From 4a1f8b44fb2fa6eebf6552d80cc4706d037d9bd3 Mon Sep 17 00:00:00 2001 From: CentOS Sources Date: Tue, 8 Nov 2022 01:43:27 -0500 Subject: [PATCH] import crash-7.3.2-2.el8 --- .crash.metadata | 2 +- .gitignore | 2 +- ...-pvops-Xen-detection-for-arm-machine.patch | 70 ---- ...1-arm64-Support-overflow-stack-panic.patch | 379 ----------------- ...001-ppc64-update-the-NR_CPUS-to-8192.patch | 31 ++ ...x-member-changes-for-kernels-5.16-rc.patch | 101 ----- ...age-of-compatibility-of-struct-symbo.patch | 41 -- ...struct-and-member-validation-in-sbit.patch | 62 +++ ...option-to-display-all-the-per-CPU-cl.patch | 59 --- ...alid-offset-for-sbitmap_queue_alloc_.patch | 118 ++++++ ...ion-to-display-the-stack-end-address.patch | 69 --- ...alid-offset-for-sbitmap_queue_round_.patch | 103 +++++ ...-calculation-on-Linux-5.14-and-later.patch | 35 -- ...alid-offset-for-sbitmap_word_depth-o.patch | 101 +++++ ...ruct-slab-changes-on-Linux-5.17-rc1-.patch | 40 -- ...ialization-of-boot_date-to-task_init.patch | 75 ---- ...bt-x86_64-filter-out-idle-task-stack.patch | 205 +++++++++ ...mand-from-ps-t-option-to-reduce-memo.patch | 79 ---- ...8-bt-arm64-add-support-for-bt-n-idle.patch | 96 +++++ ...erformance-for-vmcores-with-large-nu.patch | 150 ------- ...-D-options-to-support-blk-mq-sbitmap.patch | 392 ++++++++++++++++++ ...ault-by-bt-command-with-offline-cpus.patch | 59 --- ...options-to-support-blk-mq-change-on-.patch | 121 ++++++ ...mem-s-S-and-bt-F-F-on-Linux-5.17-rc1.patch | 89 ---- ...age-for-the-bpf-and-sbitmapq-command.patch | 43 ++ ...-sbitmap_queue-without-ws_active-mem.patch | 48 +++ ...-sbitmap_word-without-cleared-member.patch | 110 +++++ ...-sbitmap_queue-without-min_shallow_d.patch | 49 +++ ...ions-parse-sbitmap-on-Linux-4.18-and.patch | 84 ++++ ...-kernels-without-struct-wait_queue_h.patch | 44 ++ ...-Limit-kernels-without-sbitmap-again.patch | 43 ++ SOURCES/lzo_snappy_zstd.patch | 13 +- SOURCES/rhel8_build.patch | 15 +- SOURCES/rhel8_freepointer.patch | 21 +- SPECS/crash.spec | 46 +- 35 files changed, 1700 insertions(+), 1295 deletions(-) delete mode 100644 SOURCES/0001-Fix-pvops-Xen-detection-for-arm-machine.patch delete mode 100644 SOURCES/0001-arm64-Support-overflow-stack-panic.patch create mode 100644 SOURCES/0001-ppc64-update-the-NR_CPUS-to-8192.patch delete mode 100644 SOURCES/0002-Handle-blk_mq_ctx-member-changes-for-kernels-5.16-rc.patch delete mode 100644 SOURCES/0002-defs.h-fix-breakage-of-compatibility-of-struct-symbo.patch create mode 100644 SOURCES/0002-sbitmapq-remove-struct-and-member-validation-in-sbit.patch delete mode 100644 SOURCES/0003-Fix-for-timer-r-option-to-display-all-the-per-CPU-cl.patch create mode 100644 SOURCES/0003-sbitmapq-fix-invalid-offset-for-sbitmap_queue_alloc_.patch delete mode 100644 SOURCES/0004-Fix-for-bt-v-option-to-display-the-stack-end-address.patch create mode 100644 SOURCES/0004-sbitmapq-fix-invalid-offset-for-sbitmap_queue_round_.patch delete mode 100644 SOURCES/0005-Fix-for-HZ-calculation-on-Linux-5.14-and-later.patch create mode 100644 SOURCES/0005-sbitmapq-fix-invalid-offset-for-sbitmap_word_depth-o.patch delete mode 100644 SOURCES/0006-memory-Handle-struct-slab-changes-on-Linux-5.17-rc1-.patch delete mode 100644 SOURCES/0007-Move-the-initialization-of-boot_date-to-task_init.patch create mode 100644 SOURCES/0007-bt-x86_64-filter-out-idle-task-stack.patch delete mode 100644 SOURCES/0008-Remove-ptype-command-from-ps-t-option-to-reduce-memo.patch create mode 100644 SOURCES/0008-bt-arm64-add-support-for-bt-n-idle.patch delete mode 100644 SOURCES/0009-Improve-the-ps-performance-for-vmcores-with-large-nu.patch create mode 100644 SOURCES/0010-Enhance-dev-d-D-options-to-support-blk-mq-sbitmap.patch delete mode 100644 SOURCES/0010-arm64-Fix-segfault-by-bt-command-with-offline-cpus.patch create mode 100644 SOURCES/0011-Fix-for-dev-d-D-options-to-support-blk-mq-change-on-.patch delete mode 100644 SOURCES/0011-Fix-for-kmem-s-S-and-bt-F-F-on-Linux-5.17-rc1.patch create mode 100644 SOURCES/0012-Doc-update-man-page-for-the-bpf-and-sbitmapq-command.patch create mode 100644 SOURCES/0013-sbitmapq-Fix-for-sbitmap_queue-without-ws_active-mem.patch create mode 100644 SOURCES/0014-sbitmapq-Fix-for-sbitmap_word-without-cleared-member.patch create mode 100644 SOURCES/0015-sbitmapq-Fix-for-sbitmap_queue-without-min_shallow_d.patch create mode 100644 SOURCES/0016-Make-dev-d-D-options-parse-sbitmap-on-Linux-4.18-and.patch create mode 100644 SOURCES/0017-sbitmapq-Fix-for-kernels-without-struct-wait_queue_h.patch create mode 100644 SOURCES/0018-sbitmapq-Limit-kernels-without-sbitmap-again.patch diff --git a/.crash.metadata b/.crash.metadata index 7381cdc..b1f49a7 100644 --- a/.crash.metadata +++ b/.crash.metadata @@ -1,2 +1,2 @@ -f230368e17058e61a0be4c22f0969bed76cd6c29 SOURCES/crash-7.3.1.tar.gz +aab889c6471bfc42cf2b1d065a881ea33d8ba0b7 SOURCES/crash-7.3.2.tar.gz 026f4c9e1c8152a2773354551c523acd32d7f00e SOURCES/gdb-7.6.tar.gz diff --git a/.gitignore b/.gitignore index d19e76b..3a8ba5a 100644 --- a/.gitignore +++ b/.gitignore @@ -1,2 +1,2 @@ -SOURCES/crash-7.3.1.tar.gz +SOURCES/crash-7.3.2.tar.gz SOURCES/gdb-7.6.tar.gz diff --git a/SOURCES/0001-Fix-pvops-Xen-detection-for-arm-machine.patch b/SOURCES/0001-Fix-pvops-Xen-detection-for-arm-machine.patch deleted file mode 100644 index 7b6b236..0000000 --- a/SOURCES/0001-Fix-pvops-Xen-detection-for-arm-machine.patch +++ /dev/null @@ -1,70 +0,0 @@ -From 5c4f786450ea61b87d4db0092288df83dd5cb454 Mon Sep 17 00:00:00 2001 -From: Qi Zheng -Date: Tue, 21 Dec 2021 15:40:31 +0800 -Subject: [PATCH 01/11] Fix pvops Xen detection for arm machine - -Since the xen_start_info on the arm/arm64 platform points to a static -variable '_xen_start_info'(see its definition as below), which makes -that the address of xen_start_info will never be null. - -arch/arm/xen/enlighten.c:40:static struct start_info _xen_start_info; -arch/arm/xen/enlighten.c:41:struct start_info *xen_start_info = &_xen_start_info; -arch/arm/xen/enlighten.c:42:EXPORT_SYMBOL(xen_start_info); - -As a result, the is_pvops_xen() in commit 4badc6229c69 ("Fix pvops -Xen detection for kernels >= v4.20") always returns TRUE because it -can always read out the non-null address of xen_start_info, finally -the following error will be reported on arm/arm64 platform(non-Xen -environment) because p2m_mid_missing and xen_p2m_addr are not defined: - - crash: cannot resolve "p2m_top" - -For the arm/arm64 platform, fix it by using xen_vcpu_info instead of -xen_start_info to detect Xen dumps. - -In addition, also explicitly narrow the scope of the xen_start_info -check to x86 with the machine_type(), there is no need to check it on -other architectures. - -Fixes: 4badc6229c69 ("Fix pvops Xen detection for kernels >= v4.20") -Signed-off-by: Qi Zheng -Acked-by: Kazuhito Hagio -Signed-off-by: Lianbo Jiang ---- - kernel.c | 20 +++++++++++++++----- - 1 file changed, 15 insertions(+), 5 deletions(-) - -diff --git a/kernel.c b/kernel.c -index 8ae9e0c169ff..a637dd0eb8f8 100644 ---- a/kernel.c -+++ b/kernel.c -@@ -10754,11 +10754,21 @@ is_pvops_xen(void) - STREQ(sym, "paravirt_patch_default"))) - return TRUE; - -- if (symbol_exists("xen_start_info") && -- readmem(symbol_value("xen_start_info"), KVADDR, &addr, -- sizeof(void *), "xen_start_info", RETURN_ON_ERROR) && -- addr != 0) -- return TRUE; -+ if (machine_type("X86") || machine_type("X86_64")) { -+ if (symbol_exists("xen_start_info") && -+ readmem(symbol_value("xen_start_info"), KVADDR, &addr, -+ sizeof(void *), "xen_start_info", RETURN_ON_ERROR) && -+ addr != 0) -+ return TRUE; -+ } -+ -+ if (machine_type("ARM") || machine_type("ARM64")) { -+ if (symbol_exists("xen_vcpu_info") && -+ readmem(symbol_value("xen_vcpu_info"), KVADDR, &addr, -+ sizeof(void *), "xen_vcpu_info", RETURN_ON_ERROR) && -+ addr != 0) -+ return TRUE; -+ } - - return FALSE; - } --- -2.20.1 - diff --git a/SOURCES/0001-arm64-Support-overflow-stack-panic.patch b/SOURCES/0001-arm64-Support-overflow-stack-panic.patch deleted file mode 100644 index e8cb3ac..0000000 --- a/SOURCES/0001-arm64-Support-overflow-stack-panic.patch +++ /dev/null @@ -1,379 +0,0 @@ -From c05db8d7d83389a342664073547bd29eda900158 Mon Sep 17 00:00:00 2001 -From: Hong YANG -Date: Mon, 15 Nov 2021 15:41:01 +0800 -Subject: [PATCH 1/2] arm64: Support overflow stack panic - -Kernel commit <872d8327ce89> ("arm64: add VMAP_STACK overflow detection") -has supported the overflow stack exception handling. Without the patch, the -"bt" command will make crash generate a core dump because of segmentation -fault. With the patch, the "bt" command can display the overflow stack. - -Before: -crash> bt -PID: 3607 TASK: ffffffcbf9a4da00 CPU: 2 COMMAND: "sh" -Segmentation fault (core dumped) - -After: -crash> bt -PID: 3607 TASK: ffffffcbf9a4da00 CPU: 2 COMMAND: "sh" - #0 [ffffffccbfd85f50] __delay at ffffff8008ceded8 -... - #5 [ffffffccbfd85fd0] emergency_restart at ffffff80080d49fc - #6 [ffffffccbfd86140] panic at ffffff80080af4c0 - #7 [ffffffccbfd86150] nmi_panic at ffffff80080af150 - #8 [ffffffccbfd86190] handle_bad_stack at ffffff800808b0b8 - #9 [ffffffccbfd862d0] __bad_stack at ffffff800808285c - PC: ffffff8008082e80 [el1_sync] - LR: ffffff8000d6c214 [stack_overflow_demo+84] - SP: ffffff1a79930070 PSTATE: 204003c5 - X29: ffffff8011b03d00 X28: ffffffcbf9a4da00 X27: ffffff8008e02000 - X26: 0000000000000040 X25: 0000000000000124 X24: ffffffcbf9a4da00 - X23: 0000007daec2e288 X22: ffffffcbfe03b800 X21: 0000007daec2e288 - X20: 0000000000000002 X19: 0000000000000002 X18: 0000000000000002 - X17: 00000000000003e7 X16: 0000000000000000 X15: 0000000000000000 - X14: ffffffcc17facb00 X13: ffffffccb4c25c00 X12: 0000000000000000 - X11: ffffffcc17fad660 X10: 0000000000000af0 X9: 0000000000000000 - X8: ffffff1a799334f0 X7: 0000000000000000 X6: 000000000000003f - X5: 0000000000000040 X4: 0000000000000010 X3: 00000065981d07f0 - X2: 00000065981d07f0 X1: 0000000000000000 X0: ffffff1a799334f0 - -Signed-off-by: Hong YANG ---- - arm64.c | 169 ++++++++++++++++++++++++++++++++++++++++++++++++++------ - defs.h | 6 ++ - 2 files changed, 159 insertions(+), 16 deletions(-) - -diff --git a/arm64.c b/arm64.c -index 94681d1a37db..23c3d75d85aa 100644 ---- a/arm64.c -+++ b/arm64.c -@@ -45,6 +45,7 @@ static int arm64_vtop_3level_4k(ulong, ulong, physaddr_t *, int); - static int arm64_vtop_4level_4k(ulong, ulong, physaddr_t *, int); - static ulong arm64_get_task_pgd(ulong); - static void arm64_irq_stack_init(void); -+static void arm64_overflow_stack_init(void); - static void arm64_stackframe_init(void); - static int arm64_eframe_search(struct bt_info *); - static int arm64_is_kernel_exception_frame(struct bt_info *, ulong); -@@ -63,6 +64,7 @@ static int arm64_get_dumpfile_stackframe(struct bt_info *, struct arm64_stackfra - static int arm64_in_kdump_text(struct bt_info *, struct arm64_stackframe *); - static int arm64_in_kdump_text_on_irq_stack(struct bt_info *); - static int arm64_switch_stack(struct bt_info *, struct arm64_stackframe *, FILE *); -+static int arm64_switch_stack_from_overflow(struct bt_info *, struct arm64_stackframe *, FILE *); - static int arm64_get_stackframe(struct bt_info *, struct arm64_stackframe *); - static void arm64_get_stack_frame(struct bt_info *, ulong *, ulong *); - static void arm64_gen_hidden_frame(struct bt_info *bt, ulong, struct arm64_stackframe *); -@@ -78,8 +80,11 @@ static int arm64_get_smp_cpus(void); - static void arm64_clear_machdep_cache(void); - static int arm64_on_process_stack(struct bt_info *, ulong); - static int arm64_in_alternate_stack(int, ulong); -+static int arm64_in_alternate_stackv(int cpu, ulong stkptr, ulong *stacks, ulong stack_size); - static int arm64_on_irq_stack(int, ulong); -+static int arm64_on_overflow_stack(int, ulong); - static void arm64_set_irq_stack(struct bt_info *); -+static void arm64_set_overflow_stack(struct bt_info *); - static void arm64_set_process_stack(struct bt_info *); - static int arm64_get_kvaddr_ranges(struct vaddr_range *); - static void arm64_get_crash_notes(void); -@@ -463,6 +468,7 @@ arm64_init(int when) - machdep->hz = 100; - - arm64_irq_stack_init(); -+ arm64_overflow_stack_init(); - arm64_stackframe_init(); - break; - -@@ -1715,6 +1721,49 @@ arm64_irq_stack_init(void) - } - } - -+/* -+ * Gather Overflow stack values. -+ * -+ * Overflow stack supported since 4.14, in commit 872d8327c -+ */ -+static void -+arm64_overflow_stack_init(void) -+{ -+ int i; -+ struct syment *sp; -+ struct gnu_request request, *req; -+ struct machine_specific *ms = machdep->machspec; -+ req = &request; -+ -+ if (symbol_exists("overflow_stack") && -+ (sp = per_cpu_symbol_search("overflow_stack")) && -+ get_symbol_type("overflow_stack", NULL, req)) { -+ if (CRASHDEBUG(1)) { -+ fprintf(fp, "overflow_stack: \n"); -+ fprintf(fp, " type: %x, %s\n", -+ (int)req->typecode, -+ (req->typecode == TYPE_CODE_ARRAY) ? -+ "TYPE_CODE_ARRAY" : "other"); -+ fprintf(fp, " target_typecode: %x, %s\n", -+ (int)req->target_typecode, -+ req->target_typecode == TYPE_CODE_INT ? -+ "TYPE_CODE_INT" : "other"); -+ fprintf(fp, " target_length: %ld\n", -+ req->target_length); -+ fprintf(fp, " length: %ld\n", req->length); -+ } -+ -+ if (!(ms->overflow_stacks = (ulong *)malloc((size_t)(kt->cpus * sizeof(ulong))))) -+ error(FATAL, "cannot malloc overflow_stack addresses\n"); -+ -+ ms->overflow_stack_size = ARM64_OVERFLOW_STACK_SIZE; -+ machdep->flags |= OVERFLOW_STACKS; -+ -+ for (i = 0; i < kt->cpus; i++) -+ ms->overflow_stacks[i] = kt->__per_cpu_offset[i] + sp->value; -+ } -+} -+ - /* - * Gather and verify all of the backtrace requirements. - */ -@@ -1960,6 +2009,7 @@ static char *arm64_exception_functions[] = { - "do_mem_abort", - "do_el0_irq_bp_hardening", - "do_sp_pc_abort", -+ "handle_bad_stack", - NULL - }; - -@@ -1978,7 +2028,10 @@ arm64_in_exception_text(ulong ptr) - if ((ptr >= ms->__exception_text_start) && - (ptr < ms->__exception_text_end)) - return TRUE; -- } else if ((name = closest_symbol(ptr))) { /* Linux 5.5 and later */ -+ } -+ -+ name = closest_symbol(ptr); -+ if (name != NULL) { /* Linux 5.5 and later */ - for (func = &arm64_exception_functions[0]; *func; func++) { - if (STREQ(name, *func)) - return TRUE; -@@ -2252,15 +2305,14 @@ arm64_unwind_frame(struct bt_info *bt, struct arm64_stackframe *frame) - if ((frame->fp == 0) && (frame->pc == 0)) - return FALSE; - -- if (!(machdep->flags & IRQ_STACKS)) -- return TRUE; -- -- if (!(machdep->flags & IRQ_STACKS)) -+ if (!(machdep->flags & (IRQ_STACKS | OVERFLOW_STACKS))) - return TRUE; - - if (machdep->flags & UNW_4_14) { -- if ((bt->flags & BT_IRQSTACK) && -- !arm64_on_irq_stack(bt->tc->processor, frame->fp)) { -+ if (((bt->flags & BT_IRQSTACK) && -+ !arm64_on_irq_stack(bt->tc->processor, frame->fp)) || -+ ((bt->flags & BT_OVERFLOW_STACK) && -+ !arm64_on_overflow_stack(bt->tc->processor, frame->fp))) { - if (arm64_on_process_stack(bt, frame->fp)) { - arm64_set_process_stack(bt); - -@@ -2677,6 +2729,9 @@ arm64_back_trace_cmd(struct bt_info *bt) - if (arm64_on_irq_stack(bt->tc->processor, bt->frameptr)) { - arm64_set_irq_stack(bt); - bt->flags |= BT_IRQSTACK; -+ } else if (arm64_on_overflow_stack(bt->tc->processor, bt->frameptr)) { -+ arm64_set_overflow_stack(bt); -+ bt->flags |= BT_OVERFLOW_STACK; - } - stackframe.sp = bt->stkptr; - stackframe.pc = bt->instptr; -@@ -2731,7 +2786,9 @@ arm64_back_trace_cmd(struct bt_info *bt) - break; - - if (arm64_in_exception_text(bt->instptr) && INSTACK(stackframe.fp, bt)) { -- if (!(bt->flags & BT_IRQSTACK) || -+ if (bt->flags & BT_OVERFLOW_STACK) { -+ exception_frame = stackframe.fp - KERN_EFRAME_OFFSET; -+ } else if (!(bt->flags & BT_IRQSTACK) || - ((stackframe.sp + SIZE(pt_regs)) < bt->stacktop)) { - if (arm64_is_kernel_exception_frame(bt, stackframe.fp - KERN_EFRAME_OFFSET)) - exception_frame = stackframe.fp - KERN_EFRAME_OFFSET; -@@ -2745,6 +2802,12 @@ arm64_back_trace_cmd(struct bt_info *bt) - break; - } - -+ if ((bt->flags & BT_OVERFLOW_STACK) && -+ !arm64_on_overflow_stack(bt->tc->processor, stackframe.fp)) { -+ bt->flags &= ~BT_OVERFLOW_STACK; -+ if (arm64_switch_stack_from_overflow(bt, &stackframe, ofp) == USER_MODE) -+ break; -+ } - - level++; - } -@@ -3131,6 +3194,43 @@ arm64_switch_stack(struct bt_info *bt, struct arm64_stackframe *frame, FILE *ofp - return KERNEL_MODE; - } - -+static int -+arm64_switch_stack_from_overflow(struct bt_info *bt, struct arm64_stackframe *frame, FILE *ofp) -+{ -+ int i; -+ ulong stacktop, words, addr; -+ ulong *stackbuf; -+ char buf[BUFSIZE]; -+ struct machine_specific *ms = machdep->machspec; -+ -+ if (bt->flags & BT_FULL) { -+ stacktop = ms->overflow_stacks[bt->tc->processor] + ms->overflow_stack_size; -+ words = (stacktop - bt->bptr) / sizeof(ulong); -+ stackbuf = (ulong *)GETBUF(words * sizeof(ulong)); -+ readmem(bt->bptr, KVADDR, stackbuf, words * sizeof(long), -+ "top of overflow stack", FAULT_ON_ERROR); -+ -+ addr = bt->bptr; -+ for (i = 0; i < words; i++) { -+ if (!(i & 1)) -+ fprintf(ofp, "%s %lx: ", i ? "\n" : "", addr); -+ fprintf(ofp, "%s ", format_stack_entry(bt, buf, stackbuf[i], 0)); -+ addr += sizeof(ulong); -+ } -+ fprintf(ofp, "\n"); -+ FREEBUF(stackbuf); -+ } -+ fprintf(ofp, "--- ---\n"); -+ -+ if (frame->fp == 0) -+ return USER_MODE; -+ -+ if (!(machdep->flags & UNW_4_14)) -+ arm64_print_exception_frame(bt, frame->sp, KERNEL_MODE, ofp); -+ -+ return KERNEL_MODE; -+} -+ - static int - arm64_get_dumpfile_stackframe(struct bt_info *bt, struct arm64_stackframe *frame) - { -@@ -3682,6 +3782,16 @@ arm64_display_machine_stats(void) - machdep->machspec->irq_stacks[i]); - } - } -+ if (machdep->machspec->overflow_stack_size) { -+ fprintf(fp, "OVERFLOW STACK SIZE: %ld\n", -+ machdep->machspec->overflow_stack_size); -+ fprintf(fp, " OVERFLOW STACKS:\n"); -+ for (i = 0; i < kt->cpus; i++) { -+ pad = (i < 10) ? 3 : (i < 100) ? 2 : (i < 1000) ? 1 : 0; -+ fprintf(fp, "%s CPU %d: %lx\n", space(pad), i, -+ machdep->machspec->overflow_stacks[i]); -+ } -+ } - } - - static int -@@ -3875,24 +3985,41 @@ arm64_on_process_stack(struct bt_info *bt, ulong stkptr) - } - - static int --arm64_on_irq_stack(int cpu, ulong stkptr) -+arm64_in_alternate_stackv(int cpu, ulong stkptr, ulong *stacks, ulong stack_size) - { -- return arm64_in_alternate_stack(cpu, stkptr); -+ if ((cpu >= kt->cpus) || (stacks == NULL) || !stack_size) -+ return FALSE; -+ -+ if ((stkptr >= stacks[cpu]) && -+ (stkptr < (stacks[cpu] + stack_size))) -+ return TRUE; -+ -+ return FALSE; - } - - static int - arm64_in_alternate_stack(int cpu, ulong stkptr) -+{ -+ return (arm64_on_irq_stack(cpu, stkptr) || -+ arm64_on_overflow_stack(cpu, stkptr)); -+} -+ -+static int -+arm64_on_irq_stack(int cpu, ulong stkptr) - { - struct machine_specific *ms = machdep->machspec; - -- if (!ms->irq_stack_size || (cpu >= kt->cpus)) -- return FALSE; -+ return arm64_in_alternate_stackv(cpu, stkptr, -+ ms->irq_stacks, ms->irq_stack_size); -+} - -- if ((stkptr >= ms->irq_stacks[cpu]) && -- (stkptr < (ms->irq_stacks[cpu] + ms->irq_stack_size))) -- return TRUE; -+static int -+arm64_on_overflow_stack(int cpu, ulong stkptr) -+{ -+ struct machine_specific *ms = machdep->machspec; - -- return FALSE; -+ return arm64_in_alternate_stackv(cpu, stkptr, -+ ms->overflow_stacks, ms->overflow_stack_size); - } - - static void -@@ -3905,6 +4032,16 @@ arm64_set_irq_stack(struct bt_info *bt) - alter_stackbuf(bt); - } - -+static void -+arm64_set_overflow_stack(struct bt_info *bt) -+{ -+ struct machine_specific *ms = machdep->machspec; -+ -+ bt->stackbase = ms->overflow_stacks[bt->tc->processor]; -+ bt->stacktop = bt->stackbase + ms->overflow_stack_size; -+ alter_stackbuf(bt); -+} -+ - static void - arm64_set_process_stack(struct bt_info *bt) - { -diff --git a/defs.h b/defs.h -index 43eff46b105d..caaa11e50c87 100644 ---- a/defs.h -+++ b/defs.h -@@ -3218,6 +3218,7 @@ typedef signed int s32; - #define UNW_4_14 (0x200) - #define FLIPPED_VM (0x400) - #define HAS_PHYSVIRT_OFFSET (0x800) -+#define OVERFLOW_STACKS (0x1000) - - /* - * Get kimage_voffset from /dev/crash -@@ -3260,6 +3261,7 @@ typedef signed int s32; - - #define ARM64_STACK_SIZE (16384) - #define ARM64_IRQ_STACK_SIZE ARM64_STACK_SIZE -+#define ARM64_OVERFLOW_STACK_SIZE (4096) - - #define _SECTION_SIZE_BITS 30 - #define _SECTION_SIZE_BITS_5_12 27 -@@ -3332,6 +3334,9 @@ struct machine_specific { - char *irq_stackbuf; - ulong __irqentry_text_start; - ulong __irqentry_text_end; -+ ulong overflow_stack_size; -+ ulong *overflow_stacks; -+ char *overflow_stackbuf; - /* for exception vector code */ - ulong exp_entry1_start; - ulong exp_entry1_end; -@@ -5778,6 +5783,7 @@ ulong cpu_map_addr(const char *type); - #define BT_CPUMASK (0x1000000000000ULL) - #define BT_SHOW_ALL_REGS (0x2000000000000ULL) - #define BT_REGS_NOT_FOUND (0x4000000000000ULL) -+#define BT_OVERFLOW_STACK (0x8000000000000ULL) - #define BT_SYMBOL_OFFSET (BT_SYMBOLIC_ARGS) - - #define BT_REF_HEXVAL (0x1) --- -2.30.2 - diff --git a/SOURCES/0001-ppc64-update-the-NR_CPUS-to-8192.patch b/SOURCES/0001-ppc64-update-the-NR_CPUS-to-8192.patch new file mode 100644 index 0000000..c5608f6 --- /dev/null +++ b/SOURCES/0001-ppc64-update-the-NR_CPUS-to-8192.patch @@ -0,0 +1,31 @@ +From ae52398a13fa9a238279114ed671c7c514c154ee Mon Sep 17 00:00:00 2001 +From: Sourabh Jain +Date: Mon, 9 May 2022 12:49:56 +0530 +Subject: [PATCH 01/18] ppc64: update the NR_CPUS to 8192 + +Since the kernel commit 2d8ae638bb86 ("powerpc: Make the NR_CPUS max 8192") +the NR_CPUS on Linux kernel ranges from 1-8192. So let's match NR_CPUS with +the max NR_CPUS count on the Linux kernel. + +Signed-off-by: Sourabh Jain +Signed-off-by: Lianbo Jiang +--- + defs.h | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/defs.h b/defs.h +index 1e8360d65a3b..a6735d07b32f 100644 +--- a/defs.h ++++ b/defs.h +@@ -136,7 +136,7 @@ + #define NR_CPUS (4096) + #endif + #ifdef PPC64 +-#define NR_CPUS (2048) ++#define NR_CPUS (8192) + #endif + #ifdef S390 + #define NR_CPUS (512) +-- +2.30.2 + diff --git a/SOURCES/0002-Handle-blk_mq_ctx-member-changes-for-kernels-5.16-rc.patch b/SOURCES/0002-Handle-blk_mq_ctx-member-changes-for-kernels-5.16-rc.patch deleted file mode 100644 index b9091cc..0000000 --- a/SOURCES/0002-Handle-blk_mq_ctx-member-changes-for-kernels-5.16-rc.patch +++ /dev/null @@ -1,101 +0,0 @@ -From 78255e3b33f8d51eb893e662dd1b05a008246b9d Mon Sep 17 00:00:00 2001 -From: Lianbo Jiang -Date: Fri, 24 Dec 2021 18:56:35 +0800 -Subject: [PATCH 02/11] Handle blk_mq_ctx member changes for kernels 5.16-rc1 - and later - -Kernel commit 9a14d6ce4135 ("block: remove debugfs blk_mq_ctx -dispatched/merged/completed attributes") removed the member -rq_dispatched and rq_completed from struct blk_mq_ctx. Without -the patch, "dev -d|-D" options will fail with the following error: - -crash> dev -d -MAJOR GENDISK NAME REQUEST_QUEUE TOTAL ASYNC SYNC - -dev: invalid structure member offset: blk_mq_ctx_rq_dispatched - FILE: dev.c LINE: 4229 FUNCTION: get_one_mctx_diskio() - -Signed-off-by: Lianbo Jiang -Signed-off-by: Kazuhito Hagio ---- - dev.c | 57 +++++++++++++++++++++++++++++++++++++++------------------ - 1 file changed, 39 insertions(+), 18 deletions(-) - -diff --git a/dev.c b/dev.c -index effe789f38d8..a493e51ac95c 100644 ---- a/dev.c -+++ b/dev.c -@@ -4246,6 +4246,10 @@ get_mq_diskio(unsigned long q, unsigned long *mq_count) - unsigned long mctx_addr; - struct diskio tmp; - -+ if (INVALID_MEMBER(blk_mq_ctx_rq_dispatched) || -+ INVALID_MEMBER(blk_mq_ctx_rq_completed)) -+ return; -+ - memset(&tmp, 0x00, sizeof(struct diskio)); - - readmem(q + OFFSET(request_queue_queue_ctx), KVADDR, &queue_ctx, -@@ -4475,24 +4479,41 @@ display_one_diskio(struct iter *i, unsigned long gendisk, ulong flags) - && (io.read + io.write == 0)) - return; - -- fprintf(fp, "%s%s%s %s%s%s%s %s%5d%s%s%s%s%s", -- mkstring(buf0, 5, RJUST|INT_DEC, (char *)(unsigned long)major), -- space(MINSPACE), -- mkstring(buf1, VADDR_PRLEN, LJUST|LONG_HEX, (char *)gendisk), -- space(MINSPACE), -- mkstring(buf2, 10, LJUST, disk_name), -- space(MINSPACE), -- mkstring(buf3, VADDR_PRLEN <= 11 ? 11 : VADDR_PRLEN, -- LJUST|LONG_HEX, (char *)queue_addr), -- space(MINSPACE), -- io.read + io.write, -- space(MINSPACE), -- mkstring(buf4, 5, RJUST|INT_DEC, -- (char *)(unsigned long)io.read), -- space(MINSPACE), -- mkstring(buf5, 5, RJUST|INT_DEC, -- (char *)(unsigned long)io.write), -- space(MINSPACE)); -+ if (use_mq_interface(queue_addr) && -+ (INVALID_MEMBER(blk_mq_ctx_rq_dispatched) || -+ INVALID_MEMBER(blk_mq_ctx_rq_completed))) -+ fprintf(fp, "%s%s%s %s%s%s%s %s%s%s", -+ mkstring(buf0, 5, RJUST|INT_DEC, (char *)(unsigned long)major), -+ space(MINSPACE), -+ mkstring(buf1, VADDR_PRLEN, LJUST|LONG_HEX, (char *)gendisk), -+ space(MINSPACE), -+ mkstring(buf2, 10, LJUST, disk_name), -+ space(MINSPACE), -+ mkstring(buf3, VADDR_PRLEN <= 11 ? 11 : VADDR_PRLEN, -+ LJUST|LONG_HEX, (char *)queue_addr), -+ space(MINSPACE), -+ mkstring(buf4, 17, RJUST, "(not supported)"), -+ space(MINSPACE)); -+ -+ else -+ fprintf(fp, "%s%s%s %s%s%s%s %s%5d%s%s%s%s%s", -+ mkstring(buf0, 5, RJUST|INT_DEC, (char *)(unsigned long)major), -+ space(MINSPACE), -+ mkstring(buf1, VADDR_PRLEN, LJUST|LONG_HEX, (char *)gendisk), -+ space(MINSPACE), -+ mkstring(buf2, 10, LJUST, disk_name), -+ space(MINSPACE), -+ mkstring(buf3, VADDR_PRLEN <= 11 ? 11 : VADDR_PRLEN, -+ LJUST|LONG_HEX, (char *)queue_addr), -+ space(MINSPACE), -+ io.read + io.write, -+ space(MINSPACE), -+ mkstring(buf4, 5, RJUST|INT_DEC, -+ (char *)(unsigned long)io.read), -+ space(MINSPACE), -+ mkstring(buf5, 5, RJUST|INT_DEC, -+ (char *)(unsigned long)io.write), -+ space(MINSPACE)); - - if (VALID_MEMBER(request_queue_in_flight)) { - if (!use_mq_interface(queue_addr)) { --- -2.20.1 - diff --git a/SOURCES/0002-defs.h-fix-breakage-of-compatibility-of-struct-symbo.patch b/SOURCES/0002-defs.h-fix-breakage-of-compatibility-of-struct-symbo.patch deleted file mode 100644 index 1415a8c..0000000 --- a/SOURCES/0002-defs.h-fix-breakage-of-compatibility-of-struct-symbo.patch +++ /dev/null @@ -1,41 +0,0 @@ -From a0eec39c14ee1db95a6c1a649a8f69b97e260dc6 Mon Sep 17 00:00:00 2001 -From: HATAYAMA Daisuke -Date: Wed, 8 Dec 2021 12:07:34 +0000 -Subject: [PATCH 2/2] defs.h: fix breakage of compatibility of struct - symbol_table_data for extension modules - -Commit <3ab39203ddd9> ("symbols: Implement install and remove operations -for mod_symname_hash") added new member variable mod_symname_hash in the -middle of struct symbol_table_date, which breaks compatibility of struct -symbol_table_data for extension modules. As the result, crash trace command -results in segmentation fault. - -Fixes: 3ab39203ddd9 ("symbols: Implement install and remove operations for mod_symname_hash") -Signed-off-by: HATAYAMA Daisuke ---- - defs.h | 2 +- - 1 file changed, 1 insertion(+), 1 deletion(-) - -diff --git a/defs.h b/defs.h -index caaa11e50c87..41b6cbc6cc85 100644 ---- a/defs.h -+++ b/defs.h -@@ -2753,7 +2753,6 @@ struct symbol_table_data { - double val_hash_searches; - double val_hash_iterations; - struct syment *symname_hash[SYMNAME_HASH]; -- struct syment *mod_symname_hash[SYMNAME_HASH]; - struct symbol_namespace kernel_namespace; - struct syment *ext_module_symtable; - struct syment *ext_module_symend; -@@ -2780,6 +2779,7 @@ struct symbol_table_data { - ulong kaiser_init_vmlinux; - int kernel_symbol_type; - ulong linux_banner_vmlinux; -+ struct syment *mod_symname_hash[SYMNAME_HASH]; - }; - - /* flags for st */ --- -2.30.2 - diff --git a/SOURCES/0002-sbitmapq-remove-struct-and-member-validation-in-sbit.patch b/SOURCES/0002-sbitmapq-remove-struct-and-member-validation-in-sbit.patch new file mode 100644 index 0000000..5b4fc47 --- /dev/null +++ b/SOURCES/0002-sbitmapq-remove-struct-and-member-validation-in-sbit.patch @@ -0,0 +1,62 @@ +From 364b2e413c69daf189d2bc0238e3ba9b0dcbd937 Mon Sep 17 00:00:00 2001 +From: Lianbo Jiang +Date: Mon, 23 May 2022 18:04:13 +0800 +Subject: [PATCH 02/18] sbitmapq: remove struct and member validation in + sbitmapq_init() + +Let's remove the struct and member validation from sbitmapq_init(), which +will help the crash to display the actual error when the sbitmapq fails. + +Without the patch: + crash> sbitmapq ffff8e99d0dc8010 + sbitmapq: command not supported or applicable on this architecture or kernel + +With the patch: + crash> sbitmapq ffff8e99d0dc8010 + + sbitmapq: invalid structure member offset: sbitmap_queue_alloc_hint + FILE: sbitmap.c LINE: 365 FUNCTION: sbitmap_queue_context_load() + +Signed-off-by: Lianbo Jiang +--- + sbitmap.c | 24 ------------------------ + 1 file changed, 24 deletions(-) + +diff --git a/sbitmap.c b/sbitmap.c +index 96a61e6c2c71..7693eef6cebd 100644 +--- a/sbitmap.c ++++ b/sbitmap.c +@@ -525,30 +525,6 @@ void sbitmapq_init(void) + MEMBER_OFFSET_INIT(sbq_wait_state_wait_cnt, "sbq_wait_state", "wait_cnt"); + MEMBER_OFFSET_INIT(sbq_wait_state_wait, "sbq_wait_state", "wait"); + +- if (!VALID_SIZE(sbitmap_word) || +- !VALID_SIZE(sbitmap) || +- !VALID_SIZE(sbitmap_queue) || +- !VALID_SIZE(sbq_wait_state) || +- INVALID_MEMBER(sbitmap_word_depth) || +- INVALID_MEMBER(sbitmap_word_word) || +- INVALID_MEMBER(sbitmap_word_cleared) || +- INVALID_MEMBER(sbitmap_depth) || +- INVALID_MEMBER(sbitmap_shift) || +- INVALID_MEMBER(sbitmap_map_nr) || +- INVALID_MEMBER(sbitmap_map) || +- INVALID_MEMBER(sbitmap_queue_sb) || +- INVALID_MEMBER(sbitmap_queue_alloc_hint) || +- INVALID_MEMBER(sbitmap_queue_wake_batch) || +- INVALID_MEMBER(sbitmap_queue_wake_index) || +- INVALID_MEMBER(sbitmap_queue_ws) || +- INVALID_MEMBER(sbitmap_queue_ws_active) || +- INVALID_MEMBER(sbitmap_queue_round_robin) || +- INVALID_MEMBER(sbitmap_queue_min_shallow_depth) || +- INVALID_MEMBER(sbq_wait_state_wait_cnt) || +- INVALID_MEMBER(sbq_wait_state_wait)) { +- command_not_supported(); +- } +- + sb_flags |= SB_FLAG_INIT; + } + +-- +2.30.2 + diff --git a/SOURCES/0003-Fix-for-timer-r-option-to-display-all-the-per-CPU-cl.patch b/SOURCES/0003-Fix-for-timer-r-option-to-display-all-the-per-CPU-cl.patch deleted file mode 100644 index 4a95e79..0000000 --- a/SOURCES/0003-Fix-for-timer-r-option-to-display-all-the-per-CPU-cl.patch +++ /dev/null @@ -1,59 +0,0 @@ -From c48177972f351d7853abb2a57709628c75ee38bc Mon Sep 17 00:00:00 2001 -From: Lianbo Jiang -Date: Thu, 6 Jan 2022 22:34:26 +0800 -Subject: [PATCH 03/11] Fix for "timer -r" option to display all the per-CPU - clocks - -Currently, the hrtimer_max_clock_bases is hard-coded to 3, which -makes that crash only prints three clocks, and the rest of clocks -are not displayed. - -Without the patch: -crash> timer -r -C 11 -CPU: 11 HRTIMER_CPU_BASE: ffff9a775f95ee00 - CLOCK: 0 HRTIMER_CLOCK_BASE: ffff9a775f95ee80 [ktime_get] - (empty) - - CLOCK: 1 HRTIMER_CLOCK_BASE: ffff9a775f95ef00 [ktime_get_real] - (empty) - - CLOCK: 2 HRTIMER_CLOCK_BASE: ffff9a775f95ef80 [ktime_get_boottime] - (empty) - -With the patch: -crash> timer -r -C 11 -CPU: 11 HRTIMER_CPU_BASE: ffff9a775f95ee00 - CLOCK: 0 HRTIMER_CLOCK_BASE: ffff9a775f95ee80 [ktime_get] - (empty) - - CLOCK: 1 HRTIMER_CLOCK_BASE: ffff9a775f95ef00 [ktime_get_real] - (empty) - - CLOCK: 2 HRTIMER_CLOCK_BASE: ffff9a775f95ef80 [ktime_get_boottime] - (empty) -... - CLOCK: 7 HRTIMER_CLOCK_BASE: ffff9a775f95f200 [ktime_get_clocktai] - (empty) - -Signed-off-by: Lianbo Jiang ---- - kernel.c | 3 ++- - 1 file changed, 2 insertions(+), 1 deletion(-) - -diff --git a/kernel.c b/kernel.c -index a637dd0eb8f8..a44a9c52ace0 100644 ---- a/kernel.c -+++ b/kernel.c -@@ -7672,7 +7672,8 @@ dump_hrtimer_data(const ulong *cpus) - if (VALID_STRUCT(hrtimer_clock_base)) { - hrtimer_max_clock_bases = 2; - if (symbol_exists("ktime_get_boottime")) -- hrtimer_max_clock_bases = 3; -+ hrtimer_max_clock_bases = MEMBER_SIZE("hrtimer_cpu_base", "clock_base") / -+ SIZE(hrtimer_clock_base); - } else if (VALID_STRUCT(hrtimer_base)) { - max_hrtimer_bases = 2; - } else --- -2.20.1 - diff --git a/SOURCES/0003-sbitmapq-fix-invalid-offset-for-sbitmap_queue_alloc_.patch b/SOURCES/0003-sbitmapq-fix-invalid-offset-for-sbitmap_queue_alloc_.patch new file mode 100644 index 0000000..eb1d17f --- /dev/null +++ b/SOURCES/0003-sbitmapq-fix-invalid-offset-for-sbitmap_queue_alloc_.patch @@ -0,0 +1,118 @@ +From a295cb40cd5d24fb5995cc78d29c5def3843d285 Mon Sep 17 00:00:00 2001 +From: Lianbo Jiang +Date: Mon, 23 May 2022 18:04:14 +0800 +Subject: [PATCH 03/18] sbitmapq: fix invalid offset for + "sbitmap_queue_alloc_hint" on Linux v5.13-rc1 + +Kernel commit c548e62bcf6a ("scsi: sbitmap: Move allocation hint +into sbitmap") moved the alloc_hint member from struct sbitmap_queue +to struct sbitmap. Without the patch, the sbitmapq will fail: + + crash> sbitmapq 0xffff8e99d0dc8010 + + sbitmapq: invalid structure member offset: sbitmap_queue_alloc_hint + FILE: sbitmap.c LINE: 365 FUNCTION: sbitmap_queue_context_load() + +Signed-off-by: Lianbo Jiang +--- + defs.h | 2 ++ + sbitmap.c | 14 ++++++++++++-- + symbols.c | 2 ++ + 3 files changed, 16 insertions(+), 2 deletions(-) + +diff --git a/defs.h b/defs.h +index a6735d07b32f..0aeb98c4f654 100644 +--- a/defs.h ++++ b/defs.h +@@ -2168,6 +2168,7 @@ struct offset_table { /* stash of commonly-used offsets */ + long sbitmap_queue_min_shallow_depth; + long sbq_wait_state_wait_cnt; + long sbq_wait_state_wait; ++ long sbitmap_alloc_hint; + }; + + struct size_table { /* stash of commonly-used sizes */ +@@ -5907,6 +5908,7 @@ struct sbitmap_context { + unsigned shift; + unsigned map_nr; + ulong map_addr; ++ ulong alloc_hint; + }; + + typedef bool (*sbitmap_for_each_fn)(unsigned int idx, void *p); +diff --git a/sbitmap.c b/sbitmap.c +index 7693eef6cebd..2921d5447c65 100644 +--- a/sbitmap.c ++++ b/sbitmap.c +@@ -285,6 +285,7 @@ void sbitmap_for_each_set(const struct sbitmap_context *sc, + static void sbitmap_queue_show(const struct sbitmap_queue_context *sqc, + const struct sbitmap_context *sc) + { ++ ulong alloc_hint_addr = 0; + int cpus = get_cpus_possible(); + int sbq_wait_state_size, wait_cnt_off, wait_off, list_head_off; + char *sbq_wait_state_buf; +@@ -297,6 +298,11 @@ static void sbitmap_queue_show(const struct sbitmap_queue_context *sqc, + fprintf(fp, "bits_per_word = %u\n", 1U << sc->shift); + fprintf(fp, "map_nr = %u\n", sc->map_nr); + ++ if (VALID_MEMBER(sbitmap_queue_alloc_hint)) ++ alloc_hint_addr = sqc->alloc_hint; ++ else if (VALID_MEMBER(sbitmap_alloc_hint)) /* 5.13 and later */ ++ alloc_hint_addr = sc->alloc_hint; ++ + fputs("alloc_hint = {", fp); + first = true; + for (i = 0; i < cpus; i++) { +@@ -307,7 +313,7 @@ static void sbitmap_queue_show(const struct sbitmap_queue_context *sqc, + fprintf(fp, ", "); + first = false; + +- ptr = kt->__per_cpu_offset[i] + sqc->alloc_hint; ++ ptr = kt->__per_cpu_offset[i] + alloc_hint_addr; + readmem(ptr, KVADDR, &val, sizeof(val), "alloc_hint", FAULT_ON_ERROR); + + fprintf(fp, "%u", val); +@@ -362,7 +368,8 @@ static void sbitmap_queue_context_load(ulong addr, struct sbitmap_queue_context + error(FATAL, "cannot read sbitmap_queue\n"); + } + +- sqc->alloc_hint = ULONG(sbitmap_queue_buf + OFFSET(sbitmap_queue_alloc_hint)); ++ if (VALID_MEMBER(sbitmap_queue_alloc_hint)) ++ sqc->alloc_hint = ULONG(sbitmap_queue_buf + OFFSET(sbitmap_queue_alloc_hint)); + sqc->wake_batch = UINT(sbitmap_queue_buf + OFFSET(sbitmap_queue_wake_batch)); + sqc->wake_index = INT(sbitmap_queue_buf + OFFSET(sbitmap_queue_wake_index)); + sqc->ws_addr = ULONG(sbitmap_queue_buf + OFFSET(sbitmap_queue_ws)); +@@ -387,6 +394,8 @@ void sbitmap_context_load(ulong addr, struct sbitmap_context *sc) + sc->shift = UINT(sbitmap_buf + OFFSET(sbitmap_shift)); + sc->map_nr = UINT(sbitmap_buf + OFFSET(sbitmap_map_nr)); + sc->map_addr = ULONG(sbitmap_buf + OFFSET(sbitmap_map)); ++ if (VALID_MEMBER(sbitmap_alloc_hint)) ++ sc->alloc_hint = ULONG(sbitmap_buf + OFFSET(sbitmap_alloc_hint)); + + FREEBUF(sbitmap_buf); + } +@@ -512,6 +521,7 @@ void sbitmapq_init(void) + MEMBER_OFFSET_INIT(sbitmap_shift, "sbitmap", "shift"); + MEMBER_OFFSET_INIT(sbitmap_map_nr, "sbitmap", "map_nr"); + MEMBER_OFFSET_INIT(sbitmap_map, "sbitmap", "map"); ++ MEMBER_OFFSET_INIT(sbitmap_alloc_hint, "sbitmap", "alloc_hint"); + + MEMBER_OFFSET_INIT(sbitmap_queue_sb, "sbitmap_queue", "sb"); + MEMBER_OFFSET_INIT(sbitmap_queue_alloc_hint, "sbitmap_queue", "alloc_hint"); +diff --git a/symbols.c b/symbols.c +index ba5e2741347d..fd0eb06899f0 100644 +--- a/symbols.c ++++ b/symbols.c +@@ -10708,6 +10708,8 @@ dump_offset_table(char *spec, ulong makestruct) + OFFSET(sbitmap_map_nr)); + fprintf(fp, " sbitmap_map: %ld\n", + OFFSET(sbitmap_map)); ++ fprintf(fp, " sbitmap_alloc_hint: %ld\n", ++ OFFSET(sbitmap_alloc_hint)); + fprintf(fp, " sbitmap_queue_sb: %ld\n", + OFFSET(sbitmap_queue_sb)); + fprintf(fp, " sbitmap_queue_alloc_hint: %ld\n", +-- +2.30.2 + diff --git a/SOURCES/0004-Fix-for-bt-v-option-to-display-the-stack-end-address.patch b/SOURCES/0004-Fix-for-bt-v-option-to-display-the-stack-end-address.patch deleted file mode 100644 index 0c56e07..0000000 --- a/SOURCES/0004-Fix-for-bt-v-option-to-display-the-stack-end-address.patch +++ /dev/null @@ -1,69 +0,0 @@ -From 1706f8b6ab50cd25e8fdabe8d50a37ce89bd60e0 Mon Sep 17 00:00:00 2001 -From: Lianbo Jiang -Date: Thu, 6 Jan 2022 12:01:17 +0800 -Subject: [PATCH 04/11] Fix for "bt -v" option to display the stack-end address - correctly - -The "bt -v" command prints incorrect stack-end address when the -"CONFIG_THREAD_INFO_IN_TASK=y" is enabled in kernel, the "bt -v" -command output shows that the value stored at 0xffff8dee0312c198 -is 0xffffffffc076400a, however, the value stored actually at -0xffff8dee0312c198 is NULL(0x0000000000000000), the stack-end -address is incorrect. - -Without the patch: -crash> bt -v -PID: 28642 TASK: ffff8dee0312c180 CPU: 0 COMMAND: "insmod" - possible stack overflow: ffff8dee0312c198: ffffffffc076400a != STACK_END_MAGIC - ^^^^^^^^^^^^^^^^ - -crash> rd 0xffff8dee0312c198 -ffff8dee0312c198: 0000000000000000 ........ - ^^^^^^^^^^^^^^^^ - -With the patch: -crash> bt -v -PID: 28642 TASK: ffff8dee0312c180 CPU: 0 COMMAND: "insmod" - possible stack overflow: ffff991340bc0000: ffffffffc076400a != STACK_END_MAGIC - -crash> rd 0xffff991340bc0000 -ffff991340bc0000: ffffffffc076400a .@v..... - -Signed-off-by: Lianbo Jiang ---- - task.c | 10 ++++++++-- - 1 file changed, 8 insertions(+), 2 deletions(-) - -diff --git a/task.c b/task.c -index bb6a5da8ad33..b5ddc88e0acb 100644 ---- a/task.c -+++ b/task.c -@@ -11202,7 +11202,7 @@ check_stack_overflow(void) - { - int i, overflow, cpu_size, cpu, total; - char buf[BUFSIZE]; -- ulong magic, task, stackbase; -+ ulong magic, task, stackbase, location; - struct task_context *tc; - - if (!tt->stack_end_magic && -@@ -11286,9 +11286,15 @@ check_stack_end_magic: - if (magic != STACK_END_MAGIC) { - if (!overflow) - print_task_header(fp, tc, 0); -+ -+ if (tt->flags & THREAD_INFO_IN_TASK) -+ location = task_to_stackbase(tc->task); -+ else -+ location = tc->thread_info + SIZE(thread_info); -+ - fprintf(fp, - " possible stack overflow: %lx: %lx != STACK_END_MAGIC\n", -- tc->thread_info + SIZE(thread_info), magic); -+ location, magic); - overflow++, total++; - } - --- -2.20.1 - diff --git a/SOURCES/0004-sbitmapq-fix-invalid-offset-for-sbitmap_queue_round_.patch b/SOURCES/0004-sbitmapq-fix-invalid-offset-for-sbitmap_queue_round_.patch new file mode 100644 index 0000000..1a2b611 --- /dev/null +++ b/SOURCES/0004-sbitmapq-fix-invalid-offset-for-sbitmap_queue_round_.patch @@ -0,0 +1,103 @@ +From 530fe6ad7e4d7ff6254596c1219d25ed929e3867 Mon Sep 17 00:00:00 2001 +From: Lianbo Jiang +Date: Mon, 23 May 2022 18:04:15 +0800 +Subject: [PATCH 04/18] sbitmapq: fix invalid offset for + "sbitmap_queue_round_robin" on Linux v5.13-rc1 + +Kernel commit efe1f3a1d583 ("scsi: sbitmap: Maintain allocation +round_robin in sbitmap") moved the round_robin member from struct +sbitmap_queue to struct sbitmap. Without the patch, the sbitmapq +will fail: + + crash> sbitmapq 0xffff8e99d0dc8010 + + sbitmapq: invalid structure member offset: sbitmap_queue_round_robin + FILE: sbitmap.c LINE: 378 FUNCTION: sbitmap_queue_context_load() + +Signed-off-by: Lianbo Jiang +--- + defs.h | 2 ++ + sbitmap.c | 12 ++++++++++-- + symbols.c | 2 ++ + 3 files changed, 14 insertions(+), 2 deletions(-) + +diff --git a/defs.h b/defs.h +index 0aeb98c4f654..ecbced24d2e3 100644 +--- a/defs.h ++++ b/defs.h +@@ -2169,6 +2169,7 @@ struct offset_table { /* stash of commonly-used offsets */ + long sbq_wait_state_wait_cnt; + long sbq_wait_state_wait; + long sbitmap_alloc_hint; ++ long sbitmap_round_robin; + }; + + struct size_table { /* stash of commonly-used sizes */ +@@ -5909,6 +5910,7 @@ struct sbitmap_context { + unsigned map_nr; + ulong map_addr; + ulong alloc_hint; ++ bool round_robin; + }; + + typedef bool (*sbitmap_for_each_fn)(unsigned int idx, void *p); +diff --git a/sbitmap.c b/sbitmap.c +index 2921d5447c65..7b318b533702 100644 +--- a/sbitmap.c ++++ b/sbitmap.c +@@ -352,7 +352,11 @@ static void sbitmap_queue_show(const struct sbitmap_queue_context *sqc, + + FREEBUF(sbq_wait_state_buf); + +- fprintf(fp, "round_robin = %d\n", sqc->round_robin); ++ if (VALID_MEMBER(sbitmap_queue_round_robin)) ++ fprintf(fp, "round_robin = %d\n", sqc->round_robin); ++ else if (VALID_MEMBER(sbitmap_round_robin)) /* 5.13 and later */ ++ fprintf(fp, "round_robin = %d\n", sc->round_robin); ++ + fprintf(fp, "min_shallow_depth = %u\n", sqc->min_shallow_depth); + } + +@@ -374,7 +378,8 @@ static void sbitmap_queue_context_load(ulong addr, struct sbitmap_queue_context + sqc->wake_index = INT(sbitmap_queue_buf + OFFSET(sbitmap_queue_wake_index)); + sqc->ws_addr = ULONG(sbitmap_queue_buf + OFFSET(sbitmap_queue_ws)); + sqc->ws_active = INT(sbitmap_queue_buf + OFFSET(sbitmap_queue_ws_active)); +- sqc->round_robin = BOOL(sbitmap_queue_buf + OFFSET(sbitmap_queue_round_robin)); ++ if (VALID_MEMBER(sbitmap_queue_round_robin)) ++ sqc->round_robin = BOOL(sbitmap_queue_buf + OFFSET(sbitmap_queue_round_robin)); + sqc->min_shallow_depth = UINT(sbitmap_queue_buf + OFFSET(sbitmap_queue_min_shallow_depth)); + + FREEBUF(sbitmap_queue_buf); +@@ -396,6 +401,8 @@ void sbitmap_context_load(ulong addr, struct sbitmap_context *sc) + sc->map_addr = ULONG(sbitmap_buf + OFFSET(sbitmap_map)); + if (VALID_MEMBER(sbitmap_alloc_hint)) + sc->alloc_hint = ULONG(sbitmap_buf + OFFSET(sbitmap_alloc_hint)); ++ if (VALID_MEMBER(sbitmap_round_robin)) ++ sc->round_robin = BOOL(sbitmap_buf + OFFSET(sbitmap_round_robin)); + + FREEBUF(sbitmap_buf); + } +@@ -522,6 +529,7 @@ void sbitmapq_init(void) + MEMBER_OFFSET_INIT(sbitmap_map_nr, "sbitmap", "map_nr"); + MEMBER_OFFSET_INIT(sbitmap_map, "sbitmap", "map"); + MEMBER_OFFSET_INIT(sbitmap_alloc_hint, "sbitmap", "alloc_hint"); ++ MEMBER_OFFSET_INIT(sbitmap_round_robin, "sbitmap", "round_robin"); + + MEMBER_OFFSET_INIT(sbitmap_queue_sb, "sbitmap_queue", "sb"); + MEMBER_OFFSET_INIT(sbitmap_queue_alloc_hint, "sbitmap_queue", "alloc_hint"); +diff --git a/symbols.c b/symbols.c +index fd0eb06899f0..5d12a021c769 100644 +--- a/symbols.c ++++ b/symbols.c +@@ -10710,6 +10710,8 @@ dump_offset_table(char *spec, ulong makestruct) + OFFSET(sbitmap_map)); + fprintf(fp, " sbitmap_alloc_hint: %ld\n", + OFFSET(sbitmap_alloc_hint)); ++ fprintf(fp, " sbitmap_round_robin: %ld\n", ++ OFFSET(sbitmap_round_robin)); + fprintf(fp, " sbitmap_queue_sb: %ld\n", + OFFSET(sbitmap_queue_sb)); + fprintf(fp, " sbitmap_queue_alloc_hint: %ld\n", +-- +2.30.2 + diff --git a/SOURCES/0005-Fix-for-HZ-calculation-on-Linux-5.14-and-later.patch b/SOURCES/0005-Fix-for-HZ-calculation-on-Linux-5.14-and-later.patch deleted file mode 100644 index f249f72..0000000 --- a/SOURCES/0005-Fix-for-HZ-calculation-on-Linux-5.14-and-later.patch +++ /dev/null @@ -1,35 +0,0 @@ -From f5637f341533ef2b28e2d6a6b12fcfb00d0fff2d Mon Sep 17 00:00:00 2001 -From: Lianbo Jiang -Date: Mon, 10 Jan 2022 17:25:06 +0800 -Subject: [PATCH 05/11] Fix for HZ calculation on Linux 5.14 and later - -Kernel commit 3e9a99eba058 ("block/mq-deadline: Rename dd_init_queue() -and dd_exit_queue()") renamed dd_init_queue to dd_init_sched. Without -the patch, the 'help -m' may print incorrect hz value as follows: - -crash> help -m | grep hz - hz: 1000 <---The correct hz value on ppc64le machine is 100. - ^^^^ - -Fixes: b93027ce5c75 ("Add alternate HZ calculation using write_expire") -Signed-off-by: Lianbo Jiang ---- - task.c | 2 ++ - 1 file changed, 2 insertions(+) - -diff --git a/task.c b/task.c -index b5ddc88e0acb..76e184ae70b1 100644 ---- a/task.c -+++ b/task.c -@@ -440,6 +440,8 @@ task_init(void) - } - } else if ((symbol_exists("dd_init_queue") && - gdb_set_crash_scope(symbol_value("dd_init_queue"), "dd_init_queue")) || -+ (symbol_exists("dd_init_sched") && -+ gdb_set_crash_scope(symbol_value("dd_init_sched"), "dd_init_sched")) || - (symbol_exists("deadline_init_queue") && - gdb_set_crash_scope(symbol_value("deadline_init_queue"), "deadline_init_queue"))) { - char buf[BUFSIZE]; --- -2.20.1 - diff --git a/SOURCES/0005-sbitmapq-fix-invalid-offset-for-sbitmap_word_depth-o.patch b/SOURCES/0005-sbitmapq-fix-invalid-offset-for-sbitmap_word_depth-o.patch new file mode 100644 index 0000000..838fb5b --- /dev/null +++ b/SOURCES/0005-sbitmapq-fix-invalid-offset-for-sbitmap_word_depth-o.patch @@ -0,0 +1,101 @@ +From 3750803f6ae5f5ad071f86ca916dbbb17b7a83a5 Mon Sep 17 00:00:00 2001 +From: Lianbo Jiang +Date: Mon, 23 May 2022 18:04:16 +0800 +Subject: [PATCH 05/18] sbitmapq: fix invalid offset for "sbitmap_word_depth" + on Linux v5.18-rc1 + +Kernel commit 3301bc53358a ("lib/sbitmap: kill 'depth' from sbitmap_word") +removed the depth member from struct sbitmap_word. Without the patch, the +sbitmapq will fail: + + crash> sbitmapq 0xffff8e99d0dc8010 + + sbitmapq: invalid structure member offset: sbitmap_word_depth + FILE: sbitmap.c LINE: 84 FUNCTION: __sbitmap_weight() + +Signed-off-by: Lianbo Jiang +--- + sbitmap.c | 19 +++++++++++-------- + 1 file changed, 11 insertions(+), 8 deletions(-) + +diff --git a/sbitmap.c b/sbitmap.c +index 7b318b533702..e8ebd62fe01c 100644 +--- a/sbitmap.c ++++ b/sbitmap.c +@@ -78,10 +78,16 @@ static unsigned long bitmap_weight(unsigned long bitmap, unsigned int bits) + return w; + } + ++static inline unsigned int __map_depth(const struct sbitmap_context *sc, int index) ++{ ++ if (index == sc->map_nr - 1) ++ return sc->depth - (index << sc->shift); ++ return 1U << sc->shift; ++} ++ + static unsigned int __sbitmap_weight(const struct sbitmap_context *sc, bool set) + { + const ulong sbitmap_word_size = SIZE(sbitmap_word); +- const ulong w_depth_off = OFFSET(sbitmap_word_depth); + const ulong w_word_off = OFFSET(sbitmap_word_word); + const ulong w_cleared_off = OFFSET(sbitmap_word_cleared); + +@@ -99,7 +105,7 @@ static unsigned int __sbitmap_weight(const struct sbitmap_context *sc, bool set) + error(FATAL, "cannot read sbitmap_word\n"); + } + +- depth = ULONG(sbitmap_word_buf + w_depth_off); ++ depth = __map_depth(sc, i); + + if (set) { + word = ULONG(sbitmap_word_buf + w_word_off); +@@ -142,7 +148,6 @@ static void sbitmap_emit_byte(unsigned int offset, uint8_t byte) + static void sbitmap_bitmap_show(const struct sbitmap_context *sc) + { + const ulong sbitmap_word_size = SIZE(sbitmap_word); +- const ulong w_depth_off = OFFSET(sbitmap_word_depth); + const ulong w_word_off = OFFSET(sbitmap_word_word); + const ulong w_cleared_off = OFFSET(sbitmap_word_cleared); + +@@ -165,7 +170,7 @@ static void sbitmap_bitmap_show(const struct sbitmap_context *sc) + + word = ULONG(sbitmap_word_buf + w_word_off); + cleared = ULONG(sbitmap_word_buf + w_cleared_off); +- word_bits = ULONG(sbitmap_word_buf + w_depth_off); ++ word_bits = __map_depth(sc, i); + + word &= ~cleared; + +@@ -213,7 +218,6 @@ static void __sbitmap_for_each_set(const struct sbitmap_context *sc, + unsigned int start, sbitmap_for_each_fn fn, void *data) + { + const ulong sbitmap_word_size = SIZE(sbitmap_word); +- const ulong w_depth_off = OFFSET(sbitmap_word_depth); + const ulong w_word_off = OFFSET(sbitmap_word_word); + const ulong w_cleared_off = OFFSET(sbitmap_word_cleared); + +@@ -232,7 +236,7 @@ static void __sbitmap_for_each_set(const struct sbitmap_context *sc, + + while (scanned < sc->depth) { + unsigned long w_addr = sc->map_addr + (sbitmap_word_size * index); +- unsigned long w_depth, w_word, w_cleared; ++ unsigned long w_word, w_cleared; + unsigned long word, depth; + + if (!readmem(w_addr, KVADDR, sbitmap_word_buf, sbitmap_word_size, "sbitmap_word", RETURN_ON_ERROR)) { +@@ -240,11 +244,10 @@ static void __sbitmap_for_each_set(const struct sbitmap_context *sc, + error(FATAL, "cannot read sbitmap_word\n"); + } + +- w_depth = ULONG(sbitmap_word_buf + w_depth_off); + w_word = ULONG(sbitmap_word_buf + w_word_off); + w_cleared = ULONG(sbitmap_word_buf + w_cleared_off); + +- depth = min(w_depth - nr, sc->depth - scanned); ++ depth = min(__map_depth(sc, index) - nr, sc->depth - scanned); + + scanned += depth; + word = w_word & ~w_cleared; +-- +2.30.2 + diff --git a/SOURCES/0006-memory-Handle-struct-slab-changes-on-Linux-5.17-rc1-.patch b/SOURCES/0006-memory-Handle-struct-slab-changes-on-Linux-5.17-rc1-.patch deleted file mode 100644 index 7407306..0000000 --- a/SOURCES/0006-memory-Handle-struct-slab-changes-on-Linux-5.17-rc1-.patch +++ /dev/null @@ -1,40 +0,0 @@ -From a392b27653e4e75460753522af0f006006b4dc4e Mon Sep 17 00:00:00 2001 -From: Alexander Egorenkov -Date: Mon, 6 Dec 2021 16:04:19 +0100 -Subject: [PATCH 06/11] memory: Handle struct slab changes on Linux 5.17-rc1 - and later - -Since kernel commit d122019bf061 ("mm: Split slab into its own type"), -the struct slab is used for both SLAB and SLUB. Therefore, don't depend -on the non-presence of the struct slab to decide whether SLAB implementation -should be chosen and use the member variable "cpu_slab" of the struct -kmem_cache instead, it should be present only in SLUB. - -Without the patch, crash fails to start with the error message: - - crash: invalid structure member offset: kmem_cache_s_num - FILE: memory.c LINE: 9619 FUNCTION: kmem_cache_init() - -Signed-off-by: Alexander Egorenkov -Signed-off-by: Lianbo Jiang ---- - memory.c | 3 ++- - 1 file changed, 2 insertions(+), 1 deletion(-) - -diff --git a/memory.c b/memory.c -index 86c02c132890..5af45fd7d834 100644 ---- a/memory.c -+++ b/memory.c -@@ -576,7 +576,8 @@ vm_init(void) - STRUCT_SIZE_INIT(cpucache_s, "cpucache_s"); - - } else if (!VALID_STRUCT(kmem_slab_s) && -- !VALID_STRUCT(slab_s) && -+ !VALID_STRUCT(slab_s) && -+ !MEMBER_EXISTS("kmem_cache", "cpu_slab") && - (VALID_STRUCT(slab) || (vt->flags & SLAB_OVERLOAD_PAGE))) { - vt->flags |= PERCPU_KMALLOC_V2; - --- -2.20.1 - diff --git a/SOURCES/0007-Move-the-initialization-of-boot_date-to-task_init.patch b/SOURCES/0007-Move-the-initialization-of-boot_date-to-task_init.patch deleted file mode 100644 index c8d8227..0000000 --- a/SOURCES/0007-Move-the-initialization-of-boot_date-to-task_init.patch +++ /dev/null @@ -1,75 +0,0 @@ -From fa0b6453a05c5600849e4e531c94594ed9c90270 Mon Sep 17 00:00:00 2001 -From: Lianbo Jiang -Date: Mon, 17 Jan 2022 15:14:00 +0800 -Subject: [PATCH 07/11] Move the initialization of "boot_date" to task_init() - -The "boot_date" is initialized conditionally in the cmd_log(), which may -display incorrect "boot_date" value with the following command before -running the "log -T" command: - -crash> help -k | grep date - date: Wed Dec 22 13:39:29 IST 2021 - boot_date: Thu Jan 1 05:30:00 IST 1970 - ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ -The calculation of "boot_date" depends on the HZ value, and the HZ will -be calculated in task_init() at the latest, so let's move it here. - -Signed-off-by: Lianbo Jiang ---- - kernel.c | 18 +++--------------- - task.c | 10 ++++++++++ - 2 files changed, 13 insertions(+), 15 deletions(-) - -diff --git a/kernel.c b/kernel.c -index a44a9c52ace0..9afddc0c918c 100644 ---- a/kernel.c -+++ b/kernel.c -@@ -5026,21 +5026,9 @@ cmd_log(void) - if (argerrs) - cmd_usage(pc->curcmd, SYNOPSIS); - -- if (msg_flags & SHOW_LOG_CTIME) { -- if (pc->flags & MINIMAL_MODE) { -- error(WARNING, "the option '-T' is not available in minimal mode\n"); -- return; -- } -- -- if (kt->boot_date.tv_sec == 0) { -- ulonglong uptime_jiffies; -- ulong uptime_sec; -- -- get_uptime(NULL, &uptime_jiffies); -- uptime_sec = (uptime_jiffies)/(ulonglong)machdep->hz; -- kt->boot_date.tv_sec = kt->date.tv_sec - uptime_sec; -- kt->boot_date.tv_nsec = 0; -- } -+ if (msg_flags & SHOW_LOG_CTIME && pc->flags & MINIMAL_MODE) { -+ error(WARNING, "the option '-T' is not available in minimal mode\n"); -+ return; - } - - if (msg_flags & SHOW_LOG_AUDIT) { -diff --git a/task.c b/task.c -index 76e184ae70b1..263a8344dd94 100644 ---- a/task.c -+++ b/task.c -@@ -692,6 +692,16 @@ task_init(void) - - stack_overflow_check_init(); - -+ if (machdep->hz) { -+ ulonglong uptime_jiffies; -+ ulong uptime_sec; -+ -+ get_uptime(NULL, &uptime_jiffies); -+ uptime_sec = (uptime_jiffies)/(ulonglong)machdep->hz; -+ kt->boot_date.tv_sec = kt->date.tv_sec - uptime_sec; -+ kt->boot_date.tv_nsec = 0; -+ } -+ - tt->flags |= TASK_INIT_DONE; - } - --- -2.20.1 - diff --git a/SOURCES/0007-bt-x86_64-filter-out-idle-task-stack.patch b/SOURCES/0007-bt-x86_64-filter-out-idle-task-stack.patch new file mode 100644 index 0000000..ebbc530 --- /dev/null +++ b/SOURCES/0007-bt-x86_64-filter-out-idle-task-stack.patch @@ -0,0 +1,205 @@ +From 6833262bf87177d8affe4f91b2e7d2c76ecdf636 Mon Sep 17 00:00:00 2001 +From: Qi Zheng +Date: Tue, 24 May 2022 20:25:53 +0800 +Subject: [PATCH 07/18] bt: x86_64: filter out idle task stack + +When we use crash to troubleshoot softlockup and other problems, +we often use the 'bt -a' command to print the stacks of running +processes on all CPUs. But now some servers have hundreds of CPUs +(such as AMD machines), which causes the 'bt -a' command to output +a lot of process stacks. And many of these stacks are the stacks +of the idle process, which are not needed by us. + +Therefore, in order to reduce this part of the interference information, +this patch adds the -n option to the bt command. When we specify +'-n idle' (meaning no idle), the stack of the idle process will be +filtered out, thus speeding up our troubleshooting. + +And the option works only for crash dumps captured by kdump. + +The command output is as follows: +crash> bt -a -n idle +[...] +PID: 0 TASK: ffff889ff8c34380 CPU: 8 COMMAND: "swapper/8" + +PID: 0 TASK: ffff889ff8c32d00 CPU: 9 COMMAND: "swapper/9" + +PID: 0 TASK: ffff889ff8c31680 CPU: 10 COMMAND: "swapper/10" + +PID: 0 TASK: ffff889ff8c35a00 CPU: 11 COMMAND: "swapper/11" + +PID: 0 TASK: ffff889ff8c3c380 CPU: 12 COMMAND: "swapper/12" + +PID: 150773 TASK: ffff889fe85a1680 CPU: 13 COMMAND: "bash" + #0 [ffffc9000d35bcd0] machine_kexec at ffffffff8105a407 + #1 [ffffc9000d35bd28] __crash_kexec at ffffffff8113033d + #2 [ffffc9000d35bdf0] panic at ffffffff81081930 + #3 [ffffc9000d35be70] sysrq_handle_crash at ffffffff814e38d1 + #4 [ffffc9000d35be78] __handle_sysrq.cold.12 at ffffffff814e4175 + #5 [ffffc9000d35bea8] write_sysrq_trigger at ffffffff814e404b + #6 [ffffc9000d35beb8] proc_reg_write at ffffffff81330d86 + #7 [ffffc9000d35bed0] vfs_write at ffffffff812a72d5 + #8 [ffffc9000d35bf00] ksys_write at ffffffff812a7579 + #9 [ffffc9000d35bf38] do_syscall_64 at ffffffff81004259 + RIP: 00007fa7abcdc274 RSP: 00007fffa731f678 RFLAGS: 00000246 + RAX: ffffffffffffffda RBX: 0000000000000002 RCX: 00007fa7abcdc274 + RDX: 0000000000000002 RSI: 0000563ca51ee6d0 RDI: 0000000000000001 + RBP: 0000563ca51ee6d0 R8: 000000000000000a R9: 00007fa7abd6be80 + R10: 000000000000000a R11: 0000000000000246 R12: 00007fa7abdad760 + R13: 0000000000000002 R14: 00007fa7abda8760 R15: 0000000000000002 + ORIG_RAX: 0000000000000001 CS: 0033 SS: 002b +[...] + +Signed-off-by: Qi Zheng +Acked-by: Kazuhito Hagio +Acked-by: Lianbo Jiang +Signed-off-by: Lianbo Jiang +--- + defs.h | 1 + + help.c | 33 ++++++++++++++++++++++++++++++++- + kernel.c | 13 ++++++++++++- + x86_64.c | 8 ++++++++ + 4 files changed, 53 insertions(+), 2 deletions(-) + +diff --git a/defs.h b/defs.h +index ecbced24d2e3..c8444b4e54eb 100644 +--- a/defs.h ++++ b/defs.h +@@ -5832,6 +5832,7 @@ ulong cpu_map_addr(const char *type); + #define BT_SHOW_ALL_REGS (0x2000000000000ULL) + #define BT_REGS_NOT_FOUND (0x4000000000000ULL) + #define BT_OVERFLOW_STACK (0x8000000000000ULL) ++#define BT_SKIP_IDLE (0x10000000000000ULL) + #define BT_SYMBOL_OFFSET (BT_SYMBOLIC_ARGS) + + #define BT_REF_HEXVAL (0x1) +diff --git a/help.c b/help.c +index 51a0fe3d687c..e1bbc5abe029 100644 +--- a/help.c ++++ b/help.c +@@ -1909,12 +1909,14 @@ char *help_bt[] = { + "bt", + "backtrace", + "[-a|-c cpu(s)|-g|-r|-t|-T|-l|-e|-E|-f|-F|-o|-O|-v|-p] [-R ref] [-s [-x|d]]" +-"\n [-I ip] [-S sp] [pid | task]", ++"\n [-I ip] [-S sp] [-n idle] [pid | task]", + " Display a kernel stack backtrace. If no arguments are given, the stack", + " trace of the current context will be displayed.\n", + " -a displays the stack traces of the active task on each CPU.", + " (only applicable to crash dumps)", + " -A same as -a, but also displays vector registers (S390X only).", ++" -n idle filter the stack of idle tasks (x86_64).", ++" (only applicable to crash dumps)", + " -p display the stack trace of the panic task only.", + " (only applicable to crash dumps)", + " -c cpu display the stack trace of the active task on one or more CPUs,", +@@ -2004,6 +2006,35 @@ char *help_bt[] = { + " DS: 002b ESI: bfffc8a0 ES: 002b EDI: 00000000 ", + " SS: 002b ESP: bfffc82c EBP: bfffd224 ", + " CS: 0023 EIP: 400d032e ERR: 0000008e EFLAGS: 00000246 ", ++" ", ++" Display the stack trace of the active task(s) when the kernel panicked,", ++" and filter out the stack of the idle tasks:", ++" ", ++" %s> bt -a -n idle", ++" ...", ++" PID: 0 TASK: ffff889ff8c35a00 CPU: 11 COMMAND: \"swapper/11\"", ++" ", ++" PID: 0 TASK: ffff889ff8c3c380 CPU: 12 COMMAND: \"swapper/12\"", ++" ", ++" PID: 150773 TASK: ffff889fe85a1680 CPU: 13 COMMAND: \"bash\"", ++" #0 [ffffc9000d35bcd0] machine_kexec at ffffffff8105a407", ++" #1 [ffffc9000d35bd28] __crash_kexec at ffffffff8113033d", ++" #2 [ffffc9000d35bdf0] panic at ffffffff81081930", ++" #3 [ffffc9000d35be70] sysrq_handle_crash at ffffffff814e38d1", ++" #4 [ffffc9000d35be78] __handle_sysrq.cold.12 at ffffffff814e4175", ++" #5 [ffffc9000d35bea8] write_sysrq_trigger at ffffffff814e404b", ++" #6 [ffffc9000d35beb8] proc_reg_write at ffffffff81330d86", ++" #7 [ffffc9000d35bed0] vfs_write at ffffffff812a72d5", ++" #8 [ffffc9000d35bf00] ksys_write at ffffffff812a7579", ++" #9 [ffffc9000d35bf38] do_syscall_64 at ffffffff81004259", ++" RIP: 00007fa7abcdc274 RSP: 00007fffa731f678 RFLAGS: 00000246", ++" RAX: ffffffffffffffda RBX: 0000000000000002 RCX: 00007fa7abcdc274", ++" RDX: 0000000000000002 RSI: 0000563ca51ee6d0 RDI: 0000000000000001", ++" RBP: 0000563ca51ee6d0 R8: 000000000000000a R9: 00007fa7abd6be80", ++" R10: 000000000000000a R11: 0000000000000246 R12: 00007fa7abdad760", ++" R13: 0000000000000002 R14: 00007fa7abda8760 R15: 0000000000000002", ++" ORIG_RAX: 0000000000000001 CS: 0033 SS: 002b", ++" ...", + "\n Display the stack trace of the active task on CPU 0 and 1:\n", + " %s> bt -c 0,1", + " PID: 0 TASK: ffffffff81a8d020 CPU: 0 COMMAND: \"swapper\"", +diff --git a/kernel.c b/kernel.c +index d0921cf567d9..411e9da1e54f 100644 +--- a/kernel.c ++++ b/kernel.c +@@ -2503,7 +2503,7 @@ cmd_bt(void) + if (kt->flags & USE_OPT_BT) + bt->flags |= BT_OPT_BACK_TRACE; + +- while ((c = getopt(argcnt, args, "D:fFI:S:c:aAloreEgstTdxR:Ovp")) != EOF) { ++ while ((c = getopt(argcnt, args, "D:fFI:S:c:n:aAloreEgstTdxR:Ovp")) != EOF) { + switch (c) + { + case 'f': +@@ -2672,6 +2672,13 @@ cmd_bt(void) + active++; + break; + ++ case 'n': ++ if (machine_type("X86_64") && STREQ(optarg, "idle")) ++ bt->flags |= BT_SKIP_IDLE; ++ else ++ option_not_supported(c); ++ break; ++ + case 'r': + bt->flags |= BT_RAW; + break; +@@ -3092,6 +3099,10 @@ back_trace(struct bt_info *bt) + } else + machdep->get_stack_frame(bt, &eip, &esp); + ++ /* skip idle task stack */ ++ if (bt->flags & BT_SKIP_IDLE) ++ return; ++ + if (bt->flags & BT_KSTACKP) { + bt->stkptr = esp; + return; +diff --git a/x86_64.c b/x86_64.c +index ecaefd2f46a8..cfafbcc4dabe 100644 +--- a/x86_64.c ++++ b/x86_64.c +@@ -4918,6 +4918,9 @@ x86_64_get_stack_frame(struct bt_info *bt, ulong *pcp, ulong *spp) + if (bt->flags & BT_DUMPFILE_SEARCH) + return x86_64_get_dumpfile_stack_frame(bt, pcp, spp); + ++ if (bt->flags & BT_SKIP_IDLE) ++ bt->flags &= ~BT_SKIP_IDLE; ++ + if (pcp) + *pcp = x86_64_get_pc(bt); + if (spp) +@@ -4960,6 +4963,9 @@ x86_64_get_dumpfile_stack_frame(struct bt_info *bt_in, ulong *rip, ulong *rsp) + estack = -1; + panic = FALSE; + ++ if (bt_in->flags & BT_SKIP_IDLE) ++ bt_in->flags &= ~BT_SKIP_IDLE; ++ + panic_task = tt->panic_task == bt->task ? TRUE : FALSE; + + if (panic_task && bt->machdep) { +@@ -5098,6 +5104,8 @@ next_sysrq: + if (!panic_task && STREQ(sym, "crash_nmi_callback")) { + *rip = *up; + *rsp = bt->stackbase + ((char *)(up) - bt->stackbuf); ++ if ((bt->flags & BT_SKIP_IDLE) && is_idle_thread(bt->task)) ++ bt_in->flags |= BT_SKIP_IDLE; + return; + } + +-- +2.30.2 + diff --git a/SOURCES/0008-Remove-ptype-command-from-ps-t-option-to-reduce-memo.patch b/SOURCES/0008-Remove-ptype-command-from-ps-t-option-to-reduce-memo.patch deleted file mode 100644 index ee7a5cd..0000000 --- a/SOURCES/0008-Remove-ptype-command-from-ps-t-option-to-reduce-memo.patch +++ /dev/null @@ -1,79 +0,0 @@ -From bbd5a5c1f5db3bde04628e75396155260333e53e Mon Sep 17 00:00:00 2001 -From: Kazuhito Hagio -Date: Wed, 19 Jan 2022 16:24:49 +0900 -Subject: [PATCH 08/11] Remove ptype command from "ps -t" option to reduce - memory and time - -With some vmlinux e.g. RHEL9 ones, the first execution of the gdb ptype -command heavily consumes memory and time. The "ps -t" option uses it in -start_time_timespec(), and it can be replaced with the crash macros. - -This can reduce about 1.4 GB memory and 6 seconds time comsumption in -the following test: - - $ echo "ps -t" | time crash vmlinux vmcore - - Without the patch: - 11.60user 0.43system 0:11.94elapsed 100%CPU (0avgtext+0avgdata 1837964maxresident)k - 0inputs+400outputs (0major+413636minor)pagefaults 0swaps - - With the patch: - 5.40user 0.16system 0:05.46elapsed 101%CPU (0avgtext+0avgdata 417896maxresident)k - 0inputs+384outputs (0major+41528minor)pagefaults 0swaps - -Although the ptype command and similar ones cannot be fully removed, -but removing some of them will make the use of crash safer, especially -for an automatic crash reporter. - -Signed-off-by: Kazuhito Hagio -Signed-off-by: Lianbo Jiang ---- - task.c | 25 +++++-------------------- - 1 file changed, 5 insertions(+), 20 deletions(-) - -diff --git a/task.c b/task.c -index 263a8344dd94..a79ed0d96fb5 100644 ---- a/task.c -+++ b/task.c -@@ -4662,8 +4662,6 @@ show_task_times(struct task_context *tcp, ulong flags) - static int - start_time_timespec(void) - { -- char buf[BUFSIZE]; -- - switch(tt->flags & (TIMESPEC | NO_TIMESPEC | START_TIME_NSECS)) - { - case TIMESPEC: -@@ -4677,24 +4675,11 @@ start_time_timespec(void) - - tt->flags |= NO_TIMESPEC; - -- open_tmpfile(); -- sprintf(buf, "ptype struct task_struct"); -- if (!gdb_pass_through(buf, NULL, GNU_RETURN_ON_ERROR)) { -- close_tmpfile(); -- return FALSE; -- } -- -- rewind(pc->tmpfile); -- while (fgets(buf, BUFSIZE, pc->tmpfile)) { -- if (strstr(buf, "start_time;")) { -- if (strstr(buf, "struct timespec")) { -- tt->flags &= ~NO_TIMESPEC; -- tt->flags |= TIMESPEC; -- } -- } -- } -- -- close_tmpfile(); -+ if (VALID_MEMBER(task_struct_start_time) && -+ STREQ(MEMBER_TYPE_NAME("task_struct", "start_time"), "timespec")) { -+ tt->flags &= ~NO_TIMESPEC; -+ tt->flags |= TIMESPEC; -+ } - - if ((tt->flags & NO_TIMESPEC) && (SIZE(task_struct_start_time) == 8)) { - tt->flags &= ~NO_TIMESPEC; --- -2.20.1 - diff --git a/SOURCES/0008-bt-arm64-add-support-for-bt-n-idle.patch b/SOURCES/0008-bt-arm64-add-support-for-bt-n-idle.patch new file mode 100644 index 0000000..4712ac4 --- /dev/null +++ b/SOURCES/0008-bt-arm64-add-support-for-bt-n-idle.patch @@ -0,0 +1,96 @@ +From 0f162febebc4d11a165dd40cee00f3b0ba691a52 Mon Sep 17 00:00:00 2001 +From: Qi Zheng +Date: Tue, 24 May 2022 20:25:54 +0800 +Subject: [PATCH 08/18] bt: arm64: add support for 'bt -n idle' + +The '-n idle' option of bt command can help us filter the +stack of the idle process when debugging the dumpfiles +captured by kdump. + +This patch supports this feature on ARM64. + +Signed-off-by: Qi Zheng +Signed-off-by: Lianbo Jiang +--- + arm64.c | 19 ++++++++++++++++--- + help.c | 2 +- + kernel.c | 3 ++- + 3 files changed, 19 insertions(+), 5 deletions(-) + +diff --git a/arm64.c b/arm64.c +index 65f6cdf69fa6..0f615cf52bef 100644 +--- a/arm64.c ++++ b/arm64.c +@@ -3681,6 +3681,12 @@ arm64_get_dumpfile_stackframe(struct bt_info *bt, struct arm64_stackframe *frame + { + struct machine_specific *ms = machdep->machspec; + struct arm64_pt_regs *ptregs; ++ bool skip = false; ++ ++ if (bt->flags & BT_SKIP_IDLE) { ++ skip = true; ++ bt->flags &= ~BT_SKIP_IDLE; ++ } + + if (!ms->panic_task_regs || + (!ms->panic_task_regs[bt->tc->processor].sp && +@@ -3713,8 +3719,11 @@ try_kernel: + } + + if (arm64_in_kdump_text(bt, frame) || +- arm64_in_kdump_text_on_irq_stack(bt)) ++ arm64_in_kdump_text_on_irq_stack(bt)) { + bt->flags |= BT_KDUMP_ADJUST; ++ if (skip && is_idle_thread(bt->task)) ++ bt->flags |= BT_SKIP_IDLE; ++ } + + return TRUE; + } +@@ -3738,10 +3747,14 @@ arm64_get_stack_frame(struct bt_info *bt, ulong *pcp, ulong *spp) + int ret; + struct arm64_stackframe stackframe = { 0 }; + +- if (DUMPFILE() && is_task_active(bt->task)) ++ if (DUMPFILE() && is_task_active(bt->task)) { + ret = arm64_get_dumpfile_stackframe(bt, &stackframe); +- else ++ } else { ++ if (bt->flags & BT_SKIP_IDLE) ++ bt->flags &= ~BT_SKIP_IDLE; ++ + ret = arm64_get_stackframe(bt, &stackframe); ++ } + + if (!ret) + error(WARNING, +diff --git a/help.c b/help.c +index e1bbc5abe029..99214c1590fa 100644 +--- a/help.c ++++ b/help.c +@@ -1915,7 +1915,7 @@ char *help_bt[] = { + " -a displays the stack traces of the active task on each CPU.", + " (only applicable to crash dumps)", + " -A same as -a, but also displays vector registers (S390X only).", +-" -n idle filter the stack of idle tasks (x86_64).", ++" -n idle filter the stack of idle tasks (x86_64, arm64).", + " (only applicable to crash dumps)", + " -p display the stack trace of the panic task only.", + " (only applicable to crash dumps)", +diff --git a/kernel.c b/kernel.c +index 411e9da1e54f..a521ef30cdb0 100644 +--- a/kernel.c ++++ b/kernel.c +@@ -2673,7 +2673,8 @@ cmd_bt(void) + break; + + case 'n': +- if (machine_type("X86_64") && STREQ(optarg, "idle")) ++ if ((machine_type("X86_64") || machine_type("ARM64")) && ++ STREQ(optarg, "idle")) + bt->flags |= BT_SKIP_IDLE; + else + option_not_supported(c); +-- +2.30.2 + diff --git a/SOURCES/0009-Improve-the-ps-performance-for-vmcores-with-large-nu.patch b/SOURCES/0009-Improve-the-ps-performance-for-vmcores-with-large-nu.patch deleted file mode 100644 index c398eb8..0000000 --- a/SOURCES/0009-Improve-the-ps-performance-for-vmcores-with-large-nu.patch +++ /dev/null @@ -1,150 +0,0 @@ -From d52cccfaa96ed6f61ff9d53da88715296e31db80 Mon Sep 17 00:00:00 2001 -From: Tao Liu -Date: Fri, 21 Jan 2022 13:43:09 +0800 -Subject: [PATCH 09/11] Improve the ps performance for vmcores with large - number of threads - -Previously, the ps command will iterate over all threads which -have the same tgid, to accumulate their rss value, in order to -get a thread/process's final rss value as part of the final output. - -For non-live systems, the rss accumulation values are identical for -threads which have the same tgid, so there is no need to do the -iteration and accumulation repeatly, thus a lot of readmem calls are -skipped. Otherwise it will be the performance bottleneck if the -vmcores have a large number of threads. - -In this patch, the rss accumulation value will be stored in a cache, -next time a thread with the same tgid will take it directly without -the iteration. - -For example, we can monitor the performance issue when a vmcore has -~65k processes, most of which are threads for several specific -processes. Without the patch, it will take ~7h for ps command -to finish. With the patch, ps command will finish in 1min. - -Signed-off-by: Tao Liu -Signed-off-by: Lianbo Jiang ---- - defs.h | 1 + - memory.c | 70 +++++++++++++++++++++++++++++++------------------------- - task.c | 1 + - 3 files changed, 41 insertions(+), 31 deletions(-) - -diff --git a/defs.h b/defs.h -index 41b6cbc6cc85..77e76f27cddb 100644 ---- a/defs.h -+++ b/defs.h -@@ -830,6 +830,7 @@ struct task_context { /* context stored for each task */ - struct tgid_context { /* tgid and task stored for each task */ - ulong tgid; - ulong task; -+ long rss_cache; - }; - - struct task_table { /* kernel/local task table data */ -diff --git a/memory.c b/memory.c -index 5af45fd7d834..e80c59ea4534 100644 ---- a/memory.c -+++ b/memory.c -@@ -4665,7 +4665,7 @@ void - get_task_mem_usage(ulong task, struct task_mem_usage *tm) - { - struct task_context *tc; -- long rss = 0; -+ long rss = 0, rss_cache = 0; - - BZERO(tm, sizeof(struct task_mem_usage)); - -@@ -4730,38 +4730,46 @@ get_task_mem_usage(ulong task, struct task_mem_usage *tm) - (last->tgid == (last + 1)->tgid)) - last++; - -- while (first <= last) -- { -- /* count 0 -> filepages */ -- if (!readmem(first->task + -- OFFSET(task_struct_rss_stat) + -- OFFSET(task_rss_stat_count), KVADDR, -- &sync_rss, -- sizeof(int), -- "task_struct rss_stat MM_FILEPAGES", -- RETURN_ON_ERROR)) -- continue; -- -- rss += sync_rss; -- -- /* count 1 -> anonpages */ -- if (!readmem(first->task + -- OFFSET(task_struct_rss_stat) + -- OFFSET(task_rss_stat_count) + -- sizeof(int), -- KVADDR, &sync_rss, -- sizeof(int), -- "task_struct rss_stat MM_ANONPAGES", -- RETURN_ON_ERROR)) -- continue; -- -- rss += sync_rss; -- -- if (first == last) -- break; -- first++; -+ /* -+ * Using rss cache for dumpfile is more beneficial than live debug -+ * because its value never changes in dumpfile. -+ */ -+ if (ACTIVE() || last->rss_cache == UNINITIALIZED) { -+ while (first <= last) -+ { -+ /* count 0 -> filepages */ -+ if (!readmem(first->task + -+ OFFSET(task_struct_rss_stat) + -+ OFFSET(task_rss_stat_count), KVADDR, -+ &sync_rss, -+ sizeof(int), -+ "task_struct rss_stat MM_FILEPAGES", -+ RETURN_ON_ERROR)) -+ continue; -+ -+ rss_cache += sync_rss; -+ -+ /* count 1 -> anonpages */ -+ if (!readmem(first->task + -+ OFFSET(task_struct_rss_stat) + -+ OFFSET(task_rss_stat_count) + -+ sizeof(int), -+ KVADDR, &sync_rss, -+ sizeof(int), -+ "task_struct rss_stat MM_ANONPAGES", -+ RETURN_ON_ERROR)) -+ continue; -+ -+ rss_cache += sync_rss; -+ -+ if (first == last) -+ break; -+ first++; -+ } -+ last->rss_cache = rss_cache; - } - -+ rss += last->rss_cache; - tt->last_tgid = last; - } - } -diff --git a/task.c b/task.c -index a79ed0d96fb5..864c838637ee 100644 ---- a/task.c -+++ b/task.c -@@ -2947,6 +2947,7 @@ add_context(ulong task, char *tp) - tg = tt->tgid_array + tt->running_tasks; - tg->tgid = *tgid_addr; - tg->task = task; -+ tg->rss_cache = UNINITIALIZED; - - if (do_verify && !verify_task(tc, do_verify)) { - error(INFO, "invalid task address: %lx\n", tc->task); --- -2.20.1 - diff --git a/SOURCES/0010-Enhance-dev-d-D-options-to-support-blk-mq-sbitmap.patch b/SOURCES/0010-Enhance-dev-d-D-options-to-support-blk-mq-sbitmap.patch new file mode 100644 index 0000000..6e8b008 --- /dev/null +++ b/SOURCES/0010-Enhance-dev-d-D-options-to-support-blk-mq-sbitmap.patch @@ -0,0 +1,392 @@ +From 7095c8fd029e3a33117e3b67de73f504686ebfe2 Mon Sep 17 00:00:00 2001 +From: Lianbo Jiang +Date: Thu, 2 Jun 2022 20:12:55 +0800 +Subject: [PATCH 10/18] Enhance "dev -d|-D" options to support blk-mq sbitmap + +Since Linux 5.16-rc1, which kernel commit 9a14d6ce4135 ("block: remove +debugfs blk_mq_ctx dispatched/merged/completed attributes") removed the +members from struct blk_mq_ctx, crash has not displayed disk I/O statistics +for multiqueue (blk-mq) devices. + +Let's parse the sbitmap in blk-mq layer to support it. + +Signed-off-by: Lianbo Jiang +Signed-off-by: Kazuhito Hagio +--- + defs.h | 11 +++ + dev.c | 244 +++++++++++++++++++++++++++++++++++++++++++++--------- + symbols.c | 22 +++++ + 3 files changed, 238 insertions(+), 39 deletions(-) + +diff --git a/defs.h b/defs.h +index c8444b4e54eb..2681586a33dc 100644 +--- a/defs.h ++++ b/defs.h +@@ -2170,6 +2170,16 @@ struct offset_table { /* stash of commonly-used offsets */ + long sbq_wait_state_wait; + long sbitmap_alloc_hint; + long sbitmap_round_robin; ++ long request_cmd_flags; ++ long request_q; ++ long request_state; ++ long request_queue_queue_hw_ctx; ++ long request_queue_nr_hw_queues; ++ long blk_mq_hw_ctx_tags; ++ long blk_mq_tags_bitmap_tags; ++ long blk_mq_tags_breserved_tags; ++ long blk_mq_tags_nr_reserved_tags; ++ long blk_mq_tags_rqs; + }; + + struct size_table { /* stash of commonly-used sizes */ +@@ -2339,6 +2349,7 @@ struct size_table { /* stash of commonly-used sizes */ + long sbitmap; + long sbitmap_queue; + long sbq_wait_state; ++ long blk_mq_tags; + }; + + struct array_table { +diff --git a/dev.c b/dev.c +index a493e51ac95c..4be4c96df8b0 100644 +--- a/dev.c ++++ b/dev.c +@@ -4238,19 +4238,176 @@ get_one_mctx_diskio(unsigned long mctx, struct diskio *io) + io->write = (dispatch[1] - comp[1]); + } + ++typedef bool (busy_tag_iter_fn)(ulong rq, void *data); ++ ++struct mq_inflight { ++ ulong q; ++ struct diskio *dio; ++}; ++ ++struct bt_iter_data { ++ ulong tags; ++ uint reserved; ++ uint nr_reserved_tags; ++ busy_tag_iter_fn *fn; ++ void *data; ++}; ++ ++/* ++ * See the include/linux/blk_types.h and include/linux/blk-mq.h ++ */ ++#define MQ_RQ_IN_FLIGHT 1 ++#define REQ_OP_BITS 8 ++#define REQ_OP_MASK ((1 << REQ_OP_BITS) - 1) ++ ++static uint op_is_write(uint op) ++{ ++ return (op & REQ_OP_MASK) & 1; ++} ++ ++static bool mq_check_inflight(ulong rq, void *data) ++{ ++ uint cmd_flags = 0, state = 0; ++ ulong addr = 0, queue = 0; ++ struct mq_inflight *mi = data; ++ ++ if (!IS_KVADDR(rq)) ++ return TRUE; ++ ++ addr = rq + OFFSET(request_q); ++ if (!readmem(addr, KVADDR, &queue, sizeof(ulong), "request.q", RETURN_ON_ERROR)) ++ return FALSE; ++ ++ addr = rq + OFFSET(request_cmd_flags); ++ if (!readmem(addr, KVADDR, &cmd_flags, sizeof(uint), "request.cmd_flags", RETURN_ON_ERROR)) ++ return FALSE; ++ ++ addr = rq + OFFSET(request_state); ++ if (!readmem(addr, KVADDR, &state, sizeof(uint), "request.state", RETURN_ON_ERROR)) ++ return FALSE; ++ ++ if (queue == mi->q && state == MQ_RQ_IN_FLIGHT) { ++ if (op_is_write(cmd_flags)) ++ mi->dio->write++; ++ else ++ mi->dio->read++; ++ } ++ ++ return TRUE; ++} ++ ++static bool bt_iter(uint bitnr, void *data) ++{ ++ ulong addr = 0, rqs_addr = 0, rq = 0; ++ struct bt_iter_data *iter_data = data; ++ ulong tag = iter_data->tags; ++ ++ if (!iter_data->reserved) ++ bitnr += iter_data->nr_reserved_tags; ++ ++ /* rqs */ ++ addr = tag + OFFSET(blk_mq_tags_rqs); ++ if (!readmem(addr, KVADDR, &rqs_addr, sizeof(void *), "blk_mq_tags.rqs", RETURN_ON_ERROR)) ++ return FALSE; ++ ++ addr = rqs_addr + bitnr * sizeof(ulong); /* rqs[bitnr] */ ++ if (!readmem(addr, KVADDR, &rq, sizeof(ulong), "blk_mq_tags.rqs[]", RETURN_ON_ERROR)) ++ return FALSE; ++ ++ return iter_data->fn(rq, iter_data->data); ++} ++ ++static void bt_for_each(ulong q, ulong tags, ulong sbq, uint reserved, uint nr_resvd_tags, struct diskio *dio) ++{ ++ struct sbitmap_context sc = {0}; ++ struct mq_inflight mi = { ++ .q = q, ++ .dio = dio, ++ }; ++ struct bt_iter_data iter_data = { ++ .tags = tags, ++ .reserved = reserved, ++ .nr_reserved_tags = nr_resvd_tags, ++ .fn = mq_check_inflight, ++ .data = &mi, ++ }; ++ ++ sbitmap_context_load(sbq + OFFSET(sbitmap_queue_sb), &sc); ++ sbitmap_for_each_set(&sc, bt_iter, &iter_data); ++} ++ ++static void queue_for_each_hw_ctx(ulong q, ulong *hctx, uint cnt, struct diskio *dio) ++{ ++ uint i; ++ ++ for (i = 0; i < cnt; i++) { ++ ulong addr = 0, tags = 0; ++ uint nr_reserved_tags = 0; ++ ++ /* Tags owned by the block driver */ ++ addr = hctx[i] + OFFSET(blk_mq_hw_ctx_tags); ++ if (!readmem(addr, KVADDR, &tags, sizeof(ulong), ++ "blk_mq_hw_ctx.tags", RETURN_ON_ERROR)) ++ break; ++ ++ addr = tags + OFFSET(blk_mq_tags_nr_reserved_tags); ++ if (!readmem(addr, KVADDR, &nr_reserved_tags, sizeof(uint), ++ "blk_mq_tags_nr_reserved_tags", RETURN_ON_ERROR)) ++ break; ++ ++ if (nr_reserved_tags) { ++ addr = tags + OFFSET(blk_mq_tags_breserved_tags); ++ bt_for_each(q, tags, addr, 1, nr_reserved_tags, dio); ++ } ++ addr = tags + OFFSET(blk_mq_tags_bitmap_tags); ++ bt_for_each(q, tags, addr, 0, nr_reserved_tags, dio); ++ } ++} ++ ++static void get_mq_diskio_from_hw_queues(ulong q, struct diskio *dio) ++{ ++ uint cnt = 0; ++ ulong addr = 0, hctx_addr = 0; ++ ulong *hctx_array = NULL; ++ ++ addr = q + OFFSET(request_queue_nr_hw_queues); ++ readmem(addr, KVADDR, &cnt, sizeof(uint), ++ "request_queue.nr_hw_queues", FAULT_ON_ERROR); ++ ++ addr = q + OFFSET(request_queue_queue_hw_ctx); ++ readmem(addr, KVADDR, &hctx_addr, sizeof(void *), ++ "request_queue.queue_hw_ctx", FAULT_ON_ERROR); ++ ++ hctx_array = (ulong *)GETBUF(sizeof(void *) * cnt); ++ if (!hctx_array) ++ error(FATAL, "fail to get memory for the hctx_array\n"); ++ ++ if (!readmem(hctx_addr, KVADDR, hctx_array, sizeof(void *) * cnt, ++ "request_queue.queue_hw_ctx[]", RETURN_ON_ERROR)) { ++ FREEBUF(hctx_array); ++ return; ++ } ++ ++ queue_for_each_hw_ctx(q, hctx_array, cnt, dio); ++ ++ FREEBUF(hctx_array); ++} ++ + static void + get_mq_diskio(unsigned long q, unsigned long *mq_count) + { + int cpu; + unsigned long queue_ctx; + unsigned long mctx_addr; +- struct diskio tmp; ++ struct diskio tmp = {0}; + + if (INVALID_MEMBER(blk_mq_ctx_rq_dispatched) || +- INVALID_MEMBER(blk_mq_ctx_rq_completed)) ++ INVALID_MEMBER(blk_mq_ctx_rq_completed)) { ++ get_mq_diskio_from_hw_queues(q, &tmp); ++ mq_count[0] = tmp.read; ++ mq_count[1] = tmp.write; + return; +- +- memset(&tmp, 0x00, sizeof(struct diskio)); ++ } + + readmem(q + OFFSET(request_queue_queue_ctx), KVADDR, &queue_ctx, + sizeof(ulong), "request_queue.queue_ctx", +@@ -4479,41 +4636,24 @@ display_one_diskio(struct iter *i, unsigned long gendisk, ulong flags) + && (io.read + io.write == 0)) + return; + +- if (use_mq_interface(queue_addr) && +- (INVALID_MEMBER(blk_mq_ctx_rq_dispatched) || +- INVALID_MEMBER(blk_mq_ctx_rq_completed))) +- fprintf(fp, "%s%s%s %s%s%s%s %s%s%s", +- mkstring(buf0, 5, RJUST|INT_DEC, (char *)(unsigned long)major), +- space(MINSPACE), +- mkstring(buf1, VADDR_PRLEN, LJUST|LONG_HEX, (char *)gendisk), +- space(MINSPACE), +- mkstring(buf2, 10, LJUST, disk_name), +- space(MINSPACE), +- mkstring(buf3, VADDR_PRLEN <= 11 ? 11 : VADDR_PRLEN, +- LJUST|LONG_HEX, (char *)queue_addr), +- space(MINSPACE), +- mkstring(buf4, 17, RJUST, "(not supported)"), +- space(MINSPACE)); +- +- else +- fprintf(fp, "%s%s%s %s%s%s%s %s%5d%s%s%s%s%s", +- mkstring(buf0, 5, RJUST|INT_DEC, (char *)(unsigned long)major), +- space(MINSPACE), +- mkstring(buf1, VADDR_PRLEN, LJUST|LONG_HEX, (char *)gendisk), +- space(MINSPACE), +- mkstring(buf2, 10, LJUST, disk_name), +- space(MINSPACE), +- mkstring(buf3, VADDR_PRLEN <= 11 ? 11 : VADDR_PRLEN, +- LJUST|LONG_HEX, (char *)queue_addr), +- space(MINSPACE), +- io.read + io.write, +- space(MINSPACE), +- mkstring(buf4, 5, RJUST|INT_DEC, +- (char *)(unsigned long)io.read), +- space(MINSPACE), +- mkstring(buf5, 5, RJUST|INT_DEC, +- (char *)(unsigned long)io.write), +- space(MINSPACE)); ++ fprintf(fp, "%s%s%s %s%s%s%s %s%5d%s%s%s%s%s", ++ mkstring(buf0, 5, RJUST|INT_DEC, (char *)(unsigned long)major), ++ space(MINSPACE), ++ mkstring(buf1, VADDR_PRLEN, LJUST|LONG_HEX, (char *)gendisk), ++ space(MINSPACE), ++ mkstring(buf2, 10, LJUST, disk_name), ++ space(MINSPACE), ++ mkstring(buf3, VADDR_PRLEN <= 11 ? 11 : VADDR_PRLEN, ++ LJUST|LONG_HEX, (char *)queue_addr), ++ space(MINSPACE), ++ io.read + io.write, ++ space(MINSPACE), ++ mkstring(buf4, 5, RJUST|INT_DEC, ++ (char *)(unsigned long)io.read), ++ space(MINSPACE), ++ mkstring(buf5, 5, RJUST|INT_DEC, ++ (char *)(unsigned long)io.write), ++ space(MINSPACE)); + + if (VALID_MEMBER(request_queue_in_flight)) { + if (!use_mq_interface(queue_addr)) { +@@ -4597,6 +4737,9 @@ void diskio_init(void) + MEMBER_OFFSET_INIT(kobject_entry, "kobject", "entry"); + MEMBER_OFFSET_INIT(kset_list, "kset", "list"); + MEMBER_OFFSET_INIT(request_list_count, "request_list", "count"); ++ MEMBER_OFFSET_INIT(request_cmd_flags, "request", "cmd_flags"); ++ MEMBER_OFFSET_INIT(request_q, "request", "q"); ++ MEMBER_OFFSET_INIT(request_state, "request", "state"); + MEMBER_OFFSET_INIT(request_queue_in_flight, "request_queue", + "in_flight"); + if (MEMBER_EXISTS("request_queue", "rq")) +@@ -4608,10 +4751,33 @@ void diskio_init(void) + "mq_ops"); + ANON_MEMBER_OFFSET_INIT(request_queue_queue_ctx, + "request_queue", "queue_ctx"); ++ MEMBER_OFFSET_INIT(request_queue_queue_hw_ctx, ++ "request_queue", "queue_hw_ctx"); ++ MEMBER_OFFSET_INIT(request_queue_nr_hw_queues, ++ "request_queue", "nr_hw_queues"); + MEMBER_OFFSET_INIT(blk_mq_ctx_rq_dispatched, "blk_mq_ctx", + "rq_dispatched"); + MEMBER_OFFSET_INIT(blk_mq_ctx_rq_completed, "blk_mq_ctx", + "rq_completed"); ++ MEMBER_OFFSET_INIT(blk_mq_hw_ctx_tags, "blk_mq_hw_ctx", "tags"); ++ MEMBER_OFFSET_INIT(blk_mq_tags_bitmap_tags, "blk_mq_tags", ++ "bitmap_tags"); ++ MEMBER_OFFSET_INIT(blk_mq_tags_breserved_tags, "blk_mq_tags", ++ "breserved_tags"); ++ MEMBER_OFFSET_INIT(blk_mq_tags_nr_reserved_tags, "blk_mq_tags", ++ "nr_reserved_tags"); ++ MEMBER_OFFSET_INIT(blk_mq_tags_rqs, "blk_mq_tags", "rqs"); ++ STRUCT_SIZE_INIT(blk_mq_tags, "blk_mq_tags"); ++ STRUCT_SIZE_INIT(sbitmap, "sbitmap"); ++ STRUCT_SIZE_INIT(sbitmap_word, "sbitmap_word"); ++ MEMBER_OFFSET_INIT(sbitmap_word_word, "sbitmap_word", "word"); ++ MEMBER_OFFSET_INIT(sbitmap_word_cleared, "sbitmap_word", "cleared"); ++ MEMBER_OFFSET_INIT(sbitmap_depth, "sbitmap", "depth"); ++ MEMBER_OFFSET_INIT(sbitmap_shift, "sbitmap", "shift"); ++ MEMBER_OFFSET_INIT(sbitmap_map_nr, "sbitmap", "map_nr"); ++ MEMBER_OFFSET_INIT(sbitmap_map, "sbitmap", "map"); ++ MEMBER_OFFSET_INIT(sbitmap_queue_sb, "sbitmap_queue", "sb"); ++ + } + MEMBER_OFFSET_INIT(subsys_private_klist_devices, "subsys_private", + "klist_devices"); +diff --git a/symbols.c b/symbols.c +index 5d12a021c769..c1f09556d710 100644 +--- a/symbols.c ++++ b/symbols.c +@@ -10385,6 +10385,12 @@ dump_offset_table(char *spec, ulong makestruct) + OFFSET(kset_list)); + fprintf(fp, " request_list_count: %ld\n", + OFFSET(request_list_count)); ++ fprintf(fp, " request_cmd_flags: %ld\n", ++ OFFSET(request_cmd_flags)); ++ fprintf(fp, " request_q: %ld\n", ++ OFFSET(request_q)); ++ fprintf(fp, " request_state: %ld\n", ++ OFFSET(request_state)); + fprintf(fp, " request_queue_in_flight: %ld\n", + OFFSET(request_queue_in_flight)); + fprintf(fp, " request_queue_rq: %ld\n", +@@ -10393,10 +10399,25 @@ dump_offset_table(char *spec, ulong makestruct) + OFFSET(request_queue_mq_ops)); + fprintf(fp, " request_queue_queue_ctx: %ld\n", + OFFSET(request_queue_queue_ctx)); ++ fprintf(fp, " request_queue_queue_hw_ctx: %ld\n", ++ OFFSET(request_queue_queue_hw_ctx)); ++ fprintf(fp, " request_queue_nr_hw_queues: %ld\n", ++ OFFSET(request_queue_nr_hw_queues)); + fprintf(fp, " blk_mq_ctx_rq_dispatched: %ld\n", + OFFSET(blk_mq_ctx_rq_dispatched)); + fprintf(fp, " blk_mq_ctx_rq_completed: %ld\n", + OFFSET(blk_mq_ctx_rq_completed)); ++ fprintf(fp, " blk_mq_hw_ctx_tags: %ld\n", ++ OFFSET(blk_mq_hw_ctx_tags)); ++ fprintf(fp, " blk_mq_tags_bitmap_tags: %ld\n", ++ OFFSET(blk_mq_tags_bitmap_tags)); ++ fprintf(fp, " blk_mq_tags_breserved_tags: %ld\n", ++ OFFSET(blk_mq_tags_breserved_tags)); ++ fprintf(fp, " blk_mq_tags_nr_reserved_tags: %ld\n", ++ OFFSET(blk_mq_tags_nr_reserved_tags)); ++ fprintf(fp, " blk_mq_tags_rqs: %ld\n", ++ OFFSET(blk_mq_tags_rqs)); ++ + fprintf(fp, " subsys_private_klist_devices: %ld\n", + OFFSET(subsys_private_klist_devices)); + fprintf(fp, " subsystem_kset: %ld\n", +@@ -11003,6 +11024,7 @@ dump_offset_table(char *spec, ulong makestruct) + fprintf(fp, " sbitmap: %ld\n", SIZE(sbitmap)); + fprintf(fp, " sbitmap_queue: %ld\n", SIZE(sbitmap_queue)); + fprintf(fp, " sbq_wait_state: %ld\n", SIZE(sbq_wait_state)); ++ fprintf(fp, " blk_mq_tags: %ld\n", SIZE(blk_mq_tags)); + + fprintf(fp, "\n array_table:\n"); + /* +-- +2.30.2 + diff --git a/SOURCES/0010-arm64-Fix-segfault-by-bt-command-with-offline-cpus.patch b/SOURCES/0010-arm64-Fix-segfault-by-bt-command-with-offline-cpus.patch deleted file mode 100644 index 1c4040f..0000000 --- a/SOURCES/0010-arm64-Fix-segfault-by-bt-command-with-offline-cpus.patch +++ /dev/null @@ -1,59 +0,0 @@ -From 1a1fd21c625cb2ca335e626eb50426f13c4160f7 Mon Sep 17 00:00:00 2001 -From: Kazuhito Hagio -Date: Wed, 26 Jan 2022 06:07:00 +0000 -Subject: [PATCH 10/11] arm64: Fix segfault by "bt" command with offline cpus - -Currently on arm64, NT_PRSTATUS notes in dumpfile are not mapped to -online cpus and machine_specific->panic_task_regs correctly. As a -result, the "bt" command can cause a segmentation fault. - - crash> bt -c 0 - PID: 0 TASK: ffff8000117fa240 CPU: 0 COMMAND: "swapper/0" - Segmentation fault (core dumped) - -To fix this, -1) make map_cpus_to_prstatus_kdump_cmprs() map the notes to - dd->nt_prstatus_percpu also on arm64, and -2) move arm64_get_crash_notes() to machdep_init(POST_INIT) in order - to apply the mapping to machine_specific->panic_task_regs. - -Resolves: https://github.com/crash-utility/crash/issues/105 -Reported-by: xuchunmei000 -Signed-off-by: Kazuhito Hagio -Tested-by: David Wysochanski -Signed-off-by: Lianbo Jiang ---- - arm64.c | 2 +- - diskdump.c | 3 +-- - 2 files changed, 2 insertions(+), 3 deletions(-) - -diff --git a/arm64.c b/arm64.c -index 23c3d75d85aa..4f2c2b5104a1 100644 ---- a/arm64.c -+++ b/arm64.c -@@ -472,7 +472,7 @@ arm64_init(int when) - arm64_stackframe_init(); - break; - -- case POST_VM: -+ case POST_INIT: - /* - * crash_notes contains machine specific information about the - * crash. In particular, it contains CPU registers at the time -diff --git a/diskdump.c b/diskdump.c -index 112f769f8949..690b42443ed2 100644 ---- a/diskdump.c -+++ b/diskdump.c -@@ -111,8 +111,7 @@ map_cpus_to_prstatus_kdump_cmprs(void) - if (pc->flags2 & QEMU_MEM_DUMP_COMPRESSED) /* notes exist for all cpus */ - goto resize_note_pointers; - -- if (!(online = get_cpus_online()) || (online == kt->cpus) || -- machine_type("ARM64")) -+ if (!(online = get_cpus_online()) || (online == kt->cpus)) - goto resize_note_pointers; - - if (CRASHDEBUG(1)) --- -2.20.1 - diff --git a/SOURCES/0011-Fix-for-dev-d-D-options-to-support-blk-mq-change-on-.patch b/SOURCES/0011-Fix-for-dev-d-D-options-to-support-blk-mq-change-on-.patch new file mode 100644 index 0000000..6167735 --- /dev/null +++ b/SOURCES/0011-Fix-for-dev-d-D-options-to-support-blk-mq-change-on-.patch @@ -0,0 +1,121 @@ +From 68ce0b9a35d77d767872dd1a729c50e4695a30a8 Mon Sep 17 00:00:00 2001 +From: Lianbo Jiang +Date: Thu, 2 Jun 2022 20:12:56 +0800 +Subject: [PATCH 11/18] Fix for "dev -d|-D" options to support blk-mq change on + Linux v5.18-rc1 + +Kernel commit 4e5cc99e1e48 ("blk-mq: manage hctx map via xarray") removed +the "queue_hw_ctx" member from struct request_queue at Linux v5.18-rc1, +and replaced it with a struct xarray "hctx_table". Without the patch, the +"dev -d|-D" options will print an error: + + crash> dev -d + MAJOR GENDISK NAME REQUEST_QUEUE TOTAL READ WRITE + + dev: invalid structure member offset: request_queue_queue_hw_ctx + +With the patch: + crash> dev -d + MAJOR GENDISK NAME REQUEST_QUEUE TOTAL READ WRITE + 8 ffff8e99d0a1ae00 sda ffff8e9c14c59980 10 6 4 + +Signed-off-by: Lianbo Jiang +--- + defs.h | 1 + + dev.c | 42 +++++++++++++++++++++++++++++++++--------- + symbols.c | 2 ++ + 3 files changed, 36 insertions(+), 9 deletions(-) + +diff --git a/defs.h b/defs.h +index 2681586a33dc..7d3b73422f48 100644 +--- a/defs.h ++++ b/defs.h +@@ -2180,6 +2180,7 @@ struct offset_table { /* stash of commonly-used offsets */ + long blk_mq_tags_breserved_tags; + long blk_mq_tags_nr_reserved_tags; + long blk_mq_tags_rqs; ++ long request_queue_hctx_table; + }; + + struct size_table { /* stash of commonly-used sizes */ +diff --git a/dev.c b/dev.c +index 4be4c96df8b0..0172c83ffaea 100644 +--- a/dev.c ++++ b/dev.c +@@ -4369,20 +4369,42 @@ static void get_mq_diskio_from_hw_queues(ulong q, struct diskio *dio) + uint cnt = 0; + ulong addr = 0, hctx_addr = 0; + ulong *hctx_array = NULL; ++ struct list_pair *lp = NULL; ++ ++ if (VALID_MEMBER(request_queue_hctx_table)) { ++ addr = q + OFFSET(request_queue_hctx_table); ++ cnt = do_xarray(addr, XARRAY_COUNT, NULL); ++ lp = (struct list_pair *)GETBUF(sizeof(struct list_pair) * (cnt + 1)); ++ if (!lp) ++ error(FATAL, "fail to get memory for list_pair.\n"); ++ lp[0].index = cnt; ++ cnt = do_xarray(addr, XARRAY_GATHER, lp); ++ } else { ++ addr = q + OFFSET(request_queue_nr_hw_queues); ++ readmem(addr, KVADDR, &cnt, sizeof(uint), ++ "request_queue.nr_hw_queues", FAULT_ON_ERROR); + +- addr = q + OFFSET(request_queue_nr_hw_queues); +- readmem(addr, KVADDR, &cnt, sizeof(uint), +- "request_queue.nr_hw_queues", FAULT_ON_ERROR); +- +- addr = q + OFFSET(request_queue_queue_hw_ctx); +- readmem(addr, KVADDR, &hctx_addr, sizeof(void *), +- "request_queue.queue_hw_ctx", FAULT_ON_ERROR); ++ addr = q + OFFSET(request_queue_queue_hw_ctx); ++ readmem(addr, KVADDR, &hctx_addr, sizeof(void *), ++ "request_queue.queue_hw_ctx", FAULT_ON_ERROR); ++ } + + hctx_array = (ulong *)GETBUF(sizeof(void *) * cnt); +- if (!hctx_array) ++ if (!hctx_array) { ++ if (lp) ++ FREEBUF(lp); + error(FATAL, "fail to get memory for the hctx_array\n"); ++ } ++ ++ if (lp && hctx_array) { ++ uint i; ++ ++ /* copy it from list_pair to hctx_array */ ++ for (i = 0; i < cnt; i++) ++ hctx_array[i] = (ulong)lp[i].value; + +- if (!readmem(hctx_addr, KVADDR, hctx_array, sizeof(void *) * cnt, ++ FREEBUF(lp); ++ } else if (!readmem(hctx_addr, KVADDR, hctx_array, sizeof(void *) * cnt, + "request_queue.queue_hw_ctx[]", RETURN_ON_ERROR)) { + FREEBUF(hctx_array); + return; +@@ -4755,6 +4777,8 @@ void diskio_init(void) + "request_queue", "queue_hw_ctx"); + MEMBER_OFFSET_INIT(request_queue_nr_hw_queues, + "request_queue", "nr_hw_queues"); ++ MEMBER_OFFSET_INIT(request_queue_hctx_table, ++ "request_queue", "hctx_table"); + MEMBER_OFFSET_INIT(blk_mq_ctx_rq_dispatched, "blk_mq_ctx", + "rq_dispatched"); + MEMBER_OFFSET_INIT(blk_mq_ctx_rq_completed, "blk_mq_ctx", +diff --git a/symbols.c b/symbols.c +index c1f09556d710..bee1faf92c83 100644 +--- a/symbols.c ++++ b/symbols.c +@@ -10403,6 +10403,8 @@ dump_offset_table(char *spec, ulong makestruct) + OFFSET(request_queue_queue_hw_ctx)); + fprintf(fp, " request_queue_nr_hw_queues: %ld\n", + OFFSET(request_queue_nr_hw_queues)); ++ fprintf(fp, " request_queue_hctx_table: %ld\n", ++ OFFSET(request_queue_hctx_table)); + fprintf(fp, " blk_mq_ctx_rq_dispatched: %ld\n", + OFFSET(blk_mq_ctx_rq_dispatched)); + fprintf(fp, " blk_mq_ctx_rq_completed: %ld\n", +-- +2.30.2 + diff --git a/SOURCES/0011-Fix-for-kmem-s-S-and-bt-F-F-on-Linux-5.17-rc1.patch b/SOURCES/0011-Fix-for-kmem-s-S-and-bt-F-F-on-Linux-5.17-rc1.patch deleted file mode 100644 index 1bd6774..0000000 --- a/SOURCES/0011-Fix-for-kmem-s-S-and-bt-F-F-on-Linux-5.17-rc1.patch +++ /dev/null @@ -1,89 +0,0 @@ -From 86446eaba408807e00cf2310d5748aa6b7511284 Mon Sep 17 00:00:00 2001 -From: Kazuhito Hagio -Date: Wed, 2 Feb 2022 02:14:56 +0000 -Subject: [PATCH 11/11] Fix for "kmem -s|-S" and "bt -F[F]" on Linux 5.17-rc1 - -Since the following kernel commits split slab info from struct page -into struct slab, crash cannot get several slab related offsets from -struct page. - - d122019bf061 ("mm: Split slab into its own type") - 07f910f9b729 ("mm: Remove slab from struct page") - -Without the patch, "kmem -s|-S" and "bt -F[F]" options cannot work -correctly with the following errors: - - crash> kmem -s kmem_cache - CACHE OBJSIZE ALLOCATED TOTAL SLABS SSIZE NAME - kmem: page_to_nid: invalid page: ffff9454afc35020 - kmem: kmem_cache: cannot gather relevant slab data - ffff945140042000 216 ? ? ? 8k kmem_cache - - crash> bt -F - ... - bt: invalid structure member offset: page_slab - FILE: memory.c LINE: 9477 FUNCTION: vaddr_to_kmem_cache() - -Signed-by: Kazuhito Hagio -Signed-off-by: Lianbo Jiang ---- - memory.c | 13 +++++++++++++ - 1 file changed, 13 insertions(+) - -diff --git a/memory.c b/memory.c -index e80c59ea4534..8448ddc3a16c 100644 ---- a/memory.c -+++ b/memory.c -@@ -421,6 +421,8 @@ vm_init(void) - MEMBER_OFFSET_INIT(page_prev, "page", "prev"); - if (INVALID_MEMBER(page_next)) - ANON_MEMBER_OFFSET_INIT(page_next, "page", "next"); -+ if (INVALID_MEMBER(page_next)) -+ MEMBER_OFFSET_INIT(page_next, "slab", "next"); - - MEMBER_OFFSET_INIT(page_list, "page", "list"); - if (VALID_MEMBER(page_list)) { -@@ -747,11 +749,15 @@ vm_init(void) - MEMBER_OFFSET_INIT(kmem_cache_random, "kmem_cache", "random"); - MEMBER_OFFSET_INIT(kmem_cache_cpu_freelist, "kmem_cache_cpu", "freelist"); - MEMBER_OFFSET_INIT(kmem_cache_cpu_page, "kmem_cache_cpu", "page"); -+ if (INVALID_MEMBER(kmem_cache_cpu_page)) -+ MEMBER_OFFSET_INIT(kmem_cache_cpu_page, "kmem_cache_cpu", "slab"); - MEMBER_OFFSET_INIT(kmem_cache_cpu_node, "kmem_cache_cpu", "node"); - MEMBER_OFFSET_INIT(kmem_cache_cpu_partial, "kmem_cache_cpu", "partial"); - MEMBER_OFFSET_INIT(page_inuse, "page", "inuse"); - if (INVALID_MEMBER(page_inuse)) - ANON_MEMBER_OFFSET_INIT(page_inuse, "page", "inuse"); -+ if (INVALID_MEMBER(page_inuse)) -+ MEMBER_OFFSET_INIT(page_inuse, "slab", "inuse"); - MEMBER_OFFSET_INIT(page_offset, "page", "offset"); - if (INVALID_MEMBER(page_offset)) - ANON_MEMBER_OFFSET_INIT(page_offset, "page", "offset"); -@@ -763,6 +769,9 @@ vm_init(void) - if (INVALID_MEMBER(page_slab)) - ANON_MEMBER_OFFSET_INIT(page_slab, "page", "slab_cache"); - } -+ if (INVALID_MEMBER(page_slab)) -+ MEMBER_OFFSET_INIT(page_slab, "slab", "slab_cache"); -+ - MEMBER_OFFSET_INIT(page_slab_page, "page", "slab_page"); - if (INVALID_MEMBER(page_slab_page)) - ANON_MEMBER_OFFSET_INIT(page_slab_page, "page", "slab_page"); -@@ -772,10 +781,14 @@ vm_init(void) - MEMBER_OFFSET_INIT(page_freelist, "page", "freelist"); - if (INVALID_MEMBER(page_freelist)) - ANON_MEMBER_OFFSET_INIT(page_freelist, "page", "freelist"); -+ if (INVALID_MEMBER(page_freelist)) -+ MEMBER_OFFSET_INIT(page_freelist, "slab", "freelist"); - if (INVALID_MEMBER(kmem_cache_objects)) { - MEMBER_OFFSET_INIT(kmem_cache_oo, "kmem_cache", "oo"); - /* NOTE: returns offset of containing bitfield */ - ANON_MEMBER_OFFSET_INIT(page_objects, "page", "objects"); -+ if (INVALID_MEMBER(page_objects)) -+ ANON_MEMBER_OFFSET_INIT(page_objects, "slab", "objects"); - } - if (VALID_MEMBER(kmem_cache_node)) { - ARRAY_LENGTH_INIT(len, NULL, "kmem_cache.node", NULL, 0); --- -2.20.1 - diff --git a/SOURCES/0012-Doc-update-man-page-for-the-bpf-and-sbitmapq-command.patch b/SOURCES/0012-Doc-update-man-page-for-the-bpf-and-sbitmapq-command.patch new file mode 100644 index 0000000..fc436ae --- /dev/null +++ b/SOURCES/0012-Doc-update-man-page-for-the-bpf-and-sbitmapq-command.patch @@ -0,0 +1,43 @@ +From c672d7a4c290712b32c54329cbdc1e74d122e813 Mon Sep 17 00:00:00 2001 +From: Lianbo Jiang +Date: Mon, 6 Jun 2022 19:09:16 +0800 +Subject: [PATCH 12/18] Doc: update man page for the "bpf" and "sbitmapq" + commands + +The information of the "bpf" and "sbitmapq" commands is missing in the man +page of the crash utility. Let's add it to the man page. + +Signed-off-by: Lianbo Jiang +--- + crash.8 | 8 ++++++++ + 1 file changed, 8 insertions(+) + +diff --git a/crash.8 b/crash.8 +index 1f3657b11e4c..e553a0b4adb3 100644 +--- a/crash.8 ++++ b/crash.8 +@@ -584,6 +584,9 @@ creates a single-word alias for a command. + .I ascii + displays an ascii chart or translates a numeric value into its ascii components. + .TP ++.I bpf ++provides information on currently-loaded eBPF programs and maps. ++.TP + .I bt + displays a task's kernel-stack backtrace. If it is given the + .I \-a +@@ -706,6 +709,11 @@ number of seconds between each command execution. + .I runq + displays the tasks on the run queue. + .TP ++.I sbitmapq ++dumps the contents of the sbitmap_queue structure and the used ++bits in the bitmap. Also, it shows the dump of a structure array ++associated with the sbitmap_queue. ++.TP + .I search + searches a range of user or kernel memory space for given value. + .TP +-- +2.30.2 + diff --git a/SOURCES/0013-sbitmapq-Fix-for-sbitmap_queue-without-ws_active-mem.patch b/SOURCES/0013-sbitmapq-Fix-for-sbitmap_queue-without-ws_active-mem.patch new file mode 100644 index 0000000..c9d7b95 --- /dev/null +++ b/SOURCES/0013-sbitmapq-Fix-for-sbitmap_queue-without-ws_active-mem.patch @@ -0,0 +1,48 @@ +From 9ce31a14d1083cbb2beb4a8e6eb7b88234b79a99 Mon Sep 17 00:00:00 2001 +From: Kazuhito Hagio +Date: Fri, 10 Jun 2022 11:49:47 +0900 +Subject: [PATCH 13/18] sbitmapq: Fix for sbitmap_queue without ws_active + member + +The sbitmap_queue.ws_active member was added by kernel commit 5d2ee7122c73 +("sbitmap: optimize wakeup check") at Linux 5.0. Without the patch, on +earlier kernels the "sbitmapq" command fails with the following error: + + crash> sbitmapq ffff8f1a3611cf10 + + sbitmapq: invalid structure member offset: sbitmap_queue_ws_active + FILE: sbitmap.c LINE: 393 FUNCTION: sbitmap_queue_context_load() + +Signed-off-by: Kazuhito Hagio +Signed-off-by: Lianbo Jiang +--- + sbitmap.c | 6 ++++-- + 1 file changed, 4 insertions(+), 2 deletions(-) + +diff --git a/sbitmap.c b/sbitmap.c +index e8ebd62fe01c..152c28e6875f 100644 +--- a/sbitmap.c ++++ b/sbitmap.c +@@ -325,7 +325,8 @@ static void sbitmap_queue_show(const struct sbitmap_queue_context *sqc, + + fprintf(fp, "wake_batch = %u\n", sqc->wake_batch); + fprintf(fp, "wake_index = %d\n", sqc->wake_index); +- fprintf(fp, "ws_active = %d\n", sqc->ws_active); ++ if (VALID_MEMBER(sbitmap_queue_ws_active)) /* 5.0 and later */ ++ fprintf(fp, "ws_active = %d\n", sqc->ws_active); + + sbq_wait_state_size = SIZE(sbq_wait_state); + wait_cnt_off = OFFSET(sbq_wait_state_wait_cnt); +@@ -380,7 +381,8 @@ static void sbitmap_queue_context_load(ulong addr, struct sbitmap_queue_context + sqc->wake_batch = UINT(sbitmap_queue_buf + OFFSET(sbitmap_queue_wake_batch)); + sqc->wake_index = INT(sbitmap_queue_buf + OFFSET(sbitmap_queue_wake_index)); + sqc->ws_addr = ULONG(sbitmap_queue_buf + OFFSET(sbitmap_queue_ws)); +- sqc->ws_active = INT(sbitmap_queue_buf + OFFSET(sbitmap_queue_ws_active)); ++ if (VALID_MEMBER(sbitmap_queue_ws_active)) ++ sqc->ws_active = INT(sbitmap_queue_buf + OFFSET(sbitmap_queue_ws_active)); + if (VALID_MEMBER(sbitmap_queue_round_robin)) + sqc->round_robin = BOOL(sbitmap_queue_buf + OFFSET(sbitmap_queue_round_robin)); + sqc->min_shallow_depth = UINT(sbitmap_queue_buf + OFFSET(sbitmap_queue_min_shallow_depth)); +-- +2.30.2 + diff --git a/SOURCES/0014-sbitmapq-Fix-for-sbitmap_word-without-cleared-member.patch b/SOURCES/0014-sbitmapq-Fix-for-sbitmap_word-without-cleared-member.patch new file mode 100644 index 0000000..6018402 --- /dev/null +++ b/SOURCES/0014-sbitmapq-Fix-for-sbitmap_word-without-cleared-member.patch @@ -0,0 +1,110 @@ +From 0d3e86fee5eead93b521a0e20a0e099ede4ab72b Mon Sep 17 00:00:00 2001 +From: Kazuhito Hagio +Date: Fri, 10 Jun 2022 11:49:47 +0900 +Subject: [PATCH 14/18] sbitmapq: Fix for sbitmap_word without cleared member + +The sbitmap_word.cleared member was added by kernel commit ea86ea2cdced +("sbitmap: ammortize cost of clearing bits") at Linux 5.0. Without the +patch, on earlier kernels the "sbitmapq" command fails with the +following error: + + crash> sbitmapq ffff8f1a3611cf10 + + sbitmapq: invalid structure member offset: sbitmap_word_cleared + FILE: sbitmap.c LINE: 92 FUNCTION: __sbitmap_weight() + +Signed-off-by: Kazuhito Hagio +Signed-off-by: Lianbo Jiang +--- + sbitmap.c | 26 ++++++++++++++++++-------- + 1 file changed, 18 insertions(+), 8 deletions(-) + +diff --git a/sbitmap.c b/sbitmap.c +index 152c28e6875f..c9f7209f9e3e 100644 +--- a/sbitmap.c ++++ b/sbitmap.c +@@ -89,7 +89,6 @@ static unsigned int __sbitmap_weight(const struct sbitmap_context *sc, bool set) + { + const ulong sbitmap_word_size = SIZE(sbitmap_word); + const ulong w_word_off = OFFSET(sbitmap_word_word); +- const ulong w_cleared_off = OFFSET(sbitmap_word_cleared); + + unsigned int weight = 0; + ulong addr = sc->map_addr; +@@ -111,7 +110,10 @@ static unsigned int __sbitmap_weight(const struct sbitmap_context *sc, bool set) + word = ULONG(sbitmap_word_buf + w_word_off); + weight += bitmap_weight(word, depth); + } else { +- cleared = ULONG(sbitmap_word_buf + w_cleared_off); ++ if (VALID_MEMBER(sbitmap_word_cleared)) ++ cleared = ULONG(sbitmap_word_buf + OFFSET(sbitmap_word_cleared)); ++ else ++ cleared = 0; + weight += bitmap_weight(cleared, depth); + } + +@@ -130,7 +132,10 @@ static unsigned int sbitmap_weight(const struct sbitmap_context *sc) + + static unsigned int sbitmap_cleared(const struct sbitmap_context *sc) + { +- return __sbitmap_weight(sc, false); ++ if (VALID_MEMBER(sbitmap_word_cleared)) /* 5.0 and later */ ++ return __sbitmap_weight(sc, false); ++ ++ return 0; + } + + static void sbitmap_emit_byte(unsigned int offset, uint8_t byte) +@@ -149,7 +154,6 @@ static void sbitmap_bitmap_show(const struct sbitmap_context *sc) + { + const ulong sbitmap_word_size = SIZE(sbitmap_word); + const ulong w_word_off = OFFSET(sbitmap_word_word); +- const ulong w_cleared_off = OFFSET(sbitmap_word_cleared); + + uint8_t byte = 0; + unsigned int byte_bits = 0; +@@ -169,7 +173,10 @@ static void sbitmap_bitmap_show(const struct sbitmap_context *sc) + } + + word = ULONG(sbitmap_word_buf + w_word_off); +- cleared = ULONG(sbitmap_word_buf + w_cleared_off); ++ if (VALID_MEMBER(sbitmap_word_cleared)) ++ cleared = ULONG(sbitmap_word_buf + OFFSET(sbitmap_word_cleared)); ++ else ++ cleared = 0; + word_bits = __map_depth(sc, i); + + word &= ~cleared; +@@ -219,7 +226,6 @@ static void __sbitmap_for_each_set(const struct sbitmap_context *sc, + { + const ulong sbitmap_word_size = SIZE(sbitmap_word); + const ulong w_word_off = OFFSET(sbitmap_word_word); +- const ulong w_cleared_off = OFFSET(sbitmap_word_cleared); + + unsigned int index; + unsigned int nr; +@@ -245,7 +251,10 @@ static void __sbitmap_for_each_set(const struct sbitmap_context *sc, + } + + w_word = ULONG(sbitmap_word_buf + w_word_off); +- w_cleared = ULONG(sbitmap_word_buf + w_cleared_off); ++ if (VALID_MEMBER(sbitmap_word_cleared)) ++ w_cleared = ULONG(sbitmap_word_buf + OFFSET(sbitmap_word_cleared)); ++ else ++ w_cleared = 0; + + depth = min(__map_depth(sc, index) - nr, sc->depth - scanned); + +@@ -297,7 +306,8 @@ static void sbitmap_queue_show(const struct sbitmap_queue_context *sqc, + + fprintf(fp, "depth = %u\n", sc->depth); + fprintf(fp, "busy = %u\n", sbitmap_weight(sc) - sbitmap_cleared(sc)); +- fprintf(fp, "cleared = %u\n", sbitmap_cleared(sc)); ++ if (VALID_MEMBER(sbitmap_word_cleared)) /* 5.0 and later */ ++ fprintf(fp, "cleared = %u\n", sbitmap_cleared(sc)); + fprintf(fp, "bits_per_word = %u\n", 1U << sc->shift); + fprintf(fp, "map_nr = %u\n", sc->map_nr); + +-- +2.30.2 + diff --git a/SOURCES/0015-sbitmapq-Fix-for-sbitmap_queue-without-min_shallow_d.patch b/SOURCES/0015-sbitmapq-Fix-for-sbitmap_queue-without-min_shallow_d.patch new file mode 100644 index 0000000..3871a6f --- /dev/null +++ b/SOURCES/0015-sbitmapq-Fix-for-sbitmap_queue-without-min_shallow_d.patch @@ -0,0 +1,49 @@ +From 12fe6c7cdd768f87ce6e903a2bbfb0c0591585c5 Mon Sep 17 00:00:00 2001 +From: Kazuhito Hagio +Date: Fri, 10 Jun 2022 11:49:47 +0900 +Subject: [PATCH 15/18] sbitmapq: Fix for sbitmap_queue without + min_shallow_depth member + +The sbitmap_queue.min_shallow_depth member was added by kernel commit +a327553965de ("sbitmap: fix missed wakeups caused by sbitmap_queue_get_shallow()") +at Linux 4.18. Without the patch, on earlier kernels the "sbitmapq" +command fails with the following error: + + crash> sbitmapq ffff89bb7638ee50 + + sbitmapq: invalid structure member offset: sbitmap_queue_min_shallow_depth + FILE: sbitmap.c LINE: 398 FUNCTION: sbitmap_queue_context_load() + +Signed-off-by: Kazuhito Hagio +Signed-off-by: Lianbo Jiang +--- + sbitmap.c | 6 ++++-- + 1 file changed, 4 insertions(+), 2 deletions(-) + +diff --git a/sbitmap.c b/sbitmap.c +index c9f7209f9e3e..bb2f19e6207b 100644 +--- a/sbitmap.c ++++ b/sbitmap.c +@@ -371,7 +371,8 @@ static void sbitmap_queue_show(const struct sbitmap_queue_context *sqc, + else if (VALID_MEMBER(sbitmap_round_robin)) /* 5.13 and later */ + fprintf(fp, "round_robin = %d\n", sc->round_robin); + +- fprintf(fp, "min_shallow_depth = %u\n", sqc->min_shallow_depth); ++ if (VALID_MEMBER(sbitmap_queue_min_shallow_depth)) /* 4.18 and later */ ++ fprintf(fp, "min_shallow_depth = %u\n", sqc->min_shallow_depth); + } + + static void sbitmap_queue_context_load(ulong addr, struct sbitmap_queue_context *sqc) +@@ -395,7 +396,8 @@ static void sbitmap_queue_context_load(ulong addr, struct sbitmap_queue_context + sqc->ws_active = INT(sbitmap_queue_buf + OFFSET(sbitmap_queue_ws_active)); + if (VALID_MEMBER(sbitmap_queue_round_robin)) + sqc->round_robin = BOOL(sbitmap_queue_buf + OFFSET(sbitmap_queue_round_robin)); +- sqc->min_shallow_depth = UINT(sbitmap_queue_buf + OFFSET(sbitmap_queue_min_shallow_depth)); ++ if (VALID_MEMBER(sbitmap_queue_min_shallow_depth)) ++ sqc->min_shallow_depth = UINT(sbitmap_queue_buf + OFFSET(sbitmap_queue_min_shallow_depth)); + + FREEBUF(sbitmap_queue_buf); + } +-- +2.30.2 + diff --git a/SOURCES/0016-Make-dev-d-D-options-parse-sbitmap-on-Linux-4.18-and.patch b/SOURCES/0016-Make-dev-d-D-options-parse-sbitmap-on-Linux-4.18-and.patch new file mode 100644 index 0000000..cc88afd --- /dev/null +++ b/SOURCES/0016-Make-dev-d-D-options-parse-sbitmap-on-Linux-4.18-and.patch @@ -0,0 +1,84 @@ +From c07068266b41450ca6821ee0a1a3adf34206015f Mon Sep 17 00:00:00 2001 +From: Kazuhito Hagio +Date: Fri, 10 Jun 2022 15:21:53 +0900 +Subject: [PATCH 16/18] Make "dev -d|-D" options parse sbitmap on Linux 4.18 + and later + +There have been a few reports that the "dev -d|-D" options displayed +incorrect I/O stats due to racy blk_mq_ctx.rq_* counters. To fix it, +make the options parse sbitmap to count I/O stats on Linux 4.18 and +later kernels, which include RHEL8 ones. + +To do this, adjust to the blk_mq_tags structure of Linux 5.10 through +5.15 kernels, which contain kernel commit 222a5ae03cdd ("blk-mq: Use +pointers for blk_mq_tags bitmap tags") and do not contain ae0f1a732f4a +("blk-mq: Stop using pointers for blk_mq_tags bitmap tags"). + +Signed-off-by: Kazuhito Hagio +Signed-off-by: Lianbo Jiang +--- + dev.c | 25 +++++++++++++++++++++++-- + 1 file changed, 23 insertions(+), 2 deletions(-) + +diff --git a/dev.c b/dev.c +index 0172c83ffaea..db97f8aebdc2 100644 +--- a/dev.c ++++ b/dev.c +@@ -4339,6 +4339,10 @@ static void bt_for_each(ulong q, ulong tags, ulong sbq, uint reserved, uint nr_r + static void queue_for_each_hw_ctx(ulong q, ulong *hctx, uint cnt, struct diskio *dio) + { + uint i; ++ int bitmap_tags_is_ptr = 0; ++ ++ if (MEMBER_TYPE("blk_mq_tags", "bitmap_tags") == TYPE_CODE_PTR) ++ bitmap_tags_is_ptr = 1; + + for (i = 0; i < cnt; i++) { + ulong addr = 0, tags = 0; +@@ -4357,9 +4361,17 @@ static void queue_for_each_hw_ctx(ulong q, ulong *hctx, uint cnt, struct diskio + + if (nr_reserved_tags) { + addr = tags + OFFSET(blk_mq_tags_breserved_tags); ++ if (bitmap_tags_is_ptr && ++ !readmem(addr, KVADDR, &addr, sizeof(ulong), ++ "blk_mq_tags.bitmap_tags", RETURN_ON_ERROR)) ++ break; + bt_for_each(q, tags, addr, 1, nr_reserved_tags, dio); + } + addr = tags + OFFSET(blk_mq_tags_bitmap_tags); ++ if (bitmap_tags_is_ptr && ++ !readmem(addr, KVADDR, &addr, sizeof(ulong), ++ "blk_mq_tags.bitmap_tags", RETURN_ON_ERROR)) ++ break; + bt_for_each(q, tags, addr, 0, nr_reserved_tags, dio); + } + } +@@ -4423,14 +4435,23 @@ get_mq_diskio(unsigned long q, unsigned long *mq_count) + unsigned long mctx_addr; + struct diskio tmp = {0}; + +- if (INVALID_MEMBER(blk_mq_ctx_rq_dispatched) || +- INVALID_MEMBER(blk_mq_ctx_rq_completed)) { ++ /* ++ * Currently this function does not support old blk-mq implementation ++ * before 12f5b9314545 ("blk-mq: Remove generation seqeunce"), so ++ * filter them out. ++ */ ++ if (VALID_MEMBER(request_state)) { ++ if (CRASHDEBUG(1)) ++ fprintf(fp, "mq: using sbitmap\n"); + get_mq_diskio_from_hw_queues(q, &tmp); + mq_count[0] = tmp.read; + mq_count[1] = tmp.write; + return; + } + ++ if (CRASHDEBUG(1)) ++ fprintf(fp, "mq: using blk_mq_ctx.rq_{completed,dispatched} counters\n"); ++ + readmem(q + OFFSET(request_queue_queue_ctx), KVADDR, &queue_ctx, + sizeof(ulong), "request_queue.queue_ctx", + FAULT_ON_ERROR); +-- +2.30.2 + diff --git a/SOURCES/0017-sbitmapq-Fix-for-kernels-without-struct-wait_queue_h.patch b/SOURCES/0017-sbitmapq-Fix-for-kernels-without-struct-wait_queue_h.patch new file mode 100644 index 0000000..fe4a544 --- /dev/null +++ b/SOURCES/0017-sbitmapq-Fix-for-kernels-without-struct-wait_queue_h.patch @@ -0,0 +1,44 @@ +From 6bc3b74c6e2b0aaebe1bc164594e53b010efef56 Mon Sep 17 00:00:00 2001 +From: Kazuhito Hagio +Date: Fri, 10 Jun 2022 15:52:34 +0900 +Subject: [PATCH 17/18] sbitmapq: Fix for kernels without struct + wait_queue_head + +The current struct wait_queue_head was renamed by kernel commit +9d9d676f595b ("sched/wait: Standardize internal naming of wait-queue heads") +at Linux 4.13. Without the patch, on earlier kernels the "sbitmapq" +command fails with the following error: + + crash> sbitmapq ffff8801790b3b50 + depth = 128 + busy = 0 + bits_per_word = 32 + ... + sbitmapq: invalid structure member offset: wait_queue_head_head + FILE: sbitmap.c LINE: 344 FUNCTION: sbitmap_queue_show() + +Signed-off-by: Kazuhito Hagio +Signed-off-by: Lianbo Jiang +--- + sbitmap.c | 5 ++++- + 1 file changed, 4 insertions(+), 1 deletion(-) + +diff --git a/sbitmap.c b/sbitmap.c +index bb2f19e6207b..be5d30a8ea88 100644 +--- a/sbitmap.c ++++ b/sbitmap.c +@@ -341,7 +341,10 @@ static void sbitmap_queue_show(const struct sbitmap_queue_context *sqc, + sbq_wait_state_size = SIZE(sbq_wait_state); + wait_cnt_off = OFFSET(sbq_wait_state_wait_cnt); + wait_off = OFFSET(sbq_wait_state_wait); +- list_head_off = OFFSET(wait_queue_head_head); ++ if (VALID_MEMBER(wait_queue_head_head)) /* 4.13 and later */ ++ list_head_off = OFFSET(wait_queue_head_head); ++ else ++ list_head_off = OFFSET(__wait_queue_head_task_list); + + sbq_wait_state_buf = GETBUF(sbq_wait_state_size); + +-- +2.30.2 + diff --git a/SOURCES/0018-sbitmapq-Limit-kernels-without-sbitmap-again.patch b/SOURCES/0018-sbitmapq-Limit-kernels-without-sbitmap-again.patch new file mode 100644 index 0000000..791e5ab --- /dev/null +++ b/SOURCES/0018-sbitmapq-Limit-kernels-without-sbitmap-again.patch @@ -0,0 +1,43 @@ +From b8f2ae6b494d706b1e4855b439c4930a6a6a2f5c Mon Sep 17 00:00:00 2001 +From: Kazuhito Hagio +Date: Fri, 10 Jun 2022 16:00:14 +0900 +Subject: [PATCH 18/18] sbitmapq: Limit kernels without sbitmap again + +commit 364b2e413c69 ("sbitmapq: remove struct and member validation +in sbitmapq_init()") allowed the use of the "sbitmapq" command +unconditionally. Without the patch, the command fails with the +following error on kernels without sbitmap: + + crash> sbitmapq ffff88015796e550 + + sbitmapq: invalid structure member offset: sbitmap_queue_sb + FILE: sbitmap.c LINE: 385 FUNCTION: sbitmap_queue_context_load() + +Now the command supports Linux 4.9 and later kernels since it was +abstracted out, so it can be limited by the non-existence of the +sbitmap structure. + +Signed-off-by: Kazuhito Hagio +Signed-off-by: Lianbo Jiang +--- + sbitmap.c | 4 ++++ + 1 file changed, 4 insertions(+) + +diff --git a/sbitmap.c b/sbitmap.c +index be5d30a8ea88..12d6512a1e4d 100644 +--- a/sbitmap.c ++++ b/sbitmap.c +@@ -540,6 +540,10 @@ void sbitmapq_init(void) + STRUCT_SIZE_INIT(sbitmap_queue, "sbitmap_queue"); + STRUCT_SIZE_INIT(sbq_wait_state, "sbq_wait_state"); + ++ /* sbitmap was abstracted out by commit 88459642cba4 on Linux 4.9. */ ++ if (INVALID_SIZE(sbitmap)) ++ command_not_supported(); ++ + MEMBER_OFFSET_INIT(sbitmap_word_depth, "sbitmap_word", "depth"); + MEMBER_OFFSET_INIT(sbitmap_word_word, "sbitmap_word", "word"); + MEMBER_OFFSET_INIT(sbitmap_word_cleared, "sbitmap_word", "cleared"); +-- +2.30.2 + diff --git a/SOURCES/lzo_snappy_zstd.patch b/SOURCES/lzo_snappy_zstd.patch index 4813ed0..bc38234 100644 --- a/SOURCES/lzo_snappy_zstd.patch +++ b/SOURCES/lzo_snappy_zstd.patch @@ -1,16 +1,16 @@ ---- crash-7.3.1/Makefile.orig -+++ crash-7.3.1/Makefile -@@ -230,7 +230,7 @@ all: make_configure +--- crash-7.3.2/Makefile.orig ++++ crash-7.3.2/Makefile +@@ -253,7 +253,7 @@ all: make_configure gdb_merge: force @if [ ! -f ${GDB}/README ]; then \ - make --no-print-directory gdb_unzip; fi + $(MAKE) gdb_unzip; fi - @echo "${LDFLAGS} -lz -ldl -rdynamic" > ${GDB}/gdb/mergelibs + @echo "${LDFLAGS} -lz -llzo2 -lsnappy -lzstd -ldl -rdynamic" > ${GDB}/gdb/mergelibs @echo "../../${PROGRAM} ../../${PROGRAM}lib.a" > ${GDB}/gdb/mergeobj @rm -f ${PROGRAM} @if [ ! -f ${GDB}/config.status ]; then \ ---- crash-7.3.1/diskdump.c.orig -+++ crash-7.3.1/diskdump.c +--- crash-7.3.2/diskdump.c.orig ++++ crash-7.3.2/diskdump.c @@ -23,6 +23,9 @@ * GNU General Public License for more details. */ @@ -21,3 +21,4 @@ #include "defs.h" #include "diskdump.h" #include "xen_dom0.h" +-- diff --git a/SOURCES/rhel8_build.patch b/SOURCES/rhel8_build.patch index 55560b8..a0ef062 100644 --- a/SOURCES/rhel8_build.patch +++ b/SOURCES/rhel8_build.patch @@ -1,6 +1,6 @@ ---- crash-7.3.1/Makefile.orig -+++ crash-7.3.1/Makefile -@@ -200,7 +200,7 @@ GDB_FLAGS= +--- crash-7.3.2/Makefile.orig ++++ crash-7.3.2/Makefile +@@ -201,7 +201,7 @@ GDB_FLAGS= # TARGET_CFLAGS will be configured automatically by configure TARGET_CFLAGS= @@ -9,17 +9,17 @@ GPL_FILES= TAR_FILES=${SOURCE_FILES} Makefile ${GPL_FILES} README .rh_rpm_package crash.8 \ -@@ -230,7 +230,7 @@ all: make_configure +@@ -253,7 +253,7 @@ all: make_configure gdb_merge: force @if [ ! -f ${GDB}/README ]; then \ - make --no-print-directory gdb_unzip; fi + $(MAKE) gdb_unzip; fi - @echo "${LDFLAGS} -lz -llzo2 -lsnappy -lzstd -ldl -rdynamic" > ${GDB}/gdb/mergelibs + @echo "${LDFLAGS} -lz -llzo2 -lsnappy -lzstd -ldl -rdynamic -Wl,-z,now -fpie" > ${GDB}/gdb/mergelibs @echo "../../${PROGRAM} ../../${PROGRAM}lib.a" > ${GDB}/gdb/mergeobj @rm -f ${PROGRAM} @if [ ! -f ${GDB}/config.status ]; then \ ---- crash-7.3.1/configure.c.orig -+++ crash-7.3.1/configure.c +--- crash-7.3.2/configure.c.orig ++++ crash-7.3.2/configure.c @@ -800,7 +800,8 @@ build_configure(struct supported_gdb_version *sp) fprintf(fp2, "%s\n", sp->GDB); sprintf(target_data.gdb_version, "%s", &sp->GDB[4]); @@ -30,3 +30,4 @@ } else fprintf(fp2, "%s", buf); +-- diff --git a/SOURCES/rhel8_freepointer.patch b/SOURCES/rhel8_freepointer.patch index e7aded5..235e532 100644 --- a/SOURCES/rhel8_freepointer.patch +++ b/SOURCES/rhel8_freepointer.patch @@ -1,18 +1,6 @@ -From e09e3c038c853f9a332cf05a17e5fdee1c7837e0 Mon Sep 17 00:00:00 2001 -From: Lianbo Jiang -Date: Thu, 18 Nov 2021 09:55:45 +0800 -Subject: [PATCH] fix freepointer issue - -Signed-off-by: Lianbo Jiang ---- - memory.c | 5 ++--- - 1 file changed, 2 insertions(+), 3 deletions(-) - -diff --git a/memory.c b/memory.c -index a3cf8a86728d..81db9c7bee9f 100644 ---- a/memory.c -+++ b/memory.c -@@ -19340,9 +19340,8 @@ freelist_ptr(struct meminfo *si, ulong ptr, ulong ptr_addr) +--- crash-7.3.2/memory.c.orig ++++ crash-7.3.2/memory.c +@@ -19412,9 +19412,8 @@ freelist_ptr(struct meminfo *si, ulong ptr, ulong ptr_addr) if (VALID_MEMBER(kmem_cache_random)) { /* CONFIG_SLAB_FREELIST_HARDENED */ @@ -25,5 +13,4 @@ index a3cf8a86728d..81db9c7bee9f 100644 } else return ptr; -- -2.30.2 - +fix freepointer issue diff --git a/SPECS/crash.spec b/SPECS/crash.spec index 52e8b12..607b80f 100644 --- a/SPECS/crash.spec +++ b/SPECS/crash.spec @@ -3,8 +3,8 @@ # Summary: Kernel analysis utility for live systems, netdump, diskdump, kdump, LKCD or mcore dumpfiles Name: crash -Version: 7.3.1 -Release: 5%{?dist} +Version: 7.3.2 +Release: 2%{?dist} License: GPLv3 Group: Development/Debuggers Source0: https://github.com/crash-utility/crash/archive/crash-%{version}.tar.gz @@ -13,25 +13,28 @@ URL: https://crash-utility.github.io ExclusiveOS: Linux ExclusiveArch: %{ix86} ia64 x86_64 ppc ppc64 s390 s390x %{arm} aarch64 ppc64le Buildroot: %{_tmppath}/%{name}-%{version}-%{release}-buildroot-%(%{__id_u} -n) -BuildRequires: ncurses-devel zlib-devel lzo-devel bison snappy-devel libzstd-devel +BuildRequires: ncurses-devel zlib-devel lzo-devel bison snappy-devel wget patch libzstd-devel Requires: binutils Provides: bundled(gdb) = 7.6 Patch0: lzo_snappy_zstd.patch Patch1: rhel8_build.patch Patch2: rhel8_freepointer.patch -Patch3: 0001-arm64-Support-overflow-stack-panic.patch -Patch4: 0002-defs.h-fix-breakage-of-compatibility-of-struct-symbo.patch -Patch5: 0001-Fix-pvops-Xen-detection-for-arm-machine.patch -Patch6: 0002-Handle-blk_mq_ctx-member-changes-for-kernels-5.16-rc.patch -Patch7: 0003-Fix-for-timer-r-option-to-display-all-the-per-CPU-cl.patch -Patch8: 0004-Fix-for-bt-v-option-to-display-the-stack-end-address.patch -Patch9: 0005-Fix-for-HZ-calculation-on-Linux-5.14-and-later.patch -Patch10: 0006-memory-Handle-struct-slab-changes-on-Linux-5.17-rc1-.patch -Patch11: 0007-Move-the-initialization-of-boot_date-to-task_init.patch -Patch12: 0008-Remove-ptype-command-from-ps-t-option-to-reduce-memo.patch -Patch13: 0009-Improve-the-ps-performance-for-vmcores-with-large-nu.patch -Patch14: 0010-arm64-Fix-segfault-by-bt-command-with-offline-cpus.patch -Patch15: 0011-Fix-for-kmem-s-S-and-bt-F-F-on-Linux-5.17-rc1.patch +Patch3: 0001-ppc64-update-the-NR_CPUS-to-8192.patch +Patch4: 0002-sbitmapq-remove-struct-and-member-validation-in-sbit.patch +Patch5: 0003-sbitmapq-fix-invalid-offset-for-sbitmap_queue_alloc_.patch +Patch6: 0004-sbitmapq-fix-invalid-offset-for-sbitmap_queue_round_.patch +Patch7: 0005-sbitmapq-fix-invalid-offset-for-sbitmap_word_depth-o.patch +Patch8: 0007-bt-x86_64-filter-out-idle-task-stack.patch +Patch9: 0008-bt-arm64-add-support-for-bt-n-idle.patch +Patch10: 0010-Enhance-dev-d-D-options-to-support-blk-mq-sbitmap.patch +Patch11: 0011-Fix-for-dev-d-D-options-to-support-blk-mq-change-on-.patch +Patch12: 0012-Doc-update-man-page-for-the-bpf-and-sbitmapq-command.patch +Patch13: 0013-sbitmapq-Fix-for-sbitmap_queue-without-ws_active-mem.patch +Patch14: 0014-sbitmapq-Fix-for-sbitmap_word-without-cleared-member.patch +Patch15: 0015-sbitmapq-Fix-for-sbitmap_queue-without-min_shallow_d.patch +Patch16: 0016-Make-dev-d-D-options-parse-sbitmap-on-Linux-4.18-and.patch +Patch17: 0017-sbitmapq-Fix-for-kernels-without-struct-wait_queue_h.patch +Patch18: 0018-sbitmapq-Limit-kernels-without-sbitmap-again.patch %description The core analysis suite is a self-contained tool that can be used to @@ -68,11 +71,14 @@ offered by Mission Critical Linux, or the LKCD kernel patch. %patch13 -p1 %patch14 -p1 %patch15 -p1 +%patch16 -p1 +%patch17 -p1 +%patch18 -p1 %build cp %{SOURCE1} . #make RPMPKG="%{version}-%{release}" CFLAGS="%{optflags}" -make RPMPKG="%{version}-%{release}" CFLAGS="%{optflags}" LDFLAGS="%{build_ldflags}" +make -j`nproc` RPMPKG="%{version}-%{release}" CFLAGS="%{optflags}" LDFLAGS="%{build_ldflags}" %install rm -rf %{buildroot} @@ -98,6 +104,12 @@ rm -rf %{buildroot} %{_includedir}/* %changelog +* Thu Jun 16 2022 Lianbo Jiang - 7.3.2-2 +- Enhance "dev -d|-D" options to support blk-mq sbitmap + +* Mon May 16 2022 Lianbo Jiang - 7.3.2-1 +- Rebase to upstream crash 7.3.2 + * Tue Feb 08 2022 Lianbo Jiang - 7.3.1-5 - Rebuild for osci badfuncs issue