mm: make mm->pinned_vm an atomic64 counter

Taking a sleeping lock to _only_ increment a variable is quite the
overkill, and pretty much all users do this. Furthermore, some drivers
(ie: infiniband and scif) that need pinned semantics can go to quite
some trouble to actually delay via workqueue (un)accounting for pinned
pages when not possible to acquire it.

By making the counter atomic we no longer need to hold the mmap_sem and
can simply some code around it for pinned_vm users. The counter is 64-bit
such that we need not worry about overflows such as rdma user input
controlled from userspace.

Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Reviewed-by: Christoph Lameter <cl@linux.com>
Reviewed-by: Daniel Jordan <daniel.m.jordan@oracle.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Davidlohr Bueso <dbueso@suse.de>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

drivers/infiniband/hw/hfi1/user_pages.c

@@ -92,7 +92,7 @@ bool hfi1_can_pin_pages(struct hfi1_devdata *dd, struct mm_struct *mm,
 	size = DIV_ROUND_UP(size, PAGE_SIZE);
 
 	down_read(&mm->mmap_sem);
-	pinned = mm->pinned_vm;
+	pinned = atomic64_read(&mm->pinned_vm);
 	up_read(&mm->mmap_sem);
 
 	/* First, check the absolute limit against all pinned pages. */
@@ -112,7 +112,7 @@ int hfi1_acquire_user_pages(struct mm_struct *mm, unsigned long vaddr, size_t np
 		return ret;
 
 	down_write(&mm->mmap_sem);
-	mm->pinned_vm += ret;
+	atomic64_add(ret, &mm->pinned_vm);
 	up_write(&mm->mmap_sem);
 
 	return ret;
@@ -131,7 +131,7 @@ void hfi1_release_user_pages(struct mm_struct *mm, struct page **p,
 
 	if (mm) { /* during close after signal, mm can be NULL */
 		down_write(&mm->mmap_sem);
-		mm->pinned_vm -= npages;
+		atomic64_sub(npages, &mm->pinned_vm);
 		up_write(&mm->mmap_sem);
 	}
 }