linux/arch/arc/kernel/troubleshoot.c

248 lines
6.5 KiB
C
Raw Normal View History

/*
* Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
*/
#include <linux/ptrace.h>
#include <linux/module.h>
#include <linux/mm.h>
#include <linux/fs.h>
#include <linux/kdev_t.h>
#include <linux/proc_fs.h>
#include <linux/file.h>
#include <linux/sched/mm.h>
#include <linux/sched/debug.h>
#include <asm/arcregs.h>
#include <asm/irqflags.h>
/*
* Common routine to print scratch regs (r0-r12) or callee regs (r13-r25)
* -Prints 3 regs per line and a CR.
* -To continue, callee regs right after scratch, special handling of CR
*/
static noinline void print_reg_file(long *reg_rev, int start_num)
{
unsigned int i;
char buf[512];
int n = 0, len = sizeof(buf);
for (i = start_num; i < start_num + 13; i++) {
n += scnprintf(buf + n, len - n, "r%02u: 0x%08lx\t",
i, (unsigned long)*reg_rev);
if (((i + 1) % 3) == 0)
n += scnprintf(buf + n, len - n, "\n");
/* because pt_regs has regs reversed: r12..r0, r25..r13 */
if (is_isa_arcv2() && start_num == 0)
reg_rev++;
else
reg_rev--;
}
if (start_num != 0)
n += scnprintf(buf + n, len - n, "\n\n");
/* To continue printing callee regs on same line as scratch regs */
if (start_num == 0)
pr_info("%s", buf);
else
pr_cont("%s\n", buf);
}
static void show_callee_regs(struct callee_regs *cregs)
{
print_reg_file(&(cregs->r13), 13);
}
static void print_task_path_n_nm(struct task_struct *tsk, char *buf)
{
char *path_nm = NULL;
struct mm_struct *mm;
struct file *exe_file;
mm = get_task_mm(tsk);
if (!mm)
goto done;
exe_file = get_mm_exe_file(mm);
mmput(mm);
if (exe_file) {
path_nm = file_path(exe_file, buf, 255);
fput(exe_file);
}
done:
pr_info("Path: %s\n", !IS_ERR(path_nm) ? path_nm : "?");
}
static void show_faulting_vma(unsigned long address, char *buf)
{
struct vm_area_struct *vma;
struct inode *inode;
unsigned long ino = 0;
dev_t dev = 0;
char *nm = buf;
struct mm_struct *active_mm = current->active_mm;
/* can't use print_vma_addr() yet as it doesn't check for
* non-inclusive vma
*/
down_read(&active_mm->mmap_sem);
vma = find_vma(active_mm, address);
/* check against the find_vma( ) behaviour which returns the next VMA
* if the container VMA is not found
*/
if (vma && (vma->vm_start <= address)) {
struct file *file = vma->vm_file;
if (file) {
nm = file_path(file, buf, PAGE_SIZE - 1);
inode = file_inode(vma->vm_file);
dev = inode->i_sb->s_dev;
ino = inode->i_ino;
}
pr_info(" @off 0x%lx in [%s]\n"
" VMA: 0x%08lx to 0x%08lx\n",
vma->vm_start < TASK_UNMAPPED_BASE ?
address : address - vma->vm_start,
nm, vma->vm_start, vma->vm_end);
} else
pr_info(" @No matching VMA found\n");
up_read(&active_mm->mmap_sem);
}
static void show_ecr_verbose(struct pt_regs *regs)
{
unsigned int vec, cause_code;
unsigned long address;
pr_info("\n[ECR ]: 0x%08lx => ", regs->event);
/* For Data fault, this is data address not instruction addr */
address = current->thread.fault_address;
vec = regs->ecr_vec;
cause_code = regs->ecr_cause;
/* For DTLB Miss or ProtV, display the memory involved too */
if (vec == ECR_V_DTLB_MISS) {
pr_cont("Invalid %s @ 0x%08lx by insn @ 0x%08lx\n",
(cause_code == 0x01) ? "Read" :
((cause_code == 0x02) ? "Write" : "EX"),
address, regs->ret);
} else if (vec == ECR_V_ITLB_MISS) {
pr_cont("Insn could not be fetched\n");
} else if (vec == ECR_V_MACH_CHK) {
pr_cont("Machine Check (%s)\n", (cause_code == 0x0) ?
"Double Fault" : "Other Fatal Err");
} else if (vec == ECR_V_PROTV) {
if (cause_code == ECR_C_PROTV_INST_FETCH)
pr_cont("Execute from Non-exec Page\n");
else if (cause_code == ECR_C_PROTV_MISALIG_DATA)
pr_cont("Misaligned r/w from 0x%08lx\n", address);
else
pr_cont("%s access not allowed on page\n",
(cause_code == 0x01) ? "Read" :
((cause_code == 0x02) ? "Write" : "EX"));
} else if (vec == ECR_V_INSN_ERR) {
pr_cont("Illegal Insn\n");
#ifdef CONFIG_ISA_ARCV2
} else if (vec == ECR_V_MEM_ERR) {
if (cause_code == 0x00)
pr_cont("Bus Error from Insn Mem\n");
else if (cause_code == 0x10)
pr_cont("Bus Error from Data Mem\n");
else
pr_cont("Bus Error, check PRM\n");
#endif
} else if (vec == ECR_V_TRAP) {
if (regs->ecr_param == 5)
pr_cont("gcc generated __builtin_trap\n");
} else {
pr_cont("Check Programmer's Manual\n");
}
}
/************************************************************************
* API called by rest of kernel
***********************************************************************/
void show_regs(struct pt_regs *regs)
{
struct task_struct *tsk = current;
struct callee_regs *cregs;
char *buf;
mm: treewide: remove GFP_TEMPORARY allocation flag GFP_TEMPORARY was introduced by commit e12ba74d8ff3 ("Group short-lived and reclaimable kernel allocations") along with __GFP_RECLAIMABLE. It's primary motivation was to allow users to tell that an allocation is short lived and so the allocator can try to place such allocations close together and prevent long term fragmentation. As much as this sounds like a reasonable semantic it becomes much less clear when to use the highlevel GFP_TEMPORARY allocation flag. How long is temporary? Can the context holding that memory sleep? Can it take locks? It seems there is no good answer for those questions. The current implementation of GFP_TEMPORARY is basically GFP_KERNEL | __GFP_RECLAIMABLE which in itself is tricky because basically none of the existing caller provide a way to reclaim the allocated memory. So this is rather misleading and hard to evaluate for any benefits. I have checked some random users and none of them has added the flag with a specific justification. I suspect most of them just copied from other existing users and others just thought it might be a good idea to use without any measuring. This suggests that GFP_TEMPORARY just motivates for cargo cult usage without any reasoning. I believe that our gfp flags are quite complex already and especially those with highlevel semantic should be clearly defined to prevent from confusion and abuse. Therefore I propose dropping GFP_TEMPORARY and replace all existing users to simply use GFP_KERNEL. Please note that SLAB users with shrinkers will still get __GFP_RECLAIMABLE heuristic and so they will be placed properly for memory fragmentation prevention. I can see reasons we might want some gfp flag to reflect shorterm allocations but I propose starting from a clear semantic definition and only then add users with proper justification. This was been brought up before LSF this year by Matthew [1] and it turned out that GFP_TEMPORARY really doesn't have a clear semantic. It seems to be a heuristic without any measured advantage for most (if not all) its current users. The follow up discussion has revealed that opinions on what might be temporary allocation differ a lot between developers. So rather than trying to tweak existing users into a semantic which they haven't expected I propose to simply remove the flag and start from scratch if we really need a semantic for short term allocations. [1] http://lkml.kernel.org/r/20170118054945.GD18349@bombadil.infradead.org [akpm@linux-foundation.org: fix typo] [akpm@linux-foundation.org: coding-style fixes] [sfr@canb.auug.org.au: drm/i915: fix up] Link: http://lkml.kernel.org/r/20170816144703.378d4f4d@canb.auug.org.au Link: http://lkml.kernel.org/r/20170728091904.14627-1-mhocko@kernel.org Signed-off-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Acked-by: Mel Gorman <mgorman@suse.de> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Matthew Wilcox <willy@infradead.org> Cc: Neil Brown <neilb@suse.de> Cc: "Theodore Ts'o" <tytso@mit.edu> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-13 23:28:29 +00:00
buf = (char *)__get_free_page(GFP_KERNEL);
if (!buf)
return;
print_task_path_n_nm(tsk, buf);
dump_stack: unify debug information printed by show_regs() show_regs() is inherently arch-dependent but it does make sense to print generic debug information and some archs already do albeit in slightly different forms. This patch introduces a generic function to print debug information from show_regs() so that different archs print out the same information and it's much easier to modify what's printed. show_regs_print_info() prints out the same debug info as dump_stack() does plus task and thread_info pointers. * Archs which didn't print debug info now do. alpha, arc, blackfin, c6x, cris, frv, h8300, hexagon, ia64, m32r, metag, microblaze, mn10300, openrisc, parisc, score, sh64, sparc, um, xtensa * Already prints debug info. Replaced with show_regs_print_info(). The printed information is superset of what used to be there. arm, arm64, avr32, mips, powerpc, sh32, tile, unicore32, x86 * s390 is special in that it used to print arch-specific information along with generic debug info. Heiko and Martin think that the arch-specific extra isn't worth keeping s390 specfic implementation. Converted to use the generic version. Note that now all archs print the debug info before actual register dumps. An example BUG() dump follows. kernel BUG at /work/os/work/kernel/workqueue.c:4841! invalid opcode: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC Modules linked in: CPU: 0 PID: 1 Comm: swapper/0 Not tainted 3.9.0-rc1-work+ #7 Hardware name: empty empty/S3992, BIOS 080011 10/26/2007 task: ffff88007c85e040 ti: ffff88007c860000 task.ti: ffff88007c860000 RIP: 0010:[<ffffffff8234a07e>] [<ffffffff8234a07e>] init_workqueues+0x4/0x6 RSP: 0000:ffff88007c861ec8 EFLAGS: 00010246 RAX: ffff88007c861fd8 RBX: ffffffff824466a8 RCX: 0000000000000001 RDX: 0000000000000046 RSI: 0000000000000001 RDI: ffffffff8234a07a RBP: ffff88007c861ec8 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000001 R11: 0000000000000000 R12: ffffffff8234a07a R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 FS: 0000000000000000(0000) GS:ffff88007dc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: ffff88015f7ff000 CR3: 00000000021f1000 CR4: 00000000000007f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Stack: ffff88007c861ef8 ffffffff81000312 ffffffff824466a8 ffff88007c85e650 0000000000000003 0000000000000000 ffff88007c861f38 ffffffff82335e5d ffff88007c862080 ffffffff8223d8c0 ffff88007c862080 ffffffff81c47760 Call Trace: [<ffffffff81000312>] do_one_initcall+0x122/0x170 [<ffffffff82335e5d>] kernel_init_freeable+0x9b/0x1c8 [<ffffffff81c47760>] ? rest_init+0x140/0x140 [<ffffffff81c4776e>] kernel_init+0xe/0xf0 [<ffffffff81c6be9c>] ret_from_fork+0x7c/0xb0 [<ffffffff81c47760>] ? rest_init+0x140/0x140 ... v2: Typo fix in x86-32. v3: CPU number dropped from show_regs_print_info() as dump_stack_print_info() has been updated to print it. s390 specific implementation dropped as requested by s390 maintainers. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Jesper Nilsson <jesper.nilsson@axis.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: Fengguang Wu <fengguang.wu@intel.com> Cc: Mike Frysinger <vapier@gentoo.org> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Sam Ravnborg <sam@ravnborg.org> Acked-by: Chris Metcalf <cmetcalf@tilera.com> [tile bits] Acked-by: Richard Kuo <rkuo@codeaurora.org> [hexagon bits] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-04-30 22:27:17 +00:00
show_regs_print_info(KERN_INFO);
show_ecr_verbose(regs);
pr_info("[EFA ]: 0x%08lx\n[BLINK ]: %pS\n[ERET ]: %pS\n",
current->thread.fault_address,
(void *)regs->blink, (void *)regs->ret);
if (user_mode(regs))
show_faulting_vma(regs->ret, buf); /* faulting code, not data */
pr_info("[STAT32]: 0x%08lx", regs->status32);
#define STS_BIT(r, bit) r->status32 & STATUS_##bit##_MASK ? #bit" " : ""
#ifdef CONFIG_ISA_ARCOMPACT
pr_cont(" : %2s%2s%2s%2s%2s%2s%2s\n",
(regs->status32 & STATUS_U_MASK) ? "U " : "K ",
STS_BIT(regs, DE), STS_BIT(regs, AE),
STS_BIT(regs, A2), STS_BIT(regs, A1),
STS_BIT(regs, E2), STS_BIT(regs, E1));
#else
pr_cont(" : %2s%2s%2s%2s\n",
STS_BIT(regs, IE),
(regs->status32 & STATUS_U_MASK) ? "U " : "K ",
STS_BIT(regs, DE), STS_BIT(regs, AE));
#endif
pr_info("BTA: 0x%08lx\t SP: 0x%08lx\t FP: 0x%08lx\n",
regs->bta, regs->sp, regs->fp);
pr_info("LPS: 0x%08lx\tLPE: 0x%08lx\tLPC: 0x%08lx\n",
regs->lp_start, regs->lp_end, regs->lp_count);
/* print regs->r0 thru regs->r12
* Sequential printing was generating horrible code
*/
print_reg_file(&(regs->r0), 0);
/* If Callee regs were saved, display them too */
cregs = (struct callee_regs *)current->thread.callee_reg;
if (cregs)
show_callee_regs(cregs);
free_page((unsigned long)buf);
}
void show_kernel_fault_diag(const char *str, struct pt_regs *regs,
unsigned long address)
{
current->thread.fault_address = address;
/* Show fault description */
pr_info("\n%s\n", str);
/* Caller and Callee regs */
show_regs(regs);
/* Show stack trace if this Fatality happened in kernel mode */
if (!user_mode(regs))
show_stacktrace(current, regs);
}