From eac7cc21c4e49ab7dfeef22e29abdee8432face9 Mon Sep 17 00:00:00 2001 From: Zenghui Yu Date: Mon, 21 Sep 2020 12:51:15 +0800 Subject: vfio/pci: Remove redundant declaration of vfio_pci_driver It was added by commit 137e5531351d ("vfio/pci: Add sriov_configure support") but duplicates a forward declaration earlier in the file. Remove it. Signed-off-by: Zenghui Yu Reviewed-by: Cornelia Huck Signed-off-by: Alex Williamson --- drivers/vfio/pci/vfio_pci.c | 1 - 1 file changed, 1 deletion(-) (limited to 'drivers/vfio') diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c index 1ab1f5cda4ac..da68e2f86622 100644 --- a/drivers/vfio/pci/vfio_pci.c +++ b/drivers/vfio/pci/vfio_pci.c @@ -1862,7 +1862,6 @@ 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) -- cgit v1.2.3 From 1c0f68252a6a8a793ff3352e3580664d18ec5955 Mon Sep 17 00:00:00 2001 From: Zenghui Yu Date: Mon, 21 Sep 2020 12:51:16 +0800 Subject: vfio/pci: Don't regenerate vconfig for all BARs if !bardirty Now we regenerate vconfig for all the BARs via vfio_bar_fixup(), every time any offset of any of them are read. Though BARs aren't re-read regularly, the regeneration can be avoided if no BARs had been written since they were last read, in which case vdev->bardirty is false. Let's return immediately in vfio_bar_fixup() if bardirty is false. Suggested-by: Alex Williamson Signed-off-by: Zenghui Yu Reviewed-by: Cornelia Huck Signed-off-by: Alex Williamson --- drivers/vfio/pci/vfio_pci_config.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'drivers/vfio') diff --git a/drivers/vfio/pci/vfio_pci_config.c b/drivers/vfio/pci/vfio_pci_config.c index d98843feddce..5e02ba07e8e8 100644 --- a/drivers/vfio/pci/vfio_pci_config.c +++ b/drivers/vfio/pci/vfio_pci_config.c @@ -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++) { -- cgit v1.2.3 From 7ef32e52368f62a4e041a4f0abefb4fb64e7fd4a Mon Sep 17 00:00:00 2001 From: Yan Zhao Date: Wed, 16 Sep 2020 10:28:33 +0800 Subject: vfio: add a singleton check for vfio_group_pin_pages Page pinning is used both to translate and pin device mappings for DMA purpose, as well as to indicate to the IOMMU backend to limit the dirty page scope to those pages that have been pinned, in the case of an IOMMU backed device. To support this, the vfio_pin_pages() interface limits itself to only singleton groups such that the IOMMU backend can consider dirty page scope only at the group level. Implement the same requirement for the vfio_group_pin_pages() interface. Fixes: 95fc87b44104 ("vfio: Selective dirty page tracking if IOMMU backed device pins pages") Signed-off-by: Yan Zhao Signed-off-by: Alex Williamson --- drivers/vfio/vfio.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'drivers/vfio') diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c index 262ab0efd06c..532bcaf28c11 100644 --- a/drivers/vfio/vfio.c +++ b/drivers/vfio/vfio.c @@ -2051,6 +2051,9 @@ 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; -- cgit v1.2.3 From 7d6e1329652ed971d1b6e0e7bea66fba5044e271 Mon Sep 17 00:00:00 2001 From: Matthew Rosato Date: Tue, 15 Sep 2020 15:05:18 -0400 Subject: vfio iommu: Add dma available capability Commit 492855939bdb ("vfio/type1: Limit DMA mappings per container") added the ability to limit the number of memory backed DMA mappings. However on s390x, when lazy mapping is in use, we use a very large number of concurrent mappings. Let's provide the current allowable number of DMA mappings to userspace via the IOMMU info chain so that userspace can take appropriate mitigation. Signed-off-by: Matthew Rosato Reviewed-by: Cornelia Huck Signed-off-by: Alex Williamson --- drivers/vfio/vfio_iommu_type1.c | 17 +++++++++++++++++ include/uapi/linux/vfio.h | 15 +++++++++++++++ 2 files changed, 32 insertions(+) (limited to 'drivers/vfio') diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index 5fbf0c1f7433..15e21dbffb16 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) { @@ -2641,6 +2655,9 @@ 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); diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index 920470502329..3891e03d3af0 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -1039,6 +1039,21 @@ struct vfio_iommu_type1_info_cap_migration { __u64 max_dirty_bitmap_size; /* in bytes */ }; +/* + * The DMA available capability allows to report the current number of + * simultaneously outstanding DMA mappings that are allowed. + * + * The structure below defines version 1 of this capability. + * + * avail: specifies the current number of outstanding DMA mappings allowed. + */ +#define VFIO_IOMMU_TYPE1_INFO_DMA_AVAIL 3 + +struct vfio_iommu_type1_info_dma_avail { + struct vfio_info_cap_header header; + __u32 avail; +}; + #define VFIO_IOMMU_GET_INFO _IO(VFIO_TYPE, VFIO_BASE + 12) /** -- cgit v1.2.3 From 515ecd5368f1510152fa4f9b9ce55b66ac56c334 Mon Sep 17 00:00:00 2001 From: Matthew Rosato Date: Thu, 10 Sep 2020 10:59:57 -0400 Subject: vfio/pci: Decouple PCI_COMMAND_MEMORY bit checks from is_virtfn While it is true that devices with is_virtfn=1 will have a Memory Space Enable bit that is hard-wired to 0, this is not the only case where we see this behavior -- For example some bare-metal hypervisors lack Memory Space Enable bit emulation for devices not setting is_virtfn (s390). Fix this by instead checking for the newly-added no_command_memory bit which directly denotes the need for PCI_COMMAND_MEMORY emulation in vfio. Fixes: abafbc551fdd ("vfio-pci: Invalidate mmaps and block MMIO access on disabled memory") Signed-off-by: Matthew Rosato Reviewed-by: Niklas Schnelle Reviewed-by: Pierre Morel Signed-off-by: Alex Williamson --- drivers/vfio/pci/vfio_pci_config.c | 24 ++++++++++++++---------- 1 file changed, 14 insertions(+), 10 deletions(-) (limited to 'drivers/vfio') diff --git a/drivers/vfio/pci/vfio_pci_config.c b/drivers/vfio/pci/vfio_pci_config.c index d98843feddce..5076d0155bc3 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); } /* @@ -520,8 +520,8 @@ 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 +589,11 @@ 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 +1736,14 @@ 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); -- cgit v1.2.3 From 28b130244061863cf0437b7af1625fb45ec1a71e Mon Sep 17 00:00:00 2001 From: Yan Zhao Date: Wed, 16 Sep 2020 10:29:27 +0800 Subject: vfio: fix a missed vfio group put in vfio_pin_pages When error occurs, need to put vfio group after a successful get. Fixes: 95fc87b44104 ("vfio: Selective dirty page tracking if IOMMU backed device pins pages") Signed-off-by: Yan Zhao Reviewed-by: Cornelia Huck Signed-off-by: Alex Williamson --- drivers/vfio/vfio.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'drivers/vfio') diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c index 532bcaf28c11..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) -- cgit v1.2.3 From 2c5af98592f65517170c7bcc714566590d3f7397 Mon Sep 17 00:00:00 2001 From: Yan Zhao Date: Wed, 16 Sep 2020 10:30:05 +0800 Subject: vfio/type1: fix dirty bitmap calculation in vfio_dma_rw The count of dirtied pages is not only determined by count of copied pages, but also by the start offset. e.g. if offset = PAGE_SIZE - 1, and *copied=2, the dirty pages count is 2, instead of 1 or 0. Fixes: d6a4c185660c ("vfio iommu: Implementation of ioctl for dirty pages tracking") Signed-off-by: Yan Zhao Signed-off-by: Alex Williamson --- drivers/vfio/vfio_iommu_type1.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'drivers/vfio') diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index 5fbf0c1f7433..d0438388feeb 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -2933,7 +2933,8 @@ 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, -- cgit v1.2.3 From fb1ff4c1941573aea59e4cb575dc5a723303cd70 Mon Sep 17 00:00:00 2001 From: Bharat Bhushan Date: Mon, 5 Oct 2020 20:36:45 +0300 Subject: vfio/fsl-mc: Add VFIO framework skeleton for fsl-mc devices DPAA2 (Data Path Acceleration Architecture) consists in mechanisms for processing Ethernet packets, queue management, accelerators, etc. The Management Complex (mc) is a hardware entity that manages the DPAA2 hardware resources. It provides an object-based abstraction for software drivers to use the DPAA2 hardware. The MC mediates operations such as create, discover, destroy of DPAA2 objects. The MC provides memory-mapped I/O command interfaces (MC portals) which DPAA2 software drivers use to operate on DPAA2 objects. A DPRC is a container object that holds other types of DPAA2 objects. Each object in the DPRC is a Linux device and bound to a driver. The MC-bus driver is a platform driver (different from PCI or platform bus). The DPRC driver does runtime management of a bus instance. It performs the initial scan of the DPRC and handles changes in the DPRC configuration (adding/removing objects). All objects inside a container share the same hardware isolation context, meaning that only an entire DPRC can be assigned to a virtual machine. When a container is assigned to a virtual machine, all the objects within that container are assigned to that virtual machine. The DPRC container assigned to the virtual machine is not allowed to change contents (add/remove objects) by the guest. The restriction is set by the host and enforced by the mc hardware. The DPAA2 objects can be directly assigned to the guest. However the MC portals (the memory mapped command interface to the MC) need to be emulated because there are commands that configure the interrupts and the isolation IDs which are virtual in the guest. Example: echo vfio-fsl-mc > /sys/bus/fsl-mc/devices/dprc.2/driver_override echo dprc.2 > /sys/bus/fsl-mc/drivers/vfio-fsl-mc/bind The dprc.2 is bound to the VFIO driver and all the objects within dprc.2 are going to be bound to the VFIO driver. This patch adds the infrastructure for VFIO support for fsl-mc devices. Subsequent patches will add support for binding and secure assigning these devices using VFIO. More details about the DPAA2 objects can be found here: Documentation/networking/device_drivers/freescale/dpaa2/overview.rst Signed-off-by: Bharat Bhushan Signed-off-by: Diana Craciun Reviewed-by: Eric Auger Signed-off-by: Alex Williamson --- MAINTAINERS | 6 ++ drivers/vfio/Kconfig | 1 + drivers/vfio/Makefile | 1 + drivers/vfio/fsl-mc/Kconfig | 9 ++ drivers/vfio/fsl-mc/Makefile | 4 + drivers/vfio/fsl-mc/vfio_fsl_mc.c | 157 ++++++++++++++++++++++++++++++ drivers/vfio/fsl-mc/vfio_fsl_mc_private.h | 14 +++ include/uapi/linux/vfio.h | 1 + 8 files changed, 193 insertions(+) create mode 100644 drivers/vfio/fsl-mc/Kconfig create mode 100644 drivers/vfio/fsl-mc/Makefile create mode 100644 drivers/vfio/fsl-mc/vfio_fsl_mc.c create mode 100644 drivers/vfio/fsl-mc/vfio_fsl_mc_private.h (limited to 'drivers/vfio') diff --git a/MAINTAINERS b/MAINTAINERS index d746519253c3..e955a00af046 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -18260,6 +18260,12 @@ F: drivers/vfio/ F: include/linux/vfio.h F: include/uapi/linux/vfio.h +VFIO FSL-MC DRIVER +M: Diana Craciun +L: kvm@vger.kernel.org +S: Maintained +F: drivers/vfio/fsl-mc/ + VFIO MEDIATED DEVICE DRIVERS M: Kirti Wankhede L: kvm@vger.kernel.org diff --git a/drivers/vfio/Kconfig b/drivers/vfio/Kconfig index fd17db9b432f..5533df91b257 100644 --- a/drivers/vfio/Kconfig +++ b/drivers/vfio/Kconfig @@ -47,4 +47,5 @@ menuconfig VFIO_NOIOMMU source "drivers/vfio/pci/Kconfig" source "drivers/vfio/platform/Kconfig" source "drivers/vfio/mdev/Kconfig" +source "drivers/vfio/fsl-mc/Kconfig" source "virt/lib/Kconfig" diff --git a/drivers/vfio/Makefile b/drivers/vfio/Makefile index de67c4725cce..fee73f3d9480 100644 --- a/drivers/vfio/Makefile +++ b/drivers/vfio/Makefile @@ -9,3 +9,4 @@ obj-$(CONFIG_VFIO_SPAPR_EEH) += vfio_spapr_eeh.o obj-$(CONFIG_VFIO_PCI) += pci/ obj-$(CONFIG_VFIO_PLATFORM) += platform/ obj-$(CONFIG_VFIO_MDEV) += mdev/ +obj-$(CONFIG_VFIO_FSL_MC) += fsl-mc/ diff --git a/drivers/vfio/fsl-mc/Kconfig b/drivers/vfio/fsl-mc/Kconfig new file mode 100644 index 000000000000..b1a527d6b6f2 --- /dev/null +++ b/drivers/vfio/fsl-mc/Kconfig @@ -0,0 +1,9 @@ +config VFIO_FSL_MC + tristate "VFIO support for QorIQ DPAA2 fsl-mc bus devices" + depends on VFIO && FSL_MC_BUS && EVENTFD + help + Driver to enable support for the VFIO QorIQ DPAA2 fsl-mc + (Management Complex) devices. This is required to passthrough + fsl-mc bus devices using the VFIO framework. + + If you don't know what to do here, say N. diff --git a/drivers/vfio/fsl-mc/Makefile b/drivers/vfio/fsl-mc/Makefile new file mode 100644 index 000000000000..0c6e5d2ddaae --- /dev/null +++ b/drivers/vfio/fsl-mc/Makefile @@ -0,0 +1,4 @@ +# SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) + +vfio-fsl-mc-y := vfio_fsl_mc.o +obj-$(CONFIG_VFIO_FSL_MC) += vfio-fsl-mc.o diff --git a/drivers/vfio/fsl-mc/vfio_fsl_mc.c b/drivers/vfio/fsl-mc/vfio_fsl_mc.c new file mode 100644 index 000000000000..a7a483a1e90b --- /dev/null +++ b/drivers/vfio/fsl-mc/vfio_fsl_mc.c @@ -0,0 +1,157 @@ +// SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) +/* + * Copyright 2013-2016 Freescale Semiconductor Inc. + * Copyright 2016-2017,2019-2020 NXP + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#include "vfio_fsl_mc_private.h" + +static int vfio_fsl_mc_open(void *device_data) +{ + if (!try_module_get(THIS_MODULE)) + return -ENODEV; + + return 0; +} + +static void vfio_fsl_mc_release(void *device_data) +{ + module_put(THIS_MODULE); +} + +static long vfio_fsl_mc_ioctl(void *device_data, unsigned int cmd, + unsigned long arg) +{ + switch (cmd) { + case VFIO_DEVICE_GET_INFO: + { + return -ENOTTY; + } + case VFIO_DEVICE_GET_REGION_INFO: + { + return -ENOTTY; + } + case VFIO_DEVICE_GET_IRQ_INFO: + { + return -ENOTTY; + } + case VFIO_DEVICE_SET_IRQS: + { + return -ENOTTY; + } + case VFIO_DEVICE_RESET: + { + return -ENOTTY; + } + default: + return -ENOTTY; + } +} + +static ssize_t vfio_fsl_mc_read(void *device_data, char __user *buf, + size_t count, loff_t *ppos) +{ + return -EINVAL; +} + +static ssize_t vfio_fsl_mc_write(void *device_data, const char __user *buf, + size_t count, loff_t *ppos) +{ + return -EINVAL; +} + +static int vfio_fsl_mc_mmap(void *device_data, struct vm_area_struct *vma) +{ + return -EINVAL; +} + +static const struct vfio_device_ops vfio_fsl_mc_ops = { + .name = "vfio-fsl-mc", + .open = vfio_fsl_mc_open, + .release = vfio_fsl_mc_release, + .ioctl = vfio_fsl_mc_ioctl, + .read = vfio_fsl_mc_read, + .write = vfio_fsl_mc_write, + .mmap = vfio_fsl_mc_mmap, +}; + +static int vfio_fsl_mc_probe(struct fsl_mc_device *mc_dev) +{ + struct iommu_group *group; + struct vfio_fsl_mc_device *vdev; + struct device *dev = &mc_dev->dev; + int ret; + + group = vfio_iommu_group_get(dev); + if (!group) { + dev_err(dev, "VFIO_FSL_MC: No IOMMU group\n"); + return -EINVAL; + } + + vdev = devm_kzalloc(dev, sizeof(*vdev), GFP_KERNEL); + if (!vdev) { + ret = -ENOMEM; + goto out_group_put; + } + + vdev->mc_dev = mc_dev; + + ret = vfio_add_group_dev(dev, &vfio_fsl_mc_ops, vdev); + if (ret) { + dev_err(dev, "VFIO_FSL_MC: Failed to add to vfio group\n"); + goto out_group_put; + } + return 0; + +out_group_put: + vfio_iommu_group_put(group, dev); + return ret; +} + +static int vfio_fsl_mc_remove(struct fsl_mc_device *mc_dev) +{ + struct vfio_fsl_mc_device *vdev; + struct device *dev = &mc_dev->dev; + + vdev = vfio_del_group_dev(dev); + if (!vdev) + return -EINVAL; + + vfio_iommu_group_put(mc_dev->dev.iommu_group, dev); + + return 0; +} + +static struct fsl_mc_driver vfio_fsl_mc_driver = { + .probe = vfio_fsl_mc_probe, + .remove = vfio_fsl_mc_remove, + .driver = { + .name = "vfio-fsl-mc", + .owner = THIS_MODULE, + }, +}; + +static int __init vfio_fsl_mc_driver_init(void) +{ + return fsl_mc_driver_register(&vfio_fsl_mc_driver); +} + +static void __exit vfio_fsl_mc_driver_exit(void) +{ + fsl_mc_driver_unregister(&vfio_fsl_mc_driver); +} + +module_init(vfio_fsl_mc_driver_init); +module_exit(vfio_fsl_mc_driver_exit); + +MODULE_LICENSE("Dual BSD/GPL"); +MODULE_DESCRIPTION("VFIO for FSL-MC devices - User Level meta-driver"); diff --git a/drivers/vfio/fsl-mc/vfio_fsl_mc_private.h b/drivers/vfio/fsl-mc/vfio_fsl_mc_private.h new file mode 100644 index 000000000000..e79cc116f6b8 --- /dev/null +++ b/drivers/vfio/fsl-mc/vfio_fsl_mc_private.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) */ +/* + * Copyright 2013-2016 Freescale Semiconductor Inc. + * Copyright 2016,2019-2020 NXP + */ + +#ifndef VFIO_FSL_MC_PRIVATE_H +#define VFIO_FSL_MC_PRIVATE_H + +struct vfio_fsl_mc_device { + struct fsl_mc_device *mc_dev; +}; + +#endif /* VFIO_FSL_MC_PRIVATE_H */ diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index 920470502329..95deac891378 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -201,6 +201,7 @@ struct vfio_device_info { #define VFIO_DEVICE_FLAGS_AMBA (1 << 3) /* vfio-amba device */ #define VFIO_DEVICE_FLAGS_CCW (1 << 4) /* vfio-ccw device */ #define VFIO_DEVICE_FLAGS_AP (1 << 5) /* vfio-ap device */ +#define VFIO_DEVICE_FLAGS_FSL_MC (1 << 6) /* vfio-fsl-mc device */ __u32 num_regions; /* Max region index + 1 */ __u32 num_irqs; /* Max IRQ index + 1 */ }; -- cgit v1.2.3 From 704f5082d8457a2166eb4cb4e460510117c70928 Mon Sep 17 00:00:00 2001 From: Diana Craciun Date: Mon, 5 Oct 2020 20:36:46 +0300 Subject: vfio/fsl-mc: Scan DPRC objects on vfio-fsl-mc driver bind The DPRC (Data Path Resource Container) device is a bus device and has child devices attached to it. When the vfio-fsl-mc driver is probed the DPRC is scanned and the child devices discovered and initialized. Signed-off-by: Bharat Bhushan Signed-off-by: Diana Craciun Reviewed-by: Eric Auger Signed-off-by: Alex Williamson --- drivers/vfio/fsl-mc/vfio_fsl_mc.c | 91 +++++++++++++++++++++++++++++++ drivers/vfio/fsl-mc/vfio_fsl_mc_private.h | 1 + 2 files changed, 92 insertions(+) (limited to 'drivers/vfio') diff --git a/drivers/vfio/fsl-mc/vfio_fsl_mc.c b/drivers/vfio/fsl-mc/vfio_fsl_mc.c index a7a483a1e90b..594760203268 100644 --- a/drivers/vfio/fsl-mc/vfio_fsl_mc.c +++ b/drivers/vfio/fsl-mc/vfio_fsl_mc.c @@ -15,6 +15,8 @@ #include "vfio_fsl_mc_private.h" +static struct fsl_mc_driver vfio_fsl_mc_driver; + static int vfio_fsl_mc_open(void *device_data) { if (!try_module_get(THIS_MODULE)) @@ -84,6 +86,80 @@ static const struct vfio_device_ops vfio_fsl_mc_ops = { .mmap = vfio_fsl_mc_mmap, }; +static int vfio_fsl_mc_bus_notifier(struct notifier_block *nb, + unsigned long action, void *data) +{ + struct vfio_fsl_mc_device *vdev = container_of(nb, + struct vfio_fsl_mc_device, nb); + struct device *dev = data; + struct fsl_mc_device *mc_dev = to_fsl_mc_device(dev); + struct fsl_mc_device *mc_cont = to_fsl_mc_device(mc_dev->dev.parent); + + if (action == BUS_NOTIFY_ADD_DEVICE && + vdev->mc_dev == mc_cont) { + mc_dev->driver_override = kasprintf(GFP_KERNEL, "%s", + vfio_fsl_mc_ops.name); + if (!mc_dev->driver_override) + dev_warn(dev, "VFIO_FSL_MC: Setting driver override for device in dprc %s failed\n", + dev_name(&mc_cont->dev)); + else + dev_info(dev, "VFIO_FSL_MC: Setting driver override for device in dprc %s\n", + dev_name(&mc_cont->dev)); + } else if (action == BUS_NOTIFY_BOUND_DRIVER && + vdev->mc_dev == mc_cont) { + struct fsl_mc_driver *mc_drv = to_fsl_mc_driver(dev->driver); + + if (mc_drv && mc_drv != &vfio_fsl_mc_driver) + dev_warn(dev, "VFIO_FSL_MC: Object %s bound to driver %s while DPRC bound to vfio-fsl-mc\n", + dev_name(dev), mc_drv->driver.name); + } + + return 0; +} + +static int vfio_fsl_mc_init_device(struct vfio_fsl_mc_device *vdev) +{ + struct fsl_mc_device *mc_dev = vdev->mc_dev; + int ret; + + /* Non-dprc devices share mc_io from parent */ + if (!is_fsl_mc_bus_dprc(mc_dev)) { + struct fsl_mc_device *mc_cont = to_fsl_mc_device(mc_dev->dev.parent); + + mc_dev->mc_io = mc_cont->mc_io; + return 0; + } + + vdev->nb.notifier_call = vfio_fsl_mc_bus_notifier; + ret = bus_register_notifier(&fsl_mc_bus_type, &vdev->nb); + if (ret) + return ret; + + /* open DPRC, allocate a MC portal */ + ret = dprc_setup(mc_dev); + if (ret) { + dev_err(&mc_dev->dev, "VFIO_FSL_MC: Failed to setup DPRC (%d)\n", ret); + goto out_nc_unreg; + } + + ret = dprc_scan_container(mc_dev, false); + if (ret) { + dev_err(&mc_dev->dev, "VFIO_FSL_MC: Container scanning failed (%d)\n", ret); + goto out_dprc_cleanup; + } + + return 0; + +out_dprc_cleanup: + dprc_remove_devices(mc_dev, NULL, 0); + dprc_cleanup(mc_dev); +out_nc_unreg: + bus_unregister_notifier(&fsl_mc_bus_type, &vdev->nb); + vdev->nb.notifier_call = NULL; + + return ret; +} + static int vfio_fsl_mc_probe(struct fsl_mc_device *mc_dev) { struct iommu_group *group; @@ -110,8 +186,15 @@ static int vfio_fsl_mc_probe(struct fsl_mc_device *mc_dev) dev_err(dev, "VFIO_FSL_MC: Failed to add to vfio group\n"); goto out_group_put; } + + ret = vfio_fsl_mc_init_device(vdev); + if (ret) + goto out_group_dev; + return 0; +out_group_dev: + vfio_del_group_dev(dev); out_group_put: vfio_iommu_group_put(group, dev); return ret; @@ -126,6 +209,14 @@ static int vfio_fsl_mc_remove(struct fsl_mc_device *mc_dev) if (!vdev) return -EINVAL; + if (is_fsl_mc_bus_dprc(mc_dev)) { + dprc_remove_devices(mc_dev, NULL, 0); + dprc_cleanup(mc_dev); + } + + if (vdev->nb.notifier_call) + bus_unregister_notifier(&fsl_mc_bus_type, &vdev->nb); + vfio_iommu_group_put(mc_dev->dev.iommu_group, dev); return 0; diff --git a/drivers/vfio/fsl-mc/vfio_fsl_mc_private.h b/drivers/vfio/fsl-mc/vfio_fsl_mc_private.h index e79cc116f6b8..37d61eaa58c8 100644 --- a/drivers/vfio/fsl-mc/vfio_fsl_mc_private.h +++ b/drivers/vfio/fsl-mc/vfio_fsl_mc_private.h @@ -9,6 +9,7 @@ struct vfio_fsl_mc_device { struct fsl_mc_device *mc_dev; + struct notifier_block nb; }; #endif /* VFIO_FSL_MC_PRIVATE_H */ -- cgit v1.2.3 From f97f4c04e5d6ca8b90b5b412bd7e72de79426263 Mon Sep 17 00:00:00 2001 From: Diana Craciun Date: Mon, 5 Oct 2020 20:36:47 +0300 Subject: vfio/fsl-mc: Implement VFIO_DEVICE_GET_INFO ioctl Allow userspace to get fsl-mc device info (number of regions and irqs). Signed-off-by: Bharat Bhushan Signed-off-by: Diana Craciun Reviewed-by: Eric Auger Signed-off-by: Alex Williamson --- drivers/vfio/fsl-mc/vfio_fsl_mc.c | 21 ++++++++++++++++++++- 1 file changed, 20 insertions(+), 1 deletion(-) (limited to 'drivers/vfio') diff --git a/drivers/vfio/fsl-mc/vfio_fsl_mc.c b/drivers/vfio/fsl-mc/vfio_fsl_mc.c index 594760203268..161c2cbe07dc 100644 --- a/drivers/vfio/fsl-mc/vfio_fsl_mc.c +++ b/drivers/vfio/fsl-mc/vfio_fsl_mc.c @@ -33,10 +33,29 @@ static void vfio_fsl_mc_release(void *device_data) static long vfio_fsl_mc_ioctl(void *device_data, unsigned int cmd, unsigned long arg) { + unsigned long minsz; + struct vfio_fsl_mc_device *vdev = device_data; + struct fsl_mc_device *mc_dev = vdev->mc_dev; + switch (cmd) { case VFIO_DEVICE_GET_INFO: { - return -ENOTTY; + struct vfio_device_info info; + + minsz = offsetofend(struct vfio_device_info, num_irqs); + + if (copy_from_user(&info, (void __user *)arg, minsz)) + return -EFAULT; + + if (info.argsz < minsz) + return -EINVAL; + + info.flags = VFIO_DEVICE_FLAGS_FSL_MC; + info.num_regions = mc_dev->obj_desc.region_count; + info.num_irqs = mc_dev->obj_desc.irq_count; + + return copy_to_user((void __user *)arg, &info, minsz) ? + -EFAULT : 0; } case VFIO_DEVICE_GET_REGION_INFO: { -- cgit v1.2.3 From df747bcd5b216dae7be26945fab2558ed2f7f363 Mon Sep 17 00:00:00 2001 From: Diana Craciun Date: Mon, 5 Oct 2020 20:36:48 +0300 Subject: vfio/fsl-mc: Implement VFIO_DEVICE_GET_REGION_INFO ioctl call Expose to userspace information about the memory regions. Signed-off-by: Bharat Bhushan Signed-off-by: Diana Craciun Reviewed-by: Eric Auger Signed-off-by: Alex Williamson --- drivers/vfio/fsl-mc/vfio_fsl_mc.c | 79 ++++++++++++++++++++++++++++++- drivers/vfio/fsl-mc/vfio_fsl_mc_private.h | 18 +++++++ 2 files changed, 96 insertions(+), 1 deletion(-) (limited to 'drivers/vfio') diff --git a/drivers/vfio/fsl-mc/vfio_fsl_mc.c b/drivers/vfio/fsl-mc/vfio_fsl_mc.c index 161c2cbe07dc..05dace5ddc2c 100644 --- a/drivers/vfio/fsl-mc/vfio_fsl_mc.c +++ b/drivers/vfio/fsl-mc/vfio_fsl_mc.c @@ -17,16 +17,71 @@ static struct fsl_mc_driver vfio_fsl_mc_driver; +static int vfio_fsl_mc_regions_init(struct vfio_fsl_mc_device *vdev) +{ + struct fsl_mc_device *mc_dev = vdev->mc_dev; + int count = mc_dev->obj_desc.region_count; + int i; + + vdev->regions = kcalloc(count, sizeof(struct vfio_fsl_mc_region), + GFP_KERNEL); + if (!vdev->regions) + return -ENOMEM; + + for (i = 0; i < count; i++) { + struct resource *res = &mc_dev->regions[i]; + + vdev->regions[i].addr = res->start; + vdev->regions[i].size = resource_size(res); + vdev->regions[i].flags = 0; + vdev->regions[i].type = mc_dev->regions[i].flags & IORESOURCE_BITS; + } + + return 0; +} + +static void vfio_fsl_mc_regions_cleanup(struct vfio_fsl_mc_device *vdev) +{ + kfree(vdev->regions); +} + static int vfio_fsl_mc_open(void *device_data) { + struct vfio_fsl_mc_device *vdev = device_data; + int ret; + if (!try_module_get(THIS_MODULE)) return -ENODEV; + mutex_lock(&vdev->driver_lock); + if (!vdev->refcnt) { + ret = vfio_fsl_mc_regions_init(vdev); + if (ret) + goto err_reg_init; + } + vdev->refcnt++; + + mutex_unlock(&vdev->driver_lock); + return 0; + +err_reg_init: + mutex_unlock(&vdev->driver_lock); + module_put(THIS_MODULE); + return ret; } static void vfio_fsl_mc_release(void *device_data) { + struct vfio_fsl_mc_device *vdev = device_data; + + mutex_lock(&vdev->driver_lock); + + if (!(--vdev->refcnt)) + vfio_fsl_mc_regions_cleanup(vdev); + + mutex_unlock(&vdev->driver_lock); + module_put(THIS_MODULE); } @@ -59,7 +114,25 @@ static long vfio_fsl_mc_ioctl(void *device_data, unsigned int cmd, } case VFIO_DEVICE_GET_REGION_INFO: { - return -ENOTTY; + struct vfio_region_info info; + + minsz = offsetofend(struct vfio_region_info, offset); + + if (copy_from_user(&info, (void __user *)arg, minsz)) + return -EFAULT; + + if (info.argsz < minsz) + return -EINVAL; + + if (info.index >= mc_dev->obj_desc.region_count) + return -EINVAL; + + /* map offset to the physical address */ + info.offset = VFIO_FSL_MC_INDEX_TO_OFFSET(info.index); + info.size = vdev->regions[info.index].size; + info.flags = vdev->regions[info.index].flags; + + return copy_to_user((void __user *)arg, &info, minsz); } case VFIO_DEVICE_GET_IRQ_INFO: { @@ -210,6 +283,8 @@ static int vfio_fsl_mc_probe(struct fsl_mc_device *mc_dev) if (ret) goto out_group_dev; + mutex_init(&vdev->driver_lock); + return 0; out_group_dev: @@ -228,6 +303,8 @@ static int vfio_fsl_mc_remove(struct fsl_mc_device *mc_dev) if (!vdev) return -EINVAL; + mutex_destroy(&vdev->driver_lock); + if (is_fsl_mc_bus_dprc(mc_dev)) { dprc_remove_devices(mc_dev, NULL, 0); dprc_cleanup(mc_dev); diff --git a/drivers/vfio/fsl-mc/vfio_fsl_mc_private.h b/drivers/vfio/fsl-mc/vfio_fsl_mc_private.h index 37d61eaa58c8..be60f41af30f 100644 --- a/drivers/vfio/fsl-mc/vfio_fsl_mc_private.h +++ b/drivers/vfio/fsl-mc/vfio_fsl_mc_private.h @@ -7,9 +7,27 @@ #ifndef VFIO_FSL_MC_PRIVATE_H #define VFIO_FSL_MC_PRIVATE_H +#define VFIO_FSL_MC_OFFSET_SHIFT 40 +#define VFIO_FSL_MC_OFFSET_MASK (((u64)(1) << VFIO_FSL_MC_OFFSET_SHIFT) - 1) + +#define VFIO_FSL_MC_OFFSET_TO_INDEX(off) ((off) >> VFIO_FSL_MC_OFFSET_SHIFT) + +#define VFIO_FSL_MC_INDEX_TO_OFFSET(index) \ + ((u64)(index) << VFIO_FSL_MC_OFFSET_SHIFT) + +struct vfio_fsl_mc_region { + u32 flags; + u32 type; + u64 addr; + resource_size_t size; +}; + struct vfio_fsl_mc_device { struct fsl_mc_device *mc_dev; struct notifier_block nb; + int refcnt; + struct vfio_fsl_mc_region *regions; + struct mutex driver_lock; }; #endif /* VFIO_FSL_MC_PRIVATE_H */ -- cgit v1.2.3 From 67247289688d49a610a956c23c4ff032f0281845 Mon Sep 17 00:00:00 2001 From: Diana Craciun Date: Mon, 5 Oct 2020 20:36:49 +0300 Subject: vfio/fsl-mc: Allow userspace to MMAP fsl-mc device MMIO regions Allow userspace to mmap device regions for direct access of fsl-mc devices. Signed-off-by: Bharat Bhushan Signed-off-by: Diana Craciun Reviewed-by: Eric Auger Signed-off-by: Alex Williamson --- drivers/vfio/fsl-mc/vfio_fsl_mc.c | 68 +++++++++++++++++++++++++++++++++++++-- 1 file changed, 66 insertions(+), 2 deletions(-) (limited to 'drivers/vfio') diff --git a/drivers/vfio/fsl-mc/vfio_fsl_mc.c b/drivers/vfio/fsl-mc/vfio_fsl_mc.c index 05dace5ddc2c..55190a2730fb 100644 --- a/drivers/vfio/fsl-mc/vfio_fsl_mc.c +++ b/drivers/vfio/fsl-mc/vfio_fsl_mc.c @@ -30,11 +30,20 @@ static int vfio_fsl_mc_regions_init(struct vfio_fsl_mc_device *vdev) for (i = 0; i < count; i++) { struct resource *res = &mc_dev->regions[i]; + int no_mmap = is_fsl_mc_bus_dprc(mc_dev); vdev->regions[i].addr = res->start; vdev->regions[i].size = resource_size(res); - vdev->regions[i].flags = 0; vdev->regions[i].type = mc_dev->regions[i].flags & IORESOURCE_BITS; + /* + * Only regions addressed with PAGE granularity may be + * MMAPed securely. + */ + if (!no_mmap && !(vdev->regions[i].addr & ~PAGE_MASK) && + !(vdev->regions[i].size & ~PAGE_MASK)) + vdev->regions[i].flags |= + VFIO_REGION_INFO_FLAG_MMAP; + } return 0; @@ -163,9 +172,64 @@ static ssize_t vfio_fsl_mc_write(void *device_data, const char __user *buf, return -EINVAL; } +static int vfio_fsl_mc_mmap_mmio(struct vfio_fsl_mc_region region, + struct vm_area_struct *vma) +{ + u64 size = vma->vm_end - vma->vm_start; + u64 pgoff, base; + u8 region_cacheable; + + pgoff = vma->vm_pgoff & + ((1U << (VFIO_FSL_MC_OFFSET_SHIFT - PAGE_SHIFT)) - 1); + base = pgoff << PAGE_SHIFT; + + if (region.size < PAGE_SIZE || base + size > region.size) + return -EINVAL; + + region_cacheable = (region.type & FSL_MC_REGION_CACHEABLE) && + (region.type & FSL_MC_REGION_SHAREABLE); + if (!region_cacheable) + vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); + + vma->vm_pgoff = (region.addr >> PAGE_SHIFT) + pgoff; + + return remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff, + size, vma->vm_page_prot); +} + static int vfio_fsl_mc_mmap(void *device_data, struct vm_area_struct *vma) { - return -EINVAL; + struct vfio_fsl_mc_device *vdev = device_data; + struct fsl_mc_device *mc_dev = vdev->mc_dev; + int index; + + index = vma->vm_pgoff >> (VFIO_FSL_MC_OFFSET_SHIFT - PAGE_SHIFT); + + if (vma->vm_end < vma->vm_start) + return -EINVAL; + if (vma->vm_start & ~PAGE_MASK) + return -EINVAL; + if (vma->vm_end & ~PAGE_MASK) + return -EINVAL; + if (!(vma->vm_flags & VM_SHARED)) + return -EINVAL; + if (index >= mc_dev->obj_desc.region_count) + return -EINVAL; + + if (!(vdev->regions[index].flags & VFIO_REGION_INFO_FLAG_MMAP)) + return -EINVAL; + + if (!(vdev->regions[index].flags & VFIO_REGION_INFO_FLAG_READ) + && (vma->vm_flags & VM_READ)) + return -EINVAL; + + if (!(vdev->regions[index].flags & VFIO_REGION_INFO_FLAG_WRITE) + && (vma->vm_flags & VM_WRITE)) + return -EINVAL; + + vma->vm_private_data = mc_dev; + + return vfio_fsl_mc_mmap_mmio(vdev->regions[index], vma); } static const struct vfio_device_ops vfio_fsl_mc_ops = { -- cgit v1.2.3 From f2ba7e8c947bf38fec799fdf9122e05a6a3e8382 Mon Sep 17 00:00:00 2001 From: Diana Craciun Date: Mon, 5 Oct 2020 20:36:50 +0300 Subject: vfio/fsl-mc: Added lock support in preparation for interrupt handling Only the DPRC object allocates interrupts from the MSI interrupt domain. The interrupts are managed by the DPRC in a pool of interrupts. The access to this pool of interrupts has to be protected with a lock. This patch extends the current lock implementation to have a lock per DPRC. Signed-off-by: Diana Craciun Reviewed-by: Eric Auger Signed-off-by: Alex Williamson --- drivers/vfio/fsl-mc/vfio_fsl_mc.c | 92 ++++++++++++++++++++++++++++--- drivers/vfio/fsl-mc/vfio_fsl_mc_private.h | 7 ++- 2 files changed, 90 insertions(+), 9 deletions(-) (limited to 'drivers/vfio') diff --git a/drivers/vfio/fsl-mc/vfio_fsl_mc.c b/drivers/vfio/fsl-mc/vfio_fsl_mc.c index 55190a2730fb..b52407c4e1ea 100644 --- a/drivers/vfio/fsl-mc/vfio_fsl_mc.c +++ b/drivers/vfio/fsl-mc/vfio_fsl_mc.c @@ -17,6 +17,78 @@ static struct fsl_mc_driver vfio_fsl_mc_driver; +static DEFINE_MUTEX(reflck_lock); + +static void vfio_fsl_mc_reflck_get(struct vfio_fsl_mc_reflck *reflck) +{ + kref_get(&reflck->kref); +} + +static void vfio_fsl_mc_reflck_release(struct kref *kref) +{ + struct vfio_fsl_mc_reflck *reflck = container_of(kref, + struct vfio_fsl_mc_reflck, + kref); + + mutex_destroy(&reflck->lock); + kfree(reflck); + mutex_unlock(&reflck_lock); +} + +static void vfio_fsl_mc_reflck_put(struct vfio_fsl_mc_reflck *reflck) +{ + kref_put_mutex(&reflck->kref, vfio_fsl_mc_reflck_release, &reflck_lock); +} + +static struct vfio_fsl_mc_reflck *vfio_fsl_mc_reflck_alloc(void) +{ + struct vfio_fsl_mc_reflck *reflck; + + reflck = kzalloc(sizeof(*reflck), GFP_KERNEL); + if (!reflck) + return ERR_PTR(-ENOMEM); + + kref_init(&reflck->kref); + mutex_init(&reflck->lock); + + return reflck; +} + +static int vfio_fsl_mc_reflck_attach(struct vfio_fsl_mc_device *vdev) +{ + int ret; + + mutex_lock(&reflck_lock); + if (is_fsl_mc_bus_dprc(vdev->mc_dev)) { + vdev->reflck = vfio_fsl_mc_reflck_alloc(); + ret = PTR_ERR_OR_ZERO(vdev->reflck); + } else { + struct device *mc_cont_dev = vdev->mc_dev->dev.parent; + struct vfio_device *device; + struct vfio_fsl_mc_device *cont_vdev; + + device = vfio_device_get_from_dev(mc_cont_dev); + if (!device) { + ret = -ENODEV; + goto unlock; + } + + cont_vdev = vfio_device_data(device); + if (!cont_vdev || !cont_vdev->reflck) { + vfio_device_put(device); + ret = -ENODEV; + goto unlock; + } + vfio_fsl_mc_reflck_get(cont_vdev->reflck); + vdev->reflck = cont_vdev->reflck; + vfio_device_put(device); + } + +unlock: + mutex_unlock(&reflck_lock); + return ret; +} + static int vfio_fsl_mc_regions_init(struct vfio_fsl_mc_device *vdev) { struct fsl_mc_device *mc_dev = vdev->mc_dev; @@ -62,7 +134,7 @@ static int vfio_fsl_mc_open(void *device_data) if (!try_module_get(THIS_MODULE)) return -ENODEV; - mutex_lock(&vdev->driver_lock); + mutex_lock(&vdev->reflck->lock); if (!vdev->refcnt) { ret = vfio_fsl_mc_regions_init(vdev); if (ret) @@ -70,12 +142,12 @@ static int vfio_fsl_mc_open(void *device_data) } vdev->refcnt++; - mutex_unlock(&vdev->driver_lock); + mutex_unlock(&vdev->reflck->lock); return 0; err_reg_init: - mutex_unlock(&vdev->driver_lock); + mutex_unlock(&vdev->reflck->lock); module_put(THIS_MODULE); return ret; } @@ -84,12 +156,12 @@ static void vfio_fsl_mc_release(void *device_data) { struct vfio_fsl_mc_device *vdev = device_data; - mutex_lock(&vdev->driver_lock); + mutex_lock(&vdev->reflck->lock); if (!(--vdev->refcnt)) vfio_fsl_mc_regions_cleanup(vdev); - mutex_unlock(&vdev->driver_lock); + mutex_unlock(&vdev->reflck->lock); module_put(THIS_MODULE); } @@ -343,14 +415,18 @@ static int vfio_fsl_mc_probe(struct fsl_mc_device *mc_dev) goto out_group_put; } - ret = vfio_fsl_mc_init_device(vdev); + ret = vfio_fsl_mc_reflck_attach(vdev); if (ret) goto out_group_dev; - mutex_init(&vdev->driver_lock); + ret = vfio_fsl_mc_init_device(vdev); + if (ret) + goto out_reflck; return 0; +out_reflck: + vfio_fsl_mc_reflck_put(vdev->reflck); out_group_dev: vfio_del_group_dev(dev); out_group_put: @@ -367,7 +443,7 @@ static int vfio_fsl_mc_remove(struct fsl_mc_device *mc_dev) if (!vdev) return -EINVAL; - mutex_destroy(&vdev->driver_lock); + vfio_fsl_mc_reflck_put(vdev->reflck); if (is_fsl_mc_bus_dprc(mc_dev)) { dprc_remove_devices(mc_dev, NULL, 0); diff --git a/drivers/vfio/fsl-mc/vfio_fsl_mc_private.h b/drivers/vfio/fsl-mc/vfio_fsl_mc_private.h index be60f41af30f..d47ef6215429 100644 --- a/drivers/vfio/fsl-mc/vfio_fsl_mc_private.h +++ b/drivers/vfio/fsl-mc/vfio_fsl_mc_private.h @@ -15,6 +15,11 @@ #define VFIO_FSL_MC_INDEX_TO_OFFSET(index) \ ((u64)(index) << VFIO_FSL_MC_OFFSET_SHIFT) +struct vfio_fsl_mc_reflck { + struct kref kref; + struct mutex lock; +}; + struct vfio_fsl_mc_region { u32 flags; u32 type; @@ -27,7 +32,7 @@ struct vfio_fsl_mc_device { struct notifier_block nb; int refcnt; struct vfio_fsl_mc_region *regions; - struct mutex driver_lock; + struct vfio_fsl_mc_reflck *reflck; }; #endif /* VFIO_FSL_MC_PRIVATE_H */ -- cgit v1.2.3 From 2e0d29561f593a5ab6d37ea032513d2714a007df Mon Sep 17 00:00:00 2001 From: Diana Craciun Date: Mon, 5 Oct 2020 20:36:51 +0300 Subject: vfio/fsl-mc: Add irq infrastructure for fsl-mc devices This patch adds the skeleton for interrupt support for fsl-mc devices. The interrupts are not yet functional, the functionality will be added by subsequent patches. Signed-off-by: Bharat Bhushan Signed-off-by: Diana Craciun Reviewed-by: Eric Auger Signed-off-by: Alex Williamson --- drivers/vfio/fsl-mc/Makefile | 2 +- drivers/vfio/fsl-mc/vfio_fsl_mc.c | 52 +++++++++++++++++++++++++++++-- drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c | 34 ++++++++++++++++++++ drivers/vfio/fsl-mc/vfio_fsl_mc_private.h | 6 ++++ 4 files changed, 91 insertions(+), 3 deletions(-) create mode 100644 drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c (limited to 'drivers/vfio') diff --git a/drivers/vfio/fsl-mc/Makefile b/drivers/vfio/fsl-mc/Makefile index 0c6e5d2ddaae..cad6dbf0b735 100644 --- a/drivers/vfio/fsl-mc/Makefile +++ b/drivers/vfio/fsl-mc/Makefile @@ -1,4 +1,4 @@ # SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) -vfio-fsl-mc-y := vfio_fsl_mc.o +vfio-fsl-mc-y := vfio_fsl_mc.o vfio_fsl_mc_intr.o obj-$(CONFIG_VFIO_FSL_MC) += vfio-fsl-mc.o diff --git a/drivers/vfio/fsl-mc/vfio_fsl_mc.c b/drivers/vfio/fsl-mc/vfio_fsl_mc.c index b52407c4e1ea..7803a9d6bfd9 100644 --- a/drivers/vfio/fsl-mc/vfio_fsl_mc.c +++ b/drivers/vfio/fsl-mc/vfio_fsl_mc.c @@ -217,11 +217,55 @@ static long vfio_fsl_mc_ioctl(void *device_data, unsigned int cmd, } case VFIO_DEVICE_GET_IRQ_INFO: { - return -ENOTTY; + struct vfio_irq_info info; + + minsz = offsetofend(struct vfio_irq_info, count); + if (copy_from_user(&info, (void __user *)arg, minsz)) + return -EFAULT; + + if (info.argsz < minsz) + return -EINVAL; + + if (info.index >= mc_dev->obj_desc.irq_count) + return -EINVAL; + + info.flags = VFIO_IRQ_INFO_EVENTFD; + info.count = 1; + + return copy_to_user((void __user *)arg, &info, minsz); } case VFIO_DEVICE_SET_IRQS: { - return -ENOTTY; + struct vfio_irq_set hdr; + u8 *data = NULL; + int ret = 0; + size_t data_size = 0; + + minsz = offsetofend(struct vfio_irq_set, count); + + if (copy_from_user(&hdr, (void __user *)arg, minsz)) + return -EFAULT; + + ret = vfio_set_irqs_validate_and_prepare(&hdr, mc_dev->obj_desc.irq_count, + mc_dev->obj_desc.irq_count, &data_size); + if (ret) + return ret; + + if (data_size) { + data = memdup_user((void __user *)(arg + minsz), + data_size); + if (IS_ERR(data)) + return PTR_ERR(data); + } + + mutex_lock(&vdev->igate); + ret = vfio_fsl_mc_set_irqs_ioctl(vdev, hdr.flags, + hdr.index, hdr.start, + hdr.count, data); + mutex_unlock(&vdev->igate); + kfree(data); + + return ret; } case VFIO_DEVICE_RESET: { @@ -423,6 +467,8 @@ static int vfio_fsl_mc_probe(struct fsl_mc_device *mc_dev) if (ret) goto out_reflck; + mutex_init(&vdev->igate); + return 0; out_reflck: @@ -443,6 +489,8 @@ static int vfio_fsl_mc_remove(struct fsl_mc_device *mc_dev) if (!vdev) return -EINVAL; + mutex_destroy(&vdev->igate); + vfio_fsl_mc_reflck_put(vdev->reflck); if (is_fsl_mc_bus_dprc(mc_dev)) { diff --git a/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c b/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c new file mode 100644 index 000000000000..5232f208e361 --- /dev/null +++ b/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c @@ -0,0 +1,34 @@ +// SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) +/* + * Copyright 2013-2016 Freescale Semiconductor Inc. + * Copyright 2019 NXP + */ + +#include +#include +#include +#include +#include + +#include "linux/fsl/mc.h" +#include "vfio_fsl_mc_private.h" + +static int vfio_fsl_mc_set_irq_trigger(struct vfio_fsl_mc_device *vdev, + unsigned int index, unsigned int start, + unsigned int count, u32 flags, + void *data) +{ + return -EINVAL; +} + +int vfio_fsl_mc_set_irqs_ioctl(struct vfio_fsl_mc_device *vdev, + u32 flags, unsigned int index, + unsigned int start, unsigned int count, + void *data) +{ + if (flags & VFIO_IRQ_SET_ACTION_TRIGGER) + return vfio_fsl_mc_set_irq_trigger(vdev, index, start, + count, flags, data); + else + return -EINVAL; +} diff --git a/drivers/vfio/fsl-mc/vfio_fsl_mc_private.h b/drivers/vfio/fsl-mc/vfio_fsl_mc_private.h index d47ef6215429..2c3f625a3240 100644 --- a/drivers/vfio/fsl-mc/vfio_fsl_mc_private.h +++ b/drivers/vfio/fsl-mc/vfio_fsl_mc_private.h @@ -33,6 +33,12 @@ struct vfio_fsl_mc_device { int refcnt; struct vfio_fsl_mc_region *regions; struct vfio_fsl_mc_reflck *reflck; + struct mutex igate; }; +extern int vfio_fsl_mc_set_irqs_ioctl(struct vfio_fsl_mc_device *vdev, + u32 flags, unsigned int index, + unsigned int start, unsigned int count, + void *data); + #endif /* VFIO_FSL_MC_PRIVATE_H */ -- cgit v1.2.3 From cc0ee20bd96971c10eba9a83ecf1c0733078a083 Mon Sep 17 00:00:00 2001 From: Diana Craciun Date: Mon, 5 Oct 2020 20:36:52 +0300 Subject: vfio/fsl-mc: trigger an interrupt via eventfd This patch allows to set an eventfd for fsl-mc device interrupts and also to trigger the interrupt eventfd from userspace for testing. All fsl-mc device interrupts are MSIs. The MSIs are allocated from the MSI domain only once per DPRC and used by all the DPAA2 objects. The interrupts are managed by the DPRC in a pool of interrupts. Each device requests interrupts from this pool. The pool is allocated when the first virtual device is setting the interrupts. The pool of interrupts is protected by a lock. The DPRC has an interrupt of its own which indicates if the DPRC contents have changed. However, currently, the contents of a DPRC assigned to the guest cannot be changed at runtime, so this interrupt is not configured. Signed-off-by: Bharat Bhushan Signed-off-by: Diana Craciun Reviewed-by: Eric Auger Signed-off-by: Alex Williamson --- drivers/vfio/fsl-mc/vfio_fsl_mc.c | 24 ++++- drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c | 162 +++++++++++++++++++++++++++++- drivers/vfio/fsl-mc/vfio_fsl_mc_private.h | 10 ++ 3 files changed, 194 insertions(+), 2 deletions(-) (limited to 'drivers/vfio') diff --git a/drivers/vfio/fsl-mc/vfio_fsl_mc.c b/drivers/vfio/fsl-mc/vfio_fsl_mc.c index 7803a9d6bfd9..feb5dafd4bf5 100644 --- a/drivers/vfio/fsl-mc/vfio_fsl_mc.c +++ b/drivers/vfio/fsl-mc/vfio_fsl_mc.c @@ -155,12 +155,34 @@ err_reg_init: static void vfio_fsl_mc_release(void *device_data) { struct vfio_fsl_mc_device *vdev = device_data; + int ret; mutex_lock(&vdev->reflck->lock); - if (!(--vdev->refcnt)) + if (!(--vdev->refcnt)) { + struct fsl_mc_device *mc_dev = vdev->mc_dev; + struct device *cont_dev = fsl_mc_cont_dev(&mc_dev->dev); + struct fsl_mc_device *mc_cont = to_fsl_mc_device(cont_dev); + vfio_fsl_mc_regions_cleanup(vdev); + /* reset the device before cleaning up the interrupts */ + ret = dprc_reset_container(mc_cont->mc_io, 0, + mc_cont->mc_handle, + mc_cont->obj_desc.id, + DPRC_RESET_OPTION_NON_RECURSIVE); + + if (ret) { + dev_warn(&mc_cont->dev, "VFIO_FLS_MC: reset device has failed (%d)\n", + ret); + WARN_ON(1); + } + + vfio_fsl_mc_irqs_cleanup(vdev); + + fsl_mc_cleanup_irq_pool(mc_cont); + } + mutex_unlock(&vdev->reflck->lock); module_put(THIS_MODULE); diff --git a/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c b/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c index 5232f208e361..2ce2acad3461 100644 --- a/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c +++ b/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c @@ -13,12 +13,150 @@ #include "linux/fsl/mc.h" #include "vfio_fsl_mc_private.h" +int vfio_fsl_mc_irqs_allocate(struct vfio_fsl_mc_device *vdev) +{ + struct fsl_mc_device *mc_dev = vdev->mc_dev; + struct vfio_fsl_mc_irq *mc_irq; + int irq_count; + int ret, i; + + /* Device does not support any interrupt */ + if (mc_dev->obj_desc.irq_count == 0) + return 0; + + /* interrupts were already allocated for this device */ + if (vdev->mc_irqs) + return 0; + + irq_count = mc_dev->obj_desc.irq_count; + + mc_irq = kcalloc(irq_count, sizeof(*mc_irq), GFP_KERNEL); + if (!mc_irq) + return -ENOMEM; + + /* Allocate IRQs */ + ret = fsl_mc_allocate_irqs(mc_dev); + if (ret) { + kfree(mc_irq); + return ret; + } + + for (i = 0; i < irq_count; i++) { + mc_irq[i].count = 1; + mc_irq[i].flags = VFIO_IRQ_INFO_EVENTFD; + } + + vdev->mc_irqs = mc_irq; + + return 0; +} + +static irqreturn_t vfio_fsl_mc_irq_handler(int irq_num, void *arg) +{ + struct vfio_fsl_mc_irq *mc_irq = (struct vfio_fsl_mc_irq *)arg; + + eventfd_signal(mc_irq->trigger, 1); + return IRQ_HANDLED; +} + +static int vfio_set_trigger(struct vfio_fsl_mc_device *vdev, + int index, int fd) +{ + struct vfio_fsl_mc_irq *irq = &vdev->mc_irqs[index]; + struct eventfd_ctx *trigger; + int hwirq; + int ret; + + hwirq = vdev->mc_dev->irqs[index]->msi_desc->irq; + if (irq->trigger) { + free_irq(hwirq, irq); + kfree(irq->name); + eventfd_ctx_put(irq->trigger); + irq->trigger = NULL; + } + + if (fd < 0) /* Disable only */ + return 0; + + irq->name = kasprintf(GFP_KERNEL, "vfio-irq[%d](%s)", + hwirq, dev_name(&vdev->mc_dev->dev)); + if (!irq->name) + return -ENOMEM; + + trigger = eventfd_ctx_fdget(fd); + if (IS_ERR(trigger)) { + kfree(irq->name); + return PTR_ERR(trigger); + } + + irq->trigger = trigger; + + ret = request_irq(hwirq, vfio_fsl_mc_irq_handler, 0, + irq->name, irq); + if (ret) { + kfree(irq->name); + eventfd_ctx_put(trigger); + irq->trigger = NULL; + return ret; + } + + return 0; +} + static int vfio_fsl_mc_set_irq_trigger(struct vfio_fsl_mc_device *vdev, unsigned int index, unsigned int start, unsigned int count, u32 flags, void *data) { - return -EINVAL; + struct fsl_mc_device *mc_dev = vdev->mc_dev; + int ret, hwirq; + struct vfio_fsl_mc_irq *irq; + struct device *cont_dev = fsl_mc_cont_dev(&mc_dev->dev); + struct fsl_mc_device *mc_cont = to_fsl_mc_device(cont_dev); + + if (start != 0 || count != 1) + return -EINVAL; + + mutex_lock(&vdev->reflck->lock); + ret = fsl_mc_populate_irq_pool(mc_cont, + FSL_MC_IRQ_POOL_MAX_TOTAL_IRQS); + if (ret) + goto unlock; + + ret = vfio_fsl_mc_irqs_allocate(vdev); + if (ret) + goto unlock; + mutex_unlock(&vdev->reflck->lock); + + if (!count && (flags & VFIO_IRQ_SET_DATA_NONE)) + return vfio_set_trigger(vdev, index, -1); + + if (flags & VFIO_IRQ_SET_DATA_EVENTFD) { + s32 fd = *(s32 *)data; + + return vfio_set_trigger(vdev, index, fd); + } + + hwirq = vdev->mc_dev->irqs[index]->msi_desc->irq; + + irq = &vdev->mc_irqs[index]; + + if (flags & VFIO_IRQ_SET_DATA_NONE) { + vfio_fsl_mc_irq_handler(hwirq, irq); + + } else if (flags & VFIO_IRQ_SET_DATA_BOOL) { + u8 trigger = *(u8 *)data; + + if (trigger) + vfio_fsl_mc_irq_handler(hwirq, irq); + } + + return 0; + +unlock: + mutex_unlock(&vdev->reflck->lock); + return ret; + } int vfio_fsl_mc_set_irqs_ioctl(struct vfio_fsl_mc_device *vdev, @@ -32,3 +170,25 @@ int vfio_fsl_mc_set_irqs_ioctl(struct vfio_fsl_mc_device *vdev, else return -EINVAL; } + +/* Free All IRQs for the given MC object */ +void vfio_fsl_mc_irqs_cleanup(struct vfio_fsl_mc_device *vdev) +{ + struct fsl_mc_device *mc_dev = vdev->mc_dev; + int irq_count = mc_dev->obj_desc.irq_count; + int i; + + /* + * Device does not support any interrupt or the interrupts + * were not configured + */ + if (!vdev->mc_irqs) + return; + + for (i = 0; i < irq_count; i++) + vfio_set_trigger(vdev, i, -1); + + fsl_mc_free_irqs(mc_dev); + kfree(vdev->mc_irqs); + vdev->mc_irqs = NULL; +} diff --git a/drivers/vfio/fsl-mc/vfio_fsl_mc_private.h b/drivers/vfio/fsl-mc/vfio_fsl_mc_private.h index 2c3f625a3240..7aa49b9ba60d 100644 --- a/drivers/vfio/fsl-mc/vfio_fsl_mc_private.h +++ b/drivers/vfio/fsl-mc/vfio_fsl_mc_private.h @@ -15,6 +15,13 @@ #define VFIO_FSL_MC_INDEX_TO_OFFSET(index) \ ((u64)(index) << VFIO_FSL_MC_OFFSET_SHIFT) +struct vfio_fsl_mc_irq { + u32 flags; + u32 count; + struct eventfd_ctx *trigger; + char *name; +}; + struct vfio_fsl_mc_reflck { struct kref kref; struct mutex lock; @@ -34,6 +41,7 @@ struct vfio_fsl_mc_device { struct vfio_fsl_mc_region *regions; struct vfio_fsl_mc_reflck *reflck; struct mutex igate; + struct vfio_fsl_mc_irq *mc_irqs; }; extern int vfio_fsl_mc_set_irqs_ioctl(struct vfio_fsl_mc_device *vdev, @@ -41,4 +49,6 @@ extern int vfio_fsl_mc_set_irqs_ioctl(struct vfio_fsl_mc_device *vdev, unsigned int start, unsigned int count, void *data); +void vfio_fsl_mc_irqs_cleanup(struct vfio_fsl_mc_device *vdev); + #endif /* VFIO_FSL_MC_PRIVATE_H */ -- cgit v1.2.3 From 1bb141ed5e14f773f9e08b80fe5db3fd405399db Mon Sep 17 00:00:00 2001 From: Diana Craciun Date: Mon, 5 Oct 2020 20:36:53 +0300 Subject: vfio/fsl-mc: Add read/write support for fsl-mc devices The software uses a memory-mapped I/O command interface (MC portals) to communicate with the MC hardware. This command interface is used to discover, enumerate, configure and remove DPAA2 objects. The DPAA2 objects use MSIs, so the command interface needs to be emulated such that the correct MSI is configured in the hardware (the guest has the virtual MSIs). This patch is adding read/write support for fsl-mc devices. The mc commands are emulated by the userspace. The host is just passing the correct command to the hardware. Also the current patch limits userspace to write complete 64byte command once and read 64byte response by one ioctl. Signed-off-by: Bharat Bhushan Signed-off-by: Diana Craciun Signed-off-by: Alex Williamson --- drivers/vfio/fsl-mc/vfio_fsl_mc.c | 118 +++++++++++++++++++++++++++++- drivers/vfio/fsl-mc/vfio_fsl_mc_private.h | 1 + 2 files changed, 116 insertions(+), 3 deletions(-) (limited to 'drivers/vfio') diff --git a/drivers/vfio/fsl-mc/vfio_fsl_mc.c b/drivers/vfio/fsl-mc/vfio_fsl_mc.c index feb5dafd4bf5..d95568cd8021 100644 --- a/drivers/vfio/fsl-mc/vfio_fsl_mc.c +++ b/drivers/vfio/fsl-mc/vfio_fsl_mc.c @@ -12,6 +12,7 @@ #include #include #include +#include #include "vfio_fsl_mc_private.h" @@ -115,7 +116,9 @@ static int vfio_fsl_mc_regions_init(struct vfio_fsl_mc_device *vdev) !(vdev->regions[i].size & ~PAGE_MASK)) vdev->regions[i].flags |= VFIO_REGION_INFO_FLAG_MMAP; - + vdev->regions[i].flags |= VFIO_REGION_INFO_FLAG_READ; + if (!(mc_dev->regions[i].flags & IORESOURCE_READONLY)) + vdev->regions[i].flags |= VFIO_REGION_INFO_FLAG_WRITE; } return 0; @@ -123,6 +126,11 @@ static int vfio_fsl_mc_regions_init(struct vfio_fsl_mc_device *vdev) static void vfio_fsl_mc_regions_cleanup(struct vfio_fsl_mc_device *vdev) { + struct fsl_mc_device *mc_dev = vdev->mc_dev; + int i; + + for (i = 0; i < mc_dev->obj_desc.region_count; i++) + iounmap(vdev->regions[i].ioaddr); kfree(vdev->regions); } @@ -301,13 +309,117 @@ static long vfio_fsl_mc_ioctl(void *device_data, unsigned int cmd, static ssize_t vfio_fsl_mc_read(void *device_data, char __user *buf, size_t count, loff_t *ppos) { - return -EINVAL; + struct vfio_fsl_mc_device *vdev = device_data; + unsigned int index = VFIO_FSL_MC_OFFSET_TO_INDEX(*ppos); + loff_t off = *ppos & VFIO_FSL_MC_OFFSET_MASK; + struct fsl_mc_device *mc_dev = vdev->mc_dev; + struct vfio_fsl_mc_region *region; + u64 data[8]; + int i; + + if (index >= mc_dev->obj_desc.region_count) + return -EINVAL; + + region = &vdev->regions[index]; + + if (!(region->flags & VFIO_REGION_INFO_FLAG_READ)) + return -EINVAL; + + if (!region->ioaddr) { + region->ioaddr = ioremap(region->addr, region->size); + if (!region->ioaddr) + return -ENOMEM; + } + + if (count != 64 || off != 0) + return -EINVAL; + + for (i = 7; i >= 0; i--) + data[i] = readq(region->ioaddr + i * sizeof(uint64_t)); + + if (copy_to_user(buf, data, 64)) + return -EFAULT; + + return count; +} + +#define MC_CMD_COMPLETION_TIMEOUT_MS 5000 +#define MC_CMD_COMPLETION_POLLING_MAX_SLEEP_USECS 500 + +static int vfio_fsl_mc_send_command(void __iomem *ioaddr, uint64_t *cmd_data) +{ + int i; + enum mc_cmd_status status; + unsigned long timeout_usecs = MC_CMD_COMPLETION_TIMEOUT_MS * 1000; + + /* Write at command parameter into portal */ + for (i = 7; i >= 1; i--) + writeq_relaxed(cmd_data[i], ioaddr + i * sizeof(uint64_t)); + + /* Write command header in the end */ + writeq(cmd_data[0], ioaddr); + + /* Wait for response before returning to user-space + * This can be optimized in future to even prepare response + * before returning to user-space and avoid read ioctl. + */ + for (;;) { + u64 header; + struct mc_cmd_header *resp_hdr; + + header = cpu_to_le64(readq_relaxed(ioaddr)); + + resp_hdr = (struct mc_cmd_header *)&header; + status = (enum mc_cmd_status)resp_hdr->status; + if (status != MC_CMD_STATUS_READY) + break; + + udelay(MC_CMD_COMPLETION_POLLING_MAX_SLEEP_USECS); + timeout_usecs -= MC_CMD_COMPLETION_POLLING_MAX_SLEEP_USECS; + if (timeout_usecs == 0) + return -ETIMEDOUT; + } + + return 0; } static ssize_t vfio_fsl_mc_write(void *device_data, const char __user *buf, size_t count, loff_t *ppos) { - return -EINVAL; + struct vfio_fsl_mc_device *vdev = device_data; + unsigned int index = VFIO_FSL_MC_OFFSET_TO_INDEX(*ppos); + loff_t off = *ppos & VFIO_FSL_MC_OFFSET_MASK; + struct fsl_mc_device *mc_dev = vdev->mc_dev; + struct vfio_fsl_mc_region *region; + u64 data[8]; + int ret; + + if (index >= mc_dev->obj_desc.region_count) + return -EINVAL; + + region = &vdev->regions[index]; + + if (!(region->flags & VFIO_REGION_INFO_FLAG_WRITE)) + return -EINVAL; + + if (!region->ioaddr) { + region->ioaddr = ioremap(region->addr, region->size); + if (!region->ioaddr) + return -ENOMEM; + } + + if (count != 64 || off != 0) + return -EINVAL; + + if (copy_from_user(&data, buf, 64)) + return -EFAULT; + + ret = vfio_fsl_mc_send_command(region->ioaddr, data); + if (ret) + return ret; + + return count; + } static int vfio_fsl_mc_mmap_mmio(struct vfio_fsl_mc_region region, diff --git a/drivers/vfio/fsl-mc/vfio_fsl_mc_private.h b/drivers/vfio/fsl-mc/vfio_fsl_mc_private.h index 7aa49b9ba60d..a97ee691ed47 100644 --- a/drivers/vfio/fsl-mc/vfio_fsl_mc_private.h +++ b/drivers/vfio/fsl-mc/vfio_fsl_mc_private.h @@ -32,6 +32,7 @@ struct vfio_fsl_mc_region { u32 type; u64 addr; resource_size_t size; + void __iomem *ioaddr; }; struct vfio_fsl_mc_device { -- cgit v1.2.3 From ac93ab2bf69a5b7724106ec7ce852eff9c307510 Mon Sep 17 00:00:00 2001 From: Diana Craciun Date: Mon, 5 Oct 2020 20:36:54 +0300 Subject: vfio/fsl-mc: Add support for device reset Currently only resetting the DPRC container is supported which will reset all the objects inside it. Resetting individual objects is possible from the userspace by issueing commands towards MC firmware. Signed-off-by: Diana Craciun Reviewed-by: Eric Auger Signed-off-by: Alex Williamson --- drivers/vfio/fsl-mc/vfio_fsl_mc.c | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) (limited to 'drivers/vfio') diff --git a/drivers/vfio/fsl-mc/vfio_fsl_mc.c b/drivers/vfio/fsl-mc/vfio_fsl_mc.c index d95568cd8021..d009f873578c 100644 --- a/drivers/vfio/fsl-mc/vfio_fsl_mc.c +++ b/drivers/vfio/fsl-mc/vfio_fsl_mc.c @@ -217,6 +217,10 @@ static long vfio_fsl_mc_ioctl(void *device_data, unsigned int cmd, return -EINVAL; info.flags = VFIO_DEVICE_FLAGS_FSL_MC; + + if (is_fsl_mc_bus_dprc(mc_dev)) + info.flags |= VFIO_DEVICE_FLAGS_RESET; + info.num_regions = mc_dev->obj_desc.region_count; info.num_irqs = mc_dev->obj_desc.irq_count; @@ -299,7 +303,19 @@ static long vfio_fsl_mc_ioctl(void *device_data, unsigned int cmd, } case VFIO_DEVICE_RESET: { - return -ENOTTY; + int ret; + struct fsl_mc_device *mc_dev = vdev->mc_dev; + + /* reset is supported only for the DPRC */ + if (!is_fsl_mc_bus_dprc(mc_dev)) + return -ENOTTY; + + ret = dprc_reset_container(mc_dev->mc_io, 0, + mc_dev->mc_handle, + mc_dev->obj_desc.id, + DPRC_RESET_OPTION_NON_RECURSIVE); + return ret; + } default: return -ENOTTY; -- cgit v1.2.3 From e6b817d4b8217a9528fcfd59719b924ab8a5ff23 Mon Sep 17 00:00:00 2001 From: Matthew Rosato Date: Wed, 7 Oct 2020 14:56:23 -0400 Subject: vfio-pci/zdev: Add zPCI capabilities to VFIO_DEVICE_GET_INFO Define a new configuration entry VFIO_PCI_ZDEV for VFIO/PCI. When this s390-only feature is configured we add capabilities to the VFIO_DEVICE_GET_INFO ioctl that describe features of the associated zPCI device and its underlying hardware. This patch is based on work previously done by Pierre Morel. Signed-off-by: Matthew Rosato Reviewed-by: Cornelia Huck Signed-off-by: Alex Williamson --- drivers/vfio/pci/Kconfig | 12 +++ drivers/vfio/pci/Makefile | 1 + drivers/vfio/pci/vfio_pci.c | 37 ++++++++++ drivers/vfio/pci/vfio_pci_private.h | 12 +++ drivers/vfio/pci/vfio_pci_zdev.c | 143 ++++++++++++++++++++++++++++++++++++ 5 files changed, 205 insertions(+) create mode 100644 drivers/vfio/pci/vfio_pci_zdev.c (limited to 'drivers/vfio') 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..208dea5c5dba 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; 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 + * Matthew Rosato + * + * 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 +#include +#include +#include +#include +#include +#include + +#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; +} -- cgit v1.2.3 From 83e491799e631dd41e7c7a870dd3a7603c461123 Mon Sep 17 00:00:00 2001 From: Diana Craciun Date: Tue, 13 Oct 2020 18:06:51 +0300 Subject: vfio/fsl-mc: Fixed vfio-fsl-mc driver compilation on 32 bit The FSL_MC_BUS on which the VFIO-FSL-MC driver is dependent on can be compiled on other architectures as well (not only ARM64) including 32 bit architectures. Include linux/io-64-nonatomic-hi-lo.h to make writeq/readq used in the driver available on 32bit platforms. Signed-off-by: Diana Craciun Signed-off-by: Alex Williamson --- drivers/vfio/fsl-mc/vfio_fsl_mc.c | 1 + 1 file changed, 1 insertion(+) (limited to 'drivers/vfio') diff --git a/drivers/vfio/fsl-mc/vfio_fsl_mc.c b/drivers/vfio/fsl-mc/vfio_fsl_mc.c index d009f873578c..80fc7f4ed343 100644 --- a/drivers/vfio/fsl-mc/vfio_fsl_mc.c +++ b/drivers/vfio/fsl-mc/vfio_fsl_mc.c @@ -13,6 +13,7 @@ #include #include #include +#include #include "vfio_fsl_mc_private.h" -- cgit v1.2.3 From 159246378d8483ba63844fc03027df70501552c1 Mon Sep 17 00:00:00 2001 From: Diana Craciun Date: Thu, 15 Oct 2020 21:14:17 +0300 Subject: vfio/fsl-mc: Fix the dead code in vfio_fsl_mc_set_irq_trigger Static analysis discovered that some code in vfio_fsl_mc_set_irq_trigger is dead code. Fixed the code by changing the conditions order. Fixes: cc0ee20bd969 ("vfio/fsl-mc: trigger an interrupt via eventfd") Reported-by: Colin Ian King Signed-off-by: Diana Craciun Signed-off-by: Alex Williamson --- drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'drivers/vfio') diff --git a/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c b/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c index 2ce2acad3461..c80dceb46f79 100644 --- a/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c +++ b/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c @@ -114,6 +114,9 @@ static int vfio_fsl_mc_set_irq_trigger(struct vfio_fsl_mc_device *vdev, struct device *cont_dev = fsl_mc_cont_dev(&mc_dev->dev); struct fsl_mc_device *mc_cont = to_fsl_mc_device(cont_dev); + if (!count && (flags & VFIO_IRQ_SET_DATA_NONE)) + return vfio_set_trigger(vdev, index, -1); + if (start != 0 || count != 1) return -EINVAL; @@ -128,9 +131,6 @@ static int vfio_fsl_mc_set_irq_trigger(struct vfio_fsl_mc_device *vdev, goto unlock; mutex_unlock(&vdev->reflck->lock); - if (!count && (flags & VFIO_IRQ_SET_DATA_NONE)) - return vfio_set_trigger(vdev, index, -1); - if (flags & VFIO_IRQ_SET_DATA_EVENTFD) { s32 fd = *(s32 *)data; -- cgit v1.2.3 From 822e1a90afff61826252a65e574e940c0038055c Mon Sep 17 00:00:00 2001 From: Diana Craciun Date: Fri, 16 Oct 2020 12:32:32 +0300 Subject: vfio/fsl-mc: fix the return of the uninitialized variable ret The vfio_fsl_mc_reflck_attach function may return, on success path, an uninitialized variable. Fix the problem by initializing the return variable to 0. Addresses-Coverity: ("Uninitialized scalar variable") Fixes: f2ba7e8c947b ("vfio/fsl-mc: Added lock support in preparation for interrupt handling") Reported-by: Colin Ian King Signed-off-by: Diana Craciun Signed-off-by: Alex Williamson --- drivers/vfio/fsl-mc/vfio_fsl_mc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/vfio') diff --git a/drivers/vfio/fsl-mc/vfio_fsl_mc.c b/drivers/vfio/fsl-mc/vfio_fsl_mc.c index 80fc7f4ed343..0113a980f974 100644 --- a/drivers/vfio/fsl-mc/vfio_fsl_mc.c +++ b/drivers/vfio/fsl-mc/vfio_fsl_mc.c @@ -58,7 +58,7 @@ static struct vfio_fsl_mc_reflck *vfio_fsl_mc_reflck_alloc(void) static int vfio_fsl_mc_reflck_attach(struct vfio_fsl_mc_device *vdev) { - int ret; + int ret = 0; mutex_lock(&reflck_lock); if (is_fsl_mc_bus_dprc(vdev->mc_dev)) { -- cgit v1.2.3 From 852b1beecb6ff9326f7ca4bc0fe69ae860ebdb9e Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Mon, 19 Oct 2020 07:13:55 -0600 Subject: vfio/pci: Clear token on bypass registration failure The eventfd context is used as our irqbypass token, therefore if an eventfd is re-used, our token is the same. The irqbypass code will return an -EBUSY in this case, but we'll still attempt to unregister the producer, where if that duplicate token still exists, results in removing the wrong object. Clear the token of failed producers so that they harmlessly fall out when unregistered. Fixes: 6d7425f109d2 ("vfio: Register/unregister irq_bypass_producer") Reported-by: guomin chen Tested-by: guomin chen Signed-off-by: Alex Williamson --- drivers/vfio/pci/vfio_pci_intrs.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'drivers/vfio') diff --git a/drivers/vfio/pci/vfio_pci_intrs.c b/drivers/vfio/pci/vfio_pci_intrs.c index 1d9fb2592945..869dce5f134d 100644 --- a/drivers/vfio/pci/vfio_pci_intrs.c +++ b/drivers/vfio/pci/vfio_pci_intrs.c @@ -352,11 +352,13 @@ static int vfio_msi_set_vector_signal(struct vfio_pci_device *vdev, vdev->ctx[vector].producer.token = trigger; vdev->ctx[vector].producer.irq = irq; ret = irq_bypass_register_producer(&vdev->ctx[vector].producer); - if (unlikely(ret)) + if (unlikely(ret)) { dev_info(&pdev->dev, "irq bypass producer (token %p) registration fails: %d\n", vdev->ctx[vector].producer.token, ret); + vdev->ctx[vector].producer.token = NULL; + } vdev->ctx[vector].trigger = trigger; return 0; -- cgit v1.2.3 From 2e6cfd496f5b57034cf2aec738799571b5a52124 Mon Sep 17 00:00:00 2001 From: Xiaoyang Xu Date: Fri, 16 Oct 2020 17:35:58 +0800 Subject: vfio iommu type1: Fix memory leak in vfio_iommu_type1_pin_pages pfn is not added to pfn_list when vfio_add_to_pfn_list fails. vfio_unpin_page_external will exit directly without calling vfio_iova_put_vfio_pfn. This will lead to a memory leak. Fixes: a54eb55045ae ("vfio iommu type1: Add support for mediated devices") Signed-off-by: Xiaoyang Xu [aw: simplified logic, add Fixes] Signed-off-by: Alex Williamson --- drivers/vfio/vfio_iommu_type1.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'drivers/vfio') diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index defd44522319..57b068abceb9 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -693,7 +693,8 @@ static int vfio_iommu_type1_pin_pages(void *iommu_data, ret = vfio_add_to_pfn_list(dma, iova, phys_pfn[i]); if (ret) { - vfio_unpin_page_external(dma, iova, do_accounting); + if (put_pfn(phys_pfn[i], dma->prot) && do_accounting) + vfio_lock_acct(dma, -1, true); goto pin_unwind; } -- cgit v1.2.3