X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=lib%2Flibrte_eal%2Flinuxapp%2Feal%2Feal_pci.c;h=b4dbf953afcb723c8b9746a796d45362cec31379;hb=84cc318424d49372dd2a5fbf3cf84426bf95acce;hp=9f752529b9adfa1e5a832218bab42a47f3406f6b;hpb=b8eb345378bdefc4c976eaaf5abb221e0aca3460;p=dpdk.git

diff --git a/lib/librte_eal/linuxapp/eal/eal_pci.c b/lib/librte_eal/linuxapp/eal/eal_pci.c
index 9f752529b9..b4dbf953af 100644
--- a/lib/librte_eal/linuxapp/eal/eal_pci.c
+++ b/lib/librte_eal/linuxapp/eal/eal_pci.c
@@ -35,6 +35,7 @@
 #include <dirent.h>
 
 #include <rte_log.h>
+#include <rte_bus.h>
 #include <rte_pci.h>
 #include <rte_eal_memconfig.h>
 #include <rte_malloc.h>
@@ -44,6 +45,7 @@
 #include "eal_filesystem.h"
 #include "eal_private.h"
 #include "eal_pci_init.h"
+#include "eal_vfio.h"
 
 /**
  * @file
@@ -54,44 +56,7 @@
  * IGB_UIO driver (or doesn't initialize, if the device wasn't bound to it).
  */
 
-/* unbind kernel driver for this device */
-int
-pci_unbind_kernel_driver(struct rte_pci_device *dev)
-{
-	int n;
-	FILE *f;
-	char filename[PATH_MAX];
-	char buf[BUFSIZ];
-	struct rte_pci_addr *loc = &dev->addr;
-
-	/* open /sys/bus/pci/devices/AAAA:BB:CC.D/driver */
-	snprintf(filename, sizeof(filename),
-	         SYSFS_PCI_DEVICES "/" PCI_PRI_FMT "/driver/unbind",
-	         loc->domain, loc->bus, loc->devid, loc->function);
-
-	f = fopen(filename, "w");
-	if (f == NULL) /* device was not bound */
-		return 0;
-
-	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(): snprintf failed\n", __func__);
-		goto error;
-	}
-	if (fwrite(buf, n, 1, f) == 0) {
-		RTE_LOG(ERR, EAL, "%s(): could not write to %s\n", __func__,
-				filename);
-		goto error;
-	}
-
-	fclose(f);
-	return 0;
-
-error:
-	fclose(f);
-	return -1;
-}
+extern struct rte_pci_bus rte_pci_bus;
 
 static int
 pci_get_kernel_driver_by_path(const char *filename, char *dri_name)
@@ -124,7 +89,7 @@ pci_get_kernel_driver_by_path(const char *filename, char *dri_name)
 
 /* Map pci device */
 int
-rte_eal_pci_map_device(struct rte_pci_device *dev)
+rte_pci_map_device(struct rte_pci_device *dev)
 {
 	int ret = -1;
 
@@ -138,8 +103,10 @@ rte_eal_pci_map_device(struct rte_pci_device *dev)
 		break;
 	case RTE_KDRV_IGB_UIO:
 	case RTE_KDRV_UIO_GENERIC:
-		/* map resources for devices that use uio */
-		ret = pci_uio_map_resource(dev);
+		if (rte_eal_using_phys_addrs()) {
+			/* map resources for devices that use uio */
+			ret = pci_uio_map_resource(dev);
+		}
 		break;
 	default:
 		RTE_LOG(DEBUG, EAL,
@@ -153,12 +120,15 @@ rte_eal_pci_map_device(struct rte_pci_device *dev)
 
 /* Unmap pci device */
 void
-rte_eal_pci_unmap_device(struct rte_pci_device *dev)
+rte_pci_unmap_device(struct rte_pci_device *dev)
 {
 	/* try unmapping the NIC resources using VFIO if it exists */
 	switch (dev->kdrv) {
 	case RTE_KDRV_VFIO:
-		RTE_LOG(ERR, EAL, "Hotplug doesn't support vfio yet\n");
+#ifdef VFIO_PRESENT
+		if (pci_vfio_is_enabled())
+			pci_vfio_unmap_resource(dev);
+#endif
 		break;
 	case RTE_KDRV_IGB_UIO:
 	case RTE_KDRV_UIO_GENERIC:
@@ -190,12 +160,13 @@ pci_find_max_end_va(void)
 	return RTE_PTR_ADD(last->addr, last->len);
 }
 
-/* parse the "resource" sysfs file */
-static int
-pci_parse_sysfs_resource(const char *filename, struct rte_pci_device *dev)
+/* parse one line of the "resource" sysfs file (note that the 'line'
+ * string is modified)
+ */
+int
+pci_parse_one_sysfs_resource(char *line, size_t len, uint64_t *phys_addr,
+	uint64_t *end_addr, uint64_t *flags)
 {
-	FILE *f;
-	char buf[BUFSIZ];
 	union pci_resource_info {
 		struct {
 			char *phys_addr;
@@ -204,6 +175,31 @@ pci_parse_sysfs_resource(const char *filename, struct rte_pci_device *dev)
 		};
 		char *ptrs[PCI_RESOURCE_FMT_NVAL];
 	} res_info;
+
+	if (rte_strsplit(line, len, res_info.ptrs, 3, ' ') != 3) {
+		RTE_LOG(ERR, EAL,
+			"%s(): bad resource format\n", __func__);
+		return -1;
+	}
+	errno = 0;
+	*phys_addr = strtoull(res_info.phys_addr, NULL, 16);
+	*end_addr = strtoull(res_info.end_addr, NULL, 16);
+	*flags = strtoull(res_info.flags, NULL, 16);
+	if (errno != 0) {
+		RTE_LOG(ERR, EAL,
+			"%s(): bad resource format\n", __func__);
+		return -1;
+	}
+
+	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;
 
@@ -220,21 +216,9 @@ pci_parse_sysfs_resource(const char *filename, struct rte_pci_device *dev)
 				"%s(): cannot read resource\n", __func__);
 			goto error;
 		}
-
-		if (rte_strsplit(buf, sizeof(buf), res_info.ptrs, 3, ' ') != 3) {
-			RTE_LOG(ERR, EAL,
-				"%s(): bad resource format\n", __func__);
+		if (pci_parse_one_sysfs_resource(buf, sizeof(buf), &phys_addr,
+				&end_addr, &flags) < 0)
 			goto error;
-		}
-		errno = 0;
-		phys_addr = strtoull(res_info.phys_addr, NULL, 16);
-		end_addr = strtoull(res_info.end_addr, NULL, 16);
-		flags = strtoull(res_info.flags, NULL, 16);
-		if (errno != 0) {
-			RTE_LOG(ERR, EAL,
-				"%s(): bad resource format\n", __func__);
-			goto error;
-		}
 
 		if (flags & IORESOURCE_MEM) {
 			dev->mem_resource[i].phys_addr = phys_addr;
@@ -253,8 +237,7 @@ error:
 
 /* 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)
+pci_scan_one(const char *dirname, const struct rte_pci_addr *addr)
 {
 	char filename[PATH_MAX];
 	unsigned long tmp;
@@ -267,10 +250,7 @@ pci_scan_one(const char *dirname, uint16_t domain, uint8_t bus,
 		return -1;
 
 	memset(dev, 0, sizeof(*dev));
-	dev->addr.domain = domain;
-	dev->addr.bus = bus;
-	dev->addr.devid = devid;
-	dev->addr.function = function;
+	dev->addr = *addr;
 
 	/* get vendor id */
 	snprintf(filename, sizeof(filename), "%s/vendor", dirname);
@@ -306,6 +286,16 @@ pci_scan_one(const char *dirname, uint16_t domain, uint8_t bus,
 	}
 	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);
@@ -321,20 +311,21 @@ pci_scan_one(const char *dirname, uint16_t domain, uint8_t bus,
 			dev->max_vfs = (uint16_t)tmp;
 	}
 
-	/* get numa node */
+	/* get numa node, default to 0 if not present */
 	snprintf(filename, sizeof(filename), "%s/numa_node",
 		 dirname);
-	if (access(filename, R_OK) != 0) {
-		/* if no NUMA support, set default to 0 */
-		dev->numa_node = 0;
+
+	if (access(filename, F_OK) != -1) {
+		if (eal_parse_sysfs_value(filename, &tmp) == 0)
+			dev->device.numa_node = tmp;
+		else
+			dev->device.numa_node = -1;
 	} else {
-		if (eal_parse_sysfs_value(filename, &tmp) < 0) {
-			free(dev);
-			return -1;
-		}
-		dev->numa_node = tmp;
+		dev->device.numa_node = 0;
 	}
 
+	pci_name_set(dev);
+
 	/* parse resources */
 	snprintf(filename, sizeof(filename), "%s/resource", dirname);
 	if (pci_parse_sysfs_resource(filename, dev) < 0) {
@@ -365,40 +356,53 @@ pci_scan_one(const char *dirname, uint16_t domain, uint8_t bus,
 		dev->kdrv = RTE_KDRV_NONE;
 
 	/* device is valid, add in list (sorted) */
-	if (TAILQ_EMPTY(&pci_device_list)) {
-		TAILQ_INSERT_TAIL(&pci_device_list, dev, next);
+	if (TAILQ_EMPTY(&rte_pci_bus.device_list)) {
+		rte_pci_add_device(dev);
 	} else {
 		struct rte_pci_device *dev2;
 		int ret;
 
-		TAILQ_FOREACH(dev2, &pci_device_list, next) {
+		TAILQ_FOREACH(dev2, &rte_pci_bus.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_pci_insert_device(dev2, dev);
 			} else { /* already registered */
 				dev2->kdrv = dev->kdrv;
 				dev2->max_vfs = dev->max_vfs;
+				pci_name_set(dev2);
 				memmove(dev2->mem_resource, dev->mem_resource,
 					sizeof(dev->mem_resource));
 				free(dev);
 			}
 			return 0;
 		}
-		TAILQ_INSERT_TAIL(&pci_device_list, dev, next);
+
+		rte_pci_add_device(dev);
 	}
 
 	return 0;
 }
 
+int
+pci_update_device(const struct rte_pci_addr *addr)
+{
+	char filename[PATH_MAX];
+
+	snprintf(filename, sizeof(filename), "%s/" PCI_PRI_FMT,
+		 pci_get_sysfs_path(), addr->domain, addr->bus, addr->devid,
+		 addr->function);
+
+	return pci_scan_one(filename, addr);
+}
+
 /*
  * 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)
+parse_pci_addr_format(const char *buf, int bufsize, struct rte_pci_addr *addr)
 {
 	/* first split on ':' */
 	union splitaddr {
@@ -426,10 +430,10 @@ parse_pci_addr_format(const char *buf, int bufsize, uint16_t *domain,
 
 	/* 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);
+	addr->domain = strtoul(splitaddr.domain, NULL, 16);
+	addr->bus = strtoul(splitaddr.bus, NULL, 16);
+	addr->devid = strtoul(splitaddr.devid, NULL, 16);
+	addr->function = strtoul(splitaddr.function, NULL, 10);
 	if (errno != 0)
 		goto error;
 
@@ -445,15 +449,18 @@ error:
  * list
  */
 int
-rte_eal_pci_scan(void)
+rte_pci_scan(void)
 {
 	struct dirent *e;
 	DIR *dir;
 	char dirname[PATH_MAX];
-	uint16_t domain;
-	uint8_t bus, devid, function;
+	struct rte_pci_addr addr;
+
+	/* for debug purposes, PCI can be disabled */
+	if (internal_config.no_pci)
+		return 0;
 
-	dir = opendir(SYSFS_PCI_DEVICES);
+	dir = opendir(pci_get_sysfs_path());
 	if (dir == NULL) {
 		RTE_LOG(ERR, EAL, "%s(): opendir failed: %s\n",
 			__func__, strerror(errno));
@@ -464,13 +471,13 @@ rte_eal_pci_scan(void)
 		if (e->d_name[0] == '.')
 			continue;
 
-		if (parse_pci_addr_format(e->d_name, sizeof(e->d_name), &domain,
-				&bus, &devid, &function) != 0)
+		if (parse_pci_addr_format(e->d_name, sizeof(e->d_name), &addr) != 0)
 			continue;
 
-		snprintf(dirname, sizeof(dirname), "%s/%s", SYSFS_PCI_DEVICES,
-			 e->d_name);
-		if (pci_scan_one(dirname, domain, bus, devid, function) < 0)
+		snprintf(dirname, sizeof(dirname), "%s/%s",
+				pci_get_sysfs_path(), e->d_name);
+
+		if (pci_scan_one(dirname, &addr) < 0)
 			goto error;
 	}
 	closedir(dir);
@@ -481,21 +488,104 @@ error:
 	return -1;
 }
 
-#ifdef RTE_PCI_CONFIG
 /*
- * It is deprecated, all its configurations have been moved into
- * each PMD respectively.
+ * Is pci device bound to any kdrv
  */
-void
-pci_config_space_set(__rte_unused struct rte_pci_device *dev)
+static inline int
+pci_one_device_is_bound(void)
+{
+	struct rte_pci_device *dev = NULL;
+	int ret = 0;
+
+	FOREACH_DEVICE_ON_PCIBUS(dev) {
+		if (dev->kdrv == RTE_KDRV_UNKNOWN ||
+		    dev->kdrv == RTE_KDRV_NONE) {
+			continue;
+		} else {
+			ret = 1;
+			break;
+		}
+	}
+	return ret;
+}
+
+/*
+ * Any one of the device bound to uio
+ */
+static inline int
+pci_one_device_bound_uio(void)
 {
-	RTE_LOG(DEBUG, EAL, "Nothing here, as it is deprecated\n");
+	struct rte_pci_device *dev = NULL;
+
+	FOREACH_DEVICE_ON_PCIBUS(dev) {
+		if (dev->kdrv == RTE_KDRV_IGB_UIO ||
+		   dev->kdrv == RTE_KDRV_UIO_GENERIC) {
+			return 1;
+		}
+	}
+	return 0;
 }
+
+/*
+ * Any one of the device has iova as va
+ */
+static inline int
+pci_one_device_has_iova_va(void)
+{
+	struct rte_pci_device *dev = NULL;
+	struct rte_pci_driver *drv = NULL;
+
+	FOREACH_DRIVER_ON_PCIBUS(drv) {
+		if (drv && drv->drv_flags & RTE_PCI_DRV_IOVA_AS_VA) {
+			FOREACH_DEVICE_ON_PCIBUS(dev) {
+				if (dev->kdrv == RTE_KDRV_VFIO &&
+				    rte_pci_match(drv, dev))
+					return 1;
+			}
+		}
+	}
+	return 0;
+}
+
+/*
+ * Get iommu class of PCI devices on the bus.
+ */
+enum rte_iova_mode
+rte_pci_get_iommu_class(void)
+{
+	bool is_bound;
+	bool is_vfio_noiommu_enabled = true;
+	bool has_iova_va;
+	bool is_bound_uio;
+
+	is_bound = pci_one_device_is_bound();
+	if (!is_bound)
+		return RTE_IOVA_DC;
+
+	has_iova_va = pci_one_device_has_iova_va();
+	is_bound_uio = pci_one_device_bound_uio();
+#ifdef VFIO_PRESENT
+	is_vfio_noiommu_enabled = vfio_noiommu_is_enabled() == true ?
+					true : false;
 #endif
 
+	if (has_iova_va && !is_bound_uio && !is_vfio_noiommu_enabled)
+		return RTE_IOVA_VA;
+
+	if (has_iova_va) {
+		RTE_LOG(WARNING, EAL, "Some devices want iova as va but pa will be used because.. ");
+		if (is_vfio_noiommu_enabled)
+			RTE_LOG(WARNING, EAL, "vfio-noiommu mode configured\n");
+		if (is_bound_uio)
+			RTE_LOG(WARNING, EAL, "few device bound to UIO\n");
+	}
+
+	return RTE_IOVA_PA;
+}
+
 /* Read PCI config space. */
-int rte_eal_pci_read_config(const struct rte_pci_device *device,
-			    void *buf, size_t len, off_t offset)
+int rte_pci_read_config(const struct rte_pci_device *device,
+		void *buf, size_t len, off_t offset)
 {
 	const struct rte_intr_handle *intr_handle = &device->intr_handle;
 
@@ -519,8 +609,8 @@ int rte_eal_pci_read_config(const struct rte_pci_device *device,
 }
 
 /* Write PCI config space. */
-int rte_eal_pci_write_config(const struct rte_pci_device *device,
-			     const void *buf, size_t len, off_t offset)
+int rte_pci_write_config(const struct rte_pci_device *device,
+		const void *buf, size_t len, off_t offset)
 {
 	const struct rte_intr_handle *intr_handle = &device->intr_handle;
 
@@ -546,7 +636,7 @@ int rte_eal_pci_write_config(const struct rte_pci_device *device,
 #if defined(RTE_ARCH_X86)
 static int
 pci_ioport_map(struct rte_pci_device *dev, int bar __rte_unused,
-	       struct rte_pci_ioport *p)
+		struct rte_pci_ioport *p)
 {
 	uint16_t start, end;
 	FILE *fp;
@@ -604,8 +694,8 @@ pci_ioport_map(struct rte_pci_device *dev, int bar __rte_unused,
 #endif
 
 int
-rte_eal_pci_ioport_map(struct rte_pci_device *dev, int bar,
-		       struct rte_pci_ioport *p)
+rte_pci_ioport_map(struct rte_pci_device *dev, int bar,
+		struct rte_pci_ioport *p)
 {
 	int ret = -1;
 
@@ -617,8 +707,14 @@ rte_eal_pci_ioport_map(struct rte_pci_device *dev, int bar,
 		break;
 #endif
 	case RTE_KDRV_IGB_UIO:
+		ret = pci_uio_ioport_map(dev, bar, p);
+		break;
 	case RTE_KDRV_UIO_GENERIC:
+#if defined(RTE_ARCH_X86)
+		ret = pci_ioport_map(dev, bar, p);
+#else
 		ret = pci_uio_ioport_map(dev, bar, p);
+#endif
 		break;
 	case RTE_KDRV_NONE:
 #if defined(RTE_ARCH_X86)
@@ -636,8 +732,8 @@ rte_eal_pci_ioport_map(struct rte_pci_device *dev, int bar,
 }
 
 void
-rte_eal_pci_ioport_read(struct rte_pci_ioport *p,
-			void *data, size_t len, off_t offset)
+rte_pci_ioport_read(struct rte_pci_ioport *p,
+		void *data, size_t len, off_t offset)
 {
 	switch (p->dev->kdrv) {
 #ifdef VFIO_PRESENT
@@ -646,21 +742,24 @@ rte_eal_pci_ioport_read(struct rte_pci_ioport *p,
 		break;
 #endif
 	case RTE_KDRV_IGB_UIO:
+		pci_uio_ioport_read(p, data, len, offset);
+		break;
 	case RTE_KDRV_UIO_GENERIC:
 		pci_uio_ioport_read(p, data, len, offset);
 		break;
-	default:
+	case RTE_KDRV_NONE:
 #if defined(RTE_ARCH_X86)
-		/* special case for x86 ... */
 		pci_uio_ioport_read(p, data, len, offset);
 #endif
 		break;
+	default:
+		break;
 	}
 }
 
 void
-rte_eal_pci_ioport_write(struct rte_pci_ioport *p,
-			 const void *data, size_t len, off_t offset)
+rte_pci_ioport_write(struct rte_pci_ioport *p,
+		const void *data, size_t len, off_t offset)
 {
 	switch (p->dev->kdrv) {
 #ifdef VFIO_PRESENT
@@ -669,78 +768,51 @@ rte_eal_pci_ioport_write(struct rte_pci_ioport *p,
 		break;
 #endif
 	case RTE_KDRV_IGB_UIO:
+		pci_uio_ioport_write(p, data, len, offset);
+		break;
 	case RTE_KDRV_UIO_GENERIC:
 		pci_uio_ioport_write(p, data, len, offset);
 		break;
-	default:
+	case RTE_KDRV_NONE:
 #if defined(RTE_ARCH_X86)
-		/* special case for x86 ... */
 		pci_uio_ioport_write(p, data, len, offset);
 #endif
 		break;
+	default:
+		break;
 	}
 }
 
 int
-rte_eal_pci_ioport_unmap(struct rte_pci_ioport *p)
+rte_pci_ioport_unmap(struct rte_pci_ioport *p)
 {
-	int ret;
+	int ret = -1;
 
 	switch (p->dev->kdrv) {
 #ifdef VFIO_PRESENT
 	case RTE_KDRV_VFIO:
-		ret = -1;
 		if (pci_vfio_is_enabled())
 			ret = pci_vfio_ioport_unmap(p);
 		break;
 #endif
 	case RTE_KDRV_IGB_UIO:
-	case RTE_KDRV_UIO_GENERIC:
 		ret = pci_uio_ioport_unmap(p);
 		break;
-	default:
+	case RTE_KDRV_UIO_GENERIC:
 #if defined(RTE_ARCH_X86)
-		/* special case for x86 ... nothing to do */
 		ret = 0;
 #else
-		ret = -1;
+		ret = pci_uio_ioport_unmap(p);
 #endif
 		break;
+	case RTE_KDRV_NONE:
+#if defined(RTE_ARCH_X86)
+		ret = 0;
+#endif
+		break;
+	default:
+		break;
 	}
 
 	return ret;
 }
-
-/* Init the PCI EAL subsystem */
-int
-rte_eal_pci_init(void)
-{
-	TAILQ_INIT(&pci_driver_list);
-	TAILQ_INIT(&pci_device_list);
-
-	/* 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;
-	}
-#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;
-}