[PATCH] Print which shared library/executable faulted in segfault etc. messages v3

[PATCH] Print which shared library/executable faulted in segfault etc. messages v3

[Andi Kleen]

The previously posted version was missing all the 64bit hunks. Fix 
that. Please use over previous version.

-Andi

---

They now look like

hal-resmgr[13791]: segfault at 3c rip 2b9c8caec182 rsp 7fff1e825d30 error 4 in libacl.so.1.1.0[2b9c8caea000+6000]

This makes it easier to pinpoint bugs to specific libraries. 

And printing the offset into a mapping also always allows to find the 
correct fault point in a library even with randomized mappings. Previously
there was no way to actually find the correct code address inside
the randomized mapping.

Relies on earlier patch to shorten the printk formats.

They are often now longer than 80 characters, but I think that's worth it.

Patch for i386 and x86-64.

[includes fix from Eric Dumazet to check d_path error value]
v3: readd 64bit hunks that got dropped somewhere on the way

Signed-off-by: Andi Kleen <ak@suse.de>

---
 arch/x86/kernel/signal_32.c |    7 +++++--
 arch/x86/kernel/signal_64.c |    7 +++++--
 arch/x86/kernel/traps_32.c  |    7 +++++--
 arch/x86/mm/fault_32.c      |    4 +++-
 include/linux/mm.h          |    1 +
 mm/memory.c                 |   31 +++++++++++++++++++++++++++++++
 6 files changed, 50 insertions(+), 7 deletions(-)

Index: linux/include/linux/mm.h
===================================================================
--- linux.orig/include/linux/mm.h
+++ linux/include/linux/mm.h
@@ -1145,6 +1145,7 @@ extern int randomize_va_space;
 #endif
 
 const char * arch_vma_name(struct vm_area_struct *vma);
+void print_vma_addr(char *prefix, unsigned long rip);
 
 struct page *sparse_mem_map_populate(unsigned long pnum, int nid);
 pgd_t *vmemmap_pgd_populate(unsigned long addr, int node);
Index: linux/mm/memory.c
===================================================================
--- linux.orig/mm/memory.c
+++ linux/mm/memory.c
@@ -2746,3 +2746,34 @@ int access_process_vm(struct task_struct
 
 	return buf - old_buf;
 }
+
+/*
+ * Print the name of a VMA.
+ */
+void print_vma_addr(char *prefix, unsigned long ip)
+{
+	struct mm_struct *mm = current->mm;
+	struct vm_area_struct *vma;
+
+	down_read(&mm->mmap_sem);
+	vma = find_vma(mm, ip);
+	if (vma && vma->vm_file) {
+		struct file *f = vma->vm_file;
+		char *buf = (char *)__get_free_page(GFP_KERNEL);
+		if (buf) {
+			char *p, *s;
+
+			p = d_path(f->f_dentry, f->f_vfsmnt, buf, PAGE_SIZE);
+			if (IS_ERR(p))
+				p = "?";
+			s = strrchr(p, '/');
+			if (s)
+				p = s+1;
+			printk("%s%s[%lx+%lx]", prefix, p,
+					vma->vm_start,
+					vma->vm_end - vma->vm_start);
+			free_page((unsigned long)buf);
+		}
+	}
+	up_read(&current->mm->mmap_sem);
+}
Index: linux/arch/x86/kernel/signal_32.c
===================================================================
--- linux.orig/arch/x86/kernel/signal_32.c
+++ linux/arch/x86/kernel/signal_32.c
@@ -198,12 +198,15 @@ asmlinkage int sys_sigreturn(unsigned lo
 	return ax;
 
 badframe:
-	if (show_unhandled_signals && printk_ratelimit())
+	if (show_unhandled_signals && printk_ratelimit()) {
 		printk("%s%s[%d] bad frame in sigreturn frame:%p ip:%lx"
-		       " sp:%lx oeax:%lx\n",
+		       " sp:%lx oeax:%lx",
 		    task_pid_nr(current) > 1 ? KERN_INFO : KERN_EMERG,
 		    current->comm, task_pid_nr(current), frame, regs->ip,
 		    regs->sp, regs->orig_ax);
+		print_vma_addr(" in ", regs->ip);
+		printk("\n");
+	}
 
 	force_sig(SIGSEGV, current);
 	return 0;
Index: linux/arch/x86/kernel/signal_64.c
===================================================================
--- linux.orig/arch/x86/kernel/signal_64.c
+++ linux/arch/x86/kernel/signal_64.c
@@ -481,9 +481,12 @@ do_notify_resume(struct pt_regs *regs, v
 void signal_fault(struct pt_regs *regs, void __user *frame, char *where)
 { 
 	struct task_struct *me = current; 
-	if (show_unhandled_signals && printk_ratelimit())
-		printk("%s[%d] bad frame in %s frame:%p ip:%lx sp:%lx orax:%lx\n",
+	if (show_unhandled_signals && printk_ratelimit()) {
+		printk("%s[%d] bad frame in %s frame:%p ip:%lx sp:%lx orax:%lx",
 	       me->comm,me->pid,where,frame,regs->ip,regs->sp,regs->orig_ax);
+		print_vma_addr(" in ", regs->ip);
+		printk("\n");
+	}
 
 	force_sig(SIGSEGV, me); 
 } 
Index: linux/arch/x86/kernel/traps_32.c
===================================================================
--- linux.orig/arch/x86/kernel/traps_32.c
+++ linux/arch/x86/kernel/traps_32.c
@@ -608,11 +608,14 @@ void __kprobes do_general_protection(str
 	current->thread.error_code = error_code;
 	current->thread.trap_no = 13;
 	if (show_unhandled_signals && unhandled_signal(current, SIGSEGV) &&
-	    printk_ratelimit())
+	    printk_ratelimit()) {
 		printk(KERN_INFO
-		    "%s[%d] general protection ip:%lx sp:%lx error:%lx\n",
+		    "%s[%d] general protection ip:%lx sp:%lx error:%lx",
 		    current->comm, task_pid_nr(current),
 		    regs->ip, regs->sp, error_code);
+		print_vma_addr(" in ", regs->ip);
+		printk("\n");
+	}
 
 	force_sig(SIGSEGV, current);
 	return;
Index: linux/arch/x86/mm/fault_32.c
===================================================================
--- linux.orig/arch/x86/mm/fault_32.c
+++ linux/arch/x86/mm/fault_32.c
@@ -518,11 +518,13 @@ bad_area_nosemaphore:
 #ifdef CONFIG_X86_32
 			"%s%s[%d]: segfault at %lx ip %08lx sp %08lx error %lx\n",
 #else
-			"%s%s[%d]: segfault at %lx ip %lx sp %lx error %lx\n",
+			"%s%s[%d]: segfault at %lx ip %lx sp %lx error %lx",
 #endif
 			task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG,
 			tsk->comm, task_pid_nr(tsk), address, regs->ip,
 			regs->sp, error_code);
+			print_vma_addr(" in ", regs->ip);
+			printk("\n");
 		}
 		tsk->thread.cr2 = address;
 		/* Kernel addresses are always protection faults */
Index: linux/arch/x86/kernel/traps_64.c
===================================================================
--- linux.orig/arch/x86/kernel/traps_64.c
+++ linux/arch/x86/kernel/traps_64.c
@@ -647,11 +647,14 @@ static void __kprobes do_trap(int trapnr
 		tsk->thread.trap_no = trapnr;
 
 		if (show_unhandled_signals && unhandled_signal(tsk, signr) &&
-		    printk_ratelimit())
+		    printk_ratelimit()) {
 			printk(KERN_INFO
-			       "%s[%d] trap %s ip:%lx sp:%lx error:%lx\n",
+			       "%s[%d] trap %s ip:%lx sp:%lx error:%lx",
 			       tsk->comm, tsk->pid, str,
 			       regs->ip, regs->sp, error_code);
+			print_vma_addr(" in ", regs->ip);
+			printk("\n");
+		}
 
 		if (info)
 			force_sig_info(signr, info, tsk);
@@ -745,11 +748,14 @@ asmlinkage void __kprobes do_general_pro
 		tsk->thread.trap_no = 13;
 
 		if (show_unhandled_signals && unhandled_signal(tsk, SIGSEGV) &&
-		    printk_ratelimit())
+		    printk_ratelimit()) {
 			printk(KERN_INFO
-		       "%s[%d] general protection ip:%lx sp:%lx error:%lx\n",
+		       "%s[%d] general protection ip:%lx sp:%lx error:%lx",
 			       tsk->comm, tsk->pid,
 			       regs->ip, regs->sp, error_code);
+			print_vma_addr(" in ", regs->ip);
+			printk("\n");
+		}
 
 		force_sig(SIGSEGV, tsk);
 		return;
Index: linux/arch/x86/mm/fault_64.c
===================================================================
--- linux.orig/arch/x86/mm/fault_64.c
+++ linux/arch/x86/mm/fault_64.c
@@ -556,11 +556,13 @@ bad_area_nosemaphore:
 #ifdef CONFIG_X86_32
 			"%s%s[%d]: segfault at %08lx ip %08lx sp %08lx error %lx\n",
 #else
-			"%s%s[%d]: segfault at %lx ip %lx sp %lx error %lx\n",
+			"%s%s[%d]: segfault at %lx ip %lx sp %lx error %lx",
 #endif
 			task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG,
 			tsk->comm, task_pid_nr(tsk), address, regs->ip,
 			regs->sp, error_code);
+			print_vma_addr(" in ", regs->ip);
+			printk("\n");
 		}
 
 		tsk->thread.cr2 = address;

Re: [PATCH] Print which shared library/executable faulted in segfault etc. messages v3

[Jan Engelhardt]

On Jan 17 2008 00:15, Andi Kleen wrote:
>
>The previously posted version was missing all the 64bit hunks. Fix
>that. Please use over previous version.
>
>They now look like
>
>hal-resmgr[13791]: segfault at 3c rip 2b9c8caec182 rsp 7fff1e825d30
>error 4 in libacl.so.1.1.0[2b9c8caea000+6000]

Can this also be done for executables?

>This makes it easier to pinpoint bugs to specific libraries.

[But it may very well mean improper usage (e.g. passing NULL where
NULL is definitely not expected) on behalf of the library user ;-)]

>And printing the offset into a mapping also always allows to find
>the correct fault point in a library even with randomized mappings.
>Previously there was no way to actually find the correct code
>address inside the randomized mapping.

Previously, one had to ptrace the process, wait for the crash to
happen, then inspect /proc/XXX/maps and calculate the address. It's
not like developers were left in the dark with random mappings.

Re: [PATCH] Print which shared library/executable faulted in segfault etc. messages v3

[Andi Kleen]

> >hal-resmgr[13791]: segfault at 3c rip 2b9c8caec182 rsp 7fff1e825d30
> >error 4 in libacl.so.1.1.0[2b9c8caea000+6000]
> 
> Can this also be done for executables?

This is done for executables.

-Andi