X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=drivers%2Fnet%2Fvirtio%2Fvirtio_pci.c;h=9b47165dfab0f8000605fe55d95a89b6b32fdf36;hb=b1bcff835b606239ed296750fe3e16201082663d;hp=7c7621a0bffa1aaba8eb67d4e9e6e089d59aeda0;hpb=6ba1f63b5ab0d6115c0fb74283e3a16512f56255;p=dpdk.git

diff --git a/drivers/net/virtio/virtio_pci.c b/drivers/net/virtio/virtio_pci.c
index 7c7621a0bf..9b47165dfa 100644
--- a/drivers/net/virtio/virtio_pci.c
+++ b/drivers/net/virtio/virtio_pci.c
@@ -49,56 +49,118 @@
 #define PCI_CAPABILITY_LIST	0x34
 #define PCI_CAP_ID_VNDR		0x09
 
+/*
+ * The remaining space is defined by each driver as the per-driver
+ * configuration space.
+ */
+#define VIRTIO_PCI_CONFIG(hw) (((hw)->use_msix) ? 24 : 20)
+
+static inline int
+check_vq_phys_addr_ok(struct virtqueue *vq)
+{
+	/* Virtio PCI device VIRTIO_PCI_QUEUE_PF register is 32bit,
+	 * and only accepts 32 bit page frame number.
+	 * Check if the allocated physical memory exceeds 16TB.
+	 */
+	if ((vq->vq_ring_mem + vq->vq_ring_size - 1) >>
+			(VIRTIO_PCI_QUEUE_ADDR_SHIFT + 32)) {
+		PMD_INIT_LOG(ERR, "vring address shouldn't be above 16TB!");
+		return 0;
+	}
+
+	return 1;
+}
+
+/*
+ * Since we are in legacy mode:
+ * http://ozlabs.org/~rusty/virtio-spec/virtio-0.9.5.pdf
+ *
+ * "Note that this is possible because while the virtio header is PCI (i.e.
+ * little) endian, the device-specific region is encoded in the native endian of
+ * the guest (where such distinction is applicable)."
+ *
+ * For powerpc which supports both, qemu supposes that cpu is big endian and
+ * enforces this for the virtio-net stuff.
+ */
 static void
 legacy_read_dev_config(struct virtio_hw *hw, size_t offset,
 		       void *dst, int length)
 {
-	uint64_t off;
-	uint8_t *d;
+#ifdef RTE_ARCH_PPC_64
 	int size;
 
-	off = VIRTIO_PCI_CONFIG(hw) + offset;
-	for (d = dst; length > 0; d += size, off += size, length -= size) {
+	while (length > 0) {
 		if (length >= 4) {
 			size = 4;
-			*(uint32_t *)d = VIRTIO_READ_REG_4(hw, off);
+			rte_eal_pci_ioport_read(&hw->io, dst, size,
+				VIRTIO_PCI_CONFIG(hw) + offset);
+			*(uint32_t *)dst = rte_be_to_cpu_32(*(uint32_t *)dst);
 		} else if (length >= 2) {
 			size = 2;
-			*(uint16_t *)d = VIRTIO_READ_REG_2(hw, off);
+			rte_eal_pci_ioport_read(&hw->io, dst, size,
+				VIRTIO_PCI_CONFIG(hw) + offset);
+			*(uint16_t *)dst = rte_be_to_cpu_16(*(uint16_t *)dst);
 		} else {
 			size = 1;
-			*d = VIRTIO_READ_REG_1(hw, off);
+			rte_eal_pci_ioport_read(&hw->io, dst, size,
+				VIRTIO_PCI_CONFIG(hw) + offset);
 		}
+
+		dst = (char *)dst + size;
+		offset += size;
+		length -= size;
 	}
+#else
+	rte_eal_pci_ioport_read(&hw->io, dst, length,
+				VIRTIO_PCI_CONFIG(hw) + offset);
+#endif
 }
 
 static void
 legacy_write_dev_config(struct virtio_hw *hw, size_t offset,
 			const void *src, int length)
 {
-	uint64_t off;
-	const uint8_t *s;
+#ifdef RTE_ARCH_PPC_64
+	union {
+		uint32_t u32;
+		uint16_t u16;
+	} tmp;
 	int size;
 
-	off = VIRTIO_PCI_CONFIG(hw) + offset;
-	for (s = src; length > 0; s += size, off += size, length -= size) {
+	while (length > 0) {
 		if (length >= 4) {
 			size = 4;
-			VIRTIO_WRITE_REG_4(hw, off, *(const uint32_t *)s);
+			tmp.u32 = rte_cpu_to_be_32(*(const uint32_t *)src);
+			rte_eal_pci_ioport_write(&hw->io, &tmp.u32, size,
+				VIRTIO_PCI_CONFIG(hw) + offset);
 		} else if (length >= 2) {
 			size = 2;
-			VIRTIO_WRITE_REG_2(hw, off, *(const uint16_t *)s);
+			tmp.u16 = rte_cpu_to_be_16(*(const uint16_t *)src);
+			rte_eal_pci_ioport_write(&hw->io, &tmp.u16, size,
+				VIRTIO_PCI_CONFIG(hw) + offset);
 		} else {
 			size = 1;
-			VIRTIO_WRITE_REG_1(hw, off, *s);
+			rte_eal_pci_ioport_write(&hw->io, src, size,
+				VIRTIO_PCI_CONFIG(hw) + offset);
 		}
+
+		src = (const char *)src + size;
+		offset += size;
+		length -= size;
 	}
+#else
+	rte_eal_pci_ioport_write(&hw->io, src, length,
+				 VIRTIO_PCI_CONFIG(hw) + offset);
+#endif
 }
 
 static uint64_t
 legacy_get_features(struct virtio_hw *hw)
 {
-	return VIRTIO_READ_REG_4(hw, VIRTIO_PCI_HOST_FEATURES);
+	uint32_t dst;
+
+	rte_eal_pci_ioport_read(&hw->io, &dst, 4, VIRTIO_PCI_HOST_FEATURES);
+	return dst;
 }
 
 static void
@@ -109,19 +171,23 @@ legacy_set_features(struct virtio_hw *hw, uint64_t features)
 			"only 32 bit features are allowed for legacy virtio!");
 		return;
 	}
-	VIRTIO_WRITE_REG_4(hw, VIRTIO_PCI_GUEST_FEATURES, features);
+	rte_eal_pci_ioport_write(&hw->io, &features, 4,
+				 VIRTIO_PCI_GUEST_FEATURES);
 }
 
 static uint8_t
 legacy_get_status(struct virtio_hw *hw)
 {
-	return VIRTIO_READ_REG_1(hw, VIRTIO_PCI_STATUS);
+	uint8_t dst;
+
+	rte_eal_pci_ioport_read(&hw->io, &dst, 1, VIRTIO_PCI_STATUS);
+	return dst;
 }
 
 static void
 legacy_set_status(struct virtio_hw *hw, uint8_t status)
 {
-	VIRTIO_WRITE_REG_1(hw, VIRTIO_PCI_STATUS, status);
+	rte_eal_pci_ioport_write(&hw->io, &status, 1, VIRTIO_PCI_STATUS);
 }
 
 static void
@@ -133,147 +199,67 @@ legacy_reset(struct virtio_hw *hw)
 static uint8_t
 legacy_get_isr(struct virtio_hw *hw)
 {
-	return VIRTIO_READ_REG_1(hw, VIRTIO_PCI_ISR);
+	uint8_t dst;
+
+	rte_eal_pci_ioport_read(&hw->io, &dst, 1, VIRTIO_PCI_ISR);
+	return dst;
 }
 
 /* Enable one vector (0) for Link State Intrerrupt */
 static uint16_t
 legacy_set_config_irq(struct virtio_hw *hw, uint16_t vec)
 {
-	VIRTIO_WRITE_REG_2(hw, VIRTIO_MSI_CONFIG_VECTOR, vec);
-	return VIRTIO_READ_REG_2(hw, VIRTIO_MSI_CONFIG_VECTOR);
+	uint16_t dst;
+
+	rte_eal_pci_ioport_write(&hw->io, &vec, 2, VIRTIO_MSI_CONFIG_VECTOR);
+	rte_eal_pci_ioport_read(&hw->io, &dst, 2, VIRTIO_MSI_CONFIG_VECTOR);
+	return dst;
 }
 
 static uint16_t
 legacy_get_queue_num(struct virtio_hw *hw, uint16_t queue_id)
 {
-	VIRTIO_WRITE_REG_2(hw, VIRTIO_PCI_QUEUE_SEL, queue_id);
-	return VIRTIO_READ_REG_2(hw, VIRTIO_PCI_QUEUE_NUM);
+	uint16_t dst;
+
+	rte_eal_pci_ioport_write(&hw->io, &queue_id, 2, VIRTIO_PCI_QUEUE_SEL);
+	rte_eal_pci_ioport_read(&hw->io, &dst, 2, VIRTIO_PCI_QUEUE_NUM);
+	return dst;
 }
 
-static void
+static int
 legacy_setup_queue(struct virtio_hw *hw, struct virtqueue *vq)
 {
-	VIRTIO_WRITE_REG_2(hw, VIRTIO_PCI_QUEUE_SEL, vq->vq_queue_index);
+	uint32_t src;
+
+	if (!check_vq_phys_addr_ok(vq))
+		return -1;
 
-	VIRTIO_WRITE_REG_4(hw, VIRTIO_PCI_QUEUE_PFN,
-		vq->mz->phys_addr >> VIRTIO_PCI_QUEUE_ADDR_SHIFT);
+	rte_eal_pci_ioport_write(&hw->io, &vq->vq_queue_index, 2,
+			 VIRTIO_PCI_QUEUE_SEL);
+	src = vq->vq_ring_mem >> VIRTIO_PCI_QUEUE_ADDR_SHIFT;
+	rte_eal_pci_ioport_write(&hw->io, &src, 4, VIRTIO_PCI_QUEUE_PFN);
+
+	return 0;
 }
 
 static void
 legacy_del_queue(struct virtio_hw *hw, struct virtqueue *vq)
 {
-	VIRTIO_WRITE_REG_2(hw, VIRTIO_PCI_QUEUE_SEL, vq->vq_queue_index);
+	uint32_t src = 0;
 
-	VIRTIO_WRITE_REG_4(hw, VIRTIO_PCI_QUEUE_PFN, 0);
+	rte_eal_pci_ioport_write(&hw->io, &vq->vq_queue_index, 2,
+			 VIRTIO_PCI_QUEUE_SEL);
+	rte_eal_pci_ioport_write(&hw->io, &src, 4, VIRTIO_PCI_QUEUE_PFN);
 }
 
 static void
 legacy_notify_queue(struct virtio_hw *hw, struct virtqueue *vq)
 {
-	VIRTIO_WRITE_REG_2(hw, VIRTIO_PCI_QUEUE_NOTIFY, vq->vq_queue_index);
+	rte_eal_pci_ioport_write(&hw->io, &vq->vq_queue_index, 2,
+			 VIRTIO_PCI_QUEUE_NOTIFY);
 }
 
 #ifdef RTE_EXEC_ENV_LINUXAPP
-static int
-parse_sysfs_value(const char *filename, unsigned long *val)
-{
-	FILE *f;
-	char buf[BUFSIZ];
-	char *end = NULL;
-
-	f = fopen(filename, "r");
-	if (f == NULL) {
-		PMD_INIT_LOG(ERR, "%s(): cannot open sysfs value %s",
-			     __func__, filename);
-		return -1;
-	}
-
-	if (fgets(buf, sizeof(buf), f) == NULL) {
-		PMD_INIT_LOG(ERR, "%s(): cannot read sysfs value %s",
-			     __func__, filename);
-		fclose(f);
-		return -1;
-	}
-	*val = strtoul(buf, &end, 0);
-	if ((buf[0] == '\0') || (end == NULL) || (*end != '\n')) {
-		PMD_INIT_LOG(ERR, "%s(): cannot parse sysfs value %s",
-			     __func__, filename);
-		fclose(f);
-		return -1;
-	}
-	fclose(f);
-	return 0;
-}
-
-static int
-get_uio_dev(struct rte_pci_addr *loc, char *buf, unsigned int buflen,
-			unsigned int *uio_num)
-{
-	struct dirent *e;
-	DIR *dir;
-	char dirname[PATH_MAX];
-
-	/*
-	 * depending on kernel version, uio can be located in uio/uioX
-	 * or uio:uioX
-	 */
-	snprintf(dirname, sizeof(dirname),
-		     SYSFS_PCI_DEVICES "/" PCI_PRI_FMT "/uio",
-		     loc->domain, loc->bus, loc->devid, loc->function);
-	dir = opendir(dirname);
-	if (dir == NULL) {
-		/* retry with the parent directory */
-		snprintf(dirname, sizeof(dirname),
-			     SYSFS_PCI_DEVICES "/" PCI_PRI_FMT,
-			     loc->domain, loc->bus, loc->devid, loc->function);
-		dir = opendir(dirname);
-
-		if (dir == NULL) {
-			PMD_INIT_LOG(ERR, "Cannot opendir %s", dirname);
-			return -1;
-		}
-	}
-
-	/* take the first file starting with "uio" */
-	while ((e = readdir(dir)) != NULL) {
-		/* format could be uio%d ...*/
-		int shortprefix_len = sizeof("uio") - 1;
-		/* ... or uio:uio%d */
-		int longprefix_len = sizeof("uio:uio") - 1;
-		char *endptr;
-
-		if (strncmp(e->d_name, "uio", 3) != 0)
-			continue;
-
-		/* first try uio%d */
-		errno = 0;
-		*uio_num = strtoull(e->d_name + shortprefix_len, &endptr, 10);
-		if (errno == 0 && endptr != (e->d_name + shortprefix_len)) {
-			snprintf(buf, buflen, "%s/uio%u", dirname, *uio_num);
-			break;
-		}
-
-		/* then try uio:uio%d */
-		errno = 0;
-		*uio_num = strtoull(e->d_name + longprefix_len, &endptr, 10);
-		if (errno == 0 && endptr != (e->d_name + longprefix_len)) {
-			snprintf(buf, buflen, "%s/uio:uio%u", dirname,
-				     *uio_num);
-			break;
-		}
-	}
-	closedir(dir);
-
-	/* No uio resource found */
-	if (e == NULL) {
-		PMD_INIT_LOG(ERR, "Could not find uio resource");
-		return -1;
-	}
-
-	return 0;
-}
-
 static int
 legacy_virtio_has_msix(const struct rte_pci_addr *loc)
 {
@@ -281,159 +267,38 @@ legacy_virtio_has_msix(const struct rte_pci_addr *loc)
 	char dirname[PATH_MAX];
 
 	snprintf(dirname, sizeof(dirname),
-		     SYSFS_PCI_DEVICES "/" PCI_PRI_FMT "/msi_irqs",
+		     "%s/" PCI_PRI_FMT "/msi_irqs", pci_get_sysfs_path(),
 		     loc->domain, loc->bus, loc->devid, loc->function);
 
 	d = opendir(dirname);
 	if (d)
 		closedir(d);
 
-	return (d != NULL);
+	return d != NULL;
 }
-
-/* Extract I/O port numbers from sysfs */
+#else
 static int
-virtio_resource_init_by_uio(struct rte_pci_device *pci_dev)
+legacy_virtio_has_msix(const struct rte_pci_addr *loc __rte_unused)
 {
-	char dirname[PATH_MAX];
-	char filename[PATH_MAX];
-	unsigned long start, size;
-	unsigned int uio_num;
-
-	if (get_uio_dev(&pci_dev->addr, dirname, sizeof(dirname), &uio_num) < 0)
-		return -1;
-
-	/* get portio size */
-	snprintf(filename, sizeof(filename),
-		     "%s/portio/port0/size", dirname);
-	if (parse_sysfs_value(filename, &size) < 0) {
-		PMD_INIT_LOG(ERR, "%s(): cannot parse size",
-			     __func__);
-		return -1;
-	}
-
-	/* get portio start */
-	snprintf(filename, sizeof(filename),
-		 "%s/portio/port0/start", dirname);
-	if (parse_sysfs_value(filename, &start) < 0) {
-		PMD_INIT_LOG(ERR, "%s(): cannot parse portio start",
-			     __func__);
-		return -1;
-	}
-	pci_dev->mem_resource[0].addr = (void *)(uintptr_t)start;
-	pci_dev->mem_resource[0].len =  (uint64_t)size;
-	PMD_INIT_LOG(DEBUG,
-		     "PCI Port IO found start=0x%lx with size=0x%lx",
-		     start, size);
-
-	/* save fd */
-	memset(dirname, 0, sizeof(dirname));
-	snprintf(dirname, sizeof(dirname), "/dev/uio%u", uio_num);
-	pci_dev->intr_handle.fd = open(dirname, O_RDWR);
-	if (pci_dev->intr_handle.fd < 0) {
-		PMD_INIT_LOG(ERR, "Cannot open %s: %s\n",
-			dirname, strerror(errno));
-		return -1;
-	}
-
-	pci_dev->intr_handle.type = RTE_INTR_HANDLE_UIO;
-	pci_dev->driver->drv_flags |= RTE_PCI_DRV_INTR_LSC;
-
+	/* nic_uio does not enable interrupts, return 0 (false). */
 	return 0;
 }
+#endif
 
-/* Extract port I/O numbers from proc/ioports */
 static int
-virtio_resource_init_by_ioports(struct rte_pci_device *pci_dev)
+legacy_virtio_resource_init(struct rte_pci_device *pci_dev,
+			    struct virtio_hw *hw, uint32_t *dev_flags)
 {
-	uint16_t start, end;
-	int size;
-	FILE *fp;
-	char *line = NULL;
-	char pci_id[16];
-	int found = 0;
-	size_t linesz;
-
-	snprintf(pci_id, sizeof(pci_id), PCI_PRI_FMT,
-		 pci_dev->addr.domain,
-		 pci_dev->addr.bus,
-		 pci_dev->addr.devid,
-		 pci_dev->addr.function);
-
-	fp = fopen("/proc/ioports", "r");
-	if (fp == NULL) {
-		PMD_INIT_LOG(ERR, "%s(): can't open ioports", __func__);
-		return -1;
-	}
-
-	while (getdelim(&line, &linesz, '\n', fp) > 0) {
-		char *ptr = line;
-		char *left;
-		int n;
-
-		n = strcspn(ptr, ":");
-		ptr[n] = 0;
-		left = &ptr[n + 1];
-
-		while (*left && isspace(*left))
-			left++;
-
-		if (!strncmp(left, pci_id, strlen(pci_id))) {
-			found = 1;
-
-			while (*ptr && isspace(*ptr))
-				ptr++;
-
-			sscanf(ptr, "%04hx-%04hx", &start, &end);
-			size = end - start + 1;
-
-			break;
-		}
-	}
-
-	free(line);
-	fclose(fp);
-
-	if (!found)
+	if (rte_eal_pci_ioport_map(pci_dev, 0, &hw->io) < 0)
 		return -1;
 
-	pci_dev->mem_resource[0].addr = (void *)(uintptr_t)(uint32_t)start;
-	pci_dev->mem_resource[0].len =  (uint64_t)size;
-	PMD_INIT_LOG(DEBUG,
-		"PCI Port IO found start=0x%x with size=0x%x",
-		start, size);
-
-	/* can't support lsc interrupt without uio */
-	pci_dev->driver->drv_flags &= ~RTE_PCI_DRV_INTR_LSC;
-
-	return 0;
-}
-
-/* Extract I/O port numbers from sysfs */
-static int
-legacy_virtio_resource_init(struct rte_pci_device *pci_dev)
-{
-	if (virtio_resource_init_by_uio(pci_dev) == 0)
-		return 0;
+	if (pci_dev->intr_handle.type != RTE_INTR_HANDLE_UNKNOWN)
+		*dev_flags |= RTE_ETH_DEV_INTR_LSC;
 	else
-		return virtio_resource_init_by_ioports(pci_dev);
-}
-
-#else
-static int
-legayc_virtio_has_msix(const struct rte_pci_addr *loc __rte_unused)
-{
-	/* nic_uio does not enable interrupts, return 0 (false). */
-	return 0;
-}
+		*dev_flags &= ~RTE_ETH_DEV_INTR_LSC;
 
-static int
-legacy_virtio_resource_init(struct rte_pci_device *pci_dev __rte_unused)
-{
-	/* no setup required */
 	return 0;
 }
-#endif
 
 static const struct virtio_pci_ops legacy_ops = {
 	.read_dev_cfg	= legacy_read_dev_config,
@@ -590,13 +455,16 @@ modern_get_queue_num(struct virtio_hw *hw, uint16_t queue_id)
 	return io_read16(&hw->common_cfg->queue_size);
 }
 
-static void
+static int
 modern_setup_queue(struct virtio_hw *hw, struct virtqueue *vq)
 {
 	uint64_t desc_addr, avail_addr, used_addr;
 	uint16_t notify_off;
 
-	desc_addr = vq->mz->phys_addr;
+	if (!check_vq_phys_addr_ok(vq))
+		return -1;
+
+	desc_addr = vq->vq_ring_mem;
 	avail_addr = desc_addr + vq->vq_nentries * sizeof(struct vring_desc);
 	used_addr = RTE_ALIGN_CEIL(avail_addr + offsetof(struct vring_avail,
 							 ring[vq->vq_nentries]),
@@ -623,6 +491,8 @@ modern_setup_queue(struct virtio_hw *hw, struct virtqueue *vq)
 	PMD_INIT_LOG(DEBUG, "\t used_addr: %" PRIx64, used_addr);
 	PMD_INIT_LOG(DEBUG, "\t notify addr: %p (notify offset: %u)",
 		vq->notify_addr, notify_off);
+
+	return 0;
 }
 
 static void
@@ -777,7 +647,7 @@ virtio_read_caps(struct rte_pci_device *dev, struct virtio_hw *hw)
 	struct virtio_pci_cap cap;
 	int ret;
 
-	if (rte_eal_pci_map_device(dev) < 0) {
+	if (rte_eal_pci_map_device(dev)) {
 		PMD_INIT_LOG(DEBUG, "failed to map pci device!");
 		return -1;
 	}
@@ -845,8 +715,17 @@ next:
 	return 0;
 }
 
+/*
+ * Return -1:
+ *   if there is error mapping with VFIO/UIO.
+ *   if port map error when driver type is KDRV_NONE.
+ *   if whitelisted but driver type is KDRV_UNKNOWN.
+ * Return 1 if kernel driver is managing the device.
+ * Return 0 on success.
+ */
 int
-vtpci_init(struct rte_pci_device *dev, struct virtio_hw *hw)
+vtpci_init(struct rte_pci_device *dev, struct virtio_hw *hw,
+	   uint32_t *dev_flags)
 {
 	hw->dev = dev;
 
@@ -859,17 +738,25 @@ vtpci_init(struct rte_pci_device *dev, struct virtio_hw *hw)
 		PMD_INIT_LOG(INFO, "modern virtio pci detected.");
 		hw->vtpci_ops = &modern_ops;
 		hw->modern    = 1;
-		dev->driver->drv_flags |= RTE_PCI_DRV_INTR_LSC;
+		*dev_flags |= RTE_ETH_DEV_INTR_LSC;
 		return 0;
 	}
 
 	PMD_INIT_LOG(INFO, "trying with legacy virtio pci.");
-	if (legacy_virtio_resource_init(dev) < 0)
+	if (legacy_virtio_resource_init(dev, hw, dev_flags) < 0) {
+		if (dev->kdrv == RTE_KDRV_UNKNOWN &&
+		    (!dev->device.devargs ||
+		     dev->device.devargs->type !=
+			RTE_DEVTYPE_WHITELISTED_PCI)) {
+			PMD_INIT_LOG(INFO,
+				"skip kernel managed virtio device.");
+			return 1;
+		}
 		return -1;
+	}
 
 	hw->vtpci_ops = &legacy_ops;
 	hw->use_msix = legacy_virtio_has_msix(&dev->addr);
-	hw->io_base  = (uint32_t)(uintptr_t)dev->mem_resource[0].addr;
 	hw->modern   = 0;
 
 	return 0;