#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/btf.h>
#include <linux/capability.h>
#include <linux/mm.h>
#include <linux/file.h>
#include <crypto/hash.h>
#include "kexec_internal.h"
-DEFINE_MUTEX(kexec_mutex);
-
-/* Per cpu memory for storing cpu states in case of system crash. */
-note_buf_t __percpu *crash_notes;
+atomic_t __kexec_lock = ATOMIC_INIT(0);
/* Flag to indicate we are going to kexec a new kernel */
bool kexec_in_progress = false;
-
-/* Location of the reserved area for the crash kernel */
-struct resource crashk_res = {
- .name = "Crash kernel",
- .start = 0,
- .end = 0,
- .flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM,
- .desc = IORES_DESC_CRASH_KERNEL
-};
-struct resource crashk_low_res = {
- .name = "Crash kernel",
- .start = 0,
- .end = 0,
- .flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM,
- .desc = IORES_DESC_CRASH_KERNEL
-};
-
-int kexec_should_crash(struct task_struct *p)
-{
- /*
- * If crash_kexec_post_notifiers is enabled, don't run
- * crash_kexec() here yet, which must be run after panic
- * notifiers in panic().
- */
- if (crash_kexec_post_notifiers)
- return 0;
- /*
- * There are 4 panic() calls in make_task_dead() path, each of which
- * corresponds to each of these 4 conditions.
- */
- if (in_interrupt() || !p->pid || is_global_init(p) || panic_on_oops)
- return 1;
- return 0;
-}
-
-int kexec_crash_loaded(void)
-{
- return !!kexec_crash_image;
-}
-EXPORT_SYMBOL_GPL(kexec_crash_loaded);
+bool kexec_file_dbg_print;
/*
* When kexec transitions to the new kernel there is a one-to-one
if (total_pages > nr_pages / 2)
return -EINVAL;
+#ifdef CONFIG_CRASH_DUMP
/*
* Verify we have good destination addresses. Normally
* the caller is responsible for making certain we don't
return -EADDRNOTAVAIL;
}
}
+#endif
return 0;
}
/* Initialize the list of unusable pages */
INIT_LIST_HEAD(&image->unusable_pages);
+#ifdef CONFIG_CRASH_HOTPLUG
+ image->hp_action = KEXEC_CRASH_HP_NONE;
+ image->elfcorehdr_index = -1;
+ image->elfcorehdr_updated = false;
+#endif
+
return image;
}
unsigned long mstart, mend;
mstart = image->segment[i].mem;
- mend = mstart + image->segment[i].memsz;
- if ((end > mstart) && (start < mend))
+ mend = mstart + image->segment[i].memsz - 1;
+ if ((end >= mstart) && (start <= mend))
return 1;
}
pfn = page_to_boot_pfn(pages);
epfn = pfn + count;
addr = pfn << PAGE_SHIFT;
- eaddr = epfn << PAGE_SHIFT;
+ eaddr = (epfn << PAGE_SHIFT) - 1;
if ((epfn >= (KEXEC_CONTROL_MEMORY_LIMIT >> PAGE_SHIFT)) ||
kimage_is_destination_range(image, addr, eaddr)) {
list_add(&pages->lru, &extra_pages);
return pages;
}
+#ifdef CONFIG_CRASH_DUMP
static struct page *kimage_alloc_crash_control_pages(struct kimage *image,
unsigned int order)
{
pages = NULL;
size = (1 << order) << PAGE_SHIFT;
- hole_start = (image->control_page + (size - 1)) & ~(size - 1);
+ hole_start = ALIGN(image->control_page, size);
hole_end = hole_start + size - 1;
while (hole_end <= crashk_res.end) {
unsigned long i;
mend = mstart + image->segment[i].memsz - 1;
if ((hole_end >= mstart) && (hole_start <= mend)) {
/* Advance the hole to the end of the segment */
- hole_start = (mend + (size - 1)) & ~(size - 1);
+ hole_start = ALIGN(mend, size);
hole_end = hole_start + size - 1;
break;
}
/* If I don't overlap any segments I have found my hole! */
if (i == image->nr_segments) {
pages = pfn_to_page(hole_start >> PAGE_SHIFT);
- image->control_page = hole_end;
+ image->control_page = hole_end + 1;
break;
}
}
return pages;
}
+#endif
struct page *kimage_alloc_control_pages(struct kimage *image,
case KEXEC_TYPE_DEFAULT:
pages = kimage_alloc_normal_control_pages(image, order);
break;
+#ifdef CONFIG_CRASH_DUMP
case KEXEC_TYPE_CRASH:
pages = kimage_alloc_crash_control_pages(image, order);
break;
+#endif
}
return pages;
}
-int kimage_crash_copy_vmcoreinfo(struct kimage *image)
-{
- struct page *vmcoreinfo_page;
- void *safecopy;
-
- if (image->type != KEXEC_TYPE_CRASH)
- return 0;
-
- /*
- * For kdump, allocate one vmcoreinfo safe copy from the
- * crash memory. as we have arch_kexec_protect_crashkres()
- * after kexec syscall, we naturally protect it from write
- * (even read) access under kernel direct mapping. But on
- * the other hand, we still need to operate it when crash
- * happens to generate vmcoreinfo note, hereby we rely on
- * vmap for this purpose.
- */
- vmcoreinfo_page = kimage_alloc_control_pages(image, 0);
- if (!vmcoreinfo_page) {
- pr_warn("Could not allocate vmcoreinfo buffer\n");
- return -ENOMEM;
- }
- safecopy = vmap(&vmcoreinfo_page, 1, VM_MAP, PAGE_KERNEL);
- if (!safecopy) {
- pr_warn("Could not vmap vmcoreinfo buffer\n");
- return -ENOMEM;
- }
-
- image->vmcoreinfo_data_copy = safecopy;
- crash_update_vmcoreinfo_safecopy(safecopy);
-
- return 0;
-}
-
static int kimage_add_entry(struct kimage *image, kimage_entry_t entry)
{
if (*image->entry != 0)
static int kimage_set_destination(struct kimage *image,
unsigned long destination)
{
- int result;
-
destination &= PAGE_MASK;
- result = kimage_add_entry(image, destination | IND_DESTINATION);
- return result;
+ return kimage_add_entry(image, destination | IND_DESTINATION);
}
static int kimage_add_page(struct kimage *image, unsigned long page)
{
- int result;
-
page &= PAGE_MASK;
- result = kimage_add_entry(image, page | IND_SOURCE);
- return result;
+ return kimage_add_entry(image, page | IND_SOURCE);
}
if (!image)
return;
+#ifdef CONFIG_CRASH_DUMP
if (image->vmcoreinfo_data_copy) {
crash_update_vmcoreinfo_safecopy(NULL);
vunmap(image->vmcoreinfo_data_copy);
}
+#endif
kimage_free_extra_pages(image);
for_each_kimage_entry(image, ptr, entry) {
/* If the page is not a destination page use it */
if (!kimage_is_destination_range(image, addr,
- addr + PAGE_SIZE))
+ addr + PAGE_SIZE - 1))
break;
/*
if (result < 0)
goto out;
- ptr = kmap(page);
+ ptr = kmap_local_page(page);
/* Start with a clear page */
clear_page(ptr);
ptr += maddr & ~PAGE_MASK;
PAGE_SIZE - (maddr & ~PAGE_MASK));
uchunk = min(ubytes, mchunk);
- /* For file based kexec, source pages are in kernel memory */
- if (image->file_mode)
- memcpy(ptr, kbuf, uchunk);
- else
- result = copy_from_user(ptr, buf, uchunk);
- kunmap(page);
+ if (uchunk) {
+ /* For file based kexec, source pages are in kernel memory */
+ if (image->file_mode)
+ memcpy(ptr, kbuf, uchunk);
+ else
+ result = copy_from_user(ptr, buf, uchunk);
+ ubytes -= uchunk;
+ if (image->file_mode)
+ kbuf += uchunk;
+ else
+ buf += uchunk;
+ }
+ kunmap_local(ptr);
if (result) {
result = -EFAULT;
goto out;
}
- ubytes -= uchunk;
maddr += mchunk;
- if (image->file_mode)
- kbuf += mchunk;
- else
- buf += mchunk;
mbytes -= mchunk;
cond_resched();
return result;
}
+#ifdef CONFIG_CRASH_DUMP
static int kimage_load_crash_segment(struct kimage *image,
struct kexec_segment *segment)
{
goto out;
}
arch_kexec_post_alloc_pages(page_address(page), 1, 0);
- ptr = kmap(page);
+ ptr = kmap_local_page(page);
ptr += maddr & ~PAGE_MASK;
mchunk = min_t(size_t, mbytes,
PAGE_SIZE - (maddr & ~PAGE_MASK));
memset(ptr + uchunk, 0, mchunk - uchunk);
}
- /* For file based kexec, source pages are in kernel memory */
- if (image->file_mode)
- memcpy(ptr, kbuf, uchunk);
- else
- result = copy_from_user(ptr, buf, uchunk);
+ if (uchunk) {
+ /* For file based kexec, source pages are in kernel memory */
+ if (image->file_mode)
+ memcpy(ptr, kbuf, uchunk);
+ else
+ result = copy_from_user(ptr, buf, uchunk);
+ ubytes -= uchunk;
+ if (image->file_mode)
+ kbuf += uchunk;
+ else
+ buf += uchunk;
+ }
kexec_flush_icache_page(page);
- kunmap(page);
+ kunmap_local(ptr);
arch_kexec_pre_free_pages(page_address(page), 1);
if (result) {
result = -EFAULT;
goto out;
}
- ubytes -= uchunk;
maddr += mchunk;
- if (image->file_mode)
- kbuf += mchunk;
- else
- buf += mchunk;
mbytes -= mchunk;
cond_resched();
out:
return result;
}
+#endif
int kimage_load_segment(struct kimage *image,
struct kexec_segment *segment)
case KEXEC_TYPE_DEFAULT:
result = kimage_load_normal_segment(image, segment);
break;
+#ifdef CONFIG_CRASH_DUMP
case KEXEC_TYPE_CRASH:
result = kimage_load_crash_segment(image, segment);
break;
+#endif
}
return result;
}
+struct kexec_load_limit {
+ /* Mutex protects the limit count. */
+ struct mutex mutex;
+ int limit;
+};
+
+static struct kexec_load_limit load_limit_reboot = {
+ .mutex = __MUTEX_INITIALIZER(load_limit_reboot.mutex),
+ .limit = -1,
+};
+
+static struct kexec_load_limit load_limit_panic = {
+ .mutex = __MUTEX_INITIALIZER(load_limit_panic.mutex),
+ .limit = -1,
+};
+
struct kimage *kexec_image;
struct kimage *kexec_crash_image;
-int kexec_load_disabled;
+static int kexec_load_disabled;
+
#ifdef CONFIG_SYSCTL
+static int kexec_limit_handler(struct ctl_table *table, int write,
+ void *buffer, size_t *lenp, loff_t *ppos)
+{
+ struct kexec_load_limit *limit = table->data;
+ int val;
+ struct ctl_table tmp = {
+ .data = &val,
+ .maxlen = sizeof(val),
+ .mode = table->mode,
+ };
+ int ret;
+
+ if (write) {
+ ret = proc_dointvec(&tmp, write, buffer, lenp, ppos);
+ if (ret)
+ return ret;
+
+ if (val < 0)
+ return -EINVAL;
+
+ mutex_lock(&limit->mutex);
+ if (limit->limit != -1 && val >= limit->limit)
+ ret = -EINVAL;
+ else
+ limit->limit = val;
+ mutex_unlock(&limit->mutex);
+
+ return ret;
+ }
+
+ mutex_lock(&limit->mutex);
+ val = limit->limit;
+ mutex_unlock(&limit->mutex);
+
+ return proc_dointvec(&tmp, write, buffer, lenp, ppos);
+}
+
static struct ctl_table kexec_core_sysctls[] = {
{
.procname = "kexec_load_disabled",
.extra1 = SYSCTL_ONE,
.extra2 = SYSCTL_ONE,
},
+ {
+ .procname = "kexec_load_limit_panic",
+ .data = &load_limit_panic,
+ .mode = 0644,
+ .proc_handler = kexec_limit_handler,
+ },
+ {
+ .procname = "kexec_load_limit_reboot",
+ .data = &load_limit_reboot,
+ .mode = 0644,
+ .proc_handler = kexec_limit_handler,
+ },
{ }
};
late_initcall(kexec_core_sysctl_init);
#endif
-/*
- * No panic_cpu check version of crash_kexec(). This function is called
- * only when panic_cpu holds the current CPU number; this is the only CPU
- * which processes crash_kexec routines.
- */
-void __noclone __crash_kexec(struct pt_regs *regs)
+bool kexec_load_permitted(int kexec_image_type)
{
- /* Take the kexec_mutex here to prevent sys_kexec_load
- * running on one cpu from replacing the crash kernel
- * we are using after a panic on a different cpu.
- *
- * If the crash kernel was not located in a fixed area
- * of memory the xchg(&kexec_crash_image) would be
- * sufficient. But since I reuse the memory...
- */
- if (mutex_trylock(&kexec_mutex)) {
- if (kexec_crash_image) {
- struct pt_regs fixed_regs;
-
- crash_setup_regs(&fixed_regs, regs);
- crash_save_vmcoreinfo();
- machine_crash_shutdown(&fixed_regs);
- machine_kexec(kexec_crash_image);
- }
- mutex_unlock(&kexec_mutex);
- }
-}
-STACK_FRAME_NON_STANDARD(__crash_kexec);
-
-void crash_kexec(struct pt_regs *regs)
-{
- int old_cpu, this_cpu;
+ struct kexec_load_limit *limit;
/*
- * Only one CPU is allowed to execute the crash_kexec() code as with
- * panic(). Otherwise parallel calls of panic() and crash_kexec()
- * may stop each other. To exclude them, we use panic_cpu here too.
+ * Only the superuser can use the kexec syscall and if it has not
+ * been disabled.
*/
- this_cpu = raw_smp_processor_id();
- old_cpu = atomic_cmpxchg(&panic_cpu, PANIC_CPU_INVALID, this_cpu);
- if (old_cpu == PANIC_CPU_INVALID) {
- /* This is the 1st CPU which comes here, so go ahead. */
- __crash_kexec(regs);
-
- /*
- * Reset panic_cpu to allow another panic()/crash_kexec()
- * call.
- */
- atomic_set(&panic_cpu, PANIC_CPU_INVALID);
+ if (!capable(CAP_SYS_BOOT) || kexec_load_disabled)
+ return false;
+
+ /* Check limit counter and decrease it.*/
+ limit = (kexec_image_type == KEXEC_TYPE_CRASH) ?
+ &load_limit_panic : &load_limit_reboot;
+ mutex_lock(&limit->mutex);
+ if (!limit->limit) {
+ mutex_unlock(&limit->mutex);
+ return false;
}
-}
-
-size_t crash_get_memory_size(void)
-{
- size_t size = 0;
+ if (limit->limit != -1)
+ limit->limit--;
+ mutex_unlock(&limit->mutex);
- mutex_lock(&kexec_mutex);
- if (crashk_res.end != crashk_res.start)
- size = resource_size(&crashk_res);
- mutex_unlock(&kexec_mutex);
- return size;
+ return true;
}
-int crash_shrink_memory(unsigned long new_size)
-{
- int ret = 0;
- unsigned long start, end;
- unsigned long old_size;
- struct resource *ram_res;
-
- mutex_lock(&kexec_mutex);
-
- if (kexec_crash_image) {
- ret = -ENOENT;
- goto unlock;
- }
- start = crashk_res.start;
- end = crashk_res.end;
- old_size = (end == 0) ? 0 : end - start + 1;
- if (new_size >= old_size) {
- ret = (new_size == old_size) ? 0 : -EINVAL;
- goto unlock;
- }
-
- ram_res = kzalloc(sizeof(*ram_res), GFP_KERNEL);
- if (!ram_res) {
- ret = -ENOMEM;
- goto unlock;
- }
-
- start = roundup(start, KEXEC_CRASH_MEM_ALIGN);
- end = roundup(start + new_size, KEXEC_CRASH_MEM_ALIGN);
-
- crash_free_reserved_phys_range(end, crashk_res.end);
-
- if ((start == end) && (crashk_res.parent != NULL))
- release_resource(&crashk_res);
-
- ram_res->start = end;
- ram_res->end = crashk_res.end;
- ram_res->flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM;
- ram_res->name = "System RAM";
-
- crashk_res.end = end - 1;
-
- insert_resource(&iomem_resource, ram_res);
-
-unlock:
- mutex_unlock(&kexec_mutex);
- return ret;
-}
-
-void crash_save_cpu(struct pt_regs *regs, int cpu)
-{
- struct elf_prstatus prstatus;
- u32 *buf;
-
- if ((cpu < 0) || (cpu >= nr_cpu_ids))
- return;
-
- /* Using ELF notes here is opportunistic.
- * I need a well defined structure format
- * for the data I pass, and I need tags
- * on the data to indicate what information I have
- * squirrelled away. ELF notes happen to provide
- * all of that, so there is no need to invent something new.
- */
- buf = (u32 *)per_cpu_ptr(crash_notes, cpu);
- if (!buf)
- return;
- memset(&prstatus, 0, sizeof(prstatus));
- prstatus.common.pr_pid = current->pid;
- elf_core_copy_regs(&prstatus.pr_reg, regs);
- buf = append_elf_note(buf, KEXEC_CORE_NOTE_NAME, NT_PRSTATUS,
- &prstatus, sizeof(prstatus));
- final_note(buf);
-}
-
-static int __init crash_notes_memory_init(void)
-{
- /* Allocate memory for saving cpu registers. */
- size_t size, align;
-
- /*
- * crash_notes could be allocated across 2 vmalloc pages when percpu
- * is vmalloc based . vmalloc doesn't guarantee 2 continuous vmalloc
- * pages are also on 2 continuous physical pages. In this case the
- * 2nd part of crash_notes in 2nd page could be lost since only the
- * starting address and size of crash_notes are exported through sysfs.
- * Here round up the size of crash_notes to the nearest power of two
- * and pass it to __alloc_percpu as align value. This can make sure
- * crash_notes is allocated inside one physical page.
- */
- size = sizeof(note_buf_t);
- align = min(roundup_pow_of_two(sizeof(note_buf_t)), PAGE_SIZE);
-
- /*
- * Break compile if size is bigger than PAGE_SIZE since crash_notes
- * definitely will be in 2 pages with that.
- */
- BUILD_BUG_ON(size > PAGE_SIZE);
-
- crash_notes = __alloc_percpu(size, align);
- if (!crash_notes) {
- pr_warn("Memory allocation for saving cpu register states failed\n");
- return -ENOMEM;
- }
- return 0;
-}
-subsys_initcall(crash_notes_memory_init);
-
-
/*
* Move into place and start executing a preloaded standalone
* executable. If nothing was preloaded return an error.
{
int error = 0;
- if (!mutex_trylock(&kexec_mutex))
+ if (!kexec_trylock())
return -EBUSY;
if (!kexec_image) {
error = -EINVAL;
kexec_in_progress = true;
kernel_restart_prepare("kexec reboot");
migrate_to_reboot_cpu();
+ syscore_shutdown();
/*
* migrate_to_reboot_cpu() disables CPU hotplug assuming that
#endif
Unlock:
- mutex_unlock(&kexec_mutex);
+ kexec_unlock();
return error;
}