SWAP_NR_ORDERS sizes a few small bounded arrays inside THP swap
allocator code (nofull/frag cluster lists, percpu_swap_cluster's
si/offset arrays, next array for rotational device). This currently
expands to PMD_ORDER+1, which only works when PMD_ORDER is a compile
time constant.

However on architecture like PowerPC Book3S64, PMD_ORDER is a runtime
variable which depends upon which MMU is selected (Radix / Hash), so in
that case, PMD_ORDER cannot be used to size the static arrays.

This patch provides an optional ARCH_MAX_PMD_ORDER (upper-bound)
override for such architectures. The memory overhead on enabling this
override is negligible. Even if we make SWAP_NR_ORDERS runtime alloc,
default slab padding could cause some memory waste. Also we lose the
per-cpu cacheline benefits (for percpu_swap_cluster) because it might
cost an extra cacheline indirection overhead in swap_alloc_fast() for
fetching si[order]/offset[order]. Note that a fully runtime
SWAP_NR_ORDERS was considered in previous version but was dropped for
this reason [1]

[1]: https://lore.kernel.org/linuxppc-dev/pl1zdksc.ritesh.list@gmail.com/ (local)

Suggested-by: YoungJun Park <youngjun.park@lge.com>
Signed-off-by: Ritesh Harjani (IBM) <ritesh.list@gmail.com>
---
 arch/powerpc/include/asm/book3s/64/pgtable.h |  7 +++++++
 include/linux/swap.h                         | 12 +++++++++++-
 2 files changed, 18 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index e67e64ac6e8c..7f22d5d5fbdf 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h

@@ -204,6 +204,13 @@ extern unsigned long __pmd_frag_size_shift;
 #define MAX_PTRS_PER_PGD	(1 << (H_PGD_INDEX_SIZE > RADIX_PGD_INDEX_SIZE ? \
 				       H_PGD_INDEX_SIZE : RADIX_PGD_INDEX_SIZE))
 
+/*
+ * Compile-time upper bound on PMD_ORDER across hash and radix MMUs.
+ * Used by THP SWAP code. Check include/linux/swap.h
+ */
+#define ARCH_MAX_PMD_ORDER ((H_PTE_INDEX_SIZE > RADIX_PTE_INDEX_SIZE) ? \
+				H_PTE_INDEX_SIZE : RADIX_PTE_INDEX_SIZE)
+
 /* PMD_SHIFT determines what a second-level page table entry can map */
 #define PMD_SHIFT	(PAGE_SHIFT + PTE_INDEX_SIZE)
 #define PMD_SIZE	(1UL << PMD_SHIFT)

diff --git a/include/linux/swap.h b/include/linux/swap.h
index 46c25523d7b8..4e1701b4a565 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h

@@ -223,11 +223,21 @@ enum {
  */
 #define SWAP_ENTRY_INVALID	0
 
+/*
+ * ARCH_MAX_PMD_ORDER is an optional arch hook: a compile-time upper bound for
+ * PMD_ORDER across all possible MMU configurations of that arch. It is used to
+ * size SWAP_NR_ORDERS on architectures (e.g. powerpc book3s64) where PMD_ORDER
+ * is selected at boot rather than at compile time.
+ */
 #ifdef CONFIG_THP_SWAP
+#ifdef ARCH_MAX_PMD_ORDER
+#define SWAP_NR_ORDERS		(ARCH_MAX_PMD_ORDER + 1)
+#else
 #define SWAP_NR_ORDERS		(PMD_ORDER + 1)
+#endif /* ARCH_MAX_PMD_ORDER */
 #else
 #define SWAP_NR_ORDERS		1
-#endif
+#endif /* CONFIG_THP_SWAP */
 
 /*
  * We keep using same cluster for rotational device so IO will be sequential.

-- 
2.39.5