linux/drivers/xen/xen-pciback/conf_space.h
Marek Marczykowski-Górecki 476878e4b2 xen-pciback: optionally allow interrupt enable flag writes
QEMU running in a stubdom needs to be able to set INTX_DISABLE, and the
MSI(-X) enable flags in the PCI config space. This adds an attribute
'allow_interrupt_control' which when set for a PCI device allows writes
to this flag(s). The toolstack will need to set this for stubdoms.
When enabled, guest (stubdomain) will be allowed to set relevant enable
flags, but only one at a time - i.e. it refuses to enable more than one
of INTx, MSI, MSI-X at a time.

This functionality is needed only for config space access done by device
model (stubdomain) serving a HVM with the actual PCI device. It is not
necessary and unsafe to enable direct access to those bits for PV domain
with the device attached. For PV domains, there are separate protocol
messages (XEN_PCI_OP_{enable,disable}_{msi,msix}) for this purpose.
Those ops in addition to setting enable bits, also configure MSI(-X) in
dom0 kernel - which is undesirable for PCI passthrough to HVM guests.

This should not introduce any new security issues since a malicious
guest (or stubdom) can already generate MSIs through other ways, see
[1] page 8. Additionally, when qemu runs in dom0, it already have direct
access to those bits.

This is the second iteration of this feature. First was proposed as a
direct Xen interface through a new hypercall, but ultimately it was
rejected by the maintainer, because of mixing pciback and hypercalls for
PCI config space access isn't a good design. Full discussion at [2].

[1]: https://invisiblethingslab.com/resources/2011/Software%20Attacks%20on%20Intel%20VT-d.pdf
[2]: https://xen.markmail.org/thread/smpgpws4umdzizze

[part of the commit message and sysfs handling]
Signed-off-by: Simon Gaiser <simon@invisiblethingslab.com>
[the rest]
Signed-off-by: Marek Marczykowski-Górecki <marmarek@invisiblethingslab.com>
Reviewed-by: Roger Pau Monné <roger.pau@citrix.com>
[boris: A few small changes suggested by Roger, some formatting changes]
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
2020-01-15 16:50:13 -06:00

137 lines
4.0 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
/*
* PCI Backend - Common data structures for overriding the configuration space
*
* Author: Ryan Wilson <hap9@epoch.ncsc.mil>
*/
#ifndef __XEN_PCIBACK_CONF_SPACE_H__
#define __XEN_PCIBACK_CONF_SPACE_H__
#include <linux/list.h>
#include <linux/err.h>
/* conf_field_init can return an errno in a ptr with ERR_PTR() */
typedef void *(*conf_field_init) (struct pci_dev *dev, int offset);
typedef void (*conf_field_reset) (struct pci_dev *dev, int offset, void *data);
typedef void (*conf_field_free) (struct pci_dev *dev, int offset, void *data);
typedef int (*conf_dword_write) (struct pci_dev *dev, int offset, u32 value,
void *data);
typedef int (*conf_word_write) (struct pci_dev *dev, int offset, u16 value,
void *data);
typedef int (*conf_byte_write) (struct pci_dev *dev, int offset, u8 value,
void *data);
typedef int (*conf_dword_read) (struct pci_dev *dev, int offset, u32 *value,
void *data);
typedef int (*conf_word_read) (struct pci_dev *dev, int offset, u16 *value,
void *data);
typedef int (*conf_byte_read) (struct pci_dev *dev, int offset, u8 *value,
void *data);
/* These are the fields within the configuration space which we
* are interested in intercepting reads/writes to and changing their
* values.
*/
struct config_field {
unsigned int offset;
unsigned int size;
unsigned int mask;
conf_field_init init;
conf_field_reset reset;
conf_field_free release;
void (*clean) (struct config_field *field);
union {
struct {
conf_dword_write write;
conf_dword_read read;
} dw;
struct {
conf_word_write write;
conf_word_read read;
} w;
struct {
conf_byte_write write;
conf_byte_read read;
} b;
} u;
struct list_head list;
};
struct config_field_entry {
struct list_head list;
const struct config_field *field;
unsigned int base_offset;
void *data;
};
#define INTERRUPT_TYPE_NONE (1<<0)
#define INTERRUPT_TYPE_INTX (1<<1)
#define INTERRUPT_TYPE_MSI (1<<2)
#define INTERRUPT_TYPE_MSIX (1<<3)
extern bool xen_pcibk_permissive;
#define OFFSET(cfg_entry) ((cfg_entry)->base_offset+(cfg_entry)->field->offset)
/* Add fields to a device - the add_fields macro expects to get a pointer to
* the first entry in an array (of which the ending is marked by size==0)
*/
int xen_pcibk_config_add_field_offset(struct pci_dev *dev,
const struct config_field *field,
unsigned int offset);
static inline int xen_pcibk_config_add_field(struct pci_dev *dev,
const struct config_field *field)
{
return xen_pcibk_config_add_field_offset(dev, field, 0);
}
static inline int xen_pcibk_config_add_fields(struct pci_dev *dev,
const struct config_field *field)
{
int i, err = 0;
for (i = 0; field[i].size != 0; i++) {
err = xen_pcibk_config_add_field(dev, &field[i]);
if (err)
break;
}
return err;
}
static inline int xen_pcibk_config_add_fields_offset(struct pci_dev *dev,
const struct config_field *field,
unsigned int offset)
{
int i, err = 0;
for (i = 0; field[i].size != 0; i++) {
err = xen_pcibk_config_add_field_offset(dev, &field[i], offset);
if (err)
break;
}
return err;
}
/* Read/Write the real configuration space */
int xen_pcibk_read_config_byte(struct pci_dev *dev, int offset, u8 *value,
void *data);
int xen_pcibk_read_config_word(struct pci_dev *dev, int offset, u16 *value,
void *data);
int xen_pcibk_read_config_dword(struct pci_dev *dev, int offset, u32 *value,
void *data);
int xen_pcibk_write_config_byte(struct pci_dev *dev, int offset, u8 value,
void *data);
int xen_pcibk_write_config_word(struct pci_dev *dev, int offset, u16 value,
void *data);
int xen_pcibk_write_config_dword(struct pci_dev *dev, int offset, u32 value,
void *data);
int xen_pcibk_config_capability_init(void);
int xen_pcibk_config_header_add_fields(struct pci_dev *dev);
int xen_pcibk_config_capability_add_fields(struct pci_dev *dev);
int xen_pcibk_get_interrupt_type(struct pci_dev *dev);
#endif /* __XEN_PCIBACK_CONF_SPACE_H__ */