diff options
Diffstat (limited to '')
| -rw-r--r-- | arch/powerpc/kexec/Makefile | 17 | ||||
| -rw-r--r-- | arch/powerpc/kexec/core.c | 277 | ||||
| -rw-r--r-- | arch/powerpc/kexec/core_32.c | 69 | ||||
| -rw-r--r-- | arch/powerpc/kexec/core_64.c | 422 | ||||
| -rw-r--r-- | arch/powerpc/kexec/crash.c | 394 | ||||
| -rw-r--r-- | arch/powerpc/kexec/elf_64.c | 157 | ||||
| -rw-r--r-- | arch/powerpc/kexec/file_load.c | 109 | ||||
| -rw-r--r-- | arch/powerpc/kexec/file_load_64.c | 1287 | ||||
| -rw-r--r-- | arch/powerpc/kexec/ranges.c | 412 | ||||
| -rw-r--r-- | arch/powerpc/kexec/relocate_32.S | 500 |
10 files changed, 3644 insertions, 0 deletions
diff --git a/arch/powerpc/kexec/Makefile b/arch/powerpc/kexec/Makefile new file mode 100644 index 000000000..0c2abe7f9 --- /dev/null +++ b/arch/powerpc/kexec/Makefile @@ -0,0 +1,17 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Makefile for the linux kernel. +# + +obj-y += core.o crash.o core_$(BITS).o + +obj-$(CONFIG_PPC32) += relocate_32.o + +obj-$(CONFIG_KEXEC_FILE) += file_load.o ranges.o file_load_$(BITS).o elf_$(BITS).o + +# Disable GCOV, KCOV & sanitizers in odd or sensitive code +GCOV_PROFILE_core_$(BITS).o := n +KCOV_INSTRUMENT_core_$(BITS).o := n +UBSAN_SANITIZE_core_$(BITS).o := n +KASAN_SANITIZE_core.o := n +KASAN_SANITIZE_core_$(BITS) := n diff --git a/arch/powerpc/kexec/core.c b/arch/powerpc/kexec/core.c new file mode 100644 index 000000000..de64c7962 --- /dev/null +++ b/arch/powerpc/kexec/core.c @@ -0,0 +1,277 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Code to handle transition of Linux booting another kernel. + * + * Copyright (C) 2002-2003 Eric Biederman <ebiederm@xmission.com> + * GameCube/ppc32 port Copyright (C) 2004 Albert Herranz + * Copyright (C) 2005 IBM Corporation. + */ + +#include <linux/kexec.h> +#include <linux/reboot.h> +#include <linux/threads.h> +#include <linux/memblock.h> +#include <linux/of.h> +#include <linux/irq.h> +#include <linux/ftrace.h> + +#include <asm/kdump.h> +#include <asm/machdep.h> +#include <asm/pgalloc.h> +#include <asm/sections.h> +#include <asm/setup.h> +#include <asm/firmware.h> + +void machine_kexec_mask_interrupts(void) { + unsigned int i; + struct irq_desc *desc; + + for_each_irq_desc(i, desc) { + struct irq_chip *chip; + + chip = irq_desc_get_chip(desc); + if (!chip) + continue; + + if (chip->irq_eoi && irqd_irq_inprogress(&desc->irq_data)) + chip->irq_eoi(&desc->irq_data); + + if (chip->irq_mask) + chip->irq_mask(&desc->irq_data); + + if (chip->irq_disable && !irqd_irq_disabled(&desc->irq_data)) + chip->irq_disable(&desc->irq_data); + } +} + +void machine_crash_shutdown(struct pt_regs *regs) +{ + default_machine_crash_shutdown(regs); +} + +void machine_kexec_cleanup(struct kimage *image) +{ +} + +void arch_crash_save_vmcoreinfo(void) +{ + +#ifdef CONFIG_NUMA + VMCOREINFO_SYMBOL(node_data); + VMCOREINFO_LENGTH(node_data, MAX_NUMNODES); +#endif +#ifndef CONFIG_NUMA + VMCOREINFO_SYMBOL(contig_page_data); +#endif +#if defined(CONFIG_PPC64) && defined(CONFIG_SPARSEMEM_VMEMMAP) + VMCOREINFO_SYMBOL(vmemmap_list); + VMCOREINFO_SYMBOL(mmu_vmemmap_psize); + VMCOREINFO_SYMBOL(mmu_psize_defs); + VMCOREINFO_STRUCT_SIZE(vmemmap_backing); + VMCOREINFO_OFFSET(vmemmap_backing, list); + VMCOREINFO_OFFSET(vmemmap_backing, phys); + VMCOREINFO_OFFSET(vmemmap_backing, virt_addr); + VMCOREINFO_STRUCT_SIZE(mmu_psize_def); + VMCOREINFO_OFFSET(mmu_psize_def, shift); +#endif + vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset()); +} + +/* + * Do not allocate memory (or fail in any way) in machine_kexec(). + * We are past the point of no return, committed to rebooting now. + */ +void machine_kexec(struct kimage *image) +{ + int save_ftrace_enabled; + + save_ftrace_enabled = __ftrace_enabled_save(); + this_cpu_disable_ftrace(); + + if (ppc_md.machine_kexec) + ppc_md.machine_kexec(image); + else + default_machine_kexec(image); + + this_cpu_enable_ftrace(); + __ftrace_enabled_restore(save_ftrace_enabled); + + /* Fall back to normal restart if we're still alive. */ + machine_restart(NULL); + for(;;); +} + +void __init reserve_crashkernel(void) +{ + unsigned long long crash_size, crash_base, total_mem_sz; + int ret; + + total_mem_sz = memory_limit ? memory_limit : memblock_phys_mem_size(); + /* use common parsing */ + ret = parse_crashkernel(boot_command_line, total_mem_sz, + &crash_size, &crash_base); + if (ret == 0 && crash_size > 0) { + crashk_res.start = crash_base; + crashk_res.end = crash_base + crash_size - 1; + } + + if (crashk_res.end == crashk_res.start) { + crashk_res.start = crashk_res.end = 0; + return; + } + + /* We might have got these values via the command line or the + * device tree, either way sanitise them now. */ + + crash_size = resource_size(&crashk_res); + +#ifndef CONFIG_NONSTATIC_KERNEL + if (crashk_res.start != KDUMP_KERNELBASE) + printk("Crash kernel location must be 0x%x\n", + KDUMP_KERNELBASE); + + crashk_res.start = KDUMP_KERNELBASE; +#else + if (!crashk_res.start) { +#ifdef CONFIG_PPC64 + /* + * On the LPAR platform place the crash kernel to mid of + * RMA size (max. of 512MB) to ensure the crash kernel + * gets enough space to place itself and some stack to be + * in the first segment. At the same time normal kernel + * also get enough space to allocate memory for essential + * system resource in the first segment. Keep the crash + * kernel starts at 128MB offset on other platforms. + */ + if (firmware_has_feature(FW_FEATURE_LPAR)) + crashk_res.start = min_t(u64, ppc64_rma_size / 2, SZ_512M); + else + crashk_res.start = min_t(u64, ppc64_rma_size / 2, SZ_128M); +#else + crashk_res.start = KDUMP_KERNELBASE; +#endif + } + + crash_base = PAGE_ALIGN(crashk_res.start); + if (crash_base != crashk_res.start) { + printk("Crash kernel base must be aligned to 0x%lx\n", + PAGE_SIZE); + crashk_res.start = crash_base; + } + +#endif + crash_size = PAGE_ALIGN(crash_size); + crashk_res.end = crashk_res.start + crash_size - 1; + + /* The crash region must not overlap the current kernel */ + if (overlaps_crashkernel(__pa(_stext), _end - _stext)) { + printk(KERN_WARNING + "Crash kernel can not overlap current kernel\n"); + crashk_res.start = crashk_res.end = 0; + return; + } + + /* Crash kernel trumps memory limit */ + if (memory_limit && memory_limit <= crashk_res.end) { + memory_limit = crashk_res.end + 1; + total_mem_sz = memory_limit; + printk("Adjusted memory limit for crashkernel, now 0x%llx\n", + memory_limit); + } + + printk(KERN_INFO "Reserving %ldMB of memory at %ldMB " + "for crashkernel (System RAM: %ldMB)\n", + (unsigned long)(crash_size >> 20), + (unsigned long)(crashk_res.start >> 20), + (unsigned long)(total_mem_sz >> 20)); + + if (!memblock_is_region_memory(crashk_res.start, crash_size) || + memblock_reserve(crashk_res.start, crash_size)) { + pr_err("Failed to reserve memory for crashkernel!\n"); + crashk_res.start = crashk_res.end = 0; + return; + } +} + +int __init overlaps_crashkernel(unsigned long start, unsigned long size) +{ + return (start + size) > crashk_res.start && start <= crashk_res.end; +} + +/* Values we need to export to the second kernel via the device tree. */ +static phys_addr_t kernel_end; +static phys_addr_t crashk_base; +static phys_addr_t crashk_size; +static unsigned long long mem_limit; + +static struct property kernel_end_prop = { + .name = "linux,kernel-end", + .length = sizeof(phys_addr_t), + .value = &kernel_end, +}; + +static struct property crashk_base_prop = { + .name = "linux,crashkernel-base", + .length = sizeof(phys_addr_t), + .value = &crashk_base +}; + +static struct property crashk_size_prop = { + .name = "linux,crashkernel-size", + .length = sizeof(phys_addr_t), + .value = &crashk_size, +}; + +static struct property memory_limit_prop = { + .name = "linux,memory-limit", + .length = sizeof(unsigned long long), + .value = &mem_limit, +}; + +#define cpu_to_be_ulong __PASTE(cpu_to_be, BITS_PER_LONG) + +static void __init export_crashk_values(struct device_node *node) +{ + /* There might be existing crash kernel properties, but we can't + * be sure what's in them, so remove them. */ + of_remove_property(node, of_find_property(node, + "linux,crashkernel-base", NULL)); + of_remove_property(node, of_find_property(node, + "linux,crashkernel-size", NULL)); + + if (crashk_res.start != 0) { + crashk_base = cpu_to_be_ulong(crashk_res.start), + of_add_property(node, &crashk_base_prop); + crashk_size = cpu_to_be_ulong(resource_size(&crashk_res)); + of_add_property(node, &crashk_size_prop); + } + + /* + * memory_limit is required by the kexec-tools to limit the + * crash regions to the actual memory used. + */ + mem_limit = cpu_to_be_ulong(memory_limit); + of_update_property(node, &memory_limit_prop); +} + +static int __init kexec_setup(void) +{ + struct device_node *node; + + node = of_find_node_by_path("/chosen"); + if (!node) + return -ENOENT; + + /* remove any stale properties so ours can be found */ + of_remove_property(node, of_find_property(node, kernel_end_prop.name, NULL)); + + /* information needed by userspace when using default_machine_kexec */ + kernel_end = cpu_to_be_ulong(__pa(_end)); + of_add_property(node, &kernel_end_prop); + + export_crashk_values(node); + + of_node_put(node); + return 0; +} +late_initcall(kexec_setup); diff --git a/arch/powerpc/kexec/core_32.c b/arch/powerpc/kexec/core_32.c new file mode 100644 index 000000000..c95f96850 --- /dev/null +++ b/arch/powerpc/kexec/core_32.c @@ -0,0 +1,69 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * PPC32 code to handle Linux booting another kernel. + * + * Copyright (C) 2002-2003 Eric Biederman <ebiederm@xmission.com> + * GameCube/ppc32 port Copyright (C) 2004 Albert Herranz + * Copyright (C) 2005 IBM Corporation. + */ + +#include <linux/kexec.h> +#include <linux/mm.h> +#include <linux/string.h> +#include <asm/cacheflush.h> +#include <asm/hw_irq.h> +#include <asm/io.h> + +typedef void (*relocate_new_kernel_t)( + unsigned long indirection_page, + unsigned long reboot_code_buffer, + unsigned long start_address) __noreturn; + +/* + * This is a generic machine_kexec function suitable at least for + * non-OpenFirmware embedded platforms. + * It merely copies the image relocation code to the control page and + * jumps to it. + * A platform specific function may just call this one. + */ +void default_machine_kexec(struct kimage *image) +{ + extern const unsigned int relocate_new_kernel_size; + unsigned long page_list; + unsigned long reboot_code_buffer, reboot_code_buffer_phys; + relocate_new_kernel_t rnk; + + /* Interrupts aren't acceptable while we reboot */ + local_irq_disable(); + + /* mask each interrupt so we are in a more sane state for the + * kexec kernel */ + machine_kexec_mask_interrupts(); + + page_list = image->head; + + /* we need both effective and real address here */ + reboot_code_buffer = + (unsigned long)page_address(image->control_code_page); + reboot_code_buffer_phys = virt_to_phys((void *)reboot_code_buffer); + + /* copy our kernel relocation code to the control code page */ + memcpy((void *)reboot_code_buffer, relocate_new_kernel, + relocate_new_kernel_size); + + flush_icache_range(reboot_code_buffer, + reboot_code_buffer + KEXEC_CONTROL_PAGE_SIZE); + printk(KERN_INFO "Bye!\n"); + + if (!IS_ENABLED(CONFIG_PPC_85xx) && !IS_ENABLED(CONFIG_44x)) + relocate_new_kernel(page_list, reboot_code_buffer_phys, image->start); + + /* now call it */ + rnk = (relocate_new_kernel_t) reboot_code_buffer; + (*rnk)(page_list, reboot_code_buffer_phys, image->start); +} + +int machine_kexec_prepare(struct kimage *image) +{ + return 0; +} diff --git a/arch/powerpc/kexec/core_64.c b/arch/powerpc/kexec/core_64.c new file mode 100644 index 000000000..a79e28c91 --- /dev/null +++ b/arch/powerpc/kexec/core_64.c @@ -0,0 +1,422 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * PPC64 code to handle Linux booting another kernel. + * + * Copyright (C) 2004-2005, IBM Corp. + * + * Created by: Milton D Miller II + */ + + +#include <linux/kexec.h> +#include <linux/smp.h> +#include <linux/thread_info.h> +#include <linux/init_task.h> +#include <linux/errno.h> +#include <linux/kernel.h> +#include <linux/cpu.h> +#include <linux/hardirq.h> +#include <linux/of.h> + +#include <asm/page.h> +#include <asm/current.h> +#include <asm/machdep.h> +#include <asm/cacheflush.h> +#include <asm/firmware.h> +#include <asm/paca.h> +#include <asm/mmu.h> +#include <asm/sections.h> /* _end */ +#include <asm/smp.h> +#include <asm/hw_breakpoint.h> +#include <asm/svm.h> +#include <asm/ultravisor.h> + +int machine_kexec_prepare(struct kimage *image) +{ + int i; + unsigned long begin, end; /* limits of segment */ + unsigned long low, high; /* limits of blocked memory range */ + struct device_node *node; + const unsigned long *basep; + const unsigned int *sizep; + + /* + * Since we use the kernel fault handlers and paging code to + * handle the virtual mode, we must make sure no destination + * overlaps kernel static data or bss. + */ + for (i = 0; i < image->nr_segments; i++) + if (image->segment[i].mem < __pa(_end)) + return -ETXTBSY; + + /* We also should not overwrite the tce tables */ + for_each_node_by_type(node, "pci") { + basep = of_get_property(node, "linux,tce-base", NULL); + sizep = of_get_property(node, "linux,tce-size", NULL); + if (basep == NULL || sizep == NULL) + continue; + + low = *basep; + high = low + (*sizep); + + for (i = 0; i < image->nr_segments; i++) { + begin = image->segment[i].mem; + end = begin + image->segment[i].memsz; + + if ((begin < high) && (end > low)) { + of_node_put(node); + return -ETXTBSY; + } + } + } + + return 0; +} + +/* Called during kexec sequence with MMU off */ +static notrace void copy_segments(unsigned long ind) +{ + unsigned long entry; + unsigned long *ptr; + void *dest; + void *addr; + + /* + * We rely on kexec_load to create a lists that properly + * initializes these pointers before they are used. + * We will still crash if the list is wrong, but at least + * the compiler will be quiet. + */ + ptr = NULL; + dest = NULL; + + for (entry = ind; !(entry & IND_DONE); entry = *ptr++) { + addr = __va(entry & PAGE_MASK); + + switch (entry & IND_FLAGS) { + case IND_DESTINATION: + dest = addr; + break; + case IND_INDIRECTION: + ptr = addr; + break; + case IND_SOURCE: + copy_page(dest, addr); + dest += PAGE_SIZE; + } + } +} + +/* Called during kexec sequence with MMU off */ +notrace void kexec_copy_flush(struct kimage *image) +{ + long i, nr_segments = image->nr_segments; + struct kexec_segment ranges[KEXEC_SEGMENT_MAX]; + + /* save the ranges on the stack to efficiently flush the icache */ + memcpy(ranges, image->segment, sizeof(ranges)); + + /* + * After this call we may not use anything allocated in dynamic + * memory, including *image. + * + * Only globals and the stack are allowed. + */ + copy_segments(image->head); + + /* + * we need to clear the icache for all dest pages sometime, + * including ones that were in place on the original copy + */ + for (i = 0; i < nr_segments; i++) + flush_icache_range((unsigned long)__va(ranges[i].mem), + (unsigned long)__va(ranges[i].mem + ranges[i].memsz)); +} + +#ifdef CONFIG_SMP + +static int kexec_all_irq_disabled = 0; + +static void kexec_smp_down(void *arg) +{ + local_irq_disable(); + hard_irq_disable(); + + mb(); /* make sure our irqs are disabled before we say they are */ + get_paca()->kexec_state = KEXEC_STATE_IRQS_OFF; + while(kexec_all_irq_disabled == 0) + cpu_relax(); + mb(); /* make sure all irqs are disabled before this */ + hw_breakpoint_disable(); + /* + * Now every CPU has IRQs off, we can clear out any pending + * IPIs and be sure that no more will come in after this. + */ + if (ppc_md.kexec_cpu_down) + ppc_md.kexec_cpu_down(0, 1); + + reset_sprs(); + + kexec_smp_wait(); + /* NOTREACHED */ +} + +static void kexec_prepare_cpus_wait(int wait_state) +{ + int my_cpu, i, notified=-1; + + hw_breakpoint_disable(); + my_cpu = get_cpu(); + /* Make sure each CPU has at least made it to the state we need. + * + * FIXME: There is a (slim) chance of a problem if not all of the CPUs + * are correctly onlined. If somehow we start a CPU on boot with RTAS + * start-cpu, but somehow that CPU doesn't write callin_cpu_map[] in + * time, the boot CPU will timeout. If it does eventually execute + * stuff, the secondary will start up (paca_ptrs[]->cpu_start was + * written) and get into a peculiar state. + * If the platform supports smp_ops->take_timebase(), the secondary CPU + * will probably be spinning in there. If not (i.e. pseries), the + * secondary will continue on and try to online itself/idle/etc. If it + * survives that, we need to find these + * possible-but-not-online-but-should-be CPUs and chaperone them into + * kexec_smp_wait(). + */ + for_each_online_cpu(i) { + if (i == my_cpu) + continue; + + while (paca_ptrs[i]->kexec_state < wait_state) { + barrier(); + if (i != notified) { + printk(KERN_INFO "kexec: waiting for cpu %d " + "(physical %d) to enter %i state\n", + i, paca_ptrs[i]->hw_cpu_id, wait_state); + notified = i; + } + } + } + mb(); +} + +/* + * We need to make sure each present CPU is online. The next kernel will scan + * the device tree and assume primary threads are online and query secondary + * threads via RTAS to online them if required. If we don't online primary + * threads, they will be stuck. However, we also online secondary threads as we + * may be using 'cede offline'. In this case RTAS doesn't see the secondary + * threads as offline -- and again, these CPUs will be stuck. + * + * So, we online all CPUs that should be running, including secondary threads. + */ +static void wake_offline_cpus(void) +{ + int cpu = 0; + + for_each_present_cpu(cpu) { + if (!cpu_online(cpu)) { + printk(KERN_INFO "kexec: Waking offline cpu %d.\n", + cpu); + WARN_ON(add_cpu(cpu)); + } + } +} + +static void kexec_prepare_cpus(void) +{ + wake_offline_cpus(); + smp_call_function(kexec_smp_down, NULL, /* wait */0); + local_irq_disable(); + hard_irq_disable(); + + mb(); /* make sure IRQs are disabled before we say they are */ + get_paca()->kexec_state = KEXEC_STATE_IRQS_OFF; + + kexec_prepare_cpus_wait(KEXEC_STATE_IRQS_OFF); + /* we are sure every CPU has IRQs off at this point */ + kexec_all_irq_disabled = 1; + + /* + * Before removing MMU mappings make sure all CPUs have entered real + * mode: + */ + kexec_prepare_cpus_wait(KEXEC_STATE_REAL_MODE); + + /* after we tell the others to go down */ + if (ppc_md.kexec_cpu_down) + ppc_md.kexec_cpu_down(0, 0); + + put_cpu(); +} + +#else /* ! SMP */ + +static void kexec_prepare_cpus(void) +{ + /* + * move the secondarys to us so that we can copy + * the new kernel 0-0x100 safely + * + * do this if kexec in setup.c ? + * + * We need to release the cpus if we are ever going from an + * UP to an SMP kernel. + */ + smp_release_cpus(); + if (ppc_md.kexec_cpu_down) + ppc_md.kexec_cpu_down(0, 0); + local_irq_disable(); + hard_irq_disable(); +} + +#endif /* SMP */ + +/* + * kexec thread structure and stack. + * + * We need to make sure that this is 16384-byte aligned due to the + * way process stacks are handled. It also must be statically allocated + * or allocated as part of the kimage, because everything else may be + * overwritten when we copy the kexec image. We piggyback on the + * "init_task" linker section here to statically allocate a stack. + * + * We could use a smaller stack if we don't care about anything using + * current, but that audit has not been performed. + */ +static union thread_union kexec_stack __init_task_data = + { }; + +/* + * For similar reasons to the stack above, the kexecing CPU needs to be on a + * static PACA; we switch to kexec_paca. + */ +static struct paca_struct kexec_paca; + +/* Our assembly helper, in misc_64.S */ +extern void kexec_sequence(void *newstack, unsigned long start, + void *image, void *control, + void (*clear_all)(void), + bool copy_with_mmu_off) __noreturn; + +/* too late to fail here */ +void default_machine_kexec(struct kimage *image) +{ + bool copy_with_mmu_off; + + /* prepare control code if any */ + + /* + * If the kexec boot is the normal one, need to shutdown other cpus + * into our wait loop and quiesce interrupts. + * Otherwise, in the case of crashed mode (crashing_cpu >= 0), + * stopping other CPUs and collecting their pt_regs is done before + * using debugger IPI. + */ + + if (!kdump_in_progress()) + kexec_prepare_cpus(); + + printk("kexec: Starting switchover sequence.\n"); + + /* switch to a staticly allocated stack. Based on irq stack code. + * We setup preempt_count to avoid using VMX in memcpy. + * XXX: the task struct will likely be invalid once we do the copy! + */ + current_thread_info()->flags = 0; + current_thread_info()->preempt_count = HARDIRQ_OFFSET; + + /* We need a static PACA, too; copy this CPU's PACA over and switch to + * it. Also poison per_cpu_offset and NULL lppaca to catch anyone using + * non-static data. + */ + memcpy(&kexec_paca, get_paca(), sizeof(struct paca_struct)); + kexec_paca.data_offset = 0xedeaddeadeeeeeeeUL; +#ifdef CONFIG_PPC_PSERIES + kexec_paca.lppaca_ptr = NULL; +#endif + + if (is_secure_guest() && !(image->preserve_context || + image->type == KEXEC_TYPE_CRASH)) { + uv_unshare_all_pages(); + printk("kexec: Unshared all shared pages.\n"); + } + + paca_ptrs[kexec_paca.paca_index] = &kexec_paca; + + setup_paca(&kexec_paca); + + /* + * The lppaca should be unregistered at this point so the HV won't + * touch it. In the case of a crash, none of the lppacas are + * unregistered so there is not much we can do about it here. + */ + + /* + * On Book3S, the copy must happen with the MMU off if we are either + * using Radix page tables or we are not in an LPAR since we can + * overwrite the page tables while copying. + * + * In an LPAR, we keep the MMU on otherwise we can't access beyond + * the RMA. On BookE there is no real MMU off mode, so we have to + * keep it enabled as well (but then we have bolted TLB entries). + */ +#ifdef CONFIG_PPC_BOOK3E_64 + copy_with_mmu_off = false; +#else + copy_with_mmu_off = radix_enabled() || + !(firmware_has_feature(FW_FEATURE_LPAR) || + firmware_has_feature(FW_FEATURE_PS3_LV1)); +#endif + + /* Some things are best done in assembly. Finding globals with + * a toc is easier in C, so pass in what we can. + */ + kexec_sequence(&kexec_stack, image->start, image, + page_address(image->control_code_page), + mmu_cleanup_all, copy_with_mmu_off); + /* NOTREACHED */ +} + +#ifdef CONFIG_PPC_64S_HASH_MMU +/* Values we need to export to the second kernel via the device tree. */ +static unsigned long htab_base; +static unsigned long htab_size; + +static struct property htab_base_prop = { + .name = "linux,htab-base", + .length = sizeof(unsigned long), + .value = &htab_base, +}; + +static struct property htab_size_prop = { + .name = "linux,htab-size", + .length = sizeof(unsigned long), + .value = &htab_size, +}; + +static int __init export_htab_values(void) +{ + struct device_node *node; + + /* On machines with no htab htab_address is NULL */ + if (!htab_address) + return -ENODEV; + + node = of_find_node_by_path("/chosen"); + if (!node) + return -ENODEV; + + /* remove any stale properties so ours can be found */ + of_remove_property(node, of_find_property(node, htab_base_prop.name, NULL)); + of_remove_property(node, of_find_property(node, htab_size_prop.name, NULL)); + + htab_base = cpu_to_be64(__pa(htab_address)); + of_add_property(node, &htab_base_prop); + htab_size = cpu_to_be64(htab_size_bytes); + of_add_property(node, &htab_size_prop); + + of_node_put(node); + return 0; +} +late_initcall(export_htab_values); +#endif /* CONFIG_PPC_64S_HASH_MMU */ diff --git a/arch/powerpc/kexec/crash.c b/arch/powerpc/kexec/crash.c new file mode 100644 index 000000000..252724ed6 --- /dev/null +++ b/arch/powerpc/kexec/crash.c @@ -0,0 +1,394 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Architecture specific (PPC64) functions for kexec based crash dumps. + * + * Copyright (C) 2005, IBM Corp. + * + * Created by: Haren Myneni + */ + +#include <linux/kernel.h> +#include <linux/smp.h> +#include <linux/reboot.h> +#include <linux/kexec.h> +#include <linux/export.h> +#include <linux/crash_dump.h> +#include <linux/delay.h> +#include <linux/irq.h> +#include <linux/types.h> + +#include <asm/processor.h> +#include <asm/machdep.h> +#include <asm/kexec.h> +#include <asm/smp.h> +#include <asm/setjmp.h> +#include <asm/debug.h> +#include <asm/interrupt.h> + +/* + * The primary CPU waits a while for all secondary CPUs to enter. This is to + * avoid sending an IPI if the secondary CPUs are entering + * crash_kexec_secondary on their own (eg via a system reset). + * + * The secondary timeout has to be longer than the primary. Both timeouts are + * in milliseconds. + */ +#define PRIMARY_TIMEOUT 500 +#define SECONDARY_TIMEOUT 1000 + +#define IPI_TIMEOUT 10000 +#define REAL_MODE_TIMEOUT 10000 + +static int time_to_dump; + +/* + * In case of system reset, secondary CPUs enter crash_kexec_secondary with out + * having to send an IPI explicitly. So, indicate if the crash is via + * system reset to avoid sending another IPI. + */ +static int is_via_system_reset; + +/* + * crash_wake_offline should be set to 1 by platforms that intend to wake + * up offline cpus prior to jumping to a kdump kernel. Currently powernv + * sets it to 1, since we want to avoid things from happening when an + * offline CPU wakes up due to something like an HMI (malfunction error), + * which propagates to all threads. + */ +int crash_wake_offline; + +#define CRASH_HANDLER_MAX 3 +/* List of shutdown handles */ +static crash_shutdown_t crash_shutdown_handles[CRASH_HANDLER_MAX]; +static DEFINE_SPINLOCK(crash_handlers_lock); + +static unsigned long crash_shutdown_buf[JMP_BUF_LEN]; +static int crash_shutdown_cpu = -1; + +static int handle_fault(struct pt_regs *regs) +{ + if (crash_shutdown_cpu == smp_processor_id()) + longjmp(crash_shutdown_buf, 1); + return 0; +} + +#ifdef CONFIG_SMP + +static atomic_t cpus_in_crash; +void crash_ipi_callback(struct pt_regs *regs) +{ + static cpumask_t cpus_state_saved = CPU_MASK_NONE; + + int cpu = smp_processor_id(); + + hard_irq_disable(); + if (!cpumask_test_cpu(cpu, &cpus_state_saved)) { + crash_save_cpu(regs, cpu); + cpumask_set_cpu(cpu, &cpus_state_saved); + } + + atomic_inc(&cpus_in_crash); + smp_mb__after_atomic(); + + /* + * Starting the kdump boot. + * This barrier is needed to make sure that all CPUs are stopped. + */ + while (!time_to_dump) + cpu_relax(); + + if (ppc_md.kexec_cpu_down) + ppc_md.kexec_cpu_down(1, 1); + +#ifdef CONFIG_PPC64 + kexec_smp_wait(); +#else + for (;;); /* FIXME */ +#endif + + /* NOTREACHED */ +} + +static void crash_kexec_prepare_cpus(void) +{ + unsigned int msecs; + volatile unsigned int ncpus = num_online_cpus() - 1;/* Excluding the panic cpu */ + volatile int tries = 0; + int (*old_handler)(struct pt_regs *regs); + + printk(KERN_EMERG "Sending IPI to other CPUs\n"); + + if (crash_wake_offline) + ncpus = num_present_cpus() - 1; + + /* + * If we came in via system reset, secondaries enter via crash_kexec_secondary(). + * So, wait a while for the secondary CPUs to enter for that case. + * Else, send IPI to all other CPUs. + */ + if (is_via_system_reset) + mdelay(PRIMARY_TIMEOUT); + else + crash_send_ipi(crash_ipi_callback); + smp_wmb(); + +again: + /* + * FIXME: Until we will have the way to stop other CPUs reliably, + * the crash CPU will send an IPI and wait for other CPUs to + * respond. + */ + msecs = IPI_TIMEOUT; + while ((atomic_read(&cpus_in_crash) < ncpus) && (--msecs > 0)) + mdelay(1); + + /* Would it be better to replace the trap vector here? */ + + if (atomic_read(&cpus_in_crash) >= ncpus) { + printk(KERN_EMERG "IPI complete\n"); + return; + } + + printk(KERN_EMERG "ERROR: %d cpu(s) not responding\n", + ncpus - atomic_read(&cpus_in_crash)); + + /* + * If we have a panic timeout set then we can't wait indefinitely + * for someone to activate system reset. We also give up on the + * second time through if system reset fail to work. + */ + if ((panic_timeout > 0) || (tries > 0)) + return; + + /* + * A system reset will cause all CPUs to take an 0x100 exception. + * The primary CPU returns here via setjmp, and the secondary + * CPUs reexecute the crash_kexec_secondary path. + */ + old_handler = __debugger; + __debugger = handle_fault; + crash_shutdown_cpu = smp_processor_id(); + + if (setjmp(crash_shutdown_buf) == 0) { + printk(KERN_EMERG "Activate system reset (dumprestart) " + "to stop other cpu(s)\n"); + + /* + * A system reset will force all CPUs to execute the + * crash code again. We need to reset cpus_in_crash so we + * wait for everyone to do this. + */ + atomic_set(&cpus_in_crash, 0); + smp_mb(); + + while (atomic_read(&cpus_in_crash) < ncpus) + cpu_relax(); + } + + crash_shutdown_cpu = -1; + __debugger = old_handler; + + tries++; + goto again; +} + +/* + * This function will be called by secondary cpus. + */ +void crash_kexec_secondary(struct pt_regs *regs) +{ + unsigned long flags; + int msecs = SECONDARY_TIMEOUT; + + local_irq_save(flags); + + /* Wait for the primary crash CPU to signal its progress */ + while (crashing_cpu < 0) { + if (--msecs < 0) { + /* No response, kdump image may not have been loaded */ + local_irq_restore(flags); + return; + } + + mdelay(1); + } + + crash_ipi_callback(regs); +} + +#else /* ! CONFIG_SMP */ + +static void crash_kexec_prepare_cpus(void) +{ + /* + * move the secondaries to us so that we can copy + * the new kernel 0-0x100 safely + * + * do this if kexec in setup.c ? + */ +#ifdef CONFIG_PPC64 + smp_release_cpus(); +#else + /* FIXME */ +#endif +} + +void crash_kexec_secondary(struct pt_regs *regs) +{ +} +#endif /* CONFIG_SMP */ + +/* wait for all the CPUs to hit real mode but timeout if they don't come in */ +#if defined(CONFIG_SMP) && defined(CONFIG_PPC64) +noinstr static void __maybe_unused crash_kexec_wait_realmode(int cpu) +{ + unsigned int msecs; + int i; + + msecs = REAL_MODE_TIMEOUT; + for (i=0; i < nr_cpu_ids && msecs > 0; i++) { + if (i == cpu) + continue; + + while (paca_ptrs[i]->kexec_state < KEXEC_STATE_REAL_MODE) { + barrier(); + if (!cpu_possible(i) || !cpu_online(i) || (msecs <= 0)) + break; + msecs--; + mdelay(1); + } + } + mb(); +} +#else +static inline void crash_kexec_wait_realmode(int cpu) {} +#endif /* CONFIG_SMP && CONFIG_PPC64 */ + +void crash_kexec_prepare(void) +{ + /* Avoid hardlocking with irresponsive CPU holding logbuf_lock */ + printk_deferred_enter(); + + /* + * This function is only called after the system + * has panicked or is otherwise in a critical state. + * The minimum amount of code to allow a kexec'd kernel + * to run successfully needs to happen here. + * + * In practice this means stopping other cpus in + * an SMP system. + * The kernel is broken so disable interrupts. + */ + hard_irq_disable(); + + /* + * Make a note of crashing cpu. Will be used in machine_kexec + * such that another IPI will not be sent. + */ + crashing_cpu = smp_processor_id(); + + crash_kexec_prepare_cpus(); +} + +/* + * Register a function to be called on shutdown. Only use this if you + * can't reset your device in the second kernel. + */ +int crash_shutdown_register(crash_shutdown_t handler) +{ + unsigned int i, rc; + + spin_lock(&crash_handlers_lock); + for (i = 0 ; i < CRASH_HANDLER_MAX; i++) + if (!crash_shutdown_handles[i]) { + /* Insert handle at first empty entry */ + crash_shutdown_handles[i] = handler; + rc = 0; + break; + } + + if (i == CRASH_HANDLER_MAX) { + printk(KERN_ERR "Crash shutdown handles full, " + "not registered.\n"); + rc = 1; + } + + spin_unlock(&crash_handlers_lock); + return rc; +} +EXPORT_SYMBOL(crash_shutdown_register); + +int crash_shutdown_unregister(crash_shutdown_t handler) +{ + unsigned int i, rc; + + spin_lock(&crash_handlers_lock); + for (i = 0 ; i < CRASH_HANDLER_MAX; i++) + if (crash_shutdown_handles[i] == handler) + break; + + if (i == CRASH_HANDLER_MAX) { + printk(KERN_ERR "Crash shutdown handle not found\n"); + rc = 1; + } else { + /* Shift handles down */ + for (; i < (CRASH_HANDLER_MAX - 1); i++) + crash_shutdown_handles[i] = + crash_shutdown_handles[i+1]; + /* + * Reset last entry to NULL now that it has been shifted down, + * this will allow new handles to be added here. + */ + crash_shutdown_handles[i] = NULL; + rc = 0; + } + + spin_unlock(&crash_handlers_lock); + return rc; +} +EXPORT_SYMBOL(crash_shutdown_unregister); + +void default_machine_crash_shutdown(struct pt_regs *regs) +{ + unsigned int i; + int (*old_handler)(struct pt_regs *regs); + + if (TRAP(regs) == INTERRUPT_SYSTEM_RESET) + is_via_system_reset = 1; + + crash_smp_send_stop(); + + crash_save_cpu(regs, crashing_cpu); + + time_to_dump = 1; + + crash_kexec_wait_realmode(crashing_cpu); + + machine_kexec_mask_interrupts(); + + /* + * Call registered shutdown routines safely. Swap out + * __debugger_fault_handler, and replace on exit. + */ + old_handler = __debugger_fault_handler; + __debugger_fault_handler = handle_fault; + crash_shutdown_cpu = smp_processor_id(); + for (i = 0; i < CRASH_HANDLER_MAX && crash_shutdown_handles[i]; i++) { + if (setjmp(crash_shutdown_buf) == 0) { + /* + * Insert syncs and delay to ensure + * instructions in the dangerous region don't + * leak away from this protected region. + */ + asm volatile("sync; isync"); + /* dangerous region */ + crash_shutdown_handles[i](); + asm volatile("sync; isync"); + } + } + crash_shutdown_cpu = -1; + __debugger_fault_handler = old_handler; + + if (ppc_md.kexec_cpu_down) + ppc_md.kexec_cpu_down(1, 0); +} diff --git a/arch/powerpc/kexec/elf_64.c b/arch/powerpc/kexec/elf_64.c new file mode 100644 index 000000000..eeb258002 --- /dev/null +++ b/arch/powerpc/kexec/elf_64.c @@ -0,0 +1,157 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * 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>. + */ + +#define pr_fmt(fmt) "kexec_elf: " fmt + +#include <linux/elf.h> +#include <linux/kexec.h> +#include <linux/libfdt.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/of_fdt.h> +#include <linux/slab.h> +#include <linux/types.h> + +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 ret; + unsigned long kernel_load_addr; + unsigned long initrd_load_addr = 0, fdt_load_addr; + void *fdt; + const void *slave_code; + struct elfhdr ehdr; + char *modified_cmdline = NULL; + struct kexec_elf_info elf_info; + struct kexec_buf kbuf = { .image = image, .buf_min = 0, + .buf_max = ppc64_rma_size }; + struct kexec_buf pbuf = { .image = image, .buf_min = 0, + .buf_max = ppc64_rma_size, .top_down = true, + .mem = KEXEC_BUF_MEM_UNKNOWN }; + + ret = kexec_build_elf_info(kernel_buf, kernel_len, &ehdr, &elf_info); + if (ret) + return ERR_PTR(ret); + + if (image->type == KEXEC_TYPE_CRASH) { + /* min & max buffer values for kdump case */ + kbuf.buf_min = pbuf.buf_min = crashk_res.start; + kbuf.buf_max = pbuf.buf_max = + ((crashk_res.end < ppc64_rma_size) ? + crashk_res.end : (ppc64_rma_size - 1)); + } + + ret = kexec_elf_load(image, &ehdr, &elf_info, &kbuf, &kernel_load_addr); + if (ret) + goto out; + + pr_debug("Loaded the kernel at 0x%lx\n", kernel_load_addr); + + ret = kexec_load_purgatory(image, &pbuf); + if (ret) { + pr_err("Loading purgatory failed.\n"); + goto out; + } + + pr_debug("Loaded purgatory at 0x%lx\n", pbuf.mem); + + /* Load additional segments needed for panic kernel */ + if (image->type == KEXEC_TYPE_CRASH) { + ret = load_crashdump_segments_ppc64(image, &kbuf); + if (ret) { + pr_err("Failed to load kdump kernel segments\n"); + goto out; + } + + /* Setup cmdline for kdump kernel case */ + modified_cmdline = setup_kdump_cmdline(image, cmdline, + cmdline_len); + if (!modified_cmdline) { + pr_err("Setting up cmdline for kdump kernel failed\n"); + ret = -EINVAL; + goto out; + } + cmdline = modified_cmdline; + } + + if (initrd != NULL) { + kbuf.buffer = initrd; + kbuf.bufsz = kbuf.memsz = initrd_len; + kbuf.buf_align = PAGE_SIZE; + kbuf.top_down = false; + kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; + 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 = of_kexec_alloc_and_setup_fdt(image, initrd_load_addr, + initrd_len, cmdline, + kexec_extra_fdt_size_ppc64(image)); + if (!fdt) { + pr_err("Error setting up the new device tree.\n"); + ret = -EINVAL; + goto out; + } + + ret = setup_new_fdt_ppc64(image, fdt, initrd_load_addr, + initrd_len, cmdline); + if (ret) + goto out_free_fdt; + + fdt_pack(fdt); + + kbuf.buffer = fdt; + kbuf.bufsz = kbuf.memsz = fdt_totalsize(fdt); + kbuf.buf_align = PAGE_SIZE; + kbuf.top_down = true; + kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; + ret = kexec_add_buffer(&kbuf); + if (ret) + goto out_free_fdt; + + /* FDT will be freed in arch_kimage_file_post_load_cleanup */ + image->arch.fdt = fdt; + + fdt_load_addr = kbuf.mem; + + pr_debug("Loaded device tree at 0x%lx\n", fdt_load_addr); + + slave_code = elf_info.buffer + elf_info.proghdrs[0].p_offset; + ret = setup_purgatory_ppc64(image, slave_code, fdt, kernel_load_addr, + fdt_load_addr); + if (ret) + pr_err("Error setting up the purgatory.\n"); + + goto out; + +out_free_fdt: + kvfree(fdt); +out: + kfree(modified_cmdline); + kexec_free_elf_info(&elf_info); + + return ret ? ERR_PTR(ret) : NULL; +} + +const struct kexec_file_ops kexec_elf64_ops = { + .probe = kexec_elf_probe, + .load = elf64_load, +}; diff --git a/arch/powerpc/kexec/file_load.c b/arch/powerpc/kexec/file_load.c new file mode 100644 index 000000000..4284f76cb --- /dev/null +++ b/arch/powerpc/kexec/file_load.c @@ -0,0 +1,109 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * powerpc 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>. + */ + +#include <linux/slab.h> +#include <linux/kexec.h> +#include <linux/of_fdt.h> +#include <linux/libfdt.h> +#include <asm/setup.h> + +#define SLAVE_CODE_SIZE 256 /* First 0x100 bytes */ + +/** + * setup_kdump_cmdline - Prepend "elfcorehdr=<addr> " to command line + * of kdump kernel for exporting the core. + * @image: Kexec image + * @cmdline: Command line parameters to update. + * @cmdline_len: Length of the cmdline parameters. + * + * kdump segment must be setup before calling this function. + * + * Returns new cmdline buffer for kdump kernel on success, NULL otherwise. + */ +char *setup_kdump_cmdline(struct kimage *image, char *cmdline, + unsigned long cmdline_len) +{ + int elfcorehdr_strlen; + char *cmdline_ptr; + + cmdline_ptr = kzalloc(COMMAND_LINE_SIZE, GFP_KERNEL); + if (!cmdline_ptr) + return NULL; + + elfcorehdr_strlen = sprintf(cmdline_ptr, "elfcorehdr=0x%lx ", + image->elf_load_addr); + + if (elfcorehdr_strlen + cmdline_len > COMMAND_LINE_SIZE) { + pr_err("Appending elfcorehdr=<addr> exceeds cmdline size\n"); + kfree(cmdline_ptr); + return NULL; + } + + memcpy(cmdline_ptr + elfcorehdr_strlen, cmdline, cmdline_len); + // Ensure it's nul terminated + cmdline_ptr[COMMAND_LINE_SIZE - 1] = '\0'; + return cmdline_ptr; +} + +/** + * 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. + * + * 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 int *slave_code_buf, master_entry; + int ret; + + 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; + + return 0; +} diff --git a/arch/powerpc/kexec/file_load_64.c b/arch/powerpc/kexec/file_load_64.c new file mode 100644 index 000000000..349a781ce --- /dev/null +++ b/arch/powerpc/kexec/file_load_64.c @@ -0,0 +1,1287 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * 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) 2020 IBM Corporation + * + * Based on kexec-tools' kexec-ppc64.c, kexec-elf-rel-ppc64.c, fs2dt.c. + * Heavily modified for the kernel by + * Hari Bathini, IBM Corporation. + */ + +#include <linux/kexec.h> +#include <linux/of_fdt.h> +#include <linux/libfdt.h> +#include <linux/of_device.h> +#include <linux/memblock.h> +#include <linux/slab.h> +#include <linux/vmalloc.h> +#include <asm/setup.h> +#include <asm/drmem.h> +#include <asm/firmware.h> +#include <asm/kexec_ranges.h> +#include <asm/crashdump-ppc64.h> + +struct umem_info { + u64 *buf; /* data buffer for usable-memory property */ + u32 size; /* size allocated for the data buffer */ + u32 max_entries; /* maximum no. of entries */ + u32 idx; /* index of current entry */ + + /* usable memory ranges to look up */ + unsigned int nr_ranges; + const struct crash_mem_range *ranges; +}; + +const struct kexec_file_ops * const kexec_file_loaders[] = { + &kexec_elf64_ops, + NULL +}; + +/** + * get_exclude_memory_ranges - Get exclude memory ranges. This list includes + * regions like opal/rtas, tce-table, initrd, + * kernel, htab which should be avoided while + * setting up kexec load segments. + * @mem_ranges: Range list to add the memory ranges to. + * + * Returns 0 on success, negative errno on error. + */ +static int get_exclude_memory_ranges(struct crash_mem **mem_ranges) +{ + int ret; + + ret = add_tce_mem_ranges(mem_ranges); + if (ret) + goto out; + + ret = add_initrd_mem_range(mem_ranges); + if (ret) + goto out; + + ret = add_htab_mem_range(mem_ranges); + if (ret) + goto out; + + ret = add_kernel_mem_range(mem_ranges); + if (ret) + goto out; + + ret = add_rtas_mem_range(mem_ranges); + if (ret) + goto out; + + ret = add_opal_mem_range(mem_ranges); + if (ret) + goto out; + + ret = add_reserved_mem_ranges(mem_ranges); + if (ret) + goto out; + + /* exclude memory ranges should be sorted for easy lookup */ + sort_memory_ranges(*mem_ranges, true); +out: + if (ret) + pr_err("Failed to setup exclude memory ranges\n"); + return ret; +} + +/** + * get_usable_memory_ranges - Get usable memory ranges. This list includes + * regions like crashkernel, opal/rtas & tce-table, + * that kdump kernel could use. + * @mem_ranges: Range list to add the memory ranges to. + * + * Returns 0 on success, negative errno on error. + */ +static int get_usable_memory_ranges(struct crash_mem **mem_ranges) +{ + int ret; + + /* + * Early boot failure observed on guests when low memory (first memory + * block?) is not added to usable memory. So, add [0, crashk_res.end] + * instead of [crashk_res.start, crashk_res.end] to workaround it. + * Also, crashed kernel's memory must be added to reserve map to + * avoid kdump kernel from using it. + */ + ret = add_mem_range(mem_ranges, 0, crashk_res.end + 1); + if (ret) + goto out; + + ret = add_rtas_mem_range(mem_ranges); + if (ret) + goto out; + + ret = add_opal_mem_range(mem_ranges); + if (ret) + goto out; + + ret = add_tce_mem_ranges(mem_ranges); +out: + if (ret) + pr_err("Failed to setup usable memory ranges\n"); + return ret; +} + +/** + * get_crash_memory_ranges - Get crash memory ranges. This list includes + * first/crashing kernel's memory regions that + * would be exported via an elfcore. + * @mem_ranges: Range list to add the memory ranges to. + * + * Returns 0 on success, negative errno on error. + */ +static int get_crash_memory_ranges(struct crash_mem **mem_ranges) +{ + phys_addr_t base, end; + struct crash_mem *tmem; + u64 i; + int ret; + + for_each_mem_range(i, &base, &end) { + u64 size = end - base; + + /* Skip backup memory region, which needs a separate entry */ + if (base == BACKUP_SRC_START) { + if (size > BACKUP_SRC_SIZE) { + base = BACKUP_SRC_END + 1; + size -= BACKUP_SRC_SIZE; + } else + continue; + } + + ret = add_mem_range(mem_ranges, base, size); + if (ret) + goto out; + + /* Try merging adjacent ranges before reallocation attempt */ + if ((*mem_ranges)->nr_ranges == (*mem_ranges)->max_nr_ranges) + sort_memory_ranges(*mem_ranges, true); + } + + /* Reallocate memory ranges if there is no space to split ranges */ + tmem = *mem_ranges; + if (tmem && (tmem->nr_ranges == tmem->max_nr_ranges)) { + tmem = realloc_mem_ranges(mem_ranges); + if (!tmem) + goto out; + } + + /* Exclude crashkernel region */ + ret = crash_exclude_mem_range(tmem, crashk_res.start, crashk_res.end); + if (ret) + goto out; + + /* + * FIXME: For now, stay in parity with kexec-tools but if RTAS/OPAL + * regions are exported to save their context at the time of + * crash, they should actually be backed up just like the + * first 64K bytes of memory. + */ + ret = add_rtas_mem_range(mem_ranges); + if (ret) + goto out; + + ret = add_opal_mem_range(mem_ranges); + if (ret) + goto out; + + /* create a separate program header for the backup region */ + ret = add_mem_range(mem_ranges, BACKUP_SRC_START, BACKUP_SRC_SIZE); + if (ret) + goto out; + + sort_memory_ranges(*mem_ranges, false); +out: + if (ret) + pr_err("Failed to setup crash memory ranges\n"); + return ret; +} + +/** + * get_reserved_memory_ranges - Get reserve memory ranges. This list includes + * memory regions that should be added to the + * memory reserve map to ensure the region is + * protected from any mischief. + * @mem_ranges: Range list to add the memory ranges to. + * + * Returns 0 on success, negative errno on error. + */ +static int get_reserved_memory_ranges(struct crash_mem **mem_ranges) +{ + int ret; + + ret = add_rtas_mem_range(mem_ranges); + if (ret) + goto out; + + ret = add_tce_mem_ranges(mem_ranges); + if (ret) + goto out; + + ret = add_reserved_mem_ranges(mem_ranges); +out: + if (ret) + pr_err("Failed to setup reserved memory ranges\n"); + return ret; +} + +/** + * __locate_mem_hole_top_down - Looks top down for a large enough memory hole + * in the memory regions between buf_min & buf_max + * for the buffer. If found, sets kbuf->mem. + * @kbuf: Buffer contents and memory parameters. + * @buf_min: Minimum address for the buffer. + * @buf_max: Maximum address for the buffer. + * + * Returns 0 on success, negative errno on error. + */ +static int __locate_mem_hole_top_down(struct kexec_buf *kbuf, + u64 buf_min, u64 buf_max) +{ + int ret = -EADDRNOTAVAIL; + phys_addr_t start, end; + u64 i; + + for_each_mem_range_rev(i, &start, &end) { + /* + * memblock uses [start, end) convention while it is + * [start, end] here. Fix the off-by-one to have the + * same convention. + */ + end -= 1; + + if (start > buf_max) + continue; + + /* Memory hole not found */ + if (end < buf_min) + break; + + /* Adjust memory region based on the given range */ + if (start < buf_min) + start = buf_min; + if (end > buf_max) + end = buf_max; + + start = ALIGN(start, kbuf->buf_align); + if (start < end && (end - start + 1) >= kbuf->memsz) { + /* Suitable memory range found. Set kbuf->mem */ + kbuf->mem = ALIGN_DOWN(end - kbuf->memsz + 1, + kbuf->buf_align); + ret = 0; + break; + } + } + + return ret; +} + +/** + * locate_mem_hole_top_down_ppc64 - Skip special memory regions to find a + * suitable buffer with top down approach. + * @kbuf: Buffer contents and memory parameters. + * @buf_min: Minimum address for the buffer. + * @buf_max: Maximum address for the buffer. + * @emem: Exclude memory ranges. + * + * Returns 0 on success, negative errno on error. + */ +static int locate_mem_hole_top_down_ppc64(struct kexec_buf *kbuf, + u64 buf_min, u64 buf_max, + const struct crash_mem *emem) +{ + int i, ret = 0, err = -EADDRNOTAVAIL; + u64 start, end, tmin, tmax; + + tmax = buf_max; + for (i = (emem->nr_ranges - 1); i >= 0; i--) { + start = emem->ranges[i].start; + end = emem->ranges[i].end; + + if (start > tmax) + continue; + + if (end < tmax) { + tmin = (end < buf_min ? buf_min : end + 1); + ret = __locate_mem_hole_top_down(kbuf, tmin, tmax); + if (!ret) + return 0; + } + + tmax = start - 1; + + if (tmax < buf_min) { + ret = err; + break; + } + ret = 0; + } + + if (!ret) { + tmin = buf_min; + ret = __locate_mem_hole_top_down(kbuf, tmin, tmax); + } + return ret; +} + +/** + * __locate_mem_hole_bottom_up - Looks bottom up for a large enough memory hole + * in the memory regions between buf_min & buf_max + * for the buffer. If found, sets kbuf->mem. + * @kbuf: Buffer contents and memory parameters. + * @buf_min: Minimum address for the buffer. + * @buf_max: Maximum address for the buffer. + * + * Returns 0 on success, negative errno on error. + */ +static int __locate_mem_hole_bottom_up(struct kexec_buf *kbuf, + u64 buf_min, u64 buf_max) +{ + int ret = -EADDRNOTAVAIL; + phys_addr_t start, end; + u64 i; + + for_each_mem_range(i, &start, &end) { + /* + * memblock uses [start, end) convention while it is + * [start, end] here. Fix the off-by-one to have the + * same convention. + */ + end -= 1; + + if (end < buf_min) + continue; + + /* Memory hole not found */ + if (start > buf_max) + break; + + /* Adjust memory region based on the given range */ + if (start < buf_min) + start = buf_min; + if (end > buf_max) + end = buf_max; + + start = ALIGN(start, kbuf->buf_align); + if (start < end && (end - start + 1) >= kbuf->memsz) { + /* Suitable memory range found. Set kbuf->mem */ + kbuf->mem = start; + ret = 0; + break; + } + } + + return ret; +} + +/** + * locate_mem_hole_bottom_up_ppc64 - Skip special memory regions to find a + * suitable buffer with bottom up approach. + * @kbuf: Buffer contents and memory parameters. + * @buf_min: Minimum address for the buffer. + * @buf_max: Maximum address for the buffer. + * @emem: Exclude memory ranges. + * + * Returns 0 on success, negative errno on error. + */ +static int locate_mem_hole_bottom_up_ppc64(struct kexec_buf *kbuf, + u64 buf_min, u64 buf_max, + const struct crash_mem *emem) +{ + int i, ret = 0, err = -EADDRNOTAVAIL; + u64 start, end, tmin, tmax; + + tmin = buf_min; + for (i = 0; i < emem->nr_ranges; i++) { + start = emem->ranges[i].start; + end = emem->ranges[i].end; + + if (end < tmin) + continue; + + if (start > tmin) { + tmax = (start > buf_max ? buf_max : start - 1); + ret = __locate_mem_hole_bottom_up(kbuf, tmin, tmax); + if (!ret) + return 0; + } + + tmin = end + 1; + + if (tmin > buf_max) { + ret = err; + break; + } + ret = 0; + } + + if (!ret) { + tmax = buf_max; + ret = __locate_mem_hole_bottom_up(kbuf, tmin, tmax); + } + return ret; +} + +/** + * check_realloc_usable_mem - Reallocate buffer if it can't accommodate entries + * @um_info: Usable memory buffer and ranges info. + * @cnt: No. of entries to accommodate. + * + * Frees up the old buffer if memory reallocation fails. + * + * Returns buffer on success, NULL on error. + */ +static u64 *check_realloc_usable_mem(struct umem_info *um_info, int cnt) +{ + u32 new_size; + u64 *tbuf; + + if ((um_info->idx + cnt) <= um_info->max_entries) + return um_info->buf; + + new_size = um_info->size + MEM_RANGE_CHUNK_SZ; + tbuf = krealloc(um_info->buf, new_size, GFP_KERNEL); + if (tbuf) { + um_info->buf = tbuf; + um_info->size = new_size; + um_info->max_entries = (um_info->size / sizeof(u64)); + } + + return tbuf; +} + +/** + * add_usable_mem - Add the usable memory ranges within the given memory range + * to the buffer + * @um_info: Usable memory buffer and ranges info. + * @base: Base address of memory range to look for. + * @end: End address of memory range to look for. + * + * Returns 0 on success, negative errno on error. + */ +static int add_usable_mem(struct umem_info *um_info, u64 base, u64 end) +{ + u64 loc_base, loc_end; + bool add; + int i; + + for (i = 0; i < um_info->nr_ranges; i++) { + add = false; + loc_base = um_info->ranges[i].start; + loc_end = um_info->ranges[i].end; + if (loc_base >= base && loc_end <= end) + add = true; + else if (base < loc_end && end > loc_base) { + if (loc_base < base) + loc_base = base; + if (loc_end > end) + loc_end = end; + add = true; + } + + if (add) { + if (!check_realloc_usable_mem(um_info, 2)) + return -ENOMEM; + + um_info->buf[um_info->idx++] = cpu_to_be64(loc_base); + um_info->buf[um_info->idx++] = + cpu_to_be64(loc_end - loc_base + 1); + } + } + + return 0; +} + +/** + * kdump_setup_usable_lmb - This is a callback function that gets called by + * walk_drmem_lmbs for every LMB to set its + * usable memory ranges. + * @lmb: LMB info. + * @usm: linux,drconf-usable-memory property value. + * @data: Pointer to usable memory buffer and ranges info. + * + * Returns 0 on success, negative errno on error. + */ +static int kdump_setup_usable_lmb(struct drmem_lmb *lmb, const __be32 **usm, + void *data) +{ + struct umem_info *um_info; + int tmp_idx, ret; + u64 base, end; + + /* + * kdump load isn't supported on kernels already booted with + * linux,drconf-usable-memory property. + */ + if (*usm) { + pr_err("linux,drconf-usable-memory property already exists!"); + return -EINVAL; + } + + um_info = data; + tmp_idx = um_info->idx; + if (!check_realloc_usable_mem(um_info, 1)) + return -ENOMEM; + + um_info->idx++; + base = lmb->base_addr; + end = base + drmem_lmb_size() - 1; + ret = add_usable_mem(um_info, base, end); + if (!ret) { + /* + * Update the no. of ranges added. Two entries (base & size) + * for every range added. + */ + um_info->buf[tmp_idx] = + cpu_to_be64((um_info->idx - tmp_idx - 1) / 2); + } + + return ret; +} + +#define NODE_PATH_LEN 256 +/** + * add_usable_mem_property - Add usable memory property for the given + * memory node. + * @fdt: Flattened device tree for the kdump kernel. + * @dn: Memory node. + * @um_info: Usable memory buffer and ranges info. + * + * Returns 0 on success, negative errno on error. + */ +static int add_usable_mem_property(void *fdt, struct device_node *dn, + struct umem_info *um_info) +{ + int n_mem_addr_cells, n_mem_size_cells, node; + char path[NODE_PATH_LEN]; + int i, len, ranges, ret; + const __be32 *prop; + u64 base, end; + + of_node_get(dn); + + if (snprintf(path, NODE_PATH_LEN, "%pOF", dn) > (NODE_PATH_LEN - 1)) { + pr_err("Buffer (%d) too small for memory node: %pOF\n", + NODE_PATH_LEN, dn); + return -EOVERFLOW; + } + pr_debug("Memory node path: %s\n", path); + + /* Now that we know the path, find its offset in kdump kernel's fdt */ + node = fdt_path_offset(fdt, path); + if (node < 0) { + pr_err("Malformed device tree: error reading %s\n", path); + ret = -EINVAL; + goto out; + } + + /* Get the address & size cells */ + n_mem_addr_cells = of_n_addr_cells(dn); + n_mem_size_cells = of_n_size_cells(dn); + pr_debug("address cells: %d, size cells: %d\n", n_mem_addr_cells, + n_mem_size_cells); + + um_info->idx = 0; + if (!check_realloc_usable_mem(um_info, 2)) { + ret = -ENOMEM; + goto out; + } + + prop = of_get_property(dn, "reg", &len); + if (!prop || len <= 0) { + ret = 0; + goto out; + } + + /* + * "reg" property represents sequence of (addr,size) tuples + * each representing a memory range. + */ + ranges = (len >> 2) / (n_mem_addr_cells + n_mem_size_cells); + + for (i = 0; i < ranges; i++) { + base = of_read_number(prop, n_mem_addr_cells); + prop += n_mem_addr_cells; + end = base + of_read_number(prop, n_mem_size_cells) - 1; + prop += n_mem_size_cells; + + ret = add_usable_mem(um_info, base, end); + if (ret) + goto out; + } + + /* + * No kdump kernel usable memory found in this memory node. + * Write (0,0) tuple in linux,usable-memory property for + * this region to be ignored. + */ + if (um_info->idx == 0) { + um_info->buf[0] = 0; + um_info->buf[1] = 0; + um_info->idx = 2; + } + + ret = fdt_setprop(fdt, node, "linux,usable-memory", um_info->buf, + (um_info->idx * sizeof(u64))); + +out: + of_node_put(dn); + return ret; +} + + +/** + * update_usable_mem_fdt - Updates kdump kernel's fdt with linux,usable-memory + * and linux,drconf-usable-memory DT properties as + * appropriate to restrict its memory usage. + * @fdt: Flattened device tree for the kdump kernel. + * @usable_mem: Usable memory ranges for kdump kernel. + * + * Returns 0 on success, negative errno on error. + */ +static int update_usable_mem_fdt(void *fdt, struct crash_mem *usable_mem) +{ + struct umem_info um_info; + struct device_node *dn; + int node, ret = 0; + + if (!usable_mem) { + pr_err("Usable memory ranges for kdump kernel not found\n"); + return -ENOENT; + } + + node = fdt_path_offset(fdt, "/ibm,dynamic-reconfiguration-memory"); + if (node == -FDT_ERR_NOTFOUND) + pr_debug("No dynamic reconfiguration memory found\n"); + else if (node < 0) { + pr_err("Malformed device tree: error reading /ibm,dynamic-reconfiguration-memory.\n"); + return -EINVAL; + } + + um_info.buf = NULL; + um_info.size = 0; + um_info.max_entries = 0; + um_info.idx = 0; + /* Memory ranges to look up */ + um_info.ranges = &(usable_mem->ranges[0]); + um_info.nr_ranges = usable_mem->nr_ranges; + + dn = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory"); + if (dn) { + ret = walk_drmem_lmbs(dn, &um_info, kdump_setup_usable_lmb); + of_node_put(dn); + + if (ret) { + pr_err("Could not setup linux,drconf-usable-memory property for kdump\n"); + goto out; + } + + ret = fdt_setprop(fdt, node, "linux,drconf-usable-memory", + um_info.buf, (um_info.idx * sizeof(u64))); + if (ret) { + pr_err("Failed to update fdt with linux,drconf-usable-memory property"); + goto out; + } + } + + /* + * Walk through each memory node and set linux,usable-memory property + * for the corresponding node in kdump kernel's fdt. + */ + for_each_node_by_type(dn, "memory") { + ret = add_usable_mem_property(fdt, dn, &um_info); + if (ret) { + pr_err("Failed to set linux,usable-memory property for %s node", + dn->full_name); + of_node_put(dn); + goto out; + } + } + +out: + kfree(um_info.buf); + return ret; +} + +/** + * load_backup_segment - Locate a memory hole to place the backup region. + * @image: Kexec image. + * @kbuf: Buffer contents and memory parameters. + * + * Returns 0 on success, negative errno on error. + */ +static int load_backup_segment(struct kimage *image, struct kexec_buf *kbuf) +{ + void *buf; + int ret; + + /* + * Setup a source buffer for backup segment. + * + * A source buffer has no meaning for backup region as data will + * be copied from backup source, after crash, in the purgatory. + * But as load segment code doesn't recognize such segments, + * setup a dummy source buffer to keep it happy for now. + */ + buf = vzalloc(BACKUP_SRC_SIZE); + if (!buf) + return -ENOMEM; + + kbuf->buffer = buf; + kbuf->mem = KEXEC_BUF_MEM_UNKNOWN; + kbuf->bufsz = kbuf->memsz = BACKUP_SRC_SIZE; + kbuf->top_down = false; + + ret = kexec_add_buffer(kbuf); + if (ret) { + vfree(buf); + return ret; + } + + image->arch.backup_buf = buf; + image->arch.backup_start = kbuf->mem; + return 0; +} + +/** + * update_backup_region_phdr - Update backup region's offset for the core to + * export the region appropriately. + * @image: Kexec image. + * @ehdr: ELF core header. + * + * Assumes an exclusive program header is setup for the backup region + * in the ELF headers + * + * Returns nothing. + */ +static void update_backup_region_phdr(struct kimage *image, Elf64_Ehdr *ehdr) +{ + Elf64_Phdr *phdr; + unsigned int i; + + phdr = (Elf64_Phdr *)(ehdr + 1); + for (i = 0; i < ehdr->e_phnum; i++) { + if (phdr->p_paddr == BACKUP_SRC_START) { + phdr->p_offset = image->arch.backup_start; + pr_debug("Backup region offset updated to 0x%lx\n", + image->arch.backup_start); + return; + } + } +} + +/** + * load_elfcorehdr_segment - Setup crash memory ranges and initialize elfcorehdr + * segment needed to load kdump kernel. + * @image: Kexec image. + * @kbuf: Buffer contents and memory parameters. + * + * Returns 0 on success, negative errno on error. + */ +static int load_elfcorehdr_segment(struct kimage *image, struct kexec_buf *kbuf) +{ + struct crash_mem *cmem = NULL; + unsigned long headers_sz; + void *headers = NULL; + int ret; + + ret = get_crash_memory_ranges(&cmem); + if (ret) + goto out; + + /* Setup elfcorehdr segment */ + ret = crash_prepare_elf64_headers(cmem, false, &headers, &headers_sz); + if (ret) { + pr_err("Failed to prepare elf headers for the core\n"); + goto out; + } + + /* Fix the offset for backup region in the ELF header */ + update_backup_region_phdr(image, headers); + + kbuf->buffer = headers; + kbuf->mem = KEXEC_BUF_MEM_UNKNOWN; + kbuf->bufsz = kbuf->memsz = headers_sz; + kbuf->top_down = false; + + ret = kexec_add_buffer(kbuf); + if (ret) { + vfree(headers); + goto out; + } + + image->elf_load_addr = kbuf->mem; + image->elf_headers_sz = headers_sz; + image->elf_headers = headers; +out: + kfree(cmem); + return ret; +} + +/** + * load_crashdump_segments_ppc64 - Initialize the additional segements needed + * to load kdump kernel. + * @image: Kexec image. + * @kbuf: Buffer contents and memory parameters. + * + * Returns 0 on success, negative errno on error. + */ +int load_crashdump_segments_ppc64(struct kimage *image, + struct kexec_buf *kbuf) +{ + int ret; + + /* Load backup segment - first 64K bytes of the crashing kernel */ + ret = load_backup_segment(image, kbuf); + if (ret) { + pr_err("Failed to load backup segment\n"); + return ret; + } + pr_debug("Loaded the backup region at 0x%lx\n", kbuf->mem); + + /* Load elfcorehdr segment - to export crashing kernel's vmcore */ + ret = load_elfcorehdr_segment(image, kbuf); + if (ret) { + pr_err("Failed to load elfcorehdr segment\n"); + return ret; + } + pr_debug("Loaded elf core header at 0x%lx, bufsz=0x%lx memsz=0x%lx\n", + image->elf_load_addr, kbuf->bufsz, kbuf->memsz); + + return 0; +} + +/** + * setup_purgatory_ppc64 - initialize PPC64 specific purgatory's global + * variables and call setup_purgatory() to initialize + * common global variable. + * @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. + * + * Returns 0 on success, negative errno on error. + */ +int setup_purgatory_ppc64(struct kimage *image, const void *slave_code, + const void *fdt, unsigned long kernel_load_addr, + unsigned long fdt_load_addr) +{ + struct device_node *dn = NULL; + int ret; + + ret = setup_purgatory(image, slave_code, fdt, kernel_load_addr, + fdt_load_addr); + if (ret) + goto out; + + if (image->type == KEXEC_TYPE_CRASH) { + u32 my_run_at_load = 1; + + /* + * Tell relocatable kernel to run at load address + * via the word meant for that at 0x5c. + */ + ret = kexec_purgatory_get_set_symbol(image, "run_at_load", + &my_run_at_load, + sizeof(my_run_at_load), + false); + if (ret) + goto out; + } + + /* Tell purgatory where to look for backup region */ + ret = kexec_purgatory_get_set_symbol(image, "backup_start", + &image->arch.backup_start, + sizeof(image->arch.backup_start), + false); + if (ret) + goto out; + + /* Setup OPAL base & entry values */ + dn = of_find_node_by_path("/ibm,opal"); + if (dn) { + u64 val; + + of_property_read_u64(dn, "opal-base-address", &val); + ret = kexec_purgatory_get_set_symbol(image, "opal_base", &val, + sizeof(val), false); + if (ret) + goto out; + + of_property_read_u64(dn, "opal-entry-address", &val); + ret = kexec_purgatory_get_set_symbol(image, "opal_entry", &val, + sizeof(val), false); + } +out: + if (ret) + pr_err("Failed to setup purgatory symbols"); + of_node_put(dn); + return ret; +} + +/** + * kexec_extra_fdt_size_ppc64 - Return the estimated additional size needed to + * setup FDT for kexec/kdump kernel. + * @image: kexec image being loaded. + * + * Returns the estimated extra size needed for kexec/kdump kernel FDT. + */ +unsigned int kexec_extra_fdt_size_ppc64(struct kimage *image) +{ + u64 usm_entries; + + if (image->type != KEXEC_TYPE_CRASH) + return 0; + + /* + * For kdump kernel, account for linux,usable-memory and + * linux,drconf-usable-memory properties. Get an approximate on the + * number of usable memory entries and use for FDT size estimation. + */ + usm_entries = ((memblock_end_of_DRAM() / drmem_lmb_size()) + + (2 * (resource_size(&crashk_res) / drmem_lmb_size()))); + return (unsigned int)(usm_entries * sizeof(u64)); +} + +/** + * add_node_props - Reads node properties from device node structure and add + * them to fdt. + * @fdt: Flattened device tree of the kernel + * @node_offset: offset of the node to add a property at + * @dn: device node pointer + * + * Returns 0 on success, negative errno on error. + */ +static int add_node_props(void *fdt, int node_offset, const struct device_node *dn) +{ + int ret = 0; + struct property *pp; + + if (!dn) + return -EINVAL; + + for_each_property_of_node(dn, pp) { + ret = fdt_setprop(fdt, node_offset, pp->name, pp->value, pp->length); + if (ret < 0) { + pr_err("Unable to add %s property: %s\n", pp->name, fdt_strerror(ret)); + return ret; + } + } + return ret; +} + +/** + * update_cpus_node - Update cpus node of flattened device tree using of_root + * device node. + * @fdt: Flattened device tree of the kernel. + * + * Returns 0 on success, negative errno on error. + */ +static int update_cpus_node(void *fdt) +{ + struct device_node *cpus_node, *dn; + int cpus_offset, cpus_subnode_offset, ret = 0; + + cpus_offset = fdt_path_offset(fdt, "/cpus"); + if (cpus_offset < 0 && cpus_offset != -FDT_ERR_NOTFOUND) { + pr_err("Malformed device tree: error reading /cpus node: %s\n", + fdt_strerror(cpus_offset)); + return cpus_offset; + } + + if (cpus_offset > 0) { + ret = fdt_del_node(fdt, cpus_offset); + if (ret < 0) { + pr_err("Error deleting /cpus node: %s\n", fdt_strerror(ret)); + return -EINVAL; + } + } + + /* Add cpus node to fdt */ + cpus_offset = fdt_add_subnode(fdt, fdt_path_offset(fdt, "/"), "cpus"); + if (cpus_offset < 0) { + pr_err("Error creating /cpus node: %s\n", fdt_strerror(cpus_offset)); + return -EINVAL; + } + + /* Add cpus node properties */ + cpus_node = of_find_node_by_path("/cpus"); + ret = add_node_props(fdt, cpus_offset, cpus_node); + of_node_put(cpus_node); + if (ret < 0) + return ret; + + /* Loop through all subnodes of cpus and add them to fdt */ + for_each_node_by_type(dn, "cpu") { + cpus_subnode_offset = fdt_add_subnode(fdt, cpus_offset, dn->full_name); + if (cpus_subnode_offset < 0) { + pr_err("Unable to add %s subnode: %s\n", dn->full_name, + fdt_strerror(cpus_subnode_offset)); + ret = cpus_subnode_offset; + goto out; + } + + ret = add_node_props(fdt, cpus_subnode_offset, dn); + if (ret < 0) + goto out; + } +out: + of_node_put(dn); + return ret; +} + +static int copy_property(void *fdt, int node_offset, const struct device_node *dn, + const char *propname) +{ + const void *prop, *fdtprop; + int len = 0, fdtlen = 0; + + prop = of_get_property(dn, propname, &len); + fdtprop = fdt_getprop(fdt, node_offset, propname, &fdtlen); + + if (fdtprop && !prop) + return fdt_delprop(fdt, node_offset, propname); + else if (prop) + return fdt_setprop(fdt, node_offset, propname, prop, len); + else + return -FDT_ERR_NOTFOUND; +} + +static int update_pci_dma_nodes(void *fdt, const char *dmapropname) +{ + struct device_node *dn; + int pci_offset, root_offset, ret = 0; + + if (!firmware_has_feature(FW_FEATURE_LPAR)) + return 0; + + root_offset = fdt_path_offset(fdt, "/"); + for_each_node_with_property(dn, dmapropname) { + pci_offset = fdt_subnode_offset(fdt, root_offset, of_node_full_name(dn)); + if (pci_offset < 0) + continue; + + ret = copy_property(fdt, pci_offset, dn, "ibm,dma-window"); + if (ret < 0) + break; + ret = copy_property(fdt, pci_offset, dn, dmapropname); + if (ret < 0) + break; + } + + return ret; +} + +/** + * setup_new_fdt_ppc64 - Update the flattend device-tree of the kernel + * being loaded. + * @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. + * + * Returns 0 on success, negative errno on error. + */ +int setup_new_fdt_ppc64(const struct kimage *image, void *fdt, + unsigned long initrd_load_addr, + unsigned long initrd_len, const char *cmdline) +{ + struct crash_mem *umem = NULL, *rmem = NULL; + int i, nr_ranges, ret; + + /* + * Restrict memory usage for kdump kernel by setting up + * usable memory ranges and memory reserve map. + */ + if (image->type == KEXEC_TYPE_CRASH) { + ret = get_usable_memory_ranges(&umem); + if (ret) + goto out; + + ret = update_usable_mem_fdt(fdt, umem); + if (ret) { + pr_err("Error setting up usable-memory property for kdump kernel\n"); + goto out; + } + + /* + * Ensure we don't touch crashed kernel's memory except the + * first 64K of RAM, which will be backed up. + */ + ret = fdt_add_mem_rsv(fdt, BACKUP_SRC_END + 1, + crashk_res.start - BACKUP_SRC_SIZE); + if (ret) { + pr_err("Error reserving crash memory: %s\n", + fdt_strerror(ret)); + goto out; + } + + /* Ensure backup region is not used by kdump/capture kernel */ + ret = fdt_add_mem_rsv(fdt, image->arch.backup_start, + BACKUP_SRC_SIZE); + if (ret) { + pr_err("Error reserving memory for backup: %s\n", + fdt_strerror(ret)); + goto out; + } + } + + /* Update cpus nodes information to account hotplug CPUs. */ + ret = update_cpus_node(fdt); + if (ret < 0) + goto out; + +#define DIRECT64_PROPNAME "linux,direct64-ddr-window-info" +#define DMA64_PROPNAME "linux,dma64-ddr-window-info" + ret = update_pci_dma_nodes(fdt, DIRECT64_PROPNAME); + if (ret < 0) + goto out; + + ret = update_pci_dma_nodes(fdt, DMA64_PROPNAME); + if (ret < 0) + goto out; +#undef DMA64_PROPNAME +#undef DIRECT64_PROPNAME + + /* Update memory reserve map */ + ret = get_reserved_memory_ranges(&rmem); + if (ret) + goto out; + + nr_ranges = rmem ? rmem->nr_ranges : 0; + for (i = 0; i < nr_ranges; i++) { + u64 base, size; + + base = rmem->ranges[i].start; + size = rmem->ranges[i].end - base + 1; + ret = fdt_add_mem_rsv(fdt, base, size); + if (ret) { + pr_err("Error updating memory reserve map: %s\n", + fdt_strerror(ret)); + goto out; + } + } + +out: + kfree(rmem); + kfree(umem); + return ret; +} + +/** + * arch_kexec_locate_mem_hole - Skip special memory regions like rtas, opal, + * tce-table, reserved-ranges & such (exclude + * memory ranges) as they can't be used for kexec + * segment buffer. Sets kbuf->mem when a suitable + * memory hole is found. + * @kbuf: Buffer contents and memory parameters. + * + * Assumes minimum of PAGE_SIZE alignment for kbuf->memsz & kbuf->buf_align. + * + * Returns 0 on success, negative errno on error. + */ +int arch_kexec_locate_mem_hole(struct kexec_buf *kbuf) +{ + struct crash_mem **emem; + u64 buf_min, buf_max; + int ret; + + /* Look up the exclude ranges list while locating the memory hole */ + emem = &(kbuf->image->arch.exclude_ranges); + if (!(*emem) || ((*emem)->nr_ranges == 0)) { + pr_warn("No exclude range list. Using the default locate mem hole method\n"); + return kexec_locate_mem_hole(kbuf); + } + + buf_min = kbuf->buf_min; + buf_max = kbuf->buf_max; + /* Segments for kdump kernel should be within crashkernel region */ + if (kbuf->image->type == KEXEC_TYPE_CRASH) { + buf_min = (buf_min < crashk_res.start ? + crashk_res.start : buf_min); + buf_max = (buf_max > crashk_res.end ? + crashk_res.end : buf_max); + } + + if (buf_min > buf_max) { + pr_err("Invalid buffer min and/or max values\n"); + return -EINVAL; + } + + if (kbuf->top_down) + ret = locate_mem_hole_top_down_ppc64(kbuf, buf_min, buf_max, + *emem); + else + ret = locate_mem_hole_bottom_up_ppc64(kbuf, buf_min, buf_max, + *emem); + + /* Add the buffer allocated to the exclude list for the next lookup */ + if (!ret) { + add_mem_range(emem, kbuf->mem, kbuf->memsz); + sort_memory_ranges(*emem, true); + } else { + pr_err("Failed to locate memory buffer of size %lu\n", + kbuf->memsz); + } + return ret; +} + +/** + * arch_kexec_kernel_image_probe - Does additional handling needed to setup + * kexec segments. + * @image: kexec image being loaded. + * @buf: Buffer pointing to elf data. + * @buf_len: Length of the buffer. + * + * Returns 0 on success, negative errno on error. + */ +int arch_kexec_kernel_image_probe(struct kimage *image, void *buf, + unsigned long buf_len) +{ + int ret; + + /* Get exclude memory ranges needed for setting up kexec segments */ + ret = get_exclude_memory_ranges(&(image->arch.exclude_ranges)); + if (ret) { + pr_err("Failed to setup exclude memory ranges for buffer lookup\n"); + return ret; + } + + return kexec_image_probe_default(image, buf, buf_len); +} + +/** + * arch_kimage_file_post_load_cleanup - Frees up all the allocations done + * while loading the image. + * @image: kexec image being loaded. + * + * Returns 0 on success, negative errno on error. + */ +int arch_kimage_file_post_load_cleanup(struct kimage *image) +{ + kfree(image->arch.exclude_ranges); + image->arch.exclude_ranges = NULL; + + vfree(image->arch.backup_buf); + image->arch.backup_buf = NULL; + + vfree(image->elf_headers); + image->elf_headers = NULL; + image->elf_headers_sz = 0; + + kvfree(image->arch.fdt); + image->arch.fdt = NULL; + + return kexec_image_post_load_cleanup_default(image); +} diff --git a/arch/powerpc/kexec/ranges.c b/arch/powerpc/kexec/ranges.c new file mode 100644 index 000000000..563e9989a --- /dev/null +++ b/arch/powerpc/kexec/ranges.c @@ -0,0 +1,412 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * powerpc 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) 2020 IBM Corporation + * + * Based on kexec-tools' kexec-ppc64.c, fs2dt.c. + * Heavily modified for the kernel by + * Hari Bathini, IBM Corporation. + */ + +#define pr_fmt(fmt) "kexec ranges: " fmt + +#include <linux/sort.h> +#include <linux/kexec.h> +#include <linux/of_device.h> +#include <linux/slab.h> +#include <asm/sections.h> +#include <asm/kexec_ranges.h> + +/** + * get_max_nr_ranges - Get the max no. of ranges crash_mem structure + * could hold, given the size allocated for it. + * @size: Allocation size of crash_mem structure. + * + * Returns the maximum no. of ranges. + */ +static inline unsigned int get_max_nr_ranges(size_t size) +{ + return ((size - sizeof(struct crash_mem)) / + sizeof(struct crash_mem_range)); +} + +/** + * get_mem_rngs_size - Get the allocated size of mem_rngs based on + * max_nr_ranges and chunk size. + * @mem_rngs: Memory ranges. + * + * Returns the maximum size of @mem_rngs. + */ +static inline size_t get_mem_rngs_size(struct crash_mem *mem_rngs) +{ + size_t size; + + if (!mem_rngs) + return 0; + + size = (sizeof(struct crash_mem) + + (mem_rngs->max_nr_ranges * sizeof(struct crash_mem_range))); + + /* + * Memory is allocated in size multiple of MEM_RANGE_CHUNK_SZ. + * So, align to get the actual length. + */ + return ALIGN(size, MEM_RANGE_CHUNK_SZ); +} + +/** + * __add_mem_range - add a memory range to memory ranges list. + * @mem_ranges: Range list to add the memory range to. + * @base: Base address of the range to add. + * @size: Size of the memory range to add. + * + * (Re)allocates memory, if needed. + * + * Returns 0 on success, negative errno on error. + */ +static int __add_mem_range(struct crash_mem **mem_ranges, u64 base, u64 size) +{ + struct crash_mem *mem_rngs = *mem_ranges; + + if (!mem_rngs || (mem_rngs->nr_ranges == mem_rngs->max_nr_ranges)) { + mem_rngs = realloc_mem_ranges(mem_ranges); + if (!mem_rngs) + return -ENOMEM; + } + + mem_rngs->ranges[mem_rngs->nr_ranges].start = base; + mem_rngs->ranges[mem_rngs->nr_ranges].end = base + size - 1; + pr_debug("Added memory range [%#016llx - %#016llx] at index %d\n", + base, base + size - 1, mem_rngs->nr_ranges); + mem_rngs->nr_ranges++; + return 0; +} + +/** + * __merge_memory_ranges - Merges the given memory ranges list. + * @mem_rngs: Range list to merge. + * + * Assumes a sorted range list. + * + * Returns nothing. + */ +static void __merge_memory_ranges(struct crash_mem *mem_rngs) +{ + struct crash_mem_range *ranges; + int i, idx; + + if (!mem_rngs) + return; + + idx = 0; + ranges = &(mem_rngs->ranges[0]); + for (i = 1; i < mem_rngs->nr_ranges; i++) { + if (ranges[i].start <= (ranges[i-1].end + 1)) + ranges[idx].end = ranges[i].end; + else { + idx++; + if (i == idx) + continue; + + ranges[idx] = ranges[i]; + } + } + mem_rngs->nr_ranges = idx + 1; +} + +/* cmp_func_t callback to sort ranges with sort() */ +static int rngcmp(const void *_x, const void *_y) +{ + const struct crash_mem_range *x = _x, *y = _y; + + if (x->start > y->start) + return 1; + if (x->start < y->start) + return -1; + return 0; +} + +/** + * sort_memory_ranges - Sorts the given memory ranges list. + * @mem_rngs: Range list to sort. + * @merge: If true, merge the list after sorting. + * + * Returns nothing. + */ +void sort_memory_ranges(struct crash_mem *mem_rngs, bool merge) +{ + int i; + + if (!mem_rngs) + return; + + /* Sort the ranges in-place */ + sort(&(mem_rngs->ranges[0]), mem_rngs->nr_ranges, + sizeof(mem_rngs->ranges[0]), rngcmp, NULL); + + if (merge) + __merge_memory_ranges(mem_rngs); + + /* For debugging purpose */ + pr_debug("Memory ranges:\n"); + for (i = 0; i < mem_rngs->nr_ranges; i++) { + pr_debug("\t[%03d][%#016llx - %#016llx]\n", i, + mem_rngs->ranges[i].start, + mem_rngs->ranges[i].end); + } +} + +/** + * realloc_mem_ranges - reallocate mem_ranges with size incremented + * by MEM_RANGE_CHUNK_SZ. Frees up the old memory, + * if memory allocation fails. + * @mem_ranges: Memory ranges to reallocate. + * + * Returns pointer to reallocated memory on success, NULL otherwise. + */ +struct crash_mem *realloc_mem_ranges(struct crash_mem **mem_ranges) +{ + struct crash_mem *mem_rngs = *mem_ranges; + unsigned int nr_ranges; + size_t size; + + size = get_mem_rngs_size(mem_rngs); + nr_ranges = mem_rngs ? mem_rngs->nr_ranges : 0; + + size += MEM_RANGE_CHUNK_SZ; + mem_rngs = krealloc(*mem_ranges, size, GFP_KERNEL); + if (!mem_rngs) { + kfree(*mem_ranges); + *mem_ranges = NULL; + return NULL; + } + + mem_rngs->nr_ranges = nr_ranges; + mem_rngs->max_nr_ranges = get_max_nr_ranges(size); + *mem_ranges = mem_rngs; + + return mem_rngs; +} + +/** + * add_mem_range - Updates existing memory range, if there is an overlap. + * Else, adds a new memory range. + * @mem_ranges: Range list to add the memory range to. + * @base: Base address of the range to add. + * @size: Size of the memory range to add. + * + * (Re)allocates memory, if needed. + * + * Returns 0 on success, negative errno on error. + */ +int add_mem_range(struct crash_mem **mem_ranges, u64 base, u64 size) +{ + struct crash_mem *mem_rngs = *mem_ranges; + u64 mstart, mend, end; + unsigned int i; + + if (!size) + return 0; + + end = base + size - 1; + + if (!mem_rngs || !(mem_rngs->nr_ranges)) + return __add_mem_range(mem_ranges, base, size); + + for (i = 0; i < mem_rngs->nr_ranges; i++) { + mstart = mem_rngs->ranges[i].start; + mend = mem_rngs->ranges[i].end; + if (base < mend && end > mstart) { + if (base < mstart) + mem_rngs->ranges[i].start = base; + if (end > mend) + mem_rngs->ranges[i].end = end; + return 0; + } + } + + return __add_mem_range(mem_ranges, base, size); +} + +/** + * add_tce_mem_ranges - Adds tce-table range to the given memory ranges list. + * @mem_ranges: Range list to add the memory range(s) to. + * + * Returns 0 on success, negative errno on error. + */ +int add_tce_mem_ranges(struct crash_mem **mem_ranges) +{ + struct device_node *dn = NULL; + int ret = 0; + + for_each_node_by_type(dn, "pci") { + u64 base; + u32 size; + + ret = of_property_read_u64(dn, "linux,tce-base", &base); + ret |= of_property_read_u32(dn, "linux,tce-size", &size); + if (ret) { + /* + * It is ok to have pci nodes without tce. So, ignore + * property does not exist error. + */ + if (ret == -EINVAL) { + ret = 0; + continue; + } + break; + } + + ret = add_mem_range(mem_ranges, base, size); + if (ret) + break; + } + + of_node_put(dn); + return ret; +} + +/** + * add_initrd_mem_range - Adds initrd range to the given memory ranges list, + * if the initrd was retained. + * @mem_ranges: Range list to add the memory range to. + * + * Returns 0 on success, negative errno on error. + */ +int add_initrd_mem_range(struct crash_mem **mem_ranges) +{ + u64 base, end; + int ret; + + /* This range means something, only if initrd was retained */ + if (!strstr(saved_command_line, "retain_initrd")) + return 0; + + ret = of_property_read_u64(of_chosen, "linux,initrd-start", &base); + ret |= of_property_read_u64(of_chosen, "linux,initrd-end", &end); + if (!ret) + ret = add_mem_range(mem_ranges, base, end - base + 1); + + return ret; +} + +#ifdef CONFIG_PPC_64S_HASH_MMU +/** + * add_htab_mem_range - Adds htab range to the given memory ranges list, + * if it exists + * @mem_ranges: Range list to add the memory range to. + * + * Returns 0 on success, negative errno on error. + */ +int add_htab_mem_range(struct crash_mem **mem_ranges) +{ + if (!htab_address) + return 0; + + return add_mem_range(mem_ranges, __pa(htab_address), htab_size_bytes); +} +#endif + +/** + * add_kernel_mem_range - Adds kernel text region to the given + * memory ranges list. + * @mem_ranges: Range list to add the memory range to. + * + * Returns 0 on success, negative errno on error. + */ +int add_kernel_mem_range(struct crash_mem **mem_ranges) +{ + return add_mem_range(mem_ranges, 0, __pa(_end)); +} + +/** + * add_rtas_mem_range - Adds RTAS region to the given memory ranges list. + * @mem_ranges: Range list to add the memory range to. + * + * Returns 0 on success, negative errno on error. + */ +int add_rtas_mem_range(struct crash_mem **mem_ranges) +{ + struct device_node *dn; + u32 base, size; + int ret = 0; + + dn = of_find_node_by_path("/rtas"); + if (!dn) + return 0; + + ret = of_property_read_u32(dn, "linux,rtas-base", &base); + ret |= of_property_read_u32(dn, "rtas-size", &size); + if (!ret) + ret = add_mem_range(mem_ranges, base, size); + + of_node_put(dn); + return ret; +} + +/** + * add_opal_mem_range - Adds OPAL region to the given memory ranges list. + * @mem_ranges: Range list to add the memory range to. + * + * Returns 0 on success, negative errno on error. + */ +int add_opal_mem_range(struct crash_mem **mem_ranges) +{ + struct device_node *dn; + u64 base, size; + int ret; + + dn = of_find_node_by_path("/ibm,opal"); + if (!dn) + return 0; + + ret = of_property_read_u64(dn, "opal-base-address", &base); + ret |= of_property_read_u64(dn, "opal-runtime-size", &size); + if (!ret) + ret = add_mem_range(mem_ranges, base, size); + + of_node_put(dn); + return ret; +} + +/** + * add_reserved_mem_ranges - Adds "/reserved-ranges" regions exported by f/w + * to the given memory ranges list. + * @mem_ranges: Range list to add the memory ranges to. + * + * Returns 0 on success, negative errno on error. + */ +int add_reserved_mem_ranges(struct crash_mem **mem_ranges) +{ + int n_mem_addr_cells, n_mem_size_cells, i, len, cells, ret = 0; + const __be32 *prop; + + prop = of_get_property(of_root, "reserved-ranges", &len); + if (!prop) + return 0; + + n_mem_addr_cells = of_n_addr_cells(of_root); + n_mem_size_cells = of_n_size_cells(of_root); + cells = n_mem_addr_cells + n_mem_size_cells; + + /* Each reserved range is an (address,size) pair */ + for (i = 0; i < (len / (sizeof(u32) * cells)); i++) { + u64 base, size; + + base = of_read_number(prop + (i * cells), n_mem_addr_cells); + size = of_read_number(prop + (i * cells) + n_mem_addr_cells, + n_mem_size_cells); + + ret = add_mem_range(mem_ranges, base, size); + if (ret) + break; + } + + return ret; +} diff --git a/arch/powerpc/kexec/relocate_32.S b/arch/powerpc/kexec/relocate_32.S new file mode 100644 index 000000000..d9f0dd9b3 --- /dev/null +++ b/arch/powerpc/kexec/relocate_32.S @@ -0,0 +1,500 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * This file contains kexec low-level functions. + * + * Copyright (C) 2002-2003 Eric Biederman <ebiederm@xmission.com> + * GameCube/ppc32 port Copyright (C) 2004 Albert Herranz + * PPC44x port. Copyright (C) 2011, IBM Corporation + * Author: Suzuki Poulose <suzuki@in.ibm.com> + */ + +#include <asm/reg.h> +#include <asm/page.h> +#include <asm/mmu.h> +#include <asm/ppc_asm.h> +#include <asm/kexec.h> + + .text + + /* + * Must be relocatable PIC code callable as a C function. + */ + .globl relocate_new_kernel +relocate_new_kernel: + /* r3 = page_list */ + /* r4 = reboot_code_buffer */ + /* r5 = start_address */ + +#ifdef CONFIG_PPC_85xx + + mr r29, r3 + mr r30, r4 + mr r31, r5 + +#define ENTRY_MAPPING_KEXEC_SETUP +#include <kernel/85xx_entry_mapping.S> +#undef ENTRY_MAPPING_KEXEC_SETUP + + mr r3, r29 + mr r4, r30 + mr r5, r31 + + li r0, 0 +#elif defined(CONFIG_44x) + + /* Save our parameters */ + mr r29, r3 + mr r30, r4 + mr r31, r5 + +#ifdef CONFIG_PPC_47x + /* Check for 47x cores */ + mfspr r3,SPRN_PVR + srwi r3,r3,16 + cmplwi cr0,r3,PVR_476FPE@h + beq setup_map_47x + cmplwi cr0,r3,PVR_476@h + beq setup_map_47x + cmplwi cr0,r3,PVR_476_ISS@h + beq setup_map_47x +#endif /* CONFIG_PPC_47x */ + +/* + * Code for setting up 1:1 mapping for PPC440x for KEXEC + * + * We cannot switch off the MMU on PPC44x. + * So we: + * 1) Invalidate all the mappings except the one we are running from. + * 2) Create a tmp mapping for our code in the other address space(TS) and + * jump to it. Invalidate the entry we started in. + * 3) Create a 1:1 mapping for 0-2GiB in chunks of 256M in original TS. + * 4) Jump to the 1:1 mapping in original TS. + * 5) Invalidate the tmp mapping. + * + * - Based on the kexec support code for FSL BookE + * + */ + + /* + * Load the PID with kernel PID (0). + * Also load our MSR_IS and TID to MMUCR for TLB search. + */ + li r3, 0 + mtspr SPRN_PID, r3 + mfmsr r4 + andi. r4,r4,MSR_IS@l + beq wmmucr + oris r3,r3,PPC44x_MMUCR_STS@h +wmmucr: + mtspr SPRN_MMUCR,r3 + sync + + /* + * Invalidate all the TLB entries except the current entry + * where we are running from + */ + bcl 20,31,$+4 /* Find our address */ +0: mflr r5 /* Make it accessible */ + tlbsx r23,0,r5 /* Find entry we are in */ + li r4,0 /* Start at TLB entry 0 */ + li r3,0 /* Set PAGEID inval value */ +1: cmpw r23,r4 /* Is this our entry? */ + beq skip /* If so, skip the inval */ + tlbwe r3,r4,PPC44x_TLB_PAGEID /* If not, inval the entry */ +skip: + addi r4,r4,1 /* Increment */ + cmpwi r4,64 /* Are we done? */ + bne 1b /* If not, repeat */ + isync + + /* Create a temp mapping and jump to it */ + andi. r6, r23, 1 /* Find the index to use */ + addi r24, r6, 1 /* r24 will contain 1 or 2 */ + + mfmsr r9 /* get the MSR */ + rlwinm r5, r9, 27, 31, 31 /* Extract the MSR[IS] */ + xori r7, r5, 1 /* Use the other address space */ + + /* Read the current mapping entries */ + tlbre r3, r23, PPC44x_TLB_PAGEID + tlbre r4, r23, PPC44x_TLB_XLAT + tlbre r5, r23, PPC44x_TLB_ATTRIB + + /* Save our current XLAT entry */ + mr r25, r4 + + /* Extract the TLB PageSize */ + li r10, 1 /* r10 will hold PageSize */ + rlwinm r11, r3, 0, 24, 27 /* bits 24-27 */ + + /* XXX: As of now we use 256M, 4K pages */ + cmpwi r11, PPC44x_TLB_256M + bne tlb_4k + rotlwi r10, r10, 28 /* r10 = 256M */ + b write_out +tlb_4k: + cmpwi r11, PPC44x_TLB_4K + bne default + rotlwi r10, r10, 12 /* r10 = 4K */ + b write_out +default: + rotlwi r10, r10, 10 /* r10 = 1K */ + +write_out: + /* + * Write out the tmp 1:1 mapping for this code in other address space + * Fixup EPN = RPN , TS=other address space + */ + insrwi r3, r7, 1, 23 /* Bit 23 is TS for PAGEID field */ + + /* Write out the tmp mapping entries */ + tlbwe r3, r24, PPC44x_TLB_PAGEID + tlbwe r4, r24, PPC44x_TLB_XLAT + tlbwe r5, r24, PPC44x_TLB_ATTRIB + + subi r11, r10, 1 /* PageOffset Mask = PageSize - 1 */ + not r10, r11 /* Mask for PageNum */ + + /* Switch to other address space in MSR */ + insrwi r9, r7, 1, 26 /* Set MSR[IS] = r7 */ + + bcl 20,31,$+4 +1: mflr r8 + addi r8, r8, (2f-1b) /* Find the target offset */ + + /* Jump to the tmp mapping */ + mtspr SPRN_SRR0, r8 + mtspr SPRN_SRR1, r9 + rfi + +2: + /* Invalidate the entry we were executing from */ + li r3, 0 + tlbwe r3, r23, PPC44x_TLB_PAGEID + + /* attribute fields. rwx for SUPERVISOR mode */ + li r5, 0 + ori r5, r5, (PPC44x_TLB_SW | PPC44x_TLB_SR | PPC44x_TLB_SX | PPC44x_TLB_G) + + /* Create 1:1 mapping in 256M pages */ + xori r7, r7, 1 /* Revert back to Original TS */ + + li r8, 0 /* PageNumber */ + li r6, 3 /* TLB Index, start at 3 */ + +next_tlb: + rotlwi r3, r8, 28 /* Create EPN (bits 0-3) */ + mr r4, r3 /* RPN = EPN */ + ori r3, r3, (PPC44x_TLB_VALID | PPC44x_TLB_256M) /* SIZE = 256M, Valid */ + insrwi r3, r7, 1, 23 /* Set TS from r7 */ + + tlbwe r3, r6, PPC44x_TLB_PAGEID /* PageID field : EPN, V, SIZE */ + tlbwe r4, r6, PPC44x_TLB_XLAT /* Address translation : RPN */ + tlbwe r5, r6, PPC44x_TLB_ATTRIB /* Attributes */ + + addi r8, r8, 1 /* Increment PN */ + addi r6, r6, 1 /* Increment TLB Index */ + cmpwi r8, 8 /* Are we done ? */ + bne next_tlb + isync + + /* Jump to the new mapping 1:1 */ + li r9,0 + insrwi r9, r7, 1, 26 /* Set MSR[IS] = r7 */ + + bcl 20,31,$+4 +1: mflr r8 + and r8, r8, r11 /* Get our offset within page */ + addi r8, r8, (2f-1b) + + and r5, r25, r10 /* Get our target PageNum */ + or r8, r8, r5 /* Target jump address */ + + mtspr SPRN_SRR0, r8 + mtspr SPRN_SRR1, r9 + rfi +2: + /* Invalidate the tmp entry we used */ + li r3, 0 + tlbwe r3, r24, PPC44x_TLB_PAGEID + sync + b ppc44x_map_done + +#ifdef CONFIG_PPC_47x + + /* 1:1 mapping for 47x */ + +setup_map_47x: + + /* + * Load the kernel pid (0) to PID and also to MMUCR[TID]. + * Also set the MSR IS->MMUCR STS + */ + li r3, 0 + mtspr SPRN_PID, r3 /* Set PID */ + mfmsr r4 /* Get MSR */ + andi. r4, r4, MSR_IS@l /* TS=1? */ + beq 1f /* If not, leave STS=0 */ + oris r3, r3, PPC47x_MMUCR_STS@h /* Set STS=1 */ +1: mtspr SPRN_MMUCR, r3 /* Put MMUCR */ + sync + + /* Find the entry we are running from */ + bcl 20,31,$+4 +2: mflr r23 + tlbsx r23, 0, r23 + tlbre r24, r23, 0 /* TLB Word 0 */ + tlbre r25, r23, 1 /* TLB Word 1 */ + tlbre r26, r23, 2 /* TLB Word 2 */ + + + /* + * Invalidates all the tlb entries by writing to 256 RPNs(r4) + * of 4k page size in all 4 ways (0-3 in r3). + * This would invalidate the entire UTLB including the one we are + * running from. However the shadow TLB entries would help us + * to continue the execution, until we flush them (rfi/isync). + */ + addis r3, 0, 0x8000 /* specify the way */ + addi r4, 0, 0 /* TLB Word0 = (EPN=0, VALID = 0) */ + addi r5, 0, 0 + b clear_utlb_entry + + /* Align the loop to speed things up. from head_44x.S */ + .align 6 + +clear_utlb_entry: + + tlbwe r4, r3, 0 + tlbwe r5, r3, 1 + tlbwe r5, r3, 2 + addis r3, r3, 0x2000 /* Increment the way */ + cmpwi r3, 0 + bne clear_utlb_entry + addis r3, 0, 0x8000 + addis r4, r4, 0x100 /* Increment the EPN */ + cmpwi r4, 0 + bne clear_utlb_entry + + /* Create the entries in the other address space */ + mfmsr r5 + rlwinm r7, r5, 27, 31, 31 /* Get the TS (Bit 26) from MSR */ + xori r7, r7, 1 /* r7 = !TS */ + + insrwi r24, r7, 1, 21 /* Change the TS in the saved TLB word 0 */ + + /* + * write out the TLB entries for the tmp mapping + * Use way '0' so that we could easily invalidate it later. + */ + lis r3, 0x8000 /* Way '0' */ + + tlbwe r24, r3, 0 + tlbwe r25, r3, 1 + tlbwe r26, r3, 2 + + /* Update the msr to the new TS */ + insrwi r5, r7, 1, 26 + + bcl 20,31,$+4 +1: mflr r6 + addi r6, r6, (2f-1b) + + mtspr SPRN_SRR0, r6 + mtspr SPRN_SRR1, r5 + rfi + + /* + * Now we are in the tmp address space. + * Create a 1:1 mapping for 0-2GiB in the original TS. + */ +2: + li r3, 0 + li r4, 0 /* TLB Word 0 */ + li r5, 0 /* TLB Word 1 */ + li r6, 0 + ori r6, r6, PPC47x_TLB2_S_RWX /* TLB word 2 */ + + li r8, 0 /* PageIndex */ + + xori r7, r7, 1 /* revert back to original TS */ + +write_utlb: + rotlwi r5, r8, 28 /* RPN = PageIndex * 256M */ + /* ERPN = 0 as we don't use memory above 2G */ + + mr r4, r5 /* EPN = RPN */ + ori r4, r4, (PPC47x_TLB0_VALID | PPC47x_TLB0_256M) + insrwi r4, r7, 1, 21 /* Insert the TS to Word 0 */ + + tlbwe r4, r3, 0 /* Write out the entries */ + tlbwe r5, r3, 1 + tlbwe r6, r3, 2 + addi r8, r8, 1 + cmpwi r8, 8 /* Have we completed ? */ + bne write_utlb + + /* make sure we complete the TLB write up */ + isync + + /* + * Prepare to jump to the 1:1 mapping. + * 1) Extract page size of the tmp mapping + * DSIZ = TLB_Word0[22:27] + * 2) Calculate the physical address of the address + * to jump to. + */ + rlwinm r10, r24, 0, 22, 27 + + cmpwi r10, PPC47x_TLB0_4K + bne 0f + li r10, 0x1000 /* r10 = 4k */ + bl 1f + +0: + /* Defaults to 256M */ + lis r10, 0x1000 + + bcl 20,31,$+4 +1: mflr r4 + addi r4, r4, (2f-1b) /* virtual address of 2f */ + + subi r11, r10, 1 /* offsetmask = Pagesize - 1 */ + not r10, r11 /* Pagemask = ~(offsetmask) */ + + and r5, r25, r10 /* Physical page */ + and r6, r4, r11 /* offset within the current page */ + + or r5, r5, r6 /* Physical address for 2f */ + + /* Switch the TS in MSR to the original one */ + mfmsr r8 + insrwi r8, r7, 1, 26 + + mtspr SPRN_SRR1, r8 + mtspr SPRN_SRR0, r5 + rfi + +2: + /* Invalidate the tmp mapping */ + lis r3, 0x8000 /* Way '0' */ + + clrrwi r24, r24, 12 /* Clear the valid bit */ + tlbwe r24, r3, 0 + tlbwe r25, r3, 1 + tlbwe r26, r3, 2 + + /* Make sure we complete the TLB write and flush the shadow TLB */ + isync + +#endif + +ppc44x_map_done: + + + /* Restore the parameters */ + mr r3, r29 + mr r4, r30 + mr r5, r31 + + li r0, 0 +#else + li r0, 0 + + /* + * Set Machine Status Register to a known status, + * switch the MMU off and jump to 1: in a single step. + */ + + mr r8, r0 + ori r8, r8, MSR_RI|MSR_ME + mtspr SPRN_SRR1, r8 + addi r8, r4, 1f - relocate_new_kernel + mtspr SPRN_SRR0, r8 + sync + rfi + +1: +#endif + /* from this point address translation is turned off */ + /* and interrupts are disabled */ + + /* set a new stack at the bottom of our page... */ + /* (not really needed now) */ + addi r1, r4, KEXEC_CONTROL_PAGE_SIZE - 8 /* for LR Save+Back Chain */ + stw r0, 0(r1) + + /* Do the copies */ + li r6, 0 /* checksum */ + mr r0, r3 + b 1f + +0: /* top, read another word for the indirection page */ + lwzu r0, 4(r3) + +1: + /* is it a destination page? (r8) */ + rlwinm. r7, r0, 0, 31, 31 /* IND_DESTINATION (1<<0) */ + beq 2f + + rlwinm r8, r0, 0, 0, 19 /* clear kexec flags, page align */ + b 0b + +2: /* is it an indirection page? (r3) */ + rlwinm. r7, r0, 0, 30, 30 /* IND_INDIRECTION (1<<1) */ + beq 2f + + rlwinm r3, r0, 0, 0, 19 /* clear kexec flags, page align */ + subi r3, r3, 4 + b 0b + +2: /* are we done? */ + rlwinm. r7, r0, 0, 29, 29 /* IND_DONE (1<<2) */ + beq 2f + b 3f + +2: /* is it a source page? (r9) */ + rlwinm. r7, r0, 0, 28, 28 /* IND_SOURCE (1<<3) */ + beq 0b + + rlwinm r9, r0, 0, 0, 19 /* clear kexec flags, page align */ + + li r7, PAGE_SIZE / 4 + mtctr r7 + subi r9, r9, 4 + subi r8, r8, 4 +9: + lwzu r0, 4(r9) /* do the copy */ + xor r6, r6, r0 + stwu r0, 4(r8) + dcbst 0, r8 + sync + icbi 0, r8 + bdnz 9b + + addi r9, r9, 4 + addi r8, r8, 4 + b 0b + +3: + + /* To be certain of avoiding problems with self-modifying code + * execute a serializing instruction here. + */ + isync + sync + + mfspr r3, SPRN_PIR /* current core we are running on */ + mr r4, r5 /* load physical address of chunk called */ + + /* jump to the entry point, usually the setup routine */ + mtlr r5 + blrl + +1: b 1b + +relocate_new_kernel_end: + + .globl relocate_new_kernel_size +relocate_new_kernel_size: + .long relocate_new_kernel_end - relocate_new_kernel |