Merge branch 'booke-hugetlb' into next

arch/powerpc/configs/corenet32_smp_defconfig

···
 CONFIG_NTFS_FS=y
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
+CONFIG_HUGETLBFS=y
 CONFIG_JFFS2_FS=y
 CONFIG_CRAMFS=y
 CONFIG_NFS_FS=y

arch/powerpc/configs/corenet64_smp_defconfig

···
 # CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
+CONFIG_HUGETLBFS=y
 # CONFIG_MISC_FILESYSTEMS is not set
 CONFIG_PARTITION_ADVANCED=y
 CONFIG_MAC_PARTITION=y

arch/powerpc/configs/mpc85xx_defconfig

···
 CONFIG_NTFS_FS=y
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
+CONFIG_HUGETLBFS=y
 CONFIG_ADFS_FS=m
 CONFIG_AFFS_FS=m
 CONFIG_HFS_FS=m

arch/powerpc/configs/mpc85xx_smp_defconfig

···
 CONFIG_NTFS_FS=y
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
+CONFIG_HUGETLBFS=y
 CONFIG_ADFS_FS=m
 CONFIG_AFFS_FS=m
 CONFIG_HFS_FS=m

arch/powerpc/include/asm/hugetlb.h

···
 #include <asm/page.h>
 
 extern struct kmem_cache *hugepte_cache;
-extern void __init reserve_hugetlb_gpages(void);
 
 static inline pte_t *hugepd_page(hugepd_t hpd)
 {
···
 				    unsigned pdshift)
 {
 	/*
-	 * On 32-bit, we have multiple higher-level table entries that point to
-	 * the same hugepte.  Just use the first one since they're all
+	 * On FSL BookE, we have multiple higher-level table entries that
+	 * point to the same hugepte.  Just use the first one since they're all
 	 * identical.  So for that case, idx=0.
 	 */
 	unsigned long idx = 0;
 
 	pte_t *dir = hugepd_page(*hpdp);
-#ifdef CONFIG_PPC64
+#ifndef CONFIG_PPC_FSL_BOOK3E
 	idx = (addr & ((1UL << pdshift) - 1)) >> hugepd_shift(*hpdp);
 #endif
 
···
 }
 #endif
 
-void book3e_hugetlb_preload(struct mm_struct *mm, unsigned long ea, pte_t pte);
+void book3e_hugetlb_preload(struct vm_area_struct *vma, unsigned long ea,
+			    pte_t pte);
 void flush_hugetlb_page(struct vm_area_struct *vma, unsigned long vmaddr);
 
 void hugetlb_free_pgd_range(struct mmu_gather *tlb, unsigned long addr,
···
 					     unsigned long addr, pte_t *ptep,
 					     pte_t pte, int dirty)
 {
+#ifdef HUGETLB_NEED_PRELOAD
+	/*
+	 * The "return 1" forces a call of update_mmu_cache, which will write a
+	 * TLB entry.  Without this, platforms that don't do a write of the TLB
+	 * entry in the TLB miss handler asm will fault ad infinitum.
+	 */
+	ptep_set_access_flags(vma, addr, ptep, pte, dirty);
+	return 1;
+#else
 	return ptep_set_access_flags(vma, addr, ptep, pte, dirty);
+#endif
 }
 
 static inline pte_t huge_ptep_get(pte_t *ptep)
···
 }
 
 #else /* ! CONFIG_HUGETLB_PAGE */
-static inline void reserve_hugetlb_gpages(void)
-{
-	pr_err("Cannot reserve gpages without hugetlb enabled\n");
-}
 static inline void flush_hugetlb_page(struct vm_area_struct *vma,
 				      unsigned long vmaddr)
+{
+}
+#endif /* CONFIG_HUGETLB_PAGE */
+
+
+/*
+ * FSL Book3E platforms require special gpage handling - the gpages
+ * are reserved early in the boot process by memblock instead of via
+ * the .dts as on IBM platforms.
+ */
+#if defined(CONFIG_HUGETLB_PAGE) && defined(CONFIG_PPC_FSL_BOOK3E)
+extern void __init reserve_hugetlb_gpages(void);
+#else
+static inline void reserve_hugetlb_gpages(void)
 {
 }
 #endif

arch/powerpc/include/asm/mmu-book3e.h

···
 
 #ifdef CONFIG_PPC64
 extern unsigned long linear_map_top;
+
+/*
+ * 64-bit booke platforms don't load the tlb in the tlb miss handler code.
+ * HUGETLB_NEED_PRELOAD handles this - it causes huge_ptep_set_access_flags to
+ * return 1, indicating that the tlb requires preloading.
+ */
+#define HUGETLB_NEED_PRELOAD
 #endif
 
 #endif /* !__ASSEMBLY__ */

arch/powerpc/include/asm/page_64.h

···
 
 #ifdef CONFIG_HUGETLB_PAGE
 
+#ifdef CONFIG_PPC_MM_SLICES
 #define HAVE_ARCH_HUGETLB_UNMAPPED_AREA
+#endif
 
 #endif /* !CONFIG_HUGETLB_PAGE */
 

arch/powerpc/kernel/setup_64.c

···
 #include <linux/pci.h>
 #include <linux/lockdep.h>
 #include <linux/memblock.h>
+#include <linux/hugetlb.h>
+
 #include <asm/io.h>
 #include <asm/kdump.h>
 #include <asm/prom.h>
···
 #include <asm/mmu_context.h>
 #include <asm/code-patching.h>
 #include <asm/kvm_ppc.h>
+#include <asm/hugetlb.h>
 
 #include "setup.h"
 
···
 
 	/* Initialize the hash table or TLB handling */
 	early_init_mmu();
+
+	/*
+	 * Reserve any gigantic pages requested on the command line.
+	 * memblock needs to have been initialized by the time this is
+	 * called since this will reserve memory.
+	 */
+	reserve_hugetlb_gpages();
 
 	DBG(" <- early_setup()\n");
 }

arch/powerpc/mm/hugetlbpage-book3e.c

···
 	return found;
 }
 
-void book3e_hugetlb_preload(struct mm_struct *mm, unsigned long ea, pte_t pte)
+void book3e_hugetlb_preload(struct vm_area_struct *vma, unsigned long ea,
+			    pte_t pte)
 {
 	unsigned long mas1, mas2;
 	u64 mas7_3;
 	unsigned long psize, tsize, shift;
 	unsigned long flags;
+	struct mm_struct *mm;
 
 #ifdef CONFIG_PPC_FSL_BOOK3E
-	int index, lz, ncams;
-	struct vm_area_struct *vma;
+	int index, ncams;
 #endif
 
 	if (unlikely(is_kernel_addr(ea)))
 		return;
 
+	mm = vma->vm_mm;
+
 #ifdef CONFIG_PPC_MM_SLICES
-	psize = mmu_get_tsize(get_slice_psize(mm, ea));
-	tsize = mmu_get_psize(psize);
+	psize = get_slice_psize(mm, ea);
+	tsize = mmu_get_tsize(psize);
 	shift = mmu_psize_defs[psize].shift;
 #else
-	vma = find_vma(mm, ea);
-	psize = vma_mmu_pagesize(vma);	/* returns actual size in bytes */
-	asm (PPC_CNTLZL "%0,%1" : "=r" (lz) : "r" (psize));
-	shift = 31 - lz;
-	tsize = 21 - lz;
+	psize = vma_mmu_pagesize(vma);
+	shift = __ilog2(psize);
+	tsize = shift - 10;
 #endif
 
 	/*

arch/powerpc/mm/hugetlbpage.c

···
 
 /*
  * Tracks gpages after the device tree is scanned and before the
- * huge_boot_pages list is ready.  On 64-bit implementations, this is
- * just used to track 16G pages and so is a single array.  32-bit
- * implementations may have more than one gpage size due to limitations
- * of the memory allocators, so we need multiple arrays
+ * huge_boot_pages list is ready.  On non-Freescale implementations, this is
+ * just used to track 16G pages and so is a single array.  FSL-based
+ * implementations may have more than one gpage size, so we need multiple
+ * arrays
  */
-#ifdef CONFIG_PPC64
-#define MAX_NUMBER_GPAGES	1024
-static u64 gpage_freearray[MAX_NUMBER_GPAGES];
-static unsigned nr_gpages;
-#else
+#ifdef CONFIG_PPC_FSL_BOOK3E
 #define MAX_NUMBER_GPAGES	128
 struct psize_gpages {
 	u64 gpage_list[MAX_NUMBER_GPAGES];
 	unsigned int nr_gpages;
 };
 static struct psize_gpages gpage_freearray[MMU_PAGE_COUNT];
+#else
+#define MAX_NUMBER_GPAGES	1024
+static u64 gpage_freearray[MAX_NUMBER_GPAGES];
+static unsigned nr_gpages;
 #endif
 
 static inline int shift_to_mmu_psize(unsigned int shift)
···
 	struct kmem_cache *cachep;
 	pte_t *new;
 
-#ifdef CONFIG_PPC64
-	cachep = PGT_CACHE(pdshift - pshift);
-#else
+#ifdef CONFIG_PPC_FSL_BOOK3E
 	int i;
 	int num_hugepd = 1 << (pshift - pdshift);
 	cachep = hugepte_cache;
+#else
+	cachep = PGT_CACHE(pdshift - pshift);
 #endif
 
 	new = kmem_cache_zalloc(cachep, GFP_KERNEL|__GFP_REPEAT);
···
 		return -ENOMEM;
 
 	spin_lock(&mm->page_table_lock);
-#ifdef CONFIG_PPC64
-	if (!hugepd_none(*hpdp))
-		kmem_cache_free(cachep, new);
-	else
-		hpdp->pd = ((unsigned long)new & ~PD_HUGE) | pshift;
-#else
+#ifdef CONFIG_PPC_FSL_BOOK3E
 	/*
 	 * We have multiple higher-level entries that point to the same
 	 * actual pte location.  Fill in each as we go and backtrack on error.
···
 			hpdp->pd = 0;
 		kmem_cache_free(cachep, new);
 	}
+#else
+	if (!hugepd_none(*hpdp))
+		kmem_cache_free(cachep, new);
+	else
+		hpdp->pd = ((unsigned long)new & ~PD_HUGE) | pshift;
 #endif
 	spin_unlock(&mm->page_table_lock);
 	return 0;
 }
+
+/*
+ * These macros define how to determine which level of the page table holds
+ * the hpdp.
+ */
+#ifdef CONFIG_PPC_FSL_BOOK3E
+#define HUGEPD_PGD_SHIFT PGDIR_SHIFT
+#define HUGEPD_PUD_SHIFT PUD_SHIFT
+#else
+#define HUGEPD_PGD_SHIFT PUD_SHIFT
+#define HUGEPD_PUD_SHIFT PMD_SHIFT
+#endif
 
 pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz)
 {
···
 	addr &= ~(sz-1);
 
 	pg = pgd_offset(mm, addr);
-	if (pshift >= PUD_SHIFT) {
+
+	if (pshift >= HUGEPD_PGD_SHIFT) {
 		hpdp = (hugepd_t *)pg;
 	} else {
 		pdshift = PUD_SHIFT;
 		pu = pud_alloc(mm, pg, addr);
-		if (pshift >= PMD_SHIFT) {
+		if (pshift >= HUGEPD_PUD_SHIFT) {
 			hpdp = (hugepd_t *)pu;
 		} else {
 			pdshift = PMD_SHIFT;
···
 	return hugepte_offset(hpdp, addr, pdshift);
 }
 
-#ifdef CONFIG_PPC32
+#ifdef CONFIG_PPC_FSL_BOOK3E
 /* Build list of addresses of gigantic pages.  This function is used in early
  * boot before the buddy or bootmem allocator is setup.
  */
···
 	}
 }
 
-#else /* PPC64 */
+#else /* !PPC_FSL_BOOK3E */
 
 /* Build list of addresses of gigantic pages.  This function is used in early
  * boot before the buddy or bootmem allocator is setup.
···
 	return 0;
 }
 
-#ifdef CONFIG_PPC32
+#ifdef CONFIG_PPC_FSL_BOOK3E
 #define HUGEPD_FREELIST_SIZE \
 	((PAGE_SIZE - sizeof(struct hugepd_freelist)) / sizeof(pte_t))
 
···
 	unsigned long pdmask = ~((1UL << pdshift) - 1);
 	unsigned int num_hugepd = 1;
 
-#ifdef CONFIG_PPC64
-	unsigned int shift = hugepd_shift(*hpdp);
-#else
-	/* Note: On 32-bit the hpdp may be the first of several */
+#ifdef CONFIG_PPC_FSL_BOOK3E
+	/* Note: On fsl the hpdp may be the first of several */
 	num_hugepd = (1 << (hugepd_shift(*hpdp) - pdshift));
+#else
+	unsigned int shift = hugepd_shift(*hpdp);
 #endif
 
 	start &= pdmask;
···
 		hpdp->pd = 0;
 
 	tlb->need_flush = 1;
-#ifdef CONFIG_PPC64
-	pgtable_free_tlb(tlb, hugepte, pdshift - shift);
-#else
+
+#ifdef CONFIG_PPC_FSL_BOOK3E
 	hugepd_free(tlb, hugepte);
+#else
+	pgtable_free_tlb(tlb, hugepte, pdshift - shift);
 #endif
 }
 
···
 	unsigned long start;
 
 	start = addr;
-	pmd = pmd_offset(pud, addr);
 	do {
+		pmd = pmd_offset(pud, addr);
 		next = pmd_addr_end(addr, end);
 		if (pmd_none(*pmd))
 			continue;
+#ifdef CONFIG_PPC_FSL_BOOK3E
+		/*
+		 * Increment next by the size of the huge mapping since
+		 * there may be more than one entry at this level for a
+		 * single hugepage, but all of them point to
+		 * the same kmem cache that holds the hugepte.
+		 */
+		next = addr + (1 << hugepd_shift(*(hugepd_t *)pmd));
+#endif
 		free_hugepd_range(tlb, (hugepd_t *)pmd, PMD_SHIFT,
 				  addr, next, floor, ceiling);
-	} while (pmd++, addr = next, addr != end);
+	} while (addr = next, addr != end);
 
 	start &= PUD_MASK;
 	if (start < floor)
···
 	unsigned long start;
 
 	start = addr;
-	pud = pud_offset(pgd, addr);
 	do {
+		pud = pud_offset(pgd, addr);
 		next = pud_addr_end(addr, end);
 		if (!is_hugepd(pud)) {
 			if (pud_none_or_clear_bad(pud))
···
 			hugetlb_free_pmd_range(tlb, pud, addr, next, floor,
 					       ceiling);
 		} else {
+#ifdef CONFIG_PPC_FSL_BOOK3E
+			/*
+			 * Increment next by the size of the huge mapping since
+			 * there may be more than one entry at this level for a
+			 * single hugepage, but all of them point to
+			 * the same kmem cache that holds the hugepte.
+			 */
+			next = addr + (1 << hugepd_shift(*(hugepd_t *)pud));
+#endif
 			free_hugepd_range(tlb, (hugepd_t *)pud, PUD_SHIFT,
 					  addr, next, floor, ceiling);
 		}
-	} while (pud++, addr = next, addr != end);
+	} while (addr = next, addr != end);
 
 	start &= PGDIR_MASK;
 	if (start < floor)
···
 				continue;
 			hugetlb_free_pud_range(tlb, pgd, addr, next, floor, ceiling);
 		} else {
-#ifdef CONFIG_PPC32
+#ifdef CONFIG_PPC_FSL_BOOK3E
 			/*
 			 * Increment next by the size of the huge mapping since
-			 * on 32-bit there may be more than one entry at the pgd
-			 * level for a single hugepage, but all of them point to
-			 * the same kmem cache that holds the hugepte.
+			 * there may be more than one entry at the pgd level
+			 * for a single hugepage, but all of them point to the
+			 * same kmem cache that holds the hugepte.
 			 */
 			next = addr + (1 << hugepd_shift(*(hugepd_t *)pgd));
 #endif
···
 	return 1;
 }
 
+#ifdef CONFIG_PPC_MM_SLICES
 unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 					unsigned long len, unsigned long pgoff,
 					unsigned long flags)
 {
-#ifdef CONFIG_PPC_MM_SLICES
 	struct hstate *hstate = hstate_file(file);
 	int mmu_psize = shift_to_mmu_psize(huge_page_shift(hstate));
 
 	return slice_get_unmapped_area(addr, len, flags, mmu_psize, 1, 0);
-#else
-	return get_unmapped_area(file, addr, len, pgoff, flags);
-#endif
 }
+#endif
 
 unsigned long vma_mmu_pagesize(struct vm_area_struct *vma)
 {
···
 }
 __setup("hugepagesz=", hugepage_setup_sz);
 
-#ifdef CONFIG_FSL_BOOKE
+#ifdef CONFIG_PPC_FSL_BOOK3E
 struct kmem_cache *hugepte_cache;
 static int __init hugetlbpage_init(void)
 {

arch/powerpc/mm/mem.c

···
 #if (defined(CONFIG_PPC_BOOK3E_64) || defined(CONFIG_PPC_FSL_BOOK3E)) \
 	&& defined(CONFIG_HUGETLB_PAGE)
 	if (is_vm_hugetlb_page(vma))
-		book3e_hugetlb_preload(vma->vm_mm, address, *ptep);
+		book3e_hugetlb_preload(vma, address, *ptep);
 #endif
 }
 

arch/powerpc/mm/tlb_low_64e.S

···
 
 	srdi	r15,r16,60		/* get region */
 	rldicl.	r10,r16,64-PGTABLE_EADDR_SIZE,PGTABLE_EADDR_SIZE+4
-	bne-	dtlb_miss_fault_bolted
+	bne-	dtlb_miss_fault_bolted	/* Bail if fault addr is invalid */
 
 	rlwinm	r10,r11,32-19,27,27
 	rlwimi	r10,r11,32-16,19,19
-	cmpwi	r15,0
+	cmpwi	r15,0			/* user vs kernel check */
 	ori	r10,r10,_PAGE_PRESENT
 	oris	r11,r10,_PAGE_ACCESSED@h
 
···
 	rldicl	r15,r16,64-PGDIR_SHIFT+3,64-PGD_INDEX_SIZE-3
 	cmpldi	cr0,r14,0
 	clrrdi	r15,r15,3
-	beq	tlb_miss_fault_bolted
+	beq	tlb_miss_fault_bolted	/* No PGDIR, bail */
 
 BEGIN_MMU_FTR_SECTION
 	/* Set the TLB reservation and search for existing entry. Then load
 	 * the entry.
 	 */
 	PPC_TLBSRX_DOT(0,r16)
-	ldx	r14,r14,r15
-	beq	normal_tlb_miss_done
+	ldx	r14,r14,r15		/* grab pgd entry */
+	beq	normal_tlb_miss_done	/* tlb exists already, bail */
 MMU_FTR_SECTION_ELSE
-	ldx	r14,r14,r15
+	ldx	r14,r14,r15		/* grab pgd entry */
 ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_USE_TLBRSRV)
 
 #ifndef CONFIG_PPC_64K_PAGES
 	rldicl	r15,r16,64-PUD_SHIFT+3,64-PUD_INDEX_SIZE-3
 	clrrdi	r15,r15,3
-
-	cmpldi	cr0,r14,0
-	beq	tlb_miss_fault_bolted
-
-	ldx	r14,r14,r15
+	cmpdi	cr0,r14,0
+	bge	tlb_miss_fault_bolted	/* Bad pgd entry or hugepage; bail */
+	ldx	r14,r14,r15		/* grab pud entry */
 #endif /* CONFIG_PPC_64K_PAGES */
 
 	rldicl	r15,r16,64-PMD_SHIFT+3,64-PMD_INDEX_SIZE-3
 	clrrdi	r15,r15,3
-
-	cmpldi	cr0,r14,0
-	beq	tlb_miss_fault_bolted
-
-	ldx	r14,r14,r15
+	cmpdi	cr0,r14,0
+	bge	tlb_miss_fault_bolted
+	ldx	r14,r14,r15		/* Grab pmd entry */
 
 	rldicl	r15,r16,64-PAGE_SHIFT+3,64-PTE_INDEX_SIZE-3
 	clrrdi	r15,r15,3
-
-	cmpldi	cr0,r14,0
-	beq	tlb_miss_fault_bolted
-
-	ldx	r14,r14,r15
+	cmpdi	cr0,r14,0
+	bge	tlb_miss_fault_bolted
+	ldx	r14,r14,r15		/* Grab PTE, normal (!huge) page */
 
 	/* Check if required permissions are met */
 	andc.	r15,r11,r14

arch/powerpc/mm/tlb_nohash.c

···
  * indirect page table entries.
  */
 #ifdef CONFIG_PPC_BOOK3E_MMU
-#ifdef CONFIG_FSL_BOOKE
+#ifdef CONFIG_PPC_FSL_BOOK3E
 struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT] = {
 	[MMU_PAGE_4K] = {
 		.shift	= 12,

arch/powerpc/platforms/Kconfig.cputype

···
 config FSL_BOOKE
 	bool
 	depends on (E200 || E500) && PPC32
-	select SYS_SUPPORTS_HUGETLBFS if PHYS_64BIT
 	default y
 
 # this is for common code between PPC32 & PPC64 FSL BOOKE
···
 	bool
 	select FSL_EMB_PERFMON
 	select PPC_SMP_MUXED_IPI
+	select SYS_SUPPORTS_HUGETLBFS if PHYS_64BIT || PPC64
 	default y if FSL_BOOKE
 
 config PTE_64BIT
···
 
 config PPC_MM_SLICES
 	bool
-	default y if (PPC64 && HUGETLB_PAGE) || (PPC_STD_MMU_64 && PPC_64K_PAGES)
+	default y if (!PPC_FSL_BOOK3E && PPC64 && HUGETLB_PAGE) || (PPC_STD_MMU_64 && PPC_64K_PAGES)
 	default n
 
 config VIRT_CPU_ACCOUNTING