From 314e51b9851b4f4e8ab302243ff5a6fc6147f379 Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Mon, 8 Oct 2012 16:29:02 -0700 Subject: mm: kill vma flag VM_RESERVED and mm->reserved_vm counter A long time ago, in v2.4, VM_RESERVED kept swapout process off VMA, currently it lost original meaning but still has some effects: | effect | alternative flags -+------------------------+--------------------------------------------- 1| account as reserved_vm | VM_IO 2| skip in core dump | VM_IO, VM_DONTDUMP 3| do not merge or expand | VM_IO, VM_DONTEXPAND, VM_HUGETLB, VM_PFNMAP 4| do not mlock | VM_IO, VM_DONTEXPAND, VM_HUGETLB, VM_PFNMAP This patch removes reserved_vm counter from mm_struct. Seems like nobody cares about it, it does not exported into userspace directly, it only reduces total_vm showed in proc. Thus VM_RESERVED can be replaced with VM_IO or pair VM_DONTEXPAND | VM_DONTDUMP. remap_pfn_range() and io_remap_pfn_range() set VM_IO|VM_DONTEXPAND|VM_DONTDUMP. remap_vmalloc_range() set VM_DONTEXPAND | VM_DONTDUMP. [akpm@linux-foundation.org: drivers/vfio/pci/vfio_pci.c fixup] Signed-off-by: Konstantin Khlebnikov Cc: Alexander Viro Cc: Carsten Otte Cc: Chris Metcalf Cc: Cyrill Gorcunov Cc: Eric Paris Cc: H. Peter Anvin Cc: Hugh Dickins Cc: Ingo Molnar Cc: James Morris Cc: Jason Baron Cc: Kentaro Takeda Cc: Matt Helsley Cc: Nick Piggin Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Robert Richter Cc: Suresh Siddha Cc: Tetsuo Handa Cc: Venkatesh Pallipadi Acked-by: Linus Torvalds Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/task_mmu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs/proc/task_mmu.c') diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 4540b8f76f16..79827ce03e3b 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -54,7 +54,7 @@ void task_mem(struct seq_file *m, struct mm_struct *mm) "VmPTE:\t%8lu kB\n" "VmSwap:\t%8lu kB\n", hiwater_vm << (PAGE_SHIFT-10), - (total_vm - mm->reserved_vm) << (PAGE_SHIFT-10), + total_vm << (PAGE_SHIFT-10), mm->locked_vm << (PAGE_SHIFT-10), mm->pinned_vm << (PAGE_SHIFT-10), hiwater_rss << (PAGE_SHIFT-10), -- cgit v1.2.3 From 32f8516a8c733d281faa9f6666b509035246505c Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Tue, 16 Oct 2012 17:31:23 -0700 Subject: mm, mempolicy: fix printing stack contents in numa_maps When reading /proc/pid/numa_maps, it's possible to return the contents of the stack where the mempolicy string should be printed if the policy gets freed from beneath us. This happens because mpol_to_str() may return an error the stack-allocated buffer is then printed without ever being stored. There are two possible error conditions in mpol_to_str(): - if the buffer allocated is insufficient for the string to be stored, and - if the mempolicy has an invalid mode. The first error condition is not triggered in any of the callers to mpol_to_str(): at least 50 bytes is always allocated on the stack and this is sufficient for the string to be written. A future patch should convert this into BUILD_BUG_ON() since we know the maximum strlen possible, but that's not -rc material. The second error condition is possible if a race occurs in dropping a reference to a task's mempolicy causing it to be freed during the read(). The slab poison value is then used for the mode and mpol_to_str() returns -EINVAL. This race is only possible because get_vma_policy() believes that mm->mmap_sem protects task->mempolicy, which isn't true. The exit path does not hold mm->mmap_sem when dropping the reference or setting task->mempolicy to NULL: it uses task_lock(task) instead. Thus, it's required for the caller of a task mempolicy to hold task_lock(task) while grabbing the mempolicy and reading it. Callers with a vma policy store their mempolicy earlier and can simply increment the reference count so it's guaranteed not to be freed. Reported-by: Dave Jones Signed-off-by: David Rientjes Signed-off-by: Linus Torvalds --- fs/proc/task_mmu.c | 7 +++++-- mm/mempolicy.c | 5 ++--- 2 files changed, 7 insertions(+), 5 deletions(-) (limited to 'fs/proc/task_mmu.c') diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 79827ce03e3b..14df8806ff29 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1158,6 +1158,7 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid) struct vm_area_struct *vma = v; struct numa_maps *md = &numa_priv->md; struct file *file = vma->vm_file; + struct task_struct *task = proc_priv->task; struct mm_struct *mm = vma->vm_mm; struct mm_walk walk = {}; struct mempolicy *pol; @@ -1177,9 +1178,11 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid) walk.private = md; walk.mm = mm; - pol = get_vma_policy(proc_priv->task, vma, vma->vm_start); + task_lock(task); + pol = get_vma_policy(task, vma, vma->vm_start); mpol_to_str(buffer, sizeof(buffer), pol, 0); mpol_cond_put(pol); + task_unlock(task); seq_printf(m, "%08lx %s", vma->vm_start, buffer); @@ -1189,7 +1192,7 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid) } else if (vma->vm_start <= mm->brk && vma->vm_end >= mm->start_brk) { seq_printf(m, " heap"); } else { - pid_t tid = vm_is_stack(proc_priv->task, vma, is_pid); + pid_t tid = vm_is_stack(task, vma, is_pid); if (tid != 0) { /* * Thread stack in /proc/PID/task/TID/maps or diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 0b78fb9ea65b..d04a8a54c294 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1536,9 +1536,8 @@ asmlinkage long compat_sys_mbind(compat_ulong_t start, compat_ulong_t len, * * Returns effective policy for a VMA at specified address. * Falls back to @task or system default policy, as necessary. - * Current or other task's task mempolicy and non-shared vma policies - * are protected by the task's mmap_sem, which must be held for read by - * the caller. + * Current or other task's task mempolicy and non-shared vma policies must be + * protected by task_lock(task) by the caller. * Shared policies [those marked as MPOL_F_SHARED] require an extra reference * count--added by the get_policy() vm_op, as appropriate--to protect against * freeing by another task. It is the caller's responsibility to free the -- cgit v1.2.3 From 9e7814404b77c3e8920bee4277162bf3a7460505 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Fri, 19 Oct 2012 17:00:55 +0900 Subject: hold task->mempolicy while numa_maps scans. /proc//numa_maps scans vma and show mempolicy under mmap_sem. It sometimes accesses task->mempolicy which can be freed without mmap_sem and numa_maps can show some garbage while scanning. This patch tries to take reference count of task->mempolicy at reading numa_maps before calling get_vma_policy(). By this, task->mempolicy will not be freed until numa_maps reaches its end. V2->v3 - updated comments to be more verbose. - removed task_lock() in numa_maps code. V1->V2 - access task->mempolicy only once and remember it. Becase kernel/exit.c can overwrite it. Signed-off-by: KAMEZAWA Hiroyuki Acked-by: David Rientjes Acked-by: KOSAKI Motohiro Signed-off-by: Linus Torvalds --- fs/proc/internal.h | 4 ++++ fs/proc/task_mmu.c | 50 +++++++++++++++++++++++++++++++++++++++++++++++--- 2 files changed, 51 insertions(+), 3 deletions(-) (limited to 'fs/proc/task_mmu.c') diff --git a/fs/proc/internal.h b/fs/proc/internal.h index cceaab07ad54..43973b084abf 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -12,6 +12,7 @@ #include #include struct ctl_table_header; +struct mempolicy; extern struct proc_dir_entry proc_root; #ifdef CONFIG_PROC_SYSCTL @@ -74,6 +75,9 @@ struct proc_maps_private { #ifdef CONFIG_MMU struct vm_area_struct *tail_vma; #endif +#ifdef CONFIG_NUMA + struct mempolicy *task_mempolicy; +#endif }; void proc_init_inodecache(void); diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 14df8806ff29..90c63f9392a5 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -90,10 +90,55 @@ static void pad_len_spaces(struct seq_file *m, int len) seq_printf(m, "%*c", len, ' '); } +#ifdef CONFIG_NUMA +/* + * These functions are for numa_maps but called in generic **maps seq_file + * ->start(), ->stop() ops. + * + * numa_maps scans all vmas under mmap_sem and checks their mempolicy. + * Each mempolicy object is controlled by reference counting. The problem here + * is how to avoid accessing dead mempolicy object. + * + * Because we're holding mmap_sem while reading seq_file, it's safe to access + * each vma's mempolicy, no vma objects will never drop refs to mempolicy. + * + * A task's mempolicy (task->mempolicy) has different behavior. task->mempolicy + * is set and replaced under mmap_sem but unrefed and cleared under task_lock(). + * So, without task_lock(), we cannot trust get_vma_policy() because we cannot + * gurantee the task never exits under us. But taking task_lock() around + * get_vma_plicy() causes lock order problem. + * + * To access task->mempolicy without lock, we hold a reference count of an + * object pointed by task->mempolicy and remember it. This will guarantee + * that task->mempolicy points to an alive object or NULL in numa_maps accesses. + */ +static void hold_task_mempolicy(struct proc_maps_private *priv) +{ + struct task_struct *task = priv->task; + + task_lock(task); + priv->task_mempolicy = task->mempolicy; + mpol_get(priv->task_mempolicy); + task_unlock(task); +} +static void release_task_mempolicy(struct proc_maps_private *priv) +{ + mpol_put(priv->task_mempolicy); +} +#else +static void hold_task_mempolicy(struct proc_maps_private *priv) +{ +} +static void release_task_mempolicy(struct proc_maps_private *priv) +{ +} +#endif + static void vma_stop(struct proc_maps_private *priv, struct vm_area_struct *vma) { if (vma && vma != priv->tail_vma) { struct mm_struct *mm = vma->vm_mm; + release_task_mempolicy(priv); up_read(&mm->mmap_sem); mmput(mm); } @@ -132,7 +177,7 @@ static void *m_start(struct seq_file *m, loff_t *pos) tail_vma = get_gate_vma(priv->task->mm); priv->tail_vma = tail_vma; - + hold_task_mempolicy(priv); /* Start with last addr hint */ vma = find_vma(mm, last_addr); if (last_addr && vma) { @@ -159,6 +204,7 @@ out: if (vma) return vma; + release_task_mempolicy(priv); /* End of vmas has been reached */ m->version = (tail_vma != NULL)? 0: -1UL; up_read(&mm->mmap_sem); @@ -1178,11 +1224,9 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid) walk.private = md; walk.mm = mm; - task_lock(task); pol = get_vma_policy(task, vma, vma->vm_start); mpol_to_str(buffer, sizeof(buffer), pol, 0); mpol_cond_put(pol); - task_unlock(task); seq_printf(m, "%08lx %s", vma->vm_start, buffer); -- cgit v1.2.3