eal/linux: map pci memory resources after hugepages

Multi-process DPDK application must mmap hugepages and PCI resources
into the same virtual address space. By default the virtual addresses
are chosen by the primary process automatically when calling the mmap.
But sometimes the chosen virtual addresses aren't usable in secondary
process - for example, secondary process is linked with more libraries
than primary process, and the library occupies the same address space
that the primary process has requested for PCI mappings.

This patch makes EAL try and map PCI BARs right after the hugepages
(instead of location chosen by mmap) in virtual memory, so that PCI BARs
have less chance of ending up in random places in virtual memory.

Signed-off-by: Liang Xu <liang.xu@cinfotech.cn>
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>

lib/librte_eal/linuxapp/eal/eal_pci.c

@@ -97,6 +97,25 @@ pci_unbind_kernel_driver(struct rte_pci_device *dev)
 	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)
@@ -106,21 +125,16 @@ 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 */

lib/librte_eal/linuxapp/eal/eal_pci_init.h

@@ -59,6 +59,12 @@ struct mapped_pci_resource {
 TAILQ_HEAD(mapped_pci_res_list, mapped_pci_resource);
 extern struct mapped_pci_res_list *pci_res_list;
 
+/*
+ * Helper function to map PCI resources right after hugepages in virtual memory
+ */
+extern void *pci_map_addr;
+void *pci_find_max_end_va(void);
+
 void *pci_map_resource(void *requested_addr, int fd, off_t offset,
 		size_t size);
 

lib/librte_eal/linuxapp/eal/eal_pci_uio.c

@@ -35,6 +35,7 @@
 #include <fcntl.h>
 #include <dirent.h>
 #include <sys/stat.h>
+#include <sys/mman.h>
 
 #include <rte_log.h>
 #include <rte_pci.h>
@@ -48,6 +49,8 @@
 
 static int pci_parse_sysfs_value(const char *filename, uint64_t *val);
 
+void *pci_map_addr = NULL;
+
 
 #define OFF_MAX              ((uint64_t)(off_t)-1)
 static int
@@ -371,10 +374,16 @@ pci_uio_map_resource(struct rte_pci_device *dev)
 			if (maps[j].addr != NULL)
 				fail = 1;
 			else {
-				mapaddr = pci_map_resource(NULL, fd, (off_t)offset,
+				/* try mapping somewhere close to the end of hugepages */
+				if (pci_map_addr == NULL)
+					pci_map_addr = pci_find_max_end_va();
+
+				mapaddr = pci_map_resource(pci_map_addr, fd, (off_t)offset,
 						(size_t)maps[j].size);
-				if (mapaddr == NULL)
+				if (mapaddr == MAP_FAILED)
 					fail = 1;
+
+				pci_map_addr = RTE_PTR_ADD(mapaddr, (size_t) maps[j].size);
 			}
 
 			if (fail) {

lib/librte_eal/linuxapp/eal/eal_pci_vfio.c

@@ -37,6 +37,7 @@
 #include <sys/eventfd.h>
 #include <sys/socket.h>
 #include <sys/ioctl.h>
+#include <sys/mman.h>
 
 #include <rte_log.h>
 #include <rte_pci.h>
@@ -720,10 +721,22 @@ pci_vfio_map_resource(struct rte_pci_device *dev)
 		if (i == msix_bar)
 			continue;
 
-		bar_addr = pci_map_resource(maps[i].addr, vfio_dev_fd, reg.offset,
-				reg.size);
+		if (internal_config.process_type == RTE_PROC_PRIMARY) {
+			/* try mapping somewhere close to the end of hugepages */
+			if (pci_map_addr == NULL)
+				pci_map_addr = pci_find_max_end_va();
 
-		if (bar_addr == NULL) {
+			bar_addr = pci_map_resource(pci_map_addr, vfio_dev_fd, reg.offset,
+					reg.size);
+			pci_map_addr = RTE_PTR_ADD(bar_addr, (size_t) reg.size);
+		} else {
+			bar_addr = pci_map_resource(maps[i].addr, vfio_dev_fd, reg.offset,
+					reg.size);
+		}
+
+		if (bar_addr == MAP_FAILED ||
+				(internal_config.process_type == RTE_PROC_SECONDARY &&
+						bar_addr != maps[i].addr)) {
 			RTE_LOG(ERR, EAL, "  %s mapping BAR%i failed: %s\n", pci_addr, i,
 					strerror(errno));
 			close(vfio_dev_fd);