mm: larger stack guard gap, between vmas

commit 1be7107fbe18eed3e319a6c3e83c78254b693acb upstream.

Stack guard page is a useful feature to reduce a risk of stack smashing
into a different mapping. We have been using a single page gap which
is sufficient to prevent having stack adjacent to a different mapping.
But this seems to be insufficient in the light of the stack usage in
userspace. E.g. glibc uses as large as 64kB alloca() in many commonly
used functions. Others use constructs liks gid_t buffer[NGROUPS_MAX]
which is 256kB or stack strings with MAX_ARG_STRLEN.

This will become especially dangerous for suid binaries and the default
no limit for the stack size limit because those applications can be
tricked to consume a large portion of the stack and a single glibc call
could jump over the guard page. These attacks are not theoretical,
unfortunatelly.

Make those attacks less probable by increasing the stack guard gap
to 1MB (on systems with 4k pages; but make it depend on the page size
because systems with larger base pages might cap stack allocations in
the PAGE_SIZE units) which should cover larger alloca() and VLA stack
allocations. It is obviously not a full fix because the problem is
somehow inherent, but it should reduce attack space a lot.

One could argue that the gap size should be configurable from userspace,
but that can be done later when somebody finds that the new 1MB is wrong
for some special case applications.  For now, add a kernel command line
option (stack_guard_gap) to specify the stack gap size (in page units).

Implementation wise, first delete all the old code for stack guard page:
because although we could get away with accounting one extra page in a
stack vma, accounting a larger gap can break userspace - case in point,
a program run with "ulimit -S -v 20000" failed when the 1MB gap was
counted for RLIMIT_AS; similar problems could come with RLIMIT_MLOCK
and strict non-overcommit mode.

Instead of keeping gap inside the stack vma, maintain the stack guard
gap as a gap between vmas: using vm_start_gap() in place of vm_start
(or vm_end_gap() in place of vm_end if VM_GROWSUP) in just those few
places which need to respect the gap - mainly arch_get_unmapped_area(),
and and the vma tree's subtree_gap support for that.

Original-patch-by: Oleg Nesterov <oleg@redhat.com>
Original-patch-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Hugh Dickins <hughd@google.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Tested-by: Helge Deller <deller@gmx.de> # parisc
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
[wt: backport to 4.11: adjust context]
[wt: backport to 4.9: adjust context ; kernel doc was not in admin-guide]
[wt: backport to 4.4: adjust context ; drop ppc hugetlb_radix changes]
[wt: backport to 3.18: adjust context ; no FOLL_POPULATE ;
     s390 uses generic arch_get_unmapped_area()]
Signed-off-by: Willy Tarreau <w@1wt.eu>
[gkh: minor build fixes for 3.18]
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index b2bdea1953e6d49f88e8007d61f07a58ee1246b4..9abe55280cf6ec1176156c2b0497b68427a50fe1 100644 (file)
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -3324,6 +3324,13 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
        spia_pedr=
        spia_peddr=
 
+       stack_guard_gap=        [MM]
+                       override the default stack gap protection. The value
+                       is in page units and it defines how many pages prior
+                       to (for stacks growing down) resp. after (for stacks
+                       growing up) the main stack are reserved for no other
+                       mapping. Default value is 256 pages.
+
        stacktrace      [FTRACE]
                        Enabled the stack tracer on boot up.
 

diff --git a/arch/arc/mm/mmap.c b/arch/arc/mm/mmap.c
index 2e06d56e987bf84c773b01bbfa6a7b4af1ac6fc9..cf4ae6958240074d265b4f26cb6f0d4271105b92 100644 (file)
--- a/arch/arc/mm/mmap.c
+++ b/arch/arc/mm/mmap.c
@@ -64,7 +64,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 
                vma = find_vma(mm, addr);
                if (TASK_SIZE - len >= addr &&
-                   (!vma || addr + len <= vma->vm_start))
+                   (!vma || addr + len <= vm_start_gap(vma)))
                        return addr;
        }
 

diff --git a/arch/arm/mm/mmap.c b/arch/arm/mm/mmap.c
index 5e85ed371364c17657be7d7155139a5e3f536437..8f9d1cf505dddca26311780a2ef6bc2ff2c00d4a 100644 (file)
--- a/arch/arm/mm/mmap.c
+++ b/arch/arm/mm/mmap.c
@@ -89,7 +89,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 
                vma = find_vma(mm, addr);
                if (TASK_SIZE - len >= addr &&
-                   (!vma || addr + len <= vma->vm_start))
+                   (!vma || addr + len <= vm_start_gap(vma)))
                        return addr;
        }
 
@@ -140,7 +140,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
                        addr = PAGE_ALIGN(addr);
                vma = find_vma(mm, addr);
                if (TASK_SIZE - len >= addr &&
-                               (!vma || addr + len <= vma->vm_start))
+                               (!vma || addr + len <= vm_start_gap(vma)))
                        return addr;
        }
 

diff --git a/arch/frv/mm/elf-fdpic.c b/arch/frv/mm/elf-fdpic.c
index 836f14707a627f156343154f359ac1f7758e9fd4..efa59f1f80226e6c951182ad0124aeccd38c7787 100644 (file)
--- a/arch/frv/mm/elf-fdpic.c
+++ b/arch/frv/mm/elf-fdpic.c
@@ -74,7 +74,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsi
                addr = PAGE_ALIGN(addr);
                vma = find_vma(current->mm, addr);
                if (TASK_SIZE - len >= addr &&
-                   (!vma || addr + len <= vma->vm_start))
+                   (!vma || addr + len <= vm_start_gap(vma)))
                        goto success;
        }
 

diff --git a/arch/mips/mm/mmap.c b/arch/mips/mm/mmap.c
index f1baadd56e82e2b0b4f2b79bd82686ea61a112d0..9be924f08f34c98f9c7a6bef8f3dc7ed79bde87f 100644 (file)
--- a/arch/mips/mm/mmap.c
+++ b/arch/mips/mm/mmap.c
@@ -92,7 +92,7 @@ static unsigned long arch_get_unmapped_area_common(struct file *filp,
 
                vma = find_vma(mm, addr);
                if (TASK_SIZE - len >= addr &&
-                   (!vma || addr + len <= vma->vm_start))
+                   (!vma || addr + len <= vm_start_gap(vma)))
                        return addr;
        }
 

diff --git a/arch/parisc/kernel/sys_parisc.c b/arch/parisc/kernel/sys_parisc.c
index 5aba01ac457ffc5d4823cf09c071f02f00a1d015..4dda73c44fee0aef7f4cc656c459ff2a42960281 100644 (file)
--- a/arch/parisc/kernel/sys_parisc.c
+++ b/arch/parisc/kernel/sys_parisc.c
@@ -88,7 +88,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr,
                unsigned long len, unsigned long pgoff, unsigned long flags)
 {
        struct mm_struct *mm = current->mm;
-       struct vm_area_struct *vma;
+       struct vm_area_struct *vma, *prev;
        unsigned long task_size = TASK_SIZE;
        int do_color_align, last_mmap;
        struct vm_unmapped_area_info info;
@@ -115,9 +115,10 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr,
                else
                        addr = PAGE_ALIGN(addr);
 
-               vma = find_vma(mm, addr);
+               vma = find_vma_prev(mm, addr, &prev);
                if (task_size - len >= addr &&
-                   (!vma || addr + len <= vma->vm_start))
+                   (!vma || addr + len <= vm_start_gap(vma)) &&
+                   (!prev || addr >= vm_end_gap(prev)))
                        goto found_addr;
        }
 
@@ -141,7 +142,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
                          const unsigned long len, const unsigned long pgoff,
                          const unsigned long flags)
 {
-       struct vm_area_struct *vma;
+       struct vm_area_struct *vma, *prev;
        struct mm_struct *mm = current->mm;
        unsigned long addr = addr0;
        int do_color_align, last_mmap;
@@ -175,9 +176,11 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
                        addr = COLOR_ALIGN(addr, last_mmap, pgoff);
                else
                        addr = PAGE_ALIGN(addr);
-               vma = find_vma(mm, addr);
+
+               vma = find_vma_prev(mm, addr, &prev);
                if (TASK_SIZE - len >= addr &&
-                   (!vma || addr + len <= vma->vm_start))
+                   (!vma || addr + len <= vm_start_gap(vma)) &&
+                   (!prev || addr >= vm_end_gap(prev)))
                        goto found_addr;
        }
 

diff --git a/arch/powerpc/mm/slice.c b/arch/powerpc/mm/slice.c
index ded0ea1afde4021578d21d2e969318ea6cd046eb..4c1462611576c002c55206fbe5937d5a101ca73d 100644 (file)
--- a/arch/powerpc/mm/slice.c
+++ b/arch/powerpc/mm/slice.c
@@ -105,7 +105,7 @@ static int slice_area_is_free(struct mm_struct *mm, unsigned long addr,
        if ((mm->task_size - len) < addr)
                return 0;
        vma = find_vma(mm, addr);
-       return (!vma || (addr + len) <= vma->vm_start);
+       return (!vma || (addr + len) <= vm_start_gap(vma));
 }
 
 static int slice_low_has_vma(struct mm_struct *mm, unsigned long slice)

diff --git a/arch/sh/mm/mmap.c b/arch/sh/mm/mmap.c
index 6777177807c26f5d6630ec48535bb4f7d5eba0e2..7df7d59441889aa8bc4a748cd4a40dc94ab89cff 100644 (file)
--- a/arch/sh/mm/mmap.c
+++ b/arch/sh/mm/mmap.c
@@ -63,7 +63,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr,
 
                vma = find_vma(mm, addr);
                if (TASK_SIZE - len >= addr &&
-                   (!vma || addr + len <= vma->vm_start))
+                   (!vma || addr + len <= vm_start_gap(vma)))
                        return addr;
        }
 
@@ -113,7 +113,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 
                vma = find_vma(mm, addr);
                if (TASK_SIZE - len >= addr &&
-                   (!vma || addr + len <= vma->vm_start))
+                   (!vma || addr + len <= vm_start_gap(vma)))
                        return addr;
        }
 

diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c
index c690c8e16a96ef2758fca4e9af8080ec7af6c17a..7f0f7c01b29717878968ef6804df96fbe800f586 100644 (file)
--- a/arch/sparc/kernel/sys_sparc_64.c
+++ b/arch/sparc/kernel/sys_sparc_64.c
@@ -118,7 +118,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsi
 
                vma = find_vma(mm, addr);
                if (task_size - len >= addr &&
-                   (!vma || addr + len <= vma->vm_start))
+                   (!vma || addr + len <= vm_start_gap(vma)))
                        return addr;
        }
 
@@ -181,7 +181,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 
                vma = find_vma(mm, addr);
                if (task_size - len >= addr &&
-                   (!vma || addr + len <= vma->vm_start))
+                   (!vma || addr + len <= vm_start_gap(vma)))
                        return addr;
        }
 

diff --git a/arch/sparc/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c
index 4242eab12e10738e8bdbf6117f7be26d45528a48..2b6fae615fb1601383f230c0c1cc4b08b9da7397 100644 (file)
--- a/arch/sparc/mm/hugetlbpage.c
+++ b/arch/sparc/mm/hugetlbpage.c
@@ -115,7 +115,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
                addr = ALIGN(addr, HPAGE_SIZE);
                vma = find_vma(mm, addr);
                if (task_size - len >= addr &&
-                   (!vma || addr + len <= vma->vm_start))
+                   (!vma || addr + len <= vm_start_gap(vma)))
                        return addr;
        }
        if (mm->get_unmapped_area == arch_get_unmapped_area)

diff --git a/arch/tile/mm/hugetlbpage.c b/arch/tile/mm/hugetlbpage.c
index 8a00c7b7b862b0b8f1be655129d5e6e89721b936..52deac203eac5745ce5bd3d93ea8b111b47b204c 100644 (file)
--- a/arch/tile/mm/hugetlbpage.c
+++ b/arch/tile/mm/hugetlbpage.c
@@ -237,7 +237,7 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
                addr = ALIGN(addr, huge_page_size(h));
                vma = find_vma(mm, addr);
                if (TASK_SIZE - len >= addr &&
-                   (!vma || addr + len <= vma->vm_start))
+                   (!vma || addr + len <= vm_start_gap(vma)))
                        return addr;
        }
        if (current->mm->get_unmapped_area == arch_get_unmapped_area)

diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c
index 30277e27431acde9a9320e0b1be4470bddb40e3a..d050393d3be2565c5ff80e1623db1d4b9bda089f 100644 (file)
--- a/arch/x86/kernel/sys_x86_64.c
+++ b/arch/x86/kernel/sys_x86_64.c
@@ -127,7 +127,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
                addr = PAGE_ALIGN(addr);
                vma = find_vma(mm, addr);
                if (end - len >= addr &&
-                   (!vma || addr + len <= vma->vm_start))
+                   (!vma || addr + len <= vm_start_gap(vma)))
                        return addr;
        }
 
@@ -166,7 +166,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
                addr = PAGE_ALIGN(addr);
                vma = find_vma(mm, addr);
                if (TASK_SIZE - len >= addr &&
-                               (!vma || addr + len <= vma->vm_start))
+                               (!vma || addr + len <= vm_start_gap(vma)))
                        return addr;
        }
 

diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
index 9161f764121e95daad0eff178210eb98d9dd31b4..c504866dc807dc9c8d46cd35a1ef36772175508b 100644 (file)
--- a/arch/x86/mm/hugetlbpage.c
+++ b/arch/x86/mm/hugetlbpage.c
@@ -144,7 +144,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
                addr = ALIGN(addr, huge_page_size(h));
                vma = find_vma(mm, addr);
                if (TASK_SIZE - len >= addr &&
-                   (!vma || addr + len <= vma->vm_start))
+                   (!vma || addr + len <= vm_start_gap(vma)))
                        return addr;
        }
        if (mm->get_unmapped_area == arch_get_unmapped_area)

diff --git a/arch/xtensa/kernel/syscall.c b/arch/xtensa/kernel/syscall.c
index 5d3f7a119ed1e91a5baf6fe5af7a33d842146533..1ff0b92eeae7cc85fbc84cb006471d1f516764fd 100644 (file)
--- a/arch/xtensa/kernel/syscall.c
+++ b/arch/xtensa/kernel/syscall.c
@@ -86,7 +86,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr,
                /* At this point:  (!vmm || addr < vmm->vm_end). */
                if (TASK_SIZE - len < addr)
                        return -ENOMEM;
-               if (!vmm || addr + len <= vmm->vm_start)
+               if (!vmm || addr + len <= vm_start_gap(vmm))
                        return addr;
                addr = vmm->vm_end;
                if (flags & MAP_SHARED)

diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 1e2872b25343f106df7a96d0b667e194dd070c54..148c4e9cf22fee403b377e59efc8ec1a358cec37 100644 (file)
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -171,7 +171,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
                addr = ALIGN(addr, huge_page_size(h));
                vma = find_vma(mm, addr);
                if (TASK_SIZE - len >= addr &&
-                   (!vma || addr + len <= vma->vm_start))
+                   (!vma || addr + len <= vm_start_gap(vma)))
                        return addr;
        }
 

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index af33fb77196fa23c749cc17a676ac58611424c82..aea2d0bf7174496f7498581e01010076ed01c822 100644 (file)
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -284,11 +284,7 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
 
        /* We don't show the stack guard page in /proc/maps */
        start = vma->vm_start;
-       if (stack_guard_page_start(vma, start))
-               start += PAGE_SIZE;
        end = vma->vm_end;
-       if (stack_guard_page_end(vma, end))
-               end -= PAGE_SIZE;
 
        seq_setwidth(m, 25 + sizeof(void *) * 6 - 1);
        seq_printf(m, "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu ",

diff --git a/include/linux/mm.h b/include/linux/mm.h
index db853dee1ec5291023860ac1975e1a35200f5cd6..54ad2e45bc6b92baec5e342971427a5a9b96d8c8 100644 (file)
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1242,34 +1242,6 @@ int set_page_dirty_lock(struct page *page);
 int clear_page_dirty_for_io(struct page *page);
 int get_cmdline(struct task_struct *task, char *buffer, int buflen);
 
-/* Is the vma a continuation of the stack vma above it? */
-static inline int vma_growsdown(struct vm_area_struct *vma, unsigned long addr)
-{
-       return vma && (vma->vm_end == addr) && (vma->vm_flags & VM_GROWSDOWN);
-}
-
-static inline int stack_guard_page_start(struct vm_area_struct *vma,
-                                            unsigned long addr)
-{
-       return (vma->vm_flags & VM_GROWSDOWN) &&
-               (vma->vm_start == addr) &&
-               !vma_growsdown(vma->vm_prev, addr);
-}
-
-/* Is the vma a continuation of the stack vma below it? */
-static inline int vma_growsup(struct vm_area_struct *vma, unsigned long addr)
-{
-       return vma && (vma->vm_start == addr) && (vma->vm_flags & VM_GROWSUP);
-}
-
-static inline int stack_guard_page_end(struct vm_area_struct *vma,
-                                          unsigned long addr)
-{
-       return (vma->vm_flags & VM_GROWSUP) &&
-               (vma->vm_end == addr) &&
-               !vma_growsup(vma->vm_next, addr);
-}
-
 extern struct task_struct *task_of_stack(struct task_struct *task,
                                struct vm_area_struct *vma, bool in_group);
 
@@ -1930,6 +1902,7 @@ void page_cache_async_readahead(struct address_space *mapping,
 
 unsigned long max_sane_readahead(unsigned long nr);
 
+extern unsigned long stack_guard_gap;
 /* Generic expand stack which grows the stack according to GROWS{UP,DOWN} */
 extern int expand_stack(struct vm_area_struct *vma, unsigned long address);
 
@@ -1958,6 +1931,30 @@ static inline struct vm_area_struct * find_vma_intersection(struct mm_struct * m
        return vma;
 }
 
+static inline unsigned long vm_start_gap(struct vm_area_struct *vma)
+{
+       unsigned long vm_start = vma->vm_start;
+
+       if (vma->vm_flags & VM_GROWSDOWN) {
+               vm_start -= stack_guard_gap;
+               if (vm_start > vma->vm_start)
+                       vm_start = 0;
+       }
+       return vm_start;
+}
+
+static inline unsigned long vm_end_gap(struct vm_area_struct *vma)
+{
+       unsigned long vm_end = vma->vm_end;
+
+       if (vma->vm_flags & VM_GROWSUP) {
+               vm_end += stack_guard_gap;
+               if (vm_end < vma->vm_end)
+                       vm_end = -PAGE_SIZE;
+       }
+       return vm_end;
+}
+
 static inline unsigned long vma_pages(struct vm_area_struct *vma)
 {
        return (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;

diff --git a/mm/gup.c b/mm/gup.c
index 3cec4df06e6bd311dedec8f824945273714604b7..ce1630bf0b953d60987d9fe360e3aa4441c536a9 100644 (file)
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -275,11 +275,6 @@ static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma,
        unsigned int fault_flags = 0;
        int ret;
 
-       /* For mlock, just skip the stack guard page. */
-       if ((*flags & FOLL_MLOCK) &&
-                       (stack_guard_page_start(vma, address) ||
-                        stack_guard_page_end(vma, address + PAGE_SIZE)))
-               return -ENOENT;
        if (*flags & FOLL_WRITE)
                fault_flags |= FAULT_FLAG_WRITE;
        if (nonblocking)

diff --git a/mm/memory.c b/mm/memory.c
index 6ca26c332712034f13c5610049fc3e45e278f33d..0c4f5e36b1558797f97404bec3b00e76efe343b8 100644 (file)
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2579,40 +2579,6 @@ out_release:
        return ret;
 }
 
-/*
- * 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.
@@ -2633,10 +2599,6 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
        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),

diff --git a/mm/mmap.c b/mm/mmap.c
index f03267136fb7156b7e59f3f9d674a250eec63714..14ccc949921f69bf7687d6a4d70b51e11c390346 100644 (file)
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -290,6 +290,7 @@ SYSCALL_DEFINE1(brk, unsigned long, brk)
        unsigned long retval;
        unsigned long newbrk, oldbrk;
        struct mm_struct *mm = current->mm;
+       struct vm_area_struct *next;
        unsigned long min_brk;
        bool populate;
 
@@ -334,7 +335,8 @@ SYSCALL_DEFINE1(brk, unsigned long, brk)
        }
 
        /* Check against existing mmap mappings. */
-       if (find_vma_intersection(mm, oldbrk, newbrk+PAGE_SIZE))
+       next = find_vma(mm, oldbrk);
+       if (next && newbrk + PAGE_SIZE > vm_start_gap(next))
                goto out;
 
        /* Ok, looks good - let it rip. */
@@ -357,10 +359,22 @@ out:
 
 static long vma_compute_subtree_gap(struct vm_area_struct *vma)
 {
-       unsigned long max, subtree_gap;
-       max = vma->vm_start;
-       if (vma->vm_prev)
-               max -= vma->vm_prev->vm_end;
+       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;
+       }
        if (vma->vm_rb.rb_left) {
                subtree_gap = rb_entry(vma->vm_rb.rb_left,
                                struct vm_area_struct, vm_rb)->rb_subtree_gap;
@@ -453,7 +467,7 @@ static void validate_mm(struct mm_struct *mm)
                        anon_vma_unlock_read(anon_vma);
                }
 
-               highest_address = vma->vm_end;
+               highest_address = vm_end_gap(vma);
                vma = vma->vm_next;
                i++;
        }
@@ -622,7 +636,7 @@ void __vma_link_rb(struct mm_struct *mm, struct vm_area_struct *vma,
        if (vma->vm_next)
                vma_gap_update(vma->vm_next);
        else
-               mm->highest_vm_end = vma->vm_end;
+               mm->highest_vm_end = vm_end_gap(vma);
 
        /*
         * vma->vm_prev wasn't known when we followed the rbtree to find the
@@ -874,7 +888,7 @@ again:                      remove_next = 1 + (end > next->vm_end);
                        vma_gap_update(vma);
                if (end_changed) {
                        if (!next)
-                               mm->highest_vm_end = end;
+                               mm->highest_vm_end = vm_end_gap(vma);
                        else if (!adjust_next)
                                vma_gap_update(next);
                }
@@ -917,7 +931,7 @@ again:                      remove_next = 1 + (end > next->vm_end);
                else if (next)
                        vma_gap_update(next);
                else
-                       mm->highest_vm_end = end;
+                       VM_WARN_ON(mm->highest_vm_end != vm_end_gap(vma));
        }
        if (insert && file)
                uprobe_mmap(insert);
@@ -1740,7 +1754,7 @@ unsigned long unmapped_area(struct vm_unmapped_area_info *info)
 
        while (true) {
                /* Visit left subtree if it looks promising */
-               gap_end = vma->vm_start;
+               gap_end = vm_start_gap(vma);
                if (gap_end >= low_limit && vma->vm_rb.rb_left) {
                        struct vm_area_struct *left =
                                rb_entry(vma->vm_rb.rb_left,
@@ -1751,7 +1765,7 @@ unsigned long unmapped_area(struct vm_unmapped_area_info *info)
                        }
                }
 
-               gap_start = vma->vm_prev ? vma->vm_prev->vm_end : 0;
+               gap_start = vma->vm_prev ? vm_end_gap(vma->vm_prev) : 0;
 check_current:
                /* Check if current node has a suitable gap */
                if (gap_start > high_limit)
@@ -1778,8 +1792,8 @@ check_current:
                        vma = rb_entry(rb_parent(prev),
                                       struct vm_area_struct, vm_rb);
                        if (prev == vma->vm_rb.rb_left) {
-                               gap_start = vma->vm_prev->vm_end;
-                               gap_end = vma->vm_start;
+                               gap_start = vm_end_gap(vma->vm_prev);
+                               gap_end = vm_start_gap(vma);
                                goto check_current;
                        }
                }
@@ -1843,7 +1857,7 @@ unsigned long unmapped_area_topdown(struct vm_unmapped_area_info *info)
 
        while (true) {
                /* Visit right subtree if it looks promising */
-               gap_start = vma->vm_prev ? vma->vm_prev->vm_end : 0;
+               gap_start = vma->vm_prev ? vm_end_gap(vma->vm_prev) : 0;
                if (gap_start <= high_limit && vma->vm_rb.rb_right) {
                        struct vm_area_struct *right =
                                rb_entry(vma->vm_rb.rb_right,
@@ -1856,7 +1870,7 @@ unsigned long unmapped_area_topdown(struct vm_unmapped_area_info *info)
 
 check_current:
                /* Check if current node has a suitable gap */
-               gap_end = vma->vm_start;
+               gap_end = vm_start_gap(vma);
                if (gap_end < low_limit)
                        return -ENOMEM;
                if (gap_start <= high_limit && gap_end - gap_start >= length)
@@ -1882,7 +1896,7 @@ check_current:
                                       struct vm_area_struct, vm_rb);
                        if (prev == vma->vm_rb.rb_right) {
                                gap_start = vma->vm_prev ?
-                                       vma->vm_prev->vm_end : 0;
+                                       vm_end_gap(vma->vm_prev) : 0;
                                goto check_current;
                        }
                }
@@ -1920,7 +1934,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
                unsigned long len, unsigned long pgoff, unsigned long flags)
 {
        struct mm_struct *mm = current->mm;
-       struct vm_area_struct *vma;
+       struct vm_area_struct *vma, *prev;
        struct vm_unmapped_area_info info;
 
        if (len > TASK_SIZE - mmap_min_addr)
@@ -1931,9 +1945,10 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 
        if (addr) {
                addr = PAGE_ALIGN(addr);
-               vma = find_vma(mm, addr);
+               vma = find_vma_prev(mm, addr, &prev);
                if (TASK_SIZE - len >= addr && addr >= mmap_min_addr &&
-                   (!vma || addr + len <= vma->vm_start))
+                   (!vma || addr + len <= vm_start_gap(vma)) &&
+                   (!prev || addr >= vm_end_gap(prev)))
                        return addr;
        }
 
@@ -1956,7 +1971,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
                          const unsigned long len, const unsigned long pgoff,
                          const unsigned long flags)
 {
-       struct vm_area_struct *vma;
+       struct vm_area_struct *vma, *prev;
        struct mm_struct *mm = current->mm;
        unsigned long addr = addr0;
        struct vm_unmapped_area_info info;
@@ -1971,9 +1986,10 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
        /* requesting a specific address */
        if (addr) {
                addr = PAGE_ALIGN(addr);
-               vma = find_vma(mm, addr);
+               vma = find_vma_prev(mm, addr, &prev);
                if (TASK_SIZE - len >= addr && addr >= mmap_min_addr &&
-                               (!vma || addr + len <= vma->vm_start))
+                               (!vma || addr + len <= vm_start_gap(vma)) &&
+                               (!prev || addr >= vm_end_gap(prev)))
                        return addr;
        }
 
@@ -2099,21 +2115,19 @@ find_vma_prev(struct mm_struct *mm, unsigned long 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, actual_size;
+       unsigned long new_start;
 
        /* address space limit tests */
        if (!may_expand_vm(mm, grow))
                return -ENOMEM;
 
        /* Stack limit test */
-       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))
+       if (size > ACCESS_ONCE(rlim[RLIMIT_STACK].rlim_cur))
                return -ENOMEM;
 
        /* mlock limit tests */
@@ -2154,17 +2168,30 @@ static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, uns
  */
 int expand_upwards(struct vm_area_struct *vma, unsigned long address)
 {
+       struct vm_area_struct *next;
+       unsigned long gap_addr;
        int error = 0;
 
        if (!(vma->vm_flags & VM_GROWSUP))
                return -EFAULT;
 
        /* Guard against wrapping around to address 0. */
-       if (address < PAGE_ALIGN(address+4))
-               address = PAGE_ALIGN(address+4);
-       else
+       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. */
        if (unlikely(anon_vma_prepare(vma)))
                return -ENOMEM;
@@ -2205,7 +2232,7 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address)
                                if (vma->vm_next)
                                        vma_gap_update(vma->vm_next);
                                else
-                                       vma->vm_mm->highest_vm_end = address;
+                                       vma->vm_mm->highest_vm_end = vm_end_gap(vma);
                                spin_unlock(&vma->vm_mm->page_table_lock);
 
                                perf_event_mmap(vma);
@@ -2225,6 +2252,8 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address)
 int expand_downwards(struct vm_area_struct *vma,
                                   unsigned long address)
 {
+       struct vm_area_struct *prev;
+       unsigned long gap_addr;
        int error;
 
        address &= PAGE_MASK;
@@ -2232,6 +2261,17 @@ int expand_downwards(struct vm_area_struct *vma,
        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;
@@ -2283,28 +2323,25 @@ int expand_downwards(struct vm_area_struct *vma,
        return error;
 }
 
-/*
- * 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.
- */
+/* 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);
+
 #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);
 }
 
@@ -2326,14 +2363,6 @@ find_extend_vma(struct mm_struct *mm, unsigned long addr)
 #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);
 }
 
@@ -2429,7 +2458,7 @@ detach_vmas_to_be_unmapped(struct mm_struct *mm, struct vm_area_struct *vma,
                vma->vm_prev = prev;
                vma_gap_update(vma);
        } else
-               mm->highest_vm_end = prev ? prev->vm_end : 0;
+               mm->highest_vm_end = prev ? vm_end_gap(prev) : 0;
        tail_vma->vm_next = NULL;
 
        /* Kill the cache */