Merge tag 'powerpc-4.17-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:
 "Notable changes:

   - Support for 4PB user address space on 64-bit, opt-in via mmap().

   - Removal of POWER4 support, which was accidentally broken in 2016
     and no one noticed, and blocked use of some modern instructions.

   - Workarounds so that the hypervisor can enable Transactional Memory
     on Power9.

   - A series to disable the DAWR (Data Address Watchpoint Register) on
     Power9.

   - More information displayed in the meltdown/spectre_v1/v2 sysfs
     files.

   - A vpermxor (Power8 Altivec) implementation for the raid6 Q
     Syndrome.

   - A big series to make the allocation of our pacas (per cpu area),
     kernel page tables, and per-cpu stacks NUMA aware when using the
     Radix MMU on Power9.

  And as usual many fixes, reworks and cleanups.

  Thanks to: Aaro Koskinen, Alexandre Belloni, Alexey Kardashevskiy,
  Alistair Popple, Andy Shevchenko, Aneesh Kumar K.V, Anshuman Khandual,
  Balbir Singh, Benjamin Herrenschmidt, Christophe Leroy, Christophe
  Lombard, Cyril Bur, Daniel Axtens, Dave Young, Finn Thain, Frederic
  Barrat, Gustavo Romero, Horia Geantă, Jonathan Neuschäfer, Kees Cook,
  Larry Finger, Laurent Dufour, Laurent Vivier, Logan Gunthorpe,
  Madhavan Srinivasan, Mark Greer, Mark Hairgrove, Markus Elfring,
  Mathieu Malaterre, Matt Brown, Matt Evans, Mauricio Faria de Oliveira,
  Michael Neuling, Naveen N. Rao, Nicholas Piggin, Paul Mackerras,
  Philippe Bergheaud, Ram Pai, Rob Herring, Sam Bobroff, Segher
  Boessenkool, Simon Guo, Simon Horman, Stewart Smith, Sukadev
  Bhattiprolu, Suraj Jitindar Singh, Thiago Jung Bauermann, Vaibhav
  Jain, Vaidyanathan Srinivasan, Vasant Hegde, Wei Yongjun"

* tag 'powerpc-4.17-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (207 commits)
  powerpc/64s/idle: Fix restore of AMOR on POWER9 after deep sleep
  powerpc/64s: Fix POWER9 DD2.2 and above in cputable features
  powerpc/64s: Fix pkey support in dt_cpu_ftrs, add CPU_FTR_PKEY bit
  powerpc/64s: Fix dt_cpu_ftrs to have restore_cpu clear unwanted LPCR bits
  Revert "powerpc/64s/idle: POWER9 ESL=0 stop avoid save/restore overhead"
  powerpc: iomap.c: introduce io{read|write}64_{lo_hi|hi_lo}
  powerpc: io.h: move iomap.h include so that it can use readq/writeq defs
  cxl: Fix possible deadlock when processing page faults from cxllib
  powerpc/hw_breakpoint: Only disable hw breakpoint if cpu supports it
  powerpc/mm/radix: Update command line parsing for disable_radix
  powerpc/mm/radix: Parse disable_radix commandline correctly.
  powerpc/mm/hugetlb: initialize the pagetable cache correctly for hugetlb
  powerpc/mm/radix: Update pte fragment count from 16 to 256 on radix
  powerpc/mm/keys: Update documentation and remove unnecessary check
  powerpc/64s/idle: POWER9 ESL=0 stop avoid save/restore overhead
  powerpc/64s/idle: Consolidate power9_offline_stop()/power9_idle_stop()
  powerpc/powernv: Always stop secondaries before reboot/shutdown
  powerpc: hard disable irqs in smp_send_stop loop
  powerpc: use NMI IPI for smp_send_stop
  powerpc/powernv: Fix SMT4 forcing idle code
  ...

1 files changed, 259 insertions, 226 deletions

diff --git a/arch/powerpc/mm/slice.c b/arch/powerpc/mm/slice.c
index 23ec2c5e3b78..9cd87d11fe4e 100644
--- a/arch/powerpc/mm/slice.c
+++ b/arch/powerpc/mm/slice.c
@@ -37,32 +37,25 @@
 #include <asm/hugetlb.h>
 
 static DEFINE_SPINLOCK(slice_convert_lock);
-/*
- * 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);
-};
 
 #ifdef DEBUG
 int _slice_debug = 1;
 
-static void slice_print_mask(const char *label, struct slice_mask mask)
+static void slice_print_mask(const char *label, const struct slice_mask *mask)
 {
 	if (!_slice_debug)
 		return;
-	pr_devel("%s low_slice: %*pbl\n", label, (int)SLICE_NUM_LOW, &mask.low_slices);
-	pr_devel("%s high_slice: %*pbl\n", label, (int)SLICE_NUM_HIGH, mask.high_slices);
+	pr_devel("%s low_slice: %*pbl\n", label,
+			(int)SLICE_NUM_LOW, &mask->low_slices);
+	pr_devel("%s high_slice: %*pbl\n", label,
+			(int)SLICE_NUM_HIGH, mask->high_slices);
 }
 
 #define slice_dbg(fmt...) do { if (_slice_debug) pr_devel(fmt); } while (0)
 
 #else
 
-static void slice_print_mask(const char *label, struct slice_mask mask) {}
+static void slice_print_mask(const char *label, const struct slice_mask *mask) {}
 #define slice_dbg(fmt...)
 
 #endif
@@ -73,10 +66,12 @@ 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);
+	if (SLICE_NUM_HIGH)
+		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));
@@ -113,11 +108,13 @@ 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 +125,8 @@ 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);
+	if (SLICE_NUM_HIGH)
+		bitmap_zero(ret->high_slices, SLICE_NUM_HIGH);
 
 	for (i = 0; i < SLICE_NUM_LOW; i++)
 		if (!slice_low_has_vma(mm, i))
@@ -142,53 +140,75 @@ static void slice_mask_for_free(struct mm_struct *mm, struct slice_mask *ret,
 			__set_bit(i, ret->high_slices);
 }
 
-static void slice_mask_for_size(struct mm_struct *mm, int psize, struct slice_mask *ret,
-				unsigned long high_limit)
+#ifdef CONFIG_PPC_BOOK3S_64
+static struct slice_mask *slice_mask_for_size(struct mm_struct *mm, int psize)
 {
-	unsigned char *hpsizes;
-	int index, mask_index;
-	unsigned long i;
-	u64 lpsizes;
-
-	ret->low_slices = 0;
-	bitmap_zero(ret->high_slices, SLICE_NUM_HIGH);
+#ifdef CONFIG_PPC_64K_PAGES
+	if (psize == MMU_PAGE_64K)
+		return &mm->context.mask_64k;
+#endif
+	if (psize == MMU_PAGE_4K)
+		return &mm->context.mask_4k;
+#ifdef CONFIG_HUGETLB_PAGE
+	if (psize == MMU_PAGE_16M)
+		return &mm->context.mask_16m;
+	if (psize == MMU_PAGE_16G)
+		return &mm->context.mask_16g;
+#endif
+	BUG();
+}
+#elif defined(CONFIG_PPC_8xx)
+static struct slice_mask *slice_mask_for_size(struct mm_struct *mm, int psize)
+{
+	if (psize == mmu_virtual_psize)
+		return &mm->context.mask_base_psize;
+#ifdef CONFIG_HUGETLB_PAGE
+	if (psize == MMU_PAGE_512K)
+		return &mm->context.mask_512k;
+	if (psize == MMU_PAGE_8M)
+		return &mm->context.mask_8m;
+#endif
+	BUG();
+}
+#else
+#error "Must define the slice masks for page sizes supported by the platform"
+#endif
 
-	lpsizes = mm->context.low_slices_psize;
-	for (i = 0; i < SLICE_NUM_LOW; i++)
-		if (((lpsizes >> (i * 4)) & 0xf) == psize)
-			ret->low_slices |= 1u << i;
+static bool slice_check_range_fits(struct mm_struct *mm,
+			   const struct slice_mask *available,
+			   unsigned long start, unsigned long len)
+{
+	unsigned long end = start + len - 1;
+	u64 low_slices = 0;
 
-	if (high_limit <= SLICE_LOW_TOP)
-		return;
+	if (start < SLICE_LOW_TOP) {
+		unsigned long mend = min(end,
+					 (unsigned long)(SLICE_LOW_TOP - 1));
 
-	hpsizes = mm->context.high_slices_psize;
-	for (i = 0; i < GET_HIGH_SLICE_INDEX(high_limit); i++) {
-		mask_index = i & 0x1;
-		index = i >> 1;
-		if (((hpsizes[index] >> (mask_index * 4)) & 0xf) == psize)
-			__set_bit(i, ret->high_slices);
+		low_slices = (1u << (GET_LOW_SLICE_INDEX(mend) + 1))
+				- (1u << GET_LOW_SLICE_INDEX(start));
 	}
-}
+	if ((low_slices & available->low_slices) != low_slices)
+		return false;
 
-static int slice_check_fit(struct mm_struct *mm,
-			   struct slice_mask mask, struct slice_mask available)
-{
-	DECLARE_BITMAP(result, SLICE_NUM_HIGH);
-	/*
-	 * Make sure we just do bit compare only to the max
-	 * addr limit and not the full bit map size.
-	 */
-	unsigned long slice_count = GET_HIGH_SLICE_INDEX(mm->context.slb_addr_limit);
+	if (SLICE_NUM_HIGH && ((start + len) > SLICE_LOW_TOP)) {
+		unsigned long start_index = GET_HIGH_SLICE_INDEX(start);
+		unsigned long align_end = ALIGN(end, (1UL << SLICE_HIGH_SHIFT));
+		unsigned long count = GET_HIGH_SLICE_INDEX(align_end) - start_index;
+		unsigned long i;
 
-	bitmap_and(result, mask.high_slices,
-		   available.high_slices, slice_count);
+		for (i = start_index; i < start_index + count; i++) {
+			if (!test_bit(i, available->high_slices))
+				return false;
+		}
+	}
 
-	return (mask.low_slices & available.low_slices) == mask.low_slices &&
-		bitmap_equal(result, mask.high_slices, slice_count);
+	return true;
 }
 
 static void slice_flush_segments(void *parm)
 {
+#ifdef CONFIG_PPC64
 	struct mm_struct *mm = parm;
 	unsigned long flags;
 
@@ -200,40 +220,64 @@ 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)
+static void slice_convert(struct mm_struct *mm,
+				const struct slice_mask *mask, int psize)
 {
 	int index, mask_index;
 	/* Write the new slice psize bits */
-	unsigned char *hpsizes;
-	u64 lpsizes;
+	unsigned char *hpsizes, *lpsizes;
+	struct slice_mask *psize_mask, *old_mask;
 	unsigned long i, flags;
+	int old_psize;
 
 	slice_dbg("slice_convert(mm=%p, psize=%d)\n", mm, psize);
 	slice_print_mask(" mask", mask);
 
+	psize_mask = slice_mask_for_size(mm, psize);
+
 	/* We need to use a spinlock here to protect against
 	 * concurrent 64k -> 4k demotion ...
 	 */
 	spin_lock_irqsave(&slice_convert_lock, flags);
 
 	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));
+	for (i = 0; i < SLICE_NUM_LOW; i++) {
+		if (!(mask->low_slices & (1u << i)))
+			continue;
+
+		mask_index = i & 0x1;
+		index = i >> 1;
 
-	/* Assign the value back */
-	mm->context.low_slices_psize = lpsizes;
+		/* Update the slice_mask */
+		old_psize = (lpsizes[index] >> (mask_index * 4)) & 0xf;
+		old_mask = slice_mask_for_size(mm, old_psize);
+		old_mask->low_slices &= ~(1u << i);
+		psize_mask->low_slices |= 1u << i;
+
+		/* Update the sizes array */
+		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++) {
+		if (!test_bit(i, mask->high_slices))
+			continue;
+
 		mask_index = i & 0x1;
 		index = i >> 1;
-		if (test_bit(i, mask.high_slices))
-			hpsizes[index] = (hpsizes[index] &
-					  ~(0xf << (mask_index * 4))) |
+
+		/* Update the slice_mask */
+		old_psize = (hpsizes[index] >> (mask_index * 4)) & 0xf;
+		old_mask = slice_mask_for_size(mm, old_psize);
+		__clear_bit(i, old_mask->high_slices);
+		__set_bit(i, psize_mask->high_slices);
+
+		/* Update the sizes array */
+		hpsizes[index] = (hpsizes[index] & ~(0xf << (mask_index * 4))) |
 				(((unsigned long)psize) << (mask_index * 4));
 	}
 
@@ -254,26 +298,25 @@ static void slice_convert(struct mm_struct *mm, struct slice_mask mask, int psiz
  * 'available' slice_mark.
  */
 static bool slice_scan_available(unsigned long addr,
-				 struct slice_mask available,
-				 int end,
-				 unsigned long *boundary_addr)
+				 const struct slice_mask *available,
+				 int end, unsigned long *boundary_addr)
 {
 	unsigned long slice;
 	if (addr < SLICE_LOW_TOP) {
 		slice = GET_LOW_SLICE_INDEX(addr);
 		*boundary_addr = (slice + end) << SLICE_LOW_SHIFT;
-		return !!(available.low_slices & (1u << slice));
+		return !!(available->low_slices & (1u << slice));
 	} else {
 		slice = GET_HIGH_SLICE_INDEX(addr);
 		*boundary_addr = (slice + end) ?
 			((slice + end) << SLICE_HIGH_SHIFT) : SLICE_LOW_TOP;
-		return !!test_bit(slice, available.high_slices);
+		return !!test_bit(slice, available->high_slices);
 	}
 }
 
 static unsigned long slice_find_area_bottomup(struct mm_struct *mm,
 					      unsigned long len,
-					      struct slice_mask available,
+					      const struct slice_mask *available,
 					      int psize, unsigned long high_limit)
 {
 	int pshift = max_t(int, mmu_psize_defs[psize].shift, PAGE_SHIFT);
@@ -319,7 +362,7 @@ static unsigned long slice_find_area_bottomup(struct mm_struct *mm,
 
 static unsigned long slice_find_area_topdown(struct mm_struct *mm,
 					     unsigned long len,
-					     struct slice_mask available,
+					     const struct slice_mask *available,
 					     int psize, unsigned long high_limit)
 {
 	int pshift = max_t(int, mmu_psize_defs[psize].shift, PAGE_SHIFT);
@@ -377,7 +420,7 @@ static unsigned long slice_find_area_topdown(struct mm_struct *mm,
 
 
 static unsigned long slice_find_area(struct mm_struct *mm, unsigned long len,
-				     struct slice_mask mask, int psize,
+				     const struct slice_mask *mask, int psize,
 				     int topdown, unsigned long high_limit)
 {
 	if (topdown)
@@ -386,23 +429,33 @@ static unsigned long slice_find_area(struct mm_struct *mm, unsigned long len,
 		return slice_find_area_bottomup(mm, len, mask, psize, high_limit);
 }
 
-static inline void slice_or_mask(struct slice_mask *dst, struct slice_mask *src)
+static inline void slice_copy_mask(struct slice_mask *dst,
+					const 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);
+	dst->low_slices = src->low_slices;
+	if (!SLICE_NUM_HIGH)
+		return;
+	bitmap_copy(dst->high_slices, src->high_slices, SLICE_NUM_HIGH);
 }
 
-static inline void slice_andnot_mask(struct slice_mask *dst, struct slice_mask *src)
+static inline void slice_or_mask(struct slice_mask *dst,
+					const struct slice_mask *src1,
+					const struct slice_mask *src2)
 {
-	DECLARE_BITMAP(result, SLICE_NUM_HIGH);
-
-	dst->low_slices &= ~src->low_slices;
+	dst->low_slices = src1->low_slices | src2->low_slices;
+	if (!SLICE_NUM_HIGH)
+		return;
+	bitmap_or(dst->high_slices, src1->high_slices, src2->high_slices, SLICE_NUM_HIGH);
+}
 
-	bitmap_andnot(result, dst->high_slices, src->high_slices, SLICE_NUM_HIGH);
-	bitmap_copy(dst->high_slices, result, SLICE_NUM_HIGH);
+static inline void slice_andnot_mask(struct slice_mask *dst,
+					const struct slice_mask *src1,
+					const struct slice_mask *src2)
+{
+	dst->low_slices = src1->low_slices & ~src2->low_slices;
+	if (!SLICE_NUM_HIGH)
+		return;
+	bitmap_andnot(dst->high_slices, src1->high_slices, src2->high_slices, SLICE_NUM_HIGH);
 }
 
 #ifdef CONFIG_PPC_64K_PAGES
@@ -415,10 +468,10 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len,
 				      unsigned long flags, unsigned int psize,
 				      int topdown)
 {
-	struct slice_mask mask;
 	struct slice_mask good_mask;
 	struct slice_mask potential_mask;
-	struct slice_mask compat_mask;
+	const struct slice_mask *maskp;
+	const struct slice_mask *compat_maskp = NULL;
 	int fixed = (flags & MAP_FIXED);
 	int pshift = max_t(int, mmu_psize_defs[psize].shift, PAGE_SHIFT);
 	unsigned long page_size = 1UL << pshift;
@@ -442,23 +495,16 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len,
 	}
 
 	if (high_limit > mm->context.slb_addr_limit) {
+		/*
+		 * Increasing the slb_addr_limit does not require
+		 * slice mask cache to be recalculated because it should
+		 * be already initialised beyond the old address limit.
+		 */
 		mm->context.slb_addr_limit = high_limit;
+
 		on_each_cpu(slice_flush_segments, mm, 1);
 	}
 
-	/*
-	 * init different masks
-	 */
-	mask.low_slices = 0;
-	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);
-
-	compat_mask.low_slices = 0;
-	bitmap_zero(compat_mask.high_slices, SLICE_NUM_HIGH);
-
 	/* Sanity checks */
 	BUG_ON(mm->task_size == 0);
 	BUG_ON(mm->context.slb_addr_limit == 0);
@@ -481,8 +527,7 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len,
 	/* First make up a "good" mask of slices that have the right size
 	 * already
 	 */
-	slice_mask_for_size(mm, psize, &good_mask, high_limit);
-	slice_print_mask(" good_mask", good_mask);
+	maskp = slice_mask_for_size(mm, psize);
 
 	/*
 	 * Here "good" means slices that are already the right page size,
@@ -503,40 +548,47 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len,
 	 *	search in good | compat | free, found => convert free.
 	 */
 
-#ifdef CONFIG_PPC_64K_PAGES
-	/* If we support combo pages, we can allow 64k pages in 4k slices */
-	if (psize == MMU_PAGE_64K) {
-		slice_mask_for_size(mm, MMU_PAGE_4K, &compat_mask, high_limit);
+	/*
+	 * If we support combo pages, we can allow 64k pages in 4k slices
+	 * The mask copies could be avoided in most cases here if we had
+	 * a pointer to good mask for the next code to use.
+	 */
+	if (IS_ENABLED(CONFIG_PPC_64K_PAGES) && psize == MMU_PAGE_64K) {
+		compat_maskp = slice_mask_for_size(mm, MMU_PAGE_4K);
 		if (fixed)
-			slice_or_mask(&good_mask, &compat_mask);
+			slice_or_mask(&good_mask, maskp, compat_maskp);
+		else
+			slice_copy_mask(&good_mask, maskp);
+	} else {
+		slice_copy_mask(&good_mask, maskp);
 	}
-#endif
+
+	slice_print_mask(" good_mask", &good_mask);
+	if (compat_maskp)
+		slice_print_mask(" compat_mask", compat_maskp);
 
 	/* First check hint if it's valid or if we have MAP_FIXED */
 	if (addr != 0 || fixed) {
-		/* Build a mask for the requested range */
-		slice_range_to_mask(addr, len, &mask);
-		slice_print_mask(" mask", mask);
-
 		/* Check if we fit in the good mask. If we do, we just return,
 		 * nothing else to do
 		 */
-		if (slice_check_fit(mm, mask, good_mask)) {
+		if (slice_check_range_fits(mm, &good_mask, addr, len)) {
 			slice_dbg(" fits good !\n");
-			return addr;
+			newaddr = addr;
+			goto return_addr;
 		}
 	} else {
 		/* Now let's see if we can find something in the existing
 		 * slices for that size
 		 */
-		newaddr = slice_find_area(mm, len, good_mask,
+		newaddr = slice_find_area(mm, len, &good_mask,
 					  psize, topdown, high_limit);
 		if (newaddr != -ENOMEM) {
 			/* Found within the good mask, we don't have to setup,
 			 * we thus return directly
 			 */
 			slice_dbg(" found area at 0x%lx\n", newaddr);
-			return newaddr;
+			goto return_addr;
 		}
 	}
 	/*
@@ -544,12 +596,15 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len,
 	 * empty and thus can be converted
 	 */
 	slice_mask_for_free(mm, &potential_mask, high_limit);
-	slice_or_mask(&potential_mask, &good_mask);
-	slice_print_mask(" potential", potential_mask);
+	slice_or_mask(&potential_mask, &potential_mask, &good_mask);
+	slice_print_mask(" potential", &potential_mask);
 
-	if ((addr != 0 || fixed) && slice_check_fit(mm, mask, potential_mask)) {
-		slice_dbg(" fits potential !\n");
-		goto convert;
+	if (addr != 0 || fixed) {
+		if (slice_check_range_fits(mm, &potential_mask, addr, len)) {
+			slice_dbg(" fits potential !\n");
+			newaddr = addr;
+			goto convert;
+		}
 	}
 
 	/* If we have MAP_FIXED and failed the above steps, then error out */
@@ -562,46 +617,64 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len,
 	 * anywhere in the good area.
 	 */
 	if (addr) {
-		addr = slice_find_area(mm, len, good_mask,
-				       psize, topdown, high_limit);
-		if (addr != -ENOMEM) {
-			slice_dbg(" found area at 0x%lx\n", addr);
-			return addr;
+		newaddr = slice_find_area(mm, len, &good_mask,
+					  psize, topdown, high_limit);
+		if (newaddr != -ENOMEM) {
+			slice_dbg(" found area at 0x%lx\n", newaddr);
+			goto return_addr;
 		}
 	}
 
 	/* Now let's see if we can find something in the existing slices
 	 * for that size plus free slices
 	 */
-	addr = slice_find_area(mm, len, potential_mask,
-			       psize, topdown, high_limit);
+	newaddr = slice_find_area(mm, len, &potential_mask,
+				  psize, topdown, high_limit);
 
 #ifdef CONFIG_PPC_64K_PAGES
-	if (addr == -ENOMEM && psize == MMU_PAGE_64K) {
+	if (newaddr == -ENOMEM && psize == MMU_PAGE_64K) {
 		/* retry the search with 4k-page slices included */
-		slice_or_mask(&potential_mask, &compat_mask);
-		addr = slice_find_area(mm, len, potential_mask,
-				       psize, topdown, high_limit);
+		slice_or_mask(&potential_mask, &potential_mask, compat_maskp);
+		newaddr = slice_find_area(mm, len, &potential_mask,
+					  psize, topdown, high_limit);
 	}
 #endif
 
-	if (addr == -ENOMEM)
+	if (newaddr == -ENOMEM)
 		return -ENOMEM;
 
-	slice_range_to_mask(addr, len, &mask);
-	slice_dbg(" found potential area at 0x%lx\n", addr);
-	slice_print_mask(" mask", mask);
+	slice_range_to_mask(newaddr, len, &potential_mask);
+	slice_dbg(" found potential area at 0x%lx\n", newaddr);
+	slice_print_mask(" mask", &potential_mask);
 
  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)) {
-		slice_convert(mm, mask, psize);
+	/*
+	 * Try to allocate the context before we do slice convert
+	 * so that we handle the context allocation failure gracefully.
+	 */
+	if (need_extra_context(mm, newaddr)) {
+		if (alloc_extended_context(mm, newaddr) < 0)
+			return -ENOMEM;
+	}
+
+	slice_andnot_mask(&potential_mask, &potential_mask, &good_mask);
+	if (compat_maskp && !fixed)
+		slice_andnot_mask(&potential_mask, &potential_mask, compat_maskp);
+	if (potential_mask.low_slices ||
+		(SLICE_NUM_HIGH &&
+		 !bitmap_empty(potential_mask.high_slices, SLICE_NUM_HIGH))) {
+		slice_convert(mm, &potential_mask, psize);
 		if (psize > MMU_PAGE_BASE)
 			on_each_cpu(slice_flush_segments, mm, 1);
 	}
-	return addr;
+	return newaddr;
 
+return_addr:
+	if (need_extra_context(mm, newaddr)) {
+		if (alloc_extended_context(mm, newaddr) < 0)
+			return -ENOMEM;
+	}
+	return newaddr;
 }
 EXPORT_SYMBOL_GPL(slice_get_unmapped_area);
 
@@ -627,94 +700,60 @@ 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;
 
-	/*
-	 * Radix doesn't use slice, but can get enabled along with MMU_SLICE
-	 */
-	if (radix_enabled()) {
-#ifdef CONFIG_PPC_64K_PAGES
-		return MMU_PAGE_64K;
-#else
-		return MMU_PAGE_4K;
-#endif
-	}
+	VM_BUG_ON(radix_enabled());
+
 	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);
 
-/*
- * This is called by hash_page when it needs to do a lazy conversion of
- * an address space from real 64K pages to combo 4K pages (typically
- * when hitting a non cacheable mapping on a processor or hypervisor
- * that won't allow them for 64K pages).
- *
- * This is also called in init_new_context() to change back the user
- * psize from whatever the parent context had it set to
- * N.B. This may be called before mm->context.id has been set.
- *
- * This function will only change the content of the {low,high)_slice_psize
- * masks, it will not flush SLBs as this shall be handled lazily by the
- * caller.
- */
-void slice_set_user_psize(struct mm_struct *mm, unsigned int psize)
+void slice_init_new_context_exec(struct mm_struct *mm)
 {
-	int index, mask_index;
-	unsigned char *hpsizes;
-	unsigned long flags, lpsizes;
-	unsigned int old_psize;
-	int i;
+	unsigned char *hpsizes, *lpsizes;
+	struct slice_mask *mask;
+	unsigned int psize = mmu_virtual_psize;
 
-	slice_dbg("slice_set_user_psize(mm=%p, psize=%d)\n", mm, psize);
+	slice_dbg("slice_init_new_context_exec(mm=%p)\n", mm);
 
-	VM_BUG_ON(radix_enabled());
-	spin_lock_irqsave(&slice_convert_lock, flags);
-
-	old_psize = mm->context.user_psize;
-	slice_dbg(" old_psize=%d\n", old_psize);
-	if (old_psize == psize)
-		goto bail;
+	/*
+	 * In the case of exec, use the default limit. In the
+	 * case of fork it is just inherited from the mm being
+	 * duplicated.
+	 */
+#ifdef CONFIG_PPC64
+	mm->context.slb_addr_limit = DEFAULT_MAP_WINDOW_USER64;
+#else
+	mm->context.slb_addr_limit = DEFAULT_MAP_WINDOW;
+#endif
 
 	mm->context.user_psize = psize;
-	wmb();
 
+	/*
+	 * Set all slice psizes to the default.
+	 */
 	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;
+	memset(lpsizes, (psize << 4) | psize, SLICE_NUM_LOW >> 1);
 
 	hpsizes = mm->context.high_slices_psize;
-	for (i = 0; i < SLICE_NUM_HIGH; i++) {
-		mask_index = i & 0x1;
-		index = i >> 1;
-		if (((hpsizes[index] >> (mask_index * 4)) & 0xf) == old_psize)
-			hpsizes[index] = (hpsizes[index] &
-					  ~(0xf << (mask_index * 4))) |
-				(((unsigned long)psize) << (mask_index * 4));
-	}
-
-
-
-
-	slice_dbg(" lsps=%lx, hsps=%lx\n",
-		  (unsigned long)mm->context.low_slices_psize,
-		  (unsigned long)mm->context.high_slices_psize);
+	memset(hpsizes, (psize << 4) | psize, SLICE_NUM_HIGH >> 1);
 
- bail:
-	spin_unlock_irqrestore(&slice_convert_lock, flags);
+	/*
+	 * Slice mask cache starts zeroed, fill the default size cache.
+	 */
+	mask = slice_mask_for_size(mm, psize);
+	mask->low_slices = ~0UL;
+	if (SLICE_NUM_HIGH)
+		bitmap_fill(mask->high_slices, SLICE_NUM_HIGH);
 }
 
 void slice_set_range_psize(struct mm_struct *mm, unsigned long start,
@@ -725,7 +764,7 @@ void slice_set_range_psize(struct mm_struct *mm, unsigned long start,
 	VM_BUG_ON(radix_enabled());
 
 	slice_range_to_mask(start, len, &mask);
-	slice_convert(mm, mask, psize);
+	slice_convert(mm, &mask, psize);
 }
 
 #ifdef CONFIG_HUGETLB_PAGE
@@ -748,33 +787,27 @@ void slice_set_range_psize(struct mm_struct *mm, unsigned long start,
  * for now as we only use slices with hugetlbfs enabled. This should
  * be fixed as the generic code gets fixed.
  */
-int is_hugepage_only_range(struct mm_struct *mm, unsigned long addr,
+int slice_is_hugepage_only_range(struct mm_struct *mm, unsigned long addr,
 			   unsigned long len)
 {
-	struct slice_mask mask, available;
+	const struct slice_mask *maskp;
 	unsigned int psize = mm->context.user_psize;
-	unsigned long high_limit = mm->context.slb_addr_limit;
 
-	if (radix_enabled())
-		return 0;
+	VM_BUG_ON(radix_enabled());
 
-	slice_range_to_mask(addr, len, &mask);
-	slice_mask_for_size(mm, psize, &available, high_limit);
+	maskp = slice_mask_for_size(mm, psize);
 #ifdef CONFIG_PPC_64K_PAGES
 	/* We need to account for 4k slices too */
 	if (psize == MMU_PAGE_64K) {
-		struct slice_mask compat_mask;
-		slice_mask_for_size(mm, MMU_PAGE_4K, &compat_mask, high_limit);
-		slice_or_mask(&available, &compat_mask);
+		const struct slice_mask *compat_maskp;
+		struct slice_mask available;
+
+		compat_maskp = slice_mask_for_size(mm, MMU_PAGE_4K);
+		slice_or_mask(&available, maskp, compat_maskp);
+		return !slice_check_range_fits(mm, &available, addr, len);
 	}
 #endif
 
-#if 0 /* too verbose */
-	slice_dbg("is_hugepage_only_range(mm=%p, addr=%lx, len=%lx)\n",
-		 mm, addr, len);
-	slice_print_mask(" mask", mask);
-	slice_print_mask(" available", available);
-#endif
-	return !slice_check_fit(mm, mask, available);
+	return !slice_check_range_fits(mm, maskp, addr, len);
 }
 #endif