[dpdk-dev] [PATCH v5] vfio: fix workaround of BAR mapping

Takeshi Yoshimura t.yoshimura8869 at gmail.com
Fri Jul 20 10:13:47 CEST 2018


Currently, VFIO will try to map around MSI-X table in the BARs. When
MSI-X table (page-aligned) size is equal to (page-aligned) size of BAR,
VFIO will just skip the BAR.

Recent kernel versions will allow VFIO to map the entire BAR containing
MSI-X tables (*), so instead of trying to map around the MSI-X vector
or skipping the BAR entirely if it's not possible, we can now try
mapping the entire BAR first. If mapping the entire BAR doesn't
succeed, fall back to the old behavior of mapping around MSI-X table or
skipping the BAR.

(*): "vfio-pci: Allow mapping MSIX BAR",
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/
commit/?id=a32295c612c57990d17fb0f41e7134394b2f35f6

Fixes: 90a1633b2347 ("eal/linux: allow to map BARs with MSI-X tables")

Signed-off-by: Takeshi Yoshimura <t.yoshimura8869 at gmail.com>
Reviewed-by: Anatoly Burakov <anatoly.burakov at intel.com>
---

Thanks, Anatoly.
I updated the code with munmap in an error path.
I also fixed the message and the wrong link.

Regards,
Takeshi

 drivers/bus/pci/linux/pci_vfio.c | 93 ++++++++++++++++++++++------------------
 1 file changed, 52 insertions(+), 41 deletions(-)

diff --git a/drivers/bus/pci/linux/pci_vfio.c b/drivers/bus/pci/linux/pci_vfio.c
index aeeaa9ed8..07188c071 100644
--- a/drivers/bus/pci/linux/pci_vfio.c
+++ b/drivers/bus/pci/linux/pci_vfio.c
@@ -332,50 +332,59 @@ pci_vfio_mmap_bar(int vfio_dev_fd, struct mapped_pci_resource *vfio_res,
 	void *bar_addr;
 	struct pci_msix_table *msix_table = &vfio_res->msix_table;
 	struct pci_map *bar = &vfio_res->maps[bar_index];
+	bool again = false;
 
 	if (bar->size == 0)
 		/* Skip this BAR */
 		return 0;
 
-	if (msix_table->bar_index == bar_index) {
-		/*
-		 * VFIO will not let us map the MSI-X table,
-		 * but we can map around it.
-		 */
-		uint32_t table_start = msix_table->offset;
-		uint32_t table_end = table_start + msix_table->size;
-		table_end = (table_end + ~PAGE_MASK) & PAGE_MASK;
-		table_start &= PAGE_MASK;
-
-		if (table_start == 0 && table_end >= bar->size) {
-			/* Cannot map this BAR */
-			RTE_LOG(DEBUG, EAL, "Skipping BAR%d\n", bar_index);
-			bar->size = 0;
-			bar->addr = 0;
-			return 0;
-		}
-
-		memreg[0].offset = bar->offset;
-		memreg[0].size = table_start;
-		memreg[1].offset = bar->offset + table_end;
-		memreg[1].size = bar->size - table_end;
-
-		RTE_LOG(DEBUG, EAL,
-			"Trying to map BAR%d that contains the MSI-X "
-			"table. Trying offsets: "
-			"0x%04lx:0x%04lx, 0x%04lx:0x%04lx\n", bar_index,
-			memreg[0].offset, memreg[0].size,
-			memreg[1].offset, memreg[1].size);
-	} else {
-		memreg[0].offset = bar->offset;
-		memreg[0].size = bar->size;
-	}
-
 	/* reserve the address using an inaccessible mapping */
 	bar_addr = mmap(bar->addr, bar->size, 0, MAP_PRIVATE |
 			MAP_ANONYMOUS | additional_flags, -1, 0);
-	if (bar_addr != MAP_FAILED) {
+	if (bar_addr == MAP_FAILED) {
+		RTE_LOG(ERR, EAL,
+			"Failed to create inaccessible mapping for BAR%d\n",
+			bar_index);
+		return -1;
+	}
+
+	memreg[0].offset = bar->offset;
+	memreg[0].size = bar->size;
+	do {
 		void *map_addr = NULL;
+		if (again) {
+			/*
+			 * VFIO did not let us map the MSI-X table,
+			 * but we can map around it.
+			 */
+			uint32_t table_start = msix_table->offset;
+			uint32_t table_end = table_start + msix_table->size;
+			table_end = (table_end + ~PAGE_MASK) & PAGE_MASK;
+			table_start &= PAGE_MASK;
+
+			if (table_start == 0 && table_end >= bar->size) {
+				/* Cannot map this BAR */
+				RTE_LOG(DEBUG, EAL, "Skipping BAR%d\n",
+						bar_index);
+				munmap(bar_addr, bar->size);
+				bar->size = 0;
+				bar->addr = 0;
+				return 0;
+			}
+
+			memreg[0].offset = bar->offset;
+			memreg[0].size = table_start;
+			memreg[1].offset = bar->offset + table_end;
+			memreg[1].size = bar->size - table_end;
+
+			RTE_LOG(DEBUG, EAL,
+				"Trying to map BAR%d that contains the MSI-X "
+				"table. Trying offsets: "
+				"0x%04lx:0x%04lx, 0x%04lx:0x%04lx\n", bar_index,
+				memreg[0].offset, memreg[0].size,
+				memreg[1].offset, memreg[1].size);
+		}
+
 		if (memreg[0].size) {
 			/* actual map of first part */
 			map_addr = pci_map_resource(bar_addr, vfio_dev_fd,
@@ -384,6 +393,12 @@ pci_vfio_mmap_bar(int vfio_dev_fd, struct mapped_pci_resource *vfio_res,
 							MAP_FIXED);
 		}
 
+		if (map_addr == MAP_FAILED &&
+			msix_table->bar_index == bar_index && !again) {
+			again = true;
+			continue;
+		}
+
 		/* if there's a second part, try to map it */
 		if (map_addr != MAP_FAILED
 			&& memreg[1].offset && memreg[1].size) {
@@ -404,12 +419,8 @@ pci_vfio_mmap_bar(int vfio_dev_fd, struct mapped_pci_resource *vfio_res,
 					bar_index);
 			return -1;
 		}
-	} else {
-		RTE_LOG(ERR, EAL,
-				"Failed to create inaccessible mapping for BAR%d\n",
-				bar_index);
-		return -1;
-	}
+		break;
+	} while (again);
 
 	bar->addr = bar_addr;
 	return 0;
-- 
2.15.1



More information about the dev mailing list