Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
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>
- Loading branch information
Showing
22 changed files
with
1,801 additions
and
13 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,153 @@ | ||
| /* | ||
| * SPAPR machine hooks to Virtual Open Firmware, | ||
| * | ||
| * SPDX-License-Identifier: GPL-2.0-or-later | ||
| */ | ||
| #include "qemu/osdep.h" | ||
| #include "qemu-common.h" | ||
| #include "qapi/error.h" | ||
| #include "hw/ppc/spapr.h" | ||
| #include "hw/ppc/spapr_vio.h" | ||
| #include "hw/ppc/fdt.h" | ||
| #include "hw/ppc/vof.h" | ||
| #include "sysemu/sysemu.h" | ||
| #include "qom/qom-qobject.h" | ||
| #include "trace.h" | ||
|
|
||
| target_ulong spapr_h_vof_client(PowerPCCPU *cpu, SpaprMachineState *spapr, | ||
| target_ulong opcode, target_ulong *_args) | ||
| { | ||
| int ret = vof_client_call(MACHINE(spapr), spapr->vof, spapr->fdt_blob, | ||
| ppc64_phys_to_real(_args[0])); | ||
|
|
||
| if (ret) { | ||
| return H_PARAMETER; | ||
| } | ||
| return H_SUCCESS; | ||
| } | ||
|
|
||
| void spapr_vof_client_dt_finalize(SpaprMachineState *spapr, void *fdt) | ||
| { | ||
| char *stdout_path = spapr_vio_stdout_path(spapr->vio_bus); | ||
| int chosen; | ||
|
|
||
| vof_build_dt(fdt, spapr->vof); | ||
|
|
||
| _FDT(chosen = fdt_path_offset(fdt, "/chosen")); | ||
| _FDT(fdt_setprop_string(fdt, chosen, "bootargs", | ||
| spapr->vof->bootargs ? : "")); | ||
|
|
||
| /* | ||
| * SLOF-less setup requires an open instance of stdout for early | ||
| * kernel printk. By now all phandles are settled so we can open | ||
| * the default serial console. | ||
| */ | ||
| if (stdout_path) { | ||
| _FDT(vof_client_open_store(fdt, spapr->vof, "/chosen", "stdout", | ||
| stdout_path)); | ||
| } | ||
| } | ||
|
|
||
| void spapr_vof_reset(SpaprMachineState *spapr, void *fdt, | ||
| target_ulong *stack_ptr, Error **errp) | ||
| { | ||
| Vof *vof = spapr->vof; | ||
|
|
||
| vof_init(vof, spapr->rma_size, errp); | ||
|
|
||
| *stack_ptr = vof_claim(vof, 0, VOF_STACK_SIZE, VOF_STACK_SIZE); | ||
| if (*stack_ptr == -1) { | ||
| error_setg(errp, "Memory allocation for stack failed"); | ||
| return; | ||
| } | ||
| /* Stack grows downwards plus reserve space for the minimum stack frame */ | ||
| *stack_ptr += VOF_STACK_SIZE - 0x20; | ||
|
|
||
| if (spapr->kernel_size && | ||
| vof_claim(vof, spapr->kernel_addr, spapr->kernel_size, 0) == -1) { | ||
| error_setg(errp, "Memory for kernel is in use"); | ||
| return; | ||
| } | ||
|
|
||
| if (spapr->initrd_size && | ||
| vof_claim(vof, spapr->initrd_base, spapr->initrd_size, 0) == -1) { | ||
| error_setg(errp, "Memory for initramdisk is in use"); | ||
| return; | ||
| } | ||
|
|
||
| spapr_vof_client_dt_finalize(spapr, fdt); | ||
|
|
||
| /* | ||
| * At this point the expected allocation map is: | ||
| * | ||
| * 0..c38 - the initial firmware | ||
| * 8000..10000 - stack | ||
| * 400000.. - kernel | ||
| * 3ea0000.. - initramdisk | ||
| * | ||
| * We skip writing FDT as nothing expects it; OF client interface is | ||
| * going to be used for reading the device tree. | ||
| */ | ||
| } | ||
|
|
||
| void spapr_vof_quiesce(MachineState *ms) | ||
| { | ||
| SpaprMachineState *spapr = SPAPR_MACHINE(ms); | ||
|
|
||
| spapr->fdt_size = fdt_totalsize(spapr->fdt_blob); | ||
| spapr->fdt_initial_size = spapr->fdt_size; | ||
| } | ||
|
|
||
| bool spapr_vof_setprop(MachineState *ms, const char *path, const char *propname, | ||
| void *val, int vallen) | ||
| { | ||
| SpaprMachineState *spapr = SPAPR_MACHINE(ms); | ||
|
|
||
| /* | ||
| * We only allow changing properties which we know how to update in QEMU | ||
| * OR | ||
| * the ones which we know that they need to survive during "quiesce". | ||
| */ | ||
|
|
||
| if (strcmp(path, "/rtas") == 0) { | ||
| if (strcmp(propname, "linux,rtas-base") == 0 || | ||
| strcmp(propname, "linux,rtas-entry") == 0) { | ||
| /* These need to survive quiesce so let them store in the FDT */ | ||
| return true; | ||
| } | ||
| } | ||
|
|
||
| if (strcmp(path, "/chosen") == 0) { | ||
| if (strcmp(propname, "bootargs") == 0) { | ||
| Vof *vof = spapr->vof; | ||
|
|
||
| g_free(vof->bootargs); | ||
| vof->bootargs = g_strndup(val, vallen); | ||
| return true; | ||
| } | ||
| if (strcmp(propname, "linux,initrd-start") == 0) { | ||
| if (vallen == sizeof(uint32_t)) { | ||
| spapr->initrd_base = ldl_be_p(val); | ||
| return true; | ||
| } | ||
| if (vallen == sizeof(uint64_t)) { | ||
| spapr->initrd_base = ldq_be_p(val); | ||
| return true; | ||
| } | ||
| return false; | ||
| } | ||
| if (strcmp(propname, "linux,initrd-end") == 0) { | ||
| if (vallen == sizeof(uint32_t)) { | ||
| spapr->initrd_size = ldl_be_p(val) - spapr->initrd_base; | ||
| return true; | ||
| } | ||
| if (vallen == sizeof(uint64_t)) { | ||
| spapr->initrd_size = ldq_be_p(val) - spapr->initrd_base; | ||
| return true; | ||
| } | ||
| return false; | ||
| } | ||
| } | ||
|
|
||
| return true; | ||
| } |
Oops, something went wrong.