X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=lib%2Flibrte_eal%2Flinuxapp%2Feal%2Feal_pci.c;h=6d4932d8b6f122a5d6767a146b7ef17b682e20e2;hb=47cb11c9bfd3f15ec32fbef97401173b53172c71;hp=49b2a68c192179f9909a9cbfb7b3464c524fd8c1;hpb=6bf883260d0d00fd2351a2d24c7f86f69f8850fe;p=dpdk.git

diff --git a/lib/librte_eal/linuxapp/eal/eal_pci.c b/lib/librte_eal/linuxapp/eal/eal_pci.c
index 49b2a68c19..6d4932d8b6 100644
--- a/lib/librte_eal/linuxapp/eal/eal_pci.c
+++ b/lib/librte_eal/linuxapp/eal/eal_pci.c
@@ -41,6 +41,7 @@
 #include <rte_eal_memconfig.h>
 #include <rte_malloc.h>
 #include <rte_devargs.h>
+#include <rte_memcpy.h>
 
 #include "rte_pci_dev_ids.h"
 #include "eal_filesystem.h"
@@ -69,7 +70,7 @@ pci_unbind_kernel_driver(struct rte_pci_device *dev)
 	struct rte_pci_addr *loc = &dev->addr;
 
 	/* open /sys/bus/pci/devices/AAAA:BB:CC.D/driver */
-	rte_snprintf(filename, sizeof(filename),
+	snprintf(filename, sizeof(filename),
 	         SYSFS_PCI_DEVICES "/" PCI_PRI_FMT "/driver/unbind",
 	         loc->domain, loc->bus, loc->devid, loc->function);
 
@@ -77,10 +78,10 @@ pci_unbind_kernel_driver(struct rte_pci_device *dev)
 	if (f == NULL) /* device was not bound */
 		return 0;
 
-	n = rte_snprintf(buf, sizeof(buf), PCI_PRI_FMT "\n",
+	n = snprintf(buf, sizeof(buf), PCI_PRI_FMT "\n",
 	             loc->domain, loc->bus, loc->devid, loc->function);
 	if ((n < 0) || (n >= (int)sizeof(buf))) {
-		RTE_LOG(ERR, EAL, "%s(): rte_snprintf failed\n", __func__);
+		RTE_LOG(ERR, EAL, "%s(): snprintf failed\n", __func__);
 		goto error;
 	}
 	if (fwrite(buf, n, 1, f) == 0) {
@@ -97,35 +98,94 @@ error:
 	return -1;
 }
 
+static int
+pci_get_kernel_driver_by_path(const char *filename, char *dri_name)
+{
+	int count;
+	char path[PATH_MAX];
+	char *name;
+
+	if (!filename || !dri_name)
+		return -1;
+
+	count = readlink(filename, path, PATH_MAX);
+	if (count >= PATH_MAX)
+		return -1;
+
+	/* For device does not have a driver */
+	if (count < 0)
+		return 1;
+
+	path[count] = '\0';
+
+	name = strrchr(path, '/');
+	if (name) {
+		strncpy(dri_name, name + 1, strlen(name + 1) + 1);
+		return 0;
+	}
+
+	return -1;
+}
+
+void *
+pci_find_max_end_va(void)
+{
+	const struct rte_memseg *seg = rte_eal_get_physmem_layout();
+	const struct rte_memseg *last = seg;
+	unsigned i = 0;
+
+	for (i = 0; i < RTE_MAX_MEMSEG; i++, seg++) {
+		if (seg->addr == NULL)
+			break;
+
+		if (seg->addr > last->addr)
+			last = seg;
+
+	}
+	return RTE_PTR_ADD(last->addr, last->len);
+}
+
+
 /* map a particular resource from a file */
 void *
-pci_map_resource(void *requested_addr, int fd, off_t offset, size_t size)
+pci_map_resource(void *requested_addr, int fd, off_t offset, size_t size,
+		 int additional_flags)
 {
 	void *mapaddr;
 
 	/* Map the PCI memory resource of device */
 	mapaddr = mmap(requested_addr, size, PROT_READ | PROT_WRITE,
-			MAP_SHARED, fd, offset);
-	if (mapaddr == MAP_FAILED ||
-			(requested_addr != NULL && mapaddr != requested_addr)) {
+			MAP_SHARED | additional_flags, fd, offset);
+	if (mapaddr == MAP_FAILED) {
 		RTE_LOG(ERR, EAL, "%s(): cannot mmap(%d, %p, 0x%lx, 0x%lx): %s (%p)\n",
 			__func__, fd, requested_addr,
 			(unsigned long)size, (unsigned long)offset,
 			strerror(errno), mapaddr);
-		goto fail;
+	} else {
+		RTE_LOG(DEBUG, EAL, "  PCI memory mapped at %p\n", mapaddr);
 	}
 
-	RTE_LOG(DEBUG, EAL, "  PCI memory mapped at %p\n", mapaddr);
-
 	return mapaddr;
+}
 
-fail:
-	return NULL;
+/* unmap a particular resource */
+void
+pci_unmap_resource(void *requested_addr, size_t size)
+{
+	if (requested_addr == NULL)
+		return;
+
+	/* Unmap the PCI memory resource of device */
+	if (munmap(requested_addr, size)) {
+		RTE_LOG(ERR, EAL, "%s(): cannot munmap(%p, 0x%lx): %s\n",
+			__func__, requested_addr, (unsigned long)size,
+			strerror(errno));
+	} else
+		RTE_LOG(DEBUG, EAL, "  PCI memory unmapped at %p\n",
+				requested_addr);
 }
 
 /* parse the "resource" sysfs file */
-#define IORESOURCE_MEM  0x00000200
-
 static int
 pci_parse_sysfs_resource(const char *filename, struct rte_pci_device *dev)
 {
@@ -186,20 +246,6 @@ error:
 	return -1;
 }
 
-/* Compare two PCI device addresses. */
-static int
-pci_addr_comparison(struct rte_pci_addr *addr, struct rte_pci_addr *addr2)
-{
-	uint64_t dev_addr = (addr->domain << 24) + (addr->bus << 16) + (addr->devid << 8) + addr->function;
-	uint64_t dev_addr2 = (addr2->domain << 24) + (addr2->bus << 16) + (addr2->devid << 8) + addr2->function;
-
-	if (dev_addr > dev_addr2)
-		return 1;
-	else
-		return 0;
-}
-
-
 /* 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,
@@ -208,11 +254,12 @@ pci_scan_one(const char *dirname, uint16_t domain, uint8_t bus,
 	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) {
+	if (dev == NULL)
 		return -1;
-	}
 
 	memset(dev, 0, sizeof(*dev));
 	dev->addr.domain = domain;
@@ -221,7 +268,7 @@ pci_scan_one(const char *dirname, uint16_t domain, uint8_t bus,
 	dev->addr.function = function;
 
 	/* get vendor id */
-	rte_snprintf(filename, sizeof(filename), "%s/vendor", dirname);
+	snprintf(filename, sizeof(filename), "%s/vendor", dirname);
 	if (eal_parse_sysfs_value(filename, &tmp) < 0) {
 		free(dev);
 		return -1;
@@ -229,7 +276,7 @@ pci_scan_one(const char *dirname, uint16_t domain, uint8_t bus,
 	dev->id.vendor_id = (uint16_t)tmp;
 
 	/* get device id */
-	rte_snprintf(filename, sizeof(filename), "%s/device", dirname);
+	snprintf(filename, sizeof(filename), "%s/device", dirname);
 	if (eal_parse_sysfs_value(filename, &tmp) < 0) {
 		free(dev);
 		return -1;
@@ -237,7 +284,7 @@ pci_scan_one(const char *dirname, uint16_t domain, uint8_t bus,
 	dev->id.device_id = (uint16_t)tmp;
 
 	/* get subsystem_vendor id */
-	rte_snprintf(filename, sizeof(filename), "%s/subsystem_vendor",
+	snprintf(filename, sizeof(filename), "%s/subsystem_vendor",
 		 dirname);
 	if (eal_parse_sysfs_value(filename, &tmp) < 0) {
 		free(dev);
@@ -246,7 +293,7 @@ pci_scan_one(const char *dirname, uint16_t domain, uint8_t bus,
 	dev->id.subsystem_vendor_id = (uint16_t)tmp;
 
 	/* get subsystem_device id */
-	rte_snprintf(filename, sizeof(filename), "%s/subsystem_device",
+	snprintf(filename, sizeof(filename), "%s/subsystem_device",
 		 dirname);
 	if (eal_parse_sysfs_value(filename, &tmp) < 0) {
 		free(dev);
@@ -256,17 +303,24 @@ pci_scan_one(const char *dirname, uint16_t domain, uint8_t bus,
 
 	/* get max_vfs */
 	dev->max_vfs = 0;
-	rte_snprintf(filename, sizeof(filename), "%s/max_vfs", dirname);
+	snprintf(filename, sizeof(filename), "%s/max_vfs", dirname);
 	if (!access(filename, F_OK) &&
-	    eal_parse_sysfs_value(filename, &tmp) == 0) {
+	    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 */
-	rte_snprintf(filename, sizeof(filename), "%s/numa_node",
+	snprintf(filename, sizeof(filename), "%s/numa_node",
 		 dirname);
 	if (access(filename, R_OK) != 0) {
-		/* if no NUMA support just set node to 0 */
+		/* if no NUMA support just set node to -1 */
 		dev->numa_node = -1;
 	} else {
 		if (eal_parse_sysfs_value(filename, &tmp) < 0) {
@@ -277,26 +331,56 @@ pci_scan_one(const char *dirname, uint16_t domain, uint8_t bus,
 	}
 
 	/* parse resources */
-	rte_snprintf(filename, sizeof(filename), "%s/resource", dirname);
+	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) {
+		if (!strcmp(driver, "vfio-pci"))
+			dev->pt_driver = RTE_PT_VFIO;
+		else if (!strcmp(driver, "igb_uio"))
+			dev->pt_driver = RTE_PT_IGB_UIO;
+		else if (!strcmp(driver, "uio_pci_generic"))
+			dev->pt_driver = RTE_PT_UIO_GENERIC;
+		else
+			dev->pt_driver = RTE_PT_UNKNOWN;
+	} else if (ret < 0) {
+		RTE_LOG(ERR, EAL, "Fail to get kernel driver\n");
+		free(dev);
+		return -1;
+	} else
+		dev->pt_driver = RTE_PT_UNKNOWN;
+
 	/* device is valid, add in list (sorted) */
 	if (TAILQ_EMPTY(&pci_device_list)) {
 		TAILQ_INSERT_TAIL(&pci_device_list, dev, next);
 	}
 	else {
 		struct rte_pci_device *dev2 = NULL;
+		int ret;
 
 		TAILQ_FOREACH(dev2, &pci_device_list, next) {
-			if (pci_addr_comparison(&dev->addr, &dev2->addr))
+			ret = rte_eal_compare_pci_addr(&dev->addr, &dev2->addr);
+			if (ret > 0)
 				continue;
-			else {
+			else if (ret < 0) {
 				TAILQ_INSERT_BEFORE(dev2, dev, next);
 				return 0;
+			} else { /* already registered */
+				/* update pt_driver */
+				dev2->pt_driver = dev->pt_driver;
+				dev2->max_vfs = dev->max_vfs;
+				memmove(dev2->mem_resource,
+					dev->mem_resource,
+					sizeof(dev->mem_resource));
+				free(dev);
+				return 0;
 			}
 		}
 		TAILQ_INSERT_TAIL(&pci_device_list, dev, next);
@@ -356,8 +440,8 @@ error:
  * Scan the content of the PCI bus, and the devices in the devices
  * list
  */
-static int
-pci_scan(void)
+int
+rte_eal_pci_scan(void)
 {
 	struct dirent *e;
 	DIR *dir;
@@ -380,7 +464,7 @@ pci_scan(void)
 				&bus, &devid, &function) != 0)
 			continue;
 
-		rte_snprintf(dirname, sizeof(dirname), "%s/%s", SYSFS_PCI_DEVICES,
+		snprintf(dirname, sizeof(dirname), "%s/%s", SYSFS_PCI_DEVICES,
 			 e->d_name);
 		if (pci_scan_one(dirname, domain, bus, devid, function) < 0)
 			goto error;
@@ -393,6 +477,149 @@ error:
 	return -1;
 }
 
+#ifdef RTE_PCI_CONFIG
+static int
+pci_config_extended_tag(struct rte_pci_device *dev)
+{
+	struct rte_pci_addr *loc = &dev->addr;
+	char filename[PATH_MAX];
+	char buf[BUFSIZ];
+	FILE *f;
+
+	/* not configured, let it as is */
+	if (strncmp(RTE_PCI_EXTENDED_TAG, "on", 2) != 0 &&
+		strncmp(RTE_PCI_EXTENDED_TAG, "off", 3) != 0)
+		return 0;
+
+	snprintf(filename, sizeof(filename),
+		SYSFS_PCI_DEVICES "/" PCI_PRI_FMT "/" "extended_tag",
+		loc->domain, loc->bus, loc->devid, loc->function);
+	f = fopen(filename, "rw+");
+	if (!f)
+		return -1;
+
+	fgets(buf, sizeof(buf), f);
+	if (strncmp(RTE_PCI_EXTENDED_TAG, "on", 2) == 0) {
+		/* enable Extended Tag*/
+		if (strncmp(buf, "on", 2) != 0) {
+			fseek(f, 0, SEEK_SET);
+			fputs("on", f);
+		}
+	} else {
+		/* disable Extended Tag */
+		if (strncmp(buf, "off", 3) != 0) {
+			fseek(f, 0, SEEK_SET);
+			fputs("off", f);
+		}
+	}
+	fclose(f);
+
+	return 0;
+}
+
+static int
+pci_config_max_read_request_size(struct rte_pci_device *dev)
+{
+	struct rte_pci_addr *loc = &dev->addr;
+	char filename[PATH_MAX];
+	char buf[BUFSIZ], param[BUFSIZ];
+	FILE *f;
+	/* size can be 128, 256, 512, 1024, 2048, 4096 */
+	uint32_t max_size = RTE_PCI_MAX_READ_REQUEST_SIZE;
+
+	/* not configured, let it as is */
+	if (!max_size)
+		return 0;
+
+	snprintf(filename, sizeof(filename),
+		SYSFS_PCI_DEVICES "/" PCI_PRI_FMT "/" "max_read_request_size",
+			loc->domain, loc->bus, loc->devid, loc->function);
+	f = fopen(filename, "rw+");
+	if (!f)
+		return -1;
+
+	fgets(buf, sizeof(buf), f);
+	snprintf(param, sizeof(param), "%d", max_size);
+
+	/* check if the size to be set is the same as current */
+	if (strcmp(buf, param) == 0) {
+		fclose(f);
+		return 0;
+	}
+	fseek(f, 0, SEEK_SET);
+	fputs(param, f);
+	fclose(f);
+
+	return 0;
+}
+
+static void
+pci_config_space_set(struct rte_pci_device *dev)
+{
+	if (rte_eal_process_type() != RTE_PROC_PRIMARY)
+		return;
+
+	/* configure extended tag */
+	pci_config_extended_tag(dev);
+
+	/* configure max read request size */
+	pci_config_max_read_request_size(dev);
+}
+#endif
+
+static int
+pci_map_device(struct rte_pci_device *dev)
+{
+	int ret = -1;
+
+	/* try mapping the NIC resources using VFIO if it exists */
+	switch (dev->pt_driver) {
+	case RTE_PT_VFIO:
+#ifdef VFIO_PRESENT
+		if (pci_vfio_is_enabled())
+			ret = pci_vfio_map_resource(dev);
+#endif
+		break;
+	case RTE_PT_IGB_UIO:
+	case RTE_PT_UIO_GENERIC:
+		/* map resources for devices that use uio */
+		ret = pci_uio_map_resource(dev);
+		break;
+	default:
+		RTE_LOG(DEBUG, EAL, "  Not managed by known pt driver,"
+			" skipped\n");
+		ret = 1;
+		break;
+	}
+
+	return ret;
+}
+
+#ifdef RTE_LIBRTE_EAL_HOTPLUG
+static void
+pci_unmap_device(struct rte_pci_device *dev)
+{
+	if (dev == NULL)
+		return;
+
+	/* try unmapping the NIC resources using VFIO if it exists */
+	switch (dev->pt_driver) {
+	case RTE_PT_VFIO:
+		RTE_LOG(ERR, EAL, "Hotplug doesn't support vfio yet\n");
+		break;
+	case RTE_PT_IGB_UIO:
+	case RTE_PT_UIO_GENERIC:
+		/* unmap resources for devices that use uio */
+		pci_uio_unmap_resource(dev);
+		break;
+	default:
+		RTE_LOG(DEBUG, EAL, "  Not managed by known pt driver,"
+			" skipped\n");
+		break;
+	}
+}
+#endif /* RTE_LIBRTE_EAL_HOTPLUG */
+
 /*
  * If vendor/device ID match, call the devinit() function of the
  * driver.
@@ -400,8 +627,8 @@ error:
 int
 rte_eal_pci_probe_one_driver(struct rte_pci_driver *dr, struct rte_pci_device *dev)
 {
+	int ret;
 	struct rte_pci_id *id_table;
-	int ret = 0;
 
 	for (id_table = dr->id_table ; id_table->vendor_id != 0; id_table++) {
 
@@ -435,9 +662,16 @@ rte_eal_pci_probe_one_driver(struct rte_pci_driver *dr, struct rte_pci_device *d
 			return 1;
 		}
 
-		if (dr->drv_flags & RTE_PCI_DRV_NEED_IGB_UIO) {
+		if (dr->drv_flags & RTE_PCI_DRV_NEED_MAPPING) {
+#ifdef RTE_PCI_CONFIG
+			/*
+			 * Set PCIe config space for high performance.
+			 * Return value can be ignored.
+			 */
+			pci_config_space_set(dev);
+#endif
 			/* map resources for devices that use igb_uio */
-			ret = pci_uio_map_resource(dev);
+			ret = pci_map_device(dev);
 			if (ret != 0)
 				return ret;
 		} else if (dr->drv_flags & RTE_PCI_DRV_FORCE_UNBIND &&
@@ -457,6 +691,75 @@ rte_eal_pci_probe_one_driver(struct rte_pci_driver *dr, struct rte_pci_device *d
 	return 1;
 }
 
+#ifdef RTE_LIBRTE_EAL_HOTPLUG
+/*
+ * If vendor/device ID match, call the devuninit() function of the
+ * driver.
+ */
+int
+rte_eal_pci_close_one_driver(struct rte_pci_driver *dr,
+		struct rte_pci_device *dev)
+{
+	struct rte_pci_id *id_table;
+
+	if ((dr == NULL) || (dev == NULL))
+		return -EINVAL;
+
+	for (id_table = dr->id_table ; id_table->vendor_id != 0; id_table++) {
+
+		/* check if device's identifiers match the driver's ones */
+		if (id_table->vendor_id != dev->id.vendor_id &&
+		    id_table->vendor_id != PCI_ANY_ID)
+			continue;
+		if (id_table->device_id != dev->id.device_id &&
+		    id_table->device_id != PCI_ANY_ID)
+			continue;
+		if (id_table->subsystem_vendor_id !=
+		    dev->id.subsystem_vendor_id &&
+		    id_table->subsystem_vendor_id != PCI_ANY_ID)
+			continue;
+		if (id_table->subsystem_device_id !=
+		    dev->id.subsystem_device_id &&
+		    id_table->subsystem_device_id != PCI_ANY_ID)
+			continue;
+
+		struct rte_pci_addr *loc = &dev->addr;
+
+		RTE_LOG(DEBUG, EAL,
+				"PCI device "PCI_PRI_FMT" on NUMA socket %i\n",
+				loc->domain, loc->bus, loc->devid,
+				loc->function, dev->numa_node);
+
+		RTE_LOG(DEBUG, EAL, "  remove driver: %x:%x %s\n",
+				dev->id.vendor_id, dev->id.device_id,
+				dr->name);
+
+		/* call the driver devuninit() function */
+		if (dr->devuninit && (dr->devuninit(dev) < 0))
+			return -1;	/* negative value is an error */
+
+		/* clear driver structure */
+		dev->driver = NULL;
+
+		if (dr->drv_flags & RTE_PCI_DRV_NEED_MAPPING)
+			/* unmap resources for devices that use igb_uio */
+			pci_unmap_device(dev);
+
+		return 0;
+	}
+	/* return positive value if driver is not found */
+	return 1;
+}
+#else /* RTE_LIBRTE_EAL_HOTPLUG */
+int
+rte_eal_pci_close_one_driver(struct rte_pci_driver *dr __rte_unused,
+		struct rte_pci_device *dev __rte_unused)
+{
+	RTE_LOG(ERR, EAL, "Hotplug support isn't enabled\n");
+	return -1;
+}
+#endif /* RTE_LIBRTE_EAL_HOTPLUG */
+
 /* Init the PCI EAL subsystem */
 int
 rte_eal_pci_init(void)
@@ -470,9 +773,25 @@ rte_eal_pci_init(void)
 	if (internal_config.no_pci)
 		return 0;
 
-	if (pci_scan() < 0) {
+	if (rte_eal_pci_scan() < 0) {
 		RTE_LOG(ERR, EAL, "%s(): Cannot scan PCI bus\n", __func__);
 		return -1;
 	}
+#ifdef VFIO_PRESENT
+	pci_vfio_enable();
+
+	if (pci_vfio_is_enabled()) {
+
+		/* if we are primary process, create a thread to communicate with
+		 * secondary processes. the thread will use a socket to wait for
+		 * requests from secondary process to send open file descriptors,
+		 * because VFIO does not allow multiple open descriptors on a group or
+		 * VFIO container.
+		 */
+		if (internal_config.process_type == RTE_PROC_PRIMARY &&
+				pci_vfio_mp_sync_setup() < 0)
+			return -1;
+	}
+#endif
 	return 0;
 }