From c84982adb23bcf3b99b79ca33527cd2625fbe279 Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Mon, 22 Feb 2016 16:02:32 -0700 Subject: vfio: Define capability chains We have a few cases where we need to extend the data returned from the INFO ioctls in VFIO. For instance we already have devices exposed through vfio-pci where VFIO_DEVICE_GET_REGION_INFO reports the region as mmap-capable, but really only supports sparse mmaps, avoiding the MSI-X table. If we wanted to provide in-kernel emulation or extended functionality for devices, we'd also want the ability to tell the user not to mmap various regions, rather than forcing them to figure it out on their own. Another example is VFIO_IOMMU_GET_INFO. We'd really like to expose the actual IOVA capabilities of the IOMMU rather than letting the user assume the address space they have available to them. We could add IOVA base and size fields to struct vfio_iommu_type1_info, but what if we have multiple IOVA ranges. For instance x86 uses a range of addresses at 0xfee00000 for MSI vectors. These typically are not available for standard DMA IOVA mappings and splits our available IOVA space into two ranges. POWER systems have both an IOVA window below 4G as well as dynamic data window which they can use to remap all of guest memory. Representing variable sized arrays within a fixed structure makes it very difficult to parse, we'd therefore like to put this data beyond fixed fields within the data structures. One way to do this is to emulate capabilities in PCI configuration space. A new flag indciates whether capabilties are supported and a new fixed field reports the offset of the first entry. Users can then walk the chain to find capabilities, adding capabilities does not require additional fields in the fixed structure, and parsing variable sized data becomes trivial. This patch outlines the theory and base header structure, which should be shared by all future users. Signed-off-by: Alex Williamson --- include/uapi/linux/vfio.h | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index 7d7a4c6f2090..d508adf17610 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -59,6 +59,33 @@ #define VFIO_TYPE (';') #define VFIO_BASE 100 +/* + * For extension of INFO ioctls, VFIO makes use of a capability chain + * designed after PCI/e capabilities. A flag bit indicates whether + * this capability chain is supported and a field defined in the fixed + * structure defines the offset of the first capability in the chain. + * This field is only valid when the corresponding bit in the flags + * bitmap is set. This offset field is relative to the start of the + * INFO buffer, as is the next field within each capability header. + * The id within the header is a shared address space per INFO ioctl, + * while the version field is specific to the capability id. The + * contents following the header are specific to the capability id. + */ +struct vfio_info_cap_header { + __u16 id; /* Identifies capability */ + __u16 version; /* Version specific to the capability ID */ + __u32 next; /* Offset of next capability */ +}; + +/* + * Callers of INFO ioctls passing insufficiently sized buffers will see + * the capability chain flag bit set, a zero value for the first capability + * offset (if available within the provided argsz), and argsz will be + * updated to report the necessary buffer size. For compatibility, the + * INFO ioctl will not report error in this case, but the capability chain + * will not be available. + */ + /* -------- IOCTLs for VFIO file descriptor (/dev/vfio/vfio) -------- */ /** -- cgit v1.2.3 From ff63eb638d63b95e489f976428f1df01391e15e4 Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Mon, 22 Feb 2016 16:02:35 -0700 Subject: vfio: Define sparse mmap capability for regions We can't always support mmap across an entire device region, for example we deny mmaps covering the MSI-X table of PCI devices, but we don't really have a way to report it. We expect the user to implicitly know this restriction. We also can't split the region because vfio-pci defines an API with fixed region index to BAR number mapping. We therefore define a new capability which lists areas within the region that may be mmap'd. In addition to the MSI-X case, this potentially enables in-kernel emulation and extensions to devices. Signed-off-by: Alex Williamson --- include/uapi/linux/vfio.h | 26 +++++++++++++++++++++++++- 1 file changed, 25 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index d508adf17610..fde7b1e60948 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -221,13 +221,37 @@ struct vfio_region_info { #define VFIO_REGION_INFO_FLAG_READ (1 << 0) /* Region supports read */ #define VFIO_REGION_INFO_FLAG_WRITE (1 << 1) /* Region supports write */ #define VFIO_REGION_INFO_FLAG_MMAP (1 << 2) /* Region supports mmap */ +#define VFIO_REGION_INFO_FLAG_CAPS (1 << 3) /* Info supports caps */ __u32 index; /* Region index */ - __u32 resv; /* Reserved for alignment */ + __u32 cap_offset; /* Offset within info struct of first cap */ __u64 size; /* Region size (bytes) */ __u64 offset; /* Region offset from start of device fd */ }; #define VFIO_DEVICE_GET_REGION_INFO _IO(VFIO_TYPE, VFIO_BASE + 8) +/* + * The sparse mmap capability allows finer granularity of specifying areas + * within a region with mmap support. When specified, the user should only + * mmap the offset ranges specified by the areas array. mmaps outside of the + * areas specified may fail (such as the range covering a PCI MSI-X table) or + * may result in improper device behavior. + * + * The structures below define version 1 of this capability. + */ +#define VFIO_REGION_INFO_CAP_SPARSE_MMAP 1 + +struct vfio_region_sparse_mmap_area { + __u64 offset; /* Offset of mmap'able area within region */ + __u64 size; /* Size of mmap'able area */ +}; + +struct vfio_region_info_cap_sparse_mmap { + struct vfio_info_cap_header header; + __u32 nr_areas; + __u32 reserved; + struct vfio_region_sparse_mmap_area areas[]; +}; + /** * VFIO_DEVICE_GET_IRQ_INFO - _IOWR(VFIO_TYPE, VFIO_BASE + 9, * struct vfio_irq_info) -- cgit v1.2.3 From c7bb4cb40f89224dc55755178343728e30dd583a Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Mon, 22 Feb 2016 16:02:38 -0700 Subject: vfio: Define device specific region type capability To this point vfio has only provided an interface to the user that allows them to determine the number of regions and specifics about each region. What the region represents is left to the vfio bus driver. vfio-pci chooses to use fixed indexes for fixed resources, index 0 is BAR0, 1 is BAR1,... 7 is config space, etc. This works pretty well since all PCI devices have these regions, even if they don't necessarily populate all of them. Then we start to add things like VGA, which only certain device even support. We added this the same way, but now we've wasted a region index, and due to our offset implementation the corresponding address space, for all devices. Rather than continuing that process, let's try to make regions self describing by including a capability that defines their type. For vfio-pci we'll make the current VFIO_PCI_NUM_REGIONS fixed, defining the end of the static indexes and the beginning of self describing regions. Signed-off-by: Alex Williamson --- include/uapi/linux/vfio.h | 31 ++++++++++++++++++++++++++++++- 1 file changed, 30 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index fde7b1e60948..1c37a0e500c6 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -252,6 +252,34 @@ struct vfio_region_info_cap_sparse_mmap { struct vfio_region_sparse_mmap_area areas[]; }; +/* + * The device specific type capability allows regions unique to a specific + * device or class of devices to be exposed. This helps solve the problem for + * vfio bus drivers of defining which region indexes correspond to which region + * on the device, without needing to resort to static indexes, as done by + * vfio-pci. For instance, if we were to go back in time, we might remove + * VFIO_PCI_VGA_REGION_INDEX and let vfio-pci simply define that all indexes + * greater than or equal to VFIO_PCI_NUM_REGIONS are device specific and we'd + * make a "VGA" device specific type to describe the VGA access space. This + * means that non-VGA devices wouldn't need to waste this index, and thus the + * address space associated with it due to implementation of device file + * descriptor offsets in vfio-pci. + * + * The current implementation is now part of the user ABI, so we can't use this + * for VGA, but there are other upcoming use cases, such as opregions for Intel + * IGD devices and framebuffers for vGPU devices. We missed VGA, but we'll + * use this for future additions. + * + * The structure below defines version 1 of this capability. + */ +#define VFIO_REGION_INFO_CAP_TYPE 2 + +struct vfio_region_info_cap_type { + struct vfio_info_cap_header header; + __u32 type; /* global per bus driver */ + __u32 subtype; /* type specific */ +}; + /** * VFIO_DEVICE_GET_IRQ_INFO - _IOWR(VFIO_TYPE, VFIO_BASE + 9, * struct vfio_irq_info) @@ -387,7 +415,8 @@ enum { * between described ranges are unimplemented. */ VFIO_PCI_VGA_REGION_INDEX, - VFIO_PCI_NUM_REGIONS + VFIO_PCI_NUM_REGIONS = 9 /* Fixed user ABI, region indexes >=9 use */ + /* device specific cap to define content. */ }; enum { -- cgit v1.2.3 From 5846ff54e87d8bab4f1e330af0b5407747a0a57e Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Mon, 22 Feb 2016 16:02:43 -0700 Subject: vfio/pci: Intel IGD OpRegion support This is the first consumer of vfio device specific resource support, providing read-only access to the OpRegion for Intel graphics devices. Signed-off-by: Alex Williamson --- include/uapi/linux/vfio.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index 1c37a0e500c6..e622982dbc53 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -280,6 +280,11 @@ struct vfio_region_info_cap_type { __u32 subtype; /* type specific */ }; +#define VFIO_REGION_TYPE_PCI_VENDOR_TYPE (1 << 31) +#define VFIO_REGION_TYPE_PCI_VENDOR_MASK (0xffff) + +#define VFIO_REGION_SUBTYPE_INTEL_IGD_OPREGION (1) + /** * VFIO_DEVICE_GET_IRQ_INFO - _IOWR(VFIO_TYPE, VFIO_BASE + 9, * struct vfio_irq_info) -- cgit v1.2.3 From f572a960a15e8bb56599f6d2358a9c18f0808e91 Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Mon, 22 Feb 2016 16:02:45 -0700 Subject: vfio/pci: Intel IGD host and LCP bridge config space access Provide read-only access to PCI config space of the PCI host bridge and LPC bridge through device specific regions. This may be used to configure a VM with matching register contents to satisfy driver requirements. Providing this through the vfio file descriptor removes an additional userspace requirement for access through pci-sysfs and removes the CAP_SYS_ADMIN requirement that doesn't appear to apply to the specific devices we're accessing. Signed-off-by: Alex Williamson --- include/uapi/linux/vfio.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index e622982dbc53..255a2113f53c 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -283,7 +283,10 @@ struct vfio_region_info_cap_type { #define VFIO_REGION_TYPE_PCI_VENDOR_TYPE (1 << 31) #define VFIO_REGION_TYPE_PCI_VENDOR_MASK (0xffff) +/* 8086 Vendor sub-types */ #define VFIO_REGION_SUBTYPE_INTEL_IGD_OPREGION (1) +#define VFIO_REGION_SUBTYPE_INTEL_IGD_HOST_CFG (2) +#define VFIO_REGION_SUBTYPE_INTEL_IGD_LPC_CFG (3) /** * VFIO_DEVICE_GET_IRQ_INFO - _IOWR(VFIO_TYPE, VFIO_BASE + 9, -- cgit v1.2.3