cleanup(info);
 	framebuffer_release(info);
 
 alloc_fail:
diff --git a/drivers/staging/greybus/gbphy.c b/drivers/staging/greybus/gbphy.c
index 6adcad286633..60cf09a302a7 100644
--- a/drivers/staging/greybus/gbphy.c
+++ b/drivers/staging/greybus/gbphy.c
@@ -102,8 +102,8 @@ static int gbphy_dev_uevent(const struct device *dev, struct kobj_uevent_env *en
 }
 
 static const struct gbphy_device_id *
-gbphy_dev_match_id(struct gbphy_device *gbphy_dev,
-		   struct gbphy_driver *gbphy_drv)
+gbphy_dev_match_id(const struct gbphy_device *gbphy_dev,
+		   const struct gbphy_driver *gbphy_drv)
 {
 	const struct gbphy_device_id *id = gbphy_drv->id_table;
 
@@ -119,7 +119,7 @@ gbphy_dev_match_id(struct gbphy_device *gbphy_dev,
 
 static int gbphy_dev_match(struct device *dev, const struct device_driver *drv)
 {
-	struct gbphy_driver *gbphy_drv = to_gbphy_driver(drv);
+	const struct gbphy_driver *gbphy_drv = to_gbphy_driver(drv);
 	struct gbphy_device *gbphy_dev = to_gbphy_dev(dev);
 	const struct gbphy_device_id *id;
 
diff --git a/drivers/staging/iio/adc/ad7816.c b/drivers/staging/iio/adc/ad7816.c
index 6c14d7bcdd67..081b17f49863 100644
--- a/drivers/staging/iio/adc/ad7816.c
+++ b/drivers/staging/iio/adc/ad7816.c
@@ -136,7 +136,7 @@ static ssize_t ad7816_store_mode(struct device *dev,
 	struct iio_dev *indio_dev = dev_to_iio_dev(dev);
 	struct ad7816_chip_info *chip = iio_priv(indio_dev);
 
-	if (strcmp(buf, "full")) {
+	if (strcmp(buf, "full") == 0) {
 		gpiod_set_value(chip->rdwr_pin, 1);
 		chip->mode = AD7816_FULL;
 	} else {
diff --git a/drivers/staging/iio/impedance-analyzer/ad5933.c b/drivers/staging/iio/impedance-analyzer/ad5933.c
index 4ae1a7039418..1f806ee966c3 100644
--- a/drivers/staging/iio/impedance-analyzer/ad5933.c
+++ b/drivers/staging/iio/impedance-analyzer/ad5933.c
@@ -411,7 +411,7 @@ static ssize_t ad5933_store(struct device *dev,
 		ret = ad5933_cmd(st, 0);
 		break;
 	case AD5933_OUT_SETTLING_CYCLES:
-		val = clamp(val, (u16)0, (u16)0x7FF);
+		val = clamp(val, (u16)0, (u16)0x7FC);
 		st->settling_cycles = val;
 
 		/* 2x, 4x handling, see datasheet */
diff --git a/drivers/staging/media/atomisp/pci/atomisp_gmin_platform.c b/drivers/staging/media/atomisp/pci/atomisp_gmin_platform.c
index e176483df301..b86494faa63a 100644
--- a/drivers/staging/media/atomisp/pci/atomisp_gmin_platform.c
+++ b/drivers/staging/media/atomisp/pci/atomisp_gmin_platform.c
@@ -1358,14 +1358,15 @@ static int gmin_get_config_var(struct device *maindev,
 	if (efi_rt_services_supported(EFI_RT_SUPPORTED_GET_VARIABLE))
 		status = efi.get_variable(var16, &GMIN_CFG_VAR_EFI_GUID, NULL,
 					  (unsigned long *)out_len, out);
-	if (status == EFI_SUCCESS)
+	if (status == EFI_SUCCESS) {
 		dev_info(maindev, "found EFI entry for '%s'\n", var8);
-	else if (is_gmin)
+		return 0;
+	}
+	if (is_gmin)
 		dev_info(maindev, "Failed to find EFI gmin variable %s\n", var8);
 	else
 		dev_info(maindev, "Failed to find EFI variable %s\n", var8);
-
-	return ret;
+	return -ENOENT;
 }
 
 int gmin_get_var_int(struct device *dev, bool is_gmin, const char *var, int def)
diff --git a/drivers/staging/media/imx/imx-media-of.c b/drivers/staging/media/imx/imx-media-of.c
index 118bff988bc7..bb28daa4d713 100644
--- a/drivers/staging/media/imx/imx-media-of.c
+++ b/drivers/staging/media/imx/imx-media-of.c
@@ -54,22 +54,18 @@ int imx_media_add_of_subdevs(struct imx_media_dev *imxmd,
 			break;
 
 		ret = imx_media_of_add_csi(imxmd, csi_np);
+		of_node_put(csi_np);
 		if (ret) {
 			/* unavailable or already added is not an error */
 			if (ret == -ENODEV || ret == -EEXIST) {
-				of_node_put(csi_np);
 				continue;
 			}
 
 			/* other error, can't continue */
-			goto err_out;
+			return ret;
 		}
 	}
 
 	return 0;
-
-err_out:
-	of_node_put(csi_np);
-	return ret;
 }
 EXPORT_SYMBOL_GPL(imx_media_add_of_subdevs);
diff --git a/drivers/staging/media/max96712/max96712.c b/drivers/staging/media/max96712/max96712.c
index 6bdbccbee05a..b528727ada75 100644
--- a/drivers/staging/media/max96712/max96712.c
+++ b/drivers/staging/media/max96712/max96712.c
@@ -421,7 +421,6 @@ static int max96712_probe(struct i2c_client *client)
 		return -ENOMEM;
 
 	priv->client = client;
-	i2c_set_clientdata(client, priv);
 
 	priv->regmap = devm_regmap_init_i2c(client, &max96712_i2c_regmap);
 	if (IS_ERR(priv->regmap))
@@ -454,7 +453,8 @@ static int max96712_probe(struct i2c_client *client)
 
 static void max96712_remove(struct i2c_client *client)
 {
-	struct max96712_priv *priv = i2c_get_clientdata(client);
+	struct v4l2_subdev *sd = i2c_get_clientdata(client);
+	struct max96712_priv *priv = container_of(sd, struct max96712_priv, sd);
 
 	v4l2_async_unregister_subdev(&priv->sd);
 
diff --git a/drivers/staging/media/rkvdec/rkvdec.c b/drivers/staging/media/rkvdec/rkvdec.c
index ac398b5a9736..a1d941b0be00 100644
--- a/drivers/staging/media/rkvdec/rkvdec.c
+++ b/drivers/staging/media/rkvdec/rkvdec.c
@@ -213,8 +213,14 @@ static int rkvdec_enum_framesizes(struct file *file, void *priv,
 	if (!fmt)
 		return -EINVAL;
 
-	fsize->type = V4L2_FRMSIZE_TYPE_STEPWISE;
-	fsize->stepwise = fmt->frmsize;
+	fsize->type = V4L2_FRMSIZE_TYPE_CONTINUOUS;
+	fsize->stepwise.min_width = 1;
+	fsize->stepwise.max_width = fmt->frmsize.max_width;
+	fsize->stepwise.step_width = 1;
+	fsize->stepwise.min_height = 1;
+	fsize->stepwise.max_height = fmt->frmsize.max_height;
+	fsize->stepwise.step_height = 1;
+
 	return 0;
 }
 
diff --git a/drivers/staging/nvec/nvec_power.c b/drivers/staging/nvec/nvec_power.c
index 9943b1fff190..573521e1703b 100644
--- a/drivers/staging/nvec/nvec_power.c
+++ b/drivers/staging/nvec/nvec_power.c
@@ -194,7 +194,7 @@ static int nvec_power_bat_notifier(struct notifier_block *nb,
 		break;
 	case MANUFACTURER:
 		memcpy(power->bat_manu, &res->plc, res->length - 2);
-		power->bat_model[res->length - 2] = '\0';
+		power->bat_manu[res->length - 2] = '\0';
 		break;
 	case MODEL:
 		memcpy(power->bat_model, &res->plc, res->length - 2);
diff --git a/drivers/staging/rtl8723bs/Kconfig b/drivers/staging/rtl8723bs/Kconfig
index 8d48c61961a6..353e6ee2c145 100644
--- a/drivers/staging/rtl8723bs/Kconfig
+++ b/drivers/staging/rtl8723bs/Kconfig
@@ -4,6 +4,7 @@ config RTL8723BS
 	depends on WLAN && MMC && CFG80211
 	depends on m
 	select CRYPTO
+	select CRYPTO_LIB_AES
 	select CRYPTO_LIB_ARC4
 	help
 	This option enables support for RTL8723BS SDIO drivers, such as
diff --git a/drivers/staging/rtl8723bs/core/rtw_security.c b/drivers/staging/rtl8723bs/core/rtw_security.c
index 1e9eff01b1aa..e9f382c280d9 100644
--- a/drivers/staging/rtl8723bs/core/rtw_security.c
+++ b/drivers/staging/rtl8723bs/core/rtw_security.c
@@ -868,29 +868,21 @@ static signed int aes_cipher(u8 *key, uint	hdrlen,
 		num_blocks, payload_index;
 
 	u8 pn_vector[6];
-	u8 mic_iv[16];
-	u8 mic_header1[16];
-	u8 mic_header2[16];
-	u8 ctr_preload[16];
+	u8 mic_iv[16] = {};
+	u8 mic_header1[16] = {};
+	u8 mic_header2[16] = {};
+	u8 ctr_preload[16] = {};
 
 	/* Intermediate Buffers */
-	u8 chain_buffer[16];
-	u8 aes_out[16];
-	u8 padded_buffer[16];
+	u8 chain_buffer[16] = {};
+	u8 aes_out[16] = {};
+	u8 padded_buffer[16] = {};
 	u8 mic[8];
 	uint	frtype  = GetFrameType(pframe);
 	uint	frsubtype  = GetFrameSubType(pframe);
 
 	frsubtype = frsubtype>>4;
 
-	memset((void *)mic_iv, 0, 16);
-	memset((void *)mic_header1, 0, 16);
-	memset((void *)mic_header2, 0, 16);
-	memset((void *)ctr_preload, 0, 16);
-	memset((void *)chain_buffer, 0, 16);
-	memset((void *)aes_out, 0, 16);
-	memset((void *)padded_buffer, 0, 16);
-
 	if ((hdrlen == WLAN_HDR_A3_LEN) || (hdrlen ==  WLAN_HDR_A3_QOS_LEN))
 		a4_exists = 0;
 	else
@@ -1080,15 +1072,15 @@ static signed int aes_decipher(u8 *key, uint	hdrlen,
 			num_blocks, payload_index;
 	signed int res = _SUCCESS;
 	u8 pn_vector[6];
-	u8 mic_iv[16];
-	u8 mic_header1[16];
-	u8 mic_header2[16];
-	u8 ctr_preload[16];
+	u8 mic_iv[16] = {};
+	u8 mic_header1[16] = {};
+	u8 mic_header2[16] = {};
+	u8 ctr_preload[16] = {};
 
 		/* Intermediate Buffers */
-	u8 chain_buffer[16];
-	u8 aes_out[16];
-	u8 padded_buffer[16];
+	u8 chain_buffer[16] = {};
+	u8 aes_out[16] = {};
+	u8 padded_buffer[16] = {};
 	u8 mic[8];
 
 	uint frtype  = GetFrameType(pframe);
@@ -1096,14 +1088,6 @@ static signed int aes_decipher(u8 *key, uint	hdrlen,
 
 	frsubtype = frsubtype>>4;
 
-	memset((void *)mic_iv, 0, 16);
-	memset((void *)mic_header1, 0, 16);
-	memset((void *)mic_header2, 0, 16);
-	memset((void *)ctr_preload, 0, 16);
-	memset((void *)chain_buffer, 0, 16);
-	memset((void *)aes_out, 0, 16);
-	memset((void *)padded_buffer, 0, 16);
-
 	/* start to decrypt the payload */
 
 	num_blocks = (plen-8) / 16; /* plen including LLC, payload_length and mic) */
diff --git a/drivers/staging/vc04_services/bcm2835-camera/bcm2835-camera.c b/drivers/staging/vc04_services/bcm2835-camera/bcm2835-camera.c
index deec33f63bcf..e6724329356b 100644
--- a/drivers/staging/vc04_services/bcm2835-camera/bcm2835-camera.c
+++ b/drivers/staging/vc04_services/bcm2835-camera/bcm2835-camera.c
@@ -1902,6 +1902,7 @@ static int bcm2835_mmal_probe(struct vchiq_device *device)
 				__func__, ret);
 			goto free_dev;
 		}
+		dev->v4l2_dev.dev = &device->dev;
 
 		/* setup v4l controls */
 		ret = bcm2835_mmal_init_controls(dev, &dev->ctrl_handler);
diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c
index 5fab33adf58e..20ad6b1e44bc 100644
--- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c
+++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c
@@ -739,8 +739,7 @@ int vchiq_shutdown(struct vchiq_instance *instance)
 	struct vchiq_state *state = instance->state;
 	int ret = 0;
 
-	if (mutex_lock_killable(&state->mutex))
-		return -EAGAIN;
+	mutex_lock(&state->mutex);
 
 	/* Remove all services */
 	vchiq_shutdown_internal(state, instance);
@@ -1745,8 +1744,6 @@ static int vchiq_probe(struct platform_device *pdev)
 	if (ret)
 		goto failed_platform_init;
 
-	vchiq_debugfs_init(&mgmt->state);
-
 	dev_dbg(&pdev->dev, "arm: platform initialised - version %d (min %d)\n",
 		VCHIQ_VERSION, VCHIQ_VERSION_MIN);
 
@@ -1760,6 +1757,8 @@ static int vchiq_probe(struct platform_device *pdev)
 		goto error_exit;
 	}
 
+	vchiq_debugfs_init(&mgmt->state);
+
 	bcm2835_audio = vchiq_device_register(&pdev->dev, "bcm2835-audio");
 	bcm2835_camera = vchiq_device_register(&pdev->dev, "bcm2835-camera");
 
@@ -1786,7 +1785,8 @@ static void vchiq_remove(struct platform_device *pdev)
 	kthread_stop(mgmt->state.slot_handler_thread);
 
 	arm_state = vchiq_platform_get_arm_state(&mgmt->state);
-	kthread_stop(arm_state->ka_thread);
+	if (!IS_ERR_OR_NULL(arm_state->ka_thread))
+		kthread_stop(arm_state->ka_thread);
 }
 
 static struct platform_driver vchiq_driver = {
diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c
index 6002283cbeba..68bbdf3ee101 100644
--- a/drivers/target/iscsi/iscsi_target.c
+++ b/drivers/target/iscsi/iscsi_target.c
@@ -4317,8 +4317,8 @@ int iscsit_close_connection(
 	spin_unlock(&iscsit_global->ts_bitmap_lock);
 
 	iscsit_stop_timers_for_cmds(conn);
-	iscsit_stop_nopin_response_timer(conn);
 	iscsit_stop_nopin_timer(conn);
+	iscsit_stop_nopin_response_timer(conn);
 
 	if (conn->conn_transport->iscsit_wait_conn)
 		conn->conn_transport->iscsit_wait_conn(conn);
diff --git a/drivers/target/target_core_fabric_lib.c b/drivers/target/target_core_fabric_lib.c
index 43f47e3aa448..ec7bc6e30228 100644
--- a/drivers/target/target_core_fabric_lib.c
+++ b/drivers/target/target_core_fabric_lib.c
@@ -257,11 +257,41 @@ static int iscsi_get_pr_transport_id_len(
 	return len;
 }
 
-static char *iscsi_parse_pr_out_transport_id(
+static void sas_parse_pr_out_transport_id(char *buf, char *i_str)
+{
+	char hex[17] = {};
+
+	bin2hex(hex, buf + 4, 8);
+	snprintf(i_str, TRANSPORT_IQN_LEN, "naa.%s", hex);
+}
+
+static void srp_parse_pr_out_transport_id(char *buf, char *i_str)
+{
+	char hex[33] = {};
+
+	bin2hex(hex, buf + 8, 16);
+	snprintf(i_str, TRANSPORT_IQN_LEN, "0x%s", hex);
+}
+
+static void fcp_parse_pr_out_transport_id(char *buf, char *i_str)
+{
+	snprintf(i_str, TRANSPORT_IQN_LEN, "%8phC", buf + 8);
+}
+
+static void sbp_parse_pr_out_transport_id(char *buf, char *i_str)
+{
+	char hex[17] = {};
+
+	bin2hex(hex, buf + 8, 8);
+	snprintf(i_str, TRANSPORT_IQN_LEN, "%s", hex);
+}
+
+static bool iscsi_parse_pr_out_transport_id(
 	struct se_portal_group *se_tpg,
 	char *buf,
 	u32 *out_tid_len,
-	char **port_nexus_ptr)
+	char **port_nexus_ptr,
+	char *i_str)
 {
 	char *p;
 	int i;
@@ -282,7 +312,7 @@ static char *iscsi_parse_pr_out_transport_id(
 	if ((format_code != 0x00) && (format_code != 0x40)) {
 		pr_err("Illegal format code: 0x%02x for iSCSI"
 			" Initiator Transport ID\n", format_code);
-		return NULL;
+		return false;
 	}
 	/*
 	 * If the caller wants the TransportID Length, we set that value for the
@@ -306,7 +336,7 @@ static char *iscsi_parse_pr_out_transport_id(
 			pr_err("Unable to locate \",i,0x\" separator"
 				" for Initiator port identifier: %s\n",
 				&buf[4]);
-			return NULL;
+			return false;
 		}
 		*p = '\0'; /* Terminate iSCSI Name */
 		p += 5; /* Skip over ",i,0x" separator */
@@ -339,7 +369,8 @@ static char *iscsi_parse_pr_out_transport_id(
 	} else
 		*port_nexus_ptr = NULL;
 
-	return &buf[4];
+	strscpy(i_str, &buf[4], TRANSPORT_IQN_LEN);
+	return true;
 }
 
 int target_get_pr_transport_id_len(struct se_node_acl *nacl,
@@ -387,33 +418,35 @@ int target_get_pr_transport_id(struct se_node_acl *nacl,
 	}
 }
 
-const char *target_parse_pr_out_transport_id(struct se_portal_group *tpg,
-		char *buf, u32 *out_tid_len, char **port_nexus_ptr)
+bool target_parse_pr_out_transport_id(struct se_portal_group *tpg,
+		char *buf, u32 *out_tid_len, char **port_nexus_ptr, char *i_str)
 {
-	u32 offset;
-
 	switch (tpg->proto_id) {
 	case SCSI_PROTOCOL_SAS:
 		/*
 		 * Assume the FORMAT CODE 00b from spc4r17, 7.5.4.7 TransportID
 		 * for initiator ports using SCSI over SAS Serial SCSI Protocol.
 		 */
-		offset = 4;
+		sas_parse_pr_out_transport_id(buf, i_str);
 		break;
-	case SCSI_PROTOCOL_SBP:
 	case SCSI_PROTOCOL_SRP:
+		srp_parse_pr_out_transport_id(buf, i_str);
+		break;
 	case SCSI_PROTOCOL_FCP:
-		offset = 8;
+		fcp_parse_pr_out_transport_id(buf, i_str);
+		break;
+	case SCSI_PROTOCOL_SBP:
+		sbp_parse_pr_out_transport_id(buf, i_str);
 		break;
 	case SCSI_PROTOCOL_ISCSI:
 		return iscsi_parse_pr_out_transport_id(tpg, buf, out_tid_len,
-					port_nexus_ptr);
+					port_nexus_ptr, i_str);
 	default:
 		pr_err("Unknown proto_id: 0x%02x\n", tpg->proto_id);
-		return NULL;
+		return false;
 	}
 
 	*port_nexus_ptr = NULL;
 	*out_tid_len = 24;
-	return buf + offset;
+	return true;
 }
diff --git a/drivers/target/target_core_internal.h b/drivers/target/target_core_internal.h
index 408be26d2e9b..20aab1f50565 100644
--- a/drivers/target/target_core_internal.h
+++ b/drivers/target/target_core_internal.h
@@ -103,8 +103,8 @@ int	target_get_pr_transport_id_len(struct se_node_acl *nacl,
 int	target_get_pr_transport_id(struct se_node_acl *nacl,
 		struct t10_pr_registration *pr_reg, int *format_code,
 		unsigned char *buf);
-const char *target_parse_pr_out_transport_id(struct se_portal_group *tpg,
-		char *buf, u32 *out_tid_len, char **port_nexus_ptr);
+bool target_parse_pr_out_transport_id(struct se_portal_group *tpg,
+		char *buf, u32 *out_tid_len, char **port_nexus_ptr, char *i_str);
 
 /* target_core_hba.c */
 struct se_hba *core_alloc_hba(const char *, u32, u32);
diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c
index 4f4ad6af416c..82061cbe6781 100644
--- a/drivers/target/target_core_pr.c
+++ b/drivers/target/target_core_pr.c
@@ -1478,11 +1478,12 @@ core_scsi3_decode_spec_i_port(
 	LIST_HEAD(tid_dest_list);
 	struct pr_transport_id_holder *tidh_new, *tidh, *tidh_tmp;
 	unsigned char *buf, *ptr, proto_ident;
-	const unsigned char *i_str = NULL;
+	unsigned char i_str[TRANSPORT_IQN_LEN];
 	char *iport_ptr = NULL, i_buf[PR_REG_ISID_ID_LEN];
 	sense_reason_t ret;
 	u32 tpdl, tid_len = 0;
 	u32 dest_rtpi = 0;
+	bool tid_found;
 
 	/*
 	 * Allocate a struct pr_transport_id_holder and setup the
@@ -1571,9 +1572,9 @@ core_scsi3_decode_spec_i_port(
 			dest_rtpi = tmp_lun->lun_tpg->tpg_rtpi;
 
 			iport_ptr = NULL;
-			i_str = target_parse_pr_out_transport_id(tmp_tpg,
-					ptr, &tid_len, &iport_ptr);
-			if (!i_str)
+			tid_found = target_parse_pr_out_transport_id(tmp_tpg,
+					ptr, &tid_len, &iport_ptr, i_str);
+			if (!tid_found)
 				continue;
 			/*
 			 * Determine if this SCSI device server requires that
@@ -1842,7 +1843,9 @@ out:
 		}
 
 		kmem_cache_free(t10_pr_reg_cache, dest_pr_reg);
-		core_scsi3_lunacl_undepend_item(dest_se_deve);
+
+		if (dest_se_deve)
+			core_scsi3_lunacl_undepend_item(dest_se_deve);
 
 		if (is_local)
 			continue;
@@ -3151,13 +3154,14 @@ core_scsi3_emulate_pro_register_and_move(struct se_cmd *cmd, u64 res_key,
 	struct t10_pr_registration *pr_reg, *pr_res_holder, *dest_pr_reg;
 	struct t10_reservation *pr_tmpl = &dev->t10_pr;
 	unsigned char *buf;
-	const unsigned char *initiator_str;
+	unsigned char initiator_str[TRANSPORT_IQN_LEN];
 	char *iport_ptr = NULL, i_buf[PR_REG_ISID_ID_LEN] = { };
 	u32 tid_len, tmp_tid_len;
 	int new_reg = 0, type, scope, matching_iname;
 	sense_reason_t ret;
 	unsigned short rtpi;
 	unsigned char proto_ident;
+	bool tid_found;
 
 	if (!se_sess || !se_lun) {
 		pr_err("SPC-3 PR: se_sess || struct se_lun is NULL!\n");
@@ -3276,9 +3280,9 @@ core_scsi3_emulate_pro_register_and_move(struct se_cmd *cmd, u64 res_key,
 		ret = TCM_INVALID_PARAMETER_LIST;
 		goto out;
 	}
-	initiator_str = target_parse_pr_out_transport_id(dest_se_tpg,
-			&buf[24], &tmp_tid_len, &iport_ptr);
-	if (!initiator_str) {
+	tid_found = target_parse_pr_out_transport_id(dest_se_tpg,
+			&buf[24], &tmp_tid_len, &iport_ptr, initiator_str);
+	if (!tid_found) {
 		pr_err("SPC-3 PR REGISTER_AND_MOVE: Unable to locate"
 			" initiator_str from Transport ID\n");
 		ret = TCM_INVALID_PARAMETER_LIST;
diff --git a/drivers/target/target_core_spc.c b/drivers/target/target_core_spc.c
index ea14a3835681..701dcbd7b63c 100644
--- a/drivers/target/target_core_spc.c
+++ b/drivers/target/target_core_spc.c
@@ -2151,8 +2151,10 @@ spc_rsoc_get_descr(struct se_cmd *cmd, struct target_opcode_descriptor **opcode)
 			if (descr->serv_action_valid)
 				return TCM_INVALID_CDB_FIELD;
 
-			if (!descr->enabled || descr->enabled(descr, cmd))
+			if (!descr->enabled || descr->enabled(descr, cmd)) {
 				*opcode = descr;
+				return TCM_NO_SENSE;
+			}
 			break;
 		case 0x2:
 			/*
@@ -2166,8 +2168,10 @@ spc_rsoc_get_descr(struct se_cmd *cmd, struct target_opcode_descriptor **opcode)
 			if (descr->serv_action_valid &&
 			    descr->service_action == requested_sa) {
 				if (!descr->enabled || descr->enabled(descr,
-								      cmd))
+								      cmd)) {
 					*opcode = descr;
+					return TCM_NO_SENSE;
+				}
 			} else if (!descr->serv_action_valid)
 				return TCM_INVALID_CDB_FIELD;
 			break;
@@ -2180,13 +2184,15 @@ spc_rsoc_get_descr(struct se_cmd *cmd, struct target_opcode_descriptor **opcode)
 			 */
 			if (descr->service_action == requested_sa)
 				if (!descr->enabled || descr->enabled(descr,
-								      cmd))
+								      cmd)) {
 					*opcode = descr;
+					return TCM_NO_SENSE;
+				}
 			break;
 		}
 	}
 
-	return 0;
+	return TCM_NO_SENSE;
 }
 
 static sense_reason_t
@@ -2243,7 +2249,7 @@ spc_emulate_report_supp_op_codes(struct se_cmd *cmd)
 			response_length += spc_rsoc_encode_command_descriptor(
 					&buf[response_length], rctd, descr);
 		}
-		put_unaligned_be32(response_length - 3, buf);
+		put_unaligned_be32(response_length - 4, buf);
 	} else {
 		response_length = spc_rsoc_encode_one_command_descriptor(
 				&buf[response_length], rctd, descr,
diff --git a/drivers/tee/optee/ffa_abi.c b/drivers/tee/optee/ffa_abi.c
index f3af5666bb11..f9ef7d94cebd 100644
--- a/drivers/tee/optee/ffa_abi.c
+++ b/drivers/tee/optee/ffa_abi.c
@@ -728,12 +728,21 @@ static bool optee_ffa_exchange_caps(struct ffa_device *ffa_dev,
 	return true;
 }
 
+static void notif_work_fn(struct work_struct *work)
+{
+	struct optee_ffa *optee_ffa = container_of(work, struct optee_ffa,
+						   notif_work);
+	struct optee *optee = container_of(optee_ffa, struct optee, ffa);
+
+	optee_do_bottom_half(optee->ctx);
+}
+
 static void notif_callback(int notify_id, void *cb_data)
 {
 	struct optee *optee = cb_data;
 
 	if (notify_id == optee->ffa.bottom_half_value)
-		optee_do_bottom_half(optee->ctx);
+		queue_work(optee->ffa.notif_wq, &optee->ffa.notif_work);
 	else
 		optee_notif_send(optee, notify_id);
 }
@@ -817,9 +826,11 @@ static void optee_ffa_remove(struct ffa_device *ffa_dev)
 	struct optee *optee = ffa_dev_get_drvdata(ffa_dev);
 	u32 bottom_half_id = optee->ffa.bottom_half_value;
 
-	if (bottom_half_id != U32_MAX)
+	if (bottom_half_id != U32_MAX) {
 		ffa_dev->ops->notifier_ops->notify_relinquish(ffa_dev,
 							      bottom_half_id);
+		destroy_workqueue(optee->ffa.notif_wq);
+	}
 	optee_remove_common(optee);
 
 	mutex_destroy(&optee->ffa.mutex);
@@ -835,6 +846,13 @@ static int optee_ffa_async_notif_init(struct ffa_device *ffa_dev,
 	u32 notif_id = 0;
 	int rc;
 
+	INIT_WORK(&optee->ffa.notif_work, notif_work_fn);
+	optee->ffa.notif_wq = create_workqueue("optee_notification");
+	if (!optee->ffa.notif_wq) {
+		rc = -EINVAL;
+		goto err;
+	}
+
 	while (true) {
 		rc = ffa_dev->ops->notifier_ops->notify_request(ffa_dev,
 								is_per_vcpu,
@@ -851,19 +869,24 @@ static int optee_ffa_async_notif_init(struct ffa_device *ffa_dev,
 		 * notifications in that case.
 		 */
 		if (rc != -EACCES)
-			return rc;
+			goto err_wq;
 		notif_id++;
 		if (notif_id >= OPTEE_FFA_MAX_ASYNC_NOTIF_VALUE)
-			return rc;
+			goto err_wq;
 	}
 	optee->ffa.bottom_half_value = notif_id;
 
 	rc = enable_async_notif(optee);
-	if (rc < 0) {
-		ffa_dev->ops->notifier_ops->notify_relinquish(ffa_dev,
-							      notif_id);
-		optee->ffa.bottom_half_value = U32_MAX;
-	}
+	if (rc < 0)
+		goto err_rel;
+
+	return 0;
+err_rel:
+	ffa_dev->ops->notifier_ops->notify_relinquish(ffa_dev, notif_id);
+err_wq:
+	destroy_workqueue(optee->ffa.notif_wq);
+err:
+	optee->ffa.bottom_half_value = U32_MAX;
 
 	return rc;
 }
diff --git a/drivers/tee/optee/optee_private.h b/drivers/tee/optee/optee_private.h
index dc0f355ef72a..9526087f0e68 100644
--- a/drivers/tee/optee/optee_private.h
+++ b/drivers/tee/optee/optee_private.h
@@ -165,6 +165,8 @@ struct optee_ffa {
 	/* Serializes access to @global_ids */
 	struct mutex mutex;
 	struct rhashtable global_ids;
+	struct workqueue_struct *notif_wq;
+	struct work_struct notif_work;
 };
 
 struct optee;
diff --git a/drivers/tee/optee/supp.c b/drivers/tee/optee/supp.c
index 322a543b8c27..d0f397c90242 100644
--- a/drivers/tee/optee/supp.c
+++ b/drivers/tee/optee/supp.c
@@ -80,7 +80,6 @@ u32 optee_supp_thrd_req(struct tee_context *ctx, u32 func, size_t num_params,
 	struct optee *optee = tee_get_drvdata(ctx->teedev);
 	struct optee_supp *supp = &optee->supp;
 	struct optee_supp_req *req;
-	bool interruptable;
 	u32 ret;
 
 	/*
@@ -111,36 +110,18 @@ u32 optee_supp_thrd_req(struct tee_context *ctx, u32 func, size_t num_params,
 	/*
 	 * Wait for supplicant to process and return result, once we've
 	 * returned from wait_for_completion(&req->c) successfully we have
-	 * exclusive access again.
+	 * exclusive access again. Allow the wait to be killable such that
+	 * the wait doesn't turn into an indefinite state if the supplicant
+	 * gets hung for some reason.
 	 */
-	while (wait_for_completion_interruptible(&req->c)) {
+	if (wait_for_completion_killable(&req->c)) {
 		mutex_lock(&supp->mutex);
-		interruptable = !supp->ctx;
-		if (interruptable) {
-			/*
-			 * There's no supplicant available and since the
-			 * supp->mutex currently is held none can
-			 * become available until the mutex released
-			 * again.
-			 *
-			 * Interrupting an RPC to supplicant is only
-			 * allowed as a way of slightly improving the user
-			 * experience in case the supplicant hasn't been
-			 * started yet. During normal operation the supplicant
-			 * will serve all requests in a timely manner and
-			 * interrupting then wouldn't make sense.
-			 */
-			if (req->in_queue) {
-				list_del(&req->link);
-				req->in_queue = false;
-			}
+		if (req->in_queue) {
+			list_del(&req->link);
+			req->in_queue = false;
 		}
 		mutex_unlock(&supp->mutex);
-
-		if (interruptable) {
-			req->ret = TEEC_ERROR_COMMUNICATION;
-			break;
-		}
+		req->ret = TEEC_ERROR_COMMUNICATION;
 	}
 
 	ret = req->ret;
diff --git a/drivers/tee/tee_core.c b/drivers/tee/tee_core.c
index d113679b1e2d..acc7998758ad 100644
--- a/drivers/tee/tee_core.c
+++ b/drivers/tee/tee_core.c
@@ -10,6 +10,7 @@
 #include <linux/fs.h>
 #include <linux/idr.h>
 #include <linux/module.h>
+#include <linux/overflow.h>
 #include <linux/slab.h>
 #include <linux/tee_core.h>
 #include <linux/uaccess.h>
@@ -19,7 +20,7 @@
 
 #define TEE_NUM_DEVICES	32
 
-#define TEE_IOCTL_PARAM_SIZE(x) (sizeof(struct tee_param) * (x))
+#define TEE_IOCTL_PARAM_SIZE(x) (size_mul(sizeof(struct tee_param), (x)))
 
 #define TEE_UUID_NS_NAME_SIZE	128
 
@@ -487,7 +488,7 @@ static int tee_ioctl_open_session(struct tee_context *ctx,
 	if (copy_from_user(&arg, uarg, sizeof(arg)))
 		return -EFAULT;
 
-	if (sizeof(arg) + TEE_IOCTL_PARAM_SIZE(arg.num_params) != buf.buf_len)
+	if (size_add(sizeof(arg), TEE_IOCTL_PARAM_SIZE(arg.num_params)) != buf.buf_len)
 		return -EINVAL;
 
 	if (arg.num_params) {
@@ -565,7 +566,7 @@ static int tee_ioctl_invoke(struct tee_context *ctx,
 	if (copy_from_user(&arg, uarg, sizeof(arg)))
 		return -EFAULT;
 
-	if (sizeof(arg) + TEE_IOCTL_PARAM_SIZE(arg.num_params) != buf.buf_len)
+	if (size_add(sizeof(arg), TEE_IOCTL_PARAM_SIZE(arg.num_params)) != buf.buf_len)
 		return -EINVAL;
 
 	if (arg.num_params) {
@@ -699,7 +700,7 @@ static int tee_ioctl_supp_recv(struct tee_context *ctx,
 	if (get_user(num_params, &uarg->num_params))
 		return -EFAULT;
 
-	if (sizeof(*uarg) + TEE_IOCTL_PARAM_SIZE(num_params) != buf.buf_len)
+	if (size_add(sizeof(*uarg), TEE_IOCTL_PARAM_SIZE(num_params)) != buf.buf_len)
 		return -EINVAL;
 
 	params = kcalloc(num_params, sizeof(struct tee_param), GFP_KERNEL);
@@ -798,7 +799,7 @@ static int tee_ioctl_supp_send(struct tee_context *ctx,
 	    get_user(num_params, &uarg->num_params))
 		return -EFAULT;
 
-	if (sizeof(*uarg) + TEE_IOCTL_PARAM_SIZE(num_params) > buf.buf_len)
+	if (size_add(sizeof(*uarg), TEE_IOCTL_PARAM_SIZE(num_params)) > buf.buf_len)
 		return -EINVAL;
 
 	params = kcalloc(num_params, sizeof(struct tee_param), GFP_KERNEL);
diff --git a/drivers/thermal/cpufreq_cooling.c b/drivers/thermal/cpufreq_cooling.c
index 280071be30b1..6b7ab1814c12 100644
--- a/drivers/thermal/cpufreq_cooling.c
+++ b/drivers/thermal/cpufreq_cooling.c
@@ -57,8 +57,6 @@ struct time_in_idle {
  * @max_level: maximum cooling level. One less than total number of valid
  *	cpufreq frequencies.
  * @em: Reference on the Energy Model of the device
- * @cdev: thermal_cooling_device pointer to keep track of the
- *	registered cooling device.
  * @policy: cpufreq policy.
  * @cooling_ops: cpufreq callbacks to thermal cooling device ops
  * @idle_time: idle time stats
diff --git a/drivers/thermal/gov_bang_bang.c b/drivers/thermal/gov_bang_bang.c
index 863e7a4272e6..b887e48e8c7e 100644
--- a/drivers/thermal/gov_bang_bang.c
+++ b/drivers/thermal/gov_bang_bang.c
@@ -67,6 +67,7 @@ static void bang_bang_control(struct thermal_zone_device *tz,
 			      const struct thermal_trip *trip,
 			      bool crossed_up)
 {
+	const struct thermal_trip_desc *td = trip_to_trip_desc(trip);
 	struct thermal_instance *instance;
 
 	lockdep_assert_held(&tz->lock);
@@ -75,10 +76,8 @@ static void bang_bang_control(struct thermal_zone_device *tz,
 		thermal_zone_trip_id(tz, trip), trip->temperature,
 		tz->temperature, trip->hysteresis);
 
-	list_for_each_entry(instance, &tz->thermal_instances, tz_node) {
-		if (instance->trip == trip)
-			bang_bang_set_instance_target(instance, crossed_up);
-	}
+	list_for_each_entry(instance, &td->thermal_instances, trip_node)
+		bang_bang_set_instance_target(instance, crossed_up);
 }
 
 static void bang_bang_manage(struct thermal_zone_device *tz)
@@ -104,8 +103,8 @@ static void bang_bang_manage(struct thermal_zone_device *tz)
 		 * to the thermal zone temperature and the trip point threshold.
 		 */
 		turn_on = tz->temperature >= td->threshold;
-		list_for_each_entry(instance, &tz->thermal_instances, tz_node) {
-			if (!instance->initialized && instance->trip == trip)
+		list_for_each_entry(instance, &td->thermal_instances, trip_node) {
+			if (!instance->initialized)
 				bang_bang_set_instance_target(instance, turn_on);
 		}
 	}
diff --git a/drivers/thermal/gov_fair_share.c b/drivers/thermal/gov_fair_share.c
index ce0ea571ed67..d37d57d48c38 100644
--- a/drivers/thermal/gov_fair_share.c
+++ b/drivers/thermal/gov_fair_share.c
@@ -44,7 +44,7 @@ static int get_trip_level(struct thermal_zone_device *tz)
 /**
  * fair_share_throttle - throttles devices associated with the given zone
  * @tz: thermal_zone_device
- * @trip: trip point
+ * @td: trip point descriptor
  * @trip_level: number of trips crossed by the zone temperature
  *
  * Throttling Logic: This uses three parameters to calculate the new
@@ -61,29 +61,23 @@ static int get_trip_level(struct thermal_zone_device *tz)
  * new_state of cooling device = P3 * P2 * P1
  */
 static void fair_share_throttle(struct thermal_zone_device *tz,
-				const struct thermal_trip *trip,
+				const struct thermal_trip_desc *td,
 				int trip_level)
 {
 	struct thermal_instance *instance;
 	int total_weight = 0;
 	int nr_instances = 0;
 
-	list_for_each_entry(instance, &tz->thermal_instances, tz_node) {
-		if (instance->trip != trip)
-			continue;
-
+	list_for_each_entry(instance, &td->thermal_instances, trip_node) {
 		total_weight += instance->weight;
 		nr_instances++;
 	}
 
-	list_for_each_entry(instance, &tz->thermal_instances, tz_node) {
+	list_for_each_entry(instance, &td->thermal_instances, trip_node) {
 		struct thermal_cooling_device *cdev = instance->cdev;
 		u64 dividend;
 		u32 divisor;
 
-		if (instance->trip != trip)
-			continue;
-
 		dividend = trip_level;
 		dividend *= cdev->max_state;
 		divisor = tz->num_trips;
@@ -116,7 +110,7 @@ static void fair_share_manage(struct thermal_zone_device *tz)
 		    trip->type == THERMAL_TRIP_HOT)
 			continue;
 
-		fair_share_throttle(tz, trip, trip_level);
+		fair_share_throttle(tz, td, trip_level);
 	}
 }
 
diff --git a/drivers/thermal/gov_power_allocator.c b/drivers/thermal/gov_power_allocator.c
index 1b2345a697c5..90b4bfd9237b 100644
--- a/drivers/thermal/gov_power_allocator.c
+++ b/drivers/thermal/gov_power_allocator.c
@@ -97,11 +97,9 @@ struct power_allocator_params {
 	struct power_actor *power;
 };
 
-static bool power_actor_is_valid(struct power_allocator_params *params,
-				 struct thermal_instance *instance)
+static bool power_actor_is_valid(struct thermal_instance *instance)
 {
-	return (instance->trip == params->trip_max &&
-		 cdev_is_power_actor(instance->cdev));
+	return cdev_is_power_actor(instance->cdev);
 }
 
 /**
@@ -118,13 +116,14 @@ static bool power_actor_is_valid(struct power_allocator_params *params,
 static u32 estimate_sustainable_power(struct thermal_zone_device *tz)
 {
 	struct power_allocator_params *params = tz->governor_data;
+	const struct thermal_trip_desc *td = trip_to_trip_desc(params->trip_max);
 	struct thermal_cooling_device *cdev;
 	struct thermal_instance *instance;
 	u32 sustainable_power = 0;
 	u32 min_power;
 
-	list_for_each_entry(instance, &tz->thermal_instances, tz_node) {
-		if (!power_actor_is_valid(params, instance))
+	list_for_each_entry(instance, &td->thermal_instances, trip_node) {
+		if (!power_actor_is_valid(instance))
 			continue;
 
 		cdev = instance->cdev;
@@ -364,7 +363,7 @@ static void divvy_up_power(struct power_actor *power, int num_actors,
 
 	for (i = 0; i < num_actors; i++) {
 		struct power_actor *pa = &power[i];
-		u64 req_range = (u64)pa->req_power * power_range;
+		u64 req_range = (u64)pa->weighted_req_power * power_range;
 
 		pa->granted_power = DIV_ROUND_CLOSEST_ULL(req_range,
 							  total_req_power);
@@ -400,6 +399,7 @@ static void divvy_up_power(struct power_actor *power, int num_actors,
 static void allocate_power(struct thermal_zone_device *tz, int control_temp)
 {
 	struct power_allocator_params *params = tz->governor_data;
+	const struct thermal_trip_desc *td = trip_to_trip_desc(params->trip_max);
 	unsigned int num_actors = params->num_actors;
 	struct power_actor *power = params->power;
 	struct thermal_cooling_device *cdev;
@@ -417,10 +417,10 @@ static void allocate_power(struct thermal_zone_device *tz, int control_temp)
 	/* Clean all buffers for new power estimations */
 	memset(power, 0, params->buffer_size);
 
-	list_for_each_entry(instance, &tz->thermal_instances, tz_node) {
+	list_for_each_entry(instance, &td->thermal_instances, trip_node) {
 		struct power_actor *pa = &power[i];
 
-		if (!power_actor_is_valid(params, instance))
+		if (!power_actor_is_valid(instance))
 			continue;
 
 		cdev = instance->cdev;
@@ -454,10 +454,10 @@ static void allocate_power(struct thermal_zone_device *tz, int control_temp)
 		       power_range);
 
 	i = 0;
-	list_for_each_entry(instance, &tz->thermal_instances, tz_node) {
+	list_for_each_entry(instance, &td->thermal_instances, trip_node) {
 		struct power_actor *pa = &power[i];
 
-		if (!power_actor_is_valid(params, instance))
+		if (!power_actor_is_valid(instance))
 			continue;
 
 		power_actor_set_power(instance->cdev, instance,
@@ -538,12 +538,13 @@ static void reset_pid_controller(struct power_allocator_params *params)
 static void allow_maximum_power(struct thermal_zone_device *tz)
 {
 	struct power_allocator_params *params = tz->governor_data;
+	const struct thermal_trip_desc *td = trip_to_trip_desc(params->trip_max);
 	struct thermal_cooling_device *cdev;
 	struct thermal_instance *instance;
 	u32 req_power;
 
-	list_for_each_entry(instance, &tz->thermal_instances, tz_node) {
-		if (!power_actor_is_valid(params, instance))
+	list_for_each_entry(instance, &td->thermal_instances, trip_node) {
+		if (!power_actor_is_valid(instance))
 			continue;
 
 		cdev = instance->cdev;
@@ -581,13 +582,16 @@ static void allow_maximum_power(struct thermal_zone_device *tz)
 static int check_power_actors(struct thermal_zone_device *tz,
 			      struct power_allocator_params *params)
 {
+	const struct thermal_trip_desc *td;
 	struct thermal_instance *instance;
 	int ret = 0;
 
-	list_for_each_entry(instance, &tz->thermal_instances, tz_node) {
-		if (instance->trip != params->trip_max)
-			continue;
+	if (!params->trip_max)
+		return 0;
+
+	td = trip_to_trip_desc(params->trip_max);
 
+	list_for_each_entry(instance, &td->thermal_instances, trip_node) {
 		if (!cdev_is_power_actor(instance->cdev)) {
 			dev_warn(&tz->device, "power_allocator: %s is not a power actor\n",
 				 instance->cdev->type);
@@ -631,30 +635,43 @@ clean_state:
 	return ret;
 }
 
+static void power_allocator_update_weight(struct power_allocator_params *params)
+{
+	const struct thermal_trip_desc *td;
+	struct thermal_instance *instance;
+
+	if (!params->trip_max)
+		return;
+
+	td = trip_to_trip_desc(params->trip_max);
+
+	params->total_weight = 0;
+	list_for_each_entry(instance, &td->thermal_instances, trip_node)
+		if (power_actor_is_valid(instance))
+			params->total_weight += instance->weight;
+}
+
 static void power_allocator_update_tz(struct thermal_zone_device *tz,
 				      enum thermal_notify_event reason)
 {
 	struct power_allocator_params *params = tz->governor_data;
+	const struct thermal_trip_desc *td = trip_to_trip_desc(params->trip_max);
 	struct thermal_instance *instance;
 	int num_actors = 0;
 
 	switch (reason) {
 	case THERMAL_TZ_BIND_CDEV:
 	case THERMAL_TZ_UNBIND_CDEV:
-		list_for_each_entry(instance, &tz->thermal_instances, tz_node)
-			if (power_actor_is_valid(params, instance))
+		list_for_each_entry(instance, &td->thermal_instances, trip_node)
+			if (power_actor_is_valid(instance))
 				num_actors++;
 
-		if (num_actors == params->num_actors)
-			return;
+		if (num_actors != params->num_actors)
+			allocate_actors_buffer(params, num_actors);
 
-		allocate_actors_buffer(params, num_actors);
-		break;
+		fallthrough;
 	case THERMAL_INSTANCE_WEIGHT_CHANGED:
-		params->total_weight = 0;
-		list_for_each_entry(instance, &tz->thermal_instances, tz_node)
-			if (power_actor_is_valid(params, instance))
-				params->total_weight += instance->weight;
+		power_allocator_update_weight(params);
 		break;
 	default:
 		break;
@@ -720,6 +737,8 @@ static int power_allocator_bind(struct thermal_zone_device *tz)
 
 	tz->governor_data = params;
 
+	power_allocator_update_weight(params);
+
 	return 0;
 
 free_params:
diff --git a/drivers/thermal/gov_step_wise.c b/drivers/thermal/gov_step_wise.c
index fd5527188cf9..ea4bf88d37f3 100644
--- a/drivers/thermal/gov_step_wise.c
+++ b/drivers/thermal/gov_step_wise.c
@@ -66,9 +66,10 @@ static unsigned long get_target_state(struct thermal_instance *instance,
 }
 
 static void thermal_zone_trip_update(struct thermal_zone_device *tz,
-				     const struct thermal_trip *trip,
+				     const struct thermal_trip_desc *td,
 				     int trip_threshold)
 {
+	const struct thermal_trip *trip = &td->trip;
 	enum thermal_trend trend = get_tz_trend(tz, trip);
 	int trip_id = thermal_zone_trip_id(tz, trip);
 	struct thermal_instance *instance;
@@ -82,12 +83,9 @@ static void thermal_zone_trip_update(struct thermal_zone_device *tz,
 	dev_dbg(&tz->device, "Trip%d[type=%d,temp=%d]:trend=%d,throttle=%d\n",
 		trip_id, trip->type, trip_threshold, trend, throttle);
 
-	list_for_each_entry(instance, &tz->thermal_instances, tz_node) {
+	list_for_each_entry(instance, &td->thermal_instances, trip_node) {
 		int old_target;
 
-		if (instance->trip != trip)
-			continue;
-
 		old_target = instance->target;
 		instance->target = get_target_state(instance, trend, throttle);
 
@@ -127,11 +125,13 @@ static void step_wise_manage(struct thermal_zone_device *tz)
 		    trip->type == THERMAL_TRIP_HOT)
 			continue;
 
-		thermal_zone_trip_update(tz, trip, td->threshold);
+		thermal_zone_trip_update(tz, td, td->threshold);
 	}
 
-	list_for_each_entry(instance, &tz->thermal_instances, tz_node)
-		thermal_cdev_update(instance->cdev);
+	for_each_trip_desc(tz, td) {
+		list_for_each_entry(instance, &td->thermal_instances, trip_node)
+			thermal_cdev_update(instance->cdev);
+	}
 }
 
 static struct thermal_governor thermal_gov_step_wise = {
diff --git a/drivers/thermal/intel/int340x_thermal/int3402_thermal.c b/drivers/thermal/intel/int340x_thermal/int3402_thermal.c
index ab8bfb5a3946..40ab6b2d4fb0 100644
--- a/drivers/thermal/intel/int340x_thermal/int3402_thermal.c
+++ b/drivers/thermal/intel/int340x_thermal/int3402_thermal.c
@@ -45,6 +45,9 @@ static int int3402_thermal_probe(struct platform_device *pdev)
 	struct int3402_thermal_data *d;
 	int ret;
 
+	if (!adev)
+		return -ENODEV;
+
 	if (!acpi_has_method(adev->handle, "_TMP"))
 		return -ENODEV;
 
diff --git a/drivers/thermal/intel/x86_pkg_temp_thermal.c b/drivers/thermal/intel/x86_pkg_temp_thermal.c
index 65b33b56a9be..8c44f378b61e 100644
--- a/drivers/thermal/intel/x86_pkg_temp_thermal.c
+++ b/drivers/thermal/intel/x86_pkg_temp_thermal.c
@@ -329,6 +329,7 @@ static int pkg_temp_thermal_device_add(unsigned int cpu)
 	tj_max = intel_tcc_get_tjmax(cpu);
 	if (tj_max < 0)
 		return tj_max;
+	tj_max *= 1000;
 
 	zonedev = kzalloc(sizeof(*zonedev), GFP_KERNEL);
 	if (!zonedev)
diff --git a/drivers/thermal/mediatek/lvts_thermal.c b/drivers/thermal/mediatek/lvts_thermal.c
index 1997e91bb3be..ae063d1bc95f 100644
--- a/drivers/thermal/mediatek/lvts_thermal.c
+++ b/drivers/thermal/mediatek/lvts_thermal.c
@@ -65,7 +65,6 @@
 #define LVTS_HW_FILTER				0x0
 #define LVTS_TSSEL_CONF				0x13121110
 #define LVTS_CALSCALE_CONF			0x300
-#define LVTS_MONINT_CONF			0x8300318C
 
 #define LVTS_MONINT_OFFSET_SENSOR0		0xC
 #define LVTS_MONINT_OFFSET_SENSOR1		0x180
@@ -91,8 +90,6 @@
 #define LVTS_MSR_READ_TIMEOUT_US	400
 #define LVTS_MSR_READ_WAIT_US		(LVTS_MSR_READ_TIMEOUT_US / 2)
 
-#define LVTS_HW_TSHUT_TEMP		105000
-
 #define LVTS_MINIMUM_THRESHOLD		20000
 
 static int golden_temp = LVTS_GOLDEN_TEMP_DEFAULT;
@@ -145,7 +142,6 @@ struct lvts_ctrl {
 	struct lvts_sensor sensors[LVTS_SENSOR_MAX];
 	const struct lvts_data *lvts_data;
 	u32 calibration[LVTS_SENSOR_MAX];
-	u32 hw_tshut_raw_temp;
 	u8 valid_sensor_mask;
 	int mode;
 	void __iomem *base;
@@ -213,6 +209,13 @@ static const struct debugfs_reg32 lvts_regs[] = {
 	LVTS_DEBUG_FS_REGS(LVTS_CLKEN),
 };
 
+static void lvts_debugfs_exit(void *data)
+{
+	struct lvts_domain *lvts_td = data;
+
+	debugfs_remove_recursive(lvts_td->dom_dentry);
+}
+
 static int lvts_debugfs_init(struct device *dev, struct lvts_domain *lvts_td)
 {
 	struct debugfs_regset32 *regset;
@@ -245,12 +248,7 @@ static int lvts_debugfs_init(struct device *dev, struct lvts_domain *lvts_td)
 		debugfs_create_regset32("registers", 0400, dentry, regset);
 	}
 
-	return 0;
-}
-
-static void lvts_debugfs_exit(struct lvts_domain *lvts_td)
-{
-	debugfs_remove_recursive(lvts_td->dom_dentry);
+	return devm_add_action_or_reset(dev, lvts_debugfs_exit, lvts_td);
 }
 
 #else
@@ -261,8 +259,6 @@ static inline int lvts_debugfs_init(struct device *dev,
 	return 0;
 }
 
-static void lvts_debugfs_exit(struct lvts_domain *lvts_td) { }
-
 #endif
 
 static int lvts_raw_to_temp(u32 raw_temp, int temp_factor)
@@ -837,14 +833,6 @@ static int lvts_ctrl_init(struct device *dev, struct lvts_domain *lvts_td,
 		 */
 		lvts_ctrl[i].mode = lvts_data->lvts_ctrl[i].mode;
 
-		/*
-		 * The temperature to raw temperature must be done
-		 * after initializing the calibration.
-		 */
-		lvts_ctrl[i].hw_tshut_raw_temp =
-			lvts_temp_to_raw(LVTS_HW_TSHUT_TEMP,
-					 lvts_data->temp_factor);
-
 		lvts_ctrl[i].low_thresh = INT_MIN;
 		lvts_ctrl[i].high_thresh = INT_MIN;
 	}
@@ -860,6 +848,32 @@ static int lvts_ctrl_init(struct device *dev, struct lvts_domain *lvts_td,
 	return 0;
 }
 
+static void lvts_ctrl_monitor_enable(struct device *dev, struct lvts_ctrl *lvts_ctrl, bool enable)
+{
+	/*
+	 * Bitmaps to enable each sensor on filtered mode in the MONCTL0
+	 * register.
+	 */
+	static const u8 sensor_filt_bitmap[] = { BIT(0), BIT(1), BIT(2), BIT(3) };
+	u32 sensor_map = 0;
+	int i;
+
+	if (lvts_ctrl->mode != LVTS_MSR_FILTERED_MODE)
+		return;
+
+	if (enable) {
+		lvts_for_each_valid_sensor(i, lvts_ctrl)
+			sensor_map |= sensor_filt_bitmap[i];
+	}
+
+	/*
+	 * Bits:
+	 *      9: Single point access flow
+	 *    0-3: Enable sensing point 0-3
+	 */
+	writel(sensor_map | BIT(9), LVTS_MONCTL0(lvts_ctrl->base));
+}
+
 /*
  * At this point the configuration register is the only place in the
  * driver where we write multiple values. Per hardware constraint,
@@ -893,7 +907,6 @@ static int lvts_irq_init(struct lvts_ctrl *lvts_ctrl)
 	 *         10 : Selected sensor with bits 19-18
 	 *         11 : Reserved
 	 */
-	writel(BIT(16), LVTS_PROTCTL(lvts_ctrl->base));
 
 	/*
 	 * LVTS_PROTTA : Stage 1 temperature threshold
@@ -906,8 +919,8 @@ static int lvts_irq_init(struct lvts_ctrl *lvts_ctrl)
 	 *
 	 * writel(0x0, LVTS_PROTTA(lvts_ctrl->base));
 	 * writel(0x0, LVTS_PROTTB(lvts_ctrl->base));
+	 * writel(0x0, LVTS_PROTTC(lvts_ctrl->base));
 	 */
-	writel(lvts_ctrl->hw_tshut_raw_temp, LVTS_PROTTC(lvts_ctrl->base));
 
 	/*
 	 * LVTS_MONINT : Interrupt configuration register
@@ -915,7 +928,7 @@ static int lvts_irq_init(struct lvts_ctrl *lvts_ctrl)
 	 * The LVTS_MONINT register layout is the same as the LVTS_MONINTSTS
 	 * register, except we set the bits to enable the interrupt.
 	 */
-	writel(LVTS_MONINT_CONF, LVTS_MONINT(lvts_ctrl->base));
+	writel(0, LVTS_MONINT(lvts_ctrl->base));
 
 	return 0;
 }
@@ -1339,8 +1352,6 @@ static void lvts_remove(struct platform_device *pdev)
 
 	for (i = 0; i < lvts_td->num_lvts_ctrl; i++)
 		lvts_ctrl_set_enable(&lvts_td->lvts_ctrl[i], false);
-
-	lvts_debugfs_exit(lvts_td);
 }
 
 static const struct lvts_ctrl_data mt7988_lvts_ap_data_ctrl[] = {
@@ -1381,8 +1392,11 @@ static int lvts_suspend(struct device *dev)
 
 	lvts_td = dev_get_drvdata(dev);
 
-	for (i = 0; i < lvts_td->num_lvts_ctrl; i++)
+	for (i = 0; i < lvts_td->num_lvts_ctrl; i++) {
+		lvts_ctrl_monitor_enable(dev, &lvts_td->lvts_ctrl[i], false);
+		usleep_range(100, 200);
 		lvts_ctrl_set_enable(&lvts_td->lvts_ctrl[i], false);
+	}
 
 	clk_disable_unprepare(lvts_td->clk);
 
@@ -1400,8 +1414,11 @@ static int lvts_resume(struct device *dev)
 	if (ret)
 		return ret;
 
-	for (i = 0; i < lvts_td->num_lvts_ctrl; i++)
+	for (i = 0; i < lvts_td->num_lvts_ctrl; i++) {
 		lvts_ctrl_set_enable(&lvts_td->lvts_ctrl[i], true);
+		usleep_range(100, 200);
+		lvts_ctrl_monitor_enable(dev, &lvts_td->lvts_ctrl[i], true);
+	}
 
 	return 0;
 }
diff --git a/drivers/thermal/qcom/qcom-spmi-temp-alarm.c b/drivers/thermal/qcom/qcom-spmi-temp-alarm.c
index c2d59cbfaea9..a575585c737b 100644
--- a/drivers/thermal/qcom/qcom-spmi-temp-alarm.c
+++ b/drivers/thermal/qcom/qcom-spmi-temp-alarm.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (c) 2011-2015, 2017, 2020, The Linux Foundation. All rights reserved.
+ * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries.
  */
 
 #include <linux/bitops.h>
@@ -16,6 +17,7 @@
 
 #include "../thermal_hwmon.h"
 
+#define QPNP_TM_REG_DIG_MINOR		0x00
 #define QPNP_TM_REG_DIG_MAJOR		0x01
 #define QPNP_TM_REG_TYPE		0x04
 #define QPNP_TM_REG_SUBTYPE		0x05
@@ -31,7 +33,7 @@
 #define STATUS_GEN2_STATE_MASK		GENMASK(6, 4)
 #define STATUS_GEN2_STATE_SHIFT		4
 
-#define SHUTDOWN_CTRL1_OVERRIDE_S2	BIT(6)
+#define SHUTDOWN_CTRL1_OVERRIDE_STAGE2	BIT(6)
 #define SHUTDOWN_CTRL1_THRESHOLD_MASK	GENMASK(1, 0)
 
 #define SHUTDOWN_CTRL1_RATE_25HZ	BIT(3)
@@ -78,6 +80,7 @@ struct qpnp_tm_chip {
 	/* protects .thresh, .stage and chip registers */
 	struct mutex			lock;
 	bool				initialized;
+	bool				require_stage2_shutdown;
 
 	struct iio_channel		*adc;
 	const long			(*temp_map)[THRESH_COUNT][STAGE_COUNT];
@@ -220,13 +223,13 @@ static int qpnp_tm_update_critical_trip_temp(struct qpnp_tm_chip *chip,
 {
 	long stage2_threshold_min = (*chip->temp_map)[THRESH_MIN][1];
 	long stage2_threshold_max = (*chip->temp_map)[THRESH_MAX][1];
-	bool disable_s2_shutdown = false;
+	bool disable_stage2_shutdown = false;
 	u8 reg;
 
 	WARN_ON(!mutex_is_locked(&chip->lock));
 
 	/*
-	 * Default: S2 and S3 shutdown enabled, thresholds at
+	 * Default: Stage 2 and Stage 3 shutdown enabled, thresholds at
 	 * lowest threshold set, monitoring at 25Hz
 	 */
 	reg = SHUTDOWN_CTRL1_RATE_25HZ;
@@ -241,12 +244,12 @@ static int qpnp_tm_update_critical_trip_temp(struct qpnp_tm_chip *chip,
 		chip->thresh = THRESH_MAX -
 			((stage2_threshold_max - temp) /
 			 TEMP_THRESH_STEP);
-		disable_s2_shutdown = true;
+		disable_stage2_shutdown = true;
 	} else {
 		chip->thresh = THRESH_MAX;
 
 		if (chip->adc)
-			disable_s2_shutdown = true;
+			disable_stage2_shutdown = true;
 		else
 			dev_warn(chip->dev,
 				 "No ADC is configured and critical temperature %d mC is above the maximum stage 2 threshold of %ld mC! Configuring stage 2 shutdown at %ld mC.\n",
@@ -255,8 +258,8 @@ static int qpnp_tm_update_critical_trip_temp(struct qpnp_tm_chip *chip,
 
 skip:
 	reg |= chip->thresh;
-	if (disable_s2_shutdown)
-		reg |= SHUTDOWN_CTRL1_OVERRIDE_S2;
+	if (disable_stage2_shutdown && !chip->require_stage2_shutdown)
+		reg |= SHUTDOWN_CTRL1_OVERRIDE_STAGE2;
 
 	return qpnp_tm_write(chip, QPNP_TM_REG_SHUTDOWN_CTRL1, reg);
 }
@@ -350,8 +353,8 @@ static int qpnp_tm_probe(struct platform_device *pdev)
 {
 	struct qpnp_tm_chip *chip;
 	struct device_node *node;
-	u8 type, subtype, dig_major;
-	u32 res;
+	u8 type, subtype, dig_major, dig_minor;
+	u32 res, dig_revision;
 	int ret, irq;
 
 	node = pdev->dev.of_node;
@@ -403,6 +406,11 @@ static int qpnp_tm_probe(struct platform_device *pdev)
 		return dev_err_probe(&pdev->dev, ret,
 				     "could not read dig_major\n");
 
+	ret = qpnp_tm_read(chip, QPNP_TM_REG_DIG_MINOR, &dig_minor);
+	if (ret < 0)
+		return dev_err_probe(&pdev->dev, ret,
+				     "could not read dig_minor\n");
+
 	if (type != QPNP_TM_TYPE || (subtype != QPNP_TM_SUBTYPE_GEN1
 				     && subtype != QPNP_TM_SUBTYPE_GEN2)) {
 		dev_err(&pdev->dev, "invalid type 0x%02x or subtype 0x%02x\n",
@@ -416,6 +424,23 @@ static int qpnp_tm_probe(struct platform_device *pdev)
 	else
 		chip->temp_map = &temp_map_gen1;
 
+	if (chip->subtype == QPNP_TM_SUBTYPE_GEN2) {
+		dig_revision = (dig_major << 8) | dig_minor;
+		/*
+		 * Check if stage 2 automatic partial shutdown must remain
+		 * enabled to avoid potential repeated faults upon reaching
+		 * over-temperature stage 3.
+		 */
+		switch (dig_revision) {
+		case 0x0001:
+		case 0x0002:
+		case 0x0100:
+		case 0x0101:
+			chip->require_stage2_shutdown = true;
+			break;
+		}
+	}
+
 	/*
 	 * Register the sensor before initializing the hardware to be able to
 	 * read the trip points. get_temp() returns the default temperature
diff --git a/drivers/thermal/qoriq_thermal.c b/drivers/thermal/qoriq_thermal.c
index 52e26be8c53d..aed2729f63d0 100644
--- a/drivers/thermal/qoriq_thermal.c
+++ b/drivers/thermal/qoriq_thermal.c
@@ -18,6 +18,7 @@
 #define SITES_MAX		16
 #define TMR_DISABLE		0x0
 #define TMR_ME			0x80000000
+#define TMR_CMD			BIT(29)
 #define TMR_ALPF		0x0c000000
 #define TMR_ALPF_V2		0x03000000
 #define TMTMIR_DEFAULT	0x0000000f
@@ -356,6 +357,12 @@ static int qoriq_tmu_suspend(struct device *dev)
 	if (ret)
 		return ret;
 
+	if (data->ver > TMU_VER1) {
+		ret = regmap_set_bits(data->regmap, REGS_TMR, TMR_CMD);
+		if (ret)
+			return ret;
+	}
+
 	clk_disable_unprepare(data->clk);
 
 	return 0;
@@ -370,6 +377,12 @@ static int qoriq_tmu_resume(struct device *dev)
 	if (ret)
 		return ret;
 
+	if (data->ver > TMU_VER1) {
+		ret = regmap_clear_bits(data->regmap, REGS_TMR, TMR_CMD);
+		if (ret)
+			return ret;
+	}
+
 	/* Enable monitoring */
 	return regmap_update_bits(data->regmap, REGS_TMR, TMR_ME, TMR_ME);
 }
diff --git a/drivers/thermal/rockchip_thermal.c b/drivers/thermal/rockchip_thermal.c
index 086ed42dd16c..a84f48a752d1 100644
--- a/drivers/thermal/rockchip_thermal.c
+++ b/drivers/thermal/rockchip_thermal.c
@@ -386,6 +386,7 @@ static const struct tsadc_table rk3328_code_table[] = {
 	{296, -40000},
 	{304, -35000},
 	{313, -30000},
+	{322, -25000},
 	{331, -20000},
 	{340, -15000},
 	{349, -10000},
diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index 1d2f2b307bac..c2fa236e10cd 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -490,7 +490,7 @@ static void thermal_zone_device_check(struct work_struct *work)
 
 static void thermal_zone_device_init(struct thermal_zone_device *tz)
 {
-	struct thermal_instance *pos;
+	struct thermal_trip_desc *td;
 
 	INIT_DELAYED_WORK(&tz->poll_queue, thermal_zone_device_check);
 
@@ -498,8 +498,12 @@ static void thermal_zone_device_init(struct thermal_zone_device *tz)
 	tz->passive = 0;
 	tz->prev_low_trip = -INT_MAX;
 	tz->prev_high_trip = INT_MAX;
-	list_for_each_entry(pos, &tz->thermal_instances, tz_node)
-		pos->initialized = false;
+	for_each_trip_desc(tz, td) {
+		struct thermal_instance *instance;
+
+		list_for_each_entry(instance, &td->thermal_instances, trip_node)
+			instance->initialized = false;
+	}
 }
 
 static void thermal_governor_trip_crossed(struct thermal_governor *governor,
@@ -764,12 +768,12 @@ struct thermal_zone_device *thermal_zone_get_by_id(int id)
  * Return: 0 on success, the proper error value otherwise.
  */
 static int thermal_bind_cdev_to_trip(struct thermal_zone_device *tz,
-				     const struct thermal_trip *trip,
+				     struct thermal_trip *trip,
 				     struct thermal_cooling_device *cdev,
 				     struct cooling_spec *cool_spec)
 {
-	struct thermal_instance *dev;
-	struct thermal_instance *pos;
+	struct thermal_trip_desc *td = trip_to_trip_desc(trip);
+	struct thermal_instance *dev, *instance;
 	bool upper_no_limit;
 	int result;
 
@@ -832,13 +836,13 @@ static int thermal_bind_cdev_to_trip(struct thermal_zone_device *tz,
 		goto remove_trip_file;
 
 	mutex_lock(&cdev->lock);
-	list_for_each_entry(pos, &tz->thermal_instances, tz_node)
-		if (pos->trip == trip && pos->cdev == cdev) {
+	list_for_each_entry(instance, &td->thermal_instances, trip_node)
+		if (instance->cdev == cdev) {
 			result = -EEXIST;
 			break;
 		}
 	if (!result) {
-		list_add_tail(&dev->tz_node, &tz->thermal_instances);
+		list_add_tail(&dev->trip_node, &td->thermal_instances);
 		list_add_tail(&dev->cdev_node, &cdev->thermal_instances);
 		atomic_set(&tz->need_update, 1);
 
@@ -872,15 +876,16 @@ free_mem:
  * This function is usually called in the thermal zone device .unbind callback.
  */
 static void thermal_unbind_cdev_from_trip(struct thermal_zone_device *tz,
-					  const struct thermal_trip *trip,
+					  struct thermal_trip *trip,
 					  struct thermal_cooling_device *cdev)
 {
+	struct thermal_trip_desc *td = trip_to_trip_desc(trip);
 	struct thermal_instance *pos, *next;
 
 	mutex_lock(&cdev->lock);
-	list_for_each_entry_safe(pos, next, &tz->thermal_instances, tz_node) {
-		if (pos->trip == trip && pos->cdev == cdev) {
-			list_del(&pos->tz_node);
+	list_for_each_entry_safe(pos, next, &td->thermal_instances, trip_node) {
+		if (pos->cdev == cdev) {
+			list_del(&pos->trip_node);
 			list_del(&pos->cdev_node);
 
 			thermal_governor_update_tz(tz, THERMAL_TZ_UNBIND_CDEV);
@@ -1435,7 +1440,6 @@ thermal_zone_device_register_with_trips(const char *type,
 		}
 	}
 
-	INIT_LIST_HEAD(&tz->thermal_instances);
 	INIT_LIST_HEAD(&tz->node);
 	ida_init(&tz->ida);
 	mutex_init(&tz->lock);
@@ -1459,6 +1463,7 @@ thermal_zone_device_register_with_trips(const char *type,
 	tz->num_trips = num_trips;
 	for_each_trip_desc(tz, td) {
 		td->trip = *trip++;
+		INIT_LIST_HEAD(&td->thermal_instances);
 		/*
 		 * Mark all thresholds as invalid to start with even though
 		 * this only matters for the trips that start as invalid and
diff --git a/drivers/thermal/thermal_core.h b/drivers/thermal/thermal_core.h
index 421522a2bb9d..163871699a60 100644
--- a/drivers/thermal/thermal_core.h
+++ b/drivers/thermal/thermal_core.h
@@ -30,6 +30,7 @@ struct thermal_trip_desc {
 	struct thermal_trip trip;
 	struct thermal_trip_attrs trip_attrs;
 	struct list_head notify_list_node;
+	struct list_head thermal_instances;
 	int notify_temp;
 	int threshold;
 };
@@ -99,7 +100,6 @@ struct thermal_governor {
  * @tzp:	thermal zone parameters
  * @governor:	pointer to the governor for this thermal zone
  * @governor_data:	private pointer for governor data
- * @thermal_instances:	list of &struct thermal_instance of this thermal zone
  * @ida:	&struct ida to generate unique id for this zone's cooling
  *		devices
  * @lock:	lock to protect thermal_instances list
@@ -133,7 +133,6 @@ struct thermal_zone_device {
 	struct thermal_zone_params *tzp;
 	struct thermal_governor *governor;
 	void *governor_data;
-	struct list_head thermal_instances;
 	struct ida ida;
 	struct mutex lock;
 	struct list_head node;
@@ -230,7 +229,7 @@ struct thermal_instance {
 	struct device_attribute attr;
 	char weight_attr_name[THERMAL_NAME_LENGTH];
 	struct device_attribute weight_attr;
-	struct list_head tz_node; /* node in tz->thermal_instances */
+	struct list_head trip_node; /* node in trip->thermal_instances */
 	struct list_head cdev_node; /* node in cdev->thermal_instances */
 	unsigned int weight; /* The weight of the cooling device */
 	bool upper_no_limit;
diff --git a/drivers/thermal/thermal_helpers.c b/drivers/thermal/thermal_helpers.c
index dc374a7a1a65..403d62d3ce77 100644
--- a/drivers/thermal/thermal_helpers.c
+++ b/drivers/thermal/thermal_helpers.c
@@ -43,10 +43,11 @@ static bool thermal_instance_present(struct thermal_zone_device *tz,
 				     struct thermal_cooling_device *cdev,
 				     const struct thermal_trip *trip)
 {
+	const struct thermal_trip_desc *td = trip_to_trip_desc(trip);
 	struct thermal_instance *ti;
 
-	list_for_each_entry(ti, &tz->thermal_instances, tz_node) {
-		if (ti->trip == trip && ti->cdev == cdev)
+	list_for_each_entry(ti, &td->thermal_instances, trip_node) {
+		if (ti->cdev == cdev)
 			return true;
 	}
 
diff --git a/drivers/thermal/thermal_of.c b/drivers/thermal/thermal_of.c
index 5d3d8ce672cd..e0aa9d9d5604 100644
--- a/drivers/thermal/thermal_of.c
+++ b/drivers/thermal/thermal_of.c
@@ -293,12 +293,40 @@ static bool thermal_of_get_cooling_spec(struct device_node *map_np, int index,
 	return true;
 }
 
+static bool thermal_of_cm_lookup(struct device_node *cm_np,
+				 const struct thermal_trip *trip,
+				 struct thermal_cooling_device *cdev,
+				 struct cooling_spec *c)
+{
+	for_each_child_of_node_scoped(cm_np, child) {
+		struct device_node *tr_np;
+		int count, i;
+
+		tr_np = of_parse_phandle(child, "trip", 0);
+		if (tr_np != trip->priv)
+			continue;
+
+		/* The trip has been found, look up the cdev. */
+		count = of_count_phandle_with_args(child, "cooling-device",
+						   "#cooling-cells");
+		if (count <= 0)
+			pr_err("Add a cooling_device property with at least one device\n");
+
+		for (i = 0; i < count; i++) {
+			if (thermal_of_get_cooling_spec(child, i, cdev, c))
+				return true;
+		}
+	}
+
+	return false;
+}
+
 static bool thermal_of_should_bind(struct thermal_zone_device *tz,
 				   const struct thermal_trip *trip,
 				   struct thermal_cooling_device *cdev,
 				   struct cooling_spec *c)
 {
-	struct device_node *tz_np, *cm_np, *child;
+	struct device_node *tz_np, *cm_np;
 	bool result = false;
 
 	tz_np = thermal_of_zone_get_by_name(tz);
@@ -312,28 +340,7 @@ static bool thermal_of_should_bind(struct thermal_zone_device *tz,
 		goto out;
 
 	/* Look up the trip and the cdev in the cooling maps. */
-	for_each_child_of_node(cm_np, child) {
-		struct device_node *tr_np;
-		int count, i;
-
-		tr_np = of_parse_phandle(child, "trip", 0);
-		if (tr_np != trip->priv)
-			continue;
-
-		/* The trip has been found, look up the cdev. */
-		count = of_count_phandle_with_args(child, "cooling-device", "#cooling-cells");
-		if (count <= 0)
-			pr_err("Add a cooling_device property with at least one device\n");
-
-		for (i = 0; i < count; i++) {
-			result = thermal_of_get_cooling_spec(child, i, cdev, c);
-			if (result)
-				break;
-		}
-
-		of_node_put(child);
-		break;
-	}
+	result = thermal_of_cm_lookup(cm_np, trip, cdev, c);
 
 	of_node_put(cm_np);
 out:
diff --git a/drivers/thermal/thermal_sysfs.c b/drivers/thermal/thermal_sysfs.c
index 1838aa729bb5..c58c53d4ecc6 100644
--- a/drivers/thermal/thermal_sysfs.c
+++ b/drivers/thermal/thermal_sysfs.c
@@ -40,10 +40,13 @@ temp_show(struct device *dev, struct device_attribute *attr, char *buf)
 
 	ret = thermal_zone_get_temp(tz, &temperature);
 
-	if (ret)
-		return ret;
+	if (!ret)
+		return sprintf(buf, "%d\n", temperature);
 
-	return sprintf(buf, "%d\n", temperature);
+	if (ret == -EAGAIN)
+		return -ENODATA;
+
+	return ret;
 }
 
 static ssize_t
diff --git a/drivers/thunderbolt/ctl.c b/drivers/thunderbolt/ctl.c
index 4bdb2d45e0bf..58ab3d86bc25 100644
--- a/drivers/thunderbolt/ctl.c
+++ b/drivers/thunderbolt/ctl.c
@@ -148,6 +148,11 @@ static void tb_cfg_request_dequeue(struct tb_cfg_request *req)
 	struct tb_ctl *ctl = req->ctl;
 
 	mutex_lock(&ctl->request_queue_lock);
+	if (!test_bit(TB_CFG_REQUEST_ACTIVE, &req->flags)) {
+		mutex_unlock(&ctl->request_queue_lock);
+		return;
+	}
+
 	list_del(&req->list);
 	clear_bit(TB_CFG_REQUEST_ACTIVE, &req->flags);
 	if (test_bit(TB_CFG_REQUEST_CANCELED, &req->flags))
diff --git a/drivers/thunderbolt/domain.c b/drivers/thunderbolt/domain.c
index 144d0232a70c..b692618ed9d4 100644
--- a/drivers/thunderbolt/domain.c
+++ b/drivers/thunderbolt/domain.c
@@ -36,7 +36,7 @@ static bool match_service_id(const struct tb_service_id *id,
 			return false;
 	}
 
-	if (id->match_flags & TBSVC_MATCH_PROTOCOL_VERSION) {
+	if (id->match_flags & TBSVC_MATCH_PROTOCOL_REVISION) {
 		if (id->protocol_revision != svc->prtcrevs)
 			return false;
 	}
diff --git a/drivers/thunderbolt/retimer.c b/drivers/thunderbolt/retimer.c
index eeb64433ebbc..3488be762067 100644
--- a/drivers/thunderbolt/retimer.c
+++ b/drivers/thunderbolt/retimer.c
@@ -93,9 +93,11 @@ static int tb_retimer_nvm_add(struct tb_retimer *rt)
 	if (ret)
 		goto err_nvm;
 
-	ret = tb_nvm_add_non_active(nvm, nvm_write);
-	if (ret)
-		goto err_nvm;
+	if (!rt->no_nvm_upgrade) {
+		ret = tb_nvm_add_non_active(nvm, nvm_write);
+		if (ret)
+			goto err_nvm;
+	}
 
 	rt->nvm = nvm;
 	dev_dbg(&rt->dev, "NVM version %x.%x\n", nvm->major, nvm->minor);
diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c
index 6a2116cbb06f..60818c1bec48 100644
--- a/drivers/thunderbolt/switch.c
+++ b/drivers/thunderbolt/switch.c
@@ -1450,7 +1450,7 @@ int tb_dp_port_set_hops(struct tb_port *port, unsigned int video,
 		return ret;
 
 	data[0] &= ~ADP_DP_CS_0_VIDEO_HOPID_MASK;
-	data[1] &= ~ADP_DP_CS_1_AUX_RX_HOPID_MASK;
+	data[1] &= ~ADP_DP_CS_1_AUX_TX_HOPID_MASK;
 	data[1] &= ~ADP_DP_CS_1_AUX_RX_HOPID_MASK;
 
 	data[0] |= (video << ADP_DP_CS_0_VIDEO_HOPID_SHIFT) &
@@ -3437,7 +3437,7 @@ void tb_sw_set_unplugged(struct tb_switch *sw)
 	}
 }
 
-static int tb_switch_set_wake(struct tb_switch *sw, unsigned int flags)
+static int tb_switch_set_wake(struct tb_switch *sw, unsigned int flags, bool runtime)
 {
 	if (flags)
 		tb_sw_dbg(sw, "enabling wakeup: %#x\n", flags);
@@ -3445,7 +3445,7 @@ static int tb_switch_set_wake(struct tb_switch *sw, unsigned int flags)
 		tb_sw_dbg(sw, "disabling wakeup\n");
 
 	if (tb_switch_is_usb4(sw))
-		return usb4_switch_set_wake(sw, flags);
+		return usb4_switch_set_wake(sw, flags, runtime);
 	return tb_lc_set_wake(sw, flags);
 }
 
@@ -3521,7 +3521,7 @@ int tb_switch_resume(struct tb_switch *sw, bool runtime)
 		tb_switch_check_wakes(sw);
 
 	/* Disable wakes */
-	tb_switch_set_wake(sw, 0);
+	tb_switch_set_wake(sw, 0, true);
 
 	err = tb_switch_tmu_init(sw);
 	if (err)
@@ -3602,7 +3602,7 @@ void tb_switch_suspend(struct tb_switch *sw, bool runtime)
 		flags |= TB_WAKE_ON_USB4 | TB_WAKE_ON_USB3 | TB_WAKE_ON_PCIE;
 	}
 
-	tb_switch_set_wake(sw, flags);
+	tb_switch_set_wake(sw, flags, runtime);
 
 	if (tb_switch_is_usb4(sw))
 		usb4_switch_set_sleep(sw);
diff --git a/drivers/thunderbolt/tb.c b/drivers/thunderbolt/tb.c
index a7c6919fbf97..e1da433a9e7f 100644
--- a/drivers/thunderbolt/tb.c
+++ b/drivers/thunderbolt/tb.c
@@ -1295,12 +1295,16 @@ static void tb_scan_port(struct tb_port *port)
 		goto out_rpm_put;
 	}
 
-	tb_retimer_scan(port, true);
-
 	sw = tb_switch_alloc(port->sw->tb, &port->sw->dev,
 			     tb_downstream_route(port));
 	if (IS_ERR(sw)) {
 		/*
+		 * Make the downstream retimers available even if there
+		 * is no router connected.
+		 */
+		tb_retimer_scan(port, true);
+
+		/*
 		 * If there is an error accessing the connected switch
 		 * it may be connected to another domain. Also we allow
 		 * the other domain to be connected to a max depth switch.
@@ -1350,6 +1354,14 @@ static void tb_scan_port(struct tb_port *port)
 	tb_configure_link(port, upstream_port, sw);
 
 	/*
+	 * Scan for downstream retimers. We only scan them after the
+	 * router has been enumerated to avoid issues with certain
+	 * Pluggable devices that expect the host to enumerate them
+	 * within certain timeout.
+	 */
+	tb_retimer_scan(port, true);
+
+	/*
 	 * CL0s and CL1 are enabled and supported together.
 	 * Silently ignore CLx enabling in case CLx is not supported.
 	 */
diff --git a/drivers/thunderbolt/tb.h b/drivers/thunderbolt/tb.h
index 6737188f2581..2a701f94af12 100644
--- a/drivers/thunderbolt/tb.h
+++ b/drivers/thunderbolt/tb.h
@@ -1299,7 +1299,7 @@ int usb4_switch_read_uid(struct tb_switch *sw, u64 *uid);
 int usb4_switch_drom_read(struct tb_switch *sw, unsigned int address, void *buf,
 			  size_t size);
 bool usb4_switch_lane_bonding_possible(struct tb_switch *sw);
-int usb4_switch_set_wake(struct tb_switch *sw, unsigned int flags);
+int usb4_switch_set_wake(struct tb_switch *sw, unsigned int flags, bool runtime);
 int usb4_switch_set_sleep(struct tb_switch *sw);
 int usb4_switch_nvm_sector_size(struct tb_switch *sw);
 int usb4_switch_nvm_read(struct tb_switch *sw, unsigned int address, void *buf,
diff --git a/drivers/thunderbolt/usb4.c b/drivers/thunderbolt/usb4.c
index 402fdf8b1cde..9eacde552f81 100644
--- a/drivers/thunderbolt/usb4.c
+++ b/drivers/thunderbolt/usb4.c
@@ -403,12 +403,12 @@ bool usb4_switch_lane_bonding_possible(struct tb_switch *sw)
  * usb4_switch_set_wake() - Enabled/disable wake
  * @sw: USB4 router
  * @flags: Wakeup flags (%0 to disable)
+ * @runtime: Wake is being programmed during system runtime
  *
  * Enables/disables router to wake up from sleep.
  */
-int usb4_switch_set_wake(struct tb_switch *sw, unsigned int flags)
+int usb4_switch_set_wake(struct tb_switch *sw, unsigned int flags, bool runtime)
 {
-	struct usb4_port *usb4;
 	struct tb_port *port;
 	u64 route = tb_route(sw);
 	u32 val;
@@ -438,13 +438,11 @@ int usb4_switch_set_wake(struct tb_switch *sw, unsigned int flags)
 			val |= PORT_CS_19_WOU4;
 		} else {
 			bool configured = val & PORT_CS_19_PC;
-			usb4 = port->usb4;
+			bool wakeup = runtime || device_may_wakeup(&port->usb4->dev);
 
-			if (((flags & TB_WAKE_ON_CONNECT) |
-			      device_may_wakeup(&usb4->dev)) && !configured)
+			if ((flags & TB_WAKE_ON_CONNECT) && wakeup && !configured)
 				val |= PORT_CS_19_WOC;
-			if (((flags & TB_WAKE_ON_DISCONNECT) |
-			      device_may_wakeup(&usb4->dev)) && configured)
+			if ((flags & TB_WAKE_ON_DISCONNECT) && wakeup && configured)
 				val |= PORT_CS_19_WOD;
 			if ((flags & TB_WAKE_ON_USB4) && configured)
 				val |= PORT_CS_19_WOU4;
diff --git a/drivers/tty/mips_ejtag_fdc.c b/drivers/tty/mips_ejtag_fdc.c
index afbf7738c7c4..58b28be63c79 100644
--- a/drivers/tty/mips_ejtag_fdc.c
+++ b/drivers/tty/mips_ejtag_fdc.c
@@ -1154,7 +1154,7 @@ static char kgdbfdc_rbuf[4];
 
 /* write buffer to allow compaction */
 static unsigned int kgdbfdc_wbuflen;
-static char kgdbfdc_wbuf[4];
+static u8 kgdbfdc_wbuf[4];
 
 static void __iomem *kgdbfdc_setup(void)
 {
@@ -1215,7 +1215,7 @@ static int kgdbfdc_read_char(void)
 /* push an FDC word from write buffer to TX FIFO */
 static void kgdbfdc_push_one(void)
 {
-	const char *bufs[1] = { kgdbfdc_wbuf };
+	const u8 *bufs[1] = { kgdbfdc_wbuf };
 	struct fdc_word word;
 	void __iomem *regs;
 	unsigned int i;
diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c
index 5e9ca4376d68..94fa981081fd 100644
--- a/drivers/tty/n_tty.c
+++ b/drivers/tty/n_tty.c
@@ -486,7 +486,8 @@ static int do_output_char(u8 c, struct tty_struct *tty, int space)
 static int process_output(u8 c, struct tty_struct *tty)
 {
 	struct n_tty_data *ldata = tty->disc_data;
-	int	space, retval;
+	unsigned int space;
+	int retval;
 
 	mutex_lock(&ldata->output_lock);
 
@@ -522,16 +523,16 @@ static ssize_t process_output_block(struct tty_struct *tty,
 				    const u8 *buf, unsigned int nr)
 {
 	struct n_tty_data *ldata = tty->disc_data;
-	int	space;
-	int	i;
+	unsigned int space;
+	int i;
 	const u8 *cp;
 
 	mutex_lock(&ldata->output_lock);
 
 	space = tty_write_room(tty);
-	if (space <= 0) {
+	if (space == 0) {
 		mutex_unlock(&ldata->output_lock);
-		return space;
+		return 0;
 	}
 	if (nr > space)
 		nr = space;
@@ -696,7 +697,7 @@ static int n_tty_process_echo_ops(struct tty_struct *tty, size_t *tail,
 static size_t __process_echoes(struct tty_struct *tty)
 {
 	struct n_tty_data *ldata = tty->disc_data;
-	int	space, old_space;
+	unsigned int space, old_space;
 	size_t tail;
 	u8 c;
 
diff --git a/drivers/tty/serial/8250/8250.h b/drivers/tty/serial/8250/8250.h
index e5310c65cf52..10a706fe4b24 100644
--- a/drivers/tty/serial/8250/8250.h
+++ b/drivers/tty/serial/8250/8250.h
@@ -374,6 +374,7 @@ static inline int is_omap1510_8250(struct uart_8250_port *pt)
 
 #ifdef CONFIG_SERIAL_8250_DMA
 extern int serial8250_tx_dma(struct uart_8250_port *);
+extern void serial8250_tx_dma_flush(struct uart_8250_port *);
 extern int serial8250_rx_dma(struct uart_8250_port *);
 extern void serial8250_rx_dma_flush(struct uart_8250_port *);
 extern int serial8250_request_dma(struct uart_8250_port *);
@@ -406,6 +407,7 @@ static inline int serial8250_tx_dma(struct uart_8250_port *p)
 {
 	return -1;
 }
+static inline void serial8250_tx_dma_flush(struct uart_8250_port *p) { }
 static inline int serial8250_rx_dma(struct uart_8250_port *p)
 {
 	return -1;
diff --git a/drivers/tty/serial/8250/8250_dma.c b/drivers/tty/serial/8250/8250_dma.c
index d215c494ee24..bdd26c9f34bd 100644
--- a/drivers/tty/serial/8250/8250_dma.c
+++ b/drivers/tty/serial/8250/8250_dma.c
@@ -149,6 +149,22 @@ err:
 	return ret;
 }
 
+void serial8250_tx_dma_flush(struct uart_8250_port *p)
+{
+	struct uart_8250_dma *dma = p->dma;
+
+	if (!dma->tx_running)
+		return;
+
+	/*
+	 * kfifo_reset() has been called by the serial core, avoid
+	 * advancing and underflowing in __dma_tx_complete().
+	 */
+	dma->tx_size = 0;
+
+	dmaengine_terminate_async(dma->txchan);
+}
+
 int serial8250_rx_dma(struct uart_8250_port *p)
 {
 	struct uart_8250_dma		*dma = p->dma;
diff --git a/drivers/tty/serial/8250/8250_omap.c b/drivers/tty/serial/8250/8250_omap.c
index 0dd68bdbfbcf..4f57991944dc 100644
--- a/drivers/tty/serial/8250/8250_omap.c
+++ b/drivers/tty/serial/8250/8250_omap.c
@@ -1168,16 +1168,6 @@ static int omap_8250_tx_dma(struct uart_8250_port *p)
 		return 0;
 	}
 
-	sg_init_table(&sg, 1);
-	ret = kfifo_dma_out_prepare_mapped(&tport->xmit_fifo, &sg, 1,
-					   UART_XMIT_SIZE, dma->tx_addr);
-	if (ret != 1) {
-		serial8250_clear_THRI(p);
-		return 0;
-	}
-
-	dma->tx_size = sg_dma_len(&sg);
-
 	if (priv->habit & OMAP_DMA_TX_KICK) {
 		unsigned char c;
 		u8 tx_lvl;
@@ -1202,18 +1192,22 @@ static int omap_8250_tx_dma(struct uart_8250_port *p)
 			ret = -EBUSY;
 			goto err;
 		}
-		if (dma->tx_size < 4) {
+		if (kfifo_len(&tport->xmit_fifo) < 4) {
 			ret = -EINVAL;
 			goto err;
 		}
-		if (!kfifo_get(&tport->xmit_fifo, &c)) {
+		if (!uart_fifo_out(&p->port, &c, 1)) {
 			ret = -EINVAL;
 			goto err;
 		}
 		skip_byte = c;
-		/* now we need to recompute due to kfifo_get */
-		kfifo_dma_out_prepare_mapped(&tport->xmit_fifo, &sg, 1,
-				UART_XMIT_SIZE, dma->tx_addr);
+	}
+
+	sg_init_table(&sg, 1);
+	ret = kfifo_dma_out_prepare_mapped(&tport->xmit_fifo, &sg, 1, UART_XMIT_SIZE, dma->tx_addr);
+	if (ret != 1) {
+		ret = -EINVAL;
+		goto err;
 	}
 
 	desc = dmaengine_prep_slave_sg(dma->txchan, &sg, 1, DMA_MEM_TO_DEV,
@@ -1223,6 +1217,7 @@ static int omap_8250_tx_dma(struct uart_8250_port *p)
 		goto err;
 	}
 
+	dma->tx_size = sg_dma_len(&sg);
 	dma->tx_running = 1;
 
 	desc->callback = omap_8250_dma_tx_complete;
diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c
index 6709b6a5f301..b3c19ba777c6 100644
--- a/drivers/tty/serial/8250/8250_pci.c
+++ b/drivers/tty/serial/8250/8250_pci.c
@@ -64,23 +64,17 @@
 #define PCIE_DEVICE_ID_NEO_2_OX_IBM	0x00F6
 #define PCI_DEVICE_ID_PLX_CRONYX_OMEGA	0xc001
 #define PCI_DEVICE_ID_INTEL_PATSBURG_KT 0x1d3d
-#define PCI_VENDOR_ID_WCH		0x4348
-#define PCI_DEVICE_ID_WCH_CH352_2S	0x3253
-#define PCI_DEVICE_ID_WCH_CH353_4S	0x3453
-#define PCI_DEVICE_ID_WCH_CH353_2S1PF	0x5046
-#define PCI_DEVICE_ID_WCH_CH353_1S1P	0x5053
-#define PCI_DEVICE_ID_WCH_CH353_2S1P	0x7053
-#define PCI_DEVICE_ID_WCH_CH355_4S	0x7173
+
+#define PCI_DEVICE_ID_WCHCN_CH352_2S	0x3253
+#define PCI_DEVICE_ID_WCHCN_CH355_4S	0x7173
+
 #define PCI_VENDOR_ID_AGESTAR		0x5372
 #define PCI_DEVICE_ID_AGESTAR_9375	0x6872
 #define PCI_DEVICE_ID_BROADCOM_TRUMANAGE 0x160a
 #define PCI_DEVICE_ID_AMCC_ADDIDATA_APCI7800 0x818e
 
-#define PCIE_VENDOR_ID_WCH		0x1c00
-#define PCIE_DEVICE_ID_WCH_CH382_2S1P	0x3250
-#define PCIE_DEVICE_ID_WCH_CH384_4S	0x3470
-#define PCIE_DEVICE_ID_WCH_CH384_8S	0x3853
-#define PCIE_DEVICE_ID_WCH_CH382_2S	0x3253
+#define PCI_DEVICE_ID_WCHIC_CH384_4S	0x3470
+#define PCI_DEVICE_ID_WCHIC_CH384_8S	0x3853
 
 #define PCI_DEVICE_ID_MOXA_CP102E	0x1024
 #define PCI_DEVICE_ID_MOXA_CP102EL	0x1025
@@ -2694,6 +2688,22 @@ static struct pci_serial_quirk pci_serial_quirks[] = {
 		.setup		= pci_oxsemi_tornado_setup,
 	},
 	{
+		.vendor		= PCI_VENDOR_ID_INTASHIELD,
+		.device		= 0x4026,
+		.subvendor	= PCI_ANY_ID,
+		.subdevice	= PCI_ANY_ID,
+		.init		= pci_oxsemi_tornado_init,
+		.setup		= pci_oxsemi_tornado_setup,
+	},
+	{
+		.vendor		= PCI_VENDOR_ID_INTASHIELD,
+		.device		= 0x4021,
+		.subvendor	= PCI_ANY_ID,
+		.subdevice	= PCI_ANY_ID,
+		.init		= pci_oxsemi_tornado_init,
+		.setup		= pci_oxsemi_tornado_setup,
+	},
+	{
 		.vendor         = PCI_VENDOR_ID_INTEL,
 		.device         = 0x8811,
 		.subvendor	= PCI_ANY_ID,
@@ -2777,80 +2787,80 @@ static struct pci_serial_quirk pci_serial_quirks[] = {
 	},
 	/* WCH CH353 1S1P card (16550 clone) */
 	{
-		.vendor         = PCI_VENDOR_ID_WCH,
-		.device         = PCI_DEVICE_ID_WCH_CH353_1S1P,
+		.vendor         = PCI_VENDOR_ID_WCHCN,
+		.device         = PCI_DEVICE_ID_WCHCN_CH353_1S1P,
 		.subvendor      = PCI_ANY_ID,
 		.subdevice      = PCI_ANY_ID,
 		.setup          = pci_wch_ch353_setup,
 	},
 	/* WCH CH353 2S1P card (16550 clone) */
 	{
-		.vendor         = PCI_VENDOR_ID_WCH,
-		.device         = PCI_DEVICE_ID_WCH_CH353_2S1P,
+		.vendor         = PCI_VENDOR_ID_WCHCN,
+		.device         = PCI_DEVICE_ID_WCHCN_CH353_2S1P,
 		.subvendor      = PCI_ANY_ID,
 		.subdevice      = PCI_ANY_ID,
 		.setup          = pci_wch_ch353_setup,
 	},
 	/* WCH CH353 4S card (16550 clone) */
 	{
-		.vendor         = PCI_VENDOR_ID_WCH,
-		.device         = PCI_DEVICE_ID_WCH_CH353_4S,
+		.vendor         = PCI_VENDOR_ID_WCHCN,
+		.device         = PCI_DEVICE_ID_WCHCN_CH353_4S,
 		.subvendor      = PCI_ANY_ID,
 		.subdevice      = PCI_ANY_ID,
 		.setup          = pci_wch_ch353_setup,
 	},
 	/* WCH CH353 2S1PF card (16550 clone) */
 	{
-		.vendor         = PCI_VENDOR_ID_WCH,
-		.device         = PCI_DEVICE_ID_WCH_CH353_2S1PF,
+		.vendor         = PCI_VENDOR_ID_WCHCN,
+		.device         = PCI_DEVICE_ID_WCHCN_CH353_2S1PF,
 		.subvendor      = PCI_ANY_ID,
 		.subdevice      = PCI_ANY_ID,
 		.setup          = pci_wch_ch353_setup,
 	},
 	/* WCH CH352 2S card (16550 clone) */
 	{
-		.vendor		= PCI_VENDOR_ID_WCH,
-		.device		= PCI_DEVICE_ID_WCH_CH352_2S,
+		.vendor		= PCI_VENDOR_ID_WCHCN,
+		.device		= PCI_DEVICE_ID_WCHCN_CH352_2S,
 		.subvendor	= PCI_ANY_ID,
 		.subdevice	= PCI_ANY_ID,
 		.setup		= pci_wch_ch353_setup,
 	},
 	/* WCH CH355 4S card (16550 clone) */
 	{
-		.vendor		= PCI_VENDOR_ID_WCH,
-		.device		= PCI_DEVICE_ID_WCH_CH355_4S,
+		.vendor		= PCI_VENDOR_ID_WCHCN,
+		.device		= PCI_DEVICE_ID_WCHCN_CH355_4S,
 		.subvendor	= PCI_ANY_ID,
 		.subdevice	= PCI_ANY_ID,
 		.setup		= pci_wch_ch355_setup,
 	},
 	/* WCH CH382 2S card (16850 clone) */
 	{
-		.vendor         = PCIE_VENDOR_ID_WCH,
-		.device         = PCIE_DEVICE_ID_WCH_CH382_2S,
+		.vendor         = PCI_VENDOR_ID_WCHIC,
+		.device         = PCI_DEVICE_ID_WCHIC_CH382_2S,
 		.subvendor      = PCI_ANY_ID,
 		.subdevice      = PCI_ANY_ID,
 		.setup          = pci_wch_ch38x_setup,
 	},
 	/* WCH CH382 2S1P card (16850 clone) */
 	{
-		.vendor         = PCIE_VENDOR_ID_WCH,
-		.device         = PCIE_DEVICE_ID_WCH_CH382_2S1P,
+		.vendor         = PCI_VENDOR_ID_WCHIC,
+		.device         = PCI_DEVICE_ID_WCHIC_CH382_2S1P,
 		.subvendor      = PCI_ANY_ID,
 		.subdevice      = PCI_ANY_ID,
 		.setup          = pci_wch_ch38x_setup,
 	},
 	/* WCH CH384 4S card (16850 clone) */
 	{
-		.vendor         = PCIE_VENDOR_ID_WCH,
-		.device         = PCIE_DEVICE_ID_WCH_CH384_4S,
+		.vendor         = PCI_VENDOR_ID_WCHIC,
+		.device         = PCI_DEVICE_ID_WCHIC_CH384_4S,
 		.subvendor      = PCI_ANY_ID,
 		.subdevice      = PCI_ANY_ID,
 		.setup          = pci_wch_ch38x_setup,
 	},
 	/* WCH CH384 8S card (16850 clone) */
 	{
-		.vendor         = PCIE_VENDOR_ID_WCH,
-		.device         = PCIE_DEVICE_ID_WCH_CH384_8S,
+		.vendor         = PCI_VENDOR_ID_WCHIC,
+		.device         = PCI_DEVICE_ID_WCHIC_CH384_8S,
 		.subvendor      = PCI_ANY_ID,
 		.subdevice      = PCI_ANY_ID,
 		.init           = pci_wch_ch38x_init,
@@ -3927,11 +3937,11 @@ static const struct pci_device_id blacklist[] = {
 
 	/* multi-io cards handled by parport_serial */
 	/* WCH CH353 2S1P */
-	{ PCI_DEVICE(0x4348, 0x7053), 0, 0, REPORT_CONFIG(PARPORT_SERIAL), },
+	{ PCI_VDEVICE(WCHCN, 0x7053), REPORT_CONFIG(PARPORT_SERIAL), },
 	/* WCH CH353 1S1P */
-	{ PCI_DEVICE(0x4348, 0x5053), 0, 0, REPORT_CONFIG(PARPORT_SERIAL), },
+	{ PCI_VDEVICE(WCHCN, 0x5053), REPORT_CONFIG(PARPORT_SERIAL), },
 	/* WCH CH382 2S1P */
-	{ PCI_DEVICE(0x1c00, 0x3250), 0, 0, REPORT_CONFIG(PARPORT_SERIAL), },
+	{ PCI_VDEVICE(WCHIC, 0x3250), REPORT_CONFIG(PARPORT_SERIAL), },
 
 	/* Intel platforms with MID UART */
 	{ PCI_VDEVICE(INTEL, 0x081b), REPORT_8250_CONFIG(MID), },
@@ -5219,6 +5229,14 @@ static const struct pci_device_id serial_pci_tbl[] = {
 		PCI_ANY_ID, PCI_ANY_ID,
 		0, 0,
 		pbn_b2_2_115200 },
+	{       PCI_VENDOR_ID_INTASHIELD, 0x0BA2,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0,
+		pbn_b2_2_115200 },
+	{       PCI_VENDOR_ID_INTASHIELD, 0x0BA3,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0,
+		pbn_b2_2_115200 },
 	/*
 	 * Brainboxes UC-235/246
 	 */
@@ -5339,6 +5357,14 @@ static const struct pci_device_id serial_pci_tbl[] = {
 		PCI_ANY_ID, PCI_ANY_ID,
 		0, 0,
 		pbn_b2_4_115200 },
+	{	PCI_VENDOR_ID_INTASHIELD, 0x0C42,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0,
+		pbn_b2_4_115200 },
+	{	PCI_VENDOR_ID_INTASHIELD, 0x0C43,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0,
+		pbn_b2_4_115200 },
 	/*
 	 * Brainboxes UC-420
 	 */
@@ -5565,6 +5591,20 @@ static const struct pci_device_id serial_pci_tbl[] = {
 		PCI_ANY_ID, PCI_ANY_ID,
 		0, 0,
 		pbn_oxsemi_1_15625000 },
+	/*
+	 * Brainboxes XC-235
+	 */
+	{	PCI_VENDOR_ID_INTASHIELD, 0x4026,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0,
+		pbn_oxsemi_1_15625000 },
+	/*
+	 * Brainboxes XC-475
+	 */
+	{	PCI_VENDOR_ID_INTASHIELD, 0x4021,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0,
+		pbn_oxsemi_1_15625000 },
 
 	/*
 	 * Perle PCI-RAS cards
@@ -6004,27 +6044,27 @@ static const struct pci_device_id serial_pci_tbl[] = {
 	 * WCH CH353 series devices: The 2S1P is handled by parport_serial
 	 * so not listed here.
 	 */
-	{	PCI_VENDOR_ID_WCH, PCI_DEVICE_ID_WCH_CH353_4S,
+	{	PCI_VENDOR_ID_WCHCN, PCI_DEVICE_ID_WCHCN_CH353_4S,
 		PCI_ANY_ID, PCI_ANY_ID,
 		0, 0, pbn_b0_bt_4_115200 },
 
-	{	PCI_VENDOR_ID_WCH, PCI_DEVICE_ID_WCH_CH353_2S1PF,
+	{	PCI_VENDOR_ID_WCHCN, PCI_DEVICE_ID_WCHCN_CH353_2S1PF,
 		PCI_ANY_ID, PCI_ANY_ID,
 		0, 0, pbn_b0_bt_2_115200 },
 
-	{	PCI_VENDOR_ID_WCH, PCI_DEVICE_ID_WCH_CH355_4S,
+	{	PCI_VENDOR_ID_WCHCN, PCI_DEVICE_ID_WCHCN_CH355_4S,
 		PCI_ANY_ID, PCI_ANY_ID,
 		0, 0, pbn_b0_bt_4_115200 },
 
-	{	PCIE_VENDOR_ID_WCH, PCIE_DEVICE_ID_WCH_CH382_2S,
+	{	PCI_VENDOR_ID_WCHIC, PCI_DEVICE_ID_WCHIC_CH382_2S,
 		PCI_ANY_ID, PCI_ANY_ID,
 		0, 0, pbn_wch382_2 },
 
-	{	PCIE_VENDOR_ID_WCH, PCIE_DEVICE_ID_WCH_CH384_4S,
+	{	PCI_VENDOR_ID_WCHIC, PCI_DEVICE_ID_WCHIC_CH384_4S,
 		PCI_ANY_ID, PCI_ANY_ID,
 		0, 0, pbn_wch384_4 },
 
-	{	PCIE_VENDOR_ID_WCH, PCIE_DEVICE_ID_WCH_CH384_8S,
+	{	PCI_VENDOR_ID_WCHIC, PCI_DEVICE_ID_WCHIC_CH384_8S,
 		PCI_ANY_ID, PCI_ANY_ID,
 		0, 0, pbn_wch384_8 },
 	/*
diff --git a/drivers/tty/serial/8250/8250_pci1xxxx.c b/drivers/tty/serial/8250/8250_pci1xxxx.c
index d3930bf32fe4..d6b01e015a96 100644
--- a/drivers/tty/serial/8250/8250_pci1xxxx.c
+++ b/drivers/tty/serial/8250/8250_pci1xxxx.c
@@ -78,6 +78,12 @@
 #define UART_TX_BYTE_FIFO			0x00
 #define UART_FIFO_CTL				0x02
 
+#define UART_MODEM_CTL_REG			0x04
+#define UART_MODEM_CTL_RTS_SET			BIT(1)
+
+#define UART_LINE_STAT_REG			0x05
+#define UART_LINE_XMIT_CHECK_MASK		GENMASK(6, 5)
+
 #define UART_ACTV_REG				0x11
 #define UART_BLOCK_SET_ACTIVE			BIT(0)
 
@@ -94,6 +100,7 @@
 #define UART_BIT_SAMPLE_CNT_16			16
 #define BAUD_CLOCK_DIV_INT_MSK			GENMASK(31, 8)
 #define ADCL_CFG_RTS_DELAY_MASK			GENMASK(11, 8)
+#define FRAC_DIV_TX_END_POINT_MASK		GENMASK(23, 20)
 
 #define UART_WAKE_REG				0x8C
 #define UART_WAKE_MASK_REG			0x90
@@ -108,6 +115,7 @@
 
 #define UART_RESET_REG				0x94
 #define UART_RESET_D3_RESET_DISABLE		BIT(16)
+#define UART_RESET_HOT_RESET_DISABLE		BIT(17)
 
 #define UART_BURST_STATUS_REG			0x9C
 #define UART_TX_BURST_FIFO			0xA0
@@ -134,6 +142,11 @@
 #define UART_BST_STAT_LSR_FRAME_ERR		0x8000000
 #define UART_BST_STAT_LSR_THRE			0x20000000
 
+#define GET_MODEM_CTL_RTS_STATUS(reg)		((reg) & UART_MODEM_CTL_RTS_SET)
+#define GET_RTS_PIN_STATUS(val)			(((val) & TIOCM_RTS) >> 1)
+#define RTS_TOGGLE_STATUS_MASK(val, reg)	(GET_MODEM_CTL_RTS_STATUS(reg) \
+						 != GET_RTS_PIN_STATUS(val))
+
 struct pci1xxxx_8250 {
 	unsigned int nr;
 	u8 dev_rev;
@@ -254,6 +267,47 @@ static void pci1xxxx_set_divisor(struct uart_port *port, unsigned int baud,
 	       port->membase + UART_BAUD_CLK_DIVISOR_REG);
 }
 
+static void pci1xxxx_set_mctrl(struct uart_port *port, unsigned int mctrl)
+{
+	u32 fract_div_cfg_reg;
+	u32 line_stat_reg;
+	u32 modem_ctl_reg;
+	u32 adcl_cfg_reg;
+
+	adcl_cfg_reg = readl(port->membase + ADCL_CFG_REG);
+
+	/* HW is responsible in ADCL_EN case */
+	if ((adcl_cfg_reg & (ADCL_CFG_EN | ADCL_CFG_PIN_SEL)))
+		return;
+
+	modem_ctl_reg = readl(port->membase + UART_MODEM_CTL_REG);
+
+	serial8250_do_set_mctrl(port, mctrl);
+
+	if (RTS_TOGGLE_STATUS_MASK(mctrl, modem_ctl_reg)) {
+		line_stat_reg = readl(port->membase + UART_LINE_STAT_REG);
+		if (line_stat_reg & UART_LINE_XMIT_CHECK_MASK) {
+			fract_div_cfg_reg = readl(port->membase +
+						  FRAC_DIV_CFG_REG);
+
+			writel((fract_div_cfg_reg &
+			       ~(FRAC_DIV_TX_END_POINT_MASK)),
+			       port->membase + FRAC_DIV_CFG_REG);
+
+			/* Enable ADC and set the nRTS pin */
+			writel((adcl_cfg_reg | (ADCL_CFG_EN |
+			       ADCL_CFG_PIN_SEL)),
+			       port->membase + ADCL_CFG_REG);
+
+			/* Revert to the original settings */
+			writel(adcl_cfg_reg, port->membase + ADCL_CFG_REG);
+
+			writel(fract_div_cfg_reg, port->membase +
+			       FRAC_DIV_CFG_REG);
+		}
+	}
+}
+
 static int pci1xxxx_rs485_config(struct uart_port *port,
 				 struct ktermios *termios,
 				 struct serial_rs485 *rs485)
@@ -567,6 +621,10 @@ static int pci1xxxx_suspend(struct device *dev)
 	}
 
 	data = readl(p + UART_RESET_REG);
+
+	if (priv->dev_rev >= 0xC0)
+		data |= UART_RESET_HOT_RESET_DISABLE;
+
 	writel(data | UART_RESET_D3_RESET_DISABLE, p + UART_RESET_REG);
 
 	if (wakeup)
@@ -594,7 +652,12 @@ static int pci1xxxx_resume(struct device *dev)
 	}
 
 	data = readl(p + UART_RESET_REG);
+
+	if (priv->dev_rev >= 0xC0)
+		data &= ~UART_RESET_HOT_RESET_DISABLE;
+
 	writel(data & ~UART_RESET_D3_RESET_DISABLE, p + UART_RESET_REG);
+
 	iounmap(p);
 
 	for (i = 0; i < priv->nr; i++) {
@@ -631,9 +694,14 @@ static int pci1xxxx_setup(struct pci_dev *pdev,
 	port->port.rs485_config = pci1xxxx_rs485_config;
 	port->port.rs485_supported = pci1xxxx_rs485_supported;
 
-	/* From C0 rev Burst operation is supported */
+	/*
+	 * C0 and later revisions support Burst operation.
+	 * RTS workaround in mctrl is applicable only to B0.
+	 */
 	if (rev >= 0xC0)
 		port->port.handle_irq = pci1xxxx_handle_irq;
+	else if (rev == 0xB0)
+		port->port.set_mctrl = pci1xxxx_set_mctrl;
 
 	ret = serial8250_pci_setup_port(pdev, port, 0, PORT_OFFSET * port_idx, 0);
 	if (ret < 0)
diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c
index 3509af7dc52b..051967992965 100644
--- a/drivers/tty/serial/8250/8250_port.c
+++ b/drivers/tty/serial/8250/8250_port.c
@@ -1657,7 +1657,7 @@ static void serial8250_disable_ms(struct uart_port *port)
 	if (up->bugs & UART_BUG_NOMSR)
 		return;
 
-	mctrl_gpio_disable_ms(up->gpios);
+	mctrl_gpio_disable_ms_no_sync(up->gpios);
 
 	up->ier &= ~UART_IER_MSI;
 	serial_port_out(port, UART_IER, up->ier);
@@ -2059,7 +2059,8 @@ static void serial8250_break_ctl(struct uart_port *port, int break_state)
 	serial8250_rpm_put(up);
 }
 
-static void wait_for_lsr(struct uart_8250_port *up, int bits)
+/* Returns true if @bits were set, false on timeout */
+static bool wait_for_lsr(struct uart_8250_port *up, int bits)
 {
 	unsigned int status, tmout = 10000;
 
@@ -2074,11 +2075,11 @@ static void wait_for_lsr(struct uart_8250_port *up, int bits)
 		udelay(1);
 		touch_nmi_watchdog();
 	}
+
+	return (tmout != 0);
 }
 
-/*
- *	Wait for transmitter & holding register to empty
- */
+/* Wait for transmitter and holding register to empty with timeout */
 static void wait_for_xmitr(struct uart_8250_port *up, int bits)
 {
 	unsigned int tmout;
@@ -2523,6 +2524,14 @@ static void serial8250_shutdown(struct uart_port *port)
 		serial8250_do_shutdown(port);
 }
 
+static void serial8250_flush_buffer(struct uart_port *port)
+{
+	struct uart_8250_port *up = up_to_u8250p(port);
+
+	if (up->dma)
+		serial8250_tx_dma_flush(up);
+}
+
 static unsigned int serial8250_do_get_divisor(struct uart_port *port,
 					      unsigned int baud,
 					      unsigned int *frac)
@@ -3206,6 +3215,7 @@ static const struct uart_ops serial8250_pops = {
 	.break_ctl	= serial8250_break_ctl,
 	.startup	= serial8250_startup,
 	.shutdown	= serial8250_shutdown,
+	.flush_buffer	= serial8250_flush_buffer,
 	.set_termios	= serial8250_set_termios,
 	.set_ldisc	= serial8250_set_ldisc,
 	.pm		= serial8250_pm,
@@ -3297,6 +3307,16 @@ static void serial8250_console_restore(struct uart_8250_port *up)
 	serial8250_out_MCR(up, up->mcr | UART_MCR_DTR | UART_MCR_RTS);
 }
 
+static void fifo_wait_for_lsr(struct uart_8250_port *up, unsigned int count)
+{
+	unsigned int i;
+
+	for (i = 0; i < count; i++) {
+		if (wait_for_lsr(up, UART_LSR_THRE))
+			return;
+	}
+}
+
 /*
  * Print a string to the serial port using the device FIFO
  *
@@ -3306,13 +3326,15 @@ static void serial8250_console_restore(struct uart_8250_port *up)
 static void serial8250_console_fifo_write(struct uart_8250_port *up,
 					  const char *s, unsigned int count)
 {
-	int i;
 	const char *end = s + count;
 	unsigned int fifosize = up->tx_loadsz;
+	unsigned int tx_count = 0;
 	bool cr_sent = false;
+	unsigned int i;
 
 	while (s != end) {
-		wait_for_lsr(up, UART_LSR_THRE);
+		/* Allow timeout for each byte of a possibly full FIFO */
+		fifo_wait_for_lsr(up, fifosize);
 
 		for (i = 0; i < fifosize && s != end; ++i) {
 			if (*s == '\n' && !cr_sent) {
@@ -3323,7 +3345,14 @@ static void serial8250_console_fifo_write(struct uart_8250_port *up,
 				cr_sent = false;
 			}
 		}
+		tx_count = i;
 	}
+
+	/*
+	 * Allow timeout for each byte written since the caller will only wait
+	 * for UART_LSR_BOTH_EMPTY using the timeout of a single character
+	 */
+	fifo_wait_for_lsr(up, tx_count);
 }
 
 /*
diff --git a/drivers/tty/serial/atmel_serial.c b/drivers/tty/serial/atmel_serial.c
index 09b246c9e389..8bd39586a49f 100644
--- a/drivers/tty/serial/atmel_serial.c
+++ b/drivers/tty/serial/atmel_serial.c
@@ -700,7 +700,7 @@ static void atmel_disable_ms(struct uart_port *port)
 
 	atmel_port->ms_irq_enabled = false;
 
-	mctrl_gpio_disable_ms(atmel_port->gpios);
+	mctrl_gpio_disable_ms_no_sync(atmel_port->gpios);
 
 	if (!mctrl_gpio_to_gpiod(atmel_port->gpios, UART_GPIO_CTS))
 		idr |= ATMEL_US_CTSIC;
diff --git a/drivers/tty/serial/fsl_lpuart.c b/drivers/tty/serial/fsl_lpuart.c
index 77efa7ee6eda..951c3cdac3b9 100644
--- a/drivers/tty/serial/fsl_lpuart.c
+++ b/drivers/tty/serial/fsl_lpuart.c
@@ -440,7 +440,7 @@ static unsigned int lpuart_get_baud_clk_rate(struct lpuart_port *sport)
 
 static void lpuart_stop_tx(struct uart_port *port)
 {
-	unsigned char temp;
+	u8 temp;
 
 	temp = readb(port->membase + UARTCR2);
 	temp &= ~(UARTCR2_TIE | UARTCR2_TCIE);
@@ -449,7 +449,7 @@ static void lpuart_stop_tx(struct uart_port *port)
 
 static void lpuart32_stop_tx(struct uart_port *port)
 {
-	unsigned long temp;
+	u32 temp;
 
 	temp = lpuart32_read(port, UARTCTRL);
 	temp &= ~(UARTCTRL_TIE | UARTCTRL_TCIE);
@@ -458,7 +458,7 @@ static void lpuart32_stop_tx(struct uart_port *port)
 
 static void lpuart_stop_rx(struct uart_port *port)
 {
-	unsigned char temp;
+	u8 temp;
 
 	temp = readb(port->membase + UARTCR2);
 	writeb(temp & ~UARTCR2_RE, port->membase + UARTCR2);
@@ -466,7 +466,7 @@ static void lpuart_stop_rx(struct uart_port *port)
 
 static void lpuart32_stop_rx(struct uart_port *port)
 {
-	unsigned long temp;
+	u32 temp;
 
 	temp = lpuart32_read(port, UARTCTRL);
 	lpuart32_write(port, temp & ~UARTCTRL_RE, UARTCTRL);
@@ -580,7 +580,7 @@ static int lpuart_dma_tx_request(struct uart_port *port)
 	ret = dmaengine_slave_config(sport->dma_tx_chan, &dma_tx_sconfig);
 
 	if (ret) {
-		dev_err(sport->port.dev,
+		dev_err(port->dev,
 				"DMA slave config failed, err = %d\n", ret);
 		return ret;
 	}
@@ -610,13 +610,13 @@ static void lpuart_flush_buffer(struct uart_port *port)
 	}
 
 	if (lpuart_is_32(sport)) {
-		val = lpuart32_read(&sport->port, UARTFIFO);
+		val = lpuart32_read(port, UARTFIFO);
 		val |= UARTFIFO_TXFLUSH | UARTFIFO_RXFLUSH;
-		lpuart32_write(&sport->port, val, UARTFIFO);
+		lpuart32_write(port, val, UARTFIFO);
 	} else {
-		val = readb(sport->port.membase + UARTCFIFO);
+		val = readb(port->membase + UARTCFIFO);
 		val |= UARTCFIFO_TXFLUSH | UARTCFIFO_RXFLUSH;
-		writeb(val, sport->port.membase + UARTCFIFO);
+		writeb(val, port->membase + UARTCFIFO);
 	}
 }
 
@@ -638,38 +638,36 @@ static void lpuart32_wait_bit_set(struct uart_port *port, unsigned int offset,
 
 static int lpuart_poll_init(struct uart_port *port)
 {
-	struct lpuart_port *sport = container_of(port,
-					struct lpuart_port, port);
 	unsigned long flags;
-	unsigned char temp;
+	u8 temp;
 
-	sport->port.fifosize = 0;
+	port->fifosize = 0;
 
-	uart_port_lock_irqsave(&sport->port, &flags);
+	uart_port_lock_irqsave(port, &flags);
 	/* Disable Rx & Tx */
-	writeb(0, sport->port.membase + UARTCR2);
+	writeb(0, port->membase + UARTCR2);
 
-	temp = readb(sport->port.membase + UARTPFIFO);
+	temp = readb(port->membase + UARTPFIFO);
 	/* Enable Rx and Tx FIFO */
 	writeb(temp | UARTPFIFO_RXFE | UARTPFIFO_TXFE,
-			sport->port.membase + UARTPFIFO);
+			port->membase + UARTPFIFO);
 
 	/* flush Tx and Rx FIFO */
 	writeb(UARTCFIFO_TXFLUSH | UARTCFIFO_RXFLUSH,
-			sport->port.membase + UARTCFIFO);
+			port->membase + UARTCFIFO);
 
 	/* explicitly clear RDRF */
-	if (readb(sport->port.membase + UARTSR1) & UARTSR1_RDRF) {
-		readb(sport->port.membase + UARTDR);
-		writeb(UARTSFIFO_RXUF, sport->port.membase + UARTSFIFO);
+	if (readb(port->membase + UARTSR1) & UARTSR1_RDRF) {
+		readb(port->membase + UARTDR);
+		writeb(UARTSFIFO_RXUF, port->membase + UARTSFIFO);
 	}
 
-	writeb(0, sport->port.membase + UARTTWFIFO);
-	writeb(1, sport->port.membase + UARTRWFIFO);
+	writeb(0, port->membase + UARTTWFIFO);
+	writeb(1, port->membase + UARTRWFIFO);
 
 	/* Enable Rx and Tx */
-	writeb(UARTCR2_RE | UARTCR2_TE, sport->port.membase + UARTCR2);
-	uart_port_unlock_irqrestore(&sport->port, flags);
+	writeb(UARTCR2_RE | UARTCR2_TE, port->membase + UARTCR2);
+	uart_port_unlock_irqrestore(port, flags);
 
 	return 0;
 }
@@ -692,33 +690,32 @@ static int lpuart_poll_get_char(struct uart_port *port)
 static int lpuart32_poll_init(struct uart_port *port)
 {
 	unsigned long flags;
-	struct lpuart_port *sport = container_of(port, struct lpuart_port, port);
 	u32 temp;
 
-	sport->port.fifosize = 0;
+	port->fifosize = 0;
 
-	uart_port_lock_irqsave(&sport->port, &flags);
+	uart_port_lock_irqsave(port, &flags);
 
 	/* Disable Rx & Tx */
-	lpuart32_write(&sport->port, 0, UARTCTRL);
+	lpuart32_write(port, 0, UARTCTRL);
 
-	temp = lpuart32_read(&sport->port, UARTFIFO);
+	temp = lpuart32_read(port, UARTFIFO);
 
 	/* Enable Rx and Tx FIFO */
-	lpuart32_write(&sport->port, temp | UARTFIFO_RXFE | UARTFIFO_TXFE, UARTFIFO);
+	lpuart32_write(port, temp | UARTFIFO_RXFE | UARTFIFO_TXFE, UARTFIFO);
 
 	/* flush Tx and Rx FIFO */
-	lpuart32_write(&sport->port, UARTFIFO_TXFLUSH | UARTFIFO_RXFLUSH, UARTFIFO);
+	lpuart32_write(port, UARTFIFO_TXFLUSH | UARTFIFO_RXFLUSH, UARTFIFO);
 
 	/* explicitly clear RDRF */
-	if (lpuart32_read(&sport->port, UARTSTAT) & UARTSTAT_RDRF) {
-		lpuart32_read(&sport->port, UARTDATA);
-		lpuart32_write(&sport->port, UARTFIFO_RXUF, UARTFIFO);
+	if (lpuart32_read(port, UARTSTAT) & UARTSTAT_RDRF) {
+		lpuart32_read(port, UARTDATA);
+		lpuart32_write(port, UARTFIFO_RXUF, UARTFIFO);
 	}
 
 	/* Enable Rx and Tx */
-	lpuart32_write(&sport->port, UARTCTRL_RE | UARTCTRL_TE, UARTCTRL);
-	uart_port_unlock_irqrestore(&sport->port, flags);
+	lpuart32_write(port, UARTCTRL_RE | UARTCTRL_TE, UARTCTRL);
+	uart_port_unlock_irqrestore(port, flags);
 
 	return 0;
 }
@@ -751,7 +748,7 @@ static inline void lpuart_transmit_buffer(struct lpuart_port *sport)
 static inline void lpuart32_transmit_buffer(struct lpuart_port *sport)
 {
 	struct tty_port *tport = &sport->port.state->port;
-	unsigned long txcnt;
+	u32 txcnt;
 	unsigned char c;
 
 	if (sport->port.x_char) {
@@ -788,7 +785,7 @@ static void lpuart_start_tx(struct uart_port *port)
 {
 	struct lpuart_port *sport = container_of(port,
 			struct lpuart_port, port);
-	unsigned char temp;
+	u8 temp;
 
 	temp = readb(port->membase + UARTCR2);
 	writeb(temp | UARTCR2_TIE, port->membase + UARTCR2);
@@ -805,7 +802,7 @@ static void lpuart_start_tx(struct uart_port *port)
 static void lpuart32_start_tx(struct uart_port *port)
 {
 	struct lpuart_port *sport = container_of(port, struct lpuart_port, port);
-	unsigned long temp;
+	u32 temp;
 
 	if (sport->lpuart_dma_tx_use) {
 		if (!lpuart_stopped_or_empty(port))
@@ -838,8 +835,8 @@ static unsigned int lpuart_tx_empty(struct uart_port *port)
 {
 	struct lpuart_port *sport = container_of(port,
 			struct lpuart_port, port);
-	unsigned char sr1 = readb(port->membase + UARTSR1);
-	unsigned char sfifo = readb(port->membase + UARTSFIFO);
+	u8 sr1 = readb(port->membase + UARTSR1);
+	u8 sfifo = readb(port->membase + UARTSFIFO);
 
 	if (sport->dma_tx_in_progress)
 		return 0;
@@ -854,9 +851,9 @@ static unsigned int lpuart32_tx_empty(struct uart_port *port)
 {
 	struct lpuart_port *sport = container_of(port,
 			struct lpuart_port, port);
-	unsigned long stat = lpuart32_read(port, UARTSTAT);
-	unsigned long sfifo = lpuart32_read(port, UARTFIFO);
-	unsigned long ctrl = lpuart32_read(port, UARTCTRL);
+	u32 stat = lpuart32_read(port, UARTSTAT);
+	u32 sfifo = lpuart32_read(port, UARTFIFO);
+	u32 ctrl = lpuart32_read(port, UARTCTRL);
 
 	if (sport->dma_tx_in_progress)
 		return 0;
@@ -883,7 +880,7 @@ static void lpuart_rxint(struct lpuart_port *sport)
 {
 	unsigned int flg, ignored = 0, overrun = 0;
 	struct tty_port *port = &sport->port.state->port;
-	unsigned char rx, sr;
+	u8 rx, sr;
 
 	uart_port_lock(&sport->port);
 
@@ -960,7 +957,7 @@ static void lpuart32_rxint(struct lpuart_port *sport)
 {
 	unsigned int flg, ignored = 0;
 	struct tty_port *port = &sport->port.state->port;
-	unsigned long rx, sr;
+	u32 rx, sr;
 	bool is_break;
 
 	uart_port_lock(&sport->port);
@@ -1038,7 +1035,7 @@ out:
 static irqreturn_t lpuart_int(int irq, void *dev_id)
 {
 	struct lpuart_port *sport = dev_id;
-	unsigned char sts;
+	u8 sts;
 
 	sts = readb(sport->port.membase + UARTSR1);
 
@@ -1112,7 +1109,7 @@ static void lpuart_copy_rx_to_tty(struct lpuart_port *sport)
 	int count, copied;
 
 	if (lpuart_is_32(sport)) {
-		unsigned long sr = lpuart32_read(&sport->port, UARTSTAT);
+		u32 sr = lpuart32_read(&sport->port, UARTSTAT);
 
 		if (sr & (UARTSTAT_PE | UARTSTAT_FE)) {
 			/* Clear the error flags */
@@ -1124,10 +1121,10 @@ static void lpuart_copy_rx_to_tty(struct lpuart_port *sport)
 				sport->port.icount.frame++;
 		}
 	} else {
-		unsigned char sr = readb(sport->port.membase + UARTSR1);
+		u8 sr = readb(sport->port.membase + UARTSR1);
 
 		if (sr & (UARTSR1_PE | UARTSR1_FE)) {
-			unsigned char cr2;
+			u8 cr2;
 
 			/* Disable receiver during this operation... */
 			cr2 = readb(sport->port.membase + UARTCR2);
@@ -1278,7 +1275,7 @@ static void lpuart32_dma_idleint(struct lpuart_port *sport)
 static irqreturn_t lpuart32_int(int irq, void *dev_id)
 {
 	struct lpuart_port *sport = dev_id;
-	unsigned long sts, rxcount;
+	u32 sts, rxcount;
 
 	sts = lpuart32_read(&sport->port, UARTSTAT);
 	rxcount = lpuart32_read(&sport->port, UARTWATER);
@@ -1410,12 +1407,12 @@ static inline int lpuart_start_rx_dma(struct lpuart_port *sport)
 	dma_async_issue_pending(chan);
 
 	if (lpuart_is_32(sport)) {
-		unsigned long temp = lpuart32_read(&sport->port, UARTBAUD);
+		u32 temp = lpuart32_read(&sport->port, UARTBAUD);
 
 		lpuart32_write(&sport->port, temp | UARTBAUD_RDMAE, UARTBAUD);
 
 		if (sport->dma_idle_int) {
-			unsigned long ctrl = lpuart32_read(&sport->port, UARTCTRL);
+			u32 ctrl = lpuart32_read(&sport->port, UARTCTRL);
 
 			lpuart32_write(&sport->port, ctrl | UARTCTRL_ILIE, UARTCTRL);
 		}
@@ -1448,12 +1445,9 @@ static void lpuart_dma_rx_free(struct uart_port *port)
 static int lpuart_config_rs485(struct uart_port *port, struct ktermios *termios,
 			struct serial_rs485 *rs485)
 {
-	struct lpuart_port *sport = container_of(port,
-			struct lpuart_port, port);
-
-	u8 modem = readb(sport->port.membase + UARTMODEM) &
+	u8 modem = readb(port->membase + UARTMODEM) &
 		~(UARTMODEM_TXRTSPOL | UARTMODEM_TXRTSE);
-	writeb(modem, sport->port.membase + UARTMODEM);
+	writeb(modem, port->membase + UARTMODEM);
 
 	if (rs485->flags & SER_RS485_ENABLED) {
 		/* Enable auto RS-485 RTS mode */
@@ -1471,19 +1465,29 @@ static int lpuart_config_rs485(struct uart_port *port, struct ktermios *termios,
 			modem &= ~UARTMODEM_TXRTSPOL;
 	}
 
-	writeb(modem, sport->port.membase + UARTMODEM);
+	writeb(modem, port->membase + UARTMODEM);
 	return 0;
 }
 
 static int lpuart32_config_rs485(struct uart_port *port, struct ktermios *termios,
 			struct serial_rs485 *rs485)
 {
-	struct lpuart_port *sport = container_of(port,
-			struct lpuart_port, port);
-
-	unsigned long modem = lpuart32_read(&sport->port, UARTMODIR)
+	u32 modem = lpuart32_read(port, UARTMODIR)
 				& ~(UARTMODIR_TXRTSPOL | UARTMODIR_TXRTSE);
-	lpuart32_write(&sport->port, modem, UARTMODIR);
+	u32 ctrl;
+
+	/* TXRTSE and TXRTSPOL only can be changed when transmitter is disabled. */
+	ctrl = lpuart32_read(port, UARTCTRL);
+	if (ctrl & UARTCTRL_TE) {
+		/* wait for the transmit engine to complete */
+		lpuart32_wait_bit_set(port, UARTSTAT, UARTSTAT_TC);
+		lpuart32_write(port, ctrl & ~UARTCTRL_TE, UARTCTRL);
+
+		while (lpuart32_read(port, UARTCTRL) & UARTCTRL_TE)
+			cpu_relax();
+	}
+
+	lpuart32_write(port, modem, UARTMODIR);
 
 	if (rs485->flags & SER_RS485_ENABLED) {
 		/* Enable auto RS-485 RTS mode */
@@ -1501,7 +1505,11 @@ static int lpuart32_config_rs485(struct uart_port *port, struct ktermios *termio
 			modem &= ~UARTMODIR_TXRTSPOL;
 	}
 
-	lpuart32_write(&sport->port, modem, UARTMODIR);
+	lpuart32_write(port, modem, UARTMODIR);
+
+	if (ctrl & UARTCTRL_TE)
+		lpuart32_write(port, ctrl, UARTCTRL);
+
 	return 0;
 }
 
@@ -1559,7 +1567,7 @@ static void lpuart32_set_mctrl(struct uart_port *port, unsigned int mctrl)
 
 static void lpuart_break_ctl(struct uart_port *port, int break_state)
 {
-	unsigned char temp;
+	u8 temp;
 
 	temp = readb(port->membase + UARTCR2) & ~UARTCR2_SBK;
 
@@ -1571,7 +1579,7 @@ static void lpuart_break_ctl(struct uart_port *port, int break_state)
 
 static void lpuart32_break_ctl(struct uart_port *port, int break_state)
 {
-	unsigned long temp;
+	u32 temp;
 
 	temp = lpuart32_read(port, UARTCTRL);
 
@@ -1605,8 +1613,7 @@ static void lpuart32_break_ctl(struct uart_port *port, int break_state)
 
 static void lpuart_setup_watermark(struct lpuart_port *sport)
 {
-	unsigned char val, cr2;
-	unsigned char cr2_saved;
+	u8 val, cr2, cr2_saved;
 
 	cr2 = readb(sport->port.membase + UARTCR2);
 	cr2_saved = cr2;
@@ -1639,7 +1646,7 @@ static void lpuart_setup_watermark(struct lpuart_port *sport)
 
 static void lpuart_setup_watermark_enable(struct lpuart_port *sport)
 {
-	unsigned char cr2;
+	u8 cr2;
 
 	lpuart_setup_watermark(sport);
 
@@ -1650,8 +1657,7 @@ static void lpuart_setup_watermark_enable(struct lpuart_port *sport)
 
 static void lpuart32_setup_watermark(struct lpuart_port *sport)
 {
-	unsigned long val, ctrl;
-	unsigned long ctrl_saved;
+	u32 val, ctrl, ctrl_saved;
 
 	ctrl = lpuart32_read(&sport->port, UARTCTRL);
 	ctrl_saved = ctrl;
@@ -1760,7 +1766,7 @@ err:
 static void lpuart_rx_dma_startup(struct lpuart_port *sport)
 {
 	int ret;
-	unsigned char cr3;
+	u8 cr3;
 
 	if (uart_console(&sport->port))
 		goto err;
@@ -1810,14 +1816,14 @@ static void lpuart_hw_setup(struct lpuart_port *sport)
 static int lpuart_startup(struct uart_port *port)
 {
 	struct lpuart_port *sport = container_of(port, struct lpuart_port, port);
-	unsigned char temp;
+	u8 temp;
 
 	/* determine FIFO size and enable FIFO mode */
-	temp = readb(sport->port.membase + UARTPFIFO);
+	temp = readb(port->membase + UARTPFIFO);
 
 	sport->txfifo_size = UARTFIFO_DEPTH((temp >> UARTPFIFO_TXSIZE_OFF) &
 					    UARTPFIFO_FIFOSIZE_MASK);
-	sport->port.fifosize = sport->txfifo_size;
+	port->fifosize = sport->txfifo_size;
 
 	sport->rxfifo_size = UARTFIFO_DEPTH((temp >> UARTPFIFO_RXSIZE_OFF) &
 					    UARTPFIFO_FIFOSIZE_MASK);
@@ -1830,7 +1836,7 @@ static int lpuart_startup(struct uart_port *port)
 
 static void lpuart32_hw_disable(struct lpuart_port *sport)
 {
-	unsigned long temp;
+	u32 temp;
 
 	temp = lpuart32_read(&sport->port, UARTCTRL);
 	temp &= ~(UARTCTRL_RIE | UARTCTRL_ILIE | UARTCTRL_RE |
@@ -1840,7 +1846,7 @@ static void lpuart32_hw_disable(struct lpuart_port *sport)
 
 static void lpuart32_configure(struct lpuart_port *sport)
 {
-	unsigned long temp;
+	u32 temp;
 
 	temp = lpuart32_read(&sport->port, UARTCTRL);
 	if (!sport->lpuart_dma_rx_use)
@@ -1870,14 +1876,14 @@ static void lpuart32_hw_setup(struct lpuart_port *sport)
 static int lpuart32_startup(struct uart_port *port)
 {
 	struct lpuart_port *sport = container_of(port, struct lpuart_port, port);
-	unsigned long temp;
+	u32 temp;
 
 	/* determine FIFO size */
-	temp = lpuart32_read(&sport->port, UARTFIFO);
+	temp = lpuart32_read(port, UARTFIFO);
 
 	sport->txfifo_size = UARTFIFO_DEPTH((temp >> UARTFIFO_TXSIZE_OFF) &
 					    UARTFIFO_FIFOSIZE_MASK);
-	sport->port.fifosize = sport->txfifo_size;
+	port->fifosize = sport->txfifo_size;
 
 	sport->rxfifo_size = UARTFIFO_DEPTH((temp >> UARTFIFO_RXSIZE_OFF) &
 					    UARTFIFO_FIFOSIZE_MASK);
@@ -1890,7 +1896,7 @@ static int lpuart32_startup(struct uart_port *port)
 	if (is_layerscape_lpuart(sport)) {
 		sport->rxfifo_size = 16;
 		sport->txfifo_size = 16;
-		sport->port.fifosize = sport->txfifo_size;
+		port->fifosize = sport->txfifo_size;
 	}
 
 	lpuart_request_dma(sport);
@@ -1924,7 +1930,7 @@ static void lpuart_dma_shutdown(struct lpuart_port *sport)
 static void lpuart_shutdown(struct uart_port *port)
 {
 	struct lpuart_port *sport = container_of(port, struct lpuart_port, port);
-	unsigned char temp;
+	u8 temp;
 	unsigned long flags;
 
 	uart_port_lock_irqsave(port, &flags);
@@ -1944,14 +1950,14 @@ static void lpuart32_shutdown(struct uart_port *port)
 {
 	struct lpuart_port *sport =
 		container_of(port, struct lpuart_port, port);
-	unsigned long temp;
+	u32 temp;
 	unsigned long flags;
 
 	uart_port_lock_irqsave(port, &flags);
 
 	/* clear status */
-	temp = lpuart32_read(&sport->port, UARTSTAT);
-	lpuart32_write(&sport->port, temp, UARTSTAT);
+	temp = lpuart32_read(port, UARTSTAT);
+	lpuart32_write(port, temp, UARTSTAT);
 
 	/* disable Rx/Tx DMA */
 	temp = lpuart32_read(port, UARTBAUD);
@@ -1975,17 +1981,17 @@ lpuart_set_termios(struct uart_port *port, struct ktermios *termios,
 {
 	struct lpuart_port *sport = container_of(port, struct lpuart_port, port);
 	unsigned long flags;
-	unsigned char cr1, old_cr1, old_cr2, cr3, cr4, bdh, modem;
+	u8 cr1, old_cr1, old_cr2, cr3, cr4, bdh, modem;
 	unsigned int  baud;
 	unsigned int old_csize = old ? old->c_cflag & CSIZE : CS8;
 	unsigned int sbr, brfa;
 
-	cr1 = old_cr1 = readb(sport->port.membase + UARTCR1);
-	old_cr2 = readb(sport->port.membase + UARTCR2);
-	cr3 = readb(sport->port.membase + UARTCR3);
-	cr4 = readb(sport->port.membase + UARTCR4);
-	bdh = readb(sport->port.membase + UARTBDH);
-	modem = readb(sport->port.membase + UARTMODEM);
+	cr1 = old_cr1 = readb(port->membase + UARTCR1);
+	old_cr2 = readb(port->membase + UARTCR2);
+	cr3 = readb(port->membase + UARTCR3);
+	cr4 = readb(port->membase + UARTCR4);
+	bdh = readb(port->membase + UARTBDH);
+	modem = readb(port->membase + UARTMODEM);
 	/*
 	 * only support CS8 and CS7, and for CS7 must enable PE.
 	 * supported mode:
@@ -2017,7 +2023,7 @@ lpuart_set_termios(struct uart_port *port, struct ktermios *termios,
 	 * When auto RS-485 RTS mode is enabled,
 	 * hardware flow control need to be disabled.
 	 */
-	if (sport->port.rs485.flags & SER_RS485_ENABLED)
+	if (port->rs485.flags & SER_RS485_ENABLED)
 		termios->c_cflag &= ~CRTSCTS;
 
 	if (termios->c_cflag & CRTSCTS)
@@ -2058,59 +2064,59 @@ lpuart_set_termios(struct uart_port *port, struct ktermios *termios,
 	 * Need to update the Ring buffer length according to the selected
 	 * baud rate and restart Rx DMA path.
 	 *
-	 * Since timer function acqures sport->port.lock, need to stop before
+	 * Since timer function acqures port->lock, need to stop before
 	 * acquring same lock because otherwise del_timer_sync() can deadlock.
 	 */
 	if (old && sport->lpuart_dma_rx_use)
-		lpuart_dma_rx_free(&sport->port);
+		lpuart_dma_rx_free(port);
 
-	uart_port_lock_irqsave(&sport->port, &flags);
+	uart_port_lock_irqsave(port, &flags);
 
-	sport->port.read_status_mask = 0;
+	port->read_status_mask = 0;
 	if (termios->c_iflag & INPCK)
-		sport->port.read_status_mask |= UARTSR1_FE | UARTSR1_PE;
+		port->read_status_mask |= UARTSR1_FE | UARTSR1_PE;
 	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
-		sport->port.read_status_mask |= UARTSR1_FE;
+		port->read_status_mask |= UARTSR1_FE;
 
 	/* characters to ignore */
-	sport->port.ignore_status_mask = 0;
+	port->ignore_status_mask = 0;
 	if (termios->c_iflag & IGNPAR)
-		sport->port.ignore_status_mask |= UARTSR1_PE;
+		port->ignore_status_mask |= UARTSR1_PE;
 	if (termios->c_iflag & IGNBRK) {
-		sport->port.ignore_status_mask |= UARTSR1_FE;
+		port->ignore_status_mask |= UARTSR1_FE;
 		/*
 		 * if we're ignoring parity and break indicators,
 		 * ignore overruns too (for real raw support).
 		 */
 		if (termios->c_iflag & IGNPAR)
-			sport->port.ignore_status_mask |= UARTSR1_OR;
+			port->ignore_status_mask |= UARTSR1_OR;
 	}
 
 	/* update the per-port timeout */
 	uart_update_timeout(port, termios->c_cflag, baud);
 
 	/* wait transmit engin complete */
-	lpuart_wait_bit_set(&sport->port, UARTSR1, UARTSR1_TC);
+	lpuart_wait_bit_set(port, UARTSR1, UARTSR1_TC);
 
 	/* disable transmit and receive */
 	writeb(old_cr2 & ~(UARTCR2_TE | UARTCR2_RE),
-			sport->port.membase + UARTCR2);
+			port->membase + UARTCR2);
 
-	sbr = sport->port.uartclk / (16 * baud);
-	brfa = ((sport->port.uartclk - (16 * sbr * baud)) * 2) / baud;
+	sbr = port->uartclk / (16 * baud);
+	brfa = ((port->uartclk - (16 * sbr * baud)) * 2) / baud;
 	bdh &= ~UARTBDH_SBR_MASK;
 	bdh |= (sbr >> 8) & 0x1F;
 	cr4 &= ~UARTCR4_BRFA_MASK;
 	brfa &= UARTCR4_BRFA_MASK;
-	writeb(cr4 | brfa, sport->port.membase + UARTCR4);
-	writeb(bdh, sport->port.membase + UARTBDH);
-	writeb(sbr & 0xFF, sport->port.membase + UARTBDL);
-	writeb(cr3, sport->port.membase + UARTCR3);
-	writeb(cr1, sport->port.membase + UARTCR1);
-	writeb(modem, sport->port.membase + UARTMODEM);
+	writeb(cr4 | brfa, port->membase + UARTCR4);
+	writeb(bdh, port->membase + UARTBDH);
+	writeb(sbr & 0xFF, port->membase + UARTBDL);
+	writeb(cr3, port->membase + UARTCR3);
+	writeb(cr1, port->membase + UARTCR1);
+	writeb(modem, port->membase + UARTMODEM);
 
 	/* restore control register */
-	writeb(old_cr2, sport->port.membase + UARTCR2);
+	writeb(old_cr2, port->membase + UARTCR2);
 
 	if (old && sport->lpuart_dma_rx_use) {
 		if (!lpuart_start_rx_dma(sport))
@@ -2119,7 +2125,7 @@ lpuart_set_termios(struct uart_port *port, struct ktermios *termios,
 			sport->lpuart_dma_rx_use = false;
 	}
 
-	uart_port_unlock_irqrestore(&sport->port, flags);
+	uart_port_unlock_irqrestore(port, flags);
 }
 
 static void __lpuart32_serial_setbrg(struct uart_port *port,
@@ -2213,13 +2219,13 @@ lpuart32_set_termios(struct uart_port *port, struct ktermios *termios,
 {
 	struct lpuart_port *sport = container_of(port, struct lpuart_port, port);
 	unsigned long flags;
-	unsigned long ctrl, old_ctrl, bd, modem;
+	u32 ctrl, old_ctrl, bd, modem;
 	unsigned int  baud;
 	unsigned int old_csize = old ? old->c_cflag & CSIZE : CS8;
 
-	ctrl = old_ctrl = lpuart32_read(&sport->port, UARTCTRL);
-	bd = lpuart32_read(&sport->port, UARTBAUD);
-	modem = lpuart32_read(&sport->port, UARTMODIR);
+	ctrl = old_ctrl = lpuart32_read(port, UARTCTRL);
+	bd = lpuart32_read(port, UARTBAUD);
+	modem = lpuart32_read(port, UARTMODIR);
 	sport->is_cs7 = false;
 	/*
 	 * only support CS8 and CS7, and for CS7 must enable PE.
@@ -2252,7 +2258,7 @@ lpuart32_set_termios(struct uart_port *port, struct ktermios *termios,
 	 * When auto RS-485 RTS mode is enabled,
 	 * hardware flow control need to be disabled.
 	 */
-	if (sport->port.rs485.flags & SER_RS485_ENABLED)
+	if (port->rs485.flags & SER_RS485_ENABLED)
 		termios->c_cflag &= ~CRTSCTS;
 
 	if (termios->c_cflag & CRTSCTS)
@@ -2293,59 +2299,61 @@ lpuart32_set_termios(struct uart_port *port, struct ktermios *termios,
 	 * Need to update the Ring buffer length according to the selected
 	 * baud rate and restart Rx DMA path.
 	 *
-	 * Since timer function acqures sport->port.lock, need to stop before
+	 * Since timer function acqures port->lock, need to stop before
 	 * acquring same lock because otherwise del_timer_sync() can deadlock.
 	 */
 	if (old && sport->lpuart_dma_rx_use)
-		lpuart_dma_rx_free(&sport->port);
+		lpuart_dma_rx_free(port);
 
-	uart_port_lock_irqsave(&sport->port, &flags);
+	uart_port_lock_irqsave(port, &flags);
 
-	sport->port.read_status_mask = 0;
+	port->read_status_mask = 0;
 	if (termios->c_iflag & INPCK)
-		sport->port.read_status_mask |= UARTSTAT_FE | UARTSTAT_PE;
+		port->read_status_mask |= UARTSTAT_FE | UARTSTAT_PE;
 	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
-		sport->port.read_status_mask |= UARTSTAT_FE;
+		port->read_status_mask |= UARTSTAT_FE;
 
 	/* characters to ignore */
-	sport->port.ignore_status_mask = 0;
+	port->ignore_status_mask = 0;
 	if (termios->c_iflag & IGNPAR)
-		sport->port.ignore_status_mask |= UARTSTAT_PE;
+		port->ignore_status_mask |= UARTSTAT_PE;
 	if (termios->c_iflag & IGNBRK) {
-		sport->port.ignore_status_mask |= UARTSTAT_FE;
+		port->ignore_status_mask |= UARTSTAT_FE;
 		/*
 		 * if we're ignoring parity and break indicators,
 		 * ignore overruns too (for real raw support).
 		 */
 		if (termios->c_iflag & IGNPAR)
-			sport->port.ignore_status_mask |= UARTSTAT_OR;
+			port->ignore_status_mask |= UARTSTAT_OR;
 	}
 
 	/* update the per-port timeout */
 	uart_update_timeout(port, termios->c_cflag, baud);
 
 	/*
+	 * disable CTS to ensure the transmit engine is not blocked by the flow
+	 * control when there is dirty data in TX FIFO
+	 */
+	lpuart32_write(port, modem & ~UARTMODIR_TXCTSE, UARTMODIR);
+
+	/*
 	 * LPUART Transmission Complete Flag may never be set while queuing a break
 	 * character, so skip waiting for transmission complete when UARTCTRL_SBK is
 	 * asserted.
 	 */
-	if (!(old_ctrl & UARTCTRL_SBK)) {
-		lpuart32_write(&sport->port, 0, UARTMODIR);
-		lpuart32_wait_bit_set(&sport->port, UARTSTAT, UARTSTAT_TC);
-	}
+	if (!(old_ctrl & UARTCTRL_SBK))
+		lpuart32_wait_bit_set(port, UARTSTAT, UARTSTAT_TC);
 
 	/* disable transmit and receive */
-	lpuart32_write(&sport->port, old_ctrl & ~(UARTCTRL_TE | UARTCTRL_RE),
+	lpuart32_write(port, old_ctrl & ~(UARTCTRL_TE | UARTCTRL_RE),
 		       UARTCTRL);
 
-	lpuart32_write(&sport->port, bd, UARTBAUD);
+	lpuart32_write(port, bd, UARTBAUD);
 	lpuart32_serial_setbrg(sport, baud);
-	/* disable CTS before enabling UARTCTRL_TE to avoid pending idle preamble */
-	lpuart32_write(&sport->port, modem & ~UARTMODIR_TXCTSE, UARTMODIR);
 	/* restore control register */
-	lpuart32_write(&sport->port, ctrl, UARTCTRL);
+	lpuart32_write(port, ctrl, UARTCTRL);
 	/* re-enable the CTS if needed */
-	lpuart32_write(&sport->port, modem, UARTMODIR);
+	lpuart32_write(port, modem, UARTMODIR);
 
 	if ((ctrl & (UARTCTRL_PE | UARTCTRL_M)) == UARTCTRL_PE)
 		sport->is_cs7 = true;
@@ -2357,7 +2365,7 @@ lpuart32_set_termios(struct uart_port *port, struct ktermios *termios,
 			sport->lpuart_dma_rx_use = false;
 	}
 
-	uart_port_unlock_irqrestore(&sport->port, flags);
+	uart_port_unlock_irqrestore(port, flags);
 }
 
 static const char *lpuart_type(struct uart_port *port)
@@ -2470,7 +2478,7 @@ static void
 lpuart_console_write(struct console *co, const char *s, unsigned int count)
 {
 	struct lpuart_port *sport = lpuart_ports[co->index];
-	unsigned char  old_cr2, cr2;
+	u8  old_cr2, cr2;
 	unsigned long flags;
 	int locked = 1;
 
@@ -2500,7 +2508,7 @@ static void
 lpuart32_console_write(struct console *co, const char *s, unsigned int count)
 {
 	struct lpuart_port *sport = lpuart_ports[co->index];
-	unsigned long  old_cr, cr;
+	u32 old_cr, cr;
 	unsigned long flags;
 	int locked = 1;
 
@@ -2534,7 +2542,7 @@ static void __init
 lpuart_console_get_options(struct lpuart_port *sport, int *baud,
 			   int *parity, int *bits)
 {
-	unsigned char cr, bdh, bdl, brfa;
+	u8 cr, bdh, bdl, brfa;
 	unsigned int sbr, uartclk, baud_raw;
 
 	cr = readb(sport->port.membase + UARTCR2);
@@ -2583,7 +2591,7 @@ static void __init
 lpuart32_console_get_options(struct lpuart_port *sport, int *baud,
 			   int *parity, int *bits)
 {
-	unsigned long cr, bd;
+	u32 cr, bd;
 	unsigned int sbr, uartclk, baud_raw;
 
 	cr = lpuart32_read(&sport->port, UARTCTRL);
@@ -2789,13 +2797,13 @@ static int lpuart_global_reset(struct lpuart_port *sport)
 {
 	struct uart_port *port = &sport->port;
 	void __iomem *global_addr;
-	unsigned long ctrl, bd;
+	u32 ctrl, bd;
 	unsigned int val = 0;
 	int ret;
 
 	ret = clk_prepare_enable(sport->ipg_clk);
 	if (ret) {
-		dev_err(sport->port.dev, "failed to enable uart ipg clk: %d\n", ret);
+		dev_err(port->dev, "failed to enable uart ipg clk: %d\n", ret);
 		return ret;
 	}
 
@@ -2806,10 +2814,10 @@ static int lpuart_global_reset(struct lpuart_port *sport)
 		 */
 		ctrl = lpuart32_read(port, UARTCTRL);
 		if (ctrl & UARTCTRL_TE) {
-			bd = lpuart32_read(&sport->port, UARTBAUD);
+			bd = lpuart32_read(port, UARTBAUD);
 			if (read_poll_timeout(lpuart32_tx_empty, val, val, 1, 100000, false,
 					      port)) {
-				dev_warn(sport->port.dev,
+				dev_warn(port->dev,
 					 "timeout waiting for transmit engine to complete\n");
 				clk_disable_unprepare(sport->ipg_clk);
 				return 0;
@@ -2995,7 +3003,7 @@ static int lpuart_runtime_resume(struct device *dev)
 
 static void serial_lpuart_enable_wakeup(struct lpuart_port *sport, bool on)
 {
-	unsigned int val, baud;
+	u32 val, baud;
 
 	if (lpuart_is_32(sport)) {
 		val = lpuart32_read(&sport->port, UARTCTRL);
@@ -3060,7 +3068,7 @@ static int lpuart_suspend_noirq(struct device *dev)
 static int lpuart_resume_noirq(struct device *dev)
 {
 	struct lpuart_port *sport = dev_get_drvdata(dev);
-	unsigned int val;
+	u32 val;
 
 	pinctrl_pm_select_default_state(dev);
 
@@ -3080,7 +3088,8 @@ static int lpuart_resume_noirq(struct device *dev)
 static int lpuart_suspend(struct device *dev)
 {
 	struct lpuart_port *sport = dev_get_drvdata(dev);
-	unsigned long temp, flags;
+	u32 temp;
+	unsigned long flags;
 
 	uart_suspend_port(&lpuart_reg, &sport->port);
 
@@ -3160,7 +3169,7 @@ static void lpuart_console_fixup(struct lpuart_port *sport)
 	 * in VLLS mode, or restore console setting here.
 	 */
 	if (is_imx7ulp_lpuart(sport) && lpuart_uport_is_active(sport) &&
-	    console_suspend_enabled && uart_console(&sport->port)) {
+	    console_suspend_enabled && uart_console(uport)) {
 
 		mutex_lock(&port->mutex);
 		memset(&termios, 0, sizeof(struct ktermios));
diff --git a/drivers/tty/serial/imx.c b/drivers/tty/serial/imx.c
index 90974d338f3c..deb9635cb48d 100644
--- a/drivers/tty/serial/imx.c
+++ b/drivers/tty/serial/imx.c
@@ -233,6 +233,7 @@ struct imx_port {
 	enum imx_tx_state	tx_state;
 	struct hrtimer		trigger_start_tx;
 	struct hrtimer		trigger_stop_tx;
+	unsigned int		rxtl;
 };
 
 struct imx_port_ucrs {
@@ -1328,6 +1329,7 @@ static void imx_uart_clear_rx_errors(struct imx_port *sport)
 
 #define TXTL_DEFAULT 8
 #define RXTL_DEFAULT 8 /* 8 characters or aging timer */
+#define RXTL_CONSOLE_DEFAULT 1
 #define TXTL_DMA 8 /* DMA burst setting */
 #define RXTL_DMA 9 /* DMA burst setting */
 
@@ -1445,7 +1447,7 @@ static void imx_uart_disable_dma(struct imx_port *sport)
 	ucr1 &= ~(UCR1_RXDMAEN | UCR1_TXDMAEN | UCR1_ATDMAEN);
 	imx_uart_writel(sport, ucr1, UCR1);
 
-	imx_uart_setup_ufcr(sport, TXTL_DEFAULT, RXTL_DEFAULT);
+	imx_uart_setup_ufcr(sport, TXTL_DEFAULT, sport->rxtl);
 
 	sport->dma_is_enabled = 0;
 }
@@ -1470,7 +1472,12 @@ static int imx_uart_startup(struct uart_port *port)
 		return retval;
 	}
 
-	imx_uart_setup_ufcr(sport, TXTL_DEFAULT, RXTL_DEFAULT);
+	if (uart_console(&sport->port))
+		sport->rxtl = RXTL_CONSOLE_DEFAULT;
+	else
+		sport->rxtl = RXTL_DEFAULT;
+
+	imx_uart_setup_ufcr(sport, TXTL_DEFAULT, sport->rxtl);
 
 	/* disable the DREN bit (Data Ready interrupt enable) before
 	 * requesting IRQs
@@ -1596,7 +1603,7 @@ static void imx_uart_shutdown(struct uart_port *port)
 		imx_uart_dma_exit(sport);
 	}
 
-	mctrl_gpio_disable_ms(sport->gpios);
+	mctrl_gpio_disable_ms_sync(sport->gpios);
 
 	uart_port_lock_irqsave(&sport->port, &flags);
 	ucr2 = imx_uart_readl(sport, UCR2);
@@ -1936,7 +1943,7 @@ static int imx_uart_poll_init(struct uart_port *port)
 	if (retval)
 		clk_disable_unprepare(sport->clk_ipg);
 
-	imx_uart_setup_ufcr(sport, TXTL_DEFAULT, RXTL_DEFAULT);
+	imx_uart_setup_ufcr(sport, TXTL_DEFAULT, sport->rxtl);
 
 	uart_port_lock_irqsave(&sport->port, &flags);
 
@@ -2028,7 +2035,7 @@ static int imx_uart_rs485_config(struct uart_port *port, struct ktermios *termio
 		/* If the receiver trigger is 0, set it to a default value */
 		ufcr = imx_uart_readl(sport, UFCR);
 		if ((ufcr & UFCR_RXTL_MASK) == 0)
-			imx_uart_setup_ufcr(sport, TXTL_DEFAULT, RXTL_DEFAULT);
+			imx_uart_setup_ufcr(sport, TXTL_DEFAULT, sport->rxtl);
 		imx_uart_start_rx(port);
 	}
 
@@ -2213,7 +2220,7 @@ imx_uart_console_setup(struct console *co, char *options)
 	else
 		imx_uart_console_get_options(sport, &baud, &parity, &bits);
 
-	imx_uart_setup_ufcr(sport, TXTL_DEFAULT, RXTL_DEFAULT);
+	imx_uart_setup_ufcr(sport, TXTL_DEFAULT, sport->rxtl);
 
 	retval = uart_set_options(&sport->port, co, baud, parity, bits, flow);
 
diff --git a/drivers/tty/serial/jsm/jsm_tty.c b/drivers/tty/serial/jsm/jsm_tty.c
index ce0fef7e2c66..be2f130696b3 100644
--- a/drivers/tty/serial/jsm/jsm_tty.c
+++ b/drivers/tty/serial/jsm/jsm_tty.c
@@ -451,6 +451,7 @@ int jsm_uart_port_init(struct jsm_board *brd)
 		if (!brd->channels[i])
 			continue;
 
+		brd->channels[i]->uart_port.dev = &brd->pci_dev->dev;
 		brd->channels[i]->uart_port.irq = brd->irq;
 		brd->channels[i]->uart_port.uartclk = 14745600;
 		brd->channels[i]->uart_port.type = PORT_JSM;
diff --git a/drivers/tty/serial/milbeaut_usio.c b/drivers/tty/serial/milbeaut_usio.c
index fb082ee73d5b..9b54f017f2e8 100644
--- a/drivers/tty/serial/milbeaut_usio.c
+++ b/drivers/tty/serial/milbeaut_usio.c
@@ -523,7 +523,10 @@ static int mlb_usio_probe(struct platform_device *pdev)
 	}
 	port->membase = devm_ioremap(&pdev->dev, res->start,
 				resource_size(res));
-
+	if (!port->membase) {
+		ret = -ENOMEM;
+		goto failed;
+	}
 	ret = platform_get_irq_byname(pdev, "rx");
 	mlb_usio_irq[index][RX] = ret;
 
diff --git a/drivers/tty/serial/msm_serial.c b/drivers/tty/serial/msm_serial.c
index 0a9c5219df88..9eeabedfb4d0 100644
--- a/drivers/tty/serial/msm_serial.c
+++ b/drivers/tty/serial/msm_serial.c
@@ -1746,6 +1746,12 @@ msm_serial_early_console_setup_dm(struct earlycon_device *device,
 	if (!device->port.membase)
 		return -ENODEV;
 
+	/* Disable DM / single-character modes */
+	msm_write(&device->port, 0, UARTDM_DMEN);
+	msm_write(&device->port, MSM_UART_CR_CMD_RESET_RX, MSM_UART_CR);
+	msm_write(&device->port, MSM_UART_CR_CMD_RESET_TX, MSM_UART_CR);
+	msm_write(&device->port, MSM_UART_CR_TX_ENABLE, MSM_UART_CR);
+
 	device->con->write = msm_serial_early_write_dm;
 	return 0;
 }
diff --git a/drivers/tty/serial/pch_uart.c b/drivers/tty/serial/pch_uart.c
index c7cee5fee603..70676e3247ab 100644
--- a/drivers/tty/serial/pch_uart.c
+++ b/drivers/tty/serial/pch_uart.c
@@ -954,7 +954,7 @@ static unsigned int dma_handle_tx(struct eg20t_port *priv)
 			__func__);
 		return 0;
 	}
-	dma_sync_sg_for_device(port->dev, priv->sg_tx_p, nent, DMA_TO_DEVICE);
+	dma_sync_sg_for_device(port->dev, priv->sg_tx_p, num, DMA_TO_DEVICE);
 	priv->desc_tx = desc;
 	desc->callback = pch_dma_tx_complete;
 	desc->callback_param = priv;
diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c
index ad88a33a504f..6a0a1cce3a89 100644
--- a/drivers/tty/serial/sc16is7xx.c
+++ b/drivers/tty/serial/sc16is7xx.c
@@ -8,7 +8,7 @@
  */
 
 #undef DEFAULT_SYMBOL_NAMESPACE
-#define DEFAULT_SYMBOL_NAMESPACE SERIAL_NXP_SC16IS7XX
+#define DEFAULT_SYMBOL_NAMESPACE "SERIAL_NXP_SC16IS7XX"
 
 #include <linux/bits.h>
 #include <linux/clk.h>
diff --git a/drivers/tty/serial/serial_base_bus.c b/drivers/tty/serial/serial_base_bus.c
index 5d1677f1b651..cb3b127b06b6 100644
--- a/drivers/tty/serial/serial_base_bus.c
+++ b/drivers/tty/serial/serial_base_bus.c
@@ -72,6 +72,7 @@ static int serial_base_device_init(struct uart_port *port,
 	dev->parent = parent_dev;
 	dev->bus = &serial_base_bus_type;
 	dev->release = release;
+	device_set_of_node_from_dev(dev, parent_dev);
 
 	if (!serial_base_initialized) {
 		dev_dbg(port->dev, "uart_add_one_port() called before arch_initcall()?\n");
diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index d94d73e45fb6..440303566b14 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -1353,28 +1353,28 @@ static void uart_sanitize_serial_rs485_delays(struct uart_port *port,
 	if (!port->rs485_supported.delay_rts_before_send) {
 		if (rs485->delay_rts_before_send) {
 			dev_warn_ratelimited(port->dev,
-				"%s (%d): RTS delay before sending not supported\n",
+				"%s (%u): RTS delay before sending not supported\n",
 				port->name, port->line);
 		}
 		rs485->delay_rts_before_send = 0;
 	} else if (rs485->delay_rts_before_send > RS485_MAX_RTS_DELAY) {
 		rs485->delay_rts_before_send = RS485_MAX_RTS_DELAY;
 		dev_warn_ratelimited(port->dev,
-			"%s (%d): RTS delay before sending clamped to %u ms\n",
+			"%s (%u): RTS delay before sending clamped to %u ms\n",
 			port->name, port->line, rs485->delay_rts_before_send);
 	}
 
 	if (!port->rs485_supported.delay_rts_after_send) {
 		if (rs485->delay_rts_after_send) {
 			dev_warn_ratelimited(port->dev,
-				"%s (%d): RTS delay after sending not supported\n",
+				"%s (%u): RTS delay after sending not supported\n",
 				port->name, port->line);
 		}
 		rs485->delay_rts_after_send = 0;
 	} else if (rs485->delay_rts_after_send > RS485_MAX_RTS_DELAY) {
 		rs485->delay_rts_after_send = RS485_MAX_RTS_DELAY;
 		dev_warn_ratelimited(port->dev,
-			"%s (%d): RTS delay after sending clamped to %u ms\n",
+			"%s (%u): RTS delay after sending clamped to %u ms\n",
 			port->name, port->line, rs485->delay_rts_after_send);
 	}
 }
@@ -1404,14 +1404,14 @@ static void uart_sanitize_serial_rs485(struct uart_port *port, struct serial_rs4
 			rs485->flags &= ~SER_RS485_RTS_AFTER_SEND;
 
 			dev_warn_ratelimited(port->dev,
-				"%s (%d): invalid RTS setting, using RTS_ON_SEND instead\n",
+				"%s (%u): invalid RTS setting, using RTS_ON_SEND instead\n",
 				port->name, port->line);
 		} else {
 			rs485->flags |= SER_RS485_RTS_AFTER_SEND;
 			rs485->flags &= ~SER_RS485_RTS_ON_SEND;
 
 			dev_warn_ratelimited(port->dev,
-				"%s (%d): invalid RTS setting, using RTS_AFTER_SEND instead\n",
+				"%s (%u): invalid RTS setting, using RTS_AFTER_SEND instead\n",
 				port->name, port->line);
 		}
 	}
@@ -1850,7 +1850,7 @@ static void uart_wait_until_sent(struct tty_struct *tty, int timeout)
 
 	expire = jiffies + timeout;
 
-	pr_debug("uart_wait_until_sent(%d), jiffies=%lu, expire=%lu...\n",
+	pr_debug("uart_wait_until_sent(%u), jiffies=%lu, expire=%lu...\n",
 		port->line, jiffies, expire);
 
 	/*
@@ -2046,7 +2046,7 @@ static void uart_line_info(struct seq_file *m, struct uart_driver *drv, int i)
 		return;
 
 	mmio = uport->iotype >= UPIO_MEM;
-	seq_printf(m, "%d: uart:%s %s%08llX irq:%d",
+	seq_printf(m, "%u: uart:%s %s%08llX irq:%u",
 			uport->line, uart_type(uport),
 			mmio ? "mmio:0x" : "port:",
 			mmio ? (unsigned long long)uport->mapbase
@@ -2068,18 +2068,18 @@ static void uart_line_info(struct seq_file *m, struct uart_driver *drv, int i)
 		if (pm_state != UART_PM_STATE_ON)
 			uart_change_pm(state, pm_state);
 
-		seq_printf(m, " tx:%d rx:%d",
+		seq_printf(m, " tx:%u rx:%u",
 				uport->icount.tx, uport->icount.rx);
 		if (uport->icount.frame)
-			seq_printf(m, " fe:%d",	uport->icount.frame);
+			seq_printf(m, " fe:%u",	uport->icount.frame);
 		if (uport->icount.parity)
-			seq_printf(m, " pe:%d",	uport->icount.parity);
+			seq_printf(m, " pe:%u",	uport->icount.parity);
 		if (uport->icount.brk)
-			seq_printf(m, " brk:%d", uport->icount.brk);
+			seq_printf(m, " brk:%u", uport->icount.brk);
 		if (uport->icount.overrun)
-			seq_printf(m, " oe:%d", uport->icount.overrun);
+			seq_printf(m, " oe:%u", uport->icount.overrun);
 		if (uport->icount.buf_overrun)
-			seq_printf(m, " bo:%d", uport->icount.buf_overrun);
+			seq_printf(m, " bo:%u", uport->icount.buf_overrun);
 
 #define INFOBIT(bit, str) \
 	if (uport->mctrl & (bit)) \
@@ -2571,7 +2571,7 @@ uart_report_port(struct uart_driver *drv, struct uart_port *port)
 		break;
 	}
 
-	pr_info("%s%s%s at %s (irq = %d, base_baud = %d) is a %s\n",
+	pr_info("%s%s%s at %s (irq = %u, base_baud = %u) is a %s\n",
 	       port->dev ? dev_name(port->dev) : "",
 	       port->dev ? ": " : "",
 	       port->name,
@@ -2579,7 +2579,7 @@ uart_report_port(struct uart_driver *drv, struct uart_port *port)
 
 	/* The magic multiplier feature is a bit obscure, so report it too.  */
 	if (port->flags & UPF_MAGIC_MULTIPLIER)
-		pr_info("%s%s%s extra baud rates supported: %d, %d",
+		pr_info("%s%s%s extra baud rates supported: %u, %u",
 			port->dev ? dev_name(port->dev) : "",
 			port->dev ? ": " : "",
 			port->name,
@@ -2978,7 +2978,7 @@ static ssize_t close_delay_show(struct device *dev,
 	struct tty_port *port = dev_get_drvdata(dev);
 
 	uart_get_info(port, &tmp);
-	return sprintf(buf, "%d\n", tmp.close_delay);
+	return sprintf(buf, "%u\n", tmp.close_delay);
 }
 
 static ssize_t closing_wait_show(struct device *dev,
@@ -2988,7 +2988,7 @@ static ssize_t closing_wait_show(struct device *dev,
 	struct tty_port *port = dev_get_drvdata(dev);
 
 	uart_get_info(port, &tmp);
-	return sprintf(buf, "%d\n", tmp.closing_wait);
+	return sprintf(buf, "%u\n", tmp.closing_wait);
 }
 
 static ssize_t custom_divisor_show(struct device *dev,
@@ -3008,7 +3008,7 @@ static ssize_t io_type_show(struct device *dev,
 	struct tty_port *port = dev_get_drvdata(dev);
 
 	uart_get_info(port, &tmp);
-	return sprintf(buf, "%d\n", tmp.io_type);
+	return sprintf(buf, "%u\n", tmp.io_type);
 }
 
 static ssize_t iomem_base_show(struct device *dev,
@@ -3028,7 +3028,7 @@ static ssize_t iomem_reg_shift_show(struct device *dev,
 	struct tty_port *port = dev_get_drvdata(dev);
 
 	uart_get_info(port, &tmp);
-	return sprintf(buf, "%d\n", tmp.iomem_reg_shift);
+	return sprintf(buf, "%u\n", tmp.iomem_reg_shift);
 }
 
 static ssize_t console_show(struct device *dev,
@@ -3168,7 +3168,7 @@ static int serial_core_add_one_port(struct uart_driver *drv, struct uart_port *u
 	state->pm_state = UART_PM_STATE_UNDEFINED;
 	uart_port_set_cons(uport, drv->cons);
 	uport->minor = drv->tty_driver->minor_start + uport->line;
-	uport->name = kasprintf(GFP_KERNEL, "%s%d", drv->dev_name,
+	uport->name = kasprintf(GFP_KERNEL, "%s%u", drv->dev_name,
 				drv->tty_driver->name_base + uport->line);
 	if (!uport->name) {
 		ret = -ENOMEM;
@@ -3211,7 +3211,7 @@ static int serial_core_add_one_port(struct uart_driver *drv, struct uart_port *u
 		device_set_wakeup_capable(tty_dev, 1);
 	} else {
 		uport->flags |= UPF_DEAD;
-		dev_err(uport->dev, "Cannot register tty device on line %d\n",
+		dev_err(uport->dev, "Cannot register tty device on line %u\n",
 		       uport->line);
 	}
 
diff --git a/drivers/tty/serial/serial_mctrl_gpio.c b/drivers/tty/serial/serial_mctrl_gpio.c
index 8855688a5b6c..ca55bcc0b611 100644
--- a/drivers/tty/serial/serial_mctrl_gpio.c
+++ b/drivers/tty/serial/serial_mctrl_gpio.c
@@ -322,11 +322,7 @@ void mctrl_gpio_enable_ms(struct mctrl_gpios *gpios)
 }
 EXPORT_SYMBOL_GPL(mctrl_gpio_enable_ms);
 
-/**
- * mctrl_gpio_disable_ms - disable irqs and handling of changes to the ms lines
- * @gpios: gpios to disable
- */
-void mctrl_gpio_disable_ms(struct mctrl_gpios *gpios)
+static void mctrl_gpio_disable_ms(struct mctrl_gpios *gpios, bool sync)
 {
 	enum mctrl_gpio_idx i;
 
@@ -342,10 +338,34 @@ void mctrl_gpio_disable_ms(struct mctrl_gpios *gpios)
 		if (!gpios->irq[i])
 			continue;
 
-		disable_irq(gpios->irq[i]);
+		if (sync)
+			disable_irq(gpios->irq[i]);
+		else
+			disable_irq_nosync(gpios->irq[i]);
 	}
 }
-EXPORT_SYMBOL_GPL(mctrl_gpio_disable_ms);
+
+/**
+ * mctrl_gpio_disable_ms_sync - disable irqs and handling of changes to the ms
+ * lines, and wait for any pending IRQ to be processed
+ * @gpios: gpios to disable
+ */
+void mctrl_gpio_disable_ms_sync(struct mctrl_gpios *gpios)
+{
+	mctrl_gpio_disable_ms(gpios, true);
+}
+EXPORT_SYMBOL_GPL(mctrl_gpio_disable_ms_sync);
+
+/**
+ * mctrl_gpio_disable_ms_no_sync - disable irqs and handling of changes to the
+ * ms lines, and return immediately
+ * @gpios: gpios to disable
+ */
+void mctrl_gpio_disable_ms_no_sync(struct mctrl_gpios *gpios)
+{
+	mctrl_gpio_disable_ms(gpios, false);
+}
+EXPORT_SYMBOL_GPL(mctrl_gpio_disable_ms_no_sync);
 
 void mctrl_gpio_enable_irq_wake(struct mctrl_gpios *gpios)
 {
diff --git a/drivers/tty/serial/serial_mctrl_gpio.h b/drivers/tty/serial/serial_mctrl_gpio.h
index fc76910fb105..79e97838ebe5 100644
--- a/drivers/tty/serial/serial_mctrl_gpio.h
+++ b/drivers/tty/serial/serial_mctrl_gpio.h
@@ -87,9 +87,16 @@ void mctrl_gpio_free(struct device *dev, struct mctrl_gpios *gpios);
 void mctrl_gpio_enable_ms(struct mctrl_gpios *gpios);
 
 /*
- * Disable gpio interrupts to report status line changes.
+ * Disable gpio interrupts to report status line changes, and block until
+ * any corresponding IRQ is processed
  */
-void mctrl_gpio_disable_ms(struct mctrl_gpios *gpios);
+void mctrl_gpio_disable_ms_sync(struct mctrl_gpios *gpios);
+
+/*
+ * Disable gpio interrupts to report status line changes, and return
+ * immediately
+ */
+void mctrl_gpio_disable_ms_no_sync(struct mctrl_gpios *gpios);
 
 /*
  * Enable gpio wakeup interrupts to enable wake up source.
@@ -148,7 +155,11 @@ static inline void mctrl_gpio_enable_ms(struct mctrl_gpios *gpios)
 {
 }
 
-static inline void mctrl_gpio_disable_ms(struct mctrl_gpios *gpios)
+static inline void mctrl_gpio_disable_ms_sync(struct mctrl_gpios *gpios)
+{
+}
+
+static inline void mctrl_gpio_disable_ms_no_sync(struct mctrl_gpios *gpios)
 {
 }
 
diff --git a/drivers/tty/serial/serial_port.c b/drivers/tty/serial/serial_port.c
index d35f1d24156c..85285c56fabf 100644
--- a/drivers/tty/serial/serial_port.c
+++ b/drivers/tty/serial/serial_port.c
@@ -173,6 +173,7 @@ EXPORT_SYMBOL(uart_remove_one_port);
  * The caller is responsible to initialize the following fields of the @port
  *   ->dev (must be valid)
  *   ->flags
+ *   ->iobase
  *   ->mapbase
  *   ->mapsize
  *   ->regshift (if @use_defaults is false)
@@ -214,7 +215,7 @@ static int __uart_read_properties(struct uart_port *port, bool use_defaults)
 	/* Read the registers I/O access type (default: MMIO 8-bit) */
 	ret = device_property_read_u32(dev, "reg-io-width", &value);
 	if (ret) {
-		port->iotype = UPIO_MEM;
+		port->iotype = port->iobase ? UPIO_PORT : UPIO_MEM;
 	} else {
 		switch (value) {
 		case 1:
@@ -227,11 +228,11 @@ static int __uart_read_properties(struct uart_port *port, bool use_defaults)
 			port->iotype = device_is_big_endian(dev) ? UPIO_MEM32BE : UPIO_MEM32;
 			break;
 		default:
+			port->iotype = UPIO_UNKNOWN;
 			if (!use_defaults) {
 				dev_err(dev, "Unsupported reg-io-width (%u)\n", value);
 				return -EINVAL;
 			}
-			port->iotype = UPIO_UNKNOWN;
 			break;
 		}
 	}
diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c
index bdf17eafd359..53236e3e4fa4 100644
--- a/drivers/tty/serial/sh-sci.c
+++ b/drivers/tty/serial/sh-sci.c
@@ -104,6 +104,20 @@ struct plat_sci_reg {
 	u8 offset, size;
 };
 
+struct sci_suspend_regs {
+	u16 scdl;
+	u16 sccks;
+	u16 scsmr;
+	u16 scscr;
+	u16 scfcr;
+	u16 scsptr;
+	u16 hssrr;
+	u16 scpcr;
+	u16 scpdr;
+	u8 scbrr;
+	u8 semr;
+};
+
 struct sci_port_params {
 	const struct plat_sci_reg regs[SCIx_NR_REGS];
 	unsigned int fifosize;
@@ -134,6 +148,8 @@ struct sci_port {
 	struct dma_chan			*chan_tx;
 	struct dma_chan			*chan_rx;
 
+	struct reset_control		*rstc;
+
 #ifdef CONFIG_SERIAL_SH_SCI_DMA
 	struct dma_chan			*chan_tx_saved;
 	struct dma_chan			*chan_rx_saved;
@@ -153,6 +169,7 @@ struct sci_port {
 	int				rx_trigger;
 	struct timer_list		rx_fifo_timer;
 	int				rx_fifo_timeout;
+	struct sci_suspend_regs		suspend_regs;
 	u16				hscif_tot;
 
 	bool has_rtscts;
@@ -165,6 +182,8 @@ struct sci_port {
 static struct sci_port sci_ports[SCI_NPORTS];
 static unsigned long sci_ports_in_use;
 static struct uart_driver sci_uart_driver;
+static bool sci_uart_earlycon;
+static bool sci_uart_earlycon_dev_probing;
 
 static inline struct sci_port *
 to_sci_port(struct uart_port *uart)
@@ -2296,7 +2315,7 @@ static void sci_shutdown(struct uart_port *port)
 	dev_dbg(port->dev, "%s(%d)\n", __func__, port->line);
 
 	s->autorts = false;
-	mctrl_gpio_disable_ms(to_sci_port(port)->gpios);
+	mctrl_gpio_disable_ms_sync(to_sci_port(port)->gpios);
 
 	uart_port_lock_irqsave(port, &flags);
 	sci_stop_rx(port);
@@ -3056,10 +3075,6 @@ static int sci_init_single(struct platform_device *dev,
 		ret = sci_init_clocks(sci_port, &dev->dev);
 		if (ret < 0)
 			return ret;
-
-		port->dev = &dev->dev;
-
-		pm_runtime_enable(&dev->dev);
 	}
 
 	port->type		= p->type;
@@ -3086,11 +3101,6 @@ static int sci_init_single(struct platform_device *dev,
 	return 0;
 }
 
-static void sci_cleanup_single(struct sci_port *port)
-{
-	pm_runtime_disable(port->port.dev);
-}
-
 #if defined(CONFIG_SERIAL_SH_SCI_CONSOLE) || \
     defined(CONFIG_SERIAL_SH_SCI_EARLYCON)
 static void serial_console_putchar(struct uart_port *port, unsigned char ch)
@@ -3260,8 +3270,6 @@ static void sci_remove(struct platform_device *dev)
 	sci_ports_in_use &= ~BIT(port->port.line);
 	uart_remove_one_port(&sci_uart_driver, &port->port);
 
-	sci_cleanup_single(port);
-
 	if (port->port.fifosize > 1)
 		device_remove_file(&dev->dev, &dev_attr_rx_fifo_trigger);
 	if (type == PORT_SCIFA || type == PORT_SCIFB || type == PORT_HSCIF)
@@ -3383,6 +3391,7 @@ static struct plat_sci_port *sci_parse_dt(struct platform_device *pdev,
 	}
 
 	sp = &sci_ports[id];
+	sp->rstc = rstc;
 	*dev_id = id;
 
 	p->type = SCI_OF_TYPE(data);
@@ -3396,7 +3405,8 @@ static struct plat_sci_port *sci_parse_dt(struct platform_device *pdev,
 static int sci_probe_single(struct platform_device *dev,
 				      unsigned int index,
 				      struct plat_sci_port *p,
-				      struct sci_port *sciport)
+				      struct sci_port *sciport,
+				      struct resource *sci_res)
 {
 	int ret;
 
@@ -3425,6 +3435,11 @@ static int sci_probe_single(struct platform_device *dev,
 	if (ret)
 		return ret;
 
+	sciport->port.dev = &dev->dev;
+	ret = devm_pm_runtime_enable(&dev->dev);
+	if (ret)
+		return ret;
+
 	sciport->gpios = mctrl_gpio_init(&sciport->port, 0);
 	if (IS_ERR(sciport->gpios))
 		return PTR_ERR(sciport->gpios);
@@ -3438,18 +3453,37 @@ static int sci_probe_single(struct platform_device *dev,
 		sciport->port.flags |= UPF_HARD_FLOW;
 	}
 
-	ret = uart_add_one_port(&sci_uart_driver, &sciport->port);
-	if (ret) {
-		sci_cleanup_single(sciport);
-		return ret;
+	if (sci_uart_earlycon && sci_ports[0].port.mapbase == sci_res->start) {
+		/*
+		 * In case:
+		 * - this is the earlycon port (mapped on index 0 in sci_ports[]) and
+		 * - it now maps to an alias other than zero and
+		 * - the earlycon is still alive (e.g., "earlycon keep_bootcon" is
+		 *   available in bootargs)
+		 *
+		 * we need to avoid disabling clocks and PM domains through the runtime
+		 * PM APIs called in __device_attach(). For this, increment the runtime
+		 * PM reference counter (the clocks and PM domains were already enabled
+		 * by the bootloader). Otherwise the earlycon may access the HW when it
+		 * has no clocks enabled leading to failures (infinite loop in
+		 * sci_poll_put_char()).
+		 */
+		pm_runtime_get_noresume(&dev->dev);
+
+		/*
+		 * Skip cleanup the sci_port[0] in early_console_exit(), this
+		 * port is the same as the earlycon one.
+		 */
+		sci_uart_earlycon_dev_probing = true;
 	}
 
-	return 0;
+	return uart_add_one_port(&sci_uart_driver, &sciport->port);
 }
 
 static int sci_probe(struct platform_device *dev)
 {
 	struct plat_sci_port *p;
+	struct resource *res;
 	struct sci_port *sp;
 	unsigned int dev_id;
 	int ret;
@@ -3479,9 +3513,29 @@ static int sci_probe(struct platform_device *dev)
 	}
 
 	sp = &sci_ports[dev_id];
+
+	/*
+	 * In case:
+	 * - the probed port alias is zero (as the one used by earlycon), and
+	 * - the earlycon is still active (e.g., "earlycon keep_bootcon" in
+	 *   bootargs)
+	 *
+	 * defer the probe of this serial. This is a debug scenario and the user
+	 * must be aware of it.
+	 *
+	 * Except when the probed port is the same as the earlycon port.
+	 */
+
+	res = platform_get_resource(dev, IORESOURCE_MEM, 0);
+	if (!res)
+		return -ENODEV;
+
+	if (sci_uart_earlycon && sp == &sci_ports[0] && sp->port.mapbase != res->start)
+		return dev_err_probe(&dev->dev, -EBUSY, "sci_port[0] is used by earlycon!\n");
+
 	platform_set_drvdata(dev, sp);
 
-	ret = sci_probe_single(dev, dev_id, p, sp);
+	ret = sci_probe_single(dev, dev_id, p, sp, res);
 	if (ret)
 		return ret;
 
@@ -3510,13 +3564,77 @@ static int sci_probe(struct platform_device *dev)
 	return 0;
 }
 
+static void sci_console_save(struct sci_port *s)
+{
+	struct sci_suspend_regs *regs = &s->suspend_regs;
+	struct uart_port *port = &s->port;
+
+	if (sci_getreg(port, SCDL)->size)
+		regs->scdl = sci_serial_in(port, SCDL);
+	if (sci_getreg(port, SCCKS)->size)
+		regs->sccks = sci_serial_in(port, SCCKS);
+	if (sci_getreg(port, SCSMR)->size)
+		regs->scsmr = sci_serial_in(port, SCSMR);
+	if (sci_getreg(port, SCSCR)->size)
+		regs->scscr = sci_serial_in(port, SCSCR);
+	if (sci_getreg(port, SCFCR)->size)
+		regs->scfcr = sci_serial_in(port, SCFCR);
+	if (sci_getreg(port, SCSPTR)->size)
+		regs->scsptr = sci_serial_in(port, SCSPTR);
+	if (sci_getreg(port, SCBRR)->size)
+		regs->scbrr = sci_serial_in(port, SCBRR);
+	if (sci_getreg(port, HSSRR)->size)
+		regs->hssrr = sci_serial_in(port, HSSRR);
+	if (sci_getreg(port, SCPCR)->size)
+		regs->scpcr = sci_serial_in(port, SCPCR);
+	if (sci_getreg(port, SCPDR)->size)
+		regs->scpdr = sci_serial_in(port, SCPDR);
+	if (sci_getreg(port, SEMR)->size)
+		regs->semr = sci_serial_in(port, SEMR);
+}
+
+static void sci_console_restore(struct sci_port *s)
+{
+	struct sci_suspend_regs *regs = &s->suspend_regs;
+	struct uart_port *port = &s->port;
+
+	if (sci_getreg(port, SCDL)->size)
+		sci_serial_out(port, SCDL, regs->scdl);
+	if (sci_getreg(port, SCCKS)->size)
+		sci_serial_out(port, SCCKS, regs->sccks);
+	if (sci_getreg(port, SCSMR)->size)
+		sci_serial_out(port, SCSMR, regs->scsmr);
+	if (sci_getreg(port, SCSCR)->size)
+		sci_serial_out(port, SCSCR, regs->scscr);
+	if (sci_getreg(port, SCFCR)->size)
+		sci_serial_out(port, SCFCR, regs->scfcr);
+	if (sci_getreg(port, SCSPTR)->size)
+		sci_serial_out(port, SCSPTR, regs->scsptr);
+	if (sci_getreg(port, SCBRR)->size)
+		sci_serial_out(port, SCBRR, regs->scbrr);
+	if (sci_getreg(port, HSSRR)->size)
+		sci_serial_out(port, HSSRR, regs->hssrr);
+	if (sci_getreg(port, SCPCR)->size)
+		sci_serial_out(port, SCPCR, regs->scpcr);
+	if (sci_getreg(port, SCPDR)->size)
+		sci_serial_out(port, SCPDR, regs->scpdr);
+	if (sci_getreg(port, SEMR)->size)
+		sci_serial_out(port, SEMR, regs->semr);
+}
+
 static __maybe_unused int sci_suspend(struct device *dev)
 {
 	struct sci_port *sport = dev_get_drvdata(dev);
 
-	if (sport)
+	if (sport) {
 		uart_suspend_port(&sci_uart_driver, &sport->port);
 
+		if (!console_suspend_enabled && uart_console(&sport->port))
+			sci_console_save(sport);
+		else
+			return reset_control_assert(sport->rstc);
+	}
+
 	return 0;
 }
 
@@ -3524,8 +3642,18 @@ static __maybe_unused int sci_resume(struct device *dev)
 {
 	struct sci_port *sport = dev_get_drvdata(dev);
 
-	if (sport)
+	if (sport) {
+		if (!console_suspend_enabled && uart_console(&sport->port)) {
+			sci_console_restore(sport);
+		} else {
+			int ret = reset_control_deassert(sport->rstc);
+
+			if (ret)
+				return ret;
+		}
+
 		uart_resume_port(&sci_uart_driver, &sport->port);
+	}
 
 	return 0;
 }
@@ -3562,7 +3690,23 @@ sh_early_platform_init_buffer("earlyprintk", &sci_driver,
 			   early_serial_buf, ARRAY_SIZE(early_serial_buf));
 #endif
 #ifdef CONFIG_SERIAL_SH_SCI_EARLYCON
-static struct plat_sci_port port_cfg __initdata;
+static struct plat_sci_port port_cfg;
+
+static int early_console_exit(struct console *co)
+{
+	struct sci_port *sci_port = &sci_ports[0];
+
+	/*
+	 * Clean the slot used by earlycon. A new SCI device might
+	 * map to this slot.
+	 */
+	if (!sci_uart_earlycon_dev_probing) {
+		memset(sci_port, 0, sizeof(*sci_port));
+		sci_uart_earlycon = false;
+	}
+
+	return 0;
+}
 
 static int __init early_console_setup(struct earlycon_device *device,
 				      int type)
@@ -3575,11 +3719,14 @@ static int __init early_console_setup(struct earlycon_device *device,
 	port_cfg.type = type;
 	sci_ports[0].cfg = &port_cfg;
 	sci_ports[0].params = sci_probe_regmap(&port_cfg);
+	sci_uart_earlycon = true;
 	port_cfg.scscr = sci_serial_in(&sci_ports[0].port, SCSCR);
 	sci_serial_out(&sci_ports[0].port, SCSCR,
 		       SCSCR_RE | SCSCR_TE | port_cfg.scscr);
 
 	device->con->write = serial_console_write;
+	device->con->exit = early_console_exit;
+
 	return 0;
 }
 static int __init sci_early_console_setup(struct earlycon_device *device,
diff --git a/drivers/tty/serial/sifive.c b/drivers/tty/serial/sifive.c
index cbfce65c9d22..7fbb170cf0f4 100644
--- a/drivers/tty/serial/sifive.c
+++ b/drivers/tty/serial/sifive.c
@@ -563,8 +563,11 @@ static void sifive_serial_break_ctl(struct uart_port *port, int break_state)
 static int sifive_serial_startup(struct uart_port *port)
 {
 	struct sifive_serial_port *ssp = port_to_sifive_serial_port(port);
+	unsigned long flags;
 
+	uart_port_lock_irqsave(&ssp->port, &flags);
 	__ssp_enable_rxwm(ssp);
+	uart_port_unlock_irqrestore(&ssp->port, flags);
 
 	return 0;
 }
@@ -572,9 +575,12 @@ static int sifive_serial_startup(struct uart_port *port)
 static void sifive_serial_shutdown(struct uart_port *port)
 {
 	struct sifive_serial_port *ssp = port_to_sifive_serial_port(port);
+	unsigned long flags;
 
+	uart_port_lock_irqsave(&ssp->port, &flags);
 	__ssp_disable_rxwm(ssp);
 	__ssp_disable_txwm(ssp);
+	uart_port_unlock_irqrestore(&ssp->port, flags);
 }
 
 /**
diff --git a/drivers/tty/serial/stm32-usart.c b/drivers/tty/serial/stm32-usart.c
index f5199fdecff2..e685cace5c85 100644
--- a/drivers/tty/serial/stm32-usart.c
+++ b/drivers/tty/serial/stm32-usart.c
@@ -944,7 +944,7 @@ static void stm32_usart_enable_ms(struct uart_port *port)
 
 static void stm32_usart_disable_ms(struct uart_port *port)
 {
-	mctrl_gpio_disable_ms(to_stm32_port(port)->gpios);
+	mctrl_gpio_disable_ms_sync(to_stm32_port(port)->gpios);
 }
 
 /* Transmit stop */
@@ -965,10 +965,8 @@ static void stm32_usart_start_tx(struct uart_port *port)
 {
 	struct tty_port *tport = &port->state->port;
 
-	if (kfifo_is_empty(&tport->xmit_fifo) && !port->x_char) {
-		stm32_usart_rs485_rts_disable(port);
+	if (kfifo_is_empty(&tport->xmit_fifo) && !port->x_char)
 		return;
-	}
 
 	stm32_usart_rs485_rts_enable(port);
 
diff --git a/drivers/tty/serial/uartlite.c b/drivers/tty/serial/uartlite.c
index 68357ac8ffe3..71890f3244a0 100644
--- a/drivers/tty/serial/uartlite.c
+++ b/drivers/tty/serial/uartlite.c
@@ -880,16 +880,6 @@ of_err:
 	pm_runtime_set_active(&pdev->dev);
 	pm_runtime_enable(&pdev->dev);
 
-	if (!ulite_uart_driver.state) {
-		dev_dbg(&pdev->dev, "uartlite: calling uart_register_driver()\n");
-		ret = uart_register_driver(&ulite_uart_driver);
-		if (ret < 0) {
-			dev_err(&pdev->dev, "Failed to register driver\n");
-			clk_disable_unprepare(pdata->clk);
-			return ret;
-		}
-	}
-
 	ret = ulite_assign(&pdev->dev, id, res->start, irq, pdata);
 
 	pm_runtime_mark_last_busy(&pdev->dev);
@@ -929,16 +919,25 @@ static struct platform_driver ulite_platform_driver = {
 
 static int __init ulite_init(void)
 {
+	int ret;
+
+	pr_debug("uartlite: calling uart_register_driver()\n");
+	ret = uart_register_driver(&ulite_uart_driver);
+	if (ret)
+		return ret;
 
 	pr_debug("uartlite: calling platform_driver_register()\n");
-	return platform_driver_register(&ulite_platform_driver);
+	ret = platform_driver_register(&ulite_platform_driver);
+	if (ret)
+		uart_unregister_driver(&ulite_uart_driver);
+
+	return ret;
 }
 
 static void __exit ulite_exit(void)
 {
 	platform_driver_unregister(&ulite_platform_driver);
-	if (ulite_uart_driver.state)
-		uart_unregister_driver(&ulite_uart_driver);
+	uart_unregister_driver(&ulite_uart_driver);
 }
 
 module_init(ulite_init);
diff --git a/drivers/tty/serial/xilinx_uartps.c b/drivers/tty/serial/xilinx_uartps.c
index 777392914819..1d636578c1ef 100644
--- a/drivers/tty/serial/xilinx_uartps.c
+++ b/drivers/tty/serial/xilinx_uartps.c
@@ -287,7 +287,7 @@ static void cdns_uart_handle_rx(void *dev_id, unsigned int isrstatus)
 				continue;
 		}
 
-		if (uart_handle_sysrq_char(port, data))
+		if (uart_prepare_sysrq_char(port, data))
 			continue;
 
 		if (is_rxbs_support) {
@@ -495,7 +495,7 @@ static irqreturn_t cdns_uart_isr(int irq, void *dev_id)
 	    !(readl(port->membase + CDNS_UART_CR) & CDNS_UART_CR_RX_DIS))
 		cdns_uart_handle_rx(dev_id, isrstatus);
 
-	uart_port_unlock(port);
+	uart_unlock_and_check_sysrq(port);
 	return IRQ_HANDLED;
 }
 
@@ -1380,9 +1380,7 @@ static void cdns_uart_console_write(struct console *co, const char *s,
 	unsigned int imr, ctrl;
 	int locked = 1;
 
-	if (port->sysrq)
-		locked = 0;
-	else if (oops_in_progress)
+	if (oops_in_progress)
 		locked = uart_port_trylock_irqsave(port, &flags);
 	else
 		uart_port_lock_irqsave(port, &flags);
diff --git a/drivers/tty/vt/selection.c b/drivers/tty/vt/selection.c
index 564341f1a74f..791e2f1f7c0b 100644
--- a/drivers/tty/vt/selection.c
+++ b/drivers/tty/vt/selection.c
@@ -192,6 +192,19 @@ int set_selection_user(const struct tiocl_selection __user *sel,
 	if (copy_from_user(&v, sel, sizeof(*sel)))
 		return -EFAULT;
 
+	/*
+	 * TIOCL_SELCLEAR and TIOCL_SELPOINTER are OK to use without
+	 * CAP_SYS_ADMIN as they do not modify the selection.
+	 */
+	switch (v.sel_mode) {
+	case TIOCL_SELCLEAR:
+	case TIOCL_SELPOINTER:
+		break;
+	default:
+		if (!capable(CAP_SYS_ADMIN))
+			return -EPERM;
+	}
+
 	return set_selection_kernel(&v, tty);
 }
 
diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c
index 96842ce817af..5b09ce71345b 100644
--- a/drivers/tty/vt/vt.c
+++ b/drivers/tty/vt/vt.c
@@ -3345,8 +3345,6 @@ int tioclinux(struct tty_struct *tty, unsigned long arg)
 
 	switch (type) {
 	case TIOCL_SETSEL:
-		if (!capable(CAP_SYS_ADMIN))
-			return -EPERM;
 		return set_selection_user(param, tty);
 	case TIOCL_PASTESEL:
 		if (!capable(CAP_SYS_ADMIN))
@@ -4568,6 +4566,7 @@ void do_unblank_screen(int leaving_gfx)
 	set_palette(vc);
 	set_cursor(vc);
 	vt_event_post(VT_EVENT_UNBLANK, vc->vc_num, vc->vc_num);
+	notify_update(vc);
 }
 EXPORT_SYMBOL(do_unblank_screen);
 
diff --git a/drivers/tty/vt/vt_ioctl.c b/drivers/tty/vt/vt_ioctl.c
index 4b91072f3a4e..1f2bdd2e1cc5 100644
--- a/drivers/tty/vt/vt_ioctl.c
+++ b/drivers/tty/vt/vt_ioctl.c
@@ -1103,8 +1103,6 @@ long vt_compat_ioctl(struct tty_struct *tty,
 	case VT_WAITACTIVE:
 	case VT_RELDISP:
 	case VT_DISALLOCATE:
-	case VT_RESIZE:
-	case VT_RESIZEX:
 		return vt_ioctl(tty, cmd, arg);
 
 	/*
diff --git a/drivers/ufs/core/ufs-mcq.c b/drivers/ufs/core/ufs-mcq.c
index dba935c712d6..420e943bb73a 100644
--- a/drivers/ufs/core/ufs-mcq.c
+++ b/drivers/ufs/core/ufs-mcq.c
@@ -670,16 +670,8 @@ int ufshcd_mcq_abort(struct scsi_cmnd *cmd)
 	int tag = scsi_cmd_to_rq(cmd)->tag;
 	struct ufshcd_lrb *lrbp = &hba->lrb[tag];
 	struct ufs_hw_queue *hwq;
-	unsigned long flags;
 	int err;
 
-	if (!ufshcd_cmd_inflight(lrbp->cmd)) {
-		dev_err(hba->dev,
-			"%s: skip abort. cmd at tag %d already completed.\n",
-			__func__, tag);
-		return FAILED;
-	}
-
 	/* Skip task abort in case previous aborts failed and report failure */
 	if (lrbp->req_abort_skip) {
 		dev_err(hba->dev, "%s: skip abort. tag %d failed earlier\n",
@@ -688,6 +680,11 @@ int ufshcd_mcq_abort(struct scsi_cmnd *cmd)
 	}
 
 	hwq = ufshcd_mcq_req_to_hwq(hba, scsi_cmd_to_rq(cmd));
+	if (!hwq) {
+		dev_err(hba->dev, "%s: skip abort. cmd at tag %d already completed.\n",
+			__func__, tag);
+		return FAILED;
+	}
 
 	if (ufshcd_mcq_sqe_search(hba, hwq, tag)) {
 		/*
@@ -711,10 +708,5 @@ int ufshcd_mcq_abort(struct scsi_cmnd *cmd)
 		return FAILED;
 	}
 
-	spin_lock_irqsave(&hwq->cq_lock, flags);
-	if (ufshcd_cmd_inflight(lrbp->cmd))
-		ufshcd_release_scsi_cmd(hba, lrbp);
-	spin_unlock_irqrestore(&hwq->cq_lock, flags);
-
 	return SUCCESS;
 }
diff --git a/drivers/ufs/core/ufs-sysfs.c b/drivers/ufs/core/ufs-sysfs.c
index 796e37a1d859..f8397ef3cf8d 100644
--- a/drivers/ufs/core/ufs-sysfs.c
+++ b/drivers/ufs/core/ufs-sysfs.c
@@ -1608,7 +1608,7 @@ UFS_UNIT_DESC_PARAM(logical_block_size, _LOGICAL_BLK_SIZE, 1);
 UFS_UNIT_DESC_PARAM(logical_block_count, _LOGICAL_BLK_COUNT, 8);
 UFS_UNIT_DESC_PARAM(erase_block_size, _ERASE_BLK_SIZE, 4);
 UFS_UNIT_DESC_PARAM(provisioning_type, _PROVISIONING_TYPE, 1);
-UFS_UNIT_DESC_PARAM(physical_memory_resourse_count, _PHY_MEM_RSRC_CNT, 8);
+UFS_UNIT_DESC_PARAM(physical_memory_resource_count, _PHY_MEM_RSRC_CNT, 8);
 UFS_UNIT_DESC_PARAM(context_capabilities, _CTX_CAPABILITIES, 2);
 UFS_UNIT_DESC_PARAM(large_unit_granularity, _LARGE_UNIT_SIZE_M1, 1);
 UFS_UNIT_DESC_PARAM(wb_buf_alloc_units, _WB_BUF_ALLOC_UNITS, 4);
@@ -1625,7 +1625,7 @@ static struct attribute *ufs_sysfs_unit_descriptor[] = {
 	&dev_attr_logical_block_count.attr,
 	&dev_attr_erase_block_size.attr,
 	&dev_attr_provisioning_type.attr,
-	&dev_attr_physical_memory_resourse_count.attr,
+	&dev_attr_physical_memory_resource_count.attr,
 	&dev_attr_context_capabilities.attr,
 	&dev_attr_large_unit_granularity.attr,
 	&dev_attr_wb_buf_alloc_units.attr,
diff --git a/drivers/ufs/core/ufs_bsg.c b/drivers/ufs/core/ufs_bsg.c
index 6c09d97ae006..252186124669 100644
--- a/drivers/ufs/core/ufs_bsg.c
+++ b/drivers/ufs/core/ufs_bsg.c
@@ -194,10 +194,12 @@ out:
 	ufshcd_rpm_put_sync(hba);
 	kfree(buff);
 	bsg_reply->result = ret;
-	job->reply_len = !rpmb ? sizeof(struct ufs_bsg_reply) : sizeof(struct ufs_rpmb_reply);
 	/* complete the job here only if no error */
-	if (ret == 0)
+	if (ret == 0) {
+		job->reply_len = rpmb ? sizeof(struct ufs_rpmb_reply) :
+					sizeof(struct ufs_bsg_reply);
 		bsg_job_done(job, ret, bsg_reply->reply_payload_rcv_len);
+	}
 
 	return ret;
 }
@@ -216,6 +218,7 @@ void ufs_bsg_remove(struct ufs_hba *hba)
 		return;
 
 	bsg_remove_queue(hba->bsg_queue);
+	hba->bsg_queue = NULL;
 
 	device_del(bsg_dev);
 	put_device(bsg_dev);
@@ -257,6 +260,7 @@ int ufs_bsg_probe(struct ufs_hba *hba)
 			NULL, 0);
 	if (IS_ERR(q)) {
 		ret = PTR_ERR(q);
+		device_del(bsg_dev);
 		goto out;
 	}
 
diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 6cc9e61cca07..e079cb5d9ec6 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -258,10 +258,15 @@ ufs_get_desired_pm_lvl_for_dev_link_state(enum ufs_dev_pwr_mode dev_state,
 	return UFS_PM_LVL_0;
 }
 
+static bool ufshcd_has_pending_tasks(struct ufs_hba *hba)
+{
+	return hba->outstanding_tasks || hba->active_uic_cmd ||
+	       hba->uic_async_done;
+}
+
 static bool ufshcd_is_ufs_dev_busy(struct ufs_hba *hba)
 {
-	return (hba->clk_gating.active_reqs || hba->outstanding_reqs || hba->outstanding_tasks ||
-		hba->active_uic_cmd || hba->uic_async_done);
+	return scsi_host_busy(hba->host) || ufshcd_has_pending_tasks(hba);
 }
 
 static const struct ufs_dev_quirk ufs_fixups[] = {
@@ -273,6 +278,7 @@ static const struct ufs_dev_quirk ufs_fixups[] = {
 	  .model = UFS_ANY_MODEL,
 	  .quirk = UFS_DEVICE_QUIRK_DELAY_BEFORE_LPM |
 		   UFS_DEVICE_QUIRK_HOST_PA_TACTIVATE |
+		   UFS_DEVICE_QUIRK_PA_HIBER8TIME |
 		   UFS_DEVICE_QUIRK_RECOVERY_FROM_DL_NAC_ERRORS },
 	{ .wmanufacturerid = UFS_VENDOR_SKHYNIX,
 	  .model = UFS_ANY_MODEL,
@@ -634,8 +640,8 @@ static void ufshcd_print_host_state(struct ufs_hba *hba)
 	const struct scsi_device *sdev_ufs = hba->ufs_device_wlun;
 
 	dev_err(hba->dev, "UFS Host state=%d\n", hba->ufshcd_state);
-	dev_err(hba->dev, "outstanding reqs=0x%lx tasks=0x%lx\n",
-		hba->outstanding_reqs, hba->outstanding_tasks);
+	dev_err(hba->dev, "%d outstanding reqs, tasks=0x%lx\n",
+		scsi_host_busy(hba->host), hba->outstanding_tasks);
 	dev_err(hba->dev, "saved_err=0x%x, saved_uic_err=0x%x\n",
 		hba->saved_err, hba->saved_uic_err);
 	dev_err(hba->dev, "Device power mode=%d, UIC link state=%d\n",
@@ -1386,6 +1392,7 @@ static int ufshcd_clock_scaling_prepare(struct ufs_hba *hba, u64 timeout_us)
 	 * make sure that there are no outstanding requests when
 	 * clock scaling is in progress
 	 */
+	mutex_lock(&hba->host->scan_mutex);
 	blk_mq_quiesce_tagset(&hba->host->tag_set);
 	mutex_lock(&hba->wb_mutex);
 	down_write(&hba->clk_scaling_lock);
@@ -1396,6 +1403,7 @@ static int ufshcd_clock_scaling_prepare(struct ufs_hba *hba, u64 timeout_us)
 		up_write(&hba->clk_scaling_lock);
 		mutex_unlock(&hba->wb_mutex);
 		blk_mq_unquiesce_tagset(&hba->host->tag_set);
+		mutex_unlock(&hba->host->scan_mutex);
 		goto out;
 	}
 
@@ -1417,6 +1425,7 @@ static void ufshcd_clock_scaling_unprepare(struct ufs_hba *hba, int err, bool sc
 	mutex_unlock(&hba->wb_mutex);
 
 	blk_mq_unquiesce_tagset(&hba->host->tag_set);
+	mutex_unlock(&hba->host->scan_mutex);
 	ufshcd_release(hba);
 }
 
@@ -1835,19 +1844,16 @@ static void ufshcd_exit_clk_scaling(struct ufs_hba *hba)
 static void ufshcd_ungate_work(struct work_struct *work)
 {
 	int ret;
-	unsigned long flags;
 	struct ufs_hba *hba = container_of(work, struct ufs_hba,
 			clk_gating.ungate_work);
 
 	cancel_delayed_work_sync(&hba->clk_gating.gate_work);
 
-	spin_lock_irqsave(hba->host->host_lock, flags);
-	if (hba->clk_gating.state == CLKS_ON) {
-		spin_unlock_irqrestore(hba->host->host_lock, flags);
-		return;
+	scoped_guard(spinlock_irqsave, &hba->clk_gating.lock) {
+		if (hba->clk_gating.state == CLKS_ON)
+			return;
 	}
 
-	spin_unlock_irqrestore(hba->host->host_lock, flags);
 	ufshcd_hba_vreg_set_hpm(hba);
 	ufshcd_setup_clocks(hba, true);
 
@@ -1882,7 +1888,7 @@ void ufshcd_hold(struct ufs_hba *hba)
 	if (!ufshcd_is_clkgating_allowed(hba) ||
 	    !hba->clk_gating.is_initialized)
 		return;
-	spin_lock_irqsave(hba->host->host_lock, flags);
+	spin_lock_irqsave(&hba->clk_gating.lock, flags);
 	hba->clk_gating.active_reqs++;
 
 start:
@@ -1898,11 +1904,11 @@ start:
 		 */
 		if (ufshcd_can_hibern8_during_gating(hba) &&
 		    ufshcd_is_link_hibern8(hba)) {
-			spin_unlock_irqrestore(hba->host->host_lock, flags);
+			spin_unlock_irqrestore(&hba->clk_gating.lock, flags);
 			flush_result = flush_work(&hba->clk_gating.ungate_work);
 			if (hba->clk_gating.is_suspended && !flush_result)
 				return;
-			spin_lock_irqsave(hba->host->host_lock, flags);
+			spin_lock_irqsave(&hba->clk_gating.lock, flags);
 			goto start;
 		}
 		break;
@@ -1931,17 +1937,17 @@ start:
 		 */
 		fallthrough;
 	case REQ_CLKS_ON:
-		spin_unlock_irqrestore(hba->host->host_lock, flags);
+		spin_unlock_irqrestore(&hba->clk_gating.lock, flags);
 		flush_work(&hba->clk_gating.ungate_work);
 		/* Make sure state is CLKS_ON before returning */
-		spin_lock_irqsave(hba->host->host_lock, flags);
+		spin_lock_irqsave(&hba->clk_gating.lock, flags);
 		goto start;
 	default:
 		dev_err(hba->dev, "%s: clk gating is in invalid state %d\n",
 				__func__, hba->clk_gating.state);
 		break;
 	}
-	spin_unlock_irqrestore(hba->host->host_lock, flags);
+	spin_unlock_irqrestore(&hba->clk_gating.lock, flags);
 }
 EXPORT_SYMBOL_GPL(ufshcd_hold);
 
@@ -1949,28 +1955,32 @@ static void ufshcd_gate_work(struct work_struct *work)
 {
 	struct ufs_hba *hba = container_of(work, struct ufs_hba,
 			clk_gating.gate_work.work);
-	unsigned long flags;
 	int ret;
 
-	spin_lock_irqsave(hba->host->host_lock, flags);
-	/*
-	 * In case you are here to cancel this work the gating state
-	 * would be marked as REQ_CLKS_ON. In this case save time by
-	 * skipping the gating work and exit after changing the clock
-	 * state to CLKS_ON.
-	 */
-	if (hba->clk_gating.is_suspended ||
-		(hba->clk_gating.state != REQ_CLKS_OFF)) {
-		hba->clk_gating.state = CLKS_ON;
-		trace_ufshcd_clk_gating(dev_name(hba->dev),
-					hba->clk_gating.state);
-		goto rel_lock;
-	}
+	scoped_guard(spinlock_irqsave, &hba->clk_gating.lock) {
+		/*
+		 * In case you are here to cancel this work the gating state
+		 * would be marked as REQ_CLKS_ON. In this case save time by
+		 * skipping the gating work and exit after changing the clock
+		 * state to CLKS_ON.
+		 */
+		if (hba->clk_gating.is_suspended ||
+		    hba->clk_gating.state != REQ_CLKS_OFF) {
+			hba->clk_gating.state = CLKS_ON;
+			trace_ufshcd_clk_gating(dev_name(hba->dev),
+						hba->clk_gating.state);
+			return;
+		}
 
-	if (ufshcd_is_ufs_dev_busy(hba) || hba->ufshcd_state != UFSHCD_STATE_OPERATIONAL)
-		goto rel_lock;
+		if (hba->clk_gating.active_reqs)
+			return;
+	}
 
-	spin_unlock_irqrestore(hba->host->host_lock, flags);
+	scoped_guard(spinlock_irqsave, hba->host->host_lock) {
+		if (ufshcd_is_ufs_dev_busy(hba) ||
+		    hba->ufshcd_state != UFSHCD_STATE_OPERATIONAL)
+			return;
+	}
 
 	/* put the link into hibern8 mode before turning off clocks */
 	if (ufshcd_can_hibern8_during_gating(hba)) {
@@ -1981,7 +1991,7 @@ static void ufshcd_gate_work(struct work_struct *work)
 					__func__, ret);
 			trace_ufshcd_clk_gating(dev_name(hba->dev),
 						hba->clk_gating.state);
-			goto out;
+			return;
 		}
 		ufshcd_set_link_hibern8(hba);
 	}
@@ -2001,33 +2011,34 @@ static void ufshcd_gate_work(struct work_struct *work)
 	 * prevent from doing cancel work multiple times when there are
 	 * new requests arriving before the current cancel work is done.
 	 */
-	spin_lock_irqsave(hba->host->host_lock, flags);
+	guard(spinlock_irqsave)(&hba->clk_gating.lock);
 	if (hba->clk_gating.state == REQ_CLKS_OFF) {
 		hba->clk_gating.state = CLKS_OFF;
 		trace_ufshcd_clk_gating(dev_name(hba->dev),
 					hba->clk_gating.state);
 	}
-rel_lock:
-	spin_unlock_irqrestore(hba->host->host_lock, flags);
-out:
-	return;
 }
 
-/* host lock must be held before calling this variant */
 static void __ufshcd_release(struct ufs_hba *hba)
 {
+	lockdep_assert_held(&hba->clk_gating.lock);
+
 	if (!ufshcd_is_clkgating_allowed(hba))
 		return;
 
 	hba->clk_gating.active_reqs--;
 
 	if (hba->clk_gating.active_reqs || hba->clk_gating.is_suspended ||
-	    hba->ufshcd_state != UFSHCD_STATE_OPERATIONAL ||
-	    hba->outstanding_tasks || !hba->clk_gating.is_initialized ||
-	    hba->active_uic_cmd || hba->uic_async_done ||
+	    !hba->clk_gating.is_initialized ||
 	    hba->clk_gating.state == CLKS_OFF)
 		return;
 
+	scoped_guard(spinlock_irqsave, hba->host->host_lock) {
+		if (ufshcd_has_pending_tasks(hba) ||
+		    hba->ufshcd_state != UFSHCD_STATE_OPERATIONAL)
+			return;
+	}
+
 	hba->clk_gating.state = REQ_CLKS_OFF;
 	trace_ufshcd_clk_gating(dev_name(hba->dev), hba->clk_gating.state);
 	queue_delayed_work(hba->clk_gating.clk_gating_workq,
@@ -2037,11 +2048,8 @@ static void __ufshcd_release(struct ufs_hba *hba)
 
 void ufshcd_release(struct ufs_hba *hba)
 {
-	unsigned long flags;
-
-	spin_lock_irqsave(hba->host->host_lock, flags);
+	guard(spinlock_irqsave)(&hba->clk_gating.lock);
 	__ufshcd_release(hba);
-	spin_unlock_irqrestore(hba->host->host_lock, flags);
 }
 EXPORT_SYMBOL_GPL(ufshcd_release);
 
@@ -2056,11 +2064,9 @@ static ssize_t ufshcd_clkgate_delay_show(struct device *dev,
 void ufshcd_clkgate_delay_set(struct device *dev, unsigned long value)
 {
 	struct ufs_hba *hba = dev_get_drvdata(dev);
-	unsigned long flags;
 
-	spin_lock_irqsave(hba->host->host_lock, flags);
+	guard(spinlock_irqsave)(&hba->clk_gating.lock);
 	hba->clk_gating.delay_ms = value;
-	spin_unlock_irqrestore(hba->host->host_lock, flags);
 }
 EXPORT_SYMBOL_GPL(ufshcd_clkgate_delay_set);
 
@@ -2088,7 +2094,6 @@ static ssize_t ufshcd_clkgate_enable_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t count)
 {
 	struct ufs_hba *hba = dev_get_drvdata(dev);
-	unsigned long flags;
 	u32 value;
 
 	if (kstrtou32(buf, 0, &value))
@@ -2096,9 +2101,10 @@ static ssize_t ufshcd_clkgate_enable_store(struct device *dev,
 
 	value = !!value;
 
-	spin_lock_irqsave(hba->host->host_lock, flags);
+	guard(spinlock_irqsave)(&hba->clk_gating.lock);
+
 	if (value == hba->clk_gating.is_enabled)
-		goto out;
+		return count;
 
 	if (value)
 		__ufshcd_release(hba);
@@ -2106,8 +2112,7 @@ static ssize_t ufshcd_clkgate_enable_store(struct device *dev,
 		hba->clk_gating.active_reqs++;
 
 	hba->clk_gating.is_enabled = value;
-out:
-	spin_unlock_irqrestore(hba->host->host_lock, flags);
+
 	return count;
 }
 
@@ -3137,8 +3142,13 @@ ufshcd_dev_cmd_completion(struct ufs_hba *hba, struct ufshcd_lrb *lrbp)
 	case UPIU_TRANSACTION_QUERY_RSP: {
 		u8 response = lrbp->ucd_rsp_ptr->header.response;
 
-		if (response == 0)
+		if (response == 0) {
 			err = ufshcd_copy_query_response(hba, lrbp);
+		} else {
+			err = -EINVAL;
+			dev_err(hba->dev, "%s: unexpected response in Query RSP: %x\n",
+					__func__, response);
+		}
 		break;
 	}
 	case UPIU_TRANSACTION_REJECT_UPIU:
@@ -4327,7 +4337,7 @@ out:
 	hba->uic_async_done = NULL;
 	if (reenable_intr)
 		ufshcd_enable_intr(hba, UIC_COMMAND_COMPL);
-	if (ret) {
+	if (ret && !hba->pm_op_in_progress) {
 		ufshcd_set_link_broken(hba);
 		ufshcd_schedule_eh_work(hba);
 	}
@@ -4335,6 +4345,14 @@ out_unlock:
 	spin_unlock_irqrestore(hba->host->host_lock, flags);
 	mutex_unlock(&hba->uic_cmd_mutex);
 
+	/*
+	 * If the h8 exit fails during the runtime resume process, it becomes
+	 * stuck and cannot be recovered through the error handler.  To fix
+	 * this, use link recovery instead of the error handler.
+	 */
+	if (ret && hba->pm_op_in_progress)
+		ret = ufshcd_link_recovery(hba);
+
 	return ret;
 }
 
@@ -5683,6 +5701,8 @@ static void ufshcd_mcq_compl_pending_transfer(struct ufs_hba *hba,
 			continue;
 
 		hwq = ufshcd_mcq_req_to_hwq(hba, scsi_cmd_to_rq(cmd));
+		if (!hwq)
+			continue;
 
 		if (force_compl) {
 			ufshcd_mcq_compl_all_cqes_lock(hba, hwq);
@@ -6568,9 +6588,14 @@ static void ufshcd_err_handler(struct work_struct *work)
 		up(&hba->host_sem);
 		return;
 	}
-	ufshcd_set_eh_in_progress(hba);
 	spin_unlock_irqrestore(hba->host->host_lock, flags);
+
 	ufshcd_err_handling_prepare(hba);
+
+	spin_lock_irqsave(hba->host->host_lock, flags);
+	ufshcd_set_eh_in_progress(hba);
+	spin_unlock_irqrestore(hba->host->host_lock, flags);
+
 	/* Complete requests that have door-bell cleared by h/w */
 	ufshcd_complete_requests(hba, false);
 	spin_lock_irqsave(hba->host->host_lock, flags);
@@ -7248,8 +7273,6 @@ static int ufshcd_issue_devman_upiu_cmd(struct ufs_hba *hba,
 			err = -EINVAL;
 		}
 	}
-	ufshcd_add_query_upiu_trace(hba, err ? UFS_QUERY_ERR : UFS_QUERY_COMP,
-				    (struct utp_upiu_req *)lrbp->ucd_rsp_ptr);
 
 	return err;
 }
@@ -7728,7 +7751,8 @@ static int ufshcd_host_reset_and_restore(struct ufs_hba *hba)
 	hba->silence_err_logs = false;
 
 	/* scale up clocks to max frequency before full reinitialization */
-	ufshcd_scale_clks(hba, ULONG_MAX, true);
+	if (ufshcd_is_clkscaling_supported(hba))
+		ufshcd_scale_clks(hba, ULONG_MAX, true);
 
 	err = ufshcd_hba_enable(hba);
 
@@ -8267,7 +8291,9 @@ static void ufshcd_rtc_work(struct work_struct *work)
 	hba = container_of(to_delayed_work(work), struct ufs_hba, ufs_rtc_update_work);
 
 	 /* Update RTC only when there are no requests in progress and UFSHCI is operational */
-	if (!ufshcd_is_ufs_dev_busy(hba) && hba->ufshcd_state == UFSHCD_STATE_OPERATIONAL)
+	if (!ufshcd_is_ufs_dev_busy(hba) &&
+	    hba->ufshcd_state == UFSHCD_STATE_OPERATIONAL &&
+	    !hba->clk_gating.active_reqs)
 		ufshcd_update_rtc(hba);
 
 	if (ufshcd_is_ufs_dev_active(hba) && hba->dev_info.rtc_update_period)
@@ -8451,6 +8477,31 @@ out:
 	return ret;
 }
 
+/**
+ * ufshcd_quirk_override_pa_h8time - Ensures proper adjustment of PA_HIBERN8TIME.
+ * @hba: per-adapter instance
+ *
+ * Some UFS devices require specific adjustments to the PA_HIBERN8TIME parameter
+ * to ensure proper hibernation timing. This function retrieves the current
+ * PA_HIBERN8TIME value and increments it by 100us.
+ */
+static void ufshcd_quirk_override_pa_h8time(struct ufs_hba *hba)
+{
+	u32 pa_h8time;
+	int ret;
+
+	ret = ufshcd_dme_get(hba, UIC_ARG_MIB(PA_HIBERN8TIME), &pa_h8time);
+	if (ret) {
+		dev_err(hba->dev, "Failed to get PA_HIBERN8TIME: %d\n", ret);
+		return;
+	}
+
+	/* Increment by 1 to increase hibernation time by 100 µs */
+	ret = ufshcd_dme_set(hba, UIC_ARG_MIB(PA_HIBERN8TIME), pa_h8time + 1);
+	if (ret)
+		dev_err(hba->dev, "Failed updating PA_HIBERN8TIME: %d\n", ret);
+}
+
 static void ufshcd_tune_unipro_params(struct ufs_hba *hba)
 {
 	ufshcd_vops_apply_dev_quirks(hba);
@@ -8461,6 +8512,9 @@ static void ufshcd_tune_unipro_params(struct ufs_hba *hba)
 
 	if (hba->dev_quirks & UFS_DEVICE_QUIRK_HOST_PA_TACTIVATE)
 		ufshcd_quirk_tune_host_pa_tactivate(hba);
+
+	if (hba->dev_quirks & UFS_DEVICE_QUIRK_PA_HIBER8TIME)
+		ufshcd_quirk_override_pa_h8time(hba);
 }
 
 static void ufshcd_clear_dbg_ufs_stats(struct ufs_hba *hba)
@@ -8972,7 +9026,7 @@ static enum scsi_timeout_action ufshcd_eh_timed_out(struct scsi_cmnd *scmd)
 	dev_info(hba->dev, "%s() finished; outstanding_tasks = %#lx.\n",
 		 __func__, hba->outstanding_tasks);
 
-	return hba->outstanding_reqs ? SCSI_EH_RESET_TIMER : SCSI_EH_DONE;
+	return scsi_host_busy(hba->host) ? SCSI_EH_RESET_TIMER : SCSI_EH_DONE;
 }
 
 static const struct attribute_group *ufshcd_driver_groups[] = {
@@ -9186,7 +9240,6 @@ static int ufshcd_setup_clocks(struct ufs_hba *hba, bool on)
 	int ret = 0;
 	struct ufs_clk_info *clki;
 	struct list_head *head = &hba->clk_list_head;
-	unsigned long flags;
 	ktime_t start = ktime_get();
 	bool clk_state_changed = false;
 
@@ -9236,12 +9289,11 @@ out:
 			if (!IS_ERR_OR_NULL(clki->clk) && clki->enabled)
 				clk_disable_unprepare(clki->clk);
 		}
-	} else if (!ret && on) {
-		spin_lock_irqsave(hba->host->host_lock, flags);
-		hba->clk_gating.state = CLKS_ON;
+	} else if (!ret && on && hba->clk_gating.is_initialized) {
+		scoped_guard(spinlock_irqsave, &hba->clk_gating.lock)
+			hba->clk_gating.state = CLKS_ON;
 		trace_ufshcd_clk_gating(dev_name(hba->dev),
 					hba->clk_gating.state);
-		spin_unlock_irqrestore(hba->host->host_lock, flags);
 	}
 
 	if (clk_state_changed)
@@ -10324,16 +10376,6 @@ EXPORT_SYMBOL_GPL(ufshcd_system_thaw);
 #endif /* CONFIG_PM_SLEEP  */
 
 /**
- * ufshcd_dealloc_host - deallocate Host Bus Adapter (HBA)
- * @hba: pointer to Host Bus Adapter (HBA)
- */
-void ufshcd_dealloc_host(struct ufs_hba *hba)
-{
-	scsi_host_put(hba->host);
-}
-EXPORT_SYMBOL_GPL(ufshcd_dealloc_host);
-
-/**
  * ufshcd_set_dma_mask - Set dma mask based on the controller
  *			 addressing capability
  * @hba: per adapter instance
@@ -10352,11 +10394,25 @@ static int ufshcd_set_dma_mask(struct ufs_hba *hba)
 }
 
 /**
+ * ufshcd_devres_release - devres cleanup handler, invoked during release of
+ *			   hba->dev
+ * @host: pointer to SCSI host
+ */
+static void ufshcd_devres_release(void *host)
+{
+	scsi_host_put(host);
+}
+
+/**
  * ufshcd_alloc_host - allocate Host Bus Adapter (HBA)
  * @dev: pointer to device handle
  * @hba_handle: driver private handle
  *
  * Return: 0 on success, non-zero value on failure.
+ *
+ * NOTE: There is no corresponding ufshcd_dealloc_host() because this function
+ * keeps track of its allocations using devres and deallocates everything on
+ * device removal automatically.
  */
 int ufshcd_alloc_host(struct device *dev, struct ufs_hba **hba_handle)
 {
@@ -10378,6 +10434,13 @@ int ufshcd_alloc_host(struct device *dev, struct ufs_hba **hba_handle)
 		err = -ENOMEM;
 		goto out_error;
 	}
+
+	err = devm_add_action_or_reset(dev, ufshcd_devres_release,
+				       host);
+	if (err)
+		return dev_err_probe(dev, err,
+				     "failed to add ufshcd dealloc action\n");
+
 	host->nr_maps = HCTX_TYPE_POLL + 1;
 	hba = shost_priv(host);
 	hba->host = host;
@@ -10439,6 +10502,27 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
 	hba->irq = irq;
 	hba->vps = &ufs_hba_vps;
 
+	/*
+	 * Initialize clk_gating.lock early since it is being used in
+	 * ufshcd_setup_clocks()
+	 */
+	spin_lock_init(&hba->clk_gating.lock);
+
+	/*
+	 * Set the default power management level for runtime and system PM.
+	 * Host controller drivers can override them in their
+	 * 'ufs_hba_variant_ops::init' callback.
+	 *
+	 * Default power saving mode is to keep UFS link in Hibern8 state
+	 * and UFS device in sleep state.
+	 */
+	hba->rpm_lvl = ufs_get_desired_pm_lvl_for_dev_link_state(
+						UFS_SLEEP_PWR_MODE,
+						UIC_LINK_HIBERN8_STATE);
+	hba->spm_lvl = ufs_get_desired_pm_lvl_for_dev_link_state(
+						UFS_SLEEP_PWR_MODE,
+						UIC_LINK_HIBERN8_STATE);
+
 	err = ufshcd_hba_init(hba);
 	if (err)
 		goto out_error;
@@ -10588,21 +10672,6 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
 		goto free_tmf_queue;
 	}
 
-	/*
-	 * Set the default power management level for runtime and system PM if
-	 * not set by the host controller drivers.
-	 * Default power saving mode is to keep UFS link in Hibern8 state
-	 * and UFS device in sleep state.
-	 */
-	if (!hba->rpm_lvl)
-		hba->rpm_lvl = ufs_get_desired_pm_lvl_for_dev_link_state(
-						UFS_SLEEP_PWR_MODE,
-						UIC_LINK_HIBERN8_STATE);
-	if (!hba->spm_lvl)
-		hba->spm_lvl = ufs_get_desired_pm_lvl_for_dev_link_state(
-						UFS_SLEEP_PWR_MODE,
-						UIC_LINK_HIBERN8_STATE);
-
 	INIT_DELAYED_WORK(&hba->rpm_dev_flush_recheck_work, ufshcd_rpm_dev_flush_recheck_work);
 	INIT_DELAYED_WORK(&hba->ufs_rtc_update_work, ufshcd_rtc_work);
 
diff --git a/drivers/ufs/host/ufs-exynos.c b/drivers/ufs/host/ufs-exynos.c
index 98505c68103d..5ba17ccf6417 100644
--- a/drivers/ufs/host/ufs-exynos.c
+++ b/drivers/ufs/host/ufs-exynos.c
@@ -34,7 +34,7 @@
  * Exynos's Vendor specific registers for UFSHCI
  */
 #define HCI_TXPRDT_ENTRY_SIZE	0x00
-#define PRDT_PREFECT_EN		BIT(31)
+#define PRDT_PREFETCH_EN	BIT(31)
 #define HCI_RXPRDT_ENTRY_SIZE	0x04
 #define HCI_1US_TO_CNT_VAL	0x0C
 #define CNT_VAL_1US_MASK	0x3FF
@@ -86,11 +86,16 @@
 				 UIC_TRANSPORT_NO_CONNECTION_RX |\
 				 UIC_TRANSPORT_BAD_TC)
 
-/* FSYS UFS Shareability */
-#define UFS_WR_SHARABLE		BIT(2)
-#define UFS_RD_SHARABLE		BIT(1)
-#define UFS_SHARABLE		(UFS_WR_SHARABLE | UFS_RD_SHARABLE)
-#define UFS_SHAREABILITY_OFFSET	0x710
+/* UFS Shareability */
+#define UFS_EXYNOSAUTO_WR_SHARABLE	BIT(2)
+#define UFS_EXYNOSAUTO_RD_SHARABLE	BIT(1)
+#define UFS_EXYNOSAUTO_SHARABLE		(UFS_EXYNOSAUTO_WR_SHARABLE | \
+					 UFS_EXYNOSAUTO_RD_SHARABLE)
+#define UFS_GS101_WR_SHARABLE		BIT(1)
+#define UFS_GS101_RD_SHARABLE		BIT(0)
+#define UFS_GS101_SHARABLE		(UFS_GS101_WR_SHARABLE | \
+					 UFS_GS101_RD_SHARABLE)
+#define UFS_SHAREABILITY_OFFSET		0x710
 
 /* Multi-host registers */
 #define MHCTRL			0xC4
@@ -198,20 +203,15 @@ static inline void exynos_ufs_ungate_clks(struct exynos_ufs *ufs)
 	exynos_ufs_ctrl_clkstop(ufs, false);
 }
 
-static int exynos7_ufs_drv_init(struct device *dev, struct exynos_ufs *ufs)
-{
-	return 0;
-}
-
-static int exynosauto_ufs_drv_init(struct device *dev, struct exynos_ufs *ufs)
+static int exynos_ufs_shareability(struct exynos_ufs *ufs)
 {
 	struct exynos_ufs_uic_attr *attr = ufs->drv_data->uic_attr;
 
 	/* IO Coherency setting */
 	if (ufs->sysreg) {
 		return regmap_update_bits(ufs->sysreg,
-					  ufs->shareability_reg_offset,
-					  UFS_SHARABLE, UFS_SHARABLE);
+					  ufs->iocc_offset,
+					  ufs->iocc_mask, ufs->iocc_val);
 	}
 
 	attr->tx_dif_p_nsec = 3200000;
@@ -219,6 +219,21 @@ static int exynosauto_ufs_drv_init(struct device *dev, struct exynos_ufs *ufs)
 	return 0;
 }
 
+static int gs101_ufs_drv_init(struct exynos_ufs *ufs)
+{
+	struct ufs_hba *hba = ufs->hba;
+
+	/* Enable WriteBooster */
+	hba->caps |= UFSHCD_CAP_WB_EN;
+
+	return exynos_ufs_shareability(ufs);
+}
+
+static int exynosauto_ufs_drv_init(struct exynos_ufs *ufs)
+{
+	return exynos_ufs_shareability(ufs);
+}
+
 static int exynosauto_ufs_post_hce_enable(struct exynos_ufs *ufs)
 {
 	struct ufs_hba *hba = ufs->hba;
@@ -915,6 +930,12 @@ static int exynos_ufs_phy_init(struct exynos_ufs *ufs)
 	}
 
 	phy_set_bus_width(generic_phy, ufs->avail_ln_rx);
+
+	if (generic_phy->power_count) {
+		phy_power_off(generic_phy);
+		phy_exit(generic_phy);
+	}
+
 	ret = phy_init(generic_phy);
 	if (ret) {
 		dev_err(hba->dev, "%s: phy init failed, ret = %d\n",
@@ -1007,9 +1028,14 @@ static int exynos_ufs_pre_link(struct ufs_hba *hba)
 	exynos_ufs_config_intr(ufs, DFES_DEF_L4_ERRS, UNIPRO_L4);
 	exynos_ufs_set_unipro_pclk_div(ufs);
 
+	exynos_ufs_setup_clocks(hba, true, PRE_CHANGE);
+
 	/* unipro */
 	exynos_ufs_config_unipro(ufs);
 
+	if (ufs->drv_data->pre_link)
+		ufs->drv_data->pre_link(ufs);
+
 	/* m-phy */
 	exynos_ufs_phy_init(ufs);
 	if (!(ufs->opts & EXYNOS_UFS_OPT_SKIP_CONFIG_PHY_ATTR)) {
@@ -1017,11 +1043,6 @@ static int exynos_ufs_pre_link(struct ufs_hba *hba)
 		exynos_ufs_config_phy_cap_attr(ufs);
 	}
 
-	exynos_ufs_setup_clocks(hba, true, PRE_CHANGE);
-
-	if (ufs->drv_data->pre_link)
-		ufs->drv_data->pre_link(ufs);
-
 	return 0;
 }
 
@@ -1045,12 +1066,17 @@ static int exynos_ufs_post_link(struct ufs_hba *hba)
 	struct exynos_ufs *ufs = ufshcd_get_variant(hba);
 	struct phy *generic_phy = ufs->phy;
 	struct exynos_ufs_uic_attr *attr = ufs->drv_data->uic_attr;
+	u32 val = ilog2(DATA_UNIT_SIZE);
 
 	exynos_ufs_establish_connt(ufs);
 	exynos_ufs_fit_aggr_timeout(ufs);
 
 	hci_writel(ufs, 0xa, HCI_DATA_REORDER);
-	hci_writel(ufs, ilog2(DATA_UNIT_SIZE), HCI_TXPRDT_ENTRY_SIZE);
+
+	if (hba->caps & UFSHCD_CAP_CRYPTO)
+		val |= PRDT_PREFETCH_EN;
+	hci_writel(ufs, val, HCI_TXPRDT_ENTRY_SIZE);
+
 	hci_writel(ufs, ilog2(DATA_UNIT_SIZE), HCI_RXPRDT_ENTRY_SIZE);
 	hci_writel(ufs, (1 << hba->nutrs) - 1, HCI_UTRL_NEXUS_TYPE);
 	hci_writel(ufs, (1 << hba->nutmrs) - 1, HCI_UTMRL_NEXUS_TYPE);
@@ -1126,12 +1152,22 @@ static int exynos_ufs_parse_dt(struct device *dev, struct exynos_ufs *ufs)
 		ufs->sysreg = NULL;
 	else {
 		if (of_property_read_u32_index(np, "samsung,sysreg", 1,
-					       &ufs->shareability_reg_offset)) {
+					       &ufs->iocc_offset)) {
 			dev_warn(dev, "can't get an offset from sysreg. Set to default value\n");
-			ufs->shareability_reg_offset = UFS_SHAREABILITY_OFFSET;
+			ufs->iocc_offset = UFS_SHAREABILITY_OFFSET;
 		}
 	}
 
+	ufs->iocc_mask = ufs->drv_data->iocc_mask;
+	/*
+	 * no 'dma-coherent' property means the descriptors are
+	 * non-cacheable so iocc shareability should be disabled.
+	 */
+	if (of_dma_is_coherent(dev->of_node))
+		ufs->iocc_val = ufs->iocc_mask;
+	else
+		ufs->iocc_val = 0;
+
 	ufs->pclk_avail_min = PCLK_AVAIL_MIN;
 	ufs->pclk_avail_max = PCLK_AVAIL_MAX;
 
@@ -1432,7 +1468,7 @@ static int exynos_ufs_init(struct ufs_hba *hba)
 	exynos_ufs_fmp_init(hba, ufs);
 
 	if (ufs->drv_data->drv_init) {
-		ret = ufs->drv_data->drv_init(dev, ufs);
+		ret = ufs->drv_data->drv_init(ufs);
 		if (ret) {
 			dev_err(dev, "failed to init drv-data\n");
 			goto out;
@@ -1454,6 +1490,14 @@ out:
 	return ret;
 }
 
+static void exynos_ufs_exit(struct ufs_hba *hba)
+{
+	struct exynos_ufs *ufs = ufshcd_get_variant(hba);
+
+	phy_power_off(ufs->phy);
+	phy_exit(ufs->phy);
+}
+
 static int exynos_ufs_host_reset(struct ufs_hba *hba)
 {
 	struct exynos_ufs *ufs = ufshcd_get_variant(hba);
@@ -1643,6 +1687,12 @@ static void exynos_ufs_hibern8_notify(struct ufs_hba *hba,
 	}
 }
 
+static int gs101_ufs_suspend(struct exynos_ufs *ufs)
+{
+	hci_writel(ufs, 0 << 0, HCI_GPIO_OUT);
+	return 0;
+}
+
 static int exynos_ufs_suspend(struct ufs_hba *hba, enum ufs_pm_op pm_op,
 	enum ufs_notify_change_status status)
 {
@@ -1651,6 +1701,9 @@ static int exynos_ufs_suspend(struct ufs_hba *hba, enum ufs_pm_op pm_op,
 	if (status == PRE_CHANGE)
 		return 0;
 
+	if (ufs->drv_data->suspend)
+		ufs->drv_data->suspend(ufs);
+
 	if (!ufshcd_is_link_active(hba))
 		phy_power_off(ufs->phy);
 
@@ -1922,6 +1975,7 @@ static int gs101_ufs_pre_pwr_change(struct exynos_ufs *ufs,
 static const struct ufs_hba_variant_ops ufs_hba_exynos_ops = {
 	.name				= "exynos_ufs",
 	.init				= exynos_ufs_init,
+	.exit				= exynos_ufs_exit,
 	.hce_enable_notify		= exynos_ufs_hce_enable_notify,
 	.link_startup_notify		= exynos_ufs_link_startup_notify,
 	.pwr_change_notify		= exynos_ufs_pwr_change_notify,
@@ -1960,13 +2014,7 @@ static int exynos_ufs_probe(struct platform_device *pdev)
 
 static void exynos_ufs_remove(struct platform_device *pdev)
 {
-	struct ufs_hba *hba =  platform_get_drvdata(pdev);
-	struct exynos_ufs *ufs = ufshcd_get_variant(hba);
-
 	ufshcd_pltfrm_remove(pdev);
-
-	phy_power_off(ufs->phy);
-	phy_exit(ufs->phy);
 }
 
 static struct exynos_ufs_uic_attr exynos7_uic_attr = {
@@ -2005,6 +2053,7 @@ static const struct exynos_ufs_drv_data exynosauto_ufs_drvs = {
 	.opts			= EXYNOS_UFS_OPT_BROKEN_AUTO_CLK_CTRL |
 				  EXYNOS_UFS_OPT_SKIP_CONFIG_PHY_ATTR |
 				  EXYNOS_UFS_OPT_BROKEN_RX_SEL_IDX,
+	.iocc_mask		= UFS_EXYNOSAUTO_SHARABLE,
 	.drv_init		= exynosauto_ufs_drv_init,
 	.post_hce_enable	= exynosauto_ufs_post_hce_enable,
 	.pre_link		= exynosauto_ufs_pre_link,
@@ -2038,7 +2087,6 @@ static const struct exynos_ufs_drv_data exynos_ufs_drvs = {
 				  EXYNOS_UFS_OPT_BROKEN_RX_SEL_IDX |
 				  EXYNOS_UFS_OPT_SKIP_CONNECTION_ESTAB |
 				  EXYNOS_UFS_OPT_USE_SW_HIBERN8_TIMER,
-	.drv_init		= exynos7_ufs_drv_init,
 	.pre_link		= exynos7_ufs_pre_link,
 	.post_link		= exynos7_ufs_post_link,
 	.pre_pwr_change		= exynos7_ufs_pre_pwr_change,
@@ -2128,10 +2176,12 @@ static const struct exynos_ufs_drv_data gs101_ufs_drvs = {
 				  EXYNOS_UFS_OPT_SKIP_CONFIG_PHY_ATTR |
 				  EXYNOS_UFS_OPT_UFSPR_SECURE |
 				  EXYNOS_UFS_OPT_TIMER_TICK_SELECT,
-	.drv_init		= exynosauto_ufs_drv_init,
+	.iocc_mask		= UFS_GS101_SHARABLE,
+	.drv_init		= gs101_ufs_drv_init,
 	.pre_link		= gs101_ufs_pre_link,
 	.post_link		= gs101_ufs_post_link,
 	.pre_pwr_change		= gs101_ufs_pre_pwr_change,
+	.suspend		= gs101_ufs_suspend,
 };
 
 static const struct of_device_id exynos_ufs_of_match[] = {
diff --git a/drivers/ufs/host/ufs-exynos.h b/drivers/ufs/host/ufs-exynos.h
index 1646c4a9bb08..3c6fe5132190 100644
--- a/drivers/ufs/host/ufs-exynos.h
+++ b/drivers/ufs/host/ufs-exynos.h
@@ -181,8 +181,9 @@ struct exynos_ufs_drv_data {
 	struct exynos_ufs_uic_attr *uic_attr;
 	unsigned int quirks;
 	unsigned int opts;
+	u32 iocc_mask;
 	/* SoC's specific operations */
-	int (*drv_init)(struct device *dev, struct exynos_ufs *ufs);
+	int (*drv_init)(struct exynos_ufs *ufs);
 	int (*pre_link)(struct exynos_ufs *ufs);
 	int (*post_link)(struct exynos_ufs *ufs);
 	int (*pre_pwr_change)(struct exynos_ufs *ufs,
@@ -191,6 +192,7 @@ struct exynos_ufs_drv_data {
 				struct ufs_pa_layer_attr *pwr);
 	int (*pre_hce_enable)(struct exynos_ufs *ufs);
 	int (*post_hce_enable)(struct exynos_ufs *ufs);
+	int (*suspend)(struct exynos_ufs *ufs);
 };
 
 struct ufs_phy_time_cfg {
@@ -230,7 +232,9 @@ struct exynos_ufs {
 	ktime_t entry_hibern8_t;
 	const struct exynos_ufs_drv_data *drv_data;
 	struct regmap *sysreg;
-	u32 shareability_reg_offset;
+	u32 iocc_offset;
+	u32 iocc_mask;
+	u32 iocc_val;
 
 	u32 opts;
 #define EXYNOS_UFS_OPT_HAS_APB_CLK_CTRL		BIT(0)
diff --git a/drivers/ufs/host/ufs-qcom.c b/drivers/ufs/host/ufs-qcom.c
index 989692fb9108..a715f377d0a8 100644
--- a/drivers/ufs/host/ufs-qcom.c
+++ b/drivers/ufs/host/ufs-qcom.c
@@ -118,7 +118,7 @@ static int ufs_qcom_ice_init(struct ufs_qcom_host *host)
 	struct device *dev = hba->dev;
 	struct qcom_ice *ice;
 
-	ice = of_qcom_ice_get(dev);
+	ice = devm_of_qcom_ice_get(dev);
 	if (ice == ERR_PTR(-EOPNOTSUPP)) {
 		dev_warn(dev, "Disabling inline encryption support\n");
 		ice = NULL;
@@ -155,8 +155,9 @@ static int ufs_qcom_ice_program_key(struct ufs_hba *hba,
 {
 	struct ufs_qcom_host *host = ufshcd_get_variant(hba);
 	union ufs_crypto_cap_entry cap;
-	bool config_enable =
-		cfg->config_enable & UFS_CRYPTO_CONFIGURATION_ENABLE;
+
+	if (!(cfg->config_enable & UFS_CRYPTO_CONFIGURATION_ENABLE))
+		return qcom_ice_evict_key(host->ice, slot);
 
 	/* Only AES-256-XTS has been tested so far. */
 	cap = hba->crypto_cap_array[cfg->crypto_cap_idx];
@@ -164,14 +165,11 @@ static int ufs_qcom_ice_program_key(struct ufs_hba *hba,
 	    cap.key_size != UFS_CRYPTO_KEY_SIZE_256)
 		return -EOPNOTSUPP;
 
-	if (config_enable)
-		return qcom_ice_program_key(host->ice,
-					    QCOM_ICE_CRYPTO_ALG_AES_XTS,
-					    QCOM_ICE_CRYPTO_KEY_SIZE_256,
-					    cfg->crypto_key,
-					    cfg->data_unit_size, slot);
-	else
-		return qcom_ice_evict_key(host->ice, slot);
+	return qcom_ice_program_key(host->ice,
+				    QCOM_ICE_CRYPTO_ALG_AES_XTS,
+				    QCOM_ICE_CRYPTO_KEY_SIZE_256,
+				    cfg->crypto_key,
+				    cfg->data_unit_size, slot);
 }
 
 #else
@@ -368,10 +366,9 @@ static int ufs_qcom_power_up_sequence(struct ufs_hba *hba)
 	if (ret)
 		return ret;
 
-	if (phy->power_count) {
+	if (phy->power_count)
 		phy_power_off(phy);
-		phy_exit(phy);
-	}
+
 
 	/* phy initialization - calibrate the phy */
 	ret = phy_init(phy);
diff --git a/drivers/ufs/host/ufshcd-pci.c b/drivers/ufs/host/ufshcd-pci.c
index 54e0cc0653a2..850ff71130d5 100644
--- a/drivers/ufs/host/ufshcd-pci.c
+++ b/drivers/ufs/host/ufshcd-pci.c
@@ -562,7 +562,6 @@ static void ufshcd_pci_remove(struct pci_dev *pdev)
 	pm_runtime_forbid(&pdev->dev);
 	pm_runtime_get_noresume(&pdev->dev);
 	ufshcd_remove(hba);
-	ufshcd_dealloc_host(hba);
 }
 
 /**
@@ -607,7 +606,6 @@ ufshcd_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	err = ufshcd_init(hba, mmio_base, pdev->irq);
 	if (err) {
 		dev_err(&pdev->dev, "Initialization failed\n");
-		ufshcd_dealloc_host(hba);
 		return err;
 	}
 
diff --git a/drivers/ufs/host/ufshcd-pltfrm.c b/drivers/ufs/host/ufshcd-pltfrm.c
index 505572d4fa87..ffe5d1d2b215 100644
--- a/drivers/ufs/host/ufshcd-pltfrm.c
+++ b/drivers/ufs/host/ufshcd-pltfrm.c
@@ -465,21 +465,17 @@ int ufshcd_pltfrm_init(struct platform_device *pdev,
 	struct device *dev = &pdev->dev;
 
 	mmio_base = devm_platform_ioremap_resource(pdev, 0);
-	if (IS_ERR(mmio_base)) {
-		err = PTR_ERR(mmio_base);
-		goto out;
-	}
+	if (IS_ERR(mmio_base))
+		return PTR_ERR(mmio_base);
 
 	irq = platform_get_irq(pdev, 0);
-	if (irq < 0) {
-		err = irq;
-		goto out;
-	}
+	if (irq < 0)
+		return irq;
 
 	err = ufshcd_alloc_host(dev, &hba);
 	if (err) {
 		dev_err(dev, "Allocation failed\n");
-		goto out;
+		return err;
 	}
 
 	hba->vops = vops;
@@ -488,13 +484,13 @@ int ufshcd_pltfrm_init(struct platform_device *pdev,
 	if (err) {
 		dev_err(dev, "%s: clock parse failed %d\n",
 				__func__, err);
-		goto dealloc_host;
+		return err;
 	}
 	err = ufshcd_parse_regulator_info(hba);
 	if (err) {
 		dev_err(dev, "%s: regulator init failed %d\n",
 				__func__, err);
-		goto dealloc_host;
+		return err;
 	}
 
 	ufshcd_init_lanes_per_dir(hba);
@@ -502,25 +498,20 @@ int ufshcd_pltfrm_init(struct platform_device *pdev,
 	err = ufshcd_parse_operating_points(hba);
 	if (err) {
 		dev_err(dev, "%s: OPP parse failed %d\n", __func__, err);
-		goto dealloc_host;
+		return err;
 	}
 
 	err = ufshcd_init(hba, mmio_base, irq);
 	if (err) {
 		dev_err_probe(dev, err, "Initialization failed with error %d\n",
 			      err);
-		goto dealloc_host;
+		return err;
 	}
 
 	pm_runtime_set_active(dev);
 	pm_runtime_enable(dev);
 
 	return 0;
-
-dealloc_host:
-	ufshcd_dealloc_host(hba);
-out:
-	return err;
 }
 EXPORT_SYMBOL_GPL(ufshcd_pltfrm_init);
 
@@ -534,7 +525,6 @@ void ufshcd_pltfrm_remove(struct platform_device *pdev)
 
 	pm_runtime_get_sync(&pdev->dev);
 	ufshcd_remove(hba);
-	ufshcd_dealloc_host(hba);
 	pm_runtime_disable(&pdev->dev);
 	pm_runtime_put_noidle(&pdev->dev);
 }
diff --git a/drivers/uio/uio_hv_generic.c b/drivers/uio/uio_hv_generic.c
index 870409599411..a6551a795f74 100644
--- a/drivers/uio/uio_hv_generic.c
+++ b/drivers/uio/uio_hv_generic.c
@@ -131,15 +131,12 @@ static void hv_uio_rescind(struct vmbus_channel *channel)
 	vmbus_device_unregister(channel->device_obj);
 }
 
-/* Sysfs API to allow mmap of the ring buffers
+/* Function used for mmap of ring buffer sysfs interface.
  * The ring buffer is allocated as contiguous memory by vmbus_open
  */
-static int hv_uio_ring_mmap(struct file *filp, struct kobject *kobj,
-			    struct bin_attribute *attr,
-			    struct vm_area_struct *vma)
+static int
+hv_uio_ring_mmap(struct vmbus_channel *channel, struct vm_area_struct *vma)
 {
-	struct vmbus_channel *channel
-		= container_of(kobj, struct vmbus_channel, kobj);
 	void *ring_buffer = page_address(channel->ringbuffer_page);
 
 	if (channel->state != CHANNEL_OPENED_STATE)
@@ -149,15 +146,6 @@ static int hv_uio_ring_mmap(struct file *filp, struct kobject *kobj,
 			       channel->ringbuffer_pagecount << PAGE_SHIFT);
 }
 
-static const struct bin_attribute ring_buffer_bin_attr = {
-	.attr = {
-		.name = "ring",
-		.mode = 0600,
-	},
-	.size = 2 * SZ_2M,
-	.mmap = hv_uio_ring_mmap,
-};
-
 /* Callback from VMBUS subsystem when new channel created. */
 static void
 hv_uio_new_channel(struct vmbus_channel *new_sc)
@@ -178,8 +166,7 @@ hv_uio_new_channel(struct vmbus_channel *new_sc)
 	/* Disable interrupts on sub channel */
 	new_sc->inbound.ring_buffer->interrupt_mask = 1;
 	set_channel_read_mode(new_sc, HV_CALL_ISR);
-
-	ret = sysfs_create_bin_file(&new_sc->kobj, &ring_buffer_bin_attr);
+	ret = hv_create_ring_sysfs(new_sc, hv_uio_ring_mmap);
 	if (ret) {
 		dev_err(device, "sysfs create ring bin file failed; %d\n", ret);
 		vmbus_close(new_sc);
@@ -256,6 +243,9 @@ hv_uio_probe(struct hv_device *dev,
 	if (!ring_size)
 		ring_size = SZ_2M;
 
+	/* Adjust ring size if necessary to have it page aligned */
+	ring_size = VMBUS_RING_SIZE(ring_size);
+
 	pdata = devm_kzalloc(&dev->device, sizeof(*pdata), GFP_KERNEL);
 	if (!pdata)
 		return -ENOMEM;
@@ -287,13 +277,13 @@ hv_uio_probe(struct hv_device *dev,
 	pdata->info.mem[INT_PAGE_MAP].name = "int_page";
 	pdata->info.mem[INT_PAGE_MAP].addr
 		= (uintptr_t)vmbus_connection.int_page;
-	pdata->info.mem[INT_PAGE_MAP].size = PAGE_SIZE;
+	pdata->info.mem[INT_PAGE_MAP].size = HV_HYP_PAGE_SIZE;
 	pdata->info.mem[INT_PAGE_MAP].memtype = UIO_MEM_LOGICAL;
 
 	pdata->info.mem[MON_PAGE_MAP].name = "monitor_page";
 	pdata->info.mem[MON_PAGE_MAP].addr
 		= (uintptr_t)vmbus_connection.monitor_pages[1];
-	pdata->info.mem[MON_PAGE_MAP].size = PAGE_SIZE;
+	pdata->info.mem[MON_PAGE_MAP].size = HV_HYP_PAGE_SIZE;
 	pdata->info.mem[MON_PAGE_MAP].memtype = UIO_MEM_LOGICAL;
 
 	pdata->recv_buf = vzalloc(RECV_BUFFER_SIZE);
@@ -350,10 +340,18 @@ hv_uio_probe(struct hv_device *dev,
 		goto fail_close;
 	}
 
-	ret = sysfs_create_bin_file(&channel->kobj, &ring_buffer_bin_attr);
-	if (ret)
-		dev_notice(&dev->device,
-			   "sysfs create ring bin file failed; %d\n", ret);
+	/*
+	 * This internally calls sysfs_update_group, which returns a non-zero value if it executes
+	 * before sysfs_create_group. This is expected as the 'ring' will be created later in
+	 * vmbus_device_register() -> vmbus_add_channel_kobj(). Thus, no need to check the return
+	 * value and print warning.
+	 *
+	 * Creating/exposing sysfs in driver probe is not encouraged as it can lead to race
+	 * conditions with userspace. For backward compatibility, "ring" sysfs could not be removed
+	 * or decoupled from uio_hv_generic probe. Userspace programs can make use of inotify
+	 * APIs to make sure that ring is created.
+	 */
+	hv_create_ring_sysfs(channel, hv_uio_ring_mmap);
 
 	hv_set_drvdata(dev, pdata);
 
@@ -375,7 +373,7 @@ hv_uio_remove(struct hv_device *dev)
 	if (!pdata)
 		return;
 
-	sysfs_remove_bin_file(&dev->channel->kobj, &ring_buffer_bin_attr);
+	hv_remove_ring_sysfs(dev->channel);
 	uio_unregister_device(&pdata->info);
 	hv_uio_cleanup(dev, pdata);
 
diff --git a/drivers/usb/atm/cxacru.c b/drivers/usb/atm/cxacru.c
index 0dd85d2635b9..47d06af33747 100644
--- a/drivers/usb/atm/cxacru.c
+++ b/drivers/usb/atm/cxacru.c
@@ -1131,7 +1131,10 @@ static int cxacru_bind(struct usbatm_data *usbatm_instance,
 	struct cxacru_data *instance;
 	struct usb_device *usb_dev = interface_to_usbdev(intf);
 	struct usb_host_endpoint *cmd_ep = usb_dev->ep_in[CXACRU_EP_CMD];
-	struct usb_endpoint_descriptor *in, *out;
+	static const u8 ep_addrs[] = {
+		CXACRU_EP_CMD + USB_DIR_IN,
+		CXACRU_EP_CMD + USB_DIR_OUT,
+		0};
 	int ret;
 
 	/* instance init */
@@ -1179,13 +1182,11 @@ static int cxacru_bind(struct usbatm_data *usbatm_instance,
 	}
 
 	if (usb_endpoint_xfer_int(&cmd_ep->desc))
-		ret = usb_find_common_endpoints(intf->cur_altsetting,
-						NULL, NULL, &in, &out);
+		ret = usb_check_int_endpoints(intf, ep_addrs);
 	else
-		ret = usb_find_common_endpoints(intf->cur_altsetting,
-						&in, &out, NULL, NULL);
+		ret = usb_check_bulk_endpoints(intf, ep_addrs);
 
-	if (ret) {
+	if (!ret) {
 		usb_err(usbatm_instance, "cxacru_bind: interface has incorrect endpoints\n");
 		ret = -ENODEV;
 		goto fail;
diff --git a/drivers/usb/cdns3/cdns3-gadget.c b/drivers/usb/cdns3/cdns3-gadget.c
index fd1beb10bba7..19101ff1cf1b 100644
--- a/drivers/usb/cdns3/cdns3-gadget.c
+++ b/drivers/usb/cdns3/cdns3-gadget.c
@@ -1963,6 +1963,7 @@ static irqreturn_t cdns3_device_thread_irq_handler(int irq, void *data)
 	unsigned int bit;
 	unsigned long reg;
 
+	local_bh_disable();
 	spin_lock_irqsave(&priv_dev->lock, flags);
 
 	reg = readl(&priv_dev->regs->usb_ists);
@@ -2004,6 +2005,7 @@ static irqreturn_t cdns3_device_thread_irq_handler(int irq, void *data)
 irqend:
 	writel(~0, &priv_dev->regs->ep_ien);
 	spin_unlock_irqrestore(&priv_dev->lock, flags);
+	local_bh_enable();
 
 	return ret;
 }
diff --git a/drivers/usb/cdns3/cdnsp-debug.h b/drivers/usb/cdns3/cdnsp-debug.h
index cd138acdcce1..86860686d836 100644
--- a/drivers/usb/cdns3/cdnsp-debug.h
+++ b/drivers/usb/cdns3/cdnsp-debug.h
@@ -327,12 +327,13 @@ static inline const char *cdnsp_decode_trb(char *str, size_t size, u32 field0,
 	case TRB_RESET_EP:
 	case TRB_HALT_ENDPOINT:
 		ret = scnprintf(str, size,
-				"%s: ep%d%s(%d) ctx %08x%08x slot %ld flags %c",
+				"%s: ep%d%s(%d) ctx %08x%08x slot %ld flags %c %c",
 				cdnsp_trb_type_string(type),
 				ep_num, ep_id % 2 ? "out" : "in",
 				TRB_TO_EP_INDEX(field3), field1, field0,
 				TRB_TO_SLOT_ID(field3),
-				field3 & TRB_CYCLE ? 'C' : 'c');
+				field3 & TRB_CYCLE ? 'C' : 'c',
+				field3 & TRB_ESP ? 'P' : 'p');
 		break;
 	case TRB_STOP_RING:
 		ret = scnprintf(str, size,
diff --git a/drivers/usb/cdns3/cdnsp-ep0.c b/drivers/usb/cdns3/cdnsp-ep0.c
index f317d3c84781..5cd9b898ce97 100644
--- a/drivers/usb/cdns3/cdnsp-ep0.c
+++ b/drivers/usb/cdns3/cdnsp-ep0.c
@@ -414,6 +414,7 @@ static int cdnsp_ep0_std_request(struct cdnsp_device *pdev,
 void cdnsp_setup_analyze(struct cdnsp_device *pdev)
 {
 	struct usb_ctrlrequest *ctrl = &pdev->setup;
+	struct cdnsp_ep *pep;
 	int ret = -EINVAL;
 	u16 len;
 
@@ -427,10 +428,21 @@ void cdnsp_setup_analyze(struct cdnsp_device *pdev)
 		goto out;
 	}
 
+	pep = &pdev->eps[0];
+
 	/* Restore the ep0 to Stopped/Running state. */
-	if (pdev->eps[0].ep_state & EP_HALTED) {
-		trace_cdnsp_ep0_halted("Restore to normal state");
-		cdnsp_halt_endpoint(pdev, &pdev->eps[0], 0);
+	if (pep->ep_state & EP_HALTED) {
+		if (GET_EP_CTX_STATE(pep->out_ctx) == EP_STATE_HALTED)
+			cdnsp_halt_endpoint(pdev, pep, 0);
+
+		/*
+		 * Halt Endpoint Command for SSP2 for ep0 preserve current
+		 * endpoint state and driver has to synchronize the
+		 * software endpoint state with endpoint output context
+		 * state.
+		 */
+		pep->ep_state &= ~EP_HALTED;
+		pep->ep_state |= EP_STOPPED;
 	}
 
 	/*
diff --git a/drivers/usb/cdns3/cdnsp-gadget.c b/drivers/usb/cdns3/cdnsp-gadget.c
index 4a3f0f958256..38e693cd3efc 100644
--- a/drivers/usb/cdns3/cdnsp-gadget.c
+++ b/drivers/usb/cdns3/cdnsp-gadget.c
@@ -28,7 +28,8 @@
 unsigned int cdnsp_port_speed(unsigned int port_status)
 {
 	/*Detect gadget speed based on PORTSC register*/
-	if (DEV_SUPERSPEEDPLUS(port_status))
+	if (DEV_SUPERSPEEDPLUS(port_status) ||
+	    DEV_SSP_GEN1x2(port_status) || DEV_SSP_GEN2x2(port_status))
 		return USB_SPEED_SUPER_PLUS;
 	else if (DEV_SUPERSPEED(port_status))
 		return USB_SPEED_SUPER;
@@ -138,6 +139,26 @@ static void cdnsp_clear_port_change_bit(struct cdnsp_device *pdev,
 	       (portsc & PORT_CHANGE_BITS), port_regs);
 }
 
+static void cdnsp_set_apb_timeout_value(struct cdnsp_device *pdev)
+{
+	struct cdns *cdns = dev_get_drvdata(pdev->dev);
+	__le32 __iomem *reg;
+	void __iomem *base;
+	u32 offset = 0;
+	u32 val;
+
+	if (!cdns->override_apb_timeout)
+		return;
+
+	base = &pdev->cap_regs->hc_capbase;
+	offset = cdnsp_find_next_ext_cap(base, offset, D_XEC_PRE_REGS_CAP);
+	reg = base + offset + REG_CHICKEN_BITS_3_OFFSET;
+
+	val  = le32_to_cpu(readl(reg));
+	val = CHICKEN_APB_TIMEOUT_SET(val, cdns->override_apb_timeout);
+	writel(cpu_to_le32(val), reg);
+}
+
 static void cdnsp_set_chicken_bits_2(struct cdnsp_device *pdev, u32 bit)
 {
 	__le32 __iomem *reg;
@@ -526,6 +547,7 @@ int cdnsp_wait_for_cmd_compl(struct cdnsp_device *pdev)
 	dma_addr_t cmd_deq_dma;
 	union cdnsp_trb *event;
 	u32 cycle_state;
+	u32 retry = 10;
 	int ret, val;
 	u64 cmd_dma;
 	u32  flags;
@@ -557,8 +579,23 @@ int cdnsp_wait_for_cmd_compl(struct cdnsp_device *pdev)
 		flags = le32_to_cpu(event->event_cmd.flags);
 
 		/* Check the owner of the TRB. */
-		if ((flags & TRB_CYCLE) != cycle_state)
+		if ((flags & TRB_CYCLE) != cycle_state) {
+			/*
+			 * Give some extra time to get chance controller
+			 * to finish command before returning error code.
+			 * Checking CMD_RING_BUSY is not sufficient because
+			 * this bit is cleared to '0' when the Command
+			 * Descriptor has been executed by controller
+			 * and not when command completion event has
+			 * be added to event ring.
+			 */
+			if (retry--) {
+				udelay(20);
+				continue;
+			}
+
 			return -EINVAL;
+		}
 
 		cmd_dma = le64_to_cpu(event->event_cmd.cmd_trb);
 
@@ -1772,6 +1809,8 @@ static void cdnsp_get_rev_cap(struct cdnsp_device *pdev)
 	reg += cdnsp_find_next_ext_cap(reg, 0, RTL_REV_CAP);
 	pdev->rev_cap  = reg;
 
+	pdev->rtl_revision = readl(&pdev->rev_cap->rtl_revision);
+
 	dev_info(pdev->dev, "Rev: %08x/%08x, eps: %08x, buff: %08x/%08x\n",
 		 readl(&pdev->rev_cap->ctrl_revision),
 		 readl(&pdev->rev_cap->rtl_revision),
@@ -1797,6 +1836,15 @@ static int cdnsp_gen_setup(struct cdnsp_device *pdev)
 	pdev->hci_version = HC_VERSION(pdev->hcc_params);
 	pdev->hcc_params = readl(&pdev->cap_regs->hcc_params);
 
+	/*
+	 * Override the APB timeout value to give the controller more time for
+	 * enabling UTMI clock and synchronizing APB and UTMI clock domains.
+	 * This fix is platform specific and is required to fixes issue with
+	 * reading incorrect value from PORTSC register after resuming
+	 * from L1 state.
+	 */
+	cdnsp_set_apb_timeout_value(pdev);
+
 	cdnsp_get_rev_cap(pdev);
 
 	/* Make sure the Device Controller is halted. */
diff --git a/drivers/usb/cdns3/cdnsp-gadget.h b/drivers/usb/cdns3/cdnsp-gadget.h
index 84887dfea763..a91cca509db0 100644
--- a/drivers/usb/cdns3/cdnsp-gadget.h
+++ b/drivers/usb/cdns3/cdnsp-gadget.h
@@ -285,11 +285,15 @@ struct cdnsp_port_regs {
 #define XDEV_HS			(0x3 << 10)
 #define XDEV_SS			(0x4 << 10)
 #define XDEV_SSP		(0x5 << 10)
+#define XDEV_SSP1x2		(0x6 << 10)
+#define XDEV_SSP2x2		(0x7 << 10)
 #define DEV_UNDEFSPEED(p)	(((p) & DEV_SPEED_MASK) == (0x0 << 10))
 #define DEV_FULLSPEED(p)	(((p) & DEV_SPEED_MASK) == XDEV_FS)
 #define DEV_HIGHSPEED(p)	(((p) & DEV_SPEED_MASK) == XDEV_HS)
 #define DEV_SUPERSPEED(p)	(((p) & DEV_SPEED_MASK) == XDEV_SS)
 #define DEV_SUPERSPEEDPLUS(p)	(((p) & DEV_SPEED_MASK) == XDEV_SSP)
+#define DEV_SSP_GEN1x2(p)	(((p) & DEV_SPEED_MASK) == XDEV_SSP1x2)
+#define DEV_SSP_GEN2x2(p)	(((p) & DEV_SPEED_MASK) == XDEV_SSP2x2)
 #define DEV_SUPERSPEED_ANY(p)	(((p) & DEV_SPEED_MASK) >= XDEV_SS)
 #define DEV_PORT_SPEED(p)	(((p) >> 10) & 0x0f)
 /* Port Link State Write Strobe - set this when changing link state */
@@ -520,6 +524,9 @@ struct cdnsp_rev_cap {
 #define REG_CHICKEN_BITS_2_OFFSET	0x48
 #define CHICKEN_XDMA_2_TP_CACHE_DIS	BIT(28)
 
+#define REG_CHICKEN_BITS_3_OFFSET       0x4C
+#define CHICKEN_APB_TIMEOUT_SET(p, val) (((p) & ~GENMASK(21, 0)) | (val))
+
 /* XBUF Extended Capability ID. */
 #define XBUF_CAP_ID			0xCB
 #define XBUF_RX_TAG_MASK_0_OFFSET	0x1C
@@ -980,6 +987,12 @@ enum cdnsp_setup_dev {
 #define STREAM_ID_FOR_TRB(p)		((((p)) << 16) & GENMASK(31, 16))
 #define SCT_FOR_TRB(p)			(((p) << 1) & 0x7)
 
+/*
+ * Halt Endpoint Command TRB field.
+ * The ESP bit only exists in the SSP2 controller.
+ */
+#define TRB_ESP				BIT(9)
+
 /* Link TRB specific fields. */
 #define TRB_TC				BIT(1)
 
@@ -1357,6 +1370,7 @@ struct cdnsp_port {
  * @rev_cap: Controller Capabilities Registers.
  * @hcs_params1: Cached register copies of read-only HCSPARAMS1
  * @hcc_params: Cached register copies of read-only HCCPARAMS1
+ * @rtl_revision: Cached controller rtl revision.
  * @setup: Temporary buffer for setup packet.
  * @ep0_preq: Internal allocated request used during enumeration.
  * @ep0_stage: ep0 stage during enumeration process.
@@ -1411,6 +1425,8 @@ struct cdnsp_device {
 	__u32 hcs_params1;
 	__u32 hcs_params3;
 	__u32 hcc_params;
+	#define RTL_REVISION_NEW_LPM 0x2700
+	__u32 rtl_revision;
 	/* Lock used in interrupt thread context. */
 	spinlock_t lock;
 	struct usb_ctrlrequest setup;
diff --git a/drivers/usb/cdns3/cdnsp-pci.c b/drivers/usb/cdns3/cdnsp-pci.c
index 2d05368a6745..36781ea60f6a 100644
--- a/drivers/usb/cdns3/cdnsp-pci.c
+++ b/drivers/usb/cdns3/cdnsp-pci.c
@@ -34,6 +34,8 @@
 #define PCI_CLASS_SERIAL_USB_CDNS_USB3	(PCI_CLASS_SERIAL_USB << 8 | 0x80)
 #define PCI_CLASS_SERIAL_USB_CDNS_UDC	PCI_CLASS_SERIAL_USB_DEVICE
 
+#define CHICKEN_APB_TIMEOUT_VALUE       0x1C20
+
 static struct pci_dev *cdnsp_get_second_fun(struct pci_dev *pdev)
 {
 	/*
@@ -145,6 +147,14 @@ static int cdnsp_pci_probe(struct pci_dev *pdev,
 		cdnsp->otg_irq = pdev->irq;
 	}
 
+	/*
+	 * Cadence PCI based platform require some longer timeout for APB
+	 * to fixes domain clock synchronization issue after resuming
+	 * controller from L1 state.
+	 */
+	cdnsp->override_apb_timeout = CHICKEN_APB_TIMEOUT_VALUE;
+	pci_set_drvdata(pdev, cdnsp);
+
 	if (pci_is_enabled(func)) {
 		cdnsp->dev = dev;
 		cdnsp->gadget_init = cdnsp_gadget_init;
@@ -154,8 +164,6 @@ static int cdnsp_pci_probe(struct pci_dev *pdev,
 			goto free_cdnsp;
 	}
 
-	pci_set_drvdata(pdev, cdnsp);
-
 	device_wakeup_enable(&pdev->dev);
 	if (pci_dev_run_wake(pdev))
 		pm_runtime_put_noidle(&pdev->dev);
diff --git a/drivers/usb/cdns3/cdnsp-ring.c b/drivers/usb/cdns3/cdnsp-ring.c
index 46852529499d..0758f171f73e 100644
--- a/drivers/usb/cdns3/cdnsp-ring.c
+++ b/drivers/usb/cdns3/cdnsp-ring.c
@@ -308,7 +308,8 @@ static bool cdnsp_ring_ep_doorbell(struct cdnsp_device *pdev,
 
 	writel(db_value, reg_addr);
 
-	cdnsp_force_l0_go(pdev);
+	if (pdev->rtl_revision < RTL_REVISION_NEW_LPM)
+		cdnsp_force_l0_go(pdev);
 
 	/* Doorbell was set. */
 	return true;
@@ -771,7 +772,9 @@ static int cdnsp_update_port_id(struct cdnsp_device *pdev, u32 port_id)
 	}
 
 	if (port_id != old_port) {
-		cdnsp_disable_slot(pdev);
+		if (pdev->slot_id)
+			cdnsp_disable_slot(pdev);
+
 		pdev->active_port = port;
 		cdnsp_enable_slot(pdev);
 	}
@@ -2482,7 +2485,8 @@ void cdnsp_queue_halt_endpoint(struct cdnsp_device *pdev, unsigned int ep_index)
 {
 	cdnsp_queue_command(pdev, 0, 0, 0, TRB_TYPE(TRB_HALT_ENDPOINT) |
 			    SLOT_ID_FOR_TRB(pdev->slot_id) |
-			    EP_ID_FOR_TRB(ep_index));
+			    EP_ID_FOR_TRB(ep_index) |
+			    (!ep_index ? TRB_ESP : 0));
 }
 
 void cdnsp_force_header_wakeup(struct cdnsp_device *pdev, int intf_num)
diff --git a/drivers/usb/cdns3/core.h b/drivers/usb/cdns3/core.h
index 57d47348dc19..ac30ee21309d 100644
--- a/drivers/usb/cdns3/core.h
+++ b/drivers/usb/cdns3/core.h
@@ -79,6 +79,8 @@ struct cdns3_platform_data {
  * @pdata: platform data from glue layer
  * @lock: spinlock structure
  * @xhci_plat_data: xhci private data structure pointer
+ * @override_apb_timeout: hold value of APB timeout. For value 0 the default
+ *                        value in CHICKEN_BITS_3 will be preserved.
  * @gadget_init: pointer to gadget initialization function
  */
 struct cdns {
@@ -117,6 +119,7 @@ struct cdns {
 	struct cdns3_platform_data	*pdata;
 	spinlock_t			lock;
 	struct xhci_plat_priv		*xhci_plat_data;
+	u32                             override_apb_timeout;
 
 	int (*gadget_init)(struct cdns *cdns);
 };
diff --git a/drivers/usb/chipidea/ci_hdrc_imx.c b/drivers/usb/chipidea/ci_hdrc_imx.c
index 46d1a4428b9a..2174f6e1f82a 100644
--- a/drivers/usb/chipidea/ci_hdrc_imx.c
+++ b/drivers/usb/chipidea/ci_hdrc_imx.c
@@ -336,6 +336,13 @@ static int ci_hdrc_imx_notify_event(struct ci_hdrc *ci, unsigned int event)
 	return ret;
 }
 
+static void ci_hdrc_imx_disable_regulator(void *arg)
+{
+	struct ci_hdrc_imx_data *data = arg;
+
+	regulator_disable(data->hsic_pad_regulator);
+}
+
 static int ci_hdrc_imx_probe(struct platform_device *pdev)
 {
 	struct ci_hdrc_imx_data *data;
@@ -394,6 +401,13 @@ static int ci_hdrc_imx_probe(struct platform_device *pdev)
 					"Failed to enable HSIC pad regulator\n");
 				goto err_put;
 			}
+			ret = devm_add_action_or_reset(dev,
+					ci_hdrc_imx_disable_regulator, data);
+			if (ret) {
+				dev_err(dev,
+					"Failed to add regulator devm action\n");
+				goto err_put;
+			}
 		}
 	}
 
@@ -432,11 +446,11 @@ static int ci_hdrc_imx_probe(struct platform_device *pdev)
 
 	ret = imx_get_clks(dev);
 	if (ret)
-		goto disable_hsic_regulator;
+		goto qos_remove_request;
 
 	ret = imx_prepare_enable_clks(dev);
 	if (ret)
-		goto disable_hsic_regulator;
+		goto qos_remove_request;
 
 	ret = clk_prepare_enable(data->clk_wakeup);
 	if (ret)
@@ -470,7 +484,11 @@ static int ci_hdrc_imx_probe(struct platform_device *pdev)
 	    of_usb_get_phy_mode(np) == USBPHY_INTERFACE_MODE_ULPI) {
 		pdata.flags |= CI_HDRC_OVERRIDE_PHY_CONTROL;
 		data->override_phy_control = true;
-		usb_phy_init(pdata.usb_phy);
+		ret = usb_phy_init(pdata.usb_phy);
+		if (ret) {
+			dev_err(dev, "Failed to init phy\n");
+			goto err_clk;
+		}
 	}
 
 	if (pdata.flags & CI_HDRC_SUPPORTS_RUNTIME_PM)
@@ -479,7 +497,7 @@ static int ci_hdrc_imx_probe(struct platform_device *pdev)
 	ret = imx_usbmisc_init(data->usbmisc_data);
 	if (ret) {
 		dev_err(dev, "usbmisc init failed, ret=%d\n", ret);
-		goto err_clk;
+		goto phy_shutdown;
 	}
 
 	data->ci_pdev = ci_hdrc_add_device(dev,
@@ -488,7 +506,7 @@ static int ci_hdrc_imx_probe(struct platform_device *pdev)
 	if (IS_ERR(data->ci_pdev)) {
 		ret = PTR_ERR(data->ci_pdev);
 		dev_err_probe(dev, ret, "ci_hdrc_add_device failed\n");
-		goto err_clk;
+		goto phy_shutdown;
 	}
 
 	if (data->usbmisc_data) {
@@ -522,19 +540,20 @@ static int ci_hdrc_imx_probe(struct platform_device *pdev)
 
 disable_device:
 	ci_hdrc_remove_device(data->ci_pdev);
+phy_shutdown:
+	if (data->override_phy_control)
+		usb_phy_shutdown(data->phy);
 err_clk:
 	clk_disable_unprepare(data->clk_wakeup);
 err_wakeup_clk:
 	imx_disable_unprepare_clks(dev);
-disable_hsic_regulator:
-	if (data->hsic_pad_regulator)
-		/* don't overwrite original ret (cf. EPROBE_DEFER) */
-		regulator_disable(data->hsic_pad_regulator);
+qos_remove_request:
 	if (pdata.flags & CI_HDRC_PMQOS)
 		cpu_latency_qos_remove_request(&data->pm_qos_req);
 	data->ci_pdev = NULL;
 err_put:
-	put_device(data->usbmisc_data->dev);
+	if (data->usbmisc_data)
+		put_device(data->usbmisc_data->dev);
 	return ret;
 }
 
@@ -556,10 +575,9 @@ static void ci_hdrc_imx_remove(struct platform_device *pdev)
 		clk_disable_unprepare(data->clk_wakeup);
 		if (data->plat_data->flags & CI_HDRC_PMQOS)
 			cpu_latency_qos_remove_request(&data->pm_qos_req);
-		if (data->hsic_pad_regulator)
-			regulator_disable(data->hsic_pad_regulator);
 	}
-	put_device(data->usbmisc_data->dev);
+	if (data->usbmisc_data)
+		put_device(data->usbmisc_data->dev);
 }
 
 static void ci_hdrc_imx_shutdown(struct platform_device *pdev)
diff --git a/drivers/usb/chipidea/udc.c b/drivers/usb/chipidea/udc.c
index fd6032874bf3..8f73bd5057a6 100644
--- a/drivers/usb/chipidea/udc.c
+++ b/drivers/usb/chipidea/udc.c
@@ -2362,6 +2362,10 @@ static void udc_suspend(struct ci_hdrc *ci)
 	 */
 	if (hw_read(ci, OP_ENDPTLISTADDR, ~0) == 0)
 		hw_write(ci, OP_ENDPTLISTADDR, ~0, ~0);
+
+	if (ci->gadget.connected &&
+	    (!ci->suspended || !device_may_wakeup(ci->dev)))
+		usb_gadget_disconnect(&ci->gadget);
 }
 
 static void udc_resume(struct ci_hdrc *ci, bool power_lost)
@@ -2372,6 +2376,9 @@ static void udc_resume(struct ci_hdrc *ci, bool power_lost)
 					OTGSC_BSVIS | OTGSC_BSVIE);
 		if (ci->vbus_active)
 			usb_gadget_vbus_disconnect(&ci->gadget);
+	} else if (ci->vbus_active && ci->driver &&
+		   !ci->gadget.connected) {
+		usb_gadget_connect(&ci->gadget);
 	}
 
 	/* Restore value 0 if it was set for power lost check */
diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
index 6b37d1c47fce..5a334e370f4d 100644
--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -371,7 +371,7 @@ static void acm_process_notification(struct acm *acm, unsigned char *buf)
 static void acm_ctrl_irq(struct urb *urb)
 {
 	struct acm *acm = urb->context;
-	struct usb_cdc_notification *dr = urb->transfer_buffer;
+	struct usb_cdc_notification *dr;
 	unsigned int current_size = urb->actual_length;
 	unsigned int expected_size, copy_size, alloc_size;
 	int retval;
@@ -398,14 +398,25 @@ static void acm_ctrl_irq(struct urb *urb)
 
 	usb_mark_last_busy(acm->dev);
 
-	if (acm->nb_index)
+	if (acm->nb_index == 0) {
+		/*
+		 * The first chunk of a message must contain at least the
+		 * notification header with the length field, otherwise we
+		 * can't get an expected_size.
+		 */
+		if (current_size < sizeof(struct usb_cdc_notification)) {
+			dev_dbg(&acm->control->dev, "urb too short\n");
+			goto exit;
+		}
+		dr = urb->transfer_buffer;
+	} else {
 		dr = (struct usb_cdc_notification *)acm->notification_buffer;
-
+	}
 	/* size = notification-header + (optional) data */
 	expected_size = sizeof(struct usb_cdc_notification) +
 					le16_to_cpu(dr->wLength);
 
-	if (current_size < expected_size) {
+	if (acm->nb_index != 0 || current_size < expected_size) {
 		/* notification is transmitted fragmented, reassemble */
 		if (acm->nb_size < expected_size) {
 			u8 *new_buffer;
@@ -1509,6 +1520,12 @@ skip_countries:
 			goto err_remove_files;
 	}
 
+	if (quirks & CLEAR_HALT_CONDITIONS) {
+		/* errors intentionally ignored */
+		usb_clear_halt(usb_dev, acm->in);
+		usb_clear_halt(usb_dev, acm->out);
+	}
+
 	tty_dev = tty_port_register_device(&acm->port, acm_tty_driver, minor,
 			&control_interface->dev);
 	if (IS_ERR(tty_dev)) {
@@ -1516,11 +1533,6 @@ skip_countries:
 		goto err_release_data_interface;
 	}
 
-	if (quirks & CLEAR_HALT_CONDITIONS) {
-		usb_clear_halt(usb_dev, acm->in);
-		usb_clear_halt(usb_dev, acm->out);
-	}
-
 	dev_info(&intf->dev, "ttyACM%d: USB ACM device\n", minor);
 
 	return 0;
@@ -1727,13 +1739,16 @@ static const struct usb_device_id acm_ids[] = {
 	{ USB_DEVICE(0x0870, 0x0001), /* Metricom GS Modem */
 	.driver_info = NO_UNION_NORMAL, /* has no union descriptor */
 	},
-	{ USB_DEVICE(0x045b, 0x023c),	/* Renesas USB Download mode */
+	{ USB_DEVICE(0x045b, 0x023c),	/* Renesas R-Car H3 USB Download mode */
+	.driver_info = DISABLE_ECHO,	/* Don't echo banner */
+	},
+	{ USB_DEVICE(0x045b, 0x0247),	/* Renesas R-Car D3 USB Download mode */
 	.driver_info = DISABLE_ECHO,	/* Don't echo banner */
 	},
-	{ USB_DEVICE(0x045b, 0x0248),	/* Renesas USB Download mode */
+	{ USB_DEVICE(0x045b, 0x0248),	/* Renesas R-Car M3-N USB Download mode */
 	.driver_info = DISABLE_ECHO,	/* Don't echo banner */
 	},
-	{ USB_DEVICE(0x045b, 0x024D),	/* Renesas USB Download mode */
+	{ USB_DEVICE(0x045b, 0x024D),	/* Renesas R-Car E3 USB Download mode */
 	.driver_info = DISABLE_ECHO,	/* Don't echo banner */
 	},
 	{ USB_DEVICE(0x0e8d, 0x0003), /* FIREFLY, MediaTek Inc; andrey.arapov@gmail.com */
diff --git a/drivers/usb/class/cdc-wdm.c b/drivers/usb/class/cdc-wdm.c
index 86ee39db013f..ecd6d1f39e49 100644
--- a/drivers/usb/class/cdc-wdm.c
+++ b/drivers/usb/class/cdc-wdm.c
@@ -92,7 +92,6 @@ struct wdm_device {
 	u16			wMaxCommand;
 	u16			wMaxPacketSize;
 	__le16			inum;
-	int			reslength;
 	int			length;
 	int			read;
 	int			count;
@@ -214,6 +213,11 @@ static void wdm_in_callback(struct urb *urb)
 	if (desc->rerr == 0 && status != -EPIPE)
 		desc->rerr = status;
 
+	if (length == 0) {
+		dev_dbg(&desc->intf->dev, "received ZLP\n");
+		goto skip_zlp;
+	}
+
 	if (length + desc->length > desc->wMaxCommand) {
 		/* The buffer would overflow */
 		set_bit(WDM_OVERFLOW, &desc->flags);
@@ -222,18 +226,18 @@ static void wdm_in_callback(struct urb *urb)
 		if (!test_bit(WDM_OVERFLOW, &desc->flags)) {
 			memmove(desc->ubuf + desc->length, desc->inbuf, length);
 			desc->length += length;
-			desc->reslength = length;
 		}
 	}
 skip_error:
 
 	if (desc->rerr) {
 		/*
-		 * Since there was an error, userspace may decide to not read
-		 * any data after poll'ing.
+		 * If there was a ZLP or an error, userspace may decide to not
+		 * read any data after poll'ing.
 		 * We should respond to further attempts from the device to send
 		 * data, so that we can get unstuck.
 		 */
+skip_zlp:
 		schedule_work(&desc->service_outs_intr);
 	} else {
 		set_bit(WDM_READ, &desc->flags);
@@ -585,15 +589,6 @@ retry:
 			goto retry;
 		}
 
-		if (!desc->reslength) { /* zero length read */
-			dev_dbg(&desc->intf->dev, "zero length - clearing WDM_READ\n");
-			clear_bit(WDM_READ, &desc->flags);
-			rv = service_outstanding_interrupt(desc);
-			spin_unlock_irq(&desc->iuspin);
-			if (rv < 0)
-				goto err;
-			goto retry;
-		}
 		cntr = desc->length;
 		spin_unlock_irq(&desc->iuspin);
 	}
@@ -726,7 +721,7 @@ static int wdm_open(struct inode *inode, struct file *file)
 		rv = -EBUSY;
 		goto out;
 	}
-
+	smp_rmb(); /* ordered against wdm_wwan_port_stop() */
 	rv = usb_autopm_get_interface(desc->intf);
 	if (rv < 0) {
 		dev_err(&desc->intf->dev, "Error autopm - %d\n", rv);
@@ -829,6 +824,7 @@ static struct usb_class_driver wdm_class = {
 static int wdm_wwan_port_start(struct wwan_port *port)
 {
 	struct wdm_device *desc = wwan_port_get_drvdata(port);
+	int rv;
 
 	/* The interface is both exposed via the WWAN framework and as a
 	 * legacy usbmisc chardev. If chardev is already open, just fail
@@ -848,7 +844,15 @@ static int wdm_wwan_port_start(struct wwan_port *port)
 	wwan_port_txon(port);
 
 	/* Start getting events */
-	return usb_submit_urb(desc->validity, GFP_KERNEL);
+	rv = usb_submit_urb(desc->validity, GFP_KERNEL);
+	if (rv < 0) {
+		wwan_port_txoff(port);
+		desc->manage_power(desc->intf, 0);
+		/* this must be last lest we race with chardev open */
+		clear_bit(WDM_WWAN_IN_USE, &desc->flags);
+	}
+
+	return rv;
 }
 
 static void wdm_wwan_port_stop(struct wwan_port *port)
@@ -859,8 +863,10 @@ static void wdm_wwan_port_stop(struct wwan_port *port)
 	poison_urbs(desc);
 	desc->manage_power(desc->intf, 0);
 	clear_bit(WDM_READ, &desc->flags);
-	clear_bit(WDM_WWAN_IN_USE, &desc->flags);
 	unpoison_urbs(desc);
+	smp_wmb(); /* ordered against wdm_open() */
+	/* this must be last lest we open a poisoned device */
+	clear_bit(WDM_WWAN_IN_USE, &desc->flags);
 }
 
 static void wdm_wwan_port_tx_complete(struct urb *urb)
@@ -868,7 +874,7 @@ static void wdm_wwan_port_tx_complete(struct urb *urb)
 	struct sk_buff *skb = urb->context;
 	struct wdm_device *desc = skb_shinfo(skb)->destructor_arg;
 
-	usb_autopm_put_interface(desc->intf);
+	usb_autopm_put_interface_async(desc->intf);
 	wwan_port_txon(desc->wwanp);
 	kfree_skb(skb);
 }
@@ -898,7 +904,7 @@ static int wdm_wwan_port_tx(struct wwan_port *port, struct sk_buff *skb)
 	req->bRequestType = (USB_DIR_OUT | USB_TYPE_CLASS | USB_RECIP_INTERFACE);
 	req->bRequest = USB_CDC_SEND_ENCAPSULATED_COMMAND;
 	req->wValue = 0;
-	req->wIndex = desc->inum;
+	req->wIndex = desc->inum; /* already converted */
 	req->wLength = cpu_to_le16(skb->len);
 
 	skb_shinfo(skb)->destructor_arg = desc;
@@ -1005,7 +1011,7 @@ static void service_interrupt_work(struct work_struct *work)
 
 	spin_lock_irq(&desc->iuspin);
 	service_outstanding_interrupt(desc);
-	if (!desc->resp_count) {
+	if (!desc->resp_count && (desc->length || desc->rerr)) {
 		set_bit(WDM_READ, &desc->flags);
 		wake_up(&desc->wait);
 	}
diff --git a/drivers/usb/class/usbtmc.c b/drivers/usb/class/usbtmc.c
index 34e46ef308ab..75de29725a45 100644
--- a/drivers/usb/class/usbtmc.c
+++ b/drivers/usb/class/usbtmc.c
@@ -482,6 +482,8 @@ static int usbtmc_get_stb(struct usbtmc_file_data *file_data, __u8 *stb)
 	u8 *buffer;
 	u8 tag;
 	int rv;
+	long wait_rv;
+	unsigned long expire;
 
 	dev_dbg(dev, "Enter ioctl_read_stb iin_ep_present: %d\n",
 		data->iin_ep_present);
@@ -511,16 +513,18 @@ static int usbtmc_get_stb(struct usbtmc_file_data *file_data, __u8 *stb)
 	}
 
 	if (data->iin_ep_present) {
-		rv = wait_event_interruptible_timeout(
+		expire = msecs_to_jiffies(file_data->timeout);
+		wait_rv = wait_event_interruptible_timeout(
 			data->waitq,
 			atomic_read(&data->iin_data_valid) != 0,
-			file_data->timeout);
-		if (rv < 0) {
-			dev_dbg(dev, "wait interrupted %d\n", rv);
+			expire);
+		if (wait_rv < 0) {
+			dev_dbg(dev, "wait interrupted %ld\n", wait_rv);
+			rv = wait_rv;
 			goto exit;
 		}
 
-		if (rv == 0) {
+		if (wait_rv == 0) {
 			dev_dbg(dev, "wait timed out\n");
 			rv = -ETIMEDOUT;
 			goto exit;
@@ -539,6 +543,8 @@ static int usbtmc_get_stb(struct usbtmc_file_data *file_data, __u8 *stb)
 
 	dev_dbg(dev, "stb:0x%02x received %d\n", (unsigned int)*stb, rv);
 
+	rv = 0;
+
  exit:
 	/* bump interrupt bTag */
 	data->iin_bTag += 1;
@@ -559,14 +565,15 @@ static int usbtmc488_ioctl_read_stb(struct usbtmc_file_data *file_data,
 
 	rv = usbtmc_get_stb(file_data, &stb);
 
-	if (rv > 0) {
-		srq_asserted = atomic_xchg(&file_data->srq_asserted,
-					srq_asserted);
-		if (srq_asserted)
-			stb |= 0x40; /* Set RQS bit */
+	if (rv < 0)
+		return rv;
+
+	srq_asserted = atomic_xchg(&file_data->srq_asserted, srq_asserted);
+	if (srq_asserted)
+		stb |= 0x40; /* Set RQS bit */
+
+	rv = put_user(stb, (__u8 __user *)arg);
 
-		rv = put_user(stb, (__u8 __user *)arg);
-	}
 	return rv;
 
 }
@@ -602,9 +609,9 @@ static int usbtmc488_ioctl_wait_srq(struct usbtmc_file_data *file_data,
 {
 	struct usbtmc_device_data *data = file_data->data;
 	struct device *dev = &data->intf->dev;
-	int rv;
 	u32 timeout;
 	unsigned long expire;
+	long wait_rv;
 
 	if (!data->iin_ep_present) {
 		dev_dbg(dev, "no interrupt endpoint present\n");
@@ -618,25 +625,24 @@ static int usbtmc488_ioctl_wait_srq(struct usbtmc_file_data *file_data,
 
 	mutex_unlock(&data->io_mutex);
 
-	rv = wait_event_interruptible_timeout(
-			data->waitq,
-			atomic_read(&file_data->srq_asserted) != 0 ||
-			atomic_read(&file_data->closing),
-			expire);
+	wait_rv = wait_event_interruptible_timeout(
+		data->waitq,
+		atomic_read(&file_data->srq_asserted) != 0 ||
+		atomic_read(&file_data->closing),
+		expire);
 
 	mutex_lock(&data->io_mutex);
 
 	/* Note! disconnect or close could be called in the meantime */
 	if (atomic_read(&file_data->closing) || data->zombie)
-		rv = -ENODEV;
+		return -ENODEV;
 
-	if (rv < 0) {
-		/* dev can be invalid now! */
-		pr_debug("%s - wait interrupted %d\n", __func__, rv);
-		return rv;
+	if (wait_rv < 0) {
+		dev_dbg(dev, "%s - wait interrupted %ld\n", __func__, wait_rv);
+		return wait_rv;
 	}
 
-	if (rv == 0) {
+	if (wait_rv == 0) {
 		dev_dbg(dev, "%s - wait timed out\n", __func__);
 		return -ETIMEDOUT;
 	}
@@ -830,6 +836,7 @@ static ssize_t usbtmc_generic_read(struct usbtmc_file_data *file_data,
 	unsigned long expire;
 	int bufcount = 1;
 	int again = 0;
+	long wait_rv;
 
 	/* mutex already locked */
 
@@ -942,19 +949,24 @@ static ssize_t usbtmc_generic_read(struct usbtmc_file_data *file_data,
 		if (!(flags & USBTMC_FLAG_ASYNC)) {
 			dev_dbg(dev, "%s: before wait time %lu\n",
 				__func__, expire);
-			retval = wait_event_interruptible_timeout(
+			wait_rv = wait_event_interruptible_timeout(
 				file_data->wait_bulk_in,
 				usbtmc_do_transfer(file_data),
 				expire);
 
-			dev_dbg(dev, "%s: wait returned %d\n",
-				__func__, retval);
+			dev_dbg(dev, "%s: wait returned %ld\n",
+				__func__, wait_rv);
+
+			if (wait_rv < 0) {
+				retval = wait_rv;
+				goto error;
+			}
 
-			if (retval <= 0) {
-				if (retval == 0)
-					retval = -ETIMEDOUT;
+			if (wait_rv == 0) {
+				retval = -ETIMEDOUT;
 				goto error;
 			}
+
 		}
 
 		urb = usb_get_from_anchor(&file_data->in_anchor);
@@ -1380,7 +1392,10 @@ static ssize_t usbtmc_read(struct file *filp, char __user *buf,
 	if (!buffer)
 		return -ENOMEM;
 
-	mutex_lock(&data->io_mutex);
+	retval = mutex_lock_interruptible(&data->io_mutex);
+	if (retval < 0)
+		goto exit_nolock;
+
 	if (data->zombie) {
 		retval = -ENODEV;
 		goto exit;
@@ -1503,6 +1518,7 @@ static ssize_t usbtmc_read(struct file *filp, char __user *buf,
 
 exit:
 	mutex_unlock(&data->io_mutex);
+exit_nolock:
 	kfree(buffer);
 	return retval;
 }
@@ -2186,7 +2202,7 @@ static long usbtmc_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 
 	case USBTMC_IOCTL_GET_STB:
 		retval = usbtmc_get_stb(file_data, &tmp_byte);
-		if (retval > 0)
+		if (!retval)
 			retval = put_user(tmp_byte, (__u8 __user *)arg);
 		break;
 
diff --git a/drivers/usb/common/usb-conn-gpio.c b/drivers/usb/common/usb-conn-gpio.c
index 501e8bc9738e..1096a884c8d7 100644
--- a/drivers/usb/common/usb-conn-gpio.c
+++ b/drivers/usb/common/usb-conn-gpio.c
@@ -20,6 +20,9 @@
 #include <linux/power_supply.h>
 #include <linux/regulator/consumer.h>
 #include <linux/usb/role.h>
+#include <linux/idr.h>
+
+static DEFINE_IDA(usb_conn_ida);
 
 #define USB_GPIO_DEB_MS		20	/* ms */
 #define USB_GPIO_DEB_US		((USB_GPIO_DEB_MS) * 1000)	/* us */
@@ -29,6 +32,7 @@
 
 struct usb_conn_info {
 	struct device *dev;
+	int conn_id; /* store the IDA-allocated ID */
 	struct usb_role_switch *role_sw;
 	enum usb_role last_role;
 	struct regulator *vbus;
@@ -160,7 +164,17 @@ static int usb_conn_psy_register(struct usb_conn_info *info)
 		.of_node = dev->of_node,
 	};
 
-	desc->name = "usb-charger";
+	info->conn_id = ida_alloc(&usb_conn_ida, GFP_KERNEL);
+	if (info->conn_id < 0)
+		return info->conn_id;
+
+	desc->name = devm_kasprintf(dev, GFP_KERNEL, "usb-charger-%d",
+				    info->conn_id);
+	if (!desc->name) {
+		ida_free(&usb_conn_ida, info->conn_id);
+		return -ENOMEM;
+	}
+
 	desc->properties = usb_charger_properties;
 	desc->num_properties = ARRAY_SIZE(usb_charger_properties);
 	desc->get_property = usb_charger_get_property;
@@ -168,8 +182,10 @@ static int usb_conn_psy_register(struct usb_conn_info *info)
 	cfg.drv_data = info;
 
 	info->charger = devm_power_supply_register(dev, desc, &cfg);
-	if (IS_ERR(info->charger))
-		dev_err(dev, "Unable to register charger\n");
+	if (IS_ERR(info->charger)) {
+		dev_err(dev, "Unable to register charger %d\n", info->conn_id);
+		ida_free(&usb_conn_ida, info->conn_id);
+	}
 
 	return PTR_ERR_OR_ZERO(info->charger);
 }
@@ -277,6 +293,9 @@ static void usb_conn_remove(struct platform_device *pdev)
 
 	cancel_delayed_work_sync(&info->dw_det);
 
+	if (info->charger)
+		ida_free(&usb_conn_ida, info->conn_id);
+
 	if (info->last_role == USB_ROLE_HOST && info->vbus)
 		regulator_disable(info->vbus);
 
diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c
index 880d52c0949d..9565d14d7c07 100644
--- a/drivers/usb/core/config.c
+++ b/drivers/usb/core/config.c
@@ -81,8 +81,14 @@ static void usb_parse_ss_endpoint_companion(struct device *ddev, int cfgno,
 	 */
 	desc = (struct usb_ss_ep_comp_descriptor *) buffer;
 
-	if (desc->bDescriptorType != USB_DT_SS_ENDPOINT_COMP ||
-			size < USB_DT_SS_EP_COMP_SIZE) {
+	if (size < USB_DT_SS_EP_COMP_SIZE) {
+		dev_notice(ddev,
+			   "invalid SuperSpeed endpoint companion descriptor "
+			   "of length %d, skipping\n", size);
+		return;
+	}
+
+	if (desc->bDescriptorType != USB_DT_SS_ENDPOINT_COMP) {
 		dev_notice(ddev, "No SuperSpeed endpoint companion for config %d "
 				" interface %d altsetting %d ep %d: "
 				"using minimum values\n",
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index 21ac9b464696..090b3a757112 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -67,6 +67,12 @@
  */
 #define USB_SHORT_SET_ADDRESS_REQ_TIMEOUT	500  /* ms */
 
+/*
+ * Give SS hubs 200ms time after wake to train downstream links before
+ * assuming no port activity and allowing hub to runtime suspend back.
+ */
+#define USB_SS_PORT_U0_WAKE_TIME	200  /* ms */
+
 /* Protect struct usb_device->state and ->children members
  * Note: Both are also protected by ->dev.sem, except that ->state can
  * change to USB_STATE_NOTATTACHED even when the semaphore isn't held. */
@@ -1094,6 +1100,7 @@ static void hub_activate(struct usb_hub *hub, enum hub_activation_type type)
 			goto init2;
 		goto init3;
 	}
+
 	hub_get(hub);
 
 	/* The superspeed hub except for root hub has to use Hub Depth
@@ -1342,6 +1349,17 @@ static void hub_activate(struct usb_hub *hub, enum hub_activation_type type)
 		device_unlock(&hdev->dev);
 	}
 
+	if (type == HUB_RESUME && hub_is_superspeed(hub->hdev)) {
+		/* give usb3 downstream links training time after hub resume */
+		usb_autopm_get_interface_no_resume(
+			to_usb_interface(hub->intfdev));
+
+		queue_delayed_work(system_power_efficient_wq,
+				   &hub->post_resume_work,
+				   msecs_to_jiffies(USB_SS_PORT_U0_WAKE_TIME));
+		return;
+	}
+
 	hub_put(hub);
 }
 
@@ -1360,6 +1378,14 @@ static void hub_init_func3(struct work_struct *ws)
 	hub_activate(hub, HUB_INIT3);
 }
 
+static void hub_post_resume(struct work_struct *ws)
+{
+	struct usb_hub *hub = container_of(ws, struct usb_hub, post_resume_work.work);
+
+	usb_autopm_put_interface_async(to_usb_interface(hub->intfdev));
+	hub_put(hub);
+}
+
 enum hub_quiescing_type {
 	HUB_DISCONNECT, HUB_PRE_RESET, HUB_SUSPEND
 };
@@ -1385,6 +1411,7 @@ static void hub_quiesce(struct usb_hub *hub, enum hub_quiescing_type type)
 
 	/* Stop hub_wq and related activity */
 	del_timer_sync(&hub->irq_urb_retry);
+	flush_delayed_work(&hub->post_resume_work);
 	usb_kill_urb(hub->urb);
 	if (hub->has_indicators)
 		cancel_delayed_work_sync(&hub->leds);
@@ -1848,6 +1875,17 @@ static int hub_probe(struct usb_interface *intf, const struct usb_device_id *id)
 	hdev = interface_to_usbdev(intf);
 
 	/*
+	 * The USB 2.0 spec prohibits hubs from having more than one
+	 * configuration or interface, and we rely on this prohibition.
+	 * Refuse to accept a device that violates it.
+	 */
+	if (hdev->descriptor.bNumConfigurations > 1 ||
+			hdev->actconfig->desc.bNumInterfaces > 1) {
+		dev_err(&intf->dev, "Invalid hub with more than one config or interface\n");
+		return -EINVAL;
+	}
+
+	/*
 	 * Set default autosuspend delay as 0 to speedup bus suspend,
 	 * based on the below considerations:
 	 *
@@ -1932,6 +1970,7 @@ static int hub_probe(struct usb_interface *intf, const struct usb_device_id *id)
 	hub->hdev = hdev;
 	INIT_DELAYED_WORK(&hub->leds, led_work);
 	INIT_DELAYED_WORK(&hub->init_work, NULL);
+	INIT_DELAYED_WORK(&hub->post_resume_work, hub_post_resume);
 	INIT_WORK(&hub->events, hub_event);
 	INIT_LIST_HEAD(&hub->onboard_devs);
 	spin_lock_init(&hub->irq_urb_lock);
@@ -2325,6 +2364,9 @@ void usb_disconnect(struct usb_device **pdev)
 	usb_remove_ep_devs(&udev->ep0);
 	usb_unlock_device(udev);
 
+	if (udev->usb4_link)
+		device_link_del(udev->usb4_link);
+
 	/* Unregister the device.  The device driver is responsible
 	 * for de-configuring the device and invoking the remove-device
 	 * notifier chain (used by usbfs and possibly others).
@@ -4698,7 +4740,6 @@ void usb_ep0_reinit(struct usb_device *udev)
 EXPORT_SYMBOL_GPL(usb_ep0_reinit);
 
 #define usb_sndaddr0pipe()	(PIPE_CONTROL << 30)
-#define usb_rcvaddr0pipe()	((PIPE_CONTROL << 30) | USB_DIR_IN)
 
 static int hub_set_address(struct usb_device *udev, int devnum)
 {
@@ -4804,7 +4845,7 @@ static int get_bMaxPacketSize0(struct usb_device *udev,
 	for (i = 0; i < GET_MAXPACKET0_TRIES; ++i) {
 		/* Start with invalid values in case the transfer fails */
 		buf->bDescriptorType = buf->bMaxPacketSize0 = 0;
-		rc = usb_control_msg(udev, usb_rcvaddr0pipe(),
+		rc = usb_control_msg(udev, usb_rcvctrlpipe(udev, 0),
 				USB_REQ_GET_DESCRIPTOR, USB_DIR_IN,
 				USB_DT_DEVICE << 8, 0,
 				buf, size,
@@ -5708,6 +5749,7 @@ static void port_event(struct usb_hub *hub, int port1)
 	struct usb_device *hdev = hub->hdev;
 	u16 portstatus, portchange;
 	int i = 0;
+	int err;
 
 	connect_change = test_bit(port1, hub->change_bits);
 	clear_bit(port1, hub->event_bits);
@@ -5804,8 +5846,11 @@ static void port_event(struct usb_hub *hub, int port1)
 		} else if (!udev || !(portstatus & USB_PORT_STAT_CONNECTION)
 				|| udev->state == USB_STATE_NOTATTACHED) {
 			dev_dbg(&port_dev->dev, "do warm reset, port only\n");
-			if (hub_port_reset(hub, port1, NULL,
-					HUB_BH_RESET_TIME, true) < 0)
+			err = hub_port_reset(hub, port1, NULL,
+					     HUB_BH_RESET_TIME, true);
+			if (!udev && err == -ENOTCONN)
+				connect_change = 0;
+			else if (err < 0)
 				hub_port_disable(hub, port1, 1);
 		} else {
 			dev_dbg(&port_dev->dev, "do warm reset, full device\n");
@@ -6056,6 +6101,36 @@ void usb_hub_cleanup(void)
 } /* usb_hub_cleanup() */
 
 /**
+ * hub_hc_release_resources - clear resources used by host controller
+ * @udev: pointer to device being released
+ *
+ * Context: task context, might sleep
+ *
+ * Function releases the host controller resources in correct order before
+ * making any operation on resuming usb device. The host controller resources
+ * allocated for devices in tree should be released starting from the last
+ * usb device in tree toward the root hub. This function is used only during
+ * resuming device when usb device require reinitialization – that is, when
+ * flag udev->reset_resume is set.
+ *
+ * This call is synchronous, and may not be used in an interrupt context.
+ */
+static void hub_hc_release_resources(struct usb_device *udev)
+{
+	struct usb_hub *hub = usb_hub_to_struct_hub(udev);
+	struct usb_hcd *hcd = bus_to_hcd(udev->bus);
+	int i;
+
+	/* Release up resources for all children before this device */
+	for (i = 0; i < udev->maxchild; i++)
+		if (hub->ports[i]->child)
+			hub_hc_release_resources(hub->ports[i]->child);
+
+	if (hcd->driver->reset_device)
+		hcd->driver->reset_device(hcd, udev);
+}
+
+/**
  * usb_reset_and_verify_device - perform a USB port reset to reinitialize a device
  * @udev: device to reset (not in SUSPENDED or NOTATTACHED state)
  *
@@ -6095,6 +6170,7 @@ static int usb_reset_and_verify_device(struct usb_device *udev)
 	struct usb_hub			*parent_hub;
 	struct usb_hcd			*hcd = bus_to_hcd(udev->bus);
 	struct usb_device_descriptor	descriptor;
+	struct usb_interface		*intf;
 	struct usb_host_bos		*bos;
 	int				i, j, ret = 0;
 	int				port1 = udev->portnum;
@@ -6119,6 +6195,9 @@ static int usb_reset_and_verify_device(struct usb_device *udev)
 	bos = udev->bos;
 	udev->bos = NULL;
 
+	if (udev->reset_resume)
+		hub_hc_release_resources(udev);
+
 	mutex_lock(hcd->address0_mutex);
 
 	for (i = 0; i < PORT_INIT_TRIES; ++i) {
@@ -6149,6 +6228,18 @@ static int usb_reset_and_verify_device(struct usb_device *udev)
 	if (!udev->actconfig)
 		goto done;
 
+	/*
+	 * Some devices can't handle setting default altsetting 0 with a
+	 * Set-Interface request. Disable host-side endpoints of those
+	 * interfaces here. Enable and reset them back after host has set
+	 * its internal endpoint structures during usb_hcd_alloc_bandwith()
+	 */
+	for (i = 0; i < udev->actconfig->desc.bNumInterfaces; i++) {
+		intf = udev->actconfig->interface[i];
+		if (intf->cur_altsetting->desc.bAlternateSetting == 0)
+			usb_disable_interface(udev, intf, true);
+	}
+
 	mutex_lock(hcd->bandwidth_mutex);
 	ret = usb_hcd_alloc_bandwidth(udev, udev->actconfig, NULL, NULL);
 	if (ret < 0) {
@@ -6180,12 +6271,11 @@ static int usb_reset_and_verify_device(struct usb_device *udev)
 	 */
 	for (i = 0; i < udev->actconfig->desc.bNumInterfaces; i++) {
 		struct usb_host_config *config = udev->actconfig;
-		struct usb_interface *intf = config->interface[i];
 		struct usb_interface_descriptor *desc;
 
+		intf = config->interface[i];
 		desc = &intf->cur_altsetting->desc;
 		if (desc->bAlternateSetting == 0) {
-			usb_disable_interface(udev, intf, true);
 			usb_enable_interface(udev, intf, true);
 			ret = 0;
 		} else {
diff --git a/drivers/usb/core/hub.h b/drivers/usb/core/hub.h
index e6ae73f8a95d..9ebc5ef54a32 100644
--- a/drivers/usb/core/hub.h
+++ b/drivers/usb/core/hub.h
@@ -70,6 +70,7 @@ struct usb_hub {
 	u8			indicator[USB_MAXCHILDREN];
 	struct delayed_work	leds;
 	struct delayed_work	init_work;
+	struct delayed_work	post_resume_work;
 	struct work_struct      events;
 	spinlock_t		irq_urb_lock;
 	struct timer_list	irq_urb_retry;
diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index 13171454f959..46db600fdd82 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -227,7 +227,8 @@ static const struct usb_device_id usb_quirk_list[] = {
 	{ USB_DEVICE(0x046a, 0x0023), .driver_info = USB_QUIRK_RESET_RESUME },
 
 	/* Logitech HD Webcam C270 */
-	{ USB_DEVICE(0x046d, 0x0825), .driver_info = USB_QUIRK_RESET_RESUME },
+	{ USB_DEVICE(0x046d, 0x0825), .driver_info = USB_QUIRK_RESET_RESUME |
+		USB_QUIRK_NO_LPM},
 
 	/* Logitech HD Pro Webcams C920, C920-C, C922, C925e and C930e */
 	{ USB_DEVICE(0x046d, 0x082d), .driver_info = USB_QUIRK_DELAY_INIT },
@@ -341,6 +342,10 @@ static const struct usb_device_id usb_quirk_list[] = {
 	{ USB_DEVICE(0x0638, 0x0a13), .driver_info =
 	  USB_QUIRK_STRING_FETCH_255 },
 
+	/* Prolific Single-LUN Mass Storage Card Reader */
+	{ USB_DEVICE(0x067b, 0x2731), .driver_info = USB_QUIRK_DELAY_INIT |
+	  USB_QUIRK_NO_LPM },
+
 	/* Saitek Cyborg Gold Joystick */
 	{ USB_DEVICE(0x06a3, 0x0006), .driver_info =
 			USB_QUIRK_CONFIG_INTF_STRINGS },
@@ -365,6 +370,12 @@ static const struct usb_device_id usb_quirk_list[] = {
 	{ USB_DEVICE(0x0781, 0x5583), .driver_info = USB_QUIRK_NO_LPM },
 	{ USB_DEVICE(0x0781, 0x5591), .driver_info = USB_QUIRK_NO_LPM },
 
+	/* SanDisk Corp. SanDisk 3.2Gen1 */
+	{ USB_DEVICE(0x0781, 0x55a3), .driver_info = USB_QUIRK_DELAY_INIT },
+
+	/* SanDisk Extreme 55AE */
+	{ USB_DEVICE(0x0781, 0x55ae), .driver_info = USB_QUIRK_NO_LPM },
+
 	/* Realforce 87U Keyboard */
 	{ USB_DEVICE(0x0853, 0x011b), .driver_info = USB_QUIRK_NO_LPM },
 
@@ -379,6 +390,9 @@ static const struct usb_device_id usb_quirk_list[] = {
 	{ USB_DEVICE(0x0904, 0x6103), .driver_info =
 			USB_QUIRK_LINEAR_FRAME_INTR_BINTERVAL },
 
+	/* Silicon Motion Flash Drive */
+	{ USB_DEVICE(0x090c, 0x1000), .driver_info = USB_QUIRK_DELAY_INIT },
+
 	/* Sound Devices USBPre2 */
 	{ USB_DEVICE(0x0926, 0x0202), .driver_info =
 			USB_QUIRK_ENDPOINT_IGNORE },
@@ -432,6 +446,9 @@ static const struct usb_device_id usb_quirk_list[] = {
 	{ USB_DEVICE(0x0c45, 0x7056), .driver_info =
 			USB_QUIRK_IGNORE_REMOTE_WAKEUP },
 
+	/* Sony Xperia XZ1 Compact (lilac) smartphone in fastboot mode */
+	{ USB_DEVICE(0x0fce, 0x0dde), .driver_info = USB_QUIRK_NO_LPM },
+
 	/* Action Semiconductor flash disk */
 	{ USB_DEVICE(0x10d6, 0x2200), .driver_info =
 			USB_QUIRK_STRING_FETCH_255 },
@@ -522,10 +539,16 @@ static const struct usb_device_id usb_quirk_list[] = {
 	/* Blackmagic Design UltraStudio SDI */
 	{ USB_DEVICE(0x1edb, 0xbd4f), .driver_info = USB_QUIRK_NO_LPM },
 
+	/* Teclast disk */
+	{ USB_DEVICE(0x1f75, 0x0917), .driver_info = USB_QUIRK_NO_LPM },
+
 	/* Hauppauge HVR-950q */
 	{ USB_DEVICE(0x2040, 0x7200), .driver_info =
 			USB_QUIRK_CONFIG_INTF_STRINGS },
 
+	/* VLI disk */
+	{ USB_DEVICE(0x2109, 0x0711), .driver_info = USB_QUIRK_NO_LPM },
+
 	/* Raydium Touchscreen */
 	{ USB_DEVICE(0x2386, 0x3114), .driver_info = USB_QUIRK_NO_LPM },
 
diff --git a/drivers/usb/core/urb.c b/drivers/usb/core/urb.c
index 7576920e2d5a..9f202f575cec 100644
--- a/drivers/usb/core/urb.c
+++ b/drivers/usb/core/urb.c
@@ -500,7 +500,7 @@ int usb_submit_urb(struct urb *urb, gfp_t mem_flags)
 
 	/* Check that the pipe's type matches the endpoint's type */
 	if (usb_pipe_type_check(urb->dev, urb->pipe))
-		dev_WARN(&dev->dev, "BOGUS urb xfer, pipe %x != type %x\n",
+		dev_warn_once(&dev->dev, "BOGUS urb xfer, pipe %x != type %x\n",
 			usb_pipetype(urb->pipe), pipetypes[xfertype]);
 
 	/* Check against a simple/standard policy */
diff --git a/drivers/usb/core/usb-acpi.c b/drivers/usb/core/usb-acpi.c
index 03c22114214b..3bc68534dbcd 100644
--- a/drivers/usb/core/usb-acpi.c
+++ b/drivers/usb/core/usb-acpi.c
@@ -157,7 +157,7 @@ EXPORT_SYMBOL_GPL(usb_acpi_set_power_state);
  */
 static int usb_acpi_add_usb4_devlink(struct usb_device *udev)
 {
-	const struct device_link *link;
+	struct device_link *link;
 	struct usb_port *port_dev;
 	struct usb_hub *hub;
 
@@ -165,6 +165,8 @@ static int usb_acpi_add_usb4_devlink(struct usb_device *udev)
 		return 0;
 
 	hub = usb_hub_to_struct_hub(udev->parent);
+	if (!hub)
+		return 0;
 	port_dev = hub->ports[udev->portnum - 1];
 
 	struct fwnode_handle *nhi_fwnode __free(fwnode_handle) =
@@ -186,6 +188,8 @@ static int usb_acpi_add_usb4_devlink(struct usb_device *udev)
 	dev_dbg(&port_dev->dev, "Created device link from %s to %s\n",
 		dev_name(&port_dev->child->dev), dev_name(nhi_fwnode->dev));
 
+	udev->usb4_link = link;
+
 	return 0;
 }
 
diff --git a/drivers/usb/core/usb.c b/drivers/usb/core/usb.c
index 0b4685aad2d5..118fa4c93a79 100644
--- a/drivers/usb/core/usb.c
+++ b/drivers/usb/core/usb.c
@@ -695,15 +695,16 @@ struct usb_device *usb_alloc_dev(struct usb_device *parent,
 		device_set_of_node_from_dev(&dev->dev, bus->sysdev);
 		dev_set_name(&dev->dev, "usb%d", bus->busnum);
 	} else {
+		int n;
+
 		/* match any labeling on the hubs; it's one-based */
 		if (parent->devpath[0] == '0') {
-			snprintf(dev->devpath, sizeof dev->devpath,
-				"%d", port1);
+			n = snprintf(dev->devpath, sizeof(dev->devpath), "%d", port1);
 			/* Root ports are not counted in route string */
 			dev->route = 0;
 		} else {
-			snprintf(dev->devpath, sizeof dev->devpath,
-				"%s.%d", parent->devpath, port1);
+			n = snprintf(dev->devpath, sizeof(dev->devpath), "%s.%d",
+				     parent->devpath, port1);
 			/* Route string assumes hubs have less than 16 ports */
 			if (port1 < 15)
 				dev->route = parent->route +
@@ -712,6 +713,11 @@ struct usb_device *usb_alloc_dev(struct usb_device *parent,
 				dev->route = parent->route +
 					(15 << ((parent->level - 1)*4));
 		}
+		if (n >= sizeof(dev->devpath)) {
+			usb_put_hcd(bus_to_hcd(bus));
+			usb_put_dev(dev);
+			return NULL;
+		}
 
 		dev->dev.parent = &parent->dev;
 		dev_set_name(&dev->dev, "%d-%s", bus->busnum, dev->devpath);
diff --git a/drivers/usb/dwc2/gadget.c b/drivers/usb/dwc2/gadget.c
index e7bf9cc635be..834fc02610a2 100644
--- a/drivers/usb/dwc2/gadget.c
+++ b/drivers/usb/dwc2/gadget.c
@@ -4604,6 +4604,12 @@ static int dwc2_hsotg_udc_stop(struct usb_gadget *gadget)
 	if (!hsotg)
 		return -ENODEV;
 
+	/* Exit clock gating when driver is stopped. */
+	if (hsotg->params.power_down == DWC2_POWER_DOWN_PARAM_NONE &&
+	    hsotg->bus_suspended && !hsotg->params.no_clock_gating) {
+		dwc2_gadget_exit_clock_gating(hsotg, 0);
+	}
+
 	/* all endpoints should be shutdown */
 	for (ep = 1; ep < hsotg->num_of_eps; ep++) {
 		if (hsotg->eps_in[ep])
@@ -4615,6 +4621,7 @@ static int dwc2_hsotg_udc_stop(struct usb_gadget *gadget)
 	spin_lock_irqsave(&hsotg->lock, flags);
 
 	hsotg->driver = NULL;
+	hsotg->gadget.dev.of_node = NULL;
 	hsotg->gadget.speed = USB_SPEED_UNKNOWN;
 	hsotg->enabled = 0;
 
@@ -5345,20 +5352,34 @@ int dwc2_gadget_enter_hibernation(struct dwc2_hsotg *hsotg)
 	if (gusbcfg & GUSBCFG_ULPI_UTMI_SEL) {
 		/* ULPI interface */
 		gpwrdn |= GPWRDN_ULPI_LATCH_EN_DURING_HIB_ENTRY;
-	}
-	dwc2_writel(hsotg, gpwrdn, GPWRDN);
-	udelay(10);
+		dwc2_writel(hsotg, gpwrdn, GPWRDN);
+		udelay(10);
 
-	/* Suspend the Phy Clock */
-	pcgcctl = dwc2_readl(hsotg, PCGCTL);
-	pcgcctl |= PCGCTL_STOPPCLK;
-	dwc2_writel(hsotg, pcgcctl, PCGCTL);
-	udelay(10);
+		/* Suspend the Phy Clock */
+		pcgcctl = dwc2_readl(hsotg, PCGCTL);
+		pcgcctl |= PCGCTL_STOPPCLK;
+		dwc2_writel(hsotg, pcgcctl, PCGCTL);
+		udelay(10);
 
-	gpwrdn = dwc2_readl(hsotg, GPWRDN);
-	gpwrdn |= GPWRDN_PMUACTV;
-	dwc2_writel(hsotg, gpwrdn, GPWRDN);
-	udelay(10);
+		gpwrdn = dwc2_readl(hsotg, GPWRDN);
+		gpwrdn |= GPWRDN_PMUACTV;
+		dwc2_writel(hsotg, gpwrdn, GPWRDN);
+		udelay(10);
+	} else {
+		/* UTMI+ Interface */
+		dwc2_writel(hsotg, gpwrdn, GPWRDN);
+		udelay(10);
+
+		gpwrdn = dwc2_readl(hsotg, GPWRDN);
+		gpwrdn |= GPWRDN_PMUACTV;
+		dwc2_writel(hsotg, gpwrdn, GPWRDN);
+		udelay(10);
+
+		pcgcctl = dwc2_readl(hsotg, PCGCTL);
+		pcgcctl |= PCGCTL_STOPPCLK;
+		dwc2_writel(hsotg, pcgcctl, PCGCTL);
+		udelay(10);
+	}
 
 	/* Set flag to indicate that we are in hibernation */
 	hsotg->hibernated = 1;
diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c
index 98114c2827c0..f4209726f8ec 100644
--- a/drivers/usb/dwc3/core.c
+++ b/drivers/usb/dwc3/core.c
@@ -131,11 +131,24 @@ void dwc3_enable_susphy(struct dwc3 *dwc, bool enable)
 	}
 }
 
-void dwc3_set_prtcap(struct dwc3 *dwc, u32 mode)
+void dwc3_set_prtcap(struct dwc3 *dwc, u32 mode, bool ignore_susphy)
 {
+	unsigned int hw_mode;
 	u32 reg;
 
 	reg = dwc3_readl(dwc->regs, DWC3_GCTL);
+
+	 /*
+	  * For DRD controllers, GUSB3PIPECTL.SUSPENDENABLE and
+	  * GUSB2PHYCFG.SUSPHY should be cleared during mode switching,
+	  * and they can be set after core initialization.
+	  */
+	hw_mode = DWC3_GHWPARAMS0_MODE(dwc->hwparams.hwparams0);
+	if (hw_mode == DWC3_GHWPARAMS0_MODE_DRD && !ignore_susphy) {
+		if (DWC3_GCTL_PRTCAP(reg) != mode)
+			dwc3_enable_susphy(dwc, false);
+	}
+
 	reg &= ~(DWC3_GCTL_PRTCAPDIR(DWC3_GCTL_PRTCAP_OTG));
 	reg |= DWC3_GCTL_PRTCAPDIR(mode);
 	dwc3_writel(dwc->regs, DWC3_GCTL, reg);
@@ -216,7 +229,7 @@ static void __dwc3_set_mode(struct work_struct *work)
 
 	spin_lock_irqsave(&dwc->lock, flags);
 
-	dwc3_set_prtcap(dwc, desired_dr_role);
+	dwc3_set_prtcap(dwc, desired_dr_role, false);
 
 	spin_unlock_irqrestore(&dwc->lock, flags);
 
@@ -658,16 +671,7 @@ static int dwc3_ss_phy_setup(struct dwc3 *dwc, int index)
 	 */
 	reg &= ~DWC3_GUSB3PIPECTL_UX_EXIT_PX;
 
-	/*
-	 * Above DWC_usb3.0 1.94a, it is recommended to set
-	 * DWC3_GUSB3PIPECTL_SUSPHY to '0' during coreConsultant configuration.
-	 * So default value will be '0' when the core is reset. Application
-	 * needs to set it to '1' after the core initialization is completed.
-	 *
-	 * Similarly for DRD controllers, GUSB3PIPECTL.SUSPENDENABLE must be
-	 * cleared after power-on reset, and it can be set after core
-	 * initialization.
-	 */
+	/* Ensure the GUSB3PIPECTL.SUSPENDENABLE is cleared prior to phy init. */
 	reg &= ~DWC3_GUSB3PIPECTL_SUSPHY;
 
 	if (dwc->u2ss_inp3_quirk)
@@ -747,15 +751,7 @@ static int dwc3_hs_phy_setup(struct dwc3 *dwc, int index)
 		break;
 	}
 
-	/*
-	 * Above DWC_usb3.0 1.94a, it is recommended to set
-	 * DWC3_GUSB2PHYCFG_SUSPHY to '0' during coreConsultant configuration.
-	 * So default value will be '0' when the core is reset. Application
-	 * needs to set it to '1' after the core initialization is completed.
-	 *
-	 * Similarly for DRD controllers, GUSB2PHYCFG.SUSPHY must be cleared
-	 * after power-on reset, and it can be set after core initialization.
-	 */
+	/* Ensure the GUSB2PHYCFG.SUSPHY is cleared prior to phy init. */
 	reg &= ~DWC3_GUSB2PHYCFG_SUSPHY;
 
 	if (dwc->dis_enblslpm_quirk)
@@ -830,6 +826,25 @@ static int dwc3_phy_init(struct dwc3 *dwc)
 			goto err_exit_usb3_phy;
 	}
 
+	/*
+	 * Above DWC_usb3.0 1.94a, it is recommended to set
+	 * DWC3_GUSB3PIPECTL_SUSPHY and DWC3_GUSB2PHYCFG_SUSPHY to '0' during
+	 * coreConsultant configuration. So default value will be '0' when the
+	 * core is reset. Application needs to set it to '1' after the core
+	 * initialization is completed.
+	 *
+	 * Certain phy requires to be in P0 power state during initialization.
+	 * Make sure GUSB3PIPECTL.SUSPENDENABLE and GUSB2PHYCFG.SUSPHY are clear
+	 * prior to phy init to maintain in the P0 state.
+	 *
+	 * After phy initialization, some phy operations can only be executed
+	 * while in lower P states. Ensure GUSB3PIPECTL.SUSPENDENABLE and
+	 * GUSB2PHYCFG.SUSPHY are set soon after initialization to avoid
+	 * blocking phy ops.
+	 */
+	if (!DWC3_VER_IS_WITHIN(DWC3, ANY, 194A))
+		dwc3_enable_susphy(dwc, true);
+
 	return 0;
 
 err_exit_usb3_phy:
@@ -1564,7 +1579,7 @@ static int dwc3_core_init_mode(struct dwc3 *dwc)
 
 	switch (dwc->dr_mode) {
 	case USB_DR_MODE_PERIPHERAL:
-		dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_DEVICE);
+		dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_DEVICE, false);
 
 		if (dwc->usb2_phy)
 			otg_set_vbus(dwc->usb2_phy->otg, false);
@@ -1576,7 +1591,7 @@ static int dwc3_core_init_mode(struct dwc3 *dwc)
 			return dev_err_probe(dev, ret, "failed to initialize gadget\n");
 		break;
 	case USB_DR_MODE_HOST:
-		dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_HOST);
+		dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_HOST, false);
 
 		if (dwc->usb2_phy)
 			otg_set_vbus(dwc->usb2_phy->otg, true);
@@ -1621,7 +1636,7 @@ static void dwc3_core_exit_mode(struct dwc3 *dwc)
 	}
 
 	/* de-assert DRVVBUS for HOST and OTG mode */
-	dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_DEVICE);
+	dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_DEVICE, true);
 }
 
 static void dwc3_get_software_properties(struct dwc3 *dwc)
@@ -1660,8 +1675,6 @@ static void dwc3_get_properties(struct dwc3 *dwc)
 	u8			tx_thr_num_pkt_prd = 0;
 	u8			tx_max_burst_prd = 0;
 	u8			tx_fifo_resize_max_num;
-	const char		*usb_psy_name;
-	int			ret;
 
 	/* default to highest possible threshold */
 	lpm_nyet_threshold = 0xf;
@@ -1696,13 +1709,6 @@ static void dwc3_get_properties(struct dwc3 *dwc)
 
 	dwc->sys_wakeup = device_may_wakeup(dwc->sysdev);
 
-	ret = device_property_read_string(dev, "usb-psy-name", &usb_psy_name);
-	if (ret >= 0) {
-		dwc->usb_psy = power_supply_get_by_name(usb_psy_name);
-		if (!dwc->usb_psy)
-			dev_err(dev, "couldn't get usb power supply\n");
-	}
-
 	dwc->has_lpm_erratum = device_property_read_bool(dev,
 				"snps,has-lpm-erratum");
 	device_property_read_u8(dev, "snps,lpm-nyet-threshold",
@@ -1820,8 +1826,6 @@ static void dwc3_get_properties(struct dwc3 *dwc)
 	dwc->tx_thr_num_pkt_prd = tx_thr_num_pkt_prd;
 	dwc->tx_max_burst_prd = tx_max_burst_prd;
 
-	dwc->imod_interval = 0;
-
 	dwc->tx_fifo_resize_max_num = tx_fifo_resize_max_num;
 }
 
@@ -1839,21 +1843,19 @@ static void dwc3_check_params(struct dwc3 *dwc)
 	unsigned int hwparam_gen =
 		DWC3_GHWPARAMS3_SSPHY_IFC(dwc->hwparams.hwparams3);
 
-	/* Check for proper value of imod_interval */
-	if (dwc->imod_interval && !dwc3_has_imod(dwc)) {
-		dev_warn(dwc->dev, "Interrupt moderation not supported\n");
-		dwc->imod_interval = 0;
-	}
-
 	/*
+	 * Enable IMOD for all supporting controllers.
+	 *
+	 * Particularly, DWC_usb3 v3.00a must enable this feature for
+	 * the following reason:
+	 *
 	 * Workaround for STAR 9000961433 which affects only version
 	 * 3.00a of the DWC_usb3 core. This prevents the controller
 	 * interrupt from being masked while handling events. IMOD
 	 * allows us to work around this issue. Enable it for the
 	 * affected version.
 	 */
-	if (!dwc->imod_interval &&
-	    DWC3_VER_IS(DWC3, 300A))
+	if (dwc3_has_imod((dwc)))
 		dwc->imod_interval = 1;
 
 	/* Check the maximum_speed parameter */
@@ -2105,6 +2107,23 @@ static int dwc3_get_num_ports(struct dwc3 *dwc)
 	return 0;
 }
 
+static struct power_supply *dwc3_get_usb_power_supply(struct dwc3 *dwc)
+{
+	struct power_supply *usb_psy;
+	const char *usb_psy_name;
+	int ret;
+
+	ret = device_property_read_string(dwc->dev, "usb-psy-name", &usb_psy_name);
+	if (ret < 0)
+		return NULL;
+
+	usb_psy = power_supply_get_by_name(usb_psy_name);
+	if (!usb_psy)
+		return ERR_PTR(-EPROBE_DEFER);
+
+	return usb_psy;
+}
+
 static int dwc3_probe(struct platform_device *pdev)
 {
 	struct device		*dev = &pdev->dev;
@@ -2161,6 +2180,10 @@ static int dwc3_probe(struct platform_device *pdev)
 
 	dwc3_get_software_properties(dwc);
 
+	dwc->usb_psy = dwc3_get_usb_power_supply(dwc);
+	if (IS_ERR(dwc->usb_psy))
+		return dev_err_probe(dev, PTR_ERR(dwc->usb_psy), "couldn't get usb power supply\n");
+
 	dwc->reset = devm_reset_control_array_get_optional_shared(dev);
 	if (IS_ERR(dwc->reset)) {
 		ret = PTR_ERR(dwc->reset);
@@ -2341,6 +2364,7 @@ static int dwc3_suspend_common(struct dwc3 *dwc, pm_message_t msg)
 {
 	u32 reg;
 	int i;
+	int ret;
 
 	if (!pm_runtime_suspended(dwc->dev) && !PMSG_IS_AUTO(msg)) {
 		dwc->susphy_state = (dwc3_readl(dwc->regs, DWC3_GUSB2PHYCFG(0)) &
@@ -2359,7 +2383,9 @@ static int dwc3_suspend_common(struct dwc3 *dwc, pm_message_t msg)
 	case DWC3_GCTL_PRTCAP_DEVICE:
 		if (pm_runtime_suspended(dwc->dev))
 			break;
-		dwc3_gadget_suspend(dwc);
+		ret = dwc3_gadget_suspend(dwc);
+		if (ret)
+			return ret;
 		synchronize_irq(dwc->irq_gadget);
 		dwc3_core_exit(dwc);
 		break;
@@ -2394,7 +2420,9 @@ static int dwc3_suspend_common(struct dwc3 *dwc, pm_message_t msg)
 			break;
 
 		if (dwc->current_otg_role == DWC3_OTG_ROLE_DEVICE) {
-			dwc3_gadget_suspend(dwc);
+			ret = dwc3_gadget_suspend(dwc);
+			if (ret)
+				return ret;
 			synchronize_irq(dwc->irq_gadget);
 		}
 
@@ -2421,7 +2449,7 @@ static int dwc3_resume_common(struct dwc3 *dwc, pm_message_t msg)
 		if (ret)
 			return ret;
 
-		dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_DEVICE);
+		dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_DEVICE, true);
 		dwc3_gadget_resume(dwc);
 		break;
 	case DWC3_GCTL_PRTCAP_HOST:
@@ -2429,7 +2457,7 @@ static int dwc3_resume_common(struct dwc3 *dwc, pm_message_t msg)
 			ret = dwc3_core_init_for_resume(dwc);
 			if (ret)
 				return ret;
-			dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_HOST);
+			dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_HOST, true);
 			break;
 		}
 		/* Restore GUSB2PHYCFG bits that were modified in suspend */
@@ -2458,7 +2486,7 @@ static int dwc3_resume_common(struct dwc3 *dwc, pm_message_t msg)
 		if (ret)
 			return ret;
 
-		dwc3_set_prtcap(dwc, dwc->current_dr_role);
+		dwc3_set_prtcap(dwc, dwc->current_dr_role, true);
 
 		dwc3_otg_init(dwc);
 		if (dwc->current_otg_role == DWC3_OTG_ROLE_HOST) {
@@ -2585,12 +2613,15 @@ static int dwc3_resume(struct device *dev)
 	pinctrl_pm_select_default_state(dev);
 
 	pm_runtime_disable(dev);
-	pm_runtime_set_active(dev);
+	ret = pm_runtime_set_active(dev);
+	if (ret)
+		goto out;
 
 	ret = dwc3_resume_common(dwc, PMSG_RESUME);
 	if (ret)
 		pm_runtime_set_suspended(dev);
 
+out:
 	pm_runtime_enable(dev);
 
 	return ret;
diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h
index 0e91a227507f..30fe7df1c3ca 100644
--- a/drivers/usb/dwc3/core.h
+++ b/drivers/usb/dwc3/core.h
@@ -1168,6 +1168,9 @@ struct dwc3_scratchpad_array {
  * @gsbuscfg0_reqinfo: store GSBUSCFG0.DATRDREQINFO, DESRDREQINFO,
  *		       DATWRREQINFO, and DESWRREQINFO value passed from
  *		       glue driver.
+ * @wakeup_pending_funcs: Indicates whether any interface has requested for
+ *			 function wakeup in bitmap format where bit position
+ *			 represents interface_id.
  */
 struct dwc3 {
 	struct work_struct	drd_work;
@@ -1398,6 +1401,7 @@ struct dwc3 {
 	int			num_ep_resized;
 	struct dentry		*debug_root;
 	u32			gsbuscfg0_reqinfo;
+	u32			wakeup_pending_funcs;
 };
 
 #define INCRX_BURST_MODE 0
@@ -1562,7 +1566,7 @@ struct dwc3_gadget_ep_cmd_params {
 #define DWC3_HAS_OTG			BIT(3)
 
 /* prototypes */
-void dwc3_set_prtcap(struct dwc3 *dwc, u32 mode);
+void dwc3_set_prtcap(struct dwc3 *dwc, u32 mode, bool ignore_susphy);
 void dwc3_set_mode(struct dwc3 *dwc, u32 mode);
 u32 dwc3_core_fifo_space(struct dwc3_ep *dep, u8 type);
 
diff --git a/drivers/usb/dwc3/drd.c b/drivers/usb/dwc3/drd.c
index d76ae676783c..7977860932b1 100644
--- a/drivers/usb/dwc3/drd.c
+++ b/drivers/usb/dwc3/drd.c
@@ -173,7 +173,7 @@ void dwc3_otg_init(struct dwc3 *dwc)
 	 * block "Initialize GCTL for OTG operation".
 	 */
 	/* GCTL.PrtCapDir=2'b11 */
-	dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_OTG);
+	dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_OTG, true);
 	/* GUSB2PHYCFG0.SusPHY=0 */
 	reg = dwc3_readl(dwc->regs, DWC3_GUSB2PHYCFG(0));
 	reg &= ~DWC3_GUSB2PHYCFG_SUSPHY;
@@ -556,7 +556,7 @@ int dwc3_drd_init(struct dwc3 *dwc)
 
 		dwc3_drd_update(dwc);
 	} else {
-		dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_OTG);
+		dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_OTG, true);
 
 		/* use OTG block to get ID event */
 		irq = dwc3_otg_get_irq(dwc);
diff --git a/drivers/usb/dwc3/dwc3-am62.c b/drivers/usb/dwc3/dwc3-am62.c
index 538185a4d1b4..c507e576bbe0 100644
--- a/drivers/usb/dwc3/dwc3-am62.c
+++ b/drivers/usb/dwc3/dwc3-am62.c
@@ -166,6 +166,7 @@ static int phy_syscon_pll_refclk(struct dwc3_am62 *am62)
 	if (ret)
 		return ret;
 
+	of_node_put(args.np);
 	am62->offset = args.args[0];
 
 	/* Core voltage. PHY_CORE_VOLTAGE bit Recommended to be 0 always */
diff --git a/drivers/usb/dwc3/dwc3-pci.c b/drivers/usb/dwc3/dwc3-pci.c
index 052852f80146..54a4ee2b90b7 100644
--- a/drivers/usb/dwc3/dwc3-pci.c
+++ b/drivers/usb/dwc3/dwc3-pci.c
@@ -148,11 +148,21 @@ static const struct property_entry dwc3_pci_intel_byt_properties[] = {
 	{}
 };
 
+/*
+ * Intel Merrifield SoC uses these endpoints for tracing and they cannot
+ * be re-allocated if being used because the side band flow control signals
+ * are hard wired to certain endpoints:
+ * - 1 High BW Bulk IN (IN#1) (RTIT)
+ * - 1 1KB BW Bulk IN (IN#8) + 1 1KB BW Bulk OUT (Run Control) (OUT#8)
+ */
+static const u8 dwc3_pci_mrfld_reserved_endpoints[] = { 3, 16, 17 };
+
 static const struct property_entry dwc3_pci_mrfld_properties[] = {
 	PROPERTY_ENTRY_STRING("dr_mode", "otg"),
 	PROPERTY_ENTRY_STRING("linux,extcon-name", "mrfld_bcove_pwrsrc"),
 	PROPERTY_ENTRY_BOOL("snps,dis_u3_susphy_quirk"),
 	PROPERTY_ENTRY_BOOL("snps,dis_u2_susphy_quirk"),
+	PROPERTY_ENTRY_U8_ARRAY("snps,reserved-endpoints", dwc3_pci_mrfld_reserved_endpoints),
 	PROPERTY_ENTRY_BOOL("snps,usb2-gadget-lpm-disable"),
 	PROPERTY_ENTRY_BOOL("linux,sysdev_is_parent"),
 	{}
diff --git a/drivers/usb/dwc3/dwc3-qcom.c b/drivers/usb/dwc3/dwc3-qcom.c
index c1d4b52f25b0..6c79303891d1 100644
--- a/drivers/usb/dwc3/dwc3-qcom.c
+++ b/drivers/usb/dwc3/dwc3-qcom.c
@@ -763,13 +763,13 @@ static int dwc3_qcom_probe(struct platform_device *pdev)
 	ret = reset_control_deassert(qcom->resets);
 	if (ret) {
 		dev_err(&pdev->dev, "failed to deassert resets, err=%d\n", ret);
-		goto reset_assert;
+		return ret;
 	}
 
 	ret = dwc3_qcom_clk_init(qcom, of_clk_get_parent_count(np));
 	if (ret) {
 		dev_err_probe(dev, ret, "failed to get clocks\n");
-		goto reset_assert;
+		return ret;
 	}
 
 	qcom->qscratch_base = devm_platform_ioremap_resource(pdev, 0);
@@ -835,8 +835,6 @@ clk_disable:
 		clk_disable_unprepare(qcom->clks[i]);
 		clk_put(qcom->clks[i]);
 	}
-reset_assert:
-	reset_control_assert(qcom->resets);
 
 	return ret;
 }
@@ -857,8 +855,6 @@ static void dwc3_qcom_remove(struct platform_device *pdev)
 	qcom->num_clocks = 0;
 
 	dwc3_qcom_interconnect_exit(qcom);
-	reset_control_assert(qcom->resets);
-
 	pm_runtime_allow(dev);
 	pm_runtime_disable(dev);
 }
diff --git a/drivers/usb/dwc3/dwc3-xilinx.c b/drivers/usb/dwc3/dwc3-xilinx.c
index 96c87dc4757f..47e891c92337 100644
--- a/drivers/usb/dwc3/dwc3-xilinx.c
+++ b/drivers/usb/dwc3/dwc3-xilinx.c
@@ -207,15 +207,13 @@ static int dwc3_xlnx_init_zynqmp(struct dwc3_xlnx *priv_data)
 
 skip_usb3_phy:
 	/* ulpi reset via gpio-modepin or gpio-framework driver */
-	reset_gpio = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_LOW);
+	reset_gpio = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_HIGH);
 	if (IS_ERR(reset_gpio)) {
 		return dev_err_probe(dev, PTR_ERR(reset_gpio),
 				     "Failed to request reset GPIO\n");
 	}
 
 	if (reset_gpio) {
-		/* Toggle ulpi to reset the phy. */
-		gpiod_set_value_cansleep(reset_gpio, 1);
 		usleep_range(5000, 10000);
 		gpiod_set_value_cansleep(reset_gpio, 0);
 		usleep_range(5000, 10000);
diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index a5d75d7d0a87..37ae1dd3345d 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -277,8 +277,6 @@ int dwc3_send_gadget_generic_command(struct dwc3 *dwc, unsigned int cmd,
 	return ret;
 }
 
-static int __dwc3_gadget_wakeup(struct dwc3 *dwc, bool async);
-
 /**
  * dwc3_send_gadget_ep_cmd - issue an endpoint command
  * @dep: the endpoint to which the command is going to be issued
@@ -548,6 +546,7 @@ static int dwc3_gadget_set_xfer_resource(struct dwc3_ep *dep)
 int dwc3_gadget_start_config(struct dwc3 *dwc, unsigned int resource_index)
 {
 	struct dwc3_gadget_ep_cmd_params params;
+	struct dwc3_ep		*dep;
 	u32			cmd;
 	int			i;
 	int			ret;
@@ -564,8 +563,13 @@ int dwc3_gadget_start_config(struct dwc3 *dwc, unsigned int resource_index)
 		return ret;
 
 	/* Reset resource allocation flags */
-	for (i = resource_index; i < dwc->num_eps && dwc->eps[i]; i++)
-		dwc->eps[i]->flags &= ~DWC3_EP_RESOURCE_ALLOCATED;
+	for (i = resource_index; i < dwc->num_eps; i++) {
+		dep = dwc->eps[i];
+		if (!dep)
+			continue;
+
+		dep->flags &= ~DWC3_EP_RESOURCE_ALLOCATED;
+	}
 
 	return 0;
 }
@@ -752,9 +756,11 @@ void dwc3_gadget_clear_tx_fifos(struct dwc3 *dwc)
 
 	dwc->last_fifo_depth = fifo_depth;
 	/* Clear existing TXFIFO for all IN eps except ep0 */
-	for (num = 3; num < min_t(int, dwc->num_eps, DWC3_ENDPOINTS_NUM);
-	     num += 2) {
+	for (num = 3; num < min_t(int, dwc->num_eps, DWC3_ENDPOINTS_NUM); num += 2) {
 		dep = dwc->eps[num];
+		if (!dep)
+			continue;
+
 		/* Don't change TXFRAMNUM on usb31 version */
 		size = DWC3_IP_IS(DWC3) ? 0 :
 			dwc3_readl(dwc->regs, DWC3_GTXFIFOSIZ(num >> 1)) &
@@ -2340,10 +2346,8 @@ static int dwc3_gadget_get_frame(struct usb_gadget *g)
 	return __dwc3_gadget_get_frame(dwc);
 }
 
-static int __dwc3_gadget_wakeup(struct dwc3 *dwc, bool async)
+static int __dwc3_gadget_wakeup(struct dwc3 *dwc)
 {
-	int			retries;
-
 	int			ret;
 	u32			reg;
 
@@ -2371,8 +2375,7 @@ static int __dwc3_gadget_wakeup(struct dwc3 *dwc, bool async)
 		return -EINVAL;
 	}
 
-	if (async)
-		dwc3_gadget_enable_linksts_evts(dwc, true);
+	dwc3_gadget_enable_linksts_evts(dwc, true);
 
 	ret = dwc3_gadget_set_link_state(dwc, DWC3_LINK_STATE_RECOV);
 	if (ret < 0) {
@@ -2391,27 +2394,8 @@ static int __dwc3_gadget_wakeup(struct dwc3 *dwc, bool async)
 
 	/*
 	 * Since link status change events are enabled we will receive
-	 * an U0 event when wakeup is successful. So bail out.
+	 * an U0 event when wakeup is successful.
 	 */
-	if (async)
-		return 0;
-
-	/* poll until Link State changes to ON */
-	retries = 20000;
-
-	while (retries--) {
-		reg = dwc3_readl(dwc->regs, DWC3_DSTS);
-
-		/* in HS, means ON */
-		if (DWC3_DSTS_USBLNKST(reg) == DWC3_LINK_STATE_U0)
-			break;
-	}
-
-	if (DWC3_DSTS_USBLNKST(reg) != DWC3_LINK_STATE_U0) {
-		dev_err(dwc->dev, "failed to send remote wakeup\n");
-		return -EINVAL;
-	}
-
 	return 0;
 }
 
@@ -2432,7 +2416,7 @@ static int dwc3_gadget_wakeup(struct usb_gadget *g)
 		spin_unlock_irqrestore(&dwc->lock, flags);
 		return -EINVAL;
 	}
-	ret = __dwc3_gadget_wakeup(dwc, true);
+	ret = __dwc3_gadget_wakeup(dwc);
 
 	spin_unlock_irqrestore(&dwc->lock, flags);
 
@@ -2460,14 +2444,10 @@ static int dwc3_gadget_func_wakeup(struct usb_gadget *g, int intf_id)
 	 */
 	link_state = dwc3_gadget_get_link_state(dwc);
 	if (link_state == DWC3_LINK_STATE_U3) {
-		ret = __dwc3_gadget_wakeup(dwc, false);
-		if (ret) {
-			spin_unlock_irqrestore(&dwc->lock, flags);
-			return -EINVAL;
-		}
-		dwc3_resume_gadget(dwc);
-		dwc->suspended = false;
-		dwc->link_state = DWC3_LINK_STATE_U0;
+		dwc->wakeup_pending_funcs |= BIT(intf_id);
+		ret = __dwc3_gadget_wakeup(dwc);
+		spin_unlock_irqrestore(&dwc->lock, flags);
+		return ret;
 	}
 
 	ret = dwc3_send_gadget_generic_command(dwc, DWC3_DGCMD_DEV_NOTIFICATION,
@@ -2618,10 +2598,38 @@ static int dwc3_gadget_run_stop(struct dwc3 *dwc, int is_on)
 {
 	u32			reg;
 	u32			timeout = 2000;
+	u32			saved_config = 0;
 
 	if (pm_runtime_suspended(dwc->dev))
 		return 0;
 
+	/*
+	 * When operating in USB 2.0 speeds (HS/FS), ensure that
+	 * GUSB2PHYCFG.ENBLSLPM and GUSB2PHYCFG.SUSPHY are cleared before starting
+	 * or stopping the controller. This resolves timeout issues that occur
+	 * during frequent role switches between host and device modes.
+	 *
+	 * Save and clear these settings, then restore them after completing the
+	 * controller start or stop sequence.
+	 *
+	 * This solution was discovered through experimentation as it is not
+	 * mentioned in the dwc3 programming guide. It has been tested on an
+	 * Exynos platforms.
+	 */
+	reg = dwc3_readl(dwc->regs, DWC3_GUSB2PHYCFG(0));
+	if (reg & DWC3_GUSB2PHYCFG_SUSPHY) {
+		saved_config |= DWC3_GUSB2PHYCFG_SUSPHY;
+		reg &= ~DWC3_GUSB2PHYCFG_SUSPHY;
+	}
+
+	if (reg & DWC3_GUSB2PHYCFG_ENBLSLPM) {
+		saved_config |= DWC3_GUSB2PHYCFG_ENBLSLPM;
+		reg &= ~DWC3_GUSB2PHYCFG_ENBLSLPM;
+	}
+
+	if (saved_config)
+		dwc3_writel(dwc->regs, DWC3_GUSB2PHYCFG(0), reg);
+
 	reg = dwc3_readl(dwc->regs, DWC3_DCTL);
 	if (is_on) {
 		if (DWC3_VER_IS_WITHIN(DWC3, ANY, 187A)) {
@@ -2649,6 +2657,12 @@ static int dwc3_gadget_run_stop(struct dwc3 *dwc, int is_on)
 		reg &= DWC3_DSTS_DEVCTRLHLT;
 	} while (--timeout && !(!is_on ^ !reg));
 
+	if (saved_config) {
+		reg = dwc3_readl(dwc->regs, DWC3_GUSB2PHYCFG(0));
+		reg |= saved_config;
+		dwc3_writel(dwc->regs, DWC3_GUSB2PHYCFG(0), reg);
+	}
+
 	if (!timeout)
 		return -ETIMEDOUT;
 
@@ -3636,6 +3650,8 @@ out:
 
 		for (i = 0; i < DWC3_ENDPOINTS_NUM; i++) {
 			dep = dwc->eps[i];
+			if (!dep)
+				continue;
 
 			if (!(dep->flags & DWC3_EP_ENABLED))
 				continue;
@@ -3824,6 +3840,10 @@ static void dwc3_endpoint_interrupt(struct dwc3 *dwc,
 	u8			epnum = event->endpoint_number;
 
 	dep = dwc->eps[epnum];
+	if (!dep) {
+		dev_warn(dwc->dev, "spurious event, endpoint %u is not allocated\n", epnum);
+		return;
+	}
 
 	if (!(dep->flags & DWC3_EP_ENABLED)) {
 		if ((epnum > 1) && !(dep->flags & DWC3_EP_TRANSFER_STARTED))
@@ -4272,6 +4292,8 @@ static void dwc3_gadget_linksts_change_interrupt(struct dwc3 *dwc,
 {
 	enum dwc3_link_state	next = evtinfo & DWC3_LINK_STATE_MASK;
 	unsigned int		pwropt;
+	int			ret;
+	int			intf_id;
 
 	/*
 	 * WORKAROUND: DWC3 < 2.50a have an issue when configured without
@@ -4347,7 +4369,7 @@ static void dwc3_gadget_linksts_change_interrupt(struct dwc3 *dwc,
 
 	switch (next) {
 	case DWC3_LINK_STATE_U0:
-		if (dwc->gadget->wakeup_armed) {
+		if (dwc->gadget->wakeup_armed || dwc->wakeup_pending_funcs) {
 			dwc3_gadget_enable_linksts_evts(dwc, false);
 			dwc3_resume_gadget(dwc);
 			dwc->suspended = false;
@@ -4370,6 +4392,18 @@ static void dwc3_gadget_linksts_change_interrupt(struct dwc3 *dwc,
 	}
 
 	dwc->link_state = next;
+
+	/* Proceed with func wakeup if any interfaces that has requested */
+	while (dwc->wakeup_pending_funcs && (next == DWC3_LINK_STATE_U0)) {
+		intf_id = ffs(dwc->wakeup_pending_funcs) - 1;
+		ret = dwc3_send_gadget_generic_command(dwc, DWC3_DGCMD_DEV_NOTIFICATION,
+						       DWC3_DGCMDPAR_DN_FUNC_WAKE |
+						       DWC3_DGCMDPAR_INTF_SEL(intf_id));
+		if (ret)
+			dev_err(dwc->dev, "Failed to send DN wake for intf %d\n", intf_id);
+
+		dwc->wakeup_pending_funcs &= ~BIT(intf_id);
+	}
 }
 
 static void dwc3_gadget_suspend_interrupt(struct dwc3 *dwc,
@@ -4473,14 +4507,18 @@ static irqreturn_t dwc3_process_event_buf(struct dwc3_event_buffer *evt)
 	dwc3_writel(dwc->regs, DWC3_GEVNTSIZ(0),
 		    DWC3_GEVNTSIZ_SIZE(evt->length));
 
+	evt->flags &= ~DWC3_EVENT_PENDING;
+	/*
+	 * Add an explicit write memory barrier to make sure that the update of
+	 * clearing DWC3_EVENT_PENDING is observed in dwc3_check_event_buf()
+	 */
+	wmb();
+
 	if (dwc->imod_interval) {
 		dwc3_writel(dwc->regs, DWC3_GEVNTCOUNT(0), DWC3_GEVNTCOUNT_EHB);
 		dwc3_writel(dwc->regs, DWC3_DEV_IMOD(0), dwc->imod_interval);
 	}
 
-	/* Keep the clearing of DWC3_EVENT_PENDING at the end */
-	evt->flags &= ~DWC3_EVENT_PENDING;
-
 	return ret;
 }
 
@@ -4532,6 +4570,12 @@ static irqreturn_t dwc3_check_event_buf(struct dwc3_event_buffer *evt)
 	if (!count)
 		return IRQ_NONE;
 
+	if (count > evt->length) {
+		dev_err_ratelimited(dwc->dev, "invalid count(%u) > evt->length(%u)\n",
+			count, evt->length);
+		return IRQ_NONE;
+	}
+
 	evt->count = count;
 	evt->flags |= DWC3_EVENT_PENDING;
 
@@ -4744,26 +4788,22 @@ int dwc3_gadget_suspend(struct dwc3 *dwc)
 	int ret;
 
 	ret = dwc3_gadget_soft_disconnect(dwc);
-	if (ret)
-		goto err;
-
-	spin_lock_irqsave(&dwc->lock, flags);
-	if (dwc->gadget_driver)
-		dwc3_disconnect_gadget(dwc);
-	spin_unlock_irqrestore(&dwc->lock, flags);
-
-	return 0;
-
-err:
 	/*
 	 * Attempt to reset the controller's state. Likely no
 	 * communication can be established until the host
 	 * performs a port reset.
 	 */
-	if (dwc->softconnect)
+	if (ret && dwc->softconnect) {
 		dwc3_gadget_soft_connect(dwc);
+		return -EAGAIN;
+	}
 
-	return ret;
+	spin_lock_irqsave(&dwc->lock, flags);
+	if (dwc->gadget_driver)
+		dwc3_disconnect_gadget(dwc);
+	spin_unlock_irqrestore(&dwc->lock, flags);
+
+	return 0;
 }
 
 int dwc3_gadget_resume(struct dwc3 *dwc)
diff --git a/drivers/usb/early/xhci-dbc.c b/drivers/usb/early/xhci-dbc.c
index 341408410ed9..41118bba9197 100644
--- a/drivers/usb/early/xhci-dbc.c
+++ b/drivers/usb/early/xhci-dbc.c
@@ -681,6 +681,10 @@ int __init early_xdbc_setup_hardware(void)
 
 		xdbc.table_base = NULL;
 		xdbc.out_buf = NULL;
+
+		early_iounmap(xdbc.xhci_base, xdbc.xhci_length);
+		xdbc.xhci_base = NULL;
+		xdbc.xhci_length = 0;
 	}
 
 	return ret;
diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c
index cec86c0c6369..460a102c1419 100644
--- a/drivers/usb/gadget/composite.c
+++ b/drivers/usb/gadget/composite.c
@@ -1050,10 +1050,11 @@ static int set_config(struct usb_composite_dev *cdev,
 	else
 		usb_gadget_set_remote_wakeup(gadget, 0);
 done:
-	if (power <= USB_SELF_POWER_VBUS_MAX_DRAW)
-		usb_gadget_set_selfpowered(gadget);
-	else
+	if (power > USB_SELF_POWER_VBUS_MAX_DRAW ||
+	    (c && !(c->bmAttributes & USB_CONFIG_ATT_SELFPOWER)))
 		usb_gadget_clear_selfpowered(gadget);
+	else
+		usb_gadget_set_selfpowered(gadget);
 
 	usb_gadget_vbus_draw(gadget, power);
 	if (result >= 0 && cdev->delayed_status)
@@ -2010,15 +2011,13 @@ composite_setup(struct usb_gadget *gadget, const struct usb_ctrlrequest *ctrl)
 
 		if (f->get_status) {
 			status = f->get_status(f);
+
 			if (status < 0)
 				break;
-		} else {
-			/* Set D0 and D1 bits based on func wakeup capability */
-			if (f->config->bmAttributes & USB_CONFIG_ATT_WAKEUP) {
-				status |= USB_INTRF_STAT_FUNC_RW_CAP;
-				if (f->func_wakeup_armed)
-					status |= USB_INTRF_STAT_FUNC_RW;
-			}
+
+			/* if D5 is not set, then device is not wakeup capable */
+			if (!(f->config->bmAttributes & USB_CONFIG_ATT_WAKEUP))
+				status &= ~(USB_INTRF_STAT_FUNC_RW_CAP | USB_INTRF_STAT_FUNC_RW);
 		}
 
 		put_unaligned_le16(status & 0x0000ffff, req->buf);
@@ -2490,6 +2489,11 @@ int composite_os_desc_req_prepare(struct usb_composite_dev *cdev,
 	if (!cdev->os_desc_req->buf) {
 		ret = -ENOMEM;
 		usb_ep_free_request(ep0, cdev->os_desc_req);
+		/*
+		 * Set os_desc_req to NULL so that composite_dev_cleanup()
+		 * will not try to free it again.
+		 */
+		cdev->os_desc_req = NULL;
 		goto end;
 	}
 	cdev->os_desc_req->context = cdev;
@@ -2615,7 +2619,10 @@ void composite_suspend(struct usb_gadget *gadget)
 
 	cdev->suspended = 1;
 
-	usb_gadget_set_selfpowered(gadget);
+	if (cdev->config &&
+	    cdev->config->bmAttributes & USB_CONFIG_ATT_SELFPOWER)
+		usb_gadget_set_selfpowered(gadget);
+
 	usb_gadget_vbus_draw(gadget, 2);
 }
 
@@ -2649,8 +2656,11 @@ void composite_resume(struct usb_gadget *gadget)
 		else
 			maxpower = min(maxpower, 900U);
 
-		if (maxpower > USB_SELF_POWER_VBUS_MAX_DRAW)
+		if (maxpower > USB_SELF_POWER_VBUS_MAX_DRAW ||
+		    !(cdev->config->bmAttributes & USB_CONFIG_ATT_SELFPOWER))
 			usb_gadget_clear_selfpowered(gadget);
+		else
+			usb_gadget_set_selfpowered(gadget);
 
 		usb_gadget_vbus_draw(gadget, maxpower);
 	} else {
diff --git a/drivers/usb/gadget/configfs.c b/drivers/usb/gadget/configfs.c
index 29390d573e23..1b4d0056f1d0 100644
--- a/drivers/usb/gadget/configfs.c
+++ b/drivers/usb/gadget/configfs.c
@@ -1065,6 +1065,8 @@ static ssize_t webusb_landingPage_store(struct config_item *item, const char *pa
 	unsigned int bytes_to_strip = 0;
 	int l = len;
 
+	if (!len)
+		return len;
 	if (page[l - 1] == '\n') {
 		--l;
 		++bytes_to_strip;
@@ -1188,6 +1190,8 @@ static ssize_t os_desc_qw_sign_store(struct config_item *item, const char *page,
 	struct gadget_info *gi = os_desc_item_to_gadget_info(item);
 	int res, l;
 
+	if (!len)
+		return len;
 	l = min((int)len, OS_STRING_QW_SIGN_LEN >> 1);
 	if (page[l - 1] == '\n')
 		--l;
diff --git a/drivers/usb/gadget/function/f_ecm.c b/drivers/usb/gadget/function/f_ecm.c
index 6cb7771e8a69..549efc84dd83 100644
--- a/drivers/usb/gadget/function/f_ecm.c
+++ b/drivers/usb/gadget/function/f_ecm.c
@@ -892,6 +892,12 @@ static void ecm_resume(struct usb_function *f)
 	gether_resume(&ecm->port);
 }
 
+static int ecm_get_status(struct usb_function *f)
+{
+	return (f->func_wakeup_armed ? USB_INTRF_STAT_FUNC_RW : 0) |
+		USB_INTRF_STAT_FUNC_RW_CAP;
+}
+
 static void ecm_free(struct usb_function *f)
 {
 	struct f_ecm *ecm;
@@ -960,6 +966,7 @@ static struct usb_function *ecm_alloc(struct usb_function_instance *fi)
 	ecm->port.func.disable = ecm_disable;
 	ecm->port.func.free_func = ecm_free;
 	ecm->port.func.suspend = ecm_suspend;
+	ecm->port.func.get_status = ecm_get_status;
 	ecm->port.func.resume = ecm_resume;
 
 	return &ecm->port.func;
diff --git a/drivers/usb/gadget/function/f_hid.c b/drivers/usb/gadget/function/f_hid.c
index 740311c4fa24..ab4d170469f5 100644
--- a/drivers/usb/gadget/function/f_hid.c
+++ b/drivers/usb/gadget/function/f_hid.c
@@ -75,6 +75,7 @@ struct f_hidg {
 	/* recv report */
 	spinlock_t			read_spinlock;
 	wait_queue_head_t		read_queue;
+	bool				disabled;
 	/* recv report - interrupt out only (use_out_ep == 1) */
 	struct list_head		completed_out_req;
 	unsigned int			qlen;
@@ -144,8 +145,8 @@ static struct hid_descriptor hidg_desc = {
 	.bcdHID				= cpu_to_le16(0x0101),
 	.bCountryCode			= 0x00,
 	.bNumDescriptors		= 0x1,
-	/*.desc[0].bDescriptorType	= DYNAMIC */
-	/*.desc[0].wDescriptorLenght	= DYNAMIC */
+	/*.rpt_desc.bDescriptorType	= DYNAMIC */
+	/*.rpt_desc.wDescriptorLength	= DYNAMIC */
 };
 
 /* Super-Speed Support */
@@ -329,7 +330,7 @@ static ssize_t f_hidg_intout_read(struct file *file, char __user *buffer,
 
 	spin_lock_irqsave(&hidg->read_spinlock, flags);
 
-#define READ_COND_INTOUT (!list_empty(&hidg->completed_out_req))
+#define READ_COND_INTOUT (!list_empty(&hidg->completed_out_req) || hidg->disabled)
 
 	/* wait for at least one buffer to complete */
 	while (!READ_COND_INTOUT) {
@@ -343,6 +344,11 @@ static ssize_t f_hidg_intout_read(struct file *file, char __user *buffer,
 		spin_lock_irqsave(&hidg->read_spinlock, flags);
 	}
 
+	if (hidg->disabled) {
+		spin_unlock_irqrestore(&hidg->read_spinlock, flags);
+		return -ESHUTDOWN;
+	}
+
 	/* pick the first one */
 	list = list_first_entry(&hidg->completed_out_req,
 				struct f_hidg_req_list, list);
@@ -387,7 +393,7 @@ static ssize_t f_hidg_intout_read(struct file *file, char __user *buffer,
 	return count;
 }
 
-#define READ_COND_SSREPORT (hidg->set_report_buf != NULL)
+#define READ_COND_SSREPORT (hidg->set_report_buf != NULL || hidg->disabled)
 
 static ssize_t f_hidg_ssreport_read(struct file *file, char __user *buffer,
 				    size_t count, loff_t *ptr)
@@ -939,8 +945,8 @@ static int hidg_setup(struct usb_function *f,
 			struct hid_descriptor hidg_desc_copy = hidg_desc;
 
 			VDBG(cdev, "USB_REQ_GET_DESCRIPTOR: HID\n");
-			hidg_desc_copy.desc[0].bDescriptorType = HID_DT_REPORT;
-			hidg_desc_copy.desc[0].wDescriptorLength =
+			hidg_desc_copy.rpt_desc.bDescriptorType = HID_DT_REPORT;
+			hidg_desc_copy.rpt_desc.wDescriptorLength =
 				cpu_to_le16(hidg->report_desc_length);
 
 			length = min_t(unsigned short, length,
@@ -1012,6 +1018,11 @@ static void hidg_disable(struct usb_function *f)
 	}
 	spin_unlock_irqrestore(&hidg->get_report_spinlock, flags);
 
+	spin_lock_irqsave(&hidg->read_spinlock, flags);
+	hidg->disabled = true;
+	spin_unlock_irqrestore(&hidg->read_spinlock, flags);
+	wake_up(&hidg->read_queue);
+
 	spin_lock_irqsave(&hidg->write_spinlock, flags);
 	if (!hidg->write_pending) {
 		free_ep_req(hidg->in_ep, hidg->req);
@@ -1097,6 +1108,10 @@ static int hidg_set_alt(struct usb_function *f, unsigned intf, unsigned alt)
 		}
 	}
 
+	spin_lock_irqsave(&hidg->read_spinlock, flags);
+	hidg->disabled = false;
+	spin_unlock_irqrestore(&hidg->read_spinlock, flags);
+
 	if (hidg->in_ep != NULL) {
 		spin_lock_irqsave(&hidg->write_spinlock, flags);
 		hidg->req = req_in;
@@ -1210,8 +1225,8 @@ static int hidg_bind(struct usb_configuration *c, struct usb_function *f)
 	 * We can use hidg_desc struct here but we should not relay
 	 * that its content won't change after returning from this function.
 	 */
-	hidg_desc.desc[0].bDescriptorType = HID_DT_REPORT;
-	hidg_desc.desc[0].wDescriptorLength =
+	hidg_desc.rpt_desc.bDescriptorType = HID_DT_REPORT;
+	hidg_desc.rpt_desc.wDescriptorLength =
 		cpu_to_le16(hidg->report_desc_length);
 
 	hidg_hs_in_ep_desc.bEndpointAddress =
@@ -1260,18 +1275,19 @@ static int hidg_bind(struct usb_configuration *c, struct usb_function *f)
 
 	if (!hidg->workqueue) {
 		status = -ENOMEM;
-		goto fail;
+		goto fail_free_descs;
 	}
 
 	/* create char device */
 	cdev_init(&hidg->cdev, &f_hidg_fops);
 	status = cdev_device_add(&hidg->cdev, &hidg->dev);
 	if (status)
-		goto fail_free_descs;
+		goto fail_free_all;
 
 	return 0;
-fail_free_descs:
+fail_free_all:
 	destroy_workqueue(hidg->workqueue);
+fail_free_descs:
 	usb_free_all_descriptors(f);
 fail:
 	ERROR(f->config->cdev, "hidg_bind FAILED\n");
diff --git a/drivers/usb/gadget/function/f_midi.c b/drivers/usb/gadget/function/f_midi.c
index 1067847cc079..1f18f15dba27 100644
--- a/drivers/usb/gadget/function/f_midi.c
+++ b/drivers/usb/gadget/function/f_midi.c
@@ -283,7 +283,7 @@ f_midi_complete(struct usb_ep *ep, struct usb_request *req)
 			/* Our transmit completed. See if there's more to go.
 			 * f_midi_transmit eats req, don't queue it again. */
 			req->length = 0;
-			f_midi_transmit(midi);
+			queue_work(system_highpri_wq, &midi->work);
 			return;
 		}
 		break;
@@ -907,6 +907,15 @@ static int f_midi_bind(struct usb_configuration *c, struct usb_function *f)
 
 	status = -ENODEV;
 
+	/*
+	 * Reset wMaxPacketSize with maximum packet size of FS bulk transfer before
+	 * endpoint claim. This ensures that the wMaxPacketSize does not exceed the
+	 * limit during bind retries where configured dwc3 TX/RX FIFO's maxpacket
+	 * size of 512 bytes for IN/OUT endpoints in support HS speed only.
+	 */
+	bulk_in_desc.wMaxPacketSize = cpu_to_le16(64);
+	bulk_out_desc.wMaxPacketSize = cpu_to_le16(64);
+
 	/* allocate instance-specific endpoints */
 	midi->in_ep = usb_ep_autoconfig(cdev->gadget, &bulk_in_desc);
 	if (!midi->in_ep)
@@ -1000,11 +1009,11 @@ static int f_midi_bind(struct usb_configuration *c, struct usb_function *f)
 	}
 
 	/* configure the endpoint descriptors ... */
-	ms_out_desc.bLength = USB_DT_MS_ENDPOINT_SIZE(midi->in_ports);
-	ms_out_desc.bNumEmbMIDIJack = midi->in_ports;
+	ms_out_desc.bLength = USB_DT_MS_ENDPOINT_SIZE(midi->out_ports);
+	ms_out_desc.bNumEmbMIDIJack = midi->out_ports;
 
-	ms_in_desc.bLength = USB_DT_MS_ENDPOINT_SIZE(midi->out_ports);
-	ms_in_desc.bNumEmbMIDIJack = midi->out_ports;
+	ms_in_desc.bLength = USB_DT_MS_ENDPOINT_SIZE(midi->in_ports);
+	ms_in_desc.bNumEmbMIDIJack = midi->in_ports;
 
 	/* ... and add them to the list */
 	endpoint_descriptor_index = i;
diff --git a/drivers/usb/gadget/function/f_midi2.c b/drivers/usb/gadget/function/f_midi2.c
index 8c9d0074db58..0c45936f51b3 100644
--- a/drivers/usb/gadget/function/f_midi2.c
+++ b/drivers/usb/gadget/function/f_midi2.c
@@ -475,7 +475,7 @@ static void reply_ump_stream_ep_info(struct f_midi2_ep *ep)
 /* reply a UMP EP device info */
 static void reply_ump_stream_ep_device(struct f_midi2_ep *ep)
 {
-	struct snd_ump_stream_msg_devince_info rep = {
+	struct snd_ump_stream_msg_device_info rep = {
 		.type = UMP_MSG_TYPE_STREAM,
 		.status = UMP_STREAM_MSG_STATUS_DEVICE_INFO,
 		.manufacture_id = ep->info.manufacturer,
diff --git a/drivers/usb/gadget/function/f_tcm.c b/drivers/usb/gadget/function/f_tcm.c
index 15bb3aa12aa8..6ad205046032 100644
--- a/drivers/usb/gadget/function/f_tcm.c
+++ b/drivers/usb/gadget/function/f_tcm.c
@@ -245,7 +245,6 @@ static int bot_send_write_request(struct usbg_cmd *cmd)
 {
 	struct f_uas *fu = cmd->fu;
 	struct se_cmd *se_cmd = &cmd->se_cmd;
-	struct usb_gadget *gadget = fuas_to_gadget(fu);
 	int ret;
 
 	init_completion(&cmd->write_complete);
@@ -256,22 +255,6 @@ static int bot_send_write_request(struct usbg_cmd *cmd)
 		return -EINVAL;
 	}
 
-	if (!gadget->sg_supported) {
-		cmd->data_buf = kmalloc(se_cmd->data_length, GFP_KERNEL);
-		if (!cmd->data_buf)
-			return -ENOMEM;
-
-		fu->bot_req_out->buf = cmd->data_buf;
-	} else {
-		fu->bot_req_out->buf = NULL;
-		fu->bot_req_out->num_sgs = se_cmd->t_data_nents;
-		fu->bot_req_out->sg = se_cmd->t_data_sg;
-	}
-
-	fu->bot_req_out->complete = usbg_data_write_cmpl;
-	fu->bot_req_out->length = se_cmd->data_length;
-	fu->bot_req_out->context = cmd;
-
 	ret = usbg_prepare_w_request(cmd, fu->bot_req_out);
 	if (ret)
 		goto cleanup;
@@ -973,6 +956,7 @@ static void usbg_data_write_cmpl(struct usb_ep *ep, struct usb_request *req)
 	return;
 
 cleanup:
+	target_put_sess_cmd(se_cmd);
 	transport_generic_free_cmd(&cmd->se_cmd, 0);
 }
 
@@ -1065,8 +1049,7 @@ static void usbg_cmd_work(struct work_struct *work)
 
 out:
 	transport_send_check_condition_and_sense(se_cmd,
-			TCM_UNSUPPORTED_SCSI_OPCODE, 1);
-	transport_generic_free_cmd(&cmd->se_cmd, 0);
+			TCM_UNSUPPORTED_SCSI_OPCODE, 0);
 }
 
 static struct usbg_cmd *usbg_get_cmd(struct f_uas *fu,
@@ -1194,8 +1177,7 @@ static void bot_cmd_work(struct work_struct *work)
 
 out:
 	transport_send_check_condition_and_sense(se_cmd,
-				TCM_UNSUPPORTED_SCSI_OPCODE, 1);
-	transport_generic_free_cmd(&cmd->se_cmd, 0);
+				TCM_UNSUPPORTED_SCSI_OPCODE, 0);
 }
 
 static int bot_submit_command(struct f_uas *fu,
@@ -1315,14 +1297,14 @@ static struct se_portal_group *usbg_make_tpg(struct se_wwn *wwn,
 	struct usbg_tport *tport = container_of(wwn, struct usbg_tport,
 			tport_wwn);
 	struct usbg_tpg *tpg;
-	unsigned long tpgt;
+	u16 tpgt;
 	int ret;
 	struct f_tcm_opts *opts;
 	unsigned i;
 
 	if (strstr(name, "tpgt_") != name)
 		return ERR_PTR(-EINVAL);
-	if (kstrtoul(name + 5, 0, &tpgt) || tpgt > UINT_MAX)
+	if (kstrtou16(name + 5, 0, &tpgt))
 		return ERR_PTR(-EINVAL);
 	ret = -ENODEV;
 	mutex_lock(&tpg_instances_lock);
@@ -1971,43 +1953,39 @@ static int tcm_bind(struct usb_configuration *c, struct usb_function *f)
 	bot_intf_desc.bInterfaceNumber = iface;
 	uasp_intf_desc.bInterfaceNumber = iface;
 	fu->iface = iface;
-	ep = usb_ep_autoconfig_ss(gadget, &uasp_ss_bi_desc,
-			&uasp_bi_ep_comp_desc);
+	ep = usb_ep_autoconfig(gadget, &uasp_fs_bi_desc);
 	if (!ep)
 		goto ep_fail;
 
 	fu->ep_in = ep;
 
-	ep = usb_ep_autoconfig_ss(gadget, &uasp_ss_bo_desc,
-			&uasp_bo_ep_comp_desc);
+	ep = usb_ep_autoconfig(gadget, &uasp_fs_bo_desc);
 	if (!ep)
 		goto ep_fail;
 	fu->ep_out = ep;
 
-	ep = usb_ep_autoconfig_ss(gadget, &uasp_ss_status_desc,
-			&uasp_status_in_ep_comp_desc);
+	ep = usb_ep_autoconfig(gadget, &uasp_fs_status_desc);
 	if (!ep)
 		goto ep_fail;
 	fu->ep_status = ep;
 
-	ep = usb_ep_autoconfig_ss(gadget, &uasp_ss_cmd_desc,
-			&uasp_cmd_comp_desc);
+	ep = usb_ep_autoconfig(gadget, &uasp_fs_cmd_desc);
 	if (!ep)
 		goto ep_fail;
 	fu->ep_cmd = ep;
 
 	/* Assume endpoint addresses are the same for both speeds */
-	uasp_bi_desc.bEndpointAddress =	uasp_ss_bi_desc.bEndpointAddress;
-	uasp_bo_desc.bEndpointAddress = uasp_ss_bo_desc.bEndpointAddress;
+	uasp_bi_desc.bEndpointAddress =	uasp_fs_bi_desc.bEndpointAddress;
+	uasp_bo_desc.bEndpointAddress = uasp_fs_bo_desc.bEndpointAddress;
 	uasp_status_desc.bEndpointAddress =
-		uasp_ss_status_desc.bEndpointAddress;
-	uasp_cmd_desc.bEndpointAddress = uasp_ss_cmd_desc.bEndpointAddress;
+		uasp_fs_status_desc.bEndpointAddress;
+	uasp_cmd_desc.bEndpointAddress = uasp_fs_cmd_desc.bEndpointAddress;
 
-	uasp_fs_bi_desc.bEndpointAddress = uasp_ss_bi_desc.bEndpointAddress;
-	uasp_fs_bo_desc.bEndpointAddress = uasp_ss_bo_desc.bEndpointAddress;
-	uasp_fs_status_desc.bEndpointAddress =
-		uasp_ss_status_desc.bEndpointAddress;
-	uasp_fs_cmd_desc.bEndpointAddress = uasp_ss_cmd_desc.bEndpointAddress;
+	uasp_ss_bi_desc.bEndpointAddress = uasp_fs_bi_desc.bEndpointAddress;
+	uasp_ss_bo_desc.bEndpointAddress = uasp_fs_bo_desc.bEndpointAddress;
+	uasp_ss_status_desc.bEndpointAddress =
+		uasp_fs_status_desc.bEndpointAddress;
+	uasp_ss_cmd_desc.bEndpointAddress = uasp_fs_cmd_desc.bEndpointAddress;
 
 	ret = usb_assign_descriptors(f, uasp_fs_function_desc,
 			uasp_hs_function_desc, uasp_ss_function_desc,
@@ -2051,9 +2029,14 @@ static void tcm_delayed_set_alt(struct work_struct *wq)
 
 static int tcm_get_alt(struct usb_function *f, unsigned intf)
 {
-	if (intf == bot_intf_desc.bInterfaceNumber)
+	struct f_uas *fu = to_f_uas(f);
+
+	if (fu->iface != intf)
+		return -EOPNOTSUPP;
+
+	if (fu->flags & USBG_IS_BOT)
 		return USB_G_ALT_INT_BBB;
-	if (intf == uasp_intf_desc.bInterfaceNumber)
+	else if (fu->flags & USBG_IS_UAS)
 		return USB_G_ALT_INT_UAS;
 
 	return -EOPNOTSUPP;
@@ -2063,6 +2046,9 @@ static int tcm_set_alt(struct usb_function *f, unsigned intf, unsigned alt)
 {
 	struct f_uas *fu = to_f_uas(f);
 
+	if (fu->iface != intf)
+		return -EOPNOTSUPP;
+
 	if ((alt == USB_G_ALT_INT_BBB) || (alt == USB_G_ALT_INT_UAS)) {
 		struct guas_setup_wq *work;
 
diff --git a/drivers/usb/gadget/function/u_ether.c b/drivers/usb/gadget/function/u_ether.c
index 09e2838917e2..f58590bf5e02 100644
--- a/drivers/usb/gadget/function/u_ether.c
+++ b/drivers/usb/gadget/function/u_ether.c
@@ -1052,8 +1052,8 @@ void gether_suspend(struct gether *link)
 		 * There is a transfer in progress. So we trigger a remote
 		 * wakeup to inform the host.
 		 */
-		ether_wakeup_host(dev->port_usb);
-		return;
+		if (!ether_wakeup_host(dev->port_usb))
+			return;
 	}
 	spin_lock_irqsave(&dev->lock, flags);
 	link->is_suspend = true;
diff --git a/drivers/usb/gadget/function/u_serial.c b/drivers/usb/gadget/function/u_serial.c
index bc143a86c2dd..2412f81f4412 100644
--- a/drivers/usb/gadget/function/u_serial.c
+++ b/drivers/usb/gadget/function/u_serial.c
@@ -294,8 +294,8 @@ __acquires(&port->port_lock)
 			break;
 	}
 
-	if (do_tty_wake && port->port.tty)
-		tty_wakeup(port->port.tty);
+	if (do_tty_wake)
+		tty_port_tty_wakeup(&port->port);
 	return status;
 }
 
@@ -543,20 +543,16 @@ static int gs_alloc_requests(struct usb_ep *ep, struct list_head *head,
 static int gs_start_io(struct gs_port *port)
 {
 	struct list_head	*head = &port->read_pool;
-	struct usb_ep		*ep;
+	struct usb_ep		*ep = port->port_usb->out;
 	int			status;
 	unsigned		started;
 
-	if (!port->port_usb || !port->port.tty)
-		return -EIO;
-
 	/* Allocate RX and TX I/O buffers.  We can't easily do this much
 	 * earlier (with GFP_KERNEL) because the requests are coupled to
 	 * endpoints, as are the packet sizes we'll be using.  Different
 	 * configurations may use different endpoints with a given port;
 	 * and high speed vs full speed changes packet sizes too.
 	 */
-	ep = port->port_usb->out;
 	status = gs_alloc_requests(ep, head, gs_read_complete,
 		&port->read_allocated);
 	if (status)
@@ -577,7 +573,7 @@ static int gs_start_io(struct gs_port *port)
 		gs_start_tx(port);
 		/* Unblock any pending writes into our circular buffer, in case
 		 * we didn't in gs_start_tx() */
-		tty_wakeup(port->port.tty);
+		tty_port_tty_wakeup(&port->port);
 	} else {
 		/* Free reqs only if we are still connected */
 		if (port->port_usb) {
@@ -1420,10 +1416,6 @@ void gserial_disconnect(struct gserial *gser)
 	/* REVISIT as above: how best to track this? */
 	port->port_line_coding = gser->port_line_coding;
 
-	/* disable endpoints, aborting down any active I/O */
-	usb_ep_disable(gser->out);
-	usb_ep_disable(gser->in);
-
 	port->port_usb = NULL;
 	gser->ioport = NULL;
 	if (port->port.count > 0) {
@@ -1435,6 +1427,10 @@ void gserial_disconnect(struct gserial *gser)
 	spin_unlock(&port->port_lock);
 	spin_unlock_irqrestore(&serial_port_lock, flags);
 
+	/* disable endpoints, aborting down any active I/O */
+	usb_ep_disable(gser->out);
+	usb_ep_disable(gser->in);
+
 	/* finally, free any unused/unusable I/O buffers */
 	spin_lock_irqsave(&port->port_lock, flags);
 	if (port->port.count == 0)
diff --git a/drivers/usb/gadget/udc/aspeed-vhub/dev.c b/drivers/usb/gadget/udc/aspeed-vhub/dev.c
index 573109ca5b79..a09f72772e6e 100644
--- a/drivers/usb/gadget/udc/aspeed-vhub/dev.c
+++ b/drivers/usb/gadget/udc/aspeed-vhub/dev.c
@@ -548,6 +548,9 @@ int ast_vhub_init_dev(struct ast_vhub *vhub, unsigned int idx)
 	d->vhub = vhub;
 	d->index = idx;
 	d->name = devm_kasprintf(parent, GFP_KERNEL, "port%d", idx+1);
+	if (!d->name)
+		return -ENOMEM;
+
 	d->regs = vhub->regs + 0x100 + 0x10 * idx;
 
 	ast_vhub_init_ep0(vhub, &d->ep0, d);
diff --git a/drivers/usb/gadget/udc/core.c b/drivers/usb/gadget/udc/core.c
index a6f46364be65..d709e24c1fd4 100644
--- a/drivers/usb/gadget/udc/core.c
+++ b/drivers/usb/gadget/udc/core.c
@@ -1543,8 +1543,8 @@ void usb_del_gadget(struct usb_gadget *gadget)
 
 	kobject_uevent(&udc->dev.kobj, KOBJ_REMOVE);
 	sysfs_remove_link(&udc->dev.kobj, "gadget");
-	flush_work(&gadget->work);
 	device_del(&gadget->dev);
+	flush_work(&gadget->work);
 	ida_free(&gadget_id_numbers, gadget->id_number);
 	cancel_work_sync(&udc->vbus_work);
 	device_unregister(&udc->dev);
@@ -1570,7 +1570,7 @@ static int gadget_match_driver(struct device *dev, const struct device_driver *d
 {
 	struct usb_gadget *gadget = dev_to_usb_gadget(dev);
 	struct usb_udc *udc = gadget->udc;
-	struct usb_gadget_driver *driver = container_of(drv,
+	const struct usb_gadget_driver *driver = container_of(drv,
 			struct usb_gadget_driver, driver);
 
 	/* If the driver specifies a udc_name, it must match the UDC's name */
diff --git a/drivers/usb/gadget/udc/renesas_usb3.c b/drivers/usb/gadget/udc/renesas_usb3.c
index 3b01734ce1b7..a93ad93390ba 100644
--- a/drivers/usb/gadget/udc/renesas_usb3.c
+++ b/drivers/usb/gadget/udc/renesas_usb3.c
@@ -310,7 +310,7 @@ struct renesas_usb3_request {
 	struct list_head	queue;
 };
 
-#define USB3_EP_NAME_SIZE	8
+#define USB3_EP_NAME_SIZE	16
 struct renesas_usb3_ep {
 	struct usb_ep ep;
 	struct renesas_usb3 *usb3;
diff --git a/drivers/usb/gadget/udc/tegra-xudc.c b/drivers/usb/gadget/udc/tegra-xudc.c
index 7aa46d426f31..9bb54da8a6ae 100644
--- a/drivers/usb/gadget/udc/tegra-xudc.c
+++ b/drivers/usb/gadget/udc/tegra-xudc.c
@@ -1749,6 +1749,10 @@ static int __tegra_xudc_ep_disable(struct tegra_xudc_ep *ep)
 		val = xudc_readl(xudc, CTRL);
 		val &= ~CTRL_RUN;
 		xudc_writel(xudc, val, CTRL);
+
+		val = xudc_readl(xudc, ST);
+		if (val & ST_RC)
+			xudc_writel(xudc, ST_RC, ST);
 	}
 
 	dev_info(xudc->dev, "ep %u disabled\n", ep->index);
diff --git a/drivers/usb/host/max3421-hcd.c b/drivers/usb/host/max3421-hcd.c
index 0881fdd1823e..dcf31a592f5d 100644
--- a/drivers/usb/host/max3421-hcd.c
+++ b/drivers/usb/host/max3421-hcd.c
@@ -1946,6 +1946,12 @@ max3421_remove(struct spi_device *spi)
 	usb_put_hcd(hcd);
 }
 
+static const struct spi_device_id max3421_spi_ids[] = {
+	{ "max3421" },
+	{ },
+};
+MODULE_DEVICE_TABLE(spi, max3421_spi_ids);
+
 static const struct of_device_id max3421_of_match_table[] = {
 	{ .compatible = "maxim,max3421", },
 	{},
@@ -1955,6 +1961,7 @@ MODULE_DEVICE_TABLE(of, max3421_of_match_table);
 static struct spi_driver max3421_driver = {
 	.probe		= max3421_probe,
 	.remove		= max3421_remove,
+	.id_table	= max3421_spi_ids,
 	.driver		= {
 		.name	= "max3421-hcd",
 		.of_match_table = max3421_of_match_table,
diff --git a/drivers/usb/host/ohci-pci.c b/drivers/usb/host/ohci-pci.c
index 900ea0d368e0..9f0a6b27e47c 100644
--- a/drivers/usb/host/ohci-pci.c
+++ b/drivers/usb/host/ohci-pci.c
@@ -165,6 +165,25 @@ static int ohci_quirk_amd700(struct usb_hcd *hcd)
 	return 0;
 }
 
+static int ohci_quirk_loongson(struct usb_hcd *hcd)
+{
+	struct pci_dev *pdev = to_pci_dev(hcd->self.controller);
+
+	/*
+	 * Loongson's LS7A OHCI controller (rev 0x02) has a
+	 * flaw. MMIO register with offset 0x60/64 is treated
+	 * as legacy PS2-compatible keyboard/mouse interface.
+	 * Since OHCI only use 4KB BAR resource, LS7A OHCI's
+	 * 32KB BAR is wrapped around (the 2nd 4KB BAR space
+	 * is the same as the 1st 4KB internally). So add 4KB
+	 * offset (0x1000) to the OHCI registers as a quirk.
+	 */
+	if (pdev->revision == 0x2)
+		hcd->regs += SZ_4K;	/* SZ_4K = 0x1000 */
+
+	return 0;
+}
+
 static int ohci_quirk_qemu(struct usb_hcd *hcd)
 {
 	struct ohci_hcd *ohci = hcd_to_ohci(hcd);
@@ -225,6 +244,10 @@ static const struct pci_device_id ohci_pci_quirks[] = {
 		.driver_data = (unsigned long)ohci_quirk_amd700,
 	},
 	{
+		PCI_DEVICE(PCI_VENDOR_ID_LOONGSON, 0x7a24),
+		.driver_data = (unsigned long)ohci_quirk_loongson,
+	},
+	{
 		.vendor		= PCI_VENDOR_ID_APPLE,
 		.device		= 0x003f,
 		.subvendor	= PCI_SUBVENDOR_ID_REDHAT_QUMRANET,
diff --git a/drivers/usb/host/pci-quirks.c b/drivers/usb/host/pci-quirks.c
index 1f9c1b1435d8..0404489c2f6a 100644
--- a/drivers/usb/host/pci-quirks.c
+++ b/drivers/usb/host/pci-quirks.c
@@ -958,6 +958,15 @@ static void quirk_usb_disable_ehci(struct pci_dev *pdev)
 	 * booting from USB disk or using a usb keyboard
 	 */
 	hcc_params = readl(base + EHCI_HCC_PARAMS);
+
+	/* LS7A EHCI controller doesn't have extended capabilities, the
+	 * EECP (EHCI Extended Capabilities Pointer) field of HCCPARAMS
+	 * register should be 0x0 but it reads as 0xa0.  So clear it to
+	 * avoid error messages on boot.
+	 */
+	if (pdev->vendor == PCI_VENDOR_ID_LOONGSON && pdev->device == 0x7a14)
+		hcc_params &= ~(0xffL << 8);
+
 	offset = (hcc_params >> 8) & 0xff;
 	while (offset && --count) {
 		pci_read_config_dword(pdev, offset, &cap);
diff --git a/drivers/usb/host/uhci-platform.c b/drivers/usb/host/uhci-platform.c
index 3dec5dd3a0d5..712389599d46 100644
--- a/drivers/usb/host/uhci-platform.c
+++ b/drivers/usb/host/uhci-platform.c
@@ -121,7 +121,7 @@ static int uhci_hcd_platform_probe(struct platform_device *pdev)
 	}
 
 	/* Get and enable clock if any specified */
-	uhci->clk = devm_clk_get(&pdev->dev, NULL);
+	uhci->clk = devm_clk_get_optional(&pdev->dev, NULL);
 	if (IS_ERR(uhci->clk)) {
 		ret = PTR_ERR(uhci->clk);
 		goto err_rmr;
diff --git a/drivers/usb/host/xhci-dbgcap.c b/drivers/usb/host/xhci-dbgcap.c
index 241d7aa1fbc2..bdc664ad6a93 100644
--- a/drivers/usb/host/xhci-dbgcap.c
+++ b/drivers/usb/host/xhci-dbgcap.c
@@ -651,6 +651,10 @@ static void xhci_dbc_stop(struct xhci_dbc *dbc)
 	case DS_DISABLED:
 		return;
 	case DS_CONFIGURED:
+		spin_lock(&dbc->lock);
+		xhci_dbc_flush_requests(dbc);
+		spin_unlock(&dbc->lock);
+
 		if (dbc->driver->disconnect)
 			dbc->driver->disconnect(dbc);
 		break;
@@ -822,6 +826,7 @@ static enum evtreturn xhci_dbc_do_handle_events(struct xhci_dbc *dbc)
 {
 	dma_addr_t		deq;
 	union xhci_trb		*evt;
+	enum evtreturn		ret = EVT_DONE;
 	u32			ctrl, portsc;
 	bool			update_erdp = false;
 
@@ -906,6 +911,7 @@ static enum evtreturn xhci_dbc_do_handle_events(struct xhci_dbc *dbc)
 			break;
 		case TRB_TYPE(TRB_TRANSFER):
 			dbc_handle_xfer_event(dbc, evt);
+			ret = EVT_XFER_DONE;
 			break;
 		default:
 			break;
@@ -924,7 +930,7 @@ static enum evtreturn xhci_dbc_do_handle_events(struct xhci_dbc *dbc)
 		lo_hi_writeq(deq, &dbc->regs->erdp);
 	}
 
-	return EVT_DONE;
+	return ret;
 }
 
 static void xhci_dbc_handle_events(struct work_struct *work)
@@ -933,6 +939,7 @@ static void xhci_dbc_handle_events(struct work_struct *work)
 	struct xhci_dbc		*dbc;
 	unsigned long		flags;
 	unsigned int		poll_interval;
+	unsigned long		busypoll_timelimit;
 
 	dbc = container_of(to_delayed_work(work), struct xhci_dbc, event_work);
 	poll_interval = dbc->poll_interval;
@@ -951,10 +958,20 @@ static void xhci_dbc_handle_events(struct work_struct *work)
 			dbc->driver->disconnect(dbc);
 		break;
 	case EVT_DONE:
-		/* set fast poll rate if there are pending data transfers */
+		/*
+		 * Set fast poll rate if there are pending out transfers, or
+		 * a transfer was recently processed
+		 */
+		busypoll_timelimit = dbc->xfer_timestamp +
+			msecs_to_jiffies(DBC_XFER_INACTIVITY_TIMEOUT);
+
 		if (!list_empty(&dbc->eps[BULK_OUT].list_pending) ||
-		    !list_empty(&dbc->eps[BULK_IN].list_pending))
-			poll_interval = 1;
+		    time_is_after_jiffies(busypoll_timelimit))
+			poll_interval = 0;
+		break;
+	case EVT_XFER_DONE:
+		dbc->xfer_timestamp = jiffies;
+		poll_interval = 0;
 		break;
 	default:
 		dev_info(dbc->dev, "stop handling dbc events\n");
diff --git a/drivers/usb/host/xhci-dbgcap.h b/drivers/usb/host/xhci-dbgcap.h
index 9dc8f4d8077c..47ac72c2286d 100644
--- a/drivers/usb/host/xhci-dbgcap.h
+++ b/drivers/usb/host/xhci-dbgcap.h
@@ -96,6 +96,7 @@ struct dbc_ep {
 #define DBC_WRITE_BUF_SIZE		8192
 #define DBC_POLL_INTERVAL_DEFAULT	64	/* milliseconds */
 #define DBC_POLL_INTERVAL_MAX		5000	/* milliseconds */
+#define DBC_XFER_INACTIVITY_TIMEOUT	10	/* milliseconds */
 /*
  * Private structure for DbC hardware state:
  */
@@ -142,6 +143,7 @@ struct xhci_dbc {
 	enum dbc_state			state;
 	struct delayed_work		event_work;
 	unsigned int			poll_interval;	/* ms */
+	unsigned long			xfer_timestamp;
 	unsigned			resume_required:1;
 	struct dbc_ep			eps[2];
 
@@ -187,6 +189,7 @@ struct dbc_request {
 enum evtreturn {
 	EVT_ERR	= -1,
 	EVT_DONE,
+	EVT_XFER_DONE,
 	EVT_GSER,
 	EVT_DISC,
 };
diff --git a/drivers/usb/host/xhci-dbgtty.c b/drivers/usb/host/xhci-dbgtty.c
index d719c16ea30b..2b8558005cbb 100644
--- a/drivers/usb/host/xhci-dbgtty.c
+++ b/drivers/usb/host/xhci-dbgtty.c
@@ -585,6 +585,7 @@ int dbc_tty_init(void)
 	dbc_tty_driver->type = TTY_DRIVER_TYPE_SERIAL;
 	dbc_tty_driver->subtype = SERIAL_TYPE_NORMAL;
 	dbc_tty_driver->init_termios = tty_std_termios;
+	dbc_tty_driver->init_termios.c_lflag &= ~ECHO;
 	dbc_tty_driver->init_termios.c_cflag =
 			B9600 | CS8 | CREAD | HUPCL | CLOCAL;
 	dbc_tty_driver->init_termios.c_ispeed = 9600;
diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c
index 8d774f19271e..1952e0503340 100644
--- a/drivers/usb/host/xhci-hub.c
+++ b/drivers/usb/host/xhci-hub.c
@@ -12,6 +12,7 @@
 #include <linux/slab.h>
 #include <linux/unaligned.h>
 #include <linux/bitfield.h>
+#include <linux/pci.h>
 
 #include "xhci.h"
 #include "xhci-trace.h"
@@ -770,9 +771,16 @@ static int xhci_exit_test_mode(struct xhci_hcd *xhci)
 enum usb_link_tunnel_mode xhci_port_is_tunneled(struct xhci_hcd *xhci,
 						struct xhci_port *port)
 {
+	struct usb_hcd *hcd;
 	void __iomem *base;
 	u32 offset;
 
+	/* Don't try and probe this capability for non-Intel hosts */
+	hcd = xhci_to_hcd(xhci);
+	if (!dev_is_pci(hcd->self.controller) ||
+	    to_pci_dev(hcd->self.controller)->vendor != PCI_VENDOR_ID_INTEL)
+		return USB_LINK_UNKNOWN;
+
 	base = &xhci->cap_regs->hc_capbase;
 	offset = xhci_find_next_ext_cap(base, 0, XHCI_EXT_CAPS_INTEL_SPR_SHADOW);
 
@@ -1870,9 +1878,10 @@ int xhci_bus_resume(struct usb_hcd *hcd)
 	int max_ports, port_index;
 	int sret;
 	u32 next_state;
-	u32 temp, portsc;
+	u32 portsc;
 	struct xhci_hub *rhub;
 	struct xhci_port **ports;
+	bool disabled_irq = false;
 
 	rhub = xhci_get_rhub(hcd);
 	ports = rhub->ports;
@@ -1888,17 +1897,20 @@ int xhci_bus_resume(struct usb_hcd *hcd)
 		return -ESHUTDOWN;
 	}
 
-	/* delay the irqs */
-	temp = readl(&xhci->op_regs->command);
-	temp &= ~CMD_EIE;
-	writel(temp, &xhci->op_regs->command);
-
 	/* bus specific resume for ports we suspended at bus_suspend */
-	if (hcd->speed >= HCD_USB3)
+	if (hcd->speed >= HCD_USB3) {
 		next_state = XDEV_U0;
-	else
+	} else {
 		next_state = XDEV_RESUME;
-
+		if (bus_state->bus_suspended) {
+			/*
+			 * prevent port event interrupts from interfering
+			 * with usb2 port resume process
+			 */
+			xhci_disable_interrupter(xhci->interrupters[0]);
+			disabled_irq = true;
+		}
+	}
 	port_index = max_ports;
 	while (port_index--) {
 		portsc = readl(ports[port_index]->addr);
@@ -1966,11 +1978,9 @@ int xhci_bus_resume(struct usb_hcd *hcd)
 	(void) readl(&xhci->op_regs->command);
 
 	bus_state->next_statechange = jiffies + msecs_to_jiffies(5);
-	/* re-enable irqs */
-	temp = readl(&xhci->op_regs->command);
-	temp |= CMD_EIE;
-	writel(temp, &xhci->op_regs->command);
-	temp = readl(&xhci->op_regs->command);
+	/* re-enable interrupter */
+	if (disabled_irq)
+		xhci_enable_interrupter(xhci->interrupters[0]);
 
 	spin_unlock_irqrestore(&xhci->lock, flags);
 	return 0;
diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c
index d2900197a49e..1111650757ea 100644
--- a/drivers/usb/host/xhci-mem.c
+++ b/drivers/usb/host/xhci-mem.c
@@ -1172,6 +1172,8 @@ int xhci_setup_addressable_virt_dev(struct xhci_hcd *xhci, struct usb_device *ud
 	ep0_ctx->deq = cpu_to_le64(dev->eps[0].ring->first_seg->dma |
 				   dev->eps[0].ring->cycle_state);
 
+	ep0_ctx->tx_info = cpu_to_le32(EP_AVG_TRB_LENGTH(8));
+
 	trace_xhci_setup_addressable_virt_device(dev);
 
 	/* Steps 7 and 8 were done in xhci_alloc_virt_device() */
@@ -1426,6 +1428,10 @@ int xhci_endpoint_init(struct xhci_hcd *xhci,
 	/* Periodic endpoint bInterval limit quirk */
 	if (usb_endpoint_xfer_int(&ep->desc) ||
 	    usb_endpoint_xfer_isoc(&ep->desc)) {
+		if ((xhci->quirks & XHCI_LIMIT_ENDPOINT_INTERVAL_9) &&
+		    interval >= 9) {
+			interval = 8;
+		}
 		if ((xhci->quirks & XHCI_LIMIT_ENDPOINT_INTERVAL_7) &&
 		    udev->speed >= USB_SPEED_HIGH &&
 		    interval >= 7) {
@@ -1959,7 +1965,6 @@ no_bw:
 	xhci->interrupters = NULL;
 
 	xhci->page_size = 0;
-	xhci->page_shift = 0;
 	xhci->usb2_rhub.bus_state.bus_suspended = 0;
 	xhci->usb3_rhub.bus_state.bus_suspended = 0;
 }
@@ -2378,6 +2383,22 @@ xhci_create_secondary_interrupter(struct usb_hcd *hcd, unsigned int segs,
 }
 EXPORT_SYMBOL_GPL(xhci_create_secondary_interrupter);
 
+static void xhci_hcd_page_size(struct xhci_hcd *xhci)
+{
+	u32 page_size;
+
+	page_size = readl(&xhci->op_regs->page_size) & XHCI_PAGE_SIZE_MASK;
+	if (!is_power_of_2(page_size)) {
+		xhci_warn(xhci, "Invalid page size register = 0x%x\n", page_size);
+		/* Fallback to 4K page size, since that's common */
+		page_size = 1;
+	}
+
+	xhci->page_size = page_size << 12;
+	xhci_dbg_trace(xhci, trace_xhci_dbg_init, "HCD page size set to %iK",
+		       xhci->page_size >> 10);
+}
+
 int xhci_mem_init(struct xhci_hcd *xhci, gfp_t flags)
 {
 	struct xhci_interrupter *ir;
@@ -2385,7 +2406,7 @@ int xhci_mem_init(struct xhci_hcd *xhci, gfp_t flags)
 	dma_addr_t	dma;
 	unsigned int	val, val2;
 	u64		val_64;
-	u32		page_size, temp;
+	u32		temp;
 	int		i;
 
 	INIT_LIST_HEAD(&xhci->cmd_list);
@@ -2394,20 +2415,7 @@ int xhci_mem_init(struct xhci_hcd *xhci, gfp_t flags)
 	INIT_DELAYED_WORK(&xhci->cmd_timer, xhci_handle_command_timeout);
 	init_completion(&xhci->cmd_ring_stop_completion);
 
-	page_size = readl(&xhci->op_regs->page_size);
-	xhci_dbg_trace(xhci, trace_xhci_dbg_init,
-			"Supported page size register = 0x%x", page_size);
-	i = ffs(page_size);
-	if (i < 16)
-		xhci_dbg_trace(xhci, trace_xhci_dbg_init,
-			"Supported page size of %iK", (1 << (i+12)) / 1024);
-	else
-		xhci_warn(xhci, "WARN: no supported page size\n");
-	/* Use 4K pages, since that's common and the minimum the HC supports */
-	xhci->page_shift = 12;
-	xhci->page_size = 1 << xhci->page_shift;
-	xhci_dbg_trace(xhci, trace_xhci_dbg_init,
-			"HCD page size set to %iK", xhci->page_size / 1024);
+	xhci_hcd_page_size(xhci);
 
 	/*
 	 * Program the Number of Device Slots Enabled field in the CONFIG
@@ -2443,7 +2451,8 @@ int xhci_mem_init(struct xhci_hcd *xhci, gfp_t flags)
 	 * and our use of dma addresses in the trb_address_map radix tree needs
 	 * TRB_SEGMENT_SIZE alignment, so we pick the greater alignment need.
 	 */
-	if (xhci->quirks & XHCI_ZHAOXIN_TRB_FETCH)
+	if (xhci->quirks & XHCI_TRB_OVERFETCH)
+		/* Buggy HC prefetches beyond segment bounds - allocate dummy space at the end */
 		xhci->segment_pool = dma_pool_create("xHCI ring segments", dev,
 				TRB_SEGMENT_SIZE * 2, TRB_SEGMENT_SIZE * 2, xhci->page_size * 2);
 	else
diff --git a/drivers/usb/host/xhci-mvebu.c b/drivers/usb/host/xhci-mvebu.c
index 87f1597a0e5a..257e4d79971f 100644
--- a/drivers/usb/host/xhci-mvebu.c
+++ b/drivers/usb/host/xhci-mvebu.c
@@ -73,13 +73,3 @@ int xhci_mvebu_mbus_init_quirk(struct usb_hcd *hcd)
 
 	return 0;
 }
-
-int xhci_mvebu_a3700_init_quirk(struct usb_hcd *hcd)
-{
-	struct xhci_hcd	*xhci = hcd_to_xhci(hcd);
-
-	/* Without reset on resume, the HC won't work at all */
-	xhci->quirks |= XHCI_RESET_ON_RESUME;
-
-	return 0;
-}
diff --git a/drivers/usb/host/xhci-mvebu.h b/drivers/usb/host/xhci-mvebu.h
index 3be021793cc8..9d26e22c4842 100644
--- a/drivers/usb/host/xhci-mvebu.h
+++ b/drivers/usb/host/xhci-mvebu.h
@@ -12,16 +12,10 @@ struct usb_hcd;
 
 #if IS_ENABLED(CONFIG_USB_XHCI_MVEBU)
 int xhci_mvebu_mbus_init_quirk(struct usb_hcd *hcd);
-int xhci_mvebu_a3700_init_quirk(struct usb_hcd *hcd);
 #else
 static inline int xhci_mvebu_mbus_init_quirk(struct usb_hcd *hcd)
 {
 	return 0;
 }
-
-static inline int xhci_mvebu_a3700_init_quirk(struct usb_hcd *hcd)
-{
-	return 0;
-}
 #endif
 #endif /* __LINUX_XHCI_MVEBU_H */
diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index 3ba9902dd209..234efb9731b2 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -28,8 +28,8 @@
 #define SPARSE_CNTL_ENABLE	0xC12C
 
 /* Device for a quirk */
-#define PCI_VENDOR_ID_FRESCO_LOGIC	0x1b73
-#define PCI_DEVICE_ID_FRESCO_LOGIC_PDK	0x1000
+#define PCI_VENDOR_ID_FRESCO_LOGIC		0x1b73
+#define PCI_DEVICE_ID_FRESCO_LOGIC_PDK		0x1000
 #define PCI_DEVICE_ID_FRESCO_LOGIC_FL1009	0x1009
 #define PCI_DEVICE_ID_FRESCO_LOGIC_FL1100	0x1100
 #define PCI_DEVICE_ID_FRESCO_LOGIC_FL1400	0x1400
@@ -38,8 +38,10 @@
 #define PCI_DEVICE_ID_EJ168		0x7023
 #define PCI_DEVICE_ID_EJ188		0x7052
 
-#define PCI_DEVICE_ID_INTEL_LYNXPOINT_XHCI	0x8c31
-#define PCI_DEVICE_ID_INTEL_LYNXPOINT_LP_XHCI	0x9c31
+#define PCI_DEVICE_ID_VIA_VL805			0x3483
+
+#define PCI_DEVICE_ID_INTEL_LYNXPOINT_XHCI		0x8c31
+#define PCI_DEVICE_ID_INTEL_LYNXPOINT_LP_XHCI		0x9c31
 #define PCI_DEVICE_ID_INTEL_WILDCATPOINT_LP_XHCI	0x9cb1
 #define PCI_DEVICE_ID_INTEL_CHERRYVIEW_XHCI		0x22b5
 #define PCI_DEVICE_ID_INTEL_SUNRISEPOINT_H_XHCI		0xa12f
@@ -69,12 +71,22 @@
 #define PCI_DEVICE_ID_INTEL_TITAN_RIDGE_4C_XHCI		0x15ec
 #define PCI_DEVICE_ID_INTEL_TITAN_RIDGE_DD_XHCI		0x15f0
 
+#define PCI_DEVICE_ID_AMD_ARIEL_TYPEC_XHCI		0x13ed
+#define PCI_DEVICE_ID_AMD_ARIEL_TYPEA_XHCI		0x13ee
+#define PCI_DEVICE_ID_AMD_STARSHIP_XHCI			0x148c
+#define PCI_DEVICE_ID_AMD_FIREFLIGHT_15D4_XHCI		0x15d4
+#define PCI_DEVICE_ID_AMD_FIREFLIGHT_15D5_XHCI		0x15d5
+#define PCI_DEVICE_ID_AMD_RAVEN_15E0_XHCI		0x15e0
+#define PCI_DEVICE_ID_AMD_RAVEN_15E1_XHCI		0x15e1
+#define PCI_DEVICE_ID_AMD_RAVEN2_XHCI			0x15e5
 #define PCI_DEVICE_ID_AMD_RENOIR_XHCI			0x1639
 #define PCI_DEVICE_ID_AMD_PROMONTORYA_4			0x43b9
 #define PCI_DEVICE_ID_AMD_PROMONTORYA_3			0x43ba
 #define PCI_DEVICE_ID_AMD_PROMONTORYA_2			0x43bb
 #define PCI_DEVICE_ID_AMD_PROMONTORYA_1			0x43bc
 
+#define PCI_DEVICE_ID_ATI_NAVI10_7316_XHCI		0x7316
+
 #define PCI_DEVICE_ID_ASMEDIA_1042_XHCI			0x1042
 #define PCI_DEVICE_ID_ASMEDIA_1042A_XHCI		0x1142
 #define PCI_DEVICE_ID_ASMEDIA_1142_XHCI			0x1242
@@ -284,6 +296,21 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
 	if (pdev->vendor == PCI_VENDOR_ID_NEC)
 		xhci->quirks |= XHCI_NEC_HOST;
 
+	if (pdev->vendor == PCI_VENDOR_ID_AMD &&
+	    (pdev->device == PCI_DEVICE_ID_AMD_ARIEL_TYPEC_XHCI ||
+	     pdev->device == PCI_DEVICE_ID_AMD_ARIEL_TYPEA_XHCI ||
+	     pdev->device == PCI_DEVICE_ID_AMD_STARSHIP_XHCI ||
+	     pdev->device == PCI_DEVICE_ID_AMD_FIREFLIGHT_15D4_XHCI ||
+	     pdev->device == PCI_DEVICE_ID_AMD_FIREFLIGHT_15D5_XHCI ||
+	     pdev->device == PCI_DEVICE_ID_AMD_RAVEN_15E0_XHCI ||
+	     pdev->device == PCI_DEVICE_ID_AMD_RAVEN_15E1_XHCI ||
+	     pdev->device == PCI_DEVICE_ID_AMD_RAVEN2_XHCI))
+		xhci->quirks |= XHCI_LIMIT_ENDPOINT_INTERVAL_9;
+
+	if (pdev->vendor == PCI_VENDOR_ID_ATI &&
+	    pdev->device == PCI_DEVICE_ID_ATI_NAVI10_7316_XHCI)
+		xhci->quirks |= XHCI_LIMIT_ENDPOINT_INTERVAL_9;
+
 	if (pdev->vendor == PCI_VENDOR_ID_AMD && xhci->hci_version == 0x96)
 		xhci->quirks |= XHCI_AMD_0x96_HOST;
 
@@ -424,8 +451,10 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
 			pdev->device == 0x3432)
 		xhci->quirks |= XHCI_BROKEN_STREAMS;
 
-	if (pdev->vendor == PCI_VENDOR_ID_VIA && pdev->device == 0x3483)
+	if (pdev->vendor == PCI_VENDOR_ID_VIA && pdev->device == PCI_DEVICE_ID_VIA_VL805) {
 		xhci->quirks |= XHCI_LPM_SUPPORT;
+		xhci->quirks |= XHCI_TRB_OVERFETCH;
+	}
 
 	if (pdev->vendor == PCI_VENDOR_ID_ASMEDIA &&
 		pdev->device == PCI_DEVICE_ID_ASMEDIA_1042_XHCI) {
@@ -473,11 +502,11 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
 
 		if (pdev->device == 0x9202) {
 			xhci->quirks |= XHCI_RESET_ON_RESUME;
-			xhci->quirks |= XHCI_ZHAOXIN_TRB_FETCH;
+			xhci->quirks |= XHCI_TRB_OVERFETCH;
 		}
 
 		if (pdev->device == 0x9203)
-			xhci->quirks |= XHCI_ZHAOXIN_TRB_FETCH;
+			xhci->quirks |= XHCI_TRB_OVERFETCH;
 	}
 
 	if (pdev->vendor == PCI_DEVICE_ID_CADENCE &&
@@ -656,8 +685,8 @@ put_runtime_pm:
 }
 EXPORT_SYMBOL_NS_GPL(xhci_pci_common_probe, xhci);
 
-static const struct pci_device_id pci_ids_reject[] = {
-	/* handled by xhci-pci-renesas */
+/* handled by xhci-pci-renesas if enabled */
+static const struct pci_device_id pci_ids_renesas[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_RENESAS, 0x0014) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_RENESAS, 0x0015) },
 	{ /* end: all zeroes */ }
@@ -665,7 +694,8 @@ static const struct pci_device_id pci_ids_reject[] = {
 
 static int xhci_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
 {
-	if (pci_match_id(pci_ids_reject, dev))
+	if (IS_ENABLED(CONFIG_USB_XHCI_PCI_RENESAS) &&
+			pci_match_id(pci_ids_renesas, dev))
 		return -ENODEV;
 
 	return xhci_pci_common_probe(dev, id);
diff --git a/drivers/usb/host/xhci-plat.c b/drivers/usb/host/xhci-plat.c
index e6660472501e..8cf278a40bd9 100644
--- a/drivers/usb/host/xhci-plat.c
+++ b/drivers/usb/host/xhci-plat.c
@@ -106,7 +106,7 @@ static const struct xhci_plat_priv xhci_plat_marvell_armada = {
 };
 
 static const struct xhci_plat_priv xhci_plat_marvell_armada3700 = {
-	.init_quirk = xhci_mvebu_a3700_init_quirk,
+	.quirks = XHCI_RESET_ON_RESUME,
 };
 
 static const struct xhci_plat_priv xhci_plat_brcm = {
@@ -152,7 +152,7 @@ int xhci_plat_probe(struct platform_device *pdev, struct device *sysdev, const s
 	int			ret;
 	int			irq;
 	struct xhci_plat_priv	*priv = NULL;
-	bool			of_match;
+	const struct of_device_id *of_match;
 
 	if (usb_disabled())
 		return -ENODEV;
@@ -326,7 +326,8 @@ int xhci_plat_probe(struct platform_device *pdev, struct device *sysdev, const s
 	}
 
 	usb3_hcd = xhci_get_usb3_hcd(xhci);
-	if (usb3_hcd && HCC_MAX_PSA(xhci->hcc_params) >= 4)
+	if (usb3_hcd && HCC_MAX_PSA(xhci->hcc_params) >= 4 &&
+	    !(xhci->quirks & XHCI_BROKEN_STREAMS))
 		usb3_hcd->can_do_streams = 1;
 
 	if (xhci->shared_hcd) {
diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index b267dae14d39..f6ecb3b9fb14 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -422,7 +422,8 @@ static void xhci_handle_stopped_cmd_ring(struct xhci_hcd *xhci,
 	if ((xhci->cmd_ring->dequeue != xhci->cmd_ring->enqueue) &&
 	    !(xhci->xhc_state & XHCI_STATE_DYING)) {
 		xhci->current_cmd = cur_cmd;
-		xhci_mod_cmd_timer(xhci);
+		if (cur_cmd)
+			xhci_mod_cmd_timer(xhci);
 		xhci_ring_cmd_db(xhci);
 	}
 }
@@ -460,9 +461,8 @@ static int xhci_abort_cmd_ring(struct xhci_hcd *xhci, unsigned long flags)
 	 * In the future we should distinguish between -ENODEV and -ETIMEDOUT
 	 * and try to recover a -ETIMEDOUT with a host controller reset.
 	 */
-	ret = xhci_handshake_check_state(xhci, &xhci->op_regs->cmd_ring,
-			CMD_RING_RUNNING, 0, 5 * 1000 * 1000,
-			XHCI_STATE_REMOVING);
+	ret = xhci_handshake(&xhci->op_regs->cmd_ring,
+			CMD_RING_RUNNING, 0, 5 * 1000 * 1000);
 	if (ret < 0) {
 		xhci_err(xhci, "Abort failed to stop command ring: %d\n", ret);
 		xhci_halt(xhci);
@@ -1155,7 +1155,14 @@ static void xhci_handle_cmd_stop_ep(struct xhci_hcd *xhci, int slot_id,
 	 */
 		switch (GET_EP_CTX_STATE(ep_ctx)) {
 		case EP_STATE_HALTED:
-			xhci_dbg(xhci, "Stop ep completion raced with stall, reset ep\n");
+			xhci_dbg(xhci, "Stop ep completion raced with stall\n");
+			/*
+			 * If the halt happened before Stop Endpoint failed, its transfer event
+			 * should have already been handled and Reset Endpoint should be pending.
+			 */
+			if (ep->ep_state & EP_HALTED)
+				goto reset_done;
+
 			if (ep->ep_state & EP_HAS_STREAMS) {
 				reset_type = EP_SOFT_RESET;
 			} else {
@@ -1166,8 +1173,11 @@ static void xhci_handle_cmd_stop_ep(struct xhci_hcd *xhci, int slot_id,
 			}
 			/* reset ep, reset handler cleans up cancelled tds */
 			err = xhci_handle_halted_endpoint(xhci, ep, td, reset_type);
+			xhci_dbg(xhci, "Stop ep completion resetting ep, status %d\n", err);
 			if (err)
 				break;
+reset_done:
+			/* Reset EP handler will clean up cancelled TDs */
 			ep->ep_state &= ~EP_STOP_CMD_PENDING;
 			return;
 		case EP_STATE_STOPPED:
@@ -1189,16 +1199,19 @@ static void xhci_handle_cmd_stop_ep(struct xhci_hcd *xhci, int slot_id,
 			 * Stopped state, but it will soon change to Running.
 			 *
 			 * Assume this bug on unexpected Stop Endpoint failures.
-			 * Keep retrying until the EP starts and stops again, on
-			 * chips where this is known to help. Wait for 100ms.
+			 * Keep retrying until the EP starts and stops again.
 			 */
-			if (time_is_before_jiffies(ep->stop_time + msecs_to_jiffies(100)))
-				break;
 			fallthrough;
 		case EP_STATE_RUNNING:
 			/* Race, HW handled stop ep cmd before ep was running */
 			xhci_dbg(xhci, "Stop ep completion ctx error, ctx_state %d\n",
 					GET_EP_CTX_STATE(ep_ctx));
+			/*
+			 * Don't retry forever if we guessed wrong or a defective HC never starts
+			 * the EP or says 'Running' but fails the command. We must give back TDs.
+			 */
+			if (time_is_before_jiffies(ep->stop_time + msecs_to_jiffies(100)))
+				break;
 
 			command = xhci_alloc_command(xhci, false, GFP_ATOMIC);
 			if (!command) {
@@ -1300,12 +1313,15 @@ static void xhci_kill_endpoint_urbs(struct xhci_hcd *xhci,
  */
 void xhci_hc_died(struct xhci_hcd *xhci)
 {
+	bool notify;
 	int i, j;
 
 	if (xhci->xhc_state & XHCI_STATE_DYING)
 		return;
 
-	xhci_err(xhci, "xHCI host controller not responding, assume dead\n");
+	notify = !(xhci->xhc_state & XHCI_STATE_REMOVING);
+	if (notify)
+		xhci_err(xhci, "xHCI host controller not responding, assume dead\n");
 	xhci->xhc_state |= XHCI_STATE_DYING;
 
 	xhci_cleanup_command_queue(xhci);
@@ -1319,7 +1335,7 @@ void xhci_hc_died(struct xhci_hcd *xhci)
 	}
 
 	/* inform usb core hc died if PCI remove isn't already handling it */
-	if (!(xhci->xhc_state & XHCI_STATE_REMOVING))
+	if (notify)
 		usb_hc_died(xhci_to_hcd(xhci));
 }
 
@@ -2641,6 +2657,22 @@ static int handle_transferless_tx_event(struct xhci_hcd *xhci, struct xhci_virt_
 	return 0;
 }
 
+static bool xhci_spurious_success_tx_event(struct xhci_hcd *xhci,
+					   struct xhci_ring *ring)
+{
+	switch (ring->old_trb_comp_code) {
+	case COMP_SHORT_PACKET:
+		return xhci->quirks & XHCI_SPURIOUS_SUCCESS;
+	case COMP_USB_TRANSACTION_ERROR:
+	case COMP_BABBLE_DETECTED_ERROR:
+	case COMP_ISOCH_BUFFER_OVERRUN:
+		return xhci->quirks & XHCI_ETRON_HOST &&
+			ring->type == TYPE_ISOC;
+	default:
+		return false;
+	}
+}
+
 /*
  * If this function returns an error condition, it means it got a Transfer
  * event with a corrupted Slot ID, Endpoint ID, or TRB DMA address.
@@ -2661,6 +2693,7 @@ static int handle_tx_event(struct xhci_hcd *xhci,
 	int status = -EINPROGRESS;
 	struct xhci_ep_ctx *ep_ctx;
 	u32 trb_comp_code;
+	bool ring_xrun_event = false;
 
 	slot_id = TRB_TO_SLOT_ID(le32_to_cpu(event->flags));
 	ep_index = TRB_TO_EP_ID(le32_to_cpu(event->flags)) - 1;
@@ -2694,8 +2727,8 @@ static int handle_tx_event(struct xhci_hcd *xhci,
 	case COMP_SUCCESS:
 		if (EVENT_TRB_LEN(le32_to_cpu(event->transfer_len)) != 0) {
 			trb_comp_code = COMP_SHORT_PACKET;
-			xhci_dbg(xhci, "Successful completion on short TX for slot %u ep %u with last td short %d\n",
-				 slot_id, ep_index, ep_ring->last_td_was_short);
+			xhci_dbg(xhci, "Successful completion on short TX for slot %u ep %u with last td comp code %d\n",
+				 slot_id, ep_index, ep_ring->old_trb_comp_code);
 		}
 		break;
 	case COMP_SHORT_PACKET:
@@ -2767,14 +2800,12 @@ static int handle_tx_event(struct xhci_hcd *xhci,
 		 * Underrun Event for OUT Isoch endpoint.
 		 */
 		xhci_dbg(xhci, "Underrun event on slot %u ep %u\n", slot_id, ep_index);
-		if (ep->skip)
-			break;
-		return 0;
+		ring_xrun_event = true;
+		break;
 	case COMP_RING_OVERRUN:
 		xhci_dbg(xhci, "Overrun event on slot %u ep %u\n", slot_id, ep_index);
-		if (ep->skip)
-			break;
-		return 0;
+		ring_xrun_event = true;
+		break;
 	case COMP_MISSED_SERVICE_ERROR:
 		/*
 		 * When encounter missed service error, one or more isoc tds
@@ -2786,7 +2817,7 @@ static int handle_tx_event(struct xhci_hcd *xhci,
 		xhci_dbg(xhci,
 			 "Miss service interval error for slot %u ep %u, set skip flag\n",
 			 slot_id, ep_index);
-		return 0;
+		break;
 	case COMP_NO_PING_RESPONSE_ERROR:
 		ep->skip = true;
 		xhci_dbg(xhci,
@@ -2837,6 +2868,10 @@ static int handle_tx_event(struct xhci_hcd *xhci,
 		xhci_td_cleanup(xhci, td, ep_ring, td->status);
 	}
 
+	/* Missed TDs will be skipped on the next event */
+	if (trb_comp_code == COMP_MISSED_SERVICE_ERROR)
+		return 0;
+
 	if (list_empty(&ep_ring->td_list)) {
 		/*
 		 * Don't print wanings if ring is empty due to a stopped endpoint generating an
@@ -2846,7 +2881,8 @@ static int handle_tx_event(struct xhci_hcd *xhci,
 		 */
 		if (trb_comp_code != COMP_STOPPED &&
 		    trb_comp_code != COMP_STOPPED_LENGTH_INVALID &&
-		    !ep_ring->last_td_was_short) {
+		    !ring_xrun_event &&
+		    !xhci_spurious_success_tx_event(xhci, ep_ring)) {
 			xhci_warn(xhci, "Event TRB for slot %u ep %u with no TDs queued\n",
 				  slot_id, ep_index);
 		}
@@ -2865,6 +2901,10 @@ static int handle_tx_event(struct xhci_hcd *xhci,
 		if (!ep_seg) {
 
 			if (ep->skip && usb_endpoint_xfer_isoc(&td->urb->ep->desc)) {
+				/* this event is unlikely to match any TD, don't skip them all */
+				if (trb_comp_code == COMP_STOPPED_LENGTH_INVALID)
+					return 0;
+
 				skip_isoc_td(xhci, td, ep, status);
 				if (!list_empty(&ep_ring->td_list))
 					continue;
@@ -2876,6 +2916,10 @@ static int handle_tx_event(struct xhci_hcd *xhci,
 				goto check_endpoint_halted;
 			}
 
+			/* TD was queued after xrun, maybe xrun was on a link, don't panic yet */
+			if (ring_xrun_event)
+				return 0;
+
 			/*
 			 * Skip the Force Stopped Event. The 'ep_trb' of FSE is not in the current
 			 * TD pointed by 'ep_ring->dequeue' because that the hardware dequeue
@@ -2890,11 +2934,12 @@ static int handle_tx_event(struct xhci_hcd *xhci,
 
 			/*
 			 * Some hosts give a spurious success event after a short
-			 * transfer. Ignore it.
+			 * transfer or error on last TRB. Ignore it.
 			 */
-			if ((xhci->quirks & XHCI_SPURIOUS_SUCCESS) &&
-			    ep_ring->last_td_was_short) {
-				ep_ring->last_td_was_short = false;
+			if (xhci_spurious_success_tx_event(xhci, ep_ring)) {
+				xhci_dbg(xhci, "Spurious event dma %pad, comp_code %u after %u\n",
+					 &ep_trb_dma, trb_comp_code, ep_ring->old_trb_comp_code);
+				ep_ring->old_trb_comp_code = 0;
 				return 0;
 			}
 
@@ -2922,10 +2967,11 @@ static int handle_tx_event(struct xhci_hcd *xhci,
 	 */
 	} while (ep->skip);
 
-	if (trb_comp_code == COMP_SHORT_PACKET)
-		ep_ring->last_td_was_short = true;
-	else
-		ep_ring->last_td_was_short = false;
+	ep_ring->old_trb_comp_code = trb_comp_code;
+
+	/* Get out if a TD was queued at enqueue after the xrun occurred */
+	if (ring_xrun_event)
+		return 0;
 
 	ep_trb = &ep_seg->trbs[(ep_trb_dma - ep_seg->dma) / sizeof(*ep_trb)];
 	trace_xhci_handle_transfer(ep_ring, (struct xhci_generic_trb *) ep_trb);
@@ -3773,7 +3819,7 @@ int xhci_queue_ctrl_tx(struct xhci_hcd *xhci, gfp_t mem_flags,
 		 * enqueue a No Op TRB, this can prevent the Setup and Data Stage
 		 * TRB to be breaked by the Link TRB.
 		 */
-		if (trb_is_link(ep_ring->enqueue + 1)) {
+		if (last_trb_on_seg(ep_ring->enq_seg, ep_ring->enqueue + 1)) {
 			field = TRB_TYPE(TRB_TR_NOOP) | ep_ring->cycle_state;
 			queue_trb(xhci, ep_ring, false, 0, 0,
 					TRB_INTR_TARGET(0), field);
@@ -4335,7 +4381,8 @@ static int queue_command(struct xhci_hcd *xhci, struct xhci_command *cmd,
 
 	if ((xhci->xhc_state & XHCI_STATE_DYING) ||
 		(xhci->xhc_state & XHCI_STATE_HALTED)) {
-		xhci_dbg(xhci, "xHCI dying or halted, can't queue_command\n");
+		xhci_dbg(xhci, "xHCI dying or halted, can't queue_command. state: 0x%x\n",
+			 xhci->xhc_state);
 		return -ESHUTDOWN;
 	}
 
diff --git a/drivers/usb/host/xhci-tegra.c b/drivers/usb/host/xhci-tegra.c
index 76f228e7443c..89b3079194d7 100644
--- a/drivers/usb/host/xhci-tegra.c
+++ b/drivers/usb/host/xhci-tegra.c
@@ -1363,6 +1363,7 @@ static void tegra_xhci_id_work(struct work_struct *work)
 	tegra->otg_usb3_port = tegra_xusb_padctl_get_usb3_companion(tegra->padctl,
 								    tegra->otg_usb2_port);
 
+	pm_runtime_get_sync(tegra->dev);
 	if (tegra->host_mode) {
 		/* switch to host mode */
 		if (tegra->otg_usb3_port >= 0) {
@@ -1392,6 +1393,7 @@ static void tegra_xhci_id_work(struct work_struct *work)
 		}
 
 		tegra_xhci_set_port_power(tegra, true, true);
+		pm_runtime_mark_last_busy(tegra->dev);
 
 	} else {
 		if (tegra->otg_usb3_port >= 0)
@@ -1399,6 +1401,7 @@ static void tegra_xhci_id_work(struct work_struct *work)
 
 		tegra_xhci_set_port_power(tegra, true, false);
 	}
+	pm_runtime_put_autosuspend(tegra->dev);
 }
 
 #if IS_ENABLED(CONFIG_PM) || IS_ENABLED(CONFIG_PM_SLEEP)
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 358ed674f782..e399638d6000 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -83,29 +83,6 @@ int xhci_handshake(void __iomem *ptr, u32 mask, u32 done, u64 timeout_us)
 }
 
 /*
- * xhci_handshake_check_state - same as xhci_handshake but takes an additional
- * exit_state parameter, and bails out with an error immediately when xhc_state
- * has exit_state flag set.
- */
-int xhci_handshake_check_state(struct xhci_hcd *xhci, void __iomem *ptr,
-		u32 mask, u32 done, int usec, unsigned int exit_state)
-{
-	u32	result;
-	int	ret;
-
-	ret = readl_poll_timeout_atomic(ptr, result,
-				(result & mask) == done ||
-				result == U32_MAX ||
-				xhci->xhc_state & exit_state,
-				1, usec);
-
-	if (result == U32_MAX || xhci->xhc_state & exit_state)
-		return -ENODEV;
-
-	return ret;
-}
-
-/*
  * Disable interrupts and begin the xHCI halting process.
  */
 void xhci_quiesce(struct xhci_hcd *xhci)
@@ -142,7 +119,8 @@ int xhci_halt(struct xhci_hcd *xhci)
 	ret = xhci_handshake(&xhci->op_regs->status,
 			STS_HALT, STS_HALT, XHCI_MAX_HALT_USEC);
 	if (ret) {
-		xhci_warn(xhci, "Host halt failed, %d\n", ret);
+		if (!(xhci->xhc_state & XHCI_STATE_DYING))
+			xhci_warn(xhci, "Host halt failed, %d\n", ret);
 		return ret;
 	}
 
@@ -201,7 +179,8 @@ int xhci_reset(struct xhci_hcd *xhci, u64 timeout_us)
 	state = readl(&xhci->op_regs->status);
 
 	if (state == ~(u32)0) {
-		xhci_warn(xhci, "Host not accessible, reset failed.\n");
+		if (!(xhci->xhc_state & XHCI_STATE_DYING))
+			xhci_warn(xhci, "Host not accessible, reset failed.\n");
 		return -ENODEV;
 	}
 
@@ -225,8 +204,7 @@ int xhci_reset(struct xhci_hcd *xhci, u64 timeout_us)
 	if (xhci->quirks & XHCI_INTEL_HOST)
 		udelay(1000);
 
-	ret = xhci_handshake_check_state(xhci, &xhci->op_regs->command,
-				CMD_RESET, 0, timeout_us, XHCI_STATE_REMOVING);
+	ret = xhci_handshake(&xhci->op_regs->command, CMD_RESET, 0, timeout_us);
 	if (ret)
 		return ret;
 
@@ -321,7 +299,7 @@ static void xhci_zero_64b_regs(struct xhci_hcd *xhci)
 		xhci_info(xhci, "Fault detected\n");
 }
 
-static int xhci_enable_interrupter(struct xhci_interrupter *ir)
+int xhci_enable_interrupter(struct xhci_interrupter *ir)
 {
 	u32 iman;
 
@@ -334,7 +312,7 @@ static int xhci_enable_interrupter(struct xhci_interrupter *ir)
 	return 0;
 }
 
-static int xhci_disable_interrupter(struct xhci_interrupter *ir)
+int xhci_disable_interrupter(struct xhci_interrupter *ir)
 {
 	u32 iman;
 
@@ -1094,7 +1072,10 @@ int xhci_resume(struct xhci_hcd *xhci, pm_message_t msg)
 		xhci_dbg(xhci, "Stop HCD\n");
 		xhci_halt(xhci);
 		xhci_zero_64b_regs(xhci);
-		retval = xhci_reset(xhci, XHCI_RESET_LONG_USEC);
+		if (xhci->xhc_state & XHCI_STATE_REMOVING)
+			retval = -ENODEV;
+		else
+			retval = xhci_reset(xhci, XHCI_RESET_LONG_USEC);
 		spin_unlock_irq(&xhci->lock);
 		if (retval)
 			return retval;
diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h
index 673179047eb8..11580495e09c 100644
--- a/drivers/usb/host/xhci.h
+++ b/drivers/usb/host/xhci.h
@@ -211,6 +211,9 @@ struct xhci_op_regs {
 #define CONFIG_CIE		(1 << 9)
 /* bits 10:31 - reserved and should be preserved */
 
+/* bits 15:0 - HCD page shift bit */
+#define XHCI_PAGE_SIZE_MASK     0xffff
+
 /**
  * struct xhci_intr_reg - Interrupt Register Set
  * @irq_pending:	IMAN - Interrupt Management Register.  Used to enable
@@ -1360,7 +1363,7 @@ struct xhci_ring {
 	unsigned int		num_trbs_free; /* used only by xhci DbC */
 	unsigned int		bounce_buf_len;
 	enum xhci_ring_type	type;
-	bool			last_td_was_short;
+	u32			old_trb_comp_code;
 	struct radix_tree_root	*trb_address_map;
 };
 
@@ -1503,10 +1506,7 @@ struct xhci_hcd {
 	u16		max_interrupters;
 	/* imod_interval in ns (I * 250ns) */
 	u32		imod_interval;
-	/* 4KB min, 128MB max */
-	int		page_size;
-	/* Valid values are 12 to 20, inclusive */
-	int		page_shift;
+	u32		page_size;
 	/* MSI-X/MSI vectors */
 	int		nvecs;
 	/* optional clocks */
@@ -1621,11 +1621,12 @@ struct xhci_hcd {
 #define XHCI_EP_CTX_BROKEN_DCS	BIT_ULL(42)
 #define XHCI_SUSPEND_RESUME_CLKS	BIT_ULL(43)
 #define XHCI_RESET_TO_DEFAULT	BIT_ULL(44)
-#define XHCI_ZHAOXIN_TRB_FETCH	BIT_ULL(45)
+#define XHCI_TRB_OVERFETCH	BIT_ULL(45)
 #define XHCI_ZHAOXIN_HOST	BIT_ULL(46)
 #define XHCI_WRITE_64_HI_LO	BIT_ULL(47)
 #define XHCI_CDNS_SCTX_QUIRK	BIT_ULL(48)
 #define XHCI_ETRON_HOST	BIT_ULL(49)
+#define XHCI_LIMIT_ENDPOINT_INTERVAL_9 BIT_ULL(50)
 
 	unsigned int		num_active_eps;
 	unsigned int		limit_active_eps;
@@ -1748,11 +1749,20 @@ static inline void xhci_write_64(struct xhci_hcd *xhci,
 }
 
 
-/* Link TRB chain should always be set on 0.95 hosts, and AMD 0.96 ISOC rings */
+/*
+ * Reportedly, some chapters of v0.95 spec said that Link TRB always has its chain bit set.
+ * Other chapters and later specs say that it should only be set if the link is inside a TD
+ * which continues from the end of one segment to the next segment.
+ *
+ * Some 0.95 hardware was found to misbehave if any link TRB doesn't have the chain bit set.
+ *
+ * 0.96 hardware from AMD and NEC was found to ignore unchained isochronous link TRBs when
+ * "resynchronizing the pipe" after a Missed Service Error.
+ */
 static inline bool xhci_link_chain_quirk(struct xhci_hcd *xhci, enum xhci_ring_type type)
 {
 	return (xhci->quirks & XHCI_LINK_TRB_QUIRK) ||
-	       (type == TYPE_ISOC && (xhci->quirks & XHCI_AMD_0x96_HOST));
+	       (type == TYPE_ISOC && (xhci->quirks & (XHCI_AMD_0x96_HOST | XHCI_NEC_HOST)));
 }
 
 /* xHCI debugging */
@@ -1837,8 +1847,6 @@ void xhci_remove_secondary_interrupter(struct usb_hcd
 /* xHCI host controller glue */
 typedef void (*xhci_get_quirks_t)(struct device *, struct xhci_hcd *);
 int xhci_handshake(void __iomem *ptr, u32 mask, u32 done, u64 timeout_us);
-int xhci_handshake_check_state(struct xhci_hcd *xhci, void __iomem *ptr,
-		u32 mask, u32 done, int usec, unsigned int exit_state);
 void xhci_quiesce(struct xhci_hcd *xhci);
 int xhci_halt(struct xhci_hcd *xhci);
 int xhci_start(struct xhci_hcd *xhci);
@@ -1872,6 +1880,8 @@ int xhci_alloc_tt_info(struct xhci_hcd *xhci,
 		struct usb_tt *tt, gfp_t mem_flags);
 int xhci_set_interrupter_moderation(struct xhci_interrupter *ir,
 				    u32 imod_interval);
+int xhci_enable_interrupter(struct xhci_interrupter *ir);
+int xhci_disable_interrupter(struct xhci_interrupter *ir);
 
 /* xHCI ring, segment, TRB, and TD functions */
 dma_addr_t xhci_trb_virt_to_dma(struct xhci_segment *seg, union xhci_trb *trb);
diff --git a/drivers/usb/misc/apple-mfi-fastcharge.c b/drivers/usb/misc/apple-mfi-fastcharge.c
index ac8695195c13..8e852f4b8262 100644
--- a/drivers/usb/misc/apple-mfi-fastcharge.c
+++ b/drivers/usb/misc/apple-mfi-fastcharge.c
@@ -44,6 +44,7 @@ MODULE_DEVICE_TABLE(usb, mfi_fc_id_table);
 struct mfi_device {
 	struct usb_device *udev;
 	struct power_supply *battery;
+	struct power_supply_desc battery_desc;
 	int charge_type;
 };
 
@@ -178,6 +179,7 @@ static int mfi_fc_probe(struct usb_device *udev)
 {
 	struct power_supply_config battery_cfg = {};
 	struct mfi_device *mfi = NULL;
+	char *battery_name;
 	int err;
 
 	if (!mfi_fc_match(udev))
@@ -187,23 +189,38 @@ static int mfi_fc_probe(struct usb_device *udev)
 	if (!mfi)
 		return -ENOMEM;
 
+	battery_name = kasprintf(GFP_KERNEL, "apple_mfi_fastcharge_%d-%d",
+				 udev->bus->busnum, udev->devnum);
+	if (!battery_name) {
+		err = -ENOMEM;
+		goto err_free_mfi;
+	}
+
+	mfi->battery_desc = apple_mfi_fc_desc;
+	mfi->battery_desc.name = battery_name;
+
 	battery_cfg.drv_data = mfi;
 
 	mfi->charge_type = POWER_SUPPLY_CHARGE_TYPE_TRICKLE;
 	mfi->battery = power_supply_register(&udev->dev,
-						&apple_mfi_fc_desc,
+						&mfi->battery_desc,
 						&battery_cfg);
 	if (IS_ERR(mfi->battery)) {
 		dev_err(&udev->dev, "Can't register battery\n");
 		err = PTR_ERR(mfi->battery);
-		kfree(mfi);
-		return err;
+		goto err_free_name;
 	}
 
 	mfi->udev = usb_get_dev(udev);
 	dev_set_drvdata(&udev->dev, mfi);
 
 	return 0;
+
+err_free_name:
+	kfree(battery_name);
+err_free_mfi:
+	kfree(mfi);
+	return err;
 }
 
 static void mfi_fc_disconnect(struct usb_device *udev)
@@ -213,6 +230,7 @@ static void mfi_fc_disconnect(struct usb_device *udev)
 	mfi = dev_get_drvdata(&udev->dev);
 	if (mfi->battery)
 		power_supply_unregister(mfi->battery);
+	kfree(mfi->battery_desc.name);
 	dev_set_drvdata(&udev->dev, NULL);
 	usb_put_dev(mfi->udev);
 	kfree(mfi);
diff --git a/drivers/usb/misc/onboard_usb_dev.c b/drivers/usb/misc/onboard_usb_dev.c
index 27b0a6e18267..cf716ae870b8 100644
--- a/drivers/usb/misc/onboard_usb_dev.c
+++ b/drivers/usb/misc/onboard_usb_dev.c
@@ -36,9 +36,10 @@
 #define USB5744_CMD_CREG_ACCESS			0x99
 #define USB5744_CMD_CREG_ACCESS_LSB		0x37
 #define USB5744_CREG_MEM_ADDR			0x00
+#define USB5744_CREG_MEM_RD_ADDR		0x04
 #define USB5744_CREG_WRITE			0x00
-#define USB5744_CREG_RUNTIMEFLAGS2		0x41
-#define USB5744_CREG_RUNTIMEFLAGS2_LSB		0x1D
+#define USB5744_CREG_READ			0x01
+#define USB5744_CREG_RUNTIMEFLAGS2		0x411D
 #define USB5744_CREG_BYPASS_UDC_SUSPEND		BIT(3)
 
 static void onboard_dev_attach_usb_driver(struct work_struct *work);
@@ -309,11 +310,88 @@ static void onboard_dev_attach_usb_driver(struct work_struct *work)
 		pr_err("Failed to attach USB driver: %pe\n", ERR_PTR(err));
 }
 
+#if IS_ENABLED(CONFIG_USB_ONBOARD_DEV_USB5744)
+static int onboard_dev_5744_i2c_read_byte(struct i2c_client *client, u16 addr, u8 *data)
+{
+	struct i2c_msg msg[2];
+	u8 rd_buf[3];
+	int ret;
+
+	u8 wr_buf[7] = {0, USB5744_CREG_MEM_ADDR, 4,
+			USB5744_CREG_READ, 1,
+			addr >> 8 & 0xff,
+			addr & 0xff};
+	msg[0].addr = client->addr;
+	msg[0].flags = 0;
+	msg[0].len = sizeof(wr_buf);
+	msg[0].buf = wr_buf;
+
+	ret = i2c_transfer(client->adapter, msg, 1);
+	if (ret < 0)
+		return ret;
+
+	wr_buf[0] = USB5744_CMD_CREG_ACCESS;
+	wr_buf[1] = USB5744_CMD_CREG_ACCESS_LSB;
+	wr_buf[2] = 0;
+	msg[0].len = 3;
+
+	ret = i2c_transfer(client->adapter, msg, 1);
+	if (ret < 0)
+		return ret;
+
+	wr_buf[0] = 0;
+	wr_buf[1] = USB5744_CREG_MEM_RD_ADDR;
+	msg[0].len = 2;
+
+	msg[1].addr = client->addr;
+	msg[1].flags = I2C_M_RD;
+	msg[1].len = 2;
+	msg[1].buf = rd_buf;
+
+	ret = i2c_transfer(client->adapter, msg, 2);
+	if (ret < 0)
+		return ret;
+	*data = rd_buf[1];
+
+	return 0;
+}
+
+static int onboard_dev_5744_i2c_write_byte(struct i2c_client *client, u16 addr, u8 data)
+{
+	struct i2c_msg msg[2];
+	int ret;
+
+	u8 wr_buf[8] = {0, USB5744_CREG_MEM_ADDR, 5,
+			USB5744_CREG_WRITE, 1,
+			addr >> 8 & 0xff,
+			addr & 0xff,
+			data};
+	msg[0].addr = client->addr;
+	msg[0].flags = 0;
+	msg[0].len = sizeof(wr_buf);
+	msg[0].buf = wr_buf;
+
+	ret = i2c_transfer(client->adapter, msg, 1);
+	if (ret < 0)
+		return ret;
+
+	msg[0].len = 3;
+	wr_buf[0] = USB5744_CMD_CREG_ACCESS;
+	wr_buf[1] = USB5744_CMD_CREG_ACCESS_LSB;
+	wr_buf[2] = 0;
+
+	ret = i2c_transfer(client->adapter, msg, 1);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
 static int onboard_dev_5744_i2c_init(struct i2c_client *client)
 {
-#if IS_ENABLED(CONFIG_USB_ONBOARD_DEV_USB5744)
 	struct device *dev = &client->dev;
 	int ret;
+	u8 reg;
 
 	/*
 	 * Set BYPASS_UDC_SUSPEND bit to ensure MCU is always enabled
@@ -321,20 +399,16 @@ static int onboard_dev_5744_i2c_init(struct i2c_client *client)
 	 * The command writes 5 bytes to memory and single data byte in
 	 * configuration register.
 	 */
-	char wr_buf[7] = {USB5744_CREG_MEM_ADDR, 5,
-			  USB5744_CREG_WRITE, 1,
-			  USB5744_CREG_RUNTIMEFLAGS2,
-			  USB5744_CREG_RUNTIMEFLAGS2_LSB,
-			  USB5744_CREG_BYPASS_UDC_SUSPEND};
-
-	ret = i2c_smbus_write_block_data(client, 0, sizeof(wr_buf), wr_buf);
+	ret = onboard_dev_5744_i2c_read_byte(client,
+					     USB5744_CREG_RUNTIMEFLAGS2, &reg);
 	if (ret)
-		return dev_err_probe(dev, ret, "BYPASS_UDC_SUSPEND bit configuration failed\n");
+		return dev_err_probe(dev, ret, "CREG_RUNTIMEFLAGS2 read failed\n");
 
-	ret = i2c_smbus_write_word_data(client, USB5744_CMD_CREG_ACCESS,
-					USB5744_CMD_CREG_ACCESS_LSB);
+	reg |= USB5744_CREG_BYPASS_UDC_SUSPEND;
+	ret = onboard_dev_5744_i2c_write_byte(client,
+					      USB5744_CREG_RUNTIMEFLAGS2, reg);
 	if (ret)
-		return dev_err_probe(dev, ret, "Configuration Register Access Command failed\n");
+		return dev_err_probe(dev, ret, "BYPASS_UDC_SUSPEND bit configuration failed\n");
 
 	/* Send SMBus command to boot hub. */
 	ret = i2c_smbus_write_word_data(client, USB5744_CMD_ATTACH,
@@ -343,10 +417,13 @@ static int onboard_dev_5744_i2c_init(struct i2c_client *client)
 		return dev_err_probe(dev, ret, "USB Attach with SMBus command failed\n");
 
 	return ret;
+}
 #else
+static int onboard_dev_5744_i2c_init(struct i2c_client *client)
+{
 	return -ENODEV;
-#endif
 }
+#endif
 
 static int onboard_dev_probe(struct platform_device *pdev)
 {
@@ -569,8 +646,14 @@ static void onboard_dev_usbdev_disconnect(struct usb_device *udev)
 }
 
 static const struct usb_device_id onboard_dev_id_table[] = {
-	{ USB_DEVICE(VENDOR_ID_CYPRESS, 0x6504) }, /* CYUSB33{0,1,2}x/CYUSB230x 3.0 HUB */
-	{ USB_DEVICE(VENDOR_ID_CYPRESS, 0x6506) }, /* CYUSB33{0,1,2}x/CYUSB230x 2.0 HUB */
+	{ USB_DEVICE(VENDOR_ID_CYPRESS, 0x6500) }, /* CYUSB330x 3.0 HUB */
+	{ USB_DEVICE(VENDOR_ID_CYPRESS, 0x6502) }, /* CYUSB330x 2.0 HUB */
+	{ USB_DEVICE(VENDOR_ID_CYPRESS, 0x6503) }, /* CYUSB33{0,1}x 2.0 HUB, Vendor Mode */
+	{ USB_DEVICE(VENDOR_ID_CYPRESS, 0x6504) }, /* CYUSB331x 3.0 HUB */
+	{ USB_DEVICE(VENDOR_ID_CYPRESS, 0x6506) }, /* CYUSB331x 2.0 HUB */
+	{ USB_DEVICE(VENDOR_ID_CYPRESS, 0x6507) }, /* CYUSB332x 2.0 HUB, Vendor Mode */
+	{ USB_DEVICE(VENDOR_ID_CYPRESS, 0x6508) }, /* CYUSB332x 3.0 HUB */
+	{ USB_DEVICE(VENDOR_ID_CYPRESS, 0x650a) }, /* CYUSB332x 2.0 HUB */
 	{ USB_DEVICE(VENDOR_ID_CYPRESS, 0x6570) }, /* CY7C6563x 2.0 HUB */
 	{ USB_DEVICE(VENDOR_ID_GENESYS, 0x0608) }, /* Genesys Logic GL850G USB 2.0 HUB */
 	{ USB_DEVICE(VENDOR_ID_GENESYS, 0x0610) }, /* Genesys Logic GL852G USB 2.0 HUB */
diff --git a/drivers/usb/musb/musb_gadget.c b/drivers/usb/musb/musb_gadget.c
index c6076df0d50c..da2b864fdadf 100644
--- a/drivers/usb/musb/musb_gadget.c
+++ b/drivers/usb/musb/musb_gadget.c
@@ -1912,6 +1912,7 @@ static int musb_gadget_stop(struct usb_gadget *g)
 	 * gadget driver here and have everything work;
 	 * that currently misbehaves.
 	 */
+	usb_gadget_set_state(g, USB_STATE_NOTATTACHED);
 
 	/* Force check of devctl register for PM runtime */
 	pm_runtime_mark_last_busy(musb->controller);
@@ -2018,6 +2019,7 @@ void musb_g_disconnect(struct musb *musb)
 	case OTG_STATE_B_PERIPHERAL:
 	case OTG_STATE_B_IDLE:
 		musb_set_state(musb, OTG_STATE_B_IDLE);
+		usb_gadget_set_state(&musb->g, USB_STATE_NOTATTACHED);
 		break;
 	case OTG_STATE_B_SRP_INIT:
 		break;
diff --git a/drivers/usb/phy/phy-generic.c b/drivers/usb/phy/phy-generic.c
index e7d50e0a1612..aadf98f65c60 100644
--- a/drivers/usb/phy/phy-generic.c
+++ b/drivers/usb/phy/phy-generic.c
@@ -212,7 +212,7 @@ int usb_phy_gen_create_phy(struct device *dev, struct usb_phy_generic *nop)
 		if (of_property_read_u32(node, "clock-frequency", &clk_rate))
 			clk_rate = 0;
 
-		needs_clk = of_property_read_bool(node, "clocks");
+		needs_clk = of_property_present(node, "clocks");
 	}
 	nop->gpiod_reset = devm_gpiod_get_optional(dev, "reset",
 						   GPIOD_ASIS);
diff --git a/drivers/usb/renesas_usbhs/common.c b/drivers/usb/renesas_usbhs/common.c
index edc43f169d49..161786e9b7e4 100644
--- a/drivers/usb/renesas_usbhs/common.c
+++ b/drivers/usb/renesas_usbhs/common.c
@@ -312,8 +312,10 @@ static int usbhsc_clk_get(struct device *dev, struct usbhs_priv *priv)
 	priv->clks[1] = of_clk_get(dev_of_node(dev), 1);
 	if (PTR_ERR(priv->clks[1]) == -ENOENT)
 		priv->clks[1] = NULL;
-	else if (IS_ERR(priv->clks[1]))
+	else if (IS_ERR(priv->clks[1])) {
+		clk_put(priv->clks[0]);
 		return PTR_ERR(priv->clks[1]);
+	}
 
 	return 0;
 }
@@ -683,10 +685,29 @@ static int usbhs_probe(struct platform_device *pdev)
 	INIT_DELAYED_WORK(&priv->notify_hotplug_work, usbhsc_notify_hotplug);
 	spin_lock_init(usbhs_priv_to_lock(priv));
 
+	/*
+	 * Acquire clocks and enable power management (PM) early in the
+	 * probe process, as the driver accesses registers during
+	 * initialization. Ensure the device is active before proceeding.
+	 */
+	pm_runtime_enable(dev);
+
+	ret = usbhsc_clk_get(dev, priv);
+	if (ret)
+		goto probe_pm_disable;
+
+	ret = pm_runtime_resume_and_get(dev);
+	if (ret)
+		goto probe_clk_put;
+
+	ret = usbhsc_clk_prepare_enable(priv);
+	if (ret)
+		goto probe_pm_put;
+
 	/* call pipe and module init */
 	ret = usbhs_pipe_probe(priv);
 	if (ret < 0)
-		return ret;
+		goto probe_clk_dis_unprepare;
 
 	ret = usbhs_fifo_probe(priv);
 	if (ret < 0)
@@ -703,10 +724,6 @@ static int usbhs_probe(struct platform_device *pdev)
 	if (ret)
 		goto probe_fail_rst;
 
-	ret = usbhsc_clk_get(dev, priv);
-	if (ret)
-		goto probe_fail_clks;
-
 	/*
 	 * deviece reset here because
 	 * USB device might be used in boot loader.
@@ -719,7 +736,7 @@ static int usbhs_probe(struct platform_device *pdev)
 		if (ret) {
 			dev_warn(dev, "USB function not selected (GPIO)\n");
 			ret = -ENOTSUPP;
-			goto probe_end_mod_exit;
+			goto probe_assert_rest;
 		}
 	}
 
@@ -733,14 +750,19 @@ static int usbhs_probe(struct platform_device *pdev)
 	ret = usbhs_platform_call(priv, hardware_init, pdev);
 	if (ret < 0) {
 		dev_err(dev, "platform init failed.\n");
-		goto probe_end_mod_exit;
+		goto probe_assert_rest;
 	}
 
 	/* reset phy for connection */
 	usbhs_platform_call(priv, phy_reset, pdev);
 
-	/* power control */
-	pm_runtime_enable(dev);
+	/*
+	 * Disable the clocks that were enabled earlier in the probe path,
+	 * and let the driver handle the clocks beyond this point.
+	 */
+	usbhsc_clk_disable_unprepare(priv);
+	pm_runtime_put(dev);
+
 	if (!usbhs_get_dparam(priv, runtime_pwctrl)) {
 		usbhsc_power_ctrl(priv, 1);
 		usbhs_mod_autonomy_mode(priv);
@@ -757,9 +779,7 @@ static int usbhs_probe(struct platform_device *pdev)
 
 	return ret;
 
-probe_end_mod_exit:
-	usbhsc_clk_put(priv);
-probe_fail_clks:
+probe_assert_rest:
 	reset_control_assert(priv->rsts);
 probe_fail_rst:
 	usbhs_mod_remove(priv);
@@ -767,6 +787,14 @@ probe_end_fifo_exit:
 	usbhs_fifo_remove(priv);
 probe_end_pipe_exit:
 	usbhs_pipe_remove(priv);
+probe_clk_dis_unprepare:
+	usbhsc_clk_disable_unprepare(priv);
+probe_pm_put:
+	pm_runtime_put(dev);
+probe_clk_put:
+	usbhsc_clk_put(priv);
+probe_pm_disable:
+	pm_runtime_disable(dev);
 
 	dev_info(dev, "probe failed (%d)\n", ret);
 
@@ -779,6 +807,8 @@ static void usbhs_remove(struct platform_device *pdev)
 
 	dev_dbg(&pdev->dev, "usb remove\n");
 
+	flush_delayed_work(&priv->notify_hotplug_work);
+
 	/* power off */
 	if (!usbhs_get_dparam(priv, runtime_pwctrl))
 		usbhsc_power_ctrl(priv, 0);
diff --git a/drivers/usb/renesas_usbhs/mod_gadget.c b/drivers/usb/renesas_usbhs/mod_gadget.c
index 105132ae87ac..e8e5723f5412 100644
--- a/drivers/usb/renesas_usbhs/mod_gadget.c
+++ b/drivers/usb/renesas_usbhs/mod_gadget.c
@@ -1094,7 +1094,7 @@ int usbhs_mod_gadget_probe(struct usbhs_priv *priv)
 		goto usbhs_mod_gadget_probe_err_gpriv;
 	}
 
-	gpriv->transceiver = usb_get_phy(USB_PHY_TYPE_UNDEFINED);
+	gpriv->transceiver = devm_usb_get_phy(dev, USB_PHY_TYPE_UNDEFINED);
 	dev_info(dev, "%stransceiver found\n",
 		 !IS_ERR(gpriv->transceiver) ? "" : "no ");
 
diff --git a/drivers/usb/roles/class.c b/drivers/usb/roles/class.c
index c58a12c147f4..30482d4cf826 100644
--- a/drivers/usb/roles/class.c
+++ b/drivers/usb/roles/class.c
@@ -387,8 +387,11 @@ usb_role_switch_register(struct device *parent,
 	dev_set_name(&sw->dev, "%s-role-switch",
 		     desc->name ? desc->name : dev_name(parent));
 
+	sw->registered = true;
+
 	ret = device_register(&sw->dev);
 	if (ret) {
+		sw->registered = false;
 		put_device(&sw->dev);
 		return ERR_PTR(ret);
 	}
@@ -399,8 +402,6 @@ usb_role_switch_register(struct device *parent,
 			dev_warn(&sw->dev, "failed to add component\n");
 	}
 
-	sw->registered = true;
-
 	/* TODO: Symlinks for the host port and the device controller. */
 
 	return sw;
diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c
index c6f17d732b95..4f21d75f5877 100644
--- a/drivers/usb/serial/ftdi_sio.c
+++ b/drivers/usb/serial/ftdi_sio.c
@@ -803,6 +803,8 @@ static const struct usb_device_id id_table_combined[] = {
 		.driver_info = (kernel_ulong_t)&ftdi_NDI_device_quirk },
 	{ USB_DEVICE(FTDI_VID, FTDI_NDI_AURORA_SCU_PID),
 		.driver_info = (kernel_ulong_t)&ftdi_NDI_device_quirk },
+	{ USB_DEVICE(FTDI_NDI_VID, FTDI_NDI_EMGUIDE_GEMINI_PID),
+		.driver_info = (kernel_ulong_t)&ftdi_NDI_device_quirk },
 	{ USB_DEVICE(TELLDUS_VID, TELLDUS_TELLSTICK_PID) },
 	{ USB_DEVICE(NOVITUS_VID, NOVITUS_BONO_E_PID) },
 	{ USB_DEVICE(FTDI_VID, RTSYSTEMS_USB_VX8_PID) },
@@ -1079,6 +1081,22 @@ static const struct usb_device_id id_table_combined[] = {
 		.driver_info = (kernel_ulong_t)&ftdi_jtag_quirk },
 	/* GMC devices */
 	{ USB_DEVICE(GMC_VID, GMC_Z216C_PID) },
+	/* Altera USB Blaster 3 */
+	{ USB_DEVICE_INTERFACE_NUMBER(ALTERA_VID, ALTERA_UB3_6022_PID, 1) },
+	{ USB_DEVICE_INTERFACE_NUMBER(ALTERA_VID, ALTERA_UB3_6025_PID, 2) },
+	{ USB_DEVICE_INTERFACE_NUMBER(ALTERA_VID, ALTERA_UB3_6026_PID, 2) },
+	{ USB_DEVICE_INTERFACE_NUMBER(ALTERA_VID, ALTERA_UB3_6026_PID, 3) },
+	{ USB_DEVICE_INTERFACE_NUMBER(ALTERA_VID, ALTERA_UB3_6029_PID, 2) },
+	{ USB_DEVICE_INTERFACE_NUMBER(ALTERA_VID, ALTERA_UB3_602A_PID, 2) },
+	{ USB_DEVICE_INTERFACE_NUMBER(ALTERA_VID, ALTERA_UB3_602A_PID, 3) },
+	{ USB_DEVICE_INTERFACE_NUMBER(ALTERA_VID, ALTERA_UB3_602C_PID, 1) },
+	{ USB_DEVICE_INTERFACE_NUMBER(ALTERA_VID, ALTERA_UB3_602D_PID, 1) },
+	{ USB_DEVICE_INTERFACE_NUMBER(ALTERA_VID, ALTERA_UB3_602D_PID, 2) },
+	{ USB_DEVICE_INTERFACE_NUMBER(ALTERA_VID, ALTERA_UB3_602E_PID, 1) },
+	{ USB_DEVICE_INTERFACE_NUMBER(ALTERA_VID, ALTERA_UB3_602E_PID, 2) },
+	{ USB_DEVICE_INTERFACE_NUMBER(ALTERA_VID, ALTERA_UB3_602E_PID, 3) },
+	/* Abacus Electrics */
+	{ USB_DEVICE(FTDI_VID, ABACUS_OPTICAL_PROBE_PID) },
 	{ }					/* Terminating entry */
 };
 
diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h
index 5ee60ba2a73c..4cc1fae8acb9 100644
--- a/drivers/usb/serial/ftdi_sio_ids.h
+++ b/drivers/usb/serial/ftdi_sio_ids.h
@@ -204,6 +204,9 @@
 #define FTDI_NDI_FUTURE_3_PID		0xDA73	/* NDI future device #3 */
 #define FTDI_NDI_AURORA_SCU_PID		0xDA74	/* NDI Aurora SCU */
 
+#define FTDI_NDI_VID			0x23F2
+#define FTDI_NDI_EMGUIDE_GEMINI_PID	0x0003	/* NDI Emguide Gemini */
+
 /*
  * ChamSys Limited (www.chamsys.co.uk) USB wing/interface product IDs
  */
@@ -443,6 +446,11 @@
 #define LINX_FUTURE_2_PID   0xF44C	/* Linx future device */
 
 /*
+ * Abacus Electrics
+ */
+#define ABACUS_OPTICAL_PROBE_PID	0xf458 /* ABACUS ELECTRICS Optical Probe */
+
+/*
  * Oceanic product ids
  */
 #define FTDI_OCEANIC_PID	0xF460  /* Oceanic dive instrument */
@@ -1612,3 +1620,16 @@
  */
 #define GMC_VID				0x1cd7
 #define GMC_Z216C_PID			0x0217 /* GMC Z216C Adapter IR-USB */
+
+/*
+ *  Altera USB Blaster 3 (http://www.altera.com).
+ */
+#define ALTERA_VID			0x09fb
+#define ALTERA_UB3_6022_PID		0x6022
+#define ALTERA_UB3_6025_PID		0x6025
+#define ALTERA_UB3_6026_PID		0x6026
+#define ALTERA_UB3_6029_PID		0x6029
+#define ALTERA_UB3_602A_PID		0x602a
+#define ALTERA_UB3_602C_PID		0x602c
+#define ALTERA_UB3_602D_PID		0x602d
+#define ALTERA_UB3_602E_PID		0x602e
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index 1e2ae0c6c41c..e5cd33093423 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -611,6 +611,7 @@ static void option_instat_callback(struct urb *urb);
 /* Sierra Wireless products */
 #define SIERRA_VENDOR_ID			0x1199
 #define SIERRA_PRODUCT_EM9191			0x90d3
+#define SIERRA_PRODUCT_EM9291			0x90e3
 
 /* UNISOC (Spreadtrum) products */
 #define UNISOC_VENDOR_ID			0x1782
@@ -619,15 +620,6 @@ static void option_instat_callback(struct urb *urb);
 /* Luat Air72*U series based on UNISOC UIS8910 uses UNISOC's vendor ID */
 #define LUAT_PRODUCT_AIR720U			0x4e00
 
-/* MeiG Smart Technology products */
-#define MEIGSMART_VENDOR_ID			0x2dee
-/* MeiG Smart SRM815/SRM825L based on Qualcomm 315 */
-#define MEIGSMART_PRODUCT_SRM825L		0x4d22
-/* MeiG Smart SLM320 based on UNISOC UIS8910 */
-#define MEIGSMART_PRODUCT_SLM320		0x4d41
-/* MeiG Smart SLM770A based on ASR1803 */
-#define MEIGSMART_PRODUCT_SLM770A		0x4d57
-
 /* Device flags */
 
 /* Highest interface number which can be used with NCTRL() and RSVD() */
@@ -1367,23 +1359,23 @@ static const struct usb_device_id option_ids[] = {
 	  .driver_info = NCTRL(2) | RSVD(3) },
 	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1063, 0xff),	/* Telit LN920 (ECM) */
 	  .driver_info = NCTRL(0) | RSVD(1) },
-	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1070, 0xff),	/* Telit FN990 (rmnet) */
+	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1070, 0xff),	/* Telit FN990A (rmnet) */
 	  .driver_info = NCTRL(0) | RSVD(1) | RSVD(2) },
-	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1071, 0xff),	/* Telit FN990 (MBIM) */
+	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1071, 0xff),	/* Telit FN990A (MBIM) */
 	  .driver_info = NCTRL(0) | RSVD(1) },
-	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1072, 0xff),	/* Telit FN990 (RNDIS) */
+	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1072, 0xff),	/* Telit FN990A (RNDIS) */
 	  .driver_info = NCTRL(2) | RSVD(3) },
-	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1073, 0xff),	/* Telit FN990 (ECM) */
+	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1073, 0xff),	/* Telit FN990A (ECM) */
 	  .driver_info = NCTRL(0) | RSVD(1) },
-	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1075, 0xff),	/* Telit FN990 (PCIe) */
+	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1075, 0xff),	/* Telit FN990A (PCIe) */
 	  .driver_info = RSVD(0) },
-	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1080, 0xff),	/* Telit FE990 (rmnet) */
+	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1080, 0xff),	/* Telit FE990A (rmnet) */
 	  .driver_info = NCTRL(0) | RSVD(1) | RSVD(2) },
-	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1081, 0xff),	/* Telit FE990 (MBIM) */
+	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1081, 0xff),	/* Telit FE990A (MBIM) */
 	  .driver_info = NCTRL(0) | RSVD(1) },
-	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1082, 0xff),	/* Telit FE990 (RNDIS) */
+	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1082, 0xff),	/* Telit FE990A (RNDIS) */
 	  .driver_info = NCTRL(2) | RSVD(3) },
-	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1083, 0xff),	/* Telit FE990 (ECM) */
+	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1083, 0xff),	/* Telit FE990A (ECM) */
 	  .driver_info = NCTRL(0) | RSVD(1) },
 	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10a0, 0xff),	/* Telit FN20C04 (rmnet) */
 	  .driver_info = RSVD(0) | NCTRL(3) },
@@ -1397,12 +1389,47 @@ static const struct usb_device_id option_ids[] = {
 	  .driver_info = RSVD(0) | NCTRL(2) | RSVD(3) | RSVD(4) },
 	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10aa, 0xff),	/* Telit FN920C04 (MBIM) */
 	  .driver_info = NCTRL(3) | RSVD(4) | RSVD(5) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10b0, 0xff, 0xff, 0x30),	/* Telit FE990B (rmnet) */
+	  .driver_info = NCTRL(5) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10b0, 0xff, 0xff, 0x40) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10b0, 0xff, 0xff, 0x60) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10b1, 0xff, 0xff, 0x30),	/* Telit FE990B (MBIM) */
+	  .driver_info = NCTRL(6) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10b1, 0xff, 0xff, 0x40) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10b1, 0xff, 0xff, 0x60) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10b2, 0xff, 0xff, 0x30),	/* Telit FE990B (RNDIS) */
+	  .driver_info = NCTRL(6) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10b2, 0xff, 0xff, 0x40) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10b2, 0xff, 0xff, 0x60) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10b3, 0xff, 0xff, 0x30),	/* Telit FE990B (ECM) */
+	  .driver_info = NCTRL(6) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10b3, 0xff, 0xff, 0x40) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10b3, 0xff, 0xff, 0x60) },
 	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10c0, 0xff),	/* Telit FE910C04 (rmnet) */
 	  .driver_info = RSVD(0) | NCTRL(3) },
 	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10c4, 0xff),	/* Telit FE910C04 (rmnet) */
 	  .driver_info = RSVD(0) | NCTRL(3) },
 	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10c8, 0xff),	/* Telit FE910C04 (rmnet) */
 	  .driver_info = RSVD(0) | NCTRL(2) | RSVD(3) | RSVD(4) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10d0, 0xff, 0xff, 0x30),	/* Telit FN990B (rmnet) */
+	  .driver_info = NCTRL(5) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10d0, 0xff, 0xff, 0x40) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10d0, 0xff, 0xff, 0x60) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10c7, 0xff, 0xff, 0x30),	/* Telit FE910C04 (ECM) */
+	  .driver_info = NCTRL(4) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10c7, 0xff, 0xff, 0x40) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10d1, 0xff, 0xff, 0x30),	/* Telit FN990B (MBIM) */
+	  .driver_info = NCTRL(6) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10d1, 0xff, 0xff, 0x40) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10d1, 0xff, 0xff, 0x60) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10d2, 0xff, 0xff, 0x30),	/* Telit FN990B (RNDIS) */
+	  .driver_info = NCTRL(6) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10d2, 0xff, 0xff, 0x40) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10d2, 0xff, 0xff, 0x60) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10d3, 0xff, 0xff, 0x30),	/* Telit FN990B (ECM) */
+	  .driver_info = NCTRL(6) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10d3, 0xff, 0xff, 0x40) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10d3, 0xff, 0xff, 0x60) },
 	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910),
 	  .driver_info = NCTRL(0) | RSVD(1) | RSVD(3) },
 	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910_DUAL_MODEM),
@@ -2319,6 +2346,10 @@ static const struct usb_device_id option_ids[] = {
 	  .driver_info = RSVD(3) },
 	{ USB_DEVICE_INTERFACE_CLASS(0x0489, 0xe145, 0xff),			/* Foxconn T99W651 RNDIS */
 	  .driver_info = RSVD(5) | RSVD(6) },
+	{ USB_DEVICE_INTERFACE_CLASS(0x0489, 0xe15f, 0xff),                     /* Foxconn T99W709 */
+	  .driver_info = RSVD(5) },
+	{ USB_DEVICE_INTERFACE_CLASS(0x0489, 0xe167, 0xff),                     /* Foxconn T99W640 MBIM */
+	  .driver_info = RSVD(3) },
 	{ USB_DEVICE(0x1508, 0x1001),						/* Fibocom NL668 (IOT version) */
 	  .driver_info = RSVD(4) | RSVD(5) | RSVD(6) },
 	{ USB_DEVICE(0x1782, 0x4d10) },						/* Fibocom L610 (AT mode) */
@@ -2347,6 +2378,14 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x0a05, 0xff) },			/* Fibocom FM650-CN (NCM mode) */
 	{ USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x0a06, 0xff) },			/* Fibocom FM650-CN (RNDIS mode) */
 	{ USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x0a07, 0xff) },			/* Fibocom FM650-CN (MBIM mode) */
+	{ USB_DEVICE_AND_INTERFACE_INFO(0x2dee, 0x4d41, 0xff, 0, 0) },		/* MeiG Smart SLM320 */
+	{ USB_DEVICE_AND_INTERFACE_INFO(0x2dee, 0x4d57, 0xff, 0, 0) },		/* MeiG Smart SLM770A */
+	{ USB_DEVICE_AND_INTERFACE_INFO(0x2dee, 0x4d22, 0xff, 0, 0) },		/* MeiG Smart SRM815 */
+	{ USB_DEVICE_AND_INTERFACE_INFO(0x2dee, 0x4d22, 0xff, 0x10, 0x02) },	/* MeiG Smart SLM828 */
+	{ USB_DEVICE_AND_INTERFACE_INFO(0x2dee, 0x4d22, 0xff, 0x10, 0x03) },	/* MeiG Smart SLM828 */
+	{ USB_DEVICE_AND_INTERFACE_INFO(0x2dee, 0x4d22, 0xff, 0xff, 0x30) },	/* MeiG Smart SRM815 and SRM825L */
+	{ USB_DEVICE_AND_INTERFACE_INFO(0x2dee, 0x4d22, 0xff, 0xff, 0x40) },	/* MeiG Smart SRM825L */
+	{ USB_DEVICE_AND_INTERFACE_INFO(0x2dee, 0x4d22, 0xff, 0xff, 0x60) },	/* MeiG Smart SRM825L */
 	{ USB_DEVICE_INTERFACE_CLASS(0x2df3, 0x9d03, 0xff) },			/* LongSung M5710 */
 	{ USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1404, 0xff) },			/* GosunCn GM500 RNDIS */
 	{ USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1405, 0xff) },			/* GosunCn GM500 MBIM */
@@ -2401,14 +2440,10 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9191, 0xff, 0xff, 0x30) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9191, 0xff, 0xff, 0x40) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9191, 0xff, 0, 0) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9291, 0xff, 0xff, 0x30) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9291, 0xff, 0xff, 0x40) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(UNISOC_VENDOR_ID, TOZED_PRODUCT_LT70C, 0xff, 0, 0) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(UNISOC_VENDOR_ID, LUAT_PRODUCT_AIR720U, 0xff, 0, 0) },
-	{ USB_DEVICE_AND_INTERFACE_INFO(MEIGSMART_VENDOR_ID, MEIGSMART_PRODUCT_SLM320, 0xff, 0, 0) },
-	{ USB_DEVICE_AND_INTERFACE_INFO(MEIGSMART_VENDOR_ID, MEIGSMART_PRODUCT_SLM770A, 0xff, 0, 0) },
-	{ USB_DEVICE_AND_INTERFACE_INFO(MEIGSMART_VENDOR_ID, MEIGSMART_PRODUCT_SRM825L, 0xff, 0, 0) },
-	{ USB_DEVICE_AND_INTERFACE_INFO(MEIGSMART_VENDOR_ID, MEIGSMART_PRODUCT_SRM825L, 0xff, 0xff, 0x30) },
-	{ USB_DEVICE_AND_INTERFACE_INFO(MEIGSMART_VENDOR_ID, MEIGSMART_PRODUCT_SRM825L, 0xff, 0xff, 0x40) },
-	{ USB_DEVICE_AND_INTERFACE_INFO(MEIGSMART_VENDOR_ID, MEIGSMART_PRODUCT_SRM825L, 0xff, 0xff, 0x60) },
 	{ USB_DEVICE_INTERFACE_CLASS(0x1bbb, 0x0530, 0xff),			/* TCL IK512 MBIM */
 	  .driver_info = NCTRL(1) },
 	{ USB_DEVICE_INTERFACE_CLASS(0x1bbb, 0x0640, 0xff),			/* TCL IK512 ECM */
diff --git a/drivers/usb/serial/pl2303.c b/drivers/usb/serial/pl2303.c
index ad41363e3cea..9708c3d40f07 100644
--- a/drivers/usb/serial/pl2303.c
+++ b/drivers/usb/serial/pl2303.c
@@ -457,6 +457,8 @@ static int pl2303_detect_type(struct usb_serial *serial)
 		case 0x605:
 		case 0x700:	/* GR */
 		case 0x705:
+		case 0x905:	/* GT-2AB */
+		case 0x1005:	/* GC-Q20 */
 			return TYPE_HXN;
 		}
 		break;
diff --git a/drivers/usb/serial/quatech2.c b/drivers/usb/serial/quatech2.c
index a317bdbd00ad..72fe83a6c978 100644
--- a/drivers/usb/serial/quatech2.c
+++ b/drivers/usb/serial/quatech2.c
@@ -503,7 +503,7 @@ static void qt2_process_read_urb(struct urb *urb)
 
 				newport = *(ch + 3);
 
-				if (newport > serial->num_ports) {
+				if (newport >= serial->num_ports) {
 					dev_err(&port->dev,
 						"%s - port change to invalid port: %i\n",
 						__func__, newport);
diff --git a/drivers/usb/serial/usb-serial-simple.c b/drivers/usb/serial/usb-serial-simple.c
index 2c12449ff60c..a0afaf254d12 100644
--- a/drivers/usb/serial/usb-serial-simple.c
+++ b/drivers/usb/serial/usb-serial-simple.c
@@ -100,6 +100,11 @@ DEVICE(nokia, NOKIA_IDS);
 	{ USB_DEVICE(0x09d7, 0x0100) }	/* NovAtel FlexPack GPS */
 DEVICE_N(novatel_gps, NOVATEL_IDS, 3);
 
+/* OWON electronic test and measurement equipment driver */
+#define OWON_IDS()			\
+	{ USB_DEVICE(0x5345, 0x1234) } /* HDS200 oscilloscopes and others */
+DEVICE(owon, OWON_IDS);
+
 /* Siemens USB/MPI adapter */
 #define SIEMENS_IDS()			\
 	{ USB_DEVICE(0x908, 0x0004) }
@@ -134,6 +139,7 @@ static struct usb_serial_driver * const serial_drivers[] = {
 	&motorola_tetra_device,
 	&nokia_device,
 	&novatel_gps_device,
+	&owon_device,
 	&siemens_mpi_device,
 	&suunto_device,
 	&vivopay_device,
@@ -153,6 +159,7 @@ static const struct usb_device_id id_table[] = {
 	MOTOROLA_TETRA_IDS(),
 	NOKIA_IDS(),
 	NOVATEL_IDS(),
+	OWON_IDS(),
 	SIEMENS_IDS(),
 	SUUNTO_IDS(),
 	VIVOPAY_IDS(),
diff --git a/drivers/usb/storage/Makefile b/drivers/usb/storage/Makefile
index 46635fa4a340..28db337f190b 100644
--- a/drivers/usb/storage/Makefile
+++ b/drivers/usb/storage/Makefile
@@ -8,7 +8,7 @@
 
 ccflags-y := -I $(srctree)/drivers/scsi
 
-ccflags-y += -DDEFAULT_SYMBOL_NAMESPACE=USB_STORAGE
+ccflags-y += -DDEFAULT_SYMBOL_NAMESPACE='"USB_STORAGE"'
 
 obj-$(CONFIG_USB_UAS)		+= uas.o
 obj-$(CONFIG_USB_STORAGE)	+= usb-storage.o
diff --git a/drivers/usb/storage/unusual_uas.h b/drivers/usb/storage/unusual_uas.h
index 1f8c9b16a0fb..1477e31d7763 100644
--- a/drivers/usb/storage/unusual_uas.h
+++ b/drivers/usb/storage/unusual_uas.h
@@ -52,6 +52,13 @@ UNUSUAL_DEV(0x059f, 0x1061, 0x0000, 0x9999,
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
 		US_FL_NO_REPORT_OPCODES | US_FL_NO_SAME),
 
+/* Reported-by: Zhihong Zhou <zhouzhihong@greatwall.com.cn> */
+UNUSUAL_DEV(0x0781, 0x55e8, 0x0000, 0x9999,
+		"SanDisk",
+		"",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_IGNORE_UAS),
+
 /* Reported-by: Hongling Zeng <zenghongling@kylinos.cn> */
 UNUSUAL_DEV(0x090c, 0x2000, 0x0000, 0x9999,
 		"Hiksemi",
@@ -83,6 +90,13 @@ UNUSUAL_DEV(0x0bc2, 0x331a, 0x0000, 0x9999,
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
 		US_FL_NO_REPORT_LUNS),
 
+/* Reported-by: Oliver Neukum <oneukum@suse.com> */
+UNUSUAL_DEV(0x125f, 0xa94a, 0x0160, 0x0160,
+		"ADATA",
+		"Portable HDD CH94",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_NO_ATA_1X),
+
 /* Reported-by: Benjamin Tissoires <benjamin.tissoires@redhat.com> */
 UNUSUAL_DEV(0x13fd, 0x3940, 0x0000, 0x9999,
 		"Initio Corporation",
diff --git a/drivers/usb/typec/altmodes/displayport.c b/drivers/usb/typec/altmodes/displayport.c
index 92cc1b136120..6964f403a2d5 100644
--- a/drivers/usb/typec/altmodes/displayport.c
+++ b/drivers/usb/typec/altmodes/displayport.c
@@ -393,6 +393,9 @@ static int dp_altmode_vdm(struct typec_altmode *alt,
 		break;
 	case CMDT_RSP_NAK:
 		switch (cmd) {
+		case DP_CMD_STATUS_UPDATE:
+			dp->state = DP_STATE_EXIT;
+			break;
 		case DP_CMD_CONFIGURE:
 			dp->data.conf = 0;
 			ret = dp_altmode_configured(dp);
@@ -673,7 +676,7 @@ static ssize_t pin_assignment_show(struct device *dev,
 
 	assignments = get_current_pin_assignments(dp);
 
-	for (i = 0; assignments; assignments >>= 1, i++) {
+	for (i = 0; assignments && i < DP_PIN_ASSIGN_MAX; assignments >>= 1, i++) {
 		if (assignments & 1) {
 			if (i == cur)
 				len += sprintf(buf + len, "[%s] ",
diff --git a/drivers/usb/typec/bus.c b/drivers/usb/typec/bus.c
index aa879253d3b8..13044ee5be10 100644
--- a/drivers/usb/typec/bus.c
+++ b/drivers/usb/typec/bus.c
@@ -449,7 +449,7 @@ ATTRIBUTE_GROUPS(typec);
 
 static int typec_match(struct device *dev, const struct device_driver *driver)
 {
-	struct typec_altmode_driver *drv = to_altmode_driver(driver);
+	const struct typec_altmode_driver *drv = to_altmode_driver(driver);
 	struct typec_altmode *altmode = to_typec_altmode(dev);
 	const struct typec_device_id *id;
 
diff --git a/drivers/usb/typec/class.c b/drivers/usb/typec/class.c
index 58f40156de56..5c75634b8fa3 100644
--- a/drivers/usb/typec/class.c
+++ b/drivers/usb/typec/class.c
@@ -932,9 +932,11 @@ struct typec_partner *typec_register_partner(struct typec_port *port,
 	partner->dev.type = &typec_partner_dev_type;
 	dev_set_name(&partner->dev, "%s-partner", dev_name(&port->dev));
 
+	mutex_lock(&port->partner_link_lock);
 	ret = device_register(&partner->dev);
 	if (ret) {
 		dev_err(&port->dev, "failed to register partner (%d)\n", ret);
+		mutex_unlock(&port->partner_link_lock);
 		put_device(&partner->dev);
 		return ERR_PTR(ret);
 	}
@@ -943,6 +945,7 @@ struct typec_partner *typec_register_partner(struct typec_port *port,
 		typec_partner_link_device(partner, port->usb2_dev);
 	if (port->usb3_dev)
 		typec_partner_link_device(partner, port->usb3_dev);
+	mutex_unlock(&port->partner_link_lock);
 
 	return partner;
 }
@@ -963,12 +966,18 @@ void typec_unregister_partner(struct typec_partner *partner)
 
 	port = to_typec_port(partner->dev.parent);
 
-	if (port->usb2_dev)
+	mutex_lock(&port->partner_link_lock);
+	if (port->usb2_dev) {
 		typec_partner_unlink_device(partner, port->usb2_dev);
-	if (port->usb3_dev)
+		port->usb2_dev = NULL;
+	}
+	if (port->usb3_dev) {
 		typec_partner_unlink_device(partner, port->usb3_dev);
+		port->usb3_dev = NULL;
+	}
 
 	device_unregister(&partner->dev);
+	mutex_unlock(&port->partner_link_lock);
 }
 EXPORT_SYMBOL_GPL(typec_unregister_partner);
 
@@ -1862,25 +1871,30 @@ static struct typec_partner *typec_get_partner(struct typec_port *port)
 static void typec_partner_attach(struct typec_connector *con, struct device *dev)
 {
 	struct typec_port *port = container_of(con, struct typec_port, con);
-	struct typec_partner *partner = typec_get_partner(port);
+	struct typec_partner *partner;
 	struct usb_device *udev = to_usb_device(dev);
 
+	mutex_lock(&port->partner_link_lock);
 	if (udev->speed < USB_SPEED_SUPER)
 		port->usb2_dev = dev;
 	else
 		port->usb3_dev = dev;
 
+	partner = typec_get_partner(port);
 	if (partner) {
 		typec_partner_link_device(partner, dev);
 		put_device(&partner->dev);
 	}
+	mutex_unlock(&port->partner_link_lock);
 }
 
 static void typec_partner_deattach(struct typec_connector *con, struct device *dev)
 {
 	struct typec_port *port = container_of(con, struct typec_port, con);
-	struct typec_partner *partner = typec_get_partner(port);
+	struct typec_partner *partner;
 
+	mutex_lock(&port->partner_link_lock);
+	partner = typec_get_partner(port);
 	if (partner) {
 		typec_partner_unlink_device(partner, dev);
 		put_device(&partner->dev);
@@ -1890,6 +1904,7 @@ static void typec_partner_deattach(struct typec_connector *con, struct device *d
 		port->usb2_dev = NULL;
 	else if (port->usb3_dev == dev)
 		port->usb3_dev = NULL;
+	mutex_unlock(&port->partner_link_lock);
 }
 
 /**
@@ -2425,6 +2440,7 @@ struct typec_port *typec_register_port(struct device *parent,
 
 	ida_init(&port->mode_ids);
 	mutex_init(&port->port_type_lock);
+	mutex_init(&port->partner_link_lock);
 
 	port->id = id;
 	port->ops = cap->ops;
diff --git a/drivers/usb/typec/class.h b/drivers/usb/typec/class.h
index 7485cdb9dd20..300312a1c152 100644
--- a/drivers/usb/typec/class.h
+++ b/drivers/usb/typec/class.h
@@ -56,6 +56,7 @@ struct typec_port {
 	enum typec_pwr_opmode		pwr_opmode;
 	enum typec_port_type		port_type;
 	struct mutex			port_type_lock;
+	struct mutex			partner_link_lock;
 
 	enum typec_orientation		orientation;
 	struct typec_switch		*sw;
diff --git a/drivers/usb/typec/mux.c b/drivers/usb/typec/mux.c
index 49926d6e72c7..182c902c42f6 100644
--- a/drivers/usb/typec/mux.c
+++ b/drivers/usb/typec/mux.c
@@ -214,7 +214,7 @@ int typec_switch_set(struct typec_switch *sw,
 		sw_dev = sw->sw_devs[i];
 
 		ret = sw_dev->set(sw_dev, orientation);
-		if (ret)
+		if (ret && ret != -EOPNOTSUPP)
 			return ret;
 	}
 
@@ -378,7 +378,7 @@ int typec_mux_set(struct typec_mux *mux, struct typec_mux_state *state)
 		mux_dev = mux->mux_devs[i];
 
 		ret = mux_dev->set(mux_dev, state);
-		if (ret)
+		if (ret && ret != -EOPNOTSUPP)
 			return ret;
 	}
 
diff --git a/drivers/usb/typec/mux/intel_pmc_mux.c b/drivers/usb/typec/mux/intel_pmc_mux.c
index 46b4c5c3a6be..32343f567d44 100644
--- a/drivers/usb/typec/mux/intel_pmc_mux.c
+++ b/drivers/usb/typec/mux/intel_pmc_mux.c
@@ -754,7 +754,7 @@ static int pmc_usb_probe(struct platform_device *pdev)
 
 	pmc->ipc = devm_intel_scu_ipc_dev_get(&pdev->dev);
 	if (!pmc->ipc)
-		return -ENODEV;
+		return -EPROBE_DEFER;
 
 	pmc->dev = &pdev->dev;
 
diff --git a/drivers/usb/typec/tcpm/tcpci.c b/drivers/usb/typec/tcpm/tcpci.c
index 24a6a4354df8..b2c83f552da5 100644
--- a/drivers/usb/typec/tcpm/tcpci.c
+++ b/drivers/usb/typec/tcpm/tcpci.c
@@ -27,6 +27,7 @@
 #define	VPPS_NEW_MIN_PERCENT			95
 #define	VPPS_VALID_MIN_MV			100
 #define	VSINKDISCONNECT_PD_MIN_PERCENT		90
+#define	VPPS_SHUTDOWN_MIN_PERCENT		85
 
 struct tcpci {
 	struct device *dev;
@@ -366,7 +367,8 @@ static int tcpci_enable_auto_vbus_discharge(struct tcpc_dev *dev, bool enable)
 }
 
 static int tcpci_set_auto_vbus_discharge_threshold(struct tcpc_dev *dev, enum typec_pwr_opmode mode,
-						   bool pps_active, u32 requested_vbus_voltage_mv)
+						   bool pps_active, u32 requested_vbus_voltage_mv,
+						   u32 apdo_min_voltage_mv)
 {
 	struct tcpci *tcpci = tcpc_to_tcpci(dev);
 	unsigned int pwr_ctrl, threshold = 0;
@@ -388,9 +390,12 @@ static int tcpci_set_auto_vbus_discharge_threshold(struct tcpc_dev *dev, enum ty
 		threshold = AUTO_DISCHARGE_DEFAULT_THRESHOLD_MV;
 	} else if (mode == TYPEC_PWR_MODE_PD) {
 		if (pps_active)
-			threshold = ((VPPS_NEW_MIN_PERCENT * requested_vbus_voltage_mv / 100) -
-				     VSINKPD_MIN_IR_DROP_MV - VPPS_VALID_MIN_MV) *
-				     VSINKDISCONNECT_PD_MIN_PERCENT / 100;
+			/*
+			 * To prevent disconnect when the source is in Current Limit Mode.
+			 * Set the threshold to the lowest possible voltage vPpsShutdown (min)
+			 */
+			threshold = VPPS_SHUTDOWN_MIN_PERCENT * apdo_min_voltage_mv / 100 -
+				    VSINKPD_MIN_IR_DROP_MV;
 		else
 			threshold = ((VSRC_NEW_MIN_PERCENT * requested_vbus_voltage_mv / 100) -
 				     VSINKPD_MIN_IR_DROP_MV - VSRC_VALID_MIN_MV) *
diff --git a/drivers/usb/typec/tcpm/tcpci_maxim_core.c b/drivers/usb/typec/tcpm/tcpci_maxim_core.c
index fd1b80593367..eeaf79e97261 100644
--- a/drivers/usb/typec/tcpm/tcpci_maxim_core.c
+++ b/drivers/usb/typec/tcpm/tcpci_maxim_core.c
@@ -166,7 +166,8 @@ static void process_rx(struct max_tcpci_chip *chip, u16 status)
 		return;
 	}
 
-	if (count > sizeof(struct pd_message) || count + 1 > TCPC_RECEIVE_BUFFER_LEN) {
+	if (count > sizeof(struct pd_message) + 1 ||
+	    count + 1 > TCPC_RECEIVE_BUFFER_LEN) {
 		dev_err(chip->dev, "Invalid TCPC_RX_BYTE_CNT %d\n", count);
 		return;
 	}
@@ -420,21 +421,6 @@ static irqreturn_t max_tcpci_isr(int irq, void *dev_id)
 	return IRQ_WAKE_THREAD;
 }
 
-static int max_tcpci_init_alert(struct max_tcpci_chip *chip, struct i2c_client *client)
-{
-	int ret;
-
-	ret = devm_request_threaded_irq(chip->dev, client->irq, max_tcpci_isr, max_tcpci_irq,
-					(IRQF_TRIGGER_LOW | IRQF_ONESHOT), dev_name(chip->dev),
-					chip);
-
-	if (ret < 0)
-		return ret;
-
-	enable_irq_wake(client->irq);
-	return 0;
-}
-
 static int max_tcpci_start_toggling(struct tcpci *tcpci, struct tcpci_data *tdata,
 				    enum typec_cc_status cc)
 {
@@ -531,7 +517,9 @@ static int max_tcpci_probe(struct i2c_client *client)
 
 	chip->port = tcpci_get_tcpm_port(chip->tcpci);
 
-	ret = max_tcpci_init_alert(chip, client);
+	ret = devm_request_threaded_irq(&client->dev, client->irq, max_tcpci_isr, max_tcpci_irq,
+					(IRQF_TRIGGER_LOW | IRQF_ONESHOT), dev_name(chip->dev),
+					chip);
 	if (ret < 0)
 		return dev_err_probe(&client->dev, ret,
 				     "IRQ initialization failed\n");
@@ -540,6 +528,32 @@ static int max_tcpci_probe(struct i2c_client *client)
 	return 0;
 }
 
+#ifdef CONFIG_PM_SLEEP
+static int max_tcpci_resume(struct device *dev)
+{
+	struct i2c_client *client = to_i2c_client(dev);
+	int ret = 0;
+
+	if (client->irq && device_may_wakeup(dev))
+		ret = disable_irq_wake(client->irq);
+
+	return ret;
+}
+
+static int max_tcpci_suspend(struct device *dev)
+{
+	struct i2c_client *client = to_i2c_client(dev);
+	int ret = 0;
+
+	if (client->irq && device_may_wakeup(dev))
+		ret = enable_irq_wake(client->irq);
+
+	return ret;
+}
+#endif /* CONFIG_PM_SLEEP */
+
+static SIMPLE_DEV_PM_OPS(max_tcpci_pm_ops, max_tcpci_suspend, max_tcpci_resume);
+
 static const struct i2c_device_id max_tcpci_id[] = {
 	{ "maxtcpc" },
 	{ }
@@ -558,6 +572,7 @@ static struct i2c_driver max_tcpci_i2c_driver = {
 	.driver = {
 		.name = "maxtcpc",
 		.of_match_table = of_match_ptr(max_tcpci_of_match),
+		.pm = &max_tcpci_pm_ops,
 	},
 	.probe = max_tcpci_probe,
 	.id_table = max_tcpci_id,
diff --git a/drivers/usb/typec/tcpm/tcpci_rt1711h.c b/drivers/usb/typec/tcpm/tcpci_rt1711h.c
index 64f6dd0dc660..88c50b984e8a 100644
--- a/drivers/usb/typec/tcpm/tcpci_rt1711h.c
+++ b/drivers/usb/typec/tcpm/tcpci_rt1711h.c
@@ -334,6 +334,11 @@ static int rt1711h_probe(struct i2c_client *client)
 {
 	int ret;
 	struct rt1711h_chip *chip;
+	const u16 alert_mask = TCPC_ALERT_TX_SUCCESS | TCPC_ALERT_TX_DISCARDED |
+			       TCPC_ALERT_TX_FAILED | TCPC_ALERT_RX_HARD_RST |
+			       TCPC_ALERT_RX_STATUS | TCPC_ALERT_POWER_STATUS |
+			       TCPC_ALERT_CC_STATUS | TCPC_ALERT_RX_BUF_OVF |
+			       TCPC_ALERT_FAULT;
 
 	chip = devm_kzalloc(&client->dev, sizeof(*chip), GFP_KERNEL);
 	if (!chip)
@@ -382,6 +387,12 @@ static int rt1711h_probe(struct i2c_client *client)
 					dev_name(chip->dev), chip);
 	if (ret < 0)
 		return ret;
+
+	/* Enable alert interrupts */
+	ret = rt1711h_write16(chip, TCPC_ALERT_MASK, alert_mask);
+	if (ret < 0)
+		return ret;
+
 	enable_irq_wake(client->irq);
 
 	return 0;
diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c
index 7ae341a40342..aa2fa720af15 100644
--- a/drivers/usb/typec/tcpm/tcpm.c
+++ b/drivers/usb/typec/tcpm/tcpm.c
@@ -568,6 +568,15 @@ struct pd_rx_event {
 	enum tcpm_transmit_type rx_sop_type;
 };
 
+struct altmode_vdm_event {
+	struct kthread_work work;
+	struct tcpm_port *port;
+	u32 header;
+	u32 *data;
+	int cnt;
+	enum tcpm_transmit_type tx_sop_type;
+};
+
 static const char * const pd_rev[] = {
 	[PD_REV10]		= "rev1",
 	[PD_REV20]		= "rev2",
@@ -1123,7 +1132,7 @@ static int tcpm_set_attached_state(struct tcpm_port *port, bool attached)
 				     port->data_role);
 }
 
-static int tcpm_set_roles(struct tcpm_port *port, bool attached,
+static int tcpm_set_roles(struct tcpm_port *port, bool attached, int state,
 			  enum typec_role role, enum typec_data_role data)
 {
 	enum typec_orientation orientation;
@@ -1160,7 +1169,7 @@ static int tcpm_set_roles(struct tcpm_port *port, bool attached,
 		}
 	}
 
-	ret = tcpm_mux_set(port, TYPEC_STATE_USB, usb_role, orientation);
+	ret = tcpm_mux_set(port, state, usb_role, orientation);
 	if (ret < 0)
 		return ret;
 
@@ -1562,18 +1571,68 @@ static void tcpm_queue_vdm(struct tcpm_port *port, const u32 header,
 	mod_vdm_delayed_work(port, 0);
 }
 
-static void tcpm_queue_vdm_unlocked(struct tcpm_port *port, const u32 header,
-				    const u32 *data, int cnt, enum tcpm_transmit_type tx_sop_type)
+static void tcpm_queue_vdm_work(struct kthread_work *work)
 {
-	if (port->state != SRC_READY && port->state != SNK_READY &&
-	    port->state != SRC_VDM_IDENTITY_REQUEST)
-		return;
+	struct altmode_vdm_event *event = container_of(work,
+						       struct altmode_vdm_event,
+						       work);
+	struct tcpm_port *port = event->port;
 
 	mutex_lock(&port->lock);
-	tcpm_queue_vdm(port, header, data, cnt, tx_sop_type);
+	if (port->state != SRC_READY && port->state != SNK_READY &&
+	    port->state != SRC_VDM_IDENTITY_REQUEST) {
+		tcpm_log_force(port, "dropping altmode_vdm_event");
+		goto port_unlock;
+	}
+
+	tcpm_queue_vdm(port, event->header, event->data, event->cnt, event->tx_sop_type);
+
+port_unlock:
+	kfree(event->data);
+	kfree(event);
 	mutex_unlock(&port->lock);
 }
 
+static int tcpm_queue_vdm_unlocked(struct tcpm_port *port, const u32 header,
+				   const u32 *data, int cnt, enum tcpm_transmit_type tx_sop_type)
+{
+	struct altmode_vdm_event *event;
+	u32 *data_cpy;
+	int ret = -ENOMEM;
+
+	event = kzalloc(sizeof(*event), GFP_KERNEL);
+	if (!event)
+		goto err_event;
+
+	data_cpy = kcalloc(cnt, sizeof(u32), GFP_KERNEL);
+	if (!data_cpy)
+		goto err_data;
+
+	kthread_init_work(&event->work, tcpm_queue_vdm_work);
+	event->port = port;
+	event->header = header;
+	memcpy(data_cpy, data, sizeof(u32) * cnt);
+	event->data = data_cpy;
+	event->cnt = cnt;
+	event->tx_sop_type = tx_sop_type;
+
+	ret = kthread_queue_work(port->wq, &event->work);
+	if (!ret) {
+		ret = -EBUSY;
+		goto err_queue;
+	}
+
+	return 0;
+
+err_queue:
+	kfree(data_cpy);
+err_data:
+	kfree(event);
+err_event:
+	tcpm_log_force(port, "failed to queue altmode vdm, err:%d", ret);
+	return ret;
+}
+
 static void svdm_consume_identity(struct tcpm_port *port, const u32 *p, int cnt)
 {
 	u32 vdo = p[VDO_INDEX_IDH];
@@ -2784,8 +2843,7 @@ static int tcpm_altmode_enter(struct typec_altmode *altmode, u32 *vdo)
 	header = VDO(altmode->svid, vdo ? 2 : 1, svdm_version, CMD_ENTER_MODE);
 	header |= VDO_OPOS(altmode->mode);
 
-	tcpm_queue_vdm_unlocked(port, header, vdo, vdo ? 1 : 0, TCPC_TX_SOP);
-	return 0;
+	return tcpm_queue_vdm_unlocked(port, header, vdo, vdo ? 1 : 0, TCPC_TX_SOP);
 }
 
 static int tcpm_altmode_exit(struct typec_altmode *altmode)
@@ -2801,8 +2859,7 @@ static int tcpm_altmode_exit(struct typec_altmode *altmode)
 	header = VDO(altmode->svid, 1, svdm_version, CMD_EXIT_MODE);
 	header |= VDO_OPOS(altmode->mode);
 
-	tcpm_queue_vdm_unlocked(port, header, NULL, 0, TCPC_TX_SOP);
-	return 0;
+	return tcpm_queue_vdm_unlocked(port, header, NULL, 0, TCPC_TX_SOP);
 }
 
 static int tcpm_altmode_vdm(struct typec_altmode *altmode,
@@ -2810,9 +2867,7 @@ static int tcpm_altmode_vdm(struct typec_altmode *altmode,
 {
 	struct tcpm_port *port = typec_altmode_get_drvdata(altmode);
 
-	tcpm_queue_vdm_unlocked(port, header, data, count - 1, TCPC_TX_SOP);
-
-	return 0;
+	return tcpm_queue_vdm_unlocked(port, header, data, count - 1, TCPC_TX_SOP);
 }
 
 static const struct typec_altmode_ops tcpm_altmode_ops = {
@@ -2836,8 +2891,7 @@ static int tcpm_cable_altmode_enter(struct typec_altmode *altmode, enum typec_pl
 	header = VDO(altmode->svid, vdo ? 2 : 1, svdm_version, CMD_ENTER_MODE);
 	header |= VDO_OPOS(altmode->mode);
 
-	tcpm_queue_vdm_unlocked(port, header, vdo, vdo ? 1 : 0, TCPC_TX_SOP_PRIME);
-	return 0;
+	return tcpm_queue_vdm_unlocked(port, header, vdo, vdo ? 1 : 0, TCPC_TX_SOP_PRIME);
 }
 
 static int tcpm_cable_altmode_exit(struct typec_altmode *altmode, enum typec_plug_index sop)
@@ -2853,8 +2907,7 @@ static int tcpm_cable_altmode_exit(struct typec_altmode *altmode, enum typec_plu
 	header = VDO(altmode->svid, 1, svdm_version, CMD_EXIT_MODE);
 	header |= VDO_OPOS(altmode->mode);
 
-	tcpm_queue_vdm_unlocked(port, header, NULL, 0, TCPC_TX_SOP_PRIME);
-	return 0;
+	return tcpm_queue_vdm_unlocked(port, header, NULL, 0, TCPC_TX_SOP_PRIME);
 }
 
 static int tcpm_cable_altmode_vdm(struct typec_altmode *altmode, enum typec_plug_index sop,
@@ -2862,9 +2915,7 @@ static int tcpm_cable_altmode_vdm(struct typec_altmode *altmode, enum typec_plug
 {
 	struct tcpm_port *port = typec_altmode_get_drvdata(altmode);
 
-	tcpm_queue_vdm_unlocked(port, header, data, count - 1, TCPC_TX_SOP_PRIME);
-
-	return 0;
+	return tcpm_queue_vdm_unlocked(port, header, data, count - 1, TCPC_TX_SOP_PRIME);
 }
 
 static const struct typec_cable_ops tcpm_cable_ops = {
@@ -2928,10 +2979,12 @@ static int tcpm_set_auto_vbus_discharge_threshold(struct tcpm_port *port,
 		return 0;
 
 	ret = port->tcpc->set_auto_vbus_discharge_threshold(port->tcpc, mode, pps_active,
-							    requested_vbus_voltage);
+							    requested_vbus_voltage,
+							    port->pps_data.min_volt);
 	tcpm_log_force(port,
-		       "set_auto_vbus_discharge_threshold mode:%d pps_active:%c vbus:%u ret:%d",
-		       mode, pps_active ? 'y' : 'n', requested_vbus_voltage, ret);
+		       "set_auto_vbus_discharge_threshold mode:%d pps_active:%c vbus:%u pps_apdo_min_volt:%u ret:%d",
+		       mode, pps_active ? 'y' : 'n', requested_vbus_voltage,
+		       port->pps_data.min_volt, ret);
 
 	return ret;
 }
@@ -4286,16 +4339,6 @@ static int tcpm_src_attach(struct tcpm_port *port)
 
 	tcpm_enable_auto_vbus_discharge(port, true);
 
-	ret = tcpm_set_roles(port, true, TYPEC_SOURCE, tcpm_data_role_for_source(port));
-	if (ret < 0)
-		return ret;
-
-	if (port->pd_supported) {
-		ret = port->tcpc->set_pd_rx(port->tcpc, true);
-		if (ret < 0)
-			goto out_disable_mux;
-	}
-
 	/*
 	 * USB Type-C specification, version 1.2,
 	 * chapter 4.5.2.2.8.1 (Attached.SRC Requirements)
@@ -4305,13 +4348,24 @@ static int tcpm_src_attach(struct tcpm_port *port)
 	    (polarity == TYPEC_POLARITY_CC2 && port->cc1 == TYPEC_CC_RA)) {
 		ret = tcpm_set_vconn(port, true);
 		if (ret < 0)
-			goto out_disable_pd;
+			return ret;
 	}
 
 	ret = tcpm_set_vbus(port, true);
 	if (ret < 0)
 		goto out_disable_vconn;
 
+	ret = tcpm_set_roles(port, true, TYPEC_STATE_USB, TYPEC_SOURCE,
+			     tcpm_data_role_for_source(port));
+	if (ret < 0)
+		goto out_disable_vbus;
+
+	if (port->pd_supported) {
+		ret = port->tcpc->set_pd_rx(port->tcpc, true);
+		if (ret < 0)
+			goto out_disable_mux;
+	}
+
 	port->pd_capable = false;
 
 	port->partner = NULL;
@@ -4322,14 +4376,14 @@ static int tcpm_src_attach(struct tcpm_port *port)
 
 	return 0;
 
-out_disable_vconn:
-	tcpm_set_vconn(port, false);
-out_disable_pd:
-	if (port->pd_supported)
-		port->tcpc->set_pd_rx(port->tcpc, false);
 out_disable_mux:
 	tcpm_mux_set(port, TYPEC_STATE_SAFE, USB_ROLE_NONE,
 		     TYPEC_ORIENTATION_NONE);
+out_disable_vbus:
+	tcpm_set_vbus(port, false);
+out_disable_vconn:
+	tcpm_set_vconn(port, false);
+
 	return ret;
 }
 
@@ -4461,7 +4515,8 @@ static int tcpm_snk_attach(struct tcpm_port *port)
 
 	tcpm_enable_auto_vbus_discharge(port, true);
 
-	ret = tcpm_set_roles(port, true, TYPEC_SINK, tcpm_data_role_for_sink(port));
+	ret = tcpm_set_roles(port, true, TYPEC_STATE_USB,
+			     TYPEC_SINK, tcpm_data_role_for_sink(port));
 	if (ret < 0)
 		return ret;
 
@@ -4484,12 +4539,24 @@ static void tcpm_snk_detach(struct tcpm_port *port)
 static int tcpm_acc_attach(struct tcpm_port *port)
 {
 	int ret;
+	enum typec_role role;
+	enum typec_data_role data;
+	int state = TYPEC_STATE_USB;
 
 	if (port->attached)
 		return 0;
 
-	ret = tcpm_set_roles(port, true, TYPEC_SOURCE,
-			     tcpm_data_role_for_source(port));
+	role = tcpm_port_is_sink(port) ? TYPEC_SINK : TYPEC_SOURCE;
+	data = tcpm_port_is_sink(port) ? tcpm_data_role_for_sink(port)
+				       : tcpm_data_role_for_source(port);
+
+	if (tcpm_port_is_audio(port))
+		state = TYPEC_MODE_AUDIO;
+
+	if (tcpm_port_is_debug(port))
+		state = TYPEC_MODE_DEBUG;
+
+	ret = tcpm_set_roles(port, true, state, role, data);
 	if (ret < 0)
 		return ret;
 
@@ -4757,7 +4824,7 @@ static void run_state_machine(struct tcpm_port *port)
 			port->caps_count = 0;
 			port->pd_capable = true;
 			tcpm_set_state_cond(port, SRC_SEND_CAPABILITIES_TIMEOUT,
-					    PD_T_SEND_SOURCE_CAP);
+					    PD_T_SENDER_RESPONSE);
 		}
 		break;
 	case SRC_SEND_CAPABILITIES_TIMEOUT:
@@ -5248,7 +5315,7 @@ static void run_state_machine(struct tcpm_port *port)
 		 */
 		tcpm_set_vconn(port, false);
 		tcpm_set_vbus(port, false);
-		tcpm_set_roles(port, port->self_powered, TYPEC_SOURCE,
+		tcpm_set_roles(port, port->self_powered, TYPEC_STATE_USB, TYPEC_SOURCE,
 			       tcpm_data_role_for_source(port));
 		/*
 		 * If tcpc fails to notify vbus off, TCPM will wait for PD_T_SAFE_0V +
@@ -5280,7 +5347,7 @@ static void run_state_machine(struct tcpm_port *port)
 		tcpm_set_vconn(port, false);
 		if (port->pd_capable)
 			tcpm_set_charge(port, false);
-		tcpm_set_roles(port, port->self_powered, TYPEC_SINK,
+		tcpm_set_roles(port, port->self_powered, TYPEC_STATE_USB, TYPEC_SINK,
 			       tcpm_data_role_for_sink(port));
 		/*
 		 * VBUS may or may not toggle, depending on the adapter.
@@ -5404,10 +5471,10 @@ static void run_state_machine(struct tcpm_port *port)
 	case DR_SWAP_CHANGE_DR:
 		tcpm_unregister_altmodes(port);
 		if (port->data_role == TYPEC_HOST)
-			tcpm_set_roles(port, true, port->pwr_role,
+			tcpm_set_roles(port, true, TYPEC_STATE_USB, port->pwr_role,
 				       TYPEC_DEVICE);
 		else
-			tcpm_set_roles(port, true, port->pwr_role,
+			tcpm_set_roles(port, true, TYPEC_STATE_USB, port->pwr_role,
 				       TYPEC_HOST);
 		tcpm_ams_finish(port);
 		tcpm_set_state(port, ready_state(port), 0);
@@ -5513,8 +5580,7 @@ static void run_state_machine(struct tcpm_port *port)
 		tcpm_set_auto_vbus_discharge_threshold(port, TYPEC_PWR_MODE_USB,
 						       port->pps_data.active, 0);
 		tcpm_set_charge(port, false);
-		tcpm_set_state(port, hard_reset_state(port),
-			       PD_T_PS_SOURCE_OFF);
+		tcpm_set_state(port, ERROR_RECOVERY, PD_T_PS_SOURCE_OFF);
 		break;
 	case PR_SWAP_SNK_SRC_SOURCE_ON:
 		tcpm_enable_auto_vbus_discharge(port, true);
@@ -5888,7 +5954,7 @@ static void _tcpm_cc_change(struct tcpm_port *port, enum typec_cc_status cc1,
 	case SNK_TRY_WAIT_DEBOUNCE:
 		if (!tcpm_port_is_sink(port)) {
 			port->max_wait = 0;
-			tcpm_set_state(port, SRC_TRYWAIT, 0);
+			tcpm_set_state(port, SRC_TRYWAIT, PD_T_PD_DEBOUNCE);
 		}
 		break;
 	case SRC_TRY_WAIT:
diff --git a/drivers/usb/typec/ucsi/displayport.c b/drivers/usb/typec/ucsi/displayport.c
index 420af5139c70..8aae80b457d7 100644
--- a/drivers/usb/typec/ucsi/displayport.c
+++ b/drivers/usb/typec/ucsi/displayport.c
@@ -54,7 +54,8 @@ static int ucsi_displayport_enter(struct typec_altmode *alt, u32 *vdo)
 	u8 cur = 0;
 	int ret;
 
-	mutex_lock(&dp->con->lock);
+	if (!ucsi_con_mutex_lock(dp->con))
+		return -ENOTCONN;
 
 	if (!dp->override && dp->initialized) {
 		const struct typec_altmode *p = typec_altmode_get_partner(alt);
@@ -100,7 +101,7 @@ static int ucsi_displayport_enter(struct typec_altmode *alt, u32 *vdo)
 	schedule_work(&dp->work);
 	ret = 0;
 err_unlock:
-	mutex_unlock(&dp->con->lock);
+	ucsi_con_mutex_unlock(dp->con);
 
 	return ret;
 }
@@ -112,7 +113,8 @@ static int ucsi_displayport_exit(struct typec_altmode *alt)
 	u64 command;
 	int ret = 0;
 
-	mutex_lock(&dp->con->lock);
+	if (!ucsi_con_mutex_lock(dp->con))
+		return -ENOTCONN;
 
 	if (!dp->override) {
 		const struct typec_altmode *p = typec_altmode_get_partner(alt);
@@ -144,7 +146,7 @@ static int ucsi_displayport_exit(struct typec_altmode *alt)
 	schedule_work(&dp->work);
 
 out_unlock:
-	mutex_unlock(&dp->con->lock);
+	ucsi_con_mutex_unlock(dp->con);
 
 	return ret;
 }
@@ -202,20 +204,21 @@ static int ucsi_displayport_vdm(struct typec_altmode *alt,
 	int cmd = PD_VDO_CMD(header);
 	int svdm_version;
 
-	mutex_lock(&dp->con->lock);
+	if (!ucsi_con_mutex_lock(dp->con))
+		return -ENOTCONN;
 
 	if (!dp->override && dp->initialized) {
 		const struct typec_altmode *p = typec_altmode_get_partner(alt);
 
 		dev_warn(&p->dev,
 			 "firmware doesn't support alternate mode overriding\n");
-		mutex_unlock(&dp->con->lock);
+		ucsi_con_mutex_unlock(dp->con);
 		return -EOPNOTSUPP;
 	}
 
 	svdm_version = typec_altmode_get_svdm_version(alt);
 	if (svdm_version < 0) {
-		mutex_unlock(&dp->con->lock);
+		ucsi_con_mutex_unlock(dp->con);
 		return svdm_version;
 	}
 
@@ -259,7 +262,7 @@ static int ucsi_displayport_vdm(struct typec_altmode *alt,
 		break;
 	}
 
-	mutex_unlock(&dp->con->lock);
+	ucsi_con_mutex_unlock(dp->con);
 
 	return 0;
 }
@@ -296,6 +299,8 @@ void ucsi_displayport_remove_partner(struct typec_altmode *alt)
 	if (!dp)
 		return;
 
+	cancel_work_sync(&dp->work);
+
 	dp->data.conf = 0;
 	dp->data.status = 0;
 	dp->initialized = false;
diff --git a/drivers/usb/typec/ucsi/psy.c b/drivers/usb/typec/ucsi/psy.c
index 1c631c7855a9..9447a50716ec 100644
--- a/drivers/usb/typec/ucsi/psy.c
+++ b/drivers/usb/typec/ucsi/psy.c
@@ -164,7 +164,7 @@ static int ucsi_psy_get_current_max(struct ucsi_connector *con,
 	case UCSI_CONSTAT_PWR_OPMODE_DEFAULT:
 	/* UCSI can't tell b/w DCP/CDP or USB2/3x1/3x2 SDP chargers */
 	default:
-		val->intval = 0;
+		val->intval = UCSI_TYPEC_DEFAULT_CURRENT * 1000;
 		break;
 	}
 	return 0;
diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c
index 7a3f0f5af38f..896e6bc1b5e2 100644
--- a/drivers/usb/typec/ucsi/ucsi.c
+++ b/drivers/usb/typec/ucsi/ucsi.c
@@ -25,7 +25,7 @@
  * difficult to estimate the time it takes for the system to process the command
  * before it is actually passed to the PPM.
  */
-#define UCSI_TIMEOUT_MS		5000
+#define UCSI_TIMEOUT_MS		10000
 
 /*
  * UCSI_SWAP_TIMEOUT_MS - Timeout for role swap requests
@@ -1225,6 +1225,7 @@ static void ucsi_handle_connector_change(struct work_struct *work)
 
 	if (con->status.change & UCSI_CONSTAT_POWER_DIR_CHANGE) {
 		typec_set_pwr_role(con->port, role);
+		ucsi_port_psy_changed(con);
 
 		/* Complete pending power role swap */
 		if (!completion_done(&con->complete))
@@ -1330,7 +1331,7 @@ static int ucsi_reset_ppm(struct ucsi *ucsi)
 
 	mutex_lock(&ucsi->ppm_lock);
 
-	ret = ucsi->ops->read_cci(ucsi, &cci);
+	ret = ucsi->ops->poll_cci(ucsi, &cci);
 	if (ret < 0)
 		goto out;
 
@@ -1348,7 +1349,7 @@ static int ucsi_reset_ppm(struct ucsi *ucsi)
 
 		tmo = jiffies + msecs_to_jiffies(UCSI_TIMEOUT_MS);
 		do {
-			ret = ucsi->ops->read_cci(ucsi, &cci);
+			ret = ucsi->ops->poll_cci(ucsi, &cci);
 			if (ret < 0)
 				goto out;
 			if (cci & UCSI_CCI_COMMAND_COMPLETE)
@@ -1377,7 +1378,7 @@ static int ucsi_reset_ppm(struct ucsi *ucsi)
 		/* Give the PPM time to process a reset before reading CCI */
 		msleep(20);
 
-		ret = ucsi->ops->read_cci(ucsi, &cci);
+		ret = ucsi->ops->poll_cci(ucsi, &cci);
 		if (ret)
 			goto out;
 
@@ -1809,11 +1810,11 @@ static int ucsi_init(struct ucsi *ucsi)
 
 err_unregister:
 	for (con = connector; con->port; con++) {
+		if (con->wq)
+			destroy_workqueue(con->wq);
 		ucsi_unregister_partner(con);
 		ucsi_unregister_altmodes(con, UCSI_RECIPIENT_CON);
 		ucsi_unregister_port_psy(con);
-		if (con->wq)
-			destroy_workqueue(con->wq);
 
 		usb_power_delivery_unregister_capabilities(con->port_sink_caps);
 		con->port_sink_caps = NULL;
@@ -1904,6 +1905,40 @@ void ucsi_set_drvdata(struct ucsi *ucsi, void *data)
 EXPORT_SYMBOL_GPL(ucsi_set_drvdata);
 
 /**
+ * ucsi_con_mutex_lock - Acquire the connector mutex
+ * @con: The connector interface to lock
+ *
+ * Returns true on success, false if the connector is disconnected
+ */
+bool ucsi_con_mutex_lock(struct ucsi_connector *con)
+{
+	bool mutex_locked = false;
+	bool connected = true;
+
+	while (connected && !mutex_locked) {
+		mutex_locked = mutex_trylock(&con->lock) != 0;
+		connected = con->status.flags & UCSI_CONSTAT_CONNECTED;
+		if (connected && !mutex_locked)
+			msleep(20);
+	}
+
+	connected = connected && con->partner;
+	if (!connected && mutex_locked)
+		mutex_unlock(&con->lock);
+
+	return connected;
+}
+
+/**
+ * ucsi_con_mutex_unlock - Release the connector mutex
+ * @con: The connector interface to unlock
+ */
+void ucsi_con_mutex_unlock(struct ucsi_connector *con)
+{
+	mutex_unlock(&con->lock);
+}
+
+/**
  * ucsi_create - Allocate UCSI instance
  * @dev: Device interface to the PPM (Platform Policy Manager)
  * @ops: I/O routines
@@ -1913,8 +1948,8 @@ struct ucsi *ucsi_create(struct device *dev, const struct ucsi_operations *ops)
 	struct ucsi *ucsi;
 
 	if (!ops ||
-	    !ops->read_version || !ops->read_cci || !ops->read_message_in ||
-	    !ops->sync_control || !ops->async_control)
+	    !ops->read_version || !ops->read_cci || !ops->poll_cci ||
+	    !ops->read_message_in || !ops->sync_control || !ops->async_control)
 		return ERR_PTR(-EINVAL);
 
 	ucsi = kzalloc(sizeof(*ucsi), GFP_KERNEL);
@@ -1997,10 +2032,6 @@ void ucsi_unregister(struct ucsi *ucsi)
 
 	for (i = 0; i < ucsi->cap.num_connectors; i++) {
 		cancel_work_sync(&ucsi->connector[i].work);
-		ucsi_unregister_partner(&ucsi->connector[i]);
-		ucsi_unregister_altmodes(&ucsi->connector[i],
-					 UCSI_RECIPIENT_CON);
-		ucsi_unregister_port_psy(&ucsi->connector[i]);
 
 		if (ucsi->connector[i].wq) {
 			struct ucsi_work *uwork;
@@ -2016,6 +2047,11 @@ void ucsi_unregister(struct ucsi *ucsi)
 			destroy_workqueue(ucsi->connector[i].wq);
 		}
 
+		ucsi_unregister_partner(&ucsi->connector[i]);
+		ucsi_unregister_altmodes(&ucsi->connector[i],
+					 UCSI_RECIPIENT_CON);
+		ucsi_unregister_port_psy(&ucsi->connector[i]);
+
 		usb_power_delivery_unregister_capabilities(ucsi->connector[i].port_sink_caps);
 		ucsi->connector[i].port_sink_caps = NULL;
 		usb_power_delivery_unregister_capabilities(ucsi->connector[i].port_source_caps);
diff --git a/drivers/usb/typec/ucsi/ucsi.h b/drivers/usb/typec/ucsi/ucsi.h
index 1cf5aad4c23a..25cff9658966 100644
--- a/drivers/usb/typec/ucsi/ucsi.h
+++ b/drivers/usb/typec/ucsi/ucsi.h
@@ -60,6 +60,7 @@ struct dentry;
  * struct ucsi_operations - UCSI I/O operations
  * @read_version: Read implemented UCSI version
  * @read_cci: Read CCI register
+ * @poll_cci: Read CCI register while polling with notifications disabled
  * @read_message_in: Read message data from UCSI
  * @sync_control: Blocking control operation
  * @async_control: Non-blocking control operation
@@ -74,6 +75,7 @@ struct dentry;
 struct ucsi_operations {
 	int (*read_version)(struct ucsi *ucsi, u16 *version);
 	int (*read_cci)(struct ucsi *ucsi, u32 *cci);
+	int (*poll_cci)(struct ucsi *ucsi, u32 *cci);
 	int (*read_message_in)(struct ucsi *ucsi, void *val, size_t val_len);
 	int (*sync_control)(struct ucsi *ucsi, u64 command);
 	int (*async_control)(struct ucsi *ucsi, u64 command);
@@ -89,6 +91,8 @@ int ucsi_register(struct ucsi *ucsi);
 void ucsi_unregister(struct ucsi *ucsi);
 void *ucsi_get_drvdata(struct ucsi *ucsi);
 void ucsi_set_drvdata(struct ucsi *ucsi, void *data);
+bool ucsi_con_mutex_lock(struct ucsi_connector *con);
+void ucsi_con_mutex_unlock(struct ucsi_connector *con);
 
 void ucsi_connector_change(struct ucsi *ucsi, u8 num);
 
@@ -363,7 +367,7 @@ struct ucsi_debugfs_entry {
 		u64 low;
 		u64 high;
 	} response;
-	u32 status;
+	int status;
 	struct dentry *dentry;
 };
 
@@ -408,9 +412,10 @@ struct ucsi {
 #define UCSI_MAX_SVID		5
 #define UCSI_MAX_ALTMODES	(UCSI_MAX_SVID * 6)
 
-#define UCSI_TYPEC_VSAFE5V	5000
-#define UCSI_TYPEC_1_5_CURRENT	1500
-#define UCSI_TYPEC_3_0_CURRENT	3000
+#define UCSI_TYPEC_VSAFE5V		5000
+#define UCSI_TYPEC_DEFAULT_CURRENT	 100
+#define UCSI_TYPEC_1_5_CURRENT		1500
+#define UCSI_TYPEC_3_0_CURRENT		3000
 
 struct ucsi_connector {
 	int num;
diff --git a/drivers/usb/typec/ucsi/ucsi_acpi.c b/drivers/usb/typec/ucsi/ucsi_acpi.c
index accf15ff1306..8de2961718cd 100644
--- a/drivers/usb/typec/ucsi/ucsi_acpi.c
+++ b/drivers/usb/typec/ucsi/ucsi_acpi.c
@@ -59,19 +59,24 @@ static int ucsi_acpi_read_version(struct ucsi *ucsi, u16 *version)
 static int ucsi_acpi_read_cci(struct ucsi *ucsi, u32 *cci)
 {
 	struct ucsi_acpi *ua = ucsi_get_drvdata(ucsi);
-	int ret;
-
-	if (UCSI_COMMAND(ua->cmd) == UCSI_PPM_RESET) {
-		ret = ucsi_acpi_dsm(ua, UCSI_DSM_FUNC_READ);
-		if (ret)
-			return ret;
-	}
 
 	memcpy(cci, ua->base + UCSI_CCI, sizeof(*cci));
 
 	return 0;
 }
 
+static int ucsi_acpi_poll_cci(struct ucsi *ucsi, u32 *cci)
+{
+	struct ucsi_acpi *ua = ucsi_get_drvdata(ucsi);
+	int ret;
+
+	ret = ucsi_acpi_dsm(ua, UCSI_DSM_FUNC_READ);
+	if (ret)
+		return ret;
+
+	return ucsi_acpi_read_cci(ucsi, cci);
+}
+
 static int ucsi_acpi_read_message_in(struct ucsi *ucsi, void *val, size_t val_len)
 {
 	struct ucsi_acpi *ua = ucsi_get_drvdata(ucsi);
@@ -94,6 +99,7 @@ static int ucsi_acpi_async_control(struct ucsi *ucsi, u64 command)
 static const struct ucsi_operations ucsi_acpi_ops = {
 	.read_version = ucsi_acpi_read_version,
 	.read_cci = ucsi_acpi_read_cci,
+	.poll_cci = ucsi_acpi_poll_cci,
 	.read_message_in = ucsi_acpi_read_message_in,
 	.sync_control = ucsi_sync_control_common,
 	.async_control = ucsi_acpi_async_control
@@ -145,6 +151,7 @@ static int ucsi_gram_sync_control(struct ucsi *ucsi, u64 command)
 static const struct ucsi_operations ucsi_gram_ops = {
 	.read_version = ucsi_acpi_read_version,
 	.read_cci = ucsi_acpi_read_cci,
+	.poll_cci = ucsi_acpi_poll_cci,
 	.read_message_in = ucsi_gram_read_message_in,
 	.sync_control = ucsi_gram_sync_control,
 	.async_control = ucsi_acpi_async_control
diff --git a/drivers/usb/typec/ucsi/ucsi_ccg.c b/drivers/usb/typec/ucsi/ucsi_ccg.c
index 740171f24ef9..511dd1b224ae 100644
--- a/drivers/usb/typec/ucsi/ucsi_ccg.c
+++ b/drivers/usb/typec/ucsi/ucsi_ccg.c
@@ -664,6 +664,7 @@ err_put:
 static const struct ucsi_operations ucsi_ccg_ops = {
 	.read_version = ucsi_ccg_read_version,
 	.read_cci = ucsi_ccg_read_cci,
+	.poll_cci = ucsi_ccg_read_cci,
 	.read_message_in = ucsi_ccg_read_message_in,
 	.sync_control = ucsi_ccg_sync_control,
 	.async_control = ucsi_ccg_async_control,
@@ -1432,11 +1433,10 @@ static int ucsi_ccg_probe(struct i2c_client *client)
 			uc->fw_build = CCG_FW_BUILD_NVIDIA_TEGRA;
 		else if (!strcmp(fw_name, "nvidia,gpu"))
 			uc->fw_build = CCG_FW_BUILD_NVIDIA;
+		if (!uc->fw_build)
+			dev_err(uc->dev, "failed to get FW build information\n");
 	}
 
-	if (!uc->fw_build)
-		dev_err(uc->dev, "failed to get FW build information\n");
-
 	/* reset ccg device and initialize ucsi */
 	status = ucsi_ccg_init(uc);
 	if (status < 0) {
diff --git a/drivers/usb/typec/ucsi/ucsi_glink.c b/drivers/usb/typec/ucsi/ucsi_glink.c
index 9b6cb76e6328..75c0e54c37fa 100644
--- a/drivers/usb/typec/ucsi/ucsi_glink.c
+++ b/drivers/usb/typec/ucsi/ucsi_glink.c
@@ -201,6 +201,7 @@ static void pmic_glink_ucsi_connector_status(struct ucsi_connector *con)
 static const struct ucsi_operations pmic_glink_ucsi_ops = {
 	.read_version = pmic_glink_ucsi_read_version,
 	.read_cci = pmic_glink_ucsi_read_cci,
+	.poll_cci = pmic_glink_ucsi_read_cci,
 	.read_message_in = pmic_glink_ucsi_read_message_in,
 	.sync_control = ucsi_sync_control_common,
 	.async_control = pmic_glink_ucsi_async_control,
diff --git a/drivers/usb/typec/ucsi/ucsi_stm32g0.c b/drivers/usb/typec/ucsi/ucsi_stm32g0.c
index 6923fad31d79..57ef7d83a412 100644
--- a/drivers/usb/typec/ucsi/ucsi_stm32g0.c
+++ b/drivers/usb/typec/ucsi/ucsi_stm32g0.c
@@ -424,6 +424,7 @@ static irqreturn_t ucsi_stm32g0_irq_handler(int irq, void *data)
 static const struct ucsi_operations ucsi_stm32g0_ops = {
 	.read_version = ucsi_stm32g0_read_version,
 	.read_cci = ucsi_stm32g0_read_cci,
+	.poll_cci = ucsi_stm32g0_read_cci,
 	.read_message_in = ucsi_stm32g0_read_message_in,
 	.sync_control = ucsi_sync_control_common,
 	.async_control = ucsi_stm32g0_async_control,
diff --git a/drivers/usb/typec/ucsi/ucsi_yoga_c630.c b/drivers/usb/typec/ucsi/ucsi_yoga_c630.c
index f3a5e24ea84d..080b6369a88c 100644
--- a/drivers/usb/typec/ucsi/ucsi_yoga_c630.c
+++ b/drivers/usb/typec/ucsi/ucsi_yoga_c630.c
@@ -74,6 +74,7 @@ static int yoga_c630_ucsi_async_control(struct ucsi *ucsi, u64 command)
 const struct ucsi_operations yoga_c630_ucsi_ops = {
 	.read_version = yoga_c630_ucsi_read_version,
 	.read_cci = yoga_c630_ucsi_read_cci,
+	.poll_cci = yoga_c630_ucsi_read_cci,
 	.read_message_in = yoga_c630_ucsi_read_message_in,
 	.sync_control = ucsi_sync_control_common,
 	.async_control = yoga_c630_ucsi_async_control,
@@ -132,17 +133,30 @@ static int yoga_c630_ucsi_probe(struct auxiliary_device *adev,
 
 	ret = yoga_c630_ec_register_notify(ec, &uec->nb);
 	if (ret)
-		return ret;
+		goto err_destroy;
+
+	ret = ucsi_register(uec->ucsi);
+	if (ret)
+		goto err_unregister;
+
+	return 0;
 
-	return ucsi_register(uec->ucsi);
+err_unregister:
+	yoga_c630_ec_unregister_notify(uec->ec, &uec->nb);
+
+err_destroy:
+	ucsi_destroy(uec->ucsi);
+
+	return ret;
 }
 
 static void yoga_c630_ucsi_remove(struct auxiliary_device *adev)
 {
 	struct yoga_c630_ucsi *uec = auxiliary_get_drvdata(adev);
 
-	yoga_c630_ec_unregister_notify(uec->ec, &uec->nb);
 	ucsi_unregister(uec->ucsi);
+	yoga_c630_ec_unregister_notify(uec->ec, &uec->nb);
+	ucsi_destroy(uec->ucsi);
 }
 
 static const struct auxiliary_device_id yoga_c630_ucsi_id_table[] = {
diff --git a/drivers/vdpa/mlx5/core/mr.c b/drivers/vdpa/mlx5/core/mr.c
index 8455f08f5d40..c7a20278bc3c 100644
--- a/drivers/vdpa/mlx5/core/mr.c
+++ b/drivers/vdpa/mlx5/core/mr.c
@@ -190,9 +190,12 @@ again:
 			klm->bcount = cpu_to_be32(klm_bcount(dmr->end - dmr->start));
 			preve = dmr->end;
 		} else {
+			u64 bcount = min_t(u64, dmr->start - preve, MAX_KLM_SIZE);
+
 			klm->key = cpu_to_be32(mvdev->res.null_mkey);
-			klm->bcount = cpu_to_be32(klm_bcount(dmr->start - preve));
-			preve = dmr->start;
+			klm->bcount = cpu_to_be32(klm_bcount(bcount));
+			preve += bcount;
+
 			goto again;
 		}
 	}
@@ -905,6 +908,9 @@ void mlx5_vdpa_destroy_mr_resources(struct mlx5_vdpa_dev *mvdev)
 {
 	struct mlx5_vdpa_mr_resources *mres = &mvdev->mres;
 
+	if (!mres->wq_gc)
+		return;
+
 	atomic_set(&mres->shutdown, 1);
 
 	flush_delayed_work(&mres->gc_dwork_ent);
diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
index 5f581e71e201..2e0b8c5bec8d 100644
--- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
+++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
@@ -2491,7 +2491,7 @@ static void mlx5_vdpa_set_vq_num(struct vdpa_device *vdev, u16 idx, u32 num)
         }
 
 	mvq = &ndev->vqs[idx];
-	ndev->needs_teardown = num != mvq->num_ent;
+	ndev->needs_teardown |= num != mvq->num_ent;
 	mvq->num_ent = num;
 }
 
@@ -3432,15 +3432,17 @@ static void mlx5_vdpa_free(struct vdpa_device *vdev)
 
 	ndev = to_mlx5_vdpa_ndev(mvdev);
 
+	/* Functions called here should be able to work with
+	 * uninitialized resources.
+	 */
 	free_fixed_resources(ndev);
 	mlx5_vdpa_clean_mrs(mvdev);
 	mlx5_vdpa_destroy_mr_resources(&ndev->mvdev);
-	mlx5_cmd_cleanup_async_ctx(&mvdev->async_ctx);
-
 	if (!is_zero_ether_addr(ndev->config.mac)) {
 		pfmdev = pci_get_drvdata(pci_physfn(mvdev->mdev->pdev));
 		mlx5_mpfs_del_mac(pfmdev, ndev->config.mac);
 	}
+	mlx5_cmd_cleanup_async_ctx(&mvdev->async_ctx);
 	mlx5_vdpa_free_resources(&ndev->mvdev);
 	free_irqs(ndev);
 	kfree(ndev->event_cbs);
@@ -3884,6 +3886,11 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name,
 	ndev->mvdev.max_vqs = max_vqs;
 	mvdev = &ndev->mvdev;
 	mvdev->mdev = mdev;
+	/* cpu_to_mlx5vdpa16() below depends on this flag */
+	mvdev->actual_features =
+			(device_features & BIT_ULL(VIRTIO_F_VERSION_1));
+
+	mlx5_cmd_init_async_ctx(mdev, &mvdev->async_ctx);
 
 	ndev->vqs = kcalloc(max_vqs, sizeof(*ndev->vqs), GFP_KERNEL);
 	ndev->event_cbs = kcalloc(max_vqs + 1, sizeof(*ndev->event_cbs), GFP_KERNEL);
@@ -3957,8 +3964,6 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name,
 		ndev->rqt_size = 1;
 	}
 
-	mlx5_cmd_init_async_ctx(mdev, &mvdev->async_ctx);
-
 	ndev->mvdev.mlx_features = device_features;
 	mvdev->vdev.dma_dev = &mdev->pdev->dev;
 	err = mlx5_vdpa_alloc_resources(&ndev->mvdev);
diff --git a/drivers/vdpa/vdpa_user/vduse_dev.c b/drivers/vdpa/vdpa_user/vduse_dev.c
index 7ae99691efdf..7f569ce8fc7b 100644
--- a/drivers/vdpa/vdpa_user/vduse_dev.c
+++ b/drivers/vdpa/vdpa_user/vduse_dev.c
@@ -2215,6 +2215,7 @@ static void vduse_exit(void)
 	cdev_del(&vduse_ctrl_cdev);
 	unregister_chrdev_region(vduse_major, VDUSE_DEV_MAX);
 	class_unregister(&vduse_class);
+	idr_destroy(&vduse_idr);
 }
 module_exit(vduse_exit);
 
diff --git a/drivers/vfio/group.c b/drivers/vfio/group.c
index 95b336de8a17..5f2b2c950bbc 100644
--- a/drivers/vfio/group.c
+++ b/drivers/vfio/group.c
@@ -194,11 +194,10 @@ static int vfio_df_group_open(struct vfio_device_file *df)
 		 * implies they expected translation to exist
 		 */
 		if (!capable(CAP_SYS_RAWIO) ||
-		    vfio_iommufd_device_has_compat_ioas(device, df->iommufd))
+		    vfio_iommufd_device_has_compat_ioas(device, df->iommufd)) {
 			ret = -EPERM;
-		else
-			ret = 0;
-		goto out_put_kvm;
+			goto out_put_kvm;
+		}
 	}
 
 	ret = vfio_df_open(df);
diff --git a/drivers/vfio/iommufd.c b/drivers/vfio/iommufd.c
index 82eba6966fa5..02852899c2ae 100644
--- a/drivers/vfio/iommufd.c
+++ b/drivers/vfio/iommufd.c
@@ -25,6 +25,10 @@ int vfio_df_iommufd_bind(struct vfio_device_file *df)
 
 	lockdep_assert_held(&vdev->dev_set->lock);
 
+	/* Returns 0 to permit device opening under noiommu mode */
+	if (vfio_device_is_noiommu(vdev))
+		return 0;
+
 	return vdev->ops->bind_iommufd(vdev, ictx, &df->devid);
 }
 
diff --git a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
index 0d632ba5d2a3..dda8cb3262e0 100644
--- a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
+++ b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
@@ -350,6 +350,32 @@ static int vf_qm_func_stop(struct hisi_qm *qm)
 	return hisi_qm_mb(qm, QM_MB_CMD_PAUSE_QM, 0, 0, 0);
 }
 
+static int vf_qm_version_check(struct acc_vf_data *vf_data, struct device *dev)
+{
+	switch (vf_data->acc_magic) {
+	case ACC_DEV_MAGIC_V2:
+		if (vf_data->major_ver != ACC_DRV_MAJOR_VER) {
+			dev_info(dev, "migration driver version<%u.%u> not match!\n",
+				 vf_data->major_ver, vf_data->minor_ver);
+			return -EINVAL;
+		}
+		break;
+	case ACC_DEV_MAGIC_V1:
+		/* Correct dma address */
+		vf_data->eqe_dma = vf_data->qm_eqc_dw[QM_XQC_ADDR_HIGH];
+		vf_data->eqe_dma <<= QM_XQC_ADDR_OFFSET;
+		vf_data->eqe_dma |= vf_data->qm_eqc_dw[QM_XQC_ADDR_LOW];
+		vf_data->aeqe_dma = vf_data->qm_aeqc_dw[QM_XQC_ADDR_HIGH];
+		vf_data->aeqe_dma <<= QM_XQC_ADDR_OFFSET;
+		vf_data->aeqe_dma |= vf_data->qm_aeqc_dw[QM_XQC_ADDR_LOW];
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static int vf_qm_check_match(struct hisi_acc_vf_core_device *hisi_acc_vdev,
 			     struct hisi_acc_vf_migration_file *migf)
 {
@@ -363,7 +389,8 @@ static int vf_qm_check_match(struct hisi_acc_vf_core_device *hisi_acc_vdev,
 	if (migf->total_length < QM_MATCH_SIZE || hisi_acc_vdev->match_done)
 		return 0;
 
-	if (vf_data->acc_magic != ACC_DEV_MAGIC) {
+	ret = vf_qm_version_check(vf_data, dev);
+	if (ret) {
 		dev_err(dev, "failed to match ACC_DEV_MAGIC\n");
 		return -EINVAL;
 	}
@@ -399,13 +426,6 @@ static int vf_qm_check_match(struct hisi_acc_vf_core_device *hisi_acc_vdev,
 		return -EINVAL;
 	}
 
-	ret = qm_write_regs(vf_qm, QM_VF_STATE, &vf_data->vf_qm_state, 1);
-	if (ret) {
-		dev_err(dev, "failed to write QM_VF_STATE\n");
-		return ret;
-	}
-
-	hisi_acc_vdev->vf_qm_state = vf_data->vf_qm_state;
 	hisi_acc_vdev->match_done = true;
 	return 0;
 }
@@ -418,7 +438,9 @@ static int vf_qm_get_match_data(struct hisi_acc_vf_core_device *hisi_acc_vdev,
 	int vf_id = hisi_acc_vdev->vf_id;
 	int ret;
 
-	vf_data->acc_magic = ACC_DEV_MAGIC;
+	vf_data->acc_magic = ACC_DEV_MAGIC_V2;
+	vf_data->major_ver = ACC_DRV_MAJOR_VER;
+	vf_data->minor_ver = ACC_DRV_MINOR_VER;
 	/* Save device id */
 	vf_data->dev_id = hisi_acc_vdev->vf_dev->device;
 
@@ -441,6 +463,19 @@ static int vf_qm_get_match_data(struct hisi_acc_vf_core_device *hisi_acc_vdev,
 	return 0;
 }
 
+static void vf_qm_xeqc_save(struct hisi_qm *qm,
+			    struct hisi_acc_vf_migration_file *migf)
+{
+	struct acc_vf_data *vf_data = &migf->vf_data;
+	u16 eq_head, aeq_head;
+
+	eq_head = vf_data->qm_eqc_dw[0] & 0xFFFF;
+	qm_db(qm, 0, QM_DOORBELL_CMD_EQ, eq_head, 0);
+
+	aeq_head = vf_data->qm_aeqc_dw[0] & 0xFFFF;
+	qm_db(qm, 0, QM_DOORBELL_CMD_AEQ, aeq_head, 0);
+}
+
 static int vf_qm_load_data(struct hisi_acc_vf_core_device *hisi_acc_vdev,
 			   struct hisi_acc_vf_migration_file *migf)
 {
@@ -456,6 +491,20 @@ static int vf_qm_load_data(struct hisi_acc_vf_core_device *hisi_acc_vdev,
 	if (migf->total_length < sizeof(struct acc_vf_data))
 		return -EINVAL;
 
+	if (!vf_data->eqe_dma || !vf_data->aeqe_dma ||
+	    !vf_data->sqc_dma || !vf_data->cqc_dma) {
+		dev_info(dev, "resume dma addr is NULL!\n");
+		hisi_acc_vdev->vf_qm_state = QM_NOT_READY;
+		return 0;
+	}
+
+	ret = qm_write_regs(qm, QM_VF_STATE, &vf_data->vf_qm_state, 1);
+	if (ret) {
+		dev_err(dev, "failed to write QM_VF_STATE\n");
+		return -EINVAL;
+	}
+	hisi_acc_vdev->vf_qm_state = vf_data->vf_qm_state;
+
 	qm->eqe_dma = vf_data->eqe_dma;
 	qm->aeqe_dma = vf_data->aeqe_dma;
 	qm->sqc_dma = vf_data->sqc_dma;
@@ -505,23 +554,17 @@ static int vf_qm_state_save(struct hisi_acc_vf_core_device *hisi_acc_vdev,
 	vf_data->vf_qm_state = QM_READY;
 	hisi_acc_vdev->vf_qm_state = vf_data->vf_qm_state;
 
-	ret = vf_qm_cache_wb(vf_qm);
-	if (ret) {
-		dev_err(dev, "failed to writeback QM Cache!\n");
-		return ret;
-	}
-
 	ret = qm_get_regs(vf_qm, vf_data);
 	if (ret)
 		return -EINVAL;
 
 	/* Every reg is 32 bit, the dma address is 64 bit. */
-	vf_data->eqe_dma = vf_data->qm_eqc_dw[1];
+	vf_data->eqe_dma = vf_data->qm_eqc_dw[QM_XQC_ADDR_HIGH];
 	vf_data->eqe_dma <<= QM_XQC_ADDR_OFFSET;
-	vf_data->eqe_dma |= vf_data->qm_eqc_dw[0];
-	vf_data->aeqe_dma = vf_data->qm_aeqc_dw[1];
+	vf_data->eqe_dma |= vf_data->qm_eqc_dw[QM_XQC_ADDR_LOW];
+	vf_data->aeqe_dma = vf_data->qm_aeqc_dw[QM_XQC_ADDR_HIGH];
 	vf_data->aeqe_dma <<= QM_XQC_ADDR_OFFSET;
-	vf_data->aeqe_dma |= vf_data->qm_aeqc_dw[0];
+	vf_data->aeqe_dma |= vf_data->qm_aeqc_dw[QM_XQC_ADDR_LOW];
 
 	/* Through SQC_BT/CQC_BT to get sqc and cqc address */
 	ret = qm_get_sqc(vf_qm, &vf_data->sqc_dma);
@@ -537,6 +580,9 @@ static int vf_qm_state_save(struct hisi_acc_vf_core_device *hisi_acc_vdev,
 	}
 
 	migf->total_length = sizeof(struct acc_vf_data);
+	/* Save eqc and aeqc interrupt information */
+	vf_qm_xeqc_save(vf_qm, migf);
+
 	return 0;
 }
 
@@ -933,6 +979,13 @@ static int hisi_acc_vf_stop_device(struct hisi_acc_vf_core_device *hisi_acc_vdev
 		dev_err(dev, "failed to check QM INT state!\n");
 		return ret;
 	}
+
+	ret = vf_qm_cache_wb(vf_qm);
+	if (ret) {
+		dev_err(dev, "failed to writeback QM cache!\n");
+		return ret;
+	}
+
 	return 0;
 }
 
@@ -1306,6 +1359,7 @@ static void hisi_acc_vfio_pci_close_device(struct vfio_device *core_vdev)
 			struct hisi_acc_vf_core_device, core_device.vdev);
 	struct hisi_qm *vf_qm = &hisi_acc_vdev->vf_qm;
 
+	hisi_acc_vf_disable_fds(hisi_acc_vdev);
 	iounmap(vf_qm->io_base);
 	vfio_pci_core_close_device(core_vdev);
 }
@@ -1326,6 +1380,7 @@ static int hisi_acc_vfio_pci_migrn_init_dev(struct vfio_device *core_vdev)
 	hisi_acc_vdev->vf_id = pci_iov_vf_id(pdev) + 1;
 	hisi_acc_vdev->pf_qm = pf_qm;
 	hisi_acc_vdev->vf_dev = pdev;
+	hisi_acc_vdev->vf_qm_state = QM_NOT_READY;
 	mutex_init(&hisi_acc_vdev->state_mutex);
 
 	core_vdev->migration_flags = VFIO_MIGRATION_STOP_COPY | VFIO_MIGRATION_PRE_COPY;
diff --git a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.h b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.h
index 5bab46602fad..465284168906 100644
--- a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.h
+++ b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.h
@@ -38,6 +38,9 @@
 #define QM_REG_ADDR_OFFSET	0x0004
 
 #define QM_XQC_ADDR_OFFSET	32U
+#define QM_XQC_ADDR_LOW	0x1
+#define QM_XQC_ADDR_HIGH	0x2
+
 #define QM_VF_AEQ_INT_MASK	0x0004
 #define QM_VF_EQ_INT_MASK	0x000c
 #define QM_IFC_INT_SOURCE_V	0x0020
@@ -49,10 +52,15 @@
 #define QM_EQC_DW0		0X8000
 #define QM_AEQC_DW0		0X8020
 
+#define ACC_DRV_MAJOR_VER 1
+#define ACC_DRV_MINOR_VER 0
+
+#define ACC_DEV_MAGIC_V1	0XCDCDCDCDFEEDAACC
+#define ACC_DEV_MAGIC_V2	0xAACCFEEDDECADEDE
+
 struct acc_vf_data {
 #define QM_MATCH_SIZE offsetofend(struct acc_vf_data, qm_rsv_state)
 	/* QM match information */
-#define ACC_DEV_MAGIC	0XCDCDCDCDFEEDAACC
 	u64 acc_magic;
 	u32 qp_num;
 	u32 dev_id;
@@ -60,7 +68,9 @@ struct acc_vf_data {
 	u32 qp_base;
 	u32 vf_qm_state;
 	/* QM reserved match information */
-	u32 qm_rsv_state[3];
+	u16 major_ver;
+	u16 minor_ver;
+	u32 qm_rsv_state[2];
 
 	/* QM RW regs */
 	u32 aeq_int_mask;
diff --git a/drivers/vfio/pci/mlx5/cmd.c b/drivers/vfio/pci/mlx5/cmd.c
index eb7387ee6ebd..e7d2251db626 100644
--- a/drivers/vfio/pci/mlx5/cmd.c
+++ b/drivers/vfio/pci/mlx5/cmd.c
@@ -1538,8 +1538,8 @@ int mlx5vf_start_page_tracker(struct vfio_device *vdev,
 	log_max_msg_size = MLX5_CAP_ADV_VIRTUALIZATION(mdev, pg_track_log_max_msg_size);
 	max_msg_size = (1ULL << log_max_msg_size);
 	/* The RQ must hold at least 4 WQEs/messages for successful QP creation */
-	if (rq_size < 4 * max_msg_size)
-		rq_size = 4 * max_msg_size;
+	if (rq_size < 4ULL * max_msg_size)
+		rq_size = 4ULL * max_msg_size;
 
 	memset(tracker, 0, sizeof(*tracker));
 	tracker->uar = mlx5_get_uars_page(mdev);
diff --git a/drivers/vfio/pci/nvgrace-gpu/main.c b/drivers/vfio/pci/nvgrace-gpu/main.c
index a7fd018aa548..9e1c57baab64 100644
--- a/drivers/vfio/pci/nvgrace-gpu/main.c
+++ b/drivers/vfio/pci/nvgrace-gpu/main.c
@@ -17,12 +17,14 @@
 #define RESMEM_REGION_INDEX VFIO_PCI_BAR2_REGION_INDEX
 #define USEMEM_REGION_INDEX VFIO_PCI_BAR4_REGION_INDEX
 
-/* Memory size expected as non cached and reserved by the VM driver */
-#define RESMEM_SIZE SZ_1G
-
 /* A hardwired and constant ABI value between the GPU FW and VFIO driver. */
 #define MEMBLK_SIZE SZ_512M
 
+#define DVSEC_BITMAP_OFFSET 0xA
+#define MIG_SUPPORTED_WITH_CACHED_RESMEM BIT(0)
+
+#define GPU_CAP_DVSEC_REGISTER 3
+
 /*
  * The state of the two device memory region - resmem and usemem - is
  * saved as struct mem_region.
@@ -46,6 +48,7 @@ struct nvgrace_gpu_pci_core_device {
 	struct mem_region resmem;
 	/* Lock to control device memory kernel mapping */
 	struct mutex remap_lock;
+	bool has_mig_hw_bug;
 };
 
 static void nvgrace_gpu_init_fake_bar_emu_regs(struct vfio_device *core_vdev)
@@ -66,7 +69,7 @@ nvgrace_gpu_memregion(int index,
 	if (index == USEMEM_REGION_INDEX)
 		return &nvdev->usemem;
 
-	if (index == RESMEM_REGION_INDEX)
+	if (nvdev->resmem.memlength && index == RESMEM_REGION_INDEX)
 		return &nvdev->resmem;
 
 	return NULL;
@@ -751,40 +754,67 @@ nvgrace_gpu_init_nvdev_struct(struct pci_dev *pdev,
 			      u64 memphys, u64 memlength)
 {
 	int ret = 0;
+	u64 resmem_size = 0;
 
 	/*
-	 * The VM GPU device driver needs a non-cacheable region to support
-	 * the MIG feature. Since the device memory is mapped as NORMAL cached,
-	 * carve out a region from the end with a different NORMAL_NC
-	 * property (called as reserved memory and represented as resmem). This
-	 * region then is exposed as a 64b BAR (region 2 and 3) to the VM, while
-	 * exposing the rest (termed as usable memory and represented using usemem)
-	 * as cacheable 64b BAR (region 4 and 5).
+	 * On Grace Hopper systems, the VM GPU device driver needs a non-cacheable
+	 * region to support the MIG feature owing to a hardware bug. Since the
+	 * device memory is mapped as NORMAL cached, carve out a region from the end
+	 * with a different NORMAL_NC property (called as reserved memory and
+	 * represented as resmem). This region then is exposed as a 64b BAR
+	 * (region 2 and 3) to the VM, while exposing the rest (termed as usable
+	 * memory and represented using usemem) as cacheable 64b BAR (region 4 and 5).
 	 *
 	 *               devmem (memlength)
 	 * |-------------------------------------------------|
 	 * |                                           |
 	 * usemem.memphys                              resmem.memphys
+	 *
+	 * This hardware bug is fixed on the Grace Blackwell platforms and the
+	 * presence of the bug can be determined through nvdev->has_mig_hw_bug.
+	 * Thus on systems with the hardware fix, there is no need to partition
+	 * the GPU device memory and the entire memory is usable and mapped as
+	 * NORMAL cached (i.e. resmem size is 0).
 	 */
+	if (nvdev->has_mig_hw_bug)
+		resmem_size = SZ_1G;
+
 	nvdev->usemem.memphys = memphys;
 
 	/*
 	 * The device memory exposed to the VM is added to the kernel by the
-	 * VM driver module in chunks of memory block size. Only the usable
-	 * memory (usemem) is added to the kernel for usage by the VM
-	 * workloads. Make the usable memory size memblock aligned.
+	 * VM driver module in chunks of memory block size. Note that only the
+	 * usable memory (usemem) is added to the kernel for usage by the VM
+	 * workloads.
 	 */
-	if (check_sub_overflow(memlength, RESMEM_SIZE,
+	if (check_sub_overflow(memlength, resmem_size,
 			       &nvdev->usemem.memlength)) {
 		ret = -EOVERFLOW;
 		goto done;
 	}
 
 	/*
-	 * The USEMEM part of the device memory has to be MEMBLK_SIZE
-	 * aligned. This is a hardwired ABI value between the GPU FW and
-	 * VFIO driver. The VM device driver is also aware of it and make
-	 * use of the value for its calculation to determine USEMEM size.
+	 * The usemem region is exposed as a 64B Bar composed of region 4 and 5.
+	 * Calculate and save the BAR size for the region.
+	 */
+	nvdev->usemem.bar_size = roundup_pow_of_two(nvdev->usemem.memlength);
+
+	/*
+	 * If the hardware has the fix for MIG, there is no requirement
+	 * for splitting the device memory to create RESMEM. The entire
+	 * device memory is usable and will be USEMEM. Return here for
+	 * such case.
+	 */
+	if (!nvdev->has_mig_hw_bug)
+		goto done;
+
+	/*
+	 * When the device memory is split to workaround the MIG bug on
+	 * Grace Hopper, the USEMEM part of the device memory has to be
+	 * MEMBLK_SIZE aligned. This is a hardwired ABI value between the
+	 * GPU FW and VFIO driver. The VM device driver is also aware of it
+	 * and make use of the value for its calculation to determine USEMEM
+	 * size. Note that the device memory may not be 512M aligned.
 	 */
 	nvdev->usemem.memlength = round_down(nvdev->usemem.memlength,
 					     MEMBLK_SIZE);
@@ -803,15 +833,34 @@ nvgrace_gpu_init_nvdev_struct(struct pci_dev *pdev,
 	}
 
 	/*
-	 * The memory regions are exposed as BARs. Calculate and save
-	 * the BAR size for them.
+	 * The resmem region is exposed as a 64b BAR composed of region 2 and 3
+	 * for Grace Hopper. Calculate and save the BAR size for the region.
 	 */
-	nvdev->usemem.bar_size = roundup_pow_of_two(nvdev->usemem.memlength);
 	nvdev->resmem.bar_size = roundup_pow_of_two(nvdev->resmem.memlength);
 done:
 	return ret;
 }
 
+static bool nvgrace_gpu_has_mig_hw_bug(struct pci_dev *pdev)
+{
+	int pcie_dvsec;
+	u16 dvsec_ctrl16;
+
+	pcie_dvsec = pci_find_dvsec_capability(pdev, PCI_VENDOR_ID_NVIDIA,
+					       GPU_CAP_DVSEC_REGISTER);
+
+	if (pcie_dvsec) {
+		pci_read_config_word(pdev,
+				     pcie_dvsec + DVSEC_BITMAP_OFFSET,
+				     &dvsec_ctrl16);
+
+		if (dvsec_ctrl16 & MIG_SUPPORTED_WITH_CACHED_RESMEM)
+			return false;
+	}
+
+	return true;
+}
+
 static int nvgrace_gpu_probe(struct pci_dev *pdev,
 			     const struct pci_device_id *id)
 {
@@ -832,6 +881,8 @@ static int nvgrace_gpu_probe(struct pci_dev *pdev,
 	dev_set_drvdata(&pdev->dev, &nvdev->core_device);
 
 	if (ops == &nvgrace_gpu_pci_ops) {
+		nvdev->has_mig_hw_bug = nvgrace_gpu_has_mig_hw_bug(pdev);
+
 		/*
 		 * Device memory properties are identified in the host ACPI
 		 * table. Set the nvgrace_gpu_pci_core_device structure.
diff --git a/drivers/vfio/pci/pds/vfio_dev.c b/drivers/vfio/pci/pds/vfio_dev.c
index 76a80ae7087b..f6e0253a8a14 100644
--- a/drivers/vfio/pci/pds/vfio_dev.c
+++ b/drivers/vfio/pci/pds/vfio_dev.c
@@ -204,6 +204,7 @@ static const struct vfio_device_ops pds_vfio_ops = {
 	.bind_iommufd = vfio_iommufd_physical_bind,
 	.unbind_iommufd = vfio_iommufd_physical_unbind,
 	.attach_ioas = vfio_iommufd_physical_attach_ioas,
+	.detach_ioas = vfio_iommufd_physical_detach_ioas,
 };
 
 const struct vfio_device_ops *pds_vfio_ops_info(void)
diff --git a/drivers/vfio/pci/vfio_pci_config.c b/drivers/vfio/pci/vfio_pci_config.c
index ea2745c1ac5e..8ea38e7421df 100644
--- a/drivers/vfio/pci/vfio_pci_config.c
+++ b/drivers/vfio/pci/vfio_pci_config.c
@@ -1813,7 +1813,8 @@ int vfio_config_init(struct vfio_pci_core_device *vdev)
 					cpu_to_le16(PCI_COMMAND_MEMORY);
 	}
 
-	if (!IS_ENABLED(CONFIG_VFIO_PCI_INTX) || vdev->nointx)
+	if (!IS_ENABLED(CONFIG_VFIO_PCI_INTX) || vdev->nointx ||
+	    vdev->pdev->irq == IRQ_NOTCONNECTED)
 		vconfig[PCI_INTERRUPT_PIN] = 0;
 
 	ret = vfio_cap_init(vdev);
diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c
index 1a4ed5a357d3..595503fa9ca8 100644
--- a/drivers/vfio/pci/vfio_pci_core.c
+++ b/drivers/vfio/pci/vfio_pci_core.c
@@ -727,15 +727,7 @@ EXPORT_SYMBOL_GPL(vfio_pci_core_finish_enable);
 static int vfio_pci_get_irq_count(struct vfio_pci_core_device *vdev, int irq_type)
 {
 	if (irq_type == VFIO_PCI_INTX_IRQ_INDEX) {
-		u8 pin;
-
-		if (!IS_ENABLED(CONFIG_VFIO_PCI_INTX) ||
-		    vdev->nointx || vdev->pdev->is_virtfn)
-			return 0;
-
-		pci_read_config_byte(vdev->pdev, PCI_INTERRUPT_PIN, &pin);
-
-		return pin ? 1 : 0;
+		return vdev->vconfig[PCI_INTERRUPT_PIN] ? 1 : 0;
 	} else if (irq_type == VFIO_PCI_MSI_IRQ_INDEX) {
 		u8 pos;
 		u16 flags;
@@ -1658,14 +1650,14 @@ static vm_fault_t vfio_pci_mmap_huge_fault(struct vm_fault *vmf,
 {
 	struct vm_area_struct *vma = vmf->vma;
 	struct vfio_pci_core_device *vdev = vma->vm_private_data;
-	unsigned long pfn, pgoff = vmf->pgoff - vma->vm_pgoff;
+	unsigned long addr = vmf->address & ~((PAGE_SIZE << order) - 1);
+	unsigned long pgoff = (addr - vma->vm_start) >> PAGE_SHIFT;
+	unsigned long pfn = vma_to_pfn(vma) + pgoff;
 	vm_fault_t ret = VM_FAULT_SIGBUS;
 
-	pfn = vma_to_pfn(vma) + pgoff;
-
-	if (order && (pfn & ((1 << order) - 1) ||
-		      vmf->address & ((PAGE_SIZE << order) - 1) ||
-		      vmf->address + (PAGE_SIZE << order) > vma->vm_end)) {
+	if (order && (addr < vma->vm_start ||
+		      addr + (PAGE_SIZE << order) > vma->vm_end ||
+		      pfn & ((1 << order) - 1))) {
 		ret = VM_FAULT_FALLBACK;
 		goto out;
 	}
@@ -2161,7 +2153,7 @@ int vfio_pci_core_register_device(struct vfio_pci_core_device *vdev)
 		return -EBUSY;
 	}
 
-	if (pci_is_root_bus(pdev->bus)) {
+	if (pci_is_root_bus(pdev->bus) || pdev->is_virtfn) {
 		ret = vfio_assign_device_set(&vdev->vdev, vdev);
 	} else if (!pci_probe_reset_slot(pdev->slot)) {
 		ret = vfio_assign_device_set(&vdev->vdev, pdev->slot);
diff --git a/drivers/vfio/pci/vfio_pci_intrs.c b/drivers/vfio/pci/vfio_pci_intrs.c
index 8382c5834335..565966351dfa 100644
--- a/drivers/vfio/pci/vfio_pci_intrs.c
+++ b/drivers/vfio/pci/vfio_pci_intrs.c
@@ -259,7 +259,7 @@ static int vfio_intx_enable(struct vfio_pci_core_device *vdev,
 	if (!is_irq_none(vdev))
 		return -EINVAL;
 
-	if (!pdev->irq)
+	if (!pdev->irq || pdev->irq == IRQ_NOTCONNECTED)
 		return -ENODEV;
 
 	name = kasprintf(GFP_KERNEL_ACCOUNT, "vfio-intx(%s)", pci_name(pdev));
diff --git a/drivers/vfio/pci/vfio_pci_rdwr.c b/drivers/vfio/pci/vfio_pci_rdwr.c
index 66b72c289284..a0595c745732 100644
--- a/drivers/vfio/pci/vfio_pci_rdwr.c
+++ b/drivers/vfio/pci/vfio_pci_rdwr.c
@@ -16,6 +16,7 @@
 #include <linux/io.h>
 #include <linux/vfio.h>
 #include <linux/vgaarb.h>
+#include <linux/io-64-nonatomic-lo-hi.h>
 
 #include "vfio_pci_priv.h"
 
diff --git a/drivers/vfio/platform/vfio_platform_common.c b/drivers/vfio/platform/vfio_platform_common.c
index e53757d1d095..3bf1043cd795 100644
--- a/drivers/vfio/platform/vfio_platform_common.c
+++ b/drivers/vfio/platform/vfio_platform_common.c
@@ -388,6 +388,11 @@ static ssize_t vfio_platform_read_mmio(struct vfio_platform_region *reg,
 {
 	unsigned int done = 0;
 
+	if (off >= reg->size)
+		return -EINVAL;
+
+	count = min_t(size_t, count, reg->size - off);
+
 	if (!reg->ioaddr) {
 		reg->ioaddr =
 			ioremap(reg->addr, reg->size);
@@ -467,6 +472,11 @@ static ssize_t vfio_platform_write_mmio(struct vfio_platform_region *reg,
 {
 	unsigned int done = 0;
 
+	if (off >= reg->size)
+		return -EINVAL;
+
+	count = min_t(size_t, count, reg->size - off);
+
 	if (!reg->ioaddr) {
 		reg->ioaddr =
 			ioremap(reg->addr, reg->size);
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index bf391b40e576..124997ce00d6 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -294,7 +294,7 @@ static int vfio_dma_bitmap_alloc_all(struct vfio_iommu *iommu, size_t pgsize)
 			struct rb_node *p;
 
 			for (p = rb_prev(n); p; p = rb_prev(p)) {
-				struct vfio_dma *dma = rb_entry(n,
+				struct vfio_dma *dma = rb_entry(p,
 							struct vfio_dma, node);
 
 				vfio_dma_bitmap_free(dma);
@@ -619,6 +619,13 @@ static long vfio_pin_pages_remote(struct vfio_dma *dma, unsigned long vaddr,
 
 	while (npage) {
 		if (!batch->size) {
+			/*
+			 * Large mappings may take a while to repeatedly refill
+			 * the batch, so conditionally relinquish the CPU when
+			 * needed to avoid stalls.
+			 */
+			cond_resched();
+
 			/* Empty batch, so refill it. */
 			long req_pages = min_t(long, npage, batch->capacity);
 
diff --git a/drivers/vfio/vfio_main.c b/drivers/vfio/vfio_main.c
index a5a62d9d963f..ae78822f2d71 100644
--- a/drivers/vfio/vfio_main.c
+++ b/drivers/vfio/vfio_main.c
@@ -583,7 +583,8 @@ void vfio_df_close(struct vfio_device_file *df)
 
 	lockdep_assert_held(&device->dev_set->lock);
 
-	vfio_assert_device_open(device);
+	if (!vfio_assert_device_open(device))
+		return;
 	if (device->open_count == 1)
 		vfio_df_device_last_close(df);
 	device->open_count--;
diff --git a/drivers/vhost/Kconfig b/drivers/vhost/Kconfig
index b455d9ab6f3d..a4730217bfb6 100644
--- a/drivers/vhost/Kconfig
+++ b/drivers/vhost/Kconfig
@@ -94,4 +94,22 @@ config VHOST_CROSS_ENDIAN_LEGACY
 
 	  If unsure, say "N".
 
+config VHOST_ENABLE_FORK_OWNER_CONTROL
+	bool "Enable VHOST_ENABLE_FORK_OWNER_CONTROL"
+	default y
+	help
+	  This option enables two IOCTLs: VHOST_SET_FORK_FROM_OWNER and
+	  VHOST_GET_FORK_FROM_OWNER. These allow userspace applications
+	  to modify the vhost worker mode for vhost devices.
+
+	  Also expose module parameter 'fork_from_owner_default' to allow users
+	  to configure the default mode for vhost workers.
+
+	  By default, `VHOST_ENABLE_FORK_OWNER_CONTROL` is set to `y`,
+	  users can change the worker thread mode as needed.
+	  If this config is disabled (n),the related IOCTLs and parameters will
+	  be unavailable.
+
+	  If unsure, say "Y".
+
 endif
diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index 718fa4e0b31e..88f213d1106f 100644
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -571,6 +571,9 @@ static void vhost_scsi_complete_cmd_work(struct vhost_work *work)
 	int ret;
 
 	llnode = llist_del_all(&svq->completion_list);
+
+	mutex_lock(&svq->vq.mutex);
+
 	llist_for_each_entry_safe(cmd, t, llnode, tvc_completion_list) {
 		se_cmd = &cmd->tvc_se_cmd;
 
@@ -604,6 +607,8 @@ static void vhost_scsi_complete_cmd_work(struct vhost_work *work)
 		vhost_scsi_release_cmd_res(se_cmd);
 	}
 
+	mutex_unlock(&svq->vq.mutex);
+
 	if (signal)
 		vhost_signal(&svq->vs->dev, &svq->vq);
 }
@@ -630,7 +635,7 @@ vhost_scsi_get_cmd(struct vhost_virtqueue *vq, struct vhost_scsi_tpg *tpg,
 
 	tag = sbitmap_get(&svq->scsi_tags);
 	if (tag < 0) {
-		pr_err("Unable to obtain tag for vhost_scsi_cmd\n");
+		pr_warn_once("Guest sent too many cmds. Returning TASK_SET_FULL.\n");
 		return ERR_PTR(-ENOMEM);
 	}
 
@@ -757,7 +762,7 @@ vhost_scsi_copy_iov_to_sgl(struct vhost_scsi_cmd *cmd, struct iov_iter *iter,
 	size_t len = iov_iter_count(iter);
 	unsigned int nbytes = 0;
 	struct page *page;
-	int i;
+	int i, ret;
 
 	if (cmd->tvc_data_direction == DMA_FROM_DEVICE) {
 		cmd->saved_iter_addr = dup_iter(&cmd->saved_iter, iter,
@@ -770,6 +775,7 @@ vhost_scsi_copy_iov_to_sgl(struct vhost_scsi_cmd *cmd, struct iov_iter *iter,
 		page = alloc_page(GFP_KERNEL);
 		if (!page) {
 			i--;
+			ret = -ENOMEM;
 			goto err;
 		}
 
@@ -777,8 +783,10 @@ vhost_scsi_copy_iov_to_sgl(struct vhost_scsi_cmd *cmd, struct iov_iter *iter,
 		sg_set_page(&sg[i], page, nbytes, 0);
 
 		if (cmd->tvc_data_direction == DMA_TO_DEVICE &&
-		    copy_page_from_iter(page, 0, nbytes, iter) != nbytes)
+		    copy_page_from_iter(page, 0, nbytes, iter) != nbytes) {
+			ret = -EFAULT;
 			goto err;
+		}
 
 		len -= nbytes;
 	}
@@ -793,7 +801,7 @@ err:
 	for (; i >= 0; i--)
 		__free_page(sg_page(&sg[i]));
 	kfree(cmd->saved_iter_addr);
-	return -ENOMEM;
+	return ret;
 }
 
 static int
@@ -930,24 +938,69 @@ static void vhost_scsi_target_queue_cmd(struct vhost_scsi_cmd *cmd)
 }
 
 static void
-vhost_scsi_send_bad_target(struct vhost_scsi *vs,
-			   struct vhost_virtqueue *vq,
-			   int head, unsigned out)
+vhost_scsi_send_status(struct vhost_scsi *vs, struct vhost_virtqueue *vq,
+		       struct vhost_scsi_ctx *vc, u8 status)
 {
-	struct virtio_scsi_cmd_resp __user *resp;
 	struct virtio_scsi_cmd_resp rsp;
+	struct iov_iter iov_iter;
 	int ret;
 
 	memset(&rsp, 0, sizeof(rsp));
-	rsp.response = VIRTIO_SCSI_S_BAD_TARGET;
-	resp = vq->iov[out].iov_base;
-	ret = __copy_to_user(resp, &rsp, sizeof(rsp));
-	if (!ret)
-		vhost_add_used_and_signal(&vs->dev, vq, head, 0);
+	rsp.status = status;
+
+	iov_iter_init(&iov_iter, ITER_DEST, &vq->iov[vc->out], vc->in,
+		      sizeof(rsp));
+
+	ret = copy_to_iter(&rsp, sizeof(rsp), &iov_iter);
+
+	if (likely(ret == sizeof(rsp)))
+		vhost_add_used_and_signal(&vs->dev, vq, vc->head, 0);
 	else
 		pr_err("Faulted on virtio_scsi_cmd_resp\n");
 }
 
+#define TYPE_IO_CMD    0
+#define TYPE_CTRL_TMF  1
+#define TYPE_CTRL_AN   2
+
+static void
+vhost_scsi_send_bad_target(struct vhost_scsi *vs,
+			   struct vhost_virtqueue *vq,
+			   struct vhost_scsi_ctx *vc, int type)
+{
+	union {
+		struct virtio_scsi_cmd_resp cmd;
+		struct virtio_scsi_ctrl_tmf_resp tmf;
+		struct virtio_scsi_ctrl_an_resp an;
+	} rsp;
+	struct iov_iter iov_iter;
+	size_t rsp_size;
+	int ret;
+
+	memset(&rsp, 0, sizeof(rsp));
+
+	if (type == TYPE_IO_CMD) {
+		rsp_size = sizeof(struct virtio_scsi_cmd_resp);
+		rsp.cmd.response = VIRTIO_SCSI_S_BAD_TARGET;
+	} else if (type == TYPE_CTRL_TMF) {
+		rsp_size = sizeof(struct virtio_scsi_ctrl_tmf_resp);
+		rsp.tmf.response = VIRTIO_SCSI_S_BAD_TARGET;
+	} else {
+		rsp_size = sizeof(struct virtio_scsi_ctrl_an_resp);
+		rsp.an.response = VIRTIO_SCSI_S_BAD_TARGET;
+	}
+
+	iov_iter_init(&iov_iter, ITER_DEST, &vq->iov[vc->out], vc->in,
+		      rsp_size);
+
+	ret = copy_to_iter(&rsp, rsp_size, &iov_iter);
+
+	if (likely(ret == rsp_size))
+		vhost_add_used_and_signal(&vs->dev, vq, vc->head, 0);
+	else
+		pr_err("Faulted on virtio scsi type=%d\n", type);
+}
+
 static int
 vhost_scsi_get_desc(struct vhost_scsi *vs, struct vhost_virtqueue *vq,
 		    struct vhost_scsi_ctx *vc)
@@ -1035,10 +1088,8 @@ vhost_scsi_get_req(struct vhost_virtqueue *vq, struct vhost_scsi_ctx *vc,
 			/* validated at handler entry */
 			vs_tpg = vhost_vq_get_backend(vq);
 			tpg = READ_ONCE(vs_tpg[*vc->target]);
-			if (unlikely(!tpg)) {
-				vq_err(vq, "Target 0x%x does not exist\n", *vc->target);
+			if (unlikely(!tpg))
 				goto out;
-			}
 		}
 
 		if (tpgp)
@@ -1216,8 +1267,8 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq)
 					 exp_data_len + prot_bytes,
 					 data_direction);
 		if (IS_ERR(cmd)) {
-			vq_err(vq, "vhost_scsi_get_cmd failed %ld\n",
-			       PTR_ERR(cmd));
+			ret = PTR_ERR(cmd);
+			vq_err(vq, "vhost_scsi_get_tag failed %dd\n", ret);
 			goto err;
 		}
 		cmd->tvc_vhost = vs;
@@ -1232,9 +1283,9 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq)
 			 " %d\n", cmd, exp_data_len, prot_bytes, data_direction);
 
 		if (data_direction != DMA_NONE) {
-			if (unlikely(vhost_scsi_mapal(cmd, prot_bytes,
-						      &prot_iter, exp_data_len,
-						      &data_iter))) {
+			ret = vhost_scsi_mapal(cmd, prot_bytes, &prot_iter,
+					       exp_data_len, &data_iter);
+			if (unlikely(ret)) {
 				vq_err(vq, "Failed to map iov to sgl\n");
 				vhost_scsi_release_cmd_res(&cmd->tvc_se_cmd);
 				goto err;
@@ -1254,11 +1305,15 @@ err:
 		 * EINVAL: Invalid response buffer, drop the request
 		 * EIO:    Respond with bad target
 		 * EAGAIN: Pending request
+		 * ENOMEM: Could not allocate resources for request
 		 */
 		if (ret == -ENXIO)
 			break;
 		else if (ret == -EIO)
-			vhost_scsi_send_bad_target(vs, vq, vc.head, vc.out);
+			vhost_scsi_send_bad_target(vs, vq, &vc, TYPE_IO_CMD);
+		else if (ret == -ENOMEM)
+			vhost_scsi_send_status(vs, vq, &vc,
+					       SAM_STAT_TASK_SET_FULL);
 	} while (likely(!vhost_exceeds_weight(vq, ++c, 0)));
 out:
 	mutex_unlock(&vq->mutex);
@@ -1297,8 +1352,11 @@ static void vhost_scsi_tmf_resp_work(struct vhost_work *work)
 	else
 		resp_code = VIRTIO_SCSI_S_FUNCTION_REJECTED;
 
+	mutex_lock(&tmf->svq->vq.mutex);
 	vhost_scsi_send_tmf_resp(tmf->vhost, &tmf->svq->vq, tmf->in_iovs,
 				 tmf->vq_desc, &tmf->resp_iov, resp_code);
+	mutex_unlock(&tmf->svq->vq.mutex);
+
 	vhost_scsi_release_tmf_res(tmf);
 }
 
@@ -1488,7 +1546,10 @@ err:
 		if (ret == -ENXIO)
 			break;
 		else if (ret == -EIO)
-			vhost_scsi_send_bad_target(vs, vq, vc.head, vc.out);
+			vhost_scsi_send_bad_target(vs, vq, &vc,
+						   v_req.type == VIRTIO_SCSI_T_TMF ?
+						   TYPE_CTRL_TMF :
+						   TYPE_CTRL_AN);
 	} while (likely(!vhost_exceeds_weight(vq, ++c, 0)));
 out:
 	mutex_unlock(&vq->mutex);
@@ -1699,14 +1760,19 @@ vhost_scsi_set_endpoint(struct vhost_scsi *vs,
 		}
 	}
 
+	if (vs->vs_tpg) {
+		pr_err("vhost-scsi endpoint already set for %s.\n",
+		       vs->vs_vhost_wwpn);
+		ret = -EEXIST;
+		goto out;
+	}
+
 	len = sizeof(vs_tpg[0]) * VHOST_SCSI_MAX_TARGET;
 	vs_tpg = kzalloc(len, GFP_KERNEL);
 	if (!vs_tpg) {
 		ret = -ENOMEM;
 		goto out;
 	}
-	if (vs->vs_tpg)
-		memcpy(vs_tpg, vs->vs_tpg, len);
 
 	mutex_lock(&vhost_scsi_mutex);
 	list_for_each_entry(tpg, &vhost_scsi_list, tv_tpg_list) {
@@ -1722,12 +1788,6 @@ vhost_scsi_set_endpoint(struct vhost_scsi *vs,
 		tv_tport = tpg->tport;
 
 		if (!strcmp(tv_tport->tport_name, t->vhost_wwpn)) {
-			if (vs->vs_tpg && vs->vs_tpg[tpg->tport_tpgt]) {
-				mutex_unlock(&tpg->tv_tpg_mutex);
-				mutex_unlock(&vhost_scsi_mutex);
-				ret = -EEXIST;
-				goto undepend;
-			}
 			/*
 			 * In order to ensure individual vhost-scsi configfs
 			 * groups cannot be removed while in use by vhost ioctl,
@@ -1774,15 +1834,15 @@ vhost_scsi_set_endpoint(struct vhost_scsi *vs,
 		}
 		ret = 0;
 	} else {
-		ret = -EEXIST;
+		ret = -ENODEV;
+		goto free_tpg;
 	}
 
 	/*
-	 * Act as synchronize_rcu to make sure access to
-	 * old vs->vs_tpg is finished.
+	 * Act as synchronize_rcu to make sure requests after this point
+	 * see a fully setup device.
 	 */
 	vhost_scsi_flush(vs);
-	kfree(vs->vs_tpg);
 	vs->vs_tpg = vs_tpg;
 	goto out;
 
@@ -1802,6 +1862,7 @@ undepend:
 			target_undepend_item(&tpg->se_tpg.tpg_group.cg_item);
 		}
 	}
+free_tpg:
 	kfree(vs_tpg);
 out:
 	mutex_unlock(&vs->dev.mutex);
@@ -1904,6 +1965,7 @@ free_vs_tpg:
 	vhost_scsi_flush(vs);
 	kfree(vs->vs_tpg);
 	vs->vs_tpg = NULL;
+	memset(vs->vs_vhost_wwpn, 0, sizeof(vs->vs_vhost_wwpn));
 	WARN_ON(vs->vs_events_nr);
 	mutex_unlock(&vs->dev.mutex);
 	return 0;
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 9ac25d08f473..71604668e53f 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -22,6 +22,7 @@
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/kthread.h>
+#include <linux/cgroup.h>
 #include <linux/module.h>
 #include <linux/sort.h>
 #include <linux/sched/mm.h>
@@ -41,6 +42,13 @@ static int max_iotlb_entries = 2048;
 module_param(max_iotlb_entries, int, 0444);
 MODULE_PARM_DESC(max_iotlb_entries,
 	"Maximum number of iotlb entries. (default: 2048)");
+static bool fork_from_owner_default = VHOST_FORK_OWNER_TASK;
+
+#ifdef CONFIG_VHOST_ENABLE_FORK_OWNER_CONTROL
+module_param(fork_from_owner_default, bool, 0444);
+MODULE_PARM_DESC(fork_from_owner_default,
+		 "Set task mode as the default(default: Y)");
+#endif
 
 enum {
 	VHOST_MEMORY_F_LOG = 0x1,
@@ -242,7 +250,7 @@ static void vhost_worker_queue(struct vhost_worker *worker,
 		 * test_and_set_bit() implies a memory barrier.
 		 */
 		llist_add(&work->node, &worker->work_list);
-		vhost_task_wake(worker->vtsk);
+		worker->ops->wakeup(worker);
 	}
 }
 
@@ -388,6 +396,44 @@ static void vhost_vq_reset(struct vhost_dev *dev,
 	__vhost_vq_meta_reset(vq);
 }
 
+static int vhost_run_work_kthread_list(void *data)
+{
+	struct vhost_worker *worker = data;
+	struct vhost_work *work, *work_next;
+	struct vhost_dev *dev = worker->dev;
+	struct llist_node *node;
+
+	kthread_use_mm(dev->mm);
+
+	for (;;) {
+		/* mb paired w/ kthread_stop */
+		set_current_state(TASK_INTERRUPTIBLE);
+
+		if (kthread_should_stop()) {
+			__set_current_state(TASK_RUNNING);
+			break;
+		}
+		node = llist_del_all(&worker->work_list);
+		if (!node)
+			schedule();
+
+		node = llist_reverse_order(node);
+		/* make sure flag is seen after deletion */
+		smp_wmb();
+		llist_for_each_entry_safe(work, work_next, node, node) {
+			clear_bit(VHOST_WORK_QUEUED, &work->flags);
+			__set_current_state(TASK_RUNNING);
+			kcov_remote_start_common(worker->kcov_handle);
+			work->fn(work);
+			kcov_remote_stop();
+			cond_resched();
+		}
+	}
+	kthread_unuse_mm(dev->mm);
+
+	return 0;
+}
+
 static bool vhost_run_work_list(void *data)
 {
 	struct vhost_worker *worker = data;
@@ -552,6 +598,7 @@ void vhost_dev_init(struct vhost_dev *dev,
 	dev->byte_weight = byte_weight;
 	dev->use_worker = use_worker;
 	dev->msg_handler = msg_handler;
+	dev->fork_owner = fork_from_owner_default;
 	init_waitqueue_head(&dev->wait);
 	INIT_LIST_HEAD(&dev->read_list);
 	INIT_LIST_HEAD(&dev->pending_list);
@@ -581,6 +628,46 @@ long vhost_dev_check_owner(struct vhost_dev *dev)
 }
 EXPORT_SYMBOL_GPL(vhost_dev_check_owner);
 
+struct vhost_attach_cgroups_struct {
+	struct vhost_work work;
+	struct task_struct *owner;
+	int ret;
+};
+
+static void vhost_attach_cgroups_work(struct vhost_work *work)
+{
+	struct vhost_attach_cgroups_struct *s;
+
+	s = container_of(work, struct vhost_attach_cgroups_struct, work);
+	s->ret = cgroup_attach_task_all(s->owner, current);
+}
+
+static int vhost_attach_task_to_cgroups(struct vhost_worker *worker)
+{
+	struct vhost_attach_cgroups_struct attach;
+	int saved_cnt;
+
+	attach.owner = current;
+
+	vhost_work_init(&attach.work, vhost_attach_cgroups_work);
+	vhost_worker_queue(worker, &attach.work);
+
+	mutex_lock(&worker->mutex);
+
+	/*
+	 * Bypass attachment_cnt check in __vhost_worker_flush:
+	 * Temporarily change it to INT_MAX to bypass the check
+	 */
+	saved_cnt = worker->attachment_cnt;
+	worker->attachment_cnt = INT_MAX;
+	__vhost_worker_flush(worker);
+	worker->attachment_cnt = saved_cnt;
+
+	mutex_unlock(&worker->mutex);
+
+	return attach.ret;
+}
+
 /* Caller should have device mutex */
 bool vhost_dev_has_owner(struct vhost_dev *dev)
 {
@@ -626,7 +713,7 @@ static void vhost_worker_destroy(struct vhost_dev *dev,
 
 	WARN_ON(!llist_empty(&worker->work_list));
 	xa_erase(&dev->worker_xa, worker->id);
-	vhost_task_stop(worker->vtsk);
+	worker->ops->stop(worker);
 	kfree(worker);
 }
 
@@ -649,42 +736,115 @@ static void vhost_workers_free(struct vhost_dev *dev)
 	xa_destroy(&dev->worker_xa);
 }
 
+static void vhost_task_wakeup(struct vhost_worker *worker)
+{
+	return vhost_task_wake(worker->vtsk);
+}
+
+static void vhost_kthread_wakeup(struct vhost_worker *worker)
+{
+	wake_up_process(worker->kthread_task);
+}
+
+static void vhost_task_do_stop(struct vhost_worker *worker)
+{
+	return vhost_task_stop(worker->vtsk);
+}
+
+static void vhost_kthread_do_stop(struct vhost_worker *worker)
+{
+	kthread_stop(worker->kthread_task);
+}
+
+static int vhost_task_worker_create(struct vhost_worker *worker,
+				    struct vhost_dev *dev, const char *name)
+{
+	struct vhost_task *vtsk;
+	u32 id;
+	int ret;
+
+	vtsk = vhost_task_create(vhost_run_work_list, vhost_worker_killed,
+				 worker, name);
+	if (IS_ERR(vtsk))
+		return PTR_ERR(vtsk);
+
+	worker->vtsk = vtsk;
+	vhost_task_start(vtsk);
+	ret = xa_alloc(&dev->worker_xa, &id, worker, xa_limit_32b, GFP_KERNEL);
+	if (ret < 0) {
+		vhost_task_do_stop(worker);
+		return ret;
+	}
+	worker->id = id;
+	return 0;
+}
+
+static int vhost_kthread_worker_create(struct vhost_worker *worker,
+				       struct vhost_dev *dev, const char *name)
+{
+	struct task_struct *task;
+	u32 id;
+	int ret;
+
+	task = kthread_create(vhost_run_work_kthread_list, worker, "%s", name);
+	if (IS_ERR(task))
+		return PTR_ERR(task);
+
+	worker->kthread_task = task;
+	wake_up_process(task);
+	ret = xa_alloc(&dev->worker_xa, &id, worker, xa_limit_32b, GFP_KERNEL);
+	if (ret < 0)
+		goto stop_worker;
+
+	ret = vhost_attach_task_to_cgroups(worker);
+	if (ret)
+		goto stop_worker;
+
+	worker->id = id;
+	return 0;
+
+stop_worker:
+	vhost_kthread_do_stop(worker);
+	return ret;
+}
+
+static const struct vhost_worker_ops kthread_ops = {
+	.create = vhost_kthread_worker_create,
+	.stop = vhost_kthread_do_stop,
+	.wakeup = vhost_kthread_wakeup,
+};
+
+static const struct vhost_worker_ops vhost_task_ops = {
+	.create = vhost_task_worker_create,
+	.stop = vhost_task_do_stop,
+	.wakeup = vhost_task_wakeup,
+};
+
 static struct vhost_worker *vhost_worker_create(struct vhost_dev *dev)
 {
 	struct vhost_worker *worker;
-	struct vhost_task *vtsk;
 	char name[TASK_COMM_LEN];
 	int ret;
-	u32 id;
+	const struct vhost_worker_ops *ops = dev->fork_owner ? &vhost_task_ops :
+							       &kthread_ops;
 
 	worker = kzalloc(sizeof(*worker), GFP_KERNEL_ACCOUNT);
 	if (!worker)
 		return NULL;
 
 	worker->dev = dev;
+	worker->ops = ops;
 	snprintf(name, sizeof(name), "vhost-%d", current->pid);
 
-	vtsk = vhost_task_create(vhost_run_work_list, vhost_worker_killed,
-				 worker, name);
-	if (!vtsk)
-		goto free_worker;
-
 	mutex_init(&worker->mutex);
 	init_llist_head(&worker->work_list);
 	worker->kcov_handle = kcov_common_handle();
-	worker->vtsk = vtsk;
-
-	vhost_task_start(vtsk);
-
-	ret = xa_alloc(&dev->worker_xa, &id, worker, xa_limit_32b, GFP_KERNEL);
+	ret = ops->create(worker, dev, name);
 	if (ret < 0)
-		goto stop_worker;
-	worker->id = id;
+		goto free_worker;
 
 	return worker;
 
-stop_worker:
-	vhost_task_stop(vtsk);
 free_worker:
 	kfree(worker);
 	return NULL;
@@ -865,6 +1025,14 @@ long vhost_worker_ioctl(struct vhost_dev *dev, unsigned int ioctl,
 	switch (ioctl) {
 	/* dev worker ioctls */
 	case VHOST_NEW_WORKER:
+		/*
+		 * vhost_tasks will account for worker threads under the parent's
+		 * NPROC value but kthreads do not. To avoid userspace overflowing
+		 * the system with worker threads fork_owner must be true.
+		 */
+		if (!dev->fork_owner)
+			return -EFAULT;
+
 		ret = vhost_new_worker(dev, &state);
 		if (!ret && copy_to_user(argp, &state, sizeof(state)))
 			ret = -EFAULT;
@@ -982,6 +1150,7 @@ void vhost_dev_reset_owner(struct vhost_dev *dev, struct vhost_iotlb *umem)
 
 	vhost_dev_cleanup(dev);
 
+	dev->fork_owner = fork_from_owner_default;
 	dev->umem = umem;
 	/* We don't need VQ locks below since vhost_dev_cleanup makes sure
 	 * VQs aren't running.
@@ -2135,6 +2304,45 @@ long vhost_dev_ioctl(struct vhost_dev *d, unsigned int ioctl, void __user *argp)
 		goto done;
 	}
 
+#ifdef CONFIG_VHOST_ENABLE_FORK_OWNER_CONTROL
+	if (ioctl == VHOST_SET_FORK_FROM_OWNER) {
+		/* Only allow modification before owner is set */
+		if (vhost_dev_has_owner(d)) {
+			r = -EBUSY;
+			goto done;
+		}
+		u8 fork_owner_val;
+
+		if (get_user(fork_owner_val, (u8 __user *)argp)) {
+			r = -EFAULT;
+			goto done;
+		}
+		if (fork_owner_val != VHOST_FORK_OWNER_TASK &&
+		    fork_owner_val != VHOST_FORK_OWNER_KTHREAD) {
+			r = -EINVAL;
+			goto done;
+		}
+		d->fork_owner = !!fork_owner_val;
+		r = 0;
+		goto done;
+	}
+	if (ioctl == VHOST_GET_FORK_FROM_OWNER) {
+		u8 fork_owner_val = d->fork_owner;
+
+		if (fork_owner_val != VHOST_FORK_OWNER_TASK &&
+		    fork_owner_val != VHOST_FORK_OWNER_KTHREAD) {
+			r = -EINVAL;
+			goto done;
+		}
+		if (put_user(fork_owner_val, (u8 __user *)argp)) {
+			r = -EFAULT;
+			goto done;
+		}
+		r = 0;
+		goto done;
+	}
+#endif
+
 	/* You must be the owner to do anything else */
 	r = vhost_dev_check_owner(d);
 	if (r)
@@ -2763,6 +2971,9 @@ int vhost_add_used_n(struct vhost_virtqueue *vq, struct vring_used_elem *heads,
 	}
 	r = __vhost_add_used_n(vq, heads, count);
 
+	if (r < 0)
+		return r;
+
 	/* Make sure buffer is written before we update index. */
 	smp_wmb();
 	if (vhost_put_used_idx(vq)) {
diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
index bb75a292d50c..ab704d84fb34 100644
--- a/drivers/vhost/vhost.h
+++ b/drivers/vhost/vhost.h
@@ -26,7 +26,18 @@ struct vhost_work {
 	unsigned long		flags;
 };
 
+struct vhost_worker;
+struct vhost_dev;
+
+struct vhost_worker_ops {
+	int (*create)(struct vhost_worker *worker, struct vhost_dev *dev,
+		      const char *name);
+	void (*stop)(struct vhost_worker *worker);
+	void (*wakeup)(struct vhost_worker *worker);
+};
+
 struct vhost_worker {
+	struct task_struct *kthread_task;
 	struct vhost_task	*vtsk;
 	struct vhost_dev	*dev;
 	/* Used to serialize device wide flushing with worker swapping. */
@@ -36,6 +47,7 @@ struct vhost_worker {
 	u32			id;
 	int			attachment_cnt;
 	bool			killed;
+	const struct vhost_worker_ops *ops;
 };
 
 /* Poll a file (eventfd or socket) */
@@ -176,6 +188,16 @@ struct vhost_dev {
 	int byte_weight;
 	struct xarray worker_xa;
 	bool use_worker;
+	/*
+	 * If fork_owner is true we use vhost_tasks to create
+	 * the worker so all settings/limits like cgroups, NPROC,
+	 * scheduler, etc are inherited from the owner. If false,
+	 * we use kthreads and only attach to the same cgroups
+	 * as the owner for compat with older kernels.
+	 * here we use true as default value.
+	 * The default value is set by fork_from_owner_default
+	 */
+	bool fork_owner;
 	int (*msg_handler)(struct vhost_dev *dev, u32 asid,
 			   struct vhost_iotlb_msg *msg);
 };
diff --git a/drivers/video/backlight/led_bl.c b/drivers/video/backlight/led_bl.c
index c7aefcd6e4e3..782600601845 100644
--- a/drivers/video/backlight/led_bl.c
+++ b/drivers/video/backlight/led_bl.c
@@ -229,8 +229,11 @@ static void led_bl_remove(struct platform_device *pdev)
 	backlight_device_unregister(bl);
 
 	led_bl_power_off(priv);
-	for (i = 0; i < priv->nb_leds; i++)
+	for (i = 0; i < priv->nb_leds; i++) {
+		mutex_lock(&priv->leds[i]->led_access);
 		led_sysfs_enable(priv->leds[i]);
+		mutex_unlock(&priv->leds[i]->led_access);
+	}
 }
 
 static const struct of_device_id led_bl_of_match[] = {
diff --git a/drivers/video/backlight/qcom-wled.c b/drivers/video/backlight/qcom-wled.c
index 10129095a4c1..b19e5f73de8b 100644
--- a/drivers/video/backlight/qcom-wled.c
+++ b/drivers/video/backlight/qcom-wled.c
@@ -1406,9 +1406,11 @@ static int wled_configure(struct wled *wled)
 	wled->ctrl_addr = be32_to_cpu(*prop_addr);
 
 	rc = of_property_read_string(dev->of_node, "label", &wled->name);
-	if (rc)
+	if (rc) {
 		wled->name = devm_kasprintf(dev, GFP_KERNEL, "%pOFn", dev->of_node);
-
+		if (!wled->name)
+			return -ENOMEM;
+	}
 	switch (wled->version) {
 	case 3:
 		u32_opts = wled3_opts;
diff --git a/drivers/video/console/Kconfig b/drivers/video/console/Kconfig
index bc31db6ef7d2..3e9f2bda6702 100644
--- a/drivers/video/console/Kconfig
+++ b/drivers/video/console/Kconfig
@@ -24,7 +24,7 @@ config VGA_CONSOLE
 	  Say Y.
 
 config MDA_CONSOLE
-	depends on !M68K && !PARISC && ISA
+	depends on VGA_CONSOLE && ISA
 	tristate "MDA text console (dual-headed)"
 	help
 	  Say Y here if you have an old MDA or monochrome Hercules graphics
@@ -52,7 +52,7 @@ config DUMMY_CONSOLE
 
 config DUMMY_CONSOLE_COLUMNS
 	int "Initial number of console screen columns"
-	depends on DUMMY_CONSOLE && !ARCH_FOOTBRIDGE
+	depends on DUMMY_CONSOLE && !(ARCH_FOOTBRIDGE && VGA_CONSOLE)
 	default 160 if PARISC
 	default 80
 	help
@@ -62,7 +62,7 @@ config DUMMY_CONSOLE_COLUMNS
 
 config DUMMY_CONSOLE_ROWS
 	int "Initial number of console screen rows"
-	depends on DUMMY_CONSOLE && !ARCH_FOOTBRIDGE
+	depends on DUMMY_CONSOLE && !(ARCH_FOOTBRIDGE && VGA_CONSOLE)
 	default 64 if PARISC
 	default 30 if ARM
 	default 25
diff --git a/drivers/video/console/dummycon.c b/drivers/video/console/dummycon.c
index 139049368fdc..7d02470f19b9 100644
--- a/drivers/video/console/dummycon.c
+++ b/drivers/video/console/dummycon.c
@@ -85,6 +85,15 @@ static bool dummycon_blank(struct vc_data *vc, enum vesa_blank_mode blank,
 	/* Redraw, so that we get putc(s) for output done while blanked */
 	return true;
 }
+
+static bool dummycon_switch(struct vc_data *vc)
+{
+	/*
+	 * Redraw, so that we get putc(s) for output done while switched
+	 * away. Informs deferred consoles to take over the display.
+	 */
+	return true;
+}
 #else
 static void dummycon_putc(struct vc_data *vc, u16 c, unsigned int y,
 			  unsigned int x) { }
@@ -95,6 +104,10 @@ static bool dummycon_blank(struct vc_data *vc, enum vesa_blank_mode blank,
 {
 	return false;
 }
+static bool dummycon_switch(struct vc_data *vc)
+{
+	return false;
+}
 #endif
 
 static const char *dummycon_startup(void)
@@ -124,11 +137,6 @@ static bool dummycon_scroll(struct vc_data *vc, unsigned int top,
 	return false;
 }
 
-static bool dummycon_switch(struct vc_data *vc)
-{
-	return false;
-}
-
 /*
  *  The console `switch' structure for the dummy console
  *
diff --git a/drivers/video/console/vgacon.c b/drivers/video/console/vgacon.c
index 37bd18730fe0..f9cdbf8c53e3 100644
--- a/drivers/video/console/vgacon.c
+++ b/drivers/video/console/vgacon.c
@@ -1168,7 +1168,7 @@ static bool vgacon_scroll(struct vc_data *c, unsigned int t, unsigned int b,
 				     c->vc_screenbuf_size - delta);
 			c->vc_origin = vga_vram_end - c->vc_screenbuf_size;
 			vga_rolled_over = 0;
-		} else
+		} else if (oldo - delta >= (unsigned long)c->vc_screenbuf)
 			c->vc_origin -= delta;
 		c->vc_scr_end = c->vc_origin + c->vc_screenbuf_size;
 		scr_memsetw((u16 *) (c->vc_origin), c->vc_video_erase_char,
diff --git a/drivers/video/fbdev/au1100fb.c b/drivers/video/fbdev/au1100fb.c
index 840f22160763..6251a6b07b3a 100644
--- a/drivers/video/fbdev/au1100fb.c
+++ b/drivers/video/fbdev/au1100fb.c
@@ -137,13 +137,15 @@ static int au1100fb_fb_blank(int blank_mode, struct fb_info *fbi)
 	 */
 int au1100fb_setmode(struct au1100fb_device *fbdev)
 {
-	struct fb_info *info = &fbdev->info;
+	struct fb_info *info;
 	u32 words;
 	int index;
 
 	if (!fbdev)
 		return -EINVAL;
 
+	info = &fbdev->info;
+
 	/* Update var-dependent FB info */
 	if (panel_is_active(fbdev->panel) || panel_is_color(fbdev->panel)) {
 		if (info->var.bits_per_pixel <= 8) {
diff --git a/drivers/video/fbdev/core/bitblit.c b/drivers/video/fbdev/core/bitblit.c
index 3ff1b2a8659e..f9475c14f733 100644
--- a/drivers/video/fbdev/core/bitblit.c
+++ b/drivers/video/fbdev/core/bitblit.c
@@ -59,12 +59,11 @@ static void bit_bmove(struct vc_data *vc, struct fb_info *info, int sy,
 }
 
 static void bit_clear(struct vc_data *vc, struct fb_info *info, int sy,
-		      int sx, int height, int width)
+		      int sx, int height, int width, int fg, int bg)
 {
-	int bgshift = (vc->vc_hi_font_mask) ? 13 : 12;
 	struct fb_fillrect region;
 
-	region.color = attr_bgcol_ec(bgshift, vc, info);
+	region.color = bg;
 	region.dx = sx * vc->vc_font.width;
 	region.dy = sy * vc->vc_font.height;
 	region.width = width * vc->vc_font.width;
diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c
index e8b4e8c119b5..893fd66b5269 100644
--- a/drivers/video/fbdev/core/fbcon.c
+++ b/drivers/video/fbdev/core/fbcon.c
@@ -117,9 +117,14 @@ static signed char con2fb_map_boot[MAX_NR_CONSOLES];
 
 static struct fb_info *fbcon_info_from_console(int console)
 {
+	signed char fb;
 	WARN_CONSOLE_UNLOCKED();
 
-	return fbcon_registered_fb[con2fb_map[console]];
+	fb = con2fb_map[console];
+	if (fb < 0 || fb >= ARRAY_SIZE(fbcon_registered_fb))
+		return NULL;
+
+	return fbcon_registered_fb[fb];
 }
 
 static int logo_lines;
@@ -821,7 +826,8 @@ static void con2fb_init_display(struct vc_data *vc, struct fb_info *info,
 				   fg_vc->vc_rows);
 	}
 
-	update_screen(vc_cons[fg_console].d);
+	if (fg_console != unit)
+		update_screen(vc_cons[fg_console].d);
 }
 
 /**
@@ -948,13 +954,13 @@ static const char *fbcon_startup(void)
 	int rows, cols;
 
 	/*
-	 *  If num_registered_fb is zero, this is a call for the dummy part.
+	 *  If fbcon_num_registered_fb is zero, this is a call for the dummy part.
 	 *  The frame buffer devices weren't initialized yet.
 	 */
 	if (!fbcon_num_registered_fb || info_idx == -1)
 		return display_desc;
 	/*
-	 * Instead of blindly using registered_fb[0], we use info_idx, set by
+	 * Instead of blindly using fbcon_registered_fb[0], we use info_idx, set by
 	 * fbcon_fb_registered();
 	 */
 	info = fbcon_registered_fb[info_idx];
@@ -1258,7 +1264,7 @@ static void __fbcon_clear(struct vc_data *vc, unsigned int sy, unsigned int sx,
 {
 	struct fb_info *info = fbcon_info_from_console(vc->vc_num);
 	struct fbcon_ops *ops = info->fbcon_par;
-
+	int fg, bg;
 	struct fbcon_display *p = &fb_display[vc->vc_num];
 	u_int y_break;
 
@@ -1279,16 +1285,18 @@ static void __fbcon_clear(struct vc_data *vc, unsigned int sy, unsigned int sx,
 		fbcon_clear_margins(vc, 0);
 	}
 
+	fg = get_color(vc, info, vc->vc_video_erase_char, 1);
+	bg = get_color(vc, info, vc->vc_video_erase_char, 0);
 	/* Split blits that cross physical y_wrap boundary */
 
 	y_break = p->vrows - p->yscroll;
 	if (sy < y_break && sy + height - 1 >= y_break) {
 		u_int b = y_break - sy;
-		ops->clear(vc, info, real_y(p, sy), sx, b, width);
+		ops->clear(vc, info, real_y(p, sy), sx, b, width, fg, bg);
 		ops->clear(vc, info, real_y(p, sy + b), sx, height - b,
-				 width);
+				 width, fg, bg);
 	} else
-		ops->clear(vc, info, real_y(p, sy), sx, height, width);
+		ops->clear(vc, info, real_y(p, sy), sx, height, width, fg, bg);
 }
 
 static void fbcon_clear(struct vc_data *vc, unsigned int sy, unsigned int sx,
@@ -1356,6 +1364,7 @@ static void fbcon_set_disp(struct fb_info *info, struct fb_var_screeninfo *var,
 	struct vc_data *svc;
 	struct fbcon_ops *ops = info->fbcon_par;
 	int rows, cols;
+	unsigned long ret = 0;
 
 	p = &fb_display[unit];
 
@@ -1406,11 +1415,10 @@ static void fbcon_set_disp(struct fb_info *info, struct fb_var_screeninfo *var,
 	rows = FBCON_SWAP(ops->rotate, info->var.yres, info->var.xres);
 	cols /= vc->vc_font.width;
 	rows /= vc->vc_font.height;
-	vc_resize(vc, cols, rows);
+	ret = vc_resize(vc, cols, rows);
 
-	if (con_is_visible(vc)) {
+	if (con_is_visible(vc) && !ret)
 		update_screen(vc);
-	}
 }
 
 static __inline__ void ywrap_up(struct vc_data *vc, int count)
diff --git a/drivers/video/fbdev/core/fbcon.h b/drivers/video/fbdev/core/fbcon.h
index df70ea5ec5b3..4d97e6d8a16a 100644
--- a/drivers/video/fbdev/core/fbcon.h
+++ b/drivers/video/fbdev/core/fbcon.h
@@ -55,7 +55,7 @@ struct fbcon_ops {
 	void (*bmove)(struct vc_data *vc, struct fb_info *info, int sy,
 		      int sx, int dy, int dx, int height, int width);
 	void (*clear)(struct vc_data *vc, struct fb_info *info, int sy,
-		      int sx, int height, int width);
+		      int sx, int height, int width, int fb, int bg);
 	void (*putcs)(struct vc_data *vc, struct fb_info *info,
 		      const unsigned short *s, int count, int yy, int xx,
 		      int fg, int bg);
@@ -116,42 +116,6 @@ static inline int mono_col(const struct fb_info *info)
 	return (~(0xfff << max_len)) & 0xff;
 }
 
-static inline int attr_col_ec(int shift, struct vc_data *vc,
-			      struct fb_info *info, int is_fg)
-{
-	int is_mono01;
-	int col;
-	int fg;
-	int bg;
-
-	if (!vc)
-		return 0;
-
-	if (vc->vc_can_do_color)
-		return is_fg ? attr_fgcol(shift,vc->vc_video_erase_char)
-			: attr_bgcol(shift,vc->vc_video_erase_char);
-
-	if (!info)
-		return 0;
-
-	col = mono_col(info);
-	is_mono01 = info->fix.visual == FB_VISUAL_MONO01;
-
-	if (attr_reverse(vc->vc_video_erase_char)) {
-		fg = is_mono01 ? col : 0;
-		bg = is_mono01 ? 0 : col;
-	}
-	else {
-		fg = is_mono01 ? 0 : col;
-		bg = is_mono01 ? col : 0;
-	}
-
-	return is_fg ? fg : bg;
-}
-
-#define attr_bgcol_ec(bgshift, vc, info) attr_col_ec(bgshift, vc, info, 0)
-#define attr_fgcol_ec(fgshift, vc, info) attr_col_ec(fgshift, vc, info, 1)
-
     /*
      *  Scroll Method
      */
diff --git a/drivers/video/fbdev/core/fbcon_ccw.c b/drivers/video/fbdev/core/fbcon_ccw.c
index f9b794ff7d39..89ef4ba7e867 100644
--- a/drivers/video/fbdev/core/fbcon_ccw.c
+++ b/drivers/video/fbdev/core/fbcon_ccw.c
@@ -78,14 +78,13 @@ static void ccw_bmove(struct vc_data *vc, struct fb_info *info, int sy,
 }
 
 static void ccw_clear(struct vc_data *vc, struct fb_info *info, int sy,
-		     int sx, int height, int width)
+		     int sx, int height, int width, int fg, int bg)
 {
 	struct fbcon_ops *ops = info->fbcon_par;
 	struct fb_fillrect region;
-	int bgshift = (vc->vc_hi_font_mask) ? 13 : 12;
 	u32 vyres = GETVYRES(ops->p, info);
 
-	region.color = attr_bgcol_ec(bgshift,vc,info);
+	region.color = bg;
 	region.dx = sy * vc->vc_font.height;
 	region.dy = vyres - ((sx + width) * vc->vc_font.width);
 	region.height = width * vc->vc_font.width;
diff --git a/drivers/video/fbdev/core/fbcon_cw.c b/drivers/video/fbdev/core/fbcon_cw.c
index 903f6fc174e1..b9dac7940fb7 100644
--- a/drivers/video/fbdev/core/fbcon_cw.c
+++ b/drivers/video/fbdev/core/fbcon_cw.c
@@ -63,14 +63,13 @@ static void cw_bmove(struct vc_data *vc, struct fb_info *info, int sy,
 }
 
 static void cw_clear(struct vc_data *vc, struct fb_info *info, int sy,
-		     int sx, int height, int width)
+		     int sx, int height, int width, int fg, int bg)
 {
 	struct fbcon_ops *ops = info->fbcon_par;
 	struct fb_fillrect region;
-	int bgshift = (vc->vc_hi_font_mask) ? 13 : 12;
 	u32 vxres = GETVXRES(ops->p, info);
 
-	region.color = attr_bgcol_ec(bgshift,vc,info);
+	region.color = bg;
 	region.dx = vxres - ((sy + height) * vc->vc_font.height);
 	region.dy = sx *  vc->vc_font.width;
 	region.height = width * vc->vc_font.width;
diff --git a/drivers/video/fbdev/core/fbcon_ud.c b/drivers/video/fbdev/core/fbcon_ud.c
index 594331936fd3..0af7913a2abd 100644
--- a/drivers/video/fbdev/core/fbcon_ud.c
+++ b/drivers/video/fbdev/core/fbcon_ud.c
@@ -64,15 +64,14 @@ static void ud_bmove(struct vc_data *vc, struct fb_info *info, int sy,
 }
 
 static void ud_clear(struct vc_data *vc, struct fb_info *info, int sy,
-		     int sx, int height, int width)
+		     int sx, int height, int width, int fg, int bg)
 {
 	struct fbcon_ops *ops = info->fbcon_par;
 	struct fb_fillrect region;
-	int bgshift = (vc->vc_hi_font_mask) ? 13 : 12;
 	u32 vyres = GETVYRES(ops->p, info);
 	u32 vxres = GETVXRES(ops->p, info);
 
-	region.color = attr_bgcol_ec(bgshift,vc,info);
+	region.color = bg;
 	region.dy = vyres - ((sy + height) * vc->vc_font.height);
 	region.dx = vxres - ((sx + width) *  vc->vc_font.width);
 	region.width = width * vc->vc_font.width;
diff --git a/drivers/video/fbdev/core/fbcvt.c b/drivers/video/fbdev/core/fbcvt.c
index 64843464c661..cd3821bd82e5 100644
--- a/drivers/video/fbdev/core/fbcvt.c
+++ b/drivers/video/fbdev/core/fbcvt.c
@@ -312,7 +312,7 @@ int fb_find_mode_cvt(struct fb_videomode *mode, int margins, int rb)
 	cvt.f_refresh = cvt.refresh;
 	cvt.interlace = 1;
 
-	if (!cvt.xres || !cvt.yres || !cvt.refresh) {
+	if (!cvt.xres || !cvt.yres || !cvt.refresh || cvt.f_refresh > INT_MAX) {
 		printk(KERN_INFO "fbcvt: Invalid input parameters\n");
 		return 1;
 	}
diff --git a/drivers/video/fbdev/core/fbmem.c b/drivers/video/fbdev/core/fbmem.c
index 3c568cff2913..6a033bf17ab6 100644
--- a/drivers/video/fbdev/core/fbmem.c
+++ b/drivers/video/fbdev/core/fbmem.c
@@ -328,8 +328,10 @@ fb_set_var(struct fb_info *info, struct fb_var_screeninfo *var)
 	    !list_empty(&info->modelist))
 		ret = fb_add_videomode(&mode, &info->modelist);
 
-	if (ret)
+	if (ret) {
+		info->var = old_var;
 		return ret;
+	}
 
 	event.info = info;
 	event.data = &mode;
@@ -388,7 +390,7 @@ static int fb_check_foreignness(struct fb_info *fi)
 
 static int do_register_framebuffer(struct fb_info *fb_info)
 {
-	int i;
+	int i, err = 0;
 	struct fb_videomode mode;
 
 	if (fb_check_foreignness(fb_info))
@@ -397,10 +399,21 @@ static int do_register_framebuffer(struct fb_info *fb_info)
 	if (num_registered_fb == FB_MAX)
 		return -ENXIO;
 
-	num_registered_fb++;
 	for (i = 0 ; i < FB_MAX; i++)
 		if (!registered_fb[i])
 			break;
+
+	if (i >= FB_MAX)
+		return -ENXIO;
+
+	if (!fb_info->modelist.prev || !fb_info->modelist.next)
+		INIT_LIST_HEAD(&fb_info->modelist);
+
+	fb_var_to_videomode(&mode, &fb_info->var);
+	err = fb_add_videomode(&mode, &fb_info->modelist);
+	if (err < 0)
+		return err;
+
 	fb_info->node = i;
 	refcount_set(&fb_info->count, 1);
 	mutex_init(&fb_info->lock);
@@ -426,16 +439,12 @@ static int do_register_framebuffer(struct fb_info *fb_info)
 	if (bitmap_empty(fb_info->pixmap.blit_y, FB_MAX_BLIT_HEIGHT))
 		bitmap_fill(fb_info->pixmap.blit_y, FB_MAX_BLIT_HEIGHT);
 
-	if (!fb_info->modelist.prev || !fb_info->modelist.next)
-		INIT_LIST_HEAD(&fb_info->modelist);
-
 	if (fb_info->skip_vt_switch)
 		pm_vt_switch_required(fb_info->device, false);
 	else
 		pm_vt_switch_required(fb_info->device, true);
 
-	fb_var_to_videomode(&mode, &fb_info->var);
-	fb_add_videomode(&mode, &fb_info->modelist);
+	num_registered_fb++;
 	registered_fb[i] = fb_info;
 
 #ifdef CONFIG_GUMSTIX_AM200EPD
diff --git a/drivers/video/fbdev/core/tileblit.c b/drivers/video/fbdev/core/tileblit.c
index eff7ec4da167..d342b90c42b7 100644
--- a/drivers/video/fbdev/core/tileblit.c
+++ b/drivers/video/fbdev/core/tileblit.c
@@ -32,16 +32,14 @@ static void tile_bmove(struct vc_data *vc, struct fb_info *info, int sy,
 }
 
 static void tile_clear(struct vc_data *vc, struct fb_info *info, int sy,
-		       int sx, int height, int width)
+		       int sx, int height, int width, int fg, int bg)
 {
 	struct fb_tilerect rect;
-	int bgshift = (vc->vc_hi_font_mask) ? 13 : 12;
-	int fgshift = (vc->vc_hi_font_mask) ? 9 : 8;
 
 	rect.index = vc->vc_video_erase_char &
 		((vc->vc_hi_font_mask) ? 0x1ff : 0xff);
-	rect.fg = attr_fgcol_ec(fgshift, vc, info);
-	rect.bg = attr_bgcol_ec(bgshift, vc, info);
+	rect.fg = fg;
+	rect.bg = bg;
 	rect.sx = sx;
 	rect.sy = sy;
 	rect.width = width;
@@ -76,7 +74,42 @@ static void tile_putcs(struct vc_data *vc, struct fb_info *info,
 static void tile_clear_margins(struct vc_data *vc, struct fb_info *info,
 			       int color, int bottom_only)
 {
-	return;
+	unsigned int cw = vc->vc_font.width;
+	unsigned int ch = vc->vc_font.height;
+	unsigned int rw = info->var.xres - (vc->vc_cols*cw);
+	unsigned int bh = info->var.yres - (vc->vc_rows*ch);
+	unsigned int rs = info->var.xres - rw;
+	unsigned int bs = info->var.yres - bh;
+	unsigned int vwt = info->var.xres_virtual / cw;
+	unsigned int vht = info->var.yres_virtual / ch;
+	struct fb_tilerect rect;
+
+	rect.index = vc->vc_video_erase_char &
+		((vc->vc_hi_font_mask) ? 0x1ff : 0xff);
+	rect.fg = color;
+	rect.bg = color;
+
+	if ((int) rw > 0 && !bottom_only) {
+		rect.sx = (info->var.xoffset + rs + cw - 1) / cw;
+		rect.sy = 0;
+		rect.width = (rw + cw - 1) / cw;
+		rect.height = vht;
+		if (rect.width + rect.sx > vwt)
+			rect.width = vwt - rect.sx;
+		if (rect.sx < vwt)
+			info->tileops->fb_tilefill(info, &rect);
+	}
+
+	if ((int) bh > 0) {
+		rect.sx = info->var.xoffset / cw;
+		rect.sy = (info->var.yoffset + bs) / ch;
+		rect.width = rs / cw;
+		rect.height = (bh + ch - 1) / ch;
+		if (rect.height + rect.sy > vht)
+			rect.height = vht - rect.sy;
+		if (rect.sy < vht)
+			info->tileops->fb_tilefill(info, &rect);
+	}
 }
 
 static void tile_cursor(struct vc_data *vc, struct fb_info *info, bool enable,
diff --git a/drivers/video/fbdev/fsl-diu-fb.c b/drivers/video/fbdev/fsl-diu-fb.c
index 5ac8201c3533..b71d15794ce8 100644
--- a/drivers/video/fbdev/fsl-diu-fb.c
+++ b/drivers/video/fbdev/fsl-diu-fb.c
@@ -1827,6 +1827,7 @@ static void fsl_diu_remove(struct platform_device *pdev)
 	int i;
 
 	data = dev_get_drvdata(&pdev->dev);
+	device_remove_file(&pdev->dev, &data->dev_attr);
 	disable_lcdc(&data->fsl_diu_info[0]);
 
 	free_irq(data->irq, data->diu_reg);
diff --git a/drivers/video/fbdev/hyperv_fb.c b/drivers/video/fbdev/hyperv_fb.c
index 7fdb5edd7e2e..75338ffc703f 100644
--- a/drivers/video/fbdev/hyperv_fb.c
+++ b/drivers/video/fbdev/hyperv_fb.c
@@ -282,6 +282,8 @@ static uint screen_depth;
 static uint screen_fb_size;
 static uint dio_fb_size; /* FB size for deferred IO */
 
+static void hvfb_putmem(struct fb_info *info);
+
 /* Send message to Hyper-V host */
 static inline int synthvid_send(struct hv_device *hdev,
 				struct synthvid_msg *msg)
@@ -863,6 +865,17 @@ static void hvfb_ops_damage_area(struct fb_info *info, u32 x, u32 y, u32 width,
 }
 
 /*
+ * fb_ops.fb_destroy is called by the last put_fb_info() call at the end
+ * of unregister_framebuffer() or fb_release(). Do any cleanup related to
+ * framebuffer here.
+ */
+static void hvfb_destroy(struct fb_info *info)
+{
+	hvfb_putmem(info);
+	framebuffer_release(info);
+}
+
+/*
  * TODO: GEN1 codepaths allocate from system or DMA-able memory. Fix the
  *       driver to use the _SYSMEM_ or _DMAMEM_ helpers in these cases.
  */
@@ -877,6 +890,7 @@ static const struct fb_ops hvfb_ops = {
 	.fb_set_par = hvfb_set_par,
 	.fb_setcolreg = hvfb_setcolreg,
 	.fb_blank = hvfb_blank,
+	.fb_destroy	= hvfb_destroy,
 };
 
 /* Get options from kernel paramenter "video=" */
@@ -952,7 +966,7 @@ static phys_addr_t hvfb_get_phymem(struct hv_device *hdev,
 }
 
 /* Release contiguous physical memory */
-static void hvfb_release_phymem(struct hv_device *hdev,
+static void hvfb_release_phymem(struct device *device,
 				phys_addr_t paddr, unsigned int size)
 {
 	unsigned int order = get_order(size);
@@ -960,7 +974,7 @@ static void hvfb_release_phymem(struct hv_device *hdev,
 	if (order <= MAX_PAGE_ORDER)
 		__free_pages(pfn_to_page(paddr >> PAGE_SHIFT), order);
 	else
-		dma_free_coherent(&hdev->device,
+		dma_free_coherent(device,
 				  round_up(size, PAGE_SIZE),
 				  phys_to_virt(paddr),
 				  paddr);
@@ -989,6 +1003,7 @@ static int hvfb_getmem(struct hv_device *hdev, struct fb_info *info)
 
 		base = pci_resource_start(pdev, 0);
 		size = pci_resource_len(pdev, 0);
+		aperture_remove_conflicting_devices(base, size, KBUILD_MODNAME);
 
 		/*
 		 * For Gen 1 VM, we can directly use the contiguous memory
@@ -1010,11 +1025,21 @@ static int hvfb_getmem(struct hv_device *hdev, struct fb_info *info)
 			goto getmem_done;
 		}
 		pr_info("Unable to allocate enough contiguous physical memory on Gen 1 VM. Using MMIO instead.\n");
+	} else {
+		aperture_remove_all_conflicting_devices(KBUILD_MODNAME);
 	}
 
 	/*
-	 * Cannot use the contiguous physical memory.
-	 * Allocate mmio space for framebuffer.
+	 * Cannot use contiguous physical memory, so allocate MMIO space for
+	 * the framebuffer. At this point in the function, conflicting devices
+	 * that might have claimed the framebuffer MMIO space based on
+	 * screen_info.lfb_base must have already been removed so that
+	 * vmbus_allocate_mmio() does not allocate different MMIO space. If the
+	 * kdump image were to be loaded using kexec_file_load(), the
+	 * framebuffer location in the kdump image would be set from
+	 * screen_info.lfb_base at the time that kdump is enabled. If the
+	 * framebuffer has moved elsewhere, this could be the wrong location,
+	 * causing kdump to hang when efifb (for example) loads.
 	 */
 	dio_fb_size =
 		screen_width * screen_height * screen_depth / 8;
@@ -1051,11 +1076,6 @@ static int hvfb_getmem(struct hv_device *hdev, struct fb_info *info)
 	info->screen_size = dio_fb_size;
 
 getmem_done:
-	if (base && size)
-		aperture_remove_conflicting_devices(base, size, KBUILD_MODNAME);
-	else
-		aperture_remove_all_conflicting_devices(KBUILD_MODNAME);
-
 	if (!gen2vm)
 		pci_dev_put(pdev);
 
@@ -1074,16 +1094,16 @@ err1:
 }
 
 /* Release the framebuffer */
-static void hvfb_putmem(struct hv_device *hdev, struct fb_info *info)
+static void hvfb_putmem(struct fb_info *info)
 {
 	struct hvfb_par *par = info->par;
 
 	if (par->need_docopy) {
 		vfree(par->dio_vp);
-		iounmap(info->screen_base);
+		iounmap(par->mmio_vp);
 		vmbus_free_mmio(par->mem->start, screen_fb_size);
 	} else {
-		hvfb_release_phymem(hdev, info->fix.smem_start,
+		hvfb_release_phymem(info->device, info->fix.smem_start,
 				    screen_fb_size);
 	}
 
@@ -1172,7 +1192,7 @@ static int hvfb_probe(struct hv_device *hdev,
 	if (ret)
 		goto error;
 
-	ret = register_framebuffer(info);
+	ret = devm_register_framebuffer(&hdev->device, info);
 	if (ret) {
 		pr_err("Unable to register framebuffer\n");
 		goto error;
@@ -1197,7 +1217,7 @@ static int hvfb_probe(struct hv_device *hdev,
 
 error:
 	fb_deferred_io_cleanup(info);
-	hvfb_putmem(hdev, info);
+	hvfb_putmem(info);
 error2:
 	vmbus_close(hdev->channel);
 error1:
@@ -1220,14 +1240,10 @@ static void hvfb_remove(struct hv_device *hdev)
 
 	fb_deferred_io_cleanup(info);
 
-	unregister_framebuffer(info);
 	cancel_delayed_work_sync(&par->dwork);
 
 	vmbus_close(hdev->channel);
 	hv_set_drvdata(hdev, NULL);
-
-	hvfb_putmem(hdev, info);
-	framebuffer_release(info);
 }
 
 static int hvfb_suspend(struct hv_device *hdev)
diff --git a/drivers/video/fbdev/imxfb.c b/drivers/video/fbdev/imxfb.c
index ff343e4ed35b..c0bdfb10f681 100644
--- a/drivers/video/fbdev/imxfb.c
+++ b/drivers/video/fbdev/imxfb.c
@@ -1007,8 +1007,13 @@ static int imxfb_probe(struct platform_device *pdev)
 	info->fix.smem_start = fbi->map_dma;
 
 	INIT_LIST_HEAD(&info->modelist);
-	for (i = 0; i < fbi->num_modes; i++)
-		fb_add_videomode(&fbi->mode[i].mode, &info->modelist);
+	for (i = 0; i < fbi->num_modes; i++) {
+		ret = fb_add_videomode(&fbi->mode[i].mode, &info->modelist);
+		if (ret) {
+			dev_err(&pdev->dev, "Failed to add videomode\n");
+			goto failed_cmap;
+		}
+	}
 
 	/*
 	 * This makes sure that our colour bitfield
diff --git a/drivers/video/fbdev/omap/lcd_dma.c b/drivers/video/fbdev/omap/lcd_dma.c
index f85817635a8c..0da23c57e475 100644
--- a/drivers/video/fbdev/omap/lcd_dma.c
+++ b/drivers/video/fbdev/omap/lcd_dma.c
@@ -432,8 +432,8 @@ static int __init omap_init_lcd_dma(void)
 
 	spin_lock_init(&lcd_dma.lock);
 
-	r = request_irq(INT_DMA_LCD, lcd_dma_irq_handler, 0,
-			"LCD DMA", NULL);
+	r = request_threaded_irq(INT_DMA_LCD, NULL, lcd_dma_irq_handler,
+				 IRQF_ONESHOT, "LCD DMA", NULL);
 	if (r != 0)
 		pr_err("unable to request IRQ for LCD DMA (error %d)\n", r);
 
diff --git a/drivers/video/fbdev/omap2/omapfb/dss/dispc.c b/drivers/video/fbdev/omap2/omapfb/dss/dispc.c
index 5832485ab998..c29b6236952b 100644
--- a/drivers/video/fbdev/omap2/omapfb/dss/dispc.c
+++ b/drivers/video/fbdev/omap2/omapfb/dss/dispc.c
@@ -2749,9 +2749,13 @@ int dispc_ovl_setup(enum omap_plane plane, const struct omap_overlay_info *oi,
 		bool mem_to_mem)
 {
 	int r;
-	enum omap_overlay_caps caps = dss_feat_get_overlay_caps(plane);
+	enum omap_overlay_caps caps;
 	enum omap_channel channel;
 
+	if (plane == OMAP_DSS_WB)
+		return -EINVAL;
+
+	caps = dss_feat_get_overlay_caps(plane);
 	channel = dispc_ovl_get_channel_out(plane);
 
 	DSSDBG("dispc_ovl_setup %d, pa %pad, pa_uv %pad, sw %d, %d,%d, %dx%d ->"
diff --git a/drivers/video/fbdev/omap2/omapfb/dss/dss-of.c b/drivers/video/fbdev/omap2/omapfb/dss/dss-of.c
index d5a43b3bf45e..c46108a16a9d 100644
--- a/drivers/video/fbdev/omap2/omapfb/dss/dss-of.c
+++ b/drivers/video/fbdev/omap2/omapfb/dss/dss-of.c
@@ -102,6 +102,7 @@ struct device_node *dss_of_port_get_parent_device(struct device_node *port)
 		np = of_get_next_parent(np);
 	}
 
+	of_node_put(np);
 	return NULL;
 }
 
diff --git a/drivers/video/fbdev/sm501fb.c b/drivers/video/fbdev/sm501fb.c
index 86ecbb2d86db..2eb27ebf822e 100644
--- a/drivers/video/fbdev/sm501fb.c
+++ b/drivers/video/fbdev/sm501fb.c
@@ -326,6 +326,13 @@ static int sm501fb_check_var(struct fb_var_screeninfo *var,
 	if (var->xres_virtual > 4096 || var->yres_virtual > 2048)
 		return -EINVAL;
 
+	/* geometry sanity checks */
+	if (var->xres + var->xoffset > var->xres_virtual)
+		return -EINVAL;
+
+	if (var->yres + var->yoffset > var->yres_virtual)
+		return -EINVAL;
+
 	/* can cope with 8,16 or 32bpp */
 
 	if (var->bits_per_pixel <= 8)
diff --git a/drivers/video/screen_info_pci.c b/drivers/video/screen_info_pci.c
index 6c5833517141..66bfc1d0a6dc 100644
--- a/drivers/video/screen_info_pci.c
+++ b/drivers/video/screen_info_pci.c
@@ -7,8 +7,8 @@
 
 static struct pci_dev *screen_info_lfb_pdev;
 static size_t screen_info_lfb_bar;
-static resource_size_t screen_info_lfb_offset;
-static struct resource screen_info_lfb_res = DEFINE_RES_MEM(0, 0);
+static resource_size_t screen_info_lfb_res_start; // original start of resource
+static resource_size_t screen_info_lfb_offset; // framebuffer offset within resource
 
 static bool __screen_info_relocation_is_valid(const struct screen_info *si, struct resource *pr)
 {
@@ -31,7 +31,7 @@ void screen_info_apply_fixups(void)
 	if (screen_info_lfb_pdev) {
 		struct resource *pr = &screen_info_lfb_pdev->resource[screen_info_lfb_bar];
 
-		if (pr->start != screen_info_lfb_res.start) {
+		if (pr->start != screen_info_lfb_res_start) {
 			if (__screen_info_relocation_is_valid(si, pr)) {
 				/*
 				 * Only update base if we have an actual
@@ -47,46 +47,67 @@ void screen_info_apply_fixups(void)
 	}
 }
 
+static int __screen_info_lfb_pci_bus_region(const struct screen_info *si, unsigned int type,
+					    struct pci_bus_region *r)
+{
+	u64 base, size;
+
+	base = __screen_info_lfb_base(si);
+	if (!base)
+		return -EINVAL;
+
+	size = __screen_info_lfb_size(si, type);
+	if (!size)
+		return -EINVAL;
+
+	r->start = base;
+	r->end = base + size - 1;
+
+	return 0;
+}
+
 static void screen_info_fixup_lfb(struct pci_dev *pdev)
 {
 	unsigned int type;
-	struct resource res[SCREEN_INFO_MAX_RESOURCES];
-	size_t i, numres;
+	struct pci_bus_region bus_region;
 	int ret;
+	struct resource r = {
+		.flags = IORESOURCE_MEM,
+	};
+	const struct resource *pr;
 	const struct screen_info *si = &screen_info;
 
 	if (screen_info_lfb_pdev)
 		return; // already found
 
 	type = screen_info_video_type(si);
-	if (type != VIDEO_TYPE_EFI)
-		return; // only applies to EFI
+	if (!__screen_info_has_lfb(type))
+		return; // only applies to EFI; maybe VESA
 
-	ret = screen_info_resources(si, res, ARRAY_SIZE(res));
+	ret = __screen_info_lfb_pci_bus_region(si, type, &bus_region);
 	if (ret < 0)
 		return;
-	numres = ret;
 
-	for (i = 0; i < numres; ++i) {
-		struct resource *r = &res[i];
-		const struct resource *pr;
-
-		if (!(r->flags & IORESOURCE_MEM))
-			continue;
-		pr = pci_find_resource(pdev, r);
-		if (!pr)
-			continue;
-
-		/*
-		 * We've found a PCI device with the framebuffer
-		 * resource. Store away the parameters to track
-		 * relocation of the framebuffer aperture.
-		 */
-		screen_info_lfb_pdev = pdev;
-		screen_info_lfb_bar = pr - pdev->resource;
-		screen_info_lfb_offset = r->start - pr->start;
-		memcpy(&screen_info_lfb_res, r, sizeof(screen_info_lfb_res));
-	}
+	/*
+	 * Translate the PCI bus address to resource. Account
+	 * for an offset if the framebuffer is behind a PCI host
+	 * bridge.
+	 */
+	pcibios_bus_to_resource(pdev->bus, &r, &bus_region);
+
+	pr = pci_find_resource(pdev, &r);
+	if (!pr)
+		return;
+
+	/*
+	 * We've found a PCI device with the framebuffer
+	 * resource. Store away the parameters to track
+	 * relocation of the framebuffer aperture.
+	 */
+	screen_info_lfb_pdev = pdev;
+	screen_info_lfb_bar = pr - pdev->resource;
+	screen_info_lfb_offset = r.start - pr->start;
+	screen_info_lfb_res_start = bus_region.start;
 }
 DECLARE_PCI_FIXUP_CLASS_HEADER(PCI_ANY_ID, PCI_ANY_ID, PCI_BASE_CLASS_DISPLAY, 16,
 			       screen_info_fixup_lfb);
diff --git a/drivers/virt/acrn/hsm.c b/drivers/virt/acrn/hsm.c
index c24036c4e51e..e4e196abdaac 100644
--- a/drivers/virt/acrn/hsm.c
+++ b/drivers/virt/acrn/hsm.c
@@ -49,7 +49,7 @@ static int pmcmd_ioctl(u64 cmd, void __user *uptr)
 	switch (cmd & PMCMD_TYPE_MASK) {
 	case ACRN_PMCMD_GET_PX_CNT:
 	case ACRN_PMCMD_GET_CX_CNT:
-		pm_info = kmalloc(sizeof(u64), GFP_KERNEL);
+		pm_info = kzalloc(sizeof(u64), GFP_KERNEL);
 		if (!pm_info)
 			return -ENOMEM;
 
@@ -64,7 +64,7 @@ static int pmcmd_ioctl(u64 cmd, void __user *uptr)
 		kfree(pm_info);
 		break;
 	case ACRN_PMCMD_GET_PX_DATA:
-		px_data = kmalloc(sizeof(*px_data), GFP_KERNEL);
+		px_data = kzalloc(sizeof(*px_data), GFP_KERNEL);
 		if (!px_data)
 			return -ENOMEM;
 
@@ -79,7 +79,7 @@ static int pmcmd_ioctl(u64 cmd, void __user *uptr)
 		kfree(px_data);
 		break;
 	case ACRN_PMCMD_GET_CX_DATA:
-		cx_data = kmalloc(sizeof(*cx_data), GFP_KERNEL);
+		cx_data = kzalloc(sizeof(*cx_data), GFP_KERNEL);
 		if (!cx_data)
 			return -ENOMEM;
 
diff --git a/drivers/virt/coco/efi_secret/efi_secret.c b/drivers/virt/coco/efi_secret/efi_secret.c
index cd29e66b1543..8482be108e82 100644
--- a/drivers/virt/coco/efi_secret/efi_secret.c
+++ b/drivers/virt/coco/efi_secret/efi_secret.c
@@ -136,15 +136,7 @@ static int efi_secret_unlink(struct inode *dir, struct dentry *dentry)
 		if (s->fs_files[i] == dentry)
 			s->fs_files[i] = NULL;
 
-	/*
-	 * securityfs_remove tries to lock the directory's inode, but we reach
-	 * the unlink callback when it's already locked
-	 */
-	inode_unlock(dir);
-	securityfs_remove(dentry);
-	inode_lock(dir);
-
-	return 0;
+	return simple_unlink(inode, dentry);
 }
 
 static const struct inode_operations efi_secret_dir_inode_operations = {
diff --git a/drivers/virt/coco/tsm.c b/drivers/virt/coco/tsm.c
index 9432d4e303f1..8a638bc34d4a 100644
--- a/drivers/virt/coco/tsm.c
+++ b/drivers/virt/coco/tsm.c
@@ -15,6 +15,7 @@
 static struct tsm_provider {
 	const struct tsm_ops *ops;
 	void *data;
+	atomic_t count;
 } provider;
 static DECLARE_RWSEM(tsm_rwsem);
 
@@ -92,6 +93,10 @@ static ssize_t tsm_report_privlevel_store(struct config_item *cfg,
 	if (rc)
 		return rc;
 
+	guard(rwsem_write)(&tsm_rwsem);
+	if (!provider.ops)
+		return -ENXIO;
+
 	/*
 	 * The valid privilege levels that a TSM might accept, if it accepts a
 	 * privilege level setting at all, are a max of TSM_PRIVLEVEL_MAX (see
@@ -101,7 +106,6 @@ static ssize_t tsm_report_privlevel_store(struct config_item *cfg,
 	if (provider.ops->privlevel_floor > val || val > TSM_PRIVLEVEL_MAX)
 		return -EINVAL;
 
-	guard(rwsem_write)(&tsm_rwsem);
 	rc = try_advance_write_generation(report);
 	if (rc)
 		return rc;
@@ -115,6 +119,10 @@ static ssize_t tsm_report_privlevel_floor_show(struct config_item *cfg,
 					       char *buf)
 {
 	guard(rwsem_read)(&tsm_rwsem);
+
+	if (!provider.ops)
+		return -ENXIO;
+
 	return sysfs_emit(buf, "%u\n", provider.ops->privlevel_floor);
 }
 CONFIGFS_ATTR_RO(tsm_report_, privlevel_floor);
@@ -217,6 +225,9 @@ CONFIGFS_ATTR_RO(tsm_report_, generation);
 static ssize_t tsm_report_provider_show(struct config_item *cfg, char *buf)
 {
 	guard(rwsem_read)(&tsm_rwsem);
+	if (!provider.ops)
+		return -ENXIO;
+
 	return sysfs_emit(buf, "%s\n", provider.ops->name);
 }
 CONFIGFS_ATTR_RO(tsm_report_, provider);
@@ -284,7 +295,7 @@ static ssize_t tsm_report_read(struct tsm_report *report, void *buf,
 	guard(rwsem_write)(&tsm_rwsem);
 	ops = provider.ops;
 	if (!ops)
-		return -ENOTTY;
+		return -ENXIO;
 	if (!report->desc.inblob_len)
 		return -EINVAL;
 
@@ -421,12 +432,20 @@ static struct config_item *tsm_report_make_item(struct config_group *group,
 	if (!state)
 		return ERR_PTR(-ENOMEM);
 
+	atomic_inc(&provider.count);
 	config_item_init_type_name(&state->cfg, name, &tsm_report_type);
 	return &state->cfg;
 }
 
+static void tsm_report_drop_item(struct config_group *group, struct config_item *item)
+{
+	config_item_put(item);
+	atomic_dec(&provider.count);
+}
+
 static struct configfs_group_operations tsm_report_group_ops = {
 	.make_item = tsm_report_make_item,
+	.drop_item = tsm_report_drop_item,
 };
 
 static const struct config_item_type tsm_reports_type = {
@@ -459,6 +478,11 @@ int tsm_register(const struct tsm_ops *ops, void *priv)
 		return -EBUSY;
 	}
 
+	if (atomic_read(&provider.count)) {
+		pr_err("configfs/tsm/report not empty\n");
+		return -EBUSY;
+	}
+
 	provider.ops = ops;
 	provider.data = priv;
 	return 0;
@@ -470,6 +494,9 @@ int tsm_unregister(const struct tsm_ops *ops)
 	guard(rwsem_write)(&tsm_rwsem);
 	if (ops != provider.ops)
 		return -EBUSY;
+	if (atomic_read(&provider.count))
+		pr_warn("\"%s\" unregistered with items present in configfs/tsm/report\n",
+			provider.ops->name);
 	provider.ops = NULL;
 	provider.data = NULL;
 	return 0;
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index 0112742e4504..c0276979675d 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -2530,7 +2530,7 @@ bool virtqueue_enable_cb_delayed(struct virtqueue *_vq)
 	struct vring_virtqueue *vq = to_vvq(_vq);
 
 	if (vq->event_triggered)
-		vq->event_triggered = false;
+		data_race(vq->event_triggered = false);
 
 	return vq->packed_ring ? virtqueue_enable_cb_delayed_packed(_vq) :
 				 virtqueue_enable_cb_delayed_split(_vq);
@@ -2741,7 +2741,7 @@ int virtqueue_resize(struct virtqueue *_vq, u32 num,
 		     void (*recycle_done)(struct virtqueue *vq))
 {
 	struct vring_virtqueue *vq = to_vvq(_vq);
-	int err;
+	int err, err_reset;
 
 	if (num > vq->vq.num_max)
 		return -E2BIG;
@@ -2763,7 +2763,11 @@ int virtqueue_resize(struct virtqueue *_vq, u32 num,
 	else
 		err = virtqueue_resize_split(_vq, num);
 
-	return virtqueue_enable_after_reset(_vq);
+	err_reset = virtqueue_enable_after_reset(_vq);
+	if (err_reset)
+		return err_reset;
+
+	return err;
 }
 EXPORT_SYMBOL_GPL(virtqueue_resize);
 
@@ -2815,6 +2819,7 @@ EXPORT_SYMBOL_GPL(virtqueue_set_dma_premapped);
  * virtqueue_reset - detach and recycle all unused buffers
  * @_vq: the struct virtqueue we're talking about.
  * @recycle: callback to recycle unused buffers
+ * @recycle_done: callback to be invoked when recycle for all unused buffers done
  *
  * Caller must ensure we don't call this with other virtqueue operations
  * at the same time (except where noted).
@@ -2826,7 +2831,8 @@ EXPORT_SYMBOL_GPL(virtqueue_set_dma_premapped);
  * -EPERM: Operation not permitted
  */
 int virtqueue_reset(struct virtqueue *_vq,
-		    void (*recycle)(struct virtqueue *vq, void *buf))
+		    void (*recycle)(struct virtqueue *vq, void *buf),
+		    void (*recycle_done)(struct virtqueue *vq))
 {
 	struct vring_virtqueue *vq = to_vvq(_vq);
 	int err;
@@ -2834,6 +2840,8 @@ int virtqueue_reset(struct virtqueue *_vq,
 	err = virtqueue_disable_and_recycle(_vq, recycle);
 	if (err)
 		return err;
+	if (recycle_done)
+		recycle_done(_vq);
 
 	if (vq->packed_ring)
 		virtqueue_reinit_packed(vq);
diff --git a/drivers/w1/masters/w1-uart.c b/drivers/w1/masters/w1-uart.c
index a31782e56ba7..c87eea347806 100644
--- a/drivers/w1/masters/w1-uart.c
+++ b/drivers/w1/masters/w1-uart.c
@@ -372,11 +372,11 @@ static int w1_uart_probe(struct serdev_device *serdev)
 	init_completion(&w1dev->rx_byte_received);
 	mutex_init(&w1dev->rx_mutex);
 
+	serdev_device_set_drvdata(serdev, w1dev);
+	serdev_device_set_client_ops(serdev, &w1_uart_serdev_ops);
 	ret = w1_uart_serdev_open(w1dev);
 	if (ret < 0)
 		return ret;
-	serdev_device_set_drvdata(serdev, w1dev);
-	serdev_device_set_client_ops(serdev, &w1_uart_serdev_ops);
 
 	return w1_add_master_device(&w1dev->bus);
 }
diff --git a/drivers/watchdog/aspeed_wdt.c b/drivers/watchdog/aspeed_wdt.c
index b4773a6aaf8c..837e15701c0e 100644
--- a/drivers/watchdog/aspeed_wdt.c
+++ b/drivers/watchdog/aspeed_wdt.c
@@ -11,21 +11,30 @@
 #include <linux/io.h>
 #include <linux/kernel.h>
 #include <linux/kstrtox.h>
+#include <linux/mfd/syscon.h>
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/of_irq.h>
 #include <linux/platform_device.h>
+#include <linux/regmap.h>
 #include <linux/watchdog.h>
 
 static bool nowayout = WATCHDOG_NOWAYOUT;
 module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started (default="
 				__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
+struct aspeed_wdt_scu {
+	const char *compatible;
+	u32 reset_status_reg;
+	u32 wdt_reset_mask;
+	u32 wdt_reset_mask_shift;
+};
 
 struct aspeed_wdt_config {
 	u32 ext_pulse_width_mask;
 	u32 irq_shift;
 	u32 irq_mask;
+	struct aspeed_wdt_scu scu;
 };
 
 struct aspeed_wdt {
@@ -39,18 +48,36 @@ static const struct aspeed_wdt_config ast2400_config = {
 	.ext_pulse_width_mask = 0xff,
 	.irq_shift = 0,
 	.irq_mask = 0,
+	.scu = {
+		.compatible = "aspeed,ast2400-scu",
+		.reset_status_reg = 0x3c,
+		.wdt_reset_mask = 0x1,
+		.wdt_reset_mask_shift = 1,
+	},
 };
 
 static const struct aspeed_wdt_config ast2500_config = {
 	.ext_pulse_width_mask = 0xfffff,
 	.irq_shift = 12,
 	.irq_mask = GENMASK(31, 12),
+	.scu = {
+		.compatible = "aspeed,ast2500-scu",
+		.reset_status_reg = 0x3c,
+		.wdt_reset_mask = 0x1,
+		.wdt_reset_mask_shift = 2,
+	},
 };
 
 static const struct aspeed_wdt_config ast2600_config = {
 	.ext_pulse_width_mask = 0xfffff,
 	.irq_shift = 0,
 	.irq_mask = GENMASK(31, 10),
+	.scu = {
+		.compatible = "aspeed,ast2600-scu",
+		.reset_status_reg = 0x74,
+		.wdt_reset_mask = 0xf,
+		.wdt_reset_mask_shift = 16,
+	},
 };
 
 static const struct of_device_id aspeed_wdt_of_table[] = {
@@ -213,6 +240,56 @@ static int aspeed_wdt_restart(struct watchdog_device *wdd,
 	return 0;
 }
 
+static void aspeed_wdt_update_bootstatus(struct platform_device *pdev,
+					 struct aspeed_wdt *wdt)
+{
+	const struct resource *res;
+	struct aspeed_wdt_scu scu = wdt->cfg->scu;
+	struct regmap *scu_base;
+	u32 reset_mask_width;
+	u32 reset_mask_shift;
+	u32 idx = 0;
+	u32 status;
+	int ret;
+
+	if (!of_device_is_compatible(pdev->dev.of_node, "aspeed,ast2400-wdt")) {
+		res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+		idx = ((intptr_t)wdt->base & 0x00000fff) / (uintptr_t)resource_size(res);
+	}
+
+	scu_base = syscon_regmap_lookup_by_compatible(scu.compatible);
+	if (IS_ERR(scu_base)) {
+		wdt->wdd.bootstatus = WDIOS_UNKNOWN;
+		return;
+	}
+
+	ret = regmap_read(scu_base, scu.reset_status_reg, &status);
+	if (ret) {
+		wdt->wdd.bootstatus = WDIOS_UNKNOWN;
+		return;
+	}
+
+	reset_mask_width = hweight32(scu.wdt_reset_mask);
+	reset_mask_shift = scu.wdt_reset_mask_shift +
+			   reset_mask_width * idx;
+
+	if (status & (scu.wdt_reset_mask << reset_mask_shift))
+		wdt->wdd.bootstatus = WDIOF_CARDRESET;
+
+	/* clear wdt reset event flag */
+	if (of_device_is_compatible(pdev->dev.of_node, "aspeed,ast2400-wdt") ||
+	    of_device_is_compatible(pdev->dev.of_node, "aspeed,ast2500-wdt")) {
+		ret = regmap_read(scu_base, scu.reset_status_reg, &status);
+		if (!ret) {
+			status &= ~(scu.wdt_reset_mask << reset_mask_shift);
+			regmap_write(scu_base, scu.reset_status_reg, status);
+		}
+	} else {
+		regmap_write(scu_base, scu.reset_status_reg,
+			     scu.wdt_reset_mask << reset_mask_shift);
+	}
+}
+
 /* access_cs0 shows if cs0 is accessible, hence the reverted bit */
 static ssize_t access_cs0_show(struct device *dev,
 			       struct device_attribute *attr, char *buf)
@@ -458,10 +535,10 @@ static int aspeed_wdt_probe(struct platform_device *pdev)
 		writel(duration - 1, wdt->base + WDT_RESET_WIDTH);
 	}
 
+	aspeed_wdt_update_bootstatus(pdev, wdt);
+
 	status = readl(wdt->base + WDT_TIMEOUT_STATUS);
 	if (status & WDT_TIMEOUT_STATUS_BOOT_SECONDARY) {
-		wdt->wdd.bootstatus = WDIOF_CARDRESET;
-
 		if (of_device_is_compatible(np, "aspeed,ast2400-wdt") ||
 		    of_device_is_compatible(np, "aspeed,ast2500-wdt"))
 			wdt->wdd.groups = bswitch_groups;
diff --git a/drivers/watchdog/da9052_wdt.c b/drivers/watchdog/da9052_wdt.c
index d708c091bf1b..180526220d8c 100644
--- a/drivers/watchdog/da9052_wdt.c
+++ b/drivers/watchdog/da9052_wdt.c
@@ -164,6 +164,7 @@ static int da9052_wdt_probe(struct platform_device *pdev)
 	da9052_wdt = &driver_data->wdt;
 
 	da9052_wdt->timeout = DA9052_DEF_TIMEOUT;
+	da9052_wdt->min_hw_heartbeat_ms = DA9052_TWDMIN;
 	da9052_wdt->info = &da9052_wdt_info;
 	da9052_wdt->ops = &da9052_wdt_ops;
 	da9052_wdt->parent = dev;
diff --git a/drivers/watchdog/dw_wdt.c b/drivers/watchdog/dw_wdt.c
index 84dca3695f86..e5e6d7f15918 100644
--- a/drivers/watchdog/dw_wdt.c
+++ b/drivers/watchdog/dw_wdt.c
@@ -644,6 +644,8 @@ static int dw_wdt_drv_probe(struct platform_device *pdev)
 	} else {
 		wdd->timeout = DW_WDT_DEFAULT_SECONDS;
 		watchdog_init_timeout(wdd, 0, dev);
+		/* Limit timeout value to hardware constraints. */
+		dw_wdt_set_timeout(wdd, wdd->timeout);
 	}
 
 	platform_set_drvdata(pdev, dw_wdt);
diff --git a/drivers/watchdog/exar_wdt.c b/drivers/watchdog/exar_wdt.c
index 7c61ff343271..c2e3bb08df89 100644
--- a/drivers/watchdog/exar_wdt.c
+++ b/drivers/watchdog/exar_wdt.c
@@ -221,7 +221,7 @@ static const struct watchdog_info exar_wdt_info = {
 	.options	= WDIOF_KEEPALIVEPING |
 			  WDIOF_SETTIMEOUT |
 			  WDIOF_MAGICCLOSE,
-	.identity	= "Exar/MaxLinear XR28V38x Watchdog",
+	.identity	= "Exar XR28V38x Watchdog",
 };
 
 static const struct watchdog_ops exar_wdt_ops = {
diff --git a/drivers/watchdog/iTCO_wdt.c b/drivers/watchdog/iTCO_wdt.c
index f01ed38aba67..d5c91759dc00 100644
--- a/drivers/watchdog/iTCO_wdt.c
+++ b/drivers/watchdog/iTCO_wdt.c
@@ -601,7 +601,11 @@ static int iTCO_wdt_probe(struct platform_device *pdev)
 	/* Check that the heartbeat value is within it's range;
 	   if not reset to the default */
 	if (iTCO_wdt_set_timeout(&p->wddev, heartbeat)) {
-		iTCO_wdt_set_timeout(&p->wddev, WATCHDOG_TIMEOUT);
+		ret = iTCO_wdt_set_timeout(&p->wddev, WATCHDOG_TIMEOUT);
+		if (ret != 0) {
+			dev_err(dev, "Failed to set watchdog timeout (%d)\n", WATCHDOG_TIMEOUT);
+			return ret;
+		}
 		dev_info(dev, "timeout value out of range, using %d\n",
 			WATCHDOG_TIMEOUT);
 	}
diff --git a/drivers/watchdog/rti_wdt.c b/drivers/watchdog/rti_wdt.c
index 563d842014df..cc239251e193 100644
--- a/drivers/watchdog/rti_wdt.c
+++ b/drivers/watchdog/rti_wdt.c
@@ -301,6 +301,7 @@ static int rti_wdt_probe(struct platform_device *pdev)
 	node = of_parse_phandle(pdev->dev.of_node, "memory-region", 0);
 	if (node) {
 		ret = of_address_to_resource(node, 0, &res);
+		of_node_put(node);
 		if (ret) {
 			dev_err(dev, "No memory address assigned to the region.\n");
 			goto err_iomap;
diff --git a/drivers/watchdog/sbsa_gwdt.c b/drivers/watchdog/sbsa_gwdt.c
index 5f23913ce3b4..6ce1bfb39064 100644
--- a/drivers/watchdog/sbsa_gwdt.c
+++ b/drivers/watchdog/sbsa_gwdt.c
@@ -75,11 +75,17 @@
 #define SBSA_GWDT_VERSION_MASK  0xF
 #define SBSA_GWDT_VERSION_SHIFT 16
 
+#define SBSA_GWDT_IMPL_MASK	0x7FF
+#define SBSA_GWDT_IMPL_SHIFT	0
+#define SBSA_GWDT_IMPL_MEDIATEK	0x426
+
 /**
  * struct sbsa_gwdt - Internal representation of the SBSA GWDT
  * @wdd:		kernel watchdog_device structure
  * @clk:		store the System Counter clock frequency, in Hz.
  * @version:            store the architecture version
+ * @need_ws0_race_workaround:
+ *			indicate whether to adjust wdd->timeout to avoid a race with WS0
  * @refresh_base:	Virtual address of the watchdog refresh frame
  * @control_base:	Virtual address of the watchdog control frame
  */
@@ -87,6 +93,7 @@ struct sbsa_gwdt {
 	struct watchdog_device	wdd;
 	u32			clk;
 	int			version;
+	bool			need_ws0_race_workaround;
 	void __iomem		*refresh_base;
 	void __iomem		*control_base;
 };
@@ -161,6 +168,31 @@ static int sbsa_gwdt_set_timeout(struct watchdog_device *wdd,
 		 */
 		sbsa_gwdt_reg_write(((u64)gwdt->clk / 2) * timeout, gwdt);
 
+	/*
+	 * Some watchdog hardware has a race condition where it will ignore
+	 * sbsa_gwdt_keepalive() if it is called at the exact moment that a
+	 * timeout occurs and WS0 is being asserted. Unfortunately, the default
+	 * behavior of the watchdog core is very likely to trigger this race
+	 * when action=0 because it programs WOR to be half of the desired
+	 * timeout, and watchdog_next_keepalive() chooses the exact same time to
+	 * send keepalive pings.
+	 *
+	 * This triggers a race where sbsa_gwdt_keepalive() can be called right
+	 * as WS0 is being asserted, and affected hardware will ignore that
+	 * write and continue to assert WS0. After another (timeout / 2)
+	 * seconds, the same race happens again. If the driver wins then the
+	 * explicit refresh will reset WS0 to false but if the hardware wins,
+	 * then WS1 is asserted and the system resets.
+	 *
+	 * Avoid the problem by scheduling keepalive heartbeats one second later
+	 * than the WOR timeout.
+	 *
+	 * This workaround might not be needed in a future revision of the
+	 * hardware.
+	 */
+	if (gwdt->need_ws0_race_workaround)
+		wdd->min_hw_heartbeat_ms = timeout * 500 + 1000;
+
 	return 0;
 }
 
@@ -202,12 +234,15 @@ static int sbsa_gwdt_keepalive(struct watchdog_device *wdd)
 static void sbsa_gwdt_get_version(struct watchdog_device *wdd)
 {
 	struct sbsa_gwdt *gwdt = watchdog_get_drvdata(wdd);
-	int ver;
+	int iidr, ver, impl;
 
-	ver = readl(gwdt->control_base + SBSA_GWDT_W_IIDR);
-	ver = (ver >> SBSA_GWDT_VERSION_SHIFT) & SBSA_GWDT_VERSION_MASK;
+	iidr = readl(gwdt->control_base + SBSA_GWDT_W_IIDR);
+	ver = (iidr >> SBSA_GWDT_VERSION_SHIFT) & SBSA_GWDT_VERSION_MASK;
+	impl = (iidr >> SBSA_GWDT_IMPL_SHIFT) & SBSA_GWDT_IMPL_MASK;
 
 	gwdt->version = ver;
+	gwdt->need_ws0_race_workaround =
+		!action && (impl == SBSA_GWDT_IMPL_MEDIATEK);
 }
 
 static int sbsa_gwdt_start(struct watchdog_device *wdd)
@@ -299,6 +334,15 @@ static int sbsa_gwdt_probe(struct platform_device *pdev)
 	else
 		wdd->max_hw_heartbeat_ms = GENMASK_ULL(47, 0) / gwdt->clk * 1000;
 
+	if (gwdt->need_ws0_race_workaround) {
+		/*
+		 * A timeout of 3 seconds means that WOR will be set to 1.5
+		 * seconds and the heartbeat will be scheduled every 2.5
+		 * seconds.
+		 */
+		wdd->min_timeout = 3;
+	}
+
 	status = readl(cf_base + SBSA_GWDT_WCS);
 	if (status & SBSA_GWDT_WCS_WS1) {
 		dev_warn(dev, "System reset by WDT.\n");
diff --git a/drivers/watchdog/ziirave_wdt.c b/drivers/watchdog/ziirave_wdt.c
index 775838346bb5..09d6721c7bfa 100644
--- a/drivers/watchdog/ziirave_wdt.c
+++ b/drivers/watchdog/ziirave_wdt.c
@@ -302,6 +302,9 @@ static int ziirave_firm_verify(struct watchdog_device *wdd,
 		const u16 len = be16_to_cpu(rec->len);
 		const u32 addr = be32_to_cpu(rec->addr);
 
+		if (len > sizeof(data))
+			return -EINVAL;
+
 		if (ziirave_firm_addr_readonly(addr))
 			continue;
 
diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig
index f7d6f47971fd..24f485827e03 100644
--- a/drivers/xen/Kconfig
+++ b/drivers/xen/Kconfig
@@ -278,7 +278,7 @@ config XEN_PRIVCMD_EVENTFD
 
 config XEN_ACPI_PROCESSOR
 	tristate "Xen ACPI processor"
-	depends on XEN && XEN_PV_DOM0 && X86 && ACPI_PROCESSOR && CPU_FREQ
+	depends on XEN && XEN_DOM0 && X86 && ACPI_PROCESSOR && CPU_FREQ
 	default m
 	help
 	  This ACPI processor uploads Power Management information to the Xen
diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c
index 528395133b4f..e47bb157aa09 100644
--- a/drivers/xen/balloon.c
+++ b/drivers/xen/balloon.c
@@ -675,7 +675,7 @@ void xen_free_ballooned_pages(unsigned int nr_pages, struct page **pages)
 }
 EXPORT_SYMBOL(xen_free_ballooned_pages);
 
-static void __init balloon_add_regions(void)
+static int __init balloon_add_regions(void)
 {
 	unsigned long start_pfn, pages;
 	unsigned long pfn, extra_pfn_end;
@@ -698,26 +698,41 @@ static void __init balloon_add_regions(void)
 		for (pfn = start_pfn; pfn < extra_pfn_end; pfn++)
 			balloon_append(pfn_to_page(pfn));
 
-		balloon_stats.total_pages += extra_pfn_end - start_pfn;
+		/*
+		 * Extra regions are accounted for in the physmap, but need
+		 * decreasing from current_pages and target_pages to balloon
+		 * down the initial allocation, because they are already
+		 * accounted for in total_pages.
+		 */
+		pages = extra_pfn_end - start_pfn;
+		if (pages >= balloon_stats.current_pages ||
+		    pages >= balloon_stats.target_pages) {
+			WARN(1, "Extra pages underflow current target");
+			return -ERANGE;
+		}
+		balloon_stats.current_pages -= pages;
+		balloon_stats.target_pages -= pages;
 	}
+
+	return 0;
 }
 
 static int __init balloon_init(void)
 {
 	struct task_struct *task;
+	int rc;
 
 	if (!xen_domain())
 		return -ENODEV;
 
 	pr_info("Initialising balloon driver\n");
 
-#ifdef CONFIG_XEN_PV
-	balloon_stats.current_pages = xen_pv_domain()
-		? min(xen_start_info->nr_pages - xen_released_pages, max_pfn)
-		: get_num_physpages();
-#else
-	balloon_stats.current_pages = get_num_physpages();
-#endif
+	if (xen_released_pages >= get_num_physpages()) {
+		WARN(1, "Released pages underflow current target");
+		return -ERANGE;
+	}
+
+	balloon_stats.current_pages = get_num_physpages() - xen_released_pages;
 	balloon_stats.target_pages  = balloon_stats.current_pages;
 	balloon_stats.balloon_low   = 0;
 	balloon_stats.balloon_high  = 0;
@@ -734,7 +749,9 @@ static int __init balloon_init(void)
 	register_sysctl_init("xen/balloon", balloon_table);
 #endif
 
-	balloon_add_regions();
+	rc = balloon_add_regions();
+	if (rc)
+		return rc;
 
 	task = kthread_run(balloon_thread, NULL, "xen-balloon");
 	if (IS_ERR(task)) {
diff --git a/drivers/xen/gntdev-common.h b/drivers/xen/gntdev-common.h
index 9c286b2a1900..ac8ce3179ba2 100644
--- a/drivers/xen/gntdev-common.h
+++ b/drivers/xen/gntdev-common.h
@@ -26,6 +26,10 @@ struct gntdev_priv {
 	/* lock protects maps and freeable_maps. */
 	struct mutex lock;
 
+	/* Free instances of struct gntdev_copy_batch. */
+	struct gntdev_copy_batch *batch;
+	struct mutex batch_lock;
+
 #ifdef CONFIG_XEN_GRANT_DMA_ALLOC
 	/* Device for which DMA memory is allocated. */
 	struct device *dma_dev;
diff --git a/drivers/xen/gntdev-dmabuf.c b/drivers/xen/gntdev-dmabuf.c
index 42adc2c1e06b..5ab973627d18 100644
--- a/drivers/xen/gntdev-dmabuf.c
+++ b/drivers/xen/gntdev-dmabuf.c
@@ -357,8 +357,11 @@ struct gntdev_dmabuf_export_args {
 static int dmabuf_exp_from_pages(struct gntdev_dmabuf_export_args *args)
 {
 	DEFINE_DMA_BUF_EXPORT_INFO(exp_info);
-	struct gntdev_dmabuf *gntdev_dmabuf;
-	int ret;
+	struct gntdev_dmabuf *gntdev_dmabuf __free(kfree) = NULL;
+	CLASS(get_unused_fd, ret)(O_CLOEXEC);
+
+	if (ret < 0)
+		return ret;
 
 	gntdev_dmabuf = kzalloc(sizeof(*gntdev_dmabuf), GFP_KERNEL);
 	if (!gntdev_dmabuf)
@@ -383,32 +386,21 @@ static int dmabuf_exp_from_pages(struct gntdev_dmabuf_export_args *args)
 	exp_info.priv = gntdev_dmabuf;
 
 	gntdev_dmabuf->dmabuf = dma_buf_export(&exp_info);
-	if (IS_ERR(gntdev_dmabuf->dmabuf)) {
-		ret = PTR_ERR(gntdev_dmabuf->dmabuf);
-		gntdev_dmabuf->dmabuf = NULL;
-		goto fail;
-	}
-
-	ret = dma_buf_fd(gntdev_dmabuf->dmabuf, O_CLOEXEC);
-	if (ret < 0)
-		goto fail;
+	if (IS_ERR(gntdev_dmabuf->dmabuf))
+		return PTR_ERR(gntdev_dmabuf->dmabuf);
 
 	gntdev_dmabuf->fd = ret;
 	args->fd = ret;
 
 	pr_debug("Exporting DMA buffer with fd %d\n", ret);
 
+	get_file(gntdev_dmabuf->priv->filp);
 	mutex_lock(&args->dmabuf_priv->lock);
 	list_add(&gntdev_dmabuf->next, &args->dmabuf_priv->exp_list);
 	mutex_unlock(&args->dmabuf_priv->lock);
-	get_file(gntdev_dmabuf->priv->filp);
-	return 0;
 
-fail:
-	if (gntdev_dmabuf->dmabuf)
-		dma_buf_put(gntdev_dmabuf->dmabuf);
-	kfree(gntdev_dmabuf);
-	return ret;
+	fd_install(take_fd(ret), no_free_ptr(gntdev_dmabuf)->dmabuf->file);
+	return 0;
 }
 
 static struct gntdev_grant_map *
diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c
index 61faea1f0663..1f2160765618 100644
--- a/drivers/xen/gntdev.c
+++ b/drivers/xen/gntdev.c
@@ -56,6 +56,18 @@ MODULE_AUTHOR("Derek G. Murray <Derek.Murray@cl.cam.ac.uk>, "
 	      "Gerd Hoffmann <kraxel@redhat.com>");
 MODULE_DESCRIPTION("User-space granted page access driver");
 
+#define GNTDEV_COPY_BATCH 16
+
+struct gntdev_copy_batch {
+	struct gnttab_copy ops[GNTDEV_COPY_BATCH];
+	struct page *pages[GNTDEV_COPY_BATCH];
+	s16 __user *status[GNTDEV_COPY_BATCH];
+	unsigned int nr_ops;
+	unsigned int nr_pages;
+	bool writeable;
+	struct gntdev_copy_batch *next;
+};
+
 static unsigned int limit = 64*1024;
 module_param(limit, uint, 0644);
 MODULE_PARM_DESC(limit,
@@ -584,6 +596,8 @@ static int gntdev_open(struct inode *inode, struct file *flip)
 	INIT_LIST_HEAD(&priv->maps);
 	mutex_init(&priv->lock);
 
+	mutex_init(&priv->batch_lock);
+
 #ifdef CONFIG_XEN_GNTDEV_DMABUF
 	priv->dmabuf_priv = gntdev_dmabuf_init(flip);
 	if (IS_ERR(priv->dmabuf_priv)) {
@@ -608,6 +622,7 @@ static int gntdev_release(struct inode *inode, struct file *flip)
 {
 	struct gntdev_priv *priv = flip->private_data;
 	struct gntdev_grant_map *map;
+	struct gntdev_copy_batch *batch;
 
 	pr_debug("priv %p\n", priv);
 
@@ -620,6 +635,14 @@ static int gntdev_release(struct inode *inode, struct file *flip)
 	}
 	mutex_unlock(&priv->lock);
 
+	mutex_lock(&priv->batch_lock);
+	while (priv->batch) {
+		batch = priv->batch;
+		priv->batch = batch->next;
+		kfree(batch);
+	}
+	mutex_unlock(&priv->batch_lock);
+
 #ifdef CONFIG_XEN_GNTDEV_DMABUF
 	gntdev_dmabuf_fini(priv->dmabuf_priv);
 #endif
@@ -785,17 +808,6 @@ static long gntdev_ioctl_notify(struct gntdev_priv *priv, void __user *u)
 	return rc;
 }
 
-#define GNTDEV_COPY_BATCH 16
-
-struct gntdev_copy_batch {
-	struct gnttab_copy ops[GNTDEV_COPY_BATCH];
-	struct page *pages[GNTDEV_COPY_BATCH];
-	s16 __user *status[GNTDEV_COPY_BATCH];
-	unsigned int nr_ops;
-	unsigned int nr_pages;
-	bool writeable;
-};
-
 static int gntdev_get_page(struct gntdev_copy_batch *batch, void __user *virt,
 				unsigned long *gfn)
 {
@@ -953,36 +965,53 @@ static int gntdev_grant_copy_seg(struct gntdev_copy_batch *batch,
 static long gntdev_ioctl_grant_copy(struct gntdev_priv *priv, void __user *u)
 {
 	struct ioctl_gntdev_grant_copy copy;
-	struct gntdev_copy_batch batch;
+	struct gntdev_copy_batch *batch;
 	unsigned int i;
 	int ret = 0;
 
 	if (copy_from_user(&copy, u, sizeof(copy)))
 		return -EFAULT;
 
-	batch.nr_ops = 0;
-	batch.nr_pages = 0;
+	mutex_lock(&priv->batch_lock);
+	if (!priv->batch) {
+		batch = kmalloc(sizeof(*batch), GFP_KERNEL);
+	} else {
+		batch = priv->batch;
+		priv->batch = batch->next;
+	}
+	mutex_unlock(&priv->batch_lock);
+	if (!batch)
+		return -ENOMEM;
+
+	batch->nr_ops = 0;
+	batch->nr_pages = 0;
 
 	for (i = 0; i < copy.count; i++) {
 		struct gntdev_grant_copy_segment seg;
 
 		if (copy_from_user(&seg, &copy.segments[i], sizeof(seg))) {
 			ret = -EFAULT;
+			gntdev_put_pages(batch);
 			goto out;
 		}
 
-		ret = gntdev_grant_copy_seg(&batch, &seg, &copy.segments[i].status);
-		if (ret < 0)
+		ret = gntdev_grant_copy_seg(batch, &seg, &copy.segments[i].status);
+		if (ret < 0) {
+			gntdev_put_pages(batch);
 			goto out;
+		}
 
 		cond_resched();
 	}
-	if (batch.nr_ops)
-		ret = gntdev_copy(&batch);
-	return ret;
+	if (batch->nr_ops)
+		ret = gntdev_copy(batch);
+
+ out:
+	mutex_lock(&priv->batch_lock);
+	batch->next = priv->batch;
+	priv->batch = batch;
+	mutex_unlock(&priv->batch_lock);
 
-  out:
-	gntdev_put_pages(&batch);
 	return ret;
 }
 
diff --git a/drivers/xen/pci.c b/drivers/xen/pci.c
index 416f231809cb..bfe07adb3e3a 100644
--- a/drivers/xen/pci.c
+++ b/drivers/xen/pci.c
@@ -43,6 +43,18 @@ static int xen_add_device(struct device *dev)
 		pci_mcfg_reserved = true;
 	}
 #endif
+
+	if (pci_domain_nr(pci_dev->bus) >> 16) {
+		/*
+		 * The hypercall interface is limited to 16bit PCI segment
+		 * values, do not attempt to register devices with Xen in
+		 * segments greater or equal than 0x10000.
+		 */
+		dev_info(dev,
+			 "not registering with Xen: invalid PCI segment\n");
+		return 0;
+	}
+
 	if (pci_seg_supported) {
 		DEFINE_RAW_FLEX(struct physdev_pci_device_add, add, optarr, 1);
 
@@ -149,6 +161,16 @@ static int xen_remove_device(struct device *dev)
 	int r;
 	struct pci_dev *pci_dev = to_pci_dev(dev);
 
+	if (pci_domain_nr(pci_dev->bus) >> 16) {
+		/*
+		 * The hypercall interface is limited to 16bit PCI segment
+		 * values.
+		 */
+		dev_info(dev,
+			 "not unregistering with Xen: invalid PCI segment\n");
+		return 0;
+	}
+
 	if (pci_seg_supported) {
 		struct physdev_pci_device device = {
 			.seg = pci_domain_nr(pci_dev->bus),
@@ -182,6 +204,16 @@ int xen_reset_device(const struct pci_dev *dev)
 		.flags = PCI_DEVICE_RESET_FLR,
 	};
 
+	if (pci_domain_nr(dev->bus) >> 16) {
+		/*
+		 * The hypercall interface is limited to 16bit PCI segment
+		 * values.
+		 */
+		dev_info(&dev->dev,
+			 "unable to notify Xen of device reset: invalid PCI segment\n");
+		return 0;
+	}
+
 	return HYPERVISOR_physdev_op(PHYSDEVOP_pci_device_reset, &device);
 }
 EXPORT_SYMBOL_GPL(xen_reset_device);
diff --git a/drivers/xen/platform-pci.c b/drivers/xen/platform-pci.c
index 544d3f9010b9..1db82da56db6 100644
--- a/drivers/xen/platform-pci.c
+++ b/drivers/xen/platform-pci.c
@@ -26,6 +26,8 @@
 
 #define DRV_NAME    "xen-platform-pci"
 
+#define PCI_DEVICE_ID_XEN_PLATFORM_XS61	0x0002
+
 static unsigned long platform_mmio;
 static unsigned long platform_mmio_alloc;
 static unsigned long platform_mmiolen;
@@ -174,6 +176,8 @@ pci_out:
 static const struct pci_device_id platform_pci_tbl[] = {
 	{PCI_VENDOR_ID_XEN, PCI_DEVICE_ID_XEN_PLATFORM,
 		PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0},
+	{PCI_VENDOR_ID_XEN, PCI_DEVICE_ID_XEN_PLATFORM_XS61,
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0},
 	{0,}
 };
 
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index a337edcf8faf..ef56a2500ed6 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -74,19 +74,21 @@ static inline phys_addr_t xen_dma_to_phys(struct device *dev,
 	return xen_bus_to_phys(dev, dma_to_phys(dev, dma_addr));
 }
 
+static inline bool range_requires_alignment(phys_addr_t p, size_t size)
+{
+	phys_addr_t algn = 1ULL << (get_order(size) + PAGE_SHIFT);
+	phys_addr_t bus_addr = pfn_to_bfn(XEN_PFN_DOWN(p)) << XEN_PAGE_SHIFT;
+
+	return IS_ALIGNED(p, algn) && !IS_ALIGNED(bus_addr, algn);
+}
+
 static inline int range_straddles_page_boundary(phys_addr_t p, size_t size)
 {
 	unsigned long next_bfn, xen_pfn = XEN_PFN_DOWN(p);
 	unsigned int i, nr_pages = XEN_PFN_UP(xen_offset_in_page(p) + size);
-	phys_addr_t algn = 1ULL << (get_order(size) + PAGE_SHIFT);
 
 	next_bfn = pfn_to_bfn(xen_pfn);
 
-	/* If buffer is physically aligned, ensure DMA alignment. */
-	if (IS_ALIGNED(p, algn) &&
-	    !IS_ALIGNED((phys_addr_t)next_bfn << XEN_PAGE_SHIFT, algn))
-		return 1;
-
 	for (i = 1; i < nr_pages; i++)
 		if (pfn_to_bfn(++xen_pfn) != ++next_bfn)
 			return 1;
@@ -111,7 +113,7 @@ static struct io_tlb_pool *xen_swiotlb_find_pool(struct device *dev,
 }
 
 #ifdef CONFIG_X86
-int xen_swiotlb_fixup(void *buf, unsigned long nslabs)
+int __init xen_swiotlb_fixup(void *buf, unsigned long nslabs)
 {
 	int rc;
 	unsigned int order = get_order(IO_TLB_SEGSIZE << IO_TLB_SHIFT);
@@ -156,7 +158,8 @@ xen_swiotlb_alloc_coherent(struct device *dev, size_t size,
 
 	*dma_handle = xen_phys_to_dma(dev, phys);
 	if (*dma_handle + size - 1 > dma_mask ||
-	    range_straddles_page_boundary(phys, size)) {
+	    range_straddles_page_boundary(phys, size) ||
+	    range_requires_alignment(phys, size)) {
 		if (xen_create_contiguous_region(phys, order, fls64(dma_mask),
 				dma_handle) != 0)
 			goto out_free_pages;
@@ -182,7 +185,8 @@ xen_swiotlb_free_coherent(struct device *dev, size_t size, void *vaddr,
 	size = ALIGN(size, XEN_PAGE_SIZE);
 
 	if (WARN_ON_ONCE(dma_handle + size - 1 > dev->coherent_dma_mask) ||
-	    WARN_ON_ONCE(range_straddles_page_boundary(phys, size)))
+	    WARN_ON_ONCE(range_straddles_page_boundary(phys, size) ||
+			 range_requires_alignment(phys, size)))
 	    	return;
 
 	if (TestClearPageXenRemapped(virt_to_page(vaddr)))
@@ -213,6 +217,7 @@ static dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
 	 * buffering it.
 	 */
 	if (dma_capable(dev, dev_addr, size, true) &&
+	    !dma_kmalloc_needs_bounce(dev, size, dir) &&
 	    !range_straddles_page_boundary(phys, size) &&
 		!xen_arch_need_swiotlb(dev, phys, dev_addr) &&
 		!is_swiotlb_force_bounce(dev))
diff --git a/drivers/xen/xenbus/xenbus.h b/drivers/xen/xenbus/xenbus.h
index 13821e7e825e..9ac0427724a3 100644
--- a/drivers/xen/xenbus/xenbus.h
+++ b/drivers/xen/xenbus/xenbus.h
@@ -77,6 +77,7 @@ enum xb_req_state {
 struct xb_req_data {
 	struct list_head list;
 	wait_queue_head_t wq;
+	struct kref kref;
 	struct xsd_sockmsg msg;
 	uint32_t caller_req_id;
 	enum xsd_sockmsg_type type;
@@ -103,6 +104,7 @@ int xb_init_comms(void);
 void xb_deinit_comms(void);
 int xs_watch_msg(struct xs_watch_event *event);
 void xs_request_exit(struct xb_req_data *req);
+void xs_free_req(struct kref *kref);
 
 int xenbus_match(struct device *_dev, const struct device_driver *_drv);
 int xenbus_dev_probe(struct device *_dev);
diff --git a/drivers/xen/xenbus/xenbus_comms.c b/drivers/xen/xenbus/xenbus_comms.c
index e5fda0256feb..82df2da1b880 100644
--- a/drivers/xen/xenbus/xenbus_comms.c
+++ b/drivers/xen/xenbus/xenbus_comms.c
@@ -309,8 +309,8 @@ static int process_msg(void)
 			virt_wmb();
 			req->state = xb_req_state_got_reply;
 			req->cb(req);
-		} else
-			kfree(req);
+		}
+		kref_put(&req->kref, xs_free_req);
 	}
 
 	mutex_unlock(&xs_response_mutex);
@@ -386,14 +386,13 @@ static int process_writes(void)
 	state.req->msg.type = XS_ERROR;
 	state.req->err = err;
 	list_del(&state.req->list);
-	if (state.req->state == xb_req_state_aborted)
-		kfree(state.req);
-	else {
+	if (state.req->state != xb_req_state_aborted) {
 		/* write err, then update state */
 		virt_wmb();
 		state.req->state = xb_req_state_got_reply;
 		wake_up(&state.req->wq);
 	}
+	kref_put(&state.req->kref, xs_free_req);
 
 	mutex_unlock(&xb_write_mutex);
 
diff --git a/drivers/xen/xenbus/xenbus_dev_frontend.c b/drivers/xen/xenbus/xenbus_dev_frontend.c
index 46f8916597e5..f5c21ba64df5 100644
--- a/drivers/xen/xenbus/xenbus_dev_frontend.c
+++ b/drivers/xen/xenbus/xenbus_dev_frontend.c
@@ -406,7 +406,7 @@ void xenbus_dev_queue_reply(struct xb_req_data *req)
 	mutex_unlock(&u->reply_mutex);
 
 	kfree(req->body);
-	kfree(req);
+	kref_put(&req->kref, xs_free_req);
 
 	kref_put(&u->kref, xenbus_file_free);
 
diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c
index 6d32ffb01136..86fe6e779056 100644
--- a/drivers/xen/xenbus/xenbus_probe.c
+++ b/drivers/xen/xenbus/xenbus_probe.c
@@ -966,9 +966,15 @@ static int __init xenbus_init(void)
 	if (xen_pv_domain())
 		xen_store_domain_type = XS_PV;
 	if (xen_hvm_domain())
+	{
 		xen_store_domain_type = XS_HVM;
-	if (xen_hvm_domain() && xen_initial_domain())
-		xen_store_domain_type = XS_LOCAL;
+		err = hvm_get_parameter(HVM_PARAM_STORE_EVTCHN, &v);
+		if (err)
+			goto out_error;
+		xen_store_evtchn = (int)v;
+		if (!v && xen_initial_domain())
+			xen_store_domain_type = XS_LOCAL;
+	}
 	if (xen_pv_domain() && !xen_start_info->store_evtchn)
 		xen_store_domain_type = XS_LOCAL;
 	if (xen_pv_domain() && xen_start_info->store_evtchn)
@@ -987,10 +993,6 @@ static int __init xenbus_init(void)
 		xen_store_interface = gfn_to_virt(xen_store_gfn);
 		break;
 	case XS_HVM:
-		err = hvm_get_parameter(HVM_PARAM_STORE_EVTCHN, &v);
-		if (err)
-			goto out_error;
-		xen_store_evtchn = (int)v;
 		err = hvm_get_parameter(HVM_PARAM_STORE_PFN, &v);
 		if (err)
 			goto out_error;
diff --git a/drivers/xen/xenbus/xenbus_xs.c b/drivers/xen/xenbus/xenbus_xs.c
index d32c726f7a12..dcf9182c8451 100644
--- a/drivers/xen/xenbus/xenbus_xs.c
+++ b/drivers/xen/xenbus/xenbus_xs.c
@@ -112,6 +112,12 @@ static void xs_suspend_exit(void)
 	wake_up_all(&xs_state_enter_wq);
 }
 
+void xs_free_req(struct kref *kref)
+{
+	struct xb_req_data *req = container_of(kref, struct xb_req_data, kref);
+	kfree(req);
+}
+
 static uint32_t xs_request_enter(struct xb_req_data *req)
 {
 	uint32_t rq_id;
@@ -237,6 +243,12 @@ static void xs_send(struct xb_req_data *req, struct xsd_sockmsg *msg)
 	req->caller_req_id = req->msg.req_id;
 	req->msg.req_id = xs_request_enter(req);
 
+	/*
+	 * Take 2nd ref.  One for this thread, and the second for the
+	 * xenbus_thread.
+	 */
+	kref_get(&req->kref);
+
 	mutex_lock(&xb_write_mutex);
 	list_add_tail(&req->list, &xb_write_list);
 	notify = list_is_singular(&xb_write_list);
@@ -261,8 +273,8 @@ static void *xs_wait_for_reply(struct xb_req_data *req, struct xsd_sockmsg *msg)
 	if (req->state == xb_req_state_queued ||
 	    req->state == xb_req_state_wait_reply)
 		req->state = xb_req_state_aborted;
-	else
-		kfree(req);
+
+	kref_put(&req->kref, xs_free_req);
 	mutex_unlock(&xb_write_mutex);
 
 	return ret;
@@ -291,6 +303,7 @@ int xenbus_dev_request_and_reply(struct xsd_sockmsg *msg, void *par)
 	req->cb = xenbus_dev_queue_reply;
 	req->par = par;
 	req->user_req = true;
+	kref_init(&req->kref);
 
 	xs_send(req, msg);
 
@@ -319,6 +332,7 @@ static void *xs_talkv(struct xenbus_transaction t,
 	req->num_vecs = num_vecs;
 	req->cb = xs_wake_up;
 	req->user_req = false;
+	kref_init(&req->kref);
 
 	msg.req_id = 0;
 	msg.tx_id = t.id;
diff --git a/drivers/xen/xenfs/xensyms.c b/drivers/xen/xenfs/xensyms.c
index b799bc759c15..088b7f02c358 100644
--- a/drivers/xen/xenfs/xensyms.c
+++ b/drivers/xen/xenfs/xensyms.c
@@ -48,7 +48,7 @@ static int xensyms_next_sym(struct xensyms *xs)
 			return -ENOMEM;
 
 		set_xen_guest_handle(symdata->name, xs->name);
-		symdata->symnum--; /* Rewind */
+		symdata->symnum = symnum; /* Rewind */
 
 		ret = HYPERVISOR_platform_op(&xs->op);
 		if (ret < 0)
@@ -78,7 +78,7 @@ static void *xensyms_next(struct seq_file *m, void *p, loff_t *pos)
 {
 	struct xensyms *xs = m->private;
 
-	xs->op.u.symdata.symnum = ++(*pos);
+	*pos = xs->op.u.symdata.symnum;
 
 	if (xensyms_next_sym(xs))
 		return NULL;