[PATCH v4 1/5] powerpc/mm/slice: Remove intermediate bitmap copy

@@ -388,21 +388,17 @@ static unsigned long slice_find_area(struct mm_struct *mm, unsigned long len,
 
 static inline void slice_or_mask(struct slice_mask *dst, struct slice_mask *src)
 {
-	DECLARE_BITMAP(result, SLICE_NUM_HIGH);
-
 	dst->low_slices |= src->low_slices;
-	bitmap_or(result, dst->high_slices, src->high_slices, SLICE_NUM_HIGH);
-	bitmap_copy(dst->high_slices, result, SLICE_NUM_HIGH);
+	bitmap_or(dst->high_slices, dst->high_slices, src->high_slices,
+		  SLICE_NUM_HIGH);
 }
 
 static inline void slice_andnot_mask(struct slice_mask *dst, struct slice_mask *src)
 {
-	DECLARE_BITMAP(result, SLICE_NUM_HIGH);
-
 	dst->low_slices &= ~src->low_slices;
 
-	bitmap_andnot(result, dst->high_slices, src->high_slices, SLICE_NUM_HIGH);
-	bitmap_copy(dst->high_slices, result, SLICE_NUM_HIGH);
+	bitmap_andnot(dst->high_slices, dst->high_slices, src->high_slices,
+		      SLICE_NUM_HIGH);
 }
 
 #ifdef CONFIG_PPC_64K_PAGES

@@ -0,0 +1,79 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_BOOK3S_64_SLICE_H
+#define _ASM_POWERPC_BOOK3S_64_SLICE_H
+
+#ifdef CONFIG_PPC_MM_SLICES
+
+#define SLICE_LOW_SHIFT		28
+#define SLICE_LOW_TOP		(0x100000000ul)
+#define SLICE_NUM_LOW		(SLICE_LOW_TOP >> SLICE_LOW_SHIFT)
+#define GET_LOW_SLICE_INDEX(addr)	((addr) >> SLICE_LOW_SHIFT)
+
+#define SLICE_HIGH_SHIFT	40
+#define SLICE_NUM_HIGH		(H_PGTABLE_RANGE >> SLICE_HIGH_SHIFT)
+#define GET_HIGH_SLICE_INDEX(addr)	((addr) >> SLICE_HIGH_SHIFT)
+
+#ifndef __ASSEMBLY__
+
+#include <linux/bitmap.h>
+
+static inline void slice_bitmap_zero(unsigned long *dst, unsigned int nbits)
+{
+	bitmap_zero(dst, nbits);
+}
+
+static inline int slice_bitmap_and(unsigned long *dst,
+				   const unsigned long *src1,
+				   const unsigned long *src2,
+				   unsigned int nbits)
+{
+	return bitmap_and(dst, src1, src2, nbits);
+}
+
+static inline void slice_bitmap_or(unsigned long *dst,
+				   const unsigned long *src1,
+				   const unsigned long *src2,
+				   unsigned int nbits)
+{
+	bitmap_or(dst, src1, src2, nbits);
+}
+
+static inline int slice_bitmap_andnot(unsigned long *dst,
+				      const unsigned long *src1,
+				      const unsigned long *src2,
+				      unsigned int nbits)
+{
+	return bitmap_andnot(dst, src1, src2, nbits);
+}
+
+static inline int slice_bitmap_equal(const unsigned long *src1,
+				     const unsigned long *src2,
+				     unsigned int nbits)
+{
+	return bitmap_equal(src1, src2, nbits);
+}
+
+static inline int slice_bitmap_empty(const unsigned long *src, unsigned nbits)
+{
+	return bitmap_empty(src, nbits);
+}
+
+static inline void slice_bitmap_set(unsigned long *map, unsigned int start,
+				    unsigned int nbits)
+{
+	bitmap_set(map, start, nbits);
+}
+#endif /* __ASSEMBLY__ */
+
+#else /* CONFIG_PPC_MM_SLICES */
+
+#define get_slice_psize(mm, addr)	((mm)->context.user_psize)
+#define slice_set_user_psize(mm, psize)		\
+do {						\
+	(mm)->context.user_psize = (psize);	\
+	(mm)->context.sllp = SLB_VSID_USER | mmu_psize_defs[(psize)].sllp; \
+} while (0)
+
+#endif /* CONFIG_PPC_MM_SLICES */
+
+#endif /* _ASM_POWERPC_BOOK3S_64_SLICE_H */

@@ -0,0 +1,65 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_NOHASH_32_SLICE_H
+#define _ASM_POWERPC_NOHASH_32_SLICE_H
+
+#ifdef CONFIG_PPC_MM_SLICES
+
+#define SLICE_LOW_SHIFT		28
+#define SLICE_LOW_TOP		(0x100000000ull)
+#define SLICE_NUM_LOW		(SLICE_LOW_TOP >> SLICE_LOW_SHIFT)
+#define GET_LOW_SLICE_INDEX(addr)	((addr) >> SLICE_LOW_SHIFT)
+
+#define SLICE_HIGH_SHIFT	0
+#define SLICE_NUM_HIGH		0ul
+#define GET_HIGH_SLICE_INDEX(addr)	(addr & 0)
+
+#ifndef __ASSEMBLY__
+
+static inline void slice_bitmap_zero(unsigned long *dst, unsigned int nbits)
+{
+}
+
+static inline int slice_bitmap_and(unsigned long *dst,
+				   const unsigned long *src1,
+				   const unsigned long *src2,
+				   unsigned int nbits)
+{
+	return 0;
+}
+
+static inline void slice_bitmap_or(unsigned long *dst,
+				   const unsigned long *src1,
+				   const unsigned long *src2,
+				   unsigned int nbits)
+{
+}
+
+static inline int slice_bitmap_andnot(unsigned long *dst,
+				      const unsigned long *src1,
+				      const unsigned long *src2,
+				      unsigned int nbits)
+{
+	return 0;
+}
+
+static inline int slice_bitmap_equal(const unsigned long *src1,
+				     const unsigned long *src2,
+				     unsigned int nbits)
+{
+	return 1;
+}
+
+static inline int slice_bitmap_empty(const unsigned long *src, unsigned nbits)
+{
+	return 1;
+}
+
+static inline void slice_bitmap_set(unsigned long *map, unsigned int start,
+				    unsigned int nbits)
+{
+}
+#endif /* __ASSEMBLY__ */
+
+#endif /* CONFIG_PPC_MM_SLICES */
+
+#endif /* _ASM_POWERPC_NOHASH_32_SLICE_H */

@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_NOHASH_64_SLICE_H
+#define _ASM_POWERPC_NOHASH_64_SLICE_H
+
+#ifdef CONFIG_PPC_64K_PAGES
+#define get_slice_psize(mm, addr)	MMU_PAGE_64K
+#else /* CONFIG_PPC_64K_PAGES */
+#define get_slice_psize(mm, addr)	MMU_PAGE_4K
+#endif /* !CONFIG_PPC_64K_PAGES */
+#define slice_set_user_psize(mm, psize)	do { BUG(); } while (0)
+
+#endif /* _ASM_POWERPC_NOHASH_64_SLICE_H */

@@ -344,5 +344,6 @@ typedef struct page *pgtable_t;
 
 #include <asm-generic/memory_model.h>
 #endif /* __ASSEMBLY__ */
+#include <asm/slice.h>
 
 #endif /* _ASM_POWERPC_PAGE_H */

@@ -86,65 +86,6 @@ extern u64 ppc64_pft_size;
 
 #endif /* __ASSEMBLY__ */
 
-#ifdef CONFIG_PPC_MM_SLICES
-
-#define SLICE_LOW_SHIFT		28
-#define SLICE_HIGH_SHIFT	40
-
-#define SLICE_LOW_TOP		(0x100000000ul)
-#define SLICE_NUM_LOW		(SLICE_LOW_TOP >> SLICE_LOW_SHIFT)
-#define SLICE_NUM_HIGH		(H_PGTABLE_RANGE >> SLICE_HIGH_SHIFT)
-
-#define GET_LOW_SLICE_INDEX(addr)	((addr) >> SLICE_LOW_SHIFT)
-#define GET_HIGH_SLICE_INDEX(addr)	((addr) >> SLICE_HIGH_SHIFT)
-
-#ifndef __ASSEMBLY__
-struct mm_struct;
-
-extern unsigned long slice_get_unmapped_area(unsigned long addr,
-					     unsigned long len,
-					     unsigned long flags,
-					     unsigned int psize,
-					     int topdown);
-
-extern unsigned int get_slice_psize(struct mm_struct *mm,
-				    unsigned long addr);
-
-extern void slice_set_user_psize(struct mm_struct *mm, unsigned int psize);
-extern void slice_set_range_psize(struct mm_struct *mm, unsigned long start,
-				  unsigned long len, unsigned int psize);
-
-#endif /* __ASSEMBLY__ */
-#else
-#define slice_init()
-#ifdef CONFIG_PPC_BOOK3S_64
-#define get_slice_psize(mm, addr)	((mm)->context.user_psize)
-#define slice_set_user_psize(mm, psize)		\
-do {						\
-	(mm)->context.user_psize = (psize);	\
-	(mm)->context.sllp = SLB_VSID_USER | mmu_psize_defs[(psize)].sllp; \
-} while (0)
-#else /* !CONFIG_PPC_BOOK3S_64 */
-#ifdef CONFIG_PPC_64K_PAGES
-#define get_slice_psize(mm, addr)	MMU_PAGE_64K
-#else /* CONFIG_PPC_64K_PAGES */
-#define get_slice_psize(mm, addr)	MMU_PAGE_4K
-#endif /* !CONFIG_PPC_64K_PAGES */
-#define slice_set_user_psize(mm, psize)	do { BUG(); } while(0)
-#endif /* CONFIG_PPC_BOOK3S_64 */
-
-#define slice_set_range_psize(mm, start, len, psize)	\
-	slice_set_user_psize((mm), (psize))
-#endif /* CONFIG_PPC_MM_SLICES */
-
-#ifdef CONFIG_HUGETLB_PAGE
-
-#ifdef CONFIG_PPC_MM_SLICES
-#define HAVE_ARCH_HUGETLB_UNMAPPED_AREA
-#endif
-
-#endif /* !CONFIG_HUGETLB_PAGE */
-
 #define VM_DATA_DEFAULT_FLAGS \
 	(is_32bit_task() ? \
 	 VM_DATA_DEFAULT_FLAGS32 : VM_DATA_DEFAULT_FLAGS64)

@@ -0,0 +1,42 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_SLICE_H
+#define _ASM_POWERPC_SLICE_H
+
+#ifdef CONFIG_PPC_BOOK3S_64
+#include <asm/book3s/64/slice.h>
+#elif defined(CONFIG_PPC64)
+#include <asm/nohash/64/slice.h>
+#elif defined(CONFIG_PPC_MMU_NOHASH)
+#include <asm/nohash/32/slice.h>
+#endif
+
+#ifdef CONFIG_PPC_MM_SLICES
+
+#ifdef CONFIG_HUGETLB_PAGE
+#define HAVE_ARCH_HUGETLB_UNMAPPED_AREA
+#endif
+#define HAVE_ARCH_UNMAPPED_AREA
+#define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN
+
+#ifndef __ASSEMBLY__
+
+struct mm_struct;
+
+unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len,
+				      unsigned long flags, unsigned int psize,
+				      int topdown);
+
+unsigned int get_slice_psize(struct mm_struct *mm, unsigned long addr);
+
+void slice_set_user_psize(struct mm_struct *mm, unsigned int psize);
+void slice_set_range_psize(struct mm_struct *mm, unsigned long start,
+			   unsigned long len, unsigned int psize);
+#endif /* __ASSEMBLY__ */
+
+#else /* CONFIG_PPC_MM_SLICES */
+
+#define slice_set_range_psize(mm, start, len, psize)	\
+	slice_set_user_psize((mm), (psize))
+#endif /* CONFIG_PPC_MM_SLICES */
+
+#endif /* _ASM_POWERPC_SLICE_H */

@@ -73,10 +73,11 @@ static void slice_range_to_mask(unsigned long start, unsigned long len,
 	unsigned long end = start + len - 1;
 
 	ret->low_slices = 0;
-	bitmap_zero(ret->high_slices, SLICE_NUM_HIGH);
+	slice_bitmap_zero(ret->high_slices, SLICE_NUM_HIGH);
 
 	if (start < SLICE_LOW_TOP) {
-		unsigned long mend = min(end, (SLICE_LOW_TOP - 1));
+		unsigned long mend = min(end,
+					 (unsigned long)(SLICE_LOW_TOP - 1));
 
 		ret->low_slices = (1u << (GET_LOW_SLICE_INDEX(mend) + 1))
 			- (1u << GET_LOW_SLICE_INDEX(start));

@@ -87,7 +88,7 @@ static void slice_range_to_mask(unsigned long start, unsigned long len,
 		unsigned long align_end = ALIGN(end, (1UL << SLICE_HIGH_SHIFT));
 		unsigned long count = GET_HIGH_SLICE_INDEX(align_end) - start_index;
 
-		bitmap_set(ret->high_slices, start_index, count);
+		slice_bitmap_set(ret->high_slices, start_index, count);
 	}
 }
 

@@ -113,11 +114,13 @@ static int slice_high_has_vma(struct mm_struct *mm, unsigned long slice)
 	unsigned long start = slice << SLICE_HIGH_SHIFT;
 	unsigned long end = start + (1ul << SLICE_HIGH_SHIFT);
 
+#ifdef CONFIG_PPC64
 	/* Hack, so that each addresses is controlled by exactly one
 	 * of the high or low area bitmaps, the first high area starts
 	 * at 4GB, not 0 */
 	if (start == 0)
 		start = SLICE_LOW_TOP;
+#endif
 
 	return !slice_area_is_free(mm, start, end - start);
 }

@@ -128,7 +131,7 @@ static void slice_mask_for_free(struct mm_struct *mm, struct slice_mask *ret,
 	unsigned long i;
 
 	ret->low_slices = 0;
-	bitmap_zero(ret->high_slices, SLICE_NUM_HIGH);
+	slice_bitmap_zero(ret->high_slices, SLICE_NUM_HIGH);
 
 	for (i = 0; i < SLICE_NUM_LOW; i++)
 		if (!slice_low_has_vma(mm, i))

@@ -151,7 +154,7 @@ static void slice_mask_for_size(struct mm_struct *mm, int psize, struct slice_ma
 	u64 lpsizes;
 
 	ret->low_slices = 0;
-	bitmap_zero(ret->high_slices, SLICE_NUM_HIGH);
+	slice_bitmap_zero(ret->high_slices, SLICE_NUM_HIGH);
 
 	lpsizes = mm->context.low_slices_psize;
 	for (i = 0; i < SLICE_NUM_LOW; i++)

@@ -180,15 +183,16 @@ static int slice_check_fit(struct mm_struct *mm,
 	 */
 	unsigned long slice_count = GET_HIGH_SLICE_INDEX(mm->context.slb_addr_limit);
 
-	bitmap_and(result, mask.high_slices,
-		   available.high_slices, slice_count);
+	slice_bitmap_and(result, mask.high_slices, available.high_slices,
+			 slice_count);
 
 	return (mask.low_slices & available.low_slices) == mask.low_slices &&
-		bitmap_equal(result, mask.high_slices, slice_count);
+		slice_bitmap_equal(result, mask.high_slices, slice_count);
 }
 
 static void slice_flush_segments(void *parm)
 {
+#ifdef CONFIG_PPC64
 	struct mm_struct *mm = parm;
 	unsigned long flags;
 

@@ -200,6 +204,7 @@ static void slice_flush_segments(void *parm)
 	local_irq_save(flags);
 	slb_flush_and_rebolt();
 	local_irq_restore(flags);
+#endif
 }
 
 static void slice_convert(struct mm_struct *mm, struct slice_mask mask, int psize)

@@ -389,16 +394,16 @@ static unsigned long slice_find_area(struct mm_struct *mm, unsigned long len,
 static inline void slice_or_mask(struct slice_mask *dst, struct slice_mask *src)
 {
 	dst->low_slices |= src->low_slices;
-	bitmap_or(dst->high_slices, dst->high_slices, src->high_slices,
-		  SLICE_NUM_HIGH);
+	slice_bitmap_or(dst->high_slices, dst->high_slices, src->high_slices,
+			SLICE_NUM_HIGH);
 }
 
 static inline void slice_andnot_mask(struct slice_mask *dst, struct slice_mask *src)
 {
 	dst->low_slices &= ~src->low_slices;
 
-	bitmap_andnot(dst->high_slices, dst->high_slices, src->high_slices,
-		      SLICE_NUM_HIGH);
+	slice_bitmap_andnot(dst->high_slices, dst->high_slices,
+			    src->high_slices, SLICE_NUM_HIGH);
 }
 
 #ifdef CONFIG_PPC_64K_PAGES

@@ -446,14 +451,14 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len,
 	 * init different masks
 	 */
 	mask.low_slices = 0;
-	bitmap_zero(mask.high_slices, SLICE_NUM_HIGH);
+	slice_bitmap_zero(mask.high_slices, SLICE_NUM_HIGH);
 
 	/* silence stupid warning */;
 	potential_mask.low_slices = 0;
-	bitmap_zero(potential_mask.high_slices, SLICE_NUM_HIGH);
+	slice_bitmap_zero(potential_mask.high_slices, SLICE_NUM_HIGH);
 
 	compat_mask.low_slices = 0;
-	bitmap_zero(compat_mask.high_slices, SLICE_NUM_HIGH);
+	slice_bitmap_zero(compat_mask.high_slices, SLICE_NUM_HIGH);
 
 	/* Sanity checks */
 	BUG_ON(mm->task_size == 0);

@@ -591,7 +596,8 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len,
  convert:
 	slice_andnot_mask(&mask, &good_mask);
 	slice_andnot_mask(&mask, &compat_mask);
-	if (mask.low_slices || !bitmap_empty(mask.high_slices, SLICE_NUM_HIGH)) {
+	if (mask.low_slices ||
+	    !slice_bitmap_empty(mask.high_slices, SLICE_NUM_HIGH)) {
 		slice_convert(mm, mask, psize);
 		if (psize > MMU_PAGE_BASE)
 			on_each_cpu(slice_flush_segments, mm, 1);

@@ -4,7 +4,7 @@
 
 #ifdef CONFIG_PPC_MM_SLICES
 
-#define SLICE_LOW_SHIFT		28
+#define SLICE_LOW_SHIFT		26	/* 64 slices */
 #define SLICE_LOW_TOP		(0x100000000ull)
 #define SLICE_NUM_LOW		(SLICE_LOW_TOP >> SLICE_LOW_SHIFT)
 #define GET_LOW_SLICE_INDEX(addr)	((addr) >> SLICE_LOW_SHIFT)

@@ -91,7 +91,8 @@ typedef struct {
 	struct npu_context *npu_context;
 
 #ifdef CONFIG_PPC_MM_SLICES
-	u64 low_slices_psize;	/* SLB page size encodings */
+	 /* SLB page size encodings*/
+	unsigned char low_slices_psize[BITS_PER_LONG / BITS_PER_BYTE];
 	unsigned char high_slices_psize[SLICE_ARRAY_SIZE];
 	unsigned long slb_addr_limit;
 #else

@@ -186,6 +186,11 @@
 #define M_APG2		0x00000040
 #define M_APG3		0x00000060
 
+#ifdef CONFIG_PPC_MM_SLICES
+#include <asm/nohash/32/slice.h>
+#define SLICE_ARRAY_SIZE	(1 << (32 - SLICE_LOW_SHIFT - 1))
+#endif
+
 #ifndef __ASSEMBLY__
 typedef struct {
 	unsigned int id;

@@ -193,7 +198,7 @@ typedef struct {
 	unsigned long vdso_base;
 #ifdef CONFIG_PPC_MM_SLICES
 	u16 user_psize;		/* page size index */
-	u64 low_slices_psize;	/* page size encodings */
+	unsigned char low_slices_psize[SLICE_ARRAY_SIZE];
 	unsigned char high_slices_psize[0];
 	unsigned long slb_addr_limit;
 #endif

@@ -141,7 +141,7 @@ struct paca_struct {
 #ifdef CONFIG_PPC_BOOK3S
 	mm_context_id_t mm_ctx_id;
 #ifdef CONFIG_PPC_MM_SLICES
-	u64 mm_ctx_low_slices_psize;
+	unsigned char mm_ctx_low_slices_psize[BITS_PER_LONG / BITS_PER_BYTE];
 	unsigned char mm_ctx_high_slices_psize[SLICE_ARRAY_SIZE];
 	unsigned long mm_ctx_slb_addr_limit;
 #else

@@ -265,7 +265,8 @@ void copy_mm_to_paca(struct mm_struct *mm)
 #ifdef CONFIG_PPC_MM_SLICES
 	VM_BUG_ON(!mm->context.slb_addr_limit);
 	get_paca()->mm_ctx_slb_addr_limit = mm->context.slb_addr_limit;
-	get_paca()->mm_ctx_low_slices_psize = context->low_slices_psize;
+	memcpy(&get_paca()->mm_ctx_low_slices_psize,
+	       &context->low_slices_psize, sizeof(context->low_slices_psize));
 	memcpy(&get_paca()->mm_ctx_high_slices_psize,
 	       &context->high_slices_psize, TASK_SLICE_ARRAY_SZ(mm));
 #else /* CONFIG_PPC_MM_SLICES */

@@ -1109,19 +1109,18 @@ unsigned int hash_page_do_lazy_icache(unsigned int pp, pte_t pte, int trap)
 #ifdef CONFIG_PPC_MM_SLICES
 static unsigned int get_paca_psize(unsigned long addr)
 {
-	u64 lpsizes;
-	unsigned char *hpsizes;
+	unsigned char *psizes;
 	unsigned long index, mask_index;
 
 	if (addr < SLICE_LOW_TOP) {
-		lpsizes = get_paca()->mm_ctx_low_slices_psize;
+		psizes = get_paca()->mm_ctx_low_slices_psize;
 		index = GET_LOW_SLICE_INDEX(addr);
-		return (lpsizes >> (index * 4)) & 0xF;
+	} else {
+		psizes = get_paca()->mm_ctx_high_slices_psize;
+		index = GET_HIGH_SLICE_INDEX(addr);
 	}
-	hpsizes = get_paca()->mm_ctx_high_slices_psize;
-	index = GET_HIGH_SLICE_INDEX(addr);
 	mask_index = index & 0x1;
-	return (hpsizes[index >> 1] >> (mask_index * 4)) & 0xF;
+	return (psizes[index >> 1] >> (mask_index * 4)) & 0xF;
 }
 
 #else

@@ -200,10 +200,12 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_1T_SEGMENT)
 5:
 	/*
 	 * Handle lpsizes
-	 * r9 is get_paca()->context.low_slices_psize, r11 is index
+	 * r9 is get_paca()->context.low_slices_psize[index], r11 is mask_index
 	 */
-	ld	r9,PACALOWSLICESPSIZE(r13)
-	mr	r11,r10
+	srdi    r11,r10,1 /* index */
+	addi	r9,r11,PACALOWSLICESPSIZE
+	lbzx	r9,r13,r9		/* r9 is lpsizes[r11] */
+	rldicl	r11,r10,0,63		/* r11 = r10 & 0x1 */
 6:
 	sldi	r11,r11,2  /* index * 4 */
 	/* Extract the psize and multiply to get an array offset */

@@ -148,18 +148,20 @@ static void slice_mask_for_free(struct mm_struct *mm, struct slice_mask *ret,
 static void slice_mask_for_size(struct mm_struct *mm, int psize, struct slice_mask *ret,
 				unsigned long high_limit)
 {
-	unsigned char *hpsizes;
+	unsigned char *hpsizes, *lpsizes;
 	int index, mask_index;
 	unsigned long i;
-	u64 lpsizes;
 
 	ret->low_slices = 0;
 	slice_bitmap_zero(ret->high_slices, SLICE_NUM_HIGH);
 
 	lpsizes = mm->context.low_slices_psize;
-	for (i = 0; i < SLICE_NUM_LOW; i++)
-		if (((lpsizes >> (i * 4)) & 0xf) == psize)
+	for (i = 0; i < SLICE_NUM_LOW; i++) {
+		mask_index = i & 0x1;
+		index = i >> 1;
+		if (((lpsizes[index] >> (mask_index * 4)) & 0xf) == psize)
 			ret->low_slices |= 1u << i;
+	}
 
 	if (high_limit <= SLICE_LOW_TOP)
 		return;

@@ -211,8 +213,7 @@ static void slice_convert(struct mm_struct *mm, struct slice_mask mask, int psiz
 {
 	int index, mask_index;
 	/* Write the new slice psize bits */
-	unsigned char *hpsizes;
-	u64 lpsizes;
+	unsigned char *hpsizes, *lpsizes;
 	unsigned long i, flags;
 
 	slice_dbg("slice_convert(mm=%p, psize=%d)\n", mm, psize);

@@ -225,12 +226,13 @@ static void slice_convert(struct mm_struct *mm, struct slice_mask mask, int psiz
 
 	lpsizes = mm->context.low_slices_psize;
 	for (i = 0; i < SLICE_NUM_LOW; i++)
-		if (mask.low_slices & (1u << i))
-			lpsizes = (lpsizes & ~(0xful << (i * 4))) |
-				(((unsigned long)psize) << (i * 4));
-
-	/* Assign the value back */
-	mm->context.low_slices_psize = lpsizes;
+		if (mask.low_slices & (1u << i)) {
+			mask_index = i & 0x1;
+			index = i >> 1;
+			lpsizes[index] = (lpsizes[index] &
+					  ~(0xf << (mask_index * 4))) |
+				(((unsigned long)psize) << (mask_index * 4));
+		}
 
 	hpsizes = mm->context.high_slices_psize;
 	for (i = 0; i < GET_HIGH_SLICE_INDEX(mm->context.slb_addr_limit); i++) {

@@ -629,7 +631,7 @@ unsigned long arch_get_unmapped_area_topdown(struct file *filp,
 
 unsigned int get_slice_psize(struct mm_struct *mm, unsigned long addr)
 {
-	unsigned char *hpsizes;
+	unsigned char *psizes;
 	int index, mask_index;
 
 	/*

@@ -643,15 +645,14 @@ unsigned int get_slice_psize(struct mm_struct *mm, unsigned long addr)
 #endif
 	}
 	if (addr < SLICE_LOW_TOP) {
-		u64 lpsizes;
-		lpsizes = mm->context.low_slices_psize;
+		psizes = mm->context.low_slices_psize;
 		index = GET_LOW_SLICE_INDEX(addr);
-		return (lpsizes >> (index * 4)) & 0xf;
+	} else {
+		psizes = mm->context.high_slices_psize;
+		index = GET_HIGH_SLICE_INDEX(addr);
 	}
-	hpsizes = mm->context.high_slices_psize;
-	index = GET_HIGH_SLICE_INDEX(addr);
 	mask_index = index & 0x1;
-	return (hpsizes[index >> 1] >> (mask_index * 4)) & 0xf;
+	return (psizes[index >> 1] >> (mask_index * 4)) & 0xf;
 }
 EXPORT_SYMBOL_GPL(get_slice_psize);
 

@@ -672,8 +673,8 @@ EXPORT_SYMBOL_GPL(get_slice_psize);
 void slice_set_user_psize(struct mm_struct *mm, unsigned int psize)
 {
 	int index, mask_index;
-	unsigned char *hpsizes;
-	unsigned long flags, lpsizes;
+	unsigned char *hpsizes, *lpsizes;
+	unsigned long flags;
 	unsigned int old_psize;
 	int i;
 

@@ -691,12 +692,14 @@ void slice_set_user_psize(struct mm_struct *mm, unsigned int psize)
 	wmb();
 
 	lpsizes = mm->context.low_slices_psize;
-	for (i = 0; i < SLICE_NUM_LOW; i++)
-		if (((lpsizes >> (i * 4)) & 0xf) == old_psize)
-			lpsizes = (lpsizes & ~(0xful << (i * 4))) |
-				(((unsigned long)psize) << (i * 4));
-	/* Assign the value back */
-	mm->context.low_slices_psize = lpsizes;
+	for (i = 0; i < SLICE_NUM_LOW; i++) {
+		mask_index = i & 0x1;
+		index = i >> 1;
+		if (((lpsizes[index] >> (mask_index * 4)) & 0xf) == old_psize)
+			lpsizes[index] = (lpsizes[index] &
+					  ~(0xf << (mask_index * 4))) |
+				(((unsigned long)psize) << (mask_index * 4));
+	}
 
 	hpsizes = mm->context.high_slices_psize;
 	for (i = 0; i < SLICE_NUM_HIGH; i++) {

@@ -191,6 +191,12 @@ typedef struct {
 	unsigned int id;
 	unsigned int active;
 	unsigned long vdso_base;
+#ifdef CONFIG_PPC_MM_SLICES
+	u16 user_psize;		/* page size index */
+	u64 low_slices_psize;	/* page size encodings */
+	unsigned char high_slices_psize[0];
+	unsigned long slb_addr_limit;
+#endif
 } mm_context_t;
 
 #define PHYS_IMMR_BASE (mfspr(SPRN_IMMR) & 0xfff80000)

@@ -919,6 +919,8 @@ void __init setup_arch(char **cmdline_p)
 #ifdef CONFIG_PPC64
 	if (!radix_enabled())
 		init_mm.context.slb_addr_limit = DEFAULT_MAP_WINDOW_USER64;
+#elif defined(CONFIG_PPC_8xx)
+	init_mm.context.slb_addr_limit = DEFAULT_MAP_WINDOW;
 #else
 #error	"context.addr_limit not initialized."
 #endif

@@ -192,7 +192,7 @@ void set_context(unsigned long id, pgd_t *pgd)
 	mtspr(SPRN_M_TW, __pa(pgd) - offset);
 
 	/* Update context */
-	mtspr(SPRN_M_CASID, id);
+	mtspr(SPRN_M_CASID, id - 1);
 	/* sync */
 	mb();
 }

@@ -553,9 +553,11 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 	struct hstate *hstate = hstate_file(file);
 	int mmu_psize = shift_to_mmu_psize(huge_page_shift(hstate));
 
+#ifdef CONFIG_PPC_RADIX_MMU
 	if (radix_enabled())
 		return radix__hugetlb_get_unmapped_area(file, addr, len,
 						       pgoff, flags);
+#endif
 	return slice_get_unmapped_area(addr, len, flags, mmu_psize, 1);
 }
 #endif

@@ -331,6 +331,20 @@ int init_new_context(struct task_struct *t, struct mm_struct *mm)
 {
 	pr_hard("initing context for mm @%p\n", mm);
 
+#ifdef	CONFIG_PPC_MM_SLICES
+	if (!mm->context.slb_addr_limit)
+		mm->context.slb_addr_limit = DEFAULT_MAP_WINDOW;
+
+	/*
+	 * We have MMU_NO_CONTEXT set to be ~0. Hence check
+	 * explicitly against context.id == 0. This ensures that we properly
+	 * initialize context slice details for newly allocated mm's (which will
+	 * have id == 0) and don't alter context slice inherited via fork (which
+	 * will have id != 0).
+	 */
+	if (mm->context.id == 0)
+		slice_set_user_psize(mm, mmu_virtual_psize);
+#endif
 	mm->context.id = MMU_NO_CONTEXT;
 	mm->context.active = 0;
 	return 0;

@@ -428,8 +442,8 @@ void __init mmu_context_init(void)
 	 *      -- BenH
 	 */
 	if (mmu_has_feature(MMU_FTR_TYPE_8xx)) {
-		first_context = 0;
-		last_context = 15;
+		first_context = 1;
+		last_context = 16;
 		no_selective_tlbil = true;
 	} else if (mmu_has_feature(MMU_FTR_TYPE_47x)) {
 		first_context = 1;

@@ -326,6 +326,7 @@ config PPC_BOOK3E_MMU
 config PPC_MM_SLICES
 	bool
 	default y if PPC_BOOK3S_64
+	default y if PPC_8xx && HUGETLB_PAGE
 	default n
 
 config PPC_HAVE_PMU_SUPPORT