#define HPAGE_SHIFT 23
#define REAL_HPAGE_SHIFT 22
-
+#define HPAGE_256MB_SHIFT 28
#define REAL_HPAGE_SIZE (_AC(1,UL) << REAL_HPAGE_SHIFT)
#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
#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 2
#endif
#ifndef __ASSEMBLY__
#define pgprot_noncached pgprot_noncached
#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
-static inline unsigned long __pte_huge_mask(void)
+extern pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma,
+ struct page *page, int writable);
+#define arch_make_huge_pte arch_make_huge_pte
+static inline unsigned long __pte_default_huge_mask(void)
{
unsigned long mask;
static inline pte_t pte_mkhuge(pte_t pte)
{
- return __pte(pte_val(pte) | _PAGE_PMD_HUGE | __pte_huge_mask());
+ return __pte(pte_val(pte) | __pte_default_huge_mask());
}
-static inline bool is_hugetlb_pte(pte_t pte)
+static inline bool is_default_hugetlb_pte(pte_t pte)
{
- return !!(pte_val(pte) & __pte_huge_mask());
+ unsigned long mask = __pte_default_huge_mask();
+
+ return (pte_val(pte) & mask) == mask;
}
static inline bool is_hugetlb_pmd(pmd_t pmd)
/* Actual page table PTE updates. */
void tlb_batch_add(struct mm_struct *mm, unsigned long vaddr,
- pte_t *ptep, pte_t orig, int fullmm);
+ pte_t *ptep, pte_t orig, int fullmm,
+ unsigned int hugepage_shift);
static void maybe_tlb_batch_add(struct mm_struct *mm, unsigned long vaddr,
- pte_t *ptep, pte_t orig, int fullmm)
+ pte_t *ptep, pte_t orig, int fullmm,
+ unsigned int hugepage_shift)
{
/* It is more efficient to let flush_tlb_kernel_range()
* handle init_mm tlb flushes.
* and SUN4V pte layout, so this inline test is fine.
*/
if (likely(mm != &init_mm) && pte_accessible(mm, orig))
- tlb_batch_add(mm, vaddr, ptep, orig, fullmm);
+ tlb_batch_add(mm, vaddr, ptep, orig, fullmm, hugepage_shift);
}
#define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR
pte_t orig = *ptep;
*ptep = pte;
- maybe_tlb_batch_add(mm, addr, ptep, orig, fullmm);
+ maybe_tlb_batch_add(mm, addr, ptep, orig, fullmm, PAGE_SHIFT);
}
#define set_pte_at(mm,addr,ptep,pte) \
#define TLB_BATCH_NR 192
struct tlb_batch {
- bool huge;
+ unsigned int hugepage_shift;
struct mm_struct *mm;
unsigned long tlb_nr;
unsigned long active;
void flush_tsb_kernel_range(unsigned long start, unsigned long end);
void flush_tsb_user(struct tlb_batch *tb);
-void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr, bool huge);
+void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr,
+ unsigned int hugepage_shift);
/* TLB flush operations. */
/* Valid PTE is now in %g5. */
#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
-661: sethi %uhi(_PAGE_SZALL_4U), %g7
+ sethi %uhi(_PAGE_PMD_HUGE), %g7
sllx %g7, 32, %g7
- .section .sun4v_2insn_patch, "ax"
- .word 661b
- mov _PAGE_SZALL_4V, %g7
- nop
- .previous
-
- and %g5, %g7, %g2
-
-661: sethi %uhi(_PAGE_SZHUGE_4U), %g7
- sllx %g7, 32, %g7
- .section .sun4v_2insn_patch, "ax"
- .word 661b
- mov _PAGE_SZHUGE_4V, %g7
- nop
- .previous
- cmp %g2, %g7
- bne,pt %xcc, 60f
+ andcc %g5, %g7, %g0
+ be,pt %xcc, 60f
nop
/* It is a huge page, use huge page TSB entry address we
unsigned long pgoff,
unsigned long flags)
{
+ struct hstate *h = hstate_file(filp);
unsigned long task_size = TASK_SIZE;
struct vm_unmapped_area_info info;
info.length = len;
info.low_limit = TASK_UNMAPPED_BASE;
info.high_limit = min(task_size, VA_EXCLUDE_START);
- info.align_mask = PAGE_MASK & ~HPAGE_MASK;
+ info.align_mask = PAGE_MASK & ~huge_page_mask(h);
info.align_offset = 0;
addr = vm_unmapped_area(&info);
const unsigned long pgoff,
const unsigned long flags)
{
+ struct hstate *h = hstate_file(filp);
struct mm_struct *mm = current->mm;
unsigned long addr = addr0;
struct vm_unmapped_area_info info;
info.length = len;
info.low_limit = PAGE_SIZE;
info.high_limit = mm->mmap_base;
- info.align_mask = PAGE_MASK & ~HPAGE_MASK;
+ info.align_mask = PAGE_MASK & ~huge_page_mask(h);
info.align_offset = 0;
addr = vm_unmapped_area(&info);
hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
unsigned long len, unsigned long pgoff, unsigned long flags)
{
+ struct hstate *h = hstate_file(file);
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma;
unsigned long task_size = TASK_SIZE;
if (test_thread_flag(TIF_32BIT))
task_size = STACK_TOP32;
- if (len & ~HPAGE_MASK)
+ if (len & ~huge_page_mask(h))
return -EINVAL;
if (len > task_size)
return -ENOMEM;
}
if (addr) {
- addr = ALIGN(addr, HPAGE_SIZE);
+ addr = ALIGN(addr, huge_page_size(h));
vma = find_vma(mm, addr);
if (task_size - len >= addr &&
(!vma || addr + len <= vma->vm_start))
pgoff, flags);
}
+static pte_t sun4u_hugepage_shift_to_tte(pte_t entry, unsigned int shift)
+{
+ return entry;
+}
+
+static pte_t sun4v_hugepage_shift_to_tte(pte_t entry, unsigned int shift)
+{
+ unsigned long hugepage_size = _PAGE_SZ4MB_4V;
+
+ pte_val(entry) = pte_val(entry) & ~_PAGE_SZALL_4V;
+
+ switch (shift) {
+ case HPAGE_256MB_SHIFT:
+ hugepage_size = _PAGE_SZ256MB_4V;
+ pte_val(entry) |= _PAGE_PMD_HUGE;
+ break;
+ case HPAGE_SHIFT:
+ pte_val(entry) |= _PAGE_PMD_HUGE;
+ break;
+ default:
+ WARN_ONCE(1, "unsupported hugepage shift=%u\n", shift);
+ }
+
+ pte_val(entry) = pte_val(entry) | hugepage_size;
+ return entry;
+}
+
+static pte_t hugepage_shift_to_tte(pte_t entry, unsigned int shift)
+{
+ if (tlb_type == hypervisor)
+ return sun4v_hugepage_shift_to_tte(entry, shift);
+ else
+ return sun4u_hugepage_shift_to_tte(entry, shift);
+}
+
+pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma,
+ struct page *page, int writeable)
+{
+ unsigned int shift = huge_page_shift(hstate_vma(vma));
+
+ return hugepage_shift_to_tte(entry, shift);
+}
+
+static unsigned int sun4v_huge_tte_to_shift(pte_t entry)
+{
+ unsigned long tte_szbits = pte_val(entry) & _PAGE_SZALL_4V;
+ unsigned int shift;
+
+ switch (tte_szbits) {
+ case _PAGE_SZ256MB_4V:
+ shift = HPAGE_256MB_SHIFT;
+ break;
+ case _PAGE_SZ4MB_4V:
+ shift = REAL_HPAGE_SHIFT;
+ break;
+ default:
+ shift = PAGE_SHIFT;
+ break;
+ }
+ return shift;
+}
+
+static unsigned int sun4u_huge_tte_to_shift(pte_t entry)
+{
+ unsigned long tte_szbits = pte_val(entry) & _PAGE_SZALL_4U;
+ unsigned int shift;
+
+ switch (tte_szbits) {
+ case _PAGE_SZ256MB_4U:
+ shift = HPAGE_256MB_SHIFT;
+ break;
+ case _PAGE_SZ4MB_4U:
+ shift = REAL_HPAGE_SHIFT;
+ break;
+ default:
+ shift = PAGE_SHIFT;
+ break;
+ }
+ return shift;
+}
+
+static unsigned int huge_tte_to_shift(pte_t entry)
+{
+ unsigned long shift;
+
+ if (tlb_type == hypervisor)
+ shift = sun4v_huge_tte_to_shift(entry);
+ else
+ shift = sun4u_huge_tte_to_shift(entry);
+
+ if (shift == PAGE_SHIFT)
+ WARN_ONCE(1, "tto_to_shift: invalid hugepage tte=0x%lx\n",
+ pte_val(entry));
+
+ return shift;
+}
+
+static unsigned long huge_tte_to_size(pte_t pte)
+{
+ unsigned long size = 1UL << huge_tte_to_shift(pte);
+
+ if (size == REAL_HPAGE_SIZE)
+ size = HPAGE_SIZE;
+ return size;
+}
+
pte_t *huge_pte_alloc(struct mm_struct *mm,
unsigned long addr, unsigned long sz)
{
void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, pte_t entry)
{
+ unsigned int i, nptes, hugepage_shift;
+ unsigned long size;
pte_t orig;
+ size = huge_tte_to_size(entry);
+ nptes = size >> PMD_SHIFT;
+
if (!pte_present(*ptep) && pte_present(entry))
- mm->context.hugetlb_pte_count++;
+ mm->context.hugetlb_pte_count += nptes;
- addr &= HPAGE_MASK;
+ addr &= ~(size - 1);
orig = *ptep;
- *ptep = entry;
+ hugepage_shift = pte_none(orig) ? PAGE_SIZE : huge_tte_to_shift(orig);
- /* Issue TLB flush at REAL_HPAGE_SIZE boundaries */
- maybe_tlb_batch_add(mm, addr, ptep, orig, 0);
- maybe_tlb_batch_add(mm, addr + REAL_HPAGE_SIZE, ptep, orig, 0);
+ for (i = 0; i < nptes; i++)
+ ptep[i] = __pte(pte_val(entry) + (i << PMD_SHIFT));
+
+ maybe_tlb_batch_add(mm, addr, ptep, orig, 0, hugepage_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, orig, 0,
+ hugepage_shift);
}
pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
pte_t *ptep)
{
+ unsigned int i, nptes, hugepage_shift;
+ unsigned long size;
pte_t entry;
entry = *ptep;
+ size = huge_tte_to_size(entry);
+ nptes = size >> PMD_SHIFT;
+ hugepage_shift = pte_none(entry) ? PAGE_SIZE : huge_tte_to_shift(entry);
+
if (pte_present(entry))
- mm->context.hugetlb_pte_count--;
+ mm->context.hugetlb_pte_count -= nptes;
- addr &= HPAGE_MASK;
- *ptep = __pte(0UL);
+ addr &= ~(size - 1);
+ for (i = 0; i < nptes; i++)
+ ptep[i] = __pte(0UL);
- /* Issue TLB flush at REAL_HPAGE_SIZE boundaries */
- maybe_tlb_batch_add(mm, addr, ptep, entry, 0);
- maybe_tlb_batch_add(mm, addr + REAL_HPAGE_SIZE, ptep, entry, 0);
+ maybe_tlb_batch_add(mm, addr, ptep, entry, 0, hugepage_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);
return entry;
}
tsb_insert(tsb, tag, tte);
}
+#ifdef CONFIG_HUGETLB_PAGE
+static int __init setup_hugepagesz(char *string)
+{
+ unsigned long long hugepage_size;
+ unsigned int hugepage_shift;
+ unsigned short hv_pgsz_idx;
+ unsigned int hv_pgsz_mask;
+ int rc = 0;
+
+ hugepage_size = memparse(string, &string);
+ hugepage_shift = ilog2(hugepage_size);
+
+ switch (hugepage_shift) {
+ case HPAGE_256MB_SHIFT:
+ hv_pgsz_mask = HV_PGSZ_MASK_256MB;
+ hv_pgsz_idx = HV_PGSZ_IDX_256MB;
+ break;
+ case HPAGE_SHIFT:
+ hv_pgsz_mask = HV_PGSZ_MASK_4MB;
+ hv_pgsz_idx = HV_PGSZ_IDX_4MB;
+ break;
+ default:
+ hv_pgsz_mask = 0;
+ }
+
+ if ((hv_pgsz_mask & cpu_pgsz_mask) == 0U) {
+ pr_warn("hugepagesz=%llu not supported by MMU.\n",
+ hugepage_size);
+ goto out;
+ }
+
+ hugetlb_add_hstate(hugepage_shift - PAGE_SHIFT);
+ rc = 1;
+
+out:
+ return rc;
+}
+__setup("hugepagesz=", setup_hugepagesz);
+#endif /* CONFIG_HUGETLB_PAGE */
+
void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep)
{
struct mm_struct *mm;
#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
if ((mm->context.hugetlb_pte_count || mm->context.thp_pte_count) &&
- is_hugetlb_pte(pte)) {
+ 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,
}
static void tlb_batch_add_one(struct mm_struct *mm, unsigned long vaddr,
- bool exec, bool huge)
+ bool exec, unsigned int hugepage_shift)
{
struct tlb_batch *tb = &get_cpu_var(tlb_batch);
unsigned long nr;
}
if (!tb->active) {
- flush_tsb_user_page(mm, vaddr, huge);
+ flush_tsb_user_page(mm, vaddr, hugepage_shift);
global_flush_tlb_page(mm, vaddr);
goto out;
}
if (nr == 0) {
tb->mm = mm;
- tb->huge = huge;
+ tb->hugepage_shift = hugepage_shift;
}
- if (tb->huge != huge) {
+ if (tb->hugepage_shift != hugepage_shift) {
flush_tlb_pending();
- tb->huge = huge;
+ tb->hugepage_shift = hugepage_shift;
nr = 0;
}
}
void tlb_batch_add(struct mm_struct *mm, unsigned long vaddr,
- pte_t *ptep, pte_t orig, int fullmm)
+ pte_t *ptep, pte_t orig, int fullmm,
+ unsigned int hugepage_shift)
{
- bool huge = is_hugetlb_pte(orig);
-
if (tlb_type != hypervisor &&
pte_dirty(orig)) {
unsigned long paddr, pfn = pte_pfn(orig);
no_cache_flush:
if (!fullmm)
- tlb_batch_add_one(mm, vaddr, pte_exec(orig), huge);
+ tlb_batch_add_one(mm, vaddr, pte_exec(orig), hugepage_shift);
}
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
__flush_tsb_one_entry(tsb, tb->vaddrs[i], hash_shift, nentries);
}
+#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
+static void __flush_huge_tsb_one_entry(unsigned long tsb, unsigned long v,
+ unsigned long hash_shift,
+ unsigned long nentries,
+ unsigned int hugepage_shift)
+{
+ unsigned int hpage_entries;
+ unsigned int i;
+
+ hpage_entries = 1 << (hugepage_shift - hash_shift);
+ for (i = 0; i < hpage_entries; i++)
+ __flush_tsb_one_entry(tsb, v + (i << hash_shift), hash_shift,
+ nentries);
+}
+
+static void __flush_huge_tsb_one(struct tlb_batch *tb, unsigned long hash_shift,
+ unsigned long tsb, unsigned long nentries,
+ unsigned int hugepage_shift)
+{
+ unsigned long i;
+
+ for (i = 0; i < tb->tlb_nr; i++)
+ __flush_huge_tsb_one_entry(tsb, tb->vaddrs[i], hash_shift,
+ nentries, hugepage_shift);
+}
+#endif
+
void flush_tsb_user(struct tlb_batch *tb)
{
struct mm_struct *mm = tb->mm;
spin_lock_irqsave(&mm->context.lock, flags);
- if (!tb->huge) {
+ if (tb->hugepage_shift == PAGE_SHIFT) {
base = (unsigned long) mm->context.tsb_block[MM_TSB_BASE].tsb;
nentries = mm->context.tsb_block[MM_TSB_BASE].tsb_nentries;
if (tlb_type == cheetah_plus || tlb_type == hypervisor)
__flush_tsb_one(tb, PAGE_SHIFT, base, nentries);
}
#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
- if (tb->huge && mm->context.tsb_block[MM_TSB_HUGE].tsb) {
+ else if (mm->context.tsb_block[MM_TSB_HUGE].tsb) {
base = (unsigned long) mm->context.tsb_block[MM_TSB_HUGE].tsb;
nentries = mm->context.tsb_block[MM_TSB_HUGE].tsb_nentries;
if (tlb_type == cheetah_plus || tlb_type == hypervisor)
base = __pa(base);
- __flush_tsb_one(tb, REAL_HPAGE_SHIFT, base, nentries);
+ __flush_huge_tsb_one(tb, REAL_HPAGE_SHIFT, base, nentries,
+ tb->hugepage_shift);
}
#endif
spin_unlock_irqrestore(&mm->context.lock, flags);
}
-void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr, bool huge)
+void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr,
+ unsigned int hugepage_shift)
{
unsigned long nentries, base, flags;
spin_lock_irqsave(&mm->context.lock, flags);
- if (!huge) {
+ if (hugepage_shift == PAGE_SHIFT) {
base = (unsigned long) mm->context.tsb_block[MM_TSB_BASE].tsb;
nentries = mm->context.tsb_block[MM_TSB_BASE].tsb_nentries;
if (tlb_type == cheetah_plus || tlb_type == hypervisor)
__flush_tsb_one_entry(base, vaddr, PAGE_SHIFT, nentries);
}
#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
- if (huge && mm->context.tsb_block[MM_TSB_HUGE].tsb) {
+ else if (mm->context.tsb_block[MM_TSB_HUGE].tsb) {
base = (unsigned long) mm->context.tsb_block[MM_TSB_HUGE].tsb;
nentries = mm->context.tsb_block[MM_TSB_HUGE].tsb_nentries;
if (tlb_type == cheetah_plus || tlb_type == hypervisor)
base = __pa(base);
- __flush_tsb_one_entry(base, vaddr, REAL_HPAGE_SHIFT, nentries);
+ __flush_huge_tsb_one_entry(base, vaddr, REAL_HPAGE_SHIFT,
+ nentries, hugepage_shift);
}
#endif
spin_unlock_irqrestore(&mm->context.lock, flags);