mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-10-31 16:38:12 +00:00
mm,fork: introduce MADV_WIPEONFORK
Introduce MADV_WIPEONFORK semantics, which result in a VMA being empty in the child process after fork. This differs from MADV_DONTFORK in one important way. If a child process accesses memory that was MADV_WIPEONFORK, it will get zeroes. The address ranges are still valid, they are just empty. If a child process accesses memory that was MADV_DONTFORK, it will get a segmentation fault, since those address ranges are no longer valid in the child after fork. Since MADV_DONTFORK also seems to be used to allow very large programs to fork in systems with strict memory overcommit restrictions, changing the semantics of MADV_DONTFORK might break existing programs. MADV_WIPEONFORK only works on private, anonymous VMAs. The use case is libraries that store or cache information, and want to know that they need to regenerate it in the child process after fork. Examples of this would be: - systemd/pulseaudio API checks (fail after fork) (replacing a getpid check, which is too slow without a PID cache) - PKCS#11 API reinitialization check (mandated by specification) - glibc's upcoming PRNG (reseed after fork) - OpenSSL PRNG (reseed after fork) The security benefits of a forking server having a re-inialized PRNG in every child process are pretty obvious. However, due to libraries having all kinds of internal state, and programs getting compiled with many different versions of each library, it is unreasonable to expect calling programs to re-initialize everything manually after fork. A further complication is the proliferation of clone flags, programs bypassing glibc's functions to call clone directly, and programs calling unshare, causing the glibc pthread_atfork hook to not get called. It would be better to have the kernel take care of this automatically. The patch also adds MADV_KEEPONFORK, to undo the effects of a prior MADV_WIPEONFORK. This is similar to the OpenBSD minherit syscall with MAP_INHERIT_ZERO: https://man.openbsd.org/minherit.2 [akpm@linux-foundation.org: numerically order arch/parisc/include/uapi/asm/mman.h #defines] Link: http://lkml.kernel.org/r/20170811212829.29186-3-riel@redhat.com Signed-off-by: Rik van Riel <riel@redhat.com> Reported-by: Florian Weimer <fweimer@redhat.com> Reported-by: Colm MacCártaigh <colm@allcosts.net> Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Helge Deller <deller@gmx.de> Cc: Kees Cook <keescook@chromium.org> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Will Drewry <wad@chromium.org> Cc: <linux-api@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This commit is contained in:
parent
df3735c5b4
commit
d2cd9ede6e
10 changed files with 39 additions and 10 deletions
|
@ -64,6 +64,9 @@
|
|||
overrides the coredump filter bits */
|
||||
#define MADV_DODUMP 17 /* Clear the MADV_NODUMP flag */
|
||||
|
||||
#define MADV_WIPEONFORK 18 /* Zero memory on fork, child only */
|
||||
#define MADV_KEEPONFORK 19 /* Undo MADV_WIPEONFORK */
|
||||
|
||||
/* compatibility flags */
|
||||
#define MAP_FILE 0
|
||||
|
||||
|
|
|
@ -91,6 +91,9 @@
|
|||
overrides the coredump filter bits */
|
||||
#define MADV_DODUMP 17 /* Clear the MADV_NODUMP flag */
|
||||
|
||||
#define MADV_WIPEONFORK 18 /* Zero memory on fork, child only */
|
||||
#define MADV_KEEPONFORK 19 /* Undo MADV_WIPEONFORK */
|
||||
|
||||
/* compatibility flags */
|
||||
#define MAP_FILE 0
|
||||
|
||||
|
|
|
@ -57,6 +57,9 @@
|
|||
overrides the coredump filter bits */
|
||||
#define MADV_DODUMP 70 /* Clear the MADV_NODUMP flag */
|
||||
|
||||
#define MADV_WIPEONFORK 71 /* Zero memory on fork, child only */
|
||||
#define MADV_KEEPONFORK 72 /* Undo MADV_WIPEONFORK */
|
||||
|
||||
#define MADV_HWPOISON 100 /* poison a page for testing */
|
||||
#define MADV_SOFT_OFFLINE 101 /* soft offline page for testing */
|
||||
|
||||
|
|
|
@ -103,6 +103,9 @@
|
|||
overrides the coredump filter bits */
|
||||
#define MADV_DODUMP 17 /* Clear the MADV_NODUMP flag */
|
||||
|
||||
#define MADV_WIPEONFORK 18 /* Zero memory on fork, child only */
|
||||
#define MADV_KEEPONFORK 19 /* Undo MADV_WIPEONFORK */
|
||||
|
||||
/* compatibility flags */
|
||||
#define MAP_FILE 0
|
||||
|
||||
|
|
|
@ -663,6 +663,7 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma)
|
|||
[ilog2(VM_NORESERVE)] = "nr",
|
||||
[ilog2(VM_HUGETLB)] = "ht",
|
||||
[ilog2(VM_ARCH_1)] = "ar",
|
||||
[ilog2(VM_WIPEONFORK)] = "wf",
|
||||
[ilog2(VM_DONTDUMP)] = "dd",
|
||||
#ifdef CONFIG_MEM_SOFT_DIRTY
|
||||
[ilog2(VM_SOFTDIRTY)] = "sd",
|
||||
|
|
|
@ -189,7 +189,7 @@ extern unsigned int kobjsize(const void *objp);
|
|||
#define VM_NORESERVE 0x00200000 /* should the VM suppress accounting */
|
||||
#define VM_HUGETLB 0x00400000 /* Huge TLB Page VM */
|
||||
#define VM_ARCH_1 0x01000000 /* Architecture-specific flag */
|
||||
#define VM_ARCH_2 0x02000000
|
||||
#define VM_WIPEONFORK 0x02000000 /* Wipe VMA contents in child. */
|
||||
#define VM_DONTDUMP 0x04000000 /* Do not include in the core dump */
|
||||
|
||||
#ifdef CONFIG_MEM_SOFT_DIRTY
|
||||
|
|
|
@ -125,12 +125,6 @@ IF_HAVE_PG_IDLE(PG_idle, "idle" )
|
|||
#define __VM_ARCH_SPECIFIC_1 {VM_ARCH_1, "arch_1" }
|
||||
#endif
|
||||
|
||||
#if defined(CONFIG_X86)
|
||||
#define __VM_ARCH_SPECIFIC_2 {VM_MPX, "mpx" }
|
||||
#else
|
||||
#define __VM_ARCH_SPECIFIC_2 {VM_ARCH_2, "arch_2" }
|
||||
#endif
|
||||
|
||||
#ifdef CONFIG_MEM_SOFT_DIRTY
|
||||
#define IF_HAVE_VM_SOFTDIRTY(flag,name) {flag, name },
|
||||
#else
|
||||
|
@ -162,7 +156,7 @@ IF_HAVE_PG_IDLE(PG_idle, "idle" )
|
|||
{VM_NORESERVE, "noreserve" }, \
|
||||
{VM_HUGETLB, "hugetlb" }, \
|
||||
__VM_ARCH_SPECIFIC_1 , \
|
||||
__VM_ARCH_SPECIFIC_2 , \
|
||||
{VM_WIPEONFORK, "wipeonfork" }, \
|
||||
{VM_DONTDUMP, "dontdump" }, \
|
||||
IF_HAVE_VM_SOFTDIRTY(VM_SOFTDIRTY, "softdirty" ) \
|
||||
{VM_MIXEDMAP, "mixedmap" }, \
|
||||
|
|
|
@ -58,6 +58,9 @@
|
|||
overrides the coredump filter bits */
|
||||
#define MADV_DODUMP 17 /* Clear the MADV_DONTDUMP flag */
|
||||
|
||||
#define MADV_WIPEONFORK 18 /* Zero memory on fork, child only */
|
||||
#define MADV_KEEPONFORK 19 /* Undo MADV_WIPEONFORK */
|
||||
|
||||
/* compatibility flags */
|
||||
#define MAP_FILE 0
|
||||
|
||||
|
|
|
@ -657,7 +657,12 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
|
|||
retval = dup_userfaultfd(tmp, &uf);
|
||||
if (retval)
|
||||
goto fail_nomem_anon_vma_fork;
|
||||
if (anon_vma_fork(tmp, mpnt))
|
||||
if (tmp->vm_flags & VM_WIPEONFORK) {
|
||||
/* VM_WIPEONFORK gets a clean slate in the child. */
|
||||
tmp->anon_vma = NULL;
|
||||
if (anon_vma_prepare(tmp))
|
||||
goto fail_nomem_anon_vma_fork;
|
||||
} else if (anon_vma_fork(tmp, mpnt))
|
||||
goto fail_nomem_anon_vma_fork;
|
||||
tmp->vm_flags &= ~(VM_LOCKED | VM_LOCKONFAULT);
|
||||
tmp->vm_next = tmp->vm_prev = NULL;
|
||||
|
@ -701,7 +706,8 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
|
|||
rb_parent = &tmp->vm_rb;
|
||||
|
||||
mm->map_count++;
|
||||
retval = copy_page_range(mm, oldmm, mpnt);
|
||||
if (!(tmp->vm_flags & VM_WIPEONFORK))
|
||||
retval = copy_page_range(mm, oldmm, mpnt);
|
||||
|
||||
if (tmp->vm_ops && tmp->vm_ops->open)
|
||||
tmp->vm_ops->open(tmp);
|
||||
|
|
13
mm/madvise.c
13
mm/madvise.c
|
@ -80,6 +80,17 @@ static long madvise_behavior(struct vm_area_struct *vma,
|
|||
}
|
||||
new_flags &= ~VM_DONTCOPY;
|
||||
break;
|
||||
case MADV_WIPEONFORK:
|
||||
/* MADV_WIPEONFORK is only supported on anonymous memory. */
|
||||
if (vma->vm_file || vma->vm_flags & VM_SHARED) {
|
||||
error = -EINVAL;
|
||||
goto out;
|
||||
}
|
||||
new_flags |= VM_WIPEONFORK;
|
||||
break;
|
||||
case MADV_KEEPONFORK:
|
||||
new_flags &= ~VM_WIPEONFORK;
|
||||
break;
|
||||
case MADV_DONTDUMP:
|
||||
new_flags |= VM_DONTDUMP;
|
||||
break;
|
||||
|
@ -696,6 +707,8 @@ madvise_behavior_valid(int behavior)
|
|||
#endif
|
||||
case MADV_DONTDUMP:
|
||||
case MADV_DODUMP:
|
||||
case MADV_WIPEONFORK:
|
||||
case MADV_KEEPONFORK:
|
||||
#ifdef CONFIG_MEMORY_FAILURE
|
||||
case MADV_SOFT_OFFLINE:
|
||||
case MADV_HWPOISON:
|
||||
|
|
Loading…
Reference in a new issue