RE: [PATCH 1/2] KVM/userspace: Support for assigning PCI devices to guest
On Thu, 2008-07-17 at 15:52 +0800, Han, Weidong wrote:
Ben-Ami Yassour wrote:
From: Or Sagi [EMAIL PROTECTED]
From: Nir Peleg [EMAIL PROTECTED]
From: Amit Shah [EMAIL PROTECTED]
From: Glauber de Oliveira Costa [EMAIL PROTECTED]
We can assign a device from the host machine to a guest. The
original code comes from Neocleus.
A new command-line option, -pcidevice is added.
For example, to invoke it for an Ethernet device sitting at
PCI bus:dev.fn 04:08.0 with host IRQ 18, use this:
-pcidevice Ethernet/04:08.0
The host ethernet driver is to be removed before doing the
passthrough. If not, the device assignment fails but the
guest continues without the assignment.
If kvm uses the in-kernel irqchip, interrupts are routed to the
guest via the kvm module (accompanied kernel changes are necessary).
If -no-kvm-irqchip is used, the 'irqhook' module, available
separately, is to be used for interrupt injection into the guest. In
this case, an extra parameter, -intr-number is to be appended to
the above-mentioned pcidevice parameter.
Signed-off-by: Amit Shah [EMAIL PROTECTED]
---
+static pt_dev_t *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 rc;
+ pt_dev_t *pci_dev;
+ uint8_t e_device, e_intx;
+
+ DEBUG(register_real_device: Registering real physical
+ device %s (devfn=0x%x)\n, e_dev_name, e_devfn);
+
+ pci_dev = (pt_dev_t *) pci_register_device(e_bus, e_dev_name,
+ sizeof(pt_dev_t),
e_devfn,
+ pt_pci_read_config,
+ pt_pci_write_config);
+
+ if (NULL == pci_dev) {
+ fprintf(stderr, register_real_device: Error: Couldn't
+ register real device %s\n, e_dev_name);
+ return NULL;
+ }
+ if (pt_get_real_device(pci_dev, r_bus, r_dev, r_func)) {
+ fprintf(stderr, register_real_device: Error: Couldn't
get
+ real device (%s)!\n, e_dev_name);
+ return NULL;
+ }
+
+ /* handle real device's MMIO/PIO BARs */
+ if (pt_register_regions(pci_dev-real_device.regions,
+ pci_dev-real_device.region_number,
pci_dev))
+ return NULL;
+
+ /* 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_PCI_PASSTHROUGH
+ if (kvm_enabled()) {
+ struct kvm_pci_passthrough_dev pci_pt_dev;
+
+ memset(pci_pt_dev, 0, sizeof(pci_pt_dev));
+ pci_pt_dev.guest.busnr = pci_bus_num(e_bus);
+ pci_pt_dev.guest.devfn = PCI_DEVFN(e_device, r_func);
Why combine e_device and r_func? The guest devfn is e_devfn.
the current assumption is that e_func and r_func are identical.
+ pci_pt_dev.host.busnr = pci_dev-h_busnr;
+ pci_pt_dev.host.devfn = pci_dev-h_devfn;
+
+ /* We'll set the value of the guest irq as and when
+* the piix config gets updated. See pci_pt_update_irq.
+* The host irq field never gets used anyway
+*/
+
+ rc = kvm_update_pci_pt_device(kvm_context, pci_pt_dev);
+ if (rc 0) {
+ fprintf(stderr, Could not notify kernel about
+ passthrough device\n);
+ perror(pt-ioctl);
+ return NULL;
+ }
+ }
+#endif
+
+ fprintf(logfile, Registered host PCI device %02x:%02x.%1x
+ as guest device %02x:%02x.%1x\n,
+ r_bus, r_dev, r_func,
+ pci_bus_num(e_bus), e_device, r_func);
Second r_func should replaced by e_devfn 0x7.
same as above.
Randy (Weidong)
--
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
RE: [PATCH 1/2] KVM/userspace: Support for assigning PCI devices to guest
Ben-Ami Yassour wrote:
From: Or Sagi [EMAIL PROTECTED]
From: Nir Peleg [EMAIL PROTECTED]
From: Amit Shah [EMAIL PROTECTED]
From: Glauber de Oliveira Costa [EMAIL PROTECTED]
We can assign a device from the host machine to a guest. The
original code comes from Neocleus.
A new command-line option, -pcidevice is added.
For example, to invoke it for an Ethernet device sitting at
PCI bus:dev.fn 04:08.0 with host IRQ 18, use this:
-pcidevice Ethernet/04:08.0
The host ethernet driver is to be removed before doing the
passthrough. If not, the device assignment fails but the
guest continues without the assignment.
If kvm uses the in-kernel irqchip, interrupts are routed to the
guest via the kvm module (accompanied kernel changes are necessary).
If -no-kvm-irqchip is used, the 'irqhook' module, available
separately, is to be used for interrupt injection into the guest. In
this case, an extra parameter, -intr-number is to be appended to
the above-mentioned pcidevice parameter.
Signed-off-by: Amit Shah [EMAIL PROTECTED]
---
+static pt_dev_t *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 rc;
+ pt_dev_t *pci_dev;
+ uint8_t e_device, e_intx;
+
+ DEBUG(register_real_device: Registering real physical
+ device %s (devfn=0x%x)\n, e_dev_name, e_devfn);
+
+ pci_dev = (pt_dev_t *) pci_register_device(e_bus, e_dev_name,
+sizeof(pt_dev_t),
e_devfn,
+pt_pci_read_config,
+pt_pci_write_config);
+
+ if (NULL == pci_dev) {
+ fprintf(stderr, register_real_device: Error: Couldn't
+ register real device %s\n, e_dev_name);
+ return NULL;
+ }
+ if (pt_get_real_device(pci_dev, r_bus, r_dev, r_func)) {
+ fprintf(stderr, register_real_device: Error: Couldn't
get
+ real device (%s)!\n, e_dev_name);
+ return NULL;
+ }
+
+ /* handle real device's MMIO/PIO BARs */
+ if (pt_register_regions(pci_dev-real_device.regions,
+ pci_dev-real_device.region_number,
pci_dev))
+ return NULL;
+
+ /* 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_PCI_PASSTHROUGH
+ if (kvm_enabled()) {
+ struct kvm_pci_passthrough_dev pci_pt_dev;
+
+ memset(pci_pt_dev, 0, sizeof(pci_pt_dev));
+ pci_pt_dev.guest.busnr = pci_bus_num(e_bus);
+ pci_pt_dev.guest.devfn = PCI_DEVFN(e_device, r_func);
Why combine e_device and r_func? The guest devfn is e_devfn.
+ pci_pt_dev.host.busnr = pci_dev-h_busnr;
+ pci_pt_dev.host.devfn = pci_dev-h_devfn;
+
+ /* We'll set the value of the guest irq as and when
+ * the piix config gets updated. See pci_pt_update_irq.
+ * The host irq field never gets used anyway
+ */
+
+ rc = kvm_update_pci_pt_device(kvm_context, pci_pt_dev);
+ if (rc 0) {
+ fprintf(stderr, Could not notify kernel about
+ passthrough device\n);
+ perror(pt-ioctl);
+ return NULL;
+ }
+ }
+#endif
+
+ fprintf(logfile, Registered host PCI device %02x:%02x.%1x
+ as guest device %02x:%02x.%1x\n,
+ r_bus, r_dev, r_func,
+ pci_bus_num(e_bus), e_device, r_func);
Second r_func should replaced by e_devfn 0x7.
Randy (Weidong)
--
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
[PATCH 1/2] KVM/userspace: Support for assigning PCI devices to guest
From: Or Sagi [EMAIL PROTECTED]
From: Nir Peleg [EMAIL PROTECTED]
From: Amit Shah [EMAIL PROTECTED]
From: Glauber de Oliveira Costa [EMAIL PROTECTED]
We can assign a device from the host machine to a guest. The
original code comes from Neocleus.
A new command-line option, -pcidevice is added.
For example, to invoke it for an Ethernet device sitting at
PCI bus:dev.fn 04:08.0 with host IRQ 18, use this:
-pcidevice Ethernet/04:08.0
The host ethernet driver is to be removed before doing the
passthrough. If not, the device assignment fails but the
guest continues without the assignment.
If kvm uses the in-kernel irqchip, interrupts are routed to the
guest via the kvm module (accompanied kernel changes are necessary).
If -no-kvm-irqchip is used, the 'irqhook' module, available
separately, is to be used for interrupt injection into the guest. In
this case, an extra parameter, -intr-number is to be appended to
the above-mentioned pcidevice parameter.
Signed-off-by: Amit Shah [EMAIL PROTECTED]
---
libkvm/libkvm-x86.c |9 +-
libkvm/libkvm.h | 16 ++
qemu/Makefile.target |1 +
qemu/hw/isa.h |2 +
qemu/hw/pc.c |9 +
qemu/hw/pci-passthrough.c | 594 +
qemu/hw/pci-passthrough.h | 93 +++
qemu/hw/pci.c | 12 +
qemu/hw/pci.h |1 +
qemu/hw/piix_pci.c| 19 ++
qemu/vl.c | 17 ++
11 files changed, 772 insertions(+), 1 deletions(-)
create mode 100644 qemu/hw/pci-passthrough.c
create mode 100644 qemu/hw/pci-passthrough.h
diff --git a/libkvm/libkvm-x86.c b/libkvm/libkvm-x86.c
index ea97bdd..0c4cdbe 100644
--- a/libkvm/libkvm-x86.c
+++ b/libkvm/libkvm-x86.c
@@ -126,6 +126,14 @@ static int kvm_init_tss(kvm_context_t kvm)
return 0;
}
+#ifdef KVM_CAP_PCI_PASSTHROUGH
+int kvm_update_pci_pt_device(kvm_context_t kvm,
+struct kvm_pci_passthrough_dev *pci_pt_dev)
+{
+ return ioctl(kvm-vm_fd, KVM_UPDATE_PCI_PT_DEV, pci_pt_dev);
+}
+#endif
+
int kvm_arch_create_default_phys_mem(kvm_context_t kvm,
unsigned long phys_mem_bytes,
void **vm_mem)
@@ -435,7 +443,6 @@ void kvm_show_code(kvm_context_t kvm, int vcpu)
fprintf(stderr, code:%s\n, code_str);
}
-
/*
* Returns available msr list. User must free.
*/
diff --git a/libkvm/libkvm.h b/libkvm/libkvm.h
index ad6e26a..ccb086f 100644
--- a/libkvm/libkvm.h
+++ b/libkvm/libkvm.h
@@ -12,6 +12,7 @@
#endif
#include linux/kvm.h
+#include linux/kvm_para.h
#include signal.h
@@ -639,4 +640,19 @@ int kvm_enable_vapic(kvm_context_t kvm, int vcpu, uint64_t
vapic);
#endif
+#ifdef KVM_CAP_PCI_PASSTHROUGH
+/*!
+ * \brief Notifies host kernel about changes to 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 and the guest
+ * PCI parameters or updates to the PCI config space from the guest
+ * (mainly the device irq)
+ *
+ * \param kvm Pointer to the current kvm_context
+ * \param pci_pt_dev Parameters like irq, PCI bus, devfn number, etc
+ */
+int kvm_update_pci_pt_device(kvm_context_t kvm,
+struct kvm_pci_passthrough_dev *pci_pt_dev);
+#endif
#endif
diff --git a/qemu/Makefile.target b/qemu/Makefile.target
index 77b2301..432011f 100644
--- a/qemu/Makefile.target
+++ b/qemu/Makefile.target
@@ -602,6 +602,7 @@ OBJS+= ide.o pckbd.o ps2.o vga.o $(SOUND_HW) dma.o
OBJS+= fdc.o mc146818rtc.o serial.o i8259.o i8254.o pcspk.o pc.o
OBJS+= cirrus_vga.o apic.o parallel.o acpi.o piix_pci.o
OBJS+= usb-uhci.o vmmouse.o vmport.o vmware_vga.o extboot.o
+OBJS+= pci-passthrough.o
ifeq ($(USE_KVM_PIT), 1)
OBJS+= i8254-kvm.o
endif
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 6334c76..0b0606a 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 pci-passthrough.h
#include qemu-kvm.h
@@ -995,6 +996,14 @@ static void pc_init1(ram_addr_t ram_size, int vga_ram_size,
}
}
+/* Initialize pass-through */
+if (pci_enabled) {
+int r = -1;
+do {
+pt_init_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-passthrough.c b/qemu/hw/pci-passthrough.c
new file mode 100644
index 000..250d7ef
--- /dev/null
+++ b/qemu/hw/pci-passthrough.c
@@ -0,0 +1,594 @@
+/*
+ * Copyright (c) 2007, Neocleus Corporation.
+ *
+ * This program is free software; you
