IB/hfi1: Make use of mm consistent

The hfi1 driver registers a mmu_notifier callback when /dev/hfi1_* is
opened, and unregisters it when the device is closed.  The driver
incorrectly assumes that the close will always happen from the same
context as the open.  In particular, closes due to SIGKILL or OOM killer
activity may happen from a different context.  In these cases, the wrong
mm is passed to mmu_notifier_unregister(), which causes improper reference
counting for the victim mm, and eventual memory corruption.

Preserve the mm for all open file descriptors and use this mm rather than
current->mm for memory operations for the lifetime of that fd.  Note: this
patch leaves 1 use of current->mm in place.  This use is removed in a
follow on patch because other functional changes were required prior to
that use being removed.

If registration fails, there is no reason to keep the handler object
around.  Free the handler object rather than add it to the list to
prevent any mmu_notifier operations, including unregister, when
registration fails.

Suggested-by: Jim Foraker <foraker1@llnl.gov>
Reviewed-by: Dean Luick <dean.luick@intel.com>
Signed-off-by: Ira Weiny <ira.weiny@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

1 files changed, 10 insertions, 9 deletions

diff --git a/drivers/infiniband/hw/hfi1/user_pages.c b/drivers/infiniband/hw/hfi1/user_pages.c
index 88e10b5f55f1..20f4ddcac3b0 100644
--- a/drivers/infiniband/hw/hfi1/user_pages.c
+++ b/drivers/infiniband/hw/hfi1/user_pages.c
@@ -68,7 +68,8 @@ MODULE_PARM_DESC(cache_size, "Send and receive side cache size limit (in MB)");
  * could keeping caching buffers.
  *
  */
-bool hfi1_can_pin_pages(struct hfi1_devdata *dd, u32 nlocked, u32 npages)
+bool hfi1_can_pin_pages(struct hfi1_devdata *dd, struct mm_struct *mm,
+			u32 nlocked, u32 npages)
 {
 	unsigned long ulimit = rlimit(RLIMIT_MEMLOCK), pinned, cache_limit,
 		size = (cache_size * (1UL << 20)); /* convert to bytes */
@@ -89,9 +90,9 @@ bool hfi1_can_pin_pages(struct hfi1_devdata *dd, u32 nlocked, u32 npages)
 	/* Convert to number of pages */
 	size = DIV_ROUND_UP(size, PAGE_SIZE);
 
-	down_read(&current->mm->mmap_sem);
-	pinned = current->mm->pinned_vm;
-	up_read(&current->mm->mmap_sem);
+	down_read(&mm->mmap_sem);
+	pinned = mm->pinned_vm;
+	up_read(&mm->mmap_sem);
 
 	/* First, check the absolute limit against all pinned pages. */
 	if (pinned + npages >= ulimit && !can_lock)
@@ -100,8 +101,8 @@ bool hfi1_can_pin_pages(struct hfi1_devdata *dd, u32 nlocked, u32 npages)
 	return ((nlocked + npages) <= size) || can_lock;
 }
 
-int hfi1_acquire_user_pages(unsigned long vaddr, size_t npages, bool writable,
-			    struct page **pages)
+int hfi1_acquire_user_pages(struct mm_struct *mm, unsigned long vaddr, size_t npages,
+			    bool writable, struct page **pages)
 {
 	int ret;
 
@@ -109,9 +110,9 @@ int hfi1_acquire_user_pages(unsigned long vaddr, size_t npages, bool writable,
 	if (ret < 0)
 		return ret;
 
-	down_write(&current->mm->mmap_sem);
-	current->mm->pinned_vm += ret;
-	up_write(&current->mm->mmap_sem);
+	down_write(&mm->mmap_sem);
+	mm->pinned_vm += ret;
+	up_write(&mm->mmap_sem);
 
 	return ret;
 }