aboutsummaryrefslogtreecommitdiff
path: root/kernel/kexec.c
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/kexec.c')
-rw-r--r--kernel/kexec.c465
1 files changed, 312 insertions, 153 deletions
diff --git a/kernel/kexec.c b/kernel/kexec.c
index a9a93d9ee7a..4b8f0c92588 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -21,7 +21,6 @@
#include <linux/hardirq.h>
#include <linux/elf.h>
#include <linux/elfcore.h>
-#include <generated/utsrelease.h>
#include <linux/utsname.h>
#include <linux/numa.h>
#include <linux/suspend.h>
@@ -32,15 +31,17 @@
#include <linux/console.h>
#include <linux/vmalloc.h>
#include <linux/swap.h>
+#include <linux/syscore_ops.h>
+#include <linux/compiler.h>
+#include <linux/hugetlb.h>
#include <asm/page.h>
#include <asm/uaccess.h>
#include <asm/io.h>
-#include <asm/system.h>
#include <asm/sections.h>
/* Per cpu memory for storing cpu states in case of system crash. */
-note_buf_t* crash_notes;
+note_buf_t __percpu *crash_notes;
/* vmcoreinfo stuff */
static unsigned char vmcoreinfo_data[VMCOREINFO_BYTES];
@@ -48,6 +49,9 @@ u32 vmcoreinfo_note[VMCOREINFO_NOTE_SIZE/4];
size_t vmcoreinfo_size;
size_t vmcoreinfo_max_size = sizeof(vmcoreinfo_data);
+/* 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",
@@ -55,6 +59,12 @@ struct resource crashk_res = {
.end = 0,
.flags = IORESOURCE_BUSY | IORESOURCE_MEM
};
+struct resource crashk_low_res = {
+ .name = "Crash kernel",
+ .start = 0,
+ .end = 0,
+ .flags = IORESOURCE_BUSY | IORESOURCE_MEM
+};
int kexec_should_crash(struct task_struct *p)
{
@@ -116,8 +126,8 @@ static struct page *kimage_alloc_page(struct kimage *image,
unsigned long dest);
static int do_kimage_alloc(struct kimage **rimage, unsigned long entry,
- unsigned long nr_segments,
- struct kexec_segment __user *segments)
+ unsigned long nr_segments,
+ struct kexec_segment __user *segments)
{
size_t segment_bytes;
struct kimage *image;
@@ -143,15 +153,17 @@ static int do_kimage_alloc(struct kimage **rimage, unsigned long entry,
/* Initialize the list of destination pages */
INIT_LIST_HEAD(&image->dest_pages);
- /* Initialize the list of unuseable pages */
+ /* Initialize the list of unusable pages */
INIT_LIST_HEAD(&image->unuseable_pages);
/* Read in the segments */
image->nr_segments = nr_segments;
segment_bytes = nr_segments * sizeof(*segments);
result = copy_from_user(image->segment, segments, segment_bytes);
- if (result)
+ if (result) {
+ result = -EFAULT;
goto out;
+ }
/*
* Verify we have good destination addresses. The caller is
@@ -160,7 +172,7 @@ static int do_kimage_alloc(struct kimage **rimage, unsigned long entry,
* just verifies it is an address we can use.
*
* Since the kernel does everything in page size chunks ensure
- * the destination addreses are page aligned. Too many
+ * the destination addresses are page aligned. Too many
* special cases crop of when we don't do this. The most
* insidious is getting overlapping destination addresses
* simply because addresses are changed to page size
@@ -222,6 +234,8 @@ out:
}
+static void kimage_free_page_list(struct list_head *list);
+
static int kimage_normal_alloc(struct kimage **rimage, unsigned long entry,
unsigned long nr_segments,
struct kexec_segment __user *segments)
@@ -235,8 +249,6 @@ static int kimage_normal_alloc(struct kimage **rimage, unsigned long entry,
if (result)
goto out;
- *rimage = image;
-
/*
* Find a location for the control code buffer, and add it
* the vector of segments so that it's pages will also be
@@ -246,23 +258,23 @@ static int kimage_normal_alloc(struct kimage **rimage, unsigned long entry,
image->control_code_page = kimage_alloc_control_pages(image,
get_order(KEXEC_CONTROL_PAGE_SIZE));
if (!image->control_code_page) {
- printk(KERN_ERR "Could not allocate control_code_buffer\n");
- goto out;
+ pr_err("Could not allocate control_code_buffer\n");
+ goto out_free;
}
image->swap_page = kimage_alloc_control_pages(image, 0);
if (!image->swap_page) {
- printk(KERN_ERR "Could not allocate swap buffer\n");
- goto out;
+ pr_err("Could not allocate swap buffer\n");
+ goto out_free;
}
- result = 0;
- out:
- if (result == 0)
- *rimage = image;
- else
- kfree(image);
+ *rimage = image;
+ return 0;
+out_free:
+ kimage_free_page_list(&image->control_pages);
+ kfree(image);
+out:
return result;
}
@@ -309,7 +321,7 @@ static int kimage_crash_alloc(struct kimage **rimage, unsigned long entry,
mend = mstart + image->segment[i].memsz - 1;
/* Ensure we are within the crash kernel limits */
if ((mstart < crashk_res.start) || (mend > crashk_res.end))
- goto out;
+ goto out_free;
}
/*
@@ -321,17 +333,16 @@ static int kimage_crash_alloc(struct kimage **rimage, unsigned long entry,
image->control_code_page = kimage_alloc_control_pages(image,
get_order(KEXEC_CONTROL_PAGE_SIZE));
if (!image->control_code_page) {
- printk(KERN_ERR "Could not allocate control_code_buffer\n");
- goto out;
+ pr_err("Could not allocate control_code_buffer\n");
+ goto out_free;
}
- result = 0;
-out:
- if (result == 0)
- *rimage = image;
- else
- kfree(image);
+ *rimage = image;
+ return 0;
+out_free:
+ kfree(image);
+out:
return result;
}
@@ -451,7 +462,7 @@ static struct page *kimage_alloc_normal_control_pages(struct kimage *image,
/* Deal with the destination pages I have inadvertently allocated.
*
* Ideally I would convert multi-page allocations into single
- * page allocations, and add everyting to image->dest_pages.
+ * page allocations, and add everything to image->dest_pages.
*
* For now it is simpler to just free the pages.
*/
@@ -494,9 +505,7 @@ static struct page *kimage_alloc_crash_control_pages(struct kimage *image,
while (hole_end <= crashk_res.end) {
unsigned long i;
- if (hole_end > KEXEC_CONTROL_MEMORY_LIMIT)
- break;
- if (hole_end > crashk_res.end)
+ if (hole_end > KEXEC_CRASH_CONTROL_MEMORY_LIMIT)
break;
/* See if I overlap any of the segments */
for (i = 0; i < image->nr_segments; i++) {
@@ -599,7 +608,7 @@ static void kimage_free_extra_pages(struct kimage *image)
/* Walk through and free any extra destination pages I may have */
kimage_free_page_list(&image->dest_pages);
- /* Walk through and free any unuseable pages I have cached */
+ /* Walk through and free any unusable pages I have cached */
kimage_free_page_list(&image->unuseable_pages);
}
@@ -613,8 +622,8 @@ static void kimage_terminate(struct kimage *image)
#define for_each_kimage_entry(image, ptr, entry) \
for (ptr = &image->head; (entry = *ptr) && !(entry & IND_DONE); \
- ptr = (entry & IND_INDIRECTION)? \
- phys_to_virt((entry & PAGE_MASK)): ptr +1)
+ ptr = (entry & IND_INDIRECTION) ? \
+ phys_to_virt((entry & PAGE_MASK)) : ptr + 1)
static void kimage_free_entry(kimage_entry_t entry)
{
@@ -642,8 +651,7 @@ static void kimage_free(struct kimage *image)
* done with it.
*/
ind = entry;
- }
- else if (entry & IND_SOURCE)
+ } else if (entry & IND_SOURCE)
kimage_free_entry(entry);
}
/* Free the final indirection page */
@@ -766,8 +774,7 @@ static struct page *kimage_alloc_page(struct kimage *image,
addr = old_addr;
page = old_page;
break;
- }
- else {
+ } else {
/* Place the page on the destination list I
* will use it later.
*/
@@ -782,7 +789,7 @@ static int kimage_load_normal_segment(struct kimage *image,
struct kexec_segment *segment)
{
unsigned long maddr;
- unsigned long ubytes, mbytes;
+ size_t ubytes, mbytes;
int result;
unsigned char __user *buf;
@@ -813,20 +820,16 @@ static int kimage_load_normal_segment(struct kimage *image,
ptr = kmap(page);
/* Start with a clear page */
- memset(ptr, 0, PAGE_SIZE);
+ clear_page(ptr);
ptr += maddr & ~PAGE_MASK;
- mchunk = PAGE_SIZE - (maddr & ~PAGE_MASK);
- if (mchunk > mbytes)
- mchunk = mbytes;
-
- uchunk = mchunk;
- if (uchunk > ubytes)
- uchunk = ubytes;
+ mchunk = min_t(size_t, mbytes,
+ PAGE_SIZE - (maddr & ~PAGE_MASK));
+ uchunk = min(ubytes, mchunk);
result = copy_from_user(ptr, buf, uchunk);
kunmap(page);
if (result) {
- result = (result < 0) ? result : -EIO;
+ result = -EFAULT;
goto out;
}
ubytes -= uchunk;
@@ -846,7 +849,7 @@ static int kimage_load_crash_segment(struct kimage *image,
* We do things a page at a time for the sake of kmap.
*/
unsigned long maddr;
- unsigned long ubytes, mbytes;
+ size_t ubytes, mbytes;
int result;
unsigned char __user *buf;
@@ -867,13 +870,10 @@ static int kimage_load_crash_segment(struct kimage *image,
}
ptr = kmap(page);
ptr += maddr & ~PAGE_MASK;
- mchunk = PAGE_SIZE - (maddr & ~PAGE_MASK);
- if (mchunk > mbytes)
- mchunk = mbytes;
-
- uchunk = mchunk;
- if (uchunk > ubytes) {
- uchunk = ubytes;
+ mchunk = min_t(size_t, mbytes,
+ PAGE_SIZE - (maddr & ~PAGE_MASK));
+ uchunk = min(ubytes, mchunk);
+ if (mchunk > uchunk) {
/* Zero the trailing part of the page */
memset(ptr + uchunk, 0, mchunk - uchunk);
}
@@ -881,7 +881,7 @@ static int kimage_load_crash_segment(struct kimage *image,
kexec_flush_icache_page(page);
kunmap(page);
if (result) {
- result = (result < 0) ? result : -EIO;
+ result = -EFAULT;
goto out;
}
ubytes -= uchunk;
@@ -924,7 +924,7 @@ static int kimage_load_segment(struct kimage *image,
* reinitialize them.
*
* - A machine specific part that includes the syscall number
- * and the copies the image to it's final destination. And
+ * and then copies the image to it's final destination. And
* jumps into the image at entry.
*
* kexec does not sync, or unmount filesystems so if you need
@@ -932,6 +932,7 @@ static int kimage_load_segment(struct kimage *image,
*/
struct kimage *kexec_image;
struct kimage *kexec_crash_image;
+int kexec_load_disabled;
static DEFINE_MUTEX(kexec_mutex);
@@ -942,7 +943,7 @@ SYSCALL_DEFINE4(kexec_load, unsigned long, entry, unsigned long, nr_segments,
int result;
/* We only trust the superuser with rebooting the system. */
- if (!capable(CAP_SYS_BOOT))
+ if (!capable(CAP_SYS_BOOT) || kexec_load_disabled)
return -EPERM;
/*
@@ -995,6 +996,7 @@ SYSCALL_DEFINE4(kexec_load, unsigned long, entry, unsigned long, nr_segments,
kimage_free(xchg(&kexec_crash_image, NULL));
result = kimage_crash_alloc(&image, entry,
nr_segments, segments);
+ crash_map_reserved_pages();
}
if (result)
goto out;
@@ -1011,6 +1013,8 @@ SYSCALL_DEFINE4(kexec_load, unsigned long, entry, unsigned long, nr_segments,
goto out;
}
kimage_terminate(image);
+ if (flags & KEXEC_ON_CRASH)
+ crash_unmap_reserved_pages();
}
/* Install the new kernel, and Uninstall the old */
image = xchg(dest_image, image);
@@ -1022,11 +1026,23 @@ out:
return result;
}
+/*
+ * Add and remove page tables for crashkernel memory
+ *
+ * Provide an empty default implementation here -- architecture
+ * code may override this
+ */
+void __weak crash_map_reserved_pages(void)
+{}
+
+void __weak crash_unmap_reserved_pages(void)
+{}
+
#ifdef CONFIG_COMPAT
-asmlinkage long compat_sys_kexec_load(unsigned long entry,
- unsigned long nr_segments,
- struct compat_kexec_segment __user *segments,
- unsigned long flags)
+COMPAT_SYSCALL_DEFINE4(kexec_load, compat_ulong_t, entry,
+ compat_ulong_t, nr_segments,
+ struct compat_kexec_segment __user *, segments,
+ compat_ulong_t, flags)
{
struct compat_kexec_segment in;
struct kexec_segment out, __user *ksegments;
@@ -1042,7 +1058,7 @@ asmlinkage long compat_sys_kexec_load(unsigned long entry,
return -EINVAL;
ksegments = compat_alloc_user_space(nr_segments * sizeof(out));
- for (i=0; i < nr_segments; i++) {
+ for (i = 0; i < nr_segments; i++) {
result = copy_from_user(&in, &segments[i], sizeof(in));
if (result)
return -EFAULT;
@@ -1074,6 +1090,7 @@ void crash_kexec(struct pt_regs *regs)
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);
@@ -1085,29 +1102,29 @@ void crash_kexec(struct pt_regs *regs)
size_t crash_get_memory_size(void)
{
- size_t size;
+ size_t size = 0;
mutex_lock(&kexec_mutex);
- size = crashk_res.end - crashk_res.start + 1;
+ if (crashk_res.end != crashk_res.start)
+ size = resource_size(&crashk_res);
mutex_unlock(&kexec_mutex);
return size;
}
-static void free_reserved_phys_range(unsigned long begin, unsigned long end)
+void __weak crash_free_reserved_phys_range(unsigned long begin,
+ unsigned long end)
{
unsigned long addr;
- for (addr = begin; addr < end; addr += PAGE_SIZE) {
- ClearPageReserved(pfn_to_page(addr >> PAGE_SHIFT));
- init_page_count(pfn_to_page(addr >> PAGE_SHIFT));
- free_page((unsigned long)__va(addr));
- totalram_pages++;
- }
+ for (addr = begin; addr < end; addr += PAGE_SIZE)
+ free_reserved_page(pfn_to_page(addr >> PAGE_SHIFT));
}
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);
@@ -1117,24 +1134,36 @@ int crash_shrink_memory(unsigned long new_size)
}
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;
+ }
- if (new_size >= end - start + 1) {
- ret = -EINVAL;
- if (new_size == end - start + 1)
- ret = 0;
+ ram_res = kzalloc(sizeof(*ram_res), GFP_KERNEL);
+ if (!ram_res) {
+ ret = -ENOMEM;
goto unlock;
}
- start = roundup(start, PAGE_SIZE);
- end = roundup(start + new_size, PAGE_SIZE);
+ start = roundup(start, KEXEC_CRASH_MEM_ALIGN);
+ end = roundup(start + new_size, KEXEC_CRASH_MEM_ALIGN);
- free_reserved_phys_range(end, crashk_res.end);
+ crash_map_reserved_pages();
+ crash_free_reserved_phys_range(end, crashk_res.end);
- if (start == end) {
- crashk_res.end = end;
+ if ((start == end) && (crashk_res.parent != NULL))
release_resource(&crashk_res);
- } else
- crashk_res.end = end - 1;
+
+ ram_res->start = end;
+ ram_res->end = crashk_res.end;
+ ram_res->flags = IORESOURCE_BUSY | IORESOURCE_MEM;
+ ram_res->name = "System RAM";
+
+ crashk_res.end = end - 1;
+
+ insert_resource(&iomem_resource, ram_res);
+ crash_unmap_reserved_pages();
unlock:
mutex_unlock(&kexec_mutex);
@@ -1184,14 +1213,14 @@ void crash_save_cpu(struct pt_regs *regs, int cpu)
* 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);
+ buf = (u32 *)per_cpu_ptr(crash_notes, cpu);
if (!buf)
return;
memset(&prstatus, 0, sizeof(prstatus));
prstatus.pr_pid = current->pid;
elf_core_copy_kernel_regs(&prstatus.pr_reg, regs);
buf = append_elf_note(buf, KEXEC_CORE_NOTE_NAME, NT_PRSTATUS,
- &prstatus, sizeof(prstatus));
+ &prstatus, sizeof(prstatus));
final_note(buf);
}
@@ -1200,13 +1229,12 @@ static int __init crash_notes_memory_init(void)
/* Allocate memory for saving cpu registers. */
crash_notes = alloc_percpu(note_buf_t);
if (!crash_notes) {
- printk("Kexec: Memory allocation for saving cpu register"
- " states failed\n");
+ pr_warn("Kexec: Memory allocation for saving cpu register states failed\n");
return -ENOMEM;
}
return 0;
}
-module_init(crash_notes_memory_init)
+subsys_initcall(crash_notes_memory_init);
/*
@@ -1223,10 +1251,10 @@ module_init(crash_notes_memory_init)
*
* The function returns 0 on success and -EINVAL on failure.
*/
-static int __init parse_crashkernel_mem(char *cmdline,
- unsigned long long system_ram,
- unsigned long long *crash_size,
- unsigned long long *crash_base)
+static int __init parse_crashkernel_mem(char *cmdline,
+ unsigned long long system_ram,
+ unsigned long long *crash_size,
+ unsigned long long *crash_base)
{
char *cur = cmdline, *tmp;
@@ -1237,12 +1265,12 @@ static int __init parse_crashkernel_mem(char *cmdline,
/* get the start of the range */
start = memparse(cur, &tmp);
if (cur == tmp) {
- pr_warning("crashkernel: Memory value expected\n");
+ pr_warn("crashkernel: Memory value expected\n");
return -EINVAL;
}
cur = tmp;
if (*cur != '-') {
- pr_warning("crashkernel: '-' expected\n");
+ pr_warn("crashkernel: '-' expected\n");
return -EINVAL;
}
cur++;
@@ -1251,31 +1279,30 @@ static int __init parse_crashkernel_mem(char *cmdline,
if (*cur != ':') {
end = memparse(cur, &tmp);
if (cur == tmp) {
- pr_warning("crashkernel: Memory "
- "value expected\n");
+ pr_warn("crashkernel: Memory value expected\n");
return -EINVAL;
}
cur = tmp;
if (end <= start) {
- pr_warning("crashkernel: end <= start\n");
+ pr_warn("crashkernel: end <= start\n");
return -EINVAL;
}
}
if (*cur != ':') {
- pr_warning("crashkernel: ':' expected\n");
+ pr_warn("crashkernel: ':' expected\n");
return -EINVAL;
}
cur++;
size = memparse(cur, &tmp);
if (cur == tmp) {
- pr_warning("Memory value expected\n");
+ pr_warn("Memory value expected\n");
return -EINVAL;
}
cur = tmp;
if (size >= system_ram) {
- pr_warning("crashkernel: invalid size\n");
+ pr_warn("crashkernel: invalid size\n");
return -EINVAL;
}
@@ -1293,8 +1320,7 @@ static int __init parse_crashkernel_mem(char *cmdline,
cur++;
*crash_base = memparse(cur, &tmp);
if (cur == tmp) {
- pr_warning("Memory value expected "
- "after '@'\n");
+ pr_warn("Memory value expected after '@'\n");
return -EINVAL;
}
}
@@ -1306,56 +1332,140 @@ static int __init parse_crashkernel_mem(char *cmdline,
/*
* That function parses "simple" (old) crashkernel command lines like
*
- * crashkernel=size[@offset]
+ * crashkernel=size[@offset]
*
* It returns 0 on success and -EINVAL on failure.
*/
-static int __init parse_crashkernel_simple(char *cmdline,
- unsigned long long *crash_size,
- unsigned long long *crash_base)
+static int __init parse_crashkernel_simple(char *cmdline,
+ unsigned long long *crash_size,
+ unsigned long long *crash_base)
{
char *cur = cmdline;
*crash_size = memparse(cmdline, &cur);
if (cmdline == cur) {
- pr_warning("crashkernel: memory value expected\n");
+ pr_warn("crashkernel: memory value expected\n");
return -EINVAL;
}
if (*cur == '@')
*crash_base = memparse(cur+1, &cur);
+ else if (*cur != ' ' && *cur != '\0') {
+ pr_warn("crashkernel: unrecognized char\n");
+ return -EINVAL;
+ }
return 0;
}
+#define SUFFIX_HIGH 0
+#define SUFFIX_LOW 1
+#define SUFFIX_NULL 2
+static __initdata char *suffix_tbl[] = {
+ [SUFFIX_HIGH] = ",high",
+ [SUFFIX_LOW] = ",low",
+ [SUFFIX_NULL] = NULL,
+};
+
/*
- * That function is the entry point for command line parsing and should be
- * called from the arch-specific code.
+ * That function parses "suffix" crashkernel command lines like
+ *
+ * crashkernel=size,[high|low]
+ *
+ * It returns 0 on success and -EINVAL on failure.
*/
-int __init parse_crashkernel(char *cmdline,
+static int __init parse_crashkernel_suffix(char *cmdline,
+ unsigned long long *crash_size,
+ unsigned long long *crash_base,
+ const char *suffix)
+{
+ char *cur = cmdline;
+
+ *crash_size = memparse(cmdline, &cur);
+ if (cmdline == cur) {
+ pr_warn("crashkernel: memory value expected\n");
+ return -EINVAL;
+ }
+
+ /* check with suffix */
+ if (strncmp(cur, suffix, strlen(suffix))) {
+ pr_warn("crashkernel: unrecognized char\n");
+ return -EINVAL;
+ }
+ cur += strlen(suffix);
+ if (*cur != ' ' && *cur != '\0') {
+ pr_warn("crashkernel: unrecognized char\n");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static __init char *get_last_crashkernel(char *cmdline,
+ const char *name,
+ const char *suffix)
+{
+ char *p = cmdline, *ck_cmdline = NULL;
+
+ /* find crashkernel and use the last one if there are more */
+ p = strstr(p, name);
+ while (p) {
+ char *end_p = strchr(p, ' ');
+ char *q;
+
+ if (!end_p)
+ end_p = p + strlen(p);
+
+ if (!suffix) {
+ int i;
+
+ /* skip the one with any known suffix */
+ for (i = 0; suffix_tbl[i]; i++) {
+ q = end_p - strlen(suffix_tbl[i]);
+ if (!strncmp(q, suffix_tbl[i],
+ strlen(suffix_tbl[i])))
+ goto next;
+ }
+ ck_cmdline = p;
+ } else {
+ q = end_p - strlen(suffix);
+ if (!strncmp(q, suffix, strlen(suffix)))
+ ck_cmdline = p;
+ }
+next:
+ p = strstr(p+1, name);
+ }
+
+ if (!ck_cmdline)
+ return NULL;
+
+ return ck_cmdline;
+}
+
+static int __init __parse_crashkernel(char *cmdline,
unsigned long long system_ram,
unsigned long long *crash_size,
- unsigned long long *crash_base)
+ unsigned long long *crash_base,
+ const char *name,
+ const char *suffix)
{
- char *p = cmdline, *ck_cmdline = NULL;
char *first_colon, *first_space;
+ char *ck_cmdline;
BUG_ON(!crash_size || !crash_base);
*crash_size = 0;
*crash_base = 0;
- /* find crashkernel and use the last one if there are more */
- p = strstr(p, "crashkernel=");
- while (p) {
- ck_cmdline = p;
- p = strstr(p+1, "crashkernel=");
- }
+ ck_cmdline = get_last_crashkernel(cmdline, name, suffix);
if (!ck_cmdline)
return -EINVAL;
- ck_cmdline += 12; /* strlen("crashkernel=") */
+ ck_cmdline += strlen(name);
+ if (suffix)
+ return parse_crashkernel_suffix(ck_cmdline, crash_size,
+ crash_base, suffix);
/*
* if the commandline contains a ':', then that's the extended
* syntax -- if not, it must be the classic syntax
@@ -1365,44 +1475,69 @@ int __init parse_crashkernel(char *cmdline,
if (first_colon && (!first_space || first_colon < first_space))
return parse_crashkernel_mem(ck_cmdline, system_ram,
crash_size, crash_base);
- else
- return parse_crashkernel_simple(ck_cmdline, crash_size,
- crash_base);
- return 0;
+ return parse_crashkernel_simple(ck_cmdline, crash_size, crash_base);
+}
+
+/*
+ * That function is the entry point for command line parsing and should be
+ * called from the arch-specific code.
+ */
+int __init parse_crashkernel(char *cmdline,
+ unsigned long long system_ram,
+ unsigned long long *crash_size,
+ unsigned long long *crash_base)
+{
+ return __parse_crashkernel(cmdline, system_ram, crash_size, crash_base,
+ "crashkernel=", NULL);
}
+int __init parse_crashkernel_high(char *cmdline,
+ unsigned long long system_ram,
+ unsigned long long *crash_size,
+ unsigned long long *crash_base)
+{
+ return __parse_crashkernel(cmdline, system_ram, crash_size, crash_base,
+ "crashkernel=", suffix_tbl[SUFFIX_HIGH]);
+}
+int __init parse_crashkernel_low(char *cmdline,
+ unsigned long long system_ram,
+ unsigned long long *crash_size,
+ unsigned long long *crash_base)
+{
+ return __parse_crashkernel(cmdline, system_ram, crash_size, crash_base,
+ "crashkernel=", suffix_tbl[SUFFIX_LOW]);
+}
-void crash_save_vmcoreinfo(void)
+static void update_vmcoreinfo_note(void)
{
- u32 *buf;
+ u32 *buf = vmcoreinfo_note;
if (!vmcoreinfo_size)
return;
-
- vmcoreinfo_append_str("CRASHTIME=%ld", get_seconds());
-
- buf = (u32 *)vmcoreinfo_note;
-
buf = append_elf_note(buf, VMCOREINFO_NOTE_NAME, 0, vmcoreinfo_data,
vmcoreinfo_size);
-
final_note(buf);
}
+void crash_save_vmcoreinfo(void)
+{
+ vmcoreinfo_append_str("CRASHTIME=%ld\n", get_seconds());
+ update_vmcoreinfo_note();
+}
+
void vmcoreinfo_append_str(const char *fmt, ...)
{
va_list args;
char buf[0x50];
- int r;
+ size_t r;
va_start(args, fmt);
- r = vsnprintf(buf, sizeof(buf), fmt, args);
+ r = vscnprintf(buf, sizeof(buf), fmt, args);
va_end(args);
- if (r + vmcoreinfo_size > vmcoreinfo_max_size)
- r = vmcoreinfo_max_size - vmcoreinfo_size;
+ r = min(r, vmcoreinfo_max_size - vmcoreinfo_size);
memcpy(&vmcoreinfo_data[vmcoreinfo_size], buf, r);
@@ -1413,10 +1548,10 @@ void vmcoreinfo_append_str(const char *fmt, ...)
* provide an empty default implementation here -- architecture
* code may override this
*/
-void __attribute__ ((weak)) arch_crash_save_vmcoreinfo(void)
+void __weak arch_crash_save_vmcoreinfo(void)
{}
-unsigned long __attribute__ ((weak)) paddr_vmcoreinfo_note(void)
+unsigned long __weak paddr_vmcoreinfo_note(void)
{
return __pa((unsigned long)(char *)&vmcoreinfo_note);
}
@@ -1428,9 +1563,11 @@ static int __init crash_save_vmcoreinfo_init(void)
VMCOREINFO_SYMBOL(init_uts_ns);
VMCOREINFO_SYMBOL(node_online_map);
+#ifdef CONFIG_MMU
VMCOREINFO_SYMBOL(swapper_pg_dir);
+#endif
VMCOREINFO_SYMBOL(_stext);
- VMCOREINFO_SYMBOL(vmlist);
+ VMCOREINFO_SYMBOL(vmap_area_list);
#ifndef CONFIG_NEED_MULTIPLE_NODES
VMCOREINFO_SYMBOL(mem_map);
@@ -1452,6 +1589,8 @@ static int __init crash_save_vmcoreinfo_init(void)
VMCOREINFO_OFFSET(page, _count);
VMCOREINFO_OFFSET(page, mapping);
VMCOREINFO_OFFSET(page, lru);
+ VMCOREINFO_OFFSET(page, _mapcount);
+ VMCOREINFO_OFFSET(page, private);
VMCOREINFO_OFFSET(pglist_data, node_zones);
VMCOREINFO_OFFSET(pglist_data, nr_zones);
#ifdef CONFIG_FLAT_NODE_MEM_MAP
@@ -1466,7 +1605,8 @@ static int __init crash_save_vmcoreinfo_init(void)
VMCOREINFO_OFFSET(free_area, free_list);
VMCOREINFO_OFFSET(list_head, next);
VMCOREINFO_OFFSET(list_head, prev);
- VMCOREINFO_OFFSET(vm_struct, addr);
+ VMCOREINFO_OFFSET(vmap_area, va_start);
+ VMCOREINFO_OFFSET(vmap_area, list);
VMCOREINFO_LENGTH(zone.free_area, MAX_ORDER);
log_buf_kexec_setup();
VMCOREINFO_LENGTH(free_area.free_list, MIGRATE_TYPES);
@@ -1474,13 +1614,23 @@ static int __init crash_save_vmcoreinfo_init(void)
VMCOREINFO_NUMBER(PG_lru);
VMCOREINFO_NUMBER(PG_private);
VMCOREINFO_NUMBER(PG_swapcache);
+ VMCOREINFO_NUMBER(PG_slab);
+#ifdef CONFIG_MEMORY_FAILURE
+ VMCOREINFO_NUMBER(PG_hwpoison);
+#endif
+ VMCOREINFO_NUMBER(PG_head_mask);
+ VMCOREINFO_NUMBER(PAGE_BUDDY_MAPCOUNT_VALUE);
+#ifdef CONFIG_HUGETLBFS
+ VMCOREINFO_SYMBOL(free_huge_page);
+#endif
arch_crash_save_vmcoreinfo();
+ update_vmcoreinfo_note();
return 0;
}
-module_init(crash_save_vmcoreinfo_init)
+subsys_initcall(crash_save_vmcoreinfo_init);
/*
* Move into place and start executing a preloaded standalone
@@ -1499,7 +1649,7 @@ int kernel_kexec(void)
#ifdef CONFIG_KEXEC_JUMP
if (kexec_image->preserve_context) {
- mutex_lock(&pm_mutex);
+ lock_system_sleep();
pm_prepare_console();
error = freeze_processes();
if (error) {
@@ -1511,28 +1661,37 @@ int kernel_kexec(void)
if (error)
goto Resume_console;
/* At this point, dpm_suspend_start() has been called,
- * but *not* dpm_suspend_noirq(). We *must* call
- * dpm_suspend_noirq() now. Otherwise, drivers for
+ * but *not* dpm_suspend_end(). We *must* call
+ * dpm_suspend_end() now. Otherwise, drivers for
* some devices (e.g. interrupt controllers) become
* desynchronized with the actual state of the
* hardware at resume time, and evil weirdness ensues.
*/
- error = dpm_suspend_noirq(PMSG_FREEZE);
+ error = dpm_suspend_end(PMSG_FREEZE);
if (error)
goto Resume_devices;
error = disable_nonboot_cpus();
if (error)
goto Enable_cpus;
local_irq_disable();
- /* Suspend system devices */
- error = sysdev_suspend(PMSG_FREEZE);
+ error = syscore_suspend();
if (error)
goto Enable_irqs;
} else
#endif
{
+ kexec_in_progress = true;
kernel_restart_prepare(NULL);
- printk(KERN_EMERG "Starting new kernel\n");
+ migrate_to_reboot_cpu();
+
+ /*
+ * migrate_to_reboot_cpu() disables CPU hotplug assuming that
+ * no further code needs to use CPU hotplug (which is true in
+ * the reboot case). However, the kexec path depends on using
+ * CPU hotplug again; so re-enable it here.
+ */
+ cpu_hotplug_enable();
+ pr_emerg("Starting new kernel\n");
machine_shutdown();
}
@@ -1540,12 +1699,12 @@ int kernel_kexec(void)
#ifdef CONFIG_KEXEC_JUMP
if (kexec_image->preserve_context) {
- sysdev_resume();
+ syscore_resume();
Enable_irqs:
local_irq_enable();
Enable_cpus:
enable_nonboot_cpus();
- dpm_resume_noirq(PMSG_RESTORE);
+ dpm_resume_start(PMSG_RESTORE);
Resume_devices:
dpm_resume_end(PMSG_RESTORE);
Resume_console:
@@ -1553,7 +1712,7 @@ int kernel_kexec(void)
thaw_processes();
Restore_console:
pm_restore_console();
- mutex_unlock(&pm_mutex);
+ unlock_system_sleep();
}
#endif
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-11-09 08:48:09 +0000