vfio: support 64KB kernel page size

[dpdk.git] / drivers / bus / pci / linux / pci_vfio.c

diff --git a/drivers/bus/pci/linux/pci_vfio.c b/drivers/bus/pci/linux/pci_vfio.c
index d2c8410..fa8cfbb 100644 (file)
--- a/drivers/bus/pci/linux/pci_vfio.c
+++ b/drivers/bus/pci/linux/pci_vfio.c
@@ -36,14 +36,6 @@
  * This file is only compiled if CONFIG_RTE_EAL_VFIO is set to "y".
  */
 
-/*
- * spinlock for device hot-unplug failure handling. If it try to access bus or
- * device, such as handle sigbus on bus or handle memory failure for device
- * just need to use this lock. It could protect the bus and the device to avoid
- * race condition.
- */
-static rte_spinlock_t failure_handle_lock = RTE_SPINLOCK_INITIALIZER;
-
 #ifdef VFIO_PRESENT
 
 #ifndef PAGE_SIZE
@@ -291,6 +283,14 @@ pci_vfio_setup_interrupts(struct rte_pci_device *dev, int vfio_dev_fd)
 }
 
 #ifdef HAVE_VFIO_DEV_REQ_INTERFACE
+/*
+ * Spinlock for device hot-unplug failure handling.
+ * If it tries to access bus or device, such as handle sigbus on bus
+ * or handle memory failure for device, just need to use this lock.
+ * It could protect the bus and the device to avoid race condition.
+ */
+static rte_spinlock_t failure_handle_lock = RTE_SPINLOCK_INITIALIZER;
+
 static void
 pci_vfio_req_handler(void *param)
 {
@@ -457,9 +457,10 @@ pci_vfio_mmap_bar(int vfio_dev_fd, struct mapped_pci_resource *vfio_res,
        struct pci_msix_table *msix_table = &vfio_res->msix_table;
        struct pci_map *bar = &vfio_res->maps[bar_index];
 
-       if (bar->size == 0)
-               /* Skip this BAR */
+       if (bar->size == 0) {
+               RTE_LOG(DEBUG, EAL, "Bar size is 0, skip BAR%d\n", bar_index);
                return 0;
+       }
 
        if (msix_table->bar_index == bar_index) {
                /*
@@ -468,8 +469,15 @@ pci_vfio_mmap_bar(int vfio_dev_fd, struct mapped_pci_resource *vfio_res,
                 */
                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;
+               table_end = RTE_ALIGN(table_end, PAGE_SIZE);
+               table_start = RTE_ALIGN_FLOOR(table_start, PAGE_SIZE);
+
+               /* If page-aligned start of MSI-X table is less than the
+                * actual MSI-X table start address, reassign to the actual
+                * start address.
+                */
+               if (table_start < msix_table->offset)
+                       table_start = msix_table->offset;
 
                if (table_start == 0 && table_end >= bar->size) {
                        /* Cannot map this BAR */
@@ -481,8 +489,17 @@ pci_vfio_mmap_bar(int vfio_dev_fd, struct mapped_pci_resource *vfio_res,
 
                memreg[0].offset = bar->offset;
                memreg[0].size = table_start;
-               memreg[1].offset = bar->offset + table_end;
-               memreg[1].size = bar->size - table_end;
+               if (bar->size < table_end) {
+                       /*
+                        * If MSI-X table end is beyond BAR end, don't attempt
+                        * to perform second mapping.
+                        */
+                       memreg[1].offset = 0;
+                       memreg[1].size = 0;
+               } else {
+                       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 "
@@ -794,11 +811,6 @@ pci_vfio_map_resource_secondary(struct rte_pci_device *dev)
        snprintf(pci_addr, sizeof(pci_addr), PCI_PRI_FMT,
                        loc->domain, loc->bus, loc->devid, loc->function);
 
-       ret = rte_vfio_setup_device(rte_pci_get_sysfs_path(), pci_addr,
-                                       &vfio_dev_fd, &device_info);
-       if (ret)
-               return ret;
-
        /* if we're in a secondary process, just find our tailq entry */
        TAILQ_FOREACH(vfio_res, vfio_res_list, next) {
                if (rte_pci_addr_cmp(&vfio_res->pci_addr,
@@ -810,9 +822,14 @@ pci_vfio_map_resource_secondary(struct rte_pci_device *dev)
        if (vfio_res == NULL) {
                RTE_LOG(ERR, EAL, "  %s cannot find TAILQ entry for PCI device!\n",
                                pci_addr);
-               goto err_vfio_dev_fd;
+               return -1;
        }
 
+       ret = rte_vfio_setup_device(rte_pci_get_sysfs_path(), pci_addr,
+                                       &vfio_dev_fd, &device_info);
+       if (ret)
+               return ret;
+
        /* map BARs */
        maps = vfio_res->maps;