Release 4.14 arch/powerpc/kernel/machine_kexec_64.c

/*
 * PPC64 code to handle Linux booting another kernel.
 *
 * Copyright (C) 2004-2005, IBM Corp.
 *
 * Created by: Milton D Miller II
 *
 * This source code is licensed under the GNU General Public License,
 * Version 2.  See the file COPYING for more details.
 */


#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 <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/prom.h>
#include <asm/smp.h>
#include <asm/hw_breakpoint.h>
#include <asm/asm-prototypes.h>



int default_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))
				return -ETXTBSY;
		}
	}

	return 0;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
R Sharada
191
96.46%
1
20.00%
Anton Blanchard
2
1.01%
1
20.00%
Stephen Rothwell
2
1.01%
1
20.00%
Jeremy Kerr
2
1.01%
1
20.00%
Michael Ellerman
1
0.51%
1
20.00%
Total
198
100.00%
5
100.00%



static 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;
		}
	}
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
R Sharada
104
100.00%
1
100.00%
Total
104
100.00%
1
100.00%



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));
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
R Sharada
87
86.14%
1
50.00%
Michael Ellerman
14
13.86%
1
50.00%
Total
101
100.00%
2
100.00%

#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);

	kexec_smp_wait();
	/* NOTREACHED */
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Michael Neuling
28
44.44%
1
14.29%
R Sharada
21
33.33%
1
14.29%
Michael Ellerman
5
7.94%
2
28.57%
Paul Mackerras
3
4.76%
1
14.29%
K.Prasad
3
4.76%
1
14.29%
Phileas Fogg
3
4.76%
1
14.29%
Total
63
100.00%
7
100.00%



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[].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[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[i].hw_cpu_id, wait_state);
				notified = i;
			}
		}
	}
	mb();
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
R Sharada
64
71.11%
1
16.67%
Michael Neuling
12
13.33%
1
16.67%
Matt Evans
8
8.89%
2
33.33%
Anton Blanchard
3
3.33%
1
16.67%
K.Prasad
3
3.33%
1
16.67%
Total
90
100.00%
6
100.00%

/*
 * 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(cpu_up(cpu));
		}
	}
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Matt Evans
42
93.33%
1
50.00%
Srivatsa S. Bhat
3
6.67%
1
50.00%
Total
45
100.00%
2
100.00%



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;

	/* after we tell the others to go down */
	if (ppc_md.kexec_cpu_down)
		ppc_md.kexec_cpu_down(0, 0);

	/*
         * Before removing MMU mappings make sure all CPUs have entered real
         * mode:
         */
	kexec_prepare_cpus_wait(KEXEC_STATE_REAL_MODE);

	put_cpu();
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Michael Neuling
46
63.01%
1
14.29%
R Sharada
13
17.81%
1
14.29%
Matt Evans
4
5.48%
2
28.57%
Michael Ellerman
4
5.48%
1
14.29%
Paul Mackerras
3
4.11%
1
14.29%
Phileas Fogg
3
4.11%
1
14.29%
Total
73
100.00%
7
100.00%

#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();
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
R Sharada
21
63.64%
1
20.00%
Michael Ellerman
4
12.12%
1
20.00%
Phileas Fogg
3
9.09%
1
20.00%
Paul Mackerras
3
9.09%
1
20.00%
Olof Johansson
2
6.06%
1
20.00%
Total
33
100.00%
5
100.00%

#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.
 */

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!
         */
	kexec_stack.thread_info.task = current_thread_info()->task;
	kexec_stack.thread_info.flags = 0;
	kexec_stack.thread_info.preempt_count = HARDIRQ_OFFSET;
	kexec_stack.thread_info.cpu = current_thread_info()->cpu;

	/* We need a static PACA, too; copy this CPU's PACA over and switch to
         * it.  Also poison per_cpu_offset to catch anyone using non-static
         * data.
         */
	memcpy(&kexec_paca, get_paca(), sizeof(struct paca_struct));
	kexec_paca.data_offset = 0xedeaddeadeeeeeeeUL;
	paca = (struct paca_struct *)RELOC_HIDE(&kexec_paca, 0) -
		kexec_paca.paca_index;
	setup_paca(&kexec_paca);

	/* XXX: If anyone does 'dynamic lppacas' this will also need to be
         * switched to a static version!
         */
	/*
         * 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
	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 */
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Matt Evans
52
30.41%
2
20.00%
Benjamin Herrenschmidt
49
28.65%
2
20.00%
R Sharada
41
23.98%
1
10.00%
Anton Blanchard
20
11.70%
1
10.00%
Michael Ellerman
5
2.92%
2
20.00%
Hari Bathini
3
1.75%
1
10.00%
Thiago Jung Bauermann
1
0.58%
1
10.00%
Total
171
100.00%
10
100.00%

#ifdef CONFIG_PPC_STD_MMU_64
/* 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 propertys 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;
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Michael Ellerman
54
47.37%
3
33.33%
Milton D. Miller II
27
23.68%
1
11.11%
Dale Farnsworth
15
13.16%
2
22.22%
Anton Blanchard
10
8.77%
1
11.11%
Suraj Jitindar Singh
5
4.39%
1
11.11%
Nathan Fontenot
3
2.63%
1
11.11%
Total
114
100.00%
9
100.00%


late_initcall(export_htab_values);
#endif /* CONFIG_PPC_STD_MMU_64 */
Overall Contributors
Person
Tokens
Prop
Commits
CommitProp
R Sharada
626
52.34%
1
2.44%
Michael Ellerman
151
12.63%
8
19.51%
Matt Evans
118
9.87%
4
9.76%
Michael Neuling
92
7.69%
1
2.44%
Benjamin Herrenschmidt
55
4.60%
2
4.88%
Anton Blanchard
44
3.68%
4
9.76%
Milton D. Miller II
27
2.26%
1
2.44%
Dale Farnsworth
17
1.42%
2
4.88%
Paul Mackerras
12
1.00%
2
4.88%
Phileas Fogg
9
0.75%
1
2.44%
K.Prasad
9
0.75%
1
2.44%
Suraj Jitindar Singh
5
0.42%
1
2.44%
Joe Perches
5
0.42%
2
4.88%
Aneesh Kumar K.V
4
0.33%
1
2.44%
Hari Bathini
3
0.25%
1
2.44%
Srivatsa S. Bhat
3
0.25%
1
2.44%
Nathan Fontenot
3
0.25%
1
2.44%
Daniel Axtens
3
0.25%
1
2.44%
Jeremy Kerr
2
0.17%
1
2.44%
Stephen Rothwell
2
0.17%
1
2.44%
Tiejun Chen
2
0.17%
1
2.44%
Olof Johansson
2
0.17%
1
2.44%
Thiago Jung Bauermann
1
0.08%
1
2.44%
Geert Uytterhoeven
1
0.08%
1
2.44%
Total
1196
100.00%
41
100.00%
Directory: arch/powerpc/kernel

Information contained on this website is for historical information purposes only and does not indicate or represent copyright ownership.