IB: ib_umem_release() should decrement mm->pinned_vm from ib_umem_get

In debugging an application that receives -ENOMEM from ib_reg_mr(), I
found that ib_umem_get() can fail because the pinned_vm count has
wrapped causing it to always be larger than the lock limit even with
RLIMIT_MEMLOCK set to RLIM_INFINITY.

The wrapping of pinned_vm occurs because the process that calls
ib_reg_mr() will have its mm->pinned_vm count incremented.  Later a
different process with a different mm_struct than the one that
allocated the ib_umem struct ends up releasing it which results in
decrementing the new processes mm->pinned_vm count past zero and
wrapping.

I'm not entirely sure what circumstances cause a different process to
release the ib_umem than the one that allocated it but the kernel
stack trace of the freeing process from my situation looks like the
following:

    Call Trace:
     [<ffffffff814d64b1>] dump_stack+0x19/0x1b
     [<ffffffffa0b522a5>] ib_umem_release+0x1f5/0x200 [ib_core]
     [<ffffffffa0b90681>] mlx4_ib_destroy_qp+0x241/0x440 [mlx4_ib]
     [<ffffffffa0b4d93c>] ib_destroy_qp+0x12c/0x170 [ib_core]
     [<ffffffffa0cc7129>] ib_uverbs_close+0x259/0x4e0 [ib_uverbs]
     [<ffffffff81141cba>] __fput+0xba/0x240
     [<ffffffff81141e4e>] ____fput+0xe/0x10
     [<ffffffff81060894>] task_work_run+0xc4/0xe0
     [<ffffffff810029e5>] do_notify_resume+0x95/0xa0
     [<ffffffff814e3dd0>] int_signal+0x12/0x17

The following patch fixes the issue by storing the pid struct of the
process that calls ib_umem_get() so that ib_umem_release and/or
ib_umem_account() can properly decrement the pinned_vm count of the
correct mm_struct.

Signed-off-by: Shawn Bohrer <[email protected]>
Reviewed-by: Shachar Raindel <[email protected]>
Signed-off-by: Roland Dreier <[email protected]>

Author: Shawn Bohrer

drivers/infiniband/core/umem.c

@@ -105,6 +105,7 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr,
 	umem->length    = size;
 	umem->offset    = addr & ~PAGE_MASK;
 	umem->page_size = PAGE_SIZE;
+	umem->pid       = get_task_pid(current, PIDTYPE_PID);
 	/*
 	 * We ask for writable memory if any access flags other than
 	 * "remote read" are set.  "Local write" and "remote write"
@@ -198,6 +199,7 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr,
 	if (ret < 0) {
 		if (need_release)
 			__ib_umem_release(context->device, umem, 0);
+		put_pid(umem->pid);
 		kfree(umem);
 	} else
 		current->mm->pinned_vm = locked;
@@ -230,15 +232,19 @@ void ib_umem_release(struct ib_umem *umem)
 {
 	struct ib_ucontext *context = umem->context;
 	struct mm_struct *mm;
+	struct task_struct *task;
 	unsigned long diff;
 
 	__ib_umem_release(umem->context->device, umem, 1);
 
-	mm = get_task_mm(current);
-	if (!mm) {
-		kfree(umem);
-		return;
-	}
+	task = get_pid_task(umem->pid, PIDTYPE_PID);
+	put_pid(umem->pid);
+	if (!task)
+		goto out;
+	mm = get_task_mm(task);
+	put_task_struct(task);
+	if (!mm)
+		goto out;
 
 	diff = PAGE_ALIGN(umem->length + umem->offset) >> PAGE_SHIFT;
 
@@ -262,9 +268,10 @@ void ib_umem_release(struct ib_umem *umem)
 	} else
 		down_write(&mm->mmap_sem);
 
-	current->mm->pinned_vm -= diff;
+	mm->pinned_vm -= diff;
 	up_write(&mm->mmap_sem);
 	mmput(mm);
+out:
 	kfree(umem);
 }
 EXPORT_SYMBOL(ib_umem_release);

include/rdma/ib_umem.h

@@ -47,6 +47,7 @@ struct ib_umem {
 	int                     writable;
 	int                     hugetlb;
 	struct work_struct	work;
+	struct pid             *pid;
 	struct mm_struct       *mm;
 	unsigned long		diff;
 	struct sg_table sg_head;