20 changed files with 1354 additions and 1077 deletions
-
2.crash.metadata
-
2.gitignore
-
70SOURCES/0001-Fix-pvops-Xen-detection-for-arm-machine.patch
-
379SOURCES/0001-arm64-Support-overflow-stack-panic.patch
-
101SOURCES/0002-Handle-blk_mq_ctx-member-changes-for-kernels-5.16-rc.patch
-
41SOURCES/0002-defs.h-fix-breakage-of-compatibility-of-struct-symbo.patch
-
59SOURCES/0003-Fix-for-timer-r-option-to-display-all-the-per-CPU-cl.patch
-
69SOURCES/0004-Fix-for-bt-v-option-to-display-the-stack-end-address.patch
-
35SOURCES/0005-Fix-for-HZ-calculation-on-Linux-5.14-and-later.patch
-
40SOURCES/0006-memory-Handle-struct-slab-changes-on-Linux-5.17-rc1-.patch
-
75SOURCES/0007-Move-the-initialization-of-boot_date-to-task_init.patch
-
79SOURCES/0008-Remove-ptype-command-from-ps-t-option-to-reduce-memo.patch
-
150SOURCES/0009-Improve-the-ps-performance-for-vmcores-with-large-nu.patch
-
59SOURCES/0010-arm64-Fix-segfault-by-bt-command-with-offline-cpus.patch
-
89SOURCES/0011-Fix-for-kmem-s-S-and-bt-F-F-on-Linux-5.17-rc1.patch
-
19SOURCES/lzo_snappy_zstd.patch
-
1043SOURCES/rhel8_arm64_52_bit_fix.patch
-
23SOURCES/rhel8_build.patch
-
29SOURCES/rhel8_freepointer.patch
-
67SPECS/crash.spec
@ -1,2 +1,2 @@ |
|||
35a06244e58606ebf2b5612fbfcb51301bd5877a SOURCES/crash-7.3.0.tar.gz |
|||
f230368e17058e61a0be4c22f0969bed76cd6c29 SOURCES/crash-7.3.1.tar.gz |
|||
026f4c9e1c8152a2773354551c523acd32d7f00e SOURCES/gdb-7.6.tar.gz |
@ -1,2 +1,2 @@ |
|||
SOURCES/crash-7.3.0.tar.gz |
|||
SOURCES/crash-7.3.1.tar.gz |
|||
SOURCES/gdb-7.6.tar.gz |
@ -0,0 +1,70 @@ |
|||
From 5c4f786450ea61b87d4db0092288df83dd5cb454 Mon Sep 17 00:00:00 2001 |
|||
From: Qi Zheng <zhengqi.arch@bytedance.com> |
|||
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 <zhengqi.arch@bytedance.com> |
|||
Acked-by: Kazuhito Hagio <k-hagio-ab@nec.com> |
|||
Signed-off-by: Lianbo Jiang <lijiang@redhat.com> |
|||
---
|
|||
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 |
|||
|
@ -0,0 +1,379 @@ |
|||
From c05db8d7d83389a342664073547bd29eda900158 Mon Sep 17 00:00:00 2001 |
|||
From: Hong YANG <hong.yang3@nio.com> |
|||
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 <hong.yang3@nio.com> |
|||
---
|
|||
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, "--- <Overflow stack> ---\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 |
|||
|
@ -0,0 +1,101 @@ |
|||
From 78255e3b33f8d51eb893e662dd1b05a008246b9d Mon Sep 17 00:00:00 2001 |
|||
From: Lianbo Jiang <lijiang@redhat.com> |
|||
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 <lijiang@redhat.com> |
|||
Signed-off-by: Kazuhito Hagio <k-hagio-ab@nec.com> |
|||
---
|
|||
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 |
|||
|
@ -0,0 +1,41 @@ |
|||
From a0eec39c14ee1db95a6c1a649a8f69b97e260dc6 Mon Sep 17 00:00:00 2001 |
|||
From: HATAYAMA Daisuke <d.hatayama@fujitsu.com> |
|||
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 <d.hatayama@fujitsu.com> |
|||
---
|
|||
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 |
|||
|
@ -0,0 +1,59 @@ |
|||
From c48177972f351d7853abb2a57709628c75ee38bc Mon Sep 17 00:00:00 2001 |
|||
From: Lianbo Jiang <lijiang@redhat.com> |
|||
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 <lijiang@redhat.com> |
|||
---
|
|||
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 |
|||
|
@ -0,0 +1,69 @@ |
|||
From 1706f8b6ab50cd25e8fdabe8d50a37ce89bd60e0 Mon Sep 17 00:00:00 2001 |
|||
From: Lianbo Jiang <lijiang@redhat.com> |
|||
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 <lijiang@redhat.com> |
|||
---
|
|||
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 |
|||
|
@ -0,0 +1,35 @@ |
|||
From f5637f341533ef2b28e2d6a6b12fcfb00d0fff2d Mon Sep 17 00:00:00 2001 |
|||
From: Lianbo Jiang <lijiang@redhat.com> |
|||
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 <lijiang@redhat.com> |
|||
---
|
|||
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 |
|||
|
@ -0,0 +1,40 @@ |
|||
From a392b27653e4e75460753522af0f006006b4dc4e Mon Sep 17 00:00:00 2001 |
|||
From: Alexander Egorenkov <egorenar@linux.ibm.com> |
|||
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 <egorenar@linux.ibm.com> |
|||
Signed-off-by: Lianbo Jiang <lijiang@redhat.com> |
|||
---
|
|||
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 |
|||
|
@ -0,0 +1,75 @@ |
|||
From fa0b6453a05c5600849e4e531c94594ed9c90270 Mon Sep 17 00:00:00 2001 |
|||
From: Lianbo Jiang <lijiang@redhat.com> |
|||
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 <lijiang@redhat.com> |
|||
---
|
|||
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 |
|||
|
@ -0,0 +1,79 @@ |
|||
From bbd5a5c1f5db3bde04628e75396155260333e53e Mon Sep 17 00:00:00 2001 |
|||
From: Kazuhito Hagio <k-hagio-ab@nec.com> |
|||
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 <k-hagio-ab@nec.com> |
|||
Signed-off-by: Lianbo Jiang <lijiang@redhat.com> |
|||
---
|
|||
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 |
|||
|
@ -0,0 +1,150 @@ |
|||
From d52cccfaa96ed6f61ff9d53da88715296e31db80 Mon Sep 17 00:00:00 2001 |
|||
From: Tao Liu <ltao@redhat.com> |
|||
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 <ltao@redhat.com> |
|||
Signed-off-by: Lianbo Jiang <lijiang@redhat.com> |
|||
---
|
|||
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 |
|||
|
@ -0,0 +1,59 @@ |
|||
From 1a1fd21c625cb2ca335e626eb50426f13c4160f7 Mon Sep 17 00:00:00 2001 |
|||
From: Kazuhito Hagio <k-hagio-ab@nec.com> |
|||
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 <xuchunmei@linux.alibaba.com> |
|||
Signed-off-by: Kazuhito Hagio <k-hagio-ab@nec.com> |
|||
Tested-by: David Wysochanski <dwysocha@redhat.com> |
|||
Signed-off-by: Lianbo Jiang <lijiang@redhat.com> |
|||
---
|
|||
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 |
|||
|
@ -0,0 +1,89 @@ |
|||
From 86446eaba408807e00cf2310d5748aa6b7511284 Mon Sep 17 00:00:00 2001 |
|||
From: Kazuhito Hagio <k-hagio-ab@nec.com> |
|||
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 <k-hagio-ab@nec.com> |
|||
Signed-off-by: Lianbo Jiang <lijiang@redhat.com> |
|||
---
|
|||
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 |
|||
|
@ -1,26 +1,23 @@ |
|||
diff --git crash-7.3.0/Makefile crash-7.3.0/Makefile
|
|||
index 745541012f43..d0574d8f07d3 100644
|
|||
--- crash-7.3.0/Makefile
|
|||
+++ crash-7.3.0/Makefile
|
|||
@@ -228,7 +228,7 @@ all: make_configure
|
|||
--- crash-7.3.1/Makefile.orig
|
|||
+++ crash-7.3.1/Makefile
|
|||
@@ -230,7 +230,7 @@ all: make_configure
|
|||
gdb_merge: force |
|||
@if [ ! -f ${GDB}/README ]; then \ |
|||
make --no-print-directory gdb_unzip; fi |
|||
- @echo "${LDFLAGS} -lz -ldl -rdynamic" > ${GDB}/gdb/mergelibs
|
|||
+ @echo "${LDFLAGS} -lz -llzo2 -lsnappy -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 \ |
|||
diff --git crash-7.3.0/diskdump.c crash-7.3.0/diskdump.c
|
|||
index e88243e616cc..9ccf7039231b 100644
|
|||
--- crash-7.3.0/diskdump.c
|
|||
+++ crash-7.3.0/diskdump.c
|
|||
@@ -23,6 +23,8 @@
|
|||
--- crash-7.3.1/diskdump.c.orig
|
|||
+++ crash-7.3.1/diskdump.c
|
|||
@@ -23,6 +23,9 @@
|
|||
* GNU General Public License for more details. |
|||
*/ |
|||
|
|||
+#define LZO
|
|||
+#define SNAPPY
|
|||
+#define ZSTD
|
|||
#include "defs.h" |
|||
#include "diskdump.h" |
|||
#include "xen_dom0.h" |
1043
SOURCES/rhel8_arm64_52_bit_fix.patch
File diff suppressed because it is too large
View File
File diff suppressed because it is too large
View File
@ -0,0 +1,29 @@ |
|||
From e09e3c038c853f9a332cf05a17e5fdee1c7837e0 Mon Sep 17 00:00:00 2001 |
|||
From: Lianbo Jiang <lijiang@redhat.com> |
|||
Date: Thu, 18 Nov 2021 09:55:45 +0800 |
|||
Subject: [PATCH] fix freepointer issue |
|||
|
|||
Signed-off-by: Lianbo Jiang <lijiang@redhat.com> |
|||
---
|
|||
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)
|
|||
if (VALID_MEMBER(kmem_cache_random)) { |
|||
/* CONFIG_SLAB_FREELIST_HARDENED */ |
|||
|
|||
- if (THIS_KERNEL_VERSION >= LINUX(5,7,0))
|
|||
- ptr_addr = (sizeof(long) == 8) ? bswap_64(ptr_addr)
|
|||
- : bswap_32(ptr_addr);
|
|||
+ ptr_addr = (sizeof(long) == 8) ? bswap_64(ptr_addr)
|
|||
+ : bswap_32(ptr_addr);
|
|||
return (ptr ^ si->random ^ ptr_addr); |
|||
} else |
|||
return ptr; |
|||
--
|
|||
2.30.2 |
|||
|
Write
Preview
Loading…
Cancel
Save
Reference in new issue