[dpdk-dev] [RFC PATCH 5/6] eal: supporting bus model in init process

[Shreyansh Jain]

This patch makes necessary changes to the EAL for handling bus scan and
probe. Most of the scan function has been moved to bus/* implementation,
(currently only for pci, linuxapp). There are still some functions which
exists in the EAL (bind, unbind module, mmap etc).

Missing/Grey area;
 - Should all the operations for a PCI device, whether binding to a driver
   or mmap, be moved to PCI bus code base? All of that is not relevant for
   a bus, but then having multiple implementation areas for a common
   sub-system (PCI, here) is also not a nice thing.

Signed-off-by: Shreyansh Jain <shreyansh.jain at nxp.com>
---
 lib/librte_eal/linuxapp/eal/Makefile  |   1 +
 lib/librte_eal/linuxapp/eal/eal.c     |  51 +++++-
 lib/librte_eal/linuxapp/eal/eal_pci.c | 298 ----------------------------------
 3 files changed, 44 insertions(+), 306 deletions(-)

diff --git a/lib/librte_eal/linuxapp/eal/Makefile b/lib/librte_eal/linuxapp/eal/Makefile
index 4e206f0..124dceb 100644
--- a/lib/librte_eal/linuxapp/eal/Makefile
+++ b/lib/librte_eal/linuxapp/eal/Makefile
@@ -77,6 +77,7 @@ SRCS-$(CONFIG_RTE_EXEC_ENV_LINUXAPP) += eal_common_timer.c
 SRCS-$(CONFIG_RTE_EXEC_ENV_LINUXAPP) += eal_common_memzone.c
 SRCS-$(CONFIG_RTE_EXEC_ENV_LINUXAPP) += eal_common_log.c
 SRCS-$(CONFIG_RTE_EXEC_ENV_LINUXAPP) += eal_common_launch.c
+SRCS-$(CONFIG_RTE_EXEC_ENV_LINUXAPP) += eal_common_bus.c
 SRCS-$(CONFIG_RTE_EXEC_ENV_LINUXAPP) += eal_common_vdev.c
 SRCS-$(CONFIG_RTE_EXEC_ENV_LINUXAPP) += eal_common_pci.c
 SRCS-$(CONFIG_RTE_EXEC_ENV_LINUXAPP) += eal_common_pci_uio.c
diff --git a/lib/librte_eal/linuxapp/eal/eal.c b/lib/librte_eal/linuxapp/eal/eal.c
index 2075282..332d1f4 100644
--- a/lib/librte_eal/linuxapp/eal/eal.c
+++ b/lib/librte_eal/linuxapp/eal/eal.c
@@ -739,6 +739,44 @@ static int rte_eal_vfio_setup(void)
 }
 #endif
 
+static int
+rte_eal_scan(void)
+{
+	int ret = 0;
+
+	/* For now, as vdev replacement is not complete, continue with a call
+	 * rte_bus_list scan
+	 */
+	rte_eal_bus_scan();
+
+	ret = rte_eal_dev_init();
+	if (ret) {
+		RTE_LOG(ERR, EAL, "Cannot init pmd devices\n");
+	}
+
+out:
+	return ret;
+}
+
+static int
+rte_eal_probe(void)
+{
+	int ret = 0;
+
+	/* Probe & Initialize PCI devices */
+	ret = rte_eal_pci_probe();
+	if (ret) {
+		RTE_LOG(ERR, EAL, "Cannot probe PCI\n");
+		goto out;
+	}
+
+	/* ToDo: vdev scan already does the probe - it should be moved here */
+
+	/* Last successful bus probe would set ret = 0 */
+out:
+	return ret;
+}
+
 /* Launch threads, called at application init(). */
 int
 rte_eal_init(int argc, char **argv)
@@ -802,9 +840,6 @@ rte_eal_init(int argc, char **argv)
 	if (rte_eal_log_init(logid, internal_config.syslog_facility) < 0)
 		rte_panic("Cannot init logs\n");
 
-	if (rte_eal_pci_init() < 0)
-		rte_panic("Cannot init PCI\n");
-
 #ifdef VFIO_PRESENT
 	if (rte_eal_vfio_setup() < 0)
 		rte_panic("Cannot init VFIO\n");
@@ -828,6 +863,9 @@ rte_eal_init(int argc, char **argv)
 	if (rte_eal_timer_init() < 0)
 		rte_panic("Cannot init HPET or TSC timers\n");
 
+	if (rte_eal_scan() < 0)
+		rte_panic("Cannot scan for devices\n");
+
 	eal_check_mem_on_local_socket();
 
 	if (eal_plugins_init() < 0)
@@ -841,9 +879,6 @@ rte_eal_init(int argc, char **argv)
 		rte_config.master_lcore, (int)thread_id, cpuset,
 		ret == 0 ? "" : "...");
 
-	if (rte_eal_dev_init() < 0)
-		rte_panic("Cannot init pmd devices\n");
-
 	if (rte_eal_intr_init() < 0)
 		rte_panic("Cannot init interrupt-handling thread\n");
 
@@ -884,8 +919,8 @@ rte_eal_init(int argc, char **argv)
 	rte_eal_mp_wait_lcore();
 
 	/* Probe & Initialize PCI devices */
-	if (rte_eal_pci_probe())
-		rte_panic("Cannot probe PCI\n");
+	if (rte_eal_probe())
+		rte_panic("Cannot complete probe\n");
 
 	rte_eal_mcfg_complete();
 
diff --git a/lib/librte_eal/linuxapp/eal/eal_pci.c b/lib/librte_eal/linuxapp/eal/eal_pci.c
index 876ba38..e3916ab 100644
--- a/lib/librte_eal/linuxapp/eal/eal_pci.c
+++ b/lib/librte_eal/linuxapp/eal/eal_pci.c
@@ -224,202 +224,6 @@ pci_parse_one_sysfs_resource(char *line, size_t len, uint64_t *phys_addr,
 	return 0;
 }
 
-/* parse the "resource" sysfs file */
-static int
-pci_parse_sysfs_resource(const char *filename, struct rte_pci_device *dev)
-{
-	FILE *f;
-	char buf[BUFSIZ];
-	int i;
-	uint64_t phys_addr, end_addr, flags;
-
-	f = fopen(filename, "r");
-	if (f == NULL) {
-		RTE_LOG(ERR, EAL, "Cannot open sysfs resource\n");
-		return -1;
-	}
-
-	for (i = 0; i<PCI_MAX_RESOURCE; i++) {
-
-		if (fgets(buf, sizeof(buf), f) == NULL) {
-			RTE_LOG(ERR, EAL,
-				"%s(): cannot read resource\n", __func__);
-			goto error;
-		}
-		if (pci_parse_one_sysfs_resource(buf, sizeof(buf), &phys_addr,
-				&end_addr, &flags) < 0)
-			goto error;
-
-		if (flags & IORESOURCE_MEM) {
-			dev->mem_resource[i].phys_addr = phys_addr;
-			dev->mem_resource[i].len = end_addr - phys_addr + 1;
-			/* not mapped for now */
-			dev->mem_resource[i].addr = NULL;
-		}
-	}
-	fclose(f);
-	return 0;
-
-error:
-	fclose(f);
-	return -1;
-}
-
-/* Scan one pci sysfs entry, and fill the devices list from it. */
-static int
-pci_scan_one(const char *dirname, uint16_t domain, uint8_t bus,
-	     uint8_t devid, uint8_t function)
-{
-	char filename[PATH_MAX];
-	unsigned long tmp;
-	struct rte_pci_device *dev;
-	char driver[PATH_MAX];
-	int ret;
-
-	dev = malloc(sizeof(*dev));
-	if (dev == NULL)
-		return -1;
-
-	memset(dev, 0, sizeof(*dev));
-	dev->addr.domain = domain;
-	dev->addr.bus = bus;
-	dev->addr.devid = devid;
-	dev->addr.function = function;
-
-	/* get vendor id */
-	snprintf(filename, sizeof(filename), "%s/vendor", dirname);
-	if (eal_parse_sysfs_value(filename, &tmp) < 0) {
-		free(dev);
-		return -1;
-	}
-	dev->id.vendor_id = (uint16_t)tmp;
-
-	/* get device id */
-	snprintf(filename, sizeof(filename), "%s/device", dirname);
-	if (eal_parse_sysfs_value(filename, &tmp) < 0) {
-		free(dev);
-		return -1;
-	}
-	dev->id.device_id = (uint16_t)tmp;
-
-	/* get subsystem_vendor id */
-	snprintf(filename, sizeof(filename), "%s/subsystem_vendor",
-		 dirname);
-	if (eal_parse_sysfs_value(filename, &tmp) < 0) {
-		free(dev);
-		return -1;
-	}
-	dev->id.subsystem_vendor_id = (uint16_t)tmp;
-
-	/* get subsystem_device id */
-	snprintf(filename, sizeof(filename), "%s/subsystem_device",
-		 dirname);
-	if (eal_parse_sysfs_value(filename, &tmp) < 0) {
-		free(dev);
-		return -1;
-	}
-	dev->id.subsystem_device_id = (uint16_t)tmp;
-
-	/* get class_id */
-	snprintf(filename, sizeof(filename), "%s/class",
-		 dirname);
-	if (eal_parse_sysfs_value(filename, &tmp) < 0) {
-		free(dev);
-		return -1;
-	}
-	/* the least 24 bits are valid: class, subclass, program interface */
-	dev->id.class_id = (uint32_t)tmp & RTE_CLASS_ANY_ID;
-
-	/* get max_vfs */
-	dev->max_vfs = 0;
-	snprintf(filename, sizeof(filename), "%s/max_vfs", dirname);
-	if (!access(filename, F_OK) &&
-	    eal_parse_sysfs_value(filename, &tmp) == 0)
-		dev->max_vfs = (uint16_t)tmp;
-	else {
-		/* for non igb_uio driver, need kernel version >= 3.8 */
-		snprintf(filename, sizeof(filename),
-			 "%s/sriov_numvfs", dirname);
-		if (!access(filename, F_OK) &&
-		    eal_parse_sysfs_value(filename, &tmp) == 0)
-			dev->max_vfs = (uint16_t)tmp;
-	}
-
-	/* get numa node */
-	snprintf(filename, sizeof(filename), "%s/numa_node",
-		 dirname);
-	if (access(filename, R_OK) != 0) {
-		/* if no NUMA support, set default to 0 */
-		dev->device.numa_node = 0;
-	} else {
-		if (eal_parse_sysfs_value(filename, &tmp) < 0) {
-			free(dev);
-			return -1;
-		}
-		dev->device.numa_node = tmp;
-	}
-
-	/* parse resources */
-	snprintf(filename, sizeof(filename), "%s/resource", dirname);
-	if (pci_parse_sysfs_resource(filename, dev) < 0) {
-		RTE_LOG(ERR, EAL, "%s(): cannot parse resource\n", __func__);
-		free(dev);
-		return -1;
-	}
-
-	/* parse driver */
-	snprintf(filename, sizeof(filename), "%s/driver", dirname);
-	ret = pci_get_kernel_driver_by_path(filename, driver);
-	if (ret < 0) {
-		RTE_LOG(ERR, EAL, "Fail to get kernel driver\n");
-		free(dev);
-		return -1;
-	}
-
-	if (!ret) {
-		if (!strcmp(driver, "vfio-pci"))
-			dev->kdrv = RTE_KDRV_VFIO;
-		else if (!strcmp(driver, "igb_uio"))
-			dev->kdrv = RTE_KDRV_IGB_UIO;
-		else if (!strcmp(driver, "uio_pci_generic"))
-			dev->kdrv = RTE_KDRV_UIO_GENERIC;
-		else
-			dev->kdrv = RTE_KDRV_UNKNOWN;
-	} else
-		dev->kdrv = RTE_KDRV_NONE;
-
-	/* device is valid, add in list (sorted) */
-	if (TAILQ_EMPTY(&pci_device_list)) {
-		rte_eal_device_insert(&dev->device);
-		TAILQ_INSERT_TAIL(&pci_device_list, dev, next);
-	} else {
-		struct rte_pci_device *dev2;
-		int ret;
-
-		TAILQ_FOREACH(dev2, &pci_device_list, next) {
-			ret = rte_eal_compare_pci_addr(&dev->addr, &dev2->addr);
-			if (ret > 0)
-				continue;
-
-			if (ret < 0) {
-				TAILQ_INSERT_BEFORE(dev2, dev, next);
-				rte_eal_device_insert(&dev->device);
-			} else { /* already registered */
-				dev2->kdrv = dev->kdrv;
-				dev2->max_vfs = dev->max_vfs;
-				memmove(dev2->mem_resource, dev->mem_resource,
-					sizeof(dev->mem_resource));
-				free(dev);
-			}
-			return 0;
-		}
-		rte_eal_device_insert(&dev->device);
-		TAILQ_INSERT_TAIL(&pci_device_list, dev, next);
-	}
-
-	return 0;
-}
-
 int
 pci_update_device(const struct rte_pci_addr *addr)
 {
@@ -433,93 +237,7 @@ pci_update_device(const struct rte_pci_addr *addr)
 				addr->function);
 }
 
-/*
- * split up a pci address into its constituent parts.
- */
-static int
-parse_pci_addr_format(const char *buf, int bufsize, uint16_t *domain,
-		uint8_t *bus, uint8_t *devid, uint8_t *function)
-{
-	/* first split on ':' */
-	union splitaddr {
-		struct {
-			char *domain;
-			char *bus;
-			char *devid;
-			char *function;
-		};
-		char *str[PCI_FMT_NVAL]; /* last element-separator is "." not ":" */
-	} splitaddr;
-
-	char *buf_copy = strndup(buf, bufsize);
-	if (buf_copy == NULL)
-		return -1;
-
-	if (rte_strsplit(buf_copy, bufsize, splitaddr.str, PCI_FMT_NVAL, ':')
-			!= PCI_FMT_NVAL - 1)
-		goto error;
-	/* final split is on '.' between devid and function */
-	splitaddr.function = strchr(splitaddr.devid,'.');
-	if (splitaddr.function == NULL)
-		goto error;
-	*splitaddr.function++ = '\0';
-
-	/* now convert to int values */
-	errno = 0;
-	*domain = (uint16_t)strtoul(splitaddr.domain, NULL, 16);
-	*bus = (uint8_t)strtoul(splitaddr.bus, NULL, 16);
-	*devid = (uint8_t)strtoul(splitaddr.devid, NULL, 16);
-	*function = (uint8_t)strtoul(splitaddr.function, NULL, 10);
-	if (errno != 0)
-		goto error;
-
-	free(buf_copy); /* free the copy made with strdup */
-	return 0;
-error:
-	free(buf_copy);
-	return -1;
-}
-
-/*
- * Scan the content of the PCI bus, and the devices in the devices
- * list
- */
-int
-rte_eal_pci_scan(void)
-{
-	struct dirent *e;
-	DIR *dir;
-	char dirname[PATH_MAX];
-	uint16_t domain;
-	uint8_t bus, devid, function;
-
-	dir = opendir(pci_get_sysfs_path());
-	if (dir == NULL) {
-		RTE_LOG(ERR, EAL, "%s(): opendir failed: %s\n",
-			__func__, strerror(errno));
-		return -1;
-	}
 
-	while ((e = readdir(dir)) != NULL) {
-		if (e->d_name[0] == '.')
-			continue;
-
-		if (parse_pci_addr_format(e->d_name, sizeof(e->d_name), &domain,
-				&bus, &devid, &function) != 0)
-			continue;
-
-		snprintf(dirname, sizeof(dirname), "%s/%s",
-				pci_get_sysfs_path(), e->d_name);
-		if (pci_scan_one(dirname, domain, bus, devid, function) < 0)
-			goto error;
-	}
-	closedir(dir);
-	return 0;
-
-error:
-	closedir(dir);
-	return -1;
-}
 
 /* Read PCI config space. */
 int rte_eal_pci_read_config(const struct rte_pci_device *device,
@@ -754,19 +472,3 @@ rte_eal_pci_ioport_unmap(struct rte_pci_ioport *p)
 
 	return ret;
 }
-
-/* Init the PCI EAL subsystem */
-int
-rte_eal_pci_init(void)
-{
-	/* for debug purposes, PCI can be disabled */
-	if (internal_config.no_pci)
-		return 0;
-
-	if (rte_eal_pci_scan() < 0) {
-		RTE_LOG(ERR, EAL, "%s(): Cannot scan PCI bus\n", __func__);
-		return -1;
-	}
-
-	return 0;
-}
-- 
2.7.4