6 files changed, 177 insertions, 96 deletions

diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c
index b6c559cbd..4714061d6 100644
--- a/arch/sparc/mm/fault_32.c
+++ b/arch/sparc/mm/fault_32.c
@@ -241,7 +241,7 @@ good_area:
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.
 	 */
-	fault = handle_mm_fault(mm, vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags);
 
 	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
 		return;
@@ -411,7 +411,7 @@ good_area:
 		if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
 			goto bad_area;
 	}
-	switch (handle_mm_fault(mm, vma, address, flags)) {
+	switch (handle_mm_fault(vma, address, flags)) {
 	case VM_FAULT_SIGBUS:
 	case VM_FAULT_OOM:
 		goto do_sigbus;
diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c
index cb841a33d..3f291d8c5 100644
--- a/arch/sparc/mm/fault_64.c
+++ b/arch/sparc/mm/fault_64.c
@@ -111,8 +111,8 @@ static unsigned int get_user_insn(unsigned long tpc)
 	if (pmd_none(*pmdp) || unlikely(pmd_bad(*pmdp)))
 		goto out_irq_enable;
 
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-	if (pmd_trans_huge(*pmdp)) {
+#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
+	if (is_hugetlb_pmd(*pmdp)) {
 		pa  = pmd_pfn(*pmdp) << PAGE_SHIFT;
 		pa += tpc & ~HPAGE_MASK;
 
@@ -436,7 +436,7 @@ good_area:
 			goto bad_area;
 	}
 
-	fault = handle_mm_fault(mm, vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags);
 
 	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
 		goto exit_exception;
@@ -476,14 +476,15 @@ good_area:
 	up_read(&mm->mmap_sem);
 
 	mm_rss = get_mm_rss(mm);
-#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
-	mm_rss -= (mm->context.huge_pte_count * (HPAGE_SIZE / PAGE_SIZE));
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE)
+	mm_rss -= (mm->context.thp_pte_count * (HPAGE_SIZE / PAGE_SIZE));
 #endif
 	if (unlikely(mm_rss >
 		     mm->context.tsb_block[MM_TSB_BASE].tsb_rss_limit))
 		tsb_grow(mm, MM_TSB_BASE, mm_rss);
 #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
-	mm_rss = mm->context.huge_pte_count;
+	mm_rss = mm->context.hugetlb_pte_count + mm->context.thp_pte_count;
+	mm_rss *= REAL_HPAGE_PER_HPAGE;
 	if (unlikely(mm_rss >
 		     mm->context.tsb_block[MM_TSB_HUGE].tsb_rss_limit)) {
 		if (mm->context.tsb_block[MM_TSB_HUGE].tsb)
diff --git a/arch/sparc/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c
index ba52e6466..988acc8b1 100644
--- a/arch/sparc/mm/hugetlbpage.c
+++ b/arch/sparc/mm/hugetlbpage.c
@@ -12,6 +12,7 @@
 
 #include <asm/mman.h>
 #include <asm/pgalloc.h>
+#include <asm/pgtable.h>
 #include <asm/tlb.h>
 #include <asm/tlbflush.h>
 #include <asm/cacheflush.h>
@@ -131,23 +132,13 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
 {
 	pgd_t *pgd;
 	pud_t *pud;
-	pmd_t *pmd;
 	pte_t *pte = NULL;
 
-	/* We must align the address, because our caller will run
-	 * set_huge_pte_at() on whatever we return, which writes out
-	 * all of the sub-ptes for the hugepage range.  So we have
-	 * to give it the first such sub-pte.
-	 */
-	addr &= HPAGE_MASK;
-
 	pgd = pgd_offset(mm, addr);
 	pud = pud_alloc(mm, pgd, addr);
-	if (pud) {
-		pmd = pmd_alloc(mm, pud, addr);
-		if (pmd)
-			pte = pte_alloc_map(mm, pmd, addr);
-	}
+	if (pud)
+		pte = (pte_t *)pmd_alloc(mm, pud, addr);
+
 	return pte;
 }
 
@@ -155,19 +146,13 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
 {
 	pgd_t *pgd;
 	pud_t *pud;
-	pmd_t *pmd;
 	pte_t *pte = NULL;
 
-	addr &= HPAGE_MASK;
-
 	pgd = pgd_offset(mm, addr);
 	if (!pgd_none(*pgd)) {
 		pud = pud_offset(pgd, addr);
-		if (!pud_none(*pud)) {
-			pmd = pmd_offset(pud, addr);
-			if (!pmd_none(*pmd))
-				pte = pte_offset_map(pmd, addr);
-		}
+		if (!pud_none(*pud))
+			pte = (pte_t *)pmd_offset(pud, addr);
 	}
 	return pte;
 }
@@ -175,70 +160,143 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
 void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 		     pte_t *ptep, pte_t entry)
 {
-	int i;
-	pte_t orig[2];
-	unsigned long nptes;
+	pte_t orig;
 
 	if (!pte_present(*ptep) && pte_present(entry))
-		mm->context.huge_pte_count++;
+		mm->context.hugetlb_pte_count++;
 
 	addr &= HPAGE_MASK;
-
-	nptes = 1 << HUGETLB_PAGE_ORDER;
-	orig[0] = *ptep;
-	orig[1] = *(ptep + nptes / 2);
-	for (i = 0; i < nptes; i++) {
-		*ptep = entry;
-		ptep++;
-		addr += PAGE_SIZE;
-		pte_val(entry) += PAGE_SIZE;
-	}
+	orig = *ptep;
+	*ptep = entry;
 
 	/* Issue TLB flush at REAL_HPAGE_SIZE boundaries */
-	addr -= REAL_HPAGE_SIZE;
-	ptep -= nptes / 2;
-	maybe_tlb_batch_add(mm, addr, ptep, orig[1], 0);
-	addr -= REAL_HPAGE_SIZE;
-	ptep -= nptes / 2;
-	maybe_tlb_batch_add(mm, addr, ptep, orig[0], 0);
+	maybe_tlb_batch_add(mm, addr, ptep, orig, 0);
+	maybe_tlb_batch_add(mm, addr + REAL_HPAGE_SIZE, ptep, orig, 0);
 }
 
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
 			      pte_t *ptep)
 {
 	pte_t entry;
-	int i;
-	unsigned long nptes;
 
 	entry = *ptep;
 	if (pte_present(entry))
-		mm->context.huge_pte_count--;
+		mm->context.hugetlb_pte_count--;
 
 	addr &= HPAGE_MASK;
-	nptes = 1 << HUGETLB_PAGE_ORDER;
-	for (i = 0; i < nptes; i++) {
-		*ptep = __pte(0UL);
-		addr += PAGE_SIZE;
-		ptep++;
-	}
+	*ptep = __pte(0UL);
 
 	/* Issue TLB flush at REAL_HPAGE_SIZE boundaries */
-	addr -= REAL_HPAGE_SIZE;
-	ptep -= nptes / 2;
-	maybe_tlb_batch_add(mm, addr, ptep, entry, 0);
-	addr -= REAL_HPAGE_SIZE;
-	ptep -= nptes / 2;
 	maybe_tlb_batch_add(mm, addr, ptep, entry, 0);
+	maybe_tlb_batch_add(mm, addr + REAL_HPAGE_SIZE, ptep, entry, 0);
 
 	return entry;
 }
 
 int pmd_huge(pmd_t pmd)
 {
-	return 0;
+	return !pmd_none(pmd) &&
+		(pmd_val(pmd) & (_PAGE_VALID|_PAGE_PMD_HUGE)) != _PAGE_VALID;
 }
 
 int pud_huge(pud_t pud)
 {
 	return 0;
 }
+
+static void hugetlb_free_pte_range(struct mmu_gather *tlb, pmd_t *pmd,
+			   unsigned long addr)
+{
+	pgtable_t token = pmd_pgtable(*pmd);
+
+	pmd_clear(pmd);
+	pte_free_tlb(tlb, token, addr);
+	atomic_long_dec(&tlb->mm->nr_ptes);
+}
+
+static void hugetlb_free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
+				   unsigned long addr, unsigned long end,
+				   unsigned long floor, unsigned long ceiling)
+{
+	pmd_t *pmd;
+	unsigned long next;
+	unsigned long start;
+
+	start = addr;
+	pmd = pmd_offset(pud, addr);
+	do {
+		next = pmd_addr_end(addr, end);
+		if (pmd_none(*pmd))
+			continue;
+		if (is_hugetlb_pmd(*pmd))
+			pmd_clear(pmd);
+		else
+			hugetlb_free_pte_range(tlb, pmd, addr);
+	} while (pmd++, addr = next, addr != end);
+
+	start &= PUD_MASK;
+	if (start < floor)
+		return;
+	if (ceiling) {
+		ceiling &= PUD_MASK;
+		if (!ceiling)
+			return;
+	}
+	if (end - 1 > ceiling - 1)
+		return;
+
+	pmd = pmd_offset(pud, start);
+	pud_clear(pud);
+	pmd_free_tlb(tlb, pmd, start);
+	mm_dec_nr_pmds(tlb->mm);
+}
+
+static void hugetlb_free_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
+				   unsigned long addr, unsigned long end,
+				   unsigned long floor, unsigned long ceiling)
+{
+	pud_t *pud;
+	unsigned long next;
+	unsigned long start;
+
+	start = addr;
+	pud = pud_offset(pgd, addr);
+	do {
+		next = pud_addr_end(addr, end);
+		if (pud_none_or_clear_bad(pud))
+			continue;
+		hugetlb_free_pmd_range(tlb, pud, addr, next, floor,
+				       ceiling);
+	} while (pud++, addr = next, addr != end);
+
+	start &= PGDIR_MASK;
+	if (start < floor)
+		return;
+	if (ceiling) {
+		ceiling &= PGDIR_MASK;
+		if (!ceiling)
+			return;
+	}
+	if (end - 1 > ceiling - 1)
+		return;
+
+	pud = pud_offset(pgd, start);
+	pgd_clear(pgd);
+	pud_free_tlb(tlb, pud, start);
+}
+
+void hugetlb_free_pgd_range(struct mmu_gather *tlb,
+			    unsigned long addr, unsigned long end,
+			    unsigned long floor, unsigned long ceiling)
+{
+	pgd_t *pgd;
+	unsigned long next;
+
+	pgd = pgd_offset(tlb->mm, addr);
+	do {
+		next = pgd_addr_end(addr, end);
+		if (pgd_none_or_clear_bad(pgd))
+			continue;
+		hugetlb_free_pud_range(tlb, pgd, addr, next, floor, ceiling);
+	} while (pgd++, addr = next, addr != end);
+}
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index aec508e37..7ac6b62fb 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -346,10 +346,13 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *
 	spin_lock_irqsave(&mm->context.lock, flags);
 
 #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
-	if (mm->context.huge_pte_count && is_hugetlb_pte(pte))
+	if ((mm->context.hugetlb_pte_count || mm->context.thp_pte_count) &&
+	    is_hugetlb_pte(pte)) {
+		/* We are fabricating 8MB pages using 4MB real hw pages.  */
+		pte_val(pte) |= (address & (1UL << REAL_HPAGE_SHIFT));
 		__update_mmu_tsb_insert(mm, MM_TSB_HUGE, REAL_HPAGE_SHIFT,
 					address, pte_val(pte));
-	else
+	} else
 #endif
 		__update_mmu_tsb_insert(mm, MM_TSB_BASE, PAGE_SHIFT,
 					address, pte_val(pte));
@@ -1157,7 +1160,7 @@ int __node_distance(int from, int to)
 	return numa_latency[from][to];
 }
 
-static int find_best_numa_node_for_mlgroup(struct mdesc_mlgroup *grp)
+static int __init find_best_numa_node_for_mlgroup(struct mdesc_mlgroup *grp)
 {
 	int i;
 
@@ -1170,8 +1173,8 @@ static int find_best_numa_node_for_mlgroup(struct mdesc_mlgroup *grp)
 	return i;
 }
 
-static void find_numa_latencies_for_group(struct mdesc_handle *md, u64 grp,
-					  int index)
+static void __init find_numa_latencies_for_group(struct mdesc_handle *md,
+						 u64 grp, int index)
 {
 	u64 arc;
 
@@ -2078,7 +2081,6 @@ void __init paging_init(void)
 {
 	unsigned long end_pfn, shift, phys_base;
 	unsigned long real_end, i;
-	int node;
 
 	setup_page_offset();
 
@@ -2247,21 +2249,6 @@ void __init paging_init(void)
 	/* Setup bootmem... */
 	last_valid_pfn = end_pfn = bootmem_init(phys_base);
 
-	/* Once the OF device tree and MDESC have been setup, we know
-	 * the list of possible cpus.  Therefore we can allocate the
-	 * IRQ stacks.
-	 */
-	for_each_possible_cpu(i) {
-		node = cpu_to_node(i);
-
-		softirq_stack[i] = __alloc_bootmem_node(NODE_DATA(node),
-							THREAD_SIZE,
-							THREAD_SIZE, 0);
-		hardirq_stack[i] = __alloc_bootmem_node(NODE_DATA(node),
-							THREAD_SIZE,
-							THREAD_SIZE, 0);
-	}
-
 	kernel_physical_mapping_init();
 
 	{
diff --git a/arch/sparc/mm/tlb.c b/arch/sparc/mm/tlb.c
index f81cd9736..c56a195c9 100644
--- a/arch/sparc/mm/tlb.c
+++ b/arch/sparc/mm/tlb.c
@@ -174,10 +174,25 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 		return;
 
 	if ((pmd_val(pmd) ^ pmd_val(orig)) & _PAGE_PMD_HUGE) {
-		if (pmd_val(pmd) & _PAGE_PMD_HUGE)
-			mm->context.huge_pte_count++;
-		else
-			mm->context.huge_pte_count--;
+		/*
+		 * Note that this routine only sets pmds for THP pages.
+		 * Hugetlb pages are handled elsewhere.  We need to check
+		 * for huge zero page.  Huge zero pages are like hugetlb
+		 * pages in that there is no RSS, but there is the need
+		 * for TSB entries.  So, huge zero page counts go into
+		 * hugetlb_pte_count.
+		 */
+		if (pmd_val(pmd) & _PAGE_PMD_HUGE) {
+			if (is_huge_zero_page(pmd_page(pmd)))
+				mm->context.hugetlb_pte_count++;
+			else
+				mm->context.thp_pte_count++;
+		} else {
+			if (is_huge_zero_page(pmd_page(orig)))
+				mm->context.hugetlb_pte_count--;
+			else
+				mm->context.thp_pte_count--;
+		}
 
 		/* Do not try to allocate the TSB hash table if we
 		 * don't have one already.  We have various locks held
@@ -204,6 +219,9 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 	}
 }
 
+/*
+ * This routine is only called when splitting a THP
+ */
 void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
 		     pmd_t *pmdp)
 {
@@ -213,6 +231,15 @@ void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
 
 	set_pmd_at(vma->vm_mm, address, pmdp, entry);
 	flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
+
+	/*
+	 * set_pmd_at() will not be called in a way to decrement
+	 * thp_pte_count when splitting a THP, so do it now.
+	 * Sanity check pmd before doing the actual decrement.
+	 */
+	if ((pmd_val(entry) & _PAGE_PMD_HUGE) &&
+	    !is_huge_zero_page(pmd_page(entry)))
+		(vma->vm_mm)->context.thp_pte_count--;
 }
 
 void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c
index a0604a493..f2b77112e 100644
--- a/arch/sparc/mm/tsb.c
+++ b/arch/sparc/mm/tsb.c
@@ -469,8 +469,10 @@ retry_tsb_alloc:
 
 int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
 {
+	unsigned long mm_rss = get_mm_rss(mm);
 #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
-	unsigned long huge_pte_count;
+	unsigned long saved_hugetlb_pte_count;
+	unsigned long saved_thp_pte_count;
 #endif
 	unsigned int i;
 
@@ -479,12 +481,16 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
 	mm->context.sparc64_ctx_val = 0UL;
 
 #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
-	/* We reset it to zero because the fork() page copying
+	/* We reset them to zero because the fork() page copying
 	 * will re-increment the counters as the parent PTEs are
 	 * copied into the child address space.
 	 */
-	huge_pte_count = mm->context.huge_pte_count;
-	mm->context.huge_pte_count = 0;
+	saved_hugetlb_pte_count = mm->context.hugetlb_pte_count;
+	saved_thp_pte_count = mm->context.thp_pte_count;
+	mm->context.hugetlb_pte_count = 0;
+	mm->context.thp_pte_count = 0;
+
+	mm_rss -= saved_thp_pte_count * (HPAGE_SIZE / PAGE_SIZE);
 #endif
 
 	/* copy_mm() copies over the parent's mm_struct before calling
@@ -497,11 +503,13 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
 	/* If this is fork, inherit the parent's TSB size.  We would
 	 * grow it to that size on the first page fault anyways.
 	 */
-	tsb_grow(mm, MM_TSB_BASE, get_mm_rss(mm));
+	tsb_grow(mm, MM_TSB_BASE, mm_rss);
 
 #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
-	if (unlikely(huge_pte_count))
-		tsb_grow(mm, MM_TSB_HUGE, huge_pte_count);
+	if (unlikely(saved_hugetlb_pte_count + saved_thp_pte_count))
+		tsb_grow(mm, MM_TSB_HUGE,
+			 (saved_hugetlb_pte_count + saved_thp_pte_count) *
+			 REAL_HPAGE_PER_HPAGE);
 #endif
 
 	if (unlikely(!mm->context.tsb_block[MM_TSB_BASE].tsb))