2015-09-23 21:04:44 +02:00
|
|
|
/*
|
|
|
|
* vfio based device assignment support - PCI devices
|
|
|
|
*
|
|
|
|
* Copyright Red Hat, Inc. 2012-2015
|
|
|
|
*
|
|
|
|
* Authors:
|
|
|
|
* Alex Williamson <alex.williamson@redhat.com>
|
|
|
|
*
|
|
|
|
* This work is licensed under the terms of the GNU GPL, version 2. See
|
|
|
|
* the COPYING file in the top-level directory.
|
|
|
|
*/
|
|
|
|
#ifndef HW_VFIO_VFIO_PCI_H
|
|
|
|
#define HW_VFIO_VFIO_PCI_H
|
|
|
|
|
|
|
|
#include "qemu-common.h"
|
|
|
|
#include "exec/memory.h"
|
|
|
|
#include "hw/pci/pci.h"
|
|
|
|
#include "hw/vfio/vfio-common.h"
|
|
|
|
#include "qemu/event_notifier.h"
|
|
|
|
#include "qemu/queue.h"
|
|
|
|
#include "qemu/timer.h"
|
|
|
|
|
2015-09-23 21:04:49 +02:00
|
|
|
#define PCI_ANY_ID (~0)
|
|
|
|
|
2015-09-23 21:04:44 +02:00
|
|
|
struct VFIOPCIDevice;
|
|
|
|
|
2015-09-23 21:04:46 +02:00
|
|
|
typedef struct VFIOQuirk {
|
|
|
|
QLIST_ENTRY(VFIOQuirk) next;
|
|
|
|
void *data;
|
|
|
|
int nr_mem;
|
|
|
|
MemoryRegion *mem;
|
2015-09-23 21:04:44 +02:00
|
|
|
} VFIOQuirk;
|
|
|
|
|
|
|
|
typedef struct VFIOBAR {
|
|
|
|
VFIORegion region;
|
|
|
|
bool ioport;
|
|
|
|
bool mem64;
|
|
|
|
QLIST_HEAD(, VFIOQuirk) quirks;
|
|
|
|
} VFIOBAR;
|
|
|
|
|
|
|
|
typedef struct VFIOVGARegion {
|
|
|
|
MemoryRegion mem;
|
|
|
|
off_t offset;
|
|
|
|
int nr;
|
|
|
|
QLIST_HEAD(, VFIOQuirk) quirks;
|
|
|
|
} VFIOVGARegion;
|
|
|
|
|
|
|
|
typedef struct VFIOVGA {
|
|
|
|
off_t fd_offset;
|
|
|
|
int fd;
|
|
|
|
VFIOVGARegion region[QEMU_PCI_VGA_NUM_REGIONS];
|
|
|
|
} VFIOVGA;
|
|
|
|
|
|
|
|
typedef struct VFIOINTx {
|
|
|
|
bool pending; /* interrupt pending */
|
|
|
|
bool kvm_accel; /* set when QEMU bypass through KVM enabled */
|
|
|
|
uint8_t pin; /* which pin to pull for qemu_set_irq */
|
|
|
|
EventNotifier interrupt; /* eventfd triggered on interrupt */
|
|
|
|
EventNotifier unmask; /* eventfd for unmask on QEMU bypass */
|
|
|
|
PCIINTxRoute route; /* routing info for QEMU bypass */
|
|
|
|
uint32_t mmap_timeout; /* delay to re-enable mmaps after interrupt */
|
|
|
|
QEMUTimer *mmap_timer; /* enable mmaps after periods w/o interrupts */
|
|
|
|
} VFIOINTx;
|
|
|
|
|
|
|
|
typedef struct VFIOMSIVector {
|
|
|
|
/*
|
|
|
|
* Two interrupt paths are configured per vector. The first, is only used
|
|
|
|
* for interrupts injected via QEMU. This is typically the non-accel path,
|
|
|
|
* but may also be used when we want QEMU to handle masking and pending
|
|
|
|
* bits. The KVM path bypasses QEMU and is therefore higher performance,
|
|
|
|
* but requires masking at the device. virq is used to track the MSI route
|
|
|
|
* through KVM, thus kvm_interrupt is only available when virq is set to a
|
|
|
|
* valid (>= 0) value.
|
|
|
|
*/
|
|
|
|
EventNotifier interrupt;
|
|
|
|
EventNotifier kvm_interrupt;
|
|
|
|
struct VFIOPCIDevice *vdev; /* back pointer to device */
|
|
|
|
int virq;
|
|
|
|
bool use;
|
|
|
|
} VFIOMSIVector;
|
|
|
|
|
|
|
|
enum {
|
|
|
|
VFIO_INT_NONE = 0,
|
|
|
|
VFIO_INT_INTx = 1,
|
|
|
|
VFIO_INT_MSI = 2,
|
|
|
|
VFIO_INT_MSIX = 3,
|
|
|
|
};
|
|
|
|
|
|
|
|
/* Cache of MSI-X setup plus extra mmap and memory region for split BAR map */
|
|
|
|
typedef struct VFIOMSIXInfo {
|
|
|
|
uint8_t table_bar;
|
|
|
|
uint8_t pba_bar;
|
|
|
|
uint16_t entries;
|
|
|
|
uint32_t table_offset;
|
|
|
|
uint32_t pba_offset;
|
2016-01-19 19:33:42 +01:00
|
|
|
unsigned long *pending;
|
2015-09-23 21:04:44 +02:00
|
|
|
} VFIOMSIXInfo;
|
|
|
|
|
|
|
|
typedef struct VFIOPCIDevice {
|
|
|
|
PCIDevice pdev;
|
|
|
|
VFIODevice vbasedev;
|
|
|
|
VFIOINTx intx;
|
|
|
|
unsigned int config_size;
|
|
|
|
uint8_t *emulated_config_bits; /* QEMU emulated bits, little-endian */
|
|
|
|
off_t config_offset; /* Offset of config space region within device fd */
|
|
|
|
unsigned int rom_size;
|
|
|
|
off_t rom_offset; /* Offset of ROM region within device fd */
|
|
|
|
void *rom;
|
|
|
|
int msi_cap_size;
|
|
|
|
VFIOMSIVector *msi_vectors;
|
|
|
|
VFIOMSIXInfo *msix;
|
|
|
|
int nr_vectors; /* Number of MSI/MSIX vectors currently in use */
|
|
|
|
int interrupt; /* Current interrupt type */
|
|
|
|
VFIOBAR bars[PCI_NUM_REGIONS - 1]; /* No ROM */
|
2016-03-10 17:39:08 +01:00
|
|
|
VFIOVGA *vga; /* 0xa0000, 0x3b0, 0x3c0 */
|
vfio/pci: Intel graphics legacy mode assignment
Enable quirks to support SandyBridge and newer IGD devices as primary
VM graphics. This requires new vfio-pci device specific regions added
in kernel v4.6 to expose the IGD OpRegion, the shadow ROM, and config
space access to the PCI host bridge and LPC/ISA bridge. VM firmware
support, SeaBIOS only so far, is also required for reserving memory
regions for IGD specific use. In order to enable this mode, IGD must
be assigned to the VM at PCI bus address 00:02.0, it must have a ROM,
it must be able to enable VGA, it must have or be able to create on
its own an LPC/ISA bridge of the proper type at PCI bus address
00:1f.0 (sorry, not compatible with Q35 yet), and it must have the
above noted vfio-pci kernel features and BIOS. The intention is that
to enable this mode, a user simply needs to assign 00:02.0 from the
host to 00:02.0 in the VM:
-device vfio-pci,host=0000:00:02.0,bus=pci.0,addr=02.0
and everything either happens automatically or it doesn't. In the
case that it doesn't, we leave error reports, but assume the device
will operate in universal passthrough mode (UPT), which doesn't
require any of this, but has a much more narrow window of supported
devices, supported use cases, and supported guest drivers.
When using IGD in this mode, the VM firmware is required to reserve
some VM RAM for the OpRegion (on the order or several 4k pages) and
stolen memory for the GTT (up to 8MB for the latest GPUs). An
additional option, x-igd-gms allows the user to specify some amount
of additional memory (value is number of 32MB chunks up to 512MB) that
is pre-allocated for graphics use. TBH, I don't know of anything that
requires this or makes use of this memory, which is why we don't
allocate any by default, but the specification suggests this is not
actually a valid combination, so the option exists as a workaround.
Please report if it's actually necessary in some environment.
See code comments for further discussion about the actual operation
of the quirks necessary to assign these devices.
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Reviewed-by: Gerd Hoffmann <kraxel@redhat.com>
Tested-by: Gerd Hoffmann <kraxel@redhat.com>
2016-05-26 17:43:21 +02:00
|
|
|
void *igd_opregion;
|
2015-09-23 21:04:44 +02:00
|
|
|
PCIHostDeviceAddress host;
|
|
|
|
EventNotifier err_notifier;
|
|
|
|
EventNotifier req_notifier;
|
|
|
|
int (*resetfn)(struct VFIOPCIDevice *);
|
2015-09-23 21:04:49 +02:00
|
|
|
uint32_t vendor_id;
|
|
|
|
uint32_t device_id;
|
|
|
|
uint32_t sub_vendor_id;
|
|
|
|
uint32_t sub_device_id;
|
2015-09-23 21:04:44 +02:00
|
|
|
uint32_t features;
|
|
|
|
#define VFIO_FEATURE_ENABLE_VGA_BIT 0
|
|
|
|
#define VFIO_FEATURE_ENABLE_VGA (1 << VFIO_FEATURE_ENABLE_VGA_BIT)
|
|
|
|
#define VFIO_FEATURE_ENABLE_REQ_BIT 1
|
|
|
|
#define VFIO_FEATURE_ENABLE_REQ (1 << VFIO_FEATURE_ENABLE_REQ_BIT)
|
2016-05-26 17:43:22 +02:00
|
|
|
#define VFIO_FEATURE_ENABLE_IGD_OPREGION_BIT 2
|
|
|
|
#define VFIO_FEATURE_ENABLE_IGD_OPREGION \
|
|
|
|
(1 << VFIO_FEATURE_ENABLE_IGD_OPREGION_BIT)
|
2015-09-23 21:04:44 +02:00
|
|
|
int32_t bootindex;
|
vfio/pci: Intel graphics legacy mode assignment
Enable quirks to support SandyBridge and newer IGD devices as primary
VM graphics. This requires new vfio-pci device specific regions added
in kernel v4.6 to expose the IGD OpRegion, the shadow ROM, and config
space access to the PCI host bridge and LPC/ISA bridge. VM firmware
support, SeaBIOS only so far, is also required for reserving memory
regions for IGD specific use. In order to enable this mode, IGD must
be assigned to the VM at PCI bus address 00:02.0, it must have a ROM,
it must be able to enable VGA, it must have or be able to create on
its own an LPC/ISA bridge of the proper type at PCI bus address
00:1f.0 (sorry, not compatible with Q35 yet), and it must have the
above noted vfio-pci kernel features and BIOS. The intention is that
to enable this mode, a user simply needs to assign 00:02.0 from the
host to 00:02.0 in the VM:
-device vfio-pci,host=0000:00:02.0,bus=pci.0,addr=02.0
and everything either happens automatically or it doesn't. In the
case that it doesn't, we leave error reports, but assume the device
will operate in universal passthrough mode (UPT), which doesn't
require any of this, but has a much more narrow window of supported
devices, supported use cases, and supported guest drivers.
When using IGD in this mode, the VM firmware is required to reserve
some VM RAM for the OpRegion (on the order or several 4k pages) and
stolen memory for the GTT (up to 8MB for the latest GPUs). An
additional option, x-igd-gms allows the user to specify some amount
of additional memory (value is number of 32MB chunks up to 512MB) that
is pre-allocated for graphics use. TBH, I don't know of anything that
requires this or makes use of this memory, which is why we don't
allocate any by default, but the specification suggests this is not
actually a valid combination, so the option exists as a workaround.
Please report if it's actually necessary in some environment.
See code comments for further discussion about the actual operation
of the quirks necessary to assign these devices.
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Reviewed-by: Gerd Hoffmann <kraxel@redhat.com>
Tested-by: Gerd Hoffmann <kraxel@redhat.com>
2016-05-26 17:43:21 +02:00
|
|
|
uint32_t igd_gms;
|
2015-09-23 21:04:44 +02:00
|
|
|
uint8_t pm_cap;
|
2017-08-30 00:05:47 +02:00
|
|
|
uint8_t nv_gpudirect_clique;
|
2015-09-23 21:04:44 +02:00
|
|
|
bool pci_aer;
|
|
|
|
bool req_enabled;
|
|
|
|
bool has_flr;
|
|
|
|
bool has_pm_reset;
|
|
|
|
bool rom_read_failed;
|
|
|
|
bool no_kvm_intx;
|
|
|
|
bool no_kvm_msi;
|
|
|
|
bool no_kvm_msix;
|
|
|
|
} VFIOPCIDevice;
|
|
|
|
|
2015-09-23 21:04:45 +02:00
|
|
|
uint32_t vfio_pci_read_config(PCIDevice *pdev, uint32_t addr, int len);
|
|
|
|
void vfio_pci_write_config(PCIDevice *pdev,
|
|
|
|
uint32_t addr, uint32_t val, int len);
|
|
|
|
|
|
|
|
uint64_t vfio_vga_read(void *opaque, hwaddr addr, unsigned size);
|
|
|
|
void vfio_vga_write(void *opaque, hwaddr addr, uint64_t data, unsigned size);
|
|
|
|
|
|
|
|
bool vfio_blacklist_opt_rom(VFIOPCIDevice *vdev);
|
|
|
|
void vfio_vga_quirk_setup(VFIOPCIDevice *vdev);
|
2016-03-10 17:39:08 +01:00
|
|
|
void vfio_vga_quirk_exit(VFIOPCIDevice *vdev);
|
|
|
|
void vfio_vga_quirk_finalize(VFIOPCIDevice *vdev);
|
2015-09-23 21:04:45 +02:00
|
|
|
void vfio_bar_quirk_setup(VFIOPCIDevice *vdev, int nr);
|
2016-03-10 17:39:08 +01:00
|
|
|
void vfio_bar_quirk_exit(VFIOPCIDevice *vdev, int nr);
|
|
|
|
void vfio_bar_quirk_finalize(VFIOPCIDevice *vdev, int nr);
|
2015-09-23 21:04:49 +02:00
|
|
|
void vfio_setup_resetfn_quirk(VFIOPCIDevice *vdev);
|
2017-08-30 00:05:39 +02:00
|
|
|
int vfio_add_virt_caps(VFIOPCIDevice *vdev, Error **errp);
|
2015-09-23 21:04:45 +02:00
|
|
|
|
2017-08-30 00:05:47 +02:00
|
|
|
extern const PropertyInfo qdev_prop_nv_gpudirect_clique;
|
|
|
|
|
2016-10-17 18:57:57 +02:00
|
|
|
int vfio_populate_vga(VFIOPCIDevice *vdev, Error **errp);
|
2016-03-10 17:39:08 +01:00
|
|
|
|
2016-05-26 17:43:22 +02:00
|
|
|
int vfio_pci_igd_opregion_init(VFIOPCIDevice *vdev,
|
2016-10-17 18:57:59 +02:00
|
|
|
struct vfio_region_info *info,
|
|
|
|
Error **errp);
|
2016-05-26 17:43:22 +02:00
|
|
|
|
2015-09-23 21:04:44 +02:00
|
|
|
#endif /* HW_VFIO_VFIO_PCI_H */
|