From e277c750ea81076d8dc68694acc7994a024d83b2 Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Mon, 9 May 2011 13:01:09 +0200 Subject: [PATCH] Don't lock guardpage if the stack is growing up commit a09a79f66874c905af35d5bb5e5f2fdc7b6b894d upstream. Linux kernel excludes guard page when performing mlock on a VMA with down-growing stack. However, some architectures have up-growing stack and locking the guard page should be excluded in this case too. This patch fixes lvm2 on PA-RISC (and possibly other architectures with up-growing stack). lvm2 calculates number of used pages when locking and when unlocking and reports an internal error if the numbers mismatch. [ Patch changed fairly extensively to also fix /proc//maps for the grows-up case, and to move things around a bit to clean it all up and share the infrstructure with the /proc bits. Tested on ia64 that has both grow-up and grow-down segments - Linus ] Signed-off-by: Mikulas Patocka Tested-by: Tony Luck Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- fs/proc/task_mmu.c | 12 +++++++----- include/linux/mm.h | 24 +++++++++++++++++++++++- mm/memory.c | 16 +++++++--------- 3 files changed, 37 insertions(+), 15 deletions(-) diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index f269ee673c8b..c4bec29cf7d1 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -211,7 +211,7 @@ static void show_map_vma(struct seq_file *m, struct vm_area_struct *vma) int flags = vma->vm_flags; unsigned long ino = 0; unsigned long long pgoff = 0; - unsigned long start; + unsigned long start, end; dev_t dev = 0; int len; @@ -224,13 +224,15 @@ static void show_map_vma(struct seq_file *m, struct vm_area_struct *vma) /* We don't show the stack guard page in /proc/maps */ start = vma->vm_start; - if (vma->vm_flags & VM_GROWSDOWN) - if (!vma_stack_continue(vma->vm_prev, vma->vm_start)) - start += PAGE_SIZE; + 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_printf(m, "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu %n", start, - vma->vm_end, + end, flags & VM_READ ? 'r' : '-', flags & VM_WRITE ? 'w' : '-', flags & VM_EXEC ? 'x' : '-', diff --git a/include/linux/mm.h b/include/linux/mm.h index 248c94685037..957a90b962f0 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -994,11 +994,33 @@ int set_page_dirty_lock(struct page *page); int clear_page_dirty_for_io(struct page *page); /* Is the vma a continuation of the stack vma above it? */ -static inline int vma_stack_continue(struct vm_area_struct *vma, unsigned long addr) +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 unsigned long move_page_tables(struct vm_area_struct *vma, unsigned long old_addr, struct vm_area_struct *new_vma, unsigned long new_addr, unsigned long len); diff --git a/mm/memory.c b/mm/memory.c index 8b2bb7dcdae5..c8fff7027742 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1412,9 +1412,8 @@ no_page_table: static inline int stack_guard_page(struct vm_area_struct *vma, unsigned long addr) { - return (vma->vm_flags & VM_GROWSDOWN) && - (vma->vm_start == addr) && - !vma_stack_continue(vma->vm_prev, addr); + return stack_guard_page_start(vma, addr) || + stack_guard_page_end(vma, addr+PAGE_SIZE); } int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, @@ -1502,12 +1501,6 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, continue; } - /* - * For mlock, just skip the stack guard page. - */ - if ((gup_flags & FOLL_MLOCK) && stack_guard_page(vma, start)) - goto next_page; - do { struct page *page; unsigned int foll_flags = gup_flags; @@ -1524,6 +1517,11 @@ 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) -- 2.39.5