[PATCH v4 5/7] PCI: endpoint: pci-epf-vntb: Allow DMA and MW to share a BAR

[Koichiro Den]

Some endpoint configurations have no spare BAR for DMA resources. Allow
dma_bar to select an MW BAR and place the DMA ranges after that MW.

DMA submaps have fixed BAR offsets, so a shared MW translation must cover
its configured size. Report the configured MW size as its size alignment
and require it to be a power of two.

BAR sharing requires ntb_hw_epf to parse the DMA extension, since older
versions treat the whole BAR as an MW.

Signed-off-by: Koichiro Den <den@xxxxxxxxxxxxx>
---
Changes in v4:
  - Keep the shared BAR mapping installed until EPF unbind. (Sashiko)
  - Advertise and validate the full-size shared MW translation.
  - Reject dma_bar values that overlap the control or doorbell BAR.

 drivers/pci/endpoint/functions/pci-epf-vntb.c | 162 +++++++++++++-----
 1 file changed, 117 insertions(+), 45 deletions(-)

diff --git a/drivers/pci/endpoint/functions/pci-epf-vntb.c b/drivers/pci/endpoint/functions/pci-epf-vntb.c
index ad34530642fc..e800a317f059 100644
--- a/drivers/pci/endpoint/functions/pci-epf-vntb.c
+++ b/drivers/pci/endpoint/functions/pci-epf-vntb.c
@@ -44,6 +44,7 @@
 #include <linux/dmaengine.h>
 #include <linux/io.h>
 #include <linux/module.h>
+#include <linux/mutex.h>
 #include <linux/overflow.h>
 #include <linux/slab.h>
 
@@ -167,12 +168,13 @@ struct epf_ntb_ctrl {
 } __packed;
 
 struct epf_ntb_dma {
+	struct mutex lock; /* Serialize DMA submap and MW updates */
 	struct epf_ntb_dma_ctrl ctrl;
 	struct dma_chan *dchan[EDMA_MAX_RD_CH];
 	void *bar_scratch;
 	dma_addr_t bar_scratch_phys;
 	size_t bar_scratch_size;
-	struct pci_epf_bar_submap submap[EDMA_MAX_RD_CH + 2];
+	struct pci_epf_bar_submap submap[EDMA_MAX_RD_CH + 3];
 	struct pci_epf_bar_submap *reg_submap;
 	unsigned int num_submap;
 	u16 rd_ch_cnt;
@@ -273,18 +275,23 @@ static bool epf_ntb_is_bar_used(struct epf_ntb *ntb,
 	return false;
 }
 
-static int epf_ntb_dma_validate_bar(struct epf_ntb *ntb,
-				    const struct pci_epc_features *features)
+static u64 epf_ntb_dma_bar_offset(struct epf_ntb *ntb, enum pci_barno barno)
 {
-	enum pci_barno barno = ntb->epf_ntb_bar[BAR_DMA];
+	unsigned int i;
 
-	if (epf_ntb_is_bar_used(ntb, barno) ||
-	    pci_epc_get_next_free_bar(features, barno) != barno)
-		return -EINVAL;
+	for (i = 0; i < ntb->num_mws; i++)
+		if (ntb->epf_ntb_bar[BAR_MW1 + i] == barno)
+			return ntb->mws_size[i];
 
 	return 0;
 }
 
+static bool epf_ntb_dma_shares_bar(struct epf_ntb *ntb, enum pci_barno barno)
+{
+	return ntb->dma && ntb->dma->num_submap &&
+	       ntb->epf_ntb_bar[BAR_DMA] == barno;
+}
+
 struct epf_ntb_dma_filter {
 	struct device *dev;
 	int chan_id;
@@ -437,6 +444,7 @@ static int epf_ntb_dw_edma_collect(struct epf_ntb *ntb,
 	unsigned int i;
 	size_t align;
 	u32 next = 0;
+	u64 offset;
 	int ret;
 
 	if (ctrl->u.dma_ctrl.reg_layout_data != EDMA_MF_EDMA_UNROLL)
@@ -471,9 +479,28 @@ static int epf_ntb_dw_edma_collect(struct epf_ntb *ntb,
 		if (!features->subrange_mapping ||
 		    !features->dynamic_inbound_mapping)
 			return -EOPNOTSUPP;
-		ret = epf_ntb_dma_validate_bar(ntb, features);
-		if (ret)
-			return ret;
+		if (barno == ntb->epf_ntb_bar[BAR_CONFIG] ||
+		    barno == ntb->epf_ntb_bar[BAR_DB])
+			return -EINVAL;
+
+		offset = epf_ntb_dma_bar_offset(ntb, barno);
+		if (!offset &&
+		    (epf_ntb_is_bar_used(ntb, barno) ||
+		     pci_epc_get_next_free_bar(features, barno) != barno))
+			return -EINVAL;
+		if (offset > U32_MAX)
+			return -EOVERFLOW;
+		dma->ctrl.submap.offset = offset;
+		next = offset;
+		if (next) {
+			/*
+			 * submap[0] covers the MW prefix. Keep its temporary
+			 * target at address 0 until the MW translation is
+			 * installed.
+			 */
+			dma->submap[0].size = next;
+			dma->num_submap = 1;
+		}
 	}
 
 	dma->ctrl.magic = EPF_NTB_DMA_MAGIC;
@@ -502,7 +529,7 @@ static int epf_ntb_dw_edma_collect(struct epf_ntb *ntb,
 	}
 	if (dma->num_submap) {
 		dma->ctrl.submap.bar = barno;
-		dma->ctrl.submap.size = next;
+		dma->ctrl.submap.size = next - dma->ctrl.submap.offset;
 	}
 
 	dma_dev = ntb->epf->epc->dev.parent;
@@ -572,6 +599,8 @@ static int epf_ntb_dma_collect(struct epf_ntb *ntb)
 	if (!dma)
 		return -ENOMEM;
 
+	mutex_init(&dma->lock);
+
 	switch (ctrl->u.dma_ctrl.reg_layout) {
 	case PCI_EPC_AUX_DMA_REG_LAYOUT_DW_EDMA:
 		ret = epf_ntb_dw_edma_collect(ntb, dma, ctrl, resources, count);
@@ -625,24 +654,28 @@ static void epf_ntb_dma_release(struct epf_ntb *ntb, bool quiesce)
 	ntb->dma = NULL;
 }
 
-static int epf_ntb_dma_set_bar(struct epf_ntb *ntb)
+static int epf_ntb_dma_set_bar_locked(struct epf_ntb *ntb,
+				      const dma_addr_t *mw_addr)
 {
 	struct pci_epf_bar_submap *old_submap;
 	struct epf_ntb_dma *dma = ntb->dma;
-	struct pci_epf_bar *bar;
 	unsigned int old_num_submap;
+	struct pci_epf_bar *bar;
+	dma_addr_t old_mw_addr;
 	int restore, ret;
-
-	if (!dma || !dma->num_submap)
-		return 0;
+	lockdep_assert_held(&dma->lock);
 
 	bar = &ntb->epf->bar[ntb->epf_ntb_bar[BAR_DMA]];
-	if (bar->submap == dma->submap &&
+	if (!mw_addr && bar->submap == dma->submap &&
 	    bar->num_submap == dma->num_submap)
 		return 0;
 
 	old_submap = bar->submap;
 	old_num_submap = bar->num_submap;
+	if (mw_addr) {
+		old_mw_addr = dma->submap[0].phys_addr;
+		dma->submap[0].phys_addr = *mw_addr;
+	}
 	bar->submap = dma->submap;
 	bar->num_submap = dma->num_submap;
 
@@ -652,17 +685,31 @@ static int epf_ntb_dma_set_bar(struct epf_ntb *ntb)
 		return 0;
 
 	/* A failed dynamic update may have already removed the old mapping. */
+	if (mw_addr)
+		dma->submap[0].phys_addr = old_mw_addr;
 	bar->submap = old_submap;
 	bar->num_submap = old_num_submap;
 	restore = pci_epc_set_bar(ntb->epf->epc, ntb->epf->func_no,
 				  ntb->epf->vfunc_no, bar);
 	if (restore)
 		dev_warn(&ntb->epf->dev,
-			 "failed to restore DMA BAR mapping: %d\n", restore);
+			 "failed to restore DMA/MW BAR mapping: %d\n", restore);
 
 	return ret;
 }
 
+static int epf_ntb_dma_set_bar(struct epf_ntb *ntb)
+{
+	struct epf_ntb_dma *dma = ntb->dma;
+
+	if (!dma || !dma->num_submap)
+		return 0;
+
+	guard(mutex)(&dma->lock);
+
+	return epf_ntb_dma_set_bar_locked(ntb, NULL);
+}
+
 /**
  * epf_ntb_configure_mw() - Configure the Outbound Address Space for VHOST
  *   to access the memory window of HOST
@@ -1205,6 +1252,7 @@ static int epf_ntb_dma_bar_init(struct epf_ntb *ntb)
 	struct pci_epf_bar *bar;
 	enum pci_barno barno;
 	size_t backing_size;
+	unsigned int i;
 	u32 mapped_size;
 	int ret;
 
@@ -1214,7 +1262,13 @@ static int epf_ntb_dma_bar_init(struct epf_ntb *ntb)
 		return -EOPNOTSUPP;
 
 	barno = ntb->epf_ntb_bar[BAR_DMA];
-	mapped_size = dma->ctrl.submap.size;
+	for (i = 0; i < ntb->num_mws; i++) {
+		if (ntb->epf_ntb_bar[BAR_MW1 + i] == barno &&
+		    !is_power_of_2(ntb->mws_size[i]))
+			return -EINVAL;
+	}
+
+	mapped_size = dma->ctrl.submap.offset + dma->ctrl.submap.size;
 	/*
 	 * Submaps cannot be installed until the host assigns the BAR address.
 	 * Use address 0 for the temporary BAR Match Mode mapping, as is done
@@ -1315,6 +1369,7 @@ static void epf_ntb_db_bar_clear(struct epf_ntb *ntb)
  */
 static int epf_ntb_mw_bar_init(struct epf_ntb *ntb)
 {
+	bool shared;
 	int ret = 0;
 	int i;
 	u64 size;
@@ -1324,22 +1379,25 @@ static int epf_ntb_mw_bar_init(struct epf_ntb *ntb)
 	for (i = 0; i < ntb->num_mws; i++) {
 		size = ntb->mws_size[i];
 		barno = ntb->epf_ntb_bar[BAR_MW1 + i];
-
-		ntb->epf->bar[barno].barno = barno;
-		ntb->epf->bar[barno].size = size;
-		ntb->epf->bar[barno].addr = NULL;
-		ntb->epf->bar[barno].phys_addr = 0;
-		ntb->epf->bar[barno].flags |= upper_32_bits(size) ?
-				PCI_BASE_ADDRESS_MEM_TYPE_64 :
-				PCI_BASE_ADDRESS_MEM_TYPE_32;
-
-		ret = pci_epc_set_bar(ntb->epf->epc,
-				      ntb->epf->func_no,
-				      ntb->epf->vfunc_no,
-				      &ntb->epf->bar[barno]);
-		if (ret) {
-			dev_err(dev, "MW set failed\n");
-			goto err_alloc_mem;
+		shared = epf_ntb_dma_shares_bar(ntb, barno);
+
+		if (!shared) {
+			ntb->epf->bar[barno].barno = barno;
+			ntb->epf->bar[barno].size = size;
+			ntb->epf->bar[barno].addr = NULL;
+			ntb->epf->bar[barno].phys_addr = 0;
+			ntb->epf->bar[barno].flags |= upper_32_bits(size) ?
+					PCI_BASE_ADDRESS_MEM_TYPE_64 :
+					PCI_BASE_ADDRESS_MEM_TYPE_32;
+
+			ret = pci_epc_set_bar(ntb->epf->epc,
+					      ntb->epf->func_no,
+					      ntb->epf->vfunc_no,
+					      &ntb->epf->bar[barno]);
+			if (ret) {
+				dev_err(dev, "MW set failed\n");
+				goto err_alloc_mem;
+			}
 		}
 
 		/* Allocate EPC outbound memory windows to vpci vntb device */
@@ -1356,10 +1414,11 @@ static int epf_ntb_mw_bar_init(struct epf_ntb *ntb)
 	return ret;
 
 err_set_bar:
-	pci_epc_clear_bar(ntb->epf->epc,
-			  ntb->epf->func_no,
-			  ntb->epf->vfunc_no,
-			  &ntb->epf->bar[barno]);
+	if (!shared)
+		pci_epc_clear_bar(ntb->epf->epc,
+				  ntb->epf->func_no,
+				  ntb->epf->vfunc_no,
+				  &ntb->epf->bar[barno]);
 err_alloc_mem:
 	epf_ntb_mw_bar_clear(ntb, i);
 	return ret;
@@ -1377,10 +1436,11 @@ static void epf_ntb_mw_bar_clear(struct epf_ntb *ntb, int num_mws)
 
 	for (i = 0; i < num_mws; i++) {
 		barno = ntb->epf_ntb_bar[BAR_MW1 + i];
-		pci_epc_clear_bar(ntb->epf->epc,
-				  ntb->epf->func_no,
-				  ntb->epf->vfunc_no,
-				  &ntb->epf->bar[barno]);
+		if (!epf_ntb_dma_shares_bar(ntb, barno))
+			pci_epc_clear_bar(ntb->epf->epc,
+					  ntb->epf->func_no,
+					  ntb->epf->vfunc_no,
+					  &ntb->epf->bar[barno]);
 
 		pci_epc_mem_free_addr(ntb->epf->epc,
 				      ntb->vpci_mw_phy[i],
@@ -1982,6 +2042,16 @@ static int vntb_epf_mw_set_trans(struct ntb_dev *ndev, int pidx, int idx,
 	dev = &ndev->dev;
 	barno = ntb->epf_ntb_bar[BAR_MW1 + idx];
 	epf_bar = &ntb->epf->bar[barno];
+	if (epf_ntb_dma_shares_bar(ntb, barno)) {
+		/* DMA submaps start after the configured MW size. */
+		if (size != ntb->mws_size[idx])
+			return -EINVAL;
+
+		guard(mutex)(&ntb->dma->lock);
+
+		return epf_ntb_dma_set_bar_locked(ntb, &addr);
+	}
+
 	epf_bar->phys_addr = addr;
 	epf_bar->barno = barno;
 	epf_bar->size = size;
@@ -2159,15 +2229,17 @@ static int vntb_epf_mw_get_align(struct ntb_dev *ndev, int pidx, int idx,
 			resource_size_t *size_max)
 {
 	struct epf_ntb *ntb = ntb_ndev(ndev);
+	enum pci_barno barno = ntb->epf_ntb_bar[BAR_MW1 + idx];
+	u64 size = ntb->mws_size[idx];
 
 	if (addr_align)
 		*addr_align = SZ_4K;
 
 	if (size_align)
-		*size_align = 1;
+		*size_align = epf_ntb_dma_shares_bar(ntb, barno) ? size : 1;
 
 	if (size_max)
-		*size_max = ntb->mws_size[idx];
+		*size_max = size;
 
 	return 0;
 }
-- 
2.51.0