| Message ID | 1488578667.25946.1.camel@sandisk.com (mailing list archive) |
|---|---|
| State | Superseded |
| Headers | show |
Hi Bart, > -----Original Message----- > From: linux-rdma-owner@vger.kernel.org [mailto:linux-rdma- > owner@vger.kernel.org] On Behalf Of Bart Van Assche > Sent: Friday, March 3, 2017 4:05 PM > To: Parav Pandit <parav@mellanox.com>; loberman@redhat.com > Cc: linux-rdma@vger.kernel.org; dledford@redhat.com > Subject: Re: v4.11 mlx5 regression > > On Tue, 2017-02-28 at 20:34 +0000, Parav Pandit wrote: > > In middle of debugging/using setup right now for other issue. > > I am basically using nvme-rdma target mode code and somewhere in path > of MR or QP setup it fails. > > I am suspecting MR because QP1 creation has passed. > > I will get to the bottom of this to provide traces tomorrow. > Sorry. I didn't any chance last whole week to debug it. > Hello Parav, > > The I/O MMU was disabled while I prepared and tested the patch series that > reworks DMA support for RDMA drivers. I assume that the error message > you reported means that the I/O MMU was enabled on your test setup? Yes. Iommu is enabled. >If so, can you check whether the patch below makes the mlx5 driver (and all > other RDMA > drivers) work again on your test setup? > I tested this patch. It works with mlx5 driver. -- To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
T24gU2F0LCAyMDE3LTAzLTA0IGF0IDAyOjQ1ICswMDAwLCBQYXJhdiBQYW5kaXQgd3JvdGU6DQo+ ID4gRnJvbTogbGludXgtcmRtYS1vd25lckB2Z2VyLmtlcm5lbC5vcmcgW21haWx0bzpsaW51eC1y ZG1hLQ0KPiA+IG93bmVyQHZnZXIua2VybmVsLm9yZ10gT24gQmVoYWxmIE9mIEJhcnQgVmFuIEFz c2NoZQ0KPiA+IA0KPiA+IElmIHNvLCBjYW4geW91IGNoZWNrIHdoZXRoZXIgdGhlIHBhdGNoIGJl bG93IG1ha2VzIHRoZSBtbHg1IGRyaXZlciAoYW5kIGFsbA0KPiA+IG90aGVyIFJETUENCj4gPiBk cml2ZXJzKSB3b3JrIGFnYWluIG9uIHlvdXIgdGVzdCBzZXR1cD8NCj4gDQo+IEkgdGVzdGVkIHRo aXMgcGF0Y2guIEl0IHdvcmtzIHdpdGggbWx4NSBkcml2ZXIuDQoNClRoYW5rcyBmb3IgdGhlIHRl c3RpbmchDQoNCkJhcnQu -- To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c index 593d2ce6ec7c..d80e3f3b9bae 100644 --- a/drivers/infiniband/core/device.c +++ b/drivers/infiniband/core/device.c @@ -39,6 +39,7 @@ #include <linux/init.h> #include <linux/mutex.h> #include <linux/netdevice.h> +#include <linux/pci.h> #include <rdma/rdma_netlink.h> #include <rdma/ib_addr.h> #include <rdma/ib_cache.h> @@ -336,8 +337,12 @@ int ib_register_device(struct ib_device *device, struct device *parent = device->dev.parent; WARN_ON_ONCE(!parent); - if (!device->dev.dma_ops) + if (!device->dev.dma_ops) { device->dev.dma_ops = parent->dma_ops; + device->dev.pci_dev = to_pci_dev(parent); + /* For I/O MMU support */ + device->dev.archdata = parent->archdata; + } if (!device->dev.dma_mask) device->dev.dma_mask = parent->dma_mask; if (!device->dev.coherent_dma_mask) diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index dfc9a2794141..60d739b59520 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -1736,6 +1736,7 @@ struct pci_dev *pci_alloc_dev(struct pci_bus *bus) INIT_LIST_HEAD(&dev->bus_list); dev->dev.type = &pci_dev_type; + dev->dev.pci_dev = dev; dev->bus = pci_bus_get(bus); return dev; diff --git a/include/linux/device.h b/include/linux/device.h index 30c4570e928d..c18afd376d2a 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -42,6 +42,7 @@ struct fwnode_handle; struct iommu_ops; struct iommu_group; struct iommu_fwspec; +struct pci_dev; struct bus_attribute { struct attribute attr; @@ -860,6 +861,9 @@ struct dev_links_info { * segment limitations. * @dma_pools: Dma pools (if dma'ble device). * @dma_mem: Internal for coherent mem override. + * @pci_dev: PCI device associated with this device. Used by DMA mapping + * operations on architectures that need access to PCI device + * members that are not in struct device. * @cma_area: Contiguous memory area for dma allocations * @archdata: For arch-specific additions. * @of_node: Associated device tree node. @@ -940,6 +944,7 @@ struct device { struct dma_coherent_mem *dma_mem; /* internal for coherent mem override */ + struct pci_dev *pci_dev; /* for DMA mapping operations */ #ifdef CONFIG_DMA_CMA struct cma *cma_area; /* contiguous memory area for dma allocations */ diff --git a/include/linux/pci.h b/include/linux/pci.h index eb3da1a04e6c..eca790eaae20 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -409,7 +409,10 @@ static inline struct pci_dev *pci_physfn(struct pci_dev *dev) struct pci_dev *pci_alloc_dev(struct pci_bus *bus); -#define to_pci_dev(n) container_of(n, struct pci_dev, dev) +static inline struct pci_dev *to_pci_dev(const struct device *dev) +{ + return dev->pci_dev; +} #define for_each_pci_dev(d) while ((d = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, d)) != NULL) static inline int pci_channel_offline(struct pci_dev *pdev)--