* On Wednesday 17 Sep 2008 11:15:16 Zhang, Xiantao wrote:
> Seems it lacks device-assignment.[c,h] ?
> Xiantao
Hmm, here is the version with the files.
>From cd82862ef7493afd3431e538b85adb9771f94da6 Mon Sep 17 00:00:00 2001
From: Amit Shah <[EMAIL PROTECTED]>
Date: Tue, 16 Sep 2008 23:09:23 +0530
Subject: [PATCH] KVM/userspace: Support for assigning PCI devices to guests
[This still doesn't include some fixes to review comments.
I'm posting this just so that people can use this to test
or base their work off the latest patch.]
From: Or Sagi <[EMAIL PROTECTED]>
From: Nir Peleg <[EMAIL PROTECTED]>
From: Amit Shah <[EMAIL PROTECTED]>
From: Ben-Ami Yassour <[EMAIL PROTECTED]>
From: Glauber de Oliveira Costa <[EMAIL PROTECTED]>
With this patch, we can assign a device on the host machine to a
guest.
A new command-line option, -pcidevice is added.
For example, to invoke it for a device sitting at PCI bus:dev.fn
04:08.0 with host IRQ 18, use this:
-pcidevice host=04:08.0
The host driver for the device, if any, is to be removed before
assigning the device.
This works only with the in-kernel irqchip method; to use the
userspace irqchip, a kernel module (irqhook) and some extra changes
are needed.
Signed-off-by: Amit Shah <[EMAIL PROTECTED]>
---
libkvm/libkvm-x86.c | 14 +
libkvm/libkvm.h | 27 ++
qemu/Makefile.target | 1 +
qemu/hw/device-assignment.c | 605
+++++++++++++++++++++++++++++++++++++++++++
qemu/hw/device-assignment.h | 92 +++++++
qemu/hw/isa.h | 2 +
qemu/hw/pc.c | 9 +
qemu/hw/pci.c | 12 +
qemu/hw/pci.h | 1 +
qemu/hw/piix_pci.c | 19 ++
qemu/qemu-kvm-x86.c | 3 +
qemu/vl.c | 18 ++
12 files changed, 803 insertions(+), 0 deletions(-)
create mode 100644 qemu/hw/device-assignment.c
create mode 100644 qemu/hw/device-assignment.h
diff --git a/libkvm/libkvm-x86.c b/libkvm/libkvm-x86.c
index a8cca15..6157f75 100644
--- a/libkvm/libkvm-x86.c
+++ b/libkvm/libkvm-x86.c
@@ -53,6 +53,20 @@ static int kvm_init_tss(kvm_context_t kvm)
return 0;
}
+#ifdef KVM_CAP_DEVICE_ASSIGNMENT
+int kvm_assign_pci_device(kvm_context_t kvm,
+ struct kvm_assigned_pci_dev *assigned_dev)
+{
+ return ioctl(kvm->vm_fd, KVM_ASSIGN_PCI_DEVICE, assigned_dev);
+}
+
+int kvm_assign_irq(kvm_context_t kvm,
+ struct kvm_assigned_irq *assigned_irq)
+{
+ return ioctl(kvm->vm_fd, KVM_ASSIGN_IRQ, assigned_irq);
+}
+#endif
+
int kvm_create_pit(kvm_context_t kvm)
{
#ifdef KVM_CAP_PIT
diff --git a/libkvm/libkvm.h b/libkvm/libkvm.h
index 79dd769..edf8e9e 100644
--- a/libkvm/libkvm.h
+++ b/libkvm/libkvm.h
@@ -658,4 +658,31 @@ int kvm_s390_interrupt(kvm_context_t kvm, int slot,
int kvm_s390_set_initial_psw(kvm_context_t kvm, int slot, psw_t psw);
int kvm_s390_store_status(kvm_context_t kvm, int slot, unsigned long addr);
#endif
+
+#ifdef KVM_CAP_DEVICE_ASSIGNMENT
+/*!
+ * \brief Notifies host kernel aboud a PCI device assigned to guest
+ *
+ * Used for PCI device assignment, this function notifies the host
+ * kernel about the assigning of the physical PCI device.
+ *
+ * \param kvm Pointer to the current kvm_context
+ * \param assigned_dev Parameters, like bus, devfn number, etc
+ */
+int kvm_assign_pci_device(kvm_context_t kvm,
+ struct kvm_assigned_pci_dev *assigned_dev);
+
+/*!
+ * \brief Notifies host kernel about changes to a irq assignment
+ *
+ * Used for PCI device assignment, this function notifies the host
+ * kernel about the assigning of the irq for an assigned physical
+ * PCI device.
+ *
+ * \param kvm Pointer to the current kvm_context
+ * \param assigned_irq Parameters, like dev id, host irq, guest irq, etc
+ */
+int kvm_assign_irq(kvm_context_t kvm,
+ struct kvm_assigned_irq *assigned_irq);
+#endif
#endif
diff --git a/qemu/Makefile.target b/qemu/Makefile.target
index 89814fd..958c33b 100644
--- a/qemu/Makefile.target
+++ b/qemu/Makefile.target
@@ -611,6 +611,7 @@ OBJS+= ide.o pckbd.o ps2.o vga.o $(SOUND_HW) dma.o
OBJS+= fdc.o mc146818rtc.o serial.o i8259.o i8254.o pcspk.o pc.o
OBJS+= cirrus_vga.o apic.o parallel.o acpi.o piix_pci.o
OBJS+= usb-uhci.o vmmouse.o vmport.o vmware_vga.o extboot.o
+OBJS+= device-assignment.o
ifeq ($(USE_KVM_PIT), 1)
OBJS+= i8254-kvm.o
endif
diff --git a/qemu/hw/device-assignment.c b/qemu/hw/device-assignment.c
new file mode 100644
index 0000000..d32bbb4
--- /dev/null
+++ b/qemu/hw/device-assignment.c
@@ -0,0 +1,605 @@
+/*
+ * Copyright (c) 2007, Neocleus Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along
with
+ * this program; if not, write to the Free Software Foundation, Inc., 59
Temple
+ * Place - Suite 330, Boston, MA 02111-1307 USA.
+ *
+ *
+ * Assign a PCI device from the host to a guest VM.
+ *
+ * Adapted for KVM by Qumranet.
+ *
+ * Copyright (c) 2007, Neocleus, Alex Novik ([EMAIL PROTECTED])
+ * Copyright (c) 2007, Neocleus, Guy Zana ([EMAIL PROTECTED])
+ * Copyright (C) 2008, Qumranet, Amit Shah ([EMAIL PROTECTED])
+ */
+#include <stdio.h>
+#include <sys/io.h>
+#include "qemu-kvm.h"
+#include <linux/kvm_para.h>
+#include "device-assignment.h"
+
+/* From linux/ioport.h */
+#define IORESOURCE_IO 0x00000100 /* Resource type */
+#define IORESOURCE_MEM 0x00000200
+#define IORESOURCE_IRQ 0x00000400
+#define IORESOURCE_DMA 0x00000800
+#define IORESOURCE_PREFETCH 0x00001000 /* No side effects */
+
+/* #define DEVICE_ASSIGNMENT_DEBUG */
+
+#ifdef DEVICE_ASSIGNMENT_DEBUG
+#define DEBUG(fmt, args...) fprintf(stderr, "%s: " fmt, __func__ , ## args)
+#else
+#define DEBUG(fmt, args...)
+#endif
+
+#define assigned_dev_ioport_write(suffix) \
+ static void assigned_dev_ioport_write##suffix(void *opaque, uint32_t addr, \
+ uint32_t value) \
+ { \
+ AssignedDevRegion *r_access = (AssignedDevRegion *)opaque; \
+ uint32_t r_pio = (unsigned long)r_access->r_virtbase \
+ + (addr - r_access->e_physbase); \
+ if (r_access->debug & DEVICE_ASSIGNMENT_DEBUG_PIO) { \
+ fprintf(stderr, "assigned_dev_ioport_write" #suffix \
+ ": r_pio=%08x e_physbase=%08x" \
+ " r_virtbase=%08lx value=%08x\n", \
+ r_pio, (int)r_access->e_physbase, \
+ (unsigned long)r_access->r_virtbase, value); \
+ } \
+ iopl(3); \
+ out##suffix(value, r_pio); \
+ }
+
+assigned_dev_ioport_write(b)
+assigned_dev_ioport_write(w)
+assigned_dev_ioport_write(l)
+
+#define assigned_dev_ioport_read(suffix) \
+ static uint32_t assigned_dev_ioport_read##suffix(void *opaque, uint32_t
addr) \
+ { \
+ AssignedDevRegion *r_access = (AssignedDevRegion *)opaque; \
+ uint32_t r_pio = (addr - r_access->e_physbase) \
+ + (unsigned long)r_access->r_virtbase; \
+ uint32_t value = in##suffix(r_pio); \
+ if (r_access->debug & DEVICE_ASSIGNMENT_DEBUG_PIO) { \
+ fprintf(stderr, "assigned_dev_ioport_read" #suffix \
+ ": r_pio=%08x e_physbase=%08x r_virtbase=%08lx " \
+ "value=%08x\n", \
+ r_pio, (int)r_access->e_physbase, \
+ (unsigned long)r_access->r_virtbase, value); \
+ } \
+ return value; \
+ }
+
+assigned_dev_ioport_read(b)
+assigned_dev_ioport_read(w)
+assigned_dev_ioport_read(l)
+
+static void assigned_dev_iomem_map(PCIDevice *pci_dev, int region_num,
+ uint32_t e_phys, uint32_t e_size, int type)
+{
+ AssignedDevice *r_dev = (AssignedDevice *) pci_dev;
+ AssignedDevRegion *region = &r_dev->v_addrs[region_num];
+ int first_map = (region->e_size == 0);
+ int ret = 0;
+
+ DEBUG("e_phys=%08x r_virt=%p type=%d len=%08x region_num=%d \n",
+ e_phys, r_dev->v_addrs[region_num].r_virtbase, type, e_size,
+ region_num);
+
+ region->e_physbase = e_phys;
+ region->e_size = e_size;
+
+ if (!first_map)
+ kvm_destroy_phys_mem(kvm_context, e_phys, e_size);
+ if (e_size > 0)
+ ret = kvm_register_phys_mem(kvm_context,
+ e_phys,
+ region->r_virtbase,
+ e_size,
+ 0);
+ if (ret != 0)
+ fprintf(stderr, "%s: Error: create new mapping failed\n",
+ __func__);
+}
+
+static void assigned_dev_ioport_map(PCIDevice *pci_dev, int region_num,
+ uint32_t addr, uint32_t size, int type)
+{
+ AssignedDevice *r_dev = (AssignedDevice *) pci_dev;
+ int i;
+ uint32_t ((*rf[])(void *, uint32_t)) =
+ { assigned_dev_ioport_readb,
+ assigned_dev_ioport_readw,
+ assigned_dev_ioport_readl
+ };
+ void ((*wf[])(void *, uint32_t, uint32_t)) =
+ { assigned_dev_ioport_writeb,
+ assigned_dev_ioport_writew,
+ assigned_dev_ioport_writel
+ };
+
+ r_dev->v_addrs[region_num].e_physbase = addr;
+ DEBUG("%s: address=0x%x type=0x%x len=%d region_num=%d \n",
+ __func__, addr, type, size, region_num);
+
+ for (i = 0; i < 3; i++) {
+ register_ioport_write(addr, size, 1<<i, wf[i],
+ (void *) (r_dev->v_addrs + region_num));
+ register_ioport_read(addr, size, 1<<i, rf[i],
+ (void *) (r_dev->v_addrs + region_num));
+ }
+}
+
+static void assigned_dev_pci_write_config(PCIDevice *d, uint32_t address,
+ uint32_t val, int len)
+{
+ int fd, r;
+
+ DEBUG("%s: (%x.%x): address=%04x val=0x%08x len=%d\n",
+ __func__, ((d->devfn >> 3) & 0x1F), (d->devfn & 0x7),
+ (uint16_t) address, val, len);
+
+ if (address == 0x4)
+ pci_default_write_config(d, address, val, len);
+
+ if ((address >= 0x10 && address <= 0x24) || address == 0x34 ||
+ address == 0x3c || address == 0x3d) {
+ /* used for update-mappings (BAR emulation) */
+ pci_default_write_config(d, address, val, len);
+ return;
+ }
+ DEBUG("%s: NON BAR (%x.%x): address=%04x val=0x%08x len=%d\n",
+ __func__, ((d->devfn >> 3) & 0x1F), (d->devfn & 0x7),
+ (uint16_t) address, val, len);
+ fd = ((AssignedDevice *)d)->real_device.config_fd;
+ lseek(fd, address, SEEK_SET);
+again:
+ r = write(fd, &val, len);
+ if (r < 0) {
+ if (errno == EINTR || errno == EAGAIN)
+ goto again;
+ fprintf(stderr, "%s: write failed, errno = %d\n",
+ __func__, errno);
+ }
+}
+
+static uint32_t assigned_dev_pci_read_config(PCIDevice *d, uint32_t address,
+ int len)
+{
+ uint32_t val = 0;
+ int fd, r;
+
+ if ((address >= 0x10 && address <= 0x24) || address == 0x34 ||
+ address == 0x3c || address == 0x3d) {
+ val = pci_default_read_config(d, address, len);
+ DEBUG("(%x.%x): address=%04x val=0x%08x len=%d\n",
+ (d->devfn >> 3) & 0x1F, (d->devfn & 0x7), address, val,
+ len);
+ return val;
+ }
+
+ /* vga specific, remove later */
+ if (address == 0xFC)
+ goto do_log;
+
+ fd = ((AssignedDevice *)d)->real_device.config_fd;
+ lseek(fd, address, SEEK_SET);
+again:
+ r = read(fd, &val, len);
+ if (r < 0) {
+ if (errno == EINTR || errno == EAGAIN)
+ goto again;
+ fprintf(stderr, "%s: read failed, errno = %d\n",
+ __func__, errno);
+ }
+do_log:
+ DEBUG("(%x.%x): address=%04x val=0x%08x len=%d\n",
+ (d->devfn >> 3) & 0x1F, (d->devfn & 0x7), address, val, len);
+
+ /* kill the special capabilities */
+ if (address == 4 && len == 4)
+ val &= ~0x100000;
+ else if (address == 6)
+ val &= ~0x10;
+
+ return val;
+}
+
+static int assigned_dev_register_regions(PCIRegion *io_regions,
+ unsigned long regions_num,
+ AssignedDevice *pci_dev)
+{
+ uint32_t i;
+ PCIRegion *cur_region = io_regions;
+
+ for (i = 0; i < regions_num; i++, cur_region++) {
+ if (!cur_region->valid)
+ continue;
+#ifdef DEVICE_ASSIGNMENT_DEBUG
+ pci_dev->v_addrs[i].debug |= DEVICE_ASSIGNMENT_DEBUG_MMIO
+ | DEVICE_ASSIGNMENT_DEBUG_PIO;
+#endif
+ pci_dev->v_addrs[i].num = i;
+
+ /* handle memory io regions */
+ if (cur_region->type & IORESOURCE_MEM) {
+ int t = cur_region->type & IORESOURCE_PREFETCH
+ ? PCI_ADDRESS_SPACE_MEM_PREFETCH
+ : PCI_ADDRESS_SPACE_MEM;
+
+ /* map physical memory */
+ pci_dev->v_addrs[i].e_physbase = cur_region->base_addr;
+ pci_dev->v_addrs[i].r_virtbase =
+ mmap(NULL,
+ (cur_region->size + 0xFFF) & 0xFFFFF000,
+ PROT_WRITE | PROT_READ, MAP_SHARED,
+ cur_region->resource_fd, (off_t) 0);
+
+ if ((void *) -1 == pci_dev->v_addrs[i].r_virtbase) {
+ fprintf(stderr, "%s: Error: Couldn't mmap 0x%x!"
+ "\n", __func__,
+ (uint32_t) (cur_region->base_addr));
+ return -1;
+ }
+ pci_dev->v_addrs[i].r_size = cur_region->size;
+ pci_dev->v_addrs[i].e_size = 0;
+
+ /* add offset */
+ pci_dev->v_addrs[i].r_virtbase +=
+ (cur_region->base_addr & 0xFFF);
+
+ pci_register_io_region((PCIDevice *) pci_dev, i,
+ cur_region->size, t,
+ assigned_dev_iomem_map);
+ continue;
+ }
+ /* handle port io regions */
+ pci_register_io_region((PCIDevice *) pci_dev, i,
+ cur_region->size, PCI_ADDRESS_SPACE_IO,
+ assigned_dev_ioport_map);
+
+ pci_dev->v_addrs[i].e_physbase = cur_region->base_addr;
+ pci_dev->v_addrs[i].r_virtbase =
+ (void *)(long)cur_region->base_addr;
+ /* not relevant for port io */
+ pci_dev->v_addrs[i].memory_index = 0;
+ }
+
+ /* success */
+ return 0;
+}
+
+static int get_real_device(AssignedDevice *pci_dev, uint8_t r_bus,
+ uint8_t r_dev, uint8_t r_func)
+{
+ char dir[128], name[128], comp[16];
+ int fd, r = 0;
+ FILE *f;
+ unsigned long long start, end, size, flags;
+ PCIRegion *rp;
+ PCIDevRegions *dev = &pci_dev->real_device;
+
+ dev->region_number = 0;
+
+ sprintf(dir, "/sys/bus/pci/devices/0000:%02x:%02x.%x/",
+ r_bus, r_dev, r_func);
+ strcpy(name, dir);
+ strcat(name, "config");
+ fd = open(name, O_RDWR);
+ if (fd == -1) {
+ fprintf(stderr, "%s: %s: %m\n", __func__, name);
+ return 1;
+ }
+ dev->config_fd = fd;
+again:
+ r = read(fd, pci_dev->dev.config, sizeof pci_dev->dev.config);
+ if (r < 0) {
+ if (errno == EINTR || errno == EAGAIN)
+ goto again;
+ fprintf(stderr, "%s: read failed, errno = %d\n",
+ __func__, errno);
+ }
+ strcpy(name, dir);
+ strcat(name, "resource");
+
+ f = fopen(name, "r");
+ if (f == NULL) {
+ fprintf(stderr, "%s: %s: %m\n", __func__, name);
+ return 1;
+ }
+ for (r = 0; fscanf(f, "%lli %lli %lli\n", &start, &end, &flags) == 3;
+ r++) {
+ rp = dev->regions + r;
+ rp->valid = 0;
+ size = end - start + 1;
+ flags &= IORESOURCE_IO | IORESOURCE_MEM | IORESOURCE_PREFETCH;
+ if (size == 0 || (flags & ~IORESOURCE_PREFETCH) == 0)
+ continue;
+ if (flags & IORESOURCE_MEM) {
+ flags &= ~IORESOURCE_IO;
+ sprintf(comp, "resource%d", r);
+ strcpy(name, dir);
+ strcat(name, comp);
+ fd = open(name, O_RDWR);
+ if (fd == -1)
+ continue; /* probably ROM */
+ rp->resource_fd = fd;
+ } else
+ flags &= ~IORESOURCE_PREFETCH;
+
+ rp->type = flags;
+ rp->valid = 1;
+ rp->base_addr = start;
+ rp->size = size;
+ DEBUG("%s: region %d size %d start 0x%x type %d "
+ "resource_fd %d\n", __func__, r, rp->size, start,
+ rp->type, rp->resource_fd);
+ }
+ fclose(f);
+
+ dev->region_number = r;
+ return 0;
+}
+
+#define MAX_ASSIGNED_DEVS 4
+struct {
+ char name[15];
+ int bus;
+ int dev;
+ int func;
+ int dma;
+ AssignedDevice *assigned_dev;
+} assigned_devices[MAX_ASSIGNED_DEVS];
+
+int nr_assigned_devices;
+static int disable_iommu;
+
+static uint32_t calc_assigned_dev_id(uint8_t bus, uint8_t devfn)
+{
+ return (uint32_t)bus << 8 | (uint32_t)devfn;
+}
+
+static AssignedDevice *register_real_device(PCIBus *e_bus,
+ const char *e_dev_name,
+ int e_devfn, uint8_t r_bus,
+ uint8_t r_dev, uint8_t r_func,
+ int flags)
+{
+ int r;
+ AssignedDevice *pci_dev;
+ uint8_t e_device, e_intx;
+
+ DEBUG("%s: Registering real physical device %s (devfn=0x%x)\n",
+ __func__, e_dev_name, e_devfn);
+
+ pci_dev = (AssignedDevice *)
+ pci_register_device(e_bus, e_dev_name, sizeof(AssignedDevice),
+ e_devfn, assigned_dev_pci_read_config,
+ assigned_dev_pci_write_config);
+ if (NULL == pci_dev) {
+ fprintf(stderr, "%s: Error: Couldn't register real device %s\n",
+ __func__, e_dev_name);
+ return NULL;
+ }
+ if (get_real_device(pci_dev, r_bus, r_dev, r_func)) {
+ fprintf(stderr, "%s: Error: Couldn't get real device (%s)!\n",
+ __func__, e_dev_name);
+ goto out;
+ }
+
+ /* handle real device's MMIO/PIO BARs */
+ if (assigned_dev_register_regions(pci_dev->real_device.regions,
+ pci_dev->real_device.region_number,
+ pci_dev))
+ goto out;
+
+ /* handle interrupt routing */
+ e_device = (pci_dev->dev.devfn >> 3) & 0x1f;
+ e_intx = pci_dev->dev.config[0x3d] - 1;
+ pci_dev->intpin = e_intx;
+ pci_dev->run = 0;
+ pci_dev->girq = 0;
+ pci_dev->h_busnr = r_bus;
+ pci_dev->h_devfn = PCI_DEVFN(r_dev, r_func);
+
+#ifdef KVM_CAP_DEVICE_ASSIGNMENT
+ if (kvm_enabled()) {
+ struct kvm_assigned_pci_dev assigned_dev_data;
+
+ memset(&assigned_dev_data, 0, sizeof(assigned_dev_data));
+ assigned_dev_data.assigned_dev_id =
+ calc_assigned_dev_id(pci_dev->h_busnr,
+ (uint32_t)pci_dev->h_devfn);
+ assigned_dev_data.busnr = pci_dev->h_busnr;
+ assigned_dev_data.devfn = pci_dev->h_devfn;
+ assigned_dev_data.flags = flags;
+#ifdef KVM_CAP_PV_DMA
+ assigned_dev_data.guest_dev_id =
+ calc_assigned_dev_id(pci_bus_num(e_bus),
+ PCI_DEVFN(e_device, r_func));
+#endif
+
+#ifdef KVM_CAP_IOMMU
+ /* We always enable the IOMMU if present
+ * (or when not disabled on the command line)
+ */
+ r = kvm_check_extension(kvm_context, KVM_CAP_IOMMU);
+ if (r && !disable_iommu)
+ assigned_devices[nr_assigned_devices].dma |=
+ KVM_DEV_ASSIGN_ENABLE_IOMMU;
+#endif
+ r = kvm_assign_pci_device(kvm_context,
+ &assigned_dev_data);
+ if (r < 0) {
+ fprintf(stderr, "Could not notify kernel about "
+ "assigned device \"%s\"\n", e_dev_name);
+ perror("pt-ioctl");
+ goto out;
+ }
+ }
+#endif
+ fprintf(stderr, "Registered host PCI device %02x:%02x.%1x "
+ "(\"%s\") as guest device %02x:%02x.%1x\n",
+ r_bus, r_dev, r_func, e_dev_name,
+ pci_bus_num(e_bus), e_device, r_func);
+
+ return pci_dev;
+out:
+ pci_unregister_device(&pci_dev->dev);
+ return NULL;
+}
+
+extern int get_param_value(char *buf, int buf_size,
+ const char *tag, const char *str);
+extern int piix_get_irq(int);
+
+#ifdef KVM_CAP_DEVICE_ASSIGNMENT
+/* The pci config space got updated. Check if irq numbers have changed
+ * for our devices
+ */
+void assigned_dev_update_irq(PCIDevice *d)
+{
+ int i, irq, r;
+ AssignedDevice *assigned_dev;
+
+ for (i = 0; i < nr_assigned_devices; i++) {
+ assigned_dev = assigned_devices[i].assigned_dev;
+ if (assigned_dev == NULL)
+ continue;
+
+ irq = pci_map_irq(&assigned_dev->dev, assigned_dev->intpin);
+ irq = piix_get_irq(irq);
+
+ if (irq != assigned_dev->girq) {
+ struct kvm_assigned_irq assigned_irq_data;
+
+ memset(&assigned_irq_data, 0, sizeof assigned_irq_data);
+ assigned_irq_data.assigned_dev_id =
+ calc_assigned_dev_id(assigned_dev->h_busnr,
+ (uint8_t)
+ assigned_dev->h_devfn);
+ assigned_irq_data.guest_irq = irq;
+ assigned_irq_data.host_irq =
+ assigned_dev->real_device.irq;
+ r = kvm_assign_irq(kvm_context, &assigned_irq_data);
+ if (r < 0) {
+ perror("assigned_dev_update_irq");
+ fprintf(stderr, "Are you assigning a device "
+ "that shares IRQ with some other "
+ "device?\n");
+ pci_unregister_device(&assigned_dev->dev);
+ continue;
+ }
+ assigned_dev->girq = irq;
+ }
+ }
+}
+#endif
+
+static int init_device_assignment(void)
+{
+ /* Do we have any devices to be assigned? */
+ if (nr_assigned_devices == 0)
+ return -1;
+ iopl(3);
+ return 0;
+}
+
+int init_assigned_device(PCIBus *bus, int *index)
+{
+ AssignedDevice *dev = NULL;
+ int i, ret = 0;
+
+ if (*index == -1) {
+ if (init_device_assignment() < 0)
+ return -1;
+
+ *index = nr_assigned_devices - 1;
+ }
+ i = *index;
+ dev = register_real_device(bus, assigned_devices[i].name, -1,
+ assigned_devices[i].bus,
+ assigned_devices[i].dev,
+ assigned_devices[i].func,
+ assigned_devices[i].dma);
+ if (dev == NULL) {
+ fprintf(stderr, "Error: Couldn't register device \"%s\"\n",
+ assigned_devices[i].name);
+ ret = -1;
+ }
+ assigned_devices[i].assigned_dev = dev;
+
+ --*index;
+ return ret;
+}
+
+/*
+ * Syntax to assign device:
+ *
+ * -pcidevice dev=bus:dev.func,dma=dma
+ *
+ * Example:
+ * -pcidevice dev=00:13.0,dma=pvdma
+ *
+ * dma can currently be 'none' to disable iommu support.
+ */
+void add_assigned_device(const char *arg)
+{
+ char *cp, *cp1;
+ char device[8];
+ char dma[6];
+ int r;
+
+ if (nr_assigned_devices >= MAX_ASSIGNED_DEVS) {
+ fprintf(stderr, "Too many assigned devices (max %d)\n",
+ MAX_ASSIGNED_DEVS);
+ return;
+ }
+ memset(&assigned_devices[nr_assigned_devices], 0,
+ sizeof assigned_devices[nr_assigned_devices]);
+
+ r = get_param_value(device, sizeof device, "host", arg);
+
+ r = get_param_value(assigned_devices[nr_assigned_devices].name,
+ sizeof assigned_devices[nr_assigned_devices].name,
+ "name", arg);
+ if (!r)
+ strncpy(assigned_devices[nr_assigned_devices].name, device, 8);
+
+#ifdef KVM_CAP_IOMMU
+ r = get_param_value(dma, sizeof dma, "dma", arg);
+ if (r && !strncmp(dma, "none", 4))
+ disable_iommu = 1;
+#endif
+ cp = device;
+ assigned_devices[nr_assigned_devices].bus = strtoul(cp, &cp1, 16);
+ if (*cp1 != ':')
+ goto bad;
+ cp = cp1 + 1;
+
+ assigned_devices[nr_assigned_devices].dev = strtoul(cp, &cp1, 16);
+ if (*cp1 != '.')
+ goto bad;
+ cp = cp1 + 1;
+
+ assigned_devices[nr_assigned_devices].func = strtoul(cp, &cp1, 16);
+
+ nr_assigned_devices++;
+ return;
+bad:
+ fprintf(stderr, "pcidevice argument parse error; "
+ "please check the help text for usage\n");
+}
diff --git a/qemu/hw/device-assignment.h b/qemu/hw/device-assignment.h
new file mode 100644
index 0000000..621df82
--- /dev/null
+++ b/qemu/hw/device-assignment.h
@@ -0,0 +1,92 @@
+/*
+ * Copyright (c) 2007, Neocleus Corporation.
+ * Copyright (c) 2007, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along
with
+ * this program; if not, write to the Free Software Foundation, Inc., 59
Temple
+ * Place - Suite 330, Boston, MA 02111-1307 USA.
+ *
+ * Data structures for storing PCI state
+ *
+ * Adapted to kvm by Qumranet
+ *
+ * Copyright (c) 2007, Neocleus, Alex Novik ([EMAIL PROTECTED])
+ * Copyright (c) 2007, Neocleus, Guy Zana ([EMAIL PROTECTED])
+ * Copyright (C) 2008, Qumranet, Amit Shah ([EMAIL PROTECTED])
+ */
+
+#ifndef __DEVICE_ASSIGNMENT_H__
+#define __DEVICE_ASSIGNMENT_H__
+
+#include <sys/mman.h>
+#include "qemu-common.h"
+#include "pci.h"
+#include <linux/types.h>
+
+#define DEVICE_ASSIGNMENT_DEBUG_PIO (0x01)
+#define DEVICE_ASSIGNMENT_DEBUG_MMIO (0x02)
+
+/* From include/linux/pci.h in the kernel sources */
+#define PCI_DEVFN(slot,func) ((((slot) & 0x1f) << 3) | ((func) & 0x07))
+
+typedef uint32_t pciaddr_t;
+
+#define MAX_IO_REGIONS (6)
+
+typedef struct pci_region_s {
+ int type; /* Memory or port I/O */
+ int valid;
+ pciaddr_t base_addr;
+ pciaddr_t size; /* size of the region */
+ int resource_fd;
+} PCIRegion;
+
+typedef struct pci_dev_s {
+ uint8_t bus, dev, func; /* Bus inside domain, device and function */
+ int irq; /* IRQ number */
+ uint16_t region_number; /* number of active regions */
+
+ /* Port I/O or MMIO Regions */
+ PCIRegion regions[MAX_IO_REGIONS];
+ int config_fd;
+} PCIDevRegions;
+
+typedef struct assigned_dev_region_s {
+ target_phys_addr_t e_physbase;
+ uint32_t memory_index;
+ void *r_virtbase; /* mmapped access address */
+ int num; /* our index within v_addrs[] */
+ uint32_t e_size; /* emulated size of region in bytes */
+ uint32_t r_size; /* real size of region in bytes */
+ uint32_t debug;
+} AssignedDevRegion;
+
+typedef struct assigned_dev_s {
+ PCIDevice dev;
+ int intpin;
+ uint8_t debug_flags;
+ AssignedDevRegion v_addrs[PCI_NUM_REGIONS];
+ PCIDevRegions real_device;
+ int run;
+ int girq;
+ unsigned char h_busnr;
+ unsigned int h_devfn;
+ int bound;
+} AssignedDevice;
+
+/* Initialization functions */
+int init_assigned_device(PCIBus *bus, int *index);
+void add_assigned_device(const char *arg);
+void assigned_dev_set_vector(int irq, int vector);
+void assigned_dev_ack_mirq(int vector);
+
+#endif /* __DEVICE_ASSIGNMENT_H__ */
diff --git a/qemu/hw/isa.h b/qemu/hw/isa.h
index 89b3004..c720f5e 100644
--- a/qemu/hw/isa.h
+++ b/qemu/hw/isa.h
@@ -1,5 +1,7 @@
/* ISA bus */
+#include "hw.h"
+
extern target_phys_addr_t isa_mem_base;
int register_ioport_read(int start, int length, int size,
diff --git a/qemu/hw/pc.c b/qemu/hw/pc.c
index 8a50096..59c2098 100644
--- a/qemu/hw/pc.c
+++ b/qemu/hw/pc.c
@@ -32,6 +32,7 @@
#include "smbus.h"
#include "boards.h"
#include "console.h"
+#include "device-assignment.h"
#include "qemu-kvm.h"
@@ -1013,6 +1014,14 @@ static void pc_init1(ram_addr_t ram_size, int
vga_ram_size,
}
}
+ /* Initialize assigned devices */
+ if (pci_enabled) {
+ int r = -1;
+ do {
+ init_assigned_device(pci_bus, &r);
+ } while (r >= 0);
+ }
+
rtc_state = rtc_init(0x70, i8259[8]);
qemu_register_boot_set(pc_boot_set, rtc_state);
diff --git a/qemu/hw/pci.c b/qemu/hw/pci.c
index 07d37a8..e4e8386 100644
--- a/qemu/hw/pci.c
+++ b/qemu/hw/pci.c
@@ -50,6 +50,7 @@ struct PCIBus {
static void pci_update_mappings(PCIDevice *d);
static void pci_set_irq(void *opaque, int irq_num, int level);
+void assigned_dev_update_irq(PCIDevice *d);
target_phys_addr_t pci_mem_base;
static int pci_irq_index;
@@ -453,6 +454,12 @@ void pci_default_write_config(PCIDevice *d,
val >>= 8;
}
+#ifdef KVM_CAP_DEVICE_ASSIGNMENT
+ if (kvm_enabled() && qemu_kvm_irqchip_in_kernel() &&
+ address >= 0x60 && address <= 0x63)
+ assigned_dev_update_irq(d);
+#endif
+
end = address + len;
if (end > PCI_COMMAND && address < (PCI_COMMAND + 2)) {
/* if the command register is modified, we must modify the mappings
*/
@@ -560,6 +567,11 @@ static void pci_set_irq(void *opaque, int irq_num, int
level)
bus->set_irq(bus->irq_opaque, irq_num, bus->irq_count[irq_num] != 0);
}
+int pci_map_irq(PCIDevice *pci_dev, int pin)
+{
+ return pci_dev->bus->map_irq(pci_dev, pin);
+}
+
/***********************************************************/
/* monitor info on PCI */
diff --git a/qemu/hw/pci.h b/qemu/hw/pci.h
index 60e4094..e11fbbf 100644
--- a/qemu/hw/pci.h
+++ b/qemu/hw/pci.h
@@ -81,6 +81,7 @@ void pci_register_io_region(PCIDevice *pci_dev, int
region_num,
uint32_t size, int type,
PCIMapIORegionFunc *map_func);
+int pci_map_irq(PCIDevice *pci_dev, int pin);
uint32_t pci_default_read_config(PCIDevice *d,
uint32_t address, int len);
void pci_default_write_config(PCIDevice *d,
diff --git a/qemu/hw/piix_pci.c b/qemu/hw/piix_pci.c
index 6fbf47b..dc12c8a 100644
--- a/qemu/hw/piix_pci.c
+++ b/qemu/hw/piix_pci.c
@@ -243,6 +243,25 @@ static void piix3_set_irq(qemu_irq *pic, int irq_num, int
level)
}
}
+int piix3_get_pin(int pic_irq)
+{
+ int i;
+ for (i = 0; i < 4; i++)
+ if (piix3_dev->config[0x60+i] == pic_irq)
+ return i;
+ return -1;
+}
+
+int piix_get_irq(int pin)
+{
+ if (piix3_dev)
+ return piix3_dev->config[0x60+pin];
+ if (piix4_dev)
+ return piix4_dev->config[0x60+pin];
+
+ return 0;
+}
+
static void piix3_reset(PCIDevice *d)
{
uint8_t *pci_conf = d->config;
diff --git a/qemu/qemu-kvm-x86.c b/qemu/qemu-kvm-x86.c
index 5daedd1..5123e52 100644
--- a/qemu/qemu-kvm-x86.c
+++ b/qemu/qemu-kvm-x86.c
@@ -530,6 +530,9 @@ struct kvm_para_features {
#ifdef KVM_CAP_CR3_CACHE
{ KVM_CAP_CR3_CACHE, KVM_FEATURE_CR3_CACHE },
#endif
+#ifdef KVM_CAP_PV_DMA
+ { KVM_CAP_PV_DMA, KVM_FEATURE_DMA_OP },
+#endif
{ -1, -1 }
};
diff --git a/qemu/vl.c b/qemu/vl.c
index 022b3b8..bab720d 100644
--- a/qemu/vl.c
+++ b/qemu/vl.c
@@ -37,6 +37,7 @@
#include "qemu-char.h"
#include "block.h"
#include "audio/audio.h"
+#include "hw/device-assignment.h"
#include "migration.h"
#include "balloon.h"
#include "qemu-kvm.h"
@@ -8478,6 +8479,12 @@ static void help(int exitcode)
#endif
"-no-kvm-irqchip disable KVM kernel mode PIC/IOAPIC/LAPIC\n"
"-no-kvm-pit disable KVM kernel mode PIT\n"
+#if defined(TARGET_I386) || defined(TARGET_X86_64)
+ "-pcidevice host=bus:dev.func[,dma=none][,name=\"string\"]\n"
+ " expose a PCI device to the guest OS.\n"
+ " dma=none: don't perform any dma translations
(default is
to use an iommu)\n"
+ " 'string' is used in log output.\n"
+#endif
#endif
#ifdef TARGET_I386
"-std-vga simulate a standard VGA card with VESA Bochs
Extensions\n"
@@ -8601,6 +8608,9 @@ enum {
QEMU_OPTION_no_kvm,
QEMU_OPTION_no_kvm_irqchip,
QEMU_OPTION_no_kvm_pit,
+#if defined(TARGET_I386) || defined(TARGET_X86_64)
+ QEMU_OPTION_pcidevice,
+#endif
QEMU_OPTION_no_reboot,
QEMU_OPTION_no_shutdown,
QEMU_OPTION_show_cursor,
@@ -8689,6 +8699,9 @@ const QEMUOption qemu_options[] = {
#endif
{ "no-kvm-irqchip", 0, QEMU_OPTION_no_kvm_irqchip },
{ "no-kvm-pit", 0, QEMU_OPTION_no_kvm_pit },
+#if defined(TARGET_I386) || defined(TARGET_X86_64)
+ { "pcidevice", HAS_ARG, QEMU_OPTION_pcidevice },
+#endif
#endif
#if defined(TARGET_PPC) || defined(TARGET_SPARC)
{ "g", 1, QEMU_OPTION_g },
@@ -9595,6 +9608,11 @@ int main(int argc, char **argv)
kvm_pit = 0;
break;
}
+#if defined(TARGET_I386) || defined(TARGET_X86_64)
+ case QEMU_OPTION_pcidevice:
+ add_assigned_device(optarg);
+ break;
+#endif
#endif
case QEMU_OPTION_usb:
usb_enabled = 1;
--
1.5.4.3
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to [EMAIL PROTECTED]
More majordomo info at http://vger.kernel.org/majordomo-info.html
