diff options
Diffstat (limited to 'arch/powerpc')
51 files changed, 2563 insertions, 233 deletions
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 2e1b47dbd7fb..e119acad8559 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -457,6 +457,20 @@ config KEXEC interface is strongly in flux, so no good recommendation can be made. +config KEXEC_FILE + bool "kexec file based system call" + select KEXEC_CORE + select HAVE_IMA_KEXEC + select BUILD_BIN2C + depends on PPC64 + depends on CRYPTO=y + depends on CRYPTO_SHA256=y + help + This is a new version of the kexec system call. This call is + file based and takes in file descriptors as system call arguments + for kernel and initramfs as opposed to a list of segments as is the + case for the older kexec call. + config RELOCATABLE bool "Build a relocatable kernel" depends on (PPC64 && !COMPILE_TEST) || (FLATMEM && (44x || FSL_BOOKE)) @@ -500,7 +514,7 @@ config CRASH_DUMP config FA_DUMP bool "Firmware-assisted dump" - depends on PPC64 && PPC_RTAS && CRASH_DUMP && KEXEC + depends on PPC64 && PPC_RTAS && CRASH_DUMP && KEXEC_CORE help A robust mechanism to get reliable kernel crash dump with assistance from firmware. This approach does not use kexec, diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index 041fda1e2a5d..426328b0b141 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -250,6 +250,7 @@ core-y += arch/powerpc/kernel/ \ core-$(CONFIG_XMON) += arch/powerpc/xmon/ core-$(CONFIG_KVM) += arch/powerpc/kvm/ core-$(CONFIG_PERF_EVENTS) += arch/powerpc/perf/ +core-$(CONFIG_KEXEC_FILE) += arch/powerpc/purgatory/ drivers-$(CONFIG_OPROFILE) += arch/powerpc/oprofile/ diff --git a/arch/powerpc/boot/string.S b/arch/powerpc/boot/string.S index acc9428f2789..b54bbad5f83d 100644 --- a/arch/powerpc/boot/string.S +++ b/arch/powerpc/boot/string.S @@ -11,9 +11,18 @@ #include "ppc_asm.h" +/* + * The ppc64 kexec purgatory uses this file and packages it in ELF64, + * so it needs dot symbols for the ppc64 big endian ABI. This macro + * allows it to create those symbols. + */ +#ifndef DOTSYM +#define DOTSYM(a) a +#endif + .text - .globl strcpy -strcpy: + .globl DOTSYM(strcpy) +DOTSYM(strcpy): addi r5,r3,-1 addi r4,r4,-1 1: lbzu r0,1(r4) @@ -22,8 +31,8 @@ strcpy: bne 1b blr - .globl strncpy -strncpy: + .globl DOTSYM(strncpy) +DOTSYM(strncpy): cmpwi 0,r5,0 beqlr mtctr r5 @@ -35,8 +44,8 @@ strncpy: bdnzf 2,1b /* dec ctr, branch if ctr != 0 && !cr0.eq */ blr - .globl strcat -strcat: + .globl DOTSYM(strcat) +DOTSYM(strcat): addi r5,r3,-1 addi r4,r4,-1 1: lbzu r0,1(r5) @@ -49,8 +58,8 @@ strcat: bne 1b blr - .globl strchr -strchr: + .globl DOTSYM(strchr) +DOTSYM(strchr): addi r3,r3,-1 1: lbzu r0,1(r3) cmpw 0,r0,r4 @@ -60,8 +69,8 @@ strchr: li r3,0 blr - .globl strcmp -strcmp: + .globl DOTSYM(strcmp) +DOTSYM(strcmp): addi r5,r3,-1 addi r4,r4,-1 1: lbzu r3,1(r5) @@ -72,8 +81,8 @@ strcmp: beq 1b blr - .globl strncmp -strncmp: + .globl DOTSYM(strncmp) +DOTSYM(strncmp): mtctr r5 addi r5,r3,-1 addi r4,r4,-1 @@ -85,8 +94,8 @@ strncmp: bdnzt eq,1b blr - .globl strlen -strlen: + .globl DOTSYM(strlen) +DOTSYM(strlen): addi r4,r3,-1 1: lbzu r0,1(r4) cmpwi 0,r0,0 @@ -94,8 +103,8 @@ strlen: subf r3,r3,r4 blr - .globl memset -memset: + .globl DOTSYM(memset) +DOTSYM(memset): rlwimi r4,r4,8,16,23 rlwimi r4,r4,16,0,15 addi r6,r3,-4 @@ -120,14 +129,14 @@ memset: bdnz 8b blr - .globl memmove -memmove: + .globl DOTSYM(memmove) +DOTSYM(memmove): cmplw 0,r3,r4 - bgt backwards_memcpy + bgt DOTSYM(backwards_memcpy) /* fall through */ - .globl memcpy -memcpy: + .globl DOTSYM(memcpy) +DOTSYM(memcpy): rlwinm. r7,r5,32-3,3,31 /* r7 = r5 >> 3 */ addi r6,r3,-4 addi r4,r4,-4 @@ -175,8 +184,8 @@ memcpy: mtctr r7 b 1b - .globl backwards_memcpy -backwards_memcpy: + .globl DOTSYM(backwards_memcpy) +DOTSYM(backwards_memcpy): rlwinm. r7,r5,32-3,3,31 /* r7 = r5 >> 3 */ add r6,r3,r5 add r4,r4,r5 @@ -219,8 +228,8 @@ backwards_memcpy: mtctr r7 b 1b - .globl memchr -memchr: + .globl DOTSYM(memchr) +DOTSYM(memchr): cmpwi 0,r5,0 blelr mtctr r5 @@ -232,8 +241,8 @@ memchr: li r3,0 blr - .globl memcmp -memcmp: + .globl DOTSYM(memcmp) +DOTSYM(memcmp): cmpwi 0,r5,0 ble 2f mtctr r5 @@ -253,8 +262,8 @@ memcmp: * * flush_cache(addr, len) */ - .global flush_cache -flush_cache: + .globl DOTSYM(flush_cache) +DOTSYM(flush_cache): addi 4,4,0x1f /* len = (len + 0x1f) / 0x20 */ rlwinm. 4,4,27,5,31 mtctr 4 diff --git a/arch/powerpc/configs/powernv_defconfig b/arch/powerpc/configs/powernv_defconfig index d77af0eca967..a0359daac863 100644 --- a/arch/powerpc/configs/powernv_defconfig +++ b/arch/powerpc/configs/powernv_defconfig @@ -49,6 +49,7 @@ CONFIG_BINFMT_MISC=m CONFIG_PPC_TRANSACTIONAL_MEM=y CONFIG_HOTPLUG_CPU=y CONFIG_KEXEC=y +CONFIG_KEXEC_FILE=y CONFIG_IRQ_ALL_CPUS=y CONFIG_NUMA=y CONFIG_MEMORY_HOTPLUG=y @@ -297,6 +298,7 @@ CONFIG_CRYPTO_CCM=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_HMAC=y CONFIG_CRYPTO_MICHAEL_MIC=m +CONFIG_CRYPTO_SHA256=y CONFIG_CRYPTO_TGR192=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_ANUBIS=m diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig index 58a98d40086f..0059d2088b9c 100644 --- a/arch/powerpc/configs/ppc64_defconfig +++ b/arch/powerpc/configs/ppc64_defconfig @@ -46,6 +46,7 @@ CONFIG_HZ_100=y CONFIG_BINFMT_MISC=m CONFIG_PPC_TRANSACTIONAL_MEM=y CONFIG_KEXEC=y +CONFIG_KEXEC_FILE=y CONFIG_CRASH_DUMP=y CONFIG_IRQ_ALL_CPUS=y CONFIG_MEMORY_HOTREMOVE=y @@ -336,6 +337,7 @@ CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_HMAC=y CONFIG_CRYPTO_MICHAEL_MIC=m +CONFIG_CRYPTO_SHA256=y CONFIG_CRYPTO_TGR192=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_ANUBIS=m diff --git a/arch/powerpc/configs/pseries_defconfig b/arch/powerpc/configs/pseries_defconfig index c8cee26fd9a0..f7ea7c204c13 100644 --- a/arch/powerpc/configs/pseries_defconfig +++ b/arch/powerpc/configs/pseries_defconfig @@ -52,6 +52,7 @@ CONFIG_HZ_100=y CONFIG_BINFMT_MISC=m CONFIG_PPC_TRANSACTIONAL_MEM=y CONFIG_KEXEC=y +CONFIG_KEXEC_FILE=y CONFIG_IRQ_ALL_CPUS=y CONFIG_MEMORY_HOTPLUG=y CONFIG_MEMORY_HOTREMOVE=y @@ -299,6 +300,7 @@ CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_HMAC=y CONFIG_CRYPTO_MICHAEL_MIC=m +CONFIG_CRYPTO_SHA256=y CONFIG_CRYPTO_TGR192=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_ANUBIS=m diff --git a/arch/powerpc/include/asm/debug.h b/arch/powerpc/include/asm/debug.h index a954e4975049..86308f177f2d 100644 --- a/arch/powerpc/include/asm/debug.h +++ b/arch/powerpc/include/asm/debug.h @@ -10,7 +10,7 @@ struct pt_regs; extern struct dentry *powerpc_debugfs_root; -#if defined(CONFIG_DEBUGGER) || defined(CONFIG_KEXEC) +#if defined(CONFIG_DEBUGGER) || defined(CONFIG_KEXEC_CORE) extern int (*__debugger)(struct pt_regs *regs); extern int (*__debugger_ipi)(struct pt_regs *regs); diff --git a/arch/powerpc/include/asm/elf_util.h b/arch/powerpc/include/asm/elf_util.h new file mode 100644 index 000000000000..3dbad8cc7179 --- /dev/null +++ b/arch/powerpc/include/asm/elf_util.h @@ -0,0 +1,64 @@ +/* + * Utility functions to work with ELF files. + * + * Copyright (C) 2016, IBM Corporation + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2, or (at your option) + * any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef _ASM_POWERPC_ELF_UTIL_H +#define _ASM_POWERPC_ELF_UTIL_H + +#include <linux/elf.h> + +struct elf_info { + /* + * Where the ELF binary contents are kept. + * Memory managed by the user of the struct. + */ + const char *buffer; + + const struct elfhdr *ehdr; + const struct elf_phdr *proghdrs; + struct elf_shdr *sechdrs; +}; + +/* + * r2 is the TOC pointer: it actually points 0x8000 into the TOC (this + * gives the value maximum span in an instruction which uses a signed + * offset) + */ +static inline unsigned long elf_my_r2(const struct elf_shdr *sechdrs, + unsigned int toc_section) +{ + return sechdrs[toc_section].sh_addr + 0x8000; +} + +unsigned int elf_toc_section(const struct elfhdr *ehdr, + const struct elf_shdr *sechdrs); + +int elf64_apply_relocate_add_item(const Elf64_Shdr *sechdrs, const char *strtab, + const Elf64_Rela *rela, const Elf64_Sym *sym, + unsigned long *location, + unsigned long address, unsigned long value, + unsigned long my_r2, const char *obj_name, + struct module *me); + +static inline bool elf_is_elf_file(const struct elfhdr *ehdr) +{ + return memcmp(ehdr->e_ident, ELFMAG, SELFMAG) == 0; +} + +int elf_read_from_buffer(const char *buf, size_t len, struct elfhdr *ehdr, + struct elf_info *elf_info); +void elf_free_info(struct elf_info *elf_info); + +#endif /* _ASM_POWERPC_ELF_UTIL_H */ diff --git a/arch/powerpc/include/asm/ima.h b/arch/powerpc/include/asm/ima.h new file mode 100644 index 000000000000..2313bdface34 --- /dev/null +++ b/arch/powerpc/include/asm/ima.h @@ -0,0 +1,29 @@ +#ifndef _ASM_POWERPC_IMA_H +#define _ASM_POWERPC_IMA_H + +struct kimage; + +int ima_get_kexec_buffer(void **addr, size_t *size); +int ima_free_kexec_buffer(void); + +#ifdef CONFIG_IMA +void remove_ima_buffer(void *fdt, int chosen_node); +#else +static inline void remove_ima_buffer(void *fdt, int chosen_node) {} +#endif + +#ifdef CONFIG_IMA_KEXEC +int arch_ima_add_kexec_buffer(struct kimage *image, unsigned long load_addr, + size_t size); + +int setup_ima_buffer(const struct kimage *image, void *fdt, int chosen_node); +#else +static inline int setup_ima_buffer(const struct kimage *image, void *fdt, + int chosen_node) +{ + remove_ima_buffer(fdt, chosen_node); + return 0; +} +#endif /* CONFIG_IMA_KEXEC */ + +#endif /* _ASM_POWERPC_IMA_H */ diff --git a/arch/powerpc/include/asm/kexec.h b/arch/powerpc/include/asm/kexec.h index a46f5f45570c..a49cab287acb 100644 --- a/arch/powerpc/include/asm/kexec.h +++ b/arch/powerpc/include/asm/kexec.h @@ -53,7 +53,7 @@ typedef void (*crash_shutdown_t)(void); -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE /* * This function is responsible for capturing register states if coming @@ -91,7 +91,30 @@ static inline bool kdump_in_progress(void) return crashing_cpu >= 0; } -#else /* !CONFIG_KEXEC */ +#ifdef CONFIG_KEXEC_FILE +extern struct kexec_file_ops kexec_elf64_ops; + +#ifdef CONFIG_IMA_KEXEC +#define ARCH_HAS_KIMAGE_ARCH + +struct kimage_arch { + phys_addr_t ima_buffer_addr; + size_t ima_buffer_size; +}; +#endif + +int setup_purgatory(struct kimage *image, const void *slave_code, + const void *fdt, unsigned long kernel_load_addr, + unsigned long fdt_load_addr, unsigned long stack_top, + int debug); +int setup_new_fdt(const struct kimage *image, void *fdt, + unsigned long initrd_load_addr, unsigned long initrd_len, + const char *cmdline); +bool find_debug_console(const void *fdt); +int delete_fdt_mem_rsv(void *fdt, unsigned long start, unsigned long size); +#endif /* CONFIG_KEXEC_FILE */ + +#else /* !CONFIG_KEXEC_CORE */ static inline void crash_kexec_secondary(struct pt_regs *regs) { } static inline int overlaps_crashkernel(unsigned long start, unsigned long size) @@ -116,7 +139,7 @@ static inline bool kdump_in_progress(void) return false; } -#endif /* CONFIG_KEXEC */ +#endif /* CONFIG_KEXEC_CORE */ #endif /* ! __ASSEMBLY__ */ #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_KEXEC_H */ diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h index e02cbc6a6c70..5011b69107a7 100644 --- a/arch/powerpc/include/asm/machdep.h +++ b/arch/powerpc/include/asm/machdep.h @@ -183,7 +183,7 @@ struct machdep_calls { */ void (*machine_shutdown)(void); -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE void (*kexec_cpu_down)(int crash_shutdown, int secondary); /* Called to do what every setup is needed on image and the @@ -198,7 +198,7 @@ struct machdep_calls { * no return. */ void (*machine_kexec)(struct kimage *image); -#endif /* CONFIG_KEXEC */ +#endif /* CONFIG_KEXEC_CORE */ #ifdef CONFIG_SUSPEND /* These are called to disable and enable, respectively, IRQs when diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h index 0d02c11dc331..32db16d2e7ad 100644 --- a/arch/powerpc/include/asm/smp.h +++ b/arch/powerpc/include/asm/smp.h @@ -176,7 +176,7 @@ static inline void set_hard_smp_processor_id(int cpu, int phys) #endif /* !CONFIG_SMP */ #endif /* !CONFIG_PPC64 */ -#if defined(CONFIG_PPC64) && (defined(CONFIG_SMP) || defined(CONFIG_KEXEC)) +#if defined(CONFIG_PPC64) && (defined(CONFIG_SMP) || defined(CONFIG_KEXEC_CORE)) extern void smp_release_cpus(void); #else static inline void smp_release_cpus(void) { }; diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h index 2fc5d4db503c..4b369d83fe9c 100644 --- a/arch/powerpc/include/asm/systbl.h +++ b/arch/powerpc/include/asm/systbl.h @@ -386,3 +386,4 @@ SYSCALL(mlock2) SYSCALL(copy_file_range) COMPAT_SYS_SPU(preadv2) COMPAT_SYS_SPU(pwritev2) +SYSCALL(kexec_file_load) diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h index e8cdfec8d512..eb1acee91a20 100644 --- a/arch/powerpc/include/asm/unistd.h +++ b/arch/powerpc/include/asm/unistd.h @@ -12,7 +12,7 @@ #include <uapi/asm/unistd.h> -#define NR_syscalls 382 +#define NR_syscalls 383 #define __NR__exit __NR_exit diff --git a/arch/powerpc/include/uapi/asm/unistd.h b/arch/powerpc/include/uapi/asm/unistd.h index e9f5f41aa55a..2f26335a3c42 100644 --- a/arch/powerpc/include/uapi/asm/unistd.h +++ b/arch/powerpc/include/uapi/asm/unistd.h @@ -392,5 +392,6 @@ #define __NR_copy_file_range 379 #define __NR_preadv2 380 #define __NR_pwritev2 381 +#define __NR_kexec_file_load 382 #endif /* _UAPI_ASM_POWERPC_UNISTD_H_ */ diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 1925341dbb9c..c3b37171168c 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -107,8 +107,14 @@ pci64-$(CONFIG_PPC64) += pci_dn.o pci-hotplug.o isa-bridge.o obj-$(CONFIG_PCI) += pci_$(BITS).o $(pci64-y) \ pci-common.o pci_of_scan.o obj-$(CONFIG_PCI_MSI) += msi.o -obj-$(CONFIG_KEXEC) += machine_kexec.o crash.o \ +obj-$(CONFIG_KEXEC_CORE) += machine_kexec.o crash.o \ machine_kexec_$(BITS).o +obj-$(CONFIG_KEXEC_FILE) += machine_kexec_file_$(BITS).o elf_util.o \ + kexec_elf_$(BITS).o +ifeq ($(CONFIG_HAVE_IMA_KEXEC)$(CONFIG_IMA),yy) +obj-y += ima_kexec.o +endif + obj-$(CONFIG_AUDIT) += audit.o obj64-$(CONFIG_AUDIT) += compat_audit.o @@ -128,7 +134,7 @@ obj64-$(CONFIG_PPC_TRANSACTIONAL_MEM) += tm.o obj-$(CONFIG_PPC64) += $(obj64-y) obj-$(CONFIG_PPC32) += $(obj32-y) -ifneq ($(CONFIG_XMON)$(CONFIG_KEXEC),) +ifneq ($(CONFIG_XMON)$(CONFIG_KEXEC_CORE),) obj-y += ppc_save_regs.o endif diff --git a/arch/powerpc/kernel/elf_util.c b/arch/powerpc/kernel/elf_util.c new file mode 100644 index 000000000000..e57e7397f65c --- /dev/null +++ b/arch/powerpc/kernel/elf_util.c @@ -0,0 +1,464 @@ +/* + * Utility functions to work with ELF files. + * + * Copyright (C) 2016, IBM Corporation + * + * Based on kexec-tools' kexec-elf.c. Heavily modified for the + * kernel by Thiago Jung Bauermann <bauerman@linux.vnet.ibm.com>. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation (version 2 of the License). + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/slab.h> +#include <asm/elf_util.h> +#include <asm-generic/module.h> + +#if ELF_CLASS == ELFCLASS32 +#define elf_addr_to_cpu elf32_to_cpu + +#ifndef Elf_Rel +#define Elf_Rel Elf32_Rel +#endif /* Elf_Rel */ +#else /* ELF_CLASS == ELFCLASS32 */ +#define elf_addr_to_cpu elf64_to_cpu + +#ifndef Elf_Rel +#define Elf_Rel Elf64_Rel +#endif /* Elf_Rel */ + +/** + * elf_toc_section - find the toc section in the file with the given ELF headers + * @ehdr: Pointer to already loaded ELF header. + * @sechdrs: Pointer to already loaded section headers contents. + * + * Return: TOC section index or 0 if one wasn't found. + */ +unsigned int elf_toc_section(const struct elfhdr *ehdr, + const struct elf_shdr *sechdrs) +{ + int i; + const char *shstrtab; + + /* Section header string table. */ + shstrtab = (const char *) sechdrs[ehdr->e_shstrndx].sh_offset; + + for (i = 0; i < ehdr->e_shnum; i++) { + if (sechdrs[i].sh_size == 0) + continue; + + if (!strcmp(&shstrtab[sechdrs[i].sh_name], ".toc")) + return i; + } + + return 0; +} + +static uint64_t elf64_to_cpu(const struct elfhdr *ehdr, uint64_t value) +{ + if (ehdr->e_ident[EI_DATA] == ELFDATA2LSB) + value = le64_to_cpu(value); + else if (ehdr->e_ident[EI_DATA] == ELFDATA2MSB) + value = be64_to_cpu(value); + + return value; +} +#endif /* ELF_CLASS == ELFCLASS32 */ + +static uint16_t elf16_to_cpu(const struct elfhdr *ehdr, uint16_t value) +{ + if (ehdr->e_ident[EI_DATA] == ELFDATA2LSB) + value = le16_to_cpu(value); + else if (ehdr->e_ident[EI_DATA] == ELFDATA2MSB) + value = be16_to_cpu(value); + + return value; +} + +static uint32_t elf32_to_cpu(const struct elfhdr *ehdr, uint32_t value) +{ + if (ehdr->e_ident[EI_DATA] == ELFDATA2LSB) + value = le32_to_cpu(value); + else if (ehdr->e_ident[EI_DATA] == ELFDATA2MSB) + value = be32_to_cpu(value); + + return value; +} + +/** + * elf_is_ehdr_sane - check that it is safe to use the ELF header + * @buf_len: size of the buffer in which the ELF file is loaded. + */ +static bool elf_is_ehdr_sane(const struct elfhdr *ehdr, size_t buf_len) +{ + if (ehdr->e_phnum > 0 && ehdr->e_phentsize != sizeof(struct elf_phdr)) { + pr_debug("Bad program header size.\n"); + return false; + } else if (ehdr->e_shnum > 0 && + ehdr->e_shentsize != sizeof(struct elf_shdr)) { + pr_debug("Bad section header size.\n"); + return false; + } else if (ehdr->e_ident[EI_VERSION] != EV_CURRENT || + ehdr->e_version != EV_CURRENT) { + pr_debug("Unknown ELF version.\n"); + return false; + } + + if (ehdr->e_phoff > 0 && ehdr->e_phnum > 0) { + size_t phdr_size; + + /* + * e_phnum is at most 65535 so calculating the size of the + * program header cannot overflow. + */ + phdr_size = sizeof(struct elf_phdr) * ehdr->e_phnum; + + /* Sanity check the program header table location. */ + if (ehdr->e_phoff + phdr_size < ehdr->e_phoff) { + pr_debug("Program headers at invalid location.\n"); + return false; + } else if (ehdr->e_phoff + phdr_size > buf_len) { + pr_debug("Program headers truncated.\n"); + return false; + } + } + + if (ehdr->e_shoff > 0 && ehdr->e_shnum > 0) { + size_t shdr_size; + + /* + * e_shnum is at most 65536 so calculating + * the size of the section header cannot overflow. + */ + shdr_size = sizeof(struct elf_shdr) * ehdr->e_shnum; + + /* Sanity check the section header table location. */ + if (ehdr->e_shoff + shdr_size < ehdr->e_shoff) { + pr_debug("Section headers at invalid location.\n"); + return false; + } else if (ehdr->e_shoff + shdr_size > buf_len) { + pr_debug("Section headers truncated.\n"); + return false; + } + } + + return true; +} + +static int elf_read_ehdr(const char *buf, size_t len, struct elfhdr *ehdr) +{ + struct elfhdr *buf_ehdr; + + if (len < sizeof(*buf_ehdr)) { + pr_debug("Buffer is too small to hold ELF header.\n"); + return -ENOEXEC; + } + + memset(ehdr, 0, sizeof(*ehdr)); + memcpy(ehdr->e_ident, buf, sizeof(ehdr->e_ident)); + if (!elf_is_elf_file(ehdr)) { + pr_debug("No ELF header magic.\n"); + return -ENOEXEC; + } + + if (ehdr->e_ident[EI_CLASS] != ELF_CLASS) { + pr_debug("Not a supported ELF class.\n"); + return -1; + } else if (ehdr->e_ident[EI_DATA] != ELFDATA2LSB && + ehdr->e_ident[EI_DATA] != ELFDATA2MSB) { + pr_debug("Not a supported ELF data format.\n"); + return -ENOEXEC; + } + + buf_ehdr = (struct elfhdr *) buf; + if (elf16_to_cpu(ehdr, buf_ehdr->e_ehsize) != sizeof(*buf_ehdr)) { + pr_debug("Bad ELF header size.\n"); + return -ENOEXEC; + } + + ehdr->e_type = elf16_to_cpu(ehdr, buf_ehdr->e_type); + ehdr->e_machine = elf16_to_cpu(ehdr, buf_ehdr->e_machine); + ehdr->e_version = elf32_to_cpu(ehdr, buf_ehdr->e_version); + ehdr->e_entry = elf_addr_to_cpu(ehdr, buf_ehdr->e_entry); + ehdr->e_phoff = elf_addr_to_cpu(ehdr, buf_ehdr->e_phoff); + ehdr->e_shoff = elf_addr_to_cpu(ehdr, buf_ehdr->e_shoff); + ehdr->e_flags = elf32_to_cpu(ehdr, buf_ehdr->e_flags); + ehdr->e_phentsize = elf16_to_cpu(ehdr, buf_ehdr->e_phentsize); + ehdr->e_phnum = elf16_to_cpu(ehdr, buf_ehdr->e_phnum); + ehdr->e_shentsize = elf16_to_cpu(ehdr, buf_ehdr->e_shentsize); + ehdr->e_shnum = elf16_to_cpu(ehdr, buf_ehdr->e_shnum); + ehdr->e_shstrndx = elf16_to_cpu(ehdr, buf_ehdr->e_shstrndx); + + return elf_is_ehdr_sane(ehdr, len) ? 0 : -ENOEXEC; +} + +/** + * elf_is_phdr_sane - check that it is safe to use the program header + * @buf_len: size of the buffer in which the ELF file is loaded. + */ +static bool elf_is_phdr_sane(const struct elf_phdr *phdr, size_t buf_len) +{ + + if (phdr->p_offset + phdr->p_filesz < phdr->p_offset) { + pr_debug("ELF segment location wraps around.\n"); + return false; + } else if (phdr->p_offset + phdr->p_filesz > buf_len) { + pr_debug("ELF segment not in file.\n"); + return false; + } else if (phdr->p_paddr + phdr->p_memsz < phdr->p_paddr) { + pr_debug("ELF segment address wraps around.\n"); + return false; + } + + return true; +} + +static int elf_read_phdr(const char *buf, size_t len, struct elf_info *elf_info, + int idx) +{ + /* Override the const in proghdrs, we are the ones doing the loading. */ + struct elf_phdr *phdr = (struct elf_phdr *) &elf_info->proghdrs[idx]; + const char *pbuf; + struct elf_phdr *buf_phdr; + + pbuf = buf + elf_info->ehdr->e_phoff + (idx * sizeof(*buf_phdr)); + buf_phdr = (struct elf_phdr *) pbuf; + + phdr->p_type = elf32_to_cpu(elf_info->ehdr, buf_phdr->p_type); + phdr->p_offset = elf_addr_to_cpu(elf_info->ehdr, buf_phdr->p_offset); + phdr->p_paddr = elf_addr_to_cpu(elf_info->ehdr, buf_phdr->p_paddr); + phdr->p_vaddr = elf_addr_to_cpu(elf_info->ehdr, buf_phdr->p_vaddr); + phdr->p_flags = elf32_to_cpu(elf_info->ehdr, buf_phdr->p_flags); + + /* + * The following fields have a type equivalent to Elf_Addr + * both in 32 bit and 64 bit ELF. + */ + phdr->p_filesz = elf_addr_to_cpu(elf_info->ehdr, buf_phdr->p_filesz); + phdr->p_memsz = elf_addr_to_cpu(elf_info->ehdr, buf_phdr->p_memsz); + phdr->p_align = elf_addr_to_cpu(elf_info->ehdr, buf_phdr->p_align); + + return elf_is_phdr_sane(phdr, len) ? 0 : -ENOEXEC; +} + +/** + * elf_read_phdrs - read the program headers from the buffer + * + * This function assumes that the program header table was checked for sanity. + * Use elf_is_ehdr_sane() if it wasn't. + */ +static int elf_read_phdrs(const char *buf, size_t len, + struct elf_info *elf_info) +{ + size_t phdr_size, i; + const struct elfhdr *ehdr = elf_info->ehdr; + + /* + * e_phnum is at most 65535 so calculating the size of the + * program header cannot overflow. + */ + phdr_size = sizeof(struct elf_phdr) * ehdr->e_phnum; + + elf_info->proghdrs = kzalloc(phdr_size, GFP_KERNEL); + if (!elf_info->proghdrs) + return -ENOMEM; + + for (i = 0; i < ehdr->e_phnum; i++) { + int ret; + + ret = elf_read_phdr(buf, len, elf_info, i); + if (ret) { + kfree(elf_info->proghdrs); + elf_info->proghdrs = NULL; + return ret; + } + } + + return 0; +} + +/** + * elf_is_shdr_sane - check that it is safe to use the section header + * @buf_len: size of the buffer in which the ELF file is loaded. + */ +static bool elf_is_shdr_sane(const struct elf_shdr *shdr, size_t buf_len) +{ + bool size_ok; + + /* SHT_NULL headers have undefined values, so we can't check them. */ + if (shdr->sh_type == SHT_NULL) + return true; + + /* Now verify sh_entsize */ + switch (shdr->sh_type) { + case SHT_SYMTAB: + size_ok = shdr->sh_entsize == sizeof(Elf_Sym); + break; + case SHT_RELA: + size_ok = shdr->sh_entsize == sizeof(Elf_Rela); + break; + case SHT_DYNAMIC: + size_ok = shdr->sh_entsize == sizeof(Elf_Dyn); + break; + case SHT_REL: + size_ok = shdr->sh_entsize == sizeof(Elf_Rel); + break; + case SHT_NOTE: + case SHT_PROGBITS: + case SHT_HASH: + case SHT_NOBITS: + default: + /* + * This is a section whose entsize requirements + * I don't care about. If I don't know about + * the section I can't care about it's entsize + * requirements. + */ + size_ok = true; + break; + } + + if (!size_ok) { + pr_debug("ELF section with wrong entry size.\n"); + return false; + } else if (shdr->sh_addr + shdr->sh_size < shdr->sh_addr) { + pr_debug("ELF section address wraps around.\n"); + return false; + } + + if (shdr->sh_type != SHT_NOBITS) { + if (shdr->sh_offset + shdr->sh_size < shdr->sh_offset) { + pr_debug("ELF section location wraps around.\n"); + return false; + } else if (shdr->sh_offset + shdr->sh_size > buf_len) { + pr_debug("ELF section not in file.\n"); + return false; + } + } + + return true; +} + +static int elf_read_shdr(const char *buf, size_t len, struct elf_info *elf_info, + int idx) +{ + struct elf_shdr *shdr = &elf_info->sechdrs[idx]; + const struct elfhdr *ehdr = elf_info->ehdr; + const char *sbuf; + struct elf_shdr *buf_shdr; + + sbuf = buf + ehdr->e_shoff + idx * sizeof(*buf_shdr); + buf_shdr = (struct elf_shdr *) sbuf; + + shdr->sh_name = elf32_to_cpu(ehdr, buf_shdr->sh_name); + shdr->sh_type = elf32_to_cpu(ehdr, buf_shdr->sh_type); + shdr->sh_addr = elf_addr_to_cpu(ehdr, buf_shdr->sh_addr); + shdr->sh_offset = elf_addr_to_cpu(ehdr, buf_shdr->sh_offset); + shdr->sh_link = elf32_to_cpu(ehdr, buf_shdr->sh_link); + shdr->sh_info = elf32_to_cpu(ehdr, buf_shdr->sh_info); + + /* + * The following fields have a type equivalent to Elf_Addr + * both in 32 bit and 64 bit ELF. + */ + shdr->sh_flags = elf_addr_to_cpu(ehdr, buf_shdr->sh_flags); + shdr->sh_size = elf_addr_to_cpu(ehdr, buf_shdr->sh_size); + shdr->sh_addralign = elf_addr_to_cpu(ehdr, buf_shdr->sh_addralign); + shdr->sh_entsize = elf_addr_to_cpu(ehdr, buf_shdr->sh_entsize); + + return elf_is_shdr_sane(shdr, len) ? 0 : -ENOEXEC; +} + +/** + * elf_read_shdrs - read the section headers from the buffer + * + * This function assumes that the section header table was checked for sanity. + * Use elf_is_ehdr_sane() if it wasn't. + */ +static int elf_read_shdrs(const char *buf, size_t len, + struct elf_info *elf_info) +{ + size_t shdr_size, i; + + /* + * e_shnum is at most 65536 so calculating + * the size of the section header cannot overflow. + */ + shdr_size = sizeof(struct elf_shdr) * elf_info->ehdr->e_shnum; + + elf_info->sechdrs = kzalloc(shdr_size, GFP_KERNEL); + if (!elf_info->sechdrs) + return -ENOMEM; + + for (i = 0; i < elf_info->ehdr->e_shnum; i++) { + int ret; + + ret = elf_read_shdr(buf, len, elf_info, i); + if (ret) { + kfree(elf_info->sechdrs); + elf_info->sechdrs = NULL; + return ret; + } + } + + return 0; +} + +/** + * elf_read_from_buffer - read ELF file and sets up ELF header and ELF info + * @buf: Buffer to read ELF file from. + * @len: Size of @buf. + * @ehdr: Pointer to existing struct which will be populated. + * @elf_info: Pointer to existing struct which will be populated. + * + * This function allows reading ELF files with different byte order than + * the kernel, byte-swapping the fields as needed. + * + * Return: + * On success returns 0, and the caller should call elf_free_info(elf_info) to + * free the memory allocated for the section and program headers. + */ +int elf_read_from_buffer(const char *buf, size_t len, struct elfhdr *ehdr, + struct elf_info *elf_info) +{ + int ret; + + ret = elf_read_ehdr(buf, len, ehdr); + if (ret) + return ret; + + elf_info->buffer = buf; + elf_info->ehdr = ehdr; + if (ehdr->e_phoff > 0 && ehdr->e_phnum > 0) { + ret = elf_read_phdrs(buf, len, elf_info); + if (ret) + return ret; + } + if (ehdr->e_shoff > 0 && ehdr->e_shnum > 0) { + ret = elf_read_shdrs(buf, len, elf_info); + if (ret) { + kfree(elf_info->proghdrs); + return ret; + } + } + + return 0; +} + +/** + * elf_free_info - free memory allocated by elf_read_from_buffer + */ +void elf_free_info(struct elf_info *elf_info) +{ + kfree(elf_info->proghdrs); + kfree(elf_info->sechdrs); + memset(elf_info, 0, sizeof(*elf_info)); +} diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index 451a8e1cf57b..b9c65d8fee4e 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -160,7 +160,7 @@ __secondary_hold: cmpdi 0,r12,0 beq 100b -#if defined(CONFIG_SMP) || defined(CONFIG_KEXEC) +#if defined(CONFIG_SMP) || defined(CONFIG_KEXEC_CORE) #ifdef CONFIG_PPC_BOOK3E tovirt(r12,r12) #endif diff --git a/arch/powerpc/kernel/ima_kexec.c b/arch/powerpc/kernel/ima_kexec.c new file mode 100644 index 000000000000..5ea42c937ca9 --- /dev/null +++ b/arch/powerpc/kernel/ima_kexec.c @@ -0,0 +1,223 @@ +/* + * Copyright (C) 2016 IBM Corporation + * + * Authors: + * Thiago Jung Bauermann <bauerman@linux.vnet.ibm.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include <linux/slab.h> +#include <linux/kexec.h> +#include <linux/of.h> +#include <linux/memblock.h> +#include <linux/libfdt.h> + +static int get_addr_size_cells(int *addr_cells, int *size_cells) +{ + struct device_node *root; + + root = of_find_node_by_path("/"); + if (!root) + return -EINVAL; + + *addr_cells = of_n_addr_cells(root); + *size_cells = of_n_size_cells(root); + + of_node_put(root); + + return 0; +} + +static int do_get_kexec_buffer(const void *prop, int len, unsigned long *addr, + size_t *size) +{ + int ret, addr_cells, size_cells; + + ret = get_addr_size_cells(&addr_cells, &size_cells); + if (ret) + return ret; + + if (len < 4 * (addr_cells + size_cells)) + return -ENOENT; + + *addr = of_read_number(prop, addr_cells); + *size = of_read_number(prop + 4 * addr_cells, size_cells); + + return 0; +} + +/** + * ima_get_kexec_buffer - get IMA buffer from the previous kernel + * @addr: On successful return, set to point to the buffer contents. + * @size: On successful return, set to the buffer size. + * + * Return: 0 on success, negative errno on error. + */ +int ima_get_kexec_buffer(void **addr, size_t *size) +{ + int ret, len; + unsigned long tmp_addr; + size_t tmp_size; + const void *prop; + + prop = of_get_property(of_chosen, "linux,ima-kexec-buffer", &len); + if (!prop) + return -ENOENT; + + ret = do_get_kexec_buffer(prop, len, &tmp_addr, &tmp_size); + if (ret) + return ret; + + *addr = __va(tmp_addr); + *size = tmp_size; + + return 0; +} + +/** + * ima_free_kexec_buffer - free memory used by the IMA buffer + */ +int ima_free_kexec_buffer(void) +{ + int ret; + unsigned long addr; + size_t size; + struct property *prop; + + prop = of_find_property(of_chosen, "linux,ima-kexec-buffer", NULL); + if (!prop) + return -ENOENT; + + ret = do_get_kexec_buffer(prop->value, prop->length, &addr, &size); + if (ret) + return ret; + + ret = of_remove_property(of_chosen, prop); + if (ret) + return ret; + + return memblock_free(addr, size); + +} + +/** + * remove_ima_buffer - remove the IMA buffer property and reservation from @fdt + * + * The IMA measurement buffer is of no use to a subsequent kernel, so we always + * remove it from the device tree. + */ +void remove_ima_buffer(void *fdt, int chosen_node) +{ + int ret, len; + unsigned long addr; + size_t size; + const void *prop; + + prop = fdt_getprop(fdt, chosen_node, "linux,ima-kexec-buffer", &len); + if (!prop) + return; + + ret = do_get_kexec_buffer(prop, len, &addr, &size); + fdt_delprop(fdt, chosen_node, "linux,ima-kexec-buffer"); + if (ret) + return; + + ret = delete_fdt_mem_rsv(fdt, addr, size); + if (!ret) + pr_debug("Removed old IMA buffer reservation.\n"); +} + +#ifdef CONFIG_IMA_KEXEC +/** + * arch_ima_add_kexec_buffer - do arch-specific steps to add the IMA buffer + * + * Architectures should use this function to pass on the IMA buffer + * information to the next kernel. + * + * Return: 0 on success, negative errno on error. + */ +int arch_ima_add_kexec_buffer(struct kimage *image, unsigned long load_addr, + size_t size) +{ + image->arch.ima_buffer_addr = load_addr; + image->arch.ima_buffer_size = size; + + return 0; +} + +static int write_number(void *p, u64 value, int cells) +{ + if (cells == 1) { + u32 tmp; + + if (value > U32_MAX) + return -EINVAL; + + tmp = cpu_to_be32(value); + memcpy(p, &tmp, sizeof(tmp)); + } else if (cells == 2) { + u64 tmp; + + tmp = cpu_to_be64(value); + memcpy(p, &tmp, sizeof(tmp)); + } else + return -EINVAL; + + return 0; +} + +/** + * setup_ima_buffer - add IMA buffer information to the fdt + * @image: kexec image being loaded. + * @fdt: Flattened device tree for the next kernel. + * @chosen_node: Offset to the chosen node. + * + * Return: 0 on success, or negative errno on error. + */ +int setup_ima_buffer(const struct kimage *image, void *fdt, int chosen_node) +{ + int ret, addr_cells, size_cells, entry_size; + u8 value[16]; + + remove_ima_buffer(fdt, chosen_node); + if (!image->arch.ima_buffer_size) + return 0; + + ret = get_addr_size_cells(&addr_cells, &size_cells); + if (ret) + return ret; + + entry_size = 4 * (addr_cells + size_cells); + + if (entry_size > sizeof(value)) + return -EINVAL; + + ret = write_number(value, image->arch.ima_buffer_addr, addr_cells); + if (ret) + return ret; + + ret = write_number(value + 4 * addr_cells, image->arch.ima_buffer_size, + size_cells); + if (ret) + return ret; + + ret = fdt_setprop(fdt, chosen_node, "linux,ima-kexec-buffer", value, + entry_size); + if (ret < 0) + return -EINVAL; + + ret = fdt_add_mem_rsv(fdt, image->arch.ima_buffer_addr, + image->arch.ima_buffer_size); + if (ret) + return -EINVAL; + + pr_debug("IMA buffer at 0x%llx, size = 0x%zx\n", + image->arch.ima_buffer_addr, image->arch.ima_buffer_size); + + return 0; +} +#endif /* CONFIG_IMA_KEXEC */ diff --git a/arch/powerpc/kernel/kexec_elf_64.c b/arch/powerpc/kernel/kexec_elf_64.c new file mode 100644 index 000000000000..1bd1e9865835 --- /dev/null +++ b/arch/powerpc/kernel/kexec_elf_64.c @@ -0,0 +1,280 @@ +/* + * Load ELF vmlinux file for the kexec_file_load syscall. + * + * Copyright (C) 2004 Adam Litke (agl@us.ibm.com) + * Copyright (C) 2004 IBM Corp. + * Copyright (C) 2005 R Sharada (sharada@in.ibm.com) + * Copyright (C) 2006 Mohan Kumar M (mohan@in.ibm.com) + * Copyright (C) 2016 IBM Corporation + * + * Based on kexec-tools' kexec-elf-exec.c and kexec-elf-ppc64.c. + * Heavily modified for the kernel by + * Thiago Jung Bauermann <bauerman@linux.vnet.ibm.com>. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation (version 2 of the License). + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#define pr_fmt(fmt) "kexec_elf: " fmt + +#include <linux/types.h> +#include <linux/slab.h> +#include <linux/elf.h> +#include <linux/kexec.h> +#include <linux/of_fdt.h> +#include <linux/libfdt.h> +#include <asm/elf_util.h> + +#define PURGATORY_STACK_SIZE (16 * 1024) + +/** + * build_elf_exec_info - read ELF executable and check that we can use it + */ +static int build_elf_exec_info(const char *buf, size_t len, struct elfhdr *ehdr, + struct elf_info *elf_info) +{ + int i; + int ret; + + ret = elf_read_from_buffer(buf, len, ehdr, elf_info); + if (ret) + return ret; + + /* Big endian vmlinux has type ET_DYN. */ + if (ehdr->e_type != ET_EXEC && ehdr->e_type != ET_DYN) { + pr_err("Not an ELF executable.\n"); + goto error; + } else if (!elf_info->proghdrs) { + pr_err("No ELF program header.\n"); + goto error; + } + + for (i = 0; i < ehdr->e_phnum; i++) { + /* + * Kexec does not support loading interpreters. + * In addition this check keeps us from attempting + * to kexec ordinay executables. + */ + if (elf_info->proghdrs[i].p_type == PT_INTERP) { + pr_err("Requires an ELF interpreter.\n"); + goto error; + } + } + + return 0; +error: + elf_free_info(elf_info); + return -ENOEXEC; +} + +static int elf64_probe(const char *buf, unsigned long len) +{ + struct elfhdr ehdr; + struct elf_info elf_info; + int ret; + + ret = build_elf_exec_info(buf, len, &ehdr, &elf_info); + if (ret) + return ret; + + elf_free_info(&elf_info); + + return elf_check_arch(&ehdr) ? 0 : -ENOEXEC; +} + +/** + * elf_exec_load - load ELF executable image + * @lowest_load_addr: On return, will be the address where the first PT_LOAD + * section will be loaded in memory. + * + * Return: + * 0 on success, negative value on failure. + */ +static int elf_exec_load(struct kimage *image, struct elfhdr *ehdr, + struct elf_info *elf_info, + unsigned long *lowest_load_addr) +{ + unsigned long base = 0, lowest_addr = UINT_MAX; + int ret; + size_t i; + struct kexec_buf kbuf = { .image = image, .buf_max = ppc64_rma_size, + .top_down = false }; + + /* Read in the PT_LOAD segments. */ + for (i = 0; i < ehdr->e_phnum; i++) { + unsigned long load_addr; + size_t size; + const struct elf_phdr *phdr; + + phdr = &elf_info->proghdrs[i]; + if (phdr->p_type != PT_LOAD) + continue; + + size = phdr->p_filesz; + if (size > phdr->p_memsz) + size = phdr->p_memsz; + + kbuf.buffer = (void *) elf_info->buffer + phdr->p_offset; + kbuf.bufsz = size; + kbuf.memsz = phdr->p_memsz; + kbuf.buf_align = phdr->p_align; + kbuf.buf_min = phdr->p_paddr + base; + ret = kexec_add_buffer(&kbuf); + if (ret) + goto out; + load_addr = kbuf.mem; + + if (load_addr < lowest_addr) + lowest_addr = load_addr; + } + + /* Update entry point to reflect new load address. */ + ehdr->e_entry += base; + + *lowest_load_addr = lowest_addr; + ret = 0; + out: + return ret; +} + +static void *elf64_load(struct kimage *image, char *kernel_buf, + unsigned long kernel_len, char *initrd, + unsigned long initrd_len, char *cmdline, + unsigned long cmdline_len) +{ + int i, ret; + unsigned int fdt_size; + unsigned long kernel_load_addr, purgatory_load_addr; + unsigned long initrd_load_addr = 0, fdt_load_addr, stack_top; + void *fdt; + const void *slave_code; + struct elfhdr ehdr; + struct elf_info elf_info; + struct fdt_reserve_entry *rsvmap; + struct kexec_buf kbuf = { .image = image, .buf_min = 0, + .buf_max = ppc64_rma_size }; + + ret = build_elf_exec_info(kernel_buf, kernel_len, &ehdr, &elf_info); + if (ret) + goto out; + + ret = elf_exec_load(image, &ehdr, &elf_info, &kernel_load_addr); + if (ret) + goto out; + + pr_debug("Loaded the kernel at 0x%lx\n", kernel_load_addr); + + ret = kexec_load_purgatory(image, 0, ppc64_rma_size, true, + &purgatory_load_addr); + if (ret) { + pr_err("Loading purgatory failed.\n"); + goto out; + } + + pr_debug("Loaded purgatory at 0x%lx\n", purgatory_load_addr); + + if (initrd != NULL) { + kbuf.buffer = initrd; + kbuf.bufsz = kbuf.memsz = initrd_len; + kbuf.buf_align = PAGE_SIZE; + kbuf.top_down = false; + ret = kexec_add_buffer(&kbuf); + if (ret) + goto out; + initrd_load_addr = kbuf.mem; + + pr_debug("Loaded initrd at 0x%lx\n", initrd_load_addr); + } + + fdt_size = fdt_totalsize(initial_boot_params) * 2; + fdt = kmalloc(fdt_size, GFP_KERNEL); + if (!fdt) { + pr_err("Not enough memory for the device tree.\n"); + ret = -ENOMEM; + goto out; + } + ret = fdt_open_into(initial_boot_params, fdt, fdt_size); + if (ret < 0) { + pr_err("Error setting up the new device tree.\n"); + ret = -EINVAL; + goto out; + } + + ret = setup_new_fdt(image, fdt, initrd_load_addr, initrd_len, cmdline); + if (ret) + goto out; + + /* + * Documentation/devicetree/booting-without-of.txt says we need to + * add a reservation entry for the device tree block, but + * early_init_fdt_reserve_self reserves the memory even if there's no + * such entry. We'll add a reservation entry anyway, to be safe and + * compliant. + * + * Use dummy values, we will correct them in a moment. + */ + ret = fdt_add_mem_rsv(fdt, 1, 1); + if (ret) { + pr_err("Error reserving device tree memory: %s\n", + fdt_strerror(ret)); + ret = -EINVAL; + goto out; + } + fdt_pack(fdt); + + kbuf.buffer = fdt; + kbuf.bufsz = kbuf.memsz = fdt_size; + kbuf.buf_align = PAGE_SIZE; + kbuf.top_down = true; + ret = kexec_add_buffer(&kbuf); + if (ret) + goto out; + fdt_load_addr = kbuf.mem; + + /* + * Fix fdt reservation, now that we now where it will be loaded + * and how big it is. + */ + rsvmap = fdt + fdt_off_mem_rsvmap(fdt); + i = fdt_num_mem_rsv(fdt) - 1; + rsvmap[i].address = cpu_to_fdt64(fdt_load_addr); + rsvmap[i].size = cpu_to_fdt64(fdt_totalsize(fdt)); + + pr_debug("Loaded device tree at 0x%lx\n", fdt_load_addr); + + kbuf.memsz = PURGATORY_STACK_SIZE; + kbuf.buf_align = PAGE_SIZE; + kbuf.top_down = true; + ret = kexec_locate_mem_hole(&kbuf); + if (ret) { + pr_err("Couldn't find free memory for the purgatory stack.\n"); + ret = -ENOMEM; + goto out; + } + stack_top = kbuf.mem + PURGATORY_STACK_SIZE - 1; + pr_debug("Purgatory stack is at 0x%lx\n", stack_top); + + slave_code = elf_info.buffer + elf_info.proghdrs[0].p_offset; + ret = setup_purgatory(image, slave_code, fdt, kernel_load_addr, + fdt_load_addr, stack_top, + find_debug_console(fdt)); + if (ret) + pr_err("Error setting up the purgatory.\n"); + +out: + elf_free_info(&elf_info); + + /* Make kimage_file_post_load_cleanup free the fdt buffer for us. */ + return ret ? ERR_PTR(ret) : fdt; +} + +struct kexec_file_ops kexec_elf64_ops = { + .probe = elf64_probe, + .load = elf64_load, +}; diff --git a/arch/powerpc/kernel/machine_kexec_file_64.c b/arch/powerpc/kernel/machine_kexec_file_64.c new file mode 100644 index 000000000000..e4da26dabbaf --- /dev/null +++ b/arch/powerpc/kernel/machine_kexec_file_64.c @@ -0,0 +1,588 @@ +/* + * ppc64 code to implement the kexec_file_load syscall + * + * Copyright (C) 2004 Adam Litke (agl@us.ibm.com) + * Copyright (C) 2004 IBM Corp. + * Copyright (C) 2004,2005 Milton D Miller II, IBM Corporation + * Copyright (C) 2005 R Sharada (sharada@in.ibm.com) + * Copyright (C) 2006 Mohan Kumar M (mohan@in.ibm.com) + * Copyright (C) 2016 IBM Corporation + * + * Based on kexec-tools' kexec-elf-ppc64.c, fs2dt.c. + * Heavily modified for the kernel by + * Thiago Jung Bauermann <bauerman@linux.vnet.ibm.com>. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation (version 2 of the License). + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include <linux/slab.h> +#include <linux/kexec.h> +#include <linux/memblock.h> +#include <linux/of_fdt.h> +#include <linux/libfdt.h> +#include <asm/elf_util.h> +#include <asm/ima.h> + +#define SLAVE_CODE_SIZE 256 + +static struct kexec_file_ops *kexec_file_loaders[] = { + &kexec_elf64_ops, +}; + +int arch_kexec_kernel_image_probe(struct kimage *image, void *buf, + unsigned long buf_len) +{ + int i, ret = -ENOEXEC; + struct kexec_file_ops *fops; + + /* We don't support crash kernels yet. */ + if (image->type == KEXEC_TYPE_CRASH) + return -ENOTSUPP; + + for (i = 0; i < ARRAY_SIZE(kexec_file_loaders); i++) { + fops = kexec_file_loaders[i]; + if (!fops || !fops->probe) + continue; + + ret = fops->probe(buf, buf_len); + if (!ret) { + image->fops = fops; + return ret; + } + } + + return ret; +} + +void *arch_kexec_kernel_image_load(struct kimage *image) +{ + if (!image->fops || !image->fops->load) + return ERR_PTR(-ENOEXEC); + + return image->fops->load(image, image->kernel_buf, + image->kernel_buf_len, image->initrd_buf, + image->initrd_buf_len, image->cmdline_buf, + image->cmdline_buf_len); +} + +int arch_kimage_file_post_load_cleanup(struct kimage *image) +{ + if (!image->fops || !image->fops->cleanup) + return 0; + + return image->fops->cleanup(image->image_loader_data); +} + +/** + * arch_kexec_walk_mem - call func(data) for each unreserved memory block + * @kbuf: Context info for the search. Also passed to @func. + * @func: Function to call for each memory block. + * + * This function is used by kexec_add_buffer and kexec_locate_mem_hole + * to find unreserved memory to load kexec segments into. + * + * Return: The memory walk will stop when func returns a non-zero value + * and that value will be returned. If all free regions are visited without + * func returning non-zero, then zero will be returned. + */ +int arch_kexec_walk_mem(struct kexec_buf *kbuf, int (*func)(u64, u64, void *)) +{ + int ret = 0; + u64 i; + phys_addr_t mstart, mend; + + if (kbuf->top_down) { + for_each_free_mem_range_reverse(i, NUMA_NO_NODE, 0, + &mstart, &mend, NULL) { + /* + * In memblock, end points to the first byte after the + * range while in kexec, end points to the last byte + * in the range. + */ + ret = func(mstart, mend - 1, kbuf); + if (ret) + break; + } + } else { + for_each_free_mem_range(i, NUMA_NO_NODE, 0, &mstart, &mend, + NULL) { + /* + * In memblock, end points to the first byte after the + * range while in kexec, end points to the last byte + * in the range. + */ + ret = func(mstart, mend - 1, kbuf); + if (ret) + break; + } + } + + return ret; +} + +/** + * arch_kexec_apply_relocations_add - apply purgatory relocations + * @ehdr: Pointer to ELF headers. + * @sechdrs: Pointer to section headers. + * @relsec: Section index of SHT_RELA section. + * + * Elf64_Shdr.sh_offset has been modified to keep the pointer to the section + * contents, while Elf64_Shdr.sh_addr points to the final address of the + * section in memory. + */ +int arch_kexec_apply_relocations_add(const Elf64_Ehdr *ehdr, + Elf64_Shdr *sechdrs, unsigned int relsec) +{ + unsigned int i; + int ret; + int reloc_type; + unsigned long *location; + unsigned long address; + unsigned long value; + const char *name; + Elf64_Sym *sym; + /* Section containing the relocation entries. */ + Elf64_Shdr *rel_section = &sechdrs[relsec]; + const Elf64_Rela *rela = (const Elf64_Rela *) rel_section->sh_offset; + /* Section to which relocations apply. */ + Elf64_Shdr *target_section = &sechdrs[rel_section->sh_info]; + /* Associated symbol table. */ + Elf64_Shdr *symtabsec = &sechdrs[rel_section->sh_link]; + void *syms_base = (void *) symtabsec->sh_offset; + void *loc_base = (void *) target_section->sh_offset; + Elf64_Addr addr_base = target_section->sh_addr; + unsigned long sec_base; + unsigned long r2; + unsigned int toc; + const char *strtab; + + if (symtabsec->sh_link >= ehdr->e_shnum) { + /* Invalid strtab section number */ + pr_err("Invalid string table section index %d\n", + symtabsec->sh_link); + return -ENOEXEC; + } + + toc = elf_toc_section(ehdr, sechdrs); + if (!toc) { + pr_err("Purgatory TOC section not found."); + return -ENOEXEC; + } + + r2 = elf_my_r2(sechdrs, toc); + + /* String table for the associated symbol table. */ + strtab = (const char *) sechdrs[symtabsec->sh_link].sh_offset; + + for (i = 0; i < rel_section->sh_size / sizeof(Elf64_Rela); i++) { + /* + * rels[i].r_offset contains the byte offset from the beginning + * of section to the storage unit affected. + * + * This is the location to update in the temporary buffer where + * the section is currently loaded. The section will finally + * be loaded to a different address later, pointed to by + * addr_base. + */ + location = loc_base + rela[i].r_offset; + + /* Final address of the location. */ + address = addr_base + rela[i].r_offset; + + /* This is the symbol the relocation is referring to. */ + sym = (Elf64_Sym *) syms_base + ELF64_R_SYM(rela[i].r_info); + + if (sym->st_name) + name = strtab + sym->st_name; + else + name = "<unnamed symbol>"; + + reloc_type = ELF64_R_TYPE(rela[i].r_info); + + pr_debug("RELOC at %p: %i-type as %s (0x%lx) + %li\n", + location, reloc_type, name, (unsigned long)sym->st_value, + (long)rela[i].r_addend); + + /* + * TOC symbols appear as undefined but should be + * resolved as well, so allow them to be processed. + */ + if (sym->st_shndx == SHN_UNDEF && strcmp(name, ".TOC.") != 0 && + reloc_type != R_PPC64_TOC) { + pr_err("Undefined symbol: %s\n", name); + return -ENOEXEC; + } else if (sym->st_shndx == SHN_COMMON) { + pr_err("Symbol '%s' in common section.\n", + name); + return -ENOEXEC; + } + + if (sym->st_shndx != SHN_ABS) { + if (sym->st_shndx >= ehdr->e_shnum) { + pr_err("Invalid section %d for symbol %s\n", + sym->st_shndx, name); + return -ENOEXEC; + } + + sec_base = sechdrs[sym->st_shndx].sh_addr; + } else + sec_base = 0; + + /* `Everything is relative'. */ + value = sym->st_value + sec_base + rela[i].r_addend; + + ret = elf64_apply_relocate_add_item(sechdrs, strtab, &rela[i], + sym, location, address, + value, r2, + "kexec purgatory", NULL); + if (ret) + return ret; + } + + return 0; +} + +/** + * setup_purgatory - initialize the purgatory's global variables + * @image: kexec image. + * @slave_code: Slave code for the purgatory. + * @fdt: Flattened device tree for the next kernel. + * @kernel_load_addr: Address where the kernel is loaded. + * @fdt_load_addr: Address where the flattened device tree is loaded. + * @stack_top: Address where the purgatory can place its stack. + * @debug: Can the purgatory print messages to the console? + * + * Return: 0 on success, or negative errno on error. + */ +int setup_purgatory(struct kimage *image, const void *slave_code, + const void *fdt, unsigned long kernel_load_addr, + unsigned long fdt_load_addr, unsigned long stack_top, + int debug) +{ + int ret, tree_node; + const void *prop; + unsigned long opal_base, opal_entry; + uint64_t toc; + unsigned int *slave_code_buf, master_entry; + unsigned int toc_section; + + slave_code_buf = kmalloc(SLAVE_CODE_SIZE, GFP_KERNEL); + if (!slave_code_buf) + return -ENOMEM; + + /* Get the slave code from the new kernel and put it in purgatory. */ + ret = kexec_purgatory_get_set_symbol(image, "purgatory_start", + slave_code_buf, SLAVE_CODE_SIZE, + true); + if (ret) { + kfree(slave_code_buf); + return ret; + } + + master_entry = slave_code_buf[0]; + memcpy(slave_code_buf, slave_code, SLAVE_CODE_SIZE); + slave_code_buf[0] = master_entry; + ret = kexec_purgatory_get_set_symbol(image, "purgatory_start", + slave_code_buf, SLAVE_CODE_SIZE, + false); + kfree(slave_code_buf); + + ret = kexec_purgatory_get_set_symbol(image, "kernel", &kernel_load_addr, + sizeof(kernel_load_addr), false); + if (ret) + return ret; + ret = kexec_purgatory_get_set_symbol(image, "dt_offset", &fdt_load_addr, + sizeof(fdt_load_addr), false); + if (ret) + return ret; + + tree_node = fdt_path_offset(fdt, "/ibm,opal"); + if (tree_node >= 0) { + prop = fdt_getprop(fdt, tree_node, "opal-base-address", NULL); + if (!prop) { + pr_err("OPAL address not found in the device tree.\n"); + return -EINVAL; + } + opal_base = fdt64_to_cpu((const fdt64_t *) prop); + + prop = fdt_getprop(fdt, tree_node, "opal-entry-address", NULL); + if (!prop) { + pr_err("OPAL address not found in the device tree.\n"); + return -EINVAL; + } + opal_entry = fdt64_to_cpu((const fdt64_t *) prop); + + ret = kexec_purgatory_get_set_symbol(image, "opal_base", + &opal_base, + sizeof(opal_base), false); + if (ret) + return ret; + ret = kexec_purgatory_get_set_symbol(image, "opal_entry", + &opal_entry, + sizeof(opal_entry), false); + if (ret) + return ret; + } + + ret = kexec_purgatory_get_set_symbol(image, "stack", &stack_top, + sizeof(stack_top), false); + if (ret) + return ret; + + toc_section = elf_toc_section(image->purgatory_info.ehdr, + image->purgatory_info.sechdrs); + if (!toc_section) + return -ENOEXEC; + + toc = elf_my_r2(image->purgatory_info.sechdrs, toc_section); + ret = kexec_purgatory_get_set_symbol(image, "my_toc", &toc, sizeof(toc), + false); + if (ret) + return ret; + + pr_debug("Purgatory TOC is at 0x%llx\n", toc); + + ret = kexec_purgatory_get_set_symbol(image, "debug", &debug, + sizeof(debug), false); + if (ret) + return ret; + if (!debug) + pr_debug("Disabling purgatory output.\n"); + + return 0; +} + +/** + * delete_fdt_mem_rsv - delete memory reservation with given address and size + * + * Return: 0 on success, or negative errno on error. + */ +int delete_fdt_mem_rsv(void *fdt, unsigned long start, unsigned long size) +{ + int i, ret, num_rsvs = fdt_num_mem_rsv(fdt); + + for (i = 0; i < num_rsvs; i++) { + uint64_t rsv_start, rsv_size; + + ret = fdt_get_mem_rsv(fdt, i, &rsv_start, &rsv_size); + if (ret) { + pr_err("Malformed device tree.\n"); + return -EINVAL; + } + + if (rsv_start == start && rsv_size == size) { + ret = fdt_del_mem_rsv(fdt, i); + if (ret) { + pr_err("Error deleting device tree reservation.\n"); + return -EINVAL; + } + + return 0; + } + } + + return -ENOENT; +} + +/* + * setup_new_fdt - modify /chosen and memory reservation for the next kernel + * @image: kexec image being loaded. + * @fdt: Flattened device tree for the next kernel. + * @initrd_load_addr: Address where the next initrd will be loaded. + * @initrd_len: Size of the next initrd, or 0 if there will be none. + * @cmdline: Command line for the next kernel, or NULL if there will + * be none. + * + * Return: 0 on success, or negative errno on error. + */ +int setup_new_fdt(const struct kimage *image, void *fdt, + unsigned long initrd_load_addr, unsigned long initrd_len, + const char *cmdline) +{ + int ret, chosen_node; + const void *prop; + + /* Remove memory reservation for the current device tree. */ + ret = delete_fdt_mem_rsv(fdt, __pa(initial_boot_params), + fdt_totalsize(initial_boot_params)); + if (ret == 0) + pr_debug("Removed old device tree reservation.\n"); + else if (ret != -ENOENT) + return ret; + + chosen_node = fdt_path_offset(fdt, "/chosen"); + if (chosen_node == -FDT_ERR_NOTFOUND) { + chosen_node = fdt_add_subnode(fdt, fdt_path_offset(fdt, "/"), + "chosen"); + if (chosen_node < 0) { + pr_err("Error creating /chosen.\n"); + return -EINVAL; + } + } else if (chosen_node < 0) { + pr_err("Malformed device tree: error reading /chosen.\n"); + return -EINVAL; + } + + /* Did we boot using an initrd? */ + prop = fdt_getprop(fdt, chosen_node, "linux,initrd-start", NULL); + if (prop) { + uint64_t tmp_start, tmp_end, tmp_size; + + tmp_start = fdt64_to_cpu(*((const fdt64_t *) prop)); + + prop = fdt_getprop(fdt, chosen_node, "linux,initrd-end", NULL); + if (!prop) { + pr_err("Malformed device tree.\n"); + return -EINVAL; + } + tmp_end = fdt64_to_cpu(*((const fdt64_t *) prop)); + + /* + * kexec reserves exact initrd size, while firmware may + * reserve a multiple of PAGE_SIZE, so check for both. + */ + tmp_size = tmp_end - tmp_start; + ret = delete_fdt_mem_rsv(fdt, tmp_start, tmp_size); + if (ret == -ENOENT) + ret = delete_fdt_mem_rsv(fdt, tmp_start, + round_up(tmp_size, PAGE_SIZE)); + if (ret == 0) + pr_debug("Removed old initrd reservation.\n"); + else if (ret != -ENOENT) + return ret; + + /* If there's no new initrd, delete the old initrd's info. */ + if (initrd_len == 0) { + ret = fdt_delprop(fdt, chosen_node, + "linux,initrd-start"); + if (ret) { + pr_err("Error deleting linux,initrd-start.\n"); + return -EINVAL; + } + + ret = fdt_delprop(fdt, chosen_node, "linux,initrd-end"); + if (ret) { + pr_err("Error deleting linux,initrd-end.\n"); + return -EINVAL; + } + } + } + + if (initrd_len) { + ret = fdt_setprop_u64(fdt, chosen_node, + "linux,initrd-start", + initrd_load_addr); + if (ret < 0) { + pr_err("Error setting up the new device tree.\n"); + return -EINVAL; + } + + /* initrd-end is the first address after the initrd image. */ + ret = fdt_setprop_u64(fdt, chosen_node, "linux,initrd-end", + initrd_load_addr + initrd_len); + if (ret < 0) { + pr_err("Error setting up the new device tree.\n"); + return -EINVAL; + } + + ret = fdt_add_mem_rsv(fdt, initrd_load_addr, initrd_len); + if (ret) { + pr_err("Error reserving initrd memory: %s\n", + fdt_strerror(ret)); + return -EINVAL; + } + } + + if (cmdline != NULL) { + ret = fdt_setprop_string(fdt, chosen_node, "bootargs", cmdline); + if (ret < 0) { + pr_err("Error setting up the new device tree.\n"); + return -EINVAL; + } + } else { + ret = fdt_delprop(fdt, chosen_node, "bootargs"); + if (ret && ret != -FDT_ERR_NOTFOUND) { + pr_err("Error deleting bootargs.\n"); + return -EINVAL; + } + } + + ret = setup_ima_buffer(image, fdt, chosen_node); + if (ret) { + pr_err("Error setting up the new device tree.\n"); + return ret; + } + + ret = fdt_setprop(fdt, chosen_node, "linux,booted-from-kexec", NULL, 0); + if (ret) { + pr_err("Error setting up the new device tree.\n"); + return -EINVAL; + } + + return 0; +} + +/** + * find_debug_console - find out whether there is a console for the purgatory + * @fdt: Flattened device tree to search. + */ +bool find_debug_console(const void *fdt) +{ + int len; + int console_node, chosen_node; + const void *prop, *colon; + + chosen_node = fdt_path_offset(fdt, "/chosen"); + if (chosen_node < 0) { + pr_err("Malformed device tree: /chosen not found.\n"); + return false; + } + + prop = fdt_getprop(fdt, chosen_node, "stdout-path", &len); + if (prop == NULL) { + if (len == -FDT_ERR_NOTFOUND) { + prop = fdt_getprop(fdt, chosen_node, + "linux,stdout-path", &len); + if (prop == NULL) { + pr_debug("Unable to find [linux,]stdout-path.\n"); + return false; + } + } else { + pr_debug("Error finding console: %s\n", + fdt_strerror(len)); + return false; + } + } + + /* + * stdout-path can have a ':' separating the path from device-specific + * information, so we should only consider what's before it. + */ + colon = strchr(prop, ':'); + if (colon != NULL) + len = colon - prop; + else + len -= 1; /* Ignore the terminating NUL. */ + + console_node = fdt_path_offset_namelen(fdt, prop, len); + if (console_node < 0) { + pr_debug("Error finding console: %s\n", + fdt_strerror(console_node)); + return false; + } + + if (fdt_node_check_compatible(fdt, console_node, "hvterm1") == 0) + return true; + else if (fdt_node_check_compatible(fdt, console_node, + "hvterm-protocol") == 0) + return true; + + return false; +} diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S index 93cf7a5846a6..1863324c6a3c 100644 --- a/arch/powerpc/kernel/misc_32.S +++ b/arch/powerpc/kernel/misc_32.S @@ -614,7 +614,7 @@ _GLOBAL(start_secondary_resume) _GLOBAL(__main) blr -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE /* * Must be relocatable PIC code callable as a C function. */ diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S index 4f178671f230..32be2a844947 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -478,7 +478,7 @@ _GLOBAL(kexec_wait) addi r5,r5,kexec_flag-1b 99: HMT_LOW -#ifdef CONFIG_KEXEC /* use no memory without kexec */ +#ifdef CONFIG_KEXEC_CORE /* use no memory without kexec */ lwz r4,0(r5) cmpwi 0,r4,0 beq 99b @@ -503,7 +503,7 @@ kexec_flag: .long 0 -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE #ifdef CONFIG_PPC_BOOK3E /* * BOOK3E has no real MMU mode, so we have to setup the initial TLB @@ -716,4 +716,4 @@ _GLOBAL(kexec_sequence) mtlr 4 li r5,0 blr /* image->start(physid, image->start, 0); */ -#endif /* CONFIG_KEXEC */ +#endif /* CONFIG_KEXEC_CORE */ diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index bb1807184bad..12c88c34e696 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -507,6 +507,224 @@ static int restore_r2(u32 *instruction, struct module *me) return 1; } +int elf64_apply_relocate_add_item(const Elf64_Shdr *sechdrs, const char *strtab, + const Elf64_Rela *rela, const Elf64_Sym *sym, + unsigned long *location, + unsigned long address, unsigned long value, + unsigned long my_r2, const char *obj_name, + struct module *me) +{ + switch (ELF64_R_TYPE(rela->r_info)) { + case R_PPC64_ADDR32: + /* Simply set it */ + *(u32 *)location = value; + break; + + case R_PPC64_ADDR64: + /* Simply set it */ + *(unsigned long *)location = value; + break; + + case R_PPC64_TOC: + *(unsigned long *)location = my_r2; + break; + + case R_PPC64_TOC16: + /* Subtract TOC pointer */ + value -= my_r2; + if (value + 0x8000 > 0xffff) { + pr_err("%s: bad TOC16 relocation (0x%lx)\n", + obj_name, value); + return -ENOEXEC; + } + *((uint16_t *) location) + = (*((uint16_t *) location) & ~0xffff) + | (value & 0xffff); + break; + + case R_PPC64_TOC16_LO: + /* Subtract TOC pointer */ + value -= my_r2; + *((uint16_t *) location) + = (*((uint16_t *) location) & ~0xffff) + | (value & 0xffff); + break; + + case R_PPC64_TOC16_DS: + /* Subtract TOC pointer */ + value -= my_r2; + if ((value & 3) != 0 || value + 0x8000 > 0xffff) { + pr_err("%s: bad TOC16_DS relocation (0x%lx)\n", + obj_name, value); + return -ENOEXEC; + } + *((uint16_t *) location) + = (*((uint16_t *) location) & ~0xfffc) + | (value & 0xfffc); + break; + + case R_PPC64_TOC16_LO_DS: + /* Subtract TOC pointer */ + value -= my_r2; + if ((value & 3) != 0) { + pr_err("%s: bad TOC16_LO_DS relocation (0x%lx)\n", + obj_name, value); + return -ENOEXEC; + } + *((uint16_t *) location) + = (*((uint16_t *) location) & ~0xfffc) + | (value & 0xfffc); + break; + + case R_PPC64_TOC16_HA: + /* Subtract TOC pointer */ + value -= my_r2; + value = ((value + 0x8000) >> 16); + *((uint16_t *) location) + = (*((uint16_t *) location) & ~0xffff) + | (value & 0xffff); + break; + + case R_PPC64_REL14: + /* Convert value to relative */ + value -= address; + if (value + 0x8000 > 0xffff || (value & 3) != 0) { + pr_err("%s: REL14 %li out of range!\n", + obj_name, (long int) value); + return -ENOEXEC; + } + + /* Only replace bits 2 through 16 */ + *(uint32_t *)location + = (*(uint32_t *)location & ~0xfffc) + | (value & 0xfffc); + break; + + case R_PPC_REL24: + /* FIXME: Handle weak symbols here --RR */ + if (sym->st_shndx == SHN_UNDEF) { + /* + * The purgatory relocation code passes NULL for me, + * but the purgatory doesn't have any REL24 relocations + * for undefined symbols, so if this happens it's a bug. + */ + if (WARN_ON(!me)) + return -ENOEXEC; + + /* External: go via stub */ + value = stub_for_addr(sechdrs, value, me); + if (!value) + return -ENOENT; + if (!restore_r2((u32 *)location + 1, me)) + return -ENOEXEC; + + squash_toc_save_inst(strtab + sym->st_name, value); + } else + value += local_entry_offset(sym); + + /* Convert value to relative */ + value -= address; + if (value + 0x2000000 > 0x3ffffff || (value & 3) != 0) { + pr_err("%s: REL24 %li out of range!\n", + obj_name, (long int)value); + return -ENOEXEC; + } + + /* Only replace bits 2 through 26 */ + *(uint32_t *)location + = (*(uint32_t *)location & ~0x03fffffc) + | (value & 0x03fffffc); + break; + + case R_PPC64_REL64: + /* 64 bits relative (used by features fixups) */ + *location = value - address; + break; + + case R_PPC64_REL32: + /* 32 bits relative (used by relative exception tables) */ + *(u32 *)location = value - (unsigned long)location; + break; + + case R_PPC64_TOCSAVE: + /* + * Marker reloc indicates we don't have to save r2. + * That would only save us one instruction, so ignore + * it. + */ + break; + + case R_PPC64_ENTRY: + /* + * Optimize ELFv2 large code model entry point if + * the TOC is within 2GB range of current location. + */ + value = my_r2 - address; + if (value + 0x80008000 > 0xffffffff) + break; + /* + * Check for the large code model prolog sequence: + * ld r2, ...(r12) + * add r2, r2, r12 + */ + if ((((uint32_t *)location)[0] & ~0xfffc) + != 0xe84c0000) + break; + if (((uint32_t *)location)[1] != 0x7c426214) + break; + /* + * If found, replace it with: + * addis r2, r12, (.TOC.-func)@ha + * addi r2, r12, (.TOC.-func)@l + */ + ((uint32_t *)location)[0] = 0x3c4c0000 + PPC_HA(value); + ((uint32_t *)location)[1] = 0x38420000 + PPC_LO(value); + break; + + case R_PPC64_ADDR16_LO: + *(uint16_t *)location = value & 0xffff; + break; + + case R_PPC64_ADDR16_HI: + *(uint16_t *)location = (value >> 16) & 0xffff; + break; + + case R_PPC64_ADDR16_HIGHER: + *(uint16_t *)location = (((uint64_t)value >> 32) & + 0xffff); + break; + + case R_PPC64_ADDR16_HIGHEST: + *(uint16_t *)location = (((uint64_t)value >> 48) & + 0xffff); + break; + + case R_PPC64_REL16_HA: + /* Subtract location pointer */ + value -= address; + value = ((value + 0x8000) >> 16); + *((uint16_t *) location) + = (*((uint16_t *) location) & ~0xffff) + | (value & 0xffff); + break; + + case R_PPC64_REL16_LO: + /* Subtract location pointer */ + value -= address; + *((uint16_t *) location) + = (*((uint16_t *) location) & ~0xffff) + | (value & 0xffff); + break; + + default: + pr_err("%s: Unknown ADD relocation: %lu\n", obj_name, + (unsigned long)ELF64_R_TYPE(rela->r_info)); + return -ENOEXEC; + } + + return 0; +} + int apply_relocate_add(Elf64_Shdr *sechdrs, const char *strtab, unsigned int symindex, @@ -514,6 +732,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, struct module *me) { unsigned int i; + int ret; Elf64_Rela *rela = (void *)sechdrs[relsec].sh_addr; Elf64_Sym *sym; unsigned long *location; @@ -548,173 +767,13 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, /* `Everything is relative'. */ value = sym->st_value + rela[i].r_addend; - switch (ELF64_R_TYPE(rela[i].r_info)) { - case R_PPC64_ADDR32: - /* Simply set it */ - *(u32 *)location = value; - break; - - case R_PPC64_ADDR64: - /* Simply set it */ - *(unsigned long *)location = value; - break; - - case R_PPC64_TOC: - *(unsigned long *)location = my_r2(sechdrs, me); - break; - - case R_PPC64_TOC16: - /* Subtract TOC pointer */ - value -= my_r2(sechdrs, me); - if (value + 0x8000 > 0xffff) { - pr_err("%s: bad TOC16 relocation (0x%lx)\n", - me->name, value); - return -ENOEXEC; - } - *((uint16_t *) location) - = (*((uint16_t *) location) & ~0xffff) - | (value & 0xffff); - break; - - case R_PPC64_TOC16_LO: - /* Subtract TOC pointer */ - value -= my_r2(sechdrs, me); - *((uint16_t *) location) - = (*((uint16_t *) location) & ~0xffff) - | (value & 0xffff); - break; - - case R_PPC64_TOC16_DS: - /* Subtract TOC pointer */ - value -= my_r2(sechdrs, me); - if ((value & 3) != 0 || value + 0x8000 > 0xffff) { - pr_err("%s: bad TOC16_DS relocation (0x%lx)\n", - me->name, value); - return -ENOEXEC; - } - *((uint16_t *) location) - = (*((uint16_t *) location) & ~0xfffc) - | (value & 0xfffc); - break; - - case R_PPC64_TOC16_LO_DS: - /* Subtract TOC pointer */ - value -= my_r2(sechdrs, me); - if ((value & 3) != 0) { - pr_err("%s: bad TOC16_LO_DS relocation (0x%lx)\n", - me->name, value); - return -ENOEXEC; - } - *((uint16_t *) location) - = (*((uint16_t *) location) & ~0xfffc) - | (value & 0xfffc); - break; - - case R_PPC64_TOC16_HA: - /* Subtract TOC pointer */ - value -= my_r2(sechdrs, me); - value = ((value + 0x8000) >> 16); - *((uint16_t *) location) - = (*((uint16_t *) location) & ~0xffff) - | (value & 0xffff); - break; - - case R_PPC_REL24: - /* FIXME: Handle weak symbols here --RR */ - if (sym->st_shndx == SHN_UNDEF) { - /* External: go via stub */ - value = stub_for_addr(sechdrs, value, me); - if (!value) - return -ENOENT; - if (!restore_r2((u32 *)location + 1, me)) - return -ENOEXEC; - - squash_toc_save_inst(strtab + sym->st_name, value); - } else - value += local_entry_offset(sym); - - /* Convert value to relative */ - value -= (unsigned long)location; - if (value + 0x2000000 > 0x3ffffff || (value & 3) != 0){ - pr_err("%s: REL24 %li out of range!\n", - me->name, (long int)value); - return -ENOEXEC; - } - - /* Only replace bits 2 through 26 */ - *(uint32_t *)location - = (*(uint32_t *)location & ~0x03fffffc) - | (value & 0x03fffffc); - break; - - case R_PPC64_REL64: - /* 64 bits relative (used by features fixups) */ - *location = value - (unsigned long)location; - break; - - case R_PPC64_REL32: - /* 32 bits relative (used by relative exception tables) */ - *(u32 *)location = value - (unsigned long)location; - break; - - case R_PPC64_TOCSAVE: - /* - * Marker reloc indicates we don't have to save r2. - * That would only save us one instruction, so ignore - * it. - */ - break; - - case R_PPC64_ENTRY: - /* - * Optimize ELFv2 large code model entry point if - * the TOC is within 2GB range of current location. - */ - value = my_r2(sechdrs, me) - (unsigned long)location; - if (value + 0x80008000 > 0xffffffff) - break; - /* - * Check for the large code model prolog sequence: - * ld r2, ...(r12) - * add r2, r2, r12 - */ - if ((((uint32_t *)location)[0] & ~0xfffc) - != 0xe84c0000) - break; - if (((uint32_t *)location)[1] != 0x7c426214) - break; - /* - * If found, replace it with: - * addis r2, r12, (.TOC.-func)@ha - * addi r2, r12, (.TOC.-func)@l - */ - ((uint32_t *)location)[0] = 0x3c4c0000 + PPC_HA(value); - ((uint32_t *)location)[1] = 0x38420000 + PPC_LO(value); - break; - - case R_PPC64_REL16_HA: - /* Subtract location pointer */ - value -= (unsigned long)location; - value = ((value + 0x8000) >> 16); - *((uint16_t *) location) - = (*((uint16_t *) location) & ~0xffff) - | (value & 0xffff); - break; - - case R_PPC64_REL16_LO: - /* Subtract location pointer */ - value -= (unsigned long)location; - *((uint16_t *) location) - = (*((uint16_t *) location) & ~0xffff) - | (value & 0xffff); - break; - - default: - pr_err("%s: Unknown ADD relocation: %lu\n", - me->name, - (unsigned long)ELF64_R_TYPE(rela[i].r_info)); - return -ENOEXEC; - } + ret = elf64_apply_relocate_add_item(sechdrs, strtab, &rela[i], + sym, location, + (unsigned long) location, + value, my_r2(sechdrs, me), + me->name, me); + if (ret) + return ret; } return 0; diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index b0245bed6f54..fa7aea479fba 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -427,7 +427,7 @@ static int __init early_init_dt_scan_chosen_ppc(unsigned long node, tce_alloc_end = *lprop; #endif -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE lprop = of_get_flat_dt_prop(node, "linux,crashkernel-base", NULL); if (lprop) crashk_res.start = *lprop; diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 8d586cff8a41..6824157e4d2e 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -354,7 +354,7 @@ void early_setup_secondary(void) #endif /* CONFIG_SMP */ -#if defined(CONFIG_SMP) || defined(CONFIG_KEXEC) +#if defined(CONFIG_SMP) || defined(CONFIG_KEXEC_CORE) static bool use_spinloop(void) { if (!IS_ENABLED(CONFIG_PPC_BOOK3E)) @@ -399,7 +399,7 @@ void smp_release_cpus(void) DBG(" <- smp_release_cpus()\n"); } -#endif /* CONFIG_SMP || CONFIG_KEXEC */ +#endif /* CONFIG_SMP || CONFIG_KEXEC_CORE */ /* * Initialize some remaining members of the ppc64_caches and systemcfg diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 9c6f3fd58059..893bd7f79be6 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -193,7 +193,7 @@ int smp_request_message_ipi(int virq, int msg) if (msg < 0 || msg > PPC_MSG_DEBUGGER_BREAK) { return -EINVAL; } -#if !defined(CONFIG_DEBUGGER) && !defined(CONFIG_KEXEC) +#if !defined(CONFIG_DEBUGGER) && !defined(CONFIG_KEXEC_CORE) if (msg == PPC_MSG_DEBUGGER_BREAK) { return 1; } @@ -325,7 +325,7 @@ void tick_broadcast(const struct cpumask *mask) } #endif -#if defined(CONFIG_DEBUGGER) || defined(CONFIG_KEXEC) +#if defined(CONFIG_DEBUGGER) || defined(CONFIG_KEXEC_CORE) void smp_send_debugger_break(void) { int cpu; @@ -340,7 +340,7 @@ void smp_send_debugger_break(void) } #endif -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE void crash_send_ipi(void (*crash_ipi_callback)(struct pt_regs *)) { crash_ipi_function_ptr = crash_ipi_callback; diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 91d278c9ab28..a95555e628b6 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -65,7 +65,7 @@ #include <asm/hmi.h> #include <sysdev/fsl_pci.h> -#if defined(CONFIG_DEBUGGER) || defined(CONFIG_KEXEC) +#if defined(CONFIG_DEBUGGER) || defined(CONFIG_KEXEC_CORE) int (*__debugger)(struct pt_regs *regs) __read_mostly; int (*__debugger_ipi)(struct pt_regs *regs) __read_mostly; int (*__debugger_bpt)(struct pt_regs *regs) __read_mostly; diff --git a/arch/powerpc/platforms/85xx/corenet_generic.c b/arch/powerpc/platforms/85xx/corenet_generic.c index 1179115a4b5c..3803b0addf65 100644 --- a/arch/powerpc/platforms/85xx/corenet_generic.c +++ b/arch/powerpc/platforms/85xx/corenet_generic.c @@ -220,7 +220,7 @@ define_machine(corenet_generic) { * * Likewise, problems have been seen with kexec when coreint is enabled. */ -#if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_KEXEC) +#if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_KEXEC_CORE) .get_irq = mpic_get_irq, #else .get_irq = mpic_get_coreint_irq, diff --git a/arch/powerpc/platforms/85xx/smp.c b/arch/powerpc/platforms/85xx/smp.c index fe9f19e5e935..a83a6d26090d 100644 --- a/arch/powerpc/platforms/85xx/smp.c +++ b/arch/powerpc/platforms/85xx/smp.c @@ -349,13 +349,13 @@ struct smp_ops_t smp_85xx_ops = { .cpu_disable = generic_cpu_disable, .cpu_die = generic_cpu_die, #endif -#if defined(CONFIG_KEXEC) && !defined(CONFIG_PPC64) +#if defined(CONFIG_KEXEC_CORE) && !defined(CONFIG_PPC64) .give_timebase = smp_generic_give_timebase, .take_timebase = smp_generic_take_timebase, #endif }; -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE #ifdef CONFIG_PPC32 atomic_t kexec_down_cpus = ATOMIC_INIT(0); @@ -458,7 +458,7 @@ static void mpc85xx_smp_machine_kexec(struct kimage *image) default_machine_kexec(image); } -#endif /* CONFIG_KEXEC */ +#endif /* CONFIG_KEXEC_CORE */ static void smp_85xx_basic_setup(int cpu_nr) { @@ -512,7 +512,7 @@ void __init mpc85xx_smp_init(void) #endif smp_ops = &smp_85xx_ops; -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE ppc_md.kexec_cpu_down = mpc85xx_smp_kexec_cpu_down; ppc_md.machine_kexec = mpc85xx_smp_machine_kexec; #endif diff --git a/arch/powerpc/platforms/cell/spu_base.c b/arch/powerpc/platforms/cell/spu_base.c index e84d8fbc2e21..96c2b8a40630 100644 --- a/arch/powerpc/platforms/cell/spu_base.c +++ b/arch/powerpc/platforms/cell/spu_base.c @@ -676,7 +676,7 @@ static ssize_t spu_stat_show(struct device *dev, static DEVICE_ATTR(stat, 0444, spu_stat_show, NULL); -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE struct crash_spu_info { struct spu *spu; diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c index efe8b6bb168b..d50c7d99baaf 100644 --- a/arch/powerpc/platforms/powernv/setup.c +++ b/arch/powerpc/platforms/powernv/setup.c @@ -174,7 +174,7 @@ static void pnv_shutdown(void) opal_shutdown(); } -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE static void pnv_kexec_wait_secondaries_down(void) { int my_cpu, i, notified = -1; @@ -245,7 +245,7 @@ static void pnv_kexec_cpu_down(int crash_shutdown, int secondary) opal_reinit_cpus(OPAL_REINIT_CPUS_HILE_BE); } } -#endif /* CONFIG_KEXEC */ +#endif /* CONFIG_KEXEC_CORE */ #ifdef CONFIG_MEMORY_HOTPLUG_SPARSE static unsigned long pnv_memory_block_size(void) @@ -311,7 +311,7 @@ define_machine(powernv) { .machine_shutdown = pnv_shutdown, .power_save = NULL, .calibrate_decr = generic_calibrate_decr, -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE .kexec_cpu_down = pnv_kexec_cpu_down, #endif #ifdef CONFIG_MEMORY_HOTPLUG_SPARSE diff --git a/arch/powerpc/platforms/ps3/setup.c b/arch/powerpc/platforms/ps3/setup.c index 3a487e7f4a5e..6244bc849469 100644 --- a/arch/powerpc/platforms/ps3/setup.c +++ b/arch/powerpc/platforms/ps3/setup.c @@ -250,7 +250,7 @@ static int __init ps3_probe(void) return 1; } -#if defined(CONFIG_KEXEC) +#if defined(CONFIG_KEXEC_CORE) static void ps3_kexec_cpu_down(int crash_shutdown, int secondary) { int cpu = smp_processor_id(); @@ -276,7 +276,7 @@ define_machine(ps3) { .progress = ps3_progress, .restart = ps3_restart, .halt = ps3_halt, -#if defined(CONFIG_KEXEC) +#if defined(CONFIG_KEXEC_CORE) .kexec_cpu_down = ps3_kexec_cpu_down, #endif }; diff --git a/arch/powerpc/platforms/pseries/Makefile b/arch/powerpc/platforms/pseries/Makefile index fedc2ccf029d..dd9d9c2ba71b 100644 --- a/arch/powerpc/platforms/pseries/Makefile +++ b/arch/powerpc/platforms/pseries/Makefile @@ -8,7 +8,7 @@ obj-y := lpar.o hvCall.o nvram.o reconfig.o \ pci.o pci_dlpar.o eeh_pseries.o msi.o obj-$(CONFIG_SMP) += smp.o obj-$(CONFIG_SCANLOG) += scanlog.o -obj-$(CONFIG_KEXEC) += kexec.o +obj-$(CONFIG_KEXEC_CORE) += kexec.o obj-$(CONFIG_PSERIES_ENERGY) += pseries_energy.o obj-$(CONFIG_HOTPLUG_CPU) += hotplug-cpu.o diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 97aa3f332f24..7736352f7279 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -367,7 +367,7 @@ void pseries_disable_reloc_on_exc(void) } EXPORT_SYMBOL(pseries_disable_reloc_on_exc); -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE static void pSeries_machine_kexec(struct kimage *image) { if (firmware_has_feature(FW_FEATURE_SET_MODE)) @@ -725,7 +725,7 @@ define_machine(pseries) { .progress = rtas_progress, .system_reset_exception = pSeries_system_reset_exception, .machine_check_exception = pSeries_machine_check_exception, -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE .machine_kexec = pSeries_machine_kexec, .kexec_cpu_down = pseries_kexec_cpu_down, #endif diff --git a/arch/powerpc/purgatory/.gitignore b/arch/powerpc/purgatory/.gitignore new file mode 100644 index 000000000000..e9e66f178a6d --- /dev/null +++ b/arch/powerpc/purgatory/.gitignore @@ -0,0 +1,2 @@ +kexec-purgatory.c +purgatory.ro diff --git a/arch/powerpc/purgatory/Makefile b/arch/powerpc/purgatory/Makefile new file mode 100644 index 000000000000..32822234b049 --- /dev/null +++ b/arch/powerpc/purgatory/Makefile @@ -0,0 +1,33 @@ +OBJECT_FILES_NON_STANDARD := y + +purgatory-y := purgatory.o printf.o string.o v2wrap.o hvCall.o \ + purgatory-ppc64.o console-ppc64.o crtsavres.o sha256.o + +targets += $(purgatory-y) +PURGATORY_OBJS = $(addprefix $(obj)/,$(purgatory-y)) + +LDFLAGS_purgatory.ro := -e purgatory_start -r --no-undefined -nostartfiles \ + -nostdlib -nodefaultlibs +targets += purgatory.ro + +KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_FTRACE), $(KBUILD_CFLAGS)) + +KBUILD_CFLAGS += -fno-zero-initialized-in-bss -fno-builtin -ffreestanding \ + -fno-stack-protector -fno-exceptions -fpie +KBUILD_AFLAGS += -fno-exceptions -msoft-float -fpie + +$(obj)/purgatory.ro: $(PURGATORY_OBJS) FORCE + $(call if_changed,ld) + +targets += kexec-purgatory.c + +CMD_BIN2C = $(objtree)/scripts/basic/bin2c +quiet_cmd_bin2c = BIN2C $@ + cmd_bin2c = $(CMD_BIN2C) kexec_purgatory < $< > $@ + +$(obj)/kexec-purgatory.c: $(obj)/purgatory.ro FORCE + $(call if_changed,bin2c) + @: + + +obj-$(CONFIG_KEXEC_FILE) += kexec-purgatory.o diff --git a/arch/powerpc/purgatory/console-ppc64.c b/arch/powerpc/purgatory/console-ppc64.c new file mode 100644 index 000000000000..8c89686fa340 --- /dev/null +++ b/arch/powerpc/purgatory/console-ppc64.c @@ -0,0 +1,37 @@ +/* + * kexec: Linux boots Linux + * + * Created by: Mohan Kumar M (mohan@in.ibm.com) + * + * Copyright (C) IBM Corporation, 2005. All rights reserved + * + * Code taken from kexec-tools. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation (version 2 of the License). + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include "hvCall.h" +#include <asm/byteorder.h> +#include "purgatory.h" + +void putchar(int c) +{ + char buff[8]; + unsigned long *lbuf = (unsigned long *)buff; + + if (!debug) /* running on non pseries */ + return; + + if (c == '\n') + putchar('\r'); + + buff[0] = c; + plpar_hcall_norets(H_PUT_TERM_CHAR, 0, 1, __cpu_to_be64(*lbuf), 0); +} diff --git a/arch/powerpc/purgatory/crtsavres.S b/arch/powerpc/purgatory/crtsavres.S new file mode 100644 index 000000000000..5d17e1c0d575 --- /dev/null +++ b/arch/powerpc/purgatory/crtsavres.S @@ -0,0 +1,5 @@ +#ifndef CONFIG_CC_OPTIMIZE_FOR_SIZE +#define CONFIG_CC_OPTIMIZE_FOR_SIZE 1 +#endif + +#include "../lib/crtsavres.S" diff --git a/arch/powerpc/purgatory/hvCall.S b/arch/powerpc/purgatory/hvCall.S new file mode 100644 index 000000000000..a96c4898f1d8 --- /dev/null +++ b/arch/powerpc/purgatory/hvCall.S @@ -0,0 +1,27 @@ +/* + * This file contains the generic function to perform a call to the + * pSeries LPAR hypervisor. + * + * Taken from linux/arch/powerpc/platforms/pseries/hvCall.S + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ +#include "ppc64_asm.h" + +#define HVSC .long 0x44000022 +.text + .machine ppc64 +.globl DOTSYM(plpar_hcall_norets) +DOTSYM(plpar_hcall_norets): + or 6,6,6 # medium low priority + mfcr 0 + stw 0,8(1) + + HVSC /* invoke the hypervisor */ + + lwz 0,8(1) + mtcrf 0xff,0 + blr /* return r3 = status */ diff --git a/arch/powerpc/purgatory/hvCall.h b/arch/powerpc/purgatory/hvCall.h new file mode 100644 index 000000000000..187e24d8b964 --- /dev/null +++ b/arch/powerpc/purgatory/hvCall.h @@ -0,0 +1,8 @@ +#ifndef HVCALL_H +#define HVCALL_H + +#define H_PUT_TERM_CHAR 0x58 + +long plpar_hcall_norets(unsigned long opcode, ...); + +#endif diff --git a/arch/powerpc/purgatory/kexec-sha256.h b/arch/powerpc/purgatory/kexec-sha256.h new file mode 100644 index 000000000000..4418ed02c052 --- /dev/null +++ b/arch/powerpc/purgatory/kexec-sha256.h @@ -0,0 +1,11 @@ +#ifndef KEXEC_SHA256_H +#define KEXEC_SHA256_H + +struct kexec_sha_region { + unsigned long start; + unsigned long len; +}; + +#define SHA256_REGIONS 16 + +#endif /* KEXEC_SHA256_H */ diff --git a/arch/powerpc/purgatory/ppc64_asm.h b/arch/powerpc/purgatory/ppc64_asm.h new file mode 100644 index 000000000000..95d721718237 --- /dev/null +++ b/arch/powerpc/purgatory/ppc64_asm.h @@ -0,0 +1,20 @@ +/* + * ppc64_asm.h - common defines for PPC64 assembly parts + * + * Code taken from kexec-tools. + * + * This source code is licensed under the GNU General Public License, + * Version 2. See the file COPYING for more details. + */ + +#include <asm/types.h> + +/* + * ABIv1 requires dot symbol while ABIv2 does not. + */ +#ifdef PPC64_ELF_ABI_v2 +#define DOTSYM(a) a +#else +#define GLUE(a, b) a##b +#define DOTSYM(a) GLUE(., a) +#endif diff --git a/arch/powerpc/purgatory/printf.c b/arch/powerpc/purgatory/printf.c new file mode 100644 index 000000000000..c5f425b55fd5 --- /dev/null +++ b/arch/powerpc/purgatory/printf.c @@ -0,0 +1,164 @@ +/* + * Code taken from kexec-tools. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation (version 2 of the License). + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include <stdarg.h> +#include "purgatory.h" +#include "../boot/string.h" + +#define CHAR_BIT 8 + +/* + * Output + * ============================================================================= + */ + +#define LONG_LONG_SHIFT ((int)((sizeof(unsigned long long)*CHAR_BIT) - 4)) +#define LONG_SHIFT ((int)((sizeof(unsigned long)*CHAR_BIT) - 4)) +#define INT_SHIFT ((int)((sizeof(unsigned int)*CHAR_BIT) - 4)) +#define SHRT_SHIFT ((int)((sizeof(unsigned short)*CHAR_BIT) - 4)) +#define CHAR_SHIFT ((int)((sizeof(unsigned char)*CHAR_BIT) - 4)) + +/************************************************************************** +PRINTF and friends + + Formats: + %x - 4 bytes int (8 hex digits, lower case) + %X - 4 bytes int (8 hex digits, upper case) + %lx - 8 bytes long (16 hex digits, lower case) + %lX - 8 bytes long (16 hex digits, upper case) + %hx - 2 bytes int (4 hex digits, lower case) + %hX - 2 bytes int (4 hex digits, upper case) + %hhx - 1 byte int (2 hex digits, lower case) + %hhX - 1 byte int (2 hex digits, upper case) + - optional # prefixes 0x or 0X + %d - decimal int + %c - char + %s - string + Note: width specification not supported +**************************************************************************/ +void vsprintf(char *buffer, const char *fmt, va_list args) +{ + char *p; + + for ( ; *fmt != '\0'; ++fmt) { + if (*fmt != '%') { + if (buffer) + *buffer++ = *fmt; + else + putchar(*fmt); + continue; + } + if (*++fmt == 's') { + for (p = va_arg(args, char *); *p != '\0'; p++) + if (buffer) + *buffer++ = *p; + else + putchar(*p); + } else { /* Length of item is bounded */ + char tmp[40], *q = tmp; + int shift = INT_SHIFT; + + if (*fmt == 'L') { + shift = LONG_LONG_SHIFT; + fmt++; + } else if (*fmt == 'l') { + shift = LONG_SHIFT; + fmt++; + } else if (*fmt == 'h') { + shift = SHRT_SHIFT; + fmt++; + if (*fmt == 'h') { + shift = CHAR_SHIFT; + fmt++; + } + } + + /* + * Before each format q points to tmp buffer + * After each format q points past end of item + */ + if ((*fmt | 0x20) == 'x') { + /* With x86 gcc, sizeof(long) == sizeof(int) */ + unsigned long long h; + int ncase; + + if (shift > LONG_SHIFT) + h = va_arg(args, unsigned long long); + else if (shift > INT_SHIFT) + h = va_arg(args, unsigned long); + else + h = va_arg(args, unsigned int); + + ncase = (*fmt & 0x20); + for ( ; shift >= 0; shift -= 4) + *q++ = "0123456789ABCDEF"[(h >> shift) & 0xF] | ncase; + } else if (*fmt == 'd') { + char *r; + long i; + + if (shift > LONG_SHIFT) + i = va_arg(args, long long); + else if (shift > INT_SHIFT) + i = va_arg(args, long); + else + i = va_arg(args, int); + + if (i < 0) { + *q++ = '-'; + i = -i; + } + p = q; /* save beginning of digits */ + do { + *q++ = '0' + (i % 10); + i /= 10; + } while (i); + /* reverse digits, stop in middle */ + r = q; /* don't alter q */ + while (--r > p) { + i = *r; + *r = *p; + *p++ = i; + } + } else if (*fmt == 'c') + *q++ = va_arg(args, int); + else + *q++ = *fmt; + /* now output the saved string */ + for (p = tmp; p < q; ++p) + if (buffer) + *buffer++ = *p; + else + putchar(*p); + } + } + if (buffer) + *buffer = '\0'; +} + +void sprintf(char *buffer, const char *fmt, ...) +{ + va_list args; + + va_start(args, fmt); + vsprintf(buffer, fmt, args); + va_end(args); +} + +void printf(const char *fmt, ...) +{ + va_list args; + + va_start(args, fmt); + vsprintf(0, fmt, args); + va_end(args); +} diff --git a/arch/powerpc/purgatory/purgatory-ppc64.c b/arch/powerpc/purgatory/purgatory-ppc64.c new file mode 100644 index 000000000000..2e9545bcdcb4 --- /dev/null +++ b/arch/powerpc/purgatory/purgatory-ppc64.c @@ -0,0 +1,36 @@ +/* + * kexec: Linux boots Linux + * + * Created by: Mohan Kumar M (mohan@in.ibm.com) + * + * Copyright (C) IBM Corporation, 2005. All rights reserved + * + * Code taken from kexec-tools. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation (version 2 of the License). + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include "purgatory.h" + +unsigned long stack __section(".data"); +unsigned long dt_offset __section(".data"); +unsigned long my_toc __section(".data"); +unsigned long kernel __section(".data"); +int debug __section(".data"); +unsigned long opal_base __section(".data"); +unsigned long opal_entry __section(".data"); + +void setup_arch(void) +{ +} + +void post_verification_setup_arch(void) +{ +} diff --git a/arch/powerpc/purgatory/purgatory.c b/arch/powerpc/purgatory/purgatory.c new file mode 100644 index 000000000000..179f2da2b56f --- /dev/null +++ b/arch/powerpc/purgatory/purgatory.c @@ -0,0 +1,62 @@ +/* + * Code taken from kexec-tools. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation (version 2 of the License). + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include "purgatory.h" +#include "sha256.h" +#include "../boot/string.h" +#include "kexec-sha256.h" + +struct kexec_sha_region sha_regions[SHA256_REGIONS] __section(".data"); +u8 sha256_digest[SHA256_DIGEST_SIZE] __section(".data"); + +int verify_sha256_digest(void) +{ + struct kexec_sha_region *ptr, *end; + u8 digest[SHA256_DIGEST_SIZE]; + size_t i; + struct sha256_state sctx; + + sha256_init(&sctx); + end = &sha_regions[sizeof(sha_regions)/sizeof(sha_regions[0])]; + for (ptr = sha_regions; ptr < end; ptr++) + sha256_update(&sctx, (uint8_t *)(ptr->start), ptr->len); + sha256_final(&sctx, digest); + + if (memcmp(digest, sha256_digest, sizeof(digest)) != 0) { + printf("sha256 digests do not match :(\n"); + printf(" digest: "); + for (i = 0; i < sizeof(digest); i++) + printf("%hhx ", digest[i]); + printf("\n"); + + printf("sha256_digest: "); + for (i = 0; i < sizeof(sha256_digest); i++) + printf("%hhx ", sha256_digest[i]); + + printf("\n"); + return 1; + } + return 0; +} + +void purgatory(void) +{ + printf("I'm in purgatory\n"); + setup_arch(); + if (verify_sha256_digest()) { + /* loop forever */ + for (;;) + ; + } + post_verification_setup_arch(); +} diff --git a/arch/powerpc/purgatory/purgatory.h b/arch/powerpc/purgatory/purgatory.h new file mode 100644 index 000000000000..fde99e8b5043 --- /dev/null +++ b/arch/powerpc/purgatory/purgatory.h @@ -0,0 +1,14 @@ +#ifndef PURGATORY_H +#define PURGATORY_H + +#include <linux/compiler.h> + +extern int debug; + +void putchar(int ch); +void sprintf(char *buffer, const char *fmt, ...) __printf(2, 3); +void printf(const char *fmt, ...) __printf(1, 2); +void setup_arch(void); +void post_verification_setup_arch(void); + +#endif /* PURGATORY_H */ diff --git a/arch/powerpc/purgatory/sha256.c b/arch/powerpc/purgatory/sha256.c new file mode 100644 index 000000000000..6abee1877d56 --- /dev/null +++ b/arch/powerpc/purgatory/sha256.c @@ -0,0 +1,6 @@ +#include "../boot/string.h" + +/* Avoid including x86's boot/string.h in sha256.c. */ +#define BOOT_STRING_H + +#include "../../x86/purgatory/sha256.c" diff --git a/arch/powerpc/purgatory/sha256.h b/arch/powerpc/purgatory/sha256.h new file mode 100644 index 000000000000..72818f3a207e --- /dev/null +++ b/arch/powerpc/purgatory/sha256.h @@ -0,0 +1 @@ +#include "../../x86/purgatory/sha256.h" diff --git a/arch/powerpc/purgatory/string.S b/arch/powerpc/purgatory/string.S new file mode 100644 index 000000000000..19d92e4e7554 --- /dev/null +++ b/arch/powerpc/purgatory/string.S @@ -0,0 +1,2 @@ +#include "ppc64_asm.h" +#include "../boot/string.S" diff --git a/arch/powerpc/purgatory/v2wrap.S b/arch/powerpc/purgatory/v2wrap.S new file mode 100644 index 000000000000..c9a981c39a78 --- /dev/null +++ b/arch/powerpc/purgatory/v2wrap.S @@ -0,0 +1,134 @@ +# +# kexec: Linux boots Linux +# +# Copyright (C) 2004 - 2005, Milton D Miller II, IBM Corporation +# Copyright (C) 2006, Mohan Kumar M (mohan@in.ibm.com), IBM Corporation +# +# Code taken from kexec-tools. +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation (version 2 of the License). +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. + +#include "ppc64_asm.h" + +# v2wrap.S +# a wrapper to call purgatory code to backup first +# 32kB of first kernel into the backup region +# reserved by kexec-tools. +# Invokes ppc64 kernel with the expected arguments +# of kernel(device-tree, phys-offset, 0) + +# +# calling convention: +# r3 = physical number of this cpu (all cpus) +# r4 = address of this chunk (master only) +# master enters at purgatory_start (aka first byte of this chunk) +# slaves (additional cpus), if any, enter a copy of the +# first 0x100 bytes of this code relocated to 0x0 +# +# in other words, +# a copy of the first 0x100 bytes of this code is copied to 0 +# and the slaves are sent to address 0x60 +# with r3 = their physical cpu number. + +#define LOADADDR(rn,name) \ + lis rn,name##@highest; \ + ori rn,rn,name##@higher; \ + rldicr rn,rn,32,31; \ + oris rn,rn,name##@h; \ + ori rn,rn,name##@l + + .machine ppc64 + .align 8 + .globl purgatory_start +purgatory_start: b master + .org purgatory_start + 0x5c # ABI: possible run_at_load flag at 0x5c + .globl run_at_load +run_at_load: + .long 0 + .size run_at_load, . - run_at_load + .org purgatory_start + 0x60 # ABI: slaves start at 60 with r3=phys +slave: b $ + .org purgatory_start + 0x100 # ABI: end of copied region + .size purgatory_start, . - purgatory_start + +# +# The above 0x100 bytes at purgatory_start are replaced with the +# code from the kernel (or next stage) by kexec/arch/ppc64/kexec-elf-ppc64.c +# + +master: + or 1,1,1 # low priority to let other threads catchup + isync + mr 17,3 # save cpu id to r17 + mr 15,4 # save physical address in reg15 + + LOADADDR(6,my_toc) + ld 2,0(6) #setup toc + + LOADADDR(6,stack) + ld 1,0(6) #setup stack + + subi 1,1,112 + bl DOTSYM(purgatory) + nop + + or 3,3,3 # ok now to high priority, lets boot + lis 6,0x1 + mtctr 6 # delay a bit for slaves to catch up +83: bdnz 83b # before we overwrite 0-100 again + + LOADADDR(16, dt_offset) + ld 3,0(16) # load device-tree address + mr 16,3 # save dt address in reg16 +#ifdef __BIG_ENDIAN__ + lwz 6,20(3) # fetch version number +#else + li 4,20 + lwbrx 6,3,4 # fetch BE version number +#endif + cmpwi 0,6,2 # v2 ? + blt 80f +#ifdef __BIG_ENDIAN__ + stw 17,28(3) # save my cpu number as boot_cpu_phys +#else + li 4,28 + stwbrx 17,3,4 # Store my cpu as BE value +#endif +80: + LOADADDR(6,opal_base) # For OPAL early debug + ld 8,0(6) # load the OPAL base address in r8 + LOADADDR(6,opal_entry) # For OPAL early debug + ld 9,0(6) # load the OPAL entry address in r9 + LOADADDR(6,kernel) + ld 4,0(6) # load the kernel address + LOADADDR(6,run_at_load) # the load flag + lwz 7,0(6) # possibly patched by kexec-elf-ppc64 + stw 7,0x5c(4) # and patch it into the kernel + mr 3,16 # restore dt address + + mfmsr 5 + andi. 10,5,1 # test MSR_LE + bne little_endian + + li 5,0 # r5 will be 0 for kernel + mtctr 4 # prepare branch to + bctr # start kernel + +little_endian: # book3s-only + mtsrr0 4 # prepare branch to + + clrrdi 5,5,1 # clear MSR_LE + mtsrr1 5 + + li 5,0 # r5 will be 0 for kernel + + # skip cache flush, do we care? + + rfid # update MSR and start kernel |