Files
linux-stable-mirror/include/linux/binfmts.h
Christian Brauner 1686594d72 coredump: hand a pidfd to the usermode coredump helper
commit b5325b2a27 upstream.

Give userspace a way to instruct the kernel to install a pidfd into the
usermode helper process. This makes coredump handling a lot more
reliable for userspace. In parallel with this commit we already have
systemd adding support for this in [1].

We create a pidfs file for the coredumping process when we process the
corename pattern. When the usermode helper process is forked we then
install the pidfs file as file descriptor three into the usermode
helpers file descriptor table so it's available to the exec'd program.

Since usermode helpers are either children of the system_unbound_wq
workqueue or kthreadd we know that the file descriptor table is empty
and can thus always use three as the file descriptor number.

Note, that we'll install a pidfd for the thread-group leader even if a
subthread is calling do_coredump(). We know that task linkage hasn't
been removed due to delay_group_leader() and even if this @current isn't
the actual thread-group leader we know that the thread-group leader
cannot be reaped until @current has exited.

[brauner: This is a backport for the v5.14 series. Upstream has
significantly changed and backporting all that infra is a non-starter.
So simply backport the pidfd_prepare() helper and waste the file
descriptor we allocated. Then we minimally massage the umh coredump
setup code.]

Link: https://github.com/systemd/systemd/pull/37125 [1]
Link: https://lore.kernel.org/20250414-work-coredump-v2-3-685bf231f828@kernel.org
Tested-by: Luca Boccassi <luca.boccassi@gmail.com>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2025-06-04 14:38:07 +02:00

151 lines
4.6 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_BINFMTS_H
#define _LINUX_BINFMTS_H
#include <linux/sched.h>
#include <linux/unistd.h>
#include <asm/exec.h>
#include <uapi/linux/binfmts.h>
struct filename;
#define CORENAME_MAX_SIZE 128
/*
* This structure is used to hold the arguments that are used when loading binaries.
*/
struct linux_binprm {
#ifdef CONFIG_MMU
struct vm_area_struct *vma;
unsigned long vma_pages;
#else
# define MAX_ARG_PAGES 32
struct page *page[MAX_ARG_PAGES];
#endif
struct mm_struct *mm;
unsigned long p; /* current top of mem */
unsigned long argmin; /* rlimit marker for copy_strings() */
unsigned int
/* Should an execfd be passed to userspace? */
have_execfd:1,
/* Use the creds of a script (see binfmt_misc) */
execfd_creds:1,
/*
* Set by bprm_creds_for_exec hook to indicate a
* privilege-gaining exec has happened. Used to set
* AT_SECURE auxv for glibc.
*/
secureexec:1,
/*
* Set when errors can no longer be returned to the
* original userspace.
*/
point_of_no_return:1;
#ifdef __alpha__
unsigned int taso:1;
#endif
struct file *executable; /* Executable to pass to the interpreter */
struct file *interpreter;
struct file *file;
struct cred *cred; /* new credentials */
int unsafe; /* how unsafe this exec is (mask of LSM_UNSAFE_*) */
unsigned int per_clear; /* bits to clear in current->personality */
int argc, envc;
const char *filename; /* Name of binary as seen by procps */
const char *interp; /* Name of the binary really executed. Most
of the time same as filename, but could be
different for binfmt_{misc,script} */
const char *fdpath; /* generated filename for execveat */
unsigned interp_flags;
int execfd; /* File descriptor of the executable */
unsigned long loader, exec;
struct rlimit rlim_stack; /* Saved RLIMIT_STACK used during exec. */
char buf[BINPRM_BUF_SIZE];
} __randomize_layout;
#define BINPRM_FLAGS_ENFORCE_NONDUMP_BIT 0
#define BINPRM_FLAGS_ENFORCE_NONDUMP (1 << BINPRM_FLAGS_ENFORCE_NONDUMP_BIT)
/* filename of the binary will be inaccessible after exec */
#define BINPRM_FLAGS_PATH_INACCESSIBLE_BIT 2
#define BINPRM_FLAGS_PATH_INACCESSIBLE (1 << BINPRM_FLAGS_PATH_INACCESSIBLE_BIT)
/* preserve argv0 for the interpreter */
#define BINPRM_FLAGS_PRESERVE_ARGV0_BIT 3
#define BINPRM_FLAGS_PRESERVE_ARGV0 (1 << BINPRM_FLAGS_PRESERVE_ARGV0_BIT)
/* Function parameter for binfmt->coredump */
struct coredump_params {
const kernel_siginfo_t *siginfo;
struct pt_regs *regs;
struct file *file;
unsigned long limit;
unsigned long mm_flags;
loff_t written;
loff_t pos;
loff_t to_skip;
int vma_count;
size_t vma_data_size;
struct core_vma_metadata *vma_meta;
struct pid *pid;
};
/*
* This structure defines the functions that are used to load the binary formats that
* linux accepts.
*/
struct linux_binfmt {
struct list_head lh;
struct module *module;
int (*load_binary)(struct linux_binprm *);
int (*load_shlib)(struct file *);
int (*core_dump)(struct coredump_params *cprm);
unsigned long min_coredump; /* minimal dump size */
} __randomize_layout;
extern void __register_binfmt(struct linux_binfmt *fmt, int insert);
/* Registration of default binfmt handlers */
static inline void register_binfmt(struct linux_binfmt *fmt)
{
__register_binfmt(fmt, 0);
}
/* Same as above, but adds a new binfmt at the top of the list */
static inline void insert_binfmt(struct linux_binfmt *fmt)
{
__register_binfmt(fmt, 1);
}
extern void unregister_binfmt(struct linux_binfmt *);
extern int __must_check remove_arg_zero(struct linux_binprm *);
extern int begin_new_exec(struct linux_binprm * bprm);
extern void setup_new_exec(struct linux_binprm * bprm);
extern void finalize_exec(struct linux_binprm *bprm);
extern void would_dump(struct linux_binprm *, struct file *);
extern int suid_dumpable;
/* Stack area protections */
#define EXSTACK_DEFAULT 0 /* Whatever the arch defaults to */
#define EXSTACK_DISABLE_X 1 /* Disable executable stacks */
#define EXSTACK_ENABLE_X 2 /* Enable executable stacks */
extern int setup_arg_pages(struct linux_binprm * bprm,
unsigned long stack_top,
int executable_stack);
extern int transfer_args_to_stack(struct linux_binprm *bprm,
unsigned long *sp_location);
extern int bprm_change_interp(const char *interp, struct linux_binprm *bprm);
int copy_string_kernel(const char *arg, struct linux_binprm *bprm);
extern void set_binfmt(struct linux_binfmt *new);
extern ssize_t read_code(struct file *, unsigned long, loff_t, size_t);
int kernel_execve(const char *filename,
const char *const *argv, const char *const *envp);
#endif /* _LINUX_BINFMTS_H */