[dpdk-dev] [RFC v3 2/6] bus/pci: avoid depending on private value in kernel source

[Chenbo Xia <chenbo.xia@intel.com>]

From: Tiwei Bie <tiwei.bie@intel.com>

The value 40 used in VFIO_GET_REGION_ADDR() is a private value
(VFIO_PCI_OFFSET_SHIFT) defined in Linux kernel source [1]. It
is not part of VFIO API, and we should not depend on it.

[1] https://github.com/torvalds/linux/blob/v5.12/drivers/vfio/pci/vfio_pci_private.h

Signed-off-by: Tiwei Bie <tiwei.bie@intel.com>
---
 drivers/bus/pci/linux/pci.c      |   4 +-
 drivers/bus/pci/linux/pci_init.h |   4 +-
 drivers/bus/pci/linux/pci_vfio.c | 176 ++++++++++++++++++++++++-------
 drivers/bus/pci/private.h        |   9 ++
 4 files changed, 153 insertions(+), 40 deletions(-)

diff --git a/drivers/bus/pci/linux/pci.c b/drivers/bus/pci/linux/pci.c
index 6dbba10657..8f1fddbf20 100644
--- a/drivers/bus/pci/linux/pci.c
+++ b/drivers/bus/pci/linux/pci.c
@@ -647,7 +647,7 @@ int rte_pci_read_config(const struct rte_pci_device *device,
 		return pci_uio_read_config(intr_handle, buf, len, offset);
 #ifdef VFIO_PRESENT
 	case RTE_PCI_KDRV_VFIO:
-		return pci_vfio_read_config(intr_handle, buf, len, offset);
+		return pci_vfio_read_config(device, buf, len, offset);
 #endif
 	default:
 		rte_pci_device_name(&device->addr, devname,
@@ -671,7 +671,7 @@ int rte_pci_write_config(const struct rte_pci_device *device,
 		return pci_uio_write_config(intr_handle, buf, len, offset);
 #ifdef VFIO_PRESENT
 	case RTE_PCI_KDRV_VFIO:
-		return pci_vfio_write_config(intr_handle, buf, len, offset);
+		return pci_vfio_write_config(device, buf, len, offset);
 #endif
 	default:
 		rte_pci_device_name(&device->addr, devname,
diff --git a/drivers/bus/pci/linux/pci_init.h b/drivers/bus/pci/linux/pci_init.h
index dcea726186..9f6659ba6e 100644
--- a/drivers/bus/pci/linux/pci_init.h
+++ b/drivers/bus/pci/linux/pci_init.h
@@ -66,9 +66,9 @@ int pci_uio_ioport_unmap(struct rte_pci_ioport *p);
 #endif
 
 /* access config space */
-int pci_vfio_read_config(const struct rte_intr_handle *intr_handle,
+int pci_vfio_read_config(const struct rte_pci_device *dev,
 			 void *buf, size_t len, off_t offs);
-int pci_vfio_write_config(const struct rte_intr_handle *intr_handle,
+int pci_vfio_write_config(const struct rte_pci_device *dev,
 			  const void *buf, size_t len, off_t offs);
 
 int pci_vfio_ioport_map(struct rte_pci_device *dev, int bar,
diff --git a/drivers/bus/pci/linux/pci_vfio.c b/drivers/bus/pci/linux/pci_vfio.c
index 07706f7338..012e7f72c1 100644
--- a/drivers/bus/pci/linux/pci_vfio.c
+++ b/drivers/bus/pci/linux/pci_vfio.c
@@ -43,35 +43,82 @@ static struct rte_tailq_elem rte_vfio_tailq = {
 };
 EAL_REGISTER_TAILQ(rte_vfio_tailq)
 
+static int
+pci_vfio_get_region(const struct rte_pci_device *dev, int index,
+		    uint64_t *size, uint64_t *offset)
+{
+	const struct rte_pci_device_internal *pdev =
+		RTE_PCI_DEVICE_INTERNAL_CONST(dev);
+
+	if (index >= VFIO_PCI_NUM_REGIONS || index >= RTE_MAX_PCI_REGIONS)
+		return -1;
+
+	if (pdev->region[index].size == 0 && pdev->region[index].offset == 0)
+		return -1;
+
+	*size   = pdev->region[index].size;
+	*offset = pdev->region[index].offset;
+
+	return 0;
+}
+
 int
-pci_vfio_read_config(const struct rte_intr_handle *intr_handle,
+pci_vfio_read_config(const struct rte_pci_device *dev,
 		    void *buf, size_t len, off_t offs)
 {
-	return pread64(intr_handle->vfio_dev_fd, buf, len,
-	       VFIO_GET_REGION_ADDR(VFIO_PCI_CONFIG_REGION_INDEX) + offs);
+	uint64_t size, offset;
+	int fd;
+
+	fd = dev->intr_handle.vfio_dev_fd;
+
+	if (pci_vfio_get_region(dev, VFIO_PCI_CONFIG_REGION_INDEX,
+				&size, &offset) != 0)
+		return -1;
+
+	if ((uint64_t)len + offs > size)
+		return -1;
+
+	return pread64(fd, buf, len, offset + offs);
 }
 
 int
-pci_vfio_write_config(const struct rte_intr_handle *intr_handle,
+pci_vfio_write_config(const struct rte_pci_device *dev,
 		    const void *buf, size_t len, off_t offs)
 {
-	return pwrite64(intr_handle->vfio_dev_fd, buf, len,
-	       VFIO_GET_REGION_ADDR(VFIO_PCI_CONFIG_REGION_INDEX) + offs);
+	uint64_t size, offset;
+	int fd;
+
+	fd = dev->intr_handle.vfio_dev_fd;
+
+	if (pci_vfio_get_region(dev, VFIO_PCI_CONFIG_REGION_INDEX,
+				&size, &offset) != 0)
+		return -1;
+
+	if ((uint64_t)len + offs > size)
+		return -1;
+
+	return pwrite64(fd, buf, len, offset + offs);
 }
 
 /* get PCI BAR number where MSI-X interrupts are */
 static int
-pci_vfio_get_msix_bar(int fd, struct pci_msix_table *msix_table)
+pci_vfio_get_msix_bar(const struct rte_pci_device *dev, int fd,
+		struct pci_msix_table *msix_table)
 {
 	int ret;
 	uint32_t reg;
 	uint16_t flags;
 	uint8_t cap_id, cap_offset;
+	uint64_t size, offset;
+
+	if (pci_vfio_get_region(dev, VFIO_PCI_CONFIG_REGION_INDEX,
+		&size, &offset) != 0) {
+		RTE_LOG(ERR, EAL, "Cannot get offset of CONFIG region.\n");
+		return -1;
+	}
 
 	/* read PCI capability pointer from config space */
-	ret = pread64(fd, &reg, sizeof(reg),
-			VFIO_GET_REGION_ADDR(VFIO_PCI_CONFIG_REGION_INDEX) +
-			PCI_CAPABILITY_LIST);
+	ret = pread64(fd, &reg, sizeof(reg), offset + PCI_CAPABILITY_LIST);
 	if (ret != sizeof(reg)) {
 		RTE_LOG(ERR, EAL,
 			"Cannot read capability pointer from PCI config space!\n");
@@ -84,9 +131,7 @@ pci_vfio_get_msix_bar(int fd, struct pci_msix_table *msix_table)
 	while (cap_offset) {
 
 		/* read PCI capability ID */
-		ret = pread64(fd, &reg, sizeof(reg),
-				VFIO_GET_REGION_ADDR(VFIO_PCI_CONFIG_REGION_INDEX) +
-				cap_offset);
+		ret = pread64(fd, &reg, sizeof(reg), offset + cap_offset);
 		if (ret != sizeof(reg)) {
 			RTE_LOG(ERR, EAL,
 				"Cannot read capability ID from PCI config space!\n");
@@ -99,8 +144,7 @@ pci_vfio_get_msix_bar(int fd, struct pci_msix_table *msix_table)
 		/* if we haven't reached MSI-X, check next capability */
 		if (cap_id != PCI_CAP_ID_MSIX) {
 			ret = pread64(fd, &reg, sizeof(reg),
-					VFIO_GET_REGION_ADDR(VFIO_PCI_CONFIG_REGION_INDEX) +
-					cap_offset);
+				offset + cap_offset);
 			if (ret != sizeof(reg)) {
 				RTE_LOG(ERR, EAL,
 					"Cannot read capability pointer from PCI config space!\n");
@@ -116,8 +160,7 @@ pci_vfio_get_msix_bar(int fd, struct pci_msix_table *msix_table)
 		else {
 			/* table offset resides in the next 4 bytes */
 			ret = pread64(fd, &reg, sizeof(reg),
-					VFIO_GET_REGION_ADDR(VFIO_PCI_CONFIG_REGION_INDEX) +
-					cap_offset + 4);
+				offset + cap_offset + 4);
 			if (ret != sizeof(reg)) {
 				RTE_LOG(ERR, EAL,
 					"Cannot read table offset from PCI config space!\n");
@@ -125,8 +168,7 @@ pci_vfio_get_msix_bar(int fd, struct pci_msix_table *msix_table)
 			}
 
 			ret = pread64(fd, &flags, sizeof(flags),
-					VFIO_GET_REGION_ADDR(VFIO_PCI_CONFIG_REGION_INDEX) +
-					cap_offset + 2);
+				offset + cap_offset + 2);
 			if (ret != sizeof(flags)) {
 				RTE_LOG(ERR, EAL,
 					"Cannot read table flags from PCI config space!\n");
@@ -178,14 +220,19 @@ pci_vfio_enable_bus_memory(int dev_fd)
 
 /* set PCI bus mastering */
 static int
-pci_vfio_set_bus_master(int dev_fd, bool op)
+pci_vfio_set_bus_master(const struct rte_pci_device *dev, int dev_fd, bool op)
 {
+	uint64_t size, offset;
 	uint16_t reg;
 	int ret;
 
-	ret = pread64(dev_fd, &reg, sizeof(reg),
-			VFIO_GET_REGION_ADDR(VFIO_PCI_CONFIG_REGION_INDEX) +
-			PCI_COMMAND);
+	if (pci_vfio_get_region(dev, VFIO_PCI_CONFIG_REGION_INDEX,
+		&size, &offset) != 0) {
+		RTE_LOG(ERR, EAL, "Cannot get offset of CONFIG region.\n");
+		return -1;
+	}
+
+	ret = pread64(dev_fd, &reg, sizeof(reg), offset + PCI_COMMAND);
 	if (ret != sizeof(reg)) {
 		RTE_LOG(ERR, EAL, "Cannot read command from PCI config space!\n");
 		return -1;
@@ -197,10 +244,7 @@ pci_vfio_set_bus_master(int dev_fd, bool op)
 	else
 		reg &= ~(PCI_COMMAND_MASTER);
 
-	ret = pwrite64(dev_fd, &reg, sizeof(reg),
-			VFIO_GET_REGION_ADDR(VFIO_PCI_CONFIG_REGION_INDEX) +
-			PCI_COMMAND);
-
+	ret = pwrite64(dev_fd, &reg, sizeof(reg), offset + PCI_COMMAND);
 	if (ret != sizeof(reg)) {
 		RTE_LOG(ERR, EAL, "Cannot write command to PCI config space!\n");
 		return -1;
@@ -429,14 +473,21 @@ pci_vfio_disable_notifier(struct rte_pci_device *dev)
 #endif
 
 static int
-pci_vfio_is_ioport_bar(int vfio_dev_fd, int bar_index)
+pci_vfio_is_ioport_bar(const struct rte_pci_device *dev, int vfio_dev_fd,
+	int bar_index)
 {
+	uint64_t size, offset;
 	uint32_t ioport_bar;
 	int ret;
 
+	if (pci_vfio_get_region(dev, VFIO_PCI_CONFIG_REGION_INDEX,
+		&size, &offset) != 0) {
+		RTE_LOG(ERR, EAL, "Cannot get offset of CONFIG region.\n");
+		return -1;
+	}
+
 	ret = pread64(vfio_dev_fd, &ioport_bar, sizeof(ioport_bar),
-			  VFIO_GET_REGION_ADDR(VFIO_PCI_CONFIG_REGION_INDEX)
-			  + PCI_BASE_ADDRESS_0 + bar_index*4);
+			  offset + PCI_BASE_ADDRESS_0 + bar_index * 4);
 	if (ret != sizeof(ioport_bar)) {
 		RTE_LOG(ERR, EAL, "Cannot read command (%x) from config space!\n",
 			PCI_BASE_ADDRESS_0 + bar_index*4);
@@ -460,7 +511,7 @@ pci_rte_vfio_setup_device(struct rte_pci_device *dev, int vfio_dev_fd)
 	}
 
 	/* set bus mastering for the device */
-	if (pci_vfio_set_bus_master(vfio_dev_fd, true)) {
+	if (pci_vfio_set_bus_master(dev, vfio_dev_fd, true)) {
 		RTE_LOG(ERR, EAL, "Cannot set up bus mastering!\n");
 		return -1;
 	}
@@ -690,11 +741,40 @@ pci_vfio_msix_is_mappable(int vfio_dev_fd, int msix_region)
 	return ret;
 }
 
+static int
+pci_vfio_fill_regions(struct rte_pci_device *dev, int vfio_dev_fd,
+		      struct vfio_device_info *device_info)
+{
+	struct rte_pci_device_internal *pdev = RTE_PCI_DEVICE_INTERNAL(dev);
+	struct vfio_region_info *reg = NULL;
+	int nb_maps, i, ret;
+
+	nb_maps = RTE_MIN((int)device_info->num_regions,
+			VFIO_PCI_CONFIG_REGION_INDEX + 1);
+
+	for (i = 0; i < nb_maps; i++) {
+		ret = pci_vfio_get_region_info(vfio_dev_fd, &reg, i);
+		if (ret < 0) {
+			RTE_LOG(DEBUG, EAL, "%s cannot get device region info error %i (%s)\n",
+				dev->name, errno, strerror(errno));
+			return -1;
+		}
+
+		pdev->region[i].size = reg->size;
+		pdev->region[i].offset = reg->offset;
+
+		free(reg);
+	}
+
+	return 0;
+}
 
 static int
 pci_vfio_map_resource_primary(struct rte_pci_device *dev)
 {
+	struct rte_pci_device_internal *pdev = RTE_PCI_DEVICE_INTERNAL(dev);
 	struct vfio_device_info device_info = { .argsz = sizeof(device_info) };
+	struct vfio_region_info *reg = NULL;
 	char pci_addr[PATH_MAX] = {0};
 	int vfio_dev_fd;
 	struct rte_pci_addr *loc = &dev->addr;
@@ -735,11 +815,22 @@ pci_vfio_map_resource_primary(struct rte_pci_device *dev)
 	/* map BARs */
 	maps = vfio_res->maps;
 
+	ret = pci_vfio_get_region_info(vfio_dev_fd, &reg,
+		VFIO_PCI_CONFIG_REGION_INDEX);
+	if (ret < 0) {
+		RTE_LOG(ERR, EAL, "%s cannot get device region info error %i (%s)\n",
+			dev->name, errno, strerror(errno));
+		goto err_vfio_res;
+	}
+	pdev->region[VFIO_PCI_CONFIG_REGION_INDEX].size = reg->size;
+	pdev->region[VFIO_PCI_CONFIG_REGION_INDEX].offset = reg->offset;
+	free(reg);
+
 	vfio_res->msix_table.bar_index = -1;
 	/* get MSI-X BAR, if any (we have to know where it is because we can't
 	 * easily mmap it when using VFIO)
 	 */
-	ret = pci_vfio_get_msix_bar(vfio_dev_fd, &vfio_res->msix_table);
+	ret = pci_vfio_get_msix_bar(dev, vfio_dev_fd, &vfio_res->msix_table);
 	if (ret < 0) {
 		RTE_LOG(ERR, EAL, "%s cannot get MSI-X BAR number!\n",
 				pci_addr);
@@ -760,7 +851,6 @@ pci_vfio_map_resource_primary(struct rte_pci_device *dev)
 	}
 
 	for (i = 0; i < vfio_res->nb_maps; i++) {
-		struct vfio_region_info *reg = NULL;
 		void *bar_addr;
 
 		ret = pci_vfio_get_region_info(vfio_dev_fd, &reg, i);
@@ -771,8 +861,11 @@ pci_vfio_map_resource_primary(struct rte_pci_device *dev)
 			goto err_vfio_res;
 		}
 
+		pdev->region[i].size = reg->size;
+		pdev->region[i].offset = reg->offset;
+
 		/* chk for io port region */
-		ret = pci_vfio_is_ioport_bar(vfio_dev_fd, i);
+		ret = pci_vfio_is_ioport_bar(dev, vfio_dev_fd, i);
 		if (ret < 0) {
 			free(reg);
 			goto err_vfio_res;
@@ -882,6 +975,10 @@ pci_vfio_map_resource_secondary(struct rte_pci_device *dev)
 	if (ret)
 		return ret;
 
+	ret = pci_vfio_fill_regions(dev, vfio_dev_fd, &device_info);
+	if (ret)
+		return ret;
+
 	/* map BARs */
 	maps = vfio_res->maps;
 
@@ -988,7 +1085,7 @@ pci_vfio_unmap_resource_primary(struct rte_pci_device *dev)
 		return -1;
 	}
 
-	if (pci_vfio_set_bus_master(dev->intr_handle.vfio_dev_fd, false)) {
+	if (pci_vfio_set_bus_master(dev, dev->intr_handle.vfio_dev_fd, false)) {
 		RTE_LOG(ERR, EAL, "%s cannot unset bus mastering for PCI device!\n",
 				pci_addr);
 		return -1;
@@ -1064,14 +1161,21 @@ int
 pci_vfio_ioport_map(struct rte_pci_device *dev, int bar,
 		    struct rte_pci_ioport *p)
 {
+	uint64_t size, offset;
+
 	if (bar < VFIO_PCI_BAR0_REGION_INDEX ||
 	    bar > VFIO_PCI_BAR5_REGION_INDEX) {
 		RTE_LOG(ERR, EAL, "invalid bar (%d)!\n", bar);
 		return -1;
 	}
 
+	if (pci_vfio_get_region(dev, bar, &size, &offset) != 0) {
+		RTE_LOG(ERR, EAL, "Cannot get offset of region %d.\n", bar);
+		return -1;
+	}
+
 	p->dev = dev;
-	p->base = VFIO_GET_REGION_ADDR(bar);
+	p->base = offset;
 	return 0;
 }
 
diff --git a/drivers/bus/pci/private.h b/drivers/bus/pci/private.h
index 49a29d45cf..8b5fa70641 100644
--- a/drivers/bus/pci/private.h
+++ b/drivers/bus/pci/private.h
@@ -12,6 +12,8 @@
 #include <rte_os_shim.h>
 #include <rte_pci.h>
 
+#define RTE_MAX_PCI_REGIONS	9
+
 /*
  * Convert struct rte_pci_device to struct rte_pci_device_internal
  */
@@ -25,8 +27,15 @@ extern struct rte_pci_bus rte_pci_bus;
 struct rte_pci_driver;
 struct rte_pci_device;
 
+struct rte_pci_region {
+	uint64_t size;
+	uint64_t offset;
+};
+
 struct rte_pci_device_internal {
 	struct rte_pci_device device;
+	/* PCI regions provided by e.g. VFIO. */
+	struct rte_pci_region region[RTE_MAX_PCI_REGIONS];
 };
 
 /**
-- 
2.17.1