command line size is restricted by kernel, sometimes memmap=exactmap has
too many memory ranges to pass to cmdline. A better approach, to pass the
memory ranges for crash kernel to boot into, is filling the memory
ranges into E820.
boot_params only got 128 slots for E820 map to fit in, when the number of
memory map exceeds 128, use setup_data to pass the rest as extended E820
memory map.
kexec boot could also benefit from setup_data in case E820 memory map
exceeds 128.
Now this new approach becomes default instead of memmap=exactmap.
saved_max_pfn users can specify --pass-memmap-cmdline to use the
exactmap approach.
Signed-off-by: WANG Chao <chaowang at redhat.com>
---
kexec/arch/i386/crashdump-x86.c | 25 +++--
kexec/arch/i386/crashdump-x86.h | 1 +
kexec/arch/i386/x86-linux-setup.c | 195 +++++++++++++++++++++++++++-----------
3 files changed, 158 insertions(+), 63 deletions(-)
diff --git a/kexec/arch/i386/crashdump-x86.c b/kexec/arch/i386/crashdump-x86.c
index c55a6b1..cb19e7d 100644
--- a/kexec/arch/i386/crashdump-x86.c
+++ b/kexec/arch/i386/crashdump-x86.c
@@ -182,6 +182,8 @@ static int exclude_region(int *nr_ranges, uint64_t start, uint64_t end);
struct memory_range crash_memory_range[CRASH_MAX_MEMORY_RANGES];
int crash_memory_ranges;
+int pass_memmap_cmdline;
+
/* Memory region reserved for storing panic kernel and other data. */
#define CRASH_RESERVED_MEM_NR 8
static struct memory_range crash_reserved_mem[CRASH_RESERVED_MEM_NR];
@@ -947,20 +949,23 @@ int load_crashdump_segments(struct kexec_info *info, char* mod_cmdline,
dbgprintf("Created elf header segment at 0x%lx\n", elfcorehdr);
if (delete_memmap(crash_memory_range, &crash_memory_ranges, elfcorehdr, memsz) < 0)
return -1;
- cmdline_add_memmap(mod_cmdline, crash_memory_range);
if (!bzImage_support_efi_boot)
cmdline_add_efi(mod_cmdline);
cmdline_add_elfcorehdr(mod_cmdline, elfcorehdr);
- /* Inform second kernel about the presence of ACPI tables. */
- for (i = 0; i < CRASH_MAX_MEMORY_RANGES; i++) {
- unsigned long start, end;
- if ( !( mem_range[i].type == RANGE_ACPI
- || mem_range[i].type == RANGE_ACPI_NVS) )
- continue;
- start = mem_range[i].start;
- end = mem_range[i].end;
- cmdline_add_memmap_acpi(mod_cmdline, start, end);
+ pass_memmap_cmdline = arch_options.pass_memmap_cmdline;
+ if (pass_memmap_cmdline) {
+ cmdline_add_memmap(mod_cmdline, crash_memory_range);
+ /* Inform second kernel about the presence of ACPI tables. */
+ for (i = 0; i < CRASH_MAX_MEMORY_RANGES; i++) {
+ unsigned long start, end;
+ if ( !( mem_range[i].type == RANGE_ACPI
+ || mem_range[i].type == RANGE_ACPI_NVS) )
+ continue;
+ start = mem_range[i].start;
+ end = mem_range[i].end;
+ cmdline_add_memmap_acpi(mod_cmdline, start, end);
+ }
}
return 0;
diff --git a/kexec/arch/i386/crashdump-x86.h b/kexec/arch/i386/crashdump-x86.h
index 633ee0e..e68b626 100644
--- a/kexec/arch/i386/crashdump-x86.h
+++ b/kexec/arch/i386/crashdump-x86.h
@@ -30,5 +30,6 @@ int load_crashdump_segments(struct kexec_info *info, char *mod_cmdline,
extern struct memory_range crash_memory_range[CRASH_MAX_MEMORY_RANGES];
extern int crash_memory_ranges;
+extern int pass_memmap_cmdline;
#endif /* CRASHDUMP_X86_H */
diff --git a/kexec/arch/i386/x86-linux-setup.c b/kexec/arch/i386/x86-linux-setup.c
index 5884f4d..209652c 100644
--- a/kexec/arch/i386/x86-linux-setup.c
+++ b/kexec/arch/i386/x86-linux-setup.c
@@ -35,8 +35,7 @@
#include "kexec-x86.h"
#include "x86-linux-setup.h"
#include "../../kexec/kexec-syscall.h"
-
-#define SETUP_EFI 4
+#include "crashdump-x86.h"
void init_linux_parameters(struct x86_linux_param_header *real_mode)
{
@@ -502,6 +501,11 @@ struct efi_setup_data {
struct setup_data {
uint64_t next;
uint32_t type;
+#define SETUP_NONE 0
+#define SETUP_E820_EXT 1
+#define SETUP_DTB 2
+#define SETUP_PCI 3
+#define SETUP_EFI 4
uint32_t len;
uint8_t data[0];
} __attribute__((packed));
@@ -602,6 +606,17 @@ struct efi_info {
uint32_t efi_memmap_hi;
};
+static void add_setup_data(struct kexec_info *info,
+ struct x86_linux_param_header *real_mode,
+ struct setup_data *sd)
+{
+ int sdsize = sizeof(struct setup_data) + sd->len;
+
+ sd->next = real_mode->setup_data;
+ real_mode->setup_data = add_buffer(info, sd, sdsize, sdsize, getpagesize(),
+ 0x100000, ULONG_MAX, INT_MAX);
+}
+
/*
* setup_efi_data will collect below data and pass them to 2nd kernel.
* 1) SMBIOS, fw_vendor, runtime, config_table, they are passed via x86
@@ -611,11 +626,11 @@ struct efi_info {
static int setup_efi_data(struct kexec_info *info,
struct x86_linux_param_header *real_mode)
{
- int64_t setup_data_paddr, memmap_paddr;
+ int64_t memmap_paddr;
struct setup_data *sd;
struct efi_setup_data *esd;
struct efi_mem_descriptor *maps;
- int nr_maps, size, sdsize, ret = 0;
+ int nr_maps, size, ret = 0;
struct efi_info *ei = (struct efi_info *)real_mode->efi_info;
ret = access("/sys/firmware/efi/systab", F_OK);
@@ -648,10 +663,8 @@ static int setup_efi_data(struct kexec_info *info,
sd->len = sizeof(*esd);
memcpy(sd->data, esd, sizeof(*esd));
free(esd);
- sdsize = sd->len + sizeof(struct setup_data);
- setup_data_paddr = add_buffer(info, sd, sdsize, sdsize, getpagesize(),
- 0x100000, ULONG_MAX, INT_MAX);
- real_mode->setup_data = setup_data_paddr;
+
+ add_setup_data(info, real_mode, sd);
size = nr_maps * sizeof(struct efi_mem_descriptor);
memmap_paddr = add_buffer(info, maps, size, size, getpagesize(),
@@ -669,6 +682,119 @@ out:
return ret;
}
+static void setup_e820_ext(struct kexec_info *info, struct x86_linux_param_header *real_mode,
+ struct memory_range *range, int nr_range)
+{
+ struct setup_data *sd;
+ struct e820entry *e820;
+ int i, j, nr_range_ext;
+
+ nr_range_ext = nr_range - E820MAX;
+ sd = malloc(sizeof(struct setup_data) + nr_range_ext * sizeof(struct e820entry));
+ sd->next = 0;
+ sd->len = nr_range_ext * sizeof(struct e820entry);
+ sd->type = SETUP_E820_EXT;
+
+ e820 = (struct e820entry *) sd->data;
+ dbgprintf("Extended E820 via setup_data:\n");
+ for(i = 0, j = E820MAX; i < nr_range_ext; i++, j++) {
+ e820[i].addr = range[j].start;
+ e820[i].size = range[j].end - range[j].start;
+ switch (range[j].type) {
+ case RANGE_RAM:
+ e820[i].type = E820_RAM;
+ break;
+ case RANGE_ACPI:
+ e820[i].type = E820_ACPI;
+ break;
+ case RANGE_ACPI_NVS:
+ e820[i].type = E820_NVS;
+ break;
+ default:
+ case RANGE_RESERVED:
+ e820[i].type = E820_RESERVED;
+ break;
+ }
+ dbgprintf("%016lx-%016lx (%d)\n",
+ e820[i].addr,
+ e820[i].addr + e820[i].size - 1,
+ e820[i].type);
+
+ if (range[j].type != RANGE_RAM)
+ continue;
+ if ((range[j].start <= 0x100000) && range[j].end > 0x100000) {
+ unsigned long long mem_k = (range[j].end >> 10) - (0x100000 >> 10);
+ real_mode->ext_mem_k = mem_k;
+ real_mode->alt_mem_k = mem_k;
+ if (mem_k > 0xfc00) {
+ real_mode->ext_mem_k = 0xfc00; /* 64M */
+ }
+ if (mem_k > 0xffffffff) {
+ real_mode->alt_mem_k = 0xffffffff;
+ }
+ }
+ }
+ add_setup_data(info, real_mode, sd);
+ free(sd);
+}
+
+static void setup_e820(struct kexec_info *info, struct x86_linux_param_header *real_mode,
+ struct memory_range *range, int nr_range)
+{
+
+ int nr_range_saved = nr_range;
+ int i;
+
+ if (nr_range > E820MAX) {
+ nr_range = E820MAX;
+ }
+
+ real_mode->e820_map_nr = nr_range;
+ dbgprintf("E820 memmap:\n");
+ for(i = 0; i < nr_range; i++) {
+ real_mode->e820_map[i].addr = range[i].start;
+ real_mode->e820_map[i].size = range[i].end - range[i].start;
+ switch (range[i].type) {
+ case RANGE_RAM:
+ real_mode->e820_map[i].type = E820_RAM;
+ break;
+ case RANGE_ACPI:
+ real_mode->e820_map[i].type = E820_ACPI;
+ break;
+ case RANGE_ACPI_NVS:
+ real_mode->e820_map[i].type = E820_NVS;
+ break;
+ default:
+ case RANGE_RESERVED:
+ real_mode->e820_map[i].type = E820_RESERVED;
+ break;
+ }
+ dbgprintf("%016lx-%016lx (%d)\n",
+ real_mode->e820_map[i].addr,
+ real_mode->e820_map[i].addr + real_mode->e820_map[i].size - 1,
+ real_mode->e820_map[i].type);
+
+ if (range[i].type != RANGE_RAM)
+ continue;
+ if ((range[i].start <= 0x100000) && range[i].end > 0x100000) {
+ unsigned long long mem_k = (range[i].end >> 10) - (0x100000 >> 10);
+ real_mode->ext_mem_k = mem_k;
+ real_mode->alt_mem_k = mem_k;
+ if (mem_k > 0xfc00) {
+ real_mode->ext_mem_k = 0xfc00; /* 64M */
+ }
+ if (mem_k > 0xffffffff) {
+ real_mode->alt_mem_k = 0xffffffff;
+ }
+ }
+ }
+
+ if (nr_range_saved > E820MAX) {
+ dbgprintf("extra E820 memmap are passed via setup_data\n");
+ setup_e820_ext(info, real_mode, range, nr_range_saved);
+ }
+}
+
static int
get_efi_mem_desc_version(struct x86_linux_param_header *real_mode)
{
@@ -704,7 +830,7 @@ void setup_linux_system_parameters(struct kexec_info *info,
{
/* Fill in information the BIOS would usually provide */
struct memory_range *range;
- int i, ranges;
+ int ranges;
/* get subarch from running kernel */
setup_subarch(real_mode);
@@ -746,51 +872,14 @@ void setup_linux_system_parameters(struct kexec_info *info,
/* another safe default */
real_mode->aux_device_info = 0;
- range = info->memory_range;
- ranges = info->memory_ranges;
- if (ranges > E820MAX) {
- if (!(info->kexec_flags & KEXEC_ON_CRASH))
- /*
- * this e820 not used for capture kernel, see
- * do_bzImage_load()
- */
- fprintf(stderr,
- "Too many memory ranges, truncating...\n");
- ranges = E820MAX;
- }
- real_mode->e820_map_nr = ranges;
- for(i = 0; i < ranges; i++) {
- real_mode->e820_map[i].addr = range[i].start;
- real_mode->e820_map[i].size = range[i].end - range[i].start;
- switch (range[i].type) {
- case RANGE_RAM:
- real_mode->e820_map[i].type = E820_RAM;
- break;
- case RANGE_ACPI:
- real_mode->e820_map[i].type = E820_ACPI;
- break;
- case RANGE_ACPI_NVS:
- real_mode->e820_map[i].type = E820_NVS;
- break;
- default:
- case RANGE_RESERVED:
- real_mode->e820_map[i].type = E820_RESERVED;
- break;
- }
- if (range[i].type != RANGE_RAM)
- continue;
- if ((range[i].start <= 0x100000) && range[i].end > 0x100000) {
- unsigned long long mem_k = (range[i].end >> 10) - (0x100000 >> 10);
- real_mode->ext_mem_k = mem_k;
- real_mode->alt_mem_k = mem_k;
- if (mem_k > 0xfc00) {
- real_mode->ext_mem_k = 0xfc00; /* 64M */
- }
- if (mem_k > 0xffffffff) {
- real_mode->alt_mem_k = 0xffffffff;
- }
- }
+ if (info->kexec_flags & KEXEC_ON_CRASH && !pass_memmap_cmdline) {
+ range = crash_memory_range;
+ ranges = crash_memory_ranges;
+ } else {
+ range = info->memory_range;
+ ranges = info->memory_ranges;
}
+ setup_e820(info, real_mode, range, ranges);
/* fill the EDD information */
setup_edd_info(real_mode);
--
1.8.5.3
