mm: memblock: do not enforce current limit for memblock_phys* family
authorMike Rapoport <rppt@linux.ibm.com>
Sat, 19 Oct 2019 03:20:01 +0000 (20:20 -0700)
committerLinus Torvalds <torvalds@linux-foundation.org>
Sat, 19 Oct 2019 10:32:32 +0000 (06:32 -0400)
Until commit 92d12f9544b7 ("memblock: refactor internal allocation
functions") the maximal address for memblock allocations was forced to
memblock.current_limit only for the allocation functions returning
virtual address.  The changes introduced by that commit moved the limit
enforcement into the allocation core and as a result the allocation
functions returning physical address also started to limit allocations
to memblock.current_limit.

This caused breakage of etnaviv GPU driver:

  etnaviv etnaviv: bound 130000.gpu (ops gpu_ops)
  etnaviv etnaviv: bound 134000.gpu (ops gpu_ops)
  etnaviv etnaviv: bound 2204000.gpu (ops gpu_ops)
  etnaviv-gpu 130000.gpu: model: GC2000, revision: 5108
  etnaviv-gpu 130000.gpu: command buffer outside valid memory window
  etnaviv-gpu 134000.gpu: model: GC320, revision: 5007
  etnaviv-gpu 134000.gpu: command buffer outside valid memory window
  etnaviv-gpu 2204000.gpu: model: GC355, revision: 1215
  etnaviv-gpu 2204000.gpu: Ignoring GPU with VG and FE2.0

Restore the behaviour of memblock_phys* family so that these functions
will not enforce memblock.current_limit.

Link: http://lkml.kernel.org/r/1570915861-17633-1-git-send-email-rppt@kernel.org
Fixes: 92d12f9544b7 ("memblock: refactor internal allocation functions")
Signed-off-by: Mike Rapoport <rppt@linux.ibm.com>
Reported-by: Adam Ford <aford173@gmail.com>
Tested-by: Adam Ford <aford173@gmail.com> [imx6q-logicpd]
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Fabio Estevam <festevam@gmail.com>
Cc: Lucas Stach <l.stach@pengutronix.de>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
mm/memblock.c

index 7d4f61a..c4b16ca 100644 (file)
@@ -1356,9 +1356,6 @@ static phys_addr_t __init memblock_alloc_range_nid(phys_addr_t size,
                align = SMP_CACHE_BYTES;
        }
 
-       if (end > memblock.current_limit)
-               end = memblock.current_limit;
-
 again:
        found = memblock_find_in_range_node(size, align, start, end, nid,
                                            flags);
@@ -1469,6 +1466,9 @@ static void * __init memblock_alloc_internal(
        if (WARN_ON_ONCE(slab_is_available()))
                return kzalloc_node(size, GFP_NOWAIT, nid);
 
+       if (max_addr > memblock.current_limit)
+               max_addr = memblock.current_limit;
+
        alloc = memblock_alloc_range_nid(size, align, min_addr, max_addr, nid);
 
        /* retry allocation without lower limit */