Dave, When I looked at the output from "bt -f" command, I found that stack dump starts from frame.sp in arm64_print_stackframe_entry(). Usage of stack frames on arm64 is a bit different from that on x86, and using frame.fp is, I believe, much useful (and accurate) for crash users. See my patch attached below. Details: A layout of a stack frame in a function looks like: stack grows to lower addresses. /|\ | | | new sp +------+ <--- |dyn | | | vars | | new fp +- - - + | |old fp| | a function's stack frame |old lr| | |static| | | vars| | old sp +------+ <--- |dyn | | vars | old fp +------+ | | * On function entry, sp is decremented down to new fp. * and old fp and sp are saved into this stack frame. "Static" local variables are allocated at the same time. * Later on, "dynamic" local variables may be allocated on a stack. But those dynamic variables are rarely used in the kernel image, and, as a matter of fact, sp is equal to fp in almost all functions. (not 100% though.) * Currently, sp is determined in arm64_unwind_frame() by sp = a callee's fp + 0x10 where 0x10 stands for a saved area for fp and sp * As you can see, however, this calculated sp still points to the top of callee's static local variables and doesn't match with a *real* sp. * So, generally, dumping a stack from this calculated sp to the next frame's sp shows "callee's static local variables", old fp and sp. Confused?

Probably you will be able to understand more easily by seeing an example from my vmlinux/vmcore cases: === crash with my patch === crash> bt -f 1324 PID: 1324 TASK: ffff80002018be80 CPU: 2 COMMAND: "dhry" ffff800022f6ae08: ffff00000812ae44 (crash_save_cpu on IRQ stack) ffff800022f6ae10: ffff800022f74e00 ffff800020107ed0 ffff800022f6ae20: 0000000000000000 ffff800020107ed0 ffff800022f6ae30: ffff000008a26800 0000000000000003 ffff800022f6ae40: 0000018800000005 0000000000000001 #0 [ffff800022f6ae50] crash_save_cpu at ffff00000812ae44 ffff800022f6ae50: ffff800022f6b010 ffff00000808e718 #1's fp #1's lr (=handle_IPI) ffff800022f6ae60: ffff000008bce000 0000000000000002 ----- ffff800022f6ae70: ffff800022f6ae90 0000000000000000 | ffff800022f6ae80: ffff800000000000 0000000000000000 | ffff800022f6ae90: 0000000000000000 0000000000000000 |local variables ... | including a big ffff800022f6afd0: 0000000000000000 0000000000000000 |"struct elf_prsatus" ffff800022f6afe0: ffff800022f6aff0 ffff00000808a820 | ffff800022f6aff0: ffff800022f6b010 ffff00000808e758 | ffff800022f6b000: ffff000008bce000 0000000000000000 ----- #1 [ffff800022f6b010] handle_IPI at ffff00000808e718 ffff800022f6b010: ffff800022f6b040 ffff0000080815f8 ffff800022f6b020: 0000000000000003 0000000000001fff ffff800022f6b030: ffff800020107ed0 ffff000008e60c54 #2 [ffff800022f6b040] gic_handle_irq at ffff0000080815f8 ffff800022f6b040: ffff800022f6b080 ffff000008084c4c == crash(master branch) === crash.dave> bt -f 1324 PID: 1324 TASK: ffff80002018be80 CPU: 2 COMMAND: "dhry" ffff800022f6ae08: ffff00000812ae44 (crash_save_cpu on IRQ stack) #0 [ffff800022f6ae10] crash_save_cpu at ffff00000812ae44 ffff800022f6ae10: ffff800022f74e00 ffff800020107ed0 ----- ffff800022f6ae20: 0000000000000000 ffff800020107ed0 |local variables ffff800022f6ae30: ffff000008a26800 0000000000000003 | of callee(*) ffff800022f6ae40: 0000018800000005 0000000000000001 ----- ffff800022f6ae50: ffff800022f6b010 ffff00000808e718 <= *real* stack frame #1 [ffff800022f6ae60] handle_IPI at ffff00000808e718 of crash_save_cpu() ffff800022f6ae60: ffff000008bce000 0000000000000002 starts here. ffff800022f6ae70: ffff800022f6ae90 0000000000000000 ffff800022f6ae80: ffff800000000000 0000000000000000 ffff800022f6ae90: 0000000000000000 0000000000000000 ffff800022f6aea0: 0000000000000000 000000000000052c ffff800022f6aeb0: 0000000000000000 0000000000000000 ... ffff800022f6afa0: ffff800022f6afc0 0000000000000000 ffff800022f6afb0: ffff800022f6afe0 ffff000008675850 ffff800022f6afc0: 0000000000402138 0000000000000000 ffff800022f6afd0: 0000000000000000 0000000000000000 ffff800022f6afe0: ffff800022f6aff0 ffff00000808a820 ffff800022f6aff0: ffff800022f6b010 ffff00000808e758 ffff800022f6b000: ffff000008bce000 0000000000000000 ffff800022f6b010: ffff800022f6b040 ffff0000080815f8 #2 [ffff800022f6b020] gic_handle_irq at ffff0000080815f8 ffff800022f6b020: 0000000000000003 0000000000001fff ffff800022f6b030: ffff800020107ed0 ffff000008e60c54 ffff800022f6b040: ffff800022f6b080 ffff000008084c4c === END === (*) append_elf_note() Thanks, -Takahiro AKASHI ======8<====== >From b3ca69ace916a5c233ce937954da887ba5487e50 Mon Sep 17 00:00:00 2001 From: AKASHI Takahiro <takahiro.akashi(a)linaro.org&gt; Date: Wed, 8 Jun 2016 11:14:22 +0900 Subject: [PATCH] arm64: dump a stack frame based on fp Signed-off-by: AKASHI Takahiro <takahiro.akashi(a)linaro.org&gt; --- arm64.c | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/arm64.c b/arm64.c index bdea79c..22f93a2 100644 --- a/arm64.c +++ b/arm64.c @@ -1508,12 +1508,12 @@ arm64_print_stackframe_entry(struct bt_info *bt, int level, struct arm64_stackfr } if (bt->flags & BT_FULL) { - arm64_display_full_frame(bt, frame->sp); - bt->frameptr = frame->sp; + arm64_display_full_frame(bt, frame->fp); + bt->frameptr = frame->fp; } fprintf(ofp, "%s#%d [%8lx] %s at %lx", level < 10 ? " " : "", level, - frame->sp, name_plus_offset ? name_plus_offset : name, frame->pc); + frame->fp, name_plus_offset ? name_plus_offset : name, frame->pc); if (BT_REFERENCE_CHECK(bt)) arm64_do_bt_reference_check(bt, frame->pc, name); @@ -1571,12 +1571,10 @@ arm64_unwind_frame(struct bt_info *bt, struct arm64_stackframe *frame) { unsigned long high, low, fp; unsigned long stack_mask; - unsigned long irq_stack_ptr, orig_sp, sp_in; + unsigned long irq_stack_ptr, orig_sp; struct arm64_pt_regs *ptregs; struct machine_specific *ms; - sp_in = frame->sp; - stack_mask = (unsigned long)(ARM64_STACK_SIZE) - 1; fp = frame->fp; @@ -1613,7 +1611,7 @@ arm64_unwind_frame(struct bt_info *bt, struct arm64_stackframe *frame) ptregs = (struct arm64_pt_regs *)&bt->stackbuf[(ulong)(STACK_OFFSET_TYPE(orig_sp))]; frame->sp = orig_sp; frame->pc = ptregs->pc; - bt->bptr = sp_in; + bt->bptr = fp; if (CRASHDEBUG(1)) error(INFO, "arm64_unwind_frame: switch stacks: fp: %lx sp: %lx pc: %lx\n", @@ -2004,8 +2002,11 @@ arm64_print_exception_frame(struct bt_info *bt, ulong pt_regs, int mode, FILE *o ulong LR, SP, offset; char buf[BUFSIZE]; +#if 0 /* FIXME? */ if (bt->flags & BT_FULL) arm64_display_full_frame(bt, pt_regs); +} +#endif if (CRASHDEBUG(1)) fprintf(ofp, "pt_regs: %lx\n", pt_regs); -- 2.8.1 -- Crash-utility mailing list Crash-utility(a)redhat.com https://www.redhat.com/mailman/listinfo/crash-utility

Hi Takahiro, To address my concerns about your patch, I added a few additional changes and attached it to this email. The changes are: (1) Prevent the stack dump "below" the #0 level. Yes, the stack data region is contained within the incoming frame parameters, but it's ugly and we really don't care to see what's before the #0 crash_kexec and crash_save_cpu #0 frames. (2) Fill in the missing stack dump at the top of the process stack, up to, but not including the user-space exception frame. (3) Instead of showing the fp of 0 in the top-most frame's stack address, fill it in with the address of the user-space exception frame. Note that there is no dump of the stack containing the user-space exception frame, but the register dump itself should suffice.

If you can live with the display, I'll clean up the patch, and maybe add the stack-layout diagram from your last post into a comment. It was quite helpful, especially in comparison to the x86_64 model, which is what I was mistakenly using as a guide. Thanks, Dave

diff --git a/arm64.c b/arm64.c index 86ec348..3b29ef4 100644 --- a/arm64.c +++ b/arm64.c @@ -1407,13 +1407,14 @@ arm64_print_stackframe_entry(struct bt_info *bt, int level, struct arm64_stackfr value_to_symstr(frame->pc, buf, bt->radix); } - if (bt->flags & BT_FULL) { - arm64_display_full_frame(bt, frame->sp); - bt->frameptr = frame->sp; + if ((bt->flags & BT_FULL) && level) { + arm64_display_full_frame(bt, frame->fp); + bt->frameptr = frame->fp; } fprintf(ofp, "%s#%d [%8lx] %s at %lx", level < 10 ? " " : "", level, - frame->sp, name_plus_offset ? name_plus_offset : name, frame->pc); +// frame->fp, name_plus_offset ? name_plus_offset : name, frame->pc); + frame->fp ? frame->fp : bt->stacktop - USER_EFRAME_OFFSET, name_plus_offset ? name_plus_offset : name, frame->pc); if (BT_REFERENCE_CHECK(bt)) arm64_do_bt_reference_check(bt, frame->pc, name); @@ -1447,8 +1448,12 @@ arm64_display_full_frame(struct bt_info *bt, ulong sp) if (bt->frameptr == sp) return; - if (!INSTACK(sp, bt) || !INSTACK(bt->frameptr, bt)) - return; + if (!INSTACK(sp, bt) || !INSTACK(bt->frameptr, bt)) { + if (sp == 0) + sp = bt->stacktop - USER_EFRAME_OFFSET; + else + return; + } words = (sp - bt->frameptr) / sizeof(ulong); @@ -1471,12 +1476,10 @@ arm64_unwind_frame(struct bt_info *bt, struct arm64_stackframe *frame) { unsigned long high, low, fp; unsigned long stack_mask; - unsigned long irq_stack_ptr, orig_sp, sp_in; + unsigned long irq_stack_ptr, orig_sp; struct arm64_pt_regs *ptregs; struct machine_specific *ms; - sp_in = frame->sp; - stack_mask = (unsigned long)(ARM64_STACK_SIZE) - 1; fp = frame->fp; @@ -1513,7 +1516,7 @@ arm64_unwind_frame(struct bt_info *bt, struct arm64_stackframe *frame) ptregs = (struct arm64_pt_regs *)&bt->stackbuf[(ulong)(STACK_OFFSET_TYPE(orig_sp))]; frame->sp = orig_sp; frame->pc = ptregs->pc; - bt->bptr = sp_in; + bt->bptr = fp; if (CRASHDEBUG(1)) error(INFO, "arm64_unwind_frame: switch stacks: fp: %lx sp: %lx pc: %lx\n", @@ -1904,8 +1907,10 @@ arm64_print_exception_frame(struct bt_info *bt, ulong pt_regs, int mode, FILE *o ulong LR, SP, offset; char buf[BUFSIZE]; +#if 0 /* FIXME? */ if (bt->flags & BT_FULL) arm64_display_full_frame(bt, pt_regs); +#endif if (CRASHDEBUG(1)) fprintf(ofp, "pt_regs: %lx\n", pt_regs);

-- Crash-utility mailing list Crash-utility(a)redhat.com https://www.redhat.com/mailman/listinfo/crash-utility

> Dave, > > On Fri, Jun 10, 2016 at 04:37:42PM -0400, Dave Anderson wrote: > > Hi Takahiro, > > > > To address my concerns about your patch, I added a few additional changes and attached > > it to this email. The changes are: > > > > (1) Prevent the stack dump "below" the #0 level. Yes, the stack data region is contained within > > the incoming frame parameters, but it's ugly and we really don't care to see what's before > > the #0 crash_kexec and crash_save_cpu #0 frames. > > (2) Fill in the missing stack dump at the top of the process stack, up to, but not including > > the user-space exception frame. > > (3) Instead of showing the fp of 0 in the top-most frame's stack address, fill it in with the > > address of the user-space exception frame. > > > > Note that there is no dump of the stack containing the user-space exception frame, but the > > register dump itself should suffice. > > Well, the essential problem with my patch is that the output from "bt -f" > looks like: > #XX ['fp'] 'function' at 'pc' --- (1) > <function's stack dump> --- (2) > but that (1) and (2) are not printed as a single stack frame in the same > iteration of while loop in arm64_back_trace_cmd(). > (I hope you understand what I mean :) Actually I prefer your first approach. I find this new one confusing, not to mention unlike any of the other architectures in that the "frame level" #X address value is not contiguous with the stack addresses that get filled in by -f.

Taking your picture into account: stack grows to lower addresses. /|\ | | | new sp +------+ <--- |dyn | | | vars | | new fp +- - - + | |old fp| | a function's stack frame |old lr| | |static| | | vars| | old sp +------+ <--- |dyn | | vars | old fp +------+ | | Your first patch seemed natural to me because for any "#X" line containing a function name, that function's dynamic variables, the "old fp/old lr" pair, and the function's static variables were dumped below it (i.e., at higher stack addresses). > To be consistent with the out format of x86, the output should be > <function's stack dump> > #XX ['fp'] 'function' at 'pc' > > Unfortunately, this requires that arm64_back_trace_cmd() and other functions should be overhauled. > Please take a look at my next patch though it is uncompleted and still has room for improvement. I don't know what you mean by "consistent with the out format of x86"? With x86_64, each #<level> line is simply the stack address where the function pushed its return address as a result of its making a "callq" to the next function. Any local variables of the calling function would be at the next higher stack addresses: ... #X [stack address] function2 at 'return address' <function2's local variables> #Y [stack address] function1 at 'return address' <functions1's local variables> ... So for digging out local stack variables associated with a function, it's a simple matter of looking "below" it in the "bt -f" output.

Dave > Thanks, > -Takahiro AKASHI > > > > If you can live with the display, I'll clean up the patch, and maybe add > > the stack-layout diagram > > from your last post into a comment. It was quite helpful, especially in > > comparison to the > > x86_64 model, which is what I was mistakenly using as a guide. > > > > Thanks, > > Dave > > > > > > > > > diff --git a/arm64.c b/arm64.c > > index 86ec348..3b29ef4 100644 > > --- a/arm64.c > > +++ b/arm64.c > > @@ -1407,13 +1407,14 @@ arm64_print_stackframe_entry(struct bt_info *bt, > > int level, struct arm64_stackfr > > value_to_symstr(frame->pc, buf, > > bt->radix); > > } > > > > - if (bt->flags & BT_FULL) { > > - arm64_display_full_frame(bt, frame->sp); > > - bt->frameptr = frame->sp; > > + if ((bt->flags & BT_FULL) && level) { > > + arm64_display_full_frame(bt, frame->fp); > > + bt->frameptr = frame->fp; > > } > > > > fprintf(ofp, "%s#%d [%8lx] %s at %lx", level < 10 ? " " : "", > > level, > > - frame->sp, name_plus_offset ? name_plus_offset : name, > > frame->pc); > > +// frame->fp, name_plus_offset ? name_plus_offset : name, > > frame->pc); > > + frame->fp ? frame->fp : bt->stacktop - USER_EFRAME_OFFSET, > > name_plus_offset ? name_plus_offset : name, frame->pc); > > > > if (BT_REFERENCE_CHECK(bt)) > > arm64_do_bt_reference_check(bt, frame->pc, name); > > @@ -1447,8 +1448,12 @@ arm64_display_full_frame(struct bt_info *bt, ulong > > sp) > > if (bt->frameptr == sp) > > return; > > > > - if (!INSTACK(sp, bt) || !INSTACK(bt->frameptr, bt)) > > - return; > > + if (!INSTACK(sp, bt) || !INSTACK(bt->frameptr, bt)) { > > + if (sp == 0) > > + sp = bt->stacktop - USER_EFRAME_OFFSET; > > + else > > + return; > > + } > > > > words = (sp - bt->frameptr) / sizeof(ulong); > > > > @@ -1471,12 +1476,10 @@ arm64_unwind_frame(struct bt_info *bt, struct > > arm64_stackframe *frame) > > { > > unsigned long high, low, fp; > > unsigned long stack_mask; > > - unsigned long irq_stack_ptr, orig_sp, sp_in; > > + unsigned long irq_stack_ptr, orig_sp; > > struct arm64_pt_regs *ptregs; > > struct machine_specific *ms; > > > > - sp_in = frame->sp; > > - > > stack_mask = (unsigned long)(ARM64_STACK_SIZE) - 1; > > fp = frame->fp; > > > > @@ -1513,7 +1516,7 @@ arm64_unwind_frame(struct bt_info *bt, struct > > arm64_stackframe *frame) > > ptregs = (struct arm64_pt_regs > > *)&bt->stackbuf[(ulong)(STACK_OFFSET_TYPE(orig_sp))]; > > frame->sp = orig_sp; > > frame->pc = ptregs->pc; > > - bt->bptr = sp_in; > > + bt->bptr = fp; > > if (CRASHDEBUG(1)) > > error(INFO, > > "arm64_unwind_frame: switch stacks: fp: %lx sp: %lx pc: %lx\n", > > @@ -1904,8 +1907,10 @@ arm64_print_exception_frame(struct bt_info *bt, > > ulong pt_regs, int mode, FILE *o > > ulong LR, SP, offset; > > char buf[BUFSIZE]; > > > > +#if 0 /* FIXME? */ > > if (bt->flags & BT_FULL) > > arm64_display_full_frame(bt, pt_regs); > > +#endif > > > > if (CRASHDEBUG(1)) > > fprintf(ofp, "pt_regs: %lx\n", pt_regs); > > > -- > > Crash-utility mailing list > > Crash-utility(a)redhat.com > > https://www.redhat.com/mailman/listinfo/crash-utility > > -- > Crash-utility mailing list > Crash-utility(a)redhat.com > https://www.redhat.com/mailman/listinfo/crash-utility > -- Crash-utility mailing list Crash-utility(a)redhat.com https://www.redhat.com/mailman/listinfo/crash-utility

> Adds ARM64 support for 3-level page tables with 64K pages and 48 VA bits. Nicely done, Jim. Queued for crash-7.1.5: https://github.com/crash-utility/crash/commit/ab91852f945bfecfa0bca6a4225... Thanks, Dave

> --- > arm64.c | 126 > ++++++++++++++++++++++++++++++++++++++++++++++++++++++++-------- > defs.h | 28 +++++++++++---- > 2 files changed, 133 insertions(+), 21 deletions(-) > > diff --git a/arm64.c b/arm64.c > index f6ea7a1..d1c9c3e 100644 > --- a/arm64.c > +++ b/arm64.c > @@ -34,6 +34,7 @@ static void arm64_init_kernel_pgd(void); > static int arm64_kvtop(struct task_context *, ulong, physaddr_t *, int); > static int arm64_uvtop(struct task_context *, ulong, physaddr_t *, int); > static int arm64_vtop_2level_64k(ulong, ulong, physaddr_t *, int); > +static int arm64_vtop_3level_64k(ulong, ulong, physaddr_t *, int); > static int arm64_vtop_3level_4k(ulong, ulong, physaddr_t *, int); > static ulong arm64_get_task_pgd(ulong); > static void arm64_irq_stack_init(void); > @@ -188,15 +189,29 @@ arm64_init(int when) > break; > > case 65536: > - machdep->flags |= VM_L2_64K; > - machdep->ptrs_per_pgd = PTRS_PER_PGD_L2_64K; > - if ((machdep->pgd = > - (char *)malloc(PTRS_PER_PGD_L2_64K * 8)) == NULL) > - error(FATAL, "cannot malloc pgd space."); > - if ((machdep->ptbl = > - (char *)malloc(PTRS_PER_PTE_L2_64K * 8)) == NULL) > - error(FATAL, "cannot malloc ptbl space."); > - machdep->pmd = NULL; /* not used */ > + if (machdep->machspec->VA_BITS > PGDIR_SHIFT_L3_64K) { > + machdep->flags |= VM_L3_64K; > + machdep->ptrs_per_pgd = PTRS_PER_PGD_L3_64K; > + if ((machdep->pgd = > + (char *)malloc(PTRS_PER_PGD_L3_64K * 8)) == NULL) > + error(FATAL, "cannot malloc pgd space."); > + if ((machdep->pmd = > + (char *)malloc(PTRS_PER_PMD_L3_64K * 8)) == NULL) > + error(FATAL, "cannot malloc pmd space."); > + if ((machdep->ptbl = > + (char *)malloc(PTRS_PER_PTE_L3_64K * 8)) == NULL) > + error(FATAL, "cannot malloc ptbl space."); > + } else { > + machdep->flags |= VM_L2_64K; > + machdep->ptrs_per_pgd = PTRS_PER_PGD_L2_64K; > + if ((machdep->pgd = > + (char *)malloc(PTRS_PER_PGD_L2_64K * 8)) == NULL) > + error(FATAL, "cannot malloc pgd space."); > + if ((machdep->ptbl = > + (char *)malloc(PTRS_PER_PTE_L2_64K * 8)) == NULL) > + error(FATAL, "cannot malloc ptbl space."); > + machdep->pmd = NULL; /* not used */ > + } > machdep->pud = NULL; /* not used */ > break; > > @@ -379,6 +394,8 @@ arm64_dump_machdep_table(ulong arg) > fprintf(fp, "%sPHYS_OFFSET", others++ ? "|" : ""); > if (machdep->flags & VM_L2_64K) > fprintf(fp, "%sVM_L2_64K", others++ ? "|" : ""); > + if (machdep->flags & VM_L3_64K) > + fprintf(fp, "%sVM_L3_64K", others++ ? "|" : ""); > if (machdep->flags & VM_L3_4K) > fprintf(fp, "%sVM_L3_4K", others++ ? "|" : ""); > if (machdep->flags & VMEMMAP) > @@ -410,10 +427,14 @@ arm64_dump_machdep_table(ulong arg) > fprintf(fp, " processor_speed: arm64_processor_speed()\n"); > fprintf(fp, " uvtop: arm64_uvtop()->%s()\n", > machdep->flags & VM_L3_4K ? > - "arm64_vtop_3level_4k" : "arm64_vtop_2level_64k"); > + "arm64_vtop_3level_4k" : > + machdep->flags & VM_L3_64K ? > + "arm64_vtop_3level_64k" : "arm64_vtop_2level_64k"); > fprintf(fp, " kvtop: arm64_kvtop()->%s()\n", > machdep->flags & VM_L3_4K ? > - "arm64_vtop_3level_4k" : "arm64_vtop_2level_64k"); > + "arm64_vtop_3level_4k" : > + machdep->flags & VM_L3_64K ? > + "arm64_vtop_3level_64k" : "arm64_vtop_2level_64k"); > fprintf(fp, " get_task_pgd: arm64_get_task_pgd()\n"); > fprintf(fp, " dump_irq: generic_dump_irq()\n"); > fprintf(fp, " get_stack_frame: arm64_get_stack_frame()\n"); > @@ -719,10 +740,12 @@ arm64_kvtop(struct task_context *tc, ulong kvaddr, > physaddr_t *paddr, int verbos > kernel_pgd = vt->kernel_pgd[0]; > *paddr = 0; > > - switch (machdep->flags & (VM_L2_64K|VM_L3_4K)) > + switch (machdep->flags & (VM_L2_64K|VM_L3_64K|VM_L3_4K)) > { > case VM_L2_64K: > return arm64_vtop_2level_64k(kernel_pgd, kvaddr, paddr, verbose); > + case VM_L3_64K: > + return arm64_vtop_3level_64k(kernel_pgd, kvaddr, paddr, verbose); > case VM_L3_4K: > return arm64_vtop_3level_4k(kernel_pgd, kvaddr, paddr, verbose); > default: > @@ -740,10 +763,12 @@ arm64_uvtop(struct task_context *tc, ulong uvaddr, > physaddr_t *paddr, int verbos > > *paddr = 0; > > - switch (machdep->flags & (VM_L2_64K|VM_L3_4K)) > + switch (machdep->flags & (VM_L2_64K|VM_L3_64K|VM_L3_4K)) > { > case VM_L2_64K: > return arm64_vtop_2level_64k(user_pgd, uvaddr, paddr, verbose); > + case VM_L3_64K: > + return arm64_vtop_3level_64k(user_pgd, uvaddr, paddr, verbose); > case VM_L3_4K: > return arm64_vtop_3level_4k(user_pgd, uvaddr, paddr, verbose); > default: > @@ -820,6 +845,78 @@ no_page: > return FALSE; > } > > +static int > +arm64_vtop_3level_64k(ulong pgd, ulong vaddr, physaddr_t *paddr, int > verbose) > +{ > + ulong *pgd_base, *pgd_ptr, pgd_val; > + ulong *pmd_base, *pmd_ptr, pmd_val; > + ulong *pte_base, *pte_ptr, pte_val; > + > + if (verbose) > + fprintf(fp, "PAGE DIRECTORY: %lx\n", pgd); > + > + pgd_base = (ulong *)pgd; > + FILL_PGD(pgd_base, KVADDR, PTRS_PER_PGD_L3_64K * sizeof(ulong)); > + pgd_ptr = pgd_base + (((vaddr) >> PGDIR_SHIFT_L3_64K) & > (PTRS_PER_PGD_L3_64K - 1)); > + pgd_val = ULONG(machdep->pgd + PAGEOFFSET(pgd_ptr)); > + if (verbose) > + fprintf(fp, " PGD: %lx => %lx\n", (ulong)pgd_ptr, > pgd_val); > + if (!pgd_val) > + goto no_page; > + > + /* > + * #define __PAGETABLE_PUD_FOLDED > + */ > + > + pmd_base = (ulong *)PTOV(pgd_val & PHYS_MASK & (s32)machdep->pagemask); > + FILL_PMD(pmd_base, KVADDR, PTRS_PER_PMD_L3_64K * sizeof(ulong)); > + pmd_ptr = pmd_base + (((vaddr) >> PMD_SHIFT_L3_64K) & (PTRS_PER_PMD_L3_64K > - 1)); > + pmd_val = ULONG(machdep->pmd + PAGEOFFSET(pmd_ptr)); > + if (verbose) > + fprintf(fp, " PMD: %lx => %lx\n", (ulong)pmd_ptr, > pmd_val); > + if (!pmd_val) > + goto no_page; > + > + if ((pmd_val & PMD_TYPE_MASK) == PMD_TYPE_SECT) { > + ulong sectionbase = (pmd_val & SECTION_PAGE_MASK_512MB) & PHYS_MASK; > + if (verbose) { > + fprintf(fp, " PAGE: %lx (512MB)\n\n", sectionbase); > + arm64_translate_pte(pmd_val, 0, 0); > + } > + *paddr = sectionbase + (vaddr & ~SECTION_PAGE_MASK_512MB); > + return TRUE; > + } > + > + pte_base = (ulong *)PTOV(pmd_val & PHYS_MASK & (s32)machdep->pagemask); > + FILL_PTBL(pte_base, KVADDR, PTRS_PER_PTE_L3_64K * sizeof(ulong)); > + pte_ptr = pte_base + (((vaddr) >> machdep->pageshift) & > (PTRS_PER_PTE_L3_64K - 1)); > + pte_val = ULONG(machdep->ptbl + PAGEOFFSET(pte_ptr)); > + if (verbose) > + fprintf(fp, " PTE: %lx => %lx\n", (ulong)pte_ptr, > pte_val); > + if (!pte_val) > + goto no_page; > + > + if (pte_val & PTE_VALID) { > + *paddr = (PAGEBASE(pte_val) & PHYS_MASK) + PAGEOFFSET(vaddr); > + if (verbose) { > + fprintf(fp, " PAGE: %lx\n\n", PAGEBASE(*paddr)); > + arm64_translate_pte(pte_val, 0, 0); > + } > + } else { > + if (IS_UVADDR(vaddr, NULL)) > + *paddr = pte_val; > + if (verbose) { > + fprintf(fp, "\n"); > + arm64_translate_pte(pte_val, 0, 0); > + } > + goto no_page; > + } > + > + return TRUE; > +no_page: > + return FALSE; > +} > + > static int > arm64_vtop_3level_4k(ulong pgd, ulong vaddr, physaddr_t *paddr, int verbose) > { > @@ -2348,9 +2445,10 @@ arm64_calc_virtual_memory_ranges(void) > > STRUCT_SIZE_INIT(page, "page"); > > - switch (machdep->flags & (VM_L2_64K|VM_L3_4K)) > + switch (machdep->flags & (VM_L2_64K|VM_L3_64K|VM_L3_4K)) > { > case VM_L2_64K: > + case VM_L3_64K: > PUD_SIZE = PGDIR_SIZE_L2_64K; > break; > case VM_L3_4K: > diff --git a/defs.h b/defs.h > index 56ae06c..d1b49d0 100644 > --- a/defs.h > +++ b/defs.h > @@ -2815,7 +2815,7 @@ typedef u64 pte_t; > > typedef signed int s32; > > -/* > +/* > * 3-levels / 4K pages > */ > #define PTRS_PER_PGD_L3_4K (512) > @@ -2823,10 +2823,23 @@ typedef signed int s32; > #define PTRS_PER_PTE_L3_4K (512) > #define PGDIR_SHIFT_L3_4K (30) > #define PGDIR_SIZE_L3_4K ((1UL) << PGDIR_SHIFT_L3_4K) > -#define PGDIR_MASK_L3 4K (~(PGDIR_SIZE_L3_4K-1)) > +#define PGDIR_MASK_L3_4K (~(PGDIR_SIZE_L3_4K-1)) > #define PMD_SHIFT_L3_4K (21) > -#define PMD_SIZE_L3_4K (1UL << PMD_SHIFT_4K) > -#define PMD_MASK_L3 4K (~(PMD_SIZE_4K-1)) > +#define PMD_SIZE_L3_4K (1UL << PMD_SHIFT_L3_4K) > +#define PMD_MASK_L3_4K (~(PMD_SIZE_L3_4K-1)) > + > +/* > + * 3-levels / 64K pages > + */ > +#define PTRS_PER_PGD_L3_64K (64) > +#define PTRS_PER_PMD_L3_64K (8192) > +#define PTRS_PER_PTE_L3_64K (8192) > +#define PGDIR_SHIFT_L3_64K (42) > +#define PGDIR_SIZE_L3_64K ((1UL) << PGDIR_SHIFT_L3_64K) > +#define PGDIR_MASK_L3_64K (~(PGDIR_SIZE_L3_64K-1)) > +#define PMD_SHIFT_L3_64K (29) > +#define PMD_SIZE_L3_64K (1UL << PMD_SHIFT_L3_64K) > +#define PMD_MASK_L3_64K (~(PMD_SIZE_L3_64K-1)) > > /* > * 2-levels / 64K pages > @@ -2868,9 +2881,10 @@ typedef signed int s32; > #define KSYMS_START (0x1) > #define PHYS_OFFSET (0x2) > #define VM_L2_64K (0x4) > -#define VM_L3_4K (0x8) > -#define KDUMP_ENABLED (0x10) > -#define IRQ_STACKS (0x20) > +#define VM_L3_64K (0x8) > +#define VM_L3_4K (0x10) > +#define KDUMP_ENABLED (0x20) > +#define IRQ_STACKS (0x40) > > /* > * sources: Documentation/arm64/memory.txt > -- > 2.1.4 > > -- > Crash-utility mailing list > Crash-utility redhat com > https://www.redhat.com/mailman/listinfo/crash-utility >

Hi Jim, The problem looks to be the use of PAGEOFFSET() into the 512-byte pgd used for 3-level/64K-pages:

static int arm64_vtop_3level_64k(ulong pgd, ulong vaddr, physaddr_t *paddr, int verbose) { ulong *pgd_base, *pgd_ptr, pgd_val; ulong *pmd_base, *pmd_ptr, pmd_val; ulong *pte_base, *pte_ptr, pte_val; if (verbose) fprintf(fp, "PAGE DIRECTORY: %lx\n", pgd); pgd_base = (ulong *)pgd; FILL_PGD(pgd_base, KVADDR, PTRS_PER_PGD_L3_64K * sizeof(ulong)); pgd_ptr = pgd_base + (((vaddr) >> PGDIR_SHIFT_L3_64K) & (PTRS_PER_PGD_L3_64K - 1)); pgd_val = ULONG(machdep->pgd + PAGEOFFSET(pgd_ptr)); ^^^^^^^^^^^^^^^^^^ For kernel vmalloc addresses, the kernel's "swapper_pg_dir" is used, which has a base address that's aligned on a 64k page boundary. So PAGEOFFSET() works as an index. But for user-space addresses, the mm_struct->pgd is not 64K page aligned so the use of PAGEOFFSET() calculates an address that's goes way beyond the end of the 512-byte aligned pgd: crash> for user vm -p | grep -e PGD -e "k " MM PGD RSS TOTAL_VM ffff8003d61ec240 ffff8003d5b12c00 11904k 12992k MM PGD RSS TOTAL_VM ffff8003d60aec40 ffff8003dcb7ca00 4864k 88448k MM PGD RSS TOTAL_VM ffff8000dbf1dc80 ffff8003d69bca00 8704k 92928k MM PGD RSS TOTAL_VM ffff8000dbf1e700 ffff8003d69b4a00 8768k 17536k MM PGD RSS TOTAL_VM ffff8003d65c9300 ffff8000d4055600 5696k 16576k MM PGD RSS TOTAL_VM ffff8003d65c9300 ffff8000d4055600 5696k 16576k MM PGD RSS TOTAL_VM ffff8003d65c9840 ffff8000d4051800 1664k 2560k MM PGD RSS TOTAL_VM ffff8003d60a8340 ffff8003dcb7fa00 10944k 303552k MM PGD RSS TOTAL_VM ffff8003d65c8880 ffff8000d4052c00 19456k 353600k MM PGD RSS TOTAL_VM ffff8003d61ab7c0 ffff8003dc86b800 4864k 14016k MM PGD RSS TOTAL_VM ffff8000dbf18340 ffff8003d69b1400 7424k 157632k MM PGD RSS TOTAL_VM ffff8003d60a8340 ffff8003dcb7fa00 10944k 303552k MM PGD RSS TOTAL_VM ffff8003d60a8340 ffff8003dcb7fa00 10944k 303552k MM PGD RSS TOTAL_VM ffff8000dbf18340 ffff8003d69b1400 7424k 157632k MM PGD RSS TOTAL_VM ffff8000dbf18340 ffff8003d69b1400 7424k 157632k MM PGD RSS TOTAL_VM ffff8000dbf18340 ffff8003d69b1400 7424k 157632k MM PGD RSS TOTAL_VM ffff8000dbf18340 ffff8003d69b1400 7424k 157632k MM PGD RSS TOTAL_VM ffff8000dbf18340 ffff8003d69b1400 7424k 157632k MM PGD RSS TOTAL_VM ffff8003d61ab7c0 ffff8003dc86b800 4864k 14016k MM PGD RSS TOTAL_VM ffff8000c403b7c0 ffff8003d6597800 4928k 5888k MM PGD RSS TOTAL_VM ffff8003d59db7c0 ffff8003dcd18600 4352k 5248k MM PGD RSS TOTAL_VM ffff8003d61ead40 ffff8003d4107400 3776k 5760k MM PGD RSS TOTAL_VM ffff8000c403ad40 ffff8003d6592000 4224k 5120k MM PGD RSS TOTAL_VM ffff8003d60a78c0 ffff8003dcb72600 2496k 109888k MM PGD RSS TOTAL_VM ffff8003d61a8880 ffff8003dc86b200 2176k 109888k MM PGD RSS TOTAL_VM ffff8003d65c8880 ffff8000d4052c00 19456k 353600k MM PGD RSS TOTAL_VM ffff8003d65c8880 ffff8000d4052c00 19456k 353600k ... Dave ----- Original Message ----- > > ----- Original Message ----- > > > Adds ARM64 support for 3-level page tables with 64K pages and 48 VA > > > bits. > > > > Nicely done, Jim. Queued for crash-7.1.5: > > > > https://github.com/crash-utility/crash/commit/ab91852f945bfecfa0bca6a4225... > > > > Thanks, > > Dave > > > > Hi Jim, > > I just noticed today that your 3-level 64K patch does not work for user > virtual address space. > I haven't looked too deeply into it, but for example on a live system, all > user virtual address > vtop operations fail, all disk-backed user memory space shows the "FILE:" > backing, and the > anonymous space shows "(not mapped)": > > crash> help -m | grep VM > flags: 10400069 > (KSYMS_START|VM_L3_64K|VMEMMAP|KDUMP_ENABLED|IRQ_STACKS|MACHDEP_BT_TEXT) > crash> sys | grep RELEASE > RELEASE: 4.5.0-0.38.el7.aarch64 > crash> set > PID: 1212 > COMMAND: "crash" > TASK: ffff8003d74f3f00 [THREAD_INFO: ffff8003d7454000] > CPU: 1 > STATE: TASK_RUNNING (ACTIVE) > crash> vm -p > PID: 1212 TASK: ffff8003d74f3f00 CPU: 1 COMMAND: "crash" > MM PGD RSS TOTAL_VM > ffff8000c40363c0 ffff8003db6a9200 211904k 355264k > VMA START END FLAGS FILE > ffff8003de746d40 400000 a00000 875 /root/crash.git/crash > VIRTUAL PHYSICAL > 400000 FILE: /root/crash.git/crash OFFSET: 0 > 410000 FILE: /root/crash.git/crash OFFSET: 10000 > 420000 FILE: /root/crash.git/crash OFFSET: 20000 > 430000 FILE: /root/crash.git/crash OFFSET: 30000 > 440000 FILE: /root/crash.git/crash OFFSET: 40000 > 450000 FILE: /root/crash.git/crash OFFSET: 50000 > ... [ cut ] ... > VMA START END FLAGS FILE > ffff8003de745d70 a50000 b00000 100073 > VIRTUAL PHYSICAL > a50000 (not mapped) > a60000 (not mapped) > a70000 (not mapped) > a80000 (not mapped) > a90000 (not mapped) > aa0000 (not mapped) > ab0000 (not mapped) > ac0000 (not mapped) > ... > > In all cases, the PGD value reads as 0 and therefore fails: > > crash> vtop 400000 > VIRTUAL PHYSICAL > 400000 (not mapped) > > PAGE DIRECTORY: ffff8003db6a9200 > PGD: ffff8003db6a9200 => 0 > > VMA START END FLAGS FILE > ffff8003de746d40 400000 a00000 875 /root/crash.git/crash > > FILE: /root/crash.git/crash OFFSET: 0 > > crash> > > That is the correct PGD address, and when read, it looks like a valid PTE: > > crash> rd ffff8003db6a9200 > ffff8003db6a9200: 00000043dee60003 ....C... > crash> > > vmalloc() addresses translate just fine, and since they use the same > function, > I'm not sure what's going on? Did you ever check user-space translations? > > Thanks, > Dave > > > > > > > > > > --- > > > arm64.c | 126 > > > ++++++++++++++++++++++++++++++++++++++++++++++++++++++++-------- > > > defs.h | 28 +++++++++++---- > > > 2 files changed, 133 insertions(+), 21 deletions(-) > > > > > > diff --git a/arm64.c b/arm64.c > > > index f6ea7a1..d1c9c3e 100644 > > > --- a/arm64.c > > > +++ b/arm64.c > > > @@ -34,6 +34,7 @@ static void arm64_init_kernel_pgd(void); > > > static int arm64_kvtop(struct task_context *, ulong, physaddr_t *, > > > int); > > > static int arm64_uvtop(struct task_context *, ulong, physaddr_t *, > > > int); > > > static int arm64_vtop_2level_64k(ulong, ulong, physaddr_t *, int); > > > +static int arm64_vtop_3level_64k(ulong, ulong, physaddr_t *, int); > > > static int arm64_vtop_3level_4k(ulong, ulong, physaddr_t *, int); > > > static ulong arm64_get_task_pgd(ulong); > > > static void arm64_irq_stack_init(void); > > > @@ -188,15 +189,29 @@ arm64_init(int when) > > > break; > > > > > > case 65536: > > > - machdep->flags |= VM_L2_64K; > > > - machdep->ptrs_per_pgd = PTRS_PER_PGD_L2_64K; > > > - if ((machdep->pgd = > > > - (char *)malloc(PTRS_PER_PGD_L2_64K * 8)) == NULL) > > > - error(FATAL, "cannot malloc pgd space."); > > > - if ((machdep->ptbl = > > > - (char *)malloc(PTRS_PER_PTE_L2_64K * 8)) == NULL) > > > - error(FATAL, "cannot malloc ptbl space."); > > > - machdep->pmd = NULL; /* not used */ > > > + if (machdep->machspec->VA_BITS > PGDIR_SHIFT_L3_64K) { > > > + machdep->flags |= VM_L3_64K; > > > + machdep->ptrs_per_pgd = PTRS_PER_PGD_L3_64K; > > > + if ((machdep->pgd = > > > + (char *)malloc(PTRS_PER_PGD_L3_64K * 8)) == NULL) > > > + error(FATAL, "cannot malloc pgd space."); > > > + if ((machdep->pmd = > > > + (char *)malloc(PTRS_PER_PMD_L3_64K * 8)) == NULL) > > > + error(FATAL, "cannot malloc pmd space."); > > > + if ((machdep->ptbl = > > > + (char *)malloc(PTRS_PER_PTE_L3_64K * 8)) == NULL) > > > + error(FATAL, "cannot malloc ptbl space."); > > > + } else { > > > + machdep->flags |= VM_L2_64K; > > > + machdep->ptrs_per_pgd = PTRS_PER_PGD_L2_64K; > > > + if ((machdep->pgd = > > > + (char *)malloc(PTRS_PER_PGD_L2_64K * 8)) == NULL) > > > + error(FATAL, "cannot malloc pgd space."); > > > + if ((machdep->ptbl = > > > + (char *)malloc(PTRS_PER_PTE_L2_64K * 8)) == NULL) > > > + error(FATAL, "cannot malloc ptbl space."); > > > + machdep->pmd = NULL; /* not used */ > > > + } > > > machdep->pud = NULL; /* not used */ > > > break; > > > > > > @@ -379,6 +394,8 @@ arm64_dump_machdep_table(ulong arg) > > > fprintf(fp, "%sPHYS_OFFSET", others++ ? "|" : ""); > > > if (machdep->flags & VM_L2_64K) > > > fprintf(fp, "%sVM_L2_64K", others++ ? "|" : ""); > > > + if (machdep->flags & VM_L3_64K) > > > + fprintf(fp, "%sVM_L3_64K", others++ ? "|" : ""); > > > if (machdep->flags & VM_L3_4K) > > > fprintf(fp, "%sVM_L3_4K", others++ ? "|" : ""); > > > if (machdep->flags & VMEMMAP) > > > @@ -410,10 +427,14 @@ arm64_dump_machdep_table(ulong arg) > > > fprintf(fp, " processor_speed: arm64_processor_speed()\n"); > > > fprintf(fp, " uvtop: arm64_uvtop()->%s()\n", > > > machdep->flags & VM_L3_4K ? > > > - "arm64_vtop_3level_4k" : "arm64_vtop_2level_64k"); > > > + "arm64_vtop_3level_4k" : > > > + machdep->flags & VM_L3_64K ? > > > + "arm64_vtop_3level_64k" : "arm64_vtop_2level_64k"); > > > fprintf(fp, " kvtop: arm64_kvtop()->%s()\n", > > > machdep->flags & VM_L3_4K ? > > > - "arm64_vtop_3level_4k" : "arm64_vtop_2level_64k"); > > > + "arm64_vtop_3level_4k" : > > > + machdep->flags & VM_L3_64K ? > > > + "arm64_vtop_3level_64k" : "arm64_vtop_2level_64k"); > > > fprintf(fp, " get_task_pgd: arm64_get_task_pgd()\n"); > > > fprintf(fp, " dump_irq: generic_dump_irq()\n"); > > > fprintf(fp, " get_stack_frame: arm64_get_stack_frame()\n"); > > > @@ -719,10 +740,12 @@ arm64_kvtop(struct task_context *tc, ulong > > > kvaddr, > > > physaddr_t *paddr, int verbos > > > kernel_pgd = vt->kernel_pgd[0]; > > > *paddr = 0; > > > > > > - switch (machdep->flags & (VM_L2_64K|VM_L3_4K)) > > > + switch (machdep->flags & (VM_L2_64K|VM_L3_64K|VM_L3_4K)) > > > { > > > case VM_L2_64K: > > > return arm64_vtop_2level_64k(kernel_pgd, kvaddr, paddr, verbose); > > > + case VM_L3_64K: > > > + return arm64_vtop_3level_64k(kernel_pgd, kvaddr, paddr, verbose); > > > case VM_L3_4K: > > > return arm64_vtop_3level_4k(kernel_pgd, kvaddr, paddr, verbose); > > > default: > > > @@ -740,10 +763,12 @@ arm64_uvtop(struct task_context *tc, ulong > > > uvaddr, > > > physaddr_t *paddr, int verbos > > > > > > *paddr = 0; > > > > > > - switch (machdep->flags & (VM_L2_64K|VM_L3_4K)) > > > + switch (machdep->flags & (VM_L2_64K|VM_L3_64K|VM_L3_4K)) > > > { > > > case VM_L2_64K: > > > return arm64_vtop_2level_64k(user_pgd, uvaddr, paddr, verbose); > > > + case VM_L3_64K: > > > + return arm64_vtop_3level_64k(user_pgd, uvaddr, paddr, verbose); > > > case VM_L3_4K: > > > return arm64_vtop_3level_4k(user_pgd, uvaddr, paddr, verbose); > > > default: > > > @@ -820,6 +845,78 @@ no_page: > > > return FALSE; > > > } > > > > > > +static int > > > +arm64_vtop_3level_64k(ulong pgd, ulong vaddr, physaddr_t *paddr, int > > > verbose) > > > +{ > > > + ulong *pgd_base, *pgd_ptr, pgd_val; > > > + ulong *pmd_base, *pmd_ptr, pmd_val; > > > + ulong *pte_base, *pte_ptr, pte_val; > > > + > > > + if (verbose) > > > + fprintf(fp, "PAGE DIRECTORY: %lx\n", pgd); > > > + > > > + pgd_base = (ulong *)pgd; > > > + FILL_PGD(pgd_base, KVADDR, PTRS_PER_PGD_L3_64K * sizeof(ulong)); > > > + pgd_ptr = pgd_base + (((vaddr) >> PGDIR_SHIFT_L3_64K) & > > > (PTRS_PER_PGD_L3_64K - 1)); > > > + pgd_val = ULONG(machdep->pgd + PAGEOFFSET(pgd_ptr)); > > > + if (verbose) > > > + fprintf(fp, " PGD: %lx => %lx\n", (ulong)pgd_ptr, > > > pgd_val); > > > + if (!pgd_val) > > > + goto no_page; > > > + > > > + /* > > > + * #define __PAGETABLE_PUD_FOLDED > > > + */ > > > + > > > + pmd_base = (ulong *)PTOV(pgd_val & PHYS_MASK & > > > (s32)machdep->pagemask); > > > + FILL_PMD(pmd_base, KVADDR, PTRS_PER_PMD_L3_64K * sizeof(ulong)); > > > + pmd_ptr = pmd_base + (((vaddr) >> PMD_SHIFT_L3_64K) & > > > (PTRS_PER_PMD_L3_64K > > > - 1)); > > > + pmd_val = ULONG(machdep->pmd + PAGEOFFSET(pmd_ptr)); > > > + if (verbose) > > > + fprintf(fp, " PMD: %lx => %lx\n", (ulong)pmd_ptr, > > > pmd_val); > > > + if (!pmd_val) > > > + goto no_page; > > > + > > > + if ((pmd_val & PMD_TYPE_MASK) == PMD_TYPE_SECT) { > > > + ulong sectionbase = (pmd_val & SECTION_PAGE_MASK_512MB) & PHYS_MASK; > > > + if (verbose) { > > > + fprintf(fp, " PAGE: %lx (512MB)\n\n", sectionbase); > > > + arm64_translate_pte(pmd_val, 0, 0); > > > + } > > > + *paddr = sectionbase + (vaddr & ~SECTION_PAGE_MASK_512MB); > > > + return TRUE; > > > + } > > > + > > > + pte_base = (ulong *)PTOV(pmd_val & PHYS_MASK & > > > (s32)machdep->pagemask); > > > + FILL_PTBL(pte_base, KVADDR, PTRS_PER_PTE_L3_64K * sizeof(ulong)); > > > + pte_ptr = pte_base + (((vaddr) >> machdep->pageshift) & > > > (PTRS_PER_PTE_L3_64K - 1)); > > > + pte_val = ULONG(machdep->ptbl + PAGEOFFSET(pte_ptr)); > > > + if (verbose) > > > + fprintf(fp, " PTE: %lx => %lx\n", (ulong)pte_ptr, > > > pte_val); > > > + if (!pte_val) > > > + goto no_page; > > > + > > > + if (pte_val & PTE_VALID) { > > > + *paddr = (PAGEBASE(pte_val) & PHYS_MASK) + PAGEOFFSET(vaddr); > > > + if (verbose) { > > > + fprintf(fp, " PAGE: %lx\n\n", PAGEBASE(*paddr)); > > > + arm64_translate_pte(pte_val, 0, 0); > > > + } > > > + } else { > > > + if (IS_UVADDR(vaddr, NULL)) > > > + *paddr = pte_val; > > > + if (verbose) { > > > + fprintf(fp, "\n"); > > > + arm64_translate_pte(pte_val, 0, 0); > > > + } > > > + goto no_page; > > > + } > > > + > > > + return TRUE; > > > +no_page: > > > + return FALSE; > > > +} > > > + > > > static int > > > arm64_vtop_3level_4k(ulong pgd, ulong vaddr, physaddr_t *paddr, int > > > verbose) > > > { > > > @@ -2348,9 +2445,10 @@ arm64_calc_virtual_memory_ranges(void) > > > > > > STRUCT_SIZE_INIT(page, "page"); > > > > > > - switch (machdep->flags & (VM_L2_64K|VM_L3_4K)) > > > + switch (machdep->flags & (VM_L2_64K|VM_L3_64K|VM_L3_4K)) > > > { > > > case VM_L2_64K: > > > + case VM_L3_64K: > > > PUD_SIZE = PGDIR_SIZE_L2_64K; > > > break; > > > case VM_L3_4K: > > > diff --git a/defs.h b/defs.h > > > index 56ae06c..d1b49d0 100644 > > > --- a/defs.h > > > +++ b/defs.h > > > @@ -2815,7 +2815,7 @@ typedef u64 pte_t; > > > > > > typedef signed int s32; > > > > > > -/* > > > +/* > > > * 3-levels / 4K pages > > > */ > > > #define PTRS_PER_PGD_L3_4K (512) > > > @@ -2823,10 +2823,23 @@ typedef signed int s32; > > > #define PTRS_PER_PTE_L3_4K (512) > > > #define PGDIR_SHIFT_L3_4K (30) > > > #define PGDIR_SIZE_L3_4K ((1UL) << PGDIR_SHIFT_L3_4K) > > > -#define PGDIR_MASK_L3 4K (~(PGDIR_SIZE_L3_4K-1)) > > > +#define PGDIR_MASK_L3_4K (~(PGDIR_SIZE_L3_4K-1)) > > > #define PMD_SHIFT_L3_4K (21) > > > -#define PMD_SIZE_L3_4K (1UL << PMD_SHIFT_4K) > > > -#define PMD_MASK_L3 4K (~(PMD_SIZE_4K-1)) > > > +#define PMD_SIZE_L3_4K (1UL << PMD_SHIFT_L3_4K) > > > +#define PMD_MASK_L3_4K (~(PMD_SIZE_L3_4K-1)) > > > + > > > +/* > > > + * 3-levels / 64K pages > > > + */ > > > +#define PTRS_PER_PGD_L3_64K (64) > > > +#define PTRS_PER_PMD_L3_64K (8192) > > > +#define PTRS_PER_PTE_L3_64K (8192) > > > +#define PGDIR_SHIFT_L3_64K (42) > > > +#define PGDIR_SIZE_L3_64K ((1UL) << PGDIR_SHIFT_L3_64K) > > > +#define PGDIR_MASK_L3_64K (~(PGDIR_SIZE_L3_64K-1)) > > > +#define PMD_SHIFT_L3_64K (29) > > > +#define PMD_SIZE_L3_64K (1UL << PMD_SHIFT_L3_64K) > > > +#define PMD_MASK_L3_64K (~(PMD_SIZE_L3_64K-1)) > > > > > > /* > > > * 2-levels / 64K pages > > > @@ -2868,9 +2881,10 @@ typedef signed int s32; > > > #define KSYMS_START (0x1) > > > #define PHYS_OFFSET (0x2) > > > #define VM_L2_64K (0x4) > > > -#define VM_L3_4K (0x8) > > > -#define KDUMP_ENABLED (0x10) > > > -#define IRQ_STACKS (0x20) > > > +#define VM_L3_64K (0x8) > > > +#define VM_L3_4K (0x10) > > > +#define KDUMP_ENABLED (0x20) > > > +#define IRQ_STACKS (0x40) > > > > > > /* > > > * sources: Documentation/arm64/memory.txt > > > -- > > > 2.1.4 > > > > > > -- > > > Crash-utility mailing list > > > Crash-utility redhat com > > > https://www.redhat.com/mailman/listinfo/crash-utility > > >

On Mon, 2016-06-13 at 11:30 -0400, Dave Anderson wrote: > > ----- Original Message ----- > > Dave, > > > > On Fri, Jun 10, 2016 at 04:37:42PM -0400, Dave Anderson wrote: > > > Hi Takahiro, > > > > > > To address my concerns about your patch, I added a few additional changes and attached > > > it to this email. The changes are: > > > > > > (1) Prevent the stack dump "below" the #0 level. Yes, the stack data region is contained within > > > the incoming frame parameters, but it's ugly and we really don't care to see what's before > > > the #0 crash_kexec and crash_save_cpu #0 frames. > > > (2) Fill in the missing stack dump at the top of the process stack, up to, but not including > > > the user-space exception frame. > > > (3) Instead of showing the fp of 0 in the top-most frame's stack address, fill it in with the > > > address of the user-space exception frame. > > > > > > Note that there is no dump of the stack containing the user-space exception frame, but the > > > register dump itself should suffice. > > > > Well, the essential problem with my patch is that the output from "bt -f" > > looks like: > > #XX ['fp'] 'function' at 'pc' --- (1) > > <function's stack dump> --- (2) > > but that (1) and (2) are not printed as a single stack frame in the same > > iteration of while loop in arm64_back_trace_cmd(). > > (I hope you understand what I mean :) > > Actually I prefer your first approach. I find this new one confusing, not > to mention unlike any of the other architectures in that the "frame level" > #X address value is not contiguous with the stack addresses that get filled > in by -f. > > Taking your picture into account: > > stack grows to lower addresses. > /|\ > | > | | > new sp +------+ <--- > |dyn | | > | vars | | > new fp +- - - + | > |old fp| | a function's stack frame > |old lr| | > |static| | > | vars| | > old sp +------+ <--- > |dyn | > | vars | > old fp +------+ > | | > > Your first patch seemed natural to me because for any "#X" line containing a function > name, that function's dynamic variables, the "old fp/old lr" pair, and the function's > static variables were dumped below it (i.e., at higher stack addresses). > > > > To be consistent with the out format of x86, the output should be > > <function's stack dump> > > #XX ['fp'] 'function' at 'pc' > > > > Unfortunately, this requires that arm64_back_trace_cmd() and other functions should be overhauled. > > Please take a look at my next patch though it is uncompleted and still has room for improvement. > > I don't know what you mean by "consistent with the out format of x86"? With x86_64, > each #<level> line is simply the stack address where the function pushed its return > address as a result of its making a "callq" to the next function. Any local variables of > the calling function would be at the next higher stack addresses: > I've been confused by the address in []'s on arm64. Is this supposed to be the stack address where the return address is stored, or does it vary by arch?

On x86_64 (crash-7.1.4-1.el6_6): crash> bt | grep " vfs_read at " #5 [ffff89b6e510ff08] vfs_read at ffffffff811dea1c crash> rd ffff89b6e510ff08 ffff89b6e510ff08: ffffffff811dea1c ........

On arm64 (crash-7.1.5-1.el7.aarch64) this isn't the case: crash> bt | grep " vfs_read at " #7 [ffff80015b93fdb0] vfs_read at ffff800000236b0c crash> rd ffff80015b93fdb0 ffff80015b93fdb0: ffff80015c92e100 ...\....

> ... > #X [stack address] function2 at 'return address' > <function2's local variables> > #Y [stack address] function1 at 'return address' > <functions1's local variables> > ... > > So for digging out local stack variables associated with a function, it's a simple > matter of looking "below" it in the "bt -f" output. > > Dave > > > > Thanks, > > -Takahiro AKASHI > > > > > > > If you can live with the display, I'll clean up the patch, and maybe add > > > the stack-layout diagram > > > from your last post into a comment. It was quite helpful, especially in > > > comparison to the > > > x86_64 model, which is what I was mistakenly using as a guide. > > > > > > Thanks, > > > Dave > > > > > > > > > > > > > > diff --git a/arm64.c b/arm64.c > > > index 86ec348..3b29ef4 100644 > > > --- a/arm64.c > > > +++ b/arm64.c > > > @@ -1407,13 +1407,14 @@ arm64_print_stackframe_entry(struct bt_info *bt, > > > int level, struct arm64_stackfr > > > value_to_symstr(frame->pc, buf, > > > bt->radix); > > > } > > > > > > - if (bt->flags & BT_FULL) { > > > - arm64_display_full_frame(bt, frame->sp); > > > - bt->frameptr = frame->sp; > > > + if ((bt->flags & BT_FULL) && level) { > > > + arm64_display_full_frame(bt, frame->fp); > > > + bt->frameptr = frame->fp; > > > } > > > > > > fprintf(ofp, "%s#%d [%8lx] %s at %lx", level < 10 ? " " : "", > > > level, > > > - frame->sp, name_plus_offset ? name_plus_offset : name, > > > frame->pc); > > > +// frame->fp, name_plus_offset ? name_plus_offset : name, > > > frame->pc); > > > + frame->fp ? frame->fp : bt->stacktop - USER_EFRAME_OFFSET, > > > name_plus_offset ? name_plus_offset : name, frame->pc); > > > > > > if (BT_REFERENCE_CHECK(bt)) > > > arm64_do_bt_reference_check(bt, frame->pc, name); > > > @@ -1447,8 +1448,12 @@ arm64_display_full_frame(struct bt_info *bt, ulong > > > sp) > > > if (bt->frameptr == sp) > > > return; > > > > > > - if (!INSTACK(sp, bt) || !INSTACK(bt->frameptr, bt)) > > > - return; > > > + if (!INSTACK(sp, bt) || !INSTACK(bt->frameptr, bt)) { > > > + if (sp == 0) > > > + sp = bt->stacktop - USER_EFRAME_OFFSET; > > > + else > > > + return; > > > + } > > > > > > words = (sp - bt->frameptr) / sizeof(ulong); > > > > > > @@ -1471,12 +1476,10 @@ arm64_unwind_frame(struct bt_info *bt, struct > > > arm64_stackframe *frame) > > > { > > > unsigned long high, low, fp; > > > unsigned long stack_mask; > > > - unsigned long irq_stack_ptr, orig_sp, sp_in; > > > + unsigned long irq_stack_ptr, orig_sp; > > > struct arm64_pt_regs *ptregs; > > > struct machine_specific *ms; > > > > > > - sp_in = frame->sp; > > > - > > > stack_mask = (unsigned long)(ARM64_STACK_SIZE) - 1; > > > fp = frame->fp; > > > > > > @@ -1513,7 +1516,7 @@ arm64_unwind_frame(struct bt_info *bt, struct > > > arm64_stackframe *frame) > > > ptregs = (struct arm64_pt_regs > > > *)&bt->stackbuf[(ulong)(STACK_OFFSET_TYPE(orig_sp))]; > > > frame->sp = orig_sp; > > > frame->pc = ptregs->pc; > > > - bt->bptr = sp_in; > > > + bt->bptr = fp; > > > if (CRASHDEBUG(1)) > > > error(INFO, > > > "arm64_unwind_frame: switch stacks: fp: %lx sp: %lx pc: %lx\n", > > > @@ -1904,8 +1907,10 @@ arm64_print_exception_frame(struct bt_info *bt, > > > ulong pt_regs, int mode, FILE *o > > > ulong LR, SP, offset; > > > char buf[BUFSIZE]; > > > > > > +#if 0 /* FIXME? */ > > > if (bt->flags & BT_FULL) > > > arm64_display_full_frame(bt, pt_regs); > > > +#endif > > > > > > if (CRASHDEBUG(1)) > > > fprintf(ofp, "pt_regs: %lx\n", pt_regs); > > > > > -- > > > Crash-utility mailing list > > > Crash-utility(a)redhat.com > > > https://www.redhat.com/mailman/listinfo/crash-utility > > > > -- > > Crash-utility mailing list > > Crash-utility(a)redhat.com > > https://www.redhat.com/mailman/listinfo/crash-utility > > > > -- > Crash-utility mailing list > Crash-utility(a)redhat.com > https://www.redhat.com/mailman/listinfo/crash-utility -- Crash-utility mailing list Crash-utility(a)redhat.com https://www.redhat.com/mailman/listinfo/crash-utility