1 files changed, 186 insertions, 67 deletions

diff --git a/fs/coredump.c b/fs/coredump.c
index a6b3c196cdef..7bad7785e8e6 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -31,7 +31,6 @@
 #include <linux/tsacct_kern.h>
 #include <linux/cn_proc.h>
 #include <linux/audit.h>
-#include <linux/tracehook.h>
 #include <linux/kmod.h>
 #include <linux/fsnotify.h>
 #include <linux/fs_struct.h>
@@ -41,6 +40,8 @@
 #include <linux/fs.h>
 #include <linux/path.h>
 #include <linux/timekeeping.h>
+#include <linux/sysctl.h>
+#include <linux/elf.h>
 
 #include <linux/uaccess.h>
 #include <asm/mmu_context.h>
@@ -52,9 +53,12 @@
 
 #include <trace/events/sched.h>
 
-int core_uses_pid;
-unsigned int core_pipe_limit;
-char core_pattern[CORENAME_MAX_SIZE] = "core";
+static bool dump_vma_snapshot(struct coredump_params *cprm);
+static void free_vma_snapshot(struct coredump_params *cprm);
+
+static int core_uses_pid;
+static unsigned int core_pipe_limit;
+static char core_pattern[CORENAME_MAX_SIZE] = "core";
 static int core_name_size = CORENAME_MAX_SIZE;
 
 struct core_name {
@@ -62,8 +66,6 @@ struct core_name {
 	int used, size;
 };
 
-/* The maximal length of core_pattern is also specified in sysctl.c */
-
 static int expand_corename(struct core_name *cn, int size)
 {
 	char *corename = krealloc(cn->corename, size, GFP_KERNEL);
@@ -347,13 +349,13 @@ out:
 	return ispipe;
 }
 
-static int zap_process(struct task_struct *start, int exit_code, int flags)
+static int zap_process(struct task_struct *start, int exit_code)
 {
 	struct task_struct *t;
 	int nr = 0;
 
-	/* ignore all signals except SIGKILL, see prepare_signal() */
-	start->signal->flags = SIGNAL_GROUP_COREDUMP | flags;
+	/* Allow SIGKILL, see prepare_signal() */
+	start->signal->flags = SIGNAL_GROUP_EXIT;
 	start->signal->group_exit_code = exit_code;
 	start->signal->group_stop_count = 0;
 
@@ -372,13 +374,13 @@ static int zap_process(struct task_struct *start, int exit_code, int flags)
 static int zap_threads(struct task_struct *tsk,
 			struct core_state *core_state, int exit_code)
 {
+	struct signal_struct *signal = tsk->signal;
 	int nr = -EAGAIN;
 
 	spin_lock_irq(&tsk->sighand->siglock);
-	if (!signal_group_exit(tsk->signal)) {
-		tsk->signal->core_state = core_state;
-		tsk->signal->group_exit_task = tsk;
-		nr = zap_process(tsk, exit_code, 0);
+	if (!(signal->flags & SIGNAL_GROUP_EXIT) && !signal->group_exec_task) {
+		signal->core_state = core_state;
+		nr = zap_process(tsk, exit_code);
 		clear_tsk_thread_flag(tsk, TIF_SIGPENDING);
 		tsk->flags |= PF_DUMPCORE;
 		atomic_set(&core_state->nr_threads, nr);
@@ -400,9 +402,8 @@ static int coredump_wait(int exit_code, struct core_state *core_state)
 	if (core_waiters > 0) {
 		struct core_thread *ptr;
 
-		freezer_do_not_count();
-		wait_for_completion(&core_state->startup);
-		freezer_count();
+		wait_for_completion_state(&core_state->startup,
+					  TASK_UNINTERRUPTIBLE|TASK_FREEZABLE);
 		/*
 		 * Wait for all the threads to become inactive, so that
 		 * all the thread context (extended register state, like
@@ -410,7 +411,7 @@ static int coredump_wait(int exit_code, struct core_state *core_state)
 		 */
 		ptr = core_state->dumper.next;
 		while (ptr != NULL) {
-			wait_task_inactive(ptr->task, 0);
+			wait_task_inactive(ptr->task, TASK_ANY);
 			ptr = ptr->next;
 		}
 	}
@@ -426,8 +427,6 @@ static void coredump_finish(bool core_dumped)
 	spin_lock_irq(&current->sighand->siglock);
 	if (core_dumped && !__fatal_signal_pending(current))
 		current->signal->group_exit_code |= 0x80;
-	current->signal->group_exit_task = NULL;
-	current->signal->flags = SIGNAL_GROUP_EXIT;
 	next = current->signal->core_state->dumper.next;
 	current->signal->core_state = NULL;
 	spin_unlock_irq(&current->sighand->siglock);
@@ -534,6 +533,7 @@ void do_coredump(const kernel_siginfo_t *siginfo)
 		 * by any locks.
 		 */
 		.mm_flags = mm->flags,
+		.vma_meta = NULL,
 	};
 
 	audit_core_dumps(siginfo->si_signo);
@@ -748,6 +748,9 @@ void do_coredump(const kernel_siginfo_t *siginfo)
 			pr_info("Core dump to |%s disabled\n", cn.corename);
 			goto close_fail;
 		}
+		if (!dump_vma_snapshot(&cprm))
+			goto close_fail;
+
 		file_start_write(cprm.file);
 		core_dumped = binfmt->core_dump(&cprm);
 		/*
@@ -761,6 +764,7 @@ void do_coredump(const kernel_siginfo_t *siginfo)
 			dump_emit(&cprm, "", 1);
 		}
 		file_end_write(cprm.file);
+		free_vma_snapshot(&cprm);
 	}
 	if (ispipe && core_pipe_limit)
 		wait_for_dump_helpers(cprm.file);
@@ -811,9 +815,9 @@ static int __dump_skip(struct coredump_params *cprm, size_t nr)
 {
 	static char zeroes[PAGE_SIZE];
 	struct file *file = cprm->file;
-	if (file->f_op->llseek && file->f_op->llseek != no_llseek) {
+	if (file->f_mode & FMODE_LSEEK) {
 		if (dump_interrupted() ||
-		    file->f_op->llseek(file, nr, SEEK_CUR) < 0)
+		    vfs_llseek(file, nr, SEEK_CUR) < 0)
 			return 0;
 		cprm->pos += nr;
 		return 1;
@@ -827,6 +831,39 @@ static int __dump_skip(struct coredump_params *cprm, size_t nr)
 	}
 }
 
+static int dump_emit_page(struct coredump_params *cprm, struct page *page)
+{
+	struct bio_vec bvec = {
+		.bv_page	= page,
+		.bv_offset	= 0,
+		.bv_len		= PAGE_SIZE,
+	};
+	struct iov_iter iter;
+	struct file *file = cprm->file;
+	loff_t pos;
+	ssize_t n;
+
+	if (cprm->to_skip) {
+		if (!__dump_skip(cprm, cprm->to_skip))
+			return 0;
+		cprm->to_skip = 0;
+	}
+	if (cprm->written + PAGE_SIZE > cprm->limit)
+		return 0;
+	if (dump_interrupted())
+		return 0;
+	pos = file->f_pos;
+	iov_iter_bvec(&iter, WRITE, &bvec, 1, PAGE_SIZE);
+	n = __kernel_write_iter(cprm->file, &iter, &pos);
+	if (n != PAGE_SIZE)
+		return 0;
+	file->f_pos = pos;
+	cprm->written += PAGE_SIZE;
+	cprm->pos += PAGE_SIZE;
+
+	return 1;
+}
+
 int dump_emit(struct coredump_params *cprm, const void *addr, int nr)
 {
 	if (cprm->to_skip) {
@@ -858,7 +895,6 @@ int dump_user_range(struct coredump_params *cprm, unsigned long start,
 
 	for (addr = start; addr < start + len; addr += PAGE_SIZE) {
 		struct page *page;
-		int stop;
 
 		/*
 		 * To avoid having to allocate page tables for virtual address
@@ -869,10 +905,7 @@ int dump_user_range(struct coredump_params *cprm, unsigned long start,
 		 */
 		page = get_dump_page(addr);
 		if (page) {
-			void *kaddr = kmap_local_page(page);
-
-			stop = !dump_emit(cprm, kaddr, PAGE_SIZE);
-			kunmap_local(kaddr);
+			int stop = !dump_emit_page(cprm, page);
 			put_page(page);
 			if (stop)
 				return 0;
@@ -895,6 +928,63 @@ int dump_align(struct coredump_params *cprm, int align)
 }
 EXPORT_SYMBOL(dump_align);
 
+#ifdef CONFIG_SYSCTL
+
+void validate_coredump_safety(void)
+{
+	if (suid_dumpable == SUID_DUMP_ROOT &&
+	    core_pattern[0] != '/' && core_pattern[0] != '|') {
+		pr_warn(
+"Unsafe core_pattern used with fs.suid_dumpable=2.\n"
+"Pipe handler or fully qualified core dump path required.\n"
+"Set kernel.core_pattern before fs.suid_dumpable.\n"
+		);
+	}
+}
+
+static int proc_dostring_coredump(struct ctl_table *table, int write,
+		  void *buffer, size_t *lenp, loff_t *ppos)
+{
+	int error = proc_dostring(table, write, buffer, lenp, ppos);
+
+	if (!error)
+		validate_coredump_safety();
+	return error;
+}
+
+static struct ctl_table coredump_sysctls[] = {
+	{
+		.procname	= "core_uses_pid",
+		.data		= &core_uses_pid,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "core_pattern",
+		.data		= core_pattern,
+		.maxlen		= CORENAME_MAX_SIZE,
+		.mode		= 0644,
+		.proc_handler	= proc_dostring_coredump,
+	},
+	{
+		.procname	= "core_pipe_limit",
+		.data		= &core_pipe_limit,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{ }
+};
+
+static int __init init_fs_coredump_sysctls(void)
+{
+	register_sysctl_init("kernel", coredump_sysctls);
+	return 0;
+}
+fs_initcall(init_fs_coredump_sysctls);
+#endif /* CONFIG_SYSCTL */
+
 /*
  * 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.
@@ -926,6 +1016,8 @@ static bool always_dump_vma(struct vm_area_struct *vma)
 	return false;
 }
 
+#define DUMP_SIZE_MAYBE_ELFHDR_PLACEHOLDER 1
+
 /*
  * Decide how much of @vma's contents should be included in a core dump.
  */
@@ -985,9 +1077,20 @@ static unsigned long vma_dump_size(struct vm_area_struct *vma,
 	 * 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) &&
-	    (READ_ONCE(file_inode(vma->vm_file)->i_mode) & 0111) != 0)
-		return PAGE_SIZE;
+	    vma->vm_pgoff == 0 && (vma->vm_flags & VM_READ)) {
+		if ((READ_ONCE(file_inode(vma->vm_file)->i_mode) & 0111) != 0)
+			return PAGE_SIZE;
+
+		/*
+		 * ELF libraries aren't always executable.
+		 * We'll want to check whether the mapping starts with the ELF
+		 * magic, but not now - we're holding the mmap lock,
+		 * so copy_from_user() doesn't work here.
+		 * Use a placeholder instead, and fix it up later in
+		 * dump_vma_snapshot().
+		 */
+		return DUMP_SIZE_MAYBE_ELFHDR_PLACEHOLDER;
+	}
 
 #undef	FILTER
 
@@ -997,45 +1100,47 @@ whole:
 	return vma->vm_end - vma->vm_start;
 }
 
-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,
+static struct vm_area_struct *coredump_next_vma(struct ma_state *mas,
+				       struct vm_area_struct *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)
+	if (gate_vma && (vma == gate_vma))
 		return NULL;
+
+	vma = mas_next(mas, ULONG_MAX);
+	if (vma)
+		return vma;
 	return gate_vma;
 }
 
+static void free_vma_snapshot(struct coredump_params *cprm)
+{
+	if (cprm->vma_meta) {
+		int i;
+		for (i = 0; i < cprm->vma_count; i++) {
+			struct file *file = cprm->vma_meta[i].file;
+			if (file)
+				fput(file);
+		}
+		kvfree(cprm->vma_meta);
+		cprm->vma_meta = NULL;
+	}
+}
+
 /*
  * Under the mmap_lock, take a snapshot of relevant information about the task's
  * VMAs.
  */
-int dump_vma_snapshot(struct coredump_params *cprm, int *vma_count,
-		      struct core_vma_metadata **vma_meta,
-		      size_t *vma_data_size_ptr)
+static bool dump_vma_snapshot(struct coredump_params *cprm)
 {
-	struct vm_area_struct *vma, *gate_vma;
+	struct vm_area_struct *gate_vma, *vma = NULL;
 	struct mm_struct *mm = current->mm;
-	int i;
-	size_t vma_data_size = 0;
+	MA_STATE(mas, &mm->mm_mt, 0, 0);
+	int i = 0;
 
 	/*
 	 * Once the stack expansion code is fixed to not change VMA bounds
@@ -1043,36 +1148,50 @@ int dump_vma_snapshot(struct coredump_params *cprm, int *vma_count,
 	 * mmap_lock in read mode.
 	 */
 	if (mmap_write_lock_killable(mm))
-		return -EINTR;
+		return false;
 
+	cprm->vma_data_size = 0;
 	gate_vma = get_gate_vma(mm);
-	*vma_count = mm->map_count + (gate_vma ? 1 : 0);
+	cprm->vma_count = mm->map_count + (gate_vma ? 1 : 0);
 
-	*vma_meta = kvmalloc_array(*vma_count, sizeof(**vma_meta), GFP_KERNEL);
-	if (!*vma_meta) {
+	cprm->vma_meta = kvmalloc_array(cprm->vma_count, sizeof(*cprm->vma_meta), GFP_KERNEL);
+	if (!cprm->vma_meta) {
 		mmap_write_unlock(mm);
-		return -ENOMEM;
+		return false;
 	}
 
-	for (i = 0, vma = first_vma(current, gate_vma); vma != NULL;
-			vma = next_vma(vma, gate_vma), i++) {
-		struct core_vma_metadata *m = (*vma_meta) + i;
+	while ((vma = coredump_next_vma(&mas, vma, gate_vma)) != NULL) {
+		struct core_vma_metadata *m = cprm->vma_meta + i;
 
 		m->start = vma->vm_start;
 		m->end = vma->vm_end;
 		m->flags = vma->vm_flags;
 		m->dump_size = vma_dump_size(vma, cprm->mm_flags);
-
-		vma_data_size += m->dump_size;
+		m->pgoff = vma->vm_pgoff;
+		m->file = vma->vm_file;
+		if (m->file)
+			get_file(m->file);
+		i++;
 	}
 
 	mmap_write_unlock(mm);
 
-	if (WARN_ON(i != *vma_count)) {
-		kvfree(*vma_meta);
-		return -EFAULT;
+	for (i = 0; i < cprm->vma_count; i++) {
+		struct core_vma_metadata *m = cprm->vma_meta + i;
+
+		if (m->dump_size == DUMP_SIZE_MAYBE_ELFHDR_PLACEHOLDER) {
+			char elfmag[SELFMAG];
+
+			if (copy_from_user(elfmag, (void __user *)m->start, SELFMAG) ||
+					memcmp(elfmag, ELFMAG, SELFMAG) != 0) {
+				m->dump_size = 0;
+			} else {
+				m->dump_size = PAGE_SIZE;
+			}
+		}
+
+		cprm->vma_data_size += m->dump_size;
 	}
 
-	*vma_data_size_ptr = vma_data_size;
-	return 0;
+	return true;
 }