arch/ppc64/kernel/machine_kexec.c

   1 /*
   2  * machine_kexec.c - handle transition of Linux booting another kernel
   3  *
   4  * Copyright (C) 2004-2005, IBM Corp.
   5  *
   6  * Created by: Milton D Miller II
   7  *
   8  * This source code is licensed under the GNU General Public License,
   9  * Version 2.  See the file COPYING for more details.
  10  */
  11
  12
  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>
  18
  19 #include <asm/page.h>
  20 #include <asm/current.h>
  21 #include <asm/machdep.h>
  22 #include <asm/cacheflush.h>
  23 #include <asm/paca.h>
  24 #include <asm/mmu.h>
  25 #include <asm/sections.h>       /* _end */
  26 #include <asm/prom.h>
  27
  28 #define HASH_GROUP_SIZE 0x80    /* size of each hash group, asm/mmu.h */
  29
  30 /* Have this around till we move it into crash specific file */
  31 note_buf_t crash_notes[NR_CPUS];
  32
  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
  36  */
  37 void machine_crash_shutdown(struct pt_regs *regs)
  38 {
  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 */
  42 }
  43
  44 int machine_kexec_prepare(struct kimage *image)
  45 {
  46         int i;
  47         unsigned long begin, end;       /* limits of segment */
  48         unsigned long low, high;        /* limits of blocked memory range */
  49         struct device_node *node;
  50         unsigned long *basep;
  51         unsigned int *sizep;
  52
  53         if (!ppc_md.hpte_clear_all)
  54                 return -ENOENT;
  55
  56         /*
  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.
  60          */
  61         for(i = 0; i < image->nr_segments; i++)
  62                 if (image->segment[i].mem < __pa(_end))
  63                         return -ETXTBSY;
  64
  65         /*
  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.
  69          *
  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).
  74          */
  75         if (htab_address) {
  76                 low = __pa(htab_address);
  77                 high = low + (htab_hash_mask + 1) * HASH_GROUP_SIZE;
  78
  79                 for(i = 0; i < image->nr_segments; i++) {
  80                         begin = image->segment[i].mem;
  81                         end = begin + image->segment[i].memsz;
  82
  83                         if ((begin < high) && (end > low))
  84                                 return -ETXTBSY;
  85                 }
  86         }
  87
  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",
  92                                                         NULL);
  93                 sizep = (unsigned int *)get_property(node, "linux,tce-size",
  94                                                         NULL);
  95                 if (basep == NULL || sizep == NULL)
  96                         continue;
  97
  98                 low = *basep;
  99                 high = low + (*sizep);
 100
 101                 for(i = 0; i < image->nr_segments; i++) {
 102                         begin = image->segment[i].mem;
 103                         end = begin + image->segment[i].memsz;
 104
 105                         if ((begin < high) && (end > low))
 106                                 return -ETXTBSY;
 107                 }
 108         }
 109
 110         return 0;
 111 }
 112
 113 void machine_kexec_cleanup(struct kimage *image)
 114 {
 115         /* we do nothing in prepare that needs to be undone */
 116 }
 117
 118 #define IND_FLAGS (IND_DESTINATION | IND_INDIRECTION | IND_DONE | IND_SOURCE)
 119
 120 static void copy_segments(unsigned long ind)
 121 {
 122         unsigned long entry;
 123         unsigned long *ptr;
 124         void *dest;
 125         void *addr;
 126
 127         /*
 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.
 132          */
 133         ptr = NULL;
 134         dest = NULL;
 135
 136         for (entry = ind; !(entry & IND_DONE); entry = *ptr++) {
 137                 addr = __va(entry & PAGE_MASK);
 138
 139                 switch (entry & IND_FLAGS) {
 140                 case IND_DESTINATION:
 141                         dest = addr;
 142                         break;
 143                 case IND_INDIRECTION:
 144                         ptr = addr;
 145                         break;
 146                 case IND_SOURCE:
 147                         copy_page(dest, addr);
 148                         dest += PAGE_SIZE;
 149                 }
 150         }
 151 }
 152
 153 void kexec_copy_flush(struct kimage *image)
 154 {
 155         long i, nr_segments = image->nr_segments;
 156         struct  kexec_segment ranges[KEXEC_SEGMENT_MAX];
 157
 158         /* save the ranges on the stack to efficiently flush the icache */
 159         memcpy(ranges, image->segment, sizeof(ranges));
 160
 161         /*
 162          * After this call we may not use anything allocated in dynamic
 163          * memory, including *image.
 164          *
 165          * Only globals and the stack are allowed.
 166          */
 167         copy_segments(image->head);
 168
 169         /*
 170          * we need to clear the icache for all dest pages sometime,
 171          * including ones that were in place on the original copy
 172          */
 173         for (i = 0; i < nr_segments; i++)
 174                 flush_icache_range(ranges[i].mem + KERNELBASE,
 175                                 ranges[i].mem + KERNELBASE +
 176                                 ranges[i].memsz);
 177 }
 178
 179 #ifdef CONFIG_SMP
 180
 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.
 184  */
 185 void kexec_smp_down(void *arg)
 186 {
 187         if (ppc_md.cpu_irq_down)
 188                 ppc_md.cpu_irq_down();
 189
 190         local_irq_disable();
 191         kexec_smp_wait();
 192         /* NOTREACHED */
 193 }
 194
 195 static void kexec_prepare_cpus(void)
 196 {
 197         int my_cpu, i, notified=-1;
 198
 199         smp_call_function(kexec_smp_down, NULL, 0, /* wait */0);
 200         my_cpu = get_cpu();
 201
 202         /* check the others cpus are now down (via paca hw cpu id == -1) */
 203         for (i=0; i < NR_CPUS; i++) {
 204                 if (i == my_cpu)
 205                         continue;
 206
 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);
 212                                 break;
 213                         }
 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.
 218                                  */
 219                                 printk("kexec: cpu %d hw_cpu_id %d is not"
 220                                                 " online, ignoring\n",
 221                                                 i, paca[i].hw_cpu_id);
 222                                 break;
 223                         }
 224                         if (i != notified) {
 225                                 printk( "kexec: waiting for cpu %d (physical"
 226                                                 " %d) to go down\n",
 227                                                 i, paca[i].hw_cpu_id);
 228                                 notified = i;
 229                         }
 230                 }
 231         }
 232
 233         /* after we tell the others to go down */
 234         if (ppc_md.cpu_irq_down)
 235                 ppc_md.cpu_irq_down();
 236
 237         put_cpu();
 238
 239         local_irq_disable();
 240 }
 241
 242 #else /* ! SMP */
 243
 244 static void kexec_prepare_cpus(void)
 245 {
 246         /*
 247          * move the secondarys to us so that we can copy
 248          * the new kernel 0-0x100 safely
 249          *
 250          * do this if kexec in setup.c ?
 251          */
 252         smp_relase_cpus();
 253         if (ppc_md.cpu_irq_down)
 254                 ppc_md.cpu_irq_down();
 255         local_irq_disable();
 256 }
 257
 258 #endif /* SMP */
 259
 260 /*
 261  * kexec thread structure and stack.
 262  *
 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.
 268  *
 269  * We could use a smaller stack if we don't care about anything using
 270  * current, but that audit has not been performed.
 271  */
 272 union thread_union kexec_stack
 273         __attribute__((__section__(".data.init_task"))) = { };
 274
 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, void (*clear_all)(void)) ATTRIB_NORET;
 278
 279 /* too late to fail here */
 280 void machine_kexec(struct kimage *image)
 281 {
 282
 283         /* prepare control code if any */
 284
 285         /* shutdown other cpus into our wait loop and quiesce interrupts */
 286         kexec_prepare_cpus();
 287
 288         /* switch to a staticly allocated stack.  Based on irq stack code.
 289          * XXX: the task struct will likely be invalid once we do the copy!
 290          */
 291         kexec_stack.thread_info.task = current_thread_info()->task;
 292         kexec_stack.thread_info.flags = 0;
 293
 294         /* Some things are best done in assembly.  Finding globals with
 295          * a toc is easier in C, so pass in what we can.
 296          */
 297         kexec_sequence(&kexec_stack, image->start, image,
 298                         page_address(image->control_code_page),
 299                         ppc_md.hpte_clear_all);
 300         /* NOTREACHED */
 301 }