mirror of
https://github.com/torvalds/linux.git
synced 2024-12-29 14:21:47 +00:00
30656177c4
The ioeventfd here is actually irqfd handling of an ioeventfd such as supported in KVM. A user is able to pre-program a device write to occur when the eventfd triggers. This is yet another instance of eventfd-irqfd triggering between KVM and vfio. The impetus for this is high frequency writes to pages which are virtualized in QEMU. Enabling this near-direct write path for selected registers within the virtualized page can improve performance and reduce overhead. Specifically this is initially targeted at NVIDIA graphics cards where the driver issues a write to an MMIO register within a virtualized region in order to allow the MSI interrupt to re-trigger. Reviewed-by: Peter Xu <peterx@redhat.com> Reviewed-by: Alexey Kardashevskiy <aik@ozlabs.ru> Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
389 lines
8.2 KiB
C
389 lines
8.2 KiB
C
/*
|
|
* VFIO PCI I/O Port & MMIO access
|
|
*
|
|
* Copyright (C) 2012 Red Hat, Inc. All rights reserved.
|
|
* Author: Alex Williamson <alex.williamson@redhat.com>
|
|
*
|
|
* 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.
|
|
*
|
|
* Derived from original vfio:
|
|
* Copyright 2010 Cisco Systems, Inc. All rights reserved.
|
|
* Author: Tom Lyon, pugs@cisco.com
|
|
*/
|
|
|
|
#include <linux/fs.h>
|
|
#include <linux/pci.h>
|
|
#include <linux/uaccess.h>
|
|
#include <linux/io.h>
|
|
#include <linux/vfio.h>
|
|
#include <linux/vgaarb.h>
|
|
|
|
#include "vfio_pci_private.h"
|
|
|
|
#ifdef __LITTLE_ENDIAN
|
|
#define vfio_ioread64 ioread64
|
|
#define vfio_iowrite64 iowrite64
|
|
#define vfio_ioread32 ioread32
|
|
#define vfio_iowrite32 iowrite32
|
|
#define vfio_ioread16 ioread16
|
|
#define vfio_iowrite16 iowrite16
|
|
#else
|
|
#define vfio_ioread64 ioread64be
|
|
#define vfio_iowrite64 iowrite64be
|
|
#define vfio_ioread32 ioread32be
|
|
#define vfio_iowrite32 iowrite32be
|
|
#define vfio_ioread16 ioread16be
|
|
#define vfio_iowrite16 iowrite16be
|
|
#endif
|
|
#define vfio_ioread8 ioread8
|
|
#define vfio_iowrite8 iowrite8
|
|
|
|
/*
|
|
* Read or write from an __iomem region (MMIO or I/O port) with an excluded
|
|
* range which is inaccessible. The excluded range drops writes and fills
|
|
* reads with -1. This is intended for handling MSI-X vector tables and
|
|
* leftover space for ROM BARs.
|
|
*/
|
|
static ssize_t do_io_rw(void __iomem *io, char __user *buf,
|
|
loff_t off, size_t count, size_t x_start,
|
|
size_t x_end, bool iswrite)
|
|
{
|
|
ssize_t done = 0;
|
|
|
|
while (count) {
|
|
size_t fillable, filled;
|
|
|
|
if (off < x_start)
|
|
fillable = min(count, (size_t)(x_start - off));
|
|
else if (off >= x_end)
|
|
fillable = count;
|
|
else
|
|
fillable = 0;
|
|
|
|
if (fillable >= 4 && !(off % 4)) {
|
|
u32 val;
|
|
|
|
if (iswrite) {
|
|
if (copy_from_user(&val, buf, 4))
|
|
return -EFAULT;
|
|
|
|
vfio_iowrite32(val, io + off);
|
|
} else {
|
|
val = vfio_ioread32(io + off);
|
|
|
|
if (copy_to_user(buf, &val, 4))
|
|
return -EFAULT;
|
|
}
|
|
|
|
filled = 4;
|
|
} else if (fillable >= 2 && !(off % 2)) {
|
|
u16 val;
|
|
|
|
if (iswrite) {
|
|
if (copy_from_user(&val, buf, 2))
|
|
return -EFAULT;
|
|
|
|
vfio_iowrite16(val, io + off);
|
|
} else {
|
|
val = vfio_ioread16(io + off);
|
|
|
|
if (copy_to_user(buf, &val, 2))
|
|
return -EFAULT;
|
|
}
|
|
|
|
filled = 2;
|
|
} else if (fillable) {
|
|
u8 val;
|
|
|
|
if (iswrite) {
|
|
if (copy_from_user(&val, buf, 1))
|
|
return -EFAULT;
|
|
|
|
vfio_iowrite8(val, io + off);
|
|
} else {
|
|
val = vfio_ioread8(io + off);
|
|
|
|
if (copy_to_user(buf, &val, 1))
|
|
return -EFAULT;
|
|
}
|
|
|
|
filled = 1;
|
|
} else {
|
|
/* Fill reads with -1, drop writes */
|
|
filled = min(count, (size_t)(x_end - off));
|
|
if (!iswrite) {
|
|
u8 val = 0xFF;
|
|
size_t i;
|
|
|
|
for (i = 0; i < filled; i++)
|
|
if (copy_to_user(buf + i, &val, 1))
|
|
return -EFAULT;
|
|
}
|
|
}
|
|
|
|
count -= filled;
|
|
done += filled;
|
|
off += filled;
|
|
buf += filled;
|
|
}
|
|
|
|
return done;
|
|
}
|
|
|
|
static int vfio_pci_setup_barmap(struct vfio_pci_device *vdev, int bar)
|
|
{
|
|
struct pci_dev *pdev = vdev->pdev;
|
|
int ret;
|
|
void __iomem *io;
|
|
|
|
if (vdev->barmap[bar])
|
|
return 0;
|
|
|
|
ret = pci_request_selected_regions(pdev, 1 << bar, "vfio");
|
|
if (ret)
|
|
return ret;
|
|
|
|
io = pci_iomap(pdev, bar, 0);
|
|
if (!io) {
|
|
pci_release_selected_regions(pdev, 1 << bar);
|
|
return -ENOMEM;
|
|
}
|
|
|
|
vdev->barmap[bar] = io;
|
|
|
|
return 0;
|
|
}
|
|
|
|
ssize_t vfio_pci_bar_rw(struct vfio_pci_device *vdev, char __user *buf,
|
|
size_t count, loff_t *ppos, bool iswrite)
|
|
{
|
|
struct pci_dev *pdev = vdev->pdev;
|
|
loff_t pos = *ppos & VFIO_PCI_OFFSET_MASK;
|
|
int bar = VFIO_PCI_OFFSET_TO_INDEX(*ppos);
|
|
size_t x_start = 0, x_end = 0;
|
|
resource_size_t end;
|
|
void __iomem *io;
|
|
ssize_t done;
|
|
|
|
if (pci_resource_start(pdev, bar))
|
|
end = pci_resource_len(pdev, bar);
|
|
else if (bar == PCI_ROM_RESOURCE &&
|
|
pdev->resource[bar].flags & IORESOURCE_ROM_SHADOW)
|
|
end = 0x20000;
|
|
else
|
|
return -EINVAL;
|
|
|
|
if (pos >= end)
|
|
return -EINVAL;
|
|
|
|
count = min(count, (size_t)(end - pos));
|
|
|
|
if (bar == PCI_ROM_RESOURCE) {
|
|
/*
|
|
* The ROM can fill less space than the BAR, so we start the
|
|
* excluded range at the end of the actual ROM. This makes
|
|
* filling large ROM BARs much faster.
|
|
*/
|
|
io = pci_map_rom(pdev, &x_start);
|
|
if (!io)
|
|
return -ENOMEM;
|
|
x_end = end;
|
|
} else {
|
|
int ret = vfio_pci_setup_barmap(vdev, bar);
|
|
if (ret)
|
|
return ret;
|
|
|
|
io = vdev->barmap[bar];
|
|
}
|
|
|
|
if (bar == vdev->msix_bar) {
|
|
x_start = vdev->msix_offset;
|
|
x_end = vdev->msix_offset + vdev->msix_size;
|
|
}
|
|
|
|
done = do_io_rw(io, buf, pos, count, x_start, x_end, iswrite);
|
|
|
|
if (done >= 0)
|
|
*ppos += done;
|
|
|
|
if (bar == PCI_ROM_RESOURCE)
|
|
pci_unmap_rom(pdev, io);
|
|
|
|
return done;
|
|
}
|
|
|
|
ssize_t vfio_pci_vga_rw(struct vfio_pci_device *vdev, char __user *buf,
|
|
size_t count, loff_t *ppos, bool iswrite)
|
|
{
|
|
int ret;
|
|
loff_t off, pos = *ppos & VFIO_PCI_OFFSET_MASK;
|
|
void __iomem *iomem = NULL;
|
|
unsigned int rsrc;
|
|
bool is_ioport;
|
|
ssize_t done;
|
|
|
|
if (!vdev->has_vga)
|
|
return -EINVAL;
|
|
|
|
if (pos > 0xbfffful)
|
|
return -EINVAL;
|
|
|
|
switch ((u32)pos) {
|
|
case 0xa0000 ... 0xbffff:
|
|
count = min(count, (size_t)(0xc0000 - pos));
|
|
iomem = ioremap_nocache(0xa0000, 0xbffff - 0xa0000 + 1);
|
|
off = pos - 0xa0000;
|
|
rsrc = VGA_RSRC_LEGACY_MEM;
|
|
is_ioport = false;
|
|
break;
|
|
case 0x3b0 ... 0x3bb:
|
|
count = min(count, (size_t)(0x3bc - pos));
|
|
iomem = ioport_map(0x3b0, 0x3bb - 0x3b0 + 1);
|
|
off = pos - 0x3b0;
|
|
rsrc = VGA_RSRC_LEGACY_IO;
|
|
is_ioport = true;
|
|
break;
|
|
case 0x3c0 ... 0x3df:
|
|
count = min(count, (size_t)(0x3e0 - pos));
|
|
iomem = ioport_map(0x3c0, 0x3df - 0x3c0 + 1);
|
|
off = pos - 0x3c0;
|
|
rsrc = VGA_RSRC_LEGACY_IO;
|
|
is_ioport = true;
|
|
break;
|
|
default:
|
|
return -EINVAL;
|
|
}
|
|
|
|
if (!iomem)
|
|
return -ENOMEM;
|
|
|
|
ret = vga_get_interruptible(vdev->pdev, rsrc);
|
|
if (ret) {
|
|
is_ioport ? ioport_unmap(iomem) : iounmap(iomem);
|
|
return ret;
|
|
}
|
|
|
|
done = do_io_rw(iomem, buf, off, count, 0, 0, iswrite);
|
|
|
|
vga_put(vdev->pdev, rsrc);
|
|
|
|
is_ioport ? ioport_unmap(iomem) : iounmap(iomem);
|
|
|
|
if (done >= 0)
|
|
*ppos += done;
|
|
|
|
return done;
|
|
}
|
|
|
|
static int vfio_pci_ioeventfd_handler(void *opaque, void *unused)
|
|
{
|
|
struct vfio_pci_ioeventfd *ioeventfd = opaque;
|
|
|
|
switch (ioeventfd->count) {
|
|
case 1:
|
|
vfio_iowrite8(ioeventfd->data, ioeventfd->addr);
|
|
break;
|
|
case 2:
|
|
vfio_iowrite16(ioeventfd->data, ioeventfd->addr);
|
|
break;
|
|
case 4:
|
|
vfio_iowrite32(ioeventfd->data, ioeventfd->addr);
|
|
break;
|
|
#ifdef iowrite64
|
|
case 8:
|
|
vfio_iowrite64(ioeventfd->data, ioeventfd->addr);
|
|
break;
|
|
#endif
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
long vfio_pci_ioeventfd(struct vfio_pci_device *vdev, loff_t offset,
|
|
uint64_t data, int count, int fd)
|
|
{
|
|
struct pci_dev *pdev = vdev->pdev;
|
|
loff_t pos = offset & VFIO_PCI_OFFSET_MASK;
|
|
int ret, bar = VFIO_PCI_OFFSET_TO_INDEX(offset);
|
|
struct vfio_pci_ioeventfd *ioeventfd;
|
|
|
|
/* Only support ioeventfds into BARs */
|
|
if (bar > VFIO_PCI_BAR5_REGION_INDEX)
|
|
return -EINVAL;
|
|
|
|
if (pos + count > pci_resource_len(pdev, bar))
|
|
return -EINVAL;
|
|
|
|
/* Disallow ioeventfds working around MSI-X table writes */
|
|
if (bar == vdev->msix_bar &&
|
|
!(pos + count <= vdev->msix_offset ||
|
|
pos >= vdev->msix_offset + vdev->msix_size))
|
|
return -EINVAL;
|
|
|
|
#ifndef iowrite64
|
|
if (count == 8)
|
|
return -EINVAL;
|
|
#endif
|
|
|
|
ret = vfio_pci_setup_barmap(vdev, bar);
|
|
if (ret)
|
|
return ret;
|
|
|
|
mutex_lock(&vdev->ioeventfds_lock);
|
|
|
|
list_for_each_entry(ioeventfd, &vdev->ioeventfds_list, next) {
|
|
if (ioeventfd->pos == pos && ioeventfd->bar == bar &&
|
|
ioeventfd->data == data && ioeventfd->count == count) {
|
|
if (fd == -1) {
|
|
vfio_virqfd_disable(&ioeventfd->virqfd);
|
|
list_del(&ioeventfd->next);
|
|
vdev->ioeventfds_nr--;
|
|
kfree(ioeventfd);
|
|
ret = 0;
|
|
} else
|
|
ret = -EEXIST;
|
|
|
|
goto out_unlock;
|
|
}
|
|
}
|
|
|
|
if (fd < 0) {
|
|
ret = -ENODEV;
|
|
goto out_unlock;
|
|
}
|
|
|
|
if (vdev->ioeventfds_nr >= VFIO_PCI_IOEVENTFD_MAX) {
|
|
ret = -ENOSPC;
|
|
goto out_unlock;
|
|
}
|
|
|
|
ioeventfd = kzalloc(sizeof(*ioeventfd), GFP_KERNEL);
|
|
if (!ioeventfd) {
|
|
ret = -ENOMEM;
|
|
goto out_unlock;
|
|
}
|
|
|
|
ioeventfd->addr = vdev->barmap[bar] + pos;
|
|
ioeventfd->data = data;
|
|
ioeventfd->pos = pos;
|
|
ioeventfd->bar = bar;
|
|
ioeventfd->count = count;
|
|
|
|
ret = vfio_virqfd_enable(ioeventfd, vfio_pci_ioeventfd_handler,
|
|
NULL, NULL, &ioeventfd->virqfd, fd);
|
|
if (ret) {
|
|
kfree(ioeventfd);
|
|
goto out_unlock;
|
|
}
|
|
|
|
list_add(&ioeventfd->next, &vdev->ioeventfds_list);
|
|
vdev->ioeventfds_nr++;
|
|
|
|
out_unlock:
|
|
mutex_unlock(&vdev->ioeventfds_lock);
|
|
|
|
return ret;
|
|
}
|