freebsd-nq/usr.sbin/bhyve/inout.c

302 lines
7.0 KiB
C
Raw Normal View History

/*-
* SPDX-License-Identifier: BSD-2-Clause-FreeBSD
*
* Copyright (c) 2011 NetApp, Inc.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
*
* THIS SOFTWARE IS PROVIDED BY NETAPP, INC ``AS IS'' AND
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL NETAPP, INC OR CONTRIBUTORS BE LIABLE
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
*
* $FreeBSD$
*/
#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");
#include <sys/param.h>
#include <sys/linker_set.h>
#include <sys/_iovec.h>
#include <sys/mman.h>
#include <x86/psl.h>
#include <x86/segments.h>
#include <machine/vmm.h>
#include <machine/vmm_instruction_emul.h>
#include <vmmapi.h>
#include <stdio.h>
#include <string.h>
#include <assert.h>
#include "bhyverun.h"
Refactor configuration management in bhyve. Replace the existing ad-hoc configuration via various global variables with a small database of key-value pairs. The database supports heirarchical keys using a MIB-like syntax to name the path to a given key. Values are always stored as strings. The API used to manage configuation values does include wrappers to handling boolean values. Other values use non-string types require parsing by consumers. The configuration values are stored in a tree using nvlists. Leaf nodes hold string values. Configuration values are permitted to reference other configuration values using '%(name)'. This permits constructing template configurations. All existing command line arguments now set configuration values. For devices, the "-s" option parses its option argument to generate a list of key-value pairs for the given device. A new '-o' command line option permits setting an individual configuration variable. The key name is always given as a full path of dot-separated components. A new '-k' command line option parses a simple configuration file. This configuration file holds a flat list of 'key=value' lines where the 'key' is the full path of a configuration variable. Lines starting with a '#' are comments. In general, bhyve starts by parsing command line options in sequence and applying those settings to configuration values. Once this is complete, bhyve then begins initializing its state based on the configuration values. This means that subsequent configuration options or files may override or supplement previously given settings. A special 'config.dump' configuration value can be set to true to help debug configuration issues. When this value is set, bhyve will print out the configuration variables as a flat list of 'key=value' lines. Most command line argments map to a single configuration variable, e.g. '-w' sets the 'x86.strictmsr' value to false. A few command line arguments have less obvious effects: - Multiple '-p' options append their values (as a comma-seperated list) to "vcpu.N.cpuset" values (where N is a decimal vcpu number). - For '-s' options, a pci.<bus>.<slot>.<function> node is created. The first argument to '-s' (the device type) is used as the value of a "device" variable. Additional comma-separated arguments are then parsed into 'key=value' pairs and used to set additional variables under the device node. A PCI device emulation driver can provide its own hook to override the parsing of the additonal '-s' arguments after the device type. After the configuration phase as completed, the init_pci hook then walks the "pci.<bus>.<slot>.<func>" nodes. It uses the "device" value to find the device model to use. The device model's init routine is passed a reference to its nvlist node in the configuration tree which it can query for specific variables. The result is that a lot of the string parsing is removed from the device models and centralized. In addition, adding a new variable just requires teaching the model to look for the new variable. - For '-l' options, a similar model is used where the string is parsed into values that are later read during initialization. One key note here is that the serial ports use the commonly used lowercase names from existing documentation and examples (e.g. "lpc.com1") instead of the uppercase names previously used internally in bhyve. Reviewed by: grehan MFC after: 3 months Differential Revision: https://reviews.freebsd.org/D26035
2019-06-26 20:30:41 +00:00
#include "config.h"
#include "inout.h"
SET_DECLARE(inout_port_set, struct inout_port);
#define MAX_IOPORTS (1 << 16)
#define VERIFY_IOPORT(port, size) \
assert((port) >= 0 && (size) > 0 && ((port) + (size)) <= MAX_IOPORTS)
static struct {
const char *name;
int flags;
inout_func_t handler;
void *arg;
} inout_handlers[MAX_IOPORTS];
static int
default_inout(struct vmctx *ctx, int vcpu, int in, int port, int bytes,
uint32_t *eax, void *arg)
{
if (in) {
switch (bytes) {
case 4:
*eax = 0xffffffff;
break;
case 2:
*eax = 0xffff;
break;
case 1:
*eax = 0xff;
break;
}
}
return (0);
}
static void
register_default_iohandler(int start, int size)
{
struct inout_port iop;
VERIFY_IOPORT(start, size);
bzero(&iop, sizeof(iop));
iop.name = "default";
iop.port = start;
iop.size = size;
Add support for PCI-to-ISA LPC bridge emulation. If the LPC bus is attached to a virtual machine then we implicitly create COM1 and COM2 ISA devices. Prior to this change the only way of attaching a COM port to the virtual machine was by presenting it as a PCI device that is mapped at the legacy I/O address 0x3F8 or 0x2F8. There were some issues with the original approach: - It did not work at all with UEFI because UEFI will reprogram the PCI device BARs and remap the COM1/COM2 ports at non-legacy addresses. - OpenBSD GENERIC kernel does not create a /dev/console because it expects the uart device at the legacy 0x3F8/0x2F8 address to be an ISA device. - It was functional with a FreeBSD guest but caused the console to appear on /dev/ttyu2 which was not intuitive. The uart emulation is now independent of the bus on which it resides. Thus it is possible to have uart devices on the PCI bus in addition to the legacy COM1/COM2 devices behind the LPC bus. The command line option to attach ISA COM1/COM2 ports to a virtual machine is "-s <bus>,lpc -l com1,stdio". The command line option to create a PCI-attached uart device is: "-s <bus>,uart[,stdio]" The command line option to create PCI-attached COM1/COM2 device is: "-S <bus>,uart[,stdio]". This style of creating COM ports is deprecated. Discussed with: grehan Reviewed by: grehan Submitted by: Tycho Nightingale (tycho.nightingale@pluribusnetworks.com) M share/examples/bhyve/vmrun.sh AM usr.sbin/bhyve/legacy_irq.c AM usr.sbin/bhyve/legacy_irq.h M usr.sbin/bhyve/Makefile AM usr.sbin/bhyve/uart_emul.c M usr.sbin/bhyve/bhyverun.c AM usr.sbin/bhyve/uart_emul.h M usr.sbin/bhyve/pci_uart.c M usr.sbin/bhyve/pci_emul.c M usr.sbin/bhyve/inout.c M usr.sbin/bhyve/pci_emul.h M usr.sbin/bhyve/inout.h AM usr.sbin/bhyve/pci_lpc.c AM usr.sbin/bhyve/pci_lpc.h
2013-10-29 00:18:11 +00:00
iop.flags = IOPORT_F_INOUT | IOPORT_F_DEFAULT;
iop.handler = default_inout;
register_inout(&iop);
}
int
Refactor configuration management in bhyve. Replace the existing ad-hoc configuration via various global variables with a small database of key-value pairs. The database supports heirarchical keys using a MIB-like syntax to name the path to a given key. Values are always stored as strings. The API used to manage configuation values does include wrappers to handling boolean values. Other values use non-string types require parsing by consumers. The configuration values are stored in a tree using nvlists. Leaf nodes hold string values. Configuration values are permitted to reference other configuration values using '%(name)'. This permits constructing template configurations. All existing command line arguments now set configuration values. For devices, the "-s" option parses its option argument to generate a list of key-value pairs for the given device. A new '-o' command line option permits setting an individual configuration variable. The key name is always given as a full path of dot-separated components. A new '-k' command line option parses a simple configuration file. This configuration file holds a flat list of 'key=value' lines where the 'key' is the full path of a configuration variable. Lines starting with a '#' are comments. In general, bhyve starts by parsing command line options in sequence and applying those settings to configuration values. Once this is complete, bhyve then begins initializing its state based on the configuration values. This means that subsequent configuration options or files may override or supplement previously given settings. A special 'config.dump' configuration value can be set to true to help debug configuration issues. When this value is set, bhyve will print out the configuration variables as a flat list of 'key=value' lines. Most command line argments map to a single configuration variable, e.g. '-w' sets the 'x86.strictmsr' value to false. A few command line arguments have less obvious effects: - Multiple '-p' options append their values (as a comma-seperated list) to "vcpu.N.cpuset" values (where N is a decimal vcpu number). - For '-s' options, a pci.<bus>.<slot>.<function> node is created. The first argument to '-s' (the device type) is used as the value of a "device" variable. Additional comma-separated arguments are then parsed into 'key=value' pairs and used to set additional variables under the device node. A PCI device emulation driver can provide its own hook to override the parsing of the additonal '-s' arguments after the device type. After the configuration phase as completed, the init_pci hook then walks the "pci.<bus>.<slot>.<func>" nodes. It uses the "device" value to find the device model to use. The device model's init routine is passed a reference to its nvlist node in the configuration tree which it can query for specific variables. The result is that a lot of the string parsing is removed from the device models and centralized. In addition, adding a new variable just requires teaching the model to look for the new variable. - For '-l' options, a similar model is used where the string is parsed into values that are later read during initialization. One key note here is that the serial ports use the commonly used lowercase names from existing documentation and examples (e.g. "lpc.com1") instead of the uppercase names previously used internally in bhyve. Reviewed by: grehan MFC after: 3 months Differential Revision: https://reviews.freebsd.org/D26035
2019-06-26 20:30:41 +00:00
emulate_inout(struct vmctx *ctx, int vcpu, struct vm_exit *vmexit)
{
int addrsize, bytes, flags, in, port, prot, rep;
uint32_t eax, val;
inout_func_t handler;
void *arg;
int error, fault, retval;
enum vm_reg_name idxreg;
uint64_t gla, index, iterations, count;
struct vm_inout_str *vis;
struct iovec iov[2];
bytes = vmexit->u.inout.bytes;
in = vmexit->u.inout.in;
port = vmexit->u.inout.port;
assert(port < MAX_IOPORTS);
assert(bytes == 1 || bytes == 2 || bytes == 4);
handler = inout_handlers[port].handler;
Refactor configuration management in bhyve. Replace the existing ad-hoc configuration via various global variables with a small database of key-value pairs. The database supports heirarchical keys using a MIB-like syntax to name the path to a given key. Values are always stored as strings. The API used to manage configuation values does include wrappers to handling boolean values. Other values use non-string types require parsing by consumers. The configuration values are stored in a tree using nvlists. Leaf nodes hold string values. Configuration values are permitted to reference other configuration values using '%(name)'. This permits constructing template configurations. All existing command line arguments now set configuration values. For devices, the "-s" option parses its option argument to generate a list of key-value pairs for the given device. A new '-o' command line option permits setting an individual configuration variable. The key name is always given as a full path of dot-separated components. A new '-k' command line option parses a simple configuration file. This configuration file holds a flat list of 'key=value' lines where the 'key' is the full path of a configuration variable. Lines starting with a '#' are comments. In general, bhyve starts by parsing command line options in sequence and applying those settings to configuration values. Once this is complete, bhyve then begins initializing its state based on the configuration values. This means that subsequent configuration options or files may override or supplement previously given settings. A special 'config.dump' configuration value can be set to true to help debug configuration issues. When this value is set, bhyve will print out the configuration variables as a flat list of 'key=value' lines. Most command line argments map to a single configuration variable, e.g. '-w' sets the 'x86.strictmsr' value to false. A few command line arguments have less obvious effects: - Multiple '-p' options append their values (as a comma-seperated list) to "vcpu.N.cpuset" values (where N is a decimal vcpu number). - For '-s' options, a pci.<bus>.<slot>.<function> node is created. The first argument to '-s' (the device type) is used as the value of a "device" variable. Additional comma-separated arguments are then parsed into 'key=value' pairs and used to set additional variables under the device node. A PCI device emulation driver can provide its own hook to override the parsing of the additonal '-s' arguments after the device type. After the configuration phase as completed, the init_pci hook then walks the "pci.<bus>.<slot>.<func>" nodes. It uses the "device" value to find the device model to use. The device model's init routine is passed a reference to its nvlist node in the configuration tree which it can query for specific variables. The result is that a lot of the string parsing is removed from the device models and centralized. In addition, adding a new variable just requires teaching the model to look for the new variable. - For '-l' options, a similar model is used where the string is parsed into values that are later read during initialization. One key note here is that the serial ports use the commonly used lowercase names from existing documentation and examples (e.g. "lpc.com1") instead of the uppercase names previously used internally in bhyve. Reviewed by: grehan MFC after: 3 months Differential Revision: https://reviews.freebsd.org/D26035
2019-06-26 20:30:41 +00:00
if (handler == default_inout &&
get_config_bool_default("x86.strictio", false))
return (-1);
flags = inout_handlers[port].flags;
arg = inout_handlers[port].arg;
if (in) {
if (!(flags & IOPORT_F_IN))
return (-1);
} else {
if (!(flags & IOPORT_F_OUT))
return (-1);
}
retval = 0;
if (vmexit->u.inout.string) {
vis = &vmexit->u.inout_str;
rep = vis->inout.rep;
addrsize = vis->addrsize;
prot = in ? PROT_WRITE : PROT_READ;
assert(addrsize == 2 || addrsize == 4 || addrsize == 8);
/* Index register */
idxreg = in ? VM_REG_GUEST_RDI : VM_REG_GUEST_RSI;
index = vis->index & vie_size2mask(addrsize);
/* Count register */
count = vis->count & vie_size2mask(addrsize);
/* Limit number of back-to-back in/out emulations to 16 */
iterations = MIN(count, 16);
while (iterations > 0) {
assert(retval == 0);
if (vie_calculate_gla(vis->paging.cpu_mode,
vis->seg_name, &vis->seg_desc, index, bytes,
addrsize, prot, &gla)) {
vm_inject_gp(ctx, vcpu);
break;
}
error = vm_copy_setup(ctx, vcpu, &vis->paging, gla,
bytes, prot, iov, nitems(iov), &fault);
if (error) {
retval = -1; /* Unrecoverable error */
break;
} else if (fault) {
retval = 0; /* Resume guest to handle fault */
break;
}
if (vie_alignment_check(vis->paging.cpl, bytes,
vis->cr0, vis->rflags, gla)) {
vm_inject_ac(ctx, vcpu, 0);
break;
}
val = 0;
if (!in)
vm_copyin(ctx, vcpu, iov, &val, bytes);
retval = handler(ctx, vcpu, in, port, bytes, &val, arg);
if (retval != 0)
break;
if (in)
vm_copyout(ctx, vcpu, &val, iov, bytes);
/* Update index */
if (vis->rflags & PSL_D)
index -= bytes;
else
index += bytes;
count--;
iterations--;
}
/* Update index register */
error = vie_update_register(ctx, vcpu, idxreg, index, addrsize);
assert(error == 0);
/*
* Update count register only if the instruction had a repeat
* prefix.
*/
if (rep) {
error = vie_update_register(ctx, vcpu, VM_REG_GUEST_RCX,
count, addrsize);
assert(error == 0);
}
/* Restart the instruction if more iterations remain */
if (retval == 0 && count != 0) {
error = vm_restart_instruction(ctx, vcpu);
assert(error == 0);
}
} else {
eax = vmexit->u.inout.eax;
val = eax & vie_size2mask(bytes);
retval = handler(ctx, vcpu, in, port, bytes, &val, arg);
if (retval == 0 && in) {
eax &= ~vie_size2mask(bytes);
eax |= val & vie_size2mask(bytes);
error = vm_set_register(ctx, vcpu, VM_REG_GUEST_RAX,
eax);
assert(error == 0);
}
}
return (retval);
}
void
init_inout(void)
{
struct inout_port **iopp, *iop;
/*
* Set up the default handler for all ports
*/
register_default_iohandler(0, MAX_IOPORTS);
/*
* Overwrite with specified handlers
*/
SET_FOREACH(iopp, inout_port_set) {
iop = *iopp;
assert(iop->port < MAX_IOPORTS);
inout_handlers[iop->port].name = iop->name;
inout_handlers[iop->port].flags = iop->flags;
inout_handlers[iop->port].handler = iop->handler;
inout_handlers[iop->port].arg = NULL;
}
}
int
register_inout(struct inout_port *iop)
{
int i;
VERIFY_IOPORT(iop->port, iop->size);
Add support for PCI-to-ISA LPC bridge emulation. If the LPC bus is attached to a virtual machine then we implicitly create COM1 and COM2 ISA devices. Prior to this change the only way of attaching a COM port to the virtual machine was by presenting it as a PCI device that is mapped at the legacy I/O address 0x3F8 or 0x2F8. There were some issues with the original approach: - It did not work at all with UEFI because UEFI will reprogram the PCI device BARs and remap the COM1/COM2 ports at non-legacy addresses. - OpenBSD GENERIC kernel does not create a /dev/console because it expects the uart device at the legacy 0x3F8/0x2F8 address to be an ISA device. - It was functional with a FreeBSD guest but caused the console to appear on /dev/ttyu2 which was not intuitive. The uart emulation is now independent of the bus on which it resides. Thus it is possible to have uart devices on the PCI bus in addition to the legacy COM1/COM2 devices behind the LPC bus. The command line option to attach ISA COM1/COM2 ports to a virtual machine is "-s <bus>,lpc -l com1,stdio". The command line option to create a PCI-attached uart device is: "-s <bus>,uart[,stdio]" The command line option to create PCI-attached COM1/COM2 device is: "-S <bus>,uart[,stdio]". This style of creating COM ports is deprecated. Discussed with: grehan Reviewed by: grehan Submitted by: Tycho Nightingale (tycho.nightingale@pluribusnetworks.com) M share/examples/bhyve/vmrun.sh AM usr.sbin/bhyve/legacy_irq.c AM usr.sbin/bhyve/legacy_irq.h M usr.sbin/bhyve/Makefile AM usr.sbin/bhyve/uart_emul.c M usr.sbin/bhyve/bhyverun.c AM usr.sbin/bhyve/uart_emul.h M usr.sbin/bhyve/pci_uart.c M usr.sbin/bhyve/pci_emul.c M usr.sbin/bhyve/inout.c M usr.sbin/bhyve/pci_emul.h M usr.sbin/bhyve/inout.h AM usr.sbin/bhyve/pci_lpc.c AM usr.sbin/bhyve/pci_lpc.h
2013-10-29 00:18:11 +00:00
/*
* Verify that the new registration is not overwriting an already
* allocated i/o range.
*/
if ((iop->flags & IOPORT_F_DEFAULT) == 0) {
for (i = iop->port; i < iop->port + iop->size; i++) {
if ((inout_handlers[i].flags & IOPORT_F_DEFAULT) == 0)
return (-1);
}
}
for (i = iop->port; i < iop->port + iop->size; i++) {
inout_handlers[i].name = iop->name;
inout_handlers[i].flags = iop->flags;
inout_handlers[i].handler = iop->handler;
inout_handlers[i].arg = iop->arg;
}
return (0);
}
int
unregister_inout(struct inout_port *iop)
{
VERIFY_IOPORT(iop->port, iop->size);
assert(inout_handlers[iop->port].name == iop->name);
register_default_iohandler(iop->port, iop->size);
return (0);
}