Skip to contentSkip to conversation

dmaengine: dw-edma: fix dw_edma_probe() can't be call globally

PATCH Superseded Frank Li 1 participant 6 messages Mar 7, 2022

Subsystems (4)
lore
Share & tools
lore

Frank Li

author
#0 lore raw

PATCH v3 1/6 dmaengine: dw-edma: fix dw_edma_probe() can't be call globally

"struct dw_edma_chip" contains an internal structure "struct dw_edma" that is used by the eDMA core internally. This structure should not be touched by the eDMA controller drivers themselves. But currently, the eDMA controller drivers like "dw-edma-pci" allocates and populates this internal structure then passes it on to eDMA core. The eDMA core further populates the structure and uses it. This is wrong!

Hence, move all the "struct dw_edma" specifics from controller drivers to the eDMA core.

---
Change from v2 to v3
- none
Change from v1 to v2
- rework commit message
- remove duplicate field in struct dw_edma

 drivers/dma/dw-edma/dw-edma-core.c       |  91 +++++-----
 drivers/dma/dw-edma/dw-edma-core.h       |  30 +---
 drivers/dma/dw-edma/dw-edma-v0-core.c    | 206 ++++++++++++-----------
 drivers/dma/dw-edma/dw-edma-v0-core.h    |   8 +-
 drivers/dma/dw-edma/dw-edma-v0-debugfs.c |  37 ++--
 include/linux/dma/edma.h                 |  47 +++++-
 6 files changed, 230 insertions(+), 189 deletions(-)
drivers/dma/dw-edma/dw-edma-core.c +51 -40
index 53289927dd0d6..0cb66434f9e14 100644
@@ -65,7 +65,7 @@ static struct dw_edma_burst *dw_edma_alloc_burst(struct dw_edma_chunk *chunk)
 static struct dw_edma_chunk *dw_edma_alloc_chunk(struct dw_edma_desc *desc)
 {
 	struct dw_edma_chan *chan = desc->chan;
-	struct dw_edma *dw = chan->chip->dw;
+	struct dw_edma_chip *chip = chan->chip;
 	struct dw_edma_chunk *chunk;
 
 	chunk = kzalloc(sizeof(*chunk), GFP_NOWAIT);
@@ -82,11 +82,11 @@ static struct dw_edma_chunk *dw_edma_alloc_chunk(struct dw_edma_desc *desc)
 	 */
 	chunk->cb = !(desc->chunks_alloc % 2);
 	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;
+		chunk->ll_region.paddr = chip->ll_region_wr[chan->id].paddr;
+		chunk->ll_region.vaddr = chip->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;
+		chunk->ll_region.paddr = chip->ll_region_rd[chan->id].paddr;
+		chunk->ll_region.vaddr = chip->ll_region_rd[chan->id].vaddr;
 	}
 
 	if (desc->chunk) {
@@ -601,7 +601,8 @@ static void dw_edma_abort_interrupt(struct dw_edma_chan *chan)
 static irqreturn_t dw_edma_interrupt(int irq, void *data, bool write)
 {
 	struct dw_edma_irq *dw_irq = data;
-	struct dw_edma *dw = dw_irq->dw;
+	struct dw_edma_chip *chip = dw_irq->chip;
+	struct dw_edma *dw = chip->dw;
 	unsigned long total, pos, val;
 	unsigned long off;
 	u32 mask;
@@ -616,7 +617,7 @@ static irqreturn_t dw_edma_interrupt(int irq, void *data, bool write)
 		mask = dw_irq->rd_mask;
 	}
 
-	val = dw_edma_v0_core_status_done_int(dw, write ?
+	val = dw_edma_v0_core_status_done_int(chip, write ?
 							  EDMA_DIR_WRITE :
 							  EDMA_DIR_READ);
 	val &= mask;
@@ -626,7 +627,7 @@ static irqreturn_t dw_edma_interrupt(int irq, void *data, bool write)
 		dw_edma_done_interrupt(chan);
 	}
 
-	val = dw_edma_v0_core_status_abort_int(dw, write ?
+	val = dw_edma_v0_core_status_abort_int(chip, write ?
 							   EDMA_DIR_WRITE :
 							   EDMA_DIR_READ);
 	val &= mask;
@@ -718,7 +719,7 @@ static int dw_edma_channel_setup(struct dw_edma_chip *chip, bool write,
 	}
 
 	INIT_LIST_HEAD(&dma->channels);
-	for (j = 0; (alloc || dw->nr_irqs == 1) && j < cnt; j++, i++) {
+	for (j = 0; (alloc || chip->nr_irqs == 1) && j < cnt; j++, i++) {
 		chan = &dw->chan[i];
 
 		dt_region = devm_kzalloc(dev, sizeof(*dt_region), GFP_KERNEL);
@@ -735,15 +736,15 @@ static int dw_edma_channel_setup(struct dw_edma_chip *chip, bool write,
 		chan->status = EDMA_ST_IDLE;
 
 		if (write)
-			chan->ll_max = (dw->ll_region_wr[j].sz / EDMA_LL_SZ);
+			chan->ll_max = (chip->ll_region_wr[j].sz / EDMA_LL_SZ);
 		else
-			chan->ll_max = (dw->ll_region_rd[j].sz / EDMA_LL_SZ);
+			chan->ll_max = (chip->ll_region_rd[j].sz / EDMA_LL_SZ);
 		chan->ll_max -= 1;
 
 		dev_vdbg(dev, "L. List:\tChannel %s[%u] max_cnt=%u\n",
 			 write ? "write" : "read", j, chan->ll_max);
 
-		if (dw->nr_irqs == 1)
+		if (chip->nr_irqs == 1)
 			pos = 0;
 		else
 			pos = off_alloc + (j % alloc);
@@ -755,7 +756,7 @@ static int dw_edma_channel_setup(struct dw_edma_chip *chip, bool write,
 		else
 			irq->rd_mask |= BIT(j);
 
-		irq->dw = dw;
+		irq->chip = chip;
 		memcpy(&chan->msi, &irq->msi, sizeof(chan->msi));
 
 		dev_vdbg(dev, "MSI:\t\tChannel %s[%u] addr=0x%.8x%.8x, data=0x%.8x\n",
@@ -767,13 +768,13 @@ static int dw_edma_channel_setup(struct dw_edma_chip *chip, bool write,
 		vchan_init(&chan->vc, dma);
 
 		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;
+			dt_region->paddr = chip->dt_region_wr[j].paddr;
+			dt_region->vaddr = chip->dt_region_wr[j].vaddr;
+			dt_region->sz = chip->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;
+			dt_region->paddr = chip->dt_region_rd[j].paddr;
+			dt_region->vaddr = chip->dt_region_rd[j].vaddr;
+			dt_region->sz = chip->dt_region_rd[j].sz;
 		}
 
 		dw_edma_v0_core_device_config(chan);
@@ -840,16 +841,16 @@ static int dw_edma_irq_request(struct dw_edma_chip *chip,
 
 	ch_cnt = dw->wr_ch_cnt + dw->rd_ch_cnt;
 
-	if (dw->nr_irqs < 1)
+	if (chip->nr_irqs < 1)
 		return -EINVAL;
 
-	if (dw->nr_irqs == 1) {
+	if (chip->nr_irqs == 1) {
 		/* Common IRQ shared among all channels */
-		irq = dw->ops->irq_vector(dev, 0);
+		irq = chip->ops->irq_vector(dev, 0);
 		err = request_irq(irq, dw_edma_interrupt_common,
 				  IRQF_SHARED, dw->name, &dw->irq[0]);
 		if (err) {
-			dw->nr_irqs = 0;
+			chip->nr_irqs = 0;
 			return err;
 		}
 
@@ -857,7 +858,7 @@ static int dw_edma_irq_request(struct dw_edma_chip *chip,
 			get_cached_msi_msg(irq, &dw->irq[0].msi);
 	} else {
 		/* Distribute IRQs equally among all channels */
-		int tmp = dw->nr_irqs;
+		int tmp = chip->nr_irqs;
 
 		while (tmp && (*wr_alloc + *rd_alloc) < ch_cnt) {
 			dw_edma_dec_irq_alloc(&tmp, wr_alloc, dw->wr_ch_cnt);
@@ -868,7 +869,7 @@ static int dw_edma_irq_request(struct dw_edma_chip *chip,
 		dw_edma_add_irq_mask(&rd_mask, *rd_alloc, dw->rd_ch_cnt);
 
 		for (i = 0; i < (*wr_alloc + *rd_alloc); i++) {
-			irq = dw->ops->irq_vector(dev, i);
+			irq = chip->ops->irq_vector(dev, i);
 			err = request_irq(irq,
 					  i < *wr_alloc ?
 						dw_edma_interrupt_write :
@@ -876,7 +877,7 @@ static int dw_edma_irq_request(struct dw_edma_chip *chip,
 					  IRQF_SHARED, dw->name,
 					  &dw->irq[i]);
 			if (err) {
-				dw->nr_irqs = i;
+				chip->nr_irqs = i;
 				return err;
 			}
 
@@ -884,7 +885,7 @@ static int dw_edma_irq_request(struct dw_edma_chip *chip,
 				get_cached_msi_msg(irq, &dw->irq[i].msi);
 		}
 
-		dw->nr_irqs = i;
+		chip->nr_irqs = i;
 	}
 
 	return err;
@@ -905,18 +906,24 @@ int dw_edma_probe(struct dw_edma_chip *chip)
 	if (!dev)
 		return -EINVAL;
 
-	dw = chip->dw;
-	if (!dw || !dw->irq || !dw->ops || !dw->ops->irq_vector)
+	dw = devm_kzalloc(dev, sizeof(*dw), GFP_KERNEL);
+	if (!dw)
+		return -ENOMEM;
+
+	chip->dw = dw;
+
+	if (!chip->nr_irqs || !chip->ops)
 		return -EINVAL;
 
 	raw_spin_lock_init(&dw->lock);
 
-	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, chip->ll_wr_cnt,
+			      dw_edma_v0_core_ch_count(chip, EDMA_DIR_WRITE));
 	dw->wr_ch_cnt = min_t(u16, dw->wr_ch_cnt, EDMA_MAX_WR_CH);
 
-	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, chip->ll_rd_cnt,
+			      dw_edma_v0_core_ch_count(chip, 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)
@@ -934,7 +941,11 @@ int dw_edma_probe(struct dw_edma_chip *chip)
 	snprintf(dw->name, sizeof(dw->name), "dw-edma-core:%d", chip->id);
 
 	/* Disable eDMA, only to establish the ideal initial conditions */
-	dw_edma_v0_core_off(dw);
+	dw_edma_v0_core_off(chip);
+
+	dw->irq = devm_kcalloc(dev, chip->nr_irqs, sizeof(*dw->irq), GFP_KERNEL);
+	if (!dw->irq)
+		return -ENOMEM;
 
 	/* Request IRQs */
 	err = dw_edma_irq_request(chip, &wr_alloc, &rd_alloc);
@@ -960,10 +971,10 @@ int dw_edma_probe(struct dw_edma_chip *chip)
 	return 0;
 
 err_irq_free:
-	for (i = (dw->nr_irqs - 1); i >= 0; i--)
-		free_irq(dw->ops->irq_vector(dev, i), &dw->irq[i]);
+	for (i = (chip->nr_irqs - 1); i >= 0; i--)
+		free_irq(chip->ops->irq_vector(dev, i), &dw->irq[i]);
 
-	dw->nr_irqs = 0;
+	chip->nr_irqs = 0;
 
 	return err;
 }
@@ -977,11 +988,11 @@ int dw_edma_remove(struct dw_edma_chip *chip)
 	int i;
 
 	/* Disable eDMA */
-	dw_edma_v0_core_off(dw);
+	dw_edma_v0_core_off(chip);
 
 	/* Free irqs */
-	for (i = (dw->nr_irqs - 1); i >= 0; i--)
-		free_irq(dw->ops->irq_vector(dev, i), &dw->irq[i]);
+	for (i = (chip->nr_irqs - 1); i >= 0; i--)
+		free_irq(chip->ops->irq_vector(dev, i), &dw->irq[i]);
 
 	/* Power management */
 	pm_runtime_disable(dev);
drivers/dma/dw-edma/dw-edma-core.h +1 -29
index 60316d408c3e0..885f6719c9462 100644
@@ -15,20 +15,12 @@
 #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_map_format {
-	EDMA_MF_EDMA_LEGACY = 0x0,
-	EDMA_MF_EDMA_UNROLL = 0x1,
-	EDMA_MF_HDMA_COMPAT = 0x5
-};
-
 enum dw_edma_request {
 	EDMA_REQ_NONE = 0,
 	EDMA_REQ_STOP,
@@ -57,12 +49,6 @@ struct dw_edma_burst {
 	u32				sz;
 };
 
-struct dw_edma_region {
-	phys_addr_t			paddr;
-	void				__iomem *vaddr;
-	size_t				sz;
-};
-
 struct dw_edma_chunk {
 	struct list_head		list;
 	struct dw_edma_chan		*chan;
@@ -106,11 +92,7 @@ struct dw_edma_irq {
 	struct msi_msg                  msi;
 	u32				wr_mask;
 	u32				rd_mask;
-	struct dw_edma			*dw;
-};
-
-struct dw_edma_core_ops {
-	int	(*irq_vector)(struct device *dev, unsigned int nr);
+	struct dw_edma_chip		*chip;
 };
 
 struct dw_edma {
@@ -122,19 +104,9 @@ struct dw_edma {
 	struct dma_device		rd_edma;
 	u16				rd_ch_cnt;
 
-	struct dw_edma_region		rg_region;	/* Registers */
-	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;
-
-	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
drivers/dma/dw-edma/dw-edma-v0-core.c +106 -100

457 lines not on this page · raw message

drivers/dma/dw-edma/dw-edma-v0-core.h +4 -4
index 2afa626b8300c..01a29c74c0c43 100644
@@ -12,13 +12,13 @@
 #include <linux/dma/edma.h>
 
 /* eDMA management callbacks */
-void dw_edma_v0_core_off(struct dw_edma *chan);
-u16 dw_edma_v0_core_ch_count(struct dw_edma *chan, enum dw_edma_dir dir);
+void dw_edma_v0_core_off(struct dw_edma_chip *chip);
+u16 dw_edma_v0_core_ch_count(struct dw_edma_chip *chip, enum dw_edma_dir dir);
 enum dma_status dw_edma_v0_core_ch_status(struct dw_edma_chan *chan);
 void dw_edma_v0_core_clear_done_int(struct dw_edma_chan *chan);
 void dw_edma_v0_core_clear_abort_int(struct dw_edma_chan *chan);
-u32 dw_edma_v0_core_status_done_int(struct dw_edma *chan, enum dw_edma_dir dir);
-u32 dw_edma_v0_core_status_abort_int(struct dw_edma *chan, enum dw_edma_dir dir);
+u32 dw_edma_v0_core_status_done_int(struct dw_edma_chip *chip, enum dw_edma_dir dir);
+u32 dw_edma_v0_core_status_abort_int(struct dw_edma_chip *chip, enum dw_edma_dir dir);
 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 */
drivers/dma/dw-edma/dw-edma-v0-debugfs.c +23 -14
index 4b3bcffd15ef1..5819a64aceb0f 100644
@@ -38,7 +38,7 @@
 #define CHANNEL_STR				"channel"
 #define REGISTERS_STR				"registers"
 
-static struct dw_edma				*dw;
+static struct dw_edma_chip			*chip;
 static struct dw_edma_v0_regs			__iomem *regs;
 
 static struct {
@@ -53,8 +53,10 @@ struct debugfs_entries {
 
 static int dw_edma_debugfs_u32_get(void *data, u64 *val)
 {
+	struct dw_edma *dw = chip->dw;
+
 	void __iomem *reg = (void __force __iomem *)data;
-	if (dw->mf == EDMA_MF_EDMA_LEGACY &&
+	if (chip->mf == EDMA_MF_EDMA_LEGACY &&
 	    reg >= (void __iomem *)&regs->type.legacy.ch) {
 		void __iomem *ptr = &regs->type.legacy.ch;
 		u32 viewport_sel = 0;
@@ -127,6 +129,8 @@ static void dw_edma_debugfs_regs_ch(struct dw_edma_v0_ch_regs __iomem *regs,
 
 static void dw_edma_debugfs_regs_wr(struct dentry *dir)
 {
+	struct dw_edma *dw = chip->dw;
+
 	const struct debugfs_entries debugfs_regs[] = {
 		/* eDMA global registers */
 		WR_REGISTER(engine_en),
@@ -173,7 +177,7 @@ 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->mf == EDMA_MF_HDMA_COMPAT) {
+	if (chip->mf == EDMA_MF_HDMA_COMPAT) {
 		nr_entries = ARRAY_SIZE(debugfs_unroll_regs);
 		dw_edma_debugfs_create_x32(debugfs_unroll_regs, nr_entries,
 					   regs_dir);
@@ -195,6 +199,8 @@ static void dw_edma_debugfs_regs_wr(struct dentry *dir)
 
 static void dw_edma_debugfs_regs_rd(struct dentry *dir)
 {
+	struct dw_edma *dw = chip->dw;
+
 	const struct debugfs_entries debugfs_regs[] = {
 		/* eDMA global registers */
 		RD_REGISTER(engine_en),
@@ -242,7 +248,7 @@ 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->mf == EDMA_MF_HDMA_COMPAT) {
+	if (chip->mf == EDMA_MF_HDMA_COMPAT) {
 		nr_entries = ARRAY_SIZE(debugfs_unroll_regs);
 		dw_edma_debugfs_create_x32(debugfs_unroll_regs, nr_entries,
 					   regs_dir);
@@ -264,6 +270,7 @@ static void dw_edma_debugfs_regs_rd(struct dentry *dir)
 
 static void dw_edma_debugfs_regs(void)
 {
+	struct dw_edma *dw = chip->dw;
 	const struct debugfs_entries debugfs_regs[] = {
 		REGISTER(ctrl_data_arb_prior),
 		REGISTER(ctrl),
@@ -282,13 +289,15 @@ static void dw_edma_debugfs_regs(void)
 	dw_edma_debugfs_regs_rd(regs_dir);
 }
 
-void dw_edma_v0_debugfs_on(struct dw_edma_chip *chip)
+void dw_edma_v0_debugfs_on(struct dw_edma_chip *p)
 {
-	dw = chip->dw;
-	if (!dw)
+	struct dw_edma *dw;
+	chip = p;
+	if (!chip)
 		return;
 
-	regs = dw->rg_region.vaddr;
+	dw = chip->dw;
+	regs = chip->reg_base;
 	if (!regs)
 		return;
 
@@ -296,19 +305,19 @@ void dw_edma_v0_debugfs_on(struct dw_edma_chip *chip)
 	if (!dw->debugfs)
 		return;
 
-	debugfs_create_u32("mf", 0444, dw->debugfs, &dw->mf);
+	debugfs_create_u32("mf", 0444, dw->debugfs, &chip->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(struct dw_edma_chip *chip)
+void dw_edma_v0_debugfs_off(struct dw_edma_chip *p)
 {
-	dw = chip->dw;
-	if (!dw)
+	chip = p;
+	if (!chip)
 		return;
 
-	debugfs_remove_recursive(dw->debugfs);
-	dw->debugfs = NULL;
+	debugfs_remove_recursive(chip->dw->debugfs);
+	chip->dw->debugfs = NULL;
 }
include/linux/dma/edma.h +45 -2

64 lines not on this page · raw message

Signature · 1 line
2.24.0.rc1
author
#1 lore raw

PATCH v3 2/6 dmaengine: dw-edma-pcie: don't touch internal struct dw_edma

"struct dw_edma" is an internal structure of the eDMA core. This should not be used by the eDMA controllers like "dw-edma-pcie" for passing the controller specific information to the core.

Instead, use the fields local to the "struct dw_edma_chip" for passing the controller specific info to the core.

---
Change from v2 to v3:
None

Change from v1 to v2:
- rework commit message
- rg_region only use virtual address. using chip->reg_base instead

 drivers/dma/dw-edma/dw-edma-pcie.c | 83 ++++++++++++------------------
 1 file changed, 34 insertions(+), 49 deletions(-)
drivers/dma/dw-edma/dw-edma-pcie.c +34 -49
index 44f6e09bdb531..7732537f96086 100644
@@ -148,7 +148,6 @@ static int dw_edma_pcie_probe(struct pci_dev *pdev,
 	struct dw_edma_pcie_data vsec_data;
 	struct device *dev = &pdev->dev;
 	struct dw_edma_chip *chip;
-	struct dw_edma *dw;
 	int err, nr_irqs;
 	int i, mask;
 
@@ -214,10 +213,6 @@ static int dw_edma_pcie_probe(struct pci_dev *pdev,
 	if (!chip)
 		return -ENOMEM;
 
-	dw = devm_kzalloc(dev, sizeof(*dw), GFP_KERNEL);
-	if (!dw)
-		return -ENOMEM;
-
 	/* IRQs allocation */
 	nr_irqs = pci_alloc_irq_vectors(pdev, 1, vsec_data.irqs,
 					PCI_IRQ_MSI | PCI_IRQ_MSIX);
@@ -228,29 +223,23 @@ static int dw_edma_pcie_probe(struct pci_dev *pdev,
 	}
 
 	/* Data structure initialization */
-	chip->dw = dw;
 	chip->dev = dev;
 	chip->id = pdev->devfn;
-	chip->irq = pdev->irq;
 
-	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;
+	chip->mf = vsec_data.mf;
+	chip->nr_irqs = nr_irqs;
+	chip->ops = &dw_edma_pcie_core_ops;
 
-	dw->rg_region.vaddr = pcim_iomap_table(pdev)[vsec_data.rg.bar];
-	if (!dw->rg_region.vaddr)
-		return -ENOMEM;
+	chip->ll_wr_cnt = vsec_data.wr_ch_cnt;
+	chip->ll_rd_cnt = vsec_data.rd_ch_cnt;
 
-	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;
+	chip->reg_base = pcim_iomap_table(pdev)[vsec_data.rg.bar];
+	if (!chip->reg_base)
+		return -ENOMEM;
 
-	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];
+	for (i = 0; i < chip->ll_wr_cnt; i++) {
+		struct dw_edma_region *ll_region = &chip->ll_region_wr[i];
+		struct dw_edma_region *dt_region = &chip->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];
 
@@ -273,9 +262,9 @@ static int dw_edma_pcie_probe(struct pci_dev *pdev,
 		dt_region->sz = dt_block->sz;
 	}
 
-	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];
+	for (i = 0; i < chip->ll_rd_cnt; i++) {
+		struct dw_edma_region *ll_region = &chip->ll_region_rd[i];
+		struct dw_edma_region *dt_region = &chip->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];
 
@@ -299,45 +288,45 @@ static int dw_edma_pcie_probe(struct pci_dev *pdev,
 	}
 
 	/* 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);
+	if (chip->mf == EDMA_MF_EDMA_LEGACY)
+		pci_dbg(pdev, "Version:\teDMA Port Logic (0x%x)\n", chip->mf);
+	else if (chip->mf == EDMA_MF_EDMA_UNROLL)
+		pci_dbg(pdev, "Version:\teDMA Unroll (0x%x)\n", chip->mf);
+	else if (chip->mf == EDMA_MF_HDMA_COMPAT)
+		pci_dbg(pdev, "Version:\tHDMA Compatible (0x%x)\n", chip->mf);
 	else
-		pci_dbg(pdev, "Version:\tUnknown (0x%x)\n", dw->mf);
+		pci_dbg(pdev, "Version:\tUnknown (0x%x)\n", chip->mf);
 
-	pci_dbg(pdev, "Registers:\tBAR=%u, off=0x%.8lx, sz=0x%zx bytes, addr(v=%p, p=%pa)\n",
+	pci_dbg(pdev, "Registers:\tBAR=%u, off=0x%.8lx, sz=0x%zx bytes, addr(v=%p)\n",
 		vsec_data.rg.bar, vsec_data.rg.off, vsec_data.rg.sz,
-		dw->rg_region.vaddr, &dw->rg_region.paddr);
+		chip->reg_base);
 
 
-	for (i = 0; i < dw->wr_ch_cnt; i++) {
+	for (i = 0; i < chip->ll_wr_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);
+			vsec_data.ll_wr[i].off, chip->ll_region_wr[i].sz,
+			chip->ll_region_wr[i].vaddr, &chip->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);
+			vsec_data.dt_wr[i].off, chip->dt_region_wr[i].sz,
+			chip->dt_region_wr[i].vaddr, &chip->dt_region_wr[i].paddr);
 	}
 
-	for (i = 0; i < dw->rd_ch_cnt; i++) {
+	for (i = 0; i < chip->ll_rd_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);
+			vsec_data.ll_rd[i].off, chip->ll_region_rd[i].sz,
+			chip->ll_region_rd[i].vaddr, &chip->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);
+			vsec_data.dt_rd[i].off, chip->dt_region_rd[i].sz,
+			chip->dt_region_rd[i].vaddr, &chip->dt_region_rd[i].paddr);
 	}
 
-	pci_dbg(pdev, "Nr. IRQs:\t%u\n", dw->nr_irqs);
+	pci_dbg(pdev, "Nr. IRQs:\t%u\n", chip->nr_irqs);
 
 	/* Validating if PCI interrupts were enabled */
 	if (!pci_dev_msi_enabled(pdev)) {
@@ -345,10 +334,6 @@ static int dw_edma_pcie_probe(struct pci_dev *pdev,
 		return -EPERM;
 	}
 
-	dw->irq = devm_kcalloc(dev, nr_irqs, sizeof(*dw->irq), GFP_KERNEL);
-	if (!dw->irq)
-		return -ENOMEM;
-
 	/* Starting eDMA driver */
 	err = dw_edma_probe(chip);
 	if (err) {
Signature · 1 line
2.24.0.rc1
author
#2 lore raw

PATCH v3 3/6 dmaengine: dw-edma: Fix programming the source & dest addresses for ep

In reply to Frank Li

From: Manivannan Sadhasivam <[email protected]>

When eDMA is controlled by the Endpoint (EP), the current logic incorrectly programs the source and destination addresses for read and write. Since the Root complex and Endpoint uses the opposite channels for read/write, fix the issue by finding out the read operation first and program the eDMA accordingly.

Fixes bd96f1b2f43a ("dmaengine: dw-edma: support local dma device transfer semantics")
Fixes e63d79d1ffcd ("dmaengine: Add Synopsys eDMA IP core driver")

---

Change from V1-v3
- Direct pick up from Manivannan

 drivers/dma/dw-edma/dw-edma-core.c | 32 +++++++++++++++++++++++++++++-
 1 file changed, 31 insertions(+), 1 deletion(-)
drivers/dma/dw-edma/dw-edma-core.c +31 -1
index 0cb66434f9e14..3636c48f5df15 100644
@@ -334,6 +334,7 @@ dw_edma_device_transfer(struct dw_edma_transfer *xfer)
 	struct dw_edma_chunk *chunk;
 	struct dw_edma_burst *burst;
 	struct dw_edma_desc *desc;
+	bool read = false;
 	u32 cnt = 0;
 	int i;
 
@@ -424,7 +425,36 @@ dw_edma_device_transfer(struct dw_edma_transfer *xfer)
 		chunk->ll_region.sz += burst->sz;
 		desc->alloc_sz += burst->sz;
 
-		if (chan->dir == EDMA_DIR_WRITE) {
+		/****************************************************************
+		 *
+		 *        Root Complex                           Endpoint
+		 * +-----------------------+             +----------------------+
+		 * |                       |    TX CH    |                      |
+		 * |                       |             |                      |
+		 * |      DEV_TO_MEM       <-------------+     MEM_TO_DEV       |
+		 * |                       |             |                      |
+		 * |                       |             |                      |
+		 * |      MEM_TO_DEV       +------------->     DEV_TO_MEM       |
+		 * |                       |             |                      |
+		 * |                       |    RX CH    |                      |
+		 * +-----------------------+             +----------------------+
+		 *
+		 * If eDMA is controlled by the Root complex, TX channel
+		 * (EDMA_DIR_WRITE) is used for memory read (DEV_TO_MEM) and RX
+		 * channel (EDMA_DIR_READ) is used for memory write (MEM_TO_DEV).
+		 *
+		 * If eDMA is controlled by the endpoint, RX channel
+		 * (EDMA_DIR_READ) is used for memory read (DEV_TO_MEM) and TX
+		 * channel (EDMA_DIR_WRITE) is used for memory write (MEM_TO_DEV).
+		 *
+		 ****************************************************************/
+
+		if ((dir == DMA_DEV_TO_MEM && chan->dir == EDMA_DIR_READ) ||
+		    (dir == DMA_DEV_TO_MEM && chan->dir == EDMA_DIR_WRITE))
+			read = true;
+
+		/* Program the source and destination addresses for DMA read/write */
+		if (read) {
 			burst->sar = src_addr;
 			if (xfer->type == EDMA_XFER_CYCLIC) {
 				burst->dar = xfer->xfer.cyclic.paddr;
Signature · 1 line
2.24.0.rc1
author
#3 lore raw

PATCH v3 4/6 dmaengine: dw-edma: Don't rely on the deprecated "direction" member

In reply to Frank Li

From: Manivannan Sadhasivam <[email protected]>

The "direction" member of the "dma_slave_config" structure is deprecated. The clients no longer use this field to specify the direction of the slave channel. But in the eDMA core, this field is used to differentiate between the Root complex (remote) and Endpoint (local) DMA accesses.

Nevertheless, we can't differentiate between local and remote accesses without a dedicated flag. So let's get rid of the old check and add a new check for verifying the DMA operation between local and remote memory instead.

---
Change from v1 to v3
- direct pick up from Manivannan

 drivers/dma/dw-edma/dw-edma-core.c | 17 ++---------------
 1 file changed, 2 insertions(+), 15 deletions(-)
drivers/dma/dw-edma/dw-edma-core.c +2 -15
index 3636c48f5df15..0635157d260c1 100644
@@ -341,22 +341,9 @@ dw_edma_device_transfer(struct dw_edma_transfer *xfer)
 	if (!chan->configured)
 		return NULL;
 
-	switch (chan->config.direction) {
-	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 */
-		if (dir == DMA_MEM_TO_DEV && chan->dir == EDMA_DIR_WRITE)
-			break;
+	/* eDMA supports only read and write between local and remote memory */
+	if (dir != DMA_DEV_TO_MEM && dir != DMA_MEM_TO_DEV)
 		return NULL;
-	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)
-			break;
-		return NULL;
-	}
 
 	if (xfer->type == EDMA_XFER_CYCLIC) {
 		if (!xfer->xfer.cyclic.len || !xfer->xfer.cyclic.cnt)
Signature · 1 line
2.24.0.rc1
author
#4 lore raw

PATCH v3 5/6 dmaengine: dw-edma: add flags at struct dw_edma_chip

In reply to Frank Li

Allow PCI EP probe DMA locally and prevent use of remote MSI to remote PCI host.

Add option to force 32bit DBI register access even on 64-bit systems. i.MX8 hardware only allowed 32bit register access.

---
Change from v2 to v3
- rework commit message
- Change to DW_EDMA_CHIP_32BIT_DBI
- using DW_EDMA_CHIP_LOCAL control msi
- Apply Bjorn's comments,

	if (!j) {
               control |= DW_EDMA_V0_LIE;
               if (!(chan->chip->flags & DW_EDMA_CHIP_LOCAL))
                               control |= DW_EDMA_V0_RIE;
        }

	if ((chan->chip->flags & DW_EDMA_CHIP_REG32BIT) ||
              !IS_ENABLED(CONFIG_64BIT)) {
          SET_CH_32(...);
          SET_CH_32(...);
       } else {
          SET_CH_64(...);
       }

Change from v1 to v2
- none

 drivers/dma/dw-edma/dw-edma-v0-core.c | 20 ++++++++++++--------
 include/linux/dma/edma.h              |  9 +++++++++
 2 files changed, 21 insertions(+), 8 deletions(-)
drivers/dma/dw-edma/dw-edma-v0-core.c +12 -8
index 6e2f83e31a03a..081cd7997348d 100644
@@ -307,6 +307,7 @@ u32 dw_edma_v0_core_status_abort_int(struct dw_edma_chip *chip, enum dw_edma_dir
 static void dw_edma_v0_core_write_chunk(struct dw_edma_chunk *chunk)
 {
 	struct dw_edma_burst *child;
+	struct dw_edma_chan *chan = chunk->chan;
 	struct dw_edma_v0_lli __iomem *lli;
 	struct dw_edma_v0_llp __iomem *llp;
 	u32 control = 0, i = 0;
@@ -320,9 +321,11 @@ static void dw_edma_v0_core_write_chunk(struct dw_edma_chunk *chunk)
 	j = chunk->bursts_alloc;
 	list_for_each_entry(child, &chunk->burst->list, list) {
 		j--;
-		if (!j)
-			control |= (DW_EDMA_V0_LIE | DW_EDMA_V0_RIE);
-
+		if (!j) {
+			control |= DW_EDMA_V0_LIE;
+			if (!(chan->chip->flags & DW_EDMA_CHIP_LOCAL))
+				control |= DW_EDMA_V0_RIE;
+		}
 		/* Channel control */
 		SET_LL_32(&lli[i].control, control);
 		/* Transfer size */
@@ -420,15 +423,16 @@ void dw_edma_v0_core_start(struct dw_edma_chunk *chunk, bool first)
 		SET_CH_32(chip, chan->dir, chan->id, ch_control1,
 			  (DW_EDMA_V0_CCS | DW_EDMA_V0_LLE));
 		/* Linked list */
-		#ifdef CONFIG_64BIT
-			SET_CH_64(chip, chan->dir, chan->id, llp.reg,
-				  chunk->ll_region.paddr);
-		#else /* CONFIG_64BIT */
+		if ((chan->chip->flags & DW_EDMA_CHIP_32BIT_DBI) ||
+		    !IS_ENABLED(CONFIG_64BIT)) {
 			SET_CH_32(chip, chan->dir, chan->id, llp.lsb,
 				  lower_32_bits(chunk->ll_region.paddr));
 			SET_CH_32(chip, chan->dir, chan->id, llp.msb,
 				  upper_32_bits(chunk->ll_region.paddr));
-		#endif /* CONFIG_64BIT */
+		} else {
+			SET_CH_64(chip, chan->dir, chan->id, llp.reg,
+				  chunk->ll_region.paddr);
+		}
 	}
 	/* Doorbell */
 	SET_RW_32(chip, chan->dir, doorbell,
include/linux/dma/edma.h +9 -0
index fcfbc0f47f83d..4321f6378ef66 100644
@@ -33,6 +33,12 @@ enum dw_edma_map_format {
 	EDMA_MF_HDMA_COMPAT = 0x5
 };
 
+/* Probe EDMA engine locally and prevent generate MSI to host side*/
+#define DW_EDMA_CHIP_LOCAL	BIT(0)
+
+/* Only support 32bit DBI register access */
+#define DW_EDMA_CHIP_32BIT_DBI	BIT(1)
+
 /**
  * struct dw_edma_chip - representation of DesignWare eDMA controller hardware
  * @dev:		 struct device of the eDMA controller
@@ -40,6 +46,8 @@ enum dw_edma_map_format {
  * @nr_irqs:		 total dma irq number
  * reg64bit		 if support 64bit write to register
  * @ops			 DMA channel to IRQ number mapping
+ * @flags		 - DW_EDMA_CHIP_LOCAL
+ *			 - DW_EDMA_CHIP_32BIT_DBI
  * @wr_ch_cnt		 DMA write channel number
  * @rd_ch_cnt		 DMA read channel number
  * @rg_region		 DMA register region
@@ -53,6 +61,7 @@ struct dw_edma_chip {
 	int			id;
 	int			nr_irqs;
 	const struct dw_edma_core_ops   *ops;
+	u32			flags;
 
 	void __iomem		*reg_base;
 
Signature · 1 line
2.24.0.rc1
author
#5 lore raw

PATCH v3 6/6 PCI: endpoint: functions/pci-epf-test: Support PCI controller DMA

In reply to Frank Li

Designware provided DMA support in controller. This enabled use this DMA controller to transfer data.

The whole flow align with standard DMA usage module

1. Using dma_request_channel() and filter function to find correct RX and TX Channel.
2. dmaengine_slave_config() config remote side physcial address.
3. using dmaengine_prep_slave_single() create transfer descriptor
4. tx_submit();
5. dma_async_issue_pending();

Tested at i.MX8DXL platform.

root@imx8qmmek:~# /usr/bin/pcitest -d -w
WRITE ( 102400 bytes):          OKAY
root@imx8qmmek:~# /usr/bin/pcitest -d -r
READ ( 102400 bytes):           OKAY

WRITE => Size: 102400 bytes DMA: YES Time: 0.000180145 seconds Rate: 555108 KB/s READ => Size: 102400 bytes DMA: YES Time: 0.000194397 seconds Rate: 514411 KB/s

READ => Size: 102400 bytes DMA: NO Time: 0.013532597 seconds Rate: 7389 KB/s
WRITE => Size: 102400 bytes DMA: NO Time: 0.000857090 seconds Rate: 116673 KB/s

---

Change from v1 to v3
- none

 drivers/pci/endpoint/functions/pci-epf-test.c | 106 ++++++++++++++++--
 1 file changed, 96 insertions(+), 10 deletions(-)
drivers/pci/endpoint/functions/pci-epf-test.c +96 -10
index 90d84d3bc868f..22ae420c30693 100644
@@ -52,9 +52,11 @@ struct pci_epf_test {
 	enum pci_barno		test_reg_bar;
 	size_t			msix_table_offset;
 	struct delayed_work	cmd_handler;
-	struct dma_chan		*dma_chan;
+	struct dma_chan		*dma_chan_tx;
+	struct dma_chan		*dma_chan_rx;
 	struct completion	transfer_complete;
 	bool			dma_supported;
+	bool			dma_private;
 	const struct pci_epc_features *epc_features;
 };
 
@@ -105,14 +107,17 @@ static void pci_epf_test_dma_callback(void *param)
  */
 static int pci_epf_test_data_transfer(struct pci_epf_test *epf_test,
 				      dma_addr_t dma_dst, dma_addr_t dma_src,
-				      size_t len)
+				      size_t len, dma_addr_t remote,
+				      enum dma_transfer_direction dir)
 {
 	enum dma_ctrl_flags flags = DMA_CTRL_ACK | DMA_PREP_INTERRUPT;
-	struct dma_chan *chan = epf_test->dma_chan;
+	struct dma_chan *chan = (dir == DMA_DEV_TO_MEM) ? epf_test->dma_chan_tx : epf_test->dma_chan_rx;
 	struct pci_epf *epf = epf_test->epf;
 	struct dma_async_tx_descriptor *tx;
 	struct device *dev = &epf->dev;
 	dma_cookie_t cookie;
+	struct dma_slave_config	sconf;
+	dma_addr_t local = (dir == DMA_MEM_TO_DEV) ? dma_src : dma_dst;
 	int ret;
 
 	if (IS_ERR_OR_NULL(chan)) {
@@ -120,7 +125,20 @@ static int pci_epf_test_data_transfer(struct pci_epf_test *epf_test,
 		return -EINVAL;
 	}
 
-	tx = dmaengine_prep_dma_memcpy(chan, dma_dst, dma_src, len, flags);
+	if (epf_test->dma_private) {
+		memset(&sconf, 0, sizeof(sconf));
+		sconf.direction = dir;
+		if (dir == DMA_MEM_TO_DEV)
+			sconf.dst_addr = remote;
+		else
+			sconf.src_addr = remote;
+
+		dmaengine_slave_config(chan, &sconf);
+		tx = dmaengine_prep_slave_single(chan, local, len, dir, flags);
+	} else {
+		tx = dmaengine_prep_dma_memcpy(chan, dma_dst, dma_src, len, flags);
+	}
+
 	if (!tx) {
 		dev_err(dev, "Failed to prepare DMA memcpy\n");
 		return -EIO;
@@ -148,6 +166,23 @@ static int pci_epf_test_data_transfer(struct pci_epf_test *epf_test,
 	return 0;
 }
 
+struct epf_dma_filter {
+	struct device *dev;
+	u32 dma_mask;
+};
+
+static bool epf_dma_filter_fn(struct dma_chan *chan, void *node)
+{
+	struct epf_dma_filter *filter = node;
+	struct dma_slave_caps caps;
+
+	memset(&caps, 0, sizeof(caps));
+	dma_get_slave_caps(chan, &caps);
+
+	return chan->device->dev == filter->dev
+		&& (filter->dma_mask & caps.directions);
+}
+
 /**
  * pci_epf_test_init_dma_chan() - Function to initialize EPF test DMA channel
  * @epf_test: the EPF test device that performs data transfer operation
@@ -160,8 +195,42 @@ static int pci_epf_test_init_dma_chan(struct pci_epf_test *epf_test)
 	struct device *dev = &epf->dev;
 	struct dma_chan *dma_chan;
 	dma_cap_mask_t mask;
+	struct epf_dma_filter filter;
 	int ret;
 
+	filter.dev = epf->epc->dev.parent;
+	filter.dma_mask = BIT(DMA_DEV_TO_MEM);
+
+	dma_cap_zero(mask);
+	dma_cap_set(DMA_SLAVE, mask);
+	dma_chan = dma_request_channel(mask, epf_dma_filter_fn, &filter);
+	if (IS_ERR(dma_chan)) {
+		dev_info(dev, "Failure get built-in DMA channel, fail back to try allocate general DMA channel\n");
+		goto fail_back_tx;
+	}
+
+	epf_test->dma_chan_rx = dma_chan;
+
+	filter.dma_mask = BIT(DMA_MEM_TO_DEV);
+	dma_chan = dma_request_channel(mask, epf_dma_filter_fn, &filter);
+
+	if (IS_ERR(dma_chan)) {
+		dev_info(dev, "Failure get built-in DMA channel, fail back to try allocate general DMA channel\n");
+		goto fail_back_rx;
+	}
+
+	epf_test->dma_chan_tx = dma_chan;
+	epf_test->dma_private = true;
+
+	init_completion(&epf_test->transfer_complete);
+
+	return 0;
+
+fail_back_rx:
+	dma_release_channel(epf_test->dma_chan_rx);
+	epf_test->dma_chan_tx = NULL;
+
+fail_back_tx:
 	dma_cap_zero(mask);
 	dma_cap_set(DMA_MEMCPY, mask);
 
@@ -174,7 +243,7 @@ static int pci_epf_test_init_dma_chan(struct pci_epf_test *epf_test)
 	}
 	init_completion(&epf_test->transfer_complete);
 
-	epf_test->dma_chan = dma_chan;
+	epf_test->dma_chan_tx = epf_test->dma_chan_rx = dma_chan;
 
 	return 0;
 }
@@ -190,8 +259,17 @@ static void pci_epf_test_clean_dma_chan(struct pci_epf_test *epf_test)
 	if (!epf_test->dma_supported)
 		return;
 
-	dma_release_channel(epf_test->dma_chan);
-	epf_test->dma_chan = NULL;
+	dma_release_channel(epf_test->dma_chan_tx);
+	if (epf_test->dma_chan_tx == epf_test->dma_chan_rx) {
+		epf_test->dma_chan_tx = NULL;
+		epf_test->dma_chan_rx = NULL;
+		return;
+	}
+
+	dma_release_channel(epf_test->dma_chan_rx);
+	epf_test->dma_chan_rx = NULL;
+
+	return;
 }
 
 static void pci_epf_test_print_rate(const char *ops, u64 size,
@@ -280,8 +358,14 @@ static int pci_epf_test_copy(struct pci_epf_test *epf_test)
 			goto err_map_addr;
 		}
 
+		if (epf_test->dma_private) {
+			dev_err(dev, "Cannot transfer data using DMA\n");
+			ret = -EINVAL;
+			goto err_map_addr;
+		}
+
 		ret = pci_epf_test_data_transfer(epf_test, dst_phys_addr,
-						 src_phys_addr, reg->size);
+						 src_phys_addr, reg->size, 0, DMA_MEM_TO_MEM);
 		if (ret)
 			dev_err(dev, "Data transfer failed\n");
 	} else {
@@ -363,7 +447,8 @@ static int pci_epf_test_read(struct pci_epf_test *epf_test)
 
 		ktime_get_ts64(&start);
 		ret = pci_epf_test_data_transfer(epf_test, dst_phys_addr,
-						 phys_addr, reg->size);
+						 phys_addr, reg->size,
+						 reg->src_addr, DMA_DEV_TO_MEM);
 		if (ret)
 			dev_err(dev, "Data transfer failed\n");
 		ktime_get_ts64(&end);
@@ -453,8 +538,9 @@ static int pci_epf_test_write(struct pci_epf_test *epf_test)
 		}
 
 		ktime_get_ts64(&start);
+
 		ret = pci_epf_test_data_transfer(epf_test, phys_addr,
-						 src_phys_addr, reg->size);
+						 src_phys_addr, reg->size, reg->dst_addr, DMA_MEM_TO_DEV);
 		if (ret)
 			dev_err(dev, "Data transfer failed\n");
 		ktime_get_ts64(&end);
Signature · 1 line
2.24.0.rc1