pci: get IOMMU class on Linux

Get iommu class of PCI device on the bus and returns preferred iova
mapping mode for that bus.

Patch also introduces RTE_PCI_DRV_IOVA_AS_VA drv flag.
Flag used when driver needs to operate in iova=va mode.

Algorithm for iova scheme selection for PCI bus:
0. If no device bound then return with RTE_IOVA_DC mapping mode,
else goto 1).
1. Look for device attached to vfio kdrv and has .drv_flag set
to RTE_PCI_DRV_IOVA_AS_VA.
2. Look for any device attached to UIO class of driver.
3. Check for vfio-noiommu mode enabled.

If 2) & 3) is false and 1) is true then select
mapping scheme as RTE_IOVA_VA. Otherwise use default
mapping scheme (RTE_IOVA_PA).

Signed-off-by: Santosh Shukla <santosh.shukla@caviumnetworks.com>
Signed-off-by: Jerin Jacob <jerin.jacob@caviumnetworks.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Reviewed-by: Anatoly Burakov <anatoly.burakov@intel.com>
Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com>
Tested-by: Hemant Agrawal <hemant.agrawal@nxp.com>

diff --git a/lib/librte_eal/common/include/rte_pci.h b/lib/librte_eal/common/include/rte_pci.h
index 0e36de0..7a61898 100644 (file)
--- a/lib/librte_eal/common/include/rte_pci.h
+++ b/lib/librte_eal/common/include/rte_pci.h
@@ -202,6 +202,8 @@ struct rte_pci_bus {
 #define RTE_PCI_DRV_INTR_RMV 0x0010
 /** Device driver needs to keep mapped resources if unsupported dev detected */
 #define RTE_PCI_DRV_KEEP_MAPPED_RES 0x0020
+/** Device driver supports IOVA as VA */
+#define RTE_PCI_DRV_IOVA_AS_VA 0X0040
 
 /**
  * A structure describing a PCI mapping.

diff --git a/lib/librte_eal/linuxapp/eal/eal_pci.c b/lib/librte_eal/linuxapp/eal/eal_pci.c
index b1d6fbd..b4dbf95 100644 (file)
--- a/lib/librte_eal/linuxapp/eal/eal_pci.c
+++ b/lib/librte_eal/linuxapp/eal/eal_pci.c
@@ -45,6 +45,7 @@
 #include "eal_filesystem.h"
 #include "eal_private.h"
 #include "eal_pci_init.h"
+#include "eal_vfio.h"
 
 /**
  * @file
@@ -487,12 +488,98 @@ error:
        return -1;
 }
 
+/*
+ * Is pci device bound to any kdrv
+ */
+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)
+{
+       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;
 }
 

diff --git a/lib/librte_eal/linuxapp/eal/eal_vfio.c b/lib/librte_eal/linuxapp/eal/eal_vfio.c
index 946df7e..c8a97b7 100644 (file)
--- a/lib/librte_eal/linuxapp/eal/eal_vfio.c
+++ b/lib/librte_eal/linuxapp/eal/eal_vfio.c
@@ -816,4 +816,23 @@ vfio_noiommu_dma_map(int __rte_unused vfio_container_fd)
        return 0;
 }
 
+int
+vfio_noiommu_is_enabled(void)
+{
+       int fd, ret, cnt __rte_unused;
+       char c;
+
+       ret = -1;
+       fd = open(VFIO_NOIOMMU_MODE, O_RDONLY);
+       if (fd < 0)
+               return -1;
+
+       cnt = read(fd, &c, 1);
+       if (c == 'Y')
+               ret = 1;
+
+       close(fd);
+       return ret;
+}
+
 #endif

diff --git a/lib/librte_eal/linuxapp/eal/eal_vfio.h b/lib/librte_eal/linuxapp/eal/eal_vfio.h
index 5ff63e5..26ea8e1 100644 (file)
--- a/lib/librte_eal/linuxapp/eal/eal_vfio.h
+++ b/lib/librte_eal/linuxapp/eal/eal_vfio.h
@@ -150,6 +150,8 @@ struct vfio_config {
 #define VFIO_NOIOMMU_GROUP_FMT "/dev/vfio/noiommu-%u"
 #define VFIO_GET_REGION_ADDR(x) ((uint64_t) x << 40ULL)
 #define VFIO_GET_REGION_IDX(x) (x >> 40)
+#define VFIO_NOIOMMU_MODE      \
+       "/sys/module/vfio/parameters/enable_unsafe_noiommu_mode"
 
 /* DMA mapping function prototype.
  * Takes VFIO container fd as a parameter.
@@ -210,6 +212,8 @@ int pci_vfio_is_enabled(void);
 
 int vfio_mp_sync_setup(void);
 
+int vfio_noiommu_is_enabled(void);
+
 #define SOCKET_REQ_CONTAINER 0x100
 #define SOCKET_REQ_GROUP 0x200
 #define SOCKET_CLR_GROUP 0x300