Re: [Crash-utility] [PATCH v5] arm64: fix kernel memory map handling for kaslr-enabled

Hi Takahiro, On 13/06/2016:05:10:08 PM, AKASHI Takahiro wrote: > In my next version of kdump patch, the following VMCOREINFO will be > added: > NUMBER(VA_BITS) > NUMBER(kimage_voffset) > NUMBER(PHYS_OFFSET) > KERNELOFFSET > > I think that those will also satisfy mkdumpfile requirements. > -> Pratyush Thanks, Those would be useful for Makedumpfile. However, I am still not able to see a way to distinguish between kernel text area and others. makedumpfile needs a way to identify between VAs "which could be translated using __pa()" and others, "which needs to be translated using page tables". Currently, it uses __pa() if a VA is not within either vmalloc, or vmemmap or module area. But as, you had suggested, it seems a better approach to translate using __pa() when VA >= PAGE_OFFSET || (VA >= SYMBOL(_text) && vaddr <= SYMBOL(_end)). I am still not getting, how can I get _end from the passed information.

~Pratyush > > Thanks, > -Takahiro AKASHI > > changes in v5: > * Calcs PHYS_OFFSET by reading VMCOREINFO, "NUMBER(PHYS_OFFSET)" > "memstart_addr"-based routine was also moved into arm64_calc_phys_base(). > > changes in v4: > * Fixed VA_BITS calculation for v4.5 or earlier > * Added 4-level address translation with 4KB page size > * Removed "fix a renaming of a member of struct page, _count to _refcount" > > Chnages in v3: > * Refined KASLR handling > hopefully the tool works even on a live system if CONFIG_RANDOMIZE_RAM is > not configured > * Fixed a renaming of a member of struct page > * Removed a commit message regarding an issue of backtracing a panic'ed task > because this is not a bug in this tool, but my kdump patch's. > * Reported "kmem <vmalloc addr>" issue in a commit message > > changes in v2: > * Fixed build warnings > * Moved ARM64_NEW_VMEMMAP to machdep->flags > * Show additional kaslr-related parameters in arm64_dump_machdep_table() > * Handle a VMCOREINFO, "NUMBER(kimage_voffset)" > > ======8<====== > >From a6dd9d73120dcc3f2d68dbe9a8f2d16a128c4002 Mon Sep 17 00:00:00 2001 > From: AKASHI Takahiro <takahiro.akashi(a)linaro.org&gt; > Date: Mon, 16 May 2016 17:31:55 +0900 > Subject: [PATCH v5] arm64: fix kernel memory map handling for kaslr-enabled > kernel > > In kernel v4.6, Kernel ASLR (KASLR) is supported on arm64, and the start > address of the kernel image can be randomized if CONFIG_RANDOMIZE_BASE is > enabled. > Even worse, the kernel image is no more mapped in the linear mapping, but > in vmalloc area (i.e. below PAGE_OFFSET). > > Now, according to the kernel's memory.h, converting a virtual address to > a physical address should be done like below: > > phys_addr_t __x = (phys_addr_t)(x); \ > __x & BIT(VA_BITS - 1) ? (__x & ~PAGE_OFFSET) + PHYS_OFFSET : \ > (__x - kimage_voffset); }) > > Please note that PHYS_OFFSET is no more equal to the start address of > the first usable memory block in SYSTEM RAM due to the fact mentioned > above. > > This patch addresses this change and allows the crash utility to access > memory contents with correct addresses. > > * On a live system, crash with this patch won't work, especially > with CONFIG_RANDOMIZE_BASE configured, because we currently have no way > to know kimage_voffset. > > * For a core dump file, we can do simply: > $ crash <vmlinux> <vmcore> > as long as the file has "NUMBER(kimage_voffset)" > (RELOC_AUTO|KASLR is automatically set.) > > Signed-off-by: AKASHI Takahiro <takahiro.akashi(a)linaro.org&gt; > --- > arm64.c | 232 ++++++++++++++++++++++++++++++++++++++++++++++++-------------- > defs.h | 26 ++++--- > main.c | 7 +- > symbols.c | 12 ++-- > 4 files changed, 211 insertions(+), 66 deletions(-) > > diff --git a/arm64.c b/arm64.c > index 86ec348..37524c8 100644 > --- a/arm64.c > +++ b/arm64.c > @@ -73,6 +73,23 @@ static int arm64_get_crash_notes(void); > static void arm64_calc_VA_BITS(void); > static int arm64_is_uvaddr(ulong, struct task_context *); > > +ulong > +arm64_VTOP(ulong addr) > +{ > + if (machdep->flags & NEW_VMEMMAP) { > + if (addr >= machdep->machspec->page_offset) > + return machdep->machspec->phys_offset > + + (addr - machdep->machspec->page_offset); > + else if (machdep->machspec->kimage_voffset) > + return addr - machdep->machspec->kimage_voffset; > + else /* no randomness */ > + return machdep->machspec->phys_offset > + + (addr - machdep->machspec->vmalloc_start_addr); > + } else { > + return machdep->machspec->phys_offset > + + (addr - machdep->machspec->page_offset); > + } > +} > > /* > * Do all necessary machine-specific setup here. This is called several times > @@ -82,6 +99,7 @@ void > arm64_init(int when) > { > ulong value; > + char *string; > struct machine_specific *ms; > > #if defined(__x86_64__) > @@ -103,9 +121,32 @@ arm64_init(int when) > if (machdep->cmdline_args[0]) > arm64_parse_cmdline_args(); > machdep->flags |= MACHDEP_BT_TEXT; > + > + ms = machdep->machspec; > + if (!ms->kimage_voffset && > + (string = pc->read_vmcoreinfo("NUMBER(kimage_voffset)"))) { > + ms->kimage_voffset = htol(string, QUIET, NULL); > + free(string); > + } > + > + if (ms->kimage_voffset) { > + machdep->flags |= NEW_VMEMMAP; > + > + /* > + * Even if CONFIG_RANDOMIZE_BASE is not configured, > + * derive_kaslr_offset() should work and set > + * kt->relocate to 0 > + */ > + if (!kt->relocate && !(kt->flags2 & (RELOC_AUTO|KASLR))) > + kt->flags2 |= (RELOC_AUTO|KASLR); > + } > + > break; > > case PRE_GDB: > + if (kernel_symbol_exists("kimage_voffset")) > + machdep->flags |= NEW_VMEMMAP; > + > if (!machdep->pagesize) { > /* > * Kerneldoc Documentation/arm64/booting.txt describes > @@ -161,16 +202,34 @@ arm64_init(int when) > machdep->pagemask = ~((ulonglong)machdep->pageoffset); > > arm64_calc_VA_BITS(); > - machdep->machspec->page_offset = ARM64_PAGE_OFFSET; > + ms = machdep->machspec; > + ms->page_offset = ARM64_PAGE_OFFSET; > machdep->identity_map_base = ARM64_PAGE_OFFSET; > - machdep->machspec->userspace_top = ARM64_USERSPACE_TOP; > - machdep->machspec->modules_vaddr = ARM64_MODULES_VADDR; > - machdep->machspec->modules_end = ARM64_MODULES_END; > - machdep->machspec->vmalloc_start_addr = ARM64_VMALLOC_START; > - machdep->machspec->vmalloc_end = ARM64_VMALLOC_END; > - machdep->kvbase = ARM64_VMALLOC_START; > - machdep->machspec->vmemmap_vaddr = ARM64_VMEMMAP_VADDR; > - machdep->machspec->vmemmap_end = ARM64_VMEMMAP_END; > + machdep->kvbase = ARM64_VA_START; > + ms->userspace_top = ARM64_USERSPACE_TOP; > + if (machdep->flags & NEW_VMEMMAP) { > + struct syment *sp; > + > + sp = kernel_symbol_search("_text"); > + ms->kimage_text = (sp ? sp->value : 0); > + sp = kernel_symbol_search("_end"); > + ms->kimage_end = (sp ? sp->value : 0); > + > + 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; > + } 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) > { > @@ -241,8 +300,6 @@ arm64_init(int when) > machdep->stacksize = ARM64_STACK_SIZE; > machdep->flags |= VMEMMAP; > > - arm64_calc_phys_offset(); > - > machdep->uvtop = arm64_uvtop; > machdep->kvtop = arm64_kvtop; > machdep->is_kvaddr = generic_is_kvaddr; > @@ -271,6 +328,10 @@ arm64_init(int when) > machdep->dumpfile_init = NULL; > machdep->verify_line_number = NULL; > machdep->init_kernel_pgd = arm64_init_kernel_pgd; > + > + /* use machdep parameters */ > + arm64_calc_phys_offset(); > + > break; > > case POST_GDB: > @@ -420,6 +481,8 @@ arm64_dump_machdep_table(ulong arg) > fprintf(fp, "%sIRQ_STACKS", others++ ? "|" : ""); > if (machdep->flags & MACHDEP_BT_TEXT) > fprintf(fp, "%sMACHDEP_BT_TEXT", others++ ? "|" : ""); > + if (machdep->flags & NEW_VMEMMAP) > + fprintf(fp, "%sNEW_VMEMMAP", others++ ? "|" : ""); > fprintf(fp, ")\n"); > > fprintf(fp, " kvbase: %lx\n", machdep->kvbase); > @@ -524,6 +587,11 @@ arm64_dump_machdep_table(ulong arg) > fprintf(fp, " modules_end: %016lx\n", ms->modules_end); > fprintf(fp, " vmemmap_vaddr: %016lx\n", ms->vmemmap_vaddr); > fprintf(fp, " vmemmap_end: %016lx\n", ms->vmemmap_end); > + if (machdep->flags & NEW_VMEMMAP) { > + fprintf(fp, " kimage_text: %016lx\n", ms->kimage_text); > + fprintf(fp, " kimage_end: %016lx\n", ms->kimage_end); > + fprintf(fp, " kimage_voffset: %016lx\n", ms->kimage_voffset); > + } > fprintf(fp, " phys_offset: %lx\n", ms->phys_offset); > fprintf(fp, "__exception_text_start: %lx\n", ms->__exception_text_start); > fprintf(fp, " __exception_text_end: %lx\n", ms->__exception_text_end); > @@ -566,6 +634,42 @@ arm64_dump_machdep_table(ulong arg) > } > } > > +static int > +arm64_parse_machdep_arg_l(char *argstring, char *param, ulong *value) > +{ > + int len; > + int megabytes = FALSE; > + char *p; > + > + len = strlen(param); > + if (!STRNEQ(argstring, param) || (argstring[len] != '=')) > + return FALSE; > + > + if ((LASTCHAR(argstring) == 'm') || > + (LASTCHAR(argstring) == 'M')) { > + LASTCHAR(argstring) = NULLCHAR; > + megabytes = TRUE; > + } > + > + p = argstring + len + 1; > + if (strlen(p)) { > + int flags = RETURN_ON_ERROR | QUIET; > + int err = 0; > + > + if (megabytes) { > + *value = dtol(p, flags, &err); > + if (!err) > + *value = MEGABYTES(*value); > + } else { > + *value = htol(p, flags, &err); > + } > + > + if (!err) > + return TRUE; > + } > + > + return FALSE; > +} > > /* > * Parse machine dependent command line arguments. > @@ -577,11 +681,10 @@ arm64_dump_machdep_table(ulong arg) > static void > arm64_parse_cmdline_args(void) > { > - int index, i, c, err; > + int index, i, c; > char *arglist[MAXARGS]; > char buf[BUFSIZE]; > char *p; > - ulong value = 0; > > for (index = 0; index < MAX_MACHDEP_ARGS; index++) { > if (!machdep->cmdline_args[index]) > @@ -603,39 +706,23 @@ arm64_parse_cmdline_args(void) > c = parse_line(buf, arglist); > > for (i = 0; i < c; i++) { > - err = 0; > - > - if (STRNEQ(arglist[i], "phys_offset=")) { > - int megabytes = FALSE; > - int flags = RETURN_ON_ERROR | QUIET; > - > - if ((LASTCHAR(arglist[i]) == 'm') || > - (LASTCHAR(arglist[i]) == 'M')) { > - LASTCHAR(arglist[i]) = NULLCHAR; > - megabytes = TRUE; > - } > - > - p = arglist[i] + strlen("phys_offset="); > - if (strlen(p)) { > - if (megabytes) > - value = dtol(p, flags, &err); > - else > - value = htol(p, flags, &err); > - } > - > - if (!err) { > - if (megabytes) > - value = MEGABYTES(value); > - > - machdep->machspec->phys_offset = value; > - > - error(NOTE, > - "setting phys_offset to: 0x%lx\n\n", > - machdep->machspec->phys_offset); > + if (arm64_parse_machdep_arg_l(arglist[i], > + "phys_offset", > + &machdep->machspec->phys_offset)) { > + error(NOTE, > + "setting phys_offset to: 0x%lx\n\n", > + machdep->machspec->phys_offset); > + > + machdep->flags |= PHYS_OFFSET; > + continue; > + } else if (arm64_parse_machdep_arg_l(arglist[i], > + "kimage_voffset", > + &machdep->machspec->kimage_voffset)) { > + error(NOTE, > + "setting kimage_voffset to: 0x%lx\n\n", > + machdep->machspec->kimage_voffset); > > - machdep->flags |= PHYS_OFFSET; > - continue; > - } > + continue; > } > > error(WARNING, "ignoring --machdep option: %s\n", > @@ -720,7 +807,32 @@ arm64_calc_phys_offset(void) > static int > arm64_kdump_phys_base(ulong *phys_offset) > { > - return arm_kdump_phys_base(phys_offset); > + char *string; > + struct syment *sp; > + physaddr_t paddr; > + > + if (string = pc->read_vmcoreinfo("NUMBER(PHYS_OFFSET)")) { > + *phys_offset = htol(string, QUIET, NULL); > + free(string); > + return TRUE; > + } > + > + if (machdep->flags & NEW_VMEMMAP) { > + if (!(sp = kernel_symbol_search("memstart_addr"))) > + return FALSE; > + > + /* sanity check */ > + if (!machdep->machspec->kimage_voffset) > + return FALSE; > + > + paddr = sp->value - machdep->machspec->kimage_voffset; > + if (READMEM(-1, phys_offset, sizeof(*phys_offset), > + sp->value, paddr) > 0) > + return TRUE; > + else > + return FALSE; > + } else > + return arm_kdump_phys_base(phys_offset); > } > > static void > @@ -2509,6 +2621,11 @@ arm64_IS_VMALLOC_ADDR(ulong vaddr) > { > struct machine_specific *ms = machdep->machspec; > > + if ((machdep->flags & NEW_VMEMMAP) && > + (vaddr >= machdep->machspec->kimage_text) && > + (vaddr <= machdep->machspec->kimage_end)) > + return FALSE; > + > return ((vaddr >= ms->vmalloc_start_addr && vaddr <= ms->vmalloc_end) || > ((machdep->flags & VMEMMAP) && > (vaddr >= ms->vmemmap_vaddr && vaddr <= ms->vmemmap_end)) || > @@ -2539,7 +2656,10 @@ arm64_calc_VA_BITS(void) > > for (bitval = highest_bit_long(value); bitval; bitval--) { > if ((value & (1UL << bitval)) == 0) { > - machdep->machspec->VA_BITS = bitval + 2; > + if (machdep->flags & NEW_VMEMMAP) > + machdep->machspec->VA_BITS = bitval + 1; > + else > + machdep->machspec->VA_BITS = bitval + 2; > break; > } > } > @@ -2593,10 +2713,22 @@ arm64_calc_virtual_memory_ranges(void) > break; > } > > - vmemmap_size = ALIGN((1UL << (ms->VA_BITS - machdep->pageshift)) * SIZE(page), PUD_SIZE); > + if (machdep->flags & NEW_VMEMMAP) > +#define STRUCT_PAGE_MAX_SHIFT 6 > + vmemmap_size = 1UL << (ms->VA_BITS - machdep->pageshift - 1 > + + STRUCT_PAGE_MAX_SHIFT); > + else > + vmemmap_size = ALIGN((1UL << (ms->VA_BITS - machdep->pageshift)) * SIZE(page), PUD_SIZE); > + > vmalloc_end = (ms->page_offset - PUD_SIZE - vmemmap_size - SZ_64K); > - vmemmap_start = vmalloc_end + SZ_64K; > - vmemmap_end = vmemmap_start + vmemmap_size; > + > + if (machdep->flags & NEW_VMEMMAP) { > + vmemmap_start = ms->page_offset - vmemmap_size; > + vmemmap_end = ms->page_offset; > + } else { > + vmemmap_start = vmalloc_end + SZ_64K; > + vmemmap_end = vmemmap_start + vmemmap_size; > + } > > ms->vmalloc_end = vmalloc_end - 1; > ms->vmemmap_vaddr = vmemmap_start; > diff --git a/defs.h b/defs.h > index 8eb601b..d6f719c 100644 > --- a/defs.h > +++ b/defs.h > @@ -2846,8 +2846,8 @@ typedef u64 pte_t; > > #define PTOV(X) \ > ((unsigned long)(X)-(machdep->machspec->phys_offset)+(machdep->machspec->page_offset)) > -#define VTOP(X) \ > - ((unsigned long)(X)-(machdep->machspec->page_offset)+(machdep->machspec->phys_offset)) > + > +#define VTOP(X) arm64_VTOP((ulong)(X)) > > #define USERSPACE_TOP (machdep->machspec->userspace_top) > #define PAGE_OFFSET (machdep->machspec->page_offset) > @@ -2962,19 +2962,24 @@ typedef signed int s32; > #define VM_L3_4K (0x10) > #define KDUMP_ENABLED (0x20) > #define IRQ_STACKS (0x40) > -#define VM_L4_4K (0x80) > +#define NEW_VMEMMAP (0x80) > +#define VM_L4_4K (0x100) > > /* > * sources: Documentation/arm64/memory.txt > * arch/arm64/include/asm/memory.h > * arch/arm64/include/asm/pgtable.h > */ > - > -#define ARM64_PAGE_OFFSET ((0xffffffffffffffffUL) << (machdep->machspec->VA_BITS - 1)) > +#define ARM64_VA_START ((0xffffffffffffffffUL) \ > + << machdep->machspec->VA_BITS) > +#define ARM64_PAGE_OFFSET ((0xffffffffffffffffUL) \ > + << (machdep->machspec->VA_BITS - 1)) > #define ARM64_USERSPACE_TOP ((1UL) << machdep->machspec->VA_BITS) > -#define ARM64_MODULES_VADDR (ARM64_PAGE_OFFSET - MEGABYTES(64)) > -#define ARM64_MODULES_END (ARM64_PAGE_OFFSET - 1) > -#define ARM64_VMALLOC_START ((0xffffffffffffffffUL) << machdep->machspec->VA_BITS) > + > +/* only used for v4.6 or later */ > +#define ARM64_MODULES_VSIZE MEGABYTES(128) > +#define ARM64_KASAN_SHADOW_SIZE (1UL << (machdep->machspec->VA_BITS - 3)) > + > /* > * The following 3 definitions are the original values, but are obsolete > * for 3.17 and later kernels because they are now build-time calculations. > @@ -3055,6 +3060,10 @@ struct machine_specific { > ulong *irq_stacks; > ulong __irqentry_text_start; > ulong __irqentry_text_end; > + /* only needed for v4.6 or later kernel */ > + ulong kimage_voffset; > + ulong kimage_text; > + ulong kimage_end; > }; > > struct arm64_stackframe { > @@ -5412,6 +5421,7 @@ void unwind_backtrace(struct bt_info *); > #ifdef ARM64 > void arm64_init(int); > void arm64_dump_machdep_table(ulong); > +ulong arm64_VTOP(ulong); > int arm64_IS_VMALLOC_ADDR(ulong); > ulong arm64_swp_type(ulong); > ulong arm64_swp_offset(ulong); > diff --git a/main.c b/main.c > index 05787f0..4065e9a 100644 > --- a/main.c > +++ b/main.c > @@ -227,9 +227,10 @@ main(int argc, char **argv) > optarg); > } > } else if (STREQ(long_options[option_index].name, "kaslr")) { > - if (!machine_type("X86_64")) > - error(INFO, "--kaslr only valid " > - "with X86_64 machine type.\n"); > + if (!machine_type("X86_64") && > + !machine_type("ARM64")) > + error(INFO, "--kaslr not valid " > + "with this machine type.\n"); > else if (STREQ(optarg, "auto")) > kt->flags2 |= (RELOC_AUTO|KASLR); > else { > diff --git a/symbols.c b/symbols.c > index a8d3563..b0a6461 100644 > --- a/symbols.c > +++ b/symbols.c > @@ -593,7 +593,8 @@ kaslr_init(void) > { > char *string; > > - if (!machine_type("X86_64") || (kt->flags & RELOC_SET)) > + if ((!machine_type("X86_64") && !machine_type("ARM64")) || > + (kt->flags & RELOC_SET)) > return; > > /* > @@ -712,7 +713,7 @@ store_symbols(bfd *abfd, int dynamic, void *minisyms, long symcount, > if (machine_type("X86")) { > if (!(kt->flags & RELOC_SET)) > kt->flags |= RELOC_FORCE; > - } else if (machine_type("X86_64")) { > + } else if (machine_type("X86_64") || machine_type("ARM64")) { > if ((kt->flags2 & RELOC_AUTO) && !(kt->flags & RELOC_SET)) > derive_kaslr_offset(abfd, dynamic, from, > fromend, size, store); > @@ -783,7 +784,8 @@ store_sysmap_symbols(void) > error(FATAL, "symbol table namespace malloc: %s\n", > strerror(errno)); > > - if (!machine_type("X86") && !machine_type("X86_64")) > + if (!machine_type("X86") && !machine_type("X86_64") && > + !machine_type("ARM64")) > kt->flags &= ~RELOC_SET; > > first = 0; > @@ -833,7 +835,7 @@ store_sysmap_symbols(void) > } > > /* > - * Handle x86 kernels configured such that the vmlinux symbols > + * Handle x86/arm64 kernels configured such that the vmlinux symbols > * are not as loaded into the kernel (not unity-mapped). > */ > static ulong > @@ -4681,7 +4683,7 @@ value_search(ulong value, ulong *offset) > if ((sp = machdep->value_to_symbol(value, offset))) > return sp; > > - if (IS_VMALLOC_ADDR(value)) > + if (IS_VMALLOC_ADDR(value)) > goto check_modules; > > if ((sp = symval_hash_search(value)) == NULL) > -- > 2.8.1