return page;
}
+static inline int stack_guard_page(struct vm_area_struct *vma, unsigned long addr)
+{
+ return stack_guard_page_start(vma, addr) ||
+ stack_guard_page_end(vma, addr+PAGE_SIZE);
+}
+
/**
* __get_user_pages() - pin user pages in memory
* @tsk: task_struct of target task
int ret;
unsigned int fault_flags = 0;
+ /* For mlock, just skip the stack guard page. */
+ if (foll_flags & FOLL_MLOCK) {
+ if (stack_guard_page(vma, start))
+ goto next_page;
+ }
if (foll_flags & FOLL_WRITE)
fault_flags |= FAULT_FLAG_WRITE;
if (nonblocking)
}
/*
+ * This is like a special single-page "expand_{down|up}wards()",
+ * except we must first make sure that 'address{-|+}PAGE_SIZE'
+ * doesn't hit another vma.
+ */
+static inline int check_stack_guard_page(struct vm_area_struct *vma, unsigned long address)
+{
+ address &= PAGE_MASK;
+ if ((vma->vm_flags & VM_GROWSDOWN) && address == vma->vm_start) {
+ struct vm_area_struct *prev = vma->vm_prev;
+
+ /*
+ * Is there a mapping abutting this one below?
+ *
+ * That's only ok if it's the same stack mapping
+ * that has gotten split..
+ */
+ if (prev && prev->vm_end == address)
+ return prev->vm_flags & VM_GROWSDOWN ? 0 : -ENOMEM;
+
+ return expand_downwards(vma, address - PAGE_SIZE);
+ }
+ if ((vma->vm_flags & VM_GROWSUP) && address + PAGE_SIZE == vma->vm_end) {
+ struct vm_area_struct *next = vma->vm_next;
+
+ /* As VM_GROWSDOWN but s/below/above/ */
+ if (next && next->vm_start == address + PAGE_SIZE)
+ return next->vm_flags & VM_GROWSUP ? 0 : -ENOMEM;
+
+ return expand_upwards(vma, address + PAGE_SIZE);
+ }
+ return 0;
+}
+
+/*
* We enter with non-exclusive mmap_sem (to exclude vma changes,
* but allow concurrent faults), and pte mapped but not yet locked.
* We return with mmap_sem still held, but pte unmapped and unlocked.
if (vma->vm_flags & VM_SHARED)
return VM_FAULT_SIGBUS;
+ /* Check if we need to add a guard page to the stack */
+ if (check_stack_guard_page(vma, address) < 0)
+ return VM_FAULT_SIGSEGV;
+
/* Use the zero-page for reads */
if (!(flags & FAULT_FLAG_WRITE)) {
entry = pte_mkspecial(pfn_pte(my_zero_pfn(address),
unsigned long rlim, retval;
unsigned long newbrk, oldbrk;
struct mm_struct *mm = current->mm;
- struct vm_area_struct *next;
unsigned long min_brk;
bool populate;
}
/* Check against existing mmap mappings. */
- next = find_vma(mm, oldbrk);
- if (next && newbrk + PAGE_SIZE > vm_start_gap(next))
+ if (find_vma_intersection(mm, oldbrk, newbrk+PAGE_SIZE))
goto out;
/* Ok, looks good - let it rip. */
static long vma_compute_subtree_gap(struct vm_area_struct *vma)
{
- unsigned long max, prev_end, subtree_gap;
-
- /*
- * Note: in the rare case of a VM_GROWSDOWN above a VM_GROWSUP, we
- * allow two stack_guard_gaps between them here, and when choosing
- * an unmapped area; whereas when expanding we only require one.
- * That's a little inconsistent, but keeps the code here simpler.
- */
- max = vm_start_gap(vma);
- if (vma->vm_prev) {
- prev_end = vm_end_gap(vma->vm_prev);
- if (max > prev_end)
- max -= prev_end;
- else
- max = 0;
- }
+ unsigned long max, subtree_gap;
+ max = vma->vm_start;
+ if (vma->vm_prev)
+ max -= vma->vm_prev->vm_end;
if (vma->vm_rb.rb_left) {
subtree_gap = rb_entry(vma->vm_rb.rb_left,
struct vm_area_struct, vm_rb)->rb_subtree_gap;
list_for_each_entry(avc, &vma->anon_vma_chain, same_vma)
anon_vma_interval_tree_verify(avc);
vma_unlock_anon_vma(vma);
- highest_address = vm_end_gap(vma);
+ highest_address = vma->vm_end;
vma = vma->vm_next;
i++;
}
if (vma->vm_next)
vma_gap_update(vma->vm_next);
else
- mm->highest_vm_end = vm_end_gap(vma);
+ mm->highest_vm_end = vma->vm_end;
/*
* vma->vm_prev wasn't known when we followed the rbtree to find the
vma_gap_update(vma);
if (end_changed) {
if (!next)
- mm->highest_vm_end = vm_end_gap(vma);
+ mm->highest_vm_end = end;
else if (!adjust_next)
vma_gap_update(next);
}
else if (next)
vma_gap_update(next);
else
- WARN_ON(mm->highest_vm_end != vm_end_gap(vma));
+ mm->highest_vm_end = end;
}
if (insert && file)
uprobe_mmap(insert);
while (true) {
/* Visit left subtree if it looks promising */
- gap_end = vm_start_gap(vma);
+ gap_end = vma->vm_start;
if (gap_end >= low_limit && vma->vm_rb.rb_left) {
struct vm_area_struct *left =
rb_entry(vma->vm_rb.rb_left,
}
}
- gap_start = vma->vm_prev ? vm_end_gap(vma->vm_prev) : 0;
+ gap_start = vma->vm_prev ? vma->vm_prev->vm_end : 0;
check_current:
/* Check if current node has a suitable gap */
if (gap_start > high_limit)
vma = rb_entry(rb_parent(prev),
struct vm_area_struct, vm_rb);
if (prev == vma->vm_rb.rb_left) {
- gap_start = vm_end_gap(vma->vm_prev);
- gap_end = vm_start_gap(vma);
+ gap_start = vma->vm_prev->vm_end;
+ gap_end = vma->vm_start;
goto check_current;
}
}
while (true) {
/* Visit right subtree if it looks promising */
- gap_start = vma->vm_prev ? vm_end_gap(vma->vm_prev) : 0;
+ gap_start = vma->vm_prev ? vma->vm_prev->vm_end : 0;
if (gap_start <= high_limit && vma->vm_rb.rb_right) {
struct vm_area_struct *right =
rb_entry(vma->vm_rb.rb_right,
check_current:
/* Check if current node has a suitable gap */
- gap_end = vm_start_gap(vma);
+ gap_end = vma->vm_start;
if (gap_end < low_limit)
return -ENOMEM;
if (gap_start <= high_limit && gap_end - gap_start >= length)
struct vm_area_struct, vm_rb);
if (prev == vma->vm_rb.rb_right) {
gap_start = vma->vm_prev ?
- vm_end_gap(vma->vm_prev) : 0;
+ vma->vm_prev->vm_end : 0;
goto check_current;
}
}
unsigned long len, unsigned long pgoff, unsigned long flags)
{
struct mm_struct *mm = current->mm;
- struct vm_area_struct *vma, *prev;
+ struct vm_area_struct *vma;
struct vm_unmapped_area_info info;
if (len > TASK_SIZE - mmap_min_addr)
if (addr) {
addr = PAGE_ALIGN(addr);
- vma = find_vma_prev(mm, addr, &prev);
+ vma = find_vma(mm, addr);
if (TASK_SIZE - len >= addr && addr >= mmap_min_addr &&
- (!vma || addr + len <= vm_start_gap(vma)) &&
- (!prev || addr >= vm_end_gap(prev)))
+ (!vma || addr + len <= vma->vm_start))
return addr;
}
const unsigned long len, const unsigned long pgoff,
const unsigned long flags)
{
- struct vm_area_struct *vma, *prev;
+ struct vm_area_struct *vma;
struct mm_struct *mm = current->mm;
unsigned long addr = addr0;
struct vm_unmapped_area_info info;
/* requesting a specific address */
if (addr) {
addr = PAGE_ALIGN(addr);
- vma = find_vma_prev(mm, addr, &prev);
+ vma = find_vma(mm, addr);
if (TASK_SIZE - len >= addr && addr >= mmap_min_addr &&
- (!vma || addr + len <= vm_start_gap(vma)) &&
- (!prev || addr >= vm_end_gap(prev)))
+ (!vma || addr + len <= vma->vm_start))
return addr;
}
* update accounting. This is shared with both the
* grow-up and grow-down cases.
*/
-static int acct_stack_growth(struct vm_area_struct *vma,
- unsigned long size, unsigned long grow)
+static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, unsigned long grow)
{
struct mm_struct *mm = vma->vm_mm;
struct rlimit *rlim = current->signal->rlim;
- unsigned long new_start;
+ unsigned long new_start, actual_size;
/* address space limit tests */
if (!may_expand_vm(mm, grow))
return -ENOMEM;
/* Stack limit test */
- if (size > ACCESS_ONCE(rlim[RLIMIT_STACK].rlim_cur))
+ actual_size = size;
+ if (size && (vma->vm_flags & (VM_GROWSUP | VM_GROWSDOWN)))
+ actual_size -= PAGE_SIZE;
+ if (actual_size > ACCESS_ONCE(rlim[RLIMIT_STACK].rlim_cur))
return -ENOMEM;
/* mlock limit tests */
*/
int expand_upwards(struct vm_area_struct *vma, unsigned long address)
{
- struct vm_area_struct *next;
- unsigned long gap_addr;
- int error = 0;
+ int error;
if (!(vma->vm_flags & VM_GROWSUP))
return -EFAULT;
- /* Guard against wrapping around to address 0. */
- address &= PAGE_MASK;
- address += PAGE_SIZE;
- if (!address)
- return -ENOMEM;
-
- /* Enforce stack_guard_gap */
- gap_addr = address + stack_guard_gap;
- if (gap_addr < address)
- return -ENOMEM;
- next = vma->vm_next;
- if (next && next->vm_start < gap_addr) {
- if (!(next->vm_flags & VM_GROWSUP))
- return -ENOMEM;
- /* Check that both stack segments have the same anon_vma? */
- }
-
- /* We must make sure the anon_vma is allocated. */
+ /*
+ * We must make sure the anon_vma is allocated
+ * so that the anon_vma locking is not a noop.
+ */
if (unlikely(anon_vma_prepare(vma)))
return -ENOMEM;
+ vma_lock_anon_vma(vma);
/*
* vma->vm_start/vm_end cannot change under us because the caller
* is required to hold the mmap_sem in read mode. We need the
* anon_vma lock to serialize against concurrent expand_stacks.
+ * Also guard against wrapping around to address 0.
*/
- vma_lock_anon_vma(vma);
+ if (address < PAGE_ALIGN(address+4))
+ address = PAGE_ALIGN(address+4);
+ else {
+ vma_unlock_anon_vma(vma);
+ return -ENOMEM;
+ }
+ error = 0;
/* Somebody else might have raced and expanded it already */
if (address > vma->vm_end) {
if (vma->vm_next)
vma_gap_update(vma->vm_next);
else
- vma->vm_mm->highest_vm_end = vm_end_gap(vma);
+ vma->vm_mm->highest_vm_end = address;
spin_unlock(&vma->vm_mm->page_table_lock);
perf_event_mmap(vma);
int expand_downwards(struct vm_area_struct *vma,
unsigned long address)
{
- struct vm_area_struct *prev;
- unsigned long gap_addr;
int error;
+ /*
+ * We must make sure the anon_vma is allocated
+ * so that the anon_vma locking is not a noop.
+ */
+ if (unlikely(anon_vma_prepare(vma)))
+ return -ENOMEM;
+
address &= PAGE_MASK;
error = security_mmap_addr(address);
if (error)
return error;
- /* Enforce stack_guard_gap */
- gap_addr = address - stack_guard_gap;
- if (gap_addr > address)
- return -ENOMEM;
- prev = vma->vm_prev;
- if (prev && prev->vm_end > gap_addr) {
- if (!(prev->vm_flags & VM_GROWSDOWN))
- return -ENOMEM;
- /* Check that both stack segments have the same anon_vma? */
- }
-
- /* We must make sure the anon_vma is allocated. */
- if (unlikely(anon_vma_prepare(vma)))
- return -ENOMEM;
+ vma_lock_anon_vma(vma);
/*
* vma->vm_start/vm_end cannot change under us because the caller
* is required to hold the mmap_sem in read mode. We need the
* anon_vma lock to serialize against concurrent expand_stacks.
*/
- vma_lock_anon_vma(vma);
/* Somebody else might have raced and expanded it already */
if (address < vma->vm_start) {
return error;
}
-/* enforced gap between the expanding stack and other mappings. */
-unsigned long stack_guard_gap = 256UL<<PAGE_SHIFT;
-
-static int __init cmdline_parse_stack_guard_gap(char *p)
-{
- unsigned long val;
- char *endptr;
-
- val = simple_strtoul(p, &endptr, 10);
- if (!*endptr)
- stack_guard_gap = val << PAGE_SHIFT;
-
- return 0;
-}
-__setup("stack_guard_gap=", cmdline_parse_stack_guard_gap);
-
+/*
+ * Note how expand_stack() refuses to expand the stack all the way to
+ * abut the next virtual mapping, *unless* that mapping itself is also
+ * a stack mapping. We want to leave room for a guard page, after all
+ * (the guard page itself is not added here, that is done by the
+ * actual page faulting logic)
+ *
+ * This matches the behavior of the guard page logic (see mm/memory.c:
+ * check_stack_guard_page()), which only allows the guard page to be
+ * removed under these circumstances.
+ */
#ifdef CONFIG_STACK_GROWSUP
int expand_stack(struct vm_area_struct *vma, unsigned long address)
{
+ struct vm_area_struct *next;
+
+ address &= PAGE_MASK;
+ next = vma->vm_next;
+ if (next && next->vm_start == address + PAGE_SIZE) {
+ if (!(next->vm_flags & VM_GROWSUP))
+ return -ENOMEM;
+ }
return expand_upwards(vma, address);
}
#else
int expand_stack(struct vm_area_struct *vma, unsigned long address)
{
+ struct vm_area_struct *prev;
+
+ address &= PAGE_MASK;
+ prev = vma->vm_prev;
+ if (prev && prev->vm_end == address) {
+ if (!(prev->vm_flags & VM_GROWSDOWN))
+ return -ENOMEM;
+ }
return expand_downwards(vma, address);
}
vma->vm_prev = prev;
vma_gap_update(vma);
} else
- mm->highest_vm_end = prev ? vm_end_gap(prev) : 0;
+ mm->highest_vm_end = prev ? prev->vm_end : 0;
tail_vma->vm_next = NULL;
if (mm->unmap_area == arch_unmap_area)
addr = prev ? prev->vm_end : mm->mmap_base;