From a1fde08c74e90accd62d4cfdbf580d2ede938fe7 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Wed, 4 May 2011 21:30:28 -0700 Subject: VM: skip the stack guard page lookup in get_user_pages only for mlock The logic in __get_user_pages() used to skip the stack guard page lookup whenever the caller wasn't interested in seeing what the actual page was. But Michel Lespinasse points out that there are cases where we don't care about the physical page itself (so 'pages' may be NULL), but do want to make sure a page is mapped into the virtual address space. So using the existence of the "pages" array as an indication of whether to look up the guard page or not isn't actually so great, and we really should just use the FOLL_MLOCK bit. But because that bit was only set for the VM_LOCKED case (and not all vma's necessarily have it, even for mlock()), we couldn't do that originally. Fix that by moving the VM_LOCKED check deeper into the call-chain, which actually simplifies many things. Now mlock() gets simpler, and we can also check for FOLL_MLOCK in __get_user_pages() and the code ends up much more straightforward. Reported-and-reviewed-by: Michel Lespinasse Cc: stable@kernel.org Signed-off-by: Linus Torvalds --- mm/memory.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'mm/memory.c') diff --git a/mm/memory.c b/mm/memory.c index 607098d47e74..27f425378112 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1359,7 +1359,7 @@ split_fallthrough: */ mark_page_accessed(page); } - if (flags & FOLL_MLOCK) { + if ((flags & FOLL_MLOCK) && (vma->vm_flags & VM_LOCKED)) { /* * The preliminary mapping check is mainly to avoid the * pointless overhead of lock_page on the ZERO_PAGE @@ -1552,10 +1552,9 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, } /* - * If we don't actually want the page itself, - * and it's the stack guard page, just skip it. + * For mlock, just skip the stack guard page. */ - if (!pages && stack_guard_page(vma, start)) + if ((gup_flags & FOLL_MLOCK) && stack_guard_page(vma, start)) goto next_page; do { -- cgit v1.2.3 From a09a79f66874c905af35d5bb5e5f2fdc7b6b894d Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Mon, 9 May 2011 13:01:09 +0200 Subject: Don't lock guardpage if the stack is growing up 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 Cc: stable@kernel.org Signed-off-by: Linus Torvalds --- fs/proc/task_mmu.c | 12 +++++++----- include/linux/mm.h | 24 +++++++++++++++++++++++- mm/memory.c | 16 +++++++--------- 3 files changed, 37 insertions(+), 15 deletions(-) (limited to 'mm/memory.c') diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 2e7addfd9803..318d8654989b 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -214,7 +214,7 @@ 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; @@ -227,13 +227,15 @@ 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 2348db26bc3d..6507dde38b16 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1011,11 +1011,33 @@ 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 27f425378112..61e66f026563 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); } /** @@ -1551,12 +1550,6 @@ 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; @@ -1573,6 +1566,11 @@ 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) -- cgit v1.2.3