Hi Bhupesh,
On 10/29/2018 3:50 AM, Bhupesh Sharma wrote:
> makedumpfile commit 94c97db3fe859ca14d7b38b0ae9ee0ffb83689d2 (arm64: Get
> 'info->page_offset' from PT_LOAD segments to support KASLR boot cases)
> added a method to determine 'info->page_offset' from PT_LOAD segments
> for arm64 platforms.
>
> In this commit, I hardcoded the 'NOT_PADDR_ARM64' macro as
> 0x0000000010a80000UL which was a valid value on qualcomm-amberwing
> boards (which was the arm64 board available with me at the time).
>
> However, I was testing this change on several other arm64 boards
> like apm-mustang, huawei-taishan and hp-moonshot (now that I have
> access to them) and saw that this value can vary on the basis of
> the "Kernel code" memory range placement.
>
> To fix the same, this patchset uses a new approach. Since kernel
> version 4.19-rc5 (commit
> 23c85094fe1895caefdd19ef624ee687ec5f4507 ["proc/kcore: add vmcoreinfo
> note to /proc/kcore"]), '/proc/kcore' contains a new
> PT_NOTE which carries the VMCOREINFO information.
>
> If the same is available, we can use it for makedumpfile
> 'show_mem_usage()' functionality. This is especially useful
> for architectures like arm64 as we can get kernel symbols like
> 'VA_BITS' and 'kimage_voffset' from the '/proc/kcore' itself and use it
> to calculate 'info->page_offset' when we make a call to
> 'get_page_offset()'.
First, in show_mem_usage(), we set info->page_offset in advance
in order to get the offset of vmcoreinfo in /proc/kcore (not in PT_NOTE)
from /sys/kernel/vmcoreinfo information.
Since now PT_NOTE has vmcoreinfo in /proc/kcore as well, we don't
need get_page_offset() here any longer, right?
So I suggest the following patch for show_mem_usage(),
in addition, we can remove the get_elf_loads() function.
diff --git a/makedumpfile.c b/makedumpfile.c
index 91c1ab4..a02665b 100644
--- a/makedumpfile.c
+++ b/makedumpfile.c
@@ -11208,17 +11208,23 @@ int show_mem_usage(void)
if (!open_files_for_creating_dumpfile())
return FALSE;
- if (!get_elf_loads(info->fd_memory, info->name_memory))
+ if (!get_elf_info(info->fd_memory, info->name_memory))
return FALSE;
- if (!get_page_offset())
- return FALSE;
+ /*
+ * Since kernel 4.19, /proc/kcore also has vmcoreinfo in PT_NOTE,
+ * in that case we don't need /sys/kernel/vmcoreinfo.
+ */
+ if (!has_vmcoreinfo()) {
+ if (!get_page_offset())
+ return FALSE;
- if (!get_sys_kernel_vmcoreinfo(&vmcoreinfo_addr, &vmcoreinfo_len))
- return FALSE;
+ if (!get_sys_kernel_vmcoreinfo(&vmcoreinfo_addr, &vmcoreinfo_len))
+ return FALSE;
- if (!set_kcore_vmcoreinfo(vmcoreinfo_addr, vmcoreinfo_len))
- return FALSE;
+ if (!set_kcore_vmcoreinfo(vmcoreinfo_addr, vmcoreinfo_len))
+ return FALSE;
+ }
if (!initial())
return FALSE;
>
> This VMCOREINFO note provides us a standard interface which can be
> leveraged while debugging live (or primary) kernel with makedumpfile
> (and other user-space tools), especially to derive the machine specific
> details (for e.g. VA_BITS, PHYS_OFFSET and kimage_voffset for arm64
> arch). The same has been suggested by the arm64 kernel maintainers (see
> [0]) as the standard interface exposed by kernel for sharing
> machine specific details with the user-land via vmcoreinfo.
>
> [0]. https://www.mail-archive.com/kexec@xxxxxxxxxxxxxxxxxxx/msg20300.html
>
> I will send a follow-up patch to read 'kaslr_offset' for arm64 cases
> from vmcoreinfo inside '/proc/kcore' after this patchset is applied.
>
> Here are some details of the tests I ran:
>
> Testing:
> --------
> 1. arm64 boards tested:
> huawei-taishan, apm-mustang and qualcomm-amberwing boards.
>
> 2. Use-cases tested:
> a) Primary kernel ->
> [] --mem-usage:
> # makedumpfile -f --mem-usage /proc/kcore
>
> [] filtering use-case:
> # makedumpfile --split -d 31 -x vmlinux --config scrub.conf vmcore dumpfile_{1,2,3}
>
> [] dumpfile creation:
> # makedumpfile -d 31 -x vmlinux vmcore dumpfile
>
> b) Crash kernel ->
> [] dumpfile creation:
> # makedumpfile -l --message-level 31 -d 31 /proc/vmcore dump
>
> 3. Kernel versions tested:
> a) Kernel version 4.19-rc5 and above.
> b) Kernel version 4.14.
>
> Fixes: 94c97db3fe859ca14d7b38b0ae9ee0ffb83689d2 "arm64: Get 'info->page_offset' from PT_LOAD segments to
> support KASLR boot cases"
> Cc: Baoquan He <bhe@xxxxxxxxxx>
> Cc: Kazuhito Hagio <k-hagio@xxxxxxxxxxxxx>
> Signed-off-by: Bhupesh Sharma <bhsharma@xxxxxxxxxx>
> ---
> arch/arm64.c | 114 +++++++++++++++++++++++++++++++++++++++++++--------------
> makedumpfile.c | 67 ++++++++++++++++++++++++++++++---
> makedumpfile.h | 2 +-
> 3 files changed, 149 insertions(+), 34 deletions(-)
>
> diff --git a/arch/arm64.c b/arch/arm64.c
> index 362609668ea2..d695eff628f0 100644
> --- a/arch/arm64.c
> +++ b/arch/arm64.c
> @@ -53,6 +53,7 @@ static unsigned long kimage_voffset;
> #define PAGE_OFFSET_42 ((0xffffffffffffffffUL) << 42)
> #define PAGE_OFFSET_47 ((0xffffffffffffffffUL) << 47)
> #define PAGE_OFFSET_48 ((0xffffffffffffffffUL) << 48)
> +#define __PAGE_OFFSET(x) ((0xffffffffffffffffUL) << (x - 1))
>
> #define pgd_val(x) ((x).pgd)
> #define pud_val(x) (pgd_val((x).pgd))
> @@ -311,45 +312,104 @@ get_versiondep_info_arm64(void)
> unsigned long long virt_start;
> ulong _stext;
>
> - _stext = get_stext_symbol();
> - if (!_stext) {
> - ERRMSG("Can't get the symbol of _stext.\n");
> - return FALSE;
> - }
> + /* Calculate 'VA_BITS'. */
>
> - /* Derive va_bits as per arch/arm64/Kconfig */
> - if ((_stext & PAGE_OFFSET_36) == PAGE_OFFSET_36) {
> - va_bits = 36;
> - } else if ((_stext & PAGE_OFFSET_39) == PAGE_OFFSET_39) {
> - va_bits = 39;
> - } else if ((_stext & PAGE_OFFSET_42) == PAGE_OFFSET_42) {
> - va_bits = 42;
> - } else if ((_stext & PAGE_OFFSET_47) == PAGE_OFFSET_47) {
> - va_bits = 47;
> - } else if ((_stext & PAGE_OFFSET_48) == PAGE_OFFSET_48) {
> - va_bits = 48;
> + /* Since kernel version 4.19, '/proc/kcore' contains a new
> + * PT_NOTE which carries the VMCOREINFO information.
> + *
> + * If the same is available, use it as it already contains the
> + * value of 'VA_BITS' on the machine.
> + *
> + * Otherwise, we can read the '_stext' symbol and determine the
> + * 'VA_BITS' value from the same as well.
> + */
> + if (info->flag_kcore_contains_vmcoreinfo &&
> + (NUMBER(VA_BITS) != NOT_FOUND_NUMBER)) {
> + va_bits = NUMBER(VA_BITS);
> } else {
> - ERRMSG("Cannot find a proper _stext for calculating VA_BITS\n");
> - return FALSE;
> + _stext = get_stext_symbol();
> + if (!_stext) {
> + ERRMSG("Can't get the symbol of _stext.\n");
> + return FALSE;
> + }
> +
> + /* Derive va_bits as per arch/arm64/Kconfig */
> + if ((_stext & PAGE_OFFSET_36) == PAGE_OFFSET_36) {
> + va_bits = 36;
> + } else if ((_stext & PAGE_OFFSET_39) == PAGE_OFFSET_39) {
> + va_bits = 39;
> + } else if ((_stext & PAGE_OFFSET_42) == PAGE_OFFSET_42) {
> + va_bits = 42;
> + } else if ((_stext & PAGE_OFFSET_47) == PAGE_OFFSET_47) {
> + va_bits = 47;
> + } else if ((_stext & PAGE_OFFSET_48) == PAGE_OFFSET_48) {
> + va_bits = 48;
> + } else {
> + ERRMSG("Cannot find a proper _stext for calculating VA_BITS\n");
> + return FALSE;
> + }
> + }
> +
> + /* Calculate 'info->page_offset'. */
> +
> + /* Since kernel version 4.19, '/proc/kcore' contains a new
> + * PT_NOTE which carries the VMCOREINFO information.
> + *
> + * If the same is available, use it as it already contains the
> + * value of 'kimage_voffset' on the machine.
> + */
> + if (info->flag_kcore_contains_vmcoreinfo &&
> + (NUMBER(kimage_voffset) != NOT_FOUND_NUMBER)) {
> + kimage_voffset = NUMBER(kimage_voffset);
> }
>
> + /* First, lets try and calculate the 'info->page_offset' value
> + * from PT_LOAD segments, if they are available.
> + */
> if (get_num_pt_loads()) {
> for (i = 0;
> get_pt_load(i, &phys_start, NULL, &virt_start, NULL);
> i++) {
> - if (virt_start != NOT_KV_ADDR
> - && virt_start < __START_KERNEL_map
> - && phys_start != NOT_PADDR
> - && phys_start != NOT_PADDR_ARM64) {
> - info->page_offset = virt_start - phys_start;
> - DEBUG_MSG("info->page_offset: %lx, VA_BITS: %d\n",
> - info->page_offset, va_bits);
> - return TRUE;
> + /* On systems where we have a valid 'kimage_voffset'
> + * available by now, we should give preference to the same
> + * while calculating 'info->page_offset'.
> + *
> + * Otherwise, we can ensure that we consider
> + * only those PT_LOAD segments whose 'virt_start'
> + * is greater than the PAGE_OFFSET value (as defined
> + * in 'arch/arm64/include/asm/memory.h').
> + */
> + if (!kimage_voffset) {
> + if (virt_start != NOT_KV_ADDR &&
> + virt_start > __PAGE_OFFSET(va_bits) &&
> + phys_start != NOT_PADDR) {
> + info->page_offset = virt_start - phys_start;
> + DEBUG_MSG("info->page_offset: %lx, VA_BITS: %d\n",
> + info->page_offset, va_bits);
> + return TRUE;
> + }
> + } else {
> + if (virt_start != NOT_KV_ADDR &&
> + phys_start != NOT_PADDR &&
> + (virt_start - phys_start) != kimage_voffset) {
> + info->page_offset = virt_start - phys_start;
> + DEBUG_MSG("info->page_offset: %lx, VA_BITS: %d\n",
> + info->page_offset, va_bits);
> + return TRUE;
> + }
If something like KCORE_REMAP are added to kcore on arm64, even with
vmcoreinfo, this calculation can return a wrong page_offset, right?
Can we calculate info->page_offset without PT_LOAD information?
Originally, info->page_offset (PAGE_OFFSET) is used in the following
parts on arm64.
arch/arm64.c:
__pa(unsigned long vaddr)
{
if (kimage_voffset == NOT_FOUND_NUMBER ||
(vaddr >= PAGE_OFFSET))
return (vaddr - PAGE_OFFSET + info->phys_base);
else
return (vaddr - kimage_voffset);
}
elf_info.c:
kvstart = (ulong)start + PAGE_OFFSET;
kvend = (ulong)end + PAGE_OFFSET;
--
kvaddr = (ulong)vmcoreinfo_addr + PAGE_OFFSET;
I'm wondering about its consistency. Is it OK to set
(virt_start - phys_start) to info->page_offset on arm64?
In other words, on arm64 system with info->phys_base != 0, does it
work correctly for both /proc/vmcore and --mem-usage /proc/kcore?
Maybe I have some misunderstanding..
Thanks,
Kazu
> }
> }
> }
>
> - info->page_offset = (0xffffffffffffffffUL) << (va_bits - 1);
> + /* Fallback to hard-coded value (equal to PAGE_OFFSET macro
> + * defined in 'arch/arm64/include/asm/memory.h'), as the last
> + * resort.
> + *
> + * Note that this will not be a valid value on KASLR enabled
> + * kernels as the start address of linear range is also
> + * randomized for KASLR boot cases.
> + */
> + info->page_offset = __PAGE_OFFSET(va_bits);
> DEBUG_MSG("page_offset=%lx, va_bits=%d\n", info->page_offset,
> va_bits);
>
> diff --git a/makedumpfile.c b/makedumpfile.c
> index 91c1ab47fca4..a1b8d8ff5a84 100644
> --- a/makedumpfile.c
> +++ b/makedumpfile.c
> @@ -1302,6 +1302,20 @@ error:
> return FALSE;
> }
>
> +static int
> +check_kcore_contains_vmcoreinfo(int fd, char *name)
> +{
> + if (!get_elf_info(fd, name))
> + return FALSE;
> +
> + if (!has_vmcoreinfo())
> + return FALSE;
> +
> + DEBUG_MSG("VMCOREINFO PT_NOTE found in %s\n", name);
> +
> + return TRUE;
> +}
> +
> int
> open_dump_memory(void)
> {
> @@ -1314,6 +1328,23 @@ open_dump_memory(void)
> }
> info->fd_memory = fd;
>
> + /* Since kernel version 4.19, '/proc/kcore' contains a new
> + * PT_NOTE which carries the VMCOREINFO information.
> + *
> + * If the same is available, use it for makedumpfile
> + * show_mem_usage() cases.
> + */
> + if (info->flag_mem_usage &&
> + !(strcmp(info->name_memory, "/proc/kcore")) &&
> + (info->kernel_version >= KERNEL_VERSION(4, 19, 0))){
> + status = check_kcore_contains_vmcoreinfo(fd,
> + info->name_memory);
> + if (status == TRUE) {
> + info->flag_kcore_contains_vmcoreinfo = TRUE;
> + return TRUE;
> + }
> + }
> +
> status = check_kdump_compressed(info->name_memory);
> if (status == TRUE) {
> info->flag_refiltering = TRUE;
> @@ -11195,6 +11226,8 @@ static int get_sys_kernel_vmcoreinfo(uint64_t *addr, uint64_t *len)
>
> int show_mem_usage(void)
> {
> + off_t offset;
> + unsigned long size;
> uint64_t vmcoreinfo_addr, vmcoreinfo_len;
> struct cycle cycle = {0};
>
> @@ -11208,17 +11241,39 @@ int show_mem_usage(void)
> if (!open_files_for_creating_dumpfile())
> return FALSE;
>
> - if (!get_elf_loads(info->fd_memory, info->name_memory))
> - return FALSE;
> + /* Since kernel version 4.19, '/proc/kcore' contains a new
> + * PT_NOTE which carries the VMCOREINFO information.
> + *
> + * If the same is available, use it for makedumpfile
> + * show_mem_usage(). This is especially useful for architectures
> + * like arm64 as we can get symbols like 'VA_BITS' and
> + * 'kimage_voffset' before we call get_page_offset().
> + */
> +
> + if (!info->flag_kcore_contains_vmcoreinfo) {
> + if (!get_elf_loads(info->fd_memory, info->name_memory))
> + return FALSE;
> + } else {
> + if (has_vmcoreinfo()) {
> + get_vmcoreinfo(&offset, &size);
> + if (!read_vmcoreinfo_from_vmcore(offset, size, FALSE))
> + return FALSE;
> + }
> + }
>
> if (!get_page_offset())
> return FALSE;
>
> - if (!get_sys_kernel_vmcoreinfo(&vmcoreinfo_addr, &vmcoreinfo_len))
> - return FALSE;
> + /* If flag_kcore_contains_vmcoreinfo is TRUE when we are here,
> + * we don't need to read the vmcoreinfo again.
> + */
> + if (!info->flag_kcore_contains_vmcoreinfo)
> + if (!get_sys_kernel_vmcoreinfo(&vmcoreinfo_addr, &vmcoreinfo_len))
> + return FALSE;
>
> - if (!set_kcore_vmcoreinfo(vmcoreinfo_addr, vmcoreinfo_len))
> - return FALSE;
> + if (!info->flag_kcore_contains_vmcoreinfo)
> + if (!set_kcore_vmcoreinfo(vmcoreinfo_addr, vmcoreinfo_len))
> + return FALSE;
>
> if (!initial())
> return FALSE;
> diff --git a/makedumpfile.h b/makedumpfile.h
> index 46ebe2ee5a1f..77f7ec8e3867 100644
> --- a/makedumpfile.h
> +++ b/makedumpfile.h
> @@ -544,7 +544,6 @@ unsigned long get_kvbase_arm64(void);
> #define KVBASE get_kvbase_arm64()
>
> #define __START_KERNEL_map (0xffffffff80000000UL)
> -#define NOT_PADDR_ARM64 (0x0000000010a80000UL)
>
> #endif /* aarch64 */
>
> @@ -1308,6 +1307,7 @@ struct DumpInfo {
> int flag_vmemmap; /* kernel supports vmemmap address space */
> int flag_excludevm; /* -e - excluding unused vmemmap pages */
> int flag_use_count; /* _refcount is named _count in struct page */
> + int flag_kcore_contains_vmcoreinfo; /* '/proc/kcore' contains a VMCOREINFO PT_NOTE */
> unsigned long vaddr_for_vtop; /* virtual address for debugging */
> long page_size; /* size of page */
> long page_shift;
> --
> 2.7.4
>
_______________________________________________
kexec mailing list
kexec@xxxxxxxxxxxxxxxxxxx
http://lists.infradead.org/mailman/listinfo/kexec
