16 files changed, 134 insertions, 90 deletions

diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile
index 438dcd3fd0d1..9c8770b5f96f 100644
--- a/arch/powerpc/mm/Makefile
+++ b/arch/powerpc/mm/Makefile
@@ -24,6 +24,7 @@ obj-$(CONFIG_40x)		+= 40x_mmu.o
 obj-$(CONFIG_44x)		+= 44x_mmu.o
 obj-$(CONFIG_PPC_FSL_BOOK3E)	+= fsl_booke_mmu.o
 obj-$(CONFIG_NEED_MULTIPLE_NODES) += numa.o
+obj-$(CONFIG_PPC_SPLPAR)	+= vphn.o
 obj-$(CONFIG_PPC_MM_SLICES)	+= slice.o
 obj-y				+= hugetlbpage.o
 ifeq ($(CONFIG_HUGETLB_PAGE),y)
diff --git a/arch/powerpc/mm/dma-noncoherent.c b/arch/powerpc/mm/dma-noncoherent.c
index d85e86aac7fb..169aba446a74 100644
--- a/arch/powerpc/mm/dma-noncoherent.c
+++ b/arch/powerpc/mm/dma-noncoherent.c
@@ -228,7 +228,7 @@ __dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *handle, gfp_t
 		do {
 			SetPageReserved(page);
 			map_page(vaddr, page_to_phys(page),
-				 pgprot_noncached(PAGE_KERNEL));
+				 pgprot_val(pgprot_noncached(PAGE_KERNEL)));
 			page++;
 			vaddr += PAGE_SIZE;
 		} while (size -= PAGE_SIZE);
diff --git a/arch/powerpc/mm/fsl_booke_mmu.c b/arch/powerpc/mm/fsl_booke_mmu.c
index b46912fee7cd..9c90e66cffb6 100644
--- a/arch/powerpc/mm/fsl_booke_mmu.c
+++ b/arch/powerpc/mm/fsl_booke_mmu.c
@@ -181,7 +181,7 @@ static unsigned long map_mem_in_cams_addr(phys_addr_t phys, unsigned long virt,
 		unsigned long cam_sz;
 
 		cam_sz = calc_cam_sz(ram, virt, phys);
-		settlbcam(i, virt, phys, cam_sz, PAGE_KERNEL_X, 0);
+		settlbcam(i, virt, phys, cam_sz, pgprot_val(PAGE_KERNEL_X), 0);
 
 		ram -= cam_sz;
 		amount_mapped += cam_sz;
diff --git a/arch/powerpc/mm/hugepage-hash64.c b/arch/powerpc/mm/hugepage-hash64.c
index 86686514ae13..43dafb9d6a46 100644
--- a/arch/powerpc/mm/hugepage-hash64.c
+++ b/arch/powerpc/mm/hugepage-hash64.c
@@ -33,7 +33,7 @@ int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid,
 	 * atomically mark the linux large page PMD busy and dirty
 	 */
 	do {
-		pmd_t pmd = ACCESS_ONCE(*pmdp);
+		pmd_t pmd = READ_ONCE(*pmdp);
 
 		old_pmd = pmd_val(pmd);
 		/* If PMD busy, retry the access */
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 7e408bfc7948..fa9d5c238d22 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -964,7 +964,7 @@ pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, unsigned *shift
 		*shift = 0;
 
 	pgdp = pgdir + pgd_index(ea);
-	pgd  = ACCESS_ONCE(*pgdp);
+	pgd  = READ_ONCE(*pgdp);
 	/*
 	 * Always operate on the local stack value. This make sure the
 	 * value don't get updated by a parallel THP split/collapse,
@@ -1045,7 +1045,7 @@ int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr,
 	if (pte_end < end)
 		end = pte_end;
 
-	pte = ACCESS_ONCE(*ptep);
+	pte = READ_ONCE(*ptep);
 	mask = _PAGE_PRESENT | _PAGE_USER;
 	if (write)
 		mask |= _PAGE_RW;
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index 10471f9bb63f..d747dd7bc90b 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -132,6 +132,7 @@ void pgtable_cache_add(unsigned shift, void (*ctor)(void *))
 	align = max_t(unsigned long, align, minalign);
 	name = kasprintf(GFP_KERNEL, "pgtable-2^%d", shift);
 	new = kmem_cache_create(name, table_size, align, 0, ctor);
+	kfree(name);
 	pgtable_cache[shift - 1] = new;
 	pr_debug("Allocated pgtable cache for order %d\n", shift);
 }
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index b7285a5870f8..45fda71feb27 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -61,7 +61,6 @@
 #define CPU_FTR_NOEXECUTE	0
 #endif
 
-int mem_init_done;
 unsigned long long memory_limit;
 
 #ifdef CONFIG_HIGHMEM
@@ -377,8 +376,6 @@ void __init mem_init(void)
 	pr_info("  * 0x%08lx..0x%08lx  : vmalloc & ioremap\n",
 		VMALLOC_START, VMALLOC_END);
 #endif /* CONFIG_PPC32 */
-
-	mem_init_done = 1;
 }
 
 void free_initmem(void)
diff --git a/arch/powerpc/mm/mmap.c b/arch/powerpc/mm/mmap.c
index cb8bdbe4972f..0f0502e12f6c 100644
--- a/arch/powerpc/mm/mmap.c
+++ b/arch/powerpc/mm/mmap.c
@@ -53,21 +53,20 @@ static inline int mmap_is_legacy(void)
 	return sysctl_legacy_va_layout;
 }
 
-static unsigned long mmap_rnd(void)
+unsigned long arch_mmap_rnd(void)
 {
-	unsigned long rnd = 0;
+	unsigned long rnd;
+
+	/* 8MB for 32bit, 1GB for 64bit */
+	if (is_32bit_task())
+		rnd = (unsigned long)get_random_int() % (1<<(23-PAGE_SHIFT));
+	else
+		rnd = (unsigned long)get_random_int() % (1<<(30-PAGE_SHIFT));
 
-	if (current->flags & PF_RANDOMIZE) {
-		/* 8MB for 32bit, 1GB for 64bit */
-		if (is_32bit_task())
-			rnd = (long)(get_random_int() % (1<<(23-PAGE_SHIFT)));
-		else
-			rnd = (long)(get_random_int() % (1<<(30-PAGE_SHIFT)));
-	}
 	return rnd << PAGE_SHIFT;
 }
 
-static inline unsigned long mmap_base(void)
+static inline unsigned long mmap_base(unsigned long rnd)
 {
 	unsigned long gap = rlimit(RLIMIT_STACK);
 
@@ -76,7 +75,7 @@ static inline unsigned long mmap_base(void)
 	else if (gap > MAX_GAP)
 		gap = MAX_GAP;
 
-	return PAGE_ALIGN(TASK_SIZE - gap - mmap_rnd());
+	return PAGE_ALIGN(TASK_SIZE - gap - rnd);
 }
 
 /*
@@ -85,6 +84,11 @@ static inline unsigned long mmap_base(void)
  */
 void arch_pick_mmap_layout(struct mm_struct *mm)
 {
+	unsigned long random_factor = 0UL;
+
+	if (current->flags & PF_RANDOMIZE)
+		random_factor = arch_mmap_rnd();
+
 	/*
 	 * Fall back to the standard layout if the personality
 	 * bit is set, or if the expected stack growth is unlimited:
@@ -93,7 +97,7 @@ void arch_pick_mmap_layout(struct mm_struct *mm)
 		mm->mmap_base = TASK_UNMAPPED_BASE;
 		mm->get_unmapped_area = arch_get_unmapped_area;
 	} else {
-		mm->mmap_base = mmap_base();
+		mm->mmap_base = mmap_base(random_factor);
 		mm->get_unmapped_area = arch_get_unmapped_area_topdown;
 	}
 }
diff --git a/arch/powerpc/mm/mmu_decl.h b/arch/powerpc/mm/mmu_decl.h
index 78c45f392f5b..085b66b10891 100644
--- a/arch/powerpc/mm/mmu_decl.h
+++ b/arch/powerpc/mm/mmu_decl.h
@@ -96,7 +96,7 @@ extern void _tlbia(void);
 extern void mapin_ram(void);
 extern int map_page(unsigned long va, phys_addr_t pa, int flags);
 extern void setbat(int index, unsigned long virt, phys_addr_t phys,
-		   unsigned int size, int flags);
+		   unsigned int size, pgprot_t prot);
 
 extern int __map_without_bats;
 extern int __allow_ioremap_reserved;
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 0257a7d659ef..5e80621d9324 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -958,6 +958,13 @@ void __init initmem_init(void)
 
 	memblock_dump_all();
 
+	/*
+	 * Reduce the possible NUMA nodes to the online NUMA nodes,
+	 * since we do not support node hotplug. This ensures that  we
+	 * lower the maximum NUMA node ID to what is actually present.
+	 */
+	nodes_and(node_possible_map, node_possible_map, node_online_map);
+
 	for_each_online_node(nid) {
 		unsigned long start_pfn, end_pfn;
 
@@ -1177,6 +1184,9 @@ u64 memory_hotplug_max(void)
 
 /* Virtual Processor Home Node (VPHN) support */
 #ifdef CONFIG_PPC_SPLPAR
+
+#include "vphn.h"
+
 struct topology_update_data {
 	struct topology_update_data *next;
 	unsigned int cpu;
@@ -1248,55 +1258,6 @@ static int update_cpu_associativity_changes_mask(void)
 }
 
 /*
- * 6 64-bit registers unpacked into 12 32-bit associativity values. To form
- * the complete property we have to add the length in the first cell.
- */
-#define VPHN_ASSOC_BUFSIZE (6*sizeof(u64)/sizeof(u32) + 1)
-
-/*
- * Convert the associativity domain numbers returned from the hypervisor
- * to the sequence they would appear in the ibm,associativity property.
- */
-static int vphn_unpack_associativity(const long *packed, __be32 *unpacked)
-{
-	int i, nr_assoc_doms = 0;
-	const __be16 *field = (const __be16 *) packed;
-
-#define VPHN_FIELD_UNUSED	(0xffff)
-#define VPHN_FIELD_MSB		(0x8000)
-#define VPHN_FIELD_MASK		(~VPHN_FIELD_MSB)
-
-	for (i = 1; i < VPHN_ASSOC_BUFSIZE; i++) {
-		if (be16_to_cpup(field) == VPHN_FIELD_UNUSED) {
-			/* All significant fields processed, and remaining
-			 * fields contain the reserved value of all 1's.
-			 * Just store them.
-			 */
-			unpacked[i] = *((__be32 *)field);
-			field += 2;
-		} else if (be16_to_cpup(field) & VPHN_FIELD_MSB) {
-			/* Data is in the lower 15 bits of this field */
-			unpacked[i] = cpu_to_be32(
-				be16_to_cpup(field) & VPHN_FIELD_MASK);
-			field++;
-			nr_assoc_doms++;
-		} else {
-			/* Data is in the lower 15 bits of this field
-			 * concatenated with the next 16 bit field
-			 */
-			unpacked[i] = *((__be32 *)field);
-			field += 2;
-			nr_assoc_doms++;
-		}
-	}
-
-	/* The first cell contains the length of the property */
-	unpacked[0] = cpu_to_be32(nr_assoc_doms);
-
-	return nr_assoc_doms;
-}
-
-/*
  * Retrieve the new associativity information for a virtual processor's
  * home node.
  */
@@ -1306,11 +1267,8 @@ static long hcall_vphn(unsigned long cpu, __be32 *associativity)
 	long retbuf[PLPAR_HCALL9_BUFSIZE] = {0};
 	u64 flags = 1;
 	int hwcpu = get_hard_smp_processor_id(cpu);
-	int i;
 
 	rc = plpar_hcall9(H_HOME_NODE_ASSOCIATIVITY, retbuf, flags, hwcpu);
-	for (i = 0; i < 6; i++)
-		retbuf[i] = cpu_to_be64(retbuf[i]);
 	vphn_unpack_associativity(retbuf, associativity);
 
 	return rc;
diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index 03b1a3b0fbd5..7692d1bb1bc6 100644
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -54,9 +54,6 @@ extern char etext[], _stext[];
 #ifdef HAVE_BATS
 extern phys_addr_t v_mapped_by_bats(unsigned long va);
 extern unsigned long p_mapped_by_bats(phys_addr_t pa);
-void setbat(int index, unsigned long virt, phys_addr_t phys,
-	    unsigned int size, int flags);
-
 #else /* !HAVE_BATS */
 #define v_mapped_by_bats(x)	(0UL)
 #define p_mapped_by_bats(x)	(0UL)
@@ -110,9 +107,8 @@ void pgd_free(struct mm_struct *mm, pgd_t *pgd)
 __init_refok pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
 {
 	pte_t *pte;
-	extern int mem_init_done;
 
-	if (mem_init_done) {
+	if (slab_is_available()) {
 		pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
 	} else {
 		pte = __va(memblock_alloc(PAGE_SIZE, PAGE_SIZE));
@@ -192,7 +188,7 @@ __ioremap_caller(phys_addr_t addr, unsigned long size, unsigned long flags,
 
 	/* Make sure we have the base flags */
 	if ((flags & _PAGE_PRESENT) == 0)
-		flags |= PAGE_KERNEL;
+		flags |= pgprot_val(PAGE_KERNEL);
 
 	/* Non-cacheable page cannot be coherent */
 	if (flags & _PAGE_NO_CACHE)
@@ -219,9 +215,9 @@ __ioremap_caller(phys_addr_t addr, unsigned long size, unsigned long flags,
 	 * Don't allow anybody to remap normal RAM that we're using.
 	 * mem_init() sets high_memory so only do the check after that.
 	 */
-	if (mem_init_done && (p < virt_to_phys(high_memory)) &&
+	if (slab_is_available() && (p < virt_to_phys(high_memory)) &&
 	    !(__allow_ioremap_reserved && memblock_is_region_reserved(p, size))) {
-		printk("__ioremap(): phys addr 0x%llx is RAM lr %pf\n",
+		printk("__ioremap(): phys addr 0x%llx is RAM lr %ps\n",
 		       (unsigned long long)p, __builtin_return_address(0));
 		return NULL;
 	}
@@ -247,7 +243,7 @@ __ioremap_caller(phys_addr_t addr, unsigned long size, unsigned long flags,
 	if ((v = p_mapped_by_tlbcam(p)))
 		goto out;
 
-	if (mem_init_done) {
+	if (slab_is_available()) {
 		struct vm_struct *area;
 		area = get_vm_area_caller(size, VM_IOREMAP, caller);
 		if (area == 0)
@@ -266,7 +262,7 @@ __ioremap_caller(phys_addr_t addr, unsigned long size, unsigned long flags,
 	for (i = 0; i < size && err == 0; i += PAGE_SIZE)
 		err = map_page(v+i, p+i, flags);
 	if (err) {
-		if (mem_init_done)
+		if (slab_is_available())
 			vunmap((void *)v);
 		return NULL;
 	}
@@ -327,7 +323,7 @@ void __init __mapin_ram_chunk(unsigned long offset, unsigned long top)
 	p = memstart_addr + s;
 	for (; s < top; s += PAGE_SIZE) {
 		ktext = ((char *) v >= _stext && (char *) v < etext);
-		f = ktext ? PAGE_KERNEL_TEXT : PAGE_KERNEL;
+		f = ktext ? pgprot_val(PAGE_KERNEL_TEXT) : pgprot_val(PAGE_KERNEL);
 		map_page(v, p, f);
 #ifdef CONFIG_PPC_STD_MMU_32
 		if (ktext)
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index 6957cc1ca0a7..59daa5eeec25 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -231,7 +231,7 @@ void __iomem * __ioremap_caller(phys_addr_t addr, unsigned long size,
 	if ((size == 0) || (paligned == 0))
 		return NULL;
 
-	if (mem_init_done) {
+	if (slab_is_available()) {
 		struct vm_struct *area;
 
 		area = __get_vm_area_caller(size, VM_IOREMAP,
@@ -315,7 +315,7 @@ void __iounmap(volatile void __iomem *token)
 {
 	void *addr;
 
-	if (!mem_init_done)
+	if (!slab_is_available())
 		return;
 	
 	addr = (void *) ((unsigned long __force)
@@ -723,7 +723,7 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 	assert_spin_locked(&mm->page_table_lock);
 	WARN_ON(!pmd_trans_huge(pmd));
 #endif
-	trace_hugepage_set_pmd(addr, pmd);
+	trace_hugepage_set_pmd(addr, pmd_val(pmd));
 	return set_pte_at(mm, addr, pmdp_ptep(pmdp), pmd_pte(pmd));
 }
 
diff --git a/arch/powerpc/mm/ppc_mmu_32.c b/arch/powerpc/mm/ppc_mmu_32.c
index 5029dc19b517..6b2f3e457171 100644
--- a/arch/powerpc/mm/ppc_mmu_32.c
+++ b/arch/powerpc/mm/ppc_mmu_32.c
@@ -113,11 +113,12 @@ unsigned long __init mmu_mapin_ram(unsigned long top)
  * of 2 between 128k and 256M.
  */
 void __init setbat(int index, unsigned long virt, phys_addr_t phys,
-		   unsigned int size, int flags)
+		   unsigned int size, pgprot_t prot)
 {
 	unsigned int bl;
 	int wimgxpp;
 	struct ppc_bat *bat = BATS[index];
+	unsigned long flags = pgprot_val(prot);
 
 	if ((flags & _PAGE_NO_CACHE) ||
 	    (cpu_has_feature(CPU_FTR_NEED_COHERENT) == 0))
@@ -224,7 +225,7 @@ void __init MMU_init_hw(void)
 	 */
 	if ( ppc_md.progress ) ppc_md.progress("hash:find piece", 0x322);
 	Hash = __va(memblock_alloc(Hash_size, Hash_size));
-	cacheable_memzero(Hash, Hash_size);
+	memset(Hash, 0, Hash_size);
 	_SDR1 = __pa(Hash) | SDR1_LOW_BITS;
 
 	Hash_end = (struct hash_pte *) ((unsigned long)Hash + Hash_size);
diff --git a/arch/powerpc/mm/tlb_hash64.c b/arch/powerpc/mm/tlb_hash64.c
index d2a94b85dbc2..c522969f012d 100644
--- a/arch/powerpc/mm/tlb_hash64.c
+++ b/arch/powerpc/mm/tlb_hash64.c
@@ -216,7 +216,7 @@ void __flush_hash_table_range(struct mm_struct *mm, unsigned long start,
 			continue;
 		pte = pte_val(*ptep);
 		if (hugepage_shift)
-			trace_hugepage_invalidate(start, pte_val(pte));
+			trace_hugepage_invalidate(start, pte);
 		if (!(pte & _PAGE_HASHPTE))
 			continue;
 		if (unlikely(hugepage_shift && pmd_trans_huge(*(pmd_t *)pte)))
diff --git a/arch/powerpc/mm/vphn.c b/arch/powerpc/mm/vphn.c
new file mode 100644
index 000000000000..5f8ef50e5c66
--- /dev/null
+++ b/arch/powerpc/mm/vphn.c
@@ -0,0 +1,70 @@
+#include <asm/byteorder.h>
+#include "vphn.h"
+
+/*
+ * The associativity domain numbers are returned from the hypervisor as a
+ * stream of mixed 16-bit and 32-bit fields. The stream is terminated by the
+ * special value of "all ones" (aka. 0xffff) and its size may not exceed 48
+ * bytes.
+ *
+ *    --- 16-bit fields -->
+ *  _________________________
+ *  |  0  |  1  |  2  |  3  |   be_packed[0]
+ *  ------+-----+-----+------
+ *  _________________________
+ *  |  4  |  5  |  6  |  7  |   be_packed[1]
+ *  -------------------------
+ *            ...
+ *  _________________________
+ *  | 20  | 21  | 22  | 23  |   be_packed[5]
+ *  -------------------------
+ *
+ * Convert to the sequence they would appear in the ibm,associativity property.
+ */
+int vphn_unpack_associativity(const long *packed, __be32 *unpacked)
+{
+	__be64 be_packed[VPHN_REGISTER_COUNT];
+	int i, nr_assoc_doms = 0;
+	const __be16 *field = (const __be16 *) be_packed;
+	u16 last = 0;
+	bool is_32bit = false;
+
+#define VPHN_FIELD_UNUSED	(0xffff)
+#define VPHN_FIELD_MSB		(0x8000)
+#define VPHN_FIELD_MASK		(~VPHN_FIELD_MSB)
+
+	/* Let's fix the values returned by plpar_hcall9() */
+	for (i = 0; i < VPHN_REGISTER_COUNT; i++)
+		be_packed[i] = cpu_to_be64(packed[i]);
+
+	for (i = 1; i < VPHN_ASSOC_BUFSIZE; i++) {
+		u16 new = be16_to_cpup(field++);
+
+		if (is_32bit) {
+			/* Let's concatenate the 16 bits of this field to the
+			 * 15 lower bits of the previous field
+			 */
+			unpacked[++nr_assoc_doms] =
+				cpu_to_be32(last << 16 | new);
+			is_32bit = false;
+		} else if (new == VPHN_FIELD_UNUSED)
+			/* This is the list terminator */
+			break;
+		else if (new & VPHN_FIELD_MSB) {
+			/* Data is in the lower 15 bits of this field */
+			unpacked[++nr_assoc_doms] =
+				cpu_to_be32(new & VPHN_FIELD_MASK);
+		} else {
+			/* Data is in the lower 15 bits of this field
+			 * concatenated with the next 16 bit field
+			 */
+			last = new;
+			is_32bit = true;
+		}
+	}
+
+	/* The first cell contains the length of the property */
+	unpacked[0] = cpu_to_be32(nr_assoc_doms);
+
+	return nr_assoc_doms;
+}
diff --git a/arch/powerpc/mm/vphn.h b/arch/powerpc/mm/vphn.h
new file mode 100644
index 000000000000..fe8b7805b78f
--- /dev/null
+++ b/arch/powerpc/mm/vphn.h
@@ -0,0 +1,16 @@
+#ifndef _ARCH_POWERPC_MM_VPHN_H_
+#define _ARCH_POWERPC_MM_VPHN_H_
+
+/* The H_HOME_NODE_ASSOCIATIVITY h_call returns 6 64-bit registers.
+ */
+#define VPHN_REGISTER_COUNT 6
+
+/*
+ * 6 64-bit registers unpacked into up to 24 be32 associativity values. To
+ * form the complete property we have to add the length in the first cell.
+ */
+#define VPHN_ASSOC_BUFSIZE (VPHN_REGISTER_COUNT*sizeof(u64)/sizeof(u16) + 1)
+
+extern int vphn_unpack_associativity(const long *packed, __be32 *unpacked);
+
+#endif