sparc64: Add 16GB hugepage support

Adds support for 16GB hugepage size. To use this page size
use kernel parameters as:

default_hugepagesz=16G hugepagesz=16G hugepages=10

Testing:

Tested with the stream benchmark which allocates 48G of
arrays backed by 16G hugepages and does RW operation on
them in parallel.

Orabug: 25362942

Cc: Anthony Yznaga <anthony.yznaga@oracle.com>
Reviewed-by: Bob Picco <bob.picco@oracle.com>
Signed-off-by: Nitin Gupta <nitin.m.gupta@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 100 insertions, 28 deletions

diff --git a/arch/sparc/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c
index 28ee8d8ffa07..7acb84db952c 100644
--- a/arch/sparc/mm/hugetlbpage.c
+++ b/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;
@@ -263,7 +270,12 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
 
 	pgd = pgd_offset(mm, addr);
 	pud = pud_alloc(mm, pgd, addr);
-	if (pud) {
+	if (!pud)
+		return NULL;
+
+	if (sz >= PUD_SIZE)
+		pte = (pte_t *)pud;
+	else {
 		pmd = pmd_alloc(mm, pud, addr);
 		if (!pmd)
 			return NULL;
@@ -289,12 +301,16 @@ pte_t *huge_pte_offset(struct mm_struct *mm,
 	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);
+			if (is_hugetlb_pud(*pud))
+				pte = (pte_t *)pud;
+			else {
+				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);
+				}
 			}
 		}
 	}
@@ -305,12 +321,20 @@ pte_t *huge_pte_offset(struct mm_struct *mm,
 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 +357,23 @@ 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 +382,11 @@ 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 +399,8 @@ 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 +464,11 @@ 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;
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index afa0099f3748..b2ba410b26f4 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -348,6 +348,18 @@ static int __init hugetlbpage_init(void)
 
 arch_initcall(hugetlbpage_init);
 
+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;
@@ -360,6 +372,11 @@ 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;
@@ -400,6 +417,7 @@ 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) {
@@ -417,15 +435,37 @@ 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));