Merge tag 'dmaengine-5.13-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/vkoul/dmaengine

Pull dmaengine updates from Vinod Koul:
 "New drivers/devices:

   - Support for QCOM SM8150 GPI DMA

  Updates:

   - Big pile of idxd updates including support for performance
     monitoring

   - Support in dw-edma for interleaved dma

   - Support for synchronize() in Xilinx driver"

* tag 'dmaengine-5.13-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/vkoul/dmaengine: (42 commits)
  dmaengine: idxd: Enable IDXD performance monitor support
  dmaengine: idxd: Add IDXD performance monitor support
  dmaengine: idxd: remove MSIX masking for interrupt handlers
  dmaengine: idxd: device cmd should use dedicated lock
  dmaengine: idxd: support reporting of halt interrupt
  dmaengine: idxd: enable SVA feature for IOMMU
  dmaengine: idxd: convert sprintf() to sysfs_emit() for all usages
  dmaengine: idxd: add interrupt handle request and release support
  dmaengine: idxd: add support for readonly config mode
  dmaengine: idxd: add percpu_ref to descriptor submission path
  dmaengine: idxd: remove detection of device type
  dmaengine: idxd: iax bus removal
  dmaengine: idxd: fix cdev setup and free device lifetime issues
  dmaengine: idxd: fix group conf_dev lifetime
  dmaengine: idxd: fix engine conf_dev lifetime
  dmaengine: idxd: fix wq conf_dev 'struct device' lifetime
  dmaengine: idxd: fix idxd conf_dev 'struct device' lifetime
  dmaengine: idxd: use ida for device instance enumeration
  dmaengine: idxd: removal of pcim managed mmio mapping
  dmaengine: idxd: cleanup pci interrupt vector allocation management
  ...

26 files changed, 2967 insertions, 1136 deletions

diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index a0836ffc22e0..6ab9d9a488a6 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -300,6 +300,18 @@ config INTEL_IDXD_SVM
 	depends on PCI_PASID
 	depends on PCI_IOV
 
+config INTEL_IDXD_PERFMON
+	bool "Intel Data Accelerators performance monitor support"
+	depends on INTEL_IDXD
+	help
+	  Enable performance monitor (pmu) support for the Intel(R)
+	  data accelerators present in Intel Xeon CPU.  With this
+	  enabled, perf can be used to monitor the DSA (Intel Data
+	  Streaming Accelerator) events described in the Intel DSA
+	  spec.
+
+	  If unsure, say N.
+
 config INTEL_IOATDMA
 	tristate "Intel I/OAT DMA support"
 	depends on PCI && X86_64
diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c
index fe45ad5d06c4..64a52bf4d737 100644
--- a/drivers/dma/at_xdmac.c
+++ b/drivers/dma/at_xdmac.c
@@ -344,17 +344,6 @@ static inline int at_xdmac_chan_is_paused(struct at_xdmac_chan *atchan)
 	return test_bit(AT_XDMAC_CHAN_IS_PAUSED, &atchan->status);
 }
 
-static inline int at_xdmac_csize(u32 maxburst)
-{
-	int csize;
-
-	csize = ffs(maxburst) - 1;
-	if (csize > 4)
-		csize = -EINVAL;
-
-	return csize;
-};
-
 static inline bool at_xdmac_chan_is_peripheral_xfer(u32 cfg)
 {
 	return cfg & AT_XDMAC_CC_TYPE_PER_TRAN;
diff --git a/drivers/dma/dw-edma/dw-edma-core.c b/drivers/dma/dw-edma/dw-edma-core.c
index 08d71dafa001..53289927dd0d 100644
--- a/drivers/dma/dw-edma/dw-edma-core.c
+++ b/drivers/dma/dw-edma/dw-edma-core.c
@@ -81,8 +81,13 @@ static struct dw_edma_chunk *dw_edma_alloc_chunk(struct dw_edma_desc *desc)
 	 *  - Even chunks originate CB equal to 1
 	 */
 	chunk->cb = !(desc->chunks_alloc % 2);
-	chunk->ll_region.paddr = dw->ll_region.paddr + chan->ll_off;
-	chunk->ll_region.vaddr = dw->ll_region.vaddr + chan->ll_off;
+	if (chan->dir == EDMA_DIR_WRITE) {
+		chunk->ll_region.paddr = dw->ll_region_wr[chan->id].paddr;
+		chunk->ll_region.vaddr = dw->ll_region_wr[chan->id].vaddr;
+	} else {
+		chunk->ll_region.paddr = dw->ll_region_rd[chan->id].paddr;
+		chunk->ll_region.vaddr = dw->ll_region_rd[chan->id].vaddr;
+	}
 
 	if (desc->chunk) {
 		/* Create and add new element into the linked list */
@@ -329,22 +334,22 @@ dw_edma_device_transfer(struct dw_edma_transfer *xfer)
 	struct dw_edma_chunk *chunk;
 	struct dw_edma_burst *burst;
 	struct dw_edma_desc *desc;
-	u32 cnt;
+	u32 cnt = 0;
 	int i;
 
 	if (!chan->configured)
 		return NULL;
 
 	switch (chan->config.direction) {
-	case DMA_DEV_TO_MEM: /* local dma */
+	case DMA_DEV_TO_MEM: /* local DMA */
 		if (dir == DMA_DEV_TO_MEM && chan->dir == EDMA_DIR_READ)
 			break;
 		return NULL;
-	case DMA_MEM_TO_DEV: /* local dma */
+	case DMA_MEM_TO_DEV: /* local DMA */
 		if (dir == DMA_MEM_TO_DEV && chan->dir == EDMA_DIR_WRITE)
 			break;
 		return NULL;
-	default: /* remote dma */
+	default: /* remote DMA */
 		if (dir == DMA_MEM_TO_DEV && chan->dir == EDMA_DIR_READ)
 			break;
 		if (dir == DMA_DEV_TO_MEM && chan->dir == EDMA_DIR_WRITE)
@@ -352,12 +357,19 @@ dw_edma_device_transfer(struct dw_edma_transfer *xfer)
 		return NULL;
 	}
 
-	if (xfer->cyclic) {
+	if (xfer->type == EDMA_XFER_CYCLIC) {
 		if (!xfer->xfer.cyclic.len || !xfer->xfer.cyclic.cnt)
 			return NULL;
-	} else {
+	} else if (xfer->type == EDMA_XFER_SCATTER_GATHER) {
 		if (xfer->xfer.sg.len < 1)
 			return NULL;
+	} else if (xfer->type == EDMA_XFER_INTERLEAVED) {
+		if (!xfer->xfer.il->numf)
+			return NULL;
+		if (xfer->xfer.il->numf > 0 && xfer->xfer.il->frame_size > 0)
+			return NULL;
+	} else {
+		return NULL;
 	}
 
 	desc = dw_edma_alloc_desc(chan);
@@ -368,18 +380,28 @@ dw_edma_device_transfer(struct dw_edma_transfer *xfer)
 	if (unlikely(!chunk))
 		goto err_alloc;
 
-	src_addr = chan->config.src_addr;
-	dst_addr = chan->config.dst_addr;
+	if (xfer->type == EDMA_XFER_INTERLEAVED) {
+		src_addr = xfer->xfer.il->src_start;
+		dst_addr = xfer->xfer.il->dst_start;
+	} else {
+		src_addr = chan->config.src_addr;
+		dst_addr = chan->config.dst_addr;
+	}
 
-	if (xfer->cyclic) {
+	if (xfer->type == EDMA_XFER_CYCLIC) {
 		cnt = xfer->xfer.cyclic.cnt;
-	} else {
+	} else if (xfer->type == EDMA_XFER_SCATTER_GATHER) {
 		cnt = xfer->xfer.sg.len;
 		sg = xfer->xfer.sg.sgl;
+	} else if (xfer->type == EDMA_XFER_INTERLEAVED) {
+		if (xfer->xfer.il->numf > 0)
+			cnt = xfer->xfer.il->numf;
+		else
+			cnt = xfer->xfer.il->frame_size;
 	}
 
 	for (i = 0; i < cnt; i++) {
-		if (!xfer->cyclic && !sg)
+		if (xfer->type == EDMA_XFER_SCATTER_GATHER && !sg)
 			break;
 
 		if (chunk->bursts_alloc == chan->ll_max) {
@@ -392,20 +414,23 @@ dw_edma_device_transfer(struct dw_edma_transfer *xfer)
 		if (unlikely(!burst))
 			goto err_alloc;
 
-		if (xfer->cyclic)
+		if (xfer->type == EDMA_XFER_CYCLIC)
 			burst->sz = xfer->xfer.cyclic.len;
-		else
+		else if (xfer->type == EDMA_XFER_SCATTER_GATHER)
 			burst->sz = sg_dma_len(sg);
+		else if (xfer->type == EDMA_XFER_INTERLEAVED)
+			burst->sz = xfer->xfer.il->sgl[i].size;
 
 		chunk->ll_region.sz += burst->sz;
 		desc->alloc_sz += burst->sz;
 
 		if (chan->dir == EDMA_DIR_WRITE) {
 			burst->sar = src_addr;
-			if (xfer->cyclic) {
+			if (xfer->type == EDMA_XFER_CYCLIC) {
 				burst->dar = xfer->xfer.cyclic.paddr;
-			} else {
-				burst->dar = dst_addr;
+			} else if (xfer->type == EDMA_XFER_SCATTER_GATHER) {
+				src_addr += sg_dma_len(sg);
+				burst->dar = sg_dma_address(sg);
 				/* Unlike the typical assumption by other
 				 * drivers/IPs the peripheral memory isn't
 				 * a FIFO memory, in this case, it's a
@@ -416,10 +441,11 @@ dw_edma_device_transfer(struct dw_edma_transfer *xfer)
 			}
 		} else {
 			burst->dar = dst_addr;
-			if (xfer->cyclic) {
+			if (xfer->type == EDMA_XFER_CYCLIC) {
 				burst->sar = xfer->xfer.cyclic.paddr;
-			} else {
-				burst->sar = src_addr;
+			} else if (xfer->type == EDMA_XFER_SCATTER_GATHER) {
+				dst_addr += sg_dma_len(sg);
+				burst->sar = sg_dma_address(sg);
 				/* Unlike the typical assumption by other
 				 * drivers/IPs the peripheral memory isn't
 				 * a FIFO memory, in this case, it's a
@@ -430,10 +456,22 @@ dw_edma_device_transfer(struct dw_edma_transfer *xfer)
 			}
 		}
 
-		if (!xfer->cyclic) {
-			src_addr += sg_dma_len(sg);
-			dst_addr += sg_dma_len(sg);
+		if (xfer->type == EDMA_XFER_SCATTER_GATHER) {
 			sg = sg_next(sg);
+		} else if (xfer->type == EDMA_XFER_INTERLEAVED &&
+			   xfer->xfer.il->frame_size > 0) {
+			struct dma_interleaved_template *il = xfer->xfer.il;
+			struct data_chunk *dc = &il->sgl[i];
+
+			if (il->src_sgl) {
+				src_addr += burst->sz;
+				src_addr += dmaengine_get_src_icg(il, dc);
+			}
+
+			if (il->dst_sgl) {
+				dst_addr += burst->sz;
+				dst_addr += dmaengine_get_dst_icg(il, dc);
+			}
 		}
 	}
 
@@ -459,7 +497,7 @@ dw_edma_device_prep_slave_sg(struct dma_chan *dchan, struct scatterlist *sgl,
 	xfer.xfer.sg.sgl = sgl;
 	xfer.xfer.sg.len = len;
 	xfer.flags = flags;
-	xfer.cyclic = false;
+	xfer.type = EDMA_XFER_SCATTER_GATHER;
 
 	return dw_edma_device_transfer(&xfer);
 }
@@ -478,7 +516,23 @@ dw_edma_device_prep_dma_cyclic(struct dma_chan *dchan, dma_addr_t paddr,
 	xfer.xfer.cyclic.len = len;
 	xfer.xfer.cyclic.cnt = count;
 	xfer.flags = flags;
-	xfer.cyclic = true;
+	xfer.type = EDMA_XFER_CYCLIC;
+
+	return dw_edma_device_transfer(&xfer);
+}
+
+static struct dma_async_tx_descriptor *
+dw_edma_device_prep_interleaved_dma(struct dma_chan *dchan,
+				    struct dma_interleaved_template *ilt,
+				    unsigned long flags)
+{
+	struct dw_edma_transfer xfer;
+
+	xfer.dchan = dchan;
+	xfer.direction = ilt->dir;
+	xfer.xfer.il = ilt;
+	xfer.flags = flags;
+	xfer.type = EDMA_XFER_INTERLEAVED;
 
 	return dw_edma_device_transfer(&xfer);
 }
@@ -642,24 +696,13 @@ static int dw_edma_channel_setup(struct dw_edma_chip *chip, bool write,
 	struct device *dev = chip->dev;
 	struct dw_edma *dw = chip->dw;
 	struct dw_edma_chan *chan;
-	size_t ll_chunk, dt_chunk;
 	struct dw_edma_irq *irq;
 	struct dma_device *dma;
-	u32 i, j, cnt, ch_cnt;
 	u32 alloc, off_alloc;
+	u32 i, j, cnt;
 	int err = 0;
 	u32 pos;
 
-	ch_cnt = dw->wr_ch_cnt + dw->rd_ch_cnt;
-	ll_chunk = dw->ll_region.sz;
-	dt_chunk = dw->dt_region.sz;
-
-	/* Calculate linked list chunk for each channel */
-	ll_chunk /= roundup_pow_of_two(ch_cnt);
-
-	/* Calculate linked list chunk for each channel */
-	dt_chunk /= roundup_pow_of_two(ch_cnt);
-
 	if (write) {
 		i = 0;
 		cnt = dw->wr_ch_cnt;
@@ -691,14 +734,14 @@ static int dw_edma_channel_setup(struct dw_edma_chip *chip, bool write,
 		chan->request = EDMA_REQ_NONE;
 		chan->status = EDMA_ST_IDLE;
 
-		chan->ll_off = (ll_chunk * i);
-		chan->ll_max = (ll_chunk / EDMA_LL_SZ) - 1;
-
-		chan->dt_off = (dt_chunk * i);
+		if (write)
+			chan->ll_max = (dw->ll_region_wr[j].sz / EDMA_LL_SZ);
+		else
+			chan->ll_max = (dw->ll_region_rd[j].sz / EDMA_LL_SZ);
+		chan->ll_max -= 1;
 
-		dev_vdbg(dev, "L. List:\tChannel %s[%u] off=0x%.8lx, max_cnt=%u\n",
-			 write ? "write" : "read", j,
-			 chan->ll_off, chan->ll_max);
+		dev_vdbg(dev, "L. List:\tChannel %s[%u] max_cnt=%u\n",
+			 write ? "write" : "read", j, chan->ll_max);
 
 		if (dw->nr_irqs == 1)
 			pos = 0;
@@ -723,12 +766,15 @@ static int dw_edma_channel_setup(struct dw_edma_chip *chip, bool write,
 		chan->vc.desc_free = vchan_free_desc;
 		vchan_init(&chan->vc, dma);
 
-		dt_region->paddr = dw->dt_region.paddr + chan->dt_off;
-		dt_region->vaddr = dw->dt_region.vaddr + chan->dt_off;
-		dt_region->sz = dt_chunk;
-
-		dev_vdbg(dev, "Data:\tChannel %s[%u] off=0x%.8lx\n",
-			 write ? "write" : "read", j, chan->dt_off);
+		if (write) {
+			dt_region->paddr = dw->dt_region_wr[j].paddr;
+			dt_region->vaddr = dw->dt_region_wr[j].vaddr;
+			dt_region->sz = dw->dt_region_wr[j].sz;
+		} else {
+			dt_region->paddr = dw->dt_region_rd[j].paddr;
+			dt_region->vaddr = dw->dt_region_rd[j].vaddr;
+			dt_region->sz = dw->dt_region_rd[j].sz;
+		}
 
 		dw_edma_v0_core_device_config(chan);
 	}
@@ -738,6 +784,7 @@ static int dw_edma_channel_setup(struct dw_edma_chip *chip, bool write,
 	dma_cap_set(DMA_SLAVE, dma->cap_mask);
 	dma_cap_set(DMA_CYCLIC, dma->cap_mask);
 	dma_cap_set(DMA_PRIVATE, dma->cap_mask);
+	dma_cap_set(DMA_INTERLEAVE, dma->cap_mask);
 	dma->directions = BIT(write ? DMA_DEV_TO_MEM : DMA_MEM_TO_DEV);
 	dma->src_addr_widths = BIT(DMA_SLAVE_BUSWIDTH_4_BYTES);
 	dma->dst_addr_widths = BIT(DMA_SLAVE_BUSWIDTH_4_BYTES);
@@ -756,6 +803,7 @@ static int dw_edma_channel_setup(struct dw_edma_chip *chip, bool write,
 	dma->device_tx_status = dw_edma_device_tx_status;
 	dma->device_prep_slave_sg = dw_edma_device_prep_slave_sg;
 	dma->device_prep_dma_cyclic = dw_edma_device_prep_dma_cyclic;
+	dma->device_prep_interleaved_dma = dw_edma_device_prep_interleaved_dma;
 
 	dma_set_max_seg_size(dma->dev, U32_MAX);
 
@@ -863,14 +911,15 @@ int dw_edma_probe(struct dw_edma_chip *chip)
 
 	raw_spin_lock_init(&dw->lock);
 
-	/* Find out how many write channels are supported by hardware */
-	dw->wr_ch_cnt = dw_edma_v0_core_ch_count(dw, EDMA_DIR_WRITE);
-	if (!dw->wr_ch_cnt)
-		return -EINVAL;
+	dw->wr_ch_cnt = min_t(u16, dw->wr_ch_cnt,
+			      dw_edma_v0_core_ch_count(dw, EDMA_DIR_WRITE));
+	dw->wr_ch_cnt = min_t(u16, dw->wr_ch_cnt, EDMA_MAX_WR_CH);
 
-	/* Find out how many read channels are supported by hardware */
-	dw->rd_ch_cnt = dw_edma_v0_core_ch_count(dw, EDMA_DIR_READ);
-	if (!dw->rd_ch_cnt)
+	dw->rd_ch_cnt = min_t(u16, dw->rd_ch_cnt,
+			      dw_edma_v0_core_ch_count(dw, EDMA_DIR_READ));
+	dw->rd_ch_cnt = min_t(u16, dw->rd_ch_cnt, EDMA_MAX_RD_CH);
+
+	if (!dw->wr_ch_cnt && !dw->rd_ch_cnt)
 		return -EINVAL;
 
 	dev_vdbg(dev, "Channels:\twrite=%d, read=%d\n",
@@ -937,24 +986,23 @@ int dw_edma_remove(struct dw_edma_chip *chip)
 	/* Power management */
 	pm_runtime_disable(dev);
 
+	/* Deregister eDMA device */
+	dma_async_device_unregister(&dw->wr_edma);
 	list_for_each_entry_safe(chan, _chan, &dw->wr_edma.channels,
 				 vc.chan.device_node) {
-		list_del(&chan->vc.chan.device_node);
 		tasklet_kill(&chan->vc.task);
+		list_del(&chan->vc.chan.device_node);
 	}
 
+	dma_async_device_unregister(&dw->rd_edma);
 	list_for_each_entry_safe(chan, _chan, &dw->rd_edma.channels,
 				 vc.chan.device_node) {
-		list_del(&chan->vc.chan.device_node);
 		tasklet_kill(&chan->vc.task);
+		list_del(&chan->vc.chan.device_node);
 	}
 
-	/* Deregister eDMA device */
-	dma_async_device_unregister(&dw->wr_edma);
-	dma_async_device_unregister(&dw->rd_edma);
-
 	/* Turn debugfs off */
-	dw_edma_v0_core_debugfs_off();
+	dw_edma_v0_core_debugfs_off(chip);
 
 	return 0;
 }
diff --git a/drivers/dma/dw-edma/dw-edma-core.h b/drivers/dma/dw-edma/dw-edma-core.h
index 31fc50d31792..60316d408c3e 100644
--- a/drivers/dma/dw-edma/dw-edma-core.h
+++ b/drivers/dma/dw-edma/dw-edma-core.h
@@ -15,15 +15,18 @@
 #include "../virt-dma.h"
 
 #define EDMA_LL_SZ					24
+#define EDMA_MAX_WR_CH					8
+#define EDMA_MAX_RD_CH					8
 
 enum dw_edma_dir {
 	EDMA_DIR_WRITE = 0,
 	EDMA_DIR_READ
 };
 
-enum dw_edma_mode {
-	EDMA_MODE_LEGACY = 0,
-	EDMA_MODE_UNROLL
+enum dw_edma_map_format {
+	EDMA_MF_EDMA_LEGACY = 0x0,
+	EDMA_MF_EDMA_UNROLL = 0x1,
+	EDMA_MF_HDMA_COMPAT = 0x5
 };
 
 enum dw_edma_request {
@@ -38,6 +41,12 @@ enum dw_edma_status {
 	EDMA_ST_BUSY
 };
 
+enum dw_edma_xfer_type {
+	EDMA_XFER_SCATTER_GATHER = 0,
+	EDMA_XFER_CYCLIC,
+	EDMA_XFER_INTERLEAVED
+};
+
 struct dw_edma_chan;
 struct dw_edma_chunk;
 
@@ -82,11 +91,8 @@ struct dw_edma_chan {
 	int				id;
 	enum dw_edma_dir		dir;
 
-	off_t				ll_off;
 	u32				ll_max;
 
-	off_t				dt_off;
-
 	struct msi_msg			msi;
 
 	enum dw_edma_request		request;
@@ -117,19 +123,23 @@ struct dw_edma {
 	u16				rd_ch_cnt;
 
 	struct dw_edma_region		rg_region;	/* Registers */
-	struct dw_edma_region		ll_region;	/* Linked list */
-	struct dw_edma_region		dt_region;	/* Data */
+	struct dw_edma_region		ll_region_wr[EDMA_MAX_WR_CH];
+	struct dw_edma_region		ll_region_rd[EDMA_MAX_RD_CH];
+	struct dw_edma_region		dt_region_wr[EDMA_MAX_WR_CH];
+	struct dw_edma_region		dt_region_rd[EDMA_MAX_RD_CH];
 
 	struct dw_edma_irq		*irq;
 	int				nr_irqs;
 
-	u32				version;
-	enum dw_edma_mode		mode;
+	enum dw_edma_map_format		mf;
 
 	struct dw_edma_chan		*chan;
 	const struct dw_edma_core_ops	*ops;
 
 	raw_spinlock_t			lock;		/* Only for legacy */
+#ifdef CONFIG_DEBUG_FS
+	struct dentry			*debugfs;
+#endif /* CONFIG_DEBUG_FS */
 };
 
 struct dw_edma_sg {
@@ -146,12 +156,13 @@ struct dw_edma_cyclic {
 struct dw_edma_transfer {
 	struct dma_chan			*dchan;
 	union dw_edma_xfer {
-		struct dw_edma_sg	sg;
-		struct dw_edma_cyclic	cyclic;
+		struct dw_edma_sg		sg;
+		struct dw_edma_cyclic		cyclic;
+		struct dma_interleaved_template *il;
 	} xfer;
 	enum dma_transfer_direction	direction;
 	unsigned long			flags;
-	bool				cyclic;
+	enum dw_edma_xfer_type		type;
 };
 
 static inline
diff --git a/drivers/dma/dw-edma/dw-edma-pcie.c b/drivers/dma/dw-edma/dw-edma-pcie.c
index 1eafc602e17e..44f6e09bdb53 100644
--- a/drivers/dma/dw-edma/dw-edma-pcie.c
+++ b/drivers/dma/dw-edma/dw-edma-pcie.c
@@ -13,45 +13,81 @@
 #include <linux/dma/edma.h>
 #include <linux/pci-epf.h>
 #include <linux/msi.h>
+#include <linux/bitfield.h>
 
 #include "dw-edma-core.h"
 
+#define DW_PCIE_VSEC_DMA_ID			0x6
+#define DW_PCIE_VSEC_DMA_BAR			GENMASK(10, 8)
+#define DW_PCIE_VSEC_DMA_MAP			GENMASK(2, 0)
+#define DW_PCIE_VSEC_DMA_WR_CH			GENMASK(9, 0)
+#define DW_PCIE_VSEC_DMA_RD_CH			GENMASK(25, 16)
+
+#define DW_BLOCK(a, b, c) \
+	{ \
+		.bar = a, \
+		.off = b, \
+		.sz = c, \
+	},
+
+struct dw_edma_block {
+	enum pci_barno			bar;
+	off_t				off;
+	size_t				sz;
+};
+
 struct dw_edma_pcie_data {
 	/* eDMA registers location */
-	enum pci_barno			rg_bar;
-	off_t				rg_off;
-	size_t				rg_sz;
+	struct dw_edma_block		rg;
 	/* eDMA memory linked list location */
-	enum pci_barno			ll_bar;
-	off_t				ll_off;
-	size_t				ll_sz;
+	struct dw_edma_block		ll_wr[EDMA_MAX_WR_CH];
+	struct dw_edma_block		ll_rd[EDMA_MAX_RD_CH];
 	/* eDMA memory data location */
-	enum pci_barno			dt_bar;
-	off_t				dt_off;
-	size_t				dt_sz;
+	struct dw_edma_block		dt_wr[EDMA_MAX_WR_CH];
+	struct dw_edma_block		dt_rd[EDMA_MAX_RD_CH];
 	/* Other */
-	u32				version;
-	enum dw_edma_mode		mode;
+	enum dw_edma_map_format		mf;
 	u8				irqs;
+	u16				wr_ch_cnt;
+	u16				rd_ch_cnt;
 };
 
 static const struct dw_edma_pcie_data snps_edda_data = {
 	/* eDMA registers location */
-	.rg_bar				= BAR_0,
-	.rg_off				= 0x00001000,	/*  4 Kbytes */
-	.rg_sz				= 0x00002000,	/*  8 Kbytes */
+	.rg.bar				= BAR_0,
+	.rg.off				= 0x00001000,	/*  4 Kbytes */
+	.rg.sz				= 0x00002000,	/*  8 Kbytes */
 	/* eDMA memory linked list location */
-	.ll_bar				= BAR_2,
-	.ll_off				= 0x00000000,	/*  0 Kbytes */
-	.ll_sz				= 0x00800000,	/*  8 Mbytes */
+	.ll_wr = {
+		/* Channel 0 - BAR 2, offset 0 Mbytes, size 2 Kbytes */
+		DW_BLOCK(BAR_2, 0x00000000, 0x00000800)
+		/* Channel 1 - BAR 2, offset 2 Mbytes, size 2 Kbytes */
+		DW_BLOCK(BAR_2, 0x00200000, 0x00000800)
+	},
+	.ll_rd = {
+		/* Channel 0 - BAR 2, offset 4 Mbytes, size 2 Kbytes */
+		DW_BLOCK(BAR_2, 0x00400000, 0x00000800)
+		/* Channel 1 - BAR 2, offset 6 Mbytes, size 2 Kbytes */
+		DW_BLOCK(BAR_2, 0x00600000, 0x00000800)
+	},
 	/* eDMA memory data location */
-	.dt_bar				= BAR_2,
-	.dt_off				= 0x00800000,	/*  8 Mbytes */
-	.dt_sz				= 0x03800000,	/* 56 Mbytes */
+	.dt_wr = {
+		/* Channel 0 - BAR 2, offset 8 Mbytes, size 2 Kbytes */
+		DW_BLOCK(BAR_2, 0x00800000, 0x00000800)
+		/* Channel 1 - BAR 2, offset 9 Mbytes, size 2 Kbytes */
+		DW_BLOCK(BAR_2, 0x00900000, 0x00000800)
+	},
+	.dt_rd = {
+		/* Channel 0 - BAR 2, offset 10 Mbytes, size 2 Kbytes */
+		DW_BLOCK(BAR_2, 0x00a00000, 0x00000800)
+		/* Channel 1 - BAR 2, offset 11 Mbytes, size 2 Kbytes */
+		DW_BLOCK(BAR_2, 0x00b00000, 0x00000800)
+	},
 	/* Other */
-	.version			= 0,
-	.mode				= EDMA_MODE_UNROLL,
+	.mf				= EDMA_MF_EDMA_UNROLL,
 	.irqs				= 1,
+	.wr_ch_cnt			= 2,
+	.rd_ch_cnt			= 2,
 };
 
 static int dw_edma_pcie_irq_vector(struct device *dev, unsigned int nr)
@@ -63,14 +99,58 @@ static const struct dw_edma_core_ops dw_edma_pcie_core_ops = {
 	.irq_vector = dw_edma_pcie_irq_vector,
 };
 
+static void dw_edma_pcie_get_vsec_dma_data(struct pci_dev *pdev,
+					   struct dw_edma_pcie_data *pdata)
+{
+	u32 val, map;
+	u16 vsec;
+	u64 off;
+
+	vsec = pci_find_vsec_capability(pdev, PCI_VENDOR_ID_SYNOPSYS,
+					DW_PCIE_VSEC_DMA_ID);
+	if (!vsec)
+		return;
+
+	pci_read_config_dword(pdev, vsec + PCI_VNDR_HEADER, &val);
+	if (PCI_VNDR_HEADER_REV(val) != 0x00 ||
+	    PCI_VNDR_HEADER_LEN(val) != 0x18)
+		return;
+
+	pci_dbg(pdev, "Detected PCIe Vendor-Specific Extended Capability DMA\n");
+	pci_read_config_dword(pdev, vsec + 0x8, &val);
+	map = FIELD_GET(DW_PCIE_VSEC_DMA_MAP, val);
+	if (map != EDMA_MF_EDMA_LEGACY &&
+	    map != EDMA_MF_EDMA_UNROLL &&
+	    map != EDMA_MF_HDMA_COMPAT)
+		return;
+
+	pdata->mf = map;
+	pdata->rg.bar = FIELD_GET(DW_PCIE_VSEC_DMA_BAR, val);
+
+	pci_read_config_dword(pdev, vsec + 0xc, &val);
+	pdata->wr_ch_cnt = min_t(u16, pdata->wr_ch_cnt,
+				 FIELD_GET(DW_PCIE_VSEC_DMA_WR_CH, val));
+	pdata->rd_ch_cnt = min_t(u16, pdata->rd_ch_cnt,
+				 FIELD_GET(DW_PCIE_VSEC_DMA_RD_CH, val));
+
+	pci_read_config_dword(pdev, vsec + 0x14, &val);
+	off = val;
+	pci_read_config_dword(pdev, vsec + 0x10, &val);
+	off <<= 32;
+	off |= val;
+	pdata->rg.off = off;
+}
+
 static int dw_edma_pcie_probe(struct pci_dev *pdev,
 			      const struct pci_device_id *pid)
 {
-	const struct dw_edma_pcie_data *pdata = (void *)pid->driver_data;
+	struct dw_edma_pcie_data *pdata = (void *)pid->driver_data;
+	struct dw_edma_pcie_data vsec_data;
 	struct device *dev = &pdev->dev;
 	struct dw_edma_chip *chip;
-	int err, nr_irqs;
 	struct dw_edma *dw;
+	int err, nr_irqs;
+	int i, mask;
 
 	/* Enable PCI device */
 	err = pcim_enable_device(pdev);
@@ -79,11 +159,25 @@ static int dw_edma_pcie_probe(struct pci_dev *pdev,
 		return err;
 	}
 
+	memcpy(&vsec_data, pdata, sizeof(struct dw_edma_pcie_data));
+
+	/*
+	 * Tries to find if exists a PCIe Vendor-Specific Extended Capability
+	 * for the DMA, if one exists, then reconfigures it.
+	 */
+	dw_edma_pcie_get_vsec_dma_data(pdev, &vsec_data);
+
 	/* Mapping PCI BAR regions */
-	err = pcim_iomap_regions(pdev, BIT(pdata->rg_bar) |
-				       BIT(pdata->ll_bar) |
-				       BIT(pdata->dt_bar),
-				 pci_name(pdev));
+	mask = BIT(vsec_data.rg.bar);
+	for (i = 0; i < vsec_data.wr_ch_cnt; i++) {
+		mask |= BIT(vsec_data.ll_wr[i].bar);
+		mask |= BIT(vsec_data.dt_wr[i].bar);
+	}
+	for (i = 0; i < vsec_data.rd_ch_cnt; i++) {
+		mask |= BIT(vsec_data.ll_rd[i].bar);
+		mask |= BIT(vsec_data.dt_rd[i].bar);
+	}
+	err = pcim_iomap_regions(pdev, mask, pci_name(pdev));
 	if (err) {
 		pci_err(pdev, "eDMA BAR I/O remapping failed\n");
 		return err;
@@ -125,7 +219,7 @@ static int dw_edma_pcie_probe(struct pci_dev *pdev,
 		return -ENOMEM;
 
 	/* IRQs allocation */
-	nr_irqs = pci_alloc_irq_vectors(pdev, 1, pdata->irqs,
+	nr_irqs = pci_alloc_irq_vectors(pdev, 1, vsec_data.irqs,
 					PCI_IRQ_MSI | PCI_IRQ_MSIX);
 	if (nr_irqs < 1) {
 		pci_err(pdev, "fail to alloc IRQ vector (number of IRQs=%u)\n",
@@ -139,46 +233,109 @@ static int dw_edma_pcie_probe(struct pci_dev *pdev,
 	chip->id = pdev->devfn;
 	chip->irq = pdev->irq;
 
-	dw->rg_region.vaddr = pcim_iomap_table(pdev)[pdata->rg_bar];
-	dw->rg_region.vaddr += pdata->rg_off;
-	dw->rg_region.paddr = pdev->resource[pdata->rg_bar].start;
-	dw->rg_region.paddr += pdata->rg_off;
-	dw->rg_region.sz = pdata->rg_sz;
-
-	dw->ll_region.vaddr = pcim_iomap_table(pdev)[pdata->ll_bar];
-	dw->ll_region.vaddr += pdata->ll_off;
-	dw->ll_region.paddr = pdev->resource[pdata->ll_bar].start;
-	dw->ll_region.paddr += pdata->ll_off;
-	dw->ll_region.sz = pdata->ll_sz;
-
-	dw->dt_region.vaddr = pcim_iomap_table(pdev)[pdata->dt_bar];
-	dw->dt_region.vaddr += pdata->dt_off;
-	dw->dt_region.paddr = pdev->resource[pdata->dt_bar].start;
-	dw->dt_region.paddr += pdata->dt_off;
-	dw->dt_region.sz = pdata->dt_sz;
-
-	dw->version = pdata->version;
-	dw->mode = pdata->mode;
+	dw->mf = vsec_data.mf;
 	dw->nr_irqs = nr_irqs;
 	dw->ops = &dw_edma_pcie_core_ops;
+	dw->wr_ch_cnt = vsec_data.wr_ch_cnt;
+	dw->rd_ch_cnt = vsec_data.rd_ch_cnt;
 
-	/* Debug info */
-	pci_dbg(pdev, "Version:\t%u\n", dw->version);
+	dw->rg_region.vaddr = pcim_iomap_table(pdev)[vsec_data.rg.bar];
+	if (!dw->rg_region.vaddr)
+		return -ENOMEM;
+
+	dw->rg_region.vaddr += vsec_data.rg.off;
+	dw->rg_region.paddr = pdev->resource[vsec_data.rg.bar].start;
+	dw->rg_region.paddr += vsec_data.rg.off;
+	dw->rg_region.sz = vsec_data.rg.sz;
+
+	for (i = 0; i < dw->wr_ch_cnt; i++) {
+		struct dw_edma_region *ll_region = &dw->ll_region_wr[i];
+		struct dw_edma_region *dt_region = &dw->dt_region_wr[i];
+		struct dw_edma_block *ll_block = &vsec_data.ll_wr[i];
+		struct dw_edma_block *dt_block = &vsec_data.dt_wr[i];
+
+		ll_region->vaddr = pcim_iomap_table(pdev)[ll_block->bar];
+		if (!ll_region->vaddr)
+			return -ENOMEM;
+
+		ll_region->vaddr += ll_block->off;
+		ll_region->paddr = pdev->resource[ll_block->bar].start;
+		ll_region->paddr += ll_block->off;
+		ll_region->sz = ll_block->sz;
+
+		dt_region->vaddr = pcim_iomap_table(pdev)[dt_block->bar];
+		if (!dt_region->vaddr)
+			return -ENOMEM;
+
+		dt_region->vaddr += dt_block->off;
+		dt_region->paddr = pdev->resource[dt_block->bar].start;
+		dt_region->paddr += dt_block->off;
+		dt_region->sz = dt_block->sz;
+	}
 
-	pci_dbg(pdev, "Mode:\t%s\n",
-		dw->mode == EDMA_MODE_LEGACY ? "Legacy" : "Unroll");
+	for (i = 0; i < dw->rd_ch_cnt; i++) {
+		struct dw_edma_region *ll_region = &dw->ll_region_rd[i];
+		struct dw_edma_region *dt_region = &dw->dt_region_rd[i];
+		struct dw_edma_block *ll_block = &vsec_data.ll_rd[i];
+		struct dw_edma_block *dt_block = &vsec_data.dt_rd[i];
+
+		ll_region->vaddr = pcim_iomap_table(pdev)[ll_block->bar];
+		if (!ll_region->vaddr)
+			return -ENOMEM;
+
+		ll_region->vaddr += ll_block->off;
+		ll_region->paddr = pdev->resource[ll_block->bar].start;
+		ll_region->paddr += ll_block->off;
+		ll_region->sz = ll_block->sz;
+
+		dt_region->vaddr = pcim_iomap_table(pdev)[dt_block->bar];
+		if (!dt_region->vaddr)
+			return -ENOMEM;
+
+		dt_region->vaddr += dt_block->off;
+		dt_region->paddr = pdev->resource[dt_block->bar].start;
+		dt_region->paddr += dt_block->off;
+		dt_region->sz = dt_block->sz;
+	}
+
+	/* Debug info */
+	if (dw->mf == EDMA_MF_EDMA_LEGACY)
+		pci_dbg(pdev, "Version:\teDMA Port Logic (0x%x)\n", dw->mf);
+	else if (dw->mf == EDMA_MF_EDMA_UNROLL)
+		pci_dbg(pdev, "Version:\teDMA Unroll (0x%x)\n", dw->mf);
+	else if (dw->mf == EDMA_MF_HDMA_COMPAT)
+		pci_dbg(pdev, "Version:\tHDMA Compatible (0x%x)\n", dw->mf);
+	else
+		pci_dbg(pdev, "Version:\tUnknown (0x%x)\n", dw->mf);
 
 	pci_dbg(pdev, "Registers:\tBAR=%u, off=0x%.8lx, sz=0x%zx bytes, addr(v=%p, p=%pa)\n",
-		pdata->rg_bar, pdata->rg_off, pdata->rg_sz,
+		vsec_data.rg.bar, vsec_data.rg.off, vsec_data.rg.sz,
 		dw->rg_region.vaddr, &dw->rg_region.paddr);
 
-	pci_dbg(pdev, "L. List:\tBAR=%u, off=0x%.8lx, sz=0x%zx bytes, addr(v=%p, p=%pa)\n",
-		pdata->ll_bar, pdata->ll_off, pdata->ll_sz,
-		dw->ll_region.vaddr, &dw->ll_region.paddr);
 
-	pci_dbg(pdev, "Data:\tBAR=%u, off=0x%.8lx, sz=0x%zx bytes, addr(v=%p, p=%pa)\n",
-		pdata->dt_bar, pdata->dt_off, pdata->dt_sz,
-		dw->dt_region.vaddr, &dw->dt_region.paddr);
+	for (i = 0; i < dw->wr_ch_cnt; i++) {
+		pci_dbg(pdev, "L. List:\tWRITE CH%.2u, BAR=%u, off=0x%.8lx, sz=0x%zx bytes, addr(v=%p, p=%pa)\n",
+			i, vsec_data.ll_wr[i].bar,
+			vsec_data.ll_wr[i].off, dw->ll_region_wr[i].sz,
+			dw->ll_region_wr[i].vaddr, &dw->ll_region_wr[i].paddr);
+
+		pci_dbg(pdev, "Data:\tWRITE CH%.2u, BAR=%u, off=0x%.8lx, sz=0x%zx bytes, addr(v=%p, p=%pa)\n",
+			i, vsec_data.dt_wr[i].bar,
+			vsec_data.dt_wr[i].off, dw->dt_region_wr[i].sz,
+			dw->dt_region_wr[i].vaddr, &dw->dt_region_wr[i].paddr);
+	}
+
+	for (i = 0; i < dw->rd_ch_cnt; i++) {
+		pci_dbg(pdev, "L. List:\tREAD CH%.2u, BAR=%u, off=0x%.8lx, sz=0x%zx bytes, addr(v=%p, p=%pa)\n",
+			i, vsec_data.ll_rd[i].bar,
+			vsec_data.ll_rd[i].off, dw->ll_region_rd[i].sz,
+			dw->ll_region_rd[i].vaddr, &dw->ll_region_rd[i].paddr);
+
+		pci_dbg(pdev, "Data:\tREAD CH%.2u, BAR=%u, off=0x%.8lx, sz=0x%zx bytes, addr(v=%p, p=%pa)\n",
+			i, vsec_data.dt_rd[i].bar,
+			vsec_data.dt_rd[i].off, dw->dt_region_rd[i].sz,
+			dw->dt_region_rd[i].vaddr, &dw->dt_region_rd[i].paddr);
+	}
 
 	pci_dbg(pdev, "Nr. IRQs:\t%u\n", dw->nr_irqs);
 
diff --git a/drivers/dma/dw-edma/dw-edma-v0-core.c b/drivers/dma/dw-edma/dw-edma-v0-core.c
index 692de47b1670..329fc2e57b70 100644
--- a/drivers/dma/dw-edma/dw-edma-v0-core.c
+++ b/drivers/dma/dw-edma/dw-edma-v0-core.c
@@ -28,35 +28,75 @@ static inline struct dw_edma_v0_regs __iomem *__dw_regs(struct dw_edma *dw)
 	return dw->rg_region.vaddr;
 }
 
-#define SET(dw, name, value)				\
+#define SET_32(dw, name, value)				\
 	writel(value, &(__dw_regs(dw)->name))
 
-#define GET(dw, name)					\
+#define GET_32(dw, name)				\
 	readl(&(__dw_regs(dw)->name))
 
-#define SET_RW(dw, dir, name, value)			\
+#define SET_RW_32(dw, dir, name, value)			\
 	do {						\
 		if ((dir) == EDMA_DIR_WRITE)		\
-			SET(dw, wr_##name, value);	\
+			SET_32(dw, wr_##name, value);	\
 		else					\
-			SET(dw, rd_##name, value);	\
+			SET_32(dw, rd_##name, value);	\
 	} while (0)
 
-#define GET_RW(dw, dir, name)				\
+#define GET_RW_32(dw, dir, name)			\
 	((dir) == EDMA_DIR_WRITE			\
-	  ? GET(dw, wr_##name)				\
-	  : GET(dw, rd_##name))
+	  ? GET_32(dw, wr_##name)			\
+	  : GET_32(dw, rd_##name))
 
-#define SET_BOTH(dw, name, value)			\
+#define SET_BOTH_32(dw, name, value)			\
 	do {						\
-		SET(dw, wr_##name, value);		\
-		SET(dw, rd_##name, value);		\
+		SET_32(dw, wr_##name, value);		\
+		SET_32(dw, rd_##name, value);		\
+	} while (0)
+
+#ifdef CONFIG_64BIT
+
+#define SET_64(dw, name, value)				\
+	writeq(value, &(__dw_regs(dw)->name))
+
+#define GET_64(dw, name)				\
+	readq(&(__dw_regs(dw)->name))
+
+#define SET_RW_64(dw, dir, name, value)			\
+	do {						\
+		if ((dir) == EDMA_DIR_WRITE)		\
+			SET_64(dw, wr_##name, value);	\
+		else					\
+			SET_64(dw, rd_##name, value);	\
+	} while (0)
+
+#define GET_RW_64(dw, dir, name)			\
+	((dir) == EDMA_DIR_WRITE			\
+	  ? GET_64(dw, wr_##name)			\
+	  : GET_64(dw, rd_##name))
+
+#define SET_BOTH_64(dw, name, value)			\
+	do {						\
+		SET_64(dw, wr_##name, value);		\
+		SET_64(dw, rd_##name, value);		\
+	} while (0)
+
+#endif /* CONFIG_64BIT */
+
+#define SET_COMPAT(dw, name, value)			\
+	writel(value, &(__dw_regs(dw)->type.unroll.name))
+
+#define SET_RW_COMPAT(dw, dir, name, value)		\
+	do {						\
+		if ((dir) == EDMA_DIR_WRITE)		\
+			SET_COMPAT(dw, wr_##name, value); \
+		else					\
+			SET_COMPAT(dw, rd_##name, value); \
 	} while (0)
 
 static inline struct dw_edma_v0_ch_regs __iomem *
 __dw_ch_regs(struct dw_edma *dw, enum dw_edma_dir dir, u16 ch)
 {
-	if (dw->mode == EDMA_MODE_LEGACY)
+	if (dw->mf == EDMA_MF_EDMA_LEGACY)
 		return &(__dw_regs(dw)->type.legacy.ch);
 
 	if (dir == EDMA_DIR_WRITE)
@@ -68,7 +108,7 @@ __dw_ch_regs(struct dw_edma *dw, enum dw_edma_dir dir, u16 ch)
 static inline void writel_ch(struct dw_edma *dw, enum dw_edma_dir dir, u16 ch,
 			     u32 value, void __iomem *addr)
 {
-	if (dw->mode == EDMA_MODE_LEGACY) {
+	if (dw->mf == EDMA_MF_EDMA_LEGACY) {
 		u32 viewport_sel;
 		unsigned long flags;
 
@@ -93,7 +133,7 @@ static inline u32 readl_ch(struct dw_edma *dw, enum dw_edma_dir dir, u16 ch,
 {
 	u32 value;
 
-	if (dw->mode == EDMA_MODE_LEGACY) {
+	if (dw->mf == EDMA_MF_EDMA_LEGACY) {
 		u32 viewport_sel;
 		unsigned long flags;
 
@@ -115,21 +155,86 @@ static inline u32 readl_ch(struct dw_edma *dw, enum dw_edma_dir dir, u16 ch,
 	return value;
 }
 
-#define SET_CH(dw, dir, ch, name, value) \
+#define SET_CH_32(dw, dir, ch, name, value) \
 	writel_ch(dw, dir, ch, value, &(__dw_ch_regs(dw, dir, ch)->name))
 
-#define GET_CH(dw, dir, ch, name) \
+#define GET_CH_32(dw, dir, ch, name) \
 	readl_ch(dw, dir, ch, &(__dw_ch_regs(dw, dir, ch)->name))
 
-#define SET_LL(ll, value) \
+#define SET_LL_32(ll, value) \
 	writel(value, ll)
 
+#ifdef CONFIG_64BIT
+
+static inline void writeq_ch(struct dw_edma *dw, enum dw_edma_dir dir, u16 ch,
+			     u64 value, void __iomem *addr)
+{
+	if (dw->mf == EDMA_MF_EDMA_LEGACY) {
+		u32 viewport_sel;
+		unsigned long flags;
+
+		raw_spin_lock_irqsave(&dw->lock, flags);
+
+		viewport_sel = FIELD_PREP(EDMA_V0_VIEWPORT_MASK, ch);
+		if (dir == EDMA_DIR_READ)
+			viewport_sel |= BIT(31);
+
+		writel(viewport_sel,
+		       &(__dw_regs(dw)->type.legacy.viewport_sel));
+		writeq(value, addr);
+
+		raw_spin_unlock_irqrestore(&dw->lock, flags);
+	} else {
+		writeq(value, addr);
+	}
+}
+
+static inline u64 readq_ch(struct dw_edma *dw, enum dw_edma_dir dir, u16 ch,
+			   const void __iomem *addr)
+{
+	u32 value;
+
+	if (dw->mf == EDMA_MF_EDMA_LEGACY) {
+		u32 viewport_sel;
+		unsigned long flags;
+
+		raw_spin_lock_irqsave(&dw->lock, flags);
+
+		viewport_sel = FIELD_PREP(EDMA_V0_VIEWPORT_MASK, ch);
+		if (dir == EDMA_DIR_READ)
+			viewport_sel |= BIT(31);
+
+		writel(viewport_sel,
+		       &(__dw_regs(dw)->type.legacy.viewport_sel));
+		value = readq(addr);
+
+		raw_spin_unlock_irqrestore(&dw->lock, flags);
+	} else {
+		value = readq(addr);
+	}
+
+	return value;
+}
+
+#define SET_CH_64(dw, dir, ch, name, value) \
+	writeq_ch(dw, dir, ch, value, &(__dw_ch_regs(dw, dir, ch)->name))
+
+#define GET_CH_64(dw, dir, ch, name) \
+	readq_ch(dw, dir, ch, &(__dw_ch_regs(dw, dir, ch)->name))
+
+#define SET_LL_64(ll, value) \
+	writeq(value, ll)
+
+#endif /* CONFIG_64BIT */
+
 /* eDMA management callbacks */
 void dw_edma_v0_core_off(struct dw_edma *dw)
 {
-	SET_BOTH(dw, int_mask, EDMA_V0_DONE_INT_MASK | EDMA_V0_ABORT_INT_MASK);
-	SET_BOTH(dw, int_clear, EDMA_V0_DONE_INT_MASK | EDMA_V0_ABORT_INT_MASK);
-	SET_BOTH(dw, engine_en, 0);
+	SET_BOTH_32(dw, int_mask,
+		    EDMA_V0_DONE_INT_MASK | EDMA_V0_ABORT_INT_MASK);
+	SET_BOTH_32(dw, int_clear,
+		    EDMA_V0_DONE_INT_MASK | EDMA_V0_ABORT_INT_MASK);
+	SET_BOTH_32(dw, engine_en, 0);
 }
 
 u16 dw_edma_v0_core_ch_count(struct dw_edma *dw, enum dw_edma_dir dir)
@@ -137,9 +242,11 @@ u16 dw_edma_v0_core_ch_count(struct dw_edma *dw, enum dw_edma_dir dir)
 	u32 num_ch;
 
 	if (dir == EDMA_DIR_WRITE)
-		num_ch = FIELD_GET(EDMA_V0_WRITE_CH_COUNT_MASK, GET(dw, ctrl));
+		num_ch = FIELD_GET(EDMA_V0_WRITE_CH_COUNT_MASK,
+				   GET_32(dw, ctrl));
 	else
-		num_ch = FIELD_GET(EDMA_V0_READ_CH_COUNT_MASK, GET(dw, ctrl));
+		num_ch = FIELD_GET(EDMA_V0_READ_CH_COUNT_MASK,
+				   GET_32(dw, ctrl));
 
 	if (num_ch > EDMA_V0_MAX_NR_CH)
 		num_ch = EDMA_V0_MAX_NR_CH;
@@ -153,7 +260,7 @@ enum dma_status dw_edma_v0_core_ch_status(struct dw_edma_chan *chan)
 	u32 tmp;
 
 	tmp = FIELD_GET(EDMA_V0_CH_STATUS_MASK,
-			GET_CH(dw, chan->dir, chan->id, ch_control1));
+			GET_CH_32(dw, chan->dir, chan->id, ch_control1));
 
 	if (tmp == 1)
 		return DMA_IN_PROGRESS;
@@ -167,26 +274,28 @@ void dw_edma_v0_core_clear_done_int(struct dw_edma_chan *chan)
 {
 	struct dw_edma *dw = chan->chip->dw;
 
-	SET_RW(dw, chan->dir, int_clear,
-	       FIELD_PREP(EDMA_V0_DONE_INT_MASK, BIT(chan->id)));
+	SET_RW_32(dw, chan->dir, int_clear,
+		  FIELD_PREP(EDMA_V0_DONE_INT_MASK, BIT(chan->id)));
 }
 
 void dw_edma_v0_core_clear_abort_int(struct dw_edma_chan *chan)
 {
 	struct dw_edma *dw = chan->chip->dw;
 
-	SET_RW(dw, chan->dir, int_clear,
-	       FIELD_PREP(EDMA_V0_ABORT_INT_MASK, BIT(chan->id)));
+	SET_RW_32(dw, chan->dir, int_clear,
+		  FIELD_PREP(EDMA_V0_ABORT_INT_MASK, BIT(chan->id)));
 }
 
 u32 dw_edma_v0_core_status_done_int(struct dw_edma *dw, enum dw_edma_dir dir)
 {
-	return FIELD_GET(EDMA_V0_DONE_INT_MASK, GET_RW(dw, dir, int_status));
+	return FIELD_GET(EDMA_V0_DONE_INT_MASK,
+			 GET_RW_32(dw, dir, int_status));
 }
 
 u32 dw_edma_v0_core_status_abort_int(struct dw_edma *dw, enum dw_edma_dir dir)
 {
-	return FIELD_GET(EDMA_V0_ABORT_INT_MASK, GET_RW(dw, dir, int_status));
+	return FIELD_GET(EDMA_V0_ABORT_INT_MASK,
+			 GET_RW_32(dw, dir, int_status));
 }
 
 static void dw_edma_v0_core_write_chunk(struct dw_edma_chunk *chunk)
@@ -209,15 +318,23 @@ static void dw_edma_v0_core_write_chunk(struct dw_edma_chunk *chunk)
 			control |= (DW_EDMA_V0_LIE | DW_EDMA_V0_RIE);
 
 		/* Channel control */
-		SET_LL(&lli[i].control, control);
+		SET_LL_32(&lli[i].control, control);
 		/* Transfer size */
-		SET_LL(&lli[i].transfer_size, child->sz);
-		/* SAR - low, high */
-		SET_LL(&lli[i].sar_low, lower_32_bits(child->sar));
-		SET_LL(&lli[i].sar_high, upper_32_bits(child->sar));
-		/* DAR - low, high */
-		SET_LL(&lli[i].dar_low, lower_32_bits(child->dar));
-		SET_LL(&lli[i].dar_high, upper_32_bits(child->dar));
+		SET_LL_32(&lli[i].transfer_size, child->sz);
+		/* SAR */
+		#ifdef CONFIG_64BIT
+			SET_LL_64(&lli[i].sar.reg, child->sar);
+		#else /* CONFIG_64BIT */
+			SET_LL_32(&lli[i].sar.lsb, lower_32_bits(child->sar));
+			SET_LL_32(&lli[i].sar.msb, upper_32_bits(child->sar));
+		#endif /* CONFIG_64BIT */
+		/* DAR */
+		#ifdef CONFIG_64BIT
+			SET_LL_64(&lli[i].dar.reg, child->dar);
+		#else /* CONFIG_64BIT */
+			SET_LL_32(&lli[i].dar.lsb, lower_32_bits(child->dar));
+			SET_LL_32(&lli[i].dar.msb, upper_32_bits(child->dar));
+		#endif /* CONFIG_64BIT */
 		i++;
 	}
 
@@ -227,10 +344,14 @@ static void dw_edma_v0_core_write_chunk(struct dw_edma_chunk *chunk)
 		control |= DW_EDMA_V0_CB;
 
 	/* Channel control */
-	SET_LL(&llp->control, control);
-	/* Linked list  - low, high */
-	SET_LL(&llp->llp_low, lower_32_bits(chunk->ll_region.paddr));
-	SET_LL(&llp->llp_high, upper_32_bits(chunk->ll_region.paddr));
+	SET_LL_32(&llp->control, control);
+	/* Linked list */
+	#ifdef CONFIG_64BIT
+		SET_LL_64(&llp->llp.reg, chunk->ll_region.paddr);
+	#else /* CONFIG_64BIT */
+		SET_LL_32(&llp->llp.lsb, lower_32_bits(chunk->ll_region.paddr));
+		SET_LL_32(&llp->llp.msb, upper_32_bits(chunk->ll_region.paddr));
+	#endif /* CONFIG_64BIT */
 }
 
 void dw_edma_v0_core_start(struct dw_edma_chunk *chunk, bool first)
@@ -243,28 +364,69 @@ void dw_edma_v0_core_start(struct dw_edma_chunk *chunk, bool first)
 
 	if (first) {
 		/* Enable engine */
-		SET_RW(dw, chan->dir, engine_en, BIT(0));
+		SET_RW_32(dw, chan->dir, engine_en, BIT(0));
+		if (dw->mf == EDMA_MF_HDMA_COMPAT) {
+			switch (chan->id) {
+			case 0:
+				SET_RW_COMPAT(dw, chan->dir, ch0_pwr_en,
+					      BIT(0));
+				break;
+			case 1:
+				SET_RW_COMPAT(dw, chan->dir, ch1_pwr_en,
+					      BIT(0));
+				break;
+			case 2:
+				SET_RW_COMPAT(dw, chan->dir, ch2_pwr_en,
+					      BIT(0));
+				break;
+			case 3:
+				SET_RW_COMPAT(dw, chan->dir, ch3_pwr_en,
+					      BIT(0));
+				break;
+			case 4:
+				SET_RW_COMPAT(dw, chan->dir, ch4_pwr_en,
+					      BIT(0));
+				break;
+			case 5:
+				SET_RW_COMPAT(dw, chan->dir, ch5_pwr_en,
+					      BIT(0));
+				break;
+			case 6:
+				SET_RW_COMPAT(dw, chan->dir, ch6_pwr_en,
+					      BIT(0));
+				break;
+			case 7:
+				SET_RW_COMPAT(dw, chan->dir, ch7_pwr_en,
+					      BIT(0));
+				break;
+			}
+		}
 		/* Interrupt unmask - done, abort */
-		tmp = GET_RW(dw, chan->dir, int_mask);
+		tmp = GET_RW_32(dw, chan->dir, int_mask);
 		tmp &= ~FIELD_PREP(EDMA_V0_DONE_INT_MASK, BIT(chan->id));
 		tmp &= ~FIELD_PREP(EDMA_V0_ABORT_INT_MASK, BIT(chan->id));
-		SET_RW(dw, chan->dir, int_mask, tmp);
+		SET_RW_32(dw, chan->dir, int_mask, tmp);
 		/* Linked list error */
-		tmp = GET_RW(dw, chan->dir, linked_list_err_en);
+		tmp = GET_RW_32(dw, chan->dir, linked_list_err_en);
 		tmp |= FIELD_PREP(EDMA_V0_LINKED_LIST_ERR_MASK, BIT(chan->id));
-		SET_RW(dw, chan->dir, linked_list_err_en, tmp);
+		SET_RW_32(dw, chan->dir, linked_list_err_en, tmp);
 		/* Channel control */
-		SET_CH(dw, chan->dir, chan->id, ch_control1,
-		       (DW_EDMA_V0_CCS | DW_EDMA_V0_LLE));
-		/* Linked list - low, high */
-		SET_CH(dw, chan->dir, chan->id, llp_low,
-		       lower_32_bits(chunk->ll_region.paddr));
-		SET_CH(dw, chan->dir, chan->id, llp_high,
-		       upper_32_bits(chunk->ll_region.paddr));
+		SET_CH_32(dw, chan->dir, chan->id, ch_control1,
+			  (DW_EDMA_V0_CCS | DW_EDMA_V0_LLE));
+		/* Linked list */
+		#ifdef CONFIG_64BIT
+			SET_CH_64(dw, chan->dir, chan->id, llp.reg,
+				  chunk->ll_region.paddr);
+		#else /* CONFIG_64BIT */
+			SET_CH_32(dw, chan->dir, chan->id, llp.lsb,
+				  lower_32_bits(chunk->ll_region.paddr));
+			SET_CH_32(dw, chan->dir, chan->id, llp.msb,
+				  upper_32_bits(chunk->ll_region.paddr));
+		#endif /* CONFIG_64BIT */
 	}
 	/* Doorbell */
-	SET_RW(dw, chan->dir, doorbell,
-	       FIELD_PREP(EDMA_V0_DOORBELL_CH_MASK, chan->id));
+	SET_RW_32(dw, chan->dir, doorbell,
+		  FIELD_PREP(EDMA_V0_DOORBELL_CH_MASK, chan->id));
 }
 
 int dw_edma_v0_core_device_config(struct dw_edma_chan *chan)
@@ -273,31 +435,31 @@ int dw_edma_v0_core_device_config(struct dw_edma_chan *chan)
 	u32 tmp = 0;
 
 	/* MSI done addr - low, high */
-	SET_RW(dw, chan->dir, done_imwr_low, chan->msi.address_lo);
-	SET_RW(dw, chan->dir, done_imwr_high, chan->msi.address_hi);
+	SET_RW_32(dw, chan->dir, done_imwr.lsb, chan->msi.address_lo);
+	SET_RW_32(dw, chan->dir, done_imwr.msb, chan->msi.address_hi);
 	/* MSI abort addr - low, high */
-	SET_RW(dw, chan->dir, abort_imwr_low, chan->msi.address_lo);
-	SET_RW(dw, chan->dir, abort_imwr_high, chan->msi.address_hi);
+	SET_RW_32(dw, chan->dir, abort_imwr.lsb, chan->msi.address_lo);
+	SET_RW_32(dw, chan->dir, abort_imwr.msb, chan->msi.address_hi);
 	/* MSI data - low, high */
 	switch (chan->id) {
 	case 0:
 	case 1:
-		tmp = GET_RW(dw, chan->dir, ch01_imwr_data);
+		tmp = GET_RW_32(dw, chan->dir, ch01_imwr_data);
 		break;
 
 	case 2:
 	case 3:
-		tmp = GET_RW(dw, chan->dir, ch23_imwr_data);
+		tmp = GET_RW_32(dw, chan->dir, ch23_imwr_data);
 		break;
 
 	case 4:
 	case 5:
-		tmp = GET_RW(dw, chan->dir, ch45_imwr_data);
+		tmp = GET_RW_32(dw, chan->dir, ch45_imwr_data);
 		break;
 
 	case 6:
 	case 7:
-		tmp = GET_RW(dw, chan->dir, ch67_imwr_data);
+		tmp = GET_RW_32(dw, chan->dir, ch67_imwr_data);
 		break;
 	}
 
@@ -316,22 +478,22 @@ int dw_edma_v0_core_device_config(struct dw_edma_chan *chan)
 	switch (chan->id) {
 	case 0:
 	case 1:
-		SET_RW(dw, chan->dir, ch01_imwr_data, tmp);
+		SET_RW_32(dw, chan->dir, ch01_imwr_data, tmp);
 		break;
 
 	case 2:
 	case 3:
-		SET_RW(dw, chan->dir, ch23_imwr_data, tmp);
+		SET_RW_32(dw, chan->dir, ch23_imwr_data, tmp);
 		break;
 
 	case 4:
 	case 5:
-		SET_RW(dw, chan->dir, ch45_imwr_data, tmp);
+		SET_RW_32(dw, chan->dir, ch45_imwr_data, tmp);
 		break;
 
 	case 6:
 	case 7:
-		SET_RW(dw, chan->dir, ch67_imwr_data, tmp);
+		SET_RW_32(dw, chan->dir, ch67_imwr_data, tmp);
 		break;
 	}
 
@@ -344,7 +506,7 @@ void dw_edma_v0_core_debugfs_on(struct dw_edma_chip *chip)
 	dw_edma_v0_debugfs_on(chip);
 }
 
-void dw_edma_v0_core_debugfs_off(void)
+void dw_edma_v0_core_debugfs_off(struct dw_edma_chip *chip)
 {
-	dw_edma_v0_debugfs_off();
+	dw_edma_v0_debugfs_off(chip);
 }
diff --git a/drivers/dma/dw-edma/dw-edma-v0-core.h b/drivers/dma/dw-edma/dw-edma-v0-core.h
index abae1527f1f9..2afa626b8300 100644
--- a/drivers/dma/dw-edma/dw-edma-v0-core.h
+++ b/drivers/dma/dw-edma/dw-edma-v0-core.h
@@ -23,6 +23,6 @@ void dw_edma_v0_core_start(struct dw_edma_chunk *chunk, bool first);
 int dw_edma_v0_core_device_config(struct dw_edma_chan *chan);
 /* eDMA debug fs callbacks */
 void dw_edma_v0_core_debugfs_on(struct dw_edma_chip *chip);
-void dw_edma_v0_core_debugfs_off(void);
+void dw_edma_v0_core_debugfs_off(struct dw_edma_chip *chip);
 
 #endif /* _DW_EDMA_V0_CORE_H */
diff --git a/drivers/dma/dw-edma/dw-edma-v0-debugfs.c b/drivers/dma/dw-edma/dw-edma-v0-debugfs.c
index 6f62711a4c94..4b3bcffd15ef 100644
--- a/drivers/dma/dw-edma/dw-edma-v0-debugfs.c
+++ b/drivers/dma/dw-edma/dw-edma-v0-debugfs.c
@@ -38,7 +38,6 @@
 #define CHANNEL_STR				"channel"
 #define REGISTERS_STR				"registers"
 
-static struct dentry				*base_dir;
 static struct dw_edma				*dw;
 static struct dw_edma_v0_regs			__iomem *regs;
 
@@ -55,7 +54,7 @@ struct debugfs_entries {
 static int dw_edma_debugfs_u32_get(void *data, u64 *val)
 {
 	void __iomem *reg = (void __force __iomem *)data;
-	if (dw->mode == EDMA_MODE_LEGACY &&
+	if (dw->mf == EDMA_MF_EDMA_LEGACY &&
 	    reg >= (void __iomem *)&regs->type.legacy.ch) {
 		void __iomem *ptr = &regs->type.legacy.ch;
 		u32 viewport_sel = 0;
@@ -114,12 +113,12 @@ static void dw_edma_debugfs_regs_ch(struct dw_edma_v0_ch_regs __iomem *regs,
 		REGISTER(ch_control1),
 		REGISTER(ch_control2),
 		REGISTER(transfer_size),
-		REGISTER(sar_low),
-		REGISTER(sar_high),
-		REGISTER(dar_low),
-		REGISTER(dar_high),
-		REGISTER(llp_low),
-		REGISTER(llp_high),
+		REGISTER(sar.lsb),
+		REGISTER(sar.msb),
+		REGISTER(dar.lsb),
+		REGISTER(dar.msb),
+		REGISTER(llp.lsb),
+		REGISTER(llp.msb),
 	};
 
 	nr_entries = ARRAY_SIZE(debugfs_regs);
@@ -132,17 +131,17 @@ static void dw_edma_debugfs_regs_wr(struct dentry *dir)
 		/* eDMA global registers */
 		WR_REGISTER(engine_en),
 		WR_REGISTER(doorbell),
-		WR_REGISTER(ch_arb_weight_low),
-		WR_REGISTER(ch_arb_weight_high),
+		WR_REGISTER(ch_arb_weight.lsb),
+		WR_REGISTER(ch_arb_weight.msb),
 		/* eDMA interrupts registers */
 		WR_REGISTER(int_status),
 		WR_REGISTER(int_mask),
 		WR_REGISTER(int_clear),
 		WR_REGISTER(err_status),
-		WR_REGISTER(done_imwr_low),
-		WR_REGISTER(done_imwr_high),
-		WR_REGISTER(abort_imwr_low),
-		WR_REGISTER(abort_imwr_high),
+		WR_REGISTER(done_imwr.lsb),
+		WR_REGISTER(done_imwr.msb),
+		WR_REGISTER(abort_imwr.lsb),
+		WR_REGISTER(abort_imwr.msb),
 		WR_REGISTER(ch01_imwr_data),
 		WR_REGISTER(ch23_imwr_data),
 		WR_REGISTER(ch45_imwr_data),
@@ -152,8 +151,8 @@ static void dw_edma_debugfs_regs_wr(struct dentry *dir)
 	const struct debugfs_entries debugfs_unroll_regs[] = {
 		/* eDMA channel context grouping */
 		WR_REGISTER_UNROLL(engine_chgroup),
-		WR_REGISTER_UNROLL(engine_hshake_cnt_low),
-		WR_REGISTER_UNROLL(engine_hshake_cnt_high),
+		WR_REGISTER_UNROLL(engine_hshake_cnt.lsb),
+		WR_REGISTER_UNROLL(engine_hshake_cnt.msb),
 		WR_REGISTER_UNROLL(ch0_pwr_en),
 		WR_REGISTER_UNROLL(ch1_pwr_en),
 		WR_REGISTER_UNROLL(ch2_pwr_en),
@@ -174,7 +173,7 @@ static void dw_edma_debugfs_regs_wr(struct dentry *dir)
 	nr_entries = ARRAY_SIZE(debugfs_regs);
 	dw_edma_debugfs_create_x32(debugfs_regs, nr_entries, regs_dir);
 
-	if (dw->mode == EDMA_MODE_UNROLL) {
+	if (dw->mf == EDMA_MF_HDMA_COMPAT) {
 		nr_entries = ARRAY_SIZE(debugfs_unroll_regs);
 		dw_edma_debugfs_create_x32(debugfs_unroll_regs, nr_entries,
 					   regs_dir);
@@ -200,19 +199,19 @@ static void dw_edma_debugfs_regs_rd(struct dentry *dir)
 		/* eDMA global registers */
 		RD_REGISTER(engine_en),
 		RD_REGISTER(doorbell),
-		RD_REGISTER(ch_arb_weight_low),
-		RD_REGISTER(ch_arb_weight_high),
+		RD_REGISTER(ch_arb_weight.lsb),
+		RD_REGISTER(ch_arb_weight.msb),
 		/* eDMA interrupts registers */
 		RD_REGISTER(int_status),
 		RD_REGISTER(int_mask),
 		RD_REGISTER(int_clear),
-		RD_REGISTER(err_status_low),
-		RD_REGISTER(err_status_high),
+		RD_REGISTER(err_status.lsb),
+		RD_REGISTER(err_status.msb),
 		RD_REGISTER(linked_list_err_en),
-		RD_REGISTER(done_imwr_low),
-		RD_REGISTER(done_imwr_high),
-		RD_REGISTER(abort_imwr_low),
-		RD_REGISTER(abort_imwr_high),
+		RD_REGISTER(done_imwr.lsb),
+		RD_REGISTER(done_imwr.msb),
+		RD_REGISTER(abort_imwr.lsb),
+		RD_REGISTER(abort_imwr.msb),
 		RD_REGISTER(ch01_imwr_data),
 		RD_REGISTER(ch23_imwr_data),
 		RD_REGISTER(ch45_imwr_data),
@@ -221,8 +220,8 @@ static void dw_edma_debugfs_regs_rd(struct dentry *dir)
 	const struct debugfs_entries debugfs_unroll_regs[] = {
 		/* eDMA channel context grouping */
 		RD_REGISTER_UNROLL(engine_chgroup),
-		RD_REGISTER_UNROLL(engine_hshake_cnt_low),
-		RD_REGISTER_UNROLL(engine_hshake_cnt_high),
+		RD_REGISTER_UNROLL(engine_hshake_cnt.lsb),
+		RD_REGISTER_UNROLL(engine_hshake_cnt.msb),
 		RD_REGISTER_UNROLL(ch0_pwr_en),
 		RD_REGISTER_UNROLL(ch1_pwr_en),
 		RD_REGISTER_UNROLL(ch2_pwr_en),
@@ -243,7 +242,7 @@ static void dw_edma_debugfs_regs_rd(struct dentry *dir)
 	nr_entries = ARRAY_SIZE(debugfs_regs);
 	dw_edma_debugfs_create_x32(debugfs_regs, nr_entries, regs_dir);
 
-	if (dw->mode == EDMA_MODE_UNROLL) {
+	if (dw->mf == EDMA_MF_HDMA_COMPAT) {
 		nr_entries = ARRAY_SIZE(debugfs_unroll_regs);
 		dw_edma_debugfs_create_x32(debugfs_unroll_regs, nr_entries,
 					   regs_dir);
@@ -272,7 +271,7 @@ static void dw_edma_debugfs_regs(void)
 	struct dentry *regs_dir;
 	int nr_entries;
 
-	regs_dir = debugfs_create_dir(REGISTERS_STR, base_dir);
+	regs_dir = debugfs_create_dir(REGISTERS_STR, dw->debugfs);
 	if (!regs_dir)
 		return;
 
@@ -293,19 +292,23 @@ void dw_edma_v0_debugfs_on(struct dw_edma_chip *chip)
 	if (!regs)
 		return;
 
-	base_dir = debugfs_create_dir(dw->name, NULL);
-	if (!base_dir)
+	dw->debugfs = debugfs_create_dir(dw->name, NULL);
+	if (!dw->debugfs)
 		return;
 
-	debugfs_create_u32("version", 0444, base_dir, &dw->version);
-	debugfs_create_u32("mode", 0444, base_dir, &dw->mode);
-	debugfs_create_u16("wr_ch_cnt", 0444, base_dir, &dw->wr_ch_cnt);
-	debugfs_create_u16("rd_ch_cnt", 0444, base_dir, &dw->rd_ch_cnt);
+	debugfs_create_u32("mf", 0444, dw->debugfs, &dw->mf);
+	debugfs_create_u16("wr_ch_cnt", 0444, dw->debugfs, &dw->wr_ch_cnt);
+	debugfs_create_u16("rd_ch_cnt", 0444, dw->debugfs, &dw->rd_ch_cnt);
 
 	dw_edma_debugfs_regs();
 }
 
-void dw_edma_v0_debugfs_off(void)
+void dw_edma_v0_debugfs_off(struct dw_edma_chip *chip)
 {
-	debugfs_remove_recursive(base_dir);
+	dw = chip->dw;
+	if (!dw)
+		return;
+
+	debugfs_remove_recursive(dw->debugfs);
+	dw->debugfs = NULL;
 }
diff --git a/drivers/dma/dw-edma/dw-edma-v0-debugfs.h b/drivers/dma/dw-edma/dw-edma-v0-debugfs.h
index 5450a0a94193..d0ff25a9ea5c 100644
--- a/drivers/dma/dw-edma/dw-edma-v0-debugfs.h
+++ b/drivers/dma/dw-edma/dw-edma-v0-debugfs.h
@@ -13,13 +13,13 @@
 
 #ifdef CONFIG_DEBUG_FS
 void dw_edma_v0_debugfs_on(struct dw_edma_chip *chip);
-void dw_edma_v0_debugfs_off(void);
+void dw_edma_v0_debugfs_off(struct dw_edma_chip *chip);
 #else
 static inline void dw_edma_v0_debugfs_on(struct dw_edma_chip *chip)
 {
 }
 
-static inline void dw_edma_v0_debugfs_off(void)
+static inline void dw_edma_v0_debugfs_off(struct dw_edma_chip *chip)
 {
 }
 #endif /* CONFIG_DEBUG_FS */
diff --git a/drivers/dma/dw-edma/dw-edma-v0-regs.h b/drivers/dma/dw-edma/dw-edma-v0-regs.h
index dfd70e223c2f..e175f7b20480 100644
--- a/drivers/dma/dw-edma/dw-edma-v0-regs.h
+++ b/drivers/dma/dw-edma/dw-edma-v0-regs.h
@@ -25,134 +25,209 @@
 #define EDMA_V0_CH_EVEN_MSI_DATA_MASK			GENMASK(15, 0)
 
 struct dw_edma_v0_ch_regs {
-	u32 ch_control1;				/* 0x000 */
-	u32 ch_control2;				/* 0x004 */
-	u32 transfer_size;				/* 0x008 */
-	u32 sar_low;					/* 0x00c */
-	u32 sar_high;					/* 0x010 */
-	u32 dar_low;					/* 0x014 */
-	u32 dar_high;					/* 0x018 */
-	u32 llp_low;					/* 0x01c */
-	u32 llp_high;					/* 0x020 */
-};
+	u32 ch_control1;				/* 0x0000 */
+	u32 ch_control2;				/* 0x0004 */
+	u32 transfer_size;				/* 0x0008 */
+	union {
+		u64 reg;				/* 0x000c..0x0010 */
+		struct {
+			u32 lsb;			/* 0x000c */
+			u32 msb;			/* 0x0010 */
+		};
+	} sar;
+	union {
+		u64 reg;				/* 0x0014..0x0018 */
+		struct {
+			u32 lsb;			/* 0x0014 */
+			u32 msb;			/* 0x0018 */
+		};
+	} dar;
+	union {
+		u64 reg;				/* 0x001c..0x0020 */
+		struct {
+			u32 lsb;			/* 0x001c */
+			u32 msb;			/* 0x0020 */
+		};
+	} llp;
+} __packed;
 
 struct dw_edma_v0_ch {
-	struct dw_edma_v0_ch_regs wr;			/* 0x200 */
-	u32 padding_1[55];				/* [0x224..0x2fc] */
-	struct dw_edma_v0_ch_regs rd;			/* 0x300 */
-	u32 padding_2[55];				/* [0x324..0x3fc] */
-};
+	struct dw_edma_v0_ch_regs wr;			/* 0x0200 */
+	u32 padding_1[55];				/* 0x0224..0x02fc */
+	struct dw_edma_v0_ch_regs rd;			/* 0x0300 */
+	u32 padding_2[55];				/* 0x0324..0x03fc */
+} __packed;
 
 struct dw_edma_v0_unroll {
-	u32 padding_1;					/* 0x0f8 */
-	u32 wr_engine_chgroup;				/* 0x100 */
-	u32 rd_engine_chgroup;				/* 0x104 */
-	u32 wr_engine_hshake_cnt_low;			/* 0x108 */
-	u32 wr_engine_hshake_cnt_high;			/* 0x10c */
-	u32 padding_2[2];				/* [0x110..0x114] */
-	u32 rd_engine_hshake_cnt_low;			/* 0x118 */
-	u32 rd_engine_hshake_cnt_high;			/* 0x11c */
-	u32 padding_3[2];				/* [0x120..0x124] */
-	u32 wr_ch0_pwr_en;				/* 0x128 */
-	u32 wr_ch1_pwr_en;				/* 0x12c */
-	u32 wr_ch2_pwr_en;				/* 0x130 */
-	u32 wr_ch3_pwr_en;				/* 0x134 */
-	u32 wr_ch4_pwr_en;				/* 0x138 */
-	u32 wr_ch5_pwr_en;				/* 0x13c */
-	u32 wr_ch6_pwr_en;				/* 0x140 */
-	u32 wr_ch7_pwr_en;				/* 0x144 */
-	u32 padding_4[8];				/* [0x148..0x164] */
-	u32 rd_ch0_pwr_en;				/* 0x168 */
-	u32 rd_ch1_pwr_en;				/* 0x16c */
-	u32 rd_ch2_pwr_en;				/* 0x170 */
-	u32 rd_ch3_pwr_en;				/* 0x174 */
-	u32 rd_ch4_pwr_en;				/* 0x178 */
-	u32 rd_ch5_pwr_en;				/* 0x18c */
-	u32 rd_ch6_pwr_en;				/* 0x180 */
-	u32 rd_ch7_pwr_en;				/* 0x184 */
-	u32 padding_5[30];				/* [0x188..0x1fc] */
-	struct dw_edma_v0_ch ch[EDMA_V0_MAX_NR_CH];	/* [0x200..0x1120] */
-};
+	u32 padding_1;					/* 0x00f8 */
+	u32 wr_engine_chgroup;				/* 0x0100 */
+	u32 rd_engine_chgroup;				/* 0x0104 */
+	union {
+		u64 reg;				/* 0x0108..0x010c */
+		struct {
+			u32 lsb;			/* 0x0108 */
+			u32 msb;			/* 0x010c */
+		};
+	} wr_engine_hshake_cnt;
+	u32 padding_2[2];				/* 0x0110..0x0114 */
+	union {
+		u64 reg;				/* 0x0120..0x0124 */
+		struct {
+			u32 lsb;			/* 0x0120 */
+			u32 msb;			/* 0x0124 */
+		};
+	} rd_engine_hshake_cnt;
+	u32 padding_3[2];				/* 0x0120..0x0124 */
+	u32 wr_ch0_pwr_en;				/* 0x0128 */
+	u32 wr_ch1_pwr_en;				/* 0x012c */
+	u32 wr_ch2_pwr_en;				/* 0x0130 */
+	u32 wr_ch3_pwr_en;				/* 0x0134 */
+	u32 wr_ch4_pwr_en;				/* 0x0138 */
+	u32 wr_ch5_pwr_en;				/* 0x013c */
+	u32 wr_ch6_pwr_en;				/* 0x0140 */
+	u32 wr_ch7_pwr_en;				/* 0x0144 */
+	u32 padding_4[8];				/* 0x0148..0x0164 */
+	u32 rd_ch0_pwr_en;				/* 0x0168 */
+	u32 rd_ch1_pwr_en;				/* 0x016c */
+	u32 rd_ch2_pwr_en;				/* 0x0170 */
+	u32 rd_ch3_pwr_en;				/* 0x0174 */
+	u32 rd_ch4_pwr_en;				/* 0x0178 */
+	u32 rd_ch5_pwr_en;				/* 0x018c */
+	u32 rd_ch6_pwr_en;				/* 0x0180 */
+	u32 rd_ch7_pwr_en;				/* 0x0184 */
+	u32 padding_5[30];				/* 0x0188..0x01fc */
+	struct dw_edma_v0_ch ch[EDMA_V0_MAX_NR_CH];	/* 0x0200..0x1120 */
+} __packed;
 
 struct dw_edma_v0_legacy {
-	u32 viewport_sel;				/* 0x0f8 */
-	struct dw_edma_v0_ch_regs ch;			/* [0x100..0x120] */
-};
+	u32 viewport_sel;				/* 0x00f8 */
+	struct dw_edma_v0_ch_regs ch;			/* 0x0100..0x0120 */
+} __packed;
 
 struct dw_edma_v0_regs {
 	/* eDMA global registers */
-	u32 ctrl_data_arb_prior;			/* 0x000 */
-	u32 padding_1;					/* 0x004 */
-	u32 ctrl;					/* 0x008 */
-	u32 wr_engine_en;				/* 0x00c */
-	u32 wr_doorbell;				/* 0x010 */
-	u32 padding_2;					/* 0x014 */
-	u32 wr_ch_arb_weight_low;			/* 0x018 */
-	u32 wr_ch_arb_weight_high;			/* 0x01c */
-	u32 padding_3[3];				/* [0x020..0x028] */
-	u32 rd_engine_en;				/* 0x02c */
-	u32 rd_doorbell;				/* 0x030 */
-	u32 padding_4;					/* 0x034 */
-	u32 rd_ch_arb_weight_low;			/* 0x038 */
-	u32 rd_ch_arb_weight_high;			/* 0x03c */
-	u32 padding_5[3];				/* [0x040..0x048] */
+	u32 ctrl_data_arb_prior;			/* 0x0000 */
+	u32 padding_1;					/* 0x0004 */
+	u32 ctrl;					/* 0x0008 */
+	u32 wr_engine_en;				/* 0x000c */
+	u32 wr_doorbell;				/* 0x0010 */
+	u32 padding_2;					/* 0x0014 */
+	union {
+		u64 reg;				/* 0x0018..0x001c */
+		struct {
+			u32 lsb;			/* 0x0018 */
+			u32 msb;			/* 0x001c */
+		};
+	} wr_ch_arb_weight;
+	u32 padding_3[3];				/* 0x0020..0x0028 */
+	u32 rd_engine_en;				/* 0x002c */
+	u32 rd_doorbell;				/* 0x0030 */
+	u32 padding_4;					/* 0x0034 */
+	union {
+		u64 reg;				/* 0x0038..0x003c */
+		struct {
+			u32 lsb;			/* 0x0038 */
+			u32 msb;			/* 0x003c */
+		};
+	} rd_ch_arb_weight;
+	u32 padding_5[3];				/* 0x0040..0x0048 */
 	/* eDMA interrupts registers */
-	u32 wr_int_status;				/* 0x04c */
-	u32 padding_6;					/* 0x050 */
-	u32 wr_int_mask;				/* 0x054 */
-	u32 wr_int_clear;				/* 0x058 */
-	u32 wr_err_status;				/* 0x05c */
-	u32 wr_done_imwr_low;				/* 0x060 */
-	u32 wr_done_imwr_high;				/* 0x064 */
-	u32 wr_abort_imwr_low;				/* 0x068 */
-	u32 wr_abort_imwr_high;				/* 0x06c */
-	u32 wr_ch01_imwr_data;				/* 0x070 */
-	u32 wr_ch23_imwr_data;				/* 0x074 */
-	u32 wr_ch45_imwr_data;				/* 0x078 */
-	u32 wr_ch67_imwr_data;				/* 0x07c */
-	u32 padding_7[4];				/* [0x080..0x08c] */
-	u32 wr_linked_list_err_en;			/* 0x090 */
-	u32 padding_8[3];				/* [0x094..0x09c] */
-	u32 rd_int_status;				/* 0x0a0 */
-	u32 padding_9;					/* 0x0a4 */
-	u32 rd_int_mask;				/* 0x0a8 */
-	u32 rd_int_clear;				/* 0x0ac */
-	u32 padding_10;					/* 0x0b0 */
-	u32 rd_err_status_low;				/* 0x0b4 */
-	u32 rd_err_status_high;				/* 0x0b8 */
-	u32 padding_11[2];				/* [0x0bc..0x0c0] */
-	u32 rd_linked_list_err_en;			/* 0x0c4 */
-	u32 padding_12;					/* 0x0c8 */
-	u32 rd_done_imwr_low;				/* 0x0cc */
-	u32 rd_done_imwr_high;				/* 0x0d0 */
-	u32 rd_abort_imwr_low;				/* 0x0d4 */
-	u32 rd_abort_imwr_high;				/* 0x0d8 */
-	u32 rd_ch01_imwr_data;				/* 0x0dc */
-	u32 rd_ch23_imwr_data;				/* 0x0e0 */
-	u32 rd_ch45_imwr_data;				/* 0x0e4 */
-	u32 rd_ch67_imwr_data;				/* 0x0e8 */
-	u32 padding_13[4];				/* [0x0ec..0x0f8] */
+	u32 wr_int_status;				/* 0x004c */
+	u32 padding_6;					/* 0x0050 */
+	u32 wr_int_mask;				/* 0x0054 */
+	u32 wr_int_clear;				/* 0x0058 */
+	u32 wr_err_status;				/* 0x005c */
+	union {
+		u64 reg;				/* 0x0060..0x0064 */
+		struct {
+			u32 lsb;			/* 0x0060 */
+			u32 msb;			/* 0x0064 */
+		};
+	} wr_done_imwr;
+	union {
+		u64 reg;				/* 0x0068..0x006c */
+		struct {
+			u32 lsb;			/* 0x0068 */
+			u32 msb;			/* 0x006c */
+		};
+	} wr_abort_imwr;
+	u32 wr_ch01_imwr_data;				/* 0x0070 */
+	u32 wr_ch23_imwr_data;				/* 0x0074 */
+	u32 wr_ch45_imwr_data;				/* 0x0078 */
+	u32 wr_ch67_imwr_data;				/* 0x007c */
+	u32 padding_7[4];				/* 0x0080..0x008c */
+	u32 wr_linked_list_err_en;			/* 0x0090 */
+	u32 padding_8[3];				/* 0x0094..0x009c */
+	u32 rd_int_status;				/* 0x00a0 */
+	u32 padding_9;					/* 0x00a4 */
+	u32 rd_int_mask;				/* 0x00a8 */
+	u32 rd_int_clear;				/* 0x00ac */
+	u32 padding_10;					/* 0x00b0 */
+	union {
+		u64 reg;				/* 0x00b4..0x00b8 */
+		struct {
+			u32 lsb;			/* 0x00b4 */
+			u32 msb;			/* 0x00b8 */
+		};
+	} rd_err_status;
+	u32 padding_11[2];				/* 0x00bc..0x00c0 */
+	u32 rd_linked_list_err_en;			/* 0x00c4 */
+	u32 padding_12;					/* 0x00c8 */
+	union {
+		u64 reg;				/* 0x00cc..0x00d0 */
+		struct {
+			u32 lsb;			/* 0x00cc */
+			u32 msb;			/* 0x00d0 */
+		};
+	} rd_done_imwr;
+	union {
+		u64 reg;				/* 0x00d4..0x00d8 */
+		struct {
+			u32 lsb;			/* 0x00d4 */
+			u32 msb;			/* 0x00d8 */
+		};
+	} rd_abort_imwr;
+	u32 rd_ch01_imwr_data;				/* 0x00dc */
+	u32 rd_ch23_imwr_data;				/* 0x00e0 */
+	u32 rd_ch45_imwr_data;				/* 0x00e4 */
+	u32 rd_ch67_imwr_data;				/* 0x00e8 */
+	u32 padding_13[4];				/* 0x00ec..0x00f8 */
 	/* eDMA channel context grouping */
 	union dw_edma_v0_type {
-		struct dw_edma_v0_legacy legacy;	/* [0x0f8..0x120] */
-		struct dw_edma_v0_unroll unroll;	/* [0x0f8..0x1120] */
+		struct dw_edma_v0_legacy legacy;	/* 0x00f8..0x0120 */
+		struct dw_edma_v0_unroll unroll;	/* 0x00f8..0x1120 */
 	} type;
-};
+} __packed;
 
 struct dw_edma_v0_lli {
 	u32 control;
 	u32 transfer_size;
-	u32 sar_low;
-	u32 sar_high;
-	u32 dar_low;
-	u32 dar_high;
-};
+	union {
+		u64 reg;
+		struct {
+			u32 lsb;
+			u32 msb;
+		};
+	} sar;
+	union {
+		u64 reg;
+		struct {
+			u32 lsb;
+			u32 msb;
+		};
+	} dar;
+} __packed;
 
 struct dw_edma_v0_llp {
 	u32 control;
 	u32 reserved;
-	u32 llp_low;
-	u32 llp_high;
-};
+	union {
+		u64 reg;
+		struct {
+			u32 lsb;
+			u32 msb;
+		};
+	} llp;
+} __packed;
 
 #endif /* _DW_EDMA_V0_REGS_H */
diff --git a/drivers/dma/idxd/Makefile b/drivers/dma/idxd/Makefile
index 8978b898d777..6d11558756f8 100644
--- a/drivers/dma/idxd/Makefile
+++ b/drivers/dma/idxd/Makefile
@@ -1,2 +1,4 @@
 obj-$(CONFIG_INTEL_IDXD) += idxd.o
 idxd-y := init.o irq.o device.o sysfs.o submit.o dma.o cdev.o
+
+idxd-$(CONFIG_INTEL_IDXD_PERFMON) += perfmon.o
diff --git a/drivers/dma/idxd/cdev.c b/drivers/dma/idxd/cdev.c
index 0db9b82ed8cf..302cba5ff779 100644
--- a/drivers/dma/idxd/cdev.c
+++ b/drivers/dma/idxd/cdev.c
@@ -39,15 +39,15 @@ struct idxd_user_context {
 	struct iommu_sva *sva;
 };
 
-enum idxd_cdev_cleanup {
-	CDEV_NORMAL = 0,
-	CDEV_FAILED,
-};
-
 static void idxd_cdev_dev_release(struct device *dev)
 {
-	dev_dbg(dev, "releasing cdev device\n");
-	kfree(dev);
+	struct idxd_cdev *idxd_cdev = container_of(dev, struct idxd_cdev, dev);
+	struct idxd_cdev_context *cdev_ctx;
+	struct idxd_wq *wq = idxd_cdev->wq;
+
+	cdev_ctx = &ictx[wq->idxd->data->type];
+	ida_simple_remove(&cdev_ctx->minor_ida, idxd_cdev->minor);
+	kfree(idxd_cdev);
 }
 
 static struct device_type idxd_cdev_device_type = {
@@ -62,14 +62,11 @@ static inline struct idxd_cdev *inode_idxd_cdev(struct inode *inode)
 	return container_of(cdev, struct idxd_cdev, cdev);
 }
 
-static inline struct idxd_wq *idxd_cdev_wq(struct idxd_cdev *idxd_cdev)
-{
-	return container_of(idxd_cdev, struct idxd_wq, idxd_cdev);
-}
-
 static inline struct idxd_wq *inode_wq(struct inode *inode)
 {
-	return idxd_cdev_wq(inode_idxd_cdev(inode));
+	struct idxd_cdev *idxd_cdev = inode_idxd_cdev(inode);
+
+	return idxd_cdev->wq;
 }
 
 static int idxd_cdev_open(struct inode *inode, struct file *filp)
@@ -220,11 +217,10 @@ static __poll_t idxd_cdev_poll(struct file *filp,
 	struct idxd_user_context *ctx = filp->private_data;
 	struct idxd_wq *wq = ctx->wq;
 	struct idxd_device *idxd = wq->idxd;
-	struct idxd_cdev *idxd_cdev = &wq->idxd_cdev;
 	unsigned long flags;
 	__poll_t out = 0;
 
-	poll_wait(filp, &idxd_cdev->err_queue, wait);
+	poll_wait(filp, &wq->err_queue, wait);
 	spin_lock_irqsave(&idxd->dev_lock, flags);
 	if (idxd->sw_err.valid)
 		out = EPOLLIN | EPOLLRDNORM;
@@ -243,101 +239,69 @@ static const struct file_operations idxd_cdev_fops = {
 
 int idxd_cdev_get_major(struct idxd_device *idxd)
 {
-	return MAJOR(ictx[idxd->type].devt);
+	return MAJOR(ictx[idxd->data->type].devt);
 }
 
-static int idxd_wq_cdev_dev_setup(struct idxd_wq *wq)
+int idxd_wq_add_cdev(struct idxd_wq *wq)
 {
 	struct idxd_device *idxd = wq->idxd;
-	struct idxd_cdev *idxd_cdev = &wq->idxd_cdev;
-	struct idxd_cdev_context *cdev_ctx;
+	struct idxd_cdev *idxd_cdev;
+	struct cdev *cdev;
 	struct device *dev;
-	int minor, rc;
+	struct idxd_cdev_context *cdev_ctx;
+	int rc, minor;
 
-	idxd_cdev->dev = kzalloc(sizeof(*idxd_cdev->dev), GFP_KERNEL);
-	if (!idxd_cdev->dev)
+	idxd_cdev = kzalloc(sizeof(*idxd_cdev), GFP_KERNEL);
+	if (!idxd_cdev)
 		return -ENOMEM;
 
-	dev = idxd_cdev->dev;
-	dev->parent = &idxd->pdev->dev;
-	dev_set_name(dev, "%s/wq%u.%u", idxd_get_dev_name(idxd),
-		     idxd->id, wq->id);
-	dev->bus = idxd_get_bus_type(idxd);
-
-	cdev_ctx = &ictx[wq->idxd->type];
+	idxd_cdev->wq = wq;
+	cdev = &idxd_cdev->cdev;
+	dev = &idxd_cdev->dev;
+	cdev_ctx = &ictx[wq->idxd->data->type];
 	minor = ida_simple_get(&cdev_ctx->minor_ida, 0, MINORMASK, GFP_KERNEL);
 	if (minor < 0) {
-		rc = minor;
-		kfree(dev);
-		goto ida_err;
-	}
-
-	dev->devt = MKDEV(MAJOR(cdev_ctx->devt), minor);
-	dev->type = &idxd_cdev_device_type;
-	rc = device_register(dev);
-	if (rc < 0) {
-		dev_err(&idxd->pdev->dev, "device register failed\n");
-		goto dev_reg_err;
+		kfree(idxd_cdev);
+		return minor;
 	}
 	idxd_cdev->minor = minor;
 
-	return 0;
-
- dev_reg_err:
-	ida_simple_remove(&cdev_ctx->minor_ida, MINOR(dev->devt));
-	put_device(dev);
- ida_err:
-	idxd_cdev->dev = NULL;
-	return rc;
-}
-
-static void idxd_wq_cdev_cleanup(struct idxd_wq *wq,
-				 enum idxd_cdev_cleanup cdev_state)
-{
-	struct idxd_cdev *idxd_cdev = &wq->idxd_cdev;
-	struct idxd_cdev_context *cdev_ctx;
-
-	cdev_ctx = &ictx[wq->idxd->type];
-	if (cdev_state == CDEV_NORMAL)
-		cdev_del(&idxd_cdev->cdev);
-	device_unregister(idxd_cdev->dev);
-	/*
-	 * The device_type->release() will be called on the device and free
-	 * the allocated struct device. We can just forget it.
-	 */
-	ida_simple_remove(&cdev_ctx->minor_ida, idxd_cdev->minor);
-	idxd_cdev->dev = NULL;
-	idxd_cdev->minor = -1;
-}
-
-int idxd_wq_add_cdev(struct idxd_wq *wq)
-{
-	struct idxd_cdev *idxd_cdev = &wq->idxd_cdev;
-	struct cdev *cdev = &idxd_cdev->cdev;
-	struct device *dev;
-	int rc;
+	device_initialize(dev);
+	dev->parent = &wq->conf_dev;
+	dev->bus = &dsa_bus_type;
+	dev->type = &idxd_cdev_device_type;
+	dev->devt = MKDEV(MAJOR(cdev_ctx->devt), minor);
 
-	rc = idxd_wq_cdev_dev_setup(wq);
+	rc = dev_set_name(dev, "%s/wq%u.%u", idxd->data->name_prefix, idxd->id, wq->id);
 	if (rc < 0)
-		return rc;
+		goto err;
 
-	dev = idxd_cdev->dev;
+	wq->idxd_cdev = idxd_cdev;
 	cdev_init(cdev, &idxd_cdev_fops);
-	cdev_set_parent(cdev, &dev->kobj);
-	rc = cdev_add(cdev, dev->devt, 1);
+	rc = cdev_device_add(cdev, dev);
 	if (rc) {
 		dev_dbg(&wq->idxd->pdev->dev, "cdev_add failed: %d\n", rc);
-		idxd_wq_cdev_cleanup(wq, CDEV_FAILED);
-		return rc;
+		goto err;
 	}
 
-	init_waitqueue_head(&idxd_cdev->err_queue);
 	return 0;
+
+ err:
+	put_device(dev);
+	wq->idxd_cdev = NULL;
+	return rc;
 }
 
 void idxd_wq_del_cdev(struct idxd_wq *wq)
 {
-	idxd_wq_cdev_cleanup(wq, CDEV_NORMAL);
+	struct idxd_cdev *idxd_cdev;
+	struct idxd_cdev_context *cdev_ctx;
+
+	cdev_ctx = &ictx[wq->idxd->data->type];
+	idxd_cdev = wq->idxd_cdev;
+	wq->idxd_cdev = NULL;
+	cdev_device_del(&idxd_cdev->cdev, &idxd_cdev->dev);
+	put_device(&idxd_cdev->dev);
 }
 
 int idxd_cdev_register(void)
diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c
index 31c819544a22..420b93fe5feb 100644
--- a/drivers/dma/idxd/device.c
+++ b/drivers/dma/idxd/device.c
@@ -19,7 +19,7 @@ static void idxd_cmd_exec(struct idxd_device *idxd, int cmd_code, u32 operand,
 /* Interrupt control bits */
 void idxd_mask_msix_vector(struct idxd_device *idxd, int vec_id)
 {
-	struct irq_data *data = irq_get_irq_data(idxd->msix_entries[vec_id].vector);
+	struct irq_data *data = irq_get_irq_data(idxd->irq_entries[vec_id].vector);
 
 	pci_msi_mask_irq(data);
 }
@@ -36,7 +36,7 @@ void idxd_mask_msix_vectors(struct idxd_device *idxd)
 
 void idxd_unmask_msix_vector(struct idxd_device *idxd, int vec_id)
 {
-	struct irq_data *data = irq_get_irq_data(idxd->msix_entries[vec_id].vector);
+	struct irq_data *data = irq_get_irq_data(idxd->irq_entries[vec_id].vector);
 
 	pci_msi_unmask_irq(data);
 }
@@ -47,6 +47,7 @@ void idxd_unmask_error_interrupts(struct idxd_device *idxd)
 
 	genctrl.bits = ioread32(idxd->reg_base + IDXD_GENCTRL_OFFSET);
 	genctrl.softerr_int_en = 1;
+	genctrl.halt_int_en = 1;
 	iowrite32(genctrl.bits, idxd->reg_base + IDXD_GENCTRL_OFFSET);
 }
 
@@ -56,6 +57,7 @@ void idxd_mask_error_interrupts(struct idxd_device *idxd)
 
 	genctrl.bits = ioread32(idxd->reg_base + IDXD_GENCTRL_OFFSET);
 	genctrl.softerr_int_en = 0;
+	genctrl.halt_int_en = 0;
 	iowrite32(genctrl.bits, idxd->reg_base + IDXD_GENCTRL_OFFSET);
 }
 
@@ -144,14 +146,8 @@ int idxd_wq_alloc_resources(struct idxd_wq *wq)
 	if (rc < 0)
 		return rc;
 
-	if (idxd->type == IDXD_TYPE_DSA)
-		align = 32;
-	else if (idxd->type == IDXD_TYPE_IAX)
-		align = 64;
-	else
-		return -ENODEV;
-
-	wq->compls_size = num_descs * idxd->compl_size + align;
+	align = idxd->data->align;
+	wq->compls_size = num_descs * idxd->data->compl_size + align;
 	wq->compls_raw = dma_alloc_coherent(dev, wq->compls_size,
 					    &wq->compls_addr_raw, GFP_KERNEL);
 	if (!wq->compls_raw) {
@@ -178,16 +174,14 @@ int idxd_wq_alloc_resources(struct idxd_wq *wq)
 		struct idxd_desc *desc = wq->descs[i];
 
 		desc->hw = wq->hw_descs[i];
-		if (idxd->type == IDXD_TYPE_DSA)
+		if (idxd->data->type == IDXD_TYPE_DSA)
 			desc->completion = &wq->compls[i];
-		else if (idxd->type == IDXD_TYPE_IAX)
+		else if (idxd->data->type == IDXD_TYPE_IAX)
 			desc->iax_completion = &wq->iax_compls[i];
-		desc->compl_dma = wq->compls_addr + idxd->compl_size * i;
+		desc->compl_dma = wq->compls_addr + idxd->data->compl_size * i;
 		desc->id = i;
 		desc->wq = wq;
 		desc->cpu = -1;
-		dma_async_tx_descriptor_init(&desc->txd, &wq->dma_chan);
-		desc->txd.tx_submit = idxd_dma_tx_submit;
 	}
 
 	return 0;
@@ -320,6 +314,19 @@ void idxd_wq_unmap_portal(struct idxd_wq *wq)
 	struct device *dev = &wq->idxd->pdev->dev;
 
 	devm_iounmap(dev, wq->portal);
+	wq->portal = NULL;
+}
+
+void idxd_wqs_unmap_portal(struct idxd_device *idxd)
+{
+	int i;
+
+	for (i = 0; i < idxd->max_wqs; i++) {
+		struct idxd_wq *wq = idxd->wqs[i];
+
+		if (wq->portal)
+			idxd_wq_unmap_portal(wq);
+	}
 }
 
 int idxd_wq_set_pasid(struct idxd_wq *wq, int pasid)
@@ -392,6 +399,32 @@ void idxd_wq_disable_cleanup(struct idxd_wq *wq)
 	memset(wq->name, 0, WQ_NAME_SIZE);
 }
 
+static void idxd_wq_ref_release(struct percpu_ref *ref)
+{
+	struct idxd_wq *wq = container_of(ref, struct idxd_wq, wq_active);
+
+	complete(&wq->wq_dead);
+}
+
+int idxd_wq_init_percpu_ref(struct idxd_wq *wq)
+{
+	int rc;
+
+	memset(&wq->wq_active, 0, sizeof(wq->wq_active));
+	rc = percpu_ref_init(&wq->wq_active, idxd_wq_ref_release, 0, GFP_KERNEL);
+	if (rc < 0)
+		return rc;
+	reinit_completion(&wq->wq_dead);
+	return 0;
+}
+
+void idxd_wq_quiesce(struct idxd_wq *wq)
+{
+	percpu_ref_kill(&wq->wq_active);
+	wait_for_completion(&wq->wq_dead);
+	percpu_ref_exit(&wq->wq_active);
+}
+
 /* Device control bits */
 static inline bool idxd_is_enabled(struct idxd_device *idxd)
 {
@@ -432,13 +465,13 @@ int idxd_device_init_reset(struct idxd_device *idxd)
 	memset(&cmd, 0, sizeof(cmd));
 	cmd.cmd = IDXD_CMD_RESET_DEVICE;
 	dev_dbg(dev, "%s: sending reset for init.\n", __func__);
-	spin_lock_irqsave(&idxd->dev_lock, flags);
+	spin_lock_irqsave(&idxd->cmd_lock, flags);
 	iowrite32(cmd.bits, idxd->reg_base + IDXD_CMD_OFFSET);
 
 	while (ioread32(idxd->reg_base + IDXD_CMDSTS_OFFSET) &
 	       IDXD_CMDSTS_ACTIVE)
 		cpu_relax();
-	spin_unlock_irqrestore(&idxd->dev_lock, flags);
+	spin_unlock_irqrestore(&idxd->cmd_lock, flags);
 	return 0;
 }
 
@@ -451,7 +484,8 @@ static void idxd_cmd_exec(struct idxd_device *idxd, int cmd_code, u32 operand,
 
 	if (idxd_device_is_halted(idxd)) {
 		dev_warn(&idxd->pdev->dev, "Device is HALTED!\n");
-		*status = IDXD_CMDSTS_HW_ERR;
+		if (status)
+			*status = IDXD_CMDSTS_HW_ERR;
 		return;
 	}
 
@@ -460,10 +494,10 @@ static void idxd_cmd_exec(struct idxd_device *idxd, int cmd_code, u32 operand,
 	cmd.operand = operand;
 	cmd.int_req = 1;
 
-	spin_lock_irqsave(&idxd->dev_lock, flags);
+	spin_lock_irqsave(&idxd->cmd_lock, flags);
 	wait_event_lock_irq(idxd->cmd_waitq,
 			    !test_bit(IDXD_FLAG_CMD_RUNNING, &idxd->flags),
-			    idxd->dev_lock);
+			    idxd->cmd_lock);
 
 	dev_dbg(&idxd->pdev->dev, "%s: sending cmd: %#x op: %#x\n",
 		__func__, cmd_code, operand);
@@ -477,9 +511,9 @@ static void idxd_cmd_exec(struct idxd_device *idxd, int cmd_code, u32 operand,
 	 * After command submitted, release lock and go to sleep until
 	 * the command completes via interrupt.
 	 */
-	spin_unlock_irqrestore(&idxd->dev_lock, flags);
+	spin_unlock_irqrestore(&idxd->cmd_lock, flags);
 	wait_for_completion(&done);
-	spin_lock_irqsave(&idxd->dev_lock, flags);
+	spin_lock_irqsave(&idxd->cmd_lock, flags);
 	if (status) {
 		*status = ioread32(idxd->reg_base + IDXD_CMDSTS_OFFSET);
 		idxd->cmd_status = *status & GENMASK(7, 0);
@@ -488,7 +522,7 @@ static void idxd_cmd_exec(struct idxd_device *idxd, int cmd_code, u32 operand,
 	__clear_bit(IDXD_FLAG_CMD_RUNNING, &idxd->flags);
 	/* Wake up other pending commands */
 	wake_up(&idxd->cmd_waitq);
-	spin_unlock_irqrestore(&idxd->dev_lock, flags);
+	spin_unlock_irqrestore(&idxd->cmd_lock, flags);
 }
 
 int idxd_device_enable(struct idxd_device *idxd)
@@ -521,7 +555,7 @@ void idxd_device_wqs_clear_state(struct idxd_device *idxd)
 	lockdep_assert_held(&idxd->dev_lock);
 
 	for (i = 0; i < idxd->max_wqs; i++) {
-		struct idxd_wq *wq = &idxd->wqs[i];
+		struct idxd_wq *wq = idxd->wqs[i];
 
 		if (wq->state == IDXD_WQ_ENABLED) {
 			idxd_wq_disable_cleanup(wq);
@@ -579,6 +613,77 @@ void idxd_device_drain_pasid(struct idxd_device *idxd, int pasid)
 	dev_dbg(dev, "pasid %d drained\n", pasid);
 }
 
+int idxd_device_request_int_handle(struct idxd_device *idxd, int idx, int *handle,
+				   enum idxd_interrupt_type irq_type)
+{
+	struct device *dev = &idxd->pdev->dev;
+	u32 operand, status;
+
+	if (!(idxd->hw.cmd_cap & BIT(IDXD_CMD_REQUEST_INT_HANDLE)))
+		return -EOPNOTSUPP;
+
+	dev_dbg(dev, "get int handle, idx %d\n", idx);
+
+	operand = idx & GENMASK(15, 0);
+	if (irq_type == IDXD_IRQ_IMS)
+		operand |= CMD_INT_HANDLE_IMS;
+
+	dev_dbg(dev, "cmd: %u operand: %#x\n", IDXD_CMD_REQUEST_INT_HANDLE, operand);
+
+	idxd_cmd_exec(idxd, IDXD_CMD_REQUEST_INT_HANDLE, operand, &status);
+
+	if ((status & IDXD_CMDSTS_ERR_MASK) != IDXD_CMDSTS_SUCCESS) {
+		dev_dbg(dev, "request int handle failed: %#x\n", status);
+		return -ENXIO;
+	}
+
+	*handle = (status >> IDXD_CMDSTS_RES_SHIFT) & GENMASK(15, 0);
+
+	dev_dbg(dev, "int handle acquired: %u\n", *handle);
+	return 0;
+}
+
+int idxd_device_release_int_handle(struct idxd_device *idxd, int handle,
+				   enum idxd_interrupt_type irq_type)
+{
+	struct device *dev = &idxd->pdev->dev;
+	u32 operand, status;
+	union idxd_command_reg cmd;
+	unsigned long flags;
+
+	if (!(idxd->hw.cmd_cap & BIT(IDXD_CMD_RELEASE_INT_HANDLE)))
+		return -EOPNOTSUPP;
+
+	dev_dbg(dev, "release int handle, handle %d\n", handle);
+
+	memset(&cmd, 0, sizeof(cmd));
+	operand = handle & GENMASK(15, 0);
+
+	if (irq_type == IDXD_IRQ_IMS)
+		operand |= CMD_INT_HANDLE_IMS;
+
+	cmd.cmd = IDXD_CMD_RELEASE_INT_HANDLE;
+	cmd.operand = operand;
+
+	dev_dbg(dev, "cmd: %u operand: %#x\n", IDXD_CMD_RELEASE_INT_HANDLE, operand);
+
+	spin_lock_irqsave(&idxd->cmd_lock, flags);
+	iowrite32(cmd.bits, idxd->reg_base + IDXD_CMD_OFFSET);
+
+	while (ioread32(idxd->reg_base + IDXD_CMDSTS_OFFSET) & IDXD_CMDSTS_ACTIVE)
+		cpu_relax();
+	status = ioread32(idxd->reg_base + IDXD_CMDSTS_OFFSET);
+	spin_unlock_irqrestore(&idxd->cmd_lock, flags);
+
+	if ((status & IDXD_CMDSTS_ERR_MASK) != IDXD_CMDSTS_SUCCESS) {
+		dev_dbg(dev, "release int handle failed: %#x\n", status);
+		return -ENXIO;
+	}
+
+	dev_dbg(dev, "int handle released.\n");
+	return 0;
+}
+
 /* Device configuration bits */
 void idxd_msix_perm_setup(struct idxd_device *idxd)
 {
@@ -660,7 +765,7 @@ static int idxd_groups_config_write(struct idxd_device *idxd)
 		ioread32(idxd->reg_base + IDXD_GENCFG_OFFSET));
 
 	for (i = 0; i < idxd->max_groups; i++) {
-		struct idxd_group *group = &idxd->groups[i];
+		struct idxd_group *group = idxd->groups[i];
 
 		idxd_group_config_write(group);
 	}
@@ -739,7 +844,7 @@ static int idxd_wqs_config_write(struct idxd_device *idxd)
 	int i, rc;
 
 	for (i = 0; i < idxd->max_wqs; i++) {
-		struct idxd_wq *wq = &idxd->wqs[i];
+		struct idxd_wq *wq = idxd->wqs[i];
 
 		rc = idxd_wq_config_write(wq);
 		if (rc < 0)
@@ -755,7 +860,7 @@ static void idxd_group_flags_setup(struct idxd_device *idxd)
 
 	/* TC-A 0 and TC-B 1 should be defaults */
 	for (i = 0; i < idxd->max_groups; i++) {
-		struct idxd_group *group = &idxd->groups[i];
+		struct idxd_group *group = idxd->groups[i];
 
 		if (group->tc_a == -1)
 			group->tc_a = group->grpcfg.flags.tc_a = 0;
@@ -782,12 +887,12 @@ static int idxd_engines_setup(struct idxd_device *idxd)
 	struct idxd_group *group;
 
 	for (i = 0; i < idxd->max_groups; i++) {
-		group = &idxd->groups[i];
+		group = idxd->groups[i];
 		group->grpcfg.engines = 0;
 	}
 
 	for (i = 0; i < idxd->max_engines; i++) {
-		eng = &idxd->engines[i];
+		eng = idxd->engines[i];
 		group = eng->group;
 
 		if (!group)
@@ -811,13 +916,13 @@ static int idxd_wqs_setup(struct idxd_device *idxd)
 	struct device *dev = &idxd->pdev->dev;
 
 	for (i = 0; i < idxd->max_groups; i++) {
-		group = &idxd->groups[i];
+		group = idxd->groups[i];
 		for (j = 0; j < 4; j++)
 			group->grpcfg.wqs[j] = 0;
 	}
 
 	for (i = 0; i < idxd->max_wqs; i++) {
-		wq = &idxd->wqs[i];
+		wq = idxd->wqs[i];
 		group = wq->group;
 
 		if (!wq->group)
@@ -865,3 +970,119 @@ int idxd_device_config(struct idxd_device *idxd)
 
 	return 0;
 }
+
+static int idxd_wq_load_config(struct idxd_wq *wq)
+{
+	struct idxd_device *idxd = wq->idxd;
+	struct device *dev = &idxd->pdev->dev;
+	int wqcfg_offset;
+	int i;
+
+	wqcfg_offset = WQCFG_OFFSET(idxd, wq->id, 0);
+	memcpy_fromio(wq->wqcfg, idxd->reg_base + wqcfg_offset, idxd->wqcfg_size);
+
+	wq->size = wq->wqcfg->wq_size;
+	wq->threshold = wq->wqcfg->wq_thresh;
+	if (wq->wqcfg->priv)
+		wq->type = IDXD_WQT_KERNEL;
+
+	/* The driver does not support shared WQ mode in read-only config yet */
+	if (wq->wqcfg->mode == 0 || wq->wqcfg->pasid_en)
+		return -EOPNOTSUPP;
+
+	set_bit(WQ_FLAG_DEDICATED, &wq->flags);
+
+	wq->priority = wq->wqcfg->priority;
+
+	for (i = 0; i < WQCFG_STRIDES(idxd); i++) {
+		wqcfg_offset = WQCFG_OFFSET(idxd, wq->id, i);
+		dev_dbg(dev, "WQ[%d][%d][%#x]: %#x\n", wq->id, i, wqcfg_offset, wq->wqcfg->bits[i]);
+	}
+
+	return 0;
+}
+
+static void idxd_group_load_config(struct idxd_group *group)
+{
+	struct idxd_device *idxd = group->idxd;
+	struct device *dev = &idxd->pdev->dev;
+	int i, j, grpcfg_offset;
+
+	/*
+	 * Load WQS bit fields
+	 * Iterate through all 256 bits 64 bits at a time
+	 */
+	for (i = 0; i < GRPWQCFG_STRIDES; i++) {
+		struct idxd_wq *wq;
+
+		grpcfg_offset = GRPWQCFG_OFFSET(idxd, group->id, i);
+		group->grpcfg.wqs[i] = ioread64(idxd->reg_base + grpcfg_offset);
+		dev_dbg(dev, "GRPCFG wq[%d:%d: %#x]: %#llx\n",
+			group->id, i, grpcfg_offset, group->grpcfg.wqs[i]);
+
+		if (i * 64 >= idxd->max_wqs)
+			break;
+
+		/* Iterate through all 64 bits and check for wq set */
+		for (j = 0; j < 64; j++) {
+			int id = i * 64 + j;
+
+			/* No need to check beyond max wqs */
+			if (id >= idxd->max_wqs)
+				break;
+
+			/* Set group assignment for wq if wq bit is set */
+			if (group->grpcfg.wqs[i] & BIT(j)) {
+				wq = idxd->wqs[id];
+				wq->group = group;
+			}
+		}
+	}
+
+	grpcfg_offset = GRPENGCFG_OFFSET(idxd, group->id);
+	group->grpcfg.engines = ioread64(idxd->reg_base + grpcfg_offset);
+	dev_dbg(dev, "GRPCFG engs[%d: %#x]: %#llx\n", group->id,
+		grpcfg_offset, group->grpcfg.engines);
+
+	/* Iterate through all 64 bits to check engines set */
+	for (i = 0; i < 64; i++) {
+		if (i >= idxd->max_engines)
+			break;
+
+		if (group->grpcfg.engines & BIT(i)) {
+			struct idxd_engine *engine = idxd->engines[i];
+
+			engine->group = group;
+		}
+	}
+
+	grpcfg_offset = GRPFLGCFG_OFFSET(idxd, group->id);
+	group->grpcfg.flags.bits = ioread32(idxd->reg_base + grpcfg_offset);
+	dev_dbg(dev, "GRPFLAGS flags[%d: %#x]: %#x\n",
+		group->id, grpcfg_offset, group->grpcfg.flags.bits);
+}
+
+int idxd_device_load_config(struct idxd_device *idxd)
+{
+	union gencfg_reg reg;
+	int i, rc;
+
+	reg.bits = ioread32(idxd->reg_base + IDXD_GENCFG_OFFSET);
+	idxd->token_limit = reg.token_limit;
+
+	for (i = 0; i < idxd->max_groups; i++) {
+		struct idxd_group *group = idxd->groups[i];
+
+		idxd_group_load_config(group);
+	}
+
+	for (i = 0; i < idxd->max_wqs; i++) {
+		struct idxd_wq *wq = idxd->wqs[i];
+
+		rc = idxd_wq_load_config(wq);
+		if (rc < 0)
+			return rc;
+	}
+
+	return 0;
+}
diff --git a/drivers/dma/idxd/dma.c b/drivers/dma/idxd/dma.c
index a15e50126434..77439b645044 100644
--- a/drivers/dma/idxd/dma.c
+++ b/drivers/dma/idxd/dma.c
@@ -14,7 +14,10 @@
 
 static inline struct idxd_wq *to_idxd_wq(struct dma_chan *c)
 {
-	return container_of(c, struct idxd_wq, dma_chan);
+	struct idxd_dma_chan *idxd_chan;
+
+	idxd_chan = container_of(c, struct idxd_dma_chan, chan);
+	return idxd_chan->wq;
 }
 
 void idxd_dma_complete_txd(struct idxd_desc *desc,
@@ -135,7 +138,7 @@ static void idxd_dma_issue_pending(struct dma_chan *dma_chan)
 {
 }
 
-dma_cookie_t idxd_dma_tx_submit(struct dma_async_tx_descriptor *tx)
+static dma_cookie_t idxd_dma_tx_submit(struct dma_async_tx_descriptor *tx)
 {
 	struct dma_chan *c = tx->chan;
 	struct idxd_wq *wq = to_idxd_wq(c);
@@ -156,14 +159,25 @@ dma_cookie_t idxd_dma_tx_submit(struct dma_async_tx_descriptor *tx)
 
 static void idxd_dma_release(struct dma_device *device)
 {
+	struct idxd_dma_dev *idxd_dma = container_of(device, struct idxd_dma_dev, dma);
+
+	kfree(idxd_dma);
 }
 
 int idxd_register_dma_device(struct idxd_device *idxd)
 {
-	struct dma_device *dma = &idxd->dma_dev;
+	struct idxd_dma_dev *idxd_dma;
+	struct dma_device *dma;
+	struct device *dev = &idxd->pdev->dev;
+	int rc;
 
+	idxd_dma = kzalloc_node(sizeof(*idxd_dma), GFP_KERNEL, dev_to_node(dev));
+	if (!idxd_dma)
+		return -ENOMEM;
+
+	dma = &idxd_dma->dma;
 	INIT_LIST_HEAD(&dma->channels);
-	dma->dev = &idxd->pdev->dev;
+	dma->dev = dev;
 
 	dma_cap_set(DMA_PRIVATE, dma->cap_mask);
 	dma_cap_set(DMA_COMPLETION_NO_ORDER, dma->cap_mask);
@@ -179,35 +193,72 @@ int idxd_register_dma_device(struct idxd_device *idxd)
 	dma->device_alloc_chan_resources = idxd_dma_alloc_chan_resources;
 	dma->device_free_chan_resources = idxd_dma_free_chan_resources;
 
-	return dma_async_device_register(&idxd->dma_dev);
+	rc = dma_async_device_register(dma);
+	if (rc < 0) {
+		kfree(idxd_dma);
+		return rc;
+	}
+
+	idxd_dma->idxd = idxd;
+	/*
+	 * This pointer is protected by the refs taken by the dma_chan. It will remain valid
+	 * as long as there are outstanding channels.
+	 */
+	idxd->idxd_dma = idxd_dma;
+	return 0;
 }
 
 void idxd_unregister_dma_device(struct idxd_device *idxd)
 {
-	dma_async_device_unregister(&idxd->dma_dev);
+	dma_async_device_unregister(&idxd->idxd_dma->dma);
 }
 
 int idxd_register_dma_channel(struct idxd_wq *wq)
 {
 	struct idxd_device *idxd = wq->idxd;
-	struct dma_device *dma = &idxd->dma_dev;
-	struct dma_chan *chan = &wq->dma_chan;
-	int rc;
+	struct dma_device *dma = &idxd->idxd_dma->dma;
+	struct device *dev = &idxd->pdev->dev;
+	struct idxd_dma_chan *idxd_chan;
+	struct dma_chan *chan;
+	int rc, i;
+
+	idxd_chan = kzalloc_node(sizeof(*idxd_chan), GFP_KERNEL, dev_to_node(dev));
+	if (!idxd_chan)
+		return -ENOMEM;
 
-	memset(&wq->dma_chan, 0, sizeof(struct dma_chan));
+	chan = &idxd_chan->chan;
 	chan->device = dma;
 	list_add_tail(&chan->device_node, &dma->channels);
+
+	for (i = 0; i < wq->num_descs; i++) {
+		struct idxd_desc *desc = wq->descs[i];
+
+		dma_async_tx_descriptor_init(&desc->txd, chan);
+		desc->txd.tx_submit = idxd_dma_tx_submit;
+	}
+
 	rc = dma_async_device_channel_register(dma, chan);
-	if (rc < 0)
+	if (rc < 0) {
+		kfree(idxd_chan);
 		return rc;
+	}
+
+	wq->idxd_chan = idxd_chan;
+	idxd_chan->wq = wq;
+	get_device(&wq->conf_dev);
 
 	return 0;
 }
 
 void idxd_unregister_dma_channel(struct idxd_wq *wq)
 {
-	struct dma_chan *chan = &wq->dma_chan;
+	struct idxd_dma_chan *idxd_chan = wq->idxd_chan;
+	struct dma_chan *chan = &idxd_chan->chan;
+	struct idxd_dma_dev *idxd_dma = wq->idxd->idxd_dma;
 
-	dma_async_device_channel_unregister(&wq->idxd->dma_dev, chan);
+	dma_async_device_channel_unregister(&idxd_dma->dma, chan);
 	list_del(&chan->device_node);
+	kfree(wq->idxd_chan);
+	wq->idxd_chan = NULL;
+	put_device(&wq->conf_dev);
 }
diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h
index 76014c14f473..26482c7d4c3a 100644
--- a/drivers/dma/idxd/idxd.h
+++ b/drivers/dma/idxd/idxd.h
@@ -8,12 +8,18 @@
 #include <linux/percpu-rwsem.h>
 #include <linux/wait.h>
 #include <linux/cdev.h>
+#include <linux/idr.h>
+#include <linux/pci.h>
+#include <linux/perf_event.h>
 #include "registers.h"
 
 #define IDXD_DRIVER_VERSION	"1.00"
 
 extern struct kmem_cache *idxd_desc_pool;
 
+struct idxd_device;
+struct idxd_wq;
+
 #define IDXD_REG_TIMEOUT	50
 #define IDXD_DRAIN_TIMEOUT	5000
 
@@ -25,6 +31,7 @@ enum idxd_type {
 };
 
 #define IDXD_NAME_SIZE		128
+#define IDXD_PMU_EVENT_MAX	64
 
 struct idxd_device_driver {
 	struct device_driver drv;
@@ -33,6 +40,7 @@ struct idxd_device_driver {
 struct idxd_irq_entry {
 	struct idxd_device *idxd;
 	int id;
+	int vector;
 	struct llist_head pending_llist;
 	struct list_head work_list;
 	/*
@@ -56,6 +64,31 @@ struct idxd_group {
 	int tc_b;
 };
 
+struct idxd_pmu {
+	struct idxd_device *idxd;
+
+	struct perf_event *event_list[IDXD_PMU_EVENT_MAX];
+	int n_events;
+
+	DECLARE_BITMAP(used_mask, IDXD_PMU_EVENT_MAX);
+
+	struct pmu pmu;
+	char name[IDXD_NAME_SIZE];
+	int cpu;
+
+	int n_counters;
+	int counter_width;
+	int n_event_categories;
+
+	bool per_counter_caps_supported;
+	unsigned long supported_event_categories;
+
+	unsigned long supported_filters;
+	int n_filters;
+
+	struct hlist_node cpuhp_node;
+};
+
 #define IDXD_MAX_PRIORITY	0xf
 
 enum idxd_wq_state {
@@ -75,10 +108,10 @@ enum idxd_wq_type {
 };
 
 struct idxd_cdev {
+	struct idxd_wq *wq;
 	struct cdev cdev;
-	struct device *dev;
+	struct device dev;
 	int minor;
-	struct wait_queue_head err_queue;
 };
 
 #define IDXD_ALLOCATED_BATCH_SIZE	128U
@@ -96,10 +129,18 @@ enum idxd_complete_type {
 	IDXD_COMPLETE_DEV_FAIL,
 };
 
+struct idxd_dma_chan {
+	struct dma_chan chan;
+	struct idxd_wq *wq;
+};
+
 struct idxd_wq {
 	void __iomem *portal;
+	struct percpu_ref wq_active;
+	struct completion wq_dead;
 	struct device conf_dev;
-	struct idxd_cdev idxd_cdev;
+	struct idxd_cdev *idxd_cdev;
+	struct wait_queue_head err_queue;
 	struct idxd_device *idxd;
 	int id;
 	enum idxd_wq_type type;
@@ -125,7 +166,7 @@ struct idxd_wq {
 	int compls_size;
 	struct idxd_desc **descs;
 	struct sbitmap_queue sbq;
-	struct dma_chan dma_chan;
+	struct idxd_dma_chan *idxd_chan;
 	char name[WQ_NAME_SIZE + 1];
 	u64 max_xfer_bytes;
 	u32 max_batch_size;
@@ -147,6 +188,7 @@ struct idxd_hw {
 	union group_cap_reg group_cap;
 	union engine_cap_reg engine_cap;
 	struct opcap opcap;
+	u32 cmd_cap;
 };
 
 enum idxd_device_state {
@@ -162,9 +204,22 @@ enum idxd_device_flag {
 	IDXD_FLAG_PASID_ENABLED,
 };
 
-struct idxd_device {
+struct idxd_dma_dev {
+	struct idxd_device *idxd;
+	struct dma_device dma;
+};
+
+struct idxd_driver_data {
+	const char *name_prefix;
 	enum idxd_type type;
+	struct device_type *dev_type;
+	int compl_size;
+	int align;
+};
+
+struct idxd_device {
 	struct device conf_dev;
+	struct idxd_driver_data *data;
 	struct list_head list;
 	struct idxd_hw hw;
 	enum idxd_device_state state;
@@ -177,10 +232,11 @@ struct idxd_device {
 	void __iomem *reg_base;
 
 	spinlock_t dev_lock;	/* spinlock for device */
+	spinlock_t cmd_lock;	/* spinlock for device commands */
 	struct completion *cmd_done;
-	struct idxd_group *groups;
-	struct idxd_wq *wqs;
-	struct idxd_engine *engines;
+	struct idxd_group **groups;
+	struct idxd_wq **wqs;
+	struct idxd_engine **engines;
 
 	struct iommu_sva *sva;
 	unsigned int pasid;
@@ -202,17 +258,19 @@ struct idxd_device {
 	int token_limit;
 	int nr_tokens;		/* non-reserved tokens */
 	unsigned int wqcfg_size;
-	int compl_size;
 
 	union sw_err_reg sw_err;
 	wait_queue_head_t cmd_waitq;
-	struct msix_entry *msix_entries;
 	int num_wq_irqs;
 	struct idxd_irq_entry *irq_entries;
 
-	struct dma_device dma_dev;
+	struct idxd_dma_dev *idxd_dma;
 	struct workqueue_struct *wq;
 	struct work_struct work;
+
+	int *int_handles;
+
+	struct idxd_pmu *idxd_pmu;
 };
 
 /* IDXD software descriptor */
@@ -232,6 +290,7 @@ struct idxd_desc {
 	struct list_head list;
 	int id;
 	int cpu;
+	unsigned int vector;
 	struct idxd_wq *wq;
 };
 
@@ -242,6 +301,44 @@ extern struct bus_type dsa_bus_type;
 extern struct bus_type iax_bus_type;
 
 extern bool support_enqcmd;
+extern struct ida idxd_ida;
+extern struct device_type dsa_device_type;
+extern struct device_type iax_device_type;
+extern struct device_type idxd_wq_device_type;
+extern struct device_type idxd_engine_device_type;
+extern struct device_type idxd_group_device_type;
+
+static inline bool is_dsa_dev(struct device *dev)
+{
+	return dev->type == &dsa_device_type;
+}
+
+static inline bool is_iax_dev(struct device *dev)
+{
+	return dev->type == &iax_device_type;
+}
+
+static inline bool is_idxd_dev(struct device *dev)
+{
+	return is_dsa_dev(dev) || is_iax_dev(dev);
+}
+
+static inline bool is_idxd_wq_dev(struct device *dev)
+{
+	return dev->type == &idxd_wq_device_type;
+}
+
+static inline bool is_idxd_wq_dmaengine(struct idxd_wq *wq)
+{
+	if (wq->type == IDXD_WQT_KERNEL && strcmp(wq->name, "dmaengine") == 0)
+		return true;
+	return false;
+}
+
+static inline bool is_idxd_wq_cdev(struct idxd_wq *wq)
+{
+	return wq->type == IDXD_WQT_USER;
+}
 
 static inline bool wq_dedicated(struct idxd_wq *wq)
 {
@@ -268,6 +365,11 @@ enum idxd_portal_prot {
 	IDXD_PORTAL_LIMITED,
 };
 
+enum idxd_interrupt_type {
+	IDXD_IRQ_MSIX = 0,
+	IDXD_IRQ_IMS,
+};
+
 static inline int idxd_get_wq_portal_offset(enum idxd_portal_prot prot)
 {
 	return prot * 0x1000;
@@ -279,18 +381,6 @@ static inline int idxd_get_wq_portal_full_offset(int wq_id,
 	return ((wq_id * 4) << PAGE_SHIFT) + idxd_get_wq_portal_offset(prot);
 }
 
-static inline void idxd_set_type(struct idxd_device *idxd)
-{
-	struct pci_dev *pdev = idxd->pdev;
-
-	if (pdev->device == PCI_DEVICE_ID_INTEL_DSA_SPR0)
-		idxd->type = IDXD_TYPE_DSA;
-	else if (pdev->device == PCI_DEVICE_ID_INTEL_IAX_SPR0)
-		idxd->type = IDXD_TYPE_IAX;
-	else
-		idxd->type = IDXD_TYPE_UNKNOWN;
-}
-
 static inline void idxd_wq_get(struct idxd_wq *wq)
 {
 	wq->client_count++;
@@ -306,19 +396,17 @@ static inline int idxd_wq_refcount(struct idxd_wq *wq)
 	return wq->client_count;
 };
 
-const char *idxd_get_dev_name(struct idxd_device *idxd);
 int idxd_register_bus_type(void);
 void idxd_unregister_bus_type(void);
-int idxd_setup_sysfs(struct idxd_device *idxd);
-void idxd_cleanup_sysfs(struct idxd_device *idxd);
+int idxd_register_devices(struct idxd_device *idxd);
+void idxd_unregister_devices(struct idxd_device *idxd);
 int idxd_register_driver(void);
 void idxd_unregister_driver(void);
-struct bus_type *idxd_get_bus_type(struct idxd_device *idxd);
+void idxd_wqs_quiesce(struct idxd_device *idxd);
 
 /* device interrupt control */
 void idxd_msix_perm_setup(struct idxd_device *idxd);
 void idxd_msix_perm_clear(struct idxd_device *idxd);
-irqreturn_t idxd_irq_handler(int vec, void *data);
 irqreturn_t idxd_misc_thread(int vec, void *data);
 irqreturn_t idxd_wq_thread(int irq, void *data);
 void idxd_mask_error_interrupts(struct idxd_device *idxd);
@@ -336,8 +424,14 @@ void idxd_device_cleanup(struct idxd_device *idxd);
 int idxd_device_config(struct idxd_device *idxd);
 void idxd_device_wqs_clear_state(struct idxd_device *idxd);
 void idxd_device_drain_pasid(struct idxd_device *idxd, int pasid);
+int idxd_device_load_config(struct idxd_device *idxd);
+int idxd_device_request_int_handle(struct idxd_device *idxd, int idx, int *handle,
+				   enum idxd_interrupt_type irq_type);
+int idxd_device_release_int_handle(struct idxd_device *idxd, int handle,
+				   enum idxd_interrupt_type irq_type);
 
 /* work queue control */
+void idxd_wqs_unmap_portal(struct idxd_device *idxd);
 int idxd_wq_alloc_resources(struct idxd_wq *wq);
 void idxd_wq_free_resources(struct idxd_wq *wq);
 int idxd_wq_enable(struct idxd_wq *wq);
@@ -349,6 +443,8 @@ void idxd_wq_unmap_portal(struct idxd_wq *wq);
 void idxd_wq_disable_cleanup(struct idxd_wq *wq);
 int idxd_wq_set_pasid(struct idxd_wq *wq, int pasid);
 int idxd_wq_disable_pasid(struct idxd_wq *wq);
+void idxd_wq_quiesce(struct idxd_wq *wq);
+int idxd_wq_init_percpu_ref(struct idxd_wq *wq);
 
 /* submission */
 int idxd_submit_desc(struct idxd_wq *wq, struct idxd_desc *desc);
@@ -363,7 +459,6 @@ void idxd_unregister_dma_channel(struct idxd_wq *wq);
 void idxd_parse_completion_status(u8 status, enum dmaengine_tx_result *res);
 void idxd_dma_complete_txd(struct idxd_desc *desc,
 			   enum idxd_complete_type comp_type);
-dma_cookie_t idxd_dma_tx_submit(struct dma_async_tx_descriptor *tx);
 
 /* cdev */
 int idxd_cdev_register(void);
@@ -372,4 +467,19 @@ int idxd_cdev_get_major(struct idxd_device *idxd);
 int idxd_wq_add_cdev(struct idxd_wq *wq);
 void idxd_wq_del_cdev(struct idxd_wq *wq);
 
+/* perfmon */
+#if IS_ENABLED(CONFIG_INTEL_IDXD_PERFMON)
+int perfmon_pmu_init(struct idxd_device *idxd);
+void perfmon_pmu_remove(struct idxd_device *idxd);
+void perfmon_counter_overflow(struct idxd_device *idxd);
+void perfmon_init(void);
+void perfmon_exit(void);
+#else
+static inline int perfmon_pmu_init(struct idxd_device *idxd) { return 0; }
+static inline void perfmon_pmu_remove(struct idxd_device *idxd) {}
+static inline void perfmon_counter_overflow(struct idxd_device *idxd) {}
+static inline void perfmon_init(void) {}
+static inline void perfmon_exit(void) {}
+#endif
+
 #endif
diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c
index 6584b0ec07d5..2a926bef87f2 100644
--- a/drivers/dma/idxd/init.c
+++ b/drivers/dma/idxd/init.c
@@ -21,6 +21,7 @@
 #include "../dmaengine.h"
 #include "registers.h"
 #include "idxd.h"
+#include "perfmon.h"
 
 MODULE_VERSION(IDXD_DRIVER_VERSION);
 MODULE_LICENSE("GPL v2");
@@ -33,35 +34,39 @@ MODULE_PARM_DESC(sva, "Toggle SVA support on/off");
 #define DRV_NAME "idxd"
 
 bool support_enqcmd;
-
-static struct idr idxd_idrs[IDXD_TYPE_MAX];
-static DEFINE_MUTEX(idxd_idr_lock);
+DEFINE_IDA(idxd_ida);
+
+static struct idxd_driver_data idxd_driver_data[] = {
+	[IDXD_TYPE_DSA] = {
+		.name_prefix = "dsa",
+		.type = IDXD_TYPE_DSA,
+		.compl_size = sizeof(struct dsa_completion_record),
+		.align = 32,
+		.dev_type = &dsa_device_type,
+	},
+	[IDXD_TYPE_IAX] = {
+		.name_prefix = "iax",
+		.type = IDXD_TYPE_IAX,
+		.compl_size = sizeof(struct iax_completion_record),
+		.align = 64,
+		.dev_type = &iax_device_type,
+	},
+};
 
 static struct pci_device_id idxd_pci_tbl[] = {
 	/* DSA ver 1.0 platforms */
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_DSA_SPR0) },
+	{ PCI_DEVICE_DATA(INTEL, DSA_SPR0, &idxd_driver_data[IDXD_TYPE_DSA]) },
 
 	/* IAX ver 1.0 platforms */
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IAX_SPR0) },
+	{ PCI_DEVICE_DATA(INTEL, IAX_SPR0, &idxd_driver_data[IDXD_TYPE_IAX]) },
 	{ 0, }
 };
 MODULE_DEVICE_TABLE(pci, idxd_pci_tbl);
 
-static char *idxd_name[] = {
-	"dsa",
-	"iax"
-};
-
-const char *idxd_get_dev_name(struct idxd_device *idxd)
-{
-	return idxd_name[idxd->type];
-}
-
 static int idxd_setup_interrupts(struct idxd_device *idxd)
 {
 	struct pci_dev *pdev = idxd->pdev;
 	struct device *dev = &pdev->dev;
-	struct msix_entry *msix;
 	struct idxd_irq_entry *irq_entry;
 	int i, msixcnt;
 	int rc = 0;
@@ -69,23 +74,13 @@ static int idxd_setup_interrupts(struct idxd_device *idxd)
 	msixcnt = pci_msix_vec_count(pdev);
 	if (msixcnt < 0) {
 		dev_err(dev, "Not MSI-X interrupt capable.\n");
-		goto err_no_irq;
+		return -ENOSPC;
 	}
 
-	idxd->msix_entries = devm_kzalloc(dev, sizeof(struct msix_entry) *
-			msixcnt, GFP_KERNEL);
-	if (!idxd->msix_entries) {
-		rc = -ENOMEM;
-		goto err_no_irq;
-	}
-
-	for (i = 0; i < msixcnt; i++)
-		idxd->msix_entries[i].entry = i;
-
-	rc = pci_enable_msix_exact(pdev, idxd->msix_entries, msixcnt);
-	if (rc) {
-		dev_err(dev, "Failed enabling %d MSIX entries.\n", msixcnt);
-		goto err_no_irq;
+	rc = pci_alloc_irq_vectors(pdev, msixcnt, msixcnt, PCI_IRQ_MSIX);
+	if (rc != msixcnt) {
+		dev_err(dev, "Failed enabling %d MSIX entries: %d\n", msixcnt, rc);
+		return -ENOSPC;
 	}
 	dev_dbg(dev, "Enabled %d msix vectors\n", msixcnt);
 
@@ -93,119 +88,266 @@ static int idxd_setup_interrupts(struct idxd_device *idxd)
 	 * We implement 1 completion list per MSI-X entry except for
 	 * entry 0, which is for errors and others.
 	 */
-	idxd->irq_entries = devm_kcalloc(dev, msixcnt,
-					 sizeof(struct idxd_irq_entry),
-					 GFP_KERNEL);
+	idxd->irq_entries = kcalloc_node(msixcnt, sizeof(struct idxd_irq_entry),
+					 GFP_KERNEL, dev_to_node(dev));
 	if (!idxd->irq_entries) {
 		rc = -ENOMEM;
-		goto err_no_irq;
+		goto err_irq_entries;
 	}
 
 	for (i = 0; i < msixcnt; i++) {
 		idxd->irq_entries[i].id = i;
 		idxd->irq_entries[i].idxd = idxd;
+		idxd->irq_entries[i].vector = pci_irq_vector(pdev, i);
 		spin_lock_init(&idxd->irq_entries[i].list_lock);
 	}
 
-	msix = &idxd->msix_entries[0];
 	irq_entry = &idxd->irq_entries[0];
-	rc = devm_request_threaded_irq(dev, msix->vector, idxd_irq_handler,
-				       idxd_misc_thread, 0, "idxd-misc",
-				       irq_entry);
+	rc = request_threaded_irq(irq_entry->vector, NULL, idxd_misc_thread,
+				  0, "idxd-misc", irq_entry);
 	if (rc < 0) {
 		dev_err(dev, "Failed to allocate misc interrupt.\n");
-		goto err_no_irq;
+		goto err_misc_irq;
 	}
 
-	dev_dbg(dev, "Allocated idxd-misc handler on msix vector %d\n",
-		msix->vector);
+	dev_dbg(dev, "Allocated idxd-misc handler on msix vector %d\n", irq_entry->vector);
 
 	/* first MSI-X entry is not for wq interrupts */
 	idxd->num_wq_irqs = msixcnt - 1;
 
 	for (i = 1; i < msixcnt; i++) {
-		msix = &idxd->msix_entries[i];
 		irq_entry = &idxd->irq_entries[i];
 
 		init_llist_head(&idxd->irq_entries[i].pending_llist);
 		INIT_LIST_HEAD(&idxd->irq_entries[i].work_list);
-		rc = devm_request_threaded_irq(dev, msix->vector,
-					       idxd_irq_handler,
-					       idxd_wq_thread, 0,
-					       "idxd-portal", irq_entry);
+		rc = request_threaded_irq(irq_entry->vector, NULL,
+					  idxd_wq_thread, 0, "idxd-portal", irq_entry);
 		if (rc < 0) {
-			dev_err(dev, "Failed to allocate irq %d.\n",
-				msix->vector);
-			goto err_no_irq;
+			dev_err(dev, "Failed to allocate irq %d.\n", irq_entry->vector);
+			goto err_wq_irqs;
+		}
+
+		dev_dbg(dev, "Allocated idxd-msix %d for vector %d\n", i, irq_entry->vector);
+		if (idxd->hw.cmd_cap & BIT(IDXD_CMD_REQUEST_INT_HANDLE)) {
+			/*
+			 * The MSIX vector enumeration starts at 1 with vector 0 being the
+			 * misc interrupt that handles non I/O completion events. The
+			 * interrupt handles are for IMS enumeration on guest. The misc
+			 * interrupt vector does not require a handle and therefore we start
+			 * the int_handles at index 0. Since 'i' starts at 1, the first
+			 * int_handles index will be 0.
+			 */
+			rc = idxd_device_request_int_handle(idxd, i, &idxd->int_handles[i - 1],
+							    IDXD_IRQ_MSIX);
+			if (rc < 0) {
+				free_irq(irq_entry->vector, irq_entry);
+				goto err_wq_irqs;
+			}
+			dev_dbg(dev, "int handle requested: %u\n", idxd->int_handles[i - 1]);
 		}
-		dev_dbg(dev, "Allocated idxd-msix %d for vector %d\n",
-			i, msix->vector);
 	}
 
 	idxd_unmask_error_interrupts(idxd);
 	idxd_msix_perm_setup(idxd);
 	return 0;
 
- err_no_irq:
+ err_wq_irqs:
+	while (--i >= 0) {
+		irq_entry = &idxd->irq_entries[i];
+		free_irq(irq_entry->vector, irq_entry);
+		if (i != 0)
+			idxd_device_release_int_handle(idxd,
+						       idxd->int_handles[i], IDXD_IRQ_MSIX);
+	}
+ err_misc_irq:
 	/* Disable error interrupt generation */
 	idxd_mask_error_interrupts(idxd);
-	pci_disable_msix(pdev);
+ err_irq_entries:
+	pci_free_irq_vectors(pdev);
 	dev_err(dev, "No usable interrupts\n");
 	return rc;
 }
 
-static int idxd_setup_internals(struct idxd_device *idxd)
+static int idxd_setup_wqs(struct idxd_device *idxd)
 {
 	struct device *dev = &idxd->pdev->dev;
-	int i;
+	struct idxd_wq *wq;
+	int i, rc;
 
-	init_waitqueue_head(&idxd->cmd_waitq);
-	idxd->groups = devm_kcalloc(dev, idxd->max_groups,
-				    sizeof(struct idxd_group), GFP_KERNEL);
-	if (!idxd->groups)
-		return -ENOMEM;
-
-	for (i = 0; i < idxd->max_groups; i++) {
-		idxd->groups[i].idxd = idxd;
-		idxd->groups[i].id = i;
-		idxd->groups[i].tc_a = -1;
-		idxd->groups[i].tc_b = -1;
-	}
-
-	idxd->wqs = devm_kcalloc(dev, idxd->max_wqs, sizeof(struct idxd_wq),
-				 GFP_KERNEL);
+	idxd->wqs = kcalloc_node(idxd->max_wqs, sizeof(struct idxd_wq *),
+				 GFP_KERNEL, dev_to_node(dev));
 	if (!idxd->wqs)
 		return -ENOMEM;
 
-	idxd->engines = devm_kcalloc(dev, idxd->max_engines,
-				     sizeof(struct idxd_engine), GFP_KERNEL);
-	if (!idxd->engines)
-		return -ENOMEM;
-
 	for (i = 0; i < idxd->max_wqs; i++) {
-		struct idxd_wq *wq = &idxd->wqs[i];
+		wq = kzalloc_node(sizeof(*wq), GFP_KERNEL, dev_to_node(dev));
+		if (!wq) {
+			rc = -ENOMEM;
+			goto err;
+		}
 
 		wq->id = i;
 		wq->idxd = idxd;
+		device_initialize(&wq->conf_dev);
+		wq->conf_dev.parent = &idxd->conf_dev;
+		wq->conf_dev.bus = &dsa_bus_type;
+		wq->conf_dev.type = &idxd_wq_device_type;
+		rc = dev_set_name(&wq->conf_dev, "wq%d.%d", idxd->id, wq->id);
+		if (rc < 0) {
+			put_device(&wq->conf_dev);
+			goto err;
+		}
+
 		mutex_init(&wq->wq_lock);
-		wq->idxd_cdev.minor = -1;
+		init_waitqueue_head(&wq->err_queue);
+		init_completion(&wq->wq_dead);
 		wq->max_xfer_bytes = idxd->max_xfer_bytes;
 		wq->max_batch_size = idxd->max_batch_size;
-		wq->wqcfg = devm_kzalloc(dev, idxd->wqcfg_size, GFP_KERNEL);
-		if (!wq->wqcfg)
-			return -ENOMEM;
+		wq->wqcfg = kzalloc_node(idxd->wqcfg_size, GFP_KERNEL, dev_to_node(dev));
+		if (!wq->wqcfg) {
+			put_device(&wq->conf_dev);
+			rc = -ENOMEM;
+			goto err;
+		}
+		idxd->wqs[i] = wq;
 	}
 
+	return 0;
+
+ err:
+	while (--i >= 0)
+		put_device(&idxd->wqs[i]->conf_dev);
+	return rc;
+}
+
+static int idxd_setup_engines(struct idxd_device *idxd)
+{
+	struct idxd_engine *engine;
+	struct device *dev = &idxd->pdev->dev;
+	int i, rc;
+
+	idxd->engines = kcalloc_node(idxd->max_engines, sizeof(struct idxd_engine *),
+				     GFP_KERNEL, dev_to_node(dev));
+	if (!idxd->engines)
+		return -ENOMEM;
+
 	for (i = 0; i < idxd->max_engines; i++) {
-		idxd->engines[i].idxd = idxd;
-		idxd->engines[i].id = i;
+		engine = kzalloc_node(sizeof(*engine), GFP_KERNEL, dev_to_node(dev));
+		if (!engine) {
+			rc = -ENOMEM;
+			goto err;
+		}
+
+		engine->id = i;
+		engine->idxd = idxd;
+		device_initialize(&engine->conf_dev);
+		engine->conf_dev.parent = &idxd->conf_dev;
+		engine->conf_dev.type = &idxd_engine_device_type;
+		rc = dev_set_name(&engine->conf_dev, "engine%d.%d", idxd->id, engine->id);
+		if (rc < 0) {
+			put_device(&engine->conf_dev);
+			goto err;
+		}
+
+		idxd->engines[i] = engine;
 	}
 
-	idxd->wq = create_workqueue(dev_name(dev));
-	if (!idxd->wq)
+	return 0;
+
+ err:
+	while (--i >= 0)
+		put_device(&idxd->engines[i]->conf_dev);
+	return rc;
+}
+
+static int idxd_setup_groups(struct idxd_device *idxd)
+{
+	struct device *dev = &idxd->pdev->dev;
+	struct idxd_group *group;
+	int i, rc;
+
+	idxd->groups = kcalloc_node(idxd->max_groups, sizeof(struct idxd_group *),
+				    GFP_KERNEL, dev_to_node(dev));
+	if (!idxd->groups)
 		return -ENOMEM;
 
+	for (i = 0; i < idxd->max_groups; i++) {
+		group = kzalloc_node(sizeof(*group), GFP_KERNEL, dev_to_node(dev));
+		if (!group) {
+			rc = -ENOMEM;
+			goto err;
+		}
+
+		group->id = i;
+		group->idxd = idxd;
+		device_initialize(&group->conf_dev);
+		group->conf_dev.parent = &idxd->conf_dev;
+		group->conf_dev.bus = &dsa_bus_type;
+		group->conf_dev.type = &idxd_group_device_type;
+		rc = dev_set_name(&group->conf_dev, "group%d.%d", idxd->id, group->id);
+		if (rc < 0) {
+			put_device(&group->conf_dev);
+			goto err;
+		}
+
+		idxd->groups[i] = group;
+		group->tc_a = -1;
+		group->tc_b = -1;
+	}
+
+	return 0;
+
+ err:
+	while (--i >= 0)
+		put_device(&idxd->groups[i]->conf_dev);
+	return rc;
+}
+
+static int idxd_setup_internals(struct idxd_device *idxd)
+{
+	struct device *dev = &idxd->pdev->dev;
+	int rc, i;
+
+	init_waitqueue_head(&idxd->cmd_waitq);
+
+	if (idxd->hw.cmd_cap & BIT(IDXD_CMD_REQUEST_INT_HANDLE)) {
+		idxd->int_handles = devm_kcalloc(dev, idxd->max_wqs, sizeof(int), GFP_KERNEL);
+		if (!idxd->int_handles)
+			return -ENOMEM;
+	}
+
+	rc = idxd_setup_wqs(idxd);
+	if (rc < 0)
+		goto err_wqs;
+
+	rc = idxd_setup_engines(idxd);
+	if (rc < 0)
+		goto err_engine;
+
+	rc = idxd_setup_groups(idxd);
+	if (rc < 0)
+		goto err_group;
+
+	idxd->wq = create_workqueue(dev_name(dev));
+	if (!idxd->wq) {
+		rc = -ENOMEM;
+		goto err_wkq_create;
+	}
+
 	return 0;
+
+ err_wkq_create:
+	for (i = 0; i < idxd->max_groups; i++)
+		put_device(&idxd->groups[i]->conf_dev);
+ err_group:
+	for (i = 0; i < idxd->max_engines; i++)
+		put_device(&idxd->engines[i]->conf_dev);
+ err_engine:
+	for (i = 0; i < idxd->max_wqs; i++)
+		put_device(&idxd->wqs[i]->conf_dev);
+ err_wqs:
+	kfree(idxd->int_handles);
+	return rc;
 }
 
 static void idxd_read_table_offsets(struct idxd_device *idxd)
@@ -233,6 +375,12 @@ static void idxd_read_caps(struct idxd_device *idxd)
 	/* reading generic capabilities */
 	idxd->hw.gen_cap.bits = ioread64(idxd->reg_base + IDXD_GENCAP_OFFSET);
 	dev_dbg(dev, "gen_cap: %#llx\n", idxd->hw.gen_cap.bits);
+
+	if (idxd->hw.gen_cap.cmd_cap) {
+		idxd->hw.cmd_cap = ioread32(idxd->reg_base + IDXD_CMDCAP_OFFSET);
+		dev_dbg(dev, "cmd_cap: %#x\n", idxd->hw.cmd_cap);
+	}
+
 	idxd->max_xfer_bytes = 1ULL << idxd->hw.gen_cap.max_xfer_shift;
 	dev_dbg(dev, "max xfer size: %llu bytes\n", idxd->max_xfer_bytes);
 	idxd->max_batch_size = 1U << idxd->hw.gen_cap.max_batch_shift;
@@ -275,17 +423,34 @@ static void idxd_read_caps(struct idxd_device *idxd)
 	}
 }
 
-static struct idxd_device *idxd_alloc(struct pci_dev *pdev)
+static struct idxd_device *idxd_alloc(struct pci_dev *pdev, struct idxd_driver_data *data)
 {
 	struct device *dev = &pdev->dev;
 	struct idxd_device *idxd;
+	int rc;
 
-	idxd = devm_kzalloc(dev, sizeof(struct idxd_device), GFP_KERNEL);
+	idxd = kzalloc_node(sizeof(*idxd), GFP_KERNEL, dev_to_node(dev));
 	if (!idxd)
 		return NULL;
 
 	idxd->pdev = pdev;
+	idxd->data = data;
+	idxd->id = ida_alloc(&idxd_ida, GFP_KERNEL);
+	if (idxd->id < 0)
+		return NULL;
+
+	device_initialize(&idxd->conf_dev);
+	idxd->conf_dev.parent = dev;
+	idxd->conf_dev.bus = &dsa_bus_type;
+	idxd->conf_dev.type = idxd->data->dev_type;
+	rc = dev_set_name(&idxd->conf_dev, "%s%d", idxd->data->name_prefix, idxd->id);
+	if (rc < 0) {
+		put_device(&idxd->conf_dev);
+		return NULL;
+	}
+
 	spin_lock_init(&idxd->dev_lock);
+	spin_lock_init(&idxd->cmd_lock);
 
 	return idxd;
 }
@@ -338,11 +503,18 @@ static int idxd_probe(struct idxd_device *idxd)
 	dev_dbg(dev, "IDXD reset complete\n");
 
 	if (IS_ENABLED(CONFIG_INTEL_IDXD_SVM) && sva) {
-		rc = idxd_enable_system_pasid(idxd);
-		if (rc < 0)
-			dev_warn(dev, "Failed to enable PASID. No SVA support: %d\n", rc);
-		else
-			set_bit(IDXD_FLAG_PASID_ENABLED, &idxd->flags);
+		rc = iommu_dev_enable_feature(dev, IOMMU_DEV_FEAT_SVA);
+		if (rc == 0) {
+			rc = idxd_enable_system_pasid(idxd);
+			if (rc < 0) {
+				iommu_dev_disable_feature(dev, IOMMU_DEV_FEAT_SVA);
+				dev_warn(dev, "Failed to enable PASID. No SVA support: %d\n", rc);
+			} else {
+				set_bit(IDXD_FLAG_PASID_ENABLED, &idxd->flags);
+			}
+		} else {
+			dev_warn(dev, "Unable to turn on SVA feature.\n");
+		}
 	} else if (!sva) {
 		dev_warn(dev, "User forced SVA off via module param.\n");
 	}
@@ -352,80 +524,75 @@ static int idxd_probe(struct idxd_device *idxd)
 
 	rc = idxd_setup_internals(idxd);
 	if (rc)
-		goto err_setup;
+		goto err;
+
+	/* If the configs are readonly, then load them from device */
+	if (!test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags)) {
+		dev_dbg(dev, "Loading RO device config\n");
+		rc = idxd_device_load_config(idxd);
+		if (rc < 0)
+			goto err;
+	}
 
 	rc = idxd_setup_interrupts(idxd);
 	if (rc)
-		goto err_setup;
+		goto err;
 
 	dev_dbg(dev, "IDXD interrupt setup complete.\n");
 
-	mutex_lock(&idxd_idr_lock);
-	idxd->id = idr_alloc(&idxd_idrs[idxd->type], idxd, 0, 0, GFP_KERNEL);
-	mutex_unlock(&idxd_idr_lock);
-	if (idxd->id < 0) {
-		rc = -ENOMEM;
-		goto err_idr_fail;
-	}
-
 	idxd->major = idxd_cdev_get_major(idxd);
 
+	rc = perfmon_pmu_init(idxd);
+	if (rc < 0)
+		dev_warn(dev, "Failed to initialize perfmon. No PMU support: %d\n", rc);
+
 	dev_dbg(dev, "IDXD device %d probed successfully\n", idxd->id);
 	return 0;
 
- err_idr_fail:
-	idxd_mask_error_interrupts(idxd);
-	idxd_mask_msix_vectors(idxd);
- err_setup:
+ err:
 	if (device_pasid_enabled(idxd))
 		idxd_disable_system_pasid(idxd);
+	iommu_dev_disable_feature(dev, IOMMU_DEV_FEAT_SVA);
 	return rc;
 }
 
-static void idxd_type_init(struct idxd_device *idxd)
-{
-	if (idxd->type == IDXD_TYPE_DSA)
-		idxd->compl_size = sizeof(struct dsa_completion_record);
-	else if (idxd->type == IDXD_TYPE_IAX)
-		idxd->compl_size = sizeof(struct iax_completion_record);
-}
-
 static int idxd_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
 	struct device *dev = &pdev->dev;
 	struct idxd_device *idxd;
+	struct idxd_driver_data *data = (struct idxd_driver_data *)id->driver_data;
 	int rc;
 
-	rc = pcim_enable_device(pdev);
+	rc = pci_enable_device(pdev);
 	if (rc)
 		return rc;
 
 	dev_dbg(dev, "Alloc IDXD context\n");
-	idxd = idxd_alloc(pdev);
-	if (!idxd)
-		return -ENOMEM;
+	idxd = idxd_alloc(pdev, data);
+	if (!idxd) {
+		rc = -ENOMEM;
+		goto err_idxd_alloc;
+	}
 
 	dev_dbg(dev, "Mapping BARs\n");
-	idxd->reg_base = pcim_iomap(pdev, IDXD_MMIO_BAR, 0);
-	if (!idxd->reg_base)
-		return -ENOMEM;
+	idxd->reg_base = pci_iomap(pdev, IDXD_MMIO_BAR, 0);
+	if (!idxd->reg_base) {
+		rc = -ENOMEM;
+		goto err_iomap;
+	}
 
 	dev_dbg(dev, "Set DMA masks\n");
 	rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(64));
 	if (rc)
 		rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
 	if (rc)
-		return rc;
+		goto err;
 
 	rc = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
 	if (rc)
 		rc = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32));
 	if (rc)
-		return rc;
-
-	idxd_set_type(idxd);
-
-	idxd_type_init(idxd);
+		goto err;
 
 	dev_dbg(dev, "Set PCI master\n");
 	pci_set_master(pdev);
@@ -435,13 +602,13 @@ static int idxd_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	rc = idxd_probe(idxd);
 	if (rc) {
 		dev_err(dev, "Intel(R) IDXD DMA Engine init failed\n");
-		return -ENODEV;
+		goto err;
 	}
 
-	rc = idxd_setup_sysfs(idxd);
+	rc = idxd_register_devices(idxd);
 	if (rc) {
 		dev_err(dev, "IDXD sysfs setup failed\n");
-		return -ENODEV;
+		goto err;
 	}
 
 	idxd->state = IDXD_DEV_CONF_READY;
@@ -450,6 +617,14 @@ static int idxd_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		 idxd->hw.version);
 
 	return 0;
+
+ err:
+	pci_iounmap(pdev, idxd->reg_base);
+ err_iomap:
+	put_device(&idxd->conf_dev);
+ err_idxd_alloc:
+	pci_disable_device(pdev);
+	return rc;
 }
 
 static void idxd_flush_pending_llist(struct idxd_irq_entry *ie)
@@ -478,6 +653,36 @@ static void idxd_flush_work_list(struct idxd_irq_entry *ie)
 	}
 }
 
+void idxd_wqs_quiesce(struct idxd_device *idxd)
+{
+	struct idxd_wq *wq;
+	int i;
+
+	for (i = 0; i < idxd->max_wqs; i++) {
+		wq = idxd->wqs[i];
+		if (wq->state == IDXD_WQ_ENABLED && wq->type == IDXD_WQT_KERNEL)
+			idxd_wq_quiesce(wq);
+	}
+}
+
+static void idxd_release_int_handles(struct idxd_device *idxd)
+{
+	struct device *dev = &idxd->pdev->dev;
+	int i, rc;
+
+	for (i = 0; i < idxd->num_wq_irqs; i++) {
+		if (idxd->hw.cmd_cap & BIT(IDXD_CMD_RELEASE_INT_HANDLE)) {
+			rc = idxd_device_release_int_handle(idxd, idxd->int_handles[i],
+							    IDXD_IRQ_MSIX);
+			if (rc < 0)
+				dev_warn(dev, "irq handle %d release failed\n",
+					 idxd->int_handles[i]);
+			else
+				dev_dbg(dev, "int handle requested: %u\n", idxd->int_handles[i]);
+		}
+	}
+}
+
 static void idxd_shutdown(struct pci_dev *pdev)
 {
 	struct idxd_device *idxd = pci_get_drvdata(pdev);
@@ -495,7 +700,8 @@ static void idxd_shutdown(struct pci_dev *pdev)
 
 	for (i = 0; i < msixcnt; i++) {
 		irq_entry = &idxd->irq_entries[i];
-		synchronize_irq(idxd->msix_entries[i].vector);
+		synchronize_irq(irq_entry->vector);
+		free_irq(irq_entry->vector, irq_entry);
 		if (i == 0)
 			continue;
 		idxd_flush_pending_llist(irq_entry);
@@ -503,6 +709,10 @@ static void idxd_shutdown(struct pci_dev *pdev)
 	}
 
 	idxd_msix_perm_clear(idxd);
+	idxd_release_int_handles(idxd);
+	pci_free_irq_vectors(pdev);
+	pci_iounmap(pdev, idxd->reg_base);
+	pci_disable_device(pdev);
 	destroy_workqueue(idxd->wq);
 }
 
@@ -511,13 +721,12 @@ static void idxd_remove(struct pci_dev *pdev)
 	struct idxd_device *idxd = pci_get_drvdata(pdev);
 
 	dev_dbg(&pdev->dev, "%s called\n", __func__);
-	idxd_cleanup_sysfs(idxd);
 	idxd_shutdown(pdev);
 	if (device_pasid_enabled(idxd))
 		idxd_disable_system_pasid(idxd);
-	mutex_lock(&idxd_idr_lock);
-	idr_remove(&idxd_idrs[idxd->type], idxd->id);
-	mutex_unlock(&idxd_idr_lock);
+	idxd_unregister_devices(idxd);
+	perfmon_pmu_remove(idxd);
+	iommu_dev_disable_feature(&pdev->dev, IOMMU_DEV_FEAT_SVA);
 }
 
 static struct pci_driver idxd_pci_driver = {
@@ -530,7 +739,7 @@ static struct pci_driver idxd_pci_driver = {
 
 static int __init idxd_init_module(void)
 {
-	int err, i;
+	int err;
 
 	/*
 	 * If the CPU does not support MOVDIR64B or ENQCMDS, there's no point in
@@ -546,8 +755,7 @@ static int __init idxd_init_module(void)
 	else
 		support_enqcmd = true;
 
-	for (i = 0; i < IDXD_TYPE_MAX; i++)
-		idr_init(&idxd_idrs[i]);
+	perfmon_init();
 
 	err = idxd_register_bus_type();
 	if (err < 0)
@@ -582,5 +790,6 @@ static void __exit idxd_exit_module(void)
 	pci_unregister_driver(&idxd_pci_driver);
 	idxd_cdev_remove();
 	idxd_unregister_bus_type();
+	perfmon_exit();
 }
 module_exit(idxd_exit_module);
diff --git a/drivers/dma/idxd/irq.c b/drivers/dma/idxd/irq.c
index f1463fc58112..ae68e1e5487a 100644
--- a/drivers/dma/idxd/irq.c
+++ b/drivers/dma/idxd/irq.c
@@ -45,7 +45,7 @@ static void idxd_device_reinit(struct work_struct *work)
 		goto out;
 
 	for (i = 0; i < idxd->max_wqs; i++) {
-		struct idxd_wq *wq = &idxd->wqs[i];
+		struct idxd_wq *wq = idxd->wqs[i];
 
 		if (wq->state == IDXD_WQ_ENABLED) {
 			rc = idxd_wq_enable(wq);
@@ -102,15 +102,6 @@ static int idxd_device_schedule_fault_process(struct idxd_device *idxd,
 	return 0;
 }
 
-irqreturn_t idxd_irq_handler(int vec, void *data)
-{
-	struct idxd_irq_entry *irq_entry = data;
-	struct idxd_device *idxd = irq_entry->idxd;
-
-	idxd_mask_msix_vector(idxd, irq_entry->id);
-	return IRQ_WAKE_THREAD;
-}
-
 static int process_misc_interrupts(struct idxd_device *idxd, u32 cause)
 {
 	struct device *dev = &idxd->pdev->dev;
@@ -130,18 +121,18 @@ static int process_misc_interrupts(struct idxd_device *idxd, u32 cause)
 
 		if (idxd->sw_err.valid && idxd->sw_err.wq_idx_valid) {
 			int id = idxd->sw_err.wq_idx;
-			struct idxd_wq *wq = &idxd->wqs[id];
+			struct idxd_wq *wq = idxd->wqs[id];
 
 			if (wq->type == IDXD_WQT_USER)
-				wake_up_interruptible(&wq->idxd_cdev.err_queue);
+				wake_up_interruptible(&wq->err_queue);
 		} else {
 			int i;
 
 			for (i = 0; i < idxd->max_wqs; i++) {
-				struct idxd_wq *wq = &idxd->wqs[i];
+				struct idxd_wq *wq = idxd->wqs[i];
 
 				if (wq->type == IDXD_WQT_USER)
-					wake_up_interruptible(&wq->idxd_cdev.err_queue);
+					wake_up_interruptible(&wq->err_queue);
 			}
 		}
 
@@ -165,11 +156,8 @@ static int process_misc_interrupts(struct idxd_device *idxd, u32 cause)
 	}
 
 	if (cause & IDXD_INTC_PERFMON_OVFL) {
-		/*
-		 * Driver does not utilize perfmon counter overflow interrupt
-		 * yet.
-		 */
 		val |= IDXD_INTC_PERFMON_OVFL;
+		perfmon_counter_overflow(idxd);
 	}
 
 	val ^= cause;
@@ -202,6 +190,8 @@ static int process_misc_interrupts(struct idxd_device *idxd, u32 cause)
 			queue_work(idxd->wq, &idxd->work);
 		} else {
 			spin_lock_bh(&idxd->dev_lock);
+			idxd_wqs_quiesce(idxd);
+			idxd_wqs_unmap_portal(idxd);
 			idxd_device_wqs_clear_state(idxd);
 			dev_err(&idxd->pdev->dev,
 				"idxd halted, need %s.\n",
@@ -235,7 +225,6 @@ irqreturn_t idxd_misc_thread(int vec, void *data)
 			iowrite32(cause, idxd->reg_base + IDXD_INTCAUSE_OFFSET);
 	}
 
-	idxd_unmask_msix_vector(idxd, irq_entry->id);
 	return IRQ_HANDLED;
 }
 
@@ -392,8 +381,6 @@ irqreturn_t idxd_wq_thread(int irq, void *data)
 	int processed;
 
 	processed = idxd_desc_process(irq_entry);
-	idxd_unmask_msix_vector(irq_entry->idxd, irq_entry->id);
-
 	if (processed == 0)
 		return IRQ_NONE;
 
diff --git a/drivers/dma/idxd/perfmon.c b/drivers/dma/idxd/perfmon.c
new file mode 100644
index 000000000000..d73004f47cf4
--- /dev/null
+++ b/drivers/dma/idxd/perfmon.c
@@ -0,0 +1,662 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2020 Intel Corporation. All rights rsvd. */
+
+#include <linux/sched/task.h>
+#include <linux/io-64-nonatomic-lo-hi.h>
+#include "idxd.h"
+#include "perfmon.h"
+
+static ssize_t cpumask_show(struct device *dev, struct device_attribute *attr,
+			    char *buf);
+
+static cpumask_t		perfmon_dsa_cpu_mask;
+static bool			cpuhp_set_up;
+static enum cpuhp_state		cpuhp_slot;
+
+/*
+ * perf userspace reads this attribute to determine which cpus to open
+ * counters on.  It's connected to perfmon_dsa_cpu_mask, which is
+ * maintained by the cpu hotplug handlers.
+ */
+static DEVICE_ATTR_RO(cpumask);
+
+static struct attribute *perfmon_cpumask_attrs[] = {
+	&dev_attr_cpumask.attr,
+	NULL,
+};
+
+static struct attribute_group cpumask_attr_group = {
+	.attrs = perfmon_cpumask_attrs,
+};
+
+/*
+ * These attributes specify the bits in the config word that the perf
+ * syscall uses to pass the event ids and categories to perfmon.
+ */
+DEFINE_PERFMON_FORMAT_ATTR(event_category, "config:0-3");
+DEFINE_PERFMON_FORMAT_ATTR(event, "config:4-31");
+
+/*
+ * These attributes specify the bits in the config1 word that the perf
+ * syscall uses to pass filter data to perfmon.
+ */
+DEFINE_PERFMON_FORMAT_ATTR(filter_wq, "config1:0-31");
+DEFINE_PERFMON_FORMAT_ATTR(filter_tc, "config1:32-39");
+DEFINE_PERFMON_FORMAT_ATTR(filter_pgsz, "config1:40-43");
+DEFINE_PERFMON_FORMAT_ATTR(filter_sz, "config1:44-51");
+DEFINE_PERFMON_FORMAT_ATTR(filter_eng, "config1:52-59");
+
+#define PERFMON_FILTERS_START	2
+#define PERFMON_FILTERS_MAX	5
+
+static struct attribute *perfmon_format_attrs[] = {
+	&format_attr_idxd_event_category.attr,
+	&format_attr_idxd_event.attr,
+	&format_attr_idxd_filter_wq.attr,
+	&format_attr_idxd_filter_tc.attr,
+	&format_attr_idxd_filter_pgsz.attr,
+	&format_attr_idxd_filter_sz.attr,
+	&format_attr_idxd_filter_eng.attr,
+	NULL,
+};
+
+static struct attribute_group perfmon_format_attr_group = {
+	.name = "format",
+	.attrs = perfmon_format_attrs,
+};
+
+static const struct attribute_group *perfmon_attr_groups[] = {
+	&perfmon_format_attr_group,
+	&cpumask_attr_group,
+	NULL,
+};
+
+static ssize_t cpumask_show(struct device *dev, struct device_attribute *attr,
+			    char *buf)
+{
+	return cpumap_print_to_pagebuf(true, buf, &perfmon_dsa_cpu_mask);
+}
+
+static bool is_idxd_event(struct idxd_pmu *idxd_pmu, struct perf_event *event)
+{
+	return &idxd_pmu->pmu == event->pmu;
+}
+
+static int perfmon_collect_events(struct idxd_pmu *idxd_pmu,
+				  struct perf_event *leader,
+				  bool do_grp)
+{
+	struct perf_event *event;
+	int n, max_count;
+
+	max_count = idxd_pmu->n_counters;
+	n = idxd_pmu->n_events;
+
+	if (n >= max_count)
+		return -EINVAL;
+
+	if (is_idxd_event(idxd_pmu, leader)) {
+		idxd_pmu->event_list[n] = leader;
+		idxd_pmu->event_list[n]->hw.idx = n;
+		n++;
+	}
+
+	if (!do_grp)
+		return n;
+
+	for_each_sibling_event(event, leader) {
+		if (!is_idxd_event(idxd_pmu, event) ||
+		    event->state <= PERF_EVENT_STATE_OFF)
+			continue;
+
+		if (n >= max_count)
+			return -EINVAL;
+
+		idxd_pmu->event_list[n] = event;
+		idxd_pmu->event_list[n]->hw.idx = n;
+		n++;
+	}
+
+	return n;
+}
+
+static void perfmon_assign_hw_event(struct idxd_pmu *idxd_pmu,
+				    struct perf_event *event, int idx)
+{
+	struct idxd_device *idxd = idxd_pmu->idxd;
+	struct hw_perf_event *hwc = &event->hw;
+
+	hwc->idx = idx;
+	hwc->config_base = ioread64(CNTRCFG_REG(idxd, idx));
+	hwc->event_base = ioread64(CNTRCFG_REG(idxd, idx));
+}
+
+static int perfmon_assign_event(struct idxd_pmu *idxd_pmu,
+				struct perf_event *event)
+{
+	int i;
+
+	for (i = 0; i < IDXD_PMU_EVENT_MAX; i++)
+		if (!test_and_set_bit(i, idxd_pmu->used_mask))
+			return i;
+
+	return -EINVAL;
+}
+
+/*
+ * Check whether there are enough counters to satisfy that all the
+ * events in the group can actually be scheduled at the same time.
+ *
+ * To do this, create a fake idxd_pmu object so the event collection
+ * and assignment functions can be used without affecting the internal
+ * state of the real idxd_pmu object.
+ */
+static int perfmon_validate_group(struct idxd_pmu *pmu,
+				  struct perf_event *event)
+{
+	struct perf_event *leader = event->group_leader;
+	struct idxd_pmu *fake_pmu;
+	int i, ret = 0, n, idx;
+
+	fake_pmu = kzalloc(sizeof(*fake_pmu), GFP_KERNEL);
+	if (!fake_pmu)
+		return -ENOMEM;
+
+	fake_pmu->pmu.name = pmu->pmu.name;
+	fake_pmu->n_counters = pmu->n_counters;
+
+	n = perfmon_collect_events(fake_pmu, leader, true);
+	if (n < 0) {
+		ret = n;
+		goto out;
+	}
+
+	fake_pmu->n_events = n;
+	n = perfmon_collect_events(fake_pmu, event, false);
+	if (n < 0) {
+		ret = n;
+		goto out;
+	}
+
+	fake_pmu->n_events = n;
+
+	for (i = 0; i < n; i++) {
+		event = fake_pmu->event_list[i];
+
+		idx = perfmon_assign_event(fake_pmu, event);
+		if (idx < 0) {
+			ret = idx;
+			goto out;
+		}
+	}
+out:
+	kfree(fake_pmu);
+
+	return ret;
+}
+
+static int perfmon_pmu_event_init(struct perf_event *event)
+{
+	struct idxd_device *idxd;
+	int ret = 0;
+
+	idxd = event_to_idxd(event);
+	event->hw.idx = -1;
+
+	if (event->attr.type != event->pmu->type)
+		return -ENOENT;
+
+	/* sampling not supported */
+	if (event->attr.sample_period)
+		return -EINVAL;
+
+	if (event->cpu < 0)
+		return -EINVAL;
+
+	if (event->pmu != &idxd->idxd_pmu->pmu)
+		return -EINVAL;
+
+	event->hw.event_base = ioread64(PERFMON_TABLE_OFFSET(idxd));
+	event->cpu = idxd->idxd_pmu->cpu;
+	event->hw.config = event->attr.config;
+
+	if (event->group_leader != event)
+		 /* non-group events have themselves as leader */
+		ret = perfmon_validate_group(idxd->idxd_pmu, event);
+
+	return ret;
+}
+
+static inline u64 perfmon_pmu_read_counter(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct idxd_device *idxd;
+	int cntr = hwc->idx;
+
+	idxd = event_to_idxd(event);
+
+	return ioread64(CNTRDATA_REG(idxd, cntr));
+}
+
+static void perfmon_pmu_event_update(struct perf_event *event)
+{
+	struct idxd_device *idxd = event_to_idxd(event);
+	u64 prev_raw_count, new_raw_count, delta, p, n;
+	int shift = 64 - idxd->idxd_pmu->counter_width;
+	struct hw_perf_event *hwc = &event->hw;
+
+	do {
+		prev_raw_count = local64_read(&hwc->prev_count);
+		new_raw_count = perfmon_pmu_read_counter(event);
+	} while (local64_cmpxchg(&hwc->prev_count, prev_raw_count,
+			new_raw_count) != prev_raw_count);
+
+	n = (new_raw_count << shift);
+	p = (prev_raw_count << shift);
+
+	delta = ((n - p) >> shift);
+
+	local64_add(delta, &event->count);
+}
+
+void perfmon_counter_overflow(struct idxd_device *idxd)
+{
+	int i, n_counters, max_loop = OVERFLOW_SIZE;
+	struct perf_event *event;
+	unsigned long ovfstatus;
+
+	n_counters = min(idxd->idxd_pmu->n_counters, OVERFLOW_SIZE);
+
+	ovfstatus = ioread32(OVFSTATUS_REG(idxd));
+
+	/*
+	 * While updating overflowed counters, other counters behind
+	 * them could overflow and be missed in a given pass.
+	 * Normally this could happen at most n_counters times, but in
+	 * theory a tiny counter width could result in continual
+	 * overflows and endless looping.  max_loop provides a
+	 * failsafe in that highly unlikely case.
+	 */
+	while (ovfstatus && max_loop--) {
+		/* Figure out which counter(s) overflowed */
+		for_each_set_bit(i, &ovfstatus, n_counters) {
+			unsigned long ovfstatus_clear = 0;
+
+			/* Update event->count for overflowed counter */
+			event = idxd->idxd_pmu->event_list[i];
+			perfmon_pmu_event_update(event);
+			/* Writing 1 to OVFSTATUS bit clears it */
+			set_bit(i, &ovfstatus_clear);
+			iowrite32(ovfstatus_clear, OVFSTATUS_REG(idxd));
+		}
+
+		ovfstatus = ioread32(OVFSTATUS_REG(idxd));
+	}
+
+	/*
+	 * Should never happen.  If so, it means a counter(s) looped
+	 * around twice while this handler was running.
+	 */
+	WARN_ON_ONCE(ovfstatus);
+}
+
+static inline void perfmon_reset_config(struct idxd_device *idxd)
+{
+	iowrite32(CONFIG_RESET, PERFRST_REG(idxd));
+	iowrite32(0, OVFSTATUS_REG(idxd));
+	iowrite32(0, PERFFRZ_REG(idxd));
+}
+
+static inline void perfmon_reset_counters(struct idxd_device *idxd)
+{
+	iowrite32(CNTR_RESET, PERFRST_REG(idxd));
+}
+
+static inline void perfmon_reset(struct idxd_device *idxd)
+{
+	perfmon_reset_config(idxd);
+	perfmon_reset_counters(idxd);
+}
+
+static void perfmon_pmu_event_start(struct perf_event *event, int mode)
+{
+	u32 flt_wq, flt_tc, flt_pg_sz, flt_xfer_sz, flt_eng = 0;
+	u64 cntr_cfg, cntrdata, event_enc, event_cat = 0;
+	struct hw_perf_event *hwc = &event->hw;
+	union filter_cfg flt_cfg;
+	union event_cfg event_cfg;
+	struct idxd_device *idxd;
+	int cntr;
+
+	idxd = event_to_idxd(event);
+
+	event->hw.idx = hwc->idx;
+	cntr = hwc->idx;
+
+	/* Obtain event category and event value from user space */
+	event_cfg.val = event->attr.config;
+	flt_cfg.val = event->attr.config1;
+	event_cat = event_cfg.event_cat;
+	event_enc = event_cfg.event_enc;
+
+	/* Obtain filter configuration from user space */
+	flt_wq = flt_cfg.wq;
+	flt_tc = flt_cfg.tc;
+	flt_pg_sz = flt_cfg.pg_sz;
+	flt_xfer_sz = flt_cfg.xfer_sz;
+	flt_eng = flt_cfg.eng;
+
+	if (flt_wq && test_bit(FLT_WQ, &idxd->idxd_pmu->supported_filters))
+		iowrite32(flt_wq, FLTCFG_REG(idxd, cntr, FLT_WQ));
+	if (flt_tc && test_bit(FLT_TC, &idxd->idxd_pmu->supported_filters))
+		iowrite32(flt_tc, FLTCFG_REG(idxd, cntr, FLT_TC));
+	if (flt_pg_sz && test_bit(FLT_PG_SZ, &idxd->idxd_pmu->supported_filters))
+		iowrite32(flt_pg_sz, FLTCFG_REG(idxd, cntr, FLT_PG_SZ));
+	if (flt_xfer_sz && test_bit(FLT_XFER_SZ, &idxd->idxd_pmu->supported_filters))
+		iowrite32(flt_xfer_sz, FLTCFG_REG(idxd, cntr, FLT_XFER_SZ));
+	if (flt_eng && test_bit(FLT_ENG, &idxd->idxd_pmu->supported_filters))
+		iowrite32(flt_eng, FLTCFG_REG(idxd, cntr, FLT_ENG));
+
+	/* Read the start value */
+	cntrdata = ioread64(CNTRDATA_REG(idxd, cntr));
+	local64_set(&event->hw.prev_count, cntrdata);
+
+	/* Set counter to event/category */
+	cntr_cfg = event_cat << CNTRCFG_CATEGORY_SHIFT;
+	cntr_cfg |= event_enc << CNTRCFG_EVENT_SHIFT;
+	/* Set interrupt on overflow and counter enable bits */
+	cntr_cfg |= (CNTRCFG_IRQ_OVERFLOW | CNTRCFG_ENABLE);
+
+	iowrite64(cntr_cfg, CNTRCFG_REG(idxd, cntr));
+}
+
+static void perfmon_pmu_event_stop(struct perf_event *event, int mode)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct idxd_device *idxd;
+	int i, cntr = hwc->idx;
+	u64 cntr_cfg;
+
+	idxd = event_to_idxd(event);
+
+	/* remove this event from event list */
+	for (i = 0; i < idxd->idxd_pmu->n_events; i++) {
+		if (event != idxd->idxd_pmu->event_list[i])
+			continue;
+
+		for (++i; i < idxd->idxd_pmu->n_events; i++)
+			idxd->idxd_pmu->event_list[i - 1] = idxd->idxd_pmu->event_list[i];
+		--idxd->idxd_pmu->n_events;
+		break;
+	}
+
+	cntr_cfg = ioread64(CNTRCFG_REG(idxd, cntr));
+	cntr_cfg &= ~CNTRCFG_ENABLE;
+	iowrite64(cntr_cfg, CNTRCFG_REG(idxd, cntr));
+
+	if (mode == PERF_EF_UPDATE)
+		perfmon_pmu_event_update(event);
+
+	event->hw.idx = -1;
+	clear_bit(cntr, idxd->idxd_pmu->used_mask);
+}
+
+static void perfmon_pmu_event_del(struct perf_event *event, int mode)
+{
+	perfmon_pmu_event_stop(event, PERF_EF_UPDATE);
+}
+
+static int perfmon_pmu_event_add(struct perf_event *event, int flags)
+{
+	struct idxd_device *idxd = event_to_idxd(event);
+	struct idxd_pmu *idxd_pmu = idxd->idxd_pmu;
+	struct hw_perf_event *hwc = &event->hw;
+	int idx, n;
+
+	n = perfmon_collect_events(idxd_pmu, event, false);
+	if (n < 0)
+		return n;
+
+	hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
+	if (!(flags & PERF_EF_START))
+		hwc->state |= PERF_HES_ARCH;
+
+	idx = perfmon_assign_event(idxd_pmu, event);
+	if (idx < 0)
+		return idx;
+
+	perfmon_assign_hw_event(idxd_pmu, event, idx);
+
+	if (flags & PERF_EF_START)
+		perfmon_pmu_event_start(event, 0);
+
+	idxd_pmu->n_events = n;
+
+	return 0;
+}
+
+static void enable_perfmon_pmu(struct idxd_device *idxd)
+{
+	iowrite32(COUNTER_UNFREEZE, PERFFRZ_REG(idxd));
+}
+
+static void disable_perfmon_pmu(struct idxd_device *idxd)
+{
+	iowrite32(COUNTER_FREEZE, PERFFRZ_REG(idxd));
+}
+
+static void perfmon_pmu_enable(struct pmu *pmu)
+{
+	struct idxd_device *idxd = pmu_to_idxd(pmu);
+
+	enable_perfmon_pmu(idxd);
+}
+
+static void perfmon_pmu_disable(struct pmu *pmu)
+{
+	struct idxd_device *idxd = pmu_to_idxd(pmu);
+
+	disable_perfmon_pmu(idxd);
+}
+
+static void skip_filter(int i)
+{
+	int j;
+
+	for (j = i; j < PERFMON_FILTERS_MAX; j++)
+		perfmon_format_attrs[PERFMON_FILTERS_START + j] =
+			perfmon_format_attrs[PERFMON_FILTERS_START + j + 1];
+}
+
+static void idxd_pmu_init(struct idxd_pmu *idxd_pmu)
+{
+	int i;
+
+	for (i = 0 ; i < PERFMON_FILTERS_MAX; i++) {
+		if (!test_bit(i, &idxd_pmu->supported_filters))
+			skip_filter(i);
+	}
+
+	idxd_pmu->pmu.name		= idxd_pmu->name;
+	idxd_pmu->pmu.attr_groups	= perfmon_attr_groups;
+	idxd_pmu->pmu.task_ctx_nr	= perf_invalid_context;
+	idxd_pmu->pmu.event_init	= perfmon_pmu_event_init;
+	idxd_pmu->pmu.pmu_enable	= perfmon_pmu_enable,
+	idxd_pmu->pmu.pmu_disable	= perfmon_pmu_disable,
+	idxd_pmu->pmu.add		= perfmon_pmu_event_add;
+	idxd_pmu->pmu.del		= perfmon_pmu_event_del;
+	idxd_pmu->pmu.start		= perfmon_pmu_event_start;
+	idxd_pmu->pmu.stop		= perfmon_pmu_event_stop;
+	idxd_pmu->pmu.read		= perfmon_pmu_event_update;
+	idxd_pmu->pmu.capabilities	= PERF_PMU_CAP_NO_EXCLUDE;
+	idxd_pmu->pmu.module		= THIS_MODULE;
+}
+
+void perfmon_pmu_remove(struct idxd_device *idxd)
+{
+	if (!idxd->idxd_pmu)
+		return;
+
+	cpuhp_state_remove_instance(cpuhp_slot, &idxd->idxd_pmu->cpuhp_node);
+	perf_pmu_unregister(&idxd->idxd_pmu->pmu);
+	kfree(idxd->idxd_pmu);
+	idxd->idxd_pmu = NULL;
+}
+
+static int perf_event_cpu_online(unsigned int cpu, struct hlist_node *node)
+{
+	struct idxd_pmu *idxd_pmu;
+
+	idxd_pmu = hlist_entry_safe(node, typeof(*idxd_pmu), cpuhp_node);
+
+	/* select the first online CPU as the designated reader */
+	if (cpumask_empty(&perfmon_dsa_cpu_mask)) {
+		cpumask_set_cpu(cpu, &perfmon_dsa_cpu_mask);
+		idxd_pmu->cpu = cpu;
+	}
+
+	return 0;
+}
+
+static int perf_event_cpu_offline(unsigned int cpu, struct hlist_node *node)
+{
+	struct idxd_pmu *idxd_pmu;
+	unsigned int target;
+
+	idxd_pmu = hlist_entry_safe(node, typeof(*idxd_pmu), cpuhp_node);
+
+	if (!cpumask_test_and_clear_cpu(cpu, &perfmon_dsa_cpu_mask))
+		return 0;
+
+	target = cpumask_any_but(cpu_online_mask, cpu);
+
+	/* migrate events if there is a valid target */
+	if (target < nr_cpu_ids)
+		cpumask_set_cpu(target, &perfmon_dsa_cpu_mask);
+	else
+		target = -1;
+
+	perf_pmu_migrate_context(&idxd_pmu->pmu, cpu, target);
+
+	return 0;
+}
+
+int perfmon_pmu_init(struct idxd_device *idxd)
+{
+	union idxd_perfcap perfcap;
+	struct idxd_pmu *idxd_pmu;
+	int rc = -ENODEV;
+
+	/*
+	 * perfmon module initialization failed, nothing to do
+	 */
+	if (!cpuhp_set_up)
+		return -ENODEV;
+
+	/*
+	 * If perfmon_offset or num_counters is 0, it means perfmon is
+	 * not supported on this hardware.
+	 */
+	if (idxd->perfmon_offset == 0)
+		return -ENODEV;
+
+	idxd_pmu = kzalloc(sizeof(*idxd_pmu), GFP_KERNEL);
+	if (!idxd_pmu)
+		return -ENOMEM;
+
+	idxd_pmu->idxd = idxd;
+	idxd->idxd_pmu = idxd_pmu;
+
+	if (idxd->data->type == IDXD_TYPE_DSA) {
+		rc = sprintf(idxd_pmu->name, "dsa%d", idxd->id);
+		if (rc < 0)
+			goto free;
+	} else if (idxd->data->type == IDXD_TYPE_IAX) {
+		rc = sprintf(idxd_pmu->name, "iax%d", idxd->id);
+		if (rc < 0)
+			goto free;
+	} else {
+		goto free;
+	}
+
+	perfmon_reset(idxd);
+
+	perfcap.bits = ioread64(PERFCAP_REG(idxd));
+
+	/*
+	 * If total perf counter is 0, stop further registration.
+	 * This is necessary in order to support driver running on
+	 * guest which does not have pmon support.
+	 */
+	if (perfcap.num_perf_counter == 0)
+		goto free;
+
+	/* A counter width of 0 means it can't count */
+	if (perfcap.counter_width == 0)
+		goto free;
+
+	/* Overflow interrupt and counter freeze support must be available */
+	if (!perfcap.overflow_interrupt || !perfcap.counter_freeze)
+		goto free;
+
+	/* Number of event categories cannot be 0 */
+	if (perfcap.num_event_category == 0)
+		goto free;
+
+	/*
+	 * We don't support per-counter capabilities for now.
+	 */
+	if (perfcap.cap_per_counter)
+		goto free;
+
+	idxd_pmu->n_event_categories = perfcap.num_event_category;
+	idxd_pmu->supported_event_categories = perfcap.global_event_category;
+	idxd_pmu->per_counter_caps_supported = perfcap.cap_per_counter;
+
+	/* check filter capability.  If 0, then filters are not supported */
+	idxd_pmu->supported_filters = perfcap.filter;
+	if (perfcap.filter)
+		idxd_pmu->n_filters = hweight8(perfcap.filter);
+
+	/* Store the total number of counters categories, and counter width */
+	idxd_pmu->n_counters = perfcap.num_perf_counter;
+	idxd_pmu->counter_width = perfcap.counter_width;
+
+	idxd_pmu_init(idxd_pmu);
+
+	rc = perf_pmu_register(&idxd_pmu->pmu, idxd_pmu->name, -1);
+	if (rc)
+		goto free;
+
+	rc = cpuhp_state_add_instance(cpuhp_slot, &idxd_pmu->cpuhp_node);
+	if (rc) {
+		perf_pmu_unregister(&idxd->idxd_pmu->pmu);
+		goto free;
+	}
+out:
+	return rc;
+free:
+	kfree(idxd_pmu);
+	idxd->idxd_pmu = NULL;
+
+	goto out;
+}
+
+void __init perfmon_init(void)
+{
+	int rc = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN,
+					 "driver/dma/idxd/perf:online",
+					 perf_event_cpu_online,
+					 perf_event_cpu_offline);
+	if (WARN_ON(rc < 0))
+		return;
+
+	cpuhp_slot = rc;
+	cpuhp_set_up = true;
+}
+
+void __exit perfmon_exit(void)
+{
+	if (cpuhp_set_up)
+		cpuhp_remove_multi_state(cpuhp_slot);
+}
diff --git a/drivers/dma/idxd/perfmon.h b/drivers/dma/idxd/perfmon.h
new file mode 100644
index 000000000000..9a081a1bc605
--- /dev/null
+++ b/drivers/dma/idxd/perfmon.h
@@ -0,0 +1,119 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2020 Intel Corporation. All rights rsvd. */
+
+#ifndef _PERFMON_H_
+#define _PERFMON_H_
+
+#include <linux/slab.h>
+#include <linux/pci.h>
+#include <linux/sbitmap.h>
+#include <linux/dmaengine.h>
+#include <linux/percpu-rwsem.h>
+#include <linux/wait.h>
+#include <linux/cdev.h>
+#include <linux/uuid.h>
+#include <linux/idxd.h>
+#include <linux/perf_event.h>
+#include "registers.h"
+
+static inline struct idxd_pmu *event_to_pmu(struct perf_event *event)
+{
+	struct idxd_pmu *idxd_pmu;
+	struct pmu *pmu;
+
+	pmu = event->pmu;
+	idxd_pmu = container_of(pmu, struct idxd_pmu, pmu);
+
+	return idxd_pmu;
+}
+
+static inline struct idxd_device *event_to_idxd(struct perf_event *event)
+{
+	struct idxd_pmu *idxd_pmu;
+	struct pmu *pmu;
+
+	pmu = event->pmu;
+	idxd_pmu = container_of(pmu, struct idxd_pmu, pmu);
+
+	return idxd_pmu->idxd;
+}
+
+static inline struct idxd_device *pmu_to_idxd(struct pmu *pmu)
+{
+	struct idxd_pmu *idxd_pmu;
+
+	idxd_pmu = container_of(pmu, struct idxd_pmu, pmu);
+
+	return idxd_pmu->idxd;
+}
+
+enum dsa_perf_events {
+	DSA_PERF_EVENT_WQ = 0,
+	DSA_PERF_EVENT_ENGINE,
+	DSA_PERF_EVENT_ADDR_TRANS,
+	DSA_PERF_EVENT_OP,
+	DSA_PERF_EVENT_COMPL,
+	DSA_PERF_EVENT_MAX,
+};
+
+enum filter_enc {
+	FLT_WQ = 0,
+	FLT_TC,
+	FLT_PG_SZ,
+	FLT_XFER_SZ,
+	FLT_ENG,
+	FLT_MAX,
+};
+
+#define CONFIG_RESET		0x0000000000000001
+#define CNTR_RESET		0x0000000000000002
+#define CNTR_ENABLE		0x0000000000000001
+#define INTR_OVFL		0x0000000000000002
+
+#define COUNTER_FREEZE		0x00000000FFFFFFFF
+#define COUNTER_UNFREEZE	0x0000000000000000
+#define OVERFLOW_SIZE		32
+
+#define CNTRCFG_ENABLE		BIT(0)
+#define CNTRCFG_IRQ_OVERFLOW	BIT(1)
+#define CNTRCFG_CATEGORY_SHIFT	8
+#define CNTRCFG_EVENT_SHIFT	32
+
+#define PERFMON_TABLE_OFFSET(_idxd)				\
+({								\
+	typeof(_idxd) __idxd = (_idxd);				\
+	((__idxd)->reg_base + (__idxd)->perfmon_offset);	\
+})
+#define PERFMON_REG_OFFSET(idxd, offset)			\
+	(PERFMON_TABLE_OFFSET(idxd) + (offset))
+
+#define PERFCAP_REG(idxd)	(PERFMON_REG_OFFSET(idxd, IDXD_PERFCAP_OFFSET))
+#define PERFRST_REG(idxd)	(PERFMON_REG_OFFSET(idxd, IDXD_PERFRST_OFFSET))
+#define OVFSTATUS_REG(idxd)	(PERFMON_REG_OFFSET(idxd, IDXD_OVFSTATUS_OFFSET))
+#define PERFFRZ_REG(idxd)	(PERFMON_REG_OFFSET(idxd, IDXD_PERFFRZ_OFFSET))
+
+#define FLTCFG_REG(idxd, cntr, flt)				\
+	(PERFMON_REG_OFFSET(idxd, IDXD_FLTCFG_OFFSET) +	((cntr) * 32) + ((flt) * 4))
+
+#define CNTRCFG_REG(idxd, cntr)					\
+	(PERFMON_REG_OFFSET(idxd, IDXD_CNTRCFG_OFFSET) + ((cntr) * 8))
+#define CNTRDATA_REG(idxd, cntr)					\
+	(PERFMON_REG_OFFSET(idxd, IDXD_CNTRDATA_OFFSET) + ((cntr) * 8))
+#define CNTRCAP_REG(idxd, cntr)					\
+	(PERFMON_REG_OFFSET(idxd, IDXD_CNTRCAP_OFFSET) + ((cntr) * 8))
+
+#define EVNTCAP_REG(idxd, category) \
+	(PERFMON_REG_OFFSET(idxd, IDXD_EVNTCAP_OFFSET) + ((category) * 8))
+
+#define DEFINE_PERFMON_FORMAT_ATTR(_name, _format)			\
+static ssize_t __perfmon_idxd_##_name##_show(struct kobject *kobj,	\
+				struct kobj_attribute *attr,		\
+				char *page)				\
+{									\
+	BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE);			\
+	return sprintf(page, _format "\n");				\
+}									\
+static struct kobj_attribute format_attr_idxd_##_name =			\
+	__ATTR(_name, 0444, __perfmon_idxd_##_name##_show, NULL)
+
+#endif
diff --git a/drivers/dma/idxd/registers.h b/drivers/dma/idxd/registers.h
index 751ecb4f9f81..c970c3f025f0 100644
--- a/drivers/dma/idxd/registers.h
+++ b/drivers/dma/idxd/registers.h
@@ -24,8 +24,8 @@ union gen_cap_reg {
 		u64 overlap_copy:1;
 		u64 cache_control_mem:1;
 		u64 cache_control_cache:1;
+		u64 cmd_cap:1;
 		u64 rsvd:3;
-		u64 int_handle_req:1;
 		u64 dest_readback:1;
 		u64 drain_readback:1;
 		u64 rsvd2:6;
@@ -120,7 +120,8 @@ union gencfg_reg {
 union genctrl_reg {
 	struct {
 		u32 softerr_int_en:1;
-		u32 rsvd:31;
+		u32 halt_int_en:1;
+		u32 rsvd:30;
 	};
 	u32 bits;
 } __packed;
@@ -180,8 +181,11 @@ enum idxd_cmd {
 	IDXD_CMD_DRAIN_PASID,
 	IDXD_CMD_ABORT_PASID,
 	IDXD_CMD_REQUEST_INT_HANDLE,
+	IDXD_CMD_RELEASE_INT_HANDLE,
 };
 
+#define CMD_INT_HANDLE_IMS		0x10000
+
 #define IDXD_CMDSTS_OFFSET		0xa8
 union cmdsts_reg {
 	struct {
@@ -193,6 +197,8 @@ union cmdsts_reg {
 	u32 bits;
 } __packed;
 #define IDXD_CMDSTS_ACTIVE		0x80000000
+#define IDXD_CMDSTS_ERR_MASK		0xff
+#define IDXD_CMDSTS_RES_SHIFT		8
 
 enum idxd_cmdsts_err {
 	IDXD_CMDSTS_SUCCESS = 0,
@@ -228,6 +234,8 @@ enum idxd_cmdsts_err {
 	IDXD_CMDSTS_ERR_NO_HANDLE,
 };
 
+#define IDXD_CMDCAP_OFFSET		0xb0
+
 #define IDXD_SWERR_OFFSET		0xc0
 #define IDXD_SWERR_VALID		0x00000001
 #define IDXD_SWERR_OVERFLOW		0x00000002
@@ -378,4 +386,112 @@ union wqcfg {
 #define GRPENGCFG_OFFSET(idxd_dev, n) ((idxd_dev)->grpcfg_offset + (n) * GRPCFG_SIZE + 32)
 #define GRPFLGCFG_OFFSET(idxd_dev, n) ((idxd_dev)->grpcfg_offset + (n) * GRPCFG_SIZE + 40)
 
+/* Following is performance monitor registers */
+#define IDXD_PERFCAP_OFFSET		0x0
+union idxd_perfcap {
+	struct {
+		u64 num_perf_counter:6;
+		u64 rsvd1:2;
+		u64 counter_width:8;
+		u64 num_event_category:4;
+		u64 global_event_category:16;
+		u64 filter:8;
+		u64 rsvd2:8;
+		u64 cap_per_counter:1;
+		u64 writeable_counter:1;
+		u64 counter_freeze:1;
+		u64 overflow_interrupt:1;
+		u64 rsvd3:8;
+	};
+	u64 bits;
+} __packed;
+
+#define IDXD_EVNTCAP_OFFSET		0x80
+union idxd_evntcap {
+	struct {
+		u64 events:28;
+		u64 rsvd:36;
+	};
+	u64 bits;
+} __packed;
+
+struct idxd_event {
+	union {
+		struct {
+			u32 event_category:4;
+			u32 events:28;
+		};
+		u32 val;
+	};
+} __packed;
+
+#define IDXD_CNTRCAP_OFFSET		0x800
+struct idxd_cntrcap {
+	union {
+		struct {
+			u32 counter_width:8;
+			u32 rsvd:20;
+			u32 num_events:4;
+		};
+		u32 val;
+	};
+	struct idxd_event events[];
+} __packed;
+
+#define IDXD_PERFRST_OFFSET		0x10
+union idxd_perfrst {
+	struct {
+		u32 perfrst_config:1;
+		u32 perfrst_counter:1;
+		u32 rsvd:30;
+	};
+	u32 val;
+} __packed;
+
+#define IDXD_OVFSTATUS_OFFSET		0x30
+#define IDXD_PERFFRZ_OFFSET		0x20
+#define IDXD_CNTRCFG_OFFSET		0x100
+union idxd_cntrcfg {
+	struct {
+		u64 enable:1;
+		u64 interrupt_ovf:1;
+		u64 global_freeze_ovf:1;
+		u64 rsvd1:5;
+		u64 event_category:4;
+		u64 rsvd2:20;
+		u64 events:28;
+		u64 rsvd3:4;
+	};
+	u64 val;
+} __packed;
+
+#define IDXD_FLTCFG_OFFSET		0x300
+
+#define IDXD_CNTRDATA_OFFSET		0x200
+union idxd_cntrdata {
+	struct {
+		u64 event_count_value;
+	};
+	u64 val;
+} __packed;
+
+union event_cfg {
+	struct {
+		u64 event_cat:4;
+		u64 event_enc:28;
+	};
+	u64 val;
+} __packed;
+
+union filter_cfg {
+	struct {
+		u64 wq:32;
+		u64 tc:8;
+		u64 pg_sz:4;
+		u64 xfer_sz:8;
+		u64 eng:8;
+	};
+	u64 val;
+} __packed;
+
 #endif
diff --git a/drivers/dma/idxd/submit.c b/drivers/dma/idxd/submit.c
index a7a61bcc17d5..19afb62abaff 100644
--- a/drivers/dma/idxd/submit.c
+++ b/drivers/dma/idxd/submit.c
@@ -15,18 +15,30 @@ static struct idxd_desc *__get_desc(struct idxd_wq *wq, int idx, int cpu)
 
 	desc = wq->descs[idx];
 	memset(desc->hw, 0, sizeof(struct dsa_hw_desc));
-	memset(desc->completion, 0, idxd->compl_size);
+	memset(desc->completion, 0, idxd->data->compl_size);
 	desc->cpu = cpu;
 
 	if (device_pasid_enabled(idxd))
 		desc->hw->pasid = idxd->pasid;
 
 	/*
-	 * Descriptor completion vectors are 1-8 for MSIX. We will round
-	 * robin through the 8 vectors.
+	 * Descriptor completion vectors are 1...N for MSIX. We will round
+	 * robin through the N vectors.
 	 */
 	wq->vec_ptr = (wq->vec_ptr % idxd->num_wq_irqs) + 1;
-	desc->hw->int_handle = wq->vec_ptr;
+	if (!idxd->int_handles) {
+		desc->hw->int_handle = wq->vec_ptr;
+	} else {
+		desc->vector = wq->vec_ptr;
+		/*
+		 * int_handles are only for descriptor completion. However for device
+		 * MSIX enumeration, vec 0 is used for misc interrupts. Therefore even
+		 * though we are rotating through 1...N for descriptor interrupts, we
+		 * need to acqurie the int_handles from 0..N-1.
+		 */
+		desc->hw->int_handle = idxd->int_handles[desc->vector - 1];
+	}
+
 	return desc;
 }
 
@@ -79,13 +91,15 @@ void idxd_free_desc(struct idxd_wq *wq, struct idxd_desc *desc)
 int idxd_submit_desc(struct idxd_wq *wq, struct idxd_desc *desc)
 {
 	struct idxd_device *idxd = wq->idxd;
-	int vec = desc->hw->int_handle;
 	void __iomem *portal;
 	int rc;
 
 	if (idxd->state != IDXD_DEV_ENABLED)
 		return -EIO;
 
+	if (!percpu_ref_tryget_live(&wq->wq_active))
+		return -ENXIO;
+
 	portal = wq->portal;
 
 	/*
@@ -108,13 +122,25 @@ int idxd_submit_desc(struct idxd_wq *wq, struct idxd_desc *desc)
 			return rc;
 	}
 
+	percpu_ref_put(&wq->wq_active);
+
 	/*
 	 * Pending the descriptor to the lockless list for the irq_entry
 	 * that we designated the descriptor to.
 	 */
-	if (desc->hw->flags & IDXD_OP_FLAG_RCI)
-		llist_add(&desc->llnode,
-			  &idxd->irq_entries[vec].pending_llist);
+	if (desc->hw->flags & IDXD_OP_FLAG_RCI) {
+		int vec;
+
+		/*
+		 * If the driver is on host kernel, it would be the value
+		 * assigned to interrupt handle, which is index for MSIX
+		 * vector. If it's guest then can't use the int_handle since
+		 * that is the index to IMS for the entire device. The guest
+		 * device local index will be used.
+		 */
+		vec = !idxd->int_handles ? desc->hw->int_handle : desc->vector;
+		llist_add(&desc->llnode, &idxd->irq_entries[vec].pending_llist);
+	}
 
 	return 0;
 }
diff --git a/drivers/dma/idxd/sysfs.c b/drivers/dma/idxd/sysfs.c
index 18bf4d148989..0460d58e3941 100644
--- a/drivers/dma/idxd/sysfs.c
+++ b/drivers/dma/idxd/sysfs.c
@@ -16,69 +16,6 @@ static char *idxd_wq_type_names[] = {
 	[IDXD_WQT_USER]		= "user",
 };
 
-static void idxd_conf_device_release(struct device *dev)
-{
-	dev_dbg(dev, "%s for %s\n", __func__, dev_name(dev));
-}
-
-static struct device_type idxd_group_device_type = {
-	.name = "group",
-	.release = idxd_conf_device_release,
-};
-
-static struct device_type idxd_wq_device_type = {
-	.name = "wq",
-	.release = idxd_conf_device_release,
-};
-
-static struct device_type idxd_engine_device_type = {
-	.name = "engine",
-	.release = idxd_conf_device_release,
-};
-
-static struct device_type dsa_device_type = {
-	.name = "dsa",
-	.release = idxd_conf_device_release,
-};
-
-static struct device_type iax_device_type = {
-	.name = "iax",
-	.release = idxd_conf_device_release,
-};
-
-static inline bool is_dsa_dev(struct device *dev)
-{
-	return dev ? dev->type == &dsa_device_type : false;
-}
-
-static inline bool is_iax_dev(struct device *dev)
-{
-	return dev ? dev->type == &iax_device_type : false;
-}
-
-static inline bool is_idxd_dev(struct device *dev)
-{
-	return is_dsa_dev(dev) || is_iax_dev(dev);
-}
-
-static inline bool is_idxd_wq_dev(struct device *dev)
-{
-	return dev ? dev->type == &idxd_wq_device_type : false;
-}
-
-static inline bool is_idxd_wq_dmaengine(struct idxd_wq *wq)
-{
-	if (wq->type == IDXD_WQT_KERNEL &&
-	    strcmp(wq->name, "dmaengine") == 0)
-		return true;
-	return false;
-}
-
-static inline bool is_idxd_wq_cdev(struct idxd_wq *wq)
-{
-	return wq->type == IDXD_WQT_USER;
-}
-
 static int idxd_config_bus_match(struct device *dev,
 				 struct device_driver *drv)
 {
@@ -110,9 +47,131 @@ static int idxd_config_bus_match(struct device *dev,
 	return matched;
 }
 
-static int idxd_config_bus_probe(struct device *dev)
+static int enable_wq(struct idxd_wq *wq)
 {
+	struct idxd_device *idxd = wq->idxd;
+	struct device *dev = &idxd->pdev->dev;
+	unsigned long flags;
 	int rc;
+
+	mutex_lock(&wq->wq_lock);
+
+	if (idxd->state != IDXD_DEV_ENABLED) {
+		mutex_unlock(&wq->wq_lock);
+		dev_warn(dev, "Enabling while device not enabled.\n");
+		return -EPERM;
+	}
+
+	if (wq->state != IDXD_WQ_DISABLED) {
+		mutex_unlock(&wq->wq_lock);
+		dev_warn(dev, "WQ %d already enabled.\n", wq->id);
+		return -EBUSY;
+	}
+
+	if (!wq->group) {
+		mutex_unlock(&wq->wq_lock);
+		dev_warn(dev, "WQ not attached to group.\n");
+		return -EINVAL;
+	}
+
+	if (strlen(wq->name) == 0) {
+		mutex_unlock(&wq->wq_lock);
+		dev_warn(dev, "WQ name not set.\n");
+		return -EINVAL;
+	}
+
+	/* Shared WQ checks */
+	if (wq_shared(wq)) {
+		if (!device_swq_supported(idxd)) {
+			dev_warn(dev, "PASID not enabled and shared WQ.\n");
+			mutex_unlock(&wq->wq_lock);
+			return -ENXIO;
+		}
+		/*
+		 * Shared wq with the threshold set to 0 means the user
+		 * did not set the threshold or transitioned from a
+		 * dedicated wq but did not set threshold. A value
+		 * of 0 would effectively disable the shared wq. The
+		 * driver does not allow a value of 0 to be set for
+		 * threshold via sysfs.
+		 */
+		if (wq->threshold == 0) {
+			dev_warn(dev, "Shared WQ and threshold 0.\n");
+			mutex_unlock(&wq->wq_lock);
+			return -EINVAL;
+		}
+	}
+
+	rc = idxd_wq_alloc_resources(wq);
+	if (rc < 0) {
+		mutex_unlock(&wq->wq_lock);
+		dev_warn(dev, "WQ resource alloc failed\n");
+		return rc;
+	}
+
+	spin_lock_irqsave(&idxd->dev_lock, flags);
+	if (test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags))
+		rc = idxd_device_config(idxd);
+	spin_unlock_irqrestore(&idxd->dev_lock, flags);
+	if (rc < 0) {
+		mutex_unlock(&wq->wq_lock);
+		dev_warn(dev, "Writing WQ %d config failed: %d\n", wq->id, rc);
+		return rc;
+	}
+
+	rc = idxd_wq_enable(wq);
+	if (rc < 0) {
+		mutex_unlock(&wq->wq_lock);
+		dev_warn(dev, "WQ %d enabling failed: %d\n", wq->id, rc);
+		return rc;
+	}
+
+	rc = idxd_wq_map_portal(wq);
+	if (rc < 0) {
+		dev_warn(dev, "wq portal mapping failed: %d\n", rc);
+		rc = idxd_wq_disable(wq);
+		if (rc < 0)
+			dev_warn(dev, "IDXD wq disable failed\n");
+		mutex_unlock(&wq->wq_lock);
+		return rc;
+	}
+
+	wq->client_count = 0;
+
+	if (wq->type == IDXD_WQT_KERNEL) {
+		rc = idxd_wq_init_percpu_ref(wq);
+		if (rc < 0) {
+			dev_dbg(dev, "percpu_ref setup failed\n");
+			mutex_unlock(&wq->wq_lock);
+			return rc;
+		}
+	}
+
+	if (is_idxd_wq_dmaengine(wq)) {
+		rc = idxd_register_dma_channel(wq);
+		if (rc < 0) {
+			dev_dbg(dev, "DMA channel register failed\n");
+			mutex_unlock(&wq->wq_lock);
+			return rc;
+		}
+	} else if (is_idxd_wq_cdev(wq)) {
+		rc = idxd_wq_add_cdev(wq);
+		if (rc < 0) {
+			dev_dbg(dev, "Cdev creation failed\n");
+			mutex_unlock(&wq->wq_lock);
+			return rc;
+		}
+	}
+
+	mutex_unlock(&wq->wq_lock);
+	dev_info(dev, "wq %s enabled\n", dev_name(&wq->conf_dev));
+
+	return 0;
+}
+
+static int idxd_config_bus_probe(struct device *dev)
+{
+	int rc = 0;
 	unsigned long flags;
 
 	dev_dbg(dev, "%s called\n", __func__);
@@ -130,7 +189,8 @@ static int idxd_config_bus_probe(struct device *dev)
 
 		/* Perform IDXD configuration and enabling */
 		spin_lock_irqsave(&idxd->dev_lock, flags);
-		rc = idxd_device_config(idxd);
+		if (test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags))
+			rc = idxd_device_config(idxd);
 		spin_unlock_irqrestore(&idxd->dev_lock, flags);
 		if (rc < 0) {
 			module_put(THIS_MODULE);
@@ -157,115 +217,8 @@ static int idxd_config_bus_probe(struct device *dev)
 		return 0;
 	} else if (is_idxd_wq_dev(dev)) {
 		struct idxd_wq *wq = confdev_to_wq(dev);
-		struct idxd_device *idxd = wq->idxd;
-
-		mutex_lock(&wq->wq_lock);
-
-		if (idxd->state != IDXD_DEV_ENABLED) {
-			mutex_unlock(&wq->wq_lock);
-			dev_warn(dev, "Enabling while device not enabled.\n");
-			return -EPERM;
-		}
-
-		if (wq->state != IDXD_WQ_DISABLED) {
-			mutex_unlock(&wq->wq_lock);
-			dev_warn(dev, "WQ %d already enabled.\n", wq->id);
-			return -EBUSY;
-		}
-
-		if (!wq->group) {
-			mutex_unlock(&wq->wq_lock);
-			dev_warn(dev, "WQ not attached to group.\n");
-			return -EINVAL;
-		}
-
-		if (strlen(wq->name) == 0) {
-			mutex_unlock(&wq->wq_lock);
-			dev_warn(dev, "WQ name not set.\n");
-			return -EINVAL;
-		}
-
-		/* Shared WQ checks */
-		if (wq_shared(wq)) {
-			if (!device_swq_supported(idxd)) {
-				dev_warn(dev,
-					 "PASID not enabled and shared WQ.\n");
-				mutex_unlock(&wq->wq_lock);
-				return -ENXIO;
-			}
-			/*
-			 * Shared wq with the threshold set to 0 means the user
-			 * did not set the threshold or transitioned from a
-			 * dedicated wq but did not set threshold. A value
-			 * of 0 would effectively disable the shared wq. The
-			 * driver does not allow a value of 0 to be set for
-			 * threshold via sysfs.
-			 */
-			if (wq->threshold == 0) {
-				dev_warn(dev,
-					 "Shared WQ and threshold 0.\n");
-				mutex_unlock(&wq->wq_lock);
-				return -EINVAL;
-			}
-		}
-
-		rc = idxd_wq_alloc_resources(wq);
-		if (rc < 0) {
-			mutex_unlock(&wq->wq_lock);
-			dev_warn(dev, "WQ resource alloc failed\n");
-			return rc;
-		}
-
-		spin_lock_irqsave(&idxd->dev_lock, flags);
-		rc = idxd_device_config(idxd);
-		spin_unlock_irqrestore(&idxd->dev_lock, flags);
-		if (rc < 0) {
-			mutex_unlock(&wq->wq_lock);
-			dev_warn(dev, "Writing WQ %d config failed: %d\n",
-				 wq->id, rc);
-			return rc;
-		}
-
-		rc = idxd_wq_enable(wq);
-		if (rc < 0) {
-			mutex_unlock(&wq->wq_lock);
-			dev_warn(dev, "WQ %d enabling failed: %d\n",
-				 wq->id, rc);
-			return rc;
-		}
-
-		rc = idxd_wq_map_portal(wq);
-		if (rc < 0) {
-			dev_warn(dev, "wq portal mapping failed: %d\n", rc);
-			rc = idxd_wq_disable(wq);
-			if (rc < 0)
-				dev_warn(dev, "IDXD wq disable failed\n");
-			mutex_unlock(&wq->wq_lock);
-			return rc;
-		}
-
-		wq->client_count = 0;
-
-		dev_info(dev, "wq %s enabled\n", dev_name(&wq->conf_dev));
 
-		if (is_idxd_wq_dmaengine(wq)) {
-			rc = idxd_register_dma_channel(wq);
-			if (rc < 0) {
-				dev_dbg(dev, "DMA channel register failed\n");
-				mutex_unlock(&wq->wq_lock);
-				return rc;
-			}
-		} else if (is_idxd_wq_cdev(wq)) {
-			rc = idxd_wq_add_cdev(wq);
-			if (rc < 0) {
-				dev_dbg(dev, "Cdev creation failed\n");
-				mutex_unlock(&wq->wq_lock);
-				return rc;
-			}
-		}
-
-		mutex_unlock(&wq->wq_lock);
-		return 0;
+		return enable_wq(wq);
 	}
 
 	return -ENODEV;
@@ -283,6 +236,9 @@ static void disable_wq(struct idxd_wq *wq)
 		return;
 	}
 
+	if (wq->type == IDXD_WQT_KERNEL)
+		idxd_wq_quiesce(wq);
+
 	if (is_idxd_wq_dmaengine(wq))
 		idxd_unregister_dma_channel(wq);
 	else if (is_idxd_wq_cdev(wq))
@@ -322,7 +278,7 @@ static int idxd_config_bus_remove(struct device *dev)
 		dev_dbg(dev, "%s removing dev %s\n", __func__,
 			dev_name(&idxd->conf_dev));
 		for (i = 0; i < idxd->max_wqs; i++) {
-			struct idxd_wq *wq = &idxd->wqs[i];
+			struct idxd_wq *wq = idxd->wqs[i];
 
 			if (wq->state == IDXD_WQ_DISABLED)
 				continue;
@@ -333,12 +289,14 @@ static int idxd_config_bus_remove(struct device *dev)
 
 		idxd_unregister_dma_device(idxd);
 		rc = idxd_device_disable(idxd);
-		for (i = 0; i < idxd->max_wqs; i++) {
-			struct idxd_wq *wq = &idxd->wqs[i];
+		if (test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags)) {
+			for (i = 0; i < idxd->max_wqs; i++) {
+				struct idxd_wq *wq = idxd->wqs[i];
 
-			mutex_lock(&wq->wq_lock);
-			idxd_wq_disable_cleanup(wq);
-			mutex_unlock(&wq->wq_lock);
+				mutex_lock(&wq->wq_lock);
+				idxd_wq_disable_cleanup(wq);
+				mutex_unlock(&wq->wq_lock);
+			}
 		}
 		module_put(THIS_MODULE);
 		if (rc < 0)
@@ -364,19 +322,6 @@ struct bus_type dsa_bus_type = {
 	.shutdown = idxd_config_bus_shutdown,
 };
 
-struct bus_type iax_bus_type = {
-	.name = "iax",
-	.match = idxd_config_bus_match,
-	.probe = idxd_config_bus_probe,
-	.remove = idxd_config_bus_remove,
-	.shutdown = idxd_config_bus_shutdown,
-};
-
-static struct bus_type *idxd_bus_types[] = {
-	&dsa_bus_type,
-	&iax_bus_type
-};
-
 static struct idxd_device_driver dsa_drv = {
 	.drv = {
 		.name = "dsa",
@@ -386,60 +331,15 @@ static struct idxd_device_driver dsa_drv = {
 	},
 };
 
-static struct idxd_device_driver iax_drv = {
-	.drv = {
-		.name = "iax",
-		.bus = &iax_bus_type,
-		.owner = THIS_MODULE,
-		.mod_name = KBUILD_MODNAME,
-	},
-};
-
-static struct idxd_device_driver *idxd_drvs[] = {
-	&dsa_drv,
-	&iax_drv
-};
-
-struct bus_type *idxd_get_bus_type(struct idxd_device *idxd)
-{
-	return idxd_bus_types[idxd->type];
-}
-
-static struct device_type *idxd_get_device_type(struct idxd_device *idxd)
-{
-	if (idxd->type == IDXD_TYPE_DSA)
-		return &dsa_device_type;
-	else if (idxd->type == IDXD_TYPE_IAX)
-		return &iax_device_type;
-	else
-		return NULL;
-}
-
 /* IDXD generic driver setup */
 int idxd_register_driver(void)
 {
-	int i, rc;
-
-	for (i = 0; i < IDXD_TYPE_MAX; i++) {
-		rc = driver_register(&idxd_drvs[i]->drv);
-		if (rc < 0)
-			goto drv_fail;
-	}
-
-	return 0;
-
-drv_fail:
-	while (--i >= 0)
-		driver_unregister(&idxd_drvs[i]->drv);
-	return rc;
+	return driver_register(&dsa_drv.drv);
 }
 
 void idxd_unregister_driver(void)
 {
-	int i;
-
-	for (i = 0; i < IDXD_TYPE_MAX; i++)
-		driver_unregister(&idxd_drvs[i]->drv);
+	driver_unregister(&dsa_drv.drv);
 }
 
 /* IDXD engine attributes */
@@ -450,9 +350,9 @@ static ssize_t engine_group_id_show(struct device *dev,
 		container_of(dev, struct idxd_engine, conf_dev);
 
 	if (engine->group)
-		return sprintf(buf, "%d\n", engine->group->id);
+		return sysfs_emit(buf, "%d\n", engine->group->id);
 	else
-		return sprintf(buf, "%d\n", -1);
+		return sysfs_emit(buf, "%d\n", -1);
 }
 
 static ssize_t engine_group_id_store(struct device *dev,
@@ -488,7 +388,7 @@ static ssize_t engine_group_id_store(struct device *dev,
 
 	if (prevg)
 		prevg->num_engines--;
-	engine->group = &idxd->groups[id];
+	engine->group = idxd->groups[id];
 	engine->group->num_engines++;
 
 	return count;
@@ -512,6 +412,19 @@ static const struct attribute_group *idxd_engine_attribute_groups[] = {
 	NULL,
 };
 
+static void idxd_conf_engine_release(struct device *dev)
+{
+	struct idxd_engine *engine = container_of(dev, struct idxd_engine, conf_dev);
+
+	kfree(engine);
+}
+
+struct device_type idxd_engine_device_type = {
+	.name = "engine",
+	.release = idxd_conf_engine_release,
+	.groups = idxd_engine_attribute_groups,
+};
+
 /* Group attributes */
 
 static void idxd_set_free_tokens(struct idxd_device *idxd)
@@ -519,7 +432,7 @@ static void idxd_set_free_tokens(struct idxd_device *idxd)
 	int i, tokens;
 
 	for (i = 0, tokens = 0; i < idxd->max_groups; i++) {
-		struct idxd_group *g = &idxd->groups[i];
+		struct idxd_group *g = idxd->groups[i];
 
 		tokens += g->tokens_reserved;
 	}
@@ -534,7 +447,7 @@ static ssize_t group_tokens_reserved_show(struct device *dev,
 	struct idxd_group *group =
 		container_of(dev, struct idxd_group, conf_dev);
 
-	return sprintf(buf, "%u\n", group->tokens_reserved);
+	return sysfs_emit(buf, "%u\n", group->tokens_reserved);
 }
 
 static ssize_t group_tokens_reserved_store(struct device *dev,
@@ -551,7 +464,7 @@ static ssize_t group_tokens_reserved_store(struct device *dev,
 	if (rc < 0)
 		return -EINVAL;
 
-	if (idxd->type == IDXD_TYPE_IAX)
+	if (idxd->data->type == IDXD_TYPE_IAX)
 		return -EOPNOTSUPP;
 
 	if (!test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags))
@@ -582,7 +495,7 @@ static ssize_t group_tokens_allowed_show(struct device *dev,
 	struct idxd_group *group =
 		container_of(dev, struct idxd_group, conf_dev);
 
-	return sprintf(buf, "%u\n", group->tokens_allowed);
+	return sysfs_emit(buf, "%u\n", group->tokens_allowed);
 }
 
 static ssize_t group_tokens_allowed_store(struct device *dev,
@@ -599,7 +512,7 @@ static ssize_t group_tokens_allowed_store(struct device *dev,
 	if (rc < 0)
 		return -EINVAL;
 
-	if (idxd->type == IDXD_TYPE_IAX)
+	if (idxd->data->type == IDXD_TYPE_IAX)
 		return -EOPNOTSUPP;
 
 	if (!test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags))
@@ -627,7 +540,7 @@ static ssize_t group_use_token_limit_show(struct device *dev,
 	struct idxd_group *group =
 		container_of(dev, struct idxd_group, conf_dev);
 
-	return sprintf(buf, "%u\n", group->use_token_limit);
+	return sysfs_emit(buf, "%u\n", group->use_token_limit);
 }
 
 static ssize_t group_use_token_limit_store(struct device *dev,
@@ -644,7 +557,7 @@ static ssize_t group_use_token_limit_store(struct device *dev,
 	if (rc < 0)
 		return -EINVAL;
 
-	if (idxd->type == IDXD_TYPE_IAX)
+	if (idxd->data->type == IDXD_TYPE_IAX)
 		return -EOPNOTSUPP;
 
 	if (!test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags))
@@ -670,22 +583,22 @@ static ssize_t group_engines_show(struct device *dev,
 	struct idxd_group *group =
 		container_of(dev, struct idxd_group, conf_dev);
 	int i, rc = 0;
-	char *tmp = buf;
 	struct idxd_device *idxd = group->idxd;
 
 	for (i = 0; i < idxd->max_engines; i++) {
-		struct idxd_engine *engine = &idxd->engines[i];
+		struct idxd_engine *engine = idxd->engines[i];
 
 		if (!engine->group)
 			continue;
 
 		if (engine->group->id == group->id)
-			rc += sprintf(tmp + rc, "engine%d.%d ",
-					idxd->id, engine->id);
+			rc += sysfs_emit_at(buf, rc, "engine%d.%d ", idxd->id, engine->id);
 	}
 
+	if (!rc)
+		return 0;
 	rc--;
-	rc += sprintf(tmp + rc, "\n");
+	rc += sysfs_emit_at(buf, rc, "\n");
 
 	return rc;
 }
@@ -699,22 +612,22 @@ static ssize_t group_work_queues_show(struct device *dev,
 	struct idxd_group *group =
 		container_of(dev, struct idxd_group, conf_dev);
 	int i, rc = 0;
-	char *tmp = buf;
 	struct idxd_device *idxd = group->idxd;
 
 	for (i = 0; i < idxd->max_wqs; i++) {
-		struct idxd_wq *wq = &idxd->wqs[i];
+		struct idxd_wq *wq = idxd->wqs[i];
 
 		if (!wq->group)
 			continue;
 
 		if (wq->group->id == group->id)
-			rc += sprintf(tmp + rc, "wq%d.%d ",
-					idxd->id, wq->id);
+			rc += sysfs_emit_at(buf, rc, "wq%d.%d ", idxd->id, wq->id);
 	}
 
+	if (!rc)
+		return 0;
 	rc--;
-	rc += sprintf(tmp + rc, "\n");
+	rc += sysfs_emit_at(buf, rc, "\n");
 
 	return rc;
 }
@@ -729,7 +642,7 @@ static ssize_t group_traffic_class_a_show(struct device *dev,
 	struct idxd_group *group =
 		container_of(dev, struct idxd_group, conf_dev);
 
-	return sprintf(buf, "%d\n", group->tc_a);
+	return sysfs_emit(buf, "%d\n", group->tc_a);
 }
 
 static ssize_t group_traffic_class_a_store(struct device *dev,
@@ -770,7 +683,7 @@ static ssize_t group_traffic_class_b_show(struct device *dev,
 	struct idxd_group *group =
 		container_of(dev, struct idxd_group, conf_dev);
 
-	return sprintf(buf, "%d\n", group->tc_b);
+	return sysfs_emit(buf, "%d\n", group->tc_b);
 }
 
 static ssize_t group_traffic_class_b_store(struct device *dev,
@@ -824,13 +737,26 @@ static const struct attribute_group *idxd_group_attribute_groups[] = {
 	NULL,
 };
 
+static void idxd_conf_group_release(struct device *dev)
+{
+	struct idxd_group *group = container_of(dev, struct idxd_group, conf_dev);
+
+	kfree(group);
+}
+
+struct device_type idxd_group_device_type = {
+	.name = "group",
+	.release = idxd_conf_group_release,
+	.groups = idxd_group_attribute_groups,
+};
+
 /* IDXD work queue attribs */
 static ssize_t wq_clients_show(struct device *dev,
 			       struct device_attribute *attr, char *buf)
 {
 	struct idxd_wq *wq = container_of(dev, struct idxd_wq, conf_dev);
 
-	return sprintf(buf, "%d\n", wq->client_count);
+	return sysfs_emit(buf, "%d\n", wq->client_count);
 }
 
 static struct device_attribute dev_attr_wq_clients =
@@ -843,12 +769,12 @@ static ssize_t wq_state_show(struct device *dev,
 
 	switch (wq->state) {
 	case IDXD_WQ_DISABLED:
-		return sprintf(buf, "disabled\n");
+		return sysfs_emit(buf, "disabled\n");
 	case IDXD_WQ_ENABLED:
-		return sprintf(buf, "enabled\n");
+		return sysfs_emit(buf, "enabled\n");
 	}
 
-	return sprintf(buf, "unknown\n");
+	return sysfs_emit(buf, "unknown\n");
 }
 
 static struct device_attribute dev_attr_wq_state =
@@ -860,9 +786,9 @@ static ssize_t wq_group_id_show(struct device *dev,
 	struct idxd_wq *wq = container_of(dev, struct idxd_wq, conf_dev);
 
 	if (wq->group)
-		return sprintf(buf, "%u\n", wq->group->id);
+		return sysfs_emit(buf, "%u\n", wq->group->id);
 	else
-		return sprintf(buf, "-1\n");
+		return sysfs_emit(buf, "-1\n");
 }
 
 static ssize_t wq_group_id_store(struct device *dev,
@@ -896,7 +822,7 @@ static ssize_t wq_group_id_store(struct device *dev,
 		return count;
 	}
 
-	group = &idxd->groups[id];
+	group = idxd->groups[id];
 	prevg = wq->group;
 
 	if (prevg)
@@ -914,8 +840,7 @@ static ssize_t wq_mode_show(struct device *dev, struct device_attribute *attr,
 {
 	struct idxd_wq *wq = container_of(dev, struct idxd_wq, conf_dev);
 
-	return sprintf(buf, "%s\n",
-			wq_dedicated(wq) ? "dedicated" : "shared");
+	return sysfs_emit(buf, "%s\n", wq_dedicated(wq) ? "dedicated" : "shared");
 }
 
 static ssize_t wq_mode_store(struct device *dev,
@@ -951,7 +876,7 @@ static ssize_t wq_size_show(struct device *dev, struct device_attribute *attr,
 {
 	struct idxd_wq *wq = container_of(dev, struct idxd_wq, conf_dev);
 
-	return sprintf(buf, "%u\n", wq->size);
+	return sysfs_emit(buf, "%u\n", wq->size);
 }
 
 static int total_claimed_wq_size(struct idxd_device *idxd)
@@ -960,7 +885,7 @@ static int total_claimed_wq_size(struct idxd_device *idxd)
 	int wq_size = 0;
 
 	for (i = 0; i < idxd->max_wqs; i++) {
-		struct idxd_wq *wq = &idxd->wqs[i];
+		struct idxd_wq *wq = idxd->wqs[i];
 
 		wq_size += wq->size;
 	}
@@ -1002,7 +927,7 @@ static ssize_t wq_priority_show(struct device *dev,
 {
 	struct idxd_wq *wq = container_of(dev, struct idxd_wq, conf_dev);
 
-	return sprintf(buf, "%u\n", wq->priority);
+	return sysfs_emit(buf, "%u\n", wq->priority);
 }
 
 static ssize_t wq_priority_store(struct device *dev,
@@ -1039,8 +964,7 @@ static ssize_t wq_block_on_fault_show(struct device *dev,
 {
 	struct idxd_wq *wq = container_of(dev, struct idxd_wq, conf_dev);
 
-	return sprintf(buf, "%u\n",
-		       test_bit(WQ_FLAG_BLOCK_ON_FAULT, &wq->flags));
+	return sysfs_emit(buf, "%u\n", test_bit(WQ_FLAG_BLOCK_ON_FAULT, &wq->flags));
 }
 
 static ssize_t wq_block_on_fault_store(struct device *dev,
@@ -1079,7 +1003,7 @@ static ssize_t wq_threshold_show(struct device *dev,
 {
 	struct idxd_wq *wq = container_of(dev, struct idxd_wq, conf_dev);
 
-	return sprintf(buf, "%u\n", wq->threshold);
+	return sysfs_emit(buf, "%u\n", wq->threshold);
 }
 
 static ssize_t wq_threshold_store(struct device *dev,
@@ -1122,15 +1046,12 @@ static ssize_t wq_type_show(struct device *dev,
 
 	switch (wq->type) {
 	case IDXD_WQT_KERNEL:
-		return sprintf(buf, "%s\n",
-			       idxd_wq_type_names[IDXD_WQT_KERNEL]);
+		return sysfs_emit(buf, "%s\n", idxd_wq_type_names[IDXD_WQT_KERNEL]);
 	case IDXD_WQT_USER:
-		return sprintf(buf, "%s\n",
-			       idxd_wq_type_names[IDXD_WQT_USER]);
+		return sysfs_emit(buf, "%s\n", idxd_wq_type_names[IDXD_WQT_USER]);
 	case IDXD_WQT_NONE:
 	default:
-		return sprintf(buf, "%s\n",
-			       idxd_wq_type_names[IDXD_WQT_NONE]);
+		return sysfs_emit(buf, "%s\n", idxd_wq_type_names[IDXD_WQT_NONE]);
 	}
 
 	return -EINVAL;
@@ -1171,7 +1092,7 @@ static ssize_t wq_name_show(struct device *dev,
 {
 	struct idxd_wq *wq = container_of(dev, struct idxd_wq, conf_dev);
 
-	return sprintf(buf, "%s\n", wq->name);
+	return sysfs_emit(buf, "%s\n", wq->name);
 }
 
 static ssize_t wq_name_store(struct device *dev,
@@ -1206,8 +1127,16 @@ static ssize_t wq_cdev_minor_show(struct device *dev,
 				  struct device_attribute *attr, char *buf)
 {
 	struct idxd_wq *wq = container_of(dev, struct idxd_wq, conf_dev);
+	int minor = -1;
 
-	return sprintf(buf, "%d\n", wq->idxd_cdev.minor);
+	mutex_lock(&wq->wq_lock);
+	if (wq->idxd_cdev)
+		minor = wq->idxd_cdev->minor;
+	mutex_unlock(&wq->wq_lock);
+
+	if (minor == -1)
+		return -ENXIO;
+	return sysfs_emit(buf, "%d\n", minor);
 }
 
 static struct device_attribute dev_attr_wq_cdev_minor =
@@ -1233,7 +1162,7 @@ static ssize_t wq_max_transfer_size_show(struct device *dev, struct device_attri
 {
 	struct idxd_wq *wq = container_of(dev, struct idxd_wq, conf_dev);
 
-	return sprintf(buf, "%llu\n", wq->max_xfer_bytes);
+	return sysfs_emit(buf, "%llu\n", wq->max_xfer_bytes);
 }
 
 static ssize_t wq_max_transfer_size_store(struct device *dev, struct device_attribute *attr,
@@ -1267,7 +1196,7 @@ static ssize_t wq_max_batch_size_show(struct device *dev, struct device_attribut
 {
 	struct idxd_wq *wq = container_of(dev, struct idxd_wq, conf_dev);
 
-	return sprintf(buf, "%u\n", wq->max_batch_size);
+	return sysfs_emit(buf, "%u\n", wq->max_batch_size);
 }
 
 static ssize_t wq_max_batch_size_store(struct device *dev, struct device_attribute *attr,
@@ -1300,7 +1229,7 @@ static ssize_t wq_ats_disable_show(struct device *dev, struct device_attribute *
 {
 	struct idxd_wq *wq = container_of(dev, struct idxd_wq, conf_dev);
 
-	return sprintf(buf, "%u\n", wq->ats_dis);
+	return sysfs_emit(buf, "%u\n", wq->ats_dis);
 }
 
 static ssize_t wq_ats_disable_store(struct device *dev, struct device_attribute *attr,
@@ -1356,6 +1285,20 @@ static const struct attribute_group *idxd_wq_attribute_groups[] = {
 	NULL,
 };
 
+static void idxd_conf_wq_release(struct device *dev)
+{
+	struct idxd_wq *wq = container_of(dev, struct idxd_wq, conf_dev);
+
+	kfree(wq->wqcfg);
+	kfree(wq);
+}
+
+struct device_type idxd_wq_device_type = {
+	.name = "wq",
+	.release = idxd_conf_wq_release,
+	.groups = idxd_wq_attribute_groups,
+};
+
 /* IDXD device attribs */
 static ssize_t version_show(struct device *dev, struct device_attribute *attr,
 			    char *buf)
@@ -1363,7 +1306,7 @@ static ssize_t version_show(struct device *dev, struct device_attribute *attr,
 	struct idxd_device *idxd =
 		container_of(dev, struct idxd_device, conf_dev);
 
-	return sprintf(buf, "%#x\n", idxd->hw.version);
+	return sysfs_emit(buf, "%#x\n", idxd->hw.version);
 }
 static DEVICE_ATTR_RO(version);
 
@@ -1374,7 +1317,7 @@ static ssize_t max_work_queues_size_show(struct device *dev,
 	struct idxd_device *idxd =
 		container_of(dev, struct idxd_device, conf_dev);
 
-	return sprintf(buf, "%u\n", idxd->max_wq_size);
+	return sysfs_emit(buf, "%u\n", idxd->max_wq_size);
 }
 static DEVICE_ATTR_RO(max_work_queues_size);
 
@@ -1384,7 +1327,7 @@ static ssize_t max_groups_show(struct device *dev,
 	struct idxd_device *idxd =
 		container_of(dev, struct idxd_device, conf_dev);
 
-	return sprintf(buf, "%u\n", idxd->max_groups);
+	return sysfs_emit(buf, "%u\n", idxd->max_groups);
 }
 static DEVICE_ATTR_RO(max_groups);
 
@@ -1394,7 +1337,7 @@ static ssize_t max_work_queues_show(struct device *dev,
 	struct idxd_device *idxd =
 		container_of(dev, struct idxd_device, conf_dev);
 
-	return sprintf(buf, "%u\n", idxd->max_wqs);
+	return sysfs_emit(buf, "%u\n", idxd->max_wqs);
 }
 static DEVICE_ATTR_RO(max_work_queues);
 
@@ -1404,7 +1347,7 @@ static ssize_t max_engines_show(struct device *dev,
 	struct idxd_device *idxd =
 		container_of(dev, struct idxd_device, conf_dev);
 
-	return sprintf(buf, "%u\n", idxd->max_engines);
+	return sysfs_emit(buf, "%u\n", idxd->max_engines);
 }
 static DEVICE_ATTR_RO(max_engines);
 
@@ -1414,7 +1357,7 @@ static ssize_t numa_node_show(struct device *dev,
 	struct idxd_device *idxd =
 		container_of(dev, struct idxd_device, conf_dev);
 
-	return sprintf(buf, "%d\n", dev_to_node(&idxd->pdev->dev));
+	return sysfs_emit(buf, "%d\n", dev_to_node(&idxd->pdev->dev));
 }
 static DEVICE_ATTR_RO(numa_node);
 
@@ -1424,7 +1367,7 @@ static ssize_t max_batch_size_show(struct device *dev,
 	struct idxd_device *idxd =
 		container_of(dev, struct idxd_device, conf_dev);
 
-	return sprintf(buf, "%u\n", idxd->max_batch_size);
+	return sysfs_emit(buf, "%u\n", idxd->max_batch_size);
 }
 static DEVICE_ATTR_RO(max_batch_size);
 
@@ -1435,7 +1378,7 @@ static ssize_t max_transfer_size_show(struct device *dev,
 	struct idxd_device *idxd =
 		container_of(dev, struct idxd_device, conf_dev);
 
-	return sprintf(buf, "%llu\n", idxd->max_xfer_bytes);
+	return sysfs_emit(buf, "%llu\n", idxd->max_xfer_bytes);
 }
 static DEVICE_ATTR_RO(max_transfer_size);
 
@@ -1461,7 +1404,7 @@ static ssize_t gen_cap_show(struct device *dev,
 	struct idxd_device *idxd =
 		container_of(dev, struct idxd_device, conf_dev);
 
-	return sprintf(buf, "%#llx\n", idxd->hw.gen_cap.bits);
+	return sysfs_emit(buf, "%#llx\n", idxd->hw.gen_cap.bits);
 }
 static DEVICE_ATTR_RO(gen_cap);
 
@@ -1471,8 +1414,7 @@ static ssize_t configurable_show(struct device *dev,
 	struct idxd_device *idxd =
 		container_of(dev, struct idxd_device, conf_dev);
 
-	return sprintf(buf, "%u\n",
-			test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags));
+	return sysfs_emit(buf, "%u\n", test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags));
 }
 static DEVICE_ATTR_RO(configurable);
 
@@ -1486,13 +1428,13 @@ static ssize_t clients_show(struct device *dev,
 
 	spin_lock_irqsave(&idxd->dev_lock, flags);
 	for (i = 0; i < idxd->max_wqs; i++) {
-		struct idxd_wq *wq = &idxd->wqs[i];
+		struct idxd_wq *wq = idxd->wqs[i];
 
 		count += wq->client_count;
 	}
 	spin_unlock_irqrestore(&idxd->dev_lock, flags);
 
-	return sprintf(buf, "%d\n", count);
+	return sysfs_emit(buf, "%d\n", count);
 }
 static DEVICE_ATTR_RO(clients);
 
@@ -1502,7 +1444,7 @@ static ssize_t pasid_enabled_show(struct device *dev,
 	struct idxd_device *idxd =
 		container_of(dev, struct idxd_device, conf_dev);
 
-	return sprintf(buf, "%u\n", device_pasid_enabled(idxd));
+	return sysfs_emit(buf, "%u\n", device_pasid_enabled(idxd));
 }
 static DEVICE_ATTR_RO(pasid_enabled);
 
@@ -1515,14 +1457,14 @@ static ssize_t state_show(struct device *dev,
 	switch (idxd->state) {
 	case IDXD_DEV_DISABLED:
 	case IDXD_DEV_CONF_READY:
-		return sprintf(buf, "disabled\n");
+		return sysfs_emit(buf, "disabled\n");
 	case IDXD_DEV_ENABLED:
-		return sprintf(buf, "enabled\n");
+		return sysfs_emit(buf, "enabled\n");
 	case IDXD_DEV_HALTED:
-		return sprintf(buf, "halted\n");
+		return sysfs_emit(buf, "halted\n");
 	}
 
-	return sprintf(buf, "unknown\n");
+	return sysfs_emit(buf, "unknown\n");
 }
 static DEVICE_ATTR_RO(state);
 
@@ -1536,10 +1478,10 @@ static ssize_t errors_show(struct device *dev,
 
 	spin_lock_irqsave(&idxd->dev_lock, flags);
 	for (i = 0; i < 4; i++)
-		out += sprintf(buf + out, "%#018llx ", idxd->sw_err.bits[i]);
+		out += sysfs_emit_at(buf, out, "%#018llx ", idxd->sw_err.bits[i]);
 	spin_unlock_irqrestore(&idxd->dev_lock, flags);
 	out--;
-	out += sprintf(buf + out, "\n");
+	out += sysfs_emit_at(buf, out, "\n");
 	return out;
 }
 static DEVICE_ATTR_RO(errors);
@@ -1550,7 +1492,7 @@ static ssize_t max_tokens_show(struct device *dev,
 	struct idxd_device *idxd =
 		container_of(dev, struct idxd_device, conf_dev);
 
-	return sprintf(buf, "%u\n", idxd->max_tokens);
+	return sysfs_emit(buf, "%u\n", idxd->max_tokens);
 }
 static DEVICE_ATTR_RO(max_tokens);
 
@@ -1560,7 +1502,7 @@ static ssize_t token_limit_show(struct device *dev,
 	struct idxd_device *idxd =
 		container_of(dev, struct idxd_device, conf_dev);
 
-	return sprintf(buf, "%u\n", idxd->token_limit);
+	return sysfs_emit(buf, "%u\n", idxd->token_limit);
 }
 
 static ssize_t token_limit_store(struct device *dev,
@@ -1599,7 +1541,7 @@ static ssize_t cdev_major_show(struct device *dev,
 	struct idxd_device *idxd =
 		container_of(dev, struct idxd_device, conf_dev);
 
-	return sprintf(buf, "%u\n", idxd->major);
+	return sysfs_emit(buf, "%u\n", idxd->major);
 }
 static DEVICE_ATTR_RO(cdev_major);
 
@@ -1608,7 +1550,7 @@ static ssize_t cmd_status_show(struct device *dev,
 {
 	struct idxd_device *idxd = container_of(dev, struct idxd_device, conf_dev);
 
-	return sprintf(buf, "%#x\n", idxd->cmd_status);
+	return sysfs_emit(buf, "%#x\n", idxd->cmd_status);
 }
 static DEVICE_ATTR_RO(cmd_status);
 
@@ -1644,183 +1586,161 @@ static const struct attribute_group *idxd_attribute_groups[] = {
 	NULL,
 };
 
-static int idxd_setup_engine_sysfs(struct idxd_device *idxd)
+static void idxd_conf_device_release(struct device *dev)
 {
-	struct device *dev = &idxd->pdev->dev;
-	int i, rc;
+	struct idxd_device *idxd = container_of(dev, struct idxd_device, conf_dev);
+
+	kfree(idxd->groups);
+	kfree(idxd->wqs);
+	kfree(idxd->engines);
+	kfree(idxd->irq_entries);
+	kfree(idxd->int_handles);
+	ida_free(&idxd_ida, idxd->id);
+	kfree(idxd);
+}
+
+struct device_type dsa_device_type = {
+	.name = "dsa",
+	.release = idxd_conf_device_release,
+	.groups = idxd_attribute_groups,
+};
+
+struct device_type iax_device_type = {
+	.name = "iax",
+	.release = idxd_conf_device_release,
+	.groups = idxd_attribute_groups,
+};
+
+static int idxd_register_engine_devices(struct idxd_device *idxd)
+{
+	int i, j, rc;
 
 	for (i = 0; i < idxd->max_engines; i++) {
-		struct idxd_engine *engine = &idxd->engines[i];
-
-		engine->conf_dev.parent = &idxd->conf_dev;
-		dev_set_name(&engine->conf_dev, "engine%d.%d",
-			     idxd->id, engine->id);
-		engine->conf_dev.bus = idxd_get_bus_type(idxd);
-		engine->conf_dev.groups = idxd_engine_attribute_groups;
-		engine->conf_dev.type = &idxd_engine_device_type;
-		dev_dbg(dev, "Engine device register: %s\n",
-			dev_name(&engine->conf_dev));
-		rc = device_register(&engine->conf_dev);
-		if (rc < 0) {
-			put_device(&engine->conf_dev);
+		struct idxd_engine *engine = idxd->engines[i];
+
+		rc = device_add(&engine->conf_dev);
+		if (rc < 0)
 			goto cleanup;
-		}
 	}
 
 	return 0;
 
 cleanup:
-	while (i--) {
-		struct idxd_engine *engine = &idxd->engines[i];
+	j = i - 1;
+	for (; i < idxd->max_engines; i++)
+		put_device(&idxd->engines[i]->conf_dev);
 
-		device_unregister(&engine->conf_dev);
-	}
+	while (j--)
+		device_unregister(&idxd->engines[j]->conf_dev);
 	return rc;
 }
 
-static int idxd_setup_group_sysfs(struct idxd_device *idxd)
+static int idxd_register_group_devices(struct idxd_device *idxd)
 {
-	struct device *dev = &idxd->pdev->dev;
-	int i, rc;
+	int i, j, rc;
 
 	for (i = 0; i < idxd->max_groups; i++) {
-		struct idxd_group *group = &idxd->groups[i];
-
-		group->conf_dev.parent = &idxd->conf_dev;
-		dev_set_name(&group->conf_dev, "group%d.%d",
-			     idxd->id, group->id);
-		group->conf_dev.bus = idxd_get_bus_type(idxd);
-		group->conf_dev.groups = idxd_group_attribute_groups;
-		group->conf_dev.type = &idxd_group_device_type;
-		dev_dbg(dev, "Group device register: %s\n",
-			dev_name(&group->conf_dev));
-		rc = device_register(&group->conf_dev);
-		if (rc < 0) {
-			put_device(&group->conf_dev);
+		struct idxd_group *group = idxd->groups[i];
+
+		rc = device_add(&group->conf_dev);
+		if (rc < 0)
 			goto cleanup;
-		}
 	}
 
 	return 0;
 
 cleanup:
-	while (i--) {
-		struct idxd_group *group = &idxd->groups[i];
+	j = i - 1;
+	for (; i < idxd->max_groups; i++)
+		put_device(&idxd->groups[i]->conf_dev);
 
-		device_unregister(&group->conf_dev);
-	}
+	while (j--)
+		device_unregister(&idxd->groups[j]->conf_dev);
 	return rc;
 }
 
-static int idxd_setup_wq_sysfs(struct idxd_device *idxd)
+static int idxd_register_wq_devices(struct idxd_device *idxd)
 {
-	struct device *dev = &idxd->pdev->dev;
-	int i, rc;
+	int i, rc, j;
 
 	for (i = 0; i < idxd->max_wqs; i++) {
-		struct idxd_wq *wq = &idxd->wqs[i];
-
-		wq->conf_dev.parent = &idxd->conf_dev;
-		dev_set_name(&wq->conf_dev, "wq%d.%d", idxd->id, wq->id);
-		wq->conf_dev.bus = idxd_get_bus_type(idxd);
-		wq->conf_dev.groups = idxd_wq_attribute_groups;
-		wq->conf_dev.type = &idxd_wq_device_type;
-		dev_dbg(dev, "WQ device register: %s\n",
-			dev_name(&wq->conf_dev));
-		rc = device_register(&wq->conf_dev);
-		if (rc < 0) {
-			put_device(&wq->conf_dev);
+		struct idxd_wq *wq = idxd->wqs[i];
+
+		rc = device_add(&wq->conf_dev);
+		if (rc < 0)
 			goto cleanup;
-		}
 	}
 
 	return 0;
 
 cleanup:
-	while (i--) {
-		struct idxd_wq *wq = &idxd->wqs[i];
+	j = i - 1;
+	for (; i < idxd->max_wqs; i++)
+		put_device(&idxd->wqs[i]->conf_dev);
 
-		device_unregister(&wq->conf_dev);
-	}
+	while (j--)
+		device_unregister(&idxd->wqs[j]->conf_dev);
 	return rc;
 }
 
-static int idxd_setup_device_sysfs(struct idxd_device *idxd)
+int idxd_register_devices(struct idxd_device *idxd)
 {
 	struct device *dev = &idxd->pdev->dev;
-	int rc;
-	char devname[IDXD_NAME_SIZE];
+	int rc, i;
 
-	sprintf(devname, "%s%d", idxd_get_dev_name(idxd), idxd->id);
-	idxd->conf_dev.parent = dev;
-	dev_set_name(&idxd->conf_dev, "%s", devname);
-	idxd->conf_dev.bus = idxd_get_bus_type(idxd);
-	idxd->conf_dev.groups = idxd_attribute_groups;
-	idxd->conf_dev.type = idxd_get_device_type(idxd);
-
-	dev_dbg(dev, "IDXD device register: %s\n", dev_name(&idxd->conf_dev));
-	rc = device_register(&idxd->conf_dev);
-	if (rc < 0) {
-		put_device(&idxd->conf_dev);
-		return rc;
-	}
-
-	return 0;
-}
-
-int idxd_setup_sysfs(struct idxd_device *idxd)
-{
-	struct device *dev = &idxd->pdev->dev;
-	int rc;
-
-	rc = idxd_setup_device_sysfs(idxd);
-	if (rc < 0) {
-		dev_dbg(dev, "Device sysfs registering failed: %d\n", rc);
+	rc = device_add(&idxd->conf_dev);
+	if (rc < 0)
 		return rc;
-	}
 
-	rc = idxd_setup_wq_sysfs(idxd);
+	rc = idxd_register_wq_devices(idxd);
 	if (rc < 0) {
-		/* unregister conf dev */
-		dev_dbg(dev, "Work Queue sysfs registering failed: %d\n", rc);
-		return rc;
+		dev_dbg(dev, "WQ devices registering failed: %d\n", rc);
+		goto err_wq;
 	}
 
-	rc = idxd_setup_group_sysfs(idxd);
+	rc = idxd_register_engine_devices(idxd);
 	if (rc < 0) {
-		/* unregister conf dev */
-		dev_dbg(dev, "Group sysfs registering failed: %d\n", rc);
-		return rc;
+		dev_dbg(dev, "Engine devices registering failed: %d\n", rc);
+		goto err_engine;
 	}
 
-	rc = idxd_setup_engine_sysfs(idxd);
+	rc = idxd_register_group_devices(idxd);
 	if (rc < 0) {
-		/* unregister conf dev */
-		dev_dbg(dev, "Engine sysfs registering failed: %d\n", rc);
-		return rc;
+		dev_dbg(dev, "Group device registering failed: %d\n", rc);
+		goto err_group;
 	}
 
 	return 0;
+
+ err_group:
+	for (i = 0; i < idxd->max_engines; i++)
+		device_unregister(&idxd->engines[i]->conf_dev);
+ err_engine:
+	for (i = 0; i < idxd->max_wqs; i++)
+		device_unregister(&idxd->wqs[i]->conf_dev);
+ err_wq:
+	device_del(&idxd->conf_dev);
+	return rc;
 }
 
-void idxd_cleanup_sysfs(struct idxd_device *idxd)
+void idxd_unregister_devices(struct idxd_device *idxd)
 {
 	int i;
 
 	for (i = 0; i < idxd->max_wqs; i++) {
-		struct idxd_wq *wq = &idxd->wqs[i];
+		struct idxd_wq *wq = idxd->wqs[i];
 
 		device_unregister(&wq->conf_dev);
 	}
 
 	for (i = 0; i < idxd->max_engines; i++) {
-		struct idxd_engine *engine = &idxd->engines[i];
+		struct idxd_engine *engine = idxd->engines[i];
 
 		device_unregister(&engine->conf_dev);
 	}
 
 	for (i = 0; i < idxd->max_groups; i++) {
-		struct idxd_group *group = &idxd->groups[i];
+		struct idxd_group *group = idxd->groups[i];
 
 		device_unregister(&group->conf_dev);
 	}
@@ -1830,26 +1750,10 @@ void idxd_cleanup_sysfs(struct idxd_device *idxd)
 
 int idxd_register_bus_type(void)
 {
-	int i, rc;
-
-	for (i = 0; i < IDXD_TYPE_MAX; i++) {
-		rc = bus_register(idxd_bus_types[i]);
-		if (rc < 0)
-			goto bus_err;
-	}
-
-	return 0;
-
-bus_err:
-	while (--i >= 0)
-		bus_unregister(idxd_bus_types[i]);
-	return rc;
+	return bus_register(&dsa_bus_type);
 }
 
 void idxd_unregister_bus_type(void)
 {
-	int i;
-
-	for (i = 0; i < IDXD_TYPE_MAX; i++)
-		bus_unregister(idxd_bus_types[i]);
+	bus_unregister(&dsa_bus_type);
 }
diff --git a/drivers/dma/k3dma.c b/drivers/dma/k3dma.c
index d0b2e601e3e5..ecdaada95120 100644
--- a/drivers/dma/k3dma.c
+++ b/drivers/dma/k3dma.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (c) 2013 - 2015 Linaro Ltd.
- * Copyright (c) 2013 Hisilicon Limited.
+ * Copyright (c) 2013 HiSilicon Limited.
  */
 #include <linux/sched.h>
 #include <linux/device.h>
@@ -1039,6 +1039,6 @@ static struct platform_driver k3_pdma_driver = {
 
 module_platform_driver(k3_pdma_driver);
 
-MODULE_DESCRIPTION("Hisilicon k3 DMA Driver");
+MODULE_DESCRIPTION("HiSilicon k3 DMA Driver");
 MODULE_ALIAS("platform:k3dma");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/dma/qcom/gpi.c b/drivers/dma/qcom/gpi.c
index 57f5ee4235c7..43ac3ab23d4c 100644
--- a/drivers/dma/qcom/gpi.c
+++ b/drivers/dma/qcom/gpi.c
@@ -2281,6 +2281,7 @@ static int gpi_probe(struct platform_device *pdev)
 
 static const struct of_device_id gpi_of_match[] = {
 	{ .compatible = "qcom,sdm845-gpi-dma" },
+	{ .compatible = "qcom,sm8150-gpi-dma" },
 	{ },
 };
 MODULE_DEVICE_TABLE(of, gpi_of_match);
diff --git a/drivers/dma/qcom/hidma.c b/drivers/dma/qcom/hidma.c
index 6c0f9eb8ecc6..23d64489d25f 100644
--- a/drivers/dma/qcom/hidma.c
+++ b/drivers/dma/qcom/hidma.c
@@ -90,12 +90,6 @@ static inline struct hidma_chan *to_hidma_chan(struct dma_chan *dmach)
 	return container_of(dmach, struct hidma_chan, chan);
 }
 
-static inline
-struct hidma_desc *to_hidma_desc(struct dma_async_tx_descriptor *t)
-{
-	return container_of(t, struct hidma_desc, desc);
-}
-
 static void hidma_free(struct hidma_dev *dmadev)
 {
 	INIT_LIST_HEAD(&dmadev->ddev.channels);
diff --git a/drivers/dma/xilinx/xilinx_dma.c b/drivers/dma/xilinx/xilinx_dma.c
index 3aded7861fef..75c0b8e904e5 100644
--- a/drivers/dma/xilinx/xilinx_dma.c
+++ b/drivers/dma/xilinx/xilinx_dma.c
@@ -2453,6 +2453,13 @@ static int xilinx_dma_terminate_all(struct dma_chan *dchan)
 	return 0;
 }
 
+static void xilinx_dma_synchronize(struct dma_chan *dchan)
+{
+	struct xilinx_dma_chan *chan = to_xilinx_chan(dchan);
+
+	tasklet_kill(&chan->tasklet);
+}
+
 /**
  * xilinx_dma_channel_set_config - Configure VDMA channel
  * Run-time configuration for Axi VDMA, supports:
@@ -3074,6 +3081,7 @@ static int xilinx_dma_probe(struct platform_device *pdev)
 	xdev->common.device_free_chan_resources =
 				xilinx_dma_free_chan_resources;
 	xdev->common.device_terminate_all = xilinx_dma_terminate_all;
+	xdev->common.device_synchronize = xilinx_dma_synchronize;
 	xdev->common.device_tx_status = xilinx_dma_tx_status;
 	xdev->common.device_issue_pending = xilinx_dma_issue_pending;
 	if (xdev->dma_config->dmatype == XDMA_TYPE_AXIDMA) {