spapr: Implement Open Firmware client interface
The PAPR platform describes an OS environment that's presented by
a combination of a hypervisor and firmware. The features it specifies
require collaboration between the firmware and the hypervisor.
Since the beginning, the runtime component of the firmware (RTAS) has
been implemented as a 20 byte shim which simply forwards it to
a hypercall implemented in qemu. The boot time firmware component is
SLOF - but a build that's specific to qemu, and has always needed to be
updated in sync with it. Even though we've managed to limit the amount
of runtime communication we need between qemu and SLOF, there's some,
and it has become increasingly awkward to handle as we've implemented
new features.
This implements a boot time OF client interface (CI) which is
enabled by a new "x-vof" pseries machine option (stands for "Virtual Open
Firmware). When enabled, QEMU implements the custom H_OF_CLIENT hcall
which implements Open Firmware Client Interface (OF CI). This allows
using a smaller stateless firmware which does not have to manage
the device tree.
The new "vof.bin" firmware image is included with source code under
pc-bios/. It also includes RTAS blob.
This implements a handful of CI methods just to get -kernel/-initrd
working. In particular, this implements the device tree fetching and
simple memory allocator - "claim" (an OF CI memory allocator) and updates
"/memory@0/available" to report the client about available memory.
This implements changing some device tree properties which we know how
to deal with, the rest is ignored. To allow changes, this skips
fdt_pack() when x-vof=on as not packing the blob leaves some room for
appending.
In absence of SLOF, this assigns phandles to device tree nodes to make
device tree traversing work.
When x-vof=on, this adds "/chosen" every time QEMU (re)builds a tree.
This adds basic instances support which are managed by a hash map
ihandle -> [phandle].
Before the guest started, the used memory is:
0..e60 - the initial firmware
8000..10000 - stack
400000.. - kernel
3ea0000.. - initramdisk
This OF CI does not implement "interpret".
Unlike SLOF, this does not format uninitialized nvram. Instead, this
includes a disk image with pre-formatted nvram.
With this basic support, this can only boot into kernel directly.
However this is just enough for the petitboot kernel and initradmdisk to
boot from any possible source. Note this requires reasonably recent guest
kernel with:
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=df5be5be8735
The immediate benefit is much faster booting time which especially
crucial with fully emulated early CPU bring up environments. Also this
may come handy when/if GRUB-in-the-userspace sees light of the day.
This separates VOF and sPAPR in a hope that VOF bits may be reused by
other POWERPC boards which do not support pSeries.
This assumes potential support for booting from QEMU backends
such as blockdev or netdev without devices/drivers used.
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Message-Id: <20210625055155.2252896-1-aik@ozlabs.ru>
Reviewed-by: BALATON Zoltan <balaton@eik.bme.hu>
[dwg: Adjusted some includes which broke compile in some more obscure
compilation setups]
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
2021-06-25 07:51:55 +02:00
|
|
|
#include "vof.h"
|
|
|
|
|
|
|
|
struct prom_args {
|
|
|
|
uint32_t service;
|
|
|
|
uint32_t nargs;
|
|
|
|
uint32_t nret;
|
|
|
|
uint32_t args[10];
|
|
|
|
};
|
|
|
|
|
|
|
|
typedef unsigned long prom_arg_t;
|
|
|
|
|
|
|
|
#define ADDR(x) (uint32_t)(x)
|
|
|
|
|
|
|
|
static int prom_handle(struct prom_args *pargs)
|
|
|
|
{
|
|
|
|
void *rtasbase;
|
|
|
|
uint32_t rtassize = 0;
|
|
|
|
phandle rtas;
|
|
|
|
|
|
|
|
if (strcmp("call-method", (void *)(unsigned long)pargs->service)) {
|
|
|
|
return -1;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (strcmp("instantiate-rtas", (void *)(unsigned long)pargs->args[0])) {
|
|
|
|
return -1;
|
|
|
|
}
|
|
|
|
|
|
|
|
rtas = ci_finddevice("/rtas");
|
|
|
|
/* rtas-size is set by QEMU depending of FWNMI support */
|
|
|
|
ci_getprop(rtas, "rtas-size", &rtassize, sizeof(rtassize));
|
|
|
|
if (rtassize < hv_rtas_size) {
|
|
|
|
return -1;
|
|
|
|
}
|
|
|
|
|
|
|
|
rtasbase = (void *)(unsigned long) pargs->args[2];
|
|
|
|
|
|
|
|
memcpy(rtasbase, hv_rtas, hv_rtas_size);
|
|
|
|
pargs->args[pargs->nargs] = 0;
|
|
|
|
pargs->args[pargs->nargs + 1] = pargs->args[2];
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
void prom_entry(uint32_t args)
|
|
|
|
{
|
|
|
|
if (prom_handle((void *)(unsigned long) args)) {
|
|
|
|
ci_entry(args);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
static int call_ci(const char *service, int nargs, int nret, ...)
|
|
|
|
{
|
|
|
|
int i;
|
|
|
|
struct prom_args args;
|
|
|
|
va_list list;
|
|
|
|
|
|
|
|
args.service = ADDR(service);
|
|
|
|
args.nargs = nargs;
|
|
|
|
args.nret = nret;
|
|
|
|
|
|
|
|
va_start(list, nret);
|
|
|
|
for (i = 0; i < nargs; i++) {
|
|
|
|
args.args[i] = va_arg(list, prom_arg_t);
|
|
|
|
}
|
|
|
|
va_end(list);
|
|
|
|
|
|
|
|
for (i = 0; i < nret; i++) {
|
|
|
|
args.args[nargs + i] = 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (ci_entry((uint32_t)(&args)) < 0) {
|
2021-07-08 08:56:25 +02:00
|
|
|
return -1;
|
spapr: Implement Open Firmware client interface
The PAPR platform describes an OS environment that's presented by
a combination of a hypervisor and firmware. The features it specifies
require collaboration between the firmware and the hypervisor.
Since the beginning, the runtime component of the firmware (RTAS) has
been implemented as a 20 byte shim which simply forwards it to
a hypercall implemented in qemu. The boot time firmware component is
SLOF - but a build that's specific to qemu, and has always needed to be
updated in sync with it. Even though we've managed to limit the amount
of runtime communication we need between qemu and SLOF, there's some,
and it has become increasingly awkward to handle as we've implemented
new features.
This implements a boot time OF client interface (CI) which is
enabled by a new "x-vof" pseries machine option (stands for "Virtual Open
Firmware). When enabled, QEMU implements the custom H_OF_CLIENT hcall
which implements Open Firmware Client Interface (OF CI). This allows
using a smaller stateless firmware which does not have to manage
the device tree.
The new "vof.bin" firmware image is included with source code under
pc-bios/. It also includes RTAS blob.
This implements a handful of CI methods just to get -kernel/-initrd
working. In particular, this implements the device tree fetching and
simple memory allocator - "claim" (an OF CI memory allocator) and updates
"/memory@0/available" to report the client about available memory.
This implements changing some device tree properties which we know how
to deal with, the rest is ignored. To allow changes, this skips
fdt_pack() when x-vof=on as not packing the blob leaves some room for
appending.
In absence of SLOF, this assigns phandles to device tree nodes to make
device tree traversing work.
When x-vof=on, this adds "/chosen" every time QEMU (re)builds a tree.
This adds basic instances support which are managed by a hash map
ihandle -> [phandle].
Before the guest started, the used memory is:
0..e60 - the initial firmware
8000..10000 - stack
400000.. - kernel
3ea0000.. - initramdisk
This OF CI does not implement "interpret".
Unlike SLOF, this does not format uninitialized nvram. Instead, this
includes a disk image with pre-formatted nvram.
With this basic support, this can only boot into kernel directly.
However this is just enough for the petitboot kernel and initradmdisk to
boot from any possible source. Note this requires reasonably recent guest
kernel with:
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=df5be5be8735
The immediate benefit is much faster booting time which especially
crucial with fully emulated early CPU bring up environments. Also this
may come handy when/if GRUB-in-the-userspace sees light of the day.
This separates VOF and sPAPR in a hope that VOF bits may be reused by
other POWERPC boards which do not support pSeries.
This assumes potential support for booting from QEMU backends
such as blockdev or netdev without devices/drivers used.
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Message-Id: <20210625055155.2252896-1-aik@ozlabs.ru>
Reviewed-by: BALATON Zoltan <balaton@eik.bme.hu>
[dwg: Adjusted some includes which broke compile in some more obscure
compilation setups]
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
2021-06-25 07:51:55 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
return (nret > 0) ? args.args[nargs] : 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
void ci_panic(const char *str)
|
|
|
|
{
|
|
|
|
call_ci("exit", 0, 0);
|
|
|
|
}
|
|
|
|
|
|
|
|
phandle ci_finddevice(const char *path)
|
|
|
|
{
|
|
|
|
return call_ci("finddevice", 1, 1, path);
|
|
|
|
}
|
|
|
|
|
|
|
|
uint32_t ci_getprop(phandle ph, const char *propname, void *prop, int len)
|
|
|
|
{
|
|
|
|
return call_ci("getprop", 4, 1, ph, propname, prop, len);
|
|
|
|
}
|