| Message ID | 1394750828-16351-12-git-send-email-leif.lindholm@linaro.org (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
On Thu, Mar 13, 2014 at 10:47:04PM +0000, Leif Lindholm wrote: > --- /dev/null > +++ b/arch/arm64/kernel/efi-entry.S > @@ -0,0 +1,93 @@ > +/* > + * EFI entry point. > + * > + * Copyright (C) 2013 Red Hat, Inc. > + * Author: Mark Salter <msalter@redhat.com> > + * > + * This program is free software; you can redistribute it and/or modify > + * it under the terms of the GNU General Public License version 2 as > + * published by the Free Software Foundation. > + * > + */ > +#include <linux/linkage.h> > +#include <linux/init.h> > + > +#include <asm/assembler.h> > + > +#define EFI_LOAD_ERROR 0x8000000000000001 > + > + __INIT > + > + /* > + * We arrive here from the EFI boot manager with: > + * > + * * MMU on with identity-mapped RAM. > + * * Icache and Dcache on > + * > + * We will most likely be running from some place other than where > + * we want to be. The kernel image wants to be placed at TEXT_OFFSET > + * from start of RAM. > + */ > +ENTRY(efi_stub_entry) > + stp x29, x30, [sp, #-32]! > + > + /* > + * Call efi_entry to do the real work. > + * x0 and x1 are already set up by firmware. Current runtime > + * address of image is calculated and passed via *image_addr. > + * > + * unsigned long efi_entry(void *handle, > + * efi_system_table_t *sys_table, > + * unsigned long *image_addr) ; > + */ > + adrp x8, _text > + add x8, x8, #:lo12:_text > + add x2, sp, 16 > + str x8, [x2] > + bl efi_entry > + cmn x0, #1 > + b.eq efi_load_fail > + > + /* > + * efi_entry() will have relocated the kernel image if necessary > + * and we return here with device tree address in x0 and the kernel > + * entry point stored at *image_addr. Save those values in registers > + * which are preserved by __flush_dcache_all. > + */ > + ldr x1, [sp, #16] > + mov x20, x0 > + mov x21, x1 > + > + /* Turn off Dcache and MMU */ > + mrs x0, CurrentEL > + cmp x0, #PSR_MODE_EL2t > + ccmp x0, #PSR_MODE_EL2h, #0x4, ne > + b.ne 1f > + mrs x0, sctlr_el2 > + bic x0, x0, #1 << 0 // clear SCTLR.M > + bic x0, x0, #1 << 2 // clear SCTLR.C > + msr sctlr_el2, x0 > + isb > + b 2f > +1: > + mrs x0, sctlr_el1 > + bic x0, x0, #1 << 0 // clear SCTLR.M > + bic x0, x0, #1 << 2 // clear SCTLR.C > + msr sctlr_el1, x0 > + isb > +2: > + bl __flush_dcache_all In linux-next I'm pushing a patch which no longer exports the __flush_dcache_all function. The reason is that it doesn't really work if you have a (not fully transparent) external cache like on the Applied Micro boards. There other issues when running as a guest as well. If you know exactly what needs to be flushed here, can you use a range (MVA) operation? > diff --git a/arch/arm64/kernel/efi-stub.c b/arch/arm64/kernel/efi-stub.c > new file mode 100644 > index 0000000..bf30913 > --- /dev/null > +++ b/arch/arm64/kernel/efi-stub.c > @@ -0,0 +1,83 @@ > +/* > + * linux/arch/arm/boot/compressed/efi-stub.c Nitpick: arch/arm64/... But we don't really need to write the file name here, I use a smart editor that tells me which file I'm viewing ;). Better write a one-line summary of what this file is about. > + * > + * Copyright (C) 2013, 2014 Linaro Ltd; <roy.franz@linaro.org> > + * > + * This file implements the EFI boot stub for the arm64 kernel. > + * Adapted from ARM version by Mark Salter <msalter@redhat.com> > + * > + * This program is free software; you can redistribute it and/or modify > + * it under the terms of the GNU General Public License version 2 as > + * published by the Free Software Foundation. > + * > + */ > +#include <linux/efi.h> > +#include <linux/libfdt.h> > +#include <asm/sections.h> > +#include <generated/compile.h> > +#include <generated/utsrelease.h> > + > +/* > + * EFI function call wrappers. These are not required for arm/arm64, but > + * wrappers are required for X86 to convert between ABIs. These wrappers are > + * provided to allow code sharing between X86 and other architectures. Since > + * these wrappers directly invoke the EFI function pointer, the function > + * pointer type must be properly defined, which is not the case for X86. One > + * advantage of this is it allows for type checking of arguments, which is not > + * possible with the X86 wrappers. > + */ > +#define efi_call_phys0(f) f() > +#define efi_call_phys1(f, a1) f(a1) > +#define efi_call_phys2(f, a1, a2) f(a1, a2) > +#define efi_call_phys3(f, a1, a2, a3) f(a1, a2, a3) > +#define efi_call_phys4(f, a1, a2, a3, a4) f(a1, a2, a3, a4) > +#define efi_call_phys5(f, a1, a2, a3, a4, a5) f(a1, a2, a3, a4, a5) > + > +/* > + * AArch64 requires the DTB to be 8-byte aligned in the first 512MiB from > + * start of kernel and may not cross a 2MiB boundary. We set alignment to > + * 2MiB so we know it won't cross a 2MiB boundary. > + */ > +#define EFI_FDT_ALIGN SZ_2M /* used by allocate_new_fdt_and_exit_boot() */ > +#define MAX_FDT_OFFSET SZ_512M > + > +/* Include shared EFI stub code */ > +#include "../../../drivers/firmware/efi/efi-stub-helper.c" It looks like this is done by x86 as well. > +#include "../../../drivers/firmware/efi/fdt.c" > +#include "../../../drivers/firmware/efi/arm-stub.c" But why do we need to create more stuff like this? Is it because on arm we need this as part of the decompressor (which would be a good enough argument)?
On Tue, 2014-03-18 at 12:09 +0000, Catalin Marinas wrote: > On Thu, Mar 13, 2014 at 10:47:04PM +0000, Leif Lindholm wrote: > > --- /dev/null > > +++ b/arch/arm64/kernel/efi-entry.S > > @@ -0,0 +1,93 @@ > > +/* > > + * EFI entry point. > > + * > > + * Copyright (C) 2013 Red Hat, Inc. > > + * Author: Mark Salter <msalter@redhat.com> > > + * > > + * This program is free software; you can redistribute it and/or modify > > + * it under the terms of the GNU General Public License version 2 as > > + * published by the Free Software Foundation. > > + * > > + */ > > +#include <linux/linkage.h> > > +#include <linux/init.h> > > + > > +#include <asm/assembler.h> > > + > > +#define EFI_LOAD_ERROR 0x8000000000000001 > > + > > + __INIT > > + > > + /* > > + * We arrive here from the EFI boot manager with: > > + * > > + * * MMU on with identity-mapped RAM. > > + * * Icache and Dcache on > > + * > > + * We will most likely be running from some place other than where > > + * we want to be. The kernel image wants to be placed at TEXT_OFFSET > > + * from start of RAM. > > + */ > > +ENTRY(efi_stub_entry) > > + stp x29, x30, [sp, #-32]! > > + > > + /* > > + * Call efi_entry to do the real work. > > + * x0 and x1 are already set up by firmware. Current runtime > > + * address of image is calculated and passed via *image_addr. > > + * > > + * unsigned long efi_entry(void *handle, > > + * efi_system_table_t *sys_table, > > + * unsigned long *image_addr) ; > > + */ > > + adrp x8, _text > > + add x8, x8, #:lo12:_text > > + add x2, sp, 16 > > + str x8, [x2] > > + bl efi_entry > > + cmn x0, #1 > > + b.eq efi_load_fail > > + > > + /* > > + * efi_entry() will have relocated the kernel image if necessary > > + * and we return here with device tree address in x0 and the kernel > > + * entry point stored at *image_addr. Save those values in registers > > + * which are preserved by __flush_dcache_all. > > + */ > > + ldr x1, [sp, #16] > > + mov x20, x0 > > + mov x21, x1 > > + > > + /* Turn off Dcache and MMU */ > > + mrs x0, CurrentEL > > + cmp x0, #PSR_MODE_EL2t > > + ccmp x0, #PSR_MODE_EL2h, #0x4, ne > > + b.ne 1f > > + mrs x0, sctlr_el2 > > + bic x0, x0, #1 << 0 // clear SCTLR.M > > + bic x0, x0, #1 << 2 // clear SCTLR.C > > + msr sctlr_el2, x0 > > + isb > > + b 2f > > +1: > > + mrs x0, sctlr_el1 > > + bic x0, x0, #1 << 0 // clear SCTLR.M > > + bic x0, x0, #1 << 2 // clear SCTLR.C > > + msr sctlr_el1, x0 > > + isb > > +2: > > + bl __flush_dcache_all > > In linux-next I'm pushing a patch which no longer exports the > __flush_dcache_all function. The reason is that it doesn't really work > if you have a (not fully transparent) external cache like on the Applied > Micro boards. There other issues when running as a guest as well. > > If you know exactly what needs to be flushed here, can you use a range > (MVA) operation? This is just before the EFI stub jumps to kernel proper. The only things in the dcache would be from identity mapped references to RAM used by UEFI. The booting.txt doc says dcache should be off and invalidated. I am just wanting to comply with that. The code here doesn't really know the extent of DRAM to flush by address. > > > diff --git a/arch/arm64/kernel/efi-stub.c b/arch/arm64/kernel/efi-stub.c > > new file mode 100644 > > index 0000000..bf30913 > > --- /dev/null > > +++ b/arch/arm64/kernel/efi-stub.c > > @@ -0,0 +1,83 @@ > > +/* > > + * linux/arch/arm/boot/compressed/efi-stub.c > > Nitpick: arch/arm64/... But we don't really need to write the file name > here, I use a smart editor that tells me which file I'm viewing ;). > Better write a one-line summary of what this file is about. Okay. Leftover cruft from copy of arm stub. > > > + * > > + * Copyright (C) 2013, 2014 Linaro Ltd; <roy.franz@linaro.org> > > + * > > + * This file implements the EFI boot stub for the arm64 kernel. > > + * Adapted from ARM version by Mark Salter <msalter@redhat.com> > > + * > > + * This program is free software; you can redistribute it and/or modify > > + * it under the terms of the GNU General Public License version 2 as > > + * published by the Free Software Foundation. > > + * > > + */ > > +#include <linux/efi.h> > > +#include <linux/libfdt.h> > > +#include <asm/sections.h> > > +#include <generated/compile.h> > > +#include <generated/utsrelease.h> > > + > > +/* > > + * EFI function call wrappers. These are not required for arm/arm64, but > > + * wrappers are required for X86 to convert between ABIs. These wrappers are > > + * provided to allow code sharing between X86 and other architectures. Since > > + * these wrappers directly invoke the EFI function pointer, the function > > + * pointer type must be properly defined, which is not the case for X86. One > > + * advantage of this is it allows for type checking of arguments, which is not > > + * possible with the X86 wrappers. > > + */ > > +#define efi_call_phys0(f) f() > > +#define efi_call_phys1(f, a1) f(a1) > > +#define efi_call_phys2(f, a1, a2) f(a1, a2) > > +#define efi_call_phys3(f, a1, a2, a3) f(a1, a2, a3) > > +#define efi_call_phys4(f, a1, a2, a3, a4) f(a1, a2, a3, a4) > > +#define efi_call_phys5(f, a1, a2, a3, a4, a5) f(a1, a2, a3, a4, a5) > > + > > +/* > > + * AArch64 requires the DTB to be 8-byte aligned in the first 512MiB from > > + * start of kernel and may not cross a 2MiB boundary. We set alignment to > > + * 2MiB so we know it won't cross a 2MiB boundary. > > + */ > > +#define EFI_FDT_ALIGN SZ_2M /* used by allocate_new_fdt_and_exit_boot() */ > > +#define MAX_FDT_OFFSET SZ_512M > > + > > +/* Include shared EFI stub code */ > > +#include "../../../drivers/firmware/efi/efi-stub-helper.c" > > It looks like this is done by x86 as well. > > > +#include "../../../drivers/firmware/efi/fdt.c" > > +#include "../../../drivers/firmware/efi/arm-stub.c" > > But why do we need to create more stuff like this? Is it because on arm > we need this as part of the decompressor (which would be a good enough > argument)? That is the reason exactly. I wish there were a better way.
On Tue, Mar 18, 2014 at 02:40:29PM +0000, Mark Salter wrote: > On Tue, 2014-03-18 at 12:09 +0000, Catalin Marinas wrote: > > On Thu, Mar 13, 2014 at 10:47:04PM +0000, Leif Lindholm wrote: > > > --- /dev/null > > > +++ b/arch/arm64/kernel/efi-entry.S > > > @@ -0,0 +1,93 @@ > > > +/* > > > + * EFI entry point. > > > + * > > > + * Copyright (C) 2013 Red Hat, Inc. > > > + * Author: Mark Salter <msalter@redhat.com> > > > + * > > > + * This program is free software; you can redistribute it and/or modify > > > + * it under the terms of the GNU General Public License version 2 as > > > + * published by the Free Software Foundation. > > > + * > > > + */ > > > +#include <linux/linkage.h> > > > +#include <linux/init.h> > > > + > > > +#include <asm/assembler.h> > > > + > > > +#define EFI_LOAD_ERROR 0x8000000000000001 > > > + > > > + __INIT > > > + > > > + /* > > > + * We arrive here from the EFI boot manager with: > > > + * > > > + * * MMU on with identity-mapped RAM. > > > + * * Icache and Dcache on > > > + * > > > + * We will most likely be running from some place other than where > > > + * we want to be. The kernel image wants to be placed at TEXT_OFFSET > > > + * from start of RAM. > > > + */ > > > +ENTRY(efi_stub_entry) > > > + stp x29, x30, [sp, #-32]! > > > + > > > + /* > > > + * Call efi_entry to do the real work. > > > + * x0 and x1 are already set up by firmware. Current runtime > > > + * address of image is calculated and passed via *image_addr. > > > + * > > > + * unsigned long efi_entry(void *handle, > > > + * efi_system_table_t *sys_table, > > > + * unsigned long *image_addr) ; > > > + */ > > > + adrp x8, _text > > > + add x8, x8, #:lo12:_text > > > + add x2, sp, 16 > > > + str x8, [x2] > > > + bl efi_entry > > > + cmn x0, #1 > > > + b.eq efi_load_fail > > > + > > > + /* > > > + * efi_entry() will have relocated the kernel image if necessary > > > + * and we return here with device tree address in x0 and the kernel > > > + * entry point stored at *image_addr. Save those values in registers > > > + * which are preserved by __flush_dcache_all. > > > + */ > > > + ldr x1, [sp, #16] > > > + mov x20, x0 > > > + mov x21, x1 > > > + > > > + /* Turn off Dcache and MMU */ > > > + mrs x0, CurrentEL > > > + cmp x0, #PSR_MODE_EL2t > > > + ccmp x0, #PSR_MODE_EL2h, #0x4, ne > > > + b.ne 1f > > > + mrs x0, sctlr_el2 > > > + bic x0, x0, #1 << 0 // clear SCTLR.M > > > + bic x0, x0, #1 << 2 // clear SCTLR.C > > > + msr sctlr_el2, x0 > > > + isb > > > + b 2f > > > +1: > > > + mrs x0, sctlr_el1 > > > + bic x0, x0, #1 << 0 // clear SCTLR.M > > > + bic x0, x0, #1 << 2 // clear SCTLR.C > > > + msr sctlr_el1, x0 > > > + isb > > > +2: > > > + bl __flush_dcache_all > > > > In linux-next I'm pushing a patch which no longer exports the > > __flush_dcache_all function. The reason is that it doesn't really work > > if you have a (not fully transparent) external cache like on the Applied > > Micro boards. There other issues when running as a guest as well. > > > > If you know exactly what needs to be flushed here, can you use a range > > (MVA) operation? > > This is just before the EFI stub jumps to kernel proper. The only things > in the dcache would be from identity mapped references to RAM used by > UEFI. The booting.txt doc says dcache should be off and invalidated. I > am just wanting to comply with that. The code here doesn't really know > the extent of DRAM to flush by address. Does UEFI do anything with the caches before invoking the EFI_STUB code? I guess it doesn't since that's just another application for it. Can UEFI flush the caches via exit boot? When is this called? As I said, we have a real problem here since the EFI_STUB call does not have information about the SoC to be able to flush all the caches. But UEFI should know more about the hardware. If UEFI doesn't handle the caches, the only thing left to EFI_STUB is to flush by MVA. We don't need to flush the whole DRAM (and I would even recommend it) but at least the relevant kernel code/data touched with the MMU disabled.
On Tue, 2014-03-18 at 18:28 +0000, Catalin Marinas wrote: > On Tue, Mar 18, 2014 at 02:40:29PM +0000, Mark Salter wrote: > > On Tue, 2014-03-18 at 12:09 +0000, Catalin Marinas wrote: > > > On Thu, Mar 13, 2014 at 10:47:04PM +0000, Leif Lindholm wrote: > > > > --- /dev/null > > > > +++ b/arch/arm64/kernel/efi-entry.S > > > > @@ -0,0 +1,93 @@ > > > > +/* > > > > + * EFI entry point. > > > > + * > > > > + * Copyright (C) 2013 Red Hat, Inc. > > > > + * Author: Mark Salter <msalter@redhat.com> > > > > + * > > > > + * This program is free software; you can redistribute it and/or modify > > > > + * it under the terms of the GNU General Public License version 2 as > > > > + * published by the Free Software Foundation. > > > > + * > > > > + */ > > > > +#include <linux/linkage.h> > > > > +#include <linux/init.h> > > > > + > > > > +#include <asm/assembler.h> > > > > + > > > > +#define EFI_LOAD_ERROR 0x8000000000000001 > > > > + > > > > + __INIT > > > > + > > > > + /* > > > > + * We arrive here from the EFI boot manager with: > > > > + * > > > > + * * MMU on with identity-mapped RAM. > > > > + * * Icache and Dcache on > > > > + * > > > > + * We will most likely be running from some place other than where > > > > + * we want to be. The kernel image wants to be placed at TEXT_OFFSET > > > > + * from start of RAM. > > > > + */ > > > > +ENTRY(efi_stub_entry) > > > > + stp x29, x30, [sp, #-32]! > > > > + > > > > + /* > > > > + * Call efi_entry to do the real work. > > > > + * x0 and x1 are already set up by firmware. Current runtime > > > > + * address of image is calculated and passed via *image_addr. > > > > + * > > > > + * unsigned long efi_entry(void *handle, > > > > + * efi_system_table_t *sys_table, > > > > + * unsigned long *image_addr) ; > > > > + */ > > > > + adrp x8, _text > > > > + add x8, x8, #:lo12:_text > > > > + add x2, sp, 16 > > > > + str x8, [x2] > > > > + bl efi_entry > > > > + cmn x0, #1 > > > > + b.eq efi_load_fail > > > > + > > > > + /* > > > > + * efi_entry() will have relocated the kernel image if necessary > > > > + * and we return here with device tree address in x0 and the kernel > > > > + * entry point stored at *image_addr. Save those values in registers > > > > + * which are preserved by __flush_dcache_all. > > > > + */ > > > > + ldr x1, [sp, #16] > > > > + mov x20, x0 > > > > + mov x21, x1 > > > > + > > > > + /* Turn off Dcache and MMU */ > > > > + mrs x0, CurrentEL > > > > + cmp x0, #PSR_MODE_EL2t > > > > + ccmp x0, #PSR_MODE_EL2h, #0x4, ne > > > > + b.ne 1f > > > > + mrs x0, sctlr_el2 > > > > + bic x0, x0, #1 << 0 // clear SCTLR.M > > > > + bic x0, x0, #1 << 2 // clear SCTLR.C > > > > + msr sctlr_el2, x0 > > > > + isb > > > > + b 2f > > > > +1: > > > > + mrs x0, sctlr_el1 > > > > + bic x0, x0, #1 << 0 // clear SCTLR.M > > > > + bic x0, x0, #1 << 2 // clear SCTLR.C > > > > + msr sctlr_el1, x0 > > > > + isb > > > > +2: > > > > + bl __flush_dcache_all > > > > > > In linux-next I'm pushing a patch which no longer exports the > > > __flush_dcache_all function. The reason is that it doesn't really work > > > if you have a (not fully transparent) external cache like on the Applied > > > Micro boards. There other issues when running as a guest as well. > > > > > > If you know exactly what needs to be flushed here, can you use a range > > > (MVA) operation? > > > > This is just before the EFI stub jumps to kernel proper. The only things > > in the dcache would be from identity mapped references to RAM used by > > UEFI. The booting.txt doc says dcache should be off and invalidated. I > > am just wanting to comply with that. The code here doesn't really know > > the extent of DRAM to flush by address. > > Does UEFI do anything with the caches before invoking the EFI_STUB code? > I guess it doesn't since that's just another application for it. Can > UEFI flush the caches via exit boot? When is this called? > > As I said, we have a real problem here since the EFI_STUB call does not > have information about the SoC to be able to flush all the caches. But > UEFI should know more about the hardware. > > If UEFI doesn't handle the caches, the only thing left to EFI_STUB is to > flush by MVA. We don't need to flush the whole DRAM (and I would even > recommend it) but at least the relevant kernel code/data touched with > the MMU disabled. > So, it goes like this: 1) UEFI calls stub with MMU/Caches on. Stub/kernel can be anywhere. 2) Stub runs and relocates kernel to the desired runtime location but continues to execute from wherever UEFI loaded it until just after ExitBootServices(). 3) After ExitBootServices, efi_entry() returns relocated entry point for kernel to efi_stub_entry() in efi-entry.S where the Dcache and MMU are turned off, the __flush_dcache_all is called, then the code jumps to the kernel proper entry point. It isn't clear to me if UEFI does cache flushing at ExitBootServices time, but even so, at least stack use will get cached between then and the kernel entry point. The stub could conceivably get its hands on the EFI memmap and invalidate dcache using address ranges from UEFI memory descriptors so maybe that is the way we should do it.
On Tue, Mar 18, 2014 at 2:40 PM, Mark Salter <msalter@redhat.com> wrote: > On Tue, 2014-03-18 at 18:28 +0000, Catalin Marinas wrote: >> On Tue, Mar 18, 2014 at 02:40:29PM +0000, Mark Salter wrote: >> > On Tue, 2014-03-18 at 12:09 +0000, Catalin Marinas wrote: >> > > On Thu, Mar 13, 2014 at 10:47:04PM +0000, Leif Lindholm wrote: >> > > > --- /dev/null >> > > > +++ b/arch/arm64/kernel/efi-entry.S >> > > > @@ -0,0 +1,93 @@ >> > > > +/* >> > > > + * EFI entry point. >> > > > + * >> > > > + * Copyright (C) 2013 Red Hat, Inc. >> > > > + * Author: Mark Salter <msalter@redhat.com> >> > > > + * >> > > > + * This program is free software; you can redistribute it and/or modify >> > > > + * it under the terms of the GNU General Public License version 2 as >> > > > + * published by the Free Software Foundation. >> > > > + * >> > > > + */ >> > > > +#include <linux/linkage.h> >> > > > +#include <linux/init.h> >> > > > + >> > > > +#include <asm/assembler.h> >> > > > + >> > > > +#define EFI_LOAD_ERROR 0x8000000000000001 >> > > > + >> > > > + __INIT >> > > > + >> > > > + /* >> > > > + * We arrive here from the EFI boot manager with: >> > > > + * >> > > > + * * MMU on with identity-mapped RAM. >> > > > + * * Icache and Dcache on >> > > > + * >> > > > + * We will most likely be running from some place other than where >> > > > + * we want to be. The kernel image wants to be placed at TEXT_OFFSET >> > > > + * from start of RAM. >> > > > + */ >> > > > +ENTRY(efi_stub_entry) >> > > > + stp x29, x30, [sp, #-32]! >> > > > + >> > > > + /* >> > > > + * Call efi_entry to do the real work. >> > > > + * x0 and x1 are already set up by firmware. Current runtime >> > > > + * address of image is calculated and passed via *image_addr. >> > > > + * >> > > > + * unsigned long efi_entry(void *handle, >> > > > + * efi_system_table_t *sys_table, >> > > > + * unsigned long *image_addr) ; >> > > > + */ >> > > > + adrp x8, _text >> > > > + add x8, x8, #:lo12:_text >> > > > + add x2, sp, 16 >> > > > + str x8, [x2] >> > > > + bl efi_entry >> > > > + cmn x0, #1 >> > > > + b.eq efi_load_fail >> > > > + >> > > > + /* >> > > > + * efi_entry() will have relocated the kernel image if necessary >> > > > + * and we return here with device tree address in x0 and the kernel >> > > > + * entry point stored at *image_addr. Save those values in registers >> > > > + * which are preserved by __flush_dcache_all. >> > > > + */ >> > > > + ldr x1, [sp, #16] >> > > > + mov x20, x0 >> > > > + mov x21, x1 >> > > > + >> > > > + /* Turn off Dcache and MMU */ >> > > > + mrs x0, CurrentEL >> > > > + cmp x0, #PSR_MODE_EL2t >> > > > + ccmp x0, #PSR_MODE_EL2h, #0x4, ne >> > > > + b.ne 1f >> > > > + mrs x0, sctlr_el2 >> > > > + bic x0, x0, #1 << 0 // clear SCTLR.M >> > > > + bic x0, x0, #1 << 2 // clear SCTLR.C >> > > > + msr sctlr_el2, x0 >> > > > + isb >> > > > + b 2f >> > > > +1: >> > > > + mrs x0, sctlr_el1 >> > > > + bic x0, x0, #1 << 0 // clear SCTLR.M >> > > > + bic x0, x0, #1 << 2 // clear SCTLR.C >> > > > + msr sctlr_el1, x0 >> > > > + isb >> > > > +2: >> > > > + bl __flush_dcache_all >> > > >> > > In linux-next I'm pushing a patch which no longer exports the >> > > __flush_dcache_all function. The reason is that it doesn't really work >> > > if you have a (not fully transparent) external cache like on the Applied >> > > Micro boards. There other issues when running as a guest as well. >> > > >> > > If you know exactly what needs to be flushed here, can you use a range >> > > (MVA) operation? >> > >> > This is just before the EFI stub jumps to kernel proper. The only things >> > in the dcache would be from identity mapped references to RAM used by >> > UEFI. The booting.txt doc says dcache should be off and invalidated. I >> > am just wanting to comply with that. The code here doesn't really know >> > the extent of DRAM to flush by address. >> >> Does UEFI do anything with the caches before invoking the EFI_STUB code? >> I guess it doesn't since that's just another application for it. Can >> UEFI flush the caches via exit boot? When is this called? >> >> As I said, we have a real problem here since the EFI_STUB call does not >> have information about the SoC to be able to flush all the caches. But >> UEFI should know more about the hardware. >> >> If UEFI doesn't handle the caches, the only thing left to EFI_STUB is to >> flush by MVA. We don't need to flush the whole DRAM (and I would even >> recommend it) but at least the relevant kernel code/data touched with >> the MMU disabled. >> > > So, it goes like this: > > 1) UEFI calls stub with MMU/Caches on. Stub/kernel can be anywhere. > 2) Stub runs and relocates kernel to the desired runtime location > but continues to execute from wherever UEFI loaded it until just > after ExitBootServices(). > 3) After ExitBootServices, efi_entry() returns relocated entry point > for kernel to efi_stub_entry() in efi-entry.S where the Dcache and > MMU are turned off, the __flush_dcache_all is called, then the > code jumps to the kernel proper entry point. > > It isn't clear to me if UEFI does cache flushing at ExitBootServices > time, but even so, at least stack use will get cached between then and > the kernel entry point. The stub could conceivably get its hands on the > EFI memmap and invalidate dcache using address ranges from UEFI memory > descriptors so maybe that is the way we should do it. > I looked at the UEFI spec and there is no mention of cache flushing in ExitBootServices(), so it seems it is up to the OS to do any cache management. Roy
On Tue, Mar 18, 2014 at 02:48:30PM -0700, Roy Franz wrote: > > It isn't clear to me if UEFI does cache flushing at ExitBootServices > > time, but even so, at least stack use will get cached between then and > > the kernel entry point. The stub could conceivably get its hands on the > > EFI memmap and invalidate dcache using address ranges from UEFI memory > > descriptors so maybe that is the way we should do it. > I looked at the UEFI spec and there is no mention of cache flushing > in ExitBootServices(), so it seems it is up to the OS to do any > cache management. Something to think about: On mvebu we recently confirmed a situation where turning off the L1 cache is not sufficient for booting. The L2 cache must also be completely off and disabled prior to jumping in to the kernel. The issue is the decompressor turns the L1 cache back on, and if the L2 is also enabled at this point then it gets filled with decompression data. Things go wrong from here because after decompression the L1 dcache is switched off, but the L2 isn't flush-invalidated. So now the L2 holds writeback data and uncached reads return garbage, and/or the L2 misses the uncached writes (eg relocation fixup) and becomes inconsistent with memory. Either case gives a black screen crash at boot. Fundementally if the L2 doesn't monitor uncached read/writes then it will cause a big problem. Thus, if the UEFI calls the sub with the caches on, and the stub doesn't know enough to turn off the L2 then you might not be able to turn the dcache off at all. :( On ARM64 at least the L1 cache ops are standardized so maybe ARM64 could keep the mmu+caches enabled during boot and do the L1 d-flush/i-inval required for instruction coherency? Jason
On Tue, Mar 18, 2014 at 10:21:05PM +0000, Jason Gunthorpe wrote: > On Tue, Mar 18, 2014 at 02:48:30PM -0700, Roy Franz wrote: > > > > It isn't clear to me if UEFI does cache flushing at ExitBootServices > > > time, but even so, at least stack use will get cached between then and > > > the kernel entry point. The stub could conceivably get its hands on the > > > EFI memmap and invalidate dcache using address ranges from UEFI memory > > > descriptors so maybe that is the way we should do it. > > > I looked at the UEFI spec and there is no mention of cache flushing > > in ExitBootServices(), so it seems it is up to the OS to do any > > cache management. > > Something to think about: On mvebu we recently confirmed a situation > where turning off the L1 cache is not sufficient for booting. The L2 > cache must also be completely off and disabled prior to jumping in to > the kernel. > > The issue is the decompressor turns the L1 cache back on, and if the > L2 is also enabled at this point then it gets filled with > decompression data. Things go wrong from here because after > decompression the L1 dcache is switched off, but the L2 isn't > flush-invalidated. > > So now the L2 holds writeback data and uncached reads return garbage, > and/or the L2 misses the uncached writes (eg relocation fixup) and > becomes inconsistent with memory. Either case gives a black screen > crash at boot. > > Fundementally if the L2 doesn't monitor uncached read/writes then it > will cause a big problem. Yes, that's a problem on (ARMv7) SoCs booting in non-secure mode with external L2 already enabled. For ARMv8 at least, the SoCs I've seen with external caches detect the data cache by MVA ops. > Thus, if the UEFI calls the sub with the caches on, and the stub > doesn't know enough to turn off the L2 then you might not be able to > turn the dcache off at all. :( > > On ARM64 at least the L1 cache ops are standardized so maybe ARM64 > could keep the mmu+caches enabled during boot and do the L1 > d-flush/i-inval required for instruction coherency? We thought about keeping the MMU on from EFI_STUB into the kernel but it gets messier since UEFI has different MMU settings. So with some sane external cache, we could get away with flushing a range.
On Tue, Mar 18, 2014 at 09:40:31PM +0000, Mark Salter wrote: > On Tue, 2014-03-18 at 18:28 +0000, Catalin Marinas wrote: > > If UEFI doesn't handle the caches, the only thing left to EFI_STUB is to > > flush by MVA. We don't need to flush the whole DRAM (and I would even > > recommend it) but at least the relevant kernel code/data touched with > > the MMU disabled. > > So, it goes like this: > > 1) UEFI calls stub with MMU/Caches on. Stub/kernel can be anywhere. > 2) Stub runs and relocates kernel to the desired runtime location > but continues to execute from wherever UEFI loaded it until just > after ExitBootServices(). > 3) After ExitBootServices, efi_entry() returns relocated entry point > for kernel to efi_stub_entry() in efi-entry.S where the Dcache and > MMU are turned off, the __flush_dcache_all is called, then the > code jumps to the kernel proper entry point. > > It isn't clear to me if UEFI does cache flushing at ExitBootServices > time, but even so, at least stack use will get cached between then and > the kernel entry point. The stub could conceivably get its hands on the > EFI memmap and invalidate dcache using address ranges from UEFI memory > descriptors so maybe that is the way we should do it. I think the stub just needs to flush the relocated kernel image, ensure it is sync with the memory. Additional flushing can be done by the kernel for bits it writes (like page tables, code patching etc). We can enter the kernel with the SCTLR.I bit set, so it can allocate in an unified cache already and D-cache maintenance would be needed anyway. Another aspect in the booting document is that we require any external cache to be disabled. I think on ARMv8 with a more transparent external cache we can relax this (Applied's SoC already does this). Otherwise, since external cache enabling is usually a secure operation, we would need some SoC specific code just for this early during boot and I'd like to avoid it.
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index da4304a..6333d49 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -259,6 +259,16 @@ config CMDLINE_FORCE This is useful if you cannot or don't want to change the command-line options your boot loader passes to the kernel. +config EFI_STUB + bool "EFI stub support" + depends on OF + select LIBFDT + default y + help + This kernel feature allows an Image to be loaded directly + by EFI firmware without the use of a bootloader. + See Documentation/efi-stub.txt for more information. + endmenu menu "Userspace binary formats" diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index 2d4554b..0f60b45 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -4,6 +4,8 @@ CPPFLAGS_vmlinux.lds := -DTEXT_OFFSET=$(TEXT_OFFSET) AFLAGS_head.o := -DTEXT_OFFSET=$(TEXT_OFFSET) +CFLAGS_efi-stub.o := -DTEXT_OFFSET=$(TEXT_OFFSET) \ + -I$(src)/../../../scripts/dtc/libfdt # Object file lists. arm64-obj-y := cputable.o debug-monitors.o entry.o irq.o fpsimd.o \ @@ -20,6 +22,7 @@ arm64-obj-$(CONFIG_HAVE_HW_BREAKPOINT)+= hw_breakpoint.o arm64-obj-$(CONFIG_EARLY_PRINTK) += early_printk.o arm64-obj-$(CONFIG_ARM64_CPU_SUSPEND) += sleep.o suspend.o arm64-obj-$(CONFIG_JUMP_LABEL) += jump_label.o +arm64-obj-$(CONFIG_EFI_STUB) += efi-stub.o efi-entry.o obj-y += $(arm64-obj-y) vdso/ obj-m += $(arm64-obj-m) diff --git a/arch/arm64/kernel/efi-entry.S b/arch/arm64/kernel/efi-entry.S new file mode 100644 index 0000000..bfe8c9b --- /dev/null +++ b/arch/arm64/kernel/efi-entry.S @@ -0,0 +1,93 @@ +/* + * EFI entry point. + * + * Copyright (C) 2013 Red Hat, Inc. + * Author: Mark Salter <msalter@redhat.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + */ +#include <linux/linkage.h> +#include <linux/init.h> + +#include <asm/assembler.h> + +#define EFI_LOAD_ERROR 0x8000000000000001 + + __INIT + + /* + * We arrive here from the EFI boot manager with: + * + * * MMU on with identity-mapped RAM. + * * Icache and Dcache on + * + * We will most likely be running from some place other than where + * we want to be. The kernel image wants to be placed at TEXT_OFFSET + * from start of RAM. + */ +ENTRY(efi_stub_entry) + stp x29, x30, [sp, #-32]! + + /* + * Call efi_entry to do the real work. + * x0 and x1 are already set up by firmware. Current runtime + * address of image is calculated and passed via *image_addr. + * + * unsigned long efi_entry(void *handle, + * efi_system_table_t *sys_table, + * unsigned long *image_addr) ; + */ + adrp x8, _text + add x8, x8, #:lo12:_text + add x2, sp, 16 + str x8, [x2] + bl efi_entry + cmn x0, #1 + b.eq efi_load_fail + + /* + * efi_entry() will have relocated the kernel image if necessary + * and we return here with device tree address in x0 and the kernel + * entry point stored at *image_addr. Save those values in registers + * which are preserved by __flush_dcache_all. + */ + ldr x1, [sp, #16] + mov x20, x0 + mov x21, x1 + + /* Turn off Dcache and MMU */ + mrs x0, CurrentEL + cmp x0, #PSR_MODE_EL2t + ccmp x0, #PSR_MODE_EL2h, #0x4, ne + b.ne 1f + mrs x0, sctlr_el2 + bic x0, x0, #1 << 0 // clear SCTLR.M + bic x0, x0, #1 << 2 // clear SCTLR.C + msr sctlr_el2, x0 + isb + b 2f +1: + mrs x0, sctlr_el1 + bic x0, x0, #1 << 0 // clear SCTLR.M + bic x0, x0, #1 << 2 // clear SCTLR.C + msr sctlr_el1, x0 + isb +2: + bl __flush_dcache_all + + /* Jump to real entry point */ + mov x0, x20 + mov x1, xzr + mov x2, xzr + mov x3, xzr + br x21 + +efi_load_fail: + mov x0, #EFI_LOAD_ERROR + ldp x29, x30, [sp], #32 + ret + +ENDPROC(efi_stub_entry) diff --git a/arch/arm64/kernel/efi-stub.c b/arch/arm64/kernel/efi-stub.c new file mode 100644 index 0000000..bf30913 --- /dev/null +++ b/arch/arm64/kernel/efi-stub.c @@ -0,0 +1,83 @@ +/* + * linux/arch/arm/boot/compressed/efi-stub.c + * + * Copyright (C) 2013, 2014 Linaro Ltd; <roy.franz@linaro.org> + * + * This file implements the EFI boot stub for the arm64 kernel. + * Adapted from ARM version by Mark Salter <msalter@redhat.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + */ +#include <linux/efi.h> +#include <linux/libfdt.h> +#include <asm/sections.h> +#include <generated/compile.h> +#include <generated/utsrelease.h> + +/* + * EFI function call wrappers. These are not required for arm/arm64, but + * wrappers are required for X86 to convert between ABIs. These wrappers are + * provided to allow code sharing between X86 and other architectures. Since + * these wrappers directly invoke the EFI function pointer, the function + * pointer type must be properly defined, which is not the case for X86. One + * advantage of this is it allows for type checking of arguments, which is not + * possible with the X86 wrappers. + */ +#define efi_call_phys0(f) f() +#define efi_call_phys1(f, a1) f(a1) +#define efi_call_phys2(f, a1, a2) f(a1, a2) +#define efi_call_phys3(f, a1, a2, a3) f(a1, a2, a3) +#define efi_call_phys4(f, a1, a2, a3, a4) f(a1, a2, a3, a4) +#define efi_call_phys5(f, a1, a2, a3, a4, a5) f(a1, a2, a3, a4, a5) + +/* + * AArch64 requires the DTB to be 8-byte aligned in the first 512MiB from + * start of kernel and may not cross a 2MiB boundary. We set alignment to + * 2MiB so we know it won't cross a 2MiB boundary. + */ +#define EFI_FDT_ALIGN SZ_2M /* used by allocate_new_fdt_and_exit_boot() */ +#define MAX_FDT_OFFSET SZ_512M + +/* Include shared EFI stub code */ +#include "../../../drivers/firmware/efi/efi-stub-helper.c" +#include "../../../drivers/firmware/efi/fdt.c" +#include "../../../drivers/firmware/efi/arm-stub.c" + + +static efi_status_t handle_kernel_image(efi_system_table_t *sys_table, + unsigned long *image_addr, + unsigned long *image_size, + unsigned long *reserve_addr, + unsigned long *reserve_size, + unsigned long dram_base, + efi_loaded_image_t *image) +{ + efi_status_t status; + unsigned long kernel_size, kernel_memsize = 0; + + /* Relocate the image, if required. */ + kernel_size = _edata - _text; + if (*image_addr != (dram_base + TEXT_OFFSET)) { + kernel_memsize = kernel_size + (_end - _edata); + status = efi_relocate_kernel(sys_table, image_addr, + kernel_size, kernel_memsize, + dram_base + TEXT_OFFSET, + PAGE_SIZE); + if (status != EFI_SUCCESS) { + pr_efi_err(sys_table, "Failed to relocate kernel\n"); + return status; + } + if (*image_addr != (dram_base + TEXT_OFFSET)) { + pr_efi_err(sys_table, "Failed to alloc kernel memory\n"); + efi_free(sys_table, kernel_memsize, *image_addr); + return EFI_ERROR; + } + *image_size = kernel_memsize; + } + + + return EFI_SUCCESS; +} diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index c86bfdf..2f07979 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -107,8 +107,18 @@ /* * DO NOT MODIFY. Image header expected by Linux boot-loaders. */ +#ifdef CONFIG_EFI_STUB + /* + * Magic "MZ" signature for PE/COFF + * Little Endian: add x13, x18, #0x16 + */ +efi_head: + .long 0x91005a4d + b stext +#else b stext // branch to kernel start, magic .long 0 // reserved +#endif .quad TEXT_OFFSET // Image load offset from start of RAM .quad 0 // reserved .quad 0 // reserved @@ -119,7 +129,109 @@ .byte 0x52 .byte 0x4d .byte 0x64 +#ifdef CONFIG_EFI_STUB + .long pe_header - efi_head // Offset to the PE header. +#else .word 0 // reserved +#endif + +#ifdef CONFIG_EFI_STUB + .align 3 +pe_header: + .ascii "PE" + .short 0 +coff_header: + .short 0xaa64 // AArch64 + .short 2 // nr_sections + .long 0 // TimeDateStamp + .long 0 // PointerToSymbolTable + .long 1 // NumberOfSymbols + .short section_table - optional_header // SizeOfOptionalHeader + .short 0x206 // Characteristics. + // IMAGE_FILE_DEBUG_STRIPPED | + // IMAGE_FILE_EXECUTABLE_IMAGE | + // IMAGE_FILE_LINE_NUMS_STRIPPED +optional_header: + .short 0x20b // PE32+ format + .byte 0x02 // MajorLinkerVersion + .byte 0x14 // MinorLinkerVersion + .long _edata - stext // SizeOfCode + .long 0 // SizeOfInitializedData + .long 0 // SizeOfUninitializedData + .long efi_stub_entry - efi_head // AddressOfEntryPoint + .long stext - efi_head // BaseOfCode + +extra_header_fields: + .quad 0 // ImageBase + .long 0x20 // SectionAlignment + .long 0x8 // FileAlignment + .short 0 // MajorOperatingSystemVersion + .short 0 // MinorOperatingSystemVersion + .short 0 // MajorImageVersion + .short 0 // MinorImageVersion + .short 0 // MajorSubsystemVersion + .short 0 // MinorSubsystemVersion + .long 0 // Win32VersionValue + + .long _edata - efi_head // SizeOfImage + + // Everything before the kernel image is considered part of the header + .long stext - efi_head // SizeOfHeaders + .long 0 // CheckSum + .short 0xa // Subsystem (EFI application) + .short 0 // DllCharacteristics + .quad 0 // SizeOfStackReserve + .quad 0 // SizeOfStackCommit + .quad 0 // SizeOfHeapReserve + .quad 0 // SizeOfHeapCommit + .long 0 // LoaderFlags + .long 0x6 // NumberOfRvaAndSizes + + .quad 0 // ExportTable + .quad 0 // ImportTable + .quad 0 // ResourceTable + .quad 0 // ExceptionTable + .quad 0 // CertificationTable + .quad 0 // BaseRelocationTable + + // Section table +section_table: + + /* + * The EFI application loader requires a relocation section + * because EFI applications must be relocatable. This is a + * dummy section as far as we are concerned. + */ + .ascii ".reloc" + .byte 0 + .byte 0 // end of 0 padding of section name + .long 0 + .long 0 + .long 0 // SizeOfRawData + .long 0 // PointerToRawData + .long 0 // PointerToRelocations + .long 0 // PointerToLineNumbers + .short 0 // NumberOfRelocations + .short 0 // NumberOfLineNumbers + .long 0x42100040 // Characteristics (section flags) + + + .ascii ".text" + .byte 0 + .byte 0 + .byte 0 // end of 0 padding of section name + .long _edata - stext // VirtualSize + .long stext - efi_head // VirtualAddress + .long _edata - stext // SizeOfRawData + .long stext - efi_head // PointerToRawData + + .long 0 // PointerToRelocations (0 for executables) + .long 0 // PointerToLineNumbers (0 for executables) + .short 0 // NumberOfRelocations (0 for executables) + .short 0 // NumberOfLineNumbers (0 for executables) + .long 0xe0500020 // Characteristics (section flags) + .align 5 +#endif ENTRY(stext) mov x21, x0 // x21=FDT diff --git a/drivers/firmware/efi/arm-stub.c b/drivers/firmware/efi/arm-stub.c new file mode 100644 index 0000000..b505fde --- /dev/null +++ b/drivers/firmware/efi/arm-stub.c @@ -0,0 +1,144 @@ +/* + * EFI stub implementation that is shared by arm and arm64 architectures. + * This should be #included by the EFI stub implementation files. + * + * Copyright (C) 2013,2014 Linaro Limited + * Roy Franz <roy.franz@linaro.org + * Copyright (C) 2013 Red Hat, Inc. + * Mark Salter <msalter@redhat.com> + * + * This file is part of the Linux kernel, and is made available under the + * terms of the GNU General Public License version 2. + * + */ + +/* + * This function handles the architcture specific differences between arm and + * arm64 regarding where the kernel image must be loaded and any memory that + * must be reserved. On failure it is required to free all + * all allocations it has made. + */ +static efi_status_t handle_kernel_image(efi_system_table_t *sys_table, + unsigned long *image_addr, + unsigned long *image_size, + unsigned long *reserve_addr, + unsigned long *reserve_size, + unsigned long dram_base, + efi_loaded_image_t *image); +/* + * EFI entry point for the arm/arm64 EFI stubs. This is the entrypoint + * that is described in the PE/COFF header. Most of the code is the same + * for both archictectures, with the arch-specific code provided in the + * handle_kernel_image() function. + */ +unsigned long efi_entry(void *handle, efi_system_table_t *sys_table, + unsigned long *image_addr) +{ + efi_loaded_image_t *image; + efi_status_t status; + unsigned long image_size = 0; + unsigned long dram_base; + /* addr/point and size pairs for memory management*/ + unsigned long initrd_addr; + u64 initrd_size = 0; + unsigned long fdt_addr; /* Original DTB */ + u64 fdt_size = 0; /* We don't get size from configuration table */ + char *cmdline_ptr = NULL; + int cmdline_size = 0; + unsigned long new_fdt_addr; + efi_guid_t loaded_image_proto = LOADED_IMAGE_PROTOCOL_GUID; + unsigned long reserve_addr = 0; + unsigned long reserve_size = 0; + + /* Check if we were booted by the EFI firmware */ + if (sys_table->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE) + goto fail; + + pr_efi(sys_table, "Booting Linux Kernel...\n"); + + /* + * Get a handle to the loaded image protocol. This is used to get + * information about the running image, such as size and the command + * line. + */ + status = efi_call_phys3(sys_table->boottime->handle_protocol, + handle, &loaded_image_proto, (void *)&image); + if (status != EFI_SUCCESS) { + pr_efi_err(sys_table, "Failed to get loaded image protocol\n"); + goto fail; + } + + dram_base = get_dram_base(sys_table); + if (dram_base == EFI_ERROR) { + pr_efi_err(sys_table, "Failed to find DRAM base\n"); + goto fail; + } + status = handle_kernel_image(sys_table, image_addr, &image_size, + &reserve_addr, + &reserve_size, + dram_base, image); + if (status != EFI_SUCCESS) { + pr_efi_err(sys_table, "Failed to relocate kernel\n"); + goto fail; + } + + /* + * Get the command line from EFI, using the LOADED_IMAGE + * protocol. We are going to copy the command line into the + * device tree, so this can be allocated anywhere. + */ + cmdline_ptr = efi_convert_cmdline(sys_table, image, &cmdline_size); + if (!cmdline_ptr) { + pr_efi_err(sys_table, "getting command line via LOADED_IMAGE_PROTOCOL\n"); + goto fail_free_image; + } + + /* Load a device tree from the configuration table, if present. */ + fdt_addr = (uintptr_t)get_fdt(sys_table); + if (!fdt_addr) { + status = handle_cmdline_files(sys_table, image, cmdline_ptr, + "dtb=", + ~0UL, (unsigned long *)&fdt_addr, + (unsigned long *)&fdt_size); + + if (status != EFI_SUCCESS) { + pr_efi_err(sys_table, "Failed to load device tree!\n"); + goto fail_free_cmdline; + } + } + + status = handle_cmdline_files(sys_table, image, cmdline_ptr, + "initrd=", dram_base + SZ_512M, + (unsigned long *)&initrd_addr, + (unsigned long *)&initrd_size); + if (status != EFI_SUCCESS) + pr_efi_err(sys_table, "Failed initrd from command line!\n"); + + new_fdt_addr = fdt_addr; + status = allocate_new_fdt_and_exit_boot(sys_table, handle, + &new_fdt_addr, dram_base + MAX_FDT_OFFSET, + initrd_addr, initrd_size, cmdline_ptr, + fdt_addr, fdt_size); + + /* + * If all went well, we need to return the FDT address to the + * calling function so it can be passed to kernel as part of + * the kernel boot protocol. + */ + if (status == EFI_SUCCESS) + return new_fdt_addr; + + pr_efi_err(sys_table, "Failed to update FDT and exit boot services\n"); + + efi_free(sys_table, initrd_size, initrd_addr); + efi_free(sys_table, fdt_size, fdt_addr); + +fail_free_cmdline: + efi_free(sys_table, cmdline_size, (unsigned long)cmdline_ptr); + +fail_free_image: + efi_free(sys_table, image_size, *image_addr); + efi_free(sys_table, reserve_size, reserve_addr); +fail: + return EFI_ERROR; +}