LinuxLists.cc - [PATCH 0/3] kexec/fadump: remove dependency with CONFIG_KEXEC and reuse crashkernel parameter for fadump

2016-11-10 11:57:29

Subject: [PATCH 0/3] kexec/fadump: remove dependency with CONFIG_KEXEC and reuse crashkernel parameter for fadump

2016-11-10 11:57:58

Subject: [PATCH 1/3] crash: move crashkernel parsing and vmcore related code under CONFIG_CRASH_CORE

Traditionally, kdump is used to save vmcore in case of a crash. Some
architectures like powerpc can save vmcore using architecture specific
support instead of kexec/kdump mechanism. Such architecture specific
support also needs to reserve memory, to be used by dump capture kernel.
crashkernel parameter can be a reused, for memory reservation, by such
architecture specific infrastructure.

But currently, code related to vmcoreinfo and parsing of crashkernel
parameter is built under CONFIG_KEXEC_CORE. This patch introduces
CONFIG_CRASH_CORE and moves the above mentioned code under this config,
allowing code reuse without dependency on CONFIG_KEXEC. While here,
removing the multiple definitions of append_elf_note() and final_note()
for one defined under CONFIG_CONFIG_CORE. There is no functional change
with this patch.

Signed-off-by: Hari Bathini <[email protected]>
---
arch/Kconfig | 4
arch/ia64/kernel/crash.c | 22 --
arch/powerpc/Kconfig | 10 -
arch/powerpc/include/asm/fadump.h | 2
arch/powerpc/kernel/crash.c | 2
arch/powerpc/kernel/fadump.c | 34 ---
arch/powerpc/kernel/setup-common.c | 5
include/linux/crash_core.h | 75 ++++++
include/linux/kexec.h | 63 -----
kernel/Makefile | 1
kernel/crash_core.c | 450 ++++++++++++++++++++++++++++++++++++
kernel/kexec_core.c | 435 -----------------------------------
12 files changed, 550 insertions(+), 553 deletions(-)
create mode 100644 include/linux/crash_core.h
create mode 100644 kernel/crash_core.c

diff --git a/arch/Kconfig b/arch/Kconfig
index 659bdd0..4ad34b9 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -2,7 +2,11 @@
# General architecture dependent options
#

+config CRASH_CORE
+ bool
+
config KEXEC_CORE
+ select CRASH_CORE
bool

config OPROFILE
diff --git a/arch/ia64/kernel/crash.c b/arch/ia64/kernel/crash.c
index 2955f35..75859a0 100644
--- a/arch/ia64/kernel/crash.c
+++ b/arch/ia64/kernel/crash.c
@@ -27,28 +27,6 @@ static int kdump_freeze_monarch;
static int kdump_on_init = 1;
static int kdump_on_fatal_mca = 1;

-static inline Elf64_Word
-*append_elf_note(Elf64_Word *buf, char *name, unsigned type, void *data,
- size_t data_len)
-{
- struct elf_note *note = (struct elf_note *)buf;
- note->n_namesz = strlen(name) + 1;
- note->n_descsz = data_len;
- note->n_type = type;
- buf += (sizeof(*note) + 3)/4;
- memcpy(buf, name, note->n_namesz);
- buf += (note->n_namesz + 3)/4;
- memcpy(buf, data, data_len);
- buf += (data_len + 3)/4;
- return buf;
-}
-
-static void
-final_note(void *buf)
-{
- memset(buf, 0, sizeof(struct elf_note));
-}
-
extern void ia64_dump_cpu_regs(void *);

static DEFINE_PER_CPU(struct elf_prstatus, elf_prstatus);
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 65fba4c..644703f 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -479,21 +479,23 @@ config RELOCATABLE
load address of the kernel (eg. u-boot/mkimage).

config CRASH_DUMP
- bool "Build a kdump crash kernel"
+ bool "Build a dump capture kernel"
depends on PPC64 || 6xx || FSL_BOOKE || (44x && !SMP)
select RELOCATABLE if (PPC64 && !COMPILE_TEST) || 44x || FSL_BOOKE
help
- Build a kernel suitable for use as a kdump capture kernel.
+ Build a kernel suitable for use as a dump capture kernel.
The same kernel binary can be used as production kernel and dump
capture kernel.

config FA_DUMP
bool "Firmware-assisted dump"
- depends on PPC64 && PPC_RTAS && CRASH_DUMP && KEXEC
+ depends on PPC64 && PPC_RTAS
+ select CRASH_CORE
+ select CRASH_DUMP
help
A robust mechanism to get reliable kernel crash dump with
assistance from firmware. This approach does not use kexec,
- instead firmware assists in booting the kdump kernel
+ instead firmware assists in booting the capture kernel
while preserving memory contents. Firmware-assisted dump
is meant to be a kdump replacement offering robustness and
speed not possible without system firmware assistance.
diff --git a/arch/powerpc/include/asm/fadump.h b/arch/powerpc/include/asm/fadump.h
index 0031806..60b9108 100644
--- a/arch/powerpc/include/asm/fadump.h
+++ b/arch/powerpc/include/asm/fadump.h
@@ -73,6 +73,8 @@
reg_entry++; \
})

+extern int crashing_cpu;
+
/* Kernel Dump section info */
struct fadump_section {
__be32 request_flag;
diff --git a/arch/powerpc/kernel/crash.c b/arch/powerpc/kernel/crash.c
index 47b63de..cbabb5a 100644
--- a/arch/powerpc/kernel/crash.c
+++ b/arch/powerpc/kernel/crash.c
@@ -43,8 +43,6 @@
#define IPI_TIMEOUT 10000
#define REAL_MODE_TIMEOUT 10000

-/* This keeps a track of which one is the crashing cpu. */
-int crashing_cpu = -1;
static int time_to_dump;

#define CRASH_HANDLER_MAX 3
diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
index 8f0c7c5..db0b339 100644
--- a/arch/powerpc/kernel/fadump.c
+++ b/arch/powerpc/kernel/fadump.c
@@ -486,34 +486,6 @@ fadump_read_registers(struct fadump_reg_entry *reg_entry, struct pt_regs *regs)
return reg_entry;
}

-static u32 *fadump_append_elf_note(u32 *buf, char *name, unsigned type,
- void *data, size_t data_len)
-{
- struct elf_note note;
-
- note.n_namesz = strlen(name) + 1;
- note.n_descsz = data_len;
- note.n_type = type;
- memcpy(buf, &note, sizeof(note));
- buf += (sizeof(note) + 3)/4;
- memcpy(buf, name, note.n_namesz);
- buf += (note.n_namesz + 3)/4;
- memcpy(buf, data, note.n_descsz);
- buf += (note.n_descsz + 3)/4;
-
- return buf;
-}
-
-static void fadump_final_note(u32 *buf)
-{
- struct elf_note note;
-
- note.n_namesz = 0;
- note.n_descsz = 0;
- note.n_type = 0;
- memcpy(buf, &note, sizeof(note));
-}
-
static u32 *fadump_regs_to_elf_notes(u32 *buf, struct pt_regs *regs)
{
struct elf_prstatus prstatus;
@@ -524,8 +496,8 @@ static u32 *fadump_regs_to_elf_notes(u32 *buf, struct pt_regs *regs)
* prstatus.pr_pid = ????
*/
elf_core_copy_kernel_regs(&prstatus.pr_reg, regs);
- buf = fadump_append_elf_note(buf, KEXEC_CORE_NOTE_NAME, NT_PRSTATUS,
- &prstatus, sizeof(prstatus));
+ buf = append_elf_note(buf, CRASH_CORE_NOTE_NAME, NT_PRSTATUS,
+ &prstatus, sizeof(prstatus));
return buf;
}

@@ -666,7 +638,7 @@ static int __init fadump_build_cpu_notes(const struct fadump_mem_struct *fdm)
note_buf = fadump_regs_to_elf_notes(note_buf, &regs);
}
}
- fadump_final_note(note_buf);
+ final_note(note_buf);

if (fdh) {
pr_debug("Updating elfcore header (%llx) with cpu notes\n",
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index 270ee30..d322527 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -116,6 +116,11 @@ int ppc_do_canonicalize_irqs;
EXPORT_SYMBOL(ppc_do_canonicalize_irqs);
#endif

+#if defined(CONFIG_KEXEC) || defined(CONFIG_FA_DUMP)
+/* This keeps a track of which one is the crashing cpu. */
+int crashing_cpu = -1;
+#endif
+
/* also used by kexec */
void machine_shutdown(void)
{
diff --git a/include/linux/crash_core.h b/include/linux/crash_core.h
new file mode 100644
index 0000000..2ae20b1
--- /dev/null
+++ b/include/linux/crash_core.h
@@ -0,0 +1,75 @@
+#ifndef LINUX_CRASH_CORE_H
+#define LINUX_CRASH_CORE_H
+
+#include <linux/linkage.h>
+#include <linux/elfcore.h>
+#include <linux/elf.h>
+
+#define CRASH_CORE_NOTE_NAME "CORE"
+#define CRASH_CORE_NOTE_HEAD_BYTES ALIGN(sizeof(struct elf_note), 4)
+#define CRASH_CORE_NOTE_NAME_BYTES ALIGN(sizeof(CRASH_CORE_NOTE_NAME), 4)
+#define CRASH_CORE_NOTE_DESC_BYTES ALIGN(sizeof(struct elf_prstatus), 4)
+
+#define CRASH_CORE_NOTE_BYTES ((CRASH_CORE_NOTE_HEAD_BYTES * 2) + \
+ CRASH_CORE_NOTE_NAME_BYTES + \
+ CRASH_CORE_NOTE_DESC_BYTES)
+
+#define VMCOREINFO_BYTES (4096)
+#define VMCOREINFO_NOTE_NAME "VMCOREINFO"
+#define VMCOREINFO_NOTE_NAME_BYTES ALIGN(sizeof(VMCOREINFO_NOTE_NAME), 4)
+#define VMCOREINFO_NOTE_SIZE ((CRASH_CORE_NOTE_HEAD_BYTES * 2) + \
+ VMCOREINFO_NOTE_NAME_BYTES + \
+ VMCOREINFO_BYTES)
+
+typedef u32 note_buf_t[CRASH_CORE_NOTE_BYTES/4];
+
+void crash_save_vmcoreinfo(void);
+void arch_crash_save_vmcoreinfo(void);
+__printf(1, 2)
+void vmcoreinfo_append_str(const char *fmt, ...);
+phys_addr_t paddr_vmcoreinfo_note(void);
+
+#define VMCOREINFO_OSRELEASE(value) \
+ vmcoreinfo_append_str("OSRELEASE=%s\n", value)
+#define VMCOREINFO_PAGESIZE(value) \
+ vmcoreinfo_append_str("PAGESIZE=%ld\n", value)
+#define VMCOREINFO_SYMBOL(name) \
+ vmcoreinfo_append_str("SYMBOL(%s)=%lx\n", #name, (unsigned long)&name)
+#define VMCOREINFO_SIZE(name) \
+ vmcoreinfo_append_str("SIZE(%s)=%lu\n", #name, \
+ (unsigned long)sizeof(name))
+#define VMCOREINFO_STRUCT_SIZE(name) \
+ vmcoreinfo_append_str("SIZE(%s)=%lu\n", #name, \
+ (unsigned long)sizeof(struct name))
+#define VMCOREINFO_OFFSET(name, field) \
+ vmcoreinfo_append_str("OFFSET(%s.%s)=%lu\n", #name, #field, \
+ (unsigned long)offsetof(struct name, field))
+#define VMCOREINFO_LENGTH(name, value) \
+ vmcoreinfo_append_str("LENGTH(%s)=%lu\n", #name, (unsigned long)value)
+#define VMCOREINFO_NUMBER(name) \
+ vmcoreinfo_append_str("NUMBER(%s)=%ld\n", #name, (long)name)
+#define VMCOREINFO_CONFIG(name) \
+ vmcoreinfo_append_str("CONFIG_%s=y\n", #name)
+#define VMCOREINFO_PAGE_OFFSET(value) \
+ vmcoreinfo_append_str("PAGE_OFFSET=%lx\n", (unsigned long)value)
+#define VMCOREINFO_VMALLOC_START(value) \
+ vmcoreinfo_append_str("VMALLOC_START=%lx\n", (unsigned long)value)
+#define VMCOREINFO_VMEMMAP_START(value) \
+ vmcoreinfo_append_str("VMEMMAP_START=%lx\n", (unsigned long)value)
+
+extern u32 vmcoreinfo_note[VMCOREINFO_NOTE_SIZE/4];
+extern size_t vmcoreinfo_size;
+extern size_t vmcoreinfo_max_size;
+
+u32 *append_elf_note(u32 *buf, char *name, unsigned int type,
+ void *data, size_t data_len);
+void final_note(u32 *buf);
+
+int __init parse_crashkernel(char *cmdline, unsigned long long system_ram,
+ unsigned long long *crash_size, unsigned long long *crash_base);
+int parse_crashkernel_high(char *cmdline, unsigned long long system_ram,
+ unsigned long long *crash_size, unsigned long long *crash_base);
+int parse_crashkernel_low(char *cmdline, unsigned long long system_ram,
+ unsigned long long *crash_size, unsigned long long *crash_base);
+
+#endif /* LINUX_CRASH_CORE_H */
diff --git a/include/linux/kexec.h b/include/linux/kexec.h
index 406c33d..aa3c747 100644
--- a/include/linux/kexec.h
+++ b/include/linux/kexec.h
@@ -14,17 +14,15 @@

#if !defined(__ASSEMBLY__)

+#include <linux/crash_core.h>
#include <asm/io.h>

#include <uapi/linux/kexec.h>

#ifdef CONFIG_KEXEC_CORE
#include <linux/list.h>
-#include <linux/linkage.h>
#include <linux/compat.h>
#include <linux/ioport.h>
-#include <linux/elfcore.h>
-#include <linux/elf.h>
#include <linux/module.h>
#include <asm/kexec.h>

@@ -62,19 +60,15 @@
#define KEXEC_CRASH_MEM_ALIGN PAGE_SIZE
#endif

-#define KEXEC_NOTE_HEAD_BYTES ALIGN(sizeof(struct elf_note), 4)
-#define KEXEC_CORE_NOTE_NAME "CORE"
-#define KEXEC_CORE_NOTE_NAME_BYTES ALIGN(sizeof(KEXEC_CORE_NOTE_NAME), 4)
-#define KEXEC_CORE_NOTE_DESC_BYTES ALIGN(sizeof(struct elf_prstatus), 4)
+#define KEXEC_CORE_NOTE_NAME CRASH_CORE_NOTE_NAME
+
/*
* The per-cpu notes area is a list of notes terminated by a "NULL"
* note header. For kdump, the code in vmcore.c runs in the context
* of the second kernel to combine them into one note.
*/
#ifndef KEXEC_NOTE_BYTES
-#define KEXEC_NOTE_BYTES ( (KEXEC_NOTE_HEAD_BYTES * 2) + \
- KEXEC_CORE_NOTE_NAME_BYTES + \
- KEXEC_CORE_NOTE_DESC_BYTES )
+#define KEXEC_NOTE_BYTES CRASH_CORE_NOTE_BYTES
#endif

/*
@@ -232,39 +226,6 @@ extern void crash_kexec(struct pt_regs *);
int kexec_should_crash(struct task_struct *);
int kexec_crash_loaded(void);
void crash_save_cpu(struct pt_regs *regs, int cpu);
-void crash_save_vmcoreinfo(void);
-void arch_crash_save_vmcoreinfo(void);
-__printf(1, 2)
-void vmcoreinfo_append_str(const char *fmt, ...);
-phys_addr_t paddr_vmcoreinfo_note(void);
-
-#define VMCOREINFO_OSRELEASE(value) \
- vmcoreinfo_append_str("OSRELEASE=%s\n", value)
-#define VMCOREINFO_PAGESIZE(value) \
- vmcoreinfo_append_str("PAGESIZE=%ld\n", value)
-#define VMCOREINFO_SYMBOL(name) \
- vmcoreinfo_append_str("SYMBOL(%s)=%lx\n", #name, (unsigned long)&name)
-#define VMCOREINFO_SIZE(name) \
- vmcoreinfo_append_str("SIZE(%s)=%lu\n", #name, \
- (unsigned long)sizeof(name))
-#define VMCOREINFO_STRUCT_SIZE(name) \
- vmcoreinfo_append_str("SIZE(%s)=%lu\n", #name, \
- (unsigned long)sizeof(struct name))
-#define VMCOREINFO_OFFSET(name, field) \
- vmcoreinfo_append_str("OFFSET(%s.%s)=%lu\n", #name, #field, \
- (unsigned long)offsetof(struct name, field))
-#define VMCOREINFO_LENGTH(name, value) \
- vmcoreinfo_append_str("LENGTH(%s)=%lu\n", #name, (unsigned long)value)
-#define VMCOREINFO_NUMBER(name) \
- vmcoreinfo_append_str("NUMBER(%s)=%ld\n", #name, (long)name)
-#define VMCOREINFO_CONFIG(name) \
- vmcoreinfo_append_str("CONFIG_%s=y\n", #name)
-#define VMCOREINFO_PAGE_OFFSET(value) \
- vmcoreinfo_append_str("PAGE_OFFSET=%lx\n", (unsigned long)value)
-#define VMCOREINFO_VMALLOC_START(value) \
- vmcoreinfo_append_str("VMALLOC_START=%lx\n", (unsigned long)value)
-#define VMCOREINFO_VMEMMAP_START(value) \
- vmcoreinfo_append_str("VMEMMAP_START=%lx\n", (unsigned long)value)

extern struct kimage *kexec_image;
extern struct kimage *kexec_crash_image;
@@ -285,31 +246,15 @@ extern int kexec_load_disabled;
#define KEXEC_FILE_FLAGS (KEXEC_FILE_UNLOAD | KEXEC_FILE_ON_CRASH | \
KEXEC_FILE_NO_INITRAMFS)

-#define VMCOREINFO_BYTES (4096)
-#define VMCOREINFO_NOTE_NAME "VMCOREINFO"
-#define VMCOREINFO_NOTE_NAME_BYTES ALIGN(sizeof(VMCOREINFO_NOTE_NAME), 4)
-#define VMCOREINFO_NOTE_SIZE (KEXEC_NOTE_HEAD_BYTES*2 + VMCOREINFO_BYTES \
- + VMCOREINFO_NOTE_NAME_BYTES)
-
/* Location of a reserved region to hold the crash kernel.
*/
extern struct resource crashk_res;
extern struct resource crashk_low_res;
-typedef u32 note_buf_t[KEXEC_NOTE_BYTES/4];
extern note_buf_t __percpu *crash_notes;
-extern u32 vmcoreinfo_note[VMCOREINFO_NOTE_SIZE/4];
-extern size_t vmcoreinfo_size;
-extern size_t vmcoreinfo_max_size;

/* flag to track if kexec reboot is in progress */
extern bool kexec_in_progress;

-int __init parse_crashkernel(char *cmdline, unsigned long long system_ram,
- unsigned long long *crash_size, unsigned long long *crash_base);
-int parse_crashkernel_high(char *cmdline, unsigned long long system_ram,
- unsigned long long *crash_size, unsigned long long *crash_base);
-int parse_crashkernel_low(char *cmdline, unsigned long long system_ram,
- unsigned long long *crash_size, unsigned long long *crash_base);
int crash_shrink_memory(unsigned long new_size);
size_t crash_get_memory_size(void);
void crash_free_reserved_phys_range(unsigned long begin, unsigned long end);
diff --git a/kernel/Makefile b/kernel/Makefile
index eb26e12c..017e092 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -59,6 +59,7 @@ obj-$(CONFIG_MODULES) += module.o
obj-$(CONFIG_MODULE_SIG) += module_signing.o
obj-$(CONFIG_KALLSYMS) += kallsyms.o
obj-$(CONFIG_BSD_PROCESS_ACCT) += acct.o
+obj-$(CONFIG_CRASH_CORE) += crash_core.o
obj-$(CONFIG_KEXEC_CORE) += kexec_core.o
obj-$(CONFIG_KEXEC) += kexec.o
obj-$(CONFIG_KEXEC_FILE) += kexec_file.o
diff --git a/kernel/crash_core.c b/kernel/crash_core.c
new file mode 100644
index 0000000..9223976
--- /dev/null
+++ b/kernel/crash_core.c
@@ -0,0 +1,450 @@
+/*
+ * crash.c - kernel crash support code.
+ * Copyright (C) 2002-2004 Eric Biederman <[email protected]>
+ *
+ * This source code is licensed under the GNU General Public License,
+ * Version 2. See the file COPYING for more details.
+ */
+
+#include <linux/crash_core.h>
+#include <linux/utsname.h>
+#include <linux/vmalloc.h>
+
+#include <asm/page.h>
+#include <asm/sections.h>
+
+/* vmcoreinfo stuff */
+static unsigned char vmcoreinfo_data[VMCOREINFO_BYTES];
+u32 vmcoreinfo_note[VMCOREINFO_NOTE_SIZE/4];
+size_t vmcoreinfo_size;
+size_t vmcoreinfo_max_size = sizeof(vmcoreinfo_data);
+
+/*
+ * parsing the "crashkernel" commandline
+ *
+ * this code is intended to be called from architecture specific code
+ */
+
+
+/*
+ * This function parses command lines in the format
+ *
+ * crashkernel=ramsize-range:size[,...][@offset]
+ *
+ * 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)
+{
+ char *cur = cmdline, *tmp;
+
+ /* for each entry of the comma-separated list */
+ do {
+ unsigned long long start, end = ULLONG_MAX, size;
+
+ /* get the start of the range */
+ start = memparse(cur, &tmp);
+ if (cur == tmp) {
+ pr_warn("crashkernel: Memory value expected\n");
+ return -EINVAL;
+ }
+ cur = tmp;
+ if (*cur != '-') {
+ pr_warn("crashkernel: '-' expected\n");
+ return -EINVAL;
+ }
+ cur++;
+
+ /* if no ':' is here, than we read the end */
+ if (*cur != ':') {
+ end = memparse(cur, &tmp);
+ if (cur == tmp) {
+ pr_warn("crashkernel: Memory value expected\n");
+ return -EINVAL;
+ }
+ cur = tmp;
+ if (end <= start) {
+ pr_warn("crashkernel: end <= start\n");
+ return -EINVAL;
+ }
+ }
+
+ if (*cur != ':') {
+ pr_warn("crashkernel: ':' expected\n");
+ return -EINVAL;
+ }
+ cur++;
+
+ size = memparse(cur, &tmp);
+ if (cur == tmp) {
+ pr_warn("Memory value expected\n");
+ return -EINVAL;
+ }
+ cur = tmp;
+ if (size >= system_ram) {
+ pr_warn("crashkernel: invalid size\n");
+ return -EINVAL;
+ }
+
+ /* match ? */
+ if (system_ram >= start && system_ram < end) {
+ *crash_size = size;
+ break;
+ }
+ } while (*cur++ == ',');
+
+ if (*crash_size > 0) {
+ while (*cur && *cur != ' ' && *cur != '@')
+ cur++;
+ if (*cur == '@') {
+ cur++;
+ *crash_base = memparse(cur, &tmp);
+ if (cur == tmp) {
+ pr_warn("Memory value expected after '@'\n");
+ return -EINVAL;
+ }
+ }
+ }
+
+ return 0;
+}
+
+/*
+ * That function parses "simple" (old) crashkernel command lines like
+ *
+ * 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)
+{
+ char *cur = cmdline;
+
+ *crash_size = memparse(cmdline, &cur);
+ if (cmdline == cur) {
+ 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: %c\n", *cur);
+ 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 parses "suffix" crashkernel command lines like
+ *
+ * crashkernel=size,[high|low]
+ *
+ * It returns 0 on success and -EINVAL on failure.
+ */
+static int __init parse_crashkernel_suffix(char *cmdline,
+ unsigned long long *crash_size,
+ 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: %c\n", *cur);
+ return -EINVAL;
+ }
+ cur += strlen(suffix);
+ if (*cur != ' ' && *cur != '\0') {
+ pr_warn("crashkernel: unrecognized char: %c\n", *cur);
+ 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,
+ const char *name,
+ const char *suffix)
+{
+ char *first_colon, *first_space;
+ char *ck_cmdline;
+
+ BUG_ON(!crash_size || !crash_base);
+ *crash_size = 0;
+ *crash_base = 0;
+
+ ck_cmdline = get_last_crashkernel(cmdline, name, suffix);
+
+ if (!ck_cmdline)
+ return -EINVAL;
+
+ ck_cmdline += strlen(name);
+
+ if (suffix)
+ return parse_crashkernel_suffix(ck_cmdline, crash_size,
+ suffix);
+ /*
+ * if the commandline contains a ':', then that's the extended
+ * syntax -- if not, it must be the classic syntax
+ */
+ first_colon = strchr(ck_cmdline, ':');
+ first_space = strchr(ck_cmdline, ' ');
+ if (first_colon && (!first_space || first_colon < first_space))
+ return parse_crashkernel_mem(ck_cmdline, system_ram,
+ crash_size, crash_base);
+
+ 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]);
+}
+
+u32 *append_elf_note(u32 *buf, char *name, unsigned int type,
+ void *data, size_t data_len)
+{
+ struct elf_note note;
+
+ note.n_namesz = strlen(name) + 1;
+ note.n_descsz = data_len;
+ note.n_type = type;
+ memcpy(buf, &note, sizeof(note));
+ buf += (sizeof(note) + 3)/4;
+ memcpy(buf, name, note.n_namesz);
+ buf += (note.n_namesz + 3)/4;
+ memcpy(buf, data, note.n_descsz);
+ buf += (note.n_descsz + 3)/4;
+
+ return buf;
+}
+
+void final_note(u32 *buf)
+{
+ struct elf_note note;
+
+ note.n_namesz = 0;
+ note.n_descsz = 0;
+ note.n_type = 0;
+ memcpy(buf, &note, sizeof(note));
+}
+
+static void update_vmcoreinfo_note(void)
+{
+ u32 *buf = vmcoreinfo_note;
+
+ if (!vmcoreinfo_size)
+ return;
+ 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];
+ size_t r;
+
+ va_start(args, fmt);
+ r = vscnprintf(buf, sizeof(buf), fmt, args);
+ va_end(args);
+
+ r = min(r, vmcoreinfo_max_size - vmcoreinfo_size);
+
+ memcpy(&vmcoreinfo_data[vmcoreinfo_size], buf, r);
+
+ vmcoreinfo_size += r;
+}
+
+/*
+ * provide an empty default implementation here -- architecture
+ * code may override this
+ */
+void __weak arch_crash_save_vmcoreinfo(void)
+{}
+
+phys_addr_t __weak paddr_vmcoreinfo_note(void)
+{
+ return __pa((unsigned long)(char *)&vmcoreinfo_note);
+}
+
+static int __init crash_save_vmcoreinfo_init(void)
+{
+ VMCOREINFO_OSRELEASE(init_uts_ns.name.release);
+ VMCOREINFO_PAGESIZE(PAGE_SIZE);
+
+ VMCOREINFO_SYMBOL(init_uts_ns);
+ VMCOREINFO_SYMBOL(node_online_map);
+#ifdef CONFIG_MMU
+ VMCOREINFO_SYMBOL(swapper_pg_dir);
+#endif
+ VMCOREINFO_SYMBOL(_stext);
+ VMCOREINFO_SYMBOL(vmap_area_list);
+
+#ifndef CONFIG_NEED_MULTIPLE_NODES
+ VMCOREINFO_SYMBOL(mem_map);
+ VMCOREINFO_SYMBOL(contig_page_data);
+#endif
+#ifdef CONFIG_SPARSEMEM
+ VMCOREINFO_SYMBOL(mem_section);
+ VMCOREINFO_LENGTH(mem_section, NR_SECTION_ROOTS);
+ VMCOREINFO_STRUCT_SIZE(mem_section);
+ VMCOREINFO_OFFSET(mem_section, section_mem_map);
+#endif
+ VMCOREINFO_STRUCT_SIZE(page);
+ VMCOREINFO_STRUCT_SIZE(pglist_data);
+ VMCOREINFO_STRUCT_SIZE(zone);
+ VMCOREINFO_STRUCT_SIZE(free_area);
+ VMCOREINFO_STRUCT_SIZE(list_head);
+ VMCOREINFO_SIZE(nodemask_t);
+ VMCOREINFO_OFFSET(page, flags);
+ VMCOREINFO_OFFSET(page, _refcount);
+ VMCOREINFO_OFFSET(page, mapping);
+ VMCOREINFO_OFFSET(page, lru);
+ VMCOREINFO_OFFSET(page, _mapcount);
+ VMCOREINFO_OFFSET(page, private);
+ VMCOREINFO_OFFSET(page, compound_dtor);
+ VMCOREINFO_OFFSET(page, compound_order);
+ VMCOREINFO_OFFSET(page, compound_head);
+ VMCOREINFO_OFFSET(pglist_data, node_zones);
+ VMCOREINFO_OFFSET(pglist_data, nr_zones);
+#ifdef CONFIG_FLAT_NODE_MEM_MAP
+ VMCOREINFO_OFFSET(pglist_data, node_mem_map);
+#endif
+ VMCOREINFO_OFFSET(pglist_data, node_start_pfn);
+ VMCOREINFO_OFFSET(pglist_data, node_spanned_pages);
+ VMCOREINFO_OFFSET(pglist_data, node_id);
+ VMCOREINFO_OFFSET(zone, free_area);
+ VMCOREINFO_OFFSET(zone, vm_stat);
+ VMCOREINFO_OFFSET(zone, spanned_pages);
+ VMCOREINFO_OFFSET(free_area, free_list);
+ VMCOREINFO_OFFSET(list_head, next);
+ VMCOREINFO_OFFSET(list_head, prev);
+ VMCOREINFO_OFFSET(vmap_area, va_start);
+ VMCOREINFO_OFFSET(vmap_area, list);
+ VMCOREINFO_LENGTH(zone.free_area, MAX_ORDER);
+#ifdef CONFIG_KEXEC
+ log_buf_kexec_setup();
+#endif
+ VMCOREINFO_LENGTH(free_area.free_list, MIGRATE_TYPES);
+ VMCOREINFO_NUMBER(NR_FREE_PAGES);
+ 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_X86
+ VMCOREINFO_NUMBER(KERNEL_IMAGE_SIZE);
+#endif
+#ifdef CONFIG_HUGETLB_PAGE
+ VMCOREINFO_NUMBER(HUGETLB_PAGE_DTOR);
+#endif
+
+ arch_crash_save_vmcoreinfo();
+ update_vmcoreinfo_note();
+
+ return 0;
+}
+
+subsys_initcall(crash_save_vmcoreinfo_init);
diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
index 5616755..596cb32 100644
--- a/kernel/kexec_core.c
+++ b/kernel/kexec_core.c
@@ -51,12 +51,6 @@ DEFINE_MUTEX(kexec_mutex);
/* Per cpu memory for storing cpu states in case of system crash. */
note_buf_t __percpu *crash_notes;

-/* vmcoreinfo stuff */
-static unsigned char vmcoreinfo_data[VMCOREINFO_BYTES];
-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;

@@ -994,34 +988,6 @@ int crash_shrink_memory(unsigned long new_size)
return ret;
}

-static u32 *append_elf_note(u32 *buf, char *name, unsigned type, void *data,
- size_t data_len)
-{
- struct elf_note note;
-
- note.n_namesz = strlen(name) + 1;
- note.n_descsz = data_len;
- note.n_type = type;
- memcpy(buf, &note, sizeof(note));
- buf += (sizeof(note) + 3)/4;
- memcpy(buf, name, note.n_namesz);
- buf += (note.n_namesz + 3)/4;
- memcpy(buf, data, note.n_descsz);
- buf += (note.n_descsz + 3)/4;
-
- return buf;
-}
-
-static void final_note(u32 *buf)
-{
- struct elf_note note;
-
- note.n_namesz = 0;
- note.n_descsz = 0;
- note.n_type = 0;
- memcpy(buf, &note, sizeof(note));
-}
-
void crash_save_cpu(struct pt_regs *regs, int cpu)
{
struct elf_prstatus prstatus;
@@ -1081,407 +1047,6 @@ static int __init crash_notes_memory_init(void)
}
subsys_initcall(crash_notes_memory_init);

-
-/*
- * parsing the "crashkernel" commandline
- *
- * this code is intended to be called from architecture specific code
- */
-
-
-/*
- * This function parses command lines in the format
- *
- * crashkernel=ramsize-range:size[,...][@offset]
- *
- * 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)
-{
- char *cur = cmdline, *tmp;
-
- /* for each entry of the comma-separated list */
- do {
- unsigned long long start, end = ULLONG_MAX, size;
-
- /* get the start of the range */
- start = memparse(cur, &tmp);
- if (cur == tmp) {
- pr_warn("crashkernel: Memory value expected\n");
- return -EINVAL;
- }
- cur = tmp;
- if (*cur != '-') {
- pr_warn("crashkernel: '-' expected\n");
- return -EINVAL;
- }
- cur++;
-
- /* if no ':' is here, than we read the end */
- if (*cur != ':') {
- end = memparse(cur, &tmp);
- if (cur == tmp) {
- pr_warn("crashkernel: Memory value expected\n");
- return -EINVAL;
- }
- cur = tmp;
- if (end <= start) {
- pr_warn("crashkernel: end <= start\n");
- return -EINVAL;
- }
- }
-
- if (*cur != ':') {
- pr_warn("crashkernel: ':' expected\n");
- return -EINVAL;
- }
- cur++;
-
- size = memparse(cur, &tmp);
- if (cur == tmp) {
- pr_warn("Memory value expected\n");
- return -EINVAL;
- }
- cur = tmp;
- if (size >= system_ram) {
- pr_warn("crashkernel: invalid size\n");
- return -EINVAL;
- }
-
- /* match ? */
- if (system_ram >= start && system_ram < end) {
- *crash_size = size;
- break;
- }
- } while (*cur++ == ',');
-
- if (*crash_size > 0) {
- while (*cur && *cur != ' ' && *cur != '@')
- cur++;
- if (*cur == '@') {
- cur++;
- *crash_base = memparse(cur, &tmp);
- if (cur == tmp) {
- pr_warn("Memory value expected after '@'\n");
- return -EINVAL;
- }
- }
- }
-
- return 0;
-}
-
-/*
- * That function parses "simple" (old) crashkernel command lines like
- *
- * 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)
-{
- char *cur = cmdline;
-
- *crash_size = memparse(cmdline, &cur);
- if (cmdline == cur) {
- 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: %c\n", *cur);
- 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 parses "suffix" crashkernel command lines like
- *
- * crashkernel=size,[high|low]
- *
- * It returns 0 on success and -EINVAL on failure.
- */
-static int __init parse_crashkernel_suffix(char *cmdline,
- unsigned long long *crash_size,
- 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: %c\n", *cur);
- return -EINVAL;
- }
- cur += strlen(suffix);
- if (*cur != ' ' && *cur != '\0') {
- pr_warn("crashkernel: unrecognized char: %c\n", *cur);
- 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,
- const char *name,
- const char *suffix)
-{
- char *first_colon, *first_space;
- char *ck_cmdline;
-
- BUG_ON(!crash_size || !crash_base);
- *crash_size = 0;
- *crash_base = 0;
-
- ck_cmdline = get_last_crashkernel(cmdline, name, suffix);
-
- if (!ck_cmdline)
- return -EINVAL;
-
- ck_cmdline += strlen(name);
-
- if (suffix)
- return parse_crashkernel_suffix(ck_cmdline, crash_size,
- suffix);
- /*
- * if the commandline contains a ':', then that's the extended
- * syntax -- if not, it must be the classic syntax
- */
- first_colon = strchr(ck_cmdline, ':');
- first_space = strchr(ck_cmdline, ' ');
- if (first_colon && (!first_space || first_colon < first_space))
- return parse_crashkernel_mem(ck_cmdline, system_ram,
- crash_size, crash_base);
-
- 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]);
-}
-
-static void update_vmcoreinfo_note(void)
-{
- u32 *buf = vmcoreinfo_note;
-
- if (!vmcoreinfo_size)
- return;
- 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];
- size_t r;
-
- va_start(args, fmt);
- r = vscnprintf(buf, sizeof(buf), fmt, args);
- va_end(args);
-
- r = min(r, vmcoreinfo_max_size - vmcoreinfo_size);
-
- memcpy(&vmcoreinfo_data[vmcoreinfo_size], buf, r);
-
- vmcoreinfo_size += r;
-}
-
-/*
- * provide an empty default implementation here -- architecture
- * code may override this
- */
-void __weak arch_crash_save_vmcoreinfo(void)
-{}
-
-phys_addr_t __weak paddr_vmcoreinfo_note(void)
-{
- return __pa((unsigned long)(char *)&vmcoreinfo_note);
-}
-
-static int __init crash_save_vmcoreinfo_init(void)
-{
- VMCOREINFO_OSRELEASE(init_uts_ns.name.release);
- VMCOREINFO_PAGESIZE(PAGE_SIZE);
-
- VMCOREINFO_SYMBOL(init_uts_ns);
- VMCOREINFO_SYMBOL(node_online_map);
-#ifdef CONFIG_MMU
- VMCOREINFO_SYMBOL(swapper_pg_dir);
-#endif
- VMCOREINFO_SYMBOL(_stext);
- VMCOREINFO_SYMBOL(vmap_area_list);
-
-#ifndef CONFIG_NEED_MULTIPLE_NODES
- VMCOREINFO_SYMBOL(mem_map);
- VMCOREINFO_SYMBOL(contig_page_data);
-#endif
-#ifdef CONFIG_SPARSEMEM
- VMCOREINFO_SYMBOL(mem_section);
- VMCOREINFO_LENGTH(mem_section, NR_SECTION_ROOTS);
- VMCOREINFO_STRUCT_SIZE(mem_section);
- VMCOREINFO_OFFSET(mem_section, section_mem_map);
-#endif
- VMCOREINFO_STRUCT_SIZE(page);
- VMCOREINFO_STRUCT_SIZE(pglist_data);
- VMCOREINFO_STRUCT_SIZE(zone);
- VMCOREINFO_STRUCT_SIZE(free_area);
- VMCOREINFO_STRUCT_SIZE(list_head);
- VMCOREINFO_SIZE(nodemask_t);
- VMCOREINFO_OFFSET(page, flags);
- VMCOREINFO_OFFSET(page, _refcount);
- VMCOREINFO_OFFSET(page, mapping);
- VMCOREINFO_OFFSET(page, lru);
- VMCOREINFO_OFFSET(page, _mapcount);
- VMCOREINFO_OFFSET(page, private);
- VMCOREINFO_OFFSET(page, compound_dtor);
- VMCOREINFO_OFFSET(page, compound_order);
- VMCOREINFO_OFFSET(page, compound_head);
- VMCOREINFO_OFFSET(pglist_data, node_zones);
- VMCOREINFO_OFFSET(pglist_data, nr_zones);
-#ifdef CONFIG_FLAT_NODE_MEM_MAP
- VMCOREINFO_OFFSET(pglist_data, node_mem_map);
-#endif
- VMCOREINFO_OFFSET(pglist_data, node_start_pfn);
- VMCOREINFO_OFFSET(pglist_data, node_spanned_pages);
- VMCOREINFO_OFFSET(pglist_data, node_id);
- VMCOREINFO_OFFSET(zone, free_area);
- VMCOREINFO_OFFSET(zone, vm_stat);
- VMCOREINFO_OFFSET(zone, spanned_pages);
- VMCOREINFO_OFFSET(free_area, free_list);
- VMCOREINFO_OFFSET(list_head, next);
- VMCOREINFO_OFFSET(list_head, prev);
- 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);
- VMCOREINFO_NUMBER(NR_FREE_PAGES);
- 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_X86
- VMCOREINFO_NUMBER(KERNEL_IMAGE_SIZE);
-#endif
-#ifdef CONFIG_HUGETLB_PAGE
- VMCOREINFO_NUMBER(HUGETLB_PAGE_DTOR);
-#endif
-
- arch_crash_save_vmcoreinfo();
- update_vmcoreinfo_note();
-
- return 0;
-}
-
-subsys_initcall(crash_save_vmcoreinfo_init);
-
/*
* Move into place and start executing a preloaded standalone
* executable. If nothing was preloaded return an error.

2016-11-10 11:58:13

by Hari Bathini

[permalink] [raw]

Subject: [PATCH 2/3] powerpc/fadump: reuse crashkernel parameter for fadump memory reservation

fadump supports specifying memory to reserve for fadump's crash kernel
with fadump_reserve_mem kernel parameter. This parameter currently
supports passing a fixed memory size, like fadump_reserve_mem=<size>
only. This patch aims to add support for other syntaxes like range-based
memory size <range1>:<size1>[,<range2>:<size2>,<range3>:<size3>,...]
which allows using the same parameter to boot the kernel with different
system RAM sizes.

As crashkernel parameter already supports the above mentioned syntaxes,
this patch removes fadump_reserve_mem parameter and reuses crashkernel
parameter instead, to specify memory for fadump's crash kernel memory
reservation as well. If any offset is provided in crashkernel parameter,
it will be ignored in case of fadump, as fadump reserves memory at end
of RAM.

Advantages using crashkernel parameter instead of fadump_reserve_mem
parameter are one less kernel parameter overall, code reuse and support
for multiple syntaxes to specify memory.

Suggested-by: Dave Young <[email protected]>
Signed-off-by: Hari Bathini <[email protected]>
---
arch/powerpc/kernel/fadump.c | 23 ++++++++++-------------
1 file changed, 10 insertions(+), 13 deletions(-)

diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
index db0b339..de7d39a 100644
--- a/arch/powerpc/kernel/fadump.c
+++ b/arch/powerpc/kernel/fadump.c
@@ -210,14 +210,20 @@ static unsigned long init_fadump_mem_struct(struct fadump_mem_struct *fdm,
*/
static inline unsigned long fadump_calculate_reserve_size(void)
{
- unsigned long size;
+ int ret;
+ unsigned long long base, size;

/*
- * Check if the size is specified through fadump_reserve_mem= cmdline
- * option. If yes, then use that.
+ * Check if the size is specified through crashkernel= cmdline
+ * option. If yes, then use that but ignore base as fadump
+ * reserves memory at end of RAM.
*/
- if (fw_dump.reserve_bootvar)
+ ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(),
+ &size, &base);
+ if (ret == 0 && size > 0) {
+ fw_dump.reserve_bootvar = (unsigned long)size;
return fw_dump.reserve_bootvar;
+ }

/* divide by 20 to get 5% of value */
size = memblock_end_of_DRAM() / 20;
@@ -353,15 +359,6 @@ static int __init early_fadump_param(char *p)
}
early_param("fadump", early_fadump_param);

-/* Look for fadump_reserve_mem= cmdline option */
-static int __init early_fadump_reserve_mem(char *p)
-{
- if (p)
- fw_dump.reserve_bootvar = memparse(p, &p);
- return 0;
-}
-early_param("fadump_reserve_mem", early_fadump_reserve_mem);
-
static void register_fw_dump(struct fadump_mem_struct *fdm)
{
int rc;

2016-11-10 11:58:22

by Hari Bathini

[permalink] [raw]

Subject: [PATCH 3/3] powerpc/fadump: update documentation about crashkernel parameter reuse

As we are reusing crashkernel parameter instead of fadump_reserve_mem
parameter to specify the memory to reserve for fadump's crash kernel,
update the documentation accordingly.

Signed-off-by: Hari Bathini <[email protected]>
---
Documentation/powerpc/firmware-assisted-dump.txt | 23 ++++++++++++++--------
1 file changed, 15 insertions(+), 8 deletions(-)

diff --git a/Documentation/powerpc/firmware-assisted-dump.txt b/Documentation/powerpc/firmware-assisted-dump.txt
index 3007bc9..8394bc8 100644
--- a/Documentation/powerpc/firmware-assisted-dump.txt
+++ b/Documentation/powerpc/firmware-assisted-dump.txt
@@ -55,10 +55,14 @@ as follows:
booted with restricted memory. By default, the boot memory
size will be the larger of 5% of system RAM or 256MB.
Alternatively, user can also specify boot memory size
- through boot parameter 'fadump_reserve_mem=' which will
- override the default calculated size. Use this option
- if default boot memory size is not sufficient for second
- kernel to boot successfully.
+ through boot parameter 'crashkernel=' which will override
+ the default calculated size. Use this option if default
+ boot memory size is not sufficient for second kernel to
+ boot successfully. For syntax of crashkernel= parameter,
+ refer to Documentation/kdump/kdump.txt. If any offset is
+ provided in crashkernel= parameter, it will be ignored
+ as fadump reserves memory at end of RAM for boot memory
+ dump preservation in case of a crash.

-- After the low memory (boot memory) area has been saved, the
firmware will reset PCI and other hardware state. It will
@@ -158,13 +162,16 @@ How to enable firmware-assisted dump (fadump):

1. Set config option CONFIG_FA_DUMP=y and build kernel.
2. Boot into linux kernel with 'fadump=on' kernel cmdline option.
-3. Optionally, user can also set 'fadump_reserve_mem=' kernel cmdline
+3. Optionally, user can also set 'crashkernel=' kernel cmdline
to specify size of the memory to reserve for boot memory dump
preservation.

-NOTE: If firmware-assisted dump fails to reserve memory then it will
- fallback to existing kdump mechanism if 'crashkernel=' option
- is set at kernel cmdline.
+NOTE: 1. 'fadump_reserve_mem=' parameter has been deprecated. Instead
+ use 'crashkernel=' to specify size of the memory to reserve
+ for boot memory dump preservation.
+ 2. If firmware-assisted dump fails to reserve memory then it
+ will fallback to existing kdump mechanism if 'crashkernel='
+ option is set at kernel cmdline.

Sysfs/debugfs files:
------------

2016-11-10 13:52:18

by kernel test robot

[permalink] [raw]

Subject: Re: [PATCH 1/3] crash: move crashkernel parsing and vmcore related code under CONFIG_CRASH_CORE

Hi Hari,

[auto build test WARNING on linus/master]
[also build test WARNING on v4.9-rc4]
[cannot apply to powerpc/next next-20161110]
[if your patch is applied to the wrong git tree, please drop us a note to help improve the system]

url: https://github.com/0day-ci/linux/commits/Hari-Bathini/kexec-fadump-remove-dependency-with-CONFIG_KEXEC-and-reuse-crashkernel-parameter-for-fadump/20161110-200330
config: h8300-h8300h-sim_defconfig (attached as .config)
compiler: h8300-linux-gcc (GCC) 6.2.0
reproduce:
wget https://git.kernel.org/cgit/linux/kernel/git/wfg/lkp-tests.git/plain/sbin/make.cross -O ~/bin/make.cross
chmod +x ~/bin/make.cross
# save the attached .config to linux build tree
make.cross ARCH=h8300

All warnings (new ones prefixed by >>):

In file included from arch/h8300/include/asm/elf.h:8:0,
from include/linux/elfcore.h:6,
from include/linux/crash_core.h:5,
from include/linux/kexec.h:17,
from kernel/reboot.c:11:
>> arch/h8300/include/asm/ptrace.h:31:34: warning: 'struct task_struct' declared inside parameter list will not be visible outside of this definition or declaration
extern long h8300_get_reg(struct task_struct *task, int regno);
^~~~~~~~~~~
arch/h8300/include/asm/ptrace.h:32:33: warning: 'struct task_struct' declared inside parameter list will not be visible outside of this definition or declaration
extern int h8300_put_reg(struct task_struct *task, int regno,
^~~~~~~~~~~

vim +31 arch/h8300/include/asm/ptrace.h

d2a5f499 Yoshinori Sato 2015-05-11 15 #define H8300_REGS_NO 12
d2a5f499 Yoshinori Sato 2015-05-11 16 #endif
d2a5f499 Yoshinori Sato 2015-05-11 17
d2a5f499 Yoshinori Sato 2015-05-11 18 #define arch_has_single_step() (1)
d2a5f499 Yoshinori Sato 2015-05-11 19
d2a5f499 Yoshinori Sato 2015-05-11 20 #define user_mode(regs) (!((regs)->ccr & PS_S))
d2a5f499 Yoshinori Sato 2015-05-11 21 #define instruction_pointer(regs) ((regs)->pc)
d2a5f499 Yoshinori Sato 2015-05-11 22 #define profile_pc(regs) instruction_pointer(regs)
d2a5f499 Yoshinori Sato 2015-05-11 23 #define user_stack_pointer(regs) ((regs)->sp)
d2a5f499 Yoshinori Sato 2015-05-11 24 #define current_pt_regs() ((struct pt_regs *) \
d2a5f499 Yoshinori Sato 2015-05-11 25 (THREAD_SIZE + (unsigned long)current_thread_info()) - 1)
d2a5f499 Yoshinori Sato 2015-05-11 26 #define signal_pt_regs() ((struct pt_regs *)current->thread.esp0)
d2a5f499 Yoshinori Sato 2015-05-11 27 #define current_user_stack_pointer() rdusp()
d2a5f499 Yoshinori Sato 2015-05-11 28 #define task_pt_regs(task) \
d2a5f499 Yoshinori Sato 2015-05-11 29 ((struct pt_regs *) (task_stack_page(task) + THREAD_SIZE) - 1)
d2a5f499 Yoshinori Sato 2015-05-11 30
d2a5f499 Yoshinori Sato 2015-05-11 @31 extern long h8300_get_reg(struct task_struct *task, int regno);
d2a5f499 Yoshinori Sato 2015-05-11 32 extern int h8300_put_reg(struct task_struct *task, int regno,
d2a5f499 Yoshinori Sato 2015-05-11 33 unsigned long data);
d2a5f499 Yoshinori Sato 2015-05-11 34
d2a5f499 Yoshinori Sato 2015-05-11 35 #endif /* __ASSEMBLY__ */
d2a5f499 Yoshinori Sato 2015-05-11 36 #endif /* _H8300_PTRACE_H */

:::::: The code at line 31 was first introduced by commit
:::::: d2a5f4999f6c211adf30d9788349e13988d6f2a7 h8300: Assembly headers

:::::: TO: Yoshinori Sato <[email protected]>
:::::: CC: Yoshinori Sato <[email protected]>

---
0-DAY kernel test infrastructure Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all Intel Corporation

Attachments:

(No filename) (3.63 kB)
.config.gz (4.38 kB)
Download all attachments

2016-11-14 05:36:37

by Baoquan He

[permalink] [raw]

Subject: Re: [PATCH 1/3] crash: move crashkernel parsing and vmcore related code under CONFIG_CRASH_CORE

On 11/10/16 at 05:27pm, Hari Bathini wrote:
> Traditionally, kdump is used to save vmcore in case of a crash. Some
> architectures like powerpc can save vmcore using architecture specific
> support instead of kexec/kdump mechanism. Such architecture specific
> support also needs to reserve memory, to be used by dump capture kernel.
> crashkernel parameter can be a reused, for memory reservation, by such
> architecture specific infrastructure.
>
> But currently, code related to vmcoreinfo and parsing of crashkernel
> parameter is built under CONFIG_KEXEC_CORE. This patch introduces
> CONFIG_CRASH_CORE and moves the above mentioned code under this config,
> allowing code reuse without dependency on CONFIG_KEXEC. While here,
> removing the multiple definitions of append_elf_note() and final_note()
> for one defined under CONFIG_CONFIG_CORE. There is no functional change
> with this patch.

Can't think of a reason to object.

Could it be that do the moving from kexec_core.c to crash_core.c only,
then do the arch specific clean up in another patch?

Besides there's already a file crash_dump.h, can we reuse that?

>
> Signed-off-by: Hari Bathini <[email protected]>
> ---
> arch/Kconfig | 4
> arch/ia64/kernel/crash.c | 22 --
> arch/powerpc/Kconfig | 10 -
> arch/powerpc/include/asm/fadump.h | 2
> arch/powerpc/kernel/crash.c | 2
> arch/powerpc/kernel/fadump.c | 34 ---
> arch/powerpc/kernel/setup-common.c | 5
> include/linux/crash_core.h | 75 ++++++
> include/linux/kexec.h | 63 -----
> kernel/Makefile | 1
> kernel/crash_core.c | 450 ++++++++++++++++++++++++++++++++++++
> kernel/kexec_core.c | 435 -----------------------------------
> 12 files changed, 550 insertions(+), 553 deletions(-)
> create mode 100644 include/linux/crash_core.h
> create mode 100644 kernel/crash_core.c
>
> diff --git a/arch/Kconfig b/arch/Kconfig
> index 659bdd0..4ad34b9 100644
> --- a/arch/Kconfig
> +++ b/arch/Kconfig
> @@ -2,7 +2,11 @@
> # General architecture dependent options
> #
>
> +config CRASH_CORE
> + bool
> +
> config KEXEC_CORE
> + select CRASH_CORE
> bool
>
> config OPROFILE
> diff --git a/arch/ia64/kernel/crash.c b/arch/ia64/kernel/crash.c
> index 2955f35..75859a0 100644
> --- a/arch/ia64/kernel/crash.c
> +++ b/arch/ia64/kernel/crash.c
> @@ -27,28 +27,6 @@ static int kdump_freeze_monarch;
> static int kdump_on_init = 1;
> static int kdump_on_fatal_mca = 1;
>
> -static inline Elf64_Word
> -*append_elf_note(Elf64_Word *buf, char *name, unsigned type, void *data,
> - size_t data_len)
> -{
> - struct elf_note *note = (struct elf_note *)buf;
> - note->n_namesz = strlen(name) + 1;
> - note->n_descsz = data_len;
> - note->n_type = type;
> - buf += (sizeof(*note) + 3)/4;
> - memcpy(buf, name, note->n_namesz);
> - buf += (note->n_namesz + 3)/4;
> - memcpy(buf, data, data_len);
> - buf += (data_len + 3)/4;
> - return buf;
> -}
> -
> -static void
> -final_note(void *buf)
> -{
> - memset(buf, 0, sizeof(struct elf_note));
> -}
> -
> extern void ia64_dump_cpu_regs(void *);
>
> static DEFINE_PER_CPU(struct elf_prstatus, elf_prstatus);
> diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
> index 65fba4c..644703f 100644
> --- a/arch/powerpc/Kconfig
> +++ b/arch/powerpc/Kconfig
> @@ -479,21 +479,23 @@ config RELOCATABLE
> load address of the kernel (eg. u-boot/mkimage).
>
> config CRASH_DUMP
> - bool "Build a kdump crash kernel"
> + bool "Build a dump capture kernel"
> depends on PPC64 || 6xx || FSL_BOOKE || (44x && !SMP)
> select RELOCATABLE if (PPC64 && !COMPILE_TEST) || 44x || FSL_BOOKE
> help
> - Build a kernel suitable for use as a kdump capture kernel.
> + Build a kernel suitable for use as a dump capture kernel.
> The same kernel binary can be used as production kernel and dump
> capture kernel.
>
> config FA_DUMP
> bool "Firmware-assisted dump"
> - depends on PPC64 && PPC_RTAS && CRASH_DUMP && KEXEC
> + depends on PPC64 && PPC_RTAS
> + select CRASH_CORE
> + select CRASH_DUMP
> help
> A robust mechanism to get reliable kernel crash dump with
> assistance from firmware. This approach does not use kexec,
> - instead firmware assists in booting the kdump kernel
> + instead firmware assists in booting the capture kernel
> while preserving memory contents. Firmware-assisted dump
> is meant to be a kdump replacement offering robustness and
> speed not possible without system firmware assistance.
> diff --git a/arch/powerpc/include/asm/fadump.h b/arch/powerpc/include/asm/fadump.h
> index 0031806..60b9108 100644
> --- a/arch/powerpc/include/asm/fadump.h
> +++ b/arch/powerpc/include/asm/fadump.h
> @@ -73,6 +73,8 @@
> reg_entry++; \
> })
>
> +extern int crashing_cpu;
> +
> /* Kernel Dump section info */
> struct fadump_section {
> __be32 request_flag;
> diff --git a/arch/powerpc/kernel/crash.c b/arch/powerpc/kernel/crash.c
> index 47b63de..cbabb5a 100644
> --- a/arch/powerpc/kernel/crash.c
> +++ b/arch/powerpc/kernel/crash.c
> @@ -43,8 +43,6 @@
> #define IPI_TIMEOUT 10000
> #define REAL_MODE_TIMEOUT 10000
>
> -/* This keeps a track of which one is the crashing cpu. */
> -int crashing_cpu = -1;
> static int time_to_dump;
>
> #define CRASH_HANDLER_MAX 3
> diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
> index 8f0c7c5..db0b339 100644
> --- a/arch/powerpc/kernel/fadump.c
> +++ b/arch/powerpc/kernel/fadump.c
> @@ -486,34 +486,6 @@ fadump_read_registers(struct fadump_reg_entry *reg_entry, struct pt_regs *regs)
> return reg_entry;
> }
>
> -static u32 *fadump_append_elf_note(u32 *buf, char *name, unsigned type,
> - void *data, size_t data_len)
> -{
> - struct elf_note note;
> -
> - note.n_namesz = strlen(name) + 1;
> - note.n_descsz = data_len;
> - note.n_type = type;
> - memcpy(buf, &note, sizeof(note));
> - buf += (sizeof(note) + 3)/4;
> - memcpy(buf, name, note.n_namesz);
> - buf += (note.n_namesz + 3)/4;
> - memcpy(buf, data, note.n_descsz);
> - buf += (note.n_descsz + 3)/4;
> -
> - return buf;
> -}
> -
> -static void fadump_final_note(u32 *buf)
> -{
> - struct elf_note note;
> -
> - note.n_namesz = 0;
> - note.n_descsz = 0;
> - note.n_type = 0;
> - memcpy(buf, &note, sizeof(note));
> -}
> -
> static u32 *fadump_regs_to_elf_notes(u32 *buf, struct pt_regs *regs)
> {
> struct elf_prstatus prstatus;
> @@ -524,8 +496,8 @@ static u32 *fadump_regs_to_elf_notes(u32 *buf, struct pt_regs *regs)
> * prstatus.pr_pid = ????
> */
> elf_core_copy_kernel_regs(&prstatus.pr_reg, regs);
> - buf = fadump_append_elf_note(buf, KEXEC_CORE_NOTE_NAME, NT_PRSTATUS,
> - &prstatus, sizeof(prstatus));
> + buf = append_elf_note(buf, CRASH_CORE_NOTE_NAME, NT_PRSTATUS,
> + &prstatus, sizeof(prstatus));
> return buf;
> }
>
> @@ -666,7 +638,7 @@ static int __init fadump_build_cpu_notes(const struct fadump_mem_struct *fdm)
> note_buf = fadump_regs_to_elf_notes(note_buf, &regs);
> }
> }
> - fadump_final_note(note_buf);
> + final_note(note_buf);
>
> if (fdh) {
> pr_debug("Updating elfcore header (%llx) with cpu notes\n",
> diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
> index 270ee30..d322527 100644
> --- a/arch/powerpc/kernel/setup-common.c
> +++ b/arch/powerpc/kernel/setup-common.c
> @@ -116,6 +116,11 @@ int ppc_do_canonicalize_irqs;
> EXPORT_SYMBOL(ppc_do_canonicalize_irqs);
> #endif
>
> +#if defined(CONFIG_KEXEC) || defined(CONFIG_FA_DUMP)
> +/* This keeps a track of which one is the crashing cpu. */
> +int crashing_cpu = -1;
> +#endif
> +
> /* also used by kexec */
> void machine_shutdown(void)
> {
> diff --git a/include/linux/crash_core.h b/include/linux/crash_core.h
> new file mode 100644
> index 0000000..2ae20b1
> --- /dev/null
> +++ b/include/linux/crash_core.h
> @@ -0,0 +1,75 @@
> +#ifndef LINUX_CRASH_CORE_H
> +#define LINUX_CRASH_CORE_H
> +
> +#include <linux/linkage.h>
> +#include <linux/elfcore.h>
> +#include <linux/elf.h>
> +
> +#define CRASH_CORE_NOTE_NAME "CORE"
> +#define CRASH_CORE_NOTE_HEAD_BYTES ALIGN(sizeof(struct elf_note), 4)
> +#define CRASH_CORE_NOTE_NAME_BYTES ALIGN(sizeof(CRASH_CORE_NOTE_NAME), 4)
> +#define CRASH_CORE_NOTE_DESC_BYTES ALIGN(sizeof(struct elf_prstatus), 4)
> +
> +#define CRASH_CORE_NOTE_BYTES ((CRASH_CORE_NOTE_HEAD_BYTES * 2) + \
> + CRASH_CORE_NOTE_NAME_BYTES + \
> + CRASH_CORE_NOTE_DESC_BYTES)
> +
> +#define VMCOREINFO_BYTES (4096)
> +#define VMCOREINFO_NOTE_NAME "VMCOREINFO"
> +#define VMCOREINFO_NOTE_NAME_BYTES ALIGN(sizeof(VMCOREINFO_NOTE_NAME), 4)
> +#define VMCOREINFO_NOTE_SIZE ((CRASH_CORE_NOTE_HEAD_BYTES * 2) + \
> + VMCOREINFO_NOTE_NAME_BYTES + \
> + VMCOREINFO_BYTES)
> +
> +typedef u32 note_buf_t[CRASH_CORE_NOTE_BYTES/4];
> +
> +void crash_save_vmcoreinfo(void);
> +void arch_crash_save_vmcoreinfo(void);
> +__printf(1, 2)
> +void vmcoreinfo_append_str(const char *fmt, ...);
> +phys_addr_t paddr_vmcoreinfo_note(void);
> +
> +#define VMCOREINFO_OSRELEASE(value) \
> + vmcoreinfo_append_str("OSRELEASE=%s\n", value)
> +#define VMCOREINFO_PAGESIZE(value) \
> + vmcoreinfo_append_str("PAGESIZE=%ld\n", value)
> +#define VMCOREINFO_SYMBOL(name) \
> + vmcoreinfo_append_str("SYMBOL(%s)=%lx\n", #name, (unsigned long)&name)
> +#define VMCOREINFO_SIZE(name) \
> + vmcoreinfo_append_str("SIZE(%s)=%lu\n", #name, \
> + (unsigned long)sizeof(name))
> +#define VMCOREINFO_STRUCT_SIZE(name) \
> + vmcoreinfo_append_str("SIZE(%s)=%lu\n", #name, \
> + (unsigned long)sizeof(struct name))
> +#define VMCOREINFO_OFFSET(name, field) \
> + vmcoreinfo_append_str("OFFSET(%s.%s)=%lu\n", #name, #field, \
> + (unsigned long)offsetof(struct name, field))
> +#define VMCOREINFO_LENGTH(name, value) \
> + vmcoreinfo_append_str("LENGTH(%s)=%lu\n", #name, (unsigned long)value)
> +#define VMCOREINFO_NUMBER(name) \
> + vmcoreinfo_append_str("NUMBER(%s)=%ld\n", #name, (long)name)
> +#define VMCOREINFO_CONFIG(name) \
> + vmcoreinfo_append_str("CONFIG_%s=y\n", #name)
> +#define VMCOREINFO_PAGE_OFFSET(value) \
> + vmcoreinfo_append_str("PAGE_OFFSET=%lx\n", (unsigned long)value)
> +#define VMCOREINFO_VMALLOC_START(value) \
> + vmcoreinfo_append_str("VMALLOC_START=%lx\n", (unsigned long)value)
> +#define VMCOREINFO_VMEMMAP_START(value) \
> + vmcoreinfo_append_str("VMEMMAP_START=%lx\n", (unsigned long)value)
> +
> +extern u32 vmcoreinfo_note[VMCOREINFO_NOTE_SIZE/4];
> +extern size_t vmcoreinfo_size;
> +extern size_t vmcoreinfo_max_size;
> +
> +u32 *append_elf_note(u32 *buf, char *name, unsigned int type,
> + void *data, size_t data_len);
> +void final_note(u32 *buf);
> +
> +int __init parse_crashkernel(char *cmdline, unsigned long long system_ram,
> + unsigned long long *crash_size, unsigned long long *crash_base);
> +int parse_crashkernel_high(char *cmdline, unsigned long long system_ram,
> + unsigned long long *crash_size, unsigned long long *crash_base);
> +int parse_crashkernel_low(char *cmdline, unsigned long long system_ram,
> + unsigned long long *crash_size, unsigned long long *crash_base);
> +
> +#endif /* LINUX_CRASH_CORE_H */
> diff --git a/include/linux/kexec.h b/include/linux/kexec.h
> index 406c33d..aa3c747 100644
> --- a/include/linux/kexec.h
> +++ b/include/linux/kexec.h
> @@ -14,17 +14,15 @@
>
> #if !defined(__ASSEMBLY__)
>
> +#include <linux/crash_core.h>
> #include <asm/io.h>
>
> #include <uapi/linux/kexec.h>
>
> #ifdef CONFIG_KEXEC_CORE
> #include <linux/list.h>
> -#include <linux/linkage.h>
> #include <linux/compat.h>
> #include <linux/ioport.h>
> -#include <linux/elfcore.h>
> -#include <linux/elf.h>
> #include <linux/module.h>
> #include <asm/kexec.h>
>
> @@ -62,19 +60,15 @@
> #define KEXEC_CRASH_MEM_ALIGN PAGE_SIZE
> #endif
>
> -#define KEXEC_NOTE_HEAD_BYTES ALIGN(sizeof(struct elf_note), 4)
> -#define KEXEC_CORE_NOTE_NAME "CORE"
> -#define KEXEC_CORE_NOTE_NAME_BYTES ALIGN(sizeof(KEXEC_CORE_NOTE_NAME), 4)
> -#define KEXEC_CORE_NOTE_DESC_BYTES ALIGN(sizeof(struct elf_prstatus), 4)
> +#define KEXEC_CORE_NOTE_NAME CRASH_CORE_NOTE_NAME
> +
> /*
> * The per-cpu notes area is a list of notes terminated by a "NULL"
> * note header. For kdump, the code in vmcore.c runs in the context
> * of the second kernel to combine them into one note.
> */
> #ifndef KEXEC_NOTE_BYTES
> -#define KEXEC_NOTE_BYTES ( (KEXEC_NOTE_HEAD_BYTES * 2) + \
> - KEXEC_CORE_NOTE_NAME_BYTES + \
> - KEXEC_CORE_NOTE_DESC_BYTES )
> +#define KEXEC_NOTE_BYTES CRASH_CORE_NOTE_BYTES
> #endif
>
> /*
> @@ -232,39 +226,6 @@ extern void crash_kexec(struct pt_regs *);
> int kexec_should_crash(struct task_struct *);
> int kexec_crash_loaded(void);
> void crash_save_cpu(struct pt_regs *regs, int cpu);
> -void crash_save_vmcoreinfo(void);
> -void arch_crash_save_vmcoreinfo(void);
> -__printf(1, 2)
> -void vmcoreinfo_append_str(const char *fmt, ...);
> -phys_addr_t paddr_vmcoreinfo_note(void);
> -
> -#define VMCOREINFO_OSRELEASE(value) \
> - vmcoreinfo_append_str("OSRELEASE=%s\n", value)
> -#define VMCOREINFO_PAGESIZE(value) \
> - vmcoreinfo_append_str("PAGESIZE=%ld\n", value)
> -#define VMCOREINFO_SYMBOL(name) \
> - vmcoreinfo_append_str("SYMBOL(%s)=%lx\n", #name, (unsigned long)&name)
> -#define VMCOREINFO_SIZE(name) \
> - vmcoreinfo_append_str("SIZE(%s)=%lu\n", #name, \
> - (unsigned long)sizeof(name))
> -#define VMCOREINFO_STRUCT_SIZE(name) \
> - vmcoreinfo_append_str("SIZE(%s)=%lu\n", #name, \
> - (unsigned long)sizeof(struct name))
> -#define VMCOREINFO_OFFSET(name, field) \
> - vmcoreinfo_append_str("OFFSET(%s.%s)=%lu\n", #name, #field, \
> - (unsigned long)offsetof(struct name, field))
> -#define VMCOREINFO_LENGTH(name, value) \
> - vmcoreinfo_append_str("LENGTH(%s)=%lu\n", #name, (unsigned long)value)
> -#define VMCOREINFO_NUMBER(name) \
> - vmcoreinfo_append_str("NUMBER(%s)=%ld\n", #name, (long)name)
> -#define VMCOREINFO_CONFIG(name) \
> - vmcoreinfo_append_str("CONFIG_%s=y\n", #name)
> -#define VMCOREINFO_PAGE_OFFSET(value) \
> - vmcoreinfo_append_str("PAGE_OFFSET=%lx\n", (unsigned long)value)
> -#define VMCOREINFO_VMALLOC_START(value) \
> - vmcoreinfo_append_str("VMALLOC_START=%lx\n", (unsigned long)value)
> -#define VMCOREINFO_VMEMMAP_START(value) \
> - vmcoreinfo_append_str("VMEMMAP_START=%lx\n", (unsigned long)value)
>
> extern struct kimage *kexec_image;
> extern struct kimage *kexec_crash_image;
> @@ -285,31 +246,15 @@ extern int kexec_load_disabled;
> #define KEXEC_FILE_FLAGS (KEXEC_FILE_UNLOAD | KEXEC_FILE_ON_CRASH | \
> KEXEC_FILE_NO_INITRAMFS)
>
> -#define VMCOREINFO_BYTES (4096)
> -#define VMCOREINFO_NOTE_NAME "VMCOREINFO"
> -#define VMCOREINFO_NOTE_NAME_BYTES ALIGN(sizeof(VMCOREINFO_NOTE_NAME), 4)
> -#define VMCOREINFO_NOTE_SIZE (KEXEC_NOTE_HEAD_BYTES*2 + VMCOREINFO_BYTES \
> - + VMCOREINFO_NOTE_NAME_BYTES)
> -
> /* Location of a reserved region to hold the crash kernel.
> */
> extern struct resource crashk_res;
> extern struct resource crashk_low_res;
> -typedef u32 note_buf_t[KEXEC_NOTE_BYTES/4];
> extern note_buf_t __percpu *crash_notes;
> -extern u32 vmcoreinfo_note[VMCOREINFO_NOTE_SIZE/4];
> -extern size_t vmcoreinfo_size;
> -extern size_t vmcoreinfo_max_size;
>
> /* flag to track if kexec reboot is in progress */
> extern bool kexec_in_progress;
>
> -int __init parse_crashkernel(char *cmdline, unsigned long long system_ram,
> - unsigned long long *crash_size, unsigned long long *crash_base);
> -int parse_crashkernel_high(char *cmdline, unsigned long long system_ram,
> - unsigned long long *crash_size, unsigned long long *crash_base);
> -int parse_crashkernel_low(char *cmdline, unsigned long long system_ram,
> - unsigned long long *crash_size, unsigned long long *crash_base);
> int crash_shrink_memory(unsigned long new_size);
> size_t crash_get_memory_size(void);
> void crash_free_reserved_phys_range(unsigned long begin, unsigned long end);
> diff --git a/kernel/Makefile b/kernel/Makefile
> index eb26e12c..017e092 100644
> --- a/kernel/Makefile
> +++ b/kernel/Makefile
> @@ -59,6 +59,7 @@ obj-$(CONFIG_MODULES) += module.o
> obj-$(CONFIG_MODULE_SIG) += module_signing.o
> obj-$(CONFIG_KALLSYMS) += kallsyms.o
> obj-$(CONFIG_BSD_PROCESS_ACCT) += acct.o
> +obj-$(CONFIG_CRASH_CORE) += crash_core.o
> obj-$(CONFIG_KEXEC_CORE) += kexec_core.o
> obj-$(CONFIG_KEXEC) += kexec.o
> obj-$(CONFIG_KEXEC_FILE) += kexec_file.o
> diff --git a/kernel/crash_core.c b/kernel/crash_core.c
> new file mode 100644
> index 0000000..9223976
> --- /dev/null
> +++ b/kernel/crash_core.c
> @@ -0,0 +1,450 @@
> +/*
> + * crash.c - kernel crash support code.
> + * Copyright (C) 2002-2004 Eric Biederman <[email protected]>
> + *
> + * This source code is licensed under the GNU General Public License,
> + * Version 2. See the file COPYING for more details.
> + */
> +
> +#include <linux/crash_core.h>
> +#include <linux/utsname.h>
> +#include <linux/vmalloc.h>
> +
> +#include <asm/page.h>
> +#include <asm/sections.h>
> +
> +/* vmcoreinfo stuff */
> +static unsigned char vmcoreinfo_data[VMCOREINFO_BYTES];
> +u32 vmcoreinfo_note[VMCOREINFO_NOTE_SIZE/4];
> +size_t vmcoreinfo_size;
> +size_t vmcoreinfo_max_size = sizeof(vmcoreinfo_data);
> +
> +/*
> + * parsing the "crashkernel" commandline
> + *
> + * this code is intended to be called from architecture specific code
> + */
> +
> +
> +/*
> + * This function parses command lines in the format
> + *
> + * crashkernel=ramsize-range:size[,...][@offset]
> + *
> + * 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)
> +{
> + char *cur = cmdline, *tmp;
> +
> + /* for each entry of the comma-separated list */
> + do {
> + unsigned long long start, end = ULLONG_MAX, size;
> +
> + /* get the start of the range */
> + start = memparse(cur, &tmp);
> + if (cur == tmp) {
> + pr_warn("crashkernel: Memory value expected\n");
> + return -EINVAL;
> + }
> + cur = tmp;
> + if (*cur != '-') {
> + pr_warn("crashkernel: '-' expected\n");
> + return -EINVAL;
> + }
> + cur++;
> +
> + /* if no ':' is here, than we read the end */
> + if (*cur != ':') {
> + end = memparse(cur, &tmp);
> + if (cur == tmp) {
> + pr_warn("crashkernel: Memory value expected\n");
> + return -EINVAL;
> + }
> + cur = tmp;
> + if (end <= start) {
> + pr_warn("crashkernel: end <= start\n");
> + return -EINVAL;
> + }
> + }
> +
> + if (*cur != ':') {
> + pr_warn("crashkernel: ':' expected\n");
> + return -EINVAL;
> + }
> + cur++;
> +
> + size = memparse(cur, &tmp);
> + if (cur == tmp) {
> + pr_warn("Memory value expected\n");
> + return -EINVAL;
> + }
> + cur = tmp;
> + if (size >= system_ram) {
> + pr_warn("crashkernel: invalid size\n");
> + return -EINVAL;
> + }
> +
> + /* match ? */
> + if (system_ram >= start && system_ram < end) {
> + *crash_size = size;
> + break;
> + }
> + } while (*cur++ == ',');
> +
> + if (*crash_size > 0) {
> + while (*cur && *cur != ' ' && *cur != '@')
> + cur++;
> + if (*cur == '@') {
> + cur++;
> + *crash_base = memparse(cur, &tmp);
> + if (cur == tmp) {
> + pr_warn("Memory value expected after '@'\n");
> + return -EINVAL;
> + }
> + }
> + }
> +
> + return 0;
> +}
> +
> +/*
> + * That function parses "simple" (old) crashkernel command lines like
> + *
> + * 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)
> +{
> + char *cur = cmdline;
> +
> + *crash_size = memparse(cmdline, &cur);
> + if (cmdline == cur) {
> + 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: %c\n", *cur);
> + 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 parses "suffix" crashkernel command lines like
> + *
> + * crashkernel=size,[high|low]
> + *
> + * It returns 0 on success and -EINVAL on failure.
> + */
> +static int __init parse_crashkernel_suffix(char *cmdline,
> + unsigned long long *crash_size,
> + 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: %c\n", *cur);
> + return -EINVAL;
> + }
> + cur += strlen(suffix);
> + if (*cur != ' ' && *cur != '\0') {
> + pr_warn("crashkernel: unrecognized char: %c\n", *cur);
> + 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,
> + const char *name,
> + const char *suffix)
> +{
> + char *first_colon, *first_space;
> + char *ck_cmdline;
> +
> + BUG_ON(!crash_size || !crash_base);
> + *crash_size = 0;
> + *crash_base = 0;
> +
> + ck_cmdline = get_last_crashkernel(cmdline, name, suffix);
> +
> + if (!ck_cmdline)
> + return -EINVAL;
> +
> + ck_cmdline += strlen(name);
> +
> + if (suffix)
> + return parse_crashkernel_suffix(ck_cmdline, crash_size,
> + suffix);
> + /*
> + * if the commandline contains a ':', then that's the extended
> + * syntax -- if not, it must be the classic syntax
> + */
> + first_colon = strchr(ck_cmdline, ':');
> + first_space = strchr(ck_cmdline, ' ');
> + if (first_colon && (!first_space || first_colon < first_space))
> + return parse_crashkernel_mem(ck_cmdline, system_ram,
> + crash_size, crash_base);
> +
> + 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]);
> +}
> +
> +u32 *append_elf_note(u32 *buf, char *name, unsigned int type,
> + void *data, size_t data_len)
> +{
> + struct elf_note note;
> +
> + note.n_namesz = strlen(name) + 1;
> + note.n_descsz = data_len;
> + note.n_type = type;
> + memcpy(buf, &note, sizeof(note));
> + buf += (sizeof(note) + 3)/4;
> + memcpy(buf, name, note.n_namesz);
> + buf += (note.n_namesz + 3)/4;
> + memcpy(buf, data, note.n_descsz);
> + buf += (note.n_descsz + 3)/4;
> +
> + return buf;
> +}
> +
> +void final_note(u32 *buf)
> +{
> + struct elf_note note;
> +
> + note.n_namesz = 0;
> + note.n_descsz = 0;
> + note.n_type = 0;
> + memcpy(buf, &note, sizeof(note));
> +}
> +
> +static void update_vmcoreinfo_note(void)
> +{
> + u32 *buf = vmcoreinfo_note;
> +
> + if (!vmcoreinfo_size)
> + return;
> + 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];
> + size_t r;
> +
> + va_start(args, fmt);
> + r = vscnprintf(buf, sizeof(buf), fmt, args);
> + va_end(args);
> +
> + r = min(r, vmcoreinfo_max_size - vmcoreinfo_size);
> +
> + memcpy(&vmcoreinfo_data[vmcoreinfo_size], buf, r);
> +
> + vmcoreinfo_size += r;
> +}
> +
> +/*
> + * provide an empty default implementation here -- architecture
> + * code may override this
> + */
> +void __weak arch_crash_save_vmcoreinfo(void)
> +{}
> +
> +phys_addr_t __weak paddr_vmcoreinfo_note(void)
> +{
> + return __pa((unsigned long)(char *)&vmcoreinfo_note);
> +}
> +
> +static int __init crash_save_vmcoreinfo_init(void)
> +{
> + VMCOREINFO_OSRELEASE(init_uts_ns.name.release);
> + VMCOREINFO_PAGESIZE(PAGE_SIZE);
> +
> + VMCOREINFO_SYMBOL(init_uts_ns);
> + VMCOREINFO_SYMBOL(node_online_map);
> +#ifdef CONFIG_MMU
> + VMCOREINFO_SYMBOL(swapper_pg_dir);
> +#endif
> + VMCOREINFO_SYMBOL(_stext);
> + VMCOREINFO_SYMBOL(vmap_area_list);
> +
> +#ifndef CONFIG_NEED_MULTIPLE_NODES
> + VMCOREINFO_SYMBOL(mem_map);
> + VMCOREINFO_SYMBOL(contig_page_data);
> +#endif
> +#ifdef CONFIG_SPARSEMEM
> + VMCOREINFO_SYMBOL(mem_section);
> + VMCOREINFO_LENGTH(mem_section, NR_SECTION_ROOTS);
> + VMCOREINFO_STRUCT_SIZE(mem_section);
> + VMCOREINFO_OFFSET(mem_section, section_mem_map);
> +#endif
> + VMCOREINFO_STRUCT_SIZE(page);
> + VMCOREINFO_STRUCT_SIZE(pglist_data);
> + VMCOREINFO_STRUCT_SIZE(zone);
> + VMCOREINFO_STRUCT_SIZE(free_area);
> + VMCOREINFO_STRUCT_SIZE(list_head);
> + VMCOREINFO_SIZE(nodemask_t);
> + VMCOREINFO_OFFSET(page, flags);
> + VMCOREINFO_OFFSET(page, _refcount);
> + VMCOREINFO_OFFSET(page, mapping);
> + VMCOREINFO_OFFSET(page, lru);
> + VMCOREINFO_OFFSET(page, _mapcount);
> + VMCOREINFO_OFFSET(page, private);
> + VMCOREINFO_OFFSET(page, compound_dtor);
> + VMCOREINFO_OFFSET(page, compound_order);
> + VMCOREINFO_OFFSET(page, compound_head);
> + VMCOREINFO_OFFSET(pglist_data, node_zones);
> + VMCOREINFO_OFFSET(pglist_data, nr_zones);
> +#ifdef CONFIG_FLAT_NODE_MEM_MAP
> + VMCOREINFO_OFFSET(pglist_data, node_mem_map);
> +#endif
> + VMCOREINFO_OFFSET(pglist_data, node_start_pfn);
> + VMCOREINFO_OFFSET(pglist_data, node_spanned_pages);
> + VMCOREINFO_OFFSET(pglist_data, node_id);
> + VMCOREINFO_OFFSET(zone, free_area);
> + VMCOREINFO_OFFSET(zone, vm_stat);
> + VMCOREINFO_OFFSET(zone, spanned_pages);
> + VMCOREINFO_OFFSET(free_area, free_list);
> + VMCOREINFO_OFFSET(list_head, next);
> + VMCOREINFO_OFFSET(list_head, prev);
> + VMCOREINFO_OFFSET(vmap_area, va_start);
> + VMCOREINFO_OFFSET(vmap_area, list);
> + VMCOREINFO_LENGTH(zone.free_area, MAX_ORDER);
> +#ifdef CONFIG_KEXEC
> + log_buf_kexec_setup();
> +#endif
> + VMCOREINFO_LENGTH(free_area.free_list, MIGRATE_TYPES);
> + VMCOREINFO_NUMBER(NR_FREE_PAGES);
> + 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_X86
> + VMCOREINFO_NUMBER(KERNEL_IMAGE_SIZE);
> +#endif
> +#ifdef CONFIG_HUGETLB_PAGE
> + VMCOREINFO_NUMBER(HUGETLB_PAGE_DTOR);
> +#endif
> +
> + arch_crash_save_vmcoreinfo();
> + update_vmcoreinfo_note();
> +
> + return 0;
> +}
> +
> +subsys_initcall(crash_save_vmcoreinfo_init);
> diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
> index 5616755..596cb32 100644
> --- a/kernel/kexec_core.c
> +++ b/kernel/kexec_core.c
> @@ -51,12 +51,6 @@ DEFINE_MUTEX(kexec_mutex);
> /* Per cpu memory for storing cpu states in case of system crash. */
> note_buf_t __percpu *crash_notes;
>
> -/* vmcoreinfo stuff */
> -static unsigned char vmcoreinfo_data[VMCOREINFO_BYTES];
> -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;
>
> @@ -994,34 +988,6 @@ int crash_shrink_memory(unsigned long new_size)
> return ret;
> }
>
> -static u32 *append_elf_note(u32 *buf, char *name, unsigned type, void *data,
> - size_t data_len)
> -{
> - struct elf_note note;
> -
> - note.n_namesz = strlen(name) + 1;
> - note.n_descsz = data_len;
> - note.n_type = type;
> - memcpy(buf, &note, sizeof(note));
> - buf += (sizeof(note) + 3)/4;
> - memcpy(buf, name, note.n_namesz);
> - buf += (note.n_namesz + 3)/4;
> - memcpy(buf, data, note.n_descsz);
> - buf += (note.n_descsz + 3)/4;
> -
> - return buf;
> -}
> -
> -static void final_note(u32 *buf)
> -{
> - struct elf_note note;
> -
> - note.n_namesz = 0;
> - note.n_descsz = 0;
> - note.n_type = 0;
> - memcpy(buf, &note, sizeof(note));
> -}
> -
> void crash_save_cpu(struct pt_regs *regs, int cpu)
> {
> struct elf_prstatus prstatus;
> @@ -1081,407 +1047,6 @@ static int __init crash_notes_memory_init(void)
> }
> subsys_initcall(crash_notes_memory_init);
>
> -
> -/*
> - * parsing the "crashkernel" commandline
> - *
> - * this code is intended to be called from architecture specific code
> - */
> -
> -
> -/*
> - * This function parses command lines in the format
> - *
> - * crashkernel=ramsize-range:size[,...][@offset]
> - *
> - * 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)
> -{
> - char *cur = cmdline, *tmp;
> -
> - /* for each entry of the comma-separated list */
> - do {
> - unsigned long long start, end = ULLONG_MAX, size;
> -
> - /* get the start of the range */
> - start = memparse(cur, &tmp);
> - if (cur == tmp) {
> - pr_warn("crashkernel: Memory value expected\n");
> - return -EINVAL;
> - }
> - cur = tmp;
> - if (*cur != '-') {
> - pr_warn("crashkernel: '-' expected\n");
> - return -EINVAL;
> - }
> - cur++;
> -
> - /* if no ':' is here, than we read the end */
> - if (*cur != ':') {
> - end = memparse(cur, &tmp);
> - if (cur == tmp) {
> - pr_warn("crashkernel: Memory value expected\n");
> - return -EINVAL;
> - }
> - cur = tmp;
> - if (end <= start) {
> - pr_warn("crashkernel: end <= start\n");
> - return -EINVAL;
> - }
> - }
> -
> - if (*cur != ':') {
> - pr_warn("crashkernel: ':' expected\n");
> - return -EINVAL;
> - }
> - cur++;
> -
> - size = memparse(cur, &tmp);
> - if (cur == tmp) {
> - pr_warn("Memory value expected\n");
> - return -EINVAL;
> - }
> - cur = tmp;
> - if (size >= system_ram) {
> - pr_warn("crashkernel: invalid size\n");
> - return -EINVAL;
> - }
> -
> - /* match ? */
> - if (system_ram >= start && system_ram < end) {
> - *crash_size = size;
> - break;
> - }
> - } while (*cur++ == ',');
> -
> - if (*crash_size > 0) {
> - while (*cur && *cur != ' ' && *cur != '@')
> - cur++;
> - if (*cur == '@') {
> - cur++;
> - *crash_base = memparse(cur, &tmp);
> - if (cur == tmp) {
> - pr_warn("Memory value expected after '@'\n");
> - return -EINVAL;
> - }
> - }
> - }
> -
> - return 0;
> -}
> -
> -/*
> - * That function parses "simple" (old) crashkernel command lines like
> - *
> - * 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)
> -{
> - char *cur = cmdline;
> -
> - *crash_size = memparse(cmdline, &cur);
> - if (cmdline == cur) {
> - 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: %c\n", *cur);
> - 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 parses "suffix" crashkernel command lines like
> - *
> - * crashkernel=size,[high|low]
> - *
> - * It returns 0 on success and -EINVAL on failure.
> - */
> -static int __init parse_crashkernel_suffix(char *cmdline,
> - unsigned long long *crash_size,
> - 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: %c\n", *cur);
> - return -EINVAL;
> - }
> - cur += strlen(suffix);
> - if (*cur != ' ' && *cur != '\0') {
> - pr_warn("crashkernel: unrecognized char: %c\n", *cur);
> - 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,
> - const char *name,
> - const char *suffix)
> -{
> - char *first_colon, *first_space;
> - char *ck_cmdline;
> -
> - BUG_ON(!crash_size || !crash_base);
> - *crash_size = 0;
> - *crash_base = 0;
> -
> - ck_cmdline = get_last_crashkernel(cmdline, name, suffix);
> -
> - if (!ck_cmdline)
> - return -EINVAL;
> -
> - ck_cmdline += strlen(name);
> -
> - if (suffix)
> - return parse_crashkernel_suffix(ck_cmdline, crash_size,
> - suffix);
> - /*
> - * if the commandline contains a ':', then that's the extended
> - * syntax -- if not, it must be the classic syntax
> - */
> - first_colon = strchr(ck_cmdline, ':');
> - first_space = strchr(ck_cmdline, ' ');
> - if (first_colon && (!first_space || first_colon < first_space))
> - return parse_crashkernel_mem(ck_cmdline, system_ram,
> - crash_size, crash_base);
> -
> - 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]);
> -}
> -
> -static void update_vmcoreinfo_note(void)
> -{
> - u32 *buf = vmcoreinfo_note;
> -
> - if (!vmcoreinfo_size)
> - return;
> - 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];
> - size_t r;
> -
> - va_start(args, fmt);
> - r = vscnprintf(buf, sizeof(buf), fmt, args);
> - va_end(args);
> -
> - r = min(r, vmcoreinfo_max_size - vmcoreinfo_size);
> -
> - memcpy(&vmcoreinfo_data[vmcoreinfo_size], buf, r);
> -
> - vmcoreinfo_size += r;
> -}
> -
> -/*
> - * provide an empty default implementation here -- architecture
> - * code may override this
> - */
> -void __weak arch_crash_save_vmcoreinfo(void)
> -{}
> -
> -phys_addr_t __weak paddr_vmcoreinfo_note(void)
> -{
> - return __pa((unsigned long)(char *)&vmcoreinfo_note);
> -}
> -
> -static int __init crash_save_vmcoreinfo_init(void)
> -{
> - VMCOREINFO_OSRELEASE(init_uts_ns.name.release);
> - VMCOREINFO_PAGESIZE(PAGE_SIZE);
> -
> - VMCOREINFO_SYMBOL(init_uts_ns);
> - VMCOREINFO_SYMBOL(node_online_map);
> -#ifdef CONFIG_MMU
> - VMCOREINFO_SYMBOL(swapper_pg_dir);
> -#endif
> - VMCOREINFO_SYMBOL(_stext);
> - VMCOREINFO_SYMBOL(vmap_area_list);
> -
> -#ifndef CONFIG_NEED_MULTIPLE_NODES
> - VMCOREINFO_SYMBOL(mem_map);
> - VMCOREINFO_SYMBOL(contig_page_data);
> -#endif
> -#ifdef CONFIG_SPARSEMEM
> - VMCOREINFO_SYMBOL(mem_section);
> - VMCOREINFO_LENGTH(mem_section, NR_SECTION_ROOTS);
> - VMCOREINFO_STRUCT_SIZE(mem_section);
> - VMCOREINFO_OFFSET(mem_section, section_mem_map);
> -#endif
> - VMCOREINFO_STRUCT_SIZE(page);
> - VMCOREINFO_STRUCT_SIZE(pglist_data);
> - VMCOREINFO_STRUCT_SIZE(zone);
> - VMCOREINFO_STRUCT_SIZE(free_area);
> - VMCOREINFO_STRUCT_SIZE(list_head);
> - VMCOREINFO_SIZE(nodemask_t);
> - VMCOREINFO_OFFSET(page, flags);
> - VMCOREINFO_OFFSET(page, _refcount);
> - VMCOREINFO_OFFSET(page, mapping);
> - VMCOREINFO_OFFSET(page, lru);
> - VMCOREINFO_OFFSET(page, _mapcount);
> - VMCOREINFO_OFFSET(page, private);
> - VMCOREINFO_OFFSET(page, compound_dtor);
> - VMCOREINFO_OFFSET(page, compound_order);
> - VMCOREINFO_OFFSET(page, compound_head);
> - VMCOREINFO_OFFSET(pglist_data, node_zones);
> - VMCOREINFO_OFFSET(pglist_data, nr_zones);
> -#ifdef CONFIG_FLAT_NODE_MEM_MAP
> - VMCOREINFO_OFFSET(pglist_data, node_mem_map);
> -#endif
> - VMCOREINFO_OFFSET(pglist_data, node_start_pfn);
> - VMCOREINFO_OFFSET(pglist_data, node_spanned_pages);
> - VMCOREINFO_OFFSET(pglist_data, node_id);
> - VMCOREINFO_OFFSET(zone, free_area);
> - VMCOREINFO_OFFSET(zone, vm_stat);
> - VMCOREINFO_OFFSET(zone, spanned_pages);
> - VMCOREINFO_OFFSET(free_area, free_list);
> - VMCOREINFO_OFFSET(list_head, next);
> - VMCOREINFO_OFFSET(list_head, prev);
> - 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);
> - VMCOREINFO_NUMBER(NR_FREE_PAGES);
> - 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_X86
> - VMCOREINFO_NUMBER(KERNEL_IMAGE_SIZE);
> -#endif
> -#ifdef CONFIG_HUGETLB_PAGE
> - VMCOREINFO_NUMBER(HUGETLB_PAGE_DTOR);
> -#endif
> -
> - arch_crash_save_vmcoreinfo();
> - update_vmcoreinfo_note();
> -
> - return 0;
> -}
> -
> -subsys_initcall(crash_save_vmcoreinfo_init);
> -
> /*
> * Move into place and start executing a preloaded standalone
> * executable. If nothing was preloaded return an error.
>
>
> _______________________________________________
> kexec mailing list
> [email protected]
> http://lists.infradead.org/mailman/listinfo/kexec

2016-11-14 10:17:38

by Hari Bathini

[permalink] [raw]

Subject: Re: [PATCH 1/3] crash: move crashkernel parsing and vmcore related code under CONFIG_CRASH_CORE

On Monday 14 November 2016 11:06 AM, Baoquan He wrote:
> On 11/10/16 at 05:27pm, Hari Bathini wrote:
>> Traditionally, kdump is used to save vmcore in case of a crash. Some
>> architectures like powerpc can save vmcore using architecture specific
>> support instead of kexec/kdump mechanism. Such architecture specific
>> support also needs to reserve memory, to be used by dump capture kernel.
>> crashkernel parameter can be a reused, for memory reservation, by such
>> architecture specific infrastructure.
>>
>> But currently, code related to vmcoreinfo and parsing of crashkernel
>> parameter is built under CONFIG_KEXEC_CORE. This patch introduces
>> CONFIG_CRASH_CORE and moves the above mentioned code under this config,
>> allowing code reuse without dependency on CONFIG_KEXEC. While here,
>> removing the multiple definitions of append_elf_note() and final_note()
>> for one defined under CONFIG_CONFIG_CORE. There is no functional change
>> with this patch.
> Can't think of a reason to object.
>
> Could it be that do the moving from kexec_core.c to crash_core.c only,
> then do the arch specific clean up in another patch?

Right. Will move arch specific code into a separate patch, on the
next version..

> Besides there's already a file crash_dump.h, can we reuse that?

Did think about it. But as it is meant for dump capture kernel
(CONFIG_CRASH_DUMP) and CONFIG_KEXEC_CORE being
independent, didn't pursue it..

Thanks
Hari