1 files changed, 50 insertions, 216 deletions

diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 13d053982dd7..b6b3d052ca86 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -13,6 +13,7 @@
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/fs.h>
+#include <linux/log2.h>
 #include <linux/mm.h>
 #include <linux/mman.h>
 #include <linux/errno.h>
@@ -309,7 +310,10 @@ create_elf_tables(struct linux_binprm *bprm, const struct elfhdr *exec,
 	 * Grow the stack manually; some architectures have a limit on how
 	 * far ahead a user-space access may be in order to grow the stack.
 	 */
+	if (mmap_read_lock_killable(mm))
+		return -EINTR;
 	vma = find_extend_vma(mm, bprm->p);
+	mmap_read_unlock(mm);
 	if (!vma)
 		return -EFAULT;
 
@@ -421,6 +425,26 @@ static int elf_read(struct file *file, void *buf, size_t len, loff_t pos)
 	return 0;
 }
 
+static unsigned long maximum_alignment(struct elf_phdr *cmds, int nr)
+{
+	unsigned long alignment = 0;
+	int i;
+
+	for (i = 0; i < nr; i++) {
+		if (cmds[i].p_type == PT_LOAD) {
+			unsigned long p_align = cmds[i].p_align;
+
+			/* skip non-power of two alignments as invalid */
+			if (!is_power_of_2(p_align))
+				continue;
+			alignment = max(alignment, p_align);
+		}
+	}
+
+	/* ensure we align to at least one page */
+	return ELF_PAGEALIGN(alignment);
+}
+
 /**
  * load_elf_phdrs() - load ELF program headers
  * @elf_ex:   ELF header of the binary whose program headers should be loaded
@@ -1008,6 +1032,7 @@ out_free_interp:
 		int elf_prot, elf_flags;
 		unsigned long k, vaddr;
 		unsigned long total_size = 0;
+		unsigned long alignment;
 
 		if (elf_ppnt->p_type != PT_LOAD)
 			continue;
@@ -1086,6 +1111,9 @@ out_free_interp:
 				load_bias = ELF_ET_DYN_BASE;
 				if (current->flags & PF_RANDOMIZE)
 					load_bias += arch_mmap_rnd();
+				alignment = maximum_alignment(elf_phdata, elf_ex->e_phnum);
+				if (alignment)
+					load_bias &= ~(alignment - 1);
 				elf_flags |= MAP_FIXED;
 			} else
 				load_bias = 0;
@@ -1389,126 +1417,6 @@ out:
  * Jeremy Fitzhardinge <jeremy@sw.oz.au>
  */
 
-/*
- * The purpose of always_dump_vma() is to make sure that special kernel mappings
- * that are useful for post-mortem analysis are included in every core dump.
- * In that way we ensure that the core dump is fully interpretable later
- * without matching up the same kernel and hardware config to see what PC values
- * meant. These special mappings include - vDSO, vsyscall, and other
- * architecture specific mappings
- */
-static bool always_dump_vma(struct vm_area_struct *vma)
-{
-	/* Any vsyscall mappings? */
-	if (vma == get_gate_vma(vma->vm_mm))
-		return true;
-
-	/*
-	 * Assume that all vmas with a .name op should always be dumped.
-	 * If this changes, a new vm_ops field can easily be added.
-	 */
-	if (vma->vm_ops && vma->vm_ops->name && vma->vm_ops->name(vma))
-		return true;
-
-	/*
-	 * arch_vma_name() returns non-NULL for special architecture mappings,
-	 * such as vDSO sections.
-	 */
-	if (arch_vma_name(vma))
-		return true;
-
-	return false;
-}
-
-/*
- * Decide what to dump of a segment, part, all or none.
- */
-static unsigned long vma_dump_size(struct vm_area_struct *vma,
-				   unsigned long mm_flags)
-{
-#define FILTER(type)	(mm_flags & (1UL << MMF_DUMP_##type))
-
-	/* always dump the vdso and vsyscall sections */
-	if (always_dump_vma(vma))
-		goto whole;
-
-	if (vma->vm_flags & VM_DONTDUMP)
-		return 0;
-
-	/* support for DAX */
-	if (vma_is_dax(vma)) {
-		if ((vma->vm_flags & VM_SHARED) && FILTER(DAX_SHARED))
-			goto whole;
-		if (!(vma->vm_flags & VM_SHARED) && FILTER(DAX_PRIVATE))
-			goto whole;
-		return 0;
-	}
-
-	/* Hugetlb memory check */
-	if (is_vm_hugetlb_page(vma)) {
-		if ((vma->vm_flags & VM_SHARED) && FILTER(HUGETLB_SHARED))
-			goto whole;
-		if (!(vma->vm_flags & VM_SHARED) && FILTER(HUGETLB_PRIVATE))
-			goto whole;
-		return 0;
-	}
-
-	/* Do not dump I/O mapped devices or special mappings */
-	if (vma->vm_flags & VM_IO)
-		return 0;
-
-	/* By default, dump shared memory if mapped from an anonymous file. */
-	if (vma->vm_flags & VM_SHARED) {
-		if (file_inode(vma->vm_file)->i_nlink == 0 ?
-		    FILTER(ANON_SHARED) : FILTER(MAPPED_SHARED))
-			goto whole;
-		return 0;
-	}
-
-	/* Dump segments that have been written to.  */
-	if (vma->anon_vma && FILTER(ANON_PRIVATE))
-		goto whole;
-	if (vma->vm_file == NULL)
-		return 0;
-
-	if (FILTER(MAPPED_PRIVATE))
-		goto whole;
-
-	/*
-	 * If this looks like the beginning of a DSO or executable mapping,
-	 * check for an ELF header.  If we find one, dump the first page to
-	 * aid in determining what was mapped here.
-	 */
-	if (FILTER(ELF_HEADERS) &&
-	    vma->vm_pgoff == 0 && (vma->vm_flags & VM_READ)) {
-		u32 __user *header = (u32 __user *) vma->vm_start;
-		u32 word;
-		/*
-		 * Doing it this way gets the constant folded by GCC.
-		 */
-		union {
-			u32 cmp;
-			char elfmag[SELFMAG];
-		} magic;
-		BUILD_BUG_ON(SELFMAG != sizeof word);
-		magic.elfmag[EI_MAG0] = ELFMAG0;
-		magic.elfmag[EI_MAG1] = ELFMAG1;
-		magic.elfmag[EI_MAG2] = ELFMAG2;
-		magic.elfmag[EI_MAG3] = ELFMAG3;
-		if (unlikely(get_user(word, header)))
-			word = 0;
-		if (word == magic.cmp)
-			return PAGE_SIZE;
-	}
-
-#undef	FILTER
-
-	return 0;
-
-whole:
-	return vma->vm_end - vma->vm_start;
-}
-
 /* An ELF note in memory */
 struct memelfnote
 {
@@ -2220,32 +2128,6 @@ static void free_note_info(struct elf_note_info *info)
 
 #endif
 
-static struct vm_area_struct *first_vma(struct task_struct *tsk,
-					struct vm_area_struct *gate_vma)
-{
-	struct vm_area_struct *ret = tsk->mm->mmap;
-
-	if (ret)
-		return ret;
-	return gate_vma;
-}
-/*
- * Helper function for iterating across a vma list.  It ensures that the caller
- * will visit `gate_vma' prior to terminating the search.
- */
-static struct vm_area_struct *next_vma(struct vm_area_struct *this_vma,
-					struct vm_area_struct *gate_vma)
-{
-	struct vm_area_struct *ret;
-
-	ret = this_vma->vm_next;
-	if (ret)
-		return ret;
-	if (this_vma == gate_vma)
-		return NULL;
-	return gate_vma;
-}
-
 static void fill_extnum_info(struct elfhdr *elf, struct elf_shdr *shdr4extnum,
 			     elf_addr_t e_shoff, int segs)
 {
@@ -2272,9 +2154,8 @@ static void fill_extnum_info(struct elfhdr *elf, struct elf_shdr *shdr4extnum,
 static int elf_core_dump(struct coredump_params *cprm)
 {
 	int has_dumped = 0;
-	int segs, i;
-	size_t vma_data_size = 0;
-	struct vm_area_struct *vma, *gate_vma;
+	int vma_count, segs, i;
+	size_t vma_data_size;
 	struct elfhdr elf;
 	loff_t offset = 0, dataoff;
 	struct elf_note_info info = { };
@@ -2282,30 +2163,16 @@ static int elf_core_dump(struct coredump_params *cprm)
 	struct elf_shdr *shdr4extnum = NULL;
 	Elf_Half e_phnum;
 	elf_addr_t e_shoff;
-	elf_addr_t *vma_filesz = NULL;
+	struct core_vma_metadata *vma_meta;
+
+	if (dump_vma_snapshot(cprm, &vma_count, &vma_meta, &vma_data_size))
+		return 0;
 
-	/*
-	 * We no longer stop all VM operations.
-	 * 
-	 * This is because those proceses that could possibly change map_count
-	 * or the mmap / vma pages are now blocked in do_exit on current
-	 * finishing this core dump.
-	 *
-	 * Only ptrace can touch these memory addresses, but it doesn't change
-	 * the map_count or the pages allocated. So no possibility of crashing
-	 * exists while dumping the mm->vm_next areas to the core file.
-	 */
-  
 	/*
 	 * The number of segs are recored into ELF header as 16bit value.
 	 * Please check DEFAULT_MAX_MAP_COUNT definition when you modify here.
 	 */
-	segs = current->mm->map_count;
-	segs += elf_core_extra_phdrs();
-
-	gate_vma = get_gate_vma(current->mm);
-	if (gate_vma != NULL)
-		segs++;
+	segs = vma_count + elf_core_extra_phdrs();
 
 	/* for notes section */
 	segs++;
@@ -2343,24 +2210,6 @@ static int elf_core_dump(struct coredump_params *cprm)
 
 	dataoff = offset = roundup(offset, ELF_EXEC_PAGESIZE);
 
-	/*
-	 * Zero vma process will get ZERO_SIZE_PTR here.
-	 * Let coredump continue for register state at least.
-	 */
-	vma_filesz = kvmalloc(array_size(sizeof(*vma_filesz), (segs - 1)),
-			      GFP_KERNEL);
-	if (!vma_filesz)
-		goto end_coredump;
-
-	for (i = 0, vma = first_vma(current, gate_vma); vma != NULL;
-			vma = next_vma(vma, gate_vma)) {
-		unsigned long dump_size;
-
-		dump_size = vma_dump_size(vma, cprm->mm_flags);
-		vma_filesz[i++] = dump_size;
-		vma_data_size += dump_size;
-	}
-
 	offset += vma_data_size;
 	offset += elf_core_extra_data_size();
 	e_shoff = offset;
@@ -2381,21 +2230,23 @@ static int elf_core_dump(struct coredump_params *cprm)
 		goto end_coredump;
 
 	/* Write program headers for segments dump */
-	for (i = 0, vma = first_vma(current, gate_vma); vma != NULL;
-			vma = next_vma(vma, gate_vma)) {
+	for (i = 0; i < vma_count; i++) {
+		struct core_vma_metadata *meta = vma_meta + i;
 		struct elf_phdr phdr;
 
 		phdr.p_type = PT_LOAD;
 		phdr.p_offset = offset;
-		phdr.p_vaddr = vma->vm_start;
+		phdr.p_vaddr = meta->start;
 		phdr.p_paddr = 0;
-		phdr.p_filesz = vma_filesz[i++];
-		phdr.p_memsz = vma->vm_end - vma->vm_start;
+		phdr.p_filesz = meta->dump_size;
+		phdr.p_memsz = meta->end - meta->start;
 		offset += phdr.p_filesz;
-		phdr.p_flags = vma->vm_flags & VM_READ ? PF_R : 0;
-		if (vma->vm_flags & VM_WRITE)
+		phdr.p_flags = 0;
+		if (meta->flags & VM_READ)
+			phdr.p_flags |= PF_R;
+		if (meta->flags & VM_WRITE)
 			phdr.p_flags |= PF_W;
-		if (vma->vm_flags & VM_EXEC)
+		if (meta->flags & VM_EXEC)
 			phdr.p_flags |= PF_X;
 		phdr.p_align = ELF_EXEC_PAGESIZE;
 
@@ -2417,28 +2268,11 @@ static int elf_core_dump(struct coredump_params *cprm)
 	if (!dump_skip(cprm, dataoff - cprm->pos))
 		goto end_coredump;
 
-	for (i = 0, vma = first_vma(current, gate_vma); vma != NULL;
-			vma = next_vma(vma, gate_vma)) {
-		unsigned long addr;
-		unsigned long end;
+	for (i = 0; i < vma_count; i++) {
+		struct core_vma_metadata *meta = vma_meta + i;
 
-		end = vma->vm_start + vma_filesz[i++];
-
-		for (addr = vma->vm_start; addr < end; addr += PAGE_SIZE) {
-			struct page *page;
-			int stop;
-
-			page = get_dump_page(addr);
-			if (page) {
-				void *kaddr = kmap(page);
-				stop = !dump_emit(cprm, kaddr, PAGE_SIZE);
-				kunmap(page);
-				put_page(page);
-			} else
-				stop = !dump_skip(cprm, PAGE_SIZE);
-			if (stop)
-				goto end_coredump;
-		}
+		if (!dump_user_range(cprm, meta->start, meta->dump_size))
+			goto end_coredump;
 	}
 	dump_truncate(cprm);
 
@@ -2453,7 +2287,7 @@ static int elf_core_dump(struct coredump_params *cprm)
 end_coredump:
 	free_note_info(&info);
 	kfree(shdr4extnum);
-	kvfree(vma_filesz);
+	kvfree(vma_meta);
 	kfree(phdr4note);
 	return has_dumped;
 }