mm: distinguish between mlocked and pinned pages

Some kernel components pin user space memory (infiniband and perf) (by
increasing the page count) and account that memory as "mlocked".

The difference between mlocking and pinning is:

A. mlocked pages are marked with PG_mlocked and are exempt from
   swapping. Page migration may move them around though.
   They are kept on a special LRU list.

B. Pinned pages cannot be moved because something needs to
   directly access physical memory. They may not be on any
   LRU list.

I recently saw an mlockalled process where mm->locked_vm became
bigger than the virtual size of the process (!) because some
memory was accounted for twice:

Once when the page was mlocked and once when the Infiniband
layer increased the refcount because it needt to pin the RDMA
memory.

This patch introduces a separate counter for pinned pages and
accounts them seperately.

Signed-off-by: Christoph Lameter <cl@linux.com>
Cc: Mike Marciniszyn <infinipath@qlogic.com>
Cc: Roland Dreier <roland@kernel.org>
Cc: Sean Hefty <sean.hefty@intel.com>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

6 files changed, 14 insertions, 12 deletions

diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c
index b645e55..9155f91 100644
--- a/drivers/infiniband/core/umem.c
+++ b/drivers/infiniband/core/umem.c
@@ -136,7 +136,7 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr,
 
 	down_write(&current->mm->mmap_sem);
 
-	locked     = npages + current->mm->locked_vm;
+	locked     = npages + current->mm->pinned_vm;
 	lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
 
 	if ((locked > lock_limit) && !capable(CAP_IPC_LOCK)) {
@@ -206,7 +206,7 @@ out:
 		__ib_umem_release(context->device, umem, 0);
 		kfree(umem);
 	} else
-		current->mm->locked_vm = locked;
+		current->mm->pinned_vm = locked;
 
 	up_write(&current->mm->mmap_sem);
 	if (vma_list)
@@ -222,7 +222,7 @@ static void ib_umem_account(struct work_struct *work)
 	struct ib_umem *umem = container_of(work, struct ib_umem, work);
 
 	down_write(&umem->mm->mmap_sem);
-	umem->mm->locked_vm -= umem->diff;
+	umem->mm->pinned_vm -= umem->diff;
 	up_write(&umem->mm->mmap_sem);
 	mmput(umem->mm);
 	kfree(umem);
diff --git a/drivers/infiniband/hw/ipath/ipath_user_pages.c b/drivers/infiniband/hw/ipath/ipath_user_pages.c
index cfed539..dc66c45 100644
--- a/drivers/infiniband/hw/ipath/ipath_user_pages.c
+++ b/drivers/infiniband/hw/ipath/ipath_user_pages.c
@@ -79,7 +79,7 @@ static int __ipath_get_user_pages(unsigned long start_page, size_t num_pages,
 			goto bail_release;
 	}
 
-	current->mm->locked_vm += num_pages;
+	current->mm->pinned_vm += num_pages;
 
 	ret = 0;
 	goto bail;
@@ -178,7 +178,7 @@ void ipath_release_user_pages(struct page **p, size_t num_pages)
 
 	__ipath_release_user_pages(p, num_pages, 1);
 
-	current->mm->locked_vm -= num_pages;
+	current->mm->pinned_vm -= num_pages;
 
 	up_write(&current->mm->mmap_sem);
 }
@@ -195,7 +195,7 @@ static void user_pages_account(struct work_struct *_work)
 		container_of(_work, struct ipath_user_pages_work, work);
 
 	down_write(&work->mm->mmap_sem);
-	work->mm->locked_vm -= work->num_pages;
+	work->mm->pinned_vm -= work->num_pages;
 	up_write(&work->mm->mmap_sem);
 	mmput(work->mm);
 	kfree(work);
diff --git a/drivers/infiniband/hw/qib/qib_user_pages.c b/drivers/infiniband/hw/qib/qib_user_pages.c
index 7689e49..2bc1d2b 100644
--- a/drivers/infiniband/hw/qib/qib_user_pages.c
+++ b/drivers/infiniband/hw/qib/qib_user_pages.c
@@ -74,7 +74,7 @@ static int __qib_get_user_pages(unsigned long start_page, size_t num_pages,
 			goto bail_release;
 	}
 
-	current->mm->locked_vm += num_pages;
+	current->mm->pinned_vm += num_pages;
 
 	ret = 0;
 	goto bail;
@@ -151,7 +151,7 @@ void qib_release_user_pages(struct page **p, size_t num_pages)
 	__qib_release_user_pages(p, num_pages, 1);
 
 	if (current->mm) {
-		current->mm->locked_vm -= num_pages;
+		current->mm->pinned_vm -= num_pages;
 		up_write(&current->mm->mmap_sem);
 	}
 }
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index c7d4ee6..e418c5a 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -44,6 +44,7 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
 		"VmPeak:\t%8lu kB\n"
 		"VmSize:\t%8lu kB\n"
 		"VmLck:\t%8lu kB\n"
+		"VmPin:\t%8lu kB\n"
 		"VmHWM:\t%8lu kB\n"
 		"VmRSS:\t%8lu kB\n"
 		"VmData:\t%8lu kB\n"
@@ -55,6 +56,7 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
 		hiwater_vm << (PAGE_SHIFT-10),
 		(total_vm - mm->reserved_vm) << (PAGE_SHIFT-10),
 		mm->locked_vm << (PAGE_SHIFT-10),
+		mm->pinned_vm << (PAGE_SHIFT-10),
 		hiwater_rss << (PAGE_SHIFT-10),
 		total_rss << (PAGE_SHIFT-10),
 		data << (PAGE_SHIFT-10),
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 6456624..f317583 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -304,7 +304,7 @@ struct mm_struct {
 	unsigned long hiwater_rss;	/* High-watermark of RSS usage */
 	unsigned long hiwater_vm;	/* High-water virtual memory usage */
 
-	unsigned long total_vm, locked_vm, shared_vm, exec_vm;
+	unsigned long total_vm, locked_vm, pinned_vm, shared_vm, exec_vm;
 	unsigned long stack_vm, reserved_vm, def_flags, nr_ptes;
 	unsigned long start_code, end_code, start_data, end_data;
 	unsigned long start_brk, brk, start_stack;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index d1a1bee..12a0287 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3544,7 +3544,7 @@ static void perf_mmap_close(struct vm_area_struct *vma)
 		struct ring_buffer *rb = event->rb;
 
 		atomic_long_sub((size >> PAGE_SHIFT) + 1, &user->locked_vm);
-		vma->vm_mm->locked_vm -= event->mmap_locked;
+		vma->vm_mm->pinned_vm -= event->mmap_locked;
 		rcu_assign_pointer(event->rb, NULL);
 		mutex_unlock(&event->mmap_mutex);
 
@@ -3625,7 +3625,7 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
 
 	lock_limit = rlimit(RLIMIT_MEMLOCK);
 	lock_limit >>= PAGE_SHIFT;
-	locked = vma->vm_mm->locked_vm + extra;
+	locked = vma->vm_mm->pinned_vm + extra;
 
 	if ((locked > lock_limit) && perf_paranoid_tracepoint_raw() &&
 		!capable(CAP_IPC_LOCK)) {
@@ -3651,7 +3651,7 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
 	atomic_long_add(user_extra, &user->locked_vm);
 	event->mmap_locked = extra;
 	event->mmap_user = get_current_user();
-	vma->vm_mm->locked_vm += event->mmap_locked;
+	vma->vm_mm->pinned_vm += event->mmap_locked;
 
 unlock:
 	if (!ret)