[PATCH] arm64: deduce the start address of kernel code, based on kernel version
by Pingfan Liu
After kernel commit e2a073dde921 ("arm64: omit [_text, _stext) from
permanent kernel mapping"), the range [_text, _stext] is reclaimed. But
the current crash code still assumes kernel starting from "_text".
This change only affects the vmalloced area on arm64 and may result a
false in arm64_IS_VMALLOC_ADDR().
Since vmcore has no extra information about this trival change, it can
only be deduced from kernel version, which means ms->kimage_text can not
be correctly initialized until kernel_init() finishes. This is fine
since there is no access to vmalloced area at this early stage.
Signed-off-by: Pingfan Liu <piliu(a)redhat.com>
---
arm64.c | 17 +++++++++++++++++
defs.h | 1 +
kernel.c | 3 +++
3 files changed, 21 insertions(+)
diff --git a/arm64.c b/arm64.c
index 4f2c2b5..4aa971c 100644
--- a/arm64.c
+++ b/arm64.c
@@ -92,6 +92,21 @@ static void arm64_calc_VA_BITS(void);
static int arm64_is_uvaddr(ulong, struct task_context *);
static void arm64_calc_KERNELPACMASK(void);
+/* called by kernel_init() */
+static void arm64_post_kernel_init(void)
+{
+ struct machine_specific *ms = machdep->machspec;
+ struct syment *sp;
+
+ if (THIS_KERNEL_VERSION >= LINUX(5,11,0))
+ sp = kernel_symbol_search("_stext");
+ else
+ sp = kernel_symbol_search("_text");
+
+ ms->kimage_text = (sp ? sp->value : 0);
+ sp = kernel_symbol_search("_end");
+ ms->kimage_end = (sp ? sp->value : 0);
+}
/*
* Do all necessary machine-specific setup here. This is called several times
@@ -104,6 +119,7 @@ arm64_init(int when)
char *string;
struct machine_specific *ms;
+ arch_post_kernel_init = arm64_post_kernel_init;
#if defined(__x86_64__)
if (ACTIVE())
error(FATAL, "compiled for the ARM64 architecture\n");
@@ -241,6 +257,7 @@ arm64_init(int when)
if (machdep->flags & NEW_VMEMMAP) {
struct syment *sp;
+ /* It is finally decided in arm64_post_kernel_init() */
sp = kernel_symbol_search("_text");
ms->kimage_text = (sp ? sp->value : 0);
sp = kernel_symbol_search("_end");
diff --git a/defs.h b/defs.h
index 7d386d2..04ab55a 100644
--- a/defs.h
+++ b/defs.h
@@ -5677,6 +5677,7 @@ struct command_table_entry *crash_cmd_table(void);
/*
* kernel.c
*/
+extern void (*arch_post_kernel_init)(void);
void kernel_init(void);
void module_init(void);
void verify_version(void);
diff --git a/kernel.c b/kernel.c
index 9c4aabf..b64ffac 100644
--- a/kernel.c
+++ b/kernel.c
@@ -98,6 +98,7 @@ static char *vmcoreinfo_read_string(const char *);
static void check_vmcoreinfo(void);
static int is_pvops_xen(void);
+void (*arch_post_kernel_init)(void);
/*
* Gather a few kernel basics.
@@ -823,6 +824,8 @@ kernel_init()
source_tree_init();
kt->flags &= ~PRE_KERNEL_INIT;
+ if (arch_post_kernel_init)
+ arch_post_kernel_init();
}
/*
--
2.31.1
2 years, 9 months
Re: [Crash-utility] [PATCH v3] Makefile: crash multi-target and multithread compile support
by lijiang
On Tue, Feb 22, 2022 at 1:19 PM <crash-utility-request(a)redhat.com> wrote:
> Date: Tue, 22 Feb 2022 04:25:18 +0000
> From: HAGIO KAZUHITO(?????) <k-hagio-ab(a)nec.com>
> To: Tao Liu <ltao(a)redhat.com>
> Cc: "Discussion list for crash utility usage, maintenance and
> development" <crash-utility(a)redhat.com>
> Subject: Re: [Crash-utility] [PATCH v3] Makefile: crash multi-target
> and multithread compile support
> Message-ID:
> <
> TYYPR01MB6777A51225457BCC4EF8C5C0DD3B9(a)TYYPR01MB6777.jpnprd01.prod.outlook.com
> >
>
> Content-Type: text/plain; charset="iso-2022-jp"
>
> -----Original Message-----
> > This patch will enable making crash as follows:
> >
> > $ make -j8 warn lzo zstd
> >
Thank you for the patch, Tao.
The v3 looks good to me. Applied and added the error in patch log.
Lianbo
>
> > Signed-off-by: Tao Liu <ltao(a)redhat.com>
>
> Thanks, looks good to me.
>
> Acked-by: Kazuhito Hagio <k-hagio-ab(a)nec.com>
>
> Kazu
>
>
> > ---
> > Makefile | 51 ++++++++++++++++++++++++---------------------------
> > 1 file changed, 24 insertions(+), 27 deletions(-)
> >
> > diff --git a/Makefile b/Makefile
> > index ede87a1..1ef96fa 100644
> > --- a/Makefile
> > +++ b/Makefile
> > @@ -223,6 +223,28 @@ ifneq ($(target),)
> > CONF_TARGET_FLAG="-t$(target)"
> > endif
> >
> > +ifeq ($(findstring warn,$(MAKECMDGOALS)),warn)
> > +CONF_TARGET_FLAG += -w
> > +endif
> > +ifeq ($(findstring Warn,$(MAKECMDGOALS)),Warn)
> > +CONF_TARGET_FLAG += -W
> > +endif
> > +ifeq ($(findstring nowarn,$(MAKECMDGOALS)),nowarn)
> > +CONF_TARGET_FLAG += -n
> > +endif
> > +ifeq ($(findstring lzo,$(MAKECMDGOALS)),lzo)
> > +CONF_TARGET_FLAG += -x lzo
> > +endif
> > +ifeq ($(findstring snappy,$(MAKECMDGOALS)),snappy)
> > +CONF_TARGET_FLAG += -x snappy
> > +endif
> > +ifeq ($(findstring zstd,$(MAKECMDGOALS)),zstd)
> > +CONF_TARGET_FLAG += -x zstd
> > +endif
> > +ifeq ($(findstring valgrind,$(MAKECMDGOALS)),valgrind)
> > +CONF_TARGET_FLAG += -x valgrind
> > +endif
> > +
> > # To build the extensions library by default, uncomment the third
> command
> > # line below. Otherwise they can be built by entering "make
> extensions".
> >
> > @@ -305,33 +327,8 @@ install:
> > unconfig: make_configure
> > @./configure -u
> >
> > -warn: make_configure
> > - @./configure ${CONF_TARGET_FLAG} -w -b
> > - @$(MAKE) gdb_merge
> > -
> > -Warn: make_configure
> > - @./configure ${CONF_TARGET_FLAG} -W -b
> > - @$(MAKE) gdb_merge
> > -
> > -nowarn: make_configure
> > - @./configure ${CONF_TARGET_FLAG} -n -b
> > - @$(MAKE) gdb_merge
> > -
> > -lzo: make_configure
> > - @./configure -x lzo ${CONF_TARGET_FLAG} -w -b
> > - @$(MAKE) gdb_merge
> > -
> > -snappy: make_configure
> > - @./configure -x snappy ${CONF_TARGET_FLAG} -w -b
> > - @$(MAKE) gdb_merge
> > -
> > -zstd: make_configure
> > - @./configure -x zstd ${CONF_TARGET_FLAG} -w -b
> > - @$(MAKE) gdb_merge
> > -
> > -valgrind: make_configure
> > - @./configure -x valgrind ${CONF_TARGET_FLAG} -w -b
> > - @$(MAKE) gdb_merge
> > +warn Warn nowarn lzo snappy zstd valgrind: all
> > + @true #dummy
> >
> > main.o: ${GENERIC_HFILES} main.c
> > ${CC} -c ${CRASH_CFLAGS} main.c ${WARNING_OPTIONS} ${WARNING_ERROR}
> > --
> > 2.33.1
>
2 years, 9 months
[PATCH v2] arm64: update the modules/vmalloc/vmemmap ranges
by Huang Shijie
< 1 > The background.
The current crash code is still based at kernel v4.20, but the kernel is v5.17-rc4(now).
The MODULE/VMALLOC/VMEMMAP ranges are not be updated since v4.20.
I list all the changes from kernel v4.20 to v5.17:
1.) The current crash code is based at kernel v4.20.
The virtual memory layout looks like this:
+--------------------------------------------------------------------+
| KASAN | MODULE | VMALLOC | .... | VMEMMAP |
+--------------------------------------------------------------------+
The macros are:
#define MODULES_VADDR (VA_START + KASAN_SHADOW_SIZE)
#define MODULES_END (MODULES_VADDR + MODULES_VSIZE)
#define VMALLOC_START (MODULES_END)
#define VMALLOC_END (PAGE_OFFSET - PUD_SIZE - VMEMMAP_SIZE - SZ_64K)
#define VMEMMAP_START (PAGE_OFFSET - VMEMMAP_SIZE)
2.) In the kernel v5.0, the patch will add a new BFP JIT region:
"91fc957c9b1d arm64/bpf: don't allocate BPF JIT programs in module memory"
The virtual memory layout looks like this:
+--------------------------------------------------------------------+
| KASAN | BPF_JIT | MODULE | VMALLOC | .... | VMEMMAP |
+--------------------------------------------------------------------+
The macros are:
#define MODULES_VADDR (BPF_JIT_REGION_END)
#define MODULES_END (MODULES_VADDR + MODULES_VSIZE)
#define VMALLOC_START (MODULES_END)
#define VMALLOC_END (PAGE_OFFSET - PUD_SIZE - VMEMMAP_SIZE - SZ_64K)
#define VMEMMAP_START (PAGE_OFFSET - VMEMMAP_SIZE)
The layout does not changed until v5.4.
3.) In the kernel v5.4, several patches changes the layout, such as:
"ce3aaed87344 arm64: mm: Modify calculation of VMEMMAP_SIZE"
"14c127c957c1 arm64: mm: Flip kernel VA space"
and the virtual memory layout looks like this:
+--------------------------------------------------------------------+
| KASAN | BPF_JIT | MODULE | VMALLOC | .... | VMEMMAP |
+--------------------------------------------------------------------+
The macros are:
#define MODULES_VADDR (BPF_JIT_REGION_END)
#define MODULES_END (MODULES_VADDR + MODULES_VSIZE)
#define VMALLOC_START (MODULES_END)
#define VMALLOC_END (- PUD_SIZE - VMEMMAP_SIZE - SZ_64K)
#define VMEMMAP_START (-VMEMMAP_SIZE - SZ_2M)
In the v5.7, the patch:
"bbd6ec605c arm64/mm: Enable memory hot remove"
adds the VMEMMAP_END.
4.) In the kernel v5.11, several patches changes the layout, such as:
"9ad7c6d5e75b arm64: mm: tidy up top of kernel VA space"
"f4693c2716b3 arm64: mm: extend linear region for 52-bit VA configurations"
and the virtual memory layout looks like this:
+--------------------------------------------------------------------+
| BPF_JIT | MODULE | VMALLOC | .... | VMEMMAP |
+--------------------------------------------------------------------+
The macros are:
#define MODULES_VADDR (BPF_JIT_REGION_END)
#define MODULES_END (MODULES_VADDR + MODULES_VSIZE)
#define VMALLOC_START (MODULES_END)
#define VMALLOC_END (VMEMMAP_START - SZ_256M)
#define VMEMMAP_START (-(UL(1) << (VA_BITS - VMEMMAP_SHIFT)))
#define VMEMMAP_END (VMEMMAP_START + VMEMMAP_SIZE)
5.) In the kernel v5.17-rc1, after the patch
"b89ddf4cca43 arm64/bpf: Remove 128MB limit for BPF JIT programs"
the virtual memory layout looks like this:
+--------------------------------------------------------------------+
| MODULE | VMALLOC | .... | VMEMMAP |
+--------------------------------------------------------------------+
The macros are:
#define MODULES_VADDR (_PAGE_END(VA_BITS_MIN))
#define MODULES_END (MODULES_VADDR + MODULES_VSIZE)
#define VMALLOC_START (MODULES_END)
#define VMALLOC_END (VMEMMAP_START - SZ_256M)
#define VMEMMAP_START (-(UL(1) << (VA_BITS - VMEMMAP_SHIFT)))
#define VMEMMAP_END (VMEMMAP_START + VMEMMAP_SIZE)
< 2 > What does this patch do?
1.) Use arm64_get_struct_page_size() to get the size of struct page{} in the PRE_GDB.
2.) If we can succeed in above step, we will try to call arm64_get_va_range() to
get the proper kernel virtual ranges.
In the arm64_get_va_range(), we calculate the ranges by the hooks of
different kernel versions:
get_range: arm64_get_range_v5_17,
get_range: arm64_get_range_v5_11,
get_range: arm64_get_range_v5_4,
get_range: arm64_get_range_v5_0,
3.) If we can succeed in above steps, the arm64_calc_virtual_memory_ranges()
will be ignored. If we failed in above steps, the arm64_calc_virtual_memory_ranges()
will continue to do its work.
< 3 > Test this patch.
Tested this patch with a vmcore produced by a 5.4.119 kernel panic.
(The CONFIG_KASAN is NOT set for this kernel.)
Before this patch, we get the wrong output from "help -m":
----------------------------------------------------------
vmalloc_start_addr: ffff800048000000
vmalloc_end: fffffdffbffeffff
modules_vaddr: ffff800040000000
modules_end: ffff800047ffffff
vmemmap_vaddr: fffffdffffe00000
vmemmap_end: ffffffffffffffff
----------------------------------------------------------
After this patch, we can get the correct output from "help -m":
----------------------------------------------------------
vmalloc_start_addr: ffff800010000000
vmalloc_end: fffffdffbfff0000
modules_vaddr: ffff800008000000
modules_end: ffff800010000000
vmemmap_vaddr: fffffdffffe00000
vmemmap_end: ffffffffffffffff
----------------------------------------------------------
Signed-off-by: Huang Shijie <shijie(a)os.amperecomputing.com>
---
v1 --> v2:
The Crash code is based on v4.20 not v4.9.
Changed the commit message about it.
---
arm64.c | 362 ++++++++++++++++++++++++++++++++++++++++++++++++++++++--
1 file changed, 354 insertions(+), 8 deletions(-)
diff --git a/arm64.c b/arm64.c
index de1038a..66b7754 100644
--- a/arm64.c
+++ b/arm64.c
@@ -92,6 +92,13 @@ static void arm64_calc_VA_BITS(void);
static int arm64_is_uvaddr(ulong, struct task_context *);
static void arm64_calc_KERNELPACMASK(void);
+struct kernel_range {
+ unsigned long modules_vaddr, modules_end;
+ unsigned long vmalloc_start_addr, vmalloc_end;
+ unsigned long vmemmap_vaddr, vmemmap_end;
+};
+static struct kernel_range *arm64_get_va_range(struct machine_specific *ms);
+static void arm64_get_struct_page_size(void);
/*
* Do all necessary machine-specific setup here. This is called several times
@@ -219,6 +226,7 @@ arm64_init(int when)
machdep->pageoffset = machdep->pagesize - 1;
machdep->pagemask = ~((ulonglong)machdep->pageoffset);
+ arm64_get_struct_page_size();
arm64_calc_VA_BITS();
arm64_calc_KERNELPACMASK();
ms = machdep->machspec;
@@ -238,35 +246,47 @@ arm64_init(int when)
}
machdep->is_kvaddr = generic_is_kvaddr;
machdep->kvtop = arm64_kvtop;
+
+ /* The defaults */
+ ms->vmalloc_end = ARM64_VMALLOC_END;
+ ms->vmemmap_vaddr = ARM64_VMEMMAP_VADDR;
+ ms->vmemmap_end = ARM64_VMEMMAP_END;
+
if (machdep->flags & NEW_VMEMMAP) {
struct syment *sp;
+ struct kernel_range *r;
sp = kernel_symbol_search("_text");
ms->kimage_text = (sp ? sp->value : 0);
sp = kernel_symbol_search("_end");
ms->kimage_end = (sp ? sp->value : 0);
- if (ms->VA_BITS_ACTUAL) {
+ if (ASSIGN_SIZE(page) && (r = arm64_get_va_range(ms))) {
+ /* We can get all the MODULES/VMALLOC/VMEMMAP ranges now.*/
+ ms->modules_vaddr = r->modules_vaddr;
+ ms->modules_end = r->modules_end;
+ ms->vmalloc_start_addr = r->vmalloc_start_addr;
+ ms->vmalloc_end = r->vmalloc_end;
+ ms->vmemmap_vaddr = r->vmemmap_vaddr;
+ ms->vmemmap_end = r->vmemmap_end;
+ } else if (ms->VA_BITS_ACTUAL) {
ms->modules_vaddr = (st->_stext_vmlinux & TEXT_OFFSET_MASK) - ARM64_MODULES_VSIZE;
ms->modules_end = ms->modules_vaddr + ARM64_MODULES_VSIZE -1;
+ ms->vmalloc_start_addr = ms->modules_end + 1;
} else {
ms->modules_vaddr = ARM64_VA_START;
if (kernel_symbol_exists("kasan_init"))
ms->modules_vaddr += ARM64_KASAN_SHADOW_SIZE;
ms->modules_end = ms->modules_vaddr + ARM64_MODULES_VSIZE -1;
+ ms->vmalloc_start_addr = ms->modules_end + 1;
}
- ms->vmalloc_start_addr = ms->modules_end + 1;
-
arm64_calc_kimage_voffset();
} else {
ms->modules_vaddr = ARM64_PAGE_OFFSET - MEGABYTES(64);
ms->modules_end = ARM64_PAGE_OFFSET - 1;
ms->vmalloc_start_addr = ARM64_VA_START;
}
- ms->vmalloc_end = ARM64_VMALLOC_END;
- ms->vmemmap_vaddr = ARM64_VMEMMAP_VADDR;
- ms->vmemmap_end = ARM64_VMEMMAP_END;
switch (machdep->pagesize)
{
@@ -387,7 +407,9 @@ arm64_init(int when)
break;
case POST_GDB:
- arm64_calc_virtual_memory_ranges();
+ /* Can we get the size of struct page before POST_GDB */
+ if (!ASSIGN_SIZE(page))
+ arm64_calc_virtual_memory_ranges();
arm64_get_section_size_bits();
if (!machdep->max_physmem_bits) {
@@ -494,6 +516,331 @@ arm64_init(int when)
}
}
+struct kernel_va_range_handler {
+ unsigned long kernel_versions_start; /* include */
+ unsigned long kernel_versions_end; /* exclude */
+ struct kernel_range *(*get_range)(struct machine_specific *);
+};
+
+static struct kernel_range tmp_range;
+#define _PAGE_END(va) (-(1UL << ((va) - 1)))
+#define SZ_64K 0x00010000
+#define SZ_2M 0x00200000
+
+/*
+ * Get the max shift of the size of struct page.
+ * Most of the time, it is 64 bytes, but not sure.
+ */
+static int arm64_get_struct_page_max_shift(void)
+{
+ unsigned long v = ASSIGN_SIZE(page);
+
+ if (16 < v && v <= 32)
+ return 5;
+ if (32 < v && v <= 64)
+ return 6;
+ if (64 < v && v <= 128)
+ return 7;
+
+ error(FATAL, "We should not have such struct page size:%d!\n", v);
+ return 0;
+}
+
+/*
+ * The change is caused by the kernel patch since v5.17-rc1:
+ * "b89ddf4cca43 arm64/bpf: Remove 128MB limit for BPF JIT programs"
+ */
+static struct kernel_range *arm64_get_range_v5_17(struct machine_specific *ms)
+{
+ struct kernel_range *r = &tmp_range;
+ unsigned long v = ms->CONFIG_ARM64_VA_BITS;
+ unsigned long vmem_shift, vmemmap_size;
+
+ /* Not initialized yet */
+ if (v == 0)
+ return NULL;
+
+ if (v > 48)
+ v = 48;
+
+ /* Get the MODULES_VADDR ~ MODULES_END */
+ r->modules_vaddr = _PAGE_END(v);
+ r->modules_end = r->modules_vaddr + MEGABYTES(128);
+
+ /* Get the VMEMMAP_START ~ VMEMMAP_END */
+ vmem_shift = machdep->pageshift - arm64_get_struct_page_max_shift();
+ vmemmap_size = (_PAGE_END(v) - PAGE_OFFSET) >> vmem_shift;
+
+ r->vmemmap_vaddr = (-(1UL << (ms->VA_BITS - vmem_shift)));
+ r->vmemmap_end = r->vmemmap_vaddr + vmemmap_size;
+
+ /* Get the VMALLOC_START ~ VMALLOC_END */
+ r->vmalloc_start_addr = r->modules_end;
+ r->vmalloc_end = r->vmemmap_vaddr - MEGABYTES(256);
+ return r;
+}
+
+/*
+ * The change is caused by the kernel patch since v5.11:
+ * "9ad7c6d5e75b arm64: mm: tidy up top of kernel VA space"
+ */
+static struct kernel_range *arm64_get_range_v5_11(struct machine_specific *ms)
+{
+ struct kernel_range *r = &tmp_range;
+ unsigned long v = ms->CONFIG_ARM64_VA_BITS;
+ unsigned long vmem_shift, vmemmap_size, bpf_jit_size = MEGABYTES(128);
+
+ /* Not initialized yet */
+ if (v == 0)
+ return NULL;
+
+ if (v > 48)
+ v = 48;
+
+ /* Get the MODULES_VADDR ~ MODULES_END */
+ r->modules_vaddr = _PAGE_END(v) + bpf_jit_size;
+ r->modules_end = r->modules_vaddr + MEGABYTES(128);
+
+ /* Get the VMEMMAP_START ~ VMEMMAP_END */
+ vmem_shift = machdep->pageshift - arm64_get_struct_page_max_shift();
+ vmemmap_size = (_PAGE_END(v) - PAGE_OFFSET) >> vmem_shift;
+
+ r->vmemmap_vaddr = (-(1UL << (ms->VA_BITS - vmem_shift)));
+ r->vmemmap_end = r->vmemmap_vaddr + vmemmap_size;
+
+ /* Get the VMALLOC_START ~ VMALLOC_END */
+ r->vmalloc_start_addr = r->modules_end;
+ r->vmalloc_end = r->vmemmap_vaddr - MEGABYTES(256);
+ return r;
+}
+
+static unsigned long arm64_get_pud_size(void)
+{
+ unsigned long PUD_SIZE = 0;
+
+ switch (machdep->pagesize) {
+ case 4096:
+ if (machdep->machspec->VA_BITS > PGDIR_SHIFT_L4_4K) {
+ PUD_SIZE = PUD_SIZE_L4_4K;
+ } else {
+ PUD_SIZE = PGDIR_SIZE_L3_4K;
+ }
+ break;
+
+ case 65536:
+ PUD_SIZE = PGDIR_SIZE_L2_64K;
+ default:
+ break;
+ }
+ return PUD_SIZE;
+}
+
+/*
+ * The change is caused by the kernel patches since v5.4, such as:
+ * "ce3aaed87344 arm64: mm: Modify calculation of VMEMMAP_SIZE"
+ * "14c127c957c1 arm64: mm: Flip kernel VA space"
+ */
+static struct kernel_range *arm64_get_range_v5_4(struct machine_specific *ms)
+{
+ struct kernel_range *r = &tmp_range;
+ unsigned long v = ms->CONFIG_ARM64_VA_BITS;
+ unsigned long kasan_shadow_shift, kasan_shadow_offset, PUD_SIZE;
+ unsigned long vmem_shift, vmemmap_size, bpf_jit_size = MEGABYTES(128);
+ char *string;
+ int ret;
+
+ /* Not initialized yet */
+ if (v == 0)
+ return NULL;
+
+ if (v > 48)
+ v = 48;
+
+ /* Get the MODULES_VADDR ~ MODULES_END */
+ if (kernel_symbol_exists("kasan_init")) {
+ /* See the arch/arm64/Makefile */
+ ret = get_kernel_config("CONFIG_KASAN_SW_TAGS", NULL);
+ if (ret == IKCONFIG_N)
+ return NULL;
+ kasan_shadow_shift = (ret == IKCONFIG_Y) ? 4: 3;
+
+ /* See the arch/arm64/Kconfig*/
+ ret = get_kernel_config("CONFIG_KASAN_SHADOW_OFFSET", &string);
+ if (ret != IKCONFIG_STR)
+ return NULL;
+ kasan_shadow_offset = atol(string);
+
+ r->modules_vaddr = (1UL << (64 - kasan_shadow_shift)) + kasan_shadow_offset
+ + bpf_jit_size;
+ } else {
+ r->modules_vaddr = _PAGE_END(v) + bpf_jit_size;
+ }
+
+ r->modules_end = r->modules_vaddr + MEGABYTES(128);
+
+ /* Get the VMEMMAP_START ~ VMEMMAP_END */
+ vmem_shift = machdep->pageshift - arm64_get_struct_page_max_shift();
+ vmemmap_size = (_PAGE_END(v) - PAGE_OFFSET) >> vmem_shift;
+
+ r->vmemmap_vaddr = (-vmemmap_size - SZ_2M);
+ if (THIS_KERNEL_VERSION >= LINUX(5, 7, 0)) {
+ /*
+ * In the v5.7, the patch: "bbd6ec605c arm64/mm: Enable memory hot remove"
+ * adds the VMEMMAP_END.
+ */
+ r->vmemmap_end = r->vmemmap_vaddr + vmemmap_size;
+ } else {
+ r->vmemmap_end = 0xffffffffffffffffUL;
+ }
+
+ /* Get the VMALLOC_START ~ VMALLOC_END */
+ PUD_SIZE = arm64_get_pud_size();
+ r->vmalloc_start_addr = r->modules_end;
+ r->vmalloc_end = (-PUD_SIZE - vmemmap_size - SZ_64K);
+ return r;
+}
+
+/*
+ * The change is caused by the kernel patches since v5.0, such as:
+ * "91fc957c9b1d arm64/bpf: don't allocate BPF JIT programs in module memory"
+ */
+static struct kernel_range *arm64_get_range_v5_0(struct machine_specific *ms)
+{
+ struct kernel_range *r = &tmp_range;
+ unsigned long v = ms->CONFIG_ARM64_VA_BITS;
+ unsigned long kasan_shadow_shift, PUD_SIZE;
+ unsigned long vmemmap_size, bpf_jit_size = MEGABYTES(128);
+ unsigned long va_start, page_offset;
+ int ret;
+
+ /* Not initialized yet */
+ if (v == 0)
+ return NULL;
+
+ va_start = (0xffffffffffffffffUL - (1UL << v) + 1);
+ page_offset = (0xffffffffffffffffUL - (1UL << (v - 1)) + 1);
+
+ /* Get the MODULES_VADDR ~ MODULES_END */
+ if (kernel_symbol_exists("kasan_init")) {
+ /* See the arch/arm64/Makefile */
+ ret = get_kernel_config("CONFIG_KASAN_SW_TAGS", NULL);
+ if (ret == IKCONFIG_N)
+ return NULL;
+ kasan_shadow_shift = (ret == IKCONFIG_Y) ? 4: 3;
+
+ r->modules_vaddr = va_start + (1UL << (v - kasan_shadow_shift)) + bpf_jit_size;
+ } else {
+ r->modules_vaddr = va_start + bpf_jit_size;
+ }
+
+ r->modules_end = r->modules_vaddr + MEGABYTES(128);
+
+ /* Get the VMEMMAP_START ~ VMEMMAP_END */
+ vmemmap_size = (1UL << (v - machdep->pageshift - 1 + arm64_get_struct_page_max_shift()));
+
+ r->vmemmap_vaddr = page_offset - vmemmap_size;
+ r->vmemmap_end = 0xffffffffffffffffUL; /* this kernel does not have VMEMMAP_END */
+
+ /* Get the VMALLOC_START ~ VMALLOC_END */
+ PUD_SIZE = arm64_get_pud_size();
+
+ r->vmalloc_start_addr = r->modules_end;
+ r->vmalloc_end = page_offset - PUD_SIZE - vmemmap_size - SZ_64K;
+ return r;
+}
+
+static struct kernel_va_range_handler kernel_va_range_handlers[] = {
+ {
+ LINUX(5,17,0),
+ LINUX(6,0,0), /* Just a boundary, Change it later */
+ get_range: arm64_get_range_v5_17,
+ }, {
+ LINUX(5,11,0), LINUX(5,17,0),
+ get_range: arm64_get_range_v5_11,
+ }, {
+ LINUX(5,4,0), LINUX(5,11,0),
+ get_range: arm64_get_range_v5_4,
+ }, {
+ LINUX(5,0,0), LINUX(5,4,0),
+ get_range: arm64_get_range_v5_0,
+ },
+};
+
+#define ARRAY_SIZE(a) (sizeof (a) / sizeof ((a)[0]))
+
+static unsigned long arm64_get_kernel_version(void)
+{
+ char *string;
+ char buf[BUFSIZE];
+ char *p1, *p2;
+
+ if (THIS_KERNEL_VERSION)
+ return THIS_KERNEL_VERSION;
+
+ string = pc->read_vmcoreinfo("OSRELEASE");
+ if (string) {
+ strcpy(buf, string);
+
+ p1 = p2 = buf;
+ while (*p2 != '.')
+ p2++;
+ *p2 = NULLCHAR;
+ kt->kernel_version[0] = atoi(p1);
+
+ p1 = ++p2;
+ while (*p2 != '.')
+ p2++;
+ *p2 = NULLCHAR;
+ kt->kernel_version[1] = atoi(p1);
+
+ p1 = ++p2;
+ while ((*p2 >= '0') && (*p2 <= '9'))
+ p2++;
+ *p2 = NULLCHAR;
+ kt->kernel_version[2] = atoi(p1);
+ }
+ free(string);
+ return THIS_KERNEL_VERSION;
+}
+
+/* Return NULL if we fail. */
+static struct kernel_range *arm64_get_va_range(struct machine_specific *ms)
+{
+ struct kernel_va_range_handler *h;
+ unsigned long kernel_version = THIS_KERNEL_VERSION;
+ int i;
+
+ if (!kernel_version) {
+ kernel_version = arm64_get_kernel_version();
+ if (!kernel_version)
+ return NULL;
+ }
+
+ for (i = 0; i < ARRAY_SIZE(kernel_va_range_handlers); i++) {
+ h = kernel_va_range_handlers + i;
+
+ /* Get the right kernel version */
+ if (h->kernel_versions_start <= kernel_version &&
+ kernel_version < h->kernel_versions_end) {
+
+ /* Get the correct virtual address ranges */
+ return h->get_range(ms);
+ }
+ }
+ return NULL;
+}
+
+/* Get the size of struct page {} */
+static void arm64_get_struct_page_size()
+{
+ char *string;
+
+ string = pc->read_vmcoreinfo("SIZE(page)");
+ if (string)
+ ASSIGN_SIZE(page) = atol(string);
+ free(string);
+}
+
/*
* Accept or reject a symbol from the kernel namelist.
*/
@@ -4255,7 +4602,6 @@ arm64_calc_VA_BITS(void)
#define ALIGN(x, a) __ALIGN_KERNEL((x), (a))
#define __ALIGN_KERNEL(x, a) __ALIGN_KERNEL_MASK(x, (typeof(x))(a) - 1)
#define __ALIGN_KERNEL_MASK(x, mask) (((x) + (mask)) & ~(mask))
-#define SZ_64K 0x00010000
static void
arm64_calc_virtual_memory_ranges(void)
--
2.30.2
2 years, 9 months
[PATCH] x86_64_init: Refresh vmalloc region addresses in POST_RELOC instead of POST_GDB phase
by Tao Liu
Previously for x86_64, when memory is randomized, the region addresses
such as vmalloc_start_addr/vmemmap_vaddr/modules_vaddr are firstly set
to a default value before POST_RELOC phase, then get refreshed with the
actual value in POST_GDB phase.
However for crash mininal mode, POST_GDB phase is not called, which
leaving the region addresses unrefreshed and incorrect. As a consequence,
the x86_64_IS_VMALLOC_ADDR check will give a faulty result when
value_search tries to search a symbol by address.
For example, in crash minimal mode we can observe the following issue:
crash> dis -f panic
dis: cannot resolve address: ffffffffb20e0d30
crash> sym panic
ffffffffb20e0d30 (T) panic /usr/src/debug/kernel-4.18.0-290/linux-4.18.0-290/kernel/panic.c: 168
crash> sym ffffffffb20e0d30
symbol not found: ffffffffb20e0d30
In this patch, we will move the code which update the region addresses into
POST_RELOC phase, so in mininal mode the regions can get the correct
addresses.
Signed-off-by: Tao Liu <ltao(a)redhat.com>
---
x86_64.c | 52 ++++++++++++++++++++++++++--------------------------
1 file changed, 26 insertions(+), 26 deletions(-)
diff --git a/x86_64.c b/x86_64.c
index 552d619..2fb1277 100644
--- a/x86_64.c
+++ b/x86_64.c
@@ -384,6 +384,31 @@ x86_64_init(int when)
"page_offset_base", QUIET|FAULT_ON_ERROR);
machdep->kvbase = machdep->machspec->page_offset;
machdep->identity_map_base = machdep->machspec->page_offset;
+
+ readmem(symbol_value("vmalloc_base"), KVADDR,
+ &machdep->machspec->vmalloc_start_addr,
+ sizeof(ulong), "vmalloc_base", FAULT_ON_ERROR);
+ if (machdep->flags & VM_5LEVEL)
+ machdep->machspec->vmalloc_end =
+ machdep->machspec->vmalloc_start_addr + TERABYTES(1280) - 1;
+ else
+ machdep->machspec->vmalloc_end =
+ machdep->machspec->vmalloc_start_addr + TERABYTES(32) - 1;
+ if (kernel_symbol_exists("vmemmap_base")) {
+ readmem(symbol_value("vmemmap_base"), KVADDR,
+ &machdep->machspec->vmemmap_vaddr, sizeof(ulong),
+ "vmemmap_base", FAULT_ON_ERROR);
+ machdep->machspec->vmemmap_end =
+ machdep->machspec->vmemmap_vaddr +
+ TERABYTES(1) - 1;
+ } else {
+ machdep->machspec->vmemmap_vaddr = VMEMMAP_VADDR_2_6_31;
+ machdep->machspec->vmemmap_end = VMEMMAP_END_2_6_31;
+ }
+ machdep->machspec->modules_vaddr = __START_KERNEL_map +
+ (machdep->machspec->kernel_image_size ?
+ machdep->machspec->kernel_image_size : GIGABYTES(1));
+ machdep->machspec->modules_end = MODULES_END_2_6_31;
}
break;
@@ -414,32 +439,7 @@ x86_64_init(int when)
machdep->machspec->modules_end = MODULES_END_2_6_27;
}
if (THIS_KERNEL_VERSION >= LINUX(2,6,31)) {
- if (machdep->flags & RANDOMIZED) {
- readmem(symbol_value("vmalloc_base"), KVADDR,
- &machdep->machspec->vmalloc_start_addr,
- sizeof(ulong), "vmalloc_base", FAULT_ON_ERROR);
- if (machdep->flags & VM_5LEVEL)
- machdep->machspec->vmalloc_end =
- machdep->machspec->vmalloc_start_addr + TERABYTES(1280) - 1;
- else
- machdep->machspec->vmalloc_end =
- machdep->machspec->vmalloc_start_addr + TERABYTES(32) - 1;
- if (kernel_symbol_exists("vmemmap_base")) {
- readmem(symbol_value("vmemmap_base"), KVADDR,
- &machdep->machspec->vmemmap_vaddr, sizeof(ulong),
- "vmemmap_base", FAULT_ON_ERROR);
- machdep->machspec->vmemmap_end =
- machdep->machspec->vmemmap_vaddr +
- TERABYTES(1) - 1;
- } else {
- machdep->machspec->vmemmap_vaddr = VMEMMAP_VADDR_2_6_31;
- machdep->machspec->vmemmap_end = VMEMMAP_END_2_6_31;
- }
- machdep->machspec->modules_vaddr = __START_KERNEL_map +
- (machdep->machspec->kernel_image_size ?
- machdep->machspec->kernel_image_size : GIGABYTES(1));
- machdep->machspec->modules_end = MODULES_END_2_6_31;
- } else {
+ if (!(machdep->flags & RANDOMIZED)) {
machdep->machspec->vmalloc_start_addr = VMALLOC_START_ADDR_2_6_31;
machdep->machspec->vmalloc_end = VMALLOC_END_2_6_31;
machdep->machspec->vmemmap_vaddr = VMEMMAP_VADDR_2_6_31;
--
2.33.1
2 years, 9 months
[v3 0/2] sbitmapq command
by Sergey Samoylenko
The first patch adds the sbitmapq command to the crash. The second
adds '-p' option for sbitmapq command. The option says that
an associated with sbitmap_queue array contains the pointers of data.
Sergey Samoylenko (2):
sbitmapq command
'-p' option for sbitmapq command
Makefile | 7 +-
defs.h | 59 +++++
global_data.c | 1 +
help.c | 105 ++++++++
sbitmap.c | 677 ++++++++++++++++++++++++++++++++++++++++++++++++++
symbols.c | 39 +++
6 files changed, 886 insertions(+), 2 deletions(-)
create mode 100644 sbitmap.c
--
2.25.1
2 years, 9 months
[PATCH v2] arm64: Use CONFIG_ARM64_VA_BITS to initialize VA_BITS_ACTUAL
by Huang Shijie
We can get VA_BITS_ACTUAL from CONFIG_ARM64_VA_BITS by guess.
Without this patch, we may need to use "--machdep vabits_actual=48" to
set the VA_BITS_ACTUAL.
Signed-off-by: Huang Shijie <shijie(a)os.amperecomputing.com>
---
v1 --> v2:
Remove the DISKDUMP limit.
---
arm64.c | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/arm64.c b/arm64.c
index 4f2c2b5..de1038a 100644
--- a/arm64.c
+++ b/arm64.c
@@ -4170,6 +4170,11 @@ arm64_calc_VA_BITS(void)
} else if (machdep->machspec->VA_BITS_ACTUAL) {
machdep->machspec->VA_BITS = machdep->machspec->VA_BITS_ACTUAL;
machdep->machspec->VA_START = _VA_START(machdep->machspec->VA_BITS_ACTUAL);
+ } else if (machdep->machspec->CONFIG_ARM64_VA_BITS) {
+ /* guess */
+ machdep->machspec->VA_BITS_ACTUAL = machdep->machspec->CONFIG_ARM64_VA_BITS;
+ machdep->machspec->VA_BITS = machdep->machspec->CONFIG_ARM64_VA_BITS;
+ machdep->machspec->VA_START = _VA_START(machdep->machspec->VA_BITS_ACTUAL);
} else
error(FATAL, "cannot determine VA_BITS_ACTUAL\n");
}
--
2.30.2
2 years, 9 months
[PATCH v3] Makefile: crash multi-target and multithread compile support
by Tao Liu
This patch will enable making crash as follows:
$ make -j8 warn lzo zstd
Signed-off-by: Tao Liu <ltao(a)redhat.com>
---
Makefile | 51 ++++++++++++++++++++++++---------------------------
1 file changed, 24 insertions(+), 27 deletions(-)
diff --git a/Makefile b/Makefile
index ede87a1..1ef96fa 100644
--- a/Makefile
+++ b/Makefile
@@ -223,6 +223,28 @@ ifneq ($(target),)
CONF_TARGET_FLAG="-t$(target)"
endif
+ifeq ($(findstring warn,$(MAKECMDGOALS)),warn)
+CONF_TARGET_FLAG += -w
+endif
+ifeq ($(findstring Warn,$(MAKECMDGOALS)),Warn)
+CONF_TARGET_FLAG += -W
+endif
+ifeq ($(findstring nowarn,$(MAKECMDGOALS)),nowarn)
+CONF_TARGET_FLAG += -n
+endif
+ifeq ($(findstring lzo,$(MAKECMDGOALS)),lzo)
+CONF_TARGET_FLAG += -x lzo
+endif
+ifeq ($(findstring snappy,$(MAKECMDGOALS)),snappy)
+CONF_TARGET_FLAG += -x snappy
+endif
+ifeq ($(findstring zstd,$(MAKECMDGOALS)),zstd)
+CONF_TARGET_FLAG += -x zstd
+endif
+ifeq ($(findstring valgrind,$(MAKECMDGOALS)),valgrind)
+CONF_TARGET_FLAG += -x valgrind
+endif
+
# To build the extensions library by default, uncomment the third command
# line below. Otherwise they can be built by entering "make extensions".
@@ -305,33 +327,8 @@ install:
unconfig: make_configure
@./configure -u
-warn: make_configure
- @./configure ${CONF_TARGET_FLAG} -w -b
- @$(MAKE) gdb_merge
-
-Warn: make_configure
- @./configure ${CONF_TARGET_FLAG} -W -b
- @$(MAKE) gdb_merge
-
-nowarn: make_configure
- @./configure ${CONF_TARGET_FLAG} -n -b
- @$(MAKE) gdb_merge
-
-lzo: make_configure
- @./configure -x lzo ${CONF_TARGET_FLAG} -w -b
- @$(MAKE) gdb_merge
-
-snappy: make_configure
- @./configure -x snappy ${CONF_TARGET_FLAG} -w -b
- @$(MAKE) gdb_merge
-
-zstd: make_configure
- @./configure -x zstd ${CONF_TARGET_FLAG} -w -b
- @$(MAKE) gdb_merge
-
-valgrind: make_configure
- @./configure -x valgrind ${CONF_TARGET_FLAG} -w -b
- @$(MAKE) gdb_merge
+warn Warn nowarn lzo snappy zstd valgrind: all
+ @true #dummy
main.o: ${GENERIC_HFILES} main.c
${CC} -c ${CRASH_CFLAGS} main.c ${WARNING_OPTIONS} ${WARNING_ERROR}
--
2.33.1
2 years, 9 months
[PATCH] Makefile: crash multi-target and multithread compile support
by Tao Liu
This patch will enable making crash as follows:
$ make -j8 warn lzo zstd
Signed-off-by: Tao Liu <ltao(a)redhat.com>
---
Makefile | 50 ++++++++++++++++++++++++++++++--------------------
1 file changed, 30 insertions(+), 20 deletions(-)
diff --git a/Makefile b/Makefile
index ede87a1..79017a0 100644
--- a/Makefile
+++ b/Makefile
@@ -305,33 +305,43 @@ install:
unconfig: make_configure
@./configure -u
-warn: make_configure
- @./configure ${CONF_TARGET_FLAG} -w -b
+config: make_configure
+ if [ -n "$(findstring warn,$(MAKECMDGOALS))" ]; then \
+ ./configure ${CONF_TARGET_FLAG} -w -b; fi
+ if [ -n "$(findstring Warn,$(MAKECMDGOALS))" ]; then \
+ ./configure ${CONF_TARGET_FLAG} -W -b; fi
+ if [ -n "$(findstring nowarn,$(MAKECMDGOALS))" ]; then \
+ ./configure ${CONF_TARGET_FLAG} -n -b; fi
+ if [ -n "$(findstring lzo,$(MAKECMDGOALS))" ]; then \
+ ./configure -x lzo ${CONF_TARGET_FLAG} -w -b; fi
+ if [ -n "$(findstring snappy,$(MAKECMDGOALS))" ]; then \
+ ./configure -x snappy ${CONF_TARGET_FLAG} -w -b; fi
+ if [ -n "$(findstring zstd,$(MAKECMDGOALS))" ]; then \
+ ./configure -x zstd ${CONF_TARGET_FLAG} -w -b; fi
+ if [ -n "$(findstring valgrind,$(MAKECMDGOALS))" ]; then \
+ ./configure -x valgrind ${CONF_TARGET_FLAG} -w -b; fi
@$(MAKE) gdb_merge
-Warn: make_configure
- @./configure ${CONF_TARGET_FLAG} -W -b
- @$(MAKE) gdb_merge
+warn: config
+
-nowarn: make_configure
- @./configure ${CONF_TARGET_FLAG} -n -b
- @$(MAKE) gdb_merge
+Warn: config
+
-lzo: make_configure
- @./configure -x lzo ${CONF_TARGET_FLAG} -w -b
- @$(MAKE) gdb_merge
+nowarn: config
+
-snappy: make_configure
- @./configure -x snappy ${CONF_TARGET_FLAG} -w -b
- @$(MAKE) gdb_merge
+lzo: config
+
-zstd: make_configure
- @./configure -x zstd ${CONF_TARGET_FLAG} -w -b
- @$(MAKE) gdb_merge
+snappy: config
+
-valgrind: make_configure
- @./configure -x valgrind ${CONF_TARGET_FLAG} -w -b
- @$(MAKE) gdb_merge
+zstd: config
+
+
+valgrind: config
+
main.o: ${GENERIC_HFILES} main.c
${CC} -c ${CRASH_CFLAGS} main.c ${WARNING_OPTIONS} ${WARNING_ERROR}
--
2.33.1
2 years, 9 months
[PATCH v2] Makefile: crash multi-target and multithread compile support
by Tao Liu
This patch will enable making crash as follows:
$ make -j8 warn lzo zstd
Signed-off-by: Tao Liu <ltao(a)redhat.com>
---
Makefile | 42 +++++++++++++++++-------------------------
1 file changed, 17 insertions(+), 25 deletions(-)
diff --git a/Makefile b/Makefile
index ede87a1..e1ec83c 100644
--- a/Makefile
+++ b/Makefile
@@ -305,33 +305,25 @@ install:
unconfig: make_configure
@./configure -u
-warn: make_configure
- @./configure ${CONF_TARGET_FLAG} -w -b
+config: make_configure
+ @if [ -n "$(findstring warn,$(MAKECMDGOALS))" ]; then \
+ ./configure -q ${CONF_TARGET_FLAG} -w -b; fi
+ @if [ -n "$(findstring Warn,$(MAKECMDGOALS))" ]; then \
+ ./configure -q ${CONF_TARGET_FLAG} -W -b; fi
+ @if [ -n "$(findstring nowarn,$(MAKECMDGOALS))" ]; then \
+ ./configure -q ${CONF_TARGET_FLAG} -n -b; fi
+ @if [ -n "$(findstring lzo,$(MAKECMDGOALS))" ]; then \
+ ./configure -q -x lzo ${CONF_TARGET_FLAG} -w -b; fi
+ @if [ -n "$(findstring snappy,$(MAKECMDGOALS))" ]; then \
+ ./configure -q -x snappy ${CONF_TARGET_FLAG} -w -b; fi
+ @if [ -n "$(findstring zstd,$(MAKECMDGOALS))" ]; then \
+ ./configure -q -x zstd ${CONF_TARGET_FLAG} -w -b; fi
+ @if [ -n "$(findstring valgrind,$(MAKECMDGOALS))" ]; then \
+ ./configure -q -x valgrind ${CONF_TARGET_FLAG} -w -b; fi
@$(MAKE) gdb_merge
-Warn: make_configure
- @./configure ${CONF_TARGET_FLAG} -W -b
- @$(MAKE) gdb_merge
-
-nowarn: make_configure
- @./configure ${CONF_TARGET_FLAG} -n -b
- @$(MAKE) gdb_merge
-
-lzo: make_configure
- @./configure -x lzo ${CONF_TARGET_FLAG} -w -b
- @$(MAKE) gdb_merge
-
-snappy: make_configure
- @./configure -x snappy ${CONF_TARGET_FLAG} -w -b
- @$(MAKE) gdb_merge
-
-zstd: make_configure
- @./configure -x zstd ${CONF_TARGET_FLAG} -w -b
- @$(MAKE) gdb_merge
-
-valgrind: make_configure
- @./configure -x valgrind ${CONF_TARGET_FLAG} -w -b
- @$(MAKE) gdb_merge
+warn Warn nowarn lzo snappy zstd valgrind: config
+ @echo &> /dev/null
main.o: ${GENERIC_HFILES} main.c
${CC} -c ${CRASH_CFLAGS} main.c ${WARNING_OPTIONS} ${WARNING_ERROR}
--
2.33.1
2 years, 9 months
[PATCH] arm64: update the modules/vmalloc/vmemmap ranges
by Huang Shijie
< 1 > The background.
The current crash code is still based at kernel v4.9, but the kernel is v5.17-rc4(now).
The MODULE/VMALLOC/VMEMMAP ranges do not be updated since v4.9.
I list all the changes since kernel v4.9 to v5.17:
1.) The current crash code is based at kernel v4.9.
The virtual memory layout looks like this:
+--------------------------------------------------------------------+
| KASAN | MODULE | VMALLOC | .... | VMEMMAP |
+--------------------------------------------------------------------+
The macros are:
#define MODULES_VADDR (VA_START + KASAN_SHADOW_SIZE)
#define MODULES_END (MODULES_VADDR + MODULES_VSIZE)
#define VMALLOC_START (MODULES_END)
#define VMALLOC_END (PAGE_OFFSET - PUD_SIZE - VMEMMAP_SIZE - SZ_64K)
#define VMEMMAP_START (PAGE_OFFSET - VMEMMAP_SIZE)
2.) In the kernel v5.0, the patch will add a new BFP JIT region:
"91fc957c9b1d arm64/bpf: don't allocate BPF JIT programs in module memory"
The virtual memory layout looks like this:
+--------------------------------------------------------------------+
| KASAN | BPF_JIT | MODULE | VMALLOC | .... | VMEMMAP |
+--------------------------------------------------------------------+
The macros are:
#define MODULES_VADDR (BPF_JIT_REGION_END)
#define MODULES_END (MODULES_VADDR + MODULES_VSIZE)
#define VMALLOC_START (MODULES_END)
#define VMALLOC_END (PAGE_OFFSET - PUD_SIZE - VMEMMAP_SIZE - SZ_64K)
#define VMEMMAP_START (PAGE_OFFSET - VMEMMAP_SIZE)
The layout does not changed until v5.4.
3.) In the kernel v5.4, several patches changes the layout, such as:
"ce3aaed87344 arm64: mm: Modify calculation of VMEMMAP_SIZE"
"14c127c957c1 arm64: mm: Flip kernel VA space"
and the virtual memory layout looks like this:
+--------------------------------------------------------------------+
| KASAN | BPF_JIT | MODULE | VMALLOC | .... | VMEMMAP |
+--------------------------------------------------------------------+
The macros are:
#define MODULES_VADDR (BPF_JIT_REGION_END)
#define MODULES_END (MODULES_VADDR + MODULES_VSIZE)
#define VMALLOC_START (MODULES_END)
#define VMALLOC_END (- PUD_SIZE - VMEMMAP_SIZE - SZ_64K)
#define VMEMMAP_START (-VMEMMAP_SIZE - SZ_2M)
In the v5.7, the patch:
"bbd6ec605c arm64/mm: Enable memory hot remove"
adds the VMEMMAP_END.
4.) In the kernel v5.11, several patches changes the layout, such as:
"9ad7c6d5e75b arm64: mm: tidy up top of kernel VA space"
"f4693c2716b3 arm64: mm: extend linear region for 52-bit VA configurations"
and the virtual memory layout looks like this:
+--------------------------------------------------------------------+
| BPF_JIT | MODULE | VMALLOC | .... | VMEMMAP |
+--------------------------------------------------------------------+
The macros are:
#define MODULES_VADDR (BPF_JIT_REGION_END)
#define MODULES_END (MODULES_VADDR + MODULES_VSIZE)
#define VMALLOC_START (MODULES_END)
#define VMALLOC_END (VMEMMAP_START - SZ_256M)
#define VMEMMAP_START (-(UL(1) << (VA_BITS - VMEMMAP_SHIFT)))
#define VMEMMAP_END (VMEMMAP_START + VMEMMAP_SIZE)
5.) In the kernel v5.17-rc1, after the patch
"b89ddf4cca43 arm64/bpf: Remove 128MB limit for BPF JIT programs"
the virtual memory layout looks like this:
+--------------------------------------------------------------------+
| MODULE | VMALLOC | .... | VMEMMAP |
+--------------------------------------------------------------------+
The macros are:
#define MODULES_VADDR (_PAGE_END(VA_BITS_MIN))
#define MODULES_END (MODULES_VADDR + MODULES_VSIZE)
#define VMALLOC_START (MODULES_END)
#define VMALLOC_END (VMEMMAP_START - SZ_256M)
#define VMEMMAP_START (-(UL(1) << (VA_BITS - VMEMMAP_SHIFT)))
#define VMEMMAP_END (VMEMMAP_START + VMEMMAP_SIZE)
< 2 > What does this patch do?
1.) Use arm64_get_struct_page_size() to get the size of struct page{} in the PRE_GDB.
2.) If we can succeed in above step, we will try to call arm64_get_va_range() to
get the proper kernel virtual ranges.
In the arm64_get_va_range(), we calculate the ranges by the hooks of
different kernel versions:
get_range: arm64_get_range_v5_17,
get_range: arm64_get_range_v5_11,
get_range: arm64_get_range_v5_4,
get_range: arm64_get_range_v5_0,
3.) If we can succeed in above steps, the arm64_calc_virtual_memory_ranges()
will be ignored. If we failed in above steps, the arm64_calc_virtual_memory_ranges()
will continue to do its work.
< 3 > Test this patch.
Tested this patch with a vmcore produced by a 5.4.119 kernel panic.
(The CONFIG_KASAN is NOT set for this kernel.)
Before this patch, we get the wrong output from "help -m":
----------------------------------------------------------
vmalloc_start_addr: ffff800048000000
vmalloc_end: fffffdffbffeffff
modules_vaddr: ffff800040000000
modules_end: ffff800047ffffff
vmemmap_vaddr: fffffdffffe00000
vmemmap_end: ffffffffffffffff
----------------------------------------------------------
After this patch, we can get the correct output from "help -m":
----------------------------------------------------------
vmalloc_start_addr: ffff800010000000
vmalloc_end: fffffdffbfff0000
modules_vaddr: ffff800008000000
modules_end: ffff800010000000
vmemmap_vaddr: fffffdffffe00000
vmemmap_end: ffffffffffffffff
----------------------------------------------------------
Signed-off-by: Huang Shijie <shijie(a)os.amperecomputing.com>
---
arm64.c | 362 ++++++++++++++++++++++++++++++++++++++++++++++++++++++--
1 file changed, 354 insertions(+), 8 deletions(-)
diff --git a/arm64.c b/arm64.c
index de1038a..66b7754 100644
--- a/arm64.c
+++ b/arm64.c
@@ -92,6 +92,13 @@ static void arm64_calc_VA_BITS(void);
static int arm64_is_uvaddr(ulong, struct task_context *);
static void arm64_calc_KERNELPACMASK(void);
+struct kernel_range {
+ unsigned long modules_vaddr, modules_end;
+ unsigned long vmalloc_start_addr, vmalloc_end;
+ unsigned long vmemmap_vaddr, vmemmap_end;
+};
+static struct kernel_range *arm64_get_va_range(struct machine_specific *ms);
+static void arm64_get_struct_page_size(void);
/*
* Do all necessary machine-specific setup here. This is called several times
@@ -219,6 +226,7 @@ arm64_init(int when)
machdep->pageoffset = machdep->pagesize - 1;
machdep->pagemask = ~((ulonglong)machdep->pageoffset);
+ arm64_get_struct_page_size();
arm64_calc_VA_BITS();
arm64_calc_KERNELPACMASK();
ms = machdep->machspec;
@@ -238,35 +246,47 @@ arm64_init(int when)
}
machdep->is_kvaddr = generic_is_kvaddr;
machdep->kvtop = arm64_kvtop;
+
+ /* The defaults */
+ ms->vmalloc_end = ARM64_VMALLOC_END;
+ ms->vmemmap_vaddr = ARM64_VMEMMAP_VADDR;
+ ms->vmemmap_end = ARM64_VMEMMAP_END;
+
if (machdep->flags & NEW_VMEMMAP) {
struct syment *sp;
+ struct kernel_range *r;
sp = kernel_symbol_search("_text");
ms->kimage_text = (sp ? sp->value : 0);
sp = kernel_symbol_search("_end");
ms->kimage_end = (sp ? sp->value : 0);
- if (ms->VA_BITS_ACTUAL) {
+ if (ASSIGN_SIZE(page) && (r = arm64_get_va_range(ms))) {
+ /* We can get all the MODULES/VMALLOC/VMEMMAP ranges now.*/
+ ms->modules_vaddr = r->modules_vaddr;
+ ms->modules_end = r->modules_end;
+ ms->vmalloc_start_addr = r->vmalloc_start_addr;
+ ms->vmalloc_end = r->vmalloc_end;
+ ms->vmemmap_vaddr = r->vmemmap_vaddr;
+ ms->vmemmap_end = r->vmemmap_end;
+ } else if (ms->VA_BITS_ACTUAL) {
ms->modules_vaddr = (st->_stext_vmlinux & TEXT_OFFSET_MASK) - ARM64_MODULES_VSIZE;
ms->modules_end = ms->modules_vaddr + ARM64_MODULES_VSIZE -1;
+ ms->vmalloc_start_addr = ms->modules_end + 1;
} else {
ms->modules_vaddr = ARM64_VA_START;
if (kernel_symbol_exists("kasan_init"))
ms->modules_vaddr += ARM64_KASAN_SHADOW_SIZE;
ms->modules_end = ms->modules_vaddr + ARM64_MODULES_VSIZE -1;
+ ms->vmalloc_start_addr = ms->modules_end + 1;
}
- ms->vmalloc_start_addr = ms->modules_end + 1;
-
arm64_calc_kimage_voffset();
} else {
ms->modules_vaddr = ARM64_PAGE_OFFSET - MEGABYTES(64);
ms->modules_end = ARM64_PAGE_OFFSET - 1;
ms->vmalloc_start_addr = ARM64_VA_START;
}
- ms->vmalloc_end = ARM64_VMALLOC_END;
- ms->vmemmap_vaddr = ARM64_VMEMMAP_VADDR;
- ms->vmemmap_end = ARM64_VMEMMAP_END;
switch (machdep->pagesize)
{
@@ -387,7 +407,9 @@ arm64_init(int when)
break;
case POST_GDB:
- arm64_calc_virtual_memory_ranges();
+ /* Can we get the size of struct page before POST_GDB */
+ if (!ASSIGN_SIZE(page))
+ arm64_calc_virtual_memory_ranges();
arm64_get_section_size_bits();
if (!machdep->max_physmem_bits) {
@@ -494,6 +516,331 @@ arm64_init(int when)
}
}
+struct kernel_va_range_handler {
+ unsigned long kernel_versions_start; /* include */
+ unsigned long kernel_versions_end; /* exclude */
+ struct kernel_range *(*get_range)(struct machine_specific *);
+};
+
+static struct kernel_range tmp_range;
+#define _PAGE_END(va) (-(1UL << ((va) - 1)))
+#define SZ_64K 0x00010000
+#define SZ_2M 0x00200000
+
+/*
+ * Get the max shift of the size of struct page.
+ * Most of the time, it is 64 bytes, but not sure.
+ */
+static int arm64_get_struct_page_max_shift(void)
+{
+ unsigned long v = ASSIGN_SIZE(page);
+
+ if (16 < v && v <= 32)
+ return 5;
+ if (32 < v && v <= 64)
+ return 6;
+ if (64 < v && v <= 128)
+ return 7;
+
+ error(FATAL, "We should not have such struct page size:%d!\n", v);
+ return 0;
+}
+
+/*
+ * The change is caused by the kernel patch since v5.17-rc1:
+ * "b89ddf4cca43 arm64/bpf: Remove 128MB limit for BPF JIT programs"
+ */
+static struct kernel_range *arm64_get_range_v5_17(struct machine_specific *ms)
+{
+ struct kernel_range *r = &tmp_range;
+ unsigned long v = ms->CONFIG_ARM64_VA_BITS;
+ unsigned long vmem_shift, vmemmap_size;
+
+ /* Not initialized yet */
+ if (v == 0)
+ return NULL;
+
+ if (v > 48)
+ v = 48;
+
+ /* Get the MODULES_VADDR ~ MODULES_END */
+ r->modules_vaddr = _PAGE_END(v);
+ r->modules_end = r->modules_vaddr + MEGABYTES(128);
+
+ /* Get the VMEMMAP_START ~ VMEMMAP_END */
+ vmem_shift = machdep->pageshift - arm64_get_struct_page_max_shift();
+ vmemmap_size = (_PAGE_END(v) - PAGE_OFFSET) >> vmem_shift;
+
+ r->vmemmap_vaddr = (-(1UL << (ms->VA_BITS - vmem_shift)));
+ r->vmemmap_end = r->vmemmap_vaddr + vmemmap_size;
+
+ /* Get the VMALLOC_START ~ VMALLOC_END */
+ r->vmalloc_start_addr = r->modules_end;
+ r->vmalloc_end = r->vmemmap_vaddr - MEGABYTES(256);
+ return r;
+}
+
+/*
+ * The change is caused by the kernel patch since v5.11:
+ * "9ad7c6d5e75b arm64: mm: tidy up top of kernel VA space"
+ */
+static struct kernel_range *arm64_get_range_v5_11(struct machine_specific *ms)
+{
+ struct kernel_range *r = &tmp_range;
+ unsigned long v = ms->CONFIG_ARM64_VA_BITS;
+ unsigned long vmem_shift, vmemmap_size, bpf_jit_size = MEGABYTES(128);
+
+ /* Not initialized yet */
+ if (v == 0)
+ return NULL;
+
+ if (v > 48)
+ v = 48;
+
+ /* Get the MODULES_VADDR ~ MODULES_END */
+ r->modules_vaddr = _PAGE_END(v) + bpf_jit_size;
+ r->modules_end = r->modules_vaddr + MEGABYTES(128);
+
+ /* Get the VMEMMAP_START ~ VMEMMAP_END */
+ vmem_shift = machdep->pageshift - arm64_get_struct_page_max_shift();
+ vmemmap_size = (_PAGE_END(v) - PAGE_OFFSET) >> vmem_shift;
+
+ r->vmemmap_vaddr = (-(1UL << (ms->VA_BITS - vmem_shift)));
+ r->vmemmap_end = r->vmemmap_vaddr + vmemmap_size;
+
+ /* Get the VMALLOC_START ~ VMALLOC_END */
+ r->vmalloc_start_addr = r->modules_end;
+ r->vmalloc_end = r->vmemmap_vaddr - MEGABYTES(256);
+ return r;
+}
+
+static unsigned long arm64_get_pud_size(void)
+{
+ unsigned long PUD_SIZE = 0;
+
+ switch (machdep->pagesize) {
+ case 4096:
+ if (machdep->machspec->VA_BITS > PGDIR_SHIFT_L4_4K) {
+ PUD_SIZE = PUD_SIZE_L4_4K;
+ } else {
+ PUD_SIZE = PGDIR_SIZE_L3_4K;
+ }
+ break;
+
+ case 65536:
+ PUD_SIZE = PGDIR_SIZE_L2_64K;
+ default:
+ break;
+ }
+ return PUD_SIZE;
+}
+
+/*
+ * The change is caused by the kernel patches since v5.4, such as:
+ * "ce3aaed87344 arm64: mm: Modify calculation of VMEMMAP_SIZE"
+ * "14c127c957c1 arm64: mm: Flip kernel VA space"
+ */
+static struct kernel_range *arm64_get_range_v5_4(struct machine_specific *ms)
+{
+ struct kernel_range *r = &tmp_range;
+ unsigned long v = ms->CONFIG_ARM64_VA_BITS;
+ unsigned long kasan_shadow_shift, kasan_shadow_offset, PUD_SIZE;
+ unsigned long vmem_shift, vmemmap_size, bpf_jit_size = MEGABYTES(128);
+ char *string;
+ int ret;
+
+ /* Not initialized yet */
+ if (v == 0)
+ return NULL;
+
+ if (v > 48)
+ v = 48;
+
+ /* Get the MODULES_VADDR ~ MODULES_END */
+ if (kernel_symbol_exists("kasan_init")) {
+ /* See the arch/arm64/Makefile */
+ ret = get_kernel_config("CONFIG_KASAN_SW_TAGS", NULL);
+ if (ret == IKCONFIG_N)
+ return NULL;
+ kasan_shadow_shift = (ret == IKCONFIG_Y) ? 4: 3;
+
+ /* See the arch/arm64/Kconfig*/
+ ret = get_kernel_config("CONFIG_KASAN_SHADOW_OFFSET", &string);
+ if (ret != IKCONFIG_STR)
+ return NULL;
+ kasan_shadow_offset = atol(string);
+
+ r->modules_vaddr = (1UL << (64 - kasan_shadow_shift)) + kasan_shadow_offset
+ + bpf_jit_size;
+ } else {
+ r->modules_vaddr = _PAGE_END(v) + bpf_jit_size;
+ }
+
+ r->modules_end = r->modules_vaddr + MEGABYTES(128);
+
+ /* Get the VMEMMAP_START ~ VMEMMAP_END */
+ vmem_shift = machdep->pageshift - arm64_get_struct_page_max_shift();
+ vmemmap_size = (_PAGE_END(v) - PAGE_OFFSET) >> vmem_shift;
+
+ r->vmemmap_vaddr = (-vmemmap_size - SZ_2M);
+ if (THIS_KERNEL_VERSION >= LINUX(5, 7, 0)) {
+ /*
+ * In the v5.7, the patch: "bbd6ec605c arm64/mm: Enable memory hot remove"
+ * adds the VMEMMAP_END.
+ */
+ r->vmemmap_end = r->vmemmap_vaddr + vmemmap_size;
+ } else {
+ r->vmemmap_end = 0xffffffffffffffffUL;
+ }
+
+ /* Get the VMALLOC_START ~ VMALLOC_END */
+ PUD_SIZE = arm64_get_pud_size();
+ r->vmalloc_start_addr = r->modules_end;
+ r->vmalloc_end = (-PUD_SIZE - vmemmap_size - SZ_64K);
+ return r;
+}
+
+/*
+ * The change is caused by the kernel patches since v5.0, such as:
+ * "91fc957c9b1d arm64/bpf: don't allocate BPF JIT programs in module memory"
+ */
+static struct kernel_range *arm64_get_range_v5_0(struct machine_specific *ms)
+{
+ struct kernel_range *r = &tmp_range;
+ unsigned long v = ms->CONFIG_ARM64_VA_BITS;
+ unsigned long kasan_shadow_shift, PUD_SIZE;
+ unsigned long vmemmap_size, bpf_jit_size = MEGABYTES(128);
+ unsigned long va_start, page_offset;
+ int ret;
+
+ /* Not initialized yet */
+ if (v == 0)
+ return NULL;
+
+ va_start = (0xffffffffffffffffUL - (1UL << v) + 1);
+ page_offset = (0xffffffffffffffffUL - (1UL << (v - 1)) + 1);
+
+ /* Get the MODULES_VADDR ~ MODULES_END */
+ if (kernel_symbol_exists("kasan_init")) {
+ /* See the arch/arm64/Makefile */
+ ret = get_kernel_config("CONFIG_KASAN_SW_TAGS", NULL);
+ if (ret == IKCONFIG_N)
+ return NULL;
+ kasan_shadow_shift = (ret == IKCONFIG_Y) ? 4: 3;
+
+ r->modules_vaddr = va_start + (1UL << (v - kasan_shadow_shift)) + bpf_jit_size;
+ } else {
+ r->modules_vaddr = va_start + bpf_jit_size;
+ }
+
+ r->modules_end = r->modules_vaddr + MEGABYTES(128);
+
+ /* Get the VMEMMAP_START ~ VMEMMAP_END */
+ vmemmap_size = (1UL << (v - machdep->pageshift - 1 + arm64_get_struct_page_max_shift()));
+
+ r->vmemmap_vaddr = page_offset - vmemmap_size;
+ r->vmemmap_end = 0xffffffffffffffffUL; /* this kernel does not have VMEMMAP_END */
+
+ /* Get the VMALLOC_START ~ VMALLOC_END */
+ PUD_SIZE = arm64_get_pud_size();
+
+ r->vmalloc_start_addr = r->modules_end;
+ r->vmalloc_end = page_offset - PUD_SIZE - vmemmap_size - SZ_64K;
+ return r;
+}
+
+static struct kernel_va_range_handler kernel_va_range_handlers[] = {
+ {
+ LINUX(5,17,0),
+ LINUX(6,0,0), /* Just a boundary, Change it later */
+ get_range: arm64_get_range_v5_17,
+ }, {
+ LINUX(5,11,0), LINUX(5,17,0),
+ get_range: arm64_get_range_v5_11,
+ }, {
+ LINUX(5,4,0), LINUX(5,11,0),
+ get_range: arm64_get_range_v5_4,
+ }, {
+ LINUX(5,0,0), LINUX(5,4,0),
+ get_range: arm64_get_range_v5_0,
+ },
+};
+
+#define ARRAY_SIZE(a) (sizeof (a) / sizeof ((a)[0]))
+
+static unsigned long arm64_get_kernel_version(void)
+{
+ char *string;
+ char buf[BUFSIZE];
+ char *p1, *p2;
+
+ if (THIS_KERNEL_VERSION)
+ return THIS_KERNEL_VERSION;
+
+ string = pc->read_vmcoreinfo("OSRELEASE");
+ if (string) {
+ strcpy(buf, string);
+
+ p1 = p2 = buf;
+ while (*p2 != '.')
+ p2++;
+ *p2 = NULLCHAR;
+ kt->kernel_version[0] = atoi(p1);
+
+ p1 = ++p2;
+ while (*p2 != '.')
+ p2++;
+ *p2 = NULLCHAR;
+ kt->kernel_version[1] = atoi(p1);
+
+ p1 = ++p2;
+ while ((*p2 >= '0') && (*p2 <= '9'))
+ p2++;
+ *p2 = NULLCHAR;
+ kt->kernel_version[2] = atoi(p1);
+ }
+ free(string);
+ return THIS_KERNEL_VERSION;
+}
+
+/* Return NULL if we fail. */
+static struct kernel_range *arm64_get_va_range(struct machine_specific *ms)
+{
+ struct kernel_va_range_handler *h;
+ unsigned long kernel_version = THIS_KERNEL_VERSION;
+ int i;
+
+ if (!kernel_version) {
+ kernel_version = arm64_get_kernel_version();
+ if (!kernel_version)
+ return NULL;
+ }
+
+ for (i = 0; i < ARRAY_SIZE(kernel_va_range_handlers); i++) {
+ h = kernel_va_range_handlers + i;
+
+ /* Get the right kernel version */
+ if (h->kernel_versions_start <= kernel_version &&
+ kernel_version < h->kernel_versions_end) {
+
+ /* Get the correct virtual address ranges */
+ return h->get_range(ms);
+ }
+ }
+ return NULL;
+}
+
+/* Get the size of struct page {} */
+static void arm64_get_struct_page_size()
+{
+ char *string;
+
+ string = pc->read_vmcoreinfo("SIZE(page)");
+ if (string)
+ ASSIGN_SIZE(page) = atol(string);
+ free(string);
+}
+
/*
* Accept or reject a symbol from the kernel namelist.
*/
@@ -4255,7 +4602,6 @@ arm64_calc_VA_BITS(void)
#define ALIGN(x, a) __ALIGN_KERNEL((x), (a))
#define __ALIGN_KERNEL(x, a) __ALIGN_KERNEL_MASK(x, (typeof(x))(a) - 1)
#define __ALIGN_KERNEL_MASK(x, mask) (((x) + (mask)) & ~(mask))
-#define SZ_64K 0x00010000
static void
arm64_calc_virtual_memory_ranges(void)
--
2.30.2
2 years, 9 months
