From 137baabe351e0554d06c6d5c84059fe343e2791e Mon Sep 17 00:00:00 2001 From: Wei Yongjun Date: Mon, 17 Oct 2016 15:47:39 +0000 Subject: [PATCH 1/4] mm/numa: Remove duplicated include from mprotect.c Signed-off-by: Wei Yongjun Cc: Dave Hansen Cc: linux-mm@kvack.org Cc: Andrew Morton Cc: Mel Gorman Cc: "Kirill A. Shutemov" Link: http://lkml.kernel.org/r/1476719259-6214-1-git-send-email-weiyj.lk@gmail.com Signed-off-by: Thomas Gleixner --- mm/mprotect.c | 1 - 1 file changed, 1 deletion(-) diff --git a/mm/mprotect.c b/mm/mprotect.c index bcdbe62f3e6d..11936526b08b 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -25,7 +25,6 @@ #include #include #include -#include #include #include #include From 0a1eb2d474edfe75466be6b4677ad84e5e8ca3f5 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Fri, 30 Sep 2016 10:58:56 -0700 Subject: [PATCH 2/4] fs/proc: Stop reporting eip and esp in /proc/PID/stat Reporting these fields on a non-current task is dangerous. If the task is in any state other than normal kernel code, they may contain garbage or even kernel addresses on some architectures. (x86_64 used to do this. I bet lots of architectures still do.) With CONFIG_THREAD_INFO_IN_TASK=y, it can OOPS, too. As far as I know, there are no use programs that make any material use of these fields, so just get rid of them. Reported-by: Jann Horn Signed-off-by: Andy Lutomirski Acked-by: Thomas Gleixner Cc: Al Viro Cc: Andrew Morton Cc: Borislav Petkov Cc: Brian Gerst Cc: Kees Cook Cc: Linus Torvalds Cc: Linux API Cc: Peter Zijlstra Cc: Tetsuo Handa Cc: Tycho Andersen Link: http://lkml.kernel.org/r/a5fed4c3f4e33ed25d4bb03567e329bc5a712bcc.1475257877.git.luto@kernel.org Signed-off-by: Ingo Molnar --- fs/proc/array.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/fs/proc/array.c b/fs/proc/array.c index 89600fd5963d..81818adb8e9e 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -412,10 +412,11 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, mm = get_task_mm(task); if (mm) { vsize = task_vsize(mm); - if (permitted) { - eip = KSTK_EIP(task); - esp = KSTK_ESP(task); - } + /* + * esp and eip are intentionally zeroed out. There is no + * non-racy way to read them without freezing the task. + * Programs that need reliable values can use ptrace(2). + */ } get_task_comm(tcomm, task); From b18cb64ead400c01bf1580eeba330ace51f8087d Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Fri, 30 Sep 2016 10:58:57 -0700 Subject: [PATCH 3/4] fs/proc: Stop trying to report thread stacks This reverts more of: b76437579d13 ("procfs: mark thread stack correctly in proc//maps") ... which was partially reverted by: 65376df58217 ("proc: revert /proc//maps [stack:TID] annotation") Originally, /proc/PID/task/TID/maps was the same as /proc/TID/maps. In current kernels, /proc/PID/maps (or /proc/TID/maps even for threads) shows "[stack]" for VMAs in the mm's stack address range. In contrast, /proc/PID/task/TID/maps uses KSTK_ESP to guess the target thread's stack's VMA. This is racy, probably returns garbage and, on arches with CONFIG_TASK_INFO_IN_THREAD=y, is also crash-prone: KSTK_ESP is not safe to use on tasks that aren't known to be running ordinary process-context kernel code. This patch removes the difference and just shows "[stack]" for VMAs in the mm's stack range. This is IMO much more sensible -- the actual "stack" address really is treated specially by the VM code, and the current thread stack isn't even well-defined for programs that frequently switch stacks on their own. Reported-by: Jann Horn Signed-off-by: Andy Lutomirski Acked-by: Thomas Gleixner Cc: Al Viro Cc: Andrew Morton Cc: Borislav Petkov Cc: Brian Gerst Cc: Johannes Weiner Cc: Kees Cook Cc: Linus Torvalds Cc: Linux API Cc: Peter Zijlstra Cc: Tycho Andersen Link: http://lkml.kernel.org/r/3e678474ec14e0a0ec34c611016753eea2e1b8ba.1475257877.git.luto@kernel.org Signed-off-by: Ingo Molnar --- Documentation/filesystems/proc.txt | 26 -------------------------- fs/proc/task_mmu.c | 29 ++++++++++------------------- fs/proc/task_nommu.c | 26 +++++++++----------------- 3 files changed, 19 insertions(+), 62 deletions(-) diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt index 219ffd41a911..74329fd0add2 100644 --- a/Documentation/filesystems/proc.txt +++ b/Documentation/filesystems/proc.txt @@ -395,32 +395,6 @@ is not associated with a file: or if empty, the mapping is anonymous. -The /proc/PID/task/TID/maps is a view of the virtual memory from the viewpoint -of the individual tasks of a process. In this file you will see a mapping marked -as [stack] if that task sees it as a stack. Hence, for the example above, the -task-level map, i.e. /proc/PID/task/TID/maps for thread 1001 will look like this: - -08048000-08049000 r-xp 00000000 03:00 8312 /opt/test -08049000-0804a000 rw-p 00001000 03:00 8312 /opt/test -0804a000-0806b000 rw-p 00000000 00:00 0 [heap] -a7cb1000-a7cb2000 ---p 00000000 00:00 0 -a7cb2000-a7eb2000 rw-p 00000000 00:00 0 -a7eb2000-a7eb3000 ---p 00000000 00:00 0 -a7eb3000-a7ed5000 rw-p 00000000 00:00 0 [stack] -a7ed5000-a8008000 r-xp 00000000 03:00 4222 /lib/libc.so.6 -a8008000-a800a000 r--p 00133000 03:00 4222 /lib/libc.so.6 -a800a000-a800b000 rw-p 00135000 03:00 4222 /lib/libc.so.6 -a800b000-a800e000 rw-p 00000000 00:00 0 -a800e000-a8022000 r-xp 00000000 03:00 14462 /lib/libpthread.so.0 -a8022000-a8023000 r--p 00013000 03:00 14462 /lib/libpthread.so.0 -a8023000-a8024000 rw-p 00014000 03:00 14462 /lib/libpthread.so.0 -a8024000-a8027000 rw-p 00000000 00:00 0 -a8027000-a8043000 r-xp 00000000 03:00 8317 /lib/ld-linux.so.2 -a8043000-a8044000 r--p 0001b000 03:00 8317 /lib/ld-linux.so.2 -a8044000-a8045000 rw-p 0001c000 03:00 8317 /lib/ld-linux.so.2 -aff35000-aff4a000 rw-p 00000000 00:00 0 -ffffe000-fffff000 r-xp 00000000 00:00 0 [vdso] - The /proc/PID/smaps is an extension based on maps, showing the memory consumption for each of the process's mappings. For each of mappings there is a series of lines such as the following: diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 6909582ce5e5..35b92d81692f 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -266,24 +266,15 @@ static int do_maps_open(struct inode *inode, struct file *file, * /proc/PID/maps that is the stack of the main task. */ static int is_stack(struct proc_maps_private *priv, - struct vm_area_struct *vma, int is_pid) + struct vm_area_struct *vma) { - int stack = 0; - - if (is_pid) { - stack = vma->vm_start <= vma->vm_mm->start_stack && - vma->vm_end >= vma->vm_mm->start_stack; - } else { - struct inode *inode = priv->inode; - struct task_struct *task; - - rcu_read_lock(); - task = pid_task(proc_pid(inode), PIDTYPE_PID); - if (task) - stack = vma_is_stack_for_task(vma, task); - rcu_read_unlock(); - } - return stack; + /* + * We make no effort to guess what a given thread considers to be + * its "stack". It's not even well-defined for programs written + * languages like Go. + */ + return vma->vm_start <= vma->vm_mm->start_stack && + vma->vm_end >= vma->vm_mm->start_stack; } static void @@ -354,7 +345,7 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid) goto done; } - if (is_stack(priv, vma, is_pid)) + if (is_stack(priv, vma)) name = "[stack]"; } @@ -1669,7 +1660,7 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid) seq_file_path(m, file, "\n\t= "); } else if (vma->vm_start <= mm->brk && vma->vm_end >= mm->start_brk) { seq_puts(m, " heap"); - } else if (is_stack(proc_priv, vma, is_pid)) { + } else if (is_stack(proc_priv, vma)) { seq_puts(m, " stack"); } diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c index faacb0c0d857..37175621e890 100644 --- a/fs/proc/task_nommu.c +++ b/fs/proc/task_nommu.c @@ -124,25 +124,17 @@ unsigned long task_statm(struct mm_struct *mm, } static int is_stack(struct proc_maps_private *priv, - struct vm_area_struct *vma, int is_pid) + struct vm_area_struct *vma) { struct mm_struct *mm = vma->vm_mm; - int stack = 0; - if (is_pid) { - stack = vma->vm_start <= mm->start_stack && - vma->vm_end >= mm->start_stack; - } else { - struct inode *inode = priv->inode; - struct task_struct *task; - - rcu_read_lock(); - task = pid_task(proc_pid(inode), PIDTYPE_PID); - if (task) - stack = vma_is_stack_for_task(vma, task); - rcu_read_unlock(); - } - return stack; + /* + * We make no effort to guess what a given thread considers to be + * its "stack". It's not even well-defined for programs written + * languages like Go. + */ + return vma->vm_start <= mm->start_stack && + vma->vm_end >= mm->start_stack; } /* @@ -184,7 +176,7 @@ static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma, if (file) { seq_pad(m, ' '); seq_file_path(m, file, ""); - } else if (mm && is_stack(priv, vma, is_pid)) { + } else if (mm && is_stack(priv, vma)) { seq_pad(m, ' '); seq_printf(m, "[stack]"); } From d17af5056cf9e9fc05e68832f7c15687fcc12281 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Fri, 30 Sep 2016 10:58:58 -0700 Subject: [PATCH 4/4] mm: Change vm_is_stack_for_task() to vm_is_stack_for_current() Asking for a non-current task's stack can't be done without races unless the task is frozen in kernel mode. As far as I know, vm_is_stack_for_task() never had a safe non-current use case. The __unused annotation is because some KSTK_ESP implementations ignore their parameter, which IMO is further justification for this patch. Signed-off-by: Andy Lutomirski Acked-by: Thomas Gleixner Cc: Al Viro Cc: Andrew Morton Cc: Borislav Petkov Cc: Brian Gerst Cc: Jann Horn Cc: Kees Cook Cc: Linus Torvalds Cc: Linux API Cc: Peter Zijlstra Cc: Tycho Andersen Link: http://lkml.kernel.org/r/4c3f68f426e6c061ca98b4fc7ef85ffbb0a25b0c.1475257877.git.luto@kernel.org Signed-off-by: Ingo Molnar --- include/linux/mm.h | 2 +- mm/util.c | 4 +++- security/selinux/hooks.c | 2 +- 3 files changed, 5 insertions(+), 3 deletions(-) diff --git a/include/linux/mm.h b/include/linux/mm.h index e9caec6a51e9..a658a5167bce 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1391,7 +1391,7 @@ static inline int stack_guard_page_end(struct vm_area_struct *vma, !vma_growsup(vma->vm_next, addr); } -int vma_is_stack_for_task(struct vm_area_struct *vma, struct task_struct *t); +int vma_is_stack_for_current(struct vm_area_struct *vma); extern unsigned long move_page_tables(struct vm_area_struct *vma, unsigned long old_addr, struct vm_area_struct *new_vma, diff --git a/mm/util.c b/mm/util.c index 662cddf914af..c174e8921995 100644 --- a/mm/util.c +++ b/mm/util.c @@ -230,8 +230,10 @@ void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma, } /* Check if the vma is being used as a stack by this task */ -int vma_is_stack_for_task(struct vm_area_struct *vma, struct task_struct *t) +int vma_is_stack_for_current(struct vm_area_struct *vma) { + struct task_struct * __maybe_unused t = current; + return (vma->vm_start <= KSTK_ESP(t) && vma->vm_end >= KSTK_ESP(t)); } diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 085057936287..09fd6108e421 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -3557,7 +3557,7 @@ static int selinux_file_mprotect(struct vm_area_struct *vma, } else if (!vma->vm_file && ((vma->vm_start <= vma->vm_mm->start_stack && vma->vm_end >= vma->vm_mm->start_stack) || - vma_is_stack_for_task(vma, current))) { + vma_is_stack_for_current(vma))) { rc = current_has_perm(current, PROCESS__EXECSTACK); } else if (vma->vm_file && vma->anon_vma) { /*