qemu/hw/vfio/pci.h

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

240 lines
7.4 KiB
C
Raw Normal View History

/*
* 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 "exec/memory.h"
#include "hw/pci/pci_device.h"
#include "hw/vfio/vfio-common.h"
#include "qemu/event_notifier.h"
#include "qemu/queue.h"
#include "qemu/timer.h"
#include "qom/object.h"
#include "sysemu/kvm.h"
#define PCI_ANY_ID (~0)
struct VFIOPCIDevice;
vfio/quirks: ioeventfd quirk acceleration The NVIDIA BAR0 quirks virtualize the PCI config space mirrors found in device MMIO space. Normally PCI config space is considered a slow path and further optimization is unnecessary, however NVIDIA uses a register here to enable the MSI interrupt to re-trigger. Exiting to QEMU for this MSI-ACK handling can therefore rate limit our interrupt handling. Fortunately the MSI-ACK write is easily detected since the quirk MemoryRegion otherwise has very few accesses, so simply looking for consecutive writes with the same data is sufficient, in this case 10 consecutive writes with the same data and size is arbitrarily chosen. We configure the KVM ioeventfd with data match, so there's no risk of triggering for the wrong data or size, but we do risk that pathological driver behavior might consume all of QEMU's file descriptors, so we cap ourselves to 10 ioeventfds for this purpose. In support of the above, generic ioeventfd infrastructure is added for vfio quirks. This automatically initializes an ioeventfd list per quirk, disables and frees ioeventfds on exit, and allows ioeventfds marked as dynamic to be dropped on device reset. The rationale for this latter feature is that useful ioeventfds may depend on specific driver behavior and since we necessarily place a cap on our use of ioeventfds, a machine reset is a reasonable point at which to assume a new driver and re-profile. Reviewed-by: Peter Xu <peterx@redhat.com> Reviewed-by: Eric Auger <eric.auger@redhat.com> Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
2018-06-05 17:23:17 +03:00
typedef struct VFIOIOEventFD {
QLIST_ENTRY(VFIOIOEventFD) next;
MemoryRegion *mr;
hwaddr addr;
unsigned size;
uint64_t data;
EventNotifier e;
VFIORegion *region;
hwaddr region_addr;
bool dynamic; /* Added runtime, removed on device reset */
bool vfio;
vfio/quirks: ioeventfd quirk acceleration The NVIDIA BAR0 quirks virtualize the PCI config space mirrors found in device MMIO space. Normally PCI config space is considered a slow path and further optimization is unnecessary, however NVIDIA uses a register here to enable the MSI interrupt to re-trigger. Exiting to QEMU for this MSI-ACK handling can therefore rate limit our interrupt handling. Fortunately the MSI-ACK write is easily detected since the quirk MemoryRegion otherwise has very few accesses, so simply looking for consecutive writes with the same data is sufficient, in this case 10 consecutive writes with the same data and size is arbitrarily chosen. We configure the KVM ioeventfd with data match, so there's no risk of triggering for the wrong data or size, but we do risk that pathological driver behavior might consume all of QEMU's file descriptors, so we cap ourselves to 10 ioeventfds for this purpose. In support of the above, generic ioeventfd infrastructure is added for vfio quirks. This automatically initializes an ioeventfd list per quirk, disables and frees ioeventfds on exit, and allows ioeventfds marked as dynamic to be dropped on device reset. The rationale for this latter feature is that useful ioeventfds may depend on specific driver behavior and since we necessarily place a cap on our use of ioeventfds, a machine reset is a reasonable point at which to assume a new driver and re-profile. Reviewed-by: Peter Xu <peterx@redhat.com> Reviewed-by: Eric Auger <eric.auger@redhat.com> Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
2018-06-05 17:23:17 +03:00
} VFIOIOEventFD;
typedef struct VFIOQuirk {
QLIST_ENTRY(VFIOQuirk) next;
void *data;
vfio/quirks: ioeventfd quirk acceleration The NVIDIA BAR0 quirks virtualize the PCI config space mirrors found in device MMIO space. Normally PCI config space is considered a slow path and further optimization is unnecessary, however NVIDIA uses a register here to enable the MSI interrupt to re-trigger. Exiting to QEMU for this MSI-ACK handling can therefore rate limit our interrupt handling. Fortunately the MSI-ACK write is easily detected since the quirk MemoryRegion otherwise has very few accesses, so simply looking for consecutive writes with the same data is sufficient, in this case 10 consecutive writes with the same data and size is arbitrarily chosen. We configure the KVM ioeventfd with data match, so there's no risk of triggering for the wrong data or size, but we do risk that pathological driver behavior might consume all of QEMU's file descriptors, so we cap ourselves to 10 ioeventfds for this purpose. In support of the above, generic ioeventfd infrastructure is added for vfio quirks. This automatically initializes an ioeventfd list per quirk, disables and frees ioeventfds on exit, and allows ioeventfds marked as dynamic to be dropped on device reset. The rationale for this latter feature is that useful ioeventfds may depend on specific driver behavior and since we necessarily place a cap on our use of ioeventfds, a machine reset is a reasonable point at which to assume a new driver and re-profile. Reviewed-by: Peter Xu <peterx@redhat.com> Reviewed-by: Eric Auger <eric.auger@redhat.com> Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
2018-06-05 17:23:17 +03:00
QLIST_HEAD(, VFIOIOEventFD) ioeventfds;
int nr_mem;
MemoryRegion *mem;
void (*reset)(struct VFIOPCIDevice *vdev, struct VFIOQuirk *quirk);
} VFIOQuirk;
typedef struct VFIOBAR {
VFIORegion region;
MemoryRegion *mr;
size_t size;
uint8_t type;
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 */
typedef struct VFIOMSIXInfo {
uint8_t table_bar;
uint8_t pba_bar;
uint16_t entries;
uint32_t table_offset;
uint32_t pba_offset;
unsigned long *pending;
bool noresize;
} VFIOMSIXInfo;
#define TYPE_VFIO_PCI "vfio-pci"
OBJECT_DECLARE_SIMPLE_TYPE(VFIOPCIDevice, VFIO_PCI)
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 */
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 18:43:21 +03:00
void *igd_opregion;
PCIHostDeviceAddress host;
QemuUUID vf_token;
EventNotifier err_notifier;
EventNotifier req_notifier;
int (*resetfn)(struct VFIOPCIDevice *);
uint32_t vendor_id;
uint32_t device_id;
uint32_t sub_vendor_id;
uint32_t sub_device_id;
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)
#define VFIO_FEATURE_ENABLE_IGD_OPREGION_BIT 2
#define VFIO_FEATURE_ENABLE_IGD_OPREGION \
(1 << VFIO_FEATURE_ENABLE_IGD_OPREGION_BIT)
OnOffAuto display;
uint32_t display_xres;
uint32_t display_yres;
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 18:43:21 +03:00
uint32_t igd_gms;
vfio/pci: Allow relocating MSI-X MMIO Recently proposed vfio-pci kernel changes (v4.16) remove the restriction preventing userspace from mmap'ing PCI BARs in areas overlapping the MSI-X vector table. This change is primarily intended to benefit host platforms which make use of system page sizes larger than the PCI spec recommendation for alignment of MSI-X data structures (ie. not x86_64). In the case of POWER systems, the SPAPR spec requires the VM to program MSI-X using hypercalls, rendering the MSI-X vector table unused in the VM view of the device. However, ARM64 platforms also support 64KB pages and rely on QEMU emulation of MSI-X. Regardless of the kernel driver allowing mmaps overlapping the MSI-X vector table, emulation of the MSI-X vector table also prevents direct mapping of device MMIO spaces overlapping this page. Thanks to the fact that PCI devices have a standard self discovery mechanism, we can try to resolve this by relocating the MSI-X data structures, either by creating a new PCI BAR or extending an existing BAR and updating the MSI-X capability for the new location. There's even a very slim chance that this could benefit devices which do not adhere to the PCI spec alignment guidelines on x86_64 systems. This new x-msix-relocation option accepts the following choices: off: Disable MSI-X relocation, use native device config (default) auto: Use a known good combination for the platform/device (none yet) bar0..bar5: Specify the target BAR for MSI-X data structures If compatible, the target BAR will either be created or extended and the new portion will be used for MSI-X emulation. The first obvious user question with this option is how to determine whether a given platform and device might benefit from this option. In most cases, the answer is that it won't, especially on x86_64. Devices often dedicate an entire BAR to MSI-X and therefore no performance sensitive registers overlap the MSI-X area. Take for example: # lspci -vvvs 0a:00.0 0a:00.0 Ethernet controller: Intel Corporation I350 Gigabit Network Connection ... Region 0: Memory at db680000 (32-bit, non-prefetchable) [size=512K] Region 3: Memory at db7f8000 (32-bit, non-prefetchable) [size=16K] ... Capabilities: [70] MSI-X: Enable+ Count=10 Masked- Vector table: BAR=3 offset=00000000 PBA: BAR=3 offset=00002000 This device uses the 16K bar3 for MSI-X with the vector table at offset zero and the pending bits arrary at offset 8K, fully honoring the PCI spec alignment guidance. The data sheet specifically refers to this as an MSI-X BAR. This device would not see a benefit from MSI-X relocation regardless of the platform, regardless of the page size. However, here's another example: # lspci -vvvs 02:00.0 02:00.0 Serial Attached SCSI controller: xxxxxxxx ... Region 0: I/O ports at c000 [size=256] Region 1: Memory at ef640000 (64-bit, non-prefetchable) [size=64K] Region 3: Memory at ef600000 (64-bit, non-prefetchable) [size=256K] ... Capabilities: [c0] MSI-X: Enable+ Count=16 Masked- Vector table: BAR=1 offset=0000e000 PBA: BAR=1 offset=0000f000 Here the MSI-X data structures are placed on separate 4K pages at the end of a 64KB BAR. If our host page size is 4K, we're likely fine, but at 64KB page size, MSI-X emulation at that location prevents the entire BAR from being directly mapped into the VM address space. Overlapping performance sensitive registers then starts to be a very likely scenario on such a platform. At this point, the user could enable tracing on vfio_region_read and vfio_region_write to determine more conclusively if device accesses are being trapped through QEMU. Upon finding a device and platform in need of MSI-X relocation, the next problem is how to choose target PCI BAR to host the MSI-X data structures. A few key rules to keep in mind for this selection include: * There are only 6 BAR slots, bar0..bar5 * 64-bit BARs occupy two BAR slots, 'lspci -vvv' lists the first slot * PCI BARs are always a power of 2 in size, extending == doubling * The maximum size of a 32-bit BAR is 2GB * MSI-X data structures must reside in an MMIO BAR Using these rules, we can evaluate each BAR of the second example device above as follows: bar0: I/O port BAR, incompatible with MSI-X tables bar1: BAR could be extended, incurring another 64KB of MMIO bar2: Unavailable, bar1 is 64-bit, this register is used by bar1 bar3: BAR could be extended, incurring another 256KB of MMIO bar4: Unavailable, bar3 is 64bit, this register is used by bar3 bar5: Available, empty BAR, minimum additional MMIO A secondary optimization we might wish to make in relocating MSI-X is to minimize the additional MMIO required for the device, therefore we might test the available choices in order of preference as bar5, bar1, and finally bar3. The original proposal for this feature included an 'auto' option which would choose bar5 in this case, but various drivers have been found that make assumptions about the properties of the "first" BAR or the size of BARs such that there appears to be no foolproof automatic selection available, requiring known good combinations to be sourced from users. This patch is pre-enabled for an 'auto' selection making use of a validated lookup table, but no entries are yet identified. Tested-by: Alexey Kardashevskiy <aik@ozlabs.ru> Reviewed-by: Eric Auger <eric.auger@redhat.com> Tested-by: Eric Auger <eric.auger@redhat.com> Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
2018-02-06 21:08:26 +03:00
OffAutoPCIBAR msix_relo;
uint8_t pm_cap;
2017-08-30 01:05:47 +03:00
uint8_t nv_gpudirect_clique;
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;
bool no_geforce_quirks;
vfio/quirks: ioeventfd quirk acceleration The NVIDIA BAR0 quirks virtualize the PCI config space mirrors found in device MMIO space. Normally PCI config space is considered a slow path and further optimization is unnecessary, however NVIDIA uses a register here to enable the MSI interrupt to re-trigger. Exiting to QEMU for this MSI-ACK handling can therefore rate limit our interrupt handling. Fortunately the MSI-ACK write is easily detected since the quirk MemoryRegion otherwise has very few accesses, so simply looking for consecutive writes with the same data is sufficient, in this case 10 consecutive writes with the same data and size is arbitrarily chosen. We configure the KVM ioeventfd with data match, so there's no risk of triggering for the wrong data or size, but we do risk that pathological driver behavior might consume all of QEMU's file descriptors, so we cap ourselves to 10 ioeventfds for this purpose. In support of the above, generic ioeventfd infrastructure is added for vfio quirks. This automatically initializes an ioeventfd list per quirk, disables and frees ioeventfds on exit, and allows ioeventfds marked as dynamic to be dropped on device reset. The rationale for this latter feature is that useful ioeventfds may depend on specific driver behavior and since we necessarily place a cap on our use of ioeventfds, a machine reset is a reasonable point at which to assume a new driver and re-profile. Reviewed-by: Peter Xu <peterx@redhat.com> Reviewed-by: Eric Auger <eric.auger@redhat.com> Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
2018-06-05 17:23:17 +03:00
bool no_kvm_ioeventfd;
bool no_vfio_ioeventfd;
bool enable_ramfb;
OnOffAuto ramfb_migrate;
bool defer_kvm_irq_routing;
bool clear_parent_atomics_on_exit;
VFIODisplay *dpy;
Notifier irqchip_change_notifier;
};
/* Use uin32_t for vendor & device so PCI_ANY_ID expands and cannot match hw */
static inline bool vfio_pci_is(VFIOPCIDevice *vdev, uint32_t vendor, uint32_t device)
{
return (vendor == PCI_ANY_ID || vendor == vdev->vendor_id) &&
(device == PCI_ANY_ID || device == vdev->device_id);
}
static inline bool vfio_is_vga(VFIOPCIDevice *vdev)
{
PCIDevice *pdev = &vdev->pdev;
uint16_t class = pci_get_word(pdev->config + PCI_CLASS_DEVICE);
return class == PCI_CLASS_DISPLAY_VGA;
}
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_opt_rom_in_denylist(VFIOPCIDevice *vdev);
void vfio_vga_quirk_setup(VFIOPCIDevice *vdev);
void vfio_vga_quirk_exit(VFIOPCIDevice *vdev);
void vfio_vga_quirk_finalize(VFIOPCIDevice *vdev);
void vfio_bar_quirk_setup(VFIOPCIDevice *vdev, int nr);
void vfio_bar_quirk_exit(VFIOPCIDevice *vdev, int nr);
void vfio_bar_quirk_finalize(VFIOPCIDevice *vdev, int nr);
void vfio_setup_resetfn_quirk(VFIOPCIDevice *vdev);
int vfio_add_virt_caps(VFIOPCIDevice *vdev, Error **errp);
void vfio_quirk_reset(VFIOPCIDevice *vdev);
VFIOQuirk *vfio_quirk_alloc(int nr_mem);
void vfio_probe_igd_bar4_quirk(VFIOPCIDevice *vdev, int nr);
2017-08-30 01:05:47 +03:00
extern const PropertyInfo qdev_prop_nv_gpudirect_clique;
void vfio_pci_pre_reset(VFIOPCIDevice *vdev);
void vfio_pci_post_reset(VFIOPCIDevice *vdev);
bool vfio_pci_host_match(PCIHostDeviceAddress *addr, const char *name);
int vfio_pci_get_pci_hot_reset_info(VFIOPCIDevice *vdev,
struct vfio_pci_hot_reset_info **info_p);
int vfio_populate_vga(VFIOPCIDevice *vdev, Error **errp);
int vfio_pci_igd_opregion_init(VFIOPCIDevice *vdev,
struct vfio_region_info *info,
Error **errp);
void vfio_display_reset(VFIOPCIDevice *vdev);
int vfio_display_probe(VFIOPCIDevice *vdev, Error **errp);
void vfio_display_finalize(VFIOPCIDevice *vdev);
extern const VMStateDescription vfio_display_vmstate;
#endif /* HW_VFIO_VFIO_PCI_H */