powerpc/mm/slice: implement a slice mask cache

Calculating the slice mask can become a signifcant overhead for
get_unmapped_area. This patch adds a struct slice_mask for
each page size in the mm_context, and keeps these in synch with
the slices psize arrays and slb_addr_limit.

On Book3S/64 this adds 288 bytes to the mm_context_t for the
slice mask caches.

On POWER8, this increases vfork+exec+exit performance by 9.9%
and reduces time to mmap+munmap a 64kB page by 28%.

Reduces time to mmap+munmap by about 10% on 8xx.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

2 files changed, 28 insertions, 0 deletions

diff --git a/arch/powerpc/include/asm/book3s/64/mmu.h b/arch/powerpc/include/asm/book3s/64/mmu.h
index bef6e39ed63a..777778579305 100644
--- a/arch/powerpc/include/asm/book3s/64/mmu.h
+++ b/arch/powerpc/include/asm/book3s/64/mmu.h
@@ -80,6 +80,16 @@ struct spinlock;
 /* Maximum possible number of NPUs in a system. */
 #define NV_MAX_NPUS 8
 
+/*
+ * One bit per slice. We have lower slices which cover 256MB segments
+ * upto 4G range. That gets us 16 low slices. For the rest we track slices
+ * in 1TB size.
+ */
+struct slice_mask {
+	u64 low_slices;
+	DECLARE_BITMAP(high_slices, SLICE_NUM_HIGH);
+};
+
 typedef struct {
 	mm_context_id_t id;
 	u16 user_psize;		/* page size index */
@@ -95,6 +105,14 @@ typedef struct {
 	unsigned char low_slices_psize[BITS_PER_LONG / BITS_PER_BYTE];
 	unsigned char high_slices_psize[SLICE_ARRAY_SIZE];
 	unsigned long slb_addr_limit;
+# ifdef CONFIG_PPC_64K_PAGES
+	struct slice_mask mask_64k;
+# endif
+	struct slice_mask mask_4k;
+# ifdef CONFIG_HUGETLB_PAGE
+	struct slice_mask mask_16m;
+	struct slice_mask mask_16g;
+# endif
 #else
 	u16 sllp;		/* SLB page size encoding */
 #endif
diff --git a/arch/powerpc/include/asm/mmu-8xx.h b/arch/powerpc/include/asm/mmu-8xx.h
index d3d7e79140c6..4f547752ae79 100644
--- a/arch/powerpc/include/asm/mmu-8xx.h
+++ b/arch/powerpc/include/asm/mmu-8xx.h
@@ -192,6 +192,11 @@
 #endif
 
 #ifndef __ASSEMBLY__
+struct slice_mask {
+	u64 low_slices;
+	DECLARE_BITMAP(high_slices, 0);
+};
+
 typedef struct {
 	unsigned int id;
 	unsigned int active;
@@ -201,6 +206,11 @@ typedef struct {
 	unsigned char low_slices_psize[SLICE_ARRAY_SIZE];
 	unsigned char high_slices_psize[0];
 	unsigned long slb_addr_limit;
+	struct slice_mask mask_base_psize; /* 4k or 16k */
+# ifdef CONFIG_HUGETLB_PAGE
+	struct slice_mask mask_512k;
+	struct slice_mask mask_8m;
+# endif
 #endif
 } mm_context_t;