2 * machine_kexec.c - handle transition of Linux booting another kernel
4 * Copyright (C) 2004-2005, IBM Corp.
6 * Created by: Milton D Miller II
8 * This source code is licensed under the GNU General Public License,
9 * Version 2. See the file COPYING for more details.
13 #include <linux/cpumask.h>
14 #include <linux/kexec.h>
15 #include <linux/smp.h>
16 #include <linux/thread_info.h>
17 #include <linux/errno.h>
20 #include <asm/current.h>
21 #include <asm/machdep.h>
22 #include <asm/cacheflush.h>
25 #include <asm/sections.h> /* _end */
28 #define HASH_GROUP_SIZE 0x80 /* size of each hash group, asm/mmu.h */
30 /* Have this around till we move it into crash specific file */
31 note_buf_t crash_notes[NR_CPUS];
33 /* Dummy for now. Not sure if we need to have a crash shutdown in here
34 * and if what it will achieve. Letting it be now to compile the code
35 * in generic kexec environment
37 void machine_crash_shutdown(struct pt_regs *regs)
39 /* do nothing right now */
40 /* smp_relase_cpus() if we want smp on panic kernel */
41 /* cpu_irq_down to isolate us until we are ready */
44 int machine_kexec_prepare(struct kimage *image)
47 unsigned long begin, end; /* limits of segment */
48 unsigned long low, high; /* limits of blocked memory range */
49 struct device_node *node;
53 if (!ppc_md.hpte_clear_all)
57 * Since we use the kernel fault handlers and paging code to
58 * handle the virtual mode, we must make sure no destination
59 * overlaps kernel static data or bss.
61 for (i = 0; i < image->nr_segments; i++)
62 if (image->segment[i].mem < __pa(_end))
66 * For non-LPAR, we absolutely can not overwrite the mmu hash
67 * table, since we are still using the bolted entries in it to
68 * do the copy. Check that here.
70 * It is safe if the end is below the start of the blocked
71 * region (end <= low), or if the beginning is after the
72 * end of the blocked region (begin >= high). Use the
73 * boolean identity !(a || b) === (!a && !b).
76 low = __pa(htab_address);
77 high = low + (htab_hash_mask + 1) * HASH_GROUP_SIZE;
79 for (i = 0; i < image->nr_segments; i++) {
80 begin = image->segment[i].mem;
81 end = begin + image->segment[i].memsz;
83 if ((begin < high) && (end > low))
88 /* We also should not overwrite the tce tables */
89 for (node = of_find_node_by_type(NULL, "pci"); node != NULL;
90 node = of_find_node_by_type(node, "pci")) {
91 basep = (unsigned long *)get_property(node, "linux,tce-base",
93 sizep = (unsigned int *)get_property(node, "linux,tce-size",
95 if (basep == NULL || sizep == NULL)
99 high = low + (*sizep);
101 for (i = 0; i < image->nr_segments; i++) {
102 begin = image->segment[i].mem;
103 end = begin + image->segment[i].memsz;
105 if ((begin < high) && (end > low))
113 void machine_kexec_cleanup(struct kimage *image)
115 /* we do nothing in prepare that needs to be undone */
118 #define IND_FLAGS (IND_DESTINATION | IND_INDIRECTION | IND_DONE | IND_SOURCE)
120 static void copy_segments(unsigned long ind)
128 * We rely on kexec_load to create a lists that properly
129 * initializes these pointers before they are used.
130 * We will still crash if the list is wrong, but at least
131 * the compiler will be quiet.
136 for (entry = ind; !(entry & IND_DONE); entry = *ptr++) {
137 addr = __va(entry & PAGE_MASK);
139 switch (entry & IND_FLAGS) {
140 case IND_DESTINATION:
143 case IND_INDIRECTION:
147 copy_page(dest, addr);
153 void kexec_copy_flush(struct kimage *image)
155 long i, nr_segments = image->nr_segments;
156 struct kexec_segment ranges[KEXEC_SEGMENT_MAX];
158 /* save the ranges on the stack to efficiently flush the icache */
159 memcpy(ranges, image->segment, sizeof(ranges));
162 * After this call we may not use anything allocated in dynamic
163 * memory, including *image.
165 * Only globals and the stack are allowed.
167 copy_segments(image->head);
170 * we need to clear the icache for all dest pages sometime,
171 * including ones that were in place on the original copy
173 for (i = 0; i < nr_segments; i++)
174 flush_icache_range(ranges[i].mem + KERNELBASE,
175 ranges[i].mem + KERNELBASE +
181 /* FIXME: we should schedule this function to be called on all cpus based
182 * on calling the interrupts, but we would like to call it off irq level
183 * so that the interrupt controller is clean.
185 void kexec_smp_down(void *arg)
187 if (ppc_md.cpu_irq_down)
188 ppc_md.cpu_irq_down();
195 static void kexec_prepare_cpus(void)
197 int my_cpu, i, notified=-1;
199 smp_call_function(kexec_smp_down, NULL, 0, /* wait */0);
202 /* check the others cpus are now down (via paca hw cpu id == -1) */
203 for (i=0; i < NR_CPUS; i++) {
207 while (paca[i].hw_cpu_id != -1) {
208 if (!cpu_possible(i)) {
209 printk("kexec: cpu %d hw_cpu_id %d is not"
210 " possible, ignoring\n",
211 i, paca[i].hw_cpu_id);
214 if (!cpu_online(i)) {
215 /* Fixme: this can be spinning in
216 * pSeries_secondary_wait with a paca
217 * waiting for it to go online.
219 printk("kexec: cpu %d hw_cpu_id %d is not"
220 " online, ignoring\n",
221 i, paca[i].hw_cpu_id);
225 printk( "kexec: waiting for cpu %d (physical"
227 i, paca[i].hw_cpu_id);
233 /* after we tell the others to go down */
234 if (ppc_md.cpu_irq_down)
235 ppc_md.cpu_irq_down();
244 static void kexec_prepare_cpus(void)
247 * move the secondarys to us so that we can copy
248 * the new kernel 0-0x100 safely
250 * do this if kexec in setup.c ?
253 if (ppc_md.cpu_irq_down)
254 ppc_md.cpu_irq_down();
261 * kexec thread structure and stack.
263 * We need to make sure that this is 16384-byte aligned due to the
264 * way process stacks are handled. It also must be statically allocated
265 * or allocated as part of the kimage, because everything else may be
266 * overwritten when we copy the kexec image. We piggyback on the
267 * "init_task" linker section here to statically allocate a stack.
269 * We could use a smaller stack if we don't care about anything using
270 * current, but that audit has not been performed.
272 union thread_union kexec_stack
273 __attribute__((__section__(".data.init_task"))) = { };
275 /* Our assembly helper, in kexec_stub.S */
276 extern NORET_TYPE void kexec_sequence(void *newstack, unsigned long start,
277 void *image, void *control,
278 void (*clear_all)(void)) ATTRIB_NORET;
280 /* too late to fail here */
281 void machine_kexec(struct kimage *image)
284 /* prepare control code if any */
286 /* shutdown other cpus into our wait loop and quiesce interrupts */
287 kexec_prepare_cpus();
289 /* switch to a staticly allocated stack. Based on irq stack code.
290 * XXX: the task struct will likely be invalid once we do the copy!
292 kexec_stack.thread_info.task = current_thread_info()->task;
293 kexec_stack.thread_info.flags = 0;
295 /* Some things are best done in assembly. Finding globals with
296 * a toc is easier in C, so pass in what we can.
298 kexec_sequence(&kexec_stack, image->start, image,
299 page_address(image->control_code_page),
300 ppc_md.hpte_clear_all);