mirror of
https://github.com/torvalds/linux.git
synced 2024-11-15 00:21:59 +00:00
2fd4ef85e0
Pavel Emelianov and Kirill Korotaev observe that fs and arch users of security_vm_enough_memory tend to forget to vm_unacct_memory when a failure occurs further down (typically in setup_arg_pages variants). These are all users of insert_vm_struct, and that reservation will only be unaccounted on exit if the vma is marked VM_ACCOUNT: which in some cases it is (hidden inside VM_STACK_FLAGS) and in some cases it isn't. So x86_64 32-bit and ppc64 vDSO ELFs have been leaking memory into Committed_AS each time they're run. But don't add VM_ACCOUNT to them, it's inappropriate to reserve against the very unlikely case that gdb be used to COW a vDSO page - we ought to do something about that in do_wp_page, but there are yet other inconsistencies to be resolved. The safe and economical way to fix this is to let insert_vm_struct do the security_vm_enough_memory check when it finds VM_ACCOUNT is set. And the MIPS irix_brk has been calling security_vm_enough_memory before calling do_brk which repeats it, doubly accounting and so also leaking. Remove that, and all the fs and arch calls to security_vm_enough_memory: give it a less misleading name later on. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-Off-By: Kirill Korotaev <dev@sw.ru> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
109 lines
2.9 KiB
C
109 lines
2.9 KiB
C
/* Copyright 2002,2003 Andi Kleen, SuSE Labs */
|
|
|
|
/* vsyscall handling for 32bit processes. Map a stub page into it
|
|
on demand because 32bit cannot reach the kernel's fixmaps */
|
|
|
|
#include <linux/mm.h>
|
|
#include <linux/string.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/gfp.h>
|
|
#include <linux/init.h>
|
|
#include <linux/stringify.h>
|
|
#include <linux/security.h>
|
|
#include <asm/proto.h>
|
|
#include <asm/tlbflush.h>
|
|
#include <asm/ia32_unistd.h>
|
|
|
|
extern unsigned char syscall32_syscall[], syscall32_syscall_end[];
|
|
extern unsigned char syscall32_sysenter[], syscall32_sysenter_end[];
|
|
extern int sysctl_vsyscall32;
|
|
|
|
char *syscall32_page;
|
|
static int use_sysenter = -1;
|
|
|
|
static struct page *
|
|
syscall32_nopage(struct vm_area_struct *vma, unsigned long adr, int *type)
|
|
{
|
|
struct page *p = virt_to_page(adr - vma->vm_start + syscall32_page);
|
|
get_page(p);
|
|
return p;
|
|
}
|
|
|
|
/* Prevent VMA merging */
|
|
static void syscall32_vma_close(struct vm_area_struct *vma)
|
|
{
|
|
}
|
|
|
|
static struct vm_operations_struct syscall32_vm_ops = {
|
|
.close = syscall32_vma_close,
|
|
.nopage = syscall32_nopage,
|
|
};
|
|
|
|
struct linux_binprm;
|
|
|
|
/* Setup a VMA at program startup for the vsyscall page */
|
|
int syscall32_setup_pages(struct linux_binprm *bprm, int exstack)
|
|
{
|
|
int npages = (VSYSCALL32_END - VSYSCALL32_BASE) >> PAGE_SHIFT;
|
|
struct vm_area_struct *vma;
|
|
struct mm_struct *mm = current->mm;
|
|
int ret;
|
|
|
|
vma = kmem_cache_alloc(vm_area_cachep, SLAB_KERNEL);
|
|
if (!vma)
|
|
return -ENOMEM;
|
|
|
|
memset(vma, 0, sizeof(struct vm_area_struct));
|
|
/* Could randomize here */
|
|
vma->vm_start = VSYSCALL32_BASE;
|
|
vma->vm_end = VSYSCALL32_END;
|
|
/* MAYWRITE to allow gdb to COW and set breakpoints */
|
|
vma->vm_flags = VM_READ|VM_EXEC|VM_MAYREAD|VM_MAYEXEC|VM_MAYWRITE;
|
|
vma->vm_flags |= mm->def_flags;
|
|
vma->vm_page_prot = protection_map[vma->vm_flags & 7];
|
|
vma->vm_ops = &syscall32_vm_ops;
|
|
vma->vm_mm = mm;
|
|
|
|
down_write(&mm->mmap_sem);
|
|
if ((ret = insert_vm_struct(mm, vma))) {
|
|
up_write(&mm->mmap_sem);
|
|
kmem_cache_free(vm_area_cachep, vma);
|
|
return ret;
|
|
}
|
|
mm->total_vm += npages;
|
|
up_write(&mm->mmap_sem);
|
|
return 0;
|
|
}
|
|
|
|
static int __init init_syscall32(void)
|
|
{
|
|
syscall32_page = (void *)get_zeroed_page(GFP_KERNEL);
|
|
if (!syscall32_page)
|
|
panic("Cannot allocate syscall32 page");
|
|
if (use_sysenter > 0) {
|
|
memcpy(syscall32_page, syscall32_sysenter,
|
|
syscall32_sysenter_end - syscall32_sysenter);
|
|
} else {
|
|
memcpy(syscall32_page, syscall32_syscall,
|
|
syscall32_syscall_end - syscall32_syscall);
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
__initcall(init_syscall32);
|
|
|
|
/* May not be __init: called during resume */
|
|
void syscall32_cpu_init(void)
|
|
{
|
|
if (use_sysenter < 0)
|
|
use_sysenter = (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL);
|
|
|
|
/* Load these always in case some future AMD CPU supports
|
|
SYSENTER from compat mode too. */
|
|
checking_wrmsrl(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS);
|
|
checking_wrmsrl(MSR_IA32_SYSENTER_ESP, 0ULL);
|
|
checking_wrmsrl(MSR_IA32_SYSENTER_EIP, (u64)ia32_sysenter_target);
|
|
|
|
wrmsrl(MSR_CSTAR, ia32_cstar_target);
|
|
}
|