elf coredump: add extended numbering support

The current ELF dumper implementation can produce broken corefiles if
program headers exceed 65535.  This number is determined by the number of
vmas which the process have.  In particular, some extreme programs may use
more than 65535 vmas.  (If you google max_map_count, you can find some
users facing this problem.) This kind of program never be able to generate
correct coredumps.

This patch implements ``extended numbering'' that uses sh_info field of
the first section header instead of e_phnum field in order to represent
upto 4294967295 vmas.

This is supported by
AMD64-ABI(http://www.x86-64.org/documentation.html) and
Solaris(http://docs.sun.com/app/docs/doc/817-1984/).
Of course, we are preparing patches for gdb and binutils.

Signed-off-by: Daisuke HATAYAMA <d.hatayama@jp.fujitsu.com>
Cc: "Luck, Tony" <tony.luck@intel.com>
Cc: Jeff Dike <jdike@addtoit.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Greg Ungerer <gerg@snapgear.com>
Cc: Roland McGrath <roland@redhat.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Alan Cox <alan@lxorguk.ukuu.org.uk>
Cc: <linux-arch@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 124 insertions, 5 deletions

diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 6fc49b6ed936..78de530cfb02 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -1838,6 +1838,34 @@ static struct vm_area_struct *next_vma(struct vm_area_struct *this_vma,
 	return gate_vma;
 }
 
+static void fill_extnum_info(struct elfhdr *elf, struct elf_shdr *shdr4extnum,
+			     elf_addr_t e_shoff, int segs)
+{
+	elf->e_shoff = e_shoff;
+	elf->e_shentsize = sizeof(*shdr4extnum);
+	elf->e_shnum = 1;
+	elf->e_shstrndx = SHN_UNDEF;
+
+	memset(shdr4extnum, 0, sizeof(*shdr4extnum));
+
+	shdr4extnum->sh_type = SHT_NULL;
+	shdr4extnum->sh_size = elf->e_shnum;
+	shdr4extnum->sh_link = elf->e_shstrndx;
+	shdr4extnum->sh_info = segs;
+}
+
+static size_t elf_core_vma_data_size(struct vm_area_struct *gate_vma,
+				     unsigned long mm_flags)
+{
+	struct vm_area_struct *vma;
+	size_t size = 0;
+
+	for (vma = first_vma(current, gate_vma); vma != NULL;
+	     vma = next_vma(vma, gate_vma))
+		size += vma_dump_size(vma, mm_flags);
+	return size;
+}
+
 /*
  * Actual dumper
  *
@@ -1857,6 +1885,9 @@ static int elf_core_dump(struct coredump_params *cprm)
 	unsigned long mm_flags;
 	struct elf_note_info info;
 	struct elf_phdr *phdr4note = NULL;
+	struct elf_shdr *shdr4extnum = NULL;
+	Elf_Half e_phnum;
+	elf_addr_t e_shoff;
 
 	/*
 	 * We no longer stop all VM operations.
@@ -1885,12 +1916,19 @@ static int elf_core_dump(struct coredump_params *cprm)
 	if (gate_vma != NULL)
 		segs++;
 
+	/* for notes section */
+	segs++;
+
+	/* If segs > PN_XNUM(0xffff), then e_phnum overflows. To avoid
+	 * this, kernel supports extended numbering. Have a look at
+	 * include/linux/elf.h for further information. */
+	e_phnum = segs > PN_XNUM ? PN_XNUM : segs;
+
 	/*
 	 * Collect all the non-memory information about the process for the
 	 * notes.  This also sets up the file header.
 	 */
-	if (!fill_note_info(elf, segs + 1, /* including notes section */
-			    &info, cprm->signr, cprm->regs))
+	if (!fill_note_info(elf, e_phnum, &info, cprm->signr, cprm->regs))
 		goto cleanup;
 
 	has_dumped = 1;
@@ -1900,7 +1938,7 @@ static int elf_core_dump(struct coredump_params *cprm)
 	set_fs(KERNEL_DS);
 
 	offset += sizeof(*elf);				/* Elf header */
-	offset += (segs + 1) * sizeof(struct elf_phdr); /* Program headers */
+	offset += segs * sizeof(struct elf_phdr);	/* Program headers */
 	foffset = offset;
 
 	/* Write notes phdr entry */
@@ -1926,6 +1964,19 @@ static int elf_core_dump(struct coredump_params *cprm)
 	 */
 	mm_flags = current->mm->flags;
 
+	offset += elf_core_vma_data_size(gate_vma, mm_flags);
+	offset += elf_core_extra_data_size();
+	e_shoff = offset;
+
+	if (e_phnum == PN_XNUM) {
+		shdr4extnum = kmalloc(sizeof(*shdr4extnum), GFP_KERNEL);
+		if (!shdr4extnum)
+			goto end_coredump;
+		fill_extnum_info(elf, shdr4extnum, e_shoff, segs);
+	}
+
+	offset = dataoff;
+
 	size += sizeof(*elf);
 	if (size > cprm->limit || !dump_write(cprm->file, elf, sizeof(*elf)))
 		goto end_coredump;
@@ -2003,11 +2054,20 @@ static int elf_core_dump(struct coredump_params *cprm)
 	if (!elf_core_write_extra_data(cprm->file, &size, cprm->limit))
 		goto end_coredump;
 
+	if (e_phnum == PN_XNUM) {
+		size += sizeof(*shdr4extnum);
+		if (size > cprm->limit
+		    || !dump_write(cprm->file, shdr4extnum,
+				   sizeof(*shdr4extnum)))
+			goto end_coredump;
+	}
+
 end_coredump:
 	set_fs(fs);
 
 cleanup:
 	free_note_info(&info);
+	kfree(shdr4extnum);
 	kfree(phdr4note);
 	kfree(elf);
 out:
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index 112da491d75d..e49d9c06a4b6 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -1505,6 +1505,22 @@ static int elf_dump_thread_status(long signr, struct elf_thread_status *t)
 	return sz;
 }
 
+static void fill_extnum_info(struct elfhdr *elf, struct elf_shdr *shdr4extnum,
+			     elf_addr_t e_shoff, int segs)
+{
+	elf->e_shoff = e_shoff;
+	elf->e_shentsize = sizeof(*shdr4extnum);
+	elf->e_shnum = 1;
+	elf->e_shstrndx = SHN_UNDEF;
+
+	memset(shdr4extnum, 0, sizeof(*shdr4extnum));
+
+	shdr4extnum->sh_type = SHT_NULL;
+	shdr4extnum->sh_size = elf->e_shnum;
+	shdr4extnum->sh_link = elf->e_shstrndx;
+	shdr4extnum->sh_info = segs;
+}
+
 /*
  * dump the segments for an MMU process
  */
@@ -1569,6 +1585,17 @@ static int elf_fdpic_dump_segments(struct file *file, size_t *size,
 }
 #endif
 
+static size_t elf_core_vma_data_size(unsigned long mm_flags)
+{
+	struct vm_area_struct *vma;
+	size_t size = 0;
+
+	for (vma = current->mm->mmap; vma; vma->vm_next)
+		if (maydump(vma, mm_flags))
+			size += vma->vm_end - vma->vm_start;
+	return size;
+}
+
 /*
  * Actual dumper
  *
@@ -1601,6 +1628,9 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm)
 	elf_addr_t *auxv;
 	unsigned long mm_flags;
 	struct elf_phdr *phdr4note = NULL;
+	struct elf_shdr *shdr4extnum = NULL;
+	Elf_Half e_phnum;
+	elf_addr_t e_shoff;
 
 	/*
 	 * We no longer stop all VM operations.
@@ -1667,8 +1697,16 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm)
 	segs = current->mm->map_count;
 	segs += elf_core_extra_phdrs();
 
+	/* for notes section */
+	segs++;
+
+	/* If segs > PN_XNUM(0xffff), then e_phnum overflows. To avoid
+	 * this, kernel supports extended numbering. Have a look at
+	 * include/linux/elf.h for further information. */
+	e_phnum = segs > PN_XNUM ? PN_XNUM : segs;
+
 	/* Set up header */
-	fill_elf_fdpic_header(elf, segs + 1);	/* including notes section */
+	fill_elf_fdpic_header(elf, e_phnum);
 
 	has_dumped = 1;
 	current->flags |= PF_DUMPCORE;
@@ -1708,7 +1746,7 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm)
 	set_fs(KERNEL_DS);
 
 	offset += sizeof(*elf);				/* Elf header */
-	offset += (segs+1) * sizeof(struct elf_phdr);	/* Program headers */
+	offset += segs * sizeof(struct elf_phdr);	/* Program headers */
 	foffset = offset;
 
 	/* Write notes phdr entry */
@@ -1738,6 +1776,19 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm)
 	 */
 	mm_flags = current->mm->flags;
 
+	offset += elf_core_vma_data_size(mm_flags);
+	offset += elf_core_extra_data_size();
+	e_shoff = offset;
+
+	if (e_phnum == PN_XNUM) {
+		shdr4extnum = kmalloc(sizeof(*shdr4extnum), GFP_KERNEL);
+		if (!shdr4extnum)
+			goto end_coredump;
+		fill_extnum_info(elf, shdr4extnum, e_shoff, segs);
+	}
+
+	offset = dataoff;
+
 	size += sizeof(*elf);
 	if (size > cprm->limit || !dump_write(cprm->file, elf, sizeof(*elf)))
 		goto end_coredump;
@@ -1802,6 +1853,14 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm)
 	if (!elf_core_write_extra_data(cprm->file, &size, cprm->limit))
 		goto end_coredump;
 
+	if (e_phnum == PN_XNUM) {
+		size += sizeof(*shdr4extnum);
+		if (size > cprm->limit
+		    || !dump_write(cprm->file, shdr4extnum,
+				   sizeof(*shdr4extnum)))
+			goto end_coredump;
+	}
+
 	if (cprm->file->f_pos != offset) {
 		/* Sanity check */
 		printk(KERN_WARNING