diff options
Diffstat (limited to 'drivers/vfio')
| -rw-r--r-- | drivers/vfio/pci/Kconfig | 12 | ||||
| -rw-r--r-- | drivers/vfio/pci/Makefile | 1 | ||||
| -rw-r--r-- | drivers/vfio/pci/vfio_pci.c | 38 | ||||
| -rw-r--r-- | drivers/vfio/pci/vfio_pci_config.c | 27 | ||||
| -rw-r--r-- | drivers/vfio/pci/vfio_pci_private.h | 12 | ||||
| -rw-r--r-- | drivers/vfio/pci/vfio_pci_zdev.c | 143 | ||||
| -rw-r--r-- | drivers/vfio/vfio.c | 9 | ||||
| -rw-r--r-- | drivers/vfio/vfio_iommu_type1.c | 20 |
8 files changed, 248 insertions, 14 deletions
diff --git a/drivers/vfio/pci/Kconfig b/drivers/vfio/pci/Kconfig index ac3c1dd3edef..40a223381ab6 100644 --- a/drivers/vfio/pci/Kconfig +++ b/drivers/vfio/pci/Kconfig @@ -45,3 +45,15 @@ config VFIO_PCI_NVLINK2 depends on VFIO_PCI && PPC_POWERNV help VFIO PCI support for P9 Witherspoon machine with NVIDIA V100 GPUs + +config VFIO_PCI_ZDEV + bool "VFIO PCI ZPCI device CLP support" + depends on VFIO_PCI && S390 + default y + help + Enabling this option exposes VFIO capabilities containing hardware + configuration for zPCI devices. This enables userspace (e.g. QEMU) + to supply proper configuration values instead of hard-coded defaults + for zPCI devices passed through via VFIO on s390. + + Say Y here. diff --git a/drivers/vfio/pci/Makefile b/drivers/vfio/pci/Makefile index f027f8a0e89c..781e0809d6ee 100644 --- a/drivers/vfio/pci/Makefile +++ b/drivers/vfio/pci/Makefile @@ -3,5 +3,6 @@ vfio-pci-y := vfio_pci.o vfio_pci_intrs.o vfio_pci_rdwr.o vfio_pci_config.o vfio-pci-$(CONFIG_VFIO_PCI_IGD) += vfio_pci_igd.o vfio-pci-$(CONFIG_VFIO_PCI_NVLINK2) += vfio_pci_nvlink2.o +vfio-pci-$(CONFIG_VFIO_PCI_ZDEV) += vfio_pci_zdev.o obj-$(CONFIG_VFIO_PCI) += vfio-pci.o diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c index 1ab1f5cda4ac..36cad0b29150 100644 --- a/drivers/vfio/pci/vfio_pci.c +++ b/drivers/vfio/pci/vfio_pci.c @@ -807,15 +807,25 @@ static long vfio_pci_ioctl(void *device_data, if (cmd == VFIO_DEVICE_GET_INFO) { struct vfio_device_info info; + struct vfio_info_cap caps = { .buf = NULL, .size = 0 }; + unsigned long capsz; minsz = offsetofend(struct vfio_device_info, num_irqs); + /* For backward compatibility, cannot require this */ + capsz = offsetofend(struct vfio_iommu_type1_info, cap_offset); + if (copy_from_user(&info, (void __user *)arg, minsz)) return -EFAULT; if (info.argsz < minsz) return -EINVAL; + if (info.argsz >= capsz) { + minsz = capsz; + info.cap_offset = 0; + } + info.flags = VFIO_DEVICE_FLAGS_PCI; if (vdev->reset_works) @@ -824,6 +834,33 @@ static long vfio_pci_ioctl(void *device_data, info.num_regions = VFIO_PCI_NUM_REGIONS + vdev->num_regions; info.num_irqs = VFIO_PCI_NUM_IRQS; + if (IS_ENABLED(CONFIG_VFIO_PCI_ZDEV)) { + int ret = vfio_pci_info_zdev_add_caps(vdev, &caps); + + if (ret && ret != -ENODEV) { + pci_warn(vdev->pdev, "Failed to setup zPCI info capabilities\n"); + return ret; + } + } + + if (caps.size) { + info.flags |= VFIO_DEVICE_FLAGS_CAPS; + if (info.argsz < sizeof(info) + caps.size) { + info.argsz = sizeof(info) + caps.size; + } else { + vfio_info_cap_shift(&caps, sizeof(info)); + if (copy_to_user((void __user *)arg + + sizeof(info), caps.buf, + caps.size)) { + kfree(caps.buf); + return -EFAULT; + } + info.cap_offset = sizeof(info); + } + + kfree(caps.buf); + } + return copy_to_user((void __user *)arg, &info, minsz) ? -EFAULT : 0; @@ -1862,7 +1899,6 @@ static const struct vfio_device_ops vfio_pci_ops = { static int vfio_pci_reflck_attach(struct vfio_pci_device *vdev); static void vfio_pci_reflck_put(struct vfio_pci_reflck *reflck); -static struct pci_driver vfio_pci_driver; static int vfio_pci_bus_notifier(struct notifier_block *nb, unsigned long action, void *data) diff --git a/drivers/vfio/pci/vfio_pci_config.c b/drivers/vfio/pci/vfio_pci_config.c index d98843feddce..a402adee8a21 100644 --- a/drivers/vfio/pci/vfio_pci_config.c +++ b/drivers/vfio/pci/vfio_pci_config.c @@ -406,7 +406,7 @@ bool __vfio_pci_memory_enabled(struct vfio_pci_device *vdev) * PF SR-IOV capability, there's therefore no need to trigger * faults based on the virtual value. */ - return pdev->is_virtfn || (cmd & PCI_COMMAND_MEMORY); + return pdev->no_command_memory || (cmd & PCI_COMMAND_MEMORY); } /* @@ -467,6 +467,9 @@ static void vfio_bar_fixup(struct vfio_pci_device *vdev) __le32 *vbar; u64 mask; + if (!vdev->bardirty) + return; + vbar = (__le32 *)&vdev->vconfig[PCI_BASE_ADDRESS_0]; for (i = 0; i < PCI_STD_NUM_BARS; i++, vbar++) { @@ -520,8 +523,8 @@ static int vfio_basic_config_read(struct vfio_pci_device *vdev, int pos, count = vfio_default_config_read(vdev, pos, count, perm, offset, val); - /* Mask in virtual memory enable for SR-IOV devices */ - if (offset == PCI_COMMAND && vdev->pdev->is_virtfn) { + /* Mask in virtual memory enable */ + if (offset == PCI_COMMAND && vdev->pdev->no_command_memory) { u16 cmd = le16_to_cpu(*(__le16 *)&vdev->vconfig[PCI_COMMAND]); u32 tmp_val = le32_to_cpu(*val); @@ -589,9 +592,11 @@ static int vfio_basic_config_write(struct vfio_pci_device *vdev, int pos, * shows it disabled (phys_mem/io, then the device has * undergone some kind of backdoor reset and needs to be * restored before we allow it to enable the bars. - * SR-IOV devices will trigger this, but we catch them later + * SR-IOV devices will trigger this - for mem enable let's + * catch this now and for io enable it will be caught later */ - if ((new_mem && virt_mem && !phys_mem) || + if ((new_mem && virt_mem && !phys_mem && + !pdev->no_command_memory) || (new_io && virt_io && !phys_io) || vfio_need_bar_restore(vdev)) vfio_bar_restore(vdev); @@ -1734,12 +1739,14 @@ int vfio_config_init(struct vfio_pci_device *vdev) vconfig[PCI_INTERRUPT_PIN]); vconfig[PCI_INTERRUPT_PIN] = 0; /* Gratuitous for good VFs */ - + } + if (pdev->no_command_memory) { /* - * VFs do no implement the memory enable bit of the COMMAND - * register therefore we'll not have it set in our initial - * copy of config space after pci_enable_device(). For - * consistency with PFs, set the virtual enable bit here. + * VFs and devices that set pdev->no_command_memory do not + * implement the memory enable bit of the COMMAND register + * therefore we'll not have it set in our initial copy of + * config space after pci_enable_device(). For consistency + * with PFs, set the virtual enable bit here. */ *(__le16 *)&vconfig[PCI_COMMAND] |= cpu_to_le16(PCI_COMMAND_MEMORY); diff --git a/drivers/vfio/pci/vfio_pci_private.h b/drivers/vfio/pci/vfio_pci_private.h index 61ca8ab165dc..5c90e560c5c7 100644 --- a/drivers/vfio/pci/vfio_pci_private.h +++ b/drivers/vfio/pci/vfio_pci_private.h @@ -213,4 +213,16 @@ static inline int vfio_pci_ibm_npu2_init(struct vfio_pci_device *vdev) return -ENODEV; } #endif + +#ifdef CONFIG_VFIO_PCI_ZDEV +extern int vfio_pci_info_zdev_add_caps(struct vfio_pci_device *vdev, + struct vfio_info_cap *caps); +#else +static inline int vfio_pci_info_zdev_add_caps(struct vfio_pci_device *vdev, + struct vfio_info_cap *caps) +{ + return -ENODEV; +} +#endif + #endif /* VFIO_PCI_PRIVATE_H */ diff --git a/drivers/vfio/pci/vfio_pci_zdev.c b/drivers/vfio/pci/vfio_pci_zdev.c new file mode 100644 index 000000000000..229685634031 --- /dev/null +++ b/drivers/vfio/pci/vfio_pci_zdev.c @@ -0,0 +1,143 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * VFIO ZPCI devices support + * + * Copyright (C) IBM Corp. 2020. All rights reserved. + * Author(s): Pierre Morel <pmorel@linux.ibm.com> + * Matthew Rosato <mjrosato@linux.ibm.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + */ +#include <linux/io.h> +#include <linux/pci.h> +#include <linux/uaccess.h> +#include <linux/vfio.h> +#include <linux/vfio_zdev.h> +#include <asm/pci_clp.h> +#include <asm/pci_io.h> + +#include "vfio_pci_private.h" + +/* + * Add the Base PCI Function information to the device info region. + */ +static int zpci_base_cap(struct zpci_dev *zdev, struct vfio_pci_device *vdev, + struct vfio_info_cap *caps) +{ + struct vfio_device_info_cap_zpci_base cap = { + .header.id = VFIO_DEVICE_INFO_CAP_ZPCI_BASE, + .header.version = 1, + .start_dma = zdev->start_dma, + .end_dma = zdev->end_dma, + .pchid = zdev->pchid, + .vfn = zdev->vfn, + .fmb_length = zdev->fmb_length, + .pft = zdev->pft, + .gid = zdev->pfgid + }; + + return vfio_info_add_capability(caps, &cap.header, sizeof(cap)); +} + +/* + * Add the Base PCI Function Group information to the device info region. + */ +static int zpci_group_cap(struct zpci_dev *zdev, struct vfio_pci_device *vdev, + struct vfio_info_cap *caps) +{ + struct vfio_device_info_cap_zpci_group cap = { + .header.id = VFIO_DEVICE_INFO_CAP_ZPCI_GROUP, + .header.version = 1, + .dasm = zdev->dma_mask, + .msi_addr = zdev->msi_addr, + .flags = VFIO_DEVICE_INFO_ZPCI_FLAG_REFRESH, + .mui = zdev->fmb_update, + .noi = zdev->max_msi, + .maxstbl = ZPCI_MAX_WRITE_SIZE, + .version = zdev->version + }; + + return vfio_info_add_capability(caps, &cap.header, sizeof(cap)); +} + +/* + * Add the device utility string to the device info region. + */ +static int zpci_util_cap(struct zpci_dev *zdev, struct vfio_pci_device *vdev, + struct vfio_info_cap *caps) +{ + struct vfio_device_info_cap_zpci_util *cap; + int cap_size = sizeof(*cap) + CLP_UTIL_STR_LEN; + int ret; + + cap = kmalloc(cap_size, GFP_KERNEL); + + cap->header.id = VFIO_DEVICE_INFO_CAP_ZPCI_UTIL; + cap->header.version = 1; + cap->size = CLP_UTIL_STR_LEN; + memcpy(cap->util_str, zdev->util_str, cap->size); + + ret = vfio_info_add_capability(caps, &cap->header, cap_size); + + kfree(cap); + + return ret; +} + +/* + * Add the function path string to the device info region. + */ +static int zpci_pfip_cap(struct zpci_dev *zdev, struct vfio_pci_device *vdev, + struct vfio_info_cap *caps) +{ + struct vfio_device_info_cap_zpci_pfip *cap; + int cap_size = sizeof(*cap) + CLP_PFIP_NR_SEGMENTS; + int ret; + + cap = kmalloc(cap_size, GFP_KERNEL); + + cap->header.id = VFIO_DEVICE_INFO_CAP_ZPCI_PFIP; + cap->header.version = 1; + cap->size = CLP_PFIP_NR_SEGMENTS; + memcpy(cap->pfip, zdev->pfip, cap->size); + + ret = vfio_info_add_capability(caps, &cap->header, cap_size); + + kfree(cap); + + return ret; +} + +/* + * Add all supported capabilities to the VFIO_DEVICE_GET_INFO capability chain. + */ +int vfio_pci_info_zdev_add_caps(struct vfio_pci_device *vdev, + struct vfio_info_cap *caps) +{ + struct zpci_dev *zdev = to_zpci(vdev->pdev); + int ret; + + if (!zdev) + return -ENODEV; + + ret = zpci_base_cap(zdev, vdev, caps); + if (ret) + return ret; + + ret = zpci_group_cap(zdev, vdev, caps); + if (ret) + return ret; + + if (zdev->util_str_avail) { + ret = zpci_util_cap(zdev, vdev, caps); + if (ret) + return ret; + } + + ret = zpci_pfip_cap(zdev, vdev, caps); + + return ret; +} diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c index 262ab0efd06c..2151bc7f87ab 100644 --- a/drivers/vfio/vfio.c +++ b/drivers/vfio/vfio.c @@ -1949,8 +1949,10 @@ int vfio_pin_pages(struct device *dev, unsigned long *user_pfn, int npage, if (!group) return -ENODEV; - if (group->dev_counter > 1) - return -EINVAL; + if (group->dev_counter > 1) { + ret = -EINVAL; + goto err_pin_pages; + } ret = vfio_group_add_container_user(group); if (ret) @@ -2051,6 +2053,9 @@ int vfio_group_pin_pages(struct vfio_group *group, if (!group || !user_iova_pfn || !phys_pfn || !npage) return -EINVAL; + if (group->dev_counter > 1) + return -EINVAL; + if (npage > VFIO_PIN_PAGES_MAX_ENTRIES) return -E2BIG; diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index 5fbf0c1f7433..defd44522319 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -2609,6 +2609,20 @@ static int vfio_iommu_migration_build_caps(struct vfio_iommu *iommu, return vfio_info_add_capability(caps, &cap_mig.header, sizeof(cap_mig)); } +static int vfio_iommu_dma_avail_build_caps(struct vfio_iommu *iommu, + struct vfio_info_cap *caps) +{ + struct vfio_iommu_type1_info_dma_avail cap_dma_avail; + + cap_dma_avail.header.id = VFIO_IOMMU_TYPE1_INFO_DMA_AVAIL; + cap_dma_avail.header.version = 1; + + cap_dma_avail.avail = iommu->dma_avail; + + return vfio_info_add_capability(caps, &cap_dma_avail.header, + sizeof(cap_dma_avail)); +} + static int vfio_iommu_type1_get_info(struct vfio_iommu *iommu, unsigned long arg) { @@ -2642,6 +2656,9 @@ static int vfio_iommu_type1_get_info(struct vfio_iommu *iommu, ret = vfio_iommu_migration_build_caps(iommu, &caps); if (!ret) + ret = vfio_iommu_dma_avail_build_caps(iommu, &caps); + + if (!ret) ret = vfio_iommu_iova_build_caps(iommu, &caps); mutex_unlock(&iommu->lock); @@ -2933,7 +2950,8 @@ static int vfio_iommu_type1_dma_rw_chunk(struct vfio_iommu *iommu, * size */ bitmap_set(dma->bitmap, offset >> pgshift, - *copied >> pgshift); + ((offset + *copied - 1) >> pgshift) - + (offset >> pgshift) + 1); } } else *copied = copy_from_user(data, (void __user *)vaddr, |