aboutsummaryrefslogtreecommitdiff
path: root/arch/sparc
diff options
context:
space:
mode:
Diffstat (limited to 'arch/sparc')
-rw-r--r--arch/sparc/include/asm/atomic_32.h13
-rw-r--r--arch/sparc/include/asm/atomic_64.h16
-rw-r--r--arch/sparc/include/asm/hugetlb.h12
-rw-r--r--arch/sparc/include/asm/mmu_64.h3
-rw-r--r--arch/sparc/include/asm/pgtable_64.h7
-rw-r--r--arch/sparc/include/asm/spinlock_32.h7
-rw-r--r--arch/sparc/include/asm/spinlock_64.h10
-rw-r--r--arch/sparc/include/asm/tsb.h2
-rw-r--r--arch/sparc/kernel/dtlb_prot.S4
-rw-r--r--arch/sparc/kernel/irq_32.c4
-rw-r--r--arch/sparc/kernel/ktlb.S12
-rw-r--r--arch/sparc/kernel/tsb.S12
-rw-r--r--arch/sparc/lib/atomic32.c29
-rw-r--r--arch/sparc/lib/atomic_64.S61
-rw-r--r--arch/sparc/lib/ksyms.c17
-rw-r--r--arch/sparc/mm/fault_32.c4
-rw-r--r--arch/sparc/mm/fault_64.c12
-rw-r--r--arch/sparc/mm/hugetlbpage.c170
-rw-r--r--arch/sparc/mm/init_64.c7
-rw-r--r--arch/sparc/mm/tlb.c4
-rw-r--r--arch/sparc/mm/tsb.c14
21 files changed, 290 insertions, 130 deletions
diff --git a/arch/sparc/include/asm/atomic_32.h b/arch/sparc/include/asm/atomic_32.h
index 7dcbebbcaec6..ee3f11c43cda 100644
--- a/arch/sparc/include/asm/atomic_32.h
+++ b/arch/sparc/include/asm/atomic_32.h
@@ -20,9 +20,10 @@
#define ATOMIC_INIT(i) { (i) }
int atomic_add_return(int, atomic_t *);
-void atomic_and(int, atomic_t *);
-void atomic_or(int, atomic_t *);
-void atomic_xor(int, atomic_t *);
+int atomic_fetch_add(int, atomic_t *);
+int atomic_fetch_and(int, atomic_t *);
+int atomic_fetch_or(int, atomic_t *);
+int atomic_fetch_xor(int, atomic_t *);
int atomic_cmpxchg(atomic_t *, int, int);
int atomic_xchg(atomic_t *, int);
int __atomic_add_unless(atomic_t *, int, int);
@@ -35,7 +36,13 @@ void atomic_set(atomic_t *, int);
#define atomic_inc(v) ((void)atomic_add_return( 1, (v)))
#define atomic_dec(v) ((void)atomic_add_return( -1, (v)))
+#define atomic_and(i, v) ((void)atomic_fetch_and((i), (v)))
+#define atomic_or(i, v) ((void)atomic_fetch_or((i), (v)))
+#define atomic_xor(i, v) ((void)atomic_fetch_xor((i), (v)))
+
#define atomic_sub_return(i, v) (atomic_add_return(-(int)(i), (v)))
+#define atomic_fetch_sub(i, v) (atomic_fetch_add (-(int)(i), (v)))
+
#define atomic_inc_return(v) (atomic_add_return( 1, (v)))
#define atomic_dec_return(v) (atomic_add_return( -1, (v)))
diff --git a/arch/sparc/include/asm/atomic_64.h b/arch/sparc/include/asm/atomic_64.h
index f2fbf9e16faf..24827a3f733a 100644
--- a/arch/sparc/include/asm/atomic_64.h
+++ b/arch/sparc/include/asm/atomic_64.h
@@ -28,16 +28,24 @@ void atomic64_##op(long, atomic64_t *);
int atomic_##op##_return(int, atomic_t *); \
long atomic64_##op##_return(long, atomic64_t *);
-#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op)
+#define ATOMIC_FETCH_OP(op) \
+int atomic_fetch_##op(int, atomic_t *); \
+long atomic64_fetch_##op(long, atomic64_t *);
+
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op) ATOMIC_FETCH_OP(op)
ATOMIC_OPS(add)
ATOMIC_OPS(sub)
-ATOMIC_OP(and)
-ATOMIC_OP(or)
-ATOMIC_OP(xor)
+#undef ATOMIC_OPS
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_FETCH_OP(op)
+
+ATOMIC_OPS(and)
+ATOMIC_OPS(or)
+ATOMIC_OPS(xor)
#undef ATOMIC_OPS
+#undef ATOMIC_FETCH_OP
#undef ATOMIC_OP_RETURN
#undef ATOMIC_OP
diff --git a/arch/sparc/include/asm/hugetlb.h b/arch/sparc/include/asm/hugetlb.h
index 139e711ff80c..dcbf985ab243 100644
--- a/arch/sparc/include/asm/hugetlb.h
+++ b/arch/sparc/include/asm/hugetlb.h
@@ -31,14 +31,6 @@ static inline int prepare_hugepage_range(struct file *file,
return 0;
}
-static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb,
- unsigned long addr, unsigned long end,
- unsigned long floor,
- unsigned long ceiling)
-{
- free_pgd_range(tlb, addr, end, floor, ceiling);
-}
-
static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep)
{
@@ -82,4 +74,8 @@ static inline void arch_clear_hugepage_flags(struct page *page)
{
}
+void hugetlb_free_pgd_range(struct mmu_gather *tlb, unsigned long addr,
+ unsigned long end, unsigned long floor,
+ unsigned long ceiling);
+
#endif /* _ASM_SPARC64_HUGETLB_H */
diff --git a/arch/sparc/include/asm/mmu_64.h b/arch/sparc/include/asm/mmu_64.h
index 70067ce184b1..f7de0dbc38af 100644
--- a/arch/sparc/include/asm/mmu_64.h
+++ b/arch/sparc/include/asm/mmu_64.h
@@ -92,7 +92,8 @@ struct tsb_config {
typedef struct {
spinlock_t lock;
unsigned long sparc64_ctx_val;
- unsigned long huge_pte_count;
+ unsigned long hugetlb_pte_count;
+ unsigned long thp_pte_count;
struct tsb_config tsb_block[MM_NUM_TSBS];
struct hv_tsb_descr tsb_descr[MM_NUM_TSBS];
} mm_context_t;
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index e7d82803a48f..1fb317fbc0b3 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -395,7 +395,7 @@ static inline unsigned long __pte_huge_mask(void)
static inline pte_t pte_mkhuge(pte_t pte)
{
- return __pte(pte_val(pte) | __pte_huge_mask());
+ return __pte(pte_val(pte) | _PAGE_PMD_HUGE | __pte_huge_mask());
}
static inline bool is_hugetlb_pte(pte_t pte)
@@ -403,6 +403,11 @@ static inline bool is_hugetlb_pte(pte_t pte)
return !!(pte_val(pte) & __pte_huge_mask());
}
+static inline bool is_hugetlb_pmd(pmd_t pmd)
+{
+ return !!(pmd_val(pmd) & _PAGE_PMD_HUGE);
+}
+
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
static inline pmd_t pmd_mkhuge(pmd_t pmd)
{
diff --git a/arch/sparc/include/asm/spinlock_32.h b/arch/sparc/include/asm/spinlock_32.h
index bcc98fc35281..d9c5876c6121 100644
--- a/arch/sparc/include/asm/spinlock_32.h
+++ b/arch/sparc/include/asm/spinlock_32.h
@@ -9,12 +9,15 @@
#ifndef __ASSEMBLY__
#include <asm/psr.h>
+#include <asm/barrier.h>
#include <asm/processor.h> /* for cpu_relax */
#define arch_spin_is_locked(lock) (*((volatile unsigned char *)(lock)) != 0)
-#define arch_spin_unlock_wait(lock) \
- do { while (arch_spin_is_locked(lock)) cpu_relax(); } while (0)
+static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
+{
+ smp_cond_load_acquire(&lock->lock, !VAL);
+}
static inline void arch_spin_lock(arch_spinlock_t *lock)
{
diff --git a/arch/sparc/include/asm/spinlock_64.h b/arch/sparc/include/asm/spinlock_64.h
index 968917694978..87990b7c6b0d 100644
--- a/arch/sparc/include/asm/spinlock_64.h
+++ b/arch/sparc/include/asm/spinlock_64.h
@@ -8,6 +8,9 @@
#ifndef __ASSEMBLY__
+#include <asm/processor.h>
+#include <asm/barrier.h>
+
/* To get debugging spinlocks which detect and catch
* deadlock situations, set CONFIG_DEBUG_SPINLOCK
* and rebuild your kernel.
@@ -23,9 +26,10 @@
#define arch_spin_is_locked(lp) ((lp)->lock != 0)
-#define arch_spin_unlock_wait(lp) \
- do { rmb(); \
- } while((lp)->lock)
+static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
+{
+ smp_cond_load_acquire(&lock->lock, !VAL);
+}
static inline void arch_spin_lock(arch_spinlock_t *lock)
{
diff --git a/arch/sparc/include/asm/tsb.h b/arch/sparc/include/asm/tsb.h
index c6a155c3904e..32258e08da03 100644
--- a/arch/sparc/include/asm/tsb.h
+++ b/arch/sparc/include/asm/tsb.h
@@ -203,7 +203,7 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end;
* We have to propagate the 4MB bit of the virtual address
* because we are fabricating 8MB pages using 4MB hw pages.
*/
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
#define USER_PGTABLE_CHECK_PMD_HUGE(VADDR, REG1, REG2, FAIL_LABEL, PTE_LABEL) \
brz,pn REG1, FAIL_LABEL; \
sethi %uhi(_PAGE_PMD_HUGE), REG2; \
diff --git a/arch/sparc/kernel/dtlb_prot.S b/arch/sparc/kernel/dtlb_prot.S
index d668ca149e64..4087a62f96b0 100644
--- a/arch/sparc/kernel/dtlb_prot.S
+++ b/arch/sparc/kernel/dtlb_prot.S
@@ -25,13 +25,13 @@
/* PROT ** ICACHE line 2: More real fault processing */
ldxa [%g4] ASI_DMMU, %g5 ! Put tagaccess in %g5
+ srlx %g5, PAGE_SHIFT, %g5
+ sllx %g5, PAGE_SHIFT, %g5 ! Clear context ID bits
bgu,pn %xcc, winfix_trampoline ! Yes, perform winfixup
mov FAULT_CODE_DTLB | FAULT_CODE_WRITE, %g4
ba,pt %xcc, sparc64_realfault_common ! Nope, normal fault
nop
nop
- nop
- nop
/* PROT ** ICACHE line 3: Unused... */
nop
diff --git a/arch/sparc/kernel/irq_32.c b/arch/sparc/kernel/irq_32.c
index a979e99f8751..cac4a5554c0e 100644
--- a/arch/sparc/kernel/irq_32.c
+++ b/arch/sparc/kernel/irq_32.c
@@ -165,7 +165,7 @@ void irq_link(unsigned int irq)
p = &irq_table[irq];
pil = p->pil;
- BUG_ON(pil > SUN4D_MAX_IRQ);
+ BUG_ON(pil >= SUN4D_MAX_IRQ);
p->next = irq_map[pil];
irq_map[pil] = p;
@@ -182,7 +182,7 @@ void irq_unlink(unsigned int irq)
spin_lock_irqsave(&irq_map_lock, flags);
p = &irq_table[irq];
- BUG_ON(p->pil > SUN4D_MAX_IRQ);
+ BUG_ON(p->pil >= SUN4D_MAX_IRQ);
pnext = &irq_map[p->pil];
while (*pnext != p)
pnext = &(*pnext)->next;
diff --git a/arch/sparc/kernel/ktlb.S b/arch/sparc/kernel/ktlb.S
index ef0d8e9e1210..f22bec0db645 100644
--- a/arch/sparc/kernel/ktlb.S
+++ b/arch/sparc/kernel/ktlb.S
@@ -20,6 +20,10 @@ kvmap_itlb:
mov TLB_TAG_ACCESS, %g4
ldxa [%g4] ASI_IMMU, %g4
+ /* The kernel executes in context zero, therefore we do not
+ * need to clear the context ID bits out of %g4 here.
+ */
+
/* sun4v_itlb_miss branches here with the missing virtual
* address already loaded into %g4
*/
@@ -128,6 +132,10 @@ kvmap_dtlb:
mov TLB_TAG_ACCESS, %g4
ldxa [%g4] ASI_DMMU, %g4
+ /* The kernel executes in context zero, therefore we do not
+ * need to clear the context ID bits out of %g4 here.
+ */
+
/* sun4v_dtlb_miss branches here with the missing virtual
* address already loaded into %g4
*/
@@ -251,6 +259,10 @@ kvmap_dtlb_longpath:
nop
.previous
+ /* The kernel executes in context zero, therefore we do not
+ * need to clear the context ID bits out of %g5 here.
+ */
+
be,pt %xcc, sparc64_realfault_common
mov FAULT_CODE_DTLB, %g4
ba,pt %xcc, winfix_trampoline
diff --git a/arch/sparc/kernel/tsb.S b/arch/sparc/kernel/tsb.S
index be98685c14c6..d568c8207af7 100644
--- a/arch/sparc/kernel/tsb.S
+++ b/arch/sparc/kernel/tsb.S
@@ -29,13 +29,17 @@
*/
tsb_miss_dtlb:
mov TLB_TAG_ACCESS, %g4
+ ldxa [%g4] ASI_DMMU, %g4
+ srlx %g4, PAGE_SHIFT, %g4
ba,pt %xcc, tsb_miss_page_table_walk
- ldxa [%g4] ASI_DMMU, %g4
+ sllx %g4, PAGE_SHIFT, %g4
tsb_miss_itlb:
mov TLB_TAG_ACCESS, %g4
+ ldxa [%g4] ASI_IMMU, %g4
+ srlx %g4, PAGE_SHIFT, %g4
ba,pt %xcc, tsb_miss_page_table_walk
- ldxa [%g4] ASI_IMMU, %g4
+ sllx %g4, PAGE_SHIFT, %g4
/* At this point we have:
* %g1 -- PAGE_SIZE TSB entry address
@@ -284,6 +288,10 @@ tsb_do_dtlb_fault:
nop
.previous
+ /* Clear context ID bits. */
+ srlx %g5, PAGE_SHIFT, %g5
+ sllx %g5, PAGE_SHIFT, %g5
+
be,pt %xcc, sparc64_realfault_common
mov FAULT_CODE_DTLB, %g4
ba,pt %xcc, winfix_trampoline
diff --git a/arch/sparc/lib/atomic32.c b/arch/sparc/lib/atomic32.c
index b9d63c0a7aab..2c373329d5cb 100644
--- a/arch/sparc/lib/atomic32.c
+++ b/arch/sparc/lib/atomic32.c
@@ -27,39 +27,44 @@ static DEFINE_SPINLOCK(dummy);
#endif /* SMP */
-#define ATOMIC_OP_RETURN(op, c_op) \
-int atomic_##op##_return(int i, atomic_t *v) \
+#define ATOMIC_FETCH_OP(op, c_op) \
+int atomic_fetch_##op(int i, atomic_t *v) \
{ \
int ret; \
unsigned long flags; \
spin_lock_irqsave(ATOMIC_HASH(v), flags); \
\
- ret = (v->counter c_op i); \
+ ret = v->counter; \
+ v->counter c_op i; \
\
spin_unlock_irqrestore(ATOMIC_HASH(v), flags); \
return ret; \
} \
-EXPORT_SYMBOL(atomic_##op##_return);
+EXPORT_SYMBOL(atomic_fetch_##op);
-#define ATOMIC_OP(op, c_op) \
-void atomic_##op(int i, atomic_t *v) \
+#define ATOMIC_OP_RETURN(op, c_op) \
+int atomic_##op##_return(int i, atomic_t *v) \
{ \
+ int ret; \
unsigned long flags; \
spin_lock_irqsave(ATOMIC_HASH(v), flags); \
\
- v->counter c_op i; \
+ ret = (v->counter c_op i); \
\
spin_unlock_irqrestore(ATOMIC_HASH(v), flags); \
+ return ret; \
} \
-EXPORT_SYMBOL(atomic_##op);
+EXPORT_SYMBOL(atomic_##op##_return);
ATOMIC_OP_RETURN(add, +=)
-ATOMIC_OP(and, &=)
-ATOMIC_OP(or, |=)
-ATOMIC_OP(xor, ^=)
+ATOMIC_FETCH_OP(add, +=)
+ATOMIC_FETCH_OP(and, &=)
+ATOMIC_FETCH_OP(or, |=)
+ATOMIC_FETCH_OP(xor, ^=)
+
+#undef ATOMIC_FETCH_OP
#undef ATOMIC_OP_RETURN
-#undef ATOMIC_OP
int atomic_xchg(atomic_t *v, int new)
{
diff --git a/arch/sparc/lib/atomic_64.S b/arch/sparc/lib/atomic_64.S
index d6b0363f345b..a5c5a0279ccc 100644
--- a/arch/sparc/lib/atomic_64.S
+++ b/arch/sparc/lib/atomic_64.S
@@ -9,10 +9,11 @@
.text
- /* Two versions of the atomic routines, one that
+ /* Three versions of the atomic routines, one that
* does not return a value and does not perform
- * memory barriers, and a second which returns
- * a value and does the barriers.
+ * memory barriers, and a two which return
+ * a value, the new and old value resp. and does the
+ * barriers.
*/
#define ATOMIC_OP(op) \
@@ -43,15 +44,34 @@ ENTRY(atomic_##op##_return) /* %o0 = increment, %o1 = atomic_ptr */ \
2: BACKOFF_SPIN(%o2, %o3, 1b); \
ENDPROC(atomic_##op##_return);
-#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op)
+#define ATOMIC_FETCH_OP(op) \
+ENTRY(atomic_fetch_##op) /* %o0 = increment, %o1 = atomic_ptr */ \
+ BACKOFF_SETUP(%o2); \
+1: lduw [%o1], %g1; \
+ op %g1, %o0, %g7; \
+ cas [%o1], %g1, %g7; \
+ cmp %g1, %g7; \
+ bne,pn %icc, BACKOFF_LABEL(2f, 1b); \
+ nop; \
+ retl; \
+ sra %g1, 0, %o0; \
+2: BACKOFF_SPIN(%o2, %o3, 1b); \
+ENDPROC(atomic_fetch_##op);
+
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op) ATOMIC_FETCH_OP(op)
ATOMIC_OPS(add)
ATOMIC_OPS(sub)
-ATOMIC_OP(and)
-ATOMIC_OP(or)
-ATOMIC_OP(xor)
#undef ATOMIC_OPS
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_FETCH_OP(op)
+
+ATOMIC_OPS(and)
+ATOMIC_OPS(or)
+ATOMIC_OPS(xor)
+
+#undef ATOMIC_OPS
+#undef ATOMIC_FETCH_OP
#undef ATOMIC_OP_RETURN
#undef ATOMIC_OP
@@ -83,15 +103,34 @@ ENTRY(atomic64_##op##_return) /* %o0 = increment, %o1 = atomic_ptr */ \
2: BACKOFF_SPIN(%o2, %o3, 1b); \
ENDPROC(atomic64_##op##_return);
-#define ATOMIC64_OPS(op) ATOMIC64_OP(op) ATOMIC64_OP_RETURN(op)
+#define ATOMIC64_FETCH_OP(op) \
+ENTRY(atomic64_fetch_##op) /* %o0 = increment, %o1 = atomic_ptr */ \
+ BACKOFF_SETUP(%o2); \
+1: ldx [%o1], %g1; \
+ op %g1, %o0, %g7; \
+ casx [%o1], %g1, %g7; \
+ cmp %g1, %g7; \
+ bne,pn %xcc, BACKOFF_LABEL(2f, 1b); \
+ nop; \
+ retl; \
+ mov %g1, %o0; \
+2: BACKOFF_SPIN(%o2, %o3, 1b); \
+ENDPROC(atomic64_fetch_##op);
+
+#define ATOMIC64_OPS(op) ATOMIC64_OP(op) ATOMIC64_OP_RETURN(op) ATOMIC64_FETCH_OP(op)
ATOMIC64_OPS(add)
ATOMIC64_OPS(sub)
-ATOMIC64_OP(and)
-ATOMIC64_OP(or)
-ATOMIC64_OP(xor)
#undef ATOMIC64_OPS
+#define ATOMIC64_OPS(op) ATOMIC64_OP(op) ATOMIC64_FETCH_OP(op)
+
+ATOMIC64_OPS(and)
+ATOMIC64_OPS(or)
+ATOMIC64_OPS(xor)
+
+#undef ATOMIC64_OPS
+#undef ATOMIC64_FETCH_OP
#undef ATOMIC64_OP_RETURN
#undef ATOMIC64_OP
diff --git a/arch/sparc/lib/ksyms.c b/arch/sparc/lib/ksyms.c
index 8eb454cfe05c..de5e97817bdb 100644
--- a/arch/sparc/lib/ksyms.c
+++ b/arch/sparc/lib/ksyms.c
@@ -107,15 +107,24 @@ EXPORT_SYMBOL(atomic64_##op);
EXPORT_SYMBOL(atomic_##op##_return); \
EXPORT_SYMBOL(atomic64_##op##_return);
-#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op)
+#define ATOMIC_FETCH_OP(op) \
+EXPORT_SYMBOL(atomic_fetch_##op); \
+EXPORT_SYMBOL(atomic64_fetch_##op);
+
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op) ATOMIC_FETCH_OP(op)
ATOMIC_OPS(add)
ATOMIC_OPS(sub)
-ATOMIC_OP(and)
-ATOMIC_OP(or)
-ATOMIC_OP(xor)
#undef ATOMIC_OPS
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_FETCH_OP(op)
+
+ATOMIC_OPS(and)
+ATOMIC_OPS(or)
+ATOMIC_OPS(xor)
+
+#undef ATOMIC_OPS
+#undef ATOMIC_FETCH_OP
#undef ATOMIC_OP_RETURN
#undef ATOMIC_OP
diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c
index b6c559cbd64d..4714061d6cd3 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 cb841a33da59..e16fdd28a931 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 +476,14 @@ 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;
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 ba52e6466a82..988acc8b1b80 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 aec508e37490..65457c9f1365 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));
diff --git a/arch/sparc/mm/tlb.c b/arch/sparc/mm/tlb.c
index f81cd9736700..3659d37b4d81 100644
--- a/arch/sparc/mm/tlb.c
+++ b/arch/sparc/mm/tlb.c
@@ -175,9 +175,9 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr,
if ((pmd_val(pmd) ^ pmd_val(orig)) & _PAGE_PMD_HUGE) {
if (pmd_val(pmd) & _PAGE_PMD_HUGE)
- mm->context.huge_pte_count++;
+ mm->context.thp_pte_count++;
else
- mm->context.huge_pte_count--;
+ 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
diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c
index a0604a493a36..6725ed45580e 100644
--- a/arch/sparc/mm/tsb.c
+++ b/arch/sparc/mm/tsb.c
@@ -470,7 +470,7 @@ retry_tsb_alloc:
int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
{
#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
- unsigned long huge_pte_count;
+ unsigned long total_huge_pte_count;
#endif
unsigned int i;
@@ -479,12 +479,14 @@ 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;
+ total_huge_pte_count = mm->context.hugetlb_pte_count +
+ mm->context.thp_pte_count;
+ mm->context.hugetlb_pte_count = 0;
+ mm->context.thp_pte_count = 0;
#endif
/* copy_mm() copies over the parent's mm_struct before calling
@@ -500,8 +502,8 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
tsb_grow(mm, MM_TSB_BASE, get_mm_rss(mm));
#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(total_huge_pte_count))
+ tsb_grow(mm, MM_TSB_HUGE, total_huge_pte_count);
#endif
if (unlikely(!mm->context.tsb_block[MM_TSB_BASE].tsb))