mm/hmm: Simplify hmm_get_or_create and make it reliable

mm/hmm: Simplify hmm_get_or_create and make it reliable

As coded this function can false-fail in various racy situations. Make it
reliable and simpler by running under the write side of the mmap_sem and
avoiding the false-failing compare/exchange pattern. Due to the mmap_sem
this no longer has to avoid racing with a 2nd parallel
hmm_get_or_create().

Unfortunately this still has to use the page_table_lock as the
non-sleeping lock protecting mm->hmm, since the contexts where we free the
hmm are incompatible with mmap_sem.

Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Reviewed-by: John Hubbard <jhubbard@nvidia.com>
Reviewed-by: Ralph Campbell <rcampbell@nvidia.com>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Tested-by: Philip Yang <Philip.Yang@amd.com>