[RFC PATCH v4 06/38] NTB: epf: Add mwN_offset support and config region versioning

Introduce new mwN_offset configfs attributes to specify memory window
offsets. This enables mapping multiple windows into a single BAR at
arbitrary offsets, improving layout flexibility.

Extend the control register region and add a 32-bit config version
field. Reuse the unused NTB_EPF_TOPOLOGY offset (0x0C) for a version
field. The endpoint function driver writes 1 (NTB_EPF_CTRL_VERSION_V1),
and ntb_hw_epf reads it at probe time and refuses to bind to unknown
versions.

Compatibility matrix:

            | EP v1 | EP legacy
  ----------+-------+----------
  RC v1     | v1    | legacy
  RC legacy | ? (*) | legacy

(*) An unpatched (legacy) RC may misinterpret the paired EP's intention
    and program MW layout incorrectly when offsets are used.

Signed-off-by: Koichiro Den <[email protected]>
---
 drivers/ntb/hw/epf/ntb_hw_epf.c               |  60 +++++++-
 drivers/pci/endpoint/functions/pci-epf-vntb.c | 136 ++++++++++++++++--
 2 files changed, 176 insertions(+), 20 deletions(-)

diff --git a/drivers/ntb/hw/epf/ntb_hw_epf.c b/drivers/ntb/hw/epf/ntb_hw_epf.c
index 9935da48a52e..4b3fa996219a 100644
--- a/drivers/ntb/hw/epf/ntb_hw_epf.c
+++ b/drivers/ntb/hw/epf/ntb_hw_epf.c
@@ -30,18 +30,27 @@
 #define NTB_EPF_LINK_STATUS	0x0A
 #define LINK_STATUS_UP		BIT(0)
 
-#define NTB_EPF_TOPOLOGY	0x0C
+/*
+ * Legacy unused NTB_EPF_TOPOLOGY (0x0c) is repurposed as a control version
+ * field
+ */
+#define NTB_EPF_CTRL_VERSION	0x0C
 #define NTB_EPF_LOWER_ADDR	0x10
 #define NTB_EPF_UPPER_ADDR	0x14
 #define NTB_EPF_LOWER_SIZE	0x18
 #define NTB_EPF_UPPER_SIZE	0x1C
 #define NTB_EPF_MW_COUNT	0x20
-#define NTB_EPF_MW1_OFFSET	0x24
+#define NTB_EPF_MW1_OFFSET	0x24 /* used by legacy (version=0) only */
 #define NTB_EPF_SPAD_OFFSET	0x28
 #define NTB_EPF_SPAD_COUNT	0x2C
 #define NTB_EPF_DB_ENTRY_SIZE	0x30
 #define NTB_EPF_DB_DATA(n)	(0x34 + (n) * 4)
 #define NTB_EPF_DB_OFFSET(n)	(0xB4 + (n) * 4)
+#define NTB_EPF_MW_OFFSET(n)	(0x134 + (n) * 4)
+#define NTB_EPF_MW_SIZE(n)	(0x144 + (n) * 4)
+
+#define NTB_EPF_CTRL_VERSION_LEGACY	0
+#define NTB_EPF_CTRL_VERSION_V1		1
 
 #define NTB_EPF_MIN_DB_COUNT	3
 #define NTB_EPF_MAX_DB_COUNT	31
@@ -451,11 +460,22 @@ static int ntb_epf_peer_mw_get_addr(struct ntb_dev *ntb, int idx,
 				    phys_addr_t *base, resource_size_t *size)
 {
 	struct ntb_epf_dev *ndev = ntb_ndev(ntb);
-	u32 offset = 0;
+	resource_size_t bar_sz;
+	u32 offset, sz, ver;
 	int bar;
 
-	if (idx == 0)
-		offset = readl(ndev->ctrl_reg + NTB_EPF_MW1_OFFSET);
+	ver = readl(ndev->ctrl_reg + NTB_EPF_CTRL_VERSION);
+	if (ver == NTB_EPF_CTRL_VERSION_LEGACY) {
+		/* Legacy layout: only MW1 offset exists, and there is no MW_SIZE[] */
+		if (idx == 0)
+			offset = readl(ndev->ctrl_reg + NTB_EPF_MW1_OFFSET);
+		else
+			offset = 0;
+		sz = 0;
+	} else {
+		offset = readl(ndev->ctrl_reg + NTB_EPF_MW_OFFSET(idx));
+		sz = readl(ndev->ctrl_reg + NTB_EPF_MW_SIZE(idx));
+	}
 
 	bar = ntb_epf_mw_to_bar(ndev, idx);
 	if (bar < 0)
@@ -464,8 +484,11 @@ static int ntb_epf_peer_mw_get_addr(struct ntb_dev *ntb, int idx,
 	if (base)
 		*base = pci_resource_start(ndev->ntb.pdev, bar) + offset;
 
-	if (size)
-		*size = pci_resource_len(ndev->ntb.pdev, bar) - offset;
+	if (size) {
+		bar_sz = pci_resource_len(ndev->ntb.pdev, bar);
+		*size = sz ? min_t(resource_size_t, sz, bar_sz - offset)
+			   : (bar_sz > offset ? bar_sz - offset : 0);
+	}
 
 	return 0;
 }
@@ -547,6 +570,25 @@ static inline void ntb_epf_init_struct(struct ntb_epf_dev *ndev,
 	ndev->ntb.ops = &ntb_epf_ops;
 }
 
+static int ntb_epf_check_version(struct ntb_epf_dev *ndev)
+{
+	struct device *dev = ndev->dev;
+	u32 ver;
+
+	ver = readl(ndev->ctrl_reg + NTB_EPF_CTRL_VERSION);
+
+	switch (ver) {
+	case NTB_EPF_CTRL_VERSION_LEGACY:
+	case NTB_EPF_CTRL_VERSION_V1:
+		break;
+	default:
+		dev_err(dev, "Unsupported NTB EPF version %u\n", ver);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static int ntb_epf_init_dev(struct ntb_epf_dev *ndev)
 {
 	struct device *dev = ndev->dev;
@@ -696,6 +738,10 @@ static int ntb_epf_pci_probe(struct pci_dev *pdev,
 		return ret;
 	}
 
+	ret = ntb_epf_check_version(ndev);
+	if (ret)
+		return ret;
+
 	ret = ntb_epf_init_dev(ndev);
 	if (ret) {
 		dev_err(dev, "Failed to init device\n");
diff --git a/drivers/pci/endpoint/functions/pci-epf-vntb.c b/drivers/pci/endpoint/functions/pci-epf-vntb.c
index c08d349db350..4927faa28255 100644
--- a/drivers/pci/endpoint/functions/pci-epf-vntb.c
+++ b/drivers/pci/endpoint/functions/pci-epf-vntb.c
@@ -39,6 +39,7 @@
 #include <linux/atomic.h>
 #include <linux/delay.h>
 #include <linux/io.h>
+#include <linux/log2.h>
 #include <linux/module.h>
 #include <linux/slab.h>
 
@@ -61,6 +62,7 @@ static struct workqueue_struct *kpcintb_workqueue;
 
 #define LINK_STATUS_UP			BIT(0)
 
+#define CTRL_VERSION			1
 #define SPAD_COUNT			64
 #define DB_COUNT			4
 #define NTB_MW_OFFSET			2
@@ -107,7 +109,7 @@ struct epf_ntb_ctrl {
 	u32 argument;
 	u16 command_status;
 	u16 link_status;
-	u32 topology;
+	u32 version;
 	u64 addr;
 	u64 size;
 	u32 num_mws;
@@ -117,6 +119,8 @@ struct epf_ntb_ctrl {
 	u32 db_entry_size;
 	u32 db_data[MAX_DB_COUNT];
 	u32 db_offset[MAX_DB_COUNT];
+	u32 mw_offset[MAX_MW];
+	u32 mw_size[MAX_MW];
 } __packed;
 
 struct epf_ntb {
@@ -128,6 +132,7 @@ struct epf_ntb {
 	u32 db_count;
 	u32 spad_count;
 	u64 mws_size[MAX_MW];
+	u64 mws_offset[MAX_MW];
 	atomic64_t db;
 	u32 vbus_number;
 	u16 vntb_pid;
@@ -460,10 +465,13 @@ static int epf_ntb_config_spad_bar_alloc(struct epf_ntb *ntb)
 	ntb->reg = base;
 
 	ctrl = ntb->reg;
+	ctrl->version = CTRL_VERSION;
 	ctrl->spad_offset = ctrl_size;
 
 	ctrl->spad_count = spad_count;
 	ctrl->num_mws = ntb->num_mws;
+	memset(ctrl->mw_offset, 0, sizeof(ctrl->mw_offset));
+	memset(ctrl->mw_size, 0, sizeof(ctrl->mw_size));
 	ntb->spad_size = spad_size;
 
 	ctrl->db_entry_size = sizeof(u32);
@@ -695,15 +703,31 @@ static void epf_ntb_db_bar_clear(struct epf_ntb *ntb)
  */
 static int epf_ntb_mw_bar_init(struct epf_ntb *ntb)
 {
+	struct device *dev = &ntb->epf->dev;
+	u64 bar_ends[BAR_5 + 1] = { 0 };
+	unsigned long bars_used = 0;
+	enum pci_barno barno;
+	u64 off, size, end;
 	int ret = 0;
 	int i;
-	u64 size;
-	enum pci_barno barno;
-	struct device *dev = &ntb->epf->dev;
 
 	for (i = 0; i < ntb->num_mws; i++) {
-		size = ntb->mws_size[i];
 		barno = ntb->epf_ntb_bar[BAR_MW1 + i];
+		off = ntb->mws_offset[i];
+		size = ntb->mws_size[i];
+		end = off + size;
+		if (end > bar_ends[barno])
+			bar_ends[barno] = end;
+		bars_used |= BIT(barno);
+	}
+
+	for (barno = BAR_0; barno <= BAR_5; barno++) {
+		if (!(bars_used & BIT(barno)))
+			continue;
+		if (bar_ends[barno] < SZ_4K)
+			size = SZ_4K;
+		else
+			size = roundup_pow_of_two(bar_ends[barno]);
 
 		ntb->epf->bar[barno].barno = barno;
 		ntb->epf->bar[barno].size = size;
@@ -719,8 +743,12 @@ static int epf_ntb_mw_bar_init(struct epf_ntb *ntb)
 				      &ntb->epf->bar[barno]);
 		if (ret) {
 			dev_err(dev, "MW set failed\n");
-			goto err_alloc_mem;
+			goto err_set_bar;
 		}
+	}
+
+	for (i = 0; i < ntb->num_mws; i++) {
+		size = ntb->mws_size[i];
 
 		/* Allocate EPC outbound memory windows to vpci vntb device */
 		ntb->vpci_mw_addr[i] = pci_epc_mem_alloc_addr(ntb->epf->epc,
@@ -729,19 +757,31 @@ static int epf_ntb_mw_bar_init(struct epf_ntb *ntb)
 		if (!ntb->vpci_mw_addr[i]) {
 			ret = -ENOMEM;
 			dev_err(dev, "Failed to allocate source address\n");
-			goto err_set_bar;
+			goto err_alloc_mem;
 		}
 	}
 
+	for (i = 0; i < ntb->num_mws; i++) {
+		ntb->reg->mw_offset[i] = (u32)ntb->mws_offset[i];
+		ntb->reg->mw_size[i] = (u32)ntb->mws_size[i];
+	}
+
 	return ret;
 
-err_set_bar:
-	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);
+	while (--i >= 0)
+		pci_epc_mem_free_addr(ntb->epf->epc,
+				      ntb->vpci_mw_phy[i],
+				      ntb->vpci_mw_addr[i],
+				      ntb->mws_size[i]);
+err_set_bar:
+	while (--barno >= BAR_0)
+		if (bars_used & BIT(barno))
+			pci_epc_clear_bar(ntb->epf->epc,
+					  ntb->epf->func_no,
+					  ntb->epf->vfunc_no,
+					  &ntb->epf->bar[barno]);
+
 	return ret;
 }
 
@@ -1034,6 +1074,60 @@ static ssize_t epf_ntb_##_name##_store(struct config_item *item,	\
 	return len;							\
 }
 
+#define EPF_NTB_MW_OFF_R(_name)						\
+static ssize_t epf_ntb_##_name##_show(struct config_item *item,		\
+				      char *page)			\
+{									\
+	struct config_group *group = to_config_group(item);		\
+	struct epf_ntb *ntb = to_epf_ntb(group);			\
+	struct device *dev = &ntb->epf->dev;				\
+	int win_no, idx;						\
+									\
+	if (sscanf(#_name, "mw%d_offset", &win_no) != 1)		\
+		return -EINVAL;						\
+									\
+	idx = win_no - 1;						\
+	if (idx < 0 || idx >= ntb->num_mws) {				\
+		dev_err(dev, "MW%d out of range (num_mws=%d)\n",	\
+			win_no, ntb->num_mws);				\
+		return -EINVAL;						\
+	}								\
+									\
+	idx = array_index_nospec(idx, ntb->num_mws);			\
+	return sprintf(page, "%llu\n", ntb->mws_offset[idx]);		\
+}
+
+#define EPF_NTB_MW_OFF_W(_name)						\
+static ssize_t epf_ntb_##_name##_store(struct config_item *item,	\
+				       const char *page, size_t len)	\
+{									\
+	struct config_group *group = to_config_group(item);		\
+	struct epf_ntb *ntb = to_epf_ntb(group);			\
+	struct device *dev = &ntb->epf->dev;				\
+	int win_no, idx;						\
+	u64 val;							\
+	int ret;							\
+									\
+	ret = kstrtou64(page, 0, &val);					\
+	if (ret)							\
+		return ret;						\
+									\
+	if (sscanf(#_name, "mw%d_offset", &win_no) != 1)		\
+		return -EINVAL;						\
+									\
+	idx = win_no - 1;						\
+	if (idx < 0 || idx >= ntb->num_mws) {				\
+		dev_err(dev, "MW%d out of range (num_mws=%d)\n",	\
+			win_no, ntb->num_mws);				\
+		return -EINVAL;						\
+	}								\
+									\
+	idx = array_index_nospec(idx, ntb->num_mws);			\
+	ntb->mws_offset[idx] = val;					\
+									\
+	return len;							\
+}
+
 #define EPF_NTB_BAR_R(_name, _id)					\
 	static ssize_t epf_ntb_##_name##_show(struct config_item *item,	\
 					      char *page)		\
@@ -1104,6 +1198,14 @@ EPF_NTB_MW_R(mw3)
 EPF_NTB_MW_W(mw3)
 EPF_NTB_MW_R(mw4)
 EPF_NTB_MW_W(mw4)
+EPF_NTB_MW_OFF_R(mw1_offset)
+EPF_NTB_MW_OFF_W(mw1_offset)
+EPF_NTB_MW_OFF_R(mw2_offset)
+EPF_NTB_MW_OFF_W(mw2_offset)
+EPF_NTB_MW_OFF_R(mw3_offset)
+EPF_NTB_MW_OFF_W(mw3_offset)
+EPF_NTB_MW_OFF_R(mw4_offset)
+EPF_NTB_MW_OFF_W(mw4_offset)
 EPF_NTB_BAR_R(ctrl_bar, BAR_CONFIG)
 EPF_NTB_BAR_W(ctrl_bar, BAR_CONFIG)
 EPF_NTB_BAR_R(db_bar, BAR_DB)
@@ -1124,6 +1226,10 @@ CONFIGFS_ATTR(epf_ntb_, mw1);
 CONFIGFS_ATTR(epf_ntb_, mw2);
 CONFIGFS_ATTR(epf_ntb_, mw3);
 CONFIGFS_ATTR(epf_ntb_, mw4);
+CONFIGFS_ATTR(epf_ntb_, mw1_offset);
+CONFIGFS_ATTR(epf_ntb_, mw2_offset);
+CONFIGFS_ATTR(epf_ntb_, mw3_offset);
+CONFIGFS_ATTR(epf_ntb_, mw4_offset);
 CONFIGFS_ATTR(epf_ntb_, vbus_number);
 CONFIGFS_ATTR(epf_ntb_, vntb_pid);
 CONFIGFS_ATTR(epf_ntb_, vntb_vid);
@@ -1142,6 +1248,10 @@ static struct configfs_attribute *epf_ntb_attrs[] = {
 	&epf_ntb_attr_mw2,
 	&epf_ntb_attr_mw3,
 	&epf_ntb_attr_mw4,
+	&epf_ntb_attr_mw1_offset,
+	&epf_ntb_attr_mw2_offset,
+	&epf_ntb_attr_mw3_offset,
+	&epf_ntb_attr_mw4_offset,
 	&epf_ntb_attr_vbus_number,
 	&epf_ntb_attr_vntb_pid,
 	&epf_ntb_attr_vntb_vid,
-- 
2.51.0