[PATCH] Support piping into commands in /proc/sys/kernel/core_pattern

Using the infrastructure created in previous patches implement support to
pipe core dumps into programs.

This is done by overloading the existing core_pattern sysctl
with a new syntax:

|program

When the first character of the pattern is a '|' the kernel will instead
threat the rest of the pattern as a command to run.  The core dump will be
written to the standard input of that program instead of to a file.

This is useful for having automatic core dump analysis without filling up
disks.  The program can do some simple analysis and save only a summary of
the core dump.

The core dump proces will run with the privileges and in the name space of
the process that caused the core dump.

I also increased the core pattern size to 128 bytes so that longer command
lines fit.

Most of the changes comes from allowing core dumps without seeks.  They are
fairly straight forward though.

One small incompatibility is that if someone had a core pattern previously
that started with '|' they will get suddenly new behaviour.  I think that's
unlikely to be a real problem though.

Additional background:

> Very nice, do you happen to have a program that can accept this kind of
> input for crash dumps?  I'm guessing that the embedded people will
> really want this functionality.

I had a cheesy demo/prototype.  Basically it wrote the dump to a file again,
ran gdb on it to get a backtrace and wrote the summary to a shared directory.
Then there was a simple CGI script to generate a "top 10" crashes HTML
listing.

Unfortunately this still had the disadvantage to needing full disk space for a
dump except for deleting it afterwards (in fact it was worse because over the
pipe holes didn't work so if you have a holey address map it would require
more space).

Fortunately gdb seems to be happy to handle /proc/pid/fd/xxx input pipes as
cores (at least it worked with zsh's =(cat core) syntax), so it would be
likely possible to do it without temporary space with a simple wrapper that
calls it in the right way.  I ran out of time before doing that though.

The demo prototype scripts weren't very good.  If there is really interest I
can dig them out (they are currently on a laptop disk on the desk with the
laptop itself being in service), but I would recommend to rewrite them for any
serious application of this and fix the disk space problem.

Also to be really useful it should probably find a way to automatically fetch
the debuginfos (I cheated and just installed them in advance).  If nobody else
does it I can probably do the rewrite myself again at some point.

My hope at some point was that desktops would support it in their builtin
crash reporters, but at least the KDE people I talked too seemed to be happy
with their user space only solution.

Alan sayeth:

  I don't believe that piping as such as neccessarily the right model, but
  the ability to intercept and processes core dumps from user space is asked
  for by many enterprise users as well.  They want to know about, capture,
  analyse and process core dumps, often centrally and in automated form.

[akpm@osdl.org: loff_t != unsigned long]
Signed-off-by: Andi Kleen <ak@suse.de>
Cc: Alan Cox <alan@lxorguk.ukuu.org.uk>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

fs/binfmt_elf.c

@@ -1151,11 +1151,23 @@ static int dump_write(struct file *file, const void *addr, int nr)
 
 static int dump_seek(struct file *file, loff_t off)
 {
-	if (file->f_op->llseek) {
-		if (file->f_op->llseek(file, off, 0) != off)
+	if (file->f_op->llseek && file->f_op->llseek != no_llseek) {
+		if (file->f_op->llseek(file, off, 1) != off)
 			return 0;
-	} else
-		file->f_pos = off;
+	} else {
+		char *buf = (char *)get_zeroed_page(GFP_KERNEL);
+		if (!buf)
+			return 0;
+		while (off > 0) {
+			unsigned long n = off;
+			if (n > PAGE_SIZE)
+				n = PAGE_SIZE;
+			if (!dump_write(file, buf, n))
+				return 0;
+			off -= n;
+		}
+		free_page((unsigned long)buf);
+	}
 	return 1;
 }
 
@@ -1203,30 +1215,35 @@ static int notesize(struct memelfnote *en)
 	return sz;
 }
 
-#define DUMP_WRITE(addr, nr)	\
-	do { if (!dump_write(file, (addr), (nr))) return 0; } while(0)
-#define DUMP_SEEK(off)	\
-	do { if (!dump_seek(file, (off))) return 0; } while(0)
+#define DUMP_WRITE(addr, nr, foffset)	\
+	do { if (!dump_write(file, (addr), (nr))) return 0; *foffset += (nr); } while(0)
 
-static int writenote(struct memelfnote *men, struct file *file)
+static int alignfile(struct file *file, loff_t *foffset)
 {
-	struct elf_note en;
+	char buf[4] = { 0, };
+	DUMP_WRITE(buf, roundup(*foffset, 4) - *foffset, foffset);
+	return 1;
+}
 
+static int writenote(struct memelfnote *men, struct file *file,
+			loff_t *foffset)
+{
+	struct elf_note en;
 	en.n_namesz = strlen(men->name) + 1;
 	en.n_descsz = men->datasz;
 	en.n_type = men->type;
 
-	DUMP_WRITE(&en, sizeof(en));
-	DUMP_WRITE(men->name, en.n_namesz);
-	/* XXX - cast from long long to long to avoid need for libgcc.a */
-	DUMP_SEEK(roundup((unsigned long)file->f_pos, 4));	/* XXX */
-	DUMP_WRITE(men->data, men->datasz);
-	DUMP_SEEK(roundup((unsigned long)file->f_pos, 4));	/* XXX */
+	DUMP_WRITE(&en, sizeof(en), foffset);
+	DUMP_WRITE(men->name, en.n_namesz, foffset);
+	if (!alignfile(file, foffset))
+		return 0;
+	DUMP_WRITE(men->data, men->datasz, foffset);
+	if (!alignfile(file, foffset))
+		return 0;
 
 	return 1;
 }
 #undef DUMP_WRITE
-#undef DUMP_SEEK
 
 #define DUMP_WRITE(addr, nr)	\
 	if ((size += (nr)) > limit || !dump_write(file, (addr), (nr))) \
@@ -1426,7 +1443,7 @@ static int elf_core_dump(long signr, struct pt_regs *regs, struct file *file)
 	int i;
 	struct vm_area_struct *vma;
 	struct elfhdr *elf = NULL;
-	loff_t offset = 0, dataoff;
+	loff_t offset = 0, dataoff, foffset;
 	unsigned long limit = current->signal->rlim[RLIMIT_CORE].rlim_cur;
 	int numnote;
 	struct memelfnote *notes = NULL;
@@ -1569,7 +1586,8 @@ static int elf_core_dump(long signr, struct pt_regs *regs, struct file *file)
 		DUMP_WRITE(&phdr, sizeof(phdr));
 	}
 
-	/* Page-align dumped data */
+	foffset = offset;
+
 	dataoff = offset = roundup(offset, ELF_EXEC_PAGESIZE);
 
 	/* Write program headers for segments dump */
@@ -1594,6 +1612,7 @@ static int elf_core_dump(long signr, struct pt_regs *regs, struct file *file)
 		phdr.p_align = ELF_EXEC_PAGESIZE;
 
 		DUMP_WRITE(&phdr, sizeof(phdr));
+		foffset += sizeof(phdr);
 	}
 
 #ifdef ELF_CORE_WRITE_EXTRA_PHDRS
@@ -1602,7 +1621,7 @@ static int elf_core_dump(long signr, struct pt_regs *regs, struct file *file)
 
  	/* write out the notes section */
 	for (i = 0; i < numnote; i++)
-		if (!writenote(notes + i, file))
+		if (!writenote(notes + i, file, &foffset))
 			goto end_coredump;
 
 	/* write out the thread status notes section */
@@ -1611,11 +1630,12 @@ static int elf_core_dump(long signr, struct pt_regs *regs, struct file *file)
 				list_entry(t, struct elf_thread_status, list);
 
 		for (i = 0; i < tmp->num_notes; i++)
-			if (!writenote(&tmp->notes[i], file))
+			if (!writenote(&tmp->notes[i], file, &foffset))
 				goto end_coredump;
 	}
- 
-	DUMP_SEEK(dataoff);
+
+	/* Align to page */
+	DUMP_SEEK(dataoff - foffset);
 
 	for (vma = current->mm->mmap; vma != NULL; vma = vma->vm_next) {
 		unsigned long addr;
@@ -1631,10 +1651,10 @@ static int elf_core_dump(long signr, struct pt_regs *regs, struct file *file)
 
 			if (get_user_pages(current, current->mm, addr, 1, 0, 1,
 						&page, &vma) <= 0) {
-				DUMP_SEEK(file->f_pos + PAGE_SIZE);
+				DUMP_SEEK(PAGE_SIZE);
 			} else {
 				if (page == ZERO_PAGE(addr)) {
-					DUMP_SEEK(file->f_pos + PAGE_SIZE);
+					DUMP_SEEK(PAGE_SIZE);
 				} else {
 					void *kaddr;
 					flush_cache_page(vma, addr,
@@ -1658,13 +1678,6 @@ static int elf_core_dump(long signr, struct pt_regs *regs, struct file *file)
 	ELF_CORE_WRITE_EXTRA_DATA;
 #endif
 
-	if (file->f_pos != offset) {
-		/* Sanity check */
-		printk(KERN_WARNING
-		       "elf_core_dump: file->f_pos (%Ld) != offset (%Ld)\n",
-		       file->f_pos, offset);
-	}
-
 end_coredump:
 	set_fs(fs);
 

fs/exec.c

@@ -58,7 +58,7 @@
 #endif
 
 int core_uses_pid;
-char core_pattern[65] = "core";
+char core_pattern[128] = "core";
 int suid_dumpable = 0;
 
 EXPORT_SYMBOL(suid_dumpable);
@@ -1463,6 +1463,7 @@ int do_coredump(long signr, int exit_code, struct pt_regs * regs)
 	int retval = 0;
 	int fsuid = current->fsuid;
 	int flag = 0;
+	int ispipe = 0;
 
 	binfmt = current->binfmt;
 	if (!binfmt || !binfmt->core_dump)
@@ -1504,22 +1505,34 @@ int do_coredump(long signr, int exit_code, struct pt_regs * regs)
  	lock_kernel();
 	format_corename(corename, core_pattern, signr);
 	unlock_kernel();
-	file = filp_open(corename, O_CREAT | 2 | O_NOFOLLOW | O_LARGEFILE | flag, 0600);
+ 	if (corename[0] == '|') {
+		/* SIGPIPE can happen, but it's just never processed */
+ 		if(call_usermodehelper_pipe(corename+1, NULL, NULL, &file)) {
+ 			printk(KERN_INFO "Core dump to %s pipe failed\n",
+			       corename);
+ 			goto fail_unlock;
+ 		}
+		ispipe = 1;
+ 	} else
+ 		file = filp_open(corename,
+				 O_CREAT | 2 | O_NOFOLLOW | O_LARGEFILE, 0600);
 	if (IS_ERR(file))
 		goto fail_unlock;
 	inode = file->f_dentry->d_inode;
 	if (inode->i_nlink > 1)
 		goto close_fail;	/* multiple links - don't dump */
-	if (d_unhashed(file->f_dentry))
+	if (!ispipe && d_unhashed(file->f_dentry))
 		goto close_fail;
 
-	if (!S_ISREG(inode->i_mode))
+	/* AK: actually i see no reason to not allow this for named pipes etc.,
+	   but keep the previous behaviour for now. */
+	if (!ispipe && !S_ISREG(inode->i_mode))
 		goto close_fail;
 	if (!file->f_op)
 		goto close_fail;
 	if (!file->f_op->write)
 		goto close_fail;
-	if (do_truncate(file->f_dentry, 0, 0, file) != 0)
+	if (!ispipe && do_truncate(file->f_dentry, 0, 0, file) != 0)
 		goto close_fail;
 
 	retval = binfmt->core_dump(signr, regs, file);

kernel/kmod.c

@@ -35,6 +35,7 @@
 #include <linux/mount.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
+#include <linux/resource.h>
 #include <asm/uaccess.h>
 
 extern int max_threads;
@@ -158,6 +159,9 @@ static int ____call_usermodehelper(void *data)
 		FD_SET(0, fdt->open_fds);
 		FD_CLR(0, fdt->close_on_exec);
 		spin_unlock(&f->file_lock);
+
+		/* and disallow core files too */
+		current->signal->rlim[RLIMIT_CORE] = (struct rlimit){0, 0};
 	}
 
 	/* We can run anywhere, unlike our parent keventd(). */

kernel/sysctl.c

@@ -294,7 +294,7 @@ static ctl_table kern_table[] = {
 		.ctl_name	= KERN_CORE_PATTERN,
 		.procname	= "core_pattern",
 		.data		= core_pattern,
-		.maxlen		= 64,
+		.maxlen		= 128,
 		.mode		= 0644,
 		.proc_handler	= &proc_dostring,
 		.strategy	= &sysctl_string,