diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 7b6fa398374..1d63bccd00c 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -2578,6 +2578,13 @@ 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/arm/mm/mmap.c b/arch/arm/mm/mmap.c index a7b8d0868bd..99ed2b45b1f 100644 --- a/arch/arm/mm/mmap.c +++ b/arch/arm/mm/mmap.c @@ -107,7 +107,7 @@ 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; } if (len > mm->cached_hole_size) { @@ -204,7 +204,7 @@ 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 385fd30b142..cd7605658dc 100644 --- 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 3b8700c3cdc..5a6a897b2e7 100644 --- a/arch/mips/mm/mmap.c +++ b/arch/mips/mm/mmap.c @@ -103,7 +103,7 @@ 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/powerpc/mm/slice.c b/arch/powerpc/mm/slice.c index 73709f7ce92..9cf001fa64a 100644 --- a/arch/powerpc/mm/slice.c +++ b/arch/powerpc/mm/slice.c @@ -98,7 +98,7 @@ 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 afeb710ec5c..d02741651cd 100644 --- a/arch/sh/mm/mmap.c +++ b/arch/sh/mm/mmap.c @@ -75,7 +75,7 @@ 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; } @@ -158,7 +158,7 @@ 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 46b63be134b..cd456614619 100644 --- a/arch/sparc/kernel/sys_sparc_64.c +++ b/arch/sparc/kernel/sys_sparc_64.c @@ -147,7 +147,7 @@ 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; } @@ -237,7 +237,7 @@ 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 07e14535375..9f076410198 100644 --- a/arch/sparc/mm/hugetlbpage.c +++ b/arch/sparc/mm/hugetlbpage.c @@ -182,7 +182,7 @@ 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 42cfcba4e1e..d659736816b 100644 --- a/arch/tile/mm/hugetlbpage.c +++ b/arch/tile/mm/hugetlbpage.c @@ -312,7 +312,7 @@ 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 51534ef23c1..b91974c4e3e 100644 --- a/arch/x86/kernel/sys_x86_64.c +++ b/arch/x86/kernel/sys_x86_64.c @@ -141,7 +141,7 @@ 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; } if (((flags & MAP_32BIT) || test_thread_flag(TIF_ADDR32)) @@ -213,7 +213,7 @@ 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 f6679a7fb8c..dbc90e6e4c5 100644 --- a/arch/x86/mm/hugetlbpage.c +++ b/arch/x86/mm/hugetlbpage.c @@ -411,7 +411,7 @@ 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/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 0b704c54871..ff55307eaf1 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -169,7 +169,7 @@ 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 6936179207e..1368e20ad26 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -274,11 +274,7 @@ 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 767111b70f0..ab0ca17a6a8 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1060,34 +1060,6 @@ 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 pid_t vm_is_stack(struct task_struct *task, struct vm_area_struct *vma, int in_group); @@ -1497,6 +1469,7 @@ unsigned long ra_submit(struct file_ra_state *ra, struct address_space *mapping, struct file *filp); +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); @@ -1525,6 +1498,30 @@ 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/memory.c b/mm/memory.c index 9844009777d..8181f74e249 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1566,8 +1566,6 @@ static struct page *__alloc_nonmovable_userpage(struct page *page, return alloc_page(GFP_HIGHUSER); } -static inline int stack_guard_page(struct vm_area_struct *vma, unsigned long addr); - static bool __need_migrate_cma_page(struct page *page, struct vm_area_struct *vma, unsigned long start, unsigned int flags) @@ -1831,12 +1829,6 @@ no_page_table: 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 @@ -2000,11 +1992,6 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, 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) @@ -3371,40 +3358,6 @@ 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. @@ -3424,10 +3377,6 @@ 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 89efbf0d6b9..6b0ee14c80c 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -260,6 +260,7 @@ SYSCALL_DEFINE1(brk, unsigned long, brk) unsigned long rlim, retval; unsigned long newbrk, oldbrk; struct mm_struct *mm = current->mm; + struct vm_area_struct *next; unsigned long min_brk; down_write(&mm->mmap_sem); @@ -304,7 +305,8 @@ 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. */ @@ -1512,8 +1514,8 @@ 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; - unsigned long start_addr; + struct vm_area_struct *vma, *prev; + unsigned long start_addr, vm_start, prev_end; if (len > TASK_SIZE) return -ENOMEM; @@ -1523,9 +1525,10 @@ 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 && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma)) && + (!prev || addr >= vm_end_gap(prev))) return addr; } if (len > mm->cached_hole_size) { @@ -1536,7 +1539,17 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, } full_search: - for (vma = find_vma(mm, addr); ; vma = vma->vm_next) { + for (vma = find_vma_prev(mm, addr, &prev); ; prev = vma, + vma = vma->vm_next) { + if (prev) { + prev_end = vm_end_gap(prev); + if (addr < prev_end) { + addr = prev_end; + /* If vma already violates gap, forget it */ + if (vma && addr > vma->vm_start) + addr = vma->vm_start; + } + } /* At this point: (!vma || addr < vma->vm_end). */ if (TASK_SIZE - len < addr) { /* @@ -1551,16 +1564,16 @@ full_search: } return -ENOMEM; } - if (!vma || addr + len <= vma->vm_start) { + vm_start = vma ? vm_start_gap(vma) : TASK_SIZE; + if (addr + len <= vm_start) { /* * Remember the place where we stopped the search: */ mm->free_area_cache = addr + len; return addr; } - if (addr + mm->cached_hole_size < vma->vm_start) - mm->cached_hole_size = vma->vm_start - addr; - addr = vma->vm_end; + if (addr + mm->cached_hole_size < vm_start) + mm->cached_hole_size = vm_start - addr; } } #endif @@ -1584,9 +1597,10 @@ 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, start_addr; + unsigned long vm_start, prev_end; /* requested length too big for entire address space */ if (len > TASK_SIZE) @@ -1598,9 +1612,10 @@ 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 && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma)) && + (!prev || addr >= vm_end_gap(prev))) return addr; } @@ -1624,18 +1639,21 @@ try_again: * else if new region fits below vma->vm_start, * return with success: */ - vma = find_vma(mm, addr); - if (!vma || addr+len <= vma->vm_start) + vma = find_vma_prev(mm, addr, &prev); + vm_start = vma ? vm_start_gap(vma) : mm->mmap_base; + prev_end = vm_end_gap(prev); + + if (addr + len <= vm_start && addr >= prev_end) /* remember the address as a hint for next time */ return (mm->free_area_cache = addr); /* remember the largest hole we saw so far */ - if (addr + mm->cached_hole_size < vma->vm_start) - mm->cached_hole_size = vma->vm_start - addr; - + if (addr + mm->cached_hole_size < vm_start) + mm->cached_hole_size = vm_start - addr; + /* try just below the current vma->vm_start */ - addr = vma->vm_start-len; - } while (len < vma->vm_start); + addr = vm_start - len; + } while (len < vm_start); fail: /* @@ -1838,7 +1856,9 @@ 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) { - int error; + struct vm_area_struct *next; + unsigned long gap_addr; + int error = 0; if (!(vma->vm_flags & VM_GROWSUP)) return -EFAULT; @@ -1847,23 +1867,33 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address) * We must make sure the anon_vma is allocated * so that the anon_vma locking is not a noop. */ + /* 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. */ 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. */ - if (address < PAGE_ALIGN(address+4)) - address = PAGE_ALIGN(address+4); - else { - vma_unlock_anon_vma(vma); - return -ENOMEM; - } - error = 0; + vma_lock_anon_vma(vma); /* Somebody else might have raced and expanded it already */ if (address > vma->vm_end) { @@ -1893,27 +1923,36 @@ 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; - /* - * 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_file_mmap(NULL, 0, 0, 0, address, 1); if (error) return error; - vma_lock_anon_vma(vma); + /* 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->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) { @@ -1937,6 +1976,22 @@ int expand_downwards(struct vm_area_struct *vma, return error; } +/* enforced gap between the expanding stack and other mappings. */ +unsigned long stack_guard_gap = 256UL<