VFIO updates for v4.20

- EDID interfaces for vfio devices supporting display extensions
    (Gerd Hoffmann)
 
  - Generically select Type-1 IOMMU model support on ARM/ARM64
    (Geert Uytterhoeven)
 
  - Quirk for VFs reporting INTx pin (Alex Williamson)
 
  - Fix error path memory leak in MSI support (Li Qiang)
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v2.0.14 (GNU/Linux)
 
 iQIcBAABAgAGBQJb2MH7AAoJECObm247sIsiJ/wP+gOlhmUz7eVNhf8ZMC9+17Ev
 mWy41waHW4ATBWRxuaSNetLG0E3Cbt9IMpf6yx3YTuOiD+zCwUUJm934ZVfOUMWb
 yh5UEC2W4+fUt8HjDvYwuGlpyVeEwSTVnprtWjYz9bBsHbCeK7WY4vUeo6WHFrTt
 K+WOsYXC8TEzqj/VQ851Cr0Q23SzdlUFOWhKN0AO/CXshsOzL8An3Ryx95X26oPc
 HlVd1+KDOxpAKmfhA028HeT2GBy6Yu6EjJEGMwo66QtylwTJCPbNxTlg1/noYTTz
 1uV02FR7oAZcmuP6R4iKLr4UBfmJDs2hjIVS6Bcm561KL+tXAUl1FX91ky7snaRq
 0wqMUBJbAmDUEx2smFQI81LoE0OHN4T/u99uEe0cyZ/aNsAcnmbwWRS0rl/1s2eD
 AE9Ht05yMRDp4ENUc8aBKHbXWjId2HjxZwqAzAFd2moVpaD4W/4bZ1ZXssbGTaQk
 /VCXnYl8HJTqAjRwqChW6dc4d2tMaTDIU+FDD85yJVzg4DEZg4xJCAz6CWsGjYmr
 JWHh2iu8fO8FAFhqx5vNz2PzTQUWfi3yfGUNRSH7pFCX07AQ25LdSwQxOQ3eov/X
 YyqFINLscLePrAzw1WAAOk3ghCFBWw/mpIXyzShYNnrGnre+tzbzOSwSFcgMojlc
 nHP6PB+3S4VR24k6ZzUc
 =cat2
 -----END PGP SIGNATURE-----

Merge tag 'vfio-v4.20-rc1.v2' of git://github.com/awilliam/linux-vfio

Pull VFIO updates from Alex Williamson:

 - EDID interfaces for vfio devices supporting display extensions (Gerd
   Hoffmann)

 - Generically select Type-1 IOMMU model support on ARM/ARM64 (Geert
   Uytterhoeven)

 - Quirk for VFs reporting INTx pin (Alex Williamson)

 - Fix error path memory leak in MSI support (Li Qiang)

* tag 'vfio-v4.20-rc1.v2' of git://github.com/awilliam/linux-vfio:
  vfio: add edid support to mbochs sample driver
  vfio: add edid api for display (vgpu) devices.
  drivers/vfio: Allow type-1 IOMMU instantiation with all ARM/ARM64 IOMMUs
  vfio/pci: Mask buggy SR-IOV VF INTx support
  vfio/pci: Fix potential memory leak in vfio_msi_cap_len
This commit is contained in:
Linus Torvalds 2018-10-31 11:01:38 -07:00
commit 0c86e761b9
5 changed files with 205 additions and 24 deletions

View File

@ -21,7 +21,7 @@ config VFIO_VIRQFD
menuconfig VFIO
tristate "VFIO Non-Privileged userspace driver framework"
depends on IOMMU_API
select VFIO_IOMMU_TYPE1 if (X86 || S390 || ARM_SMMU || ARM_SMMU_V3)
select VFIO_IOMMU_TYPE1 if (X86 || S390 || ARM || ARM64)
select ANON_INODES
help
VFIO provides a framework for secure userspace device drivers.

View File

@ -434,10 +434,14 @@ static int vfio_pci_get_irq_count(struct vfio_pci_device *vdev, int irq_type)
{
if (irq_type == VFIO_PCI_INTX_IRQ_INDEX) {
u8 pin;
pci_read_config_byte(vdev->pdev, PCI_INTERRUPT_PIN, &pin);
if (IS_ENABLED(CONFIG_VFIO_PCI_INTX) && !vdev->nointx && pin)
return 1;
if (!IS_ENABLED(CONFIG_VFIO_PCI_INTX) ||
vdev->nointx || vdev->pdev->is_virtfn)
return 0;
pci_read_config_byte(vdev->pdev, PCI_INTERRUPT_PIN, &pin);
return pin ? 1 : 0;
} else if (irq_type == VFIO_PCI_MSI_IRQ_INDEX) {
u8 pos;
u16 flags;

View File

@ -1180,8 +1180,10 @@ static int vfio_msi_cap_len(struct vfio_pci_device *vdev, u8 pos)
return -ENOMEM;
ret = init_pci_cap_msi_perm(vdev->msi_perm, len, flags);
if (ret)
if (ret) {
kfree(vdev->msi_perm);
return ret;
}
return len;
}
@ -1609,6 +1611,15 @@ static int vfio_ecap_init(struct vfio_pci_device *vdev)
return 0;
}
/*
* Nag about hardware bugs, hopefully to have vendors fix them, but at least
* to collect a list of dependencies for the VF INTx pin quirk below.
*/
static const struct pci_device_id known_bogus_vf_intx_pin[] = {
{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x270c) },
{}
};
/*
* For each device we allocate a pci_config_map that indicates the
* capability occupying each dword and thus the struct perm_bits we
@ -1674,6 +1685,24 @@ int vfio_config_init(struct vfio_pci_device *vdev)
if (pdev->is_virtfn) {
*(__le16 *)&vconfig[PCI_VENDOR_ID] = cpu_to_le16(pdev->vendor);
*(__le16 *)&vconfig[PCI_DEVICE_ID] = cpu_to_le16(pdev->device);
/*
* Per SR-IOV spec rev 1.1, 3.4.1.18 the interrupt pin register
* does not apply to VFs and VFs must implement this register
* as read-only with value zero. Userspace is not readily able
* to identify whether a device is a VF and thus that the pin
* definition on the device is bogus should it violate this
* requirement. We already virtualize the pin register for
* other purposes, so we simply need to replace the bogus value
* and consider VFs when we determine INTx IRQ count.
*/
if (vconfig[PCI_INTERRUPT_PIN] &&
!pci_match_id(known_bogus_vf_intx_pin, pdev))
pci_warn(pdev,
"Hardware bug: VF reports bogus INTx pin %d\n",
vconfig[PCI_INTERRUPT_PIN]);
vconfig[PCI_INTERRUPT_PIN] = 0; /* Gratuitous for good VFs */
}
if (!IS_ENABLED(CONFIG_VFIO_PCI_INTX) || vdev->nointx)

View File

@ -303,6 +303,56 @@ struct vfio_region_info_cap_type {
#define VFIO_REGION_SUBTYPE_INTEL_IGD_HOST_CFG (2)
#define VFIO_REGION_SUBTYPE_INTEL_IGD_LPC_CFG (3)
#define VFIO_REGION_TYPE_GFX (1)
#define VFIO_REGION_SUBTYPE_GFX_EDID (1)
/**
* struct vfio_region_gfx_edid - EDID region layout.
*
* Set display link state and EDID blob.
*
* The EDID blob has monitor information such as brand, name, serial
* number, physical size, supported video modes and more.
*
* This special region allows userspace (typically qemu) set a virtual
* EDID for the virtual monitor, which allows a flexible display
* configuration.
*
* For the edid blob spec look here:
* https://en.wikipedia.org/wiki/Extended_Display_Identification_Data
*
* On linux systems you can find the EDID blob in sysfs:
* /sys/class/drm/${card}/${connector}/edid
*
* You can use the edid-decode ulility (comes with xorg-x11-utils) to
* decode the EDID blob.
*
* @edid_offset: location of the edid blob, relative to the
* start of the region (readonly).
* @edid_max_size: max size of the edid blob (readonly).
* @edid_size: actual edid size (read/write).
* @link_state: display link state (read/write).
* VFIO_DEVICE_GFX_LINK_STATE_UP: Monitor is turned on.
* VFIO_DEVICE_GFX_LINK_STATE_DOWN: Monitor is turned off.
* @max_xres: max display width (0 == no limitation, readonly).
* @max_yres: max display height (0 == no limitation, readonly).
*
* EDID update protocol:
* (1) set link-state to down.
* (2) update edid blob and size.
* (3) set link-state to up.
*/
struct vfio_region_gfx_edid {
__u32 edid_offset;
__u32 edid_max_size;
__u32 edid_size;
__u32 max_xres;
__u32 max_yres;
__u32 link_state;
#define VFIO_DEVICE_GFX_LINK_STATE_UP 1
#define VFIO_DEVICE_GFX_LINK_STATE_DOWN 2
};
/*
* The MSIX mappable capability informs that MSIX data of a BAR can be mmapped
* which allows direct access to non-MSIX registers which happened to be within

View File

@ -71,11 +71,19 @@
#define MBOCHS_NAME "mbochs"
#define MBOCHS_CLASS_NAME "mbochs"
#define MBOCHS_EDID_REGION_INDEX VFIO_PCI_NUM_REGIONS
#define MBOCHS_NUM_REGIONS (MBOCHS_EDID_REGION_INDEX+1)
#define MBOCHS_CONFIG_SPACE_SIZE 0xff
#define MBOCHS_MMIO_BAR_OFFSET PAGE_SIZE
#define MBOCHS_MMIO_BAR_SIZE PAGE_SIZE
#define MBOCHS_MEMORY_BAR_OFFSET (MBOCHS_MMIO_BAR_OFFSET + \
#define MBOCHS_EDID_OFFSET (MBOCHS_MMIO_BAR_OFFSET + \
MBOCHS_MMIO_BAR_SIZE)
#define MBOCHS_EDID_SIZE PAGE_SIZE
#define MBOCHS_MEMORY_BAR_OFFSET (MBOCHS_EDID_OFFSET + \
MBOCHS_EDID_SIZE)
#define MBOCHS_EDID_BLOB_OFFSET (MBOCHS_EDID_SIZE/2)
#define STORE_LE16(addr, val) (*(u16 *)addr = val)
#define STORE_LE32(addr, val) (*(u32 *)addr = val)
@ -95,16 +103,24 @@ MODULE_PARM_DESC(mem, "megabytes available to " MBOCHS_NAME " devices");
static const struct mbochs_type {
const char *name;
u32 mbytes;
u32 max_x;
u32 max_y;
} mbochs_types[] = {
{
.name = MBOCHS_CLASS_NAME "-" MBOCHS_TYPE_1,
.mbytes = 4,
.max_x = 800,
.max_y = 600,
}, {
.name = MBOCHS_CLASS_NAME "-" MBOCHS_TYPE_2,
.mbytes = 16,
.max_x = 1920,
.max_y = 1440,
}, {
.name = MBOCHS_CLASS_NAME "-" MBOCHS_TYPE_3,
.mbytes = 64,
.max_x = 0,
.max_y = 0,
},
};
@ -115,6 +131,11 @@ static struct cdev mbochs_cdev;
static struct device mbochs_dev;
static int mbochs_used_mbytes;
struct vfio_region_info_ext {
struct vfio_region_info base;
struct vfio_region_info_cap_type type;
};
struct mbochs_mode {
u32 drm_format;
u32 bytepp;
@ -144,13 +165,14 @@ struct mdev_state {
u32 memory_bar_mask;
struct mutex ops_lock;
struct mdev_device *mdev;
struct vfio_device_info dev_info;
const struct mbochs_type *type;
u16 vbe[VBE_DISPI_INDEX_COUNT];
u64 memsize;
struct page **pages;
pgoff_t pagecount;
struct vfio_region_gfx_edid edid_regs;
u8 edid_blob[0x400];
struct list_head dmabufs;
u32 active_id;
@ -342,10 +364,20 @@ static void handle_mmio_read(struct mdev_state *mdev_state, u16 offset,
char *buf, u32 count)
{
struct device *dev = mdev_dev(mdev_state->mdev);
struct vfio_region_gfx_edid *edid;
u16 reg16 = 0;
int index;
switch (offset) {
case 0x000 ... 0x3ff: /* edid block */
edid = &mdev_state->edid_regs;
if (edid->link_state != VFIO_DEVICE_GFX_LINK_STATE_UP ||
offset >= edid->edid_size) {
memset(buf, 0, count);
break;
}
memcpy(buf, mdev_state->edid_blob + offset, count);
break;
case 0x500 ... 0x515: /* bochs dispi interface */
if (count != 2)
goto unhandled;
@ -365,6 +397,44 @@ unhandled:
}
}
static void handle_edid_regs(struct mdev_state *mdev_state, u16 offset,
char *buf, u32 count, bool is_write)
{
char *regs = (void *)&mdev_state->edid_regs;
if (offset + count > sizeof(mdev_state->edid_regs))
return;
if (count != 4)
return;
if (offset % 4)
return;
if (is_write) {
switch (offset) {
case offsetof(struct vfio_region_gfx_edid, link_state):
case offsetof(struct vfio_region_gfx_edid, edid_size):
memcpy(regs + offset, buf, count);
break;
default:
/* read-only regs */
break;
}
} else {
memcpy(buf, regs + offset, count);
}
}
static void handle_edid_blob(struct mdev_state *mdev_state, u16 offset,
char *buf, u32 count, bool is_write)
{
if (offset + count > mdev_state->edid_regs.edid_max_size)
return;
if (is_write)
memcpy(mdev_state->edid_blob + offset, buf, count);
else
memcpy(buf, mdev_state->edid_blob + offset, count);
}
static ssize_t mdev_access(struct mdev_device *mdev, char *buf, size_t count,
loff_t pos, bool is_write)
{
@ -384,13 +454,25 @@ static ssize_t mdev_access(struct mdev_device *mdev, char *buf, size_t count,
memcpy(buf, (mdev_state->vconfig + pos), count);
} else if (pos >= MBOCHS_MMIO_BAR_OFFSET &&
pos + count <= MBOCHS_MEMORY_BAR_OFFSET) {
pos + count <= (MBOCHS_MMIO_BAR_OFFSET +
MBOCHS_MMIO_BAR_SIZE)) {
pos -= MBOCHS_MMIO_BAR_OFFSET;
if (is_write)
handle_mmio_write(mdev_state, pos, buf, count);
else
handle_mmio_read(mdev_state, pos, buf, count);
} else if (pos >= MBOCHS_EDID_OFFSET &&
pos + count <= (MBOCHS_EDID_OFFSET +
MBOCHS_EDID_SIZE)) {
pos -= MBOCHS_EDID_OFFSET;
if (pos < MBOCHS_EDID_BLOB_OFFSET) {
handle_edid_regs(mdev_state, pos, buf, count, is_write);
} else {
pos -= MBOCHS_EDID_BLOB_OFFSET;
handle_edid_blob(mdev_state, pos, buf, count, is_write);
}
} else if (pos >= MBOCHS_MEMORY_BAR_OFFSET &&
pos + count <=
MBOCHS_MEMORY_BAR_OFFSET + mdev_state->memsize) {
@ -471,6 +553,10 @@ static int mbochs_create(struct kobject *kobj, struct mdev_device *mdev)
mdev_state->next_id = 1;
mdev_state->type = type;
mdev_state->edid_regs.max_xres = type->max_x;
mdev_state->edid_regs.max_yres = type->max_y;
mdev_state->edid_regs.edid_offset = MBOCHS_EDID_BLOB_OFFSET;
mdev_state->edid_regs.edid_max_size = sizeof(mdev_state->edid_blob);
mbochs_create_config_space(mdev_state);
mbochs_reset(mdev);
@ -932,16 +1018,16 @@ static int mbochs_dmabuf_export(struct mbochs_dmabuf *dmabuf)
}
static int mbochs_get_region_info(struct mdev_device *mdev,
struct vfio_region_info *region_info,
u16 *cap_type_id, void **cap_type)
struct vfio_region_info_ext *ext)
{
struct vfio_region_info *region_info = &ext->base;
struct mdev_state *mdev_state;
mdev_state = mdev_get_drvdata(mdev);
if (!mdev_state)
return -EINVAL;
if (region_info->index >= VFIO_PCI_NUM_REGIONS)
if (region_info->index >= MBOCHS_NUM_REGIONS)
return -EINVAL;
switch (region_info->index) {
@ -964,6 +1050,20 @@ static int mbochs_get_region_info(struct mdev_device *mdev,
region_info->flags = (VFIO_REGION_INFO_FLAG_READ |
VFIO_REGION_INFO_FLAG_WRITE);
break;
case MBOCHS_EDID_REGION_INDEX:
ext->base.argsz = sizeof(*ext);
ext->base.offset = MBOCHS_EDID_OFFSET;
ext->base.size = MBOCHS_EDID_SIZE;
ext->base.flags = (VFIO_REGION_INFO_FLAG_READ |
VFIO_REGION_INFO_FLAG_WRITE |
VFIO_REGION_INFO_FLAG_CAPS);
ext->base.cap_offset = offsetof(typeof(*ext), type);
ext->type.header.id = VFIO_REGION_INFO_CAP_TYPE;
ext->type.header.version = 1;
ext->type.header.next = 0;
ext->type.type = VFIO_REGION_TYPE_GFX;
ext->type.subtype = VFIO_REGION_SUBTYPE_GFX_EDID;
break;
default:
region_info->size = 0;
region_info->offset = 0;
@ -984,7 +1084,7 @@ static int mbochs_get_device_info(struct mdev_device *mdev,
struct vfio_device_info *dev_info)
{
dev_info->flags = VFIO_DEVICE_FLAGS_PCI;
dev_info->num_regions = VFIO_PCI_NUM_REGIONS;
dev_info->num_regions = MBOCHS_NUM_REGIONS;
dev_info->num_irqs = VFIO_PCI_NUM_IRQS;
return 0;
}
@ -1084,7 +1184,7 @@ static long mbochs_ioctl(struct mdev_device *mdev, unsigned int cmd,
unsigned long arg)
{
int ret = 0;
unsigned long minsz;
unsigned long minsz, outsz;
struct mdev_state *mdev_state;
mdev_state = mdev_get_drvdata(mdev);
@ -1106,8 +1206,6 @@ static long mbochs_ioctl(struct mdev_device *mdev, unsigned int cmd,
if (ret)
return ret;
memcpy(&mdev_state->dev_info, &info, sizeof(info));
if (copy_to_user((void __user *)arg, &info, minsz))
return -EFAULT;
@ -1115,24 +1213,24 @@ static long mbochs_ioctl(struct mdev_device *mdev, unsigned int cmd,
}
case VFIO_DEVICE_GET_REGION_INFO:
{
struct vfio_region_info info;
u16 cap_type_id = 0;
void *cap_type = NULL;
struct vfio_region_info_ext info;
minsz = offsetofend(struct vfio_region_info, offset);
minsz = offsetofend(typeof(info), base.offset);
if (copy_from_user(&info, (void __user *)arg, minsz))
return -EFAULT;
if (info.argsz < minsz)
outsz = info.base.argsz;
if (outsz < minsz)
return -EINVAL;
if (outsz > sizeof(info))
return -EINVAL;
ret = mbochs_get_region_info(mdev, &info, &cap_type_id,
&cap_type);
ret = mbochs_get_region_info(mdev, &info);
if (ret)
return ret;
if (copy_to_user((void __user *)arg, &info, minsz))
if (copy_to_user((void __user *)arg, &info, outsz))
return -EFAULT;
return 0;
@ -1148,7 +1246,7 @@ static long mbochs_ioctl(struct mdev_device *mdev, unsigned int cmd,
return -EFAULT;
if ((info.argsz < minsz) ||
(info.index >= mdev_state->dev_info.num_irqs))
(info.index >= VFIO_PCI_NUM_IRQS))
return -EINVAL;
ret = mbochs_get_irq_info(mdev, &info);