Resguardo inicial

linux-7.2.3/drivers/dma/amd/ptdma/Makefile

@@ -0,0 +1,10 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# AMD Passthru DMA driver
+#
+
+obj-$(CONFIG_AMD_PTDMA) += ptdma.o
+
+ptdma-objs := ptdma-dev.o ptdma-dmaengine.o ptdma-debugfs.o
+
+ptdma-$(CONFIG_PCI) += ptdma-pci.o

linux-7.2.3/drivers/dma/amd/ptdma/ptdma-debugfs.c

@@ -0,0 +1,143 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * AMD Passthrough DMA device driver
+ * -- Based on the CCP driver
+ *
+ * Copyright (C) 2016,2021 Advanced Micro Devices, Inc.
+ *
+ * Author: Sanjay R Mehta <sanju.mehta@amd.com>
+ * Author: Gary R Hook <gary.hook@amd.com>
+ */
+
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+
+#include "ptdma.h"
+#include "../ae4dma/ae4dma.h"
+
+/* DebugFS helpers */
+#define	RI_VERSION_NUM	0x0000003F
+
+#define	RI_NUM_VQM	0x00078000
+#define	RI_NVQM_SHIFT	15
+
+static int pt_debugfs_info_show(struct seq_file *s, void *p)
+{
+	struct pt_device *pt = s->private;
+	struct ae4_device *ae4;
+	unsigned int regval;
+
+	seq_printf(s, "Device name: %s\n", dev_name(pt->dev));
+
+	if (pt->ver == AE4_DMA_VERSION) {
+		ae4 = container_of(pt, struct ae4_device, pt);
+		seq_printf(s, "   # Queues: %d\n", ae4->cmd_q_count);
+		seq_printf(s, "     # Cmds per queue: %d\n", CMD_Q_LEN);
+	} else {
+		seq_printf(s, "   # Queues: %d\n", 1);
+		seq_printf(s, "     # Cmds: %d\n", pt->cmd_count);
+	}
+
+	regval = ioread32(pt->io_regs + CMD_PT_VERSION);
+
+	seq_printf(s, "    Version: %d\n", regval & RI_VERSION_NUM);
+	seq_puts(s, "    Engines:");
+	seq_puts(s, "\n");
+	seq_printf(s, "     Queues: %d\n", (regval & RI_NUM_VQM) >> RI_NVQM_SHIFT);
+
+	return 0;
+}
+
+/*
+ * Return a formatted buffer containing the current
+ * statistics of queue for PTDMA
+ */
+static int pt_debugfs_stats_show(struct seq_file *s, void *p)
+{
+	struct pt_device *pt = s->private;
+
+	seq_printf(s, "Total Interrupts Handled: %ld\n", pt->total_interrupts);
+
+	return 0;
+}
+
+static int pt_debugfs_queue_show(struct seq_file *s, void *p)
+{
+	struct pt_cmd_queue *cmd_q = s->private;
+	struct pt_device *pt;
+	unsigned int regval;
+
+	if (!cmd_q)
+		return 0;
+
+	seq_printf(s, "               Pass-Thru: %ld\n", cmd_q->total_pt_ops);
+
+	pt = cmd_q->pt;
+	if (pt->ver == AE4_DMA_VERSION) {
+		regval = readl(cmd_q->reg_control + 0x4);
+		seq_printf(s, "     Enabled Interrupts:: status 0x%x\n", regval);
+	} else {
+		regval = ioread32(cmd_q->reg_control + 0x000C);
+
+		seq_puts(s, "      Enabled Interrupts:");
+		if (regval & INT_EMPTY_QUEUE)
+			seq_puts(s, " EMPTY");
+		if (regval & INT_QUEUE_STOPPED)
+			seq_puts(s, " STOPPED");
+		if (regval & INT_ERROR)
+			seq_puts(s, " ERROR");
+		if (regval & INT_COMPLETION)
+			seq_puts(s, " COMPLETION");
+		seq_puts(s, "\n");
+	}
+
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(pt_debugfs_info);
+DEFINE_SHOW_ATTRIBUTE(pt_debugfs_queue);
+DEFINE_SHOW_ATTRIBUTE(pt_debugfs_stats);
+
+void ptdma_debugfs_setup(struct pt_device *pt)
+{
+	struct dentry *debugfs_q_instance;
+	struct ae4_cmd_queue *ae4cmd_q;
+	struct pt_cmd_queue *cmd_q;
+	struct ae4_device *ae4;
+	char name[30];
+	int i;
+
+	if (!debugfs_initialized())
+		return;
+
+	debugfs_create_file("info", 0400, pt->dma_dev.dbg_dev_root, pt,
+			    &pt_debugfs_info_fops);
+
+	debugfs_create_file("stats", 0400, pt->dma_dev.dbg_dev_root, pt,
+			    &pt_debugfs_stats_fops);
+
+
+	if (pt->ver == AE4_DMA_VERSION) {
+		ae4 = container_of(pt, struct ae4_device, pt);
+		for (i = 0; i < ae4->cmd_q_count; i++) {
+			ae4cmd_q = &ae4->ae4cmd_q[i];
+			cmd_q = &ae4cmd_q->cmd_q;
+
+			memset(name, 0, sizeof(name));
+			snprintf(name, 29, "q%d", ae4cmd_q->id);
+
+			debugfs_q_instance =
+				debugfs_create_dir(name, pt->dma_dev.dbg_dev_root);
+
+			debugfs_create_file("stats", 0400, debugfs_q_instance, cmd_q,
+					    &pt_debugfs_queue_fops);
+		}
+	} else {
+		debugfs_q_instance =
+			debugfs_create_dir("q", pt->dma_dev.dbg_dev_root);
+		cmd_q = &pt->cmd_q;
+		debugfs_create_file("stats", 0400, debugfs_q_instance, cmd_q,
+				    &pt_debugfs_queue_fops);
+	}
+}
+EXPORT_SYMBOL_GPL(ptdma_debugfs_setup);

linux-7.2.3/drivers/dma/amd/ptdma/ptdma-dev.c

@@ -0,0 +1,309 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * AMD Passthru DMA device driver
+ * -- Based on the CCP driver
+ *
+ * Copyright (C) 2016,2021 Advanced Micro Devices, Inc.
+ *
+ * Author: Sanjay R Mehta <sanju.mehta@amd.com>
+ * Author: Gary R Hook <gary.hook@amd.com>
+ */
+
+#include <linux/bitfield.h>
+#include <linux/dma-mapping.h>
+#include <linux/debugfs.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+
+#include "ptdma.h"
+
+/* Human-readable error strings */
+static char *pt_error_codes[] = {
+	"",
+	"ERR 01: ILLEGAL_ENGINE",
+	"ERR 03: ILLEGAL_FUNCTION_TYPE",
+	"ERR 04: ILLEGAL_FUNCTION_MODE",
+	"ERR 06: ILLEGAL_FUNCTION_SIZE",
+	"ERR 08: ILLEGAL_FUNCTION_RSVD",
+	"ERR 09: ILLEGAL_BUFFER_LENGTH",
+	"ERR 10: VLSB_FAULT",
+	"ERR 11: ILLEGAL_MEM_ADDR",
+	"ERR 12: ILLEGAL_MEM_SEL",
+	"ERR 13: ILLEGAL_CONTEXT_ID",
+	"ERR 15: 0xF Reserved",
+	"ERR 18: CMD_TIMEOUT",
+	"ERR 19: IDMA0_AXI_SLVERR",
+	"ERR 20: IDMA0_AXI_DECERR",
+	"ERR 21: 0x15 Reserved",
+	"ERR 22: IDMA1_AXI_SLAVE_FAULT",
+	"ERR 23: IDMA1_AIXI_DECERR",
+	"ERR 24: 0x18 Reserved",
+	"ERR 27: 0x1B Reserved",
+	"ERR 38: ODMA0_AXI_SLVERR",
+	"ERR 39: ODMA0_AXI_DECERR",
+	"ERR 40: 0x28 Reserved",
+	"ERR 41: ODMA1_AXI_SLVERR",
+	"ERR 42: ODMA1_AXI_DECERR",
+	"ERR 43: LSB_PARITY_ERR",
+};
+
+static void pt_log_error(struct pt_device *d, int e)
+{
+	dev_err(d->dev, "PTDMA error: %s (0x%x)\n", pt_error_codes[e], e);
+}
+
+void pt_start_queue(struct pt_cmd_queue *cmd_q)
+{
+	/* Turn on the run bit */
+	iowrite32(cmd_q->qcontrol | CMD_Q_RUN, cmd_q->reg_control);
+}
+
+void pt_stop_queue(struct pt_cmd_queue *cmd_q)
+{
+	/* Turn off the run bit */
+	iowrite32(cmd_q->qcontrol & ~CMD_Q_RUN, cmd_q->reg_control);
+}
+
+static int pt_core_execute_cmd(struct ptdma_desc *desc, struct pt_cmd_queue *cmd_q)
+{
+	bool soc = FIELD_GET(DWORD0_SOC, desc->dw0);
+	u8 *q_desc = (u8 *)&cmd_q->qbase[cmd_q->qidx];
+	u32 tail;
+	unsigned long flags;
+
+	if (soc) {
+		desc->dw0 |= FIELD_PREP(DWORD0_IOC, desc->dw0);
+		desc->dw0 &= ~DWORD0_SOC;
+	}
+	spin_lock_irqsave(&cmd_q->q_lock, flags);
+
+	/* Copy 32-byte command descriptor to hw queue. */
+	memcpy(q_desc, desc, 32);
+	cmd_q->qidx = (cmd_q->qidx + 1) % CMD_Q_LEN;
+
+	/* The data used by this command must be flushed to memory */
+	wmb();
+
+	/* Write the new tail address back to the queue register */
+	tail = lower_32_bits(cmd_q->qdma_tail + cmd_q->qidx * Q_DESC_SIZE);
+	iowrite32(tail, cmd_q->reg_control + 0x0004);
+
+	/* Turn the queue back on using our cached control register */
+	pt_start_queue(cmd_q);
+	spin_unlock_irqrestore(&cmd_q->q_lock, flags);
+
+	return 0;
+}
+
+int pt_core_perform_passthru(struct pt_cmd_queue *cmd_q,
+			     struct pt_passthru_engine *pt_engine)
+{
+	struct ptdma_desc desc;
+	struct pt_device *pt = container_of(cmd_q, struct pt_device, cmd_q);
+
+	cmd_q->cmd_error = 0;
+	cmd_q->total_pt_ops++;
+	memset(&desc, 0, sizeof(desc));
+	desc.dw0 = CMD_DESC_DW0_VAL;
+	desc.length = pt_engine->src_len;
+	desc.src_lo = lower_32_bits(pt_engine->src_dma);
+	desc.dw3.src_hi = upper_32_bits(pt_engine->src_dma);
+	desc.dst_lo = lower_32_bits(pt_engine->dst_dma);
+	desc.dw5.dst_hi = upper_32_bits(pt_engine->dst_dma);
+
+	if (cmd_q->int_en)
+		pt_core_enable_queue_interrupts(pt);
+	else
+		pt_core_disable_queue_interrupts(pt);
+
+	return pt_core_execute_cmd(&desc, cmd_q);
+}
+
+static void pt_do_cmd_complete(unsigned long data)
+{
+	struct pt_tasklet_data *tdata = (struct pt_tasklet_data *)data;
+	struct pt_cmd *cmd = tdata->cmd;
+	struct pt_cmd_queue *cmd_q = &cmd->pt->cmd_q;
+	u32 tail;
+
+	if (cmd_q->cmd_error) {
+	       /*
+		* Log the error and flush the queue by
+		* moving the head pointer
+		*/
+		tail = lower_32_bits(cmd_q->qdma_tail + cmd_q->qidx * Q_DESC_SIZE);
+		pt_log_error(cmd_q->pt, cmd_q->cmd_error);
+		iowrite32(tail, cmd_q->reg_control + 0x0008);
+	}
+
+	cmd->pt_cmd_callback(cmd->data, cmd->ret);
+}
+
+void pt_check_status_trans(struct pt_device *pt, struct pt_cmd_queue *cmd_q)
+{
+	u32 status;
+
+	status = ioread32(cmd_q->reg_control + 0x0010);
+	if (status) {
+		cmd_q->int_status = status;
+		cmd_q->q_status = ioread32(cmd_q->reg_control + 0x0100);
+		cmd_q->q_int_status = ioread32(cmd_q->reg_control + 0x0104);
+
+		/* On error, only save the first error value */
+		if ((status & INT_ERROR) && !cmd_q->cmd_error)
+			cmd_q->cmd_error = CMD_Q_ERROR(cmd_q->q_status);
+
+		/* Acknowledge the completion */
+		iowrite32(status, cmd_q->reg_control + 0x0010);
+		pt_do_cmd_complete((ulong)&pt->tdata);
+	}
+}
+
+static irqreturn_t pt_core_irq_handler(int irq, void *data)
+{
+	struct pt_device *pt = data;
+	struct pt_cmd_queue *cmd_q = &pt->cmd_q;
+
+	pt_core_disable_queue_interrupts(pt);
+	pt->total_interrupts++;
+	pt_check_status_trans(pt, cmd_q);
+	pt_core_enable_queue_interrupts(pt);
+	return IRQ_HANDLED;
+}
+
+int pt_core_init(struct pt_device *pt)
+{
+	char dma_pool_name[MAX_DMAPOOL_NAME_LEN];
+	struct pt_cmd_queue *cmd_q = &pt->cmd_q;
+	u32 dma_addr_lo, dma_addr_hi;
+	struct device *dev = pt->dev;
+	struct dma_pool *dma_pool;
+	int ret;
+
+	/* Allocate a dma pool for the queue */
+	snprintf(dma_pool_name, sizeof(dma_pool_name), "%s_q", dev_name(pt->dev));
+
+	dma_pool = dma_pool_create(dma_pool_name, dev,
+				   PT_DMAPOOL_MAX_SIZE,
+				   PT_DMAPOOL_ALIGN, 0);
+	if (!dma_pool)
+		return -ENOMEM;
+
+	/* ptdma core initialisation */
+	iowrite32(CMD_CONFIG_VHB_EN, pt->io_regs + CMD_CONFIG_OFFSET);
+	iowrite32(CMD_QUEUE_PRIO, pt->io_regs + CMD_QUEUE_PRIO_OFFSET);
+	iowrite32(CMD_TIMEOUT_DISABLE, pt->io_regs + CMD_TIMEOUT_OFFSET);
+	iowrite32(CMD_CLK_GATE_CONFIG, pt->io_regs + CMD_CLK_GATE_CTL_OFFSET);
+	iowrite32(CMD_CONFIG_REQID, pt->io_regs + CMD_REQID_CONFIG_OFFSET);
+
+	cmd_q->pt = pt;
+	cmd_q->dma_pool = dma_pool;
+	spin_lock_init(&cmd_q->q_lock);
+
+	/* Page alignment satisfies our needs for N <= 128 */
+	cmd_q->qsize = Q_SIZE(Q_DESC_SIZE);
+	cmd_q->qbase = dma_alloc_coherent(dev, cmd_q->qsize,
+					  &cmd_q->qbase_dma,
+					  GFP_KERNEL);
+	if (!cmd_q->qbase) {
+		dev_err(dev, "unable to allocate command queue\n");
+		ret = -ENOMEM;
+		goto e_destroy_pool;
+	}
+
+	cmd_q->qidx = 0;
+
+	/* Preset some register values */
+	cmd_q->reg_control = pt->io_regs + CMD_Q_STATUS_INCR;
+
+	/* Turn off the queues and disable interrupts until ready */
+	pt_core_disable_queue_interrupts(pt);
+
+	cmd_q->qcontrol = 0; /* Start with nothing */
+	iowrite32(cmd_q->qcontrol, cmd_q->reg_control);
+
+	ioread32(cmd_q->reg_control + 0x0104);
+	ioread32(cmd_q->reg_control + 0x0100);
+
+	/* Clear the interrupt status */
+	iowrite32(SUPPORTED_INTERRUPTS, cmd_q->reg_control + 0x0010);
+
+	/* Request an irq */
+	ret = request_irq(pt->pt_irq, pt_core_irq_handler, 0, dev_name(pt->dev), pt);
+	if (ret) {
+		dev_err(dev, "unable to allocate an IRQ\n");
+		goto e_free_dma;
+	}
+
+	/* Update the device registers with queue information. */
+	cmd_q->qcontrol &= ~CMD_Q_SIZE;
+	cmd_q->qcontrol |= FIELD_PREP(CMD_Q_SIZE, QUEUE_SIZE_VAL);
+
+	cmd_q->qdma_tail = cmd_q->qbase_dma;
+	dma_addr_lo = lower_32_bits(cmd_q->qdma_tail);
+	iowrite32((u32)dma_addr_lo, cmd_q->reg_control + 0x0004);
+	iowrite32((u32)dma_addr_lo, cmd_q->reg_control + 0x0008);
+
+	dma_addr_hi = upper_32_bits(cmd_q->qdma_tail);
+	cmd_q->qcontrol |= (dma_addr_hi << 16);
+	iowrite32(cmd_q->qcontrol, cmd_q->reg_control);
+
+	pt_core_enable_queue_interrupts(pt);
+
+	/* Register the DMA engine support */
+	ret = pt_dmaengine_register(pt);
+	if (ret)
+		goto e_free_irq;
+
+	/* Set up debugfs entries */
+	ptdma_debugfs_setup(pt);
+
+	return 0;
+
+e_free_irq:
+	free_irq(pt->pt_irq, pt);
+
+e_free_dma:
+	dma_free_coherent(dev, cmd_q->qsize, cmd_q->qbase, cmd_q->qbase_dma);
+
+e_destroy_pool:
+	dma_pool_destroy(pt->cmd_q.dma_pool);
+
+	return ret;
+}
+
+void pt_core_destroy(struct pt_device *pt)
+{
+	struct device *dev = pt->dev;
+	struct pt_cmd_queue *cmd_q = &pt->cmd_q;
+	struct pt_cmd *cmd;
+
+	/* Unregister the DMA engine */
+	pt_dmaengine_unregister(pt);
+
+	/* Disable and clear interrupts */
+	pt_core_disable_queue_interrupts(pt);
+
+	/* Turn off the run bit */
+	pt_stop_queue(cmd_q);
+
+	/* Clear the interrupt status */
+	iowrite32(SUPPORTED_INTERRUPTS, cmd_q->reg_control + 0x0010);
+	ioread32(cmd_q->reg_control + 0x0104);
+	ioread32(cmd_q->reg_control + 0x0100);
+
+	free_irq(pt->pt_irq, pt);
+
+	dma_free_coherent(dev, cmd_q->qsize, cmd_q->qbase,
+			  cmd_q->qbase_dma);
+
+	/* Flush the cmd queue */
+	while (!list_empty(&pt->cmd)) {
+		/* Invoke the callback directly with an error code */
+		cmd = list_first_entry(&pt->cmd, struct pt_cmd, entry);
+		list_del(&cmd->entry);
+		cmd->pt_cmd_callback(cmd->data, -ENODEV);
+	}
+}

linux-7.2.3/drivers/dma/amd/ptdma/ptdma-dmaengine.c

@@ -0,0 +1,659 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * AMD Passthrough DMA device driver
+ * -- Based on the CCP driver
+ *
+ * Copyright (C) 2016,2021 Advanced Micro Devices, Inc.
+ *
+ * Author: Sanjay R Mehta <sanju.mehta@amd.com>
+ * Author: Gary R Hook <gary.hook@amd.com>
+ */
+
+#include <linux/bitfield.h>
+#include "ptdma.h"
+#include "../ae4dma/ae4dma.h"
+#include "../../dmaengine.h"
+
+static char *ae4_error_codes[] = {
+	"",
+	"ERR 01: INVALID HEADER DW0",
+	"ERR 02: INVALID STATUS",
+	"ERR 03: INVALID LENGTH - 4 BYTE ALIGNMENT",
+	"ERR 04: INVALID SRC ADDR - 4 BYTE ALIGNMENT",
+	"ERR 05: INVALID DST ADDR - 4 BYTE ALIGNMENT",
+	"ERR 06: INVALID ALIGNMENT",
+	"ERR 07: INVALID DESCRIPTOR",
+};
+
+static void ae4_log_error(struct pt_device *d, int e)
+{
+	/* ERR 01 - 07 represents Invalid AE4 errors */
+	if (e <= 7)
+		dev_info(d->dev, "AE4DMA error: %s (0x%x)\n", ae4_error_codes[e], e);
+	/* ERR 08 - 15 represents Invalid Descriptor errors */
+	else if (e > 7 && e <= 15)
+		dev_info(d->dev, "AE4DMA error: %s (0x%x)\n", "INVALID DESCRIPTOR", e);
+	/* ERR 16 - 31 represents Firmware errors */
+	else if (e > 15 && e <= 31)
+		dev_info(d->dev, "AE4DMA error: %s (0x%x)\n", "FIRMWARE ERROR", e);
+	/* ERR 32 - 63 represents Fatal errors */
+	else if (e > 31 && e <= 63)
+		dev_info(d->dev, "AE4DMA error: %s (0x%x)\n", "FATAL ERROR", e);
+	/* ERR 64 - 255 represents PTE errors */
+	else if (e > 63 && e <= 255)
+		dev_info(d->dev, "AE4DMA error: %s (0x%x)\n", "PTE ERROR", e);
+	else
+		dev_info(d->dev, "Unknown AE4DMA error");
+}
+
+void ae4_check_status_error(struct ae4_cmd_queue *ae4cmd_q, int idx)
+{
+	struct pt_cmd_queue *cmd_q = &ae4cmd_q->cmd_q;
+	struct ae4dma_desc desc;
+	u8 status;
+
+	memcpy(&desc, &cmd_q->qbase[idx], sizeof(struct ae4dma_desc));
+	status = desc.dw1.status;
+	if (status && status != AE4_DESC_COMPLETED) {
+		cmd_q->cmd_error = desc.dw1.err_code;
+		if (cmd_q->cmd_error)
+			ae4_log_error(cmd_q->pt, cmd_q->cmd_error);
+	}
+}
+EXPORT_SYMBOL_GPL(ae4_check_status_error);
+
+static inline struct pt_dma_chan *to_pt_chan(struct dma_chan *dma_chan)
+{
+	return container_of(dma_chan, struct pt_dma_chan, vc.chan);
+}
+
+static inline struct pt_dma_desc *to_pt_desc(struct virt_dma_desc *vd)
+{
+	return container_of(vd, struct pt_dma_desc, vd);
+}
+
+static void pt_free_chan_resources(struct dma_chan *dma_chan)
+{
+	struct pt_dma_chan *chan = to_pt_chan(dma_chan);
+
+	vchan_free_chan_resources(&chan->vc);
+}
+
+static void pt_synchronize(struct dma_chan *dma_chan)
+{
+	struct pt_dma_chan *chan = to_pt_chan(dma_chan);
+
+	vchan_synchronize(&chan->vc);
+}
+
+static void pt_do_cleanup(struct virt_dma_desc *vd)
+{
+	struct pt_dma_desc *desc = to_pt_desc(vd);
+	struct pt_device *pt = desc->pt;
+
+	kmem_cache_free(pt->dma_desc_cache, desc);
+}
+
+static struct pt_cmd_queue *pt_get_cmd_queue(struct pt_device *pt, struct pt_dma_chan *chan)
+{
+	struct ae4_cmd_queue *ae4cmd_q;
+	struct pt_cmd_queue *cmd_q;
+	struct ae4_device *ae4;
+
+	if (pt->ver == AE4_DMA_VERSION) {
+		ae4 = container_of(pt, struct ae4_device, pt);
+		ae4cmd_q = &ae4->ae4cmd_q[chan->id];
+		cmd_q = &ae4cmd_q->cmd_q;
+	} else {
+		cmd_q = &pt->cmd_q;
+	}
+
+	return cmd_q;
+}
+
+static int ae4_core_execute_cmd(struct ae4dma_desc *desc, struct ae4_cmd_queue *ae4cmd_q)
+{
+	bool soc = FIELD_GET(DWORD0_SOC, desc->dwouv.dw0);
+	struct pt_cmd_queue *cmd_q = &ae4cmd_q->cmd_q;
+
+	if (soc) {
+		desc->dwouv.dw0 |= FIELD_PREP(DWORD0_IOC, desc->dwouv.dw0);
+		desc->dwouv.dw0 &= ~DWORD0_SOC;
+	}
+
+	mutex_lock(&ae4cmd_q->cmd_lock);
+	memcpy(&cmd_q->qbase[ae4cmd_q->tail_wi], desc, sizeof(struct ae4dma_desc));
+	ae4cmd_q->q_cmd_count++;
+	ae4cmd_q->tail_wi = (ae4cmd_q->tail_wi + 1) % CMD_Q_LEN;
+	writel(ae4cmd_q->tail_wi, cmd_q->reg_control + AE4_WR_IDX_OFF);
+	mutex_unlock(&ae4cmd_q->cmd_lock);
+
+	wake_up(&ae4cmd_q->q_w);
+
+	return 0;
+}
+
+static int pt_core_perform_passthru_ae4(struct pt_cmd_queue *cmd_q,
+					struct pt_passthru_engine *pt_engine)
+{
+	struct ae4_cmd_queue *ae4cmd_q = container_of(cmd_q, struct ae4_cmd_queue, cmd_q);
+	struct ae4dma_desc desc;
+
+	cmd_q->cmd_error = 0;
+	cmd_q->total_pt_ops++;
+	memset(&desc, 0, sizeof(desc));
+	desc.dwouv.dws.byte0 = CMD_AE4_DESC_DW0_VAL;
+
+	desc.dw1.status = 0;
+	desc.dw1.err_code = 0;
+	desc.dw1.desc_id = 0;
+
+	desc.length = pt_engine->src_len;
+
+	desc.src_lo = upper_32_bits(pt_engine->src_dma);
+	desc.src_hi = lower_32_bits(pt_engine->src_dma);
+	desc.dst_lo = upper_32_bits(pt_engine->dst_dma);
+	desc.dst_hi = lower_32_bits(pt_engine->dst_dma);
+
+	return ae4_core_execute_cmd(&desc, ae4cmd_q);
+}
+
+static int pt_dma_start_desc(struct pt_dma_desc *desc, struct pt_dma_chan *chan)
+{
+	struct pt_passthru_engine *pt_engine;
+	struct pt_device *pt;
+	struct pt_cmd *pt_cmd;
+	struct pt_cmd_queue *cmd_q;
+
+	desc->issued_to_hw = 1;
+
+	pt_cmd = &desc->pt_cmd;
+	pt = pt_cmd->pt;
+
+	cmd_q = pt_get_cmd_queue(pt, chan);
+
+	pt_engine = &pt_cmd->passthru;
+
+	pt->tdata.cmd = pt_cmd;
+
+	/* Execute the command */
+	if (pt->ver == AE4_DMA_VERSION)
+		pt_cmd->ret = pt_core_perform_passthru_ae4(cmd_q, pt_engine);
+	else
+		pt_cmd->ret = pt_core_perform_passthru(cmd_q, pt_engine);
+
+	return 0;
+}
+
+static struct pt_dma_desc *pt_next_dma_desc(struct pt_dma_chan *chan)
+{
+	/* Get the next DMA descriptor on the active list */
+	struct virt_dma_desc *vd = vchan_next_desc(&chan->vc);
+
+	return vd ? to_pt_desc(vd) : NULL;
+}
+
+static struct pt_dma_desc *pt_handle_active_desc(struct pt_dma_chan *chan,
+						 struct pt_dma_desc *desc)
+{
+	struct dma_async_tx_descriptor *tx_desc;
+	struct virt_dma_desc *vd;
+	struct pt_device *pt;
+	unsigned long flags;
+
+	pt = chan->pt;
+	/* Loop over descriptors until one is found with commands */
+	do {
+		if (desc) {
+			if (!desc->issued_to_hw) {
+				/* No errors, keep going */
+				if (desc->status != DMA_ERROR)
+					return desc;
+			}
+
+			tx_desc = &desc->vd.tx;
+			vd = &desc->vd;
+		} else {
+			tx_desc = NULL;
+		}
+
+		spin_lock_irqsave(&chan->vc.lock, flags);
+
+		if (pt->ver != AE4_DMA_VERSION && desc) {
+			if (desc->status != DMA_COMPLETE) {
+				if (desc->status != DMA_ERROR)
+					desc->status = DMA_COMPLETE;
+
+				dma_cookie_complete(tx_desc);
+				dma_descriptor_unmap(tx_desc);
+				list_del(&desc->vd.node);
+			} else {
+				/* Don't handle it twice */
+				tx_desc = NULL;
+			}
+		}
+
+		desc = pt_next_dma_desc(chan);
+
+		spin_unlock_irqrestore(&chan->vc.lock, flags);
+
+		if (pt->ver != AE4_DMA_VERSION && tx_desc) {
+			dmaengine_desc_get_callback_invoke(tx_desc, NULL);
+			dma_run_dependencies(tx_desc);
+			vchan_vdesc_fini(vd);
+		}
+	} while (desc);
+
+	return NULL;
+}
+
+static inline bool ae4_core_queue_full(struct pt_cmd_queue *cmd_q)
+{
+	u32 front_wi = readl(cmd_q->reg_control + AE4_WR_IDX_OFF);
+	u32 rear_ri = readl(cmd_q->reg_control + AE4_RD_IDX_OFF);
+
+	if (((MAX_CMD_QLEN + front_wi - rear_ri) % MAX_CMD_QLEN)  >= (MAX_CMD_QLEN - 1))
+		return true;
+
+	return false;
+}
+
+static void pt_cmd_callback(void *data, int err)
+{
+	struct pt_dma_desc *desc = data;
+	struct ae4_cmd_queue *ae4cmd_q;
+	struct dma_chan *dma_chan;
+	struct pt_dma_chan *chan;
+	struct ae4_device *ae4;
+	struct pt_device *pt;
+	int ret;
+
+	if (err == -EINPROGRESS)
+		return;
+
+	dma_chan = desc->vd.tx.chan;
+	chan = to_pt_chan(dma_chan);
+	pt = chan->pt;
+
+	if (err)
+		desc->status = DMA_ERROR;
+
+	while (true) {
+		if (pt->ver == AE4_DMA_VERSION) {
+			ae4 = container_of(pt, struct ae4_device, pt);
+			ae4cmd_q = &ae4->ae4cmd_q[chan->id];
+
+			if (ae4cmd_q->q_cmd_count >= (CMD_Q_LEN - 1) ||
+			    ae4_core_queue_full(&ae4cmd_q->cmd_q)) {
+				wake_up(&ae4cmd_q->q_w);
+
+				if (wait_for_completion_timeout(&ae4cmd_q->cmp,
+								msecs_to_jiffies(AE4_TIME_OUT))
+								== 0) {
+					dev_err(pt->dev, "TIMEOUT %d:\n", ae4cmd_q->id);
+					break;
+				}
+
+				reinit_completion(&ae4cmd_q->cmp);
+				continue;
+			}
+		}
+
+		/* Check for DMA descriptor completion */
+		desc = pt_handle_active_desc(chan, desc);
+
+		/* Don't submit cmd if no descriptor or DMA is paused */
+		if (!desc)
+			break;
+
+		ret = pt_dma_start_desc(desc, chan);
+		if (!ret)
+			break;
+
+		desc->status = DMA_ERROR;
+	}
+}
+
+static struct pt_dma_desc *pt_alloc_dma_desc(struct pt_dma_chan *chan,
+					     unsigned long flags)
+{
+	struct pt_dma_desc *desc;
+
+	desc = kmem_cache_zalloc(chan->pt->dma_desc_cache, GFP_NOWAIT);
+	if (!desc)
+		return NULL;
+
+	vchan_tx_prep(&chan->vc, &desc->vd, flags);
+
+	desc->pt = chan->pt;
+	desc->pt->cmd_q.int_en = !!(flags & DMA_PREP_INTERRUPT);
+	desc->issued_to_hw = 0;
+	desc->status = DMA_IN_PROGRESS;
+
+	return desc;
+}
+
+static void pt_cmd_callback_work(void *data, int err)
+{
+	struct dma_async_tx_descriptor *tx_desc;
+	struct pt_dma_desc *desc = data;
+	struct dma_chan *dma_chan;
+	struct virt_dma_desc *vd;
+	struct pt_dma_chan *chan;
+	unsigned long flags;
+
+	if (!desc)
+		return;
+
+	dma_chan = desc->vd.tx.chan;
+	chan = to_pt_chan(dma_chan);
+
+	if (err == -EINPROGRESS)
+		return;
+
+	tx_desc = &desc->vd.tx;
+	vd = &desc->vd;
+
+	if (err)
+		desc->status = DMA_ERROR;
+
+	spin_lock_irqsave(&chan->vc.lock, flags);
+	if (desc->status != DMA_COMPLETE) {
+		if (desc->status != DMA_ERROR)
+			desc->status = DMA_COMPLETE;
+
+		dma_cookie_complete(tx_desc);
+		dma_descriptor_unmap(tx_desc);
+	} else {
+		tx_desc = NULL;
+	}
+	spin_unlock_irqrestore(&chan->vc.lock, flags);
+
+	if (tx_desc) {
+		dmaengine_desc_get_callback_invoke(tx_desc, NULL);
+		dma_run_dependencies(tx_desc);
+		list_del(&desc->vd.node);
+		vchan_vdesc_fini(vd);
+	}
+}
+
+static struct pt_dma_desc *pt_create_desc(struct dma_chan *dma_chan,
+					  dma_addr_t dst,
+					  dma_addr_t src,
+					  unsigned int len,
+					  unsigned long flags)
+{
+	struct pt_dma_chan *chan = to_pt_chan(dma_chan);
+	struct pt_passthru_engine *pt_engine;
+	struct pt_device *pt = chan->pt;
+	struct ae4_cmd_queue *ae4cmd_q;
+	struct pt_dma_desc *desc;
+	struct ae4_device *ae4;
+	struct pt_cmd *pt_cmd;
+
+	desc = pt_alloc_dma_desc(chan, flags);
+	if (!desc)
+		return NULL;
+
+	pt_cmd = &desc->pt_cmd;
+	pt_cmd->pt = pt;
+	pt_engine = &pt_cmd->passthru;
+	pt_cmd->engine = PT_ENGINE_PASSTHRU;
+	pt_engine->src_dma = src;
+	pt_engine->dst_dma = dst;
+	pt_engine->src_len = len;
+	pt_cmd->pt_cmd_callback = pt_cmd_callback;
+	pt_cmd->data = desc;
+
+	desc->len = len;
+
+	if (pt->ver == AE4_DMA_VERSION) {
+		pt_cmd->pt_cmd_callback = pt_cmd_callback_work;
+		ae4 = container_of(pt, struct ae4_device, pt);
+		ae4cmd_q = &ae4->ae4cmd_q[chan->id];
+		mutex_lock(&ae4cmd_q->cmd_lock);
+		list_add_tail(&pt_cmd->entry, &ae4cmd_q->cmd);
+		mutex_unlock(&ae4cmd_q->cmd_lock);
+	}
+
+	return desc;
+}
+
+static struct dma_async_tx_descriptor *
+pt_prep_dma_memcpy(struct dma_chan *dma_chan, dma_addr_t dst,
+		   dma_addr_t src, size_t len, unsigned long flags)
+{
+	struct pt_dma_desc *desc;
+
+	desc = pt_create_desc(dma_chan, dst, src, len, flags);
+	if (!desc)
+		return NULL;
+
+	return &desc->vd.tx;
+}
+
+static struct dma_async_tx_descriptor *
+pt_prep_dma_interrupt(struct dma_chan *dma_chan, unsigned long flags)
+{
+	struct pt_dma_chan *chan = to_pt_chan(dma_chan);
+	struct pt_dma_desc *desc;
+
+	desc = pt_alloc_dma_desc(chan, flags);
+	if (!desc)
+		return NULL;
+
+	return &desc->vd.tx;
+}
+
+static void pt_issue_pending(struct dma_chan *dma_chan)
+{
+	struct pt_dma_chan *chan = to_pt_chan(dma_chan);
+	struct pt_dma_desc *desc;
+	struct pt_device *pt;
+	unsigned long flags;
+	bool engine_is_idle = true;
+
+	pt = chan->pt;
+
+	spin_lock_irqsave(&chan->vc.lock, flags);
+
+	desc = pt_next_dma_desc(chan);
+	if (desc && pt->ver != AE4_DMA_VERSION)
+		engine_is_idle = false;
+
+	vchan_issue_pending(&chan->vc);
+
+	desc = pt_next_dma_desc(chan);
+
+	spin_unlock_irqrestore(&chan->vc.lock, flags);
+
+	/* If there was nothing active, start processing */
+	if (engine_is_idle && desc)
+		pt_cmd_callback(desc, 0);
+}
+
+static void pt_check_status_trans_ae4(struct pt_device *pt, struct pt_cmd_queue *cmd_q)
+{
+	struct ae4_cmd_queue *ae4cmd_q = container_of(cmd_q, struct ae4_cmd_queue, cmd_q);
+	int i;
+
+	for (i = 0; i < CMD_Q_LEN; i++)
+		ae4_check_status_error(ae4cmd_q, i);
+}
+
+static enum dma_status
+pt_tx_status(struct dma_chan *c, dma_cookie_t cookie,
+		struct dma_tx_state *txstate)
+{
+	struct pt_dma_chan *chan = to_pt_chan(c);
+	struct pt_device *pt = chan->pt;
+	struct pt_cmd_queue *cmd_q;
+
+	cmd_q = pt_get_cmd_queue(pt, chan);
+
+	if (pt->ver == AE4_DMA_VERSION)
+		pt_check_status_trans_ae4(pt, cmd_q);
+	else
+		pt_check_status_trans(pt, cmd_q);
+
+	return dma_cookie_status(c, cookie, txstate);
+}
+
+static int pt_pause(struct dma_chan *dma_chan)
+{
+	struct pt_dma_chan *chan = to_pt_chan(dma_chan);
+	struct pt_device *pt = chan->pt;
+	struct pt_cmd_queue *cmd_q;
+	unsigned long flags;
+
+	spin_lock_irqsave(&chan->vc.lock, flags);
+	cmd_q = pt_get_cmd_queue(pt, chan);
+	pt_stop_queue(cmd_q);
+	spin_unlock_irqrestore(&chan->vc.lock, flags);
+
+	return 0;
+}
+
+static int pt_resume(struct dma_chan *dma_chan)
+{
+	struct pt_dma_chan *chan = to_pt_chan(dma_chan);
+	struct pt_dma_desc *desc = NULL;
+	struct pt_device *pt = chan->pt;
+	struct pt_cmd_queue *cmd_q;
+	unsigned long flags;
+
+	spin_lock_irqsave(&chan->vc.lock, flags);
+	cmd_q = pt_get_cmd_queue(pt, chan);
+	pt_start_queue(cmd_q);
+	desc = pt_next_dma_desc(chan);
+	spin_unlock_irqrestore(&chan->vc.lock, flags);
+
+	/* If there was something active, re-start */
+	if (desc)
+		pt_cmd_callback(desc, 0);
+
+	return 0;
+}
+
+static int pt_terminate_all(struct dma_chan *dma_chan)
+{
+	struct pt_dma_chan *chan = to_pt_chan(dma_chan);
+	struct pt_device *pt = chan->pt;
+	struct pt_cmd_queue *cmd_q;
+	unsigned long flags;
+	LIST_HEAD(head);
+
+	cmd_q = pt_get_cmd_queue(pt, chan);
+	if (pt->ver == AE4_DMA_VERSION)
+		pt_stop_queue(cmd_q);
+	else
+		iowrite32(SUPPORTED_INTERRUPTS, cmd_q->reg_control + 0x0010);
+
+	spin_lock_irqsave(&chan->vc.lock, flags);
+	vchan_get_all_descriptors(&chan->vc, &head);
+	spin_unlock_irqrestore(&chan->vc.lock, flags);
+
+	vchan_dma_desc_free_list(&chan->vc, &head);
+	vchan_free_chan_resources(&chan->vc);
+
+	return 0;
+}
+
+int pt_dmaengine_register(struct pt_device *pt)
+{
+	struct dma_device *dma_dev = &pt->dma_dev;
+	struct ae4_cmd_queue *ae4cmd_q = NULL;
+	struct ae4_device *ae4 = NULL;
+	struct pt_dma_chan *chan;
+	char *desc_cache_name;
+	int ret, i;
+
+	if (pt->ver == AE4_DMA_VERSION)
+		ae4 = container_of(pt, struct ae4_device, pt);
+
+	if (ae4)
+		pt->pt_dma_chan = devm_kcalloc(pt->dev, ae4->cmd_q_count,
+					       sizeof(*pt->pt_dma_chan), GFP_KERNEL);
+	else
+		pt->pt_dma_chan = devm_kzalloc(pt->dev, sizeof(*pt->pt_dma_chan),
+					       GFP_KERNEL);
+
+	if (!pt->pt_dma_chan)
+		return -ENOMEM;
+
+	desc_cache_name = devm_kasprintf(pt->dev, GFP_KERNEL,
+					 "%s-dmaengine-desc-cache",
+					 dev_name(pt->dev));
+	if (!desc_cache_name)
+		return -ENOMEM;
+
+	pt->dma_desc_cache = kmem_cache_create(desc_cache_name,
+					       sizeof(struct pt_dma_desc), 0,
+					       SLAB_HWCACHE_ALIGN, NULL);
+	if (!pt->dma_desc_cache)
+		return -ENOMEM;
+
+	dma_dev->dev = pt->dev;
+	dma_dev->src_addr_widths = DMA_SLAVE_BUSWIDTH_64_BYTES;
+	dma_dev->dst_addr_widths = DMA_SLAVE_BUSWIDTH_64_BYTES;
+	dma_dev->directions = DMA_MEM_TO_MEM;
+	dma_dev->residue_granularity = DMA_RESIDUE_GRANULARITY_DESCRIPTOR;
+	dma_cap_set(DMA_MEMCPY, dma_dev->cap_mask);
+	dma_cap_set(DMA_INTERRUPT, dma_dev->cap_mask);
+
+	/*
+	 * PTDMA is intended to be used with the AMD NTB devices, hence
+	 * marking it as DMA_PRIVATE.
+	 */
+	dma_cap_set(DMA_PRIVATE, dma_dev->cap_mask);
+
+	INIT_LIST_HEAD(&dma_dev->channels);
+
+	/* Set base and prep routines */
+	dma_dev->device_free_chan_resources = pt_free_chan_resources;
+	dma_dev->device_prep_dma_memcpy = pt_prep_dma_memcpy;
+	dma_dev->device_prep_dma_interrupt = pt_prep_dma_interrupt;
+	dma_dev->device_issue_pending = pt_issue_pending;
+	dma_dev->device_tx_status = pt_tx_status;
+	dma_dev->device_pause = pt_pause;
+	dma_dev->device_resume = pt_resume;
+	dma_dev->device_terminate_all = pt_terminate_all;
+	dma_dev->device_synchronize = pt_synchronize;
+
+	if (ae4) {
+		for (i = 0; i < ae4->cmd_q_count; i++) {
+			chan = pt->pt_dma_chan + i;
+			ae4cmd_q = &ae4->ae4cmd_q[i];
+			chan->id = ae4cmd_q->id;
+			chan->pt = pt;
+			chan->vc.desc_free = pt_do_cleanup;
+			vchan_init(&chan->vc, dma_dev);
+		}
+	} else {
+		chan = pt->pt_dma_chan;
+		chan->pt = pt;
+		chan->vc.desc_free = pt_do_cleanup;
+		vchan_init(&chan->vc, dma_dev);
+	}
+
+	ret = dma_async_device_register(dma_dev);
+	if (ret)
+		goto err_reg;
+
+	return 0;
+
+err_reg:
+	kmem_cache_destroy(pt->dma_desc_cache);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(pt_dmaengine_register);
+
+void pt_dmaengine_unregister(struct pt_device *pt)
+{
+	struct dma_device *dma_dev = &pt->dma_dev;
+
+	dma_async_device_unregister(dma_dev);
+
+	kmem_cache_destroy(pt->dma_desc_cache);
+}

linux-7.2.3/drivers/dma/amd/ptdma/ptdma-pci.c

@@ -0,0 +1,243 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * AMD Passthru DMA device driver
+ * -- Based on the CCP driver
+ *
+ * Copyright (C) 2016,2021 Advanced Micro Devices, Inc.
+ *
+ * Author: Sanjay R Mehta <sanju.mehta@amd.com>
+ * Author: Tom Lendacky <thomas.lendacky@amd.com>
+ * Author: Gary R Hook <gary.hook@amd.com>
+ */
+
+#include <linux/device.h>
+#include <linux/dma-mapping.h>
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/kthread.h>
+#include <linux/module.h>
+#include <linux/pci_ids.h>
+#include <linux/pci.h>
+#include <linux/spinlock.h>
+
+#include "ptdma.h"
+
+struct pt_msix {
+	int msix_count;
+	struct msix_entry msix_entry;
+};
+
+/*
+ * pt_alloc_struct - allocate and initialize the pt_device struct
+ *
+ * @dev: device struct of the PTDMA
+ */
+static struct pt_device *pt_alloc_struct(struct device *dev)
+{
+	struct pt_device *pt;
+
+	pt = devm_kzalloc(dev, sizeof(*pt), GFP_KERNEL);
+
+	if (!pt)
+		return NULL;
+	pt->dev = dev;
+
+	INIT_LIST_HEAD(&pt->cmd);
+
+	return pt;
+}
+
+static int pt_get_msix_irqs(struct pt_device *pt)
+{
+	struct pt_msix *pt_msix = pt->pt_msix;
+	struct device *dev = pt->dev;
+	struct pci_dev *pdev = to_pci_dev(dev);
+	int ret;
+
+	pt_msix->msix_entry.entry = 0;
+
+	ret = pci_enable_msix_range(pdev, &pt_msix->msix_entry, 1, 1);
+	if (ret < 0)
+		return ret;
+
+	pt_msix->msix_count = ret;
+
+	pt->pt_irq = pt_msix->msix_entry.vector;
+
+	return 0;
+}
+
+static int pt_get_msi_irq(struct pt_device *pt)
+{
+	struct device *dev = pt->dev;
+	struct pci_dev *pdev = to_pci_dev(dev);
+	int ret;
+
+	ret = pci_enable_msi(pdev);
+	if (ret)
+		return ret;
+
+	pt->pt_irq = pdev->irq;
+
+	return 0;
+}
+
+static int pt_get_irqs(struct pt_device *pt)
+{
+	struct device *dev = pt->dev;
+	int ret;
+
+	ret = pt_get_msix_irqs(pt);
+	if (!ret)
+		return 0;
+
+	/* Couldn't get MSI-X vectors, try MSI */
+	dev_err(dev, "could not enable MSI-X (%d), trying MSI\n", ret);
+	ret = pt_get_msi_irq(pt);
+	if (!ret)
+		return 0;
+
+	/* Couldn't get MSI interrupt */
+	dev_err(dev, "could not enable MSI (%d)\n", ret);
+
+	return ret;
+}
+
+static void pt_free_irqs(struct pt_device *pt)
+{
+	struct pt_msix *pt_msix = pt->pt_msix;
+	struct device *dev = pt->dev;
+	struct pci_dev *pdev = to_pci_dev(dev);
+
+	if (pt_msix->msix_count)
+		pci_disable_msix(pdev);
+	else if (pt->pt_irq)
+		pci_disable_msi(pdev);
+
+	pt->pt_irq = 0;
+}
+
+static int pt_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+{
+	struct pt_device *pt;
+	struct pt_msix *pt_msix;
+	struct device *dev = &pdev->dev;
+	void __iomem * const *iomap_table;
+	int bar_mask;
+	int ret = -ENOMEM;
+
+	pt = pt_alloc_struct(dev);
+	if (!pt)
+		goto e_err;
+
+	pt_msix = devm_kzalloc(dev, sizeof(*pt_msix), GFP_KERNEL);
+	if (!pt_msix)
+		goto e_err;
+
+	pt->pt_msix = pt_msix;
+	pt->dev_vdata = (struct pt_dev_vdata *)id->driver_data;
+	if (!pt->dev_vdata) {
+		ret = -ENODEV;
+		dev_err(dev, "missing driver data\n");
+		goto e_err;
+	}
+
+	ret = pcim_enable_device(pdev);
+	if (ret) {
+		dev_err(dev, "pcim_enable_device failed (%d)\n", ret);
+		goto e_err;
+	}
+
+	bar_mask = pci_select_bars(pdev, IORESOURCE_MEM);
+	ret = pcim_iomap_regions(pdev, bar_mask, "ptdma");
+	if (ret) {
+		dev_err(dev, "pcim_iomap_regions failed (%d)\n", ret);
+		goto e_err;
+	}
+
+	iomap_table = pcim_iomap_table(pdev);
+	if (!iomap_table) {
+		dev_err(dev, "pcim_iomap_table failed\n");
+		ret = -ENOMEM;
+		goto e_err;
+	}
+
+	pt->io_regs = iomap_table[pt->dev_vdata->bar];
+	if (!pt->io_regs) {
+		dev_err(dev, "ioremap failed\n");
+		ret = -ENOMEM;
+		goto e_err;
+	}
+
+	ret = pt_get_irqs(pt);
+	if (ret)
+		goto e_err;
+
+	pci_set_master(pdev);
+
+	ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(48));
+	if (ret) {
+		ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32));
+		if (ret) {
+			dev_err(dev, "dma_set_mask_and_coherent failed (%d)\n",
+				ret);
+			goto e_err;
+		}
+	}
+
+	dev_set_drvdata(dev, pt);
+
+	if (pt->dev_vdata)
+		ret = pt_core_init(pt);
+
+	if (ret)
+		goto e_err;
+
+	return 0;
+
+e_err:
+	dev_err(dev, "initialization failed ret = %d\n", ret);
+
+	return ret;
+}
+
+static void pt_pci_remove(struct pci_dev *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct pt_device *pt = dev_get_drvdata(dev);
+
+	if (!pt)
+		return;
+
+	if (pt->dev_vdata)
+		pt_core_destroy(pt);
+
+	pt_free_irqs(pt);
+}
+
+static const struct pt_dev_vdata dev_vdata[] = {
+	{
+		.bar = 2,
+	},
+};
+
+static const struct pci_device_id pt_pci_table[] = {
+	{ PCI_VDEVICE(AMD, 0x1498), (kernel_ulong_t)&dev_vdata[0] },
+	/* Last entry must be zero */
+	{ 0, }
+};
+MODULE_DEVICE_TABLE(pci, pt_pci_table);
+
+static struct pci_driver pt_pci_driver = {
+	.name = "ptdma",
+	.id_table = pt_pci_table,
+	.probe = pt_pci_probe,
+	.remove = pt_pci_remove,
+};
+
+module_pci_driver(pt_pci_driver);
+
+MODULE_AUTHOR("Sanjay R Mehta <sanju.mehta@amd.com>");
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("AMD PassThru DMA driver");

linux-7.2.3/drivers/dma/amd/ptdma/ptdma.h

@@ -0,0 +1,338 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * AMD Passthru DMA device driver
+ * -- Based on the CCP driver
+ *
+ * Copyright (C) 2016,2021 Advanced Micro Devices, Inc.
+ *
+ * Author: Sanjay R Mehta <sanju.mehta@amd.com>
+ * Author: Tom Lendacky <thomas.lendacky@amd.com>
+ * Author: Gary R Hook <gary.hook@amd.com>
+ */
+
+#ifndef __PT_DEV_H__
+#define __PT_DEV_H__
+
+#include <linux/device.h>
+#include <linux/dmaengine.h>
+#include <linux/pci.h>
+#include <linux/spinlock.h>
+#include <linux/mutex.h>
+#include <linux/list.h>
+#include <linux/wait.h>
+#include <linux/dmapool.h>
+
+#include "../../virt-dma.h"
+
+#define MAX_PT_NAME_LEN			16
+#define MAX_DMAPOOL_NAME_LEN		32
+
+#define MAX_HW_QUEUES			1
+#define MAX_CMD_QLEN			100
+
+#define PT_ENGINE_PASSTHRU		5
+
+/* Register Mappings */
+#define IRQ_MASK_REG			0x040
+#define IRQ_STATUS_REG			0x200
+
+#define CMD_Q_ERROR(__qs)		((__qs) & 0x0000003f)
+
+#define CMD_QUEUE_PRIO_OFFSET		0x00
+#define CMD_REQID_CONFIG_OFFSET		0x04
+#define CMD_TIMEOUT_OFFSET		0x08
+#define CMD_PT_VERSION			0x10
+
+#define CMD_Q_CONTROL_BASE		0x0000
+#define CMD_Q_TAIL_LO_BASE		0x0004
+#define CMD_Q_HEAD_LO_BASE		0x0008
+#define CMD_Q_INT_ENABLE_BASE		0x000C
+#define CMD_Q_INTERRUPT_STATUS_BASE	0x0010
+
+#define CMD_Q_STATUS_BASE		0x0100
+#define CMD_Q_INT_STATUS_BASE		0x0104
+#define CMD_Q_DMA_STATUS_BASE		0x0108
+#define CMD_Q_DMA_READ_STATUS_BASE	0x010C
+#define CMD_Q_DMA_WRITE_STATUS_BASE	0x0110
+#define CMD_Q_ABORT_BASE		0x0114
+#define CMD_Q_AX_CACHE_BASE		0x0118
+
+#define CMD_CONFIG_OFFSET		0x1120
+#define CMD_CLK_GATE_CTL_OFFSET		0x6004
+
+#define CMD_DESC_DW0_VAL		0x500012
+
+/* Address offset for virtual queue registers */
+#define CMD_Q_STATUS_INCR		0x1000
+
+/* Bit masks */
+#define CMD_CONFIG_REQID		0
+#define CMD_TIMEOUT_DISABLE		0
+#define CMD_CLK_DYN_GATING_DIS		0
+#define CMD_CLK_SW_GATE_MODE		0
+#define CMD_CLK_GATE_CTL		0
+#define CMD_QUEUE_PRIO			GENMASK(2, 1)
+#define CMD_CONFIG_VHB_EN		BIT(0)
+#define CMD_CLK_DYN_GATING_EN		BIT(0)
+#define CMD_CLK_HW_GATE_MODE		BIT(0)
+#define CMD_CLK_GATE_ON_DELAY		BIT(12)
+#define CMD_CLK_GATE_OFF_DELAY		BIT(12)
+
+#define CMD_CLK_GATE_CONFIG		(CMD_CLK_GATE_CTL | \
+					CMD_CLK_HW_GATE_MODE | \
+					CMD_CLK_GATE_ON_DELAY | \
+					CMD_CLK_DYN_GATING_EN | \
+					CMD_CLK_GATE_OFF_DELAY)
+
+#define CMD_Q_LEN			32
+#define CMD_Q_RUN			BIT(0)
+#define CMD_Q_HALT			BIT(1)
+#define CMD_Q_MEM_LOCATION		BIT(2)
+#define CMD_Q_SIZE_MASK			GENMASK(4, 0)
+#define CMD_Q_SIZE			GENMASK(7, 3)
+#define CMD_Q_SHIFT			GENMASK(1, 0)
+#define QUEUE_SIZE_VAL			((ffs(CMD_Q_LEN) - 2) & \
+								  CMD_Q_SIZE_MASK)
+#define Q_PTR_MASK			(2 << (QUEUE_SIZE_VAL + 5) - 1)
+#define Q_DESC_SIZE			sizeof(struct ptdma_desc)
+#define Q_SIZE(n)			(CMD_Q_LEN * (n))
+
+#define INT_COMPLETION			BIT(0)
+#define INT_ERROR			BIT(1)
+#define INT_QUEUE_STOPPED		BIT(2)
+#define INT_EMPTY_QUEUE			BIT(3)
+#define SUPPORTED_INTERRUPTS		(INT_COMPLETION | INT_ERROR)
+
+/****** Local Storage Block ******/
+#define LSB_START			0
+#define LSB_END				127
+#define LSB_COUNT			(LSB_END - LSB_START + 1)
+
+#define PT_DMAPOOL_MAX_SIZE		64
+#define PT_DMAPOOL_ALIGN		BIT(5)
+
+#define PT_PASSTHRU_BLOCKSIZE		512
+
+struct pt_device;
+
+struct pt_tasklet_data {
+	struct completion completion;
+	struct pt_cmd *cmd;
+};
+
+/*
+ * struct pt_passthru_engine - pass-through operation
+ *   without performing DMA mapping
+ * @mask: mask to be applied to data
+ * @mask_len: length in bytes of mask
+ * @src_dma: data to be used for this operation
+ * @dst_dma: data produced by this operation
+ * @src_len: length in bytes of data used for this operation
+ *
+ * Variables required to be set when calling pt_enqueue_cmd():
+ *   - bit_mod, byte_swap, src, dst, src_len
+ *   - mask, mask_len if bit_mod is not PT_PASSTHRU_BITWISE_NOOP
+ */
+struct pt_passthru_engine {
+	dma_addr_t mask;
+	u32 mask_len;		/* In bytes */
+
+	dma_addr_t src_dma, dst_dma;
+	u64 src_len;		/* In bytes */
+};
+
+/*
+ * struct pt_cmd - PTDMA operation request
+ * @entry: list element
+ * @work: work element used for callbacks
+ * @pt: PT device to be run on
+ * @ret: operation return code
+ * @flags: cmd processing flags
+ * @engine: PTDMA operation to perform (passthru)
+ * @engine_error: PT engine return code
+ * @passthru: engine specific structures, refer to specific engine struct below
+ * @callback: operation completion callback function
+ * @data: parameter value to be supplied to the callback function
+ *
+ * Variables required to be set when calling pt_enqueue_cmd():
+ *   - engine, callback
+ *   - See the operation structures below for what is required for each
+ *     operation.
+ */
+struct pt_cmd {
+	struct list_head entry;
+	struct work_struct work;
+	struct pt_device *pt;
+	int ret;
+	u32 engine;
+	u32 engine_error;
+	struct pt_passthru_engine passthru;
+	/* Completion callback support */
+	void (*pt_cmd_callback)(void *data, int err);
+	void *data;
+};
+
+struct pt_dma_desc {
+	struct virt_dma_desc vd;
+	struct pt_device *pt;
+	enum dma_status status;
+	size_t len;
+	bool issued_to_hw;
+	struct pt_cmd pt_cmd;
+};
+
+struct pt_dma_chan {
+	struct virt_dma_chan vc;
+	struct pt_device *pt;
+	u32 id;
+};
+
+struct pt_cmd_queue {
+	struct pt_device *pt;
+
+	/* Queue dma pool */
+	struct dma_pool *dma_pool;
+
+	/* Queue base address (not necessarily aligned)*/
+	struct ptdma_desc *qbase;
+
+	/* Aligned queue start address (per requirement) */
+	spinlock_t q_lock ____cacheline_aligned;
+	unsigned int qidx;
+
+	unsigned int qsize;
+	dma_addr_t qbase_dma;
+	dma_addr_t qdma_tail;
+
+	unsigned int active;
+	unsigned int suspended;
+
+	/* Interrupt flag */
+	bool int_en;
+
+	/* Register addresses for queue */
+	void __iomem *reg_control;
+	u32 qcontrol; /* Cached control register */
+
+	/* Status values from job */
+	u32 int_status;
+	u32 q_status;
+	u32 q_int_status;
+	u32 cmd_error;
+	/* Queue Statistics */
+	unsigned long total_pt_ops;
+} ____cacheline_aligned;
+
+struct pt_device {
+	struct list_head entry;
+
+	unsigned int ord;
+	char name[MAX_PT_NAME_LEN];
+
+	struct device *dev;
+
+	/* Bus specific device information */
+	struct pt_msix *pt_msix;
+
+	struct pt_dev_vdata *dev_vdata;
+
+	unsigned int pt_irq;
+
+	/* I/O area used for device communication */
+	void __iomem *io_regs;
+
+	spinlock_t cmd_lock ____cacheline_aligned;
+	unsigned int cmd_count;
+	struct list_head cmd;
+
+	/*
+	 * The command queue. This represent the queue available on the
+	 * PTDMA that are available for processing cmds
+	 */
+	struct pt_cmd_queue cmd_q;
+
+	/* Support for the DMA Engine capabilities */
+	struct dma_device dma_dev;
+	struct pt_dma_chan *pt_dma_chan;
+	struct kmem_cache *dma_desc_cache;
+
+	wait_queue_head_t lsb_queue;
+
+	/* Device Statistics */
+	unsigned long total_interrupts;
+
+	struct pt_tasklet_data tdata;
+	int ver;
+};
+
+/*
+ * descriptor for PTDMA commands
+ * 8 32-bit words:
+ * word 0: function; engine; control bits
+ * word 1: length of source data
+ * word 2: low 32 bits of source pointer
+ * word 3: upper 16 bits of source pointer; source memory type
+ * word 4: low 32 bits of destination pointer
+ * word 5: upper 16 bits of destination pointer; destination memory type
+ * word 6: reserved 32 bits
+ * word 7: reserved 32 bits
+ */
+
+#define DWORD0_SOC	BIT(0)
+#define DWORD0_IOC	BIT(1)
+
+struct dword3 {
+	unsigned int  src_hi:16;
+	unsigned int  src_mem:2;
+	unsigned int  lsb_cxt_id:8;
+	unsigned int  rsvd1:5;
+	unsigned int  fixed:1;
+};
+
+struct dword5 {
+	unsigned int  dst_hi:16;
+	unsigned int  dst_mem:2;
+	unsigned int  rsvd1:13;
+	unsigned int  fixed:1;
+};
+
+struct ptdma_desc {
+	u32 dw0;
+	u32 length;
+	u32 src_lo;
+	struct dword3 dw3;
+	u32 dst_lo;
+	struct dword5 dw5;
+	__le32 rsvd1;
+	__le32 rsvd2;
+};
+
+/* Structure to hold PT device data */
+struct pt_dev_vdata {
+	const unsigned int bar;
+};
+
+int pt_dmaengine_register(struct pt_device *pt);
+void pt_dmaengine_unregister(struct pt_device *pt);
+
+void ptdma_debugfs_setup(struct pt_device *pt);
+int pt_core_init(struct pt_device *pt);
+void pt_core_destroy(struct pt_device *pt);
+
+int pt_core_perform_passthru(struct pt_cmd_queue *cmd_q,
+			     struct pt_passthru_engine *pt_engine);
+
+void pt_check_status_trans(struct pt_device *pt, struct pt_cmd_queue *cmd_q);
+void pt_start_queue(struct pt_cmd_queue *cmd_q);
+void pt_stop_queue(struct pt_cmd_queue *cmd_q);
+
+static inline void pt_core_disable_queue_interrupts(struct pt_device *pt)
+{
+	iowrite32(0, pt->cmd_q.reg_control + 0x000C);
+}
+
+static inline void pt_core_enable_queue_interrupts(struct pt_device *pt)
+{
+	iowrite32(SUPPORTED_INTERRUPTS, pt->cmd_q.reg_control + 0x000C);
+}
+#endif