[Crash-utility] Increase of NR_CPUS on IA64
Dave Anderson
anderson at redhat.com
Fri Oct 19 16:23:55 UTC 2007
Bernhard Walle wrote:
> * Bernhard Walle <bwalle at suse.de> [2007-10-19 17:24]:
>
>>The solution for that problem is to calculate the number of CPUs for
>>IA64 at runtime. The 2nd patch implements this, and also reads the
>>registers from the LKCD dump header instead of guessing on the stack.
>>This fixes a problem here -- unfortunately, I don't still have that
>>dump to provide further details.
>
>
> I forget to attach the 2nd patch ;)
>
>
> Thanks,
> Bernhard
>
>
At this point I've lost most insights into the LKCD code.
The ia64 pt_regs hardwiring bothers me, mainly because there have
been changes to its definition over the years. (There's a couple
different versions hardwired in unwind.h for example).
So my biggest worry would be if this somehow breaks
backwards-compatibility, but I'm presuming that you took
that into account. But anyway, I leave this all up
to Troy.
A couple nits...
Please build with "make warn" before submitting any patch
and clean up the complaints.
Also I'd prefer to not tinker with the netdump.c file.
There is no /usr/include/stddef.h in the RHEL and FC8
environments, and the /usr/include/linux/stddef.h has
removed offsetof() in FC8 for some reason? In any case,
I'd prefer leaving it alone.
Because of the builtin array sizes that I long ago
painted crash into a corner with, I'd also prefer keeping
NR_CPUS to its minimum. I have no problem updating it if
necessary later, so 4096 is preferable to overkilling
it with 16384 at this time. I don't see how that could
be a problem? If it is, you can always release the SUSE
version with the larger value -- I'm sure that you're
almost never in sync with the upstream version anyway,
right? (I can't even do that with RHEL errata...)
Thanks,
Dave
>
> ------------------------------------------------------------------------
>
> ---
> Makefile | 4
> defs.h | 9 +
> kernel.c | 5
> lkcd_dump_v8.h | 300 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++
> lkcd_fix_mem.c | 22 ----
> lkcd_fix_mem.h | 295 --------------------------------------------------------
> lkcd_v8.c | 186 ++++++++++++++++++++++++++++++++++-
> netdump.c | 1
> 8 files changed, 502 insertions(+), 320 deletions(-)
>
> --- a/Makefile
> +++ b/Makefile
> @@ -66,7 +66,7 @@ GENERIC_HFILES=defs.h xen_hyper_defs.h
> MCORE_HFILES=va_server.h vas_crash.h
> REDHAT_HFILES=netdump.h diskdump.h xendump.h
> LKCD_DUMP_HFILES=lkcd_vmdump_v1.h lkcd_vmdump_v2_v3.h lkcd_dump_v5.h \
> - lkcd_dump_v7.h lkcd_dump_v8.h lkcd_fix_mem.h
> + lkcd_dump_v7.h lkcd_dump_v8.h
> LKCD_TRACE_HFILES=lkcd_x86_trace.h
> IBM_HFILES=ibm_common.h
> UNWIND_HFILES=unwind.h unwind_i.h rse.h unwind_x86.h unwind_x86_64.h
> @@ -406,7 +406,7 @@ unwind_v3.o: ${GENERIC_HFILES} ${UNWIND_
> cc -c ${CFLAGS} -DREDHAT -DUNWIND_V3 unwind.c -o unwind_v3.o ${WARNING_OPTIONS} ${WARNING_ERROR}
>
> lkcd_fix_mem.o: ${GENERIC_HFILES} ${LKCD_HFILES} lkcd_fix_mem.c
> - cc -c ${CFLAGS} lkcd_fix_mem.c ${WARNING_OPTIONS} ${WARNING_ERROR}
> + cc -c ${CFLAGS} -DMCLX lkcd_fix_mem.c ${WARNING_OPTIONS} ${WARNING_ERROR}
>
> xen_hyper.o: ${GENERIC_HFILES} xen_hyper.c
> cc -c ${CFLAGS} xen_hyper.c ${WARNING_OPTIONS} ${WARNING_ERROR}
> --- a/defs.h
> +++ b/defs.h
> @@ -19,6 +19,7 @@
> #ifndef GDB_COMMON
>
> #include <stdio.h>
> +#include <stddef.h>
> #include <stdarg.h>
> #include <stdint.h>
> #include <termios.h>
> @@ -54,6 +55,7 @@
>
> #define TRUE (1)
> #define FALSE (0)
> +#define STR(x) #x
>
> #ifdef X86
> #define NR_CPUS (256)
> @@ -3826,10 +3828,15 @@ void ppc_dump_machdep_table(ulong);
> */
>
> ulong get_lkcd_switch_stack(ulong);
> -int fix_addr_v8(int);
> +int fix_addr_v8();
> int fix_addr_v7(int);
>
> /*
> + * lkcd_v8.c
> + */
> +int get_lkcd_regs_for_cpu(struct bt_info *bt, ulong *eip, ulong *esp);
> +
> +/*
> * ia64.c
> */
> #ifdef IA64
> --- a/kernel.c
> +++ b/kernel.c
> @@ -2102,6 +2102,11 @@ get_lkcd_regs(struct bt_info *bt, ulong
> return;
> }
>
> + /* try to get it from the header */
> + if (get_lkcd_regs_for_cpu(bt, eip, esp) == 0)
> + return;
> +
> + /* if that fails: do guessing */
> sysrq_eip = sysrq_esp = 0;
>
> for (i = 0, up = (ulong *)bt->stackbuf; i < LONGS_PER_STACK; i++, up++){
> --- a/lkcd_dump_v8.h
> +++ b/lkcd_dump_v8.h
> @@ -235,4 +235,304 @@ typedef struct lkcdinfo_s {
> int stack_offset;
> } lkcdinfo_t;
>
> +/*
> + *
> + * machine specific dump headers
> + *
> + */
> +
> +/*
> + * IA64 ---------------------------------------------------------
> + */
> +
> +#if defined(IA64)
> +
> +#define DUMP_ASM_MAGIC_NUMBER 0xdeaddeadULL /* magic number */
> +#define DUMP_ASM_VERSION_NUMBER 0x5 /* version number */
> +
> +
> +struct pt_regs {
> + /* The following registers are saved by SAVE_MIN: */
> + unsigned long b6; /* scratch */
> + unsigned long b7; /* scratch */
> +
> + unsigned long ar_csd; /* used by cmp8xchg16 (scratch) */
> + unsigned long ar_ssd; /* reserved for future use (scratch) */
> +
> + unsigned long r8; /* scratch (return value register 0) */
> + unsigned long r9; /* scratch (return value register 1) */
> + unsigned long r10; /* scratch (return value register 2) */
> + unsigned long r11; /* scratch (return value register 3) */
> +
> + unsigned long cr_ipsr; /* interrupted task's psr */
> + unsigned long cr_iip; /* interrupted task's instruction pointer */
> + unsigned long cr_ifs; /* interrupted task's function state */
> +
> + unsigned long ar_unat; /* interrupted task's NaT register (preserved) */
> + unsigned long ar_pfs; /* prev function state */
> + unsigned long ar_rsc; /* RSE configuration */
> + /* The following two are valid only if cr_ipsr.cpl > 0: */
> + unsigned long ar_rnat; /* RSE NaT */
> + unsigned long ar_bspstore; /* RSE bspstore */
> +
> + unsigned long pr; /* 64 predicate registers (1 bit each) */
> + unsigned long b0; /* return pointer (bp) */
> + unsigned long loadrs; /* size of dirty partition << 16 */
> +
> + unsigned long r1; /* the gp pointer */
> + unsigned long r12; /* interrupted task's memory stack pointer */
> + unsigned long r13; /* thread pointer */
> +
> + unsigned long ar_fpsr; /* floating point status (preserved) */
> + unsigned long r15; /* scratch */
> +
> + /* The remaining registers are NOT saved for system calls. */
> +
> + unsigned long r14; /* scratch */
> + unsigned long r2; /* scratch */
> + unsigned long r3; /* scratch */
> +
> + /* The following registers are saved by SAVE_REST: */
> + unsigned long r16; /* scratch */
> + unsigned long r17; /* scratch */
> + unsigned long r18; /* scratch */
> + unsigned long r19; /* scratch */
> + unsigned long r20; /* scratch */
> + unsigned long r21; /* scratch */
> + unsigned long r22; /* scratch */
> + unsigned long r23; /* scratch */
> + unsigned long r24; /* scratch */
> + unsigned long r25; /* scratch */
> + unsigned long r26; /* scratch */
> + unsigned long r27; /* scratch */
> + unsigned long r28; /* scratch */
> + unsigned long r29; /* scratch */
> + unsigned long r30; /* scratch */
> + unsigned long r31; /* scratch */
> +
> + unsigned long ar_ccv; /* compare/exchange value (scratch) */
> +
> + /*
> + * Floating point registers that the kernel considers scratch:
> + */
> + struct ia64_fpreg f6; /* scratch */
> + struct ia64_fpreg f7; /* scratch */
> + struct ia64_fpreg f8; /* scratch */
> + struct ia64_fpreg f9; /* scratch */
> + struct ia64_fpreg f10; /* scratch */
> + struct ia64_fpreg f11; /* scratch */
> +};
> +
> +
> +
> +/*
> + * Structure: dump_header_asm_t
> + * Function: This is the header for architecture-specific stuff. It
> + * follows right after the dump header.
> + *
> + */
> +typedef struct __dump_header_asm_ia64 {
> +
> + /* the dump magic number -- unique to verify dump is valid */
> + uint64_t dha_magic_number;
> +
> + /* the version number of this dump */
> + uint32_t dha_version;
> +
> + /* the size of this header (in case we can't read it) */
> + uint32_t dha_header_size;
> +
> + /* pointer to pt_regs, (OLD: (struct pt_regs *, NEW: (uint64_t)) */
> + uint64_t dha_pt_regs;
> +
> + /* the dump registers */
> + struct pt_regs dha_regs;
> +
> + /* the rnat register saved after flushrs */
> + uint64_t dha_rnat;
> +
> + /* the pfs register saved after flushrs */
> + uint64_t dha_pfs;
> +
> + /* the bspstore register saved after flushrs */
> + uint64_t dha_bspstore;
> +
> + /* smp specific */
> + uint32_t dha_smp_num_cpus;
> + uint32_t dha_dumping_cpu;
> + struct pt_regs dha_smp_regs[NR_CPUS];
> + uint64_t dha_smp_current_task[NR_CPUS];
> + uint64_t dha_stack[NR_CPUS];
> + uint64_t dha_stack_ptr[NR_CPUS];
> +
> + /* load address of kernel */
> + uint64_t dha_kernel_addr;
> +
> +} __attribute__((packed)) dump_header_asm_ia64_t;
> +
> +struct dump_CPU_info_ia64 {
> + struct pt_regs dha_smp_regs;
> + uint64_t dha_smp_current_task;
> + uint64_t dha_stack;
> + uint64_t dha_stack_ptr;
> +} __attribute__((packed)) dump_CPU_info_ia64_t;
> +
> +typedef struct dump_CPU_info_ia64 dump_CPU_info_t;
> +typedef struct __dump_header_asm_ia64 dump_header_asm_t;
> +
> +#elif defined(X86)
> +
> +#define DUMP_ASM_MAGIC_NUMBER 0xdeaddeadULL /* magic number */
> +#define DUMP_ASM_VERSION_NUMBER 0x5 /* version number */
> +
> +
> +struct pt_regs {
> + long ebx;
> + long ecx;
> + long edx;
> + long esi;
> + long edi;
> + long ebp;
> + long eax;
> + int xds;
> + int xes;
> + long orig_eax;
> + long eip;
> + int xcs;
> + long eflags;
> + long esp;
> + int xss;
> +};
> +
> +/*
> + * Structure: __dump_header_asm
> + * Function: This is the header for architecture-specific stuff. It
> + * follows right after the dump header.
> + */
> +typedef struct __dump_header_asm_i386 {
> + /* the dump magic number -- unique to verify dump is valid */
> + uint64_t dha_magic_number;
> +
> + /* the version number of this dump */
> + uint32_t dha_version;
> +
> + /* the size of this header (in case we can't read it) */
> + uint32_t dha_header_size;
> +
> + /* the esp for i386 systems */
> + uint32_t dha_esp;
> +
> + /* the eip for i386 systems */
> + uint32_t dha_eip;
> +
> + /* the dump registers */
> + struct pt_regs dha_regs;
> +
> + /* smp specific */
> + uint32_t dha_smp_num_cpus;
> + uint32_t dha_dumping_cpu;
> + struct pt_regs dha_smp_regs[NR_CPUS];
> + uint32_t dha_smp_current_task[NR_CPUS];
> + uint32_t dha_stack[NR_CPUS];
> + uint32_t dha_stack_ptr[NR_CPUS];
> +} __attribute__((packed)) dump_header_asm_i386_t;
> +
> +/*
> + * CPU specific part of dump_header_asm_t
> + */
> +typedef struct dump_CPU_info_i386 {
> + struct pt_regs dha_smp_regs;
> + uint64_t dha_smp_current_task;
> + uint64_t dha_stack;
> + uint64_t dha_stack_ptr;
> +} __attribute__ ((packed)) dump_CPU_info_i386_t;
> +
> +
> +typedef struct __dump_header_asm_i386 dump_header_asm_t;
> +typedef struct dump_CPU_info_i386 dump_CPU_info_t;
> +
> +#elif defined(X86_64)
> +
> +/* definitions */
> +#define DUMP_ASM_MAGIC_NUMBER 0xdeaddeadULL /* magic number */
> +#define DUMP_ASM_VERSION_NUMBER 0x2 /* version number */
> +
> +
> +struct pt_regs {
> + unsigned long r15;
> + unsigned long r14;
> + unsigned long r13;
> + unsigned long r12;
> + unsigned long rbp;
> + unsigned long rbx;
> +/* arguments: non interrupts/non tracing syscalls only save upto here*/
> + unsigned long r11;
> + unsigned long r10;
> + unsigned long r9;
> + unsigned long r8;
> + unsigned long rax;
> + unsigned long rcx;
> + unsigned long rdx;
> + unsigned long rsi;
> + unsigned long rdi;
> + unsigned long orig_rax;
> +/* end of arguments */
> +/* cpu exception frame or undefined */
> + unsigned long rip;
> + unsigned long cs;
> + unsigned long eflags;
> + unsigned long rsp;
> + unsigned long ss;
> +/* top of stack page */
> +};
> +
> +/*
> + * Structure: dump_header_asm_t
> + * Function: This is the header for architecture-specific stuff. It
> + * follows right after the dump header.
> + */
> +typedef struct __dump_header_asm_x86_64 {
> +
> + /* the dump magic number -- unique to verify dump is valid */
> + uint64_t dha_magic_number;
> +
> + /* the version number of this dump */
> + uint32_t dha_version;
> +
> + /* the size of this header (in case we can't read it) */
> + uint32_t dha_header_size;
> +
> + /* the dump registers */
> + struct pt_regs dha_regs;
> +
> + /* smp specific */
> + uint32_t dha_smp_num_cpus;
> + int dha_dumping_cpu;
> + struct pt_regs dha_smp_regs[NR_CPUS];
> + uint64_t dha_smp_current_task[NR_CPUS];
> + uint64_t dha_stack[NR_CPUS];
> + uint64_t dha_stack_ptr[NR_CPUS];
> +} __attribute__((packed)) dump_header_asm_t_x86_64;
> +
> +
> +/*
> + * CPU specific part of dump_header_asm_t
> + */
> +typedef struct dump_CPU_info_x86_64 {
> + struct pt_regs dha_smp_regs;
> + uint64_t dha_smp_current_task;
> + uint64_t dha_stack;
> + uint64_t dha_stack_ptr;
> +} __attribute__ ((packed)) dump_CPU_info_x86_64_t;
> +
> +typedef struct dump_CPU_info_x86_64 dump_CPU_info_t;
> +typedef struct __dump_header_asm_x86_64 dump_header_asm_t;
> +
> +
> +#else
> +
> +#define HAVE_NO_DUMP_HEADER_ASM 1
> +
> +#endif
> +
> #endif /* _DUMP_H */
> --- a/lkcd_fix_mem.c
> +++ b/lkcd_fix_mem.c
> @@ -20,21 +20,13 @@
>
> #define LKCD_COMMON
> #include "defs.h"
> -#include "lkcd_fix_mem.h"
> +#include "lkcd_dump_v8.h"
>
> static int fix_addr(dump_header_asm_t *);
>
> int
> -fix_addr_v8(int fd)
> +fix_addr_v8(dump_header_asm_t *dha)
> {
> - static dump_header_asm_t dump_header_asm_v8 = { 0 };
> - dump_header_asm_t *dha;
> - dha = &dump_header_asm_v8;
> -
> - if (read(lkcd->fd, dha, sizeof(dump_header_asm_t)) !=
> - sizeof(dump_header_asm_t))
> - return -1;
> -
> fix_addr(dha);
>
> return 0;
> @@ -59,14 +51,6 @@ fix_addr_v7(int fd)
> static int
> fix_addr(dump_header_asm_t *dha)
> {
> -
> -
> - if (dha->dha_header_size != sizeof(dump_header_asm_t)) {
> - error(INFO, "LKCD machine specific dump header doesn't match crash version\n");
> - error(INFO, "traceback of currently executing threads may not work\n\n");
> - }
> -
> -
> lkcd->dump_header_asm = dha;
>
>
> @@ -83,7 +67,7 @@ fix_addr(dump_header_asm_t *dha)
> if (dha->dha_stack[i] && dha->dha_smp_current_task[i]) {
> lkcd->fix_addr[i].task = (ulong)dha->dha_smp_current_task[i];
> lkcd->fix_addr[i].saddr = (ulong)dha->dha_stack[i];
> - lkcd->fix_addr[i].sw = (ulong)dha->dha_switch_stack[i];
> + lkcd->fix_addr[i].sw = (ulong)dha->dha_stack_ptr[i];
> /* remember the highest non-zero entry */
> lkcd->fix_addr_num = i + 1;
> } else {
> --- a/lkcd_fix_mem.h
> +++ /dev/null
> @@ -1,295 +0,0 @@
> -#ifdef IA64
> -
> -#define UTSNAME_ENTRY_SZ 65
> -
> -/* necessary header definitions in all cases */
> -#define DUMP_KIOBUF_NUMBER 0xdeadbeef /* special number for kiobuf maps */
> -
> -/* size of a dump header page */
> -#define DUMP_PAGE_SZ 64 * 1024 /* size of dump page buffer */
> -
> -/* header definitions for s390 dump */
> -#define DUMP_MAGIC_S390 0xa8190173618f23fdULL /* s390 magic number */
> -#define S390_DUMP_HEADER_SIZE 4096
> -
> -/* standard header definitions */
> -#define DUMP_MAGIC_NUMBER 0xa8190173618f23edULL /* dump magic number */
> -#define DUMP_MAGIC_LIVE 0xa8190173618f23cdULL /* live magic number */
> -#define DUMP_VERSION_NUMBER 0x5 /* dump version number */
> -#define DUMP_PANIC_LEN 0x100 /* dump panic string length */
> -
> -/* dump levels - type specific stuff added later -- add as necessary */
> -#define DUMP_LEVEL_NONE 0x0 /* no dumping at all -- just bail */
> -#define DUMP_LEVEL_HEADER 0x1 /* kernel dump header only */
> -#define DUMP_LEVEL_KERN 0x2 /* dump header and kernel pages */
> -#define DUMP_LEVEL_USED 0x4 /* dump header, kernel/user pages */
> -#define DUMP_LEVEL_ALL 0x8 /* dump header, all memory pages */
> -
> -/* dump compression options -- add as necessary */
> -#define DUMP_COMPRESS_NONE 0x0 /* don't compress this dump */
> -#define DUMP_COMPRESS_RLE 0x1 /* use RLE compression */
> -#define DUMP_COMPRESS_GZIP 0x2 /* use GZIP compression */
> -
> -/* dump flags - any dump-type specific flags -- add as necessary */
> -#define DUMP_FLAGS_NONE 0x0 /* no flags are set for this dump */
> -#define DUMP_FLAGS_NONDISRUPT 0x1 /* try to keep running after dump */
> -
> -/* dump header flags -- add as necessary */
> -#define DUMP_DH_FLAGS_NONE 0x0 /* no flags set (error condition!) */
> -#define DUMP_DH_RAW 0x1 /* raw page (no compression) */
> -#define DUMP_DH_COMPRESSED 0x2 /* page is compressed */
> -#define DUMP_DH_END 0x4 /* end marker on a full dump */
> -
> -/* names for various dump tunables (they are now all read-only) */
> -#define DUMP_ROOT_NAME "sys/dump"
> -#define DUMP_DEVICE_NAME "dump_device"
> -#define DUMP_COMPRESS_NAME "dump_compress"
> -#define DUMP_LEVEL_NAME "dump_level"
> -#define DUMP_FLAGS_NAME "dump_flags"
> -
> -/* page size for gzip compression -- buffered beyond PAGE_SIZE slightly */
> -#define DUMP_DPC_PAGE_SIZE (PAGE_SIZE + 512)
> -
> -/* dump ioctl() control options */
> -#define DIOSDUMPDEV 1 /* set the dump device */
> -#define DIOGDUMPDEV 2 /* get the dump device */
> -#define DIOSDUMPLEVEL 3 /* set the dump level */
> -#define DIOGDUMPLEVEL 4 /* get the dump level */
> -#define DIOSDUMPFLAGS 5 /* set the dump flag parameters */
> -#define DIOGDUMPFLAGS 6 /* get the dump flag parameters */
> -#define DIOSDUMPCOMPRESS 7 /* set the dump compress level */
> -#define DIOGDUMPCOMPRESS 8 /* get the dump compress level */
> -
> -/* the major number used for the dumping device */
> -#ifndef DUMP_MAJOR
> -#define DUMP_MAJOR 227
> -#endif
> -
> -/*
> - * Structure: dump_header_t
> - * Function: This is the header dumped at the top of every valid crash
> - * dump.
> - * easy reassembly of each crash dump page. The address bits
> - * are split to make things easier for 64-bit/32-bit system
> - * conversions.
> - */
> -typedef struct _dump_header_s {
> - /* the dump magic number -- unique to verify dump is valid */
> - uint64_t dh_magic_number;
> -
> - /* the version number of this dump */
> - uint32_t dh_version;
> -
> - /* the size of this header (in case we can't read it) */
> - uint32_t dh_header_size;
> -
> - /* the level of this dump (just a header?) */
> - uint32_t dh_dump_level;
> -
> - /* the size of a Linux memory page (4K, 8K, 16K, etc.) */
> - uint32_t dh_page_size;
> -
> - /* the size of all physical memory */
> - uint64_t dh_memory_size;
> -
> - /* the start of physical memory */
> - uint64_t dh_memory_start;
> -
> - /* the end of physical memory */
> - uint64_t dh_memory_end;
> -
> - /* the number of pages in this dump specifically */
> - uint32_t dh_num_pages;
> -
> - /* the panic string, if available */
> - char dh_panic_string[DUMP_PANIC_LEN];
> -
> - /* timeval depends on architecture, two long values */
> - struct {
> - uint64_t tv_sec;
> - uint64_t tv_usec;
> - } dh_time; /* the time of the system crash */
> -
> - /* the NEW utsname (uname) information -- in character form */
> - /* we do this so we don't have to include utsname.h */
> - /* plus it helps us be more architecture independent */
> - /* now maybe one day soon they'll make the [65] a #define! */
> - char dh_utsname_sysname[65];
> - char dh_utsname_nodename[65];
> - char dh_utsname_release[65];
> - char dh_utsname_version[65];
> - char dh_utsname_machine[65];
> - char dh_utsname_domainname[65];
> -
> - /* the address of current task (OLD = task_struct *, NEW = void *) */
> - uint64_t dh_current_task;
> -
> - /* what type of compression we're using in this dump (if any) */
> - uint32_t dh_dump_compress;
> -
> - /* any additional flags */
> - uint32_t dh_dump_flags;
> -
> - /* any additional flags */
> - uint32_t dh_dump_device;
> -
> -} __attribute__((packed)) dump_header_t;
> -
> -/*
> - * Structure: dump_page_t
> - * Function: To act as the header associated to each physical page of
> - * memory saved in the system crash dump. This allows for
> - * easy reassembly of each crash dump page. The address bits
> - * are split to make things easier for 64-bit/32-bit system
> - * conversions.
> - */
> -typedef struct _dump_page_s {
> -
> - /* the address of this dump page */
> - uint64_t dp_address;
> -
> - /* the size of this dump page */
> - uint32_t dp_size;
> -
> - /* flags (currently DUMP_COMPRESSED, DUMP_RAW or DUMP_END) */
> - uint32_t dp_flags;
> -} __attribute__((packed)) dump_page_t;
> -
> -/*
> - * This structure contains information needed for the lkcdutils
> - * package (particularly lcrash) to determine what information is
> - * associated to this kernel, specifically.
> - */
> -typedef struct lkcdinfo_s {
> - int arch;
> - int ptrsz;
> - int byte_order;
> - int linux_release;
> - int page_shift;
> - int page_size;
> - uint64_t page_mask;
> - uint64_t page_offset;
> - int stack_offset;
> -} lkcdinfo_t;
> -
> -#define DUMP_ASM_MAGIC_NUMBER 0xdeaddeadULL /* magic number */
> -
> -
> -struct pt_regs {
> - /* The following registers are saved by SAVE_MIN: */
> - unsigned long b6; /* scratch */
> - unsigned long b7; /* scratch */
> -
> - unsigned long ar_csd; /* used by cmp8xchg16 (scratch) */
> - unsigned long ar_ssd; /* reserved for future use (scratch) */
> -
> - unsigned long r8; /* scratch (return value register 0) */
> - unsigned long r9; /* scratch (return value register 1) */
> - unsigned long r10; /* scratch (return value register 2) */
> - unsigned long r11; /* scratch (return value register 3) */
> -
> - unsigned long cr_ipsr; /* interrupted task's psr */
> - unsigned long cr_iip; /* interrupted task's instruction pointer */
> - unsigned long cr_ifs; /* interrupted task's function state */
> -
> - unsigned long ar_unat; /* interrupted task's NaT register (preserved) */
> - unsigned long ar_pfs; /* prev function state */
> - unsigned long ar_rsc; /* RSE configuration */
> - /* The following two are valid only if cr_ipsr.cpl > 0: */
> - unsigned long ar_rnat; /* RSE NaT */
> - unsigned long ar_bspstore; /* RSE bspstore */
> -
> - unsigned long pr; /* 64 predicate registers (1 bit each) */
> - unsigned long b0; /* return pointer (bp) */
> - unsigned long loadrs; /* size of dirty partition << 16 */
> -
> - unsigned long r1; /* the gp pointer */
> - unsigned long r12; /* interrupted task's memory stack pointer */
> - unsigned long r13; /* thread pointer */
> -
> - unsigned long ar_fpsr; /* floating point status (preserved) */
> - unsigned long r15; /* scratch */
> -
> - /* The remaining registers are NOT saved for system calls. */
> -
> - unsigned long r14; /* scratch */
> - unsigned long r2; /* scratch */
> - unsigned long r3; /* scratch */
> -
> - /* The following registers are saved by SAVE_REST: */
> - unsigned long r16; /* scratch */
> - unsigned long r17; /* scratch */
> - unsigned long r18; /* scratch */
> - unsigned long r19; /* scratch */
> - unsigned long r20; /* scratch */
> - unsigned long r21; /* scratch */
> - unsigned long r22; /* scratch */
> - unsigned long r23; /* scratch */
> - unsigned long r24; /* scratch */
> - unsigned long r25; /* scratch */
> - unsigned long r26; /* scratch */
> - unsigned long r27; /* scratch */
> - unsigned long r28; /* scratch */
> - unsigned long r29; /* scratch */
> - unsigned long r30; /* scratch */
> - unsigned long r31; /* scratch */
> -
> - unsigned long ar_ccv; /* compare/exchange value (scratch) */
> -
> - /*
> - * Floating point registers that the kernel considers scratch:
> - */
> - struct ia64_fpreg f6; /* scratch */
> - struct ia64_fpreg f7; /* scratch */
> - struct ia64_fpreg f8; /* scratch */
> - struct ia64_fpreg f9; /* scratch */
> - struct ia64_fpreg f10; /* scratch */
> - struct ia64_fpreg f11; /* scratch */
> -};
> -
> -
> -
> -/*
> - * Structure: dump_header_asm_t
> - * Function: This is the header for architecture-specific stuff. It
> - * follows right after the dump header.
> - *
> - */
> -typedef struct _dump_header_asm_s {
> -
> - /* the dump magic number -- unique to verify dump is valid */
> - uint64_t dha_magic_number;
> -
> - /* the version number of this dump */
> - uint32_t dha_version;
> -
> - /* the size of this header (in case we can't read it) */
> - uint32_t dha_header_size;
> -
> - /* pointer to pt_regs */
> -// struct pt_regs *dha_pt_regs; // version 4 changed this
> - uint64_t dha_pt_regs;
> -
> - /* the dump registers */
> - struct pt_regs dha_regs;
> -
> - /* the rnat register saved after flushrs */
> - uint64_t dha_rnat;
> -
> - /* the pfs register saved after flushrs */
> - uint64_t dha_pfs;
> -
> - /* the bspstore register saved after flushrs */
> - uint64_t dha_bspstore;
> -
> - /* smp specific */
> - uint32_t dha_smp_num_cpus;
> - uint32_t dha_dumping_cpu; // v4 changed this
> - struct pt_regs dha_smp_regs[NR_CPUS];
> - uint64_t dha_smp_current_task[NR_CPUS]; // v4 changed this
> - uint64_t dha_stack[NR_CPUS]; // v4 changed this
> - uint64_t dha_switch_stack[NR_CPUS]; // v4 changed this
> -
> -} __attribute__((packed)) dump_header_asm_t;
> -
> -#endif // IA64
> --- a/lkcd_v8.c
> +++ b/lkcd_v8.c
> @@ -23,11 +23,187 @@
> #include "lkcd_dump_v8.h" /* REMIND */
>
> static dump_header_t dump_header_v8 = { 0 };
> -// static dump_header_asm_t dump_header_asm_v8 = { 0 };
> +#ifndef HAVE_NO_DUMP_HEADER_ASM
> +static dump_header_asm_t dump_header_asm_v8 = { 0 };
> +#endif
> static dump_page_t dump_page = { 0 };
> static void mclx_cache_page_headers_v8(void);
> static off_t lkcd_offset_to_first_page = LKCD_OFFSET_TO_FIRST_PAGE;
>
> +#if defined(X86_64)
> +
> +int
> +get_lkcd_regs_for_cpu_arch(int cpu, ulong *eip, ulong *esp)
> +{
> + if (eip)
> + *eip = dump_header_asm_v8.dha_smp_regs[cpu].rip;
> + if (esp)
> + *esp = dump_header_asm_v8.dha_smp_regs[cpu].rsp;
> +
> + return 0;
> +}
> +
> +#elif defined(X86)
> +
> +int
> +get_lkcd_regs_for_cpu_arch(int cpu, ulong *eip, ulong *esp)
> +{
> + if (eip)
> + *eip = dump_header_asm_v8.dha_smp_regs[cpu].eip;
> + if (esp)
> + *esp = dump_header_asm_v8.dha_smp_regs[cpu].esp;
> +
> + return 0;
> +}
> +
> +#else
> +
> +int
> +get_lkcd_regs_for_cpu_arch(int cpu, ulong *eip, ulong *esp)
> +{
> + return -1;
> +}
> +
> +#endif
> +
> +
> +
> +int
> +get_lkcd_regs_for_cpu(struct bt_info *bt, ulong *eip, ulong *esp)
> +{
> + int cpu;
> +
> + if (!bt || !bt->tc) {
> + fprintf(stderr, "get_lkcd_regs_for_cpu: invalid tc\n", cpu);
> + return -EINVAL;
> + }
> +
> + cpu = bt->tc->processor;
> +
> + if (cpu >= NR_CPUS) {
> + fprintf(stderr, "get_lkcd_regs_for_cpu, cpu (%d) too high\n", cpu);
> + return -EINVAL;
> + }
> +
> + return get_lkcd_regs_for_cpu_arch(cpu, eip, esp);
> +}
> +
> +
> +#ifndef HAVE_NO_DUMP_HEADER_ASM
> +int
> +lkcd_dump_init_v8_arch(dump_header_t *dh)
> +{
> + off_t ret_of;
> + ssize_t ret_sz;
> + uint32_t hdr_size, offset, nr_cpus;
> + dump_header_asm_t arch_hdr;
> + char *hdr_buf = NULL;
> +
> + ret_of = lseek(lkcd->fd, dh->dh_header_size +
> + offsetof(dump_header_asm_t, dha_header_size),
> + SEEK_SET);
> + if (ret_of < 0) {
> + perror("lseek failed in " __FILE__ ":" STR(__LINE__));
> + goto err;
> + }
> +
> + ret_sz = read(lkcd->fd, (char *)&hdr_size, sizeof(hdr_size));
> + if (ret_sz != sizeof(hdr_size)) {
> + perror("Reading hdr_size failed in " __FILE__ ":" STR(__LINE__));
> + goto err;
> + }
> +
> + ret_of = lseek(lkcd->fd, dh->dh_header_size, SEEK_SET);
> + if (ret_of < 0) {
> + perror("lseek failed in " __FILE__ ":" STR(__LINE__));
> + goto err;
> + }
> +
> + hdr_buf = (char *)malloc(hdr_size);
> + if (!hdr_buf) {
> + perror("Could not allocate memory for dump header\n");
> + goto err;
> + }
> +
> + ret_sz = read(lkcd->fd, (char *)hdr_buf, hdr_size);
> + if (ret_sz != hdr_size) {
> + perror("Could not read header " __FILE__ ":" STR(__LINE__));
> + goto err;
> + }
> +
> +
> + /*
> + * Though we have KL_NR_CPUS is 128, the header size is different
> + * CONFIG_NR_CPUS might be different in the kernel. Hence, need
> + * to find out how many CPUs are configured.
> + */
> + offset = offsetof(dump_header_asm_t, dha_smp_regs[0]);
> + nr_cpus = (hdr_size - offset) / sizeof(dump_CPU_info_t);
> +
> + /* check for CPU overflow */
> + if (nr_cpus > NR_CPUS) {
> + fprintf(stderr, "CPU number too high %d (%s:%s)\n",
> + nr_cpus, __FILE__, __LINE__);
> + goto err;
> + }
> +
> + /* parts that don't depend on the number of CPUs */
> + memcpy(&arch_hdr, (void *)hdr_buf, offset);
> +
> + /* registers */
> + memcpy(&arch_hdr.dha_smp_regs, (void *)&hdr_buf[offset],
> + nr_cpus * sizeof(struct pt_regs));
> + offset += nr_cpus * sizeof(struct pt_regs);
> +
> + /* current task */
> + memcpy(&arch_hdr.dha_smp_current_task, (void *)&hdr_buf[offset],
> + nr_cpus * sizeof(&arch_hdr.dha_smp_current_task[0]));
> + offset += nr_cpus * sizeof(&arch_hdr.dha_smp_current_task[0]);
> +
> + /* stack */
> + memcpy(&arch_hdr.dha_stack, (void *)&hdr_buf[offset],
> + nr_cpus * sizeof(&arch_hdr.dha_stack[0]));
> + offset += nr_cpus * sizeof(&arch_hdr.dha_stack[0]);
> +
> + /* stack_ptr */
> + memcpy(&arch_hdr.dha_stack_ptr, (void *)&hdr_buf[offset],
> + nr_cpus * sizeof(&arch_hdr.dha_stack_ptr[0]));
> + offset += nr_cpus * sizeof(&arch_hdr.dha_stack_ptr[0]);
> +
> + if (arch_hdr.dha_magic_number != DUMP_ASM_MAGIC_NUMBER) {
> + fprintf(stderr, "Invalid magic number for x86_64\n");
> + goto err;
> + }
> +
> + /*
> + * read the kernel load address on IA64 -- other architectures have
> + * no relocatable kernel at the lifetime of LKCD
> + */
> +#ifdef IA64
> + memcpy(&arch_hdr.dha_kernel_addr, (void *)&hdr_buf[offset], sizeof(uint64_t));
> +#endif
> +
> + memcpy(&dump_header_asm_v8, &arch_hdr, sizeof(dump_header_asm_t));
> +
> + return 0;
> +
> +err:
> + free(hdr_buf);
> + return -1;
> +}
> +
> +#else /* architecture that has no lkcd_dump_init_v8 */
> +
> +int
> +lkcd_dump_init_v8_arch(dump_header_t *dh)
> +{
> + return 0;
> +}
> +
> +#endif
> +
> +
> +
> /*
> * Verify and initialize the LKCD environment, storing the common data
> * in the global lkcd_environment structure.
> @@ -69,8 +245,14 @@ lkcd_dump_init_v8(FILE *fp, int fd, char
> lkcd->dump_header = dh;
> if (lkcd->debug)
> dump_lkcd_environment(LKCD_DUMP_HEADER_ONLY);
> +
> + if (lkcd_dump_init_v8_arch(dh) != 0) {
> + fprintf(stderr, "Warning: Failed to initialise "
> + "arch specific dump code\n");
> + }
> +
> #ifdef IA64
> - if ( (fix_addr_v8(fd) == -1) )
> + if ( (fix_addr_v8(&dump_header_asm_v8) == -1) )
> return FALSE;
> #endif
>
> --- a/netdump.c
> +++ b/netdump.c
> @@ -1757,7 +1757,6 @@ struct x86_64_user_regs_struct {
> unsigned long fs_base, gs_base;
> unsigned long ds,es,fs,gs;
> };
> -#define offsetof(TYPE, MEMBER) ((ulong)&((TYPE *)0)->MEMBER)
>
> void
> get_netdump_regs_x86_64(struct bt_info *bt, ulong *ripp, ulong *rspp)
More information about the Crash-utility
mailing list