[PATCH v5 08/13] powerpc: Implement kexec_file_load.
Thiago Jung Bauermann
bauerman at linux.vnet.ibm.com
Thu Aug 11 16:08:13 PDT 2016
arch_kexec_walk_mem and arch_kexec_apply_relocations_add are used by
generic kexec code, while setup_purgatory is powerpc-specific and sets
runtime variables needed by the powerpc purgatory implementation.
Signed-off-by: Josh Sklar <sklar at linux.vnet.ibm.com>
Signed-off-by: Thiago Jung Bauermann <bauerman at linux.vnet.ibm.com>
---
arch/powerpc/Kconfig | 13 ++
arch/powerpc/include/asm/kexec.h | 7 +
arch/powerpc/include/asm/systbl.h | 1 +
arch/powerpc/include/asm/unistd.h | 2 +-
arch/powerpc/include/uapi/asm/unistd.h | 1 +
arch/powerpc/kernel/Makefile | 4 +-
arch/powerpc/kernel/machine_kexec_64.c | 252 +++++++++++++++++++++++++++++++++
7 files changed, 278 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index ec4047e170a0..ff362ca60d1b 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -459,6 +459,19 @@ 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 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))
diff --git a/arch/powerpc/include/asm/kexec.h b/arch/powerpc/include/asm/kexec.h
index a46f5f45570c..83b81b7bdca1 100644
--- a/arch/powerpc/include/asm/kexec.h
+++ b/arch/powerpc/include/asm/kexec.h
@@ -91,6 +91,13 @@ static inline bool kdump_in_progress(void)
return crashing_cpu >= 0;
}
+#ifdef CONFIG_KEXEC_FILE
+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);
+#endif /* CONFIG_KEXEC_FILE */
+
#else /* !CONFIG_KEXEC */
static inline void crash_kexec_secondary(struct pt_regs *regs) { }
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 cf12c580f6b2..a01e97d3f305 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 6159ec6ac032..ce18a985bcfc 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -123,9 +123,11 @@ ifneq ($(CONFIG_PPC_INDIRECT_PIO),y)
obj-y += iomap.o
endif
-ifeq ($(CONFIG_MODULES)$(CONFIG_WORD_SIZE),y64)
+ifneq ($(CONFIG_MODULES)$(CONFIG_KEXEC_FILE),)
+ifeq ($(CONFIG_WORD_SIZE),64)
obj-y += elf_util.o elf_util_64.o
endif
+endif
obj64-$(CONFIG_PPC_TRANSACTIONAL_MEM) += tm.o
diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c
index 4c780a342282..1e678dc5096a 100644
--- a/arch/powerpc/kernel/machine_kexec_64.c
+++ b/arch/powerpc/kernel/machine_kexec_64.c
@@ -18,6 +18,8 @@
#include <linux/kernel.h>
#include <linux/cpu.h>
#include <linux/hardirq.h>
+#include <linux/memblock.h>
+#include <linux/libfdt.h>
#include <asm/page.h>
#include <asm/current.h>
@@ -31,6 +33,12 @@
#include <asm/hw_breakpoint.h>
#include <asm/asm-prototypes.h>
+#define SLAVE_CODE_SIZE 256
+
+#ifdef CONFIG_KEXEC_FILE
+static struct kexec_file_ops *kexec_file_loaders[] = { };
+#endif
+
#ifdef CONFIG_PPC_BOOK3E
int default_machine_kexec_prepare(struct kimage *image)
{
@@ -432,3 +440,247 @@ static int __init export_htab_values(void)
}
late_initcall(export_htab_values);
#endif /* CONFIG_PPC_STD_MMU_64 */
+
+#ifdef CONFIG_KEXEC_FILE
+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)
+{
+ /* Section containing the relocation entries. */
+ Elf64_Shdr *rel_section = &sechdrs[relsec];
+ const Elf64_Rela *rela = (const Elf64_Rela *) rel_section->sh_offset;
+ unsigned int num_rela = rel_section->sh_size / sizeof(Elf64_Rela);
+ /* 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;
+ struct elf_info elf_info;
+ 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;
+ }
+ /* String table for the associated symbol table. */
+ strtab = (const char *) sechdrs[symtabsec->sh_link].sh_offset;
+
+ elf_init_elf_info(ehdr, sechdrs, &elf_info);
+
+ return elf64_apply_relocate_add(&elf_info, strtab, rela, num_rela,
+ syms_base, loc_base, addr_base,
+ true, true, "kexec purgatory");
+}
+
+/**
+ * setup_purgatory() - setup the purgatory runtime 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;
+ struct elf_info purg_info;
+
+ 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;
+
+ elf_init_elf_info(image->purgatory_info.ehdr,
+ image->purgatory_info.sechdrs, &purg_info);
+ toc = my_r2(&purg_info);
+ 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;
+}
+
+#endif /* CONFIG_KEXEC_FILE */
--
1.9.1
More information about the kexec
mailing list