Merge branch 'sparc64-Add-16GB-hugepage-support'

Nitin Gupta says:

====================
sparc64: Add 16GB hugepage support

SPARC architecture supports 16G hugepages but the kernel did not
support these. This patch series adds support for it and also cleanes
up some page walk/alloc functions.

Patch 1/3: Core changes needed to add 16G hugepage support: To map a
  single 16G hugepage, two PUD entries are used. Each PUD entry maps
  8G portion of a 16G page. This page table encoding scheme is same as
  that used for hugepages at PMD level (8M, 256M and 2G pages) where
  each PMD entry points successively to 8M regions within a page.  No
  page table entries below the PUD level are allocated for 16G
  hugepage since those are not required.

  TSB entries for a 16G page are created at every 4M boundary since
  the HUGE_TSB is used for these pages which is configured with page
  size of 4M.  When walking page tables (on a TSB miss), bits [32:22]
  are transferred from vaddr to PUD to resolve addresses at 4M
  boundary. The resolved address mapping is then stored in HUGE_TSB.

Patch 2/3: get_user_pages() etc. are used for direct IO. These
  functions were not aware of hugepages at the PUD level and would try
  to continue walking page tables beyond the PUD level. Since 16G
  hugepages have page tables allocated till PUD level only, these
  accesses would result in invalid access. This patch adds the case
  for PUD huge pages to these functions.

Patch 3/3: Patch 1 added the case of PUD entry being huge in page
  table walk and alloc functions. This new case further increased
  nesting in these functions and made them harder to follow. This
  patch flattens these functions for better readability.

Cc: sparclinux@vger.kernel.org

Changelog v5 vs v4:
 - Checking at PUD level for hugepage entry during page table walk is
   patched out if 16GB hugepages are not being used.
Changelog v4 vs v3:
 - Added cover letter (patch 0/4) for patch series.
Changelog v3 vs v2:
 - Fixed email headers so the subject shows up correctly.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

arch/sparc/include/asm/hugetlb.h

@@ -4,6 +4,13 @@
 #include <asm/page.h>
 #include <asm-generic/hugetlb.h>
 
+#ifdef CONFIG_HUGETLB_PAGE
+struct pud_huge_patch_entry {
+	unsigned int addr;
+	unsigned int insn;
+};
+extern struct pud_huge_patch_entry __pud_huge_patch, __pud_huge_patch_end;
+#endif
 
 void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 		     pte_t *ptep, pte_t pte);

arch/sparc/include/asm/page_64.h

@@ -17,6 +17,7 @@
 
 #define HPAGE_SHIFT		23
 #define REAL_HPAGE_SHIFT	22
+#define HPAGE_16GB_SHIFT	34
 #define HPAGE_2GB_SHIFT		31
 #define HPAGE_256MB_SHIFT	28
 #define HPAGE_64K_SHIFT		16
@@ -28,7 +29,7 @@
 #define HUGETLB_PAGE_ORDER	(HPAGE_SHIFT - PAGE_SHIFT)
 #define HAVE_ARCH_HUGETLB_UNMAPPED_AREA
 #define REAL_HPAGE_PER_HPAGE	(_AC(1,UL) << (HPAGE_SHIFT - REAL_HPAGE_SHIFT))
-#define HUGE_MAX_HSTATE		4
+#define HUGE_MAX_HSTATE		5
 #endif
 
 #ifndef __ASSEMBLY__

arch/sparc/include/asm/pgtable_64.h

@@ -414,6 +414,11 @@ static inline bool is_hugetlb_pmd(pmd_t pmd)
 	return !!(pmd_val(pmd) & _PAGE_PMD_HUGE);
 }
 
+static inline bool is_hugetlb_pud(pud_t pud)
+{
+	return !!(pud_val(pud) & _PAGE_PUD_HUGE);
+}
+
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 static inline pmd_t pmd_mkhuge(pmd_t pmd)
 {
@@ -687,6 +692,8 @@ static inline unsigned long pmd_write(pmd_t pmd)
 	return pte_write(pte);
 }
 
+#define pud_write(pud)	pte_write(__pte(pud_val(pud)))
+
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 static inline unsigned long pmd_dirty(pmd_t pmd)
 {
@@ -823,9 +830,18 @@ static inline unsigned long __pmd_page(pmd_t pmd)
 
 	return ((unsigned long) __va(pfn << PAGE_SHIFT));
 }
+
+static inline unsigned long pud_page_vaddr(pud_t pud)
+{
+	pte_t pte = __pte(pud_val(pud));
+	unsigned long pfn;
+
+	pfn = pte_pfn(pte);
+
+	return ((unsigned long) __va(pfn << PAGE_SHIFT));
+}
+
 #define pmd_page(pmd) 			virt_to_page((void *)__pmd_page(pmd))
-#define pud_page_vaddr(pud)		\
-	((unsigned long) __va(pud_val(pud)))
 #define pud_page(pud) 			virt_to_page((void *)pud_page_vaddr(pud))
 #define pmd_clear(pmdp)			(pmd_val(*(pmdp)) = 0UL)
 #define pud_present(pud)		(pud_val(pud) != 0U)

arch/sparc/include/asm/tsb.h

@@ -195,6 +195,41 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end;
 	 nop; \
 699:
 
+	/* PUD has been loaded into REG1, interpret the value, seeing
+	 * if it is a HUGE PUD or a normal one.  If it is not valid
+	 * then jump to FAIL_LABEL.  If it is a HUGE PUD, and it
+	 * translates to a valid PTE, branch to PTE_LABEL.
+	 *
+	 * We have to propagate bits [32:22] from the virtual address
+	 * to resolve at 4M granularity.
+	 */
+#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
+#define USER_PGTABLE_CHECK_PUD_HUGE(VADDR, REG1, REG2, FAIL_LABEL, PTE_LABEL) \
+700:	ba 700f;					\
+	 nop;						\
+	.section	.pud_huge_patch, "ax";		\
+	.word		700b;				\
+	nop;						\
+	.previous;					\
+	brz,pn		REG1, FAIL_LABEL;		\
+	 sethi		%uhi(_PAGE_PUD_HUGE), REG2;	\
+	sllx		REG2, 32, REG2;			\
+	andcc		REG1, REG2, %g0;		\
+	be,pt		%xcc, 700f;			\
+	 sethi		%hi(0x1ffc0000), REG2;		\
+	sllx		REG2, 1, REG2;			\
+	brgez,pn	REG1, FAIL_LABEL;		\
+	 andn		REG1, REG2, REG1;		\
+	and		VADDR, REG2, REG2;		\
+	brlz,pt		REG1, PTE_LABEL;		\
+	 or		REG1, REG2, REG1;		\
+700:
+#else
+#define USER_PGTABLE_CHECK_PUD_HUGE(VADDR, REG1, REG2, FAIL_LABEL, PTE_LABEL) \
+	brz,pn		REG1, FAIL_LABEL; \
+	 nop;
+#endif
+
 	/* PMD has been loaded into REG1, interpret the value, seeing
 	 * if it is a HUGE PMD or a normal one.  If it is not valid
 	 * then jump to FAIL_LABEL.  If it is a HUGE PMD, and it
@@ -242,6 +277,7 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end;
 	srlx		REG2, 64 - PAGE_SHIFT, REG2; \
 	andn		REG2, 0x7, REG2; \
 	ldxa		[REG1 + REG2] ASI_PHYS_USE_EC, REG1; \
+	USER_PGTABLE_CHECK_PUD_HUGE(VADDR, REG1, REG2, FAIL_LABEL, 800f) \
 	brz,pn		REG1, FAIL_LABEL; \
 	 sllx		VADDR, 64 - (PMD_SHIFT + PMD_BITS), REG2; \
 	srlx		REG2, 64 - PAGE_SHIFT, REG2; \

arch/sparc/kernel/tsb.S

@@ -117,7 +117,7 @@ tsb_miss_page_table_walk_sun4v_fastpath:
 	/* Valid PTE is now in %g5.  */
 
 #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
-	sethi		%uhi(_PAGE_PMD_HUGE), %g7
+	sethi		%uhi(_PAGE_PMD_HUGE | _PAGE_PUD_HUGE), %g7
 	sllx		%g7, 32, %g7
 
 	andcc		%g5, %g7, %g0

arch/sparc/kernel/vmlinux.lds.S

@@ -154,6 +154,11 @@ SECTIONS
 		*(.get_tick_patch)
 		__get_tick_patch_end = .;
 	}
+	.pud_huge_patch : {
+		__pud_huge_patch = .;
+		*(.pud_huge_patch)
+		__pud_huge_patch_end = .;
+	}
 	PERCPU_SECTION(SMP_CACHE_BYTES)
 
 #ifdef CONFIG_JUMP_LABEL

arch/sparc/mm/gup.c

@@ -103,6 +103,45 @@ static int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr,
 	return 1;
 }
 
+static int gup_huge_pud(pud_t *pudp, pud_t pud, unsigned long addr,
+			unsigned long end, int write, struct page **pages,
+			int *nr)
+{
+	struct page *head, *page;
+	int refs;
+
+	if (!(pud_val(pud) & _PAGE_VALID))
+		return 0;
+
+	if (write && !pud_write(pud))
+		return 0;
+
+	refs = 0;
+	page = pud_page(pud) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
+	head = compound_head(page);
+	do {
+		VM_BUG_ON(compound_head(page) != head);
+		pages[*nr] = page;
+		(*nr)++;
+		page++;
+		refs++;
+	} while (addr += PAGE_SIZE, addr != end);
+
+	if (!page_cache_add_speculative(head, refs)) {
+		*nr -= refs;
+		return 0;
+	}
+
+	if (unlikely(pud_val(pud) != pud_val(*pudp))) {
+		*nr -= refs;
+		while (refs--)
+			put_page(head);
+		return 0;
+	}
+
+	return 1;
+}
+
 static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
 		int write, struct page **pages, int *nr)
 {
@@ -141,7 +180,11 @@ static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end,
 		next = pud_addr_end(addr, end);
 		if (pud_none(pud))
 			return 0;
-		if (!gup_pmd_range(pud, addr, next, write, pages, nr))
+		if (unlikely(pud_large(pud))) {
+			if (!gup_huge_pud(pudp, pud, addr, next,
+					  write, pages, nr))
+				return 0;
+		} else if (!gup_pmd_range(pud, addr, next, write, pages, nr))
 			return 0;
 	} while (pudp++, addr = next, addr != end);
 

arch/sparc/mm/hugetlbpage.c

@@ -143,6 +143,10 @@ static pte_t sun4v_hugepage_shift_to_tte(pte_t entry, unsigned int shift)
 	pte_val(entry) = pte_val(entry) & ~_PAGE_SZALL_4V;
 
 	switch (shift) {
+	case HPAGE_16GB_SHIFT:
+		hugepage_size = _PAGE_SZ16GB_4V;
+		pte_val(entry) |= _PAGE_PUD_HUGE;
+		break;
 	case HPAGE_2GB_SHIFT:
 		hugepage_size = _PAGE_SZ2GB_4V;
 		pte_val(entry) |= _PAGE_PMD_HUGE;
@@ -187,6 +191,9 @@ static unsigned int sun4v_huge_tte_to_shift(pte_t entry)
 	unsigned int shift;
 
 	switch (tte_szbits) {
+	case _PAGE_SZ16GB_4V:
+		shift = HPAGE_16GB_SHIFT;
+		break;
 	case _PAGE_SZ2GB_4V:
 		shift = HPAGE_2GB_SHIFT;
 		break;
@@ -259,22 +266,19 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
 	pgd_t *pgd;
 	pud_t *pud;
 	pmd_t *pmd;
-	pte_t *pte = NULL;
 
 	pgd = pgd_offset(mm, addr);
 	pud = pud_alloc(mm, pgd, addr);
-	if (pud) {
-		pmd = pmd_alloc(mm, pud, addr);
-		if (!pmd)
-			return NULL;
-
-		if (sz >= PMD_SIZE)
-			pte = (pte_t *)pmd;
-		else
-			pte = pte_alloc_map(mm, pmd, addr);
-	}
-
-	return pte;
+	if (!pud)
+		return NULL;
+	if (sz >= PUD_SIZE)
+		return (pte_t *)pud;
+	pmd = pmd_alloc(mm, pud, addr);
+	if (!pmd)
+		return NULL;
+	if (sz >= PMD_SIZE)
+		return (pte_t *)pmd;
+	return pte_alloc_map(mm, pmd, addr);
 }
 
 pte_t *huge_pte_offset(struct mm_struct *mm,
@@ -283,34 +287,40 @@ pte_t *huge_pte_offset(struct mm_struct *mm,
 	pgd_t *pgd;
 	pud_t *pud;
 	pmd_t *pmd;
-	pte_t *pte = NULL;
 
 	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)) {
-				if (is_hugetlb_pmd(*pmd))
-					pte = (pte_t *)pmd;
-				else
-					pte = pte_offset_map(pmd, addr);
-			}
-		}
-	}
-
-	return pte;
+	if (pgd_none(*pgd))
+		return NULL;
+	pud = pud_offset(pgd, addr);
+	if (pud_none(*pud))
+		return NULL;
+	if (is_hugetlb_pud(*pud))
+		return (pte_t *)pud;
+	pmd = pmd_offset(pud, addr);
+	if (pmd_none(*pmd))
+		return NULL;
+	if (is_hugetlb_pmd(*pmd))
+		return (pte_t *)pmd;
+	return pte_offset_map(pmd, addr);
 }
 
 void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 		     pte_t *ptep, pte_t entry)
 {
-	unsigned int i, nptes, orig_shift, shift;
-	unsigned long size;
+	unsigned int nptes, orig_shift, shift;
+	unsigned long i, size;
 	pte_t orig;
 
 	size = huge_tte_to_size(entry);
-	shift = size >= HPAGE_SIZE ? PMD_SHIFT : PAGE_SHIFT;
+
+	shift = PAGE_SHIFT;
+	if (size >= PUD_SIZE)
+		shift = PUD_SHIFT;
+	else if (size >= PMD_SIZE)
+		shift = PMD_SHIFT;
+	else
+		shift = PAGE_SHIFT;
+
 	nptes = size >> shift;
 
 	if (!pte_present(*ptep) && pte_present(entry))
@@ -333,19 +343,23 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
 			      pte_t *ptep)
 {
-	unsigned int i, nptes, hugepage_shift;
+	unsigned int i, nptes, orig_shift, shift;
 	unsigned long size;
 	pte_t entry;
 
 	entry = *ptep;
 	size = huge_tte_to_size(entry);
-	if (size >= HPAGE_SIZE)
-		nptes = size >> PMD_SHIFT;
+
+	shift = PAGE_SHIFT;
+	if (size >= PUD_SIZE)
+		shift = PUD_SHIFT;
+	else if (size >= PMD_SIZE)
+		shift = PMD_SHIFT;
 	else
-		nptes = size >> PAGE_SHIFT;
+		shift = PAGE_SHIFT;
 
-	hugepage_shift = pte_none(entry) ? PAGE_SHIFT :
-		huge_tte_to_shift(entry);
+	nptes = size >> shift;
+	orig_shift = pte_none(entry) ? PAGE_SHIFT : huge_tte_to_shift(entry);
 
 	if (pte_present(entry))
 		mm->context.hugetlb_pte_count -= nptes;
@@ -354,11 +368,11 @@ pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
 	for (i = 0; i < nptes; i++)
 		ptep[i] = __pte(0UL);
 
-	maybe_tlb_batch_add(mm, addr, ptep, entry, 0, hugepage_shift);
+	maybe_tlb_batch_add(mm, addr, ptep, entry, 0, orig_shift);
 	/* An HPAGE_SIZE'ed page is composed of two REAL_HPAGE_SIZE'ed pages */
 	if (size == HPAGE_SIZE)
 		maybe_tlb_batch_add(mm, addr + REAL_HPAGE_SIZE, ptep, entry, 0,
-				    hugepage_shift);
+				    orig_shift);
 
 	return entry;
 }
@@ -371,7 +385,8 @@ int pmd_huge(pmd_t pmd)
 
 int pud_huge(pud_t pud)
 {
-	return 0;
+	return !pud_none(pud) &&
+		(pud_val(pud) & (_PAGE_VALID|_PAGE_PUD_HUGE)) != _PAGE_VALID;
 }
 
 static void hugetlb_free_pte_range(struct mmu_gather *tlb, pmd_t *pmd,
@@ -435,8 +450,11 @@ static void hugetlb_free_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
 		next = pud_addr_end(addr, end);
 		if (pud_none_or_clear_bad(pud))
 			continue;
-		hugetlb_free_pmd_range(tlb, pud, addr, next, floor,
-				       ceiling);
+		if (is_hugetlb_pud(*pud))
+			pud_clear(pud);
+		else
+			hugetlb_free_pmd_range(tlb, pud, addr, next, floor,
+					       ceiling);
 	} while (pud++, addr = next, addr != end);
 
 	start &= PGDIR_MASK;

arch/sparc/mm/init_64.c

@@ -325,6 +325,18 @@ static void __update_mmu_tsb_insert(struct mm_struct *mm, unsigned long tsb_inde
 }
 
 #ifdef CONFIG_HUGETLB_PAGE
+static void __init pud_huge_patch(void)
+{
+	struct pud_huge_patch_entry *p;
+	unsigned long addr;
+
+	p = &__pud_huge_patch;
+	addr = p->addr;
+	*(unsigned int *)addr = p->insn;
+
+	__asm__ __volatile__("flush %0" : : "r" (addr));
+}
+
 static int __init setup_hugepagesz(char *string)
 {
 	unsigned long long hugepage_size;
@@ -337,6 +349,11 @@ static int __init setup_hugepagesz(char *string)
 	hugepage_shift = ilog2(hugepage_size);
 
 	switch (hugepage_shift) {
+	case HPAGE_16GB_SHIFT:
+		hv_pgsz_mask = HV_PGSZ_MASK_16GB;
+		hv_pgsz_idx = HV_PGSZ_IDX_16GB;
+		pud_huge_patch();
+		break;
 	case HPAGE_2GB_SHIFT:
 		hv_pgsz_mask = HV_PGSZ_MASK_2GB;
 		hv_pgsz_idx = HV_PGSZ_IDX_2GB;
@@ -377,6 +394,7 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *
 {
 	struct mm_struct *mm;
 	unsigned long flags;
+	bool is_huge_tsb;
 	pte_t pte = *ptep;
 
 	if (tlb_type != hypervisor) {
@@ -394,15 +412,37 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *
 
 	spin_lock_irqsave(&mm->context.lock, flags);
 
+	is_huge_tsb = false;
 #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
-	if ((mm->context.hugetlb_pte_count || mm->context.thp_pte_count) &&
-	    is_hugetlb_pmd(__pmd(pte_val(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
+	if (mm->context.hugetlb_pte_count || mm->context.thp_pte_count) {
+		unsigned long hugepage_size = PAGE_SIZE;
+
+		if (is_vm_hugetlb_page(vma))
+			hugepage_size = huge_page_size(hstate_vma(vma));
+
+		if (hugepage_size >= PUD_SIZE) {
+			unsigned long mask = 0x1ffc00000UL;
+
+			/* Transfer bits [32:22] from address to resolve
+			 * at 4M granularity.
+			 */
+			pte_val(pte) &= ~mask;
+			pte_val(pte) |= (address & mask);
+		} else if (hugepage_size >= PMD_SIZE) {
+			/* We are fabricating 8MB pages using 4MB
+			 * real hw pages.
+			 */
+			pte_val(pte) |= (address & (1UL << REAL_HPAGE_SHIFT));
+		}
+
+		if (hugepage_size >= PMD_SIZE) {
+			__update_mmu_tsb_insert(mm, MM_TSB_HUGE,
+				REAL_HPAGE_SHIFT, address, pte_val(pte));
+			is_huge_tsb = true;
+		}
+	}
 #endif
+	if (!is_huge_tsb)
 		__update_mmu_tsb_insert(mm, MM_TSB_BASE, PAGE_SHIFT,
 					address, pte_val(pte));