X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=lib%2Flibrte_eal%2Flinuxapp%2Feal%2Feal_pci.c;h=63bcbceb1d916a000611d81376616d35aaf58708;hb=8bae1da2afe0;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..63bcbceb1d 100644
--- a/lib/librte_eal/linuxapp/eal/eal_pci.c
+++ b/lib/librte_eal/linuxapp/eal/eal_pci.c
@@ -69,7 +69,7 @@ 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 +77,10 @@ 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) {
@@ -97,6 +97,25 @@ error:
 	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)
@@ -106,26 +125,19 @@ pci_map_resource(void *requested_addr, int fd, off_t offset, size_t size)
 	/* 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)) {
+	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;
 }
 
 /* parse the "resource" sysfs file */
-#define IORESOURCE_MEM  0x00000200
-
 static int
 pci_parse_sysfs_resource(const char *filename, struct rte_pci_device *dev)
 {
@@ -221,7 +233,7 @@ 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 +241,7 @@ 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 +249,7 @@ 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 +258,7 @@ 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 +268,24 @@ 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) {
@@ -277,7 +296,7 @@ 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);
@@ -380,7 +399,7 @@ 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 +412,120 @@ 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, mapped = 0;
+
+	/* try mapping the NIC resources using VFIO if it exists */
+#ifdef VFIO_PRESENT
+	if (pci_vfio_is_enabled()) {
+		ret = pci_vfio_map_resource(dev);
+		if (ret == 0)
+			mapped = 1;
+		else if (ret < 0)
+			return ret;
+	}
+#endif
+	/* map resources for devices that use uio_pci_generic or igb_uio */
+	if (!mapped) {
+		ret = pci_uio_map_resource(dev);
+		if (ret != 0)
+			return ret;
+	}
+	return 0;
+}
+
 /*
  * If vendor/device ID match, call the devinit() function of the
  * driver.
@@ -400,8 +533,8 @@ 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 +568,16 @@ 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 &&
@@ -474,5 +614,21 @@ rte_eal_pci_init(void)
 		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;
 }